Namespace(aa='rand-m9-mstd0.5-inc1', auto_resume=True, batch_size=512, cfg_path='iFormer_l_distill.yaml', clip_grad=None, color_jitter=0.4, crop_pct=None, cutmix=1.0, cutmix_minmax=None, data_path='imagenet', data_set='IMNET', device='cuda', disable_eval=False, dist_backend='nccl', dist_eval=True, dist_on_itp=False, dist_url='env://', distillation_alpha=0.5, distillation_tau=1.0, distillation_type='hard', distributed=True, drop_path=0, enable_wandb=False, epochs=300, eval=False, eval_data_path=None, finetune='', gpu=0, head_init_scale=1.0, imagenet_default_mean_and_std=True, input_size=224, layer_decay=1.0, layer_scale_init_value=0, local_rank=-1, log_dir=None, lr=0.004, min_lr=1e-06, mixup=0.8, mixup_mode='batch', mixup_prob=1.0, mixup_switch_prob=0.5, model='iFormer_l', model_ema=False, model_ema_decay=0.9999, model_ema_eval=False, model_ema_force_cpu=False, model_key='model|module', model_prefix='', momentum=0.9, nb_classes=1000, num_workers=16, opt='adamw', opt_betas=None, opt_eps=1e-08, output_dir='', pin_mem=True, project='iFormer', rank=0, recount=1, remode='pixel', reprob=0.25, resplit=False, resume='', save_ckpt=True, save_ckpt_freq=1, save_ckpt_num=3, seed=0, smoothing=0.1, start_epoch=0, teacher_model='regnety_160', teacher_path='regnety_160-a5fe301d.pth', train_interpolation='bicubic', update_freq=1, use_amp=False, wandb_ckpt=False, warmup_epochs=20, warmup_steps=-1, weight_decay=0.05, weight_decay_end=None, world_size=8)
Transform = 
RandomResizedCropAndInterpolation(size=(224, 224), scale=(0.08, 1.0), ratio=(0.75, 1.3333), interpolation=PIL.Image.BICUBIC)
RandomHorizontalFlip(p=0.5)
<timm.data.auto_augment.RandAugment object at 0x7fba58904bb0>
ToTensor()
Normalize(mean=tensor([0.4850, 0.4560, 0.4060]), std=tensor([0.2290, 0.2240, 0.2250]))
<timm.data.random_erasing.RandomErasing object at 0x7fba588fef10>
---------------------------
reading from datapath imagenet
Number of the class = 1000
Transform = 
Resize(size=256, interpolation=bicubic, max_size=None, antialias=warn)
CenterCrop(size=(224, 224))
ToTensor()
Normalize(mean=(0.485, 0.456, 0.406), std=(0.229, 0.224, 0.225))
---------------------------
reading from datapath imagenet
Number of the class = 1000
Sampler_train = <torch.utils.data.distributed.DistributedSampler object at 0x7fba588feac0>
Mixup is activated!
Model = iFormer(
  (downsample_layers): ModuleList(
    (0): Sequential(
      (0): Conv2d_BN(
        (c): Conv2d(3, 24, kernel_size=(5, 5), stride=(2, 2), padding=(2, 2), bias=False)
        (bn): BatchNorm2d(24, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      )
      (1): GELU(approximate='none')
      (2): EdgeResidual(
        (conv_exp_bn1): Conv2d_BN(
          (c): Conv2d(24, 96, kernel_size=(5, 5), stride=(2, 2), padding=(2, 2), bias=False)
          (bn): BatchNorm2d(96, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        )
        (act): GELU(approximate='none')
        (conv_pwl_bn2): Conv2d_BN(
          (c): Conv2d(96, 48, kernel_size=(1, 1), stride=(1, 1), bias=False)
          (bn): BatchNorm2d(48, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        )
      )
    )
    (1): Sequential(
      (0): Conv2d_BN(
        (c): Conv2d(48, 96, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False)
        (bn): BatchNorm2d(96, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      )
    )
    (2): Sequential(
      (0): Conv2d_BN(
        (c): Conv2d(96, 256, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False)
        (bn): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      )
    )
    (3): Sequential(
      (0): Conv2d_BN(
        (c): Conv2d(256, 384, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False)
        (bn): BatchNorm2d(384, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      )
    )
  )
  (stages): ModuleList(
    (0): Sequential(
      (0): BasicBlock(
        (block): ConvBlock(
          (token_channel_mixer): Residual(
            (m): Sequential(
              (0): Conv2d_BN(
                (c): Conv2d(48, 48, kernel_size=(7, 7), stride=(1, 1), padding=(3, 3), groups=48, bias=False)
                (bn): BatchNorm2d(48, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
              )
              (1): Conv2d_BN(
                (c): Conv2d(48, 192, kernel_size=(1, 1), stride=(1, 1), bias=False)
                (bn): BatchNorm2d(192, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
              )
              (2): GELU(approximate='none')
              (3): Conv2d_BN(
                (c): Conv2d(192, 48, kernel_size=(1, 1), stride=(1, 1), bias=False)
                (bn): BatchNorm2d(48, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
              )
            )
          )
        )
      )
      (1): BasicBlock(
        (block): ConvBlock(
          (token_channel_mixer): Residual(
            (m): Sequential(
              (0): Conv2d_BN(
                (c): Conv2d(48, 48, kernel_size=(7, 7), stride=(1, 1), padding=(3, 3), groups=48, bias=False)
                (bn): BatchNorm2d(48, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
              )
              (1): Conv2d_BN(
                (c): Conv2d(48, 192, kernel_size=(1, 1), stride=(1, 1), bias=False)
                (bn): BatchNorm2d(192, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
              )
              (2): GELU(approximate='none')
              (3): Conv2d_BN(
                (c): Conv2d(192, 48, kernel_size=(1, 1), stride=(1, 1), bias=False)
                (bn): BatchNorm2d(48, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
              )
            )
          )
        )
      )
    )
    (1): Sequential(
      (0): BasicBlock(
        (block): ConvBlock(
          (token_channel_mixer): Residual(
            (m): Sequential(
              (0): Conv2d_BN(
                (c): Conv2d(96, 96, kernel_size=(7, 7), stride=(1, 1), padding=(3, 3), groups=96, bias=False)
                (bn): BatchNorm2d(96, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
              )
              (1): Conv2d_BN(
                (c): Conv2d(96, 384, kernel_size=(1, 1), stride=(1, 1), bias=False)
                (bn): BatchNorm2d(384, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
              )
              (2): GELU(approximate='none')
              (3): Conv2d_BN(
                (c): Conv2d(384, 96, kernel_size=(1, 1), stride=(1, 1), bias=False)
                (bn): BatchNorm2d(96, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
              )
            )
          )
        )
      )
      (1): BasicBlock(
        (block): ConvBlock(
          (token_channel_mixer): Residual(
            (m): Sequential(
              (0): Conv2d_BN(
                (c): Conv2d(96, 96, kernel_size=(7, 7), stride=(1, 1), padding=(3, 3), groups=96, bias=False)
                (bn): BatchNorm2d(96, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
              )
              (1): Conv2d_BN(
                (c): Conv2d(96, 384, kernel_size=(1, 1), stride=(1, 1), bias=False)
                (bn): BatchNorm2d(384, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
              )
              (2): GELU(approximate='none')
              (3): Conv2d_BN(
                (c): Conv2d(384, 96, kernel_size=(1, 1), stride=(1, 1), bias=False)
                (bn): BatchNorm2d(96, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
              )
            )
          )
        )
      )
    )
    (2): Sequential(
      (0): BasicBlock(
        (block): ConvBlock(
          (token_channel_mixer): Residual(
            (m): Sequential(
              (0): Conv2d_BN(
                (c): Conv2d(256, 256, kernel_size=(7, 7), stride=(1, 1), padding=(3, 3), groups=256, bias=False)
                (bn): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
              )
              (1): Conv2d_BN(
                (c): Conv2d(256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)
                (bn): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
              )
              (2): GELU(approximate='none')
              (3): Conv2d_BN(
                (c): Conv2d(1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
                (bn): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
              )
            )
          )
        )
      )
      (1): BasicBlock(
        (block): ConvBlock(
          (token_channel_mixer): Residual(
            (m): Sequential(
              (0): Conv2d_BN(
                (c): Conv2d(256, 256, kernel_size=(7, 7), stride=(1, 1), padding=(3, 3), groups=256, bias=False)
                (bn): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
              )
              (1): Conv2d_BN(
                (c): Conv2d(256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)
                (bn): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
              )
              (2): GELU(approximate='none')
              (3): Conv2d_BN(
                (c): Conv2d(1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
                (bn): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
              )
            )
          )
        )
      )
      (2): BasicBlock(
        (block): ConvBlock(
          (token_channel_mixer): Residual(
            (m): Sequential(
              (0): Conv2d_BN(
                (c): Conv2d(256, 256, kernel_size=(7, 7), stride=(1, 1), padding=(3, 3), groups=256, bias=False)
                (bn): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
              )
              (1): Conv2d_BN(
                (c): Conv2d(256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)
                (bn): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
              )
              (2): GELU(approximate='none')
              (3): Conv2d_BN(
                (c): Conv2d(1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
                (bn): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
              )
            )
          )
        )
      )
      (3): BasicBlock(
        (block): ConvBlock(
          (token_channel_mixer): Residual(
            (m): Sequential(
              (0): Conv2d_BN(
                (c): Conv2d(256, 256, kernel_size=(7, 7), stride=(1, 1), padding=(3, 3), groups=256, bias=False)
                (bn): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
              )
              (1): Conv2d_BN(
                (c): Conv2d(256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)
                (bn): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
              )
              (2): GELU(approximate='none')
              (3): Conv2d_BN(
                (c): Conv2d(1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
                (bn): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
              )
            )
          )
        )
      )
      (4): BasicBlock(
        (block): ConvBlock(
          (token_channel_mixer): Residual(
            (m): Sequential(
              (0): Conv2d_BN(
                (c): Conv2d(256, 256, kernel_size=(7, 7), stride=(1, 1), padding=(3, 3), groups=256, bias=False)
                (bn): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
              )
              (1): Conv2d_BN(
                (c): Conv2d(256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)
                (bn): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
              )
              (2): GELU(approximate='none')
              (3): Conv2d_BN(
                (c): Conv2d(1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
                (bn): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
              )
            )
          )
        )
      )
      (5): BasicBlock(
        (block): ConvBlock(
          (token_channel_mixer): Residual(
            (m): Sequential(
              (0): Conv2d_BN(
                (c): Conv2d(256, 256, kernel_size=(7, 7), stride=(1, 1), padding=(3, 3), groups=256, bias=False)
                (bn): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
              )
              (1): Conv2d_BN(
                (c): Conv2d(256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)
                (bn): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
              )
              (2): GELU(approximate='none')
              (3): Conv2d_BN(
                (c): Conv2d(1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
                (bn): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
              )
            )
          )
        )
      )
      (6): BasicBlock(
        (block): ConvBlock(
          (token_channel_mixer): Residual(
            (m): Sequential(
              (0): Conv2d_BN(
                (c): Conv2d(256, 256, kernel_size=(7, 7), stride=(1, 1), padding=(3, 3), groups=256, bias=False)
                (bn): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
              )
              (1): Conv2d_BN(
                (c): Conv2d(256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)
                (bn): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
              )
              (2): GELU(approximate='none')
              (3): Conv2d_BN(
                (c): Conv2d(1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
                (bn): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
              )
            )
          )
        )
      )
      (7): BasicBlock(
        (block): ConvBlock(
          (token_channel_mixer): Residual(
            (m): Sequential(
              (0): Conv2d_BN(
                (c): Conv2d(256, 256, kernel_size=(7, 7), stride=(1, 1), padding=(3, 3), groups=256, bias=False)
                (bn): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
              )
              (1): Conv2d_BN(
                (c): Conv2d(256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)
                (bn): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
              )
              (2): GELU(approximate='none')
              (3): Conv2d_BN(
                (c): Conv2d(1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
                (bn): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
              )
            )
          )
        )
      )
      (8): BasicBlock(
        (block): RepCPE(
          (cpe): Residual(
            (m): Conv2d_BN(
              (c): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=256, bias=False)
              (bn): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
            )
          )
        )
      )
      (9): BasicBlock(
        (block): SHMABlock(
          (token_channel_mixer): Residual(
            (m): GAU2dv2(
              (q): Conv2d_BN(
                (c): Conv2d(256, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
                (bn): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
              )
              (k): Conv2d_BN(
                (c): Conv2d(256, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
                (bn): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
              )
              (v_gate): Conv2d_BN(
                (c): Conv2d(256, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)
                (bn): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
              )
              (gate_act): Sigmoid()
              (attn_drop): Dropout(p=0.0, inplace=False)
              (proj): Conv2d_BN(
                (c): Conv2d(256, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
                (bn): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
              )
            )
          )
        )
      )
      (10): BasicBlock(
        (block): FFN2d(
          (channel_mixer): Residual(
            (m): Sequential(
              (0): Conv2d_BN(
                (c): Conv2d(256, 768, kernel_size=(1, 1), stride=(1, 1), bias=False)
                (bn): BatchNorm2d(768, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
              )
              (1): GELU(approximate='none')
              (2): Conv2d_BN(
                (c): Conv2d(768, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
                (bn): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
              )
            )
          )
        )
      )
      (11): BasicBlock(
        (block): RepCPE(
          (cpe): Residual(
            (m): Conv2d_BN(
              (c): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=256, bias=False)
              (bn): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
            )
          )
        )
      )
      (12): BasicBlock(
        (block): SHMABlock(
          (token_channel_mixer): Residual(
            (m): GAU2dv2(
              (q): Conv2d_BN(
                (c): Conv2d(256, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
                (bn): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
              )
              (k): Conv2d_BN(
                (c): Conv2d(256, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
                (bn): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
              )
              (v_gate): Conv2d_BN(
                (c): Conv2d(256, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)
                (bn): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
              )
              (gate_act): Sigmoid()
              (attn_drop): Dropout(p=0.0, inplace=False)
              (proj): Conv2d_BN(
                (c): Conv2d(256, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
                (bn): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
              )
            )
          )
        )
      )
      (13): BasicBlock(
        (block): FFN2d(
          (channel_mixer): Residual(
            (m): Sequential(
              (0): Conv2d_BN(
                (c): Conv2d(256, 768, kernel_size=(1, 1), stride=(1, 1), bias=False)
                (bn): BatchNorm2d(768, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
              )
              (1): GELU(approximate='none')
              (2): Conv2d_BN(
                (c): Conv2d(768, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
                (bn): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
              )
            )
          )
        )
      )
      (14): BasicBlock(
        (block): RepCPE(
          (cpe): Residual(
            (m): Conv2d_BN(
              (c): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=256, bias=False)
              (bn): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
            )
          )
        )
      )
      (15): BasicBlock(
        (block): SHMABlock(
          (token_channel_mixer): Residual(
            (m): GAU2dv2(
              (q): Conv2d_BN(
                (c): Conv2d(256, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
                (bn): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
              )
              (k): Conv2d_BN(
                (c): Conv2d(256, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
                (bn): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
              )
              (v_gate): Conv2d_BN(
                (c): Conv2d(256, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)
                (bn): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
              )
              (gate_act): Sigmoid()
              (attn_drop): Dropout(p=0.0, inplace=False)
              (proj): Conv2d_BN(
                (c): Conv2d(256, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
                (bn): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
              )
            )
          )
        )
      )
      (16): BasicBlock(
        (block): FFN2d(
          (channel_mixer): Residual(
            (m): Sequential(
              (0): Conv2d_BN(
                (c): Conv2d(256, 768, kernel_size=(1, 1), stride=(1, 1), bias=False)
                (bn): BatchNorm2d(768, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
              )
              (1): GELU(approximate='none')
              (2): Conv2d_BN(
                (c): Conv2d(768, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
                (bn): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
              )
            )
          )
        )
      )
      (17): BasicBlock(
        (block): RepCPE(
          (cpe): Residual(
            (m): Conv2d_BN(
              (c): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=256, bias=False)
              (bn): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
            )
          )
        )
      )
      (18): BasicBlock(
        (block): SHMABlock(
          (token_channel_mixer): Residual(
            (m): GAU2dv2(
              (q): Conv2d_BN(
                (c): Conv2d(256, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
                (bn): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
              )
              (k): Conv2d_BN(
                (c): Conv2d(256, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
                (bn): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
              )
              (v_gate): Conv2d_BN(
                (c): Conv2d(256, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)
                (bn): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
              )
              (gate_act): Sigmoid()
              (attn_drop): Dropout(p=0.0, inplace=False)
              (proj): Conv2d_BN(
                (c): Conv2d(256, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
                (bn): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
              )
            )
          )
        )
      )
      (19): BasicBlock(
        (block): FFN2d(
          (channel_mixer): Residual(
            (m): Sequential(
              (0): Conv2d_BN(
                (c): Conv2d(256, 768, kernel_size=(1, 1), stride=(1, 1), bias=False)
                (bn): BatchNorm2d(768, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
              )
              (1): GELU(approximate='none')
              (2): Conv2d_BN(
                (c): Conv2d(768, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
                (bn): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
              )
            )
          )
        )
      )
      (20): BasicBlock(
        (block): RepCPE(
          (cpe): Residual(
            (m): Conv2d_BN(
              (c): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=256, bias=False)
              (bn): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
            )
          )
        )
      )
      (21): BasicBlock(
        (block): SHMABlock(
          (token_channel_mixer): Residual(
            (m): GAU2dv2(
              (q): Conv2d_BN(
                (c): Conv2d(256, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
                (bn): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
              )
              (k): Conv2d_BN(
                (c): Conv2d(256, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
                (bn): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
              )
              (v_gate): Conv2d_BN(
                (c): Conv2d(256, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)
                (bn): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
              )
              (gate_act): Sigmoid()
              (attn_drop): Dropout(p=0.0, inplace=False)
              (proj): Conv2d_BN(
                (c): Conv2d(256, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
                (bn): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
              )
            )
          )
        )
      )
      (22): BasicBlock(
        (block): FFN2d(
          (channel_mixer): Residual(
            (m): Sequential(
              (0): Conv2d_BN(
                (c): Conv2d(256, 768, kernel_size=(1, 1), stride=(1, 1), bias=False)
                (bn): BatchNorm2d(768, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
              )
              (1): GELU(approximate='none')
              (2): Conv2d_BN(
                (c): Conv2d(768, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
                (bn): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
              )
            )
          )
        )
      )
      (23): BasicBlock(
        (block): RepCPE(
          (cpe): Residual(
            (m): Conv2d_BN(
              (c): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=256, bias=False)
              (bn): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
            )
          )
        )
      )
      (24): BasicBlock(
        (block): SHMABlock(
          (token_channel_mixer): Residual(
            (m): GAU2dv2(
              (q): Conv2d_BN(
                (c): Conv2d(256, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
                (bn): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
              )
              (k): Conv2d_BN(
                (c): Conv2d(256, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
                (bn): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
              )
              (v_gate): Conv2d_BN(
                (c): Conv2d(256, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)
                (bn): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
              )
              (gate_act): Sigmoid()
              (attn_drop): Dropout(p=0.0, inplace=False)
              (proj): Conv2d_BN(
                (c): Conv2d(256, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
                (bn): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
              )
            )
          )
        )
      )
      (25): BasicBlock(
        (block): FFN2d(
          (channel_mixer): Residual(
            (m): Sequential(
              (0): Conv2d_BN(
                (c): Conv2d(256, 768, kernel_size=(1, 1), stride=(1, 1), bias=False)
                (bn): BatchNorm2d(768, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
              )
              (1): GELU(approximate='none')
              (2): Conv2d_BN(
                (c): Conv2d(768, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
                (bn): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
              )
            )
          )
        )
      )
      (26): BasicBlock(
        (block): RepCPE(
          (cpe): Residual(
            (m): Conv2d_BN(
              (c): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=256, bias=False)
              (bn): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
            )
          )
        )
      )
      (27): BasicBlock(
        (block): SHMABlock(
          (token_channel_mixer): Residual(
            (m): GAU2dv2(
              (q): Conv2d_BN(
                (c): Conv2d(256, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
                (bn): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
              )
              (k): Conv2d_BN(
                (c): Conv2d(256, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
                (bn): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
              )
              (v_gate): Conv2d_BN(
                (c): Conv2d(256, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)
                (bn): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
              )
              (gate_act): Sigmoid()
              (attn_drop): Dropout(p=0.0, inplace=False)
              (proj): Conv2d_BN(
                (c): Conv2d(256, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
                (bn): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
              )
            )
          )
        )
      )
      (28): BasicBlock(
        (block): FFN2d(
          (channel_mixer): Residual(
            (m): Sequential(
              (0): Conv2d_BN(
                (c): Conv2d(256, 768, kernel_size=(1, 1), stride=(1, 1), bias=False)
                (bn): BatchNorm2d(768, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
              )
              (1): GELU(approximate='none')
              (2): Conv2d_BN(
                (c): Conv2d(768, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
                (bn): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
              )
            )
          )
        )
      )
      (29): BasicBlock(
        (block): RepCPE(
          (cpe): Residual(
            (m): Conv2d_BN(
              (c): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=256, bias=False)
              (bn): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
            )
          )
        )
      )
      (30): BasicBlock(
        (block): SHMABlock(
          (token_channel_mixer): Residual(
            (m): GAU2dv2(
              (q): Conv2d_BN(
                (c): Conv2d(256, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
                (bn): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
              )
              (k): Conv2d_BN(
                (c): Conv2d(256, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
                (bn): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
              )
              (v_gate): Conv2d_BN(
                (c): Conv2d(256, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)
                (bn): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
              )
              (gate_act): Sigmoid()
              (attn_drop): Dropout(p=0.0, inplace=False)
              (proj): Conv2d_BN(
                (c): Conv2d(256, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
                (bn): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
              )
            )
          )
        )
      )
      (31): BasicBlock(
        (block): FFN2d(
          (channel_mixer): Residual(
            (m): Sequential(
              (0): Conv2d_BN(
                (c): Conv2d(256, 768, kernel_size=(1, 1), stride=(1, 1), bias=False)
                (bn): BatchNorm2d(768, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
              )
              (1): GELU(approximate='none')
              (2): Conv2d_BN(
                (c): Conv2d(768, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
                (bn): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
              )
            )
          )
        )
      )
      (32): BasicBlock(
        (block): ConvBlock(
          (token_channel_mixer): Residual(
            (m): Sequential(
              (0): Conv2d_BN(
                (c): Conv2d(256, 256, kernel_size=(7, 7), stride=(1, 1), padding=(3, 3), groups=256, bias=False)
                (bn): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
              )
              (1): Conv2d_BN(
                (c): Conv2d(256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)
                (bn): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
              )
              (2): GELU(approximate='none')
              (3): Conv2d_BN(
                (c): Conv2d(1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
                (bn): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
              )
            )
          )
        )
      )
    )
    (3): Sequential(
      (0): BasicBlock(
        (block): RepCPE(
          (cpe): Residual(
            (m): Conv2d_BN(
              (c): Conv2d(384, 384, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=384, bias=False)
              (bn): BatchNorm2d(384, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
            )
          )
        )
      )
      (1): BasicBlock(
        (block): SHMABlock(
          (token_channel_mixer): Residual(
            (m): GAU2dv2(
              (q): Conv2d_BN(
                (c): Conv2d(384, 96, kernel_size=(1, 1), stride=(1, 1), bias=False)
                (bn): BatchNorm2d(96, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
              )
              (k): Conv2d_BN(
                (c): Conv2d(384, 96, kernel_size=(1, 1), stride=(1, 1), bias=False)
                (bn): BatchNorm2d(96, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
              )
              (v_gate): Conv2d_BN(
                (c): Conv2d(384, 768, kernel_size=(1, 1), stride=(1, 1), bias=False)
                (bn): BatchNorm2d(768, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
              )
              (gate_act): Sigmoid()
              (attn_drop): Dropout(p=0.0, inplace=False)
              (proj): Conv2d_BN(
                (c): Conv2d(384, 384, kernel_size=(1, 1), stride=(1, 1), bias=False)
                (bn): BatchNorm2d(384, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
              )
            )
          )
        )
      )
      (2): BasicBlock(
        (block): FFN2d(
          (channel_mixer): Residual(
            (m): Sequential(
              (0): Conv2d_BN(
                (c): Conv2d(384, 1152, kernel_size=(1, 1), stride=(1, 1), bias=False)
                (bn): BatchNorm2d(1152, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
              )
              (1): GELU(approximate='none')
              (2): Conv2d_BN(
                (c): Conv2d(1152, 384, kernel_size=(1, 1), stride=(1, 1), bias=False)
                (bn): BatchNorm2d(384, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
              )
            )
          )
        )
      )
      (3): BasicBlock(
        (block): RepCPE(
          (cpe): Residual(
            (m): Conv2d_BN(
              (c): Conv2d(384, 384, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=384, bias=False)
              (bn): BatchNorm2d(384, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
            )
          )
        )
      )
      (4): BasicBlock(
        (block): SHMABlock(
          (token_channel_mixer): Residual(
            (m): GAU2dv2(
              (q): Conv2d_BN(
                (c): Conv2d(384, 96, kernel_size=(1, 1), stride=(1, 1), bias=False)
                (bn): BatchNorm2d(96, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
              )
              (k): Conv2d_BN(
                (c): Conv2d(384, 96, kernel_size=(1, 1), stride=(1, 1), bias=False)
                (bn): BatchNorm2d(96, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
              )
              (v_gate): Conv2d_BN(
                (c): Conv2d(384, 768, kernel_size=(1, 1), stride=(1, 1), bias=False)
                (bn): BatchNorm2d(768, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
              )
              (gate_act): Sigmoid()
              (attn_drop): Dropout(p=0.0, inplace=False)
              (proj): Conv2d_BN(
                (c): Conv2d(384, 384, kernel_size=(1, 1), stride=(1, 1), bias=False)
                (bn): BatchNorm2d(384, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
              )
            )
          )
        )
      )
      (5): BasicBlock(
        (block): FFN2d(
          (channel_mixer): Residual(
            (m): Sequential(
              (0): Conv2d_BN(
                (c): Conv2d(384, 1152, kernel_size=(1, 1), stride=(1, 1), bias=False)
                (bn): BatchNorm2d(1152, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
              )
              (1): GELU(approximate='none')
              (2): Conv2d_BN(
                (c): Conv2d(1152, 384, kernel_size=(1, 1), stride=(1, 1), bias=False)
                (bn): BatchNorm2d(384, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
              )
            )
          )
        )
      )
    )
  )
  (classifier): Classfier(
    (classifier): BN_Linear(
      (bn): BatchNorm1d(384, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      (l): Linear(in_features=384, out_features=1000, bias=True)
    )
    (classifier_dist): BN_Linear(
      (bn): BatchNorm1d(384, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      (l): Linear(in_features=384, out_features=1000, bias=True)
    )
  )
)
number of params: 15165576
LR = 0.00400000
Batch size = 4096
Update frequent = 1
Number of training examples = 1281167
Number of training training per epoch = 312
Param groups = {
  "decay": {
    "weight_decay": 0.05,
    "params": [
      "downsample_layers.0.0.c.weight",
      "downsample_layers.0.2.conv_exp_bn1.c.weight",
      "downsample_layers.0.2.conv_pwl_bn2.c.weight",
      "downsample_layers.1.0.c.weight",
      "downsample_layers.2.0.c.weight",
      "downsample_layers.3.0.c.weight",
      "stages.0.0.block.token_channel_mixer.m.0.c.weight",
      "stages.0.0.block.token_channel_mixer.m.1.c.weight",
      "stages.0.0.block.token_channel_mixer.m.3.c.weight",
      "stages.0.1.block.token_channel_mixer.m.0.c.weight",
      "stages.0.1.block.token_channel_mixer.m.1.c.weight",
      "stages.0.1.block.token_channel_mixer.m.3.c.weight",
      "stages.1.0.block.token_channel_mixer.m.0.c.weight",
      "stages.1.0.block.token_channel_mixer.m.1.c.weight",
      "stages.1.0.block.token_channel_mixer.m.3.c.weight",
      "stages.1.1.block.token_channel_mixer.m.0.c.weight",
      "stages.1.1.block.token_channel_mixer.m.1.c.weight",
      "stages.1.1.block.token_channel_mixer.m.3.c.weight",
      "stages.2.0.block.token_channel_mixer.m.0.c.weight",
      "stages.2.0.block.token_channel_mixer.m.1.c.weight",
      "stages.2.0.block.token_channel_mixer.m.3.c.weight",
      "stages.2.1.block.token_channel_mixer.m.0.c.weight",
      "stages.2.1.block.token_channel_mixer.m.1.c.weight",
      "stages.2.1.block.token_channel_mixer.m.3.c.weight",
      "stages.2.2.block.token_channel_mixer.m.0.c.weight",
      "stages.2.2.block.token_channel_mixer.m.1.c.weight",
      "stages.2.2.block.token_channel_mixer.m.3.c.weight",
      "stages.2.3.block.token_channel_mixer.m.0.c.weight",
      "stages.2.3.block.token_channel_mixer.m.1.c.weight",
      "stages.2.3.block.token_channel_mixer.m.3.c.weight",
      "stages.2.4.block.token_channel_mixer.m.0.c.weight",
      "stages.2.4.block.token_channel_mixer.m.1.c.weight",
      "stages.2.4.block.token_channel_mixer.m.3.c.weight",
      "stages.2.5.block.token_channel_mixer.m.0.c.weight",
      "stages.2.5.block.token_channel_mixer.m.1.c.weight",
      "stages.2.5.block.token_channel_mixer.m.3.c.weight",
      "stages.2.6.block.token_channel_mixer.m.0.c.weight",
      "stages.2.6.block.token_channel_mixer.m.1.c.weight",
      "stages.2.6.block.token_channel_mixer.m.3.c.weight",
      "stages.2.7.block.token_channel_mixer.m.0.c.weight",
      "stages.2.7.block.token_channel_mixer.m.1.c.weight",
      "stages.2.7.block.token_channel_mixer.m.3.c.weight",
      "stages.2.8.block.cpe.m.c.weight",
      "stages.2.9.block.token_channel_mixer.m.q.c.weight",
      "stages.2.9.block.token_channel_mixer.m.k.c.weight",
      "stages.2.9.block.token_channel_mixer.m.v_gate.c.weight",
      "stages.2.9.block.token_channel_mixer.m.proj.c.weight",
      "stages.2.10.block.channel_mixer.m.0.c.weight",
      "stages.2.10.block.channel_mixer.m.2.c.weight",
      "stages.2.11.block.cpe.m.c.weight",
      "stages.2.12.block.token_channel_mixer.m.q.c.weight",
      "stages.2.12.block.token_channel_mixer.m.k.c.weight",
      "stages.2.12.block.token_channel_mixer.m.v_gate.c.weight",
      "stages.2.12.block.token_channel_mixer.m.proj.c.weight",
      "stages.2.13.block.channel_mixer.m.0.c.weight",
      "stages.2.13.block.channel_mixer.m.2.c.weight",
      "stages.2.14.block.cpe.m.c.weight",
      "stages.2.15.block.token_channel_mixer.m.q.c.weight",
      "stages.2.15.block.token_channel_mixer.m.k.c.weight",
      "stages.2.15.block.token_channel_mixer.m.v_gate.c.weight",
      "stages.2.15.block.token_channel_mixer.m.proj.c.weight",
      "stages.2.16.block.channel_mixer.m.0.c.weight",
      "stages.2.16.block.channel_mixer.m.2.c.weight",
      "stages.2.17.block.cpe.m.c.weight",
      "stages.2.18.block.token_channel_mixer.m.q.c.weight",
      "stages.2.18.block.token_channel_mixer.m.k.c.weight",
      "stages.2.18.block.token_channel_mixer.m.v_gate.c.weight",
      "stages.2.18.block.token_channel_mixer.m.proj.c.weight",
      "stages.2.19.block.channel_mixer.m.0.c.weight",
      "stages.2.19.block.channel_mixer.m.2.c.weight",
      "stages.2.20.block.cpe.m.c.weight",
      "stages.2.21.block.token_channel_mixer.m.q.c.weight",
      "stages.2.21.block.token_channel_mixer.m.k.c.weight",
      "stages.2.21.block.token_channel_mixer.m.v_gate.c.weight",
      "stages.2.21.block.token_channel_mixer.m.proj.c.weight",
      "stages.2.22.block.channel_mixer.m.0.c.weight",
      "stages.2.22.block.channel_mixer.m.2.c.weight",
      "stages.2.23.block.cpe.m.c.weight",
      "stages.2.24.block.token_channel_mixer.m.q.c.weight",
      "stages.2.24.block.token_channel_mixer.m.k.c.weight",
      "stages.2.24.block.token_channel_mixer.m.v_gate.c.weight",
      "stages.2.24.block.token_channel_mixer.m.proj.c.weight",
      "stages.2.25.block.channel_mixer.m.0.c.weight",
      "stages.2.25.block.channel_mixer.m.2.c.weight",
      "stages.2.26.block.cpe.m.c.weight",
      "stages.2.27.block.token_channel_mixer.m.q.c.weight",
      "stages.2.27.block.token_channel_mixer.m.k.c.weight",
      "stages.2.27.block.token_channel_mixer.m.v_gate.c.weight",
      "stages.2.27.block.token_channel_mixer.m.proj.c.weight",
      "stages.2.28.block.channel_mixer.m.0.c.weight",
      "stages.2.28.block.channel_mixer.m.2.c.weight",
      "stages.2.29.block.cpe.m.c.weight",
      "stages.2.30.block.token_channel_mixer.m.q.c.weight",
      "stages.2.30.block.token_channel_mixer.m.k.c.weight",
      "stages.2.30.block.token_channel_mixer.m.v_gate.c.weight",
      "stages.2.30.block.token_channel_mixer.m.proj.c.weight",
      "stages.2.31.block.channel_mixer.m.0.c.weight",
      "stages.2.31.block.channel_mixer.m.2.c.weight",
      "stages.2.32.block.token_channel_mixer.m.0.c.weight",
      "stages.2.32.block.token_channel_mixer.m.1.c.weight",
      "stages.2.32.block.token_channel_mixer.m.3.c.weight",
      "stages.3.0.block.cpe.m.c.weight",
      "stages.3.1.block.token_channel_mixer.m.q.c.weight",
      "stages.3.1.block.token_channel_mixer.m.k.c.weight",
      "stages.3.1.block.token_channel_mixer.m.v_gate.c.weight",
      "stages.3.1.block.token_channel_mixer.m.proj.c.weight",
      "stages.3.2.block.channel_mixer.m.0.c.weight",
      "stages.3.2.block.channel_mixer.m.2.c.weight",
      "stages.3.3.block.cpe.m.c.weight",
      "stages.3.4.block.token_channel_mixer.m.q.c.weight",
      "stages.3.4.block.token_channel_mixer.m.k.c.weight",
      "stages.3.4.block.token_channel_mixer.m.v_gate.c.weight",
      "stages.3.4.block.token_channel_mixer.m.proj.c.weight",
      "stages.3.5.block.channel_mixer.m.0.c.weight",
      "stages.3.5.block.channel_mixer.m.2.c.weight",
      "classifier.classifier.l.weight",
      "classifier.classifier_dist.l.weight"
    ],
    "lr_scale": 1.0
  },
  "no_decay": {
    "weight_decay": 0.0,
    "params": [
      "downsample_layers.0.0.bn.weight",
      "downsample_layers.0.0.bn.bias",
      "downsample_layers.0.2.conv_exp_bn1.bn.weight",
      "downsample_layers.0.2.conv_exp_bn1.bn.bias",
      "downsample_layers.0.2.conv_pwl_bn2.bn.weight",
      "downsample_layers.0.2.conv_pwl_bn2.bn.bias",
      "downsample_layers.1.0.bn.weight",
      "downsample_layers.1.0.bn.bias",
      "downsample_layers.2.0.bn.weight",
      "downsample_layers.2.0.bn.bias",
      "downsample_layers.3.0.bn.weight",
      "downsample_layers.3.0.bn.bias",
      "stages.0.0.block.token_channel_mixer.m.0.bn.weight",
      "stages.0.0.block.token_channel_mixer.m.0.bn.bias",
      "stages.0.0.block.token_channel_mixer.m.1.bn.weight",
      "stages.0.0.block.token_channel_mixer.m.1.bn.bias",
      "stages.0.0.block.token_channel_mixer.m.3.bn.weight",
      "stages.0.0.block.token_channel_mixer.m.3.bn.bias",
      "stages.0.1.block.token_channel_mixer.m.0.bn.weight",
      "stages.0.1.block.token_channel_mixer.m.0.bn.bias",
      "stages.0.1.block.token_channel_mixer.m.1.bn.weight",
      "stages.0.1.block.token_channel_mixer.m.1.bn.bias",
      "stages.0.1.block.token_channel_mixer.m.3.bn.weight",
      "stages.0.1.block.token_channel_mixer.m.3.bn.bias",
      "stages.1.0.block.token_channel_mixer.m.0.bn.weight",
      "stages.1.0.block.token_channel_mixer.m.0.bn.bias",
      "stages.1.0.block.token_channel_mixer.m.1.bn.weight",
      "stages.1.0.block.token_channel_mixer.m.1.bn.bias",
      "stages.1.0.block.token_channel_mixer.m.3.bn.weight",
      "stages.1.0.block.token_channel_mixer.m.3.bn.bias",
      "stages.1.1.block.token_channel_mixer.m.0.bn.weight",
      "stages.1.1.block.token_channel_mixer.m.0.bn.bias",
      "stages.1.1.block.token_channel_mixer.m.1.bn.weight",
      "stages.1.1.block.token_channel_mixer.m.1.bn.bias",
      "stages.1.1.block.token_channel_mixer.m.3.bn.weight",
      "stages.1.1.block.token_channel_mixer.m.3.bn.bias",
      "stages.2.0.block.token_channel_mixer.m.0.bn.weight",
      "stages.2.0.block.token_channel_mixer.m.0.bn.bias",
      "stages.2.0.block.token_channel_mixer.m.1.bn.weight",
      "stages.2.0.block.token_channel_mixer.m.1.bn.bias",
      "stages.2.0.block.token_channel_mixer.m.3.bn.weight",
      "stages.2.0.block.token_channel_mixer.m.3.bn.bias",
      "stages.2.1.block.token_channel_mixer.m.0.bn.weight",
      "stages.2.1.block.token_channel_mixer.m.0.bn.bias",
      "stages.2.1.block.token_channel_mixer.m.1.bn.weight",
      "stages.2.1.block.token_channel_mixer.m.1.bn.bias",
      "stages.2.1.block.token_channel_mixer.m.3.bn.weight",
      "stages.2.1.block.token_channel_mixer.m.3.bn.bias",
      "stages.2.2.block.token_channel_mixer.m.0.bn.weight",
      "stages.2.2.block.token_channel_mixer.m.0.bn.bias",
      "stages.2.2.block.token_channel_mixer.m.1.bn.weight",
      "stages.2.2.block.token_channel_mixer.m.1.bn.bias",
      "stages.2.2.block.token_channel_mixer.m.3.bn.weight",
      "stages.2.2.block.token_channel_mixer.m.3.bn.bias",
      "stages.2.3.block.token_channel_mixer.m.0.bn.weight",
      "stages.2.3.block.token_channel_mixer.m.0.bn.bias",
      "stages.2.3.block.token_channel_mixer.m.1.bn.weight",
      "stages.2.3.block.token_channel_mixer.m.1.bn.bias",
      "stages.2.3.block.token_channel_mixer.m.3.bn.weight",
      "stages.2.3.block.token_channel_mixer.m.3.bn.bias",
      "stages.2.4.block.token_channel_mixer.m.0.bn.weight",
      "stages.2.4.block.token_channel_mixer.m.0.bn.bias",
      "stages.2.4.block.token_channel_mixer.m.1.bn.weight",
      "stages.2.4.block.token_channel_mixer.m.1.bn.bias",
      "stages.2.4.block.token_channel_mixer.m.3.bn.weight",
      "stages.2.4.block.token_channel_mixer.m.3.bn.bias",
      "stages.2.5.block.token_channel_mixer.m.0.bn.weight",
      "stages.2.5.block.token_channel_mixer.m.0.bn.bias",
      "stages.2.5.block.token_channel_mixer.m.1.bn.weight",
      "stages.2.5.block.token_channel_mixer.m.1.bn.bias",
      "stages.2.5.block.token_channel_mixer.m.3.bn.weight",
      "stages.2.5.block.token_channel_mixer.m.3.bn.bias",
      "stages.2.6.block.token_channel_mixer.m.0.bn.weight",
      "stages.2.6.block.token_channel_mixer.m.0.bn.bias",
      "stages.2.6.block.token_channel_mixer.m.1.bn.weight",
      "stages.2.6.block.token_channel_mixer.m.1.bn.bias",
      "stages.2.6.block.token_channel_mixer.m.3.bn.weight",
      "stages.2.6.block.token_channel_mixer.m.3.bn.bias",
      "stages.2.7.block.token_channel_mixer.m.0.bn.weight",
      "stages.2.7.block.token_channel_mixer.m.0.bn.bias",
      "stages.2.7.block.token_channel_mixer.m.1.bn.weight",
      "stages.2.7.block.token_channel_mixer.m.1.bn.bias",
      "stages.2.7.block.token_channel_mixer.m.3.bn.weight",
      "stages.2.7.block.token_channel_mixer.m.3.bn.bias",
      "stages.2.8.block.cpe.m.bn.weight",
      "stages.2.8.block.cpe.m.bn.bias",
      "stages.2.9.block.token_channel_mixer.m.q.bn.weight",
      "stages.2.9.block.token_channel_mixer.m.q.bn.bias",
      "stages.2.9.block.token_channel_mixer.m.k.bn.weight",
      "stages.2.9.block.token_channel_mixer.m.k.bn.bias",
      "stages.2.9.block.token_channel_mixer.m.v_gate.bn.weight",
      "stages.2.9.block.token_channel_mixer.m.v_gate.bn.bias",
      "stages.2.9.block.token_channel_mixer.m.proj.bn.weight",
      "stages.2.9.block.token_channel_mixer.m.proj.bn.bias",
      "stages.2.10.block.channel_mixer.m.0.bn.weight",
      "stages.2.10.block.channel_mixer.m.0.bn.bias",
      "stages.2.10.block.channel_mixer.m.2.bn.weight",
      "stages.2.10.block.channel_mixer.m.2.bn.bias",
      "stages.2.11.block.cpe.m.bn.weight",
      "stages.2.11.block.cpe.m.bn.bias",
      "stages.2.12.block.token_channel_mixer.m.q.bn.weight",
      "stages.2.12.block.token_channel_mixer.m.q.bn.bias",
      "stages.2.12.block.token_channel_mixer.m.k.bn.weight",
      "stages.2.12.block.token_channel_mixer.m.k.bn.bias",
      "stages.2.12.block.token_channel_mixer.m.v_gate.bn.weight",
      "stages.2.12.block.token_channel_mixer.m.v_gate.bn.bias",
      "stages.2.12.block.token_channel_mixer.m.proj.bn.weight",
      "stages.2.12.block.token_channel_mixer.m.proj.bn.bias",
      "stages.2.13.block.channel_mixer.m.0.bn.weight",
      "stages.2.13.block.channel_mixer.m.0.bn.bias",
      "stages.2.13.block.channel_mixer.m.2.bn.weight",
      "stages.2.13.block.channel_mixer.m.2.bn.bias",
      "stages.2.14.block.cpe.m.bn.weight",
      "stages.2.14.block.cpe.m.bn.bias",
      "stages.2.15.block.token_channel_mixer.m.q.bn.weight",
      "stages.2.15.block.token_channel_mixer.m.q.bn.bias",
      "stages.2.15.block.token_channel_mixer.m.k.bn.weight",
      "stages.2.15.block.token_channel_mixer.m.k.bn.bias",
      "stages.2.15.block.token_channel_mixer.m.v_gate.bn.weight",
      "stages.2.15.block.token_channel_mixer.m.v_gate.bn.bias",
      "stages.2.15.block.token_channel_mixer.m.proj.bn.weight",
      "stages.2.15.block.token_channel_mixer.m.proj.bn.bias",
      "stages.2.16.block.channel_mixer.m.0.bn.weight",
      "stages.2.16.block.channel_mixer.m.0.bn.bias",
      "stages.2.16.block.channel_mixer.m.2.bn.weight",
      "stages.2.16.block.channel_mixer.m.2.bn.bias",
      "stages.2.17.block.cpe.m.bn.weight",
      "stages.2.17.block.cpe.m.bn.bias",
      "stages.2.18.block.token_channel_mixer.m.q.bn.weight",
      "stages.2.18.block.token_channel_mixer.m.q.bn.bias",
      "stages.2.18.block.token_channel_mixer.m.k.bn.weight",
      "stages.2.18.block.token_channel_mixer.m.k.bn.bias",
      "stages.2.18.block.token_channel_mixer.m.v_gate.bn.weight",
      "stages.2.18.block.token_channel_mixer.m.v_gate.bn.bias",
      "stages.2.18.block.token_channel_mixer.m.proj.bn.weight",
      "stages.2.18.block.token_channel_mixer.m.proj.bn.bias",
      "stages.2.19.block.channel_mixer.m.0.bn.weight",
      "stages.2.19.block.channel_mixer.m.0.bn.bias",
      "stages.2.19.block.channel_mixer.m.2.bn.weight",
      "stages.2.19.block.channel_mixer.m.2.bn.bias",
      "stages.2.20.block.cpe.m.bn.weight",
      "stages.2.20.block.cpe.m.bn.bias",
      "stages.2.21.block.token_channel_mixer.m.q.bn.weight",
      "stages.2.21.block.token_channel_mixer.m.q.bn.bias",
      "stages.2.21.block.token_channel_mixer.m.k.bn.weight",
      "stages.2.21.block.token_channel_mixer.m.k.bn.bias",
      "stages.2.21.block.token_channel_mixer.m.v_gate.bn.weight",
      "stages.2.21.block.token_channel_mixer.m.v_gate.bn.bias",
      "stages.2.21.block.token_channel_mixer.m.proj.bn.weight",
      "stages.2.21.block.token_channel_mixer.m.proj.bn.bias",
      "stages.2.22.block.channel_mixer.m.0.bn.weight",
      "stages.2.22.block.channel_mixer.m.0.bn.bias",
      "stages.2.22.block.channel_mixer.m.2.bn.weight",
      "stages.2.22.block.channel_mixer.m.2.bn.bias",
      "stages.2.23.block.cpe.m.bn.weight",
      "stages.2.23.block.cpe.m.bn.bias",
      "stages.2.24.block.token_channel_mixer.m.q.bn.weight",
      "stages.2.24.block.token_channel_mixer.m.q.bn.bias",
      "stages.2.24.block.token_channel_mixer.m.k.bn.weight",
      "stages.2.24.block.token_channel_mixer.m.k.bn.bias",
      "stages.2.24.block.token_channel_mixer.m.v_gate.bn.weight",
      "stages.2.24.block.token_channel_mixer.m.v_gate.bn.bias",
      "stages.2.24.block.token_channel_mixer.m.proj.bn.weight",
      "stages.2.24.block.token_channel_mixer.m.proj.bn.bias",
      "stages.2.25.block.channel_mixer.m.0.bn.weight",
      "stages.2.25.block.channel_mixer.m.0.bn.bias",
      "stages.2.25.block.channel_mixer.m.2.bn.weight",
      "stages.2.25.block.channel_mixer.m.2.bn.bias",
      "stages.2.26.block.cpe.m.bn.weight",
      "stages.2.26.block.cpe.m.bn.bias",
      "stages.2.27.block.token_channel_mixer.m.q.bn.weight",
      "stages.2.27.block.token_channel_mixer.m.q.bn.bias",
      "stages.2.27.block.token_channel_mixer.m.k.bn.weight",
      "stages.2.27.block.token_channel_mixer.m.k.bn.bias",
      "stages.2.27.block.token_channel_mixer.m.v_gate.bn.weight",
      "stages.2.27.block.token_channel_mixer.m.v_gate.bn.bias",
      "stages.2.27.block.token_channel_mixer.m.proj.bn.weight",
      "stages.2.27.block.token_channel_mixer.m.proj.bn.bias",
      "stages.2.28.block.channel_mixer.m.0.bn.weight",
      "stages.2.28.block.channel_mixer.m.0.bn.bias",
      "stages.2.28.block.channel_mixer.m.2.bn.weight",
      "stages.2.28.block.channel_mixer.m.2.bn.bias",
      "stages.2.29.block.cpe.m.bn.weight",
      "stages.2.29.block.cpe.m.bn.bias",
      "stages.2.30.block.token_channel_mixer.m.q.bn.weight",
      "stages.2.30.block.token_channel_mixer.m.q.bn.bias",
      "stages.2.30.block.token_channel_mixer.m.k.bn.weight",
      "stages.2.30.block.token_channel_mixer.m.k.bn.bias",
      "stages.2.30.block.token_channel_mixer.m.v_gate.bn.weight",
      "stages.2.30.block.token_channel_mixer.m.v_gate.bn.bias",
      "stages.2.30.block.token_channel_mixer.m.proj.bn.weight",
      "stages.2.30.block.token_channel_mixer.m.proj.bn.bias",
      "stages.2.31.block.channel_mixer.m.0.bn.weight",
      "stages.2.31.block.channel_mixer.m.0.bn.bias",
      "stages.2.31.block.channel_mixer.m.2.bn.weight",
      "stages.2.31.block.channel_mixer.m.2.bn.bias",
      "stages.2.32.block.token_channel_mixer.m.0.bn.weight",
      "stages.2.32.block.token_channel_mixer.m.0.bn.bias",
      "stages.2.32.block.token_channel_mixer.m.1.bn.weight",
      "stages.2.32.block.token_channel_mixer.m.1.bn.bias",
      "stages.2.32.block.token_channel_mixer.m.3.bn.weight",
      "stages.2.32.block.token_channel_mixer.m.3.bn.bias",
      "stages.3.0.block.cpe.m.bn.weight",
      "stages.3.0.block.cpe.m.bn.bias",
      "stages.3.1.block.token_channel_mixer.m.q.bn.weight",
      "stages.3.1.block.token_channel_mixer.m.q.bn.bias",
      "stages.3.1.block.token_channel_mixer.m.k.bn.weight",
      "stages.3.1.block.token_channel_mixer.m.k.bn.bias",
      "stages.3.1.block.token_channel_mixer.m.v_gate.bn.weight",
      "stages.3.1.block.token_channel_mixer.m.v_gate.bn.bias",
      "stages.3.1.block.token_channel_mixer.m.proj.bn.weight",
      "stages.3.1.block.token_channel_mixer.m.proj.bn.bias",
      "stages.3.2.block.channel_mixer.m.0.bn.weight",
      "stages.3.2.block.channel_mixer.m.0.bn.bias",
      "stages.3.2.block.channel_mixer.m.2.bn.weight",
      "stages.3.2.block.channel_mixer.m.2.bn.bias",
      "stages.3.3.block.cpe.m.bn.weight",
      "stages.3.3.block.cpe.m.bn.bias",
      "stages.3.4.block.token_channel_mixer.m.q.bn.weight",
      "stages.3.4.block.token_channel_mixer.m.q.bn.bias",
      "stages.3.4.block.token_channel_mixer.m.k.bn.weight",
      "stages.3.4.block.token_channel_mixer.m.k.bn.bias",
      "stages.3.4.block.token_channel_mixer.m.v_gate.bn.weight",
      "stages.3.4.block.token_channel_mixer.m.v_gate.bn.bias",
      "stages.3.4.block.token_channel_mixer.m.proj.bn.weight",
      "stages.3.4.block.token_channel_mixer.m.proj.bn.bias",
      "stages.3.5.block.channel_mixer.m.0.bn.weight",
      "stages.3.5.block.channel_mixer.m.0.bn.bias",
      "stages.3.5.block.channel_mixer.m.2.bn.weight",
      "stages.3.5.block.channel_mixer.m.2.bn.bias",
      "classifier.classifier.bn.weight",
      "classifier.classifier.bn.bias",
      "classifier.classifier.l.bias",
      "classifier.classifier_dist.bn.weight",
      "classifier.classifier_dist.bn.bias",
      "classifier.classifier_dist.l.bias"
    ],
    "lr_scale": 1.0
  }
}
Use Cosine LR scheduler
Set warmup steps = 6240
Set warmup steps = 0
Max WD = 0.0500000, Min WD = 0.0500000
Creating teacher model: regnety_160
criterion = SoftTargetCrossEntropy()
Auto resume checkpoint: 
Start training for 300 epochs
Epoch: [0]  [  0/312]  eta: 9:01:34  lr: 0.000000  min_lr: 0.000000  loss: 6.9645 (6.9645)  weight_decay: 0.0500 (0.0500)  time: 104.1494  data: 20.9055  max mem: 78493
Epoch: [0]  [ 10/312]  eta: 0:56:42  lr: 0.000006  min_lr: 0.000006  loss: 6.9829 (6.9813)  weight_decay: 0.0500 (0.0500)  time: 11.2650  data: 1.9011  max mem: 78493
Epoch: [0]  [ 20/312]  eta: 0:31:02  lr: 0.000013  min_lr: 0.000013  loss: 6.9756 (6.9781)  weight_decay: 0.0500 (0.0500)  time: 1.4908  data: 0.0016  max mem: 78493
Epoch: [0]  [ 30/312]  eta: 0:21:50  lr: 0.000019  min_lr: 0.000019  loss: 6.9737 (6.9738)  weight_decay: 0.0500 (0.0500)  time: 1.0047  data: 0.0025  max mem: 78493
Epoch: [0]  [ 40/312]  eta: 0:17:02  lr: 0.000026  min_lr: 0.000026  loss: 6.9598 (6.9687)  weight_decay: 0.0500 (0.0500)  time: 1.0057  data: 0.0016  max mem: 78493
Epoch: [0]  [ 50/312]  eta: 0:14:03  lr: 0.000032  min_lr: 0.000032  loss: 6.9421 (6.9615)  weight_decay: 0.0500 (0.0500)  time: 1.0075  data: 0.0006  max mem: 78493
Epoch: [0]  [ 60/312]  eta: 0:11:59  lr: 0.000038  min_lr: 0.000038  loss: 6.9193 (6.9538)  weight_decay: 0.0500 (0.0500)  time: 1.0083  data: 0.0014  max mem: 78493
Epoch: [0]  [ 70/312]  eta: 0:10:28  lr: 0.000045  min_lr: 0.000045  loss: 6.9075 (6.9449)  weight_decay: 0.0500 (0.0500)  time: 1.0102  data: 0.0023  max mem: 78493
Epoch: [0]  [ 80/312]  eta: 0:09:17  lr: 0.000051  min_lr: 0.000051  loss: 6.8884 (6.9365)  weight_decay: 0.0500 (0.0500)  time: 1.0144  data: 0.0028  max mem: 78493
Epoch: [0]  [ 90/312]  eta: 0:08:19  lr: 0.000058  min_lr: 0.000058  loss: 6.8707 (6.9282)  weight_decay: 0.0500 (0.0500)  time: 1.0160  data: 0.0019  max mem: 78493
Epoch: [0]  [100/312]  eta: 0:07:31  lr: 0.000064  min_lr: 0.000064  loss: 6.8510 (6.9207)  weight_decay: 0.0500 (0.0500)  time: 1.0171  data: 0.0020  max mem: 78493
Epoch: [0]  [110/312]  eta: 0:06:49  lr: 0.000071  min_lr: 0.000071  loss: 6.8337 (6.9115)  weight_decay: 0.0500 (0.0500)  time: 1.0156  data: 0.0020  max mem: 78493
Epoch: [0]  [120/312]  eta: 0:06:13  lr: 0.000077  min_lr: 0.000077  loss: 6.8156 (6.9028)  weight_decay: 0.0500 (0.0500)  time: 1.0097  data: 0.0005  max mem: 78493
Epoch: [0]  [130/312]  eta: 0:05:40  lr: 0.000083  min_lr: 0.000083  loss: 6.7945 (6.8932)  weight_decay: 0.0500 (0.0500)  time: 1.0078  data: 0.0013  max mem: 78493
Epoch: [0]  [140/312]  eta: 0:05:11  lr: 0.000090  min_lr: 0.000090  loss: 6.7705 (6.8839)  weight_decay: 0.0500 (0.0500)  time: 1.0082  data: 0.0013  max mem: 78493
Epoch: [0]  [150/312]  eta: 0:04:44  lr: 0.000096  min_lr: 0.000096  loss: 6.7371 (6.8734)  weight_decay: 0.0500 (0.0500)  time: 1.0094  data: 0.0005  max mem: 78493
Epoch: [0]  [160/312]  eta: 0:04:20  lr: 0.000103  min_lr: 0.000103  loss: 6.7212 (6.8649)  weight_decay: 0.0500 (0.0500)  time: 1.0103  data: 0.0005  max mem: 78493
Epoch: [0]  [170/312]  eta: 0:03:57  lr: 0.000109  min_lr: 0.000109  loss: 6.7267 (6.8561)  weight_decay: 0.0500 (0.0500)  time: 1.0094  data: 0.0005  max mem: 78493
Epoch: [0]  [180/312]  eta: 0:03:35  lr: 0.000115  min_lr: 0.000115  loss: 6.6895 (6.8460)  weight_decay: 0.0500 (0.0500)  time: 1.0094  data: 0.0005  max mem: 78493
Epoch: [0]  [190/312]  eta: 0:03:15  lr: 0.000122  min_lr: 0.000122  loss: 6.6802 (6.8370)  weight_decay: 0.0500 (0.0500)  time: 1.0107  data: 0.0005  max mem: 78493
Epoch: [0]  [200/312]  eta: 0:02:56  lr: 0.000128  min_lr: 0.000128  loss: 6.6328 (6.8266)  weight_decay: 0.0500 (0.0500)  time: 1.0116  data: 0.0005  max mem: 78493
Epoch: [0]  [210/312]  eta: 0:02:37  lr: 0.000135  min_lr: 0.000135  loss: 6.6091 (6.8167)  weight_decay: 0.0500 (0.0500)  time: 1.0087  data: 0.0006  max mem: 78493
Epoch: [0]  [220/312]  eta: 0:02:19  lr: 0.000141  min_lr: 0.000141  loss: 6.6030 (6.8064)  weight_decay: 0.0500 (0.0500)  time: 1.0067  data: 0.0005  max mem: 78493
Epoch: [0]  [230/312]  eta: 0:02:02  lr: 0.000147  min_lr: 0.000147  loss: 6.5966 (6.7973)  weight_decay: 0.0500 (0.0500)  time: 1.0088  data: 0.0005  max mem: 78493
Epoch: [0]  [240/312]  eta: 0:01:46  lr: 0.000154  min_lr: 0.000154  loss: 6.5773 (6.7876)  weight_decay: 0.0500 (0.0500)  time: 1.0079  data: 0.0005  max mem: 78493
Epoch: [0]  [250/312]  eta: 0:01:30  lr: 0.000160  min_lr: 0.000160  loss: 6.5663 (6.7784)  weight_decay: 0.0500 (0.0500)  time: 1.0065  data: 0.0005  max mem: 78493
Epoch: [0]  [260/312]  eta: 0:01:14  lr: 0.000167  min_lr: 0.000167  loss: 6.5110 (6.7695)  weight_decay: 0.0500 (0.0500)  time: 1.0077  data: 0.0006  max mem: 78493
Epoch: [0]  [270/312]  eta: 0:00:59  lr: 0.000173  min_lr: 0.000173  loss: 6.4946 (6.7595)  weight_decay: 0.0500 (0.0500)  time: 1.0080  data: 0.0005  max mem: 78493
Epoch: [0]  [280/312]  eta: 0:00:45  lr: 0.000180  min_lr: 0.000180  loss: 6.5638 (6.7527)  weight_decay: 0.0500 (0.0500)  time: 1.0091  data: 0.0012  max mem: 78493
Epoch: [0]  [290/312]  eta: 0:00:30  lr: 0.000186  min_lr: 0.000186  loss: 6.5469 (6.7435)  weight_decay: 0.0500 (0.0500)  time: 1.0065  data: 0.0010  max mem: 78493
Epoch: [0]  [300/312]  eta: 0:00:16  lr: 0.000192  min_lr: 0.000192  loss: 6.4355 (6.7344)  weight_decay: 0.0500 (0.0500)  time: 1.0020  data: 0.0001  max mem: 78493
Epoch: [0]  [310/312]  eta: 0:00:02  lr: 0.000199  min_lr: 0.000199  loss: 6.4481 (6.7263)  weight_decay: 0.0500 (0.0500)  time: 1.0019  data: 0.0001  max mem: 78493
Epoch: [0]  [311/312]  eta: 0:00:01  lr: 0.000199  min_lr: 0.000199  loss: 6.4481 (6.7260)  weight_decay: 0.0500 (0.0500)  time: 1.0019  data: 0.0001  max mem: 78493
Epoch: [0] Total time: 0:07:09 (1.3767 s / it)
Averaged stats: lr: 0.000199  min_lr: 0.000199  loss: 6.4481 (6.7302)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:03:48  loss: 5.8962 (5.8962)  acc1: 0.9115 (0.9115)  acc5: 7.9427 (7.9427)  time: 25.3824  data: 7.9021  max mem: 78493
Test:  [8/9]  eta: 0:00:03  loss: 6.0498 (5.9314)  acc1: 2.0833 (2.5440)  acc5: 7.9427 (9.2160)  time: 3.3594  data: 0.8781  max mem: 78493
Test: Total time: 0:00:30 (3.3830 s / it)
* Acc@1 2.598 Acc@5 9.094 loss 5.943
Accuracy of the model on the 50000 test images: 2.6%
Max accuracy: 2.60%
Epoch: [1]  [  0/312]  eta: 2:35:55  lr: 0.000200  min_lr: 0.000200  loss: 6.5108 (6.5108)  weight_decay: 0.0500 (0.0500)  time: 29.9860  data: 13.1263  max mem: 78493
Epoch: [1]  [ 10/312]  eta: 0:23:56  lr: 0.000206  min_lr: 0.000206  loss: 6.5509 (6.5399)  weight_decay: 0.0500 (0.0500)  time: 4.7579  data: 1.1937  max mem: 78493
Epoch: [1]  [ 20/312]  eta: 0:15:40  lr: 0.000213  min_lr: 0.000213  loss: 6.5218 (6.5020)  weight_decay: 0.0500 (0.0500)  time: 1.8823  data: 0.0005  max mem: 78493
Epoch: [1]  [ 30/312]  eta: 0:11:46  lr: 0.000219  min_lr: 0.000219  loss: 6.4833 (6.4941)  weight_decay: 0.0500 (0.0500)  time: 1.2685  data: 0.0005  max mem: 78493
Epoch: [1]  [ 40/312]  eta: 0:09:42  lr: 0.000226  min_lr: 0.000226  loss: 6.4246 (6.4777)  weight_decay: 0.0500 (0.0500)  time: 1.0092  data: 0.0005  max mem: 78493
Epoch: [1]  [ 50/312]  eta: 0:08:22  lr: 0.000232  min_lr: 0.000232  loss: 6.4316 (6.4678)  weight_decay: 0.0500 (0.0500)  time: 1.0093  data: 0.0010  max mem: 78493
Epoch: [1]  [ 60/312]  eta: 0:07:26  lr: 0.000238  min_lr: 0.000238  loss: 6.4113 (6.4566)  weight_decay: 0.0500 (0.0500)  time: 1.0103  data: 0.0010  max mem: 78493
Epoch: [1]  [ 70/312]  eta: 0:06:42  lr: 0.000245  min_lr: 0.000245  loss: 6.4037 (6.4442)  weight_decay: 0.0500 (0.0500)  time: 1.0129  data: 0.0005  max mem: 78493
Epoch: [1]  [ 80/312]  eta: 0:06:07  lr: 0.000251  min_lr: 0.000251  loss: 6.3115 (6.4305)  weight_decay: 0.0500 (0.0500)  time: 1.0124  data: 0.0005  max mem: 78493
Epoch: [1]  [ 90/312]  eta: 0:05:37  lr: 0.000258  min_lr: 0.000258  loss: 6.3589 (6.4295)  weight_decay: 0.0500 (0.0500)  time: 1.0136  data: 0.0005  max mem: 78493
Epoch: [1]  [100/312]  eta: 0:05:11  lr: 0.000264  min_lr: 0.000264  loss: 6.3933 (6.4258)  weight_decay: 0.0500 (0.0500)  time: 1.0149  data: 0.0005  max mem: 78493
Epoch: [1]  [110/312]  eta: 0:04:48  lr: 0.000271  min_lr: 0.000271  loss: 6.3475 (6.4116)  weight_decay: 0.0500 (0.0500)  time: 1.0147  data: 0.0005  max mem: 78493
Epoch: [1]  [120/312]  eta: 0:04:27  lr: 0.000277  min_lr: 0.000277  loss: 6.3370 (6.4102)  weight_decay: 0.0500 (0.0500)  time: 1.0125  data: 0.0005  max mem: 78493
Epoch: [1]  [130/312]  eta: 0:04:08  lr: 0.000283  min_lr: 0.000283  loss: 6.3511 (6.4043)  weight_decay: 0.0500 (0.0500)  time: 1.0104  data: 0.0005  max mem: 78493
Epoch: [1]  [140/312]  eta: 0:03:50  lr: 0.000290  min_lr: 0.000290  loss: 6.2521 (6.3929)  weight_decay: 0.0500 (0.0500)  time: 1.0103  data: 0.0013  max mem: 78493
Epoch: [1]  [150/312]  eta: 0:03:33  lr: 0.000296  min_lr: 0.000296  loss: 6.1900 (6.3796)  weight_decay: 0.0500 (0.0500)  time: 1.0116  data: 0.0012  max mem: 78493
Epoch: [1]  [160/312]  eta: 0:03:17  lr: 0.000303  min_lr: 0.000303  loss: 6.1799 (6.3669)  weight_decay: 0.0500 (0.0500)  time: 1.0130  data: 0.0005  max mem: 78493
Epoch: [1]  [170/312]  eta: 0:03:02  lr: 0.000309  min_lr: 0.000309  loss: 6.2118 (6.3625)  weight_decay: 0.0500 (0.0500)  time: 1.0115  data: 0.0005  max mem: 78493
Epoch: [1]  [180/312]  eta: 0:02:47  lr: 0.000315  min_lr: 0.000315  loss: 6.2614 (6.3577)  weight_decay: 0.0500 (0.0500)  time: 1.0102  data: 0.0004  max mem: 78493
Epoch: [1]  [190/312]  eta: 0:02:33  lr: 0.000322  min_lr: 0.000322  loss: 6.2254 (6.3473)  weight_decay: 0.0500 (0.0500)  time: 1.0086  data: 0.0005  max mem: 78493
Epoch: [1]  [200/312]  eta: 0:02:19  lr: 0.000328  min_lr: 0.000328  loss: 6.2674 (6.3465)  weight_decay: 0.0500 (0.0500)  time: 1.0075  data: 0.0005  max mem: 78493
Epoch: [1]  [210/312]  eta: 0:02:05  lr: 0.000335  min_lr: 0.000335  loss: 6.2922 (6.3383)  weight_decay: 0.0500 (0.0500)  time: 1.0079  data: 0.0005  max mem: 78493
Epoch: [1]  [220/312]  eta: 0:01:52  lr: 0.000341  min_lr: 0.000341  loss: 6.2543 (6.3313)  weight_decay: 0.0500 (0.0500)  time: 1.0077  data: 0.0004  max mem: 78493
Epoch: [1]  [230/312]  eta: 0:01:39  lr: 0.000347  min_lr: 0.000347  loss: 6.2249 (6.3225)  weight_decay: 0.0500 (0.0500)  time: 1.0073  data: 0.0004  max mem: 78493
Epoch: [1]  [240/312]  eta: 0:01:26  lr: 0.000354  min_lr: 0.000354  loss: 6.2209 (6.3148)  weight_decay: 0.0500 (0.0500)  time: 1.0091  data: 0.0005  max mem: 78493
Epoch: [1]  [250/312]  eta: 0:01:14  lr: 0.000360  min_lr: 0.000360  loss: 6.2430 (6.3116)  weight_decay: 0.0500 (0.0500)  time: 1.0095  data: 0.0005  max mem: 78493
Epoch: [1]  [260/312]  eta: 0:01:01  lr: 0.000367  min_lr: 0.000367  loss: 6.2475 (6.3057)  weight_decay: 0.0500 (0.0500)  time: 1.0095  data: 0.0004  max mem: 78493
Epoch: [1]  [270/312]  eta: 0:00:49  lr: 0.000373  min_lr: 0.000373  loss: 6.2032 (6.3010)  weight_decay: 0.0500 (0.0500)  time: 1.0098  data: 0.0004  max mem: 78493
Epoch: [1]  [280/312]  eta: 0:00:37  lr: 0.000380  min_lr: 0.000380  loss: 6.1890 (6.2949)  weight_decay: 0.0500 (0.0500)  time: 1.0086  data: 0.0011  max mem: 78493
Epoch: [1]  [290/312]  eta: 0:00:25  lr: 0.000386  min_lr: 0.000386  loss: 6.0955 (6.2867)  weight_decay: 0.0500 (0.0500)  time: 1.0051  data: 0.0009  max mem: 78493
Epoch: [1]  [300/312]  eta: 0:00:13  lr: 0.000392  min_lr: 0.000392  loss: 6.0935 (6.2809)  weight_decay: 0.0500 (0.0500)  time: 1.0020  data: 0.0001  max mem: 78493
Epoch: [1]  [310/312]  eta: 0:00:02  lr: 0.000399  min_lr: 0.000399  loss: 6.1366 (6.2765)  weight_decay: 0.0500 (0.0500)  time: 1.0021  data: 0.0001  max mem: 78493
Epoch: [1]  [311/312]  eta: 0:00:01  lr: 0.000399  min_lr: 0.000399  loss: 6.1089 (6.2758)  weight_decay: 0.0500 (0.0500)  time: 1.0021  data: 0.0001  max mem: 78493
Epoch: [1] Total time: 0:06:03 (1.1648 s / it)
Averaged stats: lr: 0.000399  min_lr: 0.000399  loss: 6.1089 (6.2677)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:18  loss: 4.8507 (4.8507)  acc1: 8.4635 (8.4635)  acc5: 23.5677 (23.5677)  time: 8.7397  data: 8.4741  max mem: 78493
Test:  [8/9]  eta: 0:00:01  loss: 5.0011 (5.0778)  acc1: 7.1615 (8.0000)  acc5: 23.5677 (22.0320)  time: 1.1716  data: 0.9417  max mem: 78493
Test: Total time: 0:00:10 (1.2094 s / it)
* Acc@1 7.730 Acc@5 21.500 loss 5.099
Accuracy of the model on the 50000 test images: 7.7%
Max accuracy: 7.73%
Epoch: [2]  [  0/312]  eta: 1:27:57  lr: 0.000400  min_lr: 0.000400  loss: 6.2205 (6.2205)  weight_decay: 0.0500 (0.0500)  time: 16.9138  data: 15.8543  max mem: 78493
Epoch: [2]  [ 10/312]  eta: 0:13:22  lr: 0.000406  min_lr: 0.000406  loss: 6.0110 (6.0626)  weight_decay: 0.0500 (0.0500)  time: 2.6577  data: 1.4442  max mem: 78493
Epoch: [2]  [ 20/312]  eta: 0:09:07  lr: 0.000413  min_lr: 0.000413  loss: 5.9237 (5.9913)  weight_decay: 0.0500 (0.0500)  time: 1.1244  data: 0.0018  max mem: 78493
Epoch: [2]  [ 30/312]  eta: 0:07:30  lr: 0.000419  min_lr: 0.000419  loss: 5.8708 (5.9945)  weight_decay: 0.0500 (0.0500)  time: 1.0127  data: 0.0005  max mem: 78493
Epoch: [2]  [ 40/312]  eta: 0:06:35  lr: 0.000426  min_lr: 0.000426  loss: 5.8512 (5.9681)  weight_decay: 0.0500 (0.0500)  time: 1.0081  data: 0.0004  max mem: 78493
Epoch: [2]  [ 50/312]  eta: 0:05:57  lr: 0.000432  min_lr: 0.000432  loss: 5.9614 (5.9903)  weight_decay: 0.0500 (0.0500)  time: 1.0068  data: 0.0004  max mem: 78493
Epoch: [2]  [ 60/312]  eta: 0:05:29  lr: 0.000439  min_lr: 0.000439  loss: 5.9614 (5.9719)  weight_decay: 0.0500 (0.0500)  time: 1.0065  data: 0.0004  max mem: 78493
Epoch: [2]  [ 70/312]  eta: 0:05:06  lr: 0.000445  min_lr: 0.000445  loss: 5.8157 (5.9615)  weight_decay: 0.0500 (0.0500)  time: 1.0077  data: 0.0004  max mem: 78493
Epoch: [2]  [ 80/312]  eta: 0:04:45  lr: 0.000451  min_lr: 0.000451  loss: 5.7135 (5.9478)  weight_decay: 0.0500 (0.0500)  time: 1.0073  data: 0.0004  max mem: 78493
Epoch: [2]  [ 90/312]  eta: 0:04:28  lr: 0.000458  min_lr: 0.000458  loss: 5.7013 (5.9376)  weight_decay: 0.0500 (0.0500)  time: 1.0067  data: 0.0004  max mem: 78493
Epoch: [2]  [100/312]  eta: 0:04:11  lr: 0.000464  min_lr: 0.000464  loss: 5.7270 (5.9252)  weight_decay: 0.0500 (0.0500)  time: 1.0091  data: 0.0004  max mem: 78493
Epoch: [2]  [110/312]  eta: 0:03:56  lr: 0.000471  min_lr: 0.000471  loss: 5.8593 (5.9282)  weight_decay: 0.0500 (0.0500)  time: 1.0092  data: 0.0005  max mem: 78493
Epoch: [2]  [120/312]  eta: 0:03:42  lr: 0.000477  min_lr: 0.000477  loss: 6.0601 (5.9340)  weight_decay: 0.0500 (0.0500)  time: 1.0090  data: 0.0012  max mem: 78493
Epoch: [2]  [130/312]  eta: 0:03:28  lr: 0.000483  min_lr: 0.000483  loss: 5.9648 (5.9245)  weight_decay: 0.0500 (0.0500)  time: 1.0104  data: 0.0012  max mem: 78493
Epoch: [2]  [140/312]  eta: 0:03:15  lr: 0.000490  min_lr: 0.000490  loss: 5.9219 (5.9263)  weight_decay: 0.0500 (0.0500)  time: 1.0084  data: 0.0004  max mem: 78493
Epoch: [2]  [150/312]  eta: 0:03:02  lr: 0.000496  min_lr: 0.000496  loss: 5.9271 (5.9246)  weight_decay: 0.0500 (0.0500)  time: 1.0064  data: 0.0004  max mem: 78493
Epoch: [2]  [160/312]  eta: 0:02:50  lr: 0.000503  min_lr: 0.000503  loss: 5.9271 (5.9169)  weight_decay: 0.0500 (0.0500)  time: 1.0059  data: 0.0004  max mem: 78493
Epoch: [2]  [170/312]  eta: 0:02:38  lr: 0.000509  min_lr: 0.000509  loss: 5.9418 (5.9153)  weight_decay: 0.0500 (0.0500)  time: 1.0067  data: 0.0004  max mem: 78493
Epoch: [2]  [180/312]  eta: 0:02:26  lr: 0.000515  min_lr: 0.000515  loss: 5.8118 (5.9055)  weight_decay: 0.0500 (0.0500)  time: 1.0085  data: 0.0004  max mem: 78493
Epoch: [2]  [190/312]  eta: 0:02:14  lr: 0.000522  min_lr: 0.000522  loss: 5.6774 (5.8893)  weight_decay: 0.0500 (0.0500)  time: 1.0088  data: 0.0004  max mem: 78493
Epoch: [2]  [200/312]  eta: 0:02:03  lr: 0.000528  min_lr: 0.000528  loss: 5.4909 (5.8816)  weight_decay: 0.0500 (0.0500)  time: 1.0077  data: 0.0004  max mem: 78493
Epoch: [2]  [210/312]  eta: 0:01:51  lr: 0.000535  min_lr: 0.000535  loss: 5.5861 (5.8686)  weight_decay: 0.0500 (0.0500)  time: 1.0064  data: 0.0004  max mem: 78493
Epoch: [2]  [220/312]  eta: 0:01:40  lr: 0.000541  min_lr: 0.000541  loss: 5.5295 (5.8568)  weight_decay: 0.0500 (0.0500)  time: 1.0058  data: 0.0004  max mem: 78493
Epoch: [2]  [230/312]  eta: 0:01:29  lr: 0.000548  min_lr: 0.000548  loss: 5.7877 (5.8548)  weight_decay: 0.0500 (0.0500)  time: 1.0066  data: 0.0004  max mem: 78493
Epoch: [2]  [240/312]  eta: 0:01:17  lr: 0.000554  min_lr: 0.000554  loss: 5.7904 (5.8478)  weight_decay: 0.0500 (0.0500)  time: 1.0077  data: 0.0004  max mem: 78493
Epoch: [2]  [250/312]  eta: 0:01:06  lr: 0.000560  min_lr: 0.000560  loss: 5.7118 (5.8421)  weight_decay: 0.0500 (0.0500)  time: 1.0081  data: 0.0004  max mem: 78493
Epoch: [2]  [260/312]  eta: 0:00:56  lr: 0.000567  min_lr: 0.000567  loss: 5.6395 (5.8314)  weight_decay: 0.0500 (0.0500)  time: 1.0069  data: 0.0004  max mem: 78493
Epoch: [2]  [270/312]  eta: 0:00:45  lr: 0.000573  min_lr: 0.000573  loss: 5.6339 (5.8243)  weight_decay: 0.0500 (0.0500)  time: 1.0071  data: 0.0004  max mem: 78493
Epoch: [2]  [280/312]  eta: 0:00:34  lr: 0.000580  min_lr: 0.000580  loss: 5.7122 (5.8193)  weight_decay: 0.0500 (0.0500)  time: 1.0074  data: 0.0010  max mem: 78493
Epoch: [2]  [290/312]  eta: 0:00:23  lr: 0.000586  min_lr: 0.000586  loss: 5.7122 (5.8121)  weight_decay: 0.0500 (0.0500)  time: 1.0048  data: 0.0009  max mem: 78493
Epoch: [2]  [300/312]  eta: 0:00:12  lr: 0.000592  min_lr: 0.000592  loss: 5.7744 (5.8105)  weight_decay: 0.0500 (0.0500)  time: 1.0028  data: 0.0001  max mem: 78493
Epoch: [2]  [310/312]  eta: 0:00:02  lr: 0.000599  min_lr: 0.000599  loss: 5.7362 (5.8038)  weight_decay: 0.0500 (0.0500)  time: 1.0021  data: 0.0001  max mem: 78493
Epoch: [2]  [311/312]  eta: 0:00:01  lr: 0.000599  min_lr: 0.000599  loss: 5.7073 (5.8016)  weight_decay: 0.0500 (0.0500)  time: 1.0020  data: 0.0001  max mem: 78493
Epoch: [2] Total time: 0:05:34 (1.0712 s / it)
Averaged stats: lr: 0.000599  min_lr: 0.000599  loss: 5.7073 (5.8178)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:12  loss: 4.2717 (4.2717)  acc1: 18.6198 (18.6198)  acc5: 39.4531 (39.4531)  time: 8.1109  data: 7.8313  max mem: 78493
Test:  [8/9]  eta: 0:00:01  loss: 4.3471 (4.3645)  acc1: 16.5365 (15.4720)  acc5: 37.8906 (35.0560)  time: 1.0994  data: 0.8702  max mem: 78493
Test: Total time: 0:00:10 (1.1386 s / it)
* Acc@1 15.068 Acc@5 34.664 loss 4.347
Accuracy of the model on the 50000 test images: 15.1%
Max accuracy: 15.07%
Epoch: [3]  [  0/312]  eta: 1:30:04  lr: 0.000600  min_lr: 0.000600  loss: 6.0010 (6.0010)  weight_decay: 0.0500 (0.0500)  time: 17.3206  data: 16.2931  max mem: 78493
Epoch: [3]  [ 10/312]  eta: 0:13:22  lr: 0.000607  min_lr: 0.000607  loss: 5.5477 (5.5151)  weight_decay: 0.0500 (0.0500)  time: 2.6563  data: 1.4818  max mem: 78493
Epoch: [3]  [ 20/312]  eta: 0:09:06  lr: 0.000613  min_lr: 0.000613  loss: 5.4095 (5.4983)  weight_decay: 0.0500 (0.0500)  time: 1.0982  data: 0.0006  max mem: 78493
Epoch: [3]  [ 30/312]  eta: 0:07:29  lr: 0.000619  min_lr: 0.000619  loss: 5.5820 (5.5474)  weight_decay: 0.0500 (0.0500)  time: 1.0075  data: 0.0005  max mem: 78493
Epoch: [3]  [ 40/312]  eta: 0:06:34  lr: 0.000626  min_lr: 0.000626  loss: 5.7375 (5.5777)  weight_decay: 0.0500 (0.0500)  time: 1.0061  data: 0.0004  max mem: 78493
Epoch: [3]  [ 50/312]  eta: 0:05:56  lr: 0.000632  min_lr: 0.000632  loss: 5.7751 (5.5727)  weight_decay: 0.0500 (0.0500)  time: 1.0043  data: 0.0004  max mem: 78493
Epoch: [3]  [ 60/312]  eta: 0:05:28  lr: 0.000639  min_lr: 0.000639  loss: 5.6659 (5.5582)  weight_decay: 0.0500 (0.0500)  time: 1.0063  data: 0.0004  max mem: 78493
Epoch: [3]  [ 70/312]  eta: 0:05:05  lr: 0.000645  min_lr: 0.000645  loss: 5.5724 (5.5532)  weight_decay: 0.0500 (0.0500)  time: 1.0080  data: 0.0004  max mem: 78493
Epoch: [3]  [ 80/312]  eta: 0:04:45  lr: 0.000651  min_lr: 0.000651  loss: 5.5840 (5.5579)  weight_decay: 0.0500 (0.0500)  time: 1.0081  data: 0.0004  max mem: 78493
Epoch: [3]  [ 90/312]  eta: 0:04:27  lr: 0.000658  min_lr: 0.000658  loss: 5.5673 (5.5374)  weight_decay: 0.0500 (0.0500)  time: 1.0094  data: 0.0004  max mem: 78493
Epoch: [3]  [100/312]  eta: 0:04:11  lr: 0.000664  min_lr: 0.000664  loss: 5.4850 (5.5322)  weight_decay: 0.0500 (0.0500)  time: 1.0103  data: 0.0005  max mem: 78493
Epoch: [3]  [110/312]  eta: 0:03:56  lr: 0.000671  min_lr: 0.000671  loss: 5.5462 (5.5277)  weight_decay: 0.0500 (0.0500)  time: 1.0084  data: 0.0005  max mem: 78493
Epoch: [3]  [120/312]  eta: 0:03:42  lr: 0.000677  min_lr: 0.000677  loss: 5.6016 (5.5364)  weight_decay: 0.0500 (0.0500)  time: 1.0076  data: 0.0004  max mem: 78493
Epoch: [3]  [130/312]  eta: 0:03:28  lr: 0.000683  min_lr: 0.000683  loss: 5.5723 (5.5279)  weight_decay: 0.0500 (0.0500)  time: 1.0066  data: 0.0004  max mem: 78493
Epoch: [3]  [140/312]  eta: 0:03:15  lr: 0.000690  min_lr: 0.000690  loss: 5.4397 (5.5157)  weight_decay: 0.0500 (0.0500)  time: 1.0080  data: 0.0005  max mem: 78493
Epoch: [3]  [150/312]  eta: 0:03:02  lr: 0.000696  min_lr: 0.000696  loss: 5.3108 (5.5070)  weight_decay: 0.0500 (0.0500)  time: 1.0097  data: 0.0005  max mem: 78493
Epoch: [3]  [160/312]  eta: 0:02:50  lr: 0.000703  min_lr: 0.000703  loss: 5.4618 (5.4990)  weight_decay: 0.0500 (0.0500)  time: 1.0080  data: 0.0005  max mem: 78493
Epoch: [3]  [170/312]  eta: 0:02:38  lr: 0.000709  min_lr: 0.000709  loss: 5.5432 (5.4958)  weight_decay: 0.0500 (0.0500)  time: 1.0084  data: 0.0004  max mem: 78493
Epoch: [3]  [180/312]  eta: 0:02:26  lr: 0.000715  min_lr: 0.000715  loss: 5.6011 (5.4951)  weight_decay: 0.0500 (0.0500)  time: 1.0090  data: 0.0004  max mem: 78493
Epoch: [3]  [190/312]  eta: 0:02:14  lr: 0.000722  min_lr: 0.000722  loss: 5.5045 (5.4918)  weight_decay: 0.0500 (0.0500)  time: 1.0116  data: 0.0017  max mem: 78493
Epoch: [3]  [200/312]  eta: 0:02:03  lr: 0.000728  min_lr: 0.000728  loss: 5.3959 (5.4853)  weight_decay: 0.0500 (0.0500)  time: 1.0117  data: 0.0024  max mem: 78493
Epoch: [3]  [210/312]  eta: 0:01:51  lr: 0.000735  min_lr: 0.000735  loss: 5.4811 (5.4828)  weight_decay: 0.0500 (0.0500)  time: 1.0077  data: 0.0011  max mem: 78493
Epoch: [3]  [220/312]  eta: 0:01:40  lr: 0.000741  min_lr: 0.000741  loss: 5.4811 (5.4770)  weight_decay: 0.0500 (0.0500)  time: 1.0058  data: 0.0005  max mem: 78493
Epoch: [3]  [230/312]  eta: 0:01:29  lr: 0.000748  min_lr: 0.000748  loss: 5.3508 (5.4660)  weight_decay: 0.0500 (0.0500)  time: 1.0056  data: 0.0005  max mem: 78493
Epoch: [3]  [240/312]  eta: 0:01:17  lr: 0.000754  min_lr: 0.000754  loss: 5.4670 (5.4689)  weight_decay: 0.0500 (0.0500)  time: 1.0061  data: 0.0004  max mem: 78493
Epoch: [3]  [250/312]  eta: 0:01:06  lr: 0.000760  min_lr: 0.000760  loss: 5.5833 (5.4727)  weight_decay: 0.0500 (0.0500)  time: 1.0060  data: 0.0004  max mem: 78493
Epoch: [3]  [260/312]  eta: 0:00:56  lr: 0.000767  min_lr: 0.000767  loss: 5.3901 (5.4622)  weight_decay: 0.0500 (0.0500)  time: 1.0062  data: 0.0004  max mem: 78493
Epoch: [3]  [270/312]  eta: 0:00:45  lr: 0.000773  min_lr: 0.000773  loss: 5.3079 (5.4603)  weight_decay: 0.0500 (0.0500)  time: 1.0055  data: 0.0004  max mem: 78493
Epoch: [3]  [280/312]  eta: 0:00:34  lr: 0.000780  min_lr: 0.000780  loss: 5.4614 (5.4528)  weight_decay: 0.0500 (0.0500)  time: 1.0054  data: 0.0011  max mem: 78493
Epoch: [3]  [290/312]  eta: 0:00:23  lr: 0.000786  min_lr: 0.000786  loss: 5.2170 (5.4438)  weight_decay: 0.0500 (0.0500)  time: 1.0039  data: 0.0009  max mem: 78493
Epoch: [3]  [300/312]  eta: 0:00:12  lr: 0.000792  min_lr: 0.000792  loss: 5.1517 (5.4368)  weight_decay: 0.0500 (0.0500)  time: 1.0018  data: 0.0001  max mem: 78493
Epoch: [3]  [310/312]  eta: 0:00:02  lr: 0.000799  min_lr: 0.000799  loss: 5.3541 (5.4320)  weight_decay: 0.0500 (0.0500)  time: 1.0018  data: 0.0001  max mem: 78493
Epoch: [3]  [311/312]  eta: 0:00:01  lr: 0.000799  min_lr: 0.000799  loss: 5.3541 (5.4304)  weight_decay: 0.0500 (0.0500)  time: 1.0018  data: 0.0001  max mem: 78493
Epoch: [3] Total time: 0:05:34 (1.0709 s / it)
Averaged stats: lr: 0.000799  min_lr: 0.000799  loss: 5.3541 (5.4102)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:12  loss: 3.5083 (3.5083)  acc1: 29.0365 (29.0365)  acc5: 52.4740 (52.4740)  time: 8.0639  data: 7.7656  max mem: 78493
Test:  [8/9]  eta: 0:00:01  loss: 3.6509 (3.6137)  acc1: 25.6510 (24.8960)  acc5: 52.4740 (48.3840)  time: 1.0941  data: 0.8629  max mem: 78493
Test: Total time: 0:00:09 (1.1097 s / it)
* Acc@1 24.812 Acc@5 48.346 loss 3.607
Accuracy of the model on the 50000 test images: 24.8%
Max accuracy: 24.81%
Epoch: [4]  [  0/312]  eta: 1:16:33  lr: 0.000800  min_lr: 0.000800  loss: 4.5190 (4.5190)  weight_decay: 0.0500 (0.0500)  time: 14.7214  data: 13.3982  max mem: 78493
Epoch: [4]  [ 10/312]  eta: 0:12:52  lr: 0.000807  min_lr: 0.000807  loss: 5.2817 (5.1463)  weight_decay: 0.0500 (0.0500)  time: 2.5564  data: 1.2187  max mem: 78493
Epoch: [4]  [ 20/312]  eta: 0:08:51  lr: 0.000813  min_lr: 0.000813  loss: 5.3640 (5.2378)  weight_decay: 0.0500 (0.0500)  time: 1.1753  data: 0.0018  max mem: 78493
Epoch: [4]  [ 30/312]  eta: 0:07:19  lr: 0.000819  min_lr: 0.000819  loss: 5.4008 (5.2467)  weight_decay: 0.0500 (0.0500)  time: 1.0083  data: 0.0017  max mem: 78493
Epoch: [4]  [ 40/312]  eta: 0:06:27  lr: 0.000826  min_lr: 0.000826  loss: 5.4008 (5.2723)  weight_decay: 0.0500 (0.0500)  time: 1.0062  data: 0.0011  max mem: 78493
Epoch: [4]  [ 50/312]  eta: 0:05:51  lr: 0.000832  min_lr: 0.000832  loss: 5.3251 (5.2549)  weight_decay: 0.0500 (0.0500)  time: 1.0059  data: 0.0012  max mem: 78493
Epoch: [4]  [ 60/312]  eta: 0:05:24  lr: 0.000839  min_lr: 0.000839  loss: 5.0774 (5.2299)  weight_decay: 0.0500 (0.0500)  time: 1.0073  data: 0.0004  max mem: 78493
Epoch: [4]  [ 70/312]  eta: 0:05:01  lr: 0.000845  min_lr: 0.000845  loss: 4.9339 (5.1947)  weight_decay: 0.0500 (0.0500)  time: 1.0074  data: 0.0005  max mem: 78493
Epoch: [4]  [ 80/312]  eta: 0:04:42  lr: 0.000851  min_lr: 0.000851  loss: 5.0068 (5.1852)  weight_decay: 0.0500 (0.0500)  time: 1.0067  data: 0.0005  max mem: 78493
Epoch: [4]  [ 90/312]  eta: 0:04:25  lr: 0.000858  min_lr: 0.000858  loss: 5.2674 (5.1883)  weight_decay: 0.0500 (0.0500)  time: 1.0070  data: 0.0005  max mem: 78493
Epoch: [4]  [100/312]  eta: 0:04:09  lr: 0.000864  min_lr: 0.000864  loss: 5.2336 (5.1872)  weight_decay: 0.0500 (0.0500)  time: 1.0054  data: 0.0005  max mem: 78493
Epoch: [4]  [110/312]  eta: 0:03:54  lr: 0.000871  min_lr: 0.000871  loss: 5.2781 (5.1953)  weight_decay: 0.0500 (0.0500)  time: 1.0054  data: 0.0004  max mem: 78493
Epoch: [4]  [120/312]  eta: 0:03:40  lr: 0.000877  min_lr: 0.000877  loss: 5.3410 (5.2066)  weight_decay: 0.0500 (0.0500)  time: 1.0076  data: 0.0004  max mem: 78493
Epoch: [4]  [130/312]  eta: 0:03:26  lr: 0.000883  min_lr: 0.000883  loss: 5.3007 (5.2107)  weight_decay: 0.0500 (0.0500)  time: 1.0081  data: 0.0004  max mem: 78493
Epoch: [4]  [140/312]  eta: 0:03:14  lr: 0.000890  min_lr: 0.000890  loss: 5.2854 (5.2062)  weight_decay: 0.0500 (0.0500)  time: 1.0078  data: 0.0004  max mem: 78493
Epoch: [4]  [150/312]  eta: 0:03:01  lr: 0.000896  min_lr: 0.000896  loss: 5.0441 (5.1971)  weight_decay: 0.0500 (0.0500)  time: 1.0067  data: 0.0004  max mem: 78493
Epoch: [4]  [160/312]  eta: 0:02:49  lr: 0.000903  min_lr: 0.000903  loss: 5.0441 (5.1965)  weight_decay: 0.0500 (0.0500)  time: 1.0048  data: 0.0004  max mem: 78493
Epoch: [4]  [170/312]  eta: 0:02:37  lr: 0.000909  min_lr: 0.000909  loss: 5.1884 (5.1886)  weight_decay: 0.0500 (0.0500)  time: 1.0048  data: 0.0005  max mem: 78493
Epoch: [4]  [180/312]  eta: 0:02:25  lr: 0.000916  min_lr: 0.000916  loss: 4.9418 (5.1781)  weight_decay: 0.0500 (0.0500)  time: 1.0056  data: 0.0004  max mem: 78493
Epoch: [4]  [190/312]  eta: 0:02:13  lr: 0.000922  min_lr: 0.000922  loss: 4.9730 (5.1707)  weight_decay: 0.0500 (0.0500)  time: 1.0077  data: 0.0004  max mem: 78493
Epoch: [4]  [200/312]  eta: 0:02:02  lr: 0.000928  min_lr: 0.000928  loss: 5.1726 (5.1675)  weight_decay: 0.0500 (0.0500)  time: 1.0084  data: 0.0004  max mem: 78493
Epoch: [4]  [210/312]  eta: 0:01:50  lr: 0.000935  min_lr: 0.000935  loss: 5.2182 (5.1623)  weight_decay: 0.0500 (0.0500)  time: 1.0059  data: 0.0004  max mem: 78493
Epoch: [4]  [220/312]  eta: 0:01:39  lr: 0.000941  min_lr: 0.000941  loss: 5.2182 (5.1607)  weight_decay: 0.0500 (0.0500)  time: 1.0057  data: 0.0004  max mem: 78493
Epoch: [4]  [230/312]  eta: 0:01:28  lr: 0.000948  min_lr: 0.000948  loss: 5.1789 (5.1468)  weight_decay: 0.0500 (0.0500)  time: 1.0076  data: 0.0004  max mem: 78493
Epoch: [4]  [240/312]  eta: 0:01:17  lr: 0.000954  min_lr: 0.000954  loss: 4.5739 (5.1258)  weight_decay: 0.0500 (0.0500)  time: 1.0072  data: 0.0004  max mem: 78493
Epoch: [4]  [250/312]  eta: 0:01:06  lr: 0.000960  min_lr: 0.000960  loss: 4.5763 (5.1093)  weight_decay: 0.0500 (0.0500)  time: 1.0076  data: 0.0004  max mem: 78493
Epoch: [4]  [260/312]  eta: 0:00:55  lr: 0.000967  min_lr: 0.000967  loss: 4.9014 (5.1146)  weight_decay: 0.0500 (0.0500)  time: 1.0070  data: 0.0004  max mem: 78493
Epoch: [4]  [270/312]  eta: 0:00:44  lr: 0.000973  min_lr: 0.000973  loss: 5.1933 (5.1123)  weight_decay: 0.0500 (0.0500)  time: 1.0044  data: 0.0005  max mem: 78493
Epoch: [4]  [280/312]  eta: 0:00:34  lr: 0.000980  min_lr: 0.000980  loss: 5.0087 (5.1053)  weight_decay: 0.0500 (0.0500)  time: 1.0069  data: 0.0011  max mem: 78493
Epoch: [4]  [290/312]  eta: 0:00:23  lr: 0.000986  min_lr: 0.000986  loss: 4.9738 (5.1019)  weight_decay: 0.0500 (0.0500)  time: 1.0056  data: 0.0009  max mem: 78493
Epoch: [4]  [300/312]  eta: 0:00:12  lr: 0.000992  min_lr: 0.000992  loss: 4.7853 (5.0910)  weight_decay: 0.0500 (0.0500)  time: 1.0012  data: 0.0001  max mem: 78493
Epoch: [4]  [310/312]  eta: 0:00:02  lr: 0.000999  min_lr: 0.000999  loss: 4.9312 (5.0884)  weight_decay: 0.0500 (0.0500)  time: 1.0014  data: 0.0001  max mem: 78493
Epoch: [4]  [311/312]  eta: 0:00:01  lr: 0.001000  min_lr: 0.001000  loss: 4.7997 (5.0865)  weight_decay: 0.0500 (0.0500)  time: 1.0014  data: 0.0001  max mem: 78493
Epoch: [4] Total time: 0:05:32 (1.0665 s / it)
Averaged stats: lr: 0.001000  min_lr: 0.001000  loss: 4.7997 (5.0582)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:16  loss: 2.7935 (2.7935)  acc1: 40.6250 (40.6250)  acc5: 65.4948 (65.4948)  time: 8.4986  data: 8.2084  max mem: 78493
Test:  [8/9]  eta: 0:00:01  loss: 3.2910 (3.0974)  acc1: 31.2500 (32.2560)  acc5: 57.4219 (57.7280)  time: 1.1426  data: 0.9122  max mem: 78493
Test: Total time: 0:00:10 (1.1643 s / it)
* Acc@1 32.690 Acc@5 58.270 loss 3.087
Accuracy of the model on the 50000 test images: 32.7%
Max accuracy: 32.69%
Epoch: [5]  [  0/312]  eta: 1:18:27  lr: 0.001000  min_lr: 0.001000  loss: 4.0902 (4.0902)  weight_decay: 0.0500 (0.0500)  time: 15.0890  data: 13.4794  max mem: 78493
Epoch: [5]  [ 10/312]  eta: 0:12:27  lr: 0.001007  min_lr: 0.001007  loss: 4.4882 (4.5980)  weight_decay: 0.0500 (0.0500)  time: 2.4765  data: 1.2262  max mem: 78493
Epoch: [5]  [ 20/312]  eta: 0:08:46  lr: 0.001013  min_lr: 0.001013  loss: 4.6226 (4.6946)  weight_decay: 0.0500 (0.0500)  time: 1.1403  data: 0.0058  max mem: 78493
Epoch: [5]  [ 30/312]  eta: 0:07:16  lr: 0.001019  min_lr: 0.001019  loss: 4.9219 (4.7620)  weight_decay: 0.0500 (0.0500)  time: 1.0376  data: 0.0078  max mem: 78493
Epoch: [5]  [ 40/312]  eta: 0:06:25  lr: 0.001026  min_lr: 0.001026  loss: 5.0091 (4.8420)  weight_decay: 0.0500 (0.0500)  time: 1.0096  data: 0.0042  max mem: 78493
Epoch: [5]  [ 50/312]  eta: 0:05:50  lr: 0.001032  min_lr: 0.001032  loss: 5.0444 (4.8667)  weight_decay: 0.0500 (0.0500)  time: 1.0097  data: 0.0019  max mem: 78493
Epoch: [5]  [ 60/312]  eta: 0:05:23  lr: 0.001039  min_lr: 0.001039  loss: 4.8395 (4.8441)  weight_decay: 0.0500 (0.0500)  time: 1.0086  data: 0.0004  max mem: 78493
Epoch: [5]  [ 70/312]  eta: 0:05:00  lr: 0.001045  min_lr: 0.001045  loss: 4.8007 (4.8586)  weight_decay: 0.0500 (0.0500)  time: 1.0055  data: 0.0004  max mem: 78493
Epoch: [5]  [ 80/312]  eta: 0:04:41  lr: 0.001051  min_lr: 0.001051  loss: 4.9281 (4.8569)  weight_decay: 0.0500 (0.0500)  time: 1.0043  data: 0.0004  max mem: 78493
Epoch: [5]  [ 90/312]  eta: 0:04:24  lr: 0.001058  min_lr: 0.001058  loss: 4.5965 (4.8113)  weight_decay: 0.0500 (0.0500)  time: 1.0046  data: 0.0004  max mem: 78493
Epoch: [5]  [100/312]  eta: 0:04:08  lr: 0.001064  min_lr: 0.001064  loss: 4.3999 (4.7840)  weight_decay: 0.0500 (0.0500)  time: 1.0046  data: 0.0004  max mem: 78493
Epoch: [5]  [110/312]  eta: 0:03:53  lr: 0.001071  min_lr: 0.001071  loss: 4.6801 (4.7867)  weight_decay: 0.0500 (0.0500)  time: 1.0042  data: 0.0005  max mem: 78493
Epoch: [5]  [120/312]  eta: 0:03:39  lr: 0.001077  min_lr: 0.001077  loss: 4.9968 (4.7885)  weight_decay: 0.0500 (0.0500)  time: 1.0037  data: 0.0005  max mem: 78493
Epoch: [5]  [130/312]  eta: 0:03:26  lr: 0.001084  min_lr: 0.001084  loss: 4.9968 (4.7867)  weight_decay: 0.0500 (0.0500)  time: 1.0044  data: 0.0005  max mem: 78493
Epoch: [5]  [140/312]  eta: 0:03:13  lr: 0.001090  min_lr: 0.001090  loss: 5.0058 (4.8048)  weight_decay: 0.0500 (0.0500)  time: 1.0050  data: 0.0005  max mem: 78493
Epoch: [5]  [150/312]  eta: 0:03:00  lr: 0.001096  min_lr: 0.001096  loss: 4.8419 (4.7914)  weight_decay: 0.0500 (0.0500)  time: 1.0058  data: 0.0005  max mem: 78493
Epoch: [5]  [160/312]  eta: 0:02:48  lr: 0.001103  min_lr: 0.001103  loss: 4.5201 (4.7811)  weight_decay: 0.0500 (0.0500)  time: 1.0060  data: 0.0004  max mem: 78493
Epoch: [5]  [170/312]  eta: 0:02:36  lr: 0.001109  min_lr: 0.001109  loss: 5.0307 (4.7914)  weight_decay: 0.0500 (0.0500)  time: 1.0057  data: 0.0011  max mem: 78493
Epoch: [5]  [180/312]  eta: 0:02:25  lr: 0.001116  min_lr: 0.001116  loss: 5.0307 (4.7851)  weight_decay: 0.0500 (0.0500)  time: 1.0059  data: 0.0010  max mem: 78493
Epoch: [5]  [190/312]  eta: 0:02:13  lr: 0.001122  min_lr: 0.001122  loss: 4.4794 (4.7754)  weight_decay: 0.0500 (0.0500)  time: 1.0048  data: 0.0004  max mem: 78493
Epoch: [5]  [200/312]  eta: 0:02:01  lr: 0.001128  min_lr: 0.001128  loss: 4.4726 (4.7705)  weight_decay: 0.0500 (0.0500)  time: 1.0043  data: 0.0005  max mem: 78493
Epoch: [5]  [210/312]  eta: 0:01:50  lr: 0.001135  min_lr: 0.001135  loss: 4.8904 (4.7735)  weight_decay: 0.0500 (0.0500)  time: 1.0049  data: 0.0005  max mem: 78493
Epoch: [5]  [220/312]  eta: 0:01:39  lr: 0.001141  min_lr: 0.001141  loss: 4.9789 (4.7754)  weight_decay: 0.0500 (0.0500)  time: 1.0041  data: 0.0005  max mem: 78493
Epoch: [5]  [230/312]  eta: 0:01:28  lr: 0.001148  min_lr: 0.001148  loss: 4.8432 (4.7677)  weight_decay: 0.0500 (0.0500)  time: 1.0043  data: 0.0005  max mem: 78493
Epoch: [5]  [240/312]  eta: 0:01:17  lr: 0.001154  min_lr: 0.001154  loss: 4.8432 (4.7723)  weight_decay: 0.0500 (0.0500)  time: 1.0058  data: 0.0005  max mem: 78493
Epoch: [5]  [250/312]  eta: 0:01:06  lr: 0.001160  min_lr: 0.001160  loss: 4.9297 (4.7658)  weight_decay: 0.0500 (0.0500)  time: 1.0058  data: 0.0004  max mem: 78493
Epoch: [5]  [260/312]  eta: 0:00:55  lr: 0.001167  min_lr: 0.001167  loss: 4.6223 (4.7649)  weight_decay: 0.0500 (0.0500)  time: 1.0053  data: 0.0004  max mem: 78493
Epoch: [5]  [270/312]  eta: 0:00:44  lr: 0.001173  min_lr: 0.001173  loss: 4.8518 (4.7667)  weight_decay: 0.0500 (0.0500)  time: 1.0052  data: 0.0004  max mem: 78493
Epoch: [5]  [280/312]  eta: 0:00:34  lr: 0.001180  min_lr: 0.001180  loss: 4.8291 (4.7627)  weight_decay: 0.0500 (0.0500)  time: 1.0049  data: 0.0011  max mem: 78493
Epoch: [5]  [290/312]  eta: 0:00:23  lr: 0.001186  min_lr: 0.001186  loss: 4.6752 (4.7535)  weight_decay: 0.0500 (0.0500)  time: 1.0032  data: 0.0009  max mem: 78493
Epoch: [5]  [300/312]  eta: 0:00:12  lr: 0.001192  min_lr: 0.001192  loss: 4.6262 (4.7505)  weight_decay: 0.0500 (0.0500)  time: 1.0015  data: 0.0001  max mem: 78493
Epoch: [5]  [310/312]  eta: 0:00:02  lr: 0.001199  min_lr: 0.001199  loss: 4.7052 (4.7430)  weight_decay: 0.0500 (0.0500)  time: 1.0015  data: 0.0001  max mem: 78493
Epoch: [5]  [311/312]  eta: 0:00:01  lr: 0.001200  min_lr: 0.001200  loss: 4.7052 (4.7416)  weight_decay: 0.0500 (0.0500)  time: 1.0015  data: 0.0001  max mem: 78493
Epoch: [5] Total time: 0:05:32 (1.0648 s / it)
Averaged stats: lr: 0.001200  min_lr: 0.001200  loss: 4.7052 (4.7576)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:11  loss: 2.5966 (2.5966)  acc1: 43.8802 (43.8802)  acc5: 67.7083 (67.7083)  time: 7.8916  data: 7.6296  max mem: 78493
Test:  [8/9]  eta: 0:00:01  loss: 3.0780 (2.8402)  acc1: 36.7188 (36.8640)  acc5: 59.8958 (62.1120)  time: 1.0801  data: 0.8478  max mem: 78493
Test: Total time: 0:00:10 (1.1158 s / it)
* Acc@1 37.160 Acc@5 62.376 loss 2.833
Accuracy of the model on the 50000 test images: 37.2%
Max accuracy: 37.16%
Epoch: [6]  [  0/312]  eta: 1:22:39  lr: 0.001200  min_lr: 0.001200  loss: 5.0819 (5.0819)  weight_decay: 0.0500 (0.0500)  time: 15.8968  data: 13.7542  max mem: 78493
Epoch: [6]  [ 10/312]  eta: 0:13:24  lr: 0.001207  min_lr: 0.001207  loss: 4.9047 (4.7815)  weight_decay: 0.0500 (0.0500)  time: 2.6624  data: 1.2629  max mem: 78493
Epoch: [6]  [ 20/312]  eta: 0:09:08  lr: 0.001213  min_lr: 0.001213  loss: 4.8221 (4.6669)  weight_decay: 0.0500 (0.0500)  time: 1.1769  data: 0.0071  max mem: 78493
Epoch: [6]  [ 30/312]  eta: 0:07:30  lr: 0.001219  min_lr: 0.001219  loss: 4.4698 (4.6251)  weight_decay: 0.0500 (0.0500)  time: 1.0112  data: 0.0005  max mem: 78493
Epoch: [6]  [ 40/312]  eta: 0:06:35  lr: 0.001226  min_lr: 0.001226  loss: 4.5015 (4.6338)  weight_decay: 0.0500 (0.0500)  time: 1.0059  data: 0.0005  max mem: 78493
Epoch: [6]  [ 50/312]  eta: 0:05:57  lr: 0.001232  min_lr: 0.001232  loss: 4.3847 (4.5586)  weight_decay: 0.0500 (0.0500)  time: 1.0047  data: 0.0005  max mem: 78493
Epoch: [6]  [ 60/312]  eta: 0:05:29  lr: 0.001239  min_lr: 0.001239  loss: 4.1937 (4.5254)  weight_decay: 0.0500 (0.0500)  time: 1.0060  data: 0.0004  max mem: 78493
Epoch: [6]  [ 70/312]  eta: 0:05:05  lr: 0.001245  min_lr: 0.001245  loss: 4.4182 (4.5253)  weight_decay: 0.0500 (0.0500)  time: 1.0073  data: 0.0005  max mem: 78493
Epoch: [6]  [ 80/312]  eta: 0:04:45  lr: 0.001251  min_lr: 0.001251  loss: 4.5508 (4.5090)  weight_decay: 0.0500 (0.0500)  time: 1.0065  data: 0.0005  max mem: 78493
Epoch: [6]  [ 90/312]  eta: 0:04:28  lr: 0.001258  min_lr: 0.001258  loss: 4.4244 (4.5131)  weight_decay: 0.0500 (0.0500)  time: 1.0066  data: 0.0012  max mem: 78493
Epoch: [6]  [100/312]  eta: 0:04:11  lr: 0.001264  min_lr: 0.001264  loss: 4.4244 (4.5004)  weight_decay: 0.0500 (0.0500)  time: 1.0075  data: 0.0012  max mem: 78493
Epoch: [6]  [110/312]  eta: 0:03:56  lr: 0.001271  min_lr: 0.001271  loss: 4.4480 (4.4977)  weight_decay: 0.0500 (0.0500)  time: 1.0076  data: 0.0004  max mem: 78493
Epoch: [6]  [120/312]  eta: 0:03:42  lr: 0.001277  min_lr: 0.001277  loss: 4.4480 (4.4903)  weight_decay: 0.0500 (0.0500)  time: 1.0074  data: 0.0004  max mem: 78493
Epoch: [6]  [130/312]  eta: 0:03:28  lr: 0.001284  min_lr: 0.001284  loss: 4.5048 (4.4862)  weight_decay: 0.0500 (0.0500)  time: 1.0080  data: 0.0004  max mem: 78493
Epoch: [6]  [140/312]  eta: 0:03:15  lr: 0.001290  min_lr: 0.001290  loss: 4.6230 (4.5003)  weight_decay: 0.0500 (0.0500)  time: 1.0074  data: 0.0005  max mem: 78493
Epoch: [6]  [150/312]  eta: 0:03:02  lr: 0.001296  min_lr: 0.001296  loss: 4.7068 (4.5074)  weight_decay: 0.0500 (0.0500)  time: 1.0058  data: 0.0004  max mem: 78493
Epoch: [6]  [160/312]  eta: 0:02:50  lr: 0.001303  min_lr: 0.001303  loss: 4.8679 (4.5224)  weight_decay: 0.0500 (0.0500)  time: 1.0075  data: 0.0004  max mem: 78493
Epoch: [6]  [170/312]  eta: 0:02:38  lr: 0.001309  min_lr: 0.001309  loss: 4.8531 (4.5239)  weight_decay: 0.0500 (0.0500)  time: 1.0071  data: 0.0005  max mem: 78493
Epoch: [6]  [180/312]  eta: 0:02:26  lr: 0.001316  min_lr: 0.001316  loss: 4.4079 (4.5177)  weight_decay: 0.0500 (0.0500)  time: 1.0084  data: 0.0004  max mem: 78493
Epoch: [6]  [190/312]  eta: 0:02:14  lr: 0.001322  min_lr: 0.001322  loss: 4.2944 (4.5040)  weight_decay: 0.0500 (0.0500)  time: 1.0112  data: 0.0004  max mem: 78493
Epoch: [6]  [200/312]  eta: 0:02:03  lr: 0.001328  min_lr: 0.001328  loss: 4.5411 (4.5131)  weight_decay: 0.0500 (0.0500)  time: 1.0097  data: 0.0004  max mem: 78493
Epoch: [6]  [210/312]  eta: 0:01:51  lr: 0.001335  min_lr: 0.001335  loss: 4.5411 (4.5008)  weight_decay: 0.0500 (0.0500)  time: 1.0076  data: 0.0005  max mem: 78493
Epoch: [6]  [220/312]  eta: 0:01:40  lr: 0.001341  min_lr: 0.001341  loss: 4.6330 (4.5128)  weight_decay: 0.0500 (0.0500)  time: 1.0072  data: 0.0004  max mem: 78493
Epoch: [6]  [230/312]  eta: 0:01:29  lr: 0.001348  min_lr: 0.001348  loss: 4.7043 (4.5039)  weight_decay: 0.0500 (0.0500)  time: 1.0063  data: 0.0004  max mem: 78493
Epoch: [6]  [240/312]  eta: 0:01:17  lr: 0.001354  min_lr: 0.001354  loss: 4.2519 (4.5000)  weight_decay: 0.0500 (0.0500)  time: 1.0048  data: 0.0004  max mem: 78493
Epoch: [6]  [250/312]  eta: 0:01:06  lr: 0.001360  min_lr: 0.001360  loss: 4.5098 (4.5001)  weight_decay: 0.0500 (0.0500)  time: 1.0050  data: 0.0004  max mem: 78493
Epoch: [6]  [260/312]  eta: 0:00:56  lr: 0.001367  min_lr: 0.001367  loss: 4.5823 (4.5003)  weight_decay: 0.0500 (0.0500)  time: 1.0058  data: 0.0004  max mem: 78493
Epoch: [6]  [270/312]  eta: 0:00:45  lr: 0.001373  min_lr: 0.001373  loss: 4.6269 (4.5016)  weight_decay: 0.0500 (0.0500)  time: 1.0065  data: 0.0004  max mem: 78493
Epoch: [6]  [280/312]  eta: 0:00:34  lr: 0.001380  min_lr: 0.001380  loss: 4.5449 (4.4992)  weight_decay: 0.0500 (0.0500)  time: 1.0065  data: 0.0010  max mem: 78493
Epoch: [6]  [290/312]  eta: 0:00:23  lr: 0.001386  min_lr: 0.001386  loss: 4.6346 (4.5007)  weight_decay: 0.0500 (0.0500)  time: 1.0047  data: 0.0009  max mem: 78493
Epoch: [6]  [300/312]  eta: 0:00:12  lr: 0.001393  min_lr: 0.001393  loss: 4.6446 (4.4950)  weight_decay: 0.0500 (0.0500)  time: 1.0025  data: 0.0001  max mem: 78493
Epoch: [6]  [310/312]  eta: 0:00:02  lr: 0.001399  min_lr: 0.001399  loss: 4.3480 (4.4935)  weight_decay: 0.0500 (0.0500)  time: 1.0022  data: 0.0001  max mem: 78493
Epoch: [6]  [311/312]  eta: 0:00:01  lr: 0.001400  min_lr: 0.001400  loss: 4.3075 (4.4916)  weight_decay: 0.0500 (0.0500)  time: 1.0022  data: 0.0001  max mem: 78493
Epoch: [6] Total time: 0:05:34 (1.0708 s / it)
Averaged stats: lr: 0.001400  min_lr: 0.001400  loss: 4.3075 (4.4952)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:12  loss: 2.0453 (2.0453)  acc1: 51.8229 (51.8229)  acc5: 78.9062 (78.9062)  time: 8.1029  data: 7.8307  max mem: 78493
Test:  [8/9]  eta: 0:00:01  loss: 2.6439 (2.4161)  acc1: 43.2292 (43.9840)  acc5: 69.0104 (70.1920)  time: 1.0986  data: 0.8702  max mem: 78493
Test: Total time: 0:00:10 (1.1156 s / it)
* Acc@1 44.346 Acc@5 69.988 loss 2.435
Accuracy of the model on the 50000 test images: 44.3%
Max accuracy: 44.35%
Epoch: [7]  [  0/312]  eta: 1:20:50  lr: 0.001400  min_lr: 0.001400  loss: 4.7670 (4.7670)  weight_decay: 0.0500 (0.0500)  time: 15.5477  data: 12.7666  max mem: 78493
Epoch: [7]  [ 10/312]  eta: 0:12:06  lr: 0.001407  min_lr: 0.001407  loss: 4.7670 (4.5910)  weight_decay: 0.0500 (0.0500)  time: 2.4064  data: 1.1936  max mem: 78493
Epoch: [7]  [ 20/312]  eta: 0:08:36  lr: 0.001413  min_lr: 0.001413  loss: 4.4880 (4.4020)  weight_decay: 0.0500 (0.0500)  time: 1.0788  data: 0.0229  max mem: 78493
Epoch: [7]  [ 30/312]  eta: 0:07:09  lr: 0.001419  min_lr: 0.001419  loss: 4.2710 (4.4032)  weight_decay: 0.0500 (0.0500)  time: 1.0370  data: 0.0050  max mem: 78493
Epoch: [7]  [ 40/312]  eta: 0:06:19  lr: 0.001426  min_lr: 0.001426  loss: 4.2203 (4.3263)  weight_decay: 0.0500 (0.0500)  time: 1.0078  data: 0.0004  max mem: 78493
Epoch: [7]  [ 50/312]  eta: 0:05:46  lr: 0.001432  min_lr: 0.001432  loss: 4.1614 (4.2960)  weight_decay: 0.0500 (0.0500)  time: 1.0071  data: 0.0005  max mem: 78493
Epoch: [7]  [ 60/312]  eta: 0:05:20  lr: 0.001439  min_lr: 0.001439  loss: 4.1844 (4.2964)  weight_decay: 0.0500 (0.0500)  time: 1.0098  data: 0.0005  max mem: 78493
Epoch: [7]  [ 70/312]  eta: 0:04:58  lr: 0.001445  min_lr: 0.001445  loss: 4.1072 (4.2872)  weight_decay: 0.0500 (0.0500)  time: 1.0097  data: 0.0004  max mem: 78493
Epoch: [7]  [ 80/312]  eta: 0:04:39  lr: 0.001452  min_lr: 0.001452  loss: 4.2346 (4.3000)  weight_decay: 0.0500 (0.0500)  time: 1.0105  data: 0.0004  max mem: 78493
Epoch: [7]  [ 90/312]  eta: 0:04:22  lr: 0.001458  min_lr: 0.001458  loss: 4.5048 (4.3095)  weight_decay: 0.0500 (0.0500)  time: 1.0108  data: 0.0005  max mem: 78493
Epoch: [7]  [100/312]  eta: 0:04:07  lr: 0.001464  min_lr: 0.001464  loss: 4.4016 (4.2979)  weight_decay: 0.0500 (0.0500)  time: 1.0077  data: 0.0005  max mem: 78493
Epoch: [7]  [110/312]  eta: 0:03:52  lr: 0.001471  min_lr: 0.001471  loss: 4.2066 (4.2928)  weight_decay: 0.0500 (0.0500)  time: 1.0061  data: 0.0004  max mem: 78493
Epoch: [7]  [120/312]  eta: 0:03:38  lr: 0.001477  min_lr: 0.001477  loss: 4.4155 (4.2923)  weight_decay: 0.0500 (0.0500)  time: 1.0070  data: 0.0004  max mem: 78493
Epoch: [7]  [130/312]  eta: 0:03:25  lr: 0.001484  min_lr: 0.001484  loss: 4.4440 (4.2982)  weight_decay: 0.0500 (0.0500)  time: 1.0097  data: 0.0004  max mem: 78493
Epoch: [7]  [140/312]  eta: 0:03:12  lr: 0.001490  min_lr: 0.001490  loss: 4.5168 (4.3136)  weight_decay: 0.0500 (0.0500)  time: 1.0085  data: 0.0004  max mem: 78493
Epoch: [7]  [150/312]  eta: 0:03:00  lr: 0.001496  min_lr: 0.001496  loss: 4.5168 (4.3209)  weight_decay: 0.0500 (0.0500)  time: 1.0055  data: 0.0005  max mem: 78493
Epoch: [7]  [160/312]  eta: 0:02:48  lr: 0.001503  min_lr: 0.001503  loss: 4.3911 (4.3138)  weight_decay: 0.0500 (0.0500)  time: 1.0040  data: 0.0005  max mem: 78493
Epoch: [7]  [170/312]  eta: 0:02:36  lr: 0.001509  min_lr: 0.001509  loss: 4.3143 (4.3146)  weight_decay: 0.0500 (0.0500)  time: 1.0045  data: 0.0012  max mem: 78493
Epoch: [7]  [180/312]  eta: 0:02:24  lr: 0.001516  min_lr: 0.001516  loss: 4.2076 (4.3051)  weight_decay: 0.0500 (0.0500)  time: 1.0055  data: 0.0012  max mem: 78493
Epoch: [7]  [190/312]  eta: 0:02:13  lr: 0.001522  min_lr: 0.001522  loss: 4.2076 (4.2987)  weight_decay: 0.0500 (0.0500)  time: 1.0057  data: 0.0005  max mem: 78493
Epoch: [7]  [200/312]  eta: 0:02:01  lr: 0.001528  min_lr: 0.001528  loss: 4.4099 (4.3009)  weight_decay: 0.0500 (0.0500)  time: 1.0054  data: 0.0005  max mem: 78493
Epoch: [7]  [210/312]  eta: 0:01:50  lr: 0.001535  min_lr: 0.001535  loss: 4.1308 (4.2903)  weight_decay: 0.0500 (0.0500)  time: 1.0046  data: 0.0004  max mem: 78493
Epoch: [7]  [220/312]  eta: 0:01:39  lr: 0.001541  min_lr: 0.001541  loss: 4.1847 (4.2993)  weight_decay: 0.0500 (0.0500)  time: 1.0043  data: 0.0005  max mem: 78493
Epoch: [7]  [230/312]  eta: 0:01:28  lr: 0.001548  min_lr: 0.001548  loss: 4.5611 (4.2979)  weight_decay: 0.0500 (0.0500)  time: 1.0052  data: 0.0005  max mem: 78493
Epoch: [7]  [240/312]  eta: 0:01:17  lr: 0.001554  min_lr: 0.001554  loss: 4.0688 (4.2899)  weight_decay: 0.0500 (0.0500)  time: 1.0052  data: 0.0004  max mem: 78493
Epoch: [7]  [250/312]  eta: 0:01:06  lr: 0.001561  min_lr: 0.001561  loss: 4.2213 (4.2900)  weight_decay: 0.0500 (0.0500)  time: 1.0055  data: 0.0004  max mem: 78493
Epoch: [7]  [260/312]  eta: 0:00:55  lr: 0.001567  min_lr: 0.001567  loss: 4.3980 (4.2927)  weight_decay: 0.0500 (0.0500)  time: 1.0059  data: 0.0004  max mem: 78493
Epoch: [7]  [270/312]  eta: 0:00:44  lr: 0.001573  min_lr: 0.001573  loss: 4.5418 (4.2996)  weight_decay: 0.0500 (0.0500)  time: 1.0059  data: 0.0004  max mem: 78493
Epoch: [7]  [280/312]  eta: 0:00:34  lr: 0.001580  min_lr: 0.001580  loss: 4.1988 (4.2861)  weight_decay: 0.0500 (0.0500)  time: 1.0055  data: 0.0010  max mem: 78493
Epoch: [7]  [290/312]  eta: 0:00:23  lr: 0.001586  min_lr: 0.001586  loss: 3.9398 (4.2847)  weight_decay: 0.0500 (0.0500)  time: 1.0033  data: 0.0009  max mem: 78493
Epoch: [7]  [300/312]  eta: 0:00:12  lr: 0.001593  min_lr: 0.001593  loss: 4.1253 (4.2814)  weight_decay: 0.0500 (0.0500)  time: 1.0016  data: 0.0001  max mem: 78493
Epoch: [7]  [310/312]  eta: 0:00:02  lr: 0.001599  min_lr: 0.001599  loss: 4.1465 (4.2807)  weight_decay: 0.0500 (0.0500)  time: 1.0013  data: 0.0001  max mem: 78493
Epoch: [7]  [311/312]  eta: 0:00:01  lr: 0.001600  min_lr: 0.001600  loss: 4.1465 (4.2786)  weight_decay: 0.0500 (0.0500)  time: 1.0013  data: 0.0001  max mem: 78493
Epoch: [7] Total time: 0:05:31 (1.0634 s / it)
Averaged stats: lr: 0.001600  min_lr: 0.001600  loss: 4.1465 (4.2923)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:07  loss: 1.9391 (1.9391)  acc1: 56.9010 (56.9010)  acc5: 78.9062 (78.9062)  time: 7.5144  data: 7.2514  max mem: 78493
Test:  [8/9]  eta: 0:00:01  loss: 2.4346 (2.2629)  acc1: 47.5260 (49.4560)  acc5: 72.7865 (74.4000)  time: 1.0385  data: 0.8058  max mem: 78493
Test: Total time: 0:00:09 (1.0534 s / it)
* Acc@1 49.036 Acc@5 74.046 loss 2.268
Accuracy of the model on the 50000 test images: 49.0%
Max accuracy: 49.04%
Epoch: [8]  [  0/312]  eta: 1:20:56  lr: 0.001600  min_lr: 0.001600  loss: 3.8478 (3.8478)  weight_decay: 0.0500 (0.0500)  time: 15.5647  data: 12.2318  max mem: 78493
Epoch: [8]  [ 10/312]  eta: 0:13:12  lr: 0.001607  min_lr: 0.001607  loss: 3.8478 (4.0410)  weight_decay: 0.0500 (0.0500)  time: 2.6230  data: 1.2965  max mem: 78493
Epoch: [8]  [ 20/312]  eta: 0:09:02  lr: 0.001613  min_lr: 0.001613  loss: 4.0957 (4.1650)  weight_decay: 0.0500 (0.0500)  time: 1.1742  data: 0.1035  max mem: 78493
Epoch: [8]  [ 30/312]  eta: 0:07:27  lr: 0.001619  min_lr: 0.001619  loss: 4.4512 (4.2431)  weight_decay: 0.0500 (0.0500)  time: 1.0154  data: 0.0022  max mem: 78493
Epoch: [8]  [ 40/312]  eta: 0:06:33  lr: 0.001626  min_lr: 0.001626  loss: 4.4512 (4.2534)  weight_decay: 0.0500 (0.0500)  time: 1.0118  data: 0.0004  max mem: 78493
Epoch: [8]  [ 50/312]  eta: 0:05:56  lr: 0.001632  min_lr: 0.001632  loss: 4.1280 (4.2178)  weight_decay: 0.0500 (0.0500)  time: 1.0109  data: 0.0004  max mem: 78493
Epoch: [8]  [ 60/312]  eta: 0:05:28  lr: 0.001639  min_lr: 0.001639  loss: 4.5093 (4.2699)  weight_decay: 0.0500 (0.0500)  time: 1.0085  data: 0.0004  max mem: 78493
Epoch: [8]  [ 70/312]  eta: 0:05:05  lr: 0.001645  min_lr: 0.001645  loss: 4.5093 (4.2812)  weight_decay: 0.0500 (0.0500)  time: 1.0072  data: 0.0004  max mem: 78493
Epoch: [8]  [ 80/312]  eta: 0:04:45  lr: 0.001652  min_lr: 0.001652  loss: 4.2619 (4.2702)  weight_decay: 0.0500 (0.0500)  time: 1.0065  data: 0.0005  max mem: 78493
Epoch: [8]  [ 90/312]  eta: 0:04:27  lr: 0.001658  min_lr: 0.001658  loss: 4.2622 (4.2671)  weight_decay: 0.0500 (0.0500)  time: 1.0053  data: 0.0004  max mem: 78493
Epoch: [8]  [100/312]  eta: 0:04:11  lr: 0.001664  min_lr: 0.001664  loss: 4.2126 (4.2389)  weight_decay: 0.0500 (0.0500)  time: 1.0079  data: 0.0004  max mem: 78493
Epoch: [8]  [110/312]  eta: 0:03:56  lr: 0.001671  min_lr: 0.001671  loss: 4.1474 (4.2397)  weight_decay: 0.0500 (0.0500)  time: 1.0096  data: 0.0004  max mem: 78493
Epoch: [8]  [120/312]  eta: 0:03:41  lr: 0.001677  min_lr: 0.001677  loss: 4.2749 (4.2207)  weight_decay: 0.0500 (0.0500)  time: 1.0065  data: 0.0012  max mem: 78493
Epoch: [8]  [130/312]  eta: 0:03:28  lr: 0.001684  min_lr: 0.001684  loss: 4.2792 (4.2224)  weight_decay: 0.0500 (0.0500)  time: 1.0056  data: 0.0012  max mem: 78493
Epoch: [8]  [140/312]  eta: 0:03:15  lr: 0.001690  min_lr: 0.001690  loss: 4.2792 (4.2191)  weight_decay: 0.0500 (0.0500)  time: 1.0054  data: 0.0005  max mem: 78493
Epoch: [8]  [150/312]  eta: 0:03:02  lr: 0.001696  min_lr: 0.001696  loss: 4.4617 (4.2284)  weight_decay: 0.0500 (0.0500)  time: 1.0052  data: 0.0005  max mem: 78493
Epoch: [8]  [160/312]  eta: 0:02:50  lr: 0.001703  min_lr: 0.001703  loss: 4.4810 (4.2180)  weight_decay: 0.0500 (0.0500)  time: 1.0053  data: 0.0012  max mem: 78493
Epoch: [8]  [170/312]  eta: 0:02:37  lr: 0.001709  min_lr: 0.001709  loss: 4.1537 (4.2157)  weight_decay: 0.0500 (0.0500)  time: 1.0064  data: 0.0012  max mem: 78493
Epoch: [8]  [180/312]  eta: 0:02:26  lr: 0.001716  min_lr: 0.001716  loss: 4.3383 (4.2172)  weight_decay: 0.0500 (0.0500)  time: 1.0063  data: 0.0005  max mem: 78493
Epoch: [8]  [190/312]  eta: 0:02:14  lr: 0.001722  min_lr: 0.001722  loss: 4.4162 (4.2181)  weight_decay: 0.0500 (0.0500)  time: 1.0062  data: 0.0005  max mem: 78493
Epoch: [8]  [200/312]  eta: 0:02:02  lr: 0.001728  min_lr: 0.001728  loss: 4.4162 (4.2183)  weight_decay: 0.0500 (0.0500)  time: 1.0064  data: 0.0005  max mem: 78493
Epoch: [8]  [210/312]  eta: 0:01:51  lr: 0.001735  min_lr: 0.001735  loss: 4.4426 (4.2289)  weight_decay: 0.0500 (0.0500)  time: 1.0049  data: 0.0005  max mem: 78493
Epoch: [8]  [220/312]  eta: 0:01:40  lr: 0.001741  min_lr: 0.001741  loss: 4.3405 (4.2218)  weight_decay: 0.0500 (0.0500)  time: 1.0045  data: 0.0005  max mem: 78493
Epoch: [8]  [230/312]  eta: 0:01:28  lr: 0.001748  min_lr: 0.001748  loss: 4.1421 (4.2214)  weight_decay: 0.0500 (0.0500)  time: 1.0055  data: 0.0004  max mem: 78493
Epoch: [8]  [240/312]  eta: 0:01:17  lr: 0.001754  min_lr: 0.001754  loss: 4.1421 (4.2130)  weight_decay: 0.0500 (0.0500)  time: 1.0059  data: 0.0004  max mem: 78493
Epoch: [8]  [250/312]  eta: 0:01:06  lr: 0.001761  min_lr: 0.001761  loss: 4.0580 (4.2052)  weight_decay: 0.0500 (0.0500)  time: 1.0057  data: 0.0004  max mem: 78493
Epoch: [8]  [260/312]  eta: 0:00:55  lr: 0.001767  min_lr: 0.001767  loss: 3.9112 (4.1958)  weight_decay: 0.0500 (0.0500)  time: 1.0062  data: 0.0004  max mem: 78493
Epoch: [8]  [270/312]  eta: 0:00:45  lr: 0.001773  min_lr: 0.001773  loss: 4.2388 (4.1950)  weight_decay: 0.0500 (0.0500)  time: 1.0066  data: 0.0004  max mem: 78493
Epoch: [8]  [280/312]  eta: 0:00:34  lr: 0.001780  min_lr: 0.001780  loss: 4.2861 (4.1918)  weight_decay: 0.0500 (0.0500)  time: 1.0073  data: 0.0011  max mem: 78493
Epoch: [8]  [290/312]  eta: 0:00:23  lr: 0.001786  min_lr: 0.001786  loss: 3.8153 (4.1798)  weight_decay: 0.0500 (0.0500)  time: 1.0049  data: 0.0009  max mem: 78493
Epoch: [8]  [300/312]  eta: 0:00:12  lr: 0.001793  min_lr: 0.001793  loss: 3.8153 (4.1716)  weight_decay: 0.0500 (0.0500)  time: 1.0021  data: 0.0001  max mem: 78493
Epoch: [8]  [310/312]  eta: 0:00:02  lr: 0.001799  min_lr: 0.001799  loss: 4.2360 (4.1691)  weight_decay: 0.0500 (0.0500)  time: 1.0021  data: 0.0001  max mem: 78493
Epoch: [8]  [311/312]  eta: 0:00:01  lr: 0.001800  min_lr: 0.001800  loss: 4.2360 (4.1695)  weight_decay: 0.0500 (0.0500)  time: 1.0021  data: 0.0001  max mem: 78493
Epoch: [8] Total time: 0:05:33 (1.0693 s / it)
Averaged stats: lr: 0.001800  min_lr: 0.001800  loss: 4.2360 (4.1124)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:10  loss: 1.8673 (1.8673)  acc1: 57.2917 (57.2917)  acc5: 79.5573 (79.5573)  time: 7.8126  data: 7.5392  max mem: 78493
Test:  [8/9]  eta: 0:00:01  loss: 2.3090 (2.0898)  acc1: 50.6510 (50.8000)  acc5: 74.4792 (75.4720)  time: 1.0663  data: 0.8378  max mem: 78493
Test: Total time: 0:00:09 (1.1068 s / it)
* Acc@1 51.182 Acc@5 75.988 loss 2.091
Accuracy of the model on the 50000 test images: 51.2%
Max accuracy: 51.18%
Epoch: [9]  [  0/312]  eta: 1:15:37  lr: 0.001800  min_lr: 0.001800  loss: 4.1824 (4.1824)  weight_decay: 0.0500 (0.0500)  time: 14.5449  data: 12.5597  max mem: 78493
Epoch: [9]  [ 10/312]  eta: 0:12:37  lr: 0.001807  min_lr: 0.001807  loss: 4.1824 (4.0640)  weight_decay: 0.0500 (0.0500)  time: 2.5080  data: 1.3331  max mem: 78493
Epoch: [9]  [ 20/312]  eta: 0:08:44  lr: 0.001813  min_lr: 0.001813  loss: 4.2100 (4.0371)  weight_decay: 0.0500 (0.0500)  time: 1.1590  data: 0.1062  max mem: 78493
Epoch: [9]  [ 30/312]  eta: 0:07:14  lr: 0.001820  min_lr: 0.001820  loss: 3.8731 (3.9900)  weight_decay: 0.0500 (0.0500)  time: 1.0101  data: 0.0012  max mem: 78493
Epoch: [9]  [ 40/312]  eta: 0:06:23  lr: 0.001826  min_lr: 0.001826  loss: 3.7858 (3.9449)  weight_decay: 0.0500 (0.0500)  time: 1.0068  data: 0.0004  max mem: 78493
Epoch: [9]  [ 50/312]  eta: 0:05:48  lr: 0.001832  min_lr: 0.001832  loss: 3.6186 (3.8863)  weight_decay: 0.0500 (0.0500)  time: 1.0052  data: 0.0004  max mem: 78493
Epoch: [9]  [ 60/312]  eta: 0:05:21  lr: 0.001839  min_lr: 0.001839  loss: 3.6543 (3.8761)  weight_decay: 0.0500 (0.0500)  time: 1.0038  data: 0.0004  max mem: 78493
Epoch: [9]  [ 70/312]  eta: 0:04:59  lr: 0.001845  min_lr: 0.001845  loss: 3.9157 (3.8797)  weight_decay: 0.0500 (0.0500)  time: 1.0037  data: 0.0004  max mem: 78493
Epoch: [9]  [ 80/312]  eta: 0:04:40  lr: 0.001852  min_lr: 0.001852  loss: 3.7298 (3.8720)  weight_decay: 0.0500 (0.0500)  time: 1.0043  data: 0.0004  max mem: 78493
Epoch: [9]  [ 90/312]  eta: 0:04:23  lr: 0.001858  min_lr: 0.001858  loss: 4.0900 (3.9087)  weight_decay: 0.0500 (0.0500)  time: 1.0096  data: 0.0004  max mem: 78493
Epoch: [9]  [100/312]  eta: 0:04:08  lr: 0.001864  min_lr: 0.001864  loss: 4.0696 (3.9010)  weight_decay: 0.0500 (0.0500)  time: 1.0112  data: 0.0005  max mem: 78493
Epoch: [9]  [110/312]  eta: 0:03:53  lr: 0.001871  min_lr: 0.001871  loss: 3.9018 (3.9103)  weight_decay: 0.0500 (0.0500)  time: 1.0078  data: 0.0004  max mem: 78493
Epoch: [9]  [120/312]  eta: 0:03:39  lr: 0.001877  min_lr: 0.001877  loss: 4.0291 (3.9214)  weight_decay: 0.0500 (0.0500)  time: 1.0084  data: 0.0004  max mem: 78493
Epoch: [9]  [130/312]  eta: 0:03:26  lr: 0.001884  min_lr: 0.001884  loss: 4.2215 (3.9422)  weight_decay: 0.0500 (0.0500)  time: 1.0093  data: 0.0004  max mem: 78493
Epoch: [9]  [140/312]  eta: 0:03:13  lr: 0.001890  min_lr: 0.001890  loss: 4.0581 (3.9347)  weight_decay: 0.0500 (0.0500)  time: 1.0105  data: 0.0004  max mem: 78493
Epoch: [9]  [150/312]  eta: 0:03:00  lr: 0.001896  min_lr: 0.001896  loss: 3.8338 (3.9307)  weight_decay: 0.0500 (0.0500)  time: 1.0101  data: 0.0005  max mem: 78493
Epoch: [9]  [160/312]  eta: 0:02:48  lr: 0.001903  min_lr: 0.001903  loss: 3.9724 (3.9354)  weight_decay: 0.0500 (0.0500)  time: 1.0074  data: 0.0005  max mem: 78493
Epoch: [9]  [170/312]  eta: 0:02:36  lr: 0.001909  min_lr: 0.001909  loss: 4.1563 (3.9476)  weight_decay: 0.0500 (0.0500)  time: 1.0073  data: 0.0004  max mem: 78493
Epoch: [9]  [180/312]  eta: 0:02:25  lr: 0.001916  min_lr: 0.001916  loss: 4.0362 (3.9392)  weight_decay: 0.0500 (0.0500)  time: 1.0076  data: 0.0004  max mem: 78493
Epoch: [9]  [190/312]  eta: 0:02:13  lr: 0.001922  min_lr: 0.001922  loss: 3.9911 (3.9437)  weight_decay: 0.0500 (0.0500)  time: 1.0068  data: 0.0004  max mem: 78493
Epoch: [9]  [200/312]  eta: 0:02:02  lr: 0.001929  min_lr: 0.001929  loss: 3.9827 (3.9406)  weight_decay: 0.0500 (0.0500)  time: 1.0059  data: 0.0004  max mem: 78493
Epoch: [9]  [210/312]  eta: 0:01:50  lr: 0.001935  min_lr: 0.001935  loss: 3.9013 (3.9471)  weight_decay: 0.0500 (0.0500)  time: 1.0054  data: 0.0004  max mem: 78493
Epoch: [9]  [220/312]  eta: 0:01:39  lr: 0.001941  min_lr: 0.001941  loss: 3.8930 (3.9366)  weight_decay: 0.0500 (0.0500)  time: 1.0053  data: 0.0004  max mem: 78493
Epoch: [9]  [230/312]  eta: 0:01:28  lr: 0.001948  min_lr: 0.001948  loss: 3.9915 (3.9450)  weight_decay: 0.0500 (0.0500)  time: 1.0054  data: 0.0004  max mem: 78493
Epoch: [9]  [240/312]  eta: 0:01:17  lr: 0.001954  min_lr: 0.001954  loss: 4.1333 (3.9401)  weight_decay: 0.0500 (0.0500)  time: 1.0047  data: 0.0004  max mem: 78493
Epoch: [9]  [250/312]  eta: 0:01:06  lr: 0.001961  min_lr: 0.001961  loss: 4.1333 (3.9427)  weight_decay: 0.0500 (0.0500)  time: 1.0042  data: 0.0004  max mem: 78493
Epoch: [9]  [260/312]  eta: 0:00:55  lr: 0.001967  min_lr: 0.001967  loss: 4.0048 (3.9346)  weight_decay: 0.0500 (0.0500)  time: 1.0050  data: 0.0005  max mem: 78493
Epoch: [9]  [270/312]  eta: 0:00:44  lr: 0.001973  min_lr: 0.001973  loss: 3.9092 (3.9342)  weight_decay: 0.0500 (0.0500)  time: 1.0048  data: 0.0005  max mem: 78493
Epoch: [9]  [280/312]  eta: 0:00:34  lr: 0.001980  min_lr: 0.001980  loss: 3.7432 (3.9233)  weight_decay: 0.0500 (0.0500)  time: 1.0058  data: 0.0011  max mem: 78493
Epoch: [9]  [290/312]  eta: 0:00:23  lr: 0.001986  min_lr: 0.001986  loss: 4.1341 (3.9312)  weight_decay: 0.0500 (0.0500)  time: 1.0050  data: 0.0009  max mem: 78493
Epoch: [9]  [300/312]  eta: 0:00:12  lr: 0.001993  min_lr: 0.001993  loss: 4.1684 (3.9290)  weight_decay: 0.0500 (0.0500)  time: 1.0020  data: 0.0001  max mem: 78493
Epoch: [9]  [310/312]  eta: 0:00:02  lr: 0.001999  min_lr: 0.001999  loss: 3.9937 (3.9327)  weight_decay: 0.0500 (0.0500)  time: 1.0017  data: 0.0001  max mem: 78493
Epoch: [9]  [311/312]  eta: 0:00:01  lr: 0.002000  min_lr: 0.002000  loss: 3.9937 (3.9342)  weight_decay: 0.0500 (0.0500)  time: 1.0018  data: 0.0001  max mem: 78493
Epoch: [9] Total time: 0:05:32 (1.0650 s / it)
Averaged stats: lr: 0.002000  min_lr: 0.002000  loss: 3.9937 (3.9681)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:16  loss: 1.7171 (1.7171)  acc1: 60.4167 (60.4167)  acc5: 83.9844 (83.9844)  time: 8.5079  data: 8.2429  max mem: 78493
Test:  [8/9]  eta: 0:00:01  loss: 2.2545 (2.0369)  acc1: 51.1719 (52.5280)  acc5: 75.3906 (76.9280)  time: 1.1456  data: 0.9160  max mem: 78493
Test: Total time: 0:00:10 (1.1690 s / it)
* Acc@1 53.036 Acc@5 77.312 loss 2.036
Accuracy of the model on the 50000 test images: 53.0%
Max accuracy: 53.04%
Epoch: [10]  [  0/312]  eta: 1:23:06  lr: 0.002000  min_lr: 0.002000  loss: 4.0129 (4.0129)  weight_decay: 0.0500 (0.0500)  time: 15.9822  data: 13.4919  max mem: 78493
Epoch: [10]  [ 10/312]  eta: 0:12:56  lr: 0.002007  min_lr: 0.002007  loss: 3.9376 (3.8900)  weight_decay: 0.0500 (0.0500)  time: 2.5718  data: 1.2664  max mem: 78493
Epoch: [10]  [ 20/312]  eta: 0:08:55  lr: 0.002013  min_lr: 0.002013  loss: 3.7225 (3.7829)  weight_decay: 0.0500 (0.0500)  time: 1.1256  data: 0.0222  max mem: 78493
Epoch: [10]  [ 30/312]  eta: 0:07:21  lr: 0.002020  min_lr: 0.002020  loss: 3.7894 (3.7879)  weight_decay: 0.0500 (0.0500)  time: 1.0131  data: 0.0005  max mem: 78493
Epoch: [10]  [ 40/312]  eta: 0:06:28  lr: 0.002026  min_lr: 0.002026  loss: 3.9415 (3.7963)  weight_decay: 0.0500 (0.0500)  time: 1.0056  data: 0.0004  max mem: 78493
Epoch: [10]  [ 50/312]  eta: 0:05:52  lr: 0.002032  min_lr: 0.002032  loss: 3.8418 (3.8250)  weight_decay: 0.0500 (0.0500)  time: 1.0062  data: 0.0004  max mem: 78493
Epoch: [10]  [ 60/312]  eta: 0:05:25  lr: 0.002039  min_lr: 0.002039  loss: 3.9325 (3.8492)  weight_decay: 0.0500 (0.0500)  time: 1.0079  data: 0.0004  max mem: 78493
Epoch: [10]  [ 70/312]  eta: 0:05:02  lr: 0.002045  min_lr: 0.002045  loss: 3.9325 (3.8366)  weight_decay: 0.0500 (0.0500)  time: 1.0088  data: 0.0004  max mem: 78493
Epoch: [10]  [ 80/312]  eta: 0:04:43  lr: 0.002052  min_lr: 0.002052  loss: 3.9753 (3.8562)  weight_decay: 0.0500 (0.0500)  time: 1.0092  data: 0.0013  max mem: 78493
Epoch: [10]  [ 90/312]  eta: 0:04:26  lr: 0.002058  min_lr: 0.002058  loss: 4.1239 (3.8585)  weight_decay: 0.0500 (0.0500)  time: 1.0101  data: 0.0013  max mem: 78493
Epoch: [10]  [100/312]  eta: 0:04:10  lr: 0.002064  min_lr: 0.002064  loss: 4.0430 (3.8650)  weight_decay: 0.0500 (0.0500)  time: 1.0088  data: 0.0004  max mem: 78493
Epoch: [10]  [110/312]  eta: 0:03:55  lr: 0.002071  min_lr: 0.002071  loss: 3.9516 (3.8692)  weight_decay: 0.0500 (0.0500)  time: 1.0097  data: 0.0018  max mem: 78493
Epoch: [10]  [120/312]  eta: 0:03:41  lr: 0.002077  min_lr: 0.002077  loss: 4.1847 (3.9029)  weight_decay: 0.0500 (0.0500)  time: 1.0107  data: 0.0018  max mem: 78493
Epoch: [10]  [130/312]  eta: 0:03:27  lr: 0.002084  min_lr: 0.002084  loss: 4.1809 (3.8966)  weight_decay: 0.0500 (0.0500)  time: 1.0090  data: 0.0005  max mem: 78493
Epoch: [10]  [140/312]  eta: 0:03:14  lr: 0.002090  min_lr: 0.002090  loss: 3.7027 (3.8964)  weight_decay: 0.0500 (0.0500)  time: 1.0080  data: 0.0004  max mem: 78493
Epoch: [10]  [150/312]  eta: 0:03:01  lr: 0.002096  min_lr: 0.002096  loss: 3.7158 (3.8844)  weight_decay: 0.0500 (0.0500)  time: 1.0069  data: 0.0004  max mem: 78493
Epoch: [10]  [160/312]  eta: 0:02:49  lr: 0.002103  min_lr: 0.002103  loss: 3.6817 (3.8769)  weight_decay: 0.0500 (0.0500)  time: 1.0058  data: 0.0004  max mem: 78493
Epoch: [10]  [170/312]  eta: 0:02:37  lr: 0.002109  min_lr: 0.002109  loss: 3.7347 (3.8736)  weight_decay: 0.0500 (0.0500)  time: 1.0060  data: 0.0004  max mem: 78493
Epoch: [10]  [180/312]  eta: 0:02:25  lr: 0.002116  min_lr: 0.002116  loss: 3.8656 (3.8752)  weight_decay: 0.0500 (0.0500)  time: 1.0062  data: 0.0004  max mem: 78493
Epoch: [10]  [190/312]  eta: 0:02:14  lr: 0.002122  min_lr: 0.002122  loss: 4.0646 (3.8824)  weight_decay: 0.0500 (0.0500)  time: 1.0062  data: 0.0004  max mem: 78493
Epoch: [10]  [200/312]  eta: 0:02:02  lr: 0.002129  min_lr: 0.002129  loss: 4.0844 (3.8830)  weight_decay: 0.0500 (0.0500)  time: 1.0062  data: 0.0005  max mem: 78493
Epoch: [10]  [210/312]  eta: 0:01:51  lr: 0.002135  min_lr: 0.002135  loss: 3.8324 (3.8675)  weight_decay: 0.0500 (0.0500)  time: 1.0055  data: 0.0005  max mem: 78493
Epoch: [10]  [220/312]  eta: 0:01:39  lr: 0.002141  min_lr: 0.002141  loss: 3.4800 (3.8552)  weight_decay: 0.0500 (0.0500)  time: 1.0050  data: 0.0005  max mem: 78493
Epoch: [10]  [230/312]  eta: 0:01:28  lr: 0.002148  min_lr: 0.002148  loss: 4.0349 (3.8573)  weight_decay: 0.0500 (0.0500)  time: 1.0053  data: 0.0005  max mem: 78493
Epoch: [10]  [240/312]  eta: 0:01:17  lr: 0.002154  min_lr: 0.002154  loss: 4.0613 (3.8565)  weight_decay: 0.0500 (0.0500)  time: 1.0072  data: 0.0005  max mem: 78493
Epoch: [10]  [250/312]  eta: 0:01:06  lr: 0.002161  min_lr: 0.002161  loss: 3.9700 (3.8551)  weight_decay: 0.0500 (0.0500)  time: 1.0078  data: 0.0005  max mem: 78493
Epoch: [10]  [260/312]  eta: 0:00:55  lr: 0.002167  min_lr: 0.002167  loss: 4.0213 (3.8557)  weight_decay: 0.0500 (0.0500)  time: 1.0082  data: 0.0004  max mem: 78493
Epoch: [10]  [270/312]  eta: 0:00:44  lr: 0.002173  min_lr: 0.002173  loss: 4.0645 (3.8575)  weight_decay: 0.0500 (0.0500)  time: 1.0075  data: 0.0004  max mem: 78493
Epoch: [10]  [280/312]  eta: 0:00:34  lr: 0.002180  min_lr: 0.002180  loss: 3.7101 (3.8473)  weight_decay: 0.0500 (0.0500)  time: 1.0061  data: 0.0010  max mem: 78493
Epoch: [10]  [290/312]  eta: 0:00:23  lr: 0.002186  min_lr: 0.002186  loss: 3.8841 (3.8520)  weight_decay: 0.0500 (0.0500)  time: 1.0040  data: 0.0009  max mem: 78493
Epoch: [10]  [300/312]  eta: 0:00:12  lr: 0.002193  min_lr: 0.002193  loss: 4.1137 (3.8498)  weight_decay: 0.0500 (0.0500)  time: 1.0020  data: 0.0001  max mem: 78493
Epoch: [10]  [310/312]  eta: 0:00:02  lr: 0.002199  min_lr: 0.002199  loss: 3.6154 (3.8425)  weight_decay: 0.0500 (0.0500)  time: 1.0022  data: 0.0001  max mem: 78493
Epoch: [10]  [311/312]  eta: 0:00:01  lr: 0.002200  min_lr: 0.002200  loss: 3.7334 (3.8421)  weight_decay: 0.0500 (0.0500)  time: 1.0022  data: 0.0001  max mem: 78493
Epoch: [10] Total time: 0:05:33 (1.0682 s / it)
Averaged stats: lr: 0.002200  min_lr: 0.002200  loss: 3.7334 (3.8400)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:17  loss: 1.4696 (1.4696)  acc1: 63.1510 (63.1510)  acc5: 86.3281 (86.3281)  time: 8.5752  data: 8.3040  max mem: 78493
Test:  [8/9]  eta: 0:00:01  loss: 2.0257 (1.8170)  acc1: 53.7760 (56.0640)  acc5: 80.2083 (80.2880)  time: 1.1510  data: 0.9228  max mem: 78493
Test: Total time: 0:00:10 (1.1672 s / it)
* Acc@1 56.758 Acc@5 80.656 loss 1.807
Accuracy of the model on the 50000 test images: 56.8%
Max accuracy: 56.76%
Epoch: [11]  [  0/312]  eta: 1:22:09  lr: 0.002200  min_lr: 0.002200  loss: 4.3979 (4.3979)  weight_decay: 0.0500 (0.0500)  time: 15.7990  data: 14.7895  max mem: 78493
Epoch: [11]  [ 10/312]  eta: 0:12:52  lr: 0.002207  min_lr: 0.002207  loss: 3.5002 (3.7028)  weight_decay: 0.0500 (0.0500)  time: 2.5583  data: 1.3452  max mem: 78493
Epoch: [11]  [ 20/312]  eta: 0:08:52  lr: 0.002213  min_lr: 0.002213  loss: 3.5608 (3.7033)  weight_decay: 0.0500 (0.0500)  time: 1.1251  data: 0.0006  max mem: 78493
Epoch: [11]  [ 30/312]  eta: 0:07:20  lr: 0.002220  min_lr: 0.002220  loss: 3.8894 (3.7445)  weight_decay: 0.0500 (0.0500)  time: 1.0140  data: 0.0005  max mem: 78493
Epoch: [11]  [ 40/312]  eta: 0:06:27  lr: 0.002226  min_lr: 0.002226  loss: 3.5532 (3.6750)  weight_decay: 0.0500 (0.0500)  time: 1.0084  data: 0.0004  max mem: 78493
Epoch: [11]  [ 50/312]  eta: 0:05:51  lr: 0.002232  min_lr: 0.002232  loss: 3.5532 (3.6723)  weight_decay: 0.0500 (0.0500)  time: 1.0046  data: 0.0004  max mem: 78493
Epoch: [11]  [ 60/312]  eta: 0:05:24  lr: 0.002239  min_lr: 0.002239  loss: 3.6308 (3.6814)  weight_decay: 0.0500 (0.0500)  time: 1.0047  data: 0.0004  max mem: 78493
Epoch: [11]  [ 70/312]  eta: 0:05:02  lr: 0.002245  min_lr: 0.002245  loss: 3.6301 (3.6754)  weight_decay: 0.0500 (0.0500)  time: 1.0063  data: 0.0005  max mem: 78493
Epoch: [11]  [ 80/312]  eta: 0:04:42  lr: 0.002252  min_lr: 0.002252  loss: 3.7270 (3.6930)  weight_decay: 0.0500 (0.0500)  time: 1.0073  data: 0.0004  max mem: 78493
Epoch: [11]  [ 90/312]  eta: 0:04:25  lr: 0.002258  min_lr: 0.002258  loss: 3.6618 (3.6815)  weight_decay: 0.0500 (0.0500)  time: 1.0080  data: 0.0004  max mem: 78493
Epoch: [11]  [100/312]  eta: 0:04:09  lr: 0.002264  min_lr: 0.002264  loss: 3.7219 (3.6942)  weight_decay: 0.0500 (0.0500)  time: 1.0074  data: 0.0004  max mem: 78493
Epoch: [11]  [110/312]  eta: 0:03:54  lr: 0.002271  min_lr: 0.002271  loss: 3.6915 (3.6788)  weight_decay: 0.0500 (0.0500)  time: 1.0049  data: 0.0012  max mem: 78493
Epoch: [11]  [120/312]  eta: 0:03:40  lr: 0.002277  min_lr: 0.002277  loss: 3.5517 (3.6830)  weight_decay: 0.0500 (0.0500)  time: 1.0056  data: 0.0012  max mem: 78493
Epoch: [11]  [130/312]  eta: 0:03:27  lr: 0.002284  min_lr: 0.002284  loss: 3.9704 (3.7018)  weight_decay: 0.0500 (0.0500)  time: 1.0072  data: 0.0004  max mem: 78493
Epoch: [11]  [140/312]  eta: 0:03:14  lr: 0.002290  min_lr: 0.002290  loss: 4.0572 (3.7081)  weight_decay: 0.0500 (0.0500)  time: 1.0072  data: 0.0004  max mem: 78493
Epoch: [11]  [150/312]  eta: 0:03:01  lr: 0.002297  min_lr: 0.002297  loss: 3.9458 (3.7190)  weight_decay: 0.0500 (0.0500)  time: 1.0074  data: 0.0004  max mem: 78493
Epoch: [11]  [160/312]  eta: 0:02:49  lr: 0.002303  min_lr: 0.002303  loss: 3.9020 (3.7222)  weight_decay: 0.0500 (0.0500)  time: 1.0088  data: 0.0004  max mem: 78493
Epoch: [11]  [170/312]  eta: 0:02:37  lr: 0.002309  min_lr: 0.002309  loss: 3.8870 (3.7140)  weight_decay: 0.0500 (0.0500)  time: 1.0076  data: 0.0004  max mem: 78493
Epoch: [11]  [180/312]  eta: 0:02:25  lr: 0.002316  min_lr: 0.002316  loss: 3.7113 (3.7234)  weight_decay: 0.0500 (0.0500)  time: 1.0070  data: 0.0005  max mem: 78493
Epoch: [11]  [190/312]  eta: 0:02:13  lr: 0.002322  min_lr: 0.002322  loss: 3.8519 (3.7272)  weight_decay: 0.0500 (0.0500)  time: 1.0083  data: 0.0005  max mem: 78493
Epoch: [11]  [200/312]  eta: 0:02:02  lr: 0.002329  min_lr: 0.002329  loss: 3.8519 (3.7376)  weight_decay: 0.0500 (0.0500)  time: 1.0076  data: 0.0005  max mem: 78493
Epoch: [11]  [210/312]  eta: 0:01:51  lr: 0.002335  min_lr: 0.002335  loss: 3.8128 (3.7370)  weight_decay: 0.0500 (0.0500)  time: 1.0077  data: 0.0005  max mem: 78493
Epoch: [11]  [220/312]  eta: 0:01:39  lr: 0.002341  min_lr: 0.002341  loss: 3.7569 (3.7441)  weight_decay: 0.0500 (0.0500)  time: 1.0069  data: 0.0004  max mem: 78493
Epoch: [11]  [230/312]  eta: 0:01:28  lr: 0.002348  min_lr: 0.002348  loss: 3.8428 (3.7420)  weight_decay: 0.0500 (0.0500)  time: 1.0052  data: 0.0004  max mem: 78493
Epoch: [11]  [240/312]  eta: 0:01:17  lr: 0.002354  min_lr: 0.002354  loss: 3.8479 (3.7444)  weight_decay: 0.0500 (0.0500)  time: 1.0042  data: 0.0012  max mem: 78493
Epoch: [11]  [250/312]  eta: 0:01:06  lr: 0.002361  min_lr: 0.002361  loss: 3.8711 (3.7440)  weight_decay: 0.0500 (0.0500)  time: 1.0056  data: 0.0012  max mem: 78493
Epoch: [11]  [260/312]  eta: 0:00:55  lr: 0.002367  min_lr: 0.002367  loss: 3.8711 (3.7426)  weight_decay: 0.0500 (0.0500)  time: 1.0069  data: 0.0004  max mem: 78493
Epoch: [11]  [270/312]  eta: 0:00:44  lr: 0.002373  min_lr: 0.002373  loss: 3.8240 (3.7420)  weight_decay: 0.0500 (0.0500)  time: 1.0069  data: 0.0004  max mem: 78493
Epoch: [11]  [280/312]  eta: 0:00:34  lr: 0.002380  min_lr: 0.002380  loss: 3.7128 (3.7365)  weight_decay: 0.0500 (0.0500)  time: 1.0086  data: 0.0010  max mem: 78493
Epoch: [11]  [290/312]  eta: 0:00:23  lr: 0.002386  min_lr: 0.002386  loss: 3.7128 (3.7403)  weight_decay: 0.0500 (0.0500)  time: 1.0061  data: 0.0009  max mem: 78493
Epoch: [11]  [300/312]  eta: 0:00:12  lr: 0.002393  min_lr: 0.002393  loss: 3.8663 (3.7421)  weight_decay: 0.0500 (0.0500)  time: 1.0021  data: 0.0001  max mem: 78493
Epoch: [11]  [310/312]  eta: 0:00:02  lr: 0.002399  min_lr: 0.002399  loss: 3.8847 (3.7449)  weight_decay: 0.0500 (0.0500)  time: 1.0018  data: 0.0001  max mem: 78493
Epoch: [11]  [311/312]  eta: 0:00:01  lr: 0.002400  min_lr: 0.002400  loss: 3.8847 (3.7449)  weight_decay: 0.0500 (0.0500)  time: 1.0018  data: 0.0001  max mem: 78493
Epoch: [11] Total time: 0:05:33 (1.0674 s / it)
Averaged stats: lr: 0.002400  min_lr: 0.002400  loss: 3.8847 (3.7151)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:10  loss: 1.5799 (1.5799)  acc1: 65.4948 (65.4948)  acc5: 84.6354 (84.6354)  time: 7.7833  data: 7.5183  max mem: 78493
Test:  [8/9]  eta: 0:00:01  loss: 1.9279 (1.7876)  acc1: 57.0312 (57.2800)  acc5: 80.3385 (80.5920)  time: 1.0727  data: 0.8358  max mem: 78493
Test: Total time: 0:00:09 (1.0907 s / it)
* Acc@1 57.582 Acc@5 81.086 loss 1.789
Accuracy of the model on the 50000 test images: 57.6%
Max accuracy: 57.58%
Epoch: [12]  [  0/312]  eta: 1:21:34  lr: 0.002400  min_lr: 0.002400  loss: 3.8563 (3.8563)  weight_decay: 0.0500 (0.0500)  time: 15.6884  data: 13.8953  max mem: 78493
Epoch: [12]  [ 10/312]  eta: 0:12:18  lr: 0.002407  min_lr: 0.002407  loss: 3.4711 (3.5448)  weight_decay: 0.0500 (0.0500)  time: 2.4444  data: 1.2640  max mem: 78493
Epoch: [12]  [ 20/312]  eta: 0:08:37  lr: 0.002413  min_lr: 0.002413  loss: 3.7067 (3.6384)  weight_decay: 0.0500 (0.0500)  time: 1.0770  data: 0.0035  max mem: 78493
Epoch: [12]  [ 30/312]  eta: 0:07:10  lr: 0.002420  min_lr: 0.002420  loss: 3.8427 (3.6358)  weight_decay: 0.0500 (0.0500)  time: 1.0209  data: 0.0033  max mem: 78493
Epoch: [12]  [ 40/312]  eta: 0:06:20  lr: 0.002426  min_lr: 0.002426  loss: 3.7583 (3.6628)  weight_decay: 0.0500 (0.0500)  time: 1.0090  data: 0.0004  max mem: 78493
Epoch: [12]  [ 50/312]  eta: 0:05:46  lr: 0.002432  min_lr: 0.002432  loss: 3.8016 (3.6668)  weight_decay: 0.0500 (0.0500)  time: 1.0095  data: 0.0004  max mem: 78493
Epoch: [12]  [ 60/312]  eta: 0:05:20  lr: 0.002439  min_lr: 0.002439  loss: 3.5465 (3.6617)  weight_decay: 0.0500 (0.0500)  time: 1.0075  data: 0.0004  max mem: 78493
Epoch: [12]  [ 70/312]  eta: 0:04:58  lr: 0.002445  min_lr: 0.002445  loss: 3.5179 (3.6323)  weight_decay: 0.0500 (0.0500)  time: 1.0057  data: 0.0005  max mem: 78493
Epoch: [12]  [ 80/312]  eta: 0:04:39  lr: 0.002452  min_lr: 0.002452  loss: 3.7860 (3.6572)  weight_decay: 0.0500 (0.0500)  time: 1.0063  data: 0.0005  max mem: 78493
Epoch: [12]  [ 90/312]  eta: 0:04:22  lr: 0.002458  min_lr: 0.002458  loss: 3.8924 (3.6619)  weight_decay: 0.0500 (0.0500)  time: 1.0071  data: 0.0014  max mem: 78493
Epoch: [12]  [100/312]  eta: 0:04:07  lr: 0.002464  min_lr: 0.002464  loss: 3.7059 (3.6413)  weight_decay: 0.0500 (0.0500)  time: 1.0082  data: 0.0014  max mem: 78493
Epoch: [12]  [110/312]  eta: 0:03:52  lr: 0.002471  min_lr: 0.002471  loss: 3.8292 (3.6498)  weight_decay: 0.0500 (0.0500)  time: 1.0069  data: 0.0018  max mem: 78493
Epoch: [12]  [120/312]  eta: 0:03:38  lr: 0.002477  min_lr: 0.002477  loss: 3.7006 (3.6375)  weight_decay: 0.0500 (0.0500)  time: 1.0059  data: 0.0028  max mem: 78493
Epoch: [12]  [130/312]  eta: 0:03:25  lr: 0.002484  min_lr: 0.002484  loss: 3.7006 (3.6432)  weight_decay: 0.0500 (0.0500)  time: 1.0054  data: 0.0015  max mem: 78493
Epoch: [12]  [140/312]  eta: 0:03:12  lr: 0.002490  min_lr: 0.002490  loss: 3.6907 (3.6287)  weight_decay: 0.0500 (0.0500)  time: 1.0052  data: 0.0004  max mem: 78493
Epoch: [12]  [150/312]  eta: 0:03:00  lr: 0.002497  min_lr: 0.002497  loss: 3.6271 (3.6246)  weight_decay: 0.0500 (0.0500)  time: 1.0065  data: 0.0011  max mem: 78493
Epoch: [12]  [160/312]  eta: 0:02:48  lr: 0.002503  min_lr: 0.002503  loss: 3.6075 (3.6146)  weight_decay: 0.0500 (0.0500)  time: 1.0054  data: 0.0012  max mem: 78493
Epoch: [12]  [170/312]  eta: 0:02:36  lr: 0.002509  min_lr: 0.002509  loss: 3.5363 (3.6159)  weight_decay: 0.0500 (0.0500)  time: 1.0050  data: 0.0005  max mem: 78493
Epoch: [12]  [180/312]  eta: 0:02:24  lr: 0.002516  min_lr: 0.002516  loss: 3.5363 (3.6114)  weight_decay: 0.0500 (0.0500)  time: 1.0052  data: 0.0005  max mem: 78493
Epoch: [12]  [190/312]  eta: 0:02:13  lr: 0.002522  min_lr: 0.002522  loss: 3.7388 (3.6110)  weight_decay: 0.0500 (0.0500)  time: 1.0062  data: 0.0004  max mem: 78493
Epoch: [12]  [200/312]  eta: 0:02:01  lr: 0.002529  min_lr: 0.002529  loss: 3.6603 (3.6031)  weight_decay: 0.0500 (0.0500)  time: 1.0076  data: 0.0004  max mem: 78493
Epoch: [12]  [210/312]  eta: 0:01:50  lr: 0.002535  min_lr: 0.002535  loss: 3.5194 (3.5945)  weight_decay: 0.0500 (0.0500)  time: 1.0088  data: 0.0004  max mem: 78493
Epoch: [12]  [220/312]  eta: 0:01:39  lr: 0.002541  min_lr: 0.002541  loss: 3.5812 (3.6037)  weight_decay: 0.0500 (0.0500)  time: 1.0080  data: 0.0004  max mem: 78493
Epoch: [12]  [230/312]  eta: 0:01:28  lr: 0.002548  min_lr: 0.002548  loss: 3.7527 (3.6068)  weight_decay: 0.0500 (0.0500)  time: 1.0056  data: 0.0004  max mem: 78493
Epoch: [12]  [240/312]  eta: 0:01:17  lr: 0.002554  min_lr: 0.002554  loss: 3.7589 (3.6108)  weight_decay: 0.0500 (0.0500)  time: 1.0060  data: 0.0004  max mem: 78493
Epoch: [12]  [250/312]  eta: 0:01:06  lr: 0.002561  min_lr: 0.002561  loss: 3.8463 (3.6147)  weight_decay: 0.0500 (0.0500)  time: 1.0064  data: 0.0004  max mem: 78493
Epoch: [12]  [260/312]  eta: 0:00:55  lr: 0.002567  min_lr: 0.002567  loss: 3.9911 (3.6138)  weight_decay: 0.0500 (0.0500)  time: 1.0050  data: 0.0004  max mem: 78493
Epoch: [12]  [270/312]  eta: 0:00:44  lr: 0.002573  min_lr: 0.002573  loss: 3.4454 (3.6063)  weight_decay: 0.0500 (0.0500)  time: 1.0053  data: 0.0004  max mem: 78493
Epoch: [12]  [280/312]  eta: 0:00:34  lr: 0.002580  min_lr: 0.002580  loss: 3.7567 (3.6152)  weight_decay: 0.0500 (0.0500)  time: 1.0053  data: 0.0011  max mem: 78493
Epoch: [12]  [290/312]  eta: 0:00:23  lr: 0.002586  min_lr: 0.002586  loss: 3.6519 (3.6086)  weight_decay: 0.0500 (0.0500)  time: 1.0033  data: 0.0009  max mem: 78493
Epoch: [12]  [300/312]  eta: 0:00:12  lr: 0.002593  min_lr: 0.002593  loss: 3.6694 (3.6181)  weight_decay: 0.0500 (0.0500)  time: 1.0015  data: 0.0001  max mem: 78493
Epoch: [12]  [310/312]  eta: 0:00:02  lr: 0.002599  min_lr: 0.002599  loss: 3.9384 (3.6262)  weight_decay: 0.0500 (0.0500)  time: 1.0014  data: 0.0001  max mem: 78493
Epoch: [12]  [311/312]  eta: 0:00:01  lr: 0.002600  min_lr: 0.002600  loss: 3.9384 (3.6278)  weight_decay: 0.0500 (0.0500)  time: 1.0014  data: 0.0001  max mem: 78493
Epoch: [12] Total time: 0:05:31 (1.0632 s / it)
Averaged stats: lr: 0.002600  min_lr: 0.002600  loss: 3.9384 (3.6312)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:15  loss: 1.3505 (1.3505)  acc1: 69.0104 (69.0104)  acc5: 87.8906 (87.8906)  time: 8.4415  data: 8.1668  max mem: 78493
Test:  [8/9]  eta: 0:00:01  loss: 1.8890 (1.7047)  acc1: 57.6823 (59.8080)  acc5: 81.6406 (82.4160)  time: 1.1362  data: 0.9075  max mem: 78493
Test: Total time: 0:00:10 (1.1561 s / it)
* Acc@1 59.986 Acc@5 82.620 loss 1.703
Accuracy of the model on the 50000 test images: 60.0%
Max accuracy: 59.99%
Epoch: [13]  [  0/312]  eta: 1:22:27  lr: 0.002600  min_lr: 0.002600  loss: 3.7585 (3.7585)  weight_decay: 0.0500 (0.0500)  time: 15.8574  data: 14.0315  max mem: 78493
Epoch: [13]  [ 10/312]  eta: 0:12:39  lr: 0.002607  min_lr: 0.002607  loss: 3.2253 (3.3671)  weight_decay: 0.0500 (0.0500)  time: 2.5139  data: 1.2787  max mem: 78493
Epoch: [13]  [ 20/312]  eta: 0:08:49  lr: 0.002613  min_lr: 0.002613  loss: 3.2253 (3.4121)  weight_decay: 0.0500 (0.0500)  time: 1.1102  data: 0.0035  max mem: 78493
Epoch: [13]  [ 30/312]  eta: 0:07:18  lr: 0.002620  min_lr: 0.002620  loss: 3.2202 (3.3495)  weight_decay: 0.0500 (0.0500)  time: 1.0251  data: 0.0020  max mem: 78493
Epoch: [13]  [ 40/312]  eta: 0:06:26  lr: 0.002626  min_lr: 0.002626  loss: 3.3422 (3.4103)  weight_decay: 0.0500 (0.0500)  time: 1.0072  data: 0.0005  max mem: 78493
Epoch: [13]  [ 50/312]  eta: 0:05:50  lr: 0.002632  min_lr: 0.002632  loss: 3.4842 (3.3845)  weight_decay: 0.0500 (0.0500)  time: 1.0081  data: 0.0004  max mem: 78493
Epoch: [13]  [ 60/312]  eta: 0:05:24  lr: 0.002639  min_lr: 0.002639  loss: 3.4616 (3.4175)  weight_decay: 0.0500 (0.0500)  time: 1.0116  data: 0.0005  max mem: 78493
Epoch: [13]  [ 70/312]  eta: 0:05:01  lr: 0.002645  min_lr: 0.002645  loss: 3.5542 (3.4372)  weight_decay: 0.0500 (0.0500)  time: 1.0115  data: 0.0005  max mem: 78493
Epoch: [13]  [ 80/312]  eta: 0:04:42  lr: 0.002652  min_lr: 0.002652  loss: 3.4548 (3.4315)  weight_decay: 0.0500 (0.0500)  time: 1.0116  data: 0.0005  max mem: 78493
Epoch: [13]  [ 90/312]  eta: 0:04:25  lr: 0.002658  min_lr: 0.002658  loss: 3.4957 (3.4373)  weight_decay: 0.0500 (0.0500)  time: 1.0100  data: 0.0004  max mem: 78493
Epoch: [13]  [100/312]  eta: 0:04:09  lr: 0.002665  min_lr: 0.002665  loss: 3.4957 (3.4558)  weight_decay: 0.0500 (0.0500)  time: 1.0084  data: 0.0004  max mem: 78493
Epoch: [13]  [110/312]  eta: 0:03:54  lr: 0.002671  min_lr: 0.002671  loss: 3.7124 (3.4685)  weight_decay: 0.0500 (0.0500)  time: 1.0076  data: 0.0004  max mem: 78493
Epoch: [13]  [120/312]  eta: 0:03:40  lr: 0.002677  min_lr: 0.002677  loss: 3.7124 (3.4886)  weight_decay: 0.0500 (0.0500)  time: 1.0074  data: 0.0004  max mem: 78493
Epoch: [13]  [130/312]  eta: 0:03:27  lr: 0.002684  min_lr: 0.002684  loss: 3.7101 (3.4947)  weight_decay: 0.0500 (0.0500)  time: 1.0079  data: 0.0004  max mem: 78493
Epoch: [13]  [140/312]  eta: 0:03:14  lr: 0.002690  min_lr: 0.002690  loss: 3.6421 (3.4964)  weight_decay: 0.0500 (0.0500)  time: 1.0059  data: 0.0005  max mem: 78493
Epoch: [13]  [150/312]  eta: 0:03:01  lr: 0.002697  min_lr: 0.002697  loss: 3.6355 (3.4994)  weight_decay: 0.0500 (0.0500)  time: 1.0067  data: 0.0004  max mem: 78493
Epoch: [13]  [160/312]  eta: 0:02:49  lr: 0.002703  min_lr: 0.002703  loss: 3.6580 (3.5095)  weight_decay: 0.0500 (0.0500)  time: 1.0091  data: 0.0004  max mem: 78493
Epoch: [13]  [170/312]  eta: 0:02:37  lr: 0.002709  min_lr: 0.002709  loss: 3.6580 (3.5100)  weight_decay: 0.0500 (0.0500)  time: 1.0106  data: 0.0005  max mem: 78493
Epoch: [13]  [180/312]  eta: 0:02:25  lr: 0.002716  min_lr: 0.002716  loss: 3.2095 (3.4968)  weight_decay: 0.0500 (0.0500)  time: 1.0122  data: 0.0005  max mem: 78493
Epoch: [13]  [190/312]  eta: 0:02:13  lr: 0.002722  min_lr: 0.002722  loss: 3.4579 (3.5051)  weight_decay: 0.0500 (0.0500)  time: 1.0103  data: 0.0004  max mem: 78493
Epoch: [13]  [200/312]  eta: 0:02:02  lr: 0.002729  min_lr: 0.002729  loss: 3.9177 (3.5187)  weight_decay: 0.0500 (0.0500)  time: 1.0075  data: 0.0005  max mem: 78493
Epoch: [13]  [210/312]  eta: 0:01:51  lr: 0.002735  min_lr: 0.002735  loss: 3.5299 (3.5090)  weight_decay: 0.0500 (0.0500)  time: 1.0075  data: 0.0005  max mem: 78493
Epoch: [13]  [220/312]  eta: 0:01:39  lr: 0.002741  min_lr: 0.002741  loss: 3.3599 (3.5082)  weight_decay: 0.0500 (0.0500)  time: 1.0069  data: 0.0004  max mem: 78493
Epoch: [13]  [230/312]  eta: 0:01:28  lr: 0.002748  min_lr: 0.002748  loss: 3.4763 (3.5086)  weight_decay: 0.0500 (0.0500)  time: 1.0072  data: 0.0004  max mem: 78493
Epoch: [13]  [240/312]  eta: 0:01:17  lr: 0.002754  min_lr: 0.002754  loss: 3.6835 (3.5118)  weight_decay: 0.0500 (0.0500)  time: 1.0091  data: 0.0004  max mem: 78493
Epoch: [13]  [250/312]  eta: 0:01:06  lr: 0.002761  min_lr: 0.002761  loss: 3.3281 (3.5013)  weight_decay: 0.0500 (0.0500)  time: 1.0079  data: 0.0004  max mem: 78493
Epoch: [13]  [260/312]  eta: 0:00:55  lr: 0.002767  min_lr: 0.002767  loss: 3.5841 (3.5096)  weight_decay: 0.0500 (0.0500)  time: 1.0057  data: 0.0005  max mem: 78493
Epoch: [13]  [270/312]  eta: 0:00:44  lr: 0.002774  min_lr: 0.002774  loss: 3.8035 (3.5145)  weight_decay: 0.0500 (0.0500)  time: 1.0059  data: 0.0004  max mem: 78493
Epoch: [13]  [280/312]  eta: 0:00:34  lr: 0.002780  min_lr: 0.002780  loss: 3.6104 (3.5086)  weight_decay: 0.0500 (0.0500)  time: 1.0063  data: 0.0010  max mem: 78493
Epoch: [13]  [290/312]  eta: 0:00:23  lr: 0.002786  min_lr: 0.002786  loss: 3.3286 (3.5043)  weight_decay: 0.0500 (0.0500)  time: 1.0037  data: 0.0009  max mem: 78493
Epoch: [13]  [300/312]  eta: 0:00:12  lr: 0.002793  min_lr: 0.002793  loss: 3.6131 (3.5056)  weight_decay: 0.0500 (0.0500)  time: 1.0014  data: 0.0001  max mem: 78493
Epoch: [13]  [310/312]  eta: 0:00:02  lr: 0.002799  min_lr: 0.002799  loss: 3.6131 (3.5045)  weight_decay: 0.0500 (0.0500)  time: 1.0014  data: 0.0001  max mem: 78493
Epoch: [13]  [311/312]  eta: 0:00:01  lr: 0.002800  min_lr: 0.002800  loss: 3.6131 (3.5043)  weight_decay: 0.0500 (0.0500)  time: 1.0014  data: 0.0001  max mem: 78493
Epoch: [13] Total time: 0:05:33 (1.0676 s / it)
Averaged stats: lr: 0.002800  min_lr: 0.002800  loss: 3.6131 (3.5574)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:09  loss: 1.2892 (1.2892)  acc1: 68.3594 (68.3594)  acc5: 87.2396 (87.2396)  time: 7.7150  data: 7.4501  max mem: 78493
Test:  [8/9]  eta: 0:00:01  loss: 1.8488 (1.6410)  acc1: 59.2448 (60.5440)  acc5: 82.0312 (83.1040)  time: 1.0556  data: 0.8279  max mem: 78493
Test: Total time: 0:00:09 (1.0657 s / it)
* Acc@1 60.678 Acc@5 83.248 loss 1.633
Accuracy of the model on the 50000 test images: 60.7%
Max accuracy: 60.68%
Epoch: [14]  [  0/312]  eta: 1:21:05  lr: 0.002800  min_lr: 0.002800  loss: 3.9071 (3.9071)  weight_decay: 0.0500 (0.0500)  time: 15.5959  data: 13.4068  max mem: 78493
Epoch: [14]  [ 10/312]  eta: 0:12:57  lr: 0.002807  min_lr: 0.002807  loss: 3.6391 (3.4999)  weight_decay: 0.0500 (0.0500)  time: 2.5730  data: 1.2543  max mem: 78493
Epoch: [14]  [ 20/312]  eta: 0:08:56  lr: 0.002813  min_lr: 0.002813  loss: 3.4990 (3.4867)  weight_decay: 0.0500 (0.0500)  time: 1.1504  data: 0.0199  max mem: 78493
Epoch: [14]  [ 30/312]  eta: 0:07:22  lr: 0.002820  min_lr: 0.002820  loss: 3.7991 (3.5530)  weight_decay: 0.0500 (0.0500)  time: 1.0177  data: 0.0006  max mem: 78493
Epoch: [14]  [ 40/312]  eta: 0:06:29  lr: 0.002826  min_lr: 0.002826  loss: 3.7991 (3.5749)  weight_decay: 0.0500 (0.0500)  time: 1.0070  data: 0.0005  max mem: 78493
Epoch: [14]  [ 50/312]  eta: 0:05:53  lr: 0.002833  min_lr: 0.002833  loss: 3.5238 (3.5179)  weight_decay: 0.0500 (0.0500)  time: 1.0086  data: 0.0004  max mem: 78493
Epoch: [14]  [ 60/312]  eta: 0:05:25  lr: 0.002839  min_lr: 0.002839  loss: 3.4982 (3.4943)  weight_decay: 0.0500 (0.0500)  time: 1.0076  data: 0.0004  max mem: 78493
Epoch: [14]  [ 70/312]  eta: 0:05:03  lr: 0.002845  min_lr: 0.002845  loss: 3.6237 (3.5048)  weight_decay: 0.0500 (0.0500)  time: 1.0048  data: 0.0004  max mem: 78493
Epoch: [14]  [ 80/312]  eta: 0:04:43  lr: 0.002852  min_lr: 0.002852  loss: 3.7368 (3.5244)  weight_decay: 0.0500 (0.0500)  time: 1.0057  data: 0.0004  max mem: 78493
Epoch: [14]  [ 90/312]  eta: 0:04:26  lr: 0.002858  min_lr: 0.002858  loss: 3.6462 (3.4978)  weight_decay: 0.0500 (0.0500)  time: 1.0088  data: 0.0004  max mem: 78493
Epoch: [14]  [100/312]  eta: 0:04:10  lr: 0.002865  min_lr: 0.002865  loss: 3.6292 (3.5148)  weight_decay: 0.0500 (0.0500)  time: 1.0083  data: 0.0004  max mem: 78493
Epoch: [14]  [110/312]  eta: 0:03:55  lr: 0.002871  min_lr: 0.002871  loss: 3.6929 (3.5207)  weight_decay: 0.0500 (0.0500)  time: 1.0079  data: 0.0004  max mem: 78493
Epoch: [14]  [120/312]  eta: 0:03:41  lr: 0.002877  min_lr: 0.002877  loss: 3.7194 (3.5128)  weight_decay: 0.0500 (0.0500)  time: 1.0073  data: 0.0004  max mem: 78493
Epoch: [14]  [130/312]  eta: 0:03:27  lr: 0.002884  min_lr: 0.002884  loss: 3.6005 (3.5102)  weight_decay: 0.0500 (0.0500)  time: 1.0069  data: 0.0004  max mem: 78493
Epoch: [14]  [140/312]  eta: 0:03:14  lr: 0.002890  min_lr: 0.002890  loss: 3.6476 (3.5147)  weight_decay: 0.0500 (0.0500)  time: 1.0060  data: 0.0004  max mem: 78493
Epoch: [14]  [150/312]  eta: 0:03:01  lr: 0.002897  min_lr: 0.002897  loss: 3.6952 (3.5094)  weight_decay: 0.0500 (0.0500)  time: 1.0064  data: 0.0004  max mem: 78493
Epoch: [14]  [160/312]  eta: 0:02:49  lr: 0.002903  min_lr: 0.002903  loss: 3.6836 (3.5156)  weight_decay: 0.0500 (0.0500)  time: 1.0083  data: 0.0004  max mem: 78493
Epoch: [14]  [170/312]  eta: 0:02:37  lr: 0.002909  min_lr: 0.002909  loss: 3.5054 (3.5017)  weight_decay: 0.0500 (0.0500)  time: 1.0073  data: 0.0004  max mem: 78493
Epoch: [14]  [180/312]  eta: 0:02:25  lr: 0.002916  min_lr: 0.002916  loss: 3.5054 (3.5100)  weight_decay: 0.0500 (0.0500)  time: 1.0075  data: 0.0004  max mem: 78493
Epoch: [14]  [190/312]  eta: 0:02:14  lr: 0.002922  min_lr: 0.002922  loss: 3.6738 (3.5186)  weight_decay: 0.0500 (0.0500)  time: 1.0076  data: 0.0004  max mem: 78493
Epoch: [14]  [200/312]  eta: 0:02:02  lr: 0.002929  min_lr: 0.002929  loss: 3.7351 (3.5208)  weight_decay: 0.0500 (0.0500)  time: 1.0071  data: 0.0004  max mem: 78493
Epoch: [14]  [210/312]  eta: 0:01:51  lr: 0.002935  min_lr: 0.002935  loss: 3.6223 (3.5207)  weight_decay: 0.0500 (0.0500)  time: 1.0075  data: 0.0004  max mem: 78493
Epoch: [14]  [220/312]  eta: 0:01:39  lr: 0.002941  min_lr: 0.002941  loss: 3.5931 (3.5219)  weight_decay: 0.0500 (0.0500)  time: 1.0063  data: 0.0004  max mem: 78493
Epoch: [14]  [230/312]  eta: 0:01:28  lr: 0.002948  min_lr: 0.002948  loss: 3.5931 (3.5201)  weight_decay: 0.0500 (0.0500)  time: 1.0044  data: 0.0004  max mem: 78493
Epoch: [14]  [240/312]  eta: 0:01:17  lr: 0.002954  min_lr: 0.002954  loss: 3.4040 (3.5073)  weight_decay: 0.0500 (0.0500)  time: 1.0050  data: 0.0011  max mem: 78493
Epoch: [14]  [250/312]  eta: 0:01:06  lr: 0.002961  min_lr: 0.002961  loss: 3.4325 (3.5119)  weight_decay: 0.0500 (0.0500)  time: 1.0077  data: 0.0011  max mem: 78493
Epoch: [14]  [260/312]  eta: 0:00:55  lr: 0.002967  min_lr: 0.002967  loss: 3.6106 (3.5100)  weight_decay: 0.0500 (0.0500)  time: 1.0071  data: 0.0004  max mem: 78493
Epoch: [14]  [270/312]  eta: 0:00:44  lr: 0.002974  min_lr: 0.002974  loss: 3.6779 (3.5144)  weight_decay: 0.0500 (0.0500)  time: 1.0071  data: 0.0004  max mem: 78493
Epoch: [14]  [280/312]  eta: 0:00:34  lr: 0.002980  min_lr: 0.002980  loss: 3.6441 (3.5118)  weight_decay: 0.0500 (0.0500)  time: 1.0073  data: 0.0010  max mem: 78493
Epoch: [14]  [290/312]  eta: 0:00:23  lr: 0.002986  min_lr: 0.002986  loss: 3.6441 (3.5188)  weight_decay: 0.0500 (0.0500)  time: 1.0039  data: 0.0009  max mem: 78493
Epoch: [14]  [300/312]  eta: 0:00:12  lr: 0.002993  min_lr: 0.002993  loss: 3.7533 (3.5199)  weight_decay: 0.0500 (0.0500)  time: 1.0019  data: 0.0001  max mem: 78493
Epoch: [14]  [310/312]  eta: 0:00:02  lr: 0.002999  min_lr: 0.002999  loss: 3.5622 (3.5182)  weight_decay: 0.0500 (0.0500)  time: 1.0017  data: 0.0001  max mem: 78493
Epoch: [14]  [311/312]  eta: 0:00:01  lr: 0.003000  min_lr: 0.003000  loss: 3.5622 (3.5202)  weight_decay: 0.0500 (0.0500)  time: 1.0016  data: 0.0001  max mem: 78493
Epoch: [14] Total time: 0:05:33 (1.0684 s / it)
Averaged stats: lr: 0.003000  min_lr: 0.003000  loss: 3.5622 (3.4999)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:07  loss: 1.3843 (1.3843)  acc1: 69.0104 (69.0104)  acc5: 87.2396 (87.2396)  time: 7.5419  data: 7.2756  max mem: 78493
Test:  [8/9]  eta: 0:00:01  loss: 1.7719 (1.6208)  acc1: 62.7604 (61.7440)  acc5: 82.4219 (83.2480)  time: 1.0393  data: 0.8112  max mem: 78493
Test: Total time: 0:00:09 (1.0522 s / it)
* Acc@1 61.476 Acc@5 83.572 loss 1.619
Accuracy of the model on the 50000 test images: 61.5%
Max accuracy: 61.48%
Epoch: [15]  [  0/312]  eta: 1:20:58  lr: 0.003000  min_lr: 0.003000  loss: 3.3825 (3.3825)  weight_decay: 0.0500 (0.0500)  time: 15.5713  data: 14.5756  max mem: 78493
Epoch: [15]  [ 10/312]  eta: 0:12:41  lr: 0.003007  min_lr: 0.003007  loss: 3.6671 (3.5510)  weight_decay: 0.0500 (0.0500)  time: 2.5217  data: 1.3258  max mem: 78493
Epoch: [15]  [ 20/312]  eta: 0:08:48  lr: 0.003013  min_lr: 0.003013  loss: 3.6671 (3.6084)  weight_decay: 0.0500 (0.0500)  time: 1.1221  data: 0.0014  max mem: 78493
Epoch: [15]  [ 30/312]  eta: 0:07:17  lr: 0.003020  min_lr: 0.003020  loss: 3.4294 (3.5020)  weight_decay: 0.0500 (0.0500)  time: 1.0186  data: 0.0013  max mem: 78493
Epoch: [15]  [ 40/312]  eta: 0:06:26  lr: 0.003026  min_lr: 0.003026  loss: 3.7041 (3.5285)  weight_decay: 0.0500 (0.0500)  time: 1.0102  data: 0.0004  max mem: 78493
Epoch: [15]  [ 50/312]  eta: 0:05:50  lr: 0.003033  min_lr: 0.003033  loss: 3.7041 (3.4818)  weight_decay: 0.0500 (0.0500)  time: 1.0090  data: 0.0004  max mem: 78493
Epoch: [15]  [ 60/312]  eta: 0:05:23  lr: 0.003039  min_lr: 0.003039  loss: 3.5762 (3.5089)  weight_decay: 0.0500 (0.0500)  time: 1.0083  data: 0.0004  max mem: 78493
Epoch: [15]  [ 70/312]  eta: 0:05:01  lr: 0.003045  min_lr: 0.003045  loss: 3.6619 (3.4986)  weight_decay: 0.0500 (0.0500)  time: 1.0082  data: 0.0004  max mem: 78493
Epoch: [15]  [ 80/312]  eta: 0:04:42  lr: 0.003052  min_lr: 0.003052  loss: 3.6314 (3.4736)  weight_decay: 0.0500 (0.0500)  time: 1.0075  data: 0.0004  max mem: 78493
Epoch: [15]  [ 90/312]  eta: 0:04:24  lr: 0.003058  min_lr: 0.003058  loss: 3.5506 (3.4632)  weight_decay: 0.0500 (0.0500)  time: 1.0078  data: 0.0004  max mem: 78493
Epoch: [15]  [100/312]  eta: 0:04:09  lr: 0.003065  min_lr: 0.003065  loss: 3.4272 (3.4586)  weight_decay: 0.0500 (0.0500)  time: 1.0084  data: 0.0004  max mem: 78493
Epoch: [15]  [110/312]  eta: 0:03:54  lr: 0.003071  min_lr: 0.003071  loss: 3.5484 (3.4584)  weight_decay: 0.0500 (0.0500)  time: 1.0078  data: 0.0004  max mem: 78493
Epoch: [15]  [120/312]  eta: 0:03:40  lr: 0.003077  min_lr: 0.003077  loss: 3.5703 (3.4543)  weight_decay: 0.0500 (0.0500)  time: 1.0064  data: 0.0004  max mem: 78493
Epoch: [15]  [130/312]  eta: 0:03:26  lr: 0.003084  min_lr: 0.003084  loss: 3.4592 (3.4440)  weight_decay: 0.0500 (0.0500)  time: 1.0082  data: 0.0005  max mem: 78493
Epoch: [15]  [140/312]  eta: 0:03:13  lr: 0.003090  min_lr: 0.003090  loss: 3.4838 (3.4442)  weight_decay: 0.0500 (0.0500)  time: 1.0080  data: 0.0005  max mem: 78493
Epoch: [15]  [150/312]  eta: 0:03:01  lr: 0.003097  min_lr: 0.003097  loss: 3.5083 (3.4324)  weight_decay: 0.0500 (0.0500)  time: 1.0058  data: 0.0004  max mem: 78493
Epoch: [15]  [160/312]  eta: 0:02:49  lr: 0.003103  min_lr: 0.003103  loss: 3.5083 (3.4399)  weight_decay: 0.0500 (0.0500)  time: 1.0052  data: 0.0004  max mem: 78493
Epoch: [15]  [170/312]  eta: 0:02:37  lr: 0.003109  min_lr: 0.003109  loss: 3.6933 (3.4395)  weight_decay: 0.0500 (0.0500)  time: 1.0056  data: 0.0005  max mem: 78493
Epoch: [15]  [180/312]  eta: 0:02:25  lr: 0.003116  min_lr: 0.003116  loss: 3.2715 (3.4254)  weight_decay: 0.0500 (0.0500)  time: 1.0081  data: 0.0015  max mem: 78493
Epoch: [15]  [190/312]  eta: 0:02:13  lr: 0.003122  min_lr: 0.003122  loss: 3.1128 (3.4102)  weight_decay: 0.0500 (0.0500)  time: 1.0071  data: 0.0024  max mem: 78493
Epoch: [15]  [200/312]  eta: 0:02:02  lr: 0.003129  min_lr: 0.003129  loss: 3.1744 (3.4097)  weight_decay: 0.0500 (0.0500)  time: 1.0056  data: 0.0013  max mem: 78493
Epoch: [15]  [210/312]  eta: 0:01:50  lr: 0.003135  min_lr: 0.003135  loss: 3.4273 (3.4065)  weight_decay: 0.0500 (0.0500)  time: 1.0068  data: 0.0004  max mem: 78493
Epoch: [15]  [220/312]  eta: 0:01:39  lr: 0.003142  min_lr: 0.003142  loss: 3.1887 (3.3971)  weight_decay: 0.0500 (0.0500)  time: 1.0083  data: 0.0005  max mem: 78493
Epoch: [15]  [230/312]  eta: 0:01:28  lr: 0.003148  min_lr: 0.003148  loss: 3.1580 (3.3962)  weight_decay: 0.0500 (0.0500)  time: 1.0084  data: 0.0005  max mem: 78493
Epoch: [15]  [240/312]  eta: 0:01:17  lr: 0.003154  min_lr: 0.003154  loss: 3.4646 (3.4031)  weight_decay: 0.0500 (0.0500)  time: 1.0055  data: 0.0005  max mem: 78493
Epoch: [15]  [250/312]  eta: 0:01:06  lr: 0.003161  min_lr: 0.003161  loss: 3.5114 (3.4032)  weight_decay: 0.0500 (0.0500)  time: 1.0042  data: 0.0005  max mem: 78493
Epoch: [15]  [260/312]  eta: 0:00:55  lr: 0.003167  min_lr: 0.003167  loss: 3.6971 (3.4122)  weight_decay: 0.0500 (0.0500)  time: 1.0049  data: 0.0005  max mem: 78493
Epoch: [15]  [270/312]  eta: 0:00:44  lr: 0.003174  min_lr: 0.003174  loss: 3.6971 (3.4110)  weight_decay: 0.0500 (0.0500)  time: 1.0058  data: 0.0012  max mem: 78493
Epoch: [15]  [280/312]  eta: 0:00:34  lr: 0.003180  min_lr: 0.003180  loss: 3.4826 (3.4110)  weight_decay: 0.0500 (0.0500)  time: 1.0066  data: 0.0017  max mem: 78493
Epoch: [15]  [290/312]  eta: 0:00:23  lr: 0.003186  min_lr: 0.003186  loss: 3.3909 (3.4043)  weight_decay: 0.0500 (0.0500)  time: 1.0047  data: 0.0009  max mem: 78493
Epoch: [15]  [300/312]  eta: 0:00:12  lr: 0.003193  min_lr: 0.003193  loss: 3.6265 (3.4140)  weight_decay: 0.0500 (0.0500)  time: 1.0021  data: 0.0001  max mem: 78493
Epoch: [15]  [310/312]  eta: 0:00:02  lr: 0.003199  min_lr: 0.003199  loss: 3.7056 (3.4167)  weight_decay: 0.0500 (0.0500)  time: 1.0019  data: 0.0001  max mem: 78493
Epoch: [15]  [311/312]  eta: 0:00:01  lr: 0.003200  min_lr: 0.003200  loss: 3.6299 (3.4171)  weight_decay: 0.0500 (0.0500)  time: 1.0020  data: 0.0001  max mem: 78493
Epoch: [15] Total time: 0:05:32 (1.0666 s / it)
Averaged stats: lr: 0.003200  min_lr: 0.003200  loss: 3.6299 (3.4016)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:14  loss: 1.3115 (1.3115)  acc1: 70.0521 (70.0521)  acc5: 87.1094 (87.1094)  time: 8.3243  data: 8.0553  max mem: 78493
Test:  [8/9]  eta: 0:00:01  loss: 1.7071 (1.5746)  acc1: 60.2865 (62.1920)  acc5: 84.7656 (83.9200)  time: 1.1239  data: 0.8951  max mem: 78493
Test: Total time: 0:00:10 (1.1638 s / it)
* Acc@1 62.024 Acc@5 84.102 loss 1.565
Accuracy of the model on the 50000 test images: 62.0%
Max accuracy: 62.02%
Epoch: [16]  [  0/312]  eta: 1:30:16  lr: 0.003201  min_lr: 0.003201  loss: 3.3710 (3.3710)  weight_decay: 0.0500 (0.0500)  time: 17.3596  data: 16.3592  max mem: 78493
Epoch: [16]  [ 10/312]  eta: 0:13:01  lr: 0.003207  min_lr: 0.003207  loss: 3.6635 (3.4935)  weight_decay: 0.0500 (0.0500)  time: 2.5880  data: 1.4901  max mem: 78493
Epoch: [16]  [ 20/312]  eta: 0:08:56  lr: 0.003213  min_lr: 0.003213  loss: 3.6253 (3.4693)  weight_decay: 0.0500 (0.0500)  time: 1.0630  data: 0.0019  max mem: 78493
Epoch: [16]  [ 30/312]  eta: 0:07:22  lr: 0.003220  min_lr: 0.003220  loss: 3.4713 (3.4195)  weight_decay: 0.0500 (0.0500)  time: 1.0104  data: 0.0005  max mem: 78493
Epoch: [16]  [ 40/312]  eta: 0:06:29  lr: 0.003226  min_lr: 0.003226  loss: 3.2072 (3.3869)  weight_decay: 0.0500 (0.0500)  time: 1.0052  data: 0.0004  max mem: 78493
Epoch: [16]  [ 50/312]  eta: 0:05:53  lr: 0.003233  min_lr: 0.003233  loss: 3.3979 (3.3705)  weight_decay: 0.0500 (0.0500)  time: 1.0050  data: 0.0004  max mem: 78493
Epoch: [16]  [ 60/312]  eta: 0:05:25  lr: 0.003239  min_lr: 0.003239  loss: 3.3979 (3.3665)  weight_decay: 0.0500 (0.0500)  time: 1.0069  data: 0.0004  max mem: 78493
Epoch: [16]  [ 70/312]  eta: 0:05:03  lr: 0.003245  min_lr: 0.003245  loss: 3.4905 (3.3966)  weight_decay: 0.0500 (0.0500)  time: 1.0074  data: 0.0004  max mem: 78493
Epoch: [16]  [ 80/312]  eta: 0:04:43  lr: 0.003252  min_lr: 0.003252  loss: 3.6292 (3.3690)  weight_decay: 0.0500 (0.0500)  time: 1.0064  data: 0.0004  max mem: 78493
Epoch: [16]  [ 90/312]  eta: 0:04:26  lr: 0.003258  min_lr: 0.003258  loss: 3.5488 (3.3810)  weight_decay: 0.0500 (0.0500)  time: 1.0068  data: 0.0012  max mem: 78493
Epoch: [16]  [100/312]  eta: 0:04:10  lr: 0.003265  min_lr: 0.003265  loss: 3.5379 (3.3623)  weight_decay: 0.0500 (0.0500)  time: 1.0065  data: 0.0012  max mem: 78493
Epoch: [16]  [110/312]  eta: 0:03:55  lr: 0.003271  min_lr: 0.003271  loss: 3.2109 (3.3619)  weight_decay: 0.0500 (0.0500)  time: 1.0066  data: 0.0004  max mem: 78493
Epoch: [16]  [120/312]  eta: 0:03:40  lr: 0.003277  min_lr: 0.003277  loss: 3.3639 (3.3599)  weight_decay: 0.0500 (0.0500)  time: 1.0073  data: 0.0004  max mem: 78493
Epoch: [16]  [130/312]  eta: 0:03:27  lr: 0.003284  min_lr: 0.003284  loss: 3.2250 (3.3528)  weight_decay: 0.0500 (0.0500)  time: 1.0071  data: 0.0004  max mem: 78493
Epoch: [16]  [140/312]  eta: 0:03:14  lr: 0.003290  min_lr: 0.003290  loss: 3.3010 (3.3612)  weight_decay: 0.0500 (0.0500)  time: 1.0090  data: 0.0004  max mem: 78493
Epoch: [16]  [150/312]  eta: 0:03:01  lr: 0.003297  min_lr: 0.003297  loss: 3.6032 (3.3718)  weight_decay: 0.0500 (0.0500)  time: 1.0101  data: 0.0004  max mem: 78493
Epoch: [16]  [160/312]  eta: 0:02:49  lr: 0.003303  min_lr: 0.003303  loss: 3.4816 (3.3651)  weight_decay: 0.0500 (0.0500)  time: 1.0082  data: 0.0004  max mem: 78493
Epoch: [16]  [170/312]  eta: 0:02:37  lr: 0.003310  min_lr: 0.003310  loss: 3.4201 (3.3731)  weight_decay: 0.0500 (0.0500)  time: 1.0076  data: 0.0005  max mem: 78493
Epoch: [16]  [180/312]  eta: 0:02:25  lr: 0.003316  min_lr: 0.003316  loss: 3.4525 (3.3697)  weight_decay: 0.0500 (0.0500)  time: 1.0066  data: 0.0004  max mem: 78493
Epoch: [16]  [190/312]  eta: 0:02:14  lr: 0.003322  min_lr: 0.003322  loss: 3.4715 (3.3774)  weight_decay: 0.0500 (0.0500)  time: 1.0062  data: 0.0004  max mem: 78493
Epoch: [16]  [200/312]  eta: 0:02:02  lr: 0.003329  min_lr: 0.003329  loss: 3.3722 (3.3667)  weight_decay: 0.0500 (0.0500)  time: 1.0076  data: 0.0004  max mem: 78493
Epoch: [16]  [210/312]  eta: 0:01:51  lr: 0.003335  min_lr: 0.003335  loss: 3.5051 (3.3746)  weight_decay: 0.0500 (0.0500)  time: 1.0072  data: 0.0004  max mem: 78493
Epoch: [16]  [220/312]  eta: 0:01:39  lr: 0.003342  min_lr: 0.003342  loss: 3.6456 (3.3768)  weight_decay: 0.0500 (0.0500)  time: 1.0068  data: 0.0004  max mem: 78493
Epoch: [16]  [230/312]  eta: 0:01:28  lr: 0.003348  min_lr: 0.003348  loss: 3.5492 (3.3862)  weight_decay: 0.0500 (0.0500)  time: 1.0061  data: 0.0004  max mem: 78493
Epoch: [16]  [240/312]  eta: 0:01:17  lr: 0.003354  min_lr: 0.003354  loss: 3.5273 (3.3820)  weight_decay: 0.0500 (0.0500)  time: 1.0046  data: 0.0004  max mem: 78493
Epoch: [16]  [250/312]  eta: 0:01:06  lr: 0.003361  min_lr: 0.003361  loss: 3.5657 (3.3871)  weight_decay: 0.0500 (0.0500)  time: 1.0047  data: 0.0004  max mem: 78493
Epoch: [16]  [260/312]  eta: 0:00:55  lr: 0.003367  min_lr: 0.003367  loss: 3.5802 (3.3837)  weight_decay: 0.0500 (0.0500)  time: 1.0045  data: 0.0004  max mem: 78493
Epoch: [16]  [270/312]  eta: 0:00:44  lr: 0.003374  min_lr: 0.003374  loss: 3.5234 (3.3847)  weight_decay: 0.0500 (0.0500)  time: 1.0041  data: 0.0004  max mem: 78493
Epoch: [16]  [280/312]  eta: 0:00:34  lr: 0.003380  min_lr: 0.003380  loss: 3.4788 (3.3848)  weight_decay: 0.0500 (0.0500)  time: 1.0052  data: 0.0010  max mem: 78493
Epoch: [16]  [290/312]  eta: 0:00:23  lr: 0.003386  min_lr: 0.003386  loss: 3.4477 (3.3831)  weight_decay: 0.0500 (0.0500)  time: 1.0043  data: 0.0009  max mem: 78493
Epoch: [16]  [300/312]  eta: 0:00:12  lr: 0.003393  min_lr: 0.003393  loss: 3.5528 (3.3856)  weight_decay: 0.0500 (0.0500)  time: 1.0022  data: 0.0001  max mem: 78493
Epoch: [16]  [310/312]  eta: 0:00:02  lr: 0.003399  min_lr: 0.003399  loss: 3.6150 (3.3915)  weight_decay: 0.0500 (0.0500)  time: 1.0020  data: 0.0001  max mem: 78493
Epoch: [16]  [311/312]  eta: 0:00:01  lr: 0.003400  min_lr: 0.003400  loss: 3.5528 (3.3917)  weight_decay: 0.0500 (0.0500)  time: 1.0020  data: 0.0001  max mem: 78493
Epoch: [16] Total time: 0:05:33 (1.0676 s / it)
Averaged stats: lr: 0.003400  min_lr: 0.003400  loss: 3.5528 (3.3709)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:16  loss: 1.3097 (1.3097)  acc1: 69.1406 (69.1406)  acc5: 88.9323 (88.9323)  time: 8.5347  data: 8.2577  max mem: 78493
Test:  [8/9]  eta: 0:00:01  loss: 1.7428 (1.5594)  acc1: 61.3281 (62.5280)  acc5: 83.4635 (84.6400)  time: 1.1465  data: 0.9176  max mem: 78493
Test: Total time: 0:00:10 (1.1628 s / it)
* Acc@1 62.432 Acc@5 84.502 loss 1.566
Accuracy of the model on the 50000 test images: 62.4%
Max accuracy: 62.43%
Epoch: [17]  [  0/312]  eta: 1:20:50  lr: 0.003401  min_lr: 0.003401  loss: 3.0329 (3.0329)  weight_decay: 0.0500 (0.0500)  time: 15.5463  data: 13.6534  max mem: 78493
Epoch: [17]  [ 10/312]  eta: 0:12:41  lr: 0.003407  min_lr: 0.003407  loss: 3.0329 (3.1625)  weight_decay: 0.0500 (0.0500)  time: 2.5208  data: 1.3951  max mem: 78493
Epoch: [17]  [ 20/312]  eta: 0:08:50  lr: 0.003413  min_lr: 0.003413  loss: 3.3658 (3.2228)  weight_decay: 0.0500 (0.0500)  time: 1.1285  data: 0.0881  max mem: 78493
Epoch: [17]  [ 30/312]  eta: 0:07:18  lr: 0.003420  min_lr: 0.003420  loss: 3.1183 (3.2026)  weight_decay: 0.0500 (0.0500)  time: 1.0237  data: 0.0037  max mem: 78493
Epoch: [17]  [ 40/312]  eta: 0:06:26  lr: 0.003426  min_lr: 0.003426  loss: 3.5519 (3.2617)  weight_decay: 0.0500 (0.0500)  time: 1.0075  data: 0.0004  max mem: 78493
Epoch: [17]  [ 50/312]  eta: 0:05:50  lr: 0.003433  min_lr: 0.003433  loss: 3.6237 (3.3027)  weight_decay: 0.0500 (0.0500)  time: 1.0060  data: 0.0004  max mem: 78493
Epoch: [17]  [ 60/312]  eta: 0:05:23  lr: 0.003439  min_lr: 0.003439  loss: 3.5299 (3.2811)  weight_decay: 0.0500 (0.0500)  time: 1.0061  data: 0.0004  max mem: 78493
Epoch: [17]  [ 70/312]  eta: 0:05:01  lr: 0.003445  min_lr: 0.003445  loss: 3.1544 (3.2715)  weight_decay: 0.0500 (0.0500)  time: 1.0072  data: 0.0004  max mem: 78493
Epoch: [17]  [ 80/312]  eta: 0:04:42  lr: 0.003452  min_lr: 0.003452  loss: 3.2243 (3.2623)  weight_decay: 0.0500 (0.0500)  time: 1.0096  data: 0.0004  max mem: 78493
Epoch: [17]  [ 90/312]  eta: 0:04:25  lr: 0.003458  min_lr: 0.003458  loss: 3.2700 (3.2663)  weight_decay: 0.0500 (0.0500)  time: 1.0110  data: 0.0004  max mem: 78493
Epoch: [17]  [100/312]  eta: 0:04:09  lr: 0.003465  min_lr: 0.003465  loss: 3.4519 (3.2903)  weight_decay: 0.0500 (0.0500)  time: 1.0083  data: 0.0005  max mem: 78493
Epoch: [17]  [110/312]  eta: 0:03:54  lr: 0.003471  min_lr: 0.003471  loss: 3.4552 (3.2969)  weight_decay: 0.0500 (0.0500)  time: 1.0051  data: 0.0005  max mem: 78493
Epoch: [17]  [120/312]  eta: 0:03:40  lr: 0.003477  min_lr: 0.003477  loss: 3.2850 (3.2848)  weight_decay: 0.0500 (0.0500)  time: 1.0064  data: 0.0005  max mem: 78493
Epoch: [17]  [130/312]  eta: 0:03:26  lr: 0.003484  min_lr: 0.003484  loss: 3.3293 (3.2861)  weight_decay: 0.0500 (0.0500)  time: 1.0072  data: 0.0004  max mem: 78493
Epoch: [17]  [140/312]  eta: 0:03:13  lr: 0.003490  min_lr: 0.003490  loss: 3.5061 (3.2927)  weight_decay: 0.0500 (0.0500)  time: 1.0059  data: 0.0004  max mem: 78493
Epoch: [17]  [150/312]  eta: 0:03:01  lr: 0.003497  min_lr: 0.003497  loss: 3.5070 (3.2987)  weight_decay: 0.0500 (0.0500)  time: 1.0057  data: 0.0005  max mem: 78493
Epoch: [17]  [160/312]  eta: 0:02:49  lr: 0.003503  min_lr: 0.003503  loss: 3.5305 (3.3083)  weight_decay: 0.0500 (0.0500)  time: 1.0059  data: 0.0005  max mem: 78493
Epoch: [17]  [170/312]  eta: 0:02:37  lr: 0.003510  min_lr: 0.003510  loss: 3.6382 (3.3134)  weight_decay: 0.0500 (0.0500)  time: 1.0062  data: 0.0012  max mem: 78493
Epoch: [17]  [180/312]  eta: 0:02:25  lr: 0.003516  min_lr: 0.003516  loss: 3.1473 (3.2996)  weight_decay: 0.0500 (0.0500)  time: 1.0050  data: 0.0013  max mem: 78493
Epoch: [17]  [190/312]  eta: 0:02:13  lr: 0.003522  min_lr: 0.003522  loss: 3.4676 (3.3111)  weight_decay: 0.0500 (0.0500)  time: 1.0050  data: 0.0005  max mem: 78493
Epoch: [17]  [200/312]  eta: 0:02:02  lr: 0.003529  min_lr: 0.003529  loss: 3.5333 (3.3097)  weight_decay: 0.0500 (0.0500)  time: 1.0072  data: 0.0005  max mem: 78493
Epoch: [17]  [210/312]  eta: 0:01:50  lr: 0.003535  min_lr: 0.003535  loss: 3.1539 (3.3037)  weight_decay: 0.0500 (0.0500)  time: 1.0077  data: 0.0004  max mem: 78493
Epoch: [17]  [220/312]  eta: 0:01:39  lr: 0.003542  min_lr: 0.003542  loss: 3.4722 (3.3107)  weight_decay: 0.0500 (0.0500)  time: 1.0078  data: 0.0019  max mem: 78493
Epoch: [17]  [230/312]  eta: 0:01:28  lr: 0.003548  min_lr: 0.003548  loss: 3.4504 (3.3021)  weight_decay: 0.0500 (0.0500)  time: 1.0072  data: 0.0028  max mem: 78493
Epoch: [17]  [240/312]  eta: 0:01:17  lr: 0.003554  min_lr: 0.003554  loss: 3.3591 (3.3006)  weight_decay: 0.0500 (0.0500)  time: 1.0081  data: 0.0013  max mem: 78493
Epoch: [17]  [250/312]  eta: 0:01:06  lr: 0.003561  min_lr: 0.003561  loss: 3.4087 (3.2962)  weight_decay: 0.0500 (0.0500)  time: 1.0085  data: 0.0004  max mem: 78493
Epoch: [17]  [260/312]  eta: 0:00:55  lr: 0.003567  min_lr: 0.003567  loss: 3.2937 (3.2959)  weight_decay: 0.0500 (0.0500)  time: 1.0081  data: 0.0004  max mem: 78493
Epoch: [17]  [270/312]  eta: 0:00:44  lr: 0.003574  min_lr: 0.003574  loss: 3.1385 (3.2908)  weight_decay: 0.0500 (0.0500)  time: 1.0071  data: 0.0004  max mem: 78493
Epoch: [17]  [280/312]  eta: 0:00:34  lr: 0.003580  min_lr: 0.003580  loss: 3.2999 (3.2938)  weight_decay: 0.0500 (0.0500)  time: 1.0061  data: 0.0011  max mem: 78493
Epoch: [17]  [290/312]  eta: 0:00:23  lr: 0.003586  min_lr: 0.003586  loss: 3.5690 (3.2981)  weight_decay: 0.0500 (0.0500)  time: 1.0049  data: 0.0009  max mem: 78493
Epoch: [17]  [300/312]  eta: 0:00:12  lr: 0.003593  min_lr: 0.003593  loss: 3.3740 (3.2929)  weight_decay: 0.0500 (0.0500)  time: 1.0019  data: 0.0001  max mem: 78493
Epoch: [17]  [310/312]  eta: 0:00:02  lr: 0.003599  min_lr: 0.003599  loss: 3.3359 (3.2936)  weight_decay: 0.0500 (0.0500)  time: 1.0019  data: 0.0001  max mem: 78493
Epoch: [17]  [311/312]  eta: 0:00:01  lr: 0.003600  min_lr: 0.003600  loss: 3.3668 (3.2943)  weight_decay: 0.0500 (0.0500)  time: 1.0019  data: 0.0001  max mem: 78493
Epoch: [17] Total time: 0:05:32 (1.0671 s / it)
Averaged stats: lr: 0.003600  min_lr: 0.003600  loss: 3.3668 (3.3158)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:19  loss: 1.3170 (1.3170)  acc1: 68.8802 (68.8802)  acc5: 88.9323 (88.9323)  time: 8.7972  data: 8.5146  max mem: 78493
Test:  [8/9]  eta: 0:00:01  loss: 1.7346 (1.5715)  acc1: 60.8073 (62.4320)  acc5: 82.1615 (84.3840)  time: 1.1758  data: 0.9461  max mem: 78493
Test: Total time: 0:00:10 (1.2069 s / it)
* Acc@1 62.458 Acc@5 84.572 loss 1.566
Accuracy of the model on the 50000 test images: 62.5%
Max accuracy: 62.46%
Epoch: [18]  [  0/312]  eta: 1:19:25  lr: 0.003601  min_lr: 0.003601  loss: 2.6917 (2.6917)  weight_decay: 0.0500 (0.0500)  time: 15.2747  data: 13.0765  max mem: 78493
Epoch: [18]  [ 10/312]  eta: 0:13:08  lr: 0.003607  min_lr: 0.003607  loss: 3.5729 (3.3772)  weight_decay: 0.0500 (0.0500)  time: 2.6093  data: 1.3154  max mem: 78493
Epoch: [18]  [ 20/312]  eta: 0:09:00  lr: 0.003613  min_lr: 0.003613  loss: 3.5729 (3.4258)  weight_decay: 0.0500 (0.0500)  time: 1.1806  data: 0.0699  max mem: 78493
Epoch: [18]  [ 30/312]  eta: 0:07:25  lr: 0.003620  min_lr: 0.003620  loss: 3.4454 (3.3498)  weight_decay: 0.0500 (0.0500)  time: 1.0145  data: 0.0005  max mem: 78493
Epoch: [18]  [ 40/312]  eta: 0:06:31  lr: 0.003626  min_lr: 0.003626  loss: 3.2093 (3.3168)  weight_decay: 0.0500 (0.0500)  time: 1.0094  data: 0.0004  max mem: 78493
Epoch: [18]  [ 50/312]  eta: 0:05:55  lr: 0.003633  min_lr: 0.003633  loss: 3.1201 (3.3092)  weight_decay: 0.0500 (0.0500)  time: 1.0087  data: 0.0015  max mem: 78493
Epoch: [18]  [ 60/312]  eta: 0:05:27  lr: 0.003639  min_lr: 0.003639  loss: 3.1870 (3.2985)  weight_decay: 0.0500 (0.0500)  time: 1.0072  data: 0.0015  max mem: 78493
Epoch: [18]  [ 70/312]  eta: 0:05:04  lr: 0.003645  min_lr: 0.003645  loss: 3.4011 (3.3021)  weight_decay: 0.0500 (0.0500)  time: 1.0052  data: 0.0005  max mem: 78493
Epoch: [18]  [ 80/312]  eta: 0:04:44  lr: 0.003652  min_lr: 0.003652  loss: 3.4011 (3.3047)  weight_decay: 0.0500 (0.0500)  time: 1.0070  data: 0.0005  max mem: 78493
Epoch: [18]  [ 90/312]  eta: 0:04:27  lr: 0.003658  min_lr: 0.003658  loss: 3.4988 (3.3112)  weight_decay: 0.0500 (0.0500)  time: 1.0088  data: 0.0005  max mem: 78493
Epoch: [18]  [100/312]  eta: 0:04:10  lr: 0.003665  min_lr: 0.003665  loss: 3.2621 (3.2840)  weight_decay: 0.0500 (0.0500)  time: 1.0078  data: 0.0005  max mem: 78493
Epoch: [18]  [110/312]  eta: 0:03:55  lr: 0.003671  min_lr: 0.003671  loss: 3.1258 (3.2811)  weight_decay: 0.0500 (0.0500)  time: 1.0082  data: 0.0005  max mem: 78493
Epoch: [18]  [120/312]  eta: 0:03:41  lr: 0.003678  min_lr: 0.003678  loss: 3.1878 (3.2660)  weight_decay: 0.0500 (0.0500)  time: 1.0091  data: 0.0005  max mem: 78493
Epoch: [18]  [130/312]  eta: 0:03:28  lr: 0.003684  min_lr: 0.003684  loss: 3.2990 (3.2639)  weight_decay: 0.0500 (0.0500)  time: 1.0069  data: 0.0004  max mem: 78493
Epoch: [18]  [140/312]  eta: 0:03:14  lr: 0.003690  min_lr: 0.003690  loss: 3.3144 (3.2729)  weight_decay: 0.0500 (0.0500)  time: 1.0060  data: 0.0005  max mem: 78493
Epoch: [18]  [150/312]  eta: 0:03:02  lr: 0.003697  min_lr: 0.003697  loss: 3.3730 (3.2767)  weight_decay: 0.0500 (0.0500)  time: 1.0063  data: 0.0005  max mem: 78493
Epoch: [18]  [160/312]  eta: 0:02:49  lr: 0.003703  min_lr: 0.003703  loss: 3.3730 (3.2744)  weight_decay: 0.0500 (0.0500)  time: 1.0058  data: 0.0005  max mem: 78493
Epoch: [18]  [170/312]  eta: 0:02:37  lr: 0.003710  min_lr: 0.003710  loss: 3.4181 (3.2709)  weight_decay: 0.0500 (0.0500)  time: 1.0076  data: 0.0014  max mem: 78493
Epoch: [18]  [180/312]  eta: 0:02:25  lr: 0.003716  min_lr: 0.003716  loss: 3.1912 (3.2654)  weight_decay: 0.0500 (0.0500)  time: 1.0074  data: 0.0014  max mem: 78493
Epoch: [18]  [190/312]  eta: 0:02:14  lr: 0.003722  min_lr: 0.003722  loss: 3.2539 (3.2733)  weight_decay: 0.0500 (0.0500)  time: 1.0053  data: 0.0005  max mem: 78493
Epoch: [18]  [200/312]  eta: 0:02:02  lr: 0.003729  min_lr: 0.003729  loss: 3.2061 (3.2628)  weight_decay: 0.0500 (0.0500)  time: 1.0055  data: 0.0005  max mem: 78493
Epoch: [18]  [210/312]  eta: 0:01:51  lr: 0.003735  min_lr: 0.003735  loss: 3.4797 (3.2780)  weight_decay: 0.0500 (0.0500)  time: 1.0062  data: 0.0005  max mem: 78493
Epoch: [18]  [220/312]  eta: 0:01:40  lr: 0.003742  min_lr: 0.003742  loss: 3.5345 (3.2827)  weight_decay: 0.0500 (0.0500)  time: 1.0057  data: 0.0005  max mem: 78493
Epoch: [18]  [230/312]  eta: 0:01:28  lr: 0.003748  min_lr: 0.003748  loss: 3.3391 (3.2804)  weight_decay: 0.0500 (0.0500)  time: 1.0050  data: 0.0004  max mem: 78493
Epoch: [18]  [240/312]  eta: 0:01:17  lr: 0.003754  min_lr: 0.003754  loss: 3.2006 (3.2760)  weight_decay: 0.0500 (0.0500)  time: 1.0058  data: 0.0004  max mem: 78493
Epoch: [18]  [250/312]  eta: 0:01:06  lr: 0.003761  min_lr: 0.003761  loss: 3.5004 (3.2902)  weight_decay: 0.0500 (0.0500)  time: 1.0054  data: 0.0005  max mem: 78493
Epoch: [18]  [260/312]  eta: 0:00:55  lr: 0.003767  min_lr: 0.003767  loss: 3.6714 (3.3024)  weight_decay: 0.0500 (0.0500)  time: 1.0058  data: 0.0005  max mem: 78493
Epoch: [18]  [270/312]  eta: 0:00:45  lr: 0.003774  min_lr: 0.003774  loss: 3.6020 (3.3058)  weight_decay: 0.0500 (0.0500)  time: 1.0074  data: 0.0005  max mem: 78493
Epoch: [18]  [280/312]  eta: 0:00:34  lr: 0.003780  min_lr: 0.003780  loss: 3.1121 (3.2927)  weight_decay: 0.0500 (0.0500)  time: 1.0074  data: 0.0019  max mem: 78493
Epoch: [18]  [290/312]  eta: 0:00:23  lr: 0.003787  min_lr: 0.003787  loss: 2.9793 (3.2916)  weight_decay: 0.0500 (0.0500)  time: 1.0049  data: 0.0017  max mem: 78493
Epoch: [18]  [300/312]  eta: 0:00:12  lr: 0.003793  min_lr: 0.003793  loss: 3.3802 (3.2906)  weight_decay: 0.0500 (0.0500)  time: 1.0025  data: 0.0001  max mem: 78493
Epoch: [18]  [310/312]  eta: 0:00:02  lr: 0.003799  min_lr: 0.003799  loss: 3.4494 (3.2912)  weight_decay: 0.0500 (0.0500)  time: 1.0020  data: 0.0001  max mem: 78493
Epoch: [18]  [311/312]  eta: 0:00:01  lr: 0.003800  min_lr: 0.003800  loss: 3.5250 (3.2921)  weight_decay: 0.0500 (0.0500)  time: 1.0019  data: 0.0001  max mem: 78493
Epoch: [18] Total time: 0:05:33 (1.0688 s / it)
Averaged stats: lr: 0.003800  min_lr: 0.003800  loss: 3.5250 (3.2751)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:11  loss: 1.1316 (1.1316)  acc1: 72.2656 (72.2656)  acc5: 91.0156 (91.0156)  time: 7.9596  data: 7.6783  max mem: 78493
Test:  [8/9]  eta: 0:00:01  loss: 1.7360 (1.5000)  acc1: 62.6302 (63.5040)  acc5: 82.8125 (85.1040)  time: 1.0828  data: 0.8532  max mem: 78493
Test: Total time: 0:00:10 (1.1240 s / it)
* Acc@1 63.502 Acc@5 85.136 loss 1.510
Accuracy of the model on the 50000 test images: 63.5%
Max accuracy: 63.50%
Epoch: [19]  [  0/312]  eta: 1:22:18  lr: 0.003801  min_lr: 0.003801  loss: 3.5717 (3.5717)  weight_decay: 0.0500 (0.0500)  time: 15.8296  data: 14.8157  max mem: 78493
Epoch: [19]  [ 10/312]  eta: 0:13:12  lr: 0.003807  min_lr: 0.003807  loss: 3.5717 (3.4847)  weight_decay: 0.0500 (0.0500)  time: 2.6227  data: 1.3476  max mem: 78493
Epoch: [19]  [ 20/312]  eta: 0:09:01  lr: 0.003813  min_lr: 0.003813  loss: 3.4414 (3.3817)  weight_decay: 0.0500 (0.0500)  time: 1.1559  data: 0.0007  max mem: 78493
Epoch: [19]  [ 30/312]  eta: 0:07:25  lr: 0.003820  min_lr: 0.003820  loss: 3.2449 (3.2690)  weight_decay: 0.0500 (0.0500)  time: 1.0075  data: 0.0005  max mem: 78493
Epoch: [19]  [ 40/312]  eta: 0:06:31  lr: 0.003826  min_lr: 0.003826  loss: 3.3090 (3.3165)  weight_decay: 0.0500 (0.0500)  time: 1.0056  data: 0.0004  max mem: 78493
Epoch: [19]  [ 50/312]  eta: 0:05:54  lr: 0.003833  min_lr: 0.003833  loss: 3.5492 (3.3156)  weight_decay: 0.0500 (0.0500)  time: 1.0051  data: 0.0005  max mem: 78493
Epoch: [19]  [ 60/312]  eta: 0:05:27  lr: 0.003839  min_lr: 0.003839  loss: 3.4197 (3.3243)  weight_decay: 0.0500 (0.0500)  time: 1.0058  data: 0.0013  max mem: 78493
Epoch: [19]  [ 70/312]  eta: 0:05:04  lr: 0.003845  min_lr: 0.003845  loss: 3.3255 (3.3092)  weight_decay: 0.0500 (0.0500)  time: 1.0073  data: 0.0019  max mem: 78493
Epoch: [19]  [ 80/312]  eta: 0:04:44  lr: 0.003852  min_lr: 0.003852  loss: 3.3154 (3.3168)  weight_decay: 0.0500 (0.0500)  time: 1.0061  data: 0.0011  max mem: 78493
Epoch: [19]  [ 90/312]  eta: 0:04:26  lr: 0.003858  min_lr: 0.003858  loss: 3.3401 (3.3119)  weight_decay: 0.0500 (0.0500)  time: 1.0060  data: 0.0004  max mem: 78493
Epoch: [19]  [100/312]  eta: 0:04:10  lr: 0.003865  min_lr: 0.003865  loss: 3.3401 (3.2933)  weight_decay: 0.0500 (0.0500)  time: 1.0064  data: 0.0005  max mem: 78493
Epoch: [19]  [110/312]  eta: 0:03:55  lr: 0.003871  min_lr: 0.003871  loss: 3.0326 (3.2743)  weight_decay: 0.0500 (0.0500)  time: 1.0065  data: 0.0004  max mem: 78493
Epoch: [19]  [120/312]  eta: 0:03:41  lr: 0.003878  min_lr: 0.003878  loss: 3.0630 (3.2693)  weight_decay: 0.0500 (0.0500)  time: 1.0063  data: 0.0005  max mem: 78493
Epoch: [19]  [130/312]  eta: 0:03:27  lr: 0.003884  min_lr: 0.003884  loss: 3.1503 (3.2654)  weight_decay: 0.0500 (0.0500)  time: 1.0064  data: 0.0005  max mem: 78493
Epoch: [19]  [140/312]  eta: 0:03:14  lr: 0.003890  min_lr: 0.003890  loss: 3.4013 (3.2833)  weight_decay: 0.0500 (0.0500)  time: 1.0062  data: 0.0004  max mem: 78493
Epoch: [19]  [150/312]  eta: 0:03:02  lr: 0.003897  min_lr: 0.003897  loss: 3.4514 (3.2893)  weight_decay: 0.0500 (0.0500)  time: 1.0061  data: 0.0004  max mem: 78493
Epoch: [19]  [160/312]  eta: 0:02:49  lr: 0.003903  min_lr: 0.003903  loss: 3.3553 (3.2870)  weight_decay: 0.0500 (0.0500)  time: 1.0060  data: 0.0004  max mem: 78493
Epoch: [19]  [170/312]  eta: 0:02:37  lr: 0.003910  min_lr: 0.003910  loss: 3.3246 (3.2845)  weight_decay: 0.0500 (0.0500)  time: 1.0052  data: 0.0004  max mem: 78493
Epoch: [19]  [180/312]  eta: 0:02:25  lr: 0.003916  min_lr: 0.003916  loss: 2.9554 (3.2734)  weight_decay: 0.0500 (0.0500)  time: 1.0073  data: 0.0004  max mem: 78493
Epoch: [19]  [190/312]  eta: 0:02:14  lr: 0.003922  min_lr: 0.003922  loss: 2.9818 (3.2695)  weight_decay: 0.0500 (0.0500)  time: 1.0064  data: 0.0004  max mem: 78493
Epoch: [19]  [200/312]  eta: 0:02:02  lr: 0.003929  min_lr: 0.003929  loss: 3.2009 (3.2631)  weight_decay: 0.0500 (0.0500)  time: 1.0069  data: 0.0004  max mem: 78493
Epoch: [19]  [210/312]  eta: 0:01:51  lr: 0.003935  min_lr: 0.003935  loss: 2.9525 (3.2530)  weight_decay: 0.0500 (0.0500)  time: 1.0080  data: 0.0004  max mem: 78493
Epoch: [19]  [220/312]  eta: 0:01:39  lr: 0.003942  min_lr: 0.003942  loss: 3.0840 (3.2495)  weight_decay: 0.0500 (0.0500)  time: 1.0066  data: 0.0004  max mem: 78493
Epoch: [19]  [230/312]  eta: 0:01:28  lr: 0.003948  min_lr: 0.003948  loss: 3.0903 (3.2445)  weight_decay: 0.0500 (0.0500)  time: 1.0069  data: 0.0004  max mem: 78493
Epoch: [19]  [240/312]  eta: 0:01:17  lr: 0.003954  min_lr: 0.003954  loss: 3.0863 (3.2477)  weight_decay: 0.0500 (0.0500)  time: 1.0067  data: 0.0004  max mem: 78493
Epoch: [19]  [250/312]  eta: 0:01:06  lr: 0.003961  min_lr: 0.003961  loss: 3.4623 (3.2534)  weight_decay: 0.0500 (0.0500)  time: 1.0071  data: 0.0004  max mem: 78493
Epoch: [19]  [260/312]  eta: 0:00:55  lr: 0.003967  min_lr: 0.003967  loss: 3.5122 (3.2568)  weight_decay: 0.0500 (0.0500)  time: 1.0072  data: 0.0004  max mem: 78493
Epoch: [19]  [270/312]  eta: 0:00:45  lr: 0.003974  min_lr: 0.003974  loss: 3.5058 (3.2610)  weight_decay: 0.0500 (0.0500)  time: 1.0085  data: 0.0016  max mem: 78493
Epoch: [19]  [280/312]  eta: 0:00:34  lr: 0.003980  min_lr: 0.003980  loss: 3.2519 (3.2503)  weight_decay: 0.0500 (0.0500)  time: 1.0086  data: 0.0033  max mem: 78493
Epoch: [19]  [290/312]  eta: 0:00:23  lr: 0.003987  min_lr: 0.003987  loss: 2.8686 (3.2428)  weight_decay: 0.0500 (0.0500)  time: 1.0043  data: 0.0019  max mem: 78493
Epoch: [19]  [300/312]  eta: 0:00:12  lr: 0.003993  min_lr: 0.003993  loss: 3.1924 (3.2389)  weight_decay: 0.0500 (0.0500)  time: 1.0014  data: 0.0001  max mem: 78493
Epoch: [19]  [310/312]  eta: 0:00:02  lr: 0.003999  min_lr: 0.003999  loss: 3.3052 (3.2432)  weight_decay: 0.0500 (0.0500)  time: 1.0016  data: 0.0001  max mem: 78493
Epoch: [19]  [311/312]  eta: 0:00:01  lr: 0.004000  min_lr: 0.004000  loss: 3.2834 (3.2431)  weight_decay: 0.0500 (0.0500)  time: 1.0016  data: 0.0001  max mem: 78493
Epoch: [19] Total time: 0:05:33 (1.0690 s / it)
Averaged stats: lr: 0.004000  min_lr: 0.004000  loss: 3.2834 (3.2318)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:15  loss: 1.2485 (1.2485)  acc1: 70.8333 (70.8333)  acc5: 89.5833 (89.5833)  time: 8.4390  data: 8.1762  max mem: 78493
Test:  [8/9]  eta: 0:00:01  loss: 1.7811 (1.5893)  acc1: 59.3750 (62.1760)  acc5: 82.2917 (83.9040)  time: 1.1408  data: 0.9085  max mem: 78493
Test: Total time: 0:00:10 (1.1902 s / it)
* Acc@1 62.054 Acc@5 84.098 loss 1.595
Accuracy of the model on the 50000 test images: 62.1%
Max accuracy: 63.50%
Epoch: [20]  [  0/312]  eta: 1:25:15  lr: 0.004000  min_lr: 0.004000  loss: 3.4274 (3.4274)  weight_decay: 0.0500 (0.0500)  time: 16.3967  data: 12.4451  max mem: 78493
Epoch: [20]  [ 10/312]  eta: 0:13:07  lr: 0.004000  min_lr: 0.004000  loss: 3.4987 (3.4717)  weight_decay: 0.0500 (0.0500)  time: 2.6077  data: 1.3067  max mem: 78493
Epoch: [20]  [ 20/312]  eta: 0:09:00  lr: 0.004000  min_lr: 0.004000  loss: 3.4096 (3.3699)  weight_decay: 0.0500 (0.0500)  time: 1.1229  data: 0.0976  max mem: 78493
Epoch: [20]  [ 30/312]  eta: 0:07:24  lr: 0.004000  min_lr: 0.004000  loss: 3.3909 (3.4178)  weight_decay: 0.0500 (0.0500)  time: 1.0100  data: 0.0014  max mem: 78493
Epoch: [20]  [ 40/312]  eta: 0:06:31  lr: 0.004000  min_lr: 0.004000  loss: 3.4471 (3.3566)  weight_decay: 0.0500 (0.0500)  time: 1.0056  data: 0.0004  max mem: 78493
Epoch: [20]  [ 50/312]  eta: 0:05:54  lr: 0.004000  min_lr: 0.004000  loss: 3.3356 (3.3543)  weight_decay: 0.0500 (0.0500)  time: 1.0062  data: 0.0004  max mem: 78493
Epoch: [20]  [ 60/312]  eta: 0:05:26  lr: 0.004000  min_lr: 0.004000  loss: 3.3837 (3.3718)  weight_decay: 0.0500 (0.0500)  time: 1.0063  data: 0.0004  max mem: 78493
Epoch: [20]  [ 70/312]  eta: 0:05:03  lr: 0.004000  min_lr: 0.004000  loss: 3.5957 (3.3957)  weight_decay: 0.0500 (0.0500)  time: 1.0082  data: 0.0004  max mem: 78493
Epoch: [20]  [ 80/312]  eta: 0:04:44  lr: 0.004000  min_lr: 0.004000  loss: 3.4494 (3.3626)  weight_decay: 0.0500 (0.0500)  time: 1.0087  data: 0.0004  max mem: 78493
Epoch: [20]  [ 90/312]  eta: 0:04:26  lr: 0.004000  min_lr: 0.004000  loss: 3.2900 (3.3500)  weight_decay: 0.0500 (0.0500)  time: 1.0106  data: 0.0015  max mem: 78493
Epoch: [20]  [100/312]  eta: 0:04:10  lr: 0.004000  min_lr: 0.004000  loss: 3.2712 (3.3376)  weight_decay: 0.0500 (0.0500)  time: 1.0096  data: 0.0015  max mem: 78493
Epoch: [20]  [110/312]  eta: 0:03:55  lr: 0.004000  min_lr: 0.004000  loss: 3.2889 (3.3286)  weight_decay: 0.0500 (0.0500)  time: 1.0071  data: 0.0013  max mem: 78493
Epoch: [20]  [120/312]  eta: 0:03:41  lr: 0.004000  min_lr: 0.004000  loss: 3.4257 (3.3160)  weight_decay: 0.0500 (0.0500)  time: 1.0065  data: 0.0012  max mem: 78493
Epoch: [20]  [130/312]  eta: 0:03:27  lr: 0.004000  min_lr: 0.004000  loss: 3.4293 (3.3119)  weight_decay: 0.0500 (0.0500)  time: 1.0054  data: 0.0005  max mem: 78493
Epoch: [20]  [140/312]  eta: 0:03:14  lr: 0.004000  min_lr: 0.004000  loss: 3.3298 (3.3152)  weight_decay: 0.0500 (0.0500)  time: 1.0058  data: 0.0005  max mem: 78493
Epoch: [20]  [150/312]  eta: 0:03:02  lr: 0.004000  min_lr: 0.004000  loss: 3.3250 (3.3042)  weight_decay: 0.0500 (0.0500)  time: 1.0070  data: 0.0005  max mem: 78493
Epoch: [20]  [160/312]  eta: 0:02:49  lr: 0.004000  min_lr: 0.004000  loss: 3.0945 (3.2970)  weight_decay: 0.0500 (0.0500)  time: 1.0074  data: 0.0005  max mem: 78493
Epoch: [20]  [170/312]  eta: 0:02:37  lr: 0.004000  min_lr: 0.004000  loss: 3.2054 (3.2888)  weight_decay: 0.0500 (0.0500)  time: 1.0090  data: 0.0005  max mem: 78493
Epoch: [20]  [180/312]  eta: 0:02:25  lr: 0.004000  min_lr: 0.004000  loss: 3.3604 (3.2974)  weight_decay: 0.0500 (0.0500)  time: 1.0083  data: 0.0004  max mem: 78493
Epoch: [20]  [190/312]  eta: 0:02:14  lr: 0.004000  min_lr: 0.004000  loss: 3.3604 (3.2818)  weight_decay: 0.0500 (0.0500)  time: 1.0084  data: 0.0005  max mem: 78493
Epoch: [20]  [200/312]  eta: 0:02:02  lr: 0.004000  min_lr: 0.004000  loss: 3.0890 (3.2764)  weight_decay: 0.0500 (0.0500)  time: 1.0088  data: 0.0005  max mem: 78493
Epoch: [20]  [210/312]  eta: 0:01:51  lr: 0.004000  min_lr: 0.004000  loss: 3.1611 (3.2653)  weight_decay: 0.0500 (0.0500)  time: 1.0077  data: 0.0004  max mem: 78493
Epoch: [20]  [220/312]  eta: 0:01:40  lr: 0.004000  min_lr: 0.004000  loss: 3.0486 (3.2545)  weight_decay: 0.0500 (0.0500)  time: 1.0066  data: 0.0004  max mem: 78493
Epoch: [20]  [230/312]  eta: 0:01:28  lr: 0.004000  min_lr: 0.004000  loss: 3.0360 (3.2471)  weight_decay: 0.0500 (0.0500)  time: 1.0061  data: 0.0004  max mem: 78493
Epoch: [20]  [240/312]  eta: 0:01:17  lr: 0.004000  min_lr: 0.004000  loss: 2.9870 (3.2356)  weight_decay: 0.0500 (0.0500)  time: 1.0054  data: 0.0004  max mem: 78493
Epoch: [20]  [250/312]  eta: 0:01:06  lr: 0.004000  min_lr: 0.004000  loss: 3.0600 (3.2336)  weight_decay: 0.0500 (0.0500)  time: 1.0050  data: 0.0005  max mem: 78493
Epoch: [20]  [260/312]  eta: 0:00:55  lr: 0.004000  min_lr: 0.004000  loss: 3.3412 (3.2264)  weight_decay: 0.0500 (0.0500)  time: 1.0053  data: 0.0005  max mem: 78493
Epoch: [20]  [270/312]  eta: 0:00:45  lr: 0.004000  min_lr: 0.004000  loss: 3.4271 (3.2323)  weight_decay: 0.0500 (0.0500)  time: 1.0047  data: 0.0005  max mem: 78493
Epoch: [20]  [280/312]  eta: 0:00:34  lr: 0.004000  min_lr: 0.004000  loss: 3.3201 (3.2281)  weight_decay: 0.0500 (0.0500)  time: 1.0049  data: 0.0017  max mem: 78493
Epoch: [20]  [290/312]  eta: 0:00:23  lr: 0.004000  min_lr: 0.004000  loss: 3.2822 (3.2281)  weight_decay: 0.0500 (0.0500)  time: 1.0036  data: 0.0015  max mem: 78493
Epoch: [20]  [300/312]  eta: 0:00:12  lr: 0.004000  min_lr: 0.004000  loss: 3.3461 (3.2335)  weight_decay: 0.0500 (0.0500)  time: 1.0019  data: 0.0001  max mem: 78493
Epoch: [20]  [310/312]  eta: 0:00:02  lr: 0.004000  min_lr: 0.004000  loss: 3.3461 (3.2348)  weight_decay: 0.0500 (0.0500)  time: 1.0016  data: 0.0001  max mem: 78493
Epoch: [20]  [311/312]  eta: 0:00:01  lr: 0.004000  min_lr: 0.004000  loss: 3.3919 (3.2356)  weight_decay: 0.0500 (0.0500)  time: 1.0016  data: 0.0001  max mem: 78493
Epoch: [20] Total time: 0:05:33 (1.0689 s / it)
Averaged stats: lr: 0.004000  min_lr: 0.004000  loss: 3.3919 (3.2040)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:07  loss: 1.2855 (1.2855)  acc1: 70.8333 (70.8333)  acc5: 87.7604 (87.7604)  time: 7.4906  data: 7.2136  max mem: 78493
Test:  [8/9]  eta: 0:00:01  loss: 1.6816 (1.5346)  acc1: 61.4583 (62.8480)  acc5: 83.9844 (84.8000)  time: 1.0850  data: 0.8543  max mem: 78493
Test: Total time: 0:00:09 (1.0980 s / it)
* Acc@1 62.746 Acc@5 84.896 loss 1.533
Accuracy of the model on the 50000 test images: 62.7%
Max accuracy: 63.50%
Epoch: [21]  [  0/312]  eta: 1:21:03  lr: 0.004000  min_lr: 0.004000  loss: 2.7334 (2.7334)  weight_decay: 0.0500 (0.0500)  time: 15.5869  data: 13.4619  max mem: 78493
Epoch: [21]  [ 10/312]  eta: 0:13:01  lr: 0.004000  min_lr: 0.004000  loss: 2.8930 (3.0634)  weight_decay: 0.0500 (0.0500)  time: 2.5863  data: 1.2245  max mem: 78493
Epoch: [21]  [ 20/312]  eta: 0:09:00  lr: 0.004000  min_lr: 0.004000  loss: 3.1909 (3.1943)  weight_decay: 0.0500 (0.0500)  time: 1.1634  data: 0.0007  max mem: 78493
Epoch: [21]  [ 30/312]  eta: 0:07:25  lr: 0.004000  min_lr: 0.004000  loss: 3.3170 (3.1482)  weight_decay: 0.0500 (0.0500)  time: 1.0235  data: 0.0005  max mem: 78493
Epoch: [21]  [ 40/312]  eta: 0:06:31  lr: 0.004000  min_lr: 0.004000  loss: 3.1590 (3.1728)  weight_decay: 0.0500 (0.0500)  time: 1.0082  data: 0.0005  max mem: 78493
Epoch: [21]  [ 50/312]  eta: 0:05:54  lr: 0.004000  min_lr: 0.004000  loss: 3.2716 (3.1632)  weight_decay: 0.0500 (0.0500)  time: 1.0074  data: 0.0004  max mem: 78493
Epoch: [21]  [ 60/312]  eta: 0:05:26  lr: 0.004000  min_lr: 0.004000  loss: 3.2024 (3.1369)  weight_decay: 0.0500 (0.0500)  time: 1.0063  data: 0.0004  max mem: 78493
Epoch: [21]  [ 70/312]  eta: 0:05:04  lr: 0.004000  min_lr: 0.004000  loss: 3.2192 (3.1701)  weight_decay: 0.0500 (0.0500)  time: 1.0094  data: 0.0004  max mem: 78493
Epoch: [21]  [ 80/312]  eta: 0:04:44  lr: 0.004000  min_lr: 0.004000  loss: 3.2918 (3.1485)  weight_decay: 0.0500 (0.0500)  time: 1.0088  data: 0.0004  max mem: 78493
Epoch: [21]  [ 90/312]  eta: 0:04:26  lr: 0.004000  min_lr: 0.004000  loss: 3.2840 (3.1554)  weight_decay: 0.0500 (0.0500)  time: 1.0076  data: 0.0005  max mem: 78493
Epoch: [21]  [100/312]  eta: 0:04:10  lr: 0.004000  min_lr: 0.004000  loss: 3.1732 (3.1527)  weight_decay: 0.0500 (0.0500)  time: 1.0064  data: 0.0005  max mem: 78493
Epoch: [21]  [110/312]  eta: 0:03:55  lr: 0.004000  min_lr: 0.004000  loss: 3.1492 (3.1481)  weight_decay: 0.0500 (0.0500)  time: 1.0046  data: 0.0005  max mem: 78493
Epoch: [21]  [120/312]  eta: 0:03:41  lr: 0.004000  min_lr: 0.004000  loss: 3.1134 (3.1290)  weight_decay: 0.0500 (0.0500)  time: 1.0054  data: 0.0005  max mem: 78493
Epoch: [21]  [130/312]  eta: 0:03:27  lr: 0.004000  min_lr: 0.004000  loss: 2.9557 (3.1169)  weight_decay: 0.0500 (0.0500)  time: 1.0061  data: 0.0005  max mem: 78493
Epoch: [21]  [140/312]  eta: 0:03:14  lr: 0.004000  min_lr: 0.004000  loss: 3.0729 (3.1086)  weight_decay: 0.0500 (0.0500)  time: 1.0053  data: 0.0004  max mem: 78493
Epoch: [21]  [150/312]  eta: 0:03:02  lr: 0.004000  min_lr: 0.004000  loss: 3.2790 (3.1244)  weight_decay: 0.0500 (0.0500)  time: 1.0050  data: 0.0004  max mem: 78493
Epoch: [21]  [160/312]  eta: 0:02:49  lr: 0.004000  min_lr: 0.004000  loss: 3.3337 (3.1303)  weight_decay: 0.0500 (0.0500)  time: 1.0070  data: 0.0005  max mem: 78493
Epoch: [21]  [170/312]  eta: 0:02:37  lr: 0.004000  min_lr: 0.004000  loss: 3.3245 (3.1459)  weight_decay: 0.0500 (0.0500)  time: 1.0068  data: 0.0005  max mem: 78493
Epoch: [21]  [180/312]  eta: 0:02:25  lr: 0.004000  min_lr: 0.004000  loss: 3.3944 (3.1481)  weight_decay: 0.0500 (0.0500)  time: 1.0050  data: 0.0004  max mem: 78493
Epoch: [21]  [190/312]  eta: 0:02:14  lr: 0.004000  min_lr: 0.004000  loss: 3.1019 (3.1395)  weight_decay: 0.0500 (0.0500)  time: 1.0064  data: 0.0004  max mem: 78493
Epoch: [21]  [200/312]  eta: 0:02:02  lr: 0.004000  min_lr: 0.004000  loss: 2.8287 (3.1252)  weight_decay: 0.0500 (0.0500)  time: 1.0058  data: 0.0005  max mem: 78493
Epoch: [21]  [210/312]  eta: 0:01:51  lr: 0.004000  min_lr: 0.004000  loss: 3.0054 (3.1262)  weight_decay: 0.0500 (0.0500)  time: 1.0058  data: 0.0005  max mem: 78493
Epoch: [21]  [220/312]  eta: 0:01:39  lr: 0.004000  min_lr: 0.004000  loss: 3.0054 (3.1173)  weight_decay: 0.0500 (0.0500)  time: 1.0065  data: 0.0004  max mem: 78493
Epoch: [21]  [230/312]  eta: 0:01:28  lr: 0.004000  min_lr: 0.004000  loss: 3.0891 (3.1227)  weight_decay: 0.0500 (0.0500)  time: 1.0043  data: 0.0004  max mem: 78493
Epoch: [21]  [240/312]  eta: 0:01:17  lr: 0.004000  min_lr: 0.004000  loss: 3.4511 (3.1336)  weight_decay: 0.0500 (0.0500)  time: 1.0043  data: 0.0005  max mem: 78493
Epoch: [21]  [250/312]  eta: 0:01:06  lr: 0.004000  min_lr: 0.004000  loss: 3.4252 (3.1353)  weight_decay: 0.0500 (0.0500)  time: 1.0054  data: 0.0005  max mem: 78493
Epoch: [21]  [260/312]  eta: 0:00:55  lr: 0.004000  min_lr: 0.004000  loss: 3.2441 (3.1317)  weight_decay: 0.0500 (0.0500)  time: 1.0048  data: 0.0010  max mem: 78493
Epoch: [21]  [270/312]  eta: 0:00:45  lr: 0.004000  min_lr: 0.004000  loss: 3.1789 (3.1325)  weight_decay: 0.0500 (0.0500)  time: 1.0041  data: 0.0010  max mem: 78493
Epoch: [21]  [280/312]  eta: 0:00:34  lr: 0.004000  min_lr: 0.004000  loss: 3.0677 (3.1293)  weight_decay: 0.0500 (0.0500)  time: 1.0060  data: 0.0011  max mem: 78493
Epoch: [21]  [290/312]  eta: 0:00:23  lr: 0.004000  min_lr: 0.004000  loss: 3.2317 (3.1317)  weight_decay: 0.0500 (0.0500)  time: 1.0043  data: 0.0009  max mem: 78493
Epoch: [21]  [300/312]  eta: 0:00:12  lr: 0.004000  min_lr: 0.004000  loss: 2.9312 (3.1233)  weight_decay: 0.0500 (0.0500)  time: 1.0019  data: 0.0001  max mem: 78493
Epoch: [21]  [310/312]  eta: 0:00:02  lr: 0.003999  min_lr: 0.003999  loss: 2.8802 (3.1207)  weight_decay: 0.0500 (0.0500)  time: 1.0021  data: 0.0001  max mem: 78493
Epoch: [21]  [311/312]  eta: 0:00:01  lr: 0.003999  min_lr: 0.003999  loss: 2.8802 (3.1201)  weight_decay: 0.0500 (0.0500)  time: 1.0021  data: 0.0001  max mem: 78493
Epoch: [21] Total time: 0:05:33 (1.0684 s / it)
Averaged stats: lr: 0.003999  min_lr: 0.003999  loss: 2.8802 (3.1290)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:17  loss: 1.1580 (1.1580)  acc1: 72.1354 (72.1354)  acc5: 90.3646 (90.3646)  time: 8.5808  data: 8.3189  max mem: 78493
Test:  [8/9]  eta: 0:00:01  loss: 1.6488 (1.4241)  acc1: 61.5885 (65.0720)  acc5: 84.5052 (86.0960)  time: 1.1595  data: 0.9244  max mem: 78493
Test: Total time: 0:00:10 (1.2075 s / it)
* Acc@1 64.894 Acc@5 86.188 loss 1.430
Accuracy of the model on the 50000 test images: 64.9%
Max accuracy: 64.89%
Epoch: [22]  [  0/312]  eta: 1:22:09  lr: 0.003999  min_lr: 0.003999  loss: 2.9075 (2.9075)  weight_decay: 0.0500 (0.0500)  time: 15.8013  data: 12.2245  max mem: 78493
Epoch: [22]  [ 10/312]  eta: 0:13:27  lr: 0.003999  min_lr: 0.003999  loss: 3.2559 (3.1854)  weight_decay: 0.0500 (0.0500)  time: 2.6750  data: 1.2627  max mem: 78493
Epoch: [22]  [ 20/312]  eta: 0:09:10  lr: 0.003999  min_lr: 0.003999  loss: 3.1605 (3.0758)  weight_decay: 0.0500 (0.0500)  time: 1.1885  data: 0.0845  max mem: 78493
Epoch: [22]  [ 30/312]  eta: 0:07:31  lr: 0.003999  min_lr: 0.003999  loss: 2.9907 (3.0911)  weight_decay: 0.0500 (0.0500)  time: 1.0111  data: 0.0014  max mem: 78493
Epoch: [22]  [ 40/312]  eta: 0:06:36  lr: 0.003999  min_lr: 0.003999  loss: 3.1237 (3.0593)  weight_decay: 0.0500 (0.0500)  time: 1.0067  data: 0.0004  max mem: 78493
Epoch: [22]  [ 50/312]  eta: 0:05:58  lr: 0.003999  min_lr: 0.003999  loss: 3.1237 (3.0597)  weight_decay: 0.0500 (0.0500)  time: 1.0071  data: 0.0004  max mem: 78493
Epoch: [22]  [ 60/312]  eta: 0:05:29  lr: 0.003999  min_lr: 0.003999  loss: 3.1491 (3.0566)  weight_decay: 0.0500 (0.0500)  time: 1.0086  data: 0.0004  max mem: 78493
Epoch: [22]  [ 70/312]  eta: 0:05:06  lr: 0.003999  min_lr: 0.003999  loss: 3.1799 (3.0825)  weight_decay: 0.0500 (0.0500)  time: 1.0102  data: 0.0004  max mem: 78493
Epoch: [22]  [ 80/312]  eta: 0:04:46  lr: 0.003999  min_lr: 0.003999  loss: 3.1529 (3.0738)  weight_decay: 0.0500 (0.0500)  time: 1.0108  data: 0.0004  max mem: 78493
Epoch: [22]  [ 90/312]  eta: 0:04:28  lr: 0.003999  min_lr: 0.003999  loss: 3.0849 (3.0533)  weight_decay: 0.0500 (0.0500)  time: 1.0094  data: 0.0004  max mem: 78493
Epoch: [22]  [100/312]  eta: 0:04:12  lr: 0.003999  min_lr: 0.003999  loss: 3.1818 (3.0699)  weight_decay: 0.0500 (0.0500)  time: 1.0087  data: 0.0004  max mem: 78493
Epoch: [22]  [110/312]  eta: 0:03:57  lr: 0.003999  min_lr: 0.003999  loss: 3.1312 (3.0581)  weight_decay: 0.0500 (0.0500)  time: 1.0085  data: 0.0005  max mem: 78493
Epoch: [22]  [120/312]  eta: 0:03:42  lr: 0.003999  min_lr: 0.003999  loss: 3.1312 (3.0684)  weight_decay: 0.0500 (0.0500)  time: 1.0081  data: 0.0005  max mem: 78493
Epoch: [22]  [130/312]  eta: 0:03:29  lr: 0.003999  min_lr: 0.003999  loss: 3.1717 (3.0685)  weight_decay: 0.0500 (0.0500)  time: 1.0088  data: 0.0004  max mem: 78493
Epoch: [22]  [140/312]  eta: 0:03:15  lr: 0.003999  min_lr: 0.003999  loss: 2.8470 (3.0446)  weight_decay: 0.0500 (0.0500)  time: 1.0091  data: 0.0004  max mem: 78493
Epoch: [22]  [150/312]  eta: 0:03:03  lr: 0.003999  min_lr: 0.003999  loss: 2.7710 (3.0507)  weight_decay: 0.0500 (0.0500)  time: 1.0091  data: 0.0004  max mem: 78493
Epoch: [22]  [160/312]  eta: 0:02:50  lr: 0.003999  min_lr: 0.003999  loss: 3.3118 (3.0506)  weight_decay: 0.0500 (0.0500)  time: 1.0069  data: 0.0004  max mem: 78493
Epoch: [22]  [170/312]  eta: 0:02:38  lr: 0.003999  min_lr: 0.003999  loss: 3.2878 (3.0573)  weight_decay: 0.0500 (0.0500)  time: 1.0071  data: 0.0004  max mem: 78493
Epoch: [22]  [180/312]  eta: 0:02:26  lr: 0.003999  min_lr: 0.003999  loss: 3.2061 (3.0492)  weight_decay: 0.0500 (0.0500)  time: 1.0088  data: 0.0004  max mem: 78493
Epoch: [22]  [190/312]  eta: 0:02:14  lr: 0.003999  min_lr: 0.003999  loss: 3.1870 (3.0479)  weight_decay: 0.0500 (0.0500)  time: 1.0056  data: 0.0004  max mem: 78493
Epoch: [22]  [200/312]  eta: 0:02:03  lr: 0.003999  min_lr: 0.003999  loss: 3.3366 (3.0611)  weight_decay: 0.0500 (0.0500)  time: 1.0043  data: 0.0004  max mem: 78493
Epoch: [22]  [210/312]  eta: 0:01:51  lr: 0.003999  min_lr: 0.003999  loss: 3.2692 (3.0580)  weight_decay: 0.0500 (0.0500)  time: 1.0060  data: 0.0004  max mem: 78493
Epoch: [22]  [220/312]  eta: 0:01:40  lr: 0.003999  min_lr: 0.003999  loss: 3.0384 (3.0503)  weight_decay: 0.0500 (0.0500)  time: 1.0063  data: 0.0004  max mem: 78493
Epoch: [22]  [230/312]  eta: 0:01:29  lr: 0.003999  min_lr: 0.003999  loss: 3.0008 (3.0558)  weight_decay: 0.0500 (0.0500)  time: 1.0061  data: 0.0004  max mem: 78493
Epoch: [22]  [240/312]  eta: 0:01:18  lr: 0.003999  min_lr: 0.003999  loss: 3.2910 (3.0594)  weight_decay: 0.0500 (0.0500)  time: 1.0073  data: 0.0004  max mem: 78493
Epoch: [22]  [250/312]  eta: 0:01:07  lr: 0.003999  min_lr: 0.003999  loss: 2.8810 (3.0532)  weight_decay: 0.0500 (0.0500)  time: 1.0066  data: 0.0004  max mem: 78493
Epoch: [22]  [260/312]  eta: 0:00:56  lr: 0.003999  min_lr: 0.003999  loss: 2.9230 (3.0516)  weight_decay: 0.0500 (0.0500)  time: 1.0047  data: 0.0004  max mem: 78493
Epoch: [22]  [270/312]  eta: 0:00:45  lr: 0.003999  min_lr: 0.003999  loss: 3.1433 (3.0563)  weight_decay: 0.0500 (0.0500)  time: 1.0055  data: 0.0004  max mem: 78493
Epoch: [22]  [280/312]  eta: 0:00:34  lr: 0.003999  min_lr: 0.003999  loss: 3.1840 (3.0555)  weight_decay: 0.0500 (0.0500)  time: 1.0080  data: 0.0011  max mem: 78493
Epoch: [22]  [290/312]  eta: 0:00:23  lr: 0.003999  min_lr: 0.003999  loss: 3.4155 (3.0711)  weight_decay: 0.0500 (0.0500)  time: 1.0058  data: 0.0009  max mem: 78493
Epoch: [22]  [300/312]  eta: 0:00:12  lr: 0.003999  min_lr: 0.003999  loss: 3.4155 (3.0795)  weight_decay: 0.0500 (0.0500)  time: 1.0020  data: 0.0001  max mem: 78493
Epoch: [22]  [310/312]  eta: 0:00:02  lr: 0.003999  min_lr: 0.003999  loss: 3.3220 (3.0826)  weight_decay: 0.0500 (0.0500)  time: 1.0022  data: 0.0001  max mem: 78493
Epoch: [22]  [311/312]  eta: 0:00:01  lr: 0.003999  min_lr: 0.003999  loss: 3.3220 (3.0840)  weight_decay: 0.0500 (0.0500)  time: 1.0022  data: 0.0001  max mem: 78493
Epoch: [22] Total time: 0:05:34 (1.0721 s / it)
Averaged stats: lr: 0.003999  min_lr: 0.003999  loss: 3.3220 (3.0997)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:17  loss: 1.1473 (1.1473)  acc1: 73.9583 (73.9583)  acc5: 89.8438 (89.8438)  time: 8.5950  data: 8.3237  max mem: 78493
Test:  [8/9]  eta: 0:00:01  loss: 1.6221 (1.5156)  acc1: 61.8490 (64.0480)  acc5: 84.8958 (85.2160)  time: 1.1531  data: 0.9249  max mem: 78493
Test: Total time: 0:00:10 (1.1701 s / it)
* Acc@1 63.714 Acc@5 85.338 loss 1.520
Accuracy of the model on the 50000 test images: 63.7%
Max accuracy: 64.89%
Epoch: [23]  [  0/312]  eta: 1:28:17  lr: 0.003999  min_lr: 0.003999  loss: 3.2275 (3.2275)  weight_decay: 0.0500 (0.0500)  time: 16.9795  data: 14.3625  max mem: 78493
Epoch: [23]  [ 10/312]  eta: 0:14:01  lr: 0.003999  min_lr: 0.003999  loss: 2.7818 (2.7553)  weight_decay: 0.0500 (0.0500)  time: 2.7868  data: 1.3062  max mem: 78493
Epoch: [23]  [ 20/312]  eta: 0:09:26  lr: 0.003999  min_lr: 0.003999  loss: 3.1269 (2.9759)  weight_decay: 0.0500 (0.0500)  time: 1.1879  data: 0.0005  max mem: 78493
Epoch: [23]  [ 30/312]  eta: 0:07:42  lr: 0.003999  min_lr: 0.003999  loss: 3.1843 (2.9747)  weight_decay: 0.0500 (0.0500)  time: 1.0086  data: 0.0005  max mem: 78493
Epoch: [23]  [ 40/312]  eta: 0:06:44  lr: 0.003999  min_lr: 0.003999  loss: 3.0154 (3.0083)  weight_decay: 0.0500 (0.0500)  time: 1.0081  data: 0.0005  max mem: 78493
Epoch: [23]  [ 50/312]  eta: 0:06:04  lr: 0.003999  min_lr: 0.003999  loss: 3.0154 (3.0145)  weight_decay: 0.0500 (0.0500)  time: 1.0091  data: 0.0004  max mem: 78493
Epoch: [23]  [ 60/312]  eta: 0:05:35  lr: 0.003999  min_lr: 0.003999  loss: 3.0882 (3.0378)  weight_decay: 0.0500 (0.0500)  time: 1.0099  data: 0.0004  max mem: 78493
Epoch: [23]  [ 70/312]  eta: 0:05:10  lr: 0.003999  min_lr: 0.003999  loss: 3.1962 (3.0521)  weight_decay: 0.0500 (0.0500)  time: 1.0089  data: 0.0004  max mem: 78493
Epoch: [23]  [ 80/312]  eta: 0:04:49  lr: 0.003999  min_lr: 0.003999  loss: 3.1962 (3.0632)  weight_decay: 0.0500 (0.0500)  time: 1.0074  data: 0.0004  max mem: 78493
Epoch: [23]  [ 90/312]  eta: 0:04:31  lr: 0.003999  min_lr: 0.003999  loss: 3.3409 (3.0955)  weight_decay: 0.0500 (0.0500)  time: 1.0069  data: 0.0004  max mem: 78493
Epoch: [23]  [100/312]  eta: 0:04:14  lr: 0.003999  min_lr: 0.003999  loss: 3.3523 (3.0974)  weight_decay: 0.0500 (0.0500)  time: 1.0086  data: 0.0005  max mem: 78493
Epoch: [23]  [110/312]  eta: 0:03:59  lr: 0.003999  min_lr: 0.003999  loss: 2.8408 (3.0666)  weight_decay: 0.0500 (0.0500)  time: 1.0065  data: 0.0005  max mem: 78493
Epoch: [23]  [120/312]  eta: 0:03:44  lr: 0.003999  min_lr: 0.003999  loss: 3.0622 (3.0675)  weight_decay: 0.0500 (0.0500)  time: 1.0051  data: 0.0004  max mem: 78493
Epoch: [23]  [130/312]  eta: 0:03:30  lr: 0.003999  min_lr: 0.003999  loss: 3.0887 (3.0685)  weight_decay: 0.0500 (0.0500)  time: 1.0050  data: 0.0005  max mem: 78493
Epoch: [23]  [140/312]  eta: 0:03:17  lr: 0.003999  min_lr: 0.003999  loss: 2.9686 (3.0720)  weight_decay: 0.0500 (0.0500)  time: 1.0052  data: 0.0005  max mem: 78493
Epoch: [23]  [150/312]  eta: 0:03:04  lr: 0.003998  min_lr: 0.003998  loss: 2.9686 (3.0657)  weight_decay: 0.0500 (0.0500)  time: 1.0061  data: 0.0005  max mem: 78493
Epoch: [23]  [160/312]  eta: 0:02:51  lr: 0.003998  min_lr: 0.003998  loss: 2.9755 (3.0605)  weight_decay: 0.0500 (0.0500)  time: 1.0051  data: 0.0005  max mem: 78493
Epoch: [23]  [170/312]  eta: 0:02:39  lr: 0.003998  min_lr: 0.003998  loss: 3.1889 (3.0764)  weight_decay: 0.0500 (0.0500)  time: 1.0051  data: 0.0004  max mem: 78493
Epoch: [23]  [180/312]  eta: 0:02:27  lr: 0.003998  min_lr: 0.003998  loss: 3.1943 (3.0753)  weight_decay: 0.0500 (0.0500)  time: 1.0050  data: 0.0004  max mem: 78493
Epoch: [23]  [190/312]  eta: 0:02:15  lr: 0.003998  min_lr: 0.003998  loss: 2.9620 (3.0708)  weight_decay: 0.0500 (0.0500)  time: 1.0045  data: 0.0004  max mem: 78493
Epoch: [23]  [200/312]  eta: 0:02:03  lr: 0.003998  min_lr: 0.003998  loss: 3.1894 (3.0740)  weight_decay: 0.0500 (0.0500)  time: 1.0057  data: 0.0005  max mem: 78493
Epoch: [23]  [210/312]  eta: 0:01:52  lr: 0.003998  min_lr: 0.003998  loss: 3.1699 (3.0735)  weight_decay: 0.0500 (0.0500)  time: 1.0055  data: 0.0004  max mem: 78493
Epoch: [23]  [220/312]  eta: 0:01:40  lr: 0.003998  min_lr: 0.003998  loss: 3.0617 (3.0680)  weight_decay: 0.0500 (0.0500)  time: 1.0047  data: 0.0004  max mem: 78493
Epoch: [23]  [230/312]  eta: 0:01:29  lr: 0.003998  min_lr: 0.003998  loss: 2.9662 (3.0591)  weight_decay: 0.0500 (0.0500)  time: 1.0062  data: 0.0004  max mem: 78493
Epoch: [23]  [240/312]  eta: 0:01:18  lr: 0.003998  min_lr: 0.003998  loss: 3.0660 (3.0581)  weight_decay: 0.0500 (0.0500)  time: 1.0059  data: 0.0004  max mem: 78493
Epoch: [23]  [250/312]  eta: 0:01:07  lr: 0.003998  min_lr: 0.003998  loss: 3.1967 (3.0615)  weight_decay: 0.0500 (0.0500)  time: 1.0054  data: 0.0004  max mem: 78493
Epoch: [23]  [260/312]  eta: 0:00:56  lr: 0.003998  min_lr: 0.003998  loss: 3.0279 (3.0545)  weight_decay: 0.0500 (0.0500)  time: 1.0059  data: 0.0004  max mem: 78493
Epoch: [23]  [270/312]  eta: 0:00:45  lr: 0.003998  min_lr: 0.003998  loss: 2.9570 (3.0503)  weight_decay: 0.0500 (0.0500)  time: 1.0052  data: 0.0004  max mem: 78493
Epoch: [23]  [280/312]  eta: 0:00:34  lr: 0.003998  min_lr: 0.003998  loss: 2.9617 (3.0491)  weight_decay: 0.0500 (0.0500)  time: 1.0050  data: 0.0010  max mem: 78493
Epoch: [23]  [290/312]  eta: 0:00:23  lr: 0.003998  min_lr: 0.003998  loss: 3.3340 (3.0570)  weight_decay: 0.0500 (0.0500)  time: 1.0037  data: 0.0009  max mem: 78493
Epoch: [23]  [300/312]  eta: 0:00:12  lr: 0.003998  min_lr: 0.003998  loss: 3.0991 (3.0563)  weight_decay: 0.0500 (0.0500)  time: 1.0022  data: 0.0001  max mem: 78493
Epoch: [23]  [310/312]  eta: 0:00:02  lr: 0.003998  min_lr: 0.003998  loss: 3.0127 (3.0544)  weight_decay: 0.0500 (0.0500)  time: 1.0022  data: 0.0001  max mem: 78493
Epoch: [23]  [311/312]  eta: 0:00:01  lr: 0.003998  min_lr: 0.003998  loss: 2.9767 (3.0517)  weight_decay: 0.0500 (0.0500)  time: 1.0022  data: 0.0001  max mem: 78493
Epoch: [23] Total time: 0:05:35 (1.0744 s / it)
Averaged stats: lr: 0.003998  min_lr: 0.003998  loss: 2.9767 (3.0664)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:12  loss: 1.1086 (1.1086)  acc1: 73.1771 (73.1771)  acc5: 91.0156 (91.0156)  time: 8.0090  data: 7.7363  max mem: 78493
Test:  [8/9]  eta: 0:00:01  loss: 1.5331 (1.4202)  acc1: 66.1458 (66.1440)  acc5: 86.5885 (86.4000)  time: 1.0883  data: 0.8597  max mem: 78493
Test: Total time: 0:00:09 (1.1055 s / it)
* Acc@1 65.750 Acc@5 86.530 loss 1.410
Accuracy of the model on the 50000 test images: 65.8%
Max accuracy: 65.75%
Epoch: [24]  [  0/312]  eta: 1:26:06  lr: 0.003998  min_lr: 0.003998  loss: 3.3046 (3.3046)  weight_decay: 0.0500 (0.0500)  time: 16.5604  data: 15.5601  max mem: 78493
Epoch: [24]  [ 10/312]  eta: 0:12:25  lr: 0.003998  min_lr: 0.003998  loss: 3.2989 (3.1366)  weight_decay: 0.0500 (0.0500)  time: 2.4702  data: 1.4171  max mem: 78493
Epoch: [24]  [ 20/312]  eta: 0:08:40  lr: 0.003998  min_lr: 0.003998  loss: 2.9977 (2.9827)  weight_decay: 0.0500 (0.0500)  time: 1.0450  data: 0.0033  max mem: 78493
Epoch: [24]  [ 30/312]  eta: 0:07:12  lr: 0.003998  min_lr: 0.003998  loss: 2.8797 (2.9991)  weight_decay: 0.0500 (0.0500)  time: 1.0176  data: 0.0021  max mem: 78493
Epoch: [24]  [ 40/312]  eta: 0:06:21  lr: 0.003998  min_lr: 0.003998  loss: 3.0377 (3.0008)  weight_decay: 0.0500 (0.0500)  time: 1.0057  data: 0.0005  max mem: 78493
Epoch: [24]  [ 50/312]  eta: 0:05:47  lr: 0.003998  min_lr: 0.003998  loss: 2.9013 (2.9831)  weight_decay: 0.0500 (0.0500)  time: 1.0072  data: 0.0005  max mem: 78493
Epoch: [24]  [ 60/312]  eta: 0:05:21  lr: 0.003998  min_lr: 0.003998  loss: 3.0044 (3.0284)  weight_decay: 0.0500 (0.0500)  time: 1.0089  data: 0.0004  max mem: 78493
Epoch: [24]  [ 70/312]  eta: 0:04:59  lr: 0.003998  min_lr: 0.003998  loss: 3.1342 (3.0018)  weight_decay: 0.0500 (0.0500)  time: 1.0086  data: 0.0004  max mem: 78493
Epoch: [24]  [ 80/312]  eta: 0:04:40  lr: 0.003998  min_lr: 0.003998  loss: 2.8052 (2.9697)  weight_decay: 0.0500 (0.0500)  time: 1.0089  data: 0.0005  max mem: 78493
Epoch: [24]  [ 90/312]  eta: 0:04:23  lr: 0.003998  min_lr: 0.003998  loss: 2.9726 (2.9878)  weight_decay: 0.0500 (0.0500)  time: 1.0075  data: 0.0005  max mem: 78493
Epoch: [24]  [100/312]  eta: 0:04:07  lr: 0.003998  min_lr: 0.003998  loss: 3.1506 (2.9993)  weight_decay: 0.0500 (0.0500)  time: 1.0085  data: 0.0004  max mem: 78493
Epoch: [24]  [110/312]  eta: 0:03:53  lr: 0.003998  min_lr: 0.003998  loss: 3.0840 (2.9947)  weight_decay: 0.0500 (0.0500)  time: 1.0105  data: 0.0005  max mem: 78493
Epoch: [24]  [120/312]  eta: 0:03:39  lr: 0.003998  min_lr: 0.003998  loss: 3.1065 (2.9972)  weight_decay: 0.0500 (0.0500)  time: 1.0079  data: 0.0004  max mem: 78493
Epoch: [24]  [130/312]  eta: 0:03:26  lr: 0.003998  min_lr: 0.003998  loss: 3.1807 (2.9937)  weight_decay: 0.0500 (0.0500)  time: 1.0073  data: 0.0004  max mem: 78493
Epoch: [24]  [140/312]  eta: 0:03:13  lr: 0.003998  min_lr: 0.003998  loss: 3.1672 (3.0019)  weight_decay: 0.0500 (0.0500)  time: 1.0100  data: 0.0004  max mem: 78493
Epoch: [24]  [150/312]  eta: 0:03:00  lr: 0.003997  min_lr: 0.003997  loss: 3.1368 (2.9998)  weight_decay: 0.0500 (0.0500)  time: 1.0094  data: 0.0005  max mem: 78493
Epoch: [24]  [160/312]  eta: 0:02:48  lr: 0.003997  min_lr: 0.003997  loss: 2.9688 (3.0001)  weight_decay: 0.0500 (0.0500)  time: 1.0077  data: 0.0004  max mem: 78493
Epoch: [24]  [170/312]  eta: 0:02:36  lr: 0.003997  min_lr: 0.003997  loss: 3.0717 (3.0024)  weight_decay: 0.0500 (0.0500)  time: 1.0076  data: 0.0004  max mem: 78493
Epoch: [24]  [180/312]  eta: 0:02:24  lr: 0.003997  min_lr: 0.003997  loss: 3.2608 (3.0173)  weight_decay: 0.0500 (0.0500)  time: 1.0085  data: 0.0005  max mem: 78493
Epoch: [24]  [190/312]  eta: 0:02:13  lr: 0.003997  min_lr: 0.003997  loss: 3.2534 (3.0076)  weight_decay: 0.0500 (0.0500)  time: 1.0076  data: 0.0005  max mem: 78493
Epoch: [24]  [200/312]  eta: 0:02:01  lr: 0.003997  min_lr: 0.003997  loss: 3.0244 (3.0106)  weight_decay: 0.0500 (0.0500)  time: 1.0056  data: 0.0005  max mem: 78493
Epoch: [24]  [210/312]  eta: 0:01:50  lr: 0.003997  min_lr: 0.003997  loss: 3.0376 (3.0152)  weight_decay: 0.0500 (0.0500)  time: 1.0058  data: 0.0005  max mem: 78493
Epoch: [24]  [220/312]  eta: 0:01:39  lr: 0.003997  min_lr: 0.003997  loss: 3.2736 (3.0254)  weight_decay: 0.0500 (0.0500)  time: 1.0054  data: 0.0004  max mem: 78493
Epoch: [24]  [230/312]  eta: 0:01:28  lr: 0.003997  min_lr: 0.003997  loss: 2.9921 (3.0104)  weight_decay: 0.0500 (0.0500)  time: 1.0061  data: 0.0011  max mem: 78493
Epoch: [24]  [240/312]  eta: 0:01:17  lr: 0.003997  min_lr: 0.003997  loss: 2.6241 (3.0037)  weight_decay: 0.0500 (0.0500)  time: 1.0063  data: 0.0011  max mem: 78493
Epoch: [24]  [250/312]  eta: 0:01:06  lr: 0.003997  min_lr: 0.003997  loss: 2.9558 (3.0045)  weight_decay: 0.0500 (0.0500)  time: 1.0059  data: 0.0004  max mem: 78493
Epoch: [24]  [260/312]  eta: 0:00:55  lr: 0.003997  min_lr: 0.003997  loss: 2.9379 (3.0028)  weight_decay: 0.0500 (0.0500)  time: 1.0065  data: 0.0005  max mem: 78493
Epoch: [24]  [270/312]  eta: 0:00:44  lr: 0.003997  min_lr: 0.003997  loss: 2.8521 (3.0023)  weight_decay: 0.0500 (0.0500)  time: 1.0059  data: 0.0005  max mem: 78493
Epoch: [24]  [280/312]  eta: 0:00:34  lr: 0.003997  min_lr: 0.003997  loss: 2.9112 (3.0009)  weight_decay: 0.0500 (0.0500)  time: 1.0063  data: 0.0010  max mem: 78493
Epoch: [24]  [290/312]  eta: 0:00:23  lr: 0.003997  min_lr: 0.003997  loss: 2.9112 (2.9996)  weight_decay: 0.0500 (0.0500)  time: 1.0049  data: 0.0009  max mem: 78493
Epoch: [24]  [300/312]  eta: 0:00:12  lr: 0.003997  min_lr: 0.003997  loss: 2.9367 (3.0021)  weight_decay: 0.0500 (0.0500)  time: 1.0021  data: 0.0001  max mem: 78493
Epoch: [24]  [310/312]  eta: 0:00:02  lr: 0.003997  min_lr: 0.003997  loss: 2.9367 (3.0013)  weight_decay: 0.0500 (0.0500)  time: 1.0020  data: 0.0001  max mem: 78493
Epoch: [24]  [311/312]  eta: 0:00:01  lr: 0.003997  min_lr: 0.003997  loss: 2.9367 (2.9985)  weight_decay: 0.0500 (0.0500)  time: 1.0020  data: 0.0001  max mem: 78493
Epoch: [24] Total time: 0:05:32 (1.0648 s / it)
Averaged stats: lr: 0.003997  min_lr: 0.003997  loss: 2.9367 (3.0375)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:11  loss: 1.1588 (1.1588)  acc1: 71.6146 (71.6146)  acc5: 91.4062 (91.4062)  time: 7.9013  data: 7.6303  max mem: 78493
Test:  [8/9]  eta: 0:00:01  loss: 1.6096 (1.4434)  acc1: 63.9323 (65.2320)  acc5: 84.7656 (86.6560)  time: 1.0845  data: 0.8479  max mem: 78493
Test: Total time: 0:00:09 (1.1001 s / it)
* Acc@1 65.882 Acc@5 86.692 loss 1.423
Accuracy of the model on the 50000 test images: 65.9%
Max accuracy: 65.88%
Epoch: [25]  [  0/312]  eta: 1:21:04  lr: 0.003997  min_lr: 0.003997  loss: 3.7142 (3.7142)  weight_decay: 0.0500 (0.0500)  time: 15.5923  data: 12.5573  max mem: 78493
Epoch: [25]  [ 10/312]  eta: 0:12:39  lr: 0.003997  min_lr: 0.003997  loss: 3.0812 (3.1034)  weight_decay: 0.0500 (0.0500)  time: 2.5162  data: 1.2930  max mem: 78493
Epoch: [25]  [ 20/312]  eta: 0:08:49  lr: 0.003997  min_lr: 0.003997  loss: 3.0812 (3.1323)  weight_decay: 0.0500 (0.0500)  time: 1.1237  data: 0.0878  max mem: 78493
Epoch: [25]  [ 30/312]  eta: 0:07:18  lr: 0.003997  min_lr: 0.003997  loss: 3.1722 (3.0524)  weight_decay: 0.0500 (0.0500)  time: 1.0240  data: 0.0047  max mem: 78493
Epoch: [25]  [ 40/312]  eta: 0:06:26  lr: 0.003997  min_lr: 0.003997  loss: 2.9070 (3.0300)  weight_decay: 0.0500 (0.0500)  time: 1.0086  data: 0.0004  max mem: 78493
Epoch: [25]  [ 50/312]  eta: 0:05:50  lr: 0.003997  min_lr: 0.003997  loss: 3.2768 (3.0587)  weight_decay: 0.0500 (0.0500)  time: 1.0071  data: 0.0004  max mem: 78493
Epoch: [25]  [ 60/312]  eta: 0:05:23  lr: 0.003997  min_lr: 0.003997  loss: 3.1423 (3.0256)  weight_decay: 0.0500 (0.0500)  time: 1.0080  data: 0.0004  max mem: 78493
Epoch: [25]  [ 70/312]  eta: 0:05:01  lr: 0.003997  min_lr: 0.003997  loss: 3.1161 (3.0496)  weight_decay: 0.0500 (0.0500)  time: 1.0098  data: 0.0004  max mem: 78493
Epoch: [25]  [ 80/312]  eta: 0:04:42  lr: 0.003997  min_lr: 0.003997  loss: 3.1297 (3.0462)  weight_decay: 0.0500 (0.0500)  time: 1.0096  data: 0.0004  max mem: 78493
Epoch: [25]  [ 90/312]  eta: 0:04:25  lr: 0.003996  min_lr: 0.003996  loss: 3.0917 (3.0424)  weight_decay: 0.0500 (0.0500)  time: 1.0087  data: 0.0004  max mem: 78493
Epoch: [25]  [100/312]  eta: 0:04:09  lr: 0.003996  min_lr: 0.003996  loss: 3.1437 (3.0449)  weight_decay: 0.0500 (0.0500)  time: 1.0083  data: 0.0004  max mem: 78493
Epoch: [25]  [110/312]  eta: 0:03:54  lr: 0.003996  min_lr: 0.003996  loss: 3.1323 (3.0538)  weight_decay: 0.0500 (0.0500)  time: 1.0071  data: 0.0005  max mem: 78493
Epoch: [25]  [120/312]  eta: 0:03:40  lr: 0.003996  min_lr: 0.003996  loss: 2.9269 (3.0334)  weight_decay: 0.0500 (0.0500)  time: 1.0047  data: 0.0005  max mem: 78493
Epoch: [25]  [130/312]  eta: 0:03:26  lr: 0.003996  min_lr: 0.003996  loss: 2.8674 (3.0335)  weight_decay: 0.0500 (0.0500)  time: 1.0050  data: 0.0005  max mem: 78493
Epoch: [25]  [140/312]  eta: 0:03:13  lr: 0.003996  min_lr: 0.003996  loss: 3.0626 (3.0351)  weight_decay: 0.0500 (0.0500)  time: 1.0054  data: 0.0005  max mem: 78493
Epoch: [25]  [150/312]  eta: 0:03:01  lr: 0.003996  min_lr: 0.003996  loss: 3.1516 (3.0397)  weight_decay: 0.0500 (0.0500)  time: 1.0066  data: 0.0004  max mem: 78493
Epoch: [25]  [160/312]  eta: 0:02:49  lr: 0.003996  min_lr: 0.003996  loss: 3.1274 (3.0312)  weight_decay: 0.0500 (0.0500)  time: 1.0078  data: 0.0004  max mem: 78493
Epoch: [25]  [170/312]  eta: 0:02:37  lr: 0.003996  min_lr: 0.003996  loss: 2.8287 (3.0135)  weight_decay: 0.0500 (0.0500)  time: 1.0078  data: 0.0004  max mem: 78493
Epoch: [25]  [180/312]  eta: 0:02:25  lr: 0.003996  min_lr: 0.003996  loss: 2.8287 (3.0118)  weight_decay: 0.0500 (0.0500)  time: 1.0073  data: 0.0004  max mem: 78493
Epoch: [25]  [190/312]  eta: 0:02:13  lr: 0.003996  min_lr: 0.003996  loss: 2.9407 (3.0104)  weight_decay: 0.0500 (0.0500)  time: 1.0067  data: 0.0004  max mem: 78493
Epoch: [25]  [200/312]  eta: 0:02:02  lr: 0.003996  min_lr: 0.003996  loss: 2.9407 (3.0073)  weight_decay: 0.0500 (0.0500)  time: 1.0070  data: 0.0004  max mem: 78493
Epoch: [25]  [210/312]  eta: 0:01:50  lr: 0.003996  min_lr: 0.003996  loss: 2.9489 (3.0039)  weight_decay: 0.0500 (0.0500)  time: 1.0064  data: 0.0005  max mem: 78493
Epoch: [25]  [220/312]  eta: 0:01:39  lr: 0.003996  min_lr: 0.003996  loss: 3.0193 (3.0062)  weight_decay: 0.0500 (0.0500)  time: 1.0071  data: 0.0005  max mem: 78493
Epoch: [25]  [230/312]  eta: 0:01:28  lr: 0.003996  min_lr: 0.003996  loss: 2.8512 (2.9990)  weight_decay: 0.0500 (0.0500)  time: 1.0071  data: 0.0005  max mem: 78493
Epoch: [25]  [240/312]  eta: 0:01:17  lr: 0.003996  min_lr: 0.003996  loss: 2.9771 (2.9999)  weight_decay: 0.0500 (0.0500)  time: 1.0060  data: 0.0014  max mem: 78493
Epoch: [25]  [250/312]  eta: 0:01:06  lr: 0.003996  min_lr: 0.003996  loss: 2.9771 (2.9890)  weight_decay: 0.0500 (0.0500)  time: 1.0050  data: 0.0014  max mem: 78493
Epoch: [25]  [260/312]  eta: 0:00:55  lr: 0.003996  min_lr: 0.003996  loss: 2.8515 (2.9856)  weight_decay: 0.0500 (0.0500)  time: 1.0044  data: 0.0005  max mem: 78493
Epoch: [25]  [270/312]  eta: 0:00:44  lr: 0.003996  min_lr: 0.003996  loss: 3.1583 (2.9929)  weight_decay: 0.0500 (0.0500)  time: 1.0042  data: 0.0004  max mem: 78493
Epoch: [25]  [280/312]  eta: 0:00:34  lr: 0.003996  min_lr: 0.003996  loss: 3.2715 (2.9947)  weight_decay: 0.0500 (0.0500)  time: 1.0049  data: 0.0010  max mem: 78493
Epoch: [25]  [290/312]  eta: 0:00:23  lr: 0.003996  min_lr: 0.003996  loss: 3.1297 (2.9997)  weight_decay: 0.0500 (0.0500)  time: 1.0039  data: 0.0009  max mem: 78493
Epoch: [25]  [300/312]  eta: 0:00:12  lr: 0.003996  min_lr: 0.003996  loss: 3.1227 (2.9997)  weight_decay: 0.0500 (0.0500)  time: 1.0018  data: 0.0001  max mem: 78493
Epoch: [25]  [310/312]  eta: 0:00:02  lr: 0.003995  min_lr: 0.003995  loss: 2.9918 (2.9958)  weight_decay: 0.0500 (0.0500)  time: 1.0017  data: 0.0001  max mem: 78493
Epoch: [25]  [311/312]  eta: 0:00:01  lr: 0.003995  min_lr: 0.003995  loss: 2.9402 (2.9957)  weight_decay: 0.0500 (0.0500)  time: 1.0017  data: 0.0001  max mem: 78493
Epoch: [25] Total time: 0:05:32 (1.0663 s / it)
Averaged stats: lr: 0.003995  min_lr: 0.003995  loss: 2.9402 (3.0154)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:14  loss: 1.0450 (1.0450)  acc1: 74.2188 (74.2188)  acc5: 91.6667 (91.6667)  time: 8.2358  data: 7.9730  max mem: 78493
Test:  [8/9]  eta: 0:00:01  loss: 1.5941 (1.3857)  acc1: 63.5417 (65.7920)  acc5: 85.4167 (87.0400)  time: 1.1174  data: 0.8860  max mem: 78493
Test: Total time: 0:00:10 (1.1555 s / it)
* Acc@1 66.198 Acc@5 86.940 loss 1.381
Accuracy of the model on the 50000 test images: 66.2%
Max accuracy: 66.20%
Epoch: [26]  [  0/312]  eta: 1:21:58  lr: 0.003995  min_lr: 0.003995  loss: 3.2548 (3.2548)  weight_decay: 0.0500 (0.0500)  time: 15.7635  data: 13.5659  max mem: 78493
Epoch: [26]  [ 10/312]  eta: 0:13:14  lr: 0.003995  min_lr: 0.003995  loss: 3.0606 (2.9659)  weight_decay: 0.0500 (0.0500)  time: 2.6300  data: 1.3475  max mem: 78493
Epoch: [26]  [ 20/312]  eta: 0:09:04  lr: 0.003995  min_lr: 0.003995  loss: 2.8320 (2.9536)  weight_decay: 0.0500 (0.0500)  time: 1.1686  data: 0.0631  max mem: 78493
Epoch: [26]  [ 30/312]  eta: 0:07:27  lr: 0.003995  min_lr: 0.003995  loss: 2.8005 (2.9526)  weight_decay: 0.0500 (0.0500)  time: 1.0129  data: 0.0004  max mem: 78493
Epoch: [26]  [ 40/312]  eta: 0:06:33  lr: 0.003995  min_lr: 0.003995  loss: 2.9257 (2.9420)  weight_decay: 0.0500 (0.0500)  time: 1.0083  data: 0.0011  max mem: 78493
Epoch: [26]  [ 50/312]  eta: 0:05:56  lr: 0.003995  min_lr: 0.003995  loss: 2.9520 (2.9257)  weight_decay: 0.0500 (0.0500)  time: 1.0093  data: 0.0011  max mem: 78493
Epoch: [26]  [ 60/312]  eta: 0:05:28  lr: 0.003995  min_lr: 0.003995  loss: 3.0189 (2.9374)  weight_decay: 0.0500 (0.0500)  time: 1.0082  data: 0.0004  max mem: 78493
Epoch: [26]  [ 70/312]  eta: 0:05:05  lr: 0.003995  min_lr: 0.003995  loss: 3.0189 (2.9359)  weight_decay: 0.0500 (0.0500)  time: 1.0071  data: 0.0005  max mem: 78493
Epoch: [26]  [ 80/312]  eta: 0:04:45  lr: 0.003995  min_lr: 0.003995  loss: 3.1130 (2.9451)  weight_decay: 0.0500 (0.0500)  time: 1.0054  data: 0.0005  max mem: 78493
Epoch: [26]  [ 90/312]  eta: 0:04:27  lr: 0.003995  min_lr: 0.003995  loss: 3.0882 (2.9461)  weight_decay: 0.0500 (0.0500)  time: 1.0069  data: 0.0004  max mem: 78493
Epoch: [26]  [100/312]  eta: 0:04:11  lr: 0.003995  min_lr: 0.003995  loss: 2.9873 (2.9444)  weight_decay: 0.0500 (0.0500)  time: 1.0081  data: 0.0004  max mem: 78493
Epoch: [26]  [110/312]  eta: 0:03:56  lr: 0.003995  min_lr: 0.003995  loss: 3.0742 (2.9452)  weight_decay: 0.0500 (0.0500)  time: 1.0083  data: 0.0005  max mem: 78493
Epoch: [26]  [120/312]  eta: 0:03:41  lr: 0.003995  min_lr: 0.003995  loss: 2.5522 (2.9270)  weight_decay: 0.0500 (0.0500)  time: 1.0081  data: 0.0005  max mem: 78493
Epoch: [26]  [130/312]  eta: 0:03:28  lr: 0.003995  min_lr: 0.003995  loss: 2.6784 (2.9260)  weight_decay: 0.0500 (0.0500)  time: 1.0080  data: 0.0005  max mem: 78493
Epoch: [26]  [140/312]  eta: 0:03:15  lr: 0.003995  min_lr: 0.003995  loss: 3.0836 (2.9318)  weight_decay: 0.0500 (0.0500)  time: 1.0077  data: 0.0005  max mem: 78493
Epoch: [26]  [150/312]  eta: 0:03:02  lr: 0.003995  min_lr: 0.003995  loss: 3.1910 (2.9450)  weight_decay: 0.0500 (0.0500)  time: 1.0076  data: 0.0005  max mem: 78493
Epoch: [26]  [160/312]  eta: 0:02:50  lr: 0.003995  min_lr: 0.003995  loss: 3.2585 (2.9607)  weight_decay: 0.0500 (0.0500)  time: 1.0071  data: 0.0005  max mem: 78493
Epoch: [26]  [170/312]  eta: 0:02:38  lr: 0.003995  min_lr: 0.003995  loss: 3.1494 (2.9622)  weight_decay: 0.0500 (0.0500)  time: 1.0077  data: 0.0004  max mem: 78493
Epoch: [26]  [180/312]  eta: 0:02:26  lr: 0.003995  min_lr: 0.003995  loss: 3.0197 (2.9685)  weight_decay: 0.0500 (0.0500)  time: 1.0080  data: 0.0004  max mem: 78493
Epoch: [26]  [190/312]  eta: 0:02:14  lr: 0.003995  min_lr: 0.003995  loss: 2.8099 (2.9587)  weight_decay: 0.0500 (0.0500)  time: 1.0076  data: 0.0005  max mem: 78493
Epoch: [26]  [200/312]  eta: 0:02:02  lr: 0.003994  min_lr: 0.003994  loss: 2.7753 (2.9556)  weight_decay: 0.0500 (0.0500)  time: 1.0073  data: 0.0005  max mem: 78493
Epoch: [26]  [210/312]  eta: 0:01:51  lr: 0.003994  min_lr: 0.003994  loss: 2.9983 (2.9571)  weight_decay: 0.0500 (0.0500)  time: 1.0066  data: 0.0004  max mem: 78493
Epoch: [26]  [220/312]  eta: 0:01:40  lr: 0.003994  min_lr: 0.003994  loss: 2.9983 (2.9536)  weight_decay: 0.0500 (0.0500)  time: 1.0066  data: 0.0004  max mem: 78493
Epoch: [26]  [230/312]  eta: 0:01:28  lr: 0.003994  min_lr: 0.003994  loss: 3.0019 (2.9573)  weight_decay: 0.0500 (0.0500)  time: 1.0058  data: 0.0005  max mem: 78493
Epoch: [26]  [240/312]  eta: 0:01:17  lr: 0.003994  min_lr: 0.003994  loss: 3.0140 (2.9522)  weight_decay: 0.0500 (0.0500)  time: 1.0048  data: 0.0005  max mem: 78493
Epoch: [26]  [250/312]  eta: 0:01:06  lr: 0.003994  min_lr: 0.003994  loss: 3.1290 (2.9630)  weight_decay: 0.0500 (0.0500)  time: 1.0051  data: 0.0005  max mem: 78493
Epoch: [26]  [260/312]  eta: 0:00:55  lr: 0.003994  min_lr: 0.003994  loss: 3.2758 (2.9597)  weight_decay: 0.0500 (0.0500)  time: 1.0061  data: 0.0005  max mem: 78493
Epoch: [26]  [270/312]  eta: 0:00:45  lr: 0.003994  min_lr: 0.003994  loss: 2.9742 (2.9615)  weight_decay: 0.0500 (0.0500)  time: 1.0060  data: 0.0004  max mem: 78493
Epoch: [26]  [280/312]  eta: 0:00:34  lr: 0.003994  min_lr: 0.003994  loss: 2.9742 (2.9653)  weight_decay: 0.0500 (0.0500)  time: 1.0064  data: 0.0010  max mem: 78493
Epoch: [26]  [290/312]  eta: 0:00:23  lr: 0.003994  min_lr: 0.003994  loss: 2.9458 (2.9654)  weight_decay: 0.0500 (0.0500)  time: 1.0049  data: 0.0009  max mem: 78493
Epoch: [26]  [300/312]  eta: 0:00:12  lr: 0.003994  min_lr: 0.003994  loss: 2.9818 (2.9675)  weight_decay: 0.0500 (0.0500)  time: 1.0024  data: 0.0001  max mem: 78493
Epoch: [26]  [310/312]  eta: 0:00:02  lr: 0.003994  min_lr: 0.003994  loss: 2.8035 (2.9612)  weight_decay: 0.0500 (0.0500)  time: 1.0022  data: 0.0001  max mem: 78493
Epoch: [26]  [311/312]  eta: 0:00:01  lr: 0.003994  min_lr: 0.003994  loss: 2.8035 (2.9618)  weight_decay: 0.0500 (0.0500)  time: 1.0022  data: 0.0001  max mem: 78493
Epoch: [26] Total time: 0:05:33 (1.0698 s / it)
Averaged stats: lr: 0.003994  min_lr: 0.003994  loss: 2.8035 (2.9689)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:11  loss: 1.0787 (1.0787)  acc1: 74.6094 (74.6094)  acc5: 92.0573 (92.0573)  time: 7.9562  data: 7.6869  max mem: 78493
Test:  [8/9]  eta: 0:00:01  loss: 1.5910 (1.4272)  acc1: 63.8021 (65.9680)  acc5: 87.2396 (86.8000)  time: 1.0913  data: 0.8633  max mem: 78493
Test: Total time: 0:00:09 (1.1014 s / it)
* Acc@1 66.050 Acc@5 86.912 loss 1.424
Accuracy of the model on the 50000 test images: 66.1%
Max accuracy: 66.20%
Epoch: [27]  [  0/312]  eta: 1:22:15  lr: 0.003994  min_lr: 0.003994  loss: 2.9718 (2.9718)  weight_decay: 0.0500 (0.0500)  time: 15.8189  data: 14.3055  max mem: 78493
Epoch: [27]  [ 10/312]  eta: 0:12:50  lr: 0.003994  min_lr: 0.003994  loss: 2.9103 (2.8219)  weight_decay: 0.0500 (0.0500)  time: 2.5505  data: 1.3349  max mem: 78493
Epoch: [27]  [ 20/312]  eta: 0:08:54  lr: 0.003994  min_lr: 0.003994  loss: 3.1137 (3.0046)  weight_decay: 0.0500 (0.0500)  time: 1.1296  data: 0.0195  max mem: 78493
Epoch: [27]  [ 30/312]  eta: 0:07:20  lr: 0.003994  min_lr: 0.003994  loss: 3.1661 (3.0241)  weight_decay: 0.0500 (0.0500)  time: 1.0211  data: 0.0008  max mem: 78493
Epoch: [27]  [ 40/312]  eta: 0:06:28  lr: 0.003994  min_lr: 0.003994  loss: 3.1743 (3.0306)  weight_decay: 0.0500 (0.0500)  time: 1.0107  data: 0.0007  max mem: 78493
Epoch: [27]  [ 50/312]  eta: 0:05:53  lr: 0.003994  min_lr: 0.003994  loss: 2.9818 (2.9835)  weight_decay: 0.0500 (0.0500)  time: 1.0147  data: 0.0023  max mem: 78493
Epoch: [27]  [ 60/312]  eta: 0:05:25  lr: 0.003993  min_lr: 0.003993  loss: 2.7024 (2.9481)  weight_decay: 0.0500 (0.0500)  time: 1.0111  data: 0.0022  max mem: 78493
Epoch: [27]  [ 70/312]  eta: 0:05:03  lr: 0.003993  min_lr: 0.003993  loss: 2.9623 (2.9755)  weight_decay: 0.0500 (0.0500)  time: 1.0097  data: 0.0005  max mem: 78493
Epoch: [27]  [ 80/312]  eta: 0:04:43  lr: 0.003993  min_lr: 0.003993  loss: 3.1863 (2.9884)  weight_decay: 0.0500 (0.0500)  time: 1.0116  data: 0.0005  max mem: 78493
Epoch: [27]  [ 90/312]  eta: 0:04:26  lr: 0.003993  min_lr: 0.003993  loss: 3.0432 (2.9951)  weight_decay: 0.0500 (0.0500)  time: 1.0094  data: 0.0005  max mem: 78493
Epoch: [27]  [100/312]  eta: 0:04:10  lr: 0.003993  min_lr: 0.003993  loss: 3.0044 (2.9933)  weight_decay: 0.0500 (0.0500)  time: 1.0062  data: 0.0005  max mem: 78493
Epoch: [27]  [110/312]  eta: 0:03:55  lr: 0.003993  min_lr: 0.003993  loss: 3.0443 (2.9940)  weight_decay: 0.0500 (0.0500)  time: 1.0052  data: 0.0005  max mem: 78493
Epoch: [27]  [120/312]  eta: 0:03:41  lr: 0.003993  min_lr: 0.003993  loss: 3.1115 (2.9992)  weight_decay: 0.0500 (0.0500)  time: 1.0055  data: 0.0005  max mem: 78493
Epoch: [27]  [130/312]  eta: 0:03:27  lr: 0.003993  min_lr: 0.003993  loss: 3.1759 (3.0055)  weight_decay: 0.0500 (0.0500)  time: 1.0071  data: 0.0004  max mem: 78493
Epoch: [27]  [140/312]  eta: 0:03:14  lr: 0.003993  min_lr: 0.003993  loss: 3.1301 (3.0043)  weight_decay: 0.0500 (0.0500)  time: 1.0079  data: 0.0004  max mem: 78493
Epoch: [27]  [150/312]  eta: 0:03:01  lr: 0.003993  min_lr: 0.003993  loss: 3.0447 (3.0012)  weight_decay: 0.0500 (0.0500)  time: 1.0068  data: 0.0005  max mem: 78493
Epoch: [27]  [160/312]  eta: 0:02:49  lr: 0.003993  min_lr: 0.003993  loss: 2.9600 (2.9849)  weight_decay: 0.0500 (0.0500)  time: 1.0057  data: 0.0005  max mem: 78493
Epoch: [27]  [170/312]  eta: 0:02:37  lr: 0.003993  min_lr: 0.003993  loss: 3.1067 (3.0009)  weight_decay: 0.0500 (0.0500)  time: 1.0051  data: 0.0004  max mem: 78493
Epoch: [27]  [180/312]  eta: 0:02:25  lr: 0.003993  min_lr: 0.003993  loss: 3.2409 (3.0036)  weight_decay: 0.0500 (0.0500)  time: 1.0054  data: 0.0004  max mem: 78493
Epoch: [27]  [190/312]  eta: 0:02:13  lr: 0.003993  min_lr: 0.003993  loss: 3.0851 (3.0004)  weight_decay: 0.0500 (0.0500)  time: 1.0053  data: 0.0004  max mem: 78493
Epoch: [27]  [200/312]  eta: 0:02:02  lr: 0.003993  min_lr: 0.003993  loss: 3.0090 (3.0051)  weight_decay: 0.0500 (0.0500)  time: 1.0043  data: 0.0004  max mem: 78493
Epoch: [27]  [210/312]  eta: 0:01:51  lr: 0.003993  min_lr: 0.003993  loss: 3.0090 (2.9989)  weight_decay: 0.0500 (0.0500)  time: 1.0051  data: 0.0004  max mem: 78493
Epoch: [27]  [220/312]  eta: 0:01:39  lr: 0.003993  min_lr: 0.003993  loss: 3.1101 (3.0025)  weight_decay: 0.0500 (0.0500)  time: 1.0063  data: 0.0004  max mem: 78493
Epoch: [27]  [230/312]  eta: 0:01:28  lr: 0.003992  min_lr: 0.003992  loss: 3.0985 (2.9976)  weight_decay: 0.0500 (0.0500)  time: 1.0056  data: 0.0004  max mem: 78493
Epoch: [27]  [240/312]  eta: 0:01:17  lr: 0.003992  min_lr: 0.003992  loss: 2.7800 (2.9843)  weight_decay: 0.0500 (0.0500)  time: 1.0048  data: 0.0004  max mem: 78493
Epoch: [27]  [250/312]  eta: 0:01:06  lr: 0.003992  min_lr: 0.003992  loss: 2.8673 (2.9826)  weight_decay: 0.0500 (0.0500)  time: 1.0047  data: 0.0005  max mem: 78493
Epoch: [27]  [260/312]  eta: 0:00:55  lr: 0.003992  min_lr: 0.003992  loss: 2.8673 (2.9708)  weight_decay: 0.0500 (0.0500)  time: 1.0044  data: 0.0005  max mem: 78493
Epoch: [27]  [270/312]  eta: 0:00:44  lr: 0.003992  min_lr: 0.003992  loss: 2.6524 (2.9678)  weight_decay: 0.0500 (0.0500)  time: 1.0038  data: 0.0005  max mem: 78493
Epoch: [27]  [280/312]  eta: 0:00:34  lr: 0.003992  min_lr: 0.003992  loss: 3.1633 (2.9727)  weight_decay: 0.0500 (0.0500)  time: 1.0057  data: 0.0011  max mem: 78493
Epoch: [27]  [290/312]  eta: 0:00:23  lr: 0.003992  min_lr: 0.003992  loss: 2.9317 (2.9676)  weight_decay: 0.0500 (0.0500)  time: 1.0052  data: 0.0009  max mem: 78493
Epoch: [27]  [300/312]  eta: 0:00:12  lr: 0.003992  min_lr: 0.003992  loss: 2.9003 (2.9712)  weight_decay: 0.0500 (0.0500)  time: 1.0024  data: 0.0001  max mem: 78493
Epoch: [27]  [310/312]  eta: 0:00:02  lr: 0.003992  min_lr: 0.003992  loss: 3.0913 (2.9700)  weight_decay: 0.0500 (0.0500)  time: 1.0021  data: 0.0001  max mem: 78493
Epoch: [27]  [311/312]  eta: 0:00:01  lr: 0.003992  min_lr: 0.003992  loss: 3.0913 (2.9704)  weight_decay: 0.0500 (0.0500)  time: 1.0022  data: 0.0001  max mem: 78493
Epoch: [27] Total time: 0:05:33 (1.0674 s / it)
Averaged stats: lr: 0.003992  min_lr: 0.003992  loss: 3.0913 (2.9553)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:13  loss: 1.1522 (1.1522)  acc1: 74.2188 (74.2188)  acc5: 91.2760 (91.2760)  time: 8.1701  data: 7.8671  max mem: 78493
Test:  [8/9]  eta: 0:00:01  loss: 1.6201 (1.4494)  acc1: 63.8021 (65.6320)  acc5: 84.8958 (86.4160)  time: 1.1061  data: 0.8742  max mem: 78493
Test: Total time: 0:00:10 (1.1478 s / it)
* Acc@1 65.404 Acc@5 86.592 loss 1.445
Accuracy of the model on the 50000 test images: 65.4%
Max accuracy: 66.20%
Epoch: [28]  [  0/312]  eta: 1:25:43  lr: 0.003992  min_lr: 0.003992  loss: 3.6766 (3.6766)  weight_decay: 0.0500 (0.0500)  time: 16.4867  data: 11.9629  max mem: 78493
Epoch: [28]  [ 10/312]  eta: 0:13:45  lr: 0.003992  min_lr: 0.003992  loss: 3.1826 (3.0956)  weight_decay: 0.0500 (0.0500)  time: 2.7327  data: 1.1581  max mem: 78493
Epoch: [28]  [ 20/312]  eta: 0:09:18  lr: 0.003992  min_lr: 0.003992  loss: 3.1076 (3.0725)  weight_decay: 0.0500 (0.0500)  time: 1.1827  data: 0.0390  max mem: 78493
Epoch: [28]  [ 30/312]  eta: 0:07:36  lr: 0.003992  min_lr: 0.003992  loss: 3.0598 (3.0687)  weight_decay: 0.0500 (0.0500)  time: 1.0061  data: 0.0004  max mem: 78493
Epoch: [28]  [ 40/312]  eta: 0:06:39  lr: 0.003992  min_lr: 0.003992  loss: 3.0598 (3.0370)  weight_decay: 0.0500 (0.0500)  time: 1.0048  data: 0.0004  max mem: 78493
Epoch: [28]  [ 50/312]  eta: 0:06:01  lr: 0.003992  min_lr: 0.003992  loss: 3.0739 (3.0214)  weight_decay: 0.0500 (0.0500)  time: 1.0064  data: 0.0004  max mem: 78493
Epoch: [28]  [ 60/312]  eta: 0:05:31  lr: 0.003992  min_lr: 0.003992  loss: 3.1033 (3.0217)  weight_decay: 0.0500 (0.0500)  time: 1.0056  data: 0.0004  max mem: 78493
Epoch: [28]  [ 70/312]  eta: 0:05:08  lr: 0.003991  min_lr: 0.003991  loss: 2.9638 (2.9813)  weight_decay: 0.0500 (0.0500)  time: 1.0046  data: 0.0004  max mem: 78493
Epoch: [28]  [ 80/312]  eta: 0:04:47  lr: 0.003991  min_lr: 0.003991  loss: 2.7763 (2.9760)  weight_decay: 0.0500 (0.0500)  time: 1.0077  data: 0.0004  max mem: 78493
Epoch: [28]  [ 90/312]  eta: 0:04:29  lr: 0.003991  min_lr: 0.003991  loss: 2.8673 (2.9762)  weight_decay: 0.0500 (0.0500)  time: 1.0096  data: 0.0004  max mem: 78493
Epoch: [28]  [100/312]  eta: 0:04:13  lr: 0.003991  min_lr: 0.003991  loss: 2.9906 (2.9743)  weight_decay: 0.0500 (0.0500)  time: 1.0073  data: 0.0004  max mem: 78493
Epoch: [28]  [110/312]  eta: 0:03:57  lr: 0.003991  min_lr: 0.003991  loss: 3.0313 (2.9828)  weight_decay: 0.0500 (0.0500)  time: 1.0088  data: 0.0004  max mem: 78493
Epoch: [28]  [120/312]  eta: 0:03:43  lr: 0.003991  min_lr: 0.003991  loss: 2.9787 (2.9709)  weight_decay: 0.0500 (0.0500)  time: 1.0100  data: 0.0004  max mem: 78493
Epoch: [28]  [130/312]  eta: 0:03:29  lr: 0.003991  min_lr: 0.003991  loss: 2.7518 (2.9638)  weight_decay: 0.0500 (0.0500)  time: 1.0071  data: 0.0004  max mem: 78493
Epoch: [28]  [140/312]  eta: 0:03:16  lr: 0.003991  min_lr: 0.003991  loss: 3.1117 (2.9612)  weight_decay: 0.0500 (0.0500)  time: 1.0061  data: 0.0004  max mem: 78493
Epoch: [28]  [150/312]  eta: 0:03:03  lr: 0.003991  min_lr: 0.003991  loss: 3.1159 (2.9589)  weight_decay: 0.0500 (0.0500)  time: 1.0063  data: 0.0005  max mem: 78493
Epoch: [28]  [160/312]  eta: 0:02:50  lr: 0.003991  min_lr: 0.003991  loss: 2.9807 (2.9490)  weight_decay: 0.0500 (0.0500)  time: 1.0054  data: 0.0005  max mem: 78493
Epoch: [28]  [170/312]  eta: 0:02:38  lr: 0.003991  min_lr: 0.003991  loss: 2.7863 (2.9395)  weight_decay: 0.0500 (0.0500)  time: 1.0058  data: 0.0004  max mem: 78493
Epoch: [28]  [180/312]  eta: 0:02:26  lr: 0.003991  min_lr: 0.003991  loss: 2.9455 (2.9449)  weight_decay: 0.0500 (0.0500)  time: 1.0075  data: 0.0004  max mem: 78493
Epoch: [28]  [190/312]  eta: 0:02:14  lr: 0.003991  min_lr: 0.003991  loss: 3.0177 (2.9462)  weight_decay: 0.0500 (0.0500)  time: 1.0058  data: 0.0004  max mem: 78493
Epoch: [28]  [200/312]  eta: 0:02:03  lr: 0.003991  min_lr: 0.003991  loss: 3.0226 (2.9523)  weight_decay: 0.0500 (0.0500)  time: 1.0040  data: 0.0005  max mem: 78493
Epoch: [28]  [210/312]  eta: 0:01:51  lr: 0.003991  min_lr: 0.003991  loss: 2.8164 (2.9441)  weight_decay: 0.0500 (0.0500)  time: 1.0041  data: 0.0005  max mem: 78493
Epoch: [28]  [220/312]  eta: 0:01:40  lr: 0.003990  min_lr: 0.003990  loss: 2.7026 (2.9397)  weight_decay: 0.0500 (0.0500)  time: 1.0049  data: 0.0004  max mem: 78493
Epoch: [28]  [230/312]  eta: 0:01:29  lr: 0.003990  min_lr: 0.003990  loss: 3.1993 (2.9574)  weight_decay: 0.0500 (0.0500)  time: 1.0057  data: 0.0005  max mem: 78493
Epoch: [28]  [240/312]  eta: 0:01:18  lr: 0.003990  min_lr: 0.003990  loss: 3.1988 (2.9516)  weight_decay: 0.0500 (0.0500)  time: 1.0056  data: 0.0005  max mem: 78493
Epoch: [28]  [250/312]  eta: 0:01:07  lr: 0.003990  min_lr: 0.003990  loss: 2.9564 (2.9520)  weight_decay: 0.0500 (0.0500)  time: 1.0052  data: 0.0004  max mem: 78493
Epoch: [28]  [260/312]  eta: 0:00:56  lr: 0.003990  min_lr: 0.003990  loss: 2.8693 (2.9490)  weight_decay: 0.0500 (0.0500)  time: 1.0047  data: 0.0004  max mem: 78493
Epoch: [28]  [270/312]  eta: 0:00:45  lr: 0.003990  min_lr: 0.003990  loss: 2.7229 (2.9349)  weight_decay: 0.0500 (0.0500)  time: 1.0054  data: 0.0004  max mem: 78493
Epoch: [28]  [280/312]  eta: 0:00:34  lr: 0.003990  min_lr: 0.003990  loss: 2.7168 (2.9312)  weight_decay: 0.0500 (0.0500)  time: 1.0065  data: 0.0016  max mem: 78493
Epoch: [28]  [290/312]  eta: 0:00:23  lr: 0.003990  min_lr: 0.003990  loss: 3.1005 (2.9354)  weight_decay: 0.0500 (0.0500)  time: 1.0052  data: 0.0015  max mem: 78493
Epoch: [28]  [300/312]  eta: 0:00:12  lr: 0.003990  min_lr: 0.003990  loss: 3.1366 (2.9368)  weight_decay: 0.0500 (0.0500)  time: 1.0026  data: 0.0001  max mem: 78493
Epoch: [28]  [310/312]  eta: 0:00:02  lr: 0.003990  min_lr: 0.003990  loss: 2.7830 (2.9321)  weight_decay: 0.0500 (0.0500)  time: 1.0015  data: 0.0001  max mem: 78493
Epoch: [28]  [311/312]  eta: 0:00:01  lr: 0.003990  min_lr: 0.003990  loss: 2.6113 (2.9295)  weight_decay: 0.0500 (0.0500)  time: 1.0015  data: 0.0001  max mem: 78493
Epoch: [28] Total time: 0:05:34 (1.0722 s / it)
Averaged stats: lr: 0.003990  min_lr: 0.003990  loss: 2.6113 (2.9141)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:11  loss: 1.1149 (1.1149)  acc1: 73.5677 (73.5677)  acc5: 91.1458 (91.1458)  time: 7.9403  data: 7.6571  max mem: 78493
Test:  [8/9]  eta: 0:00:01  loss: 1.4663 (1.3479)  acc1: 65.6250 (66.8640)  acc5: 87.2396 (87.6800)  time: 1.0810  data: 0.8512  max mem: 78493
Test: Total time: 0:00:09 (1.0951 s / it)
* Acc@1 66.750 Acc@5 87.752 loss 1.345
Accuracy of the model on the 50000 test images: 66.8%
Max accuracy: 66.75%
Epoch: [29]  [  0/312]  eta: 1:19:59  lr: 0.003990  min_lr: 0.003990  loss: 2.2781 (2.2781)  weight_decay: 0.0500 (0.0500)  time: 15.3845  data: 13.7748  max mem: 78493
Epoch: [29]  [ 10/312]  eta: 0:12:13  lr: 0.003990  min_lr: 0.003990  loss: 2.9821 (2.8235)  weight_decay: 0.0500 (0.0500)  time: 2.4284  data: 1.2530  max mem: 78493
Epoch: [29]  [ 20/312]  eta: 0:08:36  lr: 0.003990  min_lr: 0.003990  loss: 2.9958 (2.8409)  weight_decay: 0.0500 (0.0500)  time: 1.0895  data: 0.0007  max mem: 78493
Epoch: [29]  [ 30/312]  eta: 0:07:09  lr: 0.003990  min_lr: 0.003990  loss: 3.0405 (2.8784)  weight_decay: 0.0500 (0.0500)  time: 1.0259  data: 0.0013  max mem: 78493
Epoch: [29]  [ 40/312]  eta: 0:06:19  lr: 0.003990  min_lr: 0.003990  loss: 2.9392 (2.8792)  weight_decay: 0.0500 (0.0500)  time: 1.0044  data: 0.0021  max mem: 78493
Epoch: [29]  [ 50/312]  eta: 0:05:45  lr: 0.003989  min_lr: 0.003989  loss: 2.9001 (2.8761)  weight_decay: 0.0500 (0.0500)  time: 1.0042  data: 0.0013  max mem: 78493
Epoch: [29]  [ 60/312]  eta: 0:05:19  lr: 0.003989  min_lr: 0.003989  loss: 2.9704 (2.9076)  weight_decay: 0.0500 (0.0500)  time: 1.0068  data: 0.0004  max mem: 78493
Epoch: [29]  [ 70/312]  eta: 0:04:58  lr: 0.003989  min_lr: 0.003989  loss: 2.9429 (2.8768)  weight_decay: 0.0500 (0.0500)  time: 1.0099  data: 0.0005  max mem: 78493
Epoch: [29]  [ 80/312]  eta: 0:04:39  lr: 0.003989  min_lr: 0.003989  loss: 2.9348 (2.8753)  weight_decay: 0.0500 (0.0500)  time: 1.0112  data: 0.0005  max mem: 78493
Epoch: [29]  [ 90/312]  eta: 0:04:22  lr: 0.003989  min_lr: 0.003989  loss: 2.9401 (2.8709)  weight_decay: 0.0500 (0.0500)  time: 1.0100  data: 0.0005  max mem: 78493
Epoch: [29]  [100/312]  eta: 0:04:07  lr: 0.003989  min_lr: 0.003989  loss: 2.9515 (2.8730)  weight_decay: 0.0500 (0.0500)  time: 1.0091  data: 0.0005  max mem: 78493
Epoch: [29]  [110/312]  eta: 0:03:52  lr: 0.003989  min_lr: 0.003989  loss: 2.7371 (2.8611)  weight_decay: 0.0500 (0.0500)  time: 1.0087  data: 0.0005  max mem: 78493
Epoch: [29]  [120/312]  eta: 0:03:38  lr: 0.003989  min_lr: 0.003989  loss: 2.7371 (2.8720)  weight_decay: 0.0500 (0.0500)  time: 1.0082  data: 0.0004  max mem: 78493
Epoch: [29]  [130/312]  eta: 0:03:25  lr: 0.003989  min_lr: 0.003989  loss: 2.9340 (2.8586)  weight_decay: 0.0500 (0.0500)  time: 1.0093  data: 0.0005  max mem: 78493
Epoch: [29]  [140/312]  eta: 0:03:12  lr: 0.003989  min_lr: 0.003989  loss: 2.8126 (2.8603)  weight_decay: 0.0500 (0.0500)  time: 1.0091  data: 0.0011  max mem: 78493
Epoch: [29]  [150/312]  eta: 0:03:00  lr: 0.003989  min_lr: 0.003989  loss: 2.8126 (2.8665)  weight_decay: 0.0500 (0.0500)  time: 1.0077  data: 0.0011  max mem: 78493
Epoch: [29]  [160/312]  eta: 0:02:48  lr: 0.003989  min_lr: 0.003989  loss: 2.9854 (2.8671)  weight_decay: 0.0500 (0.0500)  time: 1.0081  data: 0.0004  max mem: 78493
Epoch: [29]  [170/312]  eta: 0:02:36  lr: 0.003989  min_lr: 0.003989  loss: 3.2137 (2.8825)  weight_decay: 0.0500 (0.0500)  time: 1.0069  data: 0.0004  max mem: 78493
Epoch: [29]  [180/312]  eta: 0:02:24  lr: 0.003988  min_lr: 0.003988  loss: 3.0731 (2.8822)  weight_decay: 0.0500 (0.0500)  time: 1.0052  data: 0.0005  max mem: 78493
Epoch: [29]  [190/312]  eta: 0:02:13  lr: 0.003988  min_lr: 0.003988  loss: 2.8733 (2.8798)  weight_decay: 0.0500 (0.0500)  time: 1.0041  data: 0.0004  max mem: 78493
Epoch: [29]  [200/312]  eta: 0:02:01  lr: 0.003988  min_lr: 0.003988  loss: 2.8162 (2.8741)  weight_decay: 0.0500 (0.0500)  time: 1.0050  data: 0.0004  max mem: 78493
Epoch: [29]  [210/312]  eta: 0:01:50  lr: 0.003988  min_lr: 0.003988  loss: 2.8168 (2.8751)  weight_decay: 0.0500 (0.0500)  time: 1.0052  data: 0.0005  max mem: 78493
Epoch: [29]  [220/312]  eta: 0:01:39  lr: 0.003988  min_lr: 0.003988  loss: 3.0796 (2.8804)  weight_decay: 0.0500 (0.0500)  time: 1.0060  data: 0.0004  max mem: 78493
Epoch: [29]  [230/312]  eta: 0:01:28  lr: 0.003988  min_lr: 0.003988  loss: 3.1320 (2.8873)  weight_decay: 0.0500 (0.0500)  time: 1.0072  data: 0.0004  max mem: 78493
Epoch: [29]  [240/312]  eta: 0:01:17  lr: 0.003988  min_lr: 0.003988  loss: 3.0433 (2.8874)  weight_decay: 0.0500 (0.0500)  time: 1.0049  data: 0.0004  max mem: 78493
Epoch: [29]  [250/312]  eta: 0:01:06  lr: 0.003988  min_lr: 0.003988  loss: 2.8255 (2.8824)  weight_decay: 0.0500 (0.0500)  time: 1.0052  data: 0.0004  max mem: 78493
Epoch: [29]  [260/312]  eta: 0:00:55  lr: 0.003988  min_lr: 0.003988  loss: 2.9193 (2.8877)  weight_decay: 0.0500 (0.0500)  time: 1.0058  data: 0.0004  max mem: 78493
Epoch: [29]  [270/312]  eta: 0:00:44  lr: 0.003988  min_lr: 0.003988  loss: 3.0733 (2.8847)  weight_decay: 0.0500 (0.0500)  time: 1.0046  data: 0.0005  max mem: 78493
Epoch: [29]  [280/312]  eta: 0:00:34  lr: 0.003988  min_lr: 0.003988  loss: 2.6172 (2.8784)  weight_decay: 0.0500 (0.0500)  time: 1.0059  data: 0.0011  max mem: 78493
Epoch: [29]  [290/312]  eta: 0:00:23  lr: 0.003988  min_lr: 0.003988  loss: 2.7829 (2.8760)  weight_decay: 0.0500 (0.0500)  time: 1.0043  data: 0.0009  max mem: 78493
Epoch: [29]  [300/312]  eta: 0:00:12  lr: 0.003988  min_lr: 0.003988  loss: 2.8365 (2.8722)  weight_decay: 0.0500 (0.0500)  time: 1.0012  data: 0.0001  max mem: 78493
Epoch: [29]  [310/312]  eta: 0:00:02  lr: 0.003987  min_lr: 0.003987  loss: 2.8656 (2.8755)  weight_decay: 0.0500 (0.0500)  time: 1.0013  data: 0.0001  max mem: 78493
Epoch: [29]  [311/312]  eta: 0:00:01  lr: 0.003987  min_lr: 0.003987  loss: 2.8656 (2.8760)  weight_decay: 0.0500 (0.0500)  time: 1.0014  data: 0.0001  max mem: 78493
Epoch: [29] Total time: 0:05:31 (1.0635 s / it)
Averaged stats: lr: 0.003987  min_lr: 0.003987  loss: 2.8656 (2.8919)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:10  loss: 1.0842 (1.0842)  acc1: 75.0000 (75.0000)  acc5: 91.2760 (91.2760)  time: 7.7894  data: 7.5263  max mem: 78493
Test:  [8/9]  eta: 0:00:01  loss: 1.5394 (1.3784)  acc1: 63.4115 (66.5760)  acc5: 87.2396 (87.2800)  time: 1.0725  data: 0.8363  max mem: 78493
Test: Total time: 0:00:09 (1.0945 s / it)
* Acc@1 66.666 Acc@5 87.424 loss 1.381
Accuracy of the model on the 50000 test images: 66.7%
Max accuracy: 66.75%
Epoch: [30]  [  0/312]  eta: 1:22:51  lr: 0.003987  min_lr: 0.003987  loss: 3.4156 (3.4156)  weight_decay: 0.0500 (0.0500)  time: 15.9355  data: 12.5730  max mem: 78493
Epoch: [30]  [ 10/312]  eta: 0:13:43  lr: 0.003987  min_lr: 0.003987  loss: 3.0542 (3.0658)  weight_decay: 0.0500 (0.0500)  time: 2.7276  data: 1.1908  max mem: 78493
Epoch: [30]  [ 20/312]  eta: 0:09:17  lr: 0.003987  min_lr: 0.003987  loss: 3.0347 (2.9407)  weight_decay: 0.0500 (0.0500)  time: 1.2071  data: 0.0265  max mem: 78493
Epoch: [30]  [ 30/312]  eta: 0:07:36  lr: 0.003987  min_lr: 0.003987  loss: 2.8714 (2.9385)  weight_decay: 0.0500 (0.0500)  time: 1.0088  data: 0.0015  max mem: 78493
Epoch: [30]  [ 40/312]  eta: 0:06:39  lr: 0.003987  min_lr: 0.003987  loss: 3.0890 (2.9364)  weight_decay: 0.0500 (0.0500)  time: 1.0092  data: 0.0024  max mem: 78493
Epoch: [30]  [ 50/312]  eta: 0:06:01  lr: 0.003987  min_lr: 0.003987  loss: 3.1135 (2.9549)  weight_decay: 0.0500 (0.0500)  time: 1.0091  data: 0.0014  max mem: 78493
Epoch: [30]  [ 60/312]  eta: 0:05:32  lr: 0.003987  min_lr: 0.003987  loss: 3.1852 (2.9788)  weight_decay: 0.0500 (0.0500)  time: 1.0090  data: 0.0004  max mem: 78493
Epoch: [30]  [ 70/312]  eta: 0:05:08  lr: 0.003987  min_lr: 0.003987  loss: 3.1226 (2.9852)  weight_decay: 0.0500 (0.0500)  time: 1.0074  data: 0.0004  max mem: 78493
Epoch: [30]  [ 80/312]  eta: 0:04:48  lr: 0.003987  min_lr: 0.003987  loss: 2.9325 (2.9722)  weight_decay: 0.0500 (0.0500)  time: 1.0061  data: 0.0004  max mem: 78493
Epoch: [30]  [ 90/312]  eta: 0:04:29  lr: 0.003987  min_lr: 0.003987  loss: 2.9898 (2.9734)  weight_decay: 0.0500 (0.0500)  time: 1.0074  data: 0.0004  max mem: 78493
Epoch: [30]  [100/312]  eta: 0:04:13  lr: 0.003987  min_lr: 0.003987  loss: 2.7845 (2.9449)  weight_decay: 0.0500 (0.0500)  time: 1.0088  data: 0.0005  max mem: 78493
Epoch: [30]  [110/312]  eta: 0:03:58  lr: 0.003987  min_lr: 0.003987  loss: 2.9286 (2.9588)  weight_decay: 0.0500 (0.0500)  time: 1.0093  data: 0.0005  max mem: 78493
Epoch: [30]  [120/312]  eta: 0:03:43  lr: 0.003986  min_lr: 0.003986  loss: 3.1527 (2.9624)  weight_decay: 0.0500 (0.0500)  time: 1.0090  data: 0.0005  max mem: 78493
Epoch: [30]  [130/312]  eta: 0:03:29  lr: 0.003986  min_lr: 0.003986  loss: 2.9870 (2.9606)  weight_decay: 0.0500 (0.0500)  time: 1.0065  data: 0.0005  max mem: 78493
Epoch: [30]  [140/312]  eta: 0:03:16  lr: 0.003986  min_lr: 0.003986  loss: 2.9233 (2.9561)  weight_decay: 0.0500 (0.0500)  time: 1.0052  data: 0.0005  max mem: 78493
Epoch: [30]  [150/312]  eta: 0:03:03  lr: 0.003986  min_lr: 0.003986  loss: 2.4584 (2.9221)  weight_decay: 0.0500 (0.0500)  time: 1.0074  data: 0.0005  max mem: 78493
Epoch: [30]  [160/312]  eta: 0:02:51  lr: 0.003986  min_lr: 0.003986  loss: 2.3901 (2.9125)  weight_decay: 0.0500 (0.0500)  time: 1.0078  data: 0.0004  max mem: 78493
Epoch: [30]  [170/312]  eta: 0:02:38  lr: 0.003986  min_lr: 0.003986  loss: 2.8707 (2.9130)  weight_decay: 0.0500 (0.0500)  time: 1.0081  data: 0.0005  max mem: 78493
Epoch: [30]  [180/312]  eta: 0:02:26  lr: 0.003986  min_lr: 0.003986  loss: 2.9547 (2.9200)  weight_decay: 0.0500 (0.0500)  time: 1.0081  data: 0.0004  max mem: 78493
Epoch: [30]  [190/312]  eta: 0:02:15  lr: 0.003986  min_lr: 0.003986  loss: 2.8808 (2.9129)  weight_decay: 0.0500 (0.0500)  time: 1.0082  data: 0.0004  max mem: 78493
Epoch: [30]  [200/312]  eta: 0:02:03  lr: 0.003986  min_lr: 0.003986  loss: 2.7848 (2.9143)  weight_decay: 0.0500 (0.0500)  time: 1.0091  data: 0.0005  max mem: 78493
Epoch: [30]  [210/312]  eta: 0:01:51  lr: 0.003986  min_lr: 0.003986  loss: 3.1133 (2.9157)  weight_decay: 0.0500 (0.0500)  time: 1.0080  data: 0.0004  max mem: 78493
Epoch: [30]  [220/312]  eta: 0:01:40  lr: 0.003986  min_lr: 0.003986  loss: 2.8327 (2.9116)  weight_decay: 0.0500 (0.0500)  time: 1.0069  data: 0.0004  max mem: 78493
Epoch: [30]  [230/312]  eta: 0:01:29  lr: 0.003986  min_lr: 0.003986  loss: 2.9104 (2.9102)  weight_decay: 0.0500 (0.0500)  time: 1.0055  data: 0.0004  max mem: 78493
Epoch: [30]  [240/312]  eta: 0:01:18  lr: 0.003985  min_lr: 0.003985  loss: 2.9117 (2.9041)  weight_decay: 0.0500 (0.0500)  time: 1.0057  data: 0.0004  max mem: 78493
Epoch: [30]  [250/312]  eta: 0:01:07  lr: 0.003985  min_lr: 0.003985  loss: 2.9111 (2.9037)  weight_decay: 0.0500 (0.0500)  time: 1.0060  data: 0.0004  max mem: 78493
Epoch: [30]  [260/312]  eta: 0:00:56  lr: 0.003985  min_lr: 0.003985  loss: 2.7616 (2.8953)  weight_decay: 0.0500 (0.0500)  time: 1.0058  data: 0.0004  max mem: 78493
Epoch: [30]  [270/312]  eta: 0:00:45  lr: 0.003985  min_lr: 0.003985  loss: 2.8727 (2.8988)  weight_decay: 0.0500 (0.0500)  time: 1.0058  data: 0.0004  max mem: 78493
Epoch: [30]  [280/312]  eta: 0:00:34  lr: 0.003985  min_lr: 0.003985  loss: 2.7893 (2.8872)  weight_decay: 0.0500 (0.0500)  time: 1.0061  data: 0.0010  max mem: 78493
Epoch: [30]  [290/312]  eta: 0:00:23  lr: 0.003985  min_lr: 0.003985  loss: 2.7400 (2.8896)  weight_decay: 0.0500 (0.0500)  time: 1.0042  data: 0.0009  max mem: 78493
Epoch: [30]  [300/312]  eta: 0:00:12  lr: 0.003985  min_lr: 0.003985  loss: 2.9801 (2.8912)  weight_decay: 0.0500 (0.0500)  time: 1.0022  data: 0.0001  max mem: 78493
Epoch: [30]  [310/312]  eta: 0:00:02  lr: 0.003985  min_lr: 0.003985  loss: 3.0041 (2.8977)  weight_decay: 0.0500 (0.0500)  time: 1.0023  data: 0.0001  max mem: 78493
Epoch: [30]  [311/312]  eta: 0:00:01  lr: 0.003985  min_lr: 0.003985  loss: 3.0041 (2.8982)  weight_decay: 0.0500 (0.0500)  time: 1.0022  data: 0.0001  max mem: 78493
Epoch: [30] Total time: 0:05:34 (1.0733 s / it)
Averaged stats: lr: 0.003985  min_lr: 0.003985  loss: 3.0041 (2.8740)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:17  loss: 1.1451 (1.1451)  acc1: 73.3073 (73.3073)  acc5: 91.1458 (91.1458)  time: 8.6627  data: 8.3931  max mem: 78493
Test:  [8/9]  eta: 0:00:01  loss: 1.5615 (1.3907)  acc1: 65.3646 (66.0800)  acc5: 85.2865 (86.6720)  time: 1.1613  data: 0.9327  max mem: 78493
Test: Total time: 0:00:10 (1.1906 s / it)
* Acc@1 66.460 Acc@5 87.284 loss 1.375
Accuracy of the model on the 50000 test images: 66.5%
Max accuracy: 66.75%
Epoch: [31]  [  0/312]  eta: 1:22:33  lr: 0.003985  min_lr: 0.003985  loss: 2.5234 (2.5234)  weight_decay: 0.0500 (0.0500)  time: 15.8752  data: 14.8541  max mem: 78493
Epoch: [31]  [ 10/312]  eta: 0:13:08  lr: 0.003985  min_lr: 0.003985  loss: 3.1430 (3.0401)  weight_decay: 0.0500 (0.0500)  time: 2.6125  data: 1.3511  max mem: 78493
Epoch: [31]  [ 20/312]  eta: 0:09:01  lr: 0.003985  min_lr: 0.003985  loss: 3.0275 (2.9557)  weight_decay: 0.0500 (0.0500)  time: 1.1533  data: 0.0007  max mem: 78493
Epoch: [31]  [ 30/312]  eta: 0:07:26  lr: 0.003985  min_lr: 0.003985  loss: 2.9998 (2.9876)  weight_decay: 0.0500 (0.0500)  time: 1.0157  data: 0.0005  max mem: 78493
Epoch: [31]  [ 40/312]  eta: 0:06:32  lr: 0.003984  min_lr: 0.003984  loss: 3.0244 (2.9951)  weight_decay: 0.0500 (0.0500)  time: 1.0109  data: 0.0004  max mem: 78493
Epoch: [31]  [ 50/312]  eta: 0:05:55  lr: 0.003984  min_lr: 0.003984  loss: 2.9502 (2.9370)  weight_decay: 0.0500 (0.0500)  time: 1.0092  data: 0.0004  max mem: 78493
Epoch: [31]  [ 60/312]  eta: 0:05:27  lr: 0.003984  min_lr: 0.003984  loss: 2.9163 (2.9499)  weight_decay: 0.0500 (0.0500)  time: 1.0074  data: 0.0004  max mem: 78493
Epoch: [31]  [ 70/312]  eta: 0:05:04  lr: 0.003984  min_lr: 0.003984  loss: 2.9482 (2.9347)  weight_decay: 0.0500 (0.0500)  time: 1.0090  data: 0.0005  max mem: 78493
Epoch: [31]  [ 80/312]  eta: 0:04:45  lr: 0.003984  min_lr: 0.003984  loss: 2.7237 (2.9198)  weight_decay: 0.0500 (0.0500)  time: 1.0111  data: 0.0005  max mem: 78493
Epoch: [31]  [ 90/312]  eta: 0:04:27  lr: 0.003984  min_lr: 0.003984  loss: 2.8809 (2.9148)  weight_decay: 0.0500 (0.0500)  time: 1.0103  data: 0.0005  max mem: 78493
Epoch: [31]  [100/312]  eta: 0:04:11  lr: 0.003984  min_lr: 0.003984  loss: 2.7437 (2.8946)  weight_decay: 0.0500 (0.0500)  time: 1.0087  data: 0.0005  max mem: 78493
Epoch: [31]  [110/312]  eta: 0:03:56  lr: 0.003984  min_lr: 0.003984  loss: 2.7450 (2.8911)  weight_decay: 0.0500 (0.0500)  time: 1.0082  data: 0.0012  max mem: 78493
Epoch: [31]  [120/312]  eta: 0:03:41  lr: 0.003984  min_lr: 0.003984  loss: 2.9557 (2.8946)  weight_decay: 0.0500 (0.0500)  time: 1.0079  data: 0.0011  max mem: 78493
Epoch: [31]  [130/312]  eta: 0:03:28  lr: 0.003984  min_lr: 0.003984  loss: 2.9388 (2.8946)  weight_decay: 0.0500 (0.0500)  time: 1.0073  data: 0.0005  max mem: 78493
Epoch: [31]  [140/312]  eta: 0:03:15  lr: 0.003984  min_lr: 0.003984  loss: 2.9205 (2.8850)  weight_decay: 0.0500 (0.0500)  time: 1.0063  data: 0.0005  max mem: 78493
Epoch: [31]  [150/312]  eta: 0:03:02  lr: 0.003983  min_lr: 0.003983  loss: 2.9835 (2.8846)  weight_decay: 0.0500 (0.0500)  time: 1.0054  data: 0.0005  max mem: 78493
Epoch: [31]  [160/312]  eta: 0:02:50  lr: 0.003983  min_lr: 0.003983  loss: 2.9835 (2.8830)  weight_decay: 0.0500 (0.0500)  time: 1.0051  data: 0.0005  max mem: 78493
Epoch: [31]  [170/312]  eta: 0:02:37  lr: 0.003983  min_lr: 0.003983  loss: 2.9763 (2.8829)  weight_decay: 0.0500 (0.0500)  time: 1.0045  data: 0.0005  max mem: 78493
Epoch: [31]  [180/312]  eta: 0:02:25  lr: 0.003983  min_lr: 0.003983  loss: 2.7564 (2.8730)  weight_decay: 0.0500 (0.0500)  time: 1.0052  data: 0.0004  max mem: 78493
Epoch: [31]  [190/312]  eta: 0:02:14  lr: 0.003983  min_lr: 0.003983  loss: 2.8732 (2.8718)  weight_decay: 0.0500 (0.0500)  time: 1.0066  data: 0.0004  max mem: 78493
Epoch: [31]  [200/312]  eta: 0:02:02  lr: 0.003983  min_lr: 0.003983  loss: 2.8732 (2.8669)  weight_decay: 0.0500 (0.0500)  time: 1.0071  data: 0.0004  max mem: 78493
Epoch: [31]  [210/312]  eta: 0:01:51  lr: 0.003983  min_lr: 0.003983  loss: 2.9337 (2.8726)  weight_decay: 0.0500 (0.0500)  time: 1.0071  data: 0.0004  max mem: 78493
Epoch: [31]  [220/312]  eta: 0:01:40  lr: 0.003983  min_lr: 0.003983  loss: 3.0287 (2.8749)  weight_decay: 0.0500 (0.0500)  time: 1.0063  data: 0.0004  max mem: 78493
Epoch: [31]  [230/312]  eta: 0:01:28  lr: 0.003983  min_lr: 0.003983  loss: 2.7929 (2.8638)  weight_decay: 0.0500 (0.0500)  time: 1.0071  data: 0.0004  max mem: 78493
Epoch: [31]  [240/312]  eta: 0:01:17  lr: 0.003983  min_lr: 0.003983  loss: 2.7556 (2.8676)  weight_decay: 0.0500 (0.0500)  time: 1.0066  data: 0.0004  max mem: 78493
Epoch: [31]  [250/312]  eta: 0:01:06  lr: 0.003982  min_lr: 0.003982  loss: 3.0661 (2.8707)  weight_decay: 0.0500 (0.0500)  time: 1.0056  data: 0.0004  max mem: 78493
Epoch: [31]  [260/312]  eta: 0:00:55  lr: 0.003982  min_lr: 0.003982  loss: 3.0661 (2.8737)  weight_decay: 0.0500 (0.0500)  time: 1.0051  data: 0.0004  max mem: 78493
Epoch: [31]  [270/312]  eta: 0:00:45  lr: 0.003982  min_lr: 0.003982  loss: 3.0174 (2.8713)  weight_decay: 0.0500 (0.0500)  time: 1.0058  data: 0.0005  max mem: 78493
Epoch: [31]  [280/312]  eta: 0:00:34  lr: 0.003982  min_lr: 0.003982  loss: 2.9119 (2.8706)  weight_decay: 0.0500 (0.0500)  time: 1.0070  data: 0.0011  max mem: 78493
Epoch: [31]  [290/312]  eta: 0:00:23  lr: 0.003982  min_lr: 0.003982  loss: 2.7449 (2.8632)  weight_decay: 0.0500 (0.0500)  time: 1.0042  data: 0.0009  max mem: 78493
Epoch: [31]  [300/312]  eta: 0:00:12  lr: 0.003982  min_lr: 0.003982  loss: 2.7287 (2.8629)  weight_decay: 0.0500 (0.0500)  time: 1.0019  data: 0.0001  max mem: 78493
Epoch: [31]  [310/312]  eta: 0:00:02  lr: 0.003982  min_lr: 0.003982  loss: 3.0658 (2.8676)  weight_decay: 0.0500 (0.0500)  time: 1.0018  data: 0.0001  max mem: 78493
Epoch: [31]  [311/312]  eta: 0:00:01  lr: 0.003982  min_lr: 0.003982  loss: 3.0658 (2.8672)  weight_decay: 0.0500 (0.0500)  time: 1.0017  data: 0.0001  max mem: 78493
Epoch: [31] Total time: 0:05:33 (1.0694 s / it)
Averaged stats: lr: 0.003982  min_lr: 0.003982  loss: 3.0658 (2.8558)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:15  loss: 1.1665 (1.1665)  acc1: 72.7865 (72.7865)  acc5: 90.4948 (90.4948)  time: 8.3926  data: 8.1250  max mem: 78493
Test:  [8/9]  eta: 0:00:01  loss: 1.6169 (1.4431)  acc1: 62.3698 (64.6080)  acc5: 85.5469 (86.4800)  time: 1.1320  data: 0.9029  max mem: 78493
Test: Total time: 0:00:10 (1.1776 s / it)
* Acc@1 65.016 Acc@5 86.350 loss 1.443
Accuracy of the model on the 50000 test images: 65.0%
Max accuracy: 66.75%
Epoch: [32]  [  0/312]  eta: 1:18:28  lr: 0.003982  min_lr: 0.003982  loss: 2.5358 (2.5358)  weight_decay: 0.0500 (0.0500)  time: 15.0914  data: 13.7680  max mem: 78493
Epoch: [32]  [ 10/312]  eta: 0:12:23  lr: 0.003982  min_lr: 0.003982  loss: 2.7190 (2.6862)  weight_decay: 0.0500 (0.0500)  time: 2.4626  data: 1.2844  max mem: 78493
Epoch: [32]  [ 20/312]  eta: 0:08:45  lr: 0.003982  min_lr: 0.003982  loss: 2.7244 (2.7616)  weight_decay: 0.0500 (0.0500)  time: 1.1364  data: 0.0198  max mem: 78493
Epoch: [32]  [ 30/312]  eta: 0:07:15  lr: 0.003982  min_lr: 0.003982  loss: 2.9607 (2.8329)  weight_decay: 0.0500 (0.0500)  time: 1.0405  data: 0.0020  max mem: 78493
Epoch: [32]  [ 40/312]  eta: 0:06:24  lr: 0.003982  min_lr: 0.003982  loss: 3.0160 (2.8431)  weight_decay: 0.0500 (0.0500)  time: 1.0069  data: 0.0004  max mem: 78493
Epoch: [32]  [ 50/312]  eta: 0:05:49  lr: 0.003981  min_lr: 0.003981  loss: 3.0931 (2.8830)  weight_decay: 0.0500 (0.0500)  time: 1.0082  data: 0.0004  max mem: 78493
Epoch: [32]  [ 60/312]  eta: 0:05:22  lr: 0.003981  min_lr: 0.003981  loss: 3.0379 (2.8786)  weight_decay: 0.0500 (0.0500)  time: 1.0095  data: 0.0005  max mem: 78493
Epoch: [32]  [ 70/312]  eta: 0:05:00  lr: 0.003981  min_lr: 0.003981  loss: 2.8724 (2.8720)  weight_decay: 0.0500 (0.0500)  time: 1.0083  data: 0.0004  max mem: 78493
Epoch: [32]  [ 80/312]  eta: 0:04:41  lr: 0.003981  min_lr: 0.003981  loss: 2.9578 (2.8928)  weight_decay: 0.0500 (0.0500)  time: 1.0095  data: 0.0005  max mem: 78493
Epoch: [32]  [ 90/312]  eta: 0:04:24  lr: 0.003981  min_lr: 0.003981  loss: 2.9583 (2.8958)  weight_decay: 0.0500 (0.0500)  time: 1.0089  data: 0.0005  max mem: 78493
Epoch: [32]  [100/312]  eta: 0:04:08  lr: 0.003981  min_lr: 0.003981  loss: 2.8992 (2.8993)  weight_decay: 0.0500 (0.0500)  time: 1.0053  data: 0.0005  max mem: 78493
Epoch: [32]  [110/312]  eta: 0:03:53  lr: 0.003981  min_lr: 0.003981  loss: 2.8848 (2.8955)  weight_decay: 0.0500 (0.0500)  time: 1.0046  data: 0.0005  max mem: 78493
Epoch: [32]  [120/312]  eta: 0:03:39  lr: 0.003981  min_lr: 0.003981  loss: 2.8848 (2.8861)  weight_decay: 0.0500 (0.0500)  time: 1.0063  data: 0.0004  max mem: 78493
Epoch: [32]  [130/312]  eta: 0:03:26  lr: 0.003981  min_lr: 0.003981  loss: 2.8983 (2.8921)  weight_decay: 0.0500 (0.0500)  time: 1.0067  data: 0.0004  max mem: 78493
Epoch: [32]  [140/312]  eta: 0:03:13  lr: 0.003981  min_lr: 0.003981  loss: 2.9553 (2.8938)  weight_decay: 0.0500 (0.0500)  time: 1.0066  data: 0.0004  max mem: 78493
Epoch: [32]  [150/312]  eta: 0:03:01  lr: 0.003980  min_lr: 0.003980  loss: 2.9287 (2.8864)  weight_decay: 0.0500 (0.0500)  time: 1.0067  data: 0.0004  max mem: 78493
Epoch: [32]  [160/312]  eta: 0:02:48  lr: 0.003980  min_lr: 0.003980  loss: 2.9287 (2.8864)  weight_decay: 0.0500 (0.0500)  time: 1.0069  data: 0.0004  max mem: 78493
Epoch: [32]  [170/312]  eta: 0:02:36  lr: 0.003980  min_lr: 0.003980  loss: 2.8891 (2.8804)  weight_decay: 0.0500 (0.0500)  time: 1.0078  data: 0.0004  max mem: 78493
Epoch: [32]  [180/312]  eta: 0:02:25  lr: 0.003980  min_lr: 0.003980  loss: 2.6636 (2.8691)  weight_decay: 0.0500 (0.0500)  time: 1.0073  data: 0.0004  max mem: 78493
Epoch: [32]  [190/312]  eta: 0:02:13  lr: 0.003980  min_lr: 0.003980  loss: 2.8189 (2.8767)  weight_decay: 0.0500 (0.0500)  time: 1.0065  data: 0.0004  max mem: 78493
Epoch: [32]  [200/312]  eta: 0:02:02  lr: 0.003980  min_lr: 0.003980  loss: 3.0639 (2.8752)  weight_decay: 0.0500 (0.0500)  time: 1.0090  data: 0.0004  max mem: 78493
Epoch: [32]  [210/312]  eta: 0:01:50  lr: 0.003980  min_lr: 0.003980  loss: 3.0639 (2.8785)  weight_decay: 0.0500 (0.0500)  time: 1.0088  data: 0.0004  max mem: 78493
Epoch: [32]  [220/312]  eta: 0:01:39  lr: 0.003980  min_lr: 0.003980  loss: 3.0288 (2.8831)  weight_decay: 0.0500 (0.0500)  time: 1.0055  data: 0.0004  max mem: 78493
Epoch: [32]  [230/312]  eta: 0:01:28  lr: 0.003980  min_lr: 0.003980  loss: 2.9120 (2.8796)  weight_decay: 0.0500 (0.0500)  time: 1.0058  data: 0.0005  max mem: 78493
Epoch: [32]  [240/312]  eta: 0:01:17  lr: 0.003980  min_lr: 0.003980  loss: 2.8335 (2.8730)  weight_decay: 0.0500 (0.0500)  time: 1.0067  data: 0.0005  max mem: 78493
Epoch: [32]  [250/312]  eta: 0:01:06  lr: 0.003979  min_lr: 0.003979  loss: 2.7069 (2.8675)  weight_decay: 0.0500 (0.0500)  time: 1.0071  data: 0.0004  max mem: 78493
Epoch: [32]  [260/312]  eta: 0:00:55  lr: 0.003979  min_lr: 0.003979  loss: 2.8579 (2.8661)  weight_decay: 0.0500 (0.0500)  time: 1.0079  data: 0.0004  max mem: 78493
Epoch: [32]  [270/312]  eta: 0:00:44  lr: 0.003979  min_lr: 0.003979  loss: 3.0445 (2.8790)  weight_decay: 0.0500 (0.0500)  time: 1.0077  data: 0.0004  max mem: 78493
Epoch: [32]  [280/312]  eta: 0:00:34  lr: 0.003979  min_lr: 0.003979  loss: 3.1506 (2.8852)  weight_decay: 0.0500 (0.0500)  time: 1.0069  data: 0.0010  max mem: 78493
Epoch: [32]  [290/312]  eta: 0:00:23  lr: 0.003979  min_lr: 0.003979  loss: 2.8770 (2.8765)  weight_decay: 0.0500 (0.0500)  time: 1.0043  data: 0.0009  max mem: 78493
Epoch: [32]  [300/312]  eta: 0:00:12  lr: 0.003979  min_lr: 0.003979  loss: 2.9561 (2.8809)  weight_decay: 0.0500 (0.0500)  time: 1.0022  data: 0.0001  max mem: 78493
Epoch: [32]  [310/312]  eta: 0:00:02  lr: 0.003979  min_lr: 0.003979  loss: 2.9561 (2.8780)  weight_decay: 0.0500 (0.0500)  time: 1.0019  data: 0.0001  max mem: 78493
Epoch: [32]  [311/312]  eta: 0:00:01  lr: 0.003979  min_lr: 0.003979  loss: 3.0233 (2.8802)  weight_decay: 0.0500 (0.0500)  time: 1.0019  data: 0.0001  max mem: 78493
Epoch: [32] Total time: 0:05:32 (1.0663 s / it)
Averaged stats: lr: 0.003979  min_lr: 0.003979  loss: 3.0233 (2.8395)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:17  loss: 1.0016 (1.0016)  acc1: 75.5208 (75.5208)  acc5: 93.3594 (93.3594)  time: 8.5632  data: 8.3029  max mem: 78493
Test:  [8/9]  eta: 0:00:01  loss: 1.4282 (1.2646)  acc1: 67.3177 (68.0480)  acc5: 87.8906 (88.5120)  time: 1.1557  data: 0.9226  max mem: 78493
Test: Total time: 0:00:10 (1.2033 s / it)
* Acc@1 68.688 Acc@5 88.684 loss 1.268
Accuracy of the model on the 50000 test images: 68.7%
Max accuracy: 68.69%
Epoch: [33]  [  0/312]  eta: 1:19:05  lr: 0.003979  min_lr: 0.003979  loss: 2.6373 (2.6373)  weight_decay: 0.0500 (0.0500)  time: 15.2111  data: 12.7632  max mem: 78493
Epoch: [33]  [ 10/312]  eta: 0:12:51  lr: 0.003979  min_lr: 0.003979  loss: 3.0053 (3.0815)  weight_decay: 0.0500 (0.0500)  time: 2.5553  data: 1.2067  max mem: 78493
Epoch: [33]  [ 20/312]  eta: 0:08:53  lr: 0.003979  min_lr: 0.003979  loss: 2.8577 (2.8267)  weight_decay: 0.0500 (0.0500)  time: 1.1561  data: 0.0268  max mem: 78493
Epoch: [33]  [ 30/312]  eta: 0:07:20  lr: 0.003978  min_lr: 0.003978  loss: 2.6401 (2.8101)  weight_decay: 0.0500 (0.0500)  time: 1.0150  data: 0.0014  max mem: 78493
Epoch: [33]  [ 40/312]  eta: 0:06:28  lr: 0.003978  min_lr: 0.003978  loss: 2.8101 (2.8221)  weight_decay: 0.0500 (0.0500)  time: 1.0082  data: 0.0004  max mem: 78493
Epoch: [33]  [ 50/312]  eta: 0:05:52  lr: 0.003978  min_lr: 0.003978  loss: 2.8850 (2.8527)  weight_decay: 0.0500 (0.0500)  time: 1.0082  data: 0.0005  max mem: 78493
Epoch: [33]  [ 60/312]  eta: 0:05:24  lr: 0.003978  min_lr: 0.003978  loss: 3.0424 (2.8711)  weight_decay: 0.0500 (0.0500)  time: 1.0074  data: 0.0004  max mem: 78493
Epoch: [33]  [ 70/312]  eta: 0:05:02  lr: 0.003978  min_lr: 0.003978  loss: 2.9121 (2.8660)  weight_decay: 0.0500 (0.0500)  time: 1.0078  data: 0.0011  max mem: 78493
Epoch: [33]  [ 80/312]  eta: 0:04:42  lr: 0.003978  min_lr: 0.003978  loss: 2.7563 (2.8354)  weight_decay: 0.0500 (0.0500)  time: 1.0064  data: 0.0012  max mem: 78493
Epoch: [33]  [ 90/312]  eta: 0:04:25  lr: 0.003978  min_lr: 0.003978  loss: 2.4803 (2.8127)  weight_decay: 0.0500 (0.0500)  time: 1.0042  data: 0.0005  max mem: 78493
Epoch: [33]  [100/312]  eta: 0:04:09  lr: 0.003978  min_lr: 0.003978  loss: 2.7708 (2.8220)  weight_decay: 0.0500 (0.0500)  time: 1.0057  data: 0.0004  max mem: 78493
Epoch: [33]  [110/312]  eta: 0:03:54  lr: 0.003978  min_lr: 0.003978  loss: 2.7708 (2.8030)  weight_decay: 0.0500 (0.0500)  time: 1.0075  data: 0.0013  max mem: 78493
Epoch: [33]  [120/312]  eta: 0:03:40  lr: 0.003977  min_lr: 0.003977  loss: 2.6817 (2.8105)  weight_decay: 0.0500 (0.0500)  time: 1.0066  data: 0.0012  max mem: 78493
Epoch: [33]  [130/312]  eta: 0:03:27  lr: 0.003977  min_lr: 0.003977  loss: 2.9308 (2.8119)  weight_decay: 0.0500 (0.0500)  time: 1.0055  data: 0.0004  max mem: 78493
Epoch: [33]  [140/312]  eta: 0:03:14  lr: 0.003977  min_lr: 0.003977  loss: 2.7778 (2.8065)  weight_decay: 0.0500 (0.0500)  time: 1.0056  data: 0.0004  max mem: 78493
Epoch: [33]  [150/312]  eta: 0:03:01  lr: 0.003977  min_lr: 0.003977  loss: 2.6703 (2.8020)  weight_decay: 0.0500 (0.0500)  time: 1.0070  data: 0.0004  max mem: 78493
Epoch: [33]  [160/312]  eta: 0:02:49  lr: 0.003977  min_lr: 0.003977  loss: 2.6479 (2.8022)  weight_decay: 0.0500 (0.0500)  time: 1.0089  data: 0.0004  max mem: 78493
Epoch: [33]  [170/312]  eta: 0:02:37  lr: 0.003977  min_lr: 0.003977  loss: 2.8063 (2.7982)  weight_decay: 0.0500 (0.0500)  time: 1.0091  data: 0.0004  max mem: 78493
Epoch: [33]  [180/312]  eta: 0:02:25  lr: 0.003977  min_lr: 0.003977  loss: 2.9645 (2.8091)  weight_decay: 0.0500 (0.0500)  time: 1.0087  data: 0.0004  max mem: 78493
Epoch: [33]  [190/312]  eta: 0:02:13  lr: 0.003977  min_lr: 0.003977  loss: 3.0133 (2.8099)  weight_decay: 0.0500 (0.0500)  time: 1.0083  data: 0.0004  max mem: 78493
Epoch: [33]  [200/312]  eta: 0:02:02  lr: 0.003977  min_lr: 0.003977  loss: 2.7739 (2.8040)  weight_decay: 0.0500 (0.0500)  time: 1.0057  data: 0.0004  max mem: 78493
Epoch: [33]  [210/312]  eta: 0:01:51  lr: 0.003977  min_lr: 0.003977  loss: 2.9070 (2.8126)  weight_decay: 0.0500 (0.0500)  time: 1.0049  data: 0.0004  max mem: 78493
Epoch: [33]  [220/312]  eta: 0:01:39  lr: 0.003976  min_lr: 0.003976  loss: 2.9070 (2.8138)  weight_decay: 0.0500 (0.0500)  time: 1.0048  data: 0.0004  max mem: 78493
Epoch: [33]  [230/312]  eta: 0:01:28  lr: 0.003976  min_lr: 0.003976  loss: 2.8364 (2.8114)  weight_decay: 0.0500 (0.0500)  time: 1.0051  data: 0.0004  max mem: 78493
Epoch: [33]  [240/312]  eta: 0:01:17  lr: 0.003976  min_lr: 0.003976  loss: 2.5881 (2.8136)  weight_decay: 0.0500 (0.0500)  time: 1.0065  data: 0.0004  max mem: 78493
Epoch: [33]  [250/312]  eta: 0:01:06  lr: 0.003976  min_lr: 0.003976  loss: 2.5881 (2.8103)  weight_decay: 0.0500 (0.0500)  time: 1.0060  data: 0.0004  max mem: 78493
Epoch: [33]  [260/312]  eta: 0:00:55  lr: 0.003976  min_lr: 0.003976  loss: 2.9708 (2.8144)  weight_decay: 0.0500 (0.0500)  time: 1.0057  data: 0.0004  max mem: 78493
Epoch: [33]  [270/312]  eta: 0:00:44  lr: 0.003976  min_lr: 0.003976  loss: 2.5866 (2.8002)  weight_decay: 0.0500 (0.0500)  time: 1.0066  data: 0.0004  max mem: 78493
Epoch: [33]  [280/312]  eta: 0:00:34  lr: 0.003976  min_lr: 0.003976  loss: 2.5413 (2.8022)  weight_decay: 0.0500 (0.0500)  time: 1.0070  data: 0.0010  max mem: 78493
Epoch: [33]  [290/312]  eta: 0:00:23  lr: 0.003976  min_lr: 0.003976  loss: 2.8576 (2.8047)  weight_decay: 0.0500 (0.0500)  time: 1.0042  data: 0.0009  max mem: 78493
Epoch: [33]  [300/312]  eta: 0:00:12  lr: 0.003976  min_lr: 0.003976  loss: 2.7266 (2.7968)  weight_decay: 0.0500 (0.0500)  time: 1.0016  data: 0.0001  max mem: 78493
Epoch: [33]  [310/312]  eta: 0:00:02  lr: 0.003975  min_lr: 0.003975  loss: 2.6560 (2.7960)  weight_decay: 0.0500 (0.0500)  time: 1.0014  data: 0.0001  max mem: 78493
Epoch: [33]  [311/312]  eta: 0:00:01  lr: 0.003975  min_lr: 0.003975  loss: 2.6560 (2.7975)  weight_decay: 0.0500 (0.0500)  time: 1.0014  data: 0.0001  max mem: 78493
Epoch: [33] Total time: 0:05:32 (1.0669 s / it)
Averaged stats: lr: 0.003975  min_lr: 0.003975  loss: 2.6560 (2.8292)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:11  loss: 1.0016 (1.0016)  acc1: 76.6927 (76.6927)  acc5: 91.7969 (91.7969)  time: 7.9801  data: 7.6777  max mem: 78493
Test:  [8/9]  eta: 0:00:01  loss: 1.3931 (1.2953)  acc1: 67.0573 (67.6800)  acc5: 88.9323 (88.1440)  time: 1.0849  data: 0.8532  max mem: 78493
Test: Total time: 0:00:10 (1.1176 s / it)
* Acc@1 67.940 Acc@5 88.164 loss 1.308
Accuracy of the model on the 50000 test images: 67.9%
Max accuracy: 68.69%
Epoch: [34]  [  0/312]  eta: 1:26:21  lr: 0.003975  min_lr: 0.003975  loss: 3.1059 (3.1059)  weight_decay: 0.0500 (0.0500)  time: 16.6066  data: 13.1084  max mem: 78493
Epoch: [34]  [ 10/312]  eta: 0:13:27  lr: 0.003975  min_lr: 0.003975  loss: 2.7197 (2.7481)  weight_decay: 0.0500 (0.0500)  time: 2.6736  data: 1.2329  max mem: 78493
Epoch: [34]  [ 20/312]  eta: 0:09:09  lr: 0.003975  min_lr: 0.003975  loss: 2.7181 (2.7509)  weight_decay: 0.0500 (0.0500)  time: 1.1444  data: 0.0229  max mem: 78493
Epoch: [34]  [ 30/312]  eta: 0:07:30  lr: 0.003975  min_lr: 0.003975  loss: 3.0614 (2.8525)  weight_decay: 0.0500 (0.0500)  time: 1.0067  data: 0.0005  max mem: 78493
Epoch: [34]  [ 40/312]  eta: 0:06:35  lr: 0.003975  min_lr: 0.003975  loss: 2.9900 (2.8087)  weight_decay: 0.0500 (0.0500)  time: 1.0044  data: 0.0004  max mem: 78493
Epoch: [34]  [ 50/312]  eta: 0:05:57  lr: 0.003975  min_lr: 0.003975  loss: 2.5318 (2.7703)  weight_decay: 0.0500 (0.0500)  time: 1.0052  data: 0.0005  max mem: 78493
Epoch: [34]  [ 60/312]  eta: 0:05:29  lr: 0.003975  min_lr: 0.003975  loss: 2.5566 (2.7794)  weight_decay: 0.0500 (0.0500)  time: 1.0065  data: 0.0004  max mem: 78493
Epoch: [34]  [ 70/312]  eta: 0:05:05  lr: 0.003975  min_lr: 0.003975  loss: 2.8848 (2.7845)  weight_decay: 0.0500 (0.0500)  time: 1.0059  data: 0.0004  max mem: 78493
Epoch: [34]  [ 80/312]  eta: 0:04:46  lr: 0.003974  min_lr: 0.003974  loss: 2.9078 (2.8196)  weight_decay: 0.0500 (0.0500)  time: 1.0075  data: 0.0004  max mem: 78493
Epoch: [34]  [ 90/312]  eta: 0:04:28  lr: 0.003974  min_lr: 0.003974  loss: 2.9078 (2.8215)  weight_decay: 0.0500 (0.0500)  time: 1.0093  data: 0.0004  max mem: 78493
Epoch: [34]  [100/312]  eta: 0:04:11  lr: 0.003974  min_lr: 0.003974  loss: 2.8564 (2.8286)  weight_decay: 0.0500 (0.0500)  time: 1.0082  data: 0.0004  max mem: 78493
Epoch: [34]  [110/312]  eta: 0:03:56  lr: 0.003974  min_lr: 0.003974  loss: 3.0320 (2.8188)  weight_decay: 0.0500 (0.0500)  time: 1.0077  data: 0.0004  max mem: 78493
Epoch: [34]  [120/312]  eta: 0:03:42  lr: 0.003974  min_lr: 0.003974  loss: 2.8917 (2.8123)  weight_decay: 0.0500 (0.0500)  time: 1.0074  data: 0.0004  max mem: 78493
Epoch: [34]  [130/312]  eta: 0:03:28  lr: 0.003974  min_lr: 0.003974  loss: 2.9241 (2.8244)  weight_decay: 0.0500 (0.0500)  time: 1.0071  data: 0.0004  max mem: 78493
Epoch: [34]  [140/312]  eta: 0:03:15  lr: 0.003974  min_lr: 0.003974  loss: 2.9863 (2.8283)  weight_decay: 0.0500 (0.0500)  time: 1.0065  data: 0.0004  max mem: 78493
Epoch: [34]  [150/312]  eta: 0:03:02  lr: 0.003974  min_lr: 0.003974  loss: 2.8997 (2.8329)  weight_decay: 0.0500 (0.0500)  time: 1.0058  data: 0.0004  max mem: 78493
Epoch: [34]  [160/312]  eta: 0:02:50  lr: 0.003974  min_lr: 0.003974  loss: 2.8533 (2.8290)  weight_decay: 0.0500 (0.0500)  time: 1.0059  data: 0.0005  max mem: 78493
Epoch: [34]  [170/312]  eta: 0:02:38  lr: 0.003973  min_lr: 0.003973  loss: 2.7952 (2.8213)  weight_decay: 0.0500 (0.0500)  time: 1.0050  data: 0.0005  max mem: 78493
Epoch: [34]  [180/312]  eta: 0:02:26  lr: 0.003973  min_lr: 0.003973  loss: 2.8812 (2.8253)  weight_decay: 0.0500 (0.0500)  time: 1.0067  data: 0.0004  max mem: 78493
Epoch: [34]  [190/312]  eta: 0:02:14  lr: 0.003973  min_lr: 0.003973  loss: 2.8812 (2.8123)  weight_decay: 0.0500 (0.0500)  time: 1.0083  data: 0.0004  max mem: 78493
Epoch: [34]  [200/312]  eta: 0:02:02  lr: 0.003973  min_lr: 0.003973  loss: 2.8548 (2.8124)  weight_decay: 0.0500 (0.0500)  time: 1.0062  data: 0.0004  max mem: 78493
Epoch: [34]  [210/312]  eta: 0:01:51  lr: 0.003973  min_lr: 0.003973  loss: 3.0104 (2.8143)  weight_decay: 0.0500 (0.0500)  time: 1.0051  data: 0.0005  max mem: 78493
Epoch: [34]  [220/312]  eta: 0:01:40  lr: 0.003973  min_lr: 0.003973  loss: 2.6872 (2.8036)  weight_decay: 0.0500 (0.0500)  time: 1.0052  data: 0.0004  max mem: 78493
Epoch: [34]  [230/312]  eta: 0:01:29  lr: 0.003973  min_lr: 0.003973  loss: 2.8995 (2.8086)  weight_decay: 0.0500 (0.0500)  time: 1.0061  data: 0.0004  max mem: 78493
Epoch: [34]  [240/312]  eta: 0:01:17  lr: 0.003973  min_lr: 0.003973  loss: 2.9489 (2.8098)  weight_decay: 0.0500 (0.0500)  time: 1.0056  data: 0.0004  max mem: 78493
Epoch: [34]  [250/312]  eta: 0:01:06  lr: 0.003972  min_lr: 0.003972  loss: 2.9317 (2.8113)  weight_decay: 0.0500 (0.0500)  time: 1.0053  data: 0.0004  max mem: 78493
Epoch: [34]  [260/312]  eta: 0:00:55  lr: 0.003972  min_lr: 0.003972  loss: 2.9323 (2.8156)  weight_decay: 0.0500 (0.0500)  time: 1.0071  data: 0.0004  max mem: 78493
Epoch: [34]  [270/312]  eta: 0:00:45  lr: 0.003972  min_lr: 0.003972  loss: 2.9323 (2.8164)  weight_decay: 0.0500 (0.0500)  time: 1.0073  data: 0.0004  max mem: 78493
Epoch: [34]  [280/312]  eta: 0:00:34  lr: 0.003972  min_lr: 0.003972  loss: 2.9295 (2.8152)  weight_decay: 0.0500 (0.0500)  time: 1.0058  data: 0.0011  max mem: 78493
Epoch: [34]  [290/312]  eta: 0:00:23  lr: 0.003972  min_lr: 0.003972  loss: 2.8294 (2.8102)  weight_decay: 0.0500 (0.0500)  time: 1.0041  data: 0.0009  max mem: 78493
Epoch: [34]  [300/312]  eta: 0:00:12  lr: 0.003972  min_lr: 0.003972  loss: 2.8438 (2.8129)  weight_decay: 0.0500 (0.0500)  time: 1.0024  data: 0.0001  max mem: 78493
Epoch: [34]  [310/312]  eta: 0:00:02  lr: 0.003972  min_lr: 0.003972  loss: 2.9375 (2.8084)  weight_decay: 0.0500 (0.0500)  time: 1.0014  data: 0.0001  max mem: 78493
Epoch: [34]  [311/312]  eta: 0:00:01  lr: 0.003972  min_lr: 0.003972  loss: 2.9375 (2.8066)  weight_decay: 0.0500 (0.0500)  time: 1.0015  data: 0.0001  max mem: 78493
Epoch: [34] Total time: 0:05:33 (1.0704 s / it)
Averaged stats: lr: 0.003972  min_lr: 0.003972  loss: 2.9375 (2.8218)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:16  loss: 1.0023 (1.0023)  acc1: 76.5625 (76.5625)  acc5: 92.0573 (92.0573)  time: 8.5063  data: 8.2312  max mem: 78493
Test:  [8/9]  eta: 0:00:01  loss: 1.4439 (1.3258)  acc1: 66.7969 (68.2080)  acc5: 88.1510 (88.1920)  time: 1.1435  data: 0.9147  max mem: 78493
Test: Total time: 0:00:10 (1.1601 s / it)
* Acc@1 68.514 Acc@5 88.476 loss 1.314
Accuracy of the model on the 50000 test images: 68.5%
Max accuracy: 68.69%
Epoch: [35]  [  0/312]  eta: 1:26:49  lr: 0.003972  min_lr: 0.003972  loss: 2.4254 (2.4254)  weight_decay: 0.0500 (0.0500)  time: 16.6980  data: 12.9049  max mem: 78493
Epoch: [35]  [ 10/312]  eta: 0:13:19  lr: 0.003972  min_lr: 0.003972  loss: 2.7024 (2.6962)  weight_decay: 0.0500 (0.0500)  time: 2.6460  data: 1.3646  max mem: 78493
Epoch: [35]  [ 20/312]  eta: 0:09:05  lr: 0.003972  min_lr: 0.003972  loss: 2.7024 (2.7003)  weight_decay: 0.0500 (0.0500)  time: 1.1281  data: 0.1055  max mem: 78493
Epoch: [35]  [ 30/312]  eta: 0:07:28  lr: 0.003971  min_lr: 0.003971  loss: 2.8318 (2.7947)  weight_decay: 0.0500 (0.0500)  time: 1.0115  data: 0.0004  max mem: 78493
Epoch: [35]  [ 40/312]  eta: 0:06:34  lr: 0.003971  min_lr: 0.003971  loss: 2.9303 (2.7834)  weight_decay: 0.0500 (0.0500)  time: 1.0078  data: 0.0013  max mem: 78493
Epoch: [35]  [ 50/312]  eta: 0:05:57  lr: 0.003971  min_lr: 0.003971  loss: 2.8783 (2.7980)  weight_decay: 0.0500 (0.0500)  time: 1.0103  data: 0.0013  max mem: 78493
Epoch: [35]  [ 60/312]  eta: 0:05:28  lr: 0.003971  min_lr: 0.003971  loss: 2.9923 (2.8163)  weight_decay: 0.0500 (0.0500)  time: 1.0098  data: 0.0004  max mem: 78493
Epoch: [35]  [ 70/312]  eta: 0:05:05  lr: 0.003971  min_lr: 0.003971  loss: 2.8375 (2.7889)  weight_decay: 0.0500 (0.0500)  time: 1.0070  data: 0.0005  max mem: 78493
Epoch: [35]  [ 80/312]  eta: 0:04:45  lr: 0.003971  min_lr: 0.003971  loss: 2.8748 (2.8008)  weight_decay: 0.0500 (0.0500)  time: 1.0077  data: 0.0005  max mem: 78493
Epoch: [35]  [ 90/312]  eta: 0:04:27  lr: 0.003971  min_lr: 0.003971  loss: 2.9072 (2.8215)  weight_decay: 0.0500 (0.0500)  time: 1.0075  data: 0.0004  max mem: 78493
Epoch: [35]  [100/312]  eta: 0:04:11  lr: 0.003971  min_lr: 0.003971  loss: 2.9695 (2.8395)  weight_decay: 0.0500 (0.0500)  time: 1.0074  data: 0.0004  max mem: 78493
Epoch: [35]  [110/312]  eta: 0:03:56  lr: 0.003970  min_lr: 0.003970  loss: 2.9207 (2.8395)  weight_decay: 0.0500 (0.0500)  time: 1.0068  data: 0.0004  max mem: 78493
Epoch: [35]  [120/312]  eta: 0:03:42  lr: 0.003970  min_lr: 0.003970  loss: 2.7652 (2.8328)  weight_decay: 0.0500 (0.0500)  time: 1.0057  data: 0.0004  max mem: 78493
Epoch: [35]  [130/312]  eta: 0:03:28  lr: 0.003970  min_lr: 0.003970  loss: 2.8348 (2.8376)  weight_decay: 0.0500 (0.0500)  time: 1.0062  data: 0.0004  max mem: 78493
Epoch: [35]  [140/312]  eta: 0:03:15  lr: 0.003970  min_lr: 0.003970  loss: 2.8845 (2.8307)  weight_decay: 0.0500 (0.0500)  time: 1.0055  data: 0.0004  max mem: 78493
Epoch: [35]  [150/312]  eta: 0:03:02  lr: 0.003970  min_lr: 0.003970  loss: 2.9709 (2.8385)  weight_decay: 0.0500 (0.0500)  time: 1.0047  data: 0.0005  max mem: 78493
Epoch: [35]  [160/312]  eta: 0:02:50  lr: 0.003970  min_lr: 0.003970  loss: 2.9435 (2.8268)  weight_decay: 0.0500 (0.0500)  time: 1.0047  data: 0.0004  max mem: 78493
Epoch: [35]  [170/312]  eta: 0:02:38  lr: 0.003970  min_lr: 0.003970  loss: 2.5894 (2.8201)  weight_decay: 0.0500 (0.0500)  time: 1.0065  data: 0.0005  max mem: 78493
Epoch: [35]  [180/312]  eta: 0:02:26  lr: 0.003970  min_lr: 0.003970  loss: 2.8984 (2.8229)  weight_decay: 0.0500 (0.0500)  time: 1.0090  data: 0.0004  max mem: 78493
Epoch: [35]  [190/312]  eta: 0:02:14  lr: 0.003969  min_lr: 0.003969  loss: 2.8196 (2.8147)  weight_decay: 0.0500 (0.0500)  time: 1.0087  data: 0.0004  max mem: 78493
Epoch: [35]  [200/312]  eta: 0:02:02  lr: 0.003969  min_lr: 0.003969  loss: 2.7937 (2.8129)  weight_decay: 0.0500 (0.0500)  time: 1.0095  data: 0.0005  max mem: 78493
Epoch: [35]  [210/312]  eta: 0:01:51  lr: 0.003969  min_lr: 0.003969  loss: 2.9197 (2.8197)  weight_decay: 0.0500 (0.0500)  time: 1.0102  data: 0.0004  max mem: 78493
Epoch: [35]  [220/312]  eta: 0:01:40  lr: 0.003969  min_lr: 0.003969  loss: 2.8825 (2.8156)  weight_decay: 0.0500 (0.0500)  time: 1.0087  data: 0.0004  max mem: 78493
Epoch: [35]  [230/312]  eta: 0:01:29  lr: 0.003969  min_lr: 0.003969  loss: 2.9401 (2.8258)  weight_decay: 0.0500 (0.0500)  time: 1.0070  data: 0.0004  max mem: 78493
Epoch: [35]  [240/312]  eta: 0:01:17  lr: 0.003969  min_lr: 0.003969  loss: 2.8791 (2.8217)  weight_decay: 0.0500 (0.0500)  time: 1.0047  data: 0.0004  max mem: 78493
Epoch: [35]  [250/312]  eta: 0:01:06  lr: 0.003969  min_lr: 0.003969  loss: 2.7411 (2.8207)  weight_decay: 0.0500 (0.0500)  time: 1.0034  data: 0.0004  max mem: 78493
Epoch: [35]  [260/312]  eta: 0:00:55  lr: 0.003969  min_lr: 0.003969  loss: 2.9192 (2.8180)  weight_decay: 0.0500 (0.0500)  time: 1.0049  data: 0.0004  max mem: 78493
Epoch: [35]  [270/312]  eta: 0:00:45  lr: 0.003968  min_lr: 0.003968  loss: 2.7549 (2.8107)  weight_decay: 0.0500 (0.0500)  time: 1.0051  data: 0.0004  max mem: 78493
Epoch: [35]  [280/312]  eta: 0:00:34  lr: 0.003968  min_lr: 0.003968  loss: 2.9576 (2.8128)  weight_decay: 0.0500 (0.0500)  time: 1.0063  data: 0.0010  max mem: 78493
Epoch: [35]  [290/312]  eta: 0:00:23  lr: 0.003968  min_lr: 0.003968  loss: 2.9651 (2.8092)  weight_decay: 0.0500 (0.0500)  time: 1.0051  data: 0.0009  max mem: 78493
Epoch: [35]  [300/312]  eta: 0:00:12  lr: 0.003968  min_lr: 0.003968  loss: 2.9296 (2.8094)  weight_decay: 0.0500 (0.0500)  time: 1.0016  data: 0.0001  max mem: 78493
Epoch: [35]  [310/312]  eta: 0:00:02  lr: 0.003968  min_lr: 0.003968  loss: 2.9353 (2.8145)  weight_decay: 0.0500 (0.0500)  time: 1.0019  data: 0.0001  max mem: 78493
Epoch: [35]  [311/312]  eta: 0:00:01  lr: 0.003968  min_lr: 0.003968  loss: 2.9353 (2.8150)  weight_decay: 0.0500 (0.0500)  time: 1.0018  data: 0.0001  max mem: 78493
Epoch: [35] Total time: 0:05:33 (1.0700 s / it)
Averaged stats: lr: 0.003968  min_lr: 0.003968  loss: 2.9353 (2.7804)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:09  loss: 1.0482 (1.0482)  acc1: 73.5677 (73.5677)  acc5: 91.9271 (91.9271)  time: 7.7682  data: 7.4968  max mem: 78493
Test:  [8/9]  eta: 0:00:01  loss: 1.4860 (1.3591)  acc1: 64.8438 (66.9120)  acc5: 86.7188 (87.6480)  time: 1.0705  data: 0.8421  max mem: 78493
Test: Total time: 0:00:09 (1.0813 s / it)
* Acc@1 67.392 Acc@5 87.710 loss 1.356
Accuracy of the model on the 50000 test images: 67.4%
Max accuracy: 68.69%
Epoch: [36]  [  0/312]  eta: 1:25:23  lr: 0.003968  min_lr: 0.003968  loss: 3.0857 (3.0857)  weight_decay: 0.0500 (0.0500)  time: 16.4203  data: 14.4625  max mem: 78493
Epoch: [36]  [ 10/312]  eta: 0:13:11  lr: 0.003968  min_lr: 0.003968  loss: 2.6159 (2.6688)  weight_decay: 0.0500 (0.0500)  time: 2.6207  data: 1.3156  max mem: 78493
Epoch: [36]  [ 20/312]  eta: 0:09:02  lr: 0.003968  min_lr: 0.003968  loss: 2.6159 (2.6858)  weight_decay: 0.0500 (0.0500)  time: 1.1289  data: 0.0007  max mem: 78493
Epoch: [36]  [ 30/312]  eta: 0:07:26  lr: 0.003967  min_lr: 0.003967  loss: 2.8392 (2.7021)  weight_decay: 0.0500 (0.0500)  time: 1.0122  data: 0.0005  max mem: 78493
Epoch: [36]  [ 40/312]  eta: 0:06:32  lr: 0.003967  min_lr: 0.003967  loss: 2.8392 (2.7248)  weight_decay: 0.0500 (0.0500)  time: 1.0079  data: 0.0004  max mem: 78493
Epoch: [36]  [ 50/312]  eta: 0:05:55  lr: 0.003967  min_lr: 0.003967  loss: 2.7128 (2.6942)  weight_decay: 0.0500 (0.0500)  time: 1.0092  data: 0.0004  max mem: 78493
Epoch: [36]  [ 60/312]  eta: 0:05:27  lr: 0.003967  min_lr: 0.003967  loss: 2.8942 (2.7306)  weight_decay: 0.0500 (0.0500)  time: 1.0085  data: 0.0005  max mem: 78493
Epoch: [36]  [ 70/312]  eta: 0:05:04  lr: 0.003967  min_lr: 0.003967  loss: 3.0063 (2.7566)  weight_decay: 0.0500 (0.0500)  time: 1.0067  data: 0.0005  max mem: 78493
Epoch: [36]  [ 80/312]  eta: 0:04:44  lr: 0.003967  min_lr: 0.003967  loss: 2.9677 (2.7681)  weight_decay: 0.0500 (0.0500)  time: 1.0069  data: 0.0005  max mem: 78493
Epoch: [36]  [ 90/312]  eta: 0:04:27  lr: 0.003967  min_lr: 0.003967  loss: 2.8757 (2.7715)  weight_decay: 0.0500 (0.0500)  time: 1.0072  data: 0.0005  max mem: 78493
Epoch: [36]  [100/312]  eta: 0:04:11  lr: 0.003967  min_lr: 0.003967  loss: 2.7784 (2.7658)  weight_decay: 0.0500 (0.0500)  time: 1.0067  data: 0.0005  max mem: 78493
Epoch: [36]  [110/312]  eta: 0:03:56  lr: 0.003966  min_lr: 0.003966  loss: 2.8239 (2.7804)  weight_decay: 0.0500 (0.0500)  time: 1.0082  data: 0.0005  max mem: 78493
Epoch: [36]  [120/312]  eta: 0:03:41  lr: 0.003966  min_lr: 0.003966  loss: 2.9522 (2.7904)  weight_decay: 0.0500 (0.0500)  time: 1.0096  data: 0.0012  max mem: 78493
Epoch: [36]  [130/312]  eta: 0:03:28  lr: 0.003966  min_lr: 0.003966  loss: 2.8801 (2.7902)  weight_decay: 0.0500 (0.0500)  time: 1.0080  data: 0.0011  max mem: 78493
Epoch: [36]  [140/312]  eta: 0:03:15  lr: 0.003966  min_lr: 0.003966  loss: 3.0143 (2.7973)  weight_decay: 0.0500 (0.0500)  time: 1.0066  data: 0.0004  max mem: 78493
Epoch: [36]  [150/312]  eta: 0:03:02  lr: 0.003966  min_lr: 0.003966  loss: 3.0168 (2.7966)  weight_decay: 0.0500 (0.0500)  time: 1.0071  data: 0.0004  max mem: 78493
Epoch: [36]  [160/312]  eta: 0:02:50  lr: 0.003966  min_lr: 0.003966  loss: 2.8087 (2.7932)  weight_decay: 0.0500 (0.0500)  time: 1.0083  data: 0.0005  max mem: 78493
Epoch: [36]  [170/312]  eta: 0:02:37  lr: 0.003966  min_lr: 0.003966  loss: 2.7897 (2.7906)  weight_decay: 0.0500 (0.0500)  time: 1.0095  data: 0.0005  max mem: 78493
Epoch: [36]  [180/312]  eta: 0:02:26  lr: 0.003966  min_lr: 0.003966  loss: 2.7735 (2.7890)  weight_decay: 0.0500 (0.0500)  time: 1.0082  data: 0.0005  max mem: 78493
Epoch: [36]  [190/312]  eta: 0:02:14  lr: 0.003965  min_lr: 0.003965  loss: 3.0267 (2.8022)  weight_decay: 0.0500 (0.0500)  time: 1.0050  data: 0.0004  max mem: 78493
Epoch: [36]  [200/312]  eta: 0:02:02  lr: 0.003965  min_lr: 0.003965  loss: 2.9495 (2.8033)  weight_decay: 0.0500 (0.0500)  time: 1.0039  data: 0.0005  max mem: 78493
Epoch: [36]  [210/312]  eta: 0:01:51  lr: 0.003965  min_lr: 0.003965  loss: 2.6897 (2.7991)  weight_decay: 0.0500 (0.0500)  time: 1.0044  data: 0.0005  max mem: 78493
Epoch: [36]  [220/312]  eta: 0:01:40  lr: 0.003965  min_lr: 0.003965  loss: 2.8218 (2.8027)  weight_decay: 0.0500 (0.0500)  time: 1.0051  data: 0.0005  max mem: 78493
Epoch: [36]  [230/312]  eta: 0:01:28  lr: 0.003965  min_lr: 0.003965  loss: 2.8763 (2.8065)  weight_decay: 0.0500 (0.0500)  time: 1.0067  data: 0.0004  max mem: 78493
Epoch: [36]  [240/312]  eta: 0:01:17  lr: 0.003965  min_lr: 0.003965  loss: 2.8763 (2.8061)  weight_decay: 0.0500 (0.0500)  time: 1.0064  data: 0.0005  max mem: 78493
Epoch: [36]  [250/312]  eta: 0:01:06  lr: 0.003965  min_lr: 0.003965  loss: 2.8901 (2.8075)  weight_decay: 0.0500 (0.0500)  time: 1.0055  data: 0.0005  max mem: 78493
Epoch: [36]  [260/312]  eta: 0:00:55  lr: 0.003964  min_lr: 0.003964  loss: 2.9959 (2.8143)  weight_decay: 0.0500 (0.0500)  time: 1.0054  data: 0.0004  max mem: 78493
Epoch: [36]  [270/312]  eta: 0:00:45  lr: 0.003964  min_lr: 0.003964  loss: 3.0807 (2.8254)  weight_decay: 0.0500 (0.0500)  time: 1.0047  data: 0.0005  max mem: 78493
Epoch: [36]  [280/312]  eta: 0:00:34  lr: 0.003964  min_lr: 0.003964  loss: 3.0559 (2.8301)  weight_decay: 0.0500 (0.0500)  time: 1.0051  data: 0.0010  max mem: 78493
Epoch: [36]  [290/312]  eta: 0:00:23  lr: 0.003964  min_lr: 0.003964  loss: 2.8100 (2.8230)  weight_decay: 0.0500 (0.0500)  time: 1.0038  data: 0.0009  max mem: 78493
Epoch: [36]  [300/312]  eta: 0:00:12  lr: 0.003964  min_lr: 0.003964  loss: 2.6758 (2.8165)  weight_decay: 0.0500 (0.0500)  time: 1.0019  data: 0.0001  max mem: 78493
Epoch: [36]  [310/312]  eta: 0:00:02  lr: 0.003964  min_lr: 0.003964  loss: 2.7927 (2.8176)  weight_decay: 0.0500 (0.0500)  time: 1.0018  data: 0.0001  max mem: 78493
Epoch: [36]  [311/312]  eta: 0:00:01  lr: 0.003964  min_lr: 0.003964  loss: 2.6758 (2.8162)  weight_decay: 0.0500 (0.0500)  time: 1.0019  data: 0.0001  max mem: 78493
Epoch: [36] Total time: 0:05:33 (1.0691 s / it)
Averaged stats: lr: 0.003964  min_lr: 0.003964  loss: 2.6758 (2.8041)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:16  loss: 0.9284 (0.9284)  acc1: 76.1719 (76.1719)  acc5: 92.8385 (92.8385)  time: 8.5288  data: 8.2538  max mem: 78493
Test:  [8/9]  eta: 0:00:01  loss: 1.3175 (1.2560)  acc1: 69.6615 (68.8800)  acc5: 88.2812 (88.6400)  time: 1.1459  data: 0.9172  max mem: 78493
Test: Total time: 0:00:10 (1.1737 s / it)
* Acc@1 69.024 Acc@5 88.932 loss 1.260
Accuracy of the model on the 50000 test images: 69.0%
Max accuracy: 69.02%
Epoch: [37]  [  0/312]  eta: 1:19:33  lr: 0.003964  min_lr: 0.003964  loss: 3.4551 (3.4551)  weight_decay: 0.0500 (0.0500)  time: 15.3007  data: 12.8574  max mem: 78493
Epoch: [37]  [ 10/312]  eta: 0:12:55  lr: 0.003964  min_lr: 0.003964  loss: 3.0068 (2.9860)  weight_decay: 0.0500 (0.0500)  time: 2.5692  data: 1.3386  max mem: 78493
Epoch: [37]  [ 20/312]  eta: 0:08:53  lr: 0.003963  min_lr: 0.003963  loss: 2.7801 (2.8201)  weight_decay: 0.0500 (0.0500)  time: 1.1535  data: 0.0936  max mem: 78493
Epoch: [37]  [ 30/312]  eta: 0:07:20  lr: 0.003963  min_lr: 0.003963  loss: 2.6197 (2.7952)  weight_decay: 0.0500 (0.0500)  time: 1.0091  data: 0.0005  max mem: 78493
Epoch: [37]  [ 40/312]  eta: 0:06:28  lr: 0.003963  min_lr: 0.003963  loss: 2.6197 (2.7261)  weight_decay: 0.0500 (0.0500)  time: 1.0076  data: 0.0004  max mem: 78493
Epoch: [37]  [ 50/312]  eta: 0:05:52  lr: 0.003963  min_lr: 0.003963  loss: 2.6494 (2.7084)  weight_decay: 0.0500 (0.0500)  time: 1.0075  data: 0.0004  max mem: 78493
Epoch: [37]  [ 60/312]  eta: 0:05:24  lr: 0.003963  min_lr: 0.003963  loss: 2.7376 (2.7342)  weight_decay: 0.0500 (0.0500)  time: 1.0067  data: 0.0004  max mem: 78493
Epoch: [37]  [ 70/312]  eta: 0:05:02  lr: 0.003963  min_lr: 0.003963  loss: 2.7916 (2.7356)  weight_decay: 0.0500 (0.0500)  time: 1.0068  data: 0.0004  max mem: 78493
Epoch: [37]  [ 80/312]  eta: 0:04:42  lr: 0.003963  min_lr: 0.003963  loss: 2.6337 (2.7181)  weight_decay: 0.0500 (0.0500)  time: 1.0059  data: 0.0005  max mem: 78493
Epoch: [37]  [ 90/312]  eta: 0:04:25  lr: 0.003963  min_lr: 0.003963  loss: 2.6430 (2.7225)  weight_decay: 0.0500 (0.0500)  time: 1.0059  data: 0.0004  max mem: 78493
Epoch: [37]  [100/312]  eta: 0:04:09  lr: 0.003962  min_lr: 0.003962  loss: 2.7847 (2.7328)  weight_decay: 0.0500 (0.0500)  time: 1.0078  data: 0.0004  max mem: 78493
Epoch: [37]  [110/312]  eta: 0:03:54  lr: 0.003962  min_lr: 0.003962  loss: 2.8721 (2.7312)  weight_decay: 0.0500 (0.0500)  time: 1.0079  data: 0.0004  max mem: 78493
Epoch: [37]  [120/312]  eta: 0:03:40  lr: 0.003962  min_lr: 0.003962  loss: 3.0326 (2.7578)  weight_decay: 0.0500 (0.0500)  time: 1.0081  data: 0.0004  max mem: 78493
Epoch: [37]  [130/312]  eta: 0:03:27  lr: 0.003962  min_lr: 0.003962  loss: 2.7142 (2.7448)  weight_decay: 0.0500 (0.0500)  time: 1.0073  data: 0.0004  max mem: 78493
Epoch: [37]  [140/312]  eta: 0:03:14  lr: 0.003962  min_lr: 0.003962  loss: 2.5227 (2.7411)  weight_decay: 0.0500 (0.0500)  time: 1.0064  data: 0.0004  max mem: 78493
Epoch: [37]  [150/312]  eta: 0:03:01  lr: 0.003962  min_lr: 0.003962  loss: 2.7261 (2.7480)  weight_decay: 0.0500 (0.0500)  time: 1.0071  data: 0.0004  max mem: 78493
Epoch: [37]  [160/312]  eta: 0:02:49  lr: 0.003962  min_lr: 0.003962  loss: 2.8177 (2.7510)  weight_decay: 0.0500 (0.0500)  time: 1.0073  data: 0.0004  max mem: 78493
Epoch: [37]  [170/312]  eta: 0:02:37  lr: 0.003961  min_lr: 0.003961  loss: 2.8983 (2.7544)  weight_decay: 0.0500 (0.0500)  time: 1.0086  data: 0.0004  max mem: 78493
Epoch: [37]  [180/312]  eta: 0:02:25  lr: 0.003961  min_lr: 0.003961  loss: 2.5532 (2.7377)  weight_decay: 0.0500 (0.0500)  time: 1.0089  data: 0.0005  max mem: 78493
Epoch: [37]  [190/312]  eta: 0:02:13  lr: 0.003961  min_lr: 0.003961  loss: 2.5532 (2.7348)  weight_decay: 0.0500 (0.0500)  time: 1.0075  data: 0.0005  max mem: 78493
Epoch: [37]  [200/312]  eta: 0:02:02  lr: 0.003961  min_lr: 0.003961  loss: 2.7214 (2.7359)  weight_decay: 0.0500 (0.0500)  time: 1.0056  data: 0.0004  max mem: 78493
Epoch: [37]  [210/312]  eta: 0:01:51  lr: 0.003961  min_lr: 0.003961  loss: 2.6623 (2.7279)  weight_decay: 0.0500 (0.0500)  time: 1.0047  data: 0.0004  max mem: 78493
Epoch: [37]  [220/312]  eta: 0:01:39  lr: 0.003961  min_lr: 0.003961  loss: 2.7668 (2.7344)  weight_decay: 0.0500 (0.0500)  time: 1.0043  data: 0.0004  max mem: 78493
Epoch: [37]  [230/312]  eta: 0:01:28  lr: 0.003961  min_lr: 0.003961  loss: 2.8406 (2.7346)  weight_decay: 0.0500 (0.0500)  time: 1.0035  data: 0.0004  max mem: 78493
Epoch: [37]  [240/312]  eta: 0:01:17  lr: 0.003960  min_lr: 0.003960  loss: 2.8406 (2.7411)  weight_decay: 0.0500 (0.0500)  time: 1.0036  data: 0.0004  max mem: 78493
Epoch: [37]  [250/312]  eta: 0:01:06  lr: 0.003960  min_lr: 0.003960  loss: 2.7516 (2.7369)  weight_decay: 0.0500 (0.0500)  time: 1.0052  data: 0.0004  max mem: 78493
Epoch: [37]  [260/312]  eta: 0:00:55  lr: 0.003960  min_lr: 0.003960  loss: 2.7037 (2.7406)  weight_decay: 0.0500 (0.0500)  time: 1.0052  data: 0.0005  max mem: 78493
Epoch: [37]  [270/312]  eta: 0:00:44  lr: 0.003960  min_lr: 0.003960  loss: 2.9775 (2.7480)  weight_decay: 0.0500 (0.0500)  time: 1.0054  data: 0.0005  max mem: 78493
Epoch: [37]  [280/312]  eta: 0:00:34  lr: 0.003960  min_lr: 0.003960  loss: 3.0413 (2.7495)  weight_decay: 0.0500 (0.0500)  time: 1.0064  data: 0.0010  max mem: 78493
Epoch: [37]  [290/312]  eta: 0:00:23  lr: 0.003960  min_lr: 0.003960  loss: 2.7603 (2.7476)  weight_decay: 0.0500 (0.0500)  time: 1.0036  data: 0.0009  max mem: 78493
Epoch: [37]  [300/312]  eta: 0:00:12  lr: 0.003960  min_lr: 0.003960  loss: 2.8236 (2.7498)  weight_decay: 0.0500 (0.0500)  time: 1.0012  data: 0.0001  max mem: 78493
Epoch: [37]  [310/312]  eta: 0:00:02  lr: 0.003959  min_lr: 0.003959  loss: 2.9535 (2.7570)  weight_decay: 0.0500 (0.0500)  time: 1.0014  data: 0.0001  max mem: 78493
Epoch: [37]  [311/312]  eta: 0:00:01  lr: 0.003959  min_lr: 0.003959  loss: 2.9519 (2.7547)  weight_decay: 0.0500 (0.0500)  time: 1.0014  data: 0.0001  max mem: 78493
Epoch: [37] Total time: 0:05:32 (1.0668 s / it)
Averaged stats: lr: 0.003959  min_lr: 0.003959  loss: 2.9519 (2.7763)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:15  loss: 1.0632 (1.0632)  acc1: 76.0417 (76.0417)  acc5: 92.3177 (92.3177)  time: 8.3586  data: 8.0770  max mem: 78493
Test:  [8/9]  eta: 0:00:01  loss: 1.4263 (1.3353)  acc1: 68.0990 (68.2080)  acc5: 88.1510 (88.2400)  time: 1.1269  data: 0.8975  max mem: 78493
Test: Total time: 0:00:10 (1.1433 s / it)
* Acc@1 68.514 Acc@5 88.402 loss 1.332
Accuracy of the model on the 50000 test images: 68.5%
Max accuracy: 69.02%
Epoch: [38]  [  0/312]  eta: 1:25:48  lr: 0.003959  min_lr: 0.003959  loss: 2.1129 (2.1129)  weight_decay: 0.0500 (0.0500)  time: 16.5006  data: 12.3902  max mem: 78493
Epoch: [38]  [ 10/312]  eta: 0:13:01  lr: 0.003959  min_lr: 0.003959  loss: 2.6689 (2.5705)  weight_decay: 0.0500 (0.0500)  time: 2.5874  data: 1.1684  max mem: 78493
Epoch: [38]  [ 20/312]  eta: 0:08:57  lr: 0.003959  min_lr: 0.003959  loss: 2.7209 (2.6872)  weight_decay: 0.0500 (0.0500)  time: 1.1082  data: 0.0233  max mem: 78493
Epoch: [38]  [ 30/312]  eta: 0:07:23  lr: 0.003959  min_lr: 0.003959  loss: 2.8915 (2.6806)  weight_decay: 0.0500 (0.0500)  time: 1.0157  data: 0.0005  max mem: 78493
Epoch: [38]  [ 40/312]  eta: 0:06:30  lr: 0.003959  min_lr: 0.003959  loss: 2.9387 (2.7132)  weight_decay: 0.0500 (0.0500)  time: 1.0091  data: 0.0005  max mem: 78493
Epoch: [38]  [ 50/312]  eta: 0:05:54  lr: 0.003959  min_lr: 0.003959  loss: 2.8778 (2.7419)  weight_decay: 0.0500 (0.0500)  time: 1.0069  data: 0.0005  max mem: 78493
Epoch: [38]  [ 60/312]  eta: 0:05:26  lr: 0.003958  min_lr: 0.003958  loss: 2.8574 (2.7396)  weight_decay: 0.0500 (0.0500)  time: 1.0065  data: 0.0004  max mem: 78493
Epoch: [38]  [ 70/312]  eta: 0:05:03  lr: 0.003958  min_lr: 0.003958  loss: 2.8643 (2.7575)  weight_decay: 0.0500 (0.0500)  time: 1.0079  data: 0.0004  max mem: 78493
Epoch: [38]  [ 80/312]  eta: 0:04:43  lr: 0.003958  min_lr: 0.003958  loss: 2.6449 (2.7385)  weight_decay: 0.0500 (0.0500)  time: 1.0081  data: 0.0005  max mem: 78493
Epoch: [38]  [ 90/312]  eta: 0:04:26  lr: 0.003958  min_lr: 0.003958  loss: 2.7195 (2.7533)  weight_decay: 0.0500 (0.0500)  time: 1.0053  data: 0.0005  max mem: 78493
Epoch: [38]  [100/312]  eta: 0:04:10  lr: 0.003958  min_lr: 0.003958  loss: 2.9079 (2.7490)  weight_decay: 0.0500 (0.0500)  time: 1.0045  data: 0.0005  max mem: 78493
Epoch: [38]  [110/312]  eta: 0:03:55  lr: 0.003958  min_lr: 0.003958  loss: 2.9079 (2.7561)  weight_decay: 0.0500 (0.0500)  time: 1.0066  data: 0.0005  max mem: 78493
Epoch: [38]  [120/312]  eta: 0:03:41  lr: 0.003958  min_lr: 0.003958  loss: 2.8753 (2.7597)  weight_decay: 0.0500 (0.0500)  time: 1.0101  data: 0.0004  max mem: 78493
Epoch: [38]  [130/312]  eta: 0:03:27  lr: 0.003957  min_lr: 0.003957  loss: 2.6133 (2.7430)  weight_decay: 0.0500 (0.0500)  time: 1.0096  data: 0.0005  max mem: 78493
Epoch: [38]  [140/312]  eta: 0:03:14  lr: 0.003957  min_lr: 0.003957  loss: 2.6113 (2.7411)  weight_decay: 0.0500 (0.0500)  time: 1.0087  data: 0.0005  max mem: 78493
Epoch: [38]  [150/312]  eta: 0:03:02  lr: 0.003957  min_lr: 0.003957  loss: 3.0134 (2.7514)  weight_decay: 0.0500 (0.0500)  time: 1.0093  data: 0.0004  max mem: 78493
Epoch: [38]  [160/312]  eta: 0:02:49  lr: 0.003957  min_lr: 0.003957  loss: 2.9674 (2.7499)  weight_decay: 0.0500 (0.0500)  time: 1.0066  data: 0.0005  max mem: 78493
Epoch: [38]  [170/312]  eta: 0:02:37  lr: 0.003957  min_lr: 0.003957  loss: 2.5915 (2.7468)  weight_decay: 0.0500 (0.0500)  time: 1.0065  data: 0.0005  max mem: 78493
Epoch: [38]  [180/312]  eta: 0:02:25  lr: 0.003957  min_lr: 0.003957  loss: 2.8980 (2.7508)  weight_decay: 0.0500 (0.0500)  time: 1.0065  data: 0.0004  max mem: 78493
Epoch: [38]  [190/312]  eta: 0:02:14  lr: 0.003957  min_lr: 0.003957  loss: 2.9555 (2.7554)  weight_decay: 0.0500 (0.0500)  time: 1.0065  data: 0.0004  max mem: 78493
Epoch: [38]  [200/312]  eta: 0:02:02  lr: 0.003956  min_lr: 0.003956  loss: 2.9001 (2.7579)  weight_decay: 0.0500 (0.0500)  time: 1.0079  data: 0.0004  max mem: 78493
Epoch: [38]  [210/312]  eta: 0:01:51  lr: 0.003956  min_lr: 0.003956  loss: 2.8191 (2.7577)  weight_decay: 0.0500 (0.0500)  time: 1.0061  data: 0.0004  max mem: 78493
Epoch: [38]  [220/312]  eta: 0:01:39  lr: 0.003956  min_lr: 0.003956  loss: 2.8627 (2.7656)  weight_decay: 0.0500 (0.0500)  time: 1.0053  data: 0.0004  max mem: 78493
Epoch: [38]  [230/312]  eta: 0:01:28  lr: 0.003956  min_lr: 0.003956  loss: 2.7920 (2.7598)  weight_decay: 0.0500 (0.0500)  time: 1.0065  data: 0.0004  max mem: 78493
Epoch: [38]  [240/312]  eta: 0:01:17  lr: 0.003956  min_lr: 0.003956  loss: 2.5718 (2.7495)  weight_decay: 0.0500 (0.0500)  time: 1.0061  data: 0.0004  max mem: 78493
Epoch: [38]  [250/312]  eta: 0:01:06  lr: 0.003956  min_lr: 0.003956  loss: 2.5396 (2.7448)  weight_decay: 0.0500 (0.0500)  time: 1.0054  data: 0.0004  max mem: 78493
Epoch: [38]  [260/312]  eta: 0:00:55  lr: 0.003956  min_lr: 0.003956  loss: 2.7270 (2.7474)  weight_decay: 0.0500 (0.0500)  time: 1.0050  data: 0.0005  max mem: 78493
Epoch: [38]  [270/312]  eta: 0:00:45  lr: 0.003955  min_lr: 0.003955  loss: 2.7629 (2.7436)  weight_decay: 0.0500 (0.0500)  time: 1.0071  data: 0.0005  max mem: 78493
Epoch: [38]  [280/312]  eta: 0:00:34  lr: 0.003955  min_lr: 0.003955  loss: 2.5334 (2.7359)  weight_decay: 0.0500 (0.0500)  time: 1.0083  data: 0.0011  max mem: 78493
Epoch: [38]  [290/312]  eta: 0:00:23  lr: 0.003955  min_lr: 0.003955  loss: 2.5676 (2.7350)  weight_decay: 0.0500 (0.0500)  time: 1.0044  data: 0.0009  max mem: 78493
Epoch: [38]  [300/312]  eta: 0:00:12  lr: 0.003955  min_lr: 0.003955  loss: 2.6006 (2.7327)  weight_decay: 0.0500 (0.0500)  time: 1.0019  data: 0.0001  max mem: 78493
Epoch: [38]  [310/312]  eta: 0:00:02  lr: 0.003955  min_lr: 0.003955  loss: 2.8020 (2.7343)  weight_decay: 0.0500 (0.0500)  time: 1.0021  data: 0.0001  max mem: 78493
Epoch: [38]  [311/312]  eta: 0:00:01  lr: 0.003955  min_lr: 0.003955  loss: 2.8020 (2.7344)  weight_decay: 0.0500 (0.0500)  time: 1.0022  data: 0.0001  max mem: 78493
Epoch: [38] Total time: 0:05:33 (1.0686 s / it)
Averaged stats: lr: 0.003955  min_lr: 0.003955  loss: 2.8020 (2.7567)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:09  loss: 0.9945 (0.9945)  acc1: 75.9115 (75.9115)  acc5: 92.4479 (92.4479)  time: 7.6826  data: 7.4041  max mem: 78493
Test:  [8/9]  eta: 0:00:01  loss: 1.3560 (1.2595)  acc1: 67.8385 (68.5440)  acc5: 88.2812 (88.8000)  time: 1.0720  data: 0.8278  max mem: 78493
Test: Total time: 0:00:09 (1.0867 s / it)
* Acc@1 69.304 Acc@5 88.942 loss 1.236
Accuracy of the model on the 50000 test images: 69.3%
Max accuracy: 69.30%
Epoch: [39]  [  0/312]  eta: 1:22:16  lr: 0.003955  min_lr: 0.003955  loss: 2.9335 (2.9335)  weight_decay: 0.0500 (0.0500)  time: 15.8218  data: 14.8119  max mem: 78493
Epoch: [39]  [ 10/312]  eta: 0:12:59  lr: 0.003955  min_lr: 0.003955  loss: 2.4075 (2.6140)  weight_decay: 0.0500 (0.0500)  time: 2.5797  data: 1.3473  max mem: 78493
Epoch: [39]  [ 20/312]  eta: 0:08:55  lr: 0.003954  min_lr: 0.003954  loss: 2.4491 (2.5819)  weight_decay: 0.0500 (0.0500)  time: 1.1337  data: 0.0007  max mem: 78493
Epoch: [39]  [ 30/312]  eta: 0:07:22  lr: 0.003954  min_lr: 0.003954  loss: 2.4546 (2.5750)  weight_decay: 0.0500 (0.0500)  time: 1.0107  data: 0.0005  max mem: 78493
Epoch: [39]  [ 40/312]  eta: 0:06:29  lr: 0.003954  min_lr: 0.003954  loss: 2.5219 (2.5726)  weight_decay: 0.0500 (0.0500)  time: 1.0082  data: 0.0004  max mem: 78493
Epoch: [39]  [ 50/312]  eta: 0:05:53  lr: 0.003954  min_lr: 0.003954  loss: 2.7196 (2.6027)  weight_decay: 0.0500 (0.0500)  time: 1.0065  data: 0.0004  max mem: 78493
Epoch: [39]  [ 60/312]  eta: 0:05:25  lr: 0.003954  min_lr: 0.003954  loss: 2.6581 (2.6088)  weight_decay: 0.0500 (0.0500)  time: 1.0075  data: 0.0004  max mem: 78493
Epoch: [39]  [ 70/312]  eta: 0:05:02  lr: 0.003954  min_lr: 0.003954  loss: 2.6581 (2.6311)  weight_decay: 0.0500 (0.0500)  time: 1.0076  data: 0.0004  max mem: 78493
Epoch: [39]  [ 80/312]  eta: 0:04:43  lr: 0.003954  min_lr: 0.003954  loss: 2.9035 (2.6393)  weight_decay: 0.0500 (0.0500)  time: 1.0067  data: 0.0004  max mem: 78493
Epoch: [39]  [ 90/312]  eta: 0:04:25  lr: 0.003953  min_lr: 0.003953  loss: 2.7481 (2.6602)  weight_decay: 0.0500 (0.0500)  time: 1.0070  data: 0.0004  max mem: 78493
Epoch: [39]  [100/312]  eta: 0:04:09  lr: 0.003953  min_lr: 0.003953  loss: 2.8936 (2.6759)  weight_decay: 0.0500 (0.0500)  time: 1.0061  data: 0.0004  max mem: 78493
Epoch: [39]  [110/312]  eta: 0:03:55  lr: 0.003953  min_lr: 0.003953  loss: 2.6921 (2.6602)  weight_decay: 0.0500 (0.0500)  time: 1.0068  data: 0.0004  max mem: 78493
Epoch: [39]  [120/312]  eta: 0:03:40  lr: 0.003953  min_lr: 0.003953  loss: 2.6921 (2.6794)  weight_decay: 0.0500 (0.0500)  time: 1.0078  data: 0.0004  max mem: 78493
Epoch: [39]  [130/312]  eta: 0:03:27  lr: 0.003953  min_lr: 0.003953  loss: 2.9004 (2.6917)  weight_decay: 0.0500 (0.0500)  time: 1.0077  data: 0.0004  max mem: 78493
Epoch: [39]  [140/312]  eta: 0:03:14  lr: 0.003953  min_lr: 0.003953  loss: 2.8398 (2.6965)  weight_decay: 0.0500 (0.0500)  time: 1.0074  data: 0.0004  max mem: 78493
Epoch: [39]  [150/312]  eta: 0:03:01  lr: 0.003952  min_lr: 0.003952  loss: 2.8015 (2.6994)  weight_decay: 0.0500 (0.0500)  time: 1.0059  data: 0.0004  max mem: 78493
Epoch: [39]  [160/312]  eta: 0:02:49  lr: 0.003952  min_lr: 0.003952  loss: 2.9887 (2.7104)  weight_decay: 0.0500 (0.0500)  time: 1.0051  data: 0.0010  max mem: 78493
Epoch: [39]  [170/312]  eta: 0:02:37  lr: 0.003952  min_lr: 0.003952  loss: 2.9094 (2.7065)  weight_decay: 0.0500 (0.0500)  time: 1.0066  data: 0.0010  max mem: 78493
Epoch: [39]  [180/312]  eta: 0:02:25  lr: 0.003952  min_lr: 0.003952  loss: 2.9043 (2.7144)  weight_decay: 0.0500 (0.0500)  time: 1.0076  data: 0.0004  max mem: 78493
Epoch: [39]  [190/312]  eta: 0:02:13  lr: 0.003952  min_lr: 0.003952  loss: 2.8912 (2.7115)  weight_decay: 0.0500 (0.0500)  time: 1.0066  data: 0.0004  max mem: 78493
Epoch: [39]  [200/312]  eta: 0:02:02  lr: 0.003952  min_lr: 0.003952  loss: 2.5953 (2.6987)  weight_decay: 0.0500 (0.0500)  time: 1.0064  data: 0.0004  max mem: 78493
Epoch: [39]  [210/312]  eta: 0:01:51  lr: 0.003951  min_lr: 0.003951  loss: 2.4843 (2.6968)  weight_decay: 0.0500 (0.0500)  time: 1.0080  data: 0.0005  max mem: 78493
Epoch: [39]  [220/312]  eta: 0:01:39  lr: 0.003951  min_lr: 0.003951  loss: 2.8153 (2.6991)  weight_decay: 0.0500 (0.0500)  time: 1.0087  data: 0.0005  max mem: 78493
Epoch: [39]  [230/312]  eta: 0:01:28  lr: 0.003951  min_lr: 0.003951  loss: 2.7676 (2.6927)  weight_decay: 0.0500 (0.0500)  time: 1.0070  data: 0.0004  max mem: 78493
Epoch: [39]  [240/312]  eta: 0:01:17  lr: 0.003951  min_lr: 0.003951  loss: 2.7585 (2.6981)  weight_decay: 0.0500 (0.0500)  time: 1.0060  data: 0.0004  max mem: 78493
Epoch: [39]  [250/312]  eta: 0:01:06  lr: 0.003951  min_lr: 0.003951  loss: 2.6603 (2.6915)  weight_decay: 0.0500 (0.0500)  time: 1.0065  data: 0.0004  max mem: 78493
Epoch: [39]  [260/312]  eta: 0:00:55  lr: 0.003951  min_lr: 0.003951  loss: 2.6715 (2.6960)  weight_decay: 0.0500 (0.0500)  time: 1.0084  data: 0.0004  max mem: 78493
Epoch: [39]  [270/312]  eta: 0:00:44  lr: 0.003951  min_lr: 0.003951  loss: 2.5823 (2.6871)  weight_decay: 0.0500 (0.0500)  time: 1.0077  data: 0.0004  max mem: 78493
Epoch: [39]  [280/312]  eta: 0:00:34  lr: 0.003950  min_lr: 0.003950  loss: 2.6443 (2.6901)  weight_decay: 0.0500 (0.0500)  time: 1.0049  data: 0.0010  max mem: 78493
Epoch: [39]  [290/312]  eta: 0:00:23  lr: 0.003950  min_lr: 0.003950  loss: 2.7371 (2.6864)  weight_decay: 0.0500 (0.0500)  time: 1.0033  data: 0.0009  max mem: 78493
Epoch: [39]  [300/312]  eta: 0:00:12  lr: 0.003950  min_lr: 0.003950  loss: 2.6958 (2.6913)  weight_decay: 0.0500 (0.0500)  time: 1.0018  data: 0.0001  max mem: 78493
Epoch: [39]  [310/312]  eta: 0:00:02  lr: 0.003950  min_lr: 0.003950  loss: 2.6958 (2.6899)  weight_decay: 0.0500 (0.0500)  time: 1.0014  data: 0.0001  max mem: 78493
Epoch: [39]  [311/312]  eta: 0:00:01  lr: 0.003950  min_lr: 0.003950  loss: 2.7844 (2.6902)  weight_decay: 0.0500 (0.0500)  time: 1.0015  data: 0.0001  max mem: 78493
Epoch: [39] Total time: 0:05:33 (1.0682 s / it)
Averaged stats: lr: 0.003950  min_lr: 0.003950  loss: 2.7844 (2.7419)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:15  loss: 0.9704 (0.9704)  acc1: 77.3438 (77.3438)  acc5: 92.8385 (92.8385)  time: 8.3926  data: 8.1274  max mem: 78493
Test:  [8/9]  eta: 0:00:01  loss: 1.2999 (1.2023)  acc1: 68.7500 (69.9520)  acc5: 89.3229 (89.8560)  time: 1.1334  data: 0.9031  max mem: 78493
Test: Total time: 0:00:10 (1.1704 s / it)
* Acc@1 70.446 Acc@5 89.762 loss 1.203
Accuracy of the model on the 50000 test images: 70.4%
Max accuracy: 70.45%
Epoch: [40]  [  0/312]  eta: 1:19:48  lr: 0.003950  min_lr: 0.003950  loss: 2.4538 (2.4538)  weight_decay: 0.0500 (0.0500)  time: 15.3483  data: 13.9494  max mem: 78493
Epoch: [40]  [ 10/312]  eta: 0:13:15  lr: 0.003950  min_lr: 0.003950  loss: 2.6449 (2.5604)  weight_decay: 0.0500 (0.0500)  time: 2.6334  data: 1.3550  max mem: 78493
Epoch: [40]  [ 20/312]  eta: 0:09:03  lr: 0.003950  min_lr: 0.003950  loss: 2.7565 (2.6714)  weight_decay: 0.0500 (0.0500)  time: 1.1857  data: 0.0481  max mem: 78493
Epoch: [40]  [ 30/312]  eta: 0:07:26  lr: 0.003949  min_lr: 0.003949  loss: 2.8744 (2.7216)  weight_decay: 0.0500 (0.0500)  time: 1.0075  data: 0.0005  max mem: 78493
Epoch: [40]  [ 40/312]  eta: 0:06:32  lr: 0.003949  min_lr: 0.003949  loss: 2.8744 (2.7573)  weight_decay: 0.0500 (0.0500)  time: 1.0069  data: 0.0004  max mem: 78493
Epoch: [40]  [ 50/312]  eta: 0:05:55  lr: 0.003949  min_lr: 0.003949  loss: 2.8635 (2.7806)  weight_decay: 0.0500 (0.0500)  time: 1.0086  data: 0.0004  max mem: 78493
Epoch: [40]  [ 60/312]  eta: 0:05:27  lr: 0.003949  min_lr: 0.003949  loss: 2.7247 (2.7571)  weight_decay: 0.0500 (0.0500)  time: 1.0068  data: 0.0004  max mem: 78493
Epoch: [40]  [ 70/312]  eta: 0:05:04  lr: 0.003949  min_lr: 0.003949  loss: 2.6766 (2.7622)  weight_decay: 0.0500 (0.0500)  time: 1.0048  data: 0.0005  max mem: 78493
Epoch: [40]  [ 80/312]  eta: 0:04:44  lr: 0.003949  min_lr: 0.003949  loss: 2.7821 (2.7511)  weight_decay: 0.0500 (0.0500)  time: 1.0057  data: 0.0005  max mem: 78493
Epoch: [40]  [ 90/312]  eta: 0:04:27  lr: 0.003948  min_lr: 0.003948  loss: 2.7016 (2.7357)  weight_decay: 0.0500 (0.0500)  time: 1.0060  data: 0.0005  max mem: 78493
Epoch: [40]  [100/312]  eta: 0:04:10  lr: 0.003948  min_lr: 0.003948  loss: 2.9290 (2.7494)  weight_decay: 0.0500 (0.0500)  time: 1.0064  data: 0.0004  max mem: 78493
Epoch: [40]  [110/312]  eta: 0:03:55  lr: 0.003948  min_lr: 0.003948  loss: 2.9290 (2.7611)  weight_decay: 0.0500 (0.0500)  time: 1.0064  data: 0.0004  max mem: 78493
Epoch: [40]  [120/312]  eta: 0:03:41  lr: 0.003948  min_lr: 0.003948  loss: 2.6778 (2.7547)  weight_decay: 0.0500 (0.0500)  time: 1.0055  data: 0.0004  max mem: 78493
Epoch: [40]  [130/312]  eta: 0:03:28  lr: 0.003948  min_lr: 0.003948  loss: 2.5946 (2.7440)  weight_decay: 0.0500 (0.0500)  time: 1.0063  data: 0.0004  max mem: 78493
Epoch: [40]  [140/312]  eta: 0:03:14  lr: 0.003948  min_lr: 0.003948  loss: 2.8438 (2.7479)  weight_decay: 0.0500 (0.0500)  time: 1.0069  data: 0.0004  max mem: 78493
Epoch: [40]  [150/312]  eta: 0:03:02  lr: 0.003947  min_lr: 0.003947  loss: 2.9115 (2.7506)  weight_decay: 0.0500 (0.0500)  time: 1.0069  data: 0.0004  max mem: 78493
Epoch: [40]  [160/312]  eta: 0:02:49  lr: 0.003947  min_lr: 0.003947  loss: 2.8206 (2.7464)  weight_decay: 0.0500 (0.0500)  time: 1.0099  data: 0.0004  max mem: 78493
Epoch: [40]  [170/312]  eta: 0:02:37  lr: 0.003947  min_lr: 0.003947  loss: 2.7693 (2.7469)  weight_decay: 0.0500 (0.0500)  time: 1.0121  data: 0.0005  max mem: 78493
Epoch: [40]  [180/312]  eta: 0:02:26  lr: 0.003947  min_lr: 0.003947  loss: 2.7618 (2.7480)  weight_decay: 0.0500 (0.0500)  time: 1.0093  data: 0.0005  max mem: 78493
Epoch: [40]  [190/312]  eta: 0:02:14  lr: 0.003947  min_lr: 0.003947  loss: 2.8510 (2.7527)  weight_decay: 0.0500 (0.0500)  time: 1.0070  data: 0.0005  max mem: 78493
Epoch: [40]  [200/312]  eta: 0:02:02  lr: 0.003947  min_lr: 0.003947  loss: 2.9239 (2.7593)  weight_decay: 0.0500 (0.0500)  time: 1.0061  data: 0.0005  max mem: 78493
Epoch: [40]  [210/312]  eta: 0:01:51  lr: 0.003946  min_lr: 0.003946  loss: 2.9131 (2.7586)  weight_decay: 0.0500 (0.0500)  time: 1.0056  data: 0.0005  max mem: 78493
Epoch: [40]  [220/312]  eta: 0:01:40  lr: 0.003946  min_lr: 0.003946  loss: 2.8759 (2.7603)  weight_decay: 0.0500 (0.0500)  time: 1.0054  data: 0.0004  max mem: 78493
Epoch: [40]  [230/312]  eta: 0:01:28  lr: 0.003946  min_lr: 0.003946  loss: 2.8759 (2.7559)  weight_decay: 0.0500 (0.0500)  time: 1.0049  data: 0.0005  max mem: 78493
Epoch: [40]  [240/312]  eta: 0:01:17  lr: 0.003946  min_lr: 0.003946  loss: 2.8959 (2.7620)  weight_decay: 0.0500 (0.0500)  time: 1.0049  data: 0.0004  max mem: 78493
Epoch: [40]  [250/312]  eta: 0:01:06  lr: 0.003946  min_lr: 0.003946  loss: 2.9462 (2.7627)  weight_decay: 0.0500 (0.0500)  time: 1.0053  data: 0.0004  max mem: 78493
Epoch: [40]  [260/312]  eta: 0:00:55  lr: 0.003946  min_lr: 0.003946  loss: 2.8591 (2.7622)  weight_decay: 0.0500 (0.0500)  time: 1.0054  data: 0.0005  max mem: 78493
Epoch: [40]  [270/312]  eta: 0:00:45  lr: 0.003945  min_lr: 0.003945  loss: 2.5261 (2.7526)  weight_decay: 0.0500 (0.0500)  time: 1.0050  data: 0.0004  max mem: 78493
Epoch: [40]  [280/312]  eta: 0:00:34  lr: 0.003945  min_lr: 0.003945  loss: 2.5289 (2.7537)  weight_decay: 0.0500 (0.0500)  time: 1.0048  data: 0.0010  max mem: 78493
Epoch: [40]  [290/312]  eta: 0:00:23  lr: 0.003945  min_lr: 0.003945  loss: 2.9049 (2.7623)  weight_decay: 0.0500 (0.0500)  time: 1.0035  data: 0.0009  max mem: 78493
Epoch: [40]  [300/312]  eta: 0:00:12  lr: 0.003945  min_lr: 0.003945  loss: 2.8694 (2.7560)  weight_decay: 0.0500 (0.0500)  time: 1.0023  data: 0.0001  max mem: 78493
Epoch: [40]  [310/312]  eta: 0:00:02  lr: 0.003945  min_lr: 0.003945  loss: 2.6021 (2.7527)  weight_decay: 0.0500 (0.0500)  time: 1.0021  data: 0.0001  max mem: 78493
Epoch: [40]  [311/312]  eta: 0:00:01  lr: 0.003945  min_lr: 0.003945  loss: 2.6021 (2.7522)  weight_decay: 0.0500 (0.0500)  time: 1.0021  data: 0.0001  max mem: 78493
Epoch: [40] Total time: 0:05:33 (1.0696 s / it)
Averaged stats: lr: 0.003945  min_lr: 0.003945  loss: 2.6021 (2.7418)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:14  loss: 0.9484 (0.9484)  acc1: 76.6927 (76.6927)  acc5: 93.6198 (93.6198)  time: 8.2913  data: 8.0010  max mem: 78493
Test:  [8/9]  eta: 0:00:01  loss: 1.3807 (1.2939)  acc1: 67.3177 (68.0800)  acc5: 88.5417 (88.3520)  time: 1.1194  data: 0.8891  max mem: 78493
Test: Total time: 0:00:10 (1.1360 s / it)
* Acc@1 68.658 Acc@5 88.684 loss 1.284
Accuracy of the model on the 50000 test images: 68.7%
Max accuracy: 70.45%
Epoch: [41]  [  0/312]  eta: 1:22:57  lr: 0.003945  min_lr: 0.003945  loss: 2.2084 (2.2084)  weight_decay: 0.0500 (0.0500)  time: 15.9524  data: 12.1243  max mem: 78493
Epoch: [41]  [ 10/312]  eta: 0:13:14  lr: 0.003945  min_lr: 0.003945  loss: 2.2627 (2.5596)  weight_decay: 0.0500 (0.0500)  time: 2.6292  data: 1.3138  max mem: 78493
Epoch: [41]  [ 20/312]  eta: 0:09:03  lr: 0.003944  min_lr: 0.003944  loss: 2.7857 (2.6911)  weight_decay: 0.0500 (0.0500)  time: 1.1570  data: 0.1166  max mem: 78493
Epoch: [41]  [ 30/312]  eta: 0:07:27  lr: 0.003944  min_lr: 0.003944  loss: 2.9123 (2.7058)  weight_decay: 0.0500 (0.0500)  time: 1.0121  data: 0.0004  max mem: 78493
Epoch: [41]  [ 40/312]  eta: 0:06:32  lr: 0.003944  min_lr: 0.003944  loss: 2.8808 (2.7540)  weight_decay: 0.0500 (0.0500)  time: 1.0068  data: 0.0004  max mem: 78493
Epoch: [41]  [ 50/312]  eta: 0:05:55  lr: 0.003944  min_lr: 0.003944  loss: 2.6714 (2.7196)  weight_decay: 0.0500 (0.0500)  time: 1.0055  data: 0.0004  max mem: 78493
Epoch: [41]  [ 60/312]  eta: 0:05:27  lr: 0.003944  min_lr: 0.003944  loss: 2.6714 (2.7473)  weight_decay: 0.0500 (0.0500)  time: 1.0064  data: 0.0014  max mem: 78493
Epoch: [41]  [ 70/312]  eta: 0:05:04  lr: 0.003944  min_lr: 0.003944  loss: 2.6579 (2.7078)  weight_decay: 0.0500 (0.0500)  time: 1.0083  data: 0.0014  max mem: 78493
Epoch: [41]  [ 80/312]  eta: 0:04:44  lr: 0.003943  min_lr: 0.003943  loss: 2.6776 (2.7307)  weight_decay: 0.0500 (0.0500)  time: 1.0065  data: 0.0004  max mem: 78493
Epoch: [41]  [ 90/312]  eta: 0:04:27  lr: 0.003943  min_lr: 0.003943  loss: 2.8750 (2.7340)  weight_decay: 0.0500 (0.0500)  time: 1.0069  data: 0.0004  max mem: 78493
Epoch: [41]  [100/312]  eta: 0:04:11  lr: 0.003943  min_lr: 0.003943  loss: 2.8992 (2.7358)  weight_decay: 0.0500 (0.0500)  time: 1.0082  data: 0.0004  max mem: 78493
Epoch: [41]  [110/312]  eta: 0:03:56  lr: 0.003943  min_lr: 0.003943  loss: 2.8992 (2.7466)  weight_decay: 0.0500 (0.0500)  time: 1.0074  data: 0.0004  max mem: 78493
Epoch: [41]  [120/312]  eta: 0:03:41  lr: 0.003943  min_lr: 0.003943  loss: 3.0271 (2.7541)  weight_decay: 0.0500 (0.0500)  time: 1.0073  data: 0.0011  max mem: 78493
Epoch: [41]  [130/312]  eta: 0:03:28  lr: 0.003943  min_lr: 0.003943  loss: 2.9329 (2.7645)  weight_decay: 0.0500 (0.0500)  time: 1.0111  data: 0.0012  max mem: 78493
Epoch: [41]  [140/312]  eta: 0:03:15  lr: 0.003942  min_lr: 0.003942  loss: 2.7423 (2.7470)  weight_decay: 0.0500 (0.0500)  time: 1.0117  data: 0.0014  max mem: 78493
Epoch: [41]  [150/312]  eta: 0:03:02  lr: 0.003942  min_lr: 0.003942  loss: 2.6488 (2.7517)  weight_decay: 0.0500 (0.0500)  time: 1.0071  data: 0.0014  max mem: 78493
Epoch: [41]  [160/312]  eta: 0:02:50  lr: 0.003942  min_lr: 0.003942  loss: 2.8802 (2.7478)  weight_decay: 0.0500 (0.0500)  time: 1.0080  data: 0.0004  max mem: 78493
Epoch: [41]  [170/312]  eta: 0:02:37  lr: 0.003942  min_lr: 0.003942  loss: 2.8146 (2.7538)  weight_decay: 0.0500 (0.0500)  time: 1.0076  data: 0.0004  max mem: 78493
Epoch: [41]  [180/312]  eta: 0:02:26  lr: 0.003942  min_lr: 0.003942  loss: 2.8146 (2.7532)  weight_decay: 0.0500 (0.0500)  time: 1.0070  data: 0.0004  max mem: 78493
Epoch: [41]  [190/312]  eta: 0:02:14  lr: 0.003942  min_lr: 0.003942  loss: 2.7131 (2.7405)  weight_decay: 0.0500 (0.0500)  time: 1.0076  data: 0.0004  max mem: 78493
Epoch: [41]  [200/312]  eta: 0:02:02  lr: 0.003941  min_lr: 0.003941  loss: 2.5404 (2.7340)  weight_decay: 0.0500 (0.0500)  time: 1.0058  data: 0.0004  max mem: 78493
Epoch: [41]  [210/312]  eta: 0:01:51  lr: 0.003941  min_lr: 0.003941  loss: 2.6367 (2.7241)  weight_decay: 0.0500 (0.0500)  time: 1.0058  data: 0.0005  max mem: 78493
Epoch: [41]  [220/312]  eta: 0:01:40  lr: 0.003941  min_lr: 0.003941  loss: 2.8884 (2.7306)  weight_decay: 0.0500 (0.0500)  time: 1.0054  data: 0.0005  max mem: 78493
Epoch: [41]  [230/312]  eta: 0:01:28  lr: 0.003941  min_lr: 0.003941  loss: 3.0288 (2.7444)  weight_decay: 0.0500 (0.0500)  time: 1.0052  data: 0.0004  max mem: 78493
Epoch: [41]  [240/312]  eta: 0:01:17  lr: 0.003941  min_lr: 0.003941  loss: 2.9835 (2.7434)  weight_decay: 0.0500 (0.0500)  time: 1.0070  data: 0.0004  max mem: 78493
Epoch: [41]  [250/312]  eta: 0:01:06  lr: 0.003940  min_lr: 0.003940  loss: 2.8421 (2.7441)  weight_decay: 0.0500 (0.0500)  time: 1.0072  data: 0.0004  max mem: 78493
Epoch: [41]  [260/312]  eta: 0:00:55  lr: 0.003940  min_lr: 0.003940  loss: 2.9263 (2.7484)  weight_decay: 0.0500 (0.0500)  time: 1.0057  data: 0.0004  max mem: 78493
Epoch: [41]  [270/312]  eta: 0:00:45  lr: 0.003940  min_lr: 0.003940  loss: 2.8447 (2.7465)  weight_decay: 0.0500 (0.0500)  time: 1.0052  data: 0.0005  max mem: 78493
Epoch: [41]  [280/312]  eta: 0:00:34  lr: 0.003940  min_lr: 0.003940  loss: 2.4901 (2.7385)  weight_decay: 0.0500 (0.0500)  time: 1.0054  data: 0.0018  max mem: 78493
Epoch: [41]  [290/312]  eta: 0:00:23  lr: 0.003940  min_lr: 0.003940  loss: 2.6063 (2.7354)  weight_decay: 0.0500 (0.0500)  time: 1.0036  data: 0.0016  max mem: 78493
Epoch: [41]  [300/312]  eta: 0:00:12  lr: 0.003940  min_lr: 0.003940  loss: 2.8992 (2.7395)  weight_decay: 0.0500 (0.0500)  time: 1.0015  data: 0.0001  max mem: 78493
Epoch: [41]  [310/312]  eta: 0:00:02  lr: 0.003939  min_lr: 0.003939  loss: 2.9239 (2.7424)  weight_decay: 0.0500 (0.0500)  time: 1.0017  data: 0.0001  max mem: 78493
Epoch: [41]  [311/312]  eta: 0:00:01  lr: 0.003939  min_lr: 0.003939  loss: 2.9239 (2.7440)  weight_decay: 0.0500 (0.0500)  time: 1.0018  data: 0.0001  max mem: 78493
Epoch: [41] Total time: 0:05:33 (1.0698 s / it)
Averaged stats: lr: 0.003939  min_lr: 0.003939  loss: 2.9239 (2.7161)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:13  loss: 1.0629 (1.0629)  acc1: 73.9583 (73.9583)  acc5: 93.2292 (93.2292)  time: 8.1804  data: 7.9115  max mem: 78493
Test:  [8/9]  eta: 0:00:01  loss: 1.4254 (1.3301)  acc1: 66.6667 (68.3520)  acc5: 87.2396 (88.2080)  time: 1.1077  data: 0.8792  max mem: 78493
Test: Total time: 0:00:10 (1.1539 s / it)
* Acc@1 68.548 Acc@5 88.454 loss 1.305
Accuracy of the model on the 50000 test images: 68.5%
Max accuracy: 70.45%
Epoch: [42]  [  0/312]  eta: 1:27:11  lr: 0.003939  min_lr: 0.003939  loss: 3.2592 (3.2592)  weight_decay: 0.0500 (0.0500)  time: 16.7664  data: 11.4410  max mem: 78493
Epoch: [42]  [ 10/312]  eta: 0:13:23  lr: 0.003939  min_lr: 0.003939  loss: 2.6642 (2.6270)  weight_decay: 0.0500 (0.0500)  time: 2.6597  data: 1.2112  max mem: 78493
Epoch: [42]  [ 20/312]  eta: 0:09:07  lr: 0.003939  min_lr: 0.003939  loss: 2.6642 (2.6678)  weight_decay: 0.0500 (0.0500)  time: 1.1305  data: 0.0944  max mem: 78493
Epoch: [42]  [ 30/312]  eta: 0:07:29  lr: 0.003939  min_lr: 0.003939  loss: 2.6634 (2.6529)  weight_decay: 0.0500 (0.0500)  time: 1.0088  data: 0.0005  max mem: 78493
Epoch: [42]  [ 40/312]  eta: 0:06:34  lr: 0.003939  min_lr: 0.003939  loss: 2.8738 (2.6833)  weight_decay: 0.0500 (0.0500)  time: 1.0074  data: 0.0004  max mem: 78493
Epoch: [42]  [ 50/312]  eta: 0:05:57  lr: 0.003939  min_lr: 0.003939  loss: 2.9434 (2.7486)  weight_decay: 0.0500 (0.0500)  time: 1.0074  data: 0.0004  max mem: 78493
Epoch: [42]  [ 60/312]  eta: 0:05:29  lr: 0.003938  min_lr: 0.003938  loss: 2.7663 (2.7166)  weight_decay: 0.0500 (0.0500)  time: 1.0066  data: 0.0011  max mem: 78493
Epoch: [42]  [ 70/312]  eta: 0:05:05  lr: 0.003938  min_lr: 0.003938  loss: 2.6357 (2.7070)  weight_decay: 0.0500 (0.0500)  time: 1.0063  data: 0.0011  max mem: 78493
Epoch: [42]  [ 80/312]  eta: 0:04:45  lr: 0.003938  min_lr: 0.003938  loss: 2.8526 (2.7350)  weight_decay: 0.0500 (0.0500)  time: 1.0060  data: 0.0004  max mem: 78493
Epoch: [42]  [ 90/312]  eta: 0:04:27  lr: 0.003938  min_lr: 0.003938  loss: 2.6194 (2.7105)  weight_decay: 0.0500 (0.0500)  time: 1.0062  data: 0.0004  max mem: 78493
Epoch: [42]  [100/312]  eta: 0:04:11  lr: 0.003938  min_lr: 0.003938  loss: 2.6194 (2.7047)  weight_decay: 0.0500 (0.0500)  time: 1.0049  data: 0.0004  max mem: 78493
Epoch: [42]  [110/312]  eta: 0:03:56  lr: 0.003937  min_lr: 0.003937  loss: 2.8680 (2.7322)  weight_decay: 0.0500 (0.0500)  time: 1.0050  data: 0.0004  max mem: 78493
Epoch: [42]  [120/312]  eta: 0:03:42  lr: 0.003937  min_lr: 0.003937  loss: 2.8463 (2.7317)  weight_decay: 0.0500 (0.0500)  time: 1.0063  data: 0.0012  max mem: 78493
Epoch: [42]  [130/312]  eta: 0:03:28  lr: 0.003937  min_lr: 0.003937  loss: 2.6519 (2.7338)  weight_decay: 0.0500 (0.0500)  time: 1.0068  data: 0.0012  max mem: 78493
Epoch: [42]  [140/312]  eta: 0:03:15  lr: 0.003937  min_lr: 0.003937  loss: 2.6054 (2.7104)  weight_decay: 0.0500 (0.0500)  time: 1.0061  data: 0.0004  max mem: 78493
Epoch: [42]  [150/312]  eta: 0:03:02  lr: 0.003937  min_lr: 0.003937  loss: 2.6317 (2.7117)  weight_decay: 0.0500 (0.0500)  time: 1.0060  data: 0.0004  max mem: 78493
Epoch: [42]  [160/312]  eta: 0:02:50  lr: 0.003937  min_lr: 0.003937  loss: 2.6783 (2.7143)  weight_decay: 0.0500 (0.0500)  time: 1.0054  data: 0.0004  max mem: 78493
Epoch: [42]  [170/312]  eta: 0:02:38  lr: 0.003936  min_lr: 0.003936  loss: 2.5768 (2.7012)  weight_decay: 0.0500 (0.0500)  time: 1.0049  data: 0.0004  max mem: 78493
Epoch: [42]  [180/312]  eta: 0:02:26  lr: 0.003936  min_lr: 0.003936  loss: 2.5663 (2.7010)  weight_decay: 0.0500 (0.0500)  time: 1.0046  data: 0.0004  max mem: 78493
Epoch: [42]  [190/312]  eta: 0:02:14  lr: 0.003936  min_lr: 0.003936  loss: 2.9526 (2.7114)  weight_decay: 0.0500 (0.0500)  time: 1.0059  data: 0.0005  max mem: 78493
Epoch: [42]  [200/312]  eta: 0:02:02  lr: 0.003936  min_lr: 0.003936  loss: 2.8025 (2.6999)  weight_decay: 0.0500 (0.0500)  time: 1.0069  data: 0.0004  max mem: 78493
Epoch: [42]  [210/312]  eta: 0:01:51  lr: 0.003936  min_lr: 0.003936  loss: 2.4516 (2.6897)  weight_decay: 0.0500 (0.0500)  time: 1.0065  data: 0.0004  max mem: 78493
Epoch: [42]  [220/312]  eta: 0:01:40  lr: 0.003935  min_lr: 0.003935  loss: 2.7246 (2.6892)  weight_decay: 0.0500 (0.0500)  time: 1.0053  data: 0.0004  max mem: 78493
Epoch: [42]  [230/312]  eta: 0:01:28  lr: 0.003935  min_lr: 0.003935  loss: 2.6920 (2.6881)  weight_decay: 0.0500 (0.0500)  time: 1.0042  data: 0.0004  max mem: 78493
Epoch: [42]  [240/312]  eta: 0:01:17  lr: 0.003935  min_lr: 0.003935  loss: 2.6920 (2.6888)  weight_decay: 0.0500 (0.0500)  time: 1.0044  data: 0.0004  max mem: 78493
Epoch: [42]  [250/312]  eta: 0:01:06  lr: 0.003935  min_lr: 0.003935  loss: 2.8498 (2.6912)  weight_decay: 0.0500 (0.0500)  time: 1.0044  data: 0.0004  max mem: 78493
Epoch: [42]  [260/312]  eta: 0:00:55  lr: 0.003935  min_lr: 0.003935  loss: 2.8293 (2.6925)  weight_decay: 0.0500 (0.0500)  time: 1.0048  data: 0.0004  max mem: 78493
Epoch: [42]  [270/312]  eta: 0:00:45  lr: 0.003935  min_lr: 0.003935  loss: 2.8944 (2.7021)  weight_decay: 0.0500 (0.0500)  time: 1.0051  data: 0.0004  max mem: 78493
Epoch: [42]  [280/312]  eta: 0:00:34  lr: 0.003934  min_lr: 0.003934  loss: 2.9215 (2.7062)  weight_decay: 0.0500 (0.0500)  time: 1.0058  data: 0.0010  max mem: 78493
Epoch: [42]  [290/312]  eta: 0:00:23  lr: 0.003934  min_lr: 0.003934  loss: 2.7054 (2.7011)  weight_decay: 0.0500 (0.0500)  time: 1.0042  data: 0.0009  max mem: 78493
Epoch: [42]  [300/312]  eta: 0:00:12  lr: 0.003934  min_lr: 0.003934  loss: 2.4019 (2.6898)  weight_decay: 0.0500 (0.0500)  time: 1.0025  data: 0.0001  max mem: 78493
Epoch: [42]  [310/312]  eta: 0:00:02  lr: 0.003934  min_lr: 0.003934  loss: 2.4019 (2.6893)  weight_decay: 0.0500 (0.0500)  time: 1.0023  data: 0.0001  max mem: 78493
Epoch: [42]  [311/312]  eta: 0:00:01  lr: 0.003934  min_lr: 0.003934  loss: 2.4046 (2.6892)  weight_decay: 0.0500 (0.0500)  time: 1.0023  data: 0.0001  max mem: 78493
Epoch: [42] Total time: 0:05:33 (1.0697 s / it)
Averaged stats: lr: 0.003934  min_lr: 0.003934  loss: 2.4046 (2.7262)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:12  loss: 1.0342 (1.0342)  acc1: 77.0833 (77.0833)  acc5: 91.6667 (91.6667)  time: 8.0239  data: 7.7564  max mem: 78493
Test:  [8/9]  eta: 0:00:01  loss: 1.4140 (1.2603)  acc1: 67.3177 (69.3920)  acc5: 87.7604 (88.6080)  time: 1.0898  data: 0.8619  max mem: 78493
Test: Total time: 0:00:09 (1.1005 s / it)
* Acc@1 69.416 Acc@5 88.996 loss 1.259
Accuracy of the model on the 50000 test images: 69.4%
Max accuracy: 70.45%
Epoch: [43]  [  0/312]  eta: 1:25:21  lr: 0.003934  min_lr: 0.003934  loss: 2.7969 (2.7969)  weight_decay: 0.0500 (0.0500)  time: 16.4148  data: 12.5903  max mem: 78493
Epoch: [43]  [ 10/312]  eta: 0:13:05  lr: 0.003934  min_lr: 0.003934  loss: 2.7651 (2.5976)  weight_decay: 0.0500 (0.0500)  time: 2.5998  data: 1.2167  max mem: 78493
Epoch: [43]  [ 20/312]  eta: 0:09:00  lr: 0.003933  min_lr: 0.003933  loss: 2.8910 (2.7869)  weight_decay: 0.0500 (0.0500)  time: 1.1228  data: 0.0400  max mem: 78493
Epoch: [43]  [ 30/312]  eta: 0:07:25  lr: 0.003933  min_lr: 0.003933  loss: 2.9179 (2.8098)  weight_decay: 0.0500 (0.0500)  time: 1.0174  data: 0.0005  max mem: 78493
Epoch: [43]  [ 40/312]  eta: 0:06:31  lr: 0.003933  min_lr: 0.003933  loss: 2.7988 (2.7797)  weight_decay: 0.0500 (0.0500)  time: 1.0083  data: 0.0004  max mem: 78493
Epoch: [43]  [ 50/312]  eta: 0:05:55  lr: 0.003933  min_lr: 0.003933  loss: 2.8536 (2.7875)  weight_decay: 0.0500 (0.0500)  time: 1.0086  data: 0.0004  max mem: 78493
Epoch: [43]  [ 60/312]  eta: 0:05:27  lr: 0.003933  min_lr: 0.003933  loss: 2.8536 (2.7621)  weight_decay: 0.0500 (0.0500)  time: 1.0077  data: 0.0005  max mem: 78493
Epoch: [43]  [ 70/312]  eta: 0:05:04  lr: 0.003932  min_lr: 0.003932  loss: 2.5604 (2.7317)  weight_decay: 0.0500 (0.0500)  time: 1.0066  data: 0.0005  max mem: 78493
Epoch: [43]  [ 80/312]  eta: 0:04:44  lr: 0.003932  min_lr: 0.003932  loss: 2.7105 (2.7415)  weight_decay: 0.0500 (0.0500)  time: 1.0066  data: 0.0005  max mem: 78493
Epoch: [43]  [ 90/312]  eta: 0:04:26  lr: 0.003932  min_lr: 0.003932  loss: 2.8764 (2.7363)  weight_decay: 0.0500 (0.0500)  time: 1.0062  data: 0.0005  max mem: 78493
Epoch: [43]  [100/312]  eta: 0:04:10  lr: 0.003932  min_lr: 0.003932  loss: 2.7229 (2.7271)  weight_decay: 0.0500 (0.0500)  time: 1.0059  data: 0.0004  max mem: 78493
Epoch: [43]  [110/312]  eta: 0:03:55  lr: 0.003932  min_lr: 0.003932  loss: 2.4357 (2.6855)  weight_decay: 0.0500 (0.0500)  time: 1.0061  data: 0.0004  max mem: 78493
Epoch: [43]  [120/312]  eta: 0:03:41  lr: 0.003932  min_lr: 0.003932  loss: 2.6116 (2.6959)  weight_decay: 0.0500 (0.0500)  time: 1.0063  data: 0.0004  max mem: 78493
Epoch: [43]  [130/312]  eta: 0:03:27  lr: 0.003931  min_lr: 0.003931  loss: 2.6647 (2.6832)  weight_decay: 0.0500 (0.0500)  time: 1.0068  data: 0.0005  max mem: 78493
Epoch: [43]  [140/312]  eta: 0:03:14  lr: 0.003931  min_lr: 0.003931  loss: 2.6647 (2.6866)  weight_decay: 0.0500 (0.0500)  time: 1.0056  data: 0.0004  max mem: 78493
Epoch: [43]  [150/312]  eta: 0:03:02  lr: 0.003931  min_lr: 0.003931  loss: 2.6027 (2.6766)  weight_decay: 0.0500 (0.0500)  time: 1.0052  data: 0.0005  max mem: 78493
Epoch: [43]  [160/312]  eta: 0:02:49  lr: 0.003931  min_lr: 0.003931  loss: 2.5295 (2.6784)  weight_decay: 0.0500 (0.0500)  time: 1.0056  data: 0.0005  max mem: 78493
Epoch: [43]  [170/312]  eta: 0:02:37  lr: 0.003931  min_lr: 0.003931  loss: 2.8184 (2.6787)  weight_decay: 0.0500 (0.0500)  time: 1.0064  data: 0.0004  max mem: 78493
Epoch: [43]  [180/312]  eta: 0:02:25  lr: 0.003930  min_lr: 0.003930  loss: 2.5160 (2.6700)  weight_decay: 0.0500 (0.0500)  time: 1.0081  data: 0.0004  max mem: 78493
Epoch: [43]  [190/312]  eta: 0:02:14  lr: 0.003930  min_lr: 0.003930  loss: 2.3961 (2.6691)  weight_decay: 0.0500 (0.0500)  time: 1.0098  data: 0.0004  max mem: 78493
Epoch: [43]  [200/312]  eta: 0:02:02  lr: 0.003930  min_lr: 0.003930  loss: 2.8686 (2.6729)  weight_decay: 0.0500 (0.0500)  time: 1.0091  data: 0.0004  max mem: 78493
Epoch: [43]  [210/312]  eta: 0:01:51  lr: 0.003930  min_lr: 0.003930  loss: 2.9002 (2.6776)  weight_decay: 0.0500 (0.0500)  time: 1.0071  data: 0.0004  max mem: 78493
Epoch: [43]  [220/312]  eta: 0:01:40  lr: 0.003930  min_lr: 0.003930  loss: 2.8004 (2.6732)  weight_decay: 0.0500 (0.0500)  time: 1.0059  data: 0.0004  max mem: 78493
Epoch: [43]  [230/312]  eta: 0:01:28  lr: 0.003930  min_lr: 0.003930  loss: 2.3146 (2.6599)  weight_decay: 0.0500 (0.0500)  time: 1.0045  data: 0.0004  max mem: 78493
Epoch: [43]  [240/312]  eta: 0:01:17  lr: 0.003929  min_lr: 0.003929  loss: 2.2623 (2.6473)  weight_decay: 0.0500 (0.0500)  time: 1.0053  data: 0.0004  max mem: 78493
Epoch: [43]  [250/312]  eta: 0:01:06  lr: 0.003929  min_lr: 0.003929  loss: 2.4688 (2.6518)  weight_decay: 0.0500 (0.0500)  time: 1.0063  data: 0.0004  max mem: 78493
Epoch: [43]  [260/312]  eta: 0:00:55  lr: 0.003929  min_lr: 0.003929  loss: 2.8411 (2.6571)  weight_decay: 0.0500 (0.0500)  time: 1.0055  data: 0.0004  max mem: 78493
Epoch: [43]  [270/312]  eta: 0:00:45  lr: 0.003929  min_lr: 0.003929  loss: 2.8780 (2.6577)  weight_decay: 0.0500 (0.0500)  time: 1.0045  data: 0.0004  max mem: 78493
Epoch: [43]  [280/312]  eta: 0:00:34  lr: 0.003929  min_lr: 0.003929  loss: 2.8473 (2.6578)  weight_decay: 0.0500 (0.0500)  time: 1.0058  data: 0.0010  max mem: 78493
Epoch: [43]  [290/312]  eta: 0:00:23  lr: 0.003928  min_lr: 0.003928  loss: 2.6082 (2.6536)  weight_decay: 0.0500 (0.0500)  time: 1.0052  data: 0.0009  max mem: 78493
Epoch: [43]  [300/312]  eta: 0:00:12  lr: 0.003928  min_lr: 0.003928  loss: 2.6503 (2.6603)  weight_decay: 0.0500 (0.0500)  time: 1.0021  data: 0.0001  max mem: 78493
Epoch: [43]  [310/312]  eta: 0:00:02  lr: 0.003928  min_lr: 0.003928  loss: 2.8280 (2.6634)  weight_decay: 0.0500 (0.0500)  time: 1.0014  data: 0.0001  max mem: 78493
Epoch: [43]  [311/312]  eta: 0:00:01  lr: 0.003928  min_lr: 0.003928  loss: 2.8201 (2.6606)  weight_decay: 0.0500 (0.0500)  time: 1.0014  data: 0.0001  max mem: 78493
Epoch: [43] Total time: 0:05:33 (1.0685 s / it)
Averaged stats: lr: 0.003928  min_lr: 0.003928  loss: 2.8201 (2.6930)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:16  loss: 0.9522 (0.9522)  acc1: 76.6927 (76.6927)  acc5: 92.9688 (92.9688)  time: 8.4663  data: 8.1965  max mem: 78493
Test:  [8/9]  eta: 0:00:01  loss: 1.3814 (1.2695)  acc1: 67.8385 (68.5280)  acc5: 88.8021 (88.7360)  time: 1.1391  data: 0.9108  max mem: 78493
Test: Total time: 0:00:10 (1.1625 s / it)
* Acc@1 69.260 Acc@5 89.054 loss 1.254
Accuracy of the model on the 50000 test images: 69.3%
Max accuracy: 70.45%
Epoch: [44]  [  0/312]  eta: 1:24:05  lr: 0.003928  min_lr: 0.003928  loss: 2.7790 (2.7790)  weight_decay: 0.0500 (0.0500)  time: 16.1715  data: 15.1657  max mem: 78493
Epoch: [44]  [ 10/312]  eta: 0:12:33  lr: 0.003928  min_lr: 0.003928  loss: 2.7046 (2.6630)  weight_decay: 0.0500 (0.0500)  time: 2.4963  data: 1.3795  max mem: 78493
Epoch: [44]  [ 20/312]  eta: 0:08:49  lr: 0.003928  min_lr: 0.003928  loss: 2.7046 (2.6996)  weight_decay: 0.0500 (0.0500)  time: 1.0938  data: 0.0008  max mem: 78493
Epoch: [44]  [ 30/312]  eta: 0:07:18  lr: 0.003927  min_lr: 0.003927  loss: 2.7129 (2.7082)  weight_decay: 0.0500 (0.0500)  time: 1.0346  data: 0.0006  max mem: 78493
Epoch: [44]  [ 40/312]  eta: 0:06:26  lr: 0.003927  min_lr: 0.003927  loss: 2.7494 (2.7233)  weight_decay: 0.0500 (0.0500)  time: 1.0097  data: 0.0004  max mem: 78493
Epoch: [44]  [ 50/312]  eta: 0:05:50  lr: 0.003927  min_lr: 0.003927  loss: 2.9705 (2.7715)  weight_decay: 0.0500 (0.0500)  time: 1.0084  data: 0.0004  max mem: 78493
Epoch: [44]  [ 60/312]  eta: 0:05:23  lr: 0.003927  min_lr: 0.003927  loss: 2.9698 (2.7548)  weight_decay: 0.0500 (0.0500)  time: 1.0079  data: 0.0004  max mem: 78493
Epoch: [44]  [ 70/312]  eta: 0:05:01  lr: 0.003927  min_lr: 0.003927  loss: 2.7003 (2.7457)  weight_decay: 0.0500 (0.0500)  time: 1.0097  data: 0.0004  max mem: 78493
Epoch: [44]  [ 80/312]  eta: 0:04:42  lr: 0.003926  min_lr: 0.003926  loss: 2.5030 (2.7208)  weight_decay: 0.0500 (0.0500)  time: 1.0099  data: 0.0017  max mem: 78493
Epoch: [44]  [ 90/312]  eta: 0:04:25  lr: 0.003926  min_lr: 0.003926  loss: 2.5562 (2.7046)  weight_decay: 0.0500 (0.0500)  time: 1.0082  data: 0.0017  max mem: 78493
Epoch: [44]  [100/312]  eta: 0:04:09  lr: 0.003926  min_lr: 0.003926  loss: 2.6639 (2.6996)  weight_decay: 0.0500 (0.0500)  time: 1.0094  data: 0.0004  max mem: 78493
Epoch: [44]  [110/312]  eta: 0:03:54  lr: 0.003926  min_lr: 0.003926  loss: 2.7129 (2.6982)  weight_decay: 0.0500 (0.0500)  time: 1.0085  data: 0.0004  max mem: 78493
Epoch: [44]  [120/312]  eta: 0:03:40  lr: 0.003926  min_lr: 0.003926  loss: 2.8037 (2.6986)  weight_decay: 0.0500 (0.0500)  time: 1.0061  data: 0.0004  max mem: 78493
Epoch: [44]  [130/312]  eta: 0:03:26  lr: 0.003925  min_lr: 0.003925  loss: 2.8037 (2.7154)  weight_decay: 0.0500 (0.0500)  time: 1.0060  data: 0.0004  max mem: 78493
Epoch: [44]  [140/312]  eta: 0:03:14  lr: 0.003925  min_lr: 0.003925  loss: 2.7864 (2.7135)  weight_decay: 0.0500 (0.0500)  time: 1.0066  data: 0.0004  max mem: 78493
Epoch: [44]  [150/312]  eta: 0:03:01  lr: 0.003925  min_lr: 0.003925  loss: 2.6881 (2.7088)  weight_decay: 0.0500 (0.0500)  time: 1.0078  data: 0.0004  max mem: 78493
Epoch: [44]  [160/312]  eta: 0:02:49  lr: 0.003925  min_lr: 0.003925  loss: 2.6870 (2.6987)  weight_decay: 0.0500 (0.0500)  time: 1.0073  data: 0.0005  max mem: 78493
Epoch: [44]  [170/312]  eta: 0:02:37  lr: 0.003925  min_lr: 0.003925  loss: 2.7713 (2.7037)  weight_decay: 0.0500 (0.0500)  time: 1.0065  data: 0.0005  max mem: 78493
Epoch: [44]  [180/312]  eta: 0:02:25  lr: 0.003924  min_lr: 0.003924  loss: 2.7780 (2.6997)  weight_decay: 0.0500 (0.0500)  time: 1.0063  data: 0.0004  max mem: 78493
Epoch: [44]  [190/312]  eta: 0:02:13  lr: 0.003924  min_lr: 0.003924  loss: 2.7572 (2.6972)  weight_decay: 0.0500 (0.0500)  time: 1.0059  data: 0.0004  max mem: 78493
Epoch: [44]  [200/312]  eta: 0:02:02  lr: 0.003924  min_lr: 0.003924  loss: 2.6522 (2.6912)  weight_decay: 0.0500 (0.0500)  time: 1.0064  data: 0.0005  max mem: 78493
Epoch: [44]  [210/312]  eta: 0:01:50  lr: 0.003924  min_lr: 0.003924  loss: 2.5988 (2.6866)  weight_decay: 0.0500 (0.0500)  time: 1.0054  data: 0.0005  max mem: 78493
Epoch: [44]  [220/312]  eta: 0:01:39  lr: 0.003924  min_lr: 0.003924  loss: 2.6506 (2.6807)  weight_decay: 0.0500 (0.0500)  time: 1.0042  data: 0.0004  max mem: 78493
Epoch: [44]  [230/312]  eta: 0:01:28  lr: 0.003923  min_lr: 0.003923  loss: 2.6379 (2.6753)  weight_decay: 0.0500 (0.0500)  time: 1.0046  data: 0.0004  max mem: 78493
Epoch: [44]  [240/312]  eta: 0:01:17  lr: 0.003923  min_lr: 0.003923  loss: 2.6502 (2.6749)  weight_decay: 0.0500 (0.0500)  time: 1.0059  data: 0.0004  max mem: 78493
Epoch: [44]  [250/312]  eta: 0:01:06  lr: 0.003923  min_lr: 0.003923  loss: 2.6625 (2.6690)  weight_decay: 0.0500 (0.0500)  time: 1.0059  data: 0.0004  max mem: 78493
Epoch: [44]  [260/312]  eta: 0:00:55  lr: 0.003923  min_lr: 0.003923  loss: 2.8091 (2.6765)  weight_decay: 0.0500 (0.0500)  time: 1.0048  data: 0.0004  max mem: 78493
Epoch: [44]  [270/312]  eta: 0:00:44  lr: 0.003923  min_lr: 0.003923  loss: 2.9166 (2.6884)  weight_decay: 0.0500 (0.0500)  time: 1.0052  data: 0.0004  max mem: 78493
Epoch: [44]  [280/312]  eta: 0:00:34  lr: 0.003922  min_lr: 0.003922  loss: 2.9196 (2.6887)  weight_decay: 0.0500 (0.0500)  time: 1.0073  data: 0.0013  max mem: 78493
Epoch: [44]  [290/312]  eta: 0:00:23  lr: 0.003922  min_lr: 0.003922  loss: 2.7637 (2.6922)  weight_decay: 0.0500 (0.0500)  time: 1.0055  data: 0.0011  max mem: 78493
Epoch: [44]  [300/312]  eta: 0:00:12  lr: 0.003922  min_lr: 0.003922  loss: 2.7236 (2.6927)  weight_decay: 0.0500 (0.0500)  time: 1.0017  data: 0.0001  max mem: 78493
Epoch: [44]  [310/312]  eta: 0:00:02  lr: 0.003922  min_lr: 0.003922  loss: 2.6360 (2.6922)  weight_decay: 0.0500 (0.0500)  time: 1.0014  data: 0.0001  max mem: 78493
Epoch: [44]  [311/312]  eta: 0:00:01  lr: 0.003922  min_lr: 0.003922  loss: 2.6396 (2.6929)  weight_decay: 0.0500 (0.0500)  time: 1.0013  data: 0.0001  max mem: 78493
Epoch: [44] Total time: 0:05:32 (1.0662 s / it)
Averaged stats: lr: 0.003922  min_lr: 0.003922  loss: 2.6396 (2.6786)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:15  loss: 1.0179 (1.0179)  acc1: 77.4740 (77.4740)  acc5: 92.4479 (92.4479)  time: 8.3453  data: 8.0850  max mem: 78493
Test:  [8/9]  eta: 0:00:01  loss: 1.3997 (1.2818)  acc1: 68.2292 (69.2800)  acc5: 88.8021 (88.8960)  time: 1.1315  data: 0.8984  max mem: 78493
Test: Total time: 0:00:10 (1.1772 s / it)
* Acc@1 68.706 Acc@5 88.720 loss 1.281
Accuracy of the model on the 50000 test images: 68.7%
Max accuracy: 70.45%
Epoch: [45]  [  0/312]  eta: 1:26:49  lr: 0.003922  min_lr: 0.003922  loss: 2.0796 (2.0796)  weight_decay: 0.0500 (0.0500)  time: 16.6972  data: 15.6952  max mem: 78493
Epoch: [45]  [ 10/312]  eta: 0:12:30  lr: 0.003922  min_lr: 0.003922  loss: 2.7121 (2.6498)  weight_decay: 0.0500 (0.0500)  time: 2.4848  data: 1.4454  max mem: 78493
Epoch: [45]  [ 20/312]  eta: 0:08:44  lr: 0.003921  min_lr: 0.003921  loss: 2.4529 (2.5848)  weight_decay: 0.0500 (0.0500)  time: 1.0495  data: 0.0116  max mem: 78493
Epoch: [45]  [ 30/312]  eta: 0:07:14  lr: 0.003921  min_lr: 0.003921  loss: 2.7701 (2.6933)  weight_decay: 0.0500 (0.0500)  time: 1.0214  data: 0.0017  max mem: 78493
Epoch: [45]  [ 40/312]  eta: 0:06:23  lr: 0.003921  min_lr: 0.003921  loss: 2.9529 (2.7236)  weight_decay: 0.0500 (0.0500)  time: 1.0073  data: 0.0005  max mem: 78493
Epoch: [45]  [ 50/312]  eta: 0:05:48  lr: 0.003921  min_lr: 0.003921  loss: 2.8181 (2.7606)  weight_decay: 0.0500 (0.0500)  time: 1.0074  data: 0.0004  max mem: 78493
Epoch: [45]  [ 60/312]  eta: 0:05:22  lr: 0.003921  min_lr: 0.003921  loss: 2.7628 (2.7475)  weight_decay: 0.0500 (0.0500)  time: 1.0065  data: 0.0004  max mem: 78493
Epoch: [45]  [ 70/312]  eta: 0:05:00  lr: 0.003920  min_lr: 0.003920  loss: 2.4904 (2.7188)  weight_decay: 0.0500 (0.0500)  time: 1.0095  data: 0.0004  max mem: 78493
Epoch: [45]  [ 80/312]  eta: 0:04:41  lr: 0.003920  min_lr: 0.003920  loss: 2.4810 (2.6999)  weight_decay: 0.0500 (0.0500)  time: 1.0128  data: 0.0004  max mem: 78493
Epoch: [45]  [ 90/312]  eta: 0:04:24  lr: 0.003920  min_lr: 0.003920  loss: 2.7003 (2.7021)  weight_decay: 0.0500 (0.0500)  time: 1.0102  data: 0.0004  max mem: 78493
Epoch: [45]  [100/312]  eta: 0:04:08  lr: 0.003920  min_lr: 0.003920  loss: 2.7879 (2.7054)  weight_decay: 0.0500 (0.0500)  time: 1.0094  data: 0.0004  max mem: 78493
Epoch: [45]  [110/312]  eta: 0:03:53  lr: 0.003920  min_lr: 0.003920  loss: 2.8687 (2.7198)  weight_decay: 0.0500 (0.0500)  time: 1.0090  data: 0.0004  max mem: 78493
Epoch: [45]  [120/312]  eta: 0:03:39  lr: 0.003919  min_lr: 0.003919  loss: 2.8101 (2.7158)  weight_decay: 0.0500 (0.0500)  time: 1.0078  data: 0.0004  max mem: 78493
Epoch: [45]  [130/312]  eta: 0:03:26  lr: 0.003919  min_lr: 0.003919  loss: 2.6248 (2.7047)  weight_decay: 0.0500 (0.0500)  time: 1.0091  data: 0.0005  max mem: 78493
Epoch: [45]  [140/312]  eta: 0:03:13  lr: 0.003919  min_lr: 0.003919  loss: 2.5934 (2.6954)  weight_decay: 0.0500 (0.0500)  time: 1.0100  data: 0.0005  max mem: 78493
Epoch: [45]  [150/312]  eta: 0:03:01  lr: 0.003919  min_lr: 0.003919  loss: 2.8474 (2.7120)  weight_decay: 0.0500 (0.0500)  time: 1.0084  data: 0.0004  max mem: 78493
Epoch: [45]  [160/312]  eta: 0:02:48  lr: 0.003919  min_lr: 0.003919  loss: 2.8972 (2.7222)  weight_decay: 0.0500 (0.0500)  time: 1.0075  data: 0.0004  max mem: 78493
Epoch: [45]  [170/312]  eta: 0:02:36  lr: 0.003918  min_lr: 0.003918  loss: 2.4873 (2.6983)  weight_decay: 0.0500 (0.0500)  time: 1.0068  data: 0.0004  max mem: 78493
Epoch: [45]  [180/312]  eta: 0:02:25  lr: 0.003918  min_lr: 0.003918  loss: 2.3063 (2.6887)  weight_decay: 0.0500 (0.0500)  time: 1.0065  data: 0.0005  max mem: 78493
Epoch: [45]  [190/312]  eta: 0:02:13  lr: 0.003918  min_lr: 0.003918  loss: 2.7086 (2.6839)  weight_decay: 0.0500 (0.0500)  time: 1.0060  data: 0.0004  max mem: 78493
Epoch: [45]  [200/312]  eta: 0:02:02  lr: 0.003918  min_lr: 0.003918  loss: 2.7836 (2.6878)  weight_decay: 0.0500 (0.0500)  time: 1.0055  data: 0.0004  max mem: 78493
Epoch: [45]  [210/312]  eta: 0:01:50  lr: 0.003918  min_lr: 0.003918  loss: 2.7838 (2.6902)  weight_decay: 0.0500 (0.0500)  time: 1.0050  data: 0.0005  max mem: 78493
Epoch: [45]  [220/312]  eta: 0:01:39  lr: 0.003917  min_lr: 0.003917  loss: 2.7347 (2.6888)  weight_decay: 0.0500 (0.0500)  time: 1.0043  data: 0.0005  max mem: 78493
Epoch: [45]  [230/312]  eta: 0:01:28  lr: 0.003917  min_lr: 0.003917  loss: 2.6066 (2.6873)  weight_decay: 0.0500 (0.0500)  time: 1.0057  data: 0.0005  max mem: 78493
Epoch: [45]  [240/312]  eta: 0:01:17  lr: 0.003917  min_lr: 0.003917  loss: 2.4307 (2.6816)  weight_decay: 0.0500 (0.0500)  time: 1.0061  data: 0.0005  max mem: 78493
Epoch: [45]  [250/312]  eta: 0:01:06  lr: 0.003917  min_lr: 0.003917  loss: 2.6573 (2.6878)  weight_decay: 0.0500 (0.0500)  time: 1.0051  data: 0.0004  max mem: 78493
Epoch: [45]  [260/312]  eta: 0:00:55  lr: 0.003917  min_lr: 0.003917  loss: 2.6573 (2.6890)  weight_decay: 0.0500 (0.0500)  time: 1.0037  data: 0.0004  max mem: 78493
Epoch: [45]  [270/312]  eta: 0:00:44  lr: 0.003916  min_lr: 0.003916  loss: 2.4946 (2.6796)  weight_decay: 0.0500 (0.0500)  time: 1.0040  data: 0.0004  max mem: 78493
Epoch: [45]  [280/312]  eta: 0:00:34  lr: 0.003916  min_lr: 0.003916  loss: 2.7070 (2.6845)  weight_decay: 0.0500 (0.0500)  time: 1.0058  data: 0.0010  max mem: 78493
Epoch: [45]  [290/312]  eta: 0:00:23  lr: 0.003916  min_lr: 0.003916  loss: 2.7749 (2.6849)  weight_decay: 0.0500 (0.0500)  time: 1.0040  data: 0.0009  max mem: 78493
Epoch: [45]  [300/312]  eta: 0:00:12  lr: 0.003916  min_lr: 0.003916  loss: 2.7659 (2.6849)  weight_decay: 0.0500 (0.0500)  time: 1.0017  data: 0.0001  max mem: 78493
Epoch: [45]  [310/312]  eta: 0:00:02  lr: 0.003916  min_lr: 0.003916  loss: 2.7098 (2.6870)  weight_decay: 0.0500 (0.0500)  time: 1.0017  data: 0.0002  max mem: 78493
Epoch: [45]  [311/312]  eta: 0:00:01  lr: 0.003916  min_lr: 0.003916  loss: 2.7098 (2.6878)  weight_decay: 0.0500 (0.0500)  time: 1.0017  data: 0.0002  max mem: 78493
Epoch: [45] Total time: 0:05:32 (1.0654 s / it)
Averaged stats: lr: 0.003916  min_lr: 0.003916  loss: 2.7098 (2.6862)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:11  loss: 1.0729 (1.0729)  acc1: 74.4792 (74.4792)  acc5: 90.8854 (90.8854)  time: 7.8978  data: 7.6291  max mem: 78493
Test:  [8/9]  eta: 0:00:01  loss: 1.4813 (1.3291)  acc1: 66.5365 (68.4960)  acc5: 87.6302 (88.0800)  time: 1.0764  data: 0.8478  max mem: 78493
Test: Total time: 0:00:09 (1.0979 s / it)
* Acc@1 68.556 Acc@5 88.272 loss 1.309
Accuracy of the model on the 50000 test images: 68.6%
Max accuracy: 70.45%
Epoch: [46]  [  0/312]  eta: 1:25:14  lr: 0.003916  min_lr: 0.003916  loss: 2.5895 (2.5895)  weight_decay: 0.0500 (0.0500)  time: 16.3925  data: 15.2181  max mem: 78493
Epoch: [46]  [ 10/312]  eta: 0:12:59  lr: 0.003915  min_lr: 0.003915  loss: 2.7382 (2.5796)  weight_decay: 0.0500 (0.0500)  time: 2.5826  data: 1.3841  max mem: 78493
Epoch: [46]  [ 20/312]  eta: 0:08:55  lr: 0.003915  min_lr: 0.003915  loss: 2.7382 (2.6389)  weight_decay: 0.0500 (0.0500)  time: 1.1077  data: 0.0020  max mem: 78493
Epoch: [46]  [ 30/312]  eta: 0:07:22  lr: 0.003915  min_lr: 0.003915  loss: 2.8655 (2.6688)  weight_decay: 0.0500 (0.0500)  time: 1.0111  data: 0.0018  max mem: 78493
Epoch: [46]  [ 40/312]  eta: 0:06:29  lr: 0.003915  min_lr: 0.003915  loss: 2.7803 (2.6768)  weight_decay: 0.0500 (0.0500)  time: 1.0076  data: 0.0005  max mem: 78493
Epoch: [46]  [ 50/312]  eta: 0:05:53  lr: 0.003914  min_lr: 0.003914  loss: 2.7496 (2.7185)  weight_decay: 0.0500 (0.0500)  time: 1.0079  data: 0.0005  max mem: 78493
Epoch: [46]  [ 60/312]  eta: 0:05:25  lr: 0.003914  min_lr: 0.003914  loss: 2.8318 (2.7254)  weight_decay: 0.0500 (0.0500)  time: 1.0078  data: 0.0004  max mem: 78493
Epoch: [46]  [ 70/312]  eta: 0:05:03  lr: 0.003914  min_lr: 0.003914  loss: 2.7962 (2.7161)  weight_decay: 0.0500 (0.0500)  time: 1.0057  data: 0.0005  max mem: 78493
Epoch: [46]  [ 80/312]  eta: 0:04:43  lr: 0.003914  min_lr: 0.003914  loss: 2.7778 (2.7282)  weight_decay: 0.0500 (0.0500)  time: 1.0066  data: 0.0004  max mem: 78493
Epoch: [46]  [ 90/312]  eta: 0:04:26  lr: 0.003914  min_lr: 0.003914  loss: 2.7531 (2.7155)  weight_decay: 0.0500 (0.0500)  time: 1.0073  data: 0.0004  max mem: 78493
Epoch: [46]  [100/312]  eta: 0:04:10  lr: 0.003913  min_lr: 0.003913  loss: 2.7700 (2.7319)  weight_decay: 0.0500 (0.0500)  time: 1.0071  data: 0.0005  max mem: 78493
Epoch: [46]  [110/312]  eta: 0:03:55  lr: 0.003913  min_lr: 0.003913  loss: 2.9023 (2.7330)  weight_decay: 0.0500 (0.0500)  time: 1.0088  data: 0.0005  max mem: 78493
Epoch: [46]  [120/312]  eta: 0:03:41  lr: 0.003913  min_lr: 0.003913  loss: 2.9834 (2.7598)  weight_decay: 0.0500 (0.0500)  time: 1.0090  data: 0.0005  max mem: 78493
Epoch: [46]  [130/312]  eta: 0:03:27  lr: 0.003913  min_lr: 0.003913  loss: 2.9352 (2.7495)  weight_decay: 0.0500 (0.0500)  time: 1.0077  data: 0.0005  max mem: 78493
Epoch: [46]  [140/312]  eta: 0:03:14  lr: 0.003913  min_lr: 0.003913  loss: 2.7478 (2.7582)  weight_decay: 0.0500 (0.0500)  time: 1.0069  data: 0.0005  max mem: 78493
Epoch: [46]  [150/312]  eta: 0:03:01  lr: 0.003912  min_lr: 0.003912  loss: 2.7851 (2.7517)  weight_decay: 0.0500 (0.0500)  time: 1.0082  data: 0.0005  max mem: 78493
Epoch: [46]  [160/312]  eta: 0:02:49  lr: 0.003912  min_lr: 0.003912  loss: 2.7478 (2.7496)  weight_decay: 0.0500 (0.0500)  time: 1.0073  data: 0.0005  max mem: 78493
Epoch: [46]  [170/312]  eta: 0:02:37  lr: 0.003912  min_lr: 0.003912  loss: 2.8108 (2.7537)  weight_decay: 0.0500 (0.0500)  time: 1.0060  data: 0.0004  max mem: 78493
Epoch: [46]  [180/312]  eta: 0:02:25  lr: 0.003912  min_lr: 0.003912  loss: 2.8131 (2.7528)  weight_decay: 0.0500 (0.0500)  time: 1.0055  data: 0.0004  max mem: 78493
Epoch: [46]  [190/312]  eta: 0:02:13  lr: 0.003912  min_lr: 0.003912  loss: 2.8246 (2.7475)  weight_decay: 0.0500 (0.0500)  time: 1.0044  data: 0.0005  max mem: 78493
Epoch: [46]  [200/312]  eta: 0:02:02  lr: 0.003911  min_lr: 0.003911  loss: 2.7728 (2.7468)  weight_decay: 0.0500 (0.0500)  time: 1.0053  data: 0.0005  max mem: 78493
Epoch: [46]  [210/312]  eta: 0:01:51  lr: 0.003911  min_lr: 0.003911  loss: 2.7121 (2.7420)  weight_decay: 0.0500 (0.0500)  time: 1.0052  data: 0.0005  max mem: 78493
Epoch: [46]  [220/312]  eta: 0:01:39  lr: 0.003911  min_lr: 0.003911  loss: 2.7208 (2.7390)  weight_decay: 0.0500 (0.0500)  time: 1.0044  data: 0.0005  max mem: 78493
Epoch: [46]  [230/312]  eta: 0:01:28  lr: 0.003911  min_lr: 0.003911  loss: 2.7740 (2.7377)  weight_decay: 0.0500 (0.0500)  time: 1.0051  data: 0.0004  max mem: 78493
Epoch: [46]  [240/312]  eta: 0:01:17  lr: 0.003910  min_lr: 0.003910  loss: 2.8184 (2.7377)  weight_decay: 0.0500 (0.0500)  time: 1.0056  data: 0.0004  max mem: 78493
Epoch: [46]  [250/312]  eta: 0:01:06  lr: 0.003910  min_lr: 0.003910  loss: 2.8739 (2.7412)  weight_decay: 0.0500 (0.0500)  time: 1.0049  data: 0.0004  max mem: 78493
Epoch: [46]  [260/312]  eta: 0:00:55  lr: 0.003910  min_lr: 0.003910  loss: 2.9138 (2.7500)  weight_decay: 0.0500 (0.0500)  time: 1.0049  data: 0.0004  max mem: 78493
Epoch: [46]  [270/312]  eta: 0:00:44  lr: 0.003910  min_lr: 0.003910  loss: 2.8726 (2.7494)  weight_decay: 0.0500 (0.0500)  time: 1.0054  data: 0.0004  max mem: 78493
Epoch: [46]  [280/312]  eta: 0:00:34  lr: 0.003910  min_lr: 0.003910  loss: 2.8223 (2.7457)  weight_decay: 0.0500 (0.0500)  time: 1.0068  data: 0.0011  max mem: 78493
Epoch: [46]  [290/312]  eta: 0:00:23  lr: 0.003909  min_lr: 0.003909  loss: 2.7435 (2.7407)  weight_decay: 0.0500 (0.0500)  time: 1.0052  data: 0.0009  max mem: 78493
Epoch: [46]  [300/312]  eta: 0:00:12  lr: 0.003909  min_lr: 0.003909  loss: 2.7160 (2.7363)  weight_decay: 0.0500 (0.0500)  time: 1.0022  data: 0.0001  max mem: 78493
Epoch: [46]  [310/312]  eta: 0:00:02  lr: 0.003909  min_lr: 0.003909  loss: 2.7320 (2.7339)  weight_decay: 0.0500 (0.0500)  time: 1.0018  data: 0.0001  max mem: 78493
Epoch: [46]  [311/312]  eta: 0:00:01  lr: 0.003909  min_lr: 0.003909  loss: 2.7623 (2.7345)  weight_decay: 0.0500 (0.0500)  time: 1.0018  data: 0.0001  max mem: 78493
Epoch: [46] Total time: 0:05:32 (1.0673 s / it)
Averaged stats: lr: 0.003909  min_lr: 0.003909  loss: 2.7623 (2.6748)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:15  loss: 0.9984 (0.9984)  acc1: 76.4323 (76.4323)  acc5: 93.0990 (93.0990)  time: 8.3573  data: 8.0751  max mem: 78493
Test:  [8/9]  eta: 0:00:01  loss: 1.3804 (1.2340)  acc1: 69.0104 (69.7760)  acc5: 88.9323 (89.5040)  time: 1.1269  data: 0.8973  max mem: 78493
Test: Total time: 0:00:10 (1.1658 s / it)
* Acc@1 70.082 Acc@5 89.736 loss 1.223
Accuracy of the model on the 50000 test images: 70.1%
Max accuracy: 70.45%
Epoch: [47]  [  0/312]  eta: 1:19:54  lr: 0.003909  min_lr: 0.003909  loss: 2.8019 (2.8019)  weight_decay: 0.0500 (0.0500)  time: 15.3675  data: 11.2771  max mem: 78493
Epoch: [47]  [ 10/312]  eta: 0:13:19  lr: 0.003909  min_lr: 0.003909  loss: 2.6307 (2.6075)  weight_decay: 0.0500 (0.0500)  time: 2.6489  data: 1.2344  max mem: 78493
Epoch: [47]  [ 20/312]  eta: 0:09:08  lr: 0.003909  min_lr: 0.003909  loss: 2.6224 (2.5304)  weight_decay: 0.0500 (0.0500)  time: 1.2031  data: 0.1153  max mem: 78493
Epoch: [47]  [ 30/312]  eta: 0:07:30  lr: 0.003908  min_lr: 0.003908  loss: 2.3246 (2.4626)  weight_decay: 0.0500 (0.0500)  time: 1.0175  data: 0.0005  max mem: 78493
Epoch: [47]  [ 40/312]  eta: 0:06:35  lr: 0.003908  min_lr: 0.003908  loss: 2.3386 (2.4790)  weight_decay: 0.0500 (0.0500)  time: 1.0092  data: 0.0005  max mem: 78493
Epoch: [47]  [ 50/312]  eta: 0:05:58  lr: 0.003908  min_lr: 0.003908  loss: 2.6533 (2.5053)  weight_decay: 0.0500 (0.0500)  time: 1.0099  data: 0.0005  max mem: 78493
Epoch: [47]  [ 60/312]  eta: 0:05:29  lr: 0.003908  min_lr: 0.003908  loss: 2.6533 (2.5150)  weight_decay: 0.0500 (0.0500)  time: 1.0067  data: 0.0004  max mem: 78493
Epoch: [47]  [ 70/312]  eta: 0:05:06  lr: 0.003907  min_lr: 0.003907  loss: 2.7008 (2.5313)  weight_decay: 0.0500 (0.0500)  time: 1.0071  data: 0.0004  max mem: 78493
Epoch: [47]  [ 80/312]  eta: 0:04:46  lr: 0.003907  min_lr: 0.003907  loss: 2.7845 (2.5451)  weight_decay: 0.0500 (0.0500)  time: 1.0072  data: 0.0004  max mem: 78493
Epoch: [47]  [ 90/312]  eta: 0:04:28  lr: 0.003907  min_lr: 0.003907  loss: 2.6957 (2.5571)  weight_decay: 0.0500 (0.0500)  time: 1.0058  data: 0.0004  max mem: 78493
Epoch: [47]  [100/312]  eta: 0:04:11  lr: 0.003907  min_lr: 0.003907  loss: 2.7118 (2.5563)  weight_decay: 0.0500 (0.0500)  time: 1.0083  data: 0.0016  max mem: 78493
Epoch: [47]  [110/312]  eta: 0:03:56  lr: 0.003907  min_lr: 0.003907  loss: 2.5056 (2.5478)  weight_decay: 0.0500 (0.0500)  time: 1.0091  data: 0.0017  max mem: 78493
Epoch: [47]  [120/312]  eta: 0:03:42  lr: 0.003906  min_lr: 0.003906  loss: 2.5056 (2.5459)  weight_decay: 0.0500 (0.0500)  time: 1.0058  data: 0.0005  max mem: 78493
Epoch: [47]  [130/312]  eta: 0:03:28  lr: 0.003906  min_lr: 0.003906  loss: 2.7466 (2.5719)  weight_decay: 0.0500 (0.0500)  time: 1.0048  data: 0.0005  max mem: 78493
Epoch: [47]  [140/312]  eta: 0:03:15  lr: 0.003906  min_lr: 0.003906  loss: 2.8214 (2.5844)  weight_decay: 0.0500 (0.0500)  time: 1.0044  data: 0.0005  max mem: 78493
Epoch: [47]  [150/312]  eta: 0:03:02  lr: 0.003906  min_lr: 0.003906  loss: 2.7647 (2.5898)  weight_decay: 0.0500 (0.0500)  time: 1.0042  data: 0.0004  max mem: 78493
Epoch: [47]  [160/312]  eta: 0:02:50  lr: 0.003905  min_lr: 0.003905  loss: 2.3941 (2.5783)  weight_decay: 0.0500 (0.0500)  time: 1.0054  data: 0.0005  max mem: 78493
Epoch: [47]  [170/312]  eta: 0:02:38  lr: 0.003905  min_lr: 0.003905  loss: 2.5481 (2.5936)  weight_decay: 0.0500 (0.0500)  time: 1.0068  data: 0.0004  max mem: 78493
Epoch: [47]  [180/312]  eta: 0:02:26  lr: 0.003905  min_lr: 0.003905  loss: 2.8426 (2.6051)  weight_decay: 0.0500 (0.0500)  time: 1.0082  data: 0.0004  max mem: 78493
Epoch: [47]  [190/312]  eta: 0:02:14  lr: 0.003905  min_lr: 0.003905  loss: 2.8370 (2.6124)  weight_decay: 0.0500 (0.0500)  time: 1.0077  data: 0.0004  max mem: 78493
Epoch: [47]  [200/312]  eta: 0:02:02  lr: 0.003905  min_lr: 0.003905  loss: 2.7929 (2.6167)  weight_decay: 0.0500 (0.0500)  time: 1.0065  data: 0.0004  max mem: 78493
Epoch: [47]  [210/312]  eta: 0:01:51  lr: 0.003904  min_lr: 0.003904  loss: 2.7503 (2.6196)  weight_decay: 0.0500 (0.0500)  time: 1.0058  data: 0.0004  max mem: 78493
Epoch: [47]  [220/312]  eta: 0:01:40  lr: 0.003904  min_lr: 0.003904  loss: 2.7503 (2.6209)  weight_decay: 0.0500 (0.0500)  time: 1.0054  data: 0.0005  max mem: 78493
Epoch: [47]  [230/312]  eta: 0:01:29  lr: 0.003904  min_lr: 0.003904  loss: 2.7947 (2.6201)  weight_decay: 0.0500 (0.0500)  time: 1.0051  data: 0.0015  max mem: 78493
Epoch: [47]  [240/312]  eta: 0:01:17  lr: 0.003904  min_lr: 0.003904  loss: 2.8359 (2.6214)  weight_decay: 0.0500 (0.0500)  time: 1.0049  data: 0.0014  max mem: 78493
Epoch: [47]  [250/312]  eta: 0:01:06  lr: 0.003904  min_lr: 0.003904  loss: 2.9200 (2.6310)  weight_decay: 0.0500 (0.0500)  time: 1.0056  data: 0.0004  max mem: 78493
Epoch: [47]  [260/312]  eta: 0:00:55  lr: 0.003903  min_lr: 0.003903  loss: 2.8373 (2.6305)  weight_decay: 0.0500 (0.0500)  time: 1.0067  data: 0.0004  max mem: 78493
Epoch: [47]  [270/312]  eta: 0:00:45  lr: 0.003903  min_lr: 0.003903  loss: 2.6226 (2.6250)  weight_decay: 0.0500 (0.0500)  time: 1.0067  data: 0.0004  max mem: 78493
Epoch: [47]  [280/312]  eta: 0:00:34  lr: 0.003903  min_lr: 0.003903  loss: 2.6226 (2.6269)  weight_decay: 0.0500 (0.0500)  time: 1.0072  data: 0.0010  max mem: 78493
Epoch: [47]  [290/312]  eta: 0:00:23  lr: 0.003903  min_lr: 0.003903  loss: 2.7666 (2.6301)  weight_decay: 0.0500 (0.0500)  time: 1.0052  data: 0.0009  max mem: 78493
Epoch: [47]  [300/312]  eta: 0:00:12  lr: 0.003902  min_lr: 0.003902  loss: 2.7176 (2.6332)  weight_decay: 0.0500 (0.0500)  time: 1.0016  data: 0.0001  max mem: 78493
Epoch: [47]  [310/312]  eta: 0:00:02  lr: 0.003902  min_lr: 0.003902  loss: 2.5566 (2.6267)  weight_decay: 0.0500 (0.0500)  time: 1.0019  data: 0.0001  max mem: 78493
Epoch: [47]  [311/312]  eta: 0:00:01  lr: 0.003902  min_lr: 0.003902  loss: 2.5566 (2.6287)  weight_decay: 0.0500 (0.0500)  time: 1.0019  data: 0.0001  max mem: 78493
Epoch: [47] Total time: 0:05:33 (1.0702 s / it)
Averaged stats: lr: 0.003902  min_lr: 0.003902  loss: 2.5566 (2.6577)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:18  loss: 1.0072 (1.0072)  acc1: 76.4323 (76.4323)  acc5: 92.0573 (92.0573)  time: 8.6772  data: 8.4053  max mem: 78493
Test:  [8/9]  eta: 0:00:01  loss: 1.3092 (1.2506)  acc1: 69.4010 (69.7440)  acc5: 88.6719 (89.2160)  time: 1.1624  data: 0.9340  max mem: 78493
Test: Total time: 0:00:10 (1.1912 s / it)
* Acc@1 70.150 Acc@5 89.378 loss 1.230
Accuracy of the model on the 50000 test images: 70.2%
Max accuracy: 70.45%
Epoch: [48]  [  0/312]  eta: 1:26:02  lr: 0.003902  min_lr: 0.003902  loss: 2.5640 (2.5640)  weight_decay: 0.0500 (0.0500)  time: 16.5457  data: 14.3005  max mem: 78493
Epoch: [48]  [ 10/312]  eta: 0:13:35  lr: 0.003902  min_lr: 0.003902  loss: 2.8171 (2.6845)  weight_decay: 0.0500 (0.0500)  time: 2.7004  data: 1.3009  max mem: 78493
Epoch: [48]  [ 20/312]  eta: 0:09:14  lr: 0.003902  min_lr: 0.003902  loss: 2.8171 (2.6835)  weight_decay: 0.0500 (0.0500)  time: 1.1660  data: 0.0008  max mem: 78493
Epoch: [48]  [ 30/312]  eta: 0:07:34  lr: 0.003901  min_lr: 0.003901  loss: 2.7948 (2.7250)  weight_decay: 0.0500 (0.0500)  time: 1.0128  data: 0.0005  max mem: 78493
Epoch: [48]  [ 40/312]  eta: 0:06:38  lr: 0.003901  min_lr: 0.003901  loss: 2.8111 (2.6992)  weight_decay: 0.0500 (0.0500)  time: 1.0085  data: 0.0005  max mem: 78493
Epoch: [48]  [ 50/312]  eta: 0:06:00  lr: 0.003901  min_lr: 0.003901  loss: 2.6409 (2.6749)  weight_decay: 0.0500 (0.0500)  time: 1.0082  data: 0.0005  max mem: 78493
Epoch: [48]  [ 60/312]  eta: 0:05:31  lr: 0.003901  min_lr: 0.003901  loss: 2.6409 (2.6709)  weight_decay: 0.0500 (0.0500)  time: 1.0095  data: 0.0004  max mem: 78493
Epoch: [48]  [ 70/312]  eta: 0:05:07  lr: 0.003901  min_lr: 0.003901  loss: 2.6750 (2.6580)  weight_decay: 0.0500 (0.0500)  time: 1.0089  data: 0.0004  max mem: 78493
Epoch: [48]  [ 80/312]  eta: 0:04:47  lr: 0.003900  min_lr: 0.003900  loss: 2.5254 (2.6393)  weight_decay: 0.0500 (0.0500)  time: 1.0070  data: 0.0005  max mem: 78493
Epoch: [48]  [ 90/312]  eta: 0:04:29  lr: 0.003900  min_lr: 0.003900  loss: 2.4078 (2.6182)  weight_decay: 0.0500 (0.0500)  time: 1.0070  data: 0.0004  max mem: 78493
Epoch: [48]  [100/312]  eta: 0:04:12  lr: 0.003900  min_lr: 0.003900  loss: 2.7083 (2.6279)  weight_decay: 0.0500 (0.0500)  time: 1.0066  data: 0.0004  max mem: 78493
Epoch: [48]  [110/312]  eta: 0:03:57  lr: 0.003900  min_lr: 0.003900  loss: 2.6743 (2.6217)  weight_decay: 0.0500 (0.0500)  time: 1.0063  data: 0.0005  max mem: 78493
Epoch: [48]  [120/312]  eta: 0:03:43  lr: 0.003899  min_lr: 0.003899  loss: 2.6987 (2.6410)  weight_decay: 0.0500 (0.0500)  time: 1.0096  data: 0.0005  max mem: 78493
Epoch: [48]  [130/312]  eta: 0:03:29  lr: 0.003899  min_lr: 0.003899  loss: 2.7127 (2.6284)  weight_decay: 0.0500 (0.0500)  time: 1.0088  data: 0.0005  max mem: 78493
Epoch: [48]  [140/312]  eta: 0:03:16  lr: 0.003899  min_lr: 0.003899  loss: 2.8511 (2.6446)  weight_decay: 0.0500 (0.0500)  time: 1.0077  data: 0.0005  max mem: 78493
Epoch: [48]  [150/312]  eta: 0:03:03  lr: 0.003899  min_lr: 0.003899  loss: 2.8511 (2.6431)  weight_decay: 0.0500 (0.0500)  time: 1.0088  data: 0.0005  max mem: 78493
Epoch: [48]  [160/312]  eta: 0:02:50  lr: 0.003899  min_lr: 0.003899  loss: 2.5062 (2.6339)  weight_decay: 0.0500 (0.0500)  time: 1.0092  data: 0.0004  max mem: 78493
Epoch: [48]  [170/312]  eta: 0:02:38  lr: 0.003898  min_lr: 0.003898  loss: 2.6831 (2.6452)  weight_decay: 0.0500 (0.0500)  time: 1.0094  data: 0.0005  max mem: 78493
Epoch: [48]  [180/312]  eta: 0:02:26  lr: 0.003898  min_lr: 0.003898  loss: 2.8061 (2.6530)  weight_decay: 0.0500 (0.0500)  time: 1.0089  data: 0.0005  max mem: 78493
Epoch: [48]  [190/312]  eta: 0:02:14  lr: 0.003898  min_lr: 0.003898  loss: 2.7364 (2.6549)  weight_decay: 0.0500 (0.0500)  time: 1.0092  data: 0.0004  max mem: 78493
Epoch: [48]  [200/312]  eta: 0:02:03  lr: 0.003898  min_lr: 0.003898  loss: 2.7272 (2.6564)  weight_decay: 0.0500 (0.0500)  time: 1.0091  data: 0.0004  max mem: 78493
Epoch: [48]  [210/312]  eta: 0:01:51  lr: 0.003897  min_lr: 0.003897  loss: 2.8355 (2.6619)  weight_decay: 0.0500 (0.0500)  time: 1.0073  data: 0.0004  max mem: 78493
Epoch: [48]  [220/312]  eta: 0:01:40  lr: 0.003897  min_lr: 0.003897  loss: 2.8242 (2.6580)  weight_decay: 0.0500 (0.0500)  time: 1.0066  data: 0.0004  max mem: 78493
Epoch: [48]  [230/312]  eta: 0:01:29  lr: 0.003897  min_lr: 0.003897  loss: 2.5781 (2.6557)  weight_decay: 0.0500 (0.0500)  time: 1.0067  data: 0.0004  max mem: 78493
Epoch: [48]  [240/312]  eta: 0:01:18  lr: 0.003897  min_lr: 0.003897  loss: 2.6248 (2.6560)  weight_decay: 0.0500 (0.0500)  time: 1.0058  data: 0.0005  max mem: 78493
Epoch: [48]  [250/312]  eta: 0:01:07  lr: 0.003897  min_lr: 0.003897  loss: 2.8051 (2.6593)  weight_decay: 0.0500 (0.0500)  time: 1.0065  data: 0.0005  max mem: 78493
Epoch: [48]  [260/312]  eta: 0:00:56  lr: 0.003896  min_lr: 0.003896  loss: 2.7459 (2.6602)  weight_decay: 0.0500 (0.0500)  time: 1.0060  data: 0.0005  max mem: 78493
Epoch: [48]  [270/312]  eta: 0:00:45  lr: 0.003896  min_lr: 0.003896  loss: 2.7904 (2.6637)  weight_decay: 0.0500 (0.0500)  time: 1.0050  data: 0.0004  max mem: 78493
Epoch: [48]  [280/312]  eta: 0:00:34  lr: 0.003896  min_lr: 0.003896  loss: 2.8276 (2.6634)  weight_decay: 0.0500 (0.0500)  time: 1.0054  data: 0.0011  max mem: 78493
Epoch: [48]  [290/312]  eta: 0:00:23  lr: 0.003896  min_lr: 0.003896  loss: 2.7469 (2.6626)  weight_decay: 0.0500 (0.0500)  time: 1.0039  data: 0.0009  max mem: 78493
Epoch: [48]  [300/312]  eta: 0:00:12  lr: 0.003895  min_lr: 0.003895  loss: 2.8179 (2.6684)  weight_decay: 0.0500 (0.0500)  time: 1.0014  data: 0.0001  max mem: 78493
Epoch: [48]  [310/312]  eta: 0:00:02  lr: 0.003895  min_lr: 0.003895  loss: 2.8416 (2.6674)  weight_decay: 0.0500 (0.0500)  time: 1.0015  data: 0.0001  max mem: 78493
Epoch: [48]  [311/312]  eta: 0:00:01  lr: 0.003895  min_lr: 0.003895  loss: 2.8309 (2.6666)  weight_decay: 0.0500 (0.0500)  time: 1.0015  data: 0.0001  max mem: 78493
Epoch: [48] Total time: 0:05:34 (1.0729 s / it)
Averaged stats: lr: 0.003895  min_lr: 0.003895  loss: 2.8309 (2.6659)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:18  loss: 1.0248 (1.0248)  acc1: 76.9531 (76.9531)  acc5: 92.9688 (92.9688)  time: 8.6749  data: 8.3997  max mem: 78493
Test:  [8/9]  eta: 0:00:01  loss: 1.3693 (1.2518)  acc1: 67.0573 (69.6320)  acc5: 87.7604 (88.9280)  time: 1.1647  data: 0.9354  max mem: 78493
Test: Total time: 0:00:10 (1.1937 s / it)
* Acc@1 69.604 Acc@5 89.212 loss 1.253
Accuracy of the model on the 50000 test images: 69.6%
Max accuracy: 70.45%
Epoch: [49]  [  0/312]  eta: 1:19:18  lr: 0.003895  min_lr: 0.003895  loss: 2.9076 (2.9076)  weight_decay: 0.0500 (0.0500)  time: 15.2500  data: 13.1641  max mem: 78493
Epoch: [49]  [ 10/312]  eta: 0:12:45  lr: 0.003895  min_lr: 0.003895  loss: 2.7666 (2.7512)  weight_decay: 0.0500 (0.0500)  time: 2.5344  data: 1.2629  max mem: 78493
Epoch: [49]  [ 20/312]  eta: 0:08:53  lr: 0.003895  min_lr: 0.003895  loss: 2.6349 (2.5981)  weight_decay: 0.0500 (0.0500)  time: 1.1554  data: 0.0388  max mem: 78493
Epoch: [49]  [ 30/312]  eta: 0:07:20  lr: 0.003894  min_lr: 0.003894  loss: 2.6349 (2.6170)  weight_decay: 0.0500 (0.0500)  time: 1.0286  data: 0.0027  max mem: 78493
Epoch: [49]  [ 40/312]  eta: 0:06:28  lr: 0.003894  min_lr: 0.003894  loss: 2.6888 (2.5702)  weight_decay: 0.0500 (0.0500)  time: 1.0088  data: 0.0004  max mem: 78493
Epoch: [49]  [ 50/312]  eta: 0:05:52  lr: 0.003894  min_lr: 0.003894  loss: 2.5291 (2.5739)  weight_decay: 0.0500 (0.0500)  time: 1.0076  data: 0.0005  max mem: 78493
Epoch: [49]  [ 60/312]  eta: 0:05:24  lr: 0.003894  min_lr: 0.003894  loss: 2.5291 (2.5703)  weight_decay: 0.0500 (0.0500)  time: 1.0065  data: 0.0004  max mem: 78493
Epoch: [49]  [ 70/312]  eta: 0:05:02  lr: 0.003893  min_lr: 0.003893  loss: 2.7929 (2.6210)  weight_decay: 0.0500 (0.0500)  time: 1.0074  data: 0.0004  max mem: 78493
Epoch: [49]  [ 80/312]  eta: 0:04:43  lr: 0.003893  min_lr: 0.003893  loss: 2.7971 (2.6266)  weight_decay: 0.0500 (0.0500)  time: 1.0080  data: 0.0004  max mem: 78493
Epoch: [49]  [ 90/312]  eta: 0:04:25  lr: 0.003893  min_lr: 0.003893  loss: 2.7430 (2.6410)  weight_decay: 0.0500 (0.0500)  time: 1.0060  data: 0.0005  max mem: 78493
Epoch: [49]  [100/312]  eta: 0:04:09  lr: 0.003893  min_lr: 0.003893  loss: 2.7735 (2.6449)  weight_decay: 0.0500 (0.0500)  time: 1.0050  data: 0.0005  max mem: 78493
Epoch: [49]  [110/312]  eta: 0:03:54  lr: 0.003893  min_lr: 0.003893  loss: 2.5364 (2.6202)  weight_decay: 0.0500 (0.0500)  time: 1.0045  data: 0.0006  max mem: 78493
Epoch: [49]  [120/312]  eta: 0:03:40  lr: 0.003892  min_lr: 0.003892  loss: 2.3715 (2.6183)  weight_decay: 0.0500 (0.0500)  time: 1.0045  data: 0.0006  max mem: 78493
Epoch: [49]  [130/312]  eta: 0:03:27  lr: 0.003892  min_lr: 0.003892  loss: 2.5887 (2.6251)  weight_decay: 0.0500 (0.0500)  time: 1.0051  data: 0.0004  max mem: 78493
Epoch: [49]  [140/312]  eta: 0:03:14  lr: 0.003892  min_lr: 0.003892  loss: 2.5887 (2.6135)  weight_decay: 0.0500 (0.0500)  time: 1.0042  data: 0.0005  max mem: 78493
Epoch: [49]  [150/312]  eta: 0:03:01  lr: 0.003892  min_lr: 0.003892  loss: 2.4578 (2.6168)  weight_decay: 0.0500 (0.0500)  time: 1.0044  data: 0.0004  max mem: 78493
Epoch: [49]  [160/312]  eta: 0:02:49  lr: 0.003891  min_lr: 0.003891  loss: 2.7150 (2.6245)  weight_decay: 0.0500 (0.0500)  time: 1.0058  data: 0.0004  max mem: 78493
Epoch: [49]  [170/312]  eta: 0:02:37  lr: 0.003891  min_lr: 0.003891  loss: 2.7460 (2.6167)  weight_decay: 0.0500 (0.0500)  time: 1.0054  data: 0.0005  max mem: 78493
Epoch: [49]  [180/312]  eta: 0:02:25  lr: 0.003891  min_lr: 0.003891  loss: 2.4827 (2.6112)  weight_decay: 0.0500 (0.0500)  time: 1.0052  data: 0.0004  max mem: 78493
Epoch: [49]  [190/312]  eta: 0:02:13  lr: 0.003891  min_lr: 0.003891  loss: 2.4827 (2.6069)  weight_decay: 0.0500 (0.0500)  time: 1.0059  data: 0.0004  max mem: 78493
Epoch: [49]  [200/312]  eta: 0:02:02  lr: 0.003890  min_lr: 0.003890  loss: 2.6009 (2.6170)  weight_decay: 0.0500 (0.0500)  time: 1.0055  data: 0.0005  max mem: 78493
Epoch: [49]  [210/312]  eta: 0:01:50  lr: 0.003890  min_lr: 0.003890  loss: 2.8695 (2.6270)  weight_decay: 0.0500 (0.0500)  time: 1.0048  data: 0.0005  max mem: 78493
Epoch: [49]  [220/312]  eta: 0:01:39  lr: 0.003890  min_lr: 0.003890  loss: 2.8380 (2.6246)  weight_decay: 0.0500 (0.0500)  time: 1.0048  data: 0.0004  max mem: 78493
Epoch: [49]  [230/312]  eta: 0:01:28  lr: 0.003890  min_lr: 0.003890  loss: 2.8277 (2.6316)  weight_decay: 0.0500 (0.0500)  time: 1.0045  data: 0.0004  max mem: 78493
Epoch: [49]  [240/312]  eta: 0:01:17  lr: 0.003889  min_lr: 0.003889  loss: 2.8637 (2.6366)  weight_decay: 0.0500 (0.0500)  time: 1.0048  data: 0.0004  max mem: 78493
Epoch: [49]  [250/312]  eta: 0:01:06  lr: 0.003889  min_lr: 0.003889  loss: 2.7830 (2.6361)  weight_decay: 0.0500 (0.0500)  time: 1.0060  data: 0.0005  max mem: 78493
Epoch: [49]  [260/312]  eta: 0:00:55  lr: 0.003889  min_lr: 0.003889  loss: 2.8010 (2.6406)  weight_decay: 0.0500 (0.0500)  time: 1.0046  data: 0.0005  max mem: 78493
Epoch: [49]  [270/312]  eta: 0:00:44  lr: 0.003889  min_lr: 0.003889  loss: 2.7828 (2.6392)  weight_decay: 0.0500 (0.0500)  time: 1.0037  data: 0.0005  max mem: 78493
Epoch: [49]  [280/312]  eta: 0:00:34  lr: 0.003889  min_lr: 0.003889  loss: 2.8220 (2.6477)  weight_decay: 0.0500 (0.0500)  time: 1.0053  data: 0.0010  max mem: 78493
Epoch: [49]  [290/312]  eta: 0:00:23  lr: 0.003888  min_lr: 0.003888  loss: 2.8871 (2.6534)  weight_decay: 0.0500 (0.0500)  time: 1.0038  data: 0.0009  max mem: 78493
Epoch: [49]  [300/312]  eta: 0:00:12  lr: 0.003888  min_lr: 0.003888  loss: 2.7592 (2.6471)  weight_decay: 0.0500 (0.0500)  time: 1.0021  data: 0.0001  max mem: 78493
Epoch: [49]  [310/312]  eta: 0:00:02  lr: 0.003888  min_lr: 0.003888  loss: 2.3743 (2.6442)  weight_decay: 0.0500 (0.0500)  time: 1.0021  data: 0.0001  max mem: 78493
Epoch: [49]  [311/312]  eta: 0:00:01  lr: 0.003888  min_lr: 0.003888  loss: 2.5438 (2.6451)  weight_decay: 0.0500 (0.0500)  time: 1.0021  data: 0.0001  max mem: 78493
Epoch: [49] Total time: 0:05:32 (1.0661 s / it)
Averaged stats: lr: 0.003888  min_lr: 0.003888  loss: 2.5438 (2.6519)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:06  loss: 0.9480 (0.9480)  acc1: 77.0833 (77.0833)  acc5: 92.9688 (92.9688)  time: 7.3890  data: 7.1074  max mem: 78493
Test:  [8/9]  eta: 0:00:01  loss: 1.2589 (1.2089)  acc1: 69.7917 (70.4320)  acc5: 90.2344 (90.0480)  time: 1.0708  data: 0.8414  max mem: 78493
Test: Total time: 0:00:09 (1.0812 s / it)
* Acc@1 70.704 Acc@5 89.730 loss 1.212
Accuracy of the model on the 50000 test images: 70.7%
Max accuracy: 70.70%
Epoch: [50]  [  0/312]  eta: 1:19:20  lr: 0.003888  min_lr: 0.003888  loss: 2.5056 (2.5056)  weight_decay: 0.0500 (0.0500)  time: 15.2594  data: 13.3697  max mem: 78493
Epoch: [50]  [ 10/312]  eta: 0:12:37  lr: 0.003888  min_lr: 0.003888  loss: 2.5860 (2.5732)  weight_decay: 0.0500 (0.0500)  time: 2.5094  data: 1.2161  max mem: 78493
Epoch: [50]  [ 20/312]  eta: 0:08:45  lr: 0.003887  min_lr: 0.003887  loss: 2.7395 (2.6667)  weight_decay: 0.0500 (0.0500)  time: 1.1284  data: 0.0007  max mem: 78493
Epoch: [50]  [ 30/312]  eta: 0:07:15  lr: 0.003887  min_lr: 0.003887  loss: 2.7715 (2.6957)  weight_decay: 0.0500 (0.0500)  time: 1.0156  data: 0.0005  max mem: 78493
Epoch: [50]  [ 40/312]  eta: 0:06:24  lr: 0.003887  min_lr: 0.003887  loss: 2.5994 (2.6766)  weight_decay: 0.0500 (0.0500)  time: 1.0079  data: 0.0004  max mem: 78493
Epoch: [50]  [ 50/312]  eta: 0:05:49  lr: 0.003887  min_lr: 0.003887  loss: 2.4749 (2.6297)  weight_decay: 0.0500 (0.0500)  time: 1.0074  data: 0.0005  max mem: 78493
Epoch: [50]  [ 60/312]  eta: 0:05:22  lr: 0.003886  min_lr: 0.003886  loss: 2.6253 (2.6538)  weight_decay: 0.0500 (0.0500)  time: 1.0083  data: 0.0005  max mem: 78493
Epoch: [50]  [ 70/312]  eta: 0:05:00  lr: 0.003886  min_lr: 0.003886  loss: 2.8130 (2.6500)  weight_decay: 0.0500 (0.0500)  time: 1.0095  data: 0.0004  max mem: 78493
Epoch: [50]  [ 80/312]  eta: 0:04:41  lr: 0.003886  min_lr: 0.003886  loss: 2.6929 (2.6471)  weight_decay: 0.0500 (0.0500)  time: 1.0094  data: 0.0004  max mem: 78493
Epoch: [50]  [ 90/312]  eta: 0:04:24  lr: 0.003886  min_lr: 0.003886  loss: 2.5069 (2.6302)  weight_decay: 0.0500 (0.0500)  time: 1.0100  data: 0.0005  max mem: 78493
Epoch: [50]  [100/312]  eta: 0:04:08  lr: 0.003885  min_lr: 0.003885  loss: 2.6776 (2.6319)  weight_decay: 0.0500 (0.0500)  time: 1.0097  data: 0.0004  max mem: 78493
Epoch: [50]  [110/312]  eta: 0:03:54  lr: 0.003885  min_lr: 0.003885  loss: 2.7760 (2.6448)  weight_decay: 0.0500 (0.0500)  time: 1.0080  data: 0.0004  max mem: 78493
Epoch: [50]  [120/312]  eta: 0:03:40  lr: 0.003885  min_lr: 0.003885  loss: 2.8264 (2.6520)  weight_decay: 0.0500 (0.0500)  time: 1.0072  data: 0.0004  max mem: 78493
Epoch: [50]  [130/312]  eta: 0:03:26  lr: 0.003885  min_lr: 0.003885  loss: 2.6217 (2.6395)  weight_decay: 0.0500 (0.0500)  time: 1.0067  data: 0.0005  max mem: 78493
Epoch: [50]  [140/312]  eta: 0:03:13  lr: 0.003884  min_lr: 0.003884  loss: 2.6217 (2.6433)  weight_decay: 0.0500 (0.0500)  time: 1.0093  data: 0.0005  max mem: 78493
Epoch: [50]  [150/312]  eta: 0:03:01  lr: 0.003884  min_lr: 0.003884  loss: 2.7847 (2.6536)  weight_decay: 0.0500 (0.0500)  time: 1.0093  data: 0.0004  max mem: 78493
Epoch: [50]  [160/312]  eta: 0:02:49  lr: 0.003884  min_lr: 0.003884  loss: 2.7847 (2.6608)  weight_decay: 0.0500 (0.0500)  time: 1.0090  data: 0.0004  max mem: 78493
Epoch: [50]  [170/312]  eta: 0:02:37  lr: 0.003884  min_lr: 0.003884  loss: 2.7202 (2.6559)  weight_decay: 0.0500 (0.0500)  time: 1.0106  data: 0.0004  max mem: 78493
Epoch: [50]  [180/312]  eta: 0:02:25  lr: 0.003883  min_lr: 0.003883  loss: 2.6436 (2.6477)  weight_decay: 0.0500 (0.0500)  time: 1.0102  data: 0.0004  max mem: 78493
Epoch: [50]  [190/312]  eta: 0:02:13  lr: 0.003883  min_lr: 0.003883  loss: 2.4454 (2.6455)  weight_decay: 0.0500 (0.0500)  time: 1.0096  data: 0.0004  max mem: 78493
Epoch: [50]  [200/312]  eta: 0:02:02  lr: 0.003883  min_lr: 0.003883  loss: 2.7532 (2.6540)  weight_decay: 0.0500 (0.0500)  time: 1.0107  data: 0.0005  max mem: 78493
Epoch: [50]  [210/312]  eta: 0:01:50  lr: 0.003883  min_lr: 0.003883  loss: 2.7532 (2.6517)  weight_decay: 0.0500 (0.0500)  time: 1.0104  data: 0.0004  max mem: 78493
Epoch: [50]  [220/312]  eta: 0:01:39  lr: 0.003883  min_lr: 0.003883  loss: 2.7257 (2.6569)  weight_decay: 0.0500 (0.0500)  time: 1.0075  data: 0.0004  max mem: 78493
Epoch: [50]  [230/312]  eta: 0:01:28  lr: 0.003882  min_lr: 0.003882  loss: 2.7257 (2.6600)  weight_decay: 0.0500 (0.0500)  time: 1.0063  data: 0.0004  max mem: 78493
Epoch: [50]  [240/312]  eta: 0:01:17  lr: 0.003882  min_lr: 0.003882  loss: 2.7354 (2.6643)  weight_decay: 0.0500 (0.0500)  time: 1.0063  data: 0.0004  max mem: 78493
Epoch: [50]  [250/312]  eta: 0:01:06  lr: 0.003882  min_lr: 0.003882  loss: 2.7649 (2.6623)  weight_decay: 0.0500 (0.0500)  time: 1.0057  data: 0.0004  max mem: 78493
Epoch: [50]  [260/312]  eta: 0:00:55  lr: 0.003882  min_lr: 0.003882  loss: 2.8640 (2.6669)  weight_decay: 0.0500 (0.0500)  time: 1.0043  data: 0.0005  max mem: 78493
Epoch: [50]  [270/312]  eta: 0:00:44  lr: 0.003881  min_lr: 0.003881  loss: 2.8294 (2.6674)  weight_decay: 0.0500 (0.0500)  time: 1.0052  data: 0.0005  max mem: 78493
Epoch: [50]  [280/312]  eta: 0:00:34  lr: 0.003881  min_lr: 0.003881  loss: 2.8289 (2.6742)  weight_decay: 0.0500 (0.0500)  time: 1.0059  data: 0.0010  max mem: 78493
Epoch: [50]  [290/312]  eta: 0:00:23  lr: 0.003881  min_lr: 0.003881  loss: 2.8340 (2.6746)  weight_decay: 0.0500 (0.0500)  time: 1.0036  data: 0.0009  max mem: 78493
Epoch: [50]  [300/312]  eta: 0:00:12  lr: 0.003881  min_lr: 0.003881  loss: 2.8436 (2.6772)  weight_decay: 0.0500 (0.0500)  time: 1.0018  data: 0.0001  max mem: 78493
Epoch: [50]  [310/312]  eta: 0:00:02  lr: 0.003880  min_lr: 0.003880  loss: 2.8551 (2.6740)  weight_decay: 0.0500 (0.0500)  time: 1.0017  data: 0.0001  max mem: 78493
Epoch: [50]  [311/312]  eta: 0:00:01  lr: 0.003880  min_lr: 0.003880  loss: 2.5461 (2.6718)  weight_decay: 0.0500 (0.0500)  time: 1.0017  data: 0.0001  max mem: 78493
Epoch: [50] Total time: 0:05:32 (1.0668 s / it)
Averaged stats: lr: 0.003880  min_lr: 0.003880  loss: 2.5461 (2.6516)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:14  loss: 0.8788 (0.8788)  acc1: 77.9948 (77.9948)  acc5: 94.0104 (94.0104)  time: 8.2388  data: 7.9719  max mem: 78493
Test:  [8/9]  eta: 0:00:01  loss: 1.2933 (1.2018)  acc1: 69.2708 (70.3040)  acc5: 88.8021 (89.6320)  time: 1.1151  data: 0.8859  max mem: 78493
Test: Total time: 0:00:10 (1.1570 s / it)
* Acc@1 70.842 Acc@5 89.660 loss 1.190
Accuracy of the model on the 50000 test images: 70.8%
Max accuracy: 70.84%
Epoch: [51]  [  0/312]  eta: 1:21:25  lr: 0.003880  min_lr: 0.003880  loss: 2.9422 (2.9422)  weight_decay: 0.0500 (0.0500)  time: 15.6589  data: 13.0407  max mem: 78493
Epoch: [51]  [ 10/312]  eta: 0:12:17  lr: 0.003880  min_lr: 0.003880  loss: 2.6366 (2.5673)  weight_decay: 0.0500 (0.0500)  time: 2.4418  data: 1.1912  max mem: 78493
Epoch: [51]  [ 20/312]  eta: 0:08:37  lr: 0.003880  min_lr: 0.003880  loss: 2.2837 (2.4072)  weight_decay: 0.0500 (0.0500)  time: 1.0776  data: 0.0035  max mem: 78493
Epoch: [51]  [ 30/312]  eta: 0:07:10  lr: 0.003880  min_lr: 0.003880  loss: 2.5195 (2.4918)  weight_decay: 0.0500 (0.0500)  time: 1.0220  data: 0.0006  max mem: 78493
Epoch: [51]  [ 40/312]  eta: 0:06:20  lr: 0.003879  min_lr: 0.003879  loss: 2.6184 (2.4932)  weight_decay: 0.0500 (0.0500)  time: 1.0106  data: 0.0004  max mem: 78493
Epoch: [51]  [ 50/312]  eta: 0:05:46  lr: 0.003879  min_lr: 0.003879  loss: 2.6110 (2.5259)  weight_decay: 0.0500 (0.0500)  time: 1.0098  data: 0.0004  max mem: 78493
Epoch: [51]  [ 60/312]  eta: 0:05:20  lr: 0.003879  min_lr: 0.003879  loss: 2.8043 (2.5371)  weight_decay: 0.0500 (0.0500)  time: 1.0086  data: 0.0005  max mem: 78493
Epoch: [51]  [ 70/312]  eta: 0:04:58  lr: 0.003879  min_lr: 0.003879  loss: 2.7825 (2.5329)  weight_decay: 0.0500 (0.0500)  time: 1.0106  data: 0.0005  max mem: 78493
Epoch: [51]  [ 80/312]  eta: 0:04:40  lr: 0.003878  min_lr: 0.003878  loss: 2.4646 (2.5249)  weight_decay: 0.0500 (0.0500)  time: 1.0099  data: 0.0005  max mem: 78493
Epoch: [51]  [ 90/312]  eta: 0:04:23  lr: 0.003878  min_lr: 0.003878  loss: 2.6209 (2.5562)  weight_decay: 0.0500 (0.0500)  time: 1.0087  data: 0.0004  max mem: 78493
Epoch: [51]  [100/312]  eta: 0:04:07  lr: 0.003878  min_lr: 0.003878  loss: 2.6046 (2.5504)  weight_decay: 0.0500 (0.0500)  time: 1.0101  data: 0.0004  max mem: 78493
Epoch: [51]  [110/312]  eta: 0:03:53  lr: 0.003878  min_lr: 0.003878  loss: 2.5951 (2.5682)  weight_decay: 0.0500 (0.0500)  time: 1.0112  data: 0.0004  max mem: 78493
Epoch: [51]  [120/312]  eta: 0:03:39  lr: 0.003877  min_lr: 0.003877  loss: 2.7636 (2.5690)  weight_decay: 0.0500 (0.0500)  time: 1.0091  data: 0.0004  max mem: 78493
Epoch: [51]  [130/312]  eta: 0:03:25  lr: 0.003877  min_lr: 0.003877  loss: 2.7311 (2.5734)  weight_decay: 0.0500 (0.0500)  time: 1.0069  data: 0.0005  max mem: 78493
Epoch: [51]  [140/312]  eta: 0:03:13  lr: 0.003877  min_lr: 0.003877  loss: 2.7311 (2.5743)  weight_decay: 0.0500 (0.0500)  time: 1.0060  data: 0.0005  max mem: 78493
Epoch: [51]  [150/312]  eta: 0:03:00  lr: 0.003877  min_lr: 0.003877  loss: 2.5425 (2.5730)  weight_decay: 0.0500 (0.0500)  time: 1.0062  data: 0.0004  max mem: 78493
Epoch: [51]  [160/312]  eta: 0:02:48  lr: 0.003876  min_lr: 0.003876  loss: 2.7080 (2.5768)  weight_decay: 0.0500 (0.0500)  time: 1.0066  data: 0.0004  max mem: 78493
Epoch: [51]  [170/312]  eta: 0:02:36  lr: 0.003876  min_lr: 0.003876  loss: 2.7718 (2.5884)  weight_decay: 0.0500 (0.0500)  time: 1.0080  data: 0.0004  max mem: 78493
Epoch: [51]  [180/312]  eta: 0:02:24  lr: 0.003876  min_lr: 0.003876  loss: 2.7708 (2.5869)  weight_decay: 0.0500 (0.0500)  time: 1.0087  data: 0.0004  max mem: 78493
Epoch: [51]  [190/312]  eta: 0:02:13  lr: 0.003876  min_lr: 0.003876  loss: 2.7686 (2.5821)  weight_decay: 0.0500 (0.0500)  time: 1.0082  data: 0.0004  max mem: 78493
Epoch: [51]  [200/312]  eta: 0:02:01  lr: 0.003875  min_lr: 0.003875  loss: 2.5281 (2.5824)  weight_decay: 0.0500 (0.0500)  time: 1.0094  data: 0.0004  max mem: 78493
Epoch: [51]  [210/312]  eta: 0:01:50  lr: 0.003875  min_lr: 0.003875  loss: 2.5549 (2.5866)  weight_decay: 0.0500 (0.0500)  time: 1.0082  data: 0.0004  max mem: 78493
Epoch: [51]  [220/312]  eta: 0:01:39  lr: 0.003875  min_lr: 0.003875  loss: 2.6745 (2.5880)  weight_decay: 0.0500 (0.0500)  time: 1.0052  data: 0.0005  max mem: 78493
Epoch: [51]  [230/312]  eta: 0:01:28  lr: 0.003875  min_lr: 0.003875  loss: 2.7925 (2.5985)  weight_decay: 0.0500 (0.0500)  time: 1.0054  data: 0.0005  max mem: 78493
Epoch: [51]  [240/312]  eta: 0:01:17  lr: 0.003874  min_lr: 0.003874  loss: 2.8705 (2.6044)  weight_decay: 0.0500 (0.0500)  time: 1.0059  data: 0.0005  max mem: 78493
Epoch: [51]  [250/312]  eta: 0:01:06  lr: 0.003874  min_lr: 0.003874  loss: 2.6835 (2.6070)  weight_decay: 0.0500 (0.0500)  time: 1.0061  data: 0.0005  max mem: 78493
Epoch: [51]  [260/312]  eta: 0:00:55  lr: 0.003874  min_lr: 0.003874  loss: 2.6835 (2.6047)  weight_decay: 0.0500 (0.0500)  time: 1.0061  data: 0.0004  max mem: 78493
Epoch: [51]  [270/312]  eta: 0:00:44  lr: 0.003874  min_lr: 0.003874  loss: 2.4966 (2.5942)  weight_decay: 0.0500 (0.0500)  time: 1.0059  data: 0.0005  max mem: 78493
Epoch: [51]  [280/312]  eta: 0:00:34  lr: 0.003873  min_lr: 0.003873  loss: 2.4966 (2.5982)  weight_decay: 0.0500 (0.0500)  time: 1.0060  data: 0.0011  max mem: 78493
Epoch: [51]  [290/312]  eta: 0:00:23  lr: 0.003873  min_lr: 0.003873  loss: 2.8232 (2.6045)  weight_decay: 0.0500 (0.0500)  time: 1.0038  data: 0.0009  max mem: 78493
Epoch: [51]  [300/312]  eta: 0:00:12  lr: 0.003873  min_lr: 0.003873  loss: 2.7282 (2.6069)  weight_decay: 0.0500 (0.0500)  time: 1.0019  data: 0.0001  max mem: 78493
Epoch: [51]  [310/312]  eta: 0:00:02  lr: 0.003873  min_lr: 0.003873  loss: 2.8610 (2.6061)  weight_decay: 0.0500 (0.0500)  time: 1.0016  data: 0.0001  max mem: 78493
Epoch: [51]  [311/312]  eta: 0:00:01  lr: 0.003873  min_lr: 0.003873  loss: 2.8610 (2.6065)  weight_decay: 0.0500 (0.0500)  time: 1.0016  data: 0.0001  max mem: 78493
Epoch: [51] Total time: 0:05:32 (1.0643 s / it)
Averaged stats: lr: 0.003873  min_lr: 0.003873  loss: 2.8610 (2.6398)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:07  loss: 0.9500 (0.9500)  acc1: 76.0417 (76.0417)  acc5: 93.2292 (93.2292)  time: 7.4956  data: 7.2326  max mem: 78493
Test:  [8/9]  eta: 0:00:01  loss: 1.4067 (1.2519)  acc1: 68.0990 (69.0240)  acc5: 88.8021 (89.3280)  time: 1.0622  data: 0.8347  max mem: 78493
Test: Total time: 0:00:09 (1.0726 s / it)
* Acc@1 69.222 Acc@5 89.150 loss 1.258
Accuracy of the model on the 50000 test images: 69.2%
Max accuracy: 70.84%
Epoch: [52]  [  0/312]  eta: 1:24:23  lr: 0.003873  min_lr: 0.003873  loss: 2.6705 (2.6705)  weight_decay: 0.0500 (0.0500)  time: 16.2279  data: 15.2062  max mem: 78493
Epoch: [52]  [ 10/312]  eta: 0:13:07  lr: 0.003872  min_lr: 0.003872  loss: 2.6735 (2.5824)  weight_decay: 0.0500 (0.0500)  time: 2.6068  data: 1.3831  max mem: 78493
Epoch: [52]  [ 20/312]  eta: 0:09:00  lr: 0.003872  min_lr: 0.003872  loss: 2.6006 (2.5555)  weight_decay: 0.0500 (0.0500)  time: 1.1338  data: 0.0007  max mem: 78493
Epoch: [52]  [ 30/312]  eta: 0:07:25  lr: 0.003872  min_lr: 0.003872  loss: 2.4977 (2.5260)  weight_decay: 0.0500 (0.0500)  time: 1.0162  data: 0.0006  max mem: 78493
Epoch: [52]  [ 40/312]  eta: 0:06:31  lr: 0.003871  min_lr: 0.003871  loss: 2.6532 (2.5782)  weight_decay: 0.0500 (0.0500)  time: 1.0088  data: 0.0004  max mem: 78493
Epoch: [52]  [ 50/312]  eta: 0:05:55  lr: 0.003871  min_lr: 0.003871  loss: 2.7384 (2.5558)  weight_decay: 0.0500 (0.0500)  time: 1.0080  data: 0.0004  max mem: 78493
Epoch: [52]  [ 60/312]  eta: 0:05:27  lr: 0.003871  min_lr: 0.003871  loss: 2.7134 (2.5774)  weight_decay: 0.0500 (0.0500)  time: 1.0103  data: 0.0004  max mem: 78493
Epoch: [52]  [ 70/312]  eta: 0:05:04  lr: 0.003871  min_lr: 0.003871  loss: 2.6089 (2.5736)  weight_decay: 0.0500 (0.0500)  time: 1.0114  data: 0.0004  max mem: 78493
Epoch: [52]  [ 80/312]  eta: 0:04:44  lr: 0.003870  min_lr: 0.003870  loss: 2.5623 (2.5607)  weight_decay: 0.0500 (0.0500)  time: 1.0108  data: 0.0004  max mem: 78493
Epoch: [52]  [ 90/312]  eta: 0:04:27  lr: 0.003870  min_lr: 0.003870  loss: 2.6145 (2.5789)  weight_decay: 0.0500 (0.0500)  time: 1.0097  data: 0.0004  max mem: 78493
Epoch: [52]  [100/312]  eta: 0:04:11  lr: 0.003870  min_lr: 0.003870  loss: 2.6171 (2.5804)  weight_decay: 0.0500 (0.0500)  time: 1.0070  data: 0.0004  max mem: 78493
Epoch: [52]  [110/312]  eta: 0:03:56  lr: 0.003870  min_lr: 0.003870  loss: 2.5860 (2.5820)  weight_decay: 0.0500 (0.0500)  time: 1.0062  data: 0.0004  max mem: 78493
Epoch: [52]  [120/312]  eta: 0:03:41  lr: 0.003869  min_lr: 0.003869  loss: 2.6289 (2.5778)  weight_decay: 0.0500 (0.0500)  time: 1.0072  data: 0.0005  max mem: 78493
Epoch: [52]  [130/312]  eta: 0:03:28  lr: 0.003869  min_lr: 0.003869  loss: 2.4085 (2.5691)  weight_decay: 0.0500 (0.0500)  time: 1.0068  data: 0.0005  max mem: 78493
Epoch: [52]  [140/312]  eta: 0:03:15  lr: 0.003869  min_lr: 0.003869  loss: 2.6153 (2.5752)  weight_decay: 0.0500 (0.0500)  time: 1.0049  data: 0.0005  max mem: 78493
Epoch: [52]  [150/312]  eta: 0:03:02  lr: 0.003869  min_lr: 0.003869  loss: 2.7418 (2.5764)  weight_decay: 0.0500 (0.0500)  time: 1.0042  data: 0.0004  max mem: 78493
Epoch: [52]  [160/312]  eta: 0:02:49  lr: 0.003868  min_lr: 0.003868  loss: 2.5248 (2.5724)  weight_decay: 0.0500 (0.0500)  time: 1.0054  data: 0.0004  max mem: 78493
Epoch: [52]  [170/312]  eta: 0:02:37  lr: 0.003868  min_lr: 0.003868  loss: 2.5622 (2.5781)  weight_decay: 0.0500 (0.0500)  time: 1.0063  data: 0.0004  max mem: 78493
Epoch: [52]  [180/312]  eta: 0:02:25  lr: 0.003868  min_lr: 0.003868  loss: 2.5622 (2.5745)  weight_decay: 0.0500 (0.0500)  time: 1.0062  data: 0.0004  max mem: 78493
Epoch: [52]  [190/312]  eta: 0:02:14  lr: 0.003868  min_lr: 0.003868  loss: 2.7384 (2.5875)  weight_decay: 0.0500 (0.0500)  time: 1.0069  data: 0.0004  max mem: 78493
Epoch: [52]  [200/312]  eta: 0:02:02  lr: 0.003867  min_lr: 0.003867  loss: 2.5890 (2.5828)  weight_decay: 0.0500 (0.0500)  time: 1.0062  data: 0.0004  max mem: 78493
Epoch: [52]  [210/312]  eta: 0:01:51  lr: 0.003867  min_lr: 0.003867  loss: 2.4996 (2.5820)  weight_decay: 0.0500 (0.0500)  time: 1.0049  data: 0.0004  max mem: 78493
Epoch: [52]  [220/312]  eta: 0:01:40  lr: 0.003867  min_lr: 0.003867  loss: 2.6475 (2.5989)  weight_decay: 0.0500 (0.0500)  time: 1.0048  data: 0.0004  max mem: 78493
Epoch: [52]  [230/312]  eta: 0:01:28  lr: 0.003867  min_lr: 0.003867  loss: 2.6428 (2.5911)  weight_decay: 0.0500 (0.0500)  time: 1.0040  data: 0.0005  max mem: 78493
Epoch: [52]  [240/312]  eta: 0:01:17  lr: 0.003866  min_lr: 0.003866  loss: 2.5979 (2.5893)  weight_decay: 0.0500 (0.0500)  time: 1.0044  data: 0.0005  max mem: 78493
Epoch: [52]  [250/312]  eta: 0:01:06  lr: 0.003866  min_lr: 0.003866  loss: 2.6948 (2.5937)  weight_decay: 0.0500 (0.0500)  time: 1.0055  data: 0.0004  max mem: 78493
Epoch: [52]  [260/312]  eta: 0:00:55  lr: 0.003866  min_lr: 0.003866  loss: 2.6307 (2.5938)  weight_decay: 0.0500 (0.0500)  time: 1.0059  data: 0.0005  max mem: 78493
Epoch: [52]  [270/312]  eta: 0:00:45  lr: 0.003866  min_lr: 0.003866  loss: 2.6307 (2.5935)  weight_decay: 0.0500 (0.0500)  time: 1.0059  data: 0.0004  max mem: 78493
Epoch: [52]  [280/312]  eta: 0:00:34  lr: 0.003865  min_lr: 0.003865  loss: 2.6991 (2.5982)  weight_decay: 0.0500 (0.0500)  time: 1.0055  data: 0.0011  max mem: 78493
Epoch: [52]  [290/312]  eta: 0:00:23  lr: 0.003865  min_lr: 0.003865  loss: 2.8301 (2.6055)  weight_decay: 0.0500 (0.0500)  time: 1.0030  data: 0.0009  max mem: 78493
Epoch: [52]  [300/312]  eta: 0:00:12  lr: 0.003865  min_lr: 0.003865  loss: 2.8313 (2.6034)  weight_decay: 0.0500 (0.0500)  time: 1.0012  data: 0.0001  max mem: 78493
Epoch: [52]  [310/312]  eta: 0:00:02  lr: 0.003865  min_lr: 0.003865  loss: 2.4549 (2.6005)  weight_decay: 0.0500 (0.0500)  time: 1.0017  data: 0.0001  max mem: 78493
Epoch: [52]  [311/312]  eta: 0:00:01  lr: 0.003865  min_lr: 0.003865  loss: 2.4271 (2.5981)  weight_decay: 0.0500 (0.0500)  time: 1.0017  data: 0.0001  max mem: 78493
Epoch: [52] Total time: 0:05:33 (1.0686 s / it)
Averaged stats: lr: 0.003865  min_lr: 0.003865  loss: 2.4271 (2.6227)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:18  loss: 0.9065 (0.9065)  acc1: 77.8646 (77.8646)  acc5: 93.2292 (93.2292)  time: 8.6892  data: 8.3993  max mem: 78493
Test:  [8/9]  eta: 0:00:01  loss: 1.3536 (1.1990)  acc1: 68.3594 (70.3360)  acc5: 89.4531 (89.6800)  time: 1.1638  data: 0.9334  max mem: 78493
Test: Total time: 0:00:10 (1.1798 s / it)
* Acc@1 70.812 Acc@5 89.820 loss 1.190
Accuracy of the model on the 50000 test images: 70.8%
Max accuracy: 70.84%
Epoch: [53]  [  0/312]  eta: 1:26:02  lr: 0.003865  min_lr: 0.003865  loss: 2.8675 (2.8675)  weight_decay: 0.0500 (0.0500)  time: 16.5462  data: 13.7833  max mem: 78493
Epoch: [53]  [ 10/312]  eta: 0:12:48  lr: 0.003864  min_lr: 0.003864  loss: 2.7479 (2.5857)  weight_decay: 0.0500 (0.0500)  time: 2.5436  data: 1.2589  max mem: 78493
Epoch: [53]  [ 20/312]  eta: 0:08:54  lr: 0.003864  min_lr: 0.003864  loss: 2.4760 (2.4699)  weight_decay: 0.0500 (0.0500)  time: 1.0958  data: 0.0035  max mem: 78493
Epoch: [53]  [ 30/312]  eta: 0:07:21  lr: 0.003864  min_lr: 0.003864  loss: 2.4786 (2.5181)  weight_decay: 0.0500 (0.0500)  time: 1.0282  data: 0.0005  max mem: 78493
Epoch: [53]  [ 40/312]  eta: 0:06:28  lr: 0.003863  min_lr: 0.003863  loss: 2.6416 (2.5502)  weight_decay: 0.0500 (0.0500)  time: 1.0075  data: 0.0005  max mem: 78493
Epoch: [53]  [ 50/312]  eta: 0:05:52  lr: 0.003863  min_lr: 0.003863  loss: 2.7473 (2.6062)  weight_decay: 0.0500 (0.0500)  time: 1.0070  data: 0.0004  max mem: 78493
Epoch: [53]  [ 60/312]  eta: 0:05:25  lr: 0.003863  min_lr: 0.003863  loss: 2.7473 (2.5840)  weight_decay: 0.0500 (0.0500)  time: 1.0083  data: 0.0005  max mem: 78493
Epoch: [53]  [ 70/312]  eta: 0:05:02  lr: 0.003863  min_lr: 0.003863  loss: 2.6322 (2.5975)  weight_decay: 0.0500 (0.0500)  time: 1.0079  data: 0.0005  max mem: 78493
Epoch: [53]  [ 80/312]  eta: 0:04:43  lr: 0.003862  min_lr: 0.003862  loss: 2.7032 (2.5963)  weight_decay: 0.0500 (0.0500)  time: 1.0061  data: 0.0004  max mem: 78493
Epoch: [53]  [ 90/312]  eta: 0:04:25  lr: 0.003862  min_lr: 0.003862  loss: 2.7107 (2.5966)  weight_decay: 0.0500 (0.0500)  time: 1.0067  data: 0.0004  max mem: 78493
Epoch: [53]  [100/312]  eta: 0:04:09  lr: 0.003862  min_lr: 0.003862  loss: 2.7198 (2.6005)  weight_decay: 0.0500 (0.0500)  time: 1.0072  data: 0.0004  max mem: 78493
Epoch: [53]  [110/312]  eta: 0:03:54  lr: 0.003862  min_lr: 0.003862  loss: 2.8038 (2.6071)  weight_decay: 0.0500 (0.0500)  time: 1.0070  data: 0.0004  max mem: 78493
Epoch: [53]  [120/312]  eta: 0:03:40  lr: 0.003861  min_lr: 0.003861  loss: 2.7964 (2.6011)  weight_decay: 0.0500 (0.0500)  time: 1.0073  data: 0.0004  max mem: 78493
Epoch: [53]  [130/312]  eta: 0:03:27  lr: 0.003861  min_lr: 0.003861  loss: 2.7277 (2.5975)  weight_decay: 0.0500 (0.0500)  time: 1.0088  data: 0.0004  max mem: 78493
Epoch: [53]  [140/312]  eta: 0:03:14  lr: 0.003861  min_lr: 0.003861  loss: 2.6440 (2.5941)  weight_decay: 0.0500 (0.0500)  time: 1.0076  data: 0.0005  max mem: 78493
Epoch: [53]  [150/312]  eta: 0:03:01  lr: 0.003861  min_lr: 0.003861  loss: 2.5207 (2.5966)  weight_decay: 0.0500 (0.0500)  time: 1.0080  data: 0.0005  max mem: 78493
Epoch: [53]  [160/312]  eta: 0:02:49  lr: 0.003860  min_lr: 0.003860  loss: 2.7174 (2.6068)  weight_decay: 0.0500 (0.0500)  time: 1.0073  data: 0.0004  max mem: 78493
Epoch: [53]  [170/312]  eta: 0:02:37  lr: 0.003860  min_lr: 0.003860  loss: 2.8355 (2.6198)  weight_decay: 0.0500 (0.0500)  time: 1.0039  data: 0.0005  max mem: 78493
Epoch: [53]  [180/312]  eta: 0:02:25  lr: 0.003860  min_lr: 0.003860  loss: 2.8137 (2.6211)  weight_decay: 0.0500 (0.0500)  time: 1.0055  data: 0.0005  max mem: 78493
Epoch: [53]  [190/312]  eta: 0:02:13  lr: 0.003860  min_lr: 0.003860  loss: 2.5670 (2.6106)  weight_decay: 0.0500 (0.0500)  time: 1.0056  data: 0.0004  max mem: 78493
Epoch: [53]  [200/312]  eta: 0:02:02  lr: 0.003859  min_lr: 0.003859  loss: 2.5808 (2.6066)  weight_decay: 0.0500 (0.0500)  time: 1.0034  data: 0.0005  max mem: 78493
Epoch: [53]  [210/312]  eta: 0:01:51  lr: 0.003859  min_lr: 0.003859  loss: 2.7254 (2.6131)  weight_decay: 0.0500 (0.0500)  time: 1.0030  data: 0.0005  max mem: 78493
Epoch: [53]  [220/312]  eta: 0:01:39  lr: 0.003859  min_lr: 0.003859  loss: 2.7631 (2.6203)  weight_decay: 0.0500 (0.0500)  time: 1.0057  data: 0.0004  max mem: 78493
Epoch: [53]  [230/312]  eta: 0:01:28  lr: 0.003858  min_lr: 0.003858  loss: 2.8116 (2.6262)  weight_decay: 0.0500 (0.0500)  time: 1.0073  data: 0.0005  max mem: 78493
Epoch: [53]  [240/312]  eta: 0:01:17  lr: 0.003858  min_lr: 0.003858  loss: 2.9048 (2.6378)  weight_decay: 0.0500 (0.0500)  time: 1.0065  data: 0.0005  max mem: 78493
Epoch: [53]  [250/312]  eta: 0:01:06  lr: 0.003858  min_lr: 0.003858  loss: 2.6940 (2.6307)  weight_decay: 0.0500 (0.0500)  time: 1.0045  data: 0.0005  max mem: 78493
Epoch: [53]  [260/312]  eta: 0:00:55  lr: 0.003858  min_lr: 0.003858  loss: 2.2492 (2.6205)  weight_decay: 0.0500 (0.0500)  time: 1.0045  data: 0.0005  max mem: 78493
Epoch: [53]  [270/312]  eta: 0:00:44  lr: 0.003857  min_lr: 0.003857  loss: 2.4886 (2.6215)  weight_decay: 0.0500 (0.0500)  time: 1.0054  data: 0.0005  max mem: 78493
Epoch: [53]  [280/312]  eta: 0:00:34  lr: 0.003857  min_lr: 0.003857  loss: 2.5537 (2.6126)  weight_decay: 0.0500 (0.0500)  time: 1.0051  data: 0.0010  max mem: 78493
Epoch: [53]  [290/312]  eta: 0:00:23  lr: 0.003857  min_lr: 0.003857  loss: 2.6467 (2.6161)  weight_decay: 0.0500 (0.0500)  time: 1.0034  data: 0.0009  max mem: 78493
Epoch: [53]  [300/312]  eta: 0:00:12  lr: 0.003857  min_lr: 0.003857  loss: 2.8314 (2.6198)  weight_decay: 0.0500 (0.0500)  time: 1.0016  data: 0.0001  max mem: 78493
Epoch: [53]  [310/312]  eta: 0:00:02  lr: 0.003856  min_lr: 0.003856  loss: 2.8155 (2.6231)  weight_decay: 0.0500 (0.0500)  time: 1.0017  data: 0.0001  max mem: 78493
Epoch: [53]  [311/312]  eta: 0:00:01  lr: 0.003856  min_lr: 0.003856  loss: 2.8155 (2.6249)  weight_decay: 0.0500 (0.0500)  time: 1.0017  data: 0.0001  max mem: 78493
Epoch: [53] Total time: 0:05:32 (1.0671 s / it)
Averaged stats: lr: 0.003856  min_lr: 0.003856  loss: 2.8155 (2.6311)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:15  loss: 0.8726 (0.8726)  acc1: 80.8594 (80.8594)  acc5: 93.8802 (93.8802)  time: 8.3379  data: 8.0639  max mem: 78493
Test:  [8/9]  eta: 0:00:01  loss: 1.2960 (1.1643)  acc1: 70.0521 (71.7440)  acc5: 89.7135 (90.2240)  time: 1.1245  data: 0.8961  max mem: 78493
Test: Total time: 0:00:10 (1.1431 s / it)
* Acc@1 71.452 Acc@5 90.358 loss 1.173
Accuracy of the model on the 50000 test images: 71.5%
Max accuracy: 71.45%
Epoch: [54]  [  0/312]  eta: 1:17:24  lr: 0.003856  min_lr: 0.003856  loss: 3.1123 (3.1123)  weight_decay: 0.0500 (0.0500)  time: 14.8867  data: 13.6428  max mem: 78493
Epoch: [54]  [ 10/312]  eta: 0:12:43  lr: 0.003856  min_lr: 0.003856  loss: 2.5737 (2.4725)  weight_decay: 0.0500 (0.0500)  time: 2.5267  data: 1.3542  max mem: 78493
Epoch: [54]  [ 20/312]  eta: 0:08:49  lr: 0.003856  min_lr: 0.003856  loss: 2.6231 (2.6152)  weight_decay: 0.0500 (0.0500)  time: 1.1580  data: 0.0629  max mem: 78493
Epoch: [54]  [ 30/312]  eta: 0:07:17  lr: 0.003855  min_lr: 0.003855  loss: 2.7621 (2.6048)  weight_decay: 0.0500 (0.0500)  time: 1.0151  data: 0.0005  max mem: 78493
Epoch: [54]  [ 40/312]  eta: 0:06:25  lr: 0.003855  min_lr: 0.003855  loss: 2.5860 (2.5775)  weight_decay: 0.0500 (0.0500)  time: 1.0065  data: 0.0004  max mem: 78493
Epoch: [54]  [ 50/312]  eta: 0:05:50  lr: 0.003855  min_lr: 0.003855  loss: 2.5500 (2.5727)  weight_decay: 0.0500 (0.0500)  time: 1.0090  data: 0.0004  max mem: 78493
Epoch: [54]  [ 60/312]  eta: 0:05:23  lr: 0.003855  min_lr: 0.003855  loss: 2.4391 (2.5371)  weight_decay: 0.0500 (0.0500)  time: 1.0098  data: 0.0004  max mem: 78493
Epoch: [54]  [ 70/312]  eta: 0:05:01  lr: 0.003854  min_lr: 0.003854  loss: 2.7861 (2.5683)  weight_decay: 0.0500 (0.0500)  time: 1.0069  data: 0.0004  max mem: 78493
Epoch: [54]  [ 80/312]  eta: 0:04:42  lr: 0.003854  min_lr: 0.003854  loss: 2.7472 (2.5546)  weight_decay: 0.0500 (0.0500)  time: 1.0059  data: 0.0004  max mem: 78493
Epoch: [54]  [ 90/312]  eta: 0:04:24  lr: 0.003854  min_lr: 0.003854  loss: 2.4611 (2.5476)  weight_decay: 0.0500 (0.0500)  time: 1.0072  data: 0.0014  max mem: 78493
Epoch: [54]  [100/312]  eta: 0:04:08  lr: 0.003854  min_lr: 0.003854  loss: 2.6896 (2.5739)  weight_decay: 0.0500 (0.0500)  time: 1.0065  data: 0.0014  max mem: 78493
Epoch: [54]  [110/312]  eta: 0:03:54  lr: 0.003853  min_lr: 0.003853  loss: 2.8343 (2.5851)  weight_decay: 0.0500 (0.0500)  time: 1.0073  data: 0.0004  max mem: 78493
Epoch: [54]  [120/312]  eta: 0:03:40  lr: 0.003853  min_lr: 0.003853  loss: 2.5745 (2.5814)  weight_decay: 0.0500 (0.0500)  time: 1.0082  data: 0.0004  max mem: 78493
Epoch: [54]  [130/312]  eta: 0:03:26  lr: 0.003853  min_lr: 0.003853  loss: 2.5676 (2.5877)  weight_decay: 0.0500 (0.0500)  time: 1.0076  data: 0.0005  max mem: 78493
Epoch: [54]  [140/312]  eta: 0:03:13  lr: 0.003852  min_lr: 0.003852  loss: 2.5676 (2.5779)  weight_decay: 0.0500 (0.0500)  time: 1.0066  data: 0.0013  max mem: 78493
Epoch: [54]  [150/312]  eta: 0:03:01  lr: 0.003852  min_lr: 0.003852  loss: 2.5844 (2.5869)  weight_decay: 0.0500 (0.0500)  time: 1.0067  data: 0.0013  max mem: 78493
Epoch: [54]  [160/312]  eta: 0:02:49  lr: 0.003852  min_lr: 0.003852  loss: 2.8552 (2.5862)  weight_decay: 0.0500 (0.0500)  time: 1.0083  data: 0.0004  max mem: 78493
Epoch: [54]  [170/312]  eta: 0:02:37  lr: 0.003852  min_lr: 0.003852  loss: 2.6514 (2.5821)  weight_decay: 0.0500 (0.0500)  time: 1.0081  data: 0.0004  max mem: 78493
Epoch: [54]  [180/312]  eta: 0:02:25  lr: 0.003851  min_lr: 0.003851  loss: 2.3447 (2.5731)  weight_decay: 0.0500 (0.0500)  time: 1.0074  data: 0.0004  max mem: 78493
Epoch: [54]  [190/312]  eta: 0:02:13  lr: 0.003851  min_lr: 0.003851  loss: 2.3059 (2.5671)  weight_decay: 0.0500 (0.0500)  time: 1.0070  data: 0.0005  max mem: 78493
Epoch: [54]  [200/312]  eta: 0:02:02  lr: 0.003851  min_lr: 0.003851  loss: 2.5346 (2.5705)  weight_decay: 0.0500 (0.0500)  time: 1.0063  data: 0.0005  max mem: 78493
Epoch: [54]  [210/312]  eta: 0:01:50  lr: 0.003851  min_lr: 0.003851  loss: 2.5623 (2.5684)  weight_decay: 0.0500 (0.0500)  time: 1.0060  data: 0.0004  max mem: 78493
Epoch: [54]  [220/312]  eta: 0:01:39  lr: 0.003850  min_lr: 0.003850  loss: 2.4906 (2.5711)  weight_decay: 0.0500 (0.0500)  time: 1.0053  data: 0.0004  max mem: 78493
Epoch: [54]  [230/312]  eta: 0:01:28  lr: 0.003850  min_lr: 0.003850  loss: 2.5987 (2.5728)  weight_decay: 0.0500 (0.0500)  time: 1.0061  data: 0.0004  max mem: 78493
Epoch: [54]  [240/312]  eta: 0:01:17  lr: 0.003850  min_lr: 0.003850  loss: 2.7422 (2.5832)  weight_decay: 0.0500 (0.0500)  time: 1.0066  data: 0.0004  max mem: 78493
Epoch: [54]  [250/312]  eta: 0:01:06  lr: 0.003849  min_lr: 0.003849  loss: 2.7422 (2.5823)  weight_decay: 0.0500 (0.0500)  time: 1.0061  data: 0.0005  max mem: 78493
Epoch: [54]  [260/312]  eta: 0:00:55  lr: 0.003849  min_lr: 0.003849  loss: 2.6341 (2.5848)  weight_decay: 0.0500 (0.0500)  time: 1.0071  data: 0.0004  max mem: 78493
Epoch: [54]  [270/312]  eta: 0:00:44  lr: 0.003849  min_lr: 0.003849  loss: 2.7497 (2.5920)  weight_decay: 0.0500 (0.0500)  time: 1.0086  data: 0.0004  max mem: 78493
Epoch: [54]  [280/312]  eta: 0:00:34  lr: 0.003849  min_lr: 0.003849  loss: 2.6014 (2.5864)  weight_decay: 0.0500 (0.0500)  time: 1.0103  data: 0.0010  max mem: 78493
Epoch: [54]  [290/312]  eta: 0:00:23  lr: 0.003848  min_lr: 0.003848  loss: 2.6014 (2.5901)  weight_decay: 0.0500 (0.0500)  time: 1.0065  data: 0.0009  max mem: 78493
Epoch: [54]  [300/312]  eta: 0:00:12  lr: 0.003848  min_lr: 0.003848  loss: 2.7863 (2.5931)  weight_decay: 0.0500 (0.0500)  time: 1.0016  data: 0.0001  max mem: 78493
Epoch: [54]  [310/312]  eta: 0:00:02  lr: 0.003848  min_lr: 0.003848  loss: 2.7828 (2.5972)  weight_decay: 0.0500 (0.0500)  time: 1.0018  data: 0.0001  max mem: 78493
Epoch: [54]  [311/312]  eta: 0:00:01  lr: 0.003848  min_lr: 0.003848  loss: 2.7863 (2.5991)  weight_decay: 0.0500 (0.0500)  time: 1.0018  data: 0.0001  max mem: 78493
Epoch: [54] Total time: 0:05:32 (1.0668 s / it)
Averaged stats: lr: 0.003848  min_lr: 0.003848  loss: 2.7863 (2.6122)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:11  loss: 0.9750 (0.9750)  acc1: 76.8229 (76.8229)  acc5: 91.7969 (91.7969)  time: 7.9104  data: 7.6384  max mem: 78493
Test:  [8/9]  eta: 0:00:01  loss: 1.3469 (1.2418)  acc1: 69.0104 (70.4960)  acc5: 88.2812 (89.2000)  time: 1.0811  data: 0.8506  max mem: 78493
Test: Total time: 0:00:09 (1.1078 s / it)
* Acc@1 70.112 Acc@5 89.494 loss 1.224
Accuracy of the model on the 50000 test images: 70.1%
Max accuracy: 71.45%
Epoch: [55]  [  0/312]  eta: 1:22:17  lr: 0.003848  min_lr: 0.003848  loss: 3.0506 (3.0506)  weight_decay: 0.0500 (0.0500)  time: 15.8261  data: 13.3453  max mem: 78493
Epoch: [55]  [ 10/312]  eta: 0:12:51  lr: 0.003848  min_lr: 0.003848  loss: 2.6118 (2.5670)  weight_decay: 0.0500 (0.0500)  time: 2.5553  data: 1.2928  max mem: 78493
Epoch: [55]  [ 20/312]  eta: 0:08:52  lr: 0.003847  min_lr: 0.003847  loss: 2.5644 (2.5389)  weight_decay: 0.0500 (0.0500)  time: 1.1232  data: 0.0441  max mem: 78493
Epoch: [55]  [ 30/312]  eta: 0:07:20  lr: 0.003847  min_lr: 0.003847  loss: 2.4294 (2.4695)  weight_decay: 0.0500 (0.0500)  time: 1.0139  data: 0.0005  max mem: 78493
Epoch: [55]  [ 40/312]  eta: 0:06:27  lr: 0.003847  min_lr: 0.003847  loss: 2.5264 (2.5127)  weight_decay: 0.0500 (0.0500)  time: 1.0082  data: 0.0005  max mem: 78493
Epoch: [55]  [ 50/312]  eta: 0:05:52  lr: 0.003846  min_lr: 0.003846  loss: 2.6230 (2.5359)  weight_decay: 0.0500 (0.0500)  time: 1.0085  data: 0.0005  max mem: 78493
Epoch: [55]  [ 60/312]  eta: 0:05:25  lr: 0.003846  min_lr: 0.003846  loss: 2.5898 (2.5359)  weight_decay: 0.0500 (0.0500)  time: 1.0128  data: 0.0005  max mem: 78493
Epoch: [55]  [ 70/312]  eta: 0:05:02  lr: 0.003846  min_lr: 0.003846  loss: 2.4680 (2.5214)  weight_decay: 0.0500 (0.0500)  time: 1.0128  data: 0.0005  max mem: 78493
Epoch: [55]  [ 80/312]  eta: 0:04:43  lr: 0.003846  min_lr: 0.003846  loss: 2.4126 (2.5307)  weight_decay: 0.0500 (0.0500)  time: 1.0074  data: 0.0005  max mem: 78493
Epoch: [55]  [ 90/312]  eta: 0:04:25  lr: 0.003845  min_lr: 0.003845  loss: 2.7431 (2.5568)  weight_decay: 0.0500 (0.0500)  time: 1.0042  data: 0.0005  max mem: 78493
Epoch: [55]  [100/312]  eta: 0:04:09  lr: 0.003845  min_lr: 0.003845  loss: 2.8068 (2.5724)  weight_decay: 0.0500 (0.0500)  time: 1.0065  data: 0.0004  max mem: 78493
Epoch: [55]  [110/312]  eta: 0:03:54  lr: 0.003845  min_lr: 0.003845  loss: 2.5778 (2.5684)  weight_decay: 0.0500 (0.0500)  time: 1.0087  data: 0.0004  max mem: 78493
Epoch: [55]  [120/312]  eta: 0:03:40  lr: 0.003844  min_lr: 0.003844  loss: 2.5072 (2.5635)  weight_decay: 0.0500 (0.0500)  time: 1.0079  data: 0.0004  max mem: 78493
Epoch: [55]  [130/312]  eta: 0:03:27  lr: 0.003844  min_lr: 0.003844  loss: 2.7319 (2.5817)  weight_decay: 0.0500 (0.0500)  time: 1.0076  data: 0.0004  max mem: 78493
Epoch: [55]  [140/312]  eta: 0:03:14  lr: 0.003844  min_lr: 0.003844  loss: 2.6975 (2.5815)  weight_decay: 0.0500 (0.0500)  time: 1.0073  data: 0.0004  max mem: 78493
Epoch: [55]  [150/312]  eta: 0:03:01  lr: 0.003844  min_lr: 0.003844  loss: 2.6663 (2.5867)  weight_decay: 0.0500 (0.0500)  time: 1.0072  data: 0.0004  max mem: 78493
Epoch: [55]  [160/312]  eta: 0:02:49  lr: 0.003843  min_lr: 0.003843  loss: 2.7456 (2.5880)  weight_decay: 0.0500 (0.0500)  time: 1.0068  data: 0.0004  max mem: 78493
Epoch: [55]  [170/312]  eta: 0:02:37  lr: 0.003843  min_lr: 0.003843  loss: 2.7070 (2.5943)  weight_decay: 0.0500 (0.0500)  time: 1.0055  data: 0.0004  max mem: 78493
Epoch: [55]  [180/312]  eta: 0:02:25  lr: 0.003843  min_lr: 0.003843  loss: 2.6295 (2.5907)  weight_decay: 0.0500 (0.0500)  time: 1.0057  data: 0.0005  max mem: 78493
Epoch: [55]  [190/312]  eta: 0:02:13  lr: 0.003843  min_lr: 0.003843  loss: 2.5777 (2.5886)  weight_decay: 0.0500 (0.0500)  time: 1.0076  data: 0.0004  max mem: 78493
Epoch: [55]  [200/312]  eta: 0:02:02  lr: 0.003842  min_lr: 0.003842  loss: 2.6956 (2.5863)  weight_decay: 0.0500 (0.0500)  time: 1.0074  data: 0.0004  max mem: 78493
Epoch: [55]  [210/312]  eta: 0:01:51  lr: 0.003842  min_lr: 0.003842  loss: 2.7016 (2.5890)  weight_decay: 0.0500 (0.0500)  time: 1.0059  data: 0.0004  max mem: 78493
Epoch: [55]  [220/312]  eta: 0:01:39  lr: 0.003842  min_lr: 0.003842  loss: 2.5382 (2.5769)  weight_decay: 0.0500 (0.0500)  time: 1.0070  data: 0.0004  max mem: 78493
Epoch: [55]  [230/312]  eta: 0:01:28  lr: 0.003841  min_lr: 0.003841  loss: 2.3337 (2.5778)  weight_decay: 0.0500 (0.0500)  time: 1.0067  data: 0.0004  max mem: 78493
Epoch: [55]  [240/312]  eta: 0:01:17  lr: 0.003841  min_lr: 0.003841  loss: 2.6480 (2.5809)  weight_decay: 0.0500 (0.0500)  time: 1.0048  data: 0.0004  max mem: 78493
Epoch: [55]  [250/312]  eta: 0:01:06  lr: 0.003841  min_lr: 0.003841  loss: 2.7833 (2.5848)  weight_decay: 0.0500 (0.0500)  time: 1.0048  data: 0.0004  max mem: 78493
Epoch: [55]  [260/312]  eta: 0:00:55  lr: 0.003841  min_lr: 0.003841  loss: 2.7832 (2.5911)  weight_decay: 0.0500 (0.0500)  time: 1.0064  data: 0.0004  max mem: 78493
Epoch: [55]  [270/312]  eta: 0:00:44  lr: 0.003840  min_lr: 0.003840  loss: 2.7832 (2.5916)  weight_decay: 0.0500 (0.0500)  time: 1.0062  data: 0.0005  max mem: 78493
Epoch: [55]  [280/312]  eta: 0:00:34  lr: 0.003840  min_lr: 0.003840  loss: 2.5920 (2.5929)  weight_decay: 0.0500 (0.0500)  time: 1.0057  data: 0.0011  max mem: 78493
Epoch: [55]  [290/312]  eta: 0:00:23  lr: 0.003840  min_lr: 0.003840  loss: 2.4909 (2.5870)  weight_decay: 0.0500 (0.0500)  time: 1.0048  data: 0.0009  max mem: 78493
Epoch: [55]  [300/312]  eta: 0:00:12  lr: 0.003839  min_lr: 0.003839  loss: 2.3222 (2.5807)  weight_decay: 0.0500 (0.0500)  time: 1.0028  data: 0.0001  max mem: 78493
Epoch: [55]  [310/312]  eta: 0:00:02  lr: 0.003839  min_lr: 0.003839  loss: 2.7014 (2.5856)  weight_decay: 0.0500 (0.0500)  time: 1.0022  data: 0.0001  max mem: 78493
Epoch: [55]  [311/312]  eta: 0:00:01  lr: 0.003839  min_lr: 0.003839  loss: 2.7014 (2.5827)  weight_decay: 0.0500 (0.0500)  time: 1.0021  data: 0.0001  max mem: 78493
Epoch: [55] Total time: 0:05:33 (1.0676 s / it)
Averaged stats: lr: 0.003839  min_lr: 0.003839  loss: 2.7014 (2.5846)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:16  loss: 0.9012 (0.9012)  acc1: 79.8177 (79.8177)  acc5: 93.0990 (93.0990)  time: 8.5081  data: 8.2467  max mem: 78493
Test:  [8/9]  eta: 0:00:01  loss: 1.2846 (1.1250)  acc1: 68.7500 (71.9680)  acc5: 90.3646 (90.7040)  time: 1.1490  data: 0.9164  max mem: 78493
Test: Total time: 0:00:10 (1.1893 s / it)
* Acc@1 72.328 Acc@5 90.740 loss 1.124
Accuracy of the model on the 50000 test images: 72.3%
Max accuracy: 72.33%
Epoch: [56]  [  0/312]  eta: 1:21:38  lr: 0.003839  min_lr: 0.003839  loss: 2.4184 (2.4184)  weight_decay: 0.0500 (0.0500)  time: 15.7003  data: 12.7460  max mem: 78493
Epoch: [56]  [ 10/312]  eta: 0:12:39  lr: 0.003839  min_lr: 0.003839  loss: 2.6652 (2.5658)  weight_decay: 0.0500 (0.0500)  time: 2.5163  data: 1.2944  max mem: 78493
Epoch: [56]  [ 20/312]  eta: 0:08:47  lr: 0.003839  min_lr: 0.003839  loss: 2.7502 (2.5750)  weight_decay: 0.0500 (0.0500)  time: 1.1116  data: 0.0750  max mem: 78493
Epoch: [56]  [ 30/312]  eta: 0:07:16  lr: 0.003838  min_lr: 0.003838  loss: 2.4974 (2.5043)  weight_decay: 0.0500 (0.0500)  time: 1.0176  data: 0.0006  max mem: 78493
Epoch: [56]  [ 40/312]  eta: 0:06:25  lr: 0.003838  min_lr: 0.003838  loss: 2.4950 (2.5599)  weight_decay: 0.0500 (0.0500)  time: 1.0091  data: 0.0004  max mem: 78493
Epoch: [56]  [ 50/312]  eta: 0:05:50  lr: 0.003838  min_lr: 0.003838  loss: 2.8368 (2.6083)  weight_decay: 0.0500 (0.0500)  time: 1.0085  data: 0.0004  max mem: 78493
Epoch: [56]  [ 60/312]  eta: 0:05:23  lr: 0.003837  min_lr: 0.003837  loss: 2.7960 (2.5841)  weight_decay: 0.0500 (0.0500)  time: 1.0076  data: 0.0004  max mem: 78493
Epoch: [56]  [ 70/312]  eta: 0:05:01  lr: 0.003837  min_lr: 0.003837  loss: 2.8050 (2.6047)  weight_decay: 0.0500 (0.0500)  time: 1.0062  data: 0.0004  max mem: 78493
Epoch: [56]  [ 80/312]  eta: 0:04:41  lr: 0.003837  min_lr: 0.003837  loss: 2.6077 (2.5830)  weight_decay: 0.0500 (0.0500)  time: 1.0069  data: 0.0004  max mem: 78493
Epoch: [56]  [ 90/312]  eta: 0:04:24  lr: 0.003837  min_lr: 0.003837  loss: 2.3561 (2.5666)  weight_decay: 0.0500 (0.0500)  time: 1.0082  data: 0.0004  max mem: 78493
Epoch: [56]  [100/312]  eta: 0:04:08  lr: 0.003836  min_lr: 0.003836  loss: 2.8007 (2.5849)  weight_decay: 0.0500 (0.0500)  time: 1.0084  data: 0.0004  max mem: 78493
Epoch: [56]  [110/312]  eta: 0:03:54  lr: 0.003836  min_lr: 0.003836  loss: 2.8007 (2.5859)  weight_decay: 0.0500 (0.0500)  time: 1.0069  data: 0.0004  max mem: 78493
Epoch: [56]  [120/312]  eta: 0:03:40  lr: 0.003836  min_lr: 0.003836  loss: 2.7399 (2.5940)  weight_decay: 0.0500 (0.0500)  time: 1.0058  data: 0.0004  max mem: 78493
Epoch: [56]  [130/312]  eta: 0:03:26  lr: 0.003835  min_lr: 0.003835  loss: 2.7555 (2.5993)  weight_decay: 0.0500 (0.0500)  time: 1.0064  data: 0.0011  max mem: 78493
Epoch: [56]  [140/312]  eta: 0:03:13  lr: 0.003835  min_lr: 0.003835  loss: 2.6963 (2.5988)  weight_decay: 0.0500 (0.0500)  time: 1.0059  data: 0.0011  max mem: 78493
Epoch: [56]  [150/312]  eta: 0:03:01  lr: 0.003835  min_lr: 0.003835  loss: 2.7217 (2.5961)  weight_decay: 0.0500 (0.0500)  time: 1.0044  data: 0.0005  max mem: 78493
Epoch: [56]  [160/312]  eta: 0:02:48  lr: 0.003835  min_lr: 0.003835  loss: 2.4567 (2.5882)  weight_decay: 0.0500 (0.0500)  time: 1.0045  data: 0.0004  max mem: 78493
Epoch: [56]  [170/312]  eta: 0:02:36  lr: 0.003834  min_lr: 0.003834  loss: 2.6813 (2.5996)  weight_decay: 0.0500 (0.0500)  time: 1.0057  data: 0.0004  max mem: 78493
Epoch: [56]  [180/312]  eta: 0:02:25  lr: 0.003834  min_lr: 0.003834  loss: 2.6701 (2.5913)  weight_decay: 0.0500 (0.0500)  time: 1.0056  data: 0.0004  max mem: 78493
Epoch: [56]  [190/312]  eta: 0:02:13  lr: 0.003834  min_lr: 0.003834  loss: 2.6582 (2.5950)  weight_decay: 0.0500 (0.0500)  time: 1.0046  data: 0.0005  max mem: 78493
Epoch: [56]  [200/312]  eta: 0:02:02  lr: 0.003833  min_lr: 0.003833  loss: 2.7529 (2.5997)  weight_decay: 0.0500 (0.0500)  time: 1.0054  data: 0.0005  max mem: 78493
Epoch: [56]  [210/312]  eta: 0:01:50  lr: 0.003833  min_lr: 0.003833  loss: 2.7121 (2.5955)  weight_decay: 0.0500 (0.0500)  time: 1.0056  data: 0.0004  max mem: 78493
Epoch: [56]  [220/312]  eta: 0:01:39  lr: 0.003833  min_lr: 0.003833  loss: 2.1699 (2.5794)  weight_decay: 0.0500 (0.0500)  time: 1.0052  data: 0.0004  max mem: 78493
Epoch: [56]  [230/312]  eta: 0:01:28  lr: 0.003833  min_lr: 0.003833  loss: 2.3085 (2.5840)  weight_decay: 0.0500 (0.0500)  time: 1.0051  data: 0.0004  max mem: 78493
Epoch: [56]  [240/312]  eta: 0:01:17  lr: 0.003832  min_lr: 0.003832  loss: 2.7177 (2.5842)  weight_decay: 0.0500 (0.0500)  time: 1.0040  data: 0.0004  max mem: 78493
Epoch: [56]  [250/312]  eta: 0:01:06  lr: 0.003832  min_lr: 0.003832  loss: 2.5483 (2.5825)  weight_decay: 0.0500 (0.0500)  time: 1.0043  data: 0.0004  max mem: 78493
Epoch: [56]  [260/312]  eta: 0:00:55  lr: 0.003832  min_lr: 0.003832  loss: 2.5380 (2.5809)  weight_decay: 0.0500 (0.0500)  time: 1.0055  data: 0.0004  max mem: 78493
Epoch: [56]  [270/312]  eta: 0:00:44  lr: 0.003831  min_lr: 0.003831  loss: 2.7550 (2.5863)  weight_decay: 0.0500 (0.0500)  time: 1.0055  data: 0.0004  max mem: 78493
Epoch: [56]  [280/312]  eta: 0:00:34  lr: 0.003831  min_lr: 0.003831  loss: 2.7916 (2.5912)  weight_decay: 0.0500 (0.0500)  time: 1.0059  data: 0.0011  max mem: 78493
Epoch: [56]  [290/312]  eta: 0:00:23  lr: 0.003831  min_lr: 0.003831  loss: 2.7776 (2.5953)  weight_decay: 0.0500 (0.0500)  time: 1.0042  data: 0.0009  max mem: 78493
Epoch: [56]  [300/312]  eta: 0:00:12  lr: 0.003831  min_lr: 0.003831  loss: 2.7707 (2.5976)  weight_decay: 0.0500 (0.0500)  time: 1.0019  data: 0.0001  max mem: 78493
Epoch: [56]  [310/312]  eta: 0:00:02  lr: 0.003830  min_lr: 0.003830  loss: 2.4424 (2.5932)  weight_decay: 0.0500 (0.0500)  time: 1.0018  data: 0.0001  max mem: 78493
Epoch: [56]  [311/312]  eta: 0:00:01  lr: 0.003830  min_lr: 0.003830  loss: 2.7557 (2.5937)  weight_decay: 0.0500 (0.0500)  time: 1.0018  data: 0.0001  max mem: 78493
Epoch: [56] Total time: 0:05:32 (1.0655 s / it)
Averaged stats: lr: 0.003830  min_lr: 0.003830  loss: 2.7557 (2.5947)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:16  loss: 1.0027 (1.0027)  acc1: 76.0417 (76.0417)  acc5: 92.8385 (92.8385)  time: 8.5430  data: 8.2701  max mem: 78493
Test:  [8/9]  eta: 0:00:01  loss: 1.3726 (1.2147)  acc1: 68.2292 (70.2880)  acc5: 89.4531 (89.7120)  time: 1.1475  data: 0.9190  max mem: 78493
Test: Total time: 0:00:10 (1.1729 s / it)
* Acc@1 70.716 Acc@5 89.824 loss 1.207
Accuracy of the model on the 50000 test images: 70.7%
Max accuracy: 72.33%
Epoch: [57]  [  0/312]  eta: 1:26:29  lr: 0.003830  min_lr: 0.003830  loss: 1.9274 (1.9274)  weight_decay: 0.0500 (0.0500)  time: 16.6338  data: 13.9717  max mem: 78493
Epoch: [57]  [ 10/312]  eta: 0:12:27  lr: 0.003830  min_lr: 0.003830  loss: 2.7147 (2.5167)  weight_decay: 0.0500 (0.0500)  time: 2.4749  data: 1.2840  max mem: 78493
Epoch: [57]  [ 20/312]  eta: 0:08:44  lr: 0.003830  min_lr: 0.003830  loss: 2.6654 (2.5503)  weight_decay: 0.0500 (0.0500)  time: 1.0529  data: 0.0080  max mem: 78493
Epoch: [57]  [ 30/312]  eta: 0:07:14  lr: 0.003829  min_lr: 0.003829  loss: 2.6646 (2.5739)  weight_decay: 0.0500 (0.0500)  time: 1.0279  data: 0.0006  max mem: 78493
Epoch: [57]  [ 40/312]  eta: 0:06:23  lr: 0.003829  min_lr: 0.003829  loss: 2.5469 (2.5203)  weight_decay: 0.0500 (0.0500)  time: 1.0078  data: 0.0004  max mem: 78493
Epoch: [57]  [ 50/312]  eta: 0:05:49  lr: 0.003829  min_lr: 0.003829  loss: 2.4245 (2.5200)  weight_decay: 0.0500 (0.0500)  time: 1.0078  data: 0.0014  max mem: 78493
Epoch: [57]  [ 60/312]  eta: 0:05:22  lr: 0.003828  min_lr: 0.003828  loss: 2.7007 (2.5425)  weight_decay: 0.0500 (0.0500)  time: 1.0079  data: 0.0014  max mem: 78493
Epoch: [57]  [ 70/312]  eta: 0:05:00  lr: 0.003828  min_lr: 0.003828  loss: 2.5359 (2.5229)  weight_decay: 0.0500 (0.0500)  time: 1.0077  data: 0.0005  max mem: 78493
Epoch: [57]  [ 80/312]  eta: 0:04:41  lr: 0.003828  min_lr: 0.003828  loss: 2.4059 (2.5221)  weight_decay: 0.0500 (0.0500)  time: 1.0081  data: 0.0005  max mem: 78493
Epoch: [57]  [ 90/312]  eta: 0:04:24  lr: 0.003828  min_lr: 0.003828  loss: 2.6186 (2.5405)  weight_decay: 0.0500 (0.0500)  time: 1.0074  data: 0.0004  max mem: 78493
Epoch: [57]  [100/312]  eta: 0:04:08  lr: 0.003827  min_lr: 0.003827  loss: 2.5813 (2.5349)  weight_decay: 0.0500 (0.0500)  time: 1.0073  data: 0.0004  max mem: 78493
Epoch: [57]  [110/312]  eta: 0:03:53  lr: 0.003827  min_lr: 0.003827  loss: 2.5813 (2.5462)  weight_decay: 0.0500 (0.0500)  time: 1.0074  data: 0.0004  max mem: 78493
Epoch: [57]  [120/312]  eta: 0:03:39  lr: 0.003827  min_lr: 0.003827  loss: 2.8052 (2.5522)  weight_decay: 0.0500 (0.0500)  time: 1.0060  data: 0.0004  max mem: 78493
Epoch: [57]  [130/312]  eta: 0:03:26  lr: 0.003826  min_lr: 0.003826  loss: 2.7485 (2.5649)  weight_decay: 0.0500 (0.0500)  time: 1.0060  data: 0.0004  max mem: 78493
Epoch: [57]  [140/312]  eta: 0:03:13  lr: 0.003826  min_lr: 0.003826  loss: 2.7208 (2.5706)  weight_decay: 0.0500 (0.0500)  time: 1.0064  data: 0.0005  max mem: 78493
Epoch: [57]  [150/312]  eta: 0:03:00  lr: 0.003826  min_lr: 0.003826  loss: 2.4806 (2.5632)  weight_decay: 0.0500 (0.0500)  time: 1.0054  data: 0.0005  max mem: 78493
Epoch: [57]  [160/312]  eta: 0:02:48  lr: 0.003825  min_lr: 0.003825  loss: 2.6212 (2.5746)  weight_decay: 0.0500 (0.0500)  time: 1.0058  data: 0.0012  max mem: 78493
Epoch: [57]  [170/312]  eta: 0:02:36  lr: 0.003825  min_lr: 0.003825  loss: 2.5574 (2.5649)  weight_decay: 0.0500 (0.0500)  time: 1.0073  data: 0.0012  max mem: 78493
Epoch: [57]  [180/312]  eta: 0:02:24  lr: 0.003825  min_lr: 0.003825  loss: 2.4104 (2.5635)  weight_decay: 0.0500 (0.0500)  time: 1.0062  data: 0.0004  max mem: 78493
Epoch: [57]  [190/312]  eta: 0:02:13  lr: 0.003825  min_lr: 0.003825  loss: 2.7606 (2.5720)  weight_decay: 0.0500 (0.0500)  time: 1.0066  data: 0.0004  max mem: 78493
Epoch: [57]  [200/312]  eta: 0:02:02  lr: 0.003824  min_lr: 0.003824  loss: 2.7101 (2.5612)  weight_decay: 0.0500 (0.0500)  time: 1.0078  data: 0.0004  max mem: 78493
Epoch: [57]  [210/312]  eta: 0:01:50  lr: 0.003824  min_lr: 0.003824  loss: 2.3956 (2.5580)  weight_decay: 0.0500 (0.0500)  time: 1.0064  data: 0.0004  max mem: 78493
Epoch: [57]  [220/312]  eta: 0:01:39  lr: 0.003824  min_lr: 0.003824  loss: 2.6303 (2.5634)  weight_decay: 0.0500 (0.0500)  time: 1.0064  data: 0.0004  max mem: 78493
Epoch: [57]  [230/312]  eta: 0:01:28  lr: 0.003823  min_lr: 0.003823  loss: 2.6705 (2.5687)  weight_decay: 0.0500 (0.0500)  time: 1.0074  data: 0.0004  max mem: 78493
Epoch: [57]  [240/312]  eta: 0:01:17  lr: 0.003823  min_lr: 0.003823  loss: 2.6044 (2.5743)  weight_decay: 0.0500 (0.0500)  time: 1.0063  data: 0.0004  max mem: 78493
Epoch: [57]  [250/312]  eta: 0:01:06  lr: 0.003823  min_lr: 0.003823  loss: 2.5614 (2.5695)  weight_decay: 0.0500 (0.0500)  time: 1.0047  data: 0.0004  max mem: 78493
Epoch: [57]  [260/312]  eta: 0:00:55  lr: 0.003823  min_lr: 0.003823  loss: 2.5623 (2.5700)  weight_decay: 0.0500 (0.0500)  time: 1.0054  data: 0.0005  max mem: 78493
Epoch: [57]  [270/312]  eta: 0:00:44  lr: 0.003822  min_lr: 0.003822  loss: 2.7132 (2.5659)  weight_decay: 0.0500 (0.0500)  time: 1.0050  data: 0.0005  max mem: 78493
Epoch: [57]  [280/312]  eta: 0:00:34  lr: 0.003822  min_lr: 0.003822  loss: 2.6869 (2.5675)  weight_decay: 0.0500 (0.0500)  time: 1.0069  data: 0.0010  max mem: 78493
Epoch: [57]  [290/312]  eta: 0:00:23  lr: 0.003822  min_lr: 0.003822  loss: 2.6979 (2.5735)  weight_decay: 0.0500 (0.0500)  time: 1.0061  data: 0.0009  max mem: 78493
Epoch: [57]  [300/312]  eta: 0:00:12  lr: 0.003821  min_lr: 0.003821  loss: 2.8246 (2.5749)  weight_decay: 0.0500 (0.0500)  time: 1.0020  data: 0.0001  max mem: 78493
Epoch: [57]  [310/312]  eta: 0:00:02  lr: 0.003821  min_lr: 0.003821  loss: 2.8168 (2.5847)  weight_decay: 0.0500 (0.0500)  time: 1.0018  data: 0.0001  max mem: 78493
Epoch: [57]  [311/312]  eta: 0:00:01  lr: 0.003821  min_lr: 0.003821  loss: 2.8168 (2.5858)  weight_decay: 0.0500 (0.0500)  time: 1.0018  data: 0.0001  max mem: 78493
Epoch: [57] Total time: 0:05:32 (1.0649 s / it)
Averaged stats: lr: 0.003821  min_lr: 0.003821  loss: 2.8168 (2.6036)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:16  loss: 0.9399 (0.9399)  acc1: 77.3438 (77.3438)  acc5: 93.3594 (93.3594)  time: 8.4902  data: 8.2244  max mem: 78493
Test:  [8/9]  eta: 0:00:01  loss: 1.2850 (1.1854)  acc1: 69.5312 (70.8320)  acc5: 89.5833 (89.9360)  time: 1.1434  data: 0.9139  max mem: 78493
Test: Total time: 0:00:10 (1.1571 s / it)
* Acc@1 70.930 Acc@5 90.110 loss 1.182
Accuracy of the model on the 50000 test images: 70.9%
Max accuracy: 72.33%
Epoch: [58]  [  0/312]  eta: 1:27:15  lr: 0.003821  min_lr: 0.003821  loss: 2.7157 (2.7157)  weight_decay: 0.0500 (0.0500)  time: 16.7812  data: 15.7728  max mem: 78493
Epoch: [58]  [ 10/312]  eta: 0:12:30  lr: 0.003821  min_lr: 0.003821  loss: 2.7527 (2.6748)  weight_decay: 0.0500 (0.0500)  time: 2.4842  data: 1.4345  max mem: 78493
Epoch: [58]  [ 20/312]  eta: 0:08:48  lr: 0.003820  min_lr: 0.003820  loss: 2.7793 (2.6573)  weight_decay: 0.0500 (0.0500)  time: 1.0606  data: 0.0053  max mem: 78493
Epoch: [58]  [ 30/312]  eta: 0:07:18  lr: 0.003820  min_lr: 0.003820  loss: 2.7188 (2.6418)  weight_decay: 0.0500 (0.0500)  time: 1.0412  data: 0.0052  max mem: 78493
Epoch: [58]  [ 40/312]  eta: 0:06:26  lr: 0.003820  min_lr: 0.003820  loss: 2.5793 (2.6187)  weight_decay: 0.0500 (0.0500)  time: 1.0114  data: 0.0004  max mem: 78493
Epoch: [58]  [ 50/312]  eta: 0:05:51  lr: 0.003820  min_lr: 0.003820  loss: 2.6274 (2.6084)  weight_decay: 0.0500 (0.0500)  time: 1.0091  data: 0.0004  max mem: 78493
Epoch: [58]  [ 60/312]  eta: 0:05:23  lr: 0.003819  min_lr: 0.003819  loss: 2.6598 (2.5997)  weight_decay: 0.0500 (0.0500)  time: 1.0099  data: 0.0004  max mem: 78493
Epoch: [58]  [ 70/312]  eta: 0:05:01  lr: 0.003819  min_lr: 0.003819  loss: 2.6563 (2.5830)  weight_decay: 0.0500 (0.0500)  time: 1.0087  data: 0.0004  max mem: 78493
Epoch: [58]  [ 80/312]  eta: 0:04:42  lr: 0.003819  min_lr: 0.003819  loss: 2.6754 (2.6019)  weight_decay: 0.0500 (0.0500)  time: 1.0080  data: 0.0004  max mem: 78493
Epoch: [58]  [ 90/312]  eta: 0:04:25  lr: 0.003818  min_lr: 0.003818  loss: 2.6336 (2.5936)  weight_decay: 0.0500 (0.0500)  time: 1.0069  data: 0.0004  max mem: 78493
Epoch: [58]  [100/312]  eta: 0:04:09  lr: 0.003818  min_lr: 0.003818  loss: 2.6578 (2.6009)  weight_decay: 0.0500 (0.0500)  time: 1.0062  data: 0.0005  max mem: 78493
Epoch: [58]  [110/312]  eta: 0:03:54  lr: 0.003818  min_lr: 0.003818  loss: 2.6982 (2.6035)  weight_decay: 0.0500 (0.0500)  time: 1.0079  data: 0.0005  max mem: 78493
Epoch: [58]  [120/312]  eta: 0:03:40  lr: 0.003817  min_lr: 0.003817  loss: 2.6928 (2.6139)  weight_decay: 0.0500 (0.0500)  time: 1.0092  data: 0.0004  max mem: 78493
Epoch: [58]  [130/312]  eta: 0:03:26  lr: 0.003817  min_lr: 0.003817  loss: 2.6928 (2.6182)  weight_decay: 0.0500 (0.0500)  time: 1.0073  data: 0.0012  max mem: 78493
Epoch: [58]  [140/312]  eta: 0:03:14  lr: 0.003817  min_lr: 0.003817  loss: 2.8204 (2.6242)  weight_decay: 0.0500 (0.0500)  time: 1.0081  data: 0.0012  max mem: 78493
Epoch: [58]  [150/312]  eta: 0:03:01  lr: 0.003817  min_lr: 0.003817  loss: 2.8204 (2.6279)  weight_decay: 0.0500 (0.0500)  time: 1.0078  data: 0.0005  max mem: 78493
Epoch: [58]  [160/312]  eta: 0:02:49  lr: 0.003816  min_lr: 0.003816  loss: 2.8361 (2.6350)  weight_decay: 0.0500 (0.0500)  time: 1.0067  data: 0.0005  max mem: 78493
Epoch: [58]  [170/312]  eta: 0:02:37  lr: 0.003816  min_lr: 0.003816  loss: 2.8244 (2.6424)  weight_decay: 0.0500 (0.0500)  time: 1.0082  data: 0.0004  max mem: 78493
Epoch: [58]  [180/312]  eta: 0:02:25  lr: 0.003816  min_lr: 0.003816  loss: 2.8244 (2.6484)  weight_decay: 0.0500 (0.0500)  time: 1.0076  data: 0.0004  max mem: 78493
Epoch: [58]  [190/312]  eta: 0:02:13  lr: 0.003815  min_lr: 0.003815  loss: 2.8011 (2.6505)  weight_decay: 0.0500 (0.0500)  time: 1.0068  data: 0.0004  max mem: 78493
Epoch: [58]  [200/312]  eta: 0:02:02  lr: 0.003815  min_lr: 0.003815  loss: 2.5741 (2.6402)  weight_decay: 0.0500 (0.0500)  time: 1.0053  data: 0.0004  max mem: 78493
Epoch: [58]  [210/312]  eta: 0:01:50  lr: 0.003815  min_lr: 0.003815  loss: 2.4218 (2.6442)  weight_decay: 0.0500 (0.0500)  time: 1.0054  data: 0.0004  max mem: 78493
Epoch: [58]  [220/312]  eta: 0:01:39  lr: 0.003814  min_lr: 0.003814  loss: 2.5794 (2.6401)  weight_decay: 0.0500 (0.0500)  time: 1.0063  data: 0.0005  max mem: 78493
Epoch: [58]  [230/312]  eta: 0:01:28  lr: 0.003814  min_lr: 0.003814  loss: 2.7523 (2.6417)  weight_decay: 0.0500 (0.0500)  time: 1.0059  data: 0.0004  max mem: 78493
Epoch: [58]  [240/312]  eta: 0:01:17  lr: 0.003814  min_lr: 0.003814  loss: 2.7698 (2.6408)  weight_decay: 0.0500 (0.0500)  time: 1.0062  data: 0.0005  max mem: 78493
Epoch: [58]  [250/312]  eta: 0:01:06  lr: 0.003813  min_lr: 0.003813  loss: 2.4731 (2.6311)  weight_decay: 0.0500 (0.0500)  time: 1.0061  data: 0.0005  max mem: 78493
Epoch: [58]  [260/312]  eta: 0:00:55  lr: 0.003813  min_lr: 0.003813  loss: 2.3360 (2.6267)  weight_decay: 0.0500 (0.0500)  time: 1.0076  data: 0.0004  max mem: 78493
Epoch: [58]  [270/312]  eta: 0:00:44  lr: 0.003813  min_lr: 0.003813  loss: 2.5307 (2.6243)  weight_decay: 0.0500 (0.0500)  time: 1.0094  data: 0.0004  max mem: 78493
Epoch: [58]  [280/312]  eta: 0:00:34  lr: 0.003813  min_lr: 0.003813  loss: 2.6472 (2.6242)  weight_decay: 0.0500 (0.0500)  time: 1.0087  data: 0.0010  max mem: 78493
Epoch: [58]  [290/312]  eta: 0:00:23  lr: 0.003812  min_lr: 0.003812  loss: 2.7975 (2.6287)  weight_decay: 0.0500 (0.0500)  time: 1.0051  data: 0.0008  max mem: 78493
Epoch: [58]  [300/312]  eta: 0:00:12  lr: 0.003812  min_lr: 0.003812  loss: 2.8536 (2.6287)  weight_decay: 0.0500 (0.0500)  time: 1.0025  data: 0.0001  max mem: 78493
Epoch: [58]  [310/312]  eta: 0:00:02  lr: 0.003812  min_lr: 0.003812  loss: 2.6907 (2.6294)  weight_decay: 0.0500 (0.0500)  time: 1.0024  data: 0.0001  max mem: 78493
Epoch: [58]  [311/312]  eta: 0:00:01  lr: 0.003812  min_lr: 0.003812  loss: 2.6663 (2.6295)  weight_decay: 0.0500 (0.0500)  time: 1.0024  data: 0.0001  max mem: 78493
Epoch: [58] Total time: 0:05:32 (1.0670 s / it)
Averaged stats: lr: 0.003812  min_lr: 0.003812  loss: 2.6663 (2.5940)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:15  loss: 0.9804 (0.9804)  acc1: 77.0833 (77.0833)  acc5: 92.8385 (92.8385)  time: 8.4164  data: 8.1345  max mem: 78493
Test:  [8/9]  eta: 0:00:01  loss: 1.2531 (1.1538)  acc1: 71.4844 (71.6800)  acc5: 91.0156 (90.3360)  time: 1.1334  data: 0.9039  max mem: 78493
Test: Total time: 0:00:10 (1.1448 s / it)
* Acc@1 71.606 Acc@5 90.372 loss 1.147
Accuracy of the model on the 50000 test images: 71.6%
Max accuracy: 72.33%
Epoch: [59]  [  0/312]  eta: 1:27:06  lr: 0.003812  min_lr: 0.003812  loss: 2.5527 (2.5527)  weight_decay: 0.0500 (0.0500)  time: 16.7515  data: 13.3481  max mem: 78493
Epoch: [59]  [ 10/312]  eta: 0:13:18  lr: 0.003811  min_lr: 0.003811  loss: 2.8677 (2.7077)  weight_decay: 0.0500 (0.0500)  time: 2.6427  data: 1.3199  max mem: 78493
Epoch: [59]  [ 20/312]  eta: 0:09:06  lr: 0.003811  min_lr: 0.003811  loss: 2.4641 (2.5790)  weight_decay: 0.0500 (0.0500)  time: 1.1262  data: 0.0599  max mem: 78493
Epoch: [59]  [ 30/312]  eta: 0:07:28  lr: 0.003811  min_lr: 0.003811  loss: 2.4935 (2.5763)  weight_decay: 0.0500 (0.0500)  time: 1.0127  data: 0.0016  max mem: 78493
Epoch: [59]  [ 40/312]  eta: 0:06:34  lr: 0.003810  min_lr: 0.003810  loss: 2.6963 (2.5565)  weight_decay: 0.0500 (0.0500)  time: 1.0063  data: 0.0004  max mem: 78493
Epoch: [59]  [ 50/312]  eta: 0:05:56  lr: 0.003810  min_lr: 0.003810  loss: 2.5034 (2.5501)  weight_decay: 0.0500 (0.0500)  time: 1.0082  data: 0.0004  max mem: 78493
Epoch: [59]  [ 60/312]  eta: 0:05:28  lr: 0.003810  min_lr: 0.003810  loss: 2.5034 (2.5184)  weight_decay: 0.0500 (0.0500)  time: 1.0098  data: 0.0004  max mem: 78493
Epoch: [59]  [ 70/312]  eta: 0:05:05  lr: 0.003809  min_lr: 0.003809  loss: 2.6570 (2.5651)  weight_decay: 0.0500 (0.0500)  time: 1.0096  data: 0.0005  max mem: 78493
Epoch: [59]  [ 80/312]  eta: 0:04:45  lr: 0.003809  min_lr: 0.003809  loss: 2.7694 (2.5631)  weight_decay: 0.0500 (0.0500)  time: 1.0094  data: 0.0005  max mem: 78493
Epoch: [59]  [ 90/312]  eta: 0:04:28  lr: 0.003809  min_lr: 0.003809  loss: 2.5154 (2.5758)  weight_decay: 0.0500 (0.0500)  time: 1.0112  data: 0.0005  max mem: 78493
Epoch: [59]  [100/312]  eta: 0:04:11  lr: 0.003809  min_lr: 0.003809  loss: 2.6874 (2.5808)  weight_decay: 0.0500 (0.0500)  time: 1.0121  data: 0.0005  max mem: 78493
Epoch: [59]  [110/312]  eta: 0:03:56  lr: 0.003808  min_lr: 0.003808  loss: 2.7279 (2.5945)  weight_decay: 0.0500 (0.0500)  time: 1.0129  data: 0.0004  max mem: 78493
Epoch: [59]  [120/312]  eta: 0:03:42  lr: 0.003808  min_lr: 0.003808  loss: 2.7076 (2.5988)  weight_decay: 0.0500 (0.0500)  time: 1.0121  data: 0.0013  max mem: 78493
Epoch: [59]  [130/312]  eta: 0:03:28  lr: 0.003808  min_lr: 0.003808  loss: 2.4950 (2.5836)  weight_decay: 0.0500 (0.0500)  time: 1.0107  data: 0.0012  max mem: 78493
Epoch: [59]  [140/312]  eta: 0:03:15  lr: 0.003807  min_lr: 0.003807  loss: 2.3018 (2.5732)  weight_decay: 0.0500 (0.0500)  time: 1.0082  data: 0.0004  max mem: 78493
Epoch: [59]  [150/312]  eta: 0:03:02  lr: 0.003807  min_lr: 0.003807  loss: 2.6255 (2.5803)  weight_decay: 0.0500 (0.0500)  time: 1.0095  data: 0.0004  max mem: 78493
Epoch: [59]  [160/312]  eta: 0:02:50  lr: 0.003807  min_lr: 0.003807  loss: 2.6355 (2.5662)  weight_decay: 0.0500 (0.0500)  time: 1.0105  data: 0.0004  max mem: 78493
Epoch: [59]  [170/312]  eta: 0:02:38  lr: 0.003806  min_lr: 0.003806  loss: 2.3684 (2.5690)  weight_decay: 0.0500 (0.0500)  time: 1.0078  data: 0.0004  max mem: 78493
Epoch: [59]  [180/312]  eta: 0:02:26  lr: 0.003806  min_lr: 0.003806  loss: 2.5547 (2.5686)  weight_decay: 0.0500 (0.0500)  time: 1.0072  data: 0.0005  max mem: 78493
Epoch: [59]  [190/312]  eta: 0:02:14  lr: 0.003806  min_lr: 0.003806  loss: 2.6107 (2.5672)  weight_decay: 0.0500 (0.0500)  time: 1.0070  data: 0.0004  max mem: 78493
Epoch: [59]  [200/312]  eta: 0:02:03  lr: 0.003805  min_lr: 0.003805  loss: 2.7574 (2.5734)  weight_decay: 0.0500 (0.0500)  time: 1.0081  data: 0.0005  max mem: 78493
Epoch: [59]  [210/312]  eta: 0:01:51  lr: 0.003805  min_lr: 0.003805  loss: 2.7438 (2.5726)  weight_decay: 0.0500 (0.0500)  time: 1.0073  data: 0.0005  max mem: 78493
Epoch: [59]  [220/312]  eta: 0:01:40  lr: 0.003805  min_lr: 0.003805  loss: 2.5634 (2.5593)  weight_decay: 0.0500 (0.0500)  time: 1.0062  data: 0.0011  max mem: 78493
Epoch: [59]  [230/312]  eta: 0:01:29  lr: 0.003805  min_lr: 0.003805  loss: 2.2569 (2.5595)  weight_decay: 0.0500 (0.0500)  time: 1.0075  data: 0.0017  max mem: 78493
Epoch: [59]  [240/312]  eta: 0:01:18  lr: 0.003804  min_lr: 0.003804  loss: 2.6586 (2.5671)  weight_decay: 0.0500 (0.0500)  time: 1.0073  data: 0.0010  max mem: 78493
Epoch: [59]  [250/312]  eta: 0:01:07  lr: 0.003804  min_lr: 0.003804  loss: 2.7175 (2.5694)  weight_decay: 0.0500 (0.0500)  time: 1.0071  data: 0.0004  max mem: 78493
Epoch: [59]  [260/312]  eta: 0:00:56  lr: 0.003804  min_lr: 0.003804  loss: 2.6906 (2.5711)  weight_decay: 0.0500 (0.0500)  time: 1.0076  data: 0.0004  max mem: 78493
Epoch: [59]  [270/312]  eta: 0:00:45  lr: 0.003803  min_lr: 0.003803  loss: 2.5559 (2.5648)  weight_decay: 0.0500 (0.0500)  time: 1.0062  data: 0.0004  max mem: 78493
Epoch: [59]  [280/312]  eta: 0:00:34  lr: 0.003803  min_lr: 0.003803  loss: 2.6395 (2.5683)  weight_decay: 0.0500 (0.0500)  time: 1.0069  data: 0.0010  max mem: 78493
Epoch: [59]  [290/312]  eta: 0:00:23  lr: 0.003803  min_lr: 0.003803  loss: 2.7045 (2.5735)  weight_decay: 0.0500 (0.0500)  time: 1.0054  data: 0.0009  max mem: 78493
Epoch: [59]  [300/312]  eta: 0:00:12  lr: 0.003802  min_lr: 0.003802  loss: 2.6767 (2.5680)  weight_decay: 0.0500 (0.0500)  time: 1.0019  data: 0.0001  max mem: 78493
Epoch: [59]  [310/312]  eta: 0:00:02  lr: 0.003802  min_lr: 0.003802  loss: 2.3328 (2.5626)  weight_decay: 0.0500 (0.0500)  time: 1.0023  data: 0.0001  max mem: 78493
Epoch: [59]  [311/312]  eta: 0:00:01  lr: 0.003802  min_lr: 0.003802  loss: 2.3735 (2.5623)  weight_decay: 0.0500 (0.0500)  time: 1.0022  data: 0.0001  max mem: 78493
Epoch: [59] Total time: 0:05:34 (1.0716 s / it)
Averaged stats: lr: 0.003802  min_lr: 0.003802  loss: 2.3735 (2.5837)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:17  loss: 0.8944 (0.8944)  acc1: 78.9062 (78.9062)  acc5: 94.0104 (94.0104)  time: 8.6020  data: 8.3347  max mem: 78493
Test:  [8/9]  eta: 0:00:01  loss: 1.2769 (1.1302)  acc1: 69.1406 (71.4560)  acc5: 89.1927 (90.3200)  time: 1.1549  data: 0.9262  max mem: 78493
Test: Total time: 0:00:10 (1.1976 s / it)
* Acc@1 72.080 Acc@5 90.640 loss 1.115
Accuracy of the model on the 50000 test images: 72.1%
Max accuracy: 72.33%
Epoch: [60]  [  0/312]  eta: 1:24:03  lr: 0.003802  min_lr: 0.003802  loss: 2.5181 (2.5181)  weight_decay: 0.0500 (0.0500)  time: 16.1663  data: 13.3410  max mem: 78493
Epoch: [60]  [ 10/312]  eta: 0:12:51  lr: 0.003802  min_lr: 0.003802  loss: 2.5181 (2.5664)  weight_decay: 0.0500 (0.0500)  time: 2.5560  data: 1.3603  max mem: 78493
Epoch: [60]  [ 20/312]  eta: 0:08:53  lr: 0.003801  min_lr: 0.003801  loss: 2.4915 (2.4997)  weight_decay: 0.0500 (0.0500)  time: 1.1107  data: 0.0814  max mem: 78493
Epoch: [60]  [ 30/312]  eta: 0:07:20  lr: 0.003801  min_lr: 0.003801  loss: 2.5489 (2.5238)  weight_decay: 0.0500 (0.0500)  time: 1.0154  data: 0.0006  max mem: 78493
Epoch: [60]  [ 40/312]  eta: 0:06:28  lr: 0.003801  min_lr: 0.003801  loss: 2.5138 (2.5016)  weight_decay: 0.0500 (0.0500)  time: 1.0060  data: 0.0004  max mem: 78493
Epoch: [60]  [ 50/312]  eta: 0:05:52  lr: 0.003800  min_lr: 0.003800  loss: 2.6079 (2.5376)  weight_decay: 0.0500 (0.0500)  time: 1.0080  data: 0.0004  max mem: 78493
Epoch: [60]  [ 60/312]  eta: 0:05:24  lr: 0.003800  min_lr: 0.003800  loss: 2.7249 (2.5477)  weight_decay: 0.0500 (0.0500)  time: 1.0082  data: 0.0012  max mem: 78493
Epoch: [60]  [ 70/312]  eta: 0:05:02  lr: 0.003800  min_lr: 0.003800  loss: 2.6262 (2.5561)  weight_decay: 0.0500 (0.0500)  time: 1.0080  data: 0.0012  max mem: 78493
Epoch: [60]  [ 80/312]  eta: 0:04:43  lr: 0.003799  min_lr: 0.003799  loss: 2.6748 (2.5742)  weight_decay: 0.0500 (0.0500)  time: 1.0077  data: 0.0004  max mem: 78493
Epoch: [60]  [ 90/312]  eta: 0:04:25  lr: 0.003799  min_lr: 0.003799  loss: 2.6662 (2.5810)  weight_decay: 0.0500 (0.0500)  time: 1.0083  data: 0.0004  max mem: 78493
Epoch: [60]  [100/312]  eta: 0:04:09  lr: 0.003799  min_lr: 0.003799  loss: 2.5589 (2.5670)  weight_decay: 0.0500 (0.0500)  time: 1.0099  data: 0.0004  max mem: 78493
Epoch: [60]  [110/312]  eta: 0:03:54  lr: 0.003799  min_lr: 0.003799  loss: 2.4424 (2.5645)  weight_decay: 0.0500 (0.0500)  time: 1.0089  data: 0.0004  max mem: 78493
Epoch: [60]  [120/312]  eta: 0:03:40  lr: 0.003798  min_lr: 0.003798  loss: 2.6766 (2.5620)  weight_decay: 0.0500 (0.0500)  time: 1.0079  data: 0.0004  max mem: 78493
Epoch: [60]  [130/312]  eta: 0:03:27  lr: 0.003798  min_lr: 0.003798  loss: 2.5953 (2.5467)  weight_decay: 0.0500 (0.0500)  time: 1.0083  data: 0.0012  max mem: 78493
Epoch: [60]  [140/312]  eta: 0:03:14  lr: 0.003798  min_lr: 0.003798  loss: 2.5954 (2.5511)  weight_decay: 0.0500 (0.0500)  time: 1.0077  data: 0.0012  max mem: 78493
Epoch: [60]  [150/312]  eta: 0:03:01  lr: 0.003797  min_lr: 0.003797  loss: 2.7528 (2.5609)  weight_decay: 0.0500 (0.0500)  time: 1.0089  data: 0.0004  max mem: 78493
Epoch: [60]  [160/312]  eta: 0:02:49  lr: 0.003797  min_lr: 0.003797  loss: 2.7748 (2.5626)  weight_decay: 0.0500 (0.0500)  time: 1.0072  data: 0.0004  max mem: 78493
Epoch: [60]  [170/312]  eta: 0:02:37  lr: 0.003797  min_lr: 0.003797  loss: 2.7250 (2.5779)  weight_decay: 0.0500 (0.0500)  time: 1.0042  data: 0.0004  max mem: 78493
Epoch: [60]  [180/312]  eta: 0:02:25  lr: 0.003796  min_lr: 0.003796  loss: 2.7250 (2.5836)  weight_decay: 0.0500 (0.0500)  time: 1.0041  data: 0.0004  max mem: 78493
Epoch: [60]  [190/312]  eta: 0:02:13  lr: 0.003796  min_lr: 0.003796  loss: 2.6307 (2.5807)  weight_decay: 0.0500 (0.0500)  time: 1.0040  data: 0.0005  max mem: 78493
Epoch: [60]  [200/312]  eta: 0:02:02  lr: 0.003796  min_lr: 0.003796  loss: 2.5708 (2.5788)  weight_decay: 0.0500 (0.0500)  time: 1.0057  data: 0.0005  max mem: 78493
Epoch: [60]  [210/312]  eta: 0:01:51  lr: 0.003795  min_lr: 0.003795  loss: 2.6357 (2.5855)  weight_decay: 0.0500 (0.0500)  time: 1.0055  data: 0.0005  max mem: 78493
Epoch: [60]  [220/312]  eta: 0:01:39  lr: 0.003795  min_lr: 0.003795  loss: 2.6357 (2.5773)  weight_decay: 0.0500 (0.0500)  time: 1.0041  data: 0.0004  max mem: 78493
Epoch: [60]  [230/312]  eta: 0:01:28  lr: 0.003795  min_lr: 0.003795  loss: 2.4680 (2.5780)  weight_decay: 0.0500 (0.0500)  time: 1.0050  data: 0.0004  max mem: 78493
Epoch: [60]  [240/312]  eta: 0:01:17  lr: 0.003794  min_lr: 0.003794  loss: 2.4665 (2.5681)  weight_decay: 0.0500 (0.0500)  time: 1.0060  data: 0.0004  max mem: 78493
Epoch: [60]  [250/312]  eta: 0:01:06  lr: 0.003794  min_lr: 0.003794  loss: 2.5475 (2.5730)  weight_decay: 0.0500 (0.0500)  time: 1.0057  data: 0.0004  max mem: 78493
Epoch: [60]  [260/312]  eta: 0:00:55  lr: 0.003794  min_lr: 0.003794  loss: 2.6771 (2.5767)  weight_decay: 0.0500 (0.0500)  time: 1.0050  data: 0.0004  max mem: 78493
Epoch: [60]  [270/312]  eta: 0:00:44  lr: 0.003793  min_lr: 0.003793  loss: 2.8011 (2.5741)  weight_decay: 0.0500 (0.0500)  time: 1.0043  data: 0.0005  max mem: 78493
Epoch: [60]  [280/312]  eta: 0:00:34  lr: 0.003793  min_lr: 0.003793  loss: 2.5182 (2.5713)  weight_decay: 0.0500 (0.0500)  time: 1.0051  data: 0.0017  max mem: 78493
Epoch: [60]  [290/312]  eta: 0:00:23  lr: 0.003793  min_lr: 0.003793  loss: 2.6826 (2.5747)  weight_decay: 0.0500 (0.0500)  time: 1.0038  data: 0.0015  max mem: 78493
Epoch: [60]  [300/312]  eta: 0:00:12  lr: 0.003793  min_lr: 0.003793  loss: 2.6282 (2.5751)  weight_decay: 0.0500 (0.0500)  time: 1.0015  data: 0.0001  max mem: 78493
Epoch: [60]  [310/312]  eta: 0:00:02  lr: 0.003792  min_lr: 0.003792  loss: 2.6268 (2.5719)  weight_decay: 0.0500 (0.0500)  time: 1.0017  data: 0.0001  max mem: 78493
Epoch: [60]  [311/312]  eta: 0:00:01  lr: 0.003792  min_lr: 0.003792  loss: 2.6282 (2.5724)  weight_decay: 0.0500 (0.0500)  time: 1.0016  data: 0.0001  max mem: 78493
Epoch: [60] Total time: 0:05:32 (1.0668 s / it)
Averaged stats: lr: 0.003792  min_lr: 0.003792  loss: 2.6282 (2.5831)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:16  loss: 0.8947 (0.8947)  acc1: 78.6458 (78.6458)  acc5: 94.5312 (94.5312)  time: 8.5314  data: 8.2498  max mem: 78493
Test:  [8/9]  eta: 0:00:01  loss: 1.1935 (1.1331)  acc1: 72.5260 (71.8240)  acc5: 90.4948 (90.7680)  time: 1.1462  data: 0.9168  max mem: 78493
Test: Total time: 0:00:10 (1.1643 s / it)
* Acc@1 72.132 Acc@5 90.796 loss 1.120
Accuracy of the model on the 50000 test images: 72.1%
Max accuracy: 72.33%
Epoch: [61]  [  0/312]  eta: 1:25:56  lr: 0.003792  min_lr: 0.003792  loss: 2.9373 (2.9373)  weight_decay: 0.0500 (0.0500)  time: 16.5282  data: 13.3265  max mem: 78493
Epoch: [61]  [ 10/312]  eta: 0:13:01  lr: 0.003792  min_lr: 0.003792  loss: 2.3169 (2.4066)  weight_decay: 0.0500 (0.0500)  time: 2.5892  data: 1.2169  max mem: 78493
Epoch: [61]  [ 20/312]  eta: 0:08:57  lr: 0.003792  min_lr: 0.003792  loss: 2.3697 (2.4786)  weight_decay: 0.0500 (0.0500)  time: 1.1066  data: 0.0032  max mem: 78493
Epoch: [61]  [ 30/312]  eta: 0:07:23  lr: 0.003791  min_lr: 0.003791  loss: 2.6138 (2.5285)  weight_decay: 0.0500 (0.0500)  time: 1.0122  data: 0.0005  max mem: 78493
Epoch: [61]  [ 40/312]  eta: 0:06:29  lr: 0.003791  min_lr: 0.003791  loss: 2.6179 (2.5726)  weight_decay: 0.0500 (0.0500)  time: 1.0062  data: 0.0004  max mem: 78493
Epoch: [61]  [ 50/312]  eta: 0:05:53  lr: 0.003791  min_lr: 0.003791  loss: 2.7890 (2.5987)  weight_decay: 0.0500 (0.0500)  time: 1.0065  data: 0.0004  max mem: 78493
Epoch: [61]  [ 60/312]  eta: 0:05:26  lr: 0.003790  min_lr: 0.003790  loss: 2.6176 (2.5704)  weight_decay: 0.0500 (0.0500)  time: 1.0086  data: 0.0005  max mem: 78493
Epoch: [61]  [ 70/312]  eta: 0:05:03  lr: 0.003790  min_lr: 0.003790  loss: 2.6495 (2.6062)  weight_decay: 0.0500 (0.0500)  time: 1.0122  data: 0.0005  max mem: 78493
Epoch: [61]  [ 80/312]  eta: 0:04:44  lr: 0.003790  min_lr: 0.003790  loss: 2.8571 (2.6338)  weight_decay: 0.0500 (0.0500)  time: 1.0128  data: 0.0005  max mem: 78493
Epoch: [61]  [ 90/312]  eta: 0:04:26  lr: 0.003789  min_lr: 0.003789  loss: 2.7855 (2.6185)  weight_decay: 0.0500 (0.0500)  time: 1.0102  data: 0.0004  max mem: 78493
Epoch: [61]  [100/312]  eta: 0:04:10  lr: 0.003789  min_lr: 0.003789  loss: 2.4247 (2.5914)  weight_decay: 0.0500 (0.0500)  time: 1.0078  data: 0.0004  max mem: 78493
Epoch: [61]  [110/312]  eta: 0:03:55  lr: 0.003789  min_lr: 0.003789  loss: 2.4255 (2.5825)  weight_decay: 0.0500 (0.0500)  time: 1.0081  data: 0.0004  max mem: 78493
Epoch: [61]  [120/312]  eta: 0:03:41  lr: 0.003788  min_lr: 0.003788  loss: 2.6009 (2.5826)  weight_decay: 0.0500 (0.0500)  time: 1.0082  data: 0.0005  max mem: 78493
Epoch: [61]  [130/312]  eta: 0:03:27  lr: 0.003788  min_lr: 0.003788  loss: 2.6026 (2.5752)  weight_decay: 0.0500 (0.0500)  time: 1.0060  data: 0.0005  max mem: 78493
Epoch: [61]  [140/312]  eta: 0:03:14  lr: 0.003788  min_lr: 0.003788  loss: 2.8303 (2.5884)  weight_decay: 0.0500 (0.0500)  time: 1.0063  data: 0.0004  max mem: 78493
Epoch: [61]  [150/312]  eta: 0:03:02  lr: 0.003787  min_lr: 0.003787  loss: 2.8282 (2.5909)  weight_decay: 0.0500 (0.0500)  time: 1.0074  data: 0.0004  max mem: 78493
Epoch: [61]  [160/312]  eta: 0:02:49  lr: 0.003787  min_lr: 0.003787  loss: 2.6538 (2.5905)  weight_decay: 0.0500 (0.0500)  time: 1.0067  data: 0.0004  max mem: 78493
Epoch: [61]  [170/312]  eta: 0:02:37  lr: 0.003787  min_lr: 0.003787  loss: 2.6381 (2.5944)  weight_decay: 0.0500 (0.0500)  time: 1.0071  data: 0.0004  max mem: 78493
Epoch: [61]  [180/312]  eta: 0:02:25  lr: 0.003786  min_lr: 0.003786  loss: 2.7490 (2.5992)  weight_decay: 0.0500 (0.0500)  time: 1.0063  data: 0.0004  max mem: 78493
Epoch: [61]  [190/312]  eta: 0:02:14  lr: 0.003786  min_lr: 0.003786  loss: 2.7221 (2.6084)  weight_decay: 0.0500 (0.0500)  time: 1.0054  data: 0.0004  max mem: 78493
Epoch: [61]  [200/312]  eta: 0:02:02  lr: 0.003786  min_lr: 0.003786  loss: 2.7149 (2.6166)  weight_decay: 0.0500 (0.0500)  time: 1.0061  data: 0.0005  max mem: 78493
Epoch: [61]  [210/312]  eta: 0:01:51  lr: 0.003785  min_lr: 0.003785  loss: 2.6692 (2.6150)  weight_decay: 0.0500 (0.0500)  time: 1.0058  data: 0.0004  max mem: 78493
Epoch: [61]  [220/312]  eta: 0:01:39  lr: 0.003785  min_lr: 0.003785  loss: 2.5639 (2.6052)  weight_decay: 0.0500 (0.0500)  time: 1.0047  data: 0.0005  max mem: 78493
Epoch: [61]  [230/312]  eta: 0:01:28  lr: 0.003785  min_lr: 0.003785  loss: 2.5660 (2.6014)  weight_decay: 0.0500 (0.0500)  time: 1.0044  data: 0.0005  max mem: 78493
Epoch: [61]  [240/312]  eta: 0:01:17  lr: 0.003784  min_lr: 0.003784  loss: 2.4677 (2.5958)  weight_decay: 0.0500 (0.0500)  time: 1.0049  data: 0.0004  max mem: 78493
Epoch: [61]  [250/312]  eta: 0:01:06  lr: 0.003784  min_lr: 0.003784  loss: 2.2540 (2.5880)  weight_decay: 0.0500 (0.0500)  time: 1.0040  data: 0.0004  max mem: 78493
Epoch: [61]  [260/312]  eta: 0:00:55  lr: 0.003784  min_lr: 0.003784  loss: 2.6103 (2.5915)  weight_decay: 0.0500 (0.0500)  time: 1.0045  data: 0.0004  max mem: 78493
Epoch: [61]  [270/312]  eta: 0:00:45  lr: 0.003783  min_lr: 0.003783  loss: 2.7390 (2.5934)  weight_decay: 0.0500 (0.0500)  time: 1.0051  data: 0.0004  max mem: 78493
Epoch: [61]  [280/312]  eta: 0:00:34  lr: 0.003783  min_lr: 0.003783  loss: 2.6410 (2.5944)  weight_decay: 0.0500 (0.0500)  time: 1.0057  data: 0.0018  max mem: 78493
Epoch: [61]  [290/312]  eta: 0:00:23  lr: 0.003783  min_lr: 0.003783  loss: 2.5721 (2.5906)  weight_decay: 0.0500 (0.0500)  time: 1.0041  data: 0.0016  max mem: 78493
Epoch: [61]  [300/312]  eta: 0:00:12  lr: 0.003782  min_lr: 0.003782  loss: 2.3509 (2.5838)  weight_decay: 0.0500 (0.0500)  time: 1.0014  data: 0.0001  max mem: 78493
Epoch: [61]  [310/312]  eta: 0:00:02  lr: 0.003782  min_lr: 0.003782  loss: 2.5464 (2.5858)  weight_decay: 0.0500 (0.0500)  time: 1.0017  data: 0.0001  max mem: 78493
Epoch: [61]  [311/312]  eta: 0:00:01  lr: 0.003782  min_lr: 0.003782  loss: 2.5755 (2.5864)  weight_decay: 0.0500 (0.0500)  time: 1.0016  data: 0.0001  max mem: 78493
Epoch: [61] Total time: 0:05:33 (1.0680 s / it)
Averaged stats: lr: 0.003782  min_lr: 0.003782  loss: 2.5755 (2.5859)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:07  loss: 0.9009 (0.9009)  acc1: 78.6458 (78.6458)  acc5: 94.0104 (94.0104)  time: 7.4875  data: 7.2080  max mem: 78493
Test:  [8/9]  eta: 0:00:01  loss: 1.3741 (1.1992)  acc1: 69.2708 (71.6960)  acc5: 89.9740 (90.1440)  time: 1.0526  data: 0.8234  max mem: 78493
Test: Total time: 0:00:09 (1.0630 s / it)
* Acc@1 71.208 Acc@5 90.228 loss 1.204
Accuracy of the model on the 50000 test images: 71.2%
Max accuracy: 72.33%
Epoch: [62]  [  0/312]  eta: 1:27:10  lr: 0.003782  min_lr: 0.003782  loss: 2.8697 (2.8697)  weight_decay: 0.0500 (0.0500)  time: 16.7649  data: 14.7686  max mem: 78493
Epoch: [62]  [ 10/312]  eta: 0:13:32  lr: 0.003782  min_lr: 0.003782  loss: 2.6828 (2.5982)  weight_decay: 0.0500 (0.0500)  time: 2.6914  data: 1.3433  max mem: 78493
Epoch: [62]  [ 20/312]  eta: 0:09:11  lr: 0.003781  min_lr: 0.003781  loss: 2.6828 (2.6089)  weight_decay: 0.0500 (0.0500)  time: 1.1453  data: 0.0006  max mem: 78493
Epoch: [62]  [ 30/312]  eta: 0:07:32  lr: 0.003781  min_lr: 0.003781  loss: 2.4547 (2.5220)  weight_decay: 0.0500 (0.0500)  time: 1.0057  data: 0.0004  max mem: 78493
Epoch: [62]  [ 40/312]  eta: 0:06:36  lr: 0.003781  min_lr: 0.003781  loss: 2.3931 (2.5046)  weight_decay: 0.0500 (0.0500)  time: 1.0048  data: 0.0004  max mem: 78493
Epoch: [62]  [ 50/312]  eta: 0:05:58  lr: 0.003780  min_lr: 0.003780  loss: 2.3931 (2.4672)  weight_decay: 0.0500 (0.0500)  time: 1.0054  data: 0.0004  max mem: 78493
Epoch: [62]  [ 60/312]  eta: 0:05:30  lr: 0.003780  min_lr: 0.003780  loss: 2.5259 (2.4934)  weight_decay: 0.0500 (0.0500)  time: 1.0062  data: 0.0004  max mem: 78493
Epoch: [62]  [ 70/312]  eta: 0:05:06  lr: 0.003780  min_lr: 0.003780  loss: 2.6691 (2.5152)  weight_decay: 0.0500 (0.0500)  time: 1.0072  data: 0.0004  max mem: 78493
Epoch: [62]  [ 80/312]  eta: 0:04:46  lr: 0.003779  min_lr: 0.003779  loss: 2.8322 (2.5599)  weight_decay: 0.0500 (0.0500)  time: 1.0083  data: 0.0004  max mem: 78493
Epoch: [62]  [ 90/312]  eta: 0:04:28  lr: 0.003779  min_lr: 0.003779  loss: 2.7453 (2.5573)  weight_decay: 0.0500 (0.0500)  time: 1.0088  data: 0.0004  max mem: 78493
Epoch: [62]  [100/312]  eta: 0:04:12  lr: 0.003779  min_lr: 0.003779  loss: 2.6449 (2.5703)  weight_decay: 0.0500 (0.0500)  time: 1.0089  data: 0.0004  max mem: 78493
Epoch: [62]  [110/312]  eta: 0:03:57  lr: 0.003778  min_lr: 0.003778  loss: 2.7135 (2.5788)  weight_decay: 0.0500 (0.0500)  time: 1.0092  data: 0.0004  max mem: 78493
Epoch: [62]  [120/312]  eta: 0:03:42  lr: 0.003778  min_lr: 0.003778  loss: 2.6417 (2.5793)  weight_decay: 0.0500 (0.0500)  time: 1.0084  data: 0.0004  max mem: 78493
Epoch: [62]  [130/312]  eta: 0:03:29  lr: 0.003778  min_lr: 0.003778  loss: 2.6417 (2.5856)  weight_decay: 0.0500 (0.0500)  time: 1.0058  data: 0.0004  max mem: 78493
Epoch: [62]  [140/312]  eta: 0:03:15  lr: 0.003777  min_lr: 0.003777  loss: 2.7939 (2.5974)  weight_decay: 0.0500 (0.0500)  time: 1.0046  data: 0.0005  max mem: 78493
Epoch: [62]  [150/312]  eta: 0:03:02  lr: 0.003777  min_lr: 0.003777  loss: 2.7939 (2.5982)  weight_decay: 0.0500 (0.0500)  time: 1.0055  data: 0.0004  max mem: 78493
Epoch: [62]  [160/312]  eta: 0:02:50  lr: 0.003777  min_lr: 0.003777  loss: 2.6235 (2.5897)  weight_decay: 0.0500 (0.0500)  time: 1.0065  data: 0.0004  max mem: 78493
Epoch: [62]  [170/312]  eta: 0:02:38  lr: 0.003776  min_lr: 0.003776  loss: 2.5278 (2.5817)  weight_decay: 0.0500 (0.0500)  time: 1.0058  data: 0.0004  max mem: 78493
Epoch: [62]  [180/312]  eta: 0:02:26  lr: 0.003776  min_lr: 0.003776  loss: 2.5942 (2.5828)  weight_decay: 0.0500 (0.0500)  time: 1.0054  data: 0.0004  max mem: 78493
Epoch: [62]  [190/312]  eta: 0:02:14  lr: 0.003776  min_lr: 0.003776  loss: 2.5941 (2.5869)  weight_decay: 0.0500 (0.0500)  time: 1.0053  data: 0.0005  max mem: 78493
Epoch: [62]  [200/312]  eta: 0:02:03  lr: 0.003775  min_lr: 0.003775  loss: 2.7605 (2.5893)  weight_decay: 0.0500 (0.0500)  time: 1.0064  data: 0.0005  max mem: 78493
Epoch: [62]  [210/312]  eta: 0:01:51  lr: 0.003775  min_lr: 0.003775  loss: 2.7480 (2.5893)  weight_decay: 0.0500 (0.0500)  time: 1.0069  data: 0.0004  max mem: 78493
Epoch: [62]  [220/312]  eta: 0:01:40  lr: 0.003775  min_lr: 0.003775  loss: 2.6093 (2.5908)  weight_decay: 0.0500 (0.0500)  time: 1.0067  data: 0.0004  max mem: 78493
Epoch: [62]  [230/312]  eta: 0:01:29  lr: 0.003774  min_lr: 0.003774  loss: 2.6093 (2.5949)  weight_decay: 0.0500 (0.0500)  time: 1.0059  data: 0.0004  max mem: 78493
Epoch: [62]  [240/312]  eta: 0:01:17  lr: 0.003774  min_lr: 0.003774  loss: 2.6672 (2.5905)  weight_decay: 0.0500 (0.0500)  time: 1.0042  data: 0.0004  max mem: 78493
Epoch: [62]  [250/312]  eta: 0:01:06  lr: 0.003774  min_lr: 0.003774  loss: 2.4782 (2.5909)  weight_decay: 0.0500 (0.0500)  time: 1.0049  data: 0.0005  max mem: 78493
Epoch: [62]  [260/312]  eta: 0:00:56  lr: 0.003774  min_lr: 0.003774  loss: 2.5911 (2.5919)  weight_decay: 0.0500 (0.0500)  time: 1.0051  data: 0.0005  max mem: 78493
Epoch: [62]  [270/312]  eta: 0:00:45  lr: 0.003773  min_lr: 0.003773  loss: 2.6639 (2.5933)  weight_decay: 0.0500 (0.0500)  time: 1.0048  data: 0.0004  max mem: 78493
Epoch: [62]  [280/312]  eta: 0:00:34  lr: 0.003773  min_lr: 0.003773  loss: 2.6639 (2.5951)  weight_decay: 0.0500 (0.0500)  time: 1.0054  data: 0.0010  max mem: 78493
Epoch: [62]  [290/312]  eta: 0:00:23  lr: 0.003773  min_lr: 0.003773  loss: 2.6869 (2.5966)  weight_decay: 0.0500 (0.0500)  time: 1.0038  data: 0.0009  max mem: 78493
Epoch: [62]  [300/312]  eta: 0:00:12  lr: 0.003772  min_lr: 0.003772  loss: 2.6696 (2.5929)  weight_decay: 0.0500 (0.0500)  time: 1.0017  data: 0.0001  max mem: 78493
Epoch: [62]  [310/312]  eta: 0:00:02  lr: 0.003772  min_lr: 0.003772  loss: 2.4563 (2.5886)  weight_decay: 0.0500 (0.0500)  time: 1.0016  data: 0.0001  max mem: 78493
Epoch: [62]  [311/312]  eta: 0:00:01  lr: 0.003772  min_lr: 0.003772  loss: 2.4563 (2.5868)  weight_decay: 0.0500 (0.0500)  time: 1.0015  data: 0.0001  max mem: 78493
Epoch: [62] Total time: 0:05:34 (1.0709 s / it)
Averaged stats: lr: 0.003772  min_lr: 0.003772  loss: 2.4563 (2.5591)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:09  loss: 0.8370 (0.8370)  acc1: 78.3854 (78.3854)  acc5: 94.1406 (94.1406)  time: 7.7762  data: 7.5121  max mem: 78493
Test:  [8/9]  eta: 0:00:01  loss: 1.2136 (1.1157)  acc1: 71.4844 (71.3440)  acc5: 89.5833 (90.4160)  time: 1.0657  data: 0.8348  max mem: 78493
Test: Total time: 0:00:09 (1.0867 s / it)
* Acc@1 71.868 Acc@5 90.652 loss 1.108
Accuracy of the model on the 50000 test images: 71.9%
Max accuracy: 72.33%
Epoch: [63]  [  0/312]  eta: 1:25:40  lr: 0.003772  min_lr: 0.003772  loss: 2.0075 (2.0075)  weight_decay: 0.0500 (0.0500)  time: 16.4749  data: 15.1165  max mem: 78493
Epoch: [63]  [ 10/312]  eta: 0:13:22  lr: 0.003771  min_lr: 0.003771  loss: 2.5474 (2.4713)  weight_decay: 0.0500 (0.0500)  time: 2.6560  data: 1.3774  max mem: 78493
Epoch: [63]  [ 20/312]  eta: 0:09:07  lr: 0.003771  min_lr: 0.003771  loss: 2.5474 (2.4956)  weight_decay: 0.0500 (0.0500)  time: 1.1446  data: 0.0020  max mem: 78493
Epoch: [63]  [ 30/312]  eta: 0:07:29  lr: 0.003771  min_lr: 0.003771  loss: 2.5513 (2.5286)  weight_decay: 0.0500 (0.0500)  time: 1.0120  data: 0.0005  max mem: 78493
Epoch: [63]  [ 40/312]  eta: 0:06:35  lr: 0.003770  min_lr: 0.003770  loss: 2.6973 (2.5476)  weight_decay: 0.0500 (0.0500)  time: 1.0090  data: 0.0004  max mem: 78493
Epoch: [63]  [ 50/312]  eta: 0:05:57  lr: 0.003770  min_lr: 0.003770  loss: 2.7334 (2.5732)  weight_decay: 0.0500 (0.0500)  time: 1.0072  data: 0.0004  max mem: 78493
Epoch: [63]  [ 60/312]  eta: 0:05:29  lr: 0.003770  min_lr: 0.003770  loss: 2.5213 (2.5249)  weight_decay: 0.0500 (0.0500)  time: 1.0048  data: 0.0005  max mem: 78493
Epoch: [63]  [ 70/312]  eta: 0:05:05  lr: 0.003769  min_lr: 0.003769  loss: 2.5213 (2.5659)  weight_decay: 0.0500 (0.0500)  time: 1.0050  data: 0.0004  max mem: 78493
Epoch: [63]  [ 80/312]  eta: 0:04:45  lr: 0.003769  min_lr: 0.003769  loss: 2.7514 (2.5643)  weight_decay: 0.0500 (0.0500)  time: 1.0062  data: 0.0004  max mem: 78493
Epoch: [63]  [ 90/312]  eta: 0:04:28  lr: 0.003769  min_lr: 0.003769  loss: 2.6680 (2.5676)  weight_decay: 0.0500 (0.0500)  time: 1.0085  data: 0.0015  max mem: 78493
Epoch: [63]  [100/312]  eta: 0:04:11  lr: 0.003768  min_lr: 0.003768  loss: 2.5872 (2.5568)  weight_decay: 0.0500 (0.0500)  time: 1.0109  data: 0.0015  max mem: 78493
Epoch: [63]  [110/312]  eta: 0:03:56  lr: 0.003768  min_lr: 0.003768  loss: 2.7642 (2.5737)  weight_decay: 0.0500 (0.0500)  time: 1.0098  data: 0.0013  max mem: 78493
Epoch: [63]  [120/312]  eta: 0:03:42  lr: 0.003768  min_lr: 0.003768  loss: 2.6552 (2.5578)  weight_decay: 0.0500 (0.0500)  time: 1.0082  data: 0.0013  max mem: 78493
Epoch: [63]  [130/312]  eta: 0:03:28  lr: 0.003767  min_lr: 0.003767  loss: 2.4459 (2.5534)  weight_decay: 0.0500 (0.0500)  time: 1.0068  data: 0.0004  max mem: 78493
Epoch: [63]  [140/312]  eta: 0:03:15  lr: 0.003767  min_lr: 0.003767  loss: 2.5558 (2.5405)  weight_decay: 0.0500 (0.0500)  time: 1.0049  data: 0.0004  max mem: 78493
Epoch: [63]  [150/312]  eta: 0:03:02  lr: 0.003767  min_lr: 0.003767  loss: 2.5600 (2.5400)  weight_decay: 0.0500 (0.0500)  time: 1.0066  data: 0.0013  max mem: 78493
Epoch: [63]  [160/312]  eta: 0:02:50  lr: 0.003766  min_lr: 0.003766  loss: 2.4836 (2.5303)  weight_decay: 0.0500 (0.0500)  time: 1.0071  data: 0.0013  max mem: 78493
Epoch: [63]  [170/312]  eta: 0:02:38  lr: 0.003766  min_lr: 0.003766  loss: 2.4740 (2.5238)  weight_decay: 0.0500 (0.0500)  time: 1.0056  data: 0.0005  max mem: 78493
Epoch: [63]  [180/312]  eta: 0:02:26  lr: 0.003766  min_lr: 0.003766  loss: 2.6961 (2.5281)  weight_decay: 0.0500 (0.0500)  time: 1.0066  data: 0.0004  max mem: 78493
Epoch: [63]  [190/312]  eta: 0:02:14  lr: 0.003765  min_lr: 0.003765  loss: 2.6637 (2.5265)  weight_decay: 0.0500 (0.0500)  time: 1.0075  data: 0.0004  max mem: 78493
Epoch: [63]  [200/312]  eta: 0:02:02  lr: 0.003765  min_lr: 0.003765  loss: 2.4816 (2.5225)  weight_decay: 0.0500 (0.0500)  time: 1.0077  data: 0.0004  max mem: 78493
Epoch: [63]  [210/312]  eta: 0:01:51  lr: 0.003765  min_lr: 0.003765  loss: 2.5545 (2.5308)  weight_decay: 0.0500 (0.0500)  time: 1.0079  data: 0.0010  max mem: 78493
Epoch: [63]  [220/312]  eta: 0:01:40  lr: 0.003764  min_lr: 0.003764  loss: 2.6509 (2.5304)  weight_decay: 0.0500 (0.0500)  time: 1.0072  data: 0.0010  max mem: 78493
Epoch: [63]  [230/312]  eta: 0:01:29  lr: 0.003764  min_lr: 0.003764  loss: 2.8016 (2.5411)  weight_decay: 0.0500 (0.0500)  time: 1.0091  data: 0.0004  max mem: 78493
Epoch: [63]  [240/312]  eta: 0:01:17  lr: 0.003764  min_lr: 0.003764  loss: 2.8138 (2.5468)  weight_decay: 0.0500 (0.0500)  time: 1.0110  data: 0.0004  max mem: 78493
Epoch: [63]  [250/312]  eta: 0:01:06  lr: 0.003763  min_lr: 0.003763  loss: 2.4922 (2.5450)  weight_decay: 0.0500 (0.0500)  time: 1.0094  data: 0.0004  max mem: 78493
Epoch: [63]  [260/312]  eta: 0:00:56  lr: 0.003763  min_lr: 0.003763  loss: 2.6923 (2.5488)  weight_decay: 0.0500 (0.0500)  time: 1.0077  data: 0.0004  max mem: 78493
Epoch: [63]  [270/312]  eta: 0:00:45  lr: 0.003763  min_lr: 0.003763  loss: 2.6995 (2.5517)  weight_decay: 0.0500 (0.0500)  time: 1.0076  data: 0.0005  max mem: 78493
Epoch: [63]  [280/312]  eta: 0:00:34  lr: 0.003762  min_lr: 0.003762  loss: 2.5737 (2.5567)  weight_decay: 0.0500 (0.0500)  time: 1.0068  data: 0.0010  max mem: 78493
Epoch: [63]  [290/312]  eta: 0:00:23  lr: 0.003762  min_lr: 0.003762  loss: 2.5611 (2.5520)  weight_decay: 0.0500 (0.0500)  time: 1.0036  data: 0.0009  max mem: 78493
Epoch: [63]  [300/312]  eta: 0:00:12  lr: 0.003762  min_lr: 0.003762  loss: 2.6296 (2.5565)  weight_decay: 0.0500 (0.0500)  time: 1.0020  data: 0.0001  max mem: 78493
Epoch: [63]  [310/312]  eta: 0:00:02  lr: 0.003761  min_lr: 0.003761  loss: 2.7075 (2.5559)  weight_decay: 0.0500 (0.0500)  time: 1.0019  data: 0.0001  max mem: 78493
Epoch: [63]  [311/312]  eta: 0:00:01  lr: 0.003761  min_lr: 0.003761  loss: 2.7051 (2.5552)  weight_decay: 0.0500 (0.0500)  time: 1.0019  data: 0.0001  max mem: 78493
Epoch: [63] Total time: 0:05:34 (1.0708 s / it)
Averaged stats: lr: 0.003761  min_lr: 0.003761  loss: 2.7051 (2.5644)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:16  loss: 0.9550 (0.9550)  acc1: 78.6458 (78.6458)  acc5: 92.8385 (92.8385)  time: 8.5385  data: 8.2563  max mem: 78493
Test:  [8/9]  eta: 0:00:01  loss: 1.3050 (1.2087)  acc1: 69.4010 (71.2320)  acc5: 89.7135 (90.0160)  time: 1.1470  data: 0.9174  max mem: 78493
Test: Total time: 0:00:10 (1.1608 s / it)
* Acc@1 71.106 Acc@5 90.266 loss 1.208
Accuracy of the model on the 50000 test images: 71.1%
Max accuracy: 72.33%
Epoch: [64]  [  0/312]  eta: 1:24:54  lr: 0.003761  min_lr: 0.003761  loss: 2.3459 (2.3459)  weight_decay: 0.0500 (0.0500)  time: 16.3269  data: 13.3442  max mem: 78493
Epoch: [64]  [ 10/312]  eta: 0:13:31  lr: 0.003761  min_lr: 0.003761  loss: 2.4830 (2.5110)  weight_decay: 0.0500 (0.0500)  time: 2.6882  data: 1.2680  max mem: 78493
Epoch: [64]  [ 20/312]  eta: 0:09:11  lr: 0.003761  min_lr: 0.003761  loss: 2.5437 (2.4818)  weight_decay: 0.0500 (0.0500)  time: 1.1671  data: 0.0304  max mem: 78493
Epoch: [64]  [ 30/312]  eta: 0:07:32  lr: 0.003760  min_lr: 0.003760  loss: 2.4349 (2.4876)  weight_decay: 0.0500 (0.0500)  time: 1.0083  data: 0.0004  max mem: 78493
Epoch: [64]  [ 40/312]  eta: 0:06:36  lr: 0.003760  min_lr: 0.003760  loss: 2.4349 (2.4939)  weight_decay: 0.0500 (0.0500)  time: 1.0067  data: 0.0004  max mem: 78493
Epoch: [64]  [ 50/312]  eta: 0:05:59  lr: 0.003760  min_lr: 0.003760  loss: 2.5642 (2.5200)  weight_decay: 0.0500 (0.0500)  time: 1.0075  data: 0.0004  max mem: 78493
Epoch: [64]  [ 60/312]  eta: 0:05:30  lr: 0.003759  min_lr: 0.003759  loss: 2.6759 (2.5226)  weight_decay: 0.0500 (0.0500)  time: 1.0087  data: 0.0004  max mem: 78493
Epoch: [64]  [ 70/312]  eta: 0:05:06  lr: 0.003759  min_lr: 0.003759  loss: 2.7774 (2.5603)  weight_decay: 0.0500 (0.0500)  time: 1.0071  data: 0.0004  max mem: 78493
Epoch: [64]  [ 80/312]  eta: 0:04:46  lr: 0.003759  min_lr: 0.003759  loss: 2.7774 (2.5744)  weight_decay: 0.0500 (0.0500)  time: 1.0053  data: 0.0004  max mem: 78493
Epoch: [64]  [ 90/312]  eta: 0:04:28  lr: 0.003758  min_lr: 0.003758  loss: 2.7080 (2.5690)  weight_decay: 0.0500 (0.0500)  time: 1.0058  data: 0.0004  max mem: 78493
Epoch: [64]  [100/312]  eta: 0:04:12  lr: 0.003758  min_lr: 0.003758  loss: 2.7080 (2.5785)  weight_decay: 0.0500 (0.0500)  time: 1.0051  data: 0.0011  max mem: 78493
Epoch: [64]  [110/312]  eta: 0:03:57  lr: 0.003757  min_lr: 0.003757  loss: 2.7467 (2.5960)  weight_decay: 0.0500 (0.0500)  time: 1.0071  data: 0.0011  max mem: 78493
Epoch: [64]  [120/312]  eta: 0:03:42  lr: 0.003757  min_lr: 0.003757  loss: 2.6005 (2.5885)  weight_decay: 0.0500 (0.0500)  time: 1.0105  data: 0.0017  max mem: 78493
Epoch: [64]  [130/312]  eta: 0:03:29  lr: 0.003757  min_lr: 0.003757  loss: 2.6810 (2.6081)  weight_decay: 0.0500 (0.0500)  time: 1.0090  data: 0.0017  max mem: 78493
Epoch: [64]  [140/312]  eta: 0:03:15  lr: 0.003756  min_lr: 0.003756  loss: 2.7411 (2.5994)  weight_decay: 0.0500 (0.0500)  time: 1.0061  data: 0.0004  max mem: 78493
Epoch: [64]  [150/312]  eta: 0:03:02  lr: 0.003756  min_lr: 0.003756  loss: 2.3343 (2.5798)  weight_decay: 0.0500 (0.0500)  time: 1.0051  data: 0.0004  max mem: 78493
Epoch: [64]  [160/312]  eta: 0:02:50  lr: 0.003756  min_lr: 0.003756  loss: 2.4418 (2.5777)  weight_decay: 0.0500 (0.0500)  time: 1.0060  data: 0.0004  max mem: 78493
Epoch: [64]  [170/312]  eta: 0:02:38  lr: 0.003755  min_lr: 0.003755  loss: 2.5881 (2.5732)  weight_decay: 0.0500 (0.0500)  time: 1.0083  data: 0.0004  max mem: 78493
Epoch: [64]  [180/312]  eta: 0:02:26  lr: 0.003755  min_lr: 0.003755  loss: 2.4257 (2.5710)  weight_decay: 0.0500 (0.0500)  time: 1.0091  data: 0.0004  max mem: 78493
Epoch: [64]  [190/312]  eta: 0:02:14  lr: 0.003755  min_lr: 0.003755  loss: 2.5480 (2.5720)  weight_decay: 0.0500 (0.0500)  time: 1.0075  data: 0.0004  max mem: 78493
Epoch: [64]  [200/312]  eta: 0:02:03  lr: 0.003754  min_lr: 0.003754  loss: 2.5527 (2.5636)  weight_decay: 0.0500 (0.0500)  time: 1.0055  data: 0.0004  max mem: 78493
Epoch: [64]  [210/312]  eta: 0:01:51  lr: 0.003754  min_lr: 0.003754  loss: 2.4353 (2.5596)  weight_decay: 0.0500 (0.0500)  time: 1.0061  data: 0.0005  max mem: 78493
Epoch: [64]  [220/312]  eta: 0:01:40  lr: 0.003754  min_lr: 0.003754  loss: 2.4011 (2.5523)  weight_decay: 0.0500 (0.0500)  time: 1.0063  data: 0.0005  max mem: 78493
Epoch: [64]  [230/312]  eta: 0:01:29  lr: 0.003753  min_lr: 0.003753  loss: 2.4562 (2.5532)  weight_decay: 0.0500 (0.0500)  time: 1.0051  data: 0.0005  max mem: 78493
Epoch: [64]  [240/312]  eta: 0:01:18  lr: 0.003753  min_lr: 0.003753  loss: 2.6015 (2.5494)  weight_decay: 0.0500 (0.0500)  time: 1.0057  data: 0.0004  max mem: 78493
Epoch: [64]  [250/312]  eta: 0:01:06  lr: 0.003753  min_lr: 0.003753  loss: 2.6015 (2.5502)  weight_decay: 0.0500 (0.0500)  time: 1.0061  data: 0.0004  max mem: 78493
Epoch: [64]  [260/312]  eta: 0:00:56  lr: 0.003752  min_lr: 0.003752  loss: 2.5773 (2.5498)  weight_decay: 0.0500 (0.0500)  time: 1.0050  data: 0.0005  max mem: 78493
Epoch: [64]  [270/312]  eta: 0:00:45  lr: 0.003752  min_lr: 0.003752  loss: 2.5773 (2.5483)  weight_decay: 0.0500 (0.0500)  time: 1.0055  data: 0.0005  max mem: 78493
Epoch: [64]  [280/312]  eta: 0:00:34  lr: 0.003752  min_lr: 0.003752  loss: 2.7070 (2.5525)  weight_decay: 0.0500 (0.0500)  time: 1.0063  data: 0.0010  max mem: 78493
Epoch: [64]  [290/312]  eta: 0:00:23  lr: 0.003751  min_lr: 0.003751  loss: 2.6794 (2.5470)  weight_decay: 0.0500 (0.0500)  time: 1.0036  data: 0.0009  max mem: 78493
Epoch: [64]  [300/312]  eta: 0:00:12  lr: 0.003751  min_lr: 0.003751  loss: 2.4108 (2.5460)  weight_decay: 0.0500 (0.0500)  time: 1.0016  data: 0.0001  max mem: 78493
Epoch: [64]  [310/312]  eta: 0:00:02  lr: 0.003751  min_lr: 0.003751  loss: 2.6041 (2.5472)  weight_decay: 0.0500 (0.0500)  time: 1.0017  data: 0.0001  max mem: 78493
Epoch: [64]  [311/312]  eta: 0:00:01  lr: 0.003751  min_lr: 0.003751  loss: 2.6176 (2.5484)  weight_decay: 0.0500 (0.0500)  time: 1.0020  data: 0.0001  max mem: 78493
Epoch: [64] Total time: 0:05:34 (1.0716 s / it)
Averaged stats: lr: 0.003751  min_lr: 0.003751  loss: 2.6176 (2.5545)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:11  loss: 1.1619 (1.1619)  acc1: 73.3073 (73.3073)  acc5: 90.7552 (90.7552)  time: 7.9299  data: 7.6659  max mem: 78493
Test:  [8/9]  eta: 0:00:01  loss: 1.3378 (1.2418)  acc1: 70.5729 (70.4480)  acc5: 87.8906 (89.2160)  time: 1.0934  data: 0.8518  max mem: 78493
Test: Total time: 0:00:10 (1.1318 s / it)
* Acc@1 70.884 Acc@5 89.764 loss 1.222
Accuracy of the model on the 50000 test images: 70.9%
Max accuracy: 72.33%
Epoch: [65]  [  0/312]  eta: 1:27:56  lr: 0.003751  min_lr: 0.003751  loss: 2.8976 (2.8976)  weight_decay: 0.0500 (0.0500)  time: 16.9118  data: 13.8461  max mem: 78493
Epoch: [65]  [ 10/312]  eta: 0:13:45  lr: 0.003750  min_lr: 0.003750  loss: 2.8379 (2.6685)  weight_decay: 0.0500 (0.0500)  time: 2.7320  data: 1.2624  max mem: 78493
Epoch: [65]  [ 20/312]  eta: 0:09:18  lr: 0.003750  min_lr: 0.003750  loss: 2.7097 (2.6329)  weight_decay: 0.0500 (0.0500)  time: 1.1616  data: 0.0022  max mem: 78493
Epoch: [65]  [ 30/312]  eta: 0:07:36  lr: 0.003749  min_lr: 0.003749  loss: 2.6261 (2.5778)  weight_decay: 0.0500 (0.0500)  time: 1.0079  data: 0.0004  max mem: 78493
Epoch: [65]  [ 40/312]  eta: 0:06:39  lr: 0.003749  min_lr: 0.003749  loss: 2.6043 (2.5683)  weight_decay: 0.0500 (0.0500)  time: 1.0063  data: 0.0004  max mem: 78493
Epoch: [65]  [ 50/312]  eta: 0:06:01  lr: 0.003749  min_lr: 0.003749  loss: 2.6043 (2.5645)  weight_decay: 0.0500 (0.0500)  time: 1.0060  data: 0.0004  max mem: 78493
Epoch: [65]  [ 60/312]  eta: 0:05:32  lr: 0.003748  min_lr: 0.003748  loss: 2.6395 (2.6059)  weight_decay: 0.0500 (0.0500)  time: 1.0069  data: 0.0004  max mem: 78493
Epoch: [65]  [ 70/312]  eta: 0:05:08  lr: 0.003748  min_lr: 0.003748  loss: 2.4049 (2.5558)  weight_decay: 0.0500 (0.0500)  time: 1.0076  data: 0.0004  max mem: 78493
Epoch: [65]  [ 80/312]  eta: 0:04:47  lr: 0.003748  min_lr: 0.003748  loss: 2.1962 (2.5292)  weight_decay: 0.0500 (0.0500)  time: 1.0069  data: 0.0004  max mem: 78493
Epoch: [65]  [ 90/312]  eta: 0:04:29  lr: 0.003747  min_lr: 0.003747  loss: 2.4743 (2.5506)  weight_decay: 0.0500 (0.0500)  time: 1.0056  data: 0.0004  max mem: 78493
Epoch: [65]  [100/312]  eta: 0:04:13  lr: 0.003747  min_lr: 0.003747  loss: 2.6912 (2.5500)  weight_decay: 0.0500 (0.0500)  time: 1.0059  data: 0.0004  max mem: 78493
Epoch: [65]  [110/312]  eta: 0:03:57  lr: 0.003747  min_lr: 0.003747  loss: 2.6645 (2.5601)  weight_decay: 0.0500 (0.0500)  time: 1.0080  data: 0.0004  max mem: 78493
Epoch: [65]  [120/312]  eta: 0:03:43  lr: 0.003746  min_lr: 0.003746  loss: 2.5561 (2.5590)  weight_decay: 0.0500 (0.0500)  time: 1.0078  data: 0.0012  max mem: 78493
Epoch: [65]  [130/312]  eta: 0:03:29  lr: 0.003746  min_lr: 0.003746  loss: 2.4443 (2.5473)  weight_decay: 0.0500 (0.0500)  time: 1.0061  data: 0.0012  max mem: 78493
Epoch: [65]  [140/312]  eta: 0:03:16  lr: 0.003746  min_lr: 0.003746  loss: 2.6290 (2.5547)  weight_decay: 0.0500 (0.0500)  time: 1.0071  data: 0.0004  max mem: 78493
Epoch: [65]  [150/312]  eta: 0:03:03  lr: 0.003745  min_lr: 0.003745  loss: 2.7472 (2.5664)  weight_decay: 0.0500 (0.0500)  time: 1.0072  data: 0.0005  max mem: 78493
Epoch: [65]  [160/312]  eta: 0:02:50  lr: 0.003745  min_lr: 0.003745  loss: 2.6342 (2.5544)  weight_decay: 0.0500 (0.0500)  time: 1.0056  data: 0.0005  max mem: 78493
Epoch: [65]  [170/312]  eta: 0:02:38  lr: 0.003745  min_lr: 0.003745  loss: 2.4505 (2.5499)  weight_decay: 0.0500 (0.0500)  time: 1.0074  data: 0.0004  max mem: 78493
Epoch: [65]  [180/312]  eta: 0:02:26  lr: 0.003744  min_lr: 0.003744  loss: 2.6934 (2.5566)  weight_decay: 0.0500 (0.0500)  time: 1.0070  data: 0.0004  max mem: 78493
Epoch: [65]  [190/312]  eta: 0:02:14  lr: 0.003744  min_lr: 0.003744  loss: 2.6561 (2.5570)  weight_decay: 0.0500 (0.0500)  time: 1.0060  data: 0.0004  max mem: 78493
Epoch: [65]  [200/312]  eta: 0:02:03  lr: 0.003744  min_lr: 0.003744  loss: 2.6623 (2.5620)  weight_decay: 0.0500 (0.0500)  time: 1.0066  data: 0.0004  max mem: 78493
Epoch: [65]  [210/312]  eta: 0:01:51  lr: 0.003743  min_lr: 0.003743  loss: 2.6733 (2.5643)  weight_decay: 0.0500 (0.0500)  time: 1.0060  data: 0.0004  max mem: 78493
Epoch: [65]  [220/312]  eta: 0:01:40  lr: 0.003743  min_lr: 0.003743  loss: 2.4063 (2.5581)  weight_decay: 0.0500 (0.0500)  time: 1.0061  data: 0.0004  max mem: 78493
Epoch: [65]  [230/312]  eta: 0:01:29  lr: 0.003742  min_lr: 0.003742  loss: 2.5453 (2.5619)  weight_decay: 0.0500 (0.0500)  time: 1.0055  data: 0.0004  max mem: 78493
Epoch: [65]  [240/312]  eta: 0:01:18  lr: 0.003742  min_lr: 0.003742  loss: 2.7427 (2.5653)  weight_decay: 0.0500 (0.0500)  time: 1.0047  data: 0.0004  max mem: 78493
Epoch: [65]  [250/312]  eta: 0:01:07  lr: 0.003742  min_lr: 0.003742  loss: 2.7596 (2.5644)  weight_decay: 0.0500 (0.0500)  time: 1.0038  data: 0.0004  max mem: 78493
Epoch: [65]  [260/312]  eta: 0:00:56  lr: 0.003741  min_lr: 0.003741  loss: 2.8022 (2.5725)  weight_decay: 0.0500 (0.0500)  time: 1.0043  data: 0.0004  max mem: 78493
Epoch: [65]  [270/312]  eta: 0:00:45  lr: 0.003741  min_lr: 0.003741  loss: 2.7300 (2.5727)  weight_decay: 0.0500 (0.0500)  time: 1.0053  data: 0.0004  max mem: 78493
Epoch: [65]  [280/312]  eta: 0:00:34  lr: 0.003741  min_lr: 0.003741  loss: 2.4247 (2.5679)  weight_decay: 0.0500 (0.0500)  time: 1.0059  data: 0.0010  max mem: 78493
Epoch: [65]  [290/312]  eta: 0:00:23  lr: 0.003740  min_lr: 0.003740  loss: 2.7067 (2.5747)  weight_decay: 0.0500 (0.0500)  time: 1.0042  data: 0.0009  max mem: 78493
Epoch: [65]  [300/312]  eta: 0:00:12  lr: 0.003740  min_lr: 0.003740  loss: 2.7067 (2.5745)  weight_decay: 0.0500 (0.0500)  time: 1.0017  data: 0.0001  max mem: 78493
Epoch: [65]  [310/312]  eta: 0:00:02  lr: 0.003740  min_lr: 0.003740  loss: 2.6733 (2.5786)  weight_decay: 0.0500 (0.0500)  time: 1.0015  data: 0.0001  max mem: 78493
Epoch: [65]  [311/312]  eta: 0:00:01  lr: 0.003740  min_lr: 0.003740  loss: 2.6733 (2.5764)  weight_decay: 0.0500 (0.0500)  time: 1.0015  data: 0.0001  max mem: 78493
Epoch: [65] Total time: 0:05:34 (1.0726 s / it)
Averaged stats: lr: 0.003740  min_lr: 0.003740  loss: 2.6733 (2.5609)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:15  loss: 0.9479 (0.9479)  acc1: 76.4323 (76.4323)  acc5: 92.9688 (92.9688)  time: 8.3781  data: 8.1101  max mem: 78493
Test:  [8/9]  eta: 0:00:01  loss: 1.2902 (1.1586)  acc1: 70.0521 (71.3920)  acc5: 89.3229 (90.2560)  time: 1.1303  data: 0.9012  max mem: 78493
Test: Total time: 0:00:10 (1.1564 s / it)
* Acc@1 71.548 Acc@5 90.506 loss 1.154
Accuracy of the model on the 50000 test images: 71.5%
Max accuracy: 72.33%
Epoch: [66]  [  0/312]  eta: 1:22:49  lr: 0.003740  min_lr: 0.003740  loss: 2.7248 (2.7248)  weight_decay: 0.0500 (0.0500)  time: 15.9279  data: 12.8725  max mem: 78493
Epoch: [66]  [ 10/312]  eta: 0:12:59  lr: 0.003739  min_lr: 0.003739  loss: 2.7317 (2.6727)  weight_decay: 0.0500 (0.0500)  time: 2.5798  data: 1.2673  max mem: 78493
Epoch: [66]  [ 20/312]  eta: 0:09:01  lr: 0.003739  min_lr: 0.003739  loss: 2.7239 (2.6813)  weight_decay: 0.0500 (0.0500)  time: 1.1504  data: 0.0557  max mem: 78493
Epoch: [66]  [ 30/312]  eta: 0:07:26  lr: 0.003738  min_lr: 0.003738  loss: 2.7239 (2.6707)  weight_decay: 0.0500 (0.0500)  time: 1.0333  data: 0.0034  max mem: 78493
Epoch: [66]  [ 40/312]  eta: 0:06:32  lr: 0.003738  min_lr: 0.003738  loss: 2.6147 (2.6261)  weight_decay: 0.0500 (0.0500)  time: 1.0087  data: 0.0014  max mem: 78493
Epoch: [66]  [ 50/312]  eta: 0:05:55  lr: 0.003738  min_lr: 0.003738  loss: 2.5707 (2.5929)  weight_decay: 0.0500 (0.0500)  time: 1.0064  data: 0.0005  max mem: 78493
Epoch: [66]  [ 60/312]  eta: 0:05:27  lr: 0.003737  min_lr: 0.003737  loss: 2.6427 (2.6102)  weight_decay: 0.0500 (0.0500)  time: 1.0061  data: 0.0004  max mem: 78493
Epoch: [66]  [ 70/312]  eta: 0:05:04  lr: 0.003737  min_lr: 0.003737  loss: 2.7626 (2.6092)  weight_decay: 0.0500 (0.0500)  time: 1.0063  data: 0.0004  max mem: 78493
Epoch: [66]  [ 80/312]  eta: 0:04:44  lr: 0.003737  min_lr: 0.003737  loss: 2.4221 (2.5898)  weight_decay: 0.0500 (0.0500)  time: 1.0067  data: 0.0004  max mem: 78493
Epoch: [66]  [ 90/312]  eta: 0:04:26  lr: 0.003736  min_lr: 0.003736  loss: 2.5982 (2.6017)  weight_decay: 0.0500 (0.0500)  time: 1.0062  data: 0.0004  max mem: 78493
Epoch: [66]  [100/312]  eta: 0:04:10  lr: 0.003736  min_lr: 0.003736  loss: 2.6530 (2.5968)  weight_decay: 0.0500 (0.0500)  time: 1.0060  data: 0.0004  max mem: 78493
Epoch: [66]  [110/312]  eta: 0:03:55  lr: 0.003736  min_lr: 0.003736  loss: 2.6530 (2.5973)  weight_decay: 0.0500 (0.0500)  time: 1.0066  data: 0.0004  max mem: 78493
Epoch: [66]  [120/312]  eta: 0:03:41  lr: 0.003735  min_lr: 0.003735  loss: 2.6464 (2.5909)  weight_decay: 0.0500 (0.0500)  time: 1.0068  data: 0.0005  max mem: 78493
Epoch: [66]  [130/312]  eta: 0:03:28  lr: 0.003735  min_lr: 0.003735  loss: 2.5751 (2.5830)  weight_decay: 0.0500 (0.0500)  time: 1.0083  data: 0.0015  max mem: 78493
Epoch: [66]  [140/312]  eta: 0:03:14  lr: 0.003735  min_lr: 0.003735  loss: 2.5623 (2.5807)  weight_decay: 0.0500 (0.0500)  time: 1.0073  data: 0.0015  max mem: 78493
Epoch: [66]  [150/312]  eta: 0:03:02  lr: 0.003734  min_lr: 0.003734  loss: 2.5440 (2.5738)  weight_decay: 0.0500 (0.0500)  time: 1.0060  data: 0.0005  max mem: 78493
Epoch: [66]  [160/312]  eta: 0:02:49  lr: 0.003734  min_lr: 0.003734  loss: 2.5440 (2.5768)  weight_decay: 0.0500 (0.0500)  time: 1.0097  data: 0.0004  max mem: 78493
Epoch: [66]  [170/312]  eta: 0:02:37  lr: 0.003733  min_lr: 0.003733  loss: 2.6725 (2.5775)  weight_decay: 0.0500 (0.0500)  time: 1.0099  data: 0.0004  max mem: 78493
Epoch: [66]  [180/312]  eta: 0:02:25  lr: 0.003733  min_lr: 0.003733  loss: 2.6725 (2.5778)  weight_decay: 0.0500 (0.0500)  time: 1.0100  data: 0.0004  max mem: 78493
Epoch: [66]  [190/312]  eta: 0:02:14  lr: 0.003733  min_lr: 0.003733  loss: 2.7367 (2.5789)  weight_decay: 0.0500 (0.0500)  time: 1.0102  data: 0.0004  max mem: 78493
Epoch: [66]  [200/312]  eta: 0:02:02  lr: 0.003732  min_lr: 0.003732  loss: 2.7824 (2.5785)  weight_decay: 0.0500 (0.0500)  time: 1.0074  data: 0.0004  max mem: 78493
Epoch: [66]  [210/312]  eta: 0:01:51  lr: 0.003732  min_lr: 0.003732  loss: 2.3202 (2.5634)  weight_decay: 0.0500 (0.0500)  time: 1.0061  data: 0.0004  max mem: 78493
Epoch: [66]  [220/312]  eta: 0:01:40  lr: 0.003732  min_lr: 0.003732  loss: 2.6835 (2.5705)  weight_decay: 0.0500 (0.0500)  time: 1.0079  data: 0.0005  max mem: 78493
Epoch: [66]  [230/312]  eta: 0:01:28  lr: 0.003731  min_lr: 0.003731  loss: 2.7498 (2.5737)  weight_decay: 0.0500 (0.0500)  time: 1.0097  data: 0.0013  max mem: 78493
Epoch: [66]  [240/312]  eta: 0:01:17  lr: 0.003731  min_lr: 0.003731  loss: 2.7283 (2.5733)  weight_decay: 0.0500 (0.0500)  time: 1.0105  data: 0.0012  max mem: 78493
Epoch: [66]  [250/312]  eta: 0:01:06  lr: 0.003731  min_lr: 0.003731  loss: 2.7669 (2.5813)  weight_decay: 0.0500 (0.0500)  time: 1.0115  data: 0.0004  max mem: 78493
Epoch: [66]  [260/312]  eta: 0:00:55  lr: 0.003730  min_lr: 0.003730  loss: 2.5927 (2.5744)  weight_decay: 0.0500 (0.0500)  time: 1.0089  data: 0.0005  max mem: 78493
Epoch: [66]  [270/312]  eta: 0:00:45  lr: 0.003730  min_lr: 0.003730  loss: 2.5211 (2.5698)  weight_decay: 0.0500 (0.0500)  time: 1.0074  data: 0.0004  max mem: 78493
Epoch: [66]  [280/312]  eta: 0:00:34  lr: 0.003730  min_lr: 0.003730  loss: 2.5211 (2.5658)  weight_decay: 0.0500 (0.0500)  time: 1.0101  data: 0.0010  max mem: 78493
Epoch: [66]  [290/312]  eta: 0:00:23  lr: 0.003729  min_lr: 0.003729  loss: 2.5095 (2.5652)  weight_decay: 0.0500 (0.0500)  time: 1.0074  data: 0.0009  max mem: 78493
Epoch: [66]  [300/312]  eta: 0:00:12  lr: 0.003729  min_lr: 0.003729  loss: 2.6385 (2.5677)  weight_decay: 0.0500 (0.0500)  time: 1.0025  data: 0.0001  max mem: 78493
Epoch: [66]  [310/312]  eta: 0:00:02  lr: 0.003728  min_lr: 0.003728  loss: 2.6385 (2.5665)  weight_decay: 0.0500 (0.0500)  time: 1.0023  data: 0.0001  max mem: 78493
Epoch: [66]  [311/312]  eta: 0:00:01  lr: 0.003728  min_lr: 0.003728  loss: 2.6465 (2.5674)  weight_decay: 0.0500 (0.0500)  time: 1.0023  data: 0.0001  max mem: 78493
Epoch: [66] Total time: 0:05:33 (1.0702 s / it)
Averaged stats: lr: 0.003728  min_lr: 0.003728  loss: 2.6465 (2.5525)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:16  loss: 0.9618 (0.9618)  acc1: 76.0417 (76.0417)  acc5: 93.0990 (93.0990)  time: 8.5028  data: 8.2364  max mem: 78493
Test:  [8/9]  eta: 0:00:01  loss: 1.2951 (1.2238)  acc1: 71.3542 (70.5600)  acc5: 89.0625 (89.8240)  time: 1.1447  data: 0.9153  max mem: 78493
Test: Total time: 0:00:10 (1.1674 s / it)
* Acc@1 71.258 Acc@5 90.246 loss 1.197
Accuracy of the model on the 50000 test images: 71.3%
Max accuracy: 72.33%
Epoch: [67]  [  0/312]  eta: 1:27:07  lr: 0.003728  min_lr: 0.003728  loss: 2.3212 (2.3212)  weight_decay: 0.0500 (0.0500)  time: 16.7557  data: 12.7386  max mem: 78493
Epoch: [67]  [ 10/312]  eta: 0:13:12  lr: 0.003728  min_lr: 0.003728  loss: 2.4661 (2.4810)  weight_decay: 0.0500 (0.0500)  time: 2.6245  data: 1.2186  max mem: 78493
Epoch: [67]  [ 20/312]  eta: 0:09:03  lr: 0.003728  min_lr: 0.003728  loss: 2.5800 (2.5274)  weight_decay: 0.0500 (0.0500)  time: 1.1154  data: 0.0337  max mem: 78493
Epoch: [67]  [ 30/312]  eta: 0:07:27  lr: 0.003727  min_lr: 0.003727  loss: 2.6495 (2.4887)  weight_decay: 0.0500 (0.0500)  time: 1.0159  data: 0.0007  max mem: 78493
Epoch: [67]  [ 40/312]  eta: 0:06:33  lr: 0.003727  min_lr: 0.003727  loss: 2.3309 (2.4494)  weight_decay: 0.0500 (0.0500)  time: 1.0107  data: 0.0006  max mem: 78493
Epoch: [67]  [ 50/312]  eta: 0:05:56  lr: 0.003727  min_lr: 0.003727  loss: 2.5177 (2.4980)  weight_decay: 0.0500 (0.0500)  time: 1.0084  data: 0.0005  max mem: 78493
Epoch: [67]  [ 60/312]  eta: 0:05:28  lr: 0.003726  min_lr: 0.003726  loss: 2.7319 (2.4873)  weight_decay: 0.0500 (0.0500)  time: 1.0069  data: 0.0004  max mem: 78493
Epoch: [67]  [ 70/312]  eta: 0:05:05  lr: 0.003726  min_lr: 0.003726  loss: 2.5771 (2.4816)  weight_decay: 0.0500 (0.0500)  time: 1.0065  data: 0.0004  max mem: 78493
Epoch: [67]  [ 80/312]  eta: 0:04:45  lr: 0.003725  min_lr: 0.003725  loss: 2.5617 (2.4847)  weight_decay: 0.0500 (0.0500)  time: 1.0059  data: 0.0004  max mem: 78493
Epoch: [67]  [ 90/312]  eta: 0:04:27  lr: 0.003725  min_lr: 0.003725  loss: 2.4860 (2.4896)  weight_decay: 0.0500 (0.0500)  time: 1.0059  data: 0.0004  max mem: 78493
Epoch: [67]  [100/312]  eta: 0:04:11  lr: 0.003725  min_lr: 0.003725  loss: 2.5955 (2.5030)  weight_decay: 0.0500 (0.0500)  time: 1.0069  data: 0.0004  max mem: 78493
Epoch: [67]  [110/312]  eta: 0:03:56  lr: 0.003724  min_lr: 0.003724  loss: 2.5937 (2.4967)  weight_decay: 0.0500 (0.0500)  time: 1.0070  data: 0.0004  max mem: 78493
Epoch: [67]  [120/312]  eta: 0:03:41  lr: 0.003724  min_lr: 0.003724  loss: 2.4513 (2.4805)  weight_decay: 0.0500 (0.0500)  time: 1.0091  data: 0.0004  max mem: 78493
Epoch: [67]  [130/312]  eta: 0:03:28  lr: 0.003724  min_lr: 0.003724  loss: 2.4513 (2.4814)  weight_decay: 0.0500 (0.0500)  time: 1.0097  data: 0.0004  max mem: 78493
Epoch: [67]  [140/312]  eta: 0:03:15  lr: 0.003723  min_lr: 0.003723  loss: 2.5565 (2.4925)  weight_decay: 0.0500 (0.0500)  time: 1.0086  data: 0.0004  max mem: 78493
Epoch: [67]  [150/312]  eta: 0:03:02  lr: 0.003723  min_lr: 0.003723  loss: 2.5425 (2.4945)  weight_decay: 0.0500 (0.0500)  time: 1.0094  data: 0.0004  max mem: 78493
Epoch: [67]  [160/312]  eta: 0:02:50  lr: 0.003723  min_lr: 0.003723  loss: 2.5875 (2.5016)  weight_decay: 0.0500 (0.0500)  time: 1.0108  data: 0.0004  max mem: 78493
Epoch: [67]  [170/312]  eta: 0:02:38  lr: 0.003722  min_lr: 0.003722  loss: 2.5875 (2.4966)  weight_decay: 0.0500 (0.0500)  time: 1.0116  data: 0.0005  max mem: 78493
Epoch: [67]  [180/312]  eta: 0:02:26  lr: 0.003722  min_lr: 0.003722  loss: 2.3883 (2.4939)  weight_decay: 0.0500 (0.0500)  time: 1.0101  data: 0.0004  max mem: 78493
Epoch: [67]  [190/312]  eta: 0:02:14  lr: 0.003721  min_lr: 0.003721  loss: 2.6323 (2.4974)  weight_decay: 0.0500 (0.0500)  time: 1.0091  data: 0.0004  max mem: 78493
Epoch: [67]  [200/312]  eta: 0:02:02  lr: 0.003721  min_lr: 0.003721  loss: 2.6748 (2.4998)  weight_decay: 0.0500 (0.0500)  time: 1.0075  data: 0.0004  max mem: 78493
Epoch: [67]  [210/312]  eta: 0:01:51  lr: 0.003721  min_lr: 0.003721  loss: 2.5004 (2.4963)  weight_decay: 0.0500 (0.0500)  time: 1.0073  data: 0.0004  max mem: 78493
Epoch: [67]  [220/312]  eta: 0:01:40  lr: 0.003720  min_lr: 0.003720  loss: 2.3627 (2.4894)  weight_decay: 0.0500 (0.0500)  time: 1.0067  data: 0.0004  max mem: 78493
Epoch: [67]  [230/312]  eta: 0:01:29  lr: 0.003720  min_lr: 0.003720  loss: 2.4087 (2.4903)  weight_decay: 0.0500 (0.0500)  time: 1.0053  data: 0.0005  max mem: 78493
Epoch: [67]  [240/312]  eta: 0:01:17  lr: 0.003720  min_lr: 0.003720  loss: 2.5775 (2.4930)  weight_decay: 0.0500 (0.0500)  time: 1.0054  data: 0.0004  max mem: 78493
Epoch: [67]  [250/312]  eta: 0:01:06  lr: 0.003719  min_lr: 0.003719  loss: 2.7649 (2.5035)  weight_decay: 0.0500 (0.0500)  time: 1.0065  data: 0.0005  max mem: 78493
Epoch: [67]  [260/312]  eta: 0:00:55  lr: 0.003719  min_lr: 0.003719  loss: 2.7285 (2.5044)  weight_decay: 0.0500 (0.0500)  time: 1.0075  data: 0.0005  max mem: 78493
Epoch: [67]  [270/312]  eta: 0:00:45  lr: 0.003719  min_lr: 0.003719  loss: 2.5484 (2.5048)  weight_decay: 0.0500 (0.0500)  time: 1.0061  data: 0.0004  max mem: 78493
Epoch: [67]  [280/312]  eta: 0:00:34  lr: 0.003718  min_lr: 0.003718  loss: 2.4799 (2.5040)  weight_decay: 0.0500 (0.0500)  time: 1.0053  data: 0.0011  max mem: 78493
Epoch: [67]  [290/312]  eta: 0:00:23  lr: 0.003718  min_lr: 0.003718  loss: 2.7429 (2.5134)  weight_decay: 0.0500 (0.0500)  time: 1.0037  data: 0.0009  max mem: 78493
Epoch: [67]  [300/312]  eta: 0:00:12  lr: 0.003717  min_lr: 0.003717  loss: 2.8160 (2.5168)  weight_decay: 0.0500 (0.0500)  time: 1.0019  data: 0.0001  max mem: 78493
Epoch: [67]  [310/312]  eta: 0:00:02  lr: 0.003717  min_lr: 0.003717  loss: 2.7881 (2.5203)  weight_decay: 0.0500 (0.0500)  time: 1.0017  data: 0.0001  max mem: 78493
Epoch: [67]  [311/312]  eta: 0:00:01  lr: 0.003717  min_lr: 0.003717  loss: 2.7881 (2.5221)  weight_decay: 0.0500 (0.0500)  time: 1.0017  data: 0.0001  max mem: 78493
Epoch: [67] Total time: 0:05:34 (1.0706 s / it)
Averaged stats: lr: 0.003717  min_lr: 0.003717  loss: 2.7881 (2.5469)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:09  loss: 0.8910 (0.8910)  acc1: 78.1250 (78.1250)  acc5: 94.2708 (94.2708)  time: 7.6937  data: 7.4138  max mem: 78493
Test:  [8/9]  eta: 0:00:01  loss: 1.2609 (1.1664)  acc1: 69.4010 (71.4880)  acc5: 89.0625 (89.9040)  time: 1.0735  data: 0.8441  max mem: 78493
Test: Total time: 0:00:09 (1.0937 s / it)
* Acc@1 71.804 Acc@5 90.354 loss 1.152
Accuracy of the model on the 50000 test images: 71.8%
Max accuracy: 72.33%
Epoch: [68]  [  0/312]  eta: 1:24:50  lr: 0.003717  min_lr: 0.003717  loss: 2.6530 (2.6530)  weight_decay: 0.0500 (0.0500)  time: 16.3152  data: 15.3147  max mem: 78493
Epoch: [68]  [ 10/312]  eta: 0:14:04  lr: 0.003717  min_lr: 0.003717  loss: 2.5958 (2.4902)  weight_decay: 0.0500 (0.0500)  time: 2.7964  data: 1.3951  max mem: 78493
Epoch: [68]  [ 20/312]  eta: 0:09:27  lr: 0.003716  min_lr: 0.003716  loss: 2.5942 (2.5248)  weight_decay: 0.0500 (0.0500)  time: 1.2265  data: 0.0018  max mem: 78493
Epoch: [68]  [ 30/312]  eta: 0:07:43  lr: 0.003716  min_lr: 0.003716  loss: 2.6270 (2.5451)  weight_decay: 0.0500 (0.0500)  time: 1.0085  data: 0.0004  max mem: 78493
Epoch: [68]  [ 40/312]  eta: 0:06:44  lr: 0.003715  min_lr: 0.003715  loss: 2.6270 (2.5350)  weight_decay: 0.0500 (0.0500)  time: 1.0084  data: 0.0004  max mem: 78493
Epoch: [68]  [ 50/312]  eta: 0:06:05  lr: 0.003715  min_lr: 0.003715  loss: 2.6305 (2.5329)  weight_decay: 0.0500 (0.0500)  time: 1.0096  data: 0.0004  max mem: 78493
Epoch: [68]  [ 60/312]  eta: 0:05:35  lr: 0.003715  min_lr: 0.003715  loss: 2.6305 (2.5386)  weight_decay: 0.0500 (0.0500)  time: 1.0107  data: 0.0004  max mem: 78493
Epoch: [68]  [ 70/312]  eta: 0:05:11  lr: 0.003714  min_lr: 0.003714  loss: 2.6616 (2.5538)  weight_decay: 0.0500 (0.0500)  time: 1.0073  data: 0.0005  max mem: 78493
Epoch: [68]  [ 80/312]  eta: 0:04:50  lr: 0.003714  min_lr: 0.003714  loss: 2.4566 (2.5296)  weight_decay: 0.0500 (0.0500)  time: 1.0055  data: 0.0005  max mem: 78493
Epoch: [68]  [ 90/312]  eta: 0:04:31  lr: 0.003714  min_lr: 0.003714  loss: 2.4032 (2.5078)  weight_decay: 0.0500 (0.0500)  time: 1.0062  data: 0.0005  max mem: 78493
Epoch: [68]  [100/312]  eta: 0:04:14  lr: 0.003713  min_lr: 0.003713  loss: 2.0350 (2.4682)  weight_decay: 0.0500 (0.0500)  time: 1.0053  data: 0.0004  max mem: 78493
Epoch: [68]  [110/312]  eta: 0:03:59  lr: 0.003713  min_lr: 0.003713  loss: 2.2885 (2.4831)  weight_decay: 0.0500 (0.0500)  time: 1.0045  data: 0.0005  max mem: 78493
Epoch: [68]  [120/312]  eta: 0:03:44  lr: 0.003713  min_lr: 0.003713  loss: 2.6597 (2.4930)  weight_decay: 0.0500 (0.0500)  time: 1.0039  data: 0.0005  max mem: 78493
Epoch: [68]  [130/312]  eta: 0:03:30  lr: 0.003712  min_lr: 0.003712  loss: 2.6978 (2.5007)  weight_decay: 0.0500 (0.0500)  time: 1.0051  data: 0.0012  max mem: 78493
Epoch: [68]  [140/312]  eta: 0:03:17  lr: 0.003712  min_lr: 0.003712  loss: 2.6978 (2.5105)  weight_decay: 0.0500 (0.0500)  time: 1.0050  data: 0.0012  max mem: 78493
Epoch: [68]  [150/312]  eta: 0:03:04  lr: 0.003711  min_lr: 0.003711  loss: 2.6993 (2.5221)  weight_decay: 0.0500 (0.0500)  time: 1.0050  data: 0.0005  max mem: 78493
Epoch: [68]  [160/312]  eta: 0:02:51  lr: 0.003711  min_lr: 0.003711  loss: 2.6512 (2.5237)  weight_decay: 0.0500 (0.0500)  time: 1.0056  data: 0.0004  max mem: 78493
Epoch: [68]  [170/312]  eta: 0:02:39  lr: 0.003711  min_lr: 0.003711  loss: 2.4842 (2.5157)  weight_decay: 0.0500 (0.0500)  time: 1.0079  data: 0.0005  max mem: 78493
Epoch: [68]  [180/312]  eta: 0:02:27  lr: 0.003710  min_lr: 0.003710  loss: 2.4842 (2.5219)  weight_decay: 0.0500 (0.0500)  time: 1.0089  data: 0.0005  max mem: 78493
Epoch: [68]  [190/312]  eta: 0:02:15  lr: 0.003710  min_lr: 0.003710  loss: 2.3527 (2.5185)  weight_decay: 0.0500 (0.0500)  time: 1.0074  data: 0.0004  max mem: 78493
Epoch: [68]  [200/312]  eta: 0:02:03  lr: 0.003710  min_lr: 0.003710  loss: 2.3527 (2.5137)  weight_decay: 0.0500 (0.0500)  time: 1.0063  data: 0.0005  max mem: 78493
Epoch: [68]  [210/312]  eta: 0:01:52  lr: 0.003709  min_lr: 0.003709  loss: 2.5736 (2.5142)  weight_decay: 0.0500 (0.0500)  time: 1.0053  data: 0.0004  max mem: 78493
Epoch: [68]  [220/312]  eta: 0:01:40  lr: 0.003709  min_lr: 0.003709  loss: 2.5263 (2.5127)  weight_decay: 0.0500 (0.0500)  time: 1.0049  data: 0.0004  max mem: 78493
Epoch: [68]  [230/312]  eta: 0:01:29  lr: 0.003708  min_lr: 0.003708  loss: 2.4214 (2.5114)  weight_decay: 0.0500 (0.0500)  time: 1.0046  data: 0.0004  max mem: 78493
Epoch: [68]  [240/312]  eta: 0:01:18  lr: 0.003708  min_lr: 0.003708  loss: 2.4214 (2.5110)  weight_decay: 0.0500 (0.0500)  time: 1.0057  data: 0.0004  max mem: 78493
Epoch: [68]  [250/312]  eta: 0:01:07  lr: 0.003708  min_lr: 0.003708  loss: 2.5330 (2.5036)  weight_decay: 0.0500 (0.0500)  time: 1.0055  data: 0.0004  max mem: 78493
Epoch: [68]  [260/312]  eta: 0:00:56  lr: 0.003707  min_lr: 0.003707  loss: 2.5330 (2.5095)  weight_decay: 0.0500 (0.0500)  time: 1.0045  data: 0.0005  max mem: 78493
Epoch: [68]  [270/312]  eta: 0:00:45  lr: 0.003707  min_lr: 0.003707  loss: 2.7341 (2.5123)  weight_decay: 0.0500 (0.0500)  time: 1.0056  data: 0.0005  max mem: 78493
Epoch: [68]  [280/312]  eta: 0:00:34  lr: 0.003707  min_lr: 0.003707  loss: 2.4723 (2.5071)  weight_decay: 0.0500 (0.0500)  time: 1.0059  data: 0.0010  max mem: 78493
Epoch: [68]  [290/312]  eta: 0:00:23  lr: 0.003706  min_lr: 0.003706  loss: 2.2364 (2.5041)  weight_decay: 0.0500 (0.0500)  time: 1.0037  data: 0.0009  max mem: 78493
Epoch: [68]  [300/312]  eta: 0:00:12  lr: 0.003706  min_lr: 0.003706  loss: 2.5627 (2.5023)  weight_decay: 0.0500 (0.0500)  time: 1.0022  data: 0.0001  max mem: 78493
Epoch: [68]  [310/312]  eta: 0:00:02  lr: 0.003705  min_lr: 0.003705  loss: 2.6577 (2.5078)  weight_decay: 0.0500 (0.0500)  time: 1.0016  data: 0.0001  max mem: 78493
Epoch: [68]  [311/312]  eta: 0:00:01  lr: 0.003705  min_lr: 0.003705  loss: 2.6577 (2.5084)  weight_decay: 0.0500 (0.0500)  time: 1.0017  data: 0.0001  max mem: 78493
Epoch: [68] Total time: 0:05:35 (1.0745 s / it)
Averaged stats: lr: 0.003705  min_lr: 0.003705  loss: 2.6577 (2.5511)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:14  loss: 0.8324 (0.8324)  acc1: 82.2917 (82.2917)  acc5: 94.1406 (94.1406)  time: 8.2495  data: 7.9803  max mem: 78493
Test:  [8/9]  eta: 0:00:01  loss: 1.2344 (1.1186)  acc1: 72.0052 (72.4320)  acc5: 89.4531 (90.2560)  time: 1.1240  data: 0.8868  max mem: 78493
Test: Total time: 0:00:10 (1.1730 s / it)
* Acc@1 72.106 Acc@5 90.698 loss 1.121
Accuracy of the model on the 50000 test images: 72.1%
Max accuracy: 72.33%
Epoch: [69]  [  0/312]  eta: 1:24:47  lr: 0.003705  min_lr: 0.003705  loss: 1.9148 (1.9148)  weight_decay: 0.0500 (0.0500)  time: 16.3064  data: 13.3151  max mem: 78493
Epoch: [69]  [ 10/312]  eta: 0:12:59  lr: 0.003705  min_lr: 0.003705  loss: 2.0668 (2.2800)  weight_decay: 0.0500 (0.0500)  time: 2.5798  data: 1.3214  max mem: 78493
Epoch: [69]  [ 20/312]  eta: 0:08:58  lr: 0.003705  min_lr: 0.003705  loss: 2.2038 (2.3547)  weight_decay: 0.0500 (0.0500)  time: 1.1212  data: 0.0614  max mem: 78493
Epoch: [69]  [ 30/312]  eta: 0:07:23  lr: 0.003704  min_lr: 0.003704  loss: 2.3049 (2.3500)  weight_decay: 0.0500 (0.0500)  time: 1.0212  data: 0.0005  max mem: 78493
Epoch: [69]  [ 40/312]  eta: 0:06:30  lr: 0.003704  min_lr: 0.003704  loss: 2.6096 (2.4341)  weight_decay: 0.0500 (0.0500)  time: 1.0081  data: 0.0004  max mem: 78493
Epoch: [69]  [ 50/312]  eta: 0:05:54  lr: 0.003703  min_lr: 0.003703  loss: 2.6871 (2.4634)  weight_decay: 0.0500 (0.0500)  time: 1.0085  data: 0.0005  max mem: 78493
Epoch: [69]  [ 60/312]  eta: 0:05:26  lr: 0.003703  min_lr: 0.003703  loss: 2.6304 (2.4730)  weight_decay: 0.0500 (0.0500)  time: 1.0062  data: 0.0004  max mem: 78493
Epoch: [69]  [ 70/312]  eta: 0:05:03  lr: 0.003703  min_lr: 0.003703  loss: 2.3755 (2.4300)  weight_decay: 0.0500 (0.0500)  time: 1.0051  data: 0.0005  max mem: 78493
Epoch: [69]  [ 80/312]  eta: 0:04:43  lr: 0.003702  min_lr: 0.003702  loss: 2.1229 (2.4269)  weight_decay: 0.0500 (0.0500)  time: 1.0069  data: 0.0004  max mem: 78493
Epoch: [69]  [ 90/312]  eta: 0:04:26  lr: 0.003702  min_lr: 0.003702  loss: 2.2891 (2.4171)  weight_decay: 0.0500 (0.0500)  time: 1.0089  data: 0.0004  max mem: 78493
Epoch: [69]  [100/312]  eta: 0:04:10  lr: 0.003702  min_lr: 0.003702  loss: 2.6135 (2.4407)  weight_decay: 0.0500 (0.0500)  time: 1.0101  data: 0.0004  max mem: 78493
Epoch: [69]  [110/312]  eta: 0:03:55  lr: 0.003701  min_lr: 0.003701  loss: 2.7809 (2.4565)  weight_decay: 0.0500 (0.0500)  time: 1.0073  data: 0.0004  max mem: 78493
Epoch: [69]  [120/312]  eta: 0:03:41  lr: 0.003701  min_lr: 0.003701  loss: 2.7651 (2.4708)  weight_decay: 0.0500 (0.0500)  time: 1.0054  data: 0.0004  max mem: 78493
Epoch: [69]  [130/312]  eta: 0:03:27  lr: 0.003700  min_lr: 0.003700  loss: 2.4611 (2.4663)  weight_decay: 0.0500 (0.0500)  time: 1.0061  data: 0.0005  max mem: 78493
Epoch: [69]  [140/312]  eta: 0:03:14  lr: 0.003700  min_lr: 0.003700  loss: 2.3073 (2.4669)  weight_decay: 0.0500 (0.0500)  time: 1.0066  data: 0.0004  max mem: 78493
Epoch: [69]  [150/312]  eta: 0:03:02  lr: 0.003700  min_lr: 0.003700  loss: 2.4983 (2.4806)  weight_decay: 0.0500 (0.0500)  time: 1.0073  data: 0.0004  max mem: 78493
Epoch: [69]  [160/312]  eta: 0:02:49  lr: 0.003699  min_lr: 0.003699  loss: 2.5922 (2.4827)  weight_decay: 0.0500 (0.0500)  time: 1.0067  data: 0.0004  max mem: 78493
Epoch: [69]  [170/312]  eta: 0:02:37  lr: 0.003699  min_lr: 0.003699  loss: 2.6753 (2.4897)  weight_decay: 0.0500 (0.0500)  time: 1.0069  data: 0.0005  max mem: 78493
Epoch: [69]  [180/312]  eta: 0:02:25  lr: 0.003699  min_lr: 0.003699  loss: 2.6521 (2.4910)  weight_decay: 0.0500 (0.0500)  time: 1.0066  data: 0.0005  max mem: 78493
Epoch: [69]  [190/312]  eta: 0:02:14  lr: 0.003698  min_lr: 0.003698  loss: 2.5991 (2.5012)  weight_decay: 0.0500 (0.0500)  time: 1.0054  data: 0.0005  max mem: 78493
Epoch: [69]  [200/312]  eta: 0:02:02  lr: 0.003698  min_lr: 0.003698  loss: 2.6184 (2.5042)  weight_decay: 0.0500 (0.0500)  time: 1.0060  data: 0.0004  max mem: 78493
Epoch: [69]  [210/312]  eta: 0:01:51  lr: 0.003697  min_lr: 0.003697  loss: 2.6184 (2.5064)  weight_decay: 0.0500 (0.0500)  time: 1.0054  data: 0.0004  max mem: 78493
Epoch: [69]  [220/312]  eta: 0:01:39  lr: 0.003697  min_lr: 0.003697  loss: 2.5535 (2.5037)  weight_decay: 0.0500 (0.0500)  time: 1.0046  data: 0.0004  max mem: 78493
Epoch: [69]  [230/312]  eta: 0:01:28  lr: 0.003697  min_lr: 0.003697  loss: 2.6363 (2.5099)  weight_decay: 0.0500 (0.0500)  time: 1.0058  data: 0.0004  max mem: 78493
Epoch: [69]  [240/312]  eta: 0:01:17  lr: 0.003696  min_lr: 0.003696  loss: 2.7712 (2.5153)  weight_decay: 0.0500 (0.0500)  time: 1.0056  data: 0.0004  max mem: 78493
Epoch: [69]  [250/312]  eta: 0:01:06  lr: 0.003696  min_lr: 0.003696  loss: 2.7436 (2.5133)  weight_decay: 0.0500 (0.0500)  time: 1.0051  data: 0.0004  max mem: 78493
Epoch: [69]  [260/312]  eta: 0:00:55  lr: 0.003696  min_lr: 0.003696  loss: 2.7732 (2.5176)  weight_decay: 0.0500 (0.0500)  time: 1.0056  data: 0.0005  max mem: 78493
Epoch: [69]  [270/312]  eta: 0:00:44  lr: 0.003695  min_lr: 0.003695  loss: 2.4470 (2.5121)  weight_decay: 0.0500 (0.0500)  time: 1.0044  data: 0.0004  max mem: 78493
Epoch: [69]  [280/312]  eta: 0:00:34  lr: 0.003695  min_lr: 0.003695  loss: 2.6732 (2.5172)  weight_decay: 0.0500 (0.0500)  time: 1.0051  data: 0.0010  max mem: 78493
Epoch: [69]  [290/312]  eta: 0:00:23  lr: 0.003694  min_lr: 0.003694  loss: 2.7723 (2.5272)  weight_decay: 0.0500 (0.0500)  time: 1.0045  data: 0.0009  max mem: 78493
Epoch: [69]  [300/312]  eta: 0:00:12  lr: 0.003694  min_lr: 0.003694  loss: 2.8333 (2.5336)  weight_decay: 0.0500 (0.0500)  time: 1.0016  data: 0.0001  max mem: 78493
Epoch: [69]  [310/312]  eta: 0:00:02  lr: 0.003694  min_lr: 0.003694  loss: 2.6710 (2.5285)  weight_decay: 0.0500 (0.0500)  time: 1.0017  data: 0.0001  max mem: 78493
Epoch: [69]  [311/312]  eta: 0:00:01  lr: 0.003694  min_lr: 0.003694  loss: 2.5263 (2.5275)  weight_decay: 0.0500 (0.0500)  time: 1.0017  data: 0.0001  max mem: 78493
Epoch: [69] Total time: 0:05:33 (1.0680 s / it)
Averaged stats: lr: 0.003694  min_lr: 0.003694  loss: 2.5263 (2.5328)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:16  loss: 0.8565 (0.8565)  acc1: 80.5990 (80.5990)  acc5: 95.1823 (95.1823)  time: 8.5143  data: 8.2465  max mem: 78493
Test:  [8/9]  eta: 0:00:01  loss: 1.2072 (1.1119)  acc1: 71.0938 (72.4160)  acc5: 89.5833 (90.9280)  time: 1.1454  data: 0.9164  max mem: 78493
Test: Total time: 0:00:10 (1.1605 s / it)
* Acc@1 72.376 Acc@5 91.026 loss 1.097
Accuracy of the model on the 50000 test images: 72.4%
Max accuracy: 72.38%
Epoch: [70]  [  0/312]  eta: 1:26:57  lr: 0.003694  min_lr: 0.003694  loss: 2.8002 (2.8002)  weight_decay: 0.0500 (0.0500)  time: 16.7241  data: 15.7184  max mem: 78493
Epoch: [70]  [ 10/312]  eta: 0:13:16  lr: 0.003693  min_lr: 0.003693  loss: 2.7043 (2.4545)  weight_decay: 0.0500 (0.0500)  time: 2.6388  data: 1.4295  max mem: 78493
Epoch: [70]  [ 20/312]  eta: 0:09:03  lr: 0.003693  min_lr: 0.003693  loss: 2.2276 (2.4439)  weight_decay: 0.0500 (0.0500)  time: 1.1175  data: 0.0006  max mem: 78493
Epoch: [70]  [ 30/312]  eta: 0:07:26  lr: 0.003692  min_lr: 0.003692  loss: 2.4991 (2.5348)  weight_decay: 0.0500 (0.0500)  time: 1.0045  data: 0.0005  max mem: 78493
Epoch: [70]  [ 40/312]  eta: 0:06:32  lr: 0.003692  min_lr: 0.003692  loss: 2.6910 (2.5439)  weight_decay: 0.0500 (0.0500)  time: 1.0048  data: 0.0004  max mem: 78493
Epoch: [70]  [ 50/312]  eta: 0:05:55  lr: 0.003692  min_lr: 0.003692  loss: 2.5581 (2.5259)  weight_decay: 0.0500 (0.0500)  time: 1.0056  data: 0.0004  max mem: 78493
Epoch: [70]  [ 60/312]  eta: 0:05:27  lr: 0.003691  min_lr: 0.003691  loss: 2.6829 (2.5640)  weight_decay: 0.0500 (0.0500)  time: 1.0053  data: 0.0005  max mem: 78493
Epoch: [70]  [ 70/312]  eta: 0:05:04  lr: 0.003691  min_lr: 0.003691  loss: 2.6096 (2.5302)  weight_decay: 0.0500 (0.0500)  time: 1.0050  data: 0.0005  max mem: 78493
Epoch: [70]  [ 80/312]  eta: 0:04:44  lr: 0.003690  min_lr: 0.003690  loss: 2.4706 (2.5471)  weight_decay: 0.0500 (0.0500)  time: 1.0044  data: 0.0004  max mem: 78493
Epoch: [70]  [ 90/312]  eta: 0:04:26  lr: 0.003690  min_lr: 0.003690  loss: 2.6665 (2.5550)  weight_decay: 0.0500 (0.0500)  time: 1.0048  data: 0.0004  max mem: 78493
Epoch: [70]  [100/312]  eta: 0:04:10  lr: 0.003690  min_lr: 0.003690  loss: 2.5943 (2.5496)  weight_decay: 0.0500 (0.0500)  time: 1.0066  data: 0.0004  max mem: 78493
Epoch: [70]  [110/312]  eta: 0:03:55  lr: 0.003689  min_lr: 0.003689  loss: 2.5088 (2.5383)  weight_decay: 0.0500 (0.0500)  time: 1.0085  data: 0.0005  max mem: 78493
Epoch: [70]  [120/312]  eta: 0:03:41  lr: 0.003689  min_lr: 0.003689  loss: 2.5268 (2.5389)  weight_decay: 0.0500 (0.0500)  time: 1.0075  data: 0.0005  max mem: 78493
Epoch: [70]  [130/312]  eta: 0:03:28  lr: 0.003689  min_lr: 0.003689  loss: 2.4601 (2.5292)  weight_decay: 0.0500 (0.0500)  time: 1.0072  data: 0.0005  max mem: 78493
Epoch: [70]  [140/312]  eta: 0:03:14  lr: 0.003688  min_lr: 0.003688  loss: 2.5462 (2.5400)  weight_decay: 0.0500 (0.0500)  time: 1.0074  data: 0.0005  max mem: 78493
Epoch: [70]  [150/312]  eta: 0:03:02  lr: 0.003688  min_lr: 0.003688  loss: 2.6634 (2.5429)  weight_decay: 0.0500 (0.0500)  time: 1.0085  data: 0.0004  max mem: 78493
Epoch: [70]  [160/312]  eta: 0:02:49  lr: 0.003687  min_lr: 0.003687  loss: 2.5625 (2.5382)  weight_decay: 0.0500 (0.0500)  time: 1.0089  data: 0.0005  max mem: 78493
Epoch: [70]  [170/312]  eta: 0:02:37  lr: 0.003687  min_lr: 0.003687  loss: 2.6231 (2.5522)  weight_decay: 0.0500 (0.0500)  time: 1.0068  data: 0.0005  max mem: 78493
Epoch: [70]  [180/312]  eta: 0:02:25  lr: 0.003687  min_lr: 0.003687  loss: 2.7836 (2.5513)  weight_decay: 0.0500 (0.0500)  time: 1.0078  data: 0.0005  max mem: 78493
Epoch: [70]  [190/312]  eta: 0:02:14  lr: 0.003686  min_lr: 0.003686  loss: 2.4340 (2.5427)  weight_decay: 0.0500 (0.0500)  time: 1.0074  data: 0.0004  max mem: 78493
Epoch: [70]  [200/312]  eta: 0:02:02  lr: 0.003686  min_lr: 0.003686  loss: 2.2904 (2.5321)  weight_decay: 0.0500 (0.0500)  time: 1.0063  data: 0.0004  max mem: 78493
Epoch: [70]  [210/312]  eta: 0:01:51  lr: 0.003685  min_lr: 0.003685  loss: 2.5295 (2.5338)  weight_decay: 0.0500 (0.0500)  time: 1.0086  data: 0.0004  max mem: 78493
Epoch: [70]  [220/312]  eta: 0:01:40  lr: 0.003685  min_lr: 0.003685  loss: 2.6689 (2.5343)  weight_decay: 0.0500 (0.0500)  time: 1.0076  data: 0.0004  max mem: 78493
Epoch: [70]  [230/312]  eta: 0:01:28  lr: 0.003685  min_lr: 0.003685  loss: 2.6689 (2.5422)  weight_decay: 0.0500 (0.0500)  time: 1.0046  data: 0.0004  max mem: 78493
Epoch: [70]  [240/312]  eta: 0:01:17  lr: 0.003684  min_lr: 0.003684  loss: 2.6067 (2.5350)  weight_decay: 0.0500 (0.0500)  time: 1.0042  data: 0.0004  max mem: 78493
Epoch: [70]  [250/312]  eta: 0:01:06  lr: 0.003684  min_lr: 0.003684  loss: 2.3251 (2.5317)  weight_decay: 0.0500 (0.0500)  time: 1.0054  data: 0.0005  max mem: 78493
Epoch: [70]  [260/312]  eta: 0:00:55  lr: 0.003684  min_lr: 0.003684  loss: 2.3251 (2.5290)  weight_decay: 0.0500 (0.0500)  time: 1.0070  data: 0.0005  max mem: 78493
Epoch: [70]  [270/312]  eta: 0:00:45  lr: 0.003683  min_lr: 0.003683  loss: 2.5615 (2.5329)  weight_decay: 0.0500 (0.0500)  time: 1.0064  data: 0.0004  max mem: 78493
Epoch: [70]  [280/312]  eta: 0:00:34  lr: 0.003683  min_lr: 0.003683  loss: 2.5615 (2.5276)  weight_decay: 0.0500 (0.0500)  time: 1.0082  data: 0.0011  max mem: 78493
Epoch: [70]  [290/312]  eta: 0:00:23  lr: 0.003682  min_lr: 0.003682  loss: 2.2667 (2.5250)  weight_decay: 0.0500 (0.0500)  time: 1.0063  data: 0.0009  max mem: 78493
Epoch: [70]  [300/312]  eta: 0:00:12  lr: 0.003682  min_lr: 0.003682  loss: 2.2904 (2.5222)  weight_decay: 0.0500 (0.0500)  time: 1.0019  data: 0.0001  max mem: 78493
Epoch: [70]  [310/312]  eta: 0:00:02  lr: 0.003682  min_lr: 0.003682  loss: 2.5734 (2.5265)  weight_decay: 0.0500 (0.0500)  time: 1.0020  data: 0.0001  max mem: 78493
Epoch: [70]  [311/312]  eta: 0:00:01  lr: 0.003682  min_lr: 0.003682  loss: 2.5734 (2.5278)  weight_decay: 0.0500 (0.0500)  time: 1.0019  data: 0.0001  max mem: 78493
Epoch: [70] Total time: 0:05:33 (1.0694 s / it)
Averaged stats: lr: 0.003682  min_lr: 0.003682  loss: 2.5734 (2.5358)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:09  loss: 0.8714 (0.8714)  acc1: 78.6458 (78.6458)  acc5: 94.4010 (94.4010)  time: 7.7159  data: 7.4523  max mem: 78493
Test:  [8/9]  eta: 0:00:01  loss: 1.2501 (1.1278)  acc1: 71.4844 (72.4000)  acc5: 90.8854 (90.9760)  time: 1.0769  data: 0.8467  max mem: 78493
Test: Total time: 0:00:09 (1.0945 s / it)
* Acc@1 72.234 Acc@5 90.898 loss 1.137
Accuracy of the model on the 50000 test images: 72.2%
Max accuracy: 72.38%
Epoch: [71]  [  0/312]  eta: 1:26:13  lr: 0.003681  min_lr: 0.003681  loss: 1.9452 (1.9452)  weight_decay: 0.0500 (0.0500)  time: 16.5826  data: 11.5872  max mem: 78493
Epoch: [71]  [ 10/312]  eta: 0:12:52  lr: 0.003681  min_lr: 0.003681  loss: 2.3181 (2.3257)  weight_decay: 0.0500 (0.0500)  time: 2.5592  data: 1.1102  max mem: 78493
Epoch: [71]  [ 20/312]  eta: 0:08:57  lr: 0.003681  min_lr: 0.003681  loss: 2.6142 (2.4521)  weight_decay: 0.0500 (0.0500)  time: 1.1021  data: 0.0337  max mem: 78493
Epoch: [71]  [ 30/312]  eta: 0:07:23  lr: 0.003680  min_lr: 0.003680  loss: 2.7305 (2.5232)  weight_decay: 0.0500 (0.0500)  time: 1.0293  data: 0.0026  max mem: 78493
Epoch: [71]  [ 40/312]  eta: 0:06:30  lr: 0.003680  min_lr: 0.003680  loss: 2.6514 (2.5029)  weight_decay: 0.0500 (0.0500)  time: 1.0095  data: 0.0004  max mem: 78493
Epoch: [71]  [ 50/312]  eta: 0:05:54  lr: 0.003680  min_lr: 0.003680  loss: 2.6450 (2.5039)  weight_decay: 0.0500 (0.0500)  time: 1.0099  data: 0.0004  max mem: 78493
Epoch: [71]  [ 60/312]  eta: 0:05:26  lr: 0.003679  min_lr: 0.003679  loss: 2.6959 (2.5052)  weight_decay: 0.0500 (0.0500)  time: 1.0103  data: 0.0004  max mem: 78493
Epoch: [71]  [ 70/312]  eta: 0:05:03  lr: 0.003679  min_lr: 0.003679  loss: 2.5960 (2.5230)  weight_decay: 0.0500 (0.0500)  time: 1.0090  data: 0.0004  max mem: 78493
Epoch: [71]  [ 80/312]  eta: 0:04:44  lr: 0.003678  min_lr: 0.003678  loss: 2.4994 (2.5102)  weight_decay: 0.0500 (0.0500)  time: 1.0096  data: 0.0004  max mem: 78493
Epoch: [71]  [ 90/312]  eta: 0:04:26  lr: 0.003678  min_lr: 0.003678  loss: 2.5125 (2.5107)  weight_decay: 0.0500 (0.0500)  time: 1.0080  data: 0.0004  max mem: 78493
Epoch: [71]  [100/312]  eta: 0:04:10  lr: 0.003678  min_lr: 0.003678  loss: 2.5379 (2.5227)  weight_decay: 0.0500 (0.0500)  time: 1.0084  data: 0.0004  max mem: 78493
Epoch: [71]  [110/312]  eta: 0:03:55  lr: 0.003677  min_lr: 0.003677  loss: 2.7048 (2.5476)  weight_decay: 0.0500 (0.0500)  time: 1.0100  data: 0.0004  max mem: 78493
Epoch: [71]  [120/312]  eta: 0:03:41  lr: 0.003677  min_lr: 0.003677  loss: 2.7865 (2.5648)  weight_decay: 0.0500 (0.0500)  time: 1.0080  data: 0.0005  max mem: 78493
Epoch: [71]  [130/312]  eta: 0:03:27  lr: 0.003676  min_lr: 0.003676  loss: 2.7865 (2.5793)  weight_decay: 0.0500 (0.0500)  time: 1.0074  data: 0.0005  max mem: 78493
Epoch: [71]  [140/312]  eta: 0:03:14  lr: 0.003676  min_lr: 0.003676  loss: 2.5632 (2.5646)  weight_decay: 0.0500 (0.0500)  time: 1.0081  data: 0.0004  max mem: 78493
Epoch: [71]  [150/312]  eta: 0:03:02  lr: 0.003676  min_lr: 0.003676  loss: 2.3365 (2.5533)  weight_decay: 0.0500 (0.0500)  time: 1.0095  data: 0.0004  max mem: 78493
Epoch: [71]  [160/312]  eta: 0:02:49  lr: 0.003675  min_lr: 0.003675  loss: 2.4037 (2.5525)  weight_decay: 0.0500 (0.0500)  time: 1.0087  data: 0.0004  max mem: 78493
Epoch: [71]  [170/312]  eta: 0:02:37  lr: 0.003675  min_lr: 0.003675  loss: 2.6809 (2.5556)  weight_decay: 0.0500 (0.0500)  time: 1.0066  data: 0.0004  max mem: 78493
Epoch: [71]  [180/312]  eta: 0:02:25  lr: 0.003674  min_lr: 0.003674  loss: 2.8631 (2.5709)  weight_decay: 0.0500 (0.0500)  time: 1.0067  data: 0.0004  max mem: 78493
Epoch: [71]  [190/312]  eta: 0:02:14  lr: 0.003674  min_lr: 0.003674  loss: 2.7609 (2.5723)  weight_decay: 0.0500 (0.0500)  time: 1.0066  data: 0.0004  max mem: 78493
Epoch: [71]  [200/312]  eta: 0:02:02  lr: 0.003674  min_lr: 0.003674  loss: 2.4338 (2.5670)  weight_decay: 0.0500 (0.0500)  time: 1.0060  data: 0.0004  max mem: 78493
Epoch: [71]  [210/312]  eta: 0:01:51  lr: 0.003673  min_lr: 0.003673  loss: 2.5622 (2.5733)  weight_decay: 0.0500 (0.0500)  time: 1.0062  data: 0.0004  max mem: 78493
Epoch: [71]  [220/312]  eta: 0:01:40  lr: 0.003673  min_lr: 0.003673  loss: 2.5622 (2.5665)  weight_decay: 0.0500 (0.0500)  time: 1.0065  data: 0.0004  max mem: 78493
Epoch: [71]  [230/312]  eta: 0:01:28  lr: 0.003672  min_lr: 0.003672  loss: 2.5012 (2.5680)  weight_decay: 0.0500 (0.0500)  time: 1.0051  data: 0.0004  max mem: 78493
Epoch: [71]  [240/312]  eta: 0:01:17  lr: 0.003672  min_lr: 0.003672  loss: 2.6061 (2.5698)  weight_decay: 0.0500 (0.0500)  time: 1.0046  data: 0.0004  max mem: 78493
Epoch: [71]  [250/312]  eta: 0:01:06  lr: 0.003672  min_lr: 0.003672  loss: 2.6061 (2.5706)  weight_decay: 0.0500 (0.0500)  time: 1.0051  data: 0.0013  max mem: 78493
Epoch: [71]  [260/312]  eta: 0:00:55  lr: 0.003671  min_lr: 0.003671  loss: 2.6744 (2.5661)  weight_decay: 0.0500 (0.0500)  time: 1.0054  data: 0.0013  max mem: 78493
Epoch: [71]  [270/312]  eta: 0:00:45  lr: 0.003671  min_lr: 0.003671  loss: 2.5818 (2.5702)  weight_decay: 0.0500 (0.0500)  time: 1.0065  data: 0.0004  max mem: 78493
Epoch: [71]  [280/312]  eta: 0:00:34  lr: 0.003670  min_lr: 0.003670  loss: 2.6040 (2.5697)  weight_decay: 0.0500 (0.0500)  time: 1.0082  data: 0.0010  max mem: 78493
Epoch: [71]  [290/312]  eta: 0:00:23  lr: 0.003670  min_lr: 0.003670  loss: 2.6135 (2.5725)  weight_decay: 0.0500 (0.0500)  time: 1.0054  data: 0.0009  max mem: 78493
Epoch: [71]  [300/312]  eta: 0:00:12  lr: 0.003670  min_lr: 0.003670  loss: 2.7353 (2.5759)  weight_decay: 0.0500 (0.0500)  time: 1.0019  data: 0.0001  max mem: 78493
Epoch: [71]  [310/312]  eta: 0:00:02  lr: 0.003669  min_lr: 0.003669  loss: 2.7183 (2.5784)  weight_decay: 0.0500 (0.0500)  time: 1.0020  data: 0.0001  max mem: 78493
Epoch: [71]  [311/312]  eta: 0:00:01  lr: 0.003669  min_lr: 0.003669  loss: 2.7183 (2.5805)  weight_decay: 0.0500 (0.0500)  time: 1.0020  data: 0.0001  max mem: 78493
Epoch: [71] Total time: 0:05:33 (1.0692 s / it)
Averaged stats: lr: 0.003669  min_lr: 0.003669  loss: 2.7183 (2.5433)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:14  loss: 0.9541 (0.9541)  acc1: 76.0417 (76.0417)  acc5: 94.4010 (94.4010)  time: 8.3219  data: 8.0566  max mem: 78493
Test:  [8/9]  eta: 0:00:01  loss: 1.2773 (1.1281)  acc1: 69.9219 (71.4720)  acc5: 89.8438 (90.8320)  time: 1.1252  data: 0.8953  max mem: 78493
Test: Total time: 0:00:10 (1.1444 s / it)
* Acc@1 72.506 Acc@5 90.948 loss 1.121
Accuracy of the model on the 50000 test images: 72.5%
Max accuracy: 72.51%
Epoch: [72]  [  0/312]  eta: 1:29:53  lr: 0.003669  min_lr: 0.003669  loss: 2.0431 (2.0431)  weight_decay: 0.0500 (0.0500)  time: 17.2863  data: 16.2517  max mem: 78493
Epoch: [72]  [ 10/312]  eta: 0:13:40  lr: 0.003669  min_lr: 0.003669  loss: 2.6166 (2.4299)  weight_decay: 0.0500 (0.0500)  time: 2.7158  data: 1.4783  max mem: 78493
Epoch: [72]  [ 20/312]  eta: 0:09:16  lr: 0.003668  min_lr: 0.003668  loss: 2.6809 (2.5059)  weight_decay: 0.0500 (0.0500)  time: 1.1361  data: 0.0007  max mem: 78493
Epoch: [72]  [ 30/312]  eta: 0:07:35  lr: 0.003668  min_lr: 0.003668  loss: 2.6465 (2.4759)  weight_decay: 0.0500 (0.0500)  time: 1.0113  data: 0.0004  max mem: 78493
Epoch: [72]  [ 40/312]  eta: 0:06:38  lr: 0.003668  min_lr: 0.003668  loss: 2.3924 (2.4887)  weight_decay: 0.0500 (0.0500)  time: 1.0065  data: 0.0004  max mem: 78493
Epoch: [72]  [ 50/312]  eta: 0:06:00  lr: 0.003667  min_lr: 0.003667  loss: 2.7011 (2.5471)  weight_decay: 0.0500 (0.0500)  time: 1.0044  data: 0.0005  max mem: 78493
Epoch: [72]  [ 60/312]  eta: 0:05:31  lr: 0.003667  min_lr: 0.003667  loss: 2.6870 (2.5514)  weight_decay: 0.0500 (0.0500)  time: 1.0048  data: 0.0005  max mem: 78493
Epoch: [72]  [ 70/312]  eta: 0:05:07  lr: 0.003666  min_lr: 0.003666  loss: 2.5545 (2.5443)  weight_decay: 0.0500 (0.0500)  time: 1.0057  data: 0.0005  max mem: 78493
Epoch: [72]  [ 80/312]  eta: 0:04:47  lr: 0.003666  min_lr: 0.003666  loss: 2.3890 (2.5264)  weight_decay: 0.0500 (0.0500)  time: 1.0057  data: 0.0013  max mem: 78493
Epoch: [72]  [ 90/312]  eta: 0:04:29  lr: 0.003666  min_lr: 0.003666  loss: 2.5151 (2.5284)  weight_decay: 0.0500 (0.0500)  time: 1.0067  data: 0.0013  max mem: 78493
Epoch: [72]  [100/312]  eta: 0:04:12  lr: 0.003665  min_lr: 0.003665  loss: 2.5062 (2.5138)  weight_decay: 0.0500 (0.0500)  time: 1.0088  data: 0.0004  max mem: 78493
Epoch: [72]  [110/312]  eta: 0:03:57  lr: 0.003665  min_lr: 0.003665  loss: 2.5062 (2.5256)  weight_decay: 0.0500 (0.0500)  time: 1.0077  data: 0.0004  max mem: 78493
Epoch: [72]  [120/312]  eta: 0:03:43  lr: 0.003664  min_lr: 0.003664  loss: 2.7122 (2.5246)  weight_decay: 0.0500 (0.0500)  time: 1.0063  data: 0.0004  max mem: 78493
Epoch: [72]  [130/312]  eta: 0:03:29  lr: 0.003664  min_lr: 0.003664  loss: 2.1327 (2.4966)  weight_decay: 0.0500 (0.0500)  time: 1.0056  data: 0.0005  max mem: 78493
Epoch: [72]  [140/312]  eta: 0:03:16  lr: 0.003664  min_lr: 0.003664  loss: 2.3371 (2.5055)  weight_decay: 0.0500 (0.0500)  time: 1.0056  data: 0.0005  max mem: 78493
Epoch: [72]  [150/312]  eta: 0:03:03  lr: 0.003663  min_lr: 0.003663  loss: 2.6448 (2.5114)  weight_decay: 0.0500 (0.0500)  time: 1.0080  data: 0.0004  max mem: 78493
Epoch: [72]  [160/312]  eta: 0:02:50  lr: 0.003663  min_lr: 0.003663  loss: 2.7552 (2.5148)  weight_decay: 0.0500 (0.0500)  time: 1.0102  data: 0.0012  max mem: 78493
Epoch: [72]  [170/312]  eta: 0:02:38  lr: 0.003662  min_lr: 0.003662  loss: 2.7313 (2.5235)  weight_decay: 0.0500 (0.0500)  time: 1.0101  data: 0.0012  max mem: 78493
Epoch: [72]  [180/312]  eta: 0:02:26  lr: 0.003662  min_lr: 0.003662  loss: 2.6980 (2.5283)  weight_decay: 0.0500 (0.0500)  time: 1.0084  data: 0.0005  max mem: 78493
Epoch: [72]  [190/312]  eta: 0:02:14  lr: 0.003662  min_lr: 0.003662  loss: 2.6980 (2.5351)  weight_decay: 0.0500 (0.0500)  time: 1.0074  data: 0.0005  max mem: 78493
Epoch: [72]  [200/312]  eta: 0:02:03  lr: 0.003661  min_lr: 0.003661  loss: 2.6632 (2.5317)  weight_decay: 0.0500 (0.0500)  time: 1.0078  data: 0.0004  max mem: 78493
Epoch: [72]  [210/312]  eta: 0:01:51  lr: 0.003661  min_lr: 0.003661  loss: 2.3922 (2.5245)  weight_decay: 0.0500 (0.0500)  time: 1.0084  data: 0.0004  max mem: 78493
Epoch: [72]  [220/312]  eta: 0:01:40  lr: 0.003660  min_lr: 0.003660  loss: 2.3182 (2.5170)  weight_decay: 0.0500 (0.0500)  time: 1.0080  data: 0.0005  max mem: 78493
Epoch: [72]  [230/312]  eta: 0:01:29  lr: 0.003660  min_lr: 0.003660  loss: 2.3520 (2.5068)  weight_decay: 0.0500 (0.0500)  time: 1.0068  data: 0.0005  max mem: 78493
Epoch: [72]  [240/312]  eta: 0:01:18  lr: 0.003660  min_lr: 0.003660  loss: 2.3520 (2.5051)  weight_decay: 0.0500 (0.0500)  time: 1.0063  data: 0.0005  max mem: 78493
Epoch: [72]  [250/312]  eta: 0:01:07  lr: 0.003659  min_lr: 0.003659  loss: 2.5210 (2.5026)  weight_decay: 0.0500 (0.0500)  time: 1.0052  data: 0.0005  max mem: 78493
Epoch: [72]  [260/312]  eta: 0:00:56  lr: 0.003659  min_lr: 0.003659  loss: 2.6339 (2.5051)  weight_decay: 0.0500 (0.0500)  time: 1.0045  data: 0.0005  max mem: 78493
Epoch: [72]  [270/312]  eta: 0:00:45  lr: 0.003658  min_lr: 0.003658  loss: 2.5876 (2.5071)  weight_decay: 0.0500 (0.0500)  time: 1.0043  data: 0.0005  max mem: 78493
Epoch: [72]  [280/312]  eta: 0:00:34  lr: 0.003658  min_lr: 0.003658  loss: 2.5876 (2.5119)  weight_decay: 0.0500 (0.0500)  time: 1.0046  data: 0.0011  max mem: 78493
Epoch: [72]  [290/312]  eta: 0:00:23  lr: 0.003658  min_lr: 0.003658  loss: 2.6601 (2.5145)  weight_decay: 0.0500 (0.0500)  time: 1.0034  data: 0.0009  max mem: 78493
Epoch: [72]  [300/312]  eta: 0:00:12  lr: 0.003657  min_lr: 0.003657  loss: 2.6601 (2.5165)  weight_decay: 0.0500 (0.0500)  time: 1.0015  data: 0.0001  max mem: 78493
Epoch: [72]  [310/312]  eta: 0:00:02  lr: 0.003657  min_lr: 0.003657  loss: 2.5864 (2.5109)  weight_decay: 0.0500 (0.0500)  time: 1.0017  data: 0.0001  max mem: 78493
Epoch: [72]  [311/312]  eta: 0:00:01  lr: 0.003657  min_lr: 0.003657  loss: 2.5864 (2.5105)  weight_decay: 0.0500 (0.0500)  time: 1.0017  data: 0.0001  max mem: 78493
Epoch: [72] Total time: 0:05:34 (1.0723 s / it)
Averaged stats: lr: 0.003657  min_lr: 0.003657  loss: 2.5864 (2.5191)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:06  loss: 0.9251 (0.9251)  acc1: 77.6042 (77.6042)  acc5: 92.8385 (92.8385)  time: 7.3881  data: 7.1190  max mem: 78493
Test:  [8/9]  eta: 0:00:01  loss: 1.2185 (1.1377)  acc1: 71.7448 (71.9040)  acc5: 90.6250 (90.7200)  time: 1.0602  data: 0.8321  max mem: 78493
Test: Total time: 0:00:09 (1.0771 s / it)
* Acc@1 71.336 Acc@5 90.722 loss 1.134
Accuracy of the model on the 50000 test images: 71.3%
Max accuracy: 72.51%
Epoch: [73]  [  0/312]  eta: 1:27:13  lr: 0.003657  min_lr: 0.003657  loss: 3.1035 (3.1035)  weight_decay: 0.0500 (0.0500)  time: 16.7749  data: 15.7485  max mem: 78493
Epoch: [73]  [ 10/312]  eta: 0:13:53  lr: 0.003656  min_lr: 0.003656  loss: 2.7813 (2.7397)  weight_decay: 0.0500 (0.0500)  time: 2.7600  data: 1.4324  max mem: 78493
Epoch: [73]  [ 20/312]  eta: 0:09:22  lr: 0.003656  min_lr: 0.003656  loss: 2.5612 (2.5770)  weight_decay: 0.0500 (0.0500)  time: 1.1839  data: 0.0017  max mem: 78493
Epoch: [73]  [ 30/312]  eta: 0:07:39  lr: 0.003656  min_lr: 0.003656  loss: 2.7709 (2.6467)  weight_decay: 0.0500 (0.0500)  time: 1.0070  data: 0.0015  max mem: 78493
Epoch: [73]  [ 40/312]  eta: 0:06:41  lr: 0.003655  min_lr: 0.003655  loss: 2.8086 (2.6395)  weight_decay: 0.0500 (0.0500)  time: 1.0064  data: 0.0004  max mem: 78493
Epoch: [73]  [ 50/312]  eta: 0:06:02  lr: 0.003655  min_lr: 0.003655  loss: 2.4539 (2.5680)  weight_decay: 0.0500 (0.0500)  time: 1.0074  data: 0.0004  max mem: 78493
Epoch: [73]  [ 60/312]  eta: 0:05:33  lr: 0.003654  min_lr: 0.003654  loss: 2.4124 (2.5643)  weight_decay: 0.0500 (0.0500)  time: 1.0065  data: 0.0005  max mem: 78493
Epoch: [73]  [ 70/312]  eta: 0:05:09  lr: 0.003654  min_lr: 0.003654  loss: 2.5675 (2.5607)  weight_decay: 0.0500 (0.0500)  time: 1.0063  data: 0.0005  max mem: 78493
Epoch: [73]  [ 80/312]  eta: 0:04:48  lr: 0.003654  min_lr: 0.003654  loss: 2.6727 (2.5611)  weight_decay: 0.0500 (0.0500)  time: 1.0082  data: 0.0013  max mem: 78493
Epoch: [73]  [ 90/312]  eta: 0:04:30  lr: 0.003653  min_lr: 0.003653  loss: 2.5903 (2.5385)  weight_decay: 0.0500 (0.0500)  time: 1.0082  data: 0.0013  max mem: 78493
Epoch: [73]  [100/312]  eta: 0:04:13  lr: 0.003653  min_lr: 0.003653  loss: 2.2610 (2.5120)  weight_decay: 0.0500 (0.0500)  time: 1.0057  data: 0.0005  max mem: 78493
Epoch: [73]  [110/312]  eta: 0:03:58  lr: 0.003652  min_lr: 0.003652  loss: 2.4063 (2.5070)  weight_decay: 0.0500 (0.0500)  time: 1.0063  data: 0.0005  max mem: 78493
Epoch: [73]  [120/312]  eta: 0:03:43  lr: 0.003652  min_lr: 0.003652  loss: 2.6364 (2.5140)  weight_decay: 0.0500 (0.0500)  time: 1.0089  data: 0.0005  max mem: 78493
Epoch: [73]  [130/312]  eta: 0:03:30  lr: 0.003652  min_lr: 0.003652  loss: 2.7222 (2.5118)  weight_decay: 0.0500 (0.0500)  time: 1.0075  data: 0.0005  max mem: 78493
Epoch: [73]  [140/312]  eta: 0:03:16  lr: 0.003651  min_lr: 0.003651  loss: 2.6496 (2.5240)  weight_decay: 0.0500 (0.0500)  time: 1.0055  data: 0.0005  max mem: 78493
Epoch: [73]  [150/312]  eta: 0:03:03  lr: 0.003651  min_lr: 0.003651  loss: 2.5155 (2.5178)  weight_decay: 0.0500 (0.0500)  time: 1.0054  data: 0.0005  max mem: 78493
Epoch: [73]  [160/312]  eta: 0:02:51  lr: 0.003650  min_lr: 0.003650  loss: 2.5841 (2.5206)  weight_decay: 0.0500 (0.0500)  time: 1.0044  data: 0.0005  max mem: 78493
Epoch: [73]  [170/312]  eta: 0:02:38  lr: 0.003650  min_lr: 0.003650  loss: 2.6862 (2.5206)  weight_decay: 0.0500 (0.0500)  time: 1.0044  data: 0.0004  max mem: 78493
Epoch: [73]  [180/312]  eta: 0:02:26  lr: 0.003649  min_lr: 0.003649  loss: 2.6862 (2.5189)  weight_decay: 0.0500 (0.0500)  time: 1.0061  data: 0.0010  max mem: 78493
Epoch: [73]  [190/312]  eta: 0:02:15  lr: 0.003649  min_lr: 0.003649  loss: 2.7079 (2.5217)  weight_decay: 0.0500 (0.0500)  time: 1.0059  data: 0.0010  max mem: 78493
Epoch: [73]  [200/312]  eta: 0:02:03  lr: 0.003649  min_lr: 0.003649  loss: 2.5303 (2.5177)  weight_decay: 0.0500 (0.0500)  time: 1.0055  data: 0.0004  max mem: 78493
Epoch: [73]  [210/312]  eta: 0:01:51  lr: 0.003648  min_lr: 0.003648  loss: 2.4849 (2.5226)  weight_decay: 0.0500 (0.0500)  time: 1.0055  data: 0.0005  max mem: 78493
Epoch: [73]  [220/312]  eta: 0:01:40  lr: 0.003648  min_lr: 0.003648  loss: 2.6933 (2.5260)  weight_decay: 0.0500 (0.0500)  time: 1.0054  data: 0.0005  max mem: 78493
Epoch: [73]  [230/312]  eta: 0:01:29  lr: 0.003647  min_lr: 0.003647  loss: 2.6816 (2.5277)  weight_decay: 0.0500 (0.0500)  time: 1.0055  data: 0.0005  max mem: 78493
Epoch: [73]  [240/312]  eta: 0:01:18  lr: 0.003647  min_lr: 0.003647  loss: 2.6762 (2.5356)  weight_decay: 0.0500 (0.0500)  time: 1.0053  data: 0.0005  max mem: 78493
Epoch: [73]  [250/312]  eta: 0:01:07  lr: 0.003647  min_lr: 0.003647  loss: 2.6297 (2.5291)  weight_decay: 0.0500 (0.0500)  time: 1.0050  data: 0.0004  max mem: 78493
Epoch: [73]  [260/312]  eta: 0:00:56  lr: 0.003646  min_lr: 0.003646  loss: 2.3998 (2.5265)  weight_decay: 0.0500 (0.0500)  time: 1.0063  data: 0.0005  max mem: 78493
Epoch: [73]  [270/312]  eta: 0:00:45  lr: 0.003646  min_lr: 0.003646  loss: 2.5720 (2.5253)  weight_decay: 0.0500 (0.0500)  time: 1.0084  data: 0.0005  max mem: 78493
Epoch: [73]  [280/312]  eta: 0:00:34  lr: 0.003645  min_lr: 0.003645  loss: 2.5627 (2.5183)  weight_decay: 0.0500 (0.0500)  time: 1.0072  data: 0.0011  max mem: 78493
Epoch: [73]  [290/312]  eta: 0:00:23  lr: 0.003645  min_lr: 0.003645  loss: 2.2766 (2.5174)  weight_decay: 0.0500 (0.0500)  time: 1.0053  data: 0.0009  max mem: 78493
Epoch: [73]  [300/312]  eta: 0:00:12  lr: 0.003645  min_lr: 0.003645  loss: 2.5004 (2.5154)  weight_decay: 0.0500 (0.0500)  time: 1.0034  data: 0.0001  max mem: 78493
Epoch: [73]  [310/312]  eta: 0:00:02  lr: 0.003644  min_lr: 0.003644  loss: 2.6901 (2.5219)  weight_decay: 0.0500 (0.0500)  time: 1.0017  data: 0.0001  max mem: 78493
Epoch: [73]  [311/312]  eta: 0:00:01  lr: 0.003644  min_lr: 0.003644  loss: 2.6196 (2.5196)  weight_decay: 0.0500 (0.0500)  time: 1.0017  data: 0.0001  max mem: 78493
Epoch: [73] Total time: 0:05:34 (1.0735 s / it)
Averaged stats: lr: 0.003644  min_lr: 0.003644  loss: 2.6196 (2.5268)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:09  loss: 0.8726 (0.8726)  acc1: 79.5573 (79.5573)  acc5: 94.0104 (94.0104)  time: 7.7575  data: 7.4879  max mem: 78493
Test:  [8/9]  eta: 0:00:01  loss: 1.2567 (1.1243)  acc1: 70.3125 (71.9840)  acc5: 90.4948 (90.7040)  time: 1.0670  data: 0.8321  max mem: 78493
Test: Total time: 0:00:09 (1.0780 s / it)
* Acc@1 72.534 Acc@5 91.066 loss 1.105
Accuracy of the model on the 50000 test images: 72.5%
Max accuracy: 72.53%
Epoch: [74]  [  0/312]  eta: 1:20:18  lr: 0.003644  min_lr: 0.003644  loss: 2.3012 (2.3012)  weight_decay: 0.0500 (0.0500)  time: 15.4426  data: 13.3357  max mem: 78493
Epoch: [74]  [ 10/312]  eta: 0:12:31  lr: 0.003644  min_lr: 0.003644  loss: 2.6700 (2.4578)  weight_decay: 0.0500 (0.0500)  time: 2.4875  data: 1.2466  max mem: 78493
Epoch: [74]  [ 20/312]  eta: 0:08:42  lr: 0.003643  min_lr: 0.003643  loss: 2.7101 (2.5457)  weight_decay: 0.0500 (0.0500)  time: 1.1081  data: 0.0192  max mem: 78493
Epoch: [74]  [ 30/312]  eta: 0:07:13  lr: 0.003643  min_lr: 0.003643  loss: 2.6896 (2.4733)  weight_decay: 0.0500 (0.0500)  time: 1.0168  data: 0.0005  max mem: 78493
Epoch: [74]  [ 40/312]  eta: 0:06:23  lr: 0.003642  min_lr: 0.003642  loss: 2.3982 (2.4933)  weight_decay: 0.0500 (0.0500)  time: 1.0064  data: 0.0004  max mem: 78493
Epoch: [74]  [ 50/312]  eta: 0:05:48  lr: 0.003642  min_lr: 0.003642  loss: 2.5212 (2.4800)  weight_decay: 0.0500 (0.0500)  time: 1.0048  data: 0.0004  max mem: 78493
Epoch: [74]  [ 60/312]  eta: 0:05:21  lr: 0.003642  min_lr: 0.003642  loss: 2.6035 (2.4901)  weight_decay: 0.0500 (0.0500)  time: 1.0059  data: 0.0004  max mem: 78493
Epoch: [74]  [ 70/312]  eta: 0:04:59  lr: 0.003641  min_lr: 0.003641  loss: 2.6171 (2.5023)  weight_decay: 0.0500 (0.0500)  time: 1.0058  data: 0.0013  max mem: 78493
Epoch: [74]  [ 80/312]  eta: 0:04:40  lr: 0.003641  min_lr: 0.003641  loss: 2.5525 (2.4837)  weight_decay: 0.0500 (0.0500)  time: 1.0058  data: 0.0012  max mem: 78493
Epoch: [74]  [ 90/312]  eta: 0:04:23  lr: 0.003640  min_lr: 0.003640  loss: 2.5527 (2.4917)  weight_decay: 0.0500 (0.0500)  time: 1.0088  data: 0.0004  max mem: 78493
Epoch: [74]  [100/312]  eta: 0:04:07  lr: 0.003640  min_lr: 0.003640  loss: 2.5527 (2.4808)  weight_decay: 0.0500 (0.0500)  time: 1.0091  data: 0.0004  max mem: 78493
Epoch: [74]  [110/312]  eta: 0:03:53  lr: 0.003640  min_lr: 0.003640  loss: 2.6267 (2.5010)  weight_decay: 0.0500 (0.0500)  time: 1.0082  data: 0.0004  max mem: 78493
Epoch: [74]  [120/312]  eta: 0:03:39  lr: 0.003639  min_lr: 0.003639  loss: 2.7606 (2.4976)  weight_decay: 0.0500 (0.0500)  time: 1.0079  data: 0.0004  max mem: 78493
Epoch: [74]  [130/312]  eta: 0:03:26  lr: 0.003639  min_lr: 0.003639  loss: 2.4891 (2.5028)  weight_decay: 0.0500 (0.0500)  time: 1.0085  data: 0.0004  max mem: 78493
Epoch: [74]  [140/312]  eta: 0:03:13  lr: 0.003638  min_lr: 0.003638  loss: 2.6703 (2.5146)  weight_decay: 0.0500 (0.0500)  time: 1.0097  data: 0.0004  max mem: 78493
Epoch: [74]  [150/312]  eta: 0:03:00  lr: 0.003638  min_lr: 0.003638  loss: 2.5317 (2.5221)  weight_decay: 0.0500 (0.0500)  time: 1.0066  data: 0.0004  max mem: 78493
Epoch: [74]  [160/312]  eta: 0:02:48  lr: 0.003638  min_lr: 0.003638  loss: 2.5059 (2.5169)  weight_decay: 0.0500 (0.0500)  time: 1.0069  data: 0.0004  max mem: 78493
Epoch: [74]  [170/312]  eta: 0:02:36  lr: 0.003637  min_lr: 0.003637  loss: 2.4660 (2.5170)  weight_decay: 0.0500 (0.0500)  time: 1.0068  data: 0.0004  max mem: 78493
Epoch: [74]  [180/312]  eta: 0:02:24  lr: 0.003637  min_lr: 0.003637  loss: 2.6363 (2.5265)  weight_decay: 0.0500 (0.0500)  time: 1.0062  data: 0.0004  max mem: 78493
Epoch: [74]  [190/312]  eta: 0:02:13  lr: 0.003636  min_lr: 0.003636  loss: 2.6838 (2.5294)  weight_decay: 0.0500 (0.0500)  time: 1.0054  data: 0.0004  max mem: 78493
Epoch: [74]  [200/312]  eta: 0:02:01  lr: 0.003636  min_lr: 0.003636  loss: 2.5282 (2.5147)  weight_decay: 0.0500 (0.0500)  time: 1.0055  data: 0.0004  max mem: 78493
Epoch: [74]  [210/312]  eta: 0:01:50  lr: 0.003635  min_lr: 0.003635  loss: 2.4950 (2.5130)  weight_decay: 0.0500 (0.0500)  time: 1.0065  data: 0.0004  max mem: 78493
Epoch: [74]  [220/312]  eta: 0:01:39  lr: 0.003635  min_lr: 0.003635  loss: 2.6227 (2.5178)  weight_decay: 0.0500 (0.0500)  time: 1.0065  data: 0.0004  max mem: 78493
Epoch: [74]  [230/312]  eta: 0:01:28  lr: 0.003635  min_lr: 0.003635  loss: 2.6861 (2.5246)  weight_decay: 0.0500 (0.0500)  time: 1.0058  data: 0.0004  max mem: 78493
Epoch: [74]  [240/312]  eta: 0:01:17  lr: 0.003634  min_lr: 0.003634  loss: 2.7492 (2.5252)  weight_decay: 0.0500 (0.0500)  time: 1.0036  data: 0.0004  max mem: 78493
Epoch: [74]  [250/312]  eta: 0:01:06  lr: 0.003634  min_lr: 0.003634  loss: 2.5298 (2.5203)  weight_decay: 0.0500 (0.0500)  time: 1.0045  data: 0.0004  max mem: 78493
Epoch: [74]  [260/312]  eta: 0:00:55  lr: 0.003633  min_lr: 0.003633  loss: 2.6534 (2.5272)  weight_decay: 0.0500 (0.0500)  time: 1.0046  data: 0.0004  max mem: 78493
Epoch: [74]  [270/312]  eta: 0:00:44  lr: 0.003633  min_lr: 0.003633  loss: 2.5208 (2.5240)  weight_decay: 0.0500 (0.0500)  time: 1.0036  data: 0.0004  max mem: 78493
Epoch: [74]  [280/312]  eta: 0:00:34  lr: 0.003633  min_lr: 0.003633  loss: 2.6024 (2.5243)  weight_decay: 0.0500 (0.0500)  time: 1.0046  data: 0.0011  max mem: 78493
Epoch: [74]  [290/312]  eta: 0:00:23  lr: 0.003632  min_lr: 0.003632  loss: 2.6332 (2.5207)  weight_decay: 0.0500 (0.0500)  time: 1.0036  data: 0.0009  max mem: 78493
Epoch: [74]  [300/312]  eta: 0:00:12  lr: 0.003632  min_lr: 0.003632  loss: 2.5517 (2.5167)  weight_decay: 0.0500 (0.0500)  time: 1.0014  data: 0.0001  max mem: 78493
Epoch: [74]  [310/312]  eta: 0:00:02  lr: 0.003631  min_lr: 0.003631  loss: 2.3891 (2.5140)  weight_decay: 0.0500 (0.0500)  time: 1.0014  data: 0.0001  max mem: 78493
Epoch: [74]  [311/312]  eta: 0:00:01  lr: 0.003631  min_lr: 0.003631  loss: 2.1849 (2.5117)  weight_decay: 0.0500 (0.0500)  time: 1.0014  data: 0.0001  max mem: 78493
Epoch: [74] Total time: 0:05:32 (1.0647 s / it)
Averaged stats: lr: 0.003631  min_lr: 0.003631  loss: 2.1849 (2.5203)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:14  loss: 0.8760 (0.8760)  acc1: 79.6875 (79.6875)  acc5: 93.3594 (93.3594)  time: 8.3293  data: 8.0481  max mem: 78493
Test:  [8/9]  eta: 0:00:01  loss: 1.2289 (1.1082)  acc1: 71.7448 (72.6080)  acc5: 90.6250 (91.0720)  time: 1.1237  data: 0.8943  max mem: 78493
Test: Total time: 0:00:10 (1.1652 s / it)
* Acc@1 72.654 Acc@5 91.126 loss 1.094
Accuracy of the model on the 50000 test images: 72.7%
Max accuracy: 72.65%
Epoch: [75]  [  0/312]  eta: 1:20:44  lr: 0.003631  min_lr: 0.003631  loss: 2.6629 (2.6629)  weight_decay: 0.0500 (0.0500)  time: 15.5274  data: 14.4892  max mem: 78493
Epoch: [75]  [ 10/312]  eta: 0:13:08  lr: 0.003631  min_lr: 0.003631  loss: 2.3912 (2.3719)  weight_decay: 0.0500 (0.0500)  time: 2.6107  data: 1.3837  max mem: 78493
Epoch: [75]  [ 20/312]  eta: 0:09:00  lr: 0.003630  min_lr: 0.003630  loss: 2.2832 (2.3458)  weight_decay: 0.0500 (0.0500)  time: 1.1674  data: 0.0369  max mem: 78493
Epoch: [75]  [ 30/312]  eta: 0:07:25  lr: 0.003630  min_lr: 0.003630  loss: 2.4425 (2.3492)  weight_decay: 0.0500 (0.0500)  time: 1.0127  data: 0.0012  max mem: 78493
Epoch: [75]  [ 40/312]  eta: 0:06:31  lr: 0.003630  min_lr: 0.003630  loss: 2.4925 (2.3752)  weight_decay: 0.0500 (0.0500)  time: 1.0086  data: 0.0011  max mem: 78493
Epoch: [75]  [ 50/312]  eta: 0:05:55  lr: 0.003629  min_lr: 0.003629  loss: 2.4995 (2.4087)  weight_decay: 0.0500 (0.0500)  time: 1.0070  data: 0.0005  max mem: 78493
Epoch: [75]  [ 60/312]  eta: 0:05:27  lr: 0.003629  min_lr: 0.003629  loss: 2.6510 (2.4542)  weight_decay: 0.0500 (0.0500)  time: 1.0088  data: 0.0005  max mem: 78493
Epoch: [75]  [ 70/312]  eta: 0:05:04  lr: 0.003628  min_lr: 0.003628  loss: 2.7087 (2.4640)  weight_decay: 0.0500 (0.0500)  time: 1.0124  data: 0.0005  max mem: 78493
Epoch: [75]  [ 80/312]  eta: 0:04:44  lr: 0.003628  min_lr: 0.003628  loss: 2.5971 (2.4808)  weight_decay: 0.0500 (0.0500)  time: 1.0102  data: 0.0004  max mem: 78493
Epoch: [75]  [ 90/312]  eta: 0:04:27  lr: 0.003627  min_lr: 0.003627  loss: 2.5971 (2.4791)  weight_decay: 0.0500 (0.0500)  time: 1.0069  data: 0.0004  max mem: 78493
Epoch: [75]  [100/312]  eta: 0:04:11  lr: 0.003627  min_lr: 0.003627  loss: 2.4483 (2.4594)  weight_decay: 0.0500 (0.0500)  time: 1.0081  data: 0.0004  max mem: 78493
Epoch: [75]  [110/312]  eta: 0:03:55  lr: 0.003627  min_lr: 0.003627  loss: 2.1809 (2.4623)  weight_decay: 0.0500 (0.0500)  time: 1.0092  data: 0.0004  max mem: 78493
Epoch: [75]  [120/312]  eta: 0:03:41  lr: 0.003626  min_lr: 0.003626  loss: 2.5619 (2.4671)  weight_decay: 0.0500 (0.0500)  time: 1.0077  data: 0.0004  max mem: 78493
Epoch: [75]  [130/312]  eta: 0:03:28  lr: 0.003626  min_lr: 0.003626  loss: 2.5707 (2.4726)  weight_decay: 0.0500 (0.0500)  time: 1.0063  data: 0.0004  max mem: 78493
Epoch: [75]  [140/312]  eta: 0:03:14  lr: 0.003625  min_lr: 0.003625  loss: 2.6288 (2.4719)  weight_decay: 0.0500 (0.0500)  time: 1.0051  data: 0.0004  max mem: 78493
Epoch: [75]  [150/312]  eta: 0:03:02  lr: 0.003625  min_lr: 0.003625  loss: 2.5965 (2.4787)  weight_decay: 0.0500 (0.0500)  time: 1.0058  data: 0.0005  max mem: 78493
Epoch: [75]  [160/312]  eta: 0:02:49  lr: 0.003625  min_lr: 0.003625  loss: 2.5976 (2.4878)  weight_decay: 0.0500 (0.0500)  time: 1.0062  data: 0.0005  max mem: 78493
Epoch: [75]  [170/312]  eta: 0:02:37  lr: 0.003624  min_lr: 0.003624  loss: 2.6439 (2.4908)  weight_decay: 0.0500 (0.0500)  time: 1.0063  data: 0.0004  max mem: 78493
Epoch: [75]  [180/312]  eta: 0:02:25  lr: 0.003624  min_lr: 0.003624  loss: 2.6160 (2.5001)  weight_decay: 0.0500 (0.0500)  time: 1.0072  data: 0.0004  max mem: 78493
Epoch: [75]  [190/312]  eta: 0:02:14  lr: 0.003623  min_lr: 0.003623  loss: 2.6116 (2.5023)  weight_decay: 0.0500 (0.0500)  time: 1.0076  data: 0.0004  max mem: 78493
Epoch: [75]  [200/312]  eta: 0:02:02  lr: 0.003623  min_lr: 0.003623  loss: 2.6116 (2.5095)  weight_decay: 0.0500 (0.0500)  time: 1.0075  data: 0.0005  max mem: 78493
Epoch: [75]  [210/312]  eta: 0:01:51  lr: 0.003622  min_lr: 0.003622  loss: 2.7558 (2.5215)  weight_decay: 0.0500 (0.0500)  time: 1.0050  data: 0.0005  max mem: 78493
Epoch: [75]  [220/312]  eta: 0:01:40  lr: 0.003622  min_lr: 0.003622  loss: 2.7420 (2.5245)  weight_decay: 0.0500 (0.0500)  time: 1.0063  data: 0.0005  max mem: 78493
Epoch: [75]  [230/312]  eta: 0:01:28  lr: 0.003622  min_lr: 0.003622  loss: 2.5847 (2.5227)  weight_decay: 0.0500 (0.0500)  time: 1.0073  data: 0.0005  max mem: 78493
Epoch: [75]  [240/312]  eta: 0:01:17  lr: 0.003621  min_lr: 0.003621  loss: 2.5223 (2.5244)  weight_decay: 0.0500 (0.0500)  time: 1.0059  data: 0.0004  max mem: 78493
Epoch: [75]  [250/312]  eta: 0:01:06  lr: 0.003621  min_lr: 0.003621  loss: 2.4678 (2.5182)  weight_decay: 0.0500 (0.0500)  time: 1.0077  data: 0.0004  max mem: 78493
Epoch: [75]  [260/312]  eta: 0:00:55  lr: 0.003620  min_lr: 0.003620  loss: 2.4287 (2.5160)  weight_decay: 0.0500 (0.0500)  time: 1.0086  data: 0.0016  max mem: 78493
Epoch: [75]  [270/312]  eta: 0:00:45  lr: 0.003620  min_lr: 0.003620  loss: 2.6281 (2.5194)  weight_decay: 0.0500 (0.0500)  time: 1.0063  data: 0.0016  max mem: 78493
Epoch: [75]  [280/312]  eta: 0:00:34  lr: 0.003619  min_lr: 0.003619  loss: 2.7767 (2.5271)  weight_decay: 0.0500 (0.0500)  time: 1.0071  data: 0.0021  max mem: 78493
Epoch: [75]  [290/312]  eta: 0:00:23  lr: 0.003619  min_lr: 0.003619  loss: 2.7692 (2.5249)  weight_decay: 0.0500 (0.0500)  time: 1.0056  data: 0.0019  max mem: 78493
Epoch: [75]  [300/312]  eta: 0:00:12  lr: 0.003619  min_lr: 0.003619  loss: 2.4961 (2.5249)  weight_decay: 0.0500 (0.0500)  time: 1.0016  data: 0.0001  max mem: 78493
Epoch: [75]  [310/312]  eta: 0:00:02  lr: 0.003618  min_lr: 0.003618  loss: 2.4961 (2.5221)  weight_decay: 0.0500 (0.0500)  time: 1.0017  data: 0.0001  max mem: 78493
Epoch: [75]  [311/312]  eta: 0:00:01  lr: 0.003618  min_lr: 0.003618  loss: 2.4961 (2.5225)  weight_decay: 0.0500 (0.0500)  time: 1.0018  data: 0.0001  max mem: 78493
Epoch: [75] Total time: 0:05:33 (1.0696 s / it)
Averaged stats: lr: 0.003618  min_lr: 0.003618  loss: 2.4961 (2.5158)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:11  loss: 0.9295 (0.9295)  acc1: 78.9062 (78.9062)  acc5: 92.7083 (92.7083)  time: 7.9422  data: 7.6789  max mem: 78493
Test:  [8/9]  eta: 0:00:01  loss: 1.1900 (1.1130)  acc1: 72.0052 (72.0320)  acc5: 90.4948 (90.6560)  time: 1.0856  data: 0.8533  max mem: 78493
Test: Total time: 0:00:09 (1.1048 s / it)
* Acc@1 71.762 Acc@5 90.504 loss 1.121
Accuracy of the model on the 50000 test images: 71.8%
Max accuracy: 72.65%
Epoch: [76]  [  0/312]  eta: 1:25:04  lr: 0.003618  min_lr: 0.003618  loss: 2.5936 (2.5936)  weight_decay: 0.0500 (0.0500)  time: 16.3606  data: 12.4154  max mem: 78493
Epoch: [76]  [ 10/312]  eta: 0:13:21  lr: 0.003618  min_lr: 0.003618  loss: 2.8026 (2.6005)  weight_decay: 0.0500 (0.0500)  time: 2.6552  data: 1.2714  max mem: 78493
Epoch: [76]  [ 20/312]  eta: 0:09:08  lr: 0.003617  min_lr: 0.003617  loss: 2.5941 (2.4987)  weight_decay: 0.0500 (0.0500)  time: 1.1532  data: 0.0799  max mem: 78493
Epoch: [76]  [ 30/312]  eta: 0:07:30  lr: 0.003617  min_lr: 0.003617  loss: 2.4515 (2.4965)  weight_decay: 0.0500 (0.0500)  time: 1.0136  data: 0.0016  max mem: 78493
Epoch: [76]  [ 40/312]  eta: 0:06:34  lr: 0.003616  min_lr: 0.003616  loss: 2.4701 (2.4920)  weight_decay: 0.0500 (0.0500)  time: 1.0047  data: 0.0004  max mem: 78493
Epoch: [76]  [ 50/312]  eta: 0:05:57  lr: 0.003616  min_lr: 0.003616  loss: 2.5703 (2.4879)  weight_decay: 0.0500 (0.0500)  time: 1.0066  data: 0.0004  max mem: 78493
Epoch: [76]  [ 60/312]  eta: 0:05:29  lr: 0.003616  min_lr: 0.003616  loss: 2.5830 (2.4951)  weight_decay: 0.0500 (0.0500)  time: 1.0093  data: 0.0004  max mem: 78493
Epoch: [76]  [ 70/312]  eta: 0:05:05  lr: 0.003615  min_lr: 0.003615  loss: 2.4221 (2.4788)  weight_decay: 0.0500 (0.0500)  time: 1.0074  data: 0.0004  max mem: 78493
Epoch: [76]  [ 80/312]  eta: 0:04:45  lr: 0.003615  min_lr: 0.003615  loss: 2.3252 (2.4594)  weight_decay: 0.0500 (0.0500)  time: 1.0070  data: 0.0004  max mem: 78493
Epoch: [76]  [ 90/312]  eta: 0:04:28  lr: 0.003614  min_lr: 0.003614  loss: 2.4787 (2.4574)  weight_decay: 0.0500 (0.0500)  time: 1.0067  data: 0.0004  max mem: 78493
Epoch: [76]  [100/312]  eta: 0:04:11  lr: 0.003614  min_lr: 0.003614  loss: 2.4787 (2.4607)  weight_decay: 0.0500 (0.0500)  time: 1.0040  data: 0.0004  max mem: 78493
Epoch: [76]  [110/312]  eta: 0:03:56  lr: 0.003613  min_lr: 0.003613  loss: 2.4655 (2.4608)  weight_decay: 0.0500 (0.0500)  time: 1.0046  data: 0.0005  max mem: 78493
Epoch: [76]  [120/312]  eta: 0:03:42  lr: 0.003613  min_lr: 0.003613  loss: 2.6032 (2.4718)  weight_decay: 0.0500 (0.0500)  time: 1.0054  data: 0.0004  max mem: 78493
Epoch: [76]  [130/312]  eta: 0:03:28  lr: 0.003613  min_lr: 0.003613  loss: 2.6359 (2.4733)  weight_decay: 0.0500 (0.0500)  time: 1.0065  data: 0.0005  max mem: 78493
Epoch: [76]  [140/312]  eta: 0:03:15  lr: 0.003612  min_lr: 0.003612  loss: 2.3522 (2.4613)  weight_decay: 0.0500 (0.0500)  time: 1.0073  data: 0.0005  max mem: 78493
Epoch: [76]  [150/312]  eta: 0:03:02  lr: 0.003612  min_lr: 0.003612  loss: 2.5011 (2.4782)  weight_decay: 0.0500 (0.0500)  time: 1.0057  data: 0.0011  max mem: 78493
Epoch: [76]  [160/312]  eta: 0:02:50  lr: 0.003611  min_lr: 0.003611  loss: 2.7376 (2.4903)  weight_decay: 0.0500 (0.0500)  time: 1.0054  data: 0.0011  max mem: 78493
Epoch: [76]  [170/312]  eta: 0:02:38  lr: 0.003611  min_lr: 0.003611  loss: 2.6476 (2.4867)  weight_decay: 0.0500 (0.0500)  time: 1.0057  data: 0.0004  max mem: 78493
Epoch: [76]  [180/312]  eta: 0:02:26  lr: 0.003610  min_lr: 0.003610  loss: 2.6244 (2.4923)  weight_decay: 0.0500 (0.0500)  time: 1.0062  data: 0.0005  max mem: 78493
Epoch: [76]  [190/312]  eta: 0:02:14  lr: 0.003610  min_lr: 0.003610  loss: 2.6244 (2.4928)  weight_decay: 0.0500 (0.0500)  time: 1.0084  data: 0.0005  max mem: 78493
Epoch: [76]  [200/312]  eta: 0:02:02  lr: 0.003610  min_lr: 0.003610  loss: 2.5127 (2.4877)  weight_decay: 0.0500 (0.0500)  time: 1.0083  data: 0.0005  max mem: 78493
Epoch: [76]  [210/312]  eta: 0:01:51  lr: 0.003609  min_lr: 0.003609  loss: 2.5127 (2.4921)  weight_decay: 0.0500 (0.0500)  time: 1.0055  data: 0.0004  max mem: 78493
Epoch: [76]  [220/312]  eta: 0:01:40  lr: 0.003609  min_lr: 0.003609  loss: 2.5093 (2.4942)  weight_decay: 0.0500 (0.0500)  time: 1.0043  data: 0.0004  max mem: 78493
Epoch: [76]  [230/312]  eta: 0:01:29  lr: 0.003608  min_lr: 0.003608  loss: 2.5093 (2.4951)  weight_decay: 0.0500 (0.0500)  time: 1.0049  data: 0.0004  max mem: 78493
Epoch: [76]  [240/312]  eta: 0:01:17  lr: 0.003608  min_lr: 0.003608  loss: 2.5326 (2.4954)  weight_decay: 0.0500 (0.0500)  time: 1.0059  data: 0.0004  max mem: 78493
Epoch: [76]  [250/312]  eta: 0:01:06  lr: 0.003607  min_lr: 0.003607  loss: 2.6954 (2.5028)  weight_decay: 0.0500 (0.0500)  time: 1.0067  data: 0.0011  max mem: 78493
Epoch: [76]  [260/312]  eta: 0:00:55  lr: 0.003607  min_lr: 0.003607  loss: 2.7260 (2.5030)  weight_decay: 0.0500 (0.0500)  time: 1.0066  data: 0.0011  max mem: 78493
Epoch: [76]  [270/312]  eta: 0:00:45  lr: 0.003607  min_lr: 0.003607  loss: 2.7260 (2.5079)  weight_decay: 0.0500 (0.0500)  time: 1.0054  data: 0.0004  max mem: 78493
Epoch: [76]  [280/312]  eta: 0:00:34  lr: 0.003606  min_lr: 0.003606  loss: 2.6223 (2.5067)  weight_decay: 0.0500 (0.0500)  time: 1.0069  data: 0.0010  max mem: 78493
Epoch: [76]  [290/312]  eta: 0:00:23  lr: 0.003606  min_lr: 0.003606  loss: 2.5597 (2.5074)  weight_decay: 0.0500 (0.0500)  time: 1.0053  data: 0.0009  max mem: 78493
Epoch: [76]  [300/312]  eta: 0:00:12  lr: 0.003605  min_lr: 0.003605  loss: 2.6644 (2.5141)  weight_decay: 0.0500 (0.0500)  time: 1.0016  data: 0.0001  max mem: 78493
Epoch: [76]  [310/312]  eta: 0:00:02  lr: 0.003605  min_lr: 0.003605  loss: 2.6312 (2.5083)  weight_decay: 0.0500 (0.0500)  time: 1.0018  data: 0.0001  max mem: 78493
Epoch: [76]  [311/312]  eta: 0:00:01  lr: 0.003605  min_lr: 0.003605  loss: 2.6391 (2.5105)  weight_decay: 0.0500 (0.0500)  time: 1.0018  data: 0.0001  max mem: 78493
Epoch: [76] Total time: 0:05:33 (1.0703 s / it)
Averaged stats: lr: 0.003605  min_lr: 0.003605  loss: 2.6391 (2.5176)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:17  loss: 0.8311 (0.8311)  acc1: 80.5990 (80.5990)  acc5: 93.7500 (93.7500)  time: 8.5749  data: 8.3015  max mem: 78493
Test:  [8/9]  eta: 0:00:01  loss: 1.2021 (1.0647)  acc1: 70.8333 (73.0720)  acc5: 91.0156 (90.7200)  time: 1.1508  data: 0.9225  max mem: 78493
Test: Total time: 0:00:10 (1.1742 s / it)
* Acc@1 72.816 Acc@5 91.054 loss 1.068
Accuracy of the model on the 50000 test images: 72.8%
Max accuracy: 72.82%
Epoch: [77]  [  0/312]  eta: 1:23:08  lr: 0.003605  min_lr: 0.003605  loss: 2.8664 (2.8664)  weight_decay: 0.0500 (0.0500)  time: 15.9873  data: 14.9867  max mem: 78493
Epoch: [77]  [ 10/312]  eta: 0:13:08  lr: 0.003604  min_lr: 0.003604  loss: 2.1676 (2.2495)  weight_decay: 0.0500 (0.0500)  time: 2.6097  data: 1.3948  max mem: 78493
Epoch: [77]  [ 20/312]  eta: 0:08:59  lr: 0.003604  min_lr: 0.003604  loss: 2.2931 (2.3608)  weight_decay: 0.0500 (0.0500)  time: 1.1391  data: 0.0180  max mem: 78493
Epoch: [77]  [ 30/312]  eta: 0:07:24  lr: 0.003604  min_lr: 0.003604  loss: 2.5684 (2.4419)  weight_decay: 0.0500 (0.0500)  time: 1.0063  data: 0.0004  max mem: 78493
Epoch: [77]  [ 40/312]  eta: 0:06:30  lr: 0.003603  min_lr: 0.003603  loss: 2.6024 (2.4221)  weight_decay: 0.0500 (0.0500)  time: 1.0075  data: 0.0004  max mem: 78493
Epoch: [77]  [ 50/312]  eta: 0:05:54  lr: 0.003603  min_lr: 0.003603  loss: 2.4152 (2.4290)  weight_decay: 0.0500 (0.0500)  time: 1.0098  data: 0.0004  max mem: 78493
Epoch: [77]  [ 60/312]  eta: 0:05:26  lr: 0.003602  min_lr: 0.003602  loss: 2.4257 (2.4261)  weight_decay: 0.0500 (0.0500)  time: 1.0109  data: 0.0004  max mem: 78493
Epoch: [77]  [ 70/312]  eta: 0:05:04  lr: 0.003602  min_lr: 0.003602  loss: 2.6440 (2.4774)  weight_decay: 0.0500 (0.0500)  time: 1.0099  data: 0.0004  max mem: 78493
Epoch: [77]  [ 80/312]  eta: 0:04:44  lr: 0.003601  min_lr: 0.003601  loss: 2.7041 (2.4810)  weight_decay: 0.0500 (0.0500)  time: 1.0087  data: 0.0004  max mem: 78493
Epoch: [77]  [ 90/312]  eta: 0:04:26  lr: 0.003601  min_lr: 0.003601  loss: 2.5534 (2.4828)  weight_decay: 0.0500 (0.0500)  time: 1.0083  data: 0.0004  max mem: 78493
Epoch: [77]  [100/312]  eta: 0:04:10  lr: 0.003601  min_lr: 0.003601  loss: 2.5219 (2.4671)  weight_decay: 0.0500 (0.0500)  time: 1.0088  data: 0.0004  max mem: 78493
Epoch: [77]  [110/312]  eta: 0:03:55  lr: 0.003600  min_lr: 0.003600  loss: 2.5218 (2.4712)  weight_decay: 0.0500 (0.0500)  time: 1.0062  data: 0.0004  max mem: 78493
Epoch: [77]  [120/312]  eta: 0:03:41  lr: 0.003600  min_lr: 0.003600  loss: 2.6015 (2.4874)  weight_decay: 0.0500 (0.0500)  time: 1.0056  data: 0.0005  max mem: 78493
Epoch: [77]  [130/312]  eta: 0:03:27  lr: 0.003599  min_lr: 0.003599  loss: 2.6274 (2.4890)  weight_decay: 0.0500 (0.0500)  time: 1.0070  data: 0.0004  max mem: 78493
Epoch: [77]  [140/312]  eta: 0:03:14  lr: 0.003599  min_lr: 0.003599  loss: 2.7313 (2.5127)  weight_decay: 0.0500 (0.0500)  time: 1.0059  data: 0.0004  max mem: 78493
Epoch: [77]  [150/312]  eta: 0:03:02  lr: 0.003598  min_lr: 0.003598  loss: 2.6523 (2.5001)  weight_decay: 0.0500 (0.0500)  time: 1.0048  data: 0.0004  max mem: 78493
Epoch: [77]  [160/312]  eta: 0:02:49  lr: 0.003598  min_lr: 0.003598  loss: 2.4932 (2.5088)  weight_decay: 0.0500 (0.0500)  time: 1.0053  data: 0.0004  max mem: 78493
Epoch: [77]  [170/312]  eta: 0:02:37  lr: 0.003598  min_lr: 0.003598  loss: 2.6320 (2.5092)  weight_decay: 0.0500 (0.0500)  time: 1.0057  data: 0.0005  max mem: 78493
Epoch: [77]  [180/312]  eta: 0:02:25  lr: 0.003597  min_lr: 0.003597  loss: 2.6555 (2.5120)  weight_decay: 0.0500 (0.0500)  time: 1.0054  data: 0.0005  max mem: 78493
Epoch: [77]  [190/312]  eta: 0:02:14  lr: 0.003597  min_lr: 0.003597  loss: 2.6658 (2.5125)  weight_decay: 0.0500 (0.0500)  time: 1.0059  data: 0.0004  max mem: 78493
Epoch: [77]  [200/312]  eta: 0:02:02  lr: 0.003596  min_lr: 0.003596  loss: 2.5213 (2.5107)  weight_decay: 0.0500 (0.0500)  time: 1.0057  data: 0.0005  max mem: 78493
Epoch: [77]  [210/312]  eta: 0:01:51  lr: 0.003596  min_lr: 0.003596  loss: 2.5328 (2.5002)  weight_decay: 0.0500 (0.0500)  time: 1.0056  data: 0.0005  max mem: 78493
Epoch: [77]  [220/312]  eta: 0:01:39  lr: 0.003595  min_lr: 0.003595  loss: 2.5328 (2.4997)  weight_decay: 0.0500 (0.0500)  time: 1.0050  data: 0.0004  max mem: 78493
Epoch: [77]  [230/312]  eta: 0:01:28  lr: 0.003595  min_lr: 0.003595  loss: 2.5945 (2.4991)  weight_decay: 0.0500 (0.0500)  time: 1.0050  data: 0.0004  max mem: 78493
Epoch: [77]  [240/312]  eta: 0:01:17  lr: 0.003594  min_lr: 0.003594  loss: 2.6069 (2.5031)  weight_decay: 0.0500 (0.0500)  time: 1.0049  data: 0.0004  max mem: 78493
Epoch: [77]  [250/312]  eta: 0:01:06  lr: 0.003594  min_lr: 0.003594  loss: 2.5445 (2.5053)  weight_decay: 0.0500 (0.0500)  time: 1.0041  data: 0.0004  max mem: 78493
Epoch: [77]  [260/312]  eta: 0:00:55  lr: 0.003594  min_lr: 0.003594  loss: 2.5445 (2.5047)  weight_decay: 0.0500 (0.0500)  time: 1.0046  data: 0.0005  max mem: 78493
Epoch: [77]  [270/312]  eta: 0:00:45  lr: 0.003593  min_lr: 0.003593  loss: 2.4874 (2.5011)  weight_decay: 0.0500 (0.0500)  time: 1.0051  data: 0.0005  max mem: 78493
Epoch: [77]  [280/312]  eta: 0:00:34  lr: 0.003593  min_lr: 0.003593  loss: 2.5345 (2.5085)  weight_decay: 0.0500 (0.0500)  time: 1.0065  data: 0.0010  max mem: 78493
Epoch: [77]  [290/312]  eta: 0:00:23  lr: 0.003592  min_lr: 0.003592  loss: 2.6822 (2.5116)  weight_decay: 0.0500 (0.0500)  time: 1.0047  data: 0.0009  max mem: 78493
Epoch: [77]  [300/312]  eta: 0:00:12  lr: 0.003592  min_lr: 0.003592  loss: 2.6667 (2.5150)  weight_decay: 0.0500 (0.0500)  time: 1.0018  data: 0.0001  max mem: 78493
Epoch: [77]  [310/312]  eta: 0:00:02  lr: 0.003591  min_lr: 0.003591  loss: 2.4878 (2.5120)  weight_decay: 0.0500 (0.0500)  time: 1.0020  data: 0.0001  max mem: 78493
Epoch: [77]  [311/312]  eta: 0:00:01  lr: 0.003591  min_lr: 0.003591  loss: 2.5383 (2.5127)  weight_decay: 0.0500 (0.0500)  time: 1.0019  data: 0.0001  max mem: 78493
Epoch: [77] Total time: 0:05:33 (1.0682 s / it)
Averaged stats: lr: 0.003591  min_lr: 0.003591  loss: 2.5383 (2.5111)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:13  loss: 0.9392 (0.9392)  acc1: 77.2135 (77.2135)  acc5: 92.9688 (92.9688)  time: 8.1576  data: 7.8602  max mem: 78493
Test:  [8/9]  eta: 0:00:01  loss: 1.2092 (1.0960)  acc1: 71.8750 (71.7600)  acc5: 90.3646 (90.8640)  time: 1.1046  data: 0.8734  max mem: 78493
Test: Total time: 0:00:10 (1.1454 s / it)
* Acc@1 72.262 Acc@5 90.968 loss 1.102
Accuracy of the model on the 50000 test images: 72.3%
Max accuracy: 72.82%
Epoch: [78]  [  0/312]  eta: 1:29:06  lr: 0.003591  min_lr: 0.003591  loss: 1.6939 (1.6939)  weight_decay: 0.0500 (0.0500)  time: 17.1365  data: 13.0273  max mem: 78493
Epoch: [78]  [ 10/312]  eta: 0:13:20  lr: 0.003591  min_lr: 0.003591  loss: 2.5749 (2.4802)  weight_decay: 0.0500 (0.0500)  time: 2.6503  data: 1.1896  max mem: 78493
Epoch: [78]  [ 20/312]  eta: 0:09:08  lr: 0.003590  min_lr: 0.003590  loss: 2.5272 (2.4056)  weight_decay: 0.0500 (0.0500)  time: 1.1142  data: 0.0032  max mem: 78493
Epoch: [78]  [ 30/312]  eta: 0:07:30  lr: 0.003590  min_lr: 0.003590  loss: 2.4831 (2.4439)  weight_decay: 0.0500 (0.0500)  time: 1.0183  data: 0.0005  max mem: 78493
Epoch: [78]  [ 40/312]  eta: 0:06:35  lr: 0.003590  min_lr: 0.003590  loss: 2.4544 (2.4522)  weight_decay: 0.0500 (0.0500)  time: 1.0092  data: 0.0004  max mem: 78493
Epoch: [78]  [ 50/312]  eta: 0:05:57  lr: 0.003589  min_lr: 0.003589  loss: 2.2054 (2.4061)  weight_decay: 0.0500 (0.0500)  time: 1.0074  data: 0.0004  max mem: 78493
Epoch: [78]  [ 60/312]  eta: 0:05:29  lr: 0.003589  min_lr: 0.003589  loss: 2.3325 (2.4336)  weight_decay: 0.0500 (0.0500)  time: 1.0070  data: 0.0004  max mem: 78493
Epoch: [78]  [ 70/312]  eta: 0:05:06  lr: 0.003588  min_lr: 0.003588  loss: 2.5928 (2.4422)  weight_decay: 0.0500 (0.0500)  time: 1.0083  data: 0.0004  max mem: 78493
Epoch: [78]  [ 80/312]  eta: 0:04:46  lr: 0.003588  min_lr: 0.003588  loss: 2.5928 (2.4577)  weight_decay: 0.0500 (0.0500)  time: 1.0096  data: 0.0004  max mem: 78493
Epoch: [78]  [ 90/312]  eta: 0:04:28  lr: 0.003587  min_lr: 0.003587  loss: 2.4554 (2.4496)  weight_decay: 0.0500 (0.0500)  time: 1.0101  data: 0.0005  max mem: 78493
Epoch: [78]  [100/312]  eta: 0:04:12  lr: 0.003587  min_lr: 0.003587  loss: 2.4250 (2.4437)  weight_decay: 0.0500 (0.0500)  time: 1.0105  data: 0.0005  max mem: 78493
Epoch: [78]  [110/312]  eta: 0:03:57  lr: 0.003587  min_lr: 0.003587  loss: 2.4232 (2.4341)  weight_decay: 0.0500 (0.0500)  time: 1.0101  data: 0.0005  max mem: 78493
Epoch: [78]  [120/312]  eta: 0:03:42  lr: 0.003586  min_lr: 0.003586  loss: 2.0911 (2.4243)  weight_decay: 0.0500 (0.0500)  time: 1.0081  data: 0.0005  max mem: 78493
Epoch: [78]  [130/312]  eta: 0:03:28  lr: 0.003586  min_lr: 0.003586  loss: 2.3381 (2.4301)  weight_decay: 0.0500 (0.0500)  time: 1.0066  data: 0.0004  max mem: 78493
Epoch: [78]  [140/312]  eta: 0:03:15  lr: 0.003585  min_lr: 0.003585  loss: 2.6324 (2.4459)  weight_decay: 0.0500 (0.0500)  time: 1.0059  data: 0.0004  max mem: 78493
Epoch: [78]  [150/312]  eta: 0:03:02  lr: 0.003585  min_lr: 0.003585  loss: 2.6324 (2.4496)  weight_decay: 0.0500 (0.0500)  time: 1.0057  data: 0.0004  max mem: 78493
Epoch: [78]  [160/312]  eta: 0:02:50  lr: 0.003584  min_lr: 0.003584  loss: 2.5347 (2.4543)  weight_decay: 0.0500 (0.0500)  time: 1.0065  data: 0.0004  max mem: 78493
Epoch: [78]  [170/312]  eta: 0:02:38  lr: 0.003584  min_lr: 0.003584  loss: 2.5656 (2.4564)  weight_decay: 0.0500 (0.0500)  time: 1.0072  data: 0.0004  max mem: 78493
Epoch: [78]  [180/312]  eta: 0:02:26  lr: 0.003583  min_lr: 0.003583  loss: 2.6345 (2.4597)  weight_decay: 0.0500 (0.0500)  time: 1.0103  data: 0.0005  max mem: 78493
Epoch: [78]  [190/312]  eta: 0:02:14  lr: 0.003583  min_lr: 0.003583  loss: 2.5692 (2.4618)  weight_decay: 0.0500 (0.0500)  time: 1.0117  data: 0.0004  max mem: 78493
Epoch: [78]  [200/312]  eta: 0:02:03  lr: 0.003583  min_lr: 0.003583  loss: 2.6591 (2.4715)  weight_decay: 0.0500 (0.0500)  time: 1.0095  data: 0.0004  max mem: 78493
Epoch: [78]  [210/312]  eta: 0:01:51  lr: 0.003582  min_lr: 0.003582  loss: 2.6831 (2.4777)  weight_decay: 0.0500 (0.0500)  time: 1.0074  data: 0.0005  max mem: 78493
Epoch: [78]  [220/312]  eta: 0:01:40  lr: 0.003582  min_lr: 0.003582  loss: 2.5844 (2.4788)  weight_decay: 0.0500 (0.0500)  time: 1.0052  data: 0.0005  max mem: 78493
Epoch: [78]  [230/312]  eta: 0:01:29  lr: 0.003581  min_lr: 0.003581  loss: 2.4279 (2.4798)  weight_decay: 0.0500 (0.0500)  time: 1.0047  data: 0.0005  max mem: 78493
Epoch: [78]  [240/312]  eta: 0:01:18  lr: 0.003581  min_lr: 0.003581  loss: 2.7273 (2.4881)  weight_decay: 0.0500 (0.0500)  time: 1.0054  data: 0.0005  max mem: 78493
Epoch: [78]  [250/312]  eta: 0:01:06  lr: 0.003580  min_lr: 0.003580  loss: 2.6618 (2.4853)  weight_decay: 0.0500 (0.0500)  time: 1.0058  data: 0.0004  max mem: 78493
Epoch: [78]  [260/312]  eta: 0:00:56  lr: 0.003580  min_lr: 0.003580  loss: 2.5857 (2.4903)  weight_decay: 0.0500 (0.0500)  time: 1.0050  data: 0.0004  max mem: 78493
Epoch: [78]  [270/312]  eta: 0:00:45  lr: 0.003580  min_lr: 0.003580  loss: 2.5094 (2.4848)  weight_decay: 0.0500 (0.0500)  time: 1.0047  data: 0.0004  max mem: 78493
Epoch: [78]  [280/312]  eta: 0:00:34  lr: 0.003579  min_lr: 0.003579  loss: 2.3611 (2.4811)  weight_decay: 0.0500 (0.0500)  time: 1.0059  data: 0.0010  max mem: 78493
Epoch: [78]  [290/312]  eta: 0:00:23  lr: 0.003579  min_lr: 0.003579  loss: 2.6000 (2.4892)  weight_decay: 0.0500 (0.0500)  time: 1.0043  data: 0.0009  max mem: 78493
Epoch: [78]  [300/312]  eta: 0:00:12  lr: 0.003578  min_lr: 0.003578  loss: 2.6768 (2.4920)  weight_decay: 0.0500 (0.0500)  time: 1.0016  data: 0.0001  max mem: 78493
Epoch: [78]  [310/312]  eta: 0:00:02  lr: 0.003578  min_lr: 0.003578  loss: 2.5299 (2.4931)  weight_decay: 0.0500 (0.0500)  time: 1.0015  data: 0.0001  max mem: 78493
Epoch: [78]  [311/312]  eta: 0:00:01  lr: 0.003578  min_lr: 0.003578  loss: 2.5299 (2.4944)  weight_decay: 0.0500 (0.0500)  time: 1.0014  data: 0.0001  max mem: 78493
Epoch: [78] Total time: 0:05:34 (1.0713 s / it)
Averaged stats: lr: 0.003578  min_lr: 0.003578  loss: 2.5299 (2.5006)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:15  loss: 0.8398 (0.8398)  acc1: 79.5573 (79.5573)  acc5: 93.6198 (93.6198)  time: 8.3873  data: 8.1095  max mem: 78493
Test:  [8/9]  eta: 0:00:01  loss: 1.2170 (1.1052)  acc1: 72.6562 (72.3840)  acc5: 90.3646 (90.5760)  time: 1.1302  data: 0.9011  max mem: 78493
Test: Total time: 0:00:10 (1.1465 s / it)
* Acc@1 72.244 Acc@5 90.806 loss 1.102
Accuracy of the model on the 50000 test images: 72.2%
Max accuracy: 72.82%
Epoch: [79]  [  0/312]  eta: 1:25:20  lr: 0.003578  min_lr: 0.003578  loss: 2.1513 (2.1513)  weight_decay: 0.0500 (0.0500)  time: 16.4124  data: 15.2655  max mem: 78493
Epoch: [79]  [ 10/312]  eta: 0:13:21  lr: 0.003577  min_lr: 0.003577  loss: 2.9695 (2.6339)  weight_decay: 0.0500 (0.0500)  time: 2.6556  data: 1.3883  max mem: 78493
Epoch: [79]  [ 20/312]  eta: 0:09:07  lr: 0.003577  min_lr: 0.003577  loss: 2.7204 (2.6018)  weight_decay: 0.0500 (0.0500)  time: 1.1466  data: 0.0005  max mem: 78493
Epoch: [79]  [ 30/312]  eta: 0:07:29  lr: 0.003576  min_lr: 0.003576  loss: 2.5616 (2.5452)  weight_decay: 0.0500 (0.0500)  time: 1.0086  data: 0.0004  max mem: 78493
Epoch: [79]  [ 40/312]  eta: 0:06:34  lr: 0.003576  min_lr: 0.003576  loss: 2.4397 (2.5418)  weight_decay: 0.0500 (0.0500)  time: 1.0059  data: 0.0004  max mem: 78493
Epoch: [79]  [ 50/312]  eta: 0:05:57  lr: 0.003575  min_lr: 0.003575  loss: 2.6106 (2.5509)  weight_decay: 0.0500 (0.0500)  time: 1.0060  data: 0.0004  max mem: 78493
Epoch: [79]  [ 60/312]  eta: 0:05:28  lr: 0.003575  min_lr: 0.003575  loss: 2.5871 (2.5298)  weight_decay: 0.0500 (0.0500)  time: 1.0052  data: 0.0005  max mem: 78493
Epoch: [79]  [ 70/312]  eta: 0:05:05  lr: 0.003575  min_lr: 0.003575  loss: 2.5871 (2.5334)  weight_decay: 0.0500 (0.0500)  time: 1.0070  data: 0.0005  max mem: 78493
Epoch: [79]  [ 80/312]  eta: 0:04:45  lr: 0.003574  min_lr: 0.003574  loss: 2.6344 (2.5330)  weight_decay: 0.0500 (0.0500)  time: 1.0085  data: 0.0005  max mem: 78493
Epoch: [79]  [ 90/312]  eta: 0:04:27  lr: 0.003574  min_lr: 0.003574  loss: 2.7243 (2.5637)  weight_decay: 0.0500 (0.0500)  time: 1.0075  data: 0.0004  max mem: 78493
Epoch: [79]  [100/312]  eta: 0:04:11  lr: 0.003573  min_lr: 0.003573  loss: 2.7514 (2.5782)  weight_decay: 0.0500 (0.0500)  time: 1.0058  data: 0.0004  max mem: 78493
Epoch: [79]  [110/312]  eta: 0:03:56  lr: 0.003573  min_lr: 0.003573  loss: 2.7369 (2.5799)  weight_decay: 0.0500 (0.0500)  time: 1.0075  data: 0.0004  max mem: 78493
Epoch: [79]  [120/312]  eta: 0:03:42  lr: 0.003572  min_lr: 0.003572  loss: 2.5769 (2.5717)  weight_decay: 0.0500 (0.0500)  time: 1.0094  data: 0.0004  max mem: 78493
Epoch: [79]  [130/312]  eta: 0:03:28  lr: 0.003572  min_lr: 0.003572  loss: 2.6128 (2.5776)  weight_decay: 0.0500 (0.0500)  time: 1.0095  data: 0.0015  max mem: 78493
Epoch: [79]  [140/312]  eta: 0:03:15  lr: 0.003571  min_lr: 0.003571  loss: 2.2017 (2.5401)  weight_decay: 0.0500 (0.0500)  time: 1.0096  data: 0.0015  max mem: 78493
Epoch: [79]  [150/312]  eta: 0:03:02  lr: 0.003571  min_lr: 0.003571  loss: 2.1745 (2.5349)  weight_decay: 0.0500 (0.0500)  time: 1.0089  data: 0.0004  max mem: 78493
Epoch: [79]  [160/312]  eta: 0:02:50  lr: 0.003571  min_lr: 0.003571  loss: 2.4441 (2.5262)  weight_decay: 0.0500 (0.0500)  time: 1.0100  data: 0.0005  max mem: 78493
Epoch: [79]  [170/312]  eta: 0:02:38  lr: 0.003570  min_lr: 0.003570  loss: 2.5606 (2.5286)  weight_decay: 0.0500 (0.0500)  time: 1.0113  data: 0.0005  max mem: 78493
Epoch: [79]  [180/312]  eta: 0:02:26  lr: 0.003570  min_lr: 0.003570  loss: 2.5751 (2.5236)  weight_decay: 0.0500 (0.0500)  time: 1.0094  data: 0.0004  max mem: 78493
Epoch: [79]  [190/312]  eta: 0:02:14  lr: 0.003569  min_lr: 0.003569  loss: 2.3843 (2.5188)  weight_decay: 0.0500 (0.0500)  time: 1.0071  data: 0.0004  max mem: 78493
Epoch: [79]  [200/312]  eta: 0:02:03  lr: 0.003569  min_lr: 0.003569  loss: 2.5277 (2.5176)  weight_decay: 0.0500 (0.0500)  time: 1.0065  data: 0.0004  max mem: 78493
Epoch: [79]  [210/312]  eta: 0:01:51  lr: 0.003568  min_lr: 0.003568  loss: 2.5846 (2.5232)  weight_decay: 0.0500 (0.0500)  time: 1.0071  data: 0.0004  max mem: 78493
Epoch: [79]  [220/312]  eta: 0:01:40  lr: 0.003568  min_lr: 0.003568  loss: 2.6930 (2.5278)  weight_decay: 0.0500 (0.0500)  time: 1.0066  data: 0.0005  max mem: 78493
Epoch: [79]  [230/312]  eta: 0:01:29  lr: 0.003567  min_lr: 0.003567  loss: 2.6704 (2.5243)  weight_decay: 0.0500 (0.0500)  time: 1.0060  data: 0.0004  max mem: 78493
Epoch: [79]  [240/312]  eta: 0:01:17  lr: 0.003567  min_lr: 0.003567  loss: 2.6704 (2.5307)  weight_decay: 0.0500 (0.0500)  time: 1.0064  data: 0.0004  max mem: 78493
Epoch: [79]  [250/312]  eta: 0:01:06  lr: 0.003567  min_lr: 0.003567  loss: 2.5984 (2.5227)  weight_decay: 0.0500 (0.0500)  time: 1.0060  data: 0.0004  max mem: 78493
Epoch: [79]  [260/312]  eta: 0:00:56  lr: 0.003566  min_lr: 0.003566  loss: 2.4794 (2.5198)  weight_decay: 0.0500 (0.0500)  time: 1.0053  data: 0.0004  max mem: 78493
Epoch: [79]  [270/312]  eta: 0:00:45  lr: 0.003566  min_lr: 0.003566  loss: 2.2771 (2.5135)  weight_decay: 0.0500 (0.0500)  time: 1.0052  data: 0.0004  max mem: 78493
Epoch: [79]  [280/312]  eta: 0:00:34  lr: 0.003565  min_lr: 0.003565  loss: 2.4562 (2.5150)  weight_decay: 0.0500 (0.0500)  time: 1.0058  data: 0.0010  max mem: 78493
Epoch: [79]  [290/312]  eta: 0:00:23  lr: 0.003565  min_lr: 0.003565  loss: 2.6771 (2.5125)  weight_decay: 0.0500 (0.0500)  time: 1.0042  data: 0.0009  max mem: 78493
Epoch: [79]  [300/312]  eta: 0:00:12  lr: 0.003564  min_lr: 0.003564  loss: 2.6609 (2.5155)  weight_decay: 0.0500 (0.0500)  time: 1.0020  data: 0.0001  max mem: 78493
Epoch: [79]  [310/312]  eta: 0:00:02  lr: 0.003564  min_lr: 0.003564  loss: 2.7046 (2.5217)  weight_decay: 0.0500 (0.0500)  time: 1.0020  data: 0.0001  max mem: 78493
Epoch: [79]  [311/312]  eta: 0:00:01  lr: 0.003564  min_lr: 0.003564  loss: 2.6672 (2.5221)  weight_decay: 0.0500 (0.0500)  time: 1.0020  data: 0.0001  max mem: 78493
Epoch: [79] Total time: 0:05:33 (1.0705 s / it)
Averaged stats: lr: 0.003564  min_lr: 0.003564  loss: 2.6672 (2.4975)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:15  loss: 0.8859 (0.8859)  acc1: 78.9062 (78.9062)  acc5: 94.5312 (94.5312)  time: 8.3879  data: 8.1085  max mem: 78493
Test:  [8/9]  eta: 0:00:01  loss: 1.2622 (1.1385)  acc1: 69.4010 (71.5520)  acc5: 89.0625 (90.3680)  time: 1.1303  data: 0.9010  max mem: 78493
Test: Total time: 0:00:10 (1.1741 s / it)
* Acc@1 72.102 Acc@5 90.606 loss 1.133
Accuracy of the model on the 50000 test images: 72.1%
Max accuracy: 72.82%
Epoch: [80]  [  0/312]  eta: 1:27:54  lr: 0.003564  min_lr: 0.003564  loss: 2.5851 (2.5851)  weight_decay: 0.0500 (0.0500)  time: 16.9069  data: 13.9125  max mem: 78493
Epoch: [80]  [ 10/312]  eta: 0:13:14  lr: 0.003563  min_lr: 0.003563  loss: 2.5994 (2.5235)  weight_decay: 0.0500 (0.0500)  time: 2.6323  data: 1.3118  max mem: 78493
Epoch: [80]  [ 20/312]  eta: 0:09:05  lr: 0.003563  min_lr: 0.003563  loss: 2.6576 (2.6437)  weight_decay: 0.0500 (0.0500)  time: 1.1150  data: 0.0279  max mem: 78493
Epoch: [80]  [ 30/312]  eta: 0:07:28  lr: 0.003562  min_lr: 0.003562  loss: 2.5795 (2.5221)  weight_decay: 0.0500 (0.0500)  time: 1.0153  data: 0.0022  max mem: 78493
Epoch: [80]  [ 40/312]  eta: 0:06:33  lr: 0.003562  min_lr: 0.003562  loss: 2.5545 (2.5441)  weight_decay: 0.0500 (0.0500)  time: 1.0065  data: 0.0005  max mem: 78493
Epoch: [80]  [ 50/312]  eta: 0:05:56  lr: 0.003562  min_lr: 0.003562  loss: 2.5798 (2.5422)  weight_decay: 0.0500 (0.0500)  time: 1.0082  data: 0.0005  max mem: 78493
Epoch: [80]  [ 60/312]  eta: 0:05:28  lr: 0.003561  min_lr: 0.003561  loss: 2.5889 (2.5244)  weight_decay: 0.0500 (0.0500)  time: 1.0067  data: 0.0004  max mem: 78493
Epoch: [80]  [ 70/312]  eta: 0:05:05  lr: 0.003561  min_lr: 0.003561  loss: 2.5847 (2.5205)  weight_decay: 0.0500 (0.0500)  time: 1.0044  data: 0.0005  max mem: 78493
Epoch: [80]  [ 80/312]  eta: 0:04:45  lr: 0.003560  min_lr: 0.003560  loss: 2.6404 (2.5232)  weight_decay: 0.0500 (0.0500)  time: 1.0045  data: 0.0005  max mem: 78493
Epoch: [80]  [ 90/312]  eta: 0:04:27  lr: 0.003560  min_lr: 0.003560  loss: 2.6388 (2.5177)  weight_decay: 0.0500 (0.0500)  time: 1.0048  data: 0.0004  max mem: 78493
Epoch: [80]  [100/312]  eta: 0:04:11  lr: 0.003559  min_lr: 0.003559  loss: 2.3866 (2.4956)  weight_decay: 0.0500 (0.0500)  time: 1.0066  data: 0.0004  max mem: 78493
Epoch: [80]  [110/312]  eta: 0:03:56  lr: 0.003559  min_lr: 0.003559  loss: 2.3129 (2.4844)  weight_decay: 0.0500 (0.0500)  time: 1.0086  data: 0.0004  max mem: 78493
Epoch: [80]  [120/312]  eta: 0:03:41  lr: 0.003558  min_lr: 0.003558  loss: 2.5170 (2.4838)  weight_decay: 0.0500 (0.0500)  time: 1.0080  data: 0.0004  max mem: 78493
Epoch: [80]  [130/312]  eta: 0:03:28  lr: 0.003558  min_lr: 0.003558  loss: 2.5458 (2.4906)  weight_decay: 0.0500 (0.0500)  time: 1.0079  data: 0.0004  max mem: 78493
Epoch: [80]  [140/312]  eta: 0:03:15  lr: 0.003557  min_lr: 0.003557  loss: 2.5808 (2.4919)  weight_decay: 0.0500 (0.0500)  time: 1.0084  data: 0.0004  max mem: 78493
Epoch: [80]  [150/312]  eta: 0:03:02  lr: 0.003557  min_lr: 0.003557  loss: 2.4011 (2.4830)  weight_decay: 0.0500 (0.0500)  time: 1.0078  data: 0.0012  max mem: 78493
Epoch: [80]  [160/312]  eta: 0:02:50  lr: 0.003557  min_lr: 0.003557  loss: 2.1481 (2.4617)  weight_decay: 0.0500 (0.0500)  time: 1.0071  data: 0.0011  max mem: 78493
Epoch: [80]  [170/312]  eta: 0:02:37  lr: 0.003556  min_lr: 0.003556  loss: 2.2677 (2.4627)  weight_decay: 0.0500 (0.0500)  time: 1.0069  data: 0.0004  max mem: 78493
Epoch: [80]  [180/312]  eta: 0:02:26  lr: 0.003556  min_lr: 0.003556  loss: 2.3872 (2.4636)  weight_decay: 0.0500 (0.0500)  time: 1.0064  data: 0.0004  max mem: 78493
Epoch: [80]  [190/312]  eta: 0:02:14  lr: 0.003555  min_lr: 0.003555  loss: 2.3685 (2.4608)  weight_decay: 0.0500 (0.0500)  time: 1.0072  data: 0.0004  max mem: 78493
Epoch: [80]  [200/312]  eta: 0:02:02  lr: 0.003555  min_lr: 0.003555  loss: 2.3681 (2.4594)  weight_decay: 0.0500 (0.0500)  time: 1.0068  data: 0.0004  max mem: 78493
Epoch: [80]  [210/312]  eta: 0:01:51  lr: 0.003554  min_lr: 0.003554  loss: 2.5882 (2.4660)  weight_decay: 0.0500 (0.0500)  time: 1.0040  data: 0.0005  max mem: 78493
Epoch: [80]  [220/312]  eta: 0:01:40  lr: 0.003554  min_lr: 0.003554  loss: 2.7090 (2.4709)  weight_decay: 0.0500 (0.0500)  time: 1.0036  data: 0.0004  max mem: 78493
Epoch: [80]  [230/312]  eta: 0:01:28  lr: 0.003553  min_lr: 0.003553  loss: 2.5619 (2.4632)  weight_decay: 0.0500 (0.0500)  time: 1.0047  data: 0.0005  max mem: 78493
Epoch: [80]  [240/312]  eta: 0:01:17  lr: 0.003553  min_lr: 0.003553  loss: 2.5619 (2.4700)  weight_decay: 0.0500 (0.0500)  time: 1.0054  data: 0.0005  max mem: 78493
Epoch: [80]  [250/312]  eta: 0:01:06  lr: 0.003553  min_lr: 0.003553  loss: 2.6517 (2.4794)  weight_decay: 0.0500 (0.0500)  time: 1.0056  data: 0.0004  max mem: 78493
Epoch: [80]  [260/312]  eta: 0:00:55  lr: 0.003552  min_lr: 0.003552  loss: 2.6625 (2.4891)  weight_decay: 0.0500 (0.0500)  time: 1.0054  data: 0.0004  max mem: 78493
Epoch: [80]  [270/312]  eta: 0:00:45  lr: 0.003552  min_lr: 0.003552  loss: 2.6713 (2.4924)  weight_decay: 0.0500 (0.0500)  time: 1.0048  data: 0.0005  max mem: 78493
Epoch: [80]  [280/312]  eta: 0:00:34  lr: 0.003551  min_lr: 0.003551  loss: 2.5704 (2.4938)  weight_decay: 0.0500 (0.0500)  time: 1.0049  data: 0.0011  max mem: 78493
Epoch: [80]  [290/312]  eta: 0:00:23  lr: 0.003551  min_lr: 0.003551  loss: 2.5283 (2.4961)  weight_decay: 0.0500 (0.0500)  time: 1.0037  data: 0.0009  max mem: 78493
Epoch: [80]  [300/312]  eta: 0:00:12  lr: 0.003550  min_lr: 0.003550  loss: 2.5108 (2.4924)  weight_decay: 0.0500 (0.0500)  time: 1.0018  data: 0.0001  max mem: 78493
Epoch: [80]  [310/312]  eta: 0:00:02  lr: 0.003550  min_lr: 0.003550  loss: 2.4939 (2.4904)  weight_decay: 0.0500 (0.0500)  time: 1.0016  data: 0.0001  max mem: 78493
Epoch: [80]  [311/312]  eta: 0:00:01  lr: 0.003550  min_lr: 0.003550  loss: 2.4939 (2.4890)  weight_decay: 0.0500 (0.0500)  time: 1.0016  data: 0.0001  max mem: 78493
Epoch: [80] Total time: 0:05:33 (1.0691 s / it)
Averaged stats: lr: 0.003550  min_lr: 0.003550  loss: 2.4939 (2.5102)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:21  loss: 0.8086 (0.8086)  acc1: 79.5573 (79.5573)  acc5: 94.5312 (94.5312)  time: 9.0318  data: 8.7716  max mem: 78493
Test:  [8/9]  eta: 0:00:01  loss: 1.1705 (1.0636)  acc1: 71.6146 (72.8960)  acc5: 90.7552 (91.5200)  time: 1.2081  data: 0.9747  max mem: 78493
Test: Total time: 0:00:11 (1.2606 s / it)
* Acc@1 73.016 Acc@5 91.338 loss 1.069
Accuracy of the model on the 50000 test images: 73.0%
Max accuracy: 73.02%
Epoch: [81]  [  0/312]  eta: 1:18:55  lr: 0.003550  min_lr: 0.003550  loss: 3.0678 (3.0678)  weight_decay: 0.0500 (0.0500)  time: 15.1787  data: 14.1712  max mem: 78493
Epoch: [81]  [ 10/312]  eta: 0:12:37  lr: 0.003549  min_lr: 0.003549  loss: 2.8052 (2.6420)  weight_decay: 0.0500 (0.0500)  time: 2.5076  data: 1.2933  max mem: 78493
Epoch: [81]  [ 20/312]  eta: 0:08:47  lr: 0.003549  min_lr: 0.003549  loss: 2.6188 (2.5513)  weight_decay: 0.0500 (0.0500)  time: 1.1363  data: 0.0031  max mem: 78493
Epoch: [81]  [ 30/312]  eta: 0:07:16  lr: 0.003548  min_lr: 0.003548  loss: 2.6092 (2.5359)  weight_decay: 0.0500 (0.0500)  time: 1.0220  data: 0.0006  max mem: 78493
Epoch: [81]  [ 40/312]  eta: 0:06:25  lr: 0.003548  min_lr: 0.003548  loss: 2.5532 (2.5196)  weight_decay: 0.0500 (0.0500)  time: 1.0115  data: 0.0005  max mem: 78493
Epoch: [81]  [ 50/312]  eta: 0:05:50  lr: 0.003547  min_lr: 0.003547  loss: 2.4348 (2.4992)  weight_decay: 0.0500 (0.0500)  time: 1.0079  data: 0.0005  max mem: 78493
Epoch: [81]  [ 60/312]  eta: 0:05:23  lr: 0.003547  min_lr: 0.003547  loss: 2.4348 (2.4966)  weight_decay: 0.0500 (0.0500)  time: 1.0047  data: 0.0005  max mem: 78493
Epoch: [81]  [ 70/312]  eta: 0:05:00  lr: 0.003546  min_lr: 0.003546  loss: 2.6080 (2.4921)  weight_decay: 0.0500 (0.0500)  time: 1.0058  data: 0.0005  max mem: 78493
Epoch: [81]  [ 80/312]  eta: 0:04:41  lr: 0.003546  min_lr: 0.003546  loss: 2.6878 (2.5127)  weight_decay: 0.0500 (0.0500)  time: 1.0073  data: 0.0005  max mem: 78493
Epoch: [81]  [ 90/312]  eta: 0:04:24  lr: 0.003546  min_lr: 0.003546  loss: 2.6949 (2.5216)  weight_decay: 0.0500 (0.0500)  time: 1.0059  data: 0.0005  max mem: 78493
Epoch: [81]  [100/312]  eta: 0:04:08  lr: 0.003545  min_lr: 0.003545  loss: 2.5554 (2.5103)  weight_decay: 0.0500 (0.0500)  time: 1.0048  data: 0.0005  max mem: 78493
Epoch: [81]  [110/312]  eta: 0:03:54  lr: 0.003545  min_lr: 0.003545  loss: 2.4156 (2.4952)  weight_decay: 0.0500 (0.0500)  time: 1.0086  data: 0.0005  max mem: 78493
Epoch: [81]  [120/312]  eta: 0:03:40  lr: 0.003544  min_lr: 0.003544  loss: 2.3884 (2.4925)  weight_decay: 0.0500 (0.0500)  time: 1.0100  data: 0.0005  max mem: 78493
Epoch: [81]  [130/312]  eta: 0:03:26  lr: 0.003544  min_lr: 0.003544  loss: 2.5427 (2.4959)  weight_decay: 0.0500 (0.0500)  time: 1.0077  data: 0.0005  max mem: 78493
Epoch: [81]  [140/312]  eta: 0:03:13  lr: 0.003543  min_lr: 0.003543  loss: 2.4492 (2.4874)  weight_decay: 0.0500 (0.0500)  time: 1.0068  data: 0.0005  max mem: 78493
Epoch: [81]  [150/312]  eta: 0:03:01  lr: 0.003543  min_lr: 0.003543  loss: 2.3659 (2.4759)  weight_decay: 0.0500 (0.0500)  time: 1.0056  data: 0.0014  max mem: 78493
Epoch: [81]  [160/312]  eta: 0:02:48  lr: 0.003542  min_lr: 0.003542  loss: 2.5612 (2.4857)  weight_decay: 0.0500 (0.0500)  time: 1.0044  data: 0.0014  max mem: 78493
Epoch: [81]  [170/312]  eta: 0:02:36  lr: 0.003542  min_lr: 0.003542  loss: 2.7214 (2.5030)  weight_decay: 0.0500 (0.0500)  time: 1.0058  data: 0.0005  max mem: 78493
Epoch: [81]  [180/312]  eta: 0:02:25  lr: 0.003541  min_lr: 0.003541  loss: 2.7356 (2.5049)  weight_decay: 0.0500 (0.0500)  time: 1.0053  data: 0.0004  max mem: 78493
Epoch: [81]  [190/312]  eta: 0:02:13  lr: 0.003541  min_lr: 0.003541  loss: 2.5421 (2.4981)  weight_decay: 0.0500 (0.0500)  time: 1.0036  data: 0.0004  max mem: 78493
Epoch: [81]  [200/312]  eta: 0:02:02  lr: 0.003541  min_lr: 0.003541  loss: 2.1749 (2.4866)  weight_decay: 0.0500 (0.0500)  time: 1.0056  data: 0.0004  max mem: 78493
Epoch: [81]  [210/312]  eta: 0:01:50  lr: 0.003540  min_lr: 0.003540  loss: 2.5270 (2.4921)  weight_decay: 0.0500 (0.0500)  time: 1.0067  data: 0.0005  max mem: 78493
Epoch: [81]  [220/312]  eta: 0:01:39  lr: 0.003540  min_lr: 0.003540  loss: 2.7009 (2.4926)  weight_decay: 0.0500 (0.0500)  time: 1.0058  data: 0.0005  max mem: 78493
Epoch: [81]  [230/312]  eta: 0:01:28  lr: 0.003539  min_lr: 0.003539  loss: 2.3025 (2.4815)  weight_decay: 0.0500 (0.0500)  time: 1.0048  data: 0.0005  max mem: 78493
Epoch: [81]  [240/312]  eta: 0:01:17  lr: 0.003539  min_lr: 0.003539  loss: 2.1380 (2.4775)  weight_decay: 0.0500 (0.0500)  time: 1.0040  data: 0.0005  max mem: 78493
Epoch: [81]  [250/312]  eta: 0:01:06  lr: 0.003538  min_lr: 0.003538  loss: 2.4237 (2.4722)  weight_decay: 0.0500 (0.0500)  time: 1.0041  data: 0.0005  max mem: 78493
Epoch: [81]  [260/312]  eta: 0:00:55  lr: 0.003538  min_lr: 0.003538  loss: 2.1881 (2.4591)  weight_decay: 0.0500 (0.0500)  time: 1.0050  data: 0.0005  max mem: 78493
Epoch: [81]  [270/312]  eta: 0:00:44  lr: 0.003537  min_lr: 0.003537  loss: 2.1322 (2.4546)  weight_decay: 0.0500 (0.0500)  time: 1.0050  data: 0.0011  max mem: 78493
Epoch: [81]  [280/312]  eta: 0:00:34  lr: 0.003537  min_lr: 0.003537  loss: 2.4736 (2.4569)  weight_decay: 0.0500 (0.0500)  time: 1.0056  data: 0.0017  max mem: 78493
Epoch: [81]  [290/312]  eta: 0:00:23  lr: 0.003536  min_lr: 0.003536  loss: 2.6269 (2.4555)  weight_decay: 0.0500 (0.0500)  time: 1.0042  data: 0.0009  max mem: 78493
Epoch: [81]  [300/312]  eta: 0:00:12  lr: 0.003536  min_lr: 0.003536  loss: 2.6483 (2.4579)  weight_decay: 0.0500 (0.0500)  time: 1.0018  data: 0.0001  max mem: 78493
Epoch: [81]  [310/312]  eta: 0:00:02  lr: 0.003535  min_lr: 0.003535  loss: 2.6483 (2.4610)  weight_decay: 0.0500 (0.0500)  time: 1.0019  data: 0.0001  max mem: 78493
Epoch: [81]  [311/312]  eta: 0:00:01  lr: 0.003535  min_lr: 0.003535  loss: 2.6483 (2.4617)  weight_decay: 0.0500 (0.0500)  time: 1.0019  data: 0.0001  max mem: 78493
Epoch: [81] Total time: 0:05:32 (1.0653 s / it)
Averaged stats: lr: 0.003535  min_lr: 0.003535  loss: 2.6483 (2.4806)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:13  loss: 0.9134 (0.9134)  acc1: 79.1667 (79.1667)  acc5: 94.0104 (94.0104)  time: 8.1114  data: 7.8158  max mem: 78493
Test:  [8/9]  eta: 0:00:01  loss: 1.2264 (1.1411)  acc1: 71.2240 (71.7440)  acc5: 90.4948 (90.8160)  time: 1.0995  data: 0.8685  max mem: 78493
Test: Total time: 0:00:10 (1.1149 s / it)
* Acc@1 72.180 Acc@5 90.996 loss 1.128
Accuracy of the model on the 50000 test images: 72.2%
Max accuracy: 73.02%
Epoch: [82]  [  0/312]  eta: 1:27:39  lr: 0.003535  min_lr: 0.003535  loss: 2.1548 (2.1548)  weight_decay: 0.0500 (0.0500)  time: 16.8567  data: 14.0356  max mem: 78493
Epoch: [82]  [ 10/312]  eta: 0:13:12  lr: 0.003535  min_lr: 0.003535  loss: 2.6901 (2.5536)  weight_decay: 0.0500 (0.0500)  time: 2.6229  data: 1.2770  max mem: 78493
Epoch: [82]  [ 20/312]  eta: 0:09:03  lr: 0.003534  min_lr: 0.003534  loss: 2.4675 (2.4414)  weight_decay: 0.0500 (0.0500)  time: 1.1131  data: 0.0034  max mem: 78493
Epoch: [82]  [ 30/312]  eta: 0:07:27  lr: 0.003534  min_lr: 0.003534  loss: 2.5763 (2.5350)  weight_decay: 0.0500 (0.0500)  time: 1.0184  data: 0.0031  max mem: 78493
Epoch: [82]  [ 40/312]  eta: 0:06:33  lr: 0.003534  min_lr: 0.003534  loss: 2.5998 (2.5183)  weight_decay: 0.0500 (0.0500)  time: 1.0091  data: 0.0004  max mem: 78493
Epoch: [82]  [ 50/312]  eta: 0:05:56  lr: 0.003533  min_lr: 0.003533  loss: 2.5423 (2.5132)  weight_decay: 0.0500 (0.0500)  time: 1.0086  data: 0.0004  max mem: 78493
Epoch: [82]  [ 60/312]  eta: 0:05:28  lr: 0.003533  min_lr: 0.003533  loss: 2.4874 (2.4787)  weight_decay: 0.0500 (0.0500)  time: 1.0097  data: 0.0005  max mem: 78493
Epoch: [82]  [ 70/312]  eta: 0:05:05  lr: 0.003532  min_lr: 0.003532  loss: 2.4787 (2.4780)  weight_decay: 0.0500 (0.0500)  time: 1.0115  data: 0.0004  max mem: 78493
Epoch: [82]  [ 80/312]  eta: 0:04:45  lr: 0.003532  min_lr: 0.003532  loss: 2.5459 (2.4679)  weight_decay: 0.0500 (0.0500)  time: 1.0089  data: 0.0012  max mem: 78493
Epoch: [82]  [ 90/312]  eta: 0:04:27  lr: 0.003531  min_lr: 0.003531  loss: 2.5677 (2.4606)  weight_decay: 0.0500 (0.0500)  time: 1.0054  data: 0.0012  max mem: 78493
Epoch: [82]  [100/312]  eta: 0:04:11  lr: 0.003531  min_lr: 0.003531  loss: 2.2358 (2.4424)  weight_decay: 0.0500 (0.0500)  time: 1.0040  data: 0.0005  max mem: 78493
Epoch: [82]  [110/312]  eta: 0:03:56  lr: 0.003530  min_lr: 0.003530  loss: 2.2521 (2.4324)  weight_decay: 0.0500 (0.0500)  time: 1.0036  data: 0.0004  max mem: 78493
Epoch: [82]  [120/312]  eta: 0:03:41  lr: 0.003530  min_lr: 0.003530  loss: 2.4874 (2.4423)  weight_decay: 0.0500 (0.0500)  time: 1.0053  data: 0.0004  max mem: 78493
Epoch: [82]  [130/312]  eta: 0:03:28  lr: 0.003529  min_lr: 0.003529  loss: 2.5819 (2.4488)  weight_decay: 0.0500 (0.0500)  time: 1.0073  data: 0.0005  max mem: 78493
Epoch: [82]  [140/312]  eta: 0:03:15  lr: 0.003529  min_lr: 0.003529  loss: 2.7153 (2.4612)  weight_decay: 0.0500 (0.0500)  time: 1.0071  data: 0.0005  max mem: 78493
Epoch: [82]  [150/312]  eta: 0:03:02  lr: 0.003528  min_lr: 0.003528  loss: 2.7485 (2.4717)  weight_decay: 0.0500 (0.0500)  time: 1.0061  data: 0.0004  max mem: 78493
Epoch: [82]  [160/312]  eta: 0:02:50  lr: 0.003528  min_lr: 0.003528  loss: 2.5492 (2.4738)  weight_decay: 0.0500 (0.0500)  time: 1.0078  data: 0.0004  max mem: 78493
Epoch: [82]  [170/312]  eta: 0:02:37  lr: 0.003528  min_lr: 0.003528  loss: 2.5319 (2.4677)  weight_decay: 0.0500 (0.0500)  time: 1.0098  data: 0.0004  max mem: 78493
Epoch: [82]  [180/312]  eta: 0:02:26  lr: 0.003527  min_lr: 0.003527  loss: 2.4953 (2.4640)  weight_decay: 0.0500 (0.0500)  time: 1.0090  data: 0.0004  max mem: 78493
Epoch: [82]  [190/312]  eta: 0:02:14  lr: 0.003527  min_lr: 0.003527  loss: 2.3917 (2.4597)  weight_decay: 0.0500 (0.0500)  time: 1.0084  data: 0.0004  max mem: 78493
Epoch: [82]  [200/312]  eta: 0:02:02  lr: 0.003526  min_lr: 0.003526  loss: 2.4940 (2.4618)  weight_decay: 0.0500 (0.0500)  time: 1.0073  data: 0.0004  max mem: 78493
Epoch: [82]  [210/312]  eta: 0:01:51  lr: 0.003526  min_lr: 0.003526  loss: 2.3463 (2.4594)  weight_decay: 0.0500 (0.0500)  time: 1.0053  data: 0.0004  max mem: 78493
Epoch: [82]  [220/312]  eta: 0:01:40  lr: 0.003525  min_lr: 0.003525  loss: 2.5248 (2.4679)  weight_decay: 0.0500 (0.0500)  time: 1.0048  data: 0.0004  max mem: 78493
Epoch: [82]  [230/312]  eta: 0:01:28  lr: 0.003525  min_lr: 0.003525  loss: 2.5963 (2.4674)  weight_decay: 0.0500 (0.0500)  time: 1.0050  data: 0.0004  max mem: 78493
Epoch: [82]  [240/312]  eta: 0:01:17  lr: 0.003524  min_lr: 0.003524  loss: 2.4554 (2.4672)  weight_decay: 0.0500 (0.0500)  time: 1.0050  data: 0.0004  max mem: 78493
Epoch: [82]  [250/312]  eta: 0:01:06  lr: 0.003524  min_lr: 0.003524  loss: 2.5369 (2.4685)  weight_decay: 0.0500 (0.0500)  time: 1.0055  data: 0.0004  max mem: 78493
Epoch: [82]  [260/312]  eta: 0:00:55  lr: 0.003523  min_lr: 0.003523  loss: 2.5806 (2.4707)  weight_decay: 0.0500 (0.0500)  time: 1.0070  data: 0.0005  max mem: 78493
Epoch: [82]  [270/312]  eta: 0:00:45  lr: 0.003523  min_lr: 0.003523  loss: 2.6175 (2.4806)  weight_decay: 0.0500 (0.0500)  time: 1.0074  data: 0.0005  max mem: 78493
Epoch: [82]  [280/312]  eta: 0:00:34  lr: 0.003522  min_lr: 0.003522  loss: 2.7337 (2.4801)  weight_decay: 0.0500 (0.0500)  time: 1.0064  data: 0.0010  max mem: 78493
Epoch: [82]  [290/312]  eta: 0:00:23  lr: 0.003522  min_lr: 0.003522  loss: 2.7301 (2.4863)  weight_decay: 0.0500 (0.0500)  time: 1.0035  data: 0.0009  max mem: 78493
Epoch: [82]  [300/312]  eta: 0:00:12  lr: 0.003521  min_lr: 0.003521  loss: 2.2908 (2.4742)  weight_decay: 0.0500 (0.0500)  time: 1.0019  data: 0.0001  max mem: 78493
Epoch: [82]  [310/312]  eta: 0:00:02  lr: 0.003521  min_lr: 0.003521  loss: 2.2710 (2.4707)  weight_decay: 0.0500 (0.0500)  time: 1.0016  data: 0.0001  max mem: 78493
Epoch: [82]  [311/312]  eta: 0:00:01  lr: 0.003521  min_lr: 0.003521  loss: 2.2710 (2.4711)  weight_decay: 0.0500 (0.0500)  time: 1.0017  data: 0.0001  max mem: 78493
Epoch: [82] Total time: 0:05:33 (1.0698 s / it)
Averaged stats: lr: 0.003521  min_lr: 0.003521  loss: 2.2710 (2.4838)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:12  loss: 0.8752 (0.8752)  acc1: 78.7760 (78.7760)  acc5: 94.1406 (94.1406)  time: 8.0227  data: 7.7528  max mem: 78493
Test:  [8/9]  eta: 0:00:01  loss: 1.1982 (1.0886)  acc1: 72.1354 (73.0240)  acc5: 90.4948 (91.0720)  time: 1.0901  data: 0.8615  max mem: 78493
Test: Total time: 0:00:09 (1.1096 s / it)
* Acc@1 73.044 Acc@5 91.272 loss 1.078
Accuracy of the model on the 50000 test images: 73.0%
Max accuracy: 73.04%
Epoch: [83]  [  0/312]  eta: 1:21:57  lr: 0.003521  min_lr: 0.003521  loss: 2.7084 (2.7084)  weight_decay: 0.0500 (0.0500)  time: 15.7620  data: 14.4484  max mem: 78493
Epoch: [83]  [ 10/312]  eta: 0:12:50  lr: 0.003520  min_lr: 0.003520  loss: 2.3499 (2.2282)  weight_decay: 0.0500 (0.0500)  time: 2.5510  data: 1.3247  max mem: 78493
Epoch: [83]  [ 20/312]  eta: 0:08:51  lr: 0.003520  min_lr: 0.003520  loss: 2.4043 (2.3477)  weight_decay: 0.0500 (0.0500)  time: 1.1214  data: 0.0065  max mem: 78493
Epoch: [83]  [ 30/312]  eta: 0:07:18  lr: 0.003520  min_lr: 0.003520  loss: 2.4670 (2.3917)  weight_decay: 0.0500 (0.0500)  time: 1.0089  data: 0.0005  max mem: 78493
Epoch: [83]  [ 40/312]  eta: 0:06:26  lr: 0.003519  min_lr: 0.003519  loss: 2.5094 (2.3973)  weight_decay: 0.0500 (0.0500)  time: 1.0058  data: 0.0004  max mem: 78493
Epoch: [83]  [ 50/312]  eta: 0:05:51  lr: 0.003519  min_lr: 0.003519  loss: 2.5094 (2.4102)  weight_decay: 0.0500 (0.0500)  time: 1.0067  data: 0.0004  max mem: 78493
Epoch: [83]  [ 60/312]  eta: 0:05:23  lr: 0.003518  min_lr: 0.003518  loss: 2.2833 (2.3910)  weight_decay: 0.0500 (0.0500)  time: 1.0056  data: 0.0005  max mem: 78493
Epoch: [83]  [ 70/312]  eta: 0:05:01  lr: 0.003518  min_lr: 0.003518  loss: 2.3535 (2.4083)  weight_decay: 0.0500 (0.0500)  time: 1.0057  data: 0.0005  max mem: 78493
Epoch: [83]  [ 80/312]  eta: 0:04:42  lr: 0.003517  min_lr: 0.003517  loss: 2.5053 (2.4000)  weight_decay: 0.0500 (0.0500)  time: 1.0078  data: 0.0005  max mem: 78493
Epoch: [83]  [ 90/312]  eta: 0:04:25  lr: 0.003517  min_lr: 0.003517  loss: 2.3465 (2.3897)  weight_decay: 0.0500 (0.0500)  time: 1.0089  data: 0.0005  max mem: 78493
Epoch: [83]  [100/312]  eta: 0:04:09  lr: 0.003516  min_lr: 0.003516  loss: 2.3359 (2.3841)  weight_decay: 0.0500 (0.0500)  time: 1.0103  data: 0.0011  max mem: 78493
Epoch: [83]  [110/312]  eta: 0:03:54  lr: 0.003516  min_lr: 0.003516  loss: 2.4999 (2.3933)  weight_decay: 0.0500 (0.0500)  time: 1.0117  data: 0.0011  max mem: 78493
Epoch: [83]  [120/312]  eta: 0:03:40  lr: 0.003515  min_lr: 0.003515  loss: 2.5193 (2.3902)  weight_decay: 0.0500 (0.0500)  time: 1.0108  data: 0.0005  max mem: 78493
Epoch: [83]  [130/312]  eta: 0:03:27  lr: 0.003515  min_lr: 0.003515  loss: 2.5193 (2.4033)  weight_decay: 0.0500 (0.0500)  time: 1.0079  data: 0.0004  max mem: 78493
Epoch: [83]  [140/312]  eta: 0:03:14  lr: 0.003514  min_lr: 0.003514  loss: 2.5185 (2.4060)  weight_decay: 0.0500 (0.0500)  time: 1.0068  data: 0.0004  max mem: 78493
Epoch: [83]  [150/312]  eta: 0:03:01  lr: 0.003514  min_lr: 0.003514  loss: 2.4581 (2.4036)  weight_decay: 0.0500 (0.0500)  time: 1.0066  data: 0.0004  max mem: 78493
Epoch: [83]  [160/312]  eta: 0:02:49  lr: 0.003513  min_lr: 0.003513  loss: 2.3647 (2.4011)  weight_decay: 0.0500 (0.0500)  time: 1.0060  data: 0.0004  max mem: 78493
Epoch: [83]  [170/312]  eta: 0:02:37  lr: 0.003513  min_lr: 0.003513  loss: 2.3317 (2.3978)  weight_decay: 0.0500 (0.0500)  time: 1.0074  data: 0.0004  max mem: 78493
Epoch: [83]  [180/312]  eta: 0:02:25  lr: 0.003512  min_lr: 0.003512  loss: 2.4590 (2.4021)  weight_decay: 0.0500 (0.0500)  time: 1.0083  data: 0.0004  max mem: 78493
Epoch: [83]  [190/312]  eta: 0:02:13  lr: 0.003512  min_lr: 0.003512  loss: 2.5359 (2.4140)  weight_decay: 0.0500 (0.0500)  time: 1.0081  data: 0.0004  max mem: 78493
Epoch: [83]  [200/312]  eta: 0:02:02  lr: 0.003512  min_lr: 0.003512  loss: 2.6040 (2.4169)  weight_decay: 0.0500 (0.0500)  time: 1.0067  data: 0.0004  max mem: 78493
Epoch: [83]  [210/312]  eta: 0:01:50  lr: 0.003511  min_lr: 0.003511  loss: 2.4790 (2.4190)  weight_decay: 0.0500 (0.0500)  time: 1.0054  data: 0.0005  max mem: 78493
Epoch: [83]  [220/312]  eta: 0:01:39  lr: 0.003511  min_lr: 0.003511  loss: 2.4283 (2.4174)  weight_decay: 0.0500 (0.0500)  time: 1.0054  data: 0.0004  max mem: 78493
Epoch: [83]  [230/312]  eta: 0:01:28  lr: 0.003510  min_lr: 0.003510  loss: 2.5356 (2.4214)  weight_decay: 0.0500 (0.0500)  time: 1.0056  data: 0.0004  max mem: 78493
Epoch: [83]  [240/312]  eta: 0:01:17  lr: 0.003510  min_lr: 0.003510  loss: 2.5356 (2.4214)  weight_decay: 0.0500 (0.0500)  time: 1.0059  data: 0.0004  max mem: 78493
Epoch: [83]  [250/312]  eta: 0:01:06  lr: 0.003509  min_lr: 0.003509  loss: 2.2217 (2.4187)  weight_decay: 0.0500 (0.0500)  time: 1.0056  data: 0.0004  max mem: 78493
Epoch: [83]  [260/312]  eta: 0:00:55  lr: 0.003509  min_lr: 0.003509  loss: 2.2323 (2.4201)  weight_decay: 0.0500 (0.0500)  time: 1.0046  data: 0.0004  max mem: 78493
Epoch: [83]  [270/312]  eta: 0:00:44  lr: 0.003508  min_lr: 0.003508  loss: 2.5853 (2.4210)  weight_decay: 0.0500 (0.0500)  time: 1.0053  data: 0.0004  max mem: 78493
Epoch: [83]  [280/312]  eta: 0:00:34  lr: 0.003508  min_lr: 0.003508  loss: 2.6007 (2.4294)  weight_decay: 0.0500 (0.0500)  time: 1.0070  data: 0.0010  max mem: 78493
Epoch: [83]  [290/312]  eta: 0:00:23  lr: 0.003507  min_lr: 0.003507  loss: 2.6160 (2.4315)  weight_decay: 0.0500 (0.0500)  time: 1.0039  data: 0.0009  max mem: 78493
Epoch: [83]  [300/312]  eta: 0:00:12  lr: 0.003507  min_lr: 0.003507  loss: 2.6160 (2.4329)  weight_decay: 0.0500 (0.0500)  time: 1.0012  data: 0.0001  max mem: 78493
Epoch: [83]  [310/312]  eta: 0:00:02  lr: 0.003506  min_lr: 0.003506  loss: 2.3897 (2.4305)  weight_decay: 0.0500 (0.0500)  time: 1.0017  data: 0.0001  max mem: 78493
Epoch: [83]  [311/312]  eta: 0:00:01  lr: 0.003506  min_lr: 0.003506  loss: 2.4348 (2.4318)  weight_decay: 0.0500 (0.0500)  time: 1.0017  data: 0.0001  max mem: 78493
Epoch: [83] Total time: 0:05:32 (1.0666 s / it)
Averaged stats: lr: 0.003506  min_lr: 0.003506  loss: 2.4348 (2.4891)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:11  loss: 0.7876 (0.7876)  acc1: 80.0781 (80.0781)  acc5: 95.1823 (95.1823)  time: 7.8934  data: 7.6116  max mem: 78493
Test:  [8/9]  eta: 0:00:01  loss: 1.2153 (1.0921)  acc1: 71.2240 (72.8320)  acc5: 90.8854 (91.3760)  time: 1.0982  data: 0.8683  max mem: 78493
Test: Total time: 0:00:10 (1.1282 s / it)
* Acc@1 73.180 Acc@5 91.408 loss 1.057
Accuracy of the model on the 50000 test images: 73.2%
Max accuracy: 73.18%
Epoch: [84]  [  0/312]  eta: 1:29:01  lr: 0.003506  min_lr: 0.003506  loss: 2.2798 (2.2798)  weight_decay: 0.0500 (0.0500)  time: 17.1207  data: 16.1110  max mem: 78493
Epoch: [84]  [ 10/312]  eta: 0:13:49  lr: 0.003506  min_lr: 0.003506  loss: 2.6429 (2.5327)  weight_decay: 0.0500 (0.0500)  time: 2.7473  data: 1.4653  max mem: 78493
Epoch: [84]  [ 20/312]  eta: 0:09:20  lr: 0.003505  min_lr: 0.003505  loss: 2.5671 (2.4828)  weight_decay: 0.0500 (0.0500)  time: 1.1597  data: 0.0006  max mem: 78493
Epoch: [84]  [ 30/312]  eta: 0:07:38  lr: 0.003505  min_lr: 0.003505  loss: 2.5021 (2.4577)  weight_decay: 0.0500 (0.0500)  time: 1.0088  data: 0.0004  max mem: 78493
Epoch: [84]  [ 40/312]  eta: 0:06:41  lr: 0.003504  min_lr: 0.003504  loss: 2.5021 (2.4680)  weight_decay: 0.0500 (0.0500)  time: 1.0090  data: 0.0004  max mem: 78493
Epoch: [84]  [ 50/312]  eta: 0:06:02  lr: 0.003504  min_lr: 0.003504  loss: 2.7103 (2.5113)  weight_decay: 0.0500 (0.0500)  time: 1.0091  data: 0.0004  max mem: 78493
Epoch: [84]  [ 60/312]  eta: 0:05:33  lr: 0.003503  min_lr: 0.003503  loss: 2.7103 (2.5151)  weight_decay: 0.0500 (0.0500)  time: 1.0067  data: 0.0004  max mem: 78493
Epoch: [84]  [ 70/312]  eta: 0:05:09  lr: 0.003503  min_lr: 0.003503  loss: 2.5888 (2.5249)  weight_decay: 0.0500 (0.0500)  time: 1.0061  data: 0.0004  max mem: 78493
Epoch: [84]  [ 80/312]  eta: 0:04:48  lr: 0.003502  min_lr: 0.003502  loss: 2.6486 (2.5478)  weight_decay: 0.0500 (0.0500)  time: 1.0069  data: 0.0004  max mem: 78493
Epoch: [84]  [ 90/312]  eta: 0:04:30  lr: 0.003502  min_lr: 0.003502  loss: 2.4858 (2.5278)  weight_decay: 0.0500 (0.0500)  time: 1.0078  data: 0.0004  max mem: 78493
Epoch: [84]  [100/312]  eta: 0:04:13  lr: 0.003502  min_lr: 0.003502  loss: 2.4719 (2.5302)  weight_decay: 0.0500 (0.0500)  time: 1.0088  data: 0.0004  max mem: 78493
Epoch: [84]  [110/312]  eta: 0:03:58  lr: 0.003501  min_lr: 0.003501  loss: 2.4556 (2.5143)  weight_decay: 0.0500 (0.0500)  time: 1.0090  data: 0.0004  max mem: 78493
Epoch: [84]  [120/312]  eta: 0:03:43  lr: 0.003501  min_lr: 0.003501  loss: 2.5475 (2.5210)  weight_decay: 0.0500 (0.0500)  time: 1.0074  data: 0.0004  max mem: 78493
Epoch: [84]  [130/312]  eta: 0:03:29  lr: 0.003500  min_lr: 0.003500  loss: 2.6239 (2.5198)  weight_decay: 0.0500 (0.0500)  time: 1.0050  data: 0.0004  max mem: 78493
Epoch: [84]  [140/312]  eta: 0:03:16  lr: 0.003500  min_lr: 0.003500  loss: 2.5115 (2.5231)  weight_decay: 0.0500 (0.0500)  time: 1.0051  data: 0.0004  max mem: 78493
Epoch: [84]  [150/312]  eta: 0:03:03  lr: 0.003499  min_lr: 0.003499  loss: 2.4742 (2.5133)  weight_decay: 0.0500 (0.0500)  time: 1.0061  data: 0.0004  max mem: 78493
Epoch: [84]  [160/312]  eta: 0:02:51  lr: 0.003499  min_lr: 0.003499  loss: 2.4983 (2.5146)  weight_decay: 0.0500 (0.0500)  time: 1.0088  data: 0.0004  max mem: 78493
Epoch: [84]  [170/312]  eta: 0:02:38  lr: 0.003498  min_lr: 0.003498  loss: 2.6837 (2.5193)  weight_decay: 0.0500 (0.0500)  time: 1.0097  data: 0.0004  max mem: 78493
Epoch: [84]  [180/312]  eta: 0:02:26  lr: 0.003498  min_lr: 0.003498  loss: 2.6552 (2.5185)  weight_decay: 0.0500 (0.0500)  time: 1.0076  data: 0.0004  max mem: 78493
Epoch: [84]  [190/312]  eta: 0:02:15  lr: 0.003497  min_lr: 0.003497  loss: 2.4001 (2.5151)  weight_decay: 0.0500 (0.0500)  time: 1.0069  data: 0.0004  max mem: 78493
Epoch: [84]  [200/312]  eta: 0:02:03  lr: 0.003497  min_lr: 0.003497  loss: 2.3358 (2.5089)  weight_decay: 0.0500 (0.0500)  time: 1.0063  data: 0.0004  max mem: 78493
Epoch: [84]  [210/312]  eta: 0:01:52  lr: 0.003496  min_lr: 0.003496  loss: 2.6871 (2.5160)  weight_decay: 0.0500 (0.0500)  time: 1.0059  data: 0.0004  max mem: 78493
Epoch: [84]  [220/312]  eta: 0:01:40  lr: 0.003496  min_lr: 0.003496  loss: 2.6208 (2.5122)  weight_decay: 0.0500 (0.0500)  time: 1.0060  data: 0.0004  max mem: 78493
Epoch: [84]  [230/312]  eta: 0:01:29  lr: 0.003495  min_lr: 0.003495  loss: 2.5946 (2.5154)  weight_decay: 0.0500 (0.0500)  time: 1.0056  data: 0.0004  max mem: 78493
Epoch: [84]  [240/312]  eta: 0:01:18  lr: 0.003495  min_lr: 0.003495  loss: 2.5900 (2.5122)  weight_decay: 0.0500 (0.0500)  time: 1.0061  data: 0.0004  max mem: 78493
Epoch: [84]  [250/312]  eta: 0:01:07  lr: 0.003494  min_lr: 0.003494  loss: 2.5900 (2.5129)  weight_decay: 0.0500 (0.0500)  time: 1.0067  data: 0.0004  max mem: 78493
Epoch: [84]  [260/312]  eta: 0:00:56  lr: 0.003494  min_lr: 0.003494  loss: 2.5992 (2.5139)  weight_decay: 0.0500 (0.0500)  time: 1.0055  data: 0.0004  max mem: 78493
Epoch: [84]  [270/312]  eta: 0:00:45  lr: 0.003493  min_lr: 0.003493  loss: 2.4023 (2.5030)  weight_decay: 0.0500 (0.0500)  time: 1.0061  data: 0.0004  max mem: 78493
Epoch: [84]  [280/312]  eta: 0:00:34  lr: 0.003493  min_lr: 0.003493  loss: 2.3854 (2.5022)  weight_decay: 0.0500 (0.0500)  time: 1.0069  data: 0.0010  max mem: 78493
Epoch: [84]  [290/312]  eta: 0:00:23  lr: 0.003492  min_lr: 0.003492  loss: 2.3997 (2.4999)  weight_decay: 0.0500 (0.0500)  time: 1.0037  data: 0.0009  max mem: 78493
Epoch: [84]  [300/312]  eta: 0:00:12  lr: 0.003492  min_lr: 0.003492  loss: 2.5882 (2.5021)  weight_decay: 0.0500 (0.0500)  time: 1.0017  data: 0.0001  max mem: 78493
Epoch: [84]  [310/312]  eta: 0:00:02  lr: 0.003492  min_lr: 0.003492  loss: 2.6532 (2.4998)  weight_decay: 0.0500 (0.0500)  time: 1.0019  data: 0.0001  max mem: 78493
Epoch: [84]  [311/312]  eta: 0:00:01  lr: 0.003491  min_lr: 0.003491  loss: 2.6532 (2.5013)  weight_decay: 0.0500 (0.0500)  time: 1.0019  data: 0.0001  max mem: 78493
Epoch: [84] Total time: 0:05:34 (1.0735 s / it)
Averaged stats: lr: 0.003491  min_lr: 0.003491  loss: 2.6532 (2.4734)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:17  loss: 0.8093 (0.8093)  acc1: 80.8594 (80.8594)  acc5: 93.8802 (93.8802)  time: 8.5870  data: 8.3260  max mem: 78493
Test:  [8/9]  eta: 0:00:01  loss: 1.1542 (1.0850)  acc1: 72.1354 (73.0080)  acc5: 91.7969 (91.2960)  time: 1.1587  data: 0.9252  max mem: 78493
Test: Total time: 0:00:10 (1.2058 s / it)
* Acc@1 72.840 Acc@5 91.384 loss 1.078
Accuracy of the model on the 50000 test images: 72.8%
Max accuracy: 73.18%
Epoch: [85]  [  0/312]  eta: 1:24:51  lr: 0.003491  min_lr: 0.003491  loss: 2.2405 (2.2405)  weight_decay: 0.0500 (0.0500)  time: 16.3179  data: 13.4359  max mem: 78493
Epoch: [85]  [ 10/312]  eta: 0:13:18  lr: 0.003491  min_lr: 0.003491  loss: 2.4803 (2.4840)  weight_decay: 0.0500 (0.0500)  time: 2.6433  data: 1.2320  max mem: 78493
Epoch: [85]  [ 20/312]  eta: 0:09:05  lr: 0.003490  min_lr: 0.003490  loss: 2.5444 (2.5727)  weight_decay: 0.0500 (0.0500)  time: 1.1460  data: 0.0061  max mem: 78493
Epoch: [85]  [ 30/312]  eta: 0:07:28  lr: 0.003490  min_lr: 0.003490  loss: 2.6435 (2.5782)  weight_decay: 0.0500 (0.0500)  time: 1.0099  data: 0.0004  max mem: 78493
Epoch: [85]  [ 40/312]  eta: 0:06:34  lr: 0.003489  min_lr: 0.003489  loss: 2.6235 (2.5569)  weight_decay: 0.0500 (0.0500)  time: 1.0077  data: 0.0004  max mem: 78493
Epoch: [85]  [ 50/312]  eta: 0:05:56  lr: 0.003489  min_lr: 0.003489  loss: 2.6422 (2.5601)  weight_decay: 0.0500 (0.0500)  time: 1.0093  data: 0.0004  max mem: 78493
Epoch: [85]  [ 60/312]  eta: 0:05:28  lr: 0.003489  min_lr: 0.003489  loss: 2.5305 (2.5454)  weight_decay: 0.0500 (0.0500)  time: 1.0070  data: 0.0005  max mem: 78493
Epoch: [85]  [ 70/312]  eta: 0:05:05  lr: 0.003488  min_lr: 0.003488  loss: 2.5305 (2.5433)  weight_decay: 0.0500 (0.0500)  time: 1.0084  data: 0.0005  max mem: 78493
Epoch: [85]  [ 80/312]  eta: 0:04:45  lr: 0.003488  min_lr: 0.003488  loss: 2.5771 (2.5281)  weight_decay: 0.0500 (0.0500)  time: 1.0096  data: 0.0005  max mem: 78493
Epoch: [85]  [ 90/312]  eta: 0:04:27  lr: 0.003487  min_lr: 0.003487  loss: 2.4516 (2.5064)  weight_decay: 0.0500 (0.0500)  time: 1.0080  data: 0.0004  max mem: 78493
Epoch: [85]  [100/312]  eta: 0:04:11  lr: 0.003487  min_lr: 0.003487  loss: 2.3583 (2.4960)  weight_decay: 0.0500 (0.0500)  time: 1.0070  data: 0.0004  max mem: 78493
Epoch: [85]  [110/312]  eta: 0:03:56  lr: 0.003486  min_lr: 0.003486  loss: 2.3357 (2.4888)  weight_decay: 0.0500 (0.0500)  time: 1.0067  data: 0.0004  max mem: 78493
Epoch: [85]  [120/312]  eta: 0:03:42  lr: 0.003486  min_lr: 0.003486  loss: 2.2928 (2.4674)  weight_decay: 0.0500 (0.0500)  time: 1.0075  data: 0.0004  max mem: 78493
Epoch: [85]  [130/312]  eta: 0:03:28  lr: 0.003485  min_lr: 0.003485  loss: 2.3639 (2.4724)  weight_decay: 0.0500 (0.0500)  time: 1.0077  data: 0.0004  max mem: 78493
Epoch: [85]  [140/312]  eta: 0:03:15  lr: 0.003485  min_lr: 0.003485  loss: 2.5579 (2.4906)  weight_decay: 0.0500 (0.0500)  time: 1.0077  data: 0.0004  max mem: 78493
Epoch: [85]  [150/312]  eta: 0:03:02  lr: 0.003484  min_lr: 0.003484  loss: 2.6389 (2.5004)  weight_decay: 0.0500 (0.0500)  time: 1.0088  data: 0.0005  max mem: 78493
Epoch: [85]  [160/312]  eta: 0:02:50  lr: 0.003484  min_lr: 0.003484  loss: 2.6217 (2.5080)  weight_decay: 0.0500 (0.0500)  time: 1.0070  data: 0.0004  max mem: 78493
Epoch: [85]  [170/312]  eta: 0:02:38  lr: 0.003483  min_lr: 0.003483  loss: 2.4489 (2.5085)  weight_decay: 0.0500 (0.0500)  time: 1.0069  data: 0.0004  max mem: 78493
Epoch: [85]  [180/312]  eta: 0:02:26  lr: 0.003483  min_lr: 0.003483  loss: 2.4921 (2.5135)  weight_decay: 0.0500 (0.0500)  time: 1.0056  data: 0.0004  max mem: 78493
Epoch: [85]  [190/312]  eta: 0:02:14  lr: 0.003482  min_lr: 0.003482  loss: 2.5659 (2.5158)  weight_decay: 0.0500 (0.0500)  time: 1.0048  data: 0.0004  max mem: 78493
Epoch: [85]  [200/312]  eta: 0:02:02  lr: 0.003482  min_lr: 0.003482  loss: 2.5646 (2.5159)  weight_decay: 0.0500 (0.0500)  time: 1.0052  data: 0.0005  max mem: 78493
Epoch: [85]  [210/312]  eta: 0:01:51  lr: 0.003481  min_lr: 0.003481  loss: 2.6558 (2.5200)  weight_decay: 0.0500 (0.0500)  time: 1.0044  data: 0.0005  max mem: 78493
Epoch: [85]  [220/312]  eta: 0:01:40  lr: 0.003481  min_lr: 0.003481  loss: 2.4942 (2.5145)  weight_decay: 0.0500 (0.0500)  time: 1.0054  data: 0.0005  max mem: 78493
Epoch: [85]  [230/312]  eta: 0:01:28  lr: 0.003480  min_lr: 0.003480  loss: 2.3455 (2.5131)  weight_decay: 0.0500 (0.0500)  time: 1.0067  data: 0.0004  max mem: 78493
Epoch: [85]  [240/312]  eta: 0:01:17  lr: 0.003480  min_lr: 0.003480  loss: 2.3248 (2.5028)  weight_decay: 0.0500 (0.0500)  time: 1.0064  data: 0.0004  max mem: 78493
Epoch: [85]  [250/312]  eta: 0:01:06  lr: 0.003479  min_lr: 0.003479  loss: 2.3673 (2.5030)  weight_decay: 0.0500 (0.0500)  time: 1.0047  data: 0.0004  max mem: 78493
Epoch: [85]  [260/312]  eta: 0:00:55  lr: 0.003479  min_lr: 0.003479  loss: 2.5045 (2.5040)  weight_decay: 0.0500 (0.0500)  time: 1.0056  data: 0.0004  max mem: 78493
Epoch: [85]  [270/312]  eta: 0:00:45  lr: 0.003478  min_lr: 0.003478  loss: 2.6628 (2.5084)  weight_decay: 0.0500 (0.0500)  time: 1.0062  data: 0.0004  max mem: 78493
Epoch: [85]  [280/312]  eta: 0:00:34  lr: 0.003478  min_lr: 0.003478  loss: 2.6007 (2.5059)  weight_decay: 0.0500 (0.0500)  time: 1.0065  data: 0.0010  max mem: 78493
Epoch: [85]  [290/312]  eta: 0:00:23  lr: 0.003477  min_lr: 0.003477  loss: 2.4786 (2.5090)  weight_decay: 0.0500 (0.0500)  time: 1.0047  data: 0.0009  max mem: 78493
Epoch: [85]  [300/312]  eta: 0:00:12  lr: 0.003477  min_lr: 0.003477  loss: 2.6496 (2.5090)  weight_decay: 0.0500 (0.0500)  time: 1.0014  data: 0.0001  max mem: 78493
Epoch: [85]  [310/312]  eta: 0:00:02  lr: 0.003476  min_lr: 0.003476  loss: 2.6400 (2.5115)  weight_decay: 0.0500 (0.0500)  time: 1.0015  data: 0.0001  max mem: 78493
Epoch: [85]  [311/312]  eta: 0:00:01  lr: 0.003476  min_lr: 0.003476  loss: 2.6341 (2.5089)  weight_decay: 0.0500 (0.0500)  time: 1.0015  data: 0.0001  max mem: 78493
Epoch: [85] Total time: 0:05:33 (1.0700 s / it)
Averaged stats: lr: 0.003476  min_lr: 0.003476  loss: 2.6341 (2.4875)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:09  loss: 0.8456 (0.8456)  acc1: 78.9062 (78.9062)  acc5: 94.2708 (94.2708)  time: 7.7775  data: 7.5019  max mem: 78493
Test:  [8/9]  eta: 0:00:01  loss: 1.1033 (1.0547)  acc1: 73.0469 (72.7520)  acc5: 91.6667 (91.2640)  time: 1.0947  data: 0.8655  max mem: 78493
Test: Total time: 0:00:10 (1.1300 s / it)
* Acc@1 72.708 Acc@5 91.280 loss 1.055
Accuracy of the model on the 50000 test images: 72.7%
Max accuracy: 73.18%
Epoch: [86]  [  0/312]  eta: 1:28:26  lr: 0.003476  min_lr: 0.003476  loss: 1.6268 (1.6268)  weight_decay: 0.0500 (0.0500)  time: 17.0085  data: 13.5203  max mem: 78493
Epoch: [86]  [ 10/312]  eta: 0:13:35  lr: 0.003476  min_lr: 0.003476  loss: 2.2839 (2.2867)  weight_decay: 0.0500 (0.0500)  time: 2.7005  data: 1.2318  max mem: 78493
Epoch: [86]  [ 20/312]  eta: 0:09:13  lr: 0.003475  min_lr: 0.003475  loss: 2.4197 (2.4319)  weight_decay: 0.0500 (0.0500)  time: 1.1387  data: 0.0017  max mem: 78493
Epoch: [86]  [ 30/312]  eta: 0:07:33  lr: 0.003475  min_lr: 0.003475  loss: 2.6553 (2.5119)  weight_decay: 0.0500 (0.0500)  time: 1.0064  data: 0.0004  max mem: 78493
Epoch: [86]  [ 40/312]  eta: 0:06:37  lr: 0.003474  min_lr: 0.003474  loss: 2.6898 (2.5258)  weight_decay: 0.0500 (0.0500)  time: 1.0056  data: 0.0004  max mem: 78493
Epoch: [86]  [ 50/312]  eta: 0:05:59  lr: 0.003474  min_lr: 0.003474  loss: 2.5642 (2.5309)  weight_decay: 0.0500 (0.0500)  time: 1.0057  data: 0.0004  max mem: 78493
Epoch: [86]  [ 60/312]  eta: 0:05:30  lr: 0.003473  min_lr: 0.003473  loss: 2.5642 (2.4894)  weight_decay: 0.0500 (0.0500)  time: 1.0052  data: 0.0004  max mem: 78493
Epoch: [86]  [ 70/312]  eta: 0:05:06  lr: 0.003473  min_lr: 0.003473  loss: 2.5182 (2.5050)  weight_decay: 0.0500 (0.0500)  time: 1.0055  data: 0.0004  max mem: 78493
Epoch: [86]  [ 80/312]  eta: 0:04:46  lr: 0.003472  min_lr: 0.003472  loss: 2.5182 (2.4932)  weight_decay: 0.0500 (0.0500)  time: 1.0082  data: 0.0004  max mem: 78493
Epoch: [86]  [ 90/312]  eta: 0:04:28  lr: 0.003472  min_lr: 0.003472  loss: 2.4842 (2.4946)  weight_decay: 0.0500 (0.0500)  time: 1.0099  data: 0.0004  max mem: 78493
Epoch: [86]  [100/312]  eta: 0:04:12  lr: 0.003472  min_lr: 0.003472  loss: 2.5150 (2.4803)  weight_decay: 0.0500 (0.0500)  time: 1.0080  data: 0.0004  max mem: 78493
Epoch: [86]  [110/312]  eta: 0:03:57  lr: 0.003471  min_lr: 0.003471  loss: 2.4021 (2.4766)  weight_decay: 0.0500 (0.0500)  time: 1.0067  data: 0.0004  max mem: 78493
Epoch: [86]  [120/312]  eta: 0:03:42  lr: 0.003471  min_lr: 0.003471  loss: 2.6025 (2.4854)  weight_decay: 0.0500 (0.0500)  time: 1.0077  data: 0.0015  max mem: 78493
Epoch: [86]  [130/312]  eta: 0:03:29  lr: 0.003470  min_lr: 0.003470  loss: 2.6725 (2.4886)  weight_decay: 0.0500 (0.0500)  time: 1.0081  data: 0.0016  max mem: 78493
Epoch: [86]  [140/312]  eta: 0:03:15  lr: 0.003470  min_lr: 0.003470  loss: 2.5236 (2.4865)  weight_decay: 0.0500 (0.0500)  time: 1.0086  data: 0.0005  max mem: 78493
Epoch: [86]  [150/312]  eta: 0:03:03  lr: 0.003469  min_lr: 0.003469  loss: 2.4870 (2.4801)  weight_decay: 0.0500 (0.0500)  time: 1.0084  data: 0.0004  max mem: 78493
Epoch: [86]  [160/312]  eta: 0:02:50  lr: 0.003469  min_lr: 0.003469  loss: 2.5552 (2.4828)  weight_decay: 0.0500 (0.0500)  time: 1.0055  data: 0.0004  max mem: 78493
Epoch: [86]  [170/312]  eta: 0:02:38  lr: 0.003468  min_lr: 0.003468  loss: 2.5726 (2.4869)  weight_decay: 0.0500 (0.0500)  time: 1.0053  data: 0.0004  max mem: 78493
Epoch: [86]  [180/312]  eta: 0:02:26  lr: 0.003468  min_lr: 0.003468  loss: 2.5186 (2.4814)  weight_decay: 0.0500 (0.0500)  time: 1.0062  data: 0.0004  max mem: 78493
Epoch: [86]  [190/312]  eta: 0:02:14  lr: 0.003467  min_lr: 0.003467  loss: 2.2748 (2.4775)  weight_decay: 0.0500 (0.0500)  time: 1.0059  data: 0.0004  max mem: 78493
Epoch: [86]  [200/312]  eta: 0:02:03  lr: 0.003467  min_lr: 0.003467  loss: 2.5424 (2.4803)  weight_decay: 0.0500 (0.0500)  time: 1.0075  data: 0.0004  max mem: 78493
Epoch: [86]  [210/312]  eta: 0:01:51  lr: 0.003466  min_lr: 0.003466  loss: 2.5432 (2.4769)  weight_decay: 0.0500 (0.0500)  time: 1.0095  data: 0.0004  max mem: 78493
Epoch: [86]  [220/312]  eta: 0:01:40  lr: 0.003466  min_lr: 0.003466  loss: 2.5371 (2.4832)  weight_decay: 0.0500 (0.0500)  time: 1.0088  data: 0.0004  max mem: 78493
Epoch: [86]  [230/312]  eta: 0:01:29  lr: 0.003465  min_lr: 0.003465  loss: 2.5239 (2.4803)  weight_decay: 0.0500 (0.0500)  time: 1.0096  data: 0.0004  max mem: 78493
Epoch: [86]  [240/312]  eta: 0:01:18  lr: 0.003465  min_lr: 0.003465  loss: 2.3492 (2.4742)  weight_decay: 0.0500 (0.0500)  time: 1.0091  data: 0.0004  max mem: 78493
Epoch: [86]  [250/312]  eta: 0:01:07  lr: 0.003464  min_lr: 0.003464  loss: 2.5759 (2.4784)  weight_decay: 0.0500 (0.0500)  time: 1.0059  data: 0.0004  max mem: 78493
Epoch: [86]  [260/312]  eta: 0:00:56  lr: 0.003464  min_lr: 0.003464  loss: 2.6385 (2.4895)  weight_decay: 0.0500 (0.0500)  time: 1.0054  data: 0.0004  max mem: 78493
Epoch: [86]  [270/312]  eta: 0:00:45  lr: 0.003463  min_lr: 0.003463  loss: 2.6300 (2.4896)  weight_decay: 0.0500 (0.0500)  time: 1.0054  data: 0.0004  max mem: 78493
Epoch: [86]  [280/312]  eta: 0:00:34  lr: 0.003463  min_lr: 0.003463  loss: 2.5804 (2.4969)  weight_decay: 0.0500 (0.0500)  time: 1.0059  data: 0.0010  max mem: 78493
Epoch: [86]  [290/312]  eta: 0:00:23  lr: 0.003462  min_lr: 0.003462  loss: 2.6403 (2.5008)  weight_decay: 0.0500 (0.0500)  time: 1.0038  data: 0.0009  max mem: 78493
Epoch: [86]  [300/312]  eta: 0:00:12  lr: 0.003462  min_lr: 0.003462  loss: 2.5465 (2.4996)  weight_decay: 0.0500 (0.0500)  time: 1.0015  data: 0.0001  max mem: 78493
Epoch: [86]  [310/312]  eta: 0:00:02  lr: 0.003461  min_lr: 0.003461  loss: 2.5465 (2.4998)  weight_decay: 0.0500 (0.0500)  time: 1.0017  data: 0.0001  max mem: 78493
Epoch: [86]  [311/312]  eta: 0:00:01  lr: 0.003461  min_lr: 0.003461  loss: 2.5465 (2.4973)  weight_decay: 0.0500 (0.0500)  time: 1.0017  data: 0.0001  max mem: 78493
Epoch: [86] Total time: 0:05:34 (1.0720 s / it)
Averaged stats: lr: 0.003461  min_lr: 0.003461  loss: 2.5465 (2.4645)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:15  loss: 0.7485 (0.7485)  acc1: 80.2083 (80.2083)  acc5: 95.3125 (95.3125)  time: 8.4033  data: 8.1267  max mem: 78493
Test:  [8/9]  eta: 0:00:01  loss: 1.1721 (1.0562)  acc1: 73.5677 (73.3440)  acc5: 91.0156 (91.7120)  time: 1.1319  data: 0.9031  max mem: 78493
Test: Total time: 0:00:10 (1.1439 s / it)
* Acc@1 73.392 Acc@5 91.610 loss 1.052
Accuracy of the model on the 50000 test images: 73.4%
Max accuracy: 73.39%
Epoch: [87]  [  0/312]  eta: 1:22:21  lr: 0.003461  min_lr: 0.003461  loss: 2.3445 (2.3445)  weight_decay: 0.0500 (0.0500)  time: 15.8395  data: 13.5279  max mem: 78493
Epoch: [87]  [ 10/312]  eta: 0:12:43  lr: 0.003461  min_lr: 0.003461  loss: 2.6229 (2.6848)  weight_decay: 0.0500 (0.0500)  time: 2.5297  data: 1.2649  max mem: 78493
Epoch: [87]  [ 20/312]  eta: 0:08:49  lr: 0.003460  min_lr: 0.003460  loss: 2.5871 (2.6193)  weight_decay: 0.0500 (0.0500)  time: 1.1111  data: 0.0196  max mem: 78493
Epoch: [87]  [ 30/312]  eta: 0:07:17  lr: 0.003460  min_lr: 0.003460  loss: 2.4024 (2.5388)  weight_decay: 0.0500 (0.0500)  time: 1.0158  data: 0.0005  max mem: 78493
Epoch: [87]  [ 40/312]  eta: 0:06:26  lr: 0.003459  min_lr: 0.003459  loss: 2.3666 (2.5047)  weight_decay: 0.0500 (0.0500)  time: 1.0078  data: 0.0004  max mem: 78493
Epoch: [87]  [ 50/312]  eta: 0:05:50  lr: 0.003459  min_lr: 0.003459  loss: 2.5883 (2.5117)  weight_decay: 0.0500 (0.0500)  time: 1.0075  data: 0.0004  max mem: 78493
Epoch: [87]  [ 60/312]  eta: 0:05:23  lr: 0.003458  min_lr: 0.003458  loss: 2.6258 (2.5082)  weight_decay: 0.0500 (0.0500)  time: 1.0072  data: 0.0005  max mem: 78493
Epoch: [87]  [ 70/312]  eta: 0:05:01  lr: 0.003458  min_lr: 0.003458  loss: 2.3715 (2.4724)  weight_decay: 0.0500 (0.0500)  time: 1.0076  data: 0.0005  max mem: 78493
Epoch: [87]  [ 80/312]  eta: 0:04:42  lr: 0.003457  min_lr: 0.003457  loss: 2.2742 (2.4552)  weight_decay: 0.0500 (0.0500)  time: 1.0071  data: 0.0004  max mem: 78493
Epoch: [87]  [ 90/312]  eta: 0:04:24  lr: 0.003457  min_lr: 0.003457  loss: 2.1651 (2.4325)  weight_decay: 0.0500 (0.0500)  time: 1.0082  data: 0.0005  max mem: 78493
Epoch: [87]  [100/312]  eta: 0:04:09  lr: 0.003456  min_lr: 0.003456  loss: 2.1178 (2.4153)  weight_decay: 0.0500 (0.0500)  time: 1.0081  data: 0.0005  max mem: 78493
Epoch: [87]  [110/312]  eta: 0:03:54  lr: 0.003456  min_lr: 0.003456  loss: 2.4794 (2.4330)  weight_decay: 0.0500 (0.0500)  time: 1.0068  data: 0.0004  max mem: 78493
Epoch: [87]  [120/312]  eta: 0:03:40  lr: 0.003455  min_lr: 0.003455  loss: 2.6128 (2.4481)  weight_decay: 0.0500 (0.0500)  time: 1.0072  data: 0.0004  max mem: 78493
Epoch: [87]  [130/312]  eta: 0:03:26  lr: 0.003455  min_lr: 0.003455  loss: 2.5233 (2.4500)  weight_decay: 0.0500 (0.0500)  time: 1.0061  data: 0.0004  max mem: 78493
Epoch: [87]  [140/312]  eta: 0:03:13  lr: 0.003454  min_lr: 0.003454  loss: 2.5069 (2.4463)  weight_decay: 0.0500 (0.0500)  time: 1.0055  data: 0.0004  max mem: 78493
Epoch: [87]  [150/312]  eta: 0:03:01  lr: 0.003454  min_lr: 0.003454  loss: 2.5575 (2.4452)  weight_decay: 0.0500 (0.0500)  time: 1.0061  data: 0.0005  max mem: 78493
Epoch: [87]  [160/312]  eta: 0:02:49  lr: 0.003453  min_lr: 0.003453  loss: 2.3842 (2.4427)  weight_decay: 0.0500 (0.0500)  time: 1.0072  data: 0.0005  max mem: 78493
Epoch: [87]  [170/312]  eta: 0:02:37  lr: 0.003453  min_lr: 0.003453  loss: 2.3833 (2.4411)  weight_decay: 0.0500 (0.0500)  time: 1.0080  data: 0.0005  max mem: 78493
Epoch: [87]  [180/312]  eta: 0:02:25  lr: 0.003452  min_lr: 0.003452  loss: 2.6004 (2.4543)  weight_decay: 0.0500 (0.0500)  time: 1.0087  data: 0.0005  max mem: 78493
Epoch: [87]  [190/312]  eta: 0:02:13  lr: 0.003452  min_lr: 0.003452  loss: 2.6015 (2.4524)  weight_decay: 0.0500 (0.0500)  time: 1.0079  data: 0.0005  max mem: 78493
Epoch: [87]  [200/312]  eta: 0:02:02  lr: 0.003451  min_lr: 0.003451  loss: 2.4170 (2.4448)  weight_decay: 0.0500 (0.0500)  time: 1.0064  data: 0.0005  max mem: 78493
Epoch: [87]  [210/312]  eta: 0:01:50  lr: 0.003451  min_lr: 0.003451  loss: 2.3129 (2.4416)  weight_decay: 0.0500 (0.0500)  time: 1.0059  data: 0.0005  max mem: 78493
Epoch: [87]  [220/312]  eta: 0:01:39  lr: 0.003450  min_lr: 0.003450  loss: 2.5573 (2.4470)  weight_decay: 0.0500 (0.0500)  time: 1.0064  data: 0.0004  max mem: 78493
Epoch: [87]  [230/312]  eta: 0:01:28  lr: 0.003450  min_lr: 0.003450  loss: 2.5573 (2.4473)  weight_decay: 0.0500 (0.0500)  time: 1.0071  data: 0.0015  max mem: 78493
Epoch: [87]  [240/312]  eta: 0:01:17  lr: 0.003449  min_lr: 0.003449  loss: 2.3375 (2.4491)  weight_decay: 0.0500 (0.0500)  time: 1.0063  data: 0.0015  max mem: 78493
Epoch: [87]  [250/312]  eta: 0:01:06  lr: 0.003449  min_lr: 0.003449  loss: 2.6125 (2.4551)  weight_decay: 0.0500 (0.0500)  time: 1.0058  data: 0.0004  max mem: 78493
Epoch: [87]  [260/312]  eta: 0:00:55  lr: 0.003448  min_lr: 0.003448  loss: 2.6125 (2.4555)  weight_decay: 0.0500 (0.0500)  time: 1.0064  data: 0.0004  max mem: 78493
Epoch: [87]  [270/312]  eta: 0:00:44  lr: 0.003448  min_lr: 0.003448  loss: 2.5912 (2.4524)  weight_decay: 0.0500 (0.0500)  time: 1.0054  data: 0.0004  max mem: 78493
Epoch: [87]  [280/312]  eta: 0:00:34  lr: 0.003447  min_lr: 0.003447  loss: 2.5912 (2.4529)  weight_decay: 0.0500 (0.0500)  time: 1.0053  data: 0.0011  max mem: 78493
Epoch: [87]  [290/312]  eta: 0:00:23  lr: 0.003447  min_lr: 0.003447  loss: 2.5212 (2.4513)  weight_decay: 0.0500 (0.0500)  time: 1.0046  data: 0.0009  max mem: 78493
Epoch: [87]  [300/312]  eta: 0:00:12  lr: 0.003446  min_lr: 0.003446  loss: 2.5589 (2.4520)  weight_decay: 0.0500 (0.0500)  time: 1.0023  data: 0.0001  max mem: 78493
Epoch: [87]  [310/312]  eta: 0:00:02  lr: 0.003446  min_lr: 0.003446  loss: 2.5899 (2.4533)  weight_decay: 0.0500 (0.0500)  time: 1.0021  data: 0.0001  max mem: 78493
Epoch: [87]  [311/312]  eta: 0:00:01  lr: 0.003446  min_lr: 0.003446  loss: 2.5899 (2.4541)  weight_decay: 0.0500 (0.0500)  time: 1.0021  data: 0.0001  max mem: 78493
Epoch: [87] Total time: 0:05:32 (1.0665 s / it)
Averaged stats: lr: 0.003446  min_lr: 0.003446  loss: 2.5899 (2.4814)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:07  loss: 0.8606 (0.8606)  acc1: 79.2969 (79.2969)  acc5: 93.7500 (93.7500)  time: 7.4803  data: 7.1995  max mem: 78493
Test:  [8/9]  eta: 0:00:01  loss: 1.1940 (1.1435)  acc1: 70.5729 (71.8400)  acc5: 91.1458 (90.9440)  time: 1.0372  data: 0.8000  max mem: 78493
Test: Total time: 0:00:09 (1.0471 s / it)
* Acc@1 72.520 Acc@5 91.096 loss 1.128
Accuracy of the model on the 50000 test images: 72.5%
Max accuracy: 73.39%
Epoch: [88]  [  0/312]  eta: 1:25:46  lr: 0.003446  min_lr: 0.003446  loss: 1.7826 (1.7826)  weight_decay: 0.0500 (0.0500)  time: 16.4950  data: 15.4868  max mem: 78493
Epoch: [88]  [ 10/312]  eta: 0:12:59  lr: 0.003445  min_lr: 0.003445  loss: 2.1802 (2.2551)  weight_decay: 0.0500 (0.0500)  time: 2.5800  data: 1.4191  max mem: 78493
Epoch: [88]  [ 20/312]  eta: 0:08:56  lr: 0.003445  min_lr: 0.003445  loss: 2.3322 (2.3390)  weight_decay: 0.0500 (0.0500)  time: 1.1031  data: 0.0076  max mem: 78493
Epoch: [88]  [ 30/312]  eta: 0:07:22  lr: 0.003444  min_lr: 0.003444  loss: 2.5045 (2.4158)  weight_decay: 0.0500 (0.0500)  time: 1.0126  data: 0.0016  max mem: 78493
Epoch: [88]  [ 40/312]  eta: 0:06:29  lr: 0.003444  min_lr: 0.003444  loss: 2.5390 (2.4373)  weight_decay: 0.0500 (0.0500)  time: 1.0067  data: 0.0004  max mem: 78493
Epoch: [88]  [ 50/312]  eta: 0:05:53  lr: 0.003443  min_lr: 0.003443  loss: 2.5101 (2.4271)  weight_decay: 0.0500 (0.0500)  time: 1.0068  data: 0.0004  max mem: 78493
Epoch: [88]  [ 60/312]  eta: 0:05:25  lr: 0.003443  min_lr: 0.003443  loss: 2.4450 (2.4161)  weight_decay: 0.0500 (0.0500)  time: 1.0064  data: 0.0004  max mem: 78493
Epoch: [88]  [ 70/312]  eta: 0:05:03  lr: 0.003442  min_lr: 0.003442  loss: 2.6038 (2.4293)  weight_decay: 0.0500 (0.0500)  time: 1.0078  data: 0.0004  max mem: 78493
Epoch: [88]  [ 80/312]  eta: 0:04:43  lr: 0.003442  min_lr: 0.003442  loss: 2.6228 (2.4455)  weight_decay: 0.0500 (0.0500)  time: 1.0106  data: 0.0005  max mem: 78493
Epoch: [88]  [ 90/312]  eta: 0:04:26  lr: 0.003441  min_lr: 0.003441  loss: 2.7236 (2.4616)  weight_decay: 0.0500 (0.0500)  time: 1.0095  data: 0.0004  max mem: 78493
Epoch: [88]  [100/312]  eta: 0:04:10  lr: 0.003441  min_lr: 0.003441  loss: 2.7678 (2.4777)  weight_decay: 0.0500 (0.0500)  time: 1.0079  data: 0.0004  max mem: 78493
Epoch: [88]  [110/312]  eta: 0:03:55  lr: 0.003440  min_lr: 0.003440  loss: 2.5439 (2.4663)  weight_decay: 0.0500 (0.0500)  time: 1.0070  data: 0.0004  max mem: 78493
Epoch: [88]  [120/312]  eta: 0:03:41  lr: 0.003440  min_lr: 0.003440  loss: 2.3744 (2.4593)  weight_decay: 0.0500 (0.0500)  time: 1.0061  data: 0.0004  max mem: 78493
Epoch: [88]  [130/312]  eta: 0:03:27  lr: 0.003439  min_lr: 0.003439  loss: 2.3744 (2.4616)  weight_decay: 0.0500 (0.0500)  time: 1.0048  data: 0.0004  max mem: 78493
Epoch: [88]  [140/312]  eta: 0:03:14  lr: 0.003439  min_lr: 0.003439  loss: 2.4397 (2.4555)  weight_decay: 0.0500 (0.0500)  time: 1.0065  data: 0.0004  max mem: 78493
Epoch: [88]  [150/312]  eta: 0:03:01  lr: 0.003438  min_lr: 0.003438  loss: 2.5005 (2.4606)  weight_decay: 0.0500 (0.0500)  time: 1.0078  data: 0.0004  max mem: 78493
Epoch: [88]  [160/312]  eta: 0:02:49  lr: 0.003438  min_lr: 0.003438  loss: 2.4037 (2.4554)  weight_decay: 0.0500 (0.0500)  time: 1.0063  data: 0.0005  max mem: 78493
Epoch: [88]  [170/312]  eta: 0:02:37  lr: 0.003437  min_lr: 0.003437  loss: 2.3645 (2.4513)  weight_decay: 0.0500 (0.0500)  time: 1.0062  data: 0.0005  max mem: 78493
Epoch: [88]  [180/312]  eta: 0:02:25  lr: 0.003437  min_lr: 0.003437  loss: 2.4482 (2.4572)  weight_decay: 0.0500 (0.0500)  time: 1.0075  data: 0.0004  max mem: 78493
Epoch: [88]  [190/312]  eta: 0:02:14  lr: 0.003436  min_lr: 0.003436  loss: 2.3470 (2.4476)  weight_decay: 0.0500 (0.0500)  time: 1.0083  data: 0.0004  max mem: 78493
Epoch: [88]  [200/312]  eta: 0:02:02  lr: 0.003436  min_lr: 0.003436  loss: 2.2744 (2.4525)  weight_decay: 0.0500 (0.0500)  time: 1.0081  data: 0.0004  max mem: 78493
Epoch: [88]  [210/312]  eta: 0:01:51  lr: 0.003435  min_lr: 0.003435  loss: 2.6400 (2.4591)  weight_decay: 0.0500 (0.0500)  time: 1.0079  data: 0.0004  max mem: 78493
Epoch: [88]  [220/312]  eta: 0:01:39  lr: 0.003435  min_lr: 0.003435  loss: 2.4688 (2.4475)  weight_decay: 0.0500 (0.0500)  time: 1.0060  data: 0.0004  max mem: 78493
Epoch: [88]  [230/312]  eta: 0:01:28  lr: 0.003434  min_lr: 0.003434  loss: 2.2522 (2.4507)  weight_decay: 0.0500 (0.0500)  time: 1.0054  data: 0.0005  max mem: 78493
Epoch: [88]  [240/312]  eta: 0:01:17  lr: 0.003434  min_lr: 0.003434  loss: 2.6367 (2.4527)  weight_decay: 0.0500 (0.0500)  time: 1.0055  data: 0.0004  max mem: 78493
Epoch: [88]  [250/312]  eta: 0:01:06  lr: 0.003433  min_lr: 0.003433  loss: 2.5423 (2.4565)  weight_decay: 0.0500 (0.0500)  time: 1.0046  data: 0.0005  max mem: 78493
Epoch: [88]  [260/312]  eta: 0:00:55  lr: 0.003433  min_lr: 0.003433  loss: 2.4404 (2.4522)  weight_decay: 0.0500 (0.0500)  time: 1.0035  data: 0.0005  max mem: 78493
Epoch: [88]  [270/312]  eta: 0:00:44  lr: 0.003432  min_lr: 0.003432  loss: 2.5534 (2.4544)  weight_decay: 0.0500 (0.0500)  time: 1.0030  data: 0.0004  max mem: 78493
Epoch: [88]  [280/312]  eta: 0:00:34  lr: 0.003432  min_lr: 0.003432  loss: 2.4540 (2.4518)  weight_decay: 0.0500 (0.0500)  time: 1.0046  data: 0.0020  max mem: 78493
Epoch: [88]  [290/312]  eta: 0:00:23  lr: 0.003431  min_lr: 0.003431  loss: 2.2934 (2.4536)  weight_decay: 0.0500 (0.0500)  time: 1.0035  data: 0.0019  max mem: 78493
Epoch: [88]  [300/312]  eta: 0:00:12  lr: 0.003431  min_lr: 0.003431  loss: 2.5466 (2.4497)  weight_decay: 0.0500 (0.0500)  time: 1.0011  data: 0.0001  max mem: 78493
Epoch: [88]  [310/312]  eta: 0:00:02  lr: 0.003430  min_lr: 0.003430  loss: 2.3891 (2.4476)  weight_decay: 0.0500 (0.0500)  time: 1.0012  data: 0.0001  max mem: 78493
Epoch: [88]  [311/312]  eta: 0:00:01  lr: 0.003430  min_lr: 0.003430  loss: 2.3500 (2.4451)  weight_decay: 0.0500 (0.0500)  time: 1.0011  data: 0.0001  max mem: 78493
Epoch: [88] Total time: 0:05:33 (1.0676 s / it)
Averaged stats: lr: 0.003430  min_lr: 0.003430  loss: 2.3500 (2.4779)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:12  loss: 0.7979 (0.7979)  acc1: 80.2083 (80.2083)  acc5: 94.1406 (94.1406)  time: 8.0359  data: 7.7714  max mem: 78493
Test:  [8/9]  eta: 0:00:01  loss: 1.1713 (1.0578)  acc1: 71.3542 (72.9920)  acc5: 91.7969 (91.6800)  time: 1.0911  data: 0.8636  max mem: 78493
Test: Total time: 0:00:09 (1.1011 s / it)
* Acc@1 72.988 Acc@5 91.670 loss 1.058
Accuracy of the model on the 50000 test images: 73.0%
Max accuracy: 73.39%
Epoch: [89]  [  0/312]  eta: 1:28:48  lr: 0.003430  min_lr: 0.003430  loss: 2.9985 (2.9985)  weight_decay: 0.0500 (0.0500)  time: 17.0793  data: 14.3047  max mem: 78493
Epoch: [89]  [ 10/312]  eta: 0:13:19  lr: 0.003430  min_lr: 0.003430  loss: 2.6558 (2.5567)  weight_decay: 0.0500 (0.0500)  time: 2.6478  data: 1.3011  max mem: 78493
Epoch: [89]  [ 20/312]  eta: 0:09:06  lr: 0.003429  min_lr: 0.003429  loss: 2.4712 (2.4976)  weight_decay: 0.0500 (0.0500)  time: 1.1098  data: 0.0006  max mem: 78493
Epoch: [89]  [ 30/312]  eta: 0:07:28  lr: 0.003429  min_lr: 0.003429  loss: 2.3490 (2.4752)  weight_decay: 0.0500 (0.0500)  time: 1.0113  data: 0.0005  max mem: 78493
Epoch: [89]  [ 40/312]  eta: 0:06:34  lr: 0.003428  min_lr: 0.003428  loss: 2.5086 (2.5077)  weight_decay: 0.0500 (0.0500)  time: 1.0066  data: 0.0004  max mem: 78493
Epoch: [89]  [ 50/312]  eta: 0:05:57  lr: 0.003428  min_lr: 0.003428  loss: 2.6340 (2.4946)  weight_decay: 0.0500 (0.0500)  time: 1.0072  data: 0.0004  max mem: 78493
Epoch: [89]  [ 60/312]  eta: 0:05:28  lr: 0.003427  min_lr: 0.003427  loss: 2.6340 (2.5050)  weight_decay: 0.0500 (0.0500)  time: 1.0079  data: 0.0004  max mem: 78493
Epoch: [89]  [ 70/312]  eta: 0:05:05  lr: 0.003427  min_lr: 0.003427  loss: 2.6348 (2.5019)  weight_decay: 0.0500 (0.0500)  time: 1.0074  data: 0.0012  max mem: 78493
Epoch: [89]  [ 80/312]  eta: 0:04:45  lr: 0.003426  min_lr: 0.003426  loss: 2.6378 (2.5130)  weight_decay: 0.0500 (0.0500)  time: 1.0080  data: 0.0012  max mem: 78493
Epoch: [89]  [ 90/312]  eta: 0:04:27  lr: 0.003426  min_lr: 0.003426  loss: 2.6413 (2.5289)  weight_decay: 0.0500 (0.0500)  time: 1.0097  data: 0.0005  max mem: 78493
Epoch: [89]  [100/312]  eta: 0:04:11  lr: 0.003425  min_lr: 0.003425  loss: 2.7165 (2.5374)  weight_decay: 0.0500 (0.0500)  time: 1.0093  data: 0.0005  max mem: 78493
Epoch: [89]  [110/312]  eta: 0:03:56  lr: 0.003425  min_lr: 0.003425  loss: 2.7738 (2.5408)  weight_decay: 0.0500 (0.0500)  time: 1.0071  data: 0.0004  max mem: 78493
Epoch: [89]  [120/312]  eta: 0:03:42  lr: 0.003424  min_lr: 0.003424  loss: 2.5657 (2.5293)  weight_decay: 0.0500 (0.0500)  time: 1.0060  data: 0.0004  max mem: 78493
Epoch: [89]  [130/312]  eta: 0:03:28  lr: 0.003424  min_lr: 0.003424  loss: 2.3669 (2.5103)  weight_decay: 0.0500 (0.0500)  time: 1.0055  data: 0.0004  max mem: 78493
Epoch: [89]  [140/312]  eta: 0:03:15  lr: 0.003423  min_lr: 0.003423  loss: 2.3023 (2.4923)  weight_decay: 0.0500 (0.0500)  time: 1.0053  data: 0.0004  max mem: 78493
Epoch: [89]  [150/312]  eta: 0:03:02  lr: 0.003423  min_lr: 0.003423  loss: 2.3944 (2.4907)  weight_decay: 0.0500 (0.0500)  time: 1.0059  data: 0.0005  max mem: 78493
Epoch: [89]  [160/312]  eta: 0:02:50  lr: 0.003422  min_lr: 0.003422  loss: 2.4489 (2.4893)  weight_decay: 0.0500 (0.0500)  time: 1.0055  data: 0.0011  max mem: 78493
Epoch: [89]  [170/312]  eta: 0:02:38  lr: 0.003422  min_lr: 0.003422  loss: 2.4298 (2.4809)  weight_decay: 0.0500 (0.0500)  time: 1.0057  data: 0.0010  max mem: 78493
Epoch: [89]  [180/312]  eta: 0:02:26  lr: 0.003421  min_lr: 0.003421  loss: 2.4984 (2.4856)  weight_decay: 0.0500 (0.0500)  time: 1.0069  data: 0.0005  max mem: 78493
Epoch: [89]  [190/312]  eta: 0:02:14  lr: 0.003421  min_lr: 0.003421  loss: 2.3668 (2.4770)  weight_decay: 0.0500 (0.0500)  time: 1.0070  data: 0.0004  max mem: 78493
Epoch: [89]  [200/312]  eta: 0:02:02  lr: 0.003420  min_lr: 0.003420  loss: 2.5240 (2.4838)  weight_decay: 0.0500 (0.0500)  time: 1.0059  data: 0.0004  max mem: 78493
Epoch: [89]  [210/312]  eta: 0:01:51  lr: 0.003420  min_lr: 0.003420  loss: 2.6332 (2.4866)  weight_decay: 0.0500 (0.0500)  time: 1.0040  data: 0.0004  max mem: 78493
Epoch: [89]  [220/312]  eta: 0:01:40  lr: 0.003419  min_lr: 0.003419  loss: 2.4693 (2.4797)  weight_decay: 0.0500 (0.0500)  time: 1.0049  data: 0.0004  max mem: 78493
Epoch: [89]  [230/312]  eta: 0:01:28  lr: 0.003419  min_lr: 0.003419  loss: 2.3697 (2.4815)  weight_decay: 0.0500 (0.0500)  time: 1.0059  data: 0.0004  max mem: 78493
Epoch: [89]  [240/312]  eta: 0:01:17  lr: 0.003418  min_lr: 0.003418  loss: 2.6289 (2.4839)  weight_decay: 0.0500 (0.0500)  time: 1.0055  data: 0.0004  max mem: 78493
Epoch: [89]  [250/312]  eta: 0:01:06  lr: 0.003418  min_lr: 0.003418  loss: 2.4932 (2.4809)  weight_decay: 0.0500 (0.0500)  time: 1.0046  data: 0.0004  max mem: 78493
Epoch: [89]  [260/312]  eta: 0:00:55  lr: 0.003417  min_lr: 0.003417  loss: 2.2918 (2.4717)  weight_decay: 0.0500 (0.0500)  time: 1.0038  data: 0.0005  max mem: 78493
Epoch: [89]  [270/312]  eta: 0:00:45  lr: 0.003416  min_lr: 0.003416  loss: 2.4310 (2.4743)  weight_decay: 0.0500 (0.0500)  time: 1.0039  data: 0.0004  max mem: 78493
Epoch: [89]  [280/312]  eta: 0:00:34  lr: 0.003416  min_lr: 0.003416  loss: 2.6159 (2.4765)  weight_decay: 0.0500 (0.0500)  time: 1.0048  data: 0.0010  max mem: 78493
Epoch: [89]  [290/312]  eta: 0:00:23  lr: 0.003415  min_lr: 0.003415  loss: 2.5156 (2.4771)  weight_decay: 0.0500 (0.0500)  time: 1.0039  data: 0.0009  max mem: 78493
Epoch: [89]  [300/312]  eta: 0:00:12  lr: 0.003415  min_lr: 0.003415  loss: 2.3524 (2.4717)  weight_decay: 0.0500 (0.0500)  time: 1.0019  data: 0.0001  max mem: 78493
Epoch: [89]  [310/312]  eta: 0:00:02  lr: 0.003414  min_lr: 0.003414  loss: 2.5845 (2.4767)  weight_decay: 0.0500 (0.0500)  time: 1.0020  data: 0.0001  max mem: 78493
Epoch: [89]  [311/312]  eta: 0:00:01  lr: 0.003414  min_lr: 0.003414  loss: 2.4840 (2.4749)  weight_decay: 0.0500 (0.0500)  time: 1.0020  data: 0.0001  max mem: 78493
Epoch: [89] Total time: 0:05:33 (1.0698 s / it)
Averaged stats: lr: 0.003414  min_lr: 0.003414  loss: 2.4840 (2.4585)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:11  loss: 0.9055 (0.9055)  acc1: 77.6042 (77.6042)  acc5: 94.6615 (94.6615)  time: 7.9623  data: 7.6945  max mem: 78493
Test:  [8/9]  eta: 0:00:01  loss: 1.0754 (1.0888)  acc1: 73.5677 (72.6720)  acc5: 92.9688 (91.7280)  time: 1.0965  data: 0.8550  max mem: 78493
Test: Total time: 0:00:10 (1.1285 s / it)
* Acc@1 73.272 Acc@5 91.478 loss 1.090
Accuracy of the model on the 50000 test images: 73.3%
Max accuracy: 73.39%
Epoch: [90]  [  0/312]  eta: 1:23:48  lr: 0.003414  min_lr: 0.003414  loss: 2.0391 (2.0391)  weight_decay: 0.0500 (0.0500)  time: 16.1167  data: 13.9148  max mem: 78493
Epoch: [90]  [ 10/312]  eta: 0:13:22  lr: 0.003414  min_lr: 0.003414  loss: 2.6747 (2.7119)  weight_decay: 0.0500 (0.0500)  time: 2.6565  data: 1.3487  max mem: 78493
Epoch: [90]  [ 20/312]  eta: 0:09:07  lr: 0.003413  min_lr: 0.003413  loss: 2.6259 (2.4865)  weight_decay: 0.0500 (0.0500)  time: 1.1647  data: 0.0463  max mem: 78493
Epoch: [90]  [ 30/312]  eta: 0:07:30  lr: 0.003413  min_lr: 0.003413  loss: 2.3662 (2.4724)  weight_decay: 0.0500 (0.0500)  time: 1.0149  data: 0.0005  max mem: 78493
Epoch: [90]  [ 40/312]  eta: 0:06:35  lr: 0.003412  min_lr: 0.003412  loss: 2.3851 (2.4481)  weight_decay: 0.0500 (0.0500)  time: 1.0086  data: 0.0004  max mem: 78493
Epoch: [90]  [ 50/312]  eta: 0:05:57  lr: 0.003412  min_lr: 0.003412  loss: 2.3851 (2.4414)  weight_decay: 0.0500 (0.0500)  time: 1.0057  data: 0.0005  max mem: 78493
Epoch: [90]  [ 60/312]  eta: 0:05:29  lr: 0.003411  min_lr: 0.003411  loss: 2.2755 (2.4002)  weight_decay: 0.0500 (0.0500)  time: 1.0059  data: 0.0005  max mem: 78493
Epoch: [90]  [ 70/312]  eta: 0:05:05  lr: 0.003411  min_lr: 0.003411  loss: 2.5259 (2.4367)  weight_decay: 0.0500 (0.0500)  time: 1.0071  data: 0.0005  max mem: 78493
Epoch: [90]  [ 80/312]  eta: 0:04:45  lr: 0.003410  min_lr: 0.003410  loss: 2.6758 (2.4282)  weight_decay: 0.0500 (0.0500)  time: 1.0062  data: 0.0005  max mem: 78493
Epoch: [90]  [ 90/312]  eta: 0:04:28  lr: 0.003410  min_lr: 0.003410  loss: 2.5873 (2.4364)  weight_decay: 0.0500 (0.0500)  time: 1.0067  data: 0.0005  max mem: 78493
Epoch: [90]  [100/312]  eta: 0:04:11  lr: 0.003409  min_lr: 0.003409  loss: 2.5329 (2.4457)  weight_decay: 0.0500 (0.0500)  time: 1.0074  data: 0.0005  max mem: 78493
Epoch: [90]  [110/312]  eta: 0:03:56  lr: 0.003409  min_lr: 0.003409  loss: 2.4725 (2.4406)  weight_decay: 0.0500 (0.0500)  time: 1.0052  data: 0.0004  max mem: 78493
Epoch: [90]  [120/312]  eta: 0:03:42  lr: 0.003408  min_lr: 0.003408  loss: 2.4725 (2.4332)  weight_decay: 0.0500 (0.0500)  time: 1.0059  data: 0.0004  max mem: 78493
Epoch: [90]  [130/312]  eta: 0:03:28  lr: 0.003408  min_lr: 0.003408  loss: 2.4782 (2.4345)  weight_decay: 0.0500 (0.0500)  time: 1.0073  data: 0.0004  max mem: 78493
Epoch: [90]  [140/312]  eta: 0:03:15  lr: 0.003407  min_lr: 0.003407  loss: 2.2940 (2.4230)  weight_decay: 0.0500 (0.0500)  time: 1.0070  data: 0.0004  max mem: 78493
Epoch: [90]  [150/312]  eta: 0:03:02  lr: 0.003407  min_lr: 0.003407  loss: 2.4937 (2.4419)  weight_decay: 0.0500 (0.0500)  time: 1.0083  data: 0.0004  max mem: 78493
Epoch: [90]  [160/312]  eta: 0:02:50  lr: 0.003406  min_lr: 0.003406  loss: 2.6425 (2.4364)  weight_decay: 0.0500 (0.0500)  time: 1.0069  data: 0.0004  max mem: 78493
Epoch: [90]  [170/312]  eta: 0:02:38  lr: 0.003406  min_lr: 0.003406  loss: 2.5236 (2.4356)  weight_decay: 0.0500 (0.0500)  time: 1.0052  data: 0.0004  max mem: 78493
Epoch: [90]  [180/312]  eta: 0:02:26  lr: 0.003405  min_lr: 0.003405  loss: 2.5461 (2.4458)  weight_decay: 0.0500 (0.0500)  time: 1.0054  data: 0.0004  max mem: 78493
Epoch: [90]  [190/312]  eta: 0:02:14  lr: 0.003405  min_lr: 0.003405  loss: 2.5581 (2.4516)  weight_decay: 0.0500 (0.0500)  time: 1.0057  data: 0.0005  max mem: 78493
Epoch: [90]  [200/312]  eta: 0:02:02  lr: 0.003404  min_lr: 0.003404  loss: 2.5176 (2.4558)  weight_decay: 0.0500 (0.0500)  time: 1.0087  data: 0.0005  max mem: 78493
Epoch: [90]  [210/312]  eta: 0:01:51  lr: 0.003404  min_lr: 0.003404  loss: 2.3949 (2.4490)  weight_decay: 0.0500 (0.0500)  time: 1.0081  data: 0.0004  max mem: 78493
Epoch: [90]  [220/312]  eta: 0:01:40  lr: 0.003403  min_lr: 0.003403  loss: 2.4236 (2.4462)  weight_decay: 0.0500 (0.0500)  time: 1.0064  data: 0.0004  max mem: 78493
Epoch: [90]  [230/312]  eta: 0:01:29  lr: 0.003403  min_lr: 0.003403  loss: 2.4952 (2.4498)  weight_decay: 0.0500 (0.0500)  time: 1.0070  data: 0.0004  max mem: 78493
Epoch: [90]  [240/312]  eta: 0:01:17  lr: 0.003402  min_lr: 0.003402  loss: 2.4952 (2.4469)  weight_decay: 0.0500 (0.0500)  time: 1.0067  data: 0.0004  max mem: 78493
Epoch: [90]  [250/312]  eta: 0:01:06  lr: 0.003402  min_lr: 0.003402  loss: 2.4472 (2.4499)  weight_decay: 0.0500 (0.0500)  time: 1.0067  data: 0.0004  max mem: 78493
Epoch: [90]  [260/312]  eta: 0:00:55  lr: 0.003401  min_lr: 0.003401  loss: 2.4472 (2.4470)  weight_decay: 0.0500 (0.0500)  time: 1.0059  data: 0.0004  max mem: 78493
Epoch: [90]  [270/312]  eta: 0:00:45  lr: 0.003401  min_lr: 0.003401  loss: 2.3928 (2.4378)  weight_decay: 0.0500 (0.0500)  time: 1.0064  data: 0.0004  max mem: 78493
Epoch: [90]  [280/312]  eta: 0:00:34  lr: 0.003400  min_lr: 0.003400  loss: 2.5396 (2.4447)  weight_decay: 0.0500 (0.0500)  time: 1.0085  data: 0.0010  max mem: 78493
Epoch: [90]  [290/312]  eta: 0:00:23  lr: 0.003400  min_lr: 0.003400  loss: 2.6725 (2.4495)  weight_decay: 0.0500 (0.0500)  time: 1.0060  data: 0.0009  max mem: 78493
Epoch: [90]  [300/312]  eta: 0:00:12  lr: 0.003399  min_lr: 0.003399  loss: 2.4059 (2.4478)  weight_decay: 0.0500 (0.0500)  time: 1.0022  data: 0.0001  max mem: 78493
Epoch: [90]  [310/312]  eta: 0:00:02  lr: 0.003399  min_lr: 0.003399  loss: 2.3686 (2.4445)  weight_decay: 0.0500 (0.0500)  time: 1.0021  data: 0.0001  max mem: 78493
Epoch: [90]  [311/312]  eta: 0:00:01  lr: 0.003398  min_lr: 0.003398  loss: 2.3686 (2.4431)  weight_decay: 0.0500 (0.0500)  time: 1.0021  data: 0.0001  max mem: 78493
Epoch: [90] Total time: 0:05:34 (1.0711 s / it)
Averaged stats: lr: 0.003398  min_lr: 0.003398  loss: 2.3686 (2.4619)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:17  loss: 0.8436 (0.8436)  acc1: 78.1250 (78.1250)  acc5: 93.8802 (93.8802)  time: 8.5674  data: 8.2872  max mem: 78493
Test:  [8/9]  eta: 0:00:01  loss: 1.1702 (1.0950)  acc1: 71.8750 (72.3680)  acc5: 90.7552 (90.7840)  time: 1.1501  data: 0.9209  max mem: 78493
Test: Total time: 0:00:10 (1.1658 s / it)
* Acc@1 72.972 Acc@5 90.998 loss 1.082
Accuracy of the model on the 50000 test images: 73.0%
Max accuracy: 73.39%
Epoch: [91]  [  0/312]  eta: 1:25:27  lr: 0.003398  min_lr: 0.003398  loss: 2.3531 (2.3531)  weight_decay: 0.0500 (0.0500)  time: 16.4331  data: 14.6403  max mem: 78493
Epoch: [91]  [ 10/312]  eta: 0:13:16  lr: 0.003398  min_lr: 0.003398  loss: 2.5615 (2.3852)  weight_decay: 0.0500 (0.0500)  time: 2.6385  data: 1.3364  max mem: 78493
Epoch: [91]  [ 20/312]  eta: 0:09:04  lr: 0.003397  min_lr: 0.003397  loss: 2.4853 (2.3973)  weight_decay: 0.0500 (0.0500)  time: 1.1365  data: 0.0032  max mem: 78493
Epoch: [91]  [ 30/312]  eta: 0:07:28  lr: 0.003397  min_lr: 0.003397  loss: 2.4479 (2.4190)  weight_decay: 0.0500 (0.0500)  time: 1.0114  data: 0.0005  max mem: 78493
Epoch: [91]  [ 40/312]  eta: 0:06:33  lr: 0.003396  min_lr: 0.003396  loss: 2.5369 (2.4215)  weight_decay: 0.0500 (0.0500)  time: 1.0069  data: 0.0004  max mem: 78493
Epoch: [91]  [ 50/312]  eta: 0:05:56  lr: 0.003396  min_lr: 0.003396  loss: 2.3264 (2.4006)  weight_decay: 0.0500 (0.0500)  time: 1.0059  data: 0.0004  max mem: 78493
Epoch: [91]  [ 60/312]  eta: 0:05:28  lr: 0.003395  min_lr: 0.003395  loss: 2.2769 (2.3985)  weight_decay: 0.0500 (0.0500)  time: 1.0066  data: 0.0004  max mem: 78493
Epoch: [91]  [ 70/312]  eta: 0:05:05  lr: 0.003395  min_lr: 0.003395  loss: 2.5036 (2.4155)  weight_decay: 0.0500 (0.0500)  time: 1.0071  data: 0.0004  max mem: 78493
Epoch: [91]  [ 80/312]  eta: 0:04:45  lr: 0.003394  min_lr: 0.003394  loss: 2.5972 (2.4208)  weight_decay: 0.0500 (0.0500)  time: 1.0072  data: 0.0004  max mem: 78493
Epoch: [91]  [ 90/312]  eta: 0:04:27  lr: 0.003394  min_lr: 0.003394  loss: 2.5117 (2.4135)  weight_decay: 0.0500 (0.0500)  time: 1.0064  data: 0.0004  max mem: 78493
Epoch: [91]  [100/312]  eta: 0:04:11  lr: 0.003393  min_lr: 0.003393  loss: 2.5117 (2.4238)  weight_decay: 0.0500 (0.0500)  time: 1.0077  data: 0.0005  max mem: 78493
Epoch: [91]  [110/312]  eta: 0:03:56  lr: 0.003393  min_lr: 0.003393  loss: 2.6589 (2.4286)  weight_decay: 0.0500 (0.0500)  time: 1.0073  data: 0.0005  max mem: 78493
Epoch: [91]  [120/312]  eta: 0:03:41  lr: 0.003392  min_lr: 0.003392  loss: 2.6451 (2.4434)  weight_decay: 0.0500 (0.0500)  time: 1.0060  data: 0.0004  max mem: 78493
Epoch: [91]  [130/312]  eta: 0:03:28  lr: 0.003392  min_lr: 0.003392  loss: 2.4681 (2.4389)  weight_decay: 0.0500 (0.0500)  time: 1.0075  data: 0.0011  max mem: 78493
Epoch: [91]  [140/312]  eta: 0:03:15  lr: 0.003391  min_lr: 0.003391  loss: 2.4499 (2.4363)  weight_decay: 0.0500 (0.0500)  time: 1.0067  data: 0.0011  max mem: 78493
Epoch: [91]  [150/312]  eta: 0:03:02  lr: 0.003391  min_lr: 0.003391  loss: 2.4794 (2.4428)  weight_decay: 0.0500 (0.0500)  time: 1.0066  data: 0.0004  max mem: 78493
Epoch: [91]  [160/312]  eta: 0:02:50  lr: 0.003390  min_lr: 0.003390  loss: 2.3806 (2.4435)  weight_decay: 0.0500 (0.0500)  time: 1.0075  data: 0.0005  max mem: 78493
Epoch: [91]  [170/312]  eta: 0:02:37  lr: 0.003390  min_lr: 0.003390  loss: 2.5460 (2.4522)  weight_decay: 0.0500 (0.0500)  time: 1.0066  data: 0.0005  max mem: 78493
Epoch: [91]  [180/312]  eta: 0:02:26  lr: 0.003389  min_lr: 0.003389  loss: 2.5607 (2.4475)  weight_decay: 0.0500 (0.0500)  time: 1.0056  data: 0.0005  max mem: 78493
Epoch: [91]  [190/312]  eta: 0:02:14  lr: 0.003389  min_lr: 0.003389  loss: 2.5591 (2.4527)  weight_decay: 0.0500 (0.0500)  time: 1.0047  data: 0.0004  max mem: 78493
Epoch: [91]  [200/312]  eta: 0:02:02  lr: 0.003388  min_lr: 0.003388  loss: 2.5108 (2.4518)  weight_decay: 0.0500 (0.0500)  time: 1.0050  data: 0.0004  max mem: 78493
Epoch: [91]  [210/312]  eta: 0:01:51  lr: 0.003388  min_lr: 0.003388  loss: 2.5894 (2.4560)  weight_decay: 0.0500 (0.0500)  time: 1.0054  data: 0.0004  max mem: 78493
Epoch: [91]  [220/312]  eta: 0:01:40  lr: 0.003387  min_lr: 0.003387  loss: 2.6121 (2.4623)  weight_decay: 0.0500 (0.0500)  time: 1.0047  data: 0.0005  max mem: 78493
Epoch: [91]  [230/312]  eta: 0:01:28  lr: 0.003387  min_lr: 0.003387  loss: 2.6609 (2.4748)  weight_decay: 0.0500 (0.0500)  time: 1.0044  data: 0.0005  max mem: 78493
Epoch: [91]  [240/312]  eta: 0:01:17  lr: 0.003386  min_lr: 0.003386  loss: 2.6609 (2.4713)  weight_decay: 0.0500 (0.0500)  time: 1.0049  data: 0.0004  max mem: 78493
Epoch: [91]  [250/312]  eta: 0:01:06  lr: 0.003385  min_lr: 0.003385  loss: 2.5783 (2.4717)  weight_decay: 0.0500 (0.0500)  time: 1.0046  data: 0.0005  max mem: 78493
Epoch: [91]  [260/312]  eta: 0:00:55  lr: 0.003385  min_lr: 0.003385  loss: 2.4970 (2.4714)  weight_decay: 0.0500 (0.0500)  time: 1.0039  data: 0.0005  max mem: 78493
Epoch: [91]  [270/312]  eta: 0:00:45  lr: 0.003384  min_lr: 0.003384  loss: 2.5079 (2.4766)  weight_decay: 0.0500 (0.0500)  time: 1.0043  data: 0.0005  max mem: 78493
Epoch: [91]  [280/312]  eta: 0:00:34  lr: 0.003384  min_lr: 0.003384  loss: 2.4195 (2.4722)  weight_decay: 0.0500 (0.0500)  time: 1.0048  data: 0.0010  max mem: 78493
Epoch: [91]  [290/312]  eta: 0:00:23  lr: 0.003383  min_lr: 0.003383  loss: 2.4051 (2.4737)  weight_decay: 0.0500 (0.0500)  time: 1.0040  data: 0.0009  max mem: 78493
Epoch: [91]  [300/312]  eta: 0:00:12  lr: 0.003383  min_lr: 0.003383  loss: 2.4836 (2.4769)  weight_decay: 0.0500 (0.0500)  time: 1.0026  data: 0.0001  max mem: 78493
Epoch: [91]  [310/312]  eta: 0:00:02  lr: 0.003382  min_lr: 0.003382  loss: 2.6153 (2.4800)  weight_decay: 0.0500 (0.0500)  time: 1.0020  data: 0.0001  max mem: 78493
Epoch: [91]  [311/312]  eta: 0:00:01  lr: 0.003382  min_lr: 0.003382  loss: 2.6153 (2.4811)  weight_decay: 0.0500 (0.0500)  time: 1.0020  data: 0.0001  max mem: 78493
Epoch: [91] Total time: 0:05:33 (1.0691 s / it)
Averaged stats: lr: 0.003382  min_lr: 0.003382  loss: 2.6153 (2.4596)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:13  loss: 0.7865 (0.7865)  acc1: 81.6406 (81.6406)  acc5: 95.0521 (95.0521)  time: 8.1947  data: 7.9145  max mem: 78493
Test:  [8/9]  eta: 0:00:01  loss: 1.1628 (1.0859)  acc1: 70.7031 (73.2320)  acc5: 90.6250 (91.4240)  time: 1.1088  data: 0.8795  max mem: 78493
Test: Total time: 0:00:10 (1.1527 s / it)
* Acc@1 73.060 Acc@5 91.348 loss 1.078
Accuracy of the model on the 50000 test images: 73.1%
Max accuracy: 73.39%
Epoch: [92]  [  0/312]  eta: 1:24:38  lr: 0.003382  min_lr: 0.003382  loss: 2.8259 (2.8259)  weight_decay: 0.0500 (0.0500)  time: 16.2778  data: 15.0330  max mem: 78493
Epoch: [92]  [ 10/312]  eta: 0:12:35  lr: 0.003382  min_lr: 0.003382  loss: 2.5320 (2.3931)  weight_decay: 0.0500 (0.0500)  time: 2.5015  data: 1.3700  max mem: 78493
Epoch: [92]  [ 20/312]  eta: 0:08:47  lr: 0.003381  min_lr: 0.003381  loss: 2.5681 (2.4793)  weight_decay: 0.0500 (0.0500)  time: 1.0832  data: 0.0065  max mem: 78493
Epoch: [92]  [ 30/312]  eta: 0:07:17  lr: 0.003381  min_lr: 0.003381  loss: 2.7158 (2.5389)  weight_decay: 0.0500 (0.0500)  time: 1.0266  data: 0.0049  max mem: 78493
Epoch: [92]  [ 40/312]  eta: 0:06:25  lr: 0.003380  min_lr: 0.003380  loss: 2.5729 (2.4906)  weight_decay: 0.0500 (0.0500)  time: 1.0084  data: 0.0015  max mem: 78493
Epoch: [92]  [ 50/312]  eta: 0:05:50  lr: 0.003380  min_lr: 0.003380  loss: 2.5185 (2.5018)  weight_decay: 0.0500 (0.0500)  time: 1.0066  data: 0.0016  max mem: 78493
Epoch: [92]  [ 60/312]  eta: 0:05:23  lr: 0.003379  min_lr: 0.003379  loss: 2.4837 (2.4590)  weight_decay: 0.0500 (0.0500)  time: 1.0063  data: 0.0005  max mem: 78493
Epoch: [92]  [ 70/312]  eta: 0:05:01  lr: 0.003379  min_lr: 0.003379  loss: 2.3885 (2.4361)  weight_decay: 0.0500 (0.0500)  time: 1.0085  data: 0.0004  max mem: 78493
Epoch: [92]  [ 80/312]  eta: 0:04:41  lr: 0.003378  min_lr: 0.003378  loss: 2.3754 (2.4289)  weight_decay: 0.0500 (0.0500)  time: 1.0099  data: 0.0005  max mem: 78493
Epoch: [92]  [ 90/312]  eta: 0:04:24  lr: 0.003378  min_lr: 0.003378  loss: 2.5066 (2.4358)  weight_decay: 0.0500 (0.0500)  time: 1.0086  data: 0.0005  max mem: 78493
Epoch: [92]  [100/312]  eta: 0:04:08  lr: 0.003377  min_lr: 0.003377  loss: 2.5883 (2.4386)  weight_decay: 0.0500 (0.0500)  time: 1.0090  data: 0.0004  max mem: 78493
Epoch: [92]  [110/312]  eta: 0:03:54  lr: 0.003377  min_lr: 0.003377  loss: 2.5390 (2.4347)  weight_decay: 0.0500 (0.0500)  time: 1.0083  data: 0.0004  max mem: 78493
Epoch: [92]  [120/312]  eta: 0:03:40  lr: 0.003376  min_lr: 0.003376  loss: 2.4528 (2.4362)  weight_decay: 0.0500 (0.0500)  time: 1.0074  data: 0.0004  max mem: 78493
Epoch: [92]  [130/312]  eta: 0:03:26  lr: 0.003376  min_lr: 0.003376  loss: 2.5251 (2.4402)  weight_decay: 0.0500 (0.0500)  time: 1.0084  data: 0.0005  max mem: 78493
Epoch: [92]  [140/312]  eta: 0:03:13  lr: 0.003375  min_lr: 0.003375  loss: 2.4693 (2.4329)  weight_decay: 0.0500 (0.0500)  time: 1.0087  data: 0.0004  max mem: 78493
Epoch: [92]  [150/312]  eta: 0:03:01  lr: 0.003374  min_lr: 0.003374  loss: 2.4693 (2.4437)  weight_decay: 0.0500 (0.0500)  time: 1.0075  data: 0.0004  max mem: 78493
Epoch: [92]  [160/312]  eta: 0:02:49  lr: 0.003374  min_lr: 0.003374  loss: 2.7289 (2.4564)  weight_decay: 0.0500 (0.0500)  time: 1.0060  data: 0.0004  max mem: 78493
Epoch: [92]  [170/312]  eta: 0:02:37  lr: 0.003373  min_lr: 0.003373  loss: 2.7287 (2.4667)  weight_decay: 0.0500 (0.0500)  time: 1.0079  data: 0.0004  max mem: 78493
Epoch: [92]  [180/312]  eta: 0:02:25  lr: 0.003373  min_lr: 0.003373  loss: 2.5057 (2.4619)  weight_decay: 0.0500 (0.0500)  time: 1.0083  data: 0.0004  max mem: 78493
Epoch: [92]  [190/312]  eta: 0:02:13  lr: 0.003372  min_lr: 0.003372  loss: 2.4599 (2.4519)  weight_decay: 0.0500 (0.0500)  time: 1.0069  data: 0.0005  max mem: 78493
Epoch: [92]  [200/312]  eta: 0:02:02  lr: 0.003372  min_lr: 0.003372  loss: 2.3286 (2.4497)  weight_decay: 0.0500 (0.0500)  time: 1.0081  data: 0.0004  max mem: 78493
Epoch: [92]  [210/312]  eta: 0:01:50  lr: 0.003371  min_lr: 0.003371  loss: 2.4161 (2.4491)  weight_decay: 0.0500 (0.0500)  time: 1.0072  data: 0.0010  max mem: 78493
Epoch: [92]  [220/312]  eta: 0:01:39  lr: 0.003371  min_lr: 0.003371  loss: 2.3218 (2.4403)  weight_decay: 0.0500 (0.0500)  time: 1.0071  data: 0.0010  max mem: 78493
Epoch: [92]  [230/312]  eta: 0:01:28  lr: 0.003370  min_lr: 0.003370  loss: 2.3305 (2.4428)  weight_decay: 0.0500 (0.0500)  time: 1.0070  data: 0.0005  max mem: 78493
Epoch: [92]  [240/312]  eta: 0:01:17  lr: 0.003370  min_lr: 0.003370  loss: 2.3142 (2.4368)  weight_decay: 0.0500 (0.0500)  time: 1.0053  data: 0.0011  max mem: 78493
Epoch: [92]  [250/312]  eta: 0:01:06  lr: 0.003369  min_lr: 0.003369  loss: 2.2381 (2.4305)  weight_decay: 0.0500 (0.0500)  time: 1.0045  data: 0.0011  max mem: 78493
Epoch: [92]  [260/312]  eta: 0:00:55  lr: 0.003369  min_lr: 0.003369  loss: 2.4683 (2.4362)  weight_decay: 0.0500 (0.0500)  time: 1.0048  data: 0.0004  max mem: 78493
Epoch: [92]  [270/312]  eta: 0:00:44  lr: 0.003368  min_lr: 0.003368  loss: 2.5195 (2.4345)  weight_decay: 0.0500 (0.0500)  time: 1.0036  data: 0.0012  max mem: 78493
Epoch: [92]  [280/312]  eta: 0:00:34  lr: 0.003368  min_lr: 0.003368  loss: 2.5195 (2.4418)  weight_decay: 0.0500 (0.0500)  time: 1.0044  data: 0.0018  max mem: 78493
Epoch: [92]  [290/312]  eta: 0:00:23  lr: 0.003367  min_lr: 0.003367  loss: 2.6185 (2.4414)  weight_decay: 0.0500 (0.0500)  time: 1.0041  data: 0.0009  max mem: 78493
Epoch: [92]  [300/312]  eta: 0:00:12  lr: 0.003367  min_lr: 0.003367  loss: 2.4448 (2.4405)  weight_decay: 0.0500 (0.0500)  time: 1.0016  data: 0.0001  max mem: 78493
Epoch: [92]  [310/312]  eta: 0:00:02  lr: 0.003366  min_lr: 0.003366  loss: 2.4448 (2.4375)  weight_decay: 0.0500 (0.0500)  time: 1.0015  data: 0.0001  max mem: 78493
Epoch: [92]  [311/312]  eta: 0:00:01  lr: 0.003366  min_lr: 0.003366  loss: 2.3882 (2.4365)  weight_decay: 0.0500 (0.0500)  time: 1.0016  data: 0.0001  max mem: 78493
Epoch: [92] Total time: 0:05:32 (1.0663 s / it)
Averaged stats: lr: 0.003366  min_lr: 0.003366  loss: 2.3882 (2.4505)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:17  loss: 0.7610 (0.7610)  acc1: 81.1198 (81.1198)  acc5: 94.9219 (94.9219)  time: 8.5744  data: 8.2969  max mem: 78493
Test:  [8/9]  eta: 0:00:01  loss: 1.2090 (1.0540)  acc1: 72.7865 (73.3920)  acc5: 90.6250 (91.5040)  time: 1.1510  data: 0.9220  max mem: 78493
Test: Total time: 0:00:10 (1.1659 s / it)
* Acc@1 73.516 Acc@5 91.480 loss 1.045
Accuracy of the model on the 50000 test images: 73.5%
Max accuracy: 73.52%
Epoch: [93]  [  0/312]  eta: 1:28:33  lr: 0.003366  min_lr: 0.003366  loss: 2.7335 (2.7335)  weight_decay: 0.0500 (0.0500)  time: 17.0319  data: 16.0204  max mem: 78493
Epoch: [93]  [ 10/312]  eta: 0:13:17  lr: 0.003365  min_lr: 0.003365  loss: 2.6450 (2.4952)  weight_decay: 0.0500 (0.0500)  time: 2.6410  data: 1.4607  max mem: 78493
Epoch: [93]  [ 20/312]  eta: 0:09:05  lr: 0.003365  min_lr: 0.003365  loss: 2.4757 (2.4800)  weight_decay: 0.0500 (0.0500)  time: 1.1099  data: 0.0026  max mem: 78493
Epoch: [93]  [ 30/312]  eta: 0:07:28  lr: 0.003364  min_lr: 0.003364  loss: 2.4757 (2.4651)  weight_decay: 0.0500 (0.0500)  time: 1.0139  data: 0.0005  max mem: 78493
Epoch: [93]  [ 40/312]  eta: 0:06:34  lr: 0.003364  min_lr: 0.003364  loss: 2.5557 (2.4708)  weight_decay: 0.0500 (0.0500)  time: 1.0085  data: 0.0004  max mem: 78493
Epoch: [93]  [ 50/312]  eta: 0:05:57  lr: 0.003363  min_lr: 0.003363  loss: 2.5786 (2.4849)  weight_decay: 0.0500 (0.0500)  time: 1.0092  data: 0.0004  max mem: 78493
Epoch: [93]  [ 60/312]  eta: 0:05:28  lr: 0.003363  min_lr: 0.003363  loss: 2.3647 (2.4572)  weight_decay: 0.0500 (0.0500)  time: 1.0098  data: 0.0004  max mem: 78493
Epoch: [93]  [ 70/312]  eta: 0:05:05  lr: 0.003362  min_lr: 0.003362  loss: 2.5707 (2.4844)  weight_decay: 0.0500 (0.0500)  time: 1.0076  data: 0.0004  max mem: 78493
Epoch: [93]  [ 80/312]  eta: 0:04:45  lr: 0.003362  min_lr: 0.003362  loss: 2.6029 (2.4759)  weight_decay: 0.0500 (0.0500)  time: 1.0062  data: 0.0004  max mem: 78493
Epoch: [93]  [ 90/312]  eta: 0:04:27  lr: 0.003361  min_lr: 0.003361  loss: 2.3159 (2.4586)  weight_decay: 0.0500 (0.0500)  time: 1.0063  data: 0.0004  max mem: 78493
Epoch: [93]  [100/312]  eta: 0:04:11  lr: 0.003361  min_lr: 0.003361  loss: 2.4252 (2.4606)  weight_decay: 0.0500 (0.0500)  time: 1.0061  data: 0.0004  max mem: 78493
Epoch: [93]  [110/312]  eta: 0:03:56  lr: 0.003360  min_lr: 0.003360  loss: 2.4048 (2.4505)  weight_decay: 0.0500 (0.0500)  time: 1.0056  data: 0.0004  max mem: 78493
Epoch: [93]  [120/312]  eta: 0:03:42  lr: 0.003360  min_lr: 0.003360  loss: 2.4420 (2.4460)  weight_decay: 0.0500 (0.0500)  time: 1.0066  data: 0.0004  max mem: 78493
Epoch: [93]  [130/312]  eta: 0:03:28  lr: 0.003359  min_lr: 0.003359  loss: 2.5838 (2.4550)  weight_decay: 0.0500 (0.0500)  time: 1.0065  data: 0.0004  max mem: 78493
Epoch: [93]  [140/312]  eta: 0:03:15  lr: 0.003359  min_lr: 0.003359  loss: 2.5838 (2.4548)  weight_decay: 0.0500 (0.0500)  time: 1.0066  data: 0.0004  max mem: 78493
Epoch: [93]  [150/312]  eta: 0:03:02  lr: 0.003358  min_lr: 0.003358  loss: 2.4681 (2.4514)  weight_decay: 0.0500 (0.0500)  time: 1.0080  data: 0.0004  max mem: 78493
Epoch: [93]  [160/312]  eta: 0:02:50  lr: 0.003358  min_lr: 0.003358  loss: 2.3316 (2.4455)  weight_decay: 0.0500 (0.0500)  time: 1.0074  data: 0.0004  max mem: 78493
Epoch: [93]  [170/312]  eta: 0:02:38  lr: 0.003357  min_lr: 0.003357  loss: 2.3328 (2.4439)  weight_decay: 0.0500 (0.0500)  time: 1.0064  data: 0.0004  max mem: 78493
Epoch: [93]  [180/312]  eta: 0:02:26  lr: 0.003356  min_lr: 0.003356  loss: 2.3328 (2.4336)  weight_decay: 0.0500 (0.0500)  time: 1.0052  data: 0.0004  max mem: 78493
Epoch: [93]  [190/312]  eta: 0:02:14  lr: 0.003356  min_lr: 0.003356  loss: 2.5567 (2.4408)  weight_decay: 0.0500 (0.0500)  time: 1.0040  data: 0.0004  max mem: 78493
Epoch: [93]  [200/312]  eta: 0:02:02  lr: 0.003355  min_lr: 0.003355  loss: 2.5918 (2.4365)  weight_decay: 0.0500 (0.0500)  time: 1.0040  data: 0.0004  max mem: 78493
Epoch: [93]  [210/312]  eta: 0:01:51  lr: 0.003355  min_lr: 0.003355  loss: 2.4555 (2.4344)  weight_decay: 0.0500 (0.0500)  time: 1.0063  data: 0.0005  max mem: 78493
Epoch: [93]  [220/312]  eta: 0:01:40  lr: 0.003354  min_lr: 0.003354  loss: 2.5346 (2.4402)  weight_decay: 0.0500 (0.0500)  time: 1.0072  data: 0.0005  max mem: 78493
Epoch: [93]  [230/312]  eta: 0:01:28  lr: 0.003354  min_lr: 0.003354  loss: 2.6087 (2.4342)  weight_decay: 0.0500 (0.0500)  time: 1.0056  data: 0.0004  max mem: 78493
Epoch: [93]  [240/312]  eta: 0:01:17  lr: 0.003353  min_lr: 0.003353  loss: 2.5318 (2.4409)  weight_decay: 0.0500 (0.0500)  time: 1.0061  data: 0.0004  max mem: 78493
Epoch: [93]  [250/312]  eta: 0:01:06  lr: 0.003353  min_lr: 0.003353  loss: 2.4429 (2.4328)  weight_decay: 0.0500 (0.0500)  time: 1.0060  data: 0.0004  max mem: 78493
Epoch: [93]  [260/312]  eta: 0:00:55  lr: 0.003352  min_lr: 0.003352  loss: 2.5068 (2.4462)  weight_decay: 0.0500 (0.0500)  time: 1.0052  data: 0.0004  max mem: 78493
Epoch: [93]  [270/312]  eta: 0:00:45  lr: 0.003352  min_lr: 0.003352  loss: 2.6577 (2.4557)  weight_decay: 0.0500 (0.0500)  time: 1.0043  data: 0.0004  max mem: 78493
Epoch: [93]  [280/312]  eta: 0:00:34  lr: 0.003351  min_lr: 0.003351  loss: 2.6431 (2.4617)  weight_decay: 0.0500 (0.0500)  time: 1.0057  data: 0.0010  max mem: 78493
Epoch: [93]  [290/312]  eta: 0:00:23  lr: 0.003351  min_lr: 0.003351  loss: 2.6246 (2.4612)  weight_decay: 0.0500 (0.0500)  time: 1.0048  data: 0.0009  max mem: 78493
Epoch: [93]  [300/312]  eta: 0:00:12  lr: 0.003350  min_lr: 0.003350  loss: 2.4019 (2.4632)  weight_decay: 0.0500 (0.0500)  time: 1.0020  data: 0.0001  max mem: 78493
Epoch: [93]  [310/312]  eta: 0:00:02  lr: 0.003350  min_lr: 0.003350  loss: 2.4189 (2.4633)  weight_decay: 0.0500 (0.0500)  time: 1.0016  data: 0.0001  max mem: 78493
Epoch: [93]  [311/312]  eta: 0:00:01  lr: 0.003350  min_lr: 0.003350  loss: 2.4189 (2.4632)  weight_decay: 0.0500 (0.0500)  time: 1.0016  data: 0.0001  max mem: 78493
Epoch: [93] Total time: 0:05:33 (1.0696 s / it)
Averaged stats: lr: 0.003350  min_lr: 0.003350  loss: 2.4189 (2.4545)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:06  loss: 0.8226 (0.8226)  acc1: 80.5990 (80.5990)  acc5: 94.9219 (94.9219)  time: 7.3818  data: 7.1216  max mem: 78493
Test:  [8/9]  eta: 0:00:01  loss: 1.2701 (1.1048)  acc1: 71.0938 (73.2960)  acc5: 90.3646 (90.9120)  time: 1.0273  data: 0.7914  max mem: 78493
Test: Total time: 0:00:09 (1.0383 s / it)
* Acc@1 72.832 Acc@5 91.028 loss 1.092
Accuracy of the model on the 50000 test images: 72.8%
Max accuracy: 73.52%
Epoch: [94]  [  0/312]  eta: 1:25:09  lr: 0.003350  min_lr: 0.003350  loss: 2.8409 (2.8409)  weight_decay: 0.0500 (0.0500)  time: 16.3758  data: 11.6683  max mem: 78493
Epoch: [94]  [ 10/312]  eta: 0:13:10  lr: 0.003349  min_lr: 0.003349  loss: 2.6148 (2.6262)  weight_decay: 0.0500 (0.0500)  time: 2.6170  data: 1.2447  max mem: 78493
Epoch: [94]  [ 20/312]  eta: 0:09:02  lr: 0.003348  min_lr: 0.003348  loss: 2.6148 (2.5987)  weight_decay: 0.0500 (0.0500)  time: 1.1316  data: 0.1031  max mem: 78493
Epoch: [94]  [ 30/312]  eta: 0:07:26  lr: 0.003348  min_lr: 0.003348  loss: 2.6026 (2.5242)  weight_decay: 0.0500 (0.0500)  time: 1.0146  data: 0.0021  max mem: 78493
Epoch: [94]  [ 40/312]  eta: 0:06:32  lr: 0.003347  min_lr: 0.003347  loss: 2.2550 (2.4965)  weight_decay: 0.0500 (0.0500)  time: 1.0071  data: 0.0005  max mem: 78493
Epoch: [94]  [ 50/312]  eta: 0:05:55  lr: 0.003347  min_lr: 0.003347  loss: 2.4686 (2.4942)  weight_decay: 0.0500 (0.0500)  time: 1.0070  data: 0.0005  max mem: 78493
Epoch: [94]  [ 60/312]  eta: 0:05:27  lr: 0.003346  min_lr: 0.003346  loss: 2.4686 (2.4549)  weight_decay: 0.0500 (0.0500)  time: 1.0068  data: 0.0005  max mem: 78493
Epoch: [94]  [ 70/312]  eta: 0:05:04  lr: 0.003346  min_lr: 0.003346  loss: 2.5090 (2.4816)  weight_decay: 0.0500 (0.0500)  time: 1.0072  data: 0.0005  max mem: 78493
Epoch: [94]  [ 80/312]  eta: 0:04:44  lr: 0.003345  min_lr: 0.003345  loss: 2.6134 (2.4660)  weight_decay: 0.0500 (0.0500)  time: 1.0073  data: 0.0005  max mem: 78493
Epoch: [94]  [ 90/312]  eta: 0:04:27  lr: 0.003345  min_lr: 0.003345  loss: 2.4208 (2.4670)  weight_decay: 0.0500 (0.0500)  time: 1.0056  data: 0.0004  max mem: 78493
Epoch: [94]  [100/312]  eta: 0:04:10  lr: 0.003344  min_lr: 0.003344  loss: 2.5913 (2.4650)  weight_decay: 0.0500 (0.0500)  time: 1.0047  data: 0.0005  max mem: 78493
Epoch: [94]  [110/312]  eta: 0:03:55  lr: 0.003344  min_lr: 0.003344  loss: 2.6189 (2.4655)  weight_decay: 0.0500 (0.0500)  time: 1.0062  data: 0.0005  max mem: 78493
Epoch: [94]  [120/312]  eta: 0:03:41  lr: 0.003343  min_lr: 0.003343  loss: 2.3494 (2.4455)  weight_decay: 0.0500 (0.0500)  time: 1.0059  data: 0.0004  max mem: 78493
Epoch: [94]  [130/312]  eta: 0:03:28  lr: 0.003343  min_lr: 0.003343  loss: 2.3676 (2.4482)  weight_decay: 0.0500 (0.0500)  time: 1.0059  data: 0.0004  max mem: 78493
Epoch: [94]  [140/312]  eta: 0:03:14  lr: 0.003342  min_lr: 0.003342  loss: 2.5925 (2.4493)  weight_decay: 0.0500 (0.0500)  time: 1.0091  data: 0.0005  max mem: 78493
Epoch: [94]  [150/312]  eta: 0:03:02  lr: 0.003342  min_lr: 0.003342  loss: 2.5931 (2.4581)  weight_decay: 0.0500 (0.0500)  time: 1.0098  data: 0.0005  max mem: 78493
Epoch: [94]  [160/312]  eta: 0:02:49  lr: 0.003341  min_lr: 0.003341  loss: 2.5931 (2.4556)  weight_decay: 0.0500 (0.0500)  time: 1.0083  data: 0.0004  max mem: 78493
Epoch: [94]  [170/312]  eta: 0:02:37  lr: 0.003340  min_lr: 0.003340  loss: 2.6051 (2.4665)  weight_decay: 0.0500 (0.0500)  time: 1.0090  data: 0.0005  max mem: 78493
Epoch: [94]  [180/312]  eta: 0:02:25  lr: 0.003340  min_lr: 0.003340  loss: 2.6247 (2.4725)  weight_decay: 0.0500 (0.0500)  time: 1.0084  data: 0.0004  max mem: 78493
Epoch: [94]  [190/312]  eta: 0:02:14  lr: 0.003339  min_lr: 0.003339  loss: 2.5694 (2.4682)  weight_decay: 0.0500 (0.0500)  time: 1.0061  data: 0.0004  max mem: 78493
Epoch: [94]  [200/312]  eta: 0:02:02  lr: 0.003339  min_lr: 0.003339  loss: 2.3146 (2.4629)  weight_decay: 0.0500 (0.0500)  time: 1.0084  data: 0.0012  max mem: 78493
Epoch: [94]  [210/312]  eta: 0:01:51  lr: 0.003338  min_lr: 0.003338  loss: 2.4136 (2.4606)  weight_decay: 0.0500 (0.0500)  time: 1.0088  data: 0.0012  max mem: 78493
Epoch: [94]  [220/312]  eta: 0:01:40  lr: 0.003338  min_lr: 0.003338  loss: 2.4212 (2.4542)  weight_decay: 0.0500 (0.0500)  time: 1.0070  data: 0.0005  max mem: 78493
Epoch: [94]  [230/312]  eta: 0:01:28  lr: 0.003337  min_lr: 0.003337  loss: 2.4716 (2.4576)  weight_decay: 0.0500 (0.0500)  time: 1.0069  data: 0.0005  max mem: 78493
Epoch: [94]  [240/312]  eta: 0:01:17  lr: 0.003337  min_lr: 0.003337  loss: 2.4716 (2.4567)  weight_decay: 0.0500 (0.0500)  time: 1.0063  data: 0.0014  max mem: 78493
Epoch: [94]  [250/312]  eta: 0:01:06  lr: 0.003336  min_lr: 0.003336  loss: 2.5728 (2.4650)  weight_decay: 0.0500 (0.0500)  time: 1.0061  data: 0.0014  max mem: 78493
Epoch: [94]  [260/312]  eta: 0:00:55  lr: 0.003336  min_lr: 0.003336  loss: 2.5919 (2.4614)  weight_decay: 0.0500 (0.0500)  time: 1.0069  data: 0.0004  max mem: 78493
Epoch: [94]  [270/312]  eta: 0:00:45  lr: 0.003335  min_lr: 0.003335  loss: 2.4379 (2.4577)  weight_decay: 0.0500 (0.0500)  time: 1.0062  data: 0.0005  max mem: 78493
Epoch: [94]  [280/312]  eta: 0:00:34  lr: 0.003335  min_lr: 0.003335  loss: 2.2575 (2.4523)  weight_decay: 0.0500 (0.0500)  time: 1.0054  data: 0.0011  max mem: 78493
Epoch: [94]  [290/312]  eta: 0:00:23  lr: 0.003334  min_lr: 0.003334  loss: 2.2575 (2.4458)  weight_decay: 0.0500 (0.0500)  time: 1.0038  data: 0.0009  max mem: 78493
Epoch: [94]  [300/312]  eta: 0:00:12  lr: 0.003334  min_lr: 0.003334  loss: 2.1216 (2.4388)  weight_decay: 0.0500 (0.0500)  time: 1.0017  data: 0.0001  max mem: 78493
Epoch: [94]  [310/312]  eta: 0:00:02  lr: 0.003333  min_lr: 0.003333  loss: 2.4388 (2.4478)  weight_decay: 0.0500 (0.0500)  time: 1.0019  data: 0.0001  max mem: 78493
Epoch: [94]  [311/312]  eta: 0:00:01  lr: 0.003333  min_lr: 0.003333  loss: 2.6189 (2.4486)  weight_decay: 0.0500 (0.0500)  time: 1.0019  data: 0.0001  max mem: 78493
Epoch: [94] Total time: 0:05:33 (1.0694 s / it)
Averaged stats: lr: 0.003333  min_lr: 0.003333  loss: 2.6189 (2.4443)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:15  loss: 0.8274 (0.8274)  acc1: 80.4688 (80.4688)  acc5: 94.0104 (94.0104)  time: 8.4281  data: 8.1286  max mem: 78493
Test:  [8/9]  eta: 0:00:01  loss: 1.1542 (1.0866)  acc1: 72.5260 (73.3920)  acc5: 91.5365 (91.3440)  time: 1.1346  data: 0.9033  max mem: 78493
Test: Total time: 0:00:10 (1.1505 s / it)
* Acc@1 73.320 Acc@5 91.650 loss 1.066
Accuracy of the model on the 50000 test images: 73.3%
Max accuracy: 73.52%
Epoch: [95]  [  0/312]  eta: 1:23:30  lr: 0.003333  min_lr: 0.003333  loss: 2.3795 (2.3795)  weight_decay: 0.0500 (0.0500)  time: 16.0591  data: 14.0605  max mem: 78493
Epoch: [95]  [ 10/312]  eta: 0:12:34  lr: 0.003332  min_lr: 0.003332  loss: 2.3621 (2.4679)  weight_decay: 0.0500 (0.0500)  time: 2.4987  data: 1.2790  max mem: 78493
Epoch: [95]  [ 20/312]  eta: 0:08:47  lr: 0.003332  min_lr: 0.003332  loss: 2.3551 (2.4138)  weight_decay: 0.0500 (0.0500)  time: 1.0936  data: 0.0008  max mem: 78493
Epoch: [95]  [ 30/312]  eta: 0:07:16  lr: 0.003331  min_lr: 0.003331  loss: 2.5132 (2.4701)  weight_decay: 0.0500 (0.0500)  time: 1.0258  data: 0.0006  max mem: 78493
Epoch: [95]  [ 40/312]  eta: 0:06:25  lr: 0.003331  min_lr: 0.003331  loss: 2.5230 (2.4927)  weight_decay: 0.0500 (0.0500)  time: 1.0081  data: 0.0005  max mem: 78493
Epoch: [95]  [ 50/312]  eta: 0:05:50  lr: 0.003330  min_lr: 0.003330  loss: 2.5230 (2.5004)  weight_decay: 0.0500 (0.0500)  time: 1.0075  data: 0.0004  max mem: 78493
Epoch: [95]  [ 60/312]  eta: 0:05:23  lr: 0.003330  min_lr: 0.003330  loss: 2.6828 (2.5088)  weight_decay: 0.0500 (0.0500)  time: 1.0068  data: 0.0005  max mem: 78493
Epoch: [95]  [ 70/312]  eta: 0:05:00  lr: 0.003329  min_lr: 0.003329  loss: 2.5668 (2.4968)  weight_decay: 0.0500 (0.0500)  time: 1.0070  data: 0.0004  max mem: 78493
Epoch: [95]  [ 80/312]  eta: 0:04:41  lr: 0.003329  min_lr: 0.003329  loss: 2.5250 (2.4958)  weight_decay: 0.0500 (0.0500)  time: 1.0080  data: 0.0004  max mem: 78493
Epoch: [95]  [ 90/312]  eta: 0:04:24  lr: 0.003328  min_lr: 0.003328  loss: 2.4307 (2.4777)  weight_decay: 0.0500 (0.0500)  time: 1.0097  data: 0.0004  max mem: 78493
Epoch: [95]  [100/312]  eta: 0:04:08  lr: 0.003327  min_lr: 0.003327  loss: 2.3543 (2.4670)  weight_decay: 0.0500 (0.0500)  time: 1.0084  data: 0.0004  max mem: 78493
Epoch: [95]  [110/312]  eta: 0:03:54  lr: 0.003327  min_lr: 0.003327  loss: 2.4568 (2.4625)  weight_decay: 0.0500 (0.0500)  time: 1.0086  data: 0.0004  max mem: 78493
Epoch: [95]  [120/312]  eta: 0:03:40  lr: 0.003326  min_lr: 0.003326  loss: 2.4344 (2.4548)  weight_decay: 0.0500 (0.0500)  time: 1.0069  data: 0.0005  max mem: 78493
Epoch: [95]  [130/312]  eta: 0:03:26  lr: 0.003326  min_lr: 0.003326  loss: 2.5032 (2.4557)  weight_decay: 0.0500 (0.0500)  time: 1.0049  data: 0.0005  max mem: 78493
Epoch: [95]  [140/312]  eta: 0:03:13  lr: 0.003325  min_lr: 0.003325  loss: 2.4371 (2.4331)  weight_decay: 0.0500 (0.0500)  time: 1.0067  data: 0.0004  max mem: 78493
Epoch: [95]  [150/312]  eta: 0:03:01  lr: 0.003325  min_lr: 0.003325  loss: 2.3688 (2.4384)  weight_decay: 0.0500 (0.0500)  time: 1.0077  data: 0.0004  max mem: 78493
Epoch: [95]  [160/312]  eta: 0:02:48  lr: 0.003324  min_lr: 0.003324  loss: 2.5629 (2.4448)  weight_decay: 0.0500 (0.0500)  time: 1.0077  data: 0.0005  max mem: 78493
Epoch: [95]  [170/312]  eta: 0:02:37  lr: 0.003324  min_lr: 0.003324  loss: 2.5629 (2.4528)  weight_decay: 0.0500 (0.0500)  time: 1.0091  data: 0.0004  max mem: 78493
Epoch: [95]  [180/312]  eta: 0:02:25  lr: 0.003323  min_lr: 0.003323  loss: 2.6000 (2.4501)  weight_decay: 0.0500 (0.0500)  time: 1.0084  data: 0.0004  max mem: 78493
Epoch: [95]  [190/312]  eta: 0:02:13  lr: 0.003323  min_lr: 0.003323  loss: 2.6182 (2.4555)  weight_decay: 0.0500 (0.0500)  time: 1.0050  data: 0.0004  max mem: 78493
Epoch: [95]  [200/312]  eta: 0:02:02  lr: 0.003322  min_lr: 0.003322  loss: 2.6356 (2.4591)  weight_decay: 0.0500 (0.0500)  time: 1.0051  data: 0.0004  max mem: 78493
Epoch: [95]  [210/312]  eta: 0:01:50  lr: 0.003322  min_lr: 0.003322  loss: 2.5691 (2.4606)  weight_decay: 0.0500 (0.0500)  time: 1.0050  data: 0.0004  max mem: 78493
Epoch: [95]  [220/312]  eta: 0:01:39  lr: 0.003321  min_lr: 0.003321  loss: 2.4353 (2.4585)  weight_decay: 0.0500 (0.0500)  time: 1.0052  data: 0.0004  max mem: 78493
Epoch: [95]  [230/312]  eta: 0:01:28  lr: 0.003320  min_lr: 0.003320  loss: 2.4088 (2.4580)  weight_decay: 0.0500 (0.0500)  time: 1.0059  data: 0.0005  max mem: 78493
Epoch: [95]  [240/312]  eta: 0:01:17  lr: 0.003320  min_lr: 0.003320  loss: 2.4478 (2.4584)  weight_decay: 0.0500 (0.0500)  time: 1.0048  data: 0.0005  max mem: 78493
Epoch: [95]  [250/312]  eta: 0:01:06  lr: 0.003319  min_lr: 0.003319  loss: 2.4478 (2.4532)  weight_decay: 0.0500 (0.0500)  time: 1.0055  data: 0.0005  max mem: 78493
Epoch: [95]  [260/312]  eta: 0:00:55  lr: 0.003319  min_lr: 0.003319  loss: 2.3155 (2.4499)  weight_decay: 0.0500 (0.0500)  time: 1.0053  data: 0.0005  max mem: 78493
Epoch: [95]  [270/312]  eta: 0:00:44  lr: 0.003318  min_lr: 0.003318  loss: 2.5673 (2.4512)  weight_decay: 0.0500 (0.0500)  time: 1.0043  data: 0.0005  max mem: 78493
Epoch: [95]  [280/312]  eta: 0:00:34  lr: 0.003318  min_lr: 0.003318  loss: 2.5853 (2.4463)  weight_decay: 0.0500 (0.0500)  time: 1.0046  data: 0.0010  max mem: 78493
Epoch: [95]  [290/312]  eta: 0:00:23  lr: 0.003317  min_lr: 0.003317  loss: 2.3999 (2.4441)  weight_decay: 0.0500 (0.0500)  time: 1.0034  data: 0.0009  max mem: 78493
Epoch: [95]  [300/312]  eta: 0:00:12  lr: 0.003317  min_lr: 0.003317  loss: 2.4618 (2.4431)  weight_decay: 0.0500 (0.0500)  time: 1.0021  data: 0.0001  max mem: 78493
Epoch: [95]  [310/312]  eta: 0:00:02  lr: 0.003316  min_lr: 0.003316  loss: 2.6003 (2.4490)  weight_decay: 0.0500 (0.0500)  time: 1.0020  data: 0.0001  max mem: 78493
Epoch: [95]  [311/312]  eta: 0:00:01  lr: 0.003316  min_lr: 0.003316  loss: 2.6003 (2.4490)  weight_decay: 0.0500 (0.0500)  time: 1.0021  data: 0.0001  max mem: 78493
Epoch: [95] Total time: 0:05:32 (1.0657 s / it)
Averaged stats: lr: 0.003316  min_lr: 0.003316  loss: 2.6003 (2.4465)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:15  loss: 0.8839 (0.8839)  acc1: 79.1667 (79.1667)  acc5: 93.7500 (93.7500)  time: 8.4153  data: 8.1479  max mem: 78493
Test:  [8/9]  eta: 0:00:01  loss: 1.2164 (1.1008)  acc1: 70.4427 (72.0160)  acc5: 91.0156 (91.0880)  time: 1.1344  data: 0.9054  max mem: 78493
Test: Total time: 0:00:10 (1.1778 s / it)
* Acc@1 72.570 Acc@5 91.140 loss 1.094
Accuracy of the model on the 50000 test images: 72.6%
Max accuracy: 73.52%
Epoch: [96]  [  0/312]  eta: 1:26:33  lr: 0.003316  min_lr: 0.003316  loss: 2.9284 (2.9284)  weight_decay: 0.0500 (0.0500)  time: 16.6445  data: 14.2855  max mem: 78493
Epoch: [96]  [ 10/312]  eta: 0:12:43  lr: 0.003316  min_lr: 0.003316  loss: 2.6831 (2.5305)  weight_decay: 0.0500 (0.0500)  time: 2.5273  data: 1.3081  max mem: 78493
Epoch: [96]  [ 20/312]  eta: 0:08:48  lr: 0.003315  min_lr: 0.003315  loss: 2.6831 (2.5733)  weight_decay: 0.0500 (0.0500)  time: 1.0699  data: 0.0056  max mem: 78493
Epoch: [96]  [ 30/312]  eta: 0:07:18  lr: 0.003314  min_lr: 0.003314  loss: 2.5681 (2.4767)  weight_decay: 0.0500 (0.0500)  time: 1.0184  data: 0.0007  max mem: 78493
Epoch: [96]  [ 40/312]  eta: 0:06:26  lr: 0.003314  min_lr: 0.003314  loss: 2.5625 (2.4850)  weight_decay: 0.0500 (0.0500)  time: 1.0127  data: 0.0006  max mem: 78493
Epoch: [96]  [ 50/312]  eta: 0:05:51  lr: 0.003313  min_lr: 0.003313  loss: 2.5903 (2.4934)  weight_decay: 0.0500 (0.0500)  time: 1.0127  data: 0.0027  max mem: 78493
Epoch: [96]  [ 60/312]  eta: 0:05:24  lr: 0.003313  min_lr: 0.003313  loss: 2.4809 (2.4850)  weight_decay: 0.0500 (0.0500)  time: 1.0115  data: 0.0026  max mem: 78493
Epoch: [96]  [ 70/312]  eta: 0:05:02  lr: 0.003312  min_lr: 0.003312  loss: 2.5311 (2.4841)  weight_decay: 0.0500 (0.0500)  time: 1.0096  data: 0.0016  max mem: 78493
Epoch: [96]  [ 80/312]  eta: 0:04:42  lr: 0.003312  min_lr: 0.003312  loss: 2.5112 (2.4712)  weight_decay: 0.0500 (0.0500)  time: 1.0098  data: 0.0015  max mem: 78493
Epoch: [96]  [ 90/312]  eta: 0:04:25  lr: 0.003311  min_lr: 0.003311  loss: 2.3338 (2.4567)  weight_decay: 0.0500 (0.0500)  time: 1.0099  data: 0.0005  max mem: 78493
Epoch: [96]  [100/312]  eta: 0:04:09  lr: 0.003311  min_lr: 0.003311  loss: 2.5054 (2.4645)  weight_decay: 0.0500 (0.0500)  time: 1.0076  data: 0.0005  max mem: 78493
Epoch: [96]  [110/312]  eta: 0:03:54  lr: 0.003310  min_lr: 0.003310  loss: 2.5748 (2.4725)  weight_decay: 0.0500 (0.0500)  time: 1.0070  data: 0.0004  max mem: 78493
Epoch: [96]  [120/312]  eta: 0:03:40  lr: 0.003310  min_lr: 0.003310  loss: 2.5410 (2.4610)  weight_decay: 0.0500 (0.0500)  time: 1.0081  data: 0.0004  max mem: 78493
Epoch: [96]  [130/312]  eta: 0:03:27  lr: 0.003309  min_lr: 0.003309  loss: 2.3004 (2.4506)  weight_decay: 0.0500 (0.0500)  time: 1.0061  data: 0.0005  max mem: 78493
Epoch: [96]  [140/312]  eta: 0:03:14  lr: 0.003308  min_lr: 0.003308  loss: 2.4859 (2.4479)  weight_decay: 0.0500 (0.0500)  time: 1.0054  data: 0.0005  max mem: 78493
Epoch: [96]  [150/312]  eta: 0:03:01  lr: 0.003308  min_lr: 0.003308  loss: 2.5861 (2.4622)  weight_decay: 0.0500 (0.0500)  time: 1.0074  data: 0.0004  max mem: 78493
Epoch: [96]  [160/312]  eta: 0:02:49  lr: 0.003307  min_lr: 0.003307  loss: 2.6886 (2.4688)  weight_decay: 0.0500 (0.0500)  time: 1.0086  data: 0.0004  max mem: 78493
Epoch: [96]  [170/312]  eta: 0:02:37  lr: 0.003307  min_lr: 0.003307  loss: 2.6668 (2.4704)  weight_decay: 0.0500 (0.0500)  time: 1.0086  data: 0.0004  max mem: 78493
Epoch: [96]  [180/312]  eta: 0:02:25  lr: 0.003306  min_lr: 0.003306  loss: 2.6383 (2.4756)  weight_decay: 0.0500 (0.0500)  time: 1.0076  data: 0.0004  max mem: 78493
Epoch: [96]  [190/312]  eta: 0:02:13  lr: 0.003306  min_lr: 0.003306  loss: 2.5333 (2.4737)  weight_decay: 0.0500 (0.0500)  time: 1.0073  data: 0.0004  max mem: 78493
Epoch: [96]  [200/312]  eta: 0:02:02  lr: 0.003305  min_lr: 0.003305  loss: 2.5333 (2.4742)  weight_decay: 0.0500 (0.0500)  time: 1.0059  data: 0.0004  max mem: 78493
Epoch: [96]  [210/312]  eta: 0:01:51  lr: 0.003305  min_lr: 0.003305  loss: 2.5608 (2.4723)  weight_decay: 0.0500 (0.0500)  time: 1.0049  data: 0.0004  max mem: 78493
Epoch: [96]  [220/312]  eta: 0:01:39  lr: 0.003304  min_lr: 0.003304  loss: 2.5282 (2.4732)  weight_decay: 0.0500 (0.0500)  time: 1.0043  data: 0.0004  max mem: 78493
Epoch: [96]  [230/312]  eta: 0:01:28  lr: 0.003304  min_lr: 0.003304  loss: 2.4659 (2.4681)  weight_decay: 0.0500 (0.0500)  time: 1.0042  data: 0.0004  max mem: 78493
Epoch: [96]  [240/312]  eta: 0:01:17  lr: 0.003303  min_lr: 0.003303  loss: 2.4659 (2.4730)  weight_decay: 0.0500 (0.0500)  time: 1.0048  data: 0.0004  max mem: 78493
Epoch: [96]  [250/312]  eta: 0:01:06  lr: 0.003302  min_lr: 0.003302  loss: 2.4208 (2.4710)  weight_decay: 0.0500 (0.0500)  time: 1.0052  data: 0.0004  max mem: 78493
Epoch: [96]  [260/312]  eta: 0:00:55  lr: 0.003302  min_lr: 0.003302  loss: 2.4145 (2.4759)  weight_decay: 0.0500 (0.0500)  time: 1.0047  data: 0.0004  max mem: 78493
Epoch: [96]  [270/312]  eta: 0:00:44  lr: 0.003301  min_lr: 0.003301  loss: 2.3145 (2.4673)  weight_decay: 0.0500 (0.0500)  time: 1.0055  data: 0.0005  max mem: 78493
Epoch: [96]  [280/312]  eta: 0:00:34  lr: 0.003301  min_lr: 0.003301  loss: 2.2609 (2.4629)  weight_decay: 0.0500 (0.0500)  time: 1.0072  data: 0.0013  max mem: 78493
Epoch: [96]  [290/312]  eta: 0:00:23  lr: 0.003300  min_lr: 0.003300  loss: 2.4051 (2.4608)  weight_decay: 0.0500 (0.0500)  time: 1.0052  data: 0.0012  max mem: 78493
Epoch: [96]  [300/312]  eta: 0:00:12  lr: 0.003300  min_lr: 0.003300  loss: 2.4986 (2.4664)  weight_decay: 0.0500 (0.0500)  time: 1.0020  data: 0.0001  max mem: 78493
Epoch: [96]  [310/312]  eta: 0:00:02  lr: 0.003299  min_lr: 0.003299  loss: 2.6632 (2.4697)  weight_decay: 0.0500 (0.0500)  time: 1.0015  data: 0.0001  max mem: 78493
Epoch: [96]  [311/312]  eta: 0:00:01  lr: 0.003299  min_lr: 0.003299  loss: 2.6632 (2.4699)  weight_decay: 0.0500 (0.0500)  time: 1.0015  data: 0.0001  max mem: 78493
Epoch: [96] Total time: 0:05:32 (1.0671 s / it)
Averaged stats: lr: 0.003299  min_lr: 0.003299  loss: 2.6632 (2.4601)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:10  loss: 0.8214 (0.8214)  acc1: 79.8177 (79.8177)  acc5: 94.5312 (94.5312)  time: 7.7903  data: 7.5140  max mem: 78493
Test:  [8/9]  eta: 0:00:01  loss: 1.2305 (1.0810)  acc1: 72.9167 (73.2480)  acc5: 91.0156 (91.6320)  time: 1.1193  data: 0.8904  max mem: 78493
Test: Total time: 0:00:10 (1.1496 s / it)
* Acc@1 73.346 Acc@5 91.490 loss 1.075
Accuracy of the model on the 50000 test images: 73.3%
Max accuracy: 73.52%
Epoch: [97]  [  0/312]  eta: 1:20:50  lr: 0.003299  min_lr: 0.003299  loss: 2.5521 (2.5521)  weight_decay: 0.0500 (0.0500)  time: 15.5473  data: 14.5419  max mem: 78493
Epoch: [97]  [ 10/312]  eta: 0:12:27  lr: 0.003299  min_lr: 0.003299  loss: 2.5290 (2.3904)  weight_decay: 0.0500 (0.0500)  time: 2.4765  data: 1.3227  max mem: 78493
Epoch: [97]  [ 20/312]  eta: 0:08:41  lr: 0.003298  min_lr: 0.003298  loss: 2.4679 (2.3737)  weight_decay: 0.0500 (0.0500)  time: 1.0997  data: 0.0007  max mem: 78493
Epoch: [97]  [ 30/312]  eta: 0:07:13  lr: 0.003297  min_lr: 0.003297  loss: 2.4591 (2.3726)  weight_decay: 0.0500 (0.0500)  time: 1.0179  data: 0.0006  max mem: 78493
Epoch: [97]  [ 40/312]  eta: 0:06:22  lr: 0.003297  min_lr: 0.003297  loss: 2.4971 (2.4068)  weight_decay: 0.0500 (0.0500)  time: 1.0088  data: 0.0014  max mem: 78493
Epoch: [97]  [ 50/312]  eta: 0:05:48  lr: 0.003296  min_lr: 0.003296  loss: 2.5392 (2.4132)  weight_decay: 0.0500 (0.0500)  time: 1.0108  data: 0.0014  max mem: 78493
Epoch: [97]  [ 60/312]  eta: 0:05:21  lr: 0.003296  min_lr: 0.003296  loss: 2.4764 (2.4289)  weight_decay: 0.0500 (0.0500)  time: 1.0077  data: 0.0004  max mem: 78493
Epoch: [97]  [ 70/312]  eta: 0:04:59  lr: 0.003295  min_lr: 0.003295  loss: 2.5230 (2.4334)  weight_decay: 0.0500 (0.0500)  time: 1.0078  data: 0.0004  max mem: 78493
Epoch: [97]  [ 80/312]  eta: 0:04:40  lr: 0.003295  min_lr: 0.003295  loss: 2.5590 (2.4448)  weight_decay: 0.0500 (0.0500)  time: 1.0092  data: 0.0004  max mem: 78493
Epoch: [97]  [ 90/312]  eta: 0:04:23  lr: 0.003294  min_lr: 0.003294  loss: 2.5147 (2.4321)  weight_decay: 0.0500 (0.0500)  time: 1.0066  data: 0.0004  max mem: 78493
Epoch: [97]  [100/312]  eta: 0:04:08  lr: 0.003294  min_lr: 0.003294  loss: 2.3953 (2.4523)  weight_decay: 0.0500 (0.0500)  time: 1.0057  data: 0.0004  max mem: 78493
Epoch: [97]  [110/312]  eta: 0:03:53  lr: 0.003293  min_lr: 0.003293  loss: 2.4616 (2.4461)  weight_decay: 0.0500 (0.0500)  time: 1.0090  data: 0.0004  max mem: 78493
Epoch: [97]  [120/312]  eta: 0:03:39  lr: 0.003292  min_lr: 0.003292  loss: 2.4583 (2.4438)  weight_decay: 0.0500 (0.0500)  time: 1.0090  data: 0.0004  max mem: 78493
Epoch: [97]  [130/312]  eta: 0:03:26  lr: 0.003292  min_lr: 0.003292  loss: 2.4593 (2.4450)  weight_decay: 0.0500 (0.0500)  time: 1.0062  data: 0.0004  max mem: 78493
Epoch: [97]  [140/312]  eta: 0:03:13  lr: 0.003291  min_lr: 0.003291  loss: 2.4593 (2.4369)  weight_decay: 0.0500 (0.0500)  time: 1.0060  data: 0.0004  max mem: 78493
Epoch: [97]  [150/312]  eta: 0:03:00  lr: 0.003291  min_lr: 0.003291  loss: 2.1053 (2.4249)  weight_decay: 0.0500 (0.0500)  time: 1.0051  data: 0.0004  max mem: 78493
Epoch: [97]  [160/312]  eta: 0:02:48  lr: 0.003290  min_lr: 0.003290  loss: 2.3824 (2.4338)  weight_decay: 0.0500 (0.0500)  time: 1.0046  data: 0.0004  max mem: 78493
Epoch: [97]  [170/312]  eta: 0:02:36  lr: 0.003290  min_lr: 0.003290  loss: 2.5358 (2.4379)  weight_decay: 0.0500 (0.0500)  time: 1.0056  data: 0.0004  max mem: 78493
Epoch: [97]  [180/312]  eta: 0:02:24  lr: 0.003289  min_lr: 0.003289  loss: 2.5542 (2.4428)  weight_decay: 0.0500 (0.0500)  time: 1.0057  data: 0.0004  max mem: 78493
Epoch: [97]  [190/312]  eta: 0:02:13  lr: 0.003289  min_lr: 0.003289  loss: 2.5517 (2.4343)  weight_decay: 0.0500 (0.0500)  time: 1.0058  data: 0.0004  max mem: 78493
Epoch: [97]  [200/312]  eta: 0:02:01  lr: 0.003288  min_lr: 0.003288  loss: 2.5517 (2.4376)  weight_decay: 0.0500 (0.0500)  time: 1.0055  data: 0.0004  max mem: 78493
Epoch: [97]  [210/312]  eta: 0:01:50  lr: 0.003288  min_lr: 0.003288  loss: 2.5791 (2.4368)  weight_decay: 0.0500 (0.0500)  time: 1.0043  data: 0.0004  max mem: 78493
Epoch: [97]  [220/312]  eta: 0:01:39  lr: 0.003287  min_lr: 0.003287  loss: 2.5791 (2.4451)  weight_decay: 0.0500 (0.0500)  time: 1.0044  data: 0.0004  max mem: 78493
Epoch: [97]  [230/312]  eta: 0:01:28  lr: 0.003286  min_lr: 0.003286  loss: 2.5808 (2.4475)  weight_decay: 0.0500 (0.0500)  time: 1.0041  data: 0.0004  max mem: 78493
Epoch: [97]  [240/312]  eta: 0:01:17  lr: 0.003286  min_lr: 0.003286  loss: 2.4045 (2.4455)  weight_decay: 0.0500 (0.0500)  time: 1.0032  data: 0.0005  max mem: 78493
Epoch: [97]  [250/312]  eta: 0:01:06  lr: 0.003285  min_lr: 0.003285  loss: 2.2378 (2.4375)  weight_decay: 0.0500 (0.0500)  time: 1.0035  data: 0.0004  max mem: 78493
Epoch: [97]  [260/312]  eta: 0:00:55  lr: 0.003285  min_lr: 0.003285  loss: 2.0572 (2.4310)  weight_decay: 0.0500 (0.0500)  time: 1.0037  data: 0.0004  max mem: 78493
Epoch: [97]  [270/312]  eta: 0:00:44  lr: 0.003284  min_lr: 0.003284  loss: 2.0572 (2.4240)  weight_decay: 0.0500 (0.0500)  time: 1.0042  data: 0.0004  max mem: 78493
Epoch: [97]  [280/312]  eta: 0:00:34  lr: 0.003284  min_lr: 0.003284  loss: 2.2102 (2.4251)  weight_decay: 0.0500 (0.0500)  time: 1.0051  data: 0.0010  max mem: 78493
Epoch: [97]  [290/312]  eta: 0:00:23  lr: 0.003283  min_lr: 0.003283  loss: 2.5165 (2.4282)  weight_decay: 0.0500 (0.0500)  time: 1.0035  data: 0.0009  max mem: 78493
Epoch: [97]  [300/312]  eta: 0:00:12  lr: 0.003283  min_lr: 0.003283  loss: 2.4169 (2.4216)  weight_decay: 0.0500 (0.0500)  time: 1.0015  data: 0.0001  max mem: 78493
Epoch: [97]  [310/312]  eta: 0:00:02  lr: 0.003282  min_lr: 0.003282  loss: 2.1801 (2.4153)  weight_decay: 0.0500 (0.0500)  time: 1.0013  data: 0.0001  max mem: 78493
Epoch: [97]  [311/312]  eta: 0:00:01  lr: 0.003282  min_lr: 0.003282  loss: 2.1801 (2.4160)  weight_decay: 0.0500 (0.0500)  time: 1.0013  data: 0.0001  max mem: 78493
Epoch: [97] Total time: 0:05:32 (1.0642 s / it)
Averaged stats: lr: 0.003282  min_lr: 0.003282  loss: 2.1801 (2.4402)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:08  loss: 0.8202 (0.8202)  acc1: 80.9896 (80.9896)  acc5: 93.7500 (93.7500)  time: 7.6203  data: 7.3389  max mem: 78493
Test:  [8/9]  eta: 0:00:01  loss: 1.1251 (1.0519)  acc1: 72.1354 (73.7600)  acc5: 91.0156 (91.5520)  time: 1.0457  data: 0.8155  max mem: 78493
Test: Total time: 0:00:09 (1.0555 s / it)
* Acc@1 73.686 Acc@5 91.634 loss 1.047
Accuracy of the model on the 50000 test images: 73.7%
Max accuracy: 73.69%
Epoch: [98]  [  0/312]  eta: 1:19:29  lr: 0.003282  min_lr: 0.003282  loss: 2.4588 (2.4588)  weight_decay: 0.0500 (0.0500)  time: 15.2881  data: 12.3120  max mem: 78493
Epoch: [98]  [ 10/312]  eta: 0:12:46  lr: 0.003281  min_lr: 0.003281  loss: 2.4588 (2.4488)  weight_decay: 0.0500 (0.0500)  time: 2.5387  data: 1.3275  max mem: 78493
Epoch: [98]  [ 20/312]  eta: 0:08:49  lr: 0.003281  min_lr: 0.003281  loss: 2.4844 (2.4466)  weight_decay: 0.0500 (0.0500)  time: 1.1392  data: 0.1162  max mem: 78493
Epoch: [98]  [ 30/312]  eta: 0:07:18  lr: 0.003280  min_lr: 0.003280  loss: 2.6290 (2.4547)  weight_decay: 0.0500 (0.0500)  time: 1.0115  data: 0.0019  max mem: 78493
Epoch: [98]  [ 40/312]  eta: 0:06:25  lr: 0.003280  min_lr: 0.003280  loss: 2.6337 (2.4439)  weight_decay: 0.0500 (0.0500)  time: 1.0054  data: 0.0004  max mem: 78493
Epoch: [98]  [ 50/312]  eta: 0:05:50  lr: 0.003279  min_lr: 0.003279  loss: 2.6337 (2.4658)  weight_decay: 0.0500 (0.0500)  time: 1.0056  data: 0.0004  max mem: 78493
Epoch: [98]  [ 60/312]  eta: 0:05:23  lr: 0.003279  min_lr: 0.003279  loss: 2.4852 (2.4435)  weight_decay: 0.0500 (0.0500)  time: 1.0107  data: 0.0004  max mem: 78493
Epoch: [98]  [ 70/312]  eta: 0:05:01  lr: 0.003278  min_lr: 0.003278  loss: 2.4767 (2.4354)  weight_decay: 0.0500 (0.0500)  time: 1.0094  data: 0.0004  max mem: 78493
Epoch: [98]  [ 80/312]  eta: 0:04:42  lr: 0.003278  min_lr: 0.003278  loss: 2.5379 (2.4667)  weight_decay: 0.0500 (0.0500)  time: 1.0072  data: 0.0004  max mem: 78493
Epoch: [98]  [ 90/312]  eta: 0:04:25  lr: 0.003277  min_lr: 0.003277  loss: 2.6590 (2.4752)  weight_decay: 0.0500 (0.0500)  time: 1.0086  data: 0.0004  max mem: 78493
Epoch: [98]  [100/312]  eta: 0:04:09  lr: 0.003276  min_lr: 0.003276  loss: 2.5389 (2.4601)  weight_decay: 0.0500 (0.0500)  time: 1.0078  data: 0.0004  max mem: 78493
Epoch: [98]  [110/312]  eta: 0:03:54  lr: 0.003276  min_lr: 0.003276  loss: 2.0861 (2.4311)  weight_decay: 0.0500 (0.0500)  time: 1.0084  data: 0.0004  max mem: 78493
Epoch: [98]  [120/312]  eta: 0:03:40  lr: 0.003275  min_lr: 0.003275  loss: 2.1354 (2.4343)  weight_decay: 0.0500 (0.0500)  time: 1.0083  data: 0.0005  max mem: 78493
Epoch: [98]  [130/312]  eta: 0:03:26  lr: 0.003275  min_lr: 0.003275  loss: 2.4813 (2.4328)  weight_decay: 0.0500 (0.0500)  time: 1.0085  data: 0.0005  max mem: 78493
Epoch: [98]  [140/312]  eta: 0:03:14  lr: 0.003274  min_lr: 0.003274  loss: 2.5048 (2.4388)  weight_decay: 0.0500 (0.0500)  time: 1.0088  data: 0.0005  max mem: 78493
Epoch: [98]  [150/312]  eta: 0:03:01  lr: 0.003274  min_lr: 0.003274  loss: 2.4701 (2.4422)  weight_decay: 0.0500 (0.0500)  time: 1.0091  data: 0.0004  max mem: 78493
Epoch: [98]  [160/312]  eta: 0:02:49  lr: 0.003273  min_lr: 0.003273  loss: 2.3780 (2.4372)  weight_decay: 0.0500 (0.0500)  time: 1.0099  data: 0.0004  max mem: 78493
Epoch: [98]  [170/312]  eta: 0:02:37  lr: 0.003273  min_lr: 0.003273  loss: 2.4552 (2.4395)  weight_decay: 0.0500 (0.0500)  time: 1.0076  data: 0.0004  max mem: 78493
Epoch: [98]  [180/312]  eta: 0:02:25  lr: 0.003272  min_lr: 0.003272  loss: 2.5584 (2.4415)  weight_decay: 0.0500 (0.0500)  time: 1.0061  data: 0.0004  max mem: 78493
Epoch: [98]  [190/312]  eta: 0:02:13  lr: 0.003271  min_lr: 0.003271  loss: 2.5546 (2.4458)  weight_decay: 0.0500 (0.0500)  time: 1.0097  data: 0.0004  max mem: 78493
Epoch: [98]  [200/312]  eta: 0:02:02  lr: 0.003271  min_lr: 0.003271  loss: 2.5589 (2.4507)  weight_decay: 0.0500 (0.0500)  time: 1.0129  data: 0.0004  max mem: 78493
Epoch: [98]  [210/312]  eta: 0:01:51  lr: 0.003270  min_lr: 0.003270  loss: 2.4907 (2.4493)  weight_decay: 0.0500 (0.0500)  time: 1.0101  data: 0.0004  max mem: 78493
Epoch: [98]  [220/312]  eta: 0:01:39  lr: 0.003270  min_lr: 0.003270  loss: 2.4922 (2.4538)  weight_decay: 0.0500 (0.0500)  time: 1.0077  data: 0.0005  max mem: 78493
Epoch: [98]  [230/312]  eta: 0:01:28  lr: 0.003269  min_lr: 0.003269  loss: 2.6041 (2.4568)  weight_decay: 0.0500 (0.0500)  time: 1.0072  data: 0.0005  max mem: 78493
Epoch: [98]  [240/312]  eta: 0:01:17  lr: 0.003269  min_lr: 0.003269  loss: 2.6868 (2.4697)  weight_decay: 0.0500 (0.0500)  time: 1.0082  data: 0.0011  max mem: 78493
Epoch: [98]  [250/312]  eta: 0:01:06  lr: 0.003268  min_lr: 0.003268  loss: 2.6868 (2.4768)  weight_decay: 0.0500 (0.0500)  time: 1.0076  data: 0.0011  max mem: 78493
Epoch: [98]  [260/312]  eta: 0:00:55  lr: 0.003268  min_lr: 0.003268  loss: 2.6462 (2.4731)  weight_decay: 0.0500 (0.0500)  time: 1.0066  data: 0.0005  max mem: 78493
Epoch: [98]  [270/312]  eta: 0:00:44  lr: 0.003267  min_lr: 0.003267  loss: 2.4499 (2.4716)  weight_decay: 0.0500 (0.0500)  time: 1.0073  data: 0.0004  max mem: 78493
Epoch: [98]  [280/312]  eta: 0:00:34  lr: 0.003266  min_lr: 0.003266  loss: 2.4545 (2.4722)  weight_decay: 0.0500 (0.0500)  time: 1.0073  data: 0.0010  max mem: 78493
Epoch: [98]  [290/312]  eta: 0:00:23  lr: 0.003266  min_lr: 0.003266  loss: 2.6184 (2.4802)  weight_decay: 0.0500 (0.0500)  time: 1.0042  data: 0.0009  max mem: 78493
Epoch: [98]  [300/312]  eta: 0:00:12  lr: 0.003265  min_lr: 0.003265  loss: 2.6439 (2.4829)  weight_decay: 0.0500 (0.0500)  time: 1.0013  data: 0.0001  max mem: 78493
Epoch: [98]  [310/312]  eta: 0:00:02  lr: 0.003265  min_lr: 0.003265  loss: 2.4796 (2.4811)  weight_decay: 0.0500 (0.0500)  time: 1.0014  data: 0.0001  max mem: 78493
Epoch: [98]  [311/312]  eta: 0:00:01  lr: 0.003265  min_lr: 0.003265  loss: 2.5758 (2.4819)  weight_decay: 0.0500 (0.0500)  time: 1.0013  data: 0.0001  max mem: 78493
Epoch: [98] Total time: 0:05:33 (1.0678 s / it)
Averaged stats: lr: 0.003265  min_lr: 0.003265  loss: 2.5758 (2.4429)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:15  loss: 0.7605 (0.7605)  acc1: 81.1198 (81.1198)  acc5: 94.5312 (94.5312)  time: 8.4219  data: 8.1615  max mem: 78493
Test:  [8/9]  eta: 0:00:01  loss: 1.0878 (1.0499)  acc1: 73.8281 (74.3040)  acc5: 92.1875 (91.9040)  time: 1.1409  data: 0.9069  max mem: 78493
Test: Total time: 0:00:10 (1.1862 s / it)
* Acc@1 74.266 Acc@5 92.044 loss 1.027
Accuracy of the model on the 50000 test images: 74.3%
Max accuracy: 74.27%
Epoch: [99]  [  0/312]  eta: 1:24:58  lr: 0.003265  min_lr: 0.003265  loss: 2.3336 (2.3336)  weight_decay: 0.0500 (0.0500)  time: 16.3398  data: 15.3072  max mem: 78493
Epoch: [99]  [ 10/312]  eta: 0:13:30  lr: 0.003264  min_lr: 0.003264  loss: 2.3336 (2.2848)  weight_decay: 0.0500 (0.0500)  time: 2.6824  data: 1.3922  max mem: 78493
Epoch: [99]  [ 20/312]  eta: 0:09:11  lr: 0.003264  min_lr: 0.003264  loss: 2.4245 (2.3600)  weight_decay: 0.0500 (0.0500)  time: 1.1655  data: 0.0006  max mem: 78493
Epoch: [99]  [ 30/312]  eta: 0:07:32  lr: 0.003263  min_lr: 0.003263  loss: 2.5579 (2.4082)  weight_decay: 0.0500 (0.0500)  time: 1.0138  data: 0.0005  max mem: 78493
Epoch: [99]  [ 40/312]  eta: 0:06:37  lr: 0.003262  min_lr: 0.003262  loss: 2.4335 (2.4087)  weight_decay: 0.0500 (0.0500)  time: 1.0103  data: 0.0004  max mem: 78493
Epoch: [99]  [ 50/312]  eta: 0:05:59  lr: 0.003262  min_lr: 0.003262  loss: 2.6188 (2.4172)  weight_decay: 0.0500 (0.0500)  time: 1.0085  data: 0.0004  max mem: 78493
Epoch: [99]  [ 60/312]  eta: 0:05:30  lr: 0.003261  min_lr: 0.003261  loss: 2.6188 (2.4172)  weight_decay: 0.0500 (0.0500)  time: 1.0092  data: 0.0005  max mem: 78493
Epoch: [99]  [ 70/312]  eta: 0:05:07  lr: 0.003261  min_lr: 0.003261  loss: 2.4227 (2.3985)  weight_decay: 0.0500 (0.0500)  time: 1.0072  data: 0.0004  max mem: 78493
Epoch: [99]  [ 80/312]  eta: 0:04:46  lr: 0.003260  min_lr: 0.003260  loss: 2.4048 (2.3945)  weight_decay: 0.0500 (0.0500)  time: 1.0063  data: 0.0005  max mem: 78493
Epoch: [99]  [ 90/312]  eta: 0:04:28  lr: 0.003260  min_lr: 0.003260  loss: 2.4553 (2.4026)  weight_decay: 0.0500 (0.0500)  time: 1.0071  data: 0.0005  max mem: 78493
Epoch: [99]  [100/312]  eta: 0:04:12  lr: 0.003259  min_lr: 0.003259  loss: 2.4308 (2.3956)  weight_decay: 0.0500 (0.0500)  time: 1.0078  data: 0.0004  max mem: 78493
Epoch: [99]  [110/312]  eta: 0:03:57  lr: 0.003258  min_lr: 0.003258  loss: 2.3891 (2.3928)  weight_decay: 0.0500 (0.0500)  time: 1.0075  data: 0.0004  max mem: 78493
Epoch: [99]  [120/312]  eta: 0:03:42  lr: 0.003258  min_lr: 0.003258  loss: 2.3335 (2.3842)  weight_decay: 0.0500 (0.0500)  time: 1.0072  data: 0.0004  max mem: 78493
Epoch: [99]  [130/312]  eta: 0:03:29  lr: 0.003257  min_lr: 0.003257  loss: 2.4111 (2.3926)  weight_decay: 0.0500 (0.0500)  time: 1.0066  data: 0.0004  max mem: 78493
Epoch: [99]  [140/312]  eta: 0:03:15  lr: 0.003257  min_lr: 0.003257  loss: 2.4937 (2.3938)  weight_decay: 0.0500 (0.0500)  time: 1.0054  data: 0.0004  max mem: 78493
Epoch: [99]  [150/312]  eta: 0:03:03  lr: 0.003256  min_lr: 0.003256  loss: 2.4937 (2.3990)  weight_decay: 0.0500 (0.0500)  time: 1.0055  data: 0.0004  max mem: 78493
Epoch: [99]  [160/312]  eta: 0:02:50  lr: 0.003256  min_lr: 0.003256  loss: 2.5980 (2.4223)  weight_decay: 0.0500 (0.0500)  time: 1.0048  data: 0.0013  max mem: 78493
Epoch: [99]  [170/312]  eta: 0:02:38  lr: 0.003255  min_lr: 0.003255  loss: 2.7154 (2.4287)  weight_decay: 0.0500 (0.0500)  time: 1.0052  data: 0.0012  max mem: 78493
Epoch: [99]  [180/312]  eta: 0:02:26  lr: 0.003255  min_lr: 0.003255  loss: 2.6097 (2.4367)  weight_decay: 0.0500 (0.0500)  time: 1.0071  data: 0.0012  max mem: 78493
Epoch: [99]  [190/312]  eta: 0:02:14  lr: 0.003254  min_lr: 0.003254  loss: 2.5085 (2.4334)  weight_decay: 0.0500 (0.0500)  time: 1.0077  data: 0.0012  max mem: 78493
Epoch: [99]  [200/312]  eta: 0:02:03  lr: 0.003253  min_lr: 0.003253  loss: 2.4811 (2.4425)  weight_decay: 0.0500 (0.0500)  time: 1.0073  data: 0.0004  max mem: 78493
Epoch: [99]  [210/312]  eta: 0:01:51  lr: 0.003253  min_lr: 0.003253  loss: 2.4811 (2.4467)  weight_decay: 0.0500 (0.0500)  time: 1.0076  data: 0.0005  max mem: 78493
Epoch: [99]  [220/312]  eta: 0:01:40  lr: 0.003252  min_lr: 0.003252  loss: 2.5931 (2.4541)  weight_decay: 0.0500 (0.0500)  time: 1.0082  data: 0.0005  max mem: 78493
Epoch: [99]  [230/312]  eta: 0:01:29  lr: 0.003252  min_lr: 0.003252  loss: 2.5937 (2.4559)  weight_decay: 0.0500 (0.0500)  time: 1.0076  data: 0.0004  max mem: 78493
Epoch: [99]  [240/312]  eta: 0:01:18  lr: 0.003251  min_lr: 0.003251  loss: 2.6280 (2.4630)  weight_decay: 0.0500 (0.0500)  time: 1.0059  data: 0.0004  max mem: 78493
Epoch: [99]  [250/312]  eta: 0:01:07  lr: 0.003251  min_lr: 0.003251  loss: 2.6356 (2.4685)  weight_decay: 0.0500 (0.0500)  time: 1.0051  data: 0.0004  max mem: 78493
Epoch: [99]  [260/312]  eta: 0:00:56  lr: 0.003250  min_lr: 0.003250  loss: 2.6304 (2.4670)  weight_decay: 0.0500 (0.0500)  time: 1.0059  data: 0.0004  max mem: 78493
Epoch: [99]  [270/312]  eta: 0:00:45  lr: 0.003250  min_lr: 0.003250  loss: 2.5877 (2.4685)  weight_decay: 0.0500 (0.0500)  time: 1.0066  data: 0.0004  max mem: 78493
Epoch: [99]  [280/312]  eta: 0:00:34  lr: 0.003249  min_lr: 0.003249  loss: 2.3940 (2.4624)  weight_decay: 0.0500 (0.0500)  time: 1.0061  data: 0.0011  max mem: 78493
Epoch: [99]  [290/312]  eta: 0:00:23  lr: 0.003248  min_lr: 0.003248  loss: 2.3896 (2.4589)  weight_decay: 0.0500 (0.0500)  time: 1.0037  data: 0.0009  max mem: 78493
Epoch: [99]  [300/312]  eta: 0:00:12  lr: 0.003248  min_lr: 0.003248  loss: 2.4613 (2.4560)  weight_decay: 0.0500 (0.0500)  time: 1.0018  data: 0.0001  max mem: 78493
Epoch: [99]  [310/312]  eta: 0:00:02  lr: 0.003247  min_lr: 0.003247  loss: 2.3791 (2.4528)  weight_decay: 0.0500 (0.0500)  time: 1.0015  data: 0.0001  max mem: 78493
Epoch: [99]  [311/312]  eta: 0:00:01  lr: 0.003247  min_lr: 0.003247  loss: 2.3791 (2.4534)  weight_decay: 0.0500 (0.0500)  time: 1.0014  data: 0.0001  max mem: 78493
Epoch: [99] Total time: 0:05:34 (1.0714 s / it)
Averaged stats: lr: 0.003247  min_lr: 0.003247  loss: 2.3791 (2.4365)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:13  loss: 0.7589 (0.7589)  acc1: 80.2083 (80.2083)  acc5: 94.2708 (94.2708)  time: 8.1516  data: 7.8772  max mem: 78493
Test:  [8/9]  eta: 0:00:01  loss: 1.0512 (1.0368)  acc1: 73.5677 (73.9520)  acc5: 92.4479 (91.7760)  time: 1.1163  data: 0.8753  max mem: 78493
Test: Total time: 0:00:10 (1.1311 s / it)
* Acc@1 74.352 Acc@5 92.058 loss 1.021
Accuracy of the model on the 50000 test images: 74.4%
Max accuracy: 74.35%
Epoch: [100]  [  0/312]  eta: 1:22:41  lr: 0.003247  min_lr: 0.003247  loss: 1.7984 (1.7984)  weight_decay: 0.0500 (0.0500)  time: 15.9038  data: 12.5433  max mem: 78493
Epoch: [100]  [ 10/312]  eta: 0:12:48  lr: 0.003247  min_lr: 0.003247  loss: 2.3715 (2.2508)  weight_decay: 0.0500 (0.0500)  time: 2.5455  data: 1.1588  max mem: 78493
Epoch: [100]  [ 20/312]  eta: 0:08:51  lr: 0.003246  min_lr: 0.003246  loss: 2.3715 (2.3210)  weight_decay: 0.0500 (0.0500)  time: 1.1155  data: 0.0114  max mem: 78493
Epoch: [100]  [ 30/312]  eta: 0:07:19  lr: 0.003245  min_lr: 0.003245  loss: 2.5421 (2.3700)  weight_decay: 0.0500 (0.0500)  time: 1.0142  data: 0.0014  max mem: 78493
Epoch: [100]  [ 40/312]  eta: 0:06:27  lr: 0.003245  min_lr: 0.003245  loss: 2.5994 (2.4011)  weight_decay: 0.0500 (0.0500)  time: 1.0064  data: 0.0005  max mem: 78493
Epoch: [100]  [ 50/312]  eta: 0:05:51  lr: 0.003244  min_lr: 0.003244  loss: 2.5310 (2.4174)  weight_decay: 0.0500 (0.0500)  time: 1.0073  data: 0.0005  max mem: 78493
Epoch: [100]  [ 60/312]  eta: 0:05:24  lr: 0.003244  min_lr: 0.003244  loss: 2.5119 (2.4125)  weight_decay: 0.0500 (0.0500)  time: 1.0081  data: 0.0004  max mem: 78493
Epoch: [100]  [ 70/312]  eta: 0:05:02  lr: 0.003243  min_lr: 0.003243  loss: 2.4816 (2.4162)  weight_decay: 0.0500 (0.0500)  time: 1.0088  data: 0.0005  max mem: 78493
Epoch: [100]  [ 80/312]  eta: 0:04:42  lr: 0.003243  min_lr: 0.003243  loss: 2.4983 (2.4309)  weight_decay: 0.0500 (0.0500)  time: 1.0092  data: 0.0005  max mem: 78493
Epoch: [100]  [ 90/312]  eta: 0:04:25  lr: 0.003242  min_lr: 0.003242  loss: 2.4983 (2.4234)  weight_decay: 0.0500 (0.0500)  time: 1.0081  data: 0.0005  max mem: 78493
Epoch: [100]  [100/312]  eta: 0:04:09  lr: 0.003242  min_lr: 0.003242  loss: 2.1321 (2.3966)  weight_decay: 0.0500 (0.0500)  time: 1.0085  data: 0.0005  max mem: 78493
Epoch: [100]  [110/312]  eta: 0:03:54  lr: 0.003241  min_lr: 0.003241  loss: 2.4210 (2.4010)  weight_decay: 0.0500 (0.0500)  time: 1.0087  data: 0.0004  max mem: 78493
Epoch: [100]  [120/312]  eta: 0:03:40  lr: 0.003240  min_lr: 0.003240  loss: 2.3391 (2.3843)  weight_decay: 0.0500 (0.0500)  time: 1.0074  data: 0.0004  max mem: 78493
Epoch: [100]  [130/312]  eta: 0:03:27  lr: 0.003240  min_lr: 0.003240  loss: 2.4201 (2.3983)  weight_decay: 0.0500 (0.0500)  time: 1.0075  data: 0.0004  max mem: 78493
Epoch: [100]  [140/312]  eta: 0:03:14  lr: 0.003239  min_lr: 0.003239  loss: 2.6344 (2.4177)  weight_decay: 0.0500 (0.0500)  time: 1.0078  data: 0.0004  max mem: 78493
Epoch: [100]  [150/312]  eta: 0:03:01  lr: 0.003239  min_lr: 0.003239  loss: 2.5699 (2.4094)  weight_decay: 0.0500 (0.0500)  time: 1.0078  data: 0.0004  max mem: 78493
Epoch: [100]  [160/312]  eta: 0:02:49  lr: 0.003238  min_lr: 0.003238  loss: 2.5056 (2.4135)  weight_decay: 0.0500 (0.0500)  time: 1.0100  data: 0.0004  max mem: 78493
Epoch: [100]  [170/312]  eta: 0:02:37  lr: 0.003238  min_lr: 0.003238  loss: 2.6019 (2.4184)  weight_decay: 0.0500 (0.0500)  time: 1.0120  data: 0.0004  max mem: 78493
Epoch: [100]  [180/312]  eta: 0:02:25  lr: 0.003237  min_lr: 0.003237  loss: 2.4498 (2.4148)  weight_decay: 0.0500 (0.0500)  time: 1.0104  data: 0.0004  max mem: 78493
Epoch: [100]  [190/312]  eta: 0:02:13  lr: 0.003236  min_lr: 0.003236  loss: 2.5917 (2.4305)  weight_decay: 0.0500 (0.0500)  time: 1.0078  data: 0.0004  max mem: 78493
Epoch: [100]  [200/312]  eta: 0:02:02  lr: 0.003236  min_lr: 0.003236  loss: 2.5917 (2.4240)  weight_decay: 0.0500 (0.0500)  time: 1.0077  data: 0.0004  max mem: 78493
Epoch: [100]  [210/312]  eta: 0:01:51  lr: 0.003235  min_lr: 0.003235  loss: 2.4448 (2.4236)  weight_decay: 0.0500 (0.0500)  time: 1.0063  data: 0.0004  max mem: 78493
Epoch: [100]  [220/312]  eta: 0:01:39  lr: 0.003235  min_lr: 0.003235  loss: 2.5068 (2.4274)  weight_decay: 0.0500 (0.0500)  time: 1.0059  data: 0.0004  max mem: 78493
Epoch: [100]  [230/312]  eta: 0:01:28  lr: 0.003234  min_lr: 0.003234  loss: 2.6495 (2.4352)  weight_decay: 0.0500 (0.0500)  time: 1.0059  data: 0.0004  max mem: 78493
Epoch: [100]  [240/312]  eta: 0:01:17  lr: 0.003234  min_lr: 0.003234  loss: 2.7709 (2.4438)  weight_decay: 0.0500 (0.0500)  time: 1.0053  data: 0.0004  max mem: 78493
Epoch: [100]  [250/312]  eta: 0:01:06  lr: 0.003233  min_lr: 0.003233  loss: 2.4804 (2.4410)  weight_decay: 0.0500 (0.0500)  time: 1.0070  data: 0.0005  max mem: 78493
Epoch: [100]  [260/312]  eta: 0:00:55  lr: 0.003232  min_lr: 0.003232  loss: 2.4719 (2.4429)  weight_decay: 0.0500 (0.0500)  time: 1.0095  data: 0.0014  max mem: 78493
Epoch: [100]  [270/312]  eta: 0:00:44  lr: 0.003232  min_lr: 0.003232  loss: 2.5329 (2.4413)  weight_decay: 0.0500 (0.0500)  time: 1.0087  data: 0.0014  max mem: 78493
Epoch: [100]  [280/312]  eta: 0:00:34  lr: 0.003231  min_lr: 0.003231  loss: 2.5595 (2.4457)  weight_decay: 0.0500 (0.0500)  time: 1.0069  data: 0.0010  max mem: 78493
Epoch: [100]  [290/312]  eta: 0:00:23  lr: 0.003231  min_lr: 0.003231  loss: 2.5055 (2.4431)  weight_decay: 0.0500 (0.0500)  time: 1.0043  data: 0.0009  max mem: 78493
Epoch: [100]  [300/312]  eta: 0:00:12  lr: 0.003230  min_lr: 0.003230  loss: 2.5055 (2.4450)  weight_decay: 0.0500 (0.0500)  time: 1.0014  data: 0.0001  max mem: 78493
Epoch: [100]  [310/312]  eta: 0:00:02  lr: 0.003230  min_lr: 0.003230  loss: 2.4725 (2.4436)  weight_decay: 0.0500 (0.0500)  time: 1.0016  data: 0.0001  max mem: 78493
Epoch: [100]  [311/312]  eta: 0:00:01  lr: 0.003230  min_lr: 0.003230  loss: 2.4696 (2.4420)  weight_decay: 0.0500 (0.0500)  time: 1.0017  data: 0.0001  max mem: 78493
Epoch: [100] Total time: 0:05:33 (1.0677 s / it)
Averaged stats: lr: 0.003230  min_lr: 0.003230  loss: 2.4696 (2.4370)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:13  loss: 0.8235 (0.8235)  acc1: 78.7760 (78.7760)  acc5: 93.6198 (93.6198)  time: 8.1300  data: 7.8515  max mem: 78493
Test:  [8/9]  eta: 0:00:01  loss: 1.1747 (1.0475)  acc1: 72.0052 (73.5520)  acc5: 90.6250 (91.4080)  time: 1.1016  data: 0.8725  max mem: 78493
Test: Total time: 0:00:10 (1.1453 s / it)
* Acc@1 73.950 Acc@5 91.624 loss 1.039
Accuracy of the model on the 50000 test images: 74.0%
Max accuracy: 74.35%
Epoch: [101]  [  0/312]  eta: 1:22:54  lr: 0.003230  min_lr: 0.003230  loss: 2.4455 (2.4455)  weight_decay: 0.0500 (0.0500)  time: 15.9455  data: 13.4457  max mem: 78493
Epoch: [101]  [ 10/312]  eta: 0:13:21  lr: 0.003229  min_lr: 0.003229  loss: 2.5348 (2.5569)  weight_decay: 0.0500 (0.0500)  time: 2.6527  data: 1.2231  max mem: 78493
Epoch: [101]  [ 20/312]  eta: 0:09:07  lr: 0.003228  min_lr: 0.003228  loss: 2.4834 (2.4972)  weight_decay: 0.0500 (0.0500)  time: 1.1702  data: 0.0007  max mem: 78493
Epoch: [101]  [ 30/312]  eta: 0:07:29  lr: 0.003228  min_lr: 0.003228  loss: 2.4465 (2.4321)  weight_decay: 0.0500 (0.0500)  time: 1.0117  data: 0.0005  max mem: 78493
Epoch: [101]  [ 40/312]  eta: 0:06:34  lr: 0.003227  min_lr: 0.003227  loss: 2.0095 (2.3816)  weight_decay: 0.0500 (0.0500)  time: 1.0064  data: 0.0004  max mem: 78493
Epoch: [101]  [ 50/312]  eta: 0:05:57  lr: 0.003227  min_lr: 0.003227  loss: 2.4360 (2.3799)  weight_decay: 0.0500 (0.0500)  time: 1.0061  data: 0.0005  max mem: 78493
Epoch: [101]  [ 60/312]  eta: 0:05:28  lr: 0.003226  min_lr: 0.003226  loss: 2.4827 (2.4022)  weight_decay: 0.0500 (0.0500)  time: 1.0059  data: 0.0004  max mem: 78493
Epoch: [101]  [ 70/312]  eta: 0:05:05  lr: 0.003226  min_lr: 0.003226  loss: 2.6633 (2.4354)  weight_decay: 0.0500 (0.0500)  time: 1.0073  data: 0.0004  max mem: 78493
Epoch: [101]  [ 80/312]  eta: 0:04:45  lr: 0.003225  min_lr: 0.003225  loss: 2.6672 (2.4484)  weight_decay: 0.0500 (0.0500)  time: 1.0084  data: 0.0005  max mem: 78493
Epoch: [101]  [ 90/312]  eta: 0:04:27  lr: 0.003224  min_lr: 0.003224  loss: 2.5038 (2.4433)  weight_decay: 0.0500 (0.0500)  time: 1.0073  data: 0.0004  max mem: 78493
Epoch: [101]  [100/312]  eta: 0:04:11  lr: 0.003224  min_lr: 0.003224  loss: 2.2628 (2.4204)  weight_decay: 0.0500 (0.0500)  time: 1.0078  data: 0.0004  max mem: 78493
Epoch: [101]  [110/312]  eta: 0:03:56  lr: 0.003223  min_lr: 0.003223  loss: 2.1859 (2.4135)  weight_decay: 0.0500 (0.0500)  time: 1.0066  data: 0.0004  max mem: 78493
Epoch: [101]  [120/312]  eta: 0:03:42  lr: 0.003223  min_lr: 0.003223  loss: 2.3618 (2.4102)  weight_decay: 0.0500 (0.0500)  time: 1.0050  data: 0.0005  max mem: 78493
Epoch: [101]  [130/312]  eta: 0:03:28  lr: 0.003222  min_lr: 0.003222  loss: 2.4607 (2.4211)  weight_decay: 0.0500 (0.0500)  time: 1.0060  data: 0.0005  max mem: 78493
Epoch: [101]  [140/312]  eta: 0:03:15  lr: 0.003222  min_lr: 0.003222  loss: 2.5899 (2.4328)  weight_decay: 0.0500 (0.0500)  time: 1.0051  data: 0.0004  max mem: 78493
Epoch: [101]  [150/312]  eta: 0:03:02  lr: 0.003221  min_lr: 0.003221  loss: 2.5733 (2.4275)  weight_decay: 0.0500 (0.0500)  time: 1.0054  data: 0.0004  max mem: 78493
Epoch: [101]  [160/312]  eta: 0:02:50  lr: 0.003220  min_lr: 0.003220  loss: 2.4031 (2.4308)  weight_decay: 0.0500 (0.0500)  time: 1.0066  data: 0.0004  max mem: 78493
Epoch: [101]  [170/312]  eta: 0:02:38  lr: 0.003220  min_lr: 0.003220  loss: 2.6072 (2.4435)  weight_decay: 0.0500 (0.0500)  time: 1.0072  data: 0.0004  max mem: 78493
Epoch: [101]  [180/312]  eta: 0:02:26  lr: 0.003219  min_lr: 0.003219  loss: 2.4136 (2.4362)  weight_decay: 0.0500 (0.0500)  time: 1.0075  data: 0.0004  max mem: 78493
Epoch: [101]  [190/312]  eta: 0:02:14  lr: 0.003219  min_lr: 0.003219  loss: 2.3534 (2.4449)  weight_decay: 0.0500 (0.0500)  time: 1.0079  data: 0.0004  max mem: 78493
Epoch: [101]  [200/312]  eta: 0:02:02  lr: 0.003218  min_lr: 0.003218  loss: 2.5900 (2.4456)  weight_decay: 0.0500 (0.0500)  time: 1.0075  data: 0.0004  max mem: 78493
Epoch: [101]  [210/312]  eta: 0:01:51  lr: 0.003218  min_lr: 0.003218  loss: 2.4492 (2.4455)  weight_decay: 0.0500 (0.0500)  time: 1.0064  data: 0.0004  max mem: 78493
Epoch: [101]  [220/312]  eta: 0:01:40  lr: 0.003217  min_lr: 0.003217  loss: 2.3969 (2.4406)  weight_decay: 0.0500 (0.0500)  time: 1.0074  data: 0.0004  max mem: 78493
Epoch: [101]  [230/312]  eta: 0:01:29  lr: 0.003216  min_lr: 0.003216  loss: 2.3969 (2.4361)  weight_decay: 0.0500 (0.0500)  time: 1.0085  data: 0.0004  max mem: 78493
Epoch: [101]  [240/312]  eta: 0:01:17  lr: 0.003216  min_lr: 0.003216  loss: 2.4839 (2.4403)  weight_decay: 0.0500 (0.0500)  time: 1.0081  data: 0.0004  max mem: 78493
Epoch: [101]  [250/312]  eta: 0:01:06  lr: 0.003215  min_lr: 0.003215  loss: 2.6092 (2.4436)  weight_decay: 0.0500 (0.0500)  time: 1.0072  data: 0.0004  max mem: 78493
Epoch: [101]  [260/312]  eta: 0:00:55  lr: 0.003215  min_lr: 0.003215  loss: 2.6726 (2.4495)  weight_decay: 0.0500 (0.0500)  time: 1.0067  data: 0.0004  max mem: 78493
Epoch: [101]  [270/312]  eta: 0:00:45  lr: 0.003214  min_lr: 0.003214  loss: 2.6689 (2.4504)  weight_decay: 0.0500 (0.0500)  time: 1.0071  data: 0.0004  max mem: 78493
Epoch: [101]  [280/312]  eta: 0:00:34  lr: 0.003214  min_lr: 0.003214  loss: 2.5874 (2.4550)  weight_decay: 0.0500 (0.0500)  time: 1.0081  data: 0.0010  max mem: 78493
Epoch: [101]  [290/312]  eta: 0:00:23  lr: 0.003213  min_lr: 0.003213  loss: 2.5490 (2.4557)  weight_decay: 0.0500 (0.0500)  time: 1.0055  data: 0.0009  max mem: 78493
Epoch: [101]  [300/312]  eta: 0:00:12  lr: 0.003212  min_lr: 0.003212  loss: 2.3975 (2.4538)  weight_decay: 0.0500 (0.0500)  time: 1.0024  data: 0.0001  max mem: 78493
Epoch: [101]  [310/312]  eta: 0:00:02  lr: 0.003212  min_lr: 0.003212  loss: 2.4594 (2.4540)  weight_decay: 0.0500 (0.0500)  time: 1.0023  data: 0.0001  max mem: 78493
Epoch: [101]  [311/312]  eta: 0:00:01  lr: 0.003212  min_lr: 0.003212  loss: 2.4303 (2.4529)  weight_decay: 0.0500 (0.0500)  time: 1.0023  data: 0.0001  max mem: 78493
Epoch: [101] Total time: 0:05:34 (1.0707 s / it)
Averaged stats: lr: 0.003212  min_lr: 0.003212  loss: 2.4303 (2.4311)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:15  loss: 0.8051 (0.8051)  acc1: 81.1198 (81.1198)  acc5: 94.9219 (94.9219)  time: 8.3823  data: 8.1053  max mem: 78493
Test:  [8/9]  eta: 0:00:01  loss: 1.1493 (1.0500)  acc1: 73.4375 (74.0640)  acc5: 90.8854 (91.6800)  time: 1.1296  data: 0.9007  max mem: 78493
Test: Total time: 0:00:10 (1.1643 s / it)
* Acc@1 74.234 Acc@5 91.812 loss 1.043
Accuracy of the model on the 50000 test images: 74.2%
Max accuracy: 74.35%
Epoch: [102]  [  0/312]  eta: 1:26:17  lr: 0.003212  min_lr: 0.003212  loss: 2.9494 (2.9494)  weight_decay: 0.0500 (0.0500)  time: 16.5945  data: 14.6763  max mem: 78493
Epoch: [102]  [ 10/312]  eta: 0:13:03  lr: 0.003211  min_lr: 0.003211  loss: 2.6627 (2.5535)  weight_decay: 0.0500 (0.0500)  time: 2.5948  data: 1.3348  max mem: 78493
Epoch: [102]  [ 20/312]  eta: 0:08:58  lr: 0.003211  min_lr: 0.003211  loss: 2.3480 (2.4342)  weight_decay: 0.0500 (0.0500)  time: 1.1078  data: 0.0006  max mem: 78493
Epoch: [102]  [ 30/312]  eta: 0:07:24  lr: 0.003210  min_lr: 0.003210  loss: 2.2035 (2.3613)  weight_decay: 0.0500 (0.0500)  time: 1.0143  data: 0.0016  max mem: 78493
Epoch: [102]  [ 40/312]  eta: 0:06:30  lr: 0.003209  min_lr: 0.003209  loss: 2.2929 (2.3706)  weight_decay: 0.0500 (0.0500)  time: 1.0083  data: 0.0025  max mem: 78493
Epoch: [102]  [ 50/312]  eta: 0:05:54  lr: 0.003209  min_lr: 0.003209  loss: 2.4341 (2.3754)  weight_decay: 0.0500 (0.0500)  time: 1.0094  data: 0.0013  max mem: 78493
Epoch: [102]  [ 60/312]  eta: 0:05:26  lr: 0.003208  min_lr: 0.003208  loss: 2.3854 (2.3672)  weight_decay: 0.0500 (0.0500)  time: 1.0105  data: 0.0005  max mem: 78493
Epoch: [102]  [ 70/312]  eta: 0:05:03  lr: 0.003208  min_lr: 0.003208  loss: 2.3217 (2.3573)  weight_decay: 0.0500 (0.0500)  time: 1.0065  data: 0.0005  max mem: 78493
Epoch: [102]  [ 80/312]  eta: 0:04:44  lr: 0.003207  min_lr: 0.003207  loss: 2.2594 (2.3624)  weight_decay: 0.0500 (0.0500)  time: 1.0039  data: 0.0005  max mem: 78493
Epoch: [102]  [ 90/312]  eta: 0:04:26  lr: 0.003207  min_lr: 0.003207  loss: 2.5551 (2.3792)  weight_decay: 0.0500 (0.0500)  time: 1.0062  data: 0.0004  max mem: 78493
Epoch: [102]  [100/312]  eta: 0:04:10  lr: 0.003206  min_lr: 0.003206  loss: 2.6109 (2.3971)  weight_decay: 0.0500 (0.0500)  time: 1.0079  data: 0.0005  max mem: 78493
Epoch: [102]  [110/312]  eta: 0:03:55  lr: 0.003205  min_lr: 0.003205  loss: 2.6109 (2.4060)  weight_decay: 0.0500 (0.0500)  time: 1.0061  data: 0.0005  max mem: 78493
Epoch: [102]  [120/312]  eta: 0:03:41  lr: 0.003205  min_lr: 0.003205  loss: 2.5219 (2.4123)  weight_decay: 0.0500 (0.0500)  time: 1.0033  data: 0.0004  max mem: 78493
Epoch: [102]  [130/312]  eta: 0:03:27  lr: 0.003204  min_lr: 0.003204  loss: 2.5362 (2.4222)  weight_decay: 0.0500 (0.0500)  time: 1.0030  data: 0.0005  max mem: 78493
Epoch: [102]  [140/312]  eta: 0:03:14  lr: 0.003204  min_lr: 0.003204  loss: 2.5174 (2.4119)  weight_decay: 0.0500 (0.0500)  time: 1.0041  data: 0.0005  max mem: 78493
Epoch: [102]  [150/312]  eta: 0:03:01  lr: 0.003203  min_lr: 0.003203  loss: 2.3773 (2.4057)  weight_decay: 0.0500 (0.0500)  time: 1.0052  data: 0.0005  max mem: 78493
Epoch: [102]  [160/312]  eta: 0:02:49  lr: 0.003203  min_lr: 0.003203  loss: 2.1227 (2.3879)  weight_decay: 0.0500 (0.0500)  time: 1.0046  data: 0.0004  max mem: 78493
Epoch: [102]  [170/312]  eta: 0:02:37  lr: 0.003202  min_lr: 0.003202  loss: 2.1248 (2.3909)  weight_decay: 0.0500 (0.0500)  time: 1.0045  data: 0.0011  max mem: 78493
Epoch: [102]  [180/312]  eta: 0:02:25  lr: 0.003201  min_lr: 0.003201  loss: 2.5024 (2.3929)  weight_decay: 0.0500 (0.0500)  time: 1.0044  data: 0.0011  max mem: 78493
Epoch: [102]  [190/312]  eta: 0:02:13  lr: 0.003201  min_lr: 0.003201  loss: 2.3900 (2.3855)  weight_decay: 0.0500 (0.0500)  time: 1.0050  data: 0.0004  max mem: 78493
Epoch: [102]  [200/312]  eta: 0:02:02  lr: 0.003200  min_lr: 0.003200  loss: 2.4435 (2.3903)  weight_decay: 0.0500 (0.0500)  time: 1.0054  data: 0.0004  max mem: 78493
Epoch: [102]  [210/312]  eta: 0:01:51  lr: 0.003200  min_lr: 0.003200  loss: 2.5685 (2.3920)  weight_decay: 0.0500 (0.0500)  time: 1.0045  data: 0.0004  max mem: 78493
Epoch: [102]  [220/312]  eta: 0:01:39  lr: 0.003199  min_lr: 0.003199  loss: 2.2646 (2.3855)  weight_decay: 0.0500 (0.0500)  time: 1.0060  data: 0.0004  max mem: 78493
Epoch: [102]  [230/312]  eta: 0:01:28  lr: 0.003199  min_lr: 0.003199  loss: 2.3079 (2.3869)  weight_decay: 0.0500 (0.0500)  time: 1.0084  data: 0.0004  max mem: 78493
Epoch: [102]  [240/312]  eta: 0:01:17  lr: 0.003198  min_lr: 0.003198  loss: 2.3592 (2.3893)  weight_decay: 0.0500 (0.0500)  time: 1.0078  data: 0.0004  max mem: 78493
Epoch: [102]  [250/312]  eta: 0:01:06  lr: 0.003197  min_lr: 0.003197  loss: 2.5147 (2.3942)  weight_decay: 0.0500 (0.0500)  time: 1.0056  data: 0.0004  max mem: 78493
Epoch: [102]  [260/312]  eta: 0:00:55  lr: 0.003197  min_lr: 0.003197  loss: 2.5293 (2.3989)  weight_decay: 0.0500 (0.0500)  time: 1.0054  data: 0.0004  max mem: 78493
Epoch: [102]  [270/312]  eta: 0:00:44  lr: 0.003196  min_lr: 0.003196  loss: 2.4995 (2.4005)  weight_decay: 0.0500 (0.0500)  time: 1.0053  data: 0.0004  max mem: 78493
Epoch: [102]  [280/312]  eta: 0:00:34  lr: 0.003196  min_lr: 0.003196  loss: 2.4995 (2.4041)  weight_decay: 0.0500 (0.0500)  time: 1.0044  data: 0.0011  max mem: 78493
Epoch: [102]  [290/312]  eta: 0:00:23  lr: 0.003195  min_lr: 0.003195  loss: 2.4896 (2.4066)  weight_decay: 0.0500 (0.0500)  time: 1.0032  data: 0.0009  max mem: 78493
Epoch: [102]  [300/312]  eta: 0:00:12  lr: 0.003195  min_lr: 0.003195  loss: 2.5948 (2.4162)  weight_decay: 0.0500 (0.0500)  time: 1.0018  data: 0.0001  max mem: 78493
Epoch: [102]  [310/312]  eta: 0:00:02  lr: 0.003194  min_lr: 0.003194  loss: 2.5487 (2.4146)  weight_decay: 0.0500 (0.0500)  time: 1.0018  data: 0.0001  max mem: 78493
Epoch: [102]  [311/312]  eta: 0:00:01  lr: 0.003194  min_lr: 0.003194  loss: 2.5421 (2.4137)  weight_decay: 0.0500 (0.0500)  time: 1.0018  data: 0.0001  max mem: 78493
Epoch: [102] Total time: 0:05:33 (1.0675 s / it)
Averaged stats: lr: 0.003194  min_lr: 0.003194  loss: 2.5421 (2.4246)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:16  loss: 0.8108 (0.8108)  acc1: 80.5990 (80.5990)  acc5: 94.4010 (94.4010)  time: 8.5130  data: 8.2444  max mem: 78493
Test:  [8/9]  eta: 0:00:01  loss: 1.2131 (1.0667)  acc1: 70.8333 (72.7680)  acc5: 90.4948 (91.0720)  time: 1.1445  data: 0.9161  max mem: 78493
Test: Total time: 0:00:10 (1.1610 s / it)
* Acc@1 73.310 Acc@5 91.546 loss 1.049
Accuracy of the model on the 50000 test images: 73.3%
Max accuracy: 74.35%
Epoch: [103]  [  0/312]  eta: 1:18:08  lr: 0.003194  min_lr: 0.003194  loss: 2.8649 (2.8649)  weight_decay: 0.0500 (0.0500)  time: 15.0281  data: 13.5754  max mem: 78493
Epoch: [103]  [ 10/312]  eta: 0:12:06  lr: 0.003193  min_lr: 0.003193  loss: 2.5657 (2.5534)  weight_decay: 0.0500 (0.0500)  time: 2.4046  data: 1.2380  max mem: 78493
Epoch: [103]  [ 20/312]  eta: 0:08:34  lr: 0.003193  min_lr: 0.003193  loss: 2.5927 (2.5313)  weight_decay: 0.0500 (0.0500)  time: 1.0992  data: 0.0025  max mem: 78493
Epoch: [103]  [ 30/312]  eta: 0:07:08  lr: 0.003192  min_lr: 0.003192  loss: 2.5927 (2.5356)  weight_decay: 0.0500 (0.0500)  time: 1.0345  data: 0.0017  max mem: 78493
Epoch: [103]  [ 40/312]  eta: 0:06:19  lr: 0.003192  min_lr: 0.003192  loss: 2.5582 (2.5319)  weight_decay: 0.0500 (0.0500)  time: 1.0110  data: 0.0015  max mem: 78493
Epoch: [103]  [ 50/312]  eta: 0:05:45  lr: 0.003191  min_lr: 0.003191  loss: 2.5880 (2.5337)  weight_decay: 0.0500 (0.0500)  time: 1.0104  data: 0.0005  max mem: 78493
Epoch: [103]  [ 60/312]  eta: 0:05:19  lr: 0.003190  min_lr: 0.003190  loss: 2.6361 (2.5294)  weight_decay: 0.0500 (0.0500)  time: 1.0103  data: 0.0005  max mem: 78493
Epoch: [103]  [ 70/312]  eta: 0:04:58  lr: 0.003190  min_lr: 0.003190  loss: 2.5134 (2.5078)  weight_decay: 0.0500 (0.0500)  time: 1.0076  data: 0.0005  max mem: 78493
Epoch: [103]  [ 80/312]  eta: 0:04:39  lr: 0.003189  min_lr: 0.003189  loss: 2.3456 (2.5057)  weight_decay: 0.0500 (0.0500)  time: 1.0099  data: 0.0005  max mem: 78493
Epoch: [103]  [ 90/312]  eta: 0:04:22  lr: 0.003189  min_lr: 0.003189  loss: 2.4744 (2.5020)  weight_decay: 0.0500 (0.0500)  time: 1.0113  data: 0.0004  max mem: 78493
Epoch: [103]  [100/312]  eta: 0:04:07  lr: 0.003188  min_lr: 0.003188  loss: 2.4276 (2.4785)  weight_decay: 0.0500 (0.0500)  time: 1.0071  data: 0.0004  max mem: 78493
Epoch: [103]  [110/312]  eta: 0:03:52  lr: 0.003187  min_lr: 0.003187  loss: 2.4992 (2.4870)  weight_decay: 0.0500 (0.0500)  time: 1.0073  data: 0.0004  max mem: 78493
Epoch: [103]  [120/312]  eta: 0:03:38  lr: 0.003187  min_lr: 0.003187  loss: 2.5037 (2.4827)  weight_decay: 0.0500 (0.0500)  time: 1.0098  data: 0.0004  max mem: 78493
Epoch: [103]  [130/312]  eta: 0:03:25  lr: 0.003186  min_lr: 0.003186  loss: 2.4888 (2.4810)  weight_decay: 0.0500 (0.0500)  time: 1.0086  data: 0.0004  max mem: 78493
Epoch: [103]  [140/312]  eta: 0:03:12  lr: 0.003186  min_lr: 0.003186  loss: 2.5093 (2.4855)  weight_decay: 0.0500 (0.0500)  time: 1.0067  data: 0.0004  max mem: 78493
Epoch: [103]  [150/312]  eta: 0:03:00  lr: 0.003185  min_lr: 0.003185  loss: 2.3414 (2.4755)  weight_decay: 0.0500 (0.0500)  time: 1.0054  data: 0.0004  max mem: 78493
Epoch: [103]  [160/312]  eta: 0:02:48  lr: 0.003185  min_lr: 0.003185  loss: 2.3414 (2.4696)  weight_decay: 0.0500 (0.0500)  time: 1.0063  data: 0.0005  max mem: 78493
Epoch: [103]  [170/312]  eta: 0:02:36  lr: 0.003184  min_lr: 0.003184  loss: 2.5261 (2.4761)  weight_decay: 0.0500 (0.0500)  time: 1.0065  data: 0.0005  max mem: 78493
Epoch: [103]  [180/312]  eta: 0:02:24  lr: 0.003183  min_lr: 0.003183  loss: 2.6439 (2.4819)  weight_decay: 0.0500 (0.0500)  time: 1.0040  data: 0.0005  max mem: 78493
Epoch: [103]  [190/312]  eta: 0:02:13  lr: 0.003183  min_lr: 0.003183  loss: 2.6439 (2.4798)  weight_decay: 0.0500 (0.0500)  time: 1.0039  data: 0.0005  max mem: 78493
Epoch: [103]  [200/312]  eta: 0:02:01  lr: 0.003182  min_lr: 0.003182  loss: 2.6166 (2.4842)  weight_decay: 0.0500 (0.0500)  time: 1.0056  data: 0.0004  max mem: 78493
Epoch: [103]  [210/312]  eta: 0:01:50  lr: 0.003182  min_lr: 0.003182  loss: 2.6287 (2.4944)  weight_decay: 0.0500 (0.0500)  time: 1.0052  data: 0.0004  max mem: 78493
Epoch: [103]  [220/312]  eta: 0:01:39  lr: 0.003181  min_lr: 0.003181  loss: 2.6412 (2.4859)  weight_decay: 0.0500 (0.0500)  time: 1.0046  data: 0.0004  max mem: 78493
Epoch: [103]  [230/312]  eta: 0:01:28  lr: 0.003181  min_lr: 0.003181  loss: 2.2256 (2.4771)  weight_decay: 0.0500 (0.0500)  time: 1.0045  data: 0.0004  max mem: 78493
Epoch: [103]  [240/312]  eta: 0:01:17  lr: 0.003180  min_lr: 0.003180  loss: 2.3095 (2.4769)  weight_decay: 0.0500 (0.0500)  time: 1.0041  data: 0.0004  max mem: 78493
Epoch: [103]  [250/312]  eta: 0:01:06  lr: 0.003179  min_lr: 0.003179  loss: 2.4612 (2.4798)  weight_decay: 0.0500 (0.0500)  time: 1.0051  data: 0.0004  max mem: 78493
Epoch: [103]  [260/312]  eta: 0:00:55  lr: 0.003179  min_lr: 0.003179  loss: 2.4811 (2.4759)  weight_decay: 0.0500 (0.0500)  time: 1.0052  data: 0.0004  max mem: 78493
Epoch: [103]  [270/312]  eta: 0:00:44  lr: 0.003178  min_lr: 0.003178  loss: 2.5515 (2.4763)  weight_decay: 0.0500 (0.0500)  time: 1.0056  data: 0.0004  max mem: 78493
Epoch: [103]  [280/312]  eta: 0:00:34  lr: 0.003178  min_lr: 0.003178  loss: 2.5515 (2.4722)  weight_decay: 0.0500 (0.0500)  time: 1.0071  data: 0.0011  max mem: 78493
Epoch: [103]  [290/312]  eta: 0:00:23  lr: 0.003177  min_lr: 0.003177  loss: 2.4217 (2.4714)  weight_decay: 0.0500 (0.0500)  time: 1.0048  data: 0.0009  max mem: 78493
Epoch: [103]  [300/312]  eta: 0:00:12  lr: 0.003176  min_lr: 0.003176  loss: 2.4421 (2.4668)  weight_decay: 0.0500 (0.0500)  time: 1.0021  data: 0.0001  max mem: 78493
Epoch: [103]  [310/312]  eta: 0:00:02  lr: 0.003176  min_lr: 0.003176  loss: 2.5598 (2.4720)  weight_decay: 0.0500 (0.0500)  time: 1.0019  data: 0.0001  max mem: 78493
Epoch: [103]  [311/312]  eta: 0:00:01  lr: 0.003176  min_lr: 0.003176  loss: 2.5598 (2.4696)  weight_decay: 0.0500 (0.0500)  time: 1.0019  data: 0.0001  max mem: 78493
Epoch: [103] Total time: 0:05:31 (1.0631 s / it)
Averaged stats: lr: 0.003176  min_lr: 0.003176  loss: 2.5598 (2.4261)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:15  loss: 0.7837 (0.7837)  acc1: 80.8594 (80.8594)  acc5: 94.5312 (94.5312)  time: 8.4175  data: 8.1523  max mem: 78493
Test:  [8/9]  eta: 0:00:01  loss: 1.1493 (1.0425)  acc1: 73.5677 (73.9360)  acc5: 91.9271 (91.7920)  time: 1.1362  data: 0.9059  max mem: 78493
Test: Total time: 0:00:10 (1.1742 s / it)
* Acc@1 74.232 Acc@5 91.904 loss 1.011
Accuracy of the model on the 50000 test images: 74.2%
Max accuracy: 74.35%
Epoch: [104]  [  0/312]  eta: 1:26:45  lr: 0.003176  min_lr: 0.003176  loss: 2.0098 (2.0098)  weight_decay: 0.0500 (0.0500)  time: 16.6839  data: 15.1051  max mem: 78493
Epoch: [104]  [ 10/312]  eta: 0:13:22  lr: 0.003175  min_lr: 0.003175  loss: 2.2561 (2.3199)  weight_decay: 0.0500 (0.0500)  time: 2.6566  data: 1.3739  max mem: 78493
Epoch: [104]  [ 20/312]  eta: 0:09:07  lr: 0.003175  min_lr: 0.003175  loss: 2.2786 (2.3666)  weight_decay: 0.0500 (0.0500)  time: 1.1356  data: 0.0006  max mem: 78493
Epoch: [104]  [ 30/312]  eta: 0:07:29  lr: 0.003174  min_lr: 0.003174  loss: 2.5822 (2.3986)  weight_decay: 0.0500 (0.0500)  time: 1.0122  data: 0.0004  max mem: 78493
Epoch: [104]  [ 40/312]  eta: 0:06:34  lr: 0.003173  min_lr: 0.003173  loss: 2.5564 (2.3743)  weight_decay: 0.0500 (0.0500)  time: 1.0055  data: 0.0004  max mem: 78493
Epoch: [104]  [ 50/312]  eta: 0:05:57  lr: 0.003173  min_lr: 0.003173  loss: 2.1455 (2.3564)  weight_decay: 0.0500 (0.0500)  time: 1.0059  data: 0.0004  max mem: 78493
Epoch: [104]  [ 60/312]  eta: 0:05:29  lr: 0.003172  min_lr: 0.003172  loss: 2.3678 (2.3704)  weight_decay: 0.0500 (0.0500)  time: 1.0075  data: 0.0004  max mem: 78493
Epoch: [104]  [ 70/312]  eta: 0:05:05  lr: 0.003172  min_lr: 0.003172  loss: 2.3678 (2.3659)  weight_decay: 0.0500 (0.0500)  time: 1.0056  data: 0.0004  max mem: 78493
Epoch: [104]  [ 80/312]  eta: 0:04:45  lr: 0.003171  min_lr: 0.003171  loss: 2.2765 (2.3655)  weight_decay: 0.0500 (0.0500)  time: 1.0059  data: 0.0004  max mem: 78493
Epoch: [104]  [ 90/312]  eta: 0:04:28  lr: 0.003171  min_lr: 0.003171  loss: 2.4128 (2.3678)  weight_decay: 0.0500 (0.0500)  time: 1.0089  data: 0.0004  max mem: 78493
Epoch: [104]  [100/312]  eta: 0:04:11  lr: 0.003170  min_lr: 0.003170  loss: 2.3936 (2.3592)  weight_decay: 0.0500 (0.0500)  time: 1.0098  data: 0.0016  max mem: 78493
Epoch: [104]  [110/312]  eta: 0:03:56  lr: 0.003169  min_lr: 0.003169  loss: 2.3268 (2.3449)  weight_decay: 0.0500 (0.0500)  time: 1.0086  data: 0.0016  max mem: 78493
Epoch: [104]  [120/312]  eta: 0:03:42  lr: 0.003169  min_lr: 0.003169  loss: 2.4731 (2.3674)  weight_decay: 0.0500 (0.0500)  time: 1.0073  data: 0.0004  max mem: 78493
Epoch: [104]  [130/312]  eta: 0:03:28  lr: 0.003168  min_lr: 0.003168  loss: 2.6176 (2.3799)  weight_decay: 0.0500 (0.0500)  time: 1.0079  data: 0.0004  max mem: 78493
Epoch: [104]  [140/312]  eta: 0:03:15  lr: 0.003168  min_lr: 0.003168  loss: 2.4949 (2.3831)  weight_decay: 0.0500 (0.0500)  time: 1.0069  data: 0.0005  max mem: 78493
Epoch: [104]  [150/312]  eta: 0:03:02  lr: 0.003167  min_lr: 0.003167  loss: 2.3127 (2.3787)  weight_decay: 0.0500 (0.0500)  time: 1.0048  data: 0.0005  max mem: 78493
Epoch: [104]  [160/312]  eta: 0:02:50  lr: 0.003166  min_lr: 0.003166  loss: 2.2970 (2.3763)  weight_decay: 0.0500 (0.0500)  time: 1.0051  data: 0.0004  max mem: 78493
Epoch: [104]  [170/312]  eta: 0:02:38  lr: 0.003166  min_lr: 0.003166  loss: 2.2970 (2.3748)  weight_decay: 0.0500 (0.0500)  time: 1.0062  data: 0.0004  max mem: 78493
Epoch: [104]  [180/312]  eta: 0:02:26  lr: 0.003165  min_lr: 0.003165  loss: 2.2025 (2.3745)  weight_decay: 0.0500 (0.0500)  time: 1.0070  data: 0.0004  max mem: 78493
Epoch: [104]  [190/312]  eta: 0:02:14  lr: 0.003165  min_lr: 0.003165  loss: 2.5917 (2.3923)  weight_decay: 0.0500 (0.0500)  time: 1.0078  data: 0.0004  max mem: 78493
Epoch: [104]  [200/312]  eta: 0:02:02  lr: 0.003164  min_lr: 0.003164  loss: 2.5986 (2.3953)  weight_decay: 0.0500 (0.0500)  time: 1.0078  data: 0.0004  max mem: 78493
Epoch: [104]  [210/312]  eta: 0:01:51  lr: 0.003164  min_lr: 0.003164  loss: 2.4631 (2.3916)  weight_decay: 0.0500 (0.0500)  time: 1.0085  data: 0.0005  max mem: 78493
Epoch: [104]  [220/312]  eta: 0:01:40  lr: 0.003163  min_lr: 0.003163  loss: 2.4768 (2.3963)  weight_decay: 0.0500 (0.0500)  time: 1.0082  data: 0.0004  max mem: 78493
Epoch: [104]  [230/312]  eta: 0:01:29  lr: 0.003162  min_lr: 0.003162  loss: 2.5224 (2.3971)  weight_decay: 0.0500 (0.0500)  time: 1.0064  data: 0.0004  max mem: 78493
Epoch: [104]  [240/312]  eta: 0:01:17  lr: 0.003162  min_lr: 0.003162  loss: 2.4909 (2.3972)  weight_decay: 0.0500 (0.0500)  time: 1.0072  data: 0.0004  max mem: 78493
Epoch: [104]  [250/312]  eta: 0:01:06  lr: 0.003161  min_lr: 0.003161  loss: 2.3130 (2.3928)  weight_decay: 0.0500 (0.0500)  time: 1.0087  data: 0.0004  max mem: 78493
Epoch: [104]  [260/312]  eta: 0:00:56  lr: 0.003161  min_lr: 0.003161  loss: 2.3040 (2.3917)  weight_decay: 0.0500 (0.0500)  time: 1.0076  data: 0.0004  max mem: 78493
Epoch: [104]  [270/312]  eta: 0:00:45  lr: 0.003160  min_lr: 0.003160  loss: 2.4882 (2.3967)  weight_decay: 0.0500 (0.0500)  time: 1.0075  data: 0.0004  max mem: 78493
Epoch: [104]  [280/312]  eta: 0:00:34  lr: 0.003159  min_lr: 0.003159  loss: 2.5801 (2.4046)  weight_decay: 0.0500 (0.0500)  time: 1.0081  data: 0.0010  max mem: 78493
Epoch: [104]  [290/312]  eta: 0:00:23  lr: 0.003159  min_lr: 0.003159  loss: 2.5791 (2.4070)  weight_decay: 0.0500 (0.0500)  time: 1.0047  data: 0.0009  max mem: 78493
Epoch: [104]  [300/312]  eta: 0:00:12  lr: 0.003158  min_lr: 0.003158  loss: 2.4088 (2.4053)  weight_decay: 0.0500 (0.0500)  time: 1.0017  data: 0.0001  max mem: 78493
Epoch: [104]  [310/312]  eta: 0:00:02  lr: 0.003158  min_lr: 0.003158  loss: 2.3807 (2.4060)  weight_decay: 0.0500 (0.0500)  time: 1.0014  data: 0.0001  max mem: 78493
Epoch: [104]  [311/312]  eta: 0:00:01  lr: 0.003158  min_lr: 0.003158  loss: 2.3807 (2.4074)  weight_decay: 0.0500 (0.0500)  time: 1.0014  data: 0.0001  max mem: 78493
Epoch: [104] Total time: 0:05:34 (1.0709 s / it)
Averaged stats: lr: 0.003158  min_lr: 0.003158  loss: 2.3807 (2.4297)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:08  loss: 0.8099 (0.8099)  acc1: 80.7292 (80.7292)  acc5: 94.2708 (94.2708)  time: 7.6279  data: 7.3480  max mem: 78493
Test:  [8/9]  eta: 0:00:01  loss: 1.1455 (1.0558)  acc1: 73.0469 (74.2880)  acc5: 92.3177 (92.0320)  time: 1.0630  data: 0.8338  max mem: 78493
Test: Total time: 0:00:09 (1.0729 s / it)
* Acc@1 74.358 Acc@5 91.846 loss 1.040
Accuracy of the model on the 50000 test images: 74.4%
Max accuracy: 74.36%
Epoch: [105]  [  0/312]  eta: 1:27:25  lr: 0.003158  min_lr: 0.003158  loss: 1.6372 (1.6372)  weight_decay: 0.0500 (0.0500)  time: 16.8114  data: 15.8003  max mem: 78493
Epoch: [105]  [ 10/312]  eta: 0:13:36  lr: 0.003157  min_lr: 0.003157  loss: 2.5608 (2.3971)  weight_decay: 0.0500 (0.0500)  time: 2.7037  data: 1.4370  max mem: 78493
Epoch: [105]  [ 20/312]  eta: 0:09:13  lr: 0.003156  min_lr: 0.003156  loss: 2.5586 (2.4450)  weight_decay: 0.0500 (0.0500)  time: 1.1509  data: 0.0006  max mem: 78493
Epoch: [105]  [ 30/312]  eta: 0:07:34  lr: 0.003156  min_lr: 0.003156  loss: 2.4120 (2.4413)  weight_decay: 0.0500 (0.0500)  time: 1.0110  data: 0.0004  max mem: 78493
Epoch: [105]  [ 40/312]  eta: 0:06:38  lr: 0.003155  min_lr: 0.003155  loss: 2.5188 (2.4518)  weight_decay: 0.0500 (0.0500)  time: 1.0131  data: 0.0014  max mem: 78493
Epoch: [105]  [ 50/312]  eta: 0:06:00  lr: 0.003155  min_lr: 0.003155  loss: 2.4576 (2.4145)  weight_decay: 0.0500 (0.0500)  time: 1.0126  data: 0.0014  max mem: 78493
Epoch: [105]  [ 60/312]  eta: 0:05:32  lr: 0.003154  min_lr: 0.003154  loss: 2.4576 (2.4338)  weight_decay: 0.0500 (0.0500)  time: 1.0142  data: 0.0013  max mem: 78493
Epoch: [105]  [ 70/312]  eta: 0:05:08  lr: 0.003153  min_lr: 0.003153  loss: 2.5979 (2.4663)  weight_decay: 0.0500 (0.0500)  time: 1.0132  data: 0.0013  max mem: 78493
Epoch: [105]  [ 80/312]  eta: 0:04:48  lr: 0.003153  min_lr: 0.003153  loss: 2.5979 (2.4551)  weight_decay: 0.0500 (0.0500)  time: 1.0095  data: 0.0004  max mem: 78493
Epoch: [105]  [ 90/312]  eta: 0:04:29  lr: 0.003152  min_lr: 0.003152  loss: 2.6950 (2.4843)  weight_decay: 0.0500 (0.0500)  time: 1.0091  data: 0.0004  max mem: 78493
Epoch: [105]  [100/312]  eta: 0:04:13  lr: 0.003152  min_lr: 0.003152  loss: 2.6639 (2.4887)  weight_decay: 0.0500 (0.0500)  time: 1.0089  data: 0.0004  max mem: 78493
Epoch: [105]  [110/312]  eta: 0:03:58  lr: 0.003151  min_lr: 0.003151  loss: 2.5012 (2.4767)  weight_decay: 0.0500 (0.0500)  time: 1.0072  data: 0.0011  max mem: 78493
Epoch: [105]  [120/312]  eta: 0:03:43  lr: 0.003151  min_lr: 0.003151  loss: 2.3124 (2.4566)  weight_decay: 0.0500 (0.0500)  time: 1.0082  data: 0.0011  max mem: 78493
Epoch: [105]  [130/312]  eta: 0:03:29  lr: 0.003150  min_lr: 0.003150  loss: 2.2932 (2.4464)  weight_decay: 0.0500 (0.0500)  time: 1.0114  data: 0.0005  max mem: 78493
Epoch: [105]  [140/312]  eta: 0:03:16  lr: 0.003149  min_lr: 0.003149  loss: 2.4478 (2.4423)  weight_decay: 0.0500 (0.0500)  time: 1.0098  data: 0.0005  max mem: 78493
Epoch: [105]  [150/312]  eta: 0:03:03  lr: 0.003149  min_lr: 0.003149  loss: 2.4478 (2.4401)  weight_decay: 0.0500 (0.0500)  time: 1.0063  data: 0.0005  max mem: 78493
Epoch: [105]  [160/312]  eta: 0:02:51  lr: 0.003148  min_lr: 0.003148  loss: 2.3392 (2.4361)  weight_decay: 0.0500 (0.0500)  time: 1.0059  data: 0.0004  max mem: 78493
Epoch: [105]  [170/312]  eta: 0:02:38  lr: 0.003148  min_lr: 0.003148  loss: 2.4633 (2.4291)  weight_decay: 0.0500 (0.0500)  time: 1.0059  data: 0.0004  max mem: 78493
Epoch: [105]  [180/312]  eta: 0:02:26  lr: 0.003147  min_lr: 0.003147  loss: 2.5088 (2.4414)  weight_decay: 0.0500 (0.0500)  time: 1.0063  data: 0.0005  max mem: 78493
Epoch: [105]  [190/312]  eta: 0:02:15  lr: 0.003146  min_lr: 0.003146  loss: 2.6200 (2.4385)  weight_decay: 0.0500 (0.0500)  time: 1.0085  data: 0.0004  max mem: 78493
Epoch: [105]  [200/312]  eta: 0:02:03  lr: 0.003146  min_lr: 0.003146  loss: 2.2365 (2.4306)  weight_decay: 0.0500 (0.0500)  time: 1.0087  data: 0.0004  max mem: 78493
Epoch: [105]  [210/312]  eta: 0:01:51  lr: 0.003145  min_lr: 0.003145  loss: 2.4146 (2.4303)  weight_decay: 0.0500 (0.0500)  time: 1.0093  data: 0.0004  max mem: 78493
Epoch: [105]  [220/312]  eta: 0:01:40  lr: 0.003145  min_lr: 0.003145  loss: 2.2756 (2.4234)  weight_decay: 0.0500 (0.0500)  time: 1.0095  data: 0.0004  max mem: 78493
Epoch: [105]  [230/312]  eta: 0:01:29  lr: 0.003144  min_lr: 0.003144  loss: 2.2471 (2.4217)  weight_decay: 0.0500 (0.0500)  time: 1.0065  data: 0.0004  max mem: 78493
Epoch: [105]  [240/312]  eta: 0:01:18  lr: 0.003143  min_lr: 0.003143  loss: 2.3775 (2.4186)  weight_decay: 0.0500 (0.0500)  time: 1.0075  data: 0.0005  max mem: 78493
Epoch: [105]  [250/312]  eta: 0:01:07  lr: 0.003143  min_lr: 0.003143  loss: 2.4246 (2.4243)  weight_decay: 0.0500 (0.0500)  time: 1.0077  data: 0.0005  max mem: 78493
Epoch: [105]  [260/312]  eta: 0:00:56  lr: 0.003142  min_lr: 0.003142  loss: 2.5019 (2.4222)  weight_decay: 0.0500 (0.0500)  time: 1.0056  data: 0.0004  max mem: 78493
Epoch: [105]  [270/312]  eta: 0:00:45  lr: 0.003142  min_lr: 0.003142  loss: 2.5266 (2.4292)  weight_decay: 0.0500 (0.0500)  time: 1.0064  data: 0.0004  max mem: 78493
Epoch: [105]  [280/312]  eta: 0:00:34  lr: 0.003141  min_lr: 0.003141  loss: 2.5815 (2.4291)  weight_decay: 0.0500 (0.0500)  time: 1.0057  data: 0.0019  max mem: 78493
Epoch: [105]  [290/312]  eta: 0:00:23  lr: 0.003140  min_lr: 0.003140  loss: 2.5892 (2.4391)  weight_decay: 0.0500 (0.0500)  time: 1.0035  data: 0.0017  max mem: 78493
Epoch: [105]  [300/312]  eta: 0:00:12  lr: 0.003140  min_lr: 0.003140  loss: 2.5892 (2.4448)  weight_decay: 0.0500 (0.0500)  time: 1.0022  data: 0.0001  max mem: 78493
Epoch: [105]  [310/312]  eta: 0:00:02  lr: 0.003139  min_lr: 0.003139  loss: 2.4450 (2.4376)  weight_decay: 0.0500 (0.0500)  time: 1.0019  data: 0.0001  max mem: 78493
Epoch: [105]  [311/312]  eta: 0:00:01  lr: 0.003139  min_lr: 0.003139  loss: 2.4579 (2.4383)  weight_decay: 0.0500 (0.0500)  time: 1.0019  data: 0.0001  max mem: 78493
Epoch: [105] Total time: 0:05:35 (1.0737 s / it)
Averaged stats: lr: 0.003139  min_lr: 0.003139  loss: 2.4579 (2.4148)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:13  loss: 0.7688 (0.7688)  acc1: 80.5990 (80.5990)  acc5: 94.4010 (94.4010)  time: 8.1588  data: 7.8953  max mem: 78493
Test:  [8/9]  eta: 0:00:01  loss: 1.1340 (1.0265)  acc1: 73.6979 (74.1440)  acc5: 91.1458 (91.6960)  time: 1.1522  data: 0.9248  max mem: 78493
Test: Total time: 0:00:10 (1.1640 s / it)
* Acc@1 74.666 Acc@5 92.140 loss 1.014
Accuracy of the model on the 50000 test images: 74.7%
Max accuracy: 74.67%
Epoch: [106]  [  0/312]  eta: 1:18:59  lr: 0.003139  min_lr: 0.003139  loss: 2.0284 (2.0284)  weight_decay: 0.0500 (0.0500)  time: 15.1918  data: 12.9097  max mem: 78493
Epoch: [106]  [ 10/312]  eta: 0:13:10  lr: 0.003139  min_lr: 0.003139  loss: 2.5245 (2.4633)  weight_decay: 0.0500 (0.0500)  time: 2.6174  data: 1.4532  max mem: 78493
Epoch: [106]  [ 20/312]  eta: 0:09:02  lr: 0.003138  min_lr: 0.003138  loss: 2.5368 (2.4778)  weight_decay: 0.0500 (0.0500)  time: 1.1929  data: 0.1540  max mem: 78493
Epoch: [106]  [ 30/312]  eta: 0:07:26  lr: 0.003137  min_lr: 0.003137  loss: 2.5197 (2.4493)  weight_decay: 0.0500 (0.0500)  time: 1.0170  data: 0.0005  max mem: 78493
Epoch: [106]  [ 40/312]  eta: 0:06:32  lr: 0.003137  min_lr: 0.003137  loss: 2.5578 (2.4901)  weight_decay: 0.0500 (0.0500)  time: 1.0069  data: 0.0005  max mem: 78493
Epoch: [106]  [ 50/312]  eta: 0:05:55  lr: 0.003136  min_lr: 0.003136  loss: 2.6258 (2.4850)  weight_decay: 0.0500 (0.0500)  time: 1.0076  data: 0.0005  max mem: 78493
Epoch: [106]  [ 60/312]  eta: 0:05:27  lr: 0.003136  min_lr: 0.003136  loss: 2.4911 (2.4674)  weight_decay: 0.0500 (0.0500)  time: 1.0078  data: 0.0004  max mem: 78493
Epoch: [106]  [ 70/312]  eta: 0:05:04  lr: 0.003135  min_lr: 0.003135  loss: 2.2906 (2.4125)  weight_decay: 0.0500 (0.0500)  time: 1.0061  data: 0.0005  max mem: 78493
Epoch: [106]  [ 80/312]  eta: 0:04:44  lr: 0.003134  min_lr: 0.003134  loss: 2.1879 (2.3931)  weight_decay: 0.0500 (0.0500)  time: 1.0064  data: 0.0004  max mem: 78493
Epoch: [106]  [ 90/312]  eta: 0:04:27  lr: 0.003134  min_lr: 0.003134  loss: 2.4749 (2.4026)  weight_decay: 0.0500 (0.0500)  time: 1.0076  data: 0.0004  max mem: 78493
Epoch: [106]  [100/312]  eta: 0:04:11  lr: 0.003133  min_lr: 0.003133  loss: 2.4766 (2.4051)  weight_decay: 0.0500 (0.0500)  time: 1.0082  data: 0.0004  max mem: 78493
Epoch: [106]  [110/312]  eta: 0:03:56  lr: 0.003133  min_lr: 0.003133  loss: 2.4038 (2.4033)  weight_decay: 0.0500 (0.0500)  time: 1.0068  data: 0.0004  max mem: 78493
Epoch: [106]  [120/312]  eta: 0:03:41  lr: 0.003132  min_lr: 0.003132  loss: 2.4285 (2.4063)  weight_decay: 0.0500 (0.0500)  time: 1.0047  data: 0.0004  max mem: 78493
Epoch: [106]  [130/312]  eta: 0:03:28  lr: 0.003131  min_lr: 0.003131  loss: 2.4591 (2.4052)  weight_decay: 0.0500 (0.0500)  time: 1.0046  data: 0.0005  max mem: 78493
Epoch: [106]  [140/312]  eta: 0:03:14  lr: 0.003131  min_lr: 0.003131  loss: 2.3662 (2.3976)  weight_decay: 0.0500 (0.0500)  time: 1.0060  data: 0.0005  max mem: 78493
Epoch: [106]  [150/312]  eta: 0:03:02  lr: 0.003130  min_lr: 0.003130  loss: 2.2311 (2.3899)  weight_decay: 0.0500 (0.0500)  time: 1.0064  data: 0.0004  max mem: 78493
Epoch: [106]  [160/312]  eta: 0:02:49  lr: 0.003130  min_lr: 0.003130  loss: 2.3805 (2.3942)  weight_decay: 0.0500 (0.0500)  time: 1.0066  data: 0.0004  max mem: 78493
Epoch: [106]  [170/312]  eta: 0:02:37  lr: 0.003129  min_lr: 0.003129  loss: 2.5827 (2.4085)  weight_decay: 0.0500 (0.0500)  time: 1.0068  data: 0.0004  max mem: 78493
Epoch: [106]  [180/312]  eta: 0:02:25  lr: 0.003129  min_lr: 0.003129  loss: 2.6124 (2.4056)  weight_decay: 0.0500 (0.0500)  time: 1.0076  data: 0.0004  max mem: 78493
Epoch: [106]  [190/312]  eta: 0:02:14  lr: 0.003128  min_lr: 0.003128  loss: 2.3514 (2.4084)  weight_decay: 0.0500 (0.0500)  time: 1.0089  data: 0.0004  max mem: 78493
Epoch: [106]  [200/312]  eta: 0:02:02  lr: 0.003127  min_lr: 0.003127  loss: 2.3544 (2.4113)  weight_decay: 0.0500 (0.0500)  time: 1.0110  data: 0.0004  max mem: 78493
Epoch: [106]  [210/312]  eta: 0:01:51  lr: 0.003127  min_lr: 0.003127  loss: 2.4223 (2.4157)  weight_decay: 0.0500 (0.0500)  time: 1.0106  data: 0.0004  max mem: 78493
Epoch: [106]  [220/312]  eta: 0:01:40  lr: 0.003126  min_lr: 0.003126  loss: 2.4328 (2.4175)  weight_decay: 0.0500 (0.0500)  time: 1.0064  data: 0.0004  max mem: 78493
Epoch: [106]  [230/312]  eta: 0:01:28  lr: 0.003126  min_lr: 0.003126  loss: 2.5211 (2.4212)  weight_decay: 0.0500 (0.0500)  time: 1.0059  data: 0.0005  max mem: 78493
Epoch: [106]  [240/312]  eta: 0:01:17  lr: 0.003125  min_lr: 0.003125  loss: 2.4464 (2.4195)  weight_decay: 0.0500 (0.0500)  time: 1.0061  data: 0.0005  max mem: 78493
Epoch: [106]  [250/312]  eta: 0:01:06  lr: 0.003124  min_lr: 0.003124  loss: 2.6027 (2.4283)  weight_decay: 0.0500 (0.0500)  time: 1.0063  data: 0.0004  max mem: 78493
Epoch: [106]  [260/312]  eta: 0:00:55  lr: 0.003124  min_lr: 0.003124  loss: 2.6251 (2.4333)  weight_decay: 0.0500 (0.0500)  time: 1.0056  data: 0.0004  max mem: 78493
Epoch: [106]  [270/312]  eta: 0:00:45  lr: 0.003123  min_lr: 0.003123  loss: 2.5617 (2.4335)  weight_decay: 0.0500 (0.0500)  time: 1.0036  data: 0.0004  max mem: 78493
Epoch: [106]  [280/312]  eta: 0:00:34  lr: 0.003123  min_lr: 0.003123  loss: 2.5685 (2.4385)  weight_decay: 0.0500 (0.0500)  time: 1.0058  data: 0.0010  max mem: 78493
Epoch: [106]  [290/312]  eta: 0:00:23  lr: 0.003122  min_lr: 0.003122  loss: 2.4195 (2.4345)  weight_decay: 0.0500 (0.0500)  time: 1.0042  data: 0.0009  max mem: 78493
Epoch: [106]  [300/312]  eta: 0:00:12  lr: 0.003121  min_lr: 0.003121  loss: 2.2698 (2.4256)  weight_decay: 0.0500 (0.0500)  time: 1.0008  data: 0.0001  max mem: 78493
Epoch: [106]  [310/312]  eta: 0:00:02  lr: 0.003121  min_lr: 0.003121  loss: 2.3727 (2.4294)  weight_decay: 0.0500 (0.0500)  time: 1.0009  data: 0.0001  max mem: 78493
Epoch: [106]  [311/312]  eta: 0:00:01  lr: 0.003121  min_lr: 0.003121  loss: 2.4027 (2.4293)  weight_decay: 0.0500 (0.0500)  time: 1.0008  data: 0.0001  max mem: 78493
Epoch: [106] Total time: 0:05:33 (1.0693 s / it)
Averaged stats: lr: 0.003121  min_lr: 0.003121  loss: 2.4027 (2.4140)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:16  loss: 0.7687 (0.7687)  acc1: 82.1615 (82.1615)  acc5: 94.4010 (94.4010)  time: 8.5275  data: 8.2569  max mem: 78493
Test:  [8/9]  eta: 0:00:01  loss: 1.0431 (1.0027)  acc1: 74.0885 (75.1520)  acc5: 93.0990 (92.1600)  time: 1.1456  data: 0.9175  max mem: 78493
Test: Total time: 0:00:10 (1.1645 s / it)
* Acc@1 74.626 Acc@5 92.224 loss 0.991
Accuracy of the model on the 50000 test images: 74.6%
Max accuracy: 74.67%
Epoch: [107]  [  0/312]  eta: 1:24:17  lr: 0.003121  min_lr: 0.003121  loss: 2.6535 (2.6535)  weight_decay: 0.0500 (0.0500)  time: 16.2103  data: 13.0898  max mem: 78493
Epoch: [107]  [ 10/312]  eta: 0:12:38  lr: 0.003120  min_lr: 0.003120  loss: 2.5633 (2.4065)  weight_decay: 0.0500 (0.0500)  time: 2.5110  data: 1.1912  max mem: 78493
Epoch: [107]  [ 20/312]  eta: 0:08:47  lr: 0.003119  min_lr: 0.003119  loss: 2.4440 (2.3818)  weight_decay: 0.0500 (0.0500)  time: 1.0864  data: 0.0024  max mem: 78493
Epoch: [107]  [ 30/312]  eta: 0:07:17  lr: 0.003119  min_lr: 0.003119  loss: 2.1699 (2.2951)  weight_decay: 0.0500 (0.0500)  time: 1.0232  data: 0.0020  max mem: 78493
Epoch: [107]  [ 40/312]  eta: 0:06:26  lr: 0.003118  min_lr: 0.003118  loss: 2.3099 (2.3163)  weight_decay: 0.0500 (0.0500)  time: 1.0124  data: 0.0004  max mem: 78493
Epoch: [107]  [ 50/312]  eta: 0:05:50  lr: 0.003118  min_lr: 0.003118  loss: 2.5101 (2.3164)  weight_decay: 0.0500 (0.0500)  time: 1.0093  data: 0.0005  max mem: 78493
Epoch: [107]  [ 60/312]  eta: 0:05:23  lr: 0.003117  min_lr: 0.003117  loss: 2.3858 (2.3231)  weight_decay: 0.0500 (0.0500)  time: 1.0101  data: 0.0004  max mem: 78493
Epoch: [107]  [ 70/312]  eta: 0:05:01  lr: 0.003116  min_lr: 0.003116  loss: 2.3858 (2.3321)  weight_decay: 0.0500 (0.0500)  time: 1.0100  data: 0.0004  max mem: 78493
Epoch: [107]  [ 80/312]  eta: 0:04:42  lr: 0.003116  min_lr: 0.003116  loss: 2.4275 (2.3451)  weight_decay: 0.0500 (0.0500)  time: 1.0076  data: 0.0005  max mem: 78493
Epoch: [107]  [ 90/312]  eta: 0:04:24  lr: 0.003115  min_lr: 0.003115  loss: 2.5268 (2.3804)  weight_decay: 0.0500 (0.0500)  time: 1.0074  data: 0.0005  max mem: 78493
Epoch: [107]  [100/312]  eta: 0:04:09  lr: 0.003115  min_lr: 0.003115  loss: 2.6899 (2.4077)  weight_decay: 0.0500 (0.0500)  time: 1.0078  data: 0.0004  max mem: 78493
Epoch: [107]  [110/312]  eta: 0:03:54  lr: 0.003114  min_lr: 0.003114  loss: 2.5919 (2.3955)  weight_decay: 0.0500 (0.0500)  time: 1.0062  data: 0.0004  max mem: 78493
Epoch: [107]  [120/312]  eta: 0:03:40  lr: 0.003114  min_lr: 0.003114  loss: 2.5057 (2.4135)  weight_decay: 0.0500 (0.0500)  time: 1.0077  data: 0.0005  max mem: 78493
Epoch: [107]  [130/312]  eta: 0:03:26  lr: 0.003113  min_lr: 0.003113  loss: 2.5582 (2.4214)  weight_decay: 0.0500 (0.0500)  time: 1.0095  data: 0.0005  max mem: 78493
Epoch: [107]  [140/312]  eta: 0:03:13  lr: 0.003112  min_lr: 0.003112  loss: 2.5582 (2.4258)  weight_decay: 0.0500 (0.0500)  time: 1.0071  data: 0.0013  max mem: 78493
Epoch: [107]  [150/312]  eta: 0:03:01  lr: 0.003112  min_lr: 0.003112  loss: 2.5424 (2.4324)  weight_decay: 0.0500 (0.0500)  time: 1.0063  data: 0.0013  max mem: 78493
Epoch: [107]  [160/312]  eta: 0:02:49  lr: 0.003111  min_lr: 0.003111  loss: 2.5491 (2.4311)  weight_decay: 0.0500 (0.0500)  time: 1.0065  data: 0.0004  max mem: 78493
Epoch: [107]  [170/312]  eta: 0:02:37  lr: 0.003111  min_lr: 0.003111  loss: 2.4425 (2.4251)  weight_decay: 0.0500 (0.0500)  time: 1.0069  data: 0.0004  max mem: 78493
Epoch: [107]  [180/312]  eta: 0:02:25  lr: 0.003110  min_lr: 0.003110  loss: 2.4174 (2.4305)  weight_decay: 0.0500 (0.0500)  time: 1.0070  data: 0.0004  max mem: 78493
Epoch: [107]  [190/312]  eta: 0:02:13  lr: 0.003109  min_lr: 0.003109  loss: 2.5514 (2.4355)  weight_decay: 0.0500 (0.0500)  time: 1.0076  data: 0.0004  max mem: 78493
Epoch: [107]  [200/312]  eta: 0:02:02  lr: 0.003109  min_lr: 0.003109  loss: 2.4938 (2.4342)  weight_decay: 0.0500 (0.0500)  time: 1.0069  data: 0.0004  max mem: 78493
Epoch: [107]  [210/312]  eta: 0:01:50  lr: 0.003108  min_lr: 0.003108  loss: 2.4738 (2.4386)  weight_decay: 0.0500 (0.0500)  time: 1.0046  data: 0.0005  max mem: 78493
Epoch: [107]  [220/312]  eta: 0:01:39  lr: 0.003108  min_lr: 0.003108  loss: 2.5631 (2.4396)  weight_decay: 0.0500 (0.0500)  time: 1.0066  data: 0.0004  max mem: 78493
Epoch: [107]  [230/312]  eta: 0:01:28  lr: 0.003107  min_lr: 0.003107  loss: 2.6468 (2.4498)  weight_decay: 0.0500 (0.0500)  time: 1.0078  data: 0.0004  max mem: 78493
Epoch: [107]  [240/312]  eta: 0:01:17  lr: 0.003106  min_lr: 0.003106  loss: 2.6213 (2.4480)  weight_decay: 0.0500 (0.0500)  time: 1.0060  data: 0.0005  max mem: 78493
Epoch: [107]  [250/312]  eta: 0:01:06  lr: 0.003106  min_lr: 0.003106  loss: 2.5583 (2.4477)  weight_decay: 0.0500 (0.0500)  time: 1.0057  data: 0.0005  max mem: 78493
Epoch: [107]  [260/312]  eta: 0:00:55  lr: 0.003105  min_lr: 0.003105  loss: 2.4756 (2.4333)  weight_decay: 0.0500 (0.0500)  time: 1.0075  data: 0.0004  max mem: 78493
Epoch: [107]  [270/312]  eta: 0:00:44  lr: 0.003105  min_lr: 0.003105  loss: 2.0604 (2.4304)  weight_decay: 0.0500 (0.0500)  time: 1.0064  data: 0.0004  max mem: 78493
Epoch: [107]  [280/312]  eta: 0:00:34  lr: 0.003104  min_lr: 0.003104  loss: 2.4085 (2.4319)  weight_decay: 0.0500 (0.0500)  time: 1.0048  data: 0.0010  max mem: 78493
Epoch: [107]  [290/312]  eta: 0:00:23  lr: 0.003103  min_lr: 0.003103  loss: 2.3596 (2.4305)  weight_decay: 0.0500 (0.0500)  time: 1.0039  data: 0.0009  max mem: 78493
Epoch: [107]  [300/312]  eta: 0:00:12  lr: 0.003103  min_lr: 0.003103  loss: 2.3367 (2.4247)  weight_decay: 0.0500 (0.0500)  time: 1.0018  data: 0.0001  max mem: 78493
Epoch: [107]  [310/312]  eta: 0:00:02  lr: 0.003102  min_lr: 0.003102  loss: 2.3367 (2.4233)  weight_decay: 0.0500 (0.0500)  time: 1.0019  data: 0.0001  max mem: 78493
Epoch: [107]  [311/312]  eta: 0:00:01  lr: 0.003102  min_lr: 0.003102  loss: 2.3367 (2.4230)  weight_decay: 0.0500 (0.0500)  time: 1.0018  data: 0.0001  max mem: 78493
Epoch: [107] Total time: 0:05:32 (1.0663 s / it)
Averaged stats: lr: 0.003102  min_lr: 0.003102  loss: 2.3367 (2.4075)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:17  loss: 0.7199 (0.7199)  acc1: 82.0312 (82.0312)  acc5: 95.5729 (95.5729)  time: 8.6010  data: 8.3206  max mem: 78493
Test:  [8/9]  eta: 0:00:01  loss: 1.0507 (0.9811)  acc1: 74.3490 (75.1040)  acc5: 91.7969 (92.1120)  time: 1.1539  data: 0.9246  max mem: 78493
Test: Total time: 0:00:10 (1.1660 s / it)
* Acc@1 74.988 Acc@5 92.362 loss 0.971
Accuracy of the model on the 50000 test images: 75.0%
Max accuracy: 74.99%
Epoch: [108]  [  0/312]  eta: 1:21:05  lr: 0.003102  min_lr: 0.003102  loss: 2.5158 (2.5158)  weight_decay: 0.0500 (0.0500)  time: 15.5949  data: 14.5821  max mem: 78493
Epoch: [108]  [ 10/312]  eta: 0:12:54  lr: 0.003101  min_lr: 0.003101  loss: 2.5158 (2.3804)  weight_decay: 0.0500 (0.0500)  time: 2.5656  data: 1.3308  max mem: 78493
Epoch: [108]  [ 20/312]  eta: 0:08:53  lr: 0.003101  min_lr: 0.003101  loss: 2.4893 (2.3821)  weight_decay: 0.0500 (0.0500)  time: 1.1387  data: 0.0048  max mem: 78493
Epoch: [108]  [ 30/312]  eta: 0:07:21  lr: 0.003100  min_lr: 0.003100  loss: 2.3229 (2.3104)  weight_decay: 0.0500 (0.0500)  time: 1.0131  data: 0.0022  max mem: 78493
Epoch: [108]  [ 40/312]  eta: 0:06:28  lr: 0.003100  min_lr: 0.003100  loss: 2.3228 (2.3190)  weight_decay: 0.0500 (0.0500)  time: 1.0101  data: 0.0004  max mem: 78493
Epoch: [108]  [ 50/312]  eta: 0:05:52  lr: 0.003099  min_lr: 0.003099  loss: 2.5436 (2.3775)  weight_decay: 0.0500 (0.0500)  time: 1.0088  data: 0.0004  max mem: 78493
Epoch: [108]  [ 60/312]  eta: 0:05:25  lr: 0.003098  min_lr: 0.003098  loss: 2.5157 (2.3454)  weight_decay: 0.0500 (0.0500)  time: 1.0094  data: 0.0004  max mem: 78493
Epoch: [108]  [ 70/312]  eta: 0:05:02  lr: 0.003098  min_lr: 0.003098  loss: 2.2411 (2.3351)  weight_decay: 0.0500 (0.0500)  time: 1.0094  data: 0.0004  max mem: 78493
Epoch: [108]  [ 80/312]  eta: 0:04:43  lr: 0.003097  min_lr: 0.003097  loss: 2.3653 (2.3467)  weight_decay: 0.0500 (0.0500)  time: 1.0075  data: 0.0005  max mem: 78493
Epoch: [108]  [ 90/312]  eta: 0:04:25  lr: 0.003097  min_lr: 0.003097  loss: 2.2889 (2.3334)  weight_decay: 0.0500 (0.0500)  time: 1.0067  data: 0.0004  max mem: 78493
Epoch: [108]  [100/312]  eta: 0:04:10  lr: 0.003096  min_lr: 0.003096  loss: 2.3307 (2.3318)  weight_decay: 0.0500 (0.0500)  time: 1.0100  data: 0.0004  max mem: 78493
Epoch: [108]  [110/312]  eta: 0:03:55  lr: 0.003095  min_lr: 0.003095  loss: 2.5896 (2.3614)  weight_decay: 0.0500 (0.0500)  time: 1.0086  data: 0.0004  max mem: 78493
Epoch: [108]  [120/312]  eta: 0:03:40  lr: 0.003095  min_lr: 0.003095  loss: 2.5908 (2.3658)  weight_decay: 0.0500 (0.0500)  time: 1.0050  data: 0.0004  max mem: 78493
Epoch: [108]  [130/312]  eta: 0:03:27  lr: 0.003094  min_lr: 0.003094  loss: 2.5605 (2.3725)  weight_decay: 0.0500 (0.0500)  time: 1.0061  data: 0.0004  max mem: 78493
Epoch: [108]  [140/312]  eta: 0:03:14  lr: 0.003094  min_lr: 0.003094  loss: 2.6137 (2.3806)  weight_decay: 0.0500 (0.0500)  time: 1.0093  data: 0.0005  max mem: 78493
Epoch: [108]  [150/312]  eta: 0:03:01  lr: 0.003093  min_lr: 0.003093  loss: 2.5275 (2.3844)  weight_decay: 0.0500 (0.0500)  time: 1.0096  data: 0.0004  max mem: 78493
Epoch: [108]  [160/312]  eta: 0:02:49  lr: 0.003092  min_lr: 0.003092  loss: 2.5275 (2.3937)  weight_decay: 0.0500 (0.0500)  time: 1.0074  data: 0.0012  max mem: 78493
Epoch: [108]  [170/312]  eta: 0:02:37  lr: 0.003092  min_lr: 0.003092  loss: 2.5976 (2.4084)  weight_decay: 0.0500 (0.0500)  time: 1.0067  data: 0.0012  max mem: 78493
Epoch: [108]  [180/312]  eta: 0:02:25  lr: 0.003091  min_lr: 0.003091  loss: 2.6114 (2.4170)  weight_decay: 0.0500 (0.0500)  time: 1.0068  data: 0.0004  max mem: 78493
Epoch: [108]  [190/312]  eta: 0:02:13  lr: 0.003091  min_lr: 0.003091  loss: 2.4915 (2.4112)  weight_decay: 0.0500 (0.0500)  time: 1.0058  data: 0.0004  max mem: 78493
Epoch: [108]  [200/312]  eta: 0:02:02  lr: 0.003090  min_lr: 0.003090  loss: 2.4931 (2.4170)  weight_decay: 0.0500 (0.0500)  time: 1.0064  data: 0.0005  max mem: 78493
Epoch: [108]  [210/312]  eta: 0:01:51  lr: 0.003089  min_lr: 0.003089  loss: 2.4837 (2.4063)  weight_decay: 0.0500 (0.0500)  time: 1.0068  data: 0.0004  max mem: 78493
Epoch: [108]  [220/312]  eta: 0:01:39  lr: 0.003089  min_lr: 0.003089  loss: 2.2291 (2.3985)  weight_decay: 0.0500 (0.0500)  time: 1.0050  data: 0.0004  max mem: 78493
Epoch: [108]  [230/312]  eta: 0:01:28  lr: 0.003088  min_lr: 0.003088  loss: 2.2823 (2.3959)  weight_decay: 0.0500 (0.0500)  time: 1.0056  data: 0.0004  max mem: 78493
Epoch: [108]  [240/312]  eta: 0:01:17  lr: 0.003088  min_lr: 0.003088  loss: 2.4230 (2.3988)  weight_decay: 0.0500 (0.0500)  time: 1.0055  data: 0.0004  max mem: 78493
Epoch: [108]  [250/312]  eta: 0:01:06  lr: 0.003087  min_lr: 0.003087  loss: 2.4230 (2.3914)  weight_decay: 0.0500 (0.0500)  time: 1.0047  data: 0.0005  max mem: 78493
Epoch: [108]  [260/312]  eta: 0:00:55  lr: 0.003086  min_lr: 0.003086  loss: 1.9694 (2.3792)  weight_decay: 0.0500 (0.0500)  time: 1.0049  data: 0.0005  max mem: 78493
Epoch: [108]  [270/312]  eta: 0:00:44  lr: 0.003086  min_lr: 0.003086  loss: 2.1290 (2.3841)  weight_decay: 0.0500 (0.0500)  time: 1.0053  data: 0.0004  max mem: 78493
Epoch: [108]  [280/312]  eta: 0:00:34  lr: 0.003085  min_lr: 0.003085  loss: 2.4719 (2.3869)  weight_decay: 0.0500 (0.0500)  time: 1.0051  data: 0.0010  max mem: 78493
Epoch: [108]  [290/312]  eta: 0:00:23  lr: 0.003085  min_lr: 0.003085  loss: 2.4049 (2.3834)  weight_decay: 0.0500 (0.0500)  time: 1.0033  data: 0.0009  max mem: 78493
Epoch: [108]  [300/312]  eta: 0:00:12  lr: 0.003084  min_lr: 0.003084  loss: 2.4049 (2.3821)  weight_decay: 0.0500 (0.0500)  time: 1.0018  data: 0.0001  max mem: 78493
Epoch: [108]  [310/312]  eta: 0:00:02  lr: 0.003083  min_lr: 0.003083  loss: 2.5409 (2.3858)  weight_decay: 0.0500 (0.0500)  time: 1.0015  data: 0.0001  max mem: 78493
Epoch: [108]  [311/312]  eta: 0:00:01  lr: 0.003083  min_lr: 0.003083  loss: 2.5183 (2.3856)  weight_decay: 0.0500 (0.0500)  time: 1.0015  data: 0.0001  max mem: 78493
Epoch: [108] Total time: 0:05:33 (1.0679 s / it)
Averaged stats: lr: 0.003083  min_lr: 0.003083  loss: 2.5183 (2.4009)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:15  loss: 0.7650 (0.7650)  acc1: 80.7292 (80.7292)  acc5: 95.0521 (95.0521)  time: 8.4034  data: 8.1216  max mem: 78493
Test:  [8/9]  eta: 0:00:01  loss: 1.1667 (1.0338)  acc1: 72.6562 (73.9680)  acc5: 91.9271 (92.0960)  time: 1.1320  data: 0.9025  max mem: 78493
Test: Total time: 0:00:10 (1.1499 s / it)
* Acc@1 74.262 Acc@5 91.932 loss 1.020
Accuracy of the model on the 50000 test images: 74.3%
Max accuracy: 74.99%
Epoch: [109]  [  0/312]  eta: 1:27:28  lr: 0.003083  min_lr: 0.003083  loss: 1.8598 (1.8598)  weight_decay: 0.0500 (0.0500)  time: 16.8223  data: 11.9696  max mem: 78493
Epoch: [109]  [ 10/312]  eta: 0:13:41  lr: 0.003083  min_lr: 0.003083  loss: 2.4674 (2.3258)  weight_decay: 0.0500 (0.0500)  time: 2.7197  data: 1.1710  max mem: 78493
Epoch: [109]  [ 20/312]  eta: 0:09:16  lr: 0.003082  min_lr: 0.003082  loss: 2.4299 (2.3360)  weight_decay: 0.0500 (0.0500)  time: 1.1602  data: 0.0458  max mem: 78493
Epoch: [109]  [ 30/312]  eta: 0:07:35  lr: 0.003081  min_lr: 0.003081  loss: 2.3936 (2.3591)  weight_decay: 0.0500 (0.0500)  time: 1.0099  data: 0.0015  max mem: 78493
Epoch: [109]  [ 40/312]  eta: 0:06:39  lr: 0.003081  min_lr: 0.003081  loss: 2.4730 (2.3627)  weight_decay: 0.0500 (0.0500)  time: 1.0065  data: 0.0014  max mem: 78493
Epoch: [109]  [ 50/312]  eta: 0:06:00  lr: 0.003080  min_lr: 0.003080  loss: 2.4648 (2.3566)  weight_decay: 0.0500 (0.0500)  time: 1.0046  data: 0.0004  max mem: 78493
Epoch: [109]  [ 60/312]  eta: 0:05:31  lr: 0.003080  min_lr: 0.003080  loss: 2.4648 (2.3800)  weight_decay: 0.0500 (0.0500)  time: 1.0071  data: 0.0004  max mem: 78493
Epoch: [109]  [ 70/312]  eta: 0:05:08  lr: 0.003079  min_lr: 0.003079  loss: 2.4490 (2.3968)  weight_decay: 0.0500 (0.0500)  time: 1.0093  data: 0.0004  max mem: 78493
Epoch: [109]  [ 80/312]  eta: 0:04:47  lr: 0.003078  min_lr: 0.003078  loss: 2.3062 (2.3757)  weight_decay: 0.0500 (0.0500)  time: 1.0081  data: 0.0004  max mem: 78493
Epoch: [109]  [ 90/312]  eta: 0:04:29  lr: 0.003078  min_lr: 0.003078  loss: 2.4456 (2.3971)  weight_decay: 0.0500 (0.0500)  time: 1.0088  data: 0.0004  max mem: 78493
Epoch: [109]  [100/312]  eta: 0:04:13  lr: 0.003077  min_lr: 0.003077  loss: 2.4346 (2.3818)  weight_decay: 0.0500 (0.0500)  time: 1.0096  data: 0.0004  max mem: 78493
Epoch: [109]  [110/312]  eta: 0:03:57  lr: 0.003077  min_lr: 0.003077  loss: 2.3933 (2.3829)  weight_decay: 0.0500 (0.0500)  time: 1.0075  data: 0.0004  max mem: 78493
Epoch: [109]  [120/312]  eta: 0:03:43  lr: 0.003076  min_lr: 0.003076  loss: 2.3933 (2.3829)  weight_decay: 0.0500 (0.0500)  time: 1.0065  data: 0.0005  max mem: 78493
Epoch: [109]  [130/312]  eta: 0:03:29  lr: 0.003075  min_lr: 0.003075  loss: 2.5870 (2.3990)  weight_decay: 0.0500 (0.0500)  time: 1.0074  data: 0.0005  max mem: 78493
Epoch: [109]  [140/312]  eta: 0:03:16  lr: 0.003075  min_lr: 0.003075  loss: 2.4631 (2.3889)  weight_decay: 0.0500 (0.0500)  time: 1.0086  data: 0.0005  max mem: 78493
Epoch: [109]  [150/312]  eta: 0:03:03  lr: 0.003074  min_lr: 0.003074  loss: 2.3789 (2.3994)  weight_decay: 0.0500 (0.0500)  time: 1.0099  data: 0.0005  max mem: 78493
Epoch: [109]  [160/312]  eta: 0:02:51  lr: 0.003074  min_lr: 0.003074  loss: 2.6570 (2.3979)  weight_decay: 0.0500 (0.0500)  time: 1.0101  data: 0.0005  max mem: 78493
Epoch: [109]  [170/312]  eta: 0:02:38  lr: 0.003073  min_lr: 0.003073  loss: 2.3097 (2.3888)  weight_decay: 0.0500 (0.0500)  time: 1.0066  data: 0.0013  max mem: 78493
Epoch: [109]  [180/312]  eta: 0:02:26  lr: 0.003072  min_lr: 0.003072  loss: 2.5187 (2.3984)  weight_decay: 0.0500 (0.0500)  time: 1.0063  data: 0.0013  max mem: 78493
Epoch: [109]  [190/312]  eta: 0:02:14  lr: 0.003072  min_lr: 0.003072  loss: 2.3712 (2.3811)  weight_decay: 0.0500 (0.0500)  time: 1.0066  data: 0.0004  max mem: 78493
Epoch: [109]  [200/312]  eta: 0:02:03  lr: 0.003071  min_lr: 0.003071  loss: 2.0940 (2.3805)  weight_decay: 0.0500 (0.0500)  time: 1.0071  data: 0.0004  max mem: 78493
Epoch: [109]  [210/312]  eta: 0:01:51  lr: 0.003071  min_lr: 0.003071  loss: 2.2664 (2.3763)  weight_decay: 0.0500 (0.0500)  time: 1.0085  data: 0.0004  max mem: 78493
Epoch: [109]  [220/312]  eta: 0:01:40  lr: 0.003070  min_lr: 0.003070  loss: 2.1024 (2.3626)  weight_decay: 0.0500 (0.0500)  time: 1.0062  data: 0.0004  max mem: 78493
Epoch: [109]  [230/312]  eta: 0:01:29  lr: 0.003069  min_lr: 0.003069  loss: 2.3747 (2.3709)  weight_decay: 0.0500 (0.0500)  time: 1.0047  data: 0.0005  max mem: 78493
Epoch: [109]  [240/312]  eta: 0:01:18  lr: 0.003069  min_lr: 0.003069  loss: 2.6439 (2.3705)  weight_decay: 0.0500 (0.0500)  time: 1.0052  data: 0.0005  max mem: 78493
Epoch: [109]  [250/312]  eta: 0:01:07  lr: 0.003068  min_lr: 0.003068  loss: 2.4569 (2.3700)  weight_decay: 0.0500 (0.0500)  time: 1.0057  data: 0.0004  max mem: 78493
Epoch: [109]  [260/312]  eta: 0:00:56  lr: 0.003067  min_lr: 0.003067  loss: 2.4303 (2.3711)  weight_decay: 0.0500 (0.0500)  time: 1.0058  data: 0.0004  max mem: 78493
Epoch: [109]  [270/312]  eta: 0:00:45  lr: 0.003067  min_lr: 0.003067  loss: 2.6028 (2.3767)  weight_decay: 0.0500 (0.0500)  time: 1.0075  data: 0.0004  max mem: 78493
Epoch: [109]  [280/312]  eta: 0:00:34  lr: 0.003066  min_lr: 0.003066  loss: 2.4882 (2.3803)  weight_decay: 0.0500 (0.0500)  time: 1.0074  data: 0.0010  max mem: 78493
Epoch: [109]  [290/312]  eta: 0:00:23  lr: 0.003066  min_lr: 0.003066  loss: 2.4154 (2.3785)  weight_decay: 0.0500 (0.0500)  time: 1.0035  data: 0.0009  max mem: 78493
Epoch: [109]  [300/312]  eta: 0:00:12  lr: 0.003065  min_lr: 0.003065  loss: 2.4531 (2.3856)  weight_decay: 0.0500 (0.0500)  time: 1.0014  data: 0.0001  max mem: 78493
Epoch: [109]  [310/312]  eta: 0:00:02  lr: 0.003064  min_lr: 0.003064  loss: 2.5935 (2.3879)  weight_decay: 0.0500 (0.0500)  time: 1.0012  data: 0.0001  max mem: 78493
Epoch: [109]  [311/312]  eta: 0:00:01  lr: 0.003064  min_lr: 0.003064  loss: 2.5105 (2.3883)  weight_decay: 0.0500 (0.0500)  time: 1.0012  data: 0.0001  max mem: 78493
Epoch: [109] Total time: 0:05:34 (1.0726 s / it)
Averaged stats: lr: 0.003064  min_lr: 0.003064  loss: 2.5105 (2.3975)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:10  loss: 0.7922 (0.7922)  acc1: 81.5104 (81.5104)  acc5: 94.4010 (94.4010)  time: 7.8565  data: 7.5549  max mem: 78493
Test:  [8/9]  eta: 0:00:01  loss: 1.1074 (1.0180)  acc1: 73.0469 (74.8160)  acc5: 91.9271 (92.1600)  time: 1.0712  data: 0.8395  max mem: 78493
Test: Total time: 0:00:09 (1.0802 s / it)
* Acc@1 74.494 Acc@5 92.054 loss 1.009
Accuracy of the model on the 50000 test images: 74.5%
Max accuracy: 74.99%
Epoch: [110]  [  0/312]  eta: 1:27:13  lr: 0.003064  min_lr: 0.003064  loss: 2.6677 (2.6677)  weight_decay: 0.0500 (0.0500)  time: 16.7750  data: 13.8405  max mem: 78493
Epoch: [110]  [ 10/312]  eta: 0:13:07  lr: 0.003064  min_lr: 0.003064  loss: 2.5647 (2.5136)  weight_decay: 0.0500 (0.0500)  time: 2.6083  data: 1.2654  max mem: 78493
Epoch: [110]  [ 20/312]  eta: 0:09:01  lr: 0.003063  min_lr: 0.003063  loss: 2.5398 (2.3365)  weight_decay: 0.0500 (0.0500)  time: 1.1088  data: 0.0042  max mem: 78493
Epoch: [110]  [ 30/312]  eta: 0:07:26  lr: 0.003062  min_lr: 0.003062  loss: 2.1377 (2.3128)  weight_decay: 0.0500 (0.0500)  time: 1.0171  data: 0.0005  max mem: 78493
Epoch: [110]  [ 40/312]  eta: 0:06:32  lr: 0.003062  min_lr: 0.003062  loss: 2.4788 (2.3558)  weight_decay: 0.0500 (0.0500)  time: 1.0096  data: 0.0004  max mem: 78493
Epoch: [110]  [ 50/312]  eta: 0:05:55  lr: 0.003061  min_lr: 0.003061  loss: 2.5966 (2.3985)  weight_decay: 0.0500 (0.0500)  time: 1.0074  data: 0.0004  max mem: 78493
Epoch: [110]  [ 60/312]  eta: 0:05:27  lr: 0.003061  min_lr: 0.003061  loss: 2.5675 (2.4095)  weight_decay: 0.0500 (0.0500)  time: 1.0047  data: 0.0004  max mem: 78493
Epoch: [110]  [ 70/312]  eta: 0:05:04  lr: 0.003060  min_lr: 0.003060  loss: 2.4481 (2.4119)  weight_decay: 0.0500 (0.0500)  time: 1.0065  data: 0.0004  max mem: 78493
Epoch: [110]  [ 80/312]  eta: 0:04:44  lr: 0.003059  min_lr: 0.003059  loss: 2.4448 (2.4206)  weight_decay: 0.0500 (0.0500)  time: 1.0069  data: 0.0005  max mem: 78493
Epoch: [110]  [ 90/312]  eta: 0:04:27  lr: 0.003059  min_lr: 0.003059  loss: 2.5474 (2.4329)  weight_decay: 0.0500 (0.0500)  time: 1.0081  data: 0.0004  max mem: 78493
Epoch: [110]  [100/312]  eta: 0:04:10  lr: 0.003058  min_lr: 0.003058  loss: 2.3664 (2.4139)  weight_decay: 0.0500 (0.0500)  time: 1.0090  data: 0.0014  max mem: 78493
Epoch: [110]  [110/312]  eta: 0:03:55  lr: 0.003058  min_lr: 0.003058  loss: 2.2579 (2.3990)  weight_decay: 0.0500 (0.0500)  time: 1.0077  data: 0.0023  max mem: 78493
Epoch: [110]  [120/312]  eta: 0:03:41  lr: 0.003057  min_lr: 0.003057  loss: 2.3004 (2.3966)  weight_decay: 0.0500 (0.0500)  time: 1.0062  data: 0.0013  max mem: 78493
Epoch: [110]  [130/312]  eta: 0:03:28  lr: 0.003056  min_lr: 0.003056  loss: 2.6262 (2.4018)  weight_decay: 0.0500 (0.0500)  time: 1.0052  data: 0.0004  max mem: 78493
Epoch: [110]  [140/312]  eta: 0:03:14  lr: 0.003056  min_lr: 0.003056  loss: 2.3590 (2.3960)  weight_decay: 0.0500 (0.0500)  time: 1.0059  data: 0.0004  max mem: 78493
Epoch: [110]  [150/312]  eta: 0:03:02  lr: 0.003055  min_lr: 0.003055  loss: 2.2672 (2.3889)  weight_decay: 0.0500 (0.0500)  time: 1.0075  data: 0.0004  max mem: 78493
Epoch: [110]  [160/312]  eta: 0:02:49  lr: 0.003055  min_lr: 0.003055  loss: 2.4277 (2.3957)  weight_decay: 0.0500 (0.0500)  time: 1.0083  data: 0.0004  max mem: 78493
Epoch: [110]  [170/312]  eta: 0:02:37  lr: 0.003054  min_lr: 0.003054  loss: 2.6001 (2.4059)  weight_decay: 0.0500 (0.0500)  time: 1.0077  data: 0.0004  max mem: 78493
Epoch: [110]  [180/312]  eta: 0:02:25  lr: 0.003053  min_lr: 0.003053  loss: 2.5256 (2.4062)  weight_decay: 0.0500 (0.0500)  time: 1.0104  data: 0.0004  max mem: 78493
Epoch: [110]  [190/312]  eta: 0:02:14  lr: 0.003053  min_lr: 0.003053  loss: 2.2802 (2.3974)  weight_decay: 0.0500 (0.0500)  time: 1.0119  data: 0.0004  max mem: 78493
Epoch: [110]  [200/312]  eta: 0:02:02  lr: 0.003052  min_lr: 0.003052  loss: 2.3792 (2.4017)  weight_decay: 0.0500 (0.0500)  time: 1.0092  data: 0.0004  max mem: 78493
Epoch: [110]  [210/312]  eta: 0:01:51  lr: 0.003051  min_lr: 0.003051  loss: 2.3896 (2.3997)  weight_decay: 0.0500 (0.0500)  time: 1.0086  data: 0.0004  max mem: 78493
Epoch: [110]  [220/312]  eta: 0:01:40  lr: 0.003051  min_lr: 0.003051  loss: 2.4241 (2.3997)  weight_decay: 0.0500 (0.0500)  time: 1.0086  data: 0.0004  max mem: 78493
Epoch: [110]  [230/312]  eta: 0:01:28  lr: 0.003050  min_lr: 0.003050  loss: 2.4670 (2.4032)  weight_decay: 0.0500 (0.0500)  time: 1.0086  data: 0.0004  max mem: 78493
Epoch: [110]  [240/312]  eta: 0:01:17  lr: 0.003050  min_lr: 0.003050  loss: 2.4670 (2.4002)  weight_decay: 0.0500 (0.0500)  time: 1.0093  data: 0.0005  max mem: 78493
Epoch: [110]  [250/312]  eta: 0:01:06  lr: 0.003049  min_lr: 0.003049  loss: 2.4219 (2.3973)  weight_decay: 0.0500 (0.0500)  time: 1.0087  data: 0.0004  max mem: 78493
Epoch: [110]  [260/312]  eta: 0:00:55  lr: 0.003048  min_lr: 0.003048  loss: 2.4539 (2.3981)  weight_decay: 0.0500 (0.0500)  time: 1.0077  data: 0.0004  max mem: 78493
Epoch: [110]  [270/312]  eta: 0:00:45  lr: 0.003048  min_lr: 0.003048  loss: 2.4778 (2.4019)  weight_decay: 0.0500 (0.0500)  time: 1.0085  data: 0.0004  max mem: 78493
Epoch: [110]  [280/312]  eta: 0:00:34  lr: 0.003047  min_lr: 0.003047  loss: 2.3991 (2.3976)  weight_decay: 0.0500 (0.0500)  time: 1.0099  data: 0.0011  max mem: 78493
Epoch: [110]  [290/312]  eta: 0:00:23  lr: 0.003047  min_lr: 0.003047  loss: 2.3269 (2.3976)  weight_decay: 0.0500 (0.0500)  time: 1.0067  data: 0.0009  max mem: 78493
Epoch: [110]  [300/312]  eta: 0:00:12  lr: 0.003046  min_lr: 0.003046  loss: 2.3252 (2.3903)  weight_decay: 0.0500 (0.0500)  time: 1.0026  data: 0.0001  max mem: 78493
Epoch: [110]  [310/312]  eta: 0:00:02  lr: 0.003045  min_lr: 0.003045  loss: 2.3841 (2.3881)  weight_decay: 0.0500 (0.0500)  time: 1.0023  data: 0.0001  max mem: 78493
Epoch: [110]  [311/312]  eta: 0:00:01  lr: 0.003045  min_lr: 0.003045  loss: 2.3841 (2.3887)  weight_decay: 0.0500 (0.0500)  time: 1.0023  data: 0.0001  max mem: 78493
Epoch: [110] Total time: 0:05:33 (1.0703 s / it)
Averaged stats: lr: 0.003045  min_lr: 0.003045  loss: 2.3841 (2.4025)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:15  loss: 0.7203 (0.7203)  acc1: 80.4688 (80.4688)  acc5: 95.4427 (95.4427)  time: 8.3624  data: 8.0804  max mem: 78493
Test:  [8/9]  eta: 0:00:01  loss: 1.1331 (1.0111)  acc1: 72.0052 (73.6480)  acc5: 91.7969 (92.1280)  time: 1.1274  data: 0.8979  max mem: 78493
Test: Total time: 0:00:10 (1.1392 s / it)
* Acc@1 74.274 Acc@5 92.060 loss 1.000
Accuracy of the model on the 50000 test images: 74.3%
Max accuracy: 74.99%
Epoch: [111]  [  0/312]  eta: 1:23:47  lr: 0.003045  min_lr: 0.003045  loss: 2.5846 (2.5846)  weight_decay: 0.0500 (0.0500)  time: 16.1145  data: 15.1089  max mem: 78493
Epoch: [111]  [ 10/312]  eta: 0:13:24  lr: 0.003045  min_lr: 0.003045  loss: 2.1393 (2.2229)  weight_decay: 0.0500 (0.0500)  time: 2.6635  data: 1.3777  max mem: 78493
Epoch: [111]  [ 20/312]  eta: 0:09:08  lr: 0.003044  min_lr: 0.003044  loss: 2.1393 (2.2750)  weight_decay: 0.0500 (0.0500)  time: 1.1662  data: 0.0025  max mem: 78493
Epoch: [111]  [ 30/312]  eta: 0:07:30  lr: 0.003043  min_lr: 0.003043  loss: 2.3560 (2.2754)  weight_decay: 0.0500 (0.0500)  time: 1.0109  data: 0.0005  max mem: 78493
Epoch: [111]  [ 40/312]  eta: 0:06:35  lr: 0.003043  min_lr: 0.003043  loss: 2.4215 (2.3376)  weight_decay: 0.0500 (0.0500)  time: 1.0083  data: 0.0004  max mem: 78493
Epoch: [111]  [ 50/312]  eta: 0:05:57  lr: 0.003042  min_lr: 0.003042  loss: 2.4566 (2.3175)  weight_decay: 0.0500 (0.0500)  time: 1.0073  data: 0.0004  max mem: 78493
Epoch: [111]  [ 60/312]  eta: 0:05:29  lr: 0.003042  min_lr: 0.003042  loss: 2.5033 (2.3800)  weight_decay: 0.0500 (0.0500)  time: 1.0070  data: 0.0004  max mem: 78493
Epoch: [111]  [ 70/312]  eta: 0:05:06  lr: 0.003041  min_lr: 0.003041  loss: 2.6660 (2.4173)  weight_decay: 0.0500 (0.0500)  time: 1.0090  data: 0.0004  max mem: 78493
Epoch: [111]  [ 80/312]  eta: 0:04:46  lr: 0.003040  min_lr: 0.003040  loss: 2.6343 (2.4525)  weight_decay: 0.0500 (0.0500)  time: 1.0097  data: 0.0004  max mem: 78493
Epoch: [111]  [ 90/312]  eta: 0:04:28  lr: 0.003040  min_lr: 0.003040  loss: 2.5887 (2.4479)  weight_decay: 0.0500 (0.0500)  time: 1.0107  data: 0.0004  max mem: 78493
Epoch: [111]  [100/312]  eta: 0:04:12  lr: 0.003039  min_lr: 0.003039  loss: 2.4755 (2.4481)  weight_decay: 0.0500 (0.0500)  time: 1.0100  data: 0.0004  max mem: 78493
Epoch: [111]  [110/312]  eta: 0:03:56  lr: 0.003038  min_lr: 0.003038  loss: 2.4040 (2.4296)  weight_decay: 0.0500 (0.0500)  time: 1.0074  data: 0.0004  max mem: 78493
Epoch: [111]  [120/312]  eta: 0:03:42  lr: 0.003038  min_lr: 0.003038  loss: 2.3780 (2.4369)  weight_decay: 0.0500 (0.0500)  time: 1.0065  data: 0.0005  max mem: 78493
Epoch: [111]  [130/312]  eta: 0:03:28  lr: 0.003037  min_lr: 0.003037  loss: 2.5885 (2.4424)  weight_decay: 0.0500 (0.0500)  time: 1.0060  data: 0.0005  max mem: 78493
Epoch: [111]  [140/312]  eta: 0:03:15  lr: 0.003037  min_lr: 0.003037  loss: 2.6406 (2.4509)  weight_decay: 0.0500 (0.0500)  time: 1.0054  data: 0.0005  max mem: 78493
Epoch: [111]  [150/312]  eta: 0:03:02  lr: 0.003036  min_lr: 0.003036  loss: 2.6050 (2.4550)  weight_decay: 0.0500 (0.0500)  time: 1.0052  data: 0.0005  max mem: 78493
Epoch: [111]  [160/312]  eta: 0:02:50  lr: 0.003035  min_lr: 0.003035  loss: 2.3592 (2.4416)  weight_decay: 0.0500 (0.0500)  time: 1.0059  data: 0.0004  max mem: 78493
Epoch: [111]  [170/312]  eta: 0:02:38  lr: 0.003035  min_lr: 0.003035  loss: 2.2179 (2.4306)  weight_decay: 0.0500 (0.0500)  time: 1.0046  data: 0.0012  max mem: 78493
Epoch: [111]  [180/312]  eta: 0:02:26  lr: 0.003034  min_lr: 0.003034  loss: 2.4482 (2.4354)  weight_decay: 0.0500 (0.0500)  time: 1.0034  data: 0.0012  max mem: 78493
Epoch: [111]  [190/312]  eta: 0:02:14  lr: 0.003034  min_lr: 0.003034  loss: 2.4683 (2.4311)  weight_decay: 0.0500 (0.0500)  time: 1.0044  data: 0.0005  max mem: 78493
Epoch: [111]  [200/312]  eta: 0:02:02  lr: 0.003033  min_lr: 0.003033  loss: 2.4199 (2.4319)  weight_decay: 0.0500 (0.0500)  time: 1.0067  data: 0.0005  max mem: 78493
Epoch: [111]  [210/312]  eta: 0:01:51  lr: 0.003032  min_lr: 0.003032  loss: 2.4615 (2.4315)  weight_decay: 0.0500 (0.0500)  time: 1.0081  data: 0.0005  max mem: 78493
Epoch: [111]  [220/312]  eta: 0:01:40  lr: 0.003032  min_lr: 0.003032  loss: 2.5043 (2.4319)  weight_decay: 0.0500 (0.0500)  time: 1.0082  data: 0.0004  max mem: 78493
Epoch: [111]  [230/312]  eta: 0:01:29  lr: 0.003031  min_lr: 0.003031  loss: 2.5350 (2.4373)  weight_decay: 0.0500 (0.0500)  time: 1.0072  data: 0.0004  max mem: 78493
Epoch: [111]  [240/312]  eta: 0:01:17  lr: 0.003030  min_lr: 0.003030  loss: 2.5917 (2.4394)  weight_decay: 0.0500 (0.0500)  time: 1.0057  data: 0.0012  max mem: 78493
Epoch: [111]  [250/312]  eta: 0:01:06  lr: 0.003030  min_lr: 0.003030  loss: 2.4682 (2.4354)  weight_decay: 0.0500 (0.0500)  time: 1.0050  data: 0.0012  max mem: 78493
Epoch: [111]  [260/312]  eta: 0:00:55  lr: 0.003029  min_lr: 0.003029  loss: 2.2389 (2.4278)  weight_decay: 0.0500 (0.0500)  time: 1.0046  data: 0.0004  max mem: 78493
Epoch: [111]  [270/312]  eta: 0:00:45  lr: 0.003029  min_lr: 0.003029  loss: 2.5237 (2.4318)  weight_decay: 0.0500 (0.0500)  time: 1.0051  data: 0.0005  max mem: 78493
Epoch: [111]  [280/312]  eta: 0:00:34  lr: 0.003028  min_lr: 0.003028  loss: 2.3289 (2.4269)  weight_decay: 0.0500 (0.0500)  time: 1.0059  data: 0.0010  max mem: 78493
Epoch: [111]  [290/312]  eta: 0:00:23  lr: 0.003027  min_lr: 0.003027  loss: 2.4079 (2.4286)  weight_decay: 0.0500 (0.0500)  time: 1.0041  data: 0.0009  max mem: 78493
Epoch: [111]  [300/312]  eta: 0:00:12  lr: 0.003027  min_lr: 0.003027  loss: 2.5336 (2.4315)  weight_decay: 0.0500 (0.0500)  time: 1.0013  data: 0.0001  max mem: 78493
Epoch: [111]  [310/312]  eta: 0:00:02  lr: 0.003026  min_lr: 0.003026  loss: 2.3877 (2.4268)  weight_decay: 0.0500 (0.0500)  time: 1.0013  data: 0.0001  max mem: 78493
Epoch: [111]  [311/312]  eta: 0:00:01  lr: 0.003026  min_lr: 0.003026  loss: 2.3877 (2.4276)  weight_decay: 0.0500 (0.0500)  time: 1.0013  data: 0.0001  max mem: 78493
Epoch: [111] Total time: 0:05:33 (1.0703 s / it)
Averaged stats: lr: 0.003026  min_lr: 0.003026  loss: 2.3877 (2.3969)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:16  loss: 0.7427 (0.7427)  acc1: 80.8594 (80.8594)  acc5: 94.9219 (94.9219)  time: 8.5335  data: 8.2698  max mem: 78493
Test:  [8/9]  eta: 0:00:01  loss: 1.1229 (1.0046)  acc1: 74.7396 (74.6720)  acc5: 91.9271 (92.1280)  time: 1.1502  data: 0.9189  max mem: 78493
Test: Total time: 0:00:10 (1.1883 s / it)
* Acc@1 74.922 Acc@5 92.484 loss 0.997
Accuracy of the model on the 50000 test images: 74.9%
Max accuracy: 74.99%
Epoch: [112]  [  0/312]  eta: 1:23:09  lr: 0.003026  min_lr: 0.003026  loss: 2.5588 (2.5588)  weight_decay: 0.0500 (0.0500)  time: 15.9925  data: 14.9878  max mem: 78493
Epoch: [112]  [ 10/312]  eta: 0:12:53  lr: 0.003025  min_lr: 0.003025  loss: 2.7365 (2.6474)  weight_decay: 0.0500 (0.0500)  time: 2.5627  data: 1.3668  max mem: 78493
Epoch: [112]  [ 20/312]  eta: 0:08:56  lr: 0.003025  min_lr: 0.003025  loss: 2.6334 (2.5957)  weight_decay: 0.0500 (0.0500)  time: 1.1297  data: 0.0027  max mem: 78493
Epoch: [112]  [ 30/312]  eta: 0:07:22  lr: 0.003024  min_lr: 0.003024  loss: 2.5332 (2.5481)  weight_decay: 0.0500 (0.0500)  time: 1.0237  data: 0.0006  max mem: 78493
Epoch: [112]  [ 40/312]  eta: 0:06:29  lr: 0.003024  min_lr: 0.003024  loss: 2.1462 (2.4393)  weight_decay: 0.0500 (0.0500)  time: 1.0062  data: 0.0004  max mem: 78493
Epoch: [112]  [ 50/312]  eta: 0:05:53  lr: 0.003023  min_lr: 0.003023  loss: 2.0989 (2.4241)  weight_decay: 0.0500 (0.0500)  time: 1.0079  data: 0.0004  max mem: 78493
Epoch: [112]  [ 60/312]  eta: 0:05:25  lr: 0.003022  min_lr: 0.003022  loss: 2.5226 (2.4290)  weight_decay: 0.0500 (0.0500)  time: 1.0081  data: 0.0004  max mem: 78493
Epoch: [112]  [ 70/312]  eta: 0:05:03  lr: 0.003022  min_lr: 0.003022  loss: 2.3253 (2.3961)  weight_decay: 0.0500 (0.0500)  time: 1.0059  data: 0.0004  max mem: 78493
Epoch: [112]  [ 80/312]  eta: 0:04:43  lr: 0.003021  min_lr: 0.003021  loss: 2.2301 (2.3895)  weight_decay: 0.0500 (0.0500)  time: 1.0071  data: 0.0005  max mem: 78493
Epoch: [112]  [ 90/312]  eta: 0:04:26  lr: 0.003020  min_lr: 0.003020  loss: 2.3817 (2.3832)  weight_decay: 0.0500 (0.0500)  time: 1.0077  data: 0.0004  max mem: 78493
Epoch: [112]  [100/312]  eta: 0:04:10  lr: 0.003020  min_lr: 0.003020  loss: 2.5101 (2.3786)  weight_decay: 0.0500 (0.0500)  time: 1.0076  data: 0.0004  max mem: 78493
Epoch: [112]  [110/312]  eta: 0:03:55  lr: 0.003019  min_lr: 0.003019  loss: 2.4343 (2.3774)  weight_decay: 0.0500 (0.0500)  time: 1.0079  data: 0.0004  max mem: 78493
Epoch: [112]  [120/312]  eta: 0:03:41  lr: 0.003019  min_lr: 0.003019  loss: 2.2346 (2.3695)  weight_decay: 0.0500 (0.0500)  time: 1.0060  data: 0.0004  max mem: 78493
Epoch: [112]  [130/312]  eta: 0:03:27  lr: 0.003018  min_lr: 0.003018  loss: 2.5078 (2.3809)  weight_decay: 0.0500 (0.0500)  time: 1.0033  data: 0.0005  max mem: 78493
Epoch: [112]  [140/312]  eta: 0:03:14  lr: 0.003017  min_lr: 0.003017  loss: 2.4702 (2.3706)  weight_decay: 0.0500 (0.0500)  time: 1.0049  data: 0.0005  max mem: 78493
Epoch: [112]  [150/312]  eta: 0:03:01  lr: 0.003017  min_lr: 0.003017  loss: 2.4096 (2.3838)  weight_decay: 0.0500 (0.0500)  time: 1.0080  data: 0.0005  max mem: 78493
Epoch: [112]  [160/312]  eta: 0:02:49  lr: 0.003016  min_lr: 0.003016  loss: 2.2941 (2.3752)  weight_decay: 0.0500 (0.0500)  time: 1.0075  data: 0.0005  max mem: 78493
Epoch: [112]  [170/312]  eta: 0:02:37  lr: 0.003016  min_lr: 0.003016  loss: 2.4904 (2.3855)  weight_decay: 0.0500 (0.0500)  time: 1.0071  data: 0.0005  max mem: 78493
Epoch: [112]  [180/312]  eta: 0:02:25  lr: 0.003015  min_lr: 0.003015  loss: 2.6071 (2.3997)  weight_decay: 0.0500 (0.0500)  time: 1.0078  data: 0.0004  max mem: 78493
Epoch: [112]  [190/312]  eta: 0:02:14  lr: 0.003014  min_lr: 0.003014  loss: 2.6322 (2.4108)  weight_decay: 0.0500 (0.0500)  time: 1.0085  data: 0.0004  max mem: 78493
Epoch: [112]  [200/312]  eta: 0:02:02  lr: 0.003014  min_lr: 0.003014  loss: 2.5977 (2.4117)  weight_decay: 0.0500 (0.0500)  time: 1.0076  data: 0.0004  max mem: 78493
Epoch: [112]  [210/312]  eta: 0:01:51  lr: 0.003013  min_lr: 0.003013  loss: 2.5599 (2.4153)  weight_decay: 0.0500 (0.0500)  time: 1.0053  data: 0.0004  max mem: 78493
Epoch: [112]  [220/312]  eta: 0:01:39  lr: 0.003012  min_lr: 0.003012  loss: 2.5599 (2.4183)  weight_decay: 0.0500 (0.0500)  time: 1.0056  data: 0.0004  max mem: 78493
Epoch: [112]  [230/312]  eta: 0:01:28  lr: 0.003012  min_lr: 0.003012  loss: 2.5485 (2.4201)  weight_decay: 0.0500 (0.0500)  time: 1.0055  data: 0.0004  max mem: 78493
Epoch: [112]  [240/312]  eta: 0:01:17  lr: 0.003011  min_lr: 0.003011  loss: 2.5094 (2.4259)  weight_decay: 0.0500 (0.0500)  time: 1.0058  data: 0.0004  max mem: 78493
Epoch: [112]  [250/312]  eta: 0:01:06  lr: 0.003011  min_lr: 0.003011  loss: 2.4857 (2.4276)  weight_decay: 0.0500 (0.0500)  time: 1.0067  data: 0.0005  max mem: 78493
Epoch: [112]  [260/312]  eta: 0:00:55  lr: 0.003010  min_lr: 0.003010  loss: 2.5943 (2.4337)  weight_decay: 0.0500 (0.0500)  time: 1.0067  data: 0.0004  max mem: 78493
Epoch: [112]  [270/312]  eta: 0:00:44  lr: 0.003009  min_lr: 0.003009  loss: 2.6220 (2.4352)  weight_decay: 0.0500 (0.0500)  time: 1.0065  data: 0.0004  max mem: 78493
Epoch: [112]  [280/312]  eta: 0:00:34  lr: 0.003009  min_lr: 0.003009  loss: 2.4471 (2.4332)  weight_decay: 0.0500 (0.0500)  time: 1.0072  data: 0.0010  max mem: 78493
Epoch: [112]  [290/312]  eta: 0:00:23  lr: 0.003008  min_lr: 0.003008  loss: 2.3593 (2.4326)  weight_decay: 0.0500 (0.0500)  time: 1.0048  data: 0.0009  max mem: 78493
Epoch: [112]  [300/312]  eta: 0:00:12  lr: 0.003007  min_lr: 0.003007  loss: 2.4785 (2.4347)  weight_decay: 0.0500 (0.0500)  time: 1.0016  data: 0.0001  max mem: 78493
Epoch: [112]  [310/312]  eta: 0:00:02  lr: 0.003007  min_lr: 0.003007  loss: 2.5698 (2.4423)  weight_decay: 0.0500 (0.0500)  time: 1.0015  data: 0.0001  max mem: 78493
Epoch: [112]  [311/312]  eta: 0:00:01  lr: 0.003007  min_lr: 0.003007  loss: 2.5597 (2.4402)  weight_decay: 0.0500 (0.0500)  time: 1.0014  data: 0.0001  max mem: 78493
Epoch: [112] Total time: 0:05:33 (1.0677 s / it)
Averaged stats: lr: 0.003007  min_lr: 0.003007  loss: 2.5597 (2.4079)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:08  loss: 0.7517 (0.7517)  acc1: 80.0781 (80.0781)  acc5: 96.0938 (96.0938)  time: 7.5921  data: 7.3133  max mem: 78493
Test:  [8/9]  eta: 0:00:01  loss: 1.1674 (1.0258)  acc1: 73.1771 (74.2400)  acc5: 91.7969 (92.0960)  time: 1.0489  data: 0.8196  max mem: 78493
Test: Total time: 0:00:09 (1.0590 s / it)
* Acc@1 74.550 Acc@5 92.170 loss 1.022
Accuracy of the model on the 50000 test images: 74.6%
Max accuracy: 74.99%
Epoch: [113]  [  0/312]  eta: 1:24:59  lr: 0.003007  min_lr: 0.003007  loss: 2.7836 (2.7836)  weight_decay: 0.0500 (0.0500)  time: 16.3440  data: 12.4717  max mem: 78493
Epoch: [113]  [ 10/312]  eta: 0:13:13  lr: 0.003006  min_lr: 0.003006  loss: 2.5404 (2.3776)  weight_decay: 0.0500 (0.0500)  time: 2.6270  data: 1.3450  max mem: 78493
Epoch: [113]  [ 20/312]  eta: 0:09:04  lr: 0.003005  min_lr: 0.003005  loss: 2.3960 (2.3281)  weight_decay: 0.0500 (0.0500)  time: 1.1391  data: 0.1164  max mem: 78493
Epoch: [113]  [ 30/312]  eta: 0:07:27  lr: 0.003005  min_lr: 0.003005  loss: 2.2340 (2.3069)  weight_decay: 0.0500 (0.0500)  time: 1.0154  data: 0.0005  max mem: 78493
Epoch: [113]  [ 40/312]  eta: 0:06:33  lr: 0.003004  min_lr: 0.003004  loss: 2.2340 (2.3011)  weight_decay: 0.0500 (0.0500)  time: 1.0076  data: 0.0004  max mem: 78493
Epoch: [113]  [ 50/312]  eta: 0:05:56  lr: 0.003004  min_lr: 0.003004  loss: 2.3046 (2.3086)  weight_decay: 0.0500 (0.0500)  time: 1.0086  data: 0.0004  max mem: 78493
Epoch: [113]  [ 60/312]  eta: 0:05:28  lr: 0.003003  min_lr: 0.003003  loss: 2.3046 (2.3286)  weight_decay: 0.0500 (0.0500)  time: 1.0105  data: 0.0004  max mem: 78493
Epoch: [113]  [ 70/312]  eta: 0:05:05  lr: 0.003002  min_lr: 0.003002  loss: 2.2564 (2.3256)  weight_decay: 0.0500 (0.0500)  time: 1.0085  data: 0.0011  max mem: 78493
Epoch: [113]  [ 80/312]  eta: 0:04:45  lr: 0.003002  min_lr: 0.003002  loss: 2.5338 (2.3279)  weight_decay: 0.0500 (0.0500)  time: 1.0079  data: 0.0011  max mem: 78493
Epoch: [113]  [ 90/312]  eta: 0:04:27  lr: 0.003001  min_lr: 0.003001  loss: 2.2631 (2.3213)  weight_decay: 0.0500 (0.0500)  time: 1.0097  data: 0.0004  max mem: 78493
Epoch: [113]  [100/312]  eta: 0:04:11  lr: 0.003000  min_lr: 0.003000  loss: 2.2420 (2.3120)  weight_decay: 0.0500 (0.0500)  time: 1.0084  data: 0.0004  max mem: 78493
Epoch: [113]  [110/312]  eta: 0:03:56  lr: 0.003000  min_lr: 0.003000  loss: 2.1850 (2.3118)  weight_decay: 0.0500 (0.0500)  time: 1.0068  data: 0.0004  max mem: 78493
Epoch: [113]  [120/312]  eta: 0:03:42  lr: 0.002999  min_lr: 0.002999  loss: 2.1850 (2.3101)  weight_decay: 0.0500 (0.0500)  time: 1.0063  data: 0.0004  max mem: 78493
Epoch: [113]  [130/312]  eta: 0:03:28  lr: 0.002999  min_lr: 0.002999  loss: 2.3738 (2.3124)  weight_decay: 0.0500 (0.0500)  time: 1.0052  data: 0.0005  max mem: 78493
Epoch: [113]  [140/312]  eta: 0:03:15  lr: 0.002998  min_lr: 0.002998  loss: 2.1028 (2.2910)  weight_decay: 0.0500 (0.0500)  time: 1.0067  data: 0.0005  max mem: 78493
Epoch: [113]  [150/312]  eta: 0:03:02  lr: 0.002997  min_lr: 0.002997  loss: 2.1028 (2.2928)  weight_decay: 0.0500 (0.0500)  time: 1.0071  data: 0.0004  max mem: 78493
Epoch: [113]  [160/312]  eta: 0:02:50  lr: 0.002997  min_lr: 0.002997  loss: 2.3252 (2.2989)  weight_decay: 0.0500 (0.0500)  time: 1.0066  data: 0.0005  max mem: 78493
Epoch: [113]  [170/312]  eta: 0:02:38  lr: 0.002996  min_lr: 0.002996  loss: 2.3252 (2.3052)  weight_decay: 0.0500 (0.0500)  time: 1.0074  data: 0.0005  max mem: 78493
Epoch: [113]  [180/312]  eta: 0:02:26  lr: 0.002996  min_lr: 0.002996  loss: 2.4831 (2.3131)  weight_decay: 0.0500 (0.0500)  time: 1.0080  data: 0.0005  max mem: 78493
Epoch: [113]  [190/312]  eta: 0:02:14  lr: 0.002995  min_lr: 0.002995  loss: 2.4831 (2.3170)  weight_decay: 0.0500 (0.0500)  time: 1.0087  data: 0.0005  max mem: 78493
Epoch: [113]  [200/312]  eta: 0:02:02  lr: 0.002994  min_lr: 0.002994  loss: 2.4339 (2.3131)  weight_decay: 0.0500 (0.0500)  time: 1.0081  data: 0.0005  max mem: 78493
Epoch: [113]  [210/312]  eta: 0:01:51  lr: 0.002994  min_lr: 0.002994  loss: 2.4348 (2.3226)  weight_decay: 0.0500 (0.0500)  time: 1.0086  data: 0.0004  max mem: 78493
Epoch: [113]  [220/312]  eta: 0:01:40  lr: 0.002993  min_lr: 0.002993  loss: 2.4638 (2.3304)  weight_decay: 0.0500 (0.0500)  time: 1.0109  data: 0.0005  max mem: 78493
Epoch: [113]  [230/312]  eta: 0:01:29  lr: 0.002992  min_lr: 0.002992  loss: 2.4713 (2.3357)  weight_decay: 0.0500 (0.0500)  time: 1.0102  data: 0.0004  max mem: 78493
Epoch: [113]  [240/312]  eta: 0:01:17  lr: 0.002992  min_lr: 0.002992  loss: 2.5790 (2.3386)  weight_decay: 0.0500 (0.0500)  time: 1.0082  data: 0.0004  max mem: 78493
Epoch: [113]  [250/312]  eta: 0:01:06  lr: 0.002991  min_lr: 0.002991  loss: 2.4348 (2.3367)  weight_decay: 0.0500 (0.0500)  time: 1.0072  data: 0.0004  max mem: 78493
Epoch: [113]  [260/312]  eta: 0:00:55  lr: 0.002991  min_lr: 0.002991  loss: 2.4715 (2.3407)  weight_decay: 0.0500 (0.0500)  time: 1.0048  data: 0.0004  max mem: 78493
Epoch: [113]  [270/312]  eta: 0:00:45  lr: 0.002990  min_lr: 0.002990  loss: 2.5119 (2.3449)  weight_decay: 0.0500 (0.0500)  time: 1.0058  data: 0.0012  max mem: 78493
Epoch: [113]  [280/312]  eta: 0:00:34  lr: 0.002989  min_lr: 0.002989  loss: 2.1607 (2.3363)  weight_decay: 0.0500 (0.0500)  time: 1.0080  data: 0.0018  max mem: 78493
Epoch: [113]  [290/312]  eta: 0:00:23  lr: 0.002989  min_lr: 0.002989  loss: 2.3223 (2.3431)  weight_decay: 0.0500 (0.0500)  time: 1.0054  data: 0.0009  max mem: 78493
Epoch: [113]  [300/312]  eta: 0:00:12  lr: 0.002988  min_lr: 0.002988  loss: 2.6073 (2.3437)  weight_decay: 0.0500 (0.0500)  time: 1.0017  data: 0.0001  max mem: 78493
Epoch: [113]  [310/312]  eta: 0:00:02  lr: 0.002987  min_lr: 0.002987  loss: 2.4907 (2.3471)  weight_decay: 0.0500 (0.0500)  time: 1.0013  data: 0.0001  max mem: 78493
Epoch: [113]  [311/312]  eta: 0:00:01  lr: 0.002987  min_lr: 0.002987  loss: 2.5280 (2.3485)  weight_decay: 0.0500 (0.0500)  time: 1.0013  data: 0.0001  max mem: 78493
Epoch: [113] Total time: 0:05:33 (1.0704 s / it)
Averaged stats: lr: 0.002987  min_lr: 0.002987  loss: 2.5280 (2.3884)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:16  loss: 0.8192 (0.8192)  acc1: 81.9010 (81.9010)  acc5: 94.0104 (94.0104)  time: 8.4915  data: 8.2163  max mem: 78493
Test:  [8/9]  eta: 0:00:01  loss: 1.1523 (1.0291)  acc1: 71.6146 (73.9200)  acc5: 91.4062 (91.5840)  time: 1.1419  data: 0.9130  max mem: 78493
Test: Total time: 0:00:10 (1.1801 s / it)
* Acc@1 74.218 Acc@5 91.980 loss 1.016
Accuracy of the model on the 50000 test images: 74.2%
Max accuracy: 74.99%
Epoch: [114]  [  0/312]  eta: 1:27:33  lr: 0.002987  min_lr: 0.002987  loss: 2.1173 (2.1173)  weight_decay: 0.0500 (0.0500)  time: 16.8373  data: 13.8371  max mem: 78493
Epoch: [114]  [ 10/312]  eta: 0:13:47  lr: 0.002987  min_lr: 0.002987  loss: 2.4860 (2.4714)  weight_decay: 0.0500 (0.0500)  time: 2.7408  data: 1.2586  max mem: 78493
Epoch: [114]  [ 20/312]  eta: 0:09:20  lr: 0.002986  min_lr: 0.002986  loss: 2.6059 (2.4452)  weight_decay: 0.0500 (0.0500)  time: 1.1732  data: 0.0021  max mem: 78493
Epoch: [114]  [ 30/312]  eta: 0:07:38  lr: 0.002985  min_lr: 0.002985  loss: 2.6282 (2.4797)  weight_decay: 0.0500 (0.0500)  time: 1.0116  data: 0.0029  max mem: 78493
Epoch: [114]  [ 40/312]  eta: 0:06:40  lr: 0.002985  min_lr: 0.002985  loss: 2.6331 (2.5324)  weight_decay: 0.0500 (0.0500)  time: 1.0066  data: 0.0015  max mem: 78493
Epoch: [114]  [ 50/312]  eta: 0:06:02  lr: 0.002984  min_lr: 0.002984  loss: 2.5821 (2.4911)  weight_decay: 0.0500 (0.0500)  time: 1.0055  data: 0.0004  max mem: 78493
Epoch: [114]  [ 60/312]  eta: 0:05:32  lr: 0.002984  min_lr: 0.002984  loss: 2.5634 (2.5177)  weight_decay: 0.0500 (0.0500)  time: 1.0052  data: 0.0004  max mem: 78493
Epoch: [114]  [ 70/312]  eta: 0:05:08  lr: 0.002983  min_lr: 0.002983  loss: 2.6314 (2.4941)  weight_decay: 0.0500 (0.0500)  time: 1.0034  data: 0.0004  max mem: 78493
Epoch: [114]  [ 80/312]  eta: 0:04:48  lr: 0.002982  min_lr: 0.002982  loss: 2.2572 (2.4460)  weight_decay: 0.0500 (0.0500)  time: 1.0041  data: 0.0004  max mem: 78493
Epoch: [114]  [ 90/312]  eta: 0:04:30  lr: 0.002982  min_lr: 0.002982  loss: 2.4399 (2.4542)  weight_decay: 0.0500 (0.0500)  time: 1.0071  data: 0.0014  max mem: 78493
Epoch: [114]  [100/312]  eta: 0:04:13  lr: 0.002981  min_lr: 0.002981  loss: 2.4079 (2.4241)  weight_decay: 0.0500 (0.0500)  time: 1.0076  data: 0.0014  max mem: 78493
Epoch: [114]  [110/312]  eta: 0:03:58  lr: 0.002980  min_lr: 0.002980  loss: 2.1307 (2.4161)  weight_decay: 0.0500 (0.0500)  time: 1.0083  data: 0.0005  max mem: 78493
Epoch: [114]  [120/312]  eta: 0:03:43  lr: 0.002980  min_lr: 0.002980  loss: 2.5351 (2.4068)  weight_decay: 0.0500 (0.0500)  time: 1.0094  data: 0.0024  max mem: 78493
Epoch: [114]  [130/312]  eta: 0:03:29  lr: 0.002979  min_lr: 0.002979  loss: 2.5374 (2.4106)  weight_decay: 0.0500 (0.0500)  time: 1.0082  data: 0.0024  max mem: 78493
Epoch: [114]  [140/312]  eta: 0:03:16  lr: 0.002979  min_lr: 0.002979  loss: 2.5207 (2.4073)  weight_decay: 0.0500 (0.0500)  time: 1.0075  data: 0.0005  max mem: 78493
Epoch: [114]  [150/312]  eta: 0:03:03  lr: 0.002978  min_lr: 0.002978  loss: 2.1079 (2.3830)  weight_decay: 0.0500 (0.0500)  time: 1.0081  data: 0.0005  max mem: 78493
Epoch: [114]  [160/312]  eta: 0:02:51  lr: 0.002977  min_lr: 0.002977  loss: 2.2509 (2.3932)  weight_decay: 0.0500 (0.0500)  time: 1.0092  data: 0.0005  max mem: 78493
Epoch: [114]  [170/312]  eta: 0:02:38  lr: 0.002977  min_lr: 0.002977  loss: 2.4562 (2.3822)  weight_decay: 0.0500 (0.0500)  time: 1.0097  data: 0.0005  max mem: 78493
Epoch: [114]  [180/312]  eta: 0:02:26  lr: 0.002976  min_lr: 0.002976  loss: 2.4539 (2.3876)  weight_decay: 0.0500 (0.0500)  time: 1.0085  data: 0.0005  max mem: 78493
Epoch: [114]  [190/312]  eta: 0:02:15  lr: 0.002975  min_lr: 0.002975  loss: 2.5814 (2.3982)  weight_decay: 0.0500 (0.0500)  time: 1.0087  data: 0.0005  max mem: 78493
Epoch: [114]  [200/312]  eta: 0:02:03  lr: 0.002975  min_lr: 0.002975  loss: 2.3252 (2.3768)  weight_decay: 0.0500 (0.0500)  time: 1.0078  data: 0.0004  max mem: 78493
Epoch: [114]  [210/312]  eta: 0:01:52  lr: 0.002974  min_lr: 0.002974  loss: 2.1132 (2.3765)  weight_decay: 0.0500 (0.0500)  time: 1.0063  data: 0.0004  max mem: 78493
Epoch: [114]  [220/312]  eta: 0:01:40  lr: 0.002973  min_lr: 0.002973  loss: 2.3573 (2.3794)  weight_decay: 0.0500 (0.0500)  time: 1.0066  data: 0.0004  max mem: 78493
Epoch: [114]  [230/312]  eta: 0:01:29  lr: 0.002973  min_lr: 0.002973  loss: 2.5220 (2.3863)  weight_decay: 0.0500 (0.0500)  time: 1.0052  data: 0.0005  max mem: 78493
Epoch: [114]  [240/312]  eta: 0:01:18  lr: 0.002972  min_lr: 0.002972  loss: 2.5546 (2.3848)  weight_decay: 0.0500 (0.0500)  time: 1.0066  data: 0.0004  max mem: 78493
Epoch: [114]  [250/312]  eta: 0:01:07  lr: 0.002972  min_lr: 0.002972  loss: 2.2315 (2.3807)  weight_decay: 0.0500 (0.0500)  time: 1.0063  data: 0.0004  max mem: 78493
Epoch: [114]  [260/312]  eta: 0:00:56  lr: 0.002971  min_lr: 0.002971  loss: 2.3944 (2.3846)  weight_decay: 0.0500 (0.0500)  time: 1.0055  data: 0.0004  max mem: 78493
Epoch: [114]  [270/312]  eta: 0:00:45  lr: 0.002970  min_lr: 0.002970  loss: 2.4370 (2.3848)  weight_decay: 0.0500 (0.0500)  time: 1.0072  data: 0.0004  max mem: 78493
Epoch: [114]  [280/312]  eta: 0:00:34  lr: 0.002970  min_lr: 0.002970  loss: 2.4747 (2.3870)  weight_decay: 0.0500 (0.0500)  time: 1.0075  data: 0.0010  max mem: 78493
Epoch: [114]  [290/312]  eta: 0:00:23  lr: 0.002969  min_lr: 0.002969  loss: 2.3324 (2.3804)  weight_decay: 0.0500 (0.0500)  time: 1.0047  data: 0.0009  max mem: 78493
Epoch: [114]  [300/312]  eta: 0:00:12  lr: 0.002968  min_lr: 0.002968  loss: 2.2227 (2.3760)  weight_decay: 0.0500 (0.0500)  time: 1.0018  data: 0.0001  max mem: 78493
Epoch: [114]  [310/312]  eta: 0:00:02  lr: 0.002968  min_lr: 0.002968  loss: 2.4295 (2.3795)  weight_decay: 0.0500 (0.0500)  time: 1.0017  data: 0.0001  max mem: 78493
Epoch: [114]  [311/312]  eta: 0:00:01  lr: 0.002968  min_lr: 0.002968  loss: 2.4295 (2.3787)  weight_decay: 0.0500 (0.0500)  time: 1.0017  data: 0.0001  max mem: 78493
Epoch: [114] Total time: 0:05:34 (1.0735 s / it)
Averaged stats: lr: 0.002968  min_lr: 0.002968  loss: 2.4295 (2.3848)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:11  loss: 0.7871 (0.7871)  acc1: 81.1198 (81.1198)  acc5: 95.1823 (95.1823)  time: 7.9270  data: 7.6292  max mem: 78493
Test:  [8/9]  eta: 0:00:01  loss: 1.1128 (1.0154)  acc1: 73.4375 (74.0160)  acc5: 92.1875 (92.0800)  time: 1.0792  data: 0.8478  max mem: 78493
Test: Total time: 0:00:10 (1.1185 s / it)
* Acc@1 74.374 Acc@5 92.052 loss 1.022
Accuracy of the model on the 50000 test images: 74.4%
Max accuracy: 74.99%
Epoch: [115]  [  0/312]  eta: 1:25:34  lr: 0.002968  min_lr: 0.002968  loss: 1.9370 (1.9370)  weight_decay: 0.0500 (0.0500)  time: 16.4554  data: 15.3599  max mem: 78493
Epoch: [115]  [ 10/312]  eta: 0:13:59  lr: 0.002967  min_lr: 0.002967  loss: 1.9370 (2.1251)  weight_decay: 0.0500 (0.0500)  time: 2.7809  data: 1.3985  max mem: 78493
Epoch: [115]  [ 20/312]  eta: 0:09:25  lr: 0.002966  min_lr: 0.002966  loss: 2.2155 (2.1999)  weight_decay: 0.0500 (0.0500)  time: 1.2097  data: 0.0014  max mem: 78493
Epoch: [115]  [ 30/312]  eta: 0:07:41  lr: 0.002966  min_lr: 0.002966  loss: 2.4581 (2.2624)  weight_decay: 0.0500 (0.0500)  time: 1.0054  data: 0.0004  max mem: 78493
Epoch: [115]  [ 40/312]  eta: 0:06:42  lr: 0.002965  min_lr: 0.002965  loss: 2.4581 (2.2838)  weight_decay: 0.0500 (0.0500)  time: 1.0047  data: 0.0004  max mem: 78493
Epoch: [115]  [ 50/312]  eta: 0:06:03  lr: 0.002965  min_lr: 0.002965  loss: 2.3323 (2.2660)  weight_decay: 0.0500 (0.0500)  time: 1.0053  data: 0.0005  max mem: 78493
Epoch: [115]  [ 60/312]  eta: 0:05:34  lr: 0.002964  min_lr: 0.002964  loss: 2.4264 (2.3062)  weight_decay: 0.0500 (0.0500)  time: 1.0083  data: 0.0004  max mem: 78493
Epoch: [115]  [ 70/312]  eta: 0:05:10  lr: 0.002963  min_lr: 0.002963  loss: 2.4264 (2.3091)  weight_decay: 0.0500 (0.0500)  time: 1.0097  data: 0.0004  max mem: 78493
Epoch: [115]  [ 80/312]  eta: 0:04:49  lr: 0.002963  min_lr: 0.002963  loss: 2.5397 (2.3466)  weight_decay: 0.0500 (0.0500)  time: 1.0091  data: 0.0004  max mem: 78493
Epoch: [115]  [ 90/312]  eta: 0:04:31  lr: 0.002962  min_lr: 0.002962  loss: 2.5397 (2.3250)  weight_decay: 0.0500 (0.0500)  time: 1.0076  data: 0.0005  max mem: 78493
Epoch: [115]  [100/312]  eta: 0:04:14  lr: 0.002961  min_lr: 0.002961  loss: 1.9790 (2.2984)  weight_decay: 0.0500 (0.0500)  time: 1.0058  data: 0.0005  max mem: 78493
Epoch: [115]  [110/312]  eta: 0:03:58  lr: 0.002961  min_lr: 0.002961  loss: 2.2234 (2.3101)  weight_decay: 0.0500 (0.0500)  time: 1.0076  data: 0.0004  max mem: 78493
Epoch: [115]  [120/312]  eta: 0:03:44  lr: 0.002960  min_lr: 0.002960  loss: 2.3134 (2.2967)  weight_decay: 0.0500 (0.0500)  time: 1.0077  data: 0.0004  max mem: 78493
Epoch: [115]  [130/312]  eta: 0:03:30  lr: 0.002960  min_lr: 0.002960  loss: 2.2119 (2.3050)  weight_decay: 0.0500 (0.0500)  time: 1.0058  data: 0.0005  max mem: 78493
Epoch: [115]  [140/312]  eta: 0:03:17  lr: 0.002959  min_lr: 0.002959  loss: 2.3882 (2.3035)  weight_decay: 0.0500 (0.0500)  time: 1.0081  data: 0.0005  max mem: 78493
Epoch: [115]  [150/312]  eta: 0:03:04  lr: 0.002958  min_lr: 0.002958  loss: 2.5618 (2.3213)  weight_decay: 0.0500 (0.0500)  time: 1.0101  data: 0.0005  max mem: 78493
Epoch: [115]  [160/312]  eta: 0:02:51  lr: 0.002958  min_lr: 0.002958  loss: 2.5618 (2.3237)  weight_decay: 0.0500 (0.0500)  time: 1.0089  data: 0.0004  max mem: 78493
Epoch: [115]  [170/312]  eta: 0:02:39  lr: 0.002957  min_lr: 0.002957  loss: 2.4505 (2.3308)  weight_decay: 0.0500 (0.0500)  time: 1.0077  data: 0.0004  max mem: 78493
Epoch: [115]  [180/312]  eta: 0:02:27  lr: 0.002956  min_lr: 0.002956  loss: 2.4076 (2.3363)  weight_decay: 0.0500 (0.0500)  time: 1.0093  data: 0.0005  max mem: 78493
Epoch: [115]  [190/312]  eta: 0:02:15  lr: 0.002956  min_lr: 0.002956  loss: 2.3333 (2.3353)  weight_decay: 0.0500 (0.0500)  time: 1.0096  data: 0.0004  max mem: 78493
Epoch: [115]  [200/312]  eta: 0:02:03  lr: 0.002955  min_lr: 0.002955  loss: 2.1938 (2.3263)  weight_decay: 0.0500 (0.0500)  time: 1.0071  data: 0.0004  max mem: 78493
Epoch: [115]  [210/312]  eta: 0:01:52  lr: 0.002954  min_lr: 0.002954  loss: 2.3243 (2.3320)  weight_decay: 0.0500 (0.0500)  time: 1.0082  data: 0.0004  max mem: 78493
Epoch: [115]  [220/312]  eta: 0:01:40  lr: 0.002954  min_lr: 0.002954  loss: 2.3243 (2.3287)  weight_decay: 0.0500 (0.0500)  time: 1.0074  data: 0.0004  max mem: 78493
Epoch: [115]  [230/312]  eta: 0:01:29  lr: 0.002953  min_lr: 0.002953  loss: 2.2836 (2.3307)  weight_decay: 0.0500 (0.0500)  time: 1.0064  data: 0.0004  max mem: 78493
Epoch: [115]  [240/312]  eta: 0:01:18  lr: 0.002953  min_lr: 0.002953  loss: 2.3898 (2.3295)  weight_decay: 0.0500 (0.0500)  time: 1.0081  data: 0.0004  max mem: 78493
Epoch: [115]  [250/312]  eta: 0:01:07  lr: 0.002952  min_lr: 0.002952  loss: 2.2846 (2.3248)  weight_decay: 0.0500 (0.0500)  time: 1.0070  data: 0.0004  max mem: 78493
Epoch: [115]  [260/312]  eta: 0:00:56  lr: 0.002951  min_lr: 0.002951  loss: 2.4006 (2.3262)  weight_decay: 0.0500 (0.0500)  time: 1.0059  data: 0.0004  max mem: 78493
Epoch: [115]  [270/312]  eta: 0:00:45  lr: 0.002951  min_lr: 0.002951  loss: 2.3879 (2.3261)  weight_decay: 0.0500 (0.0500)  time: 1.0058  data: 0.0004  max mem: 78493
Epoch: [115]  [280/312]  eta: 0:00:34  lr: 0.002950  min_lr: 0.002950  loss: 2.5026 (2.3342)  weight_decay: 0.0500 (0.0500)  time: 1.0061  data: 0.0011  max mem: 78493
Epoch: [115]  [290/312]  eta: 0:00:23  lr: 0.002949  min_lr: 0.002949  loss: 2.5299 (2.3342)  weight_decay: 0.0500 (0.0500)  time: 1.0043  data: 0.0009  max mem: 78493
Epoch: [115]  [300/312]  eta: 0:00:12  lr: 0.002949  min_lr: 0.002949  loss: 2.2867 (2.3335)  weight_decay: 0.0500 (0.0500)  time: 1.0020  data: 0.0001  max mem: 78493
Epoch: [115]  [310/312]  eta: 0:00:02  lr: 0.002948  min_lr: 0.002948  loss: 2.3112 (2.3380)  weight_decay: 0.0500 (0.0500)  time: 1.0019  data: 0.0001  max mem: 78493
Epoch: [115]  [311/312]  eta: 0:00:01  lr: 0.002948  min_lr: 0.002948  loss: 2.3437 (2.3383)  weight_decay: 0.0500 (0.0500)  time: 1.0019  data: 0.0001  max mem: 78493
Epoch: [115] Total time: 0:05:35 (1.0751 s / it)
Averaged stats: lr: 0.002948  min_lr: 0.002948  loss: 2.3437 (2.3831)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:17  loss: 0.8116 (0.8116)  acc1: 80.4688 (80.4688)  acc5: 94.5312 (94.5312)  time: 8.6376  data: 8.3580  max mem: 78493
Test:  [8/9]  eta: 0:00:01  loss: 1.0748 (1.0260)  acc1: 73.4375 (74.2080)  acc5: 91.5365 (91.7280)  time: 1.1580  data: 0.9288  max mem: 78493
Test: Total time: 0:00:10 (1.1991 s / it)
* Acc@1 74.356 Acc@5 92.196 loss 1.014
Accuracy of the model on the 50000 test images: 74.4%
Max accuracy: 74.99%
Epoch: [116]  [  0/312]  eta: 1:24:23  lr: 0.002948  min_lr: 0.002948  loss: 2.4968 (2.4968)  weight_decay: 0.0500 (0.0500)  time: 16.2279  data: 14.3245  max mem: 78493
Epoch: [116]  [ 10/312]  eta: 0:12:59  lr: 0.002947  min_lr: 0.002947  loss: 2.3464 (2.2638)  weight_decay: 0.0500 (0.0500)  time: 2.5822  data: 1.3056  max mem: 78493
Epoch: [116]  [ 20/312]  eta: 0:08:56  lr: 0.002947  min_lr: 0.002947  loss: 2.3464 (2.3296)  weight_decay: 0.0500 (0.0500)  time: 1.1196  data: 0.0022  max mem: 78493
Epoch: [116]  [ 30/312]  eta: 0:07:23  lr: 0.002946  min_lr: 0.002946  loss: 2.3840 (2.3471)  weight_decay: 0.0500 (0.0500)  time: 1.0163  data: 0.0005  max mem: 78493
Epoch: [116]  [ 40/312]  eta: 0:06:29  lr: 0.002945  min_lr: 0.002945  loss: 2.2958 (2.3149)  weight_decay: 0.0500 (0.0500)  time: 1.0080  data: 0.0005  max mem: 78493
Epoch: [116]  [ 50/312]  eta: 0:05:53  lr: 0.002945  min_lr: 0.002945  loss: 2.2958 (2.3330)  weight_decay: 0.0500 (0.0500)  time: 1.0054  data: 0.0005  max mem: 78493
Epoch: [116]  [ 60/312]  eta: 0:05:25  lr: 0.002944  min_lr: 0.002944  loss: 2.4746 (2.3377)  weight_decay: 0.0500 (0.0500)  time: 1.0050  data: 0.0005  max mem: 78493
Epoch: [116]  [ 70/312]  eta: 0:05:03  lr: 0.002944  min_lr: 0.002944  loss: 2.4746 (2.3593)  weight_decay: 0.0500 (0.0500)  time: 1.0056  data: 0.0004  max mem: 78493
Epoch: [116]  [ 80/312]  eta: 0:04:43  lr: 0.002943  min_lr: 0.002943  loss: 2.5838 (2.3828)  weight_decay: 0.0500 (0.0500)  time: 1.0073  data: 0.0005  max mem: 78493
Epoch: [116]  [ 90/312]  eta: 0:04:26  lr: 0.002942  min_lr: 0.002942  loss: 2.5082 (2.3962)  weight_decay: 0.0500 (0.0500)  time: 1.0075  data: 0.0004  max mem: 78493
Epoch: [116]  [100/312]  eta: 0:04:10  lr: 0.002942  min_lr: 0.002942  loss: 2.4666 (2.3954)  weight_decay: 0.0500 (0.0500)  time: 1.0083  data: 0.0004  max mem: 78493
Epoch: [116]  [110/312]  eta: 0:03:55  lr: 0.002941  min_lr: 0.002941  loss: 2.5994 (2.4015)  weight_decay: 0.0500 (0.0500)  time: 1.0067  data: 0.0011  max mem: 78493
Epoch: [116]  [120/312]  eta: 0:03:41  lr: 0.002940  min_lr: 0.002940  loss: 2.1396 (2.3853)  weight_decay: 0.0500 (0.0500)  time: 1.0056  data: 0.0018  max mem: 78493
Epoch: [116]  [130/312]  eta: 0:03:27  lr: 0.002940  min_lr: 0.002940  loss: 2.0951 (2.3753)  weight_decay: 0.0500 (0.0500)  time: 1.0079  data: 0.0012  max mem: 78493
Epoch: [116]  [140/312]  eta: 0:03:14  lr: 0.002939  min_lr: 0.002939  loss: 2.3409 (2.3716)  weight_decay: 0.0500 (0.0500)  time: 1.0071  data: 0.0005  max mem: 78493
Epoch: [116]  [150/312]  eta: 0:03:01  lr: 0.002938  min_lr: 0.002938  loss: 2.2625 (2.3584)  weight_decay: 0.0500 (0.0500)  time: 1.0082  data: 0.0005  max mem: 78493
Epoch: [116]  [160/312]  eta: 0:02:49  lr: 0.002938  min_lr: 0.002938  loss: 2.2625 (2.3621)  weight_decay: 0.0500 (0.0500)  time: 1.0094  data: 0.0019  max mem: 78493
Epoch: [116]  [170/312]  eta: 0:02:37  lr: 0.002937  min_lr: 0.002937  loss: 2.4040 (2.3585)  weight_decay: 0.0500 (0.0500)  time: 1.0098  data: 0.0019  max mem: 78493
Epoch: [116]  [180/312]  eta: 0:02:25  lr: 0.002937  min_lr: 0.002937  loss: 2.4040 (2.3646)  weight_decay: 0.0500 (0.0500)  time: 1.0101  data: 0.0005  max mem: 78493
Epoch: [116]  [190/312]  eta: 0:02:14  lr: 0.002936  min_lr: 0.002936  loss: 2.5499 (2.3691)  weight_decay: 0.0500 (0.0500)  time: 1.0099  data: 0.0005  max mem: 78493
Epoch: [116]  [200/312]  eta: 0:02:02  lr: 0.002935  min_lr: 0.002935  loss: 2.3826 (2.3598)  weight_decay: 0.0500 (0.0500)  time: 1.0087  data: 0.0004  max mem: 78493
Epoch: [116]  [210/312]  eta: 0:01:51  lr: 0.002935  min_lr: 0.002935  loss: 2.3561 (2.3631)  weight_decay: 0.0500 (0.0500)  time: 1.0078  data: 0.0005  max mem: 78493
Epoch: [116]  [220/312]  eta: 0:01:39  lr: 0.002934  min_lr: 0.002934  loss: 2.5562 (2.3631)  weight_decay: 0.0500 (0.0500)  time: 1.0098  data: 0.0004  max mem: 78493
Epoch: [116]  [230/312]  eta: 0:01:28  lr: 0.002933  min_lr: 0.002933  loss: 2.5213 (2.3660)  weight_decay: 0.0500 (0.0500)  time: 1.0080  data: 0.0004  max mem: 78493
Epoch: [116]  [240/312]  eta: 0:01:17  lr: 0.002933  min_lr: 0.002933  loss: 2.4778 (2.3681)  weight_decay: 0.0500 (0.0500)  time: 1.0072  data: 0.0004  max mem: 78493
Epoch: [116]  [250/312]  eta: 0:01:06  lr: 0.002932  min_lr: 0.002932  loss: 2.5977 (2.3739)  weight_decay: 0.0500 (0.0500)  time: 1.0072  data: 0.0005  max mem: 78493
Epoch: [116]  [260/312]  eta: 0:00:55  lr: 0.002931  min_lr: 0.002931  loss: 2.5271 (2.3750)  weight_decay: 0.0500 (0.0500)  time: 1.0081  data: 0.0005  max mem: 78493
Epoch: [116]  [270/312]  eta: 0:00:45  lr: 0.002931  min_lr: 0.002931  loss: 2.2976 (2.3735)  weight_decay: 0.0500 (0.0500)  time: 1.0089  data: 0.0004  max mem: 78493
Epoch: [116]  [280/312]  eta: 0:00:34  lr: 0.002930  min_lr: 0.002930  loss: 2.2976 (2.3675)  weight_decay: 0.0500 (0.0500)  time: 1.0085  data: 0.0019  max mem: 78493
Epoch: [116]  [290/312]  eta: 0:00:23  lr: 0.002930  min_lr: 0.002930  loss: 2.2030 (2.3610)  weight_decay: 0.0500 (0.0500)  time: 1.0054  data: 0.0017  max mem: 78493
Epoch: [116]  [300/312]  eta: 0:00:12  lr: 0.002929  min_lr: 0.002929  loss: 2.4429 (2.3631)  weight_decay: 0.0500 (0.0500)  time: 1.0013  data: 0.0001  max mem: 78493
Epoch: [116]  [310/312]  eta: 0:00:02  lr: 0.002928  min_lr: 0.002928  loss: 2.5288 (2.3655)  weight_decay: 0.0500 (0.0500)  time: 1.0016  data: 0.0001  max mem: 78493
Epoch: [116]  [311/312]  eta: 0:00:01  lr: 0.002928  min_lr: 0.002928  loss: 2.5107 (2.3658)  weight_decay: 0.0500 (0.0500)  time: 1.0015  data: 0.0001  max mem: 78493
Epoch: [116] Total time: 0:05:33 (1.0688 s / it)
Averaged stats: lr: 0.002928  min_lr: 0.002928  loss: 2.5107 (2.3717)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:15  loss: 0.8325 (0.8325)  acc1: 79.9479 (79.9479)  acc5: 94.5312 (94.5312)  time: 8.3970  data: 8.1204  max mem: 78493
Test:  [8/9]  eta: 0:00:01  loss: 1.1445 (1.0211)  acc1: 71.8750 (73.9520)  acc5: 91.2760 (92.0640)  time: 1.1311  data: 0.9024  max mem: 78493
Test: Total time: 0:00:10 (1.1431 s / it)
* Acc@1 74.582 Acc@5 92.202 loss 1.004
Accuracy of the model on the 50000 test images: 74.6%
Max accuracy: 74.99%
Epoch: [117]  [  0/312]  eta: 1:26:29  lr: 0.002928  min_lr: 0.002928  loss: 3.0446 (3.0446)  weight_decay: 0.0500 (0.0500)  time: 16.6346  data: 15.0145  max mem: 78493
Epoch: [117]  [ 10/312]  eta: 0:13:53  lr: 0.002928  min_lr: 0.002928  loss: 2.5318 (2.4396)  weight_decay: 0.0500 (0.0500)  time: 2.7601  data: 1.3657  max mem: 78493
Epoch: [117]  [ 20/312]  eta: 0:09:22  lr: 0.002927  min_lr: 0.002927  loss: 2.5318 (2.4996)  weight_decay: 0.0500 (0.0500)  time: 1.1919  data: 0.0006  max mem: 78493
Epoch: [117]  [ 30/312]  eta: 0:07:40  lr: 0.002926  min_lr: 0.002926  loss: 2.3766 (2.4083)  weight_decay: 0.0500 (0.0500)  time: 1.0108  data: 0.0005  max mem: 78493
Epoch: [117]  [ 40/312]  eta: 0:06:42  lr: 0.002926  min_lr: 0.002926  loss: 2.3124 (2.4133)  weight_decay: 0.0500 (0.0500)  time: 1.0092  data: 0.0005  max mem: 78493
Epoch: [117]  [ 50/312]  eta: 0:06:03  lr: 0.002925  min_lr: 0.002925  loss: 2.3489 (2.3892)  weight_decay: 0.0500 (0.0500)  time: 1.0071  data: 0.0005  max mem: 78493
Epoch: [117]  [ 60/312]  eta: 0:05:33  lr: 0.002924  min_lr: 0.002924  loss: 2.2559 (2.3600)  weight_decay: 0.0500 (0.0500)  time: 1.0075  data: 0.0005  max mem: 78493
Epoch: [117]  [ 70/312]  eta: 0:05:09  lr: 0.002924  min_lr: 0.002924  loss: 2.4706 (2.3868)  weight_decay: 0.0500 (0.0500)  time: 1.0061  data: 0.0004  max mem: 78493
Epoch: [117]  [ 80/312]  eta: 0:04:49  lr: 0.002923  min_lr: 0.002923  loss: 2.5491 (2.3781)  weight_decay: 0.0500 (0.0500)  time: 1.0047  data: 0.0012  max mem: 78493
Epoch: [117]  [ 90/312]  eta: 0:04:30  lr: 0.002922  min_lr: 0.002922  loss: 2.5566 (2.3903)  weight_decay: 0.0500 (0.0500)  time: 1.0065  data: 0.0012  max mem: 78493
Epoch: [117]  [100/312]  eta: 0:04:14  lr: 0.002922  min_lr: 0.002922  loss: 2.6166 (2.4071)  weight_decay: 0.0500 (0.0500)  time: 1.0076  data: 0.0004  max mem: 78493
Epoch: [117]  [110/312]  eta: 0:03:58  lr: 0.002921  min_lr: 0.002921  loss: 2.5357 (2.4048)  weight_decay: 0.0500 (0.0500)  time: 1.0092  data: 0.0017  max mem: 78493
Epoch: [117]  [120/312]  eta: 0:03:44  lr: 0.002921  min_lr: 0.002921  loss: 2.4263 (2.3963)  weight_decay: 0.0500 (0.0500)  time: 1.0078  data: 0.0017  max mem: 78493
Epoch: [117]  [130/312]  eta: 0:03:30  lr: 0.002920  min_lr: 0.002920  loss: 2.2564 (2.3806)  weight_decay: 0.0500 (0.0500)  time: 1.0070  data: 0.0004  max mem: 78493
Epoch: [117]  [140/312]  eta: 0:03:16  lr: 0.002919  min_lr: 0.002919  loss: 2.1266 (2.3802)  weight_decay: 0.0500 (0.0500)  time: 1.0100  data: 0.0021  max mem: 78493
Epoch: [117]  [150/312]  eta: 0:03:03  lr: 0.002919  min_lr: 0.002919  loss: 2.4149 (2.3854)  weight_decay: 0.0500 (0.0500)  time: 1.0093  data: 0.0021  max mem: 78493
Epoch: [117]  [160/312]  eta: 0:02:51  lr: 0.002918  min_lr: 0.002918  loss: 2.5998 (2.3963)  weight_decay: 0.0500 (0.0500)  time: 1.0076  data: 0.0004  max mem: 78493
Epoch: [117]  [170/312]  eta: 0:02:39  lr: 0.002917  min_lr: 0.002917  loss: 2.5504 (2.3993)  weight_decay: 0.0500 (0.0500)  time: 1.0079  data: 0.0004  max mem: 78493
Epoch: [117]  [180/312]  eta: 0:02:27  lr: 0.002917  min_lr: 0.002917  loss: 2.4303 (2.3879)  weight_decay: 0.0500 (0.0500)  time: 1.0093  data: 0.0004  max mem: 78493
Epoch: [117]  [190/312]  eta: 0:02:15  lr: 0.002916  min_lr: 0.002916  loss: 2.2982 (2.3859)  weight_decay: 0.0500 (0.0500)  time: 1.0109  data: 0.0004  max mem: 78493
Epoch: [117]  [200/312]  eta: 0:02:03  lr: 0.002915  min_lr: 0.002915  loss: 2.3537 (2.3802)  weight_decay: 0.0500 (0.0500)  time: 1.0099  data: 0.0004  max mem: 78493
Epoch: [117]  [210/312]  eta: 0:01:52  lr: 0.002915  min_lr: 0.002915  loss: 2.3164 (2.3707)  weight_decay: 0.0500 (0.0500)  time: 1.0089  data: 0.0004  max mem: 78493
Epoch: [117]  [220/312]  eta: 0:01:40  lr: 0.002914  min_lr: 0.002914  loss: 2.4078 (2.3784)  weight_decay: 0.0500 (0.0500)  time: 1.0081  data: 0.0004  max mem: 78493
Epoch: [117]  [230/312]  eta: 0:01:29  lr: 0.002914  min_lr: 0.002914  loss: 2.4078 (2.3678)  weight_decay: 0.0500 (0.0500)  time: 1.0076  data: 0.0005  max mem: 78493
Epoch: [117]  [240/312]  eta: 0:01:18  lr: 0.002913  min_lr: 0.002913  loss: 2.3560 (2.3686)  weight_decay: 0.0500 (0.0500)  time: 1.0073  data: 0.0005  max mem: 78493
Epoch: [117]  [250/312]  eta: 0:01:07  lr: 0.002912  min_lr: 0.002912  loss: 2.4342 (2.3742)  weight_decay: 0.0500 (0.0500)  time: 1.0066  data: 0.0011  max mem: 78493
Epoch: [117]  [260/312]  eta: 0:00:56  lr: 0.002912  min_lr: 0.002912  loss: 2.6276 (2.3814)  weight_decay: 0.0500 (0.0500)  time: 1.0052  data: 0.0011  max mem: 78493
Epoch: [117]  [270/312]  eta: 0:00:45  lr: 0.002911  min_lr: 0.002911  loss: 2.6276 (2.3831)  weight_decay: 0.0500 (0.0500)  time: 1.0058  data: 0.0004  max mem: 78493
Epoch: [117]  [280/312]  eta: 0:00:34  lr: 0.002910  min_lr: 0.002910  loss: 2.2123 (2.3777)  weight_decay: 0.0500 (0.0500)  time: 1.0071  data: 0.0011  max mem: 78493
Epoch: [117]  [290/312]  eta: 0:00:23  lr: 0.002910  min_lr: 0.002910  loss: 2.2393 (2.3801)  weight_decay: 0.0500 (0.0500)  time: 1.0049  data: 0.0009  max mem: 78493
Epoch: [117]  [300/312]  eta: 0:00:12  lr: 0.002909  min_lr: 0.002909  loss: 2.2393 (2.3774)  weight_decay: 0.0500 (0.0500)  time: 1.0029  data: 0.0001  max mem: 78493
Epoch: [117]  [310/312]  eta: 0:00:02  lr: 0.002908  min_lr: 0.002908  loss: 2.1515 (2.3714)  weight_decay: 0.0500 (0.0500)  time: 1.0022  data: 0.0001  max mem: 78493
Epoch: [117]  [311/312]  eta: 0:00:01  lr: 0.002908  min_lr: 0.002908  loss: 2.1515 (2.3701)  weight_decay: 0.0500 (0.0500)  time: 1.0022  data: 0.0001  max mem: 78493
Epoch: [117] Total time: 0:05:35 (1.0751 s / it)
Averaged stats: lr: 0.002908  min_lr: 0.002908  loss: 2.1515 (2.3837)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:15  loss: 0.8585 (0.8585)  acc1: 79.5573 (79.5573)  acc5: 94.0104 (94.0104)  time: 8.3950  data: 8.1203  max mem: 78493
Test:  [8/9]  eta: 0:00:01  loss: 1.1091 (1.0316)  acc1: 73.1771 (73.8080)  acc5: 92.0573 (92.1440)  time: 1.1309  data: 0.9023  max mem: 78493
Test: Total time: 0:00:10 (1.1488 s / it)
* Acc@1 74.060 Acc@5 91.852 loss 1.031
Accuracy of the model on the 50000 test images: 74.1%
Max accuracy: 74.99%
Epoch: [118]  [  0/312]  eta: 1:25:15  lr: 0.002908  min_lr: 0.002908  loss: 2.7809 (2.7809)  weight_decay: 0.0500 (0.0500)  time: 16.3951  data: 15.0869  max mem: 78493
Epoch: [118]  [ 10/312]  eta: 0:13:41  lr: 0.002908  min_lr: 0.002908  loss: 2.4420 (2.4233)  weight_decay: 0.0500 (0.0500)  time: 2.7207  data: 1.3754  max mem: 78493
Epoch: [118]  [ 20/312]  eta: 0:09:16  lr: 0.002907  min_lr: 0.002907  loss: 2.3720 (2.3095)  weight_decay: 0.0500 (0.0500)  time: 1.1831  data: 0.0024  max mem: 78493
Epoch: [118]  [ 30/312]  eta: 0:07:36  lr: 0.002906  min_lr: 0.002906  loss: 2.4984 (2.3747)  weight_decay: 0.0500 (0.0500)  time: 1.0112  data: 0.0005  max mem: 78493
Epoch: [118]  [ 40/312]  eta: 0:06:39  lr: 0.002906  min_lr: 0.002906  loss: 2.4984 (2.3463)  weight_decay: 0.0500 (0.0500)  time: 1.0087  data: 0.0005  max mem: 78493
Epoch: [118]  [ 50/312]  eta: 0:06:01  lr: 0.002905  min_lr: 0.002905  loss: 2.4445 (2.3784)  weight_decay: 0.0500 (0.0500)  time: 1.0127  data: 0.0021  max mem: 78493
Epoch: [118]  [ 60/312]  eta: 0:05:32  lr: 0.002904  min_lr: 0.002904  loss: 2.4445 (2.3739)  weight_decay: 0.0500 (0.0500)  time: 1.0123  data: 0.0021  max mem: 78493
Epoch: [118]  [ 70/312]  eta: 0:05:08  lr: 0.002904  min_lr: 0.002904  loss: 2.4463 (2.3787)  weight_decay: 0.0500 (0.0500)  time: 1.0076  data: 0.0005  max mem: 78493
Epoch: [118]  [ 80/312]  eta: 0:04:48  lr: 0.002903  min_lr: 0.002903  loss: 2.4847 (2.3892)  weight_decay: 0.0500 (0.0500)  time: 1.0110  data: 0.0005  max mem: 78493
Epoch: [118]  [ 90/312]  eta: 0:04:30  lr: 0.002902  min_lr: 0.002902  loss: 2.5203 (2.3757)  weight_decay: 0.0500 (0.0500)  time: 1.0096  data: 0.0005  max mem: 78493
Epoch: [118]  [100/312]  eta: 0:04:13  lr: 0.002902  min_lr: 0.002902  loss: 2.5203 (2.3903)  weight_decay: 0.0500 (0.0500)  time: 1.0096  data: 0.0005  max mem: 78493
Epoch: [118]  [110/312]  eta: 0:03:58  lr: 0.002901  min_lr: 0.002901  loss: 2.4109 (2.3738)  weight_decay: 0.0500 (0.0500)  time: 1.0120  data: 0.0005  max mem: 78493
Epoch: [118]  [120/312]  eta: 0:03:43  lr: 0.002901  min_lr: 0.002901  loss: 2.5719 (2.4070)  weight_decay: 0.0500 (0.0500)  time: 1.0080  data: 0.0005  max mem: 78493
Epoch: [118]  [130/312]  eta: 0:03:29  lr: 0.002900  min_lr: 0.002900  loss: 2.5286 (2.3895)  weight_decay: 0.0500 (0.0500)  time: 1.0076  data: 0.0004  max mem: 78493
Epoch: [118]  [140/312]  eta: 0:03:16  lr: 0.002899  min_lr: 0.002899  loss: 2.2922 (2.3910)  weight_decay: 0.0500 (0.0500)  time: 1.0104  data: 0.0004  max mem: 78493
Epoch: [118]  [150/312]  eta: 0:03:03  lr: 0.002899  min_lr: 0.002899  loss: 2.4289 (2.4030)  weight_decay: 0.0500 (0.0500)  time: 1.0079  data: 0.0004  max mem: 78493
Epoch: [118]  [160/312]  eta: 0:02:51  lr: 0.002898  min_lr: 0.002898  loss: 2.5275 (2.3975)  weight_decay: 0.0500 (0.0500)  time: 1.0055  data: 0.0005  max mem: 78493
Epoch: [118]  [170/312]  eta: 0:02:38  lr: 0.002897  min_lr: 0.002897  loss: 2.5275 (2.4046)  weight_decay: 0.0500 (0.0500)  time: 1.0064  data: 0.0005  max mem: 78493
Epoch: [118]  [180/312]  eta: 0:02:26  lr: 0.002897  min_lr: 0.002897  loss: 2.6269 (2.4120)  weight_decay: 0.0500 (0.0500)  time: 1.0071  data: 0.0005  max mem: 78493
Epoch: [118]  [190/312]  eta: 0:02:15  lr: 0.002896  min_lr: 0.002896  loss: 2.5100 (2.4116)  weight_decay: 0.0500 (0.0500)  time: 1.0067  data: 0.0005  max mem: 78493
Epoch: [118]  [200/312]  eta: 0:02:03  lr: 0.002895  min_lr: 0.002895  loss: 2.4731 (2.4088)  weight_decay: 0.0500 (0.0500)  time: 1.0073  data: 0.0017  max mem: 78493
Epoch: [118]  [210/312]  eta: 0:01:52  lr: 0.002895  min_lr: 0.002895  loss: 2.3405 (2.4001)  weight_decay: 0.0500 (0.0500)  time: 1.0097  data: 0.0017  max mem: 78493
Epoch: [118]  [220/312]  eta: 0:01:40  lr: 0.002894  min_lr: 0.002894  loss: 2.4446 (2.4013)  weight_decay: 0.0500 (0.0500)  time: 1.0088  data: 0.0004  max mem: 78493
Epoch: [118]  [230/312]  eta: 0:01:29  lr: 0.002893  min_lr: 0.002893  loss: 2.2858 (2.3929)  weight_decay: 0.0500 (0.0500)  time: 1.0075  data: 0.0004  max mem: 78493
Epoch: [118]  [240/312]  eta: 0:01:18  lr: 0.002893  min_lr: 0.002893  loss: 2.2858 (2.3940)  weight_decay: 0.0500 (0.0500)  time: 1.0058  data: 0.0004  max mem: 78493
Epoch: [118]  [250/312]  eta: 0:01:07  lr: 0.002892  min_lr: 0.002892  loss: 2.5451 (2.3928)  weight_decay: 0.0500 (0.0500)  time: 1.0040  data: 0.0004  max mem: 78493
Epoch: [118]  [260/312]  eta: 0:00:56  lr: 0.002892  min_lr: 0.002892  loss: 2.5088 (2.3943)  weight_decay: 0.0500 (0.0500)  time: 1.0054  data: 0.0004  max mem: 78493
Epoch: [118]  [270/312]  eta: 0:00:45  lr: 0.002891  min_lr: 0.002891  loss: 2.3902 (2.3938)  weight_decay: 0.0500 (0.0500)  time: 1.0064  data: 0.0004  max mem: 78493
Epoch: [118]  [280/312]  eta: 0:00:34  lr: 0.002890  min_lr: 0.002890  loss: 2.2212 (2.3899)  weight_decay: 0.0500 (0.0500)  time: 1.0061  data: 0.0011  max mem: 78493
Epoch: [118]  [290/312]  eta: 0:00:23  lr: 0.002890  min_lr: 0.002890  loss: 2.2212 (2.3874)  weight_decay: 0.0500 (0.0500)  time: 1.0041  data: 0.0009  max mem: 78493
Epoch: [118]  [300/312]  eta: 0:00:12  lr: 0.002889  min_lr: 0.002889  loss: 2.3506 (2.3924)  weight_decay: 0.0500 (0.0500)  time: 1.0020  data: 0.0001  max mem: 78493
Epoch: [118]  [310/312]  eta: 0:00:02  lr: 0.002888  min_lr: 0.002888  loss: 2.3217 (2.3855)  weight_decay: 0.0500 (0.0500)  time: 1.0019  data: 0.0001  max mem: 78493
Epoch: [118]  [311/312]  eta: 0:00:01  lr: 0.002888  min_lr: 0.002888  loss: 2.3042 (2.3849)  weight_decay: 0.0500 (0.0500)  time: 1.0019  data: 0.0001  max mem: 78493
Epoch: [118] Total time: 0:05:35 (1.0738 s / it)
Averaged stats: lr: 0.002888  min_lr: 0.002888  loss: 2.3042 (2.3755)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:13  loss: 0.6872 (0.6872)  acc1: 82.8125 (82.8125)  acc5: 95.7031 (95.7031)  time: 8.2045  data: 7.9215  max mem: 78493
Test:  [8/9]  eta: 0:00:01  loss: 1.0972 (0.9654)  acc1: 73.5677 (75.1200)  acc5: 92.7083 (92.8800)  time: 1.1114  data: 0.8817  max mem: 78493
Test: Total time: 0:00:10 (1.1552 s / it)
* Acc@1 75.390 Acc@5 92.706 loss 0.973
Accuracy of the model on the 50000 test images: 75.4%
Max accuracy: 75.39%
Epoch: [119]  [  0/312]  eta: 1:17:09  lr: 0.002888  min_lr: 0.002888  loss: 2.6500 (2.6500)  weight_decay: 0.0500 (0.0500)  time: 14.8393  data: 13.3759  max mem: 78493
Epoch: [119]  [ 10/312]  eta: 0:12:22  lr: 0.002888  min_lr: 0.002888  loss: 2.6500 (2.5565)  weight_decay: 0.0500 (0.0500)  time: 2.4572  data: 1.3491  max mem: 78493
Epoch: [119]  [ 20/312]  eta: 0:08:40  lr: 0.002887  min_lr: 0.002887  loss: 2.5103 (2.4189)  weight_decay: 0.0500 (0.0500)  time: 1.1285  data: 0.0751  max mem: 78493
Epoch: [119]  [ 30/312]  eta: 0:07:12  lr: 0.002886  min_lr: 0.002886  loss: 2.3726 (2.4277)  weight_decay: 0.0500 (0.0500)  time: 1.0249  data: 0.0021  max mem: 78493
Epoch: [119]  [ 40/312]  eta: 0:06:22  lr: 0.002886  min_lr: 0.002886  loss: 2.3980 (2.3855)  weight_decay: 0.0500 (0.0500)  time: 1.0105  data: 0.0004  max mem: 78493
Epoch: [119]  [ 50/312]  eta: 0:05:47  lr: 0.002885  min_lr: 0.002885  loss: 2.4774 (2.4207)  weight_decay: 0.0500 (0.0500)  time: 1.0090  data: 0.0004  max mem: 78493
Epoch: [119]  [ 60/312]  eta: 0:05:21  lr: 0.002884  min_lr: 0.002884  loss: 2.5471 (2.4091)  weight_decay: 0.0500 (0.0500)  time: 1.0071  data: 0.0005  max mem: 78493
Epoch: [119]  [ 70/312]  eta: 0:04:59  lr: 0.002884  min_lr: 0.002884  loss: 2.1592 (2.3699)  weight_decay: 0.0500 (0.0500)  time: 1.0056  data: 0.0005  max mem: 78493
Epoch: [119]  [ 80/312]  eta: 0:04:40  lr: 0.002883  min_lr: 0.002883  loss: 2.1541 (2.3448)  weight_decay: 0.0500 (0.0500)  time: 1.0067  data: 0.0005  max mem: 78493
Epoch: [119]  [ 90/312]  eta: 0:04:23  lr: 0.002882  min_lr: 0.002882  loss: 2.3933 (2.3613)  weight_decay: 0.0500 (0.0500)  time: 1.0079  data: 0.0005  max mem: 78493
Epoch: [119]  [100/312]  eta: 0:04:07  lr: 0.002882  min_lr: 0.002882  loss: 2.4868 (2.3605)  weight_decay: 0.0500 (0.0500)  time: 1.0068  data: 0.0004  max mem: 78493
Epoch: [119]  [110/312]  eta: 0:03:53  lr: 0.002881  min_lr: 0.002881  loss: 2.3857 (2.3672)  weight_decay: 0.0500 (0.0500)  time: 1.0065  data: 0.0005  max mem: 78493
Epoch: [119]  [120/312]  eta: 0:03:39  lr: 0.002880  min_lr: 0.002880  loss: 2.2708 (2.3585)  weight_decay: 0.0500 (0.0500)  time: 1.0071  data: 0.0004  max mem: 78493
Epoch: [119]  [130/312]  eta: 0:03:25  lr: 0.002880  min_lr: 0.002880  loss: 2.2523 (2.3584)  weight_decay: 0.0500 (0.0500)  time: 1.0063  data: 0.0004  max mem: 78493
Epoch: [119]  [140/312]  eta: 0:03:13  lr: 0.002879  min_lr: 0.002879  loss: 2.2595 (2.3644)  weight_decay: 0.0500 (0.0500)  time: 1.0060  data: 0.0005  max mem: 78493
Epoch: [119]  [150/312]  eta: 0:03:00  lr: 0.002879  min_lr: 0.002879  loss: 2.4240 (2.3689)  weight_decay: 0.0500 (0.0500)  time: 1.0064  data: 0.0004  max mem: 78493
Epoch: [119]  [160/312]  eta: 0:02:48  lr: 0.002878  min_lr: 0.002878  loss: 2.5086 (2.3783)  weight_decay: 0.0500 (0.0500)  time: 1.0089  data: 0.0004  max mem: 78493
Epoch: [119]  [170/312]  eta: 0:02:36  lr: 0.002877  min_lr: 0.002877  loss: 2.4654 (2.3768)  weight_decay: 0.0500 (0.0500)  time: 1.0102  data: 0.0005  max mem: 78493
Epoch: [119]  [180/312]  eta: 0:02:24  lr: 0.002877  min_lr: 0.002877  loss: 2.4306 (2.3790)  weight_decay: 0.0500 (0.0500)  time: 1.0123  data: 0.0005  max mem: 78493
Epoch: [119]  [190/312]  eta: 0:02:13  lr: 0.002876  min_lr: 0.002876  loss: 2.4477 (2.3852)  weight_decay: 0.0500 (0.0500)  time: 1.0151  data: 0.0005  max mem: 78493
Epoch: [119]  [200/312]  eta: 0:02:02  lr: 0.002875  min_lr: 0.002875  loss: 2.4477 (2.3900)  weight_decay: 0.0500 (0.0500)  time: 1.0118  data: 0.0005  max mem: 78493
Epoch: [119]  [210/312]  eta: 0:01:50  lr: 0.002875  min_lr: 0.002875  loss: 2.3317 (2.3843)  weight_decay: 0.0500 (0.0500)  time: 1.0076  data: 0.0004  max mem: 78493
Epoch: [119]  [220/312]  eta: 0:01:39  lr: 0.002874  min_lr: 0.002874  loss: 2.4677 (2.3902)  weight_decay: 0.0500 (0.0500)  time: 1.0064  data: 0.0004  max mem: 78493
Epoch: [119]  [230/312]  eta: 0:01:28  lr: 0.002873  min_lr: 0.002873  loss: 2.5228 (2.3920)  weight_decay: 0.0500 (0.0500)  time: 1.0077  data: 0.0004  max mem: 78493
Epoch: [119]  [240/312]  eta: 0:01:17  lr: 0.002873  min_lr: 0.002873  loss: 2.3895 (2.3886)  weight_decay: 0.0500 (0.0500)  time: 1.0087  data: 0.0005  max mem: 78493
Epoch: [119]  [250/312]  eta: 0:01:06  lr: 0.002872  min_lr: 0.002872  loss: 2.1809 (2.3804)  weight_decay: 0.0500 (0.0500)  time: 1.0064  data: 0.0005  max mem: 78493
Epoch: [119]  [260/312]  eta: 0:00:55  lr: 0.002871  min_lr: 0.002871  loss: 2.3299 (2.3848)  weight_decay: 0.0500 (0.0500)  time: 1.0049  data: 0.0005  max mem: 78493
Epoch: [119]  [270/312]  eta: 0:00:44  lr: 0.002871  min_lr: 0.002871  loss: 2.6026 (2.3911)  weight_decay: 0.0500 (0.0500)  time: 1.0055  data: 0.0005  max mem: 78493
Epoch: [119]  [280/312]  eta: 0:00:34  lr: 0.002870  min_lr: 0.002870  loss: 2.3918 (2.3844)  weight_decay: 0.0500 (0.0500)  time: 1.0062  data: 0.0010  max mem: 78493
Epoch: [119]  [290/312]  eta: 0:00:23  lr: 0.002869  min_lr: 0.002869  loss: 2.3093 (2.3860)  weight_decay: 0.0500 (0.0500)  time: 1.0045  data: 0.0009  max mem: 78493
Epoch: [119]  [300/312]  eta: 0:00:12  lr: 0.002869  min_lr: 0.002869  loss: 2.4739 (2.3875)  weight_decay: 0.0500 (0.0500)  time: 1.0018  data: 0.0001  max mem: 78493
Epoch: [119]  [310/312]  eta: 0:00:02  lr: 0.002868  min_lr: 0.002868  loss: 2.3515 (2.3835)  weight_decay: 0.0500 (0.0500)  time: 1.0018  data: 0.0001  max mem: 78493
Epoch: [119]  [311/312]  eta: 0:00:01  lr: 0.002868  min_lr: 0.002868  loss: 2.3515 (2.3854)  weight_decay: 0.0500 (0.0500)  time: 1.0018  data: 0.0001  max mem: 78493
Epoch: [119] Total time: 0:05:32 (1.0655 s / it)
Averaged stats: lr: 0.002868  min_lr: 0.002868  loss: 2.3515 (2.3724)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:18  loss: 0.6911 (0.6911)  acc1: 81.9010 (81.9010)  acc5: 95.3125 (95.3125)  time: 8.6722  data: 8.4051  max mem: 78493
Test:  [8/9]  eta: 0:00:01  loss: 1.0867 (0.9690)  acc1: 72.5260 (74.6720)  acc5: 92.0573 (92.6880)  time: 1.1635  data: 0.9340  max mem: 78493
Test: Total time: 0:00:10 (1.1849 s / it)
* Acc@1 75.292 Acc@5 92.700 loss 0.951
Accuracy of the model on the 50000 test images: 75.3%
Max accuracy: 75.39%
Epoch: [120]  [  0/312]  eta: 1:22:56  lr: 0.002868  min_lr: 0.002868  loss: 2.7101 (2.7101)  weight_decay: 0.0500 (0.0500)  time: 15.9499  data: 12.0940  max mem: 78493
Epoch: [120]  [ 10/312]  eta: 0:13:58  lr: 0.002867  min_lr: 0.002867  loss: 2.3870 (2.3173)  weight_decay: 0.0500 (0.0500)  time: 2.7749  data: 1.2694  max mem: 78493
Epoch: [120]  [ 20/312]  eta: 0:09:24  lr: 0.002867  min_lr: 0.002867  loss: 2.3522 (2.3014)  weight_decay: 0.0500 (0.0500)  time: 1.2338  data: 0.0937  max mem: 78493
Epoch: [120]  [ 30/312]  eta: 0:07:41  lr: 0.002866  min_lr: 0.002866  loss: 2.3701 (2.2903)  weight_decay: 0.0500 (0.0500)  time: 1.0085  data: 0.0014  max mem: 78493
Epoch: [120]  [ 40/312]  eta: 0:06:43  lr: 0.002865  min_lr: 0.002865  loss: 2.3467 (2.3027)  weight_decay: 0.0500 (0.0500)  time: 1.0070  data: 0.0014  max mem: 78493
Epoch: [120]  [ 50/312]  eta: 0:06:04  lr: 0.002865  min_lr: 0.002865  loss: 2.3408 (2.3037)  weight_decay: 0.0500 (0.0500)  time: 1.0097  data: 0.0005  max mem: 78493
Epoch: [120]  [ 60/312]  eta: 0:05:34  lr: 0.002864  min_lr: 0.002864  loss: 2.2636 (2.2913)  weight_decay: 0.0500 (0.0500)  time: 1.0091  data: 0.0004  max mem: 78493
Epoch: [120]  [ 70/312]  eta: 0:05:10  lr: 0.002864  min_lr: 0.002864  loss: 2.3367 (2.3040)  weight_decay: 0.0500 (0.0500)  time: 1.0076  data: 0.0004  max mem: 78493
Epoch: [120]  [ 80/312]  eta: 0:04:49  lr: 0.002863  min_lr: 0.002863  loss: 2.3120 (2.3026)  weight_decay: 0.0500 (0.0500)  time: 1.0083  data: 0.0004  max mem: 78493
Epoch: [120]  [ 90/312]  eta: 0:04:31  lr: 0.002862  min_lr: 0.002862  loss: 2.2678 (2.3059)  weight_decay: 0.0500 (0.0500)  time: 1.0070  data: 0.0004  max mem: 78493
Epoch: [120]  [100/312]  eta: 0:04:14  lr: 0.002862  min_lr: 0.002862  loss: 2.3884 (2.3110)  weight_decay: 0.0500 (0.0500)  time: 1.0072  data: 0.0004  max mem: 78493
Epoch: [120]  [110/312]  eta: 0:03:58  lr: 0.002861  min_lr: 0.002861  loss: 2.4598 (2.3140)  weight_decay: 0.0500 (0.0500)  time: 1.0061  data: 0.0004  max mem: 78493
Epoch: [120]  [120/312]  eta: 0:03:44  lr: 0.002860  min_lr: 0.002860  loss: 2.4054 (2.3174)  weight_decay: 0.0500 (0.0500)  time: 1.0042  data: 0.0004  max mem: 78493
Epoch: [120]  [130/312]  eta: 0:03:30  lr: 0.002860  min_lr: 0.002860  loss: 2.4054 (2.3175)  weight_decay: 0.0500 (0.0500)  time: 1.0056  data: 0.0004  max mem: 78493
Epoch: [120]  [140/312]  eta: 0:03:16  lr: 0.002859  min_lr: 0.002859  loss: 2.4542 (2.3280)  weight_decay: 0.0500 (0.0500)  time: 1.0069  data: 0.0004  max mem: 78493
Epoch: [120]  [150/312]  eta: 0:03:04  lr: 0.002858  min_lr: 0.002858  loss: 2.4831 (2.3367)  weight_decay: 0.0500 (0.0500)  time: 1.0062  data: 0.0004  max mem: 78493
Epoch: [120]  [160/312]  eta: 0:02:51  lr: 0.002858  min_lr: 0.002858  loss: 2.4784 (2.3239)  weight_decay: 0.0500 (0.0500)  time: 1.0053  data: 0.0004  max mem: 78493
Epoch: [120]  [170/312]  eta: 0:02:39  lr: 0.002857  min_lr: 0.002857  loss: 2.4420 (2.3318)  weight_decay: 0.0500 (0.0500)  time: 1.0056  data: 0.0004  max mem: 78493
Epoch: [120]  [180/312]  eta: 0:02:27  lr: 0.002856  min_lr: 0.002856  loss: 2.4420 (2.3290)  weight_decay: 0.0500 (0.0500)  time: 1.0064  data: 0.0004  max mem: 78493
Epoch: [120]  [190/312]  eta: 0:02:15  lr: 0.002856  min_lr: 0.002856  loss: 2.3048 (2.3295)  weight_decay: 0.0500 (0.0500)  time: 1.0076  data: 0.0004  max mem: 78493
Epoch: [120]  [200/312]  eta: 0:02:03  lr: 0.002855  min_lr: 0.002855  loss: 2.5738 (2.3423)  weight_decay: 0.0500 (0.0500)  time: 1.0066  data: 0.0004  max mem: 78493
Epoch: [120]  [210/312]  eta: 0:01:52  lr: 0.002854  min_lr: 0.002854  loss: 2.6004 (2.3514)  weight_decay: 0.0500 (0.0500)  time: 1.0051  data: 0.0004  max mem: 78493
Epoch: [120]  [220/312]  eta: 0:01:40  lr: 0.002854  min_lr: 0.002854  loss: 2.5315 (2.3534)  weight_decay: 0.0500 (0.0500)  time: 1.0056  data: 0.0004  max mem: 78493
Epoch: [120]  [230/312]  eta: 0:01:29  lr: 0.002853  min_lr: 0.002853  loss: 2.3752 (2.3537)  weight_decay: 0.0500 (0.0500)  time: 1.0062  data: 0.0004  max mem: 78493
Epoch: [120]  [240/312]  eta: 0:01:18  lr: 0.002852  min_lr: 0.002852  loss: 2.2882 (2.3481)  weight_decay: 0.0500 (0.0500)  time: 1.0049  data: 0.0005  max mem: 78493
Epoch: [120]  [250/312]  eta: 0:01:07  lr: 0.002852  min_lr: 0.002852  loss: 2.3471 (2.3549)  weight_decay: 0.0500 (0.0500)  time: 1.0043  data: 0.0004  max mem: 78493
Epoch: [120]  [260/312]  eta: 0:00:56  lr: 0.002851  min_lr: 0.002851  loss: 2.4970 (2.3581)  weight_decay: 0.0500 (0.0500)  time: 1.0058  data: 0.0004  max mem: 78493
Epoch: [120]  [270/312]  eta: 0:00:45  lr: 0.002851  min_lr: 0.002851  loss: 2.4970 (2.3575)  weight_decay: 0.0500 (0.0500)  time: 1.0072  data: 0.0004  max mem: 78493
Epoch: [120]  [280/312]  eta: 0:00:34  lr: 0.002850  min_lr: 0.002850  loss: 2.5627 (2.3636)  weight_decay: 0.0500 (0.0500)  time: 1.0085  data: 0.0010  max mem: 78493
Epoch: [120]  [290/312]  eta: 0:00:23  lr: 0.002849  min_lr: 0.002849  loss: 2.5627 (2.3659)  weight_decay: 0.0500 (0.0500)  time: 1.0057  data: 0.0009  max mem: 78493
Epoch: [120]  [300/312]  eta: 0:00:12  lr: 0.002849  min_lr: 0.002849  loss: 2.4679 (2.3639)  weight_decay: 0.0500 (0.0500)  time: 1.0023  data: 0.0001  max mem: 78493
Epoch: [120]  [310/312]  eta: 0:00:02  lr: 0.002848  min_lr: 0.002848  loss: 2.1376 (2.3520)  weight_decay: 0.0500 (0.0500)  time: 1.0021  data: 0.0001  max mem: 78493
Epoch: [120]  [311/312]  eta: 0:00:01  lr: 0.002848  min_lr: 0.002848  loss: 2.0019 (2.3496)  weight_decay: 0.0500 (0.0500)  time: 1.0022  data: 0.0001  max mem: 78493
Epoch: [120] Total time: 0:05:35 (1.0742 s / it)
Averaged stats: lr: 0.002848  min_lr: 0.002848  loss: 2.0019 (2.3646)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:11  loss: 0.7702 (0.7702)  acc1: 80.8594 (80.8594)  acc5: 94.4010 (94.4010)  time: 7.9913  data: 7.7171  max mem: 78493
Test:  [8/9]  eta: 0:00:01  loss: 1.0626 (0.9880)  acc1: 74.8698 (74.8640)  acc5: 93.0990 (92.4000)  time: 1.0920  data: 0.8617  max mem: 78493
Test: Total time: 0:00:09 (1.1060 s / it)
* Acc@1 75.208 Acc@5 92.436 loss 0.975
Accuracy of the model on the 50000 test images: 75.2%
Max accuracy: 75.39%
Epoch: [121]  [  0/312]  eta: 1:26:34  lr: 0.002848  min_lr: 0.002848  loss: 2.0917 (2.0917)  weight_decay: 0.0500 (0.0500)  time: 16.6488  data: 14.5501  max mem: 78493
Epoch: [121]  [ 10/312]  eta: 0:13:13  lr: 0.002847  min_lr: 0.002847  loss: 2.5157 (2.3874)  weight_decay: 0.0500 (0.0500)  time: 2.6287  data: 1.3234  max mem: 78493
Epoch: [121]  [ 20/312]  eta: 0:09:02  lr: 0.002846  min_lr: 0.002846  loss: 2.5157 (2.3777)  weight_decay: 0.0500 (0.0500)  time: 1.1199  data: 0.0007  max mem: 78493
Epoch: [121]  [ 30/312]  eta: 0:07:26  lr: 0.002846  min_lr: 0.002846  loss: 2.2482 (2.3661)  weight_decay: 0.0500 (0.0500)  time: 1.0102  data: 0.0005  max mem: 78493
Epoch: [121]  [ 40/312]  eta: 0:06:32  lr: 0.002845  min_lr: 0.002845  loss: 2.2991 (2.3525)  weight_decay: 0.0500 (0.0500)  time: 1.0061  data: 0.0004  max mem: 78493
Epoch: [121]  [ 50/312]  eta: 0:05:55  lr: 0.002845  min_lr: 0.002845  loss: 2.3321 (2.3808)  weight_decay: 0.0500 (0.0500)  time: 1.0043  data: 0.0004  max mem: 78493
Epoch: [121]  [ 60/312]  eta: 0:05:27  lr: 0.002844  min_lr: 0.002844  loss: 2.3020 (2.3408)  weight_decay: 0.0500 (0.0500)  time: 1.0063  data: 0.0004  max mem: 78493
Epoch: [121]  [ 70/312]  eta: 0:05:04  lr: 0.002843  min_lr: 0.002843  loss: 2.2141 (2.3359)  weight_decay: 0.0500 (0.0500)  time: 1.0094  data: 0.0004  max mem: 78493
Epoch: [121]  [ 80/312]  eta: 0:04:44  lr: 0.002843  min_lr: 0.002843  loss: 2.2613 (2.3252)  weight_decay: 0.0500 (0.0500)  time: 1.0102  data: 0.0004  max mem: 78493
Epoch: [121]  [ 90/312]  eta: 0:04:27  lr: 0.002842  min_lr: 0.002842  loss: 2.2366 (2.3177)  weight_decay: 0.0500 (0.0500)  time: 1.0086  data: 0.0004  max mem: 78493
Epoch: [121]  [100/312]  eta: 0:04:11  lr: 0.002841  min_lr: 0.002841  loss: 2.4392 (2.3376)  weight_decay: 0.0500 (0.0500)  time: 1.0075  data: 0.0005  max mem: 78493
Epoch: [121]  [110/312]  eta: 0:03:56  lr: 0.002841  min_lr: 0.002841  loss: 2.4721 (2.3418)  weight_decay: 0.0500 (0.0500)  time: 1.0087  data: 0.0004  max mem: 78493
Epoch: [121]  [120/312]  eta: 0:03:41  lr: 0.002840  min_lr: 0.002840  loss: 2.4573 (2.3462)  weight_decay: 0.0500 (0.0500)  time: 1.0100  data: 0.0004  max mem: 78493
Epoch: [121]  [130/312]  eta: 0:03:28  lr: 0.002839  min_lr: 0.002839  loss: 2.6164 (2.3676)  weight_decay: 0.0500 (0.0500)  time: 1.0074  data: 0.0005  max mem: 78493
Epoch: [121]  [140/312]  eta: 0:03:15  lr: 0.002839  min_lr: 0.002839  loss: 2.5731 (2.3679)  weight_decay: 0.0500 (0.0500)  time: 1.0052  data: 0.0005  max mem: 78493
Epoch: [121]  [150/312]  eta: 0:03:02  lr: 0.002838  min_lr: 0.002838  loss: 2.4801 (2.3609)  weight_decay: 0.0500 (0.0500)  time: 1.0076  data: 0.0004  max mem: 78493
Epoch: [121]  [160/312]  eta: 0:02:50  lr: 0.002837  min_lr: 0.002837  loss: 2.4543 (2.3593)  weight_decay: 0.0500 (0.0500)  time: 1.0078  data: 0.0004  max mem: 78493
Epoch: [121]  [170/312]  eta: 0:02:37  lr: 0.002837  min_lr: 0.002837  loss: 2.5058 (2.3638)  weight_decay: 0.0500 (0.0500)  time: 1.0077  data: 0.0004  max mem: 78493
Epoch: [121]  [180/312]  eta: 0:02:26  lr: 0.002836  min_lr: 0.002836  loss: 2.4698 (2.3656)  weight_decay: 0.0500 (0.0500)  time: 1.0093  data: 0.0004  max mem: 78493
Epoch: [121]  [190/312]  eta: 0:02:14  lr: 0.002835  min_lr: 0.002835  loss: 2.4065 (2.3622)  weight_decay: 0.0500 (0.0500)  time: 1.0084  data: 0.0005  max mem: 78493
Epoch: [121]  [200/312]  eta: 0:02:02  lr: 0.002835  min_lr: 0.002835  loss: 2.0763 (2.3477)  weight_decay: 0.0500 (0.0500)  time: 1.0079  data: 0.0005  max mem: 78493
Epoch: [121]  [210/312]  eta: 0:01:51  lr: 0.002834  min_lr: 0.002834  loss: 2.3676 (2.3579)  weight_decay: 0.0500 (0.0500)  time: 1.0068  data: 0.0005  max mem: 78493
Epoch: [121]  [220/312]  eta: 0:01:40  lr: 0.002833  min_lr: 0.002833  loss: 2.4458 (2.3517)  weight_decay: 0.0500 (0.0500)  time: 1.0041  data: 0.0004  max mem: 78493
Epoch: [121]  [230/312]  eta: 0:01:28  lr: 0.002833  min_lr: 0.002833  loss: 2.1537 (2.3489)  weight_decay: 0.0500 (0.0500)  time: 1.0040  data: 0.0004  max mem: 78493
Epoch: [121]  [240/312]  eta: 0:01:17  lr: 0.002832  min_lr: 0.002832  loss: 2.4060 (2.3493)  weight_decay: 0.0500 (0.0500)  time: 1.0038  data: 0.0004  max mem: 78493
Epoch: [121]  [250/312]  eta: 0:01:06  lr: 0.002831  min_lr: 0.002831  loss: 2.4530 (2.3529)  weight_decay: 0.0500 (0.0500)  time: 1.0036  data: 0.0004  max mem: 78493
Epoch: [121]  [260/312]  eta: 0:00:55  lr: 0.002831  min_lr: 0.002831  loss: 2.2999 (2.3447)  weight_decay: 0.0500 (0.0500)  time: 1.0051  data: 0.0004  max mem: 78493
Epoch: [121]  [270/312]  eta: 0:00:45  lr: 0.002830  min_lr: 0.002830  loss: 2.3936 (2.3486)  weight_decay: 0.0500 (0.0500)  time: 1.0058  data: 0.0004  max mem: 78493
Epoch: [121]  [280/312]  eta: 0:00:34  lr: 0.002830  min_lr: 0.002830  loss: 2.4238 (2.3435)  weight_decay: 0.0500 (0.0500)  time: 1.0056  data: 0.0011  max mem: 78493
Epoch: [121]  [290/312]  eta: 0:00:23  lr: 0.002829  min_lr: 0.002829  loss: 2.3094 (2.3430)  weight_decay: 0.0500 (0.0500)  time: 1.0039  data: 0.0009  max mem: 78493
Epoch: [121]  [300/312]  eta: 0:00:12  lr: 0.002828  min_lr: 0.002828  loss: 2.3094 (2.3410)  weight_decay: 0.0500 (0.0500)  time: 1.0015  data: 0.0001  max mem: 78493
Epoch: [121]  [310/312]  eta: 0:00:02  lr: 0.002828  min_lr: 0.002828  loss: 2.2799 (2.3415)  weight_decay: 0.0500 (0.0500)  time: 1.0014  data: 0.0001  max mem: 78493
Epoch: [121]  [311/312]  eta: 0:00:01  lr: 0.002827  min_lr: 0.002827  loss: 2.3357 (2.3415)  weight_decay: 0.0500 (0.0500)  time: 1.0014  data: 0.0001  max mem: 78493
Epoch: [121] Total time: 0:05:33 (1.0695 s / it)
Averaged stats: lr: 0.002827  min_lr: 0.002827  loss: 2.3357 (2.3463)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:10  loss: 0.7036 (0.7036)  acc1: 80.5990 (80.5990)  acc5: 94.6615 (94.6615)  time: 7.7921  data: 7.5304  max mem: 78493
Test:  [8/9]  eta: 0:00:01  loss: 1.0631 (0.9706)  acc1: 75.2604 (74.7520)  acc5: 92.7083 (92.6240)  time: 1.0644  data: 0.8368  max mem: 78493
Test: Total time: 0:00:09 (1.0740 s / it)
* Acc@1 75.240 Acc@5 92.582 loss 0.967
Accuracy of the model on the 50000 test images: 75.2%
Max accuracy: 75.39%
Epoch: [122]  [  0/312]  eta: 1:25:59  lr: 0.002827  min_lr: 0.002827  loss: 2.6325 (2.6325)  weight_decay: 0.0500 (0.0500)  time: 16.5381  data: 15.2438  max mem: 78493
Epoch: [122]  [ 10/312]  eta: 0:13:12  lr: 0.002827  min_lr: 0.002827  loss: 2.5027 (2.2549)  weight_decay: 0.0500 (0.0500)  time: 2.6257  data: 1.3865  max mem: 78493
Epoch: [122]  [ 20/312]  eta: 0:09:02  lr: 0.002826  min_lr: 0.002826  loss: 2.2235 (2.2319)  weight_decay: 0.0500 (0.0500)  time: 1.1243  data: 0.0006  max mem: 78493
Epoch: [122]  [ 30/312]  eta: 0:07:26  lr: 0.002825  min_lr: 0.002825  loss: 2.2506 (2.2887)  weight_decay: 0.0500 (0.0500)  time: 1.0097  data: 0.0005  max mem: 78493
Epoch: [122]  [ 40/312]  eta: 0:06:32  lr: 0.002825  min_lr: 0.002825  loss: 2.5759 (2.3619)  weight_decay: 0.0500 (0.0500)  time: 1.0061  data: 0.0005  max mem: 78493
Epoch: [122]  [ 50/312]  eta: 0:05:55  lr: 0.002824  min_lr: 0.002824  loss: 2.5010 (2.3633)  weight_decay: 0.0500 (0.0500)  time: 1.0070  data: 0.0004  max mem: 78493
Epoch: [122]  [ 60/312]  eta: 0:05:27  lr: 0.002823  min_lr: 0.002823  loss: 2.5025 (2.3782)  weight_decay: 0.0500 (0.0500)  time: 1.0075  data: 0.0004  max mem: 78493
Epoch: [122]  [ 70/312]  eta: 0:05:04  lr: 0.002823  min_lr: 0.002823  loss: 2.5535 (2.3744)  weight_decay: 0.0500 (0.0500)  time: 1.0082  data: 0.0004  max mem: 78493
Epoch: [122]  [ 80/312]  eta: 0:04:44  lr: 0.002822  min_lr: 0.002822  loss: 2.4536 (2.3809)  weight_decay: 0.0500 (0.0500)  time: 1.0089  data: 0.0005  max mem: 78493
Epoch: [122]  [ 90/312]  eta: 0:04:27  lr: 0.002822  min_lr: 0.002822  loss: 2.5281 (2.4001)  weight_decay: 0.0500 (0.0500)  time: 1.0077  data: 0.0005  max mem: 78493
Epoch: [122]  [100/312]  eta: 0:04:11  lr: 0.002821  min_lr: 0.002821  loss: 2.4945 (2.4025)  weight_decay: 0.0500 (0.0500)  time: 1.0078  data: 0.0004  max mem: 78493
Epoch: [122]  [110/312]  eta: 0:03:56  lr: 0.002820  min_lr: 0.002820  loss: 2.3743 (2.4000)  weight_decay: 0.0500 (0.0500)  time: 1.0086  data: 0.0018  max mem: 78493
Epoch: [122]  [120/312]  eta: 0:03:41  lr: 0.002820  min_lr: 0.002820  loss: 2.3481 (2.3824)  weight_decay: 0.0500 (0.0500)  time: 1.0072  data: 0.0018  max mem: 78493
Epoch: [122]  [130/312]  eta: 0:03:28  lr: 0.002819  min_lr: 0.002819  loss: 2.3481 (2.3793)  weight_decay: 0.0500 (0.0500)  time: 1.0068  data: 0.0004  max mem: 78493
Epoch: [122]  [140/312]  eta: 0:03:15  lr: 0.002818  min_lr: 0.002818  loss: 2.4414 (2.3797)  weight_decay: 0.0500 (0.0500)  time: 1.0079  data: 0.0004  max mem: 78493
Epoch: [122]  [150/312]  eta: 0:03:02  lr: 0.002818  min_lr: 0.002818  loss: 2.4472 (2.3898)  weight_decay: 0.0500 (0.0500)  time: 1.0087  data: 0.0004  max mem: 78493
Epoch: [122]  [160/312]  eta: 0:02:50  lr: 0.002817  min_lr: 0.002817  loss: 2.4360 (2.3805)  weight_decay: 0.0500 (0.0500)  time: 1.0087  data: 0.0005  max mem: 78493
Epoch: [122]  [170/312]  eta: 0:02:37  lr: 0.002816  min_lr: 0.002816  loss: 2.4696 (2.3880)  weight_decay: 0.0500 (0.0500)  time: 1.0088  data: 0.0004  max mem: 78493
Epoch: [122]  [180/312]  eta: 0:02:26  lr: 0.002816  min_lr: 0.002816  loss: 2.5106 (2.3868)  weight_decay: 0.0500 (0.0500)  time: 1.0085  data: 0.0004  max mem: 78493
Epoch: [122]  [190/312]  eta: 0:02:14  lr: 0.002815  min_lr: 0.002815  loss: 2.4031 (2.3881)  weight_decay: 0.0500 (0.0500)  time: 1.0082  data: 0.0004  max mem: 78493
Epoch: [122]  [200/312]  eta: 0:02:02  lr: 0.002814  min_lr: 0.002814  loss: 2.3999 (2.3888)  weight_decay: 0.0500 (0.0500)  time: 1.0067  data: 0.0005  max mem: 78493
Epoch: [122]  [210/312]  eta: 0:01:51  lr: 0.002814  min_lr: 0.002814  loss: 2.5127 (2.3928)  weight_decay: 0.0500 (0.0500)  time: 1.0075  data: 0.0005  max mem: 78493
Epoch: [122]  [220/312]  eta: 0:01:40  lr: 0.002813  min_lr: 0.002813  loss: 2.4571 (2.3915)  weight_decay: 0.0500 (0.0500)  time: 1.0079  data: 0.0004  max mem: 78493
Epoch: [122]  [230/312]  eta: 0:01:28  lr: 0.002812  min_lr: 0.002812  loss: 2.2452 (2.3864)  weight_decay: 0.0500 (0.0500)  time: 1.0058  data: 0.0004  max mem: 78493
Epoch: [122]  [240/312]  eta: 0:01:17  lr: 0.002812  min_lr: 0.002812  loss: 2.1621 (2.3807)  weight_decay: 0.0500 (0.0500)  time: 1.0045  data: 0.0005  max mem: 78493
Epoch: [122]  [250/312]  eta: 0:01:06  lr: 0.002811  min_lr: 0.002811  loss: 2.2158 (2.3754)  weight_decay: 0.0500 (0.0500)  time: 1.0058  data: 0.0005  max mem: 78493
Epoch: [122]  [260/312]  eta: 0:00:55  lr: 0.002810  min_lr: 0.002810  loss: 2.3290 (2.3696)  weight_decay: 0.0500 (0.0500)  time: 1.0070  data: 0.0005  max mem: 78493
Epoch: [122]  [270/312]  eta: 0:00:45  lr: 0.002810  min_lr: 0.002810  loss: 2.2499 (2.3657)  weight_decay: 0.0500 (0.0500)  time: 1.0057  data: 0.0005  max mem: 78493
Epoch: [122]  [280/312]  eta: 0:00:34  lr: 0.002809  min_lr: 0.002809  loss: 2.2499 (2.3630)  weight_decay: 0.0500 (0.0500)  time: 1.0053  data: 0.0010  max mem: 78493
Epoch: [122]  [290/312]  eta: 0:00:23  lr: 0.002808  min_lr: 0.002808  loss: 2.3736 (2.3629)  weight_decay: 0.0500 (0.0500)  time: 1.0034  data: 0.0009  max mem: 78493
Epoch: [122]  [300/312]  eta: 0:00:12  lr: 0.002808  min_lr: 0.002808  loss: 2.3328 (2.3629)  weight_decay: 0.0500 (0.0500)  time: 1.0016  data: 0.0001  max mem: 78493
Epoch: [122]  [310/312]  eta: 0:00:02  lr: 0.002807  min_lr: 0.002807  loss: 2.3831 (2.3637)  weight_decay: 0.0500 (0.0500)  time: 1.0019  data: 0.0001  max mem: 78493
Epoch: [122]  [311/312]  eta: 0:00:01  lr: 0.002807  min_lr: 0.002807  loss: 2.3328 (2.3618)  weight_decay: 0.0500 (0.0500)  time: 1.0019  data: 0.0001  max mem: 78493
Epoch: [122] Total time: 0:05:33 (1.0694 s / it)
Averaged stats: lr: 0.002807  min_lr: 0.002807  loss: 2.3328 (2.3749)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:10  loss: 0.7108 (0.7108)  acc1: 82.1615 (82.1615)  acc5: 95.1823 (95.1823)  time: 7.8662  data: 7.5966  max mem: 78493
Test:  [8/9]  eta: 0:00:01  loss: 1.0428 (0.9824)  acc1: 74.6094 (74.5280)  acc5: 92.1875 (92.3840)  time: 1.0742  data: 0.8442  max mem: 78493
Test: Total time: 0:00:10 (1.1216 s / it)
* Acc@1 74.852 Acc@5 92.360 loss 0.977
Accuracy of the model on the 50000 test images: 74.9%
Max accuracy: 75.39%
Epoch: [123]  [  0/312]  eta: 1:28:58  lr: 0.002807  min_lr: 0.002807  loss: 2.0514 (2.0514)  weight_decay: 0.0500 (0.0500)  time: 17.1092  data: 12.1540  max mem: 78493
Epoch: [123]  [ 10/312]  eta: 0:13:31  lr: 0.002806  min_lr: 0.002806  loss: 2.4941 (2.2912)  weight_decay: 0.0500 (0.0500)  time: 2.6866  data: 1.1316  max mem: 78493
Epoch: [123]  [ 20/312]  eta: 0:09:12  lr: 0.002806  min_lr: 0.002806  loss: 2.5233 (2.3675)  weight_decay: 0.0500 (0.0500)  time: 1.1295  data: 0.0149  max mem: 78493
Epoch: [123]  [ 30/312]  eta: 0:07:32  lr: 0.002805  min_lr: 0.002805  loss: 2.4584 (2.2992)  weight_decay: 0.0500 (0.0500)  time: 1.0114  data: 0.0004  max mem: 78493
Epoch: [123]  [ 40/312]  eta: 0:06:36  lr: 0.002804  min_lr: 0.002804  loss: 2.1622 (2.2845)  weight_decay: 0.0500 (0.0500)  time: 1.0068  data: 0.0004  max mem: 78493
Epoch: [123]  [ 50/312]  eta: 0:05:59  lr: 0.002804  min_lr: 0.002804  loss: 2.3733 (2.3240)  weight_decay: 0.0500 (0.0500)  time: 1.0055  data: 0.0004  max mem: 78493
Epoch: [123]  [ 60/312]  eta: 0:05:30  lr: 0.002803  min_lr: 0.002803  loss: 2.6389 (2.3496)  weight_decay: 0.0500 (0.0500)  time: 1.0063  data: 0.0005  max mem: 78493
Epoch: [123]  [ 70/312]  eta: 0:05:06  lr: 0.002802  min_lr: 0.002802  loss: 2.4237 (2.3298)  weight_decay: 0.0500 (0.0500)  time: 1.0075  data: 0.0005  max mem: 78493
Epoch: [123]  [ 80/312]  eta: 0:04:46  lr: 0.002802  min_lr: 0.002802  loss: 2.2089 (2.3256)  weight_decay: 0.0500 (0.0500)  time: 1.0071  data: 0.0004  max mem: 78493
Epoch: [123]  [ 90/312]  eta: 0:04:28  lr: 0.002801  min_lr: 0.002801  loss: 2.2800 (2.3270)  weight_decay: 0.0500 (0.0500)  time: 1.0064  data: 0.0004  max mem: 78493
Epoch: [123]  [100/312]  eta: 0:04:12  lr: 0.002800  min_lr: 0.002800  loss: 2.3712 (2.3372)  weight_decay: 0.0500 (0.0500)  time: 1.0090  data: 0.0004  max mem: 78493
Epoch: [123]  [110/312]  eta: 0:03:57  lr: 0.002800  min_lr: 0.002800  loss: 2.3588 (2.3292)  weight_decay: 0.0500 (0.0500)  time: 1.0086  data: 0.0004  max mem: 78493
Epoch: [123]  [120/312]  eta: 0:03:42  lr: 0.002799  min_lr: 0.002799  loss: 2.1246 (2.3253)  weight_decay: 0.0500 (0.0500)  time: 1.0068  data: 0.0012  max mem: 78493
Epoch: [123]  [130/312]  eta: 0:03:29  lr: 0.002798  min_lr: 0.002798  loss: 2.5040 (2.3400)  weight_decay: 0.0500 (0.0500)  time: 1.0078  data: 0.0012  max mem: 78493
Epoch: [123]  [140/312]  eta: 0:03:15  lr: 0.002798  min_lr: 0.002798  loss: 2.5456 (2.3518)  weight_decay: 0.0500 (0.0500)  time: 1.0063  data: 0.0005  max mem: 78493
Epoch: [123]  [150/312]  eta: 0:03:03  lr: 0.002797  min_lr: 0.002797  loss: 2.4989 (2.3536)  weight_decay: 0.0500 (0.0500)  time: 1.0077  data: 0.0014  max mem: 78493
Epoch: [123]  [160/312]  eta: 0:02:50  lr: 0.002796  min_lr: 0.002796  loss: 2.3673 (2.3479)  weight_decay: 0.0500 (0.0500)  time: 1.0100  data: 0.0014  max mem: 78493
Epoch: [123]  [170/312]  eta: 0:02:38  lr: 0.002796  min_lr: 0.002796  loss: 2.0602 (2.3427)  weight_decay: 0.0500 (0.0500)  time: 1.0072  data: 0.0005  max mem: 78493
Epoch: [123]  [180/312]  eta: 0:02:26  lr: 0.002795  min_lr: 0.002795  loss: 2.2731 (2.3414)  weight_decay: 0.0500 (0.0500)  time: 1.0060  data: 0.0004  max mem: 78493
Epoch: [123]  [190/312]  eta: 0:02:14  lr: 0.002794  min_lr: 0.002794  loss: 2.3155 (2.3389)  weight_decay: 0.0500 (0.0500)  time: 1.0069  data: 0.0004  max mem: 78493
Epoch: [123]  [200/312]  eta: 0:02:03  lr: 0.002794  min_lr: 0.002794  loss: 2.4858 (2.3428)  weight_decay: 0.0500 (0.0500)  time: 1.0087  data: 0.0004  max mem: 78493
Epoch: [123]  [210/312]  eta: 0:01:51  lr: 0.002793  min_lr: 0.002793  loss: 2.4888 (2.3389)  weight_decay: 0.0500 (0.0500)  time: 1.0082  data: 0.0004  max mem: 78493
Epoch: [123]  [220/312]  eta: 0:01:40  lr: 0.002792  min_lr: 0.002792  loss: 2.3419 (2.3364)  weight_decay: 0.0500 (0.0500)  time: 1.0089  data: 0.0004  max mem: 78493
Epoch: [123]  [230/312]  eta: 0:01:29  lr: 0.002792  min_lr: 0.002792  loss: 2.4090 (2.3378)  weight_decay: 0.0500 (0.0500)  time: 1.0097  data: 0.0004  max mem: 78493
Epoch: [123]  [240/312]  eta: 0:01:18  lr: 0.002791  min_lr: 0.002791  loss: 2.5105 (2.3386)  weight_decay: 0.0500 (0.0500)  time: 1.0067  data: 0.0005  max mem: 78493
Epoch: [123]  [250/312]  eta: 0:01:07  lr: 0.002790  min_lr: 0.002790  loss: 2.4658 (2.3407)  weight_decay: 0.0500 (0.0500)  time: 1.0068  data: 0.0004  max mem: 78493
Epoch: [123]  [260/312]  eta: 0:00:56  lr: 0.002790  min_lr: 0.002790  loss: 2.4658 (2.3420)  weight_decay: 0.0500 (0.0500)  time: 1.0061  data: 0.0004  max mem: 78493
Epoch: [123]  [270/312]  eta: 0:00:45  lr: 0.002789  min_lr: 0.002789  loss: 2.3705 (2.3391)  weight_decay: 0.0500 (0.0500)  time: 1.0049  data: 0.0004  max mem: 78493
Epoch: [123]  [280/312]  eta: 0:00:34  lr: 0.002788  min_lr: 0.002788  loss: 2.3412 (2.3399)  weight_decay: 0.0500 (0.0500)  time: 1.0075  data: 0.0011  max mem: 78493
Epoch: [123]  [290/312]  eta: 0:00:23  lr: 0.002788  min_lr: 0.002788  loss: 2.2359 (2.3371)  weight_decay: 0.0500 (0.0500)  time: 1.0058  data: 0.0009  max mem: 78493
Epoch: [123]  [300/312]  eta: 0:00:12  lr: 0.002787  min_lr: 0.002787  loss: 2.4666 (2.3387)  weight_decay: 0.0500 (0.0500)  time: 1.0017  data: 0.0001  max mem: 78493
Epoch: [123]  [310/312]  eta: 0:00:02  lr: 0.002786  min_lr: 0.002786  loss: 2.3208 (2.3386)  weight_decay: 0.0500 (0.0500)  time: 1.0017  data: 0.0001  max mem: 78493
Epoch: [123]  [311/312]  eta: 0:00:01  lr: 0.002786  min_lr: 0.002786  loss: 2.3704 (2.3393)  weight_decay: 0.0500 (0.0500)  time: 1.0017  data: 0.0001  max mem: 78493
Epoch: [123] Total time: 0:05:34 (1.0719 s / it)
Averaged stats: lr: 0.002786  min_lr: 0.002786  loss: 2.3704 (2.3553)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:17  loss: 0.6833 (0.6833)  acc1: 83.3333 (83.3333)  acc5: 96.4844 (96.4844)  time: 8.6112  data: 8.3464  max mem: 78493
Test:  [8/9]  eta: 0:00:01  loss: 1.1460 (0.9877)  acc1: 71.8750 (74.8000)  acc5: 90.6250 (92.4640)  time: 1.1579  data: 0.9275  max mem: 78493
Test: Total time: 0:00:10 (1.1974 s / it)
* Acc@1 75.082 Acc@5 92.406 loss 0.978
Accuracy of the model on the 50000 test images: 75.1%
Max accuracy: 75.39%
Epoch: [124]  [  0/312]  eta: 1:30:27  lr: 0.002786  min_lr: 0.002786  loss: 1.7019 (1.7019)  weight_decay: 0.0500 (0.0500)  time: 17.3952  data: 11.9816  max mem: 78493
Epoch: [124]  [ 10/312]  eta: 0:13:27  lr: 0.002786  min_lr: 0.002786  loss: 2.2829 (2.3362)  weight_decay: 0.0500 (0.0500)  time: 2.6745  data: 1.1217  max mem: 78493
Epoch: [124]  [ 20/312]  eta: 0:09:12  lr: 0.002785  min_lr: 0.002785  loss: 2.2829 (2.3434)  weight_decay: 0.0500 (0.0500)  time: 1.1183  data: 0.0182  max mem: 78493
Epoch: [124]  [ 30/312]  eta: 0:07:33  lr: 0.002784  min_lr: 0.002784  loss: 2.5152 (2.3570)  weight_decay: 0.0500 (0.0500)  time: 1.0224  data: 0.0005  max mem: 78493
Epoch: [124]  [ 40/312]  eta: 0:06:37  lr: 0.002784  min_lr: 0.002784  loss: 2.5320 (2.3336)  weight_decay: 0.0500 (0.0500)  time: 1.0100  data: 0.0005  max mem: 78493
Epoch: [124]  [ 50/312]  eta: 0:05:59  lr: 0.002783  min_lr: 0.002783  loss: 2.5735 (2.3899)  weight_decay: 0.0500 (0.0500)  time: 1.0100  data: 0.0005  max mem: 78493
Epoch: [124]  [ 60/312]  eta: 0:05:31  lr: 0.002782  min_lr: 0.002782  loss: 2.4634 (2.3826)  weight_decay: 0.0500 (0.0500)  time: 1.0085  data: 0.0015  max mem: 78493
Epoch: [124]  [ 70/312]  eta: 0:05:07  lr: 0.002782  min_lr: 0.002782  loss: 2.3960 (2.3705)  weight_decay: 0.0500 (0.0500)  time: 1.0097  data: 0.0015  max mem: 78493
Epoch: [124]  [ 80/312]  eta: 0:04:47  lr: 0.002781  min_lr: 0.002781  loss: 2.1922 (2.3417)  weight_decay: 0.0500 (0.0500)  time: 1.0108  data: 0.0005  max mem: 78493
Epoch: [124]  [ 90/312]  eta: 0:04:29  lr: 0.002780  min_lr: 0.002780  loss: 2.3402 (2.3440)  weight_decay: 0.0500 (0.0500)  time: 1.0082  data: 0.0004  max mem: 78493
Epoch: [124]  [100/312]  eta: 0:04:12  lr: 0.002780  min_lr: 0.002780  loss: 2.4575 (2.3401)  weight_decay: 0.0500 (0.0500)  time: 1.0087  data: 0.0004  max mem: 78493
Epoch: [124]  [110/312]  eta: 0:03:57  lr: 0.002779  min_lr: 0.002779  loss: 2.4807 (2.3506)  weight_decay: 0.0500 (0.0500)  time: 1.0089  data: 0.0004  max mem: 78493
Epoch: [124]  [120/312]  eta: 0:03:43  lr: 0.002778  min_lr: 0.002778  loss: 2.4791 (2.3455)  weight_decay: 0.0500 (0.0500)  time: 1.0078  data: 0.0004  max mem: 78493
Epoch: [124]  [130/312]  eta: 0:03:29  lr: 0.002778  min_lr: 0.002778  loss: 2.1698 (2.3278)  weight_decay: 0.0500 (0.0500)  time: 1.0089  data: 0.0004  max mem: 78493
Epoch: [124]  [140/312]  eta: 0:03:16  lr: 0.002777  min_lr: 0.002777  loss: 1.9843 (2.3106)  weight_decay: 0.0500 (0.0500)  time: 1.0115  data: 0.0004  max mem: 78493
Epoch: [124]  [150/312]  eta: 0:03:03  lr: 0.002776  min_lr: 0.002776  loss: 2.0201 (2.3079)  weight_decay: 0.0500 (0.0500)  time: 1.0112  data: 0.0004  max mem: 78493
Epoch: [124]  [160/312]  eta: 0:02:50  lr: 0.002776  min_lr: 0.002776  loss: 2.3012 (2.3033)  weight_decay: 0.0500 (0.0500)  time: 1.0095  data: 0.0004  max mem: 78493
Epoch: [124]  [170/312]  eta: 0:02:38  lr: 0.002775  min_lr: 0.002775  loss: 2.2538 (2.2968)  weight_decay: 0.0500 (0.0500)  time: 1.0094  data: 0.0005  max mem: 78493
Epoch: [124]  [180/312]  eta: 0:02:26  lr: 0.002774  min_lr: 0.002774  loss: 2.3562 (2.3071)  weight_decay: 0.0500 (0.0500)  time: 1.0099  data: 0.0004  max mem: 78493
Epoch: [124]  [190/312]  eta: 0:02:15  lr: 0.002774  min_lr: 0.002774  loss: 2.5594 (2.3165)  weight_decay: 0.0500 (0.0500)  time: 1.0093  data: 0.0004  max mem: 78493
Epoch: [124]  [200/312]  eta: 0:02:03  lr: 0.002773  min_lr: 0.002773  loss: 2.5833 (2.3256)  weight_decay: 0.0500 (0.0500)  time: 1.0083  data: 0.0005  max mem: 78493
Epoch: [124]  [210/312]  eta: 0:01:51  lr: 0.002772  min_lr: 0.002772  loss: 2.5661 (2.3348)  weight_decay: 0.0500 (0.0500)  time: 1.0073  data: 0.0005  max mem: 78493
Epoch: [124]  [220/312]  eta: 0:01:40  lr: 0.002772  min_lr: 0.002772  loss: 2.5465 (2.3421)  weight_decay: 0.0500 (0.0500)  time: 1.0078  data: 0.0005  max mem: 78493
Epoch: [124]  [230/312]  eta: 0:01:29  lr: 0.002771  min_lr: 0.002771  loss: 2.4674 (2.3444)  weight_decay: 0.0500 (0.0500)  time: 1.0092  data: 0.0005  max mem: 78493
Epoch: [124]  [240/312]  eta: 0:01:18  lr: 0.002770  min_lr: 0.002770  loss: 2.4270 (2.3386)  weight_decay: 0.0500 (0.0500)  time: 1.0084  data: 0.0005  max mem: 78493
Epoch: [124]  [250/312]  eta: 0:01:07  lr: 0.002770  min_lr: 0.002770  loss: 2.1799 (2.3358)  weight_decay: 0.0500 (0.0500)  time: 1.0071  data: 0.0004  max mem: 78493
Epoch: [124]  [260/312]  eta: 0:00:56  lr: 0.002769  min_lr: 0.002769  loss: 2.3105 (2.3362)  weight_decay: 0.0500 (0.0500)  time: 1.0069  data: 0.0004  max mem: 78493
Epoch: [124]  [270/312]  eta: 0:00:45  lr: 0.002768  min_lr: 0.002768  loss: 2.5947 (2.3482)  weight_decay: 0.0500 (0.0500)  time: 1.0078  data: 0.0004  max mem: 78493
Epoch: [124]  [280/312]  eta: 0:00:34  lr: 0.002768  min_lr: 0.002768  loss: 2.5609 (2.3427)  weight_decay: 0.0500 (0.0500)  time: 1.0095  data: 0.0011  max mem: 78493
Epoch: [124]  [290/312]  eta: 0:00:23  lr: 0.002767  min_lr: 0.002767  loss: 2.2109 (2.3414)  weight_decay: 0.0500 (0.0500)  time: 1.0063  data: 0.0009  max mem: 78493
Epoch: [124]  [300/312]  eta: 0:00:12  lr: 0.002766  min_lr: 0.002766  loss: 2.5305 (2.3486)  weight_decay: 0.0500 (0.0500)  time: 1.0016  data: 0.0001  max mem: 78493
Epoch: [124]  [310/312]  eta: 0:00:02  lr: 0.002766  min_lr: 0.002766  loss: 2.4738 (2.3460)  weight_decay: 0.0500 (0.0500)  time: 1.0011  data: 0.0001  max mem: 78493
Epoch: [124]  [311/312]  eta: 0:00:01  lr: 0.002766  min_lr: 0.002766  loss: 2.3229 (2.3453)  weight_decay: 0.0500 (0.0500)  time: 1.0010  data: 0.0001  max mem: 78493
Epoch: [124] Total time: 0:05:34 (1.0736 s / it)
Averaged stats: lr: 0.002766  min_lr: 0.002766  loss: 2.3229 (2.3527)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:17  loss: 0.7347 (0.7347)  acc1: 81.5104 (81.5104)  acc5: 94.5312 (94.5312)  time: 8.6657  data: 8.3906  max mem: 78493
Test:  [8/9]  eta: 0:00:01  loss: 1.0816 (0.9765)  acc1: 74.4792 (74.8000)  acc5: 91.9271 (92.3200)  time: 1.1612  data: 0.9324  max mem: 78493
Test: Total time: 0:00:10 (1.1881 s / it)
* Acc@1 75.260 Acc@5 92.526 loss 0.963
Accuracy of the model on the 50000 test images: 75.3%
Max accuracy: 75.39%
Epoch: [125]  [  0/312]  eta: 1:26:47  lr: 0.002766  min_lr: 0.002766  loss: 2.5435 (2.5435)  weight_decay: 0.0500 (0.0500)  time: 16.6898  data: 13.1876  max mem: 78493
Epoch: [125]  [ 10/312]  eta: 0:13:25  lr: 0.002765  min_lr: 0.002765  loss: 2.2300 (2.2270)  weight_decay: 0.0500 (0.0500)  time: 2.6681  data: 1.2850  max mem: 78493
Epoch: [125]  [ 20/312]  eta: 0:09:09  lr: 0.002764  min_lr: 0.002764  loss: 2.1509 (2.1797)  weight_decay: 0.0500 (0.0500)  time: 1.1432  data: 0.0476  max mem: 78493
Epoch: [125]  [ 30/312]  eta: 0:07:31  lr: 0.002764  min_lr: 0.002764  loss: 2.3864 (2.2400)  weight_decay: 0.0500 (0.0500)  time: 1.0145  data: 0.0019  max mem: 78493
Epoch: [125]  [ 40/312]  eta: 0:06:36  lr: 0.002763  min_lr: 0.002763  loss: 2.4917 (2.2609)  weight_decay: 0.0500 (0.0500)  time: 1.0090  data: 0.0019  max mem: 78493
Epoch: [125]  [ 50/312]  eta: 0:05:58  lr: 0.002762  min_lr: 0.002762  loss: 2.5350 (2.3273)  weight_decay: 0.0500 (0.0500)  time: 1.0102  data: 0.0005  max mem: 78493
Epoch: [125]  [ 60/312]  eta: 0:05:30  lr: 0.002762  min_lr: 0.002762  loss: 2.5059 (2.3151)  weight_decay: 0.0500 (0.0500)  time: 1.0096  data: 0.0005  max mem: 78493
Epoch: [125]  [ 70/312]  eta: 0:05:06  lr: 0.002761  min_lr: 0.002761  loss: 2.4558 (2.3335)  weight_decay: 0.0500 (0.0500)  time: 1.0100  data: 0.0005  max mem: 78493
Epoch: [125]  [ 80/312]  eta: 0:04:46  lr: 0.002760  min_lr: 0.002760  loss: 2.4754 (2.3498)  weight_decay: 0.0500 (0.0500)  time: 1.0112  data: 0.0005  max mem: 78493
Epoch: [125]  [ 90/312]  eta: 0:04:28  lr: 0.002760  min_lr: 0.002760  loss: 2.5527 (2.3612)  weight_decay: 0.0500 (0.0500)  time: 1.0093  data: 0.0005  max mem: 78493
Epoch: [125]  [100/312]  eta: 0:04:12  lr: 0.002759  min_lr: 0.002759  loss: 2.4880 (2.3512)  weight_decay: 0.0500 (0.0500)  time: 1.0074  data: 0.0005  max mem: 78493
Epoch: [125]  [110/312]  eta: 0:03:57  lr: 0.002758  min_lr: 0.002758  loss: 2.4438 (2.3667)  weight_decay: 0.0500 (0.0500)  time: 1.0062  data: 0.0004  max mem: 78493
Epoch: [125]  [120/312]  eta: 0:03:42  lr: 0.002758  min_lr: 0.002758  loss: 2.5244 (2.3672)  weight_decay: 0.0500 (0.0500)  time: 1.0063  data: 0.0004  max mem: 78493
Epoch: [125]  [130/312]  eta: 0:03:29  lr: 0.002757  min_lr: 0.002757  loss: 2.4500 (2.3636)  weight_decay: 0.0500 (0.0500)  time: 1.0075  data: 0.0004  max mem: 78493
Epoch: [125]  [140/312]  eta: 0:03:15  lr: 0.002756  min_lr: 0.002756  loss: 2.3692 (2.3564)  weight_decay: 0.0500 (0.0500)  time: 1.0066  data: 0.0004  max mem: 78493
Epoch: [125]  [150/312]  eta: 0:03:03  lr: 0.002756  min_lr: 0.002756  loss: 2.1919 (2.3446)  weight_decay: 0.0500 (0.0500)  time: 1.0066  data: 0.0004  max mem: 78493
Epoch: [125]  [160/312]  eta: 0:02:50  lr: 0.002755  min_lr: 0.002755  loss: 2.3648 (2.3411)  weight_decay: 0.0500 (0.0500)  time: 1.0085  data: 0.0005  max mem: 78493
Epoch: [125]  [170/312]  eta: 0:02:38  lr: 0.002754  min_lr: 0.002754  loss: 2.3632 (2.3393)  weight_decay: 0.0500 (0.0500)  time: 1.0086  data: 0.0005  max mem: 78493
Epoch: [125]  [180/312]  eta: 0:02:26  lr: 0.002754  min_lr: 0.002754  loss: 2.4179 (2.3559)  weight_decay: 0.0500 (0.0500)  time: 1.0069  data: 0.0005  max mem: 78493
Epoch: [125]  [190/312]  eta: 0:02:14  lr: 0.002753  min_lr: 0.002753  loss: 2.4582 (2.3547)  weight_decay: 0.0500 (0.0500)  time: 1.0057  data: 0.0005  max mem: 78493
Epoch: [125]  [200/312]  eta: 0:02:03  lr: 0.002752  min_lr: 0.002752  loss: 2.3397 (2.3594)  weight_decay: 0.0500 (0.0500)  time: 1.0059  data: 0.0005  max mem: 78493
Epoch: [125]  [210/312]  eta: 0:01:51  lr: 0.002752  min_lr: 0.002752  loss: 2.4919 (2.3583)  weight_decay: 0.0500 (0.0500)  time: 1.0063  data: 0.0004  max mem: 78493
Epoch: [125]  [220/312]  eta: 0:01:40  lr: 0.002751  min_lr: 0.002751  loss: 2.4919 (2.3623)  weight_decay: 0.0500 (0.0500)  time: 1.0075  data: 0.0005  max mem: 78493
Epoch: [125]  [230/312]  eta: 0:01:29  lr: 0.002750  min_lr: 0.002750  loss: 2.4849 (2.3622)  weight_decay: 0.0500 (0.0500)  time: 1.0066  data: 0.0005  max mem: 78493
Epoch: [125]  [240/312]  eta: 0:01:18  lr: 0.002750  min_lr: 0.002750  loss: 2.3567 (2.3579)  weight_decay: 0.0500 (0.0500)  time: 1.0056  data: 0.0004  max mem: 78493
Epoch: [125]  [250/312]  eta: 0:01:07  lr: 0.002749  min_lr: 0.002749  loss: 2.3567 (2.3566)  weight_decay: 0.0500 (0.0500)  time: 1.0069  data: 0.0005  max mem: 78493
Epoch: [125]  [260/312]  eta: 0:00:56  lr: 0.002748  min_lr: 0.002748  loss: 2.5043 (2.3639)  weight_decay: 0.0500 (0.0500)  time: 1.0071  data: 0.0005  max mem: 78493
Epoch: [125]  [270/312]  eta: 0:00:45  lr: 0.002748  min_lr: 0.002748  loss: 2.4287 (2.3598)  weight_decay: 0.0500 (0.0500)  time: 1.0065  data: 0.0004  max mem: 78493
Epoch: [125]  [280/312]  eta: 0:00:34  lr: 0.002747  min_lr: 0.002747  loss: 2.2666 (2.3595)  weight_decay: 0.0500 (0.0500)  time: 1.0074  data: 0.0010  max mem: 78493
Epoch: [125]  [290/312]  eta: 0:00:23  lr: 0.002746  min_lr: 0.002746  loss: 2.2146 (2.3550)  weight_decay: 0.0500 (0.0500)  time: 1.0056  data: 0.0009  max mem: 78493
Epoch: [125]  [300/312]  eta: 0:00:12  lr: 0.002746  min_lr: 0.002746  loss: 2.1101 (2.3514)  weight_decay: 0.0500 (0.0500)  time: 1.0022  data: 0.0001  max mem: 78493
Epoch: [125]  [310/312]  eta: 0:00:02  lr: 0.002745  min_lr: 0.002745  loss: 2.3190 (2.3566)  weight_decay: 0.0500 (0.0500)  time: 1.0020  data: 0.0001  max mem: 78493
Epoch: [125]  [311/312]  eta: 0:00:01  lr: 0.002745  min_lr: 0.002745  loss: 2.3190 (2.3547)  weight_decay: 0.0500 (0.0500)  time: 1.0020  data: 0.0001  max mem: 78493
Epoch: [125] Total time: 0:05:34 (1.0717 s / it)
Averaged stats: lr: 0.002745  min_lr: 0.002745  loss: 2.3190 (2.3698)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:16  loss: 0.7442 (0.7442)  acc1: 81.9010 (81.9010)  acc5: 95.4427 (95.4427)  time: 8.4760  data: 8.2131  max mem: 78493
Test:  [8/9]  eta: 0:00:01  loss: 1.0592 (0.9881)  acc1: 74.0885 (75.2320)  acc5: 92.7083 (92.7840)  time: 1.1445  data: 0.9126  max mem: 78493
Test: Total time: 0:00:10 (1.1858 s / it)
* Acc@1 75.234 Acc@5 92.526 loss 0.978
Accuracy of the model on the 50000 test images: 75.2%
Max accuracy: 75.39%
Epoch: [126]  [  0/312]  eta: 1:25:55  lr: 0.002745  min_lr: 0.002745  loss: 2.2973 (2.2973)  weight_decay: 0.0500 (0.0500)  time: 16.5254  data: 13.2886  max mem: 78493
Epoch: [126]  [ 10/312]  eta: 0:13:39  lr: 0.002744  min_lr: 0.002744  loss: 2.3050 (2.4298)  weight_decay: 0.0500 (0.0500)  time: 2.7146  data: 1.2421  max mem: 78493
Epoch: [126]  [ 20/312]  eta: 0:09:15  lr: 0.002744  min_lr: 0.002744  loss: 2.2398 (2.2799)  weight_decay: 0.0500 (0.0500)  time: 1.1715  data: 0.0190  max mem: 78493
Epoch: [126]  [ 30/312]  eta: 0:07:35  lr: 0.002743  min_lr: 0.002743  loss: 2.0534 (2.2680)  weight_decay: 0.0500 (0.0500)  time: 1.0101  data: 0.0004  max mem: 78493
Epoch: [126]  [ 40/312]  eta: 0:06:38  lr: 0.002742  min_lr: 0.002742  loss: 2.3608 (2.3195)  weight_decay: 0.0500 (0.0500)  time: 1.0088  data: 0.0004  max mem: 78493
Epoch: [126]  [ 50/312]  eta: 0:06:00  lr: 0.002742  min_lr: 0.002742  loss: 2.5295 (2.3369)  weight_decay: 0.0500 (0.0500)  time: 1.0052  data: 0.0004  max mem: 78493
Epoch: [126]  [ 60/312]  eta: 0:05:31  lr: 0.002741  min_lr: 0.002741  loss: 2.4193 (2.3268)  weight_decay: 0.0500 (0.0500)  time: 1.0052  data: 0.0004  max mem: 78493
Epoch: [126]  [ 70/312]  eta: 0:05:07  lr: 0.002740  min_lr: 0.002740  loss: 2.4767 (2.3345)  weight_decay: 0.0500 (0.0500)  time: 1.0084  data: 0.0004  max mem: 78493
Epoch: [126]  [ 80/312]  eta: 0:04:47  lr: 0.002740  min_lr: 0.002740  loss: 2.4726 (2.3341)  weight_decay: 0.0500 (0.0500)  time: 1.0080  data: 0.0004  max mem: 78493
Epoch: [126]  [ 90/312]  eta: 0:04:29  lr: 0.002739  min_lr: 0.002739  loss: 2.4726 (2.3645)  weight_decay: 0.0500 (0.0500)  time: 1.0076  data: 0.0004  max mem: 78493
Epoch: [126]  [100/312]  eta: 0:04:13  lr: 0.002738  min_lr: 0.002738  loss: 2.4832 (2.3592)  weight_decay: 0.0500 (0.0500)  time: 1.0099  data: 0.0005  max mem: 78493
Epoch: [126]  [110/312]  eta: 0:03:57  lr: 0.002738  min_lr: 0.002738  loss: 2.4707 (2.3662)  weight_decay: 0.0500 (0.0500)  time: 1.0110  data: 0.0005  max mem: 78493
Epoch: [126]  [120/312]  eta: 0:03:43  lr: 0.002737  min_lr: 0.002737  loss: 2.4472 (2.3655)  weight_decay: 0.0500 (0.0500)  time: 1.0103  data: 0.0005  max mem: 78493
Epoch: [126]  [130/312]  eta: 0:03:29  lr: 0.002736  min_lr: 0.002736  loss: 2.3536 (2.3563)  weight_decay: 0.0500 (0.0500)  time: 1.0089  data: 0.0004  max mem: 78493
Epoch: [126]  [140/312]  eta: 0:03:16  lr: 0.002736  min_lr: 0.002736  loss: 2.3588 (2.3584)  weight_decay: 0.0500 (0.0500)  time: 1.0061  data: 0.0004  max mem: 78493
Epoch: [126]  [150/312]  eta: 0:03:03  lr: 0.002735  min_lr: 0.002735  loss: 2.4005 (2.3552)  weight_decay: 0.0500 (0.0500)  time: 1.0056  data: 0.0004  max mem: 78493
Epoch: [126]  [160/312]  eta: 0:02:50  lr: 0.002734  min_lr: 0.002734  loss: 2.3085 (2.3541)  weight_decay: 0.0500 (0.0500)  time: 1.0066  data: 0.0004  max mem: 78493
Epoch: [126]  [170/312]  eta: 0:02:38  lr: 0.002734  min_lr: 0.002734  loss: 2.4973 (2.3612)  weight_decay: 0.0500 (0.0500)  time: 1.0064  data: 0.0005  max mem: 78493
Epoch: [126]  [180/312]  eta: 0:02:26  lr: 0.002733  min_lr: 0.002733  loss: 2.4448 (2.3542)  weight_decay: 0.0500 (0.0500)  time: 1.0065  data: 0.0005  max mem: 78493
Epoch: [126]  [190/312]  eta: 0:02:14  lr: 0.002732  min_lr: 0.002732  loss: 2.4448 (2.3572)  weight_decay: 0.0500 (0.0500)  time: 1.0066  data: 0.0004  max mem: 78493
Epoch: [126]  [200/312]  eta: 0:02:03  lr: 0.002732  min_lr: 0.002732  loss: 2.4993 (2.3571)  weight_decay: 0.0500 (0.0500)  time: 1.0084  data: 0.0004  max mem: 78493
Epoch: [126]  [210/312]  eta: 0:01:51  lr: 0.002731  min_lr: 0.002731  loss: 2.5496 (2.3698)  weight_decay: 0.0500 (0.0500)  time: 1.0085  data: 0.0004  max mem: 78493
Epoch: [126]  [220/312]  eta: 0:01:40  lr: 0.002730  min_lr: 0.002730  loss: 2.5522 (2.3694)  weight_decay: 0.0500 (0.0500)  time: 1.0076  data: 0.0004  max mem: 78493
Epoch: [126]  [230/312]  eta: 0:01:29  lr: 0.002730  min_lr: 0.002730  loss: 2.2225 (2.3625)  weight_decay: 0.0500 (0.0500)  time: 1.0063  data: 0.0005  max mem: 78493
Epoch: [126]  [240/312]  eta: 0:01:18  lr: 0.002729  min_lr: 0.002729  loss: 2.1577 (2.3552)  weight_decay: 0.0500 (0.0500)  time: 1.0060  data: 0.0004  max mem: 78493
Epoch: [126]  [250/312]  eta: 0:01:07  lr: 0.002728  min_lr: 0.002728  loss: 2.3419 (2.3531)  weight_decay: 0.0500 (0.0500)  time: 1.0058  data: 0.0005  max mem: 78493
Epoch: [126]  [260/312]  eta: 0:00:56  lr: 0.002728  min_lr: 0.002728  loss: 2.3433 (2.3548)  weight_decay: 0.0500 (0.0500)  time: 1.0058  data: 0.0005  max mem: 78493
Epoch: [126]  [270/312]  eta: 0:00:45  lr: 0.002727  min_lr: 0.002727  loss: 2.4946 (2.3616)  weight_decay: 0.0500 (0.0500)  time: 1.0063  data: 0.0005  max mem: 78493
Epoch: [126]  [280/312]  eta: 0:00:34  lr: 0.002726  min_lr: 0.002726  loss: 2.5553 (2.3662)  weight_decay: 0.0500 (0.0500)  time: 1.0065  data: 0.0010  max mem: 78493
Epoch: [126]  [290/312]  eta: 0:00:23  lr: 0.002726  min_lr: 0.002726  loss: 2.5233 (2.3672)  weight_decay: 0.0500 (0.0500)  time: 1.0051  data: 0.0008  max mem: 78493
Epoch: [126]  [300/312]  eta: 0:00:12  lr: 0.002725  min_lr: 0.002725  loss: 2.4786 (2.3646)  weight_decay: 0.0500 (0.0500)  time: 1.0021  data: 0.0001  max mem: 78493
Epoch: [126]  [310/312]  eta: 0:00:02  lr: 0.002724  min_lr: 0.002724  loss: 2.3779 (2.3685)  weight_decay: 0.0500 (0.0500)  time: 1.0014  data: 0.0001  max mem: 78493
Epoch: [126]  [311/312]  eta: 0:00:01  lr: 0.002724  min_lr: 0.002724  loss: 2.4786 (2.3692)  weight_decay: 0.0500 (0.0500)  time: 1.0015  data: 0.0001  max mem: 78493
Epoch: [126] Total time: 0:05:34 (1.0728 s / it)
Averaged stats: lr: 0.002724  min_lr: 0.002724  loss: 2.4786 (2.3624)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:17  loss: 0.8050 (0.8050)  acc1: 80.8594 (80.8594)  acc5: 94.6615 (94.6615)  time: 8.5672  data: 8.3062  max mem: 78493
Test:  [8/9]  eta: 0:00:01  loss: 1.1292 (0.9936)  acc1: 73.5677 (74.9760)  acc5: 91.0156 (92.2400)  time: 1.1564  data: 0.9230  max mem: 78493
Test: Total time: 0:00:10 (1.2032 s / it)
* Acc@1 74.874 Acc@5 92.300 loss 0.986
Accuracy of the model on the 50000 test images: 74.9%
Max accuracy: 75.39%
Epoch: [127]  [  0/312]  eta: 1:25:04  lr: 0.002724  min_lr: 0.002724  loss: 2.3015 (2.3015)  weight_decay: 0.0500 (0.0500)  time: 16.3620  data: 13.1813  max mem: 78493
Epoch: [127]  [ 10/312]  eta: 0:13:38  lr: 0.002723  min_lr: 0.002723  loss: 2.3015 (2.3468)  weight_decay: 0.0500 (0.0500)  time: 2.7103  data: 1.2103  max mem: 78493
Epoch: [127]  [ 20/312]  eta: 0:09:15  lr: 0.002723  min_lr: 0.002723  loss: 2.4426 (2.3794)  weight_decay: 0.0500 (0.0500)  time: 1.1807  data: 0.0068  max mem: 78493
Epoch: [127]  [ 30/312]  eta: 0:07:35  lr: 0.002722  min_lr: 0.002722  loss: 2.5006 (2.3714)  weight_decay: 0.0500 (0.0500)  time: 1.0127  data: 0.0004  max mem: 78493
Epoch: [127]  [ 40/312]  eta: 0:06:38  lr: 0.002721  min_lr: 0.002721  loss: 2.2721 (2.3341)  weight_decay: 0.0500 (0.0500)  time: 1.0079  data: 0.0004  max mem: 78493
Epoch: [127]  [ 50/312]  eta: 0:06:00  lr: 0.002721  min_lr: 0.002721  loss: 2.4305 (2.3407)  weight_decay: 0.0500 (0.0500)  time: 1.0055  data: 0.0004  max mem: 78493
Epoch: [127]  [ 60/312]  eta: 0:05:31  lr: 0.002720  min_lr: 0.002720  loss: 2.5251 (2.3579)  weight_decay: 0.0500 (0.0500)  time: 1.0056  data: 0.0004  max mem: 78493
Epoch: [127]  [ 70/312]  eta: 0:05:07  lr: 0.002719  min_lr: 0.002719  loss: 2.5017 (2.3644)  weight_decay: 0.0500 (0.0500)  time: 1.0082  data: 0.0004  max mem: 78493
Epoch: [127]  [ 80/312]  eta: 0:04:47  lr: 0.002719  min_lr: 0.002719  loss: 2.4453 (2.3505)  weight_decay: 0.0500 (0.0500)  time: 1.0098  data: 0.0004  max mem: 78493
Epoch: [127]  [ 90/312]  eta: 0:04:29  lr: 0.002718  min_lr: 0.002718  loss: 2.3388 (2.3469)  weight_decay: 0.0500 (0.0500)  time: 1.0077  data: 0.0004  max mem: 78493
Epoch: [127]  [100/312]  eta: 0:04:13  lr: 0.002717  min_lr: 0.002717  loss: 2.4549 (2.3623)  weight_decay: 0.0500 (0.0500)  time: 1.0077  data: 0.0004  max mem: 78493
Epoch: [127]  [110/312]  eta: 0:03:57  lr: 0.002717  min_lr: 0.002717  loss: 2.5221 (2.3638)  weight_decay: 0.0500 (0.0500)  time: 1.0092  data: 0.0004  max mem: 78493
Epoch: [127]  [120/312]  eta: 0:03:43  lr: 0.002716  min_lr: 0.002716  loss: 2.4936 (2.3617)  weight_decay: 0.0500 (0.0500)  time: 1.0080  data: 0.0005  max mem: 78493
Epoch: [127]  [130/312]  eta: 0:03:29  lr: 0.002715  min_lr: 0.002715  loss: 2.4946 (2.3632)  weight_decay: 0.0500 (0.0500)  time: 1.0070  data: 0.0005  max mem: 78493
Epoch: [127]  [140/312]  eta: 0:03:16  lr: 0.002715  min_lr: 0.002715  loss: 2.4733 (2.3584)  weight_decay: 0.0500 (0.0500)  time: 1.0070  data: 0.0005  max mem: 78493
Epoch: [127]  [150/312]  eta: 0:03:03  lr: 0.002714  min_lr: 0.002714  loss: 2.3709 (2.3548)  weight_decay: 0.0500 (0.0500)  time: 1.0076  data: 0.0005  max mem: 78493
Epoch: [127]  [160/312]  eta: 0:02:50  lr: 0.002713  min_lr: 0.002713  loss: 2.2454 (2.3474)  weight_decay: 0.0500 (0.0500)  time: 1.0083  data: 0.0004  max mem: 78493
Epoch: [127]  [170/312]  eta: 0:02:38  lr: 0.002713  min_lr: 0.002713  loss: 2.2379 (2.3386)  weight_decay: 0.0500 (0.0500)  time: 1.0092  data: 0.0004  max mem: 78493
Epoch: [127]  [180/312]  eta: 0:02:26  lr: 0.002712  min_lr: 0.002712  loss: 2.2888 (2.3335)  weight_decay: 0.0500 (0.0500)  time: 1.0075  data: 0.0004  max mem: 78493
Epoch: [127]  [190/312]  eta: 0:02:14  lr: 0.002711  min_lr: 0.002711  loss: 2.4677 (2.3479)  weight_decay: 0.0500 (0.0500)  time: 1.0072  data: 0.0005  max mem: 78493
Epoch: [127]  [200/312]  eta: 0:02:03  lr: 0.002711  min_lr: 0.002711  loss: 2.4756 (2.3433)  weight_decay: 0.0500 (0.0500)  time: 1.0088  data: 0.0005  max mem: 78493
Epoch: [127]  [210/312]  eta: 0:01:51  lr: 0.002710  min_lr: 0.002710  loss: 2.4304 (2.3462)  weight_decay: 0.0500 (0.0500)  time: 1.0066  data: 0.0004  max mem: 78493
Epoch: [127]  [220/312]  eta: 0:01:40  lr: 0.002709  min_lr: 0.002709  loss: 2.3696 (2.3369)  weight_decay: 0.0500 (0.0500)  time: 1.0057  data: 0.0005  max mem: 78493
Epoch: [127]  [230/312]  eta: 0:01:29  lr: 0.002709  min_lr: 0.002709  loss: 2.3268 (2.3403)  weight_decay: 0.0500 (0.0500)  time: 1.0059  data: 0.0005  max mem: 78493
Epoch: [127]  [240/312]  eta: 0:01:18  lr: 0.002708  min_lr: 0.002708  loss: 2.3607 (2.3407)  weight_decay: 0.0500 (0.0500)  time: 1.0043  data: 0.0004  max mem: 78493
Epoch: [127]  [250/312]  eta: 0:01:07  lr: 0.002707  min_lr: 0.002707  loss: 2.5567 (2.3511)  weight_decay: 0.0500 (0.0500)  time: 1.0053  data: 0.0005  max mem: 78493
Epoch: [127]  [260/312]  eta: 0:00:56  lr: 0.002707  min_lr: 0.002707  loss: 2.4202 (2.3431)  weight_decay: 0.0500 (0.0500)  time: 1.0056  data: 0.0005  max mem: 78493
Epoch: [127]  [270/312]  eta: 0:00:45  lr: 0.002706  min_lr: 0.002706  loss: 2.1187 (2.3389)  weight_decay: 0.0500 (0.0500)  time: 1.0040  data: 0.0005  max mem: 78493
Epoch: [127]  [280/312]  eta: 0:00:34  lr: 0.002705  min_lr: 0.002705  loss: 2.1115 (2.3374)  weight_decay: 0.0500 (0.0500)  time: 1.0042  data: 0.0010  max mem: 78493
Epoch: [127]  [290/312]  eta: 0:00:23  lr: 0.002705  min_lr: 0.002705  loss: 2.4880 (2.3392)  weight_decay: 0.0500 (0.0500)  time: 1.0038  data: 0.0009  max mem: 78493
Epoch: [127]  [300/312]  eta: 0:00:12  lr: 0.002704  min_lr: 0.002704  loss: 2.3983 (2.3407)  weight_decay: 0.0500 (0.0500)  time: 1.0024  data: 0.0001  max mem: 78493
Epoch: [127]  [310/312]  eta: 0:00:02  lr: 0.002703  min_lr: 0.002703  loss: 2.3426 (2.3360)  weight_decay: 0.0500 (0.0500)  time: 1.0020  data: 0.0001  max mem: 78493
Epoch: [127]  [311/312]  eta: 0:00:01  lr: 0.002703  min_lr: 0.002703  loss: 2.3426 (2.3341)  weight_decay: 0.0500 (0.0500)  time: 1.0020  data: 0.0001  max mem: 78493
Epoch: [127] Total time: 0:05:34 (1.0726 s / it)
Averaged stats: lr: 0.002703  min_lr: 0.002703  loss: 2.3426 (2.3393)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:16  loss: 0.7250 (0.7250)  acc1: 83.0729 (83.0729)  acc5: 95.7031 (95.7031)  time: 8.4687  data: 8.2008  max mem: 78493
Test:  [8/9]  eta: 0:00:01  loss: 1.1064 (0.9767)  acc1: 73.9583 (75.7440)  acc5: 92.5781 (92.7360)  time: 1.1405  data: 0.9113  max mem: 78493
Test: Total time: 0:00:10 (1.1607 s / it)
* Acc@1 75.336 Acc@5 92.578 loss 0.968
Accuracy of the model on the 50000 test images: 75.3%
Max accuracy: 75.39%
Epoch: [128]  [  0/312]  eta: 1:26:41  lr: 0.002703  min_lr: 0.002703  loss: 2.7063 (2.7063)  weight_decay: 0.0500 (0.0500)  time: 16.6708  data: 15.0935  max mem: 78493
Epoch: [128]  [ 10/312]  eta: 0:13:06  lr: 0.002702  min_lr: 0.002702  loss: 2.7063 (2.5971)  weight_decay: 0.0500 (0.0500)  time: 2.6052  data: 1.3727  max mem: 78493
Epoch: [128]  [ 20/312]  eta: 0:09:02  lr: 0.002702  min_lr: 0.002702  loss: 2.5979 (2.4936)  weight_decay: 0.0500 (0.0500)  time: 1.1167  data: 0.0006  max mem: 78493
Epoch: [128]  [ 30/312]  eta: 0:07:26  lr: 0.002701  min_lr: 0.002701  loss: 2.3432 (2.4200)  weight_decay: 0.0500 (0.0500)  time: 1.0215  data: 0.0005  max mem: 78493
Epoch: [128]  [ 40/312]  eta: 0:06:32  lr: 0.002700  min_lr: 0.002700  loss: 2.3432 (2.3973)  weight_decay: 0.0500 (0.0500)  time: 1.0070  data: 0.0004  max mem: 78493
Epoch: [128]  [ 50/312]  eta: 0:05:55  lr: 0.002700  min_lr: 0.002700  loss: 2.4832 (2.4230)  weight_decay: 0.0500 (0.0500)  time: 1.0070  data: 0.0004  max mem: 78493
Epoch: [128]  [ 60/312]  eta: 0:05:27  lr: 0.002699  min_lr: 0.002699  loss: 2.5249 (2.4294)  weight_decay: 0.0500 (0.0500)  time: 1.0082  data: 0.0004  max mem: 78493
Epoch: [128]  [ 70/312]  eta: 0:05:04  lr: 0.002698  min_lr: 0.002698  loss: 2.5249 (2.4120)  weight_decay: 0.0500 (0.0500)  time: 1.0085  data: 0.0004  max mem: 78493
Epoch: [128]  [ 80/312]  eta: 0:04:44  lr: 0.002698  min_lr: 0.002698  loss: 2.3613 (2.3965)  weight_decay: 0.0500 (0.0500)  time: 1.0083  data: 0.0004  max mem: 78493
Epoch: [128]  [ 90/312]  eta: 0:04:27  lr: 0.002697  min_lr: 0.002697  loss: 2.0710 (2.3670)  weight_decay: 0.0500 (0.0500)  time: 1.0085  data: 0.0004  max mem: 78493
Epoch: [128]  [100/312]  eta: 0:04:11  lr: 0.002696  min_lr: 0.002696  loss: 2.1637 (2.3657)  weight_decay: 0.0500 (0.0500)  time: 1.0095  data: 0.0004  max mem: 78493
Epoch: [128]  [110/312]  eta: 0:03:56  lr: 0.002696  min_lr: 0.002696  loss: 2.2327 (2.3516)  weight_decay: 0.0500 (0.0500)  time: 1.0078  data: 0.0004  max mem: 78493
Epoch: [128]  [120/312]  eta: 0:03:41  lr: 0.002695  min_lr: 0.002695  loss: 2.2186 (2.3479)  weight_decay: 0.0500 (0.0500)  time: 1.0076  data: 0.0004  max mem: 78493
Epoch: [128]  [130/312]  eta: 0:03:28  lr: 0.002694  min_lr: 0.002694  loss: 2.4177 (2.3535)  weight_decay: 0.0500 (0.0500)  time: 1.0083  data: 0.0005  max mem: 78493
Epoch: [128]  [140/312]  eta: 0:03:15  lr: 0.002694  min_lr: 0.002694  loss: 2.5112 (2.3597)  weight_decay: 0.0500 (0.0500)  time: 1.0057  data: 0.0005  max mem: 78493
Epoch: [128]  [150/312]  eta: 0:03:02  lr: 0.002693  min_lr: 0.002693  loss: 2.4598 (2.3544)  weight_decay: 0.0500 (0.0500)  time: 1.0058  data: 0.0005  max mem: 78493
Epoch: [128]  [160/312]  eta: 0:02:49  lr: 0.002692  min_lr: 0.002692  loss: 2.5419 (2.3646)  weight_decay: 0.0500 (0.0500)  time: 1.0059  data: 0.0004  max mem: 78493
Epoch: [128]  [170/312]  eta: 0:02:37  lr: 0.002692  min_lr: 0.002692  loss: 2.5628 (2.3588)  weight_decay: 0.0500 (0.0500)  time: 1.0064  data: 0.0004  max mem: 78493
Epoch: [128]  [180/312]  eta: 0:02:26  lr: 0.002691  min_lr: 0.002691  loss: 2.4400 (2.3610)  weight_decay: 0.0500 (0.0500)  time: 1.0081  data: 0.0004  max mem: 78493
Epoch: [128]  [190/312]  eta: 0:02:14  lr: 0.002690  min_lr: 0.002690  loss: 2.2836 (2.3523)  weight_decay: 0.0500 (0.0500)  time: 1.0074  data: 0.0004  max mem: 78493
Epoch: [128]  [200/312]  eta: 0:02:02  lr: 0.002690  min_lr: 0.002690  loss: 2.2836 (2.3514)  weight_decay: 0.0500 (0.0500)  time: 1.0057  data: 0.0004  max mem: 78493
Epoch: [128]  [210/312]  eta: 0:01:51  lr: 0.002689  min_lr: 0.002689  loss: 2.4355 (2.3596)  weight_decay: 0.0500 (0.0500)  time: 1.0063  data: 0.0004  max mem: 78493
Epoch: [128]  [220/312]  eta: 0:01:40  lr: 0.002688  min_lr: 0.002688  loss: 2.4720 (2.3567)  weight_decay: 0.0500 (0.0500)  time: 1.0072  data: 0.0004  max mem: 78493
Epoch: [128]  [230/312]  eta: 0:01:28  lr: 0.002688  min_lr: 0.002688  loss: 2.3109 (2.3551)  weight_decay: 0.0500 (0.0500)  time: 1.0053  data: 0.0004  max mem: 78493
Epoch: [128]  [240/312]  eta: 0:01:17  lr: 0.002687  min_lr: 0.002687  loss: 2.3348 (2.3558)  weight_decay: 0.0500 (0.0500)  time: 1.0052  data: 0.0004  max mem: 78493
Epoch: [128]  [250/312]  eta: 0:01:06  lr: 0.002686  min_lr: 0.002686  loss: 2.3109 (2.3509)  weight_decay: 0.0500 (0.0500)  time: 1.0071  data: 0.0004  max mem: 78493
Epoch: [128]  [260/312]  eta: 0:00:55  lr: 0.002686  min_lr: 0.002686  loss: 2.3059 (2.3501)  weight_decay: 0.0500 (0.0500)  time: 1.0071  data: 0.0004  max mem: 78493
Epoch: [128]  [270/312]  eta: 0:00:45  lr: 0.002685  min_lr: 0.002685  loss: 2.3322 (2.3519)  weight_decay: 0.0500 (0.0500)  time: 1.0062  data: 0.0004  max mem: 78493
Epoch: [128]  [280/312]  eta: 0:00:34  lr: 0.002684  min_lr: 0.002684  loss: 2.3759 (2.3503)  weight_decay: 0.0500 (0.0500)  time: 1.0076  data: 0.0010  max mem: 78493
Epoch: [128]  [290/312]  eta: 0:00:23  lr: 0.002684  min_lr: 0.002684  loss: 2.3055 (2.3496)  weight_decay: 0.0500 (0.0500)  time: 1.0058  data: 0.0009  max mem: 78493
Epoch: [128]  [300/312]  eta: 0:00:12  lr: 0.002683  min_lr: 0.002683  loss: 2.2836 (2.3452)  weight_decay: 0.0500 (0.0500)  time: 1.0023  data: 0.0001  max mem: 78493
Epoch: [128]  [310/312]  eta: 0:00:02  lr: 0.002682  min_lr: 0.002682  loss: 2.2354 (2.3416)  weight_decay: 0.0500 (0.0500)  time: 1.0014  data: 0.0001  max mem: 78493
Epoch: [128]  [311/312]  eta: 0:00:01  lr: 0.002682  min_lr: 0.002682  loss: 2.2354 (2.3423)  weight_decay: 0.0500 (0.0500)  time: 1.0014  data: 0.0001  max mem: 78493
Epoch: [128] Total time: 0:05:33 (1.0694 s / it)
Averaged stats: lr: 0.002682  min_lr: 0.002682  loss: 2.2354 (2.3430)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:15  loss: 0.7228 (0.7228)  acc1: 82.8125 (82.8125)  acc5: 94.9219 (94.9219)  time: 8.3768  data: 8.1095  max mem: 78493
Test:  [8/9]  eta: 0:00:01  loss: 1.1771 (1.0201)  acc1: 72.7865 (74.3680)  acc5: 90.7552 (91.9360)  time: 1.1304  data: 0.9011  max mem: 78493
Test: Total time: 0:00:10 (1.1720 s / it)
* Acc@1 74.662 Acc@5 92.066 loss 1.003
Accuracy of the model on the 50000 test images: 74.7%
Max accuracy: 75.39%
Epoch: [129]  [  0/312]  eta: 1:26:12  lr: 0.002682  min_lr: 0.002682  loss: 2.6205 (2.6205)  weight_decay: 0.0500 (0.0500)  time: 16.5788  data: 12.3532  max mem: 78493
Epoch: [129]  [ 10/312]  eta: 0:13:26  lr: 0.002681  min_lr: 0.002681  loss: 2.4689 (2.3989)  weight_decay: 0.0500 (0.0500)  time: 2.6699  data: 1.3188  max mem: 78493
Epoch: [129]  [ 20/312]  eta: 0:09:10  lr: 0.002681  min_lr: 0.002681  loss: 2.4689 (2.4790)  weight_decay: 0.0500 (0.0500)  time: 1.1500  data: 0.1079  max mem: 78493
Epoch: [129]  [ 30/312]  eta: 0:07:31  lr: 0.002680  min_lr: 0.002680  loss: 2.4701 (2.4694)  weight_decay: 0.0500 (0.0500)  time: 1.0140  data: 0.0004  max mem: 78493
Epoch: [129]  [ 40/312]  eta: 0:06:36  lr: 0.002679  min_lr: 0.002679  loss: 2.5068 (2.5028)  weight_decay: 0.0500 (0.0500)  time: 1.0087  data: 0.0004  max mem: 78493
Epoch: [129]  [ 50/312]  eta: 0:05:58  lr: 0.002679  min_lr: 0.002679  loss: 2.5795 (2.4930)  weight_decay: 0.0500 (0.0500)  time: 1.0098  data: 0.0004  max mem: 78493
Epoch: [129]  [ 60/312]  eta: 0:05:30  lr: 0.002678  min_lr: 0.002678  loss: 2.5266 (2.4923)  weight_decay: 0.0500 (0.0500)  time: 1.0076  data: 0.0004  max mem: 78493
Epoch: [129]  [ 70/312]  eta: 0:05:06  lr: 0.002677  min_lr: 0.002677  loss: 2.5266 (2.4696)  weight_decay: 0.0500 (0.0500)  time: 1.0063  data: 0.0005  max mem: 78493
Epoch: [129]  [ 80/312]  eta: 0:04:46  lr: 0.002677  min_lr: 0.002677  loss: 2.3273 (2.4405)  weight_decay: 0.0500 (0.0500)  time: 1.0063  data: 0.0005  max mem: 78493
Epoch: [129]  [ 90/312]  eta: 0:04:28  lr: 0.002676  min_lr: 0.002676  loss: 2.2917 (2.4146)  weight_decay: 0.0500 (0.0500)  time: 1.0062  data: 0.0004  max mem: 78493
Epoch: [129]  [100/312]  eta: 0:04:12  lr: 0.002675  min_lr: 0.002675  loss: 2.2809 (2.3980)  weight_decay: 0.0500 (0.0500)  time: 1.0090  data: 0.0004  max mem: 78493
Epoch: [129]  [110/312]  eta: 0:03:57  lr: 0.002675  min_lr: 0.002675  loss: 2.2809 (2.3896)  weight_decay: 0.0500 (0.0500)  time: 1.0108  data: 0.0004  max mem: 78493
Epoch: [129]  [120/312]  eta: 0:03:42  lr: 0.002674  min_lr: 0.002674  loss: 2.3204 (2.3869)  weight_decay: 0.0500 (0.0500)  time: 1.0090  data: 0.0004  max mem: 78493
Epoch: [129]  [130/312]  eta: 0:03:29  lr: 0.002673  min_lr: 0.002673  loss: 2.3416 (2.3886)  weight_decay: 0.0500 (0.0500)  time: 1.0085  data: 0.0014  max mem: 78493
Epoch: [129]  [140/312]  eta: 0:03:15  lr: 0.002673  min_lr: 0.002673  loss: 2.4454 (2.3989)  weight_decay: 0.0500 (0.0500)  time: 1.0088  data: 0.0014  max mem: 78493
Epoch: [129]  [150/312]  eta: 0:03:03  lr: 0.002672  min_lr: 0.002672  loss: 2.5235 (2.3925)  weight_decay: 0.0500 (0.0500)  time: 1.0065  data: 0.0005  max mem: 78493
Epoch: [129]  [160/312]  eta: 0:02:50  lr: 0.002671  min_lr: 0.002671  loss: 2.1561 (2.3756)  weight_decay: 0.0500 (0.0500)  time: 1.0060  data: 0.0005  max mem: 78493
Epoch: [129]  [170/312]  eta: 0:02:38  lr: 0.002671  min_lr: 0.002671  loss: 2.1242 (2.3696)  weight_decay: 0.0500 (0.0500)  time: 1.0075  data: 0.0004  max mem: 78493
Epoch: [129]  [180/312]  eta: 0:02:26  lr: 0.002670  min_lr: 0.002670  loss: 2.3236 (2.3717)  weight_decay: 0.0500 (0.0500)  time: 1.0063  data: 0.0004  max mem: 78493
Epoch: [129]  [190/312]  eta: 0:02:14  lr: 0.002669  min_lr: 0.002669  loss: 2.3415 (2.3669)  weight_decay: 0.0500 (0.0500)  time: 1.0044  data: 0.0004  max mem: 78493
Epoch: [129]  [200/312]  eta: 0:02:03  lr: 0.002668  min_lr: 0.002668  loss: 2.4664 (2.3720)  weight_decay: 0.0500 (0.0500)  time: 1.0045  data: 0.0004  max mem: 78493
Epoch: [129]  [210/312]  eta: 0:01:51  lr: 0.002668  min_lr: 0.002668  loss: 2.5050 (2.3778)  weight_decay: 0.0500 (0.0500)  time: 1.0046  data: 0.0005  max mem: 78493
Epoch: [129]  [220/312]  eta: 0:01:40  lr: 0.002667  min_lr: 0.002667  loss: 2.5573 (2.3873)  weight_decay: 0.0500 (0.0500)  time: 1.0036  data: 0.0005  max mem: 78493
Epoch: [129]  [230/312]  eta: 0:01:29  lr: 0.002666  min_lr: 0.002666  loss: 2.5415 (2.3880)  weight_decay: 0.0500 (0.0500)  time: 1.0051  data: 0.0004  max mem: 78493
Epoch: [129]  [240/312]  eta: 0:01:18  lr: 0.002666  min_lr: 0.002666  loss: 2.3691 (2.3942)  weight_decay: 0.0500 (0.0500)  time: 1.0059  data: 0.0004  max mem: 78493
Epoch: [129]  [250/312]  eta: 0:01:06  lr: 0.002665  min_lr: 0.002665  loss: 2.4327 (2.3914)  weight_decay: 0.0500 (0.0500)  time: 1.0037  data: 0.0004  max mem: 78493
Epoch: [129]  [260/312]  eta: 0:00:56  lr: 0.002664  min_lr: 0.002664  loss: 2.4327 (2.3908)  weight_decay: 0.0500 (0.0500)  time: 1.0041  data: 0.0005  max mem: 78493
Epoch: [129]  [270/312]  eta: 0:00:45  lr: 0.002664  min_lr: 0.002664  loss: 2.4479 (2.3913)  weight_decay: 0.0500 (0.0500)  time: 1.0056  data: 0.0014  max mem: 78493
Epoch: [129]  [280/312]  eta: 0:00:34  lr: 0.002663  min_lr: 0.002663  loss: 2.4442 (2.3917)  weight_decay: 0.0500 (0.0500)  time: 1.0060  data: 0.0020  max mem: 78493
Epoch: [129]  [290/312]  eta: 0:00:23  lr: 0.002662  min_lr: 0.002662  loss: 2.3891 (2.3877)  weight_decay: 0.0500 (0.0500)  time: 1.0044  data: 0.0009  max mem: 78493
Epoch: [129]  [300/312]  eta: 0:00:12  lr: 0.002662  min_lr: 0.002662  loss: 2.2057 (2.3806)  weight_decay: 0.0500 (0.0500)  time: 1.0017  data: 0.0003  max mem: 78493
Epoch: [129]  [310/312]  eta: 0:00:02  lr: 0.002661  min_lr: 0.002661  loss: 2.1039 (2.3738)  weight_decay: 0.0500 (0.0500)  time: 1.0011  data: 0.0003  max mem: 78493
Epoch: [129]  [311/312]  eta: 0:00:01  lr: 0.002661  min_lr: 0.002661  loss: 2.1039 (2.3727)  weight_decay: 0.0500 (0.0500)  time: 1.0011  data: 0.0001  max mem: 78493
Epoch: [129] Total time: 0:05:34 (1.0710 s / it)
Averaged stats: lr: 0.002661  min_lr: 0.002661  loss: 2.1039 (2.3471)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:10  loss: 0.7299 (0.7299)  acc1: 81.6406 (81.6406)  acc5: 96.3542 (96.3542)  time: 7.7929  data: 7.5273  max mem: 78493
Test:  [8/9]  eta: 0:00:01  loss: 1.0757 (0.9787)  acc1: 75.2604 (75.4240)  acc5: 91.0156 (92.3840)  time: 1.1182  data: 0.8906  max mem: 78493
Test: Total time: 0:00:10 (1.1292 s / it)
* Acc@1 75.430 Acc@5 92.666 loss 0.971
Accuracy of the model on the 50000 test images: 75.4%
Max accuracy: 75.43%
Epoch: [130]  [  0/312]  eta: 1:22:54  lr: 0.002661  min_lr: 0.002661  loss: 2.0817 (2.0817)  weight_decay: 0.0500 (0.0500)  time: 15.9450  data: 13.3639  max mem: 78493
Epoch: [130]  [ 10/312]  eta: 0:12:22  lr: 0.002660  min_lr: 0.002660  loss: 2.5089 (2.4685)  weight_decay: 0.0500 (0.0500)  time: 2.4571  data: 1.2263  max mem: 78493
Epoch: [130]  [ 20/312]  eta: 0:08:38  lr: 0.002660  min_lr: 0.002660  loss: 2.5089 (2.4423)  weight_decay: 0.0500 (0.0500)  time: 1.0689  data: 0.0066  max mem: 78493
Epoch: [130]  [ 30/312]  eta: 0:07:11  lr: 0.002659  min_lr: 0.002659  loss: 2.4110 (2.3807)  weight_decay: 0.0500 (0.0500)  time: 1.0190  data: 0.0005  max mem: 78493
Epoch: [130]  [ 40/312]  eta: 0:06:21  lr: 0.002658  min_lr: 0.002658  loss: 2.4110 (2.3713)  weight_decay: 0.0500 (0.0500)  time: 1.0093  data: 0.0004  max mem: 78493
Epoch: [130]  [ 50/312]  eta: 0:05:47  lr: 0.002657  min_lr: 0.002657  loss: 2.3897 (2.3596)  weight_decay: 0.0500 (0.0500)  time: 1.0109  data: 0.0004  max mem: 78493
Epoch: [130]  [ 60/312]  eta: 0:05:21  lr: 0.002657  min_lr: 0.002657  loss: 2.3888 (2.3538)  weight_decay: 0.0500 (0.0500)  time: 1.0107  data: 0.0004  max mem: 78493
Epoch: [130]  [ 70/312]  eta: 0:04:59  lr: 0.002656  min_lr: 0.002656  loss: 2.3840 (2.3361)  weight_decay: 0.0500 (0.0500)  time: 1.0101  data: 0.0004  max mem: 78493
Epoch: [130]  [ 80/312]  eta: 0:04:40  lr: 0.002655  min_lr: 0.002655  loss: 2.3703 (2.3322)  weight_decay: 0.0500 (0.0500)  time: 1.0097  data: 0.0004  max mem: 78493
Epoch: [130]  [ 90/312]  eta: 0:04:23  lr: 0.002655  min_lr: 0.002655  loss: 2.3915 (2.3293)  weight_decay: 0.0500 (0.0500)  time: 1.0076  data: 0.0004  max mem: 78493
Epoch: [130]  [100/312]  eta: 0:04:07  lr: 0.002654  min_lr: 0.002654  loss: 2.3453 (2.3281)  weight_decay: 0.0500 (0.0500)  time: 1.0072  data: 0.0005  max mem: 78493
Epoch: [130]  [110/312]  eta: 0:03:53  lr: 0.002653  min_lr: 0.002653  loss: 2.3467 (2.3400)  weight_decay: 0.0500 (0.0500)  time: 1.0079  data: 0.0005  max mem: 78493
Epoch: [130]  [120/312]  eta: 0:03:39  lr: 0.002653  min_lr: 0.002653  loss: 2.3064 (2.3307)  weight_decay: 0.0500 (0.0500)  time: 1.0084  data: 0.0005  max mem: 78493
Epoch: [130]  [130/312]  eta: 0:03:26  lr: 0.002652  min_lr: 0.002652  loss: 2.1774 (2.3194)  weight_decay: 0.0500 (0.0500)  time: 1.0090  data: 0.0005  max mem: 78493
Epoch: [130]  [140/312]  eta: 0:03:13  lr: 0.002651  min_lr: 0.002651  loss: 2.2275 (2.3129)  weight_decay: 0.0500 (0.0500)  time: 1.0083  data: 0.0005  max mem: 78493
Epoch: [130]  [150/312]  eta: 0:03:00  lr: 0.002651  min_lr: 0.002651  loss: 2.4201 (2.3123)  weight_decay: 0.0500 (0.0500)  time: 1.0085  data: 0.0005  max mem: 78493
Epoch: [130]  [160/312]  eta: 0:02:48  lr: 0.002650  min_lr: 0.002650  loss: 2.4421 (2.3224)  weight_decay: 0.0500 (0.0500)  time: 1.0076  data: 0.0005  max mem: 78493
Epoch: [130]  [170/312]  eta: 0:02:36  lr: 0.002649  min_lr: 0.002649  loss: 2.4502 (2.3289)  weight_decay: 0.0500 (0.0500)  time: 1.0055  data: 0.0004  max mem: 78493
Epoch: [130]  [180/312]  eta: 0:02:24  lr: 0.002649  min_lr: 0.002649  loss: 2.3040 (2.3261)  weight_decay: 0.0500 (0.0500)  time: 1.0071  data: 0.0004  max mem: 78493
Epoch: [130]  [190/312]  eta: 0:02:13  lr: 0.002648  min_lr: 0.002648  loss: 2.4614 (2.3319)  weight_decay: 0.0500 (0.0500)  time: 1.0069  data: 0.0004  max mem: 78493
Epoch: [130]  [200/312]  eta: 0:02:01  lr: 0.002647  min_lr: 0.002647  loss: 2.5285 (2.3291)  weight_decay: 0.0500 (0.0500)  time: 1.0051  data: 0.0004  max mem: 78493
Epoch: [130]  [210/312]  eta: 0:01:50  lr: 0.002647  min_lr: 0.002647  loss: 2.1635 (2.3229)  weight_decay: 0.0500 (0.0500)  time: 1.0072  data: 0.0004  max mem: 78493
Epoch: [130]  [220/312]  eta: 0:01:39  lr: 0.002646  min_lr: 0.002646  loss: 2.2554 (2.3221)  weight_decay: 0.0500 (0.0500)  time: 1.0076  data: 0.0004  max mem: 78493
Epoch: [130]  [230/312]  eta: 0:01:28  lr: 0.002645  min_lr: 0.002645  loss: 2.2831 (2.3180)  weight_decay: 0.0500 (0.0500)  time: 1.0076  data: 0.0005  max mem: 78493
Epoch: [130]  [240/312]  eta: 0:01:17  lr: 0.002645  min_lr: 0.002645  loss: 2.2722 (2.3163)  weight_decay: 0.0500 (0.0500)  time: 1.0077  data: 0.0005  max mem: 78493
Epoch: [130]  [250/312]  eta: 0:01:06  lr: 0.002644  min_lr: 0.002644  loss: 2.4278 (2.3199)  weight_decay: 0.0500 (0.0500)  time: 1.0054  data: 0.0011  max mem: 78493
Epoch: [130]  [260/312]  eta: 0:00:55  lr: 0.002643  min_lr: 0.002643  loss: 2.4134 (2.3194)  weight_decay: 0.0500 (0.0500)  time: 1.0053  data: 0.0011  max mem: 78493
Epoch: [130]  [270/312]  eta: 0:00:44  lr: 0.002643  min_lr: 0.002643  loss: 2.1973 (2.3130)  weight_decay: 0.0500 (0.0500)  time: 1.0057  data: 0.0004  max mem: 78493
Epoch: [130]  [280/312]  eta: 0:00:34  lr: 0.002642  min_lr: 0.002642  loss: 2.0841 (2.3053)  weight_decay: 0.0500 (0.0500)  time: 1.0063  data: 0.0010  max mem: 78493
Epoch: [130]  [290/312]  eta: 0:00:23  lr: 0.002641  min_lr: 0.002641  loss: 2.2035 (2.3040)  weight_decay: 0.0500 (0.0500)  time: 1.0049  data: 0.0009  max mem: 78493
Epoch: [130]  [300/312]  eta: 0:00:12  lr: 0.002640  min_lr: 0.002640  loss: 2.3788 (2.3095)  weight_decay: 0.0500 (0.0500)  time: 1.0017  data: 0.0001  max mem: 78493
Epoch: [130]  [310/312]  eta: 0:00:02  lr: 0.002640  min_lr: 0.002640  loss: 2.5310 (2.3147)  weight_decay: 0.0500 (0.0500)  time: 1.0016  data: 0.0001  max mem: 78493
Epoch: [130]  [311/312]  eta: 0:00:01  lr: 0.002640  min_lr: 0.002640  loss: 2.5310 (2.3154)  weight_decay: 0.0500 (0.0500)  time: 1.0016  data: 0.0001  max mem: 78493
Epoch: [130] Total time: 0:05:32 (1.0644 s / it)
Averaged stats: lr: 0.002640  min_lr: 0.002640  loss: 2.5310 (2.3450)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:10  loss: 0.6665 (0.6665)  acc1: 82.9427 (82.9427)  acc5: 95.7031 (95.7031)  time: 7.8547  data: 7.5822  max mem: 78493
Test:  [8/9]  eta: 0:00:01  loss: 1.0475 (0.9700)  acc1: 74.0885 (75.1840)  acc5: 93.0990 (92.8160)  time: 1.0741  data: 0.8428  max mem: 78493
Test: Total time: 0:00:09 (1.0857 s / it)
* Acc@1 75.640 Acc@5 92.692 loss 0.957
Accuracy of the model on the 50000 test images: 75.6%
Max accuracy: 75.64%
Epoch: [131]  [  0/312]  eta: 1:20:02  lr: 0.002640  min_lr: 0.002640  loss: 1.7116 (1.7116)  weight_decay: 0.0500 (0.0500)  time: 15.3934  data: 12.8914  max mem: 78493
Epoch: [131]  [ 10/312]  eta: 0:13:05  lr: 0.002639  min_lr: 0.002639  loss: 2.2663 (2.2216)  weight_decay: 0.0500 (0.0500)  time: 2.6006  data: 1.4325  max mem: 78493
Epoch: [131]  [ 20/312]  eta: 0:08:58  lr: 0.002638  min_lr: 0.002638  loss: 2.1836 (2.1617)  weight_decay: 0.0500 (0.0500)  time: 1.1659  data: 0.1435  max mem: 78493
Epoch: [131]  [ 30/312]  eta: 0:07:23  lr: 0.002638  min_lr: 0.002638  loss: 2.3264 (2.2686)  weight_decay: 0.0500 (0.0500)  time: 1.0076  data: 0.0005  max mem: 78493
Epoch: [131]  [ 40/312]  eta: 0:06:30  lr: 0.002637  min_lr: 0.002637  loss: 2.4675 (2.2374)  weight_decay: 0.0500 (0.0500)  time: 1.0045  data: 0.0005  max mem: 78493
Epoch: [131]  [ 50/312]  eta: 0:05:53  lr: 0.002636  min_lr: 0.002636  loss: 2.2890 (2.2634)  weight_decay: 0.0500 (0.0500)  time: 1.0049  data: 0.0005  max mem: 78493
Epoch: [131]  [ 60/312]  eta: 0:05:26  lr: 0.002636  min_lr: 0.002636  loss: 2.2890 (2.2686)  weight_decay: 0.0500 (0.0500)  time: 1.0060  data: 0.0005  max mem: 78493
Epoch: [131]  [ 70/312]  eta: 0:05:03  lr: 0.002635  min_lr: 0.002635  loss: 2.1085 (2.2486)  weight_decay: 0.0500 (0.0500)  time: 1.0098  data: 0.0004  max mem: 78493
Epoch: [131]  [ 80/312]  eta: 0:04:44  lr: 0.002634  min_lr: 0.002634  loss: 2.2374 (2.2528)  weight_decay: 0.0500 (0.0500)  time: 1.0134  data: 0.0004  max mem: 78493
Epoch: [131]  [ 90/312]  eta: 0:04:26  lr: 0.002634  min_lr: 0.002634  loss: 2.2558 (2.2575)  weight_decay: 0.0500 (0.0500)  time: 1.0134  data: 0.0004  max mem: 78493
Epoch: [131]  [100/312]  eta: 0:04:10  lr: 0.002633  min_lr: 0.002633  loss: 2.2175 (2.2615)  weight_decay: 0.0500 (0.0500)  time: 1.0124  data: 0.0004  max mem: 78493
Epoch: [131]  [110/312]  eta: 0:03:55  lr: 0.002632  min_lr: 0.002632  loss: 2.3930 (2.2720)  weight_decay: 0.0500 (0.0500)  time: 1.0100  data: 0.0004  max mem: 78493
Epoch: [131]  [120/312]  eta: 0:03:41  lr: 0.002631  min_lr: 0.002631  loss: 2.4736 (2.2831)  weight_decay: 0.0500 (0.0500)  time: 1.0071  data: 0.0005  max mem: 78493
Epoch: [131]  [130/312]  eta: 0:03:27  lr: 0.002631  min_lr: 0.002631  loss: 2.3620 (2.2859)  weight_decay: 0.0500 (0.0500)  time: 1.0065  data: 0.0005  max mem: 78493
Epoch: [131]  [140/312]  eta: 0:03:14  lr: 0.002630  min_lr: 0.002630  loss: 2.3476 (2.2953)  weight_decay: 0.0500 (0.0500)  time: 1.0072  data: 0.0004  max mem: 78493
Epoch: [131]  [150/312]  eta: 0:03:02  lr: 0.002629  min_lr: 0.002629  loss: 2.4221 (2.3007)  weight_decay: 0.0500 (0.0500)  time: 1.0069  data: 0.0005  max mem: 78493
Epoch: [131]  [160/312]  eta: 0:02:49  lr: 0.002629  min_lr: 0.002629  loss: 2.4561 (2.3110)  weight_decay: 0.0500 (0.0500)  time: 1.0057  data: 0.0005  max mem: 78493
Epoch: [131]  [170/312]  eta: 0:02:37  lr: 0.002628  min_lr: 0.002628  loss: 2.4606 (2.3093)  weight_decay: 0.0500 (0.0500)  time: 1.0049  data: 0.0005  max mem: 78493
Epoch: [131]  [180/312]  eta: 0:02:25  lr: 0.002627  min_lr: 0.002627  loss: 2.4185 (2.3120)  weight_decay: 0.0500 (0.0500)  time: 1.0048  data: 0.0005  max mem: 78493
Epoch: [131]  [190/312]  eta: 0:02:14  lr: 0.002627  min_lr: 0.002627  loss: 2.2555 (2.3099)  weight_decay: 0.0500 (0.0500)  time: 1.0046  data: 0.0005  max mem: 78493
Epoch: [131]  [200/312]  eta: 0:02:02  lr: 0.002626  min_lr: 0.002626  loss: 2.3495 (2.3179)  weight_decay: 0.0500 (0.0500)  time: 1.0061  data: 0.0004  max mem: 78493
Epoch: [131]  [210/312]  eta: 0:01:51  lr: 0.002625  min_lr: 0.002625  loss: 2.4605 (2.3204)  weight_decay: 0.0500 (0.0500)  time: 1.0065  data: 0.0005  max mem: 78493
Epoch: [131]  [220/312]  eta: 0:01:39  lr: 0.002625  min_lr: 0.002625  loss: 2.5284 (2.3252)  weight_decay: 0.0500 (0.0500)  time: 1.0062  data: 0.0005  max mem: 78493
Epoch: [131]  [230/312]  eta: 0:01:28  lr: 0.002624  min_lr: 0.002624  loss: 2.4422 (2.3291)  weight_decay: 0.0500 (0.0500)  time: 1.0077  data: 0.0005  max mem: 78493
Epoch: [131]  [240/312]  eta: 0:01:17  lr: 0.002623  min_lr: 0.002623  loss: 2.4064 (2.3351)  weight_decay: 0.0500 (0.0500)  time: 1.0066  data: 0.0005  max mem: 78493
Epoch: [131]  [250/312]  eta: 0:01:06  lr: 0.002623  min_lr: 0.002623  loss: 2.5638 (2.3378)  weight_decay: 0.0500 (0.0500)  time: 1.0051  data: 0.0005  max mem: 78493
Epoch: [131]  [260/312]  eta: 0:00:55  lr: 0.002622  min_lr: 0.002622  loss: 2.4945 (2.3407)  weight_decay: 0.0500 (0.0500)  time: 1.0052  data: 0.0005  max mem: 78493
Epoch: [131]  [270/312]  eta: 0:00:45  lr: 0.002621  min_lr: 0.002621  loss: 2.5036 (2.3506)  weight_decay: 0.0500 (0.0500)  time: 1.0054  data: 0.0004  max mem: 78493
Epoch: [131]  [280/312]  eta: 0:00:34  lr: 0.002621  min_lr: 0.002621  loss: 2.5270 (2.3543)  weight_decay: 0.0500 (0.0500)  time: 1.0067  data: 0.0011  max mem: 78493
Epoch: [131]  [290/312]  eta: 0:00:23  lr: 0.002620  min_lr: 0.002620  loss: 2.4480 (2.3525)  weight_decay: 0.0500 (0.0500)  time: 1.0049  data: 0.0009  max mem: 78493
Epoch: [131]  [300/312]  eta: 0:00:12  lr: 0.002619  min_lr: 0.002619  loss: 2.4711 (2.3516)  weight_decay: 0.0500 (0.0500)  time: 1.0021  data: 0.0001  max mem: 78493
Epoch: [131]  [310/312]  eta: 0:00:02  lr: 0.002619  min_lr: 0.002619  loss: 2.3798 (2.3513)  weight_decay: 0.0500 (0.0500)  time: 1.0020  data: 0.0001  max mem: 78493
Epoch: [131]  [311/312]  eta: 0:00:01  lr: 0.002618  min_lr: 0.002618  loss: 2.3798 (2.3519)  weight_decay: 0.0500 (0.0500)  time: 1.0020  data: 0.0001  max mem: 78493
Epoch: [131] Total time: 0:05:33 (1.0684 s / it)
Averaged stats: lr: 0.002618  min_lr: 0.002618  loss: 2.3798 (2.3254)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:18  loss: 0.7122 (0.7122)  acc1: 82.2917 (82.2917)  acc5: 95.9635 (95.9635)  time: 8.6848  data: 8.4244  max mem: 78493
Test:  [8/9]  eta: 0:00:01  loss: 1.0650 (0.9490)  acc1: 74.4792 (75.7440)  acc5: 92.8385 (93.0720)  time: 1.1698  data: 0.9361  max mem: 78493
Test: Total time: 0:00:10 (1.2103 s / it)
* Acc@1 75.898 Acc@5 92.972 loss 0.944
Accuracy of the model on the 50000 test images: 75.9%
Max accuracy: 75.90%
Epoch: [132]  [  0/312]  eta: 1:23:29  lr: 0.002618  min_lr: 0.002618  loss: 1.7961 (1.7961)  weight_decay: 0.0500 (0.0500)  time: 16.0575  data: 12.4582  max mem: 78493
Epoch: [132]  [ 10/312]  eta: 0:12:44  lr: 0.002618  min_lr: 0.002618  loss: 2.2968 (2.2817)  weight_decay: 0.0500 (0.0500)  time: 2.5320  data: 1.2532  max mem: 78493
Epoch: [132]  [ 20/312]  eta: 0:08:51  lr: 0.002617  min_lr: 0.002617  loss: 2.3258 (2.3111)  weight_decay: 0.0500 (0.0500)  time: 1.1079  data: 0.0686  max mem: 78493
Epoch: [132]  [ 30/312]  eta: 0:07:19  lr: 0.002616  min_lr: 0.002616  loss: 2.4329 (2.3273)  weight_decay: 0.0500 (0.0500)  time: 1.0245  data: 0.0024  max mem: 78493
Epoch: [132]  [ 40/312]  eta: 0:06:27  lr: 0.002616  min_lr: 0.002616  loss: 2.1252 (2.2777)  weight_decay: 0.0500 (0.0500)  time: 1.0110  data: 0.0004  max mem: 78493
Epoch: [132]  [ 50/312]  eta: 0:05:52  lr: 0.002615  min_lr: 0.002615  loss: 2.1601 (2.2675)  weight_decay: 0.0500 (0.0500)  time: 1.0097  data: 0.0004  max mem: 78493
Epoch: [132]  [ 60/312]  eta: 0:05:24  lr: 0.002614  min_lr: 0.002614  loss: 2.3169 (2.2610)  weight_decay: 0.0500 (0.0500)  time: 1.0101  data: 0.0004  max mem: 78493
Epoch: [132]  [ 70/312]  eta: 0:05:02  lr: 0.002614  min_lr: 0.002614  loss: 2.3169 (2.2512)  weight_decay: 0.0500 (0.0500)  time: 1.0104  data: 0.0004  max mem: 78493
Epoch: [132]  [ 80/312]  eta: 0:04:43  lr: 0.002613  min_lr: 0.002613  loss: 2.2728 (2.2492)  weight_decay: 0.0500 (0.0500)  time: 1.0096  data: 0.0004  max mem: 78493
Epoch: [132]  [ 90/312]  eta: 0:04:25  lr: 0.002612  min_lr: 0.002612  loss: 2.3869 (2.2720)  weight_decay: 0.0500 (0.0500)  time: 1.0093  data: 0.0004  max mem: 78493
Epoch: [132]  [100/312]  eta: 0:04:09  lr: 0.002612  min_lr: 0.002612  loss: 2.5368 (2.3045)  weight_decay: 0.0500 (0.0500)  time: 1.0092  data: 0.0004  max mem: 78493
Epoch: [132]  [110/312]  eta: 0:03:54  lr: 0.002611  min_lr: 0.002611  loss: 2.5417 (2.3166)  weight_decay: 0.0500 (0.0500)  time: 1.0074  data: 0.0005  max mem: 78493
Epoch: [132]  [120/312]  eta: 0:03:40  lr: 0.002610  min_lr: 0.002610  loss: 2.4899 (2.3208)  weight_decay: 0.0500 (0.0500)  time: 1.0062  data: 0.0005  max mem: 78493
Epoch: [132]  [130/312]  eta: 0:03:27  lr: 0.002609  min_lr: 0.002609  loss: 2.4434 (2.3184)  weight_decay: 0.0500 (0.0500)  time: 1.0084  data: 0.0005  max mem: 78493
Epoch: [132]  [140/312]  eta: 0:03:14  lr: 0.002609  min_lr: 0.002609  loss: 2.3379 (2.3126)  weight_decay: 0.0500 (0.0500)  time: 1.0080  data: 0.0004  max mem: 78493
Epoch: [132]  [150/312]  eta: 0:03:01  lr: 0.002608  min_lr: 0.002608  loss: 2.3379 (2.3110)  weight_decay: 0.0500 (0.0500)  time: 1.0072  data: 0.0004  max mem: 78493
Epoch: [132]  [160/312]  eta: 0:02:49  lr: 0.002607  min_lr: 0.002607  loss: 2.2628 (2.3005)  weight_decay: 0.0500 (0.0500)  time: 1.0078  data: 0.0005  max mem: 78493
Epoch: [132]  [170/312]  eta: 0:02:37  lr: 0.002607  min_lr: 0.002607  loss: 2.2628 (2.2965)  weight_decay: 0.0500 (0.0500)  time: 1.0078  data: 0.0004  max mem: 78493
Epoch: [132]  [180/312]  eta: 0:02:25  lr: 0.002606  min_lr: 0.002606  loss: 2.4476 (2.3053)  weight_decay: 0.0500 (0.0500)  time: 1.0084  data: 0.0004  max mem: 78493
Epoch: [132]  [190/312]  eta: 0:02:13  lr: 0.002605  min_lr: 0.002605  loss: 2.5606 (2.3138)  weight_decay: 0.0500 (0.0500)  time: 1.0070  data: 0.0005  max mem: 78493
Epoch: [132]  [200/312]  eta: 0:02:02  lr: 0.002605  min_lr: 0.002605  loss: 2.4267 (2.3151)  weight_decay: 0.0500 (0.0500)  time: 1.0065  data: 0.0005  max mem: 78493
Epoch: [132]  [210/312]  eta: 0:01:51  lr: 0.002604  min_lr: 0.002604  loss: 2.3672 (2.3175)  weight_decay: 0.0500 (0.0500)  time: 1.0064  data: 0.0004  max mem: 78493
Epoch: [132]  [220/312]  eta: 0:01:39  lr: 0.002603  min_lr: 0.002603  loss: 2.3519 (2.3168)  weight_decay: 0.0500 (0.0500)  time: 1.0060  data: 0.0004  max mem: 78493
Epoch: [132]  [230/312]  eta: 0:01:28  lr: 0.002603  min_lr: 0.002603  loss: 2.3519 (2.3201)  weight_decay: 0.0500 (0.0500)  time: 1.0062  data: 0.0004  max mem: 78493
Epoch: [132]  [240/312]  eta: 0:01:17  lr: 0.002602  min_lr: 0.002602  loss: 2.1912 (2.3115)  weight_decay: 0.0500 (0.0500)  time: 1.0060  data: 0.0004  max mem: 78493
Epoch: [132]  [250/312]  eta: 0:01:06  lr: 0.002601  min_lr: 0.002601  loss: 2.1912 (2.3135)  weight_decay: 0.0500 (0.0500)  time: 1.0073  data: 0.0004  max mem: 78493
Epoch: [132]  [260/312]  eta: 0:00:55  lr: 0.002601  min_lr: 0.002601  loss: 2.3525 (2.3182)  weight_decay: 0.0500 (0.0500)  time: 1.0072  data: 0.0004  max mem: 78493
Epoch: [132]  [270/312]  eta: 0:00:44  lr: 0.002600  min_lr: 0.002600  loss: 2.4825 (2.3172)  weight_decay: 0.0500 (0.0500)  time: 1.0050  data: 0.0004  max mem: 78493
Epoch: [132]  [280/312]  eta: 0:00:34  lr: 0.002599  min_lr: 0.002599  loss: 2.2734 (2.3095)  weight_decay: 0.0500 (0.0500)  time: 1.0054  data: 0.0011  max mem: 78493
Epoch: [132]  [290/312]  eta: 0:00:23  lr: 0.002599  min_lr: 0.002599  loss: 2.2342 (2.3094)  weight_decay: 0.0500 (0.0500)  time: 1.0043  data: 0.0009  max mem: 78493
Epoch: [132]  [300/312]  eta: 0:00:12  lr: 0.002598  min_lr: 0.002598  loss: 2.3303 (2.3106)  weight_decay: 0.0500 (0.0500)  time: 1.0024  data: 0.0001  max mem: 78493
Epoch: [132]  [310/312]  eta: 0:00:02  lr: 0.002597  min_lr: 0.002597  loss: 2.3778 (2.3105)  weight_decay: 0.0500 (0.0500)  time: 1.0026  data: 0.0001  max mem: 78493
Epoch: [132]  [311/312]  eta: 0:00:01  lr: 0.002597  min_lr: 0.002597  loss: 2.3778 (2.3111)  weight_decay: 0.0500 (0.0500)  time: 1.0025  data: 0.0001  max mem: 78493
Epoch: [132] Total time: 0:05:33 (1.0677 s / it)
Averaged stats: lr: 0.002597  min_lr: 0.002597  loss: 2.3778 (2.3397)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:19  loss: 0.7428 (0.7428)  acc1: 80.8594 (80.8594)  acc5: 95.3125 (95.3125)  time: 8.8058  data: 8.5251  max mem: 78493
Test:  [8/9]  eta: 0:00:01  loss: 1.0895 (0.9959)  acc1: 73.1771 (74.0160)  acc5: 92.1875 (92.5920)  time: 1.1766  data: 0.9473  max mem: 78493
Test: Total time: 0:00:10 (1.1928 s / it)
* Acc@1 74.570 Acc@5 92.458 loss 0.993
Accuracy of the model on the 50000 test images: 74.6%
Max accuracy: 75.90%
Epoch: [133]  [  0/312]  eta: 1:23:04  lr: 0.002597  min_lr: 0.002597  loss: 1.5341 (1.5341)  weight_decay: 0.0500 (0.0500)  time: 15.9745  data: 14.9341  max mem: 78493
Epoch: [133]  [ 10/312]  eta: 0:13:29  lr: 0.002596  min_lr: 0.002596  loss: 2.3111 (2.1801)  weight_decay: 0.0500 (0.0500)  time: 2.6801  data: 1.3608  max mem: 78493
Epoch: [133]  [ 20/312]  eta: 0:09:11  lr: 0.002596  min_lr: 0.002596  loss: 2.4697 (2.2872)  weight_decay: 0.0500 (0.0500)  time: 1.1832  data: 0.0020  max mem: 78493
Epoch: [133]  [ 30/312]  eta: 0:07:32  lr: 0.002595  min_lr: 0.002595  loss: 2.4407 (2.2390)  weight_decay: 0.0500 (0.0500)  time: 1.0116  data: 0.0004  max mem: 78493
Epoch: [133]  [ 40/312]  eta: 0:06:36  lr: 0.002594  min_lr: 0.002594  loss: 2.3651 (2.2551)  weight_decay: 0.0500 (0.0500)  time: 1.0073  data: 0.0004  max mem: 78493
Epoch: [133]  [ 50/312]  eta: 0:05:59  lr: 0.002594  min_lr: 0.002594  loss: 2.3651 (2.2516)  weight_decay: 0.0500 (0.0500)  time: 1.0102  data: 0.0005  max mem: 78493
Epoch: [133]  [ 60/312]  eta: 0:05:30  lr: 0.002593  min_lr: 0.002593  loss: 2.3263 (2.2655)  weight_decay: 0.0500 (0.0500)  time: 1.0102  data: 0.0005  max mem: 78493
Epoch: [133]  [ 70/312]  eta: 0:05:06  lr: 0.002592  min_lr: 0.002592  loss: 2.5012 (2.3140)  weight_decay: 0.0500 (0.0500)  time: 1.0069  data: 0.0004  max mem: 78493
Epoch: [133]  [ 80/312]  eta: 0:04:46  lr: 0.002592  min_lr: 0.002592  loss: 2.4733 (2.3229)  weight_decay: 0.0500 (0.0500)  time: 1.0076  data: 0.0005  max mem: 78493
Epoch: [133]  [ 90/312]  eta: 0:04:28  lr: 0.002591  min_lr: 0.002591  loss: 2.4335 (2.3349)  weight_decay: 0.0500 (0.0500)  time: 1.0082  data: 0.0005  max mem: 78493
Epoch: [133]  [100/312]  eta: 0:04:12  lr: 0.002590  min_lr: 0.002590  loss: 2.4745 (2.3359)  weight_decay: 0.0500 (0.0500)  time: 1.0074  data: 0.0004  max mem: 78493
Epoch: [133]  [110/312]  eta: 0:03:57  lr: 0.002589  min_lr: 0.002589  loss: 2.2673 (2.3154)  weight_decay: 0.0500 (0.0500)  time: 1.0066  data: 0.0004  max mem: 78493
Epoch: [133]  [120/312]  eta: 0:03:42  lr: 0.002589  min_lr: 0.002589  loss: 2.2221 (2.3147)  weight_decay: 0.0500 (0.0500)  time: 1.0051  data: 0.0004  max mem: 78493
Epoch: [133]  [130/312]  eta: 0:03:29  lr: 0.002588  min_lr: 0.002588  loss: 2.3709 (2.3181)  weight_decay: 0.0500 (0.0500)  time: 1.0043  data: 0.0004  max mem: 78493
Epoch: [133]  [140/312]  eta: 0:03:15  lr: 0.002587  min_lr: 0.002587  loss: 2.3094 (2.3087)  weight_decay: 0.0500 (0.0500)  time: 1.0058  data: 0.0004  max mem: 78493
Epoch: [133]  [150/312]  eta: 0:03:02  lr: 0.002587  min_lr: 0.002587  loss: 2.1846 (2.2936)  weight_decay: 0.0500 (0.0500)  time: 1.0061  data: 0.0004  max mem: 78493
Epoch: [133]  [160/312]  eta: 0:02:50  lr: 0.002586  min_lr: 0.002586  loss: 2.1925 (2.2981)  weight_decay: 0.0500 (0.0500)  time: 1.0045  data: 0.0004  max mem: 78493
Epoch: [133]  [170/312]  eta: 0:02:38  lr: 0.002585  min_lr: 0.002585  loss: 2.4746 (2.2980)  weight_decay: 0.0500 (0.0500)  time: 1.0045  data: 0.0004  max mem: 78493
Epoch: [133]  [180/312]  eta: 0:02:26  lr: 0.002585  min_lr: 0.002585  loss: 2.4746 (2.2997)  weight_decay: 0.0500 (0.0500)  time: 1.0048  data: 0.0004  max mem: 78493
Epoch: [133]  [190/312]  eta: 0:02:14  lr: 0.002584  min_lr: 0.002584  loss: 2.3778 (2.2953)  weight_decay: 0.0500 (0.0500)  time: 1.0045  data: 0.0004  max mem: 78493
Epoch: [133]  [200/312]  eta: 0:02:03  lr: 0.002583  min_lr: 0.002583  loss: 2.3568 (2.3010)  weight_decay: 0.0500 (0.0500)  time: 1.0050  data: 0.0004  max mem: 78493
Epoch: [133]  [210/312]  eta: 0:01:51  lr: 0.002583  min_lr: 0.002583  loss: 2.3217 (2.2967)  weight_decay: 0.0500 (0.0500)  time: 1.0053  data: 0.0004  max mem: 78493
Epoch: [133]  [220/312]  eta: 0:01:40  lr: 0.002582  min_lr: 0.002582  loss: 2.2046 (2.2973)  weight_decay: 0.0500 (0.0500)  time: 1.0049  data: 0.0004  max mem: 78493
Epoch: [133]  [230/312]  eta: 0:01:29  lr: 0.002581  min_lr: 0.002581  loss: 2.2446 (2.2955)  weight_decay: 0.0500 (0.0500)  time: 1.0051  data: 0.0004  max mem: 78493
Epoch: [133]  [240/312]  eta: 0:01:17  lr: 0.002581  min_lr: 0.002581  loss: 2.4243 (2.2947)  weight_decay: 0.0500 (0.0500)  time: 1.0053  data: 0.0005  max mem: 78493
Epoch: [133]  [250/312]  eta: 0:01:06  lr: 0.002580  min_lr: 0.002580  loss: 2.4278 (2.2956)  weight_decay: 0.0500 (0.0500)  time: 1.0046  data: 0.0005  max mem: 78493
Epoch: [133]  [260/312]  eta: 0:00:56  lr: 0.002579  min_lr: 0.002579  loss: 2.3162 (2.2899)  weight_decay: 0.0500 (0.0500)  time: 1.0041  data: 0.0004  max mem: 78493
Epoch: [133]  [270/312]  eta: 0:00:45  lr: 0.002578  min_lr: 0.002578  loss: 2.2300 (2.2912)  weight_decay: 0.0500 (0.0500)  time: 1.0041  data: 0.0004  max mem: 78493
Epoch: [133]  [280/312]  eta: 0:00:34  lr: 0.002578  min_lr: 0.002578  loss: 2.2300 (2.2874)  weight_decay: 0.0500 (0.0500)  time: 1.0051  data: 0.0011  max mem: 78493
Epoch: [133]  [290/312]  eta: 0:00:23  lr: 0.002577  min_lr: 0.002577  loss: 2.4440 (2.2904)  weight_decay: 0.0500 (0.0500)  time: 1.0043  data: 0.0009  max mem: 78493
Epoch: [133]  [300/312]  eta: 0:00:12  lr: 0.002576  min_lr: 0.002576  loss: 2.4859 (2.2916)  weight_decay: 0.0500 (0.0500)  time: 1.0022  data: 0.0001  max mem: 78493
Epoch: [133]  [310/312]  eta: 0:00:02  lr: 0.002576  min_lr: 0.002576  loss: 2.2696 (2.2899)  weight_decay: 0.0500 (0.0500)  time: 1.0022  data: 0.0001  max mem: 78493
Epoch: [133]  [311/312]  eta: 0:00:01  lr: 0.002576  min_lr: 0.002576  loss: 2.3036 (2.2899)  weight_decay: 0.0500 (0.0500)  time: 1.0023  data: 0.0001  max mem: 78493
Epoch: [133] Total time: 0:05:34 (1.0708 s / it)
Averaged stats: lr: 0.002576  min_lr: 0.002576  loss: 2.3036 (2.3128)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:14  loss: 0.7263 (0.7263)  acc1: 82.2917 (82.2917)  acc5: 95.4427 (95.4427)  time: 8.3322  data: 8.0410  max mem: 78493
Test:  [8/9]  eta: 0:00:01  loss: 1.0359 (0.9598)  acc1: 76.4323 (75.4720)  acc5: 92.9688 (92.4960)  time: 1.1240  data: 0.8935  max mem: 78493
Test: Total time: 0:00:10 (1.1379 s / it)
* Acc@1 75.552 Acc@5 92.738 loss 0.950
Accuracy of the model on the 50000 test images: 75.6%
Max accuracy: 75.90%
Epoch: [134]  [  0/312]  eta: 1:21:20  lr: 0.002576  min_lr: 0.002576  loss: 2.8568 (2.8568)  weight_decay: 0.0500 (0.0500)  time: 15.6435  data: 13.8517  max mem: 78493
Epoch: [134]  [ 10/312]  eta: 0:12:32  lr: 0.002575  min_lr: 0.002575  loss: 2.4135 (2.2618)  weight_decay: 0.0500 (0.0500)  time: 2.4921  data: 1.2599  max mem: 78493
Epoch: [134]  [ 20/312]  eta: 0:08:44  lr: 0.002574  min_lr: 0.002574  loss: 2.3619 (2.1910)  weight_decay: 0.0500 (0.0500)  time: 1.1047  data: 0.0027  max mem: 78493
Epoch: [134]  [ 30/312]  eta: 0:07:15  lr: 0.002573  min_lr: 0.002573  loss: 2.0058 (2.1599)  weight_decay: 0.0500 (0.0500)  time: 1.0210  data: 0.0026  max mem: 78493
Epoch: [134]  [ 40/312]  eta: 0:06:24  lr: 0.002573  min_lr: 0.002573  loss: 2.1767 (2.2065)  weight_decay: 0.0500 (0.0500)  time: 1.0094  data: 0.0004  max mem: 78493
Epoch: [134]  [ 50/312]  eta: 0:05:49  lr: 0.002572  min_lr: 0.002572  loss: 2.3544 (2.2219)  weight_decay: 0.0500 (0.0500)  time: 1.0076  data: 0.0005  max mem: 78493
Epoch: [134]  [ 60/312]  eta: 0:05:22  lr: 0.002571  min_lr: 0.002571  loss: 2.3599 (2.2292)  weight_decay: 0.0500 (0.0500)  time: 1.0058  data: 0.0004  max mem: 78493
Epoch: [134]  [ 70/312]  eta: 0:05:00  lr: 0.002571  min_lr: 0.002571  loss: 2.3113 (2.2442)  weight_decay: 0.0500 (0.0500)  time: 1.0049  data: 0.0004  max mem: 78493
Epoch: [134]  [ 80/312]  eta: 0:04:41  lr: 0.002570  min_lr: 0.002570  loss: 2.3407 (2.2497)  weight_decay: 0.0500 (0.0500)  time: 1.0054  data: 0.0005  max mem: 78493
Epoch: [134]  [ 90/312]  eta: 0:04:23  lr: 0.002569  min_lr: 0.002569  loss: 2.3594 (2.2536)  weight_decay: 0.0500 (0.0500)  time: 1.0062  data: 0.0004  max mem: 78493
Epoch: [134]  [100/312]  eta: 0:04:08  lr: 0.002569  min_lr: 0.002569  loss: 2.5638 (2.2901)  weight_decay: 0.0500 (0.0500)  time: 1.0078  data: 0.0004  max mem: 78493
Epoch: [134]  [110/312]  eta: 0:03:53  lr: 0.002568  min_lr: 0.002568  loss: 2.5804 (2.2904)  weight_decay: 0.0500 (0.0500)  time: 1.0093  data: 0.0004  max mem: 78493
Epoch: [134]  [120/312]  eta: 0:03:39  lr: 0.002567  min_lr: 0.002567  loss: 2.2432 (2.2893)  weight_decay: 0.0500 (0.0500)  time: 1.0096  data: 0.0004  max mem: 78493
Epoch: [134]  [130/312]  eta: 0:03:26  lr: 0.002567  min_lr: 0.002567  loss: 2.2113 (2.2810)  weight_decay: 0.0500 (0.0500)  time: 1.0086  data: 0.0004  max mem: 78493
Epoch: [134]  [140/312]  eta: 0:03:13  lr: 0.002566  min_lr: 0.002566  loss: 2.2742 (2.2881)  weight_decay: 0.0500 (0.0500)  time: 1.0057  data: 0.0004  max mem: 78493
Epoch: [134]  [150/312]  eta: 0:03:00  lr: 0.002565  min_lr: 0.002565  loss: 2.3801 (2.3034)  weight_decay: 0.0500 (0.0500)  time: 1.0060  data: 0.0005  max mem: 78493
Epoch: [134]  [160/312]  eta: 0:02:48  lr: 0.002565  min_lr: 0.002565  loss: 2.3808 (2.3063)  weight_decay: 0.0500 (0.0500)  time: 1.0064  data: 0.0004  max mem: 78493
Epoch: [134]  [170/312]  eta: 0:02:36  lr: 0.002564  min_lr: 0.002564  loss: 2.4364 (2.3037)  weight_decay: 0.0500 (0.0500)  time: 1.0064  data: 0.0005  max mem: 78493
Epoch: [134]  [180/312]  eta: 0:02:25  lr: 0.002563  min_lr: 0.002563  loss: 2.5127 (2.3216)  weight_decay: 0.0500 (0.0500)  time: 1.0067  data: 0.0005  max mem: 78493
Epoch: [134]  [190/312]  eta: 0:02:13  lr: 0.002562  min_lr: 0.002562  loss: 2.5796 (2.3202)  weight_decay: 0.0500 (0.0500)  time: 1.0065  data: 0.0004  max mem: 78493
Epoch: [134]  [200/312]  eta: 0:02:02  lr: 0.002562  min_lr: 0.002562  loss: 2.3383 (2.3237)  weight_decay: 0.0500 (0.0500)  time: 1.0064  data: 0.0004  max mem: 78493
Epoch: [134]  [210/312]  eta: 0:01:50  lr: 0.002561  min_lr: 0.002561  loss: 2.3383 (2.3192)  weight_decay: 0.0500 (0.0500)  time: 1.0062  data: 0.0004  max mem: 78493
Epoch: [134]  [220/312]  eta: 0:01:39  lr: 0.002560  min_lr: 0.002560  loss: 2.3348 (2.3179)  weight_decay: 0.0500 (0.0500)  time: 1.0081  data: 0.0005  max mem: 78493
Epoch: [134]  [230/312]  eta: 0:01:28  lr: 0.002560  min_lr: 0.002560  loss: 2.3517 (2.3252)  weight_decay: 0.0500 (0.0500)  time: 1.0079  data: 0.0005  max mem: 78493
Epoch: [134]  [240/312]  eta: 0:01:17  lr: 0.002559  min_lr: 0.002559  loss: 2.4184 (2.3275)  weight_decay: 0.0500 (0.0500)  time: 1.0060  data: 0.0004  max mem: 78493
Epoch: [134]  [250/312]  eta: 0:01:06  lr: 0.002558  min_lr: 0.002558  loss: 2.4071 (2.3297)  weight_decay: 0.0500 (0.0500)  time: 1.0076  data: 0.0004  max mem: 78493
Epoch: [134]  [260/312]  eta: 0:00:55  lr: 0.002558  min_lr: 0.002558  loss: 2.3713 (2.3307)  weight_decay: 0.0500 (0.0500)  time: 1.0071  data: 0.0004  max mem: 78493
Epoch: [134]  [270/312]  eta: 0:00:44  lr: 0.002557  min_lr: 0.002557  loss: 2.1680 (2.3287)  weight_decay: 0.0500 (0.0500)  time: 1.0060  data: 0.0005  max mem: 78493
Epoch: [134]  [280/312]  eta: 0:00:34  lr: 0.002556  min_lr: 0.002556  loss: 2.3989 (2.3278)  weight_decay: 0.0500 (0.0500)  time: 1.0066  data: 0.0010  max mem: 78493
Epoch: [134]  [290/312]  eta: 0:00:23  lr: 0.002556  min_lr: 0.002556  loss: 2.4370 (2.3232)  weight_decay: 0.0500 (0.0500)  time: 1.0041  data: 0.0009  max mem: 78493
Epoch: [134]  [300/312]  eta: 0:00:12  lr: 0.002555  min_lr: 0.002555  loss: 2.2484 (2.3208)  weight_decay: 0.0500 (0.0500)  time: 1.0018  data: 0.0001  max mem: 78493
Epoch: [134]  [310/312]  eta: 0:00:02  lr: 0.002554  min_lr: 0.002554  loss: 2.2814 (2.3268)  weight_decay: 0.0500 (0.0500)  time: 1.0019  data: 0.0001  max mem: 78493
Epoch: [134]  [311/312]  eta: 0:00:01  lr: 0.002554  min_lr: 0.002554  loss: 2.2571 (2.3252)  weight_decay: 0.0500 (0.0500)  time: 1.0019  data: 0.0001  max mem: 78493
Epoch: [134] Total time: 0:05:32 (1.0655 s / it)
Averaged stats: lr: 0.002554  min_lr: 0.002554  loss: 2.2571 (2.3287)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:14  loss: 0.7401 (0.7401)  acc1: 82.0312 (82.0312)  acc5: 95.5729 (95.5729)  time: 8.3016  data: 8.0229  max mem: 78493
Test:  [8/9]  eta: 0:00:01  loss: 1.0562 (0.9621)  acc1: 74.6094 (75.9200)  acc5: 92.1875 (92.4960)  time: 1.1206  data: 0.8915  max mem: 78493
Test: Total time: 0:00:10 (1.1549 s / it)
* Acc@1 75.724 Acc@5 92.782 loss 0.959
Accuracy of the model on the 50000 test images: 75.7%
Max accuracy: 75.90%
Epoch: [135]  [  0/312]  eta: 1:21:13  lr: 0.002554  min_lr: 0.002554  loss: 2.8038 (2.8038)  weight_decay: 0.0500 (0.0500)  time: 15.6198  data: 12.8521  max mem: 78493
Epoch: [135]  [ 10/312]  eta: 0:13:12  lr: 0.002553  min_lr: 0.002553  loss: 2.3399 (2.2504)  weight_decay: 0.0500 (0.0500)  time: 2.6243  data: 1.1728  max mem: 78493
Epoch: [135]  [ 20/312]  eta: 0:09:02  lr: 0.002553  min_lr: 0.002553  loss: 2.3004 (2.3457)  weight_decay: 0.0500 (0.0500)  time: 1.1708  data: 0.0027  max mem: 78493
Epoch: [135]  [ 30/312]  eta: 0:07:26  lr: 0.002552  min_lr: 0.002552  loss: 2.3544 (2.3287)  weight_decay: 0.0500 (0.0500)  time: 1.0103  data: 0.0005  max mem: 78493
Epoch: [135]  [ 40/312]  eta: 0:06:32  lr: 0.002551  min_lr: 0.002551  loss: 2.2320 (2.2861)  weight_decay: 0.0500 (0.0500)  time: 1.0061  data: 0.0004  max mem: 78493
Epoch: [135]  [ 50/312]  eta: 0:05:55  lr: 0.002551  min_lr: 0.002551  loss: 2.2320 (2.2806)  weight_decay: 0.0500 (0.0500)  time: 1.0063  data: 0.0004  max mem: 78493
Epoch: [135]  [ 60/312]  eta: 0:05:27  lr: 0.002550  min_lr: 0.002550  loss: 2.4523 (2.3149)  weight_decay: 0.0500 (0.0500)  time: 1.0049  data: 0.0005  max mem: 78493
Epoch: [135]  [ 70/312]  eta: 0:05:04  lr: 0.002549  min_lr: 0.002549  loss: 2.5494 (2.3185)  weight_decay: 0.0500 (0.0500)  time: 1.0043  data: 0.0005  max mem: 78493
Epoch: [135]  [ 80/312]  eta: 0:04:44  lr: 0.002549  min_lr: 0.002549  loss: 2.5494 (2.3437)  weight_decay: 0.0500 (0.0500)  time: 1.0052  data: 0.0005  max mem: 78493
Epoch: [135]  [ 90/312]  eta: 0:04:26  lr: 0.002548  min_lr: 0.002548  loss: 2.3836 (2.3337)  weight_decay: 0.0500 (0.0500)  time: 1.0057  data: 0.0005  max mem: 78493
Epoch: [135]  [100/312]  eta: 0:04:10  lr: 0.002547  min_lr: 0.002547  loss: 2.3601 (2.3421)  weight_decay: 0.0500 (0.0500)  time: 1.0061  data: 0.0005  max mem: 78493
Epoch: [135]  [110/312]  eta: 0:03:55  lr: 0.002546  min_lr: 0.002546  loss: 2.3778 (2.3441)  weight_decay: 0.0500 (0.0500)  time: 1.0089  data: 0.0005  max mem: 78493
Epoch: [135]  [120/312]  eta: 0:03:41  lr: 0.002546  min_lr: 0.002546  loss: 2.4089 (2.3487)  weight_decay: 0.0500 (0.0500)  time: 1.0077  data: 0.0005  max mem: 78493
Epoch: [135]  [130/312]  eta: 0:03:27  lr: 0.002545  min_lr: 0.002545  loss: 2.2874 (2.3386)  weight_decay: 0.0500 (0.0500)  time: 1.0059  data: 0.0005  max mem: 78493
Epoch: [135]  [140/312]  eta: 0:03:14  lr: 0.002544  min_lr: 0.002544  loss: 2.4158 (2.3566)  weight_decay: 0.0500 (0.0500)  time: 1.0065  data: 0.0004  max mem: 78493
Epoch: [135]  [150/312]  eta: 0:03:02  lr: 0.002544  min_lr: 0.002544  loss: 2.4158 (2.3352)  weight_decay: 0.0500 (0.0500)  time: 1.0076  data: 0.0004  max mem: 78493
Epoch: [135]  [160/312]  eta: 0:02:49  lr: 0.002543  min_lr: 0.002543  loss: 2.0951 (2.3336)  weight_decay: 0.0500 (0.0500)  time: 1.0095  data: 0.0004  max mem: 78493
Epoch: [135]  [170/312]  eta: 0:02:37  lr: 0.002542  min_lr: 0.002542  loss: 2.3886 (2.3249)  weight_decay: 0.0500 (0.0500)  time: 1.0091  data: 0.0004  max mem: 78493
Epoch: [135]  [180/312]  eta: 0:02:25  lr: 0.002542  min_lr: 0.002542  loss: 2.3886 (2.3249)  weight_decay: 0.0500 (0.0500)  time: 1.0082  data: 0.0004  max mem: 78493
Epoch: [135]  [190/312]  eta: 0:02:14  lr: 0.002541  min_lr: 0.002541  loss: 2.4702 (2.3312)  weight_decay: 0.0500 (0.0500)  time: 1.0062  data: 0.0004  max mem: 78493
Epoch: [135]  [200/312]  eta: 0:02:02  lr: 0.002540  min_lr: 0.002540  loss: 2.4468 (2.3350)  weight_decay: 0.0500 (0.0500)  time: 1.0045  data: 0.0004  max mem: 78493
Epoch: [135]  [210/312]  eta: 0:01:51  lr: 0.002540  min_lr: 0.002540  loss: 2.4779 (2.3442)  weight_decay: 0.0500 (0.0500)  time: 1.0064  data: 0.0004  max mem: 78493
Epoch: [135]  [220/312]  eta: 0:01:40  lr: 0.002539  min_lr: 0.002539  loss: 2.4779 (2.3439)  weight_decay: 0.0500 (0.0500)  time: 1.0059  data: 0.0004  max mem: 78493
Epoch: [135]  [230/312]  eta: 0:01:28  lr: 0.002538  min_lr: 0.002538  loss: 2.4555 (2.3426)  weight_decay: 0.0500 (0.0500)  time: 1.0062  data: 0.0004  max mem: 78493
Epoch: [135]  [240/312]  eta: 0:01:17  lr: 0.002537  min_lr: 0.002537  loss: 2.4057 (2.3399)  weight_decay: 0.0500 (0.0500)  time: 1.0064  data: 0.0005  max mem: 78493
Epoch: [135]  [250/312]  eta: 0:01:06  lr: 0.002537  min_lr: 0.002537  loss: 2.3783 (2.3368)  weight_decay: 0.0500 (0.0500)  time: 1.0048  data: 0.0005  max mem: 78493
Epoch: [135]  [260/312]  eta: 0:00:55  lr: 0.002536  min_lr: 0.002536  loss: 2.3783 (2.3324)  weight_decay: 0.0500 (0.0500)  time: 1.0048  data: 0.0005  max mem: 78493
Epoch: [135]  [270/312]  eta: 0:00:45  lr: 0.002535  min_lr: 0.002535  loss: 2.2543 (2.3320)  weight_decay: 0.0500 (0.0500)  time: 1.0048  data: 0.0005  max mem: 78493
Epoch: [135]  [280/312]  eta: 0:00:34  lr: 0.002535  min_lr: 0.002535  loss: 2.4247 (2.3361)  weight_decay: 0.0500 (0.0500)  time: 1.0065  data: 0.0010  max mem: 78493
Epoch: [135]  [290/312]  eta: 0:00:23  lr: 0.002534  min_lr: 0.002534  loss: 2.4915 (2.3407)  weight_decay: 0.0500 (0.0500)  time: 1.0048  data: 0.0009  max mem: 78493
Epoch: [135]  [300/312]  eta: 0:00:12  lr: 0.002533  min_lr: 0.002533  loss: 2.3733 (2.3382)  weight_decay: 0.0500 (0.0500)  time: 1.0016  data: 0.0001  max mem: 78493
Epoch: [135]  [310/312]  eta: 0:00:02  lr: 0.002533  min_lr: 0.002533  loss: 2.3649 (2.3375)  weight_decay: 0.0500 (0.0500)  time: 1.0016  data: 0.0001  max mem: 78493
Epoch: [135]  [311/312]  eta: 0:00:01  lr: 0.002533  min_lr: 0.002533  loss: 2.3503 (2.3374)  weight_decay: 0.0500 (0.0500)  time: 1.0015  data: 0.0001  max mem: 78493
Epoch: [135] Total time: 0:05:33 (1.0691 s / it)
Averaged stats: lr: 0.002533  min_lr: 0.002533  loss: 2.3503 (2.3176)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:09  loss: 0.7115 (0.7115)  acc1: 82.8125 (82.8125)  acc5: 95.4427 (95.4427)  time: 7.7036  data: 7.4086  max mem: 78493
Test:  [8/9]  eta: 0:00:01  loss: 1.0313 (0.9383)  acc1: 75.0000 (76.2400)  acc5: 93.0990 (93.0880)  time: 1.0558  data: 0.8233  max mem: 78493
Test: Total time: 0:00:09 (1.0683 s / it)
* Acc@1 76.168 Acc@5 93.058 loss 0.938
Accuracy of the model on the 50000 test images: 76.2%
Max accuracy: 76.17%
Epoch: [136]  [  0/312]  eta: 1:24:40  lr: 0.002532  min_lr: 0.002532  loss: 2.6135 (2.6135)  weight_decay: 0.0500 (0.0500)  time: 16.2827  data: 15.2402  max mem: 78493
Epoch: [136]  [ 10/312]  eta: 0:12:51  lr: 0.002532  min_lr: 0.002532  loss: 2.2076 (2.2334)  weight_decay: 0.0500 (0.0500)  time: 2.5543  data: 1.3860  max mem: 78493
Epoch: [136]  [ 20/312]  eta: 0:08:53  lr: 0.002531  min_lr: 0.002531  loss: 2.2288 (2.3127)  weight_decay: 0.0500 (0.0500)  time: 1.1048  data: 0.0006  max mem: 78493
Epoch: [136]  [ 30/312]  eta: 0:07:21  lr: 0.002530  min_lr: 0.002530  loss: 2.3793 (2.3061)  weight_decay: 0.0500 (0.0500)  time: 1.0199  data: 0.0005  max mem: 78493
Epoch: [136]  [ 40/312]  eta: 0:06:28  lr: 0.002530  min_lr: 0.002530  loss: 2.3442 (2.2977)  weight_decay: 0.0500 (0.0500)  time: 1.0081  data: 0.0005  max mem: 78493
Epoch: [136]  [ 50/312]  eta: 0:05:52  lr: 0.002529  min_lr: 0.002529  loss: 2.3442 (2.3176)  weight_decay: 0.0500 (0.0500)  time: 1.0072  data: 0.0004  max mem: 78493
Epoch: [136]  [ 60/312]  eta: 0:05:25  lr: 0.002528  min_lr: 0.002528  loss: 2.4759 (2.3219)  weight_decay: 0.0500 (0.0500)  time: 1.0089  data: 0.0004  max mem: 78493
Epoch: [136]  [ 70/312]  eta: 0:05:02  lr: 0.002528  min_lr: 0.002528  loss: 2.5444 (2.3458)  weight_decay: 0.0500 (0.0500)  time: 1.0083  data: 0.0018  max mem: 78493
Epoch: [136]  [ 80/312]  eta: 0:04:43  lr: 0.002527  min_lr: 0.002527  loss: 2.5455 (2.3453)  weight_decay: 0.0500 (0.0500)  time: 1.0107  data: 0.0018  max mem: 78493
Epoch: [136]  [ 90/312]  eta: 0:04:25  lr: 0.002526  min_lr: 0.002526  loss: 2.4470 (2.3463)  weight_decay: 0.0500 (0.0500)  time: 1.0109  data: 0.0016  max mem: 78493
Epoch: [136]  [100/312]  eta: 0:04:10  lr: 0.002526  min_lr: 0.002526  loss: 2.2324 (2.3338)  weight_decay: 0.0500 (0.0500)  time: 1.0117  data: 0.0016  max mem: 78493
Epoch: [136]  [110/312]  eta: 0:03:55  lr: 0.002525  min_lr: 0.002525  loss: 2.3520 (2.3405)  weight_decay: 0.0500 (0.0500)  time: 1.0108  data: 0.0004  max mem: 78493
Epoch: [136]  [120/312]  eta: 0:03:41  lr: 0.002524  min_lr: 0.002524  loss: 2.3736 (2.3332)  weight_decay: 0.0500 (0.0500)  time: 1.0085  data: 0.0004  max mem: 78493
Epoch: [136]  [130/312]  eta: 0:03:27  lr: 0.002523  min_lr: 0.002523  loss: 1.9251 (2.2990)  weight_decay: 0.0500 (0.0500)  time: 1.0078  data: 0.0005  max mem: 78493
Epoch: [136]  [140/312]  eta: 0:03:14  lr: 0.002523  min_lr: 0.002523  loss: 2.3249 (2.3140)  weight_decay: 0.0500 (0.0500)  time: 1.0056  data: 0.0005  max mem: 78493
Epoch: [136]  [150/312]  eta: 0:03:01  lr: 0.002522  min_lr: 0.002522  loss: 2.3853 (2.3082)  weight_decay: 0.0500 (0.0500)  time: 1.0054  data: 0.0005  max mem: 78493
Epoch: [136]  [160/312]  eta: 0:02:49  lr: 0.002521  min_lr: 0.002521  loss: 2.3105 (2.3077)  weight_decay: 0.0500 (0.0500)  time: 1.0062  data: 0.0004  max mem: 78493
Epoch: [136]  [170/312]  eta: 0:02:37  lr: 0.002521  min_lr: 0.002521  loss: 2.4053 (2.3016)  weight_decay: 0.0500 (0.0500)  time: 1.0059  data: 0.0005  max mem: 78493
Epoch: [136]  [180/312]  eta: 0:02:25  lr: 0.002520  min_lr: 0.002520  loss: 2.2199 (2.2937)  weight_decay: 0.0500 (0.0500)  time: 1.0070  data: 0.0005  max mem: 78493
Epoch: [136]  [190/312]  eta: 0:02:14  lr: 0.002519  min_lr: 0.002519  loss: 2.2199 (2.2950)  weight_decay: 0.0500 (0.0500)  time: 1.0085  data: 0.0005  max mem: 78493
Epoch: [136]  [200/312]  eta: 0:02:02  lr: 0.002519  min_lr: 0.002519  loss: 2.2761 (2.2957)  weight_decay: 0.0500 (0.0500)  time: 1.0090  data: 0.0005  max mem: 78493
Epoch: [136]  [210/312]  eta: 0:01:51  lr: 0.002518  min_lr: 0.002518  loss: 2.4411 (2.3010)  weight_decay: 0.0500 (0.0500)  time: 1.0103  data: 0.0027  max mem: 78493
Epoch: [136]  [220/312]  eta: 0:01:39  lr: 0.002517  min_lr: 0.002517  loss: 2.5465 (2.3110)  weight_decay: 0.0500 (0.0500)  time: 1.0115  data: 0.0027  max mem: 78493
Epoch: [136]  [230/312]  eta: 0:01:28  lr: 0.002516  min_lr: 0.002516  loss: 2.4929 (2.3054)  weight_decay: 0.0500 (0.0500)  time: 1.0095  data: 0.0005  max mem: 78493
Epoch: [136]  [240/312]  eta: 0:01:17  lr: 0.002516  min_lr: 0.002516  loss: 2.3699 (2.3021)  weight_decay: 0.0500 (0.0500)  time: 1.0081  data: 0.0005  max mem: 78493
Epoch: [136]  [250/312]  eta: 0:01:06  lr: 0.002515  min_lr: 0.002515  loss: 2.4132 (2.3026)  weight_decay: 0.0500 (0.0500)  time: 1.0067  data: 0.0004  max mem: 78493
Epoch: [136]  [260/312]  eta: 0:00:55  lr: 0.002514  min_lr: 0.002514  loss: 2.2751 (2.2992)  weight_decay: 0.0500 (0.0500)  time: 1.0063  data: 0.0005  max mem: 78493
Epoch: [136]  [270/312]  eta: 0:00:45  lr: 0.002514  min_lr: 0.002514  loss: 2.2751 (2.2989)  weight_decay: 0.0500 (0.0500)  time: 1.0082  data: 0.0004  max mem: 78493
Epoch: [136]  [280/312]  eta: 0:00:34  lr: 0.002513  min_lr: 0.002513  loss: 2.1812 (2.2954)  weight_decay: 0.0500 (0.0500)  time: 1.0083  data: 0.0011  max mem: 78493
Epoch: [136]  [290/312]  eta: 0:00:23  lr: 0.002512  min_lr: 0.002512  loss: 2.2282 (2.2979)  weight_decay: 0.0500 (0.0500)  time: 1.0056  data: 0.0009  max mem: 78493
Epoch: [136]  [300/312]  eta: 0:00:12  lr: 0.002512  min_lr: 0.002512  loss: 2.4748 (2.3020)  weight_decay: 0.0500 (0.0500)  time: 1.0018  data: 0.0001  max mem: 78493
Epoch: [136]  [310/312]  eta: 0:00:02  lr: 0.002511  min_lr: 0.002511  loss: 2.4913 (2.3066)  weight_decay: 0.0500 (0.0500)  time: 1.0017  data: 0.0001  max mem: 78493
Epoch: [136]  [311/312]  eta: 0:00:01  lr: 0.002511  min_lr: 0.002511  loss: 2.4913 (2.3067)  weight_decay: 0.0500 (0.0500)  time: 1.0018  data: 0.0001  max mem: 78493
Epoch: [136] Total time: 0:05:33 (1.0688 s / it)
Averaged stats: lr: 0.002511  min_lr: 0.002511  loss: 2.4913 (2.3164)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:17  loss: 0.7599 (0.7599)  acc1: 80.2083 (80.2083)  acc5: 95.0521 (95.0521)  time: 8.6080  data: 8.3375  max mem: 78493
Test:  [8/9]  eta: 0:00:01  loss: 1.0605 (0.9562)  acc1: 74.4792 (74.9120)  acc5: 92.0573 (92.7360)  time: 1.1608  data: 0.9265  max mem: 78493
Test: Total time: 0:00:10 (1.2055 s / it)
* Acc@1 75.428 Acc@5 92.530 loss 0.955
Accuracy of the model on the 50000 test images: 75.4%
Max accuracy: 76.17%
Epoch: [137]  [  0/312]  eta: 1:26:23  lr: 0.002511  min_lr: 0.002511  loss: 2.6125 (2.6125)  weight_decay: 0.0500 (0.0500)  time: 16.6149  data: 11.9181  max mem: 78493
Epoch: [137]  [ 10/312]  eta: 0:13:15  lr: 0.002510  min_lr: 0.002510  loss: 2.4343 (2.2504)  weight_decay: 0.0500 (0.0500)  time: 2.6343  data: 1.2754  max mem: 78493
Epoch: [137]  [ 20/312]  eta: 0:09:03  lr: 0.002509  min_lr: 0.002509  loss: 2.3500 (2.2778)  weight_decay: 0.0500 (0.0500)  time: 1.1239  data: 0.1058  max mem: 78493
Epoch: [137]  [ 30/312]  eta: 0:07:27  lr: 0.002509  min_lr: 0.002509  loss: 2.3650 (2.2706)  weight_decay: 0.0500 (0.0500)  time: 1.0088  data: 0.0005  max mem: 78493
Epoch: [137]  [ 40/312]  eta: 0:06:32  lr: 0.002508  min_lr: 0.002508  loss: 2.3330 (2.2514)  weight_decay: 0.0500 (0.0500)  time: 1.0054  data: 0.0005  max mem: 78493
Epoch: [137]  [ 50/312]  eta: 0:05:55  lr: 0.002507  min_lr: 0.002507  loss: 2.1718 (2.2471)  weight_decay: 0.0500 (0.0500)  time: 1.0065  data: 0.0004  max mem: 78493
Epoch: [137]  [ 60/312]  eta: 0:05:27  lr: 0.002507  min_lr: 0.002507  loss: 2.3656 (2.2857)  weight_decay: 0.0500 (0.0500)  time: 1.0088  data: 0.0004  max mem: 78493
Epoch: [137]  [ 70/312]  eta: 0:05:04  lr: 0.002506  min_lr: 0.002506  loss: 2.3478 (2.2697)  weight_decay: 0.0500 (0.0500)  time: 1.0078  data: 0.0004  max mem: 78493
Epoch: [137]  [ 80/312]  eta: 0:04:45  lr: 0.002505  min_lr: 0.002505  loss: 2.3662 (2.2984)  weight_decay: 0.0500 (0.0500)  time: 1.0080  data: 0.0005  max mem: 78493
Epoch: [137]  [ 90/312]  eta: 0:04:27  lr: 0.002505  min_lr: 0.002505  loss: 2.3954 (2.2923)  weight_decay: 0.0500 (0.0500)  time: 1.0095  data: 0.0005  max mem: 78493
Epoch: [137]  [100/312]  eta: 0:04:11  lr: 0.002504  min_lr: 0.002504  loss: 2.3009 (2.2938)  weight_decay: 0.0500 (0.0500)  time: 1.0099  data: 0.0005  max mem: 78493
Epoch: [137]  [110/312]  eta: 0:03:56  lr: 0.002503  min_lr: 0.002503  loss: 2.3581 (2.2905)  weight_decay: 0.0500 (0.0500)  time: 1.0101  data: 0.0004  max mem: 78493
Epoch: [137]  [120/312]  eta: 0:03:42  lr: 0.002502  min_lr: 0.002502  loss: 2.5030 (2.3073)  weight_decay: 0.0500 (0.0500)  time: 1.0088  data: 0.0004  max mem: 78493
Epoch: [137]  [130/312]  eta: 0:03:28  lr: 0.002502  min_lr: 0.002502  loss: 2.5013 (2.3118)  weight_decay: 0.0500 (0.0500)  time: 1.0079  data: 0.0004  max mem: 78493
Epoch: [137]  [140/312]  eta: 0:03:15  lr: 0.002501  min_lr: 0.002501  loss: 2.4008 (2.3057)  weight_decay: 0.0500 (0.0500)  time: 1.0071  data: 0.0004  max mem: 78493
Epoch: [137]  [150/312]  eta: 0:03:02  lr: 0.002500  min_lr: 0.002500  loss: 2.0209 (2.2880)  weight_decay: 0.0500 (0.0500)  time: 1.0054  data: 0.0004  max mem: 78493
Epoch: [137]  [160/312]  eta: 0:02:50  lr: 0.002500  min_lr: 0.002500  loss: 2.2104 (2.2953)  weight_decay: 0.0500 (0.0500)  time: 1.0048  data: 0.0004  max mem: 78493
Epoch: [137]  [170/312]  eta: 0:02:37  lr: 0.002499  min_lr: 0.002499  loss: 2.3751 (2.3013)  weight_decay: 0.0500 (0.0500)  time: 1.0066  data: 0.0004  max mem: 78493
Epoch: [137]  [180/312]  eta: 0:02:26  lr: 0.002498  min_lr: 0.002498  loss: 2.3082 (2.2935)  weight_decay: 0.0500 (0.0500)  time: 1.0076  data: 0.0012  max mem: 78493
Epoch: [137]  [190/312]  eta: 0:02:14  lr: 0.002498  min_lr: 0.002498  loss: 2.1576 (2.2872)  weight_decay: 0.0500 (0.0500)  time: 1.0088  data: 0.0012  max mem: 78493
Epoch: [137]  [200/312]  eta: 0:02:02  lr: 0.002497  min_lr: 0.002497  loss: 1.9703 (2.2764)  weight_decay: 0.0500 (0.0500)  time: 1.0099  data: 0.0004  max mem: 78493
Epoch: [137]  [210/312]  eta: 0:01:51  lr: 0.002496  min_lr: 0.002496  loss: 2.0330 (2.2791)  weight_decay: 0.0500 (0.0500)  time: 1.0092  data: 0.0004  max mem: 78493
Epoch: [137]  [220/312]  eta: 0:01:40  lr: 0.002495  min_lr: 0.002495  loss: 2.2858 (2.2742)  weight_decay: 0.0500 (0.0500)  time: 1.0090  data: 0.0004  max mem: 78493
Epoch: [137]  [230/312]  eta: 0:01:29  lr: 0.002495  min_lr: 0.002495  loss: 2.2629 (2.2757)  weight_decay: 0.0500 (0.0500)  time: 1.0085  data: 0.0004  max mem: 78493
Epoch: [137]  [240/312]  eta: 0:01:17  lr: 0.002494  min_lr: 0.002494  loss: 2.4018 (2.2802)  weight_decay: 0.0500 (0.0500)  time: 1.0080  data: 0.0004  max mem: 78493
Epoch: [137]  [250/312]  eta: 0:01:06  lr: 0.002493  min_lr: 0.002493  loss: 2.4018 (2.2746)  weight_decay: 0.0500 (0.0500)  time: 1.0061  data: 0.0004  max mem: 78493
Epoch: [137]  [260/312]  eta: 0:00:55  lr: 0.002493  min_lr: 0.002493  loss: 2.2853 (2.2777)  weight_decay: 0.0500 (0.0500)  time: 1.0056  data: 0.0004  max mem: 78493
Epoch: [137]  [270/312]  eta: 0:00:45  lr: 0.002492  min_lr: 0.002492  loss: 2.2853 (2.2810)  weight_decay: 0.0500 (0.0500)  time: 1.0063  data: 0.0004  max mem: 78493
Epoch: [137]  [280/312]  eta: 0:00:34  lr: 0.002491  min_lr: 0.002491  loss: 2.2563 (2.2793)  weight_decay: 0.0500 (0.0500)  time: 1.0058  data: 0.0010  max mem: 78493
Epoch: [137]  [290/312]  eta: 0:00:23  lr: 0.002491  min_lr: 0.002491  loss: 2.4055 (2.2859)  weight_decay: 0.0500 (0.0500)  time: 1.0041  data: 0.0009  max mem: 78493
Epoch: [137]  [300/312]  eta: 0:00:12  lr: 0.002490  min_lr: 0.002490  loss: 2.4308 (2.2876)  weight_decay: 0.0500 (0.0500)  time: 1.0022  data: 0.0001  max mem: 78493
Epoch: [137]  [310/312]  eta: 0:00:02  lr: 0.002489  min_lr: 0.002489  loss: 2.3280 (2.2877)  weight_decay: 0.0500 (0.0500)  time: 1.0020  data: 0.0001  max mem: 78493
Epoch: [137]  [311/312]  eta: 0:00:01  lr: 0.002489  min_lr: 0.002489  loss: 2.3280 (2.2874)  weight_decay: 0.0500 (0.0500)  time: 1.0020  data: 0.0001  max mem: 78493
Epoch: [137] Total time: 0:05:33 (1.0702 s / it)
Averaged stats: lr: 0.002489  min_lr: 0.002489  loss: 2.3280 (2.3096)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:13  loss: 0.6867 (0.6867)  acc1: 83.0729 (83.0729)  acc5: 95.8333 (95.8333)  time: 8.1802  data: 7.9179  max mem: 78493
Test:  [8/9]  eta: 0:00:01  loss: 1.0447 (0.9267)  acc1: 76.3021 (76.2240)  acc5: 92.7083 (93.0560)  time: 1.1122  data: 0.8799  max mem: 78493
Test: Total time: 0:00:10 (1.1570 s / it)
* Acc@1 76.210 Acc@5 93.136 loss 0.932
Accuracy of the model on the 50000 test images: 76.2%
Max accuracy: 76.21%
Epoch: [138]  [  0/312]  eta: 1:19:47  lr: 0.002489  min_lr: 0.002489  loss: 2.4282 (2.4282)  weight_decay: 0.0500 (0.0500)  time: 15.3448  data: 14.3333  max mem: 78493
Epoch: [138]  [ 10/312]  eta: 0:12:35  lr: 0.002488  min_lr: 0.002488  loss: 2.4246 (2.3192)  weight_decay: 0.0500 (0.0500)  time: 2.5007  data: 1.3408  max mem: 78493
Epoch: [138]  [ 20/312]  eta: 0:08:47  lr: 0.002488  min_lr: 0.002488  loss: 2.4246 (2.3770)  weight_decay: 0.0500 (0.0500)  time: 1.1281  data: 0.0211  max mem: 78493
Epoch: [138]  [ 30/312]  eta: 0:07:16  lr: 0.002487  min_lr: 0.002487  loss: 2.4848 (2.4011)  weight_decay: 0.0500 (0.0500)  time: 1.0239  data: 0.0006  max mem: 78493
Epoch: [138]  [ 40/312]  eta: 0:06:25  lr: 0.002486  min_lr: 0.002486  loss: 2.4195 (2.3969)  weight_decay: 0.0500 (0.0500)  time: 1.0080  data: 0.0013  max mem: 78493
Epoch: [138]  [ 50/312]  eta: 0:05:50  lr: 0.002486  min_lr: 0.002486  loss: 2.4164 (2.3714)  weight_decay: 0.0500 (0.0500)  time: 1.0093  data: 0.0013  max mem: 78493
Epoch: [138]  [ 60/312]  eta: 0:05:23  lr: 0.002485  min_lr: 0.002485  loss: 2.4164 (2.3704)  weight_decay: 0.0500 (0.0500)  time: 1.0081  data: 0.0004  max mem: 78493
Epoch: [138]  [ 70/312]  eta: 0:05:01  lr: 0.002484  min_lr: 0.002484  loss: 2.2300 (2.3433)  weight_decay: 0.0500 (0.0500)  time: 1.0075  data: 0.0013  max mem: 78493
Epoch: [138]  [ 80/312]  eta: 0:04:41  lr: 0.002483  min_lr: 0.002483  loss: 2.1663 (2.3063)  weight_decay: 0.0500 (0.0500)  time: 1.0084  data: 0.0013  max mem: 78493
Epoch: [138]  [ 90/312]  eta: 0:04:24  lr: 0.002483  min_lr: 0.002483  loss: 2.3360 (2.3203)  weight_decay: 0.0500 (0.0500)  time: 1.0079  data: 0.0004  max mem: 78493
Epoch: [138]  [100/312]  eta: 0:04:08  lr: 0.002482  min_lr: 0.002482  loss: 2.3646 (2.3048)  weight_decay: 0.0500 (0.0500)  time: 1.0058  data: 0.0005  max mem: 78493
Epoch: [138]  [110/312]  eta: 0:03:53  lr: 0.002481  min_lr: 0.002481  loss: 2.2675 (2.2962)  weight_decay: 0.0500 (0.0500)  time: 1.0048  data: 0.0005  max mem: 78493
Epoch: [138]  [120/312]  eta: 0:03:39  lr: 0.002481  min_lr: 0.002481  loss: 2.3438 (2.3170)  weight_decay: 0.0500 (0.0500)  time: 1.0054  data: 0.0004  max mem: 78493
Epoch: [138]  [130/312]  eta: 0:03:26  lr: 0.002480  min_lr: 0.002480  loss: 2.5153 (2.3233)  weight_decay: 0.0500 (0.0500)  time: 1.0061  data: 0.0005  max mem: 78493
Epoch: [138]  [140/312]  eta: 0:03:13  lr: 0.002479  min_lr: 0.002479  loss: 2.5024 (2.3214)  weight_decay: 0.0500 (0.0500)  time: 1.0075  data: 0.0004  max mem: 78493
Epoch: [138]  [150/312]  eta: 0:03:01  lr: 0.002479  min_lr: 0.002479  loss: 2.4224 (2.3231)  weight_decay: 0.0500 (0.0500)  time: 1.0074  data: 0.0004  max mem: 78493
Epoch: [138]  [160/312]  eta: 0:02:48  lr: 0.002478  min_lr: 0.002478  loss: 2.3919 (2.3245)  weight_decay: 0.0500 (0.0500)  time: 1.0071  data: 0.0004  max mem: 78493
Epoch: [138]  [170/312]  eta: 0:02:36  lr: 0.002477  min_lr: 0.002477  loss: 2.3919 (2.3226)  weight_decay: 0.0500 (0.0500)  time: 1.0068  data: 0.0004  max mem: 78493
Epoch: [138]  [180/312]  eta: 0:02:25  lr: 0.002476  min_lr: 0.002476  loss: 2.4468 (2.3332)  weight_decay: 0.0500 (0.0500)  time: 1.0065  data: 0.0013  max mem: 78493
Epoch: [138]  [190/312]  eta: 0:02:13  lr: 0.002476  min_lr: 0.002476  loss: 2.4642 (2.3376)  weight_decay: 0.0500 (0.0500)  time: 1.0067  data: 0.0013  max mem: 78493
Epoch: [138]  [200/312]  eta: 0:02:02  lr: 0.002475  min_lr: 0.002475  loss: 2.5319 (2.3484)  weight_decay: 0.0500 (0.0500)  time: 1.0060  data: 0.0004  max mem: 78493
Epoch: [138]  [210/312]  eta: 0:01:50  lr: 0.002474  min_lr: 0.002474  loss: 2.5116 (2.3429)  weight_decay: 0.0500 (0.0500)  time: 1.0046  data: 0.0004  max mem: 78493
Epoch: [138]  [220/312]  eta: 0:01:39  lr: 0.002474  min_lr: 0.002474  loss: 2.3443 (2.3434)  weight_decay: 0.0500 (0.0500)  time: 1.0052  data: 0.0005  max mem: 78493
Epoch: [138]  [230/312]  eta: 0:01:28  lr: 0.002473  min_lr: 0.002473  loss: 2.4903 (2.3481)  weight_decay: 0.0500 (0.0500)  time: 1.0067  data: 0.0005  max mem: 78493
Epoch: [138]  [240/312]  eta: 0:01:17  lr: 0.002472  min_lr: 0.002472  loss: 2.5148 (2.3548)  weight_decay: 0.0500 (0.0500)  time: 1.0063  data: 0.0004  max mem: 78493
Epoch: [138]  [250/312]  eta: 0:01:06  lr: 0.002472  min_lr: 0.002472  loss: 2.3371 (2.3426)  weight_decay: 0.0500 (0.0500)  time: 1.0051  data: 0.0004  max mem: 78493
Epoch: [138]  [260/312]  eta: 0:00:55  lr: 0.002471  min_lr: 0.002471  loss: 2.3271 (2.3448)  weight_decay: 0.0500 (0.0500)  time: 1.0060  data: 0.0004  max mem: 78493
Epoch: [138]  [270/312]  eta: 0:00:44  lr: 0.002470  min_lr: 0.002470  loss: 2.4807 (2.3445)  weight_decay: 0.0500 (0.0500)  time: 1.0057  data: 0.0004  max mem: 78493
Epoch: [138]  [280/312]  eta: 0:00:34  lr: 0.002470  min_lr: 0.002470  loss: 2.3462 (2.3446)  weight_decay: 0.0500 (0.0500)  time: 1.0052  data: 0.0010  max mem: 78493
Epoch: [138]  [290/312]  eta: 0:00:23  lr: 0.002469  min_lr: 0.002469  loss: 2.3437 (2.3477)  weight_decay: 0.0500 (0.0500)  time: 1.0040  data: 0.0009  max mem: 78493
Epoch: [138]  [300/312]  eta: 0:00:12  lr: 0.002468  min_lr: 0.002468  loss: 2.3950 (2.3436)  weight_decay: 0.0500 (0.0500)  time: 1.0018  data: 0.0001  max mem: 78493
Epoch: [138]  [310/312]  eta: 0:00:02  lr: 0.002467  min_lr: 0.002467  loss: 2.2568 (2.3411)  weight_decay: 0.0500 (0.0500)  time: 1.0016  data: 0.0001  max mem: 78493
Epoch: [138]  [311/312]  eta: 0:00:01  lr: 0.002467  min_lr: 0.002467  loss: 2.2487 (2.3408)  weight_decay: 0.0500 (0.0500)  time: 1.0017  data: 0.0001  max mem: 78493
Epoch: [138] Total time: 0:05:32 (1.0655 s / it)
Averaged stats: lr: 0.002467  min_lr: 0.002467  loss: 2.2487 (2.3239)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:14  loss: 0.7016 (0.7016)  acc1: 82.5521 (82.5521)  acc5: 95.4427 (95.4427)  time: 8.2392  data: 7.9620  max mem: 78493
Test:  [8/9]  eta: 0:00:01  loss: 1.0570 (0.9707)  acc1: 75.3906 (75.8080)  acc5: 93.4896 (92.6560)  time: 1.1138  data: 0.8848  max mem: 78493
Test: Total time: 0:00:10 (1.1506 s / it)
* Acc@1 76.010 Acc@5 92.964 loss 0.957
Accuracy of the model on the 50000 test images: 76.0%
Max accuracy: 76.21%
Epoch: [139]  [  0/312]  eta: 1:27:14  lr: 0.002467  min_lr: 0.002467  loss: 2.8283 (2.8283)  weight_decay: 0.0500 (0.0500)  time: 16.7762  data: 12.2088  max mem: 78493
Epoch: [139]  [ 10/312]  eta: 0:13:15  lr: 0.002467  min_lr: 0.002467  loss: 2.3199 (2.2680)  weight_decay: 0.0500 (0.0500)  time: 2.6348  data: 1.2544  max mem: 78493
Epoch: [139]  [ 20/312]  eta: 0:09:05  lr: 0.002466  min_lr: 0.002466  loss: 2.3199 (2.3481)  weight_decay: 0.0500 (0.0500)  time: 1.1231  data: 0.0797  max mem: 78493
Epoch: [139]  [ 30/312]  eta: 0:07:28  lr: 0.002465  min_lr: 0.002465  loss: 2.4624 (2.3155)  weight_decay: 0.0500 (0.0500)  time: 1.0167  data: 0.0005  max mem: 78493
Epoch: [139]  [ 40/312]  eta: 0:06:33  lr: 0.002464  min_lr: 0.002464  loss: 2.2935 (2.3071)  weight_decay: 0.0500 (0.0500)  time: 1.0070  data: 0.0004  max mem: 78493
Epoch: [139]  [ 50/312]  eta: 0:05:56  lr: 0.002464  min_lr: 0.002464  loss: 2.3877 (2.3145)  weight_decay: 0.0500 (0.0500)  time: 1.0050  data: 0.0004  max mem: 78493
Epoch: [139]  [ 60/312]  eta: 0:05:28  lr: 0.002463  min_lr: 0.002463  loss: 2.4529 (2.3408)  weight_decay: 0.0500 (0.0500)  time: 1.0038  data: 0.0004  max mem: 78493
Epoch: [139]  [ 70/312]  eta: 0:05:05  lr: 0.002462  min_lr: 0.002462  loss: 2.4529 (2.3439)  weight_decay: 0.0500 (0.0500)  time: 1.0046  data: 0.0004  max mem: 78493
Epoch: [139]  [ 80/312]  eta: 0:04:45  lr: 0.002462  min_lr: 0.002462  loss: 2.2176 (2.3416)  weight_decay: 0.0500 (0.0500)  time: 1.0050  data: 0.0004  max mem: 78493
Epoch: [139]  [ 90/312]  eta: 0:04:27  lr: 0.002461  min_lr: 0.002461  loss: 2.4256 (2.3441)  weight_decay: 0.0500 (0.0500)  time: 1.0040  data: 0.0005  max mem: 78493
Epoch: [139]  [100/312]  eta: 0:04:11  lr: 0.002460  min_lr: 0.002460  loss: 2.4112 (2.3354)  weight_decay: 0.0500 (0.0500)  time: 1.0049  data: 0.0004  max mem: 78493
Epoch: [139]  [110/312]  eta: 0:03:56  lr: 0.002460  min_lr: 0.002460  loss: 2.3772 (2.3385)  weight_decay: 0.0500 (0.0500)  time: 1.0067  data: 0.0004  max mem: 78493
Epoch: [139]  [120/312]  eta: 0:03:41  lr: 0.002459  min_lr: 0.002459  loss: 2.2470 (2.3218)  weight_decay: 0.0500 (0.0500)  time: 1.0069  data: 0.0004  max mem: 78493
Epoch: [139]  [130/312]  eta: 0:03:28  lr: 0.002458  min_lr: 0.002458  loss: 2.0932 (2.3049)  weight_decay: 0.0500 (0.0500)  time: 1.0058  data: 0.0004  max mem: 78493
Epoch: [139]  [140/312]  eta: 0:03:15  lr: 0.002457  min_lr: 0.002457  loss: 2.2423 (2.3071)  weight_decay: 0.0500 (0.0500)  time: 1.0062  data: 0.0005  max mem: 78493
Epoch: [139]  [150/312]  eta: 0:03:02  lr: 0.002457  min_lr: 0.002457  loss: 2.2423 (2.2976)  weight_decay: 0.0500 (0.0500)  time: 1.0071  data: 0.0005  max mem: 78493
Epoch: [139]  [160/312]  eta: 0:02:49  lr: 0.002456  min_lr: 0.002456  loss: 2.3560 (2.3033)  weight_decay: 0.0500 (0.0500)  time: 1.0053  data: 0.0004  max mem: 78493
Epoch: [139]  [170/312]  eta: 0:02:37  lr: 0.002455  min_lr: 0.002455  loss: 2.4240 (2.2985)  weight_decay: 0.0500 (0.0500)  time: 1.0040  data: 0.0004  max mem: 78493
Epoch: [139]  [180/312]  eta: 0:02:25  lr: 0.002455  min_lr: 0.002455  loss: 2.2837 (2.3030)  weight_decay: 0.0500 (0.0500)  time: 1.0039  data: 0.0004  max mem: 78493
Epoch: [139]  [190/312]  eta: 0:02:14  lr: 0.002454  min_lr: 0.002454  loss: 2.3256 (2.3042)  weight_decay: 0.0500 (0.0500)  time: 1.0047  data: 0.0004  max mem: 78493
Epoch: [139]  [200/312]  eta: 0:02:02  lr: 0.002453  min_lr: 0.002453  loss: 2.3256 (2.3005)  weight_decay: 0.0500 (0.0500)  time: 1.0048  data: 0.0004  max mem: 78493
Epoch: [139]  [210/312]  eta: 0:01:51  lr: 0.002453  min_lr: 0.002453  loss: 2.1316 (2.2935)  weight_decay: 0.0500 (0.0500)  time: 1.0045  data: 0.0004  max mem: 78493
Epoch: [139]  [220/312]  eta: 0:01:40  lr: 0.002452  min_lr: 0.002452  loss: 2.3011 (2.2950)  weight_decay: 0.0500 (0.0500)  time: 1.0052  data: 0.0004  max mem: 78493
Epoch: [139]  [230/312]  eta: 0:01:28  lr: 0.002451  min_lr: 0.002451  loss: 2.4492 (2.2982)  weight_decay: 0.0500 (0.0500)  time: 1.0039  data: 0.0004  max mem: 78493
Epoch: [139]  [240/312]  eta: 0:01:17  lr: 0.002450  min_lr: 0.002450  loss: 2.4496 (2.3006)  weight_decay: 0.0500 (0.0500)  time: 1.0034  data: 0.0004  max mem: 78493
Epoch: [139]  [250/312]  eta: 0:01:06  lr: 0.002450  min_lr: 0.002450  loss: 2.3333 (2.2985)  weight_decay: 0.0500 (0.0500)  time: 1.0046  data: 0.0004  max mem: 78493
Epoch: [139]  [260/312]  eta: 0:00:55  lr: 0.002449  min_lr: 0.002449  loss: 2.1608 (2.2953)  weight_decay: 0.0500 (0.0500)  time: 1.0062  data: 0.0004  max mem: 78493
Epoch: [139]  [270/312]  eta: 0:00:45  lr: 0.002448  min_lr: 0.002448  loss: 2.0296 (2.2904)  weight_decay: 0.0500 (0.0500)  time: 1.0071  data: 0.0004  max mem: 78493
Epoch: [139]  [280/312]  eta: 0:00:34  lr: 0.002448  min_lr: 0.002448  loss: 2.4307 (2.2983)  weight_decay: 0.0500 (0.0500)  time: 1.0063  data: 0.0010  max mem: 78493
Epoch: [139]  [290/312]  eta: 0:00:23  lr: 0.002447  min_lr: 0.002447  loss: 2.4307 (2.2982)  weight_decay: 0.0500 (0.0500)  time: 1.0040  data: 0.0009  max mem: 78493
Epoch: [139]  [300/312]  eta: 0:00:12  lr: 0.002446  min_lr: 0.002446  loss: 2.3540 (2.3023)  weight_decay: 0.0500 (0.0500)  time: 1.0023  data: 0.0001  max mem: 78493
Epoch: [139]  [310/312]  eta: 0:00:02  lr: 0.002446  min_lr: 0.002446  loss: 2.3124 (2.3011)  weight_decay: 0.0500 (0.0500)  time: 1.0018  data: 0.0001  max mem: 78493
Epoch: [139]  [311/312]  eta: 0:00:01  lr: 0.002446  min_lr: 0.002446  loss: 2.3124 (2.3019)  weight_decay: 0.0500 (0.0500)  time: 1.0018  data: 0.0001  max mem: 78493
Epoch: [139] Total time: 0:05:33 (1.0689 s / it)
Averaged stats: lr: 0.002446  min_lr: 0.002446  loss: 2.3124 (2.3118)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:14  loss: 0.7316 (0.7316)  acc1: 82.5521 (82.5521)  acc5: 95.4427 (95.4427)  time: 8.2399  data: 7.9713  max mem: 78493
Test:  [8/9]  eta: 0:00:01  loss: 1.0580 (0.9197)  acc1: 73.8281 (76.0160)  acc5: 93.4896 (92.9600)  time: 1.1142  data: 0.8858  max mem: 78493
Test: Total time: 0:00:10 (1.1500 s / it)
* Acc@1 76.498 Acc@5 93.206 loss 0.910
Accuracy of the model on the 50000 test images: 76.5%
Max accuracy: 76.50%
Epoch: [140]  [  0/312]  eta: 1:23:12  lr: 0.002445  min_lr: 0.002445  loss: 1.8975 (1.8975)  weight_decay: 0.0500 (0.0500)  time: 16.0018  data: 14.5045  max mem: 78493
Epoch: [140]  [ 10/312]  eta: 0:13:16  lr: 0.002445  min_lr: 0.002445  loss: 2.4802 (2.4477)  weight_decay: 0.0500 (0.0500)  time: 2.6378  data: 1.3287  max mem: 78493
Epoch: [140]  [ 20/312]  eta: 0:09:03  lr: 0.002444  min_lr: 0.002444  loss: 2.4802 (2.4054)  weight_decay: 0.0500 (0.0500)  time: 1.1552  data: 0.0065  max mem: 78493
Epoch: [140]  [ 30/312]  eta: 0:07:27  lr: 0.002443  min_lr: 0.002443  loss: 2.3675 (2.3496)  weight_decay: 0.0500 (0.0500)  time: 1.0107  data: 0.0012  max mem: 78493
Epoch: [140]  [ 40/312]  eta: 0:06:33  lr: 0.002443  min_lr: 0.002443  loss: 2.3864 (2.3720)  weight_decay: 0.0500 (0.0500)  time: 1.0105  data: 0.0004  max mem: 78493
Epoch: [140]  [ 50/312]  eta: 0:05:56  lr: 0.002442  min_lr: 0.002442  loss: 2.4412 (2.3348)  weight_decay: 0.0500 (0.0500)  time: 1.0086  data: 0.0004  max mem: 78493
Epoch: [140]  [ 60/312]  eta: 0:05:28  lr: 0.002441  min_lr: 0.002441  loss: 2.3909 (2.3306)  weight_decay: 0.0500 (0.0500)  time: 1.0099  data: 0.0004  max mem: 78493
Epoch: [140]  [ 70/312]  eta: 0:05:05  lr: 0.002441  min_lr: 0.002441  loss: 2.4209 (2.3271)  weight_decay: 0.0500 (0.0500)  time: 1.0094  data: 0.0004  max mem: 78493
Epoch: [140]  [ 80/312]  eta: 0:04:45  lr: 0.002440  min_lr: 0.002440  loss: 2.3903 (2.3290)  weight_decay: 0.0500 (0.0500)  time: 1.0067  data: 0.0004  max mem: 78493
Epoch: [140]  [ 90/312]  eta: 0:04:27  lr: 0.002439  min_lr: 0.002439  loss: 2.3604 (2.3062)  weight_decay: 0.0500 (0.0500)  time: 1.0060  data: 0.0004  max mem: 78493
Epoch: [140]  [100/312]  eta: 0:04:11  lr: 0.002438  min_lr: 0.002438  loss: 2.2913 (2.2996)  weight_decay: 0.0500 (0.0500)  time: 1.0086  data: 0.0004  max mem: 78493
Epoch: [140]  [110/312]  eta: 0:03:56  lr: 0.002438  min_lr: 0.002438  loss: 2.4013 (2.3022)  weight_decay: 0.0500 (0.0500)  time: 1.0100  data: 0.0004  max mem: 78493
Epoch: [140]  [120/312]  eta: 0:03:42  lr: 0.002437  min_lr: 0.002437  loss: 2.3857 (2.2827)  weight_decay: 0.0500 (0.0500)  time: 1.0079  data: 0.0014  max mem: 78493
Epoch: [140]  [130/312]  eta: 0:03:28  lr: 0.002436  min_lr: 0.002436  loss: 2.0731 (2.2782)  weight_decay: 0.0500 (0.0500)  time: 1.0084  data: 0.0014  max mem: 78493
Epoch: [140]  [140/312]  eta: 0:03:15  lr: 0.002436  min_lr: 0.002436  loss: 2.4822 (2.2941)  weight_decay: 0.0500 (0.0500)  time: 1.0090  data: 0.0005  max mem: 78493
Epoch: [140]  [150/312]  eta: 0:03:02  lr: 0.002435  min_lr: 0.002435  loss: 2.5142 (2.3020)  weight_decay: 0.0500 (0.0500)  time: 1.0070  data: 0.0005  max mem: 78493
Epoch: [140]  [160/312]  eta: 0:02:50  lr: 0.002434  min_lr: 0.002434  loss: 2.3039 (2.2985)  weight_decay: 0.0500 (0.0500)  time: 1.0058  data: 0.0004  max mem: 78493
Epoch: [140]  [170/312]  eta: 0:02:38  lr: 0.002434  min_lr: 0.002434  loss: 2.4191 (2.3061)  weight_decay: 0.0500 (0.0500)  time: 1.0048  data: 0.0004  max mem: 78493
Epoch: [140]  [180/312]  eta: 0:02:26  lr: 0.002433  min_lr: 0.002433  loss: 2.4016 (2.3058)  weight_decay: 0.0500 (0.0500)  time: 1.0057  data: 0.0005  max mem: 78493
Epoch: [140]  [190/312]  eta: 0:02:14  lr: 0.002432  min_lr: 0.002432  loss: 2.2216 (2.2968)  weight_decay: 0.0500 (0.0500)  time: 1.0081  data: 0.0005  max mem: 78493
Epoch: [140]  [200/312]  eta: 0:02:02  lr: 0.002431  min_lr: 0.002431  loss: 2.1744 (2.2964)  weight_decay: 0.0500 (0.0500)  time: 1.0070  data: 0.0004  max mem: 78493
Epoch: [140]  [210/312]  eta: 0:01:51  lr: 0.002431  min_lr: 0.002431  loss: 2.3680 (2.2912)  weight_decay: 0.0500 (0.0500)  time: 1.0063  data: 0.0004  max mem: 78493
Epoch: [140]  [220/312]  eta: 0:01:40  lr: 0.002430  min_lr: 0.002430  loss: 2.3680 (2.2891)  weight_decay: 0.0500 (0.0500)  time: 1.0060  data: 0.0004  max mem: 78493
Epoch: [140]  [230/312]  eta: 0:01:28  lr: 0.002429  min_lr: 0.002429  loss: 2.4361 (2.2951)  weight_decay: 0.0500 (0.0500)  time: 1.0046  data: 0.0004  max mem: 78493
Epoch: [140]  [240/312]  eta: 0:01:17  lr: 0.002429  min_lr: 0.002429  loss: 2.4743 (2.3011)  weight_decay: 0.0500 (0.0500)  time: 1.0047  data: 0.0005  max mem: 78493
Epoch: [140]  [250/312]  eta: 0:01:06  lr: 0.002428  min_lr: 0.002428  loss: 2.4798 (2.3047)  weight_decay: 0.0500 (0.0500)  time: 1.0056  data: 0.0004  max mem: 78493
Epoch: [140]  [260/312]  eta: 0:00:55  lr: 0.002427  min_lr: 0.002427  loss: 2.2738 (2.3024)  weight_decay: 0.0500 (0.0500)  time: 1.0067  data: 0.0004  max mem: 78493
Epoch: [140]  [270/312]  eta: 0:00:45  lr: 0.002426  min_lr: 0.002426  loss: 2.2738 (2.3033)  weight_decay: 0.0500 (0.0500)  time: 1.0056  data: 0.0004  max mem: 78493
Epoch: [140]  [280/312]  eta: 0:00:34  lr: 0.002426  min_lr: 0.002426  loss: 2.3232 (2.3005)  weight_decay: 0.0500 (0.0500)  time: 1.0072  data: 0.0010  max mem: 78493
Epoch: [140]  [290/312]  eta: 0:00:23  lr: 0.002425  min_lr: 0.002425  loss: 2.4650 (2.3058)  weight_decay: 0.0500 (0.0500)  time: 1.0063  data: 0.0009  max mem: 78493
Epoch: [140]  [300/312]  eta: 0:00:12  lr: 0.002424  min_lr: 0.002424  loss: 2.5111 (2.3107)  weight_decay: 0.0500 (0.0500)  time: 1.0018  data: 0.0001  max mem: 78493
Epoch: [140]  [310/312]  eta: 0:00:02  lr: 0.002424  min_lr: 0.002424  loss: 2.3554 (2.3089)  weight_decay: 0.0500 (0.0500)  time: 1.0016  data: 0.0001  max mem: 78493
Epoch: [140]  [311/312]  eta: 0:00:01  lr: 0.002424  min_lr: 0.002424  loss: 2.4097 (2.3094)  weight_decay: 0.0500 (0.0500)  time: 1.0016  data: 0.0001  max mem: 78493
Epoch: [140] Total time: 0:05:33 (1.0704 s / it)
Averaged stats: lr: 0.002424  min_lr: 0.002424  loss: 2.4097 (2.3267)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:11  loss: 0.6583 (0.6583)  acc1: 84.5052 (84.5052)  acc5: 95.9635 (95.9635)  time: 7.9543  data: 7.6811  max mem: 78493
Test:  [8/9]  eta: 0:00:01  loss: 1.0146 (0.9193)  acc1: 74.8698 (76.4480)  acc5: 93.6198 (93.2640)  time: 1.1033  data: 0.8742  max mem: 78493
Test: Total time: 0:00:10 (1.1132 s / it)
* Acc@1 76.634 Acc@5 93.350 loss 0.911
Accuracy of the model on the 50000 test images: 76.6%
Max accuracy: 76.63%
Epoch: [141]  [  0/312]  eta: 1:17:12  lr: 0.002424  min_lr: 0.002424  loss: 2.4073 (2.4073)  weight_decay: 0.0500 (0.0500)  time: 14.8489  data: 13.3342  max mem: 78493
Epoch: [141]  [ 10/312]  eta: 0:12:26  lr: 0.002423  min_lr: 0.002423  loss: 2.4073 (2.4129)  weight_decay: 0.0500 (0.0500)  time: 2.4716  data: 1.2662  max mem: 78493
Epoch: [141]  [ 20/312]  eta: 0:08:41  lr: 0.002422  min_lr: 0.002422  loss: 2.2801 (2.3212)  weight_decay: 0.0500 (0.0500)  time: 1.1324  data: 0.0300  max mem: 78493
Epoch: [141]  [ 30/312]  eta: 0:07:12  lr: 0.002421  min_lr: 0.002421  loss: 2.1822 (2.2466)  weight_decay: 0.0500 (0.0500)  time: 1.0184  data: 0.0005  max mem: 78493
Epoch: [141]  [ 40/312]  eta: 0:06:22  lr: 0.002421  min_lr: 0.002421  loss: 2.2393 (2.2964)  weight_decay: 0.0500 (0.0500)  time: 1.0068  data: 0.0004  max mem: 78493
Epoch: [141]  [ 50/312]  eta: 0:05:47  lr: 0.002420  min_lr: 0.002420  loss: 2.4839 (2.3246)  weight_decay: 0.0500 (0.0500)  time: 1.0074  data: 0.0004  max mem: 78493
Epoch: [141]  [ 60/312]  eta: 0:05:21  lr: 0.002419  min_lr: 0.002419  loss: 2.4081 (2.3223)  weight_decay: 0.0500 (0.0500)  time: 1.0078  data: 0.0004  max mem: 78493
Epoch: [141]  [ 70/312]  eta: 0:04:59  lr: 0.002419  min_lr: 0.002419  loss: 2.3033 (2.3051)  weight_decay: 0.0500 (0.0500)  time: 1.0075  data: 0.0004  max mem: 78493
Epoch: [141]  [ 80/312]  eta: 0:04:40  lr: 0.002418  min_lr: 0.002418  loss: 2.2789 (2.3050)  weight_decay: 0.0500 (0.0500)  time: 1.0057  data: 0.0004  max mem: 78493
Epoch: [141]  [ 90/312]  eta: 0:04:23  lr: 0.002417  min_lr: 0.002417  loss: 2.3931 (2.3129)  weight_decay: 0.0500 (0.0500)  time: 1.0064  data: 0.0005  max mem: 78493
Epoch: [141]  [100/312]  eta: 0:04:07  lr: 0.002417  min_lr: 0.002417  loss: 2.4551 (2.3040)  weight_decay: 0.0500 (0.0500)  time: 1.0074  data: 0.0005  max mem: 78493
Epoch: [141]  [110/312]  eta: 0:03:53  lr: 0.002416  min_lr: 0.002416  loss: 2.3163 (2.3039)  weight_decay: 0.0500 (0.0500)  time: 1.0073  data: 0.0004  max mem: 78493
Epoch: [141]  [120/312]  eta: 0:03:39  lr: 0.002415  min_lr: 0.002415  loss: 2.3997 (2.3227)  weight_decay: 0.0500 (0.0500)  time: 1.0069  data: 0.0004  max mem: 78493
Epoch: [141]  [130/312]  eta: 0:03:25  lr: 0.002414  min_lr: 0.002414  loss: 2.4394 (2.3305)  weight_decay: 0.0500 (0.0500)  time: 1.0064  data: 0.0005  max mem: 78493
Epoch: [141]  [140/312]  eta: 0:03:13  lr: 0.002414  min_lr: 0.002414  loss: 2.4394 (2.3316)  weight_decay: 0.0500 (0.0500)  time: 1.0058  data: 0.0005  max mem: 78493
Epoch: [141]  [150/312]  eta: 0:03:00  lr: 0.002413  min_lr: 0.002413  loss: 2.3951 (2.3245)  weight_decay: 0.0500 (0.0500)  time: 1.0050  data: 0.0005  max mem: 78493
Epoch: [141]  [160/312]  eta: 0:02:48  lr: 0.002412  min_lr: 0.002412  loss: 2.4043 (2.3272)  weight_decay: 0.0500 (0.0500)  time: 1.0062  data: 0.0004  max mem: 78493
Epoch: [141]  [170/312]  eta: 0:02:36  lr: 0.002412  min_lr: 0.002412  loss: 2.4319 (2.3348)  weight_decay: 0.0500 (0.0500)  time: 1.0072  data: 0.0004  max mem: 78493
Epoch: [141]  [180/312]  eta: 0:02:24  lr: 0.002411  min_lr: 0.002411  loss: 2.4330 (2.3354)  weight_decay: 0.0500 (0.0500)  time: 1.0076  data: 0.0004  max mem: 78493
Epoch: [141]  [190/312]  eta: 0:02:13  lr: 0.002410  min_lr: 0.002410  loss: 2.5054 (2.3370)  weight_decay: 0.0500 (0.0500)  time: 1.0068  data: 0.0004  max mem: 78493
Epoch: [141]  [200/312]  eta: 0:02:01  lr: 0.002409  min_lr: 0.002409  loss: 2.5438 (2.3446)  weight_decay: 0.0500 (0.0500)  time: 1.0047  data: 0.0004  max mem: 78493
Epoch: [141]  [210/312]  eta: 0:01:50  lr: 0.002409  min_lr: 0.002409  loss: 2.5350 (2.3510)  weight_decay: 0.0500 (0.0500)  time: 1.0042  data: 0.0005  max mem: 78493
Epoch: [141]  [220/312]  eta: 0:01:39  lr: 0.002408  min_lr: 0.002408  loss: 2.3616 (2.3437)  weight_decay: 0.0500 (0.0500)  time: 1.0045  data: 0.0004  max mem: 78493
Epoch: [141]  [230/312]  eta: 0:01:28  lr: 0.002407  min_lr: 0.002407  loss: 2.2733 (2.3415)  weight_decay: 0.0500 (0.0500)  time: 1.0043  data: 0.0004  max mem: 78493
Epoch: [141]  [240/312]  eta: 0:01:17  lr: 0.002407  min_lr: 0.002407  loss: 2.4025 (2.3419)  weight_decay: 0.0500 (0.0500)  time: 1.0045  data: 0.0004  max mem: 78493
Epoch: [141]  [250/312]  eta: 0:01:06  lr: 0.002406  min_lr: 0.002406  loss: 2.3879 (2.3468)  weight_decay: 0.0500 (0.0500)  time: 1.0054  data: 0.0005  max mem: 78493
Epoch: [141]  [260/312]  eta: 0:00:55  lr: 0.002405  min_lr: 0.002405  loss: 2.4562 (2.3495)  weight_decay: 0.0500 (0.0500)  time: 1.0065  data: 0.0005  max mem: 78493
Epoch: [141]  [270/312]  eta: 0:00:44  lr: 0.002405  min_lr: 0.002405  loss: 2.4038 (2.3466)  weight_decay: 0.0500 (0.0500)  time: 1.0077  data: 0.0004  max mem: 78493
Epoch: [141]  [280/312]  eta: 0:00:34  lr: 0.002404  min_lr: 0.002404  loss: 2.3398 (2.3492)  weight_decay: 0.0500 (0.0500)  time: 1.0078  data: 0.0010  max mem: 78493
Epoch: [141]  [290/312]  eta: 0:00:23  lr: 0.002403  min_lr: 0.002403  loss: 2.3036 (2.3419)  weight_decay: 0.0500 (0.0500)  time: 1.0044  data: 0.0009  max mem: 78493
Epoch: [141]  [300/312]  eta: 0:00:12  lr: 0.002402  min_lr: 0.002402  loss: 2.2427 (2.3370)  weight_decay: 0.0500 (0.0500)  time: 1.0018  data: 0.0001  max mem: 78493
Epoch: [141]  [310/312]  eta: 0:00:02  lr: 0.002402  min_lr: 0.002402  loss: 2.3994 (2.3392)  weight_decay: 0.0500 (0.0500)  time: 1.0016  data: 0.0001  max mem: 78493
Epoch: [141]  [311/312]  eta: 0:00:01  lr: 0.002402  min_lr: 0.002402  loss: 2.4098 (2.3396)  weight_decay: 0.0500 (0.0500)  time: 1.0016  data: 0.0001  max mem: 78493
Epoch: [141] Total time: 0:05:32 (1.0641 s / it)
Averaged stats: lr: 0.002402  min_lr: 0.002402  loss: 2.4098 (2.3206)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:16  loss: 0.7229 (0.7229)  acc1: 81.7708 (81.7708)  acc5: 96.4844 (96.4844)  time: 8.4694  data: 8.1888  max mem: 78493
Test:  [8/9]  eta: 0:00:01  loss: 0.9632 (0.9312)  acc1: 75.1302 (75.9680)  acc5: 94.2708 (93.5840)  time: 1.1393  data: 0.9099  max mem: 78493
Test: Total time: 0:00:10 (1.1540 s / it)
* Acc@1 76.242 Acc@5 93.078 loss 0.934
Accuracy of the model on the 50000 test images: 76.2%
Max accuracy: 76.63%
Epoch: [142]  [  0/312]  eta: 1:25:50  lr: 0.002402  min_lr: 0.002402  loss: 1.6662 (1.6662)  weight_decay: 0.0500 (0.0500)  time: 16.5087  data: 14.7222  max mem: 78493
Epoch: [142]  [ 10/312]  eta: 0:12:49  lr: 0.002401  min_lr: 0.002401  loss: 2.3499 (2.2549)  weight_decay: 0.0500 (0.0500)  time: 2.5470  data: 1.3517  max mem: 78493
Epoch: [142]  [ 20/312]  eta: 0:08:54  lr: 0.002400  min_lr: 0.002400  loss: 2.2879 (2.2302)  weight_decay: 0.0500 (0.0500)  time: 1.0977  data: 0.0077  max mem: 78493
Epoch: [142]  [ 30/312]  eta: 0:07:21  lr: 0.002399  min_lr: 0.002399  loss: 2.2879 (2.2842)  weight_decay: 0.0500 (0.0500)  time: 1.0278  data: 0.0006  max mem: 78493
Epoch: [142]  [ 40/312]  eta: 0:06:29  lr: 0.002399  min_lr: 0.002399  loss: 2.3807 (2.2742)  weight_decay: 0.0500 (0.0500)  time: 1.0107  data: 0.0004  max mem: 78493
Epoch: [142]  [ 50/312]  eta: 0:05:53  lr: 0.002398  min_lr: 0.002398  loss: 2.3966 (2.3288)  weight_decay: 0.0500 (0.0500)  time: 1.0095  data: 0.0019  max mem: 78493
Epoch: [142]  [ 60/312]  eta: 0:05:25  lr: 0.002397  min_lr: 0.002397  loss: 2.4113 (2.3376)  weight_decay: 0.0500 (0.0500)  time: 1.0074  data: 0.0019  max mem: 78493
Epoch: [142]  [ 70/312]  eta: 0:05:02  lr: 0.002397  min_lr: 0.002397  loss: 2.3830 (2.3267)  weight_decay: 0.0500 (0.0500)  time: 1.0062  data: 0.0005  max mem: 78493
Epoch: [142]  [ 80/312]  eta: 0:04:43  lr: 0.002396  min_lr: 0.002396  loss: 2.4027 (2.3431)  weight_decay: 0.0500 (0.0500)  time: 1.0064  data: 0.0012  max mem: 78493
Epoch: [142]  [ 90/312]  eta: 0:04:25  lr: 0.002395  min_lr: 0.002395  loss: 2.4280 (2.3438)  weight_decay: 0.0500 (0.0500)  time: 1.0062  data: 0.0012  max mem: 78493
Epoch: [142]  [100/312]  eta: 0:04:10  lr: 0.002395  min_lr: 0.002395  loss: 2.3805 (2.3341)  weight_decay: 0.0500 (0.0500)  time: 1.0088  data: 0.0005  max mem: 78493
Epoch: [142]  [110/312]  eta: 0:03:55  lr: 0.002394  min_lr: 0.002394  loss: 2.1767 (2.3131)  weight_decay: 0.0500 (0.0500)  time: 1.0122  data: 0.0004  max mem: 78493
Epoch: [142]  [120/312]  eta: 0:03:41  lr: 0.002393  min_lr: 0.002393  loss: 2.1399 (2.3017)  weight_decay: 0.0500 (0.0500)  time: 1.0103  data: 0.0005  max mem: 78493
Epoch: [142]  [130/312]  eta: 0:03:27  lr: 0.002392  min_lr: 0.002392  loss: 2.3452 (2.3049)  weight_decay: 0.0500 (0.0500)  time: 1.0086  data: 0.0005  max mem: 78493
Epoch: [142]  [140/312]  eta: 0:03:14  lr: 0.002392  min_lr: 0.002392  loss: 2.3409 (2.3004)  weight_decay: 0.0500 (0.0500)  time: 1.0068  data: 0.0005  max mem: 78493
Epoch: [142]  [150/312]  eta: 0:03:01  lr: 0.002391  min_lr: 0.002391  loss: 2.2398 (2.2892)  weight_decay: 0.0500 (0.0500)  time: 1.0059  data: 0.0005  max mem: 78493
Epoch: [142]  [160/312]  eta: 0:02:49  lr: 0.002390  min_lr: 0.002390  loss: 2.3292 (2.2946)  weight_decay: 0.0500 (0.0500)  time: 1.0078  data: 0.0005  max mem: 78493
Epoch: [142]  [170/312]  eta: 0:02:37  lr: 0.002390  min_lr: 0.002390  loss: 2.3612 (2.2920)  weight_decay: 0.0500 (0.0500)  time: 1.0063  data: 0.0005  max mem: 78493
Epoch: [142]  [180/312]  eta: 0:02:25  lr: 0.002389  min_lr: 0.002389  loss: 2.3612 (2.2890)  weight_decay: 0.0500 (0.0500)  time: 1.0053  data: 0.0005  max mem: 78493
Epoch: [142]  [190/312]  eta: 0:02:14  lr: 0.002388  min_lr: 0.002388  loss: 2.3971 (2.2963)  weight_decay: 0.0500 (0.0500)  time: 1.0058  data: 0.0004  max mem: 78493
Epoch: [142]  [200/312]  eta: 0:02:02  lr: 0.002387  min_lr: 0.002387  loss: 2.3907 (2.2931)  weight_decay: 0.0500 (0.0500)  time: 1.0047  data: 0.0004  max mem: 78493
Epoch: [142]  [210/312]  eta: 0:01:51  lr: 0.002387  min_lr: 0.002387  loss: 2.3011 (2.2896)  weight_decay: 0.0500 (0.0500)  time: 1.0038  data: 0.0004  max mem: 78493
Epoch: [142]  [220/312]  eta: 0:01:39  lr: 0.002386  min_lr: 0.002386  loss: 2.1456 (2.2845)  weight_decay: 0.0500 (0.0500)  time: 1.0051  data: 0.0004  max mem: 78493
Epoch: [142]  [230/312]  eta: 0:01:28  lr: 0.002385  min_lr: 0.002385  loss: 2.0734 (2.2780)  weight_decay: 0.0500 (0.0500)  time: 1.0066  data: 0.0004  max mem: 78493
Epoch: [142]  [240/312]  eta: 0:01:17  lr: 0.002385  min_lr: 0.002385  loss: 2.4014 (2.2863)  weight_decay: 0.0500 (0.0500)  time: 1.0066  data: 0.0018  max mem: 78493
Epoch: [142]  [250/312]  eta: 0:01:06  lr: 0.002384  min_lr: 0.002384  loss: 2.4643 (2.2842)  weight_decay: 0.0500 (0.0500)  time: 1.0061  data: 0.0017  max mem: 78493
Epoch: [142]  [260/312]  eta: 0:00:55  lr: 0.002383  min_lr: 0.002383  loss: 2.2607 (2.2803)  weight_decay: 0.0500 (0.0500)  time: 1.0057  data: 0.0005  max mem: 78493
Epoch: [142]  [270/312]  eta: 0:00:44  lr: 0.002383  min_lr: 0.002383  loss: 2.3262 (2.2788)  weight_decay: 0.0500 (0.0500)  time: 1.0064  data: 0.0005  max mem: 78493
Epoch: [142]  [280/312]  eta: 0:00:34  lr: 0.002382  min_lr: 0.002382  loss: 2.4333 (2.2799)  weight_decay: 0.0500 (0.0500)  time: 1.0074  data: 0.0017  max mem: 78493
Epoch: [142]  [290/312]  eta: 0:00:23  lr: 0.002381  min_lr: 0.002381  loss: 2.4069 (2.2836)  weight_decay: 0.0500 (0.0500)  time: 1.0048  data: 0.0015  max mem: 78493
Epoch: [142]  [300/312]  eta: 0:00:12  lr: 0.002380  min_lr: 0.002380  loss: 2.3842 (2.2847)  weight_decay: 0.0500 (0.0500)  time: 1.0019  data: 0.0001  max mem: 78493
Epoch: [142]  [310/312]  eta: 0:00:02  lr: 0.002380  min_lr: 0.002380  loss: 2.3877 (2.2871)  weight_decay: 0.0500 (0.0500)  time: 1.0018  data: 0.0001  max mem: 78493
Epoch: [142]  [311/312]  eta: 0:00:01  lr: 0.002380  min_lr: 0.002380  loss: 2.3877 (2.2861)  weight_decay: 0.0500 (0.0500)  time: 1.0018  data: 0.0001  max mem: 78493
Epoch: [142] Total time: 0:05:33 (1.0680 s / it)
Averaged stats: lr: 0.002380  min_lr: 0.002380  loss: 2.3877 (2.3008)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:14  loss: 0.7299 (0.7299)  acc1: 80.5990 (80.5990)  acc5: 95.1823 (95.1823)  time: 8.2736  data: 8.0050  max mem: 78493
Test:  [8/9]  eta: 0:00:01  loss: 1.0879 (0.9632)  acc1: 74.2188 (75.0720)  acc5: 92.1875 (92.7520)  time: 1.1184  data: 0.8895  max mem: 78493
Test: Total time: 0:00:10 (1.1639 s / it)
* Acc@1 75.872 Acc@5 92.896 loss 0.945
Accuracy of the model on the 50000 test images: 75.9%
Max accuracy: 76.63%
Epoch: [143]  [  0/312]  eta: 1:21:41  lr: 0.002380  min_lr: 0.002380  loss: 1.9132 (1.9132)  weight_decay: 0.0500 (0.0500)  time: 15.7111  data: 14.2746  max mem: 78493
Epoch: [143]  [ 10/312]  eta: 0:12:54  lr: 0.002379  min_lr: 0.002379  loss: 2.4148 (2.3110)  weight_decay: 0.0500 (0.0500)  time: 2.5630  data: 1.3013  max mem: 78493
Epoch: [143]  [ 20/312]  eta: 0:08:53  lr: 0.002378  min_lr: 0.002378  loss: 2.3872 (2.2747)  weight_decay: 0.0500 (0.0500)  time: 1.1329  data: 0.0023  max mem: 78493
Epoch: [143]  [ 30/312]  eta: 0:07:20  lr: 0.002377  min_lr: 0.002377  loss: 2.4062 (2.3265)  weight_decay: 0.0500 (0.0500)  time: 1.0121  data: 0.0005  max mem: 78493
Epoch: [143]  [ 40/312]  eta: 0:06:28  lr: 0.002377  min_lr: 0.002377  loss: 2.4554 (2.3188)  weight_decay: 0.0500 (0.0500)  time: 1.0069  data: 0.0004  max mem: 78493
Epoch: [143]  [ 50/312]  eta: 0:05:52  lr: 0.002376  min_lr: 0.002376  loss: 2.3238 (2.3270)  weight_decay: 0.0500 (0.0500)  time: 1.0090  data: 0.0004  max mem: 78493
Epoch: [143]  [ 60/312]  eta: 0:05:25  lr: 0.002375  min_lr: 0.002375  loss: 2.2501 (2.2928)  weight_decay: 0.0500 (0.0500)  time: 1.0110  data: 0.0004  max mem: 78493
Epoch: [143]  [ 70/312]  eta: 0:05:02  lr: 0.002375  min_lr: 0.002375  loss: 2.2535 (2.3005)  weight_decay: 0.0500 (0.0500)  time: 1.0111  data: 0.0004  max mem: 78493
Epoch: [143]  [ 80/312]  eta: 0:04:43  lr: 0.002374  min_lr: 0.002374  loss: 2.2535 (2.2811)  weight_decay: 0.0500 (0.0500)  time: 1.0096  data: 0.0004  max mem: 78493
Epoch: [143]  [ 90/312]  eta: 0:04:25  lr: 0.002373  min_lr: 0.002373  loss: 2.2912 (2.2918)  weight_decay: 0.0500 (0.0500)  time: 1.0093  data: 0.0004  max mem: 78493
Epoch: [143]  [100/312]  eta: 0:04:10  lr: 0.002373  min_lr: 0.002373  loss: 2.4983 (2.3075)  weight_decay: 0.0500 (0.0500)  time: 1.0097  data: 0.0004  max mem: 78493
Epoch: [143]  [110/312]  eta: 0:03:55  lr: 0.002372  min_lr: 0.002372  loss: 2.4930 (2.3184)  weight_decay: 0.0500 (0.0500)  time: 1.0069  data: 0.0011  max mem: 78493
Epoch: [143]  [120/312]  eta: 0:03:40  lr: 0.002371  min_lr: 0.002371  loss: 2.4536 (2.3199)  weight_decay: 0.0500 (0.0500)  time: 1.0058  data: 0.0012  max mem: 78493
Epoch: [143]  [130/312]  eta: 0:03:27  lr: 0.002370  min_lr: 0.002370  loss: 2.4038 (2.3222)  weight_decay: 0.0500 (0.0500)  time: 1.0053  data: 0.0005  max mem: 78493
Epoch: [143]  [140/312]  eta: 0:03:14  lr: 0.002370  min_lr: 0.002370  loss: 2.3622 (2.3195)  weight_decay: 0.0500 (0.0500)  time: 1.0053  data: 0.0004  max mem: 78493
Epoch: [143]  [150/312]  eta: 0:03:01  lr: 0.002369  min_lr: 0.002369  loss: 2.2843 (2.3121)  weight_decay: 0.0500 (0.0500)  time: 1.0067  data: 0.0004  max mem: 78493
Epoch: [143]  [160/312]  eta: 0:02:49  lr: 0.002368  min_lr: 0.002368  loss: 2.3905 (2.3134)  weight_decay: 0.0500 (0.0500)  time: 1.0064  data: 0.0004  max mem: 78493
Epoch: [143]  [170/312]  eta: 0:02:37  lr: 0.002368  min_lr: 0.002368  loss: 2.4120 (2.3138)  weight_decay: 0.0500 (0.0500)  time: 1.0061  data: 0.0004  max mem: 78493
Epoch: [143]  [180/312]  eta: 0:02:25  lr: 0.002367  min_lr: 0.002367  loss: 2.4166 (2.3129)  weight_decay: 0.0500 (0.0500)  time: 1.0067  data: 0.0004  max mem: 78493
Epoch: [143]  [190/312]  eta: 0:02:13  lr: 0.002366  min_lr: 0.002366  loss: 2.4368 (2.3180)  weight_decay: 0.0500 (0.0500)  time: 1.0058  data: 0.0004  max mem: 78493
Epoch: [143]  [200/312]  eta: 0:02:02  lr: 0.002365  min_lr: 0.002365  loss: 2.4024 (2.3102)  weight_decay: 0.0500 (0.0500)  time: 1.0045  data: 0.0005  max mem: 78493
Epoch: [143]  [210/312]  eta: 0:01:51  lr: 0.002365  min_lr: 0.002365  loss: 2.3411 (2.3054)  weight_decay: 0.0500 (0.0500)  time: 1.0044  data: 0.0005  max mem: 78493
Epoch: [143]  [220/312]  eta: 0:01:39  lr: 0.002364  min_lr: 0.002364  loss: 2.3905 (2.3055)  weight_decay: 0.0500 (0.0500)  time: 1.0053  data: 0.0004  max mem: 78493
Epoch: [143]  [230/312]  eta: 0:01:28  lr: 0.002363  min_lr: 0.002363  loss: 2.2535 (2.2993)  weight_decay: 0.0500 (0.0500)  time: 1.0057  data: 0.0004  max mem: 78493
Epoch: [143]  [240/312]  eta: 0:01:17  lr: 0.002363  min_lr: 0.002363  loss: 2.2039 (2.2965)  weight_decay: 0.0500 (0.0500)  time: 1.0049  data: 0.0005  max mem: 78493
Epoch: [143]  [250/312]  eta: 0:01:06  lr: 0.002362  min_lr: 0.002362  loss: 2.1574 (2.2882)  weight_decay: 0.0500 (0.0500)  time: 1.0056  data: 0.0004  max mem: 78493
Epoch: [143]  [260/312]  eta: 0:00:55  lr: 0.002361  min_lr: 0.002361  loss: 2.1684 (2.2883)  weight_decay: 0.0500 (0.0500)  time: 1.0051  data: 0.0004  max mem: 78493
Epoch: [143]  [270/312]  eta: 0:00:44  lr: 0.002360  min_lr: 0.002360  loss: 2.3836 (2.2910)  weight_decay: 0.0500 (0.0500)  time: 1.0054  data: 0.0004  max mem: 78493
Epoch: [143]  [280/312]  eta: 0:00:34  lr: 0.002360  min_lr: 0.002360  loss: 2.3603 (2.2899)  weight_decay: 0.0500 (0.0500)  time: 1.0068  data: 0.0010  max mem: 78493
Epoch: [143]  [290/312]  eta: 0:00:23  lr: 0.002359  min_lr: 0.002359  loss: 2.2127 (2.2864)  weight_decay: 0.0500 (0.0500)  time: 1.0043  data: 0.0009  max mem: 78493
Epoch: [143]  [300/312]  eta: 0:00:12  lr: 0.002358  min_lr: 0.002358  loss: 2.4330 (2.2875)  weight_decay: 0.0500 (0.0500)  time: 1.0018  data: 0.0001  max mem: 78493
Epoch: [143]  [310/312]  eta: 0:00:02  lr: 0.002358  min_lr: 0.002358  loss: 2.3587 (2.2835)  weight_decay: 0.0500 (0.0500)  time: 1.0019  data: 0.0001  max mem: 78493
Epoch: [143]  [311/312]  eta: 0:00:01  lr: 0.002358  min_lr: 0.002358  loss: 2.3587 (2.2835)  weight_decay: 0.0500 (0.0500)  time: 1.0020  data: 0.0001  max mem: 78493
Epoch: [143] Total time: 0:05:33 (1.0676 s / it)
Averaged stats: lr: 0.002358  min_lr: 0.002358  loss: 2.3587 (2.2870)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:13  loss: 0.6445 (0.6445)  acc1: 84.1146 (84.1146)  acc5: 95.7031 (95.7031)  time: 8.1543  data: 7.8755  max mem: 78493
Test:  [8/9]  eta: 0:00:01  loss: 1.0386 (0.9188)  acc1: 74.0885 (76.1760)  acc5: 93.2292 (93.3600)  time: 1.1047  data: 0.8752  max mem: 78493
Test: Total time: 0:00:10 (1.1267 s / it)
* Acc@1 76.064 Acc@5 93.134 loss 0.921
Accuracy of the model on the 50000 test images: 76.1%
Max accuracy: 76.63%
Epoch: [144]  [  0/312]  eta: 1:18:59  lr: 0.002358  min_lr: 0.002358  loss: 2.5110 (2.5110)  weight_decay: 0.0500 (0.0500)  time: 15.1915  data: 12.8743  max mem: 78493
Epoch: [144]  [ 10/312]  eta: 0:12:50  lr: 0.002357  min_lr: 0.002357  loss: 2.4570 (2.2889)  weight_decay: 0.0500 (0.0500)  time: 2.5502  data: 1.1750  max mem: 78493
Epoch: [144]  [ 20/312]  eta: 0:08:52  lr: 0.002356  min_lr: 0.002356  loss: 2.4570 (2.3688)  weight_decay: 0.0500 (0.0500)  time: 1.1550  data: 0.0029  max mem: 78493
Epoch: [144]  [ 30/312]  eta: 0:07:19  lr: 0.002355  min_lr: 0.002355  loss: 2.4557 (2.3701)  weight_decay: 0.0500 (0.0500)  time: 1.0157  data: 0.0005  max mem: 78493
Epoch: [144]  [ 40/312]  eta: 0:06:27  lr: 0.002355  min_lr: 0.002355  loss: 2.3546 (2.3387)  weight_decay: 0.0500 (0.0500)  time: 1.0093  data: 0.0004  max mem: 78493
Epoch: [144]  [ 50/312]  eta: 0:05:52  lr: 0.002354  min_lr: 0.002354  loss: 2.3758 (2.3354)  weight_decay: 0.0500 (0.0500)  time: 1.0099  data: 0.0004  max mem: 78493
Epoch: [144]  [ 60/312]  eta: 0:05:24  lr: 0.002353  min_lr: 0.002353  loss: 2.1986 (2.3012)  weight_decay: 0.0500 (0.0500)  time: 1.0081  data: 0.0004  max mem: 78493
Epoch: [144]  [ 70/312]  eta: 0:05:02  lr: 0.002353  min_lr: 0.002353  loss: 2.2752 (2.3208)  weight_decay: 0.0500 (0.0500)  time: 1.0071  data: 0.0004  max mem: 78493
Epoch: [144]  [ 80/312]  eta: 0:04:42  lr: 0.002352  min_lr: 0.002352  loss: 2.3852 (2.3294)  weight_decay: 0.0500 (0.0500)  time: 1.0071  data: 0.0004  max mem: 78493
Epoch: [144]  [ 90/312]  eta: 0:04:25  lr: 0.002351  min_lr: 0.002351  loss: 2.3602 (2.3229)  weight_decay: 0.0500 (0.0500)  time: 1.0060  data: 0.0004  max mem: 78493
Epoch: [144]  [100/312]  eta: 0:04:09  lr: 0.002350  min_lr: 0.002350  loss: 2.2025 (2.3165)  weight_decay: 0.0500 (0.0500)  time: 1.0053  data: 0.0004  max mem: 78493
Epoch: [144]  [110/312]  eta: 0:03:54  lr: 0.002350  min_lr: 0.002350  loss: 2.3300 (2.3218)  weight_decay: 0.0500 (0.0500)  time: 1.0068  data: 0.0004  max mem: 78493
Epoch: [144]  [120/312]  eta: 0:03:40  lr: 0.002349  min_lr: 0.002349  loss: 2.3300 (2.3214)  weight_decay: 0.0500 (0.0500)  time: 1.0080  data: 0.0004  max mem: 78493
Epoch: [144]  [130/312]  eta: 0:03:27  lr: 0.002348  min_lr: 0.002348  loss: 2.2755 (2.3117)  weight_decay: 0.0500 (0.0500)  time: 1.0104  data: 0.0012  max mem: 78493
Epoch: [144]  [140/312]  eta: 0:03:14  lr: 0.002348  min_lr: 0.002348  loss: 2.2525 (2.3120)  weight_decay: 0.0500 (0.0500)  time: 1.0106  data: 0.0012  max mem: 78493
Epoch: [144]  [150/312]  eta: 0:03:01  lr: 0.002347  min_lr: 0.002347  loss: 2.4301 (2.3214)  weight_decay: 0.0500 (0.0500)  time: 1.0079  data: 0.0004  max mem: 78493
Epoch: [144]  [160/312]  eta: 0:02:49  lr: 0.002346  min_lr: 0.002346  loss: 2.4315 (2.3278)  weight_decay: 0.0500 (0.0500)  time: 1.0063  data: 0.0005  max mem: 78493
Epoch: [144]  [170/312]  eta: 0:02:37  lr: 0.002345  min_lr: 0.002345  loss: 2.4177 (2.3372)  weight_decay: 0.0500 (0.0500)  time: 1.0062  data: 0.0004  max mem: 78493
Epoch: [144]  [180/312]  eta: 0:02:25  lr: 0.002345  min_lr: 0.002345  loss: 2.3796 (2.3331)  weight_decay: 0.0500 (0.0500)  time: 1.0061  data: 0.0004  max mem: 78493
Epoch: [144]  [190/312]  eta: 0:02:13  lr: 0.002344  min_lr: 0.002344  loss: 2.3266 (2.3321)  weight_decay: 0.0500 (0.0500)  time: 1.0059  data: 0.0004  max mem: 78493
Epoch: [144]  [200/312]  eta: 0:02:02  lr: 0.002343  min_lr: 0.002343  loss: 2.3887 (2.3283)  weight_decay: 0.0500 (0.0500)  time: 1.0056  data: 0.0004  max mem: 78493
Epoch: [144]  [210/312]  eta: 0:01:51  lr: 0.002343  min_lr: 0.002343  loss: 2.3887 (2.3288)  weight_decay: 0.0500 (0.0500)  time: 1.0053  data: 0.0005  max mem: 78493
Epoch: [144]  [220/312]  eta: 0:01:39  lr: 0.002342  min_lr: 0.002342  loss: 2.4657 (2.3345)  weight_decay: 0.0500 (0.0500)  time: 1.0049  data: 0.0005  max mem: 78493
Epoch: [144]  [230/312]  eta: 0:01:28  lr: 0.002341  min_lr: 0.002341  loss: 2.3737 (2.3248)  weight_decay: 0.0500 (0.0500)  time: 1.0044  data: 0.0004  max mem: 78493
Epoch: [144]  [240/312]  eta: 0:01:17  lr: 0.002341  min_lr: 0.002341  loss: 2.2908 (2.3242)  weight_decay: 0.0500 (0.0500)  time: 1.0056  data: 0.0004  max mem: 78493
Epoch: [144]  [250/312]  eta: 0:01:06  lr: 0.002340  min_lr: 0.002340  loss: 2.4206 (2.3273)  weight_decay: 0.0500 (0.0500)  time: 1.0060  data: 0.0004  max mem: 78493
Epoch: [144]  [260/312]  eta: 0:00:55  lr: 0.002339  min_lr: 0.002339  loss: 2.3738 (2.3270)  weight_decay: 0.0500 (0.0500)  time: 1.0059  data: 0.0004  max mem: 78493
Epoch: [144]  [270/312]  eta: 0:00:44  lr: 0.002338  min_lr: 0.002338  loss: 2.2758 (2.3213)  weight_decay: 0.0500 (0.0500)  time: 1.0052  data: 0.0004  max mem: 78493
Epoch: [144]  [280/312]  eta: 0:00:34  lr: 0.002338  min_lr: 0.002338  loss: 2.3673 (2.3233)  weight_decay: 0.0500 (0.0500)  time: 1.0059  data: 0.0010  max mem: 78493
Epoch: [144]  [290/312]  eta: 0:00:23  lr: 0.002337  min_lr: 0.002337  loss: 2.3673 (2.3217)  weight_decay: 0.0500 (0.0500)  time: 1.0051  data: 0.0009  max mem: 78493
Epoch: [144]  [300/312]  eta: 0:00:12  lr: 0.002336  min_lr: 0.002336  loss: 2.2467 (2.3213)  weight_decay: 0.0500 (0.0500)  time: 1.0025  data: 0.0001  max mem: 78493
Epoch: [144]  [310/312]  eta: 0:00:02  lr: 0.002336  min_lr: 0.002336  loss: 2.3908 (2.3225)  weight_decay: 0.0500 (0.0500)  time: 1.0021  data: 0.0001  max mem: 78493
Epoch: [144]  [311/312]  eta: 0:00:01  lr: 0.002335  min_lr: 0.002335  loss: 2.3829 (2.3223)  weight_decay: 0.0500 (0.0500)  time: 1.0022  data: 0.0001  max mem: 78493
Epoch: [144] Total time: 0:05:32 (1.0670 s / it)
Averaged stats: lr: 0.002335  min_lr: 0.002335  loss: 2.3829 (2.2909)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:09  loss: 0.7261 (0.7261)  acc1: 81.2500 (81.2500)  acc5: 95.7031 (95.7031)  time: 7.7112  data: 7.4411  max mem: 78493
Test:  [8/9]  eta: 0:00:01  loss: 1.0505 (0.9548)  acc1: 76.3021 (76.0480)  acc5: 93.0990 (93.0080)  time: 1.1095  data: 0.8815  max mem: 78493
Test: Total time: 0:00:10 (1.1189 s / it)
* Acc@1 75.728 Acc@5 92.808 loss 0.948
Accuracy of the model on the 50000 test images: 75.7%
Max accuracy: 76.63%
Epoch: [145]  [  0/312]  eta: 1:22:38  lr: 0.002335  min_lr: 0.002335  loss: 1.5127 (1.5127)  weight_decay: 0.0500 (0.0500)  time: 15.8933  data: 13.7634  max mem: 78493
Epoch: [145]  [ 10/312]  eta: 0:12:59  lr: 0.002335  min_lr: 0.002335  loss: 1.8970 (2.0407)  weight_decay: 0.0500 (0.0500)  time: 2.5806  data: 1.2519  max mem: 78493
Epoch: [145]  [ 20/312]  eta: 0:08:56  lr: 0.002334  min_lr: 0.002334  loss: 2.3695 (2.1785)  weight_decay: 0.0500 (0.0500)  time: 1.1361  data: 0.0006  max mem: 78493
Epoch: [145]  [ 30/312]  eta: 0:07:23  lr: 0.002333  min_lr: 0.002333  loss: 2.3695 (2.2358)  weight_decay: 0.0500 (0.0500)  time: 1.0174  data: 0.0005  max mem: 78493
Epoch: [145]  [ 40/312]  eta: 0:06:30  lr: 0.002333  min_lr: 0.002333  loss: 2.4566 (2.2553)  weight_decay: 0.0500 (0.0500)  time: 1.0119  data: 0.0018  max mem: 78493
Epoch: [145]  [ 50/312]  eta: 0:05:54  lr: 0.002332  min_lr: 0.002332  loss: 2.3944 (2.2744)  weight_decay: 0.0500 (0.0500)  time: 1.0112  data: 0.0018  max mem: 78493
Epoch: [145]  [ 60/312]  eta: 0:05:26  lr: 0.002331  min_lr: 0.002331  loss: 2.4393 (2.3047)  weight_decay: 0.0500 (0.0500)  time: 1.0088  data: 0.0004  max mem: 78493
Epoch: [145]  [ 70/312]  eta: 0:05:03  lr: 0.002330  min_lr: 0.002330  loss: 2.4968 (2.3306)  weight_decay: 0.0500 (0.0500)  time: 1.0073  data: 0.0004  max mem: 78493
Epoch: [145]  [ 80/312]  eta: 0:04:43  lr: 0.002330  min_lr: 0.002330  loss: 2.4547 (2.3190)  weight_decay: 0.0500 (0.0500)  time: 1.0059  data: 0.0004  max mem: 78493
Epoch: [145]  [ 90/312]  eta: 0:04:26  lr: 0.002329  min_lr: 0.002329  loss: 2.0931 (2.2896)  weight_decay: 0.0500 (0.0500)  time: 1.0043  data: 0.0004  max mem: 78493
Epoch: [145]  [100/312]  eta: 0:04:10  lr: 0.002328  min_lr: 0.002328  loss: 2.1178 (2.2889)  weight_decay: 0.0500 (0.0500)  time: 1.0048  data: 0.0004  max mem: 78493
Epoch: [145]  [110/312]  eta: 0:03:55  lr: 0.002328  min_lr: 0.002328  loss: 2.3964 (2.2887)  weight_decay: 0.0500 (0.0500)  time: 1.0063  data: 0.0005  max mem: 78493
Epoch: [145]  [120/312]  eta: 0:03:41  lr: 0.002327  min_lr: 0.002327  loss: 2.3612 (2.2793)  weight_decay: 0.0500 (0.0500)  time: 1.0078  data: 0.0005  max mem: 78493
Epoch: [145]  [130/312]  eta: 0:03:27  lr: 0.002326  min_lr: 0.002326  loss: 2.0782 (2.2732)  weight_decay: 0.0500 (0.0500)  time: 1.0100  data: 0.0005  max mem: 78493
Epoch: [145]  [140/312]  eta: 0:03:14  lr: 0.002326  min_lr: 0.002326  loss: 1.9969 (2.2521)  weight_decay: 0.0500 (0.0500)  time: 1.0090  data: 0.0005  max mem: 78493
Epoch: [145]  [150/312]  eta: 0:03:02  lr: 0.002325  min_lr: 0.002325  loss: 2.2493 (2.2712)  weight_decay: 0.0500 (0.0500)  time: 1.0088  data: 0.0005  max mem: 78493
Epoch: [145]  [160/312]  eta: 0:02:49  lr: 0.002324  min_lr: 0.002324  loss: 2.5778 (2.2815)  weight_decay: 0.0500 (0.0500)  time: 1.0101  data: 0.0004  max mem: 78493
Epoch: [145]  [170/312]  eta: 0:02:37  lr: 0.002323  min_lr: 0.002323  loss: 2.4000 (2.2792)  weight_decay: 0.0500 (0.0500)  time: 1.0089  data: 0.0004  max mem: 78493
Epoch: [145]  [180/312]  eta: 0:02:25  lr: 0.002323  min_lr: 0.002323  loss: 2.2490 (2.2796)  weight_decay: 0.0500 (0.0500)  time: 1.0070  data: 0.0004  max mem: 78493
Epoch: [145]  [190/312]  eta: 0:02:14  lr: 0.002322  min_lr: 0.002322  loss: 2.4327 (2.2862)  weight_decay: 0.0500 (0.0500)  time: 1.0067  data: 0.0004  max mem: 78493
Epoch: [145]  [200/312]  eta: 0:02:02  lr: 0.002321  min_lr: 0.002321  loss: 2.4990 (2.2858)  weight_decay: 0.0500 (0.0500)  time: 1.0080  data: 0.0013  max mem: 78493
Epoch: [145]  [210/312]  eta: 0:01:51  lr: 0.002321  min_lr: 0.002321  loss: 2.2750 (2.2813)  weight_decay: 0.0500 (0.0500)  time: 1.0075  data: 0.0013  max mem: 78493
Epoch: [145]  [220/312]  eta: 0:01:40  lr: 0.002320  min_lr: 0.002320  loss: 2.2750 (2.2817)  weight_decay: 0.0500 (0.0500)  time: 1.0073  data: 0.0004  max mem: 78493
Epoch: [145]  [230/312]  eta: 0:01:28  lr: 0.002319  min_lr: 0.002319  loss: 2.2629 (2.2799)  weight_decay: 0.0500 (0.0500)  time: 1.0056  data: 0.0005  max mem: 78493
Epoch: [145]  [240/312]  eta: 0:01:17  lr: 0.002318  min_lr: 0.002318  loss: 2.2542 (2.2827)  weight_decay: 0.0500 (0.0500)  time: 1.0043  data: 0.0004  max mem: 78493
Epoch: [145]  [250/312]  eta: 0:01:06  lr: 0.002318  min_lr: 0.002318  loss: 2.4878 (2.2890)  weight_decay: 0.0500 (0.0500)  time: 1.0046  data: 0.0004  max mem: 78493
Epoch: [145]  [260/312]  eta: 0:00:55  lr: 0.002317  min_lr: 0.002317  loss: 2.4509 (2.2836)  weight_decay: 0.0500 (0.0500)  time: 1.0047  data: 0.0005  max mem: 78493
Epoch: [145]  [270/312]  eta: 0:00:45  lr: 0.002316  min_lr: 0.002316  loss: 2.3023 (2.2837)  weight_decay: 0.0500 (0.0500)  time: 1.0043  data: 0.0005  max mem: 78493
Epoch: [145]  [280/312]  eta: 0:00:34  lr: 0.002316  min_lr: 0.002316  loss: 2.1989 (2.2805)  weight_decay: 0.0500 (0.0500)  time: 1.0058  data: 0.0010  max mem: 78493
Epoch: [145]  [290/312]  eta: 0:00:23  lr: 0.002315  min_lr: 0.002315  loss: 1.9705 (2.2758)  weight_decay: 0.0500 (0.0500)  time: 1.0050  data: 0.0009  max mem: 78493
Epoch: [145]  [300/312]  eta: 0:00:12  lr: 0.002314  min_lr: 0.002314  loss: 1.9723 (2.2682)  weight_decay: 0.0500 (0.0500)  time: 1.0020  data: 0.0001  max mem: 78493
Epoch: [145]  [310/312]  eta: 0:00:02  lr: 0.002313  min_lr: 0.002313  loss: 2.2184 (2.2706)  weight_decay: 0.0500 (0.0500)  time: 1.0017  data: 0.0001  max mem: 78493
Epoch: [145]  [311/312]  eta: 0:00:01  lr: 0.002313  min_lr: 0.002313  loss: 2.2487 (2.2710)  weight_decay: 0.0500 (0.0500)  time: 1.0017  data: 0.0001  max mem: 78493
Epoch: [145] Total time: 0:05:33 (1.0684 s / it)
Averaged stats: lr: 0.002313  min_lr: 0.002313  loss: 2.2487 (2.2979)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:18  loss: 0.6576 (0.6576)  acc1: 83.9844 (83.9844)  acc5: 95.9635 (95.9635)  time: 8.7361  data: 8.4668  max mem: 78493
Test:  [8/9]  eta: 0:00:01  loss: 0.9972 (0.9138)  acc1: 77.0833 (76.9120)  acc5: 93.4896 (93.3280)  time: 1.1693  data: 0.9408  max mem: 78493
Test: Total time: 0:00:10 (1.1967 s / it)
* Acc@1 76.438 Acc@5 93.276 loss 0.913
Accuracy of the model on the 50000 test images: 76.4%
Max accuracy: 76.63%
Epoch: [146]  [  0/312]  eta: 1:26:24  lr: 0.002313  min_lr: 0.002313  loss: 2.8687 (2.8687)  weight_decay: 0.0500 (0.0500)  time: 16.6166  data: 12.4690  max mem: 78493
Epoch: [146]  [ 10/312]  eta: 0:13:54  lr: 0.002313  min_lr: 0.002313  loss: 2.4541 (2.3746)  weight_decay: 0.0500 (0.0500)  time: 2.7637  data: 1.4345  max mem: 78493
Epoch: [146]  [ 20/312]  eta: 0:09:22  lr: 0.002312  min_lr: 0.002312  loss: 2.2030 (2.2035)  weight_decay: 0.0500 (0.0500)  time: 1.1931  data: 0.1658  max mem: 78493
Epoch: [146]  [ 30/312]  eta: 0:07:40  lr: 0.002311  min_lr: 0.002311  loss: 2.0328 (2.2316)  weight_decay: 0.0500 (0.0500)  time: 1.0084  data: 0.0005  max mem: 78493
Epoch: [146]  [ 40/312]  eta: 0:06:42  lr: 0.002310  min_lr: 0.002310  loss: 2.4139 (2.2653)  weight_decay: 0.0500 (0.0500)  time: 1.0103  data: 0.0004  max mem: 78493
Epoch: [146]  [ 50/312]  eta: 0:06:03  lr: 0.002310  min_lr: 0.002310  loss: 2.3660 (2.2385)  weight_decay: 0.0500 (0.0500)  time: 1.0112  data: 0.0005  max mem: 78493
Epoch: [146]  [ 60/312]  eta: 0:05:34  lr: 0.002309  min_lr: 0.002309  loss: 2.3323 (2.2570)  weight_decay: 0.0500 (0.0500)  time: 1.0125  data: 0.0005  max mem: 78493
Epoch: [146]  [ 70/312]  eta: 0:05:10  lr: 0.002308  min_lr: 0.002308  loss: 2.3117 (2.2453)  weight_decay: 0.0500 (0.0500)  time: 1.0112  data: 0.0005  max mem: 78493
Epoch: [146]  [ 80/312]  eta: 0:04:49  lr: 0.002308  min_lr: 0.002308  loss: 2.1303 (2.2427)  weight_decay: 0.0500 (0.0500)  time: 1.0105  data: 0.0005  max mem: 78493
Epoch: [146]  [ 90/312]  eta: 0:04:31  lr: 0.002307  min_lr: 0.002307  loss: 2.3179 (2.2397)  weight_decay: 0.0500 (0.0500)  time: 1.0117  data: 0.0004  max mem: 78493
Epoch: [146]  [100/312]  eta: 0:04:14  lr: 0.002306  min_lr: 0.002306  loss: 2.1550 (2.2198)  weight_decay: 0.0500 (0.0500)  time: 1.0079  data: 0.0005  max mem: 78493
Epoch: [146]  [110/312]  eta: 0:03:59  lr: 0.002305  min_lr: 0.002305  loss: 2.1550 (2.2329)  weight_decay: 0.0500 (0.0500)  time: 1.0063  data: 0.0005  max mem: 78493
Epoch: [146]  [120/312]  eta: 0:03:44  lr: 0.002305  min_lr: 0.002305  loss: 2.5178 (2.2514)  weight_decay: 0.0500 (0.0500)  time: 1.0075  data: 0.0004  max mem: 78493
Epoch: [146]  [130/312]  eta: 0:03:30  lr: 0.002304  min_lr: 0.002304  loss: 2.4547 (2.2601)  weight_decay: 0.0500 (0.0500)  time: 1.0064  data: 0.0004  max mem: 78493
Epoch: [146]  [140/312]  eta: 0:03:17  lr: 0.002303  min_lr: 0.002303  loss: 2.3522 (2.2641)  weight_decay: 0.0500 (0.0500)  time: 1.0061  data: 0.0005  max mem: 78493
Epoch: [146]  [150/312]  eta: 0:03:04  lr: 0.002303  min_lr: 0.002303  loss: 2.4984 (2.2811)  weight_decay: 0.0500 (0.0500)  time: 1.0066  data: 0.0005  max mem: 78493
Epoch: [146]  [160/312]  eta: 0:02:51  lr: 0.002302  min_lr: 0.002302  loss: 2.3629 (2.2670)  weight_decay: 0.0500 (0.0500)  time: 1.0066  data: 0.0004  max mem: 78493
Epoch: [146]  [170/312]  eta: 0:02:39  lr: 0.002301  min_lr: 0.002301  loss: 2.3629 (2.2793)  weight_decay: 0.0500 (0.0500)  time: 1.0071  data: 0.0004  max mem: 78493
Epoch: [146]  [180/312]  eta: 0:02:27  lr: 0.002301  min_lr: 0.002301  loss: 2.4723 (2.2763)  weight_decay: 0.0500 (0.0500)  time: 1.0070  data: 0.0004  max mem: 78493
Epoch: [146]  [190/312]  eta: 0:02:15  lr: 0.002300  min_lr: 0.002300  loss: 2.3991 (2.2745)  weight_decay: 0.0500 (0.0500)  time: 1.0087  data: 0.0004  max mem: 78493
Epoch: [146]  [200/312]  eta: 0:02:03  lr: 0.002299  min_lr: 0.002299  loss: 2.2724 (2.2714)  weight_decay: 0.0500 (0.0500)  time: 1.0101  data: 0.0004  max mem: 78493
Epoch: [146]  [210/312]  eta: 0:01:52  lr: 0.002298  min_lr: 0.002298  loss: 2.2068 (2.2702)  weight_decay: 0.0500 (0.0500)  time: 1.0093  data: 0.0005  max mem: 78493
Epoch: [146]  [220/312]  eta: 0:01:40  lr: 0.002298  min_lr: 0.002298  loss: 2.3167 (2.2732)  weight_decay: 0.0500 (0.0500)  time: 1.0065  data: 0.0005  max mem: 78493
Epoch: [146]  [230/312]  eta: 0:01:29  lr: 0.002297  min_lr: 0.002297  loss: 2.4425 (2.2758)  weight_decay: 0.0500 (0.0500)  time: 1.0049  data: 0.0005  max mem: 78493
Epoch: [146]  [240/312]  eta: 0:01:18  lr: 0.002296  min_lr: 0.002296  loss: 2.2327 (2.2707)  weight_decay: 0.0500 (0.0500)  time: 1.0061  data: 0.0015  max mem: 78493
Epoch: [146]  [250/312]  eta: 0:01:07  lr: 0.002296  min_lr: 0.002296  loss: 2.1997 (2.2657)  weight_decay: 0.0500 (0.0500)  time: 1.0073  data: 0.0015  max mem: 78493
Epoch: [146]  [260/312]  eta: 0:00:56  lr: 0.002295  min_lr: 0.002295  loss: 2.0606 (2.2599)  weight_decay: 0.0500 (0.0500)  time: 1.0068  data: 0.0004  max mem: 78493
Epoch: [146]  [270/312]  eta: 0:00:45  lr: 0.002294  min_lr: 0.002294  loss: 2.2776 (2.2617)  weight_decay: 0.0500 (0.0500)  time: 1.0067  data: 0.0004  max mem: 78493
Epoch: [146]  [280/312]  eta: 0:00:34  lr: 0.002293  min_lr: 0.002293  loss: 2.4373 (2.2653)  weight_decay: 0.0500 (0.0500)  time: 1.0078  data: 0.0010  max mem: 78493
Epoch: [146]  [290/312]  eta: 0:00:23  lr: 0.002293  min_lr: 0.002293  loss: 2.4805 (2.2632)  weight_decay: 0.0500 (0.0500)  time: 1.0047  data: 0.0009  max mem: 78493
Epoch: [146]  [300/312]  eta: 0:00:12  lr: 0.002292  min_lr: 0.002292  loss: 2.3093 (2.2654)  weight_decay: 0.0500 (0.0500)  time: 1.0017  data: 0.0001  max mem: 78493
Epoch: [146]  [310/312]  eta: 0:00:02  lr: 0.002291  min_lr: 0.002291  loss: 2.3093 (2.2612)  weight_decay: 0.0500 (0.0500)  time: 1.0015  data: 0.0001  max mem: 78493
Epoch: [146]  [311/312]  eta: 0:00:01  lr: 0.002291  min_lr: 0.002291  loss: 2.3093 (2.2587)  weight_decay: 0.0500 (0.0500)  time: 1.0015  data: 0.0001  max mem: 78493
Epoch: [146] Total time: 0:05:35 (1.0757 s / it)
Averaged stats: lr: 0.002291  min_lr: 0.002291  loss: 2.3093 (2.2879)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:20  loss: 0.6705 (0.6705)  acc1: 82.8125 (82.8125)  acc5: 95.9635 (95.9635)  time: 8.8900  data: 8.6118  max mem: 78493
Test:  [8/9]  eta: 0:00:01  loss: 1.0096 (0.9339)  acc1: 77.3438 (76.2880)  acc5: 92.5781 (93.0880)  time: 1.1860  data: 0.9569  max mem: 78493
Test: Total time: 0:00:10 (1.2006 s / it)
* Acc@1 76.202 Acc@5 93.100 loss 0.918
Accuracy of the model on the 50000 test images: 76.2%
Max accuracy: 76.63%
Epoch: [147]  [  0/312]  eta: 1:23:48  lr: 0.002291  min_lr: 0.002291  loss: 1.7399 (1.7399)  weight_decay: 0.0500 (0.0500)  time: 16.1167  data: 12.6542  max mem: 78493
Epoch: [147]  [ 10/312]  eta: 0:13:22  lr: 0.002290  min_lr: 0.002290  loss: 1.9746 (2.0507)  weight_decay: 0.0500 (0.0500)  time: 2.6557  data: 1.3440  max mem: 78493
Epoch: [147]  [ 20/312]  eta: 0:09:06  lr: 0.002290  min_lr: 0.002290  loss: 2.2309 (2.1947)  weight_decay: 0.0500 (0.0500)  time: 1.1589  data: 0.1067  max mem: 78493
Epoch: [147]  [ 30/312]  eta: 0:07:29  lr: 0.002289  min_lr: 0.002289  loss: 2.3356 (2.2002)  weight_decay: 0.0500 (0.0500)  time: 1.0080  data: 0.0005  max mem: 78493
Epoch: [147]  [ 40/312]  eta: 0:06:34  lr: 0.002288  min_lr: 0.002288  loss: 2.3068 (2.2015)  weight_decay: 0.0500 (0.0500)  time: 1.0078  data: 0.0004  max mem: 78493
Epoch: [147]  [ 50/312]  eta: 0:05:57  lr: 0.002288  min_lr: 0.002288  loss: 2.1575 (2.2006)  weight_decay: 0.0500 (0.0500)  time: 1.0093  data: 0.0004  max mem: 78493
Epoch: [147]  [ 60/312]  eta: 0:05:29  lr: 0.002287  min_lr: 0.002287  loss: 2.3172 (2.2313)  weight_decay: 0.0500 (0.0500)  time: 1.0099  data: 0.0004  max mem: 78493
Epoch: [147]  [ 70/312]  eta: 0:05:05  lr: 0.002286  min_lr: 0.002286  loss: 2.4884 (2.2513)  weight_decay: 0.0500 (0.0500)  time: 1.0090  data: 0.0004  max mem: 78493
Epoch: [147]  [ 80/312]  eta: 0:04:45  lr: 0.002285  min_lr: 0.002285  loss: 2.5094 (2.2740)  weight_decay: 0.0500 (0.0500)  time: 1.0090  data: 0.0004  max mem: 78493
Epoch: [147]  [ 90/312]  eta: 0:04:28  lr: 0.002285  min_lr: 0.002285  loss: 2.4638 (2.2764)  weight_decay: 0.0500 (0.0500)  time: 1.0077  data: 0.0004  max mem: 78493
Epoch: [147]  [100/312]  eta: 0:04:11  lr: 0.002284  min_lr: 0.002284  loss: 2.3771 (2.2802)  weight_decay: 0.0500 (0.0500)  time: 1.0075  data: 0.0004  max mem: 78493
Epoch: [147]  [110/312]  eta: 0:03:56  lr: 0.002283  min_lr: 0.002283  loss: 2.3838 (2.2887)  weight_decay: 0.0500 (0.0500)  time: 1.0111  data: 0.0004  max mem: 78493
Epoch: [147]  [120/312]  eta: 0:03:42  lr: 0.002283  min_lr: 0.002283  loss: 2.4196 (2.2804)  weight_decay: 0.0500 (0.0500)  time: 1.0107  data: 0.0004  max mem: 78493
Epoch: [147]  [130/312]  eta: 0:03:28  lr: 0.002282  min_lr: 0.002282  loss: 2.4196 (2.2844)  weight_decay: 0.0500 (0.0500)  time: 1.0086  data: 0.0004  max mem: 78493
Epoch: [147]  [140/312]  eta: 0:03:15  lr: 0.002281  min_lr: 0.002281  loss: 2.4420 (2.2866)  weight_decay: 0.0500 (0.0500)  time: 1.0081  data: 0.0004  max mem: 78493
Epoch: [147]  [150/312]  eta: 0:03:02  lr: 0.002280  min_lr: 0.002280  loss: 2.4420 (2.2850)  weight_decay: 0.0500 (0.0500)  time: 1.0076  data: 0.0004  max mem: 78493
Epoch: [147]  [160/312]  eta: 0:02:50  lr: 0.002280  min_lr: 0.002280  loss: 2.4057 (2.2880)  weight_decay: 0.0500 (0.0500)  time: 1.0074  data: 0.0004  max mem: 78493
Epoch: [147]  [170/312]  eta: 0:02:38  lr: 0.002279  min_lr: 0.002279  loss: 2.3402 (2.2970)  weight_decay: 0.0500 (0.0500)  time: 1.0067  data: 0.0004  max mem: 78493
Epoch: [147]  [180/312]  eta: 0:02:26  lr: 0.002278  min_lr: 0.002278  loss: 2.2127 (2.2842)  weight_decay: 0.0500 (0.0500)  time: 1.0089  data: 0.0004  max mem: 78493
Epoch: [147]  [190/312]  eta: 0:02:14  lr: 0.002278  min_lr: 0.002278  loss: 2.2127 (2.2879)  weight_decay: 0.0500 (0.0500)  time: 1.0086  data: 0.0004  max mem: 78493
Epoch: [147]  [200/312]  eta: 0:02:03  lr: 0.002277  min_lr: 0.002277  loss: 2.3266 (2.2837)  weight_decay: 0.0500 (0.0500)  time: 1.0076  data: 0.0004  max mem: 78493
Epoch: [147]  [210/312]  eta: 0:01:51  lr: 0.002276  min_lr: 0.002276  loss: 2.2121 (2.2799)  weight_decay: 0.0500 (0.0500)  time: 1.0074  data: 0.0004  max mem: 78493
Epoch: [147]  [220/312]  eta: 0:01:40  lr: 0.002275  min_lr: 0.002275  loss: 2.2893 (2.2822)  weight_decay: 0.0500 (0.0500)  time: 1.0073  data: 0.0004  max mem: 78493
Epoch: [147]  [230/312]  eta: 0:01:29  lr: 0.002275  min_lr: 0.002275  loss: 2.3812 (2.2806)  weight_decay: 0.0500 (0.0500)  time: 1.0085  data: 0.0005  max mem: 78493
Epoch: [147]  [240/312]  eta: 0:01:18  lr: 0.002274  min_lr: 0.002274  loss: 2.3804 (2.2787)  weight_decay: 0.0500 (0.0500)  time: 1.0065  data: 0.0004  max mem: 78493
Epoch: [147]  [250/312]  eta: 0:01:06  lr: 0.002273  min_lr: 0.002273  loss: 2.4559 (2.2829)  weight_decay: 0.0500 (0.0500)  time: 1.0045  data: 0.0004  max mem: 78493
Epoch: [147]  [260/312]  eta: 0:00:56  lr: 0.002273  min_lr: 0.002273  loss: 2.4549 (2.2841)  weight_decay: 0.0500 (0.0500)  time: 1.0047  data: 0.0004  max mem: 78493
Epoch: [147]  [270/312]  eta: 0:00:45  lr: 0.002272  min_lr: 0.002272  loss: 2.4123 (2.2826)  weight_decay: 0.0500 (0.0500)  time: 1.0045  data: 0.0004  max mem: 78493
Epoch: [147]  [280/312]  eta: 0:00:34  lr: 0.002271  min_lr: 0.002271  loss: 2.3947 (2.2895)  weight_decay: 0.0500 (0.0500)  time: 1.0047  data: 0.0010  max mem: 78493
Epoch: [147]  [290/312]  eta: 0:00:23  lr: 0.002270  min_lr: 0.002270  loss: 2.4251 (2.2907)  weight_decay: 0.0500 (0.0500)  time: 1.0037  data: 0.0009  max mem: 78493
Epoch: [147]  [300/312]  eta: 0:00:12  lr: 0.002270  min_lr: 0.002270  loss: 2.2287 (2.2900)  weight_decay: 0.0500 (0.0500)  time: 1.0021  data: 0.0001  max mem: 78493
Epoch: [147]  [310/312]  eta: 0:00:02  lr: 0.002269  min_lr: 0.002269  loss: 2.4799 (2.2956)  weight_decay: 0.0500 (0.0500)  time: 1.0021  data: 0.0001  max mem: 78493
Epoch: [147]  [311/312]  eta: 0:00:01  lr: 0.002269  min_lr: 0.002269  loss: 2.4799 (2.2941)  weight_decay: 0.0500 (0.0500)  time: 1.0022  data: 0.0001  max mem: 78493
Epoch: [147] Total time: 0:05:34 (1.0708 s / it)
Averaged stats: lr: 0.002269  min_lr: 0.002269  loss: 2.4799 (2.2869)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:12  loss: 0.7194 (0.7194)  acc1: 82.4219 (82.4219)  acc5: 95.3125 (95.3125)  time: 8.0067  data: 7.7364  max mem: 78493
Test:  [8/9]  eta: 0:00:01  loss: 1.0101 (0.9477)  acc1: 76.1719 (76.2240)  acc5: 93.7500 (93.3280)  time: 1.0882  data: 0.8597  max mem: 78493
Test: Total time: 0:00:10 (1.1176 s / it)
* Acc@1 76.132 Acc@5 93.084 loss 0.945
Accuracy of the model on the 50000 test images: 76.1%
Max accuracy: 76.63%
Epoch: [148]  [  0/312]  eta: 1:27:59  lr: 0.002269  min_lr: 0.002269  loss: 2.3292 (2.3292)  weight_decay: 0.0500 (0.0500)  time: 16.9230  data: 15.4204  max mem: 78493
Epoch: [148]  [ 10/312]  eta: 0:13:42  lr: 0.002268  min_lr: 0.002268  loss: 2.3292 (2.3104)  weight_decay: 0.0500 (0.0500)  time: 2.7230  data: 1.4145  max mem: 78493
Epoch: [148]  [ 20/312]  eta: 0:09:16  lr: 0.002267  min_lr: 0.002267  loss: 2.4356 (2.4315)  weight_decay: 0.0500 (0.0500)  time: 1.1562  data: 0.0072  max mem: 78493
Epoch: [148]  [ 30/312]  eta: 0:07:36  lr: 0.002267  min_lr: 0.002267  loss: 2.3189 (2.3354)  weight_decay: 0.0500 (0.0500)  time: 1.0089  data: 0.0004  max mem: 78493
Epoch: [148]  [ 40/312]  eta: 0:06:39  lr: 0.002266  min_lr: 0.002266  loss: 2.1347 (2.3216)  weight_decay: 0.0500 (0.0500)  time: 1.0110  data: 0.0004  max mem: 78493
Epoch: [148]  [ 50/312]  eta: 0:06:01  lr: 0.002265  min_lr: 0.002265  loss: 2.4127 (2.3256)  weight_decay: 0.0500 (0.0500)  time: 1.0136  data: 0.0004  max mem: 78493
Epoch: [148]  [ 60/312]  eta: 0:05:32  lr: 0.002265  min_lr: 0.002265  loss: 2.4108 (2.3024)  weight_decay: 0.0500 (0.0500)  time: 1.0116  data: 0.0004  max mem: 78493
Epoch: [148]  [ 70/312]  eta: 0:05:08  lr: 0.002264  min_lr: 0.002264  loss: 2.2568 (2.2849)  weight_decay: 0.0500 (0.0500)  time: 1.0103  data: 0.0004  max mem: 78493
Epoch: [148]  [ 80/312]  eta: 0:04:48  lr: 0.002263  min_lr: 0.002263  loss: 2.2502 (2.2968)  weight_decay: 0.0500 (0.0500)  time: 1.0110  data: 0.0004  max mem: 78493
Epoch: [148]  [ 90/312]  eta: 0:04:30  lr: 0.002262  min_lr: 0.002262  loss: 2.3276 (2.2994)  weight_decay: 0.0500 (0.0500)  time: 1.0105  data: 0.0005  max mem: 78493
Epoch: [148]  [100/312]  eta: 0:04:13  lr: 0.002262  min_lr: 0.002262  loss: 2.3276 (2.2912)  weight_decay: 0.0500 (0.0500)  time: 1.0092  data: 0.0005  max mem: 78493
Epoch: [148]  [110/312]  eta: 0:03:58  lr: 0.002261  min_lr: 0.002261  loss: 2.3646 (2.2993)  weight_decay: 0.0500 (0.0500)  time: 1.0067  data: 0.0004  max mem: 78493
Epoch: [148]  [120/312]  eta: 0:03:43  lr: 0.002260  min_lr: 0.002260  loss: 2.4008 (2.3067)  weight_decay: 0.0500 (0.0500)  time: 1.0044  data: 0.0004  max mem: 78493
Epoch: [148]  [130/312]  eta: 0:03:29  lr: 0.002260  min_lr: 0.002260  loss: 2.2745 (2.2935)  weight_decay: 0.0500 (0.0500)  time: 1.0054  data: 0.0004  max mem: 78493
Epoch: [148]  [140/312]  eta: 0:03:16  lr: 0.002259  min_lr: 0.002259  loss: 2.3638 (2.3062)  weight_decay: 0.0500 (0.0500)  time: 1.0062  data: 0.0004  max mem: 78493
Epoch: [148]  [150/312]  eta: 0:03:03  lr: 0.002258  min_lr: 0.002258  loss: 2.4034 (2.3055)  weight_decay: 0.0500 (0.0500)  time: 1.0055  data: 0.0004  max mem: 78493
Epoch: [148]  [160/312]  eta: 0:02:51  lr: 0.002257  min_lr: 0.002257  loss: 2.4453 (2.3156)  weight_decay: 0.0500 (0.0500)  time: 1.0053  data: 0.0004  max mem: 78493
Epoch: [148]  [170/312]  eta: 0:02:38  lr: 0.002257  min_lr: 0.002257  loss: 2.4187 (2.3139)  weight_decay: 0.0500 (0.0500)  time: 1.0062  data: 0.0004  max mem: 78493
Epoch: [148]  [180/312]  eta: 0:02:26  lr: 0.002256  min_lr: 0.002256  loss: 2.2991 (2.3077)  weight_decay: 0.0500 (0.0500)  time: 1.0070  data: 0.0004  max mem: 78493
Epoch: [148]  [190/312]  eta: 0:02:15  lr: 0.002255  min_lr: 0.002255  loss: 2.4152 (2.3145)  weight_decay: 0.0500 (0.0500)  time: 1.0066  data: 0.0004  max mem: 78493
Epoch: [148]  [200/312]  eta: 0:02:03  lr: 0.002255  min_lr: 0.002255  loss: 2.4068 (2.3148)  weight_decay: 0.0500 (0.0500)  time: 1.0065  data: 0.0004  max mem: 78493
Epoch: [148]  [210/312]  eta: 0:01:51  lr: 0.002254  min_lr: 0.002254  loss: 2.2698 (2.3110)  weight_decay: 0.0500 (0.0500)  time: 1.0064  data: 0.0004  max mem: 78493
Epoch: [148]  [220/312]  eta: 0:01:40  lr: 0.002253  min_lr: 0.002253  loss: 2.2698 (2.3132)  weight_decay: 0.0500 (0.0500)  time: 1.0059  data: 0.0004  max mem: 78493
Epoch: [148]  [230/312]  eta: 0:01:29  lr: 0.002253  min_lr: 0.002253  loss: 2.4634 (2.3166)  weight_decay: 0.0500 (0.0500)  time: 1.0051  data: 0.0004  max mem: 78493
Epoch: [148]  [240/312]  eta: 0:01:18  lr: 0.002252  min_lr: 0.002252  loss: 2.4788 (2.3192)  weight_decay: 0.0500 (0.0500)  time: 1.0049  data: 0.0004  max mem: 78493
Epoch: [148]  [250/312]  eta: 0:01:07  lr: 0.002251  min_lr: 0.002251  loss: 2.3486 (2.3141)  weight_decay: 0.0500 (0.0500)  time: 1.0048  data: 0.0004  max mem: 78493
Epoch: [148]  [260/312]  eta: 0:00:56  lr: 0.002250  min_lr: 0.002250  loss: 2.1551 (2.3062)  weight_decay: 0.0500 (0.0500)  time: 1.0057  data: 0.0004  max mem: 78493
Epoch: [148]  [270/312]  eta: 0:00:45  lr: 0.002250  min_lr: 0.002250  loss: 2.1551 (2.3033)  weight_decay: 0.0500 (0.0500)  time: 1.0052  data: 0.0005  max mem: 78493
Epoch: [148]  [280/312]  eta: 0:00:34  lr: 0.002249  min_lr: 0.002249  loss: 2.3876 (2.3077)  weight_decay: 0.0500 (0.0500)  time: 1.0051  data: 0.0011  max mem: 78493
Epoch: [148]  [290/312]  eta: 0:00:23  lr: 0.002248  min_lr: 0.002248  loss: 2.4624 (2.3093)  weight_decay: 0.0500 (0.0500)  time: 1.0040  data: 0.0009  max mem: 78493
Epoch: [148]  [300/312]  eta: 0:00:12  lr: 0.002248  min_lr: 0.002248  loss: 2.2530 (2.3069)  weight_decay: 0.0500 (0.0500)  time: 1.0018  data: 0.0001  max mem: 78493
Epoch: [148]  [310/312]  eta: 0:00:02  lr: 0.002247  min_lr: 0.002247  loss: 2.1838 (2.3029)  weight_decay: 0.0500 (0.0500)  time: 1.0020  data: 0.0001  max mem: 78493
Epoch: [148]  [311/312]  eta: 0:00:01  lr: 0.002247  min_lr: 0.002247  loss: 2.2736 (2.3035)  weight_decay: 0.0500 (0.0500)  time: 1.0021  data: 0.0001  max mem: 78493
Epoch: [148] Total time: 0:05:34 (1.0729 s / it)
Averaged stats: lr: 0.002247  min_lr: 0.002247  loss: 2.2736 (2.2816)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:15  loss: 0.6060 (0.6060)  acc1: 83.7240 (83.7240)  acc5: 96.8750 (96.8750)  time: 8.3763  data: 8.1158  max mem: 78493
Test:  [8/9]  eta: 0:00:01  loss: 0.9426 (0.8941)  acc1: 76.3021 (76.7200)  acc5: 93.4896 (93.7120)  time: 1.1349  data: 0.9018  max mem: 78493
Test: Total time: 0:00:10 (1.1767 s / it)
* Acc@1 76.982 Acc@5 93.632 loss 0.890
Accuracy of the model on the 50000 test images: 77.0%
Max accuracy: 76.98%
Epoch: [149]  [  0/312]  eta: 1:26:20  lr: 0.002247  min_lr: 0.002247  loss: 2.4427 (2.4427)  weight_decay: 0.0500 (0.0500)  time: 16.6045  data: 15.5965  max mem: 78493
Epoch: [149]  [ 10/312]  eta: 0:13:14  lr: 0.002246  min_lr: 0.002246  loss: 2.0543 (2.1141)  weight_decay: 0.0500 (0.0500)  time: 2.6313  data: 1.4206  max mem: 78493
Epoch: [149]  [ 20/312]  eta: 0:09:03  lr: 0.002245  min_lr: 0.002245  loss: 2.0381 (2.1493)  weight_decay: 0.0500 (0.0500)  time: 1.1242  data: 0.0018  max mem: 78493
Epoch: [149]  [ 30/312]  eta: 0:07:27  lr: 0.002245  min_lr: 0.002245  loss: 2.4072 (2.1871)  weight_decay: 0.0500 (0.0500)  time: 1.0110  data: 0.0004  max mem: 78493
Epoch: [149]  [ 40/312]  eta: 0:06:33  lr: 0.002244  min_lr: 0.002244  loss: 2.4221 (2.1951)  weight_decay: 0.0500 (0.0500)  time: 1.0083  data: 0.0004  max mem: 78493
Epoch: [149]  [ 50/312]  eta: 0:05:56  lr: 0.002243  min_lr: 0.002243  loss: 2.4141 (2.2059)  weight_decay: 0.0500 (0.0500)  time: 1.0097  data: 0.0004  max mem: 78493
Epoch: [149]  [ 60/312]  eta: 0:05:28  lr: 0.002242  min_lr: 0.002242  loss: 2.3602 (2.2175)  weight_decay: 0.0500 (0.0500)  time: 1.0094  data: 0.0004  max mem: 78493
Epoch: [149]  [ 70/312]  eta: 0:05:05  lr: 0.002242  min_lr: 0.002242  loss: 2.2329 (2.1955)  weight_decay: 0.0500 (0.0500)  time: 1.0073  data: 0.0004  max mem: 78493
Epoch: [149]  [ 80/312]  eta: 0:04:45  lr: 0.002241  min_lr: 0.002241  loss: 2.2767 (2.2225)  weight_decay: 0.0500 (0.0500)  time: 1.0068  data: 0.0004  max mem: 78493
Epoch: [149]  [ 90/312]  eta: 0:04:27  lr: 0.002240  min_lr: 0.002240  loss: 2.4407 (2.2387)  weight_decay: 0.0500 (0.0500)  time: 1.0079  data: 0.0004  max mem: 78493
Epoch: [149]  [100/312]  eta: 0:04:11  lr: 0.002240  min_lr: 0.002240  loss: 2.3353 (2.2367)  weight_decay: 0.0500 (0.0500)  time: 1.0093  data: 0.0004  max mem: 78493
Epoch: [149]  [110/312]  eta: 0:03:56  lr: 0.002239  min_lr: 0.002239  loss: 2.3727 (2.2378)  weight_decay: 0.0500 (0.0500)  time: 1.0092  data: 0.0004  max mem: 78493
Epoch: [149]  [120/312]  eta: 0:03:42  lr: 0.002238  min_lr: 0.002238  loss: 2.4460 (2.2483)  weight_decay: 0.0500 (0.0500)  time: 1.0090  data: 0.0004  max mem: 78493
Epoch: [149]  [130/312]  eta: 0:03:28  lr: 0.002237  min_lr: 0.002237  loss: 2.3327 (2.2363)  weight_decay: 0.0500 (0.0500)  time: 1.0079  data: 0.0004  max mem: 78493
Epoch: [149]  [140/312]  eta: 0:03:15  lr: 0.002237  min_lr: 0.002237  loss: 2.1534 (2.2349)  weight_decay: 0.0500 (0.0500)  time: 1.0062  data: 0.0004  max mem: 78493
Epoch: [149]  [150/312]  eta: 0:03:02  lr: 0.002236  min_lr: 0.002236  loss: 2.3697 (2.2538)  weight_decay: 0.0500 (0.0500)  time: 1.0073  data: 0.0004  max mem: 78493
Epoch: [149]  [160/312]  eta: 0:02:50  lr: 0.002235  min_lr: 0.002235  loss: 2.4455 (2.2583)  weight_decay: 0.0500 (0.0500)  time: 1.0069  data: 0.0004  max mem: 78493
Epoch: [149]  [170/312]  eta: 0:02:38  lr: 0.002235  min_lr: 0.002235  loss: 2.3905 (2.2504)  weight_decay: 0.0500 (0.0500)  time: 1.0071  data: 0.0004  max mem: 78493
Epoch: [149]  [180/312]  eta: 0:02:26  lr: 0.002234  min_lr: 0.002234  loss: 2.2869 (2.2550)  weight_decay: 0.0500 (0.0500)  time: 1.0074  data: 0.0005  max mem: 78493
Epoch: [149]  [190/312]  eta: 0:02:14  lr: 0.002233  min_lr: 0.002233  loss: 2.3871 (2.2581)  weight_decay: 0.0500 (0.0500)  time: 1.0075  data: 0.0004  max mem: 78493
Epoch: [149]  [200/312]  eta: 0:02:02  lr: 0.002232  min_lr: 0.002232  loss: 2.3347 (2.2491)  weight_decay: 0.0500 (0.0500)  time: 1.0082  data: 0.0004  max mem: 78493
Epoch: [149]  [210/312]  eta: 0:01:51  lr: 0.002232  min_lr: 0.002232  loss: 2.0030 (2.2491)  weight_decay: 0.0500 (0.0500)  time: 1.0084  data: 0.0004  max mem: 78493
Epoch: [149]  [220/312]  eta: 0:01:40  lr: 0.002231  min_lr: 0.002231  loss: 1.9908 (2.2400)  weight_decay: 0.0500 (0.0500)  time: 1.0071  data: 0.0004  max mem: 78493
Epoch: [149]  [230/312]  eta: 0:01:29  lr: 0.002230  min_lr: 0.002230  loss: 2.3866 (2.2497)  weight_decay: 0.0500 (0.0500)  time: 1.0059  data: 0.0004  max mem: 78493
Epoch: [149]  [240/312]  eta: 0:01:17  lr: 0.002230  min_lr: 0.002230  loss: 2.4613 (2.2515)  weight_decay: 0.0500 (0.0500)  time: 1.0076  data: 0.0004  max mem: 78493
Epoch: [149]  [250/312]  eta: 0:01:06  lr: 0.002229  min_lr: 0.002229  loss: 2.2464 (2.2465)  weight_decay: 0.0500 (0.0500)  time: 1.0075  data: 0.0004  max mem: 78493
Epoch: [149]  [260/312]  eta: 0:00:55  lr: 0.002228  min_lr: 0.002228  loss: 1.9402 (2.2377)  weight_decay: 0.0500 (0.0500)  time: 1.0065  data: 0.0004  max mem: 78493
Epoch: [149]  [270/312]  eta: 0:00:45  lr: 0.002227  min_lr: 0.002227  loss: 2.0451 (2.2366)  weight_decay: 0.0500 (0.0500)  time: 1.0070  data: 0.0005  max mem: 78493
Epoch: [149]  [280/312]  eta: 0:00:34  lr: 0.002227  min_lr: 0.002227  loss: 2.3443 (2.2426)  weight_decay: 0.0500 (0.0500)  time: 1.0076  data: 0.0011  max mem: 78493
Epoch: [149]  [290/312]  eta: 0:00:23  lr: 0.002226  min_lr: 0.002226  loss: 2.4373 (2.2517)  weight_decay: 0.0500 (0.0500)  time: 1.0050  data: 0.0009  max mem: 78493
Epoch: [149]  [300/312]  eta: 0:00:12  lr: 0.002225  min_lr: 0.002225  loss: 2.4348 (2.2564)  weight_decay: 0.0500 (0.0500)  time: 1.0022  data: 0.0001  max mem: 78493
Epoch: [149]  [310/312]  eta: 0:00:02  lr: 0.002225  min_lr: 0.002225  loss: 2.4676 (2.2618)  weight_decay: 0.0500 (0.0500)  time: 1.0021  data: 0.0001  max mem: 78493
Epoch: [149]  [311/312]  eta: 0:00:01  lr: 0.002224  min_lr: 0.002224  loss: 2.4676 (2.2621)  weight_decay: 0.0500 (0.0500)  time: 1.0022  data: 0.0001  max mem: 78493
Epoch: [149] Total time: 0:05:33 (1.0704 s / it)
Averaged stats: lr: 0.002224  min_lr: 0.002224  loss: 2.4676 (2.2881)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:15  loss: 0.6989 (0.6989)  acc1: 82.1615 (82.1615)  acc5: 95.8333 (95.8333)  time: 8.3460  data: 8.0750  max mem: 78493
Test:  [8/9]  eta: 0:00:01  loss: 1.0641 (0.9553)  acc1: 74.7396 (75.3920)  acc5: 93.2292 (92.8480)  time: 1.1256  data: 0.8973  max mem: 78493
Test: Total time: 0:00:10 (1.1419 s / it)
* Acc@1 75.900 Acc@5 92.968 loss 0.946
Accuracy of the model on the 50000 test images: 75.9%
Max accuracy: 76.98%
Epoch: [150]  [  0/312]  eta: 1:27:54  lr: 0.002224  min_lr: 0.002224  loss: 1.6511 (1.6511)  weight_decay: 0.0500 (0.0500)  time: 16.9052  data: 15.9044  max mem: 78493
Epoch: [150]  [ 10/312]  eta: 0:13:29  lr: 0.002224  min_lr: 0.002224  loss: 2.2150 (2.2094)  weight_decay: 0.0500 (0.0500)  time: 2.6803  data: 1.4552  max mem: 78493
Epoch: [150]  [ 20/312]  eta: 0:09:10  lr: 0.002223  min_lr: 0.002223  loss: 2.3137 (2.2835)  weight_decay: 0.0500 (0.0500)  time: 1.1351  data: 0.0054  max mem: 78493
Epoch: [150]  [ 30/312]  eta: 0:07:31  lr: 0.002222  min_lr: 0.002222  loss: 2.3928 (2.3335)  weight_decay: 0.0500 (0.0500)  time: 1.0085  data: 0.0004  max mem: 78493
Epoch: [150]  [ 40/312]  eta: 0:06:36  lr: 0.002222  min_lr: 0.002222  loss: 2.4595 (2.3378)  weight_decay: 0.0500 (0.0500)  time: 1.0062  data: 0.0004  max mem: 78493
Epoch: [150]  [ 50/312]  eta: 0:05:58  lr: 0.002221  min_lr: 0.002221  loss: 2.2560 (2.3090)  weight_decay: 0.0500 (0.0500)  time: 1.0069  data: 0.0004  max mem: 78493
Epoch: [150]  [ 60/312]  eta: 0:05:29  lr: 0.002220  min_lr: 0.002220  loss: 2.3655 (2.3155)  weight_decay: 0.0500 (0.0500)  time: 1.0074  data: 0.0004  max mem: 78493
Epoch: [150]  [ 70/312]  eta: 0:05:06  lr: 0.002219  min_lr: 0.002219  loss: 2.3261 (2.2900)  weight_decay: 0.0500 (0.0500)  time: 1.0071  data: 0.0004  max mem: 78493
Epoch: [150]  [ 80/312]  eta: 0:04:46  lr: 0.002219  min_lr: 0.002219  loss: 2.3037 (2.2754)  weight_decay: 0.0500 (0.0500)  time: 1.0079  data: 0.0004  max mem: 78493
Epoch: [150]  [ 90/312]  eta: 0:04:28  lr: 0.002218  min_lr: 0.002218  loss: 2.3680 (2.3008)  weight_decay: 0.0500 (0.0500)  time: 1.0089  data: 0.0004  max mem: 78493
Epoch: [150]  [100/312]  eta: 0:04:12  lr: 0.002217  min_lr: 0.002217  loss: 2.4126 (2.2903)  weight_decay: 0.0500 (0.0500)  time: 1.0088  data: 0.0005  max mem: 78493
Epoch: [150]  [110/312]  eta: 0:03:57  lr: 0.002217  min_lr: 0.002217  loss: 2.1407 (2.2773)  weight_decay: 0.0500 (0.0500)  time: 1.0085  data: 0.0005  max mem: 78493
Epoch: [150]  [120/312]  eta: 0:03:42  lr: 0.002216  min_lr: 0.002216  loss: 2.1407 (2.2685)  weight_decay: 0.0500 (0.0500)  time: 1.0074  data: 0.0005  max mem: 78493
Epoch: [150]  [130/312]  eta: 0:03:28  lr: 0.002215  min_lr: 0.002215  loss: 2.3942 (2.2714)  weight_decay: 0.0500 (0.0500)  time: 1.0072  data: 0.0005  max mem: 78493
Epoch: [150]  [140/312]  eta: 0:03:15  lr: 0.002214  min_lr: 0.002214  loss: 2.4384 (2.2875)  weight_decay: 0.0500 (0.0500)  time: 1.0073  data: 0.0005  max mem: 78493
Epoch: [150]  [150/312]  eta: 0:03:03  lr: 0.002214  min_lr: 0.002214  loss: 2.4405 (2.2945)  weight_decay: 0.0500 (0.0500)  time: 1.0083  data: 0.0004  max mem: 78493
Epoch: [150]  [160/312]  eta: 0:02:50  lr: 0.002213  min_lr: 0.002213  loss: 2.4217 (2.3057)  weight_decay: 0.0500 (0.0500)  time: 1.0076  data: 0.0005  max mem: 78493
Epoch: [150]  [170/312]  eta: 0:02:38  lr: 0.002212  min_lr: 0.002212  loss: 2.4105 (2.3063)  weight_decay: 0.0500 (0.0500)  time: 1.0085  data: 0.0005  max mem: 78493
Epoch: [150]  [180/312]  eta: 0:02:26  lr: 0.002212  min_lr: 0.002212  loss: 2.2165 (2.2973)  weight_decay: 0.0500 (0.0500)  time: 1.0109  data: 0.0005  max mem: 78493
Epoch: [150]  [190/312]  eta: 0:02:14  lr: 0.002211  min_lr: 0.002211  loss: 1.9830 (2.2928)  weight_decay: 0.0500 (0.0500)  time: 1.0112  data: 0.0005  max mem: 78493
Epoch: [150]  [200/312]  eta: 0:02:03  lr: 0.002210  min_lr: 0.002210  loss: 2.3539 (2.2963)  weight_decay: 0.0500 (0.0500)  time: 1.0105  data: 0.0004  max mem: 78493
Epoch: [150]  [210/312]  eta: 0:01:51  lr: 0.002209  min_lr: 0.002209  loss: 2.4398 (2.3061)  weight_decay: 0.0500 (0.0500)  time: 1.0081  data: 0.0004  max mem: 78493
Epoch: [150]  [220/312]  eta: 0:01:40  lr: 0.002209  min_lr: 0.002209  loss: 2.4541 (2.3098)  weight_decay: 0.0500 (0.0500)  time: 1.0076  data: 0.0004  max mem: 78493
Epoch: [150]  [230/312]  eta: 0:01:29  lr: 0.002208  min_lr: 0.002208  loss: 2.3996 (2.3049)  weight_decay: 0.0500 (0.0500)  time: 1.0091  data: 0.0004  max mem: 78493
Epoch: [150]  [240/312]  eta: 0:01:18  lr: 0.002207  min_lr: 0.002207  loss: 2.2901 (2.3124)  weight_decay: 0.0500 (0.0500)  time: 1.0090  data: 0.0005  max mem: 78493
Epoch: [150]  [250/312]  eta: 0:01:07  lr: 0.002207  min_lr: 0.002207  loss: 2.3050 (2.3118)  weight_decay: 0.0500 (0.0500)  time: 1.0077  data: 0.0005  max mem: 78493
Epoch: [150]  [260/312]  eta: 0:00:56  lr: 0.002206  min_lr: 0.002206  loss: 2.1799 (2.3025)  weight_decay: 0.0500 (0.0500)  time: 1.0075  data: 0.0004  max mem: 78493
Epoch: [150]  [270/312]  eta: 0:00:45  lr: 0.002205  min_lr: 0.002205  loss: 2.0956 (2.2977)  weight_decay: 0.0500 (0.0500)  time: 1.0065  data: 0.0004  max mem: 78493
Epoch: [150]  [280/312]  eta: 0:00:34  lr: 0.002204  min_lr: 0.002204  loss: 2.3335 (2.3011)  weight_decay: 0.0500 (0.0500)  time: 1.0064  data: 0.0010  max mem: 78493
Epoch: [150]  [290/312]  eta: 0:00:23  lr: 0.002204  min_lr: 0.002204  loss: 2.3429 (2.3001)  weight_decay: 0.0500 (0.0500)  time: 1.0049  data: 0.0009  max mem: 78493
Epoch: [150]  [300/312]  eta: 0:00:12  lr: 0.002203  min_lr: 0.002203  loss: 2.3008 (2.2993)  weight_decay: 0.0500 (0.0500)  time: 1.0021  data: 0.0001  max mem: 78493
Epoch: [150]  [310/312]  eta: 0:00:02  lr: 0.002202  min_lr: 0.002202  loss: 2.3378 (2.2987)  weight_decay: 0.0500 (0.0500)  time: 1.0020  data: 0.0001  max mem: 78493
Epoch: [150]  [311/312]  eta: 0:00:01  lr: 0.002202  min_lr: 0.002202  loss: 2.4101 (2.2999)  weight_decay: 0.0500 (0.0500)  time: 1.0021  data: 0.0001  max mem: 78493
Epoch: [150] Total time: 0:05:34 (1.0724 s / it)
Averaged stats: lr: 0.002202  min_lr: 0.002202  loss: 2.4101 (2.2783)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:17  loss: 0.6956 (0.6956)  acc1: 83.4635 (83.4635)  acc5: 95.3125 (95.3125)  time: 8.6077  data: 8.3272  max mem: 78493
Test:  [8/9]  eta: 0:00:01  loss: 1.0090 (0.9136)  acc1: 75.3906 (76.1280)  acc5: 93.2292 (93.1040)  time: 1.1546  data: 0.9253  max mem: 78493
Test: Total time: 0:00:10 (1.1740 s / it)
* Acc@1 76.160 Acc@5 93.000 loss 0.930
Accuracy of the model on the 50000 test images: 76.2%
Max accuracy: 76.98%
Epoch: [151]  [  0/312]  eta: 1:23:38  lr: 0.002202  min_lr: 0.002202  loss: 2.0030 (2.0030)  weight_decay: 0.0500 (0.0500)  time: 16.0834  data: 12.1342  max mem: 78493
Epoch: [151]  [ 10/312]  eta: 0:12:56  lr: 0.002201  min_lr: 0.002201  loss: 2.0307 (2.1468)  weight_decay: 0.0500 (0.0500)  time: 2.5715  data: 1.1141  max mem: 78493
Epoch: [151]  [ 20/312]  eta: 0:08:56  lr: 0.002201  min_lr: 0.002201  loss: 1.9771 (2.1215)  weight_decay: 0.0500 (0.0500)  time: 1.1239  data: 0.0064  max mem: 78493
Epoch: [151]  [ 30/312]  eta: 0:07:22  lr: 0.002200  min_lr: 0.002200  loss: 2.3201 (2.2259)  weight_decay: 0.0500 (0.0500)  time: 1.0187  data: 0.0006  max mem: 78493
Epoch: [151]  [ 40/312]  eta: 0:06:29  lr: 0.002199  min_lr: 0.002199  loss: 2.3201 (2.2168)  weight_decay: 0.0500 (0.0500)  time: 1.0083  data: 0.0005  max mem: 78493
Epoch: [151]  [ 50/312]  eta: 0:05:53  lr: 0.002198  min_lr: 0.002198  loss: 2.3605 (2.2623)  weight_decay: 0.0500 (0.0500)  time: 1.0083  data: 0.0005  max mem: 78493
Epoch: [151]  [ 60/312]  eta: 0:05:26  lr: 0.002198  min_lr: 0.002198  loss: 2.3605 (2.2501)  weight_decay: 0.0500 (0.0500)  time: 1.0094  data: 0.0005  max mem: 78493
Epoch: [151]  [ 70/312]  eta: 0:05:03  lr: 0.002197  min_lr: 0.002197  loss: 2.2714 (2.2707)  weight_decay: 0.0500 (0.0500)  time: 1.0093  data: 0.0005  max mem: 78493
Epoch: [151]  [ 80/312]  eta: 0:04:43  lr: 0.002196  min_lr: 0.002196  loss: 2.2117 (2.2387)  weight_decay: 0.0500 (0.0500)  time: 1.0096  data: 0.0004  max mem: 78493
Epoch: [151]  [ 90/312]  eta: 0:04:26  lr: 0.002196  min_lr: 0.002196  loss: 2.1301 (2.2377)  weight_decay: 0.0500 (0.0500)  time: 1.0086  data: 0.0004  max mem: 78493
Epoch: [151]  [100/312]  eta: 0:04:10  lr: 0.002195  min_lr: 0.002195  loss: 2.2380 (2.2353)  weight_decay: 0.0500 (0.0500)  time: 1.0103  data: 0.0016  max mem: 78493
Epoch: [151]  [110/312]  eta: 0:03:55  lr: 0.002194  min_lr: 0.002194  loss: 2.4073 (2.2530)  weight_decay: 0.0500 (0.0500)  time: 1.0112  data: 0.0016  max mem: 78493
Epoch: [151]  [120/312]  eta: 0:03:41  lr: 0.002193  min_lr: 0.002193  loss: 2.3607 (2.2522)  weight_decay: 0.0500 (0.0500)  time: 1.0078  data: 0.0004  max mem: 78493
Epoch: [151]  [130/312]  eta: 0:03:27  lr: 0.002193  min_lr: 0.002193  loss: 2.3485 (2.2603)  weight_decay: 0.0500 (0.0500)  time: 1.0062  data: 0.0004  max mem: 78493
Epoch: [151]  [140/312]  eta: 0:03:14  lr: 0.002192  min_lr: 0.002192  loss: 2.3485 (2.2610)  weight_decay: 0.0500 (0.0500)  time: 1.0060  data: 0.0004  max mem: 78493
Epoch: [151]  [150/312]  eta: 0:03:01  lr: 0.002191  min_lr: 0.002191  loss: 2.4170 (2.2689)  weight_decay: 0.0500 (0.0500)  time: 1.0047  data: 0.0005  max mem: 78493
Epoch: [151]  [160/312]  eta: 0:02:49  lr: 0.002191  min_lr: 0.002191  loss: 2.4297 (2.2737)  weight_decay: 0.0500 (0.0500)  time: 1.0070  data: 0.0015  max mem: 78493
Epoch: [151]  [170/312]  eta: 0:02:37  lr: 0.002190  min_lr: 0.002190  loss: 2.2956 (2.2700)  weight_decay: 0.0500 (0.0500)  time: 1.0100  data: 0.0015  max mem: 78493
Epoch: [151]  [180/312]  eta: 0:02:25  lr: 0.002189  min_lr: 0.002189  loss: 2.3064 (2.2790)  weight_decay: 0.0500 (0.0500)  time: 1.0082  data: 0.0004  max mem: 78493
Epoch: [151]  [190/312]  eta: 0:02:14  lr: 0.002188  min_lr: 0.002188  loss: 2.2718 (2.2669)  weight_decay: 0.0500 (0.0500)  time: 1.0063  data: 0.0004  max mem: 78493
Epoch: [151]  [200/312]  eta: 0:02:02  lr: 0.002188  min_lr: 0.002188  loss: 2.1772 (2.2683)  weight_decay: 0.0500 (0.0500)  time: 1.0063  data: 0.0004  max mem: 78493
Epoch: [151]  [210/312]  eta: 0:01:51  lr: 0.002187  min_lr: 0.002187  loss: 2.2688 (2.2667)  weight_decay: 0.0500 (0.0500)  time: 1.0090  data: 0.0004  max mem: 78493
Epoch: [151]  [220/312]  eta: 0:01:39  lr: 0.002186  min_lr: 0.002186  loss: 2.3031 (2.2734)  weight_decay: 0.0500 (0.0500)  time: 1.0087  data: 0.0004  max mem: 78493
Epoch: [151]  [230/312]  eta: 0:01:28  lr: 0.002186  min_lr: 0.002186  loss: 2.4229 (2.2737)  weight_decay: 0.0500 (0.0500)  time: 1.0071  data: 0.0004  max mem: 78493
Epoch: [151]  [240/312]  eta: 0:01:17  lr: 0.002185  min_lr: 0.002185  loss: 2.4038 (2.2753)  weight_decay: 0.0500 (0.0500)  time: 1.0089  data: 0.0005  max mem: 78493
Epoch: [151]  [250/312]  eta: 0:01:06  lr: 0.002184  min_lr: 0.002184  loss: 2.4038 (2.2784)  weight_decay: 0.0500 (0.0500)  time: 1.0093  data: 0.0005  max mem: 78493
Epoch: [151]  [260/312]  eta: 0:00:55  lr: 0.002183  min_lr: 0.002183  loss: 2.4058 (2.2762)  weight_decay: 0.0500 (0.0500)  time: 1.0078  data: 0.0005  max mem: 78493
Epoch: [151]  [270/312]  eta: 0:00:45  lr: 0.002183  min_lr: 0.002183  loss: 2.1607 (2.2750)  weight_decay: 0.0500 (0.0500)  time: 1.0063  data: 0.0005  max mem: 78493
Epoch: [151]  [280/312]  eta: 0:00:34  lr: 0.002182  min_lr: 0.002182  loss: 2.1607 (2.2739)  weight_decay: 0.0500 (0.0500)  time: 1.0066  data: 0.0011  max mem: 78493
Epoch: [151]  [290/312]  eta: 0:00:23  lr: 0.002181  min_lr: 0.002181  loss: 2.2346 (2.2780)  weight_decay: 0.0500 (0.0500)  time: 1.0047  data: 0.0009  max mem: 78493
Epoch: [151]  [300/312]  eta: 0:00:12  lr: 0.002181  min_lr: 0.002181  loss: 2.4273 (2.2819)  weight_decay: 0.0500 (0.0500)  time: 1.0019  data: 0.0001  max mem: 78493
Epoch: [151]  [310/312]  eta: 0:00:02  lr: 0.002180  min_lr: 0.002180  loss: 2.4389 (2.2846)  weight_decay: 0.0500 (0.0500)  time: 1.0017  data: 0.0001  max mem: 78493
Epoch: [151]  [311/312]  eta: 0:00:01  lr: 0.002180  min_lr: 0.002180  loss: 2.4389 (2.2853)  weight_decay: 0.0500 (0.0500)  time: 1.0017  data: 0.0001  max mem: 78493
Epoch: [151] Total time: 0:05:33 (1.0691 s / it)
Averaged stats: lr: 0.002180  min_lr: 0.002180  loss: 2.4389 (2.2762)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:17  loss: 0.6977 (0.6977)  acc1: 82.8125 (82.8125)  acc5: 95.3125 (95.3125)  time: 8.5815  data: 8.3156  max mem: 78493
Test:  [8/9]  eta: 0:00:01  loss: 0.9689 (0.9055)  acc1: 77.0833 (76.4000)  acc5: 92.9688 (93.4080)  time: 1.1534  data: 0.9240  max mem: 78493
Test: Total time: 0:00:10 (1.1769 s / it)
* Acc@1 76.764 Acc@5 93.388 loss 0.901
Accuracy of the model on the 50000 test images: 76.8%
Max accuracy: 76.98%
Epoch: [152]  [  0/312]  eta: 1:25:04  lr: 0.002180  min_lr: 0.002180  loss: 2.5003 (2.5003)  weight_decay: 0.0500 (0.0500)  time: 16.3611  data: 12.6718  max mem: 78493
Epoch: [152]  [ 10/312]  eta: 0:14:02  lr: 0.002179  min_lr: 0.002179  loss: 2.3666 (2.3787)  weight_decay: 0.0500 (0.0500)  time: 2.7883  data: 1.2511  max mem: 78493
Epoch: [152]  [ 20/312]  eta: 0:09:26  lr: 0.002178  min_lr: 0.002178  loss: 2.3666 (2.3595)  weight_decay: 0.0500 (0.0500)  time: 1.2200  data: 0.0548  max mem: 78493
Epoch: [152]  [ 30/312]  eta: 0:07:42  lr: 0.002178  min_lr: 0.002178  loss: 2.1959 (2.2923)  weight_decay: 0.0500 (0.0500)  time: 1.0081  data: 0.0004  max mem: 78493
Epoch: [152]  [ 40/312]  eta: 0:06:44  lr: 0.002177  min_lr: 0.002177  loss: 2.1407 (2.2656)  weight_decay: 0.0500 (0.0500)  time: 1.0094  data: 0.0013  max mem: 78493
Epoch: [152]  [ 50/312]  eta: 0:06:04  lr: 0.002176  min_lr: 0.002176  loss: 2.4293 (2.3128)  weight_decay: 0.0500 (0.0500)  time: 1.0094  data: 0.0012  max mem: 78493
Epoch: [152]  [ 60/312]  eta: 0:05:35  lr: 0.002175  min_lr: 0.002175  loss: 2.4293 (2.3157)  weight_decay: 0.0500 (0.0500)  time: 1.0074  data: 0.0004  max mem: 78493
Epoch: [152]  [ 70/312]  eta: 0:05:10  lr: 0.002175  min_lr: 0.002175  loss: 2.3256 (2.3075)  weight_decay: 0.0500 (0.0500)  time: 1.0077  data: 0.0004  max mem: 78493
Epoch: [152]  [ 80/312]  eta: 0:04:50  lr: 0.002174  min_lr: 0.002174  loss: 2.1362 (2.2855)  weight_decay: 0.0500 (0.0500)  time: 1.0092  data: 0.0005  max mem: 78493
Epoch: [152]  [ 90/312]  eta: 0:04:31  lr: 0.002173  min_lr: 0.002173  loss: 2.0906 (2.2694)  weight_decay: 0.0500 (0.0500)  time: 1.0098  data: 0.0004  max mem: 78493
Epoch: [152]  [100/312]  eta: 0:04:14  lr: 0.002173  min_lr: 0.002173  loss: 2.4115 (2.2795)  weight_decay: 0.0500 (0.0500)  time: 1.0073  data: 0.0005  max mem: 78493
Epoch: [152]  [110/312]  eta: 0:03:59  lr: 0.002172  min_lr: 0.002172  loss: 2.4635 (2.2887)  weight_decay: 0.0500 (0.0500)  time: 1.0089  data: 0.0005  max mem: 78493
Epoch: [152]  [120/312]  eta: 0:03:44  lr: 0.002171  min_lr: 0.002171  loss: 2.3327 (2.2922)  weight_decay: 0.0500 (0.0500)  time: 1.0090  data: 0.0004  max mem: 78493
Epoch: [152]  [130/312]  eta: 0:03:30  lr: 0.002170  min_lr: 0.002170  loss: 2.2991 (2.2884)  weight_decay: 0.0500 (0.0500)  time: 1.0077  data: 0.0004  max mem: 78493
Epoch: [152]  [140/312]  eta: 0:03:17  lr: 0.002170  min_lr: 0.002170  loss: 2.3130 (2.2862)  weight_decay: 0.0500 (0.0500)  time: 1.0085  data: 0.0004  max mem: 78493
Epoch: [152]  [150/312]  eta: 0:03:04  lr: 0.002169  min_lr: 0.002169  loss: 2.3035 (2.2780)  weight_decay: 0.0500 (0.0500)  time: 1.0076  data: 0.0004  max mem: 78493
Epoch: [152]  [160/312]  eta: 0:02:51  lr: 0.002168  min_lr: 0.002168  loss: 2.3437 (2.2809)  weight_decay: 0.0500 (0.0500)  time: 1.0079  data: 0.0004  max mem: 78493
Epoch: [152]  [170/312]  eta: 0:02:39  lr: 0.002168  min_lr: 0.002168  loss: 2.4164 (2.2813)  weight_decay: 0.0500 (0.0500)  time: 1.0075  data: 0.0004  max mem: 78493
Epoch: [152]  [180/312]  eta: 0:02:27  lr: 0.002167  min_lr: 0.002167  loss: 2.4018 (2.2857)  weight_decay: 0.0500 (0.0500)  time: 1.0060  data: 0.0004  max mem: 78493
Epoch: [152]  [190/312]  eta: 0:02:15  lr: 0.002166  min_lr: 0.002166  loss: 2.3503 (2.2819)  weight_decay: 0.0500 (0.0500)  time: 1.0064  data: 0.0004  max mem: 78493
Epoch: [152]  [200/312]  eta: 0:02:03  lr: 0.002165  min_lr: 0.002165  loss: 2.3142 (2.2828)  weight_decay: 0.0500 (0.0500)  time: 1.0076  data: 0.0005  max mem: 78493
Epoch: [152]  [210/312]  eta: 0:01:52  lr: 0.002165  min_lr: 0.002165  loss: 2.2594 (2.2802)  weight_decay: 0.0500 (0.0500)  time: 1.0061  data: 0.0005  max mem: 78493
Epoch: [152]  [220/312]  eta: 0:01:40  lr: 0.002164  min_lr: 0.002164  loss: 2.3162 (2.2871)  weight_decay: 0.0500 (0.0500)  time: 1.0059  data: 0.0004  max mem: 78493
Epoch: [152]  [230/312]  eta: 0:01:29  lr: 0.002163  min_lr: 0.002163  loss: 2.3326 (2.2829)  weight_decay: 0.0500 (0.0500)  time: 1.0067  data: 0.0004  max mem: 78493
Epoch: [152]  [240/312]  eta: 0:01:18  lr: 0.002163  min_lr: 0.002163  loss: 2.2959 (2.2833)  weight_decay: 0.0500 (0.0500)  time: 1.0055  data: 0.0004  max mem: 78493
Epoch: [152]  [250/312]  eta: 0:01:07  lr: 0.002162  min_lr: 0.002162  loss: 2.3792 (2.2879)  weight_decay: 0.0500 (0.0500)  time: 1.0053  data: 0.0004  max mem: 78493
Epoch: [152]  [260/312]  eta: 0:00:56  lr: 0.002161  min_lr: 0.002161  loss: 2.3792 (2.2825)  weight_decay: 0.0500 (0.0500)  time: 1.0065  data: 0.0004  max mem: 78493
Epoch: [152]  [270/312]  eta: 0:00:45  lr: 0.002160  min_lr: 0.002160  loss: 2.4114 (2.2865)  weight_decay: 0.0500 (0.0500)  time: 1.0056  data: 0.0005  max mem: 78493
Epoch: [152]  [280/312]  eta: 0:00:34  lr: 0.002160  min_lr: 0.002160  loss: 2.4114 (2.2866)  weight_decay: 0.0500 (0.0500)  time: 1.0065  data: 0.0017  max mem: 78493
Epoch: [152]  [290/312]  eta: 0:00:23  lr: 0.002159  min_lr: 0.002159  loss: 2.4584 (2.2917)  weight_decay: 0.0500 (0.0500)  time: 1.0055  data: 0.0015  max mem: 78493
Epoch: [152]  [300/312]  eta: 0:00:12  lr: 0.002158  min_lr: 0.002158  loss: 2.4870 (2.2928)  weight_decay: 0.0500 (0.0500)  time: 1.0016  data: 0.0001  max mem: 78493
Epoch: [152]  [310/312]  eta: 0:00:02  lr: 0.002158  min_lr: 0.002158  loss: 2.2860 (2.2892)  weight_decay: 0.0500 (0.0500)  time: 1.0012  data: 0.0001  max mem: 78493
Epoch: [152]  [311/312]  eta: 0:00:01  lr: 0.002157  min_lr: 0.002157  loss: 2.2860 (2.2906)  weight_decay: 0.0500 (0.0500)  time: 1.0013  data: 0.0001  max mem: 78493
Epoch: [152] Total time: 0:05:35 (1.0756 s / it)
Averaged stats: lr: 0.002157  min_lr: 0.002157  loss: 2.2860 (2.2756)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:15  loss: 0.6416 (0.6416)  acc1: 82.1615 (82.1615)  acc5: 96.0938 (96.0938)  time: 8.4377  data: 8.1703  max mem: 78493
Test:  [8/9]  eta: 0:00:01  loss: 1.0258 (0.9174)  acc1: 75.2604 (75.8720)  acc5: 93.8802 (93.2000)  time: 1.1370  data: 0.9079  max mem: 78493
Test: Total time: 0:00:10 (1.1652 s / it)
* Acc@1 76.526 Acc@5 93.328 loss 0.908
Accuracy of the model on the 50000 test images: 76.5%
Max accuracy: 76.98%
Epoch: [153]  [  0/312]  eta: 1:27:20  lr: 0.002157  min_lr: 0.002157  loss: 2.1183 (2.1183)  weight_decay: 0.0500 (0.0500)  time: 16.7978  data: 13.9879  max mem: 78493
Epoch: [153]  [ 10/312]  eta: 0:13:30  lr: 0.002157  min_lr: 0.002157  loss: 2.4226 (2.3268)  weight_decay: 0.0500 (0.0500)  time: 2.6847  data: 1.2762  max mem: 78493
Epoch: [153]  [ 20/312]  eta: 0:09:11  lr: 0.002156  min_lr: 0.002156  loss: 2.4344 (2.3895)  weight_decay: 0.0500 (0.0500)  time: 1.1423  data: 0.0028  max mem: 78493
Epoch: [153]  [ 30/312]  eta: 0:07:32  lr: 0.002155  min_lr: 0.002155  loss: 2.4642 (2.3685)  weight_decay: 0.0500 (0.0500)  time: 1.0089  data: 0.0005  max mem: 78493
Epoch: [153]  [ 40/312]  eta: 0:06:36  lr: 0.002155  min_lr: 0.002155  loss: 2.3967 (2.3746)  weight_decay: 0.0500 (0.0500)  time: 1.0070  data: 0.0004  max mem: 78493
Epoch: [153]  [ 50/312]  eta: 0:05:59  lr: 0.002154  min_lr: 0.002154  loss: 2.3965 (2.3690)  weight_decay: 0.0500 (0.0500)  time: 1.0088  data: 0.0004  max mem: 78493
Epoch: [153]  [ 60/312]  eta: 0:05:30  lr: 0.002153  min_lr: 0.002153  loss: 2.4765 (2.3965)  weight_decay: 0.0500 (0.0500)  time: 1.0088  data: 0.0004  max mem: 78493
Epoch: [153]  [ 70/312]  eta: 0:05:06  lr: 0.002152  min_lr: 0.002152  loss: 2.4705 (2.3596)  weight_decay: 0.0500 (0.0500)  time: 1.0060  data: 0.0004  max mem: 78493
Epoch: [153]  [ 80/312]  eta: 0:04:46  lr: 0.002152  min_lr: 0.002152  loss: 2.1368 (2.3325)  weight_decay: 0.0500 (0.0500)  time: 1.0044  data: 0.0005  max mem: 78493
Epoch: [153]  [ 90/312]  eta: 0:04:28  lr: 0.002151  min_lr: 0.002151  loss: 2.2968 (2.3420)  weight_decay: 0.0500 (0.0500)  time: 1.0048  data: 0.0005  max mem: 78493
Epoch: [153]  [100/312]  eta: 0:04:12  lr: 0.002150  min_lr: 0.002150  loss: 2.2377 (2.3245)  weight_decay: 0.0500 (0.0500)  time: 1.0060  data: 0.0005  max mem: 78493
Epoch: [153]  [110/312]  eta: 0:03:57  lr: 0.002149  min_lr: 0.002149  loss: 2.2292 (2.3173)  weight_decay: 0.0500 (0.0500)  time: 1.0082  data: 0.0005  max mem: 78493
Epoch: [153]  [120/312]  eta: 0:03:42  lr: 0.002149  min_lr: 0.002149  loss: 2.3684 (2.3189)  weight_decay: 0.0500 (0.0500)  time: 1.0101  data: 0.0004  max mem: 78493
Epoch: [153]  [130/312]  eta: 0:03:28  lr: 0.002148  min_lr: 0.002148  loss: 2.3684 (2.3148)  weight_decay: 0.0500 (0.0500)  time: 1.0078  data: 0.0004  max mem: 78493
Epoch: [153]  [140/312]  eta: 0:03:15  lr: 0.002147  min_lr: 0.002147  loss: 2.4244 (2.3238)  weight_decay: 0.0500 (0.0500)  time: 1.0072  data: 0.0004  max mem: 78493
Epoch: [153]  [150/312]  eta: 0:03:03  lr: 0.002147  min_lr: 0.002147  loss: 2.4587 (2.3217)  weight_decay: 0.0500 (0.0500)  time: 1.0086  data: 0.0004  max mem: 78493
Epoch: [153]  [160/312]  eta: 0:02:50  lr: 0.002146  min_lr: 0.002146  loss: 2.2511 (2.3146)  weight_decay: 0.0500 (0.0500)  time: 1.0070  data: 0.0004  max mem: 78493
Epoch: [153]  [170/312]  eta: 0:02:38  lr: 0.002145  min_lr: 0.002145  loss: 2.3828 (2.3205)  weight_decay: 0.0500 (0.0500)  time: 1.0052  data: 0.0004  max mem: 78493
Epoch: [153]  [180/312]  eta: 0:02:26  lr: 0.002144  min_lr: 0.002144  loss: 2.3584 (2.3192)  weight_decay: 0.0500 (0.0500)  time: 1.0046  data: 0.0004  max mem: 78493
Epoch: [153]  [190/312]  eta: 0:02:14  lr: 0.002144  min_lr: 0.002144  loss: 2.2693 (2.3086)  weight_decay: 0.0500 (0.0500)  time: 1.0076  data: 0.0005  max mem: 78493
Epoch: [153]  [200/312]  eta: 0:02:03  lr: 0.002143  min_lr: 0.002143  loss: 2.2720 (2.3124)  weight_decay: 0.0500 (0.0500)  time: 1.0123  data: 0.0004  max mem: 78493
Epoch: [153]  [210/312]  eta: 0:01:51  lr: 0.002142  min_lr: 0.002142  loss: 2.3506 (2.3100)  weight_decay: 0.0500 (0.0500)  time: 1.0110  data: 0.0004  max mem: 78493
Epoch: [153]  [220/312]  eta: 0:01:40  lr: 0.002142  min_lr: 0.002142  loss: 2.2001 (2.3038)  weight_decay: 0.0500 (0.0500)  time: 1.0084  data: 0.0005  max mem: 78493
Epoch: [153]  [230/312]  eta: 0:01:29  lr: 0.002141  min_lr: 0.002141  loss: 2.2001 (2.3017)  weight_decay: 0.0500 (0.0500)  time: 1.0077  data: 0.0005  max mem: 78493
Epoch: [153]  [240/312]  eta: 0:01:18  lr: 0.002140  min_lr: 0.002140  loss: 2.1576 (2.2939)  weight_decay: 0.0500 (0.0500)  time: 1.0065  data: 0.0005  max mem: 78493
Epoch: [153]  [250/312]  eta: 0:01:07  lr: 0.002139  min_lr: 0.002139  loss: 2.0715 (2.2944)  weight_decay: 0.0500 (0.0500)  time: 1.0067  data: 0.0004  max mem: 78493
Epoch: [153]  [260/312]  eta: 0:00:56  lr: 0.002139  min_lr: 0.002139  loss: 2.4196 (2.2983)  weight_decay: 0.0500 (0.0500)  time: 1.0060  data: 0.0004  max mem: 78493
Epoch: [153]  [270/312]  eta: 0:00:45  lr: 0.002138  min_lr: 0.002138  loss: 2.4734 (2.3030)  weight_decay: 0.0500 (0.0500)  time: 1.0046  data: 0.0004  max mem: 78493
Epoch: [153]  [280/312]  eta: 0:00:34  lr: 0.002137  min_lr: 0.002137  loss: 2.4899 (2.3074)  weight_decay: 0.0500 (0.0500)  time: 1.0057  data: 0.0010  max mem: 78493
Epoch: [153]  [290/312]  eta: 0:00:23  lr: 0.002137  min_lr: 0.002137  loss: 2.3192 (2.3047)  weight_decay: 0.0500 (0.0500)  time: 1.0046  data: 0.0009  max mem: 78493
Epoch: [153]  [300/312]  eta: 0:00:12  lr: 0.002136  min_lr: 0.002136  loss: 2.2910 (2.3069)  weight_decay: 0.0500 (0.0500)  time: 1.0020  data: 0.0001  max mem: 78493
Epoch: [153]  [310/312]  eta: 0:00:02  lr: 0.002135  min_lr: 0.002135  loss: 2.3820 (2.3075)  weight_decay: 0.0500 (0.0500)  time: 1.0018  data: 0.0001  max mem: 78493
Epoch: [153]  [311/312]  eta: 0:00:01  lr: 0.002135  min_lr: 0.002135  loss: 2.3935 (2.3084)  weight_decay: 0.0500 (0.0500)  time: 1.0018  data: 0.0001  max mem: 78493
Epoch: [153] Total time: 0:05:34 (1.0719 s / it)
Averaged stats: lr: 0.002135  min_lr: 0.002135  loss: 2.3935 (2.2728)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:15  loss: 0.6751 (0.6751)  acc1: 83.9844 (83.9844)  acc5: 96.2240 (96.2240)  time: 8.3598  data: 8.0891  max mem: 78493
Test:  [8/9]  eta: 0:00:01  loss: 0.9578 (0.9066)  acc1: 77.6042 (76.5280)  acc5: 94.0104 (93.5680)  time: 1.1272  data: 0.8989  max mem: 78493
Test: Total time: 0:00:10 (1.1613 s / it)
* Acc@1 76.812 Acc@5 93.530 loss 0.906
Accuracy of the model on the 50000 test images: 76.8%
Max accuracy: 76.98%
Epoch: [154]  [  0/312]  eta: 1:28:37  lr: 0.002135  min_lr: 0.002135  loss: 2.3791 (2.3791)  weight_decay: 0.0500 (0.0500)  time: 17.0429  data: 12.5975  max mem: 78493
Epoch: [154]  [ 10/312]  eta: 0:13:00  lr: 0.002134  min_lr: 0.002134  loss: 2.3791 (2.2178)  weight_decay: 0.0500 (0.0500)  time: 2.5850  data: 1.1480  max mem: 78493
Epoch: [154]  [ 20/312]  eta: 0:08:58  lr: 0.002134  min_lr: 0.002134  loss: 2.4164 (2.2334)  weight_decay: 0.0500 (0.0500)  time: 1.0844  data: 0.0018  max mem: 78493
Epoch: [154]  [ 30/312]  eta: 0:07:23  lr: 0.002133  min_lr: 0.002133  loss: 2.1934 (2.2020)  weight_decay: 0.0500 (0.0500)  time: 1.0177  data: 0.0005  max mem: 78493
Epoch: [154]  [ 40/312]  eta: 0:06:30  lr: 0.002132  min_lr: 0.002132  loss: 2.0736 (2.2026)  weight_decay: 0.0500 (0.0500)  time: 1.0060  data: 0.0004  max mem: 78493
Epoch: [154]  [ 50/312]  eta: 0:05:54  lr: 0.002131  min_lr: 0.002131  loss: 1.9559 (2.1454)  weight_decay: 0.0500 (0.0500)  time: 1.0066  data: 0.0004  max mem: 78493
Epoch: [154]  [ 60/312]  eta: 0:05:26  lr: 0.002131  min_lr: 0.002131  loss: 1.9665 (2.1696)  weight_decay: 0.0500 (0.0500)  time: 1.0082  data: 0.0004  max mem: 78493
Epoch: [154]  [ 70/312]  eta: 0:05:03  lr: 0.002130  min_lr: 0.002130  loss: 2.2764 (2.1703)  weight_decay: 0.0500 (0.0500)  time: 1.0074  data: 0.0005  max mem: 78493
Epoch: [154]  [ 80/312]  eta: 0:04:43  lr: 0.002129  min_lr: 0.002129  loss: 2.2764 (2.1982)  weight_decay: 0.0500 (0.0500)  time: 1.0065  data: 0.0004  max mem: 78493
Epoch: [154]  [ 90/312]  eta: 0:04:26  lr: 0.002129  min_lr: 0.002129  loss: 2.3785 (2.2001)  weight_decay: 0.0500 (0.0500)  time: 1.0088  data: 0.0004  max mem: 78493
Epoch: [154]  [100/312]  eta: 0:04:10  lr: 0.002128  min_lr: 0.002128  loss: 2.2571 (2.1981)  weight_decay: 0.0500 (0.0500)  time: 1.0082  data: 0.0011  max mem: 78493
Epoch: [154]  [110/312]  eta: 0:03:55  lr: 0.002127  min_lr: 0.002127  loss: 2.3044 (2.2163)  weight_decay: 0.0500 (0.0500)  time: 1.0072  data: 0.0011  max mem: 78493
Epoch: [154]  [120/312]  eta: 0:03:41  lr: 0.002126  min_lr: 0.002126  loss: 2.3986 (2.2252)  weight_decay: 0.0500 (0.0500)  time: 1.0074  data: 0.0005  max mem: 78493
Epoch: [154]  [130/312]  eta: 0:03:27  lr: 0.002126  min_lr: 0.002126  loss: 2.3308 (2.2159)  weight_decay: 0.0500 (0.0500)  time: 1.0059  data: 0.0004  max mem: 78493
Epoch: [154]  [140/312]  eta: 0:03:14  lr: 0.002125  min_lr: 0.002125  loss: 2.3308 (2.2298)  weight_decay: 0.0500 (0.0500)  time: 1.0072  data: 0.0004  max mem: 78493
Epoch: [154]  [150/312]  eta: 0:03:02  lr: 0.002124  min_lr: 0.002124  loss: 2.3573 (2.2186)  weight_decay: 0.0500 (0.0500)  time: 1.0094  data: 0.0005  max mem: 78493
Epoch: [154]  [160/312]  eta: 0:02:49  lr: 0.002124  min_lr: 0.002124  loss: 2.2343 (2.2261)  weight_decay: 0.0500 (0.0500)  time: 1.0105  data: 0.0005  max mem: 78493
Epoch: [154]  [170/312]  eta: 0:02:37  lr: 0.002123  min_lr: 0.002123  loss: 2.3940 (2.2365)  weight_decay: 0.0500 (0.0500)  time: 1.0112  data: 0.0004  max mem: 78493
Epoch: [154]  [180/312]  eta: 0:02:25  lr: 0.002122  min_lr: 0.002122  loss: 2.4349 (2.2423)  weight_decay: 0.0500 (0.0500)  time: 1.0087  data: 0.0004  max mem: 78493
Epoch: [154]  [190/312]  eta: 0:02:14  lr: 0.002121  min_lr: 0.002121  loss: 2.4349 (2.2552)  weight_decay: 0.0500 (0.0500)  time: 1.0077  data: 0.0004  max mem: 78493
Epoch: [154]  [200/312]  eta: 0:02:02  lr: 0.002121  min_lr: 0.002121  loss: 2.4271 (2.2610)  weight_decay: 0.0500 (0.0500)  time: 1.0088  data: 0.0004  max mem: 78493
Epoch: [154]  [210/312]  eta: 0:01:51  lr: 0.002120  min_lr: 0.002120  loss: 2.3507 (2.2573)  weight_decay: 0.0500 (0.0500)  time: 1.0084  data: 0.0004  max mem: 78493
Epoch: [154]  [220/312]  eta: 0:01:40  lr: 0.002119  min_lr: 0.002119  loss: 2.3507 (2.2541)  weight_decay: 0.0500 (0.0500)  time: 1.0072  data: 0.0004  max mem: 78493
Epoch: [154]  [230/312]  eta: 0:01:28  lr: 0.002118  min_lr: 0.002118  loss: 2.1942 (2.2542)  weight_decay: 0.0500 (0.0500)  time: 1.0070  data: 0.0005  max mem: 78493
Epoch: [154]  [240/312]  eta: 0:01:17  lr: 0.002118  min_lr: 0.002118  loss: 2.5366 (2.2682)  weight_decay: 0.0500 (0.0500)  time: 1.0056  data: 0.0004  max mem: 78493
Epoch: [154]  [250/312]  eta: 0:01:06  lr: 0.002117  min_lr: 0.002117  loss: 2.4542 (2.2642)  weight_decay: 0.0500 (0.0500)  time: 1.0042  data: 0.0004  max mem: 78493
Epoch: [154]  [260/312]  eta: 0:00:55  lr: 0.002116  min_lr: 0.002116  loss: 2.1099 (2.2575)  weight_decay: 0.0500 (0.0500)  time: 1.0047  data: 0.0005  max mem: 78493
Epoch: [154]  [270/312]  eta: 0:00:45  lr: 0.002116  min_lr: 0.002116  loss: 2.0317 (2.2516)  weight_decay: 0.0500 (0.0500)  time: 1.0050  data: 0.0004  max mem: 78493
Epoch: [154]  [280/312]  eta: 0:00:34  lr: 0.002115  min_lr: 0.002115  loss: 2.1743 (2.2500)  weight_decay: 0.0500 (0.0500)  time: 1.0052  data: 0.0010  max mem: 78493
Epoch: [154]  [290/312]  eta: 0:00:23  lr: 0.002114  min_lr: 0.002114  loss: 2.3692 (2.2580)  weight_decay: 0.0500 (0.0500)  time: 1.0036  data: 0.0009  max mem: 78493
Epoch: [154]  [300/312]  eta: 0:00:12  lr: 0.002113  min_lr: 0.002113  loss: 2.3833 (2.2568)  weight_decay: 0.0500 (0.0500)  time: 1.0019  data: 0.0001  max mem: 78493
Epoch: [154]  [310/312]  eta: 0:00:02  lr: 0.002113  min_lr: 0.002113  loss: 2.3779 (2.2562)  weight_decay: 0.0500 (0.0500)  time: 1.0018  data: 0.0001  max mem: 78493
Epoch: [154]  [311/312]  eta: 0:00:01  lr: 0.002113  min_lr: 0.002113  loss: 2.3856 (2.2570)  weight_decay: 0.0500 (0.0500)  time: 1.0018  data: 0.0001  max mem: 78493
Epoch: [154] Total time: 0:05:33 (1.0686 s / it)
Averaged stats: lr: 0.002113  min_lr: 0.002113  loss: 2.3856 (2.2566)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:10  loss: 0.6281 (0.6281)  acc1: 84.5052 (84.5052)  acc5: 96.2240 (96.2240)  time: 7.8388  data: 7.5714  max mem: 78493
Test:  [8/9]  eta: 0:00:01  loss: 0.9624 (0.9010)  acc1: 74.7396 (76.3840)  acc5: 94.6615 (93.5840)  time: 1.0693  data: 0.8414  max mem: 78493
Test: Total time: 0:00:09 (1.0790 s / it)
* Acc@1 76.780 Acc@5 93.504 loss 0.893
Accuracy of the model on the 50000 test images: 76.8%
Max accuracy: 76.98%
Epoch: [155]  [  0/312]  eta: 1:25:30  lr: 0.002113  min_lr: 0.002113  loss: 2.3660 (2.3660)  weight_decay: 0.0500 (0.0500)  time: 16.4427  data: 14.4757  max mem: 78493
Epoch: [155]  [ 10/312]  eta: 0:12:30  lr: 0.002112  min_lr: 0.002112  loss: 2.4047 (2.3641)  weight_decay: 0.0500 (0.0500)  time: 2.4853  data: 1.3167  max mem: 78493
Epoch: [155]  [ 20/312]  eta: 0:08:44  lr: 0.002111  min_lr: 0.002111  loss: 2.4047 (2.3386)  weight_decay: 0.0500 (0.0500)  time: 1.0654  data: 0.0007  max mem: 78493
Epoch: [155]  [ 30/312]  eta: 0:07:15  lr: 0.002110  min_lr: 0.002110  loss: 2.3221 (2.3392)  weight_decay: 0.0500 (0.0500)  time: 1.0256  data: 0.0005  max mem: 78493
Epoch: [155]  [ 40/312]  eta: 0:06:24  lr: 0.002110  min_lr: 0.002110  loss: 2.4488 (2.3840)  weight_decay: 0.0500 (0.0500)  time: 1.0073  data: 0.0004  max mem: 78493
Epoch: [155]  [ 50/312]  eta: 0:05:49  lr: 0.002109  min_lr: 0.002109  loss: 2.4488 (2.3469)  weight_decay: 0.0500 (0.0500)  time: 1.0081  data: 0.0004  max mem: 78493
Epoch: [155]  [ 60/312]  eta: 0:05:22  lr: 0.002108  min_lr: 0.002108  loss: 2.3266 (2.3400)  weight_decay: 0.0500 (0.0500)  time: 1.0129  data: 0.0004  max mem: 78493
Epoch: [155]  [ 70/312]  eta: 0:05:00  lr: 0.002108  min_lr: 0.002108  loss: 2.2850 (2.3103)  weight_decay: 0.0500 (0.0500)  time: 1.0115  data: 0.0004  max mem: 78493
Epoch: [155]  [ 80/312]  eta: 0:04:41  lr: 0.002107  min_lr: 0.002107  loss: 2.4479 (2.3414)  weight_decay: 0.0500 (0.0500)  time: 1.0094  data: 0.0004  max mem: 78493
Epoch: [155]  [ 90/312]  eta: 0:04:24  lr: 0.002106  min_lr: 0.002106  loss: 2.4479 (2.3389)  weight_decay: 0.0500 (0.0500)  time: 1.0088  data: 0.0004  max mem: 78493
Epoch: [155]  [100/312]  eta: 0:04:08  lr: 0.002105  min_lr: 0.002105  loss: 2.2962 (2.3258)  weight_decay: 0.0500 (0.0500)  time: 1.0068  data: 0.0004  max mem: 78493
Epoch: [155]  [110/312]  eta: 0:03:53  lr: 0.002105  min_lr: 0.002105  loss: 2.2755 (2.3054)  weight_decay: 0.0500 (0.0500)  time: 1.0067  data: 0.0004  max mem: 78493
Epoch: [155]  [120/312]  eta: 0:03:39  lr: 0.002104  min_lr: 0.002104  loss: 2.3997 (2.3156)  weight_decay: 0.0500 (0.0500)  time: 1.0063  data: 0.0004  max mem: 78493
Epoch: [155]  [130/312]  eta: 0:03:26  lr: 0.002103  min_lr: 0.002103  loss: 2.4512 (2.3174)  weight_decay: 0.0500 (0.0500)  time: 1.0067  data: 0.0004  max mem: 78493
Epoch: [155]  [140/312]  eta: 0:03:13  lr: 0.002103  min_lr: 0.002103  loss: 2.1947 (2.3165)  weight_decay: 0.0500 (0.0500)  time: 1.0089  data: 0.0004  max mem: 78493
Epoch: [155]  [150/312]  eta: 0:03:01  lr: 0.002102  min_lr: 0.002102  loss: 2.2683 (2.3201)  weight_decay: 0.0500 (0.0500)  time: 1.0088  data: 0.0004  max mem: 78493
Epoch: [155]  [160/312]  eta: 0:02:48  lr: 0.002101  min_lr: 0.002101  loss: 2.3095 (2.3097)  weight_decay: 0.0500 (0.0500)  time: 1.0083  data: 0.0004  max mem: 78493
Epoch: [155]  [170/312]  eta: 0:02:36  lr: 0.002100  min_lr: 0.002100  loss: 2.1538 (2.3036)  weight_decay: 0.0500 (0.0500)  time: 1.0098  data: 0.0012  max mem: 78493
Epoch: [155]  [180/312]  eta: 0:02:25  lr: 0.002100  min_lr: 0.002100  loss: 2.1095 (2.2969)  weight_decay: 0.0500 (0.0500)  time: 1.0081  data: 0.0012  max mem: 78493
Epoch: [155]  [190/312]  eta: 0:02:13  lr: 0.002099  min_lr: 0.002099  loss: 2.1095 (2.2879)  weight_decay: 0.0500 (0.0500)  time: 1.0069  data: 0.0005  max mem: 78493
Epoch: [155]  [200/312]  eta: 0:02:02  lr: 0.002098  min_lr: 0.002098  loss: 2.3377 (2.2987)  weight_decay: 0.0500 (0.0500)  time: 1.0071  data: 0.0004  max mem: 78493
Epoch: [155]  [210/312]  eta: 0:01:50  lr: 0.002098  min_lr: 0.002098  loss: 2.4410 (2.2960)  weight_decay: 0.0500 (0.0500)  time: 1.0064  data: 0.0004  max mem: 78493
Epoch: [155]  [220/312]  eta: 0:01:39  lr: 0.002097  min_lr: 0.002097  loss: 2.1896 (2.2929)  weight_decay: 0.0500 (0.0500)  time: 1.0055  data: 0.0005  max mem: 78493
Epoch: [155]  [230/312]  eta: 0:01:28  lr: 0.002096  min_lr: 0.002096  loss: 2.3105 (2.2909)  weight_decay: 0.0500 (0.0500)  time: 1.0042  data: 0.0005  max mem: 78493
Epoch: [155]  [240/312]  eta: 0:01:17  lr: 0.002095  min_lr: 0.002095  loss: 2.4051 (2.2883)  weight_decay: 0.0500 (0.0500)  time: 1.0043  data: 0.0004  max mem: 78493
Epoch: [155]  [250/312]  eta: 0:01:06  lr: 0.002095  min_lr: 0.002095  loss: 2.4051 (2.2897)  weight_decay: 0.0500 (0.0500)  time: 1.0048  data: 0.0012  max mem: 78493
Epoch: [155]  [260/312]  eta: 0:00:55  lr: 0.002094  min_lr: 0.002094  loss: 2.4661 (2.2934)  weight_decay: 0.0500 (0.0500)  time: 1.0061  data: 0.0012  max mem: 78493
Epoch: [155]  [270/312]  eta: 0:00:44  lr: 0.002093  min_lr: 0.002093  loss: 2.4662 (2.2979)  weight_decay: 0.0500 (0.0500)  time: 1.0060  data: 0.0004  max mem: 78493
Epoch: [155]  [280/312]  eta: 0:00:34  lr: 0.002093  min_lr: 0.002093  loss: 2.3029 (2.2923)  weight_decay: 0.0500 (0.0500)  time: 1.0052  data: 0.0010  max mem: 78493
Epoch: [155]  [290/312]  eta: 0:00:23  lr: 0.002092  min_lr: 0.002092  loss: 2.2269 (2.2945)  weight_decay: 0.0500 (0.0500)  time: 1.0037  data: 0.0009  max mem: 78493
Epoch: [155]  [300/312]  eta: 0:00:12  lr: 0.002091  min_lr: 0.002091  loss: 2.2581 (2.2888)  weight_decay: 0.0500 (0.0500)  time: 1.0018  data: 0.0001  max mem: 78493
Epoch: [155]  [310/312]  eta: 0:00:02  lr: 0.002090  min_lr: 0.002090  loss: 2.2532 (2.2835)  weight_decay: 0.0500 (0.0500)  time: 1.0016  data: 0.0001  max mem: 78493
Epoch: [155]  [311/312]  eta: 0:00:01  lr: 0.002090  min_lr: 0.002090  loss: 2.0303 (2.2827)  weight_decay: 0.0500 (0.0500)  time: 1.0016  data: 0.0001  max mem: 78493
Epoch: [155] Total time: 0:05:32 (1.0657 s / it)
Averaged stats: lr: 0.002090  min_lr: 0.002090  loss: 2.0303 (2.2662)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:11  loss: 0.6912 (0.6912)  acc1: 82.9427 (82.9427)  acc5: 95.7031 (95.7031)  time: 7.9321  data: 7.6521  max mem: 78493
Test:  [8/9]  eta: 0:00:01  loss: 1.0369 (0.9279)  acc1: 74.6094 (76.3680)  acc5: 93.4896 (93.3120)  time: 1.1003  data: 0.8703  max mem: 78493
Test: Total time: 0:00:10 (1.1289 s / it)
* Acc@1 76.884 Acc@5 93.342 loss 0.918
Accuracy of the model on the 50000 test images: 76.9%
Max accuracy: 76.98%
Epoch: [156]  [  0/312]  eta: 1:22:51  lr: 0.002090  min_lr: 0.002090  loss: 2.3985 (2.3985)  weight_decay: 0.0500 (0.0500)  time: 15.9355  data: 11.3333  max mem: 78493
Epoch: [156]  [ 10/312]  eta: 0:13:05  lr: 0.002089  min_lr: 0.002089  loss: 2.3985 (2.4649)  weight_decay: 0.0500 (0.0500)  time: 2.6000  data: 1.2348  max mem: 78493
Epoch: [156]  [ 20/312]  eta: 0:09:00  lr: 0.002089  min_lr: 0.002089  loss: 2.2914 (2.3254)  weight_decay: 0.0500 (0.0500)  time: 1.1484  data: 0.1128  max mem: 78493
Epoch: [156]  [ 30/312]  eta: 0:07:25  lr: 0.002088  min_lr: 0.002088  loss: 2.1084 (2.2641)  weight_decay: 0.0500 (0.0500)  time: 1.0190  data: 0.0005  max mem: 78493
Epoch: [156]  [ 40/312]  eta: 0:06:31  lr: 0.002087  min_lr: 0.002087  loss: 2.0785 (2.2512)  weight_decay: 0.0500 (0.0500)  time: 1.0070  data: 0.0004  max mem: 78493
Epoch: [156]  [ 50/312]  eta: 0:05:55  lr: 0.002087  min_lr: 0.002087  loss: 2.1863 (2.2383)  weight_decay: 0.0500 (0.0500)  time: 1.0070  data: 0.0004  max mem: 78493
Epoch: [156]  [ 60/312]  eta: 0:05:27  lr: 0.002086  min_lr: 0.002086  loss: 2.1863 (2.2414)  weight_decay: 0.0500 (0.0500)  time: 1.0078  data: 0.0004  max mem: 78493
Epoch: [156]  [ 70/312]  eta: 0:05:04  lr: 0.002085  min_lr: 0.002085  loss: 2.1890 (2.2461)  weight_decay: 0.0500 (0.0500)  time: 1.0078  data: 0.0004  max mem: 78493
Epoch: [156]  [ 80/312]  eta: 0:04:44  lr: 0.002084  min_lr: 0.002084  loss: 2.3748 (2.2584)  weight_decay: 0.0500 (0.0500)  time: 1.0087  data: 0.0004  max mem: 78493
Epoch: [156]  [ 90/312]  eta: 0:04:27  lr: 0.002084  min_lr: 0.002084  loss: 2.4826 (2.2820)  weight_decay: 0.0500 (0.0500)  time: 1.0089  data: 0.0004  max mem: 78493
Epoch: [156]  [100/312]  eta: 0:04:10  lr: 0.002083  min_lr: 0.002083  loss: 2.3410 (2.2675)  weight_decay: 0.0500 (0.0500)  time: 1.0080  data: 0.0004  max mem: 78493
Epoch: [156]  [110/312]  eta: 0:03:55  lr: 0.002082  min_lr: 0.002082  loss: 2.3182 (2.2732)  weight_decay: 0.0500 (0.0500)  time: 1.0076  data: 0.0004  max mem: 78493
Epoch: [156]  [120/312]  eta: 0:03:41  lr: 0.002082  min_lr: 0.002082  loss: 2.3182 (2.2614)  weight_decay: 0.0500 (0.0500)  time: 1.0076  data: 0.0004  max mem: 78493
Epoch: [156]  [130/312]  eta: 0:03:28  lr: 0.002081  min_lr: 0.002081  loss: 2.3243 (2.2683)  weight_decay: 0.0500 (0.0500)  time: 1.0092  data: 0.0004  max mem: 78493
Epoch: [156]  [140/312]  eta: 0:03:15  lr: 0.002080  min_lr: 0.002080  loss: 2.4248 (2.2783)  weight_decay: 0.0500 (0.0500)  time: 1.0089  data: 0.0004  max mem: 78493
Epoch: [156]  [150/312]  eta: 0:03:02  lr: 0.002079  min_lr: 0.002079  loss: 2.3428 (2.2716)  weight_decay: 0.0500 (0.0500)  time: 1.0068  data: 0.0004  max mem: 78493
Epoch: [156]  [160/312]  eta: 0:02:49  lr: 0.002079  min_lr: 0.002079  loss: 2.2046 (2.2620)  weight_decay: 0.0500 (0.0500)  time: 1.0086  data: 0.0004  max mem: 78493
Epoch: [156]  [170/312]  eta: 0:02:37  lr: 0.002078  min_lr: 0.002078  loss: 2.1262 (2.2522)  weight_decay: 0.0500 (0.0500)  time: 1.0090  data: 0.0005  max mem: 78493
Epoch: [156]  [180/312]  eta: 0:02:25  lr: 0.002077  min_lr: 0.002077  loss: 2.2098 (2.2496)  weight_decay: 0.0500 (0.0500)  time: 1.0064  data: 0.0004  max mem: 78493
Epoch: [156]  [190/312]  eta: 0:02:14  lr: 0.002077  min_lr: 0.002077  loss: 2.2538 (2.2505)  weight_decay: 0.0500 (0.0500)  time: 1.0086  data: 0.0004  max mem: 78493
Epoch: [156]  [200/312]  eta: 0:02:02  lr: 0.002076  min_lr: 0.002076  loss: 2.1459 (2.2475)  weight_decay: 0.0500 (0.0500)  time: 1.0091  data: 0.0004  max mem: 78493
Epoch: [156]  [210/312]  eta: 0:01:51  lr: 0.002075  min_lr: 0.002075  loss: 2.2835 (2.2574)  weight_decay: 0.0500 (0.0500)  time: 1.0070  data: 0.0004  max mem: 78493
Epoch: [156]  [220/312]  eta: 0:01:40  lr: 0.002074  min_lr: 0.002074  loss: 2.4612 (2.2651)  weight_decay: 0.0500 (0.0500)  time: 1.0063  data: 0.0004  max mem: 78493
Epoch: [156]  [230/312]  eta: 0:01:28  lr: 0.002074  min_lr: 0.002074  loss: 2.4684 (2.2676)  weight_decay: 0.0500 (0.0500)  time: 1.0063  data: 0.0004  max mem: 78493
Epoch: [156]  [240/312]  eta: 0:01:17  lr: 0.002073  min_lr: 0.002073  loss: 2.4481 (2.2758)  weight_decay: 0.0500 (0.0500)  time: 1.0063  data: 0.0004  max mem: 78493
Epoch: [156]  [250/312]  eta: 0:01:06  lr: 0.002072  min_lr: 0.002072  loss: 2.4481 (2.2820)  weight_decay: 0.0500 (0.0500)  time: 1.0056  data: 0.0004  max mem: 78493
Epoch: [156]  [260/312]  eta: 0:00:55  lr: 0.002072  min_lr: 0.002072  loss: 2.3270 (2.2784)  weight_decay: 0.0500 (0.0500)  time: 1.0061  data: 0.0005  max mem: 78493
Epoch: [156]  [270/312]  eta: 0:00:45  lr: 0.002071  min_lr: 0.002071  loss: 2.4226 (2.2838)  weight_decay: 0.0500 (0.0500)  time: 1.0057  data: 0.0005  max mem: 78493
Epoch: [156]  [280/312]  eta: 0:00:34  lr: 0.002070  min_lr: 0.002070  loss: 2.3699 (2.2747)  weight_decay: 0.0500 (0.0500)  time: 1.0066  data: 0.0010  max mem: 78493
Epoch: [156]  [290/312]  eta: 0:00:23  lr: 0.002069  min_lr: 0.002069  loss: 2.1961 (2.2768)  weight_decay: 0.0500 (0.0500)  time: 1.0051  data: 0.0009  max mem: 78493
Epoch: [156]  [300/312]  eta: 0:00:12  lr: 0.002069  min_lr: 0.002069  loss: 2.3774 (2.2774)  weight_decay: 0.0500 (0.0500)  time: 1.0020  data: 0.0001  max mem: 78493
Epoch: [156]  [310/312]  eta: 0:00:02  lr: 0.002068  min_lr: 0.002068  loss: 2.4537 (2.2833)  weight_decay: 0.0500 (0.0500)  time: 1.0018  data: 0.0001  max mem: 78493
Epoch: [156]  [311/312]  eta: 0:00:01  lr: 0.002068  min_lr: 0.002068  loss: 2.4543 (2.2854)  weight_decay: 0.0500 (0.0500)  time: 1.0018  data: 0.0001  max mem: 78493
Epoch: [156] Total time: 0:05:33 (1.0696 s / it)
Averaged stats: lr: 0.002068  min_lr: 0.002068  loss: 2.4543 (2.2522)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:12  loss: 0.6979 (0.6979)  acc1: 82.2917 (82.2917)  acc5: 95.9635 (95.9635)  time: 8.0619  data: 7.7877  max mem: 78493
Test:  [8/9]  eta: 0:00:01  loss: 1.0304 (0.9381)  acc1: 76.0417 (76.1920)  acc5: 93.4896 (93.0560)  time: 1.0942  data: 0.8654  max mem: 78493
Test: Total time: 0:00:10 (1.1117 s / it)
* Acc@1 76.438 Acc@5 93.390 loss 0.937
Accuracy of the model on the 50000 test images: 76.4%
Max accuracy: 76.98%
Epoch: [157]  [  0/312]  eta: 1:19:24  lr: 0.002068  min_lr: 0.002068  loss: 2.4862 (2.4862)  weight_decay: 0.0500 (0.0500)  time: 15.2715  data: 13.2341  max mem: 78493
Epoch: [157]  [ 10/312]  eta: 0:12:17  lr: 0.002067  min_lr: 0.002067  loss: 2.3423 (2.1820)  weight_decay: 0.0500 (0.0500)  time: 2.4421  data: 1.2334  max mem: 78493
Epoch: [157]  [ 20/312]  eta: 0:08:42  lr: 0.002066  min_lr: 0.002066  loss: 2.1089 (2.1890)  weight_decay: 0.0500 (0.0500)  time: 1.1137  data: 0.0171  max mem: 78493
Epoch: [157]  [ 30/312]  eta: 0:07:13  lr: 0.002066  min_lr: 0.002066  loss: 2.3814 (2.2959)  weight_decay: 0.0500 (0.0500)  time: 1.0380  data: 0.0007  max mem: 78493
Epoch: [157]  [ 40/312]  eta: 0:06:22  lr: 0.002065  min_lr: 0.002065  loss: 2.4603 (2.2831)  weight_decay: 0.0500 (0.0500)  time: 1.0076  data: 0.0004  max mem: 78493
Epoch: [157]  [ 50/312]  eta: 0:05:48  lr: 0.002064  min_lr: 0.002064  loss: 2.2622 (2.2547)  weight_decay: 0.0500 (0.0500)  time: 1.0081  data: 0.0004  max mem: 78493
Epoch: [157]  [ 60/312]  eta: 0:05:21  lr: 0.002063  min_lr: 0.002063  loss: 2.2259 (2.2429)  weight_decay: 0.0500 (0.0500)  time: 1.0070  data: 0.0004  max mem: 78493
Epoch: [157]  [ 70/312]  eta: 0:04:59  lr: 0.002063  min_lr: 0.002063  loss: 2.3709 (2.2616)  weight_decay: 0.0500 (0.0500)  time: 1.0078  data: 0.0004  max mem: 78493
Epoch: [157]  [ 80/312]  eta: 0:04:40  lr: 0.002062  min_lr: 0.002062  loss: 2.3219 (2.2600)  weight_decay: 0.0500 (0.0500)  time: 1.0090  data: 0.0004  max mem: 78493
Epoch: [157]  [ 90/312]  eta: 0:04:23  lr: 0.002061  min_lr: 0.002061  loss: 2.2337 (2.2405)  weight_decay: 0.0500 (0.0500)  time: 1.0070  data: 0.0005  max mem: 78493
Epoch: [157]  [100/312]  eta: 0:04:07  lr: 0.002061  min_lr: 0.002061  loss: 2.1960 (2.2455)  weight_decay: 0.0500 (0.0500)  time: 1.0056  data: 0.0005  max mem: 78493
Epoch: [157]  [110/312]  eta: 0:03:53  lr: 0.002060  min_lr: 0.002060  loss: 2.3740 (2.2615)  weight_decay: 0.0500 (0.0500)  time: 1.0064  data: 0.0004  max mem: 78493
Epoch: [157]  [120/312]  eta: 0:03:39  lr: 0.002059  min_lr: 0.002059  loss: 2.3740 (2.2608)  weight_decay: 0.0500 (0.0500)  time: 1.0094  data: 0.0004  max mem: 78493
Epoch: [157]  [130/312]  eta: 0:03:26  lr: 0.002058  min_lr: 0.002058  loss: 2.3857 (2.2706)  weight_decay: 0.0500 (0.0500)  time: 1.0109  data: 0.0004  max mem: 78493
Epoch: [157]  [140/312]  eta: 0:03:13  lr: 0.002058  min_lr: 0.002058  loss: 2.3238 (2.2568)  weight_decay: 0.0500 (0.0500)  time: 1.0089  data: 0.0004  max mem: 78493
Epoch: [157]  [150/312]  eta: 0:03:00  lr: 0.002057  min_lr: 0.002057  loss: 2.1803 (2.2527)  weight_decay: 0.0500 (0.0500)  time: 1.0094  data: 0.0004  max mem: 78493
Epoch: [157]  [160/312]  eta: 0:02:48  lr: 0.002056  min_lr: 0.002056  loss: 2.1970 (2.2521)  weight_decay: 0.0500 (0.0500)  time: 1.0134  data: 0.0011  max mem: 78493
Epoch: [157]  [170/312]  eta: 0:02:36  lr: 0.002056  min_lr: 0.002056  loss: 2.3695 (2.2503)  weight_decay: 0.0500 (0.0500)  time: 1.0104  data: 0.0012  max mem: 78493
Epoch: [157]  [180/312]  eta: 0:02:25  lr: 0.002055  min_lr: 0.002055  loss: 2.3695 (2.2558)  weight_decay: 0.0500 (0.0500)  time: 1.0061  data: 0.0005  max mem: 78493
Epoch: [157]  [190/312]  eta: 0:02:13  lr: 0.002054  min_lr: 0.002054  loss: 2.3543 (2.2575)  weight_decay: 0.0500 (0.0500)  time: 1.0063  data: 0.0004  max mem: 78493
Epoch: [157]  [200/312]  eta: 0:02:02  lr: 0.002053  min_lr: 0.002053  loss: 2.4100 (2.2615)  weight_decay: 0.0500 (0.0500)  time: 1.0061  data: 0.0005  max mem: 78493
Epoch: [157]  [210/312]  eta: 0:01:50  lr: 0.002053  min_lr: 0.002053  loss: 2.4500 (2.2681)  weight_decay: 0.0500 (0.0500)  time: 1.0064  data: 0.0005  max mem: 78493
Epoch: [157]  [220/312]  eta: 0:01:39  lr: 0.002052  min_lr: 0.002052  loss: 2.3344 (2.2654)  weight_decay: 0.0500 (0.0500)  time: 1.0054  data: 0.0004  max mem: 78493
Epoch: [157]  [230/312]  eta: 0:01:28  lr: 0.002051  min_lr: 0.002051  loss: 2.3656 (2.2700)  weight_decay: 0.0500 (0.0500)  time: 1.0071  data: 0.0004  max mem: 78493
Epoch: [157]  [240/312]  eta: 0:01:17  lr: 0.002051  min_lr: 0.002051  loss: 2.4378 (2.2749)  weight_decay: 0.0500 (0.0500)  time: 1.0078  data: 0.0004  max mem: 78493
Epoch: [157]  [250/312]  eta: 0:01:06  lr: 0.002050  min_lr: 0.002050  loss: 2.2889 (2.2706)  weight_decay: 0.0500 (0.0500)  time: 1.0050  data: 0.0004  max mem: 78493
Epoch: [157]  [260/312]  eta: 0:00:55  lr: 0.002049  min_lr: 0.002049  loss: 2.1327 (2.2627)  weight_decay: 0.0500 (0.0500)  time: 1.0053  data: 0.0004  max mem: 78493
Epoch: [157]  [270/312]  eta: 0:00:44  lr: 0.002048  min_lr: 0.002048  loss: 2.1327 (2.2586)  weight_decay: 0.0500 (0.0500)  time: 1.0060  data: 0.0004  max mem: 78493
Epoch: [157]  [280/312]  eta: 0:00:34  lr: 0.002048  min_lr: 0.002048  loss: 2.2561 (2.2628)  weight_decay: 0.0500 (0.0500)  time: 1.0062  data: 0.0010  max mem: 78493
Epoch: [157]  [290/312]  eta: 0:00:23  lr: 0.002047  min_lr: 0.002047  loss: 2.3546 (2.2674)  weight_decay: 0.0500 (0.0500)  time: 1.0044  data: 0.0009  max mem: 78493
Epoch: [157]  [300/312]  eta: 0:00:12  lr: 0.002046  min_lr: 0.002046  loss: 2.3737 (2.2631)  weight_decay: 0.0500 (0.0500)  time: 1.0018  data: 0.0001  max mem: 78493
Epoch: [157]  [310/312]  eta: 0:00:02  lr: 0.002046  min_lr: 0.002046  loss: 2.3545 (2.2642)  weight_decay: 0.0500 (0.0500)  time: 1.0013  data: 0.0001  max mem: 78493
Epoch: [157]  [311/312]  eta: 0:00:01  lr: 0.002045  min_lr: 0.002045  loss: 2.3051 (2.2639)  weight_decay: 0.0500 (0.0500)  time: 1.0013  data: 0.0001  max mem: 78493
Epoch: [157] Total time: 0:05:32 (1.0653 s / it)
Averaged stats: lr: 0.002045  min_lr: 0.002045  loss: 2.3051 (2.2593)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:14  loss: 0.6822 (0.6822)  acc1: 82.5521 (82.5521)  acc5: 96.0938 (96.0938)  time: 8.3020  data: 8.0158  max mem: 78493
Test:  [8/9]  eta: 0:00:01  loss: 1.0213 (0.8987)  acc1: 76.0417 (76.4160)  acc5: 92.7083 (93.4240)  time: 1.1208  data: 0.8907  max mem: 78493
Test: Total time: 0:00:10 (1.1591 s / it)
* Acc@1 76.962 Acc@5 93.586 loss 0.887
Accuracy of the model on the 50000 test images: 77.0%
Max accuracy: 76.98%
Epoch: [158]  [  0/312]  eta: 1:27:46  lr: 0.002045  min_lr: 0.002045  loss: 2.7545 (2.7545)  weight_decay: 0.0500 (0.0500)  time: 16.8796  data: 15.8825  max mem: 78493
Epoch: [158]  [ 10/312]  eta: 0:13:12  lr: 0.002045  min_lr: 0.002045  loss: 2.4333 (2.4607)  weight_decay: 0.0500 (0.0500)  time: 2.6249  data: 1.4496  max mem: 78493
Epoch: [158]  [ 20/312]  eta: 0:09:02  lr: 0.002044  min_lr: 0.002044  loss: 2.0754 (2.2577)  weight_decay: 0.0500 (0.0500)  time: 1.1064  data: 0.0034  max mem: 78493
Epoch: [158]  [ 30/312]  eta: 0:07:26  lr: 0.002043  min_lr: 0.002043  loss: 2.0109 (2.2130)  weight_decay: 0.0500 (0.0500)  time: 1.0088  data: 0.0005  max mem: 78493
Epoch: [158]  [ 40/312]  eta: 0:06:32  lr: 0.002042  min_lr: 0.002042  loss: 2.2171 (2.2282)  weight_decay: 0.0500 (0.0500)  time: 1.0049  data: 0.0004  max mem: 78493
Epoch: [158]  [ 50/312]  eta: 0:05:55  lr: 0.002042  min_lr: 0.002042  loss: 2.2942 (2.2533)  weight_decay: 0.0500 (0.0500)  time: 1.0057  data: 0.0004  max mem: 78493
Epoch: [158]  [ 60/312]  eta: 0:05:27  lr: 0.002041  min_lr: 0.002041  loss: 2.3761 (2.2705)  weight_decay: 0.0500 (0.0500)  time: 1.0055  data: 0.0004  max mem: 78493
Epoch: [158]  [ 70/312]  eta: 0:05:04  lr: 0.002040  min_lr: 0.002040  loss: 2.3924 (2.2762)  weight_decay: 0.0500 (0.0500)  time: 1.0042  data: 0.0004  max mem: 78493
Epoch: [158]  [ 80/312]  eta: 0:04:44  lr: 0.002040  min_lr: 0.002040  loss: 2.3924 (2.2914)  weight_decay: 0.0500 (0.0500)  time: 1.0050  data: 0.0004  max mem: 78493
Epoch: [158]  [ 90/312]  eta: 0:04:26  lr: 0.002039  min_lr: 0.002039  loss: 2.4279 (2.2986)  weight_decay: 0.0500 (0.0500)  time: 1.0072  data: 0.0004  max mem: 78493
Epoch: [158]  [100/312]  eta: 0:04:10  lr: 0.002038  min_lr: 0.002038  loss: 2.4383 (2.3222)  weight_decay: 0.0500 (0.0500)  time: 1.0088  data: 0.0015  max mem: 78493
Epoch: [158]  [110/312]  eta: 0:03:55  lr: 0.002037  min_lr: 0.002037  loss: 2.4325 (2.3154)  weight_decay: 0.0500 (0.0500)  time: 1.0094  data: 0.0015  max mem: 78493
Epoch: [158]  [120/312]  eta: 0:03:41  lr: 0.002037  min_lr: 0.002037  loss: 2.3021 (2.3080)  weight_decay: 0.0500 (0.0500)  time: 1.0078  data: 0.0005  max mem: 78493
Epoch: [158]  [130/312]  eta: 0:03:28  lr: 0.002036  min_lr: 0.002036  loss: 2.3310 (2.2993)  weight_decay: 0.0500 (0.0500)  time: 1.0073  data: 0.0004  max mem: 78493
Epoch: [158]  [140/312]  eta: 0:03:14  lr: 0.002035  min_lr: 0.002035  loss: 2.1914 (2.2904)  weight_decay: 0.0500 (0.0500)  time: 1.0103  data: 0.0016  max mem: 78493
Epoch: [158]  [150/312]  eta: 0:03:02  lr: 0.002035  min_lr: 0.002035  loss: 2.2345 (2.2857)  weight_decay: 0.0500 (0.0500)  time: 1.0124  data: 0.0016  max mem: 78493
Epoch: [158]  [160/312]  eta: 0:02:50  lr: 0.002034  min_lr: 0.002034  loss: 2.3681 (2.2913)  weight_decay: 0.0500 (0.0500)  time: 1.0112  data: 0.0005  max mem: 78493
Epoch: [158]  [170/312]  eta: 0:02:37  lr: 0.002033  min_lr: 0.002033  loss: 2.3917 (2.2889)  weight_decay: 0.0500 (0.0500)  time: 1.0093  data: 0.0004  max mem: 78493
Epoch: [158]  [180/312]  eta: 0:02:26  lr: 0.002032  min_lr: 0.002032  loss: 2.2488 (2.2829)  weight_decay: 0.0500 (0.0500)  time: 1.0084  data: 0.0004  max mem: 78493
Epoch: [158]  [190/312]  eta: 0:02:14  lr: 0.002032  min_lr: 0.002032  loss: 2.3106 (2.2750)  weight_decay: 0.0500 (0.0500)  time: 1.0086  data: 0.0004  max mem: 78493
Epoch: [158]  [200/312]  eta: 0:02:02  lr: 0.002031  min_lr: 0.002031  loss: 2.2228 (2.2695)  weight_decay: 0.0500 (0.0500)  time: 1.0081  data: 0.0004  max mem: 78493
Epoch: [158]  [210/312]  eta: 0:01:51  lr: 0.002030  min_lr: 0.002030  loss: 2.2495 (2.2688)  weight_decay: 0.0500 (0.0500)  time: 1.0074  data: 0.0004  max mem: 78493
Epoch: [158]  [220/312]  eta: 0:01:40  lr: 0.002030  min_lr: 0.002030  loss: 2.3964 (2.2748)  weight_decay: 0.0500 (0.0500)  time: 1.0071  data: 0.0004  max mem: 78493
Epoch: [158]  [230/312]  eta: 0:01:28  lr: 0.002029  min_lr: 0.002029  loss: 2.3964 (2.2712)  weight_decay: 0.0500 (0.0500)  time: 1.0055  data: 0.0004  max mem: 78493
Epoch: [158]  [240/312]  eta: 0:01:17  lr: 0.002028  min_lr: 0.002028  loss: 2.0224 (2.2642)  weight_decay: 0.0500 (0.0500)  time: 1.0059  data: 0.0004  max mem: 78493
Epoch: [158]  [250/312]  eta: 0:01:06  lr: 0.002027  min_lr: 0.002027  loss: 2.2802 (2.2642)  weight_decay: 0.0500 (0.0500)  time: 1.0057  data: 0.0004  max mem: 78493
Epoch: [158]  [260/312]  eta: 0:00:55  lr: 0.002027  min_lr: 0.002027  loss: 2.4057 (2.2610)  weight_decay: 0.0500 (0.0500)  time: 1.0049  data: 0.0004  max mem: 78493
Epoch: [158]  [270/312]  eta: 0:00:45  lr: 0.002026  min_lr: 0.002026  loss: 2.2487 (2.2569)  weight_decay: 0.0500 (0.0500)  time: 1.0056  data: 0.0004  max mem: 78493
Epoch: [158]  [280/312]  eta: 0:00:34  lr: 0.002025  min_lr: 0.002025  loss: 2.2620 (2.2571)  weight_decay: 0.0500 (0.0500)  time: 1.0076  data: 0.0010  max mem: 78493
Epoch: [158]  [290/312]  eta: 0:00:23  lr: 0.002025  min_lr: 0.002025  loss: 2.2679 (2.2542)  weight_decay: 0.0500 (0.0500)  time: 1.0060  data: 0.0009  max mem: 78493
Epoch: [158]  [300/312]  eta: 0:00:12  lr: 0.002024  min_lr: 0.002024  loss: 2.2665 (2.2555)  weight_decay: 0.0500 (0.0500)  time: 1.0021  data: 0.0001  max mem: 78493
Epoch: [158]  [310/312]  eta: 0:00:02  lr: 0.002023  min_lr: 0.002023  loss: 2.1213 (2.2497)  weight_decay: 0.0500 (0.0500)  time: 1.0020  data: 0.0001  max mem: 78493
Epoch: [158]  [311/312]  eta: 0:00:01  lr: 0.002023  min_lr: 0.002023  loss: 2.1213 (2.2504)  weight_decay: 0.0500 (0.0500)  time: 1.0020  data: 0.0001  max mem: 78493
Epoch: [158] Total time: 0:05:33 (1.0696 s / it)
Averaged stats: lr: 0.002023  min_lr: 0.002023  loss: 2.1213 (2.2392)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:15  loss: 0.6984 (0.6984)  acc1: 82.2917 (82.2917)  acc5: 95.0521 (95.0521)  time: 8.3728  data: 8.0901  max mem: 78493
Test:  [8/9]  eta: 0:00:01  loss: 0.9862 (0.9125)  acc1: 75.3906 (76.6400)  acc5: 93.4896 (93.1680)  time: 1.1286  data: 0.8990  max mem: 78493
Test: Total time: 0:00:10 (1.1464 s / it)
* Acc@1 77.078 Acc@5 93.334 loss 0.896
Accuracy of the model on the 50000 test images: 77.1%
Max accuracy: 77.08%
Epoch: [159]  [  0/312]  eta: 1:21:43  lr: 0.002023  min_lr: 0.002023  loss: 2.7691 (2.7691)  weight_decay: 0.0500 (0.0500)  time: 15.7161  data: 12.0253  max mem: 78493
Epoch: [159]  [ 10/312]  eta: 0:13:01  lr: 0.002022  min_lr: 0.002022  loss: 2.2939 (2.2863)  weight_decay: 0.0500 (0.0500)  time: 2.5864  data: 1.2827  max mem: 78493
Epoch: [159]  [ 20/312]  eta: 0:08:57  lr: 0.002021  min_lr: 0.002021  loss: 2.2412 (2.2416)  weight_decay: 0.0500 (0.0500)  time: 1.1459  data: 0.1059  max mem: 78493
Epoch: [159]  [ 30/312]  eta: 0:07:23  lr: 0.002021  min_lr: 0.002021  loss: 2.1859 (2.2119)  weight_decay: 0.0500 (0.0500)  time: 1.0133  data: 0.0018  max mem: 78493
Epoch: [159]  [ 40/312]  eta: 0:06:29  lr: 0.002020  min_lr: 0.002020  loss: 2.3426 (2.2322)  weight_decay: 0.0500 (0.0500)  time: 1.0067  data: 0.0005  max mem: 78493
Epoch: [159]  [ 50/312]  eta: 0:05:53  lr: 0.002019  min_lr: 0.002019  loss: 2.3601 (2.2333)  weight_decay: 0.0500 (0.0500)  time: 1.0055  data: 0.0005  max mem: 78493
Epoch: [159]  [ 60/312]  eta: 0:05:26  lr: 0.002019  min_lr: 0.002019  loss: 2.2703 (2.2160)  weight_decay: 0.0500 (0.0500)  time: 1.0078  data: 0.0004  max mem: 78493
Epoch: [159]  [ 70/312]  eta: 0:05:03  lr: 0.002018  min_lr: 0.002018  loss: 2.2957 (2.2290)  weight_decay: 0.0500 (0.0500)  time: 1.0074  data: 0.0004  max mem: 78493
Epoch: [159]  [ 80/312]  eta: 0:04:43  lr: 0.002017  min_lr: 0.002017  loss: 2.3022 (2.2452)  weight_decay: 0.0500 (0.0500)  time: 1.0047  data: 0.0005  max mem: 78493
Epoch: [159]  [ 90/312]  eta: 0:04:26  lr: 0.002016  min_lr: 0.002016  loss: 2.3022 (2.2401)  weight_decay: 0.0500 (0.0500)  time: 1.0071  data: 0.0005  max mem: 78493
Epoch: [159]  [100/312]  eta: 0:04:10  lr: 0.002016  min_lr: 0.002016  loss: 2.1572 (2.2242)  weight_decay: 0.0500 (0.0500)  time: 1.0094  data: 0.0005  max mem: 78493
Epoch: [159]  [110/312]  eta: 0:03:55  lr: 0.002015  min_lr: 0.002015  loss: 1.9542 (2.2158)  weight_decay: 0.0500 (0.0500)  time: 1.0115  data: 0.0005  max mem: 78493
Epoch: [159]  [120/312]  eta: 0:03:41  lr: 0.002014  min_lr: 0.002014  loss: 2.1071 (2.2153)  weight_decay: 0.0500 (0.0500)  time: 1.0124  data: 0.0012  max mem: 78493
Epoch: [159]  [130/312]  eta: 0:03:27  lr: 0.002014  min_lr: 0.002014  loss: 2.3948 (2.2326)  weight_decay: 0.0500 (0.0500)  time: 1.0081  data: 0.0012  max mem: 78493
Epoch: [159]  [140/312]  eta: 0:03:14  lr: 0.002013  min_lr: 0.002013  loss: 2.3822 (2.2314)  weight_decay: 0.0500 (0.0500)  time: 1.0048  data: 0.0005  max mem: 78493
Epoch: [159]  [150/312]  eta: 0:03:01  lr: 0.002012  min_lr: 0.002012  loss: 2.1315 (2.2211)  weight_decay: 0.0500 (0.0500)  time: 1.0050  data: 0.0005  max mem: 78493
Epoch: [159]  [160/312]  eta: 0:02:49  lr: 0.002011  min_lr: 0.002011  loss: 2.3027 (2.2346)  weight_decay: 0.0500 (0.0500)  time: 1.0059  data: 0.0004  max mem: 78493
Epoch: [159]  [170/312]  eta: 0:02:37  lr: 0.002011  min_lr: 0.002011  loss: 2.4195 (2.2260)  weight_decay: 0.0500 (0.0500)  time: 1.0059  data: 0.0005  max mem: 78493
Epoch: [159]  [180/312]  eta: 0:02:25  lr: 0.002010  min_lr: 0.002010  loss: 2.3092 (2.2307)  weight_decay: 0.0500 (0.0500)  time: 1.0061  data: 0.0004  max mem: 78493
Epoch: [159]  [190/312]  eta: 0:02:14  lr: 0.002009  min_lr: 0.002009  loss: 2.3092 (2.2322)  weight_decay: 0.0500 (0.0500)  time: 1.0050  data: 0.0004  max mem: 78493
Epoch: [159]  [200/312]  eta: 0:02:02  lr: 0.002009  min_lr: 0.002009  loss: 2.3281 (2.2355)  weight_decay: 0.0500 (0.0500)  time: 1.0037  data: 0.0004  max mem: 78493
Epoch: [159]  [210/312]  eta: 0:01:51  lr: 0.002008  min_lr: 0.002008  loss: 2.4124 (2.2417)  weight_decay: 0.0500 (0.0500)  time: 1.0036  data: 0.0004  max mem: 78493
Epoch: [159]  [220/312]  eta: 0:01:39  lr: 0.002007  min_lr: 0.002007  loss: 2.3981 (2.2455)  weight_decay: 0.0500 (0.0500)  time: 1.0036  data: 0.0005  max mem: 78493
Epoch: [159]  [230/312]  eta: 0:01:28  lr: 0.002006  min_lr: 0.002006  loss: 2.3312 (2.2450)  weight_decay: 0.0500 (0.0500)  time: 1.0041  data: 0.0005  max mem: 78493
Epoch: [159]  [240/312]  eta: 0:01:17  lr: 0.002006  min_lr: 0.002006  loss: 2.2823 (2.2447)  weight_decay: 0.0500 (0.0500)  time: 1.0044  data: 0.0004  max mem: 78493
Epoch: [159]  [250/312]  eta: 0:01:06  lr: 0.002005  min_lr: 0.002005  loss: 2.2245 (2.2374)  weight_decay: 0.0500 (0.0500)  time: 1.0058  data: 0.0004  max mem: 78493
Epoch: [159]  [260/312]  eta: 0:00:55  lr: 0.002004  min_lr: 0.002004  loss: 2.2511 (2.2437)  weight_decay: 0.0500 (0.0500)  time: 1.0051  data: 0.0004  max mem: 78493
Epoch: [159]  [270/312]  eta: 0:00:44  lr: 0.002004  min_lr: 0.002004  loss: 2.3981 (2.2517)  weight_decay: 0.0500 (0.0500)  time: 1.0044  data: 0.0004  max mem: 78493
Epoch: [159]  [280/312]  eta: 0:00:34  lr: 0.002003  min_lr: 0.002003  loss: 2.3355 (2.2523)  weight_decay: 0.0500 (0.0500)  time: 1.0073  data: 0.0010  max mem: 78493
Epoch: [159]  [290/312]  eta: 0:00:23  lr: 0.002002  min_lr: 0.002002  loss: 2.3839 (2.2566)  weight_decay: 0.0500 (0.0500)  time: 1.0054  data: 0.0009  max mem: 78493
Epoch: [159]  [300/312]  eta: 0:00:12  lr: 0.002001  min_lr: 0.002001  loss: 2.3765 (2.2576)  weight_decay: 0.0500 (0.0500)  time: 1.0018  data: 0.0001  max mem: 78493
Epoch: [159]  [310/312]  eta: 0:00:02  lr: 0.002001  min_lr: 0.002001  loss: 2.3879 (2.2638)  weight_decay: 0.0500 (0.0500)  time: 1.0019  data: 0.0001  max mem: 78493
Epoch: [159]  [311/312]  eta: 0:00:01  lr: 0.002001  min_lr: 0.002001  loss: 2.3765 (2.2618)  weight_decay: 0.0500 (0.0500)  time: 1.0019  data: 0.0001  max mem: 78493
Epoch: [159] Total time: 0:05:33 (1.0675 s / it)
Averaged stats: lr: 0.002001  min_lr: 0.002001  loss: 2.3765 (2.2522)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:12  loss: 0.7056 (0.7056)  acc1: 83.0729 (83.0729)  acc5: 95.7031 (95.7031)  time: 8.0428  data: 7.7608  max mem: 78493
Test:  [8/9]  eta: 0:00:01  loss: 1.0089 (0.9160)  acc1: 75.9115 (76.3840)  acc5: 92.8385 (93.5520)  time: 1.0919  data: 0.8624  max mem: 78493
Test: Total time: 0:00:10 (1.1125 s / it)
* Acc@1 77.080 Acc@5 93.532 loss 0.900
Accuracy of the model on the 50000 test images: 77.1%
Max accuracy: 77.08%
Epoch: [160]  [  0/312]  eta: 1:25:47  lr: 0.002001  min_lr: 0.002001  loss: 1.9105 (1.9105)  weight_decay: 0.0500 (0.0500)  time: 16.4973  data: 15.4892  max mem: 78493
Epoch: [160]  [ 10/312]  eta: 0:13:39  lr: 0.002000  min_lr: 0.002000  loss: 2.3419 (2.3236)  weight_decay: 0.0500 (0.0500)  time: 2.7120  data: 1.4088  max mem: 78493
Epoch: [160]  [ 20/312]  eta: 0:09:14  lr: 0.001999  min_lr: 0.001999  loss: 2.4482 (2.4120)  weight_decay: 0.0500 (0.0500)  time: 1.1706  data: 0.0006  max mem: 78493
Epoch: [160]  [ 30/312]  eta: 0:07:34  lr: 0.001998  min_lr: 0.001998  loss: 2.5210 (2.4014)  weight_decay: 0.0500 (0.0500)  time: 1.0066  data: 0.0004  max mem: 78493
Epoch: [160]  [ 40/312]  eta: 0:06:38  lr: 0.001998  min_lr: 0.001998  loss: 2.4127 (2.3400)  weight_decay: 0.0500 (0.0500)  time: 1.0063  data: 0.0004  max mem: 78493
Epoch: [160]  [ 50/312]  eta: 0:06:00  lr: 0.001997  min_lr: 0.001997  loss: 2.1216 (2.2876)  weight_decay: 0.0500 (0.0500)  time: 1.0067  data: 0.0004  max mem: 78493
Epoch: [160]  [ 60/312]  eta: 0:05:31  lr: 0.001996  min_lr: 0.001996  loss: 2.2523 (2.3108)  weight_decay: 0.0500 (0.0500)  time: 1.0088  data: 0.0004  max mem: 78493
Epoch: [160]  [ 70/312]  eta: 0:05:07  lr: 0.001995  min_lr: 0.001995  loss: 2.4497 (2.3215)  weight_decay: 0.0500 (0.0500)  time: 1.0119  data: 0.0004  max mem: 78493
Epoch: [160]  [ 80/312]  eta: 0:04:47  lr: 0.001995  min_lr: 0.001995  loss: 2.2750 (2.2876)  weight_decay: 0.0500 (0.0500)  time: 1.0104  data: 0.0004  max mem: 78493
Epoch: [160]  [ 90/312]  eta: 0:04:29  lr: 0.001994  min_lr: 0.001994  loss: 1.9876 (2.2676)  weight_decay: 0.0500 (0.0500)  time: 1.0119  data: 0.0004  max mem: 78493
Epoch: [160]  [100/312]  eta: 0:04:13  lr: 0.001993  min_lr: 0.001993  loss: 2.1077 (2.2508)  weight_decay: 0.0500 (0.0500)  time: 1.0126  data: 0.0004  max mem: 78493
Epoch: [160]  [110/312]  eta: 0:03:57  lr: 0.001993  min_lr: 0.001993  loss: 2.2192 (2.2547)  weight_decay: 0.0500 (0.0500)  time: 1.0085  data: 0.0004  max mem: 78493
Epoch: [160]  [120/312]  eta: 0:03:43  lr: 0.001992  min_lr: 0.001992  loss: 2.2183 (2.2310)  weight_decay: 0.0500 (0.0500)  time: 1.0079  data: 0.0004  max mem: 78493
Epoch: [160]  [130/312]  eta: 0:03:29  lr: 0.001991  min_lr: 0.001991  loss: 2.1739 (2.2333)  weight_decay: 0.0500 (0.0500)  time: 1.0066  data: 0.0004  max mem: 78493
Epoch: [160]  [140/312]  eta: 0:03:16  lr: 0.001990  min_lr: 0.001990  loss: 2.3916 (2.2430)  weight_decay: 0.0500 (0.0500)  time: 1.0053  data: 0.0005  max mem: 78493
Epoch: [160]  [150/312]  eta: 0:03:03  lr: 0.001990  min_lr: 0.001990  loss: 2.4687 (2.2529)  weight_decay: 0.0500 (0.0500)  time: 1.0061  data: 0.0004  max mem: 78493
Epoch: [160]  [160/312]  eta: 0:02:50  lr: 0.001989  min_lr: 0.001989  loss: 2.3823 (2.2541)  weight_decay: 0.0500 (0.0500)  time: 1.0043  data: 0.0004  max mem: 78493
Epoch: [160]  [170/312]  eta: 0:02:38  lr: 0.001988  min_lr: 0.001988  loss: 2.3025 (2.2485)  weight_decay: 0.0500 (0.0500)  time: 1.0044  data: 0.0005  max mem: 78493
Epoch: [160]  [180/312]  eta: 0:02:26  lr: 0.001988  min_lr: 0.001988  loss: 2.2501 (2.2486)  weight_decay: 0.0500 (0.0500)  time: 1.0075  data: 0.0005  max mem: 78493
Epoch: [160]  [190/312]  eta: 0:02:14  lr: 0.001987  min_lr: 0.001987  loss: 2.2027 (2.2348)  weight_decay: 0.0500 (0.0500)  time: 1.0104  data: 0.0005  max mem: 78493
Epoch: [160]  [200/312]  eta: 0:02:03  lr: 0.001986  min_lr: 0.001986  loss: 2.2427 (2.2411)  weight_decay: 0.0500 (0.0500)  time: 1.0086  data: 0.0005  max mem: 78493
Epoch: [160]  [210/312]  eta: 0:01:51  lr: 0.001985  min_lr: 0.001985  loss: 2.2807 (2.2269)  weight_decay: 0.0500 (0.0500)  time: 1.0077  data: 0.0004  max mem: 78493
Epoch: [160]  [220/312]  eta: 0:01:40  lr: 0.001985  min_lr: 0.001985  loss: 1.9216 (2.2265)  weight_decay: 0.0500 (0.0500)  time: 1.0079  data: 0.0004  max mem: 78493
Epoch: [160]  [230/312]  eta: 0:01:29  lr: 0.001984  min_lr: 0.001984  loss: 2.2614 (2.2242)  weight_decay: 0.0500 (0.0500)  time: 1.0061  data: 0.0005  max mem: 78493
Epoch: [160]  [240/312]  eta: 0:01:18  lr: 0.001983  min_lr: 0.001983  loss: 2.3279 (2.2283)  weight_decay: 0.0500 (0.0500)  time: 1.0069  data: 0.0005  max mem: 78493
Epoch: [160]  [250/312]  eta: 0:01:07  lr: 0.001983  min_lr: 0.001983  loss: 2.4568 (2.2301)  weight_decay: 0.0500 (0.0500)  time: 1.0077  data: 0.0004  max mem: 78493
Epoch: [160]  [260/312]  eta: 0:00:56  lr: 0.001982  min_lr: 0.001982  loss: 2.1551 (2.2286)  weight_decay: 0.0500 (0.0500)  time: 1.0074  data: 0.0005  max mem: 78493
Epoch: [160]  [270/312]  eta: 0:00:45  lr: 0.001981  min_lr: 0.001981  loss: 2.1551 (2.2321)  weight_decay: 0.0500 (0.0500)  time: 1.0063  data: 0.0012  max mem: 78493
Epoch: [160]  [280/312]  eta: 0:00:34  lr: 0.001980  min_lr: 0.001980  loss: 2.3798 (2.2287)  weight_decay: 0.0500 (0.0500)  time: 1.0057  data: 0.0018  max mem: 78493
Epoch: [160]  [290/312]  eta: 0:00:23  lr: 0.001980  min_lr: 0.001980  loss: 2.3474 (2.2335)  weight_decay: 0.0500 (0.0500)  time: 1.0035  data: 0.0009  max mem: 78493
Epoch: [160]  [300/312]  eta: 0:00:12  lr: 0.001979  min_lr: 0.001979  loss: 2.2809 (2.2327)  weight_decay: 0.0500 (0.0500)  time: 1.0015  data: 0.0001  max mem: 78493
Epoch: [160]  [310/312]  eta: 0:00:02  lr: 0.001978  min_lr: 0.001978  loss: 2.2020 (2.2314)  weight_decay: 0.0500 (0.0500)  time: 1.0015  data: 0.0001  max mem: 78493
Epoch: [160]  [311/312]  eta: 0:00:01  lr: 0.001978  min_lr: 0.001978  loss: 2.2020 (2.2319)  weight_decay: 0.0500 (0.0500)  time: 1.0015  data: 0.0001  max mem: 78493
Epoch: [160] Total time: 0:05:34 (1.0727 s / it)
Averaged stats: lr: 0.001978  min_lr: 0.001978  loss: 2.2020 (2.2346)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:12  loss: 0.6666 (0.6666)  acc1: 83.4635 (83.4635)  acc5: 96.0938 (96.0938)  time: 8.0397  data: 7.7711  max mem: 78493
Test:  [8/9]  eta: 0:00:01  loss: 0.9736 (0.8876)  acc1: 74.7396 (76.6080)  acc5: 92.7083 (93.4720)  time: 1.1044  data: 0.8636  max mem: 78493
Test: Total time: 0:00:10 (1.1483 s / it)
* Acc@1 77.128 Acc@5 93.568 loss 0.883
Accuracy of the model on the 50000 test images: 77.1%
Max accuracy: 77.13%
Epoch: [161]  [  0/312]  eta: 1:27:38  lr: 0.001978  min_lr: 0.001978  loss: 1.9761 (1.9761)  weight_decay: 0.0500 (0.0500)  time: 16.8539  data: 15.8534  max mem: 78493
Epoch: [161]  [ 10/312]  eta: 0:12:54  lr: 0.001977  min_lr: 0.001977  loss: 2.3593 (2.1851)  weight_decay: 0.0500 (0.0500)  time: 2.5650  data: 1.4418  max mem: 78493
Epoch: [161]  [ 20/312]  eta: 0:08:53  lr: 0.001977  min_lr: 0.001977  loss: 2.3526 (2.1942)  weight_decay: 0.0500 (0.0500)  time: 1.0761  data: 0.0006  max mem: 78493
Epoch: [161]  [ 30/312]  eta: 0:07:20  lr: 0.001976  min_lr: 0.001976  loss: 2.2560 (2.1841)  weight_decay: 0.0500 (0.0500)  time: 1.0132  data: 0.0005  max mem: 78493
Epoch: [161]  [ 40/312]  eta: 0:06:28  lr: 0.001975  min_lr: 0.001975  loss: 2.2944 (2.2178)  weight_decay: 0.0500 (0.0500)  time: 1.0097  data: 0.0004  max mem: 78493
Epoch: [161]  [ 50/312]  eta: 0:05:52  lr: 0.001974  min_lr: 0.001974  loss: 2.3412 (2.2087)  weight_decay: 0.0500 (0.0500)  time: 1.0079  data: 0.0004  max mem: 78493
Epoch: [161]  [ 60/312]  eta: 0:05:25  lr: 0.001974  min_lr: 0.001974  loss: 2.3212 (2.2361)  weight_decay: 0.0500 (0.0500)  time: 1.0058  data: 0.0005  max mem: 78493
Epoch: [161]  [ 70/312]  eta: 0:05:02  lr: 0.001973  min_lr: 0.001973  loss: 2.3157 (2.2240)  weight_decay: 0.0500 (0.0500)  time: 1.0056  data: 0.0005  max mem: 78493
Epoch: [161]  [ 80/312]  eta: 0:04:43  lr: 0.001972  min_lr: 0.001972  loss: 1.9599 (2.2112)  weight_decay: 0.0500 (0.0500)  time: 1.0065  data: 0.0004  max mem: 78493
Epoch: [161]  [ 90/312]  eta: 0:04:25  lr: 0.001972  min_lr: 0.001972  loss: 1.9599 (2.2070)  weight_decay: 0.0500 (0.0500)  time: 1.0097  data: 0.0011  max mem: 78493
Epoch: [161]  [100/312]  eta: 0:04:09  lr: 0.001971  min_lr: 0.001971  loss: 2.2632 (2.2247)  weight_decay: 0.0500 (0.0500)  time: 1.0100  data: 0.0012  max mem: 78493
Epoch: [161]  [110/312]  eta: 0:03:54  lr: 0.001970  min_lr: 0.001970  loss: 2.4139 (2.2352)  weight_decay: 0.0500 (0.0500)  time: 1.0082  data: 0.0005  max mem: 78493
Epoch: [161]  [120/312]  eta: 0:03:40  lr: 0.001969  min_lr: 0.001969  loss: 2.3316 (2.2400)  weight_decay: 0.0500 (0.0500)  time: 1.0087  data: 0.0005  max mem: 78493
Epoch: [161]  [130/312]  eta: 0:03:27  lr: 0.001969  min_lr: 0.001969  loss: 2.2346 (2.2298)  weight_decay: 0.0500 (0.0500)  time: 1.0107  data: 0.0005  max mem: 78493
Epoch: [161]  [140/312]  eta: 0:03:14  lr: 0.001968  min_lr: 0.001968  loss: 2.2338 (2.2352)  weight_decay: 0.0500 (0.0500)  time: 1.0097  data: 0.0005  max mem: 78493
Epoch: [161]  [150/312]  eta: 0:03:01  lr: 0.001967  min_lr: 0.001967  loss: 2.3768 (2.2438)  weight_decay: 0.0500 (0.0500)  time: 1.0082  data: 0.0004  max mem: 78493
Epoch: [161]  [160/312]  eta: 0:02:49  lr: 0.001967  min_lr: 0.001967  loss: 2.4082 (2.2443)  weight_decay: 0.0500 (0.0500)  time: 1.0095  data: 0.0004  max mem: 78493
Epoch: [161]  [170/312]  eta: 0:02:37  lr: 0.001966  min_lr: 0.001966  loss: 2.4096 (2.2614)  weight_decay: 0.0500 (0.0500)  time: 1.0073  data: 0.0004  max mem: 78493
Epoch: [161]  [180/312]  eta: 0:02:25  lr: 0.001965  min_lr: 0.001965  loss: 2.5184 (2.2715)  weight_decay: 0.0500 (0.0500)  time: 1.0084  data: 0.0004  max mem: 78493
Epoch: [161]  [190/312]  eta: 0:02:14  lr: 0.001964  min_lr: 0.001964  loss: 2.4333 (2.2759)  weight_decay: 0.0500 (0.0500)  time: 1.0113  data: 0.0004  max mem: 78493
Epoch: [161]  [200/312]  eta: 0:02:02  lr: 0.001964  min_lr: 0.001964  loss: 2.3865 (2.2819)  weight_decay: 0.0500 (0.0500)  time: 1.0087  data: 0.0012  max mem: 78493
Epoch: [161]  [210/312]  eta: 0:01:51  lr: 0.001963  min_lr: 0.001963  loss: 2.3972 (2.2858)  weight_decay: 0.0500 (0.0500)  time: 1.0067  data: 0.0012  max mem: 78493
Epoch: [161]  [220/312]  eta: 0:01:39  lr: 0.001962  min_lr: 0.001962  loss: 2.4390 (2.2906)  weight_decay: 0.0500 (0.0500)  time: 1.0097  data: 0.0004  max mem: 78493
Epoch: [161]  [230/312]  eta: 0:01:28  lr: 0.001962  min_lr: 0.001962  loss: 2.4791 (2.2970)  weight_decay: 0.0500 (0.0500)  time: 1.0078  data: 0.0004  max mem: 78493
Epoch: [161]  [240/312]  eta: 0:01:17  lr: 0.001961  min_lr: 0.001961  loss: 2.4285 (2.2967)  weight_decay: 0.0500 (0.0500)  time: 1.0048  data: 0.0004  max mem: 78493
Epoch: [161]  [250/312]  eta: 0:01:06  lr: 0.001960  min_lr: 0.001960  loss: 2.3393 (2.2910)  weight_decay: 0.0500 (0.0500)  time: 1.0063  data: 0.0005  max mem: 78493
Epoch: [161]  [260/312]  eta: 0:00:55  lr: 0.001959  min_lr: 0.001959  loss: 2.1020 (2.2852)  weight_decay: 0.0500 (0.0500)  time: 1.0066  data: 0.0005  max mem: 78493
Epoch: [161]  [270/312]  eta: 0:00:45  lr: 0.001959  min_lr: 0.001959  loss: 2.3516 (2.2873)  weight_decay: 0.0500 (0.0500)  time: 1.0061  data: 0.0005  max mem: 78493
Epoch: [161]  [280/312]  eta: 0:00:34  lr: 0.001958  min_lr: 0.001958  loss: 2.3957 (2.2850)  weight_decay: 0.0500 (0.0500)  time: 1.0065  data: 0.0011  max mem: 78493
Epoch: [161]  [290/312]  eta: 0:00:23  lr: 0.001957  min_lr: 0.001957  loss: 2.1533 (2.2810)  weight_decay: 0.0500 (0.0500)  time: 1.0045  data: 0.0009  max mem: 78493
Epoch: [161]  [300/312]  eta: 0:00:12  lr: 0.001956  min_lr: 0.001956  loss: 2.2166 (2.2802)  weight_decay: 0.0500 (0.0500)  time: 1.0018  data: 0.0001  max mem: 78493
Epoch: [161]  [310/312]  eta: 0:00:02  lr: 0.001956  min_lr: 0.001956  loss: 2.3983 (2.2861)  weight_decay: 0.0500 (0.0500)  time: 1.0015  data: 0.0001  max mem: 78493
Epoch: [161]  [311/312]  eta: 0:00:01  lr: 0.001956  min_lr: 0.001956  loss: 2.4080 (2.2872)  weight_decay: 0.0500 (0.0500)  time: 1.0015  data: 0.0001  max mem: 78493
Epoch: [161] Total time: 0:05:33 (1.0682 s / it)
Averaged stats: lr: 0.001956  min_lr: 0.001956  loss: 2.4080 (2.2437)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:08  loss: 0.6948 (0.6948)  acc1: 83.4635 (83.4635)  acc5: 95.9635 (95.9635)  time: 7.6353  data: 7.3705  max mem: 78493
Test:  [8/9]  eta: 0:00:01  loss: 1.0526 (0.9318)  acc1: 73.8281 (76.4160)  acc5: 92.7083 (93.1680)  time: 1.0478  data: 0.8201  max mem: 78493
Test: Total time: 0:00:09 (1.0588 s / it)
* Acc@1 76.588 Acc@5 93.212 loss 0.910
Accuracy of the model on the 50000 test images: 76.6%
Max accuracy: 77.13%
Epoch: [162]  [  0/312]  eta: 1:25:47  lr: 0.001956  min_lr: 0.001956  loss: 2.4991 (2.4991)  weight_decay: 0.0500 (0.0500)  time: 16.5000  data: 12.3982  max mem: 78493
Epoch: [162]  [ 10/312]  eta: 0:13:17  lr: 0.001955  min_lr: 0.001955  loss: 2.3995 (2.3908)  weight_decay: 0.0500 (0.0500)  time: 2.6407  data: 1.3268  max mem: 78493
Epoch: [162]  [ 20/312]  eta: 0:09:04  lr: 0.001954  min_lr: 0.001954  loss: 2.3702 (2.2945)  weight_decay: 0.0500 (0.0500)  time: 1.1337  data: 0.1101  max mem: 78493
Epoch: [162]  [ 30/312]  eta: 0:07:28  lr: 0.001953  min_lr: 0.001953  loss: 2.3292 (2.3217)  weight_decay: 0.0500 (0.0500)  time: 1.0109  data: 0.0011  max mem: 78493
Epoch: [162]  [ 40/312]  eta: 0:06:33  lr: 0.001953  min_lr: 0.001953  loss: 2.4113 (2.3056)  weight_decay: 0.0500 (0.0500)  time: 1.0091  data: 0.0011  max mem: 78493
Epoch: [162]  [ 50/312]  eta: 0:05:56  lr: 0.001952  min_lr: 0.001952  loss: 2.3863 (2.2917)  weight_decay: 0.0500 (0.0500)  time: 1.0081  data: 0.0004  max mem: 78493
Epoch: [162]  [ 60/312]  eta: 0:05:28  lr: 0.001951  min_lr: 0.001951  loss: 2.1487 (2.2687)  weight_decay: 0.0500 (0.0500)  time: 1.0081  data: 0.0004  max mem: 78493
Epoch: [162]  [ 70/312]  eta: 0:05:05  lr: 0.001951  min_lr: 0.001951  loss: 2.1253 (2.2510)  weight_decay: 0.0500 (0.0500)  time: 1.0080  data: 0.0012  max mem: 78493
Epoch: [162]  [ 80/312]  eta: 0:04:45  lr: 0.001950  min_lr: 0.001950  loss: 2.1253 (2.2248)  weight_decay: 0.0500 (0.0500)  time: 1.0078  data: 0.0013  max mem: 78493
Epoch: [162]  [ 90/312]  eta: 0:04:27  lr: 0.001949  min_lr: 0.001949  loss: 1.9367 (2.2017)  weight_decay: 0.0500 (0.0500)  time: 1.0095  data: 0.0005  max mem: 78493
Epoch: [162]  [100/312]  eta: 0:04:11  lr: 0.001948  min_lr: 0.001948  loss: 2.3585 (2.2246)  weight_decay: 0.0500 (0.0500)  time: 1.0109  data: 0.0005  max mem: 78493
Epoch: [162]  [110/312]  eta: 0:03:56  lr: 0.001948  min_lr: 0.001948  loss: 1.9840 (2.1946)  weight_decay: 0.0500 (0.0500)  time: 1.0109  data: 0.0004  max mem: 78493
Epoch: [162]  [120/312]  eta: 0:03:42  lr: 0.001947  min_lr: 0.001947  loss: 1.9434 (2.2082)  weight_decay: 0.0500 (0.0500)  time: 1.0087  data: 0.0004  max mem: 78493
Epoch: [162]  [130/312]  eta: 0:03:28  lr: 0.001946  min_lr: 0.001946  loss: 2.4436 (2.2153)  weight_decay: 0.0500 (0.0500)  time: 1.0082  data: 0.0005  max mem: 78493
Epoch: [162]  [140/312]  eta: 0:03:15  lr: 0.001946  min_lr: 0.001946  loss: 2.3672 (2.2186)  weight_decay: 0.0500 (0.0500)  time: 1.0082  data: 0.0004  max mem: 78493
Epoch: [162]  [150/312]  eta: 0:03:02  lr: 0.001945  min_lr: 0.001945  loss: 2.4090 (2.2339)  weight_decay: 0.0500 (0.0500)  time: 1.0054  data: 0.0004  max mem: 78493
Epoch: [162]  [160/312]  eta: 0:02:50  lr: 0.001944  min_lr: 0.001944  loss: 2.4090 (2.2370)  weight_decay: 0.0500 (0.0500)  time: 1.0050  data: 0.0005  max mem: 78493
Epoch: [162]  [170/312]  eta: 0:02:38  lr: 0.001943  min_lr: 0.001943  loss: 2.3281 (2.2413)  weight_decay: 0.0500 (0.0500)  time: 1.0065  data: 0.0004  max mem: 78493
Epoch: [162]  [180/312]  eta: 0:02:26  lr: 0.001943  min_lr: 0.001943  loss: 2.4385 (2.2497)  weight_decay: 0.0500 (0.0500)  time: 1.0064  data: 0.0005  max mem: 78493
Epoch: [162]  [190/312]  eta: 0:02:14  lr: 0.001942  min_lr: 0.001942  loss: 2.3939 (2.2527)  weight_decay: 0.0500 (0.0500)  time: 1.0073  data: 0.0005  max mem: 78493
Epoch: [162]  [200/312]  eta: 0:02:02  lr: 0.001941  min_lr: 0.001941  loss: 2.3897 (2.2587)  weight_decay: 0.0500 (0.0500)  time: 1.0083  data: 0.0005  max mem: 78493
Epoch: [162]  [210/312]  eta: 0:01:51  lr: 0.001941  min_lr: 0.001941  loss: 2.2758 (2.2502)  weight_decay: 0.0500 (0.0500)  time: 1.0079  data: 0.0005  max mem: 78493
Epoch: [162]  [220/312]  eta: 0:01:40  lr: 0.001940  min_lr: 0.001940  loss: 2.1422 (2.2422)  weight_decay: 0.0500 (0.0500)  time: 1.0089  data: 0.0005  max mem: 78493
Epoch: [162]  [230/312]  eta: 0:01:29  lr: 0.001939  min_lr: 0.001939  loss: 2.1934 (2.2396)  weight_decay: 0.0500 (0.0500)  time: 1.0078  data: 0.0005  max mem: 78493
Epoch: [162]  [240/312]  eta: 0:01:17  lr: 0.001938  min_lr: 0.001938  loss: 2.0859 (2.2283)  weight_decay: 0.0500 (0.0500)  time: 1.0052  data: 0.0004  max mem: 78493
Epoch: [162]  [250/312]  eta: 0:01:06  lr: 0.001938  min_lr: 0.001938  loss: 2.1519 (2.2273)  weight_decay: 0.0500 (0.0500)  time: 1.0047  data: 0.0004  max mem: 78493
Epoch: [162]  [260/312]  eta: 0:00:55  lr: 0.001937  min_lr: 0.001937  loss: 2.1752 (2.2247)  weight_decay: 0.0500 (0.0500)  time: 1.0053  data: 0.0005  max mem: 78493
Epoch: [162]  [270/312]  eta: 0:00:45  lr: 0.001936  min_lr: 0.001936  loss: 2.3271 (2.2287)  weight_decay: 0.0500 (0.0500)  time: 1.0063  data: 0.0004  max mem: 78493
Epoch: [162]  [280/312]  eta: 0:00:34  lr: 0.001936  min_lr: 0.001936  loss: 2.3198 (2.2241)  weight_decay: 0.0500 (0.0500)  time: 1.0059  data: 0.0010  max mem: 78493
Epoch: [162]  [290/312]  eta: 0:00:23  lr: 0.001935  min_lr: 0.001935  loss: 2.4135 (2.2301)  weight_decay: 0.0500 (0.0500)  time: 1.0041  data: 0.0009  max mem: 78493
Epoch: [162]  [300/312]  eta: 0:00:12  lr: 0.001934  min_lr: 0.001934  loss: 2.4583 (2.2332)  weight_decay: 0.0500 (0.0500)  time: 1.0029  data: 0.0001  max mem: 78493
Epoch: [162]  [310/312]  eta: 0:00:02  lr: 0.001933  min_lr: 0.001933  loss: 2.4737 (2.2393)  weight_decay: 0.0500 (0.0500)  time: 1.0024  data: 0.0001  max mem: 78493
Epoch: [162]  [311/312]  eta: 0:00:01  lr: 0.001933  min_lr: 0.001933  loss: 2.4610 (2.2367)  weight_decay: 0.0500 (0.0500)  time: 1.0024  data: 0.0001  max mem: 78493
Epoch: [162] Total time: 0:05:33 (1.0701 s / it)
Averaged stats: lr: 0.001933  min_lr: 0.001933  loss: 2.4610 (2.2462)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:12  loss: 0.6625 (0.6625)  acc1: 83.2031 (83.2031)  acc5: 95.8333 (95.8333)  time: 8.0413  data: 7.7808  max mem: 78493
Test:  [8/9]  eta: 0:00:01  loss: 0.9371 (0.8855)  acc1: 75.7812 (76.9760)  acc5: 93.6198 (93.6480)  time: 1.1206  data: 0.8895  max mem: 78493
Test: Total time: 0:00:10 (1.1488 s / it)
* Acc@1 77.224 Acc@5 93.662 loss 0.871
Accuracy of the model on the 50000 test images: 77.2%
Max accuracy: 77.22%
Epoch: [163]  [  0/312]  eta: 1:27:06  lr: 0.001933  min_lr: 0.001933  loss: 1.8929 (1.8929)  weight_decay: 0.0500 (0.0500)  time: 16.7504  data: 15.7085  max mem: 78493
Epoch: [163]  [ 10/312]  eta: 0:13:43  lr: 0.001932  min_lr: 0.001932  loss: 2.5545 (2.4526)  weight_decay: 0.0500 (0.0500)  time: 2.7256  data: 1.4287  max mem: 78493
Epoch: [163]  [ 20/312]  eta: 0:09:16  lr: 0.001932  min_lr: 0.001932  loss: 2.4770 (2.4106)  weight_decay: 0.0500 (0.0500)  time: 1.1643  data: 0.0006  max mem: 78493
Epoch: [163]  [ 30/312]  eta: 0:07:35  lr: 0.001931  min_lr: 0.001931  loss: 2.4264 (2.3690)  weight_decay: 0.0500 (0.0500)  time: 1.0059  data: 0.0004  max mem: 78493
Epoch: [163]  [ 40/312]  eta: 0:06:39  lr: 0.001930  min_lr: 0.001930  loss: 2.3932 (2.3757)  weight_decay: 0.0500 (0.0500)  time: 1.0064  data: 0.0004  max mem: 78493
Epoch: [163]  [ 50/312]  eta: 0:06:00  lr: 0.001930  min_lr: 0.001930  loss: 2.3453 (2.3559)  weight_decay: 0.0500 (0.0500)  time: 1.0074  data: 0.0005  max mem: 78493
Epoch: [163]  [ 60/312]  eta: 0:05:31  lr: 0.001929  min_lr: 0.001929  loss: 2.2530 (2.3515)  weight_decay: 0.0500 (0.0500)  time: 1.0090  data: 0.0004  max mem: 78493
Epoch: [163]  [ 70/312]  eta: 0:05:08  lr: 0.001928  min_lr: 0.001928  loss: 2.3141 (2.3490)  weight_decay: 0.0500 (0.0500)  time: 1.0092  data: 0.0004  max mem: 78493
Epoch: [163]  [ 80/312]  eta: 0:04:47  lr: 0.001927  min_lr: 0.001927  loss: 2.3141 (2.3296)  weight_decay: 0.0500 (0.0500)  time: 1.0087  data: 0.0004  max mem: 78493
Epoch: [163]  [ 90/312]  eta: 0:04:29  lr: 0.001927  min_lr: 0.001927  loss: 2.3409 (2.3212)  weight_decay: 0.0500 (0.0500)  time: 1.0074  data: 0.0004  max mem: 78493
Epoch: [163]  [100/312]  eta: 0:04:13  lr: 0.001926  min_lr: 0.001926  loss: 2.3409 (2.3255)  weight_decay: 0.0500 (0.0500)  time: 1.0085  data: 0.0004  max mem: 78493
Epoch: [163]  [110/312]  eta: 0:03:57  lr: 0.001925  min_lr: 0.001925  loss: 2.3294 (2.3108)  weight_decay: 0.0500 (0.0500)  time: 1.0093  data: 0.0005  max mem: 78493
Epoch: [163]  [120/312]  eta: 0:03:43  lr: 0.001925  min_lr: 0.001925  loss: 2.3241 (2.3176)  weight_decay: 0.0500 (0.0500)  time: 1.0075  data: 0.0004  max mem: 78493
Epoch: [163]  [130/312]  eta: 0:03:29  lr: 0.001924  min_lr: 0.001924  loss: 2.1695 (2.2957)  weight_decay: 0.0500 (0.0500)  time: 1.0067  data: 0.0005  max mem: 78493
Epoch: [163]  [140/312]  eta: 0:03:16  lr: 0.001923  min_lr: 0.001923  loss: 2.1386 (2.2823)  weight_decay: 0.0500 (0.0500)  time: 1.0060  data: 0.0005  max mem: 78493
Epoch: [163]  [150/312]  eta: 0:03:03  lr: 0.001922  min_lr: 0.001922  loss: 2.2693 (2.2777)  weight_decay: 0.0500 (0.0500)  time: 1.0078  data: 0.0005  max mem: 78493
Epoch: [163]  [160/312]  eta: 0:02:51  lr: 0.001922  min_lr: 0.001922  loss: 2.2831 (2.2728)  weight_decay: 0.0500 (0.0500)  time: 1.0082  data: 0.0004  max mem: 78493
Epoch: [163]  [170/312]  eta: 0:02:38  lr: 0.001921  min_lr: 0.001921  loss: 2.2387 (2.2676)  weight_decay: 0.0500 (0.0500)  time: 1.0094  data: 0.0005  max mem: 78493
Epoch: [163]  [180/312]  eta: 0:02:26  lr: 0.001920  min_lr: 0.001920  loss: 2.3366 (2.2727)  weight_decay: 0.0500 (0.0500)  time: 1.0094  data: 0.0005  max mem: 78493
Epoch: [163]  [190/312]  eta: 0:02:15  lr: 0.001920  min_lr: 0.001920  loss: 2.3635 (2.2725)  weight_decay: 0.0500 (0.0500)  time: 1.0071  data: 0.0005  max mem: 78493
Epoch: [163]  [200/312]  eta: 0:02:03  lr: 0.001919  min_lr: 0.001919  loss: 2.3862 (2.2730)  weight_decay: 0.0500 (0.0500)  time: 1.0082  data: 0.0004  max mem: 78493
Epoch: [163]  [210/312]  eta: 0:01:51  lr: 0.001918  min_lr: 0.001918  loss: 2.3537 (2.2739)  weight_decay: 0.0500 (0.0500)  time: 1.0076  data: 0.0004  max mem: 78493
Epoch: [163]  [220/312]  eta: 0:01:40  lr: 0.001917  min_lr: 0.001917  loss: 2.0617 (2.2653)  weight_decay: 0.0500 (0.0500)  time: 1.0056  data: 0.0004  max mem: 78493
Epoch: [163]  [230/312]  eta: 0:01:29  lr: 0.001917  min_lr: 0.001917  loss: 2.1661 (2.2651)  weight_decay: 0.0500 (0.0500)  time: 1.0071  data: 0.0011  max mem: 78493
Epoch: [163]  [240/312]  eta: 0:01:18  lr: 0.001916  min_lr: 0.001916  loss: 2.3528 (2.2690)  weight_decay: 0.0500 (0.0500)  time: 1.0076  data: 0.0011  max mem: 78493
Epoch: [163]  [250/312]  eta: 0:01:07  lr: 0.001915  min_lr: 0.001915  loss: 2.3528 (2.2697)  weight_decay: 0.0500 (0.0500)  time: 1.0057  data: 0.0005  max mem: 78493
Epoch: [163]  [260/312]  eta: 0:00:56  lr: 0.001915  min_lr: 0.001915  loss: 2.3533 (2.2689)  weight_decay: 0.0500 (0.0500)  time: 1.0066  data: 0.0005  max mem: 78493
Epoch: [163]  [270/312]  eta: 0:00:45  lr: 0.001914  min_lr: 0.001914  loss: 2.3118 (2.2658)  weight_decay: 0.0500 (0.0500)  time: 1.0063  data: 0.0004  max mem: 78493
Epoch: [163]  [280/312]  eta: 0:00:34  lr: 0.001913  min_lr: 0.001913  loss: 2.1217 (2.2538)  weight_decay: 0.0500 (0.0500)  time: 1.0051  data: 0.0010  max mem: 78493
Epoch: [163]  [290/312]  eta: 0:00:23  lr: 0.001912  min_lr: 0.001912  loss: 2.1051 (2.2516)  weight_decay: 0.0500 (0.0500)  time: 1.0039  data: 0.0009  max mem: 78493
Epoch: [163]  [300/312]  eta: 0:00:12  lr: 0.001912  min_lr: 0.001912  loss: 2.3691 (2.2536)  weight_decay: 0.0500 (0.0500)  time: 1.0022  data: 0.0001  max mem: 78493
Epoch: [163]  [310/312]  eta: 0:00:02  lr: 0.001911  min_lr: 0.001911  loss: 2.3691 (2.2563)  weight_decay: 0.0500 (0.0500)  time: 1.0022  data: 0.0001  max mem: 78493
Epoch: [163]  [311/312]  eta: 0:00:01  lr: 0.001911  min_lr: 0.001911  loss: 2.3644 (2.2545)  weight_decay: 0.0500 (0.0500)  time: 1.0022  data: 0.0001  max mem: 78493
Epoch: [163] Total time: 0:05:34 (1.0732 s / it)
Averaged stats: lr: 0.001911  min_lr: 0.001911  loss: 2.3644 (2.2282)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:14  loss: 0.6765 (0.6765)  acc1: 82.8125 (82.8125)  acc5: 96.3542 (96.3542)  time: 8.2520  data: 7.9736  max mem: 78493
Test:  [8/9]  eta: 0:00:01  loss: 1.0060 (0.9029)  acc1: 75.2604 (76.7840)  acc5: 94.1406 (93.4560)  time: 1.1151  data: 0.8860  max mem: 78493
Test: Total time: 0:00:10 (1.1463 s / it)
* Acc@1 76.980 Acc@5 93.640 loss 0.888
Accuracy of the model on the 50000 test images: 77.0%
Max accuracy: 77.22%
Epoch: [164]  [  0/312]  eta: 1:27:34  lr: 0.001911  min_lr: 0.001911  loss: 2.4257 (2.4257)  weight_decay: 0.0500 (0.0500)  time: 16.8408  data: 12.3044  max mem: 78493
Epoch: [164]  [ 10/312]  eta: 0:13:19  lr: 0.001910  min_lr: 0.001910  loss: 2.2122 (2.0777)  weight_decay: 0.0500 (0.0500)  time: 2.6472  data: 1.2734  max mem: 78493
Epoch: [164]  [ 20/312]  eta: 0:09:07  lr: 0.001909  min_lr: 0.001909  loss: 2.2391 (2.1867)  weight_decay: 0.0500 (0.0500)  time: 1.1257  data: 0.0854  max mem: 78493
Epoch: [164]  [ 30/312]  eta: 0:07:29  lr: 0.001909  min_lr: 0.001909  loss: 2.3028 (2.2088)  weight_decay: 0.0500 (0.0500)  time: 1.0164  data: 0.0005  max mem: 78493
Epoch: [164]  [ 40/312]  eta: 0:06:34  lr: 0.001908  min_lr: 0.001908  loss: 2.1974 (2.1806)  weight_decay: 0.0500 (0.0500)  time: 1.0076  data: 0.0004  max mem: 78493
Epoch: [164]  [ 50/312]  eta: 0:05:57  lr: 0.001907  min_lr: 0.001907  loss: 2.1004 (2.1501)  weight_decay: 0.0500 (0.0500)  time: 1.0076  data: 0.0004  max mem: 78493
Epoch: [164]  [ 60/312]  eta: 0:05:29  lr: 0.001906  min_lr: 0.001906  loss: 2.1228 (2.1268)  weight_decay: 0.0500 (0.0500)  time: 1.0096  data: 0.0004  max mem: 78493
Epoch: [164]  [ 70/312]  eta: 0:05:06  lr: 0.001906  min_lr: 0.001906  loss: 1.9813 (2.1083)  weight_decay: 0.0500 (0.0500)  time: 1.0100  data: 0.0004  max mem: 78493
Epoch: [164]  [ 80/312]  eta: 0:04:46  lr: 0.001905  min_lr: 0.001905  loss: 1.8226 (2.0948)  weight_decay: 0.0500 (0.0500)  time: 1.0106  data: 0.0004  max mem: 78493
Epoch: [164]  [ 90/312]  eta: 0:04:28  lr: 0.001904  min_lr: 0.001904  loss: 2.2897 (2.1138)  weight_decay: 0.0500 (0.0500)  time: 1.0096  data: 0.0004  max mem: 78493
Epoch: [164]  [100/312]  eta: 0:04:12  lr: 0.001904  min_lr: 0.001904  loss: 2.3705 (2.1303)  weight_decay: 0.0500 (0.0500)  time: 1.0077  data: 0.0004  max mem: 78493
Epoch: [164]  [110/312]  eta: 0:03:56  lr: 0.001903  min_lr: 0.001903  loss: 2.3408 (2.1371)  weight_decay: 0.0500 (0.0500)  time: 1.0079  data: 0.0013  max mem: 78493
Epoch: [164]  [120/312]  eta: 0:03:42  lr: 0.001902  min_lr: 0.001902  loss: 2.2674 (2.1443)  weight_decay: 0.0500 (0.0500)  time: 1.0074  data: 0.0013  max mem: 78493
Epoch: [164]  [130/312]  eta: 0:03:28  lr: 0.001901  min_lr: 0.001901  loss: 2.3648 (2.1712)  weight_decay: 0.0500 (0.0500)  time: 1.0074  data: 0.0005  max mem: 78493
Epoch: [164]  [140/312]  eta: 0:03:15  lr: 0.001901  min_lr: 0.001901  loss: 2.3936 (2.1652)  weight_decay: 0.0500 (0.0500)  time: 1.0080  data: 0.0005  max mem: 78493
Epoch: [164]  [150/312]  eta: 0:03:02  lr: 0.001900  min_lr: 0.001900  loss: 2.0475 (2.1548)  weight_decay: 0.0500 (0.0500)  time: 1.0078  data: 0.0004  max mem: 78493
Epoch: [164]  [160/312]  eta: 0:02:50  lr: 0.001899  min_lr: 0.001899  loss: 2.3818 (2.1622)  weight_decay: 0.0500 (0.0500)  time: 1.0071  data: 0.0004  max mem: 78493
Epoch: [164]  [170/312]  eta: 0:02:38  lr: 0.001899  min_lr: 0.001899  loss: 2.3818 (2.1656)  weight_decay: 0.0500 (0.0500)  time: 1.0086  data: 0.0004  max mem: 78493
Epoch: [164]  [180/312]  eta: 0:02:26  lr: 0.001898  min_lr: 0.001898  loss: 2.3075 (2.1724)  weight_decay: 0.0500 (0.0500)  time: 1.0098  data: 0.0004  max mem: 78493
Epoch: [164]  [190/312]  eta: 0:02:14  lr: 0.001897  min_lr: 0.001897  loss: 2.3609 (2.1804)  weight_decay: 0.0500 (0.0500)  time: 1.0071  data: 0.0004  max mem: 78493
Epoch: [164]  [200/312]  eta: 0:02:03  lr: 0.001896  min_lr: 0.001896  loss: 2.1756 (2.1820)  weight_decay: 0.0500 (0.0500)  time: 1.0074  data: 0.0004  max mem: 78493
Epoch: [164]  [210/312]  eta: 0:01:51  lr: 0.001896  min_lr: 0.001896  loss: 2.1756 (2.1762)  weight_decay: 0.0500 (0.0500)  time: 1.0070  data: 0.0004  max mem: 78493
Epoch: [164]  [220/312]  eta: 0:01:40  lr: 0.001895  min_lr: 0.001895  loss: 2.3086 (2.1857)  weight_decay: 0.0500 (0.0500)  time: 1.0061  data: 0.0004  max mem: 78493
Epoch: [164]  [230/312]  eta: 0:01:29  lr: 0.001894  min_lr: 0.001894  loss: 2.3126 (2.1884)  weight_decay: 0.0500 (0.0500)  time: 1.0071  data: 0.0004  max mem: 78493
Epoch: [164]  [240/312]  eta: 0:01:18  lr: 0.001894  min_lr: 0.001894  loss: 2.2726 (2.1883)  weight_decay: 0.0500 (0.0500)  time: 1.0058  data: 0.0004  max mem: 78493
Epoch: [164]  [250/312]  eta: 0:01:06  lr: 0.001893  min_lr: 0.001893  loss: 2.3629 (2.1974)  weight_decay: 0.0500 (0.0500)  time: 1.0058  data: 0.0004  max mem: 78493
Epoch: [164]  [260/312]  eta: 0:00:56  lr: 0.001892  min_lr: 0.001892  loss: 2.4238 (2.2033)  weight_decay: 0.0500 (0.0500)  time: 1.0069  data: 0.0004  max mem: 78493
Epoch: [164]  [270/312]  eta: 0:00:45  lr: 0.001891  min_lr: 0.001891  loss: 2.3702 (2.2034)  weight_decay: 0.0500 (0.0500)  time: 1.0065  data: 0.0004  max mem: 78493
Epoch: [164]  [280/312]  eta: 0:00:34  lr: 0.001891  min_lr: 0.001891  loss: 2.3249 (2.2061)  weight_decay: 0.0500 (0.0500)  time: 1.0064  data: 0.0011  max mem: 78493
Epoch: [164]  [290/312]  eta: 0:00:23  lr: 0.001890  min_lr: 0.001890  loss: 2.2403 (2.2054)  weight_decay: 0.0500 (0.0500)  time: 1.0048  data: 0.0009  max mem: 78493
Epoch: [164]  [300/312]  eta: 0:00:12  lr: 0.001889  min_lr: 0.001889  loss: 2.2403 (2.2092)  weight_decay: 0.0500 (0.0500)  time: 1.0022  data: 0.0001  max mem: 78493
Epoch: [164]  [310/312]  eta: 0:00:02  lr: 0.001889  min_lr: 0.001889  loss: 2.2056 (2.2044)  weight_decay: 0.0500 (0.0500)  time: 1.0015  data: 0.0001  max mem: 78493
Epoch: [164]  [311/312]  eta: 0:00:01  lr: 0.001888  min_lr: 0.001888  loss: 2.2056 (2.2020)  weight_decay: 0.0500 (0.0500)  time: 1.0015  data: 0.0001  max mem: 78493
Epoch: [164] Total time: 0:05:34 (1.0710 s / it)
Averaged stats: lr: 0.001888  min_lr: 0.001888  loss: 2.2056 (2.2368)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:13  loss: 0.6519 (0.6519)  acc1: 83.9844 (83.9844)  acc5: 95.5729 (95.5729)  time: 8.1775  data: 7.9096  max mem: 78493
Test:  [8/9]  eta: 0:00:01  loss: 0.9724 (0.8802)  acc1: 75.6510 (77.0880)  acc5: 93.0990 (93.3760)  time: 1.1079  data: 0.8790  max mem: 78493
Test: Total time: 0:00:10 (1.1469 s / it)
* Acc@1 77.522 Acc@5 93.710 loss 0.872
Accuracy of the model on the 50000 test images: 77.5%
Max accuracy: 77.52%
Epoch: [165]  [  0/312]  eta: 1:26:14  lr: 0.001888  min_lr: 0.001888  loss: 1.9277 (1.9277)  weight_decay: 0.0500 (0.0500)  time: 16.5854  data: 15.5835  max mem: 78493
Epoch: [165]  [ 10/312]  eta: 0:13:40  lr: 0.001888  min_lr: 0.001888  loss: 2.0533 (2.0268)  weight_decay: 0.0500 (0.0500)  time: 2.7153  data: 1.4173  max mem: 78493
Epoch: [165]  [ 20/312]  eta: 0:09:15  lr: 0.001887  min_lr: 0.001887  loss: 2.2106 (2.1561)  weight_decay: 0.0500 (0.0500)  time: 1.1678  data: 0.0006  max mem: 78493
Epoch: [165]  [ 30/312]  eta: 0:07:35  lr: 0.001886  min_lr: 0.001886  loss: 2.2617 (2.1735)  weight_decay: 0.0500 (0.0500)  time: 1.0081  data: 0.0005  max mem: 78493
Epoch: [165]  [ 40/312]  eta: 0:06:38  lr: 0.001886  min_lr: 0.001886  loss: 2.2046 (2.1921)  weight_decay: 0.0500 (0.0500)  time: 1.0073  data: 0.0005  max mem: 78493
Epoch: [165]  [ 50/312]  eta: 0:06:00  lr: 0.001885  min_lr: 0.001885  loss: 2.3980 (2.2458)  weight_decay: 0.0500 (0.0500)  time: 1.0083  data: 0.0005  max mem: 78493
Epoch: [165]  [ 60/312]  eta: 0:05:31  lr: 0.001884  min_lr: 0.001884  loss: 2.4193 (2.2622)  weight_decay: 0.0500 (0.0500)  time: 1.0080  data: 0.0005  max mem: 78493
Epoch: [165]  [ 70/312]  eta: 0:05:07  lr: 0.001883  min_lr: 0.001883  loss: 2.1004 (2.2404)  weight_decay: 0.0500 (0.0500)  time: 1.0073  data: 0.0005  max mem: 78493
Epoch: [165]  [ 80/312]  eta: 0:04:47  lr: 0.001883  min_lr: 0.001883  loss: 2.3257 (2.2520)  weight_decay: 0.0500 (0.0500)  time: 1.0086  data: 0.0005  max mem: 78493
Epoch: [165]  [ 90/312]  eta: 0:04:29  lr: 0.001882  min_lr: 0.001882  loss: 2.2995 (2.2241)  weight_decay: 0.0500 (0.0500)  time: 1.0076  data: 0.0004  max mem: 78493
Epoch: [165]  [100/312]  eta: 0:04:13  lr: 0.001881  min_lr: 0.001881  loss: 2.1608 (2.2264)  weight_decay: 0.0500 (0.0500)  time: 1.0058  data: 0.0004  max mem: 78493
Epoch: [165]  [110/312]  eta: 0:03:57  lr: 0.001880  min_lr: 0.001880  loss: 2.2394 (2.2266)  weight_decay: 0.0500 (0.0500)  time: 1.0064  data: 0.0004  max mem: 78493
Epoch: [165]  [120/312]  eta: 0:03:43  lr: 0.001880  min_lr: 0.001880  loss: 2.2943 (2.2358)  weight_decay: 0.0500 (0.0500)  time: 1.0081  data: 0.0004  max mem: 78493
Epoch: [165]  [130/312]  eta: 0:03:29  lr: 0.001879  min_lr: 0.001879  loss: 2.2943 (2.2427)  weight_decay: 0.0500 (0.0500)  time: 1.0064  data: 0.0005  max mem: 78493
Epoch: [165]  [140/312]  eta: 0:03:16  lr: 0.001878  min_lr: 0.001878  loss: 2.3354 (2.2525)  weight_decay: 0.0500 (0.0500)  time: 1.0066  data: 0.0005  max mem: 78493
Epoch: [165]  [150/312]  eta: 0:03:03  lr: 0.001878  min_lr: 0.001878  loss: 2.2519 (2.2402)  weight_decay: 0.0500 (0.0500)  time: 1.0069  data: 0.0004  max mem: 78493
Epoch: [165]  [160/312]  eta: 0:02:50  lr: 0.001877  min_lr: 0.001877  loss: 2.3197 (2.2537)  weight_decay: 0.0500 (0.0500)  time: 1.0062  data: 0.0004  max mem: 78493
Epoch: [165]  [170/312]  eta: 0:02:38  lr: 0.001876  min_lr: 0.001876  loss: 2.3197 (2.2486)  weight_decay: 0.0500 (0.0500)  time: 1.0053  data: 0.0004  max mem: 78493
Epoch: [165]  [180/312]  eta: 0:02:26  lr: 0.001875  min_lr: 0.001875  loss: 2.1522 (2.2389)  weight_decay: 0.0500 (0.0500)  time: 1.0052  data: 0.0004  max mem: 78493
Epoch: [165]  [190/312]  eta: 0:02:14  lr: 0.001875  min_lr: 0.001875  loss: 2.2813 (2.2449)  weight_decay: 0.0500 (0.0500)  time: 1.0049  data: 0.0004  max mem: 78493
Epoch: [165]  [200/312]  eta: 0:02:03  lr: 0.001874  min_lr: 0.001874  loss: 2.3685 (2.2472)  weight_decay: 0.0500 (0.0500)  time: 1.0060  data: 0.0004  max mem: 78493
Epoch: [165]  [210/312]  eta: 0:01:51  lr: 0.001873  min_lr: 0.001873  loss: 2.3092 (2.2459)  weight_decay: 0.0500 (0.0500)  time: 1.0077  data: 0.0005  max mem: 78493
Epoch: [165]  [220/312]  eta: 0:01:40  lr: 0.001873  min_lr: 0.001873  loss: 2.1222 (2.2370)  weight_decay: 0.0500 (0.0500)  time: 1.0062  data: 0.0005  max mem: 78493
Epoch: [165]  [230/312]  eta: 0:01:29  lr: 0.001872  min_lr: 0.001872  loss: 2.0931 (2.2370)  weight_decay: 0.0500 (0.0500)  time: 1.0058  data: 0.0004  max mem: 78493
Epoch: [165]  [240/312]  eta: 0:01:18  lr: 0.001871  min_lr: 0.001871  loss: 2.0931 (2.2340)  weight_decay: 0.0500 (0.0500)  time: 1.0065  data: 0.0004  max mem: 78493
Epoch: [165]  [250/312]  eta: 0:01:07  lr: 0.001870  min_lr: 0.001870  loss: 2.0128 (2.2275)  weight_decay: 0.0500 (0.0500)  time: 1.0060  data: 0.0004  max mem: 78493
Epoch: [165]  [260/312]  eta: 0:00:56  lr: 0.001870  min_lr: 0.001870  loss: 2.2458 (2.2338)  weight_decay: 0.0500 (0.0500)  time: 1.0049  data: 0.0004  max mem: 78493
Epoch: [165]  [270/312]  eta: 0:00:45  lr: 0.001869  min_lr: 0.001869  loss: 2.4352 (2.2373)  weight_decay: 0.0500 (0.0500)  time: 1.0051  data: 0.0005  max mem: 78493
Epoch: [165]  [280/312]  eta: 0:00:34  lr: 0.001868  min_lr: 0.001868  loss: 2.2913 (2.2346)  weight_decay: 0.0500 (0.0500)  time: 1.0089  data: 0.0010  max mem: 78493
Epoch: [165]  [290/312]  eta: 0:00:23  lr: 0.001868  min_lr: 0.001868  loss: 1.9808 (2.2245)  weight_decay: 0.0500 (0.0500)  time: 1.0077  data: 0.0009  max mem: 78493
Epoch: [165]  [300/312]  eta: 0:00:12  lr: 0.001867  min_lr: 0.001867  loss: 1.9808 (2.2227)  weight_decay: 0.0500 (0.0500)  time: 1.0028  data: 0.0001  max mem: 78493
Epoch: [165]  [310/312]  eta: 0:00:02  lr: 0.001866  min_lr: 0.001866  loss: 2.2971 (2.2261)  weight_decay: 0.0500 (0.0500)  time: 1.0021  data: 0.0001  max mem: 78493
Epoch: [165]  [311/312]  eta: 0:00:01  lr: 0.001866  min_lr: 0.001866  loss: 2.2503 (2.2236)  weight_decay: 0.0500 (0.0500)  time: 1.0021  data: 0.0001  max mem: 78493
Epoch: [165] Total time: 0:05:34 (1.0722 s / it)
Averaged stats: lr: 0.001866  min_lr: 0.001866  loss: 2.2503 (2.2319)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:16  loss: 0.6495 (0.6495)  acc1: 83.3333 (83.3333)  acc5: 95.9635 (95.9635)  time: 8.5154  data: 8.2375  max mem: 78493
Test:  [8/9]  eta: 0:00:01  loss: 0.9410 (0.8944)  acc1: 76.5625 (76.5440)  acc5: 94.0104 (93.5520)  time: 1.1445  data: 0.9154  max mem: 78493
Test: Total time: 0:00:10 (1.1858 s / it)
* Acc@1 77.124 Acc@5 93.674 loss 0.878
Accuracy of the model on the 50000 test images: 77.1%
Max accuracy: 77.52%
Epoch: [166]  [  0/312]  eta: 1:25:44  lr: 0.001866  min_lr: 0.001866  loss: 2.1315 (2.1315)  weight_decay: 0.0500 (0.0500)  time: 16.4901  data: 15.4841  max mem: 78493
Epoch: [166]  [ 10/312]  eta: 0:13:42  lr: 0.001865  min_lr: 0.001865  loss: 2.2041 (2.2148)  weight_decay: 0.0500 (0.0500)  time: 2.7240  data: 1.4101  max mem: 78493
Epoch: [166]  [ 20/312]  eta: 0:09:16  lr: 0.001865  min_lr: 0.001865  loss: 2.2554 (2.2409)  weight_decay: 0.0500 (0.0500)  time: 1.1769  data: 0.0016  max mem: 78493
Epoch: [166]  [ 30/312]  eta: 0:07:35  lr: 0.001864  min_lr: 0.001864  loss: 2.2554 (2.2324)  weight_decay: 0.0500 (0.0500)  time: 1.0073  data: 0.0005  max mem: 78493
Epoch: [166]  [ 40/312]  eta: 0:06:39  lr: 0.001863  min_lr: 0.001863  loss: 2.1183 (2.2109)  weight_decay: 0.0500 (0.0500)  time: 1.0102  data: 0.0005  max mem: 78493
Epoch: [166]  [ 50/312]  eta: 0:06:01  lr: 0.001862  min_lr: 0.001862  loss: 2.1489 (2.2058)  weight_decay: 0.0500 (0.0500)  time: 1.0096  data: 0.0004  max mem: 78493
Epoch: [166]  [ 60/312]  eta: 0:05:32  lr: 0.001862  min_lr: 0.001862  loss: 2.1489 (2.1921)  weight_decay: 0.0500 (0.0500)  time: 1.0069  data: 0.0005  max mem: 78493
Epoch: [166]  [ 70/312]  eta: 0:05:08  lr: 0.001861  min_lr: 0.001861  loss: 2.1235 (2.1878)  weight_decay: 0.0500 (0.0500)  time: 1.0066  data: 0.0005  max mem: 78493
Epoch: [166]  [ 80/312]  eta: 0:04:47  lr: 0.001860  min_lr: 0.001860  loss: 2.1845 (2.1936)  weight_decay: 0.0500 (0.0500)  time: 1.0065  data: 0.0004  max mem: 78493
Epoch: [166]  [ 90/312]  eta: 0:04:29  lr: 0.001860  min_lr: 0.001860  loss: 2.1845 (2.1867)  weight_decay: 0.0500 (0.0500)  time: 1.0081  data: 0.0013  max mem: 78493
Epoch: [166]  [100/312]  eta: 0:04:13  lr: 0.001859  min_lr: 0.001859  loss: 2.4105 (2.2211)  weight_decay: 0.0500 (0.0500)  time: 1.0098  data: 0.0013  max mem: 78493
Epoch: [166]  [110/312]  eta: 0:03:58  lr: 0.001858  min_lr: 0.001858  loss: 2.3960 (2.2218)  weight_decay: 0.0500 (0.0500)  time: 1.0114  data: 0.0004  max mem: 78493
Epoch: [166]  [120/312]  eta: 0:03:43  lr: 0.001857  min_lr: 0.001857  loss: 2.3574 (2.2295)  weight_decay: 0.0500 (0.0500)  time: 1.0105  data: 0.0004  max mem: 78493
Epoch: [166]  [130/312]  eta: 0:03:29  lr: 0.001857  min_lr: 0.001857  loss: 2.3606 (2.2300)  weight_decay: 0.0500 (0.0500)  time: 1.0083  data: 0.0004  max mem: 78493
Epoch: [166]  [140/312]  eta: 0:03:16  lr: 0.001856  min_lr: 0.001856  loss: 2.4219 (2.2436)  weight_decay: 0.0500 (0.0500)  time: 1.0073  data: 0.0004  max mem: 78493
Epoch: [166]  [150/312]  eta: 0:03:03  lr: 0.001855  min_lr: 0.001855  loss: 2.3836 (2.2462)  weight_decay: 0.0500 (0.0500)  time: 1.0073  data: 0.0004  max mem: 78493
Epoch: [166]  [160/312]  eta: 0:02:51  lr: 0.001855  min_lr: 0.001855  loss: 2.2772 (2.2438)  weight_decay: 0.0500 (0.0500)  time: 1.0076  data: 0.0004  max mem: 78493
Epoch: [166]  [170/312]  eta: 0:02:38  lr: 0.001854  min_lr: 0.001854  loss: 2.2162 (2.2469)  weight_decay: 0.0500 (0.0500)  time: 1.0062  data: 0.0005  max mem: 78493
Epoch: [166]  [180/312]  eta: 0:02:26  lr: 0.001853  min_lr: 0.001853  loss: 2.2323 (2.2458)  weight_decay: 0.0500 (0.0500)  time: 1.0052  data: 0.0005  max mem: 78493
Epoch: [166]  [190/312]  eta: 0:02:15  lr: 0.001852  min_lr: 0.001852  loss: 2.2905 (2.2431)  weight_decay: 0.0500 (0.0500)  time: 1.0055  data: 0.0005  max mem: 78493
Epoch: [166]  [200/312]  eta: 0:02:03  lr: 0.001852  min_lr: 0.001852  loss: 2.1968 (2.2418)  weight_decay: 0.0500 (0.0500)  time: 1.0066  data: 0.0005  max mem: 78493
Epoch: [166]  [210/312]  eta: 0:01:51  lr: 0.001851  min_lr: 0.001851  loss: 2.1968 (2.2422)  weight_decay: 0.0500 (0.0500)  time: 1.0059  data: 0.0004  max mem: 78493
Epoch: [166]  [220/312]  eta: 0:01:40  lr: 0.001850  min_lr: 0.001850  loss: 2.2054 (2.2427)  weight_decay: 0.0500 (0.0500)  time: 1.0042  data: 0.0005  max mem: 78493
Epoch: [166]  [230/312]  eta: 0:01:29  lr: 0.001849  min_lr: 0.001849  loss: 2.3108 (2.2427)  weight_decay: 0.0500 (0.0500)  time: 1.0037  data: 0.0010  max mem: 78493
Epoch: [166]  [240/312]  eta: 0:01:18  lr: 0.001849  min_lr: 0.001849  loss: 2.2246 (2.2377)  weight_decay: 0.0500 (0.0500)  time: 1.0034  data: 0.0010  max mem: 78493
Epoch: [166]  [250/312]  eta: 0:01:07  lr: 0.001848  min_lr: 0.001848  loss: 2.2879 (2.2446)  weight_decay: 0.0500 (0.0500)  time: 1.0036  data: 0.0005  max mem: 78493
Epoch: [166]  [260/312]  eta: 0:00:56  lr: 0.001847  min_lr: 0.001847  loss: 2.2879 (2.2353)  weight_decay: 0.0500 (0.0500)  time: 1.0046  data: 0.0004  max mem: 78493
Epoch: [166]  [270/312]  eta: 0:00:45  lr: 0.001847  min_lr: 0.001847  loss: 2.1834 (2.2368)  weight_decay: 0.0500 (0.0500)  time: 1.0051  data: 0.0004  max mem: 78493
Epoch: [166]  [280/312]  eta: 0:00:34  lr: 0.001846  min_lr: 0.001846  loss: 2.2545 (2.2339)  weight_decay: 0.0500 (0.0500)  time: 1.0052  data: 0.0011  max mem: 78493
Epoch: [166]  [290/312]  eta: 0:00:23  lr: 0.001845  min_lr: 0.001845  loss: 2.3075 (2.2366)  weight_decay: 0.0500 (0.0500)  time: 1.0034  data: 0.0009  max mem: 78493
Epoch: [166]  [300/312]  eta: 0:00:12  lr: 0.001844  min_lr: 0.001844  loss: 2.3564 (2.2329)  weight_decay: 0.0500 (0.0500)  time: 1.0017  data: 0.0001  max mem: 78493
Epoch: [166]  [310/312]  eta: 0:00:02  lr: 0.001844  min_lr: 0.001844  loss: 2.2921 (2.2328)  weight_decay: 0.0500 (0.0500)  time: 1.0016  data: 0.0002  max mem: 78493
Epoch: [166]  [311/312]  eta: 0:00:01  lr: 0.001844  min_lr: 0.001844  loss: 2.2921 (2.2311)  weight_decay: 0.0500 (0.0500)  time: 1.0017  data: 0.0002  max mem: 78493
Epoch: [166] Total time: 0:05:34 (1.0725 s / it)
Averaged stats: lr: 0.001844  min_lr: 0.001844  loss: 2.2921 (2.2233)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:14  loss: 0.6504 (0.6504)  acc1: 83.7240 (83.7240)  acc5: 96.3542 (96.3542)  time: 8.3310  data: 8.0523  max mem: 78493
Test:  [8/9]  eta: 0:00:01  loss: 0.9254 (0.8668)  acc1: 76.3021 (77.1200)  acc5: 93.7500 (93.7280)  time: 1.1239  data: 0.8948  max mem: 78493
Test: Total time: 0:00:10 (1.1443 s / it)
* Acc@1 77.400 Acc@5 93.788 loss 0.860
Accuracy of the model on the 50000 test images: 77.4%
Max accuracy: 77.52%
Epoch: [167]  [  0/312]  eta: 1:21:56  lr: 0.001844  min_lr: 0.001844  loss: 2.2205 (2.2205)  weight_decay: 0.0500 (0.0500)  time: 15.7588  data: 13.5814  max mem: 78493
Epoch: [167]  [ 10/312]  eta: 0:13:09  lr: 0.001843  min_lr: 0.001843  loss: 2.2205 (2.2652)  weight_decay: 0.0500 (0.0500)  time: 2.6129  data: 1.2353  max mem: 78493
Epoch: [167]  [ 20/312]  eta: 0:09:00  lr: 0.001842  min_lr: 0.001842  loss: 2.2939 (2.3391)  weight_decay: 0.0500 (0.0500)  time: 1.1558  data: 0.0006  max mem: 78493
Epoch: [167]  [ 30/312]  eta: 0:07:25  lr: 0.001841  min_lr: 0.001841  loss: 2.3776 (2.3650)  weight_decay: 0.0500 (0.0500)  time: 1.0117  data: 0.0005  max mem: 78493
Epoch: [167]  [ 40/312]  eta: 0:06:31  lr: 0.001841  min_lr: 0.001841  loss: 2.3883 (2.3452)  weight_decay: 0.0500 (0.0500)  time: 1.0078  data: 0.0005  max mem: 78493
Epoch: [167]  [ 50/312]  eta: 0:05:54  lr: 0.001840  min_lr: 0.001840  loss: 2.2977 (2.3348)  weight_decay: 0.0500 (0.0500)  time: 1.0043  data: 0.0005  max mem: 78493
Epoch: [167]  [ 60/312]  eta: 0:05:26  lr: 0.001839  min_lr: 0.001839  loss: 2.3326 (2.3398)  weight_decay: 0.0500 (0.0500)  time: 1.0056  data: 0.0005  max mem: 78493
Epoch: [167]  [ 70/312]  eta: 0:05:04  lr: 0.001839  min_lr: 0.001839  loss: 2.2807 (2.3290)  weight_decay: 0.0500 (0.0500)  time: 1.0080  data: 0.0004  max mem: 78493
Epoch: [167]  [ 80/312]  eta: 0:04:44  lr: 0.001838  min_lr: 0.001838  loss: 2.1988 (2.3085)  weight_decay: 0.0500 (0.0500)  time: 1.0069  data: 0.0026  max mem: 78493
Epoch: [167]  [ 90/312]  eta: 0:04:26  lr: 0.001837  min_lr: 0.001837  loss: 2.1858 (2.2946)  weight_decay: 0.0500 (0.0500)  time: 1.0063  data: 0.0033  max mem: 78493
Epoch: [167]  [100/312]  eta: 0:04:10  lr: 0.001836  min_lr: 0.001836  loss: 2.2304 (2.2843)  weight_decay: 0.0500 (0.0500)  time: 1.0062  data: 0.0011  max mem: 78493
Epoch: [167]  [110/312]  eta: 0:03:55  lr: 0.001836  min_lr: 0.001836  loss: 2.2647 (2.2777)  weight_decay: 0.0500 (0.0500)  time: 1.0081  data: 0.0005  max mem: 78493
Epoch: [167]  [120/312]  eta: 0:03:41  lr: 0.001835  min_lr: 0.001835  loss: 2.3645 (2.2845)  weight_decay: 0.0500 (0.0500)  time: 1.0097  data: 0.0004  max mem: 78493
Epoch: [167]  [130/312]  eta: 0:03:27  lr: 0.001834  min_lr: 0.001834  loss: 2.3812 (2.2899)  weight_decay: 0.0500 (0.0500)  time: 1.0078  data: 0.0012  max mem: 78493
Epoch: [167]  [140/312]  eta: 0:03:14  lr: 0.001834  min_lr: 0.001834  loss: 2.4438 (2.2926)  weight_decay: 0.0500 (0.0500)  time: 1.0069  data: 0.0012  max mem: 78493
Epoch: [167]  [150/312]  eta: 0:03:02  lr: 0.001833  min_lr: 0.001833  loss: 2.4366 (2.2960)  weight_decay: 0.0500 (0.0500)  time: 1.0073  data: 0.0004  max mem: 78493
Epoch: [167]  [160/312]  eta: 0:02:49  lr: 0.001832  min_lr: 0.001832  loss: 2.2770 (2.2796)  weight_decay: 0.0500 (0.0500)  time: 1.0080  data: 0.0004  max mem: 78493
Epoch: [167]  [170/312]  eta: 0:02:37  lr: 0.001831  min_lr: 0.001831  loss: 2.1330 (2.2726)  weight_decay: 0.0500 (0.0500)  time: 1.0090  data: 0.0005  max mem: 78493
Epoch: [167]  [180/312]  eta: 0:02:25  lr: 0.001831  min_lr: 0.001831  loss: 2.1330 (2.2684)  weight_decay: 0.0500 (0.0500)  time: 1.0093  data: 0.0004  max mem: 78493
Epoch: [167]  [190/312]  eta: 0:02:14  lr: 0.001830  min_lr: 0.001830  loss: 2.2327 (2.2629)  weight_decay: 0.0500 (0.0500)  time: 1.0092  data: 0.0004  max mem: 78493
Epoch: [167]  [200/312]  eta: 0:02:02  lr: 0.001829  min_lr: 0.001829  loss: 2.2612 (2.2641)  weight_decay: 0.0500 (0.0500)  time: 1.0076  data: 0.0004  max mem: 78493
Epoch: [167]  [210/312]  eta: 0:01:51  lr: 0.001829  min_lr: 0.001829  loss: 2.3842 (2.2641)  weight_decay: 0.0500 (0.0500)  time: 1.0052  data: 0.0004  max mem: 78493
Epoch: [167]  [220/312]  eta: 0:01:40  lr: 0.001828  min_lr: 0.001828  loss: 2.2707 (2.2622)  weight_decay: 0.0500 (0.0500)  time: 1.0046  data: 0.0004  max mem: 78493
Epoch: [167]  [230/312]  eta: 0:01:28  lr: 0.001827  min_lr: 0.001827  loss: 2.3172 (2.2658)  weight_decay: 0.0500 (0.0500)  time: 1.0046  data: 0.0004  max mem: 78493
Epoch: [167]  [240/312]  eta: 0:01:17  lr: 0.001826  min_lr: 0.001826  loss: 2.2899 (2.2577)  weight_decay: 0.0500 (0.0500)  time: 1.0043  data: 0.0004  max mem: 78493
Epoch: [167]  [250/312]  eta: 0:01:06  lr: 0.001826  min_lr: 0.001826  loss: 1.8782 (2.2478)  weight_decay: 0.0500 (0.0500)  time: 1.0060  data: 0.0004  max mem: 78493
Epoch: [167]  [260/312]  eta: 0:00:55  lr: 0.001825  min_lr: 0.001825  loss: 2.2394 (2.2505)  weight_decay: 0.0500 (0.0500)  time: 1.0056  data: 0.0004  max mem: 78493
Epoch: [167]  [270/312]  eta: 0:00:45  lr: 0.001824  min_lr: 0.001824  loss: 2.3359 (2.2527)  weight_decay: 0.0500 (0.0500)  time: 1.0043  data: 0.0004  max mem: 78493
Epoch: [167]  [280/312]  eta: 0:00:34  lr: 0.001824  min_lr: 0.001824  loss: 2.2980 (2.2566)  weight_decay: 0.0500 (0.0500)  time: 1.0057  data: 0.0010  max mem: 78493
Epoch: [167]  [290/312]  eta: 0:00:23  lr: 0.001823  min_lr: 0.001823  loss: 2.3756 (2.2608)  weight_decay: 0.0500 (0.0500)  time: 1.0039  data: 0.0009  max mem: 78493
Epoch: [167]  [300/312]  eta: 0:00:12  lr: 0.001822  min_lr: 0.001822  loss: 2.4159 (2.2577)  weight_decay: 0.0500 (0.0500)  time: 1.0016  data: 0.0001  max mem: 78493
Epoch: [167]  [310/312]  eta: 0:00:02  lr: 0.001821  min_lr: 0.001821  loss: 2.4419 (2.2628)  weight_decay: 0.0500 (0.0500)  time: 1.0017  data: 0.0001  max mem: 78493
Epoch: [167]  [311/312]  eta: 0:00:01  lr: 0.001821  min_lr: 0.001821  loss: 2.4419 (2.2629)  weight_decay: 0.0500 (0.0500)  time: 1.0017  data: 0.0001  max mem: 78493
Epoch: [167] Total time: 0:05:33 (1.0690 s / it)
Averaged stats: lr: 0.001821  min_lr: 0.001821  loss: 2.4419 (2.2346)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:16  loss: 0.6793 (0.6793)  acc1: 83.7240 (83.7240)  acc5: 95.9635 (95.9635)  time: 8.5163  data: 8.2476  max mem: 78493
Test:  [8/9]  eta: 0:00:01  loss: 0.9874 (0.8998)  acc1: 76.4323 (77.3920)  acc5: 94.0104 (93.5200)  time: 1.1451  data: 0.9165  max mem: 78493
Test: Total time: 0:00:10 (1.1719 s / it)
* Acc@1 77.484 Acc@5 93.582 loss 0.892
Accuracy of the model on the 50000 test images: 77.5%
Max accuracy: 77.52%
Epoch: [168]  [  0/312]  eta: 1:26:49  lr: 0.001821  min_lr: 0.001821  loss: 2.2182 (2.2182)  weight_decay: 0.0500 (0.0500)  time: 16.6969  data: 12.7578  max mem: 78493
Epoch: [168]  [ 10/312]  eta: 0:13:27  lr: 0.001821  min_lr: 0.001821  loss: 2.2340 (2.2013)  weight_decay: 0.0500 (0.0500)  time: 2.6755  data: 1.2944  max mem: 78493
Epoch: [168]  [ 20/312]  eta: 0:09:10  lr: 0.001820  min_lr: 0.001820  loss: 2.2308 (2.1683)  weight_decay: 0.0500 (0.0500)  time: 1.1450  data: 0.0757  max mem: 78493
Epoch: [168]  [ 30/312]  eta: 0:07:32  lr: 0.001819  min_lr: 0.001819  loss: 2.2365 (2.2038)  weight_decay: 0.0500 (0.0500)  time: 1.0132  data: 0.0018  max mem: 78493
Epoch: [168]  [ 40/312]  eta: 0:06:36  lr: 0.001818  min_lr: 0.001818  loss: 2.2475 (2.2036)  weight_decay: 0.0500 (0.0500)  time: 1.0082  data: 0.0005  max mem: 78493
Epoch: [168]  [ 50/312]  eta: 0:05:58  lr: 0.001818  min_lr: 0.001818  loss: 2.3046 (2.2355)  weight_decay: 0.0500 (0.0500)  time: 1.0074  data: 0.0005  max mem: 78493
Epoch: [168]  [ 60/312]  eta: 0:05:30  lr: 0.001817  min_lr: 0.001817  loss: 2.3451 (2.2400)  weight_decay: 0.0500 (0.0500)  time: 1.0078  data: 0.0004  max mem: 78493
Epoch: [168]  [ 70/312]  eta: 0:05:06  lr: 0.001816  min_lr: 0.001816  loss: 2.2801 (2.2120)  weight_decay: 0.0500 (0.0500)  time: 1.0080  data: 0.0004  max mem: 78493
Epoch: [168]  [ 80/312]  eta: 0:04:46  lr: 0.001816  min_lr: 0.001816  loss: 2.0660 (2.2179)  weight_decay: 0.0500 (0.0500)  time: 1.0085  data: 0.0004  max mem: 78493
Epoch: [168]  [ 90/312]  eta: 0:04:28  lr: 0.001815  min_lr: 0.001815  loss: 2.0338 (2.1985)  weight_decay: 0.0500 (0.0500)  time: 1.0084  data: 0.0004  max mem: 78493
Epoch: [168]  [100/312]  eta: 0:04:12  lr: 0.001814  min_lr: 0.001814  loss: 2.1469 (2.2034)  weight_decay: 0.0500 (0.0500)  time: 1.0071  data: 0.0004  max mem: 78493
Epoch: [168]  [110/312]  eta: 0:03:57  lr: 0.001813  min_lr: 0.001813  loss: 2.3263 (2.2031)  weight_decay: 0.0500 (0.0500)  time: 1.0070  data: 0.0004  max mem: 78493
Epoch: [168]  [120/312]  eta: 0:03:42  lr: 0.001813  min_lr: 0.001813  loss: 2.3128 (2.2082)  weight_decay: 0.0500 (0.0500)  time: 1.0070  data: 0.0004  max mem: 78493
Epoch: [168]  [130/312]  eta: 0:03:28  lr: 0.001812  min_lr: 0.001812  loss: 2.3461 (2.2207)  weight_decay: 0.0500 (0.0500)  time: 1.0058  data: 0.0005  max mem: 78493
Epoch: [168]  [140/312]  eta: 0:03:15  lr: 0.001811  min_lr: 0.001811  loss: 2.3533 (2.2302)  weight_decay: 0.0500 (0.0500)  time: 1.0055  data: 0.0005  max mem: 78493
Epoch: [168]  [150/312]  eta: 0:03:02  lr: 0.001811  min_lr: 0.001811  loss: 2.3511 (2.2316)  weight_decay: 0.0500 (0.0500)  time: 1.0057  data: 0.0005  max mem: 78493
Epoch: [168]  [160/312]  eta: 0:02:50  lr: 0.001810  min_lr: 0.001810  loss: 2.3443 (2.2408)  weight_decay: 0.0500 (0.0500)  time: 1.0091  data: 0.0004  max mem: 78493
Epoch: [168]  [170/312]  eta: 0:02:38  lr: 0.001809  min_lr: 0.001809  loss: 2.3302 (2.2478)  weight_decay: 0.0500 (0.0500)  time: 1.0101  data: 0.0005  max mem: 78493
Epoch: [168]  [180/312]  eta: 0:02:26  lr: 0.001808  min_lr: 0.001808  loss: 2.2780 (2.2407)  weight_decay: 0.0500 (0.0500)  time: 1.0085  data: 0.0005  max mem: 78493
Epoch: [168]  [190/312]  eta: 0:02:14  lr: 0.001808  min_lr: 0.001808  loss: 2.2607 (2.2397)  weight_decay: 0.0500 (0.0500)  time: 1.0086  data: 0.0004  max mem: 78493
Epoch: [168]  [200/312]  eta: 0:02:03  lr: 0.001807  min_lr: 0.001807  loss: 2.2607 (2.2438)  weight_decay: 0.0500 (0.0500)  time: 1.0078  data: 0.0004  max mem: 78493
Epoch: [168]  [210/312]  eta: 0:01:51  lr: 0.001806  min_lr: 0.001806  loss: 2.2170 (2.2368)  weight_decay: 0.0500 (0.0500)  time: 1.0058  data: 0.0011  max mem: 78493
Epoch: [168]  [220/312]  eta: 0:01:40  lr: 0.001806  min_lr: 0.001806  loss: 2.1652 (2.2374)  weight_decay: 0.0500 (0.0500)  time: 1.0056  data: 0.0011  max mem: 78493
Epoch: [168]  [230/312]  eta: 0:01:29  lr: 0.001805  min_lr: 0.001805  loss: 2.1569 (2.2329)  weight_decay: 0.0500 (0.0500)  time: 1.0062  data: 0.0004  max mem: 78493
Epoch: [168]  [240/312]  eta: 0:01:18  lr: 0.001804  min_lr: 0.001804  loss: 2.0298 (2.2257)  weight_decay: 0.0500 (0.0500)  time: 1.0068  data: 0.0004  max mem: 78493
Epoch: [168]  [250/312]  eta: 0:01:07  lr: 0.001803  min_lr: 0.001803  loss: 1.9074 (2.2167)  weight_decay: 0.0500 (0.0500)  time: 1.0067  data: 0.0004  max mem: 78493
Epoch: [168]  [260/312]  eta: 0:00:56  lr: 0.001803  min_lr: 0.001803  loss: 2.0173 (2.2090)  weight_decay: 0.0500 (0.0500)  time: 1.0051  data: 0.0004  max mem: 78493
Epoch: [168]  [270/312]  eta: 0:00:45  lr: 0.001802  min_lr: 0.001802  loss: 2.1599 (2.2074)  weight_decay: 0.0500 (0.0500)  time: 1.0062  data: 0.0004  max mem: 78493
Epoch: [168]  [280/312]  eta: 0:00:34  lr: 0.001801  min_lr: 0.001801  loss: 2.3426 (2.2153)  weight_decay: 0.0500 (0.0500)  time: 1.0076  data: 0.0010  max mem: 78493
Epoch: [168]  [290/312]  eta: 0:00:23  lr: 0.001801  min_lr: 0.001801  loss: 2.3426 (2.2143)  weight_decay: 0.0500 (0.0500)  time: 1.0053  data: 0.0009  max mem: 78493
Epoch: [168]  [300/312]  eta: 0:00:12  lr: 0.001800  min_lr: 0.001800  loss: 2.2928 (2.2168)  weight_decay: 0.0500 (0.0500)  time: 1.0023  data: 0.0001  max mem: 78493
Epoch: [168]  [310/312]  eta: 0:00:02  lr: 0.001799  min_lr: 0.001799  loss: 2.2928 (2.2182)  weight_decay: 0.0500 (0.0500)  time: 1.0018  data: 0.0001  max mem: 78493
Epoch: [168]  [311/312]  eta: 0:00:01  lr: 0.001799  min_lr: 0.001799  loss: 2.2928 (2.2184)  weight_decay: 0.0500 (0.0500)  time: 1.0018  data: 0.0001  max mem: 78493
Epoch: [168] Total time: 0:05:34 (1.0717 s / it)
Averaged stats: lr: 0.001799  min_lr: 0.001799  loss: 2.2928 (2.2053)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:12  loss: 0.6512 (0.6512)  acc1: 84.8958 (84.8958)  acc5: 95.9635 (95.9635)  time: 8.0798  data: 7.7966  max mem: 78493
Test:  [8/9]  eta: 0:00:01  loss: 0.9913 (0.8941)  acc1: 76.1719 (77.0080)  acc5: 94.5312 (93.6800)  time: 1.0959  data: 0.8664  max mem: 78493
Test: Total time: 0:00:10 (1.1367 s / it)
* Acc@1 77.460 Acc@5 93.864 loss 0.868
Accuracy of the model on the 50000 test images: 77.5%
Max accuracy: 77.52%
Epoch: [169]  [  0/312]  eta: 1:22:53  lr: 0.001799  min_lr: 0.001799  loss: 2.3267 (2.3267)  weight_decay: 0.0500 (0.0500)  time: 15.9414  data: 14.9393  max mem: 78493
Epoch: [169]  [ 10/312]  eta: 0:13:11  lr: 0.001798  min_lr: 0.001798  loss: 2.3267 (2.1302)  weight_decay: 0.0500 (0.0500)  time: 2.6225  data: 1.3588  max mem: 78493
Epoch: [169]  [ 20/312]  eta: 0:09:03  lr: 0.001798  min_lr: 0.001798  loss: 2.3182 (2.1550)  weight_decay: 0.0500 (0.0500)  time: 1.1586  data: 0.0006  max mem: 78493
Epoch: [169]  [ 30/312]  eta: 0:07:27  lr: 0.001797  min_lr: 0.001797  loss: 2.3285 (2.2327)  weight_decay: 0.0500 (0.0500)  time: 1.0173  data: 0.0005  max mem: 78493
Epoch: [169]  [ 40/312]  eta: 0:06:33  lr: 0.001796  min_lr: 0.001796  loss: 2.2308 (2.2205)  weight_decay: 0.0500 (0.0500)  time: 1.0094  data: 0.0004  max mem: 78493
Epoch: [169]  [ 50/312]  eta: 0:05:56  lr: 0.001795  min_lr: 0.001795  loss: 2.0688 (2.1630)  weight_decay: 0.0500 (0.0500)  time: 1.0087  data: 0.0004  max mem: 78493
Epoch: [169]  [ 60/312]  eta: 0:05:28  lr: 0.001795  min_lr: 0.001795  loss: 1.9039 (2.1545)  weight_decay: 0.0500 (0.0500)  time: 1.0059  data: 0.0005  max mem: 78493
Epoch: [169]  [ 70/312]  eta: 0:05:04  lr: 0.001794  min_lr: 0.001794  loss: 2.2169 (2.1778)  weight_decay: 0.0500 (0.0500)  time: 1.0043  data: 0.0005  max mem: 78493
Epoch: [169]  [ 80/312]  eta: 0:04:45  lr: 0.001793  min_lr: 0.001793  loss: 2.2169 (2.1749)  weight_decay: 0.0500 (0.0500)  time: 1.0062  data: 0.0004  max mem: 78493
Epoch: [169]  [ 90/312]  eta: 0:04:27  lr: 0.001792  min_lr: 0.001792  loss: 2.1157 (2.1593)  weight_decay: 0.0500 (0.0500)  time: 1.0091  data: 0.0004  max mem: 78493
Epoch: [169]  [100/312]  eta: 0:04:11  lr: 0.001792  min_lr: 0.001792  loss: 2.0324 (2.1643)  weight_decay: 0.0500 (0.0500)  time: 1.0096  data: 0.0005  max mem: 78493
Epoch: [169]  [110/312]  eta: 0:03:56  lr: 0.001791  min_lr: 0.001791  loss: 2.1505 (2.1653)  weight_decay: 0.0500 (0.0500)  time: 1.0088  data: 0.0005  max mem: 78493
Epoch: [169]  [120/312]  eta: 0:03:42  lr: 0.001790  min_lr: 0.001790  loss: 2.1505 (2.1543)  weight_decay: 0.0500 (0.0500)  time: 1.0092  data: 0.0004  max mem: 78493
Epoch: [169]  [130/312]  eta: 0:03:28  lr: 0.001790  min_lr: 0.001790  loss: 2.2703 (2.1715)  weight_decay: 0.0500 (0.0500)  time: 1.0101  data: 0.0004  max mem: 78493
Epoch: [169]  [140/312]  eta: 0:03:15  lr: 0.001789  min_lr: 0.001789  loss: 2.3225 (2.1761)  weight_decay: 0.0500 (0.0500)  time: 1.0088  data: 0.0004  max mem: 78493
Epoch: [169]  [150/312]  eta: 0:03:02  lr: 0.001788  min_lr: 0.001788  loss: 2.3225 (2.1798)  weight_decay: 0.0500 (0.0500)  time: 1.0094  data: 0.0013  max mem: 78493
Epoch: [169]  [160/312]  eta: 0:02:50  lr: 0.001787  min_lr: 0.001787  loss: 2.3457 (2.1859)  weight_decay: 0.0500 (0.0500)  time: 1.0084  data: 0.0013  max mem: 78493
Epoch: [169]  [170/312]  eta: 0:02:38  lr: 0.001787  min_lr: 0.001787  loss: 2.1162 (2.1749)  weight_decay: 0.0500 (0.0500)  time: 1.0061  data: 0.0005  max mem: 78493
Epoch: [169]  [180/312]  eta: 0:02:26  lr: 0.001786  min_lr: 0.001786  loss: 2.0370 (2.1628)  weight_decay: 0.0500 (0.0500)  time: 1.0069  data: 0.0005  max mem: 78493
Epoch: [169]  [190/312]  eta: 0:02:14  lr: 0.001785  min_lr: 0.001785  loss: 2.0664 (2.1666)  weight_decay: 0.0500 (0.0500)  time: 1.0072  data: 0.0004  max mem: 78493
Epoch: [169]  [200/312]  eta: 0:02:02  lr: 0.001785  min_lr: 0.001785  loss: 2.3420 (2.1746)  weight_decay: 0.0500 (0.0500)  time: 1.0058  data: 0.0004  max mem: 78493
Epoch: [169]  [210/312]  eta: 0:01:51  lr: 0.001784  min_lr: 0.001784  loss: 2.2946 (2.1788)  weight_decay: 0.0500 (0.0500)  time: 1.0056  data: 0.0005  max mem: 78493
Epoch: [169]  [220/312]  eta: 0:01:40  lr: 0.001783  min_lr: 0.001783  loss: 2.2917 (2.1829)  weight_decay: 0.0500 (0.0500)  time: 1.0062  data: 0.0005  max mem: 78493
Epoch: [169]  [230/312]  eta: 0:01:29  lr: 0.001782  min_lr: 0.001782  loss: 2.2059 (2.1783)  weight_decay: 0.0500 (0.0500)  time: 1.0088  data: 0.0004  max mem: 78493
Epoch: [169]  [240/312]  eta: 0:01:17  lr: 0.001782  min_lr: 0.001782  loss: 2.1338 (2.1769)  weight_decay: 0.0500 (0.0500)  time: 1.0085  data: 0.0005  max mem: 78493
Epoch: [169]  [250/312]  eta: 0:01:06  lr: 0.001781  min_lr: 0.001781  loss: 2.2487 (2.1783)  weight_decay: 0.0500 (0.0500)  time: 1.0078  data: 0.0005  max mem: 78493
Epoch: [169]  [260/312]  eta: 0:00:55  lr: 0.001780  min_lr: 0.001780  loss: 2.3188 (2.1808)  weight_decay: 0.0500 (0.0500)  time: 1.0095  data: 0.0004  max mem: 78493
Epoch: [169]  [270/312]  eta: 0:00:45  lr: 0.001780  min_lr: 0.001780  loss: 2.3188 (2.1830)  weight_decay: 0.0500 (0.0500)  time: 1.0087  data: 0.0005  max mem: 78493
Epoch: [169]  [280/312]  eta: 0:00:34  lr: 0.001779  min_lr: 0.001779  loss: 2.2128 (2.1855)  weight_decay: 0.0500 (0.0500)  time: 1.0084  data: 0.0011  max mem: 78493
Epoch: [169]  [290/312]  eta: 0:00:23  lr: 0.001778  min_lr: 0.001778  loss: 2.3068 (2.1872)  weight_decay: 0.0500 (0.0500)  time: 1.0050  data: 0.0009  max mem: 78493
Epoch: [169]  [300/312]  eta: 0:00:12  lr: 0.001777  min_lr: 0.001777  loss: 2.3045 (2.1902)  weight_decay: 0.0500 (0.0500)  time: 1.0018  data: 0.0001  max mem: 78493
Epoch: [169]  [310/312]  eta: 0:00:02  lr: 0.001777  min_lr: 0.001777  loss: 2.3045 (2.1956)  weight_decay: 0.0500 (0.0500)  time: 1.0017  data: 0.0001  max mem: 78493
Epoch: [169]  [311/312]  eta: 0:00:01  lr: 0.001777  min_lr: 0.001777  loss: 2.3052 (2.1967)  weight_decay: 0.0500 (0.0500)  time: 1.0016  data: 0.0001  max mem: 78493
Epoch: [169] Total time: 0:05:33 (1.0703 s / it)
Averaged stats: lr: 0.001777  min_lr: 0.001777  loss: 2.3052 (2.2078)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:11  loss: 0.6530 (0.6530)  acc1: 83.8542 (83.8542)  acc5: 96.4844 (96.4844)  time: 7.9259  data: 7.6454  max mem: 78493
Test:  [8/9]  eta: 0:00:01  loss: 0.9880 (0.8720)  acc1: 77.2135 (77.4240)  acc5: 94.4010 (93.8400)  time: 1.0790  data: 0.8496  max mem: 78493
Test: Total time: 0:00:10 (1.1156 s / it)
* Acc@1 77.592 Acc@5 93.782 loss 0.873
Accuracy of the model on the 50000 test images: 77.6%
Max accuracy: 77.59%
Epoch: [170]  [  0/312]  eta: 1:16:51  lr: 0.001777  min_lr: 0.001777  loss: 1.4877 (1.4877)  weight_decay: 0.0500 (0.0500)  time: 14.7801  data: 13.7518  max mem: 78493
Epoch: [170]  [ 10/312]  eta: 0:13:24  lr: 0.001776  min_lr: 0.001776  loss: 2.2505 (2.1452)  weight_decay: 0.0500 (0.0500)  time: 2.6629  data: 1.3057  max mem: 78493
Epoch: [170]  [ 20/312]  eta: 0:09:09  lr: 0.001775  min_lr: 0.001775  loss: 2.4147 (2.2081)  weight_decay: 0.0500 (0.0500)  time: 1.2359  data: 0.0308  max mem: 78493
Epoch: [170]  [ 30/312]  eta: 0:07:30  lr: 0.001774  min_lr: 0.001774  loss: 2.2642 (2.1748)  weight_decay: 0.0500 (0.0500)  time: 1.0134  data: 0.0005  max mem: 78493
Epoch: [170]  [ 40/312]  eta: 0:06:35  lr: 0.001774  min_lr: 0.001774  loss: 2.2539 (2.1863)  weight_decay: 0.0500 (0.0500)  time: 1.0088  data: 0.0004  max mem: 78493
Epoch: [170]  [ 50/312]  eta: 0:05:58  lr: 0.001773  min_lr: 0.001773  loss: 2.2539 (2.1748)  weight_decay: 0.0500 (0.0500)  time: 1.0088  data: 0.0004  max mem: 78493
Epoch: [170]  [ 60/312]  eta: 0:05:29  lr: 0.001772  min_lr: 0.001772  loss: 2.2429 (2.1837)  weight_decay: 0.0500 (0.0500)  time: 1.0068  data: 0.0004  max mem: 78493
Epoch: [170]  [ 70/312]  eta: 0:05:06  lr: 0.001772  min_lr: 0.001772  loss: 2.2429 (2.1784)  weight_decay: 0.0500 (0.0500)  time: 1.0070  data: 0.0004  max mem: 78493
Epoch: [170]  [ 80/312]  eta: 0:04:46  lr: 0.001771  min_lr: 0.001771  loss: 2.3435 (2.2032)  weight_decay: 0.0500 (0.0500)  time: 1.0073  data: 0.0004  max mem: 78493
Epoch: [170]  [ 90/312]  eta: 0:04:28  lr: 0.001770  min_lr: 0.001770  loss: 2.3030 (2.1913)  weight_decay: 0.0500 (0.0500)  time: 1.0082  data: 0.0004  max mem: 78493
Epoch: [170]  [100/312]  eta: 0:04:12  lr: 0.001769  min_lr: 0.001769  loss: 2.2118 (2.1961)  weight_decay: 0.0500 (0.0500)  time: 1.0086  data: 0.0005  max mem: 78493
Epoch: [170]  [110/312]  eta: 0:03:56  lr: 0.001769  min_lr: 0.001769  loss: 2.2118 (2.1981)  weight_decay: 0.0500 (0.0500)  time: 1.0074  data: 0.0005  max mem: 78493
Epoch: [170]  [120/312]  eta: 0:03:42  lr: 0.001768  min_lr: 0.001768  loss: 2.3384 (2.2144)  weight_decay: 0.0500 (0.0500)  time: 1.0086  data: 0.0014  max mem: 78493
Epoch: [170]  [130/312]  eta: 0:03:28  lr: 0.001767  min_lr: 0.001767  loss: 2.3505 (2.2078)  weight_decay: 0.0500 (0.0500)  time: 1.0094  data: 0.0015  max mem: 78493
Epoch: [170]  [140/312]  eta: 0:03:15  lr: 0.001767  min_lr: 0.001767  loss: 2.0887 (2.1959)  weight_decay: 0.0500 (0.0500)  time: 1.0077  data: 0.0005  max mem: 78493
Epoch: [170]  [150/312]  eta: 0:03:02  lr: 0.001766  min_lr: 0.001766  loss: 2.2476 (2.1998)  weight_decay: 0.0500 (0.0500)  time: 1.0079  data: 0.0005  max mem: 78493
Epoch: [170]  [160/312]  eta: 0:02:50  lr: 0.001765  min_lr: 0.001765  loss: 2.2476 (2.1924)  weight_decay: 0.0500 (0.0500)  time: 1.0089  data: 0.0005  max mem: 78493
Epoch: [170]  [170/312]  eta: 0:02:38  lr: 0.001764  min_lr: 0.001764  loss: 2.0309 (2.1839)  weight_decay: 0.0500 (0.0500)  time: 1.0096  data: 0.0005  max mem: 78493
Epoch: [170]  [180/312]  eta: 0:02:26  lr: 0.001764  min_lr: 0.001764  loss: 2.1914 (2.1851)  weight_decay: 0.0500 (0.0500)  time: 1.0066  data: 0.0005  max mem: 78493
Epoch: [170]  [190/312]  eta: 0:02:14  lr: 0.001763  min_lr: 0.001763  loss: 2.3418 (2.1890)  weight_decay: 0.0500 (0.0500)  time: 1.0067  data: 0.0005  max mem: 78493
Epoch: [170]  [200/312]  eta: 0:02:03  lr: 0.001762  min_lr: 0.001762  loss: 2.2630 (2.1825)  weight_decay: 0.0500 (0.0500)  time: 1.0087  data: 0.0005  max mem: 78493
Epoch: [170]  [210/312]  eta: 0:01:51  lr: 0.001762  min_lr: 0.001762  loss: 2.1175 (2.1819)  weight_decay: 0.0500 (0.0500)  time: 1.0083  data: 0.0005  max mem: 78493
Epoch: [170]  [220/312]  eta: 0:01:40  lr: 0.001761  min_lr: 0.001761  loss: 2.3080 (2.1822)  weight_decay: 0.0500 (0.0500)  time: 1.0076  data: 0.0004  max mem: 78493
Epoch: [170]  [230/312]  eta: 0:01:29  lr: 0.001760  min_lr: 0.001760  loss: 2.1250 (2.1773)  weight_decay: 0.0500 (0.0500)  time: 1.0072  data: 0.0004  max mem: 78493
Epoch: [170]  [240/312]  eta: 0:01:18  lr: 0.001759  min_lr: 0.001759  loss: 2.3107 (2.1852)  weight_decay: 0.0500 (0.0500)  time: 1.0066  data: 0.0005  max mem: 78493
Epoch: [170]  [250/312]  eta: 0:01:07  lr: 0.001759  min_lr: 0.001759  loss: 2.3523 (2.1837)  weight_decay: 0.0500 (0.0500)  time: 1.0063  data: 0.0004  max mem: 78493
Epoch: [170]  [260/312]  eta: 0:00:56  lr: 0.001758  min_lr: 0.001758  loss: 2.2408 (2.1846)  weight_decay: 0.0500 (0.0500)  time: 1.0070  data: 0.0004  max mem: 78493
Epoch: [170]  [270/312]  eta: 0:00:45  lr: 0.001757  min_lr: 0.001757  loss: 2.2522 (2.1846)  weight_decay: 0.0500 (0.0500)  time: 1.0051  data: 0.0005  max mem: 78493
Epoch: [170]  [280/312]  eta: 0:00:34  lr: 0.001757  min_lr: 0.001757  loss: 2.2857 (2.1812)  weight_decay: 0.0500 (0.0500)  time: 1.0073  data: 0.0011  max mem: 78493
Epoch: [170]  [290/312]  eta: 0:00:23  lr: 0.001756  min_lr: 0.001756  loss: 2.3350 (2.1827)  weight_decay: 0.0500 (0.0500)  time: 1.0068  data: 0.0009  max mem: 78493
Epoch: [170]  [300/312]  eta: 0:00:12  lr: 0.001755  min_lr: 0.001755  loss: 2.3350 (2.1854)  weight_decay: 0.0500 (0.0500)  time: 1.0021  data: 0.0001  max mem: 78493
Epoch: [170]  [310/312]  eta: 0:00:02  lr: 0.001754  min_lr: 0.001754  loss: 2.1374 (2.1833)  weight_decay: 0.0500 (0.0500)  time: 1.0016  data: 0.0001  max mem: 78493
Epoch: [170]  [311/312]  eta: 0:00:01  lr: 0.001754  min_lr: 0.001754  loss: 2.1374 (2.1814)  weight_decay: 0.0500 (0.0500)  time: 1.0015  data: 0.0001  max mem: 78493
Epoch: [170] Total time: 0:05:34 (1.0719 s / it)
Averaged stats: lr: 0.001754  min_lr: 0.001754  loss: 2.1374 (2.2107)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:15  loss: 0.6108 (0.6108)  acc1: 84.8958 (84.8958)  acc5: 96.6146 (96.6146)  time: 8.3960  data: 8.1211  max mem: 78493
Test:  [8/9]  eta: 0:00:01  loss: 0.9602 (0.8662)  acc1: 77.0833 (77.4080)  acc5: 93.3594 (93.6480)  time: 1.1311  data: 0.9024  max mem: 78493
Test: Total time: 0:00:10 (1.1731 s / it)
* Acc@1 77.516 Acc@5 93.678 loss 0.868
Accuracy of the model on the 50000 test images: 77.5%
Max accuracy: 77.59%
Epoch: [171]  [  0/312]  eta: 1:25:27  lr: 0.001754  min_lr: 0.001754  loss: 2.3941 (2.3941)  weight_decay: 0.0500 (0.0500)  time: 16.4353  data: 10.5684  max mem: 78493
Epoch: [171]  [ 10/312]  eta: 0:13:19  lr: 0.001754  min_lr: 0.001754  loss: 2.3941 (2.3293)  weight_decay: 0.0500 (0.0500)  time: 2.6483  data: 1.0541  max mem: 78493
Epoch: [171]  [ 20/312]  eta: 0:09:06  lr: 0.001753  min_lr: 0.001753  loss: 2.3528 (2.2866)  weight_decay: 0.0500 (0.0500)  time: 1.1448  data: 0.0526  max mem: 78493
Epoch: [171]  [ 30/312]  eta: 0:07:29  lr: 0.001752  min_lr: 0.001752  loss: 2.0953 (2.1769)  weight_decay: 0.0500 (0.0500)  time: 1.0146  data: 0.0015  max mem: 78493
Epoch: [171]  [ 40/312]  eta: 0:06:34  lr: 0.001751  min_lr: 0.001751  loss: 2.0070 (2.1507)  weight_decay: 0.0500 (0.0500)  time: 1.0087  data: 0.0004  max mem: 78493
Epoch: [171]  [ 50/312]  eta: 0:05:57  lr: 0.001751  min_lr: 0.001751  loss: 2.0679 (2.1517)  weight_decay: 0.0500 (0.0500)  time: 1.0088  data: 0.0005  max mem: 78493
Epoch: [171]  [ 60/312]  eta: 0:05:29  lr: 0.001750  min_lr: 0.001750  loss: 2.2744 (2.1656)  weight_decay: 0.0500 (0.0500)  time: 1.0105  data: 0.0005  max mem: 78493
Epoch: [171]  [ 70/312]  eta: 0:05:06  lr: 0.001749  min_lr: 0.001749  loss: 2.2829 (2.1709)  weight_decay: 0.0500 (0.0500)  time: 1.0125  data: 0.0005  max mem: 78493
Epoch: [171]  [ 80/312]  eta: 0:04:46  lr: 0.001749  min_lr: 0.001749  loss: 2.1406 (2.1669)  weight_decay: 0.0500 (0.0500)  time: 1.0129  data: 0.0004  max mem: 78493
Epoch: [171]  [ 90/312]  eta: 0:04:28  lr: 0.001748  min_lr: 0.001748  loss: 2.1767 (2.1679)  weight_decay: 0.0500 (0.0500)  time: 1.0084  data: 0.0005  max mem: 78493
Epoch: [171]  [100/312]  eta: 0:04:12  lr: 0.001747  min_lr: 0.001747  loss: 2.3348 (2.1761)  weight_decay: 0.0500 (0.0500)  time: 1.0060  data: 0.0004  max mem: 78493
Epoch: [171]  [110/312]  eta: 0:03:56  lr: 0.001747  min_lr: 0.001747  loss: 1.9834 (2.1597)  weight_decay: 0.0500 (0.0500)  time: 1.0074  data: 0.0004  max mem: 78493
Epoch: [171]  [120/312]  eta: 0:03:42  lr: 0.001746  min_lr: 0.001746  loss: 2.0846 (2.1668)  weight_decay: 0.0500 (0.0500)  time: 1.0089  data: 0.0004  max mem: 78493
Epoch: [171]  [130/312]  eta: 0:03:28  lr: 0.001745  min_lr: 0.001745  loss: 2.1197 (2.1574)  weight_decay: 0.0500 (0.0500)  time: 1.0092  data: 0.0004  max mem: 78493
Epoch: [171]  [140/312]  eta: 0:03:15  lr: 0.001744  min_lr: 0.001744  loss: 2.1462 (2.1729)  weight_decay: 0.0500 (0.0500)  time: 1.0063  data: 0.0004  max mem: 78493
Epoch: [171]  [150/312]  eta: 0:03:02  lr: 0.001744  min_lr: 0.001744  loss: 2.4289 (2.1775)  weight_decay: 0.0500 (0.0500)  time: 1.0073  data: 0.0004  max mem: 78493
Epoch: [171]  [160/312]  eta: 0:02:50  lr: 0.001743  min_lr: 0.001743  loss: 2.2761 (2.1810)  weight_decay: 0.0500 (0.0500)  time: 1.0108  data: 0.0004  max mem: 78493
Epoch: [171]  [170/312]  eta: 0:02:38  lr: 0.001742  min_lr: 0.001742  loss: 2.2841 (2.1857)  weight_decay: 0.0500 (0.0500)  time: 1.0108  data: 0.0004  max mem: 78493
Epoch: [171]  [180/312]  eta: 0:02:26  lr: 0.001742  min_lr: 0.001742  loss: 2.3382 (2.1950)  weight_decay: 0.0500 (0.0500)  time: 1.0097  data: 0.0004  max mem: 78493
Epoch: [171]  [190/312]  eta: 0:02:14  lr: 0.001741  min_lr: 0.001741  loss: 2.2921 (2.1900)  weight_decay: 0.0500 (0.0500)  time: 1.0099  data: 0.0004  max mem: 78493
Epoch: [171]  [200/312]  eta: 0:02:03  lr: 0.001740  min_lr: 0.001740  loss: 2.2658 (2.1950)  weight_decay: 0.0500 (0.0500)  time: 1.0072  data: 0.0004  max mem: 78493
Epoch: [171]  [210/312]  eta: 0:01:51  lr: 0.001739  min_lr: 0.001739  loss: 2.3027 (2.1937)  weight_decay: 0.0500 (0.0500)  time: 1.0041  data: 0.0004  max mem: 78493
Epoch: [171]  [220/312]  eta: 0:01:40  lr: 0.001739  min_lr: 0.001739  loss: 2.3525 (2.1956)  weight_decay: 0.0500 (0.0500)  time: 1.0053  data: 0.0004  max mem: 78493
Epoch: [171]  [230/312]  eta: 0:01:29  lr: 0.001738  min_lr: 0.001738  loss: 2.3525 (2.1973)  weight_decay: 0.0500 (0.0500)  time: 1.0065  data: 0.0004  max mem: 78493
Epoch: [171]  [240/312]  eta: 0:01:18  lr: 0.001737  min_lr: 0.001737  loss: 2.3214 (2.2059)  weight_decay: 0.0500 (0.0500)  time: 1.0068  data: 0.0004  max mem: 78493
Epoch: [171]  [250/312]  eta: 0:01:07  lr: 0.001737  min_lr: 0.001737  loss: 2.3214 (2.2080)  weight_decay: 0.0500 (0.0500)  time: 1.0080  data: 0.0005  max mem: 78493
Epoch: [171]  [260/312]  eta: 0:00:56  lr: 0.001736  min_lr: 0.001736  loss: 2.2345 (2.2078)  weight_decay: 0.0500 (0.0500)  time: 1.0078  data: 0.0010  max mem: 78493
Epoch: [171]  [270/312]  eta: 0:00:45  lr: 0.001735  min_lr: 0.001735  loss: 2.2345 (2.2024)  weight_decay: 0.0500 (0.0500)  time: 1.0073  data: 0.0010  max mem: 78493
Epoch: [171]  [280/312]  eta: 0:00:34  lr: 0.001734  min_lr: 0.001734  loss: 2.1953 (2.2008)  weight_decay: 0.0500 (0.0500)  time: 1.0070  data: 0.0011  max mem: 78493
Epoch: [171]  [290/312]  eta: 0:00:23  lr: 0.001734  min_lr: 0.001734  loss: 2.0364 (2.1946)  weight_decay: 0.0500 (0.0500)  time: 1.0038  data: 0.0009  max mem: 78493
Epoch: [171]  [300/312]  eta: 0:00:12  lr: 0.001733  min_lr: 0.001733  loss: 2.1534 (2.1969)  weight_decay: 0.0500 (0.0500)  time: 1.0014  data: 0.0001  max mem: 78493
Epoch: [171]  [310/312]  eta: 0:00:02  lr: 0.001732  min_lr: 0.001732  loss: 2.1500 (2.1879)  weight_decay: 0.0500 (0.0500)  time: 1.0015  data: 0.0001  max mem: 78493
Epoch: [171]  [311/312]  eta: 0:00:01  lr: 0.001732  min_lr: 0.001732  loss: 2.0324 (2.1874)  weight_decay: 0.0500 (0.0500)  time: 1.0015  data: 0.0001  max mem: 78493
Epoch: [171] Total time: 0:05:34 (1.0715 s / it)
Averaged stats: lr: 0.001732  min_lr: 0.001732  loss: 2.0324 (2.2126)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:17  loss: 0.6013 (0.6013)  acc1: 85.2865 (85.2865)  acc5: 96.7448 (96.7448)  time: 8.5962  data: 8.3305  max mem: 78493
Test:  [8/9]  eta: 0:00:01  loss: 0.9643 (0.8469)  acc1: 75.3906 (77.5200)  acc5: 93.2292 (93.9680)  time: 1.1557  data: 0.9257  max mem: 78493
Test: Total time: 0:00:10 (1.1871 s / it)
* Acc@1 77.938 Acc@5 93.966 loss 0.842
Accuracy of the model on the 50000 test images: 77.9%
Max accuracy: 77.94%
Epoch: [172]  [  0/312]  eta: 1:20:58  lr: 0.001732  min_lr: 0.001732  loss: 2.2611 (2.2611)  weight_decay: 0.0500 (0.0500)  time: 15.5719  data: 12.6641  max mem: 78493
Epoch: [172]  [ 10/312]  eta: 0:13:09  lr: 0.001731  min_lr: 0.001731  loss: 2.2026 (2.0840)  weight_decay: 0.0500 (0.0500)  time: 2.6129  data: 1.2784  max mem: 78493
Epoch: [172]  [ 20/312]  eta: 0:09:01  lr: 0.001731  min_lr: 0.001731  loss: 2.2510 (2.1957)  weight_decay: 0.0500 (0.0500)  time: 1.1679  data: 0.0702  max mem: 78493
Epoch: [172]  [ 30/312]  eta: 0:07:26  lr: 0.001730  min_lr: 0.001730  loss: 2.3767 (2.1804)  weight_decay: 0.0500 (0.0500)  time: 1.0149  data: 0.0005  max mem: 78493
Epoch: [172]  [ 40/312]  eta: 0:06:32  lr: 0.001729  min_lr: 0.001729  loss: 2.3401 (2.2351)  weight_decay: 0.0500 (0.0500)  time: 1.0105  data: 0.0004  max mem: 78493
Epoch: [172]  [ 50/312]  eta: 0:05:55  lr: 0.001729  min_lr: 0.001729  loss: 2.2590 (2.2221)  weight_decay: 0.0500 (0.0500)  time: 1.0124  data: 0.0005  max mem: 78493
Epoch: [172]  [ 60/312]  eta: 0:05:27  lr: 0.001728  min_lr: 0.001728  loss: 2.2718 (2.2211)  weight_decay: 0.0500 (0.0500)  time: 1.0109  data: 0.0005  max mem: 78493
Epoch: [172]  [ 70/312]  eta: 0:05:04  lr: 0.001727  min_lr: 0.001727  loss: 2.2718 (2.2091)  weight_decay: 0.0500 (0.0500)  time: 1.0080  data: 0.0005  max mem: 78493
Epoch: [172]  [ 80/312]  eta: 0:04:45  lr: 0.001726  min_lr: 0.001726  loss: 2.2438 (2.2184)  weight_decay: 0.0500 (0.0500)  time: 1.0077  data: 0.0004  max mem: 78493
Epoch: [172]  [ 90/312]  eta: 0:04:27  lr: 0.001726  min_lr: 0.001726  loss: 2.2438 (2.2139)  weight_decay: 0.0500 (0.0500)  time: 1.0073  data: 0.0012  max mem: 78493
Epoch: [172]  [100/312]  eta: 0:04:11  lr: 0.001725  min_lr: 0.001725  loss: 2.2369 (2.2119)  weight_decay: 0.0500 (0.0500)  time: 1.0070  data: 0.0012  max mem: 78493
Epoch: [172]  [110/312]  eta: 0:03:56  lr: 0.001724  min_lr: 0.001724  loss: 2.1456 (2.2010)  weight_decay: 0.0500 (0.0500)  time: 1.0060  data: 0.0004  max mem: 78493
Epoch: [172]  [120/312]  eta: 0:03:41  lr: 0.001724  min_lr: 0.001724  loss: 2.2294 (2.2082)  weight_decay: 0.0500 (0.0500)  time: 1.0064  data: 0.0004  max mem: 78493
Epoch: [172]  [130/312]  eta: 0:03:28  lr: 0.001723  min_lr: 0.001723  loss: 2.2294 (2.1961)  weight_decay: 0.0500 (0.0500)  time: 1.0073  data: 0.0004  max mem: 78493
Epoch: [172]  [140/312]  eta: 0:03:15  lr: 0.001722  min_lr: 0.001722  loss: 2.1337 (2.1998)  weight_decay: 0.0500 (0.0500)  time: 1.0052  data: 0.0004  max mem: 78493
Epoch: [172]  [150/312]  eta: 0:03:02  lr: 0.001721  min_lr: 0.001721  loss: 2.2543 (2.1979)  weight_decay: 0.0500 (0.0500)  time: 1.0046  data: 0.0004  max mem: 78493
Epoch: [172]  [160/312]  eta: 0:02:49  lr: 0.001721  min_lr: 0.001721  loss: 2.2862 (2.2096)  weight_decay: 0.0500 (0.0500)  time: 1.0069  data: 0.0016  max mem: 78493
Epoch: [172]  [170/312]  eta: 0:02:37  lr: 0.001720  min_lr: 0.001720  loss: 2.3571 (2.2132)  weight_decay: 0.0500 (0.0500)  time: 1.0069  data: 0.0016  max mem: 78493
Epoch: [172]  [180/312]  eta: 0:02:25  lr: 0.001719  min_lr: 0.001719  loss: 2.3571 (2.2188)  weight_decay: 0.0500 (0.0500)  time: 1.0068  data: 0.0004  max mem: 78493
Epoch: [172]  [190/312]  eta: 0:02:14  lr: 0.001719  min_lr: 0.001719  loss: 2.2967 (2.2195)  weight_decay: 0.0500 (0.0500)  time: 1.0072  data: 0.0004  max mem: 78493
Epoch: [172]  [200/312]  eta: 0:02:02  lr: 0.001718  min_lr: 0.001718  loss: 2.2681 (2.2144)  weight_decay: 0.0500 (0.0500)  time: 1.0070  data: 0.0013  max mem: 78493
Epoch: [172]  [210/312]  eta: 0:01:51  lr: 0.001717  min_lr: 0.001717  loss: 2.1662 (2.2134)  weight_decay: 0.0500 (0.0500)  time: 1.0067  data: 0.0013  max mem: 78493
Epoch: [172]  [220/312]  eta: 0:01:40  lr: 0.001716  min_lr: 0.001716  loss: 2.3591 (2.2189)  weight_decay: 0.0500 (0.0500)  time: 1.0061  data: 0.0004  max mem: 78493
Epoch: [172]  [230/312]  eta: 0:01:28  lr: 0.001716  min_lr: 0.001716  loss: 2.3333 (2.2201)  weight_decay: 0.0500 (0.0500)  time: 1.0066  data: 0.0005  max mem: 78493
Epoch: [172]  [240/312]  eta: 0:01:17  lr: 0.001715  min_lr: 0.001715  loss: 2.2024 (2.2221)  weight_decay: 0.0500 (0.0500)  time: 1.0071  data: 0.0004  max mem: 78493
Epoch: [172]  [250/312]  eta: 0:01:06  lr: 0.001714  min_lr: 0.001714  loss: 2.1748 (2.2154)  weight_decay: 0.0500 (0.0500)  time: 1.0080  data: 0.0004  max mem: 78493
Epoch: [172]  [260/312]  eta: 0:00:55  lr: 0.001714  min_lr: 0.001714  loss: 2.1748 (2.2127)  weight_decay: 0.0500 (0.0500)  time: 1.0079  data: 0.0004  max mem: 78493
Epoch: [172]  [270/312]  eta: 0:00:45  lr: 0.001713  min_lr: 0.001713  loss: 2.2656 (2.2113)  weight_decay: 0.0500 (0.0500)  time: 1.0055  data: 0.0004  max mem: 78493
Epoch: [172]  [280/312]  eta: 0:00:34  lr: 0.001712  min_lr: 0.001712  loss: 2.3031 (2.2161)  weight_decay: 0.0500 (0.0500)  time: 1.0072  data: 0.0011  max mem: 78493
Epoch: [172]  [290/312]  eta: 0:00:23  lr: 0.001711  min_lr: 0.001711  loss: 2.2679 (2.2161)  weight_decay: 0.0500 (0.0500)  time: 1.0059  data: 0.0009  max mem: 78493
Epoch: [172]  [300/312]  eta: 0:00:12  lr: 0.001711  min_lr: 0.001711  loss: 2.1389 (2.2167)  weight_decay: 0.0500 (0.0500)  time: 1.0023  data: 0.0001  max mem: 78493
Epoch: [172]  [310/312]  eta: 0:00:02  lr: 0.001710  min_lr: 0.001710  loss: 2.0735 (2.2113)  weight_decay: 0.0500 (0.0500)  time: 1.0020  data: 0.0001  max mem: 78493
Epoch: [172]  [311/312]  eta: 0:00:01  lr: 0.001710  min_lr: 0.001710  loss: 2.0735 (2.2108)  weight_decay: 0.0500 (0.0500)  time: 1.0020  data: 0.0001  max mem: 78493
Epoch: [172] Total time: 0:05:33 (1.0699 s / it)
Averaged stats: lr: 0.001710  min_lr: 0.001710  loss: 2.0735 (2.1971)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:17  loss: 0.6225 (0.6225)  acc1: 83.2031 (83.2031)  acc5: 97.0052 (97.0052)  time: 8.5815  data: 8.3183  max mem: 78493
Test:  [8/9]  eta: 0:00:01  loss: 0.9614 (0.8698)  acc1: 75.9115 (77.1680)  acc5: 94.1406 (94.2720)  time: 1.1558  data: 0.9243  max mem: 78493
Test: Total time: 0:00:10 (1.2033 s / it)
* Acc@1 77.606 Acc@5 94.006 loss 0.855
Accuracy of the model on the 50000 test images: 77.6%
Max accuracy: 77.94%
Epoch: [173]  [  0/312]  eta: 1:25:48  lr: 0.001710  min_lr: 0.001710  loss: 2.6260 (2.6260)  weight_decay: 0.0500 (0.0500)  time: 16.5031  data: 12.4101  max mem: 78493
Epoch: [173]  [ 10/312]  eta: 0:12:52  lr: 0.001709  min_lr: 0.001709  loss: 2.1570 (2.1068)  weight_decay: 0.0500 (0.0500)  time: 2.5589  data: 1.1313  max mem: 78493
Epoch: [173]  [ 20/312]  eta: 0:08:53  lr: 0.001708  min_lr: 0.001708  loss: 2.2660 (2.1316)  weight_decay: 0.0500 (0.0500)  time: 1.0928  data: 0.0020  max mem: 78493
Epoch: [173]  [ 30/312]  eta: 0:07:20  lr: 0.001708  min_lr: 0.001708  loss: 2.3107 (2.1316)  weight_decay: 0.0500 (0.0500)  time: 1.0151  data: 0.0012  max mem: 78493
Epoch: [173]  [ 40/312]  eta: 0:06:28  lr: 0.001707  min_lr: 0.001707  loss: 2.2219 (2.1345)  weight_decay: 0.0500 (0.0500)  time: 1.0093  data: 0.0018  max mem: 78493
Epoch: [173]  [ 50/312]  eta: 0:05:52  lr: 0.001706  min_lr: 0.001706  loss: 2.3404 (2.1554)  weight_decay: 0.0500 (0.0500)  time: 1.0068  data: 0.0011  max mem: 78493
Epoch: [173]  [ 60/312]  eta: 0:05:24  lr: 0.001706  min_lr: 0.001706  loss: 2.3511 (2.1912)  weight_decay: 0.0500 (0.0500)  time: 1.0052  data: 0.0004  max mem: 78493
Epoch: [173]  [ 70/312]  eta: 0:05:02  lr: 0.001705  min_lr: 0.001705  loss: 2.3279 (2.1787)  weight_decay: 0.0500 (0.0500)  time: 1.0081  data: 0.0005  max mem: 78493
Epoch: [173]  [ 80/312]  eta: 0:04:43  lr: 0.001704  min_lr: 0.001704  loss: 2.2212 (2.1984)  weight_decay: 0.0500 (0.0500)  time: 1.0091  data: 0.0005  max mem: 78493
Epoch: [173]  [ 90/312]  eta: 0:04:25  lr: 0.001703  min_lr: 0.001703  loss: 2.3298 (2.2114)  weight_decay: 0.0500 (0.0500)  time: 1.0092  data: 0.0004  max mem: 78493
Epoch: [173]  [100/312]  eta: 0:04:09  lr: 0.001703  min_lr: 0.001703  loss: 2.3177 (2.2107)  weight_decay: 0.0500 (0.0500)  time: 1.0083  data: 0.0004  max mem: 78493
Epoch: [173]  [110/312]  eta: 0:03:54  lr: 0.001702  min_lr: 0.001702  loss: 2.2843 (2.2218)  weight_decay: 0.0500 (0.0500)  time: 1.0074  data: 0.0004  max mem: 78493
Epoch: [173]  [120/312]  eta: 0:03:40  lr: 0.001701  min_lr: 0.001701  loss: 2.2843 (2.2172)  weight_decay: 0.0500 (0.0500)  time: 1.0084  data: 0.0004  max mem: 78493
Epoch: [173]  [130/312]  eta: 0:03:27  lr: 0.001701  min_lr: 0.001701  loss: 2.0682 (2.1953)  weight_decay: 0.0500 (0.0500)  time: 1.0099  data: 0.0005  max mem: 78493
Epoch: [173]  [140/312]  eta: 0:03:14  lr: 0.001700  min_lr: 0.001700  loss: 2.1648 (2.2026)  weight_decay: 0.0500 (0.0500)  time: 1.0110  data: 0.0005  max mem: 78493
Epoch: [173]  [150/312]  eta: 0:03:01  lr: 0.001699  min_lr: 0.001699  loss: 2.1058 (2.1852)  weight_decay: 0.0500 (0.0500)  time: 1.0090  data: 0.0004  max mem: 78493
Epoch: [173]  [160/312]  eta: 0:02:49  lr: 0.001699  min_lr: 0.001699  loss: 2.1058 (2.1866)  weight_decay: 0.0500 (0.0500)  time: 1.0066  data: 0.0004  max mem: 78493
Epoch: [173]  [170/312]  eta: 0:02:37  lr: 0.001698  min_lr: 0.001698  loss: 2.3096 (2.1835)  weight_decay: 0.0500 (0.0500)  time: 1.0058  data: 0.0004  max mem: 78493
Epoch: [173]  [180/312]  eta: 0:02:25  lr: 0.001697  min_lr: 0.001697  loss: 2.1432 (2.1859)  weight_decay: 0.0500 (0.0500)  time: 1.0062  data: 0.0004  max mem: 78493
Epoch: [173]  [190/312]  eta: 0:02:13  lr: 0.001696  min_lr: 0.001696  loss: 2.1574 (2.1760)  weight_decay: 0.0500 (0.0500)  time: 1.0064  data: 0.0004  max mem: 78493
Epoch: [173]  [200/312]  eta: 0:02:02  lr: 0.001696  min_lr: 0.001696  loss: 2.1912 (2.1852)  weight_decay: 0.0500 (0.0500)  time: 1.0063  data: 0.0004  max mem: 78493
Epoch: [173]  [210/312]  eta: 0:01:51  lr: 0.001695  min_lr: 0.001695  loss: 2.3770 (2.1882)  weight_decay: 0.0500 (0.0500)  time: 1.0061  data: 0.0004  max mem: 78493
Epoch: [173]  [220/312]  eta: 0:01:39  lr: 0.001694  min_lr: 0.001694  loss: 2.2986 (2.1919)  weight_decay: 0.0500 (0.0500)  time: 1.0058  data: 0.0004  max mem: 78493
Epoch: [173]  [230/312]  eta: 0:01:28  lr: 0.001694  min_lr: 0.001694  loss: 2.3081 (2.1961)  weight_decay: 0.0500 (0.0500)  time: 1.0049  data: 0.0004  max mem: 78493
Epoch: [173]  [240/312]  eta: 0:01:17  lr: 0.001693  min_lr: 0.001693  loss: 2.3081 (2.1966)  weight_decay: 0.0500 (0.0500)  time: 1.0063  data: 0.0004  max mem: 78493
Epoch: [173]  [250/312]  eta: 0:01:06  lr: 0.001692  min_lr: 0.001692  loss: 2.2412 (2.1963)  weight_decay: 0.0500 (0.0500)  time: 1.0067  data: 0.0004  max mem: 78493
Epoch: [173]  [260/312]  eta: 0:00:55  lr: 0.001691  min_lr: 0.001691  loss: 2.3142 (2.2008)  weight_decay: 0.0500 (0.0500)  time: 1.0056  data: 0.0004  max mem: 78493
Epoch: [173]  [270/312]  eta: 0:00:44  lr: 0.001691  min_lr: 0.001691  loss: 2.3611 (2.2018)  weight_decay: 0.0500 (0.0500)  time: 1.0059  data: 0.0005  max mem: 78493
Epoch: [173]  [280/312]  eta: 0:00:34  lr: 0.001690  min_lr: 0.001690  loss: 2.2690 (2.2038)  weight_decay: 0.0500 (0.0500)  time: 1.0049  data: 0.0010  max mem: 78493
Epoch: [173]  [290/312]  eta: 0:00:23  lr: 0.001689  min_lr: 0.001689  loss: 2.3541 (2.2106)  weight_decay: 0.0500 (0.0500)  time: 1.0030  data: 0.0009  max mem: 78493
Epoch: [173]  [300/312]  eta: 0:00:12  lr: 0.001689  min_lr: 0.001689  loss: 2.3459 (2.2119)  weight_decay: 0.0500 (0.0500)  time: 1.0016  data: 0.0001  max mem: 78493
Epoch: [173]  [310/312]  eta: 0:00:02  lr: 0.001688  min_lr: 0.001688  loss: 2.3114 (2.2101)  weight_decay: 0.0500 (0.0500)  time: 1.0015  data: 0.0001  max mem: 78493
Epoch: [173]  [311/312]  eta: 0:00:01  lr: 0.001688  min_lr: 0.001688  loss: 2.3114 (2.2098)  weight_decay: 0.0500 (0.0500)  time: 1.0014  data: 0.0001  max mem: 78493
Epoch: [173] Total time: 0:05:33 (1.0677 s / it)
Averaged stats: lr: 0.001688  min_lr: 0.001688  loss: 2.3114 (2.2072)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:16  loss: 0.6181 (0.6181)  acc1: 85.1562 (85.1562)  acc5: 96.0938 (96.0938)  time: 8.5432  data: 8.2794  max mem: 78493
Test:  [8/9]  eta: 0:00:01  loss: 0.9619 (0.8864)  acc1: 76.0417 (77.3600)  acc5: 94.0104 (93.6160)  time: 1.1512  data: 0.9200  max mem: 78493
Test: Total time: 0:00:10 (1.1946 s / it)
* Acc@1 77.746 Acc@5 93.804 loss 0.870
Accuracy of the model on the 50000 test images: 77.7%
Max accuracy: 77.94%
Epoch: [174]  [  0/312]  eta: 1:26:42  lr: 0.001688  min_lr: 0.001688  loss: 2.1536 (2.1536)  weight_decay: 0.0500 (0.0500)  time: 16.6761  data: 15.6666  max mem: 78493
Epoch: [174]  [ 10/312]  eta: 0:13:36  lr: 0.001687  min_lr: 0.001687  loss: 2.2346 (2.2211)  weight_decay: 0.0500 (0.0500)  time: 2.7041  data: 1.4249  max mem: 78493
Epoch: [174]  [ 20/312]  eta: 0:09:13  lr: 0.001686  min_lr: 0.001686  loss: 2.2346 (2.1940)  weight_decay: 0.0500 (0.0500)  time: 1.1579  data: 0.0006  max mem: 78493
Epoch: [174]  [ 30/312]  eta: 0:07:33  lr: 0.001686  min_lr: 0.001686  loss: 2.1432 (2.1883)  weight_decay: 0.0500 (0.0500)  time: 1.0079  data: 0.0012  max mem: 78493
Epoch: [174]  [ 40/312]  eta: 0:06:37  lr: 0.001685  min_lr: 0.001685  loss: 2.3112 (2.2101)  weight_decay: 0.0500 (0.0500)  time: 1.0075  data: 0.0012  max mem: 78493
Epoch: [174]  [ 50/312]  eta: 0:05:59  lr: 0.001684  min_lr: 0.001684  loss: 2.3112 (2.2007)  weight_decay: 0.0500 (0.0500)  time: 1.0069  data: 0.0004  max mem: 78493
Epoch: [174]  [ 60/312]  eta: 0:05:31  lr: 0.001683  min_lr: 0.001683  loss: 2.1059 (2.1727)  weight_decay: 0.0500 (0.0500)  time: 1.0079  data: 0.0005  max mem: 78493
Epoch: [174]  [ 70/312]  eta: 0:05:07  lr: 0.001683  min_lr: 0.001683  loss: 2.0438 (2.1420)  weight_decay: 0.0500 (0.0500)  time: 1.0098  data: 0.0005  max mem: 78493
Epoch: [174]  [ 80/312]  eta: 0:04:47  lr: 0.001682  min_lr: 0.001682  loss: 2.1003 (2.1306)  weight_decay: 0.0500 (0.0500)  time: 1.0083  data: 0.0004  max mem: 78493
Epoch: [174]  [ 90/312]  eta: 0:04:29  lr: 0.001681  min_lr: 0.001681  loss: 2.2174 (2.1410)  weight_decay: 0.0500 (0.0500)  time: 1.0081  data: 0.0004  max mem: 78493
Epoch: [174]  [100/312]  eta: 0:04:12  lr: 0.001681  min_lr: 0.001681  loss: 2.3207 (2.1682)  weight_decay: 0.0500 (0.0500)  time: 1.0079  data: 0.0004  max mem: 78493
Epoch: [174]  [110/312]  eta: 0:03:57  lr: 0.001680  min_lr: 0.001680  loss: 2.1825 (2.1680)  weight_decay: 0.0500 (0.0500)  time: 1.0071  data: 0.0004  max mem: 78493
Epoch: [174]  [120/312]  eta: 0:03:43  lr: 0.001679  min_lr: 0.001679  loss: 2.0574 (2.1394)  weight_decay: 0.0500 (0.0500)  time: 1.0069  data: 0.0004  max mem: 78493
Epoch: [174]  [130/312]  eta: 0:03:29  lr: 0.001678  min_lr: 0.001678  loss: 2.0187 (2.1443)  weight_decay: 0.0500 (0.0500)  time: 1.0061  data: 0.0004  max mem: 78493
Epoch: [174]  [140/312]  eta: 0:03:16  lr: 0.001678  min_lr: 0.001678  loss: 2.1940 (2.1469)  weight_decay: 0.0500 (0.0500)  time: 1.0062  data: 0.0004  max mem: 78493
Epoch: [174]  [150/312]  eta: 0:03:03  lr: 0.001677  min_lr: 0.001677  loss: 2.2079 (2.1596)  weight_decay: 0.0500 (0.0500)  time: 1.0068  data: 0.0004  max mem: 78493
Epoch: [174]  [160/312]  eta: 0:02:50  lr: 0.001676  min_lr: 0.001676  loss: 2.0784 (2.1460)  weight_decay: 0.0500 (0.0500)  time: 1.0080  data: 0.0005  max mem: 78493
Epoch: [174]  [170/312]  eta: 0:02:38  lr: 0.001676  min_lr: 0.001676  loss: 1.9446 (2.1498)  weight_decay: 0.0500 (0.0500)  time: 1.0066  data: 0.0005  max mem: 78493
Epoch: [174]  [180/312]  eta: 0:02:26  lr: 0.001675  min_lr: 0.001675  loss: 2.3838 (2.1521)  weight_decay: 0.0500 (0.0500)  time: 1.0072  data: 0.0004  max mem: 78493
Epoch: [174]  [190/312]  eta: 0:02:14  lr: 0.001674  min_lr: 0.001674  loss: 2.3838 (2.1639)  weight_decay: 0.0500 (0.0500)  time: 1.0098  data: 0.0004  max mem: 78493
Epoch: [174]  [200/312]  eta: 0:02:03  lr: 0.001674  min_lr: 0.001674  loss: 2.3185 (2.1604)  weight_decay: 0.0500 (0.0500)  time: 1.0087  data: 0.0004  max mem: 78493
Epoch: [174]  [210/312]  eta: 0:01:51  lr: 0.001673  min_lr: 0.001673  loss: 2.1251 (2.1664)  weight_decay: 0.0500 (0.0500)  time: 1.0080  data: 0.0004  max mem: 78493
Epoch: [174]  [220/312]  eta: 0:01:40  lr: 0.001672  min_lr: 0.001672  loss: 2.4168 (2.1734)  weight_decay: 0.0500 (0.0500)  time: 1.0072  data: 0.0005  max mem: 78493
Epoch: [174]  [230/312]  eta: 0:01:29  lr: 0.001671  min_lr: 0.001671  loss: 2.4168 (2.1727)  weight_decay: 0.0500 (0.0500)  time: 1.0079  data: 0.0005  max mem: 78493
Epoch: [174]  [240/312]  eta: 0:01:18  lr: 0.001671  min_lr: 0.001671  loss: 2.2110 (2.1737)  weight_decay: 0.0500 (0.0500)  time: 1.0088  data: 0.0005  max mem: 78493
Epoch: [174]  [250/312]  eta: 0:01:07  lr: 0.001670  min_lr: 0.001670  loss: 2.2265 (2.1701)  weight_decay: 0.0500 (0.0500)  time: 1.0075  data: 0.0005  max mem: 78493
Epoch: [174]  [260/312]  eta: 0:00:56  lr: 0.001669  min_lr: 0.001669  loss: 2.2265 (2.1714)  weight_decay: 0.0500 (0.0500)  time: 1.0072  data: 0.0005  max mem: 78493
Epoch: [174]  [270/312]  eta: 0:00:45  lr: 0.001669  min_lr: 0.001669  loss: 2.3101 (2.1758)  weight_decay: 0.0500 (0.0500)  time: 1.0064  data: 0.0012  max mem: 78493
Epoch: [174]  [280/312]  eta: 0:00:34  lr: 0.001668  min_lr: 0.001668  loss: 2.3961 (2.1845)  weight_decay: 0.0500 (0.0500)  time: 1.0069  data: 0.0018  max mem: 78493
Epoch: [174]  [290/312]  eta: 0:00:23  lr: 0.001667  min_lr: 0.001667  loss: 2.4517 (2.1878)  weight_decay: 0.0500 (0.0500)  time: 1.0049  data: 0.0009  max mem: 78493
Epoch: [174]  [300/312]  eta: 0:00:12  lr: 0.001666  min_lr: 0.001666  loss: 2.3226 (2.1910)  weight_decay: 0.0500 (0.0500)  time: 1.0017  data: 0.0001  max mem: 78493
Epoch: [174]  [310/312]  eta: 0:00:02  lr: 0.001666  min_lr: 0.001666  loss: 2.3027 (2.1971)  weight_decay: 0.0500 (0.0500)  time: 1.0018  data: 0.0001  max mem: 78493
Epoch: [174]  [311/312]  eta: 0:00:01  lr: 0.001666  min_lr: 0.001666  loss: 2.3027 (2.1991)  weight_decay: 0.0500 (0.0500)  time: 1.0019  data: 0.0001  max mem: 78493
Epoch: [174] Total time: 0:05:34 (1.0726 s / it)
Averaged stats: lr: 0.001666  min_lr: 0.001666  loss: 2.3027 (2.1982)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:16  loss: 0.6130 (0.6130)  acc1: 85.0260 (85.0260)  acc5: 96.7448 (96.7448)  time: 8.4746  data: 8.2125  max mem: 78493
Test:  [8/9]  eta: 0:00:01  loss: 0.9760 (0.8873)  acc1: 77.2135 (77.4400)  acc5: 94.0104 (93.8240)  time: 1.1447  data: 0.9126  max mem: 78493
Test: Total time: 0:00:10 (1.1891 s / it)
* Acc@1 77.734 Acc@5 93.864 loss 0.871
Accuracy of the model on the 50000 test images: 77.7%
Max accuracy: 77.94%
Epoch: [175]  [  0/312]  eta: 1:26:44  lr: 0.001666  min_lr: 0.001666  loss: 2.6209 (2.6209)  weight_decay: 0.0500 (0.0500)  time: 16.6822  data: 12.6052  max mem: 78493
Epoch: [175]  [ 10/312]  eta: 0:13:01  lr: 0.001665  min_lr: 0.001665  loss: 2.2132 (2.1181)  weight_decay: 0.0500 (0.0500)  time: 2.5874  data: 1.1573  max mem: 78493
Epoch: [175]  [ 20/312]  eta: 0:08:57  lr: 0.001664  min_lr: 0.001664  loss: 2.2274 (2.1651)  weight_decay: 0.0500 (0.0500)  time: 1.0984  data: 0.0065  max mem: 78493
Epoch: [175]  [ 30/312]  eta: 0:07:23  lr: 0.001663  min_lr: 0.001663  loss: 2.3621 (2.2050)  weight_decay: 0.0500 (0.0500)  time: 1.0143  data: 0.0005  max mem: 78493
Epoch: [175]  [ 40/312]  eta: 0:06:30  lr: 0.001663  min_lr: 0.001663  loss: 2.2155 (2.1781)  weight_decay: 0.0500 (0.0500)  time: 1.0096  data: 0.0004  max mem: 78493
Epoch: [175]  [ 50/312]  eta: 0:05:54  lr: 0.001662  min_lr: 0.001662  loss: 2.0502 (2.1562)  weight_decay: 0.0500 (0.0500)  time: 1.0106  data: 0.0004  max mem: 78493
Epoch: [175]  [ 60/312]  eta: 0:05:26  lr: 0.001661  min_lr: 0.001661  loss: 2.0225 (2.1577)  weight_decay: 0.0500 (0.0500)  time: 1.0095  data: 0.0005  max mem: 78493
Epoch: [175]  [ 70/312]  eta: 0:05:03  lr: 0.001661  min_lr: 0.001661  loss: 2.1229 (2.1469)  weight_decay: 0.0500 (0.0500)  time: 1.0067  data: 0.0005  max mem: 78493
Epoch: [175]  [ 80/312]  eta: 0:04:44  lr: 0.001660  min_lr: 0.001660  loss: 2.1629 (2.1710)  weight_decay: 0.0500 (0.0500)  time: 1.0082  data: 0.0004  max mem: 78493
Epoch: [175]  [ 90/312]  eta: 0:04:26  lr: 0.001659  min_lr: 0.001659  loss: 2.2491 (2.1673)  weight_decay: 0.0500 (0.0500)  time: 1.0107  data: 0.0004  max mem: 78493
Epoch: [175]  [100/312]  eta: 0:04:10  lr: 0.001658  min_lr: 0.001658  loss: 1.9905 (2.1467)  weight_decay: 0.0500 (0.0500)  time: 1.0101  data: 0.0004  max mem: 78493
Epoch: [175]  [110/312]  eta: 0:03:55  lr: 0.001658  min_lr: 0.001658  loss: 1.8800 (2.1292)  weight_decay: 0.0500 (0.0500)  time: 1.0102  data: 0.0005  max mem: 78493
Epoch: [175]  [120/312]  eta: 0:03:41  lr: 0.001657  min_lr: 0.001657  loss: 2.1102 (2.1404)  weight_decay: 0.0500 (0.0500)  time: 1.0098  data: 0.0005  max mem: 78493
Epoch: [175]  [130/312]  eta: 0:03:27  lr: 0.001656  min_lr: 0.001656  loss: 2.1184 (2.1321)  weight_decay: 0.0500 (0.0500)  time: 1.0092  data: 0.0005  max mem: 78493
Epoch: [175]  [140/312]  eta: 0:03:14  lr: 0.001656  min_lr: 0.001656  loss: 2.0096 (2.1251)  weight_decay: 0.0500 (0.0500)  time: 1.0096  data: 0.0005  max mem: 78493
Epoch: [175]  [150/312]  eta: 0:03:02  lr: 0.001655  min_lr: 0.001655  loss: 1.9890 (2.1270)  weight_decay: 0.0500 (0.0500)  time: 1.0088  data: 0.0004  max mem: 78493
Epoch: [175]  [160/312]  eta: 0:02:49  lr: 0.001654  min_lr: 0.001654  loss: 2.1870 (2.1297)  weight_decay: 0.0500 (0.0500)  time: 1.0075  data: 0.0004  max mem: 78493
Epoch: [175]  [170/312]  eta: 0:02:37  lr: 0.001654  min_lr: 0.001654  loss: 2.0894 (2.1237)  weight_decay: 0.0500 (0.0500)  time: 1.0071  data: 0.0005  max mem: 78493
Epoch: [175]  [180/312]  eta: 0:02:25  lr: 0.001653  min_lr: 0.001653  loss: 2.0818 (2.1293)  weight_decay: 0.0500 (0.0500)  time: 1.0083  data: 0.0004  max mem: 78493
Epoch: [175]  [190/312]  eta: 0:02:14  lr: 0.001652  min_lr: 0.001652  loss: 2.2516 (2.1299)  weight_decay: 0.0500 (0.0500)  time: 1.0080  data: 0.0004  max mem: 78493
Epoch: [175]  [200/312]  eta: 0:02:02  lr: 0.001651  min_lr: 0.001651  loss: 2.2569 (2.1370)  weight_decay: 0.0500 (0.0500)  time: 1.0068  data: 0.0004  max mem: 78493
Epoch: [175]  [210/312]  eta: 0:01:51  lr: 0.001651  min_lr: 0.001651  loss: 2.2617 (2.1356)  weight_decay: 0.0500 (0.0500)  time: 1.0061  data: 0.0005  max mem: 78493
Epoch: [175]  [220/312]  eta: 0:01:40  lr: 0.001650  min_lr: 0.001650  loss: 2.1807 (2.1380)  weight_decay: 0.0500 (0.0500)  time: 1.0065  data: 0.0005  max mem: 78493
Epoch: [175]  [230/312]  eta: 0:01:28  lr: 0.001649  min_lr: 0.001649  loss: 2.2278 (2.1435)  weight_decay: 0.0500 (0.0500)  time: 1.0052  data: 0.0005  max mem: 78493
Epoch: [175]  [240/312]  eta: 0:01:17  lr: 0.001649  min_lr: 0.001649  loss: 2.0406 (2.1385)  weight_decay: 0.0500 (0.0500)  time: 1.0062  data: 0.0006  max mem: 78493
Epoch: [175]  [250/312]  eta: 0:01:06  lr: 0.001648  min_lr: 0.001648  loss: 2.3054 (2.1479)  weight_decay: 0.0500 (0.0500)  time: 1.0080  data: 0.0006  max mem: 78493
Epoch: [175]  [260/312]  eta: 0:00:55  lr: 0.001647  min_lr: 0.001647  loss: 2.3054 (2.1444)  weight_decay: 0.0500 (0.0500)  time: 1.0065  data: 0.0005  max mem: 78493
Epoch: [175]  [270/312]  eta: 0:00:45  lr: 0.001646  min_lr: 0.001646  loss: 2.1665 (2.1484)  weight_decay: 0.0500 (0.0500)  time: 1.0056  data: 0.0005  max mem: 78493
Epoch: [175]  [280/312]  eta: 0:00:34  lr: 0.001646  min_lr: 0.001646  loss: 2.3885 (2.1564)  weight_decay: 0.0500 (0.0500)  time: 1.0060  data: 0.0010  max mem: 78493
Epoch: [175]  [290/312]  eta: 0:00:23  lr: 0.001645  min_lr: 0.001645  loss: 2.3885 (2.1566)  weight_decay: 0.0500 (0.0500)  time: 1.0045  data: 0.0009  max mem: 78493
Epoch: [175]  [300/312]  eta: 0:00:12  lr: 0.001644  min_lr: 0.001644  loss: 2.3745 (2.1666)  weight_decay: 0.0500 (0.0500)  time: 1.0018  data: 0.0001  max mem: 78493
Epoch: [175]  [310/312]  eta: 0:00:02  lr: 0.001644  min_lr: 0.001644  loss: 2.3823 (2.1676)  weight_decay: 0.0500 (0.0500)  time: 1.0017  data: 0.0001  max mem: 78493
Epoch: [175]  [311/312]  eta: 0:00:01  lr: 0.001644  min_lr: 0.001644  loss: 2.3745 (2.1672)  weight_decay: 0.0500 (0.0500)  time: 1.0016  data: 0.0001  max mem: 78493
Epoch: [175] Total time: 0:05:33 (1.0690 s / it)
Averaged stats: lr: 0.001644  min_lr: 0.001644  loss: 2.3745 (2.1866)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:16  loss: 0.6410 (0.6410)  acc1: 84.3750 (84.3750)  acc5: 96.3542 (96.3542)  time: 8.4696  data: 8.1878  max mem: 78493
Test:  [8/9]  eta: 0:00:01  loss: 0.9911 (0.8744)  acc1: 75.0000 (76.8960)  acc5: 93.2292 (93.5200)  time: 1.1392  data: 0.9099  max mem: 78493
Test: Total time: 0:00:10 (1.1552 s / it)
* Acc@1 77.626 Acc@5 93.804 loss 0.864
Accuracy of the model on the 50000 test images: 77.6%
Max accuracy: 77.94%
Epoch: [176]  [  0/312]  eta: 1:22:46  lr: 0.001643  min_lr: 0.001643  loss: 2.7046 (2.7046)  weight_decay: 0.0500 (0.0500)  time: 15.9184  data: 14.4441  max mem: 78493
Epoch: [176]  [ 10/312]  eta: 0:13:17  lr: 0.001643  min_lr: 0.001643  loss: 2.2541 (2.1850)  weight_decay: 0.0500 (0.0500)  time: 2.6401  data: 1.3464  max mem: 78493
Epoch: [176]  [ 20/312]  eta: 0:09:05  lr: 0.001642  min_lr: 0.001642  loss: 2.1411 (2.1825)  weight_decay: 0.0500 (0.0500)  time: 1.1651  data: 0.0208  max mem: 78493
Epoch: [176]  [ 30/312]  eta: 0:07:28  lr: 0.001641  min_lr: 0.001641  loss: 2.2793 (2.2016)  weight_decay: 0.0500 (0.0500)  time: 1.0136  data: 0.0027  max mem: 78493
Epoch: [176]  [ 40/312]  eta: 0:06:33  lr: 0.001641  min_lr: 0.001641  loss: 2.2300 (2.1557)  weight_decay: 0.0500 (0.0500)  time: 1.0075  data: 0.0005  max mem: 78493
Epoch: [176]  [ 50/312]  eta: 0:05:56  lr: 0.001640  min_lr: 0.001640  loss: 2.2320 (2.1629)  weight_decay: 0.0500 (0.0500)  time: 1.0062  data: 0.0005  max mem: 78493
Epoch: [176]  [ 60/312]  eta: 0:05:28  lr: 0.001639  min_lr: 0.001639  loss: 2.2338 (2.1336)  weight_decay: 0.0500 (0.0500)  time: 1.0081  data: 0.0004  max mem: 78493
Epoch: [176]  [ 70/312]  eta: 0:05:05  lr: 0.001639  min_lr: 0.001639  loss: 2.2665 (2.1378)  weight_decay: 0.0500 (0.0500)  time: 1.0099  data: 0.0004  max mem: 78493
Epoch: [176]  [ 80/312]  eta: 0:04:45  lr: 0.001638  min_lr: 0.001638  loss: 2.2728 (2.1334)  weight_decay: 0.0500 (0.0500)  time: 1.0097  data: 0.0004  max mem: 78493
Epoch: [176]  [ 90/312]  eta: 0:04:27  lr: 0.001637  min_lr: 0.001637  loss: 2.1442 (2.1329)  weight_decay: 0.0500 (0.0500)  time: 1.0077  data: 0.0004  max mem: 78493
Epoch: [176]  [100/312]  eta: 0:04:11  lr: 0.001636  min_lr: 0.001636  loss: 2.0553 (2.1321)  weight_decay: 0.0500 (0.0500)  time: 1.0063  data: 0.0004  max mem: 78493
Epoch: [176]  [110/312]  eta: 0:03:56  lr: 0.001636  min_lr: 0.001636  loss: 2.1176 (2.1471)  weight_decay: 0.0500 (0.0500)  time: 1.0070  data: 0.0005  max mem: 78493
Epoch: [176]  [120/312]  eta: 0:03:42  lr: 0.001635  min_lr: 0.001635  loss: 2.4433 (2.1572)  weight_decay: 0.0500 (0.0500)  time: 1.0071  data: 0.0004  max mem: 78493
Epoch: [176]  [130/312]  eta: 0:03:28  lr: 0.001634  min_lr: 0.001634  loss: 2.2443 (2.1488)  weight_decay: 0.0500 (0.0500)  time: 1.0073  data: 0.0004  max mem: 78493
Epoch: [176]  [140/312]  eta: 0:03:15  lr: 0.001634  min_lr: 0.001634  loss: 2.2385 (2.1541)  weight_decay: 0.0500 (0.0500)  time: 1.0075  data: 0.0004  max mem: 78493
Epoch: [176]  [150/312]  eta: 0:03:02  lr: 0.001633  min_lr: 0.001633  loss: 2.2513 (2.1599)  weight_decay: 0.0500 (0.0500)  time: 1.0063  data: 0.0004  max mem: 78493
Epoch: [176]  [160/312]  eta: 0:02:50  lr: 0.001632  min_lr: 0.001632  loss: 2.2371 (2.1706)  weight_decay: 0.0500 (0.0500)  time: 1.0055  data: 0.0005  max mem: 78493
Epoch: [176]  [170/312]  eta: 0:02:38  lr: 0.001631  min_lr: 0.001631  loss: 2.2371 (2.1688)  weight_decay: 0.0500 (0.0500)  time: 1.0048  data: 0.0005  max mem: 78493
Epoch: [176]  [180/312]  eta: 0:02:26  lr: 0.001631  min_lr: 0.001631  loss: 2.2494 (2.1750)  weight_decay: 0.0500 (0.0500)  time: 1.0057  data: 0.0004  max mem: 78493
Epoch: [176]  [190/312]  eta: 0:02:14  lr: 0.001630  min_lr: 0.001630  loss: 2.2127 (2.1733)  weight_decay: 0.0500 (0.0500)  time: 1.0059  data: 0.0004  max mem: 78493
Epoch: [176]  [200/312]  eta: 0:02:02  lr: 0.001629  min_lr: 0.001629  loss: 2.1626 (2.1740)  weight_decay: 0.0500 (0.0500)  time: 1.0044  data: 0.0004  max mem: 78493
Epoch: [176]  [210/312]  eta: 0:01:51  lr: 0.001629  min_lr: 0.001629  loss: 2.2854 (2.1796)  weight_decay: 0.0500 (0.0500)  time: 1.0044  data: 0.0004  max mem: 78493
Epoch: [176]  [220/312]  eta: 0:01:40  lr: 0.001628  min_lr: 0.001628  loss: 2.3255 (2.1822)  weight_decay: 0.0500 (0.0500)  time: 1.0042  data: 0.0004  max mem: 78493
Epoch: [176]  [230/312]  eta: 0:01:28  lr: 0.001627  min_lr: 0.001627  loss: 2.2373 (2.1798)  weight_decay: 0.0500 (0.0500)  time: 1.0049  data: 0.0004  max mem: 78493
Epoch: [176]  [240/312]  eta: 0:01:17  lr: 0.001627  min_lr: 0.001627  loss: 2.2343 (2.1777)  weight_decay: 0.0500 (0.0500)  time: 1.0056  data: 0.0004  max mem: 78493
Epoch: [176]  [250/312]  eta: 0:01:06  lr: 0.001626  min_lr: 0.001626  loss: 2.2261 (2.1758)  weight_decay: 0.0500 (0.0500)  time: 1.0053  data: 0.0004  max mem: 78493
Epoch: [176]  [260/312]  eta: 0:00:55  lr: 0.001625  min_lr: 0.001625  loss: 2.2936 (2.1792)  weight_decay: 0.0500 (0.0500)  time: 1.0048  data: 0.0004  max mem: 78493
Epoch: [176]  [270/312]  eta: 0:00:45  lr: 0.001624  min_lr: 0.001624  loss: 2.2936 (2.1800)  weight_decay: 0.0500 (0.0500)  time: 1.0049  data: 0.0004  max mem: 78493
Epoch: [176]  [280/312]  eta: 0:00:34  lr: 0.001624  min_lr: 0.001624  loss: 2.3265 (2.1808)  weight_decay: 0.0500 (0.0500)  time: 1.0063  data: 0.0010  max mem: 78493
Epoch: [176]  [290/312]  eta: 0:00:23  lr: 0.001623  min_lr: 0.001623  loss: 2.3272 (2.1836)  weight_decay: 0.0500 (0.0500)  time: 1.0050  data: 0.0009  max mem: 78493
Epoch: [176]  [300/312]  eta: 0:00:12  lr: 0.001622  min_lr: 0.001622  loss: 2.2959 (2.1832)  weight_decay: 0.0500 (0.0500)  time: 1.0025  data: 0.0001  max mem: 78493
Epoch: [176]  [310/312]  eta: 0:00:02  lr: 0.001622  min_lr: 0.001622  loss: 2.3246 (2.1871)  weight_decay: 0.0500 (0.0500)  time: 1.0017  data: 0.0001  max mem: 78493
Epoch: [176]  [311/312]  eta: 0:00:01  lr: 0.001621  min_lr: 0.001621  loss: 2.1974 (2.1861)  weight_decay: 0.0500 (0.0500)  time: 1.0017  data: 0.0001  max mem: 78493
Epoch: [176] Total time: 0:05:33 (1.0694 s / it)
Averaged stats: lr: 0.001621  min_lr: 0.001621  loss: 2.1974 (2.1855)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:17  loss: 0.6396 (0.6396)  acc1: 85.0260 (85.0260)  acc5: 96.7448 (96.7448)  time: 8.5820  data: 8.3051  max mem: 78493
Test:  [8/9]  eta: 0:00:01  loss: 0.9411 (0.8640)  acc1: 76.6927 (77.6480)  acc5: 94.9219 (94.1920)  time: 1.1518  data: 0.9229  max mem: 78493
Test: Total time: 0:00:10 (1.1671 s / it)
* Acc@1 77.940 Acc@5 93.894 loss 0.853
Accuracy of the model on the 50000 test images: 77.9%
Max accuracy: 77.94%
Epoch: [177]  [  0/312]  eta: 1:23:15  lr: 0.001621  min_lr: 0.001621  loss: 2.2467 (2.2467)  weight_decay: 0.0500 (0.0500)  time: 16.0108  data: 14.4712  max mem: 78493
Epoch: [177]  [ 10/312]  eta: 0:13:19  lr: 0.001621  min_lr: 0.001621  loss: 2.2562 (2.2509)  weight_decay: 0.0500 (0.0500)  time: 2.6459  data: 1.4408  max mem: 78493
Epoch: [177]  [ 20/312]  eta: 0:09:04  lr: 0.001620  min_lr: 0.001620  loss: 2.1445 (2.1367)  weight_decay: 0.0500 (0.0500)  time: 1.1581  data: 0.0691  max mem: 78493
Epoch: [177]  [ 30/312]  eta: 0:07:27  lr: 0.001619  min_lr: 0.001619  loss: 2.1445 (2.1772)  weight_decay: 0.0500 (0.0500)  time: 1.0066  data: 0.0004  max mem: 78493
Epoch: [177]  [ 40/312]  eta: 0:06:33  lr: 0.001619  min_lr: 0.001619  loss: 2.1219 (2.1247)  weight_decay: 0.0500 (0.0500)  time: 1.0075  data: 0.0004  max mem: 78493
Epoch: [177]  [ 50/312]  eta: 0:05:56  lr: 0.001618  min_lr: 0.001618  loss: 2.0890 (2.1397)  weight_decay: 0.0500 (0.0500)  time: 1.0095  data: 0.0005  max mem: 78493
Epoch: [177]  [ 60/312]  eta: 0:05:28  lr: 0.001617  min_lr: 0.001617  loss: 2.2575 (2.1498)  weight_decay: 0.0500 (0.0500)  time: 1.0099  data: 0.0005  max mem: 78493
Epoch: [177]  [ 70/312]  eta: 0:05:05  lr: 0.001616  min_lr: 0.001616  loss: 2.0299 (2.1414)  weight_decay: 0.0500 (0.0500)  time: 1.0083  data: 0.0004  max mem: 78493
Epoch: [177]  [ 80/312]  eta: 0:04:45  lr: 0.001616  min_lr: 0.001616  loss: 2.0543 (2.1553)  weight_decay: 0.0500 (0.0500)  time: 1.0078  data: 0.0004  max mem: 78493
Epoch: [177]  [ 90/312]  eta: 0:04:27  lr: 0.001615  min_lr: 0.001615  loss: 2.3119 (2.1552)  weight_decay: 0.0500 (0.0500)  time: 1.0074  data: 0.0004  max mem: 78493
Epoch: [177]  [100/312]  eta: 0:04:11  lr: 0.001614  min_lr: 0.001614  loss: 2.2638 (2.1555)  weight_decay: 0.0500 (0.0500)  time: 1.0087  data: 0.0004  max mem: 78493
Epoch: [177]  [110/312]  eta: 0:03:56  lr: 0.001614  min_lr: 0.001614  loss: 2.2720 (2.1650)  weight_decay: 0.0500 (0.0500)  time: 1.0106  data: 0.0004  max mem: 78493
Epoch: [177]  [120/312]  eta: 0:03:42  lr: 0.001613  min_lr: 0.001613  loss: 2.3153 (2.1692)  weight_decay: 0.0500 (0.0500)  time: 1.0102  data: 0.0012  max mem: 78493
Epoch: [177]  [130/312]  eta: 0:03:28  lr: 0.001612  min_lr: 0.001612  loss: 2.3428 (2.1725)  weight_decay: 0.0500 (0.0500)  time: 1.0075  data: 0.0012  max mem: 78493
Epoch: [177]  [140/312]  eta: 0:03:15  lr: 0.001612  min_lr: 0.001612  loss: 2.3558 (2.1772)  weight_decay: 0.0500 (0.0500)  time: 1.0065  data: 0.0004  max mem: 78493
Epoch: [177]  [150/312]  eta: 0:03:02  lr: 0.001611  min_lr: 0.001611  loss: 2.3380 (2.1911)  weight_decay: 0.0500 (0.0500)  time: 1.0072  data: 0.0004  max mem: 78493
Epoch: [177]  [160/312]  eta: 0:02:50  lr: 0.001610  min_lr: 0.001610  loss: 2.2432 (2.1833)  weight_decay: 0.0500 (0.0500)  time: 1.0064  data: 0.0004  max mem: 78493
Epoch: [177]  [170/312]  eta: 0:02:38  lr: 0.001609  min_lr: 0.001609  loss: 2.0561 (2.1845)  weight_decay: 0.0500 (0.0500)  time: 1.0061  data: 0.0005  max mem: 78493
Epoch: [177]  [180/312]  eta: 0:02:26  lr: 0.001609  min_lr: 0.001609  loss: 2.1501 (2.1785)  weight_decay: 0.0500 (0.0500)  time: 1.0064  data: 0.0005  max mem: 78493
Epoch: [177]  [190/312]  eta: 0:02:14  lr: 0.001608  min_lr: 0.001608  loss: 2.2112 (2.1860)  weight_decay: 0.0500 (0.0500)  time: 1.0063  data: 0.0004  max mem: 78493
Epoch: [177]  [200/312]  eta: 0:02:02  lr: 0.001607  min_lr: 0.001607  loss: 2.3652 (2.1901)  weight_decay: 0.0500 (0.0500)  time: 1.0057  data: 0.0004  max mem: 78493
Epoch: [177]  [210/312]  eta: 0:01:51  lr: 0.001607  min_lr: 0.001607  loss: 2.2916 (2.1873)  weight_decay: 0.0500 (0.0500)  time: 1.0059  data: 0.0004  max mem: 78493
Epoch: [177]  [220/312]  eta: 0:01:40  lr: 0.001606  min_lr: 0.001606  loss: 2.2596 (2.1900)  weight_decay: 0.0500 (0.0500)  time: 1.0054  data: 0.0004  max mem: 78493
Epoch: [177]  [230/312]  eta: 0:01:28  lr: 0.001605  min_lr: 0.001605  loss: 2.3674 (2.1923)  weight_decay: 0.0500 (0.0500)  time: 1.0053  data: 0.0004  max mem: 78493
Epoch: [177]  [240/312]  eta: 0:01:17  lr: 0.001604  min_lr: 0.001604  loss: 2.2692 (2.1899)  weight_decay: 0.0500 (0.0500)  time: 1.0072  data: 0.0004  max mem: 78493
Epoch: [177]  [250/312]  eta: 0:01:06  lr: 0.001604  min_lr: 0.001604  loss: 2.3176 (2.1912)  weight_decay: 0.0500 (0.0500)  time: 1.0063  data: 0.0004  max mem: 78493
Epoch: [177]  [260/312]  eta: 0:00:55  lr: 0.001603  min_lr: 0.001603  loss: 2.3908 (2.1988)  weight_decay: 0.0500 (0.0500)  time: 1.0042  data: 0.0004  max mem: 78493
Epoch: [177]  [270/312]  eta: 0:00:45  lr: 0.001602  min_lr: 0.001602  loss: 2.3764 (2.2003)  weight_decay: 0.0500 (0.0500)  time: 1.0046  data: 0.0004  max mem: 78493
Epoch: [177]  [280/312]  eta: 0:00:34  lr: 0.001602  min_lr: 0.001602  loss: 2.1918 (2.1928)  weight_decay: 0.0500 (0.0500)  time: 1.0056  data: 0.0010  max mem: 78493
Epoch: [177]  [290/312]  eta: 0:00:23  lr: 0.001601  min_lr: 0.001601  loss: 2.2200 (2.1960)  weight_decay: 0.0500 (0.0500)  time: 1.0041  data: 0.0009  max mem: 78493
Epoch: [177]  [300/312]  eta: 0:00:12  lr: 0.001600  min_lr: 0.001600  loss: 2.2925 (2.1981)  weight_decay: 0.0500 (0.0500)  time: 1.0017  data: 0.0001  max mem: 78493
Epoch: [177]  [310/312]  eta: 0:00:02  lr: 0.001600  min_lr: 0.001600  loss: 2.3055 (2.2000)  weight_decay: 0.0500 (0.0500)  time: 1.0019  data: 0.0001  max mem: 78493
Epoch: [177]  [311/312]  eta: 0:00:01  lr: 0.001599  min_lr: 0.001599  loss: 2.3816 (2.2016)  weight_decay: 0.0500 (0.0500)  time: 1.0019  data: 0.0001  max mem: 78493
Epoch: [177] Total time: 0:05:33 (1.0696 s / it)
Averaged stats: lr: 0.001599  min_lr: 0.001599  loss: 2.3816 (2.1932)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:17  loss: 0.6430 (0.6430)  acc1: 84.2448 (84.2448)  acc5: 96.3542 (96.3542)  time: 8.6034  data: 8.3403  max mem: 78493
Test:  [8/9]  eta: 0:00:01  loss: 0.9574 (0.8694)  acc1: 76.3021 (77.4880)  acc5: 93.8802 (93.9360)  time: 1.1588  data: 0.9268  max mem: 78493
Test: Total time: 0:00:10 (1.1954 s / it)
* Acc@1 77.494 Acc@5 93.884 loss 0.865
Accuracy of the model on the 50000 test images: 77.5%
Max accuracy: 77.94%
Epoch: [178]  [  0/312]  eta: 1:23:47  lr: 0.001599  min_lr: 0.001599  loss: 2.4164 (2.4164)  weight_decay: 0.0500 (0.0500)  time: 16.1154  data: 13.9541  max mem: 78493
Epoch: [178]  [ 10/312]  eta: 0:13:16  lr: 0.001599  min_lr: 0.001599  loss: 2.1460 (2.0509)  weight_decay: 0.0500 (0.0500)  time: 2.6358  data: 1.2744  max mem: 78493
Epoch: [178]  [ 20/312]  eta: 0:09:03  lr: 0.001598  min_lr: 0.001598  loss: 2.2617 (2.1653)  weight_decay: 0.0500 (0.0500)  time: 1.1484  data: 0.0035  max mem: 78493
Epoch: [178]  [ 30/312]  eta: 0:07:27  lr: 0.001597  min_lr: 0.001597  loss: 2.4517 (2.2209)  weight_decay: 0.0500 (0.0500)  time: 1.0089  data: 0.0005  max mem: 78493
Epoch: [178]  [ 40/312]  eta: 0:06:33  lr: 0.001597  min_lr: 0.001597  loss: 2.3216 (2.1738)  weight_decay: 0.0500 (0.0500)  time: 1.0099  data: 0.0004  max mem: 78493
Epoch: [178]  [ 50/312]  eta: 0:05:56  lr: 0.001596  min_lr: 0.001596  loss: 2.2113 (2.1946)  weight_decay: 0.0500 (0.0500)  time: 1.0086  data: 0.0005  max mem: 78493
Epoch: [178]  [ 60/312]  eta: 0:05:28  lr: 0.001595  min_lr: 0.001595  loss: 2.2317 (2.1905)  weight_decay: 0.0500 (0.0500)  time: 1.0081  data: 0.0004  max mem: 78493
Epoch: [178]  [ 70/312]  eta: 0:05:05  lr: 0.001594  min_lr: 0.001594  loss: 2.2354 (2.2031)  weight_decay: 0.0500 (0.0500)  time: 1.0093  data: 0.0004  max mem: 78493
Epoch: [178]  [ 80/312]  eta: 0:04:45  lr: 0.001594  min_lr: 0.001594  loss: 2.2316 (2.1970)  weight_decay: 0.0500 (0.0500)  time: 1.0078  data: 0.0004  max mem: 78493
Epoch: [178]  [ 90/312]  eta: 0:04:27  lr: 0.001593  min_lr: 0.001593  loss: 2.2091 (2.2065)  weight_decay: 0.0500 (0.0500)  time: 1.0072  data: 0.0004  max mem: 78493
Epoch: [178]  [100/312]  eta: 0:04:11  lr: 0.001592  min_lr: 0.001592  loss: 2.2371 (2.2113)  weight_decay: 0.0500 (0.0500)  time: 1.0079  data: 0.0012  max mem: 78493
Epoch: [178]  [110/312]  eta: 0:03:56  lr: 0.001592  min_lr: 0.001592  loss: 2.1728 (2.1975)  weight_decay: 0.0500 (0.0500)  time: 1.0082  data: 0.0012  max mem: 78493
Epoch: [178]  [120/312]  eta: 0:03:42  lr: 0.001591  min_lr: 0.001591  loss: 2.0205 (2.1827)  weight_decay: 0.0500 (0.0500)  time: 1.0087  data: 0.0004  max mem: 78493
Epoch: [178]  [130/312]  eta: 0:03:28  lr: 0.001590  min_lr: 0.001590  loss: 2.1391 (2.1823)  weight_decay: 0.0500 (0.0500)  time: 1.0073  data: 0.0004  max mem: 78493
Epoch: [178]  [140/312]  eta: 0:03:15  lr: 0.001590  min_lr: 0.001590  loss: 2.2632 (2.1757)  weight_decay: 0.0500 (0.0500)  time: 1.0089  data: 0.0004  max mem: 78493
Epoch: [178]  [150/312]  eta: 0:03:02  lr: 0.001589  min_lr: 0.001589  loss: 2.2392 (2.1781)  weight_decay: 0.0500 (0.0500)  time: 1.0114  data: 0.0004  max mem: 78493
Epoch: [178]  [160/312]  eta: 0:02:50  lr: 0.001588  min_lr: 0.001588  loss: 2.2763 (2.1899)  weight_decay: 0.0500 (0.0500)  time: 1.0090  data: 0.0005  max mem: 78493
Epoch: [178]  [170/312]  eta: 0:02:38  lr: 0.001587  min_lr: 0.001587  loss: 2.2936 (2.1877)  weight_decay: 0.0500 (0.0500)  time: 1.0081  data: 0.0004  max mem: 78493
Epoch: [178]  [180/312]  eta: 0:02:26  lr: 0.001587  min_lr: 0.001587  loss: 2.0928 (2.1759)  weight_decay: 0.0500 (0.0500)  time: 1.0071  data: 0.0004  max mem: 78493
Epoch: [178]  [190/312]  eta: 0:02:14  lr: 0.001586  min_lr: 0.001586  loss: 2.0928 (2.1768)  weight_decay: 0.0500 (0.0500)  time: 1.0047  data: 0.0004  max mem: 78493
Epoch: [178]  [200/312]  eta: 0:02:02  lr: 0.001585  min_lr: 0.001585  loss: 2.1810 (2.1711)  weight_decay: 0.0500 (0.0500)  time: 1.0045  data: 0.0005  max mem: 78493
Epoch: [178]  [210/312]  eta: 0:01:51  lr: 0.001585  min_lr: 0.001585  loss: 2.1810 (2.1703)  weight_decay: 0.0500 (0.0500)  time: 1.0052  data: 0.0005  max mem: 78493
Epoch: [178]  [220/312]  eta: 0:01:40  lr: 0.001584  min_lr: 0.001584  loss: 2.2540 (2.1751)  weight_decay: 0.0500 (0.0500)  time: 1.0052  data: 0.0005  max mem: 78493
Epoch: [178]  [230/312]  eta: 0:01:28  lr: 0.001583  min_lr: 0.001583  loss: 2.2539 (2.1710)  weight_decay: 0.0500 (0.0500)  time: 1.0046  data: 0.0004  max mem: 78493
Epoch: [178]  [240/312]  eta: 0:01:17  lr: 0.001583  min_lr: 0.001583  loss: 2.2539 (2.1691)  weight_decay: 0.0500 (0.0500)  time: 1.0050  data: 0.0004  max mem: 78493
Epoch: [178]  [250/312]  eta: 0:01:06  lr: 0.001582  min_lr: 0.001582  loss: 2.2936 (2.1691)  weight_decay: 0.0500 (0.0500)  time: 1.0059  data: 0.0005  max mem: 78493
Epoch: [178]  [260/312]  eta: 0:00:55  lr: 0.001581  min_lr: 0.001581  loss: 2.2257 (2.1670)  weight_decay: 0.0500 (0.0500)  time: 1.0045  data: 0.0011  max mem: 78493
Epoch: [178]  [270/312]  eta: 0:00:45  lr: 0.001580  min_lr: 0.001580  loss: 2.2257 (2.1696)  weight_decay: 0.0500 (0.0500)  time: 1.0043  data: 0.0010  max mem: 78493
Epoch: [178]  [280/312]  eta: 0:00:34  lr: 0.001580  min_lr: 0.001580  loss: 2.2260 (2.1698)  weight_decay: 0.0500 (0.0500)  time: 1.0055  data: 0.0010  max mem: 78493
Epoch: [178]  [290/312]  eta: 0:00:23  lr: 0.001579  min_lr: 0.001579  loss: 2.0464 (2.1599)  weight_decay: 0.0500 (0.0500)  time: 1.0038  data: 0.0009  max mem: 78493
Epoch: [178]  [300/312]  eta: 0:00:12  lr: 0.001578  min_lr: 0.001578  loss: 1.9050 (2.1594)  weight_decay: 0.0500 (0.0500)  time: 1.0019  data: 0.0001  max mem: 78493
Epoch: [178]  [310/312]  eta: 0:00:02  lr: 0.001578  min_lr: 0.001578  loss: 2.1206 (2.1553)  weight_decay: 0.0500 (0.0500)  time: 1.0018  data: 0.0001  max mem: 78493
Epoch: [178]  [311/312]  eta: 0:00:01  lr: 0.001578  min_lr: 0.001578  loss: 2.2774 (2.1560)  weight_decay: 0.0500 (0.0500)  time: 1.0019  data: 0.0001  max mem: 78493
Epoch: [178] Total time: 0:05:33 (1.0697 s / it)
Averaged stats: lr: 0.001578  min_lr: 0.001578  loss: 2.2774 (2.1669)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:14  loss: 0.6176 (0.6176)  acc1: 84.5052 (84.5052)  acc5: 96.8750 (96.8750)  time: 8.2481  data: 7.9850  max mem: 78493
Test:  [8/9]  eta: 0:00:01  loss: 0.9553 (0.8695)  acc1: 77.8646 (77.3920)  acc5: 93.7500 (93.7760)  time: 1.1191  data: 0.8873  max mem: 78493
Test: Total time: 0:00:10 (1.1684 s / it)
* Acc@1 77.830 Acc@5 93.870 loss 0.860
Accuracy of the model on the 50000 test images: 77.8%
Max accuracy: 77.94%
Epoch: [179]  [  0/312]  eta: 1:25:31  lr: 0.001577  min_lr: 0.001577  loss: 2.3382 (2.3382)  weight_decay: 0.0500 (0.0500)  time: 16.4469  data: 12.0223  max mem: 78493
Epoch: [179]  [ 10/312]  eta: 0:13:07  lr: 0.001577  min_lr: 0.001577  loss: 2.3382 (2.1835)  weight_decay: 0.0500 (0.0500)  time: 2.6062  data: 1.1003  max mem: 78493
Epoch: [179]  [ 20/312]  eta: 0:08:59  lr: 0.001576  min_lr: 0.001576  loss: 2.3129 (2.2654)  weight_decay: 0.0500 (0.0500)  time: 1.1190  data: 0.0056  max mem: 78493
Epoch: [179]  [ 30/312]  eta: 0:07:24  lr: 0.001575  min_lr: 0.001575  loss: 2.2668 (2.2196)  weight_decay: 0.0500 (0.0500)  time: 1.0105  data: 0.0017  max mem: 78493
Epoch: [179]  [ 40/312]  eta: 0:06:31  lr: 0.001575  min_lr: 0.001575  loss: 2.1875 (2.1973)  weight_decay: 0.0500 (0.0500)  time: 1.0082  data: 0.0004  max mem: 78493
Epoch: [179]  [ 50/312]  eta: 0:05:54  lr: 0.001574  min_lr: 0.001574  loss: 2.2103 (2.2225)  weight_decay: 0.0500 (0.0500)  time: 1.0094  data: 0.0004  max mem: 78493
Epoch: [179]  [ 60/312]  eta: 0:05:26  lr: 0.001573  min_lr: 0.001573  loss: 2.1215 (2.1712)  weight_decay: 0.0500 (0.0500)  time: 1.0072  data: 0.0004  max mem: 78493
Epoch: [179]  [ 70/312]  eta: 0:05:03  lr: 0.001573  min_lr: 0.001573  loss: 2.1291 (2.1861)  weight_decay: 0.0500 (0.0500)  time: 1.0053  data: 0.0005  max mem: 78493
Epoch: [179]  [ 80/312]  eta: 0:04:44  lr: 0.001572  min_lr: 0.001572  loss: 2.3075 (2.1947)  weight_decay: 0.0500 (0.0500)  time: 1.0066  data: 0.0005  max mem: 78493
Epoch: [179]  [ 90/312]  eta: 0:04:26  lr: 0.001571  min_lr: 0.001571  loss: 2.2666 (2.1961)  weight_decay: 0.0500 (0.0500)  time: 1.0085  data: 0.0019  max mem: 78493
Epoch: [179]  [100/312]  eta: 0:04:10  lr: 0.001570  min_lr: 0.001570  loss: 2.2857 (2.1975)  weight_decay: 0.0500 (0.0500)  time: 1.0081  data: 0.0019  max mem: 78493
Epoch: [179]  [110/312]  eta: 0:03:55  lr: 0.001570  min_lr: 0.001570  loss: 2.2857 (2.2069)  weight_decay: 0.0500 (0.0500)  time: 1.0096  data: 0.0005  max mem: 78493
Epoch: [179]  [120/312]  eta: 0:03:41  lr: 0.001569  min_lr: 0.001569  loss: 2.2814 (2.2030)  weight_decay: 0.0500 (0.0500)  time: 1.0121  data: 0.0005  max mem: 78493
Epoch: [179]  [130/312]  eta: 0:03:28  lr: 0.001568  min_lr: 0.001568  loss: 2.4431 (2.2191)  weight_decay: 0.0500 (0.0500)  time: 1.0131  data: 0.0004  max mem: 78493
Epoch: [179]  [140/312]  eta: 0:03:15  lr: 0.001568  min_lr: 0.001568  loss: 2.4460 (2.2165)  weight_decay: 0.0500 (0.0500)  time: 1.0093  data: 0.0004  max mem: 78493
Epoch: [179]  [150/312]  eta: 0:03:02  lr: 0.001567  min_lr: 0.001567  loss: 2.2803 (2.2168)  weight_decay: 0.0500 (0.0500)  time: 1.0078  data: 0.0005  max mem: 78493
Epoch: [179]  [160/312]  eta: 0:02:49  lr: 0.001566  min_lr: 0.001566  loss: 2.2687 (2.2133)  weight_decay: 0.0500 (0.0500)  time: 1.0080  data: 0.0005  max mem: 78493
Epoch: [179]  [170/312]  eta: 0:02:37  lr: 0.001566  min_lr: 0.001566  loss: 2.2687 (2.2171)  weight_decay: 0.0500 (0.0500)  time: 1.0060  data: 0.0005  max mem: 78493
Epoch: [179]  [180/312]  eta: 0:02:25  lr: 0.001565  min_lr: 0.001565  loss: 2.0705 (2.2032)  weight_decay: 0.0500 (0.0500)  time: 1.0090  data: 0.0004  max mem: 78493
Epoch: [179]  [190/312]  eta: 0:02:14  lr: 0.001564  min_lr: 0.001564  loss: 2.1084 (2.2016)  weight_decay: 0.0500 (0.0500)  time: 1.0119  data: 0.0004  max mem: 78493
Epoch: [179]  [200/312]  eta: 0:02:02  lr: 0.001563  min_lr: 0.001563  loss: 2.2826 (2.2061)  weight_decay: 0.0500 (0.0500)  time: 1.0115  data: 0.0004  max mem: 78493
Epoch: [179]  [210/312]  eta: 0:01:51  lr: 0.001563  min_lr: 0.001563  loss: 2.3517 (2.2100)  weight_decay: 0.0500 (0.0500)  time: 1.0102  data: 0.0004  max mem: 78493
Epoch: [179]  [220/312]  eta: 0:01:40  lr: 0.001562  min_lr: 0.001562  loss: 2.3517 (2.2090)  weight_decay: 0.0500 (0.0500)  time: 1.0076  data: 0.0004  max mem: 78493
Epoch: [179]  [230/312]  eta: 0:01:28  lr: 0.001561  min_lr: 0.001561  loss: 2.1119 (2.2021)  weight_decay: 0.0500 (0.0500)  time: 1.0082  data: 0.0004  max mem: 78493
Epoch: [179]  [240/312]  eta: 0:01:17  lr: 0.001561  min_lr: 0.001561  loss: 2.0038 (2.2024)  weight_decay: 0.0500 (0.0500)  time: 1.0097  data: 0.0004  max mem: 78493
Epoch: [179]  [250/312]  eta: 0:01:06  lr: 0.001560  min_lr: 0.001560  loss: 2.0546 (2.1969)  weight_decay: 0.0500 (0.0500)  time: 1.0083  data: 0.0005  max mem: 78493
Epoch: [179]  [260/312]  eta: 0:00:55  lr: 0.001559  min_lr: 0.001559  loss: 2.1213 (2.1989)  weight_decay: 0.0500 (0.0500)  time: 1.0070  data: 0.0005  max mem: 78493
Epoch: [179]  [270/312]  eta: 0:00:45  lr: 0.001559  min_lr: 0.001559  loss: 2.1329 (2.1960)  weight_decay: 0.0500 (0.0500)  time: 1.0063  data: 0.0005  max mem: 78493
Epoch: [179]  [280/312]  eta: 0:00:34  lr: 0.001558  min_lr: 0.001558  loss: 2.0553 (2.1900)  weight_decay: 0.0500 (0.0500)  time: 1.0057  data: 0.0010  max mem: 78493
Epoch: [179]  [290/312]  eta: 0:00:23  lr: 0.001557  min_lr: 0.001557  loss: 2.1579 (2.1917)  weight_decay: 0.0500 (0.0500)  time: 1.0035  data: 0.0009  max mem: 78493
Epoch: [179]  [300/312]  eta: 0:00:12  lr: 0.001556  min_lr: 0.001556  loss: 2.2268 (2.1880)  weight_decay: 0.0500 (0.0500)  time: 1.0018  data: 0.0001  max mem: 78493
Epoch: [179]  [310/312]  eta: 0:00:02  lr: 0.001556  min_lr: 0.001556  loss: 1.9336 (2.1854)  weight_decay: 0.0500 (0.0500)  time: 1.0019  data: 0.0001  max mem: 78493
Epoch: [179]  [311/312]  eta: 0:00:01  lr: 0.001556  min_lr: 0.001556  loss: 1.9336 (2.1839)  weight_decay: 0.0500 (0.0500)  time: 1.0019  data: 0.0001  max mem: 78493
Epoch: [179] Total time: 0:05:33 (1.0701 s / it)
Averaged stats: lr: 0.001556  min_lr: 0.001556  loss: 1.9336 (2.1828)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:13  loss: 0.6265 (0.6265)  acc1: 84.2448 (84.2448)  acc5: 96.6146 (96.6146)  time: 8.1128  data: 7.8328  max mem: 78493
Test:  [8/9]  eta: 0:00:01  loss: 0.9468 (0.8545)  acc1: 77.6042 (77.4880)  acc5: 93.7500 (94.0960)  time: 1.0996  data: 0.8704  max mem: 78493
Test: Total time: 0:00:10 (1.1245 s / it)
* Acc@1 77.862 Acc@5 94.024 loss 0.849
Accuracy of the model on the 50000 test images: 77.9%
Max accuracy: 77.94%
Epoch: [180]  [  0/312]  eta: 1:27:19  lr: 0.001556  min_lr: 0.001556  loss: 2.4004 (2.4004)  weight_decay: 0.0500 (0.0500)  time: 16.7941  data: 13.6731  max mem: 78493
Epoch: [180]  [ 10/312]  eta: 0:13:31  lr: 0.001555  min_lr: 0.001555  loss: 2.1786 (2.2290)  weight_decay: 0.0500 (0.0500)  time: 2.6863  data: 1.3155  max mem: 78493
Epoch: [180]  [ 20/312]  eta: 0:09:12  lr: 0.001554  min_lr: 0.001554  loss: 2.0851 (2.1351)  weight_decay: 0.0500 (0.0500)  time: 1.1472  data: 0.0401  max mem: 78493
Epoch: [180]  [ 30/312]  eta: 0:07:33  lr: 0.001553  min_lr: 0.001553  loss: 2.3178 (2.2185)  weight_decay: 0.0500 (0.0500)  time: 1.0127  data: 0.0005  max mem: 78493
Epoch: [180]  [ 40/312]  eta: 0:06:37  lr: 0.001553  min_lr: 0.001553  loss: 2.2954 (2.1914)  weight_decay: 0.0500 (0.0500)  time: 1.0078  data: 0.0004  max mem: 78493
Epoch: [180]  [ 50/312]  eta: 0:05:59  lr: 0.001552  min_lr: 0.001552  loss: 2.2090 (2.1565)  weight_decay: 0.0500 (0.0500)  time: 1.0095  data: 0.0005  max mem: 78493
Epoch: [180]  [ 60/312]  eta: 0:05:30  lr: 0.001551  min_lr: 0.001551  loss: 2.1430 (2.1768)  weight_decay: 0.0500 (0.0500)  time: 1.0107  data: 0.0005  max mem: 78493
Epoch: [180]  [ 70/312]  eta: 0:05:07  lr: 0.001551  min_lr: 0.001551  loss: 2.1430 (2.1498)  weight_decay: 0.0500 (0.0500)  time: 1.0105  data: 0.0005  max mem: 78493
Epoch: [180]  [ 80/312]  eta: 0:04:47  lr: 0.001550  min_lr: 0.001550  loss: 2.2269 (2.1828)  weight_decay: 0.0500 (0.0500)  time: 1.0081  data: 0.0004  max mem: 78493
Epoch: [180]  [ 90/312]  eta: 0:04:29  lr: 0.001549  min_lr: 0.001549  loss: 2.3467 (2.1990)  weight_decay: 0.0500 (0.0500)  time: 1.0078  data: 0.0004  max mem: 78493
Epoch: [180]  [100/312]  eta: 0:04:12  lr: 0.001549  min_lr: 0.001549  loss: 2.2063 (2.1791)  weight_decay: 0.0500 (0.0500)  time: 1.0090  data: 0.0004  max mem: 78493
Epoch: [180]  [110/312]  eta: 0:03:57  lr: 0.001548  min_lr: 0.001548  loss: 2.2063 (2.1844)  weight_decay: 0.0500 (0.0500)  time: 1.0061  data: 0.0004  max mem: 78493
Epoch: [180]  [120/312]  eta: 0:03:43  lr: 0.001547  min_lr: 0.001547  loss: 2.2687 (2.1890)  weight_decay: 0.0500 (0.0500)  time: 1.0070  data: 0.0004  max mem: 78493
Epoch: [180]  [130/312]  eta: 0:03:29  lr: 0.001546  min_lr: 0.001546  loss: 2.2318 (2.1830)  weight_decay: 0.0500 (0.0500)  time: 1.0089  data: 0.0004  max mem: 78493
Epoch: [180]  [140/312]  eta: 0:03:16  lr: 0.001546  min_lr: 0.001546  loss: 2.1522 (2.1883)  weight_decay: 0.0500 (0.0500)  time: 1.0079  data: 0.0004  max mem: 78493
Epoch: [180]  [150/312]  eta: 0:03:03  lr: 0.001545  min_lr: 0.001545  loss: 2.1501 (2.1938)  weight_decay: 0.0500 (0.0500)  time: 1.0081  data: 0.0004  max mem: 78493
Epoch: [180]  [160/312]  eta: 0:02:50  lr: 0.001544  min_lr: 0.001544  loss: 2.4064 (2.2148)  weight_decay: 0.0500 (0.0500)  time: 1.0070  data: 0.0005  max mem: 78493
Epoch: [180]  [170/312]  eta: 0:02:38  lr: 0.001544  min_lr: 0.001544  loss: 2.4064 (2.2149)  weight_decay: 0.0500 (0.0500)  time: 1.0076  data: 0.0004  max mem: 78493
Epoch: [180]  [180/312]  eta: 0:02:26  lr: 0.001543  min_lr: 0.001543  loss: 2.3392 (2.2168)  weight_decay: 0.0500 (0.0500)  time: 1.0084  data: 0.0004  max mem: 78493
Epoch: [180]  [190/312]  eta: 0:02:14  lr: 0.001542  min_lr: 0.001542  loss: 2.0916 (2.2058)  weight_decay: 0.0500 (0.0500)  time: 1.0089  data: 0.0004  max mem: 78493
Epoch: [180]  [200/312]  eta: 0:02:03  lr: 0.001542  min_lr: 0.001542  loss: 2.1332 (2.2133)  weight_decay: 0.0500 (0.0500)  time: 1.0106  data: 0.0004  max mem: 78493
Epoch: [180]  [210/312]  eta: 0:01:51  lr: 0.001541  min_lr: 0.001541  loss: 2.3011 (2.2140)  weight_decay: 0.0500 (0.0500)  time: 1.0094  data: 0.0004  max mem: 78493
Epoch: [180]  [220/312]  eta: 0:01:40  lr: 0.001540  min_lr: 0.001540  loss: 2.3644 (2.2227)  weight_decay: 0.0500 (0.0500)  time: 1.0079  data: 0.0004  max mem: 78493
Epoch: [180]  [230/312]  eta: 0:01:29  lr: 0.001539  min_lr: 0.001539  loss: 2.4102 (2.2251)  weight_decay: 0.0500 (0.0500)  time: 1.0070  data: 0.0004  max mem: 78493
Epoch: [180]  [240/312]  eta: 0:01:18  lr: 0.001539  min_lr: 0.001539  loss: 2.3080 (2.2255)  weight_decay: 0.0500 (0.0500)  time: 1.0059  data: 0.0004  max mem: 78493
Epoch: [180]  [250/312]  eta: 0:01:07  lr: 0.001538  min_lr: 0.001538  loss: 2.2243 (2.2226)  weight_decay: 0.0500 (0.0500)  time: 1.0071  data: 0.0004  max mem: 78493
Epoch: [180]  [260/312]  eta: 0:00:56  lr: 0.001537  min_lr: 0.001537  loss: 2.2243 (2.2249)  weight_decay: 0.0500 (0.0500)  time: 1.0064  data: 0.0004  max mem: 78493
Epoch: [180]  [270/312]  eta: 0:00:45  lr: 0.001537  min_lr: 0.001537  loss: 2.1720 (2.2207)  weight_decay: 0.0500 (0.0500)  time: 1.0046  data: 0.0004  max mem: 78493
Epoch: [180]  [280/312]  eta: 0:00:34  lr: 0.001536  min_lr: 0.001536  loss: 2.0442 (2.2157)  weight_decay: 0.0500 (0.0500)  time: 1.0070  data: 0.0010  max mem: 78493
Epoch: [180]  [290/312]  eta: 0:00:23  lr: 0.001535  min_lr: 0.001535  loss: 2.2515 (2.2175)  weight_decay: 0.0500 (0.0500)  time: 1.0058  data: 0.0009  max mem: 78493
Epoch: [180]  [300/312]  eta: 0:00:12  lr: 0.001535  min_lr: 0.001535  loss: 2.2514 (2.2101)  weight_decay: 0.0500 (0.0500)  time: 1.0015  data: 0.0001  max mem: 78493
Epoch: [180]  [310/312]  eta: 0:00:02  lr: 0.001534  min_lr: 0.001534  loss: 2.2514 (2.2118)  weight_decay: 0.0500 (0.0500)  time: 1.0016  data: 0.0001  max mem: 78493
Epoch: [180]  [311/312]  eta: 0:00:01  lr: 0.001534  min_lr: 0.001534  loss: 2.2514 (2.2094)  weight_decay: 0.0500 (0.0500)  time: 1.0015  data: 0.0001  max mem: 78493
Epoch: [180] Total time: 0:05:34 (1.0725 s / it)
Averaged stats: lr: 0.001534  min_lr: 0.001534  loss: 2.2514 (2.1750)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:17  loss: 0.5779 (0.5779)  acc1: 85.4167 (85.4167)  acc5: 97.0052 (97.0052)  time: 8.6326  data: 8.3507  max mem: 78493
Test:  [8/9]  eta: 0:00:01  loss: 0.8992 (0.8394)  acc1: 78.1250 (78.4000)  acc5: 94.7917 (94.0960)  time: 1.1574  data: 0.9279  max mem: 78493
Test: Total time: 0:00:10 (1.1689 s / it)
* Acc@1 78.402 Acc@5 94.278 loss 0.828
Accuracy of the model on the 50000 test images: 78.4%
Max accuracy: 78.40%
Epoch: [181]  [  0/312]  eta: 1:21:53  lr: 0.001534  min_lr: 0.001534  loss: 2.4312 (2.4312)  weight_decay: 0.0500 (0.0500)  time: 15.7470  data: 14.2040  max mem: 78493
Epoch: [181]  [ 10/312]  eta: 0:12:41  lr: 0.001533  min_lr: 0.001533  loss: 2.2556 (2.2368)  weight_decay: 0.0500 (0.0500)  time: 2.5211  data: 1.3780  max mem: 78493
Epoch: [181]  [ 20/312]  eta: 0:08:47  lr: 0.001532  min_lr: 0.001532  loss: 2.2525 (2.2232)  weight_decay: 0.0500 (0.0500)  time: 1.1100  data: 0.0510  max mem: 78493
Epoch: [181]  [ 30/312]  eta: 0:07:16  lr: 0.001532  min_lr: 0.001532  loss: 2.2518 (2.2024)  weight_decay: 0.0500 (0.0500)  time: 1.0152  data: 0.0036  max mem: 78493
Epoch: [181]  [ 40/312]  eta: 0:06:25  lr: 0.001531  min_lr: 0.001531  loss: 2.1915 (2.2134)  weight_decay: 0.0500 (0.0500)  time: 1.0084  data: 0.0005  max mem: 78493
Epoch: [181]  [ 50/312]  eta: 0:05:50  lr: 0.001530  min_lr: 0.001530  loss: 2.2858 (2.2110)  weight_decay: 0.0500 (0.0500)  time: 1.0097  data: 0.0005  max mem: 78493
Epoch: [181]  [ 60/312]  eta: 0:05:23  lr: 0.001530  min_lr: 0.001530  loss: 2.2599 (2.1824)  weight_decay: 0.0500 (0.0500)  time: 1.0107  data: 0.0004  max mem: 78493
Epoch: [181]  [ 70/312]  eta: 0:05:01  lr: 0.001529  min_lr: 0.001529  loss: 2.1102 (2.1778)  weight_decay: 0.0500 (0.0500)  time: 1.0100  data: 0.0004  max mem: 78493
Epoch: [181]  [ 80/312]  eta: 0:04:42  lr: 0.001528  min_lr: 0.001528  loss: 2.3024 (2.1862)  weight_decay: 0.0500 (0.0500)  time: 1.0100  data: 0.0004  max mem: 78493
Epoch: [181]  [ 90/312]  eta: 0:04:24  lr: 0.001527  min_lr: 0.001527  loss: 2.1986 (2.1846)  weight_decay: 0.0500 (0.0500)  time: 1.0090  data: 0.0004  max mem: 78493
Epoch: [181]  [100/312]  eta: 0:04:09  lr: 0.001527  min_lr: 0.001527  loss: 1.9684 (2.1609)  weight_decay: 0.0500 (0.0500)  time: 1.0079  data: 0.0004  max mem: 78493
Epoch: [181]  [110/312]  eta: 0:03:54  lr: 0.001526  min_lr: 0.001526  loss: 1.9689 (2.1629)  weight_decay: 0.0500 (0.0500)  time: 1.0077  data: 0.0004  max mem: 78493
Epoch: [181]  [120/312]  eta: 0:03:40  lr: 0.001525  min_lr: 0.001525  loss: 2.2500 (2.1608)  weight_decay: 0.0500 (0.0500)  time: 1.0068  data: 0.0004  max mem: 78493
Epoch: [181]  [130/312]  eta: 0:03:26  lr: 0.001525  min_lr: 0.001525  loss: 2.2541 (2.1676)  weight_decay: 0.0500 (0.0500)  time: 1.0053  data: 0.0004  max mem: 78493
Epoch: [181]  [140/312]  eta: 0:03:13  lr: 0.001524  min_lr: 0.001524  loss: 2.2823 (2.1697)  weight_decay: 0.0500 (0.0500)  time: 1.0058  data: 0.0005  max mem: 78493
Epoch: [181]  [150/312]  eta: 0:03:01  lr: 0.001523  min_lr: 0.001523  loss: 2.2730 (2.1735)  weight_decay: 0.0500 (0.0500)  time: 1.0082  data: 0.0005  max mem: 78493
Epoch: [181]  [160/312]  eta: 0:02:49  lr: 0.001523  min_lr: 0.001523  loss: 2.2538 (2.1728)  weight_decay: 0.0500 (0.0500)  time: 1.0084  data: 0.0005  max mem: 78493
Epoch: [181]  [170/312]  eta: 0:02:37  lr: 0.001522  min_lr: 0.001522  loss: 2.2002 (2.1701)  weight_decay: 0.0500 (0.0500)  time: 1.0064  data: 0.0006  max mem: 78493
Epoch: [181]  [180/312]  eta: 0:02:25  lr: 0.001521  min_lr: 0.001521  loss: 2.2105 (2.1778)  weight_decay: 0.0500 (0.0500)  time: 1.0054  data: 0.0006  max mem: 78493
Epoch: [181]  [190/312]  eta: 0:02:13  lr: 0.001520  min_lr: 0.001520  loss: 2.2263 (2.1761)  weight_decay: 0.0500 (0.0500)  time: 1.0040  data: 0.0004  max mem: 78493
Epoch: [181]  [200/312]  eta: 0:02:02  lr: 0.001520  min_lr: 0.001520  loss: 2.2131 (2.1771)  weight_decay: 0.0500 (0.0500)  time: 1.0032  data: 0.0005  max mem: 78493
Epoch: [181]  [210/312]  eta: 0:01:50  lr: 0.001519  min_lr: 0.001519  loss: 2.2546 (2.1833)  weight_decay: 0.0500 (0.0500)  time: 1.0049  data: 0.0005  max mem: 78493
Epoch: [181]  [220/312]  eta: 0:01:39  lr: 0.001518  min_lr: 0.001518  loss: 2.3332 (2.1831)  weight_decay: 0.0500 (0.0500)  time: 1.0055  data: 0.0004  max mem: 78493
Epoch: [181]  [230/312]  eta: 0:01:28  lr: 0.001518  min_lr: 0.001518  loss: 2.2894 (2.1807)  weight_decay: 0.0500 (0.0500)  time: 1.0056  data: 0.0004  max mem: 78493
Epoch: [181]  [240/312]  eta: 0:01:17  lr: 0.001517  min_lr: 0.001517  loss: 2.2378 (2.1789)  weight_decay: 0.0500 (0.0500)  time: 1.0057  data: 0.0005  max mem: 78493
Epoch: [181]  [250/312]  eta: 0:01:06  lr: 0.001516  min_lr: 0.001516  loss: 2.2378 (2.1800)  weight_decay: 0.0500 (0.0500)  time: 1.0051  data: 0.0005  max mem: 78493
Epoch: [181]  [260/312]  eta: 0:00:55  lr: 0.001516  min_lr: 0.001516  loss: 2.2708 (2.1801)  weight_decay: 0.0500 (0.0500)  time: 1.0058  data: 0.0005  max mem: 78493
Epoch: [181]  [270/312]  eta: 0:00:44  lr: 0.001515  min_lr: 0.001515  loss: 2.2332 (2.1778)  weight_decay: 0.0500 (0.0500)  time: 1.0059  data: 0.0005  max mem: 78493
Epoch: [181]  [280/312]  eta: 0:00:34  lr: 0.001514  min_lr: 0.001514  loss: 2.1271 (2.1756)  weight_decay: 0.0500 (0.0500)  time: 1.0060  data: 0.0010  max mem: 78493
Epoch: [181]  [290/312]  eta: 0:00:23  lr: 0.001513  min_lr: 0.001513  loss: 2.1271 (2.1736)  weight_decay: 0.0500 (0.0500)  time: 1.0040  data: 0.0009  max mem: 78493
Epoch: [181]  [300/312]  eta: 0:00:12  lr: 0.001513  min_lr: 0.001513  loss: 2.3109 (2.1774)  weight_decay: 0.0500 (0.0500)  time: 1.0022  data: 0.0001  max mem: 78493
Epoch: [181]  [310/312]  eta: 0:00:02  lr: 0.001512  min_lr: 0.001512  loss: 2.2955 (2.1790)  weight_decay: 0.0500 (0.0500)  time: 1.0020  data: 0.0001  max mem: 78493
Epoch: [181]  [311/312]  eta: 0:00:01  lr: 0.001512  min_lr: 0.001512  loss: 2.2955 (2.1778)  weight_decay: 0.0500 (0.0500)  time: 1.0019  data: 0.0001  max mem: 78493
Epoch: [181] Total time: 0:05:32 (1.0659 s / it)
Averaged stats: lr: 0.001512  min_lr: 0.001512  loss: 2.2955 (2.1755)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:08  loss: 0.6014 (0.6014)  acc1: 84.1146 (84.1146)  acc5: 96.6146 (96.6146)  time: 7.6390  data: 7.3517  max mem: 78493
Test:  [8/9]  eta: 0:00:01  loss: 0.9053 (0.8449)  acc1: 76.0417 (77.2800)  acc5: 94.7917 (94.3040)  time: 1.0468  data: 0.8169  max mem: 78493
Test: Total time: 0:00:09 (1.0629 s / it)
* Acc@1 78.268 Acc@5 94.190 loss 0.834
Accuracy of the model on the 50000 test images: 78.3%
Max accuracy: 78.40%
Epoch: [182]  [  0/312]  eta: 1:20:10  lr: 0.001512  min_lr: 0.001512  loss: 2.5625 (2.5625)  weight_decay: 0.0500 (0.0500)  time: 15.4179  data: 11.8371  max mem: 78493
Epoch: [182]  [ 10/312]  eta: 0:13:04  lr: 0.001511  min_lr: 0.001511  loss: 2.2739 (2.2628)  weight_decay: 0.0500 (0.0500)  time: 2.5982  data: 1.0847  max mem: 78493
Epoch: [182]  [ 20/312]  eta: 0:08:59  lr: 0.001511  min_lr: 0.001511  loss: 2.1671 (2.1753)  weight_decay: 0.0500 (0.0500)  time: 1.1704  data: 0.0051  max mem: 78493
Epoch: [182]  [ 30/312]  eta: 0:07:24  lr: 0.001510  min_lr: 0.001510  loss: 2.2022 (2.1549)  weight_decay: 0.0500 (0.0500)  time: 1.0155  data: 0.0005  max mem: 78493
Epoch: [182]  [ 40/312]  eta: 0:06:31  lr: 0.001509  min_lr: 0.001509  loss: 2.2167 (2.1899)  weight_decay: 0.0500 (0.0500)  time: 1.0064  data: 0.0005  max mem: 78493
Epoch: [182]  [ 50/312]  eta: 0:05:54  lr: 0.001508  min_lr: 0.001508  loss: 2.2723 (2.1943)  weight_decay: 0.0500 (0.0500)  time: 1.0057  data: 0.0005  max mem: 78493
Epoch: [182]  [ 60/312]  eta: 0:05:26  lr: 0.001508  min_lr: 0.001508  loss: 2.2723 (2.2146)  weight_decay: 0.0500 (0.0500)  time: 1.0063  data: 0.0005  max mem: 78493
Epoch: [182]  [ 70/312]  eta: 0:05:03  lr: 0.001507  min_lr: 0.001507  loss: 2.2341 (2.2092)  weight_decay: 0.0500 (0.0500)  time: 1.0069  data: 0.0004  max mem: 78493
Epoch: [182]  [ 80/312]  eta: 0:04:44  lr: 0.001506  min_lr: 0.001506  loss: 2.1992 (2.2048)  weight_decay: 0.0500 (0.0500)  time: 1.0049  data: 0.0004  max mem: 78493
Epoch: [182]  [ 90/312]  eta: 0:04:26  lr: 0.001506  min_lr: 0.001506  loss: 2.0478 (2.1773)  weight_decay: 0.0500 (0.0500)  time: 1.0039  data: 0.0004  max mem: 78493
Epoch: [182]  [100/312]  eta: 0:04:10  lr: 0.001505  min_lr: 0.001505  loss: 2.1535 (2.1811)  weight_decay: 0.0500 (0.0500)  time: 1.0055  data: 0.0004  max mem: 78493
Epoch: [182]  [110/312]  eta: 0:03:55  lr: 0.001504  min_lr: 0.001504  loss: 2.0904 (2.1627)  weight_decay: 0.0500 (0.0500)  time: 1.0069  data: 0.0004  max mem: 78493
Epoch: [182]  [120/312]  eta: 0:03:41  lr: 0.001504  min_lr: 0.001504  loss: 2.1505 (2.1767)  weight_decay: 0.0500 (0.0500)  time: 1.0069  data: 0.0004  max mem: 78493
Epoch: [182]  [130/312]  eta: 0:03:27  lr: 0.001503  min_lr: 0.001503  loss: 2.2967 (2.1774)  weight_decay: 0.0500 (0.0500)  time: 1.0065  data: 0.0004  max mem: 78493
Epoch: [182]  [140/312]  eta: 0:03:14  lr: 0.001502  min_lr: 0.001502  loss: 2.1877 (2.1793)  weight_decay: 0.0500 (0.0500)  time: 1.0065  data: 0.0004  max mem: 78493
Epoch: [182]  [150/312]  eta: 0:03:01  lr: 0.001501  min_lr: 0.001501  loss: 2.0373 (2.1684)  weight_decay: 0.0500 (0.0500)  time: 1.0070  data: 0.0004  max mem: 78493
Epoch: [182]  [160/312]  eta: 0:02:49  lr: 0.001501  min_lr: 0.001501  loss: 2.1838 (2.1720)  weight_decay: 0.0500 (0.0500)  time: 1.0083  data: 0.0004  max mem: 78493
Epoch: [182]  [170/312]  eta: 0:02:37  lr: 0.001500  min_lr: 0.001500  loss: 2.2971 (2.1659)  weight_decay: 0.0500 (0.0500)  time: 1.0080  data: 0.0004  max mem: 78493
Epoch: [182]  [180/312]  eta: 0:02:25  lr: 0.001499  min_lr: 0.001499  loss: 2.2384 (2.1675)  weight_decay: 0.0500 (0.0500)  time: 1.0065  data: 0.0004  max mem: 78493
Epoch: [182]  [190/312]  eta: 0:02:14  lr: 0.001499  min_lr: 0.001499  loss: 2.3169 (2.1684)  weight_decay: 0.0500 (0.0500)  time: 1.0068  data: 0.0005  max mem: 78493
Epoch: [182]  [200/312]  eta: 0:02:02  lr: 0.001498  min_lr: 0.001498  loss: 2.3666 (2.1718)  weight_decay: 0.0500 (0.0500)  time: 1.0076  data: 0.0004  max mem: 78493
Epoch: [182]  [210/312]  eta: 0:01:51  lr: 0.001497  min_lr: 0.001497  loss: 2.1912 (2.1702)  weight_decay: 0.0500 (0.0500)  time: 1.0061  data: 0.0004  max mem: 78493
Epoch: [182]  [220/312]  eta: 0:01:39  lr: 0.001497  min_lr: 0.001497  loss: 2.1328 (2.1626)  weight_decay: 0.0500 (0.0500)  time: 1.0043  data: 0.0004  max mem: 78493
Epoch: [182]  [230/312]  eta: 0:01:28  lr: 0.001496  min_lr: 0.001496  loss: 2.3072 (2.1672)  weight_decay: 0.0500 (0.0500)  time: 1.0055  data: 0.0005  max mem: 78493
Epoch: [182]  [240/312]  eta: 0:01:17  lr: 0.001495  min_lr: 0.001495  loss: 2.2771 (2.1598)  weight_decay: 0.0500 (0.0500)  time: 1.0058  data: 0.0005  max mem: 78493
Epoch: [182]  [250/312]  eta: 0:01:06  lr: 0.001495  min_lr: 0.001495  loss: 2.1052 (2.1566)  weight_decay: 0.0500 (0.0500)  time: 1.0061  data: 0.0005  max mem: 78493
Epoch: [182]  [260/312]  eta: 0:00:55  lr: 0.001494  min_lr: 0.001494  loss: 2.1697 (2.1542)  weight_decay: 0.0500 (0.0500)  time: 1.0071  data: 0.0005  max mem: 78493
Epoch: [182]  [270/312]  eta: 0:00:45  lr: 0.001493  min_lr: 0.001493  loss: 2.2942 (2.1626)  weight_decay: 0.0500 (0.0500)  time: 1.0054  data: 0.0005  max mem: 78493
Epoch: [182]  [280/312]  eta: 0:00:34  lr: 0.001492  min_lr: 0.001492  loss: 2.3379 (2.1687)  weight_decay: 0.0500 (0.0500)  time: 1.0062  data: 0.0011  max mem: 78493
Epoch: [182]  [290/312]  eta: 0:00:23  lr: 0.001492  min_lr: 0.001492  loss: 2.2885 (2.1619)  weight_decay: 0.0500 (0.0500)  time: 1.0053  data: 0.0009  max mem: 78493
Epoch: [182]  [300/312]  eta: 0:00:12  lr: 0.001491  min_lr: 0.001491  loss: 2.0548 (2.1588)  weight_decay: 0.0500 (0.0500)  time: 1.0019  data: 0.0001  max mem: 78493
Epoch: [182]  [310/312]  eta: 0:00:02  lr: 0.001490  min_lr: 0.001490  loss: 2.1030 (2.1602)  weight_decay: 0.0500 (0.0500)  time: 1.0016  data: 0.0001  max mem: 78493
Epoch: [182]  [311/312]  eta: 0:00:01  lr: 0.001490  min_lr: 0.001490  loss: 2.1600 (2.1611)  weight_decay: 0.0500 (0.0500)  time: 1.0017  data: 0.0001  max mem: 78493
Epoch: [182] Total time: 0:05:33 (1.0681 s / it)
Averaged stats: lr: 0.001490  min_lr: 0.001490  loss: 2.1600 (2.1712)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:21  loss: 0.6137 (0.6137)  acc1: 84.6354 (84.6354)  acc5: 96.6146 (96.6146)  time: 9.0017  data: 8.7381  max mem: 78493
Test:  [8/9]  eta: 0:00:01  loss: 0.9251 (0.8540)  acc1: 77.2135 (77.3920)  acc5: 95.5729 (94.3680)  time: 1.2016  data: 0.9710  max mem: 78493
Test: Total time: 0:00:11 (1.2457 s / it)
* Acc@1 78.216 Acc@5 94.198 loss 0.839
Accuracy of the model on the 50000 test images: 78.2%
Max accuracy: 78.40%
Epoch: [183]  [  0/312]  eta: 1:23:53  lr: 0.001490  min_lr: 0.001490  loss: 1.8150 (1.8150)  weight_decay: 0.0500 (0.0500)  time: 16.1332  data: 12.0053  max mem: 78493
Epoch: [183]  [ 10/312]  eta: 0:13:11  lr: 0.001490  min_lr: 0.001490  loss: 2.3674 (2.2176)  weight_decay: 0.0500 (0.0500)  time: 2.6220  data: 1.3127  max mem: 78493
Epoch: [183]  [ 20/312]  eta: 0:09:01  lr: 0.001489  min_lr: 0.001489  loss: 2.3339 (2.1632)  weight_decay: 0.0500 (0.0500)  time: 1.1411  data: 0.1220  max mem: 78493
Epoch: [183]  [ 30/312]  eta: 0:07:25  lr: 0.001488  min_lr: 0.001488  loss: 2.3140 (2.2340)  weight_decay: 0.0500 (0.0500)  time: 1.0072  data: 0.0005  max mem: 78493
Epoch: [183]  [ 40/312]  eta: 0:06:31  lr: 0.001487  min_lr: 0.001487  loss: 2.2743 (2.1472)  weight_decay: 0.0500 (0.0500)  time: 1.0030  data: 0.0005  max mem: 78493
Epoch: [183]  [ 50/312]  eta: 0:05:54  lr: 0.001487  min_lr: 0.001487  loss: 2.2592 (2.1811)  weight_decay: 0.0500 (0.0500)  time: 1.0048  data: 0.0005  max mem: 78493
Epoch: [183]  [ 60/312]  eta: 0:05:26  lr: 0.001486  min_lr: 0.001486  loss: 2.2429 (2.1806)  weight_decay: 0.0500 (0.0500)  time: 1.0049  data: 0.0005  max mem: 78493
Epoch: [183]  [ 70/312]  eta: 0:05:04  lr: 0.001485  min_lr: 0.001485  loss: 2.2047 (2.1818)  weight_decay: 0.0500 (0.0500)  time: 1.0067  data: 0.0005  max mem: 78493
Epoch: [183]  [ 80/312]  eta: 0:04:44  lr: 0.001485  min_lr: 0.001485  loss: 2.1106 (2.1646)  weight_decay: 0.0500 (0.0500)  time: 1.0113  data: 0.0011  max mem: 78493
Epoch: [183]  [ 90/312]  eta: 0:04:27  lr: 0.001484  min_lr: 0.001484  loss: 1.9047 (2.1435)  weight_decay: 0.0500 (0.0500)  time: 1.0119  data: 0.0012  max mem: 78493
Epoch: [183]  [100/312]  eta: 0:04:10  lr: 0.001483  min_lr: 0.001483  loss: 1.9391 (2.1387)  weight_decay: 0.0500 (0.0500)  time: 1.0084  data: 0.0005  max mem: 78493
Epoch: [183]  [110/312]  eta: 0:03:55  lr: 0.001483  min_lr: 0.001483  loss: 2.2293 (2.1492)  weight_decay: 0.0500 (0.0500)  time: 1.0060  data: 0.0005  max mem: 78493
Epoch: [183]  [120/312]  eta: 0:03:41  lr: 0.001482  min_lr: 0.001482  loss: 2.2702 (2.1424)  weight_decay: 0.0500 (0.0500)  time: 1.0058  data: 0.0005  max mem: 78493
Epoch: [183]  [130/312]  eta: 0:03:28  lr: 0.001481  min_lr: 0.001481  loss: 1.9985 (2.1272)  weight_decay: 0.0500 (0.0500)  time: 1.0083  data: 0.0005  max mem: 78493
Epoch: [183]  [140/312]  eta: 0:03:14  lr: 0.001480  min_lr: 0.001480  loss: 2.0501 (2.1231)  weight_decay: 0.0500 (0.0500)  time: 1.0092  data: 0.0005  max mem: 78493
Epoch: [183]  [150/312]  eta: 0:03:02  lr: 0.001480  min_lr: 0.001480  loss: 2.1607 (2.1153)  weight_decay: 0.0500 (0.0500)  time: 1.0077  data: 0.0004  max mem: 78493
Epoch: [183]  [160/312]  eta: 0:02:49  lr: 0.001479  min_lr: 0.001479  loss: 2.1439 (2.1192)  weight_decay: 0.0500 (0.0500)  time: 1.0070  data: 0.0005  max mem: 78493
Epoch: [183]  [170/312]  eta: 0:02:37  lr: 0.001478  min_lr: 0.001478  loss: 2.2884 (2.1226)  weight_decay: 0.0500 (0.0500)  time: 1.0084  data: 0.0005  max mem: 78493
Epoch: [183]  [180/312]  eta: 0:02:25  lr: 0.001478  min_lr: 0.001478  loss: 2.2810 (2.1267)  weight_decay: 0.0500 (0.0500)  time: 1.0095  data: 0.0013  max mem: 78493
Epoch: [183]  [190/312]  eta: 0:02:14  lr: 0.001477  min_lr: 0.001477  loss: 2.2810 (2.1286)  weight_decay: 0.0500 (0.0500)  time: 1.0080  data: 0.0013  max mem: 78493
Epoch: [183]  [200/312]  eta: 0:02:02  lr: 0.001476  min_lr: 0.001476  loss: 2.2481 (2.1217)  weight_decay: 0.0500 (0.0500)  time: 1.0091  data: 0.0004  max mem: 78493
Epoch: [183]  [210/312]  eta: 0:01:51  lr: 0.001476  min_lr: 0.001476  loss: 2.2222 (2.1313)  weight_decay: 0.0500 (0.0500)  time: 1.0091  data: 0.0004  max mem: 78493
Epoch: [183]  [220/312]  eta: 0:01:40  lr: 0.001475  min_lr: 0.001475  loss: 2.3046 (2.1377)  weight_decay: 0.0500 (0.0500)  time: 1.0089  data: 0.0004  max mem: 78493
Epoch: [183]  [230/312]  eta: 0:01:28  lr: 0.001474  min_lr: 0.001474  loss: 2.3077 (2.1459)  weight_decay: 0.0500 (0.0500)  time: 1.0113  data: 0.0005  max mem: 78493
Epoch: [183]  [240/312]  eta: 0:01:17  lr: 0.001474  min_lr: 0.001474  loss: 2.2656 (2.1427)  weight_decay: 0.0500 (0.0500)  time: 1.0101  data: 0.0005  max mem: 78493
Epoch: [183]  [250/312]  eta: 0:01:06  lr: 0.001473  min_lr: 0.001473  loss: 2.1613 (2.1422)  weight_decay: 0.0500 (0.0500)  time: 1.0074  data: 0.0005  max mem: 78493
Epoch: [183]  [260/312]  eta: 0:00:55  lr: 0.001472  min_lr: 0.001472  loss: 2.1581 (2.1386)  weight_decay: 0.0500 (0.0500)  time: 1.0092  data: 0.0005  max mem: 78493
Epoch: [183]  [270/312]  eta: 0:00:45  lr: 0.001471  min_lr: 0.001471  loss: 2.1550 (2.1387)  weight_decay: 0.0500 (0.0500)  time: 1.0092  data: 0.0005  max mem: 78493
Epoch: [183]  [280/312]  eta: 0:00:34  lr: 0.001471  min_lr: 0.001471  loss: 2.0516 (2.1360)  weight_decay: 0.0500 (0.0500)  time: 1.0079  data: 0.0011  max mem: 78493
Epoch: [183]  [290/312]  eta: 0:00:23  lr: 0.001470  min_lr: 0.001470  loss: 2.2569 (2.1408)  weight_decay: 0.0500 (0.0500)  time: 1.0054  data: 0.0009  max mem: 78493
Epoch: [183]  [300/312]  eta: 0:00:12  lr: 0.001469  min_lr: 0.001469  loss: 2.2451 (2.1336)  weight_decay: 0.0500 (0.0500)  time: 1.0025  data: 0.0001  max mem: 78493
Epoch: [183]  [310/312]  eta: 0:00:02  lr: 0.001469  min_lr: 0.001469  loss: 2.1195 (2.1334)  weight_decay: 0.0500 (0.0500)  time: 1.0020  data: 0.0001  max mem: 78493
Epoch: [183]  [311/312]  eta: 0:00:01  lr: 0.001469  min_lr: 0.001469  loss: 2.1195 (2.1348)  weight_decay: 0.0500 (0.0500)  time: 1.0021  data: 0.0001  max mem: 78493
Epoch: [183] Total time: 0:05:33 (1.0701 s / it)
Averaged stats: lr: 0.001469  min_lr: 0.001469  loss: 2.1195 (2.1505)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:13  loss: 0.6093 (0.6093)  acc1: 83.8542 (83.8542)  acc5: 96.6146 (96.6146)  time: 8.2116  data: 7.9381  max mem: 78493
Test:  [8/9]  eta: 0:00:01  loss: 0.9488 (0.8459)  acc1: 77.7344 (77.7120)  acc5: 94.0104 (94.1120)  time: 1.1106  data: 0.8821  max mem: 78493
Test: Total time: 0:00:10 (1.1514 s / it)
* Acc@1 78.180 Acc@5 94.048 loss 0.838
Accuracy of the model on the 50000 test images: 78.2%
Max accuracy: 78.40%
Epoch: [184]  [  0/312]  eta: 1:26:21  lr: 0.001469  min_lr: 0.001469  loss: 2.4288 (2.4288)  weight_decay: 0.0500 (0.0500)  time: 16.6081  data: 15.5978  max mem: 78493
Epoch: [184]  [ 10/312]  eta: 0:13:44  lr: 0.001468  min_lr: 0.001468  loss: 2.2771 (2.2654)  weight_decay: 0.0500 (0.0500)  time: 2.7290  data: 1.4186  max mem: 78493
Epoch: [184]  [ 20/312]  eta: 0:09:18  lr: 0.001467  min_lr: 0.001467  loss: 2.1298 (2.1362)  weight_decay: 0.0500 (0.0500)  time: 1.1775  data: 0.0006  max mem: 78493
Epoch: [184]  [ 30/312]  eta: 0:07:37  lr: 0.001466  min_lr: 0.001466  loss: 2.0410 (2.1363)  weight_decay: 0.0500 (0.0500)  time: 1.0118  data: 0.0004  max mem: 78493
Epoch: [184]  [ 40/312]  eta: 0:06:40  lr: 0.001466  min_lr: 0.001466  loss: 2.0450 (2.1430)  weight_decay: 0.0500 (0.0500)  time: 1.0119  data: 0.0004  max mem: 78493
Epoch: [184]  [ 50/312]  eta: 0:06:02  lr: 0.001465  min_lr: 0.001465  loss: 2.1996 (2.1446)  weight_decay: 0.0500 (0.0500)  time: 1.0127  data: 0.0004  max mem: 78493
Epoch: [184]  [ 60/312]  eta: 0:05:32  lr: 0.001464  min_lr: 0.001464  loss: 2.0760 (2.1014)  weight_decay: 0.0500 (0.0500)  time: 1.0102  data: 0.0005  max mem: 78493
Epoch: [184]  [ 70/312]  eta: 0:05:09  lr: 0.001464  min_lr: 0.001464  loss: 2.0277 (2.1032)  weight_decay: 0.0500 (0.0500)  time: 1.0085  data: 0.0005  max mem: 78493
Epoch: [184]  [ 80/312]  eta: 0:04:48  lr: 0.001463  min_lr: 0.001463  loss: 2.0368 (2.0947)  weight_decay: 0.0500 (0.0500)  time: 1.0060  data: 0.0005  max mem: 78493
Epoch: [184]  [ 90/312]  eta: 0:04:30  lr: 0.001462  min_lr: 0.001462  loss: 1.9557 (2.0938)  weight_decay: 0.0500 (0.0500)  time: 1.0054  data: 0.0004  max mem: 78493
Epoch: [184]  [100/312]  eta: 0:04:13  lr: 0.001462  min_lr: 0.001462  loss: 1.9872 (2.0946)  weight_decay: 0.0500 (0.0500)  time: 1.0054  data: 0.0004  max mem: 78493
Epoch: [184]  [110/312]  eta: 0:03:58  lr: 0.001461  min_lr: 0.001461  loss: 2.2761 (2.1109)  weight_decay: 0.0500 (0.0500)  time: 1.0047  data: 0.0004  max mem: 78493
Epoch: [184]  [120/312]  eta: 0:03:43  lr: 0.001460  min_lr: 0.001460  loss: 2.3151 (2.1132)  weight_decay: 0.0500 (0.0500)  time: 1.0048  data: 0.0004  max mem: 78493
Epoch: [184]  [130/312]  eta: 0:03:29  lr: 0.001460  min_lr: 0.001460  loss: 2.1731 (2.1192)  weight_decay: 0.0500 (0.0500)  time: 1.0047  data: 0.0004  max mem: 78493
Epoch: [184]  [140/312]  eta: 0:03:16  lr: 0.001459  min_lr: 0.001459  loss: 2.2005 (2.1128)  weight_decay: 0.0500 (0.0500)  time: 1.0064  data: 0.0004  max mem: 78493
Epoch: [184]  [150/312]  eta: 0:03:03  lr: 0.001458  min_lr: 0.001458  loss: 2.1546 (2.1149)  weight_decay: 0.0500 (0.0500)  time: 1.0062  data: 0.0005  max mem: 78493
Epoch: [184]  [160/312]  eta: 0:02:51  lr: 0.001457  min_lr: 0.001457  loss: 2.2684 (2.1183)  weight_decay: 0.0500 (0.0500)  time: 1.0060  data: 0.0004  max mem: 78493
Epoch: [184]  [170/312]  eta: 0:02:38  lr: 0.001457  min_lr: 0.001457  loss: 2.2684 (2.1224)  weight_decay: 0.0500 (0.0500)  time: 1.0070  data: 0.0004  max mem: 78493
Epoch: [184]  [180/312]  eta: 0:02:26  lr: 0.001456  min_lr: 0.001456  loss: 2.3173 (2.1380)  weight_decay: 0.0500 (0.0500)  time: 1.0076  data: 0.0004  max mem: 78493
Epoch: [184]  [190/312]  eta: 0:02:15  lr: 0.001455  min_lr: 0.001455  loss: 2.3173 (2.1427)  weight_decay: 0.0500 (0.0500)  time: 1.0091  data: 0.0004  max mem: 78493
Epoch: [184]  [200/312]  eta: 0:02:03  lr: 0.001455  min_lr: 0.001455  loss: 2.2732 (2.1530)  weight_decay: 0.0500 (0.0500)  time: 1.0080  data: 0.0004  max mem: 78493
Epoch: [184]  [210/312]  eta: 0:01:51  lr: 0.001454  min_lr: 0.001454  loss: 2.2231 (2.1595)  weight_decay: 0.0500 (0.0500)  time: 1.0055  data: 0.0004  max mem: 78493
Epoch: [184]  [220/312]  eta: 0:01:40  lr: 0.001453  min_lr: 0.001453  loss: 2.2231 (2.1588)  weight_decay: 0.0500 (0.0500)  time: 1.0052  data: 0.0004  max mem: 78493
Epoch: [184]  [230/312]  eta: 0:01:29  lr: 0.001453  min_lr: 0.001453  loss: 2.2774 (2.1639)  weight_decay: 0.0500 (0.0500)  time: 1.0048  data: 0.0004  max mem: 78493
Epoch: [184]  [240/312]  eta: 0:01:18  lr: 0.001452  min_lr: 0.001452  loss: 2.3243 (2.1619)  weight_decay: 0.0500 (0.0500)  time: 1.0042  data: 0.0004  max mem: 78493
Epoch: [184]  [250/312]  eta: 0:01:07  lr: 0.001451  min_lr: 0.001451  loss: 2.2575 (2.1602)  weight_decay: 0.0500 (0.0500)  time: 1.0044  data: 0.0004  max mem: 78493
Epoch: [184]  [260/312]  eta: 0:00:56  lr: 0.001451  min_lr: 0.001451  loss: 2.2459 (2.1601)  weight_decay: 0.0500 (0.0500)  time: 1.0054  data: 0.0004  max mem: 78493
Epoch: [184]  [270/312]  eta: 0:00:45  lr: 0.001450  min_lr: 0.001450  loss: 2.2804 (2.1630)  weight_decay: 0.0500 (0.0500)  time: 1.0055  data: 0.0004  max mem: 78493
Epoch: [184]  [280/312]  eta: 0:00:34  lr: 0.001449  min_lr: 0.001449  loss: 2.3174 (2.1698)  weight_decay: 0.0500 (0.0500)  time: 1.0053  data: 0.0010  max mem: 78493
Epoch: [184]  [290/312]  eta: 0:00:23  lr: 0.001448  min_lr: 0.001448  loss: 2.3009 (2.1719)  weight_decay: 0.0500 (0.0500)  time: 1.0041  data: 0.0009  max mem: 78493
Epoch: [184]  [300/312]  eta: 0:00:12  lr: 0.001448  min_lr: 0.001448  loss: 2.1216 (2.1673)  weight_decay: 0.0500 (0.0500)  time: 1.0017  data: 0.0001  max mem: 78493
Epoch: [184]  [310/312]  eta: 0:00:02  lr: 0.001447  min_lr: 0.001447  loss: 2.0408 (2.1614)  weight_decay: 0.0500 (0.0500)  time: 1.0013  data: 0.0001  max mem: 78493
Epoch: [184]  [311/312]  eta: 0:00:01  lr: 0.001447  min_lr: 0.001447  loss: 2.0408 (2.1623)  weight_decay: 0.0500 (0.0500)  time: 1.0013  data: 0.0001  max mem: 78493
Epoch: [184] Total time: 0:05:34 (1.0726 s / it)
Averaged stats: lr: 0.001447  min_lr: 0.001447  loss: 2.0408 (2.1507)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:18  loss: 0.6193 (0.6193)  acc1: 85.6771 (85.6771)  acc5: 96.4844 (96.4844)  time: 8.7153  data: 8.4395  max mem: 78493
Test:  [8/9]  eta: 0:00:01  loss: 0.9291 (0.8527)  acc1: 76.8229 (77.6960)  acc5: 94.1406 (94.1440)  time: 1.1666  data: 0.9378  max mem: 78493
Test: Total time: 0:00:10 (1.1801 s / it)
* Acc@1 78.120 Acc@5 94.104 loss 0.837
Accuracy of the model on the 50000 test images: 78.1%
Max accuracy: 78.40%
Epoch: [185]  [  0/312]  eta: 1:27:27  lr: 0.001447  min_lr: 0.001447  loss: 1.5555 (1.5555)  weight_decay: 0.0500 (0.0500)  time: 16.8174  data: 13.4205  max mem: 78493
Epoch: [185]  [ 10/312]  eta: 0:12:49  lr: 0.001446  min_lr: 0.001446  loss: 2.2239 (2.1469)  weight_decay: 0.0500 (0.0500)  time: 2.5467  data: 1.2859  max mem: 78493
Epoch: [185]  [ 20/312]  eta: 0:08:52  lr: 0.001446  min_lr: 0.001446  loss: 2.1861 (2.0575)  weight_decay: 0.0500 (0.0500)  time: 1.0750  data: 0.0365  max mem: 78493
Epoch: [185]  [ 30/312]  eta: 0:07:20  lr: 0.001445  min_lr: 0.001445  loss: 2.1861 (2.1234)  weight_decay: 0.0500 (0.0500)  time: 1.0197  data: 0.0005  max mem: 78493
Epoch: [185]  [ 40/312]  eta: 0:06:27  lr: 0.001444  min_lr: 0.001444  loss: 2.2314 (2.1180)  weight_decay: 0.0500 (0.0500)  time: 1.0078  data: 0.0004  max mem: 78493
Epoch: [185]  [ 50/312]  eta: 0:05:52  lr: 0.001444  min_lr: 0.001444  loss: 2.2675 (2.1458)  weight_decay: 0.0500 (0.0500)  time: 1.0074  data: 0.0004  max mem: 78493
Epoch: [185]  [ 60/312]  eta: 0:05:24  lr: 0.001443  min_lr: 0.001443  loss: 2.1744 (2.1446)  weight_decay: 0.0500 (0.0500)  time: 1.0087  data: 0.0004  max mem: 78493
Epoch: [185]  [ 70/312]  eta: 0:05:02  lr: 0.001442  min_lr: 0.001442  loss: 2.2275 (2.1614)  weight_decay: 0.0500 (0.0500)  time: 1.0068  data: 0.0005  max mem: 78493
Epoch: [185]  [ 80/312]  eta: 0:04:42  lr: 0.001441  min_lr: 0.001441  loss: 2.2780 (2.1691)  weight_decay: 0.0500 (0.0500)  time: 1.0068  data: 0.0005  max mem: 78493
Epoch: [185]  [ 90/312]  eta: 0:04:25  lr: 0.001441  min_lr: 0.001441  loss: 2.1933 (2.1628)  weight_decay: 0.0500 (0.0500)  time: 1.0090  data: 0.0004  max mem: 78493
Epoch: [185]  [100/312]  eta: 0:04:09  lr: 0.001440  min_lr: 0.001440  loss: 2.1171 (2.1549)  weight_decay: 0.0500 (0.0500)  time: 1.0081  data: 0.0004  max mem: 78493
Epoch: [185]  [110/312]  eta: 0:03:54  lr: 0.001439  min_lr: 0.001439  loss: 2.0111 (2.1468)  weight_decay: 0.0500 (0.0500)  time: 1.0096  data: 0.0004  max mem: 78493
Epoch: [185]  [120/312]  eta: 0:03:40  lr: 0.001439  min_lr: 0.001439  loss: 2.0151 (2.1384)  weight_decay: 0.0500 (0.0500)  time: 1.0082  data: 0.0004  max mem: 78493
Epoch: [185]  [130/312]  eta: 0:03:27  lr: 0.001438  min_lr: 0.001438  loss: 2.2173 (2.1480)  weight_decay: 0.0500 (0.0500)  time: 1.0058  data: 0.0004  max mem: 78493
Epoch: [185]  [140/312]  eta: 0:03:14  lr: 0.001437  min_lr: 0.001437  loss: 2.2173 (2.1371)  weight_decay: 0.0500 (0.0500)  time: 1.0062  data: 0.0011  max mem: 78493
Epoch: [185]  [150/312]  eta: 0:03:01  lr: 0.001437  min_lr: 0.001437  loss: 1.9699 (2.1277)  weight_decay: 0.0500 (0.0500)  time: 1.0065  data: 0.0011  max mem: 78493
Epoch: [185]  [160/312]  eta: 0:02:49  lr: 0.001436  min_lr: 0.001436  loss: 1.7997 (2.1129)  weight_decay: 0.0500 (0.0500)  time: 1.0074  data: 0.0005  max mem: 78493
Epoch: [185]  [170/312]  eta: 0:02:37  lr: 0.001435  min_lr: 0.001435  loss: 2.0502 (2.1221)  weight_decay: 0.0500 (0.0500)  time: 1.0060  data: 0.0005  max mem: 78493
Epoch: [185]  [180/312]  eta: 0:02:25  lr: 0.001435  min_lr: 0.001435  loss: 2.1873 (2.1180)  weight_decay: 0.0500 (0.0500)  time: 1.0043  data: 0.0005  max mem: 78493
Epoch: [185]  [190/312]  eta: 0:02:13  lr: 0.001434  min_lr: 0.001434  loss: 2.1873 (2.1164)  weight_decay: 0.0500 (0.0500)  time: 1.0049  data: 0.0004  max mem: 78493
Epoch: [185]  [200/312]  eta: 0:02:02  lr: 0.001433  min_lr: 0.001433  loss: 2.2233 (2.1148)  weight_decay: 0.0500 (0.0500)  time: 1.0078  data: 0.0004  max mem: 78493
Epoch: [185]  [210/312]  eta: 0:01:51  lr: 0.001432  min_lr: 0.001432  loss: 2.1274 (2.1129)  weight_decay: 0.0500 (0.0500)  time: 1.0081  data: 0.0005  max mem: 78493
Epoch: [185]  [220/312]  eta: 0:01:39  lr: 0.001432  min_lr: 0.001432  loss: 2.1611 (2.1137)  weight_decay: 0.0500 (0.0500)  time: 1.0063  data: 0.0005  max mem: 78493
Epoch: [185]  [230/312]  eta: 0:01:28  lr: 0.001431  min_lr: 0.001431  loss: 2.3095 (2.1210)  weight_decay: 0.0500 (0.0500)  time: 1.0060  data: 0.0005  max mem: 78493
Epoch: [185]  [240/312]  eta: 0:01:17  lr: 0.001430  min_lr: 0.001430  loss: 2.2966 (2.1225)  weight_decay: 0.0500 (0.0500)  time: 1.0054  data: 0.0005  max mem: 78493
Epoch: [185]  [250/312]  eta: 0:01:06  lr: 0.001430  min_lr: 0.001430  loss: 2.1683 (2.1248)  weight_decay: 0.0500 (0.0500)  time: 1.0049  data: 0.0004  max mem: 78493
Epoch: [185]  [260/312]  eta: 0:00:55  lr: 0.001429  min_lr: 0.001429  loss: 2.1375 (2.1243)  weight_decay: 0.0500 (0.0500)  time: 1.0062  data: 0.0004  max mem: 78493
Epoch: [185]  [270/312]  eta: 0:00:44  lr: 0.001428  min_lr: 0.001428  loss: 2.0775 (2.1229)  weight_decay: 0.0500 (0.0500)  time: 1.0070  data: 0.0005  max mem: 78493
Epoch: [185]  [280/312]  eta: 0:00:34  lr: 0.001428  min_lr: 0.001428  loss: 2.0284 (2.1194)  weight_decay: 0.0500 (0.0500)  time: 1.0080  data: 0.0011  max mem: 78493
Epoch: [185]  [290/312]  eta: 0:00:23  lr: 0.001427  min_lr: 0.001427  loss: 2.0670 (2.1219)  weight_decay: 0.0500 (0.0500)  time: 1.0055  data: 0.0009  max mem: 78493
Epoch: [185]  [300/312]  eta: 0:00:12  lr: 0.001426  min_lr: 0.001426  loss: 2.1900 (2.1238)  weight_decay: 0.0500 (0.0500)  time: 1.0015  data: 0.0001  max mem: 78493
Epoch: [185]  [310/312]  eta: 0:00:02  lr: 0.001426  min_lr: 0.001426  loss: 2.1759 (2.1240)  weight_decay: 0.0500 (0.0500)  time: 1.0015  data: 0.0001  max mem: 78493
Epoch: [185]  [311/312]  eta: 0:00:01  lr: 0.001426  min_lr: 0.001426  loss: 2.1759 (2.1251)  weight_decay: 0.0500 (0.0500)  time: 1.0015  data: 0.0001  max mem: 78493
Epoch: [185] Total time: 0:05:32 (1.0669 s / it)
Averaged stats: lr: 0.001426  min_lr: 0.001426  loss: 2.1759 (2.1570)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:22  loss: 0.6265 (0.6265)  acc1: 85.1562 (85.1562)  acc5: 96.3542 (96.3542)  time: 9.1229  data: 8.8448  max mem: 78493
Test:  [8/9]  eta: 0:00:01  loss: 0.9420 (0.8798)  acc1: 76.4323 (77.7920)  acc5: 94.4010 (94.1920)  time: 1.2118  data: 0.9828  max mem: 78493
Test: Total time: 0:00:11 (1.2368 s / it)
* Acc@1 77.904 Acc@5 94.078 loss 0.869
Accuracy of the model on the 50000 test images: 77.9%
Max accuracy: 78.40%
Epoch: [186]  [  0/312]  eta: 1:25:47  lr: 0.001425  min_lr: 0.001425  loss: 2.6653 (2.6653)  weight_decay: 0.0500 (0.0500)  time: 16.4977  data: 13.2141  max mem: 78493
Epoch: [186]  [ 10/312]  eta: 0:13:40  lr: 0.001425  min_lr: 0.001425  loss: 2.3700 (2.3267)  weight_decay: 0.0500 (0.0500)  time: 2.7162  data: 1.2330  max mem: 78493
Epoch: [186]  [ 20/312]  eta: 0:09:16  lr: 0.001424  min_lr: 0.001424  loss: 2.3698 (2.3355)  weight_decay: 0.0500 (0.0500)  time: 1.1745  data: 0.0191  max mem: 78493
Epoch: [186]  [ 30/312]  eta: 0:07:35  lr: 0.001423  min_lr: 0.001423  loss: 2.2990 (2.3095)  weight_decay: 0.0500 (0.0500)  time: 1.0096  data: 0.0018  max mem: 78493
Epoch: [186]  [ 40/312]  eta: 0:06:39  lr: 0.001423  min_lr: 0.001423  loss: 2.2560 (2.2853)  weight_decay: 0.0500 (0.0500)  time: 1.0095  data: 0.0004  max mem: 78493
Epoch: [186]  [ 50/312]  eta: 0:06:01  lr: 0.001422  min_lr: 0.001422  loss: 2.0792 (2.2443)  weight_decay: 0.0500 (0.0500)  time: 1.0125  data: 0.0014  max mem: 78493
Epoch: [186]  [ 60/312]  eta: 0:05:32  lr: 0.001421  min_lr: 0.001421  loss: 2.0520 (2.2170)  weight_decay: 0.0500 (0.0500)  time: 1.0113  data: 0.0014  max mem: 78493
Epoch: [186]  [ 70/312]  eta: 0:05:08  lr: 0.001421  min_lr: 0.001421  loss: 2.2494 (2.2321)  weight_decay: 0.0500 (0.0500)  time: 1.0132  data: 0.0005  max mem: 78493
Epoch: [186]  [ 80/312]  eta: 0:04:48  lr: 0.001420  min_lr: 0.001420  loss: 2.2494 (2.2388)  weight_decay: 0.0500 (0.0500)  time: 1.0143  data: 0.0005  max mem: 78493
Epoch: [186]  [ 90/312]  eta: 0:04:30  lr: 0.001419  min_lr: 0.001419  loss: 2.1105 (2.2133)  weight_decay: 0.0500 (0.0500)  time: 1.0132  data: 0.0005  max mem: 78493
Epoch: [186]  [100/312]  eta: 0:04:13  lr: 0.001419  min_lr: 0.001419  loss: 2.1190 (2.2214)  weight_decay: 0.0500 (0.0500)  time: 1.0143  data: 0.0005  max mem: 78493
Epoch: [186]  [110/312]  eta: 0:03:58  lr: 0.001418  min_lr: 0.001418  loss: 2.1704 (2.2142)  weight_decay: 0.0500 (0.0500)  time: 1.0131  data: 0.0005  max mem: 78493
Epoch: [186]  [120/312]  eta: 0:03:44  lr: 0.001417  min_lr: 0.001417  loss: 1.9459 (2.1787)  weight_decay: 0.0500 (0.0500)  time: 1.0121  data: 0.0005  max mem: 78493
Epoch: [186]  [130/312]  eta: 0:03:30  lr: 0.001416  min_lr: 0.001416  loss: 1.9714 (2.1748)  weight_decay: 0.0500 (0.0500)  time: 1.0120  data: 0.0022  max mem: 78493
Epoch: [186]  [140/312]  eta: 0:03:16  lr: 0.001416  min_lr: 0.001416  loss: 2.1349 (2.1671)  weight_decay: 0.0500 (0.0500)  time: 1.0104  data: 0.0022  max mem: 78493
Epoch: [186]  [150/312]  eta: 0:03:04  lr: 0.001415  min_lr: 0.001415  loss: 2.0980 (2.1665)  weight_decay: 0.0500 (0.0500)  time: 1.0103  data: 0.0011  max mem: 78493
Epoch: [186]  [160/312]  eta: 0:02:51  lr: 0.001414  min_lr: 0.001414  loss: 2.3103 (2.1667)  weight_decay: 0.0500 (0.0500)  time: 1.0139  data: 0.0011  max mem: 78493
Epoch: [186]  [170/312]  eta: 0:02:39  lr: 0.001414  min_lr: 0.001414  loss: 2.3199 (2.1778)  weight_decay: 0.0500 (0.0500)  time: 1.0126  data: 0.0004  max mem: 78493
Epoch: [186]  [180/312]  eta: 0:02:27  lr: 0.001413  min_lr: 0.001413  loss: 2.2423 (2.1696)  weight_decay: 0.0500 (0.0500)  time: 1.0101  data: 0.0004  max mem: 78493
Epoch: [186]  [190/312]  eta: 0:02:15  lr: 0.001412  min_lr: 0.001412  loss: 1.9942 (2.1667)  weight_decay: 0.0500 (0.0500)  time: 1.0075  data: 0.0004  max mem: 78493
Epoch: [186]  [200/312]  eta: 0:02:03  lr: 0.001412  min_lr: 0.001412  loss: 2.1585 (2.1655)  weight_decay: 0.0500 (0.0500)  time: 1.0044  data: 0.0004  max mem: 78493
Epoch: [186]  [210/312]  eta: 0:01:52  lr: 0.001411  min_lr: 0.001411  loss: 2.3098 (2.1670)  weight_decay: 0.0500 (0.0500)  time: 1.0053  data: 0.0004  max mem: 78493
Epoch: [186]  [220/312]  eta: 0:01:40  lr: 0.001410  min_lr: 0.001410  loss: 2.2351 (2.1627)  weight_decay: 0.0500 (0.0500)  time: 1.0068  data: 0.0017  max mem: 78493
Epoch: [186]  [230/312]  eta: 0:01:29  lr: 0.001410  min_lr: 0.001410  loss: 2.2572 (2.1627)  weight_decay: 0.0500 (0.0500)  time: 1.0069  data: 0.0017  max mem: 78493
Epoch: [186]  [240/312]  eta: 0:01:18  lr: 0.001409  min_lr: 0.001409  loss: 2.2909 (2.1651)  weight_decay: 0.0500 (0.0500)  time: 1.0059  data: 0.0004  max mem: 78493
Epoch: [186]  [250/312]  eta: 0:01:07  lr: 0.001408  min_lr: 0.001408  loss: 2.3628 (2.1697)  weight_decay: 0.0500 (0.0500)  time: 1.0053  data: 0.0005  max mem: 78493
Epoch: [186]  [260/312]  eta: 0:00:56  lr: 0.001408  min_lr: 0.001408  loss: 2.0223 (2.1580)  weight_decay: 0.0500 (0.0500)  time: 1.0058  data: 0.0005  max mem: 78493
Epoch: [186]  [270/312]  eta: 0:00:45  lr: 0.001407  min_lr: 0.001407  loss: 2.1287 (2.1627)  weight_decay: 0.0500 (0.0500)  time: 1.0052  data: 0.0004  max mem: 78493
Epoch: [186]  [280/312]  eta: 0:00:34  lr: 0.001406  min_lr: 0.001406  loss: 2.3647 (2.1639)  weight_decay: 0.0500 (0.0500)  time: 1.0060  data: 0.0010  max mem: 78493
Epoch: [186]  [290/312]  eta: 0:00:23  lr: 0.001406  min_lr: 0.001406  loss: 2.2736 (2.1684)  weight_decay: 0.0500 (0.0500)  time: 1.0047  data: 0.0009  max mem: 78493
Epoch: [186]  [300/312]  eta: 0:00:12  lr: 0.001405  min_lr: 0.001405  loss: 2.1300 (2.1656)  weight_decay: 0.0500 (0.0500)  time: 1.0021  data: 0.0001  max mem: 78493
Epoch: [186]  [310/312]  eta: 0:00:02  lr: 0.001404  min_lr: 0.001404  loss: 2.0733 (2.1657)  weight_decay: 0.0500 (0.0500)  time: 1.0021  data: 0.0001  max mem: 78493
Epoch: [186]  [311/312]  eta: 0:00:01  lr: 0.001404  min_lr: 0.001404  loss: 2.0733 (2.1647)  weight_decay: 0.0500 (0.0500)  time: 1.0021  data: 0.0001  max mem: 78493
Epoch: [186] Total time: 0:05:35 (1.0750 s / it)
Averaged stats: lr: 0.001404  min_lr: 0.001404  loss: 2.0733 (2.1561)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:17  loss: 0.6513 (0.6513)  acc1: 83.4635 (83.4635)  acc5: 96.4844 (96.4844)  time: 8.5815  data: 8.2990  max mem: 78493
Test:  [8/9]  eta: 0:00:01  loss: 0.9258 (0.8570)  acc1: 76.3021 (77.2960)  acc5: 93.8802 (94.1280)  time: 1.1518  data: 0.9222  max mem: 78493
Test: Total time: 0:00:10 (1.1720 s / it)
* Acc@1 78.404 Acc@5 94.170 loss 0.831
Accuracy of the model on the 50000 test images: 78.4%
Max accuracy: 78.40%
Epoch: [187]  [  0/312]  eta: 1:24:23  lr: 0.001404  min_lr: 0.001404  loss: 2.0440 (2.0440)  weight_decay: 0.0500 (0.0500)  time: 16.2285  data: 15.2246  max mem: 78493
Epoch: [187]  [ 10/312]  eta: 0:12:18  lr: 0.001403  min_lr: 0.001403  loss: 2.0440 (2.0187)  weight_decay: 0.0500 (0.0500)  time: 2.4462  data: 1.3848  max mem: 78493
Epoch: [187]  [ 20/312]  eta: 0:08:37  lr: 0.001403  min_lr: 0.001403  loss: 1.9721 (2.0461)  weight_decay: 0.0500 (0.0500)  time: 1.0507  data: 0.0007  max mem: 78493
Epoch: [187]  [ 30/312]  eta: 0:07:10  lr: 0.001402  min_lr: 0.001402  loss: 2.0646 (2.0526)  weight_decay: 0.0500 (0.0500)  time: 1.0209  data: 0.0006  max mem: 78493
Epoch: [187]  [ 40/312]  eta: 0:06:20  lr: 0.001401  min_lr: 0.001401  loss: 2.1144 (2.0679)  weight_decay: 0.0500 (0.0500)  time: 1.0075  data: 0.0005  max mem: 78493
Epoch: [187]  [ 50/312]  eta: 0:05:46  lr: 0.001401  min_lr: 0.001401  loss: 2.0466 (2.0502)  weight_decay: 0.0500 (0.0500)  time: 1.0062  data: 0.0005  max mem: 78493
Epoch: [187]  [ 60/312]  eta: 0:05:20  lr: 0.001400  min_lr: 0.001400  loss: 1.8726 (2.0525)  weight_decay: 0.0500 (0.0500)  time: 1.0063  data: 0.0005  max mem: 78493
Epoch: [187]  [ 70/312]  eta: 0:04:58  lr: 0.001399  min_lr: 0.001399  loss: 2.1500 (2.0580)  weight_decay: 0.0500 (0.0500)  time: 1.0080  data: 0.0004  max mem: 78493
Epoch: [187]  [ 80/312]  eta: 0:04:39  lr: 0.001399  min_lr: 0.001399  loss: 2.0283 (2.0497)  weight_decay: 0.0500 (0.0500)  time: 1.0075  data: 0.0005  max mem: 78493
Epoch: [187]  [ 90/312]  eta: 0:04:22  lr: 0.001398  min_lr: 0.001398  loss: 2.2686 (2.0952)  weight_decay: 0.0500 (0.0500)  time: 1.0062  data: 0.0005  max mem: 78493
Epoch: [187]  [100/312]  eta: 0:04:07  lr: 0.001397  min_lr: 0.001397  loss: 2.3921 (2.1099)  weight_decay: 0.0500 (0.0500)  time: 1.0074  data: 0.0005  max mem: 78493
Epoch: [187]  [110/312]  eta: 0:03:52  lr: 0.001396  min_lr: 0.001396  loss: 2.2039 (2.1022)  weight_decay: 0.0500 (0.0500)  time: 1.0070  data: 0.0004  max mem: 78493
Epoch: [187]  [120/312]  eta: 0:03:38  lr: 0.001396  min_lr: 0.001396  loss: 2.2039 (2.1216)  weight_decay: 0.0500 (0.0500)  time: 1.0067  data: 0.0004  max mem: 78493
Epoch: [187]  [130/312]  eta: 0:03:25  lr: 0.001395  min_lr: 0.001395  loss: 2.3384 (2.1342)  weight_decay: 0.0500 (0.0500)  time: 1.0072  data: 0.0004  max mem: 78493
Epoch: [187]  [140/312]  eta: 0:03:12  lr: 0.001394  min_lr: 0.001394  loss: 2.2172 (2.1322)  weight_decay: 0.0500 (0.0500)  time: 1.0082  data: 0.0004  max mem: 78493
Epoch: [187]  [150/312]  eta: 0:03:00  lr: 0.001394  min_lr: 0.001394  loss: 2.2587 (2.1426)  weight_decay: 0.0500 (0.0500)  time: 1.0086  data: 0.0004  max mem: 78493
Epoch: [187]  [160/312]  eta: 0:02:48  lr: 0.001393  min_lr: 0.001393  loss: 2.3603 (2.1475)  weight_decay: 0.0500 (0.0500)  time: 1.0081  data: 0.0004  max mem: 78493
Epoch: [187]  [170/312]  eta: 0:02:36  lr: 0.001392  min_lr: 0.001392  loss: 2.2652 (2.1477)  weight_decay: 0.0500 (0.0500)  time: 1.0076  data: 0.0004  max mem: 78493
Epoch: [187]  [180/312]  eta: 0:02:24  lr: 0.001392  min_lr: 0.001392  loss: 2.0279 (2.1383)  weight_decay: 0.0500 (0.0500)  time: 1.0065  data: 0.0004  max mem: 78493
Epoch: [187]  [190/312]  eta: 0:02:13  lr: 0.001391  min_lr: 0.001391  loss: 2.0279 (2.1360)  weight_decay: 0.0500 (0.0500)  time: 1.0068  data: 0.0004  max mem: 78493
Epoch: [187]  [200/312]  eta: 0:02:01  lr: 0.001390  min_lr: 0.001390  loss: 2.1920 (2.1349)  weight_decay: 0.0500 (0.0500)  time: 1.0090  data: 0.0015  max mem: 78493
Epoch: [187]  [210/312]  eta: 0:01:50  lr: 0.001390  min_lr: 0.001390  loss: 2.0830 (2.1257)  weight_decay: 0.0500 (0.0500)  time: 1.0092  data: 0.0023  max mem: 78493
Epoch: [187]  [220/312]  eta: 0:01:39  lr: 0.001389  min_lr: 0.001389  loss: 2.0279 (2.1219)  weight_decay: 0.0500 (0.0500)  time: 1.0077  data: 0.0012  max mem: 78493
Epoch: [187]  [230/312]  eta: 0:01:28  lr: 0.001388  min_lr: 0.001388  loss: 2.0279 (2.1207)  weight_decay: 0.0500 (0.0500)  time: 1.0062  data: 0.0004  max mem: 78493
Epoch: [187]  [240/312]  eta: 0:01:17  lr: 0.001388  min_lr: 0.001388  loss: 2.2166 (2.1207)  weight_decay: 0.0500 (0.0500)  time: 1.0074  data: 0.0004  max mem: 78493
Epoch: [187]  [250/312]  eta: 0:01:06  lr: 0.001387  min_lr: 0.001387  loss: 2.2038 (2.1166)  weight_decay: 0.0500 (0.0500)  time: 1.0075  data: 0.0004  max mem: 78493
Epoch: [187]  [260/312]  eta: 0:00:55  lr: 0.001386  min_lr: 0.001386  loss: 1.9001 (2.1138)  weight_decay: 0.0500 (0.0500)  time: 1.0066  data: 0.0004  max mem: 78493
Epoch: [187]  [270/312]  eta: 0:00:44  lr: 0.001385  min_lr: 0.001385  loss: 2.1000 (2.1180)  weight_decay: 0.0500 (0.0500)  time: 1.0082  data: 0.0004  max mem: 78493
Epoch: [187]  [280/312]  eta: 0:00:34  lr: 0.001385  min_lr: 0.001385  loss: 2.0897 (2.1092)  weight_decay: 0.0500 (0.0500)  time: 1.0080  data: 0.0010  max mem: 78493
Epoch: [187]  [290/312]  eta: 0:00:23  lr: 0.001384  min_lr: 0.001384  loss: 1.8521 (2.1093)  weight_decay: 0.0500 (0.0500)  time: 1.0047  data: 0.0009  max mem: 78493
Epoch: [187]  [300/312]  eta: 0:00:12  lr: 0.001383  min_lr: 0.001383  loss: 2.1804 (2.1098)  weight_decay: 0.0500 (0.0500)  time: 1.0019  data: 0.0001  max mem: 78493
Epoch: [187]  [310/312]  eta: 0:00:02  lr: 0.001383  min_lr: 0.001383  loss: 2.1804 (2.1090)  weight_decay: 0.0500 (0.0500)  time: 1.0019  data: 0.0001  max mem: 78493
Epoch: [187]  [311/312]  eta: 0:00:01  lr: 0.001383  min_lr: 0.001383  loss: 2.1804 (2.1101)  weight_decay: 0.0500 (0.0500)  time: 1.0019  data: 0.0001  max mem: 78493
Epoch: [187] Total time: 0:05:32 (1.0644 s / it)
Averaged stats: lr: 0.001383  min_lr: 0.001383  loss: 2.1804 (2.1465)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:17  loss: 0.5935 (0.5935)  acc1: 84.1146 (84.1146)  acc5: 97.2656 (97.2656)  time: 8.5877  data: 8.3140  max mem: 78493
Test:  [8/9]  eta: 0:00:01  loss: 0.9379 (0.8463)  acc1: 76.9531 (77.8400)  acc5: 94.0104 (93.9040)  time: 1.1521  data: 0.9239  max mem: 78493
Test: Total time: 0:00:10 (1.1815 s / it)
* Acc@1 77.934 Acc@5 94.170 loss 0.838
Accuracy of the model on the 50000 test images: 77.9%
Max accuracy: 78.40%
Epoch: [188]  [  0/312]  eta: 1:21:27  lr: 0.001383  min_lr: 0.001383  loss: 2.1854 (2.1854)  weight_decay: 0.0500 (0.0500)  time: 15.6648  data: 12.5742  max mem: 78493
Epoch: [188]  [ 10/312]  eta: 0:13:04  lr: 0.001382  min_lr: 0.001382  loss: 2.1854 (2.1469)  weight_decay: 0.0500 (0.0500)  time: 2.5983  data: 1.1701  max mem: 78493
Epoch: [188]  [ 20/312]  eta: 0:08:58  lr: 0.001381  min_lr: 0.001381  loss: 2.1872 (2.2265)  weight_decay: 0.0500 (0.0500)  time: 1.1518  data: 0.0151  max mem: 78493
Epoch: [188]  [ 30/312]  eta: 0:07:23  lr: 0.001381  min_lr: 0.001381  loss: 2.2918 (2.2170)  weight_decay: 0.0500 (0.0500)  time: 1.0091  data: 0.0005  max mem: 78493
Epoch: [188]  [ 40/312]  eta: 0:06:30  lr: 0.001380  min_lr: 0.001380  loss: 2.2807 (2.2068)  weight_decay: 0.0500 (0.0500)  time: 1.0075  data: 0.0004  max mem: 78493
Epoch: [188]  [ 50/312]  eta: 0:05:54  lr: 0.001379  min_lr: 0.001379  loss: 2.2218 (2.2068)  weight_decay: 0.0500 (0.0500)  time: 1.0103  data: 0.0004  max mem: 78493
Epoch: [188]  [ 60/312]  eta: 0:05:26  lr: 0.001379  min_lr: 0.001379  loss: 2.2151 (2.1982)  weight_decay: 0.0500 (0.0500)  time: 1.0094  data: 0.0004  max mem: 78493
Epoch: [188]  [ 70/312]  eta: 0:05:03  lr: 0.001378  min_lr: 0.001378  loss: 2.2159 (2.1801)  weight_decay: 0.0500 (0.0500)  time: 1.0065  data: 0.0005  max mem: 78493
Epoch: [188]  [ 80/312]  eta: 0:04:44  lr: 0.001377  min_lr: 0.001377  loss: 2.0506 (2.1616)  weight_decay: 0.0500 (0.0500)  time: 1.0087  data: 0.0004  max mem: 78493
Epoch: [188]  [ 90/312]  eta: 0:04:26  lr: 0.001376  min_lr: 0.001376  loss: 2.1331 (2.1644)  weight_decay: 0.0500 (0.0500)  time: 1.0097  data: 0.0005  max mem: 78493
Epoch: [188]  [100/312]  eta: 0:04:10  lr: 0.001376  min_lr: 0.001376  loss: 2.2379 (2.1744)  weight_decay: 0.0500 (0.0500)  time: 1.0077  data: 0.0004  max mem: 78493
Epoch: [188]  [110/312]  eta: 0:03:55  lr: 0.001375  min_lr: 0.001375  loss: 2.2379 (2.1740)  weight_decay: 0.0500 (0.0500)  time: 1.0075  data: 0.0004  max mem: 78493
Epoch: [188]  [120/312]  eta: 0:03:41  lr: 0.001374  min_lr: 0.001374  loss: 2.1605 (2.1761)  weight_decay: 0.0500 (0.0500)  time: 1.0067  data: 0.0004  max mem: 78493
Epoch: [188]  [130/312]  eta: 0:03:27  lr: 0.001374  min_lr: 0.001374  loss: 2.2293 (2.1832)  weight_decay: 0.0500 (0.0500)  time: 1.0057  data: 0.0004  max mem: 78493
Epoch: [188]  [140/312]  eta: 0:03:14  lr: 0.001373  min_lr: 0.001373  loss: 2.2536 (2.1881)  weight_decay: 0.0500 (0.0500)  time: 1.0048  data: 0.0004  max mem: 78493
Epoch: [188]  [150/312]  eta: 0:03:02  lr: 0.001372  min_lr: 0.001372  loss: 2.3224 (2.1897)  weight_decay: 0.0500 (0.0500)  time: 1.0047  data: 0.0012  max mem: 78493
Epoch: [188]  [160/312]  eta: 0:02:49  lr: 0.001372  min_lr: 0.001372  loss: 2.0853 (2.1780)  weight_decay: 0.0500 (0.0500)  time: 1.0051  data: 0.0012  max mem: 78493
Epoch: [188]  [170/312]  eta: 0:02:37  lr: 0.001371  min_lr: 0.001371  loss: 2.0727 (2.1740)  weight_decay: 0.0500 (0.0500)  time: 1.0059  data: 0.0004  max mem: 78493
Epoch: [188]  [180/312]  eta: 0:02:25  lr: 0.001370  min_lr: 0.001370  loss: 2.0658 (2.1626)  weight_decay: 0.0500 (0.0500)  time: 1.0078  data: 0.0004  max mem: 78493
Epoch: [188]  [190/312]  eta: 0:02:14  lr: 0.001370  min_lr: 0.001370  loss: 2.0980 (2.1613)  weight_decay: 0.0500 (0.0500)  time: 1.0076  data: 0.0004  max mem: 78493
Epoch: [188]  [200/312]  eta: 0:02:02  lr: 0.001369  min_lr: 0.001369  loss: 2.1667 (2.1594)  weight_decay: 0.0500 (0.0500)  time: 1.0054  data: 0.0005  max mem: 78493
Epoch: [188]  [210/312]  eta: 0:01:51  lr: 0.001368  min_lr: 0.001368  loss: 2.1818 (2.1621)  weight_decay: 0.0500 (0.0500)  time: 1.0067  data: 0.0005  max mem: 78493
Epoch: [188]  [220/312]  eta: 0:01:39  lr: 0.001368  min_lr: 0.001368  loss: 2.1707 (2.1648)  weight_decay: 0.0500 (0.0500)  time: 1.0076  data: 0.0004  max mem: 78493
Epoch: [188]  [230/312]  eta: 0:01:28  lr: 0.001367  min_lr: 0.001367  loss: 2.2117 (2.1676)  weight_decay: 0.0500 (0.0500)  time: 1.0051  data: 0.0004  max mem: 78493
Epoch: [188]  [240/312]  eta: 0:01:17  lr: 0.001366  min_lr: 0.001366  loss: 2.1120 (2.1641)  weight_decay: 0.0500 (0.0500)  time: 1.0049  data: 0.0004  max mem: 78493
Epoch: [188]  [250/312]  eta: 0:01:06  lr: 0.001366  min_lr: 0.001366  loss: 2.0193 (2.1596)  weight_decay: 0.0500 (0.0500)  time: 1.0056  data: 0.0005  max mem: 78493
Epoch: [188]  [260/312]  eta: 0:00:55  lr: 0.001365  min_lr: 0.001365  loss: 1.9339 (2.1523)  weight_decay: 0.0500 (0.0500)  time: 1.0046  data: 0.0005  max mem: 78493
Epoch: [188]  [270/312]  eta: 0:00:45  lr: 0.001364  min_lr: 0.001364  loss: 2.1906 (2.1578)  weight_decay: 0.0500 (0.0500)  time: 1.0055  data: 0.0005  max mem: 78493
Epoch: [188]  [280/312]  eta: 0:00:34  lr: 0.001364  min_lr: 0.001364  loss: 2.2614 (2.1556)  weight_decay: 0.0500 (0.0500)  time: 1.0058  data: 0.0016  max mem: 78493
Epoch: [188]  [290/312]  eta: 0:00:23  lr: 0.001363  min_lr: 0.001363  loss: 2.0145 (2.1486)  weight_decay: 0.0500 (0.0500)  time: 1.0030  data: 0.0015  max mem: 78493
Epoch: [188]  [300/312]  eta: 0:00:12  lr: 0.001362  min_lr: 0.001362  loss: 2.2261 (2.1549)  weight_decay: 0.0500 (0.0500)  time: 1.0016  data: 0.0001  max mem: 78493
Epoch: [188]  [310/312]  eta: 0:00:02  lr: 0.001361  min_lr: 0.001361  loss: 2.3164 (2.1593)  weight_decay: 0.0500 (0.0500)  time: 1.0016  data: 0.0001  max mem: 78493
Epoch: [188]  [311/312]  eta: 0:00:01  lr: 0.001361  min_lr: 0.001361  loss: 2.3425 (2.1602)  weight_decay: 0.0500 (0.0500)  time: 1.0016  data: 0.0001  max mem: 78493
Epoch: [188] Total time: 0:05:33 (1.0682 s / it)
Averaged stats: lr: 0.001361  min_lr: 0.001361  loss: 2.3425 (2.1621)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:12  loss: 0.6091 (0.6091)  acc1: 85.6771 (85.6771)  acc5: 96.7448 (96.7448)  time: 8.0884  data: 7.7918  max mem: 78493
Test:  [8/9]  eta: 0:00:01  loss: 0.9158 (0.8370)  acc1: 77.8646 (78.1920)  acc5: 94.2708 (94.2880)  time: 1.0970  data: 0.8658  max mem: 78493
Test: Total time: 0:00:10 (1.1352 s / it)
* Acc@1 78.488 Acc@5 94.300 loss 0.831
Accuracy of the model on the 50000 test images: 78.5%
Max accuracy: 78.49%
Epoch: [189]  [  0/312]  eta: 1:23:52  lr: 0.001361  min_lr: 0.001361  loss: 1.7968 (1.7968)  weight_decay: 0.0500 (0.0500)  time: 16.1289  data: 15.1028  max mem: 78493
Epoch: [189]  [ 10/312]  eta: 0:13:13  lr: 0.001361  min_lr: 0.001361  loss: 1.9567 (2.0259)  weight_decay: 0.0500 (0.0500)  time: 2.6268  data: 1.3758  max mem: 78493
Epoch: [189]  [ 20/312]  eta: 0:09:02  lr: 0.001360  min_lr: 0.001360  loss: 2.0607 (2.1353)  weight_decay: 0.0500 (0.0500)  time: 1.1431  data: 0.0017  max mem: 78493
Epoch: [189]  [ 30/312]  eta: 0:07:26  lr: 0.001359  min_lr: 0.001359  loss: 2.2722 (2.0969)  weight_decay: 0.0500 (0.0500)  time: 1.0090  data: 0.0004  max mem: 78493
Epoch: [189]  [ 40/312]  eta: 0:06:32  lr: 0.001359  min_lr: 0.001359  loss: 2.1850 (2.0927)  weight_decay: 0.0500 (0.0500)  time: 1.0083  data: 0.0004  max mem: 78493
Epoch: [189]  [ 50/312]  eta: 0:05:55  lr: 0.001358  min_lr: 0.001358  loss: 2.0607 (2.0925)  weight_decay: 0.0500 (0.0500)  time: 1.0083  data: 0.0004  max mem: 78493
Epoch: [189]  [ 60/312]  eta: 0:05:27  lr: 0.001357  min_lr: 0.001357  loss: 2.0607 (2.0914)  weight_decay: 0.0500 (0.0500)  time: 1.0084  data: 0.0005  max mem: 78493
Epoch: [189]  [ 70/312]  eta: 0:05:04  lr: 0.001357  min_lr: 0.001357  loss: 2.1351 (2.0937)  weight_decay: 0.0500 (0.0500)  time: 1.0096  data: 0.0013  max mem: 78493
Epoch: [189]  [ 80/312]  eta: 0:04:45  lr: 0.001356  min_lr: 0.001356  loss: 2.2293 (2.1056)  weight_decay: 0.0500 (0.0500)  time: 1.0102  data: 0.0013  max mem: 78493
Epoch: [189]  [ 90/312]  eta: 0:04:27  lr: 0.001355  min_lr: 0.001355  loss: 2.1966 (2.0884)  weight_decay: 0.0500 (0.0500)  time: 1.0092  data: 0.0004  max mem: 78493
Epoch: [189]  [100/312]  eta: 0:04:11  lr: 0.001355  min_lr: 0.001355  loss: 2.1601 (2.0958)  weight_decay: 0.0500 (0.0500)  time: 1.0088  data: 0.0004  max mem: 78493
Epoch: [189]  [110/312]  eta: 0:03:56  lr: 0.001354  min_lr: 0.001354  loss: 2.3055 (2.1161)  weight_decay: 0.0500 (0.0500)  time: 1.0086  data: 0.0004  max mem: 78493
Epoch: [189]  [120/312]  eta: 0:03:41  lr: 0.001353  min_lr: 0.001353  loss: 2.3080 (2.1149)  weight_decay: 0.0500 (0.0500)  time: 1.0081  data: 0.0004  max mem: 78493
Epoch: [189]  [130/312]  eta: 0:03:28  lr: 0.001352  min_lr: 0.001352  loss: 2.2129 (2.1072)  weight_decay: 0.0500 (0.0500)  time: 1.0067  data: 0.0004  max mem: 78493
Epoch: [189]  [140/312]  eta: 0:03:15  lr: 0.001352  min_lr: 0.001352  loss: 2.0000 (2.1067)  weight_decay: 0.0500 (0.0500)  time: 1.0073  data: 0.0004  max mem: 78493
Epoch: [189]  [150/312]  eta: 0:03:02  lr: 0.001351  min_lr: 0.001351  loss: 2.1580 (2.1162)  weight_decay: 0.0500 (0.0500)  time: 1.0066  data: 0.0004  max mem: 78493
Epoch: [189]  [160/312]  eta: 0:02:50  lr: 0.001350  min_lr: 0.001350  loss: 2.2328 (2.1236)  weight_decay: 0.0500 (0.0500)  time: 1.0047  data: 0.0004  max mem: 78493
Epoch: [189]  [170/312]  eta: 0:02:37  lr: 0.001350  min_lr: 0.001350  loss: 2.2100 (2.1178)  weight_decay: 0.0500 (0.0500)  time: 1.0044  data: 0.0005  max mem: 78493
Epoch: [189]  [180/312]  eta: 0:02:26  lr: 0.001349  min_lr: 0.001349  loss: 1.9936 (2.1102)  weight_decay: 0.0500 (0.0500)  time: 1.0054  data: 0.0005  max mem: 78493
Epoch: [189]  [190/312]  eta: 0:02:14  lr: 0.001348  min_lr: 0.001348  loss: 2.1489 (2.1177)  weight_decay: 0.0500 (0.0500)  time: 1.0075  data: 0.0004  max mem: 78493
Epoch: [189]  [200/312]  eta: 0:02:02  lr: 0.001348  min_lr: 0.001348  loss: 2.2049 (2.1202)  weight_decay: 0.0500 (0.0500)  time: 1.0061  data: 0.0005  max mem: 78493
Epoch: [189]  [210/312]  eta: 0:01:51  lr: 0.001347  min_lr: 0.001347  loss: 2.1235 (2.1252)  weight_decay: 0.0500 (0.0500)  time: 1.0050  data: 0.0005  max mem: 78493
Epoch: [189]  [220/312]  eta: 0:01:40  lr: 0.001346  min_lr: 0.001346  loss: 1.9846 (2.1166)  weight_decay: 0.0500 (0.0500)  time: 1.0058  data: 0.0004  max mem: 78493
Epoch: [189]  [230/312]  eta: 0:01:28  lr: 0.001346  min_lr: 0.001346  loss: 2.1414 (2.1215)  weight_decay: 0.0500 (0.0500)  time: 1.0057  data: 0.0004  max mem: 78493
Epoch: [189]  [240/312]  eta: 0:01:17  lr: 0.001345  min_lr: 0.001345  loss: 2.3312 (2.1284)  weight_decay: 0.0500 (0.0500)  time: 1.0046  data: 0.0004  max mem: 78493
Epoch: [189]  [250/312]  eta: 0:01:06  lr: 0.001344  min_lr: 0.001344  loss: 2.3082 (2.1335)  weight_decay: 0.0500 (0.0500)  time: 1.0036  data: 0.0004  max mem: 78493
Epoch: [189]  [260/312]  eta: 0:00:55  lr: 0.001344  min_lr: 0.001344  loss: 2.2702 (2.1347)  weight_decay: 0.0500 (0.0500)  time: 1.0049  data: 0.0004  max mem: 78493
Epoch: [189]  [270/312]  eta: 0:00:45  lr: 0.001343  min_lr: 0.001343  loss: 2.0667 (2.1364)  weight_decay: 0.0500 (0.0500)  time: 1.0070  data: 0.0005  max mem: 78493
Epoch: [189]  [280/312]  eta: 0:00:34  lr: 0.001342  min_lr: 0.001342  loss: 2.0640 (2.1331)  weight_decay: 0.0500 (0.0500)  time: 1.0074  data: 0.0011  max mem: 78493
Epoch: [189]  [290/312]  eta: 0:00:23  lr: 0.001342  min_lr: 0.001342  loss: 2.0035 (2.1284)  weight_decay: 0.0500 (0.0500)  time: 1.0046  data: 0.0009  max mem: 78493
Epoch: [189]  [300/312]  eta: 0:00:12  lr: 0.001341  min_lr: 0.001341  loss: 2.0471 (2.1300)  weight_decay: 0.0500 (0.0500)  time: 1.0017  data: 0.0001  max mem: 78493
Epoch: [189]  [310/312]  eta: 0:00:02  lr: 0.001340  min_lr: 0.001340  loss: 2.0471 (2.1250)  weight_decay: 0.0500 (0.0500)  time: 1.0015  data: 0.0001  max mem: 78493
Epoch: [189]  [311/312]  eta: 0:00:01  lr: 0.001340  min_lr: 0.001340  loss: 2.0471 (2.1255)  weight_decay: 0.0500 (0.0500)  time: 1.0015  data: 0.0001  max mem: 78493
Epoch: [189] Total time: 0:05:33 (1.0692 s / it)
Averaged stats: lr: 0.001340  min_lr: 0.001340  loss: 2.0471 (2.1451)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:17  loss: 0.5857 (0.5857)  acc1: 84.7656 (84.7656)  acc5: 97.3958 (97.3958)  time: 8.6156  data: 8.3384  max mem: 78493
Test:  [8/9]  eta: 0:00:01  loss: 0.8969 (0.8390)  acc1: 78.5156 (78.0160)  acc5: 94.4010 (94.4320)  time: 1.1556  data: 0.9266  max mem: 78493
Test: Total time: 0:00:10 (1.1714 s / it)
* Acc@1 78.476 Acc@5 94.428 loss 0.827
Accuracy of the model on the 50000 test images: 78.5%
Max accuracy: 78.49%
Epoch: [190]  [  0/312]  eta: 1:24:16  lr: 0.001340  min_lr: 0.001340  loss: 2.2709 (2.2709)  weight_decay: 0.0500 (0.0500)  time: 16.2066  data: 12.0684  max mem: 78493
Epoch: [190]  [ 10/312]  eta: 0:13:08  lr: 0.001339  min_lr: 0.001339  loss: 2.2625 (2.0516)  weight_decay: 0.0500 (0.0500)  time: 2.6103  data: 1.2898  max mem: 78493
Epoch: [190]  [ 20/312]  eta: 0:09:01  lr: 0.001339  min_lr: 0.001339  loss: 1.9748 (2.0427)  weight_decay: 0.0500 (0.0500)  time: 1.1358  data: 0.1063  max mem: 78493
Epoch: [190]  [ 30/312]  eta: 0:07:25  lr: 0.001338  min_lr: 0.001338  loss: 2.2042 (2.1120)  weight_decay: 0.0500 (0.0500)  time: 1.0137  data: 0.0005  max mem: 78493
Epoch: [190]  [ 40/312]  eta: 0:06:32  lr: 0.001337  min_lr: 0.001337  loss: 2.2747 (2.1428)  weight_decay: 0.0500 (0.0500)  time: 1.0090  data: 0.0004  max mem: 78493
Epoch: [190]  [ 50/312]  eta: 0:05:55  lr: 0.001337  min_lr: 0.001337  loss: 2.2209 (2.1328)  weight_decay: 0.0500 (0.0500)  time: 1.0100  data: 0.0005  max mem: 78493
Epoch: [190]  [ 60/312]  eta: 0:05:27  lr: 0.001336  min_lr: 0.001336  loss: 2.1433 (2.1324)  weight_decay: 0.0500 (0.0500)  time: 1.0110  data: 0.0005  max mem: 78493
Epoch: [190]  [ 70/312]  eta: 0:05:04  lr: 0.001335  min_lr: 0.001335  loss: 2.2865 (2.1575)  weight_decay: 0.0500 (0.0500)  time: 1.0104  data: 0.0005  max mem: 78493
Epoch: [190]  [ 80/312]  eta: 0:04:44  lr: 0.001335  min_lr: 0.001335  loss: 2.2996 (2.1623)  weight_decay: 0.0500 (0.0500)  time: 1.0067  data: 0.0004  max mem: 78493
Epoch: [190]  [ 90/312]  eta: 0:04:27  lr: 0.001334  min_lr: 0.001334  loss: 2.2607 (2.1636)  weight_decay: 0.0500 (0.0500)  time: 1.0085  data: 0.0012  max mem: 78493
Epoch: [190]  [100/312]  eta: 0:04:11  lr: 0.001333  min_lr: 0.001333  loss: 2.2934 (2.1723)  weight_decay: 0.0500 (0.0500)  time: 1.0086  data: 0.0012  max mem: 78493
Epoch: [190]  [110/312]  eta: 0:03:56  lr: 0.001333  min_lr: 0.001333  loss: 2.2495 (2.1726)  weight_decay: 0.0500 (0.0500)  time: 1.0069  data: 0.0005  max mem: 78493
Epoch: [190]  [120/312]  eta: 0:03:41  lr: 0.001332  min_lr: 0.001332  loss: 2.2362 (2.1714)  weight_decay: 0.0500 (0.0500)  time: 1.0070  data: 0.0005  max mem: 78493
Epoch: [190]  [130/312]  eta: 0:03:28  lr: 0.001331  min_lr: 0.001331  loss: 2.2362 (2.1679)  weight_decay: 0.0500 (0.0500)  time: 1.0071  data: 0.0005  max mem: 78493
Epoch: [190]  [140/312]  eta: 0:03:15  lr: 0.001331  min_lr: 0.001331  loss: 2.2616 (2.1721)  weight_decay: 0.0500 (0.0500)  time: 1.0077  data: 0.0004  max mem: 78493
Epoch: [190]  [150/312]  eta: 0:03:02  lr: 0.001330  min_lr: 0.001330  loss: 2.2175 (2.1702)  weight_decay: 0.0500 (0.0500)  time: 1.0059  data: 0.0004  max mem: 78493
Epoch: [190]  [160/312]  eta: 0:02:49  lr: 0.001329  min_lr: 0.001329  loss: 2.1417 (2.1680)  weight_decay: 0.0500 (0.0500)  time: 1.0037  data: 0.0005  max mem: 78493
Epoch: [190]  [170/312]  eta: 0:02:37  lr: 0.001329  min_lr: 0.001329  loss: 2.1417 (2.1713)  weight_decay: 0.0500 (0.0500)  time: 1.0038  data: 0.0005  max mem: 78493
Epoch: [190]  [180/312]  eta: 0:02:25  lr: 0.001328  min_lr: 0.001328  loss: 2.1299 (2.1574)  weight_decay: 0.0500 (0.0500)  time: 1.0048  data: 0.0004  max mem: 78493
Epoch: [190]  [190/312]  eta: 0:02:14  lr: 0.001327  min_lr: 0.001327  loss: 1.9228 (2.1504)  weight_decay: 0.0500 (0.0500)  time: 1.0063  data: 0.0004  max mem: 78493
Epoch: [190]  [200/312]  eta: 0:02:02  lr: 0.001327  min_lr: 0.001327  loss: 2.1418 (2.1470)  weight_decay: 0.0500 (0.0500)  time: 1.0068  data: 0.0004  max mem: 78493
Epoch: [190]  [210/312]  eta: 0:01:51  lr: 0.001326  min_lr: 0.001326  loss: 2.2697 (2.1517)  weight_decay: 0.0500 (0.0500)  time: 1.0062  data: 0.0004  max mem: 78493
Epoch: [190]  [220/312]  eta: 0:01:40  lr: 0.001325  min_lr: 0.001325  loss: 2.2697 (2.1544)  weight_decay: 0.0500 (0.0500)  time: 1.0050  data: 0.0004  max mem: 78493
Epoch: [190]  [230/312]  eta: 0:01:28  lr: 0.001325  min_lr: 0.001325  loss: 2.2579 (2.1536)  weight_decay: 0.0500 (0.0500)  time: 1.0045  data: 0.0004  max mem: 78493
Epoch: [190]  [240/312]  eta: 0:01:17  lr: 0.001324  min_lr: 0.001324  loss: 2.2581 (2.1603)  weight_decay: 0.0500 (0.0500)  time: 1.0052  data: 0.0004  max mem: 78493
Epoch: [190]  [250/312]  eta: 0:01:06  lr: 0.001323  min_lr: 0.001323  loss: 2.3725 (2.1651)  weight_decay: 0.0500 (0.0500)  time: 1.0063  data: 0.0004  max mem: 78493
Epoch: [190]  [260/312]  eta: 0:00:55  lr: 0.001322  min_lr: 0.001322  loss: 2.1731 (2.1588)  weight_decay: 0.0500 (0.0500)  time: 1.0069  data: 0.0015  max mem: 78493
Epoch: [190]  [270/312]  eta: 0:00:45  lr: 0.001322  min_lr: 0.001322  loss: 2.0214 (2.1555)  weight_decay: 0.0500 (0.0500)  time: 1.0076  data: 0.0015  max mem: 78493
Epoch: [190]  [280/312]  eta: 0:00:34  lr: 0.001321  min_lr: 0.001321  loss: 2.2760 (2.1621)  weight_decay: 0.0500 (0.0500)  time: 1.0087  data: 0.0010  max mem: 78493
Epoch: [190]  [290/312]  eta: 0:00:23  lr: 0.001320  min_lr: 0.001320  loss: 2.2894 (2.1598)  weight_decay: 0.0500 (0.0500)  time: 1.0053  data: 0.0009  max mem: 78493
Epoch: [190]  [300/312]  eta: 0:00:12  lr: 0.001320  min_lr: 0.001320  loss: 2.2623 (2.1622)  weight_decay: 0.0500 (0.0500)  time: 1.0015  data: 0.0001  max mem: 78493
Epoch: [190]  [310/312]  eta: 0:00:02  lr: 0.001319  min_lr: 0.001319  loss: 2.2623 (2.1609)  weight_decay: 0.0500 (0.0500)  time: 1.0012  data: 0.0002  max mem: 78493
Epoch: [190]  [311/312]  eta: 0:00:01  lr: 0.001319  min_lr: 0.001319  loss: 2.2623 (2.1613)  weight_decay: 0.0500 (0.0500)  time: 1.0013  data: 0.0002  max mem: 78493
Epoch: [190] Total time: 0:05:33 (1.0692 s / it)
Averaged stats: lr: 0.001319  min_lr: 0.001319  loss: 2.2623 (2.1283)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:18  loss: 0.6037 (0.6037)  acc1: 84.6354 (84.6354)  acc5: 96.8750 (96.8750)  time: 8.7027  data: 8.4393  max mem: 78493
Test:  [8/9]  eta: 0:00:01  loss: 0.9283 (0.8350)  acc1: 76.5625 (77.7760)  acc5: 95.0521 (94.3520)  time: 1.1696  data: 0.9378  max mem: 78493
Test: Total time: 0:00:10 (1.2191 s / it)
* Acc@1 78.676 Acc@5 94.410 loss 0.808
Accuracy of the model on the 50000 test images: 78.7%
Max accuracy: 78.68%
Epoch: [191]  [  0/312]  eta: 1:26:25  lr: 0.001319  min_lr: 0.001319  loss: 2.1037 (2.1037)  weight_decay: 0.0500 (0.0500)  time: 16.6190  data: 15.6184  max mem: 78493
Epoch: [191]  [ 10/312]  eta: 0:13:37  lr: 0.001318  min_lr: 0.001318  loss: 2.3245 (2.2162)  weight_decay: 0.0500 (0.0500)  time: 2.7068  data: 1.4207  max mem: 78493
Epoch: [191]  [ 20/312]  eta: 0:09:13  lr: 0.001318  min_lr: 0.001318  loss: 2.2714 (2.0961)  weight_decay: 0.0500 (0.0500)  time: 1.1604  data: 0.0007  max mem: 78493
Epoch: [191]  [ 30/312]  eta: 0:07:33  lr: 0.001317  min_lr: 0.001317  loss: 2.1514 (2.1408)  weight_decay: 0.0500 (0.0500)  time: 1.0066  data: 0.0016  max mem: 78493
Epoch: [191]  [ 40/312]  eta: 0:06:37  lr: 0.001316  min_lr: 0.001316  loss: 2.3166 (2.1905)  weight_decay: 0.0500 (0.0500)  time: 1.0070  data: 0.0016  max mem: 78493
Epoch: [191]  [ 50/312]  eta: 0:05:59  lr: 0.001316  min_lr: 0.001316  loss: 2.1153 (2.1482)  weight_decay: 0.0500 (0.0500)  time: 1.0074  data: 0.0005  max mem: 78493
Epoch: [191]  [ 60/312]  eta: 0:05:31  lr: 0.001315  min_lr: 0.001315  loss: 2.0362 (2.1291)  weight_decay: 0.0500 (0.0500)  time: 1.0078  data: 0.0004  max mem: 78493
Epoch: [191]  [ 70/312]  eta: 0:05:07  lr: 0.001314  min_lr: 0.001314  loss: 1.9566 (2.1059)  weight_decay: 0.0500 (0.0500)  time: 1.0074  data: 0.0004  max mem: 78493
Epoch: [191]  [ 80/312]  eta: 0:04:47  lr: 0.001314  min_lr: 0.001314  loss: 2.0468 (2.1097)  weight_decay: 0.0500 (0.0500)  time: 1.0093  data: 0.0004  max mem: 78493
Epoch: [191]  [ 90/312]  eta: 0:04:29  lr: 0.001313  min_lr: 0.001313  loss: 2.2246 (2.1136)  weight_decay: 0.0500 (0.0500)  time: 1.0102  data: 0.0005  max mem: 78493
Epoch: [191]  [100/312]  eta: 0:04:12  lr: 0.001312  min_lr: 0.001312  loss: 1.8953 (2.0875)  weight_decay: 0.0500 (0.0500)  time: 1.0081  data: 0.0005  max mem: 78493
Epoch: [191]  [110/312]  eta: 0:03:57  lr: 0.001312  min_lr: 0.001312  loss: 1.8953 (2.0839)  weight_decay: 0.0500 (0.0500)  time: 1.0086  data: 0.0004  max mem: 78493
Epoch: [191]  [120/312]  eta: 0:03:43  lr: 0.001311  min_lr: 0.001311  loss: 2.0648 (2.0814)  weight_decay: 0.0500 (0.0500)  time: 1.0096  data: 0.0004  max mem: 78493
Epoch: [191]  [130/312]  eta: 0:03:29  lr: 0.001310  min_lr: 0.001310  loss: 2.1621 (2.0838)  weight_decay: 0.0500 (0.0500)  time: 1.0075  data: 0.0005  max mem: 78493
Epoch: [191]  [140/312]  eta: 0:03:16  lr: 0.001310  min_lr: 0.001310  loss: 2.1621 (2.0763)  weight_decay: 0.0500 (0.0500)  time: 1.0094  data: 0.0004  max mem: 78493
Epoch: [191]  [150/312]  eta: 0:03:03  lr: 0.001309  min_lr: 0.001309  loss: 2.1159 (2.0817)  weight_decay: 0.0500 (0.0500)  time: 1.0108  data: 0.0004  max mem: 78493
Epoch: [191]  [160/312]  eta: 0:02:50  lr: 0.001308  min_lr: 0.001308  loss: 2.2527 (2.0948)  weight_decay: 0.0500 (0.0500)  time: 1.0075  data: 0.0005  max mem: 78493
Epoch: [191]  [170/312]  eta: 0:02:38  lr: 0.001307  min_lr: 0.001307  loss: 2.3076 (2.0923)  weight_decay: 0.0500 (0.0500)  time: 1.0077  data: 0.0005  max mem: 78493
Epoch: [191]  [180/312]  eta: 0:02:26  lr: 0.001307  min_lr: 0.001307  loss: 2.1252 (2.0920)  weight_decay: 0.0500 (0.0500)  time: 1.0082  data: 0.0004  max mem: 78493
Epoch: [191]  [190/312]  eta: 0:02:14  lr: 0.001306  min_lr: 0.001306  loss: 2.0446 (2.0892)  weight_decay: 0.0500 (0.0500)  time: 1.0072  data: 0.0005  max mem: 78493
Epoch: [191]  [200/312]  eta: 0:02:03  lr: 0.001305  min_lr: 0.001305  loss: 2.0519 (2.0842)  weight_decay: 0.0500 (0.0500)  time: 1.0083  data: 0.0014  max mem: 78493
Epoch: [191]  [210/312]  eta: 0:01:51  lr: 0.001305  min_lr: 0.001305  loss: 2.1270 (2.0922)  weight_decay: 0.0500 (0.0500)  time: 1.0078  data: 0.0013  max mem: 78493
Epoch: [191]  [220/312]  eta: 0:01:40  lr: 0.001304  min_lr: 0.001304  loss: 2.3584 (2.1027)  weight_decay: 0.0500 (0.0500)  time: 1.0093  data: 0.0005  max mem: 78493
Epoch: [191]  [230/312]  eta: 0:01:29  lr: 0.001303  min_lr: 0.001303  loss: 2.3264 (2.1023)  weight_decay: 0.0500 (0.0500)  time: 1.0095  data: 0.0004  max mem: 78493
Epoch: [191]  [240/312]  eta: 0:01:18  lr: 0.001303  min_lr: 0.001303  loss: 2.2780 (2.1055)  weight_decay: 0.0500 (0.0500)  time: 1.0065  data: 0.0005  max mem: 78493
Epoch: [191]  [250/312]  eta: 0:01:07  lr: 0.001302  min_lr: 0.001302  loss: 2.2674 (2.1049)  weight_decay: 0.0500 (0.0500)  time: 1.0071  data: 0.0005  max mem: 78493
Epoch: [191]  [260/312]  eta: 0:00:56  lr: 0.001301  min_lr: 0.001301  loss: 2.1271 (2.1000)  weight_decay: 0.0500 (0.0500)  time: 1.0070  data: 0.0004  max mem: 78493
Epoch: [191]  [270/312]  eta: 0:00:45  lr: 0.001301  min_lr: 0.001301  loss: 2.2584 (2.1075)  weight_decay: 0.0500 (0.0500)  time: 1.0057  data: 0.0004  max mem: 78493
Epoch: [191]  [280/312]  eta: 0:00:34  lr: 0.001300  min_lr: 0.001300  loss: 2.2918 (2.1113)  weight_decay: 0.0500 (0.0500)  time: 1.0068  data: 0.0011  max mem: 78493
Epoch: [191]  [290/312]  eta: 0:00:23  lr: 0.001299  min_lr: 0.001299  loss: 2.1466 (2.1088)  weight_decay: 0.0500 (0.0500)  time: 1.0058  data: 0.0009  max mem: 78493
Epoch: [191]  [300/312]  eta: 0:00:12  lr: 0.001299  min_lr: 0.001299  loss: 2.0848 (2.1093)  weight_decay: 0.0500 (0.0500)  time: 1.0026  data: 0.0001  max mem: 78493
Epoch: [191]  [310/312]  eta: 0:00:02  lr: 0.001298  min_lr: 0.001298  loss: 2.1981 (2.1129)  weight_decay: 0.0500 (0.0500)  time: 1.0014  data: 0.0001  max mem: 78493
Epoch: [191]  [311/312]  eta: 0:00:01  lr: 0.001298  min_lr: 0.001298  loss: 2.2110 (2.1143)  weight_decay: 0.0500 (0.0500)  time: 1.0014  data: 0.0001  max mem: 78493
Epoch: [191] Total time: 0:05:34 (1.0730 s / it)
Averaged stats: lr: 0.001298  min_lr: 0.001298  loss: 2.2110 (2.1349)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:21  loss: 0.5929 (0.5929)  acc1: 84.8958 (84.8958)  acc5: 96.2240 (96.2240)  time: 9.0112  data: 8.7430  max mem: 78493
Test:  [8/9]  eta: 0:00:01  loss: 0.9124 (0.8433)  acc1: 79.5573 (78.5280)  acc5: 94.9219 (94.2560)  time: 1.2003  data: 0.9715  max mem: 78493
Test: Total time: 0:00:11 (1.2274 s / it)
* Acc@1 78.504 Acc@5 94.284 loss 0.823
Accuracy of the model on the 50000 test images: 78.5%
Max accuracy: 78.68%
Epoch: [192]  [  0/312]  eta: 1:28:09  lr: 0.001298  min_lr: 0.001298  loss: 1.5526 (1.5526)  weight_decay: 0.0500 (0.0500)  time: 16.9540  data: 15.9182  max mem: 78493
Epoch: [192]  [ 10/312]  eta: 0:13:30  lr: 0.001297  min_lr: 0.001297  loss: 2.0069 (1.9348)  weight_decay: 0.0500 (0.0500)  time: 2.6825  data: 1.4495  max mem: 78493
Epoch: [192]  [ 20/312]  eta: 0:09:10  lr: 0.001297  min_lr: 0.001297  loss: 2.1058 (2.0163)  weight_decay: 0.0500 (0.0500)  time: 1.1313  data: 0.0016  max mem: 78493
Epoch: [192]  [ 30/312]  eta: 0:07:31  lr: 0.001296  min_lr: 0.001296  loss: 2.1058 (2.0123)  weight_decay: 0.0500 (0.0500)  time: 1.0067  data: 0.0005  max mem: 78493
Epoch: [192]  [ 40/312]  eta: 0:06:36  lr: 0.001295  min_lr: 0.001295  loss: 2.1161 (2.0836)  weight_decay: 0.0500 (0.0500)  time: 1.0061  data: 0.0004  max mem: 78493
Epoch: [192]  [ 50/312]  eta: 0:05:58  lr: 0.001295  min_lr: 0.001295  loss: 2.2112 (2.0837)  weight_decay: 0.0500 (0.0500)  time: 1.0060  data: 0.0004  max mem: 78493
Epoch: [192]  [ 60/312]  eta: 0:05:29  lr: 0.001294  min_lr: 0.001294  loss: 2.1355 (2.1043)  weight_decay: 0.0500 (0.0500)  time: 1.0069  data: 0.0004  max mem: 78493
Epoch: [192]  [ 70/312]  eta: 0:05:06  lr: 0.001293  min_lr: 0.001293  loss: 2.2396 (2.1208)  weight_decay: 0.0500 (0.0500)  time: 1.0064  data: 0.0005  max mem: 78493
Epoch: [192]  [ 80/312]  eta: 0:04:46  lr: 0.001293  min_lr: 0.001293  loss: 2.2396 (2.1195)  weight_decay: 0.0500 (0.0500)  time: 1.0061  data: 0.0013  max mem: 78493
Epoch: [192]  [ 90/312]  eta: 0:04:28  lr: 0.001292  min_lr: 0.001292  loss: 2.2385 (2.1341)  weight_decay: 0.0500 (0.0500)  time: 1.0088  data: 0.0012  max mem: 78493
Epoch: [192]  [100/312]  eta: 0:04:12  lr: 0.001291  min_lr: 0.001291  loss: 2.2977 (2.1427)  weight_decay: 0.0500 (0.0500)  time: 1.0101  data: 0.0004  max mem: 78493
Epoch: [192]  [110/312]  eta: 0:03:57  lr: 0.001291  min_lr: 0.001291  loss: 2.2241 (2.1345)  weight_decay: 0.0500 (0.0500)  time: 1.0103  data: 0.0004  max mem: 78493
Epoch: [192]  [120/312]  eta: 0:03:42  lr: 0.001290  min_lr: 0.001290  loss: 2.1404 (2.1330)  weight_decay: 0.0500 (0.0500)  time: 1.0102  data: 0.0004  max mem: 78493
Epoch: [192]  [130/312]  eta: 0:03:29  lr: 0.001289  min_lr: 0.001289  loss: 2.1870 (2.1331)  weight_decay: 0.0500 (0.0500)  time: 1.0093  data: 0.0004  max mem: 78493
Epoch: [192]  [140/312]  eta: 0:03:15  lr: 0.001289  min_lr: 0.001289  loss: 2.1980 (2.1429)  weight_decay: 0.0500 (0.0500)  time: 1.0092  data: 0.0004  max mem: 78493
Epoch: [192]  [150/312]  eta: 0:03:03  lr: 0.001288  min_lr: 0.001288  loss: 2.3144 (2.1553)  weight_decay: 0.0500 (0.0500)  time: 1.0080  data: 0.0005  max mem: 78493
Epoch: [192]  [160/312]  eta: 0:02:50  lr: 0.001287  min_lr: 0.001287  loss: 2.3029 (2.1544)  weight_decay: 0.0500 (0.0500)  time: 1.0100  data: 0.0005  max mem: 78493
Epoch: [192]  [170/312]  eta: 0:02:38  lr: 0.001286  min_lr: 0.001286  loss: 2.0318 (2.1456)  weight_decay: 0.0500 (0.0500)  time: 1.0114  data: 0.0005  max mem: 78493
Epoch: [192]  [180/312]  eta: 0:02:26  lr: 0.001286  min_lr: 0.001286  loss: 2.1203 (2.1491)  weight_decay: 0.0500 (0.0500)  time: 1.0090  data: 0.0005  max mem: 78493
Epoch: [192]  [190/312]  eta: 0:02:14  lr: 0.001285  min_lr: 0.001285  loss: 2.2484 (2.1530)  weight_decay: 0.0500 (0.0500)  time: 1.0073  data: 0.0004  max mem: 78493
Epoch: [192]  [200/312]  eta: 0:02:03  lr: 0.001284  min_lr: 0.001284  loss: 2.2318 (2.1490)  weight_decay: 0.0500 (0.0500)  time: 1.0059  data: 0.0004  max mem: 78493
Epoch: [192]  [210/312]  eta: 0:01:51  lr: 0.001284  min_lr: 0.001284  loss: 2.1652 (2.1513)  weight_decay: 0.0500 (0.0500)  time: 1.0059  data: 0.0004  max mem: 78493
Epoch: [192]  [220/312]  eta: 0:01:40  lr: 0.001283  min_lr: 0.001283  loss: 2.2385 (2.1543)  weight_decay: 0.0500 (0.0500)  time: 1.0071  data: 0.0004  max mem: 78493
Epoch: [192]  [230/312]  eta: 0:01:29  lr: 0.001282  min_lr: 0.001282  loss: 2.2734 (2.1539)  weight_decay: 0.0500 (0.0500)  time: 1.0084  data: 0.0004  max mem: 78493
Epoch: [192]  [240/312]  eta: 0:01:18  lr: 0.001282  min_lr: 0.001282  loss: 2.2042 (2.1542)  weight_decay: 0.0500 (0.0500)  time: 1.0071  data: 0.0004  max mem: 78493
Epoch: [192]  [250/312]  eta: 0:01:07  lr: 0.001281  min_lr: 0.001281  loss: 2.2042 (2.1567)  weight_decay: 0.0500 (0.0500)  time: 1.0060  data: 0.0004  max mem: 78493
Epoch: [192]  [260/312]  eta: 0:00:56  lr: 0.001280  min_lr: 0.001280  loss: 2.0920 (2.1543)  weight_decay: 0.0500 (0.0500)  time: 1.0056  data: 0.0004  max mem: 78493
Epoch: [192]  [270/312]  eta: 0:00:45  lr: 0.001280  min_lr: 0.001280  loss: 2.0787 (2.1493)  weight_decay: 0.0500 (0.0500)  time: 1.0048  data: 0.0004  max mem: 78493
Epoch: [192]  [280/312]  eta: 0:00:34  lr: 0.001279  min_lr: 0.001279  loss: 2.2574 (2.1471)  weight_decay: 0.0500 (0.0500)  time: 1.0068  data: 0.0021  max mem: 78493
Epoch: [192]  [290/312]  eta: 0:00:23  lr: 0.001278  min_lr: 0.001278  loss: 2.2016 (2.1448)  weight_decay: 0.0500 (0.0500)  time: 1.0051  data: 0.0019  max mem: 78493
Epoch: [192]  [300/312]  eta: 0:00:12  lr: 0.001278  min_lr: 0.001278  loss: 2.0809 (2.1441)  weight_decay: 0.0500 (0.0500)  time: 1.0015  data: 0.0001  max mem: 78493
Epoch: [192]  [310/312]  eta: 0:00:02  lr: 0.001277  min_lr: 0.001277  loss: 2.3155 (2.1521)  weight_decay: 0.0500 (0.0500)  time: 1.0013  data: 0.0001  max mem: 78493
Epoch: [192]  [311/312]  eta: 0:00:01  lr: 0.001277  min_lr: 0.001277  loss: 2.2628 (2.1511)  weight_decay: 0.0500 (0.0500)  time: 1.0013  data: 0.0001  max mem: 78493
Epoch: [192] Total time: 0:05:34 (1.0720 s / it)
Averaged stats: lr: 0.001277  min_lr: 0.001277  loss: 2.2628 (2.1268)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:12  loss: 0.6301 (0.6301)  acc1: 85.1562 (85.1562)  acc5: 96.7448 (96.7448)  time: 8.0465  data: 7.7734  max mem: 78493
Test:  [8/9]  eta: 0:00:01  loss: 0.8858 (0.8263)  acc1: 78.7760 (78.5280)  acc5: 94.5312 (94.5920)  time: 1.0924  data: 0.8638  max mem: 78493
Test: Total time: 0:00:09 (1.1015 s / it)
* Acc@1 78.708 Acc@5 94.556 loss 0.810
Accuracy of the model on the 50000 test images: 78.7%
Max accuracy: 78.71%
Epoch: [193]  [  0/312]  eta: 1:20:26  lr: 0.001277  min_lr: 0.001277  loss: 1.6845 (1.6845)  weight_decay: 0.0500 (0.0500)  time: 15.4702  data: 14.1670  max mem: 78493
Epoch: [193]  [ 10/312]  eta: 0:12:39  lr: 0.001276  min_lr: 0.001276  loss: 1.8953 (1.9639)  weight_decay: 0.0500 (0.0500)  time: 2.5142  data: 1.3582  max mem: 78493
Epoch: [193]  [ 20/312]  eta: 0:08:45  lr: 0.001276  min_lr: 0.001276  loss: 1.9971 (2.0971)  weight_decay: 0.0500 (0.0500)  time: 1.1171  data: 0.0390  max mem: 78493
Epoch: [193]  [ 30/312]  eta: 0:07:15  lr: 0.001275  min_lr: 0.001275  loss: 2.1085 (2.0814)  weight_decay: 0.0500 (0.0500)  time: 1.0112  data: 0.0005  max mem: 78493
Epoch: [193]  [ 40/312]  eta: 0:06:24  lr: 0.001274  min_lr: 0.001274  loss: 2.1085 (2.0862)  weight_decay: 0.0500 (0.0500)  time: 1.0066  data: 0.0004  max mem: 78493
Epoch: [193]  [ 50/312]  eta: 0:05:49  lr: 0.001274  min_lr: 0.001274  loss: 2.2005 (2.0888)  weight_decay: 0.0500 (0.0500)  time: 1.0084  data: 0.0005  max mem: 78493
Epoch: [193]  [ 60/312]  eta: 0:05:22  lr: 0.001273  min_lr: 0.001273  loss: 2.1564 (2.0748)  weight_decay: 0.0500 (0.0500)  time: 1.0108  data: 0.0005  max mem: 78493
Epoch: [193]  [ 70/312]  eta: 0:05:00  lr: 0.001272  min_lr: 0.001272  loss: 2.0741 (2.0605)  weight_decay: 0.0500 (0.0500)  time: 1.0101  data: 0.0004  max mem: 78493
Epoch: [193]  [ 80/312]  eta: 0:04:41  lr: 0.001272  min_lr: 0.001272  loss: 2.1926 (2.0893)  weight_decay: 0.0500 (0.0500)  time: 1.0092  data: 0.0004  max mem: 78493
Epoch: [193]  [ 90/312]  eta: 0:04:24  lr: 0.001271  min_lr: 0.001271  loss: 2.2580 (2.0952)  weight_decay: 0.0500 (0.0500)  time: 1.0098  data: 0.0004  max mem: 78493
Epoch: [193]  [100/312]  eta: 0:04:08  lr: 0.001270  min_lr: 0.001270  loss: 2.1873 (2.0900)  weight_decay: 0.0500 (0.0500)  time: 1.0076  data: 0.0004  max mem: 78493
Epoch: [193]  [110/312]  eta: 0:03:54  lr: 0.001270  min_lr: 0.001270  loss: 2.0025 (2.0818)  weight_decay: 0.0500 (0.0500)  time: 1.0097  data: 0.0005  max mem: 78493
Epoch: [193]  [120/312]  eta: 0:03:40  lr: 0.001269  min_lr: 0.001269  loss: 2.0139 (2.0778)  weight_decay: 0.0500 (0.0500)  time: 1.0110  data: 0.0004  max mem: 78493
Epoch: [193]  [130/312]  eta: 0:03:26  lr: 0.001268  min_lr: 0.001268  loss: 2.1946 (2.0889)  weight_decay: 0.0500 (0.0500)  time: 1.0078  data: 0.0004  max mem: 78493
Epoch: [193]  [140/312]  eta: 0:03:13  lr: 0.001268  min_lr: 0.001268  loss: 2.2301 (2.0997)  weight_decay: 0.0500 (0.0500)  time: 1.0066  data: 0.0004  max mem: 78493
Epoch: [193]  [150/312]  eta: 0:03:01  lr: 0.001267  min_lr: 0.001267  loss: 2.2301 (2.1039)  weight_decay: 0.0500 (0.0500)  time: 1.0079  data: 0.0004  max mem: 78493
Epoch: [193]  [160/312]  eta: 0:02:49  lr: 0.001266  min_lr: 0.001266  loss: 1.9975 (2.0935)  weight_decay: 0.0500 (0.0500)  time: 1.0103  data: 0.0004  max mem: 78493
Epoch: [193]  [170/312]  eta: 0:02:37  lr: 0.001266  min_lr: 0.001266  loss: 2.0822 (2.1008)  weight_decay: 0.0500 (0.0500)  time: 1.0089  data: 0.0004  max mem: 78493
Epoch: [193]  [180/312]  eta: 0:02:25  lr: 0.001265  min_lr: 0.001265  loss: 2.3093 (2.1017)  weight_decay: 0.0500 (0.0500)  time: 1.0085  data: 0.0004  max mem: 78493
Epoch: [193]  [190/312]  eta: 0:02:13  lr: 0.001264  min_lr: 0.001264  loss: 2.2087 (2.1059)  weight_decay: 0.0500 (0.0500)  time: 1.0100  data: 0.0004  max mem: 78493
Epoch: [193]  [200/312]  eta: 0:02:02  lr: 0.001264  min_lr: 0.001264  loss: 2.1381 (2.0986)  weight_decay: 0.0500 (0.0500)  time: 1.0093  data: 0.0013  max mem: 78493
Epoch: [193]  [210/312]  eta: 0:01:50  lr: 0.001263  min_lr: 0.001263  loss: 1.8841 (2.0971)  weight_decay: 0.0500 (0.0500)  time: 1.0058  data: 0.0013  max mem: 78493
Epoch: [193]  [220/312]  eta: 0:01:39  lr: 0.001262  min_lr: 0.001262  loss: 2.3074 (2.1116)  weight_decay: 0.0500 (0.0500)  time: 1.0049  data: 0.0005  max mem: 78493
Epoch: [193]  [230/312]  eta: 0:01:28  lr: 0.001262  min_lr: 0.001262  loss: 2.3285 (2.1124)  weight_decay: 0.0500 (0.0500)  time: 1.0051  data: 0.0005  max mem: 78493
Epoch: [193]  [240/312]  eta: 0:01:17  lr: 0.001261  min_lr: 0.001261  loss: 2.2127 (2.1099)  weight_decay: 0.0500 (0.0500)  time: 1.0050  data: 0.0004  max mem: 78493
Epoch: [193]  [250/312]  eta: 0:01:06  lr: 0.001260  min_lr: 0.001260  loss: 2.2782 (2.1132)  weight_decay: 0.0500 (0.0500)  time: 1.0055  data: 0.0004  max mem: 78493
Epoch: [193]  [260/312]  eta: 0:00:55  lr: 0.001260  min_lr: 0.001260  loss: 2.2455 (2.1108)  weight_decay: 0.0500 (0.0500)  time: 1.0052  data: 0.0004  max mem: 78493
Epoch: [193]  [270/312]  eta: 0:00:44  lr: 0.001259  min_lr: 0.001259  loss: 2.1767 (2.1097)  weight_decay: 0.0500 (0.0500)  time: 1.0053  data: 0.0004  max mem: 78493
Epoch: [193]  [280/312]  eta: 0:00:34  lr: 0.001258  min_lr: 0.001258  loss: 1.9796 (2.1058)  weight_decay: 0.0500 (0.0500)  time: 1.0054  data: 0.0011  max mem: 78493
Epoch: [193]  [290/312]  eta: 0:00:23  lr: 0.001258  min_lr: 0.001258  loss: 1.9441 (2.1013)  weight_decay: 0.0500 (0.0500)  time: 1.0037  data: 0.0009  max mem: 78493
Epoch: [193]  [300/312]  eta: 0:00:12  lr: 0.001257  min_lr: 0.001257  loss: 2.1307 (2.1083)  weight_decay: 0.0500 (0.0500)  time: 1.0016  data: 0.0001  max mem: 78493
Epoch: [193]  [310/312]  eta: 0:00:02  lr: 0.001256  min_lr: 0.001256  loss: 2.3603 (2.1110)  weight_decay: 0.0500 (0.0500)  time: 1.0016  data: 0.0001  max mem: 78493
Epoch: [193]  [311/312]  eta: 0:00:01  lr: 0.001256  min_lr: 0.001256  loss: 2.3680 (2.1123)  weight_decay: 0.0500 (0.0500)  time: 1.0017  data: 0.0001  max mem: 78493
Epoch: [193] Total time: 0:05:32 (1.0662 s / it)
Averaged stats: lr: 0.001256  min_lr: 0.001256  loss: 2.3680 (2.1351)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:15  loss: 0.6204 (0.6204)  acc1: 84.5052 (84.5052)  acc5: 96.7448 (96.7448)  time: 8.3845  data: 8.0937  max mem: 78493
Test:  [8/9]  eta: 0:00:01  loss: 0.9014 (0.8203)  acc1: 77.7344 (78.3840)  acc5: 94.1406 (94.4320)  time: 1.1299  data: 0.8994  max mem: 78493
Test: Total time: 0:00:10 (1.1617 s / it)
* Acc@1 78.926 Acc@5 94.488 loss 0.803
Accuracy of the model on the 50000 test images: 78.9%
Max accuracy: 78.93%
Epoch: [194]  [  0/312]  eta: 1:30:24  lr: 0.001256  min_lr: 0.001256  loss: 2.3057 (2.3057)  weight_decay: 0.0500 (0.0500)  time: 17.3851  data: 16.3658  max mem: 78493
Epoch: [194]  [ 10/312]  eta: 0:12:45  lr: 0.001255  min_lr: 0.001255  loss: 2.2800 (2.2590)  weight_decay: 0.0500 (0.0500)  time: 2.5348  data: 1.4947  max mem: 78493
Epoch: [194]  [ 20/312]  eta: 0:08:49  lr: 0.001255  min_lr: 0.001255  loss: 2.3194 (2.3246)  weight_decay: 0.0500 (0.0500)  time: 1.0345  data: 0.0041  max mem: 78493
Epoch: [194]  [ 30/312]  eta: 0:07:18  lr: 0.001254  min_lr: 0.001254  loss: 2.2792 (2.2760)  weight_decay: 0.0500 (0.0500)  time: 1.0147  data: 0.0005  max mem: 78493
Epoch: [194]  [ 40/312]  eta: 0:06:26  lr: 0.001253  min_lr: 0.001253  loss: 2.0816 (2.1837)  weight_decay: 0.0500 (0.0500)  time: 1.0106  data: 0.0004  max mem: 78493
Epoch: [194]  [ 50/312]  eta: 0:05:51  lr: 0.001253  min_lr: 0.001253  loss: 1.9607 (2.1502)  weight_decay: 0.0500 (0.0500)  time: 1.0120  data: 0.0005  max mem: 78493
Epoch: [194]  [ 60/312]  eta: 0:05:24  lr: 0.001252  min_lr: 0.001252  loss: 2.1541 (2.1812)  weight_decay: 0.0500 (0.0500)  time: 1.0109  data: 0.0005  max mem: 78493
Epoch: [194]  [ 70/312]  eta: 0:05:02  lr: 0.001251  min_lr: 0.001251  loss: 2.2658 (2.1796)  weight_decay: 0.0500 (0.0500)  time: 1.0102  data: 0.0004  max mem: 78493
Epoch: [194]  [ 80/312]  eta: 0:04:42  lr: 0.001251  min_lr: 0.001251  loss: 2.0872 (2.1710)  weight_decay: 0.0500 (0.0500)  time: 1.0092  data: 0.0004  max mem: 78493
Epoch: [194]  [ 90/312]  eta: 0:04:25  lr: 0.001250  min_lr: 0.001250  loss: 2.1747 (2.1758)  weight_decay: 0.0500 (0.0500)  time: 1.0077  data: 0.0004  max mem: 78493
Epoch: [194]  [100/312]  eta: 0:04:09  lr: 0.001249  min_lr: 0.001249  loss: 2.0606 (2.1578)  weight_decay: 0.0500 (0.0500)  time: 1.0094  data: 0.0004  max mem: 78493
Epoch: [194]  [110/312]  eta: 0:03:54  lr: 0.001249  min_lr: 0.001249  loss: 2.1300 (2.1651)  weight_decay: 0.0500 (0.0500)  time: 1.0088  data: 0.0004  max mem: 78493
Epoch: [194]  [120/312]  eta: 0:03:40  lr: 0.001248  min_lr: 0.001248  loss: 2.2586 (2.1673)  weight_decay: 0.0500 (0.0500)  time: 1.0061  data: 0.0005  max mem: 78493
Epoch: [194]  [130/312]  eta: 0:03:27  lr: 0.001247  min_lr: 0.001247  loss: 2.1511 (2.1655)  weight_decay: 0.0500 (0.0500)  time: 1.0065  data: 0.0005  max mem: 78493
Epoch: [194]  [140/312]  eta: 0:03:14  lr: 0.001247  min_lr: 0.001247  loss: 2.1511 (2.1628)  weight_decay: 0.0500 (0.0500)  time: 1.0108  data: 0.0005  max mem: 78493
Epoch: [194]  [150/312]  eta: 0:03:01  lr: 0.001246  min_lr: 0.001246  loss: 2.1549 (2.1611)  weight_decay: 0.0500 (0.0500)  time: 1.0108  data: 0.0004  max mem: 78493
Epoch: [194]  [160/312]  eta: 0:02:49  lr: 0.001245  min_lr: 0.001245  loss: 2.2288 (2.1670)  weight_decay: 0.0500 (0.0500)  time: 1.0090  data: 0.0005  max mem: 78493
Epoch: [194]  [170/312]  eta: 0:02:37  lr: 0.001245  min_lr: 0.001245  loss: 2.2459 (2.1658)  weight_decay: 0.0500 (0.0500)  time: 1.0087  data: 0.0005  max mem: 78493
Epoch: [194]  [180/312]  eta: 0:02:25  lr: 0.001244  min_lr: 0.001244  loss: 2.2202 (2.1580)  weight_decay: 0.0500 (0.0500)  time: 1.0072  data: 0.0005  max mem: 78493
Epoch: [194]  [190/312]  eta: 0:02:13  lr: 0.001243  min_lr: 0.001243  loss: 2.1249 (2.1574)  weight_decay: 0.0500 (0.0500)  time: 1.0077  data: 0.0005  max mem: 78493
Epoch: [194]  [200/312]  eta: 0:02:02  lr: 0.001243  min_lr: 0.001243  loss: 2.1696 (2.1538)  weight_decay: 0.0500 (0.0500)  time: 1.0096  data: 0.0005  max mem: 78493
Epoch: [194]  [210/312]  eta: 0:01:51  lr: 0.001242  min_lr: 0.001242  loss: 2.2634 (2.1617)  weight_decay: 0.0500 (0.0500)  time: 1.0098  data: 0.0004  max mem: 78493
Epoch: [194]  [220/312]  eta: 0:01:39  lr: 0.001241  min_lr: 0.001241  loss: 2.3401 (2.1647)  weight_decay: 0.0500 (0.0500)  time: 1.0078  data: 0.0005  max mem: 78493
Epoch: [194]  [230/312]  eta: 0:01:28  lr: 0.001241  min_lr: 0.001241  loss: 2.3401 (2.1717)  weight_decay: 0.0500 (0.0500)  time: 1.0052  data: 0.0005  max mem: 78493
Epoch: [194]  [240/312]  eta: 0:01:17  lr: 0.001240  min_lr: 0.001240  loss: 2.1299 (2.1593)  weight_decay: 0.0500 (0.0500)  time: 1.0046  data: 0.0004  max mem: 78493
Epoch: [194]  [250/312]  eta: 0:01:06  lr: 0.001239  min_lr: 0.001239  loss: 1.8782 (2.1562)  weight_decay: 0.0500 (0.0500)  time: 1.0052  data: 0.0004  max mem: 78493
Epoch: [194]  [260/312]  eta: 0:00:55  lr: 0.001239  min_lr: 0.001239  loss: 2.1562 (2.1537)  weight_decay: 0.0500 (0.0500)  time: 1.0065  data: 0.0011  max mem: 78493
Epoch: [194]  [270/312]  eta: 0:00:44  lr: 0.001238  min_lr: 0.001238  loss: 2.2640 (2.1554)  weight_decay: 0.0500 (0.0500)  time: 1.0079  data: 0.0011  max mem: 78493
Epoch: [194]  [280/312]  eta: 0:00:34  lr: 0.001237  min_lr: 0.001237  loss: 2.3138 (2.1566)  weight_decay: 0.0500 (0.0500)  time: 1.0077  data: 0.0011  max mem: 78493
Epoch: [194]  [290/312]  eta: 0:00:23  lr: 0.001237  min_lr: 0.001237  loss: 2.1874 (2.1530)  weight_decay: 0.0500 (0.0500)  time: 1.0048  data: 0.0009  max mem: 78493
Epoch: [194]  [300/312]  eta: 0:00:12  lr: 0.001236  min_lr: 0.001236  loss: 2.2153 (2.1552)  weight_decay: 0.0500 (0.0500)  time: 1.0018  data: 0.0001  max mem: 78493
Epoch: [194]  [310/312]  eta: 0:00:02  lr: 0.001235  min_lr: 0.001235  loss: 2.2153 (2.1608)  weight_decay: 0.0500 (0.0500)  time: 1.0018  data: 0.0001  max mem: 78493
Epoch: [194]  [311/312]  eta: 0:00:01  lr: 0.001235  min_lr: 0.001235  loss: 2.2564 (2.1624)  weight_decay: 0.0500 (0.0500)  time: 1.0018  data: 0.0001  max mem: 78493
Epoch: [194] Total time: 0:05:33 (1.0678 s / it)
Averaged stats: lr: 0.001235  min_lr: 0.001235  loss: 2.2564 (2.1251)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:15  loss: 0.5836 (0.5836)  acc1: 85.8073 (85.8073)  acc5: 96.2240 (96.2240)  time: 8.3699  data: 8.0940  max mem: 78493
Test:  [8/9]  eta: 0:00:01  loss: 0.8908 (0.8207)  acc1: 77.2135 (78.3520)  acc5: 94.5312 (94.3040)  time: 1.1283  data: 0.8994  max mem: 78493
Test: Total time: 0:00:10 (1.1498 s / it)
* Acc@1 78.824 Acc@5 94.526 loss 0.812
Accuracy of the model on the 50000 test images: 78.8%
Max accuracy: 78.93%
Epoch: [195]  [  0/312]  eta: 1:21:23  lr: 0.001235  min_lr: 0.001235  loss: 1.3093 (1.3093)  weight_decay: 0.0500 (0.0500)  time: 15.6519  data: 12.9871  max mem: 78493
Epoch: [195]  [ 10/312]  eta: 0:12:54  lr: 0.001235  min_lr: 0.001235  loss: 2.1377 (2.1048)  weight_decay: 0.0500 (0.0500)  time: 2.5650  data: 1.2791  max mem: 78493
Epoch: [195]  [ 20/312]  eta: 0:08:57  lr: 0.001234  min_lr: 0.001234  loss: 2.0628 (1.9883)  weight_decay: 0.0500 (0.0500)  time: 1.1494  data: 0.0545  max mem: 78493
Epoch: [195]  [ 30/312]  eta: 0:07:23  lr: 0.001233  min_lr: 0.001233  loss: 1.9355 (2.0157)  weight_decay: 0.0500 (0.0500)  time: 1.0261  data: 0.0005  max mem: 78493
Epoch: [195]  [ 40/312]  eta: 0:06:30  lr: 0.001233  min_lr: 0.001233  loss: 2.1074 (2.0230)  weight_decay: 0.0500 (0.0500)  time: 1.0093  data: 0.0004  max mem: 78493
Epoch: [195]  [ 50/312]  eta: 0:05:54  lr: 0.001232  min_lr: 0.001232  loss: 2.0641 (2.0459)  weight_decay: 0.0500 (0.0500)  time: 1.0095  data: 0.0004  max mem: 78493
Epoch: [195]  [ 60/312]  eta: 0:05:26  lr: 0.001231  min_lr: 0.001231  loss: 2.1516 (2.0413)  weight_decay: 0.0500 (0.0500)  time: 1.0091  data: 0.0005  max mem: 78493
Epoch: [195]  [ 70/312]  eta: 0:05:03  lr: 0.001231  min_lr: 0.001231  loss: 2.2036 (2.0584)  weight_decay: 0.0500 (0.0500)  time: 1.0068  data: 0.0005  max mem: 78493
Epoch: [195]  [ 80/312]  eta: 0:04:44  lr: 0.001230  min_lr: 0.001230  loss: 2.2036 (2.0703)  weight_decay: 0.0500 (0.0500)  time: 1.0078  data: 0.0004  max mem: 78493
Epoch: [195]  [ 90/312]  eta: 0:04:26  lr: 0.001229  min_lr: 0.001229  loss: 2.1696 (2.0836)  weight_decay: 0.0500 (0.0500)  time: 1.0090  data: 0.0004  max mem: 78493
Epoch: [195]  [100/312]  eta: 0:04:10  lr: 0.001229  min_lr: 0.001229  loss: 2.0894 (2.0709)  weight_decay: 0.0500 (0.0500)  time: 1.0091  data: 0.0004  max mem: 78493
Epoch: [195]  [110/312]  eta: 0:03:55  lr: 0.001228  min_lr: 0.001228  loss: 1.9837 (2.0750)  weight_decay: 0.0500 (0.0500)  time: 1.0108  data: 0.0004  max mem: 78493
Epoch: [195]  [120/312]  eta: 0:03:41  lr: 0.001227  min_lr: 0.001227  loss: 2.0060 (2.0758)  weight_decay: 0.0500 (0.0500)  time: 1.0099  data: 0.0004  max mem: 78493
Epoch: [195]  [130/312]  eta: 0:03:27  lr: 0.001227  min_lr: 0.001227  loss: 2.0087 (2.0817)  weight_decay: 0.0500 (0.0500)  time: 1.0087  data: 0.0012  max mem: 78493
Epoch: [195]  [140/312]  eta: 0:03:14  lr: 0.001226  min_lr: 0.001226  loss: 2.2018 (2.0939)  weight_decay: 0.0500 (0.0500)  time: 1.0074  data: 0.0012  max mem: 78493
Epoch: [195]  [150/312]  eta: 0:03:02  lr: 0.001225  min_lr: 0.001225  loss: 2.2007 (2.1012)  weight_decay: 0.0500 (0.0500)  time: 1.0071  data: 0.0011  max mem: 78493
Epoch: [195]  [160/312]  eta: 0:02:49  lr: 0.001225  min_lr: 0.001225  loss: 2.0824 (2.0993)  weight_decay: 0.0500 (0.0500)  time: 1.0081  data: 0.0011  max mem: 78493
Epoch: [195]  [170/312]  eta: 0:02:37  lr: 0.001224  min_lr: 0.001224  loss: 1.9510 (2.0920)  weight_decay: 0.0500 (0.0500)  time: 1.0077  data: 0.0004  max mem: 78493
Epoch: [195]  [180/312]  eta: 0:02:25  lr: 0.001223  min_lr: 0.001223  loss: 2.0178 (2.0955)  weight_decay: 0.0500 (0.0500)  time: 1.0074  data: 0.0004  max mem: 78493
Epoch: [195]  [190/312]  eta: 0:02:14  lr: 0.001223  min_lr: 0.001223  loss: 2.1519 (2.0953)  weight_decay: 0.0500 (0.0500)  time: 1.0074  data: 0.0004  max mem: 78493
Epoch: [195]  [200/312]  eta: 0:02:02  lr: 0.001222  min_lr: 0.001222  loss: 2.3130 (2.1117)  weight_decay: 0.0500 (0.0500)  time: 1.0072  data: 0.0005  max mem: 78493
Epoch: [195]  [210/312]  eta: 0:01:51  lr: 0.001221  min_lr: 0.001221  loss: 2.2980 (2.1040)  weight_decay: 0.0500 (0.0500)  time: 1.0071  data: 0.0005  max mem: 78493
Epoch: [195]  [220/312]  eta: 0:01:40  lr: 0.001221  min_lr: 0.001221  loss: 1.9688 (2.1070)  weight_decay: 0.0500 (0.0500)  time: 1.0072  data: 0.0004  max mem: 78493
Epoch: [195]  [230/312]  eta: 0:01:28  lr: 0.001220  min_lr: 0.001220  loss: 2.0651 (2.1034)  weight_decay: 0.0500 (0.0500)  time: 1.0066  data: 0.0004  max mem: 78493
Epoch: [195]  [240/312]  eta: 0:01:17  lr: 0.001219  min_lr: 0.001219  loss: 1.9770 (2.0984)  weight_decay: 0.0500 (0.0500)  time: 1.0070  data: 0.0004  max mem: 78493
Epoch: [195]  [250/312]  eta: 0:01:06  lr: 0.001219  min_lr: 0.001219  loss: 1.9130 (2.0954)  weight_decay: 0.0500 (0.0500)  time: 1.0071  data: 0.0004  max mem: 78493
Epoch: [195]  [260/312]  eta: 0:00:55  lr: 0.001218  min_lr: 0.001218  loss: 2.0724 (2.0940)  weight_decay: 0.0500 (0.0500)  time: 1.0069  data: 0.0012  max mem: 78493
Epoch: [195]  [270/312]  eta: 0:00:45  lr: 0.001217  min_lr: 0.001217  loss: 2.1197 (2.0960)  weight_decay: 0.0500 (0.0500)  time: 1.0073  data: 0.0012  max mem: 78493
Epoch: [195]  [280/312]  eta: 0:00:34  lr: 0.001217  min_lr: 0.001217  loss: 2.1692 (2.1026)  weight_decay: 0.0500 (0.0500)  time: 1.0072  data: 0.0011  max mem: 78493
Epoch: [195]  [290/312]  eta: 0:00:23  lr: 0.001216  min_lr: 0.001216  loss: 2.1672 (2.1020)  weight_decay: 0.0500 (0.0500)  time: 1.0046  data: 0.0009  max mem: 78493
Epoch: [195]  [300/312]  eta: 0:00:12  lr: 0.001215  min_lr: 0.001215  loss: 2.0856 (2.0990)  weight_decay: 0.0500 (0.0500)  time: 1.0019  data: 0.0001  max mem: 78493
Epoch: [195]  [310/312]  eta: 0:00:02  lr: 0.001215  min_lr: 0.001215  loss: 2.2467 (2.0998)  weight_decay: 0.0500 (0.0500)  time: 1.0018  data: 0.0001  max mem: 78493
Epoch: [195]  [311/312]  eta: 0:00:01  lr: 0.001215  min_lr: 0.001215  loss: 2.2608 (2.1005)  weight_decay: 0.0500 (0.0500)  time: 1.0019  data: 0.0001  max mem: 78493
Epoch: [195] Total time: 0:05:33 (1.0691 s / it)
Averaged stats: lr: 0.001215  min_lr: 0.001215  loss: 2.2608 (2.1216)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:18  loss: 0.5816 (0.5816)  acc1: 86.3281 (86.3281)  acc5: 96.4844 (96.4844)  time: 8.6769  data: 8.3947  max mem: 78493
Test:  [8/9]  eta: 0:00:01  loss: 0.9125 (0.8095)  acc1: 78.7760 (79.3120)  acc5: 94.6615 (94.6240)  time: 1.1623  data: 0.9328  max mem: 78493
Test: Total time: 0:00:10 (1.1792 s / it)
* Acc@1 79.226 Acc@5 94.610 loss 0.796
Accuracy of the model on the 50000 test images: 79.2%
Max accuracy: 79.23%
Epoch: [196]  [  0/312]  eta: 1:18:49  lr: 0.001215  min_lr: 0.001215  loss: 1.5976 (1.5976)  weight_decay: 0.0500 (0.0500)  time: 15.1590  data: 12.3847  max mem: 78493
Epoch: [196]  [ 10/312]  eta: 0:13:02  lr: 0.001214  min_lr: 0.001214  loss: 2.1915 (2.0803)  weight_decay: 0.0500 (0.0500)  time: 2.5897  data: 1.3779  max mem: 78493
Epoch: [196]  [ 20/312]  eta: 0:08:57  lr: 0.001213  min_lr: 0.001213  loss: 2.0104 (1.9612)  weight_decay: 0.0500 (0.0500)  time: 1.1748  data: 0.1389  max mem: 78493
Epoch: [196]  [ 30/312]  eta: 0:07:23  lr: 0.001213  min_lr: 0.001213  loss: 2.1112 (2.0537)  weight_decay: 0.0500 (0.0500)  time: 1.0132  data: 0.0005  max mem: 78493
Epoch: [196]  [ 40/312]  eta: 0:06:30  lr: 0.001212  min_lr: 0.001212  loss: 2.1759 (2.0263)  weight_decay: 0.0500 (0.0500)  time: 1.0110  data: 0.0011  max mem: 78493
Epoch: [196]  [ 50/312]  eta: 0:05:54  lr: 0.001211  min_lr: 0.001211  loss: 1.8452 (2.0082)  weight_decay: 0.0500 (0.0500)  time: 1.0114  data: 0.0012  max mem: 78493
Epoch: [196]  [ 60/312]  eta: 0:05:26  lr: 0.001211  min_lr: 0.001211  loss: 2.0220 (2.0198)  weight_decay: 0.0500 (0.0500)  time: 1.0113  data: 0.0005  max mem: 78493
Epoch: [196]  [ 70/312]  eta: 0:05:03  lr: 0.001210  min_lr: 0.001210  loss: 2.1951 (2.0549)  weight_decay: 0.0500 (0.0500)  time: 1.0090  data: 0.0004  max mem: 78493
Epoch: [196]  [ 80/312]  eta: 0:04:44  lr: 0.001209  min_lr: 0.001209  loss: 2.2506 (2.0774)  weight_decay: 0.0500 (0.0500)  time: 1.0064  data: 0.0004  max mem: 78493
Epoch: [196]  [ 90/312]  eta: 0:04:26  lr: 0.001209  min_lr: 0.001209  loss: 2.1928 (2.0847)  weight_decay: 0.0500 (0.0500)  time: 1.0087  data: 0.0004  max mem: 78493
Epoch: [196]  [100/312]  eta: 0:04:10  lr: 0.001208  min_lr: 0.001208  loss: 2.1291 (2.0880)  weight_decay: 0.0500 (0.0500)  time: 1.0095  data: 0.0004  max mem: 78493
Epoch: [196]  [110/312]  eta: 0:03:55  lr: 0.001207  min_lr: 0.001207  loss: 2.1206 (2.0987)  weight_decay: 0.0500 (0.0500)  time: 1.0081  data: 0.0004  max mem: 78493
Epoch: [196]  [120/312]  eta: 0:03:41  lr: 0.001207  min_lr: 0.001207  loss: 2.2530 (2.1068)  weight_decay: 0.0500 (0.0500)  time: 1.0087  data: 0.0005  max mem: 78493
Epoch: [196]  [130/312]  eta: 0:03:27  lr: 0.001206  min_lr: 0.001206  loss: 2.0510 (2.1023)  weight_decay: 0.0500 (0.0500)  time: 1.0082  data: 0.0005  max mem: 78493
Epoch: [196]  [140/312]  eta: 0:03:14  lr: 0.001205  min_lr: 0.001205  loss: 1.9767 (2.0949)  weight_decay: 0.0500 (0.0500)  time: 1.0067  data: 0.0005  max mem: 78493
Epoch: [196]  [150/312]  eta: 0:03:02  lr: 0.001205  min_lr: 0.001205  loss: 2.0814 (2.0976)  weight_decay: 0.0500 (0.0500)  time: 1.0079  data: 0.0004  max mem: 78493
Epoch: [196]  [160/312]  eta: 0:02:49  lr: 0.001204  min_lr: 0.001204  loss: 2.1724 (2.1045)  weight_decay: 0.0500 (0.0500)  time: 1.0088  data: 0.0010  max mem: 78493
Epoch: [196]  [170/312]  eta: 0:02:37  lr: 0.001203  min_lr: 0.001203  loss: 2.1279 (2.0988)  weight_decay: 0.0500 (0.0500)  time: 1.0090  data: 0.0010  max mem: 78493
Epoch: [196]  [180/312]  eta: 0:02:25  lr: 0.001203  min_lr: 0.001203  loss: 2.0380 (2.0957)  weight_decay: 0.0500 (0.0500)  time: 1.0076  data: 0.0004  max mem: 78493
Epoch: [196]  [190/312]  eta: 0:02:14  lr: 0.001202  min_lr: 0.001202  loss: 2.1295 (2.0968)  weight_decay: 0.0500 (0.0500)  time: 1.0070  data: 0.0004  max mem: 78493
Epoch: [196]  [200/312]  eta: 0:02:02  lr: 0.001201  min_lr: 0.001201  loss: 2.1979 (2.0995)  weight_decay: 0.0500 (0.0500)  time: 1.0076  data: 0.0004  max mem: 78493
Epoch: [196]  [210/312]  eta: 0:01:51  lr: 0.001201  min_lr: 0.001201  loss: 2.1723 (2.0958)  weight_decay: 0.0500 (0.0500)  time: 1.0063  data: 0.0004  max mem: 78493
Epoch: [196]  [220/312]  eta: 0:01:40  lr: 0.001200  min_lr: 0.001200  loss: 2.1310 (2.0967)  weight_decay: 0.0500 (0.0500)  time: 1.0051  data: 0.0004  max mem: 78493
Epoch: [196]  [230/312]  eta: 0:01:28  lr: 0.001199  min_lr: 0.001199  loss: 2.2514 (2.1033)  weight_decay: 0.0500 (0.0500)  time: 1.0045  data: 0.0004  max mem: 78493
Epoch: [196]  [240/312]  eta: 0:01:17  lr: 0.001199  min_lr: 0.001199  loss: 2.2216 (2.1020)  weight_decay: 0.0500 (0.0500)  time: 1.0041  data: 0.0005  max mem: 78493
Epoch: [196]  [250/312]  eta: 0:01:06  lr: 0.001198  min_lr: 0.001198  loss: 2.1557 (2.0967)  weight_decay: 0.0500 (0.0500)  time: 1.0042  data: 0.0004  max mem: 78493
Epoch: [196]  [260/312]  eta: 0:00:55  lr: 0.001197  min_lr: 0.001197  loss: 2.0196 (2.0949)  weight_decay: 0.0500 (0.0500)  time: 1.0048  data: 0.0004  max mem: 78493
Epoch: [196]  [270/312]  eta: 0:00:45  lr: 0.001197  min_lr: 0.001197  loss: 2.0196 (2.0908)  weight_decay: 0.0500 (0.0500)  time: 1.0067  data: 0.0004  max mem: 78493
Epoch: [196]  [280/312]  eta: 0:00:34  lr: 0.001196  min_lr: 0.001196  loss: 2.0444 (2.0930)  weight_decay: 0.0500 (0.0500)  time: 1.0070  data: 0.0011  max mem: 78493
Epoch: [196]  [290/312]  eta: 0:00:23  lr: 0.001196  min_lr: 0.001196  loss: 2.1602 (2.0949)  weight_decay: 0.0500 (0.0500)  time: 1.0035  data: 0.0009  max mem: 78493
Epoch: [196]  [300/312]  eta: 0:00:12  lr: 0.001195  min_lr: 0.001195  loss: 2.1386 (2.0943)  weight_decay: 0.0500 (0.0500)  time: 1.0015  data: 0.0001  max mem: 78493
Epoch: [196]  [310/312]  eta: 0:00:02  lr: 0.001194  min_lr: 0.001194  loss: 2.0974 (2.0924)  weight_decay: 0.0500 (0.0500)  time: 1.0015  data: 0.0001  max mem: 78493
Epoch: [196]  [311/312]  eta: 0:00:01  lr: 0.001194  min_lr: 0.001194  loss: 2.0974 (2.0929)  weight_decay: 0.0500 (0.0500)  time: 1.0015  data: 0.0001  max mem: 78493
Epoch: [196] Total time: 0:05:33 (1.0687 s / it)
Averaged stats: lr: 0.001194  min_lr: 0.001194  loss: 2.0974 (2.1018)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:15  loss: 0.5817 (0.5817)  acc1: 85.5469 (85.5469)  acc5: 97.0052 (97.0052)  time: 8.3715  data: 8.0967  max mem: 78493
Test:  [8/9]  eta: 0:00:01  loss: 0.8724 (0.8082)  acc1: 79.1667 (78.4800)  acc5: 94.1406 (94.5600)  time: 1.1285  data: 0.8997  max mem: 78493
Test: Total time: 0:00:10 (1.1685 s / it)
* Acc@1 79.054 Acc@5 94.654 loss 0.793
Accuracy of the model on the 50000 test images: 79.1%
Max accuracy: 79.23%
Epoch: [197]  [  0/312]  eta: 1:21:46  lr: 0.001194  min_lr: 0.001194  loss: 2.0188 (2.0188)  weight_decay: 0.0500 (0.0500)  time: 15.7266  data: 13.5388  max mem: 78493
Epoch: [197]  [ 10/312]  eta: 0:13:23  lr: 0.001193  min_lr: 0.001193  loss: 2.0742 (2.0641)  weight_decay: 0.0500 (0.0500)  time: 2.6591  data: 1.3593  max mem: 78493
Epoch: [197]  [ 20/312]  eta: 0:09:08  lr: 0.001193  min_lr: 0.001193  loss: 2.2286 (2.1099)  weight_decay: 0.0500 (0.0500)  time: 1.1857  data: 0.0709  max mem: 78493
Epoch: [197]  [ 30/312]  eta: 0:07:30  lr: 0.001192  min_lr: 0.001192  loss: 1.9763 (2.0609)  weight_decay: 0.0500 (0.0500)  time: 1.0134  data: 0.0004  max mem: 78493
Epoch: [197]  [ 40/312]  eta: 0:06:35  lr: 0.001191  min_lr: 0.001191  loss: 1.8920 (2.0431)  weight_decay: 0.0500 (0.0500)  time: 1.0077  data: 0.0004  max mem: 78493
Epoch: [197]  [ 50/312]  eta: 0:05:57  lr: 0.001191  min_lr: 0.001191  loss: 2.1748 (2.0539)  weight_decay: 0.0500 (0.0500)  time: 1.0068  data: 0.0004  max mem: 78493
Epoch: [197]  [ 60/312]  eta: 0:05:29  lr: 0.001190  min_lr: 0.001190  loss: 2.1748 (2.0596)  weight_decay: 0.0500 (0.0500)  time: 1.0065  data: 0.0004  max mem: 78493
Epoch: [197]  [ 70/312]  eta: 0:05:06  lr: 0.001189  min_lr: 0.001189  loss: 2.1507 (2.0735)  weight_decay: 0.0500 (0.0500)  time: 1.0084  data: 0.0005  max mem: 78493
Epoch: [197]  [ 80/312]  eta: 0:04:46  lr: 0.001189  min_lr: 0.001189  loss: 2.1309 (2.0895)  weight_decay: 0.0500 (0.0500)  time: 1.0087  data: 0.0004  max mem: 78493
Epoch: [197]  [ 90/312]  eta: 0:04:28  lr: 0.001188  min_lr: 0.001188  loss: 2.0946 (2.0817)  weight_decay: 0.0500 (0.0500)  time: 1.0090  data: 0.0004  max mem: 78493
Epoch: [197]  [100/312]  eta: 0:04:12  lr: 0.001187  min_lr: 0.001187  loss: 2.2174 (2.0824)  weight_decay: 0.0500 (0.0500)  time: 1.0082  data: 0.0004  max mem: 78493
Epoch: [197]  [110/312]  eta: 0:03:56  lr: 0.001187  min_lr: 0.001187  loss: 2.2385 (2.0850)  weight_decay: 0.0500 (0.0500)  time: 1.0078  data: 0.0005  max mem: 78493
Epoch: [197]  [120/312]  eta: 0:03:42  lr: 0.001186  min_lr: 0.001186  loss: 2.1086 (2.0803)  weight_decay: 0.0500 (0.0500)  time: 1.0090  data: 0.0004  max mem: 78493
Epoch: [197]  [130/312]  eta: 0:03:28  lr: 0.001186  min_lr: 0.001186  loss: 2.1101 (2.0809)  weight_decay: 0.0500 (0.0500)  time: 1.0074  data: 0.0004  max mem: 78493
Epoch: [197]  [140/312]  eta: 0:03:15  lr: 0.001185  min_lr: 0.001185  loss: 2.1101 (2.0771)  weight_decay: 0.0500 (0.0500)  time: 1.0074  data: 0.0004  max mem: 78493
Epoch: [197]  [150/312]  eta: 0:03:02  lr: 0.001184  min_lr: 0.001184  loss: 2.0957 (2.0795)  weight_decay: 0.0500 (0.0500)  time: 1.0069  data: 0.0004  max mem: 78493
Epoch: [197]  [160/312]  eta: 0:02:50  lr: 0.001184  min_lr: 0.001184  loss: 2.0833 (2.0823)  weight_decay: 0.0500 (0.0500)  time: 1.0067  data: 0.0004  max mem: 78493
Epoch: [197]  [170/312]  eta: 0:02:38  lr: 0.001183  min_lr: 0.001183  loss: 2.0227 (2.0793)  weight_decay: 0.0500 (0.0500)  time: 1.0072  data: 0.0004  max mem: 78493
Epoch: [197]  [180/312]  eta: 0:02:26  lr: 0.001182  min_lr: 0.001182  loss: 2.1114 (2.0794)  weight_decay: 0.0500 (0.0500)  time: 1.0059  data: 0.0004  max mem: 78493
Epoch: [197]  [190/312]  eta: 0:02:14  lr: 0.001182  min_lr: 0.001182  loss: 2.1718 (2.0841)  weight_decay: 0.0500 (0.0500)  time: 1.0068  data: 0.0004  max mem: 78493
Epoch: [197]  [200/312]  eta: 0:02:03  lr: 0.001181  min_lr: 0.001181  loss: 2.2117 (2.0919)  weight_decay: 0.0500 (0.0500)  time: 1.0086  data: 0.0004  max mem: 78493
Epoch: [197]  [210/312]  eta: 0:01:51  lr: 0.001180  min_lr: 0.001180  loss: 2.2106 (2.0886)  weight_decay: 0.0500 (0.0500)  time: 1.0071  data: 0.0004  max mem: 78493
Epoch: [197]  [220/312]  eta: 0:01:40  lr: 0.001180  min_lr: 0.001180  loss: 2.2835 (2.0964)  weight_decay: 0.0500 (0.0500)  time: 1.0068  data: 0.0004  max mem: 78493
Epoch: [197]  [230/312]  eta: 0:01:29  lr: 0.001179  min_lr: 0.001179  loss: 2.3189 (2.0992)  weight_decay: 0.0500 (0.0500)  time: 1.0082  data: 0.0004  max mem: 78493
Epoch: [197]  [240/312]  eta: 0:01:17  lr: 0.001178  min_lr: 0.001178  loss: 2.2177 (2.1008)  weight_decay: 0.0500 (0.0500)  time: 1.0066  data: 0.0005  max mem: 78493
Epoch: [197]  [250/312]  eta: 0:01:06  lr: 0.001178  min_lr: 0.001178  loss: 2.2006 (2.1030)  weight_decay: 0.0500 (0.0500)  time: 1.0055  data: 0.0004  max mem: 78493
Epoch: [197]  [260/312]  eta: 0:00:56  lr: 0.001177  min_lr: 0.001177  loss: 2.1774 (2.0998)  weight_decay: 0.0500 (0.0500)  time: 1.0051  data: 0.0004  max mem: 78493
Epoch: [197]  [270/312]  eta: 0:00:45  lr: 0.001176  min_lr: 0.001176  loss: 2.1774 (2.1030)  weight_decay: 0.0500 (0.0500)  time: 1.0050  data: 0.0004  max mem: 78493
Epoch: [197]  [280/312]  eta: 0:00:34  lr: 0.001176  min_lr: 0.001176  loss: 2.2230 (2.1055)  weight_decay: 0.0500 (0.0500)  time: 1.0066  data: 0.0010  max mem: 78493
Epoch: [197]  [290/312]  eta: 0:00:23  lr: 0.001175  min_lr: 0.001175  loss: 2.2098 (2.1085)  weight_decay: 0.0500 (0.0500)  time: 1.0047  data: 0.0009  max mem: 78493
Epoch: [197]  [300/312]  eta: 0:00:12  lr: 0.001174  min_lr: 0.001174  loss: 2.1892 (2.1053)  weight_decay: 0.0500 (0.0500)  time: 1.0018  data: 0.0001  max mem: 78493
Epoch: [197]  [310/312]  eta: 0:00:02  lr: 0.001174  min_lr: 0.001174  loss: 1.9317 (2.0962)  weight_decay: 0.0500 (0.0500)  time: 1.0018  data: 0.0001  max mem: 78493
Epoch: [197]  [311/312]  eta: 0:00:01  lr: 0.001174  min_lr: 0.001174  loss: 1.9317 (2.0968)  weight_decay: 0.0500 (0.0500)  time: 1.0019  data: 0.0001  max mem: 78493
Epoch: [197] Total time: 0:05:34 (1.0710 s / it)
Averaged stats: lr: 0.001174  min_lr: 0.001174  loss: 1.9317 (2.1127)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:09  loss: 0.5913 (0.5913)  acc1: 85.2865 (85.2865)  acc5: 96.7448 (96.7448)  time: 7.7650  data: 7.4954  max mem: 78493
Test:  [8/9]  eta: 0:00:01  loss: 0.8936 (0.8045)  acc1: 77.7344 (78.8480)  acc5: 94.4010 (94.7040)  time: 1.0638  data: 0.8352  max mem: 78493
Test: Total time: 0:00:09 (1.0758 s / it)
* Acc@1 79.214 Acc@5 94.566 loss 0.796
Accuracy of the model on the 50000 test images: 79.2%
Max accuracy: 79.23%
Epoch: [198]  [  0/312]  eta: 1:22:42  lr: 0.001174  min_lr: 0.001174  loss: 2.2527 (2.2527)  weight_decay: 0.0500 (0.0500)  time: 15.9051  data: 13.1676  max mem: 78493
Epoch: [198]  [ 10/312]  eta: 0:12:38  lr: 0.001173  min_lr: 0.001173  loss: 2.2527 (2.2924)  weight_decay: 0.0500 (0.0500)  time: 2.5103  data: 1.2180  max mem: 78493
Epoch: [198]  [ 20/312]  eta: 0:08:48  lr: 0.001172  min_lr: 0.001172  loss: 2.2187 (2.1434)  weight_decay: 0.0500 (0.0500)  time: 1.1069  data: 0.0183  max mem: 78493
Epoch: [198]  [ 30/312]  eta: 0:07:17  lr: 0.001172  min_lr: 0.001172  loss: 2.2260 (2.1678)  weight_decay: 0.0500 (0.0500)  time: 1.0258  data: 0.0070  max mem: 78493
Epoch: [198]  [ 40/312]  eta: 0:06:25  lr: 0.001171  min_lr: 0.001171  loss: 2.2149 (2.1413)  weight_decay: 0.0500 (0.0500)  time: 1.0068  data: 0.0004  max mem: 78493
Epoch: [198]  [ 50/312]  eta: 0:05:50  lr: 0.001170  min_lr: 0.001170  loss: 2.1082 (2.1440)  weight_decay: 0.0500 (0.0500)  time: 1.0057  data: 0.0013  max mem: 78493
Epoch: [198]  [ 60/312]  eta: 0:05:23  lr: 0.001170  min_lr: 0.001170  loss: 2.2218 (2.1212)  weight_decay: 0.0500 (0.0500)  time: 1.0071  data: 0.0013  max mem: 78493
Epoch: [198]  [ 70/312]  eta: 0:05:01  lr: 0.001169  min_lr: 0.001169  loss: 2.1256 (2.1078)  weight_decay: 0.0500 (0.0500)  time: 1.0076  data: 0.0005  max mem: 78493
Epoch: [198]  [ 80/312]  eta: 0:04:42  lr: 0.001168  min_lr: 0.001168  loss: 2.0555 (2.0923)  weight_decay: 0.0500 (0.0500)  time: 1.0069  data: 0.0005  max mem: 78493
Epoch: [198]  [ 90/312]  eta: 0:04:24  lr: 0.001168  min_lr: 0.001168  loss: 2.1129 (2.1070)  weight_decay: 0.0500 (0.0500)  time: 1.0070  data: 0.0004  max mem: 78493
Epoch: [198]  [100/312]  eta: 0:04:09  lr: 0.001167  min_lr: 0.001167  loss: 2.2094 (2.1073)  weight_decay: 0.0500 (0.0500)  time: 1.0091  data: 0.0012  max mem: 78493
Epoch: [198]  [110/312]  eta: 0:03:54  lr: 0.001166  min_lr: 0.001166  loss: 2.2874 (2.1169)  weight_decay: 0.0500 (0.0500)  time: 1.0096  data: 0.0012  max mem: 78493
Epoch: [198]  [120/312]  eta: 0:03:40  lr: 0.001166  min_lr: 0.001166  loss: 2.2416 (2.1217)  weight_decay: 0.0500 (0.0500)  time: 1.0102  data: 0.0004  max mem: 78493
Epoch: [198]  [130/312]  eta: 0:03:26  lr: 0.001165  min_lr: 0.001165  loss: 2.1279 (2.1138)  weight_decay: 0.0500 (0.0500)  time: 1.0096  data: 0.0004  max mem: 78493
Epoch: [198]  [140/312]  eta: 0:03:13  lr: 0.001164  min_lr: 0.001164  loss: 2.1891 (2.1272)  weight_decay: 0.0500 (0.0500)  time: 1.0068  data: 0.0004  max mem: 78493
Epoch: [198]  [150/312]  eta: 0:03:01  lr: 0.001164  min_lr: 0.001164  loss: 2.3289 (2.1361)  weight_decay: 0.0500 (0.0500)  time: 1.0056  data: 0.0004  max mem: 78493
Epoch: [198]  [160/312]  eta: 0:02:49  lr: 0.001163  min_lr: 0.001163  loss: 2.2870 (2.1412)  weight_decay: 0.0500 (0.0500)  time: 1.0054  data: 0.0004  max mem: 78493
Epoch: [198]  [170/312]  eta: 0:02:37  lr: 0.001162  min_lr: 0.001162  loss: 2.2664 (2.1408)  weight_decay: 0.0500 (0.0500)  time: 1.0044  data: 0.0004  max mem: 78493
Epoch: [198]  [180/312]  eta: 0:02:25  lr: 0.001162  min_lr: 0.001162  loss: 2.2778 (2.1437)  weight_decay: 0.0500 (0.0500)  time: 1.0058  data: 0.0004  max mem: 78493
Epoch: [198]  [190/312]  eta: 0:02:13  lr: 0.001161  min_lr: 0.001161  loss: 2.1446 (2.1407)  weight_decay: 0.0500 (0.0500)  time: 1.0060  data: 0.0005  max mem: 78493
Epoch: [198]  [200/312]  eta: 0:02:02  lr: 0.001161  min_lr: 0.001161  loss: 2.1557 (2.1365)  weight_decay: 0.0500 (0.0500)  time: 1.0045  data: 0.0004  max mem: 78493
Epoch: [198]  [210/312]  eta: 0:01:50  lr: 0.001160  min_lr: 0.001160  loss: 2.1557 (2.1283)  weight_decay: 0.0500 (0.0500)  time: 1.0058  data: 0.0004  max mem: 78493
Epoch: [198]  [220/312]  eta: 0:01:39  lr: 0.001159  min_lr: 0.001159  loss: 2.1388 (2.1282)  weight_decay: 0.0500 (0.0500)  time: 1.0054  data: 0.0004  max mem: 78493
Epoch: [198]  [230/312]  eta: 0:01:28  lr: 0.001159  min_lr: 0.001159  loss: 2.2140 (2.1313)  weight_decay: 0.0500 (0.0500)  time: 1.0047  data: 0.0005  max mem: 78493
Epoch: [198]  [240/312]  eta: 0:01:17  lr: 0.001158  min_lr: 0.001158  loss: 2.1998 (2.1328)  weight_decay: 0.0500 (0.0500)  time: 1.0052  data: 0.0005  max mem: 78493
Epoch: [198]  [250/312]  eta: 0:01:06  lr: 0.001157  min_lr: 0.001157  loss: 2.1877 (2.1307)  weight_decay: 0.0500 (0.0500)  time: 1.0054  data: 0.0004  max mem: 78493
Epoch: [198]  [260/312]  eta: 0:00:55  lr: 0.001157  min_lr: 0.001157  loss: 2.1340 (2.1310)  weight_decay: 0.0500 (0.0500)  time: 1.0054  data: 0.0004  max mem: 78493
Epoch: [198]  [270/312]  eta: 0:00:44  lr: 0.001156  min_lr: 0.001156  loss: 2.1753 (2.1277)  weight_decay: 0.0500 (0.0500)  time: 1.0053  data: 0.0004  max mem: 78493
Epoch: [198]  [280/312]  eta: 0:00:34  lr: 0.001155  min_lr: 0.001155  loss: 2.2306 (2.1298)  weight_decay: 0.0500 (0.0500)  time: 1.0055  data: 0.0011  max mem: 78493
Epoch: [198]  [290/312]  eta: 0:00:23  lr: 0.001155  min_lr: 0.001155  loss: 2.1337 (2.1255)  weight_decay: 0.0500 (0.0500)  time: 1.0040  data: 0.0009  max mem: 78493
Epoch: [198]  [300/312]  eta: 0:00:12  lr: 0.001154  min_lr: 0.001154  loss: 2.0951 (2.1244)  weight_decay: 0.0500 (0.0500)  time: 1.0018  data: 0.0001  max mem: 78493
Epoch: [198]  [310/312]  eta: 0:00:02  lr: 0.001153  min_lr: 0.001153  loss: 2.1185 (2.1223)  weight_decay: 0.0500 (0.0500)  time: 1.0017  data: 0.0001  max mem: 78493
Epoch: [198]  [311/312]  eta: 0:00:01  lr: 0.001153  min_lr: 0.001153  loss: 2.0232 (2.1207)  weight_decay: 0.0500 (0.0500)  time: 1.0017  data: 0.0001  max mem: 78493
Epoch: [198] Total time: 0:05:32 (1.0658 s / it)
Averaged stats: lr: 0.001153  min_lr: 0.001153  loss: 2.0232 (2.1089)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:13  loss: 0.5545 (0.5545)  acc1: 85.1562 (85.1562)  acc5: 97.0052 (97.0052)  time: 8.2170  data: 7.9310  max mem: 78493
Test:  [8/9]  eta: 0:00:01  loss: 0.8644 (0.7951)  acc1: 79.0365 (78.7200)  acc5: 95.0521 (94.5440)  time: 1.1113  data: 0.8813  max mem: 78493
Test: Total time: 0:00:10 (1.1486 s / it)
* Acc@1 79.214 Acc@5 94.726 loss 0.788
Accuracy of the model on the 50000 test images: 79.2%
Max accuracy: 79.23%
Epoch: [199]  [  0/312]  eta: 1:25:15  lr: 0.001153  min_lr: 0.001153  loss: 2.2710 (2.2710)  weight_decay: 0.0500 (0.0500)  time: 16.3973  data: 12.9131  max mem: 78493
Epoch: [199]  [ 10/312]  eta: 0:13:41  lr: 0.001153  min_lr: 0.001153  loss: 2.1066 (1.9618)  weight_decay: 0.0500 (0.0500)  time: 2.7210  data: 1.1746  max mem: 78493
Epoch: [199]  [ 20/312]  eta: 0:09:16  lr: 0.001152  min_lr: 0.001152  loss: 1.8975 (1.9384)  weight_decay: 0.0500 (0.0500)  time: 1.1811  data: 0.0006  max mem: 78493
Epoch: [199]  [ 30/312]  eta: 0:07:35  lr: 0.001151  min_lr: 0.001151  loss: 1.8975 (1.9789)  weight_decay: 0.0500 (0.0500)  time: 1.0068  data: 0.0005  max mem: 78493
Epoch: [199]  [ 40/312]  eta: 0:06:39  lr: 0.001151  min_lr: 0.001151  loss: 2.0597 (1.9924)  weight_decay: 0.0500 (0.0500)  time: 1.0064  data: 0.0004  max mem: 78493
Epoch: [199]  [ 50/312]  eta: 0:06:00  lr: 0.001150  min_lr: 0.001150  loss: 2.0606 (1.9983)  weight_decay: 0.0500 (0.0500)  time: 1.0086  data: 0.0004  max mem: 78493
Epoch: [199]  [ 60/312]  eta: 0:05:31  lr: 0.001149  min_lr: 0.001149  loss: 2.1127 (2.0190)  weight_decay: 0.0500 (0.0500)  time: 1.0093  data: 0.0004  max mem: 78493
Epoch: [199]  [ 70/312]  eta: 0:05:08  lr: 0.001149  min_lr: 0.001149  loss: 2.1203 (2.0271)  weight_decay: 0.0500 (0.0500)  time: 1.0106  data: 0.0005  max mem: 78493
Epoch: [199]  [ 80/312]  eta: 0:04:47  lr: 0.001148  min_lr: 0.001148  loss: 2.1277 (2.0435)  weight_decay: 0.0500 (0.0500)  time: 1.0096  data: 0.0005  max mem: 78493
Epoch: [199]  [ 90/312]  eta: 0:04:29  lr: 0.001147  min_lr: 0.001147  loss: 2.2103 (2.0703)  weight_decay: 0.0500 (0.0500)  time: 1.0064  data: 0.0005  max mem: 78493
Epoch: [199]  [100/312]  eta: 0:04:13  lr: 0.001147  min_lr: 0.001147  loss: 2.2155 (2.0840)  weight_decay: 0.0500 (0.0500)  time: 1.0068  data: 0.0005  max mem: 78493
Epoch: [199]  [110/312]  eta: 0:03:57  lr: 0.001146  min_lr: 0.001146  loss: 2.1732 (2.0872)  weight_decay: 0.0500 (0.0500)  time: 1.0079  data: 0.0004  max mem: 78493
Epoch: [199]  [120/312]  eta: 0:03:43  lr: 0.001145  min_lr: 0.001145  loss: 2.1732 (2.0788)  weight_decay: 0.0500 (0.0500)  time: 1.0065  data: 0.0004  max mem: 78493
Epoch: [199]  [130/312]  eta: 0:03:29  lr: 0.001145  min_lr: 0.001145  loss: 2.1349 (2.0708)  weight_decay: 0.0500 (0.0500)  time: 1.0060  data: 0.0004  max mem: 78493
Epoch: [199]  [140/312]  eta: 0:03:16  lr: 0.001144  min_lr: 0.001144  loss: 2.1349 (2.0727)  weight_decay: 0.0500 (0.0500)  time: 1.0080  data: 0.0004  max mem: 78493
Epoch: [199]  [150/312]  eta: 0:03:03  lr: 0.001143  min_lr: 0.001143  loss: 2.2093 (2.0719)  weight_decay: 0.0500 (0.0500)  time: 1.0075  data: 0.0004  max mem: 78493
Epoch: [199]  [160/312]  eta: 0:02:50  lr: 0.001143  min_lr: 0.001143  loss: 2.0034 (2.0766)  weight_decay: 0.0500 (0.0500)  time: 1.0062  data: 0.0004  max mem: 78493
Epoch: [199]  [170/312]  eta: 0:02:38  lr: 0.001142  min_lr: 0.001142  loss: 1.9796 (2.0662)  weight_decay: 0.0500 (0.0500)  time: 1.0075  data: 0.0004  max mem: 78493
Epoch: [199]  [180/312]  eta: 0:02:26  lr: 0.001142  min_lr: 0.001142  loss: 1.9796 (2.0682)  weight_decay: 0.0500 (0.0500)  time: 1.0082  data: 0.0004  max mem: 78493
Epoch: [199]  [190/312]  eta: 0:02:14  lr: 0.001141  min_lr: 0.001141  loss: 2.0125 (2.0597)  weight_decay: 0.0500 (0.0500)  time: 1.0057  data: 0.0004  max mem: 78493
Epoch: [199]  [200/312]  eta: 0:02:03  lr: 0.001140  min_lr: 0.001140  loss: 2.0408 (2.0626)  weight_decay: 0.0500 (0.0500)  time: 1.0048  data: 0.0005  max mem: 78493
Epoch: [199]  [210/312]  eta: 0:01:51  lr: 0.001140  min_lr: 0.001140  loss: 2.2043 (2.0677)  weight_decay: 0.0500 (0.0500)  time: 1.0058  data: 0.0005  max mem: 78493
Epoch: [199]  [220/312]  eta: 0:01:40  lr: 0.001139  min_lr: 0.001139  loss: 2.1161 (2.0711)  weight_decay: 0.0500 (0.0500)  time: 1.0058  data: 0.0005  max mem: 78493
Epoch: [199]  [230/312]  eta: 0:01:29  lr: 0.001138  min_lr: 0.001138  loss: 2.1350 (2.0723)  weight_decay: 0.0500 (0.0500)  time: 1.0065  data: 0.0005  max mem: 78493
Epoch: [199]  [240/312]  eta: 0:01:18  lr: 0.001138  min_lr: 0.001138  loss: 2.1522 (2.0715)  weight_decay: 0.0500 (0.0500)  time: 1.0058  data: 0.0004  max mem: 78493
Epoch: [199]  [250/312]  eta: 0:01:07  lr: 0.001137  min_lr: 0.001137  loss: 2.1719 (2.0741)  weight_decay: 0.0500 (0.0500)  time: 1.0057  data: 0.0005  max mem: 78493
Epoch: [199]  [260/312]  eta: 0:00:56  lr: 0.001136  min_lr: 0.001136  loss: 2.2245 (2.0740)  weight_decay: 0.0500 (0.0500)  time: 1.0066  data: 0.0005  max mem: 78493
Epoch: [199]  [270/312]  eta: 0:00:45  lr: 0.001136  min_lr: 0.001136  loss: 2.1667 (2.0753)  weight_decay: 0.0500 (0.0500)  time: 1.0051  data: 0.0004  max mem: 78493
Epoch: [199]  [280/312]  eta: 0:00:34  lr: 0.001135  min_lr: 0.001135  loss: 2.2028 (2.0819)  weight_decay: 0.0500 (0.0500)  time: 1.0057  data: 0.0010  max mem: 78493
Epoch: [199]  [290/312]  eta: 0:00:23  lr: 0.001134  min_lr: 0.001134  loss: 2.0938 (2.0737)  weight_decay: 0.0500 (0.0500)  time: 1.0047  data: 0.0009  max mem: 78493
Epoch: [199]  [300/312]  eta: 0:00:12  lr: 0.001134  min_lr: 0.001134  loss: 2.0621 (2.0758)  weight_decay: 0.0500 (0.0500)  time: 1.0021  data: 0.0001  max mem: 78493
Epoch: [199]  [310/312]  eta: 0:00:02  lr: 0.001133  min_lr: 0.001133  loss: 2.1207 (2.0779)  weight_decay: 0.0500 (0.0500)  time: 1.0018  data: 0.0001  max mem: 78493
Epoch: [199]  [311/312]  eta: 0:00:01  lr: 0.001133  min_lr: 0.001133  loss: 2.1301 (2.0781)  weight_decay: 0.0500 (0.0500)  time: 1.0017  data: 0.0001  max mem: 78493
Epoch: [199] Total time: 0:05:34 (1.0726 s / it)
Averaged stats: lr: 0.001133  min_lr: 0.001133  loss: 2.1301 (2.1118)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:15  loss: 0.5894 (0.5894)  acc1: 85.6771 (85.6771)  acc5: 96.7448 (96.7448)  time: 8.4444  data: 8.1636  max mem: 78493
Test:  [8/9]  eta: 0:00:01  loss: 0.8984 (0.8192)  acc1: 78.1250 (78.8480)  acc5: 94.1406 (94.2240)  time: 1.1365  data: 0.9072  max mem: 78493
Test: Total time: 0:00:10 (1.1569 s / it)
* Acc@1 79.122 Acc@5 94.536 loss 0.802
Accuracy of the model on the 50000 test images: 79.1%
Max accuracy: 79.23%
Epoch: [200]  [  0/312]  eta: 1:26:04  lr: 0.001133  min_lr: 0.001133  loss: 2.5663 (2.5663)  weight_decay: 0.0500 (0.0500)  time: 16.5537  data: 12.9029  max mem: 78493
Epoch: [200]  [ 10/312]  eta: 0:13:51  lr: 0.001132  min_lr: 0.001132  loss: 2.0240 (2.0417)  weight_decay: 0.0500 (0.0500)  time: 2.7518  data: 1.2039  max mem: 78493
Epoch: [200]  [ 20/312]  eta: 0:09:21  lr: 0.001132  min_lr: 0.001132  loss: 2.0240 (2.0278)  weight_decay: 0.0500 (0.0500)  time: 1.1917  data: 0.0173  max mem: 78493
Epoch: [200]  [ 30/312]  eta: 0:07:39  lr: 0.001131  min_lr: 0.001131  loss: 2.1127 (2.0368)  weight_decay: 0.0500 (0.0500)  time: 1.0099  data: 0.0005  max mem: 78493
Epoch: [200]  [ 40/312]  eta: 0:06:41  lr: 0.001130  min_lr: 0.001130  loss: 2.1261 (2.0604)  weight_decay: 0.0500 (0.0500)  time: 1.0071  data: 0.0005  max mem: 78493
Epoch: [200]  [ 50/312]  eta: 0:06:02  lr: 0.001130  min_lr: 0.001130  loss: 2.2885 (2.1031)  weight_decay: 0.0500 (0.0500)  time: 1.0069  data: 0.0005  max mem: 78493
Epoch: [200]  [ 60/312]  eta: 0:05:33  lr: 0.001129  min_lr: 0.001129  loss: 2.3000 (2.1048)  weight_decay: 0.0500 (0.0500)  time: 1.0054  data: 0.0004  max mem: 78493
Epoch: [200]  [ 70/312]  eta: 0:05:09  lr: 0.001128  min_lr: 0.001128  loss: 2.1398 (2.1058)  weight_decay: 0.0500 (0.0500)  time: 1.0065  data: 0.0004  max mem: 78493
Epoch: [200]  [ 80/312]  eta: 0:04:48  lr: 0.001128  min_lr: 0.001128  loss: 2.1335 (2.0982)  weight_decay: 0.0500 (0.0500)  time: 1.0096  data: 0.0004  max mem: 78493
Epoch: [200]  [ 90/312]  eta: 0:04:30  lr: 0.001127  min_lr: 0.001127  loss: 2.0707 (2.0838)  weight_decay: 0.0500 (0.0500)  time: 1.0086  data: 0.0004  max mem: 78493
Epoch: [200]  [100/312]  eta: 0:04:13  lr: 0.001126  min_lr: 0.001126  loss: 2.0880 (2.0850)  weight_decay: 0.0500 (0.0500)  time: 1.0086  data: 0.0004  max mem: 78493
Epoch: [200]  [110/312]  eta: 0:03:58  lr: 0.001126  min_lr: 0.001126  loss: 2.1516 (2.0912)  weight_decay: 0.0500 (0.0500)  time: 1.0087  data: 0.0004  max mem: 78493
Epoch: [200]  [120/312]  eta: 0:03:43  lr: 0.001125  min_lr: 0.001125  loss: 1.9875 (2.0631)  weight_decay: 0.0500 (0.0500)  time: 1.0079  data: 0.0004  max mem: 78493
Epoch: [200]  [130/312]  eta: 0:03:30  lr: 0.001125  min_lr: 0.001125  loss: 1.9641 (2.0680)  weight_decay: 0.0500 (0.0500)  time: 1.0056  data: 0.0005  max mem: 78493
Epoch: [200]  [140/312]  eta: 0:03:16  lr: 0.001124  min_lr: 0.001124  loss: 2.2687 (2.0841)  weight_decay: 0.0500 (0.0500)  time: 1.0042  data: 0.0005  max mem: 78493
Epoch: [200]  [150/312]  eta: 0:03:03  lr: 0.001123  min_lr: 0.001123  loss: 2.2715 (2.0875)  weight_decay: 0.0500 (0.0500)  time: 1.0044  data: 0.0005  max mem: 78493
Epoch: [200]  [160/312]  eta: 0:02:51  lr: 0.001123  min_lr: 0.001123  loss: 2.0103 (2.0804)  weight_decay: 0.0500 (0.0500)  time: 1.0050  data: 0.0005  max mem: 78493
Epoch: [200]  [170/312]  eta: 0:02:38  lr: 0.001122  min_lr: 0.001122  loss: 1.9914 (2.0801)  weight_decay: 0.0500 (0.0500)  time: 1.0056  data: 0.0005  max mem: 78493
Epoch: [200]  [180/312]  eta: 0:02:26  lr: 0.001121  min_lr: 0.001121  loss: 2.1013 (2.0862)  weight_decay: 0.0500 (0.0500)  time: 1.0061  data: 0.0005  max mem: 78493
Epoch: [200]  [190/312]  eta: 0:02:15  lr: 0.001121  min_lr: 0.001121  loss: 1.8917 (2.0811)  weight_decay: 0.0500 (0.0500)  time: 1.0071  data: 0.0004  max mem: 78493
Epoch: [200]  [200/312]  eta: 0:02:03  lr: 0.001120  min_lr: 0.001120  loss: 1.8917 (2.0779)  weight_decay: 0.0500 (0.0500)  time: 1.0063  data: 0.0005  max mem: 78493
Epoch: [200]  [210/312]  eta: 0:01:51  lr: 0.001119  min_lr: 0.001119  loss: 2.1752 (2.0880)  weight_decay: 0.0500 (0.0500)  time: 1.0068  data: 0.0005  max mem: 78493
Epoch: [200]  [220/312]  eta: 0:01:40  lr: 0.001119  min_lr: 0.001119  loss: 2.1752 (2.0851)  weight_decay: 0.0500 (0.0500)  time: 1.0073  data: 0.0004  max mem: 78493
Epoch: [200]  [230/312]  eta: 0:01:29  lr: 0.001118  min_lr: 0.001118  loss: 2.0750 (2.0814)  weight_decay: 0.0500 (0.0500)  time: 1.0050  data: 0.0004  max mem: 78493
Epoch: [200]  [240/312]  eta: 0:01:18  lr: 0.001117  min_lr: 0.001117  loss: 2.1461 (2.0875)  weight_decay: 0.0500 (0.0500)  time: 1.0060  data: 0.0004  max mem: 78493
Epoch: [200]  [250/312]  eta: 0:01:07  lr: 0.001117  min_lr: 0.001117  loss: 2.2383 (2.0826)  weight_decay: 0.0500 (0.0500)  time: 1.0067  data: 0.0004  max mem: 78493
Epoch: [200]  [260/312]  eta: 0:00:56  lr: 0.001116  min_lr: 0.001116  loss: 2.2227 (2.0878)  weight_decay: 0.0500 (0.0500)  time: 1.0057  data: 0.0004  max mem: 78493
Epoch: [200]  [270/312]  eta: 0:00:45  lr: 0.001115  min_lr: 0.001115  loss: 2.2606 (2.0950)  weight_decay: 0.0500 (0.0500)  time: 1.0060  data: 0.0004  max mem: 78493
Epoch: [200]  [280/312]  eta: 0:00:34  lr: 0.001115  min_lr: 0.001115  loss: 2.2430 (2.0900)  weight_decay: 0.0500 (0.0500)  time: 1.0062  data: 0.0011  max mem: 78493
Epoch: [200]  [290/312]  eta: 0:00:23  lr: 0.001114  min_lr: 0.001114  loss: 2.2028 (2.0966)  weight_decay: 0.0500 (0.0500)  time: 1.0042  data: 0.0009  max mem: 78493
Epoch: [200]  [300/312]  eta: 0:00:12  lr: 0.001114  min_lr: 0.001114  loss: 2.2028 (2.0981)  weight_decay: 0.0500 (0.0500)  time: 1.0020  data: 0.0001  max mem: 78493
Epoch: [200]  [310/312]  eta: 0:00:02  lr: 0.001113  min_lr: 0.001113  loss: 2.0869 (2.0974)  weight_decay: 0.0500 (0.0500)  time: 1.0021  data: 0.0001  max mem: 78493
Epoch: [200]  [311/312]  eta: 0:00:01  lr: 0.001113  min_lr: 0.001113  loss: 2.0869 (2.0993)  weight_decay: 0.0500 (0.0500)  time: 1.0020  data: 0.0001  max mem: 78493
Epoch: [200] Total time: 0:05:34 (1.0737 s / it)
Averaged stats: lr: 0.001113  min_lr: 0.001113  loss: 2.0869 (2.1048)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:16  loss: 0.5798 (0.5798)  acc1: 85.2865 (85.2865)  acc5: 96.8750 (96.8750)  time: 8.5309  data: 8.2665  max mem: 78493
Test:  [8/9]  eta: 0:00:01  loss: 0.8847 (0.8014)  acc1: 78.1250 (79.0400)  acc5: 93.8802 (94.2400)  time: 1.1499  data: 0.9186  max mem: 78493
Test: Total time: 0:00:10 (1.1844 s / it)
* Acc@1 79.312 Acc@5 94.544 loss 0.793
Accuracy of the model on the 50000 test images: 79.3%
Max accuracy: 79.31%
Epoch: [201]  [  0/312]  eta: 1:27:58  lr: 0.001113  min_lr: 0.001113  loss: 2.1075 (2.1075)  weight_decay: 0.0500 (0.0500)  time: 16.9196  data: 15.9195  max mem: 78493
Epoch: [201]  [ 10/312]  eta: 0:13:34  lr: 0.001112  min_lr: 0.001112  loss: 2.1075 (2.0827)  weight_decay: 0.0500 (0.0500)  time: 2.6966  data: 1.4515  max mem: 78493
Epoch: [201]  [ 20/312]  eta: 0:09:12  lr: 0.001112  min_lr: 0.001112  loss: 2.0488 (2.1038)  weight_decay: 0.0500 (0.0500)  time: 1.1412  data: 0.0026  max mem: 78493
Epoch: [201]  [ 30/312]  eta: 0:07:33  lr: 0.001111  min_lr: 0.001111  loss: 2.0856 (2.0980)  weight_decay: 0.0500 (0.0500)  time: 1.0105  data: 0.0005  max mem: 78493
Epoch: [201]  [ 40/312]  eta: 0:06:37  lr: 0.001110  min_lr: 0.001110  loss: 2.0747 (2.0725)  weight_decay: 0.0500 (0.0500)  time: 1.0096  data: 0.0004  max mem: 78493
Epoch: [201]  [ 50/312]  eta: 0:05:59  lr: 0.001110  min_lr: 0.001110  loss: 2.0481 (2.0527)  weight_decay: 0.0500 (0.0500)  time: 1.0084  data: 0.0005  max mem: 78493
Epoch: [201]  [ 60/312]  eta: 0:05:30  lr: 0.001109  min_lr: 0.001109  loss: 2.0638 (2.0535)  weight_decay: 0.0500 (0.0500)  time: 1.0085  data: 0.0005  max mem: 78493
Epoch: [201]  [ 70/312]  eta: 0:05:07  lr: 0.001108  min_lr: 0.001108  loss: 2.1804 (2.0771)  weight_decay: 0.0500 (0.0500)  time: 1.0080  data: 0.0005  max mem: 78493
Epoch: [201]  [ 80/312]  eta: 0:04:47  lr: 0.001108  min_lr: 0.001108  loss: 2.2542 (2.0877)  weight_decay: 0.0500 (0.0500)  time: 1.0103  data: 0.0005  max mem: 78493
Epoch: [201]  [ 90/312]  eta: 0:04:29  lr: 0.001107  min_lr: 0.001107  loss: 2.0161 (2.0797)  weight_decay: 0.0500 (0.0500)  time: 1.0094  data: 0.0004  max mem: 78493
Epoch: [201]  [100/312]  eta: 0:04:12  lr: 0.001106  min_lr: 0.001106  loss: 2.1770 (2.0914)  weight_decay: 0.0500 (0.0500)  time: 1.0080  data: 0.0005  max mem: 78493
Epoch: [201]  [110/312]  eta: 0:03:57  lr: 0.001106  min_lr: 0.001106  loss: 2.3141 (2.1001)  weight_decay: 0.0500 (0.0500)  time: 1.0094  data: 0.0005  max mem: 78493
Epoch: [201]  [120/312]  eta: 0:03:43  lr: 0.001105  min_lr: 0.001105  loss: 2.1548 (2.0924)  weight_decay: 0.0500 (0.0500)  time: 1.0096  data: 0.0004  max mem: 78493
Epoch: [201]  [130/312]  eta: 0:03:29  lr: 0.001104  min_lr: 0.001104  loss: 2.0210 (2.0835)  weight_decay: 0.0500 (0.0500)  time: 1.0079  data: 0.0004  max mem: 78493
Epoch: [201]  [140/312]  eta: 0:03:16  lr: 0.001104  min_lr: 0.001104  loss: 2.0051 (2.0757)  weight_decay: 0.0500 (0.0500)  time: 1.0073  data: 0.0004  max mem: 78493
Epoch: [201]  [150/312]  eta: 0:03:03  lr: 0.001103  min_lr: 0.001103  loss: 2.2917 (2.0940)  weight_decay: 0.0500 (0.0500)  time: 1.0120  data: 0.0011  max mem: 78493
Epoch: [201]  [160/312]  eta: 0:02:51  lr: 0.001102  min_lr: 0.001102  loss: 2.3158 (2.0997)  weight_decay: 0.0500 (0.0500)  time: 1.0157  data: 0.0011  max mem: 78493
Epoch: [201]  [170/312]  eta: 0:02:38  lr: 0.001102  min_lr: 0.001102  loss: 2.2638 (2.1046)  weight_decay: 0.0500 (0.0500)  time: 1.0109  data: 0.0005  max mem: 78493
Epoch: [201]  [180/312]  eta: 0:02:26  lr: 0.001101  min_lr: 0.001101  loss: 2.2147 (2.1057)  weight_decay: 0.0500 (0.0500)  time: 1.0066  data: 0.0004  max mem: 78493
Epoch: [201]  [190/312]  eta: 0:02:14  lr: 0.001101  min_lr: 0.001101  loss: 2.2438 (2.1165)  weight_decay: 0.0500 (0.0500)  time: 1.0052  data: 0.0004  max mem: 78493
Epoch: [201]  [200/312]  eta: 0:02:03  lr: 0.001100  min_lr: 0.001100  loss: 2.2582 (2.1179)  weight_decay: 0.0500 (0.0500)  time: 1.0061  data: 0.0005  max mem: 78493
Epoch: [201]  [210/312]  eta: 0:01:51  lr: 0.001099  min_lr: 0.001099  loss: 2.1215 (2.1118)  weight_decay: 0.0500 (0.0500)  time: 1.0067  data: 0.0005  max mem: 78493
Epoch: [201]  [220/312]  eta: 0:01:40  lr: 0.001099  min_lr: 0.001099  loss: 2.0773 (2.1113)  weight_decay: 0.0500 (0.0500)  time: 1.0046  data: 0.0004  max mem: 78493
Epoch: [201]  [230/312]  eta: 0:01:29  lr: 0.001098  min_lr: 0.001098  loss: 2.1351 (2.1126)  weight_decay: 0.0500 (0.0500)  time: 1.0045  data: 0.0004  max mem: 78493
Epoch: [201]  [240/312]  eta: 0:01:18  lr: 0.001097  min_lr: 0.001097  loss: 2.1351 (2.1134)  weight_decay: 0.0500 (0.0500)  time: 1.0047  data: 0.0005  max mem: 78493
Epoch: [201]  [250/312]  eta: 0:01:07  lr: 0.001097  min_lr: 0.001097  loss: 2.0665 (2.1099)  weight_decay: 0.0500 (0.0500)  time: 1.0046  data: 0.0004  max mem: 78493
Epoch: [201]  [260/312]  eta: 0:00:56  lr: 0.001096  min_lr: 0.001096  loss: 2.0665 (2.1101)  weight_decay: 0.0500 (0.0500)  time: 1.0062  data: 0.0005  max mem: 78493
Epoch: [201]  [270/312]  eta: 0:00:45  lr: 0.001095  min_lr: 0.001095  loss: 2.2820 (2.1160)  weight_decay: 0.0500 (0.0500)  time: 1.0077  data: 0.0005  max mem: 78493
Epoch: [201]  [280/312]  eta: 0:00:34  lr: 0.001095  min_lr: 0.001095  loss: 2.2401 (2.1150)  weight_decay: 0.0500 (0.0500)  time: 1.0076  data: 0.0011  max mem: 78493
Epoch: [201]  [290/312]  eta: 0:00:23  lr: 0.001094  min_lr: 0.001094  loss: 2.1648 (2.1129)  weight_decay: 0.0500 (0.0500)  time: 1.0045  data: 0.0009  max mem: 78493
Epoch: [201]  [300/312]  eta: 0:00:12  lr: 0.001094  min_lr: 0.001094  loss: 2.2348 (2.1154)  weight_decay: 0.0500 (0.0500)  time: 1.0015  data: 0.0001  max mem: 78493
Epoch: [201]  [310/312]  eta: 0:00:02  lr: 0.001093  min_lr: 0.001093  loss: 2.2533 (2.1129)  weight_decay: 0.0500 (0.0500)  time: 1.0013  data: 0.0001  max mem: 78493
Epoch: [201]  [311/312]  eta: 0:00:01  lr: 0.001093  min_lr: 0.001093  loss: 2.2533 (2.1105)  weight_decay: 0.0500 (0.0500)  time: 1.0013  data: 0.0001  max mem: 78493
Epoch: [201] Total time: 0:05:34 (1.0728 s / it)
Averaged stats: lr: 0.001093  min_lr: 0.001093  loss: 2.2533 (2.0875)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:15  loss: 0.5785 (0.5785)  acc1: 85.4167 (85.4167)  acc5: 97.2656 (97.2656)  time: 8.3877  data: 8.1239  max mem: 78493
Test:  [8/9]  eta: 0:00:01  loss: 0.9054 (0.8063)  acc1: 77.2135 (78.5760)  acc5: 95.1823 (94.5600)  time: 1.1340  data: 0.9027  max mem: 78493
Test: Total time: 0:00:10 (1.1807 s / it)
* Acc@1 79.064 Acc@5 94.596 loss 0.794
Accuracy of the model on the 50000 test images: 79.1%
Max accuracy: 79.31%
Epoch: [202]  [  0/312]  eta: 1:26:57  lr: 0.001093  min_lr: 0.001093  loss: 2.3960 (2.3960)  weight_decay: 0.0500 (0.0500)  time: 16.7214  data: 15.7154  max mem: 78493
Epoch: [202]  [ 10/312]  eta: 0:12:48  lr: 0.001092  min_lr: 0.001092  loss: 2.2738 (2.0956)  weight_decay: 0.0500 (0.0500)  time: 2.5455  data: 1.4293  max mem: 78493
Epoch: [202]  [ 20/312]  eta: 0:08:52  lr: 0.001091  min_lr: 0.001091  loss: 2.0644 (2.0803)  weight_decay: 0.0500 (0.0500)  time: 1.0801  data: 0.0024  max mem: 78493
Epoch: [202]  [ 30/312]  eta: 0:07:20  lr: 0.001091  min_lr: 0.001091  loss: 2.0910 (2.0763)  weight_decay: 0.0500 (0.0500)  time: 1.0206  data: 0.0023  max mem: 78493
Epoch: [202]  [ 40/312]  eta: 0:06:27  lr: 0.001090  min_lr: 0.001090  loss: 2.0910 (2.0605)  weight_decay: 0.0500 (0.0500)  time: 1.0073  data: 0.0004  max mem: 78493
Epoch: [202]  [ 50/312]  eta: 0:05:51  lr: 0.001090  min_lr: 0.001090  loss: 2.1997 (2.0685)  weight_decay: 0.0500 (0.0500)  time: 1.0046  data: 0.0004  max mem: 78493
Epoch: [202]  [ 60/312]  eta: 0:05:24  lr: 0.001089  min_lr: 0.001089  loss: 2.1402 (2.0791)  weight_decay: 0.0500 (0.0500)  time: 1.0066  data: 0.0005  max mem: 78493
Epoch: [202]  [ 70/312]  eta: 0:05:02  lr: 0.001088  min_lr: 0.001088  loss: 2.2924 (2.1133)  weight_decay: 0.0500 (0.0500)  time: 1.0088  data: 0.0005  max mem: 78493
Epoch: [202]  [ 80/312]  eta: 0:04:42  lr: 0.001088  min_lr: 0.001088  loss: 2.2948 (2.1212)  weight_decay: 0.0500 (0.0500)  time: 1.0074  data: 0.0004  max mem: 78493
Epoch: [202]  [ 90/312]  eta: 0:04:25  lr: 0.001087  min_lr: 0.001087  loss: 2.1646 (2.1111)  weight_decay: 0.0500 (0.0500)  time: 1.0079  data: 0.0004  max mem: 78493
Epoch: [202]  [100/312]  eta: 0:04:09  lr: 0.001086  min_lr: 0.001086  loss: 2.2502 (2.1318)  weight_decay: 0.0500 (0.0500)  time: 1.0094  data: 0.0004  max mem: 78493
Epoch: [202]  [110/312]  eta: 0:03:54  lr: 0.001086  min_lr: 0.001086  loss: 2.1334 (2.1254)  weight_decay: 0.0500 (0.0500)  time: 1.0096  data: 0.0004  max mem: 78493
Epoch: [202]  [120/312]  eta: 0:03:40  lr: 0.001085  min_lr: 0.001085  loss: 1.8920 (2.1128)  weight_decay: 0.0500 (0.0500)  time: 1.0078  data: 0.0004  max mem: 78493
Epoch: [202]  [130/312]  eta: 0:03:27  lr: 0.001084  min_lr: 0.001084  loss: 1.8920 (2.0982)  weight_decay: 0.0500 (0.0500)  time: 1.0077  data: 0.0012  max mem: 78493
Epoch: [202]  [140/312]  eta: 0:03:14  lr: 0.001084  min_lr: 0.001084  loss: 1.9860 (2.0875)  weight_decay: 0.0500 (0.0500)  time: 1.0093  data: 0.0012  max mem: 78493
Epoch: [202]  [150/312]  eta: 0:03:01  lr: 0.001083  min_lr: 0.001083  loss: 2.1657 (2.0890)  weight_decay: 0.0500 (0.0500)  time: 1.0099  data: 0.0004  max mem: 78493
Epoch: [202]  [160/312]  eta: 0:02:49  lr: 0.001083  min_lr: 0.001083  loss: 2.2298 (2.0940)  weight_decay: 0.0500 (0.0500)  time: 1.0085  data: 0.0005  max mem: 78493
Epoch: [202]  [170/312]  eta: 0:02:37  lr: 0.001082  min_lr: 0.001082  loss: 2.1549 (2.0891)  weight_decay: 0.0500 (0.0500)  time: 1.0069  data: 0.0005  max mem: 78493
Epoch: [202]  [180/312]  eta: 0:02:25  lr: 0.001081  min_lr: 0.001081  loss: 2.1388 (2.0881)  weight_decay: 0.0500 (0.0500)  time: 1.0083  data: 0.0004  max mem: 78493
Epoch: [202]  [190/312]  eta: 0:02:13  lr: 0.001081  min_lr: 0.001081  loss: 2.1388 (2.0876)  weight_decay: 0.0500 (0.0500)  time: 1.0093  data: 0.0004  max mem: 78493
Epoch: [202]  [200/312]  eta: 0:02:02  lr: 0.001080  min_lr: 0.001080  loss: 2.1324 (2.0906)  weight_decay: 0.0500 (0.0500)  time: 1.0068  data: 0.0004  max mem: 78493
Epoch: [202]  [210/312]  eta: 0:01:51  lr: 0.001079  min_lr: 0.001079  loss: 2.1324 (2.0898)  weight_decay: 0.0500 (0.0500)  time: 1.0058  data: 0.0004  max mem: 78493
Epoch: [202]  [220/312]  eta: 0:01:39  lr: 0.001079  min_lr: 0.001079  loss: 2.0806 (2.0901)  weight_decay: 0.0500 (0.0500)  time: 1.0083  data: 0.0004  max mem: 78493
Epoch: [202]  [230/312]  eta: 0:01:28  lr: 0.001078  min_lr: 0.001078  loss: 2.1181 (2.0885)  weight_decay: 0.0500 (0.0500)  time: 1.0087  data: 0.0004  max mem: 78493
Epoch: [202]  [240/312]  eta: 0:01:17  lr: 0.001077  min_lr: 0.001077  loss: 2.2410 (2.0939)  weight_decay: 0.0500 (0.0500)  time: 1.0074  data: 0.0004  max mem: 78493
Epoch: [202]  [250/312]  eta: 0:01:06  lr: 0.001077  min_lr: 0.001077  loss: 2.2562 (2.0977)  weight_decay: 0.0500 (0.0500)  time: 1.0087  data: 0.0004  max mem: 78493
Epoch: [202]  [260/312]  eta: 0:00:55  lr: 0.001076  min_lr: 0.001076  loss: 2.1507 (2.0962)  weight_decay: 0.0500 (0.0500)  time: 1.0092  data: 0.0005  max mem: 78493
Epoch: [202]  [270/312]  eta: 0:00:44  lr: 0.001075  min_lr: 0.001075  loss: 2.0410 (2.0926)  weight_decay: 0.0500 (0.0500)  time: 1.0073  data: 0.0004  max mem: 78493
Epoch: [202]  [280/312]  eta: 0:00:34  lr: 0.001075  min_lr: 0.001075  loss: 2.2491 (2.0958)  weight_decay: 0.0500 (0.0500)  time: 1.0070  data: 0.0011  max mem: 78493
Epoch: [202]  [290/312]  eta: 0:00:23  lr: 0.001074  min_lr: 0.001074  loss: 2.2491 (2.0957)  weight_decay: 0.0500 (0.0500)  time: 1.0049  data: 0.0010  max mem: 78493
Epoch: [202]  [300/312]  eta: 0:00:12  lr: 0.001074  min_lr: 0.001074  loss: 2.1812 (2.0996)  weight_decay: 0.0500 (0.0500)  time: 1.0017  data: 0.0001  max mem: 78493
Epoch: [202]  [310/312]  eta: 0:00:02  lr: 0.001073  min_lr: 0.001073  loss: 2.2552 (2.1047)  weight_decay: 0.0500 (0.0500)  time: 1.0015  data: 0.0001  max mem: 78493
Epoch: [202]  [311/312]  eta: 0:00:01  lr: 0.001073  min_lr: 0.001073  loss: 2.2552 (2.1041)  weight_decay: 0.0500 (0.0500)  time: 1.0015  data: 0.0001  max mem: 78493
Epoch: [202] Total time: 0:05:33 (1.0680 s / it)
Averaged stats: lr: 0.001073  min_lr: 0.001073  loss: 2.2552 (2.1032)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:12  loss: 0.5810 (0.5810)  acc1: 85.2865 (85.2865)  acc5: 96.4844 (96.4844)  time: 8.1086  data: 7.8307  max mem: 78493
Test:  [8/9]  eta: 0:00:01  loss: 0.9088 (0.8163)  acc1: 76.9531 (78.3840)  acc5: 94.6615 (94.4480)  time: 1.0993  data: 0.8702  max mem: 78493
Test: Total time: 0:00:10 (1.1455 s / it)
* Acc@1 79.042 Acc@5 94.486 loss 0.802
Accuracy of the model on the 50000 test images: 79.0%
Max accuracy: 79.31%
Epoch: [203]  [  0/312]  eta: 1:19:40  lr: 0.001073  min_lr: 0.001073  loss: 2.3785 (2.3785)  weight_decay: 0.0500 (0.0500)  time: 15.3205  data: 11.5779  max mem: 78493
Epoch: [203]  [ 10/312]  eta: 0:13:06  lr: 0.001072  min_lr: 0.001072  loss: 2.2905 (2.2051)  weight_decay: 0.0500 (0.0500)  time: 2.6034  data: 1.1740  max mem: 78493
Epoch: [203]  [ 20/312]  eta: 0:08:59  lr: 0.001072  min_lr: 0.001072  loss: 2.1756 (2.1057)  weight_decay: 0.0500 (0.0500)  time: 1.1742  data: 0.0670  max mem: 78493
Epoch: [203]  [ 30/312]  eta: 0:07:24  lr: 0.001071  min_lr: 0.001071  loss: 2.1455 (2.1006)  weight_decay: 0.0500 (0.0500)  time: 1.0108  data: 0.0004  max mem: 78493
Epoch: [203]  [ 40/312]  eta: 0:06:30  lr: 0.001070  min_lr: 0.001070  loss: 2.2205 (2.1345)  weight_decay: 0.0500 (0.0500)  time: 1.0060  data: 0.0004  max mem: 78493
Epoch: [203]  [ 50/312]  eta: 0:05:54  lr: 0.001070  min_lr: 0.001070  loss: 2.2390 (2.1176)  weight_decay: 0.0500 (0.0500)  time: 1.0085  data: 0.0004  max mem: 78493
Epoch: [203]  [ 60/312]  eta: 0:05:26  lr: 0.001069  min_lr: 0.001069  loss: 2.1507 (2.1249)  weight_decay: 0.0500 (0.0500)  time: 1.0076  data: 0.0005  max mem: 78493
Epoch: [203]  [ 70/312]  eta: 0:05:04  lr: 0.001068  min_lr: 0.001068  loss: 2.1507 (2.1083)  weight_decay: 0.0500 (0.0500)  time: 1.0090  data: 0.0005  max mem: 78493
Epoch: [203]  [ 80/312]  eta: 0:04:44  lr: 0.001068  min_lr: 0.001068  loss: 2.1982 (2.1106)  weight_decay: 0.0500 (0.0500)  time: 1.0109  data: 0.0004  max mem: 78493
Epoch: [203]  [ 90/312]  eta: 0:04:26  lr: 0.001067  min_lr: 0.001067  loss: 2.2618 (2.1197)  weight_decay: 0.0500 (0.0500)  time: 1.0115  data: 0.0019  max mem: 78493
Epoch: [203]  [100/312]  eta: 0:04:10  lr: 0.001066  min_lr: 0.001066  loss: 2.1717 (2.1140)  weight_decay: 0.0500 (0.0500)  time: 1.0109  data: 0.0019  max mem: 78493
Epoch: [203]  [110/312]  eta: 0:03:55  lr: 0.001066  min_lr: 0.001066  loss: 2.1717 (2.1164)  weight_decay: 0.0500 (0.0500)  time: 1.0068  data: 0.0004  max mem: 78493
Epoch: [203]  [120/312]  eta: 0:03:41  lr: 0.001065  min_lr: 0.001065  loss: 2.2439 (2.1218)  weight_decay: 0.0500 (0.0500)  time: 1.0064  data: 0.0004  max mem: 78493
Epoch: [203]  [130/312]  eta: 0:03:28  lr: 0.001065  min_lr: 0.001065  loss: 2.0786 (2.1124)  weight_decay: 0.0500 (0.0500)  time: 1.0073  data: 0.0004  max mem: 78493
Epoch: [203]  [140/312]  eta: 0:03:14  lr: 0.001064  min_lr: 0.001064  loss: 2.0786 (2.1182)  weight_decay: 0.0500 (0.0500)  time: 1.0061  data: 0.0005  max mem: 78493
Epoch: [203]  [150/312]  eta: 0:03:02  lr: 0.001063  min_lr: 0.001063  loss: 2.0791 (2.1056)  weight_decay: 0.0500 (0.0500)  time: 1.0045  data: 0.0005  max mem: 78493
Epoch: [203]  [160/312]  eta: 0:02:49  lr: 0.001063  min_lr: 0.001063  loss: 2.0064 (2.1020)  weight_decay: 0.0500 (0.0500)  time: 1.0054  data: 0.0005  max mem: 78493
Epoch: [203]  [170/312]  eta: 0:02:37  lr: 0.001062  min_lr: 0.001062  loss: 2.2515 (2.1093)  weight_decay: 0.0500 (0.0500)  time: 1.0069  data: 0.0012  max mem: 78493
Epoch: [203]  [180/312]  eta: 0:02:25  lr: 0.001061  min_lr: 0.001061  loss: 2.1842 (2.1013)  weight_decay: 0.0500 (0.0500)  time: 1.0079  data: 0.0012  max mem: 78493
Epoch: [203]  [190/312]  eta: 0:02:14  lr: 0.001061  min_lr: 0.001061  loss: 2.0784 (2.0973)  weight_decay: 0.0500 (0.0500)  time: 1.0076  data: 0.0004  max mem: 78493
Epoch: [203]  [200/312]  eta: 0:02:02  lr: 0.001060  min_lr: 0.001060  loss: 2.1124 (2.0978)  weight_decay: 0.0500 (0.0500)  time: 1.0063  data: 0.0004  max mem: 78493
Epoch: [203]  [210/312]  eta: 0:01:51  lr: 0.001059  min_lr: 0.001059  loss: 2.2112 (2.1018)  weight_decay: 0.0500 (0.0500)  time: 1.0051  data: 0.0013  max mem: 78493
Epoch: [203]  [220/312]  eta: 0:01:40  lr: 0.001059  min_lr: 0.001059  loss: 2.1920 (2.0963)  weight_decay: 0.0500 (0.0500)  time: 1.0047  data: 0.0013  max mem: 78493
Epoch: [203]  [230/312]  eta: 0:01:28  lr: 0.001058  min_lr: 0.001058  loss: 1.9568 (2.0944)  weight_decay: 0.0500 (0.0500)  time: 1.0053  data: 0.0005  max mem: 78493
Epoch: [203]  [240/312]  eta: 0:01:17  lr: 0.001058  min_lr: 0.001058  loss: 2.1552 (2.0945)  weight_decay: 0.0500 (0.0500)  time: 1.0051  data: 0.0005  max mem: 78493
Epoch: [203]  [250/312]  eta: 0:01:06  lr: 0.001057  min_lr: 0.001057  loss: 2.0839 (2.0935)  weight_decay: 0.0500 (0.0500)  time: 1.0042  data: 0.0004  max mem: 78493
Epoch: [203]  [260/312]  eta: 0:00:55  lr: 0.001056  min_lr: 0.001056  loss: 2.0495 (2.0880)  weight_decay: 0.0500 (0.0500)  time: 1.0056  data: 0.0004  max mem: 78493
Epoch: [203]  [270/312]  eta: 0:00:45  lr: 0.001056  min_lr: 0.001056  loss: 2.0495 (2.0849)  weight_decay: 0.0500 (0.0500)  time: 1.0061  data: 0.0004  max mem: 78493
Epoch: [203]  [280/312]  eta: 0:00:34  lr: 0.001055  min_lr: 0.001055  loss: 2.1068 (2.0859)  weight_decay: 0.0500 (0.0500)  time: 1.0045  data: 0.0010  max mem: 78493
Epoch: [203]  [290/312]  eta: 0:00:23  lr: 0.001054  min_lr: 0.001054  loss: 2.0952 (2.0826)  weight_decay: 0.0500 (0.0500)  time: 1.0032  data: 0.0009  max mem: 78493
Epoch: [203]  [300/312]  eta: 0:00:12  lr: 0.001054  min_lr: 0.001054  loss: 2.1058 (2.0845)  weight_decay: 0.0500 (0.0500)  time: 1.0020  data: 0.0001  max mem: 78493
Epoch: [203]  [310/312]  eta: 0:00:02  lr: 0.001053  min_lr: 0.001053  loss: 2.1658 (2.0826)  weight_decay: 0.0500 (0.0500)  time: 1.0019  data: 0.0001  max mem: 78493
Epoch: [203]  [311/312]  eta: 0:00:01  lr: 0.001053  min_lr: 0.001053  loss: 2.1658 (2.0834)  weight_decay: 0.0500 (0.0500)  time: 1.0018  data: 0.0001  max mem: 78493
Epoch: [203] Total time: 0:05:33 (1.0687 s / it)
Averaged stats: lr: 0.001053  min_lr: 0.001053  loss: 2.1658 (2.0862)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:15  loss: 0.5307 (0.5307)  acc1: 86.3281 (86.3281)  acc5: 97.5260 (97.5260)  time: 8.3834  data: 8.1148  max mem: 78493
Test:  [8/9]  eta: 0:00:01  loss: 0.8699 (0.7809)  acc1: 78.9062 (79.2160)  acc5: 94.1406 (94.6240)  time: 1.1308  data: 0.9017  max mem: 78493
Test: Total time: 0:00:10 (1.1598 s / it)
* Acc@1 79.482 Acc@5 94.680 loss 0.776
Accuracy of the model on the 50000 test images: 79.5%
Max accuracy: 79.48%
Epoch: [204]  [  0/312]  eta: 1:29:52  lr: 0.001053  min_lr: 0.001053  loss: 1.6911 (1.6911)  weight_decay: 0.0500 (0.0500)  time: 17.2837  data: 16.2765  max mem: 78493
Epoch: [204]  [ 10/312]  eta: 0:13:54  lr: 0.001052  min_lr: 0.001052  loss: 1.9687 (2.0421)  weight_decay: 0.0500 (0.0500)  time: 2.7647  data: 1.4802  max mem: 78493
Epoch: [204]  [ 20/312]  eta: 0:09:23  lr: 0.001052  min_lr: 0.001052  loss: 2.2597 (2.1862)  weight_decay: 0.0500 (0.0500)  time: 1.1617  data: 0.0018  max mem: 78493
Epoch: [204]  [ 30/312]  eta: 0:07:40  lr: 0.001051  min_lr: 0.001051  loss: 2.2332 (2.1552)  weight_decay: 0.0500 (0.0500)  time: 1.0094  data: 0.0027  max mem: 78493
Epoch: [204]  [ 40/312]  eta: 0:06:42  lr: 0.001050  min_lr: 0.001050  loss: 2.1114 (2.1161)  weight_decay: 0.0500 (0.0500)  time: 1.0095  data: 0.0014  max mem: 78493
Epoch: [204]  [ 50/312]  eta: 0:06:03  lr: 0.001050  min_lr: 0.001050  loss: 2.1114 (2.1053)  weight_decay: 0.0500 (0.0500)  time: 1.0092  data: 0.0005  max mem: 78493
Epoch: [204]  [ 60/312]  eta: 0:05:34  lr: 0.001049  min_lr: 0.001049  loss: 2.1334 (2.0933)  weight_decay: 0.0500 (0.0500)  time: 1.0093  data: 0.0005  max mem: 78493
Epoch: [204]  [ 70/312]  eta: 0:05:10  lr: 0.001049  min_lr: 0.001049  loss: 2.1671 (2.1006)  weight_decay: 0.0500 (0.0500)  time: 1.0100  data: 0.0005  max mem: 78493
Epoch: [204]  [ 80/312]  eta: 0:04:49  lr: 0.001048  min_lr: 0.001048  loss: 2.1879 (2.0995)  weight_decay: 0.0500 (0.0500)  time: 1.0089  data: 0.0005  max mem: 78493
Epoch: [204]  [ 90/312]  eta: 0:04:31  lr: 0.001047  min_lr: 0.001047  loss: 2.1908 (2.1079)  weight_decay: 0.0500 (0.0500)  time: 1.0083  data: 0.0005  max mem: 78493
Epoch: [204]  [100/312]  eta: 0:04:14  lr: 0.001047  min_lr: 0.001047  loss: 2.1506 (2.0941)  weight_decay: 0.0500 (0.0500)  time: 1.0069  data: 0.0004  max mem: 78493
Epoch: [204]  [110/312]  eta: 0:03:58  lr: 0.001046  min_lr: 0.001046  loss: 2.2040 (2.1052)  weight_decay: 0.0500 (0.0500)  time: 1.0059  data: 0.0005  max mem: 78493
Epoch: [204]  [120/312]  eta: 0:03:44  lr: 0.001045  min_lr: 0.001045  loss: 2.2320 (2.1035)  weight_decay: 0.0500 (0.0500)  time: 1.0074  data: 0.0005  max mem: 78493
Epoch: [204]  [130/312]  eta: 0:03:30  lr: 0.001045  min_lr: 0.001045  loss: 2.1898 (2.1006)  weight_decay: 0.0500 (0.0500)  time: 1.0078  data: 0.0004  max mem: 78493
Epoch: [204]  [140/312]  eta: 0:03:16  lr: 0.001044  min_lr: 0.001044  loss: 2.2734 (2.1132)  weight_decay: 0.0500 (0.0500)  time: 1.0061  data: 0.0004  max mem: 78493
Epoch: [204]  [150/312]  eta: 0:03:04  lr: 0.001044  min_lr: 0.001044  loss: 2.2678 (2.1144)  weight_decay: 0.0500 (0.0500)  time: 1.0048  data: 0.0005  max mem: 78493
Epoch: [204]  [160/312]  eta: 0:02:51  lr: 0.001043  min_lr: 0.001043  loss: 2.1647 (2.1092)  weight_decay: 0.0500 (0.0500)  time: 1.0048  data: 0.0004  max mem: 78493
Epoch: [204]  [170/312]  eta: 0:02:39  lr: 0.001042  min_lr: 0.001042  loss: 2.2321 (2.1135)  weight_decay: 0.0500 (0.0500)  time: 1.0065  data: 0.0004  max mem: 78493
Epoch: [204]  [180/312]  eta: 0:02:27  lr: 0.001042  min_lr: 0.001042  loss: 2.1443 (2.1082)  weight_decay: 0.0500 (0.0500)  time: 1.0084  data: 0.0004  max mem: 78493
Epoch: [204]  [190/312]  eta: 0:02:15  lr: 0.001041  min_lr: 0.001041  loss: 1.9702 (2.1045)  weight_decay: 0.0500 (0.0500)  time: 1.0082  data: 0.0004  max mem: 78493
Epoch: [204]  [200/312]  eta: 0:02:03  lr: 0.001040  min_lr: 0.001040  loss: 2.1009 (2.1116)  weight_decay: 0.0500 (0.0500)  time: 1.0052  data: 0.0004  max mem: 78493
Epoch: [204]  [210/312]  eta: 0:01:52  lr: 0.001040  min_lr: 0.001040  loss: 2.0547 (2.1010)  weight_decay: 0.0500 (0.0500)  time: 1.0051  data: 0.0004  max mem: 78493
Epoch: [204]  [220/312]  eta: 0:01:40  lr: 0.001039  min_lr: 0.001039  loss: 2.2070 (2.1070)  weight_decay: 0.0500 (0.0500)  time: 1.0064  data: 0.0004  max mem: 78493
Epoch: [204]  [230/312]  eta: 0:01:29  lr: 0.001038  min_lr: 0.001038  loss: 2.2844 (2.1117)  weight_decay: 0.0500 (0.0500)  time: 1.0063  data: 0.0004  max mem: 78493
Epoch: [204]  [240/312]  eta: 0:01:18  lr: 0.001038  min_lr: 0.001038  loss: 2.0764 (2.1096)  weight_decay: 0.0500 (0.0500)  time: 1.0068  data: 0.0004  max mem: 78493
Epoch: [204]  [250/312]  eta: 0:01:07  lr: 0.001037  min_lr: 0.001037  loss: 2.0509 (2.1144)  weight_decay: 0.0500 (0.0500)  time: 1.0069  data: 0.0004  max mem: 78493
Epoch: [204]  [260/312]  eta: 0:00:56  lr: 0.001037  min_lr: 0.001037  loss: 2.1266 (2.1152)  weight_decay: 0.0500 (0.0500)  time: 1.0062  data: 0.0004  max mem: 78493
Epoch: [204]  [270/312]  eta: 0:00:45  lr: 0.001036  min_lr: 0.001036  loss: 2.1879 (2.1162)  weight_decay: 0.0500 (0.0500)  time: 1.0060  data: 0.0004  max mem: 78493
Epoch: [204]  [280/312]  eta: 0:00:34  lr: 0.001035  min_lr: 0.001035  loss: 2.1597 (2.1133)  weight_decay: 0.0500 (0.0500)  time: 1.0062  data: 0.0010  max mem: 78493
Epoch: [204]  [290/312]  eta: 0:00:23  lr: 0.001035  min_lr: 0.001035  loss: 2.0581 (2.1105)  weight_decay: 0.0500 (0.0500)  time: 1.0036  data: 0.0009  max mem: 78493
Epoch: [204]  [300/312]  eta: 0:00:12  lr: 0.001034  min_lr: 0.001034  loss: 1.9594 (2.1081)  weight_decay: 0.0500 (0.0500)  time: 1.0013  data: 0.0001  max mem: 78493
Epoch: [204]  [310/312]  eta: 0:00:02  lr: 0.001033  min_lr: 0.001033  loss: 2.0789 (2.1103)  weight_decay: 0.0500 (0.0500)  time: 1.0016  data: 0.0001  max mem: 78493
Epoch: [204]  [311/312]  eta: 0:00:01  lr: 0.001033  min_lr: 0.001033  loss: 2.1803 (2.1122)  weight_decay: 0.0500 (0.0500)  time: 1.0017  data: 0.0001  max mem: 78493
Epoch: [204] Total time: 0:05:35 (1.0741 s / it)
Averaged stats: lr: 0.001033  min_lr: 0.001033  loss: 2.1803 (2.0949)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:14  loss: 0.5827 (0.5827)  acc1: 86.3281 (86.3281)  acc5: 97.1354 (97.1354)  time: 8.2527  data: 7.9712  max mem: 78493
Test:  [8/9]  eta: 0:00:01  loss: 0.8680 (0.7969)  acc1: 78.6458 (79.2800)  acc5: 94.9219 (94.7680)  time: 1.1257  data: 0.8858  max mem: 78493
Test: Total time: 0:00:10 (1.1645 s / it)
* Acc@1 79.474 Acc@5 94.814 loss 0.787
Accuracy of the model on the 50000 test images: 79.5%
Max accuracy: 79.48%
Epoch: [205]  [  0/312]  eta: 1:27:35  lr: 0.001033  min_lr: 0.001033  loss: 2.0347 (2.0347)  weight_decay: 0.0500 (0.0500)  time: 16.8450  data: 14.6563  max mem: 78493
Epoch: [205]  [ 10/312]  eta: 0:13:40  lr: 0.001033  min_lr: 0.001033  loss: 2.0977 (1.9826)  weight_decay: 0.0500 (0.0500)  time: 2.7162  data: 1.3358  max mem: 78493
Epoch: [205]  [ 20/312]  eta: 0:09:15  lr: 0.001032  min_lr: 0.001032  loss: 2.1617 (2.0374)  weight_decay: 0.0500 (0.0500)  time: 1.1554  data: 0.0021  max mem: 78493
Epoch: [205]  [ 30/312]  eta: 0:07:35  lr: 0.001031  min_lr: 0.001031  loss: 2.1641 (2.0748)  weight_decay: 0.0500 (0.0500)  time: 1.0081  data: 0.0005  max mem: 78493
Epoch: [205]  [ 40/312]  eta: 0:06:38  lr: 0.001031  min_lr: 0.001031  loss: 2.0434 (2.0610)  weight_decay: 0.0500 (0.0500)  time: 1.0071  data: 0.0004  max mem: 78493
Epoch: [205]  [ 50/312]  eta: 0:06:00  lr: 0.001030  min_lr: 0.001030  loss: 2.1429 (2.0891)  weight_decay: 0.0500 (0.0500)  time: 1.0062  data: 0.0004  max mem: 78493
Epoch: [205]  [ 60/312]  eta: 0:05:31  lr: 0.001030  min_lr: 0.001030  loss: 2.1771 (2.0908)  weight_decay: 0.0500 (0.0500)  time: 1.0073  data: 0.0004  max mem: 78493
Epoch: [205]  [ 70/312]  eta: 0:05:07  lr: 0.001029  min_lr: 0.001029  loss: 2.1371 (2.0856)  weight_decay: 0.0500 (0.0500)  time: 1.0071  data: 0.0004  max mem: 78493
Epoch: [205]  [ 80/312]  eta: 0:04:47  lr: 0.001028  min_lr: 0.001028  loss: 2.0964 (2.0620)  weight_decay: 0.0500 (0.0500)  time: 1.0073  data: 0.0005  max mem: 78493
Epoch: [205]  [ 90/312]  eta: 0:04:29  lr: 0.001028  min_lr: 0.001028  loss: 2.0529 (2.0687)  weight_decay: 0.0500 (0.0500)  time: 1.0085  data: 0.0004  max mem: 78493
Epoch: [205]  [100/312]  eta: 0:04:13  lr: 0.001027  min_lr: 0.001027  loss: 2.1021 (2.0693)  weight_decay: 0.0500 (0.0500)  time: 1.0094  data: 0.0005  max mem: 78493
Epoch: [205]  [110/312]  eta: 0:03:57  lr: 0.001026  min_lr: 0.001026  loss: 2.2031 (2.0767)  weight_decay: 0.0500 (0.0500)  time: 1.0106  data: 0.0005  max mem: 78493
Epoch: [205]  [120/312]  eta: 0:03:43  lr: 0.001026  min_lr: 0.001026  loss: 2.0356 (2.0736)  weight_decay: 0.0500 (0.0500)  time: 1.0122  data: 0.0005  max mem: 78493
Epoch: [205]  [130/312]  eta: 0:03:29  lr: 0.001025  min_lr: 0.001025  loss: 2.0356 (2.0720)  weight_decay: 0.0500 (0.0500)  time: 1.0131  data: 0.0005  max mem: 78493
Epoch: [205]  [140/312]  eta: 0:03:16  lr: 0.001025  min_lr: 0.001025  loss: 2.1437 (2.0772)  weight_decay: 0.0500 (0.0500)  time: 1.0122  data: 0.0005  max mem: 78493
Epoch: [205]  [150/312]  eta: 0:03:03  lr: 0.001024  min_lr: 0.001024  loss: 2.1571 (2.0785)  weight_decay: 0.0500 (0.0500)  time: 1.0076  data: 0.0004  max mem: 78493
Epoch: [205]  [160/312]  eta: 0:02:51  lr: 0.001023  min_lr: 0.001023  loss: 2.0225 (2.0663)  weight_decay: 0.0500 (0.0500)  time: 1.0066  data: 0.0005  max mem: 78493
Epoch: [205]  [170/312]  eta: 0:02:38  lr: 0.001023  min_lr: 0.001023  loss: 1.8551 (2.0616)  weight_decay: 0.0500 (0.0500)  time: 1.0079  data: 0.0005  max mem: 78493
Epoch: [205]  [180/312]  eta: 0:02:26  lr: 0.001022  min_lr: 0.001022  loss: 1.8823 (2.0574)  weight_decay: 0.0500 (0.0500)  time: 1.0072  data: 0.0004  max mem: 78493
Epoch: [205]  [190/312]  eta: 0:02:15  lr: 0.001021  min_lr: 0.001021  loss: 2.1687 (2.0639)  weight_decay: 0.0500 (0.0500)  time: 1.0101  data: 0.0004  max mem: 78493
Epoch: [205]  [200/312]  eta: 0:02:03  lr: 0.001021  min_lr: 0.001021  loss: 1.9538 (2.0556)  weight_decay: 0.0500 (0.0500)  time: 1.0083  data: 0.0004  max mem: 78493
Epoch: [205]  [210/312]  eta: 0:01:51  lr: 0.001020  min_lr: 0.001020  loss: 1.8677 (2.0571)  weight_decay: 0.0500 (0.0500)  time: 1.0067  data: 0.0004  max mem: 78493
Epoch: [205]  [220/312]  eta: 0:01:40  lr: 0.001019  min_lr: 0.001019  loss: 2.2712 (2.0670)  weight_decay: 0.0500 (0.0500)  time: 1.0079  data: 0.0005  max mem: 78493
Epoch: [205]  [230/312]  eta: 0:01:29  lr: 0.001019  min_lr: 0.001019  loss: 2.2203 (2.0612)  weight_decay: 0.0500 (0.0500)  time: 1.0066  data: 0.0005  max mem: 78493
Epoch: [205]  [240/312]  eta: 0:01:18  lr: 0.001018  min_lr: 0.001018  loss: 1.9610 (2.0575)  weight_decay: 0.0500 (0.0500)  time: 1.0059  data: 0.0005  max mem: 78493
Epoch: [205]  [250/312]  eta: 0:01:07  lr: 0.001018  min_lr: 0.001018  loss: 2.1177 (2.0586)  weight_decay: 0.0500 (0.0500)  time: 1.0051  data: 0.0005  max mem: 78493
Epoch: [205]  [260/312]  eta: 0:00:56  lr: 0.001017  min_lr: 0.001017  loss: 2.1177 (2.0613)  weight_decay: 0.0500 (0.0500)  time: 1.0049  data: 0.0005  max mem: 78493
Epoch: [205]  [270/312]  eta: 0:00:45  lr: 0.001016  min_lr: 0.001016  loss: 2.1376 (2.0625)  weight_decay: 0.0500 (0.0500)  time: 1.0052  data: 0.0005  max mem: 78493
Epoch: [205]  [280/312]  eta: 0:00:34  lr: 0.001016  min_lr: 0.001016  loss: 2.1505 (2.0629)  weight_decay: 0.0500 (0.0500)  time: 1.0060  data: 0.0017  max mem: 78493
Epoch: [205]  [290/312]  eta: 0:00:23  lr: 0.001015  min_lr: 0.001015  loss: 2.2230 (2.0655)  weight_decay: 0.0500 (0.0500)  time: 1.0042  data: 0.0015  max mem: 78493
Epoch: [205]  [300/312]  eta: 0:00:12  lr: 0.001014  min_lr: 0.001014  loss: 2.1943 (2.0632)  weight_decay: 0.0500 (0.0500)  time: 1.0019  data: 0.0001  max mem: 78493
Epoch: [205]  [310/312]  eta: 0:00:02  lr: 0.001014  min_lr: 0.001014  loss: 1.9845 (2.0602)  weight_decay: 0.0500 (0.0500)  time: 1.0016  data: 0.0001  max mem: 78493
Epoch: [205]  [311/312]  eta: 0:00:01  lr: 0.001014  min_lr: 0.001014  loss: 1.9845 (2.0601)  weight_decay: 0.0500 (0.0500)  time: 1.0016  data: 0.0001  max mem: 78493
Epoch: [205] Total time: 0:05:34 (1.0733 s / it)
Averaged stats: lr: 0.001014  min_lr: 0.001014  loss: 1.9845 (2.0785)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:09  loss: 0.5731 (0.5731)  acc1: 85.9375 (85.9375)  acc5: 97.2656 (97.2656)  time: 7.6765  data: 7.3868  max mem: 78493
Test:  [8/9]  eta: 0:00:01  loss: 0.8673 (0.7847)  acc1: 78.2552 (79.1360)  acc5: 94.9219 (95.1360)  time: 1.0512  data: 0.8209  max mem: 78493
Test: Total time: 0:00:09 (1.0607 s / it)
* Acc@1 79.782 Acc@5 95.026 loss 0.773
Accuracy of the model on the 50000 test images: 79.8%
Max accuracy: 79.78%
Epoch: [206]  [  0/312]  eta: 1:22:30  lr: 0.001014  min_lr: 0.001014  loss: 2.0463 (2.0463)  weight_decay: 0.0500 (0.0500)  time: 15.8656  data: 14.8570  max mem: 78493
Epoch: [206]  [ 10/312]  eta: 0:13:08  lr: 0.001013  min_lr: 0.001013  loss: 1.9920 (2.0062)  weight_decay: 0.0500 (0.0500)  time: 2.6098  data: 1.3512  max mem: 78493
Epoch: [206]  [ 20/312]  eta: 0:09:00  lr: 0.001012  min_lr: 0.001012  loss: 1.9920 (2.0778)  weight_decay: 0.0500 (0.0500)  time: 1.1512  data: 0.0015  max mem: 78493
Epoch: [206]  [ 30/312]  eta: 0:07:25  lr: 0.001012  min_lr: 0.001012  loss: 2.1768 (2.1292)  weight_decay: 0.0500 (0.0500)  time: 1.0121  data: 0.0014  max mem: 78493
Epoch: [206]  [ 40/312]  eta: 0:06:31  lr: 0.001011  min_lr: 0.001011  loss: 2.2996 (2.1428)  weight_decay: 0.0500 (0.0500)  time: 1.0074  data: 0.0005  max mem: 78493
Epoch: [206]  [ 50/312]  eta: 0:05:55  lr: 0.001011  min_lr: 0.001011  loss: 2.0031 (2.0982)  weight_decay: 0.0500 (0.0500)  time: 1.0100  data: 0.0004  max mem: 78493
Epoch: [206]  [ 60/312]  eta: 0:05:27  lr: 0.001010  min_lr: 0.001010  loss: 2.0031 (2.1203)  weight_decay: 0.0500 (0.0500)  time: 1.0094  data: 0.0004  max mem: 78493
Epoch: [206]  [ 70/312]  eta: 0:05:04  lr: 0.001009  min_lr: 0.001009  loss: 2.1125 (2.1184)  weight_decay: 0.0500 (0.0500)  time: 1.0072  data: 0.0004  max mem: 78493
Epoch: [206]  [ 80/312]  eta: 0:04:44  lr: 0.001009  min_lr: 0.001009  loss: 2.0551 (2.1087)  weight_decay: 0.0500 (0.0500)  time: 1.0067  data: 0.0004  max mem: 78493
Epoch: [206]  [ 90/312]  eta: 0:04:26  lr: 0.001008  min_lr: 0.001008  loss: 2.1731 (2.0994)  weight_decay: 0.0500 (0.0500)  time: 1.0061  data: 0.0004  max mem: 78493
Epoch: [206]  [100/312]  eta: 0:04:10  lr: 0.001007  min_lr: 0.001007  loss: 2.1045 (2.0990)  weight_decay: 0.0500 (0.0500)  time: 1.0077  data: 0.0005  max mem: 78493
Epoch: [206]  [110/312]  eta: 0:03:55  lr: 0.001007  min_lr: 0.001007  loss: 2.1813 (2.1049)  weight_decay: 0.0500 (0.0500)  time: 1.0073  data: 0.0005  max mem: 78493
Epoch: [206]  [120/312]  eta: 0:03:41  lr: 0.001006  min_lr: 0.001006  loss: 2.1813 (2.0967)  weight_decay: 0.0500 (0.0500)  time: 1.0066  data: 0.0004  max mem: 78493
Epoch: [206]  [130/312]  eta: 0:03:27  lr: 0.001006  min_lr: 0.001006  loss: 2.0247 (2.0906)  weight_decay: 0.0500 (0.0500)  time: 1.0067  data: 0.0004  max mem: 78493
Epoch: [206]  [140/312]  eta: 0:03:14  lr: 0.001005  min_lr: 0.001005  loss: 2.1472 (2.1006)  weight_decay: 0.0500 (0.0500)  time: 1.0055  data: 0.0004  max mem: 78493
Epoch: [206]  [150/312]  eta: 0:03:02  lr: 0.001004  min_lr: 0.001004  loss: 2.2596 (2.1061)  weight_decay: 0.0500 (0.0500)  time: 1.0073  data: 0.0004  max mem: 78493
Epoch: [206]  [160/312]  eta: 0:02:49  lr: 0.001004  min_lr: 0.001004  loss: 2.2063 (2.0898)  weight_decay: 0.0500 (0.0500)  time: 1.0078  data: 0.0004  max mem: 78493
Epoch: [206]  [170/312]  eta: 0:02:37  lr: 0.001003  min_lr: 0.001003  loss: 1.9288 (2.0857)  weight_decay: 0.0500 (0.0500)  time: 1.0081  data: 0.0005  max mem: 78493
Epoch: [206]  [180/312]  eta: 0:02:25  lr: 0.001002  min_lr: 0.001002  loss: 2.1394 (2.0889)  weight_decay: 0.0500 (0.0500)  time: 1.0091  data: 0.0005  max mem: 78493
Epoch: [206]  [190/312]  eta: 0:02:14  lr: 0.001002  min_lr: 0.001002  loss: 2.1956 (2.0880)  weight_decay: 0.0500 (0.0500)  time: 1.0075  data: 0.0004  max mem: 78493
Epoch: [206]  [200/312]  eta: 0:02:02  lr: 0.001001  min_lr: 0.001001  loss: 2.1343 (2.0907)  weight_decay: 0.0500 (0.0500)  time: 1.0075  data: 0.0004  max mem: 78493
Epoch: [206]  [210/312]  eta: 0:01:51  lr: 0.001001  min_lr: 0.001001  loss: 2.2271 (2.0944)  weight_decay: 0.0500 (0.0500)  time: 1.0078  data: 0.0004  max mem: 78493
Epoch: [206]  [220/312]  eta: 0:01:40  lr: 0.001000  min_lr: 0.001000  loss: 2.2351 (2.0930)  weight_decay: 0.0500 (0.0500)  time: 1.0082  data: 0.0005  max mem: 78493
Epoch: [206]  [230/312]  eta: 0:01:28  lr: 0.000999  min_lr: 0.000999  loss: 2.0537 (2.0879)  weight_decay: 0.0500 (0.0500)  time: 1.0083  data: 0.0004  max mem: 78493
Epoch: [206]  [240/312]  eta: 0:01:17  lr: 0.000999  min_lr: 0.000999  loss: 2.0093 (2.0811)  weight_decay: 0.0500 (0.0500)  time: 1.0069  data: 0.0004  max mem: 78493
Epoch: [206]  [250/312]  eta: 0:01:06  lr: 0.000998  min_lr: 0.000998  loss: 2.0203 (2.0830)  weight_decay: 0.0500 (0.0500)  time: 1.0057  data: 0.0004  max mem: 78493
Epoch: [206]  [260/312]  eta: 0:00:55  lr: 0.000998  min_lr: 0.000998  loss: 2.0697 (2.0734)  weight_decay: 0.0500 (0.0500)  time: 1.0050  data: 0.0004  max mem: 78493
Epoch: [206]  [270/312]  eta: 0:00:45  lr: 0.000997  min_lr: 0.000997  loss: 2.0880 (2.0747)  weight_decay: 0.0500 (0.0500)  time: 1.0063  data: 0.0004  max mem: 78493
Epoch: [206]  [280/312]  eta: 0:00:34  lr: 0.000996  min_lr: 0.000996  loss: 2.0657 (2.0719)  weight_decay: 0.0500 (0.0500)  time: 1.0071  data: 0.0010  max mem: 78493
Epoch: [206]  [290/312]  eta: 0:00:23  lr: 0.000996  min_lr: 0.000996  loss: 2.0657 (2.0725)  weight_decay: 0.0500 (0.0500)  time: 1.0040  data: 0.0009  max mem: 78493
Epoch: [206]  [300/312]  eta: 0:00:12  lr: 0.000995  min_lr: 0.000995  loss: 2.1533 (2.0714)  weight_decay: 0.0500 (0.0500)  time: 1.0014  data: 0.0001  max mem: 78493
Epoch: [206]  [310/312]  eta: 0:00:02  lr: 0.000994  min_lr: 0.000994  loss: 2.1619 (2.0754)  weight_decay: 0.0500 (0.0500)  time: 1.0014  data: 0.0001  max mem: 78493
Epoch: [206]  [311/312]  eta: 0:00:01  lr: 0.000994  min_lr: 0.000994  loss: 2.1619 (2.0753)  weight_decay: 0.0500 (0.0500)  time: 1.0014  data: 0.0001  max mem: 78493
Epoch: [206] Total time: 0:05:33 (1.0689 s / it)
Averaged stats: lr: 0.000994  min_lr: 0.000994  loss: 2.1619 (2.0632)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:16  loss: 0.5801 (0.5801)  acc1: 84.7656 (84.7656)  acc5: 97.5260 (97.5260)  time: 8.4864  data: 8.2252  max mem: 78493
Test:  [8/9]  eta: 0:00:01  loss: 0.9069 (0.7986)  acc1: 79.0365 (79.0400)  acc5: 94.2708 (94.5440)  time: 1.1470  data: 0.9140  max mem: 78493
Test: Total time: 0:00:10 (1.1947 s / it)
* Acc@1 79.494 Acc@5 94.780 loss 0.786
Accuracy of the model on the 50000 test images: 79.5%
Max accuracy: 79.78%
Epoch: [207]  [  0/312]  eta: 1:31:40  lr: 0.000994  min_lr: 0.000994  loss: 1.6593 (1.6593)  weight_decay: 0.0500 (0.0500)  time: 17.6309  data: 14.2725  max mem: 78493
Epoch: [207]  [ 10/312]  eta: 0:13:22  lr: 0.000994  min_lr: 0.000994  loss: 1.8702 (1.9323)  weight_decay: 0.0500 (0.0500)  time: 2.6587  data: 1.3125  max mem: 78493
Epoch: [207]  [ 20/312]  eta: 0:09:07  lr: 0.000993  min_lr: 0.000993  loss: 2.1281 (2.0906)  weight_decay: 0.0500 (0.0500)  time: 1.0873  data: 0.0085  max mem: 78493
Epoch: [207]  [ 30/312]  eta: 0:07:29  lr: 0.000992  min_lr: 0.000992  loss: 2.3287 (2.1751)  weight_decay: 0.0500 (0.0500)  time: 1.0107  data: 0.0005  max mem: 78493
Epoch: [207]  [ 40/312]  eta: 0:06:35  lr: 0.000992  min_lr: 0.000992  loss: 2.2218 (2.1227)  weight_decay: 0.0500 (0.0500)  time: 1.0090  data: 0.0004  max mem: 78493
Epoch: [207]  [ 50/312]  eta: 0:05:57  lr: 0.000991  min_lr: 0.000991  loss: 2.1610 (2.1134)  weight_decay: 0.0500 (0.0500)  time: 1.0080  data: 0.0005  max mem: 78493
Epoch: [207]  [ 60/312]  eta: 0:05:29  lr: 0.000991  min_lr: 0.000991  loss: 2.0990 (2.0877)  weight_decay: 0.0500 (0.0500)  time: 1.0077  data: 0.0005  max mem: 78493
Epoch: [207]  [ 70/312]  eta: 0:05:05  lr: 0.000990  min_lr: 0.000990  loss: 2.0161 (2.0770)  weight_decay: 0.0500 (0.0500)  time: 1.0074  data: 0.0004  max mem: 78493
Epoch: [207]  [ 80/312]  eta: 0:04:45  lr: 0.000989  min_lr: 0.000989  loss: 2.0150 (2.0436)  weight_decay: 0.0500 (0.0500)  time: 1.0067  data: 0.0005  max mem: 78493
Epoch: [207]  [ 90/312]  eta: 0:04:28  lr: 0.000989  min_lr: 0.000989  loss: 1.9939 (2.0500)  weight_decay: 0.0500 (0.0500)  time: 1.0065  data: 0.0004  max mem: 78493
Epoch: [207]  [100/312]  eta: 0:04:11  lr: 0.000988  min_lr: 0.000988  loss: 2.2062 (2.0572)  weight_decay: 0.0500 (0.0500)  time: 1.0051  data: 0.0004  max mem: 78493
Epoch: [207]  [110/312]  eta: 0:03:56  lr: 0.000987  min_lr: 0.000987  loss: 2.1325 (2.0536)  weight_decay: 0.0500 (0.0500)  time: 1.0049  data: 0.0004  max mem: 78493
Epoch: [207]  [120/312]  eta: 0:03:42  lr: 0.000987  min_lr: 0.000987  loss: 2.0851 (2.0593)  weight_decay: 0.0500 (0.0500)  time: 1.0069  data: 0.0004  max mem: 78493
Epoch: [207]  [130/312]  eta: 0:03:28  lr: 0.000986  min_lr: 0.000986  loss: 2.1965 (2.0633)  weight_decay: 0.0500 (0.0500)  time: 1.0070  data: 0.0004  max mem: 78493
Epoch: [207]  [140/312]  eta: 0:03:15  lr: 0.000986  min_lr: 0.000986  loss: 2.0600 (2.0570)  weight_decay: 0.0500 (0.0500)  time: 1.0056  data: 0.0005  max mem: 78493
Epoch: [207]  [150/312]  eta: 0:03:02  lr: 0.000985  min_lr: 0.000985  loss: 1.9617 (2.0523)  weight_decay: 0.0500 (0.0500)  time: 1.0072  data: 0.0005  max mem: 78493
Epoch: [207]  [160/312]  eta: 0:02:50  lr: 0.000984  min_lr: 0.000984  loss: 2.1391 (2.0702)  weight_decay: 0.0500 (0.0500)  time: 1.0072  data: 0.0005  max mem: 78493
Epoch: [207]  [170/312]  eta: 0:02:38  lr: 0.000984  min_lr: 0.000984  loss: 2.3101 (2.0663)  weight_decay: 0.0500 (0.0500)  time: 1.0065  data: 0.0005  max mem: 78493
Epoch: [207]  [180/312]  eta: 0:02:26  lr: 0.000983  min_lr: 0.000983  loss: 1.9364 (2.0587)  weight_decay: 0.0500 (0.0500)  time: 1.0075  data: 0.0005  max mem: 78493
Epoch: [207]  [190/312]  eta: 0:02:14  lr: 0.000982  min_lr: 0.000982  loss: 1.9097 (2.0567)  weight_decay: 0.0500 (0.0500)  time: 1.0086  data: 0.0004  max mem: 78493
Epoch: [207]  [200/312]  eta: 0:02:02  lr: 0.000982  min_lr: 0.000982  loss: 2.0987 (2.0555)  weight_decay: 0.0500 (0.0500)  time: 1.0093  data: 0.0004  max mem: 78493
Epoch: [207]  [210/312]  eta: 0:01:51  lr: 0.000981  min_lr: 0.000981  loss: 2.1416 (2.0547)  weight_decay: 0.0500 (0.0500)  time: 1.0109  data: 0.0004  max mem: 78493
Epoch: [207]  [220/312]  eta: 0:01:40  lr: 0.000981  min_lr: 0.000981  loss: 1.8863 (2.0469)  weight_decay: 0.0500 (0.0500)  time: 1.0094  data: 0.0004  max mem: 78493
Epoch: [207]  [230/312]  eta: 0:01:29  lr: 0.000980  min_lr: 0.000980  loss: 2.0229 (2.0452)  weight_decay: 0.0500 (0.0500)  time: 1.0069  data: 0.0004  max mem: 78493
Epoch: [207]  [240/312]  eta: 0:01:17  lr: 0.000979  min_lr: 0.000979  loss: 2.0398 (2.0420)  weight_decay: 0.0500 (0.0500)  time: 1.0078  data: 0.0012  max mem: 78493
Epoch: [207]  [250/312]  eta: 0:01:06  lr: 0.000979  min_lr: 0.000979  loss: 2.0381 (2.0397)  weight_decay: 0.0500 (0.0500)  time: 1.0081  data: 0.0012  max mem: 78493
Epoch: [207]  [260/312]  eta: 0:00:56  lr: 0.000978  min_lr: 0.000978  loss: 1.9479 (2.0414)  weight_decay: 0.0500 (0.0500)  time: 1.0067  data: 0.0004  max mem: 78493
Epoch: [207]  [270/312]  eta: 0:00:45  lr: 0.000978  min_lr: 0.000978  loss: 1.9475 (2.0419)  weight_decay: 0.0500 (0.0500)  time: 1.0071  data: 0.0004  max mem: 78493
Epoch: [207]  [280/312]  eta: 0:00:34  lr: 0.000977  min_lr: 0.000977  loss: 2.1958 (2.0473)  weight_decay: 0.0500 (0.0500)  time: 1.0079  data: 0.0010  max mem: 78493
Epoch: [207]  [290/312]  eta: 0:00:23  lr: 0.000976  min_lr: 0.000976  loss: 2.2467 (2.0514)  weight_decay: 0.0500 (0.0500)  time: 1.0042  data: 0.0009  max mem: 78493
Epoch: [207]  [300/312]  eta: 0:00:12  lr: 0.000976  min_lr: 0.000976  loss: 2.2124 (2.0514)  weight_decay: 0.0500 (0.0500)  time: 1.0015  data: 0.0001  max mem: 78493
Epoch: [207]  [310/312]  eta: 0:00:02  lr: 0.000975  min_lr: 0.000975  loss: 2.2524 (2.0546)  weight_decay: 0.0500 (0.0500)  time: 1.0015  data: 0.0001  max mem: 78493
Epoch: [207]  [311/312]  eta: 0:00:01  lr: 0.000975  min_lr: 0.000975  loss: 2.2665 (2.0562)  weight_decay: 0.0500 (0.0500)  time: 1.0015  data: 0.0001  max mem: 78493
Epoch: [207] Total time: 0:05:34 (1.0712 s / it)
Averaged stats: lr: 0.000975  min_lr: 0.000975  loss: 2.2665 (2.0691)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:16  loss: 0.5666 (0.5666)  acc1: 86.0677 (86.0677)  acc5: 96.6146 (96.6146)  time: 8.5526  data: 8.2753  max mem: 78493
Test:  [8/9]  eta: 0:00:01  loss: 0.8215 (0.7768)  acc1: 78.9062 (79.4880)  acc5: 96.2240 (94.8800)  time: 1.1485  data: 0.9196  max mem: 78493
Test: Total time: 0:00:10 (1.1633 s / it)
* Acc@1 79.860 Acc@5 94.898 loss 0.769
Accuracy of the model on the 50000 test images: 79.9%
Max accuracy: 79.86%
Epoch: [208]  [  0/312]  eta: 1:23:02  lr: 0.000975  min_lr: 0.000975  loss: 1.9399 (1.9399)  weight_decay: 0.0500 (0.0500)  time: 15.9692  data: 14.9668  max mem: 78493
Epoch: [208]  [ 10/312]  eta: 0:13:14  lr: 0.000974  min_lr: 0.000974  loss: 2.1921 (2.1544)  weight_decay: 0.0500 (0.0500)  time: 2.6319  data: 1.3642  max mem: 78493
Epoch: [208]  [ 20/312]  eta: 0:09:02  lr: 0.000974  min_lr: 0.000974  loss: 2.1921 (2.0993)  weight_decay: 0.0500 (0.0500)  time: 1.1532  data: 0.0022  max mem: 78493
Epoch: [208]  [ 30/312]  eta: 0:07:27  lr: 0.000973  min_lr: 0.000973  loss: 2.0487 (2.0835)  weight_decay: 0.0500 (0.0500)  time: 1.0094  data: 0.0004  max mem: 78493
Epoch: [208]  [ 40/312]  eta: 0:06:32  lr: 0.000972  min_lr: 0.000972  loss: 2.2018 (2.1193)  weight_decay: 0.0500 (0.0500)  time: 1.0091  data: 0.0004  max mem: 78493
Epoch: [208]  [ 50/312]  eta: 0:05:55  lr: 0.000972  min_lr: 0.000972  loss: 2.2018 (2.0857)  weight_decay: 0.0500 (0.0500)  time: 1.0073  data: 0.0004  max mem: 78493
Epoch: [208]  [ 60/312]  eta: 0:05:27  lr: 0.000971  min_lr: 0.000971  loss: 2.1106 (2.0946)  weight_decay: 0.0500 (0.0500)  time: 1.0089  data: 0.0004  max mem: 78493
Epoch: [208]  [ 70/312]  eta: 0:05:04  lr: 0.000971  min_lr: 0.000971  loss: 2.1106 (2.0786)  weight_decay: 0.0500 (0.0500)  time: 1.0078  data: 0.0004  max mem: 78493
Epoch: [208]  [ 80/312]  eta: 0:04:45  lr: 0.000970  min_lr: 0.000970  loss: 1.9572 (2.0896)  weight_decay: 0.0500 (0.0500)  time: 1.0061  data: 0.0004  max mem: 78493
Epoch: [208]  [ 90/312]  eta: 0:04:27  lr: 0.000969  min_lr: 0.000969  loss: 2.1416 (2.0876)  weight_decay: 0.0500 (0.0500)  time: 1.0069  data: 0.0004  max mem: 78493
Epoch: [208]  [100/312]  eta: 0:04:11  lr: 0.000969  min_lr: 0.000969  loss: 2.1239 (2.0871)  weight_decay: 0.0500 (0.0500)  time: 1.0050  data: 0.0005  max mem: 78493
Epoch: [208]  [110/312]  eta: 0:03:56  lr: 0.000968  min_lr: 0.000968  loss: 2.1200 (2.0841)  weight_decay: 0.0500 (0.0500)  time: 1.0052  data: 0.0004  max mem: 78493
Epoch: [208]  [120/312]  eta: 0:03:41  lr: 0.000968  min_lr: 0.000968  loss: 1.9222 (2.0698)  weight_decay: 0.0500 (0.0500)  time: 1.0089  data: 0.0004  max mem: 78493
Epoch: [208]  [130/312]  eta: 0:03:28  lr: 0.000967  min_lr: 0.000967  loss: 2.1272 (2.0805)  weight_decay: 0.0500 (0.0500)  time: 1.0079  data: 0.0005  max mem: 78493
Epoch: [208]  [140/312]  eta: 0:03:15  lr: 0.000966  min_lr: 0.000966  loss: 2.1779 (2.0723)  weight_decay: 0.0500 (0.0500)  time: 1.0037  data: 0.0005  max mem: 78493
Epoch: [208]  [150/312]  eta: 0:03:02  lr: 0.000966  min_lr: 0.000966  loss: 2.1485 (2.0763)  weight_decay: 0.0500 (0.0500)  time: 1.0052  data: 0.0004  max mem: 78493
Epoch: [208]  [160/312]  eta: 0:02:49  lr: 0.000965  min_lr: 0.000965  loss: 2.1543 (2.0749)  weight_decay: 0.0500 (0.0500)  time: 1.0072  data: 0.0004  max mem: 78493
Epoch: [208]  [170/312]  eta: 0:02:37  lr: 0.000964  min_lr: 0.000964  loss: 2.0002 (2.0787)  weight_decay: 0.0500 (0.0500)  time: 1.0074  data: 0.0004  max mem: 78493
Epoch: [208]  [180/312]  eta: 0:02:25  lr: 0.000964  min_lr: 0.000964  loss: 1.9974 (2.0720)  weight_decay: 0.0500 (0.0500)  time: 1.0069  data: 0.0004  max mem: 78493
Epoch: [208]  [190/312]  eta: 0:02:14  lr: 0.000963  min_lr: 0.000963  loss: 2.1849 (2.0801)  weight_decay: 0.0500 (0.0500)  time: 1.0064  data: 0.0004  max mem: 78493
Epoch: [208]  [200/312]  eta: 0:02:02  lr: 0.000963  min_lr: 0.000963  loss: 2.1668 (2.0772)  weight_decay: 0.0500 (0.0500)  time: 1.0083  data: 0.0004  max mem: 78493
Epoch: [208]  [210/312]  eta: 0:01:51  lr: 0.000962  min_lr: 0.000962  loss: 2.1668 (2.0824)  weight_decay: 0.0500 (0.0500)  time: 1.0093  data: 0.0004  max mem: 78493
Epoch: [208]  [220/312]  eta: 0:01:40  lr: 0.000961  min_lr: 0.000961  loss: 2.2693 (2.0874)  weight_decay: 0.0500 (0.0500)  time: 1.0075  data: 0.0005  max mem: 78493
Epoch: [208]  [230/312]  eta: 0:01:28  lr: 0.000961  min_lr: 0.000961  loss: 2.1854 (2.0796)  weight_decay: 0.0500 (0.0500)  time: 1.0049  data: 0.0004  max mem: 78493
Epoch: [208]  [240/312]  eta: 0:01:17  lr: 0.000960  min_lr: 0.000960  loss: 1.7103 (2.0744)  weight_decay: 0.0500 (0.0500)  time: 1.0041  data: 0.0004  max mem: 78493
Epoch: [208]  [250/312]  eta: 0:01:06  lr: 0.000960  min_lr: 0.000960  loss: 1.9952 (2.0719)  weight_decay: 0.0500 (0.0500)  time: 1.0040  data: 0.0005  max mem: 78493
Epoch: [208]  [260/312]  eta: 0:00:55  lr: 0.000959  min_lr: 0.000959  loss: 2.0468 (2.0726)  weight_decay: 0.0500 (0.0500)  time: 1.0047  data: 0.0004  max mem: 78493
Epoch: [208]  [270/312]  eta: 0:00:45  lr: 0.000958  min_lr: 0.000958  loss: 2.1026 (2.0740)  weight_decay: 0.0500 (0.0500)  time: 1.0049  data: 0.0005  max mem: 78493
Epoch: [208]  [280/312]  eta: 0:00:34  lr: 0.000958  min_lr: 0.000958  loss: 2.1777 (2.0783)  weight_decay: 0.0500 (0.0500)  time: 1.0085  data: 0.0011  max mem: 78493
Epoch: [208]  [290/312]  eta: 0:00:23  lr: 0.000957  min_lr: 0.000957  loss: 2.2664 (2.0843)  weight_decay: 0.0500 (0.0500)  time: 1.0073  data: 0.0009  max mem: 78493
Epoch: [208]  [300/312]  eta: 0:00:12  lr: 0.000956  min_lr: 0.000956  loss: 2.2561 (2.0860)  weight_decay: 0.0500 (0.0500)  time: 1.0019  data: 0.0001  max mem: 78493
Epoch: [208]  [310/312]  eta: 0:00:02  lr: 0.000956  min_lr: 0.000956  loss: 2.2555 (2.0931)  weight_decay: 0.0500 (0.0500)  time: 1.0018  data: 0.0001  max mem: 78493
Epoch: [208]  [311/312]  eta: 0:00:01  lr: 0.000956  min_lr: 0.000956  loss: 2.2375 (2.0933)  weight_decay: 0.0500 (0.0500)  time: 1.0018  data: 0.0001  max mem: 78493
Epoch: [208] Total time: 0:05:33 (1.0698 s / it)
Averaged stats: lr: 0.000956  min_lr: 0.000956  loss: 2.2375 (2.0671)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:14  loss: 0.5581 (0.5581)  acc1: 85.9375 (85.9375)  acc5: 97.2656 (97.2656)  time: 8.3265  data: 8.0500  max mem: 78493
Test:  [8/9]  eta: 0:00:01  loss: 0.8566 (0.7867)  acc1: 80.2083 (79.4080)  acc5: 95.4427 (94.7200)  time: 1.1234  data: 0.8945  max mem: 78493
Test: Total time: 0:00:10 (1.1464 s / it)
* Acc@1 79.776 Acc@5 94.812 loss 0.772
Accuracy of the model on the 50000 test images: 79.8%
Max accuracy: 79.86%
Epoch: [209]  [  0/312]  eta: 1:26:16  lr: 0.000956  min_lr: 0.000956  loss: 2.5349 (2.5349)  weight_decay: 0.0500 (0.0500)  time: 16.5909  data: 15.5586  max mem: 78493
Epoch: [209]  [ 10/312]  eta: 0:13:31  lr: 0.000955  min_lr: 0.000955  loss: 2.0909 (2.0067)  weight_decay: 0.0500 (0.0500)  time: 2.6885  data: 1.4189  max mem: 78493
Epoch: [209]  [ 20/312]  eta: 0:09:11  lr: 0.000955  min_lr: 0.000955  loss: 2.2330 (2.1193)  weight_decay: 0.0500 (0.0500)  time: 1.1543  data: 0.0044  max mem: 78493
Epoch: [209]  [ 30/312]  eta: 0:07:32  lr: 0.000954  min_lr: 0.000954  loss: 2.1993 (2.0708)  weight_decay: 0.0500 (0.0500)  time: 1.0079  data: 0.0029  max mem: 78493
Epoch: [209]  [ 40/312]  eta: 0:06:37  lr: 0.000953  min_lr: 0.000953  loss: 1.9976 (2.0588)  weight_decay: 0.0500 (0.0500)  time: 1.0093  data: 0.0012  max mem: 78493
Epoch: [209]  [ 50/312]  eta: 0:05:59  lr: 0.000953  min_lr: 0.000953  loss: 2.0891 (2.0701)  weight_decay: 0.0500 (0.0500)  time: 1.0099  data: 0.0005  max mem: 78493
Epoch: [209]  [ 60/312]  eta: 0:05:30  lr: 0.000952  min_lr: 0.000952  loss: 2.1231 (2.0977)  weight_decay: 0.0500 (0.0500)  time: 1.0072  data: 0.0005  max mem: 78493
Epoch: [209]  [ 70/312]  eta: 0:05:07  lr: 0.000951  min_lr: 0.000951  loss: 2.1683 (2.1029)  weight_decay: 0.0500 (0.0500)  time: 1.0087  data: 0.0005  max mem: 78493
Epoch: [209]  [ 80/312]  eta: 0:04:46  lr: 0.000951  min_lr: 0.000951  loss: 2.1683 (2.0921)  weight_decay: 0.0500 (0.0500)  time: 1.0087  data: 0.0005  max mem: 78493
Epoch: [209]  [ 90/312]  eta: 0:04:28  lr: 0.000950  min_lr: 0.000950  loss: 2.0798 (2.0885)  weight_decay: 0.0500 (0.0500)  time: 1.0077  data: 0.0005  max mem: 78493
Epoch: [209]  [100/312]  eta: 0:04:12  lr: 0.000950  min_lr: 0.000950  loss: 2.0798 (2.0725)  weight_decay: 0.0500 (0.0500)  time: 1.0091  data: 0.0005  max mem: 78493
Epoch: [209]  [110/312]  eta: 0:03:57  lr: 0.000949  min_lr: 0.000949  loss: 2.0903 (2.0741)  weight_decay: 0.0500 (0.0500)  time: 1.0087  data: 0.0005  max mem: 78493
Epoch: [209]  [120/312]  eta: 0:03:42  lr: 0.000948  min_lr: 0.000948  loss: 2.0974 (2.0647)  weight_decay: 0.0500 (0.0500)  time: 1.0077  data: 0.0005  max mem: 78493
Epoch: [209]  [130/312]  eta: 0:03:29  lr: 0.000948  min_lr: 0.000948  loss: 2.0109 (2.0541)  weight_decay: 0.0500 (0.0500)  time: 1.0069  data: 0.0005  max mem: 78493
Epoch: [209]  [140/312]  eta: 0:03:15  lr: 0.000947  min_lr: 0.000947  loss: 2.2821 (2.0655)  weight_decay: 0.0500 (0.0500)  time: 1.0054  data: 0.0005  max mem: 78493
Epoch: [209]  [150/312]  eta: 0:03:03  lr: 0.000947  min_lr: 0.000947  loss: 2.2950 (2.0629)  weight_decay: 0.0500 (0.0500)  time: 1.0048  data: 0.0004  max mem: 78493
Epoch: [209]  [160/312]  eta: 0:02:50  lr: 0.000946  min_lr: 0.000946  loss: 1.9265 (2.0499)  weight_decay: 0.0500 (0.0500)  time: 1.0059  data: 0.0004  max mem: 78493
Epoch: [209]  [170/312]  eta: 0:02:38  lr: 0.000945  min_lr: 0.000945  loss: 2.1696 (2.0615)  weight_decay: 0.0500 (0.0500)  time: 1.0071  data: 0.0004  max mem: 78493
Epoch: [209]  [180/312]  eta: 0:02:26  lr: 0.000945  min_lr: 0.000945  loss: 2.1990 (2.0611)  weight_decay: 0.0500 (0.0500)  time: 1.0059  data: 0.0004  max mem: 78493
Epoch: [209]  [190/312]  eta: 0:02:14  lr: 0.000944  min_lr: 0.000944  loss: 1.9727 (2.0619)  weight_decay: 0.0500 (0.0500)  time: 1.0053  data: 0.0004  max mem: 78493
Epoch: [209]  [200/312]  eta: 0:02:03  lr: 0.000944  min_lr: 0.000944  loss: 2.1382 (2.0677)  weight_decay: 0.0500 (0.0500)  time: 1.0062  data: 0.0005  max mem: 78493
Epoch: [209]  [210/312]  eta: 0:01:51  lr: 0.000943  min_lr: 0.000943  loss: 2.2686 (2.0771)  weight_decay: 0.0500 (0.0500)  time: 1.0063  data: 0.0005  max mem: 78493
Epoch: [209]  [220/312]  eta: 0:01:40  lr: 0.000942  min_lr: 0.000942  loss: 2.2713 (2.0806)  weight_decay: 0.0500 (0.0500)  time: 1.0067  data: 0.0004  max mem: 78493
Epoch: [209]  [230/312]  eta: 0:01:29  lr: 0.000942  min_lr: 0.000942  loss: 2.2410 (2.0856)  weight_decay: 0.0500 (0.0500)  time: 1.0069  data: 0.0004  max mem: 78493
Epoch: [209]  [240/312]  eta: 0:01:18  lr: 0.000941  min_lr: 0.000941  loss: 2.0869 (2.0854)  weight_decay: 0.0500 (0.0500)  time: 1.0053  data: 0.0004  max mem: 78493
Epoch: [209]  [250/312]  eta: 0:01:07  lr: 0.000940  min_lr: 0.000940  loss: 2.2145 (2.0901)  weight_decay: 0.0500 (0.0500)  time: 1.0050  data: 0.0018  max mem: 78493
Epoch: [209]  [260/312]  eta: 0:00:56  lr: 0.000940  min_lr: 0.000940  loss: 2.2590 (2.0940)  weight_decay: 0.0500 (0.0500)  time: 1.0062  data: 0.0018  max mem: 78493
Epoch: [209]  [270/312]  eta: 0:00:45  lr: 0.000939  min_lr: 0.000939  loss: 2.1346 (2.0898)  weight_decay: 0.0500 (0.0500)  time: 1.0076  data: 0.0004  max mem: 78493
Epoch: [209]  [280/312]  eta: 0:00:34  lr: 0.000939  min_lr: 0.000939  loss: 2.2229 (2.0939)  weight_decay: 0.0500 (0.0500)  time: 1.0086  data: 0.0010  max mem: 78493
Epoch: [209]  [290/312]  eta: 0:00:23  lr: 0.000938  min_lr: 0.000938  loss: 2.2279 (2.0931)  weight_decay: 0.0500 (0.0500)  time: 1.0056  data: 0.0009  max mem: 78493
Epoch: [209]  [300/312]  eta: 0:00:12  lr: 0.000937  min_lr: 0.000937  loss: 2.2167 (2.0972)  weight_decay: 0.0500 (0.0500)  time: 1.0021  data: 0.0001  max mem: 78493
Epoch: [209]  [310/312]  eta: 0:00:02  lr: 0.000937  min_lr: 0.000937  loss: 2.2167 (2.0981)  weight_decay: 0.0500 (0.0500)  time: 1.0018  data: 0.0001  max mem: 78493
Epoch: [209]  [311/312]  eta: 0:00:01  lr: 0.000937  min_lr: 0.000937  loss: 2.1845 (2.0968)  weight_decay: 0.0500 (0.0500)  time: 1.0017  data: 0.0001  max mem: 78493
Epoch: [209] Total time: 0:05:34 (1.0717 s / it)
Averaged stats: lr: 0.000937  min_lr: 0.000937  loss: 2.1845 (2.0676)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:12  loss: 0.5900 (0.5900)  acc1: 84.7656 (84.7656)  acc5: 96.8750 (96.8750)  time: 8.0238  data: 7.7541  max mem: 78493
Test:  [8/9]  eta: 0:00:01  loss: 0.8025 (0.7720)  acc1: 81.2500 (79.5520)  acc5: 95.7031 (95.1840)  time: 1.0901  data: 0.8617  max mem: 78493
Test: Total time: 0:00:10 (1.1260 s / it)
* Acc@1 79.840 Acc@5 94.982 loss 0.773
Accuracy of the model on the 50000 test images: 79.8%
Max accuracy: 79.86%
Epoch: [210]  [  0/312]  eta: 1:17:38  lr: 0.000937  min_lr: 0.000937  loss: 2.7045 (2.7045)  weight_decay: 0.0500 (0.0500)  time: 14.9317  data: 12.3615  max mem: 78493
Epoch: [210]  [ 10/312]  eta: 0:13:24  lr: 0.000936  min_lr: 0.000936  loss: 2.2072 (2.1274)  weight_decay: 0.0500 (0.0500)  time: 2.6643  data: 1.2652  max mem: 78493
Epoch: [210]  [ 20/312]  eta: 0:09:09  lr: 0.000935  min_lr: 0.000935  loss: 2.2086 (2.2045)  weight_decay: 0.0500 (0.0500)  time: 1.2277  data: 0.0793  max mem: 78493
Epoch: [210]  [ 30/312]  eta: 0:07:30  lr: 0.000935  min_lr: 0.000935  loss: 2.2158 (2.1447)  weight_decay: 0.0500 (0.0500)  time: 1.0121  data: 0.0017  max mem: 78493
Epoch: [210]  [ 40/312]  eta: 0:06:35  lr: 0.000934  min_lr: 0.000934  loss: 2.0695 (2.1408)  weight_decay: 0.0500 (0.0500)  time: 1.0052  data: 0.0004  max mem: 78493
Epoch: [210]  [ 50/312]  eta: 0:05:57  lr: 0.000934  min_lr: 0.000934  loss: 2.1631 (2.1350)  weight_decay: 0.0500 (0.0500)  time: 1.0053  data: 0.0004  max mem: 78493
Epoch: [210]  [ 60/312]  eta: 0:05:29  lr: 0.000933  min_lr: 0.000933  loss: 2.1729 (2.1182)  weight_decay: 0.0500 (0.0500)  time: 1.0063  data: 0.0004  max mem: 78493
Epoch: [210]  [ 70/312]  eta: 0:05:05  lr: 0.000932  min_lr: 0.000932  loss: 1.9760 (2.0974)  weight_decay: 0.0500 (0.0500)  time: 1.0050  data: 0.0004  max mem: 78493
Epoch: [210]  [ 80/312]  eta: 0:04:45  lr: 0.000932  min_lr: 0.000932  loss: 1.9534 (2.0754)  weight_decay: 0.0500 (0.0500)  time: 1.0046  data: 0.0004  max mem: 78493
Epoch: [210]  [ 90/312]  eta: 0:04:28  lr: 0.000931  min_lr: 0.000931  loss: 2.1734 (2.0876)  weight_decay: 0.0500 (0.0500)  time: 1.0071  data: 0.0004  max mem: 78493
Epoch: [210]  [100/312]  eta: 0:04:11  lr: 0.000931  min_lr: 0.000931  loss: 2.1053 (2.0714)  weight_decay: 0.0500 (0.0500)  time: 1.0088  data: 0.0004  max mem: 78493
Epoch: [210]  [110/312]  eta: 0:03:56  lr: 0.000930  min_lr: 0.000930  loss: 1.9837 (2.0604)  weight_decay: 0.0500 (0.0500)  time: 1.0089  data: 0.0004  max mem: 78493
Epoch: [210]  [120/312]  eta: 0:03:42  lr: 0.000929  min_lr: 0.000929  loss: 2.0067 (2.0589)  weight_decay: 0.0500 (0.0500)  time: 1.0111  data: 0.0004  max mem: 78493
Epoch: [210]  [130/312]  eta: 0:03:28  lr: 0.000929  min_lr: 0.000929  loss: 2.0288 (2.0495)  weight_decay: 0.0500 (0.0500)  time: 1.0097  data: 0.0004  max mem: 78493
Epoch: [210]  [140/312]  eta: 0:03:15  lr: 0.000928  min_lr: 0.000928  loss: 1.9658 (2.0398)  weight_decay: 0.0500 (0.0500)  time: 1.0054  data: 0.0005  max mem: 78493
Epoch: [210]  [150/312]  eta: 0:03:02  lr: 0.000928  min_lr: 0.000928  loss: 2.2016 (2.0500)  weight_decay: 0.0500 (0.0500)  time: 1.0065  data: 0.0005  max mem: 78493
Epoch: [210]  [160/312]  eta: 0:02:50  lr: 0.000927  min_lr: 0.000927  loss: 2.1933 (2.0521)  weight_decay: 0.0500 (0.0500)  time: 1.0081  data: 0.0004  max mem: 78493
Epoch: [210]  [170/312]  eta: 0:02:38  lr: 0.000926  min_lr: 0.000926  loss: 2.0192 (2.0527)  weight_decay: 0.0500 (0.0500)  time: 1.0057  data: 0.0004  max mem: 78493
Epoch: [210]  [180/312]  eta: 0:02:26  lr: 0.000926  min_lr: 0.000926  loss: 2.0292 (2.0457)  weight_decay: 0.0500 (0.0500)  time: 1.0041  data: 0.0004  max mem: 78493
Epoch: [210]  [190/312]  eta: 0:02:14  lr: 0.000925  min_lr: 0.000925  loss: 2.0292 (2.0436)  weight_decay: 0.0500 (0.0500)  time: 1.0039  data: 0.0005  max mem: 78493
Epoch: [210]  [200/312]  eta: 0:02:02  lr: 0.000925  min_lr: 0.000925  loss: 2.1457 (2.0454)  weight_decay: 0.0500 (0.0500)  time: 1.0041  data: 0.0004  max mem: 78493
Epoch: [210]  [210/312]  eta: 0:01:51  lr: 0.000924  min_lr: 0.000924  loss: 2.1457 (2.0461)  weight_decay: 0.0500 (0.0500)  time: 1.0050  data: 0.0004  max mem: 78493
Epoch: [210]  [220/312]  eta: 0:01:40  lr: 0.000923  min_lr: 0.000923  loss: 1.9171 (2.0376)  weight_decay: 0.0500 (0.0500)  time: 1.0055  data: 0.0004  max mem: 78493
Epoch: [210]  [230/312]  eta: 0:01:29  lr: 0.000923  min_lr: 0.000923  loss: 1.9291 (2.0391)  weight_decay: 0.0500 (0.0500)  time: 1.0063  data: 0.0004  max mem: 78493
Epoch: [210]  [240/312]  eta: 0:01:17  lr: 0.000922  min_lr: 0.000922  loss: 2.2048 (2.0481)  weight_decay: 0.0500 (0.0500)  time: 1.0070  data: 0.0004  max mem: 78493
Epoch: [210]  [250/312]  eta: 0:01:06  lr: 0.000922  min_lr: 0.000922  loss: 2.3018 (2.0545)  weight_decay: 0.0500 (0.0500)  time: 1.0053  data: 0.0004  max mem: 78493
Epoch: [210]  [260/312]  eta: 0:00:55  lr: 0.000921  min_lr: 0.000921  loss: 2.0837 (2.0418)  weight_decay: 0.0500 (0.0500)  time: 1.0040  data: 0.0005  max mem: 78493
Epoch: [210]  [270/312]  eta: 0:00:45  lr: 0.000920  min_lr: 0.000920  loss: 2.1551 (2.0503)  weight_decay: 0.0500 (0.0500)  time: 1.0052  data: 0.0005  max mem: 78493
Epoch: [210]  [280/312]  eta: 0:00:34  lr: 0.000920  min_lr: 0.000920  loss: 2.2029 (2.0532)  weight_decay: 0.0500 (0.0500)  time: 1.0074  data: 0.0011  max mem: 78493
Epoch: [210]  [290/312]  eta: 0:00:23  lr: 0.000919  min_lr: 0.000919  loss: 2.1458 (2.0522)  weight_decay: 0.0500 (0.0500)  time: 1.0053  data: 0.0009  max mem: 78493
Epoch: [210]  [300/312]  eta: 0:00:12  lr: 0.000918  min_lr: 0.000918  loss: 1.9194 (2.0483)  weight_decay: 0.0500 (0.0500)  time: 1.0012  data: 0.0001  max mem: 78493
Epoch: [210]  [310/312]  eta: 0:00:02  lr: 0.000918  min_lr: 0.000918  loss: 1.7265 (2.0416)  weight_decay: 0.0500 (0.0500)  time: 1.0013  data: 0.0001  max mem: 78493
Epoch: [210]  [311/312]  eta: 0:00:01  lr: 0.000918  min_lr: 0.000918  loss: 1.7211 (2.0395)  weight_decay: 0.0500 (0.0500)  time: 1.0014  data: 0.0001  max mem: 78493
Epoch: [210] Total time: 0:05:33 (1.0701 s / it)
Averaged stats: lr: 0.000918  min_lr: 0.000918  loss: 1.7211 (2.0543)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:15  loss: 0.5359 (0.5359)  acc1: 85.6771 (85.6771)  acc5: 97.2656 (97.2656)  time: 8.3376  data: 8.0699  max mem: 78493
Test:  [8/9]  eta: 0:00:01  loss: 0.8111 (0.7552)  acc1: 79.9479 (79.8400)  acc5: 95.8333 (95.2320)  time: 1.1254  data: 0.8968  max mem: 78493
Test: Total time: 0:00:10 (1.1419 s / it)
* Acc@1 80.210 Acc@5 95.080 loss 0.751
Accuracy of the model on the 50000 test images: 80.2%
Max accuracy: 80.21%
Epoch: [211]  [  0/312]  eta: 1:25:40  lr: 0.000918  min_lr: 0.000918  loss: 1.6776 (1.6776)  weight_decay: 0.0500 (0.0500)  time: 16.4769  data: 15.4702  max mem: 78493
Epoch: [211]  [ 10/312]  eta: 0:12:45  lr: 0.000917  min_lr: 0.000917  loss: 2.0337 (1.9860)  weight_decay: 0.0500 (0.0500)  time: 2.5358  data: 1.4120  max mem: 78493
Epoch: [211]  [ 20/312]  eta: 0:08:50  lr: 0.000917  min_lr: 0.000917  loss: 2.1372 (2.0795)  weight_decay: 0.0500 (0.0500)  time: 1.0833  data: 0.0034  max mem: 78493
Epoch: [211]  [ 30/312]  eta: 0:07:18  lr: 0.000916  min_lr: 0.000916  loss: 2.1733 (2.0824)  weight_decay: 0.0500 (0.0500)  time: 1.0172  data: 0.0005  max mem: 78493
Epoch: [211]  [ 40/312]  eta: 0:06:26  lr: 0.000915  min_lr: 0.000915  loss: 2.1105 (2.0862)  weight_decay: 0.0500 (0.0500)  time: 1.0085  data: 0.0012  max mem: 78493
Epoch: [211]  [ 50/312]  eta: 0:05:51  lr: 0.000915  min_lr: 0.000915  loss: 2.1807 (2.0992)  weight_decay: 0.0500 (0.0500)  time: 1.0060  data: 0.0012  max mem: 78493
Epoch: [211]  [ 60/312]  eta: 0:05:23  lr: 0.000914  min_lr: 0.000914  loss: 2.1028 (2.0810)  weight_decay: 0.0500 (0.0500)  time: 1.0057  data: 0.0004  max mem: 78493
Epoch: [211]  [ 70/312]  eta: 0:05:01  lr: 0.000914  min_lr: 0.000914  loss: 1.9768 (2.0784)  weight_decay: 0.0500 (0.0500)  time: 1.0072  data: 0.0004  max mem: 78493
Epoch: [211]  [ 80/312]  eta: 0:04:42  lr: 0.000913  min_lr: 0.000913  loss: 2.1590 (2.0970)  weight_decay: 0.0500 (0.0500)  time: 1.0072  data: 0.0004  max mem: 78493
Epoch: [211]  [ 90/312]  eta: 0:04:25  lr: 0.000912  min_lr: 0.000912  loss: 2.2042 (2.1003)  weight_decay: 0.0500 (0.0500)  time: 1.0064  data: 0.0004  max mem: 78493
Epoch: [211]  [100/312]  eta: 0:04:09  lr: 0.000912  min_lr: 0.000912  loss: 2.1271 (2.0916)  weight_decay: 0.0500 (0.0500)  time: 1.0059  data: 0.0004  max mem: 78493
Epoch: [211]  [110/312]  eta: 0:03:54  lr: 0.000911  min_lr: 0.000911  loss: 2.1636 (2.1027)  weight_decay: 0.0500 (0.0500)  time: 1.0061  data: 0.0005  max mem: 78493
Epoch: [211]  [120/312]  eta: 0:03:40  lr: 0.000911  min_lr: 0.000911  loss: 2.1888 (2.0917)  weight_decay: 0.0500 (0.0500)  time: 1.0065  data: 0.0004  max mem: 78493
Epoch: [211]  [130/312]  eta: 0:03:26  lr: 0.000910  min_lr: 0.000910  loss: 1.9815 (2.0806)  weight_decay: 0.0500 (0.0500)  time: 1.0066  data: 0.0004  max mem: 78493
Epoch: [211]  [140/312]  eta: 0:03:13  lr: 0.000909  min_lr: 0.000909  loss: 1.9668 (2.0727)  weight_decay: 0.0500 (0.0500)  time: 1.0070  data: 0.0004  max mem: 78493
Epoch: [211]  [150/312]  eta: 0:03:01  lr: 0.000909  min_lr: 0.000909  loss: 1.9057 (2.0585)  weight_decay: 0.0500 (0.0500)  time: 1.0073  data: 0.0005  max mem: 78493
Epoch: [211]  [160/312]  eta: 0:02:49  lr: 0.000908  min_lr: 0.000908  loss: 2.1437 (2.0708)  weight_decay: 0.0500 (0.0500)  time: 1.0071  data: 0.0005  max mem: 78493
Epoch: [211]  [170/312]  eta: 0:02:37  lr: 0.000908  min_lr: 0.000908  loss: 2.1709 (2.0685)  weight_decay: 0.0500 (0.0500)  time: 1.0061  data: 0.0004  max mem: 78493
Epoch: [211]  [180/312]  eta: 0:02:25  lr: 0.000907  min_lr: 0.000907  loss: 2.0843 (2.0700)  weight_decay: 0.0500 (0.0500)  time: 1.0049  data: 0.0004  max mem: 78493
Epoch: [211]  [190/312]  eta: 0:02:13  lr: 0.000906  min_lr: 0.000906  loss: 2.0843 (2.0653)  weight_decay: 0.0500 (0.0500)  time: 1.0041  data: 0.0004  max mem: 78493
Epoch: [211]  [200/312]  eta: 0:02:02  lr: 0.000906  min_lr: 0.000906  loss: 2.1732 (2.0671)  weight_decay: 0.0500 (0.0500)  time: 1.0054  data: 0.0005  max mem: 78493
Epoch: [211]  [210/312]  eta: 0:01:50  lr: 0.000905  min_lr: 0.000905  loss: 2.2433 (2.0689)  weight_decay: 0.0500 (0.0500)  time: 1.0059  data: 0.0004  max mem: 78493
Epoch: [211]  [220/312]  eta: 0:01:39  lr: 0.000905  min_lr: 0.000905  loss: 2.2236 (2.0719)  weight_decay: 0.0500 (0.0500)  time: 1.0061  data: 0.0004  max mem: 78493
Epoch: [211]  [230/312]  eta: 0:01:28  lr: 0.000904  min_lr: 0.000904  loss: 2.1862 (2.0677)  weight_decay: 0.0500 (0.0500)  time: 1.0063  data: 0.0004  max mem: 78493
Epoch: [211]  [240/312]  eta: 0:01:17  lr: 0.000903  min_lr: 0.000903  loss: 2.0622 (2.0675)  weight_decay: 0.0500 (0.0500)  time: 1.0057  data: 0.0004  max mem: 78493
Epoch: [211]  [250/312]  eta: 0:01:06  lr: 0.000903  min_lr: 0.000903  loss: 2.1752 (2.0764)  weight_decay: 0.0500 (0.0500)  time: 1.0060  data: 0.0012  max mem: 78493
Epoch: [211]  [260/312]  eta: 0:00:55  lr: 0.000902  min_lr: 0.000902  loss: 2.1752 (2.0766)  weight_decay: 0.0500 (0.0500)  time: 1.0066  data: 0.0012  max mem: 78493
Epoch: [211]  [270/312]  eta: 0:00:44  lr: 0.000902  min_lr: 0.000902  loss: 2.1287 (2.0780)  weight_decay: 0.0500 (0.0500)  time: 1.0066  data: 0.0004  max mem: 78493
Epoch: [211]  [280/312]  eta: 0:00:34  lr: 0.000901  min_lr: 0.000901  loss: 2.1928 (2.0827)  weight_decay: 0.0500 (0.0500)  time: 1.0056  data: 0.0010  max mem: 78493
Epoch: [211]  [290/312]  eta: 0:00:23  lr: 0.000900  min_lr: 0.000900  loss: 2.0624 (2.0759)  weight_decay: 0.0500 (0.0500)  time: 1.0037  data: 0.0009  max mem: 78493
Epoch: [211]  [300/312]  eta: 0:00:12  lr: 0.000900  min_lr: 0.000900  loss: 2.0025 (2.0779)  weight_decay: 0.0500 (0.0500)  time: 1.0019  data: 0.0001  max mem: 78493
Epoch: [211]  [310/312]  eta: 0:00:02  lr: 0.000899  min_lr: 0.000899  loss: 2.1224 (2.0776)  weight_decay: 0.0500 (0.0500)  time: 1.0019  data: 0.0001  max mem: 78493
Epoch: [211]  [311/312]  eta: 0:00:01  lr: 0.000899  min_lr: 0.000899  loss: 2.1224 (2.0783)  weight_decay: 0.0500 (0.0500)  time: 1.0018  data: 0.0001  max mem: 78493
Epoch: [211] Total time: 0:05:32 (1.0663 s / it)
Averaged stats: lr: 0.000899  min_lr: 0.000899  loss: 2.1224 (2.0581)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:11  loss: 0.5838 (0.5838)  acc1: 85.2865 (85.2865)  acc5: 96.6146 (96.6146)  time: 7.9572  data: 7.6801  max mem: 78493
Test:  [8/9]  eta: 0:00:01  loss: 0.8555 (0.7834)  acc1: 78.2552 (78.9280)  acc5: 95.8333 (95.0240)  time: 1.0824  data: 0.8534  max mem: 78493
Test: Total time: 0:00:09 (1.0926 s / it)
* Acc@1 79.840 Acc@5 95.062 loss 0.763
Accuracy of the model on the 50000 test images: 79.8%
Max accuracy: 80.21%
Epoch: [212]  [  0/312]  eta: 1:27:33  lr: 0.000899  min_lr: 0.000899  loss: 2.3189 (2.3189)  weight_decay: 0.0500 (0.0500)  time: 16.8379  data: 13.7066  max mem: 78493
Epoch: [212]  [ 10/312]  eta: 0:13:20  lr: 0.000898  min_lr: 0.000898  loss: 2.0816 (2.0704)  weight_decay: 0.0500 (0.0500)  time: 2.6491  data: 1.3270  max mem: 78493
Epoch: [212]  [ 20/312]  eta: 0:09:05  lr: 0.000898  min_lr: 0.000898  loss: 2.0816 (2.1083)  weight_decay: 0.0500 (0.0500)  time: 1.1208  data: 0.0448  max mem: 78493
Epoch: [212]  [ 30/312]  eta: 0:07:28  lr: 0.000897  min_lr: 0.000897  loss: 2.1566 (2.0972)  weight_decay: 0.0500 (0.0500)  time: 1.0101  data: 0.0005  max mem: 78493
Epoch: [212]  [ 40/312]  eta: 0:06:34  lr: 0.000897  min_lr: 0.000897  loss: 2.1489 (2.0629)  weight_decay: 0.0500 (0.0500)  time: 1.0111  data: 0.0004  max mem: 78493
Epoch: [212]  [ 50/312]  eta: 0:05:57  lr: 0.000896  min_lr: 0.000896  loss: 2.1400 (2.0692)  weight_decay: 0.0500 (0.0500)  time: 1.0090  data: 0.0004  max mem: 78493
Epoch: [212]  [ 60/312]  eta: 0:05:28  lr: 0.000895  min_lr: 0.000895  loss: 2.1670 (2.0680)  weight_decay: 0.0500 (0.0500)  time: 1.0064  data: 0.0004  max mem: 78493
Epoch: [212]  [ 70/312]  eta: 0:05:05  lr: 0.000895  min_lr: 0.000895  loss: 2.1670 (2.0684)  weight_decay: 0.0500 (0.0500)  time: 1.0107  data: 0.0004  max mem: 78493
Epoch: [212]  [ 80/312]  eta: 0:04:45  lr: 0.000894  min_lr: 0.000894  loss: 2.1172 (2.0518)  weight_decay: 0.0500 (0.0500)  time: 1.0102  data: 0.0004  max mem: 78493
Epoch: [212]  [ 90/312]  eta: 0:04:28  lr: 0.000894  min_lr: 0.000894  loss: 2.1275 (2.0723)  weight_decay: 0.0500 (0.0500)  time: 1.0071  data: 0.0004  max mem: 78493
Epoch: [212]  [100/312]  eta: 0:04:11  lr: 0.000893  min_lr: 0.000893  loss: 2.2681 (2.0834)  weight_decay: 0.0500 (0.0500)  time: 1.0071  data: 0.0004  max mem: 78493
Epoch: [212]  [110/312]  eta: 0:03:56  lr: 0.000892  min_lr: 0.000892  loss: 2.1399 (2.0740)  weight_decay: 0.0500 (0.0500)  time: 1.0088  data: 0.0004  max mem: 78493
Epoch: [212]  [120/312]  eta: 0:03:42  lr: 0.000892  min_lr: 0.000892  loss: 2.0405 (2.0635)  weight_decay: 0.0500 (0.0500)  time: 1.0081  data: 0.0005  max mem: 78493
Epoch: [212]  [130/312]  eta: 0:03:28  lr: 0.000891  min_lr: 0.000891  loss: 2.1746 (2.0603)  weight_decay: 0.0500 (0.0500)  time: 1.0071  data: 0.0013  max mem: 78493
Epoch: [212]  [140/312]  eta: 0:03:15  lr: 0.000891  min_lr: 0.000891  loss: 1.9099 (2.0567)  weight_decay: 0.0500 (0.0500)  time: 1.0095  data: 0.0013  max mem: 78493
Epoch: [212]  [150/312]  eta: 0:03:02  lr: 0.000890  min_lr: 0.000890  loss: 1.9099 (2.0517)  weight_decay: 0.0500 (0.0500)  time: 1.0100  data: 0.0004  max mem: 78493
Epoch: [212]  [160/312]  eta: 0:02:50  lr: 0.000889  min_lr: 0.000889  loss: 2.1709 (2.0594)  weight_decay: 0.0500 (0.0500)  time: 1.0079  data: 0.0004  max mem: 78493
Epoch: [212]  [170/312]  eta: 0:02:38  lr: 0.000889  min_lr: 0.000889  loss: 2.0393 (2.0405)  weight_decay: 0.0500 (0.0500)  time: 1.0065  data: 0.0004  max mem: 78493
Epoch: [212]  [180/312]  eta: 0:02:26  lr: 0.000888  min_lr: 0.000888  loss: 1.8108 (2.0354)  weight_decay: 0.0500 (0.0500)  time: 1.0097  data: 0.0004  max mem: 78493
Epoch: [212]  [190/312]  eta: 0:02:14  lr: 0.000888  min_lr: 0.000888  loss: 1.9568 (2.0351)  weight_decay: 0.0500 (0.0500)  time: 1.0102  data: 0.0004  max mem: 78493
Epoch: [212]  [200/312]  eta: 0:02:03  lr: 0.000887  min_lr: 0.000887  loss: 2.1381 (2.0397)  weight_decay: 0.0500 (0.0500)  time: 1.0080  data: 0.0004  max mem: 78493
Epoch: [212]  [210/312]  eta: 0:01:51  lr: 0.000886  min_lr: 0.000886  loss: 2.1548 (2.0434)  weight_decay: 0.0500 (0.0500)  time: 1.0062  data: 0.0004  max mem: 78493
Epoch: [212]  [220/312]  eta: 0:01:40  lr: 0.000886  min_lr: 0.000886  loss: 2.2258 (2.0527)  weight_decay: 0.0500 (0.0500)  time: 1.0042  data: 0.0004  max mem: 78493
Epoch: [212]  [230/312]  eta: 0:01:29  lr: 0.000885  min_lr: 0.000885  loss: 2.2258 (2.0561)  weight_decay: 0.0500 (0.0500)  time: 1.0049  data: 0.0004  max mem: 78493
Epoch: [212]  [240/312]  eta: 0:01:17  lr: 0.000885  min_lr: 0.000885  loss: 2.1375 (2.0518)  weight_decay: 0.0500 (0.0500)  time: 1.0053  data: 0.0004  max mem: 78493
Epoch: [212]  [250/312]  eta: 0:01:06  lr: 0.000884  min_lr: 0.000884  loss: 2.1677 (2.0570)  weight_decay: 0.0500 (0.0500)  time: 1.0053  data: 0.0004  max mem: 78493
Epoch: [212]  [260/312]  eta: 0:00:56  lr: 0.000883  min_lr: 0.000883  loss: 2.1419 (2.0568)  weight_decay: 0.0500 (0.0500)  time: 1.0053  data: 0.0004  max mem: 78493
Epoch: [212]  [270/312]  eta: 0:00:45  lr: 0.000883  min_lr: 0.000883  loss: 2.1419 (2.0595)  weight_decay: 0.0500 (0.0500)  time: 1.0060  data: 0.0004  max mem: 78493
Epoch: [212]  [280/312]  eta: 0:00:34  lr: 0.000882  min_lr: 0.000882  loss: 2.1718 (2.0535)  weight_decay: 0.0500 (0.0500)  time: 1.0070  data: 0.0010  max mem: 78493
Epoch: [212]  [290/312]  eta: 0:00:23  lr: 0.000882  min_lr: 0.000882  loss: 2.0829 (2.0592)  weight_decay: 0.0500 (0.0500)  time: 1.0040  data: 0.0009  max mem: 78493
Epoch: [212]  [300/312]  eta: 0:00:12  lr: 0.000881  min_lr: 0.000881  loss: 2.1916 (2.0580)  weight_decay: 0.0500 (0.0500)  time: 1.0011  data: 0.0001  max mem: 78493
Epoch: [212]  [310/312]  eta: 0:00:02  lr: 0.000880  min_lr: 0.000880  loss: 2.0109 (2.0513)  weight_decay: 0.0500 (0.0500)  time: 1.0014  data: 0.0001  max mem: 78493
Epoch: [212]  [311/312]  eta: 0:00:01  lr: 0.000880  min_lr: 0.000880  loss: 2.0109 (2.0522)  weight_decay: 0.0500 (0.0500)  time: 1.0014  data: 0.0001  max mem: 78493
Epoch: [212] Total time: 0:05:34 (1.0706 s / it)
Averaged stats: lr: 0.000880  min_lr: 0.000880  loss: 2.0109 (2.0396)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:13  loss: 0.5575 (0.5575)  acc1: 85.4167 (85.4167)  acc5: 97.3958 (97.3958)  time: 8.1394  data: 7.8781  max mem: 78493
Test:  [8/9]  eta: 0:00:01  loss: 0.8674 (0.7872)  acc1: 79.5573 (79.6320)  acc5: 95.8333 (95.0880)  time: 1.1081  data: 0.8754  max mem: 78493
Test: Total time: 0:00:10 (1.1502 s / it)
* Acc@1 79.920 Acc@5 95.076 loss 0.767
Accuracy of the model on the 50000 test images: 79.9%
Max accuracy: 80.21%
Epoch: [213]  [  0/312]  eta: 1:22:51  lr: 0.000880  min_lr: 0.000880  loss: 2.6280 (2.6280)  weight_decay: 0.0500 (0.0500)  time: 15.9329  data: 13.8625  max mem: 78493
Epoch: [213]  [ 10/312]  eta: 0:12:49  lr: 0.000880  min_lr: 0.000880  loss: 2.1915 (2.0622)  weight_decay: 0.0500 (0.0500)  time: 2.5481  data: 1.2893  max mem: 78493
Epoch: [213]  [ 20/312]  eta: 0:08:55  lr: 0.000879  min_lr: 0.000879  loss: 1.9499 (1.9775)  weight_decay: 0.0500 (0.0500)  time: 1.1285  data: 0.0190  max mem: 78493
Epoch: [213]  [ 30/312]  eta: 0:07:22  lr: 0.000879  min_lr: 0.000879  loss: 1.9774 (2.0059)  weight_decay: 0.0500 (0.0500)  time: 1.0289  data: 0.0032  max mem: 78493
Epoch: [213]  [ 40/312]  eta: 0:06:29  lr: 0.000878  min_lr: 0.000878  loss: 2.0132 (1.9707)  weight_decay: 0.0500 (0.0500)  time: 1.0088  data: 0.0004  max mem: 78493
Epoch: [213]  [ 50/312]  eta: 0:05:53  lr: 0.000877  min_lr: 0.000877  loss: 2.0132 (2.0000)  weight_decay: 0.0500 (0.0500)  time: 1.0064  data: 0.0004  max mem: 78493
Epoch: [213]  [ 60/312]  eta: 0:05:25  lr: 0.000877  min_lr: 0.000877  loss: 2.1552 (2.0180)  weight_decay: 0.0500 (0.0500)  time: 1.0054  data: 0.0004  max mem: 78493
Epoch: [213]  [ 70/312]  eta: 0:05:02  lr: 0.000876  min_lr: 0.000876  loss: 2.1788 (2.0396)  weight_decay: 0.0500 (0.0500)  time: 1.0053  data: 0.0004  max mem: 78493
Epoch: [213]  [ 80/312]  eta: 0:04:43  lr: 0.000876  min_lr: 0.000876  loss: 2.1884 (2.0346)  weight_decay: 0.0500 (0.0500)  time: 1.0065  data: 0.0004  max mem: 78493
Epoch: [213]  [ 90/312]  eta: 0:04:25  lr: 0.000875  min_lr: 0.000875  loss: 1.9609 (2.0367)  weight_decay: 0.0500 (0.0500)  time: 1.0068  data: 0.0004  max mem: 78493
Epoch: [213]  [100/312]  eta: 0:04:09  lr: 0.000874  min_lr: 0.000874  loss: 2.0020 (2.0394)  weight_decay: 0.0500 (0.0500)  time: 1.0058  data: 0.0004  max mem: 78493
Epoch: [213]  [110/312]  eta: 0:03:54  lr: 0.000874  min_lr: 0.000874  loss: 2.1375 (2.0431)  weight_decay: 0.0500 (0.0500)  time: 1.0047  data: 0.0005  max mem: 78493
Epoch: [213]  [120/312]  eta: 0:03:40  lr: 0.000873  min_lr: 0.000873  loss: 2.1007 (2.0471)  weight_decay: 0.0500 (0.0500)  time: 1.0075  data: 0.0005  max mem: 78493
Epoch: [213]  [130/312]  eta: 0:03:27  lr: 0.000873  min_lr: 0.000873  loss: 2.1608 (2.0551)  weight_decay: 0.0500 (0.0500)  time: 1.0079  data: 0.0005  max mem: 78493
Epoch: [213]  [140/312]  eta: 0:03:14  lr: 0.000872  min_lr: 0.000872  loss: 2.0878 (2.0412)  weight_decay: 0.0500 (0.0500)  time: 1.0066  data: 0.0004  max mem: 78493
Epoch: [213]  [150/312]  eta: 0:03:01  lr: 0.000871  min_lr: 0.000871  loss: 1.8492 (2.0369)  weight_decay: 0.0500 (0.0500)  time: 1.0080  data: 0.0012  max mem: 78493
Epoch: [213]  [160/312]  eta: 0:02:49  lr: 0.000871  min_lr: 0.000871  loss: 2.0768 (2.0391)  weight_decay: 0.0500 (0.0500)  time: 1.0062  data: 0.0012  max mem: 78493
Epoch: [213]  [170/312]  eta: 0:02:37  lr: 0.000870  min_lr: 0.000870  loss: 1.8905 (2.0281)  weight_decay: 0.0500 (0.0500)  time: 1.0055  data: 0.0005  max mem: 78493
Epoch: [213]  [180/312]  eta: 0:02:25  lr: 0.000870  min_lr: 0.000870  loss: 1.9834 (2.0267)  weight_decay: 0.0500 (0.0500)  time: 1.0066  data: 0.0005  max mem: 78493
Epoch: [213]  [190/312]  eta: 0:02:13  lr: 0.000869  min_lr: 0.000869  loss: 2.0653 (2.0287)  weight_decay: 0.0500 (0.0500)  time: 1.0068  data: 0.0004  max mem: 78493
Epoch: [213]  [200/312]  eta: 0:02:02  lr: 0.000868  min_lr: 0.000868  loss: 2.1526 (2.0343)  weight_decay: 0.0500 (0.0500)  time: 1.0076  data: 0.0004  max mem: 78493
Epoch: [213]  [210/312]  eta: 0:01:51  lr: 0.000868  min_lr: 0.000868  loss: 2.0698 (2.0316)  weight_decay: 0.0500 (0.0500)  time: 1.0082  data: 0.0004  max mem: 78493
Epoch: [213]  [220/312]  eta: 0:01:39  lr: 0.000867  min_lr: 0.000867  loss: 2.0571 (2.0372)  weight_decay: 0.0500 (0.0500)  time: 1.0062  data: 0.0004  max mem: 78493
Epoch: [213]  [230/312]  eta: 0:01:28  lr: 0.000867  min_lr: 0.000867  loss: 2.1373 (2.0409)  weight_decay: 0.0500 (0.0500)  time: 1.0071  data: 0.0005  max mem: 78493
Epoch: [213]  [240/312]  eta: 0:01:17  lr: 0.000866  min_lr: 0.000866  loss: 2.1373 (2.0362)  weight_decay: 0.0500 (0.0500)  time: 1.0091  data: 0.0005  max mem: 78493
Epoch: [213]  [250/312]  eta: 0:01:06  lr: 0.000865  min_lr: 0.000865  loss: 2.1083 (2.0428)  weight_decay: 0.0500 (0.0500)  time: 1.0081  data: 0.0004  max mem: 78493
Epoch: [213]  [260/312]  eta: 0:00:55  lr: 0.000865  min_lr: 0.000865  loss: 2.1619 (2.0440)  weight_decay: 0.0500 (0.0500)  time: 1.0077  data: 0.0005  max mem: 78493
Epoch: [213]  [270/312]  eta: 0:00:44  lr: 0.000864  min_lr: 0.000864  loss: 2.1619 (2.0442)  weight_decay: 0.0500 (0.0500)  time: 1.0063  data: 0.0004  max mem: 78493
Epoch: [213]  [280/312]  eta: 0:00:34  lr: 0.000864  min_lr: 0.000864  loss: 2.0542 (2.0444)  weight_decay: 0.0500 (0.0500)  time: 1.0054  data: 0.0017  max mem: 78493
Epoch: [213]  [290/312]  eta: 0:00:23  lr: 0.000863  min_lr: 0.000863  loss: 2.0528 (2.0441)  weight_decay: 0.0500 (0.0500)  time: 1.0042  data: 0.0016  max mem: 78493
Epoch: [213]  [300/312]  eta: 0:00:12  lr: 0.000863  min_lr: 0.000863  loss: 2.0005 (2.0424)  weight_decay: 0.0500 (0.0500)  time: 1.0018  data: 0.0001  max mem: 78493
Epoch: [213]  [310/312]  eta: 0:00:02  lr: 0.000862  min_lr: 0.000862  loss: 2.1405 (2.0454)  weight_decay: 0.0500 (0.0500)  time: 1.0011  data: 0.0001  max mem: 78493
Epoch: [213]  [311/312]  eta: 0:00:01  lr: 0.000862  min_lr: 0.000862  loss: 2.1855 (2.0458)  weight_decay: 0.0500 (0.0500)  time: 1.0010  data: 0.0001  max mem: 78493
Epoch: [213] Total time: 0:05:33 (1.0679 s / it)
Averaged stats: lr: 0.000862  min_lr: 0.000862  loss: 2.1855 (2.0448)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:16  loss: 0.5840 (0.5840)  acc1: 85.2865 (85.2865)  acc5: 96.8750 (96.8750)  time: 8.5540  data: 8.2855  max mem: 78493
Test:  [8/9]  eta: 0:00:01  loss: 0.8531 (0.7978)  acc1: 79.2969 (79.1040)  acc5: 94.9219 (94.8000)  time: 1.1565  data: 0.9207  max mem: 78493
Test: Total time: 0:00:10 (1.2043 s / it)
* Acc@1 79.534 Acc@5 94.832 loss 0.779
Accuracy of the model on the 50000 test images: 79.5%
Max accuracy: 80.21%
Epoch: [214]  [  0/312]  eta: 1:24:30  lr: 0.000862  min_lr: 0.000862  loss: 2.2763 (2.2763)  weight_decay: 0.0500 (0.0500)  time: 16.2513  data: 14.6796  max mem: 78493
Epoch: [214]  [ 10/312]  eta: 0:13:11  lr: 0.000861  min_lr: 0.000861  loss: 2.1175 (2.0587)  weight_decay: 0.0500 (0.0500)  time: 2.6199  data: 1.3352  max mem: 78493
Epoch: [214]  [ 20/312]  eta: 0:09:02  lr: 0.000861  min_lr: 0.000861  loss: 2.1136 (2.0648)  weight_decay: 0.0500 (0.0500)  time: 1.1369  data: 0.0006  max mem: 78493
Epoch: [214]  [ 30/312]  eta: 0:07:26  lr: 0.000860  min_lr: 0.000860  loss: 2.0631 (2.0433)  weight_decay: 0.0500 (0.0500)  time: 1.0125  data: 0.0005  max mem: 78493
Epoch: [214]  [ 40/312]  eta: 0:06:32  lr: 0.000859  min_lr: 0.000859  loss: 2.0631 (2.0704)  weight_decay: 0.0500 (0.0500)  time: 1.0080  data: 0.0005  max mem: 78493
Epoch: [214]  [ 50/312]  eta: 0:05:55  lr: 0.000859  min_lr: 0.000859  loss: 2.1536 (2.0643)  weight_decay: 0.0500 (0.0500)  time: 1.0098  data: 0.0005  max mem: 78493
Epoch: [214]  [ 60/312]  eta: 0:05:28  lr: 0.000858  min_lr: 0.000858  loss: 2.2300 (2.0906)  weight_decay: 0.0500 (0.0500)  time: 1.0129  data: 0.0004  max mem: 78493
Epoch: [214]  [ 70/312]  eta: 0:05:05  lr: 0.000858  min_lr: 0.000858  loss: 2.2328 (2.1022)  weight_decay: 0.0500 (0.0500)  time: 1.0139  data: 0.0005  max mem: 78493
Epoch: [214]  [ 80/312]  eta: 0:04:45  lr: 0.000857  min_lr: 0.000857  loss: 2.2328 (2.1159)  weight_decay: 0.0500 (0.0500)  time: 1.0135  data: 0.0005  max mem: 78493
Epoch: [214]  [ 90/312]  eta: 0:04:27  lr: 0.000857  min_lr: 0.000857  loss: 2.2924 (2.1263)  weight_decay: 0.0500 (0.0500)  time: 1.0111  data: 0.0005  max mem: 78493
Epoch: [214]  [100/312]  eta: 0:04:11  lr: 0.000856  min_lr: 0.000856  loss: 2.0750 (2.1161)  weight_decay: 0.0500 (0.0500)  time: 1.0080  data: 0.0004  max mem: 78493
Epoch: [214]  [110/312]  eta: 0:03:56  lr: 0.000855  min_lr: 0.000855  loss: 2.0455 (2.1082)  weight_decay: 0.0500 (0.0500)  time: 1.0086  data: 0.0004  max mem: 78493
Epoch: [214]  [120/312]  eta: 0:03:42  lr: 0.000855  min_lr: 0.000855  loss: 2.1866 (2.1026)  weight_decay: 0.0500 (0.0500)  time: 1.0086  data: 0.0005  max mem: 78493
Epoch: [214]  [130/312]  eta: 0:03:28  lr: 0.000854  min_lr: 0.000854  loss: 2.1427 (2.0881)  weight_decay: 0.0500 (0.0500)  time: 1.0071  data: 0.0005  max mem: 78493
Epoch: [214]  [140/312]  eta: 0:03:15  lr: 0.000854  min_lr: 0.000854  loss: 1.8063 (2.0715)  weight_decay: 0.0500 (0.0500)  time: 1.0060  data: 0.0004  max mem: 78493
Epoch: [214]  [150/312]  eta: 0:03:02  lr: 0.000853  min_lr: 0.000853  loss: 2.0279 (2.0707)  weight_decay: 0.0500 (0.0500)  time: 1.0059  data: 0.0005  max mem: 78493
Epoch: [214]  [160/312]  eta: 0:02:50  lr: 0.000852  min_lr: 0.000852  loss: 2.1928 (2.0794)  weight_decay: 0.0500 (0.0500)  time: 1.0066  data: 0.0005  max mem: 78493
Epoch: [214]  [170/312]  eta: 0:02:38  lr: 0.000852  min_lr: 0.000852  loss: 2.2117 (2.0783)  weight_decay: 0.0500 (0.0500)  time: 1.0066  data: 0.0005  max mem: 78493
Epoch: [214]  [180/312]  eta: 0:02:26  lr: 0.000851  min_lr: 0.000851  loss: 2.0436 (2.0800)  weight_decay: 0.0500 (0.0500)  time: 1.0066  data: 0.0005  max mem: 78493
Epoch: [214]  [190/312]  eta: 0:02:14  lr: 0.000851  min_lr: 0.000851  loss: 2.1935 (2.0746)  weight_decay: 0.0500 (0.0500)  time: 1.0069  data: 0.0004  max mem: 78493
Epoch: [214]  [200/312]  eta: 0:02:02  lr: 0.000850  min_lr: 0.000850  loss: 2.2313 (2.0743)  weight_decay: 0.0500 (0.0500)  time: 1.0084  data: 0.0004  max mem: 78493
Epoch: [214]  [210/312]  eta: 0:01:51  lr: 0.000849  min_lr: 0.000849  loss: 2.0968 (2.0721)  weight_decay: 0.0500 (0.0500)  time: 1.0083  data: 0.0004  max mem: 78493
Epoch: [214]  [220/312]  eta: 0:01:40  lr: 0.000849  min_lr: 0.000849  loss: 2.0968 (2.0756)  weight_decay: 0.0500 (0.0500)  time: 1.0078  data: 0.0004  max mem: 78493
Epoch: [214]  [230/312]  eta: 0:01:29  lr: 0.000848  min_lr: 0.000848  loss: 2.0161 (2.0668)  weight_decay: 0.0500 (0.0500)  time: 1.0075  data: 0.0004  max mem: 78493
Epoch: [214]  [240/312]  eta: 0:01:17  lr: 0.000848  min_lr: 0.000848  loss: 1.8313 (2.0627)  weight_decay: 0.0500 (0.0500)  time: 1.0065  data: 0.0004  max mem: 78493
Epoch: [214]  [250/312]  eta: 0:01:06  lr: 0.000847  min_lr: 0.000847  loss: 2.0624 (2.0669)  weight_decay: 0.0500 (0.0500)  time: 1.0064  data: 0.0005  max mem: 78493
Epoch: [214]  [260/312]  eta: 0:00:55  lr: 0.000846  min_lr: 0.000846  loss: 2.0804 (2.0609)  weight_decay: 0.0500 (0.0500)  time: 1.0075  data: 0.0005  max mem: 78493
Epoch: [214]  [270/312]  eta: 0:00:45  lr: 0.000846  min_lr: 0.000846  loss: 2.0626 (2.0591)  weight_decay: 0.0500 (0.0500)  time: 1.0085  data: 0.0011  max mem: 78493
Epoch: [214]  [280/312]  eta: 0:00:34  lr: 0.000845  min_lr: 0.000845  loss: 2.0809 (2.0578)  weight_decay: 0.0500 (0.0500)  time: 1.0082  data: 0.0017  max mem: 78493
Epoch: [214]  [290/312]  eta: 0:00:23  lr: 0.000845  min_lr: 0.000845  loss: 2.1485 (2.0560)  weight_decay: 0.0500 (0.0500)  time: 1.0048  data: 0.0009  max mem: 78493
Epoch: [214]  [300/312]  eta: 0:00:12  lr: 0.000844  min_lr: 0.000844  loss: 2.1954 (2.0609)  weight_decay: 0.0500 (0.0500)  time: 1.0015  data: 0.0001  max mem: 78493
Epoch: [214]  [310/312]  eta: 0:00:02  lr: 0.000844  min_lr: 0.000844  loss: 2.1959 (2.0611)  weight_decay: 0.0500 (0.0500)  time: 1.0017  data: 0.0001  max mem: 78493
Epoch: [214]  [311/312]  eta: 0:00:01  lr: 0.000844  min_lr: 0.000844  loss: 2.1477 (2.0608)  weight_decay: 0.0500 (0.0500)  time: 1.0017  data: 0.0001  max mem: 78493
Epoch: [214] Total time: 0:05:34 (1.0705 s / it)
Averaged stats: lr: 0.000844  min_lr: 0.000844  loss: 2.1477 (2.0445)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:16  loss: 0.5476 (0.5476)  acc1: 86.1979 (86.1979)  acc5: 97.3958 (97.3958)  time: 8.4564  data: 8.1819  max mem: 78493
Test:  [8/9]  eta: 0:00:01  loss: 0.8461 (0.7773)  acc1: 78.3854 (79.3600)  acc5: 95.4427 (95.0240)  time: 1.1493  data: 0.9092  max mem: 78493
Test: Total time: 0:00:10 (1.1868 s / it)
* Acc@1 80.076 Acc@5 94.984 loss 0.760
Accuracy of the model on the 50000 test images: 80.1%
Max accuracy: 80.21%
Epoch: [215]  [  0/312]  eta: 1:25:56  lr: 0.000843  min_lr: 0.000843  loss: 1.5863 (1.5863)  weight_decay: 0.0500 (0.0500)  time: 16.5281  data: 11.6375  max mem: 78493
Epoch: [215]  [ 10/312]  eta: 0:13:26  lr: 0.000843  min_lr: 0.000843  loss: 1.8411 (1.8375)  weight_decay: 0.0500 (0.0500)  time: 2.6719  data: 1.1357  max mem: 78493
Epoch: [215]  [ 20/312]  eta: 0:09:08  lr: 0.000842  min_lr: 0.000842  loss: 2.0274 (1.9736)  weight_decay: 0.0500 (0.0500)  time: 1.1472  data: 0.0430  max mem: 78493
Epoch: [215]  [ 30/312]  eta: 0:07:30  lr: 0.000842  min_lr: 0.000842  loss: 1.7525 (1.9036)  weight_decay: 0.0500 (0.0500)  time: 1.0072  data: 0.0004  max mem: 78493
Epoch: [215]  [ 40/312]  eta: 0:06:35  lr: 0.000841  min_lr: 0.000841  loss: 1.7465 (1.9216)  weight_decay: 0.0500 (0.0500)  time: 1.0074  data: 0.0015  max mem: 78493
Epoch: [215]  [ 50/312]  eta: 0:05:58  lr: 0.000841  min_lr: 0.000841  loss: 2.0165 (1.9483)  weight_decay: 0.0500 (0.0500)  time: 1.0092  data: 0.0015  max mem: 78493
Epoch: [215]  [ 60/312]  eta: 0:05:29  lr: 0.000840  min_lr: 0.000840  loss: 2.1315 (1.9471)  weight_decay: 0.0500 (0.0500)  time: 1.0083  data: 0.0004  max mem: 78493
Epoch: [215]  [ 70/312]  eta: 0:05:06  lr: 0.000839  min_lr: 0.000839  loss: 2.1701 (1.9689)  weight_decay: 0.0500 (0.0500)  time: 1.0076  data: 0.0004  max mem: 78493
Epoch: [215]  [ 80/312]  eta: 0:04:46  lr: 0.000839  min_lr: 0.000839  loss: 2.0841 (1.9736)  weight_decay: 0.0500 (0.0500)  time: 1.0104  data: 0.0013  max mem: 78493
Epoch: [215]  [ 90/312]  eta: 0:04:28  lr: 0.000838  min_lr: 0.000838  loss: 2.0808 (1.9862)  weight_decay: 0.0500 (0.0500)  time: 1.0121  data: 0.0013  max mem: 78493
Epoch: [215]  [100/312]  eta: 0:04:12  lr: 0.000838  min_lr: 0.000838  loss: 2.1799 (2.0020)  weight_decay: 0.0500 (0.0500)  time: 1.0117  data: 0.0004  max mem: 78493
Epoch: [215]  [110/312]  eta: 0:03:57  lr: 0.000837  min_lr: 0.000837  loss: 2.2233 (2.0208)  weight_decay: 0.0500 (0.0500)  time: 1.0103  data: 0.0016  max mem: 78493
Epoch: [215]  [120/312]  eta: 0:03:42  lr: 0.000836  min_lr: 0.000836  loss: 1.9419 (2.0028)  weight_decay: 0.0500 (0.0500)  time: 1.0080  data: 0.0016  max mem: 78493
Epoch: [215]  [130/312]  eta: 0:03:29  lr: 0.000836  min_lr: 0.000836  loss: 1.8741 (2.0055)  weight_decay: 0.0500 (0.0500)  time: 1.0066  data: 0.0005  max mem: 78493
Epoch: [215]  [140/312]  eta: 0:03:15  lr: 0.000835  min_lr: 0.000835  loss: 2.0223 (2.0127)  weight_decay: 0.0500 (0.0500)  time: 1.0065  data: 0.0005  max mem: 78493
Epoch: [215]  [150/312]  eta: 0:03:03  lr: 0.000835  min_lr: 0.000835  loss: 1.9679 (2.0112)  weight_decay: 0.0500 (0.0500)  time: 1.0094  data: 0.0005  max mem: 78493
Epoch: [215]  [160/312]  eta: 0:02:50  lr: 0.000834  min_lr: 0.000834  loss: 1.9876 (2.0100)  weight_decay: 0.0500 (0.0500)  time: 1.0096  data: 0.0004  max mem: 78493
Epoch: [215]  [170/312]  eta: 0:02:38  lr: 0.000833  min_lr: 0.000833  loss: 2.0529 (2.0024)  weight_decay: 0.0500 (0.0500)  time: 1.0070  data: 0.0004  max mem: 78493
Epoch: [215]  [180/312]  eta: 0:02:26  lr: 0.000833  min_lr: 0.000833  loss: 1.8789 (1.9983)  weight_decay: 0.0500 (0.0500)  time: 1.0065  data: 0.0004  max mem: 78493
Epoch: [215]  [190/312]  eta: 0:02:14  lr: 0.000832  min_lr: 0.000832  loss: 1.9838 (1.9963)  weight_decay: 0.0500 (0.0500)  time: 1.0064  data: 0.0004  max mem: 78493
Epoch: [215]  [200/312]  eta: 0:02:03  lr: 0.000832  min_lr: 0.000832  loss: 1.9929 (2.0003)  weight_decay: 0.0500 (0.0500)  time: 1.0060  data: 0.0004  max mem: 78493
Epoch: [215]  [210/312]  eta: 0:01:51  lr: 0.000831  min_lr: 0.000831  loss: 2.1116 (2.0113)  weight_decay: 0.0500 (0.0500)  time: 1.0072  data: 0.0004  max mem: 78493
Epoch: [215]  [220/312]  eta: 0:01:40  lr: 0.000831  min_lr: 0.000831  loss: 2.2023 (2.0078)  weight_decay: 0.0500 (0.0500)  time: 1.0076  data: 0.0005  max mem: 78493
Epoch: [215]  [230/312]  eta: 0:01:29  lr: 0.000830  min_lr: 0.000830  loss: 1.9586 (2.0077)  weight_decay: 0.0500 (0.0500)  time: 1.0058  data: 0.0004  max mem: 78493
Epoch: [215]  [240/312]  eta: 0:01:18  lr: 0.000829  min_lr: 0.000829  loss: 1.8496 (1.9996)  weight_decay: 0.0500 (0.0500)  time: 1.0047  data: 0.0005  max mem: 78493
Epoch: [215]  [250/312]  eta: 0:01:07  lr: 0.000829  min_lr: 0.000829  loss: 1.8496 (2.0003)  weight_decay: 0.0500 (0.0500)  time: 1.0045  data: 0.0004  max mem: 78493
Epoch: [215]  [260/312]  eta: 0:00:56  lr: 0.000828  min_lr: 0.000828  loss: 1.9829 (2.0013)  weight_decay: 0.0500 (0.0500)  time: 1.0043  data: 0.0005  max mem: 78493
Epoch: [215]  [270/312]  eta: 0:00:45  lr: 0.000828  min_lr: 0.000828  loss: 2.1512 (2.0075)  weight_decay: 0.0500 (0.0500)  time: 1.0044  data: 0.0005  max mem: 78493
Epoch: [215]  [280/312]  eta: 0:00:34  lr: 0.000827  min_lr: 0.000827  loss: 2.1512 (2.0115)  weight_decay: 0.0500 (0.0500)  time: 1.0058  data: 0.0010  max mem: 78493
Epoch: [215]  [290/312]  eta: 0:00:23  lr: 0.000827  min_lr: 0.000827  loss: 2.0784 (2.0109)  weight_decay: 0.0500 (0.0500)  time: 1.0040  data: 0.0009  max mem: 78493
Epoch: [215]  [300/312]  eta: 0:00:12  lr: 0.000826  min_lr: 0.000826  loss: 1.9662 (2.0062)  weight_decay: 0.0500 (0.0500)  time: 1.0017  data: 0.0001  max mem: 78493
Epoch: [215]  [310/312]  eta: 0:00:02  lr: 0.000825  min_lr: 0.000825  loss: 1.9746 (2.0101)  weight_decay: 0.0500 (0.0500)  time: 1.0020  data: 0.0001  max mem: 78493
Epoch: [215]  [311/312]  eta: 0:00:01  lr: 0.000825  min_lr: 0.000825  loss: 1.9746 (2.0103)  weight_decay: 0.0500 (0.0500)  time: 1.0020  data: 0.0001  max mem: 78493
Epoch: [215] Total time: 0:05:34 (1.0711 s / it)
Averaged stats: lr: 0.000825  min_lr: 0.000825  loss: 1.9746 (2.0346)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:17  loss: 0.5636 (0.5636)  acc1: 85.2865 (85.2865)  acc5: 97.1354 (97.1354)  time: 8.5618  data: 8.2909  max mem: 78493
Test:  [8/9]  eta: 0:00:01  loss: 0.8255 (0.7778)  acc1: 80.2083 (79.7280)  acc5: 95.5729 (94.9760)  time: 1.1496  data: 0.9213  max mem: 78493
Test: Total time: 0:00:10 (1.1617 s / it)
* Acc@1 80.072 Acc@5 94.970 loss 0.762
Accuracy of the model on the 50000 test images: 80.1%
Max accuracy: 80.21%
Epoch: [216]  [  0/312]  eta: 1:26:16  lr: 0.000825  min_lr: 0.000825  loss: 2.4889 (2.4889)  weight_decay: 0.0500 (0.0500)  time: 16.5923  data: 15.2405  max mem: 78493
Epoch: [216]  [ 10/312]  eta: 0:13:28  lr: 0.000825  min_lr: 0.000825  loss: 2.0760 (1.9448)  weight_decay: 0.0500 (0.0500)  time: 2.6756  data: 1.3886  max mem: 78493
Epoch: [216]  [ 20/312]  eta: 0:09:10  lr: 0.000824  min_lr: 0.000824  loss: 2.0867 (2.0418)  weight_decay: 0.0500 (0.0500)  time: 1.1502  data: 0.0019  max mem: 78493
Epoch: [216]  [ 30/312]  eta: 0:07:31  lr: 0.000823  min_lr: 0.000823  loss: 2.1325 (2.0165)  weight_decay: 0.0500 (0.0500)  time: 1.0126  data: 0.0005  max mem: 78493
Epoch: [216]  [ 40/312]  eta: 0:06:36  lr: 0.000823  min_lr: 0.000823  loss: 2.0453 (2.0092)  weight_decay: 0.0500 (0.0500)  time: 1.0091  data: 0.0004  max mem: 78493
Epoch: [216]  [ 50/312]  eta: 0:05:58  lr: 0.000822  min_lr: 0.000822  loss: 2.1340 (2.0273)  weight_decay: 0.0500 (0.0500)  time: 1.0089  data: 0.0005  max mem: 78493
Epoch: [216]  [ 60/312]  eta: 0:05:30  lr: 0.000822  min_lr: 0.000822  loss: 2.1340 (2.0086)  weight_decay: 0.0500 (0.0500)  time: 1.0090  data: 0.0012  max mem: 78493
Epoch: [216]  [ 70/312]  eta: 0:05:06  lr: 0.000821  min_lr: 0.000821  loss: 1.8041 (2.0067)  weight_decay: 0.0500 (0.0500)  time: 1.0083  data: 0.0012  max mem: 78493
Epoch: [216]  [ 80/312]  eta: 0:04:46  lr: 0.000821  min_lr: 0.000821  loss: 2.1009 (2.0156)  weight_decay: 0.0500 (0.0500)  time: 1.0069  data: 0.0004  max mem: 78493
Epoch: [216]  [ 90/312]  eta: 0:04:28  lr: 0.000820  min_lr: 0.000820  loss: 1.9673 (2.0038)  weight_decay: 0.0500 (0.0500)  time: 1.0088  data: 0.0004  max mem: 78493
Epoch: [216]  [100/312]  eta: 0:04:12  lr: 0.000819  min_lr: 0.000819  loss: 1.9448 (1.9956)  weight_decay: 0.0500 (0.0500)  time: 1.0086  data: 0.0004  max mem: 78493
Epoch: [216]  [110/312]  eta: 0:03:57  lr: 0.000819  min_lr: 0.000819  loss: 2.1017 (2.0136)  weight_decay: 0.0500 (0.0500)  time: 1.0065  data: 0.0005  max mem: 78493
Epoch: [216]  [120/312]  eta: 0:03:42  lr: 0.000818  min_lr: 0.000818  loss: 2.0161 (2.0076)  weight_decay: 0.0500 (0.0500)  time: 1.0071  data: 0.0005  max mem: 78493
Epoch: [216]  [130/312]  eta: 0:03:29  lr: 0.000818  min_lr: 0.000818  loss: 2.0161 (2.0073)  weight_decay: 0.0500 (0.0500)  time: 1.0070  data: 0.0004  max mem: 78493
Epoch: [216]  [140/312]  eta: 0:03:15  lr: 0.000817  min_lr: 0.000817  loss: 1.9362 (1.9900)  weight_decay: 0.0500 (0.0500)  time: 1.0083  data: 0.0012  max mem: 78493
Epoch: [216]  [150/312]  eta: 0:03:03  lr: 0.000817  min_lr: 0.000817  loss: 1.9362 (1.9937)  weight_decay: 0.0500 (0.0500)  time: 1.0082  data: 0.0012  max mem: 78493
Epoch: [216]  [160/312]  eta: 0:02:50  lr: 0.000816  min_lr: 0.000816  loss: 1.9118 (1.9827)  weight_decay: 0.0500 (0.0500)  time: 1.0065  data: 0.0004  max mem: 78493
Epoch: [216]  [170/312]  eta: 0:02:38  lr: 0.000815  min_lr: 0.000815  loss: 1.9118 (1.9893)  weight_decay: 0.0500 (0.0500)  time: 1.0064  data: 0.0004  max mem: 78493
Epoch: [216]  [180/312]  eta: 0:02:26  lr: 0.000815  min_lr: 0.000815  loss: 2.1021 (2.0005)  weight_decay: 0.0500 (0.0500)  time: 1.0049  data: 0.0004  max mem: 78493
Epoch: [216]  [190/312]  eta: 0:02:14  lr: 0.000814  min_lr: 0.000814  loss: 2.1118 (2.0021)  weight_decay: 0.0500 (0.0500)  time: 1.0052  data: 0.0004  max mem: 78493
Epoch: [216]  [200/312]  eta: 0:02:03  lr: 0.000814  min_lr: 0.000814  loss: 2.1118 (2.0074)  weight_decay: 0.0500 (0.0500)  time: 1.0068  data: 0.0004  max mem: 78493
Epoch: [216]  [210/312]  eta: 0:01:51  lr: 0.000813  min_lr: 0.000813  loss: 2.2055 (2.0055)  weight_decay: 0.0500 (0.0500)  time: 1.0066  data: 0.0005  max mem: 78493
Epoch: [216]  [220/312]  eta: 0:01:40  lr: 0.000812  min_lr: 0.000812  loss: 2.0765 (2.0076)  weight_decay: 0.0500 (0.0500)  time: 1.0055  data: 0.0005  max mem: 78493
Epoch: [216]  [230/312]  eta: 0:01:29  lr: 0.000812  min_lr: 0.000812  loss: 2.1260 (2.0096)  weight_decay: 0.0500 (0.0500)  time: 1.0072  data: 0.0004  max mem: 78493
Epoch: [216]  [240/312]  eta: 0:01:18  lr: 0.000811  min_lr: 0.000811  loss: 2.2000 (2.0115)  weight_decay: 0.0500 (0.0500)  time: 1.0079  data: 0.0004  max mem: 78493
Epoch: [216]  [250/312]  eta: 0:01:07  lr: 0.000811  min_lr: 0.000811  loss: 2.2544 (2.0149)  weight_decay: 0.0500 (0.0500)  time: 1.0056  data: 0.0004  max mem: 78493
Epoch: [216]  [260/312]  eta: 0:00:56  lr: 0.000810  min_lr: 0.000810  loss: 2.1195 (2.0124)  weight_decay: 0.0500 (0.0500)  time: 1.0054  data: 0.0004  max mem: 78493
Epoch: [216]  [270/312]  eta: 0:00:45  lr: 0.000810  min_lr: 0.000810  loss: 2.1195 (2.0164)  weight_decay: 0.0500 (0.0500)  time: 1.0054  data: 0.0004  max mem: 78493
Epoch: [216]  [280/312]  eta: 0:00:34  lr: 0.000809  min_lr: 0.000809  loss: 2.2504 (2.0243)  weight_decay: 0.0500 (0.0500)  time: 1.0068  data: 0.0010  max mem: 78493
Epoch: [216]  [290/312]  eta: 0:00:23  lr: 0.000808  min_lr: 0.000808  loss: 2.1236 (2.0269)  weight_decay: 0.0500 (0.0500)  time: 1.0048  data: 0.0009  max mem: 78493
Epoch: [216]  [300/312]  eta: 0:00:12  lr: 0.000808  min_lr: 0.000808  loss: 2.0208 (2.0241)  weight_decay: 0.0500 (0.0500)  time: 1.0008  data: 0.0001  max mem: 78493
Epoch: [216]  [310/312]  eta: 0:00:02  lr: 0.000807  min_lr: 0.000807  loss: 2.0930 (2.0284)  weight_decay: 0.0500 (0.0500)  time: 1.0007  data: 0.0001  max mem: 78493
Epoch: [216]  [311/312]  eta: 0:00:01  lr: 0.000807  min_lr: 0.000807  loss: 2.0984 (2.0292)  weight_decay: 0.0500 (0.0500)  time: 1.0006  data: 0.0001  max mem: 78493
Epoch: [216] Total time: 0:05:34 (1.0711 s / it)
Averaged stats: lr: 0.000807  min_lr: 0.000807  loss: 2.0984 (2.0360)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:07  loss: 0.6164 (0.6164)  acc1: 85.4167 (85.4167)  acc5: 96.7448 (96.7448)  time: 7.5097  data: 7.2060  max mem: 78493
Test:  [8/9]  eta: 0:00:01  loss: 0.8304 (0.7809)  acc1: 78.5156 (79.4560)  acc5: 95.5729 (94.8960)  time: 1.0922  data: 0.8601  max mem: 78493
Test: Total time: 0:00:09 (1.1073 s / it)
* Acc@1 79.812 Acc@5 94.848 loss 0.771
Accuracy of the model on the 50000 test images: 79.8%
Max accuracy: 80.21%
Epoch: [217]  [  0/312]  eta: 1:27:59  lr: 0.000807  min_lr: 0.000807  loss: 2.3541 (2.3541)  weight_decay: 0.0500 (0.0500)  time: 16.9226  data: 12.1361  max mem: 78493
Epoch: [217]  [ 10/312]  eta: 0:13:42  lr: 0.000807  min_lr: 0.000807  loss: 2.2604 (2.1012)  weight_decay: 0.0500 (0.0500)  time: 2.7232  data: 1.3578  max mem: 78493
Epoch: [217]  [ 20/312]  eta: 0:09:16  lr: 0.000806  min_lr: 0.000806  loss: 2.0296 (1.9797)  weight_decay: 0.0500 (0.0500)  time: 1.1556  data: 0.1402  max mem: 78493
Epoch: [217]  [ 30/312]  eta: 0:07:36  lr: 0.000805  min_lr: 0.000805  loss: 2.0241 (2.0261)  weight_decay: 0.0500 (0.0500)  time: 1.0089  data: 0.0005  max mem: 78493
Epoch: [217]  [ 40/312]  eta: 0:06:39  lr: 0.000805  min_lr: 0.000805  loss: 2.0340 (1.9995)  weight_decay: 0.0500 (0.0500)  time: 1.0107  data: 0.0004  max mem: 78493
Epoch: [217]  [ 50/312]  eta: 0:06:01  lr: 0.000804  min_lr: 0.000804  loss: 2.1404 (2.0307)  weight_decay: 0.0500 (0.0500)  time: 1.0103  data: 0.0005  max mem: 78493
Epoch: [217]  [ 60/312]  eta: 0:05:32  lr: 0.000804  min_lr: 0.000804  loss: 2.1846 (2.0319)  weight_decay: 0.0500 (0.0500)  time: 1.0084  data: 0.0005  max mem: 78493
Epoch: [217]  [ 70/312]  eta: 0:05:08  lr: 0.000803  min_lr: 0.000803  loss: 1.9346 (2.0102)  weight_decay: 0.0500 (0.0500)  time: 1.0093  data: 0.0004  max mem: 78493
Epoch: [217]  [ 80/312]  eta: 0:04:48  lr: 0.000803  min_lr: 0.000803  loss: 1.8352 (2.0018)  weight_decay: 0.0500 (0.0500)  time: 1.0117  data: 0.0005  max mem: 78493
Epoch: [217]  [ 90/312]  eta: 0:04:30  lr: 0.000802  min_lr: 0.000802  loss: 1.8917 (2.0058)  weight_decay: 0.0500 (0.0500)  time: 1.0119  data: 0.0005  max mem: 78493
Epoch: [217]  [100/312]  eta: 0:04:13  lr: 0.000801  min_lr: 0.000801  loss: 2.2471 (2.0358)  weight_decay: 0.0500 (0.0500)  time: 1.0102  data: 0.0005  max mem: 78493
Epoch: [217]  [110/312]  eta: 0:03:58  lr: 0.000801  min_lr: 0.000801  loss: 2.2067 (2.0396)  weight_decay: 0.0500 (0.0500)  time: 1.0094  data: 0.0005  max mem: 78493
Epoch: [217]  [120/312]  eta: 0:03:43  lr: 0.000800  min_lr: 0.000800  loss: 2.0461 (2.0355)  weight_decay: 0.0500 (0.0500)  time: 1.0095  data: 0.0004  max mem: 78493
Epoch: [217]  [130/312]  eta: 0:03:29  lr: 0.000800  min_lr: 0.000800  loss: 2.0461 (2.0327)  weight_decay: 0.0500 (0.0500)  time: 1.0098  data: 0.0004  max mem: 78493
Epoch: [217]  [140/312]  eta: 0:03:16  lr: 0.000799  min_lr: 0.000799  loss: 1.9707 (2.0281)  weight_decay: 0.0500 (0.0500)  time: 1.0125  data: 0.0005  max mem: 78493
Epoch: [217]  [150/312]  eta: 0:03:03  lr: 0.000799  min_lr: 0.000799  loss: 1.8821 (2.0099)  weight_decay: 0.0500 (0.0500)  time: 1.0108  data: 0.0005  max mem: 78493
Epoch: [217]  [160/312]  eta: 0:02:51  lr: 0.000798  min_lr: 0.000798  loss: 1.8496 (2.0026)  weight_decay: 0.0500 (0.0500)  time: 1.0078  data: 0.0020  max mem: 78493
Epoch: [217]  [170/312]  eta: 0:02:39  lr: 0.000797  min_lr: 0.000797  loss: 2.0629 (2.0036)  weight_decay: 0.0500 (0.0500)  time: 1.0091  data: 0.0027  max mem: 78493
Epoch: [217]  [180/312]  eta: 0:02:27  lr: 0.000797  min_lr: 0.000797  loss: 2.0951 (2.0118)  weight_decay: 0.0500 (0.0500)  time: 1.0116  data: 0.0012  max mem: 78493
Epoch: [217]  [190/312]  eta: 0:02:15  lr: 0.000796  min_lr: 0.000796  loss: 2.1696 (2.0179)  weight_decay: 0.0500 (0.0500)  time: 1.0129  data: 0.0011  max mem: 78493
Epoch: [217]  [200/312]  eta: 0:02:03  lr: 0.000796  min_lr: 0.000796  loss: 2.1443 (2.0218)  weight_decay: 0.0500 (0.0500)  time: 1.0129  data: 0.0011  max mem: 78493
Epoch: [217]  [210/312]  eta: 0:01:52  lr: 0.000795  min_lr: 0.000795  loss: 2.1058 (2.0200)  weight_decay: 0.0500 (0.0500)  time: 1.0115  data: 0.0004  max mem: 78493
Epoch: [217]  [220/312]  eta: 0:01:40  lr: 0.000794  min_lr: 0.000794  loss: 2.0750 (2.0208)  weight_decay: 0.0500 (0.0500)  time: 1.0117  data: 0.0004  max mem: 78493
Epoch: [217]  [230/312]  eta: 0:01:29  lr: 0.000794  min_lr: 0.000794  loss: 1.9297 (2.0139)  weight_decay: 0.0500 (0.0500)  time: 1.0140  data: 0.0004  max mem: 78493
Epoch: [217]  [240/312]  eta: 0:01:18  lr: 0.000793  min_lr: 0.000793  loss: 2.0467 (2.0145)  weight_decay: 0.0500 (0.0500)  time: 1.0121  data: 0.0012  max mem: 78493
Epoch: [217]  [250/312]  eta: 0:01:07  lr: 0.000793  min_lr: 0.000793  loss: 2.0619 (2.0165)  weight_decay: 0.0500 (0.0500)  time: 1.0117  data: 0.0012  max mem: 78493
Epoch: [217]  [260/312]  eta: 0:00:56  lr: 0.000792  min_lr: 0.000792  loss: 2.0335 (2.0176)  weight_decay: 0.0500 (0.0500)  time: 1.0106  data: 0.0005  max mem: 78493
Epoch: [217]  [270/312]  eta: 0:00:45  lr: 0.000792  min_lr: 0.000792  loss: 2.0335 (2.0154)  weight_decay: 0.0500 (0.0500)  time: 1.0072  data: 0.0004  max mem: 78493
Epoch: [217]  [280/312]  eta: 0:00:34  lr: 0.000791  min_lr: 0.000791  loss: 2.1307 (2.0211)  weight_decay: 0.0500 (0.0500)  time: 1.0067  data: 0.0017  max mem: 78493
Epoch: [217]  [290/312]  eta: 0:00:23  lr: 0.000790  min_lr: 0.000790  loss: 2.1017 (2.0167)  weight_decay: 0.0500 (0.0500)  time: 1.0040  data: 0.0016  max mem: 78493
Epoch: [217]  [300/312]  eta: 0:00:12  lr: 0.000790  min_lr: 0.000790  loss: 2.0626 (2.0187)  weight_decay: 0.0500 (0.0500)  time: 1.0016  data: 0.0001  max mem: 78493
Epoch: [217]  [310/312]  eta: 0:00:02  lr: 0.000789  min_lr: 0.000789  loss: 2.0788 (2.0175)  weight_decay: 0.0500 (0.0500)  time: 1.0017  data: 0.0001  max mem: 78493
Epoch: [217]  [311/312]  eta: 0:00:01  lr: 0.000789  min_lr: 0.000789  loss: 2.0788 (2.0162)  weight_decay: 0.0500 (0.0500)  time: 1.0017  data: 0.0001  max mem: 78493
Epoch: [217] Total time: 0:05:35 (1.0757 s / it)
Averaged stats: lr: 0.000789  min_lr: 0.000789  loss: 2.0788 (2.0291)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:14  loss: 0.5199 (0.5199)  acc1: 86.8490 (86.8490)  acc5: 97.9167 (97.9167)  time: 8.3093  data: 8.0413  max mem: 78493
Test:  [8/9]  eta: 0:00:01  loss: 0.8254 (0.7480)  acc1: 80.0781 (80.4160)  acc5: 95.5729 (95.1520)  time: 1.1231  data: 0.8936  max mem: 78493
Test: Total time: 0:00:10 (1.1374 s / it)
* Acc@1 80.430 Acc@5 95.220 loss 0.741
Accuracy of the model on the 50000 test images: 80.4%
Max accuracy: 80.43%
Epoch: [218]  [  0/312]  eta: 1:21:27  lr: 0.000789  min_lr: 0.000789  loss: 1.6316 (1.6316)  weight_decay: 0.0500 (0.0500)  time: 15.6645  data: 14.6572  max mem: 78493
Epoch: [218]  [ 10/312]  eta: 0:13:43  lr: 0.000789  min_lr: 0.000789  loss: 2.0565 (1.9745)  weight_decay: 0.0500 (0.0500)  time: 2.7263  data: 1.3868  max mem: 78493
Epoch: [218]  [ 20/312]  eta: 0:09:16  lr: 0.000788  min_lr: 0.000788  loss: 2.1284 (2.0585)  weight_decay: 0.0500 (0.0500)  time: 1.2187  data: 0.0301  max mem: 78493
Epoch: [218]  [ 30/312]  eta: 0:07:36  lr: 0.000788  min_lr: 0.000788  loss: 2.0363 (1.9897)  weight_decay: 0.0500 (0.0500)  time: 1.0087  data: 0.0005  max mem: 78493
Epoch: [218]  [ 40/312]  eta: 0:06:39  lr: 0.000787  min_lr: 0.000787  loss: 1.8643 (1.9858)  weight_decay: 0.0500 (0.0500)  time: 1.0108  data: 0.0005  max mem: 78493
Epoch: [218]  [ 50/312]  eta: 0:06:01  lr: 0.000786  min_lr: 0.000786  loss: 2.0908 (1.9896)  weight_decay: 0.0500 (0.0500)  time: 1.0082  data: 0.0005  max mem: 78493
Epoch: [218]  [ 60/312]  eta: 0:05:32  lr: 0.000786  min_lr: 0.000786  loss: 1.9669 (1.9871)  weight_decay: 0.0500 (0.0500)  time: 1.0089  data: 0.0005  max mem: 78493
Epoch: [218]  [ 70/312]  eta: 0:05:08  lr: 0.000785  min_lr: 0.000785  loss: 2.0113 (1.9921)  weight_decay: 0.0500 (0.0500)  time: 1.0089  data: 0.0012  max mem: 78493
Epoch: [218]  [ 80/312]  eta: 0:04:48  lr: 0.000785  min_lr: 0.000785  loss: 2.0557 (2.0015)  weight_decay: 0.0500 (0.0500)  time: 1.0073  data: 0.0012  max mem: 78493
Epoch: [218]  [ 90/312]  eta: 0:04:29  lr: 0.000784  min_lr: 0.000784  loss: 2.1529 (2.0241)  weight_decay: 0.0500 (0.0500)  time: 1.0075  data: 0.0005  max mem: 78493
Epoch: [218]  [100/312]  eta: 0:04:13  lr: 0.000784  min_lr: 0.000784  loss: 2.1319 (2.0258)  weight_decay: 0.0500 (0.0500)  time: 1.0085  data: 0.0004  max mem: 78493
Epoch: [218]  [110/312]  eta: 0:03:58  lr: 0.000783  min_lr: 0.000783  loss: 1.9497 (2.0139)  weight_decay: 0.0500 (0.0500)  time: 1.0094  data: 0.0005  max mem: 78493
Epoch: [218]  [120/312]  eta: 0:03:43  lr: 0.000782  min_lr: 0.000782  loss: 2.0914 (2.0341)  weight_decay: 0.0500 (0.0500)  time: 1.0099  data: 0.0005  max mem: 78493
Epoch: [218]  [130/312]  eta: 0:03:29  lr: 0.000782  min_lr: 0.000782  loss: 2.0681 (2.0209)  weight_decay: 0.0500 (0.0500)  time: 1.0116  data: 0.0004  max mem: 78493
Epoch: [218]  [140/312]  eta: 0:03:16  lr: 0.000781  min_lr: 0.000781  loss: 2.0572 (2.0212)  weight_decay: 0.0500 (0.0500)  time: 1.0116  data: 0.0004  max mem: 78493
Epoch: [218]  [150/312]  eta: 0:03:03  lr: 0.000781  min_lr: 0.000781  loss: 2.0332 (2.0186)  weight_decay: 0.0500 (0.0500)  time: 1.0098  data: 0.0005  max mem: 78493
Epoch: [218]  [160/312]  eta: 0:02:51  lr: 0.000780  min_lr: 0.000780  loss: 2.1273 (2.0355)  weight_decay: 0.0500 (0.0500)  time: 1.0082  data: 0.0005  max mem: 78493
Epoch: [218]  [170/312]  eta: 0:02:39  lr: 0.000780  min_lr: 0.000780  loss: 2.2250 (2.0415)  weight_decay: 0.0500 (0.0500)  time: 1.0102  data: 0.0005  max mem: 78493
Epoch: [218]  [180/312]  eta: 0:02:27  lr: 0.000779  min_lr: 0.000779  loss: 2.1758 (2.0478)  weight_decay: 0.0500 (0.0500)  time: 1.0118  data: 0.0013  max mem: 78493
Epoch: [218]  [190/312]  eta: 0:02:15  lr: 0.000778  min_lr: 0.000778  loss: 2.1478 (2.0468)  weight_decay: 0.0500 (0.0500)  time: 1.0117  data: 0.0020  max mem: 78493
Epoch: [218]  [200/312]  eta: 0:02:03  lr: 0.000778  min_lr: 0.000778  loss: 2.0911 (2.0477)  weight_decay: 0.0500 (0.0500)  time: 1.0114  data: 0.0011  max mem: 78493
Epoch: [218]  [210/312]  eta: 0:01:52  lr: 0.000777  min_lr: 0.000777  loss: 2.1102 (2.0492)  weight_decay: 0.0500 (0.0500)  time: 1.0106  data: 0.0004  max mem: 78493
Epoch: [218]  [220/312]  eta: 0:01:40  lr: 0.000777  min_lr: 0.000777  loss: 2.1102 (2.0509)  weight_decay: 0.0500 (0.0500)  time: 1.0115  data: 0.0004  max mem: 78493
Epoch: [218]  [230/312]  eta: 0:01:29  lr: 0.000776  min_lr: 0.000776  loss: 2.1648 (2.0534)  weight_decay: 0.0500 (0.0500)  time: 1.0107  data: 0.0005  max mem: 78493
Epoch: [218]  [240/312]  eta: 0:01:18  lr: 0.000776  min_lr: 0.000776  loss: 2.1648 (2.0561)  weight_decay: 0.0500 (0.0500)  time: 1.0089  data: 0.0005  max mem: 78493
Epoch: [218]  [250/312]  eta: 0:01:07  lr: 0.000775  min_lr: 0.000775  loss: 2.1970 (2.0592)  weight_decay: 0.0500 (0.0500)  time: 1.0096  data: 0.0005  max mem: 78493
Epoch: [218]  [260/312]  eta: 0:00:56  lr: 0.000774  min_lr: 0.000774  loss: 2.1482 (2.0601)  weight_decay: 0.0500 (0.0500)  time: 1.0091  data: 0.0005  max mem: 78493
Epoch: [218]  [270/312]  eta: 0:00:45  lr: 0.000774  min_lr: 0.000774  loss: 1.9893 (2.0551)  weight_decay: 0.0500 (0.0500)  time: 1.0086  data: 0.0005  max mem: 78493
Epoch: [218]  [280/312]  eta: 0:00:34  lr: 0.000773  min_lr: 0.000773  loss: 1.9893 (2.0535)  weight_decay: 0.0500 (0.0500)  time: 1.0114  data: 0.0017  max mem: 78493
Epoch: [218]  [290/312]  eta: 0:00:23  lr: 0.000773  min_lr: 0.000773  loss: 2.0920 (2.0551)  weight_decay: 0.0500 (0.0500)  time: 1.0070  data: 0.0015  max mem: 78493
Epoch: [218]  [300/312]  eta: 0:00:12  lr: 0.000772  min_lr: 0.000772  loss: 2.1589 (2.0595)  weight_decay: 0.0500 (0.0500)  time: 1.0014  data: 0.0001  max mem: 78493
Epoch: [218]  [310/312]  eta: 0:00:02  lr: 0.000772  min_lr: 0.000772  loss: 2.1589 (2.0610)  weight_decay: 0.0500 (0.0500)  time: 1.0014  data: 0.0001  max mem: 78493
Epoch: [218]  [311/312]  eta: 0:00:01  lr: 0.000772  min_lr: 0.000772  loss: 2.1408 (2.0610)  weight_decay: 0.0500 (0.0500)  time: 1.0013  data: 0.0001  max mem: 78493
Epoch: [218] Total time: 0:05:35 (1.0750 s / it)
Averaged stats: lr: 0.000772  min_lr: 0.000772  loss: 2.1408 (2.0313)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:15  loss: 0.5612 (0.5612)  acc1: 85.8073 (85.8073)  acc5: 97.2656 (97.2656)  time: 8.4364  data: 8.1711  max mem: 78493
Test:  [8/9]  eta: 0:00:01  loss: 0.8618 (0.7685)  acc1: 78.5156 (79.6160)  acc5: 95.1823 (95.1360)  time: 1.1385  data: 0.9080  max mem: 78493
Test: Total time: 0:00:10 (1.1534 s / it)
* Acc@1 80.150 Acc@5 95.012 loss 0.759
Accuracy of the model on the 50000 test images: 80.2%
Max accuracy: 80.43%
Epoch: [219]  [  0/312]  eta: 1:27:07  lr: 0.000771  min_lr: 0.000771  loss: 2.2497 (2.2497)  weight_decay: 0.0500 (0.0500)  time: 16.7561  data: 15.4841  max mem: 78493
Epoch: [219]  [ 10/312]  eta: 0:13:09  lr: 0.000771  min_lr: 0.000771  loss: 2.0838 (2.0600)  weight_decay: 0.0500 (0.0500)  time: 2.6131  data: 1.4083  max mem: 78493
Epoch: [219]  [ 20/312]  eta: 0:09:02  lr: 0.000770  min_lr: 0.000770  loss: 2.0838 (2.1256)  weight_decay: 0.0500 (0.0500)  time: 1.1147  data: 0.0007  max mem: 78493
Epoch: [219]  [ 30/312]  eta: 0:07:26  lr: 0.000770  min_lr: 0.000770  loss: 2.1142 (2.0954)  weight_decay: 0.0500 (0.0500)  time: 1.0191  data: 0.0005  max mem: 78493
Epoch: [219]  [ 40/312]  eta: 0:06:32  lr: 0.000769  min_lr: 0.000769  loss: 2.1656 (2.0994)  weight_decay: 0.0500 (0.0500)  time: 1.0085  data: 0.0004  max mem: 78493
Epoch: [219]  [ 50/312]  eta: 0:05:55  lr: 0.000769  min_lr: 0.000769  loss: 2.1987 (2.1095)  weight_decay: 0.0500 (0.0500)  time: 1.0081  data: 0.0004  max mem: 78493
Epoch: [219]  [ 60/312]  eta: 0:05:27  lr: 0.000768  min_lr: 0.000768  loss: 2.1399 (2.1025)  weight_decay: 0.0500 (0.0500)  time: 1.0071  data: 0.0004  max mem: 78493
Epoch: [219]  [ 70/312]  eta: 0:05:04  lr: 0.000767  min_lr: 0.000767  loss: 2.1399 (2.0983)  weight_decay: 0.0500 (0.0500)  time: 1.0095  data: 0.0004  max mem: 78493
Epoch: [219]  [ 80/312]  eta: 0:04:45  lr: 0.000767  min_lr: 0.000767  loss: 2.1651 (2.0984)  weight_decay: 0.0500 (0.0500)  time: 1.0110  data: 0.0004  max mem: 78493
Epoch: [219]  [ 90/312]  eta: 0:04:27  lr: 0.000766  min_lr: 0.000766  loss: 2.1769 (2.0839)  weight_decay: 0.0500 (0.0500)  time: 1.0086  data: 0.0005  max mem: 78493
Epoch: [219]  [100/312]  eta: 0:04:11  lr: 0.000766  min_lr: 0.000766  loss: 1.9233 (2.0795)  weight_decay: 0.0500 (0.0500)  time: 1.0090  data: 0.0005  max mem: 78493
Epoch: [219]  [110/312]  eta: 0:03:56  lr: 0.000765  min_lr: 0.000765  loss: 2.2527 (2.1012)  weight_decay: 0.0500 (0.0500)  time: 1.0084  data: 0.0004  max mem: 78493
Epoch: [219]  [120/312]  eta: 0:03:42  lr: 0.000765  min_lr: 0.000765  loss: 2.2744 (2.1008)  weight_decay: 0.0500 (0.0500)  time: 1.0077  data: 0.0004  max mem: 78493
Epoch: [219]  [130/312]  eta: 0:03:28  lr: 0.000764  min_lr: 0.000764  loss: 2.0769 (2.0848)  weight_decay: 0.0500 (0.0500)  time: 1.0086  data: 0.0004  max mem: 78493
Epoch: [219]  [140/312]  eta: 0:03:15  lr: 0.000764  min_lr: 0.000764  loss: 2.1917 (2.0930)  weight_decay: 0.0500 (0.0500)  time: 1.0062  data: 0.0004  max mem: 78493
Epoch: [219]  [150/312]  eta: 0:03:02  lr: 0.000763  min_lr: 0.000763  loss: 2.2667 (2.0887)  weight_decay: 0.0500 (0.0500)  time: 1.0063  data: 0.0005  max mem: 78493
Epoch: [219]  [160/312]  eta: 0:02:50  lr: 0.000762  min_lr: 0.000762  loss: 2.2016 (2.0832)  weight_decay: 0.0500 (0.0500)  time: 1.0067  data: 0.0005  max mem: 78493
Epoch: [219]  [170/312]  eta: 0:02:37  lr: 0.000762  min_lr: 0.000762  loss: 1.9336 (2.0682)  weight_decay: 0.0500 (0.0500)  time: 1.0063  data: 0.0004  max mem: 78493
Epoch: [219]  [180/312]  eta: 0:02:26  lr: 0.000761  min_lr: 0.000761  loss: 2.0408 (2.0654)  weight_decay: 0.0500 (0.0500)  time: 1.0065  data: 0.0004  max mem: 78493
Epoch: [219]  [190/312]  eta: 0:02:14  lr: 0.000761  min_lr: 0.000761  loss: 2.1090 (2.0571)  weight_decay: 0.0500 (0.0500)  time: 1.0052  data: 0.0011  max mem: 78493
Epoch: [219]  [200/312]  eta: 0:02:02  lr: 0.000760  min_lr: 0.000760  loss: 2.1393 (2.0639)  weight_decay: 0.0500 (0.0500)  time: 1.0044  data: 0.0011  max mem: 78493
Epoch: [219]  [210/312]  eta: 0:01:51  lr: 0.000760  min_lr: 0.000760  loss: 2.1568 (2.0628)  weight_decay: 0.0500 (0.0500)  time: 1.0057  data: 0.0005  max mem: 78493
Epoch: [219]  [220/312]  eta: 0:01:40  lr: 0.000759  min_lr: 0.000759  loss: 2.1498 (2.0666)  weight_decay: 0.0500 (0.0500)  time: 1.0069  data: 0.0005  max mem: 78493
Epoch: [219]  [230/312]  eta: 0:01:28  lr: 0.000758  min_lr: 0.000758  loss: 2.1460 (2.0665)  weight_decay: 0.0500 (0.0500)  time: 1.0076  data: 0.0005  max mem: 78493
Epoch: [219]  [240/312]  eta: 0:01:17  lr: 0.000758  min_lr: 0.000758  loss: 2.1713 (2.0735)  weight_decay: 0.0500 (0.0500)  time: 1.0075  data: 0.0004  max mem: 78493
Epoch: [219]  [250/312]  eta: 0:01:06  lr: 0.000757  min_lr: 0.000757  loss: 2.1180 (2.0653)  weight_decay: 0.0500 (0.0500)  time: 1.0065  data: 0.0004  max mem: 78493
Epoch: [219]  [260/312]  eta: 0:00:55  lr: 0.000757  min_lr: 0.000757  loss: 1.8442 (2.0639)  weight_decay: 0.0500 (0.0500)  time: 1.0056  data: 0.0004  max mem: 78493
Epoch: [219]  [270/312]  eta: 0:00:45  lr: 0.000756  min_lr: 0.000756  loss: 2.1699 (2.0641)  weight_decay: 0.0500 (0.0500)  time: 1.0055  data: 0.0004  max mem: 78493
Epoch: [219]  [280/312]  eta: 0:00:34  lr: 0.000756  min_lr: 0.000756  loss: 2.1035 (2.0600)  weight_decay: 0.0500 (0.0500)  time: 1.0070  data: 0.0010  max mem: 78493
Epoch: [219]  [290/312]  eta: 0:00:23  lr: 0.000755  min_lr: 0.000755  loss: 2.1220 (2.0616)  weight_decay: 0.0500 (0.0500)  time: 1.0049  data: 0.0009  max mem: 78493
Epoch: [219]  [300/312]  eta: 0:00:12  lr: 0.000755  min_lr: 0.000755  loss: 2.2282 (2.0639)  weight_decay: 0.0500 (0.0500)  time: 1.0015  data: 0.0001  max mem: 78493
Epoch: [219]  [310/312]  eta: 0:00:02  lr: 0.000754  min_lr: 0.000754  loss: 1.8974 (2.0580)  weight_decay: 0.0500 (0.0500)  time: 1.0015  data: 0.0001  max mem: 78493
Epoch: [219]  [311/312]  eta: 0:00:01  lr: 0.000754  min_lr: 0.000754  loss: 1.8848 (2.0573)  weight_decay: 0.0500 (0.0500)  time: 1.0015  data: 0.0001  max mem: 78493
Epoch: [219] Total time: 0:05:33 (1.0697 s / it)
Averaged stats: lr: 0.000754  min_lr: 0.000754  loss: 1.8848 (2.0281)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:13  loss: 0.5494 (0.5494)  acc1: 86.0677 (86.0677)  acc5: 97.6562 (97.6562)  time: 8.1582  data: 7.8945  max mem: 78493
Test:  [8/9]  eta: 0:00:01  loss: 0.8304 (0.7550)  acc1: 78.2552 (79.9360)  acc5: 95.5729 (95.0560)  time: 1.1084  data: 0.8773  max mem: 78493
Test: Total time: 0:00:10 (1.1360 s / it)
* Acc@1 80.190 Acc@5 95.058 loss 0.747
Accuracy of the model on the 50000 test images: 80.2%
Max accuracy: 80.43%
Epoch: [220]  [  0/312]  eta: 1:25:30  lr: 0.000754  min_lr: 0.000754  loss: 2.2581 (2.2581)  weight_decay: 0.0500 (0.0500)  time: 16.4455  data: 14.9620  max mem: 78493
Epoch: [220]  [ 10/312]  eta: 0:13:05  lr: 0.000753  min_lr: 0.000753  loss: 2.2632 (2.1673)  weight_decay: 0.0500 (0.0500)  time: 2.6022  data: 1.3627  max mem: 78493
Epoch: [220]  [ 20/312]  eta: 0:09:02  lr: 0.000753  min_lr: 0.000753  loss: 2.1999 (2.1757)  weight_decay: 0.0500 (0.0500)  time: 1.1272  data: 0.0017  max mem: 78493
Epoch: [220]  [ 30/312]  eta: 0:07:26  lr: 0.000752  min_lr: 0.000752  loss: 2.1589 (2.1354)  weight_decay: 0.0500 (0.0500)  time: 1.0248  data: 0.0005  max mem: 78493
Epoch: [220]  [ 40/312]  eta: 0:06:32  lr: 0.000752  min_lr: 0.000752  loss: 2.0366 (2.0553)  weight_decay: 0.0500 (0.0500)  time: 1.0100  data: 0.0005  max mem: 78493
Epoch: [220]  [ 50/312]  eta: 0:05:55  lr: 0.000751  min_lr: 0.000751  loss: 2.0366 (2.0516)  weight_decay: 0.0500 (0.0500)  time: 1.0063  data: 0.0005  max mem: 78493
Epoch: [220]  [ 60/312]  eta: 0:05:27  lr: 0.000750  min_lr: 0.000750  loss: 2.0721 (2.0261)  weight_decay: 0.0500 (0.0500)  time: 1.0059  data: 0.0012  max mem: 78493
Epoch: [220]  [ 70/312]  eta: 0:05:04  lr: 0.000750  min_lr: 0.000750  loss: 2.0313 (2.0130)  weight_decay: 0.0500 (0.0500)  time: 1.0066  data: 0.0012  max mem: 78493
Epoch: [220]  [ 80/312]  eta: 0:04:44  lr: 0.000749  min_lr: 0.000749  loss: 2.1634 (2.0527)  weight_decay: 0.0500 (0.0500)  time: 1.0072  data: 0.0004  max mem: 78493
Epoch: [220]  [ 90/312]  eta: 0:04:27  lr: 0.000749  min_lr: 0.000749  loss: 2.2795 (2.0617)  weight_decay: 0.0500 (0.0500)  time: 1.0072  data: 0.0004  max mem: 78493
Epoch: [220]  [100/312]  eta: 0:04:11  lr: 0.000748  min_lr: 0.000748  loss: 2.1086 (2.0437)  weight_decay: 0.0500 (0.0500)  time: 1.0074  data: 0.0005  max mem: 78493
Epoch: [220]  [110/312]  eta: 0:03:56  lr: 0.000748  min_lr: 0.000748  loss: 1.9265 (2.0488)  weight_decay: 0.0500 (0.0500)  time: 1.0110  data: 0.0005  max mem: 78493
Epoch: [220]  [120/312]  eta: 0:03:41  lr: 0.000747  min_lr: 0.000747  loss: 2.0460 (2.0389)  weight_decay: 0.0500 (0.0500)  time: 1.0106  data: 0.0005  max mem: 78493
Epoch: [220]  [130/312]  eta: 0:03:28  lr: 0.000747  min_lr: 0.000747  loss: 1.9975 (2.0305)  weight_decay: 0.0500 (0.0500)  time: 1.0082  data: 0.0005  max mem: 78493
Epoch: [220]  [140/312]  eta: 0:03:15  lr: 0.000746  min_lr: 0.000746  loss: 1.9880 (2.0227)  weight_decay: 0.0500 (0.0500)  time: 1.0079  data: 0.0005  max mem: 78493
Epoch: [220]  [150/312]  eta: 0:03:02  lr: 0.000745  min_lr: 0.000745  loss: 1.9429 (2.0195)  weight_decay: 0.0500 (0.0500)  time: 1.0065  data: 0.0011  max mem: 78493
Epoch: [220]  [160/312]  eta: 0:02:50  lr: 0.000745  min_lr: 0.000745  loss: 2.0146 (2.0162)  weight_decay: 0.0500 (0.0500)  time: 1.0065  data: 0.0011  max mem: 78493
Epoch: [220]  [170/312]  eta: 0:02:37  lr: 0.000744  min_lr: 0.000744  loss: 2.0088 (2.0127)  weight_decay: 0.0500 (0.0500)  time: 1.0064  data: 0.0005  max mem: 78493
Epoch: [220]  [180/312]  eta: 0:02:26  lr: 0.000744  min_lr: 0.000744  loss: 2.0135 (2.0143)  weight_decay: 0.0500 (0.0500)  time: 1.0064  data: 0.0005  max mem: 78493
Epoch: [220]  [190/312]  eta: 0:02:14  lr: 0.000743  min_lr: 0.000743  loss: 2.1576 (2.0266)  weight_decay: 0.0500 (0.0500)  time: 1.0059  data: 0.0004  max mem: 78493
Epoch: [220]  [200/312]  eta: 0:02:02  lr: 0.000743  min_lr: 0.000743  loss: 2.1087 (2.0251)  weight_decay: 0.0500 (0.0500)  time: 1.0051  data: 0.0004  max mem: 78493
Epoch: [220]  [210/312]  eta: 0:01:51  lr: 0.000742  min_lr: 0.000742  loss: 2.0127 (2.0185)  weight_decay: 0.0500 (0.0500)  time: 1.0060  data: 0.0004  max mem: 78493
Epoch: [220]  [220/312]  eta: 0:01:40  lr: 0.000742  min_lr: 0.000742  loss: 2.0940 (2.0173)  weight_decay: 0.0500 (0.0500)  time: 1.0067  data: 0.0004  max mem: 78493
Epoch: [220]  [230/312]  eta: 0:01:28  lr: 0.000741  min_lr: 0.000741  loss: 2.0837 (2.0172)  weight_decay: 0.0500 (0.0500)  time: 1.0064  data: 0.0004  max mem: 78493
Epoch: [220]  [240/312]  eta: 0:01:17  lr: 0.000740  min_lr: 0.000740  loss: 1.8945 (2.0091)  weight_decay: 0.0500 (0.0500)  time: 1.0066  data: 0.0004  max mem: 78493
Epoch: [220]  [250/312]  eta: 0:01:06  lr: 0.000740  min_lr: 0.000740  loss: 2.1413 (2.0180)  weight_decay: 0.0500 (0.0500)  time: 1.0071  data: 0.0004  max mem: 78493
Epoch: [220]  [260/312]  eta: 0:00:55  lr: 0.000739  min_lr: 0.000739  loss: 2.2165 (2.0198)  weight_decay: 0.0500 (0.0500)  time: 1.0071  data: 0.0005  max mem: 78493
Epoch: [220]  [270/312]  eta: 0:00:45  lr: 0.000739  min_lr: 0.000739  loss: 2.0785 (2.0137)  weight_decay: 0.0500 (0.0500)  time: 1.0061  data: 0.0005  max mem: 78493
Epoch: [220]  [280/312]  eta: 0:00:34  lr: 0.000738  min_lr: 0.000738  loss: 2.0785 (2.0167)  weight_decay: 0.0500 (0.0500)  time: 1.0084  data: 0.0010  max mem: 78493
Epoch: [220]  [290/312]  eta: 0:00:23  lr: 0.000738  min_lr: 0.000738  loss: 2.2191 (2.0208)  weight_decay: 0.0500 (0.0500)  time: 1.0067  data: 0.0009  max mem: 78493
Epoch: [220]  [300/312]  eta: 0:00:12  lr: 0.000737  min_lr: 0.000737  loss: 2.1860 (2.0253)  weight_decay: 0.0500 (0.0500)  time: 1.0019  data: 0.0001  max mem: 78493
Epoch: [220]  [310/312]  eta: 0:00:02  lr: 0.000736  min_lr: 0.000736  loss: 2.1378 (2.0232)  weight_decay: 0.0500 (0.0500)  time: 1.0016  data: 0.0001  max mem: 78493
Epoch: [220]  [311/312]  eta: 0:00:01  lr: 0.000736  min_lr: 0.000736  loss: 2.1480 (2.0237)  weight_decay: 0.0500 (0.0500)  time: 1.0015  data: 0.0001  max mem: 78493
Epoch: [220] Total time: 0:05:33 (1.0697 s / it)
Averaged stats: lr: 0.000736  min_lr: 0.000736  loss: 2.1480 (2.0167)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:16  loss: 0.5483 (0.5483)  acc1: 86.7188 (86.7188)  acc5: 97.6562 (97.6562)  time: 8.5541  data: 8.2881  max mem: 78493
Test:  [8/9]  eta: 0:00:01  loss: 0.8199 (0.7481)  acc1: 80.0781 (80.2560)  acc5: 94.9219 (95.2000)  time: 1.1503  data: 0.9210  max mem: 78493
Test: Total time: 0:00:10 (1.1875 s / it)
* Acc@1 80.418 Acc@5 95.200 loss 0.744
Accuracy of the model on the 50000 test images: 80.4%
Max accuracy: 80.43%
Epoch: [221]  [  0/312]  eta: 1:27:48  lr: 0.000736  min_lr: 0.000736  loss: 1.5188 (1.5188)  weight_decay: 0.0500 (0.0500)  time: 16.8860  data: 14.5683  max mem: 78493
Epoch: [221]  [ 10/312]  eta: 0:13:21  lr: 0.000736  min_lr: 0.000736  loss: 2.1060 (2.0897)  weight_decay: 0.0500 (0.0500)  time: 2.6526  data: 1.3564  max mem: 78493
Epoch: [221]  [ 20/312]  eta: 0:09:08  lr: 0.000735  min_lr: 0.000735  loss: 2.1398 (2.1076)  weight_decay: 0.0500 (0.0500)  time: 1.1266  data: 0.0179  max mem: 78493
Epoch: [221]  [ 30/312]  eta: 0:07:30  lr: 0.000735  min_lr: 0.000735  loss: 2.1260 (2.0633)  weight_decay: 0.0500 (0.0500)  time: 1.0181  data: 0.0005  max mem: 78493
Epoch: [221]  [ 40/312]  eta: 0:06:35  lr: 0.000734  min_lr: 0.000734  loss: 1.9325 (2.0621)  weight_decay: 0.0500 (0.0500)  time: 1.0106  data: 0.0004  max mem: 78493
Epoch: [221]  [ 50/312]  eta: 0:05:58  lr: 0.000734  min_lr: 0.000734  loss: 1.9509 (2.0621)  weight_decay: 0.0500 (0.0500)  time: 1.0086  data: 0.0004  max mem: 78493
Epoch: [221]  [ 60/312]  eta: 0:05:29  lr: 0.000733  min_lr: 0.000733  loss: 2.1480 (2.0620)  weight_decay: 0.0500 (0.0500)  time: 1.0081  data: 0.0005  max mem: 78493
Epoch: [221]  [ 70/312]  eta: 0:05:06  lr: 0.000732  min_lr: 0.000732  loss: 2.1049 (2.0502)  weight_decay: 0.0500 (0.0500)  time: 1.0080  data: 0.0018  max mem: 78493
Epoch: [221]  [ 80/312]  eta: 0:04:46  lr: 0.000732  min_lr: 0.000732  loss: 2.0036 (2.0474)  weight_decay: 0.0500 (0.0500)  time: 1.0069  data: 0.0018  max mem: 78493
Epoch: [221]  [ 90/312]  eta: 0:04:28  lr: 0.000731  min_lr: 0.000731  loss: 1.9124 (2.0180)  weight_decay: 0.0500 (0.0500)  time: 1.0074  data: 0.0004  max mem: 78493
Epoch: [221]  [100/312]  eta: 0:04:12  lr: 0.000731  min_lr: 0.000731  loss: 1.9885 (2.0317)  weight_decay: 0.0500 (0.0500)  time: 1.0117  data: 0.0014  max mem: 78493
Epoch: [221]  [110/312]  eta: 0:03:57  lr: 0.000730  min_lr: 0.000730  loss: 2.2387 (2.0512)  weight_decay: 0.0500 (0.0500)  time: 1.0122  data: 0.0014  max mem: 78493
Epoch: [221]  [120/312]  eta: 0:03:42  lr: 0.000730  min_lr: 0.000730  loss: 2.1634 (2.0358)  weight_decay: 0.0500 (0.0500)  time: 1.0091  data: 0.0004  max mem: 78493
Epoch: [221]  [130/312]  eta: 0:03:29  lr: 0.000729  min_lr: 0.000729  loss: 1.8652 (2.0232)  weight_decay: 0.0500 (0.0500)  time: 1.0106  data: 0.0004  max mem: 78493
Epoch: [221]  [140/312]  eta: 0:03:15  lr: 0.000729  min_lr: 0.000729  loss: 1.7321 (2.0091)  weight_decay: 0.0500 (0.0500)  time: 1.0103  data: 0.0004  max mem: 78493
Epoch: [221]  [150/312]  eta: 0:03:03  lr: 0.000728  min_lr: 0.000728  loss: 1.8725 (2.0105)  weight_decay: 0.0500 (0.0500)  time: 1.0079  data: 0.0004  max mem: 78493
Epoch: [221]  [160/312]  eta: 0:02:50  lr: 0.000727  min_lr: 0.000727  loss: 1.9864 (2.0089)  weight_decay: 0.0500 (0.0500)  time: 1.0082  data: 0.0004  max mem: 78493
Epoch: [221]  [170/312]  eta: 0:02:38  lr: 0.000727  min_lr: 0.000727  loss: 1.9206 (2.0070)  weight_decay: 0.0500 (0.0500)  time: 1.0095  data: 0.0005  max mem: 78493
Epoch: [221]  [180/312]  eta: 0:02:26  lr: 0.000726  min_lr: 0.000726  loss: 2.0082 (2.0050)  weight_decay: 0.0500 (0.0500)  time: 1.0094  data: 0.0004  max mem: 78493
Epoch: [221]  [190/312]  eta: 0:02:14  lr: 0.000726  min_lr: 0.000726  loss: 1.9778 (2.0002)  weight_decay: 0.0500 (0.0500)  time: 1.0091  data: 0.0004  max mem: 78493
Epoch: [221]  [200/312]  eta: 0:02:03  lr: 0.000725  min_lr: 0.000725  loss: 1.9778 (2.0025)  weight_decay: 0.0500 (0.0500)  time: 1.0105  data: 0.0004  max mem: 78493
Epoch: [221]  [210/312]  eta: 0:01:51  lr: 0.000725  min_lr: 0.000725  loss: 2.0527 (2.0019)  weight_decay: 0.0500 (0.0500)  time: 1.0084  data: 0.0004  max mem: 78493
Epoch: [221]  [220/312]  eta: 0:01:40  lr: 0.000724  min_lr: 0.000724  loss: 2.0552 (2.0032)  weight_decay: 0.0500 (0.0500)  time: 1.0077  data: 0.0004  max mem: 78493
Epoch: [221]  [230/312]  eta: 0:01:29  lr: 0.000724  min_lr: 0.000724  loss: 2.0815 (2.0085)  weight_decay: 0.0500 (0.0500)  time: 1.0095  data: 0.0004  max mem: 78493
Epoch: [221]  [240/312]  eta: 0:01:18  lr: 0.000723  min_lr: 0.000723  loss: 2.0067 (2.0044)  weight_decay: 0.0500 (0.0500)  time: 1.0102  data: 0.0004  max mem: 78493
Epoch: [221]  [250/312]  eta: 0:01:07  lr: 0.000722  min_lr: 0.000722  loss: 2.0067 (2.0060)  weight_decay: 0.0500 (0.0500)  time: 1.0096  data: 0.0014  max mem: 78493
Epoch: [221]  [260/312]  eta: 0:00:56  lr: 0.000722  min_lr: 0.000722  loss: 2.0017 (2.0052)  weight_decay: 0.0500 (0.0500)  time: 1.0088  data: 0.0014  max mem: 78493
Epoch: [221]  [270/312]  eta: 0:00:45  lr: 0.000721  min_lr: 0.000721  loss: 2.1218 (2.0118)  weight_decay: 0.0500 (0.0500)  time: 1.0097  data: 0.0004  max mem: 78493
Epoch: [221]  [280/312]  eta: 0:00:34  lr: 0.000721  min_lr: 0.000721  loss: 2.1726 (2.0115)  weight_decay: 0.0500 (0.0500)  time: 1.0099  data: 0.0018  max mem: 78493
Epoch: [221]  [290/312]  eta: 0:00:23  lr: 0.000720  min_lr: 0.000720  loss: 2.0519 (2.0053)  weight_decay: 0.0500 (0.0500)  time: 1.0053  data: 0.0016  max mem: 78493
Epoch: [221]  [300/312]  eta: 0:00:12  lr: 0.000720  min_lr: 0.000720  loss: 1.8861 (2.0058)  weight_decay: 0.0500 (0.0500)  time: 1.0020  data: 0.0001  max mem: 78493
Epoch: [221]  [310/312]  eta: 0:00:02  lr: 0.000719  min_lr: 0.000719  loss: 1.8861 (2.0041)  weight_decay: 0.0500 (0.0500)  time: 1.0022  data: 0.0001  max mem: 78493
Epoch: [221]  [311/312]  eta: 0:00:01  lr: 0.000719  min_lr: 0.000719  loss: 1.8861 (2.0053)  weight_decay: 0.0500 (0.0500)  time: 1.0021  data: 0.0001  max mem: 78493
Epoch: [221] Total time: 0:05:34 (1.0728 s / it)
Averaged stats: lr: 0.000719  min_lr: 0.000719  loss: 1.8861 (2.0154)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:16  loss: 0.5534 (0.5534)  acc1: 86.0677 (86.0677)  acc5: 96.8750 (96.8750)  time: 8.5250  data: 8.2508  max mem: 78493
Test:  [8/9]  eta: 0:00:01  loss: 0.8313 (0.7631)  acc1: 78.6458 (79.7760)  acc5: 95.4427 (95.0720)  time: 1.1460  data: 0.9168  max mem: 78493
Test: Total time: 0:00:10 (1.1593 s / it)
* Acc@1 80.448 Acc@5 95.202 loss 0.743
Accuracy of the model on the 50000 test images: 80.4%
Max accuracy: 80.45%
Epoch: [222]  [  0/312]  eta: 1:17:54  lr: 0.000719  min_lr: 0.000719  loss: 2.0929 (2.0929)  weight_decay: 0.0500 (0.0500)  time: 14.9813  data: 13.4788  max mem: 78493
Epoch: [222]  [ 10/312]  eta: 0:12:50  lr: 0.000719  min_lr: 0.000719  loss: 2.0929 (2.0234)  weight_decay: 0.0500 (0.0500)  time: 2.5526  data: 1.3411  max mem: 78493
Epoch: [222]  [ 20/312]  eta: 0:08:51  lr: 0.000718  min_lr: 0.000718  loss: 1.9701 (1.9778)  weight_decay: 0.0500 (0.0500)  time: 1.1627  data: 0.0649  max mem: 78493
Epoch: [222]  [ 30/312]  eta: 0:07:19  lr: 0.000717  min_lr: 0.000717  loss: 2.0248 (2.0218)  weight_decay: 0.0500 (0.0500)  time: 1.0134  data: 0.0015  max mem: 78493
Epoch: [222]  [ 40/312]  eta: 0:06:27  lr: 0.000717  min_lr: 0.000717  loss: 2.1759 (2.0146)  weight_decay: 0.0500 (0.0500)  time: 1.0103  data: 0.0005  max mem: 78493
Epoch: [222]  [ 50/312]  eta: 0:05:52  lr: 0.000716  min_lr: 0.000716  loss: 2.0060 (1.9950)  weight_decay: 0.0500 (0.0500)  time: 1.0092  data: 0.0016  max mem: 78493
Epoch: [222]  [ 60/312]  eta: 0:05:24  lr: 0.000716  min_lr: 0.000716  loss: 2.0209 (2.0064)  weight_decay: 0.0500 (0.0500)  time: 1.0099  data: 0.0016  max mem: 78493
Epoch: [222]  [ 70/312]  eta: 0:05:02  lr: 0.000715  min_lr: 0.000715  loss: 2.0395 (2.0058)  weight_decay: 0.0500 (0.0500)  time: 1.0100  data: 0.0004  max mem: 78493
Epoch: [222]  [ 80/312]  eta: 0:04:43  lr: 0.000715  min_lr: 0.000715  loss: 2.0039 (2.0104)  weight_decay: 0.0500 (0.0500)  time: 1.0091  data: 0.0004  max mem: 78493
Epoch: [222]  [ 90/312]  eta: 0:04:25  lr: 0.000714  min_lr: 0.000714  loss: 2.0821 (2.0191)  weight_decay: 0.0500 (0.0500)  time: 1.0100  data: 0.0004  max mem: 78493
Epoch: [222]  [100/312]  eta: 0:04:09  lr: 0.000714  min_lr: 0.000714  loss: 2.1886 (2.0266)  weight_decay: 0.0500 (0.0500)  time: 1.0103  data: 0.0005  max mem: 78493
Epoch: [222]  [110/312]  eta: 0:03:54  lr: 0.000713  min_lr: 0.000713  loss: 2.1863 (2.0252)  weight_decay: 0.0500 (0.0500)  time: 1.0094  data: 0.0005  max mem: 78493
Epoch: [222]  [120/312]  eta: 0:03:40  lr: 0.000712  min_lr: 0.000712  loss: 2.0427 (2.0247)  weight_decay: 0.0500 (0.0500)  time: 1.0079  data: 0.0005  max mem: 78493
Epoch: [222]  [130/312]  eta: 0:03:27  lr: 0.000712  min_lr: 0.000712  loss: 2.0620 (2.0256)  weight_decay: 0.0500 (0.0500)  time: 1.0068  data: 0.0005  max mem: 78493
Epoch: [222]  [140/312]  eta: 0:03:14  lr: 0.000711  min_lr: 0.000711  loss: 1.8722 (2.0136)  weight_decay: 0.0500 (0.0500)  time: 1.0066  data: 0.0011  max mem: 78493
Epoch: [222]  [150/312]  eta: 0:03:01  lr: 0.000711  min_lr: 0.000711  loss: 1.8943 (2.0099)  weight_decay: 0.0500 (0.0500)  time: 1.0067  data: 0.0011  max mem: 78493
Epoch: [222]  [160/312]  eta: 0:02:49  lr: 0.000710  min_lr: 0.000710  loss: 2.1411 (2.0234)  weight_decay: 0.0500 (0.0500)  time: 1.0062  data: 0.0012  max mem: 78493
Epoch: [222]  [170/312]  eta: 0:02:37  lr: 0.000710  min_lr: 0.000710  loss: 2.2240 (2.0354)  weight_decay: 0.0500 (0.0500)  time: 1.0064  data: 0.0012  max mem: 78493
Epoch: [222]  [180/312]  eta: 0:02:25  lr: 0.000709  min_lr: 0.000709  loss: 2.1849 (2.0390)  weight_decay: 0.0500 (0.0500)  time: 1.0076  data: 0.0004  max mem: 78493
Epoch: [222]  [190/312]  eta: 0:02:13  lr: 0.000709  min_lr: 0.000709  loss: 2.1234 (2.0395)  weight_decay: 0.0500 (0.0500)  time: 1.0063  data: 0.0005  max mem: 78493
Epoch: [222]  [200/312]  eta: 0:02:02  lr: 0.000708  min_lr: 0.000708  loss: 2.0743 (2.0393)  weight_decay: 0.0500 (0.0500)  time: 1.0052  data: 0.0005  max mem: 78493
Epoch: [222]  [210/312]  eta: 0:01:51  lr: 0.000708  min_lr: 0.000708  loss: 2.0581 (2.0320)  weight_decay: 0.0500 (0.0500)  time: 1.0060  data: 0.0004  max mem: 78493
Epoch: [222]  [220/312]  eta: 0:01:39  lr: 0.000707  min_lr: 0.000707  loss: 2.0479 (2.0325)  weight_decay: 0.0500 (0.0500)  time: 1.0053  data: 0.0004  max mem: 78493
Epoch: [222]  [230/312]  eta: 0:01:28  lr: 0.000706  min_lr: 0.000706  loss: 2.0416 (2.0300)  weight_decay: 0.0500 (0.0500)  time: 1.0044  data: 0.0004  max mem: 78493
Epoch: [222]  [240/312]  eta: 0:01:17  lr: 0.000706  min_lr: 0.000706  loss: 1.8994 (2.0243)  weight_decay: 0.0500 (0.0500)  time: 1.0042  data: 0.0004  max mem: 78493
Epoch: [222]  [250/312]  eta: 0:01:06  lr: 0.000705  min_lr: 0.000705  loss: 1.9860 (2.0243)  weight_decay: 0.0500 (0.0500)  time: 1.0039  data: 0.0004  max mem: 78493
Epoch: [222]  [260/312]  eta: 0:00:55  lr: 0.000705  min_lr: 0.000705  loss: 2.0198 (2.0244)  weight_decay: 0.0500 (0.0500)  time: 1.0053  data: 0.0005  max mem: 78493
Epoch: [222]  [270/312]  eta: 0:00:44  lr: 0.000704  min_lr: 0.000704  loss: 1.9945 (2.0246)  weight_decay: 0.0500 (0.0500)  time: 1.0057  data: 0.0005  max mem: 78493
Epoch: [222]  [280/312]  eta: 0:00:34  lr: 0.000704  min_lr: 0.000704  loss: 1.9971 (2.0242)  weight_decay: 0.0500 (0.0500)  time: 1.0051  data: 0.0011  max mem: 78493
Epoch: [222]  [290/312]  eta: 0:00:23  lr: 0.000703  min_lr: 0.000703  loss: 2.0893 (2.0246)  weight_decay: 0.0500 (0.0500)  time: 1.0035  data: 0.0009  max mem: 78493
Epoch: [222]  [300/312]  eta: 0:00:12  lr: 0.000703  min_lr: 0.000703  loss: 2.0175 (2.0208)  weight_decay: 0.0500 (0.0500)  time: 1.0017  data: 0.0001  max mem: 78493
Epoch: [222]  [310/312]  eta: 0:00:02  lr: 0.000702  min_lr: 0.000702  loss: 1.7827 (2.0150)  weight_decay: 0.0500 (0.0500)  time: 1.0019  data: 0.0001  max mem: 78493
Epoch: [222]  [311/312]  eta: 0:00:01  lr: 0.000702  min_lr: 0.000702  loss: 1.8325 (2.0145)  weight_decay: 0.0500 (0.0500)  time: 1.0017  data: 0.0001  max mem: 78493
Epoch: [222] Total time: 0:05:32 (1.0672 s / it)
Averaged stats: lr: 0.000702  min_lr: 0.000702  loss: 1.8325 (2.0273)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:17  loss: 0.5360 (0.5360)  acc1: 85.2865 (85.2865)  acc5: 97.3958 (97.3958)  time: 8.5572  data: 8.2770  max mem: 78493
Test:  [8/9]  eta: 0:00:01  loss: 0.8319 (0.7655)  acc1: 80.3385 (80.4480)  acc5: 95.3125 (94.7840)  time: 1.1490  data: 0.9197  max mem: 78493
Test: Total time: 0:00:10 (1.1652 s / it)
* Acc@1 80.550 Acc@5 95.320 loss 0.744
Accuracy of the model on the 50000 test images: 80.6%
Max accuracy: 80.55%
Epoch: [223]  [  0/312]  eta: 1:24:14  lr: 0.000702  min_lr: 0.000702  loss: 1.8820 (1.8820)  weight_decay: 0.0500 (0.0500)  time: 16.2007  data: 13.1650  max mem: 78493
Epoch: [223]  [ 10/312]  eta: 0:12:50  lr: 0.000701  min_lr: 0.000701  loss: 1.8820 (1.8432)  weight_decay: 0.0500 (0.0500)  time: 2.5526  data: 1.3084  max mem: 78493
Epoch: [223]  [ 20/312]  eta: 0:08:51  lr: 0.000701  min_lr: 0.000701  loss: 2.0155 (1.9343)  weight_decay: 0.0500 (0.0500)  time: 1.0997  data: 0.0628  max mem: 78493
Epoch: [223]  [ 30/312]  eta: 0:07:18  lr: 0.000700  min_lr: 0.000700  loss: 2.0155 (1.9228)  weight_decay: 0.0500 (0.0500)  time: 1.0077  data: 0.0016  max mem: 78493
Epoch: [223]  [ 40/312]  eta: 0:06:26  lr: 0.000700  min_lr: 0.000700  loss: 2.0575 (1.9611)  weight_decay: 0.0500 (0.0500)  time: 1.0060  data: 0.0004  max mem: 78493
Epoch: [223]  [ 50/312]  eta: 0:05:51  lr: 0.000699  min_lr: 0.000699  loss: 2.0510 (1.9320)  weight_decay: 0.0500 (0.0500)  time: 1.0086  data: 0.0004  max mem: 78493
Epoch: [223]  [ 60/312]  eta: 0:05:24  lr: 0.000699  min_lr: 0.000699  loss: 1.9233 (1.9466)  weight_decay: 0.0500 (0.0500)  time: 1.0102  data: 0.0004  max mem: 78493
Epoch: [223]  [ 70/312]  eta: 0:05:02  lr: 0.000698  min_lr: 0.000698  loss: 1.9760 (1.9483)  weight_decay: 0.0500 (0.0500)  time: 1.0108  data: 0.0004  max mem: 78493
Epoch: [223]  [ 80/312]  eta: 0:04:42  lr: 0.000698  min_lr: 0.000698  loss: 1.9130 (1.9414)  weight_decay: 0.0500 (0.0500)  time: 1.0108  data: 0.0004  max mem: 78493
Epoch: [223]  [ 90/312]  eta: 0:04:25  lr: 0.000697  min_lr: 0.000697  loss: 1.9462 (1.9589)  weight_decay: 0.0500 (0.0500)  time: 1.0101  data: 0.0004  max mem: 78493
Epoch: [223]  [100/312]  eta: 0:04:09  lr: 0.000696  min_lr: 0.000696  loss: 2.0995 (1.9543)  weight_decay: 0.0500 (0.0500)  time: 1.0076  data: 0.0004  max mem: 78493
Epoch: [223]  [110/312]  eta: 0:03:54  lr: 0.000696  min_lr: 0.000696  loss: 2.0245 (1.9645)  weight_decay: 0.0500 (0.0500)  time: 1.0059  data: 0.0004  max mem: 78493
Epoch: [223]  [120/312]  eta: 0:03:40  lr: 0.000695  min_lr: 0.000695  loss: 2.0456 (1.9675)  weight_decay: 0.0500 (0.0500)  time: 1.0055  data: 0.0004  max mem: 78493
Epoch: [223]  [130/312]  eta: 0:03:27  lr: 0.000695  min_lr: 0.000695  loss: 2.0648 (1.9790)  weight_decay: 0.0500 (0.0500)  time: 1.0055  data: 0.0004  max mem: 78493
Epoch: [223]  [140/312]  eta: 0:03:14  lr: 0.000694  min_lr: 0.000694  loss: 2.1553 (1.9869)  weight_decay: 0.0500 (0.0500)  time: 1.0055  data: 0.0005  max mem: 78493
Epoch: [223]  [150/312]  eta: 0:03:01  lr: 0.000694  min_lr: 0.000694  loss: 1.9472 (1.9799)  weight_decay: 0.0500 (0.0500)  time: 1.0059  data: 0.0005  max mem: 78493
Epoch: [223]  [160/312]  eta: 0:02:49  lr: 0.000693  min_lr: 0.000693  loss: 2.0537 (1.9956)  weight_decay: 0.0500 (0.0500)  time: 1.0056  data: 0.0005  max mem: 78493
Epoch: [223]  [170/312]  eta: 0:02:37  lr: 0.000693  min_lr: 0.000693  loss: 2.2195 (2.0004)  weight_decay: 0.0500 (0.0500)  time: 1.0053  data: 0.0005  max mem: 78493
Epoch: [223]  [180/312]  eta: 0:02:25  lr: 0.000692  min_lr: 0.000692  loss: 2.0792 (2.0011)  weight_decay: 0.0500 (0.0500)  time: 1.0049  data: 0.0004  max mem: 78493
Epoch: [223]  [190/312]  eta: 0:02:13  lr: 0.000692  min_lr: 0.000692  loss: 2.1549 (2.0160)  weight_decay: 0.0500 (0.0500)  time: 1.0056  data: 0.0004  max mem: 78493
Epoch: [223]  [200/312]  eta: 0:02:02  lr: 0.000691  min_lr: 0.000691  loss: 2.1549 (2.0118)  weight_decay: 0.0500 (0.0500)  time: 1.0067  data: 0.0004  max mem: 78493
Epoch: [223]  [210/312]  eta: 0:01:50  lr: 0.000690  min_lr: 0.000690  loss: 1.9900 (2.0028)  weight_decay: 0.0500 (0.0500)  time: 1.0074  data: 0.0004  max mem: 78493
Epoch: [223]  [220/312]  eta: 0:01:39  lr: 0.000690  min_lr: 0.000690  loss: 2.0381 (2.0046)  weight_decay: 0.0500 (0.0500)  time: 1.0073  data: 0.0004  max mem: 78493
Epoch: [223]  [230/312]  eta: 0:01:28  lr: 0.000689  min_lr: 0.000689  loss: 2.1023 (2.0086)  weight_decay: 0.0500 (0.0500)  time: 1.0066  data: 0.0004  max mem: 78493
Epoch: [223]  [240/312]  eta: 0:01:17  lr: 0.000689  min_lr: 0.000689  loss: 2.0407 (2.0032)  weight_decay: 0.0500 (0.0500)  time: 1.0076  data: 0.0004  max mem: 78493
Epoch: [223]  [250/312]  eta: 0:01:06  lr: 0.000688  min_lr: 0.000688  loss: 1.9860 (2.0022)  weight_decay: 0.0500 (0.0500)  time: 1.0061  data: 0.0004  max mem: 78493
Epoch: [223]  [260/312]  eta: 0:00:55  lr: 0.000688  min_lr: 0.000688  loss: 2.0915 (2.0050)  weight_decay: 0.0500 (0.0500)  time: 1.0044  data: 0.0004  max mem: 78493
Epoch: [223]  [270/312]  eta: 0:00:44  lr: 0.000687  min_lr: 0.000687  loss: 2.1379 (2.0106)  weight_decay: 0.0500 (0.0500)  time: 1.0046  data: 0.0004  max mem: 78493
Epoch: [223]  [280/312]  eta: 0:00:34  lr: 0.000687  min_lr: 0.000687  loss: 2.0993 (2.0059)  weight_decay: 0.0500 (0.0500)  time: 1.0058  data: 0.0010  max mem: 78493
Epoch: [223]  [290/312]  eta: 0:00:23  lr: 0.000686  min_lr: 0.000686  loss: 2.0993 (2.0075)  weight_decay: 0.0500 (0.0500)  time: 1.0039  data: 0.0009  max mem: 78493
Epoch: [223]  [300/312]  eta: 0:00:12  lr: 0.000686  min_lr: 0.000686  loss: 1.9067 (1.9953)  weight_decay: 0.0500 (0.0500)  time: 1.0009  data: 0.0001  max mem: 78493
Epoch: [223]  [310/312]  eta: 0:00:02  lr: 0.000685  min_lr: 0.000685  loss: 1.6898 (1.9969)  weight_decay: 0.0500 (0.0500)  time: 1.0010  data: 0.0001  max mem: 78493
Epoch: [223]  [311/312]  eta: 0:00:01  lr: 0.000685  min_lr: 0.000685  loss: 1.6898 (1.9962)  weight_decay: 0.0500 (0.0500)  time: 1.0010  data: 0.0001  max mem: 78493
Epoch: [223] Total time: 0:05:32 (1.0665 s / it)
Averaged stats: lr: 0.000685  min_lr: 0.000685  loss: 1.6898 (2.0184)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:16  loss: 0.5254 (0.5254)  acc1: 87.3698 (87.3698)  acc5: 97.3958 (97.3958)  time: 8.4727  data: 8.1921  max mem: 78493
Test:  [8/9]  eta: 0:00:01  loss: 0.8154 (0.7439)  acc1: 79.5573 (80.4480)  acc5: 95.9635 (95.1520)  time: 1.1396  data: 0.9103  max mem: 78493
Test: Total time: 0:00:10 (1.1685 s / it)
* Acc@1 80.710 Acc@5 95.232 loss 0.735
Accuracy of the model on the 50000 test images: 80.7%
Max accuracy: 80.71%
Epoch: [224]  [  0/312]  eta: 1:27:38  lr: 0.000685  min_lr: 0.000685  loss: 2.2075 (2.2075)  weight_decay: 0.0500 (0.0500)  time: 16.8537  data: 15.8045  max mem: 78493
Epoch: [224]  [ 10/312]  eta: 0:13:25  lr: 0.000684  min_lr: 0.000684  loss: 2.0907 (2.0078)  weight_decay: 0.0500 (0.0500)  time: 2.6658  data: 1.4429  max mem: 78493
Epoch: [224]  [ 20/312]  eta: 0:09:08  lr: 0.000684  min_lr: 0.000684  loss: 2.0907 (2.0338)  weight_decay: 0.0500 (0.0500)  time: 1.1313  data: 0.0046  max mem: 78493
Epoch: [224]  [ 30/312]  eta: 0:07:30  lr: 0.000683  min_lr: 0.000683  loss: 2.1169 (2.0265)  weight_decay: 0.0500 (0.0500)  time: 1.0120  data: 0.0014  max mem: 78493
Epoch: [224]  [ 40/312]  eta: 0:06:35  lr: 0.000683  min_lr: 0.000683  loss: 2.1478 (2.0465)  weight_decay: 0.0500 (0.0500)  time: 1.0089  data: 0.0004  max mem: 78493
Epoch: [224]  [ 50/312]  eta: 0:05:58  lr: 0.000682  min_lr: 0.000682  loss: 2.1478 (2.0713)  weight_decay: 0.0500 (0.0500)  time: 1.0089  data: 0.0004  max mem: 78493
Epoch: [224]  [ 60/312]  eta: 0:05:29  lr: 0.000682  min_lr: 0.000682  loss: 1.9950 (2.0429)  weight_decay: 0.0500 (0.0500)  time: 1.0084  data: 0.0004  max mem: 78493
Epoch: [224]  [ 70/312]  eta: 0:05:06  lr: 0.000681  min_lr: 0.000681  loss: 1.9103 (2.0416)  weight_decay: 0.0500 (0.0500)  time: 1.0085  data: 0.0004  max mem: 78493
Epoch: [224]  [ 80/312]  eta: 0:04:46  lr: 0.000681  min_lr: 0.000681  loss: 1.9690 (2.0193)  weight_decay: 0.0500 (0.0500)  time: 1.0073  data: 0.0004  max mem: 78493
Epoch: [224]  [ 90/312]  eta: 0:04:28  lr: 0.000680  min_lr: 0.000680  loss: 1.9395 (2.0119)  weight_decay: 0.0500 (0.0500)  time: 1.0059  data: 0.0005  max mem: 78493
Epoch: [224]  [100/312]  eta: 0:04:12  lr: 0.000680  min_lr: 0.000680  loss: 1.8288 (1.9965)  weight_decay: 0.0500 (0.0500)  time: 1.0072  data: 0.0004  max mem: 78493
Epoch: [224]  [110/312]  eta: 0:03:56  lr: 0.000679  min_lr: 0.000679  loss: 1.8232 (1.9924)  weight_decay: 0.0500 (0.0500)  time: 1.0076  data: 0.0004  max mem: 78493
Epoch: [224]  [120/312]  eta: 0:03:42  lr: 0.000678  min_lr: 0.000678  loss: 1.7943 (1.9751)  weight_decay: 0.0500 (0.0500)  time: 1.0079  data: 0.0005  max mem: 78493
Epoch: [224]  [130/312]  eta: 0:03:28  lr: 0.000678  min_lr: 0.000678  loss: 2.0680 (1.9833)  weight_decay: 0.0500 (0.0500)  time: 1.0088  data: 0.0005  max mem: 78493
Epoch: [224]  [140/312]  eta: 0:03:15  lr: 0.000677  min_lr: 0.000677  loss: 2.0646 (1.9756)  weight_decay: 0.0500 (0.0500)  time: 1.0075  data: 0.0005  max mem: 78493
Epoch: [224]  [150/312]  eta: 0:03:02  lr: 0.000677  min_lr: 0.000677  loss: 1.8491 (1.9647)  weight_decay: 0.0500 (0.0500)  time: 1.0072  data: 0.0004  max mem: 78493
Epoch: [224]  [160/312]  eta: 0:02:50  lr: 0.000676  min_lr: 0.000676  loss: 2.0707 (1.9744)  weight_decay: 0.0500 (0.0500)  time: 1.0082  data: 0.0004  max mem: 78493
Epoch: [224]  [170/312]  eta: 0:02:38  lr: 0.000676  min_lr: 0.000676  loss: 2.0639 (1.9728)  weight_decay: 0.0500 (0.0500)  time: 1.0099  data: 0.0005  max mem: 78493
Epoch: [224]  [180/312]  eta: 0:02:26  lr: 0.000675  min_lr: 0.000675  loss: 1.9519 (1.9744)  weight_decay: 0.0500 (0.0500)  time: 1.0097  data: 0.0004  max mem: 78493
Epoch: [224]  [190/312]  eta: 0:02:14  lr: 0.000675  min_lr: 0.000675  loss: 2.1692 (1.9852)  weight_decay: 0.0500 (0.0500)  time: 1.0088  data: 0.0004  max mem: 78493
Epoch: [224]  [200/312]  eta: 0:02:03  lr: 0.000674  min_lr: 0.000674  loss: 2.1633 (1.9858)  weight_decay: 0.0500 (0.0500)  time: 1.0083  data: 0.0013  max mem: 78493
Epoch: [224]  [210/312]  eta: 0:01:51  lr: 0.000674  min_lr: 0.000674  loss: 1.8765 (1.9745)  weight_decay: 0.0500 (0.0500)  time: 1.0062  data: 0.0013  max mem: 78493
Epoch: [224]  [220/312]  eta: 0:01:40  lr: 0.000673  min_lr: 0.000673  loss: 1.8237 (1.9738)  weight_decay: 0.0500 (0.0500)  time: 1.0058  data: 0.0005  max mem: 78493
Epoch: [224]  [230/312]  eta: 0:01:29  lr: 0.000673  min_lr: 0.000673  loss: 2.0044 (1.9782)  weight_decay: 0.0500 (0.0500)  time: 1.0073  data: 0.0004  max mem: 78493
Epoch: [224]  [240/312]  eta: 0:01:18  lr: 0.000672  min_lr: 0.000672  loss: 2.0997 (1.9780)  weight_decay: 0.0500 (0.0500)  time: 1.0073  data: 0.0004  max mem: 78493
Epoch: [224]  [250/312]  eta: 0:01:07  lr: 0.000671  min_lr: 0.000671  loss: 1.7807 (1.9736)  weight_decay: 0.0500 (0.0500)  time: 1.0065  data: 0.0004  max mem: 78493
Epoch: [224]  [260/312]  eta: 0:00:56  lr: 0.000671  min_lr: 0.000671  loss: 1.8887 (1.9788)  weight_decay: 0.0500 (0.0500)  time: 1.0058  data: 0.0004  max mem: 78493
Epoch: [224]  [270/312]  eta: 0:00:45  lr: 0.000670  min_lr: 0.000670  loss: 2.1863 (1.9840)  weight_decay: 0.0500 (0.0500)  time: 1.0057  data: 0.0004  max mem: 78493
Epoch: [224]  [280/312]  eta: 0:00:34  lr: 0.000670  min_lr: 0.000670  loss: 2.0640 (1.9824)  weight_decay: 0.0500 (0.0500)  time: 1.0065  data: 0.0011  max mem: 78493
Epoch: [224]  [290/312]  eta: 0:00:23  lr: 0.000669  min_lr: 0.000669  loss: 1.8964 (1.9766)  weight_decay: 0.0500 (0.0500)  time: 1.0044  data: 0.0009  max mem: 78493
Epoch: [224]  [300/312]  eta: 0:00:12  lr: 0.000669  min_lr: 0.000669  loss: 1.9401 (1.9805)  weight_decay: 0.0500 (0.0500)  time: 1.0021  data: 0.0001  max mem: 78493
Epoch: [224]  [310/312]  eta: 0:00:02  lr: 0.000668  min_lr: 0.000668  loss: 2.1720 (1.9846)  weight_decay: 0.0500 (0.0500)  time: 1.0020  data: 0.0001  max mem: 78493
Epoch: [224]  [311/312]  eta: 0:00:01  lr: 0.000668  min_lr: 0.000668  loss: 2.1720 (1.9857)  weight_decay: 0.0500 (0.0500)  time: 1.0020  data: 0.0001  max mem: 78493
Epoch: [224] Total time: 0:05:34 (1.0711 s / it)
Averaged stats: lr: 0.000668  min_lr: 0.000668  loss: 2.1720 (2.0016)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:15  loss: 0.5283 (0.5283)  acc1: 85.9375 (85.9375)  acc5: 97.2656 (97.2656)  time: 8.3711  data: 8.0997  max mem: 78493
Test:  [8/9]  eta: 0:00:01  loss: 0.8057 (0.7488)  acc1: 78.9062 (80.4000)  acc5: 96.0938 (95.2800)  time: 1.1283  data: 0.9000  max mem: 78493
Test: Total time: 0:00:10 (1.1511 s / it)
* Acc@1 80.684 Acc@5 95.238 loss 0.732
Accuracy of the model on the 50000 test images: 80.7%
Max accuracy: 80.71%
Epoch: [225]  [  0/312]  eta: 1:27:01  lr: 0.000668  min_lr: 0.000668  loss: 1.9414 (1.9414)  weight_decay: 0.0500 (0.0500)  time: 16.7364  data: 12.9205  max mem: 78493
Epoch: [225]  [ 10/312]  eta: 0:13:22  lr: 0.000668  min_lr: 0.000668  loss: 2.0668 (2.0349)  weight_decay: 0.0500 (0.0500)  time: 2.6578  data: 1.2746  max mem: 78493
Epoch: [225]  [ 20/312]  eta: 0:09:09  lr: 0.000667  min_lr: 0.000667  loss: 2.0546 (1.9773)  weight_decay: 0.0500 (0.0500)  time: 1.1377  data: 0.0553  max mem: 78493
Epoch: [225]  [ 30/312]  eta: 0:07:31  lr: 0.000667  min_lr: 0.000667  loss: 1.8505 (1.9306)  weight_decay: 0.0500 (0.0500)  time: 1.0175  data: 0.0005  max mem: 78493
Epoch: [225]  [ 40/312]  eta: 0:06:35  lr: 0.000666  min_lr: 0.000666  loss: 1.9949 (1.9722)  weight_decay: 0.0500 (0.0500)  time: 1.0083  data: 0.0005  max mem: 78493
Epoch: [225]  [ 50/312]  eta: 0:05:58  lr: 0.000665  min_lr: 0.000665  loss: 2.0244 (1.9557)  weight_decay: 0.0500 (0.0500)  time: 1.0075  data: 0.0005  max mem: 78493
Epoch: [225]  [ 60/312]  eta: 0:05:29  lr: 0.000665  min_lr: 0.000665  loss: 1.8881 (1.9419)  weight_decay: 0.0500 (0.0500)  time: 1.0070  data: 0.0005  max mem: 78493
Epoch: [225]  [ 70/312]  eta: 0:05:06  lr: 0.000664  min_lr: 0.000664  loss: 2.1022 (1.9660)  weight_decay: 0.0500 (0.0500)  time: 1.0073  data: 0.0005  max mem: 78493
Epoch: [225]  [ 80/312]  eta: 0:04:46  lr: 0.000664  min_lr: 0.000664  loss: 2.0986 (1.9461)  weight_decay: 0.0500 (0.0500)  time: 1.0065  data: 0.0004  max mem: 78493
Epoch: [225]  [ 90/312]  eta: 0:04:28  lr: 0.000663  min_lr: 0.000663  loss: 1.9882 (1.9624)  weight_decay: 0.0500 (0.0500)  time: 1.0047  data: 0.0005  max mem: 78493
Epoch: [225]  [100/312]  eta: 0:04:11  lr: 0.000663  min_lr: 0.000663  loss: 2.1772 (1.9814)  weight_decay: 0.0500 (0.0500)  time: 1.0063  data: 0.0005  max mem: 78493
Epoch: [225]  [110/312]  eta: 0:03:56  lr: 0.000662  min_lr: 0.000662  loss: 1.9308 (1.9719)  weight_decay: 0.0500 (0.0500)  time: 1.0065  data: 0.0004  max mem: 78493
Epoch: [225]  [120/312]  eta: 0:03:42  lr: 0.000662  min_lr: 0.000662  loss: 1.8842 (1.9712)  weight_decay: 0.0500 (0.0500)  time: 1.0050  data: 0.0004  max mem: 78493
Epoch: [225]  [130/312]  eta: 0:03:28  lr: 0.000661  min_lr: 0.000661  loss: 2.1154 (1.9752)  weight_decay: 0.0500 (0.0500)  time: 1.0057  data: 0.0005  max mem: 78493
Epoch: [225]  [140/312]  eta: 0:03:15  lr: 0.000661  min_lr: 0.000661  loss: 2.1154 (1.9846)  weight_decay: 0.0500 (0.0500)  time: 1.0078  data: 0.0005  max mem: 78493
Epoch: [225]  [150/312]  eta: 0:03:02  lr: 0.000660  min_lr: 0.000660  loss: 2.2178 (1.9956)  weight_decay: 0.0500 (0.0500)  time: 1.0080  data: 0.0004  max mem: 78493
Epoch: [225]  [160/312]  eta: 0:02:50  lr: 0.000660  min_lr: 0.000660  loss: 2.2166 (1.9945)  weight_decay: 0.0500 (0.0500)  time: 1.0065  data: 0.0004  max mem: 78493
Epoch: [225]  [170/312]  eta: 0:02:38  lr: 0.000659  min_lr: 0.000659  loss: 2.0133 (1.9918)  weight_decay: 0.0500 (0.0500)  time: 1.0060  data: 0.0004  max mem: 78493
Epoch: [225]  [180/312]  eta: 0:02:26  lr: 0.000659  min_lr: 0.000659  loss: 2.0754 (2.0029)  weight_decay: 0.0500 (0.0500)  time: 1.0063  data: 0.0004  max mem: 78493
Epoch: [225]  [190/312]  eta: 0:02:14  lr: 0.000658  min_lr: 0.000658  loss: 2.1463 (2.0080)  weight_decay: 0.0500 (0.0500)  time: 1.0063  data: 0.0004  max mem: 78493
Epoch: [225]  [200/312]  eta: 0:02:02  lr: 0.000657  min_lr: 0.000657  loss: 2.1264 (2.0062)  weight_decay: 0.0500 (0.0500)  time: 1.0053  data: 0.0005  max mem: 78493
Epoch: [225]  [210/312]  eta: 0:01:51  lr: 0.000657  min_lr: 0.000657  loss: 2.0919 (2.0123)  weight_decay: 0.0500 (0.0500)  time: 1.0044  data: 0.0005  max mem: 78493
Epoch: [225]  [220/312]  eta: 0:01:40  lr: 0.000656  min_lr: 0.000656  loss: 2.1087 (2.0146)  weight_decay: 0.0500 (0.0500)  time: 1.0052  data: 0.0004  max mem: 78493
Epoch: [225]  [230/312]  eta: 0:01:29  lr: 0.000656  min_lr: 0.000656  loss: 1.9963 (2.0091)  weight_decay: 0.0500 (0.0500)  time: 1.0053  data: 0.0004  max mem: 78493
Epoch: [225]  [240/312]  eta: 0:01:17  lr: 0.000655  min_lr: 0.000655  loss: 1.9183 (2.0067)  weight_decay: 0.0500 (0.0500)  time: 1.0056  data: 0.0012  max mem: 78493
Epoch: [225]  [250/312]  eta: 0:01:06  lr: 0.000655  min_lr: 0.000655  loss: 2.0234 (2.0088)  weight_decay: 0.0500 (0.0500)  time: 1.0066  data: 0.0012  max mem: 78493
Epoch: [225]  [260/312]  eta: 0:00:55  lr: 0.000654  min_lr: 0.000654  loss: 2.0651 (2.0100)  weight_decay: 0.0500 (0.0500)  time: 1.0062  data: 0.0004  max mem: 78493
Epoch: [225]  [270/312]  eta: 0:00:45  lr: 0.000654  min_lr: 0.000654  loss: 2.1970 (2.0098)  weight_decay: 0.0500 (0.0500)  time: 1.0067  data: 0.0004  max mem: 78493
Epoch: [225]  [280/312]  eta: 0:00:34  lr: 0.000653  min_lr: 0.000653  loss: 2.2042 (2.0110)  weight_decay: 0.0500 (0.0500)  time: 1.0062  data: 0.0010  max mem: 78493
Epoch: [225]  [290/312]  eta: 0:00:23  lr: 0.000653  min_lr: 0.000653  loss: 2.0839 (2.0079)  weight_decay: 0.0500 (0.0500)  time: 1.0029  data: 0.0009  max mem: 78493
Epoch: [225]  [300/312]  eta: 0:00:12  lr: 0.000652  min_lr: 0.000652  loss: 1.9852 (2.0063)  weight_decay: 0.0500 (0.0500)  time: 1.0011  data: 0.0001  max mem: 78493
Epoch: [225]  [310/312]  eta: 0:00:02  lr: 0.000652  min_lr: 0.000652  loss: 1.9852 (2.0060)  weight_decay: 0.0500 (0.0500)  time: 1.0011  data: 0.0001  max mem: 78493
Epoch: [225]  [311/312]  eta: 0:00:01  lr: 0.000652  min_lr: 0.000652  loss: 1.9852 (2.0053)  weight_decay: 0.0500 (0.0500)  time: 1.0012  data: 0.0001  max mem: 78493
Epoch: [225] Total time: 0:05:33 (1.0704 s / it)
Averaged stats: lr: 0.000652  min_lr: 0.000652  loss: 1.9852 (2.0122)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:12  loss: 0.5210 (0.5210)  acc1: 87.3698 (87.3698)  acc5: 97.6562 (97.6562)  time: 8.0292  data: 7.7367  max mem: 78493
Test:  [8/9]  eta: 0:00:01  loss: 0.8107 (0.7415)  acc1: 80.8594 (80.7360)  acc5: 96.3542 (95.1360)  time: 1.0904  data: 0.8597  max mem: 78493
Test: Total time: 0:00:09 (1.0998 s / it)
* Acc@1 80.858 Acc@5 95.302 loss 0.726
Accuracy of the model on the 50000 test images: 80.9%
Max accuracy: 80.86%
Epoch: [226]  [  0/312]  eta: 1:27:10  lr: 0.000651  min_lr: 0.000651  loss: 2.0944 (2.0944)  weight_decay: 0.0500 (0.0500)  time: 16.7657  data: 15.7698  max mem: 78493
Epoch: [226]  [ 10/312]  eta: 0:13:14  lr: 0.000651  min_lr: 0.000651  loss: 2.1389 (2.1114)  weight_decay: 0.0500 (0.0500)  time: 2.6313  data: 1.4343  max mem: 78493
Epoch: [226]  [ 20/312]  eta: 0:09:03  lr: 0.000650  min_lr: 0.000650  loss: 2.1389 (2.1342)  weight_decay: 0.0500 (0.0500)  time: 1.1143  data: 0.0006  max mem: 78493
Epoch: [226]  [ 30/312]  eta: 0:07:26  lr: 0.000650  min_lr: 0.000650  loss: 2.1438 (2.1312)  weight_decay: 0.0500 (0.0500)  time: 1.0094  data: 0.0005  max mem: 78493
Epoch: [226]  [ 40/312]  eta: 0:06:32  lr: 0.000649  min_lr: 0.000649  loss: 2.1247 (2.0704)  weight_decay: 0.0500 (0.0500)  time: 1.0065  data: 0.0005  max mem: 78493
Epoch: [226]  [ 50/312]  eta: 0:05:55  lr: 0.000649  min_lr: 0.000649  loss: 2.0576 (2.0641)  weight_decay: 0.0500 (0.0500)  time: 1.0057  data: 0.0004  max mem: 78493
Epoch: [226]  [ 60/312]  eta: 0:05:27  lr: 0.000648  min_lr: 0.000648  loss: 2.0672 (2.0613)  weight_decay: 0.0500 (0.0500)  time: 1.0068  data: 0.0004  max mem: 78493
Epoch: [226]  [ 70/312]  eta: 0:05:04  lr: 0.000648  min_lr: 0.000648  loss: 2.0188 (2.0364)  weight_decay: 0.0500 (0.0500)  time: 1.0090  data: 0.0004  max mem: 78493
Epoch: [226]  [ 80/312]  eta: 0:04:45  lr: 0.000647  min_lr: 0.000647  loss: 1.9799 (2.0326)  weight_decay: 0.0500 (0.0500)  time: 1.0097  data: 0.0005  max mem: 78493
Epoch: [226]  [ 90/312]  eta: 0:04:27  lr: 0.000647  min_lr: 0.000647  loss: 2.1518 (2.0486)  weight_decay: 0.0500 (0.0500)  time: 1.0089  data: 0.0006  max mem: 78493
Epoch: [226]  [100/312]  eta: 0:04:11  lr: 0.000646  min_lr: 0.000646  loss: 2.1826 (2.0464)  weight_decay: 0.0500 (0.0500)  time: 1.0105  data: 0.0006  max mem: 78493
Epoch: [226]  [110/312]  eta: 0:03:56  lr: 0.000646  min_lr: 0.000646  loss: 2.1022 (2.0405)  weight_decay: 0.0500 (0.0500)  time: 1.0101  data: 0.0005  max mem: 78493
Epoch: [226]  [120/312]  eta: 0:03:41  lr: 0.000645  min_lr: 0.000645  loss: 2.1022 (2.0362)  weight_decay: 0.0500 (0.0500)  time: 1.0069  data: 0.0005  max mem: 78493
Epoch: [226]  [130/312]  eta: 0:03:28  lr: 0.000645  min_lr: 0.000645  loss: 2.1213 (2.0366)  weight_decay: 0.0500 (0.0500)  time: 1.0068  data: 0.0005  max mem: 78493
Epoch: [226]  [140/312]  eta: 0:03:15  lr: 0.000644  min_lr: 0.000644  loss: 2.1374 (2.0333)  weight_decay: 0.0500 (0.0500)  time: 1.0085  data: 0.0004  max mem: 78493
Epoch: [226]  [150/312]  eta: 0:03:02  lr: 0.000644  min_lr: 0.000644  loss: 2.1216 (2.0413)  weight_decay: 0.0500 (0.0500)  time: 1.0073  data: 0.0005  max mem: 78493
Epoch: [226]  [160/312]  eta: 0:02:50  lr: 0.000643  min_lr: 0.000643  loss: 2.1419 (2.0445)  weight_decay: 0.0500 (0.0500)  time: 1.0065  data: 0.0005  max mem: 78493
Epoch: [226]  [170/312]  eta: 0:02:37  lr: 0.000642  min_lr: 0.000642  loss: 2.0687 (2.0438)  weight_decay: 0.0500 (0.0500)  time: 1.0064  data: 0.0004  max mem: 78493
Epoch: [226]  [180/312]  eta: 0:02:26  lr: 0.000642  min_lr: 0.000642  loss: 2.0502 (2.0439)  weight_decay: 0.0500 (0.0500)  time: 1.0075  data: 0.0005  max mem: 78493
Epoch: [226]  [190/312]  eta: 0:02:14  lr: 0.000641  min_lr: 0.000641  loss: 2.1404 (2.0445)  weight_decay: 0.0500 (0.0500)  time: 1.0086  data: 0.0005  max mem: 78493
Epoch: [226]  [200/312]  eta: 0:02:02  lr: 0.000641  min_lr: 0.000641  loss: 2.1476 (2.0456)  weight_decay: 0.0500 (0.0500)  time: 1.0064  data: 0.0005  max mem: 78493
Epoch: [226]  [210/312]  eta: 0:01:51  lr: 0.000640  min_lr: 0.000640  loss: 2.1209 (2.0457)  weight_decay: 0.0500 (0.0500)  time: 1.0047  data: 0.0004  max mem: 78493
Epoch: [226]  [220/312]  eta: 0:01:40  lr: 0.000640  min_lr: 0.000640  loss: 2.1107 (2.0472)  weight_decay: 0.0500 (0.0500)  time: 1.0055  data: 0.0004  max mem: 78493
Epoch: [226]  [230/312]  eta: 0:01:28  lr: 0.000639  min_lr: 0.000639  loss: 2.0738 (2.0440)  weight_decay: 0.0500 (0.0500)  time: 1.0076  data: 0.0005  max mem: 78493
Epoch: [226]  [240/312]  eta: 0:01:17  lr: 0.000639  min_lr: 0.000639  loss: 1.8017 (2.0357)  weight_decay: 0.0500 (0.0500)  time: 1.0074  data: 0.0011  max mem: 78493
Epoch: [226]  [250/312]  eta: 0:01:06  lr: 0.000638  min_lr: 0.000638  loss: 1.9204 (2.0326)  weight_decay: 0.0500 (0.0500)  time: 1.0058  data: 0.0011  max mem: 78493
Epoch: [226]  [260/312]  eta: 0:00:55  lr: 0.000638  min_lr: 0.000638  loss: 2.0321 (2.0288)  weight_decay: 0.0500 (0.0500)  time: 1.0056  data: 0.0004  max mem: 78493
Epoch: [226]  [270/312]  eta: 0:00:45  lr: 0.000637  min_lr: 0.000637  loss: 2.0226 (2.0259)  weight_decay: 0.0500 (0.0500)  time: 1.0056  data: 0.0004  max mem: 78493
Epoch: [226]  [280/312]  eta: 0:00:34  lr: 0.000637  min_lr: 0.000637  loss: 1.9218 (2.0185)  weight_decay: 0.0500 (0.0500)  time: 1.0054  data: 0.0010  max mem: 78493
Epoch: [226]  [290/312]  eta: 0:00:23  lr: 0.000636  min_lr: 0.000636  loss: 1.5152 (2.0121)  weight_decay: 0.0500 (0.0500)  time: 1.0042  data: 0.0009  max mem: 78493
Epoch: [226]  [300/312]  eta: 0:00:12  lr: 0.000636  min_lr: 0.000636  loss: 1.9981 (2.0148)  weight_decay: 0.0500 (0.0500)  time: 1.0022  data: 0.0001  max mem: 78493
Epoch: [226]  [310/312]  eta: 0:00:02  lr: 0.000635  min_lr: 0.000635  loss: 1.9981 (2.0134)  weight_decay: 0.0500 (0.0500)  time: 1.0014  data: 0.0001  max mem: 78493
Epoch: [226]  [311/312]  eta: 0:00:01  lr: 0.000635  min_lr: 0.000635  loss: 1.9981 (2.0137)  weight_decay: 0.0500 (0.0500)  time: 1.0014  data: 0.0001  max mem: 78493
Epoch: [226] Total time: 0:05:33 (1.0698 s / it)
Averaged stats: lr: 0.000635  min_lr: 0.000635  loss: 1.9981 (2.0070)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:16  loss: 0.5469 (0.5469)  acc1: 86.0677 (86.0677)  acc5: 97.2656 (97.2656)  time: 8.5034  data: 8.2341  max mem: 78493
Test:  [8/9]  eta: 0:00:01  loss: 0.8304 (0.7546)  acc1: 79.6875 (79.8560)  acc5: 95.1823 (94.8960)  time: 1.1434  data: 0.9150  max mem: 78493
Test: Total time: 0:00:10 (1.1864 s / it)
* Acc@1 80.534 Acc@5 95.202 loss 0.739
Accuracy of the model on the 50000 test images: 80.5%
Max accuracy: 80.86%
Epoch: [227]  [  0/312]  eta: 1:27:25  lr: 0.000635  min_lr: 0.000635  loss: 2.4586 (2.4586)  weight_decay: 0.0500 (0.0500)  time: 16.8118  data: 15.7328  max mem: 78493
Epoch: [227]  [ 10/312]  eta: 0:13:09  lr: 0.000634  min_lr: 0.000634  loss: 2.1706 (2.1078)  weight_decay: 0.0500 (0.0500)  time: 2.6146  data: 1.4336  max mem: 78493
Epoch: [227]  [ 20/312]  eta: 0:09:01  lr: 0.000634  min_lr: 0.000634  loss: 1.9019 (1.9759)  weight_decay: 0.0500 (0.0500)  time: 1.1067  data: 0.0021  max mem: 78493
Epoch: [227]  [ 30/312]  eta: 0:07:25  lr: 0.000633  min_lr: 0.000633  loss: 2.0629 (2.0230)  weight_decay: 0.0500 (0.0500)  time: 1.0118  data: 0.0004  max mem: 78493
Epoch: [227]  [ 40/312]  eta: 0:06:31  lr: 0.000633  min_lr: 0.000633  loss: 2.1481 (2.0441)  weight_decay: 0.0500 (0.0500)  time: 1.0055  data: 0.0004  max mem: 78493
Epoch: [227]  [ 50/312]  eta: 0:05:55  lr: 0.000632  min_lr: 0.000632  loss: 2.1066 (2.0269)  weight_decay: 0.0500 (0.0500)  time: 1.0058  data: 0.0004  max mem: 78493
Epoch: [227]  [ 60/312]  eta: 0:05:27  lr: 0.000632  min_lr: 0.000632  loss: 1.8407 (1.9939)  weight_decay: 0.0500 (0.0500)  time: 1.0063  data: 0.0005  max mem: 78493
Epoch: [227]  [ 70/312]  eta: 0:05:04  lr: 0.000631  min_lr: 0.000631  loss: 2.0016 (2.0016)  weight_decay: 0.0500 (0.0500)  time: 1.0066  data: 0.0004  max mem: 78493
Epoch: [227]  [ 80/312]  eta: 0:04:44  lr: 0.000631  min_lr: 0.000631  loss: 2.1129 (1.9968)  weight_decay: 0.0500 (0.0500)  time: 1.0082  data: 0.0004  max mem: 78493
Epoch: [227]  [ 90/312]  eta: 0:04:27  lr: 0.000630  min_lr: 0.000630  loss: 2.1462 (2.0185)  weight_decay: 0.0500 (0.0500)  time: 1.0107  data: 0.0004  max mem: 78493
Epoch: [227]  [100/312]  eta: 0:04:10  lr: 0.000630  min_lr: 0.000630  loss: 1.9836 (2.0054)  weight_decay: 0.0500 (0.0500)  time: 1.0101  data: 0.0004  max mem: 78493
Epoch: [227]  [110/312]  eta: 0:03:55  lr: 0.000629  min_lr: 0.000629  loss: 1.7765 (1.9935)  weight_decay: 0.0500 (0.0500)  time: 1.0080  data: 0.0004  max mem: 78493
Epoch: [227]  [120/312]  eta: 0:03:41  lr: 0.000629  min_lr: 0.000629  loss: 2.0912 (2.0060)  weight_decay: 0.0500 (0.0500)  time: 1.0066  data: 0.0004  max mem: 78493
Epoch: [227]  [130/312]  eta: 0:03:28  lr: 0.000628  min_lr: 0.000628  loss: 2.2132 (2.0204)  weight_decay: 0.0500 (0.0500)  time: 1.0077  data: 0.0004  max mem: 78493
Epoch: [227]  [140/312]  eta: 0:03:14  lr: 0.000628  min_lr: 0.000628  loss: 2.2132 (2.0294)  weight_decay: 0.0500 (0.0500)  time: 1.0080  data: 0.0004  max mem: 78493
Epoch: [227]  [150/312]  eta: 0:03:02  lr: 0.000627  min_lr: 0.000627  loss: 2.1532 (2.0317)  weight_decay: 0.0500 (0.0500)  time: 1.0081  data: 0.0004  max mem: 78493
Epoch: [227]  [160/312]  eta: 0:02:49  lr: 0.000627  min_lr: 0.000627  loss: 2.0683 (2.0259)  weight_decay: 0.0500 (0.0500)  time: 1.0091  data: 0.0004  max mem: 78493
Epoch: [227]  [170/312]  eta: 0:02:37  lr: 0.000626  min_lr: 0.000626  loss: 1.9860 (2.0180)  weight_decay: 0.0500 (0.0500)  time: 1.0068  data: 0.0005  max mem: 78493
Epoch: [227]  [180/312]  eta: 0:02:25  lr: 0.000626  min_lr: 0.000626  loss: 1.8130 (2.0122)  weight_decay: 0.0500 (0.0500)  time: 1.0043  data: 0.0005  max mem: 78493
Epoch: [227]  [190/312]  eta: 0:02:14  lr: 0.000625  min_lr: 0.000625  loss: 2.0215 (2.0162)  weight_decay: 0.0500 (0.0500)  time: 1.0058  data: 0.0005  max mem: 78493
Epoch: [227]  [200/312]  eta: 0:02:02  lr: 0.000625  min_lr: 0.000625  loss: 2.0951 (2.0215)  weight_decay: 0.0500 (0.0500)  time: 1.0073  data: 0.0004  max mem: 78493
Epoch: [227]  [210/312]  eta: 0:01:51  lr: 0.000624  min_lr: 0.000624  loss: 2.1327 (2.0233)  weight_decay: 0.0500 (0.0500)  time: 1.0054  data: 0.0004  max mem: 78493
Epoch: [227]  [220/312]  eta: 0:01:40  lr: 0.000624  min_lr: 0.000624  loss: 2.2043 (2.0291)  weight_decay: 0.0500 (0.0500)  time: 1.0057  data: 0.0004  max mem: 78493
Epoch: [227]  [230/312]  eta: 0:01:28  lr: 0.000623  min_lr: 0.000623  loss: 2.2043 (2.0324)  weight_decay: 0.0500 (0.0500)  time: 1.0065  data: 0.0004  max mem: 78493
Epoch: [227]  [240/312]  eta: 0:01:17  lr: 0.000622  min_lr: 0.000622  loss: 1.9615 (2.0251)  weight_decay: 0.0500 (0.0500)  time: 1.0048  data: 0.0004  max mem: 78493
Epoch: [227]  [250/312]  eta: 0:01:06  lr: 0.000622  min_lr: 0.000622  loss: 1.9290 (2.0185)  weight_decay: 0.0500 (0.0500)  time: 1.0044  data: 0.0005  max mem: 78493
Epoch: [227]  [260/312]  eta: 0:00:55  lr: 0.000621  min_lr: 0.000621  loss: 1.9762 (2.0155)  weight_decay: 0.0500 (0.0500)  time: 1.0045  data: 0.0005  max mem: 78493
Epoch: [227]  [270/312]  eta: 0:00:45  lr: 0.000621  min_lr: 0.000621  loss: 1.9342 (2.0091)  weight_decay: 0.0500 (0.0500)  time: 1.0039  data: 0.0005  max mem: 78493
Epoch: [227]  [280/312]  eta: 0:00:34  lr: 0.000620  min_lr: 0.000620  loss: 1.9342 (2.0073)  weight_decay: 0.0500 (0.0500)  time: 1.0062  data: 0.0011  max mem: 78493
Epoch: [227]  [290/312]  eta: 0:00:23  lr: 0.000620  min_lr: 0.000620  loss: 2.0134 (2.0047)  weight_decay: 0.0500 (0.0500)  time: 1.0050  data: 0.0009  max mem: 78493
Epoch: [227]  [300/312]  eta: 0:00:12  lr: 0.000619  min_lr: 0.000619  loss: 2.0248 (2.0085)  weight_decay: 0.0500 (0.0500)  time: 1.0013  data: 0.0001  max mem: 78493
Epoch: [227]  [310/312]  eta: 0:00:02  lr: 0.000619  min_lr: 0.000619  loss: 2.1202 (2.0064)  weight_decay: 0.0500 (0.0500)  time: 1.0014  data: 0.0001  max mem: 78493
Epoch: [227]  [311/312]  eta: 0:00:01  lr: 0.000619  min_lr: 0.000619  loss: 2.1202 (2.0056)  weight_decay: 0.0500 (0.0500)  time: 1.0014  data: 0.0001  max mem: 78493
Epoch: [227] Total time: 0:05:33 (1.0687 s / it)
Averaged stats: lr: 0.000619  min_lr: 0.000619  loss: 2.1202 (1.9960)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:18  loss: 0.5274 (0.5274)  acc1: 86.7188 (86.7188)  acc5: 97.3958 (97.3958)  time: 8.7368  data: 8.4617  max mem: 78493
Test:  [8/9]  eta: 0:00:01  loss: 0.8222 (0.7456)  acc1: 80.3385 (80.3040)  acc5: 94.9219 (94.9440)  time: 1.1688  data: 0.9403  max mem: 78493
Test: Total time: 0:00:10 (1.1853 s / it)
* Acc@1 80.640 Acc@5 95.250 loss 0.732
Accuracy of the model on the 50000 test images: 80.6%
Max accuracy: 80.86%
Epoch: [228]  [  0/312]  eta: 1:23:27  lr: 0.000619  min_lr: 0.000619  loss: 2.2340 (2.2340)  weight_decay: 0.0500 (0.0500)  time: 16.0499  data: 12.7525  max mem: 78493
Epoch: [228]  [ 10/312]  eta: 0:12:45  lr: 0.000618  min_lr: 0.000618  loss: 1.9309 (1.9127)  weight_decay: 0.0500 (0.0500)  time: 2.5334  data: 1.1893  max mem: 78493
Epoch: [228]  [ 20/312]  eta: 0:08:50  lr: 0.000618  min_lr: 0.000618  loss: 2.0050 (1.9689)  weight_decay: 0.0500 (0.0500)  time: 1.1043  data: 0.0168  max mem: 78493
Epoch: [228]  [ 30/312]  eta: 0:07:18  lr: 0.000617  min_lr: 0.000617  loss: 2.0500 (1.9673)  weight_decay: 0.0500 (0.0500)  time: 1.0176  data: 0.0005  max mem: 78493
Epoch: [228]  [ 40/312]  eta: 0:06:26  lr: 0.000617  min_lr: 0.000617  loss: 1.9648 (1.9736)  weight_decay: 0.0500 (0.0500)  time: 1.0086  data: 0.0004  max mem: 78493
Epoch: [228]  [ 50/312]  eta: 0:05:51  lr: 0.000616  min_lr: 0.000616  loss: 1.9808 (1.9950)  weight_decay: 0.0500 (0.0500)  time: 1.0073  data: 0.0004  max mem: 78493
Epoch: [228]  [ 60/312]  eta: 0:05:24  lr: 0.000616  min_lr: 0.000616  loss: 1.9743 (1.9587)  weight_decay: 0.0500 (0.0500)  time: 1.0079  data: 0.0005  max mem: 78493
Epoch: [228]  [ 70/312]  eta: 0:05:01  lr: 0.000615  min_lr: 0.000615  loss: 1.8362 (1.9607)  weight_decay: 0.0500 (0.0500)  time: 1.0086  data: 0.0004  max mem: 78493
Epoch: [228]  [ 80/312]  eta: 0:04:42  lr: 0.000615  min_lr: 0.000615  loss: 1.9709 (1.9622)  weight_decay: 0.0500 (0.0500)  time: 1.0076  data: 0.0004  max mem: 78493
Epoch: [228]  [ 90/312]  eta: 0:04:25  lr: 0.000614  min_lr: 0.000614  loss: 2.0175 (1.9650)  weight_decay: 0.0500 (0.0500)  time: 1.0081  data: 0.0004  max mem: 78493
Epoch: [228]  [100/312]  eta: 0:04:09  lr: 0.000614  min_lr: 0.000614  loss: 2.0262 (1.9762)  weight_decay: 0.0500 (0.0500)  time: 1.0095  data: 0.0004  max mem: 78493
Epoch: [228]  [110/312]  eta: 0:03:54  lr: 0.000613  min_lr: 0.000613  loss: 2.1724 (1.9985)  weight_decay: 0.0500 (0.0500)  time: 1.0109  data: 0.0012  max mem: 78493
Epoch: [228]  [120/312]  eta: 0:03:40  lr: 0.000612  min_lr: 0.000612  loss: 2.1422 (1.9883)  weight_decay: 0.0500 (0.0500)  time: 1.0104  data: 0.0019  max mem: 78493
Epoch: [228]  [130/312]  eta: 0:03:27  lr: 0.000612  min_lr: 0.000612  loss: 2.0532 (1.9893)  weight_decay: 0.0500 (0.0500)  time: 1.0085  data: 0.0019  max mem: 78493
Epoch: [228]  [140/312]  eta: 0:03:14  lr: 0.000611  min_lr: 0.000611  loss: 2.1606 (1.9993)  weight_decay: 0.0500 (0.0500)  time: 1.0079  data: 0.0012  max mem: 78493
Epoch: [228]  [150/312]  eta: 0:03:01  lr: 0.000611  min_lr: 0.000611  loss: 2.1147 (1.9881)  weight_decay: 0.0500 (0.0500)  time: 1.0079  data: 0.0005  max mem: 78493
Epoch: [228]  [160/312]  eta: 0:02:49  lr: 0.000610  min_lr: 0.000610  loss: 1.7891 (1.9822)  weight_decay: 0.0500 (0.0500)  time: 1.0064  data: 0.0004  max mem: 78493
Epoch: [228]  [170/312]  eta: 0:02:37  lr: 0.000610  min_lr: 0.000610  loss: 2.0728 (1.9868)  weight_decay: 0.0500 (0.0500)  time: 1.0046  data: 0.0004  max mem: 78493
Epoch: [228]  [180/312]  eta: 0:02:25  lr: 0.000609  min_lr: 0.000609  loss: 2.2196 (1.9977)  weight_decay: 0.0500 (0.0500)  time: 1.0040  data: 0.0004  max mem: 78493
Epoch: [228]  [190/312]  eta: 0:02:13  lr: 0.000609  min_lr: 0.000609  loss: 1.9758 (1.9828)  weight_decay: 0.0500 (0.0500)  time: 1.0073  data: 0.0004  max mem: 78493
Epoch: [228]  [200/312]  eta: 0:02:02  lr: 0.000608  min_lr: 0.000608  loss: 1.7362 (1.9753)  weight_decay: 0.0500 (0.0500)  time: 1.0102  data: 0.0004  max mem: 78493
Epoch: [228]  [210/312]  eta: 0:01:50  lr: 0.000608  min_lr: 0.000608  loss: 1.8208 (1.9704)  weight_decay: 0.0500 (0.0500)  time: 1.0066  data: 0.0004  max mem: 78493
Epoch: [228]  [220/312]  eta: 0:01:39  lr: 0.000607  min_lr: 0.000607  loss: 1.9912 (1.9650)  weight_decay: 0.0500 (0.0500)  time: 1.0039  data: 0.0004  max mem: 78493
Epoch: [228]  [230/312]  eta: 0:01:28  lr: 0.000607  min_lr: 0.000607  loss: 2.0453 (1.9649)  weight_decay: 0.0500 (0.0500)  time: 1.0058  data: 0.0005  max mem: 78493
Epoch: [228]  [240/312]  eta: 0:01:17  lr: 0.000606  min_lr: 0.000606  loss: 1.9790 (1.9603)  weight_decay: 0.0500 (0.0500)  time: 1.0067  data: 0.0005  max mem: 78493
Epoch: [228]  [250/312]  eta: 0:01:06  lr: 0.000606  min_lr: 0.000606  loss: 2.0400 (1.9629)  weight_decay: 0.0500 (0.0500)  time: 1.0053  data: 0.0004  max mem: 78493
Epoch: [228]  [260/312]  eta: 0:00:55  lr: 0.000605  min_lr: 0.000605  loss: 2.0439 (1.9667)  weight_decay: 0.0500 (0.0500)  time: 1.0059  data: 0.0004  max mem: 78493
Epoch: [228]  [270/312]  eta: 0:00:44  lr: 0.000605  min_lr: 0.000605  loss: 2.1169 (1.9700)  weight_decay: 0.0500 (0.0500)  time: 1.0052  data: 0.0004  max mem: 78493
Epoch: [228]  [280/312]  eta: 0:00:34  lr: 0.000604  min_lr: 0.000604  loss: 2.1295 (1.9758)  weight_decay: 0.0500 (0.0500)  time: 1.0048  data: 0.0013  max mem: 78493
Epoch: [228]  [290/312]  eta: 0:00:23  lr: 0.000604  min_lr: 0.000604  loss: 2.0371 (1.9678)  weight_decay: 0.0500 (0.0500)  time: 1.0040  data: 0.0011  max mem: 78493
Epoch: [228]  [300/312]  eta: 0:00:12  lr: 0.000603  min_lr: 0.000603  loss: 1.9393 (1.9704)  weight_decay: 0.0500 (0.0500)  time: 1.0013  data: 0.0001  max mem: 78493
Epoch: [228]  [310/312]  eta: 0:00:02  lr: 0.000603  min_lr: 0.000603  loss: 2.1681 (1.9793)  weight_decay: 0.0500 (0.0500)  time: 1.0012  data: 0.0001  max mem: 78493
Epoch: [228]  [311/312]  eta: 0:00:01  lr: 0.000603  min_lr: 0.000603  loss: 2.1678 (1.9790)  weight_decay: 0.0500 (0.0500)  time: 1.0013  data: 0.0001  max mem: 78493
Epoch: [228] Total time: 0:05:32 (1.0670 s / it)
Averaged stats: lr: 0.000603  min_lr: 0.000603  loss: 2.1678 (1.9867)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:16  loss: 0.5219 (0.5219)  acc1: 86.7188 (86.7188)  acc5: 97.3958 (97.3958)  time: 8.4687  data: 8.1952  max mem: 78493
Test:  [8/9]  eta: 0:00:01  loss: 0.8130 (0.7368)  acc1: 80.0781 (80.3520)  acc5: 95.7031 (95.3280)  time: 1.1390  data: 0.9107  max mem: 78493
Test: Total time: 0:00:10 (1.1553 s / it)
* Acc@1 80.822 Acc@5 95.426 loss 0.723
Accuracy of the model on the 50000 test images: 80.8%
Max accuracy: 80.86%
Epoch: [229]  [  0/312]  eta: 1:27:24  lr: 0.000603  min_lr: 0.000603  loss: 1.6428 (1.6428)  weight_decay: 0.0500 (0.0500)  time: 16.8098  data: 14.6720  max mem: 78493
Epoch: [229]  [ 10/312]  eta: 0:13:27  lr: 0.000602  min_lr: 0.000602  loss: 2.0881 (2.0427)  weight_decay: 0.0500 (0.0500)  time: 2.6739  data: 1.3893  max mem: 78493
Epoch: [229]  [ 20/312]  eta: 0:09:09  lr: 0.000602  min_lr: 0.000602  loss: 2.0881 (2.0204)  weight_decay: 0.0500 (0.0500)  time: 1.1366  data: 0.0308  max mem: 78493
Epoch: [229]  [ 30/312]  eta: 0:07:31  lr: 0.000601  min_lr: 0.000601  loss: 2.0725 (2.0310)  weight_decay: 0.0500 (0.0500)  time: 1.0104  data: 0.0005  max mem: 78493
Epoch: [229]  [ 40/312]  eta: 0:06:36  lr: 0.000601  min_lr: 0.000601  loss: 2.1506 (2.0406)  weight_decay: 0.0500 (0.0500)  time: 1.0075  data: 0.0004  max mem: 78493
Epoch: [229]  [ 50/312]  eta: 0:05:58  lr: 0.000600  min_lr: 0.000600  loss: 2.1806 (2.0338)  weight_decay: 0.0500 (0.0500)  time: 1.0078  data: 0.0005  max mem: 78493
Epoch: [229]  [ 60/312]  eta: 0:05:29  lr: 0.000600  min_lr: 0.000600  loss: 2.1185 (2.0162)  weight_decay: 0.0500 (0.0500)  time: 1.0094  data: 0.0005  max mem: 78493
Epoch: [229]  [ 70/312]  eta: 0:05:06  lr: 0.000599  min_lr: 0.000599  loss: 1.8495 (1.9831)  weight_decay: 0.0500 (0.0500)  time: 1.0110  data: 0.0014  max mem: 78493
Epoch: [229]  [ 80/312]  eta: 0:04:46  lr: 0.000598  min_lr: 0.000598  loss: 1.8495 (1.9754)  weight_decay: 0.0500 (0.0500)  time: 1.0109  data: 0.0014  max mem: 78493
Epoch: [229]  [ 90/312]  eta: 0:04:28  lr: 0.000598  min_lr: 0.000598  loss: 1.8577 (1.9648)  weight_decay: 0.0500 (0.0500)  time: 1.0081  data: 0.0004  max mem: 78493
Epoch: [229]  [100/312]  eta: 0:04:12  lr: 0.000597  min_lr: 0.000597  loss: 1.9055 (1.9642)  weight_decay: 0.0500 (0.0500)  time: 1.0077  data: 0.0004  max mem: 78493
Epoch: [229]  [110/312]  eta: 0:03:57  lr: 0.000597  min_lr: 0.000597  loss: 1.9904 (1.9623)  weight_decay: 0.0500 (0.0500)  time: 1.0098  data: 0.0005  max mem: 78493
Epoch: [229]  [120/312]  eta: 0:03:42  lr: 0.000596  min_lr: 0.000596  loss: 2.0129 (1.9666)  weight_decay: 0.0500 (0.0500)  time: 1.0083  data: 0.0005  max mem: 78493
Epoch: [229]  [130/312]  eta: 0:03:29  lr: 0.000596  min_lr: 0.000596  loss: 2.0129 (1.9638)  weight_decay: 0.0500 (0.0500)  time: 1.0055  data: 0.0004  max mem: 78493
Epoch: [229]  [140/312]  eta: 0:03:15  lr: 0.000595  min_lr: 0.000595  loss: 2.0022 (1.9647)  weight_decay: 0.0500 (0.0500)  time: 1.0051  data: 0.0004  max mem: 78493
Epoch: [229]  [150/312]  eta: 0:03:03  lr: 0.000595  min_lr: 0.000595  loss: 2.1461 (1.9656)  weight_decay: 0.0500 (0.0500)  time: 1.0062  data: 0.0004  max mem: 78493
Epoch: [229]  [160/312]  eta: 0:02:50  lr: 0.000594  min_lr: 0.000594  loss: 2.0219 (1.9683)  weight_decay: 0.0500 (0.0500)  time: 1.0063  data: 0.0004  max mem: 78493
Epoch: [229]  [170/312]  eta: 0:02:38  lr: 0.000594  min_lr: 0.000594  loss: 2.0849 (1.9794)  weight_decay: 0.0500 (0.0500)  time: 1.0061  data: 0.0004  max mem: 78493
Epoch: [229]  [180/312]  eta: 0:02:26  lr: 0.000593  min_lr: 0.000593  loss: 2.1447 (1.9857)  weight_decay: 0.0500 (0.0500)  time: 1.0084  data: 0.0004  max mem: 78493
Epoch: [229]  [190/312]  eta: 0:02:14  lr: 0.000593  min_lr: 0.000593  loss: 2.1014 (1.9879)  weight_decay: 0.0500 (0.0500)  time: 1.0095  data: 0.0004  max mem: 78493
Epoch: [229]  [200/312]  eta: 0:02:03  lr: 0.000592  min_lr: 0.000592  loss: 1.9822 (1.9771)  weight_decay: 0.0500 (0.0500)  time: 1.0074  data: 0.0004  max mem: 78493
Epoch: [229]  [210/312]  eta: 0:01:51  lr: 0.000592  min_lr: 0.000592  loss: 1.8886 (1.9790)  weight_decay: 0.0500 (0.0500)  time: 1.0054  data: 0.0005  max mem: 78493
Epoch: [229]  [220/312]  eta: 0:01:40  lr: 0.000591  min_lr: 0.000591  loss: 1.9997 (1.9795)  weight_decay: 0.0500 (0.0500)  time: 1.0059  data: 0.0005  max mem: 78493
Epoch: [229]  [230/312]  eta: 0:01:29  lr: 0.000591  min_lr: 0.000591  loss: 2.1156 (1.9840)  weight_decay: 0.0500 (0.0500)  time: 1.0074  data: 0.0004  max mem: 78493
Epoch: [229]  [240/312]  eta: 0:01:18  lr: 0.000590  min_lr: 0.000590  loss: 2.1578 (1.9863)  weight_decay: 0.0500 (0.0500)  time: 1.0076  data: 0.0004  max mem: 78493
Epoch: [229]  [250/312]  eta: 0:01:07  lr: 0.000590  min_lr: 0.000590  loss: 2.1560 (1.9927)  weight_decay: 0.0500 (0.0500)  time: 1.0077  data: 0.0005  max mem: 78493
Epoch: [229]  [260/312]  eta: 0:00:56  lr: 0.000589  min_lr: 0.000589  loss: 2.1300 (1.9956)  weight_decay: 0.0500 (0.0500)  time: 1.0068  data: 0.0004  max mem: 78493
Epoch: [229]  [270/312]  eta: 0:00:45  lr: 0.000589  min_lr: 0.000589  loss: 2.0394 (1.9928)  weight_decay: 0.0500 (0.0500)  time: 1.0069  data: 0.0005  max mem: 78493
Epoch: [229]  [280/312]  eta: 0:00:34  lr: 0.000588  min_lr: 0.000588  loss: 2.0546 (1.9959)  weight_decay: 0.0500 (0.0500)  time: 1.0081  data: 0.0025  max mem: 78493
Epoch: [229]  [290/312]  eta: 0:00:23  lr: 0.000588  min_lr: 0.000588  loss: 2.1210 (1.9941)  weight_decay: 0.0500 (0.0500)  time: 1.0049  data: 0.0024  max mem: 78493
Epoch: [229]  [300/312]  eta: 0:00:12  lr: 0.000587  min_lr: 0.000587  loss: 2.1608 (1.9963)  weight_decay: 0.0500 (0.0500)  time: 1.0019  data: 0.0001  max mem: 78493
Epoch: [229]  [310/312]  eta: 0:00:02  lr: 0.000587  min_lr: 0.000587  loss: 2.1893 (2.0013)  weight_decay: 0.0500 (0.0500)  time: 1.0021  data: 0.0001  max mem: 78493
Epoch: [229]  [311/312]  eta: 0:00:01  lr: 0.000587  min_lr: 0.000587  loss: 2.1839 (2.0011)  weight_decay: 0.0500 (0.0500)  time: 1.0020  data: 0.0001  max mem: 78493
Epoch: [229] Total time: 0:05:34 (1.0718 s / it)
Averaged stats: lr: 0.000587  min_lr: 0.000587  loss: 2.1839 (1.9866)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:16  loss: 0.5199 (0.5199)  acc1: 86.7188 (86.7188)  acc5: 98.0469 (98.0469)  time: 8.5488  data: 8.2770  max mem: 78493
Test:  [8/9]  eta: 0:00:01  loss: 0.8058 (0.7362)  acc1: 79.5573 (80.4800)  acc5: 96.3542 (95.4560)  time: 1.1482  data: 0.9197  max mem: 78493
Test: Total time: 0:00:10 (1.1650 s / it)
* Acc@1 80.836 Acc@5 95.352 loss 0.728
Accuracy of the model on the 50000 test images: 80.8%
Max accuracy: 80.86%
Epoch: [230]  [  0/312]  eta: 1:26:24  lr: 0.000587  min_lr: 0.000587  loss: 1.5640 (1.5640)  weight_decay: 0.0500 (0.0500)  time: 16.6162  data: 15.2659  max mem: 78493
Epoch: [230]  [ 10/312]  eta: 0:13:04  lr: 0.000586  min_lr: 0.000586  loss: 2.1336 (1.9963)  weight_decay: 0.0500 (0.0500)  time: 2.5991  data: 1.3953  max mem: 78493
Epoch: [230]  [ 20/312]  eta: 0:09:00  lr: 0.000586  min_lr: 0.000586  loss: 2.1536 (2.0229)  weight_decay: 0.0500 (0.0500)  time: 1.1114  data: 0.0054  max mem: 78493
Epoch: [230]  [ 30/312]  eta: 0:07:25  lr: 0.000585  min_lr: 0.000585  loss: 1.8449 (1.9443)  weight_decay: 0.0500 (0.0500)  time: 1.0185  data: 0.0024  max mem: 78493
Epoch: [230]  [ 40/312]  eta: 0:06:31  lr: 0.000585  min_lr: 0.000585  loss: 1.9085 (1.9343)  weight_decay: 0.0500 (0.0500)  time: 1.0097  data: 0.0013  max mem: 78493
Epoch: [230]  [ 50/312]  eta: 0:05:55  lr: 0.000584  min_lr: 0.000584  loss: 2.0288 (1.9573)  weight_decay: 0.0500 (0.0500)  time: 1.0085  data: 0.0004  max mem: 78493
Epoch: [230]  [ 60/312]  eta: 0:05:27  lr: 0.000584  min_lr: 0.000584  loss: 2.0134 (1.9449)  weight_decay: 0.0500 (0.0500)  time: 1.0096  data: 0.0004  max mem: 78493
Epoch: [230]  [ 70/312]  eta: 0:05:04  lr: 0.000583  min_lr: 0.000583  loss: 2.1171 (1.9585)  weight_decay: 0.0500 (0.0500)  time: 1.0107  data: 0.0004  max mem: 78493
Epoch: [230]  [ 80/312]  eta: 0:04:44  lr: 0.000583  min_lr: 0.000583  loss: 2.0627 (1.9620)  weight_decay: 0.0500 (0.0500)  time: 1.0102  data: 0.0011  max mem: 78493
Epoch: [230]  [ 90/312]  eta: 0:04:27  lr: 0.000582  min_lr: 0.000582  loss: 2.0627 (1.9726)  weight_decay: 0.0500 (0.0500)  time: 1.0080  data: 0.0011  max mem: 78493
Epoch: [230]  [100/312]  eta: 0:04:11  lr: 0.000582  min_lr: 0.000582  loss: 2.0756 (1.9676)  weight_decay: 0.0500 (0.0500)  time: 1.0077  data: 0.0004  max mem: 78493
Epoch: [230]  [110/312]  eta: 0:03:55  lr: 0.000581  min_lr: 0.000581  loss: 2.0696 (1.9674)  weight_decay: 0.0500 (0.0500)  time: 1.0077  data: 0.0004  max mem: 78493
Epoch: [230]  [120/312]  eta: 0:03:41  lr: 0.000581  min_lr: 0.000581  loss: 2.0647 (1.9648)  weight_decay: 0.0500 (0.0500)  time: 1.0067  data: 0.0004  max mem: 78493
Epoch: [230]  [130/312]  eta: 0:03:28  lr: 0.000580  min_lr: 0.000580  loss: 1.8342 (1.9517)  weight_decay: 0.0500 (0.0500)  time: 1.0078  data: 0.0004  max mem: 78493
Epoch: [230]  [140/312]  eta: 0:03:15  lr: 0.000580  min_lr: 0.000580  loss: 1.8311 (1.9497)  weight_decay: 0.0500 (0.0500)  time: 1.0086  data: 0.0005  max mem: 78493
Epoch: [230]  [150/312]  eta: 0:03:02  lr: 0.000579  min_lr: 0.000579  loss: 1.8311 (1.9455)  weight_decay: 0.0500 (0.0500)  time: 1.0077  data: 0.0004  max mem: 78493
Epoch: [230]  [160/312]  eta: 0:02:49  lr: 0.000579  min_lr: 0.000579  loss: 1.9503 (1.9435)  weight_decay: 0.0500 (0.0500)  time: 1.0060  data: 0.0005  max mem: 78493
Epoch: [230]  [170/312]  eta: 0:02:37  lr: 0.000578  min_lr: 0.000578  loss: 1.9503 (1.9420)  weight_decay: 0.0500 (0.0500)  time: 1.0068  data: 0.0005  max mem: 78493
Epoch: [230]  [180/312]  eta: 0:02:26  lr: 0.000578  min_lr: 0.000578  loss: 1.9449 (1.9439)  weight_decay: 0.0500 (0.0500)  time: 1.0094  data: 0.0004  max mem: 78493
Epoch: [230]  [190/312]  eta: 0:02:14  lr: 0.000577  min_lr: 0.000577  loss: 2.1566 (1.9524)  weight_decay: 0.0500 (0.0500)  time: 1.0081  data: 0.0004  max mem: 78493
Epoch: [230]  [200/312]  eta: 0:02:02  lr: 0.000577  min_lr: 0.000577  loss: 2.1480 (1.9502)  weight_decay: 0.0500 (0.0500)  time: 1.0053  data: 0.0004  max mem: 78493
Epoch: [230]  [210/312]  eta: 0:01:51  lr: 0.000576  min_lr: 0.000576  loss: 2.0417 (1.9592)  weight_decay: 0.0500 (0.0500)  time: 1.0056  data: 0.0005  max mem: 78493
Epoch: [230]  [220/312]  eta: 0:01:40  lr: 0.000575  min_lr: 0.000575  loss: 2.1336 (1.9635)  weight_decay: 0.0500 (0.0500)  time: 1.0053  data: 0.0004  max mem: 78493
Epoch: [230]  [230/312]  eta: 0:01:28  lr: 0.000575  min_lr: 0.000575  loss: 2.1230 (1.9706)  weight_decay: 0.0500 (0.0500)  time: 1.0051  data: 0.0004  max mem: 78493
Epoch: [230]  [240/312]  eta: 0:01:17  lr: 0.000574  min_lr: 0.000574  loss: 2.1219 (1.9725)  weight_decay: 0.0500 (0.0500)  time: 1.0060  data: 0.0004  max mem: 78493
Epoch: [230]  [250/312]  eta: 0:01:06  lr: 0.000574  min_lr: 0.000574  loss: 2.1128 (1.9737)  weight_decay: 0.0500 (0.0500)  time: 1.0053  data: 0.0004  max mem: 78493
Epoch: [230]  [260/312]  eta: 0:00:55  lr: 0.000573  min_lr: 0.000573  loss: 2.0375 (1.9765)  weight_decay: 0.0500 (0.0500)  time: 1.0047  data: 0.0004  max mem: 78493
Epoch: [230]  [270/312]  eta: 0:00:45  lr: 0.000573  min_lr: 0.000573  loss: 2.0109 (1.9760)  weight_decay: 0.0500 (0.0500)  time: 1.0043  data: 0.0004  max mem: 78493
Epoch: [230]  [280/312]  eta: 0:00:34  lr: 0.000572  min_lr: 0.000572  loss: 1.9575 (1.9727)  weight_decay: 0.0500 (0.0500)  time: 1.0046  data: 0.0011  max mem: 78493
Epoch: [230]  [290/312]  eta: 0:00:23  lr: 0.000572  min_lr: 0.000572  loss: 2.0896 (1.9735)  weight_decay: 0.0500 (0.0500)  time: 1.0035  data: 0.0009  max mem: 78493
Epoch: [230]  [300/312]  eta: 0:00:12  lr: 0.000571  min_lr: 0.000571  loss: 1.8605 (1.9685)  weight_decay: 0.0500 (0.0500)  time: 1.0015  data: 0.0001  max mem: 78493
Epoch: [230]  [310/312]  eta: 0:00:02  lr: 0.000571  min_lr: 0.000571  loss: 1.8989 (1.9698)  weight_decay: 0.0500 (0.0500)  time: 1.0013  data: 0.0001  max mem: 78493
Epoch: [230]  [311/312]  eta: 0:00:01  lr: 0.000571  min_lr: 0.000571  loss: 1.8989 (1.9700)  weight_decay: 0.0500 (0.0500)  time: 1.0013  data: 0.0001  max mem: 78493
Epoch: [230] Total time: 0:05:33 (1.0689 s / it)
Averaged stats: lr: 0.000571  min_lr: 0.000571  loss: 1.8989 (1.9784)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:10  loss: 0.5383 (0.5383)  acc1: 86.0677 (86.0677)  acc5: 97.6562 (97.6562)  time: 7.8204  data: 7.5481  max mem: 78493
Test:  [8/9]  eta: 0:00:01  loss: 0.7865 (0.7379)  acc1: 79.8177 (80.6400)  acc5: 96.0938 (95.3120)  time: 1.1022  data: 0.8639  max mem: 78493
Test: Total time: 0:00:10 (1.1134 s / it)
* Acc@1 80.844 Acc@5 95.356 loss 0.721
Accuracy of the model on the 50000 test images: 80.8%
Max accuracy: 80.86%
Epoch: [231]  [  0/312]  eta: 1:16:23  lr: 0.000571  min_lr: 0.000571  loss: 2.0913 (2.0913)  weight_decay: 0.0500 (0.0500)  time: 14.6914  data: 13.6788  max mem: 78493
Epoch: [231]  [ 10/312]  eta: 0:13:02  lr: 0.000570  min_lr: 0.000570  loss: 2.1701 (2.0644)  weight_decay: 0.0500 (0.0500)  time: 2.5920  data: 1.2497  max mem: 78493
Epoch: [231]  [ 20/312]  eta: 0:08:58  lr: 0.000570  min_lr: 0.000570  loss: 2.1171 (2.0646)  weight_decay: 0.0500 (0.0500)  time: 1.2019  data: 0.0037  max mem: 78493
Epoch: [231]  [ 30/312]  eta: 0:07:23  lr: 0.000569  min_lr: 0.000569  loss: 2.0851 (2.0360)  weight_decay: 0.0500 (0.0500)  time: 1.0139  data: 0.0005  max mem: 78493
Epoch: [231]  [ 40/312]  eta: 0:06:30  lr: 0.000569  min_lr: 0.000569  loss: 2.1282 (2.0669)  weight_decay: 0.0500 (0.0500)  time: 1.0070  data: 0.0004  max mem: 78493
Epoch: [231]  [ 50/312]  eta: 0:05:54  lr: 0.000568  min_lr: 0.000568  loss: 2.1282 (2.0544)  weight_decay: 0.0500 (0.0500)  time: 1.0095  data: 0.0004  max mem: 78493
Epoch: [231]  [ 60/312]  eta: 0:05:26  lr: 0.000568  min_lr: 0.000568  loss: 2.1147 (2.0367)  weight_decay: 0.0500 (0.0500)  time: 1.0074  data: 0.0004  max mem: 78493
Epoch: [231]  [ 70/312]  eta: 0:05:03  lr: 0.000567  min_lr: 0.000567  loss: 1.9646 (2.0071)  weight_decay: 0.0500 (0.0500)  time: 1.0049  data: 0.0004  max mem: 78493
Epoch: [231]  [ 80/312]  eta: 0:04:43  lr: 0.000567  min_lr: 0.000567  loss: 1.9192 (1.9992)  weight_decay: 0.0500 (0.0500)  time: 1.0060  data: 0.0004  max mem: 78493
Epoch: [231]  [ 90/312]  eta: 0:04:26  lr: 0.000566  min_lr: 0.000566  loss: 2.0544 (1.9960)  weight_decay: 0.0500 (0.0500)  time: 1.0063  data: 0.0004  max mem: 78493
Epoch: [231]  [100/312]  eta: 0:04:10  lr: 0.000566  min_lr: 0.000566  loss: 1.9610 (1.9825)  weight_decay: 0.0500 (0.0500)  time: 1.0071  data: 0.0004  max mem: 78493
Epoch: [231]  [110/312]  eta: 0:03:55  lr: 0.000565  min_lr: 0.000565  loss: 1.9293 (1.9765)  weight_decay: 0.0500 (0.0500)  time: 1.0081  data: 0.0005  max mem: 78493
Epoch: [231]  [120/312]  eta: 0:03:41  lr: 0.000565  min_lr: 0.000565  loss: 1.7670 (1.9564)  weight_decay: 0.0500 (0.0500)  time: 1.0079  data: 0.0005  max mem: 78493
Epoch: [231]  [130/312]  eta: 0:03:27  lr: 0.000564  min_lr: 0.000564  loss: 1.7670 (1.9617)  weight_decay: 0.0500 (0.0500)  time: 1.0099  data: 0.0005  max mem: 78493
Epoch: [231]  [140/312]  eta: 0:03:14  lr: 0.000564  min_lr: 0.000564  loss: 2.0398 (1.9723)  weight_decay: 0.0500 (0.0500)  time: 1.0108  data: 0.0004  max mem: 78493
Epoch: [231]  [150/312]  eta: 0:03:02  lr: 0.000563  min_lr: 0.000563  loss: 2.0476 (1.9779)  weight_decay: 0.0500 (0.0500)  time: 1.0092  data: 0.0005  max mem: 78493
Epoch: [231]  [160/312]  eta: 0:02:49  lr: 0.000563  min_lr: 0.000563  loss: 2.0495 (1.9851)  weight_decay: 0.0500 (0.0500)  time: 1.0090  data: 0.0005  max mem: 78493
Epoch: [231]  [170/312]  eta: 0:02:37  lr: 0.000562  min_lr: 0.000562  loss: 2.1392 (1.9839)  weight_decay: 0.0500 (0.0500)  time: 1.0109  data: 0.0004  max mem: 78493
Epoch: [231]  [180/312]  eta: 0:02:25  lr: 0.000562  min_lr: 0.000562  loss: 1.9064 (1.9767)  weight_decay: 0.0500 (0.0500)  time: 1.0105  data: 0.0004  max mem: 78493
Epoch: [231]  [190/312]  eta: 0:02:14  lr: 0.000561  min_lr: 0.000561  loss: 2.0387 (1.9847)  weight_decay: 0.0500 (0.0500)  time: 1.0098  data: 0.0004  max mem: 78493
Epoch: [231]  [200/312]  eta: 0:02:02  lr: 0.000561  min_lr: 0.000561  loss: 2.1095 (1.9894)  weight_decay: 0.0500 (0.0500)  time: 1.0096  data: 0.0005  max mem: 78493
Epoch: [231]  [210/312]  eta: 0:01:51  lr: 0.000560  min_lr: 0.000560  loss: 2.1115 (1.9962)  weight_decay: 0.0500 (0.0500)  time: 1.0076  data: 0.0004  max mem: 78493
Epoch: [231]  [220/312]  eta: 0:01:40  lr: 0.000560  min_lr: 0.000560  loss: 2.1115 (2.0005)  weight_decay: 0.0500 (0.0500)  time: 1.0064  data: 0.0005  max mem: 78493
Epoch: [231]  [230/312]  eta: 0:01:28  lr: 0.000559  min_lr: 0.000559  loss: 2.0551 (2.0001)  weight_decay: 0.0500 (0.0500)  time: 1.0069  data: 0.0005  max mem: 78493
Epoch: [231]  [240/312]  eta: 0:01:17  lr: 0.000559  min_lr: 0.000559  loss: 2.0189 (2.0009)  weight_decay: 0.0500 (0.0500)  time: 1.0069  data: 0.0004  max mem: 78493
Epoch: [231]  [250/312]  eta: 0:01:06  lr: 0.000558  min_lr: 0.000558  loss: 1.9562 (1.9981)  weight_decay: 0.0500 (0.0500)  time: 1.0056  data: 0.0004  max mem: 78493
Epoch: [231]  [260/312]  eta: 0:00:55  lr: 0.000558  min_lr: 0.000558  loss: 1.7606 (1.9922)  weight_decay: 0.0500 (0.0500)  time: 1.0053  data: 0.0005  max mem: 78493
Epoch: [231]  [270/312]  eta: 0:00:45  lr: 0.000557  min_lr: 0.000557  loss: 1.7606 (1.9921)  weight_decay: 0.0500 (0.0500)  time: 1.0047  data: 0.0005  max mem: 78493
Epoch: [231]  [280/312]  eta: 0:00:34  lr: 0.000557  min_lr: 0.000557  loss: 1.9638 (1.9919)  weight_decay: 0.0500 (0.0500)  time: 1.0050  data: 0.0010  max mem: 78493
Epoch: [231]  [290/312]  eta: 0:00:23  lr: 0.000556  min_lr: 0.000556  loss: 1.8962 (1.9894)  weight_decay: 0.0500 (0.0500)  time: 1.0032  data: 0.0009  max mem: 78493
Epoch: [231]  [300/312]  eta: 0:00:12  lr: 0.000556  min_lr: 0.000556  loss: 1.8915 (1.9857)  weight_decay: 0.0500 (0.0500)  time: 1.0015  data: 0.0001  max mem: 78493
Epoch: [231]  [310/312]  eta: 0:00:02  lr: 0.000555  min_lr: 0.000555  loss: 1.9111 (1.9830)  weight_decay: 0.0500 (0.0500)  time: 1.0018  data: 0.0001  max mem: 78493
Epoch: [231]  [311/312]  eta: 0:00:01  lr: 0.000555  min_lr: 0.000555  loss: 2.0727 (1.9833)  weight_decay: 0.0500 (0.0500)  time: 1.0018  data: 0.0001  max mem: 78493
Epoch: [231] Total time: 0:05:33 (1.0695 s / it)
Averaged stats: lr: 0.000555  min_lr: 0.000555  loss: 2.0727 (1.9776)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:12  loss: 0.5166 (0.5166)  acc1: 87.1094 (87.1094)  acc5: 97.2656 (97.2656)  time: 8.0357  data: 7.7519  max mem: 78493
Test:  [8/9]  eta: 0:00:01  loss: 0.8138 (0.7333)  acc1: 80.7292 (80.1920)  acc5: 95.4427 (95.2000)  time: 1.0963  data: 0.8659  max mem: 78493
Test: Total time: 0:00:10 (1.1112 s / it)
* Acc@1 80.904 Acc@5 95.452 loss 0.721
Accuracy of the model on the 50000 test images: 80.9%
Max accuracy: 80.90%
Epoch: [232]  [  0/312]  eta: 1:21:46  lr: 0.000555  min_lr: 0.000555  loss: 2.0861 (2.0861)  weight_decay: 0.0500 (0.0500)  time: 15.7262  data: 13.0890  max mem: 78493
Epoch: [232]  [ 10/312]  eta: 0:12:44  lr: 0.000555  min_lr: 0.000555  loss: 2.2164 (2.1298)  weight_decay: 0.0500 (0.0500)  time: 2.5323  data: 1.1935  max mem: 78493
Epoch: [232]  [ 20/312]  eta: 0:08:48  lr: 0.000554  min_lr: 0.000554  loss: 2.0739 (1.9841)  weight_decay: 0.0500 (0.0500)  time: 1.1152  data: 0.0022  max mem: 78493
Epoch: [232]  [ 30/312]  eta: 0:07:17  lr: 0.000554  min_lr: 0.000554  loss: 1.9039 (1.9794)  weight_decay: 0.0500 (0.0500)  time: 1.0123  data: 0.0005  max mem: 78493
Epoch: [232]  [ 40/312]  eta: 0:06:25  lr: 0.000553  min_lr: 0.000553  loss: 1.9039 (1.9457)  weight_decay: 0.0500 (0.0500)  time: 1.0070  data: 0.0004  max mem: 78493
Epoch: [232]  [ 50/312]  eta: 0:05:50  lr: 0.000553  min_lr: 0.000553  loss: 2.0001 (1.9492)  weight_decay: 0.0500 (0.0500)  time: 1.0066  data: 0.0004  max mem: 78493
Epoch: [232]  [ 60/312]  eta: 0:05:23  lr: 0.000552  min_lr: 0.000552  loss: 2.0001 (1.9427)  weight_decay: 0.0500 (0.0500)  time: 1.0059  data: 0.0004  max mem: 78493
Epoch: [232]  [ 70/312]  eta: 0:05:01  lr: 0.000552  min_lr: 0.000552  loss: 2.0919 (1.9602)  weight_decay: 0.0500 (0.0500)  time: 1.0066  data: 0.0005  max mem: 78493
Epoch: [232]  [ 80/312]  eta: 0:04:41  lr: 0.000551  min_lr: 0.000551  loss: 2.0919 (1.9615)  weight_decay: 0.0500 (0.0500)  time: 1.0083  data: 0.0005  max mem: 78493
Epoch: [232]  [ 90/312]  eta: 0:04:24  lr: 0.000551  min_lr: 0.000551  loss: 1.9250 (1.9605)  weight_decay: 0.0500 (0.0500)  time: 1.0087  data: 0.0004  max mem: 78493
Epoch: [232]  [100/312]  eta: 0:04:09  lr: 0.000550  min_lr: 0.000550  loss: 2.0121 (1.9503)  weight_decay: 0.0500 (0.0500)  time: 1.0088  data: 0.0004  max mem: 78493
Epoch: [232]  [110/312]  eta: 0:03:54  lr: 0.000550  min_lr: 0.000550  loss: 1.8513 (1.9448)  weight_decay: 0.0500 (0.0500)  time: 1.0093  data: 0.0004  max mem: 78493
Epoch: [232]  [120/312]  eta: 0:03:40  lr: 0.000549  min_lr: 0.000549  loss: 2.0371 (1.9537)  weight_decay: 0.0500 (0.0500)  time: 1.0100  data: 0.0004  max mem: 78493
Epoch: [232]  [130/312]  eta: 0:03:26  lr: 0.000549  min_lr: 0.000549  loss: 2.0371 (1.9347)  weight_decay: 0.0500 (0.0500)  time: 1.0095  data: 0.0004  max mem: 78493
Epoch: [232]  [140/312]  eta: 0:03:13  lr: 0.000548  min_lr: 0.000548  loss: 1.8692 (1.9324)  weight_decay: 0.0500 (0.0500)  time: 1.0085  data: 0.0004  max mem: 78493
Epoch: [232]  [150/312]  eta: 0:03:01  lr: 0.000548  min_lr: 0.000548  loss: 1.9688 (1.9250)  weight_decay: 0.0500 (0.0500)  time: 1.0097  data: 0.0004  max mem: 78493
Epoch: [232]  [160/312]  eta: 0:02:49  lr: 0.000547  min_lr: 0.000547  loss: 1.9688 (1.9283)  weight_decay: 0.0500 (0.0500)  time: 1.0092  data: 0.0004  max mem: 78493
Epoch: [232]  [170/312]  eta: 0:02:37  lr: 0.000547  min_lr: 0.000547  loss: 2.0061 (1.9337)  weight_decay: 0.0500 (0.0500)  time: 1.0087  data: 0.0004  max mem: 78493
Epoch: [232]  [180/312]  eta: 0:02:25  lr: 0.000546  min_lr: 0.000546  loss: 1.8811 (1.9232)  weight_decay: 0.0500 (0.0500)  time: 1.0087  data: 0.0004  max mem: 78493
Epoch: [232]  [190/312]  eta: 0:02:13  lr: 0.000546  min_lr: 0.000546  loss: 1.8159 (1.9203)  weight_decay: 0.0500 (0.0500)  time: 1.0075  data: 0.0004  max mem: 78493
Epoch: [232]  [200/312]  eta: 0:02:02  lr: 0.000545  min_lr: 0.000545  loss: 1.9781 (1.9217)  weight_decay: 0.0500 (0.0500)  time: 1.0074  data: 0.0005  max mem: 78493
Epoch: [232]  [210/312]  eta: 0:01:50  lr: 0.000545  min_lr: 0.000545  loss: 2.0499 (1.9244)  weight_decay: 0.0500 (0.0500)  time: 1.0068  data: 0.0005  max mem: 78493
Epoch: [232]  [220/312]  eta: 0:01:39  lr: 0.000544  min_lr: 0.000544  loss: 1.9903 (1.9161)  weight_decay: 0.0500 (0.0500)  time: 1.0051  data: 0.0004  max mem: 78493
Epoch: [232]  [230/312]  eta: 0:01:28  lr: 0.000544  min_lr: 0.000544  loss: 1.7178 (1.9134)  weight_decay: 0.0500 (0.0500)  time: 1.0054  data: 0.0004  max mem: 78493
Epoch: [232]  [240/312]  eta: 0:01:17  lr: 0.000543  min_lr: 0.000543  loss: 1.8899 (1.9145)  weight_decay: 0.0500 (0.0500)  time: 1.0061  data: 0.0004  max mem: 78493
Epoch: [232]  [250/312]  eta: 0:01:06  lr: 0.000543  min_lr: 0.000543  loss: 2.0103 (1.9182)  weight_decay: 0.0500 (0.0500)  time: 1.0065  data: 0.0004  max mem: 78493
Epoch: [232]  [260/312]  eta: 0:00:55  lr: 0.000542  min_lr: 0.000542  loss: 2.1678 (1.9272)  weight_decay: 0.0500 (0.0500)  time: 1.0086  data: 0.0004  max mem: 78493
Epoch: [232]  [270/312]  eta: 0:00:44  lr: 0.000542  min_lr: 0.000542  loss: 2.1824 (1.9303)  weight_decay: 0.0500 (0.0500)  time: 1.0087  data: 0.0004  max mem: 78493
Epoch: [232]  [280/312]  eta: 0:00:34  lr: 0.000541  min_lr: 0.000541  loss: 2.1076 (1.9336)  weight_decay: 0.0500 (0.0500)  time: 1.0054  data: 0.0010  max mem: 78493
Epoch: [232]  [290/312]  eta: 0:00:23  lr: 0.000541  min_lr: 0.000541  loss: 2.0491 (1.9274)  weight_decay: 0.0500 (0.0500)  time: 1.0025  data: 0.0009  max mem: 78493
Epoch: [232]  [300/312]  eta: 0:00:12  lr: 0.000540  min_lr: 0.000540  loss: 2.0491 (1.9291)  weight_decay: 0.0500 (0.0500)  time: 1.0014  data: 0.0001  max mem: 78493
Epoch: [232]  [310/312]  eta: 0:00:02  lr: 0.000540  min_lr: 0.000540  loss: 1.9668 (1.9262)  weight_decay: 0.0500 (0.0500)  time: 1.0014  data: 0.0001  max mem: 78493
Epoch: [232]  [311/312]  eta: 0:00:01  lr: 0.000540  min_lr: 0.000540  loss: 1.9668 (1.9268)  weight_decay: 0.0500 (0.0500)  time: 1.0014  data: 0.0001  max mem: 78493
Epoch: [232] Total time: 0:05:32 (1.0667 s / it)
Averaged stats: lr: 0.000540  min_lr: 0.000540  loss: 1.9668 (1.9649)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:14  loss: 0.5440 (0.5440)  acc1: 85.5469 (85.5469)  acc5: 97.5260 (97.5260)  time: 8.3263  data: 8.0602  max mem: 78493
Test:  [8/9]  eta: 0:00:01  loss: 0.8004 (0.7389)  acc1: 80.7292 (80.2560)  acc5: 95.7031 (95.3760)  time: 1.1250  data: 0.8957  max mem: 78493
Test: Total time: 0:00:10 (1.1495 s / it)
* Acc@1 80.684 Acc@5 95.398 loss 0.728
Accuracy of the model on the 50000 test images: 80.7%
Max accuracy: 80.90%
Epoch: [233]  [  0/312]  eta: 1:25:32  lr: 0.000540  min_lr: 0.000540  loss: 2.6332 (2.6332)  weight_decay: 0.0500 (0.0500)  time: 16.4489  data: 12.8783  max mem: 78493
Epoch: [233]  [ 10/312]  eta: 0:13:53  lr: 0.000539  min_lr: 0.000539  loss: 2.1690 (2.2047)  weight_decay: 0.0500 (0.0500)  time: 2.7590  data: 1.2660  max mem: 78493
Epoch: [233]  [ 20/312]  eta: 0:09:21  lr: 0.000539  min_lr: 0.000539  loss: 2.0645 (2.0988)  weight_decay: 0.0500 (0.0500)  time: 1.1972  data: 0.0527  max mem: 78493
Epoch: [233]  [ 30/312]  eta: 0:07:39  lr: 0.000538  min_lr: 0.000538  loss: 2.0541 (2.0616)  weight_decay: 0.0500 (0.0500)  time: 1.0060  data: 0.0005  max mem: 78493
Epoch: [233]  [ 40/312]  eta: 0:06:41  lr: 0.000538  min_lr: 0.000538  loss: 2.1308 (2.0553)  weight_decay: 0.0500 (0.0500)  time: 1.0081  data: 0.0005  max mem: 78493
Epoch: [233]  [ 50/312]  eta: 0:06:02  lr: 0.000537  min_lr: 0.000537  loss: 2.1350 (2.0385)  weight_decay: 0.0500 (0.0500)  time: 1.0075  data: 0.0004  max mem: 78493
Epoch: [233]  [ 60/312]  eta: 0:05:33  lr: 0.000537  min_lr: 0.000537  loss: 2.0208 (2.0274)  weight_decay: 0.0500 (0.0500)  time: 1.0050  data: 0.0011  max mem: 78493
Epoch: [233]  [ 70/312]  eta: 0:05:09  lr: 0.000536  min_lr: 0.000536  loss: 1.9696 (2.0171)  weight_decay: 0.0500 (0.0500)  time: 1.0059  data: 0.0011  max mem: 78493
Epoch: [233]  [ 80/312]  eta: 0:04:48  lr: 0.000536  min_lr: 0.000536  loss: 1.9096 (1.9941)  weight_decay: 0.0500 (0.0500)  time: 1.0054  data: 0.0005  max mem: 78493
Epoch: [233]  [ 90/312]  eta: 0:04:30  lr: 0.000535  min_lr: 0.000535  loss: 1.6294 (1.9790)  weight_decay: 0.0500 (0.0500)  time: 1.0049  data: 0.0005  max mem: 78493
Epoch: [233]  [100/312]  eta: 0:04:13  lr: 0.000535  min_lr: 0.000535  loss: 1.9935 (1.9840)  weight_decay: 0.0500 (0.0500)  time: 1.0074  data: 0.0005  max mem: 78493
Epoch: [233]  [110/312]  eta: 0:03:58  lr: 0.000534  min_lr: 0.000534  loss: 1.8226 (1.9677)  weight_decay: 0.0500 (0.0500)  time: 1.0065  data: 0.0005  max mem: 78493
Epoch: [233]  [120/312]  eta: 0:03:43  lr: 0.000534  min_lr: 0.000534  loss: 1.7790 (1.9703)  weight_decay: 0.0500 (0.0500)  time: 1.0068  data: 0.0005  max mem: 78493
Epoch: [233]  [130/312]  eta: 0:03:29  lr: 0.000533  min_lr: 0.000533  loss: 2.1439 (1.9723)  weight_decay: 0.0500 (0.0500)  time: 1.0077  data: 0.0004  max mem: 78493
Epoch: [233]  [140/312]  eta: 0:03:16  lr: 0.000533  min_lr: 0.000533  loss: 2.1365 (1.9747)  weight_decay: 0.0500 (0.0500)  time: 1.0059  data: 0.0004  max mem: 78493
Epoch: [233]  [150/312]  eta: 0:03:03  lr: 0.000533  min_lr: 0.000533  loss: 2.0850 (1.9784)  weight_decay: 0.0500 (0.0500)  time: 1.0061  data: 0.0004  max mem: 78493
Epoch: [233]  [160/312]  eta: 0:02:51  lr: 0.000532  min_lr: 0.000532  loss: 2.0010 (1.9730)  weight_decay: 0.0500 (0.0500)  time: 1.0073  data: 0.0004  max mem: 78493
Epoch: [233]  [170/312]  eta: 0:02:38  lr: 0.000532  min_lr: 0.000532  loss: 1.9677 (1.9758)  weight_decay: 0.0500 (0.0500)  time: 1.0099  data: 0.0004  max mem: 78493
Epoch: [233]  [180/312]  eta: 0:02:26  lr: 0.000531  min_lr: 0.000531  loss: 2.1143 (1.9756)  weight_decay: 0.0500 (0.0500)  time: 1.0112  data: 0.0004  max mem: 78493
Epoch: [233]  [190/312]  eta: 0:02:15  lr: 0.000531  min_lr: 0.000531  loss: 2.1446 (1.9844)  weight_decay: 0.0500 (0.0500)  time: 1.0101  data: 0.0012  max mem: 78493
Epoch: [233]  [200/312]  eta: 0:02:03  lr: 0.000530  min_lr: 0.000530  loss: 2.1765 (1.9956)  weight_decay: 0.0500 (0.0500)  time: 1.0090  data: 0.0012  max mem: 78493
Epoch: [233]  [210/312]  eta: 0:01:52  lr: 0.000530  min_lr: 0.000530  loss: 2.1507 (1.9877)  weight_decay: 0.0500 (0.0500)  time: 1.0080  data: 0.0005  max mem: 78493
Epoch: [233]  [220/312]  eta: 0:01:40  lr: 0.000529  min_lr: 0.000529  loss: 2.1405 (1.9974)  weight_decay: 0.0500 (0.0500)  time: 1.0074  data: 0.0004  max mem: 78493
Epoch: [233]  [230/312]  eta: 0:01:29  lr: 0.000529  min_lr: 0.000529  loss: 2.1456 (1.9921)  weight_decay: 0.0500 (0.0500)  time: 1.0069  data: 0.0013  max mem: 78493
Epoch: [233]  [240/312]  eta: 0:01:18  lr: 0.000528  min_lr: 0.000528  loss: 2.1068 (1.9904)  weight_decay: 0.0500 (0.0500)  time: 1.0076  data: 0.0013  max mem: 78493
Epoch: [233]  [250/312]  eta: 0:01:07  lr: 0.000528  min_lr: 0.000528  loss: 1.9967 (1.9910)  weight_decay: 0.0500 (0.0500)  time: 1.0062  data: 0.0004  max mem: 78493
Epoch: [233]  [260/312]  eta: 0:00:56  lr: 0.000527  min_lr: 0.000527  loss: 2.0226 (1.9906)  weight_decay: 0.0500 (0.0500)  time: 1.0065  data: 0.0005  max mem: 78493
Epoch: [233]  [270/312]  eta: 0:00:45  lr: 0.000527  min_lr: 0.000527  loss: 1.9380 (1.9883)  weight_decay: 0.0500 (0.0500)  time: 1.0073  data: 0.0011  max mem: 78493
Epoch: [233]  [280/312]  eta: 0:00:34  lr: 0.000526  min_lr: 0.000526  loss: 1.9380 (1.9928)  weight_decay: 0.0500 (0.0500)  time: 1.0089  data: 0.0016  max mem: 78493
Epoch: [233]  [290/312]  eta: 0:00:23  lr: 0.000526  min_lr: 0.000526  loss: 2.2144 (1.9994)  weight_decay: 0.0500 (0.0500)  time: 1.0069  data: 0.0009  max mem: 78493
Epoch: [233]  [300/312]  eta: 0:00:12  lr: 0.000525  min_lr: 0.000525  loss: 2.1522 (2.0023)  weight_decay: 0.0500 (0.0500)  time: 1.0020  data: 0.0001  max mem: 78493
Epoch: [233]  [310/312]  eta: 0:00:02  lr: 0.000525  min_lr: 0.000525  loss: 2.1445 (2.0049)  weight_decay: 0.0500 (0.0500)  time: 1.0013  data: 0.0001  max mem: 78493
Epoch: [233]  [311/312]  eta: 0:00:01  lr: 0.000525  min_lr: 0.000525  loss: 2.1445 (2.0040)  weight_decay: 0.0500 (0.0500)  time: 1.0013  data: 0.0001  max mem: 78493
Epoch: [233] Total time: 0:05:35 (1.0745 s / it)
Averaged stats: lr: 0.000525  min_lr: 0.000525  loss: 2.1445 (1.9773)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:17  loss: 0.5176 (0.5176)  acc1: 86.9792 (86.9792)  acc5: 97.6562 (97.6562)  time: 8.6487  data: 8.3672  max mem: 78493
Test:  [8/9]  eta: 0:00:01  loss: 0.8193 (0.7403)  acc1: 79.1667 (80.1280)  acc5: 95.4427 (95.0720)  time: 1.1593  data: 0.9298  max mem: 78493
Test: Total time: 0:00:10 (1.1723 s / it)
* Acc@1 80.788 Acc@5 95.372 loss 0.726
Accuracy of the model on the 50000 test images: 80.8%
Max accuracy: 80.90%
Epoch: [234]  [  0/312]  eta: 1:27:55  lr: 0.000525  min_lr: 0.000525  loss: 1.4463 (1.4463)  weight_decay: 0.0500 (0.0500)  time: 16.9072  data: 12.2791  max mem: 78493
Epoch: [234]  [ 10/312]  eta: 0:13:13  lr: 0.000524  min_lr: 0.000524  loss: 1.8755 (1.8336)  weight_decay: 0.0500 (0.0500)  time: 2.6276  data: 1.1916  max mem: 78493
Epoch: [234]  [ 20/312]  eta: 0:09:04  lr: 0.000524  min_lr: 0.000524  loss: 1.9126 (1.8837)  weight_decay: 0.0500 (0.0500)  time: 1.1114  data: 0.0417  max mem: 78493
Epoch: [234]  [ 30/312]  eta: 0:07:27  lr: 0.000523  min_lr: 0.000523  loss: 2.0591 (1.9549)  weight_decay: 0.0500 (0.0500)  time: 1.0160  data: 0.0005  max mem: 78493
Epoch: [234]  [ 40/312]  eta: 0:06:33  lr: 0.000523  min_lr: 0.000523  loss: 1.9782 (1.9412)  weight_decay: 0.0500 (0.0500)  time: 1.0068  data: 0.0004  max mem: 78493
Epoch: [234]  [ 50/312]  eta: 0:05:56  lr: 0.000522  min_lr: 0.000522  loss: 1.8413 (1.9096)  weight_decay: 0.0500 (0.0500)  time: 1.0054  data: 0.0004  max mem: 78493
Epoch: [234]  [ 60/312]  eta: 0:05:28  lr: 0.000522  min_lr: 0.000522  loss: 2.0398 (1.9608)  weight_decay: 0.0500 (0.0500)  time: 1.0070  data: 0.0004  max mem: 78493
Epoch: [234]  [ 70/312]  eta: 0:05:04  lr: 0.000521  min_lr: 0.000521  loss: 2.0710 (1.9655)  weight_decay: 0.0500 (0.0500)  time: 1.0075  data: 0.0004  max mem: 78493
Epoch: [234]  [ 80/312]  eta: 0:04:45  lr: 0.000521  min_lr: 0.000521  loss: 1.9484 (1.9683)  weight_decay: 0.0500 (0.0500)  time: 1.0074  data: 0.0004  max mem: 78493
Epoch: [234]  [ 90/312]  eta: 0:04:27  lr: 0.000520  min_lr: 0.000520  loss: 2.0892 (1.9916)  weight_decay: 0.0500 (0.0500)  time: 1.0076  data: 0.0004  max mem: 78493
Epoch: [234]  [100/312]  eta: 0:04:11  lr: 0.000520  min_lr: 0.000520  loss: 1.9980 (1.9748)  weight_decay: 0.0500 (0.0500)  time: 1.0090  data: 0.0004  max mem: 78493
Epoch: [234]  [110/312]  eta: 0:03:56  lr: 0.000519  min_lr: 0.000519  loss: 1.9741 (1.9747)  weight_decay: 0.0500 (0.0500)  time: 1.0085  data: 0.0005  max mem: 78493
Epoch: [234]  [120/312]  eta: 0:03:41  lr: 0.000519  min_lr: 0.000519  loss: 2.1158 (1.9842)  weight_decay: 0.0500 (0.0500)  time: 1.0068  data: 0.0005  max mem: 78493
Epoch: [234]  [130/312]  eta: 0:03:28  lr: 0.000518  min_lr: 0.000518  loss: 2.2078 (2.0001)  weight_decay: 0.0500 (0.0500)  time: 1.0080  data: 0.0005  max mem: 78493
Epoch: [234]  [140/312]  eta: 0:03:15  lr: 0.000518  min_lr: 0.000518  loss: 2.0910 (1.9906)  weight_decay: 0.0500 (0.0500)  time: 1.0066  data: 0.0004  max mem: 78493
Epoch: [234]  [150/312]  eta: 0:03:02  lr: 0.000517  min_lr: 0.000517  loss: 2.0113 (1.9941)  weight_decay: 0.0500 (0.0500)  time: 1.0046  data: 0.0004  max mem: 78493
Epoch: [234]  [160/312]  eta: 0:02:50  lr: 0.000517  min_lr: 0.000517  loss: 1.9851 (1.9927)  weight_decay: 0.0500 (0.0500)  time: 1.0078  data: 0.0004  max mem: 78493
Epoch: [234]  [170/312]  eta: 0:02:37  lr: 0.000516  min_lr: 0.000516  loss: 1.9175 (1.9931)  weight_decay: 0.0500 (0.0500)  time: 1.0082  data: 0.0018  max mem: 78493
Epoch: [234]  [180/312]  eta: 0:02:26  lr: 0.000516  min_lr: 0.000516  loss: 2.0038 (1.9879)  weight_decay: 0.0500 (0.0500)  time: 1.0060  data: 0.0018  max mem: 78493
Epoch: [234]  [190/312]  eta: 0:02:14  lr: 0.000515  min_lr: 0.000515  loss: 2.1121 (1.9955)  weight_decay: 0.0500 (0.0500)  time: 1.0055  data: 0.0004  max mem: 78493
Epoch: [234]  [200/312]  eta: 0:02:02  lr: 0.000515  min_lr: 0.000515  loss: 2.1577 (1.9988)  weight_decay: 0.0500 (0.0500)  time: 1.0051  data: 0.0004  max mem: 78493
Epoch: [234]  [210/312]  eta: 0:01:51  lr: 0.000514  min_lr: 0.000514  loss: 2.1602 (2.0011)  weight_decay: 0.0500 (0.0500)  time: 1.0052  data: 0.0004  max mem: 78493
Epoch: [234]  [220/312]  eta: 0:01:40  lr: 0.000514  min_lr: 0.000514  loss: 2.1002 (2.0033)  weight_decay: 0.0500 (0.0500)  time: 1.0054  data: 0.0005  max mem: 78493
Epoch: [234]  [230/312]  eta: 0:01:28  lr: 0.000514  min_lr: 0.000514  loss: 1.9378 (1.9991)  weight_decay: 0.0500 (0.0500)  time: 1.0054  data: 0.0005  max mem: 78493
Epoch: [234]  [240/312]  eta: 0:01:17  lr: 0.000513  min_lr: 0.000513  loss: 1.9280 (1.9932)  weight_decay: 0.0500 (0.0500)  time: 1.0044  data: 0.0004  max mem: 78493
Epoch: [234]  [250/312]  eta: 0:01:06  lr: 0.000513  min_lr: 0.000513  loss: 1.9950 (1.9938)  weight_decay: 0.0500 (0.0500)  time: 1.0036  data: 0.0004  max mem: 78493
Epoch: [234]  [260/312]  eta: 0:00:55  lr: 0.000512  min_lr: 0.000512  loss: 1.9959 (1.9964)  weight_decay: 0.0500 (0.0500)  time: 1.0047  data: 0.0004  max mem: 78493
Epoch: [234]  [270/312]  eta: 0:00:45  lr: 0.000512  min_lr: 0.000512  loss: 2.0814 (1.9989)  weight_decay: 0.0500 (0.0500)  time: 1.0051  data: 0.0004  max mem: 78493
Epoch: [234]  [280/312]  eta: 0:00:34  lr: 0.000511  min_lr: 0.000511  loss: 2.0631 (1.9990)  weight_decay: 0.0500 (0.0500)  time: 1.0053  data: 0.0010  max mem: 78493
Epoch: [234]  [290/312]  eta: 0:00:23  lr: 0.000511  min_lr: 0.000511  loss: 1.9019 (1.9952)  weight_decay: 0.0500 (0.0500)  time: 1.0044  data: 0.0009  max mem: 78493
Epoch: [234]  [300/312]  eta: 0:00:12  lr: 0.000510  min_lr: 0.000510  loss: 2.0036 (1.9970)  weight_decay: 0.0500 (0.0500)  time: 1.0025  data: 0.0001  max mem: 78493
Epoch: [234]  [310/312]  eta: 0:00:02  lr: 0.000510  min_lr: 0.000510  loss: 1.9221 (1.9923)  weight_decay: 0.0500 (0.0500)  time: 1.0023  data: 0.0001  max mem: 78493
Epoch: [234]  [311/312]  eta: 0:00:01  lr: 0.000510  min_lr: 0.000510  loss: 1.9221 (1.9931)  weight_decay: 0.0500 (0.0500)  time: 1.0022  data: 0.0001  max mem: 78493
Epoch: [234] Total time: 0:05:33 (1.0696 s / it)
Averaged stats: lr: 0.000510  min_lr: 0.000510  loss: 1.9221 (1.9709)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:17  loss: 0.5186 (0.5186)  acc1: 87.5000 (87.5000)  acc5: 97.1354 (97.1354)  time: 8.6159  data: 8.3485  max mem: 78493
Test:  [8/9]  eta: 0:00:01  loss: 0.7715 (0.7220)  acc1: 81.5104 (80.7360)  acc5: 95.7031 (95.3440)  time: 1.1567  data: 0.9277  max mem: 78493
Test: Total time: 0:00:10 (1.1888 s / it)
* Acc@1 81.064 Acc@5 95.492 loss 0.712
Accuracy of the model on the 50000 test images: 81.1%
Max accuracy: 81.06%
Epoch: [235]  [  0/312]  eta: 1:23:20  lr: 0.000510  min_lr: 0.000510  loss: 2.1074 (2.1074)  weight_decay: 0.0500 (0.0500)  time: 16.0276  data: 15.0143  max mem: 78493
Epoch: [235]  [ 10/312]  eta: 0:12:48  lr: 0.000509  min_lr: 0.000509  loss: 1.9639 (1.9186)  weight_decay: 0.0500 (0.0500)  time: 2.5450  data: 1.4535  max mem: 78493
Epoch: [235]  [ 20/312]  eta: 0:08:52  lr: 0.000509  min_lr: 0.000509  loss: 1.9639 (1.9124)  weight_decay: 0.0500 (0.0500)  time: 1.1120  data: 0.0491  max mem: 78493
Epoch: [235]  [ 30/312]  eta: 0:07:20  lr: 0.000508  min_lr: 0.000508  loss: 2.0869 (1.9425)  weight_decay: 0.0500 (0.0500)  time: 1.0195  data: 0.0005  max mem: 78493
Epoch: [235]  [ 40/312]  eta: 0:06:28  lr: 0.000508  min_lr: 0.000508  loss: 2.0835 (1.9545)  weight_decay: 0.0500 (0.0500)  time: 1.0119  data: 0.0005  max mem: 78493
Epoch: [235]  [ 50/312]  eta: 0:05:52  lr: 0.000507  min_lr: 0.000507  loss: 2.0835 (1.9605)  weight_decay: 0.0500 (0.0500)  time: 1.0103  data: 0.0005  max mem: 78493
Epoch: [235]  [ 60/312]  eta: 0:05:24  lr: 0.000507  min_lr: 0.000507  loss: 2.0126 (1.9552)  weight_decay: 0.0500 (0.0500)  time: 1.0082  data: 0.0005  max mem: 78493
Epoch: [235]  [ 70/312]  eta: 0:05:02  lr: 0.000506  min_lr: 0.000506  loss: 2.0126 (1.9557)  weight_decay: 0.0500 (0.0500)  time: 1.0101  data: 0.0005  max mem: 78493
Epoch: [235]  [ 80/312]  eta: 0:04:43  lr: 0.000506  min_lr: 0.000506  loss: 2.0011 (1.9589)  weight_decay: 0.0500 (0.0500)  time: 1.0103  data: 0.0004  max mem: 78493
Epoch: [235]  [ 90/312]  eta: 0:04:25  lr: 0.000505  min_lr: 0.000505  loss: 1.9867 (1.9542)  weight_decay: 0.0500 (0.0500)  time: 1.0105  data: 0.0004  max mem: 78493
Epoch: [235]  [100/312]  eta: 0:04:09  lr: 0.000505  min_lr: 0.000505  loss: 2.0424 (1.9647)  weight_decay: 0.0500 (0.0500)  time: 1.0109  data: 0.0005  max mem: 78493
Epoch: [235]  [110/312]  eta: 0:03:55  lr: 0.000504  min_lr: 0.000504  loss: 2.0116 (1.9612)  weight_decay: 0.0500 (0.0500)  time: 1.0084  data: 0.0005  max mem: 78493
Epoch: [235]  [120/312]  eta: 0:03:41  lr: 0.000504  min_lr: 0.000504  loss: 2.0010 (1.9671)  weight_decay: 0.0500 (0.0500)  time: 1.0101  data: 0.0020  max mem: 78493
Epoch: [235]  [130/312]  eta: 0:03:27  lr: 0.000503  min_lr: 0.000503  loss: 1.9224 (1.9591)  weight_decay: 0.0500 (0.0500)  time: 1.0108  data: 0.0020  max mem: 78493
Epoch: [235]  [140/312]  eta: 0:03:14  lr: 0.000503  min_lr: 0.000503  loss: 1.9681 (1.9672)  weight_decay: 0.0500 (0.0500)  time: 1.0087  data: 0.0013  max mem: 78493
Epoch: [235]  [150/312]  eta: 0:03:01  lr: 0.000502  min_lr: 0.000502  loss: 1.9540 (1.9560)  weight_decay: 0.0500 (0.0500)  time: 1.0093  data: 0.0014  max mem: 78493
Epoch: [235]  [160/312]  eta: 0:02:49  lr: 0.000502  min_lr: 0.000502  loss: 1.9540 (1.9640)  weight_decay: 0.0500 (0.0500)  time: 1.0108  data: 0.0005  max mem: 78493
Epoch: [235]  [170/312]  eta: 0:02:37  lr: 0.000501  min_lr: 0.000501  loss: 2.0670 (1.9696)  weight_decay: 0.0500 (0.0500)  time: 1.0111  data: 0.0004  max mem: 78493
Epoch: [235]  [180/312]  eta: 0:02:25  lr: 0.000501  min_lr: 0.000501  loss: 2.0287 (1.9628)  weight_decay: 0.0500 (0.0500)  time: 1.0090  data: 0.0004  max mem: 78493
Epoch: [235]  [190/312]  eta: 0:02:14  lr: 0.000501  min_lr: 0.000501  loss: 1.9511 (1.9663)  weight_decay: 0.0500 (0.0500)  time: 1.0085  data: 0.0004  max mem: 78493
Epoch: [235]  [200/312]  eta: 0:02:02  lr: 0.000500  min_lr: 0.000500  loss: 2.0195 (1.9625)  weight_decay: 0.0500 (0.0500)  time: 1.0114  data: 0.0004  max mem: 78493
Epoch: [235]  [210/312]  eta: 0:01:51  lr: 0.000500  min_lr: 0.000500  loss: 1.9968 (1.9654)  weight_decay: 0.0500 (0.0500)  time: 1.0097  data: 0.0004  max mem: 78493
Epoch: [235]  [220/312]  eta: 0:01:40  lr: 0.000499  min_lr: 0.000499  loss: 1.9749 (1.9646)  weight_decay: 0.0500 (0.0500)  time: 1.0075  data: 0.0004  max mem: 78493
Epoch: [235]  [230/312]  eta: 0:01:28  lr: 0.000499  min_lr: 0.000499  loss: 1.9694 (1.9602)  weight_decay: 0.0500 (0.0500)  time: 1.0077  data: 0.0005  max mem: 78493
Epoch: [235]  [240/312]  eta: 0:01:17  lr: 0.000498  min_lr: 0.000498  loss: 1.8286 (1.9550)  weight_decay: 0.0500 (0.0500)  time: 1.0070  data: 0.0004  max mem: 78493
Epoch: [235]  [250/312]  eta: 0:01:06  lr: 0.000498  min_lr: 0.000498  loss: 1.9592 (1.9590)  weight_decay: 0.0500 (0.0500)  time: 1.0085  data: 0.0004  max mem: 78493
Epoch: [235]  [260/312]  eta: 0:00:55  lr: 0.000497  min_lr: 0.000497  loss: 2.1269 (1.9584)  weight_decay: 0.0500 (0.0500)  time: 1.0083  data: 0.0004  max mem: 78493
Epoch: [235]  [270/312]  eta: 0:00:45  lr: 0.000497  min_lr: 0.000497  loss: 2.0862 (1.9603)  weight_decay: 0.0500 (0.0500)  time: 1.0060  data: 0.0004  max mem: 78493
Epoch: [235]  [280/312]  eta: 0:00:34  lr: 0.000496  min_lr: 0.000496  loss: 2.0027 (1.9547)  weight_decay: 0.0500 (0.0500)  time: 1.0067  data: 0.0011  max mem: 78493
Epoch: [235]  [290/312]  eta: 0:00:23  lr: 0.000496  min_lr: 0.000496  loss: 2.0069 (1.9612)  weight_decay: 0.0500 (0.0500)  time: 1.0050  data: 0.0009  max mem: 78493
Epoch: [235]  [300/312]  eta: 0:00:12  lr: 0.000495  min_lr: 0.000495  loss: 2.1129 (1.9598)  weight_decay: 0.0500 (0.0500)  time: 1.0019  data: 0.0001  max mem: 78493
Epoch: [235]  [310/312]  eta: 0:00:02  lr: 0.000495  min_lr: 0.000495  loss: 2.0625 (1.9624)  weight_decay: 0.0500 (0.0500)  time: 1.0019  data: 0.0001  max mem: 78493
Epoch: [235]  [311/312]  eta: 0:00:01  lr: 0.000495  min_lr: 0.000495  loss: 2.0649 (1.9630)  weight_decay: 0.0500 (0.0500)  time: 1.0018  data: 0.0001  max mem: 78493
Epoch: [235] Total time: 0:05:33 (1.0690 s / it)
Averaged stats: lr: 0.000495  min_lr: 0.000495  loss: 2.0649 (1.9742)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:08  loss: 0.5318 (0.5318)  acc1: 85.5469 (85.5469)  acc5: 98.0469 (98.0469)  time: 7.6136  data: 7.3316  max mem: 78493
Test:  [8/9]  eta: 0:00:01  loss: 0.7923 (0.7343)  acc1: 81.1198 (80.5280)  acc5: 96.0938 (95.4720)  time: 1.0873  data: 0.8578  max mem: 78493
Test: Total time: 0:00:09 (1.0987 s / it)
* Acc@1 81.058 Acc@5 95.522 loss 0.717
Accuracy of the model on the 50000 test images: 81.1%
Max accuracy: 81.06%
Epoch: [236]  [  0/312]  eta: 1:25:22  lr: 0.000495  min_lr: 0.000495  loss: 1.8184 (1.8184)  weight_decay: 0.0500 (0.0500)  time: 16.4188  data: 12.0844  max mem: 78493
Epoch: [236]  [ 10/312]  eta: 0:13:21  lr: 0.000494  min_lr: 0.000494  loss: 2.0428 (1.8791)  weight_decay: 0.0500 (0.0500)  time: 2.6533  data: 1.1764  max mem: 78493
Epoch: [236]  [ 20/312]  eta: 0:09:07  lr: 0.000494  min_lr: 0.000494  loss: 2.0428 (1.9198)  weight_decay: 0.0500 (0.0500)  time: 1.1483  data: 0.0440  max mem: 78493
Epoch: [236]  [ 30/312]  eta: 0:07:30  lr: 0.000493  min_lr: 0.000493  loss: 1.9041 (1.8708)  weight_decay: 0.0500 (0.0500)  time: 1.0152  data: 0.0015  max mem: 78493
Epoch: [236]  [ 40/312]  eta: 0:06:35  lr: 0.000493  min_lr: 0.000493  loss: 1.8737 (1.9115)  weight_decay: 0.0500 (0.0500)  time: 1.0108  data: 0.0005  max mem: 78493
Epoch: [236]  [ 50/312]  eta: 0:05:57  lr: 0.000492  min_lr: 0.000492  loss: 2.0535 (1.9073)  weight_decay: 0.0500 (0.0500)  time: 1.0097  data: 0.0005  max mem: 78493
Epoch: [236]  [ 60/312]  eta: 0:05:29  lr: 0.000492  min_lr: 0.000492  loss: 2.0763 (1.9220)  weight_decay: 0.0500 (0.0500)  time: 1.0086  data: 0.0005  max mem: 78493
Epoch: [236]  [ 70/312]  eta: 0:05:06  lr: 0.000491  min_lr: 0.000491  loss: 1.9965 (1.8975)  weight_decay: 0.0500 (0.0500)  time: 1.0080  data: 0.0004  max mem: 78493
Epoch: [236]  [ 80/312]  eta: 0:04:46  lr: 0.000491  min_lr: 0.000491  loss: 1.8297 (1.8878)  weight_decay: 0.0500 (0.0500)  time: 1.0081  data: 0.0005  max mem: 78493
Epoch: [236]  [ 90/312]  eta: 0:04:28  lr: 0.000490  min_lr: 0.000490  loss: 1.9226 (1.8863)  weight_decay: 0.0500 (0.0500)  time: 1.0085  data: 0.0005  max mem: 78493
Epoch: [236]  [100/312]  eta: 0:04:12  lr: 0.000490  min_lr: 0.000490  loss: 2.1484 (1.9042)  weight_decay: 0.0500 (0.0500)  time: 1.0083  data: 0.0005  max mem: 78493
Epoch: [236]  [110/312]  eta: 0:03:56  lr: 0.000490  min_lr: 0.000490  loss: 2.1558 (1.9140)  weight_decay: 0.0500 (0.0500)  time: 1.0095  data: 0.0005  max mem: 78493
Epoch: [236]  [120/312]  eta: 0:03:42  lr: 0.000489  min_lr: 0.000489  loss: 2.0846 (1.9143)  weight_decay: 0.0500 (0.0500)  time: 1.0104  data: 0.0004  max mem: 78493
Epoch: [236]  [130/312]  eta: 0:03:28  lr: 0.000489  min_lr: 0.000489  loss: 2.0883 (1.9286)  weight_decay: 0.0500 (0.0500)  time: 1.0082  data: 0.0004  max mem: 78493
Epoch: [236]  [140/312]  eta: 0:03:15  lr: 0.000488  min_lr: 0.000488  loss: 2.0328 (1.9251)  weight_decay: 0.0500 (0.0500)  time: 1.0057  data: 0.0004  max mem: 78493
Epoch: [236]  [150/312]  eta: 0:03:02  lr: 0.000488  min_lr: 0.000488  loss: 1.8693 (1.9271)  weight_decay: 0.0500 (0.0500)  time: 1.0062  data: 0.0004  max mem: 78493
Epoch: [236]  [160/312]  eta: 0:02:50  lr: 0.000487  min_lr: 0.000487  loss: 1.9707 (1.9290)  weight_decay: 0.0500 (0.0500)  time: 1.0068  data: 0.0004  max mem: 78493
Epoch: [236]  [170/312]  eta: 0:02:38  lr: 0.000487  min_lr: 0.000487  loss: 2.0542 (1.9379)  weight_decay: 0.0500 (0.0500)  time: 1.0062  data: 0.0004  max mem: 78493
Epoch: [236]  [180/312]  eta: 0:02:26  lr: 0.000486  min_lr: 0.000486  loss: 2.0113 (1.9336)  weight_decay: 0.0500 (0.0500)  time: 1.0089  data: 0.0004  max mem: 78493
Epoch: [236]  [190/312]  eta: 0:02:14  lr: 0.000486  min_lr: 0.000486  loss: 1.9310 (1.9373)  weight_decay: 0.0500 (0.0500)  time: 1.0118  data: 0.0005  max mem: 78493
Epoch: [236]  [200/312]  eta: 0:02:03  lr: 0.000485  min_lr: 0.000485  loss: 1.9430 (1.9322)  weight_decay: 0.0500 (0.0500)  time: 1.0097  data: 0.0004  max mem: 78493
Epoch: [236]  [210/312]  eta: 0:01:51  lr: 0.000485  min_lr: 0.000485  loss: 2.1193 (1.9432)  weight_decay: 0.0500 (0.0500)  time: 1.0075  data: 0.0004  max mem: 78493
Epoch: [236]  [220/312]  eta: 0:01:40  lr: 0.000484  min_lr: 0.000484  loss: 2.1117 (1.9407)  weight_decay: 0.0500 (0.0500)  time: 1.0065  data: 0.0005  max mem: 78493
Epoch: [236]  [230/312]  eta: 0:01:29  lr: 0.000484  min_lr: 0.000484  loss: 2.0677 (1.9435)  weight_decay: 0.0500 (0.0500)  time: 1.0048  data: 0.0004  max mem: 78493
Epoch: [236]  [240/312]  eta: 0:01:18  lr: 0.000483  min_lr: 0.000483  loss: 1.8742 (1.9390)  weight_decay: 0.0500 (0.0500)  time: 1.0041  data: 0.0004  max mem: 78493
Epoch: [236]  [250/312]  eta: 0:01:06  lr: 0.000483  min_lr: 0.000483  loss: 1.7335 (1.9353)  weight_decay: 0.0500 (0.0500)  time: 1.0063  data: 0.0004  max mem: 78493
Epoch: [236]  [260/312]  eta: 0:00:56  lr: 0.000482  min_lr: 0.000482  loss: 1.9713 (1.9342)  weight_decay: 0.0500 (0.0500)  time: 1.0083  data: 0.0004  max mem: 78493
Epoch: [236]  [270/312]  eta: 0:00:45  lr: 0.000482  min_lr: 0.000482  loss: 2.0422 (1.9352)  weight_decay: 0.0500 (0.0500)  time: 1.0083  data: 0.0005  max mem: 78493
Epoch: [236]  [280/312]  eta: 0:00:34  lr: 0.000482  min_lr: 0.000482  loss: 2.1094 (1.9391)  weight_decay: 0.0500 (0.0500)  time: 1.0073  data: 0.0010  max mem: 78493
Epoch: [236]  [290/312]  eta: 0:00:23  lr: 0.000481  min_lr: 0.000481  loss: 2.1094 (1.9403)  weight_decay: 0.0500 (0.0500)  time: 1.0040  data: 0.0009  max mem: 78493
Epoch: [236]  [300/312]  eta: 0:00:12  lr: 0.000481  min_lr: 0.000481  loss: 1.9481 (1.9381)  weight_decay: 0.0500 (0.0500)  time: 1.0019  data: 0.0001  max mem: 78493
Epoch: [236]  [310/312]  eta: 0:00:02  lr: 0.000480  min_lr: 0.000480  loss: 1.9437 (1.9388)  weight_decay: 0.0500 (0.0500)  time: 1.0020  data: 0.0001  max mem: 78493
Epoch: [236]  [311/312]  eta: 0:00:01  lr: 0.000480  min_lr: 0.000480  loss: 1.9151 (1.9364)  weight_decay: 0.0500 (0.0500)  time: 1.0019  data: 0.0001  max mem: 78493
Epoch: [236] Total time: 0:05:34 (1.0715 s / it)
Averaged stats: lr: 0.000480  min_lr: 0.000480  loss: 1.9151 (1.9607)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:18  loss: 0.5070 (0.5070)  acc1: 86.1979 (86.1979)  acc5: 97.9167 (97.9167)  time: 8.7257  data: 8.4647  max mem: 78493
Test:  [8/9]  eta: 0:00:01  loss: 0.8018 (0.7228)  acc1: 79.8177 (80.4960)  acc5: 95.4427 (95.3120)  time: 1.1736  data: 0.9406  max mem: 78493
Test: Total time: 0:00:10 (1.2176 s / it)
* Acc@1 81.170 Acc@5 95.520 loss 0.707
Accuracy of the model on the 50000 test images: 81.2%
Max accuracy: 81.17%
Epoch: [237]  [  0/312]  eta: 1:23:28  lr: 0.000480  min_lr: 0.000480  loss: 1.5071 (1.5071)  weight_decay: 0.0500 (0.0500)  time: 16.0532  data: 15.0547  max mem: 78493
Epoch: [237]  [ 10/312]  eta: 0:13:04  lr: 0.000480  min_lr: 0.000480  loss: 1.7411 (1.7431)  weight_decay: 0.0500 (0.0500)  time: 2.5982  data: 1.3692  max mem: 78493
Epoch: [237]  [ 20/312]  eta: 0:08:59  lr: 0.000479  min_lr: 0.000479  loss: 1.9763 (1.8574)  weight_decay: 0.0500 (0.0500)  time: 1.1383  data: 0.0006  max mem: 78493
Epoch: [237]  [ 30/312]  eta: 0:07:25  lr: 0.000479  min_lr: 0.000479  loss: 1.9763 (1.8765)  weight_decay: 0.0500 (0.0500)  time: 1.0175  data: 0.0016  max mem: 78493
Epoch: [237]  [ 40/312]  eta: 0:06:31  lr: 0.000478  min_lr: 0.000478  loss: 1.9347 (1.8943)  weight_decay: 0.0500 (0.0500)  time: 1.0099  data: 0.0015  max mem: 78493
Epoch: [237]  [ 50/312]  eta: 0:05:54  lr: 0.000478  min_lr: 0.000478  loss: 2.1139 (1.9388)  weight_decay: 0.0500 (0.0500)  time: 1.0080  data: 0.0005  max mem: 78493
Epoch: [237]  [ 60/312]  eta: 0:05:27  lr: 0.000477  min_lr: 0.000477  loss: 2.1139 (1.9376)  weight_decay: 0.0500 (0.0500)  time: 1.0088  data: 0.0005  max mem: 78493
Epoch: [237]  [ 70/312]  eta: 0:05:04  lr: 0.000477  min_lr: 0.000477  loss: 2.0054 (1.9348)  weight_decay: 0.0500 (0.0500)  time: 1.0088  data: 0.0004  max mem: 78493
Epoch: [237]  [ 80/312]  eta: 0:04:44  lr: 0.000476  min_lr: 0.000476  loss: 2.0072 (1.9484)  weight_decay: 0.0500 (0.0500)  time: 1.0063  data: 0.0005  max mem: 78493
Epoch: [237]  [ 90/312]  eta: 0:04:26  lr: 0.000476  min_lr: 0.000476  loss: 2.0597 (1.9594)  weight_decay: 0.0500 (0.0500)  time: 1.0041  data: 0.0005  max mem: 78493
Epoch: [237]  [100/312]  eta: 0:04:10  lr: 0.000475  min_lr: 0.000475  loss: 1.9175 (1.9516)  weight_decay: 0.0500 (0.0500)  time: 1.0043  data: 0.0005  max mem: 78493
Epoch: [237]  [110/312]  eta: 0:03:55  lr: 0.000475  min_lr: 0.000475  loss: 1.8839 (1.9503)  weight_decay: 0.0500 (0.0500)  time: 1.0055  data: 0.0004  max mem: 78493
Epoch: [237]  [120/312]  eta: 0:03:41  lr: 0.000474  min_lr: 0.000474  loss: 2.0629 (1.9522)  weight_decay: 0.0500 (0.0500)  time: 1.0061  data: 0.0004  max mem: 78493
Epoch: [237]  [130/312]  eta: 0:03:27  lr: 0.000474  min_lr: 0.000474  loss: 1.9617 (1.9502)  weight_decay: 0.0500 (0.0500)  time: 1.0076  data: 0.0004  max mem: 78493
Epoch: [237]  [140/312]  eta: 0:03:14  lr: 0.000474  min_lr: 0.000474  loss: 1.9617 (1.9545)  weight_decay: 0.0500 (0.0500)  time: 1.0069  data: 0.0005  max mem: 78493
Epoch: [237]  [150/312]  eta: 0:03:02  lr: 0.000473  min_lr: 0.000473  loss: 2.0727 (1.9587)  weight_decay: 0.0500 (0.0500)  time: 1.0048  data: 0.0005  max mem: 78493
Epoch: [237]  [160/312]  eta: 0:02:49  lr: 0.000473  min_lr: 0.000473  loss: 1.9352 (1.9543)  weight_decay: 0.0500 (0.0500)  time: 1.0048  data: 0.0004  max mem: 78493
Epoch: [237]  [170/312]  eta: 0:02:37  lr: 0.000472  min_lr: 0.000472  loss: 2.0352 (1.9628)  weight_decay: 0.0500 (0.0500)  time: 1.0059  data: 0.0004  max mem: 78493
Epoch: [237]  [180/312]  eta: 0:02:25  lr: 0.000472  min_lr: 0.000472  loss: 2.1602 (1.9757)  weight_decay: 0.0500 (0.0500)  time: 1.0053  data: 0.0004  max mem: 78493
Epoch: [237]  [190/312]  eta: 0:02:14  lr: 0.000471  min_lr: 0.000471  loss: 2.1602 (1.9764)  weight_decay: 0.0500 (0.0500)  time: 1.0048  data: 0.0005  max mem: 78493
Epoch: [237]  [200/312]  eta: 0:02:02  lr: 0.000471  min_lr: 0.000471  loss: 1.8956 (1.9738)  weight_decay: 0.0500 (0.0500)  time: 1.0056  data: 0.0005  max mem: 78493
Epoch: [237]  [210/312]  eta: 0:01:51  lr: 0.000470  min_lr: 0.000470  loss: 1.9419 (1.9718)  weight_decay: 0.0500 (0.0500)  time: 1.0055  data: 0.0005  max mem: 78493
Epoch: [237]  [220/312]  eta: 0:01:39  lr: 0.000470  min_lr: 0.000470  loss: 2.0981 (1.9753)  weight_decay: 0.0500 (0.0500)  time: 1.0056  data: 0.0004  max mem: 78493
Epoch: [237]  [230/312]  eta: 0:01:28  lr: 0.000469  min_lr: 0.000469  loss: 1.9456 (1.9647)  weight_decay: 0.0500 (0.0500)  time: 1.0051  data: 0.0004  max mem: 78493
Epoch: [237]  [240/312]  eta: 0:01:17  lr: 0.000469  min_lr: 0.000469  loss: 1.9946 (1.9705)  weight_decay: 0.0500 (0.0500)  time: 1.0041  data: 0.0005  max mem: 78493
Epoch: [237]  [250/312]  eta: 0:01:06  lr: 0.000468  min_lr: 0.000468  loss: 2.0026 (1.9683)  weight_decay: 0.0500 (0.0500)  time: 1.0050  data: 0.0005  max mem: 78493
Epoch: [237]  [260/312]  eta: 0:00:55  lr: 0.000468  min_lr: 0.000468  loss: 1.9458 (1.9668)  weight_decay: 0.0500 (0.0500)  time: 1.0050  data: 0.0005  max mem: 78493
Epoch: [237]  [270/312]  eta: 0:00:44  lr: 0.000468  min_lr: 0.000468  loss: 1.9002 (1.9587)  weight_decay: 0.0500 (0.0500)  time: 1.0054  data: 0.0005  max mem: 78493
Epoch: [237]  [280/312]  eta: 0:00:34  lr: 0.000467  min_lr: 0.000467  loss: 1.6186 (1.9539)  weight_decay: 0.0500 (0.0500)  time: 1.0071  data: 0.0010  max mem: 78493
Epoch: [237]  [290/312]  eta: 0:00:23  lr: 0.000467  min_lr: 0.000467  loss: 1.8468 (1.9515)  weight_decay: 0.0500 (0.0500)  time: 1.0054  data: 0.0009  max mem: 78493
Epoch: [237]  [300/312]  eta: 0:00:12  lr: 0.000466  min_lr: 0.000466  loss: 1.9515 (1.9478)  weight_decay: 0.0500 (0.0500)  time: 1.0023  data: 0.0001  max mem: 78493
Epoch: [237]  [310/312]  eta: 0:00:02  lr: 0.000466  min_lr: 0.000466  loss: 1.9021 (1.9497)  weight_decay: 0.0500 (0.0500)  time: 1.0014  data: 0.0001  max mem: 78493
Epoch: [237]  [311/312]  eta: 0:00:01  lr: 0.000466  min_lr: 0.000466  loss: 1.9021 (1.9500)  weight_decay: 0.0500 (0.0500)  time: 1.0014  data: 0.0001  max mem: 78493
Epoch: [237] Total time: 0:05:33 (1.0683 s / it)
Averaged stats: lr: 0.000466  min_lr: 0.000466  loss: 1.9021 (1.9520)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:14  loss: 0.4857 (0.4857)  acc1: 87.6302 (87.6302)  acc5: 98.4375 (98.4375)  time: 8.3112  data: 8.0351  max mem: 78493
Test:  [8/9]  eta: 0:00:01  loss: 0.7851 (0.7218)  acc1: 80.5990 (80.7040)  acc5: 95.7031 (95.5360)  time: 1.1217  data: 0.8929  max mem: 78493
Test: Total time: 0:00:10 (1.1682 s / it)
* Acc@1 81.220 Acc@5 95.494 loss 0.713
Accuracy of the model on the 50000 test images: 81.2%
Max accuracy: 81.22%
Epoch: [238]  [  0/312]  eta: 1:18:22  lr: 0.000466  min_lr: 0.000466  loss: 2.1007 (2.1007)  weight_decay: 0.0500 (0.0500)  time: 15.0719  data: 12.2385  max mem: 78493
Epoch: [238]  [ 10/312]  eta: 0:12:36  lr: 0.000465  min_lr: 0.000465  loss: 2.0366 (2.0013)  weight_decay: 0.0500 (0.0500)  time: 2.5063  data: 1.3136  max mem: 78493
Epoch: [238]  [ 20/312]  eta: 0:08:45  lr: 0.000465  min_lr: 0.000465  loss: 2.0197 (1.9865)  weight_decay: 0.0500 (0.0500)  time: 1.1348  data: 0.1108  max mem: 78493
Epoch: [238]  [ 30/312]  eta: 0:07:15  lr: 0.000464  min_lr: 0.000464  loss: 2.0197 (1.9541)  weight_decay: 0.0500 (0.0500)  time: 1.0145  data: 0.0005  max mem: 78493
Epoch: [238]  [ 40/312]  eta: 0:06:24  lr: 0.000464  min_lr: 0.000464  loss: 2.1038 (1.9708)  weight_decay: 0.0500 (0.0500)  time: 1.0078  data: 0.0004  max mem: 78493
Epoch: [238]  [ 50/312]  eta: 0:05:49  lr: 0.000463  min_lr: 0.000463  loss: 2.0798 (1.9694)  weight_decay: 0.0500 (0.0500)  time: 1.0081  data: 0.0004  max mem: 78493
Epoch: [238]  [ 60/312]  eta: 0:05:22  lr: 0.000463  min_lr: 0.000463  loss: 2.0607 (1.9679)  weight_decay: 0.0500 (0.0500)  time: 1.0088  data: 0.0004  max mem: 78493
Epoch: [238]  [ 70/312]  eta: 0:05:00  lr: 0.000462  min_lr: 0.000462  loss: 2.0978 (1.9883)  weight_decay: 0.0500 (0.0500)  time: 1.0090  data: 0.0004  max mem: 78493
Epoch: [238]  [ 80/312]  eta: 0:04:41  lr: 0.000462  min_lr: 0.000462  loss: 2.1096 (1.9971)  weight_decay: 0.0500 (0.0500)  time: 1.0101  data: 0.0014  max mem: 78493
Epoch: [238]  [ 90/312]  eta: 0:04:24  lr: 0.000461  min_lr: 0.000461  loss: 2.1034 (1.9904)  weight_decay: 0.0500 (0.0500)  time: 1.0094  data: 0.0014  max mem: 78493
Epoch: [238]  [100/312]  eta: 0:04:08  lr: 0.000461  min_lr: 0.000461  loss: 2.0887 (2.0090)  weight_decay: 0.0500 (0.0500)  time: 1.0088  data: 0.0004  max mem: 78493
Epoch: [238]  [110/312]  eta: 0:03:53  lr: 0.000461  min_lr: 0.000461  loss: 2.0887 (2.0039)  weight_decay: 0.0500 (0.0500)  time: 1.0075  data: 0.0005  max mem: 78493
Epoch: [238]  [120/312]  eta: 0:03:39  lr: 0.000460  min_lr: 0.000460  loss: 1.9746 (1.9962)  weight_decay: 0.0500 (0.0500)  time: 1.0080  data: 0.0004  max mem: 78493
Epoch: [238]  [130/312]  eta: 0:03:26  lr: 0.000460  min_lr: 0.000460  loss: 2.1393 (2.0049)  weight_decay: 0.0500 (0.0500)  time: 1.0081  data: 0.0004  max mem: 78493
Epoch: [238]  [140/312]  eta: 0:03:13  lr: 0.000459  min_lr: 0.000459  loss: 2.1389 (2.0114)  weight_decay: 0.0500 (0.0500)  time: 1.0063  data: 0.0005  max mem: 78493
Epoch: [238]  [150/312]  eta: 0:03:01  lr: 0.000459  min_lr: 0.000459  loss: 1.9118 (2.0004)  weight_decay: 0.0500 (0.0500)  time: 1.0071  data: 0.0005  max mem: 78493
Epoch: [238]  [160/312]  eta: 0:02:48  lr: 0.000458  min_lr: 0.000458  loss: 1.9118 (1.9919)  weight_decay: 0.0500 (0.0500)  time: 1.0077  data: 0.0005  max mem: 78493
Epoch: [238]  [170/312]  eta: 0:02:36  lr: 0.000458  min_lr: 0.000458  loss: 2.0419 (1.9950)  weight_decay: 0.0500 (0.0500)  time: 1.0070  data: 0.0005  max mem: 78493
Epoch: [238]  [180/312]  eta: 0:02:25  lr: 0.000457  min_lr: 0.000457  loss: 1.9703 (1.9858)  weight_decay: 0.0500 (0.0500)  time: 1.0077  data: 0.0004  max mem: 78493
Epoch: [238]  [190/312]  eta: 0:02:13  lr: 0.000457  min_lr: 0.000457  loss: 1.8140 (1.9778)  weight_decay: 0.0500 (0.0500)  time: 1.0069  data: 0.0004  max mem: 78493
Epoch: [238]  [200/312]  eta: 0:02:02  lr: 0.000456  min_lr: 0.000456  loss: 1.9670 (1.9782)  weight_decay: 0.0500 (0.0500)  time: 1.0049  data: 0.0004  max mem: 78493
Epoch: [238]  [210/312]  eta: 0:01:50  lr: 0.000456  min_lr: 0.000456  loss: 2.0476 (1.9807)  weight_decay: 0.0500 (0.0500)  time: 1.0055  data: 0.0004  max mem: 78493
Epoch: [238]  [220/312]  eta: 0:01:39  lr: 0.000456  min_lr: 0.000456  loss: 2.0818 (1.9845)  weight_decay: 0.0500 (0.0500)  time: 1.0054  data: 0.0004  max mem: 78493
Epoch: [238]  [230/312]  eta: 0:01:28  lr: 0.000455  min_lr: 0.000455  loss: 2.0818 (1.9839)  weight_decay: 0.0500 (0.0500)  time: 1.0052  data: 0.0004  max mem: 78493
Epoch: [238]  [240/312]  eta: 0:01:17  lr: 0.000455  min_lr: 0.000455  loss: 2.0409 (1.9816)  weight_decay: 0.0500 (0.0500)  time: 1.0063  data: 0.0004  max mem: 78493
Epoch: [238]  [250/312]  eta: 0:01:06  lr: 0.000454  min_lr: 0.000454  loss: 1.9116 (1.9748)  weight_decay: 0.0500 (0.0500)  time: 1.0049  data: 0.0004  max mem: 78493
Epoch: [238]  [260/312]  eta: 0:00:55  lr: 0.000454  min_lr: 0.000454  loss: 1.9116 (1.9736)  weight_decay: 0.0500 (0.0500)  time: 1.0042  data: 0.0004  max mem: 78493
Epoch: [238]  [270/312]  eta: 0:00:44  lr: 0.000453  min_lr: 0.000453  loss: 2.0131 (1.9746)  weight_decay: 0.0500 (0.0500)  time: 1.0059  data: 0.0005  max mem: 78493
Epoch: [238]  [280/312]  eta: 0:00:34  lr: 0.000453  min_lr: 0.000453  loss: 2.0131 (1.9749)  weight_decay: 0.0500 (0.0500)  time: 1.0068  data: 0.0011  max mem: 78493
Epoch: [238]  [290/312]  eta: 0:00:23  lr: 0.000452  min_lr: 0.000452  loss: 1.7965 (1.9674)  weight_decay: 0.0500 (0.0500)  time: 1.0042  data: 0.0009  max mem: 78493
Epoch: [238]  [300/312]  eta: 0:00:12  lr: 0.000452  min_lr: 0.000452  loss: 1.7622 (1.9635)  weight_decay: 0.0500 (0.0500)  time: 1.0014  data: 0.0001  max mem: 78493
Epoch: [238]  [310/312]  eta: 0:00:02  lr: 0.000451  min_lr: 0.000451  loss: 2.0735 (1.9648)  weight_decay: 0.0500 (0.0500)  time: 1.0011  data: 0.0001  max mem: 78493
Epoch: [238]  [311/312]  eta: 0:00:01  lr: 0.000451  min_lr: 0.000451  loss: 2.0763 (1.9653)  weight_decay: 0.0500 (0.0500)  time: 1.0011  data: 0.0001  max mem: 78493
Epoch: [238] Total time: 0:05:32 (1.0654 s / it)
Averaged stats: lr: 0.000451  min_lr: 0.000451  loss: 2.0763 (1.9603)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:18  loss: 0.5270 (0.5270)  acc1: 85.6771 (85.6771)  acc5: 97.5260 (97.5260)  time: 8.7334  data: 8.4663  max mem: 78493
Test:  [8/9]  eta: 0:00:01  loss: 0.7878 (0.7184)  acc1: 80.7292 (80.7360)  acc5: 96.2240 (95.5680)  time: 1.1695  data: 0.9408  max mem: 78493
Test: Total time: 0:00:10 (1.1965 s / it)
* Acc@1 81.158 Acc@5 95.512 loss 0.703
Accuracy of the model on the 50000 test images: 81.2%
Max accuracy: 81.22%
Epoch: [239]  [  0/312]  eta: 1:24:07  lr: 0.000451  min_lr: 0.000451  loss: 2.1050 (2.1050)  weight_decay: 0.0500 (0.0500)  time: 16.1766  data: 14.5996  max mem: 78493
Epoch: [239]  [ 10/312]  eta: 0:12:57  lr: 0.000451  min_lr: 0.000451  loss: 1.9993 (1.9233)  weight_decay: 0.0500 (0.0500)  time: 2.5740  data: 1.3381  max mem: 78493
Epoch: [239]  [ 20/312]  eta: 0:08:56  lr: 0.000450  min_lr: 0.000450  loss: 1.9967 (1.9210)  weight_decay: 0.0500 (0.0500)  time: 1.1206  data: 0.0080  max mem: 78493
Epoch: [239]  [ 30/312]  eta: 0:07:22  lr: 0.000450  min_lr: 0.000450  loss: 1.9992 (1.9513)  weight_decay: 0.0500 (0.0500)  time: 1.0184  data: 0.0022  max mem: 78493
Epoch: [239]  [ 40/312]  eta: 0:06:29  lr: 0.000449  min_lr: 0.000449  loss: 2.1360 (2.0130)  weight_decay: 0.0500 (0.0500)  time: 1.0091  data: 0.0004  max mem: 78493
Epoch: [239]  [ 50/312]  eta: 0:05:53  lr: 0.000449  min_lr: 0.000449  loss: 2.1360 (1.9698)  weight_decay: 0.0500 (0.0500)  time: 1.0098  data: 0.0005  max mem: 78493
Epoch: [239]  [ 60/312]  eta: 0:05:26  lr: 0.000449  min_lr: 0.000449  loss: 1.7415 (1.9328)  weight_decay: 0.0500 (0.0500)  time: 1.0091  data: 0.0011  max mem: 78493
Epoch: [239]  [ 70/312]  eta: 0:05:03  lr: 0.000448  min_lr: 0.000448  loss: 1.9289 (1.9734)  weight_decay: 0.0500 (0.0500)  time: 1.0063  data: 0.0011  max mem: 78493
Epoch: [239]  [ 80/312]  eta: 0:04:43  lr: 0.000448  min_lr: 0.000448  loss: 2.1128 (1.9769)  weight_decay: 0.0500 (0.0500)  time: 1.0064  data: 0.0005  max mem: 78493
Epoch: [239]  [ 90/312]  eta: 0:04:26  lr: 0.000447  min_lr: 0.000447  loss: 2.1128 (1.9875)  weight_decay: 0.0500 (0.0500)  time: 1.0058  data: 0.0005  max mem: 78493
Epoch: [239]  [100/312]  eta: 0:04:10  lr: 0.000447  min_lr: 0.000447  loss: 2.0753 (1.9863)  weight_decay: 0.0500 (0.0500)  time: 1.0056  data: 0.0005  max mem: 78493
Epoch: [239]  [110/312]  eta: 0:03:55  lr: 0.000446  min_lr: 0.000446  loss: 1.9944 (1.9916)  weight_decay: 0.0500 (0.0500)  time: 1.0075  data: 0.0005  max mem: 78493
Epoch: [239]  [120/312]  eta: 0:03:41  lr: 0.000446  min_lr: 0.000446  loss: 2.0117 (1.9952)  weight_decay: 0.0500 (0.0500)  time: 1.0073  data: 0.0005  max mem: 78493
Epoch: [239]  [130/312]  eta: 0:03:27  lr: 0.000445  min_lr: 0.000445  loss: 2.1123 (1.9945)  weight_decay: 0.0500 (0.0500)  time: 1.0093  data: 0.0005  max mem: 78493
Epoch: [239]  [140/312]  eta: 0:03:14  lr: 0.000445  min_lr: 0.000445  loss: 1.9582 (1.9885)  weight_decay: 0.0500 (0.0500)  time: 1.0102  data: 0.0015  max mem: 78493
Epoch: [239]  [150/312]  eta: 0:03:01  lr: 0.000445  min_lr: 0.000445  loss: 2.0412 (1.9919)  weight_decay: 0.0500 (0.0500)  time: 1.0090  data: 0.0014  max mem: 78493
Epoch: [239]  [160/312]  eta: 0:02:49  lr: 0.000444  min_lr: 0.000444  loss: 2.0524 (1.9960)  weight_decay: 0.0500 (0.0500)  time: 1.0093  data: 0.0004  max mem: 78493
Epoch: [239]  [170/312]  eta: 0:02:37  lr: 0.000444  min_lr: 0.000444  loss: 2.0956 (2.0055)  weight_decay: 0.0500 (0.0500)  time: 1.0072  data: 0.0005  max mem: 78493
Epoch: [239]  [180/312]  eta: 0:02:25  lr: 0.000443  min_lr: 0.000443  loss: 2.1441 (2.0064)  weight_decay: 0.0500 (0.0500)  time: 1.0080  data: 0.0005  max mem: 78493
Epoch: [239]  [190/312]  eta: 0:02:14  lr: 0.000443  min_lr: 0.000443  loss: 2.0694 (2.0036)  weight_decay: 0.0500 (0.0500)  time: 1.0088  data: 0.0004  max mem: 78493
Epoch: [239]  [200/312]  eta: 0:02:02  lr: 0.000442  min_lr: 0.000442  loss: 1.9308 (1.9962)  weight_decay: 0.0500 (0.0500)  time: 1.0071  data: 0.0004  max mem: 78493
Epoch: [239]  [210/312]  eta: 0:01:51  lr: 0.000442  min_lr: 0.000442  loss: 1.9529 (1.9910)  weight_decay: 0.0500 (0.0500)  time: 1.0084  data: 0.0004  max mem: 78493
Epoch: [239]  [220/312]  eta: 0:01:39  lr: 0.000441  min_lr: 0.000441  loss: 1.9839 (1.9905)  weight_decay: 0.0500 (0.0500)  time: 1.0086  data: 0.0004  max mem: 78493
Epoch: [239]  [230/312]  eta: 0:01:28  lr: 0.000441  min_lr: 0.000441  loss: 2.0513 (1.9927)  weight_decay: 0.0500 (0.0500)  time: 1.0074  data: 0.0005  max mem: 78493
Epoch: [239]  [240/312]  eta: 0:01:17  lr: 0.000440  min_lr: 0.000440  loss: 2.0894 (1.9965)  weight_decay: 0.0500 (0.0500)  time: 1.0067  data: 0.0005  max mem: 78493
Epoch: [239]  [250/312]  eta: 0:01:06  lr: 0.000440  min_lr: 0.000440  loss: 2.0626 (1.9927)  weight_decay: 0.0500 (0.0500)  time: 1.0062  data: 0.0005  max mem: 78493
Epoch: [239]  [260/312]  eta: 0:00:55  lr: 0.000440  min_lr: 0.000440  loss: 1.8685 (1.9854)  weight_decay: 0.0500 (0.0500)  time: 1.0083  data: 0.0005  max mem: 78493
Epoch: [239]  [270/312]  eta: 0:00:45  lr: 0.000439  min_lr: 0.000439  loss: 1.8710 (1.9840)  weight_decay: 0.0500 (0.0500)  time: 1.0091  data: 0.0005  max mem: 78493
Epoch: [239]  [280/312]  eta: 0:00:34  lr: 0.000439  min_lr: 0.000439  loss: 1.9776 (1.9843)  weight_decay: 0.0500 (0.0500)  time: 1.0091  data: 0.0010  max mem: 78493
Epoch: [239]  [290/312]  eta: 0:00:23  lr: 0.000438  min_lr: 0.000438  loss: 2.1313 (1.9882)  weight_decay: 0.0500 (0.0500)  time: 1.0062  data: 0.0009  max mem: 78493
Epoch: [239]  [300/312]  eta: 0:00:12  lr: 0.000438  min_lr: 0.000438  loss: 2.0670 (1.9880)  weight_decay: 0.0500 (0.0500)  time: 1.0021  data: 0.0001  max mem: 78493
Epoch: [239]  [310/312]  eta: 0:00:02  lr: 0.000437  min_lr: 0.000437  loss: 1.9947 (1.9843)  weight_decay: 0.0500 (0.0500)  time: 1.0020  data: 0.0001  max mem: 78493
Epoch: [239]  [311/312]  eta: 0:00:01  lr: 0.000437  min_lr: 0.000437  loss: 2.0563 (1.9846)  weight_decay: 0.0500 (0.0500)  time: 1.0021  data: 0.0001  max mem: 78493
Epoch: [239] Total time: 0:05:33 (1.0691 s / it)
Averaged stats: lr: 0.000437  min_lr: 0.000437  loss: 2.0563 (1.9522)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:15  loss: 0.5128 (0.5128)  acc1: 87.2396 (87.2396)  acc5: 97.2656 (97.2656)  time: 8.3440  data: 8.0549  max mem: 78493
Test:  [8/9]  eta: 0:00:01  loss: 0.7844 (0.7108)  acc1: 80.8594 (81.2640)  acc5: 96.3542 (95.5360)  time: 1.1254  data: 0.8951  max mem: 78493
Test: Total time: 0:00:10 (1.1699 s / it)
* Acc@1 81.442 Acc@5 95.614 loss 0.701
Accuracy of the model on the 50000 test images: 81.4%
Max accuracy: 81.44%
Epoch: [240]  [  0/312]  eta: 1:15:35  lr: 0.000437  min_lr: 0.000437  loss: 1.6103 (1.6103)  weight_decay: 0.0500 (0.0500)  time: 14.5376  data: 13.4947  max mem: 78493
Epoch: [240]  [ 10/312]  eta: 0:12:22  lr: 0.000437  min_lr: 0.000437  loss: 2.0516 (2.0139)  weight_decay: 0.0500 (0.0500)  time: 2.4571  data: 1.3249  max mem: 78493
Epoch: [240]  [ 20/312]  eta: 0:08:39  lr: 0.000436  min_lr: 0.000436  loss: 2.0873 (2.0020)  weight_decay: 0.0500 (0.0500)  time: 1.1427  data: 0.0551  max mem: 78493
Epoch: [240]  [ 30/312]  eta: 0:07:12  lr: 0.000436  min_lr: 0.000436  loss: 2.0615 (2.0003)  weight_decay: 0.0500 (0.0500)  time: 1.0253  data: 0.0014  max mem: 78493
Epoch: [240]  [ 40/312]  eta: 0:06:22  lr: 0.000435  min_lr: 0.000435  loss: 1.9378 (1.9760)  weight_decay: 0.0500 (0.0500)  time: 1.0119  data: 0.0004  max mem: 78493
Epoch: [240]  [ 50/312]  eta: 0:05:47  lr: 0.000435  min_lr: 0.000435  loss: 1.9412 (1.9762)  weight_decay: 0.0500 (0.0500)  time: 1.0096  data: 0.0004  max mem: 78493
Epoch: [240]  [ 60/312]  eta: 0:05:21  lr: 0.000435  min_lr: 0.000435  loss: 2.0690 (1.9848)  weight_decay: 0.0500 (0.0500)  time: 1.0081  data: 0.0005  max mem: 78493
Epoch: [240]  [ 70/312]  eta: 0:04:59  lr: 0.000434  min_lr: 0.000434  loss: 2.0559 (1.9750)  weight_decay: 0.0500 (0.0500)  time: 1.0064  data: 0.0005  max mem: 78493
Epoch: [240]  [ 80/312]  eta: 0:04:40  lr: 0.000434  min_lr: 0.000434  loss: 1.9730 (1.9635)  weight_decay: 0.0500 (0.0500)  time: 1.0070  data: 0.0005  max mem: 78493
Epoch: [240]  [ 90/312]  eta: 0:04:23  lr: 0.000433  min_lr: 0.000433  loss: 1.9297 (1.9543)  weight_decay: 0.0500 (0.0500)  time: 1.0086  data: 0.0004  max mem: 78493
Epoch: [240]  [100/312]  eta: 0:04:07  lr: 0.000433  min_lr: 0.000433  loss: 1.9629 (1.9475)  weight_decay: 0.0500 (0.0500)  time: 1.0093  data: 0.0004  max mem: 78493
Epoch: [240]  [110/312]  eta: 0:03:53  lr: 0.000432  min_lr: 0.000432  loss: 2.0795 (1.9495)  weight_decay: 0.0500 (0.0500)  time: 1.0074  data: 0.0005  max mem: 78493
Epoch: [240]  [120/312]  eta: 0:03:39  lr: 0.000432  min_lr: 0.000432  loss: 2.0795 (1.9476)  weight_decay: 0.0500 (0.0500)  time: 1.0057  data: 0.0004  max mem: 78493
Epoch: [240]  [130/312]  eta: 0:03:26  lr: 0.000431  min_lr: 0.000431  loss: 1.8865 (1.9401)  weight_decay: 0.0500 (0.0500)  time: 1.0060  data: 0.0004  max mem: 78493
Epoch: [240]  [140/312]  eta: 0:03:13  lr: 0.000431  min_lr: 0.000431  loss: 1.9148 (1.9355)  weight_decay: 0.0500 (0.0500)  time: 1.0067  data: 0.0004  max mem: 78493
Epoch: [240]  [150/312]  eta: 0:03:00  lr: 0.000431  min_lr: 0.000431  loss: 1.9323 (1.9402)  weight_decay: 0.0500 (0.0500)  time: 1.0065  data: 0.0004  max mem: 78493
Epoch: [240]  [160/312]  eta: 0:02:48  lr: 0.000430  min_lr: 0.000430  loss: 2.0842 (1.9420)  weight_decay: 0.0500 (0.0500)  time: 1.0051  data: 0.0004  max mem: 78493
Epoch: [240]  [170/312]  eta: 0:02:36  lr: 0.000430  min_lr: 0.000430  loss: 2.1040 (1.9468)  weight_decay: 0.0500 (0.0500)  time: 1.0048  data: 0.0012  max mem: 78493
Epoch: [240]  [180/312]  eta: 0:02:24  lr: 0.000429  min_lr: 0.000429  loss: 2.0997 (1.9486)  weight_decay: 0.0500 (0.0500)  time: 1.0048  data: 0.0012  max mem: 78493
Epoch: [240]  [190/312]  eta: 0:02:13  lr: 0.000429  min_lr: 0.000429  loss: 2.0997 (1.9469)  weight_decay: 0.0500 (0.0500)  time: 1.0073  data: 0.0004  max mem: 78493
Epoch: [240]  [200/312]  eta: 0:02:01  lr: 0.000428  min_lr: 0.000428  loss: 1.8178 (1.9377)  weight_decay: 0.0500 (0.0500)  time: 1.0093  data: 0.0004  max mem: 78493
Epoch: [240]  [210/312]  eta: 0:01:50  lr: 0.000428  min_lr: 0.000428  loss: 1.8521 (1.9439)  weight_decay: 0.0500 (0.0500)  time: 1.0067  data: 0.0005  max mem: 78493
Epoch: [240]  [220/312]  eta: 0:01:39  lr: 0.000427  min_lr: 0.000427  loss: 1.9610 (1.9405)  weight_decay: 0.0500 (0.0500)  time: 1.0064  data: 0.0004  max mem: 78493
Epoch: [240]  [230/312]  eta: 0:01:28  lr: 0.000427  min_lr: 0.000427  loss: 1.9833 (1.9461)  weight_decay: 0.0500 (0.0500)  time: 1.0066  data: 0.0004  max mem: 78493
Epoch: [240]  [240/312]  eta: 0:01:17  lr: 0.000427  min_lr: 0.000427  loss: 2.0696 (1.9462)  weight_decay: 0.0500 (0.0500)  time: 1.0055  data: 0.0004  max mem: 78493
Epoch: [240]  [250/312]  eta: 0:01:06  lr: 0.000426  min_lr: 0.000426  loss: 2.0696 (1.9464)  weight_decay: 0.0500 (0.0500)  time: 1.0053  data: 0.0004  max mem: 78493
Epoch: [240]  [260/312]  eta: 0:00:55  lr: 0.000426  min_lr: 0.000426  loss: 1.9246 (1.9442)  weight_decay: 0.0500 (0.0500)  time: 1.0062  data: 0.0004  max mem: 78493
Epoch: [240]  [270/312]  eta: 0:00:44  lr: 0.000425  min_lr: 0.000425  loss: 1.9391 (1.9404)  weight_decay: 0.0500 (0.0500)  time: 1.0076  data: 0.0004  max mem: 78493
Epoch: [240]  [280/312]  eta: 0:00:34  lr: 0.000425  min_lr: 0.000425  loss: 1.9966 (1.9383)  weight_decay: 0.0500 (0.0500)  time: 1.0076  data: 0.0010  max mem: 78493
Epoch: [240]  [290/312]  eta: 0:00:23  lr: 0.000424  min_lr: 0.000424  loss: 1.9313 (1.9396)  weight_decay: 0.0500 (0.0500)  time: 1.0046  data: 0.0009  max mem: 78493
Epoch: [240]  [300/312]  eta: 0:00:12  lr: 0.000424  min_lr: 0.000424  loss: 2.0743 (1.9412)  weight_decay: 0.0500 (0.0500)  time: 1.0022  data: 0.0001  max mem: 78493
Epoch: [240]  [310/312]  eta: 0:00:02  lr: 0.000423  min_lr: 0.000423  loss: 2.0743 (1.9431)  weight_decay: 0.0500 (0.0500)  time: 1.0024  data: 0.0001  max mem: 78493
Epoch: [240]  [311/312]  eta: 0:00:01  lr: 0.000423  min_lr: 0.000423  loss: 2.0984 (1.9437)  weight_decay: 0.0500 (0.0500)  time: 1.0024  data: 0.0001  max mem: 78493
Epoch: [240] Total time: 0:05:32 (1.0644 s / it)
Averaged stats: lr: 0.000423  min_lr: 0.000423  loss: 2.0984 (1.9462)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:12  loss: 0.5370 (0.5370)  acc1: 86.8490 (86.8490)  acc5: 97.3958 (97.3958)  time: 8.0663  data: 7.7747  max mem: 78493
Test:  [8/9]  eta: 0:00:01  loss: 0.7800 (0.7207)  acc1: 81.3802 (80.6080)  acc5: 95.9635 (95.5040)  time: 1.0945  data: 0.8639  max mem: 78493
Test: Total time: 0:00:10 (1.1361 s / it)
* Acc@1 81.202 Acc@5 95.596 loss 0.706
Accuracy of the model on the 50000 test images: 81.2%
Max accuracy: 81.44%
Epoch: [241]  [  0/312]  eta: 1:23:59  lr: 0.000423  min_lr: 0.000423  loss: 1.2759 (1.2759)  weight_decay: 0.0500 (0.0500)  time: 16.1530  data: 14.7117  max mem: 78493
Epoch: [241]  [ 10/312]  eta: 0:13:07  lr: 0.000423  min_lr: 0.000423  loss: 2.1730 (2.0796)  weight_decay: 0.0500 (0.0500)  time: 2.6085  data: 1.3437  max mem: 78493
Epoch: [241]  [ 20/312]  eta: 0:09:01  lr: 0.000422  min_lr: 0.000422  loss: 2.0975 (1.9366)  weight_decay: 0.0500 (0.0500)  time: 1.1389  data: 0.0037  max mem: 78493
Epoch: [241]  [ 30/312]  eta: 0:07:25  lr: 0.000422  min_lr: 0.000422  loss: 2.0288 (1.9820)  weight_decay: 0.0500 (0.0500)  time: 1.0158  data: 0.0005  max mem: 78493
Epoch: [241]  [ 40/312]  eta: 0:06:31  lr: 0.000422  min_lr: 0.000422  loss: 2.1443 (2.0222)  weight_decay: 0.0500 (0.0500)  time: 1.0067  data: 0.0004  max mem: 78493
Epoch: [241]  [ 50/312]  eta: 0:05:55  lr: 0.000421  min_lr: 0.000421  loss: 2.1030 (1.9839)  weight_decay: 0.0500 (0.0500)  time: 1.0068  data: 0.0005  max mem: 78493
Epoch: [241]  [ 60/312]  eta: 0:05:27  lr: 0.000421  min_lr: 0.000421  loss: 1.9452 (1.9823)  weight_decay: 0.0500 (0.0500)  time: 1.0077  data: 0.0005  max mem: 78493
Epoch: [241]  [ 70/312]  eta: 0:05:04  lr: 0.000420  min_lr: 0.000420  loss: 1.8848 (1.9590)  weight_decay: 0.0500 (0.0500)  time: 1.0074  data: 0.0005  max mem: 78493
Epoch: [241]  [ 80/312]  eta: 0:04:44  lr: 0.000420  min_lr: 0.000420  loss: 1.8447 (1.9565)  weight_decay: 0.0500 (0.0500)  time: 1.0065  data: 0.0004  max mem: 78493
Epoch: [241]  [ 90/312]  eta: 0:04:26  lr: 0.000419  min_lr: 0.000419  loss: 2.0343 (1.9537)  weight_decay: 0.0500 (0.0500)  time: 1.0059  data: 0.0004  max mem: 78493
Epoch: [241]  [100/312]  eta: 0:04:10  lr: 0.000419  min_lr: 0.000419  loss: 2.0284 (1.9568)  weight_decay: 0.0500 (0.0500)  time: 1.0059  data: 0.0004  max mem: 78493
Epoch: [241]  [110/312]  eta: 0:03:55  lr: 0.000418  min_lr: 0.000418  loss: 2.0284 (1.9628)  weight_decay: 0.0500 (0.0500)  time: 1.0065  data: 0.0004  max mem: 78493
Epoch: [241]  [120/312]  eta: 0:03:41  lr: 0.000418  min_lr: 0.000418  loss: 2.0521 (1.9656)  weight_decay: 0.0500 (0.0500)  time: 1.0061  data: 0.0004  max mem: 78493
Epoch: [241]  [130/312]  eta: 0:03:27  lr: 0.000418  min_lr: 0.000418  loss: 2.0808 (1.9652)  weight_decay: 0.0500 (0.0500)  time: 1.0049  data: 0.0004  max mem: 78493
Epoch: [241]  [140/312]  eta: 0:03:14  lr: 0.000417  min_lr: 0.000417  loss: 1.9373 (1.9648)  weight_decay: 0.0500 (0.0500)  time: 1.0048  data: 0.0005  max mem: 78493
Epoch: [241]  [150/312]  eta: 0:03:02  lr: 0.000417  min_lr: 0.000417  loss: 1.9567 (1.9667)  weight_decay: 0.0500 (0.0500)  time: 1.0064  data: 0.0005  max mem: 78493
Epoch: [241]  [160/312]  eta: 0:02:49  lr: 0.000416  min_lr: 0.000416  loss: 1.9886 (1.9613)  weight_decay: 0.0500 (0.0500)  time: 1.0066  data: 0.0005  max mem: 78493
Epoch: [241]  [170/312]  eta: 0:02:37  lr: 0.000416  min_lr: 0.000416  loss: 1.9479 (1.9546)  weight_decay: 0.0500 (0.0500)  time: 1.0070  data: 0.0004  max mem: 78493
Epoch: [241]  [180/312]  eta: 0:02:25  lr: 0.000415  min_lr: 0.000415  loss: 2.0868 (1.9574)  weight_decay: 0.0500 (0.0500)  time: 1.0096  data: 0.0004  max mem: 78493
Epoch: [241]  [190/312]  eta: 0:02:14  lr: 0.000415  min_lr: 0.000415  loss: 2.0714 (1.9497)  weight_decay: 0.0500 (0.0500)  time: 1.0095  data: 0.0004  max mem: 78493
Epoch: [241]  [200/312]  eta: 0:02:02  lr: 0.000415  min_lr: 0.000415  loss: 1.8773 (1.9484)  weight_decay: 0.0500 (0.0500)  time: 1.0092  data: 0.0013  max mem: 78493
Epoch: [241]  [210/312]  eta: 0:01:51  lr: 0.000414  min_lr: 0.000414  loss: 1.9669 (1.9540)  weight_decay: 0.0500 (0.0500)  time: 1.0079  data: 0.0013  max mem: 78493
Epoch: [241]  [220/312]  eta: 0:01:40  lr: 0.000414  min_lr: 0.000414  loss: 1.9930 (1.9535)  weight_decay: 0.0500 (0.0500)  time: 1.0070  data: 0.0005  max mem: 78493
Epoch: [241]  [230/312]  eta: 0:01:28  lr: 0.000413  min_lr: 0.000413  loss: 2.0781 (1.9583)  weight_decay: 0.0500 (0.0500)  time: 1.0065  data: 0.0004  max mem: 78493
Epoch: [241]  [240/312]  eta: 0:01:17  lr: 0.000413  min_lr: 0.000413  loss: 2.0404 (1.9597)  weight_decay: 0.0500 (0.0500)  time: 1.0059  data: 0.0004  max mem: 78493
Epoch: [241]  [250/312]  eta: 0:01:06  lr: 0.000412  min_lr: 0.000412  loss: 1.9358 (1.9621)  weight_decay: 0.0500 (0.0500)  time: 1.0067  data: 0.0004  max mem: 78493
Epoch: [241]  [260/312]  eta: 0:00:55  lr: 0.000412  min_lr: 0.000412  loss: 2.1298 (1.9663)  weight_decay: 0.0500 (0.0500)  time: 1.0059  data: 0.0004  max mem: 78493
Epoch: [241]  [270/312]  eta: 0:00:45  lr: 0.000411  min_lr: 0.000411  loss: 2.0982 (1.9670)  weight_decay: 0.0500 (0.0500)  time: 1.0049  data: 0.0005  max mem: 78493
Epoch: [241]  [280/312]  eta: 0:00:34  lr: 0.000411  min_lr: 0.000411  loss: 2.0388 (1.9671)  weight_decay: 0.0500 (0.0500)  time: 1.0066  data: 0.0011  max mem: 78493
Epoch: [241]  [290/312]  eta: 0:00:23  lr: 0.000411  min_lr: 0.000411  loss: 1.9256 (1.9620)  weight_decay: 0.0500 (0.0500)  time: 1.0054  data: 0.0009  max mem: 78493
Epoch: [241]  [300/312]  eta: 0:00:12  lr: 0.000410  min_lr: 0.000410  loss: 1.9405 (1.9615)  weight_decay: 0.0500 (0.0500)  time: 1.0021  data: 0.0001  max mem: 78493
Epoch: [241]  [310/312]  eta: 0:00:02  lr: 0.000410  min_lr: 0.000410  loss: 2.0216 (1.9625)  weight_decay: 0.0500 (0.0500)  time: 1.0021  data: 0.0001  max mem: 78493
Epoch: [241]  [311/312]  eta: 0:00:01  lr: 0.000410  min_lr: 0.000410  loss: 2.0216 (1.9620)  weight_decay: 0.0500 (0.0500)  time: 1.0021  data: 0.0001  max mem: 78493
Epoch: [241] Total time: 0:05:33 (1.0691 s / it)
Averaged stats: lr: 0.000410  min_lr: 0.000410  loss: 2.0216 (1.9485)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:16  loss: 0.5165 (0.5165)  acc1: 85.6771 (85.6771)  acc5: 97.9167 (97.9167)  time: 8.5071  data: 8.2302  max mem: 78493
Test:  [8/9]  eta: 0:00:01  loss: 0.8027 (0.7166)  acc1: 80.2083 (80.5920)  acc5: 95.9635 (95.5520)  time: 1.1435  data: 0.9145  max mem: 78493
Test: Total time: 0:00:10 (1.1797 s / it)
* Acc@1 81.276 Acc@5 95.552 loss 0.705
Accuracy of the model on the 50000 test images: 81.3%
Max accuracy: 81.44%
Epoch: [242]  [  0/312]  eta: 1:24:48  lr: 0.000410  min_lr: 0.000410  loss: 1.6610 (1.6610)  weight_decay: 0.0500 (0.0500)  time: 16.3078  data: 14.6235  max mem: 78493
Epoch: [242]  [ 10/312]  eta: 0:13:02  lr: 0.000409  min_lr: 0.000409  loss: 2.1034 (2.0631)  weight_decay: 0.0500 (0.0500)  time: 2.5918  data: 1.3340  max mem: 78493
Epoch: [242]  [ 20/312]  eta: 0:09:00  lr: 0.000409  min_lr: 0.000409  loss: 2.1034 (2.0207)  weight_decay: 0.0500 (0.0500)  time: 1.1292  data: 0.0028  max mem: 78493
Epoch: [242]  [ 30/312]  eta: 0:07:25  lr: 0.000408  min_lr: 0.000408  loss: 2.0630 (1.9881)  weight_decay: 0.0500 (0.0500)  time: 1.0232  data: 0.0005  max mem: 78493
Epoch: [242]  [ 40/312]  eta: 0:06:31  lr: 0.000408  min_lr: 0.000408  loss: 2.0543 (1.9666)  weight_decay: 0.0500 (0.0500)  time: 1.0066  data: 0.0004  max mem: 78493
Epoch: [242]  [ 50/312]  eta: 0:05:55  lr: 0.000407  min_lr: 0.000407  loss: 2.0041 (1.9465)  weight_decay: 0.0500 (0.0500)  time: 1.0068  data: 0.0004  max mem: 78493
Epoch: [242]  [ 60/312]  eta: 0:05:27  lr: 0.000407  min_lr: 0.000407  loss: 1.9955 (1.9530)  weight_decay: 0.0500 (0.0500)  time: 1.0098  data: 0.0005  max mem: 78493
Epoch: [242]  [ 70/312]  eta: 0:05:04  lr: 0.000407  min_lr: 0.000407  loss: 1.9494 (1.9523)  weight_decay: 0.0500 (0.0500)  time: 1.0081  data: 0.0005  max mem: 78493
Epoch: [242]  [ 80/312]  eta: 0:04:44  lr: 0.000406  min_lr: 0.000406  loss: 1.9804 (1.9618)  weight_decay: 0.0500 (0.0500)  time: 1.0074  data: 0.0005  max mem: 78493
Epoch: [242]  [ 90/312]  eta: 0:04:26  lr: 0.000406  min_lr: 0.000406  loss: 2.0958 (1.9803)  weight_decay: 0.0500 (0.0500)  time: 1.0081  data: 0.0004  max mem: 78493
Epoch: [242]  [100/312]  eta: 0:04:10  lr: 0.000405  min_lr: 0.000405  loss: 2.0482 (1.9752)  weight_decay: 0.0500 (0.0500)  time: 1.0079  data: 0.0004  max mem: 78493
Epoch: [242]  [110/312]  eta: 0:03:55  lr: 0.000405  min_lr: 0.000405  loss: 2.0482 (1.9794)  weight_decay: 0.0500 (0.0500)  time: 1.0088  data: 0.0004  max mem: 78493
Epoch: [242]  [120/312]  eta: 0:03:41  lr: 0.000404  min_lr: 0.000404  loss: 1.9681 (1.9767)  weight_decay: 0.0500 (0.0500)  time: 1.0073  data: 0.0004  max mem: 78493
Epoch: [242]  [130/312]  eta: 0:03:28  lr: 0.000404  min_lr: 0.000404  loss: 1.9949 (1.9829)  weight_decay: 0.0500 (0.0500)  time: 1.0060  data: 0.0004  max mem: 78493
Epoch: [242]  [140/312]  eta: 0:03:14  lr: 0.000404  min_lr: 0.000404  loss: 2.0051 (1.9852)  weight_decay: 0.0500 (0.0500)  time: 1.0058  data: 0.0005  max mem: 78493
Epoch: [242]  [150/312]  eta: 0:03:02  lr: 0.000403  min_lr: 0.000403  loss: 1.9762 (1.9809)  weight_decay: 0.0500 (0.0500)  time: 1.0058  data: 0.0004  max mem: 78493
Epoch: [242]  [160/312]  eta: 0:02:49  lr: 0.000403  min_lr: 0.000403  loss: 2.0607 (1.9865)  weight_decay: 0.0500 (0.0500)  time: 1.0046  data: 0.0005  max mem: 78493
Epoch: [242]  [170/312]  eta: 0:02:37  lr: 0.000402  min_lr: 0.000402  loss: 2.1127 (1.9903)  weight_decay: 0.0500 (0.0500)  time: 1.0050  data: 0.0005  max mem: 78493
Epoch: [242]  [180/312]  eta: 0:02:25  lr: 0.000402  min_lr: 0.000402  loss: 2.1127 (1.9878)  weight_decay: 0.0500 (0.0500)  time: 1.0060  data: 0.0004  max mem: 78493
Epoch: [242]  [190/312]  eta: 0:02:14  lr: 0.000401  min_lr: 0.000401  loss: 1.9954 (1.9821)  weight_decay: 0.0500 (0.0500)  time: 1.0070  data: 0.0005  max mem: 78493
Epoch: [242]  [200/312]  eta: 0:02:02  lr: 0.000401  min_lr: 0.000401  loss: 1.9763 (1.9853)  weight_decay: 0.0500 (0.0500)  time: 1.0091  data: 0.0005  max mem: 78493
Epoch: [242]  [210/312]  eta: 0:01:51  lr: 0.000401  min_lr: 0.000401  loss: 1.9602 (1.9812)  weight_decay: 0.0500 (0.0500)  time: 1.0084  data: 0.0005  max mem: 78493
Epoch: [242]  [220/312]  eta: 0:01:40  lr: 0.000400  min_lr: 0.000400  loss: 1.9602 (1.9808)  weight_decay: 0.0500 (0.0500)  time: 1.0054  data: 0.0005  max mem: 78493
Epoch: [242]  [230/312]  eta: 0:01:28  lr: 0.000400  min_lr: 0.000400  loss: 2.0298 (1.9787)  weight_decay: 0.0500 (0.0500)  time: 1.0045  data: 0.0004  max mem: 78493
Epoch: [242]  [240/312]  eta: 0:01:17  lr: 0.000399  min_lr: 0.000399  loss: 2.0882 (1.9835)  weight_decay: 0.0500 (0.0500)  time: 1.0055  data: 0.0004  max mem: 78493
Epoch: [242]  [250/312]  eta: 0:01:06  lr: 0.000399  min_lr: 0.000399  loss: 2.0213 (1.9805)  weight_decay: 0.0500 (0.0500)  time: 1.0062  data: 0.0015  max mem: 78493
Epoch: [242]  [260/312]  eta: 0:00:55  lr: 0.000398  min_lr: 0.000398  loss: 1.9984 (1.9840)  weight_decay: 0.0500 (0.0500)  time: 1.0062  data: 0.0015  max mem: 78493
Epoch: [242]  [270/312]  eta: 0:00:45  lr: 0.000398  min_lr: 0.000398  loss: 1.9817 (1.9799)  weight_decay: 0.0500 (0.0500)  time: 1.0050  data: 0.0004  max mem: 78493
Epoch: [242]  [280/312]  eta: 0:00:34  lr: 0.000398  min_lr: 0.000398  loss: 2.0003 (1.9786)  weight_decay: 0.0500 (0.0500)  time: 1.0057  data: 0.0010  max mem: 78493
Epoch: [242]  [290/312]  eta: 0:00:23  lr: 0.000397  min_lr: 0.000397  loss: 2.0003 (1.9768)  weight_decay: 0.0500 (0.0500)  time: 1.0045  data: 0.0009  max mem: 78493
Epoch: [242]  [300/312]  eta: 0:00:12  lr: 0.000397  min_lr: 0.000397  loss: 2.0570 (1.9773)  weight_decay: 0.0500 (0.0500)  time: 1.0016  data: 0.0001  max mem: 78493
Epoch: [242]  [310/312]  eta: 0:00:02  lr: 0.000396  min_lr: 0.000396  loss: 2.0570 (1.9706)  weight_decay: 0.0500 (0.0500)  time: 1.0014  data: 0.0001  max mem: 78493
Epoch: [242]  [311/312]  eta: 0:00:01  lr: 0.000396  min_lr: 0.000396  loss: 1.9326 (1.9705)  weight_decay: 0.0500 (0.0500)  time: 1.0015  data: 0.0001  max mem: 78493
Epoch: [242] Total time: 0:05:33 (1.0688 s / it)
Averaged stats: lr: 0.000396  min_lr: 0.000396  loss: 1.9326 (1.9331)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:14  loss: 0.5079 (0.5079)  acc1: 86.5885 (86.5885)  acc5: 97.5260 (97.5260)  time: 8.2265  data: 7.9589  max mem: 78493
Test:  [8/9]  eta: 0:00:01  loss: 0.7554 (0.7078)  acc1: 80.8594 (81.0080)  acc5: 96.0938 (95.4880)  time: 1.1135  data: 0.8844  max mem: 78493
Test: Total time: 0:00:10 (1.1567 s / it)
* Acc@1 81.388 Acc@5 95.614 loss 0.700
Accuracy of the model on the 50000 test images: 81.4%
Max accuracy: 81.44%
Epoch: [243]  [  0/312]  eta: 1:21:39  lr: 0.000396  min_lr: 0.000396  loss: 1.1451 (1.1451)  weight_decay: 0.0500 (0.0500)  time: 15.7042  data: 11.9777  max mem: 78493
Epoch: [243]  [ 10/312]  eta: 0:13:22  lr: 0.000396  min_lr: 0.000396  loss: 2.0396 (1.8368)  weight_decay: 0.0500 (0.0500)  time: 2.6577  data: 1.3723  max mem: 78493
Epoch: [243]  [ 20/312]  eta: 0:09:07  lr: 0.000395  min_lr: 0.000395  loss: 2.0396 (1.9063)  weight_decay: 0.0500 (0.0500)  time: 1.1837  data: 0.1561  max mem: 78493
Epoch: [243]  [ 30/312]  eta: 0:07:30  lr: 0.000395  min_lr: 0.000395  loss: 1.9880 (1.8677)  weight_decay: 0.0500 (0.0500)  time: 1.0120  data: 0.0005  max mem: 78493
Epoch: [243]  [ 40/312]  eta: 0:06:35  lr: 0.000394  min_lr: 0.000394  loss: 2.0070 (1.9044)  weight_decay: 0.0500 (0.0500)  time: 1.0098  data: 0.0004  max mem: 78493
Epoch: [243]  [ 50/312]  eta: 0:05:57  lr: 0.000394  min_lr: 0.000394  loss: 1.9981 (1.9054)  weight_decay: 0.0500 (0.0500)  time: 1.0076  data: 0.0004  max mem: 78493
Epoch: [243]  [ 60/312]  eta: 0:05:29  lr: 0.000394  min_lr: 0.000394  loss: 1.9946 (1.9108)  weight_decay: 0.0500 (0.0500)  time: 1.0064  data: 0.0004  max mem: 78493
Epoch: [243]  [ 70/312]  eta: 0:05:05  lr: 0.000393  min_lr: 0.000393  loss: 1.9299 (1.8916)  weight_decay: 0.0500 (0.0500)  time: 1.0072  data: 0.0004  max mem: 78493
Epoch: [243]  [ 80/312]  eta: 0:04:45  lr: 0.000393  min_lr: 0.000393  loss: 1.8677 (1.8961)  weight_decay: 0.0500 (0.0500)  time: 1.0073  data: 0.0005  max mem: 78493
Epoch: [243]  [ 90/312]  eta: 0:04:28  lr: 0.000392  min_lr: 0.000392  loss: 1.9320 (1.9046)  weight_decay: 0.0500 (0.0500)  time: 1.0086  data: 0.0005  max mem: 78493
Epoch: [243]  [100/312]  eta: 0:04:11  lr: 0.000392  min_lr: 0.000392  loss: 1.9817 (1.9067)  weight_decay: 0.0500 (0.0500)  time: 1.0096  data: 0.0004  max mem: 78493
Epoch: [243]  [110/312]  eta: 0:03:56  lr: 0.000391  min_lr: 0.000391  loss: 1.8694 (1.9014)  weight_decay: 0.0500 (0.0500)  time: 1.0102  data: 0.0004  max mem: 78493
Epoch: [243]  [120/312]  eta: 0:03:42  lr: 0.000391  min_lr: 0.000391  loss: 1.8694 (1.8992)  weight_decay: 0.0500 (0.0500)  time: 1.0080  data: 0.0004  max mem: 78493
Epoch: [243]  [130/312]  eta: 0:03:28  lr: 0.000391  min_lr: 0.000391  loss: 1.9752 (1.9021)  weight_decay: 0.0500 (0.0500)  time: 1.0069  data: 0.0013  max mem: 78493
Epoch: [243]  [140/312]  eta: 0:03:15  lr: 0.000390  min_lr: 0.000390  loss: 2.0006 (1.9065)  weight_decay: 0.0500 (0.0500)  time: 1.0073  data: 0.0013  max mem: 78493
Epoch: [243]  [150/312]  eta: 0:03:02  lr: 0.000390  min_lr: 0.000390  loss: 1.8232 (1.8976)  weight_decay: 0.0500 (0.0500)  time: 1.0061  data: 0.0005  max mem: 78493
Epoch: [243]  [160/312]  eta: 0:02:50  lr: 0.000389  min_lr: 0.000389  loss: 1.9154 (1.9013)  weight_decay: 0.0500 (0.0500)  time: 1.0073  data: 0.0004  max mem: 78493
Epoch: [243]  [170/312]  eta: 0:02:38  lr: 0.000389  min_lr: 0.000389  loss: 1.9550 (1.8999)  weight_decay: 0.0500 (0.0500)  time: 1.0104  data: 0.0004  max mem: 78493
Epoch: [243]  [180/312]  eta: 0:02:26  lr: 0.000388  min_lr: 0.000388  loss: 1.9058 (1.8947)  weight_decay: 0.0500 (0.0500)  time: 1.0095  data: 0.0004  max mem: 78493
Epoch: [243]  [190/312]  eta: 0:02:14  lr: 0.000388  min_lr: 0.000388  loss: 1.7227 (1.8909)  weight_decay: 0.0500 (0.0500)  time: 1.0076  data: 0.0004  max mem: 78493
Epoch: [243]  [200/312]  eta: 0:02:03  lr: 0.000388  min_lr: 0.000388  loss: 1.7418 (1.8879)  weight_decay: 0.0500 (0.0500)  time: 1.0074  data: 0.0004  max mem: 78493
Epoch: [243]  [210/312]  eta: 0:01:51  lr: 0.000387  min_lr: 0.000387  loss: 1.9384 (1.8916)  weight_decay: 0.0500 (0.0500)  time: 1.0084  data: 0.0004  max mem: 78493
Epoch: [243]  [220/312]  eta: 0:01:40  lr: 0.000387  min_lr: 0.000387  loss: 2.0068 (1.8962)  weight_decay: 0.0500 (0.0500)  time: 1.0081  data: 0.0004  max mem: 78493
Epoch: [243]  [230/312]  eta: 0:01:29  lr: 0.000386  min_lr: 0.000386  loss: 1.9230 (1.8956)  weight_decay: 0.0500 (0.0500)  time: 1.0080  data: 0.0004  max mem: 78493
Epoch: [243]  [240/312]  eta: 0:01:18  lr: 0.000386  min_lr: 0.000386  loss: 1.9131 (1.8937)  weight_decay: 0.0500 (0.0500)  time: 1.0076  data: 0.0004  max mem: 78493
Epoch: [243]  [250/312]  eta: 0:01:06  lr: 0.000385  min_lr: 0.000385  loss: 1.8911 (1.8921)  weight_decay: 0.0500 (0.0500)  time: 1.0056  data: 0.0004  max mem: 78493
Epoch: [243]  [260/312]  eta: 0:00:56  lr: 0.000385  min_lr: 0.000385  loss: 1.9990 (1.8993)  weight_decay: 0.0500 (0.0500)  time: 1.0065  data: 0.0004  max mem: 78493
Epoch: [243]  [270/312]  eta: 0:00:45  lr: 0.000385  min_lr: 0.000385  loss: 2.1325 (1.9042)  weight_decay: 0.0500 (0.0500)  time: 1.0054  data: 0.0004  max mem: 78493
Epoch: [243]  [280/312]  eta: 0:00:34  lr: 0.000384  min_lr: 0.000384  loss: 2.1030 (1.9058)  weight_decay: 0.0500 (0.0500)  time: 1.0058  data: 0.0010  max mem: 78493
Epoch: [243]  [290/312]  eta: 0:00:23  lr: 0.000384  min_lr: 0.000384  loss: 1.9836 (1.9081)  weight_decay: 0.0500 (0.0500)  time: 1.0045  data: 0.0009  max mem: 78493
Epoch: [243]  [300/312]  eta: 0:00:12  lr: 0.000383  min_lr: 0.000383  loss: 1.9852 (1.9130)  weight_decay: 0.0500 (0.0500)  time: 1.0014  data: 0.0001  max mem: 78493
Epoch: [243]  [310/312]  eta: 0:00:02  lr: 0.000383  min_lr: 0.000383  loss: 2.0628 (1.9184)  weight_decay: 0.0500 (0.0500)  time: 1.0018  data: 0.0001  max mem: 78493
Epoch: [243]  [311/312]  eta: 0:00:01  lr: 0.000383  min_lr: 0.000383  loss: 2.0243 (1.9187)  weight_decay: 0.0500 (0.0500)  time: 1.0019  data: 0.0001  max mem: 78493
Epoch: [243] Total time: 0:05:34 (1.0712 s / it)
Averaged stats: lr: 0.000383  min_lr: 0.000383  loss: 2.0243 (1.9281)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:05  loss: 0.5306 (0.5306)  acc1: 85.5469 (85.5469)  acc5: 97.2656 (97.2656)  time: 7.3307  data: 7.0621  max mem: 78493
Test:  [8/9]  eta: 0:00:01  loss: 0.7954 (0.7241)  acc1: 79.6875 (80.4000)  acc5: 96.2240 (95.4400)  time: 1.0457  data: 0.8155  max mem: 78493
Test: Total time: 0:00:09 (1.0554 s / it)
* Acc@1 81.246 Acc@5 95.604 loss 0.702
Accuracy of the model on the 50000 test images: 81.2%
Max accuracy: 81.44%
Epoch: [244]  [  0/312]  eta: 1:25:47  lr: 0.000383  min_lr: 0.000383  loss: 2.4626 (2.4626)  weight_decay: 0.0500 (0.0500)  time: 16.4981  data: 15.5033  max mem: 78493
Epoch: [244]  [ 10/312]  eta: 0:13:26  lr: 0.000382  min_lr: 0.000382  loss: 1.9914 (2.0029)  weight_decay: 0.0500 (0.0500)  time: 2.6700  data: 1.4136  max mem: 78493
Epoch: [244]  [ 20/312]  eta: 0:09:08  lr: 0.000382  min_lr: 0.000382  loss: 1.9544 (1.9845)  weight_decay: 0.0500 (0.0500)  time: 1.1479  data: 0.0026  max mem: 78493
Epoch: [244]  [ 30/312]  eta: 0:07:30  lr: 0.000382  min_lr: 0.000382  loss: 1.8691 (1.9103)  weight_decay: 0.0500 (0.0500)  time: 1.0076  data: 0.0004  max mem: 78493
Epoch: [244]  [ 40/312]  eta: 0:06:35  lr: 0.000381  min_lr: 0.000381  loss: 1.8245 (1.9068)  weight_decay: 0.0500 (0.0500)  time: 1.0071  data: 0.0004  max mem: 78493
Epoch: [244]  [ 50/312]  eta: 0:05:57  lr: 0.000381  min_lr: 0.000381  loss: 1.9392 (1.9105)  weight_decay: 0.0500 (0.0500)  time: 1.0067  data: 0.0004  max mem: 78493
Epoch: [244]  [ 60/312]  eta: 0:05:29  lr: 0.000380  min_lr: 0.000380  loss: 2.0955 (1.9203)  weight_decay: 0.0500 (0.0500)  time: 1.0071  data: 0.0004  max mem: 78493
Epoch: [244]  [ 70/312]  eta: 0:05:06  lr: 0.000380  min_lr: 0.000380  loss: 2.0776 (1.9261)  weight_decay: 0.0500 (0.0500)  time: 1.0064  data: 0.0005  max mem: 78493
Epoch: [244]  [ 80/312]  eta: 0:04:45  lr: 0.000379  min_lr: 0.000379  loss: 1.9884 (1.9035)  weight_decay: 0.0500 (0.0500)  time: 1.0045  data: 0.0005  max mem: 78493
Epoch: [244]  [ 90/312]  eta: 0:04:28  lr: 0.000379  min_lr: 0.000379  loss: 1.8784 (1.9118)  weight_decay: 0.0500 (0.0500)  time: 1.0061  data: 0.0004  max mem: 78493
Epoch: [244]  [100/312]  eta: 0:04:11  lr: 0.000379  min_lr: 0.000379  loss: 2.1633 (1.9259)  weight_decay: 0.0500 (0.0500)  time: 1.0079  data: 0.0004  max mem: 78493
Epoch: [244]  [110/312]  eta: 0:03:56  lr: 0.000378  min_lr: 0.000378  loss: 1.9679 (1.9285)  weight_decay: 0.0500 (0.0500)  time: 1.0076  data: 0.0004  max mem: 78493
Epoch: [244]  [120/312]  eta: 0:03:42  lr: 0.000378  min_lr: 0.000378  loss: 1.8690 (1.9224)  weight_decay: 0.0500 (0.0500)  time: 1.0075  data: 0.0004  max mem: 78493
Epoch: [244]  [130/312]  eta: 0:03:28  lr: 0.000377  min_lr: 0.000377  loss: 1.8363 (1.9252)  weight_decay: 0.0500 (0.0500)  time: 1.0073  data: 0.0004  max mem: 78493
Epoch: [244]  [140/312]  eta: 0:03:15  lr: 0.000377  min_lr: 0.000377  loss: 1.9883 (1.9289)  weight_decay: 0.0500 (0.0500)  time: 1.0070  data: 0.0005  max mem: 78493
Epoch: [244]  [150/312]  eta: 0:03:02  lr: 0.000377  min_lr: 0.000377  loss: 1.9883 (1.9335)  weight_decay: 0.0500 (0.0500)  time: 1.0064  data: 0.0005  max mem: 78493
Epoch: [244]  [160/312]  eta: 0:02:50  lr: 0.000376  min_lr: 0.000376  loss: 1.8772 (1.9310)  weight_decay: 0.0500 (0.0500)  time: 1.0063  data: 0.0004  max mem: 78493
Epoch: [244]  [170/312]  eta: 0:02:38  lr: 0.000376  min_lr: 0.000376  loss: 1.8949 (1.9266)  weight_decay: 0.0500 (0.0500)  time: 1.0070  data: 0.0004  max mem: 78493
Epoch: [244]  [180/312]  eta: 0:02:26  lr: 0.000375  min_lr: 0.000375  loss: 1.9245 (1.9283)  weight_decay: 0.0500 (0.0500)  time: 1.0072  data: 0.0004  max mem: 78493
Epoch: [244]  [190/312]  eta: 0:02:14  lr: 0.000375  min_lr: 0.000375  loss: 2.0318 (1.9256)  weight_decay: 0.0500 (0.0500)  time: 1.0064  data: 0.0004  max mem: 78493
Epoch: [244]  [200/312]  eta: 0:02:02  lr: 0.000374  min_lr: 0.000374  loss: 1.8920 (1.9253)  weight_decay: 0.0500 (0.0500)  time: 1.0078  data: 0.0004  max mem: 78493
Epoch: [244]  [210/312]  eta: 0:01:51  lr: 0.000374  min_lr: 0.000374  loss: 1.8689 (1.9233)  weight_decay: 0.0500 (0.0500)  time: 1.0074  data: 0.0004  max mem: 78493
Epoch: [244]  [220/312]  eta: 0:01:40  lr: 0.000374  min_lr: 0.000374  loss: 1.9439 (1.9246)  weight_decay: 0.0500 (0.0500)  time: 1.0057  data: 0.0004  max mem: 78493
Epoch: [244]  [230/312]  eta: 0:01:29  lr: 0.000373  min_lr: 0.000373  loss: 1.9084 (1.9220)  weight_decay: 0.0500 (0.0500)  time: 1.0072  data: 0.0005  max mem: 78493
Epoch: [244]  [240/312]  eta: 0:01:17  lr: 0.000373  min_lr: 0.000373  loss: 1.7614 (1.9158)  weight_decay: 0.0500 (0.0500)  time: 1.0072  data: 0.0004  max mem: 78493
Epoch: [244]  [250/312]  eta: 0:01:06  lr: 0.000372  min_lr: 0.000372  loss: 1.8210 (1.9164)  weight_decay: 0.0500 (0.0500)  time: 1.0071  data: 0.0004  max mem: 78493
Epoch: [244]  [260/312]  eta: 0:00:56  lr: 0.000372  min_lr: 0.000372  loss: 1.8597 (1.9114)  weight_decay: 0.0500 (0.0500)  time: 1.0070  data: 0.0004  max mem: 78493
Epoch: [244]  [270/312]  eta: 0:00:45  lr: 0.000372  min_lr: 0.000372  loss: 1.8597 (1.9144)  weight_decay: 0.0500 (0.0500)  time: 1.0056  data: 0.0005  max mem: 78493
Epoch: [244]  [280/312]  eta: 0:00:34  lr: 0.000371  min_lr: 0.000371  loss: 2.1777 (1.9219)  weight_decay: 0.0500 (0.0500)  time: 1.0049  data: 0.0011  max mem: 78493
Epoch: [244]  [290/312]  eta: 0:00:23  lr: 0.000371  min_lr: 0.000371  loss: 2.1777 (1.9216)  weight_decay: 0.0500 (0.0500)  time: 1.0034  data: 0.0009  max mem: 78493
Epoch: [244]  [300/312]  eta: 0:00:12  lr: 0.000370  min_lr: 0.000370  loss: 2.0097 (1.9204)  weight_decay: 0.0500 (0.0500)  time: 1.0016  data: 0.0001  max mem: 78493
Epoch: [244]  [310/312]  eta: 0:00:02  lr: 0.000370  min_lr: 0.000370  loss: 1.9837 (1.9197)  weight_decay: 0.0500 (0.0500)  time: 1.0016  data: 0.0001  max mem: 78493
Epoch: [244]  [311/312]  eta: 0:00:01  lr: 0.000370  min_lr: 0.000370  loss: 2.0097 (1.9204)  weight_decay: 0.0500 (0.0500)  time: 1.0017  data: 0.0001  max mem: 78493
Epoch: [244] Total time: 0:05:34 (1.0706 s / it)
Averaged stats: lr: 0.000370  min_lr: 0.000370  loss: 2.0097 (1.9260)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:16  loss: 0.4876 (0.4876)  acc1: 87.5000 (87.5000)  acc5: 97.7865 (97.7865)  time: 8.4849  data: 8.2056  max mem: 78493
Test:  [8/9]  eta: 0:00:01  loss: 0.7960 (0.7141)  acc1: 79.5573 (81.0240)  acc5: 96.3542 (95.7120)  time: 1.1409  data: 0.9118  max mem: 78493
Test: Total time: 0:00:10 (1.1550 s / it)
* Acc@1 81.466 Acc@5 95.586 loss 0.702
Accuracy of the model on the 50000 test images: 81.5%
Max accuracy: 81.47%
Epoch: [245]  [  0/312]  eta: 1:22:48  lr: 0.000370  min_lr: 0.000370  loss: 1.6968 (1.6968)  weight_decay: 0.0500 (0.0500)  time: 15.9231  data: 14.2382  max mem: 78493
Epoch: [245]  [ 10/312]  eta: 0:13:08  lr: 0.000369  min_lr: 0.000369  loss: 2.0471 (2.0217)  weight_decay: 0.0500 (0.0500)  time: 2.6124  data: 1.2952  max mem: 78493
Epoch: [245]  [ 20/312]  eta: 0:09:00  lr: 0.000369  min_lr: 0.000369  loss: 1.9971 (1.9315)  weight_decay: 0.0500 (0.0500)  time: 1.1478  data: 0.0007  max mem: 78493
Epoch: [245]  [ 30/312]  eta: 0:07:25  lr: 0.000369  min_lr: 0.000369  loss: 1.7050 (1.8868)  weight_decay: 0.0500 (0.0500)  time: 1.0096  data: 0.0005  max mem: 78493
Epoch: [245]  [ 40/312]  eta: 0:06:31  lr: 0.000368  min_lr: 0.000368  loss: 1.9681 (1.8933)  weight_decay: 0.0500 (0.0500)  time: 1.0048  data: 0.0004  max mem: 78493
Epoch: [245]  [ 50/312]  eta: 0:05:54  lr: 0.000368  min_lr: 0.000368  loss: 2.0400 (1.9076)  weight_decay: 0.0500 (0.0500)  time: 1.0057  data: 0.0004  max mem: 78493
Epoch: [245]  [ 60/312]  eta: 0:05:26  lr: 0.000367  min_lr: 0.000367  loss: 2.0192 (1.9199)  weight_decay: 0.0500 (0.0500)  time: 1.0057  data: 0.0005  max mem: 78493
Epoch: [245]  [ 70/312]  eta: 0:05:03  lr: 0.000367  min_lr: 0.000367  loss: 1.9442 (1.9213)  weight_decay: 0.0500 (0.0500)  time: 1.0045  data: 0.0005  max mem: 78493
Epoch: [245]  [ 80/312]  eta: 0:04:44  lr: 0.000366  min_lr: 0.000366  loss: 1.8655 (1.9155)  weight_decay: 0.0500 (0.0500)  time: 1.0060  data: 0.0004  max mem: 78493
Epoch: [245]  [ 90/312]  eta: 0:04:26  lr: 0.000366  min_lr: 0.000366  loss: 1.8075 (1.8962)  weight_decay: 0.0500 (0.0500)  time: 1.0082  data: 0.0004  max mem: 78493
Epoch: [245]  [100/312]  eta: 0:04:10  lr: 0.000366  min_lr: 0.000366  loss: 2.0620 (1.9278)  weight_decay: 0.0500 (0.0500)  time: 1.0098  data: 0.0004  max mem: 78493
Epoch: [245]  [110/312]  eta: 0:03:55  lr: 0.000365  min_lr: 0.000365  loss: 2.1569 (1.9293)  weight_decay: 0.0500 (0.0500)  time: 1.0107  data: 0.0005  max mem: 78493
Epoch: [245]  [120/312]  eta: 0:03:41  lr: 0.000365  min_lr: 0.000365  loss: 2.0168 (1.9270)  weight_decay: 0.0500 (0.0500)  time: 1.0102  data: 0.0004  max mem: 78493
Epoch: [245]  [130/312]  eta: 0:03:28  lr: 0.000364  min_lr: 0.000364  loss: 1.8867 (1.9187)  weight_decay: 0.0500 (0.0500)  time: 1.0102  data: 0.0004  max mem: 78493
Epoch: [245]  [140/312]  eta: 0:03:14  lr: 0.000364  min_lr: 0.000364  loss: 1.9419 (1.9245)  weight_decay: 0.0500 (0.0500)  time: 1.0093  data: 0.0005  max mem: 78493
Epoch: [245]  [150/312]  eta: 0:03:02  lr: 0.000364  min_lr: 0.000364  loss: 2.0397 (1.9331)  weight_decay: 0.0500 (0.0500)  time: 1.0082  data: 0.0004  max mem: 78493
Epoch: [245]  [160/312]  eta: 0:02:49  lr: 0.000363  min_lr: 0.000363  loss: 2.0792 (1.9332)  weight_decay: 0.0500 (0.0500)  time: 1.0067  data: 0.0004  max mem: 78493
Epoch: [245]  [170/312]  eta: 0:02:37  lr: 0.000363  min_lr: 0.000363  loss: 1.9784 (1.9289)  weight_decay: 0.0500 (0.0500)  time: 1.0058  data: 0.0004  max mem: 78493
Epoch: [245]  [180/312]  eta: 0:02:25  lr: 0.000362  min_lr: 0.000362  loss: 1.9394 (1.9346)  weight_decay: 0.0500 (0.0500)  time: 1.0069  data: 0.0004  max mem: 78493
Epoch: [245]  [190/312]  eta: 0:02:14  lr: 0.000362  min_lr: 0.000362  loss: 2.0127 (1.9369)  weight_decay: 0.0500 (0.0500)  time: 1.0062  data: 0.0004  max mem: 78493
Epoch: [245]  [200/312]  eta: 0:02:02  lr: 0.000362  min_lr: 0.000362  loss: 2.0399 (1.9371)  weight_decay: 0.0500 (0.0500)  time: 1.0060  data: 0.0004  max mem: 78493
Epoch: [245]  [210/312]  eta: 0:01:51  lr: 0.000361  min_lr: 0.000361  loss: 1.8293 (1.9267)  weight_decay: 0.0500 (0.0500)  time: 1.0063  data: 0.0005  max mem: 78493
Epoch: [245]  [220/312]  eta: 0:01:40  lr: 0.000361  min_lr: 0.000361  loss: 1.9447 (1.9281)  weight_decay: 0.0500 (0.0500)  time: 1.0062  data: 0.0005  max mem: 78493
Epoch: [245]  [230/312]  eta: 0:01:28  lr: 0.000360  min_lr: 0.000360  loss: 1.9894 (1.9275)  weight_decay: 0.0500 (0.0500)  time: 1.0066  data: 0.0004  max mem: 78493
Epoch: [245]  [240/312]  eta: 0:01:17  lr: 0.000360  min_lr: 0.000360  loss: 2.0393 (1.9328)  weight_decay: 0.0500 (0.0500)  time: 1.0052  data: 0.0004  max mem: 78493
Epoch: [245]  [250/312]  eta: 0:01:06  lr: 0.000359  min_lr: 0.000359  loss: 2.0418 (1.9365)  weight_decay: 0.0500 (0.0500)  time: 1.0046  data: 0.0004  max mem: 78493
Epoch: [245]  [260/312]  eta: 0:00:55  lr: 0.000359  min_lr: 0.000359  loss: 2.0418 (1.9343)  weight_decay: 0.0500 (0.0500)  time: 1.0055  data: 0.0004  max mem: 78493
Epoch: [245]  [270/312]  eta: 0:00:45  lr: 0.000359  min_lr: 0.000359  loss: 2.0240 (1.9323)  weight_decay: 0.0500 (0.0500)  time: 1.0052  data: 0.0004  max mem: 78493
Epoch: [245]  [280/312]  eta: 0:00:34  lr: 0.000358  min_lr: 0.000358  loss: 1.9223 (1.9323)  weight_decay: 0.0500 (0.0500)  time: 1.0047  data: 0.0010  max mem: 78493
Epoch: [245]  [290/312]  eta: 0:00:23  lr: 0.000358  min_lr: 0.000358  loss: 2.0167 (1.9340)  weight_decay: 0.0500 (0.0500)  time: 1.0032  data: 0.0009  max mem: 78493
Epoch: [245]  [300/312]  eta: 0:00:12  lr: 0.000357  min_lr: 0.000357  loss: 2.0308 (1.9314)  weight_decay: 0.0500 (0.0500)  time: 1.0019  data: 0.0001  max mem: 78493
Epoch: [245]  [310/312]  eta: 0:00:02  lr: 0.000357  min_lr: 0.000357  loss: 1.9807 (1.9313)  weight_decay: 0.0500 (0.0500)  time: 1.0019  data: 0.0001  max mem: 78493
Epoch: [245]  [311/312]  eta: 0:00:01  lr: 0.000357  min_lr: 0.000357  loss: 1.9807 (1.9311)  weight_decay: 0.0500 (0.0500)  time: 1.0019  data: 0.0001  max mem: 78493
Epoch: [245] Total time: 0:05:33 (1.0685 s / it)
Averaged stats: lr: 0.000357  min_lr: 0.000357  loss: 1.9807 (1.9336)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:17  loss: 0.5117 (0.5117)  acc1: 87.1094 (87.1094)  acc5: 97.3958 (97.3958)  time: 8.6211  data: 8.3521  max mem: 78493
Test:  [8/9]  eta: 0:00:01  loss: 0.8014 (0.7187)  acc1: 80.2083 (80.6080)  acc5: 96.3542 (95.4400)  time: 1.1565  data: 0.9281  max mem: 78493
Test: Total time: 0:00:10 (1.1827 s / it)
* Acc@1 81.486 Acc@5 95.514 loss 0.703
Accuracy of the model on the 50000 test images: 81.5%
Max accuracy: 81.49%
Epoch: [246]  [  0/312]  eta: 1:20:27  lr: 0.000357  min_lr: 0.000357  loss: 2.1384 (2.1384)  weight_decay: 0.0500 (0.0500)  time: 15.4738  data: 14.4352  max mem: 78493
Epoch: [246]  [ 10/312]  eta: 0:13:06  lr: 0.000356  min_lr: 0.000356  loss: 1.8389 (1.8640)  weight_decay: 0.0500 (0.0500)  time: 2.6031  data: 1.3129  max mem: 78493
Epoch: [246]  [ 20/312]  eta: 0:08:58  lr: 0.000356  min_lr: 0.000356  loss: 1.9872 (1.9328)  weight_decay: 0.0500 (0.0500)  time: 1.1627  data: 0.0006  max mem: 78493
Epoch: [246]  [ 30/312]  eta: 0:07:23  lr: 0.000356  min_lr: 0.000356  loss: 1.9872 (1.9144)  weight_decay: 0.0500 (0.0500)  time: 1.0074  data: 0.0005  max mem: 78493
Epoch: [246]  [ 40/312]  eta: 0:06:30  lr: 0.000355  min_lr: 0.000355  loss: 1.9135 (1.9046)  weight_decay: 0.0500 (0.0500)  time: 1.0073  data: 0.0004  max mem: 78493
Epoch: [246]  [ 50/312]  eta: 0:05:54  lr: 0.000355  min_lr: 0.000355  loss: 2.0001 (1.9177)  weight_decay: 0.0500 (0.0500)  time: 1.0066  data: 0.0004  max mem: 78493
Epoch: [246]  [ 60/312]  eta: 0:05:26  lr: 0.000354  min_lr: 0.000354  loss: 2.1177 (1.9323)  weight_decay: 0.0500 (0.0500)  time: 1.0043  data: 0.0004  max mem: 78493
Epoch: [246]  [ 70/312]  eta: 0:05:03  lr: 0.000354  min_lr: 0.000354  loss: 2.0411 (1.9431)  weight_decay: 0.0500 (0.0500)  time: 1.0080  data: 0.0005  max mem: 78493
Epoch: [246]  [ 80/312]  eta: 0:04:43  lr: 0.000354  min_lr: 0.000354  loss: 2.0437 (1.9484)  weight_decay: 0.0500 (0.0500)  time: 1.0094  data: 0.0005  max mem: 78493
Epoch: [246]  [ 90/312]  eta: 0:04:26  lr: 0.000353  min_lr: 0.000353  loss: 2.0762 (1.9596)  weight_decay: 0.0500 (0.0500)  time: 1.0087  data: 0.0005  max mem: 78493
Epoch: [246]  [100/312]  eta: 0:04:10  lr: 0.000353  min_lr: 0.000353  loss: 1.9995 (1.9458)  weight_decay: 0.0500 (0.0500)  time: 1.0086  data: 0.0005  max mem: 78493
Epoch: [246]  [110/312]  eta: 0:03:55  lr: 0.000352  min_lr: 0.000352  loss: 1.9995 (1.9605)  weight_decay: 0.0500 (0.0500)  time: 1.0085  data: 0.0005  max mem: 78493
Epoch: [246]  [120/312]  eta: 0:03:41  lr: 0.000352  min_lr: 0.000352  loss: 2.0351 (1.9639)  weight_decay: 0.0500 (0.0500)  time: 1.0096  data: 0.0004  max mem: 78493
Epoch: [246]  [130/312]  eta: 0:03:27  lr: 0.000352  min_lr: 0.000352  loss: 1.9979 (1.9621)  weight_decay: 0.0500 (0.0500)  time: 1.0084  data: 0.0004  max mem: 78493
Epoch: [246]  [140/312]  eta: 0:03:14  lr: 0.000351  min_lr: 0.000351  loss: 1.9661 (1.9666)  weight_decay: 0.0500 (0.0500)  time: 1.0072  data: 0.0004  max mem: 78493
Epoch: [246]  [150/312]  eta: 0:03:02  lr: 0.000351  min_lr: 0.000351  loss: 1.9661 (1.9610)  weight_decay: 0.0500 (0.0500)  time: 1.0076  data: 0.0004  max mem: 78493
Epoch: [246]  [160/312]  eta: 0:02:49  lr: 0.000350  min_lr: 0.000350  loss: 1.9158 (1.9569)  weight_decay: 0.0500 (0.0500)  time: 1.0082  data: 0.0004  max mem: 78493
Epoch: [246]  [170/312]  eta: 0:02:37  lr: 0.000350  min_lr: 0.000350  loss: 2.0398 (1.9596)  weight_decay: 0.0500 (0.0500)  time: 1.0075  data: 0.0004  max mem: 78493
Epoch: [246]  [180/312]  eta: 0:02:25  lr: 0.000350  min_lr: 0.000350  loss: 2.0516 (1.9576)  weight_decay: 0.0500 (0.0500)  time: 1.0073  data: 0.0005  max mem: 78493
Epoch: [246]  [190/312]  eta: 0:02:14  lr: 0.000349  min_lr: 0.000349  loss: 1.9727 (1.9574)  weight_decay: 0.0500 (0.0500)  time: 1.0069  data: 0.0004  max mem: 78493
Epoch: [246]  [200/312]  eta: 0:02:02  lr: 0.000349  min_lr: 0.000349  loss: 1.9182 (1.9551)  weight_decay: 0.0500 (0.0500)  time: 1.0053  data: 0.0004  max mem: 78493
Epoch: [246]  [210/312]  eta: 0:01:51  lr: 0.000348  min_lr: 0.000348  loss: 1.8686 (1.9496)  weight_decay: 0.0500 (0.0500)  time: 1.0047  data: 0.0005  max mem: 78493
Epoch: [246]  [220/312]  eta: 0:01:39  lr: 0.000348  min_lr: 0.000348  loss: 1.8917 (1.9485)  weight_decay: 0.0500 (0.0500)  time: 1.0050  data: 0.0005  max mem: 78493
Epoch: [246]  [230/312]  eta: 0:01:28  lr: 0.000348  min_lr: 0.000348  loss: 1.9312 (1.9409)  weight_decay: 0.0500 (0.0500)  time: 1.0073  data: 0.0004  max mem: 78493
Epoch: [246]  [240/312]  eta: 0:01:17  lr: 0.000347  min_lr: 0.000347  loss: 1.8427 (1.9397)  weight_decay: 0.0500 (0.0500)  time: 1.0075  data: 0.0004  max mem: 78493
Epoch: [246]  [250/312]  eta: 0:01:06  lr: 0.000347  min_lr: 0.000347  loss: 1.9333 (1.9388)  weight_decay: 0.0500 (0.0500)  time: 1.0046  data: 0.0004  max mem: 78493
Epoch: [246]  [260/312]  eta: 0:00:55  lr: 0.000346  min_lr: 0.000346  loss: 1.9376 (1.9397)  weight_decay: 0.0500 (0.0500)  time: 1.0046  data: 0.0005  max mem: 78493
Epoch: [246]  [270/312]  eta: 0:00:45  lr: 0.000346  min_lr: 0.000346  loss: 1.9823 (1.9397)  weight_decay: 0.0500 (0.0500)  time: 1.0047  data: 0.0005  max mem: 78493
Epoch: [246]  [280/312]  eta: 0:00:34  lr: 0.000346  min_lr: 0.000346  loss: 1.9823 (1.9401)  weight_decay: 0.0500 (0.0500)  time: 1.0059  data: 0.0011  max mem: 78493
Epoch: [246]  [290/312]  eta: 0:00:23  lr: 0.000345  min_lr: 0.000345  loss: 2.0132 (1.9372)  weight_decay: 0.0500 (0.0500)  time: 1.0050  data: 0.0009  max mem: 78493
Epoch: [246]  [300/312]  eta: 0:00:12  lr: 0.000345  min_lr: 0.000345  loss: 2.0132 (1.9394)  weight_decay: 0.0500 (0.0500)  time: 1.0014  data: 0.0001  max mem: 78493
Epoch: [246]  [310/312]  eta: 0:00:02  lr: 0.000344  min_lr: 0.000344  loss: 2.0542 (1.9378)  weight_decay: 0.0500 (0.0500)  time: 1.0013  data: 0.0001  max mem: 78493
Epoch: [246]  [311/312]  eta: 0:00:01  lr: 0.000344  min_lr: 0.000344  loss: 1.9382 (1.9375)  weight_decay: 0.0500 (0.0500)  time: 1.0014  data: 0.0001  max mem: 78493
Epoch: [246] Total time: 0:05:33 (1.0684 s / it)
Averaged stats: lr: 0.000344  min_lr: 0.000344  loss: 1.9382 (1.9302)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:13  loss: 0.4989 (0.4989)  acc1: 86.7188 (86.7188)  acc5: 97.6562 (97.6562)  time: 8.1645  data: 7.8830  max mem: 78493
Test:  [8/9]  eta: 0:00:01  loss: 0.7871 (0.7079)  acc1: 80.2083 (80.9920)  acc5: 96.2240 (95.4880)  time: 1.1054  data: 0.8760  max mem: 78493
Test: Total time: 0:00:10 (1.1516 s / it)
* Acc@1 81.486 Acc@5 95.762 loss 0.695
Accuracy of the model on the 50000 test images: 81.5%
Max accuracy: 81.49%
Epoch: [247]  [  0/312]  eta: 1:25:13  lr: 0.000344  min_lr: 0.000344  loss: 2.2745 (2.2745)  weight_decay: 0.0500 (0.0500)  time: 16.3882  data: 15.3846  max mem: 78493
Epoch: [247]  [ 10/312]  eta: 0:13:08  lr: 0.000344  min_lr: 0.000344  loss: 2.1814 (2.0349)  weight_decay: 0.0500 (0.0500)  time: 2.6117  data: 1.3996  max mem: 78493
Epoch: [247]  [ 20/312]  eta: 0:09:00  lr: 0.000343  min_lr: 0.000343  loss: 2.0989 (2.0211)  weight_decay: 0.0500 (0.0500)  time: 1.1257  data: 0.0008  max mem: 78493
Epoch: [247]  [ 30/312]  eta: 0:07:25  lr: 0.000343  min_lr: 0.000343  loss: 2.0612 (2.0079)  weight_decay: 0.0500 (0.0500)  time: 1.0128  data: 0.0005  max mem: 78493
Epoch: [247]  [ 40/312]  eta: 0:06:31  lr: 0.000343  min_lr: 0.000343  loss: 2.0302 (1.9940)  weight_decay: 0.0500 (0.0500)  time: 1.0076  data: 0.0004  max mem: 78493
Epoch: [247]  [ 50/312]  eta: 0:05:55  lr: 0.000342  min_lr: 0.000342  loss: 2.0302 (1.9875)  weight_decay: 0.0500 (0.0500)  time: 1.0067  data: 0.0005  max mem: 78493
Epoch: [247]  [ 60/312]  eta: 0:05:27  lr: 0.000342  min_lr: 0.000342  loss: 1.9764 (1.9694)  weight_decay: 0.0500 (0.0500)  time: 1.0057  data: 0.0005  max mem: 78493
Epoch: [247]  [ 70/312]  eta: 0:05:04  lr: 0.000341  min_lr: 0.000341  loss: 1.8327 (1.9344)  weight_decay: 0.0500 (0.0500)  time: 1.0040  data: 0.0005  max mem: 78493
Epoch: [247]  [ 80/312]  eta: 0:04:44  lr: 0.000341  min_lr: 0.000341  loss: 1.9810 (1.9442)  weight_decay: 0.0500 (0.0500)  time: 1.0047  data: 0.0004  max mem: 78493
Epoch: [247]  [ 90/312]  eta: 0:04:26  lr: 0.000341  min_lr: 0.000341  loss: 2.0593 (1.9505)  weight_decay: 0.0500 (0.0500)  time: 1.0065  data: 0.0005  max mem: 78493
Epoch: [247]  [100/312]  eta: 0:04:10  lr: 0.000340  min_lr: 0.000340  loss: 2.0622 (1.9583)  weight_decay: 0.0500 (0.0500)  time: 1.0081  data: 0.0005  max mem: 78493
Epoch: [247]  [110/312]  eta: 0:03:55  lr: 0.000340  min_lr: 0.000340  loss: 2.0867 (1.9670)  weight_decay: 0.0500 (0.0500)  time: 1.0094  data: 0.0004  max mem: 78493
Epoch: [247]  [120/312]  eta: 0:03:41  lr: 0.000339  min_lr: 0.000339  loss: 2.0414 (1.9709)  weight_decay: 0.0500 (0.0500)  time: 1.0085  data: 0.0004  max mem: 78493
Epoch: [247]  [130/312]  eta: 0:03:27  lr: 0.000339  min_lr: 0.000339  loss: 2.0129 (1.9747)  weight_decay: 0.0500 (0.0500)  time: 1.0065  data: 0.0004  max mem: 78493
Epoch: [247]  [140/312]  eta: 0:03:14  lr: 0.000339  min_lr: 0.000339  loss: 2.0434 (1.9760)  weight_decay: 0.0500 (0.0500)  time: 1.0080  data: 0.0017  max mem: 78493
Epoch: [247]  [150/312]  eta: 0:03:02  lr: 0.000338  min_lr: 0.000338  loss: 2.0963 (1.9837)  weight_decay: 0.0500 (0.0500)  time: 1.0079  data: 0.0017  max mem: 78493
Epoch: [247]  [160/312]  eta: 0:02:49  lr: 0.000338  min_lr: 0.000338  loss: 2.0719 (1.9719)  weight_decay: 0.0500 (0.0500)  time: 1.0068  data: 0.0005  max mem: 78493
Epoch: [247]  [170/312]  eta: 0:02:37  lr: 0.000337  min_lr: 0.000337  loss: 2.0460 (1.9787)  weight_decay: 0.0500 (0.0500)  time: 1.0064  data: 0.0005  max mem: 78493
Epoch: [247]  [180/312]  eta: 0:02:25  lr: 0.000337  min_lr: 0.000337  loss: 2.1087 (1.9806)  weight_decay: 0.0500 (0.0500)  time: 1.0067  data: 0.0005  max mem: 78493
Epoch: [247]  [190/312]  eta: 0:02:14  lr: 0.000337  min_lr: 0.000337  loss: 1.9727 (1.9744)  weight_decay: 0.0500 (0.0500)  time: 1.0100  data: 0.0004  max mem: 78493
Epoch: [247]  [200/312]  eta: 0:02:02  lr: 0.000336  min_lr: 0.000336  loss: 1.9727 (1.9721)  weight_decay: 0.0500 (0.0500)  time: 1.0092  data: 0.0004  max mem: 78493
Epoch: [247]  [210/312]  eta: 0:01:51  lr: 0.000336  min_lr: 0.000336  loss: 1.8887 (1.9664)  weight_decay: 0.0500 (0.0500)  time: 1.0066  data: 0.0004  max mem: 78493
Epoch: [247]  [220/312]  eta: 0:01:40  lr: 0.000335  min_lr: 0.000335  loss: 1.8887 (1.9658)  weight_decay: 0.0500 (0.0500)  time: 1.0062  data: 0.0004  max mem: 78493
Epoch: [247]  [230/312]  eta: 0:01:28  lr: 0.000335  min_lr: 0.000335  loss: 2.0714 (1.9596)  weight_decay: 0.0500 (0.0500)  time: 1.0078  data: 0.0004  max mem: 78493
Epoch: [247]  [240/312]  eta: 0:01:17  lr: 0.000335  min_lr: 0.000335  loss: 1.9214 (1.9590)  weight_decay: 0.0500 (0.0500)  time: 1.0080  data: 0.0004  max mem: 78493
Epoch: [247]  [250/312]  eta: 0:01:06  lr: 0.000334  min_lr: 0.000334  loss: 1.9179 (1.9533)  weight_decay: 0.0500 (0.0500)  time: 1.0076  data: 0.0004  max mem: 78493
Epoch: [247]  [260/312]  eta: 0:00:55  lr: 0.000334  min_lr: 0.000334  loss: 2.0859 (1.9581)  weight_decay: 0.0500 (0.0500)  time: 1.0076  data: 0.0004  max mem: 78493
Epoch: [247]  [270/312]  eta: 0:00:45  lr: 0.000333  min_lr: 0.000333  loss: 2.0542 (1.9556)  weight_decay: 0.0500 (0.0500)  time: 1.0058  data: 0.0004  max mem: 78493
Epoch: [247]  [280/312]  eta: 0:00:34  lr: 0.000333  min_lr: 0.000333  loss: 2.0322 (1.9602)  weight_decay: 0.0500 (0.0500)  time: 1.0058  data: 0.0011  max mem: 78493
Epoch: [247]  [290/312]  eta: 0:00:23  lr: 0.000333  min_lr: 0.000333  loss: 2.1241 (1.9642)  weight_decay: 0.0500 (0.0500)  time: 1.0043  data: 0.0009  max mem: 78493
Epoch: [247]  [300/312]  eta: 0:00:12  lr: 0.000332  min_lr: 0.000332  loss: 2.0164 (1.9602)  weight_decay: 0.0500 (0.0500)  time: 1.0015  data: 0.0001  max mem: 78493
Epoch: [247]  [310/312]  eta: 0:00:02  lr: 0.000332  min_lr: 0.000332  loss: 1.9850 (1.9602)  weight_decay: 0.0500 (0.0500)  time: 1.0015  data: 0.0001  max mem: 78493
Epoch: [247]  [311/312]  eta: 0:00:01  lr: 0.000332  min_lr: 0.000332  loss: 1.9477 (1.9585)  weight_decay: 0.0500 (0.0500)  time: 1.0015  data: 0.0001  max mem: 78493
Epoch: [247] Total time: 0:05:33 (1.0691 s / it)
Averaged stats: lr: 0.000332  min_lr: 0.000332  loss: 1.9477 (1.9131)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:16  loss: 0.4999 (0.4999)  acc1: 86.7188 (86.7188)  acc5: 98.0469 (98.0469)  time: 8.5284  data: 8.2537  max mem: 78493
Test:  [8/9]  eta: 0:00:01  loss: 0.7444 (0.6923)  acc1: 80.0781 (81.0720)  acc5: 96.4844 (95.8880)  time: 1.1457  data: 0.9172  max mem: 78493
Test: Total time: 0:00:10 (1.1803 s / it)
* Acc@1 81.646 Acc@5 95.780 loss 0.688
Accuracy of the model on the 50000 test images: 81.6%
Max accuracy: 81.65%
Epoch: [248]  [  0/312]  eta: 1:19:48  lr: 0.000332  min_lr: 0.000332  loss: 1.5778 (1.5778)  weight_decay: 0.0500 (0.0500)  time: 15.3488  data: 14.3371  max mem: 78493
Epoch: [248]  [ 10/312]  eta: 0:12:32  lr: 0.000331  min_lr: 0.000331  loss: 1.9504 (1.9777)  weight_decay: 0.0500 (0.0500)  time: 2.4924  data: 1.3528  max mem: 78493
Epoch: [248]  [ 20/312]  eta: 0:08:44  lr: 0.000331  min_lr: 0.000331  loss: 1.9695 (1.9968)  weight_decay: 0.0500 (0.0500)  time: 1.1182  data: 0.0276  max mem: 78493
Epoch: [248]  [ 30/312]  eta: 0:07:14  lr: 0.000331  min_lr: 0.000331  loss: 2.0990 (2.0038)  weight_decay: 0.0500 (0.0500)  time: 1.0181  data: 0.0007  max mem: 78493
Epoch: [248]  [ 40/312]  eta: 0:06:23  lr: 0.000330  min_lr: 0.000330  loss: 2.0619 (2.0071)  weight_decay: 0.0500 (0.0500)  time: 1.0069  data: 0.0005  max mem: 78493
Epoch: [248]  [ 50/312]  eta: 0:05:48  lr: 0.000330  min_lr: 0.000330  loss: 2.0889 (2.0161)  weight_decay: 0.0500 (0.0500)  time: 1.0060  data: 0.0005  max mem: 78493
Epoch: [248]  [ 60/312]  eta: 0:05:22  lr: 0.000329  min_lr: 0.000329  loss: 1.8140 (1.9651)  weight_decay: 0.0500 (0.0500)  time: 1.0075  data: 0.0004  max mem: 78493
Epoch: [248]  [ 70/312]  eta: 0:05:00  lr: 0.000329  min_lr: 0.000329  loss: 1.7675 (1.9354)  weight_decay: 0.0500 (0.0500)  time: 1.0076  data: 0.0004  max mem: 78493
Epoch: [248]  [ 80/312]  eta: 0:04:41  lr: 0.000329  min_lr: 0.000329  loss: 1.9419 (1.9324)  weight_decay: 0.0500 (0.0500)  time: 1.0057  data: 0.0005  max mem: 78493
Epoch: [248]  [ 90/312]  eta: 0:04:23  lr: 0.000328  min_lr: 0.000328  loss: 1.9421 (1.9219)  weight_decay: 0.0500 (0.0500)  time: 1.0065  data: 0.0005  max mem: 78493
Epoch: [248]  [100/312]  eta: 0:04:08  lr: 0.000328  min_lr: 0.000328  loss: 1.8972 (1.9328)  weight_decay: 0.0500 (0.0500)  time: 1.0078  data: 0.0005  max mem: 78493
Epoch: [248]  [110/312]  eta: 0:03:53  lr: 0.000327  min_lr: 0.000327  loss: 1.9140 (1.9307)  weight_decay: 0.0500 (0.0500)  time: 1.0083  data: 0.0004  max mem: 78493
Epoch: [248]  [120/312]  eta: 0:03:39  lr: 0.000327  min_lr: 0.000327  loss: 1.9042 (1.9241)  weight_decay: 0.0500 (0.0500)  time: 1.0082  data: 0.0004  max mem: 78493
Epoch: [248]  [130/312]  eta: 0:03:26  lr: 0.000327  min_lr: 0.000327  loss: 2.0484 (1.9292)  weight_decay: 0.0500 (0.0500)  time: 1.0080  data: 0.0004  max mem: 78493
Epoch: [248]  [140/312]  eta: 0:03:13  lr: 0.000326  min_lr: 0.000326  loss: 2.0349 (1.9260)  weight_decay: 0.0500 (0.0500)  time: 1.0073  data: 0.0004  max mem: 78493
Epoch: [248]  [150/312]  eta: 0:03:00  lr: 0.000326  min_lr: 0.000326  loss: 1.8569 (1.9256)  weight_decay: 0.0500 (0.0500)  time: 1.0068  data: 0.0004  max mem: 78493
Epoch: [248]  [160/312]  eta: 0:02:48  lr: 0.000325  min_lr: 0.000325  loss: 1.6344 (1.9072)  weight_decay: 0.0500 (0.0500)  time: 1.0061  data: 0.0004  max mem: 78493
Epoch: [248]  [170/312]  eta: 0:02:36  lr: 0.000325  min_lr: 0.000325  loss: 1.6479 (1.9121)  weight_decay: 0.0500 (0.0500)  time: 1.0069  data: 0.0004  max mem: 78493
Epoch: [248]  [180/312]  eta: 0:02:25  lr: 0.000325  min_lr: 0.000325  loss: 1.9316 (1.9124)  weight_decay: 0.0500 (0.0500)  time: 1.0075  data: 0.0005  max mem: 78493
Epoch: [248]  [190/312]  eta: 0:02:13  lr: 0.000324  min_lr: 0.000324  loss: 1.9316 (1.9125)  weight_decay: 0.0500 (0.0500)  time: 1.0083  data: 0.0005  max mem: 78493
Epoch: [248]  [200/312]  eta: 0:02:02  lr: 0.000324  min_lr: 0.000324  loss: 1.8753 (1.9080)  weight_decay: 0.0500 (0.0500)  time: 1.0071  data: 0.0005  max mem: 78493
Epoch: [248]  [210/312]  eta: 0:01:50  lr: 0.000323  min_lr: 0.000323  loss: 2.0613 (1.9125)  weight_decay: 0.0500 (0.0500)  time: 1.0057  data: 0.0005  max mem: 78493
Epoch: [248]  [220/312]  eta: 0:01:39  lr: 0.000323  min_lr: 0.000323  loss: 2.1165 (1.9126)  weight_decay: 0.0500 (0.0500)  time: 1.0056  data: 0.0004  max mem: 78493
Epoch: [248]  [230/312]  eta: 0:01:28  lr: 0.000323  min_lr: 0.000323  loss: 2.0560 (1.9135)  weight_decay: 0.0500 (0.0500)  time: 1.0056  data: 0.0004  max mem: 78493
Epoch: [248]  [240/312]  eta: 0:01:17  lr: 0.000322  min_lr: 0.000322  loss: 2.0358 (1.9163)  weight_decay: 0.0500 (0.0500)  time: 1.0051  data: 0.0004  max mem: 78493
Epoch: [248]  [250/312]  eta: 0:01:06  lr: 0.000322  min_lr: 0.000322  loss: 1.8916 (1.9098)  weight_decay: 0.0500 (0.0500)  time: 1.0054  data: 0.0004  max mem: 78493
Epoch: [248]  [260/312]  eta: 0:00:55  lr: 0.000322  min_lr: 0.000322  loss: 1.8916 (1.9109)  weight_decay: 0.0500 (0.0500)  time: 1.0061  data: 0.0004  max mem: 78493
Epoch: [248]  [270/312]  eta: 0:00:44  lr: 0.000321  min_lr: 0.000321  loss: 2.0345 (1.9073)  weight_decay: 0.0500 (0.0500)  time: 1.0051  data: 0.0004  max mem: 78493
Epoch: [248]  [280/312]  eta: 0:00:34  lr: 0.000321  min_lr: 0.000321  loss: 1.9319 (1.9026)  weight_decay: 0.0500 (0.0500)  time: 1.0068  data: 0.0011  max mem: 78493
Epoch: [248]  [290/312]  eta: 0:00:23  lr: 0.000320  min_lr: 0.000320  loss: 1.9245 (1.9042)  weight_decay: 0.0500 (0.0500)  time: 1.0057  data: 0.0009  max mem: 78493
Epoch: [248]  [300/312]  eta: 0:00:12  lr: 0.000320  min_lr: 0.000320  loss: 1.9245 (1.9059)  weight_decay: 0.0500 (0.0500)  time: 1.0020  data: 0.0001  max mem: 78493
Epoch: [248]  [310/312]  eta: 0:00:02  lr: 0.000320  min_lr: 0.000320  loss: 1.7945 (1.9035)  weight_decay: 0.0500 (0.0500)  time: 1.0015  data: 0.0001  max mem: 78493
Epoch: [248]  [311/312]  eta: 0:00:01  lr: 0.000320  min_lr: 0.000320  loss: 1.8461 (1.9034)  weight_decay: 0.0500 (0.0500)  time: 1.0014  data: 0.0001  max mem: 78493
Epoch: [248] Total time: 0:05:32 (1.0650 s / it)
Averaged stats: lr: 0.000320  min_lr: 0.000320  loss: 1.8461 (1.9176)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:13  loss: 0.5207 (0.5207)  acc1: 86.5885 (86.5885)  acc5: 97.6562 (97.6562)  time: 8.1940  data: 7.9116  max mem: 78493
Test:  [8/9]  eta: 0:00:01  loss: 0.7567 (0.7030)  acc1: 81.9010 (81.2000)  acc5: 95.3125 (95.4240)  time: 1.1087  data: 0.8791  max mem: 78493
Test: Total time: 0:00:10 (1.1535 s / it)
* Acc@1 81.600 Acc@5 95.696 loss 0.693
Accuracy of the model on the 50000 test images: 81.6%
Max accuracy: 81.65%
Epoch: [249]  [  0/312]  eta: 1:25:53  lr: 0.000320  min_lr: 0.000320  loss: 1.1765 (1.1765)  weight_decay: 0.0500 (0.0500)  time: 16.5168  data: 12.0250  max mem: 78493
Epoch: [249]  [ 10/312]  eta: 0:13:19  lr: 0.000319  min_lr: 0.000319  loss: 1.5819 (1.6314)  weight_decay: 0.0500 (0.0500)  time: 2.6464  data: 1.1200  max mem: 78493
Epoch: [249]  [ 20/312]  eta: 0:09:05  lr: 0.000319  min_lr: 0.000319  loss: 1.6879 (1.7261)  weight_decay: 0.0500 (0.0500)  time: 1.1375  data: 0.0165  max mem: 78493
Epoch: [249]  [ 30/312]  eta: 0:07:29  lr: 0.000318  min_lr: 0.000318  loss: 1.7836 (1.7547)  weight_decay: 0.0500 (0.0500)  time: 1.0129  data: 0.0027  max mem: 78493
Epoch: [249]  [ 40/312]  eta: 0:06:34  lr: 0.000318  min_lr: 0.000318  loss: 1.8492 (1.7702)  weight_decay: 0.0500 (0.0500)  time: 1.0123  data: 0.0036  max mem: 78493
Epoch: [249]  [ 50/312]  eta: 0:05:57  lr: 0.000318  min_lr: 0.000318  loss: 1.8492 (1.7786)  weight_decay: 0.0500 (0.0500)  time: 1.0153  data: 0.0028  max mem: 78493
Epoch: [249]  [ 60/312]  eta: 0:05:29  lr: 0.000317  min_lr: 0.000317  loss: 1.6430 (1.7977)  weight_decay: 0.0500 (0.0500)  time: 1.0155  data: 0.0005  max mem: 78493
Epoch: [249]  [ 70/312]  eta: 0:05:06  lr: 0.000317  min_lr: 0.000317  loss: 2.0281 (1.8216)  weight_decay: 0.0500 (0.0500)  time: 1.0136  data: 0.0005  max mem: 78493
Epoch: [249]  [ 80/312]  eta: 0:04:46  lr: 0.000316  min_lr: 0.000316  loss: 2.1093 (1.8536)  weight_decay: 0.0500 (0.0500)  time: 1.0138  data: 0.0014  max mem: 78493
Epoch: [249]  [ 90/312]  eta: 0:04:28  lr: 0.000316  min_lr: 0.000316  loss: 2.1376 (1.8745)  weight_decay: 0.0500 (0.0500)  time: 1.0118  data: 0.0014  max mem: 78493
Epoch: [249]  [100/312]  eta: 0:04:12  lr: 0.000316  min_lr: 0.000316  loss: 2.0059 (1.8623)  weight_decay: 0.0500 (0.0500)  time: 1.0105  data: 0.0005  max mem: 78493
Epoch: [249]  [110/312]  eta: 0:03:57  lr: 0.000315  min_lr: 0.000315  loss: 1.9302 (1.8815)  weight_decay: 0.0500 (0.0500)  time: 1.0102  data: 0.0005  max mem: 78493
Epoch: [249]  [120/312]  eta: 0:03:42  lr: 0.000315  min_lr: 0.000315  loss: 2.0228 (1.8855)  weight_decay: 0.0500 (0.0500)  time: 1.0094  data: 0.0005  max mem: 78493
Epoch: [249]  [130/312]  eta: 0:03:29  lr: 0.000314  min_lr: 0.000314  loss: 1.8700 (1.8882)  weight_decay: 0.0500 (0.0500)  time: 1.0094  data: 0.0005  max mem: 78493
Epoch: [249]  [140/312]  eta: 0:03:16  lr: 0.000314  min_lr: 0.000314  loss: 1.8059 (1.8790)  weight_decay: 0.0500 (0.0500)  time: 1.0108  data: 0.0005  max mem: 78493
Epoch: [249]  [150/312]  eta: 0:03:03  lr: 0.000314  min_lr: 0.000314  loss: 1.7615 (1.8799)  weight_decay: 0.0500 (0.0500)  time: 1.0157  data: 0.0013  max mem: 78493
Epoch: [249]  [160/312]  eta: 0:02:50  lr: 0.000313  min_lr: 0.000313  loss: 1.8676 (1.8770)  weight_decay: 0.0500 (0.0500)  time: 1.0122  data: 0.0013  max mem: 78493
Epoch: [249]  [170/312]  eta: 0:02:38  lr: 0.000313  min_lr: 0.000313  loss: 1.9492 (1.8849)  weight_decay: 0.0500 (0.0500)  time: 1.0058  data: 0.0004  max mem: 78493
Epoch: [249]  [180/312]  eta: 0:02:26  lr: 0.000313  min_lr: 0.000313  loss: 2.0749 (1.8949)  weight_decay: 0.0500 (0.0500)  time: 1.0057  data: 0.0004  max mem: 78493
Epoch: [249]  [190/312]  eta: 0:02:14  lr: 0.000312  min_lr: 0.000312  loss: 1.9537 (1.8937)  weight_decay: 0.0500 (0.0500)  time: 1.0084  data: 0.0004  max mem: 78493
Epoch: [249]  [200/312]  eta: 0:02:03  lr: 0.000312  min_lr: 0.000312  loss: 1.8564 (1.8920)  weight_decay: 0.0500 (0.0500)  time: 1.0081  data: 0.0004  max mem: 78493
Epoch: [249]  [210/312]  eta: 0:01:51  lr: 0.000311  min_lr: 0.000311  loss: 1.7589 (1.8855)  weight_decay: 0.0500 (0.0500)  time: 1.0059  data: 0.0004  max mem: 78493
Epoch: [249]  [220/312]  eta: 0:01:40  lr: 0.000311  min_lr: 0.000311  loss: 1.8656 (1.8838)  weight_decay: 0.0500 (0.0500)  time: 1.0062  data: 0.0004  max mem: 78493
Epoch: [249]  [230/312]  eta: 0:01:29  lr: 0.000311  min_lr: 0.000311  loss: 2.0888 (1.8929)  weight_decay: 0.0500 (0.0500)  time: 1.0079  data: 0.0004  max mem: 78493
Epoch: [249]  [240/312]  eta: 0:01:18  lr: 0.000310  min_lr: 0.000310  loss: 2.1502 (1.9016)  weight_decay: 0.0500 (0.0500)  time: 1.0070  data: 0.0004  max mem: 78493
Epoch: [249]  [250/312]  eta: 0:01:07  lr: 0.000310  min_lr: 0.000310  loss: 2.1194 (1.9000)  weight_decay: 0.0500 (0.0500)  time: 1.0054  data: 0.0004  max mem: 78493
Epoch: [249]  [260/312]  eta: 0:00:56  lr: 0.000309  min_lr: 0.000309  loss: 2.0224 (1.9032)  weight_decay: 0.0500 (0.0500)  time: 1.0059  data: 0.0004  max mem: 78493
Epoch: [249]  [270/312]  eta: 0:00:45  lr: 0.000309  min_lr: 0.000309  loss: 2.0224 (1.9041)  weight_decay: 0.0500 (0.0500)  time: 1.0054  data: 0.0005  max mem: 78493
Epoch: [249]  [280/312]  eta: 0:00:34  lr: 0.000309  min_lr: 0.000309  loss: 1.9761 (1.9020)  weight_decay: 0.0500 (0.0500)  time: 1.0072  data: 0.0010  max mem: 78493
Epoch: [249]  [290/312]  eta: 0:00:23  lr: 0.000308  min_lr: 0.000308  loss: 1.9761 (1.9046)  weight_decay: 0.0500 (0.0500)  time: 1.0060  data: 0.0009  max mem: 78493
Epoch: [249]  [300/312]  eta: 0:00:12  lr: 0.000308  min_lr: 0.000308  loss: 1.9621 (1.9035)  weight_decay: 0.0500 (0.0500)  time: 1.0023  data: 0.0001  max mem: 78493
Epoch: [249]  [310/312]  eta: 0:00:02  lr: 0.000308  min_lr: 0.000308  loss: 1.9735 (1.9009)  weight_decay: 0.0500 (0.0500)  time: 1.0015  data: 0.0001  max mem: 78493
Epoch: [249]  [311/312]  eta: 0:00:01  lr: 0.000308  min_lr: 0.000308  loss: 1.8487 (1.8998)  weight_decay: 0.0500 (0.0500)  time: 1.0015  data: 0.0001  max mem: 78493
Epoch: [249] Total time: 0:05:34 (1.0724 s / it)
Averaged stats: lr: 0.000308  min_lr: 0.000308  loss: 1.8487 (1.9092)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:14  loss: 0.4924 (0.4924)  acc1: 87.5000 (87.5000)  acc5: 98.0469 (98.0469)  time: 8.2508  data: 7.9738  max mem: 78493
Test:  [8/9]  eta: 0:00:01  loss: 0.7546 (0.6958)  acc1: 81.7708 (81.2320)  acc5: 96.2240 (95.7440)  time: 1.1150  data: 0.8861  max mem: 78493
Test: Total time: 0:00:10 (1.1276 s / it)
* Acc@1 81.694 Acc@5 95.788 loss 0.685
Accuracy of the model on the 50000 test images: 81.7%
Max accuracy: 81.69%
Epoch: [250]  [  0/312]  eta: 1:21:57  lr: 0.000307  min_lr: 0.000307  loss: 1.6151 (1.6151)  weight_decay: 0.0500 (0.0500)  time: 15.7610  data: 13.1338  max mem: 78493
Epoch: [250]  [ 10/312]  eta: 0:13:18  lr: 0.000307  min_lr: 0.000307  loss: 1.8509 (1.8102)  weight_decay: 0.0500 (0.0500)  time: 2.6427  data: 1.1980  max mem: 78493
Epoch: [250]  [ 20/312]  eta: 0:09:05  lr: 0.000307  min_lr: 0.000307  loss: 1.9183 (1.8355)  weight_decay: 0.0500 (0.0500)  time: 1.1735  data: 0.0038  max mem: 78493
Epoch: [250]  [ 30/312]  eta: 0:07:28  lr: 0.000306  min_lr: 0.000306  loss: 1.9839 (1.8367)  weight_decay: 0.0500 (0.0500)  time: 1.0108  data: 0.0018  max mem: 78493
Epoch: [250]  [ 40/312]  eta: 0:06:33  lr: 0.000306  min_lr: 0.000306  loss: 2.0254 (1.8960)  weight_decay: 0.0500 (0.0500)  time: 1.0059  data: 0.0004  max mem: 78493
Epoch: [250]  [ 50/312]  eta: 0:05:56  lr: 0.000306  min_lr: 0.000306  loss: 2.0343 (1.8829)  weight_decay: 0.0500 (0.0500)  time: 1.0066  data: 0.0004  max mem: 78493
Epoch: [250]  [ 60/312]  eta: 0:05:28  lr: 0.000305  min_lr: 0.000305  loss: 2.0069 (1.9116)  weight_decay: 0.0500 (0.0500)  time: 1.0080  data: 0.0004  max mem: 78493
Epoch: [250]  [ 70/312]  eta: 0:05:05  lr: 0.000305  min_lr: 0.000305  loss: 2.0069 (1.9039)  weight_decay: 0.0500 (0.0500)  time: 1.0092  data: 0.0005  max mem: 78493
Epoch: [250]  [ 80/312]  eta: 0:04:45  lr: 0.000304  min_lr: 0.000304  loss: 1.9078 (1.8930)  weight_decay: 0.0500 (0.0500)  time: 1.0090  data: 0.0011  max mem: 78493
Epoch: [250]  [ 90/312]  eta: 0:04:27  lr: 0.000304  min_lr: 0.000304  loss: 1.8792 (1.8980)  weight_decay: 0.0500 (0.0500)  time: 1.0084  data: 0.0011  max mem: 78493
Epoch: [250]  [100/312]  eta: 0:04:11  lr: 0.000304  min_lr: 0.000304  loss: 2.0645 (1.9130)  weight_decay: 0.0500 (0.0500)  time: 1.0087  data: 0.0005  max mem: 78493
Epoch: [250]  [110/312]  eta: 0:03:56  lr: 0.000303  min_lr: 0.000303  loss: 1.9717 (1.9127)  weight_decay: 0.0500 (0.0500)  time: 1.0088  data: 0.0005  max mem: 78493
Epoch: [250]  [120/312]  eta: 0:03:42  lr: 0.000303  min_lr: 0.000303  loss: 1.9294 (1.9081)  weight_decay: 0.0500 (0.0500)  time: 1.0098  data: 0.0005  max mem: 78493
Epoch: [250]  [130/312]  eta: 0:03:28  lr: 0.000303  min_lr: 0.000303  loss: 2.0212 (1.9157)  weight_decay: 0.0500 (0.0500)  time: 1.0117  data: 0.0004  max mem: 78493
Epoch: [250]  [140/312]  eta: 0:03:15  lr: 0.000302  min_lr: 0.000302  loss: 2.0330 (1.9212)  weight_decay: 0.0500 (0.0500)  time: 1.0115  data: 0.0005  max mem: 78493
Epoch: [250]  [150/312]  eta: 0:03:02  lr: 0.000302  min_lr: 0.000302  loss: 1.9187 (1.9151)  weight_decay: 0.0500 (0.0500)  time: 1.0080  data: 0.0004  max mem: 78493
Epoch: [250]  [160/312]  eta: 0:02:50  lr: 0.000301  min_lr: 0.000301  loss: 2.0312 (1.9258)  weight_decay: 0.0500 (0.0500)  time: 1.0056  data: 0.0005  max mem: 78493
Epoch: [250]  [170/312]  eta: 0:02:38  lr: 0.000301  min_lr: 0.000301  loss: 2.0225 (1.9289)  weight_decay: 0.0500 (0.0500)  time: 1.0055  data: 0.0005  max mem: 78493
Epoch: [250]  [180/312]  eta: 0:02:26  lr: 0.000301  min_lr: 0.000301  loss: 1.9787 (1.9329)  weight_decay: 0.0500 (0.0500)  time: 1.0050  data: 0.0005  max mem: 78493
Epoch: [250]  [190/312]  eta: 0:02:14  lr: 0.000300  min_lr: 0.000300  loss: 1.9992 (1.9310)  weight_decay: 0.0500 (0.0500)  time: 1.0045  data: 0.0004  max mem: 78493
Epoch: [250]  [200/312]  eta: 0:02:02  lr: 0.000300  min_lr: 0.000300  loss: 1.9992 (1.9285)  weight_decay: 0.0500 (0.0500)  time: 1.0045  data: 0.0011  max mem: 78493
Epoch: [250]  [210/312]  eta: 0:01:51  lr: 0.000299  min_lr: 0.000299  loss: 1.6567 (1.9186)  weight_decay: 0.0500 (0.0500)  time: 1.0049  data: 0.0011  max mem: 78493
Epoch: [250]  [220/312]  eta: 0:01:40  lr: 0.000299  min_lr: 0.000299  loss: 1.9483 (1.9248)  weight_decay: 0.0500 (0.0500)  time: 1.0046  data: 0.0005  max mem: 78493
Epoch: [250]  [230/312]  eta: 0:01:29  lr: 0.000299  min_lr: 0.000299  loss: 2.0561 (1.9275)  weight_decay: 0.0500 (0.0500)  time: 1.0065  data: 0.0005  max mem: 78493
Epoch: [250]  [240/312]  eta: 0:01:17  lr: 0.000298  min_lr: 0.000298  loss: 1.9566 (1.9250)  weight_decay: 0.0500 (0.0500)  time: 1.0072  data: 0.0005  max mem: 78493
Epoch: [250]  [250/312]  eta: 0:01:06  lr: 0.000298  min_lr: 0.000298  loss: 1.7671 (1.9152)  weight_decay: 0.0500 (0.0500)  time: 1.0045  data: 0.0004  max mem: 78493
Epoch: [250]  [260/312]  eta: 0:00:55  lr: 0.000298  min_lr: 0.000298  loss: 1.8141 (1.9165)  weight_decay: 0.0500 (0.0500)  time: 1.0054  data: 0.0004  max mem: 78493
Epoch: [250]  [270/312]  eta: 0:00:45  lr: 0.000297  min_lr: 0.000297  loss: 2.0246 (1.9137)  weight_decay: 0.0500 (0.0500)  time: 1.0062  data: 0.0004  max mem: 78493
Epoch: [250]  [280/312]  eta: 0:00:34  lr: 0.000297  min_lr: 0.000297  loss: 1.8298 (1.9074)  weight_decay: 0.0500 (0.0500)  time: 1.0139  data: 0.0011  max mem: 78493
Epoch: [250]  [290/312]  eta: 0:00:23  lr: 0.000296  min_lr: 0.000296  loss: 1.8298 (1.9086)  weight_decay: 0.0500 (0.0500)  time: 1.0127  data: 0.0009  max mem: 78493
Epoch: [250]  [300/312]  eta: 0:00:12  lr: 0.000296  min_lr: 0.000296  loss: 2.0015 (1.9119)  weight_decay: 0.0500 (0.0500)  time: 1.0016  data: 0.0001  max mem: 78493
Epoch: [250]  [310/312]  eta: 0:00:02  lr: 0.000296  min_lr: 0.000296  loss: 2.0015 (1.9097)  weight_decay: 0.0500 (0.0500)  time: 1.0016  data: 0.0001  max mem: 78493
Epoch: [250]  [311/312]  eta: 0:00:01  lr: 0.000296  min_lr: 0.000296  loss: 2.0270 (1.9100)  weight_decay: 0.0500 (0.0500)  time: 1.0016  data: 0.0001  max mem: 78493
Epoch: [250] Total time: 0:05:34 (1.0708 s / it)
Averaged stats: lr: 0.000296  min_lr: 0.000296  loss: 2.0270 (1.9054)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:17  loss: 0.5074 (0.5074)  acc1: 87.5000 (87.5000)  acc5: 97.7865 (97.7865)  time: 8.6478  data: 8.3734  max mem: 78493
Test:  [8/9]  eta: 0:00:01  loss: 0.7538 (0.6865)  acc1: 81.3802 (81.4880)  acc5: 96.0938 (95.8720)  time: 1.1590  data: 0.9305  max mem: 78493
Test: Total time: 0:00:10 (1.1742 s / it)
* Acc@1 81.762 Acc@5 95.812 loss 0.682
Accuracy of the model on the 50000 test images: 81.8%
Max accuracy: 81.76%
Epoch: [251]  [  0/312]  eta: 1:27:14  lr: 0.000296  min_lr: 0.000296  loss: 2.4774 (2.4774)  weight_decay: 0.0500 (0.0500)  time: 16.7757  data: 15.7708  max mem: 78493
Epoch: [251]  [ 10/312]  eta: 0:13:19  lr: 0.000295  min_lr: 0.000295  loss: 2.0366 (2.0689)  weight_decay: 0.0500 (0.0500)  time: 2.6482  data: 1.4343  max mem: 78493
Epoch: [251]  [ 20/312]  eta: 0:09:05  lr: 0.000295  min_lr: 0.000295  loss: 1.9750 (2.0226)  weight_decay: 0.0500 (0.0500)  time: 1.1215  data: 0.0005  max mem: 78493
Epoch: [251]  [ 30/312]  eta: 0:07:28  lr: 0.000295  min_lr: 0.000295  loss: 1.9497 (1.9529)  weight_decay: 0.0500 (0.0500)  time: 1.0103  data: 0.0004  max mem: 78493
Epoch: [251]  [ 40/312]  eta: 0:06:34  lr: 0.000294  min_lr: 0.000294  loss: 1.8148 (1.9191)  weight_decay: 0.0500 (0.0500)  time: 1.0117  data: 0.0004  max mem: 78493
Epoch: [251]  [ 50/312]  eta: 0:05:57  lr: 0.000294  min_lr: 0.000294  loss: 1.7200 (1.9082)  weight_decay: 0.0500 (0.0500)  time: 1.0138  data: 0.0016  max mem: 78493
Epoch: [251]  [ 60/312]  eta: 0:05:29  lr: 0.000293  min_lr: 0.000293  loss: 1.9968 (1.9308)  weight_decay: 0.0500 (0.0500)  time: 1.0150  data: 0.0016  max mem: 78493
Epoch: [251]  [ 70/312]  eta: 0:05:06  lr: 0.000293  min_lr: 0.000293  loss: 2.0212 (1.9399)  weight_decay: 0.0500 (0.0500)  time: 1.0121  data: 0.0005  max mem: 78493
Epoch: [251]  [ 80/312]  eta: 0:04:46  lr: 0.000293  min_lr: 0.000293  loss: 1.8627 (1.9235)  weight_decay: 0.0500 (0.0500)  time: 1.0118  data: 0.0005  max mem: 78493
Epoch: [251]  [ 90/312]  eta: 0:04:28  lr: 0.000292  min_lr: 0.000292  loss: 1.6848 (1.9094)  weight_decay: 0.0500 (0.0500)  time: 1.0109  data: 0.0005  max mem: 78493
Epoch: [251]  [100/312]  eta: 0:04:12  lr: 0.000292  min_lr: 0.000292  loss: 1.9088 (1.9155)  weight_decay: 0.0500 (0.0500)  time: 1.0109  data: 0.0013  max mem: 78493
Epoch: [251]  [110/312]  eta: 0:03:57  lr: 0.000292  min_lr: 0.000292  loss: 2.0620 (1.9160)  weight_decay: 0.0500 (0.0500)  time: 1.0091  data: 0.0020  max mem: 78493
Epoch: [251]  [120/312]  eta: 0:03:42  lr: 0.000291  min_lr: 0.000291  loss: 1.7023 (1.8878)  weight_decay: 0.0500 (0.0500)  time: 1.0069  data: 0.0011  max mem: 78493
Epoch: [251]  [130/312]  eta: 0:03:28  lr: 0.000291  min_lr: 0.000291  loss: 1.5764 (1.8862)  weight_decay: 0.0500 (0.0500)  time: 1.0075  data: 0.0011  max mem: 78493
Epoch: [251]  [140/312]  eta: 0:03:15  lr: 0.000290  min_lr: 0.000290  loss: 2.0658 (1.8967)  weight_decay: 0.0500 (0.0500)  time: 1.0076  data: 0.0011  max mem: 78493
Epoch: [251]  [150/312]  eta: 0:03:03  lr: 0.000290  min_lr: 0.000290  loss: 2.0170 (1.8924)  weight_decay: 0.0500 (0.0500)  time: 1.0091  data: 0.0004  max mem: 78493
Epoch: [251]  [160/312]  eta: 0:02:50  lr: 0.000290  min_lr: 0.000290  loss: 1.8051 (1.8944)  weight_decay: 0.0500 (0.0500)  time: 1.0073  data: 0.0004  max mem: 78493
Epoch: [251]  [170/312]  eta: 0:02:38  lr: 0.000289  min_lr: 0.000289  loss: 2.0078 (1.8962)  weight_decay: 0.0500 (0.0500)  time: 1.0063  data: 0.0011  max mem: 78493
Epoch: [251]  [180/312]  eta: 0:02:26  lr: 0.000289  min_lr: 0.000289  loss: 1.9591 (1.8942)  weight_decay: 0.0500 (0.0500)  time: 1.0080  data: 0.0011  max mem: 78493
Epoch: [251]  [190/312]  eta: 0:02:14  lr: 0.000289  min_lr: 0.000289  loss: 1.8263 (1.8918)  weight_decay: 0.0500 (0.0500)  time: 1.0074  data: 0.0005  max mem: 78493
Epoch: [251]  [200/312]  eta: 0:02:03  lr: 0.000288  min_lr: 0.000288  loss: 1.9475 (1.8976)  weight_decay: 0.0500 (0.0500)  time: 1.0084  data: 0.0004  max mem: 78493
Epoch: [251]  [210/312]  eta: 0:01:51  lr: 0.000288  min_lr: 0.000288  loss: 1.9711 (1.8929)  weight_decay: 0.0500 (0.0500)  time: 1.0086  data: 0.0004  max mem: 78493
Epoch: [251]  [220/312]  eta: 0:01:40  lr: 0.000287  min_lr: 0.000287  loss: 2.0128 (1.9005)  weight_decay: 0.0500 (0.0500)  time: 1.0072  data: 0.0004  max mem: 78493
Epoch: [251]  [230/312]  eta: 0:01:29  lr: 0.000287  min_lr: 0.000287  loss: 2.0128 (1.8983)  weight_decay: 0.0500 (0.0500)  time: 1.0069  data: 0.0004  max mem: 78493
Epoch: [251]  [240/312]  eta: 0:01:18  lr: 0.000287  min_lr: 0.000287  loss: 1.8780 (1.9004)  weight_decay: 0.0500 (0.0500)  time: 1.0084  data: 0.0004  max mem: 78493
Epoch: [251]  [250/312]  eta: 0:01:07  lr: 0.000286  min_lr: 0.000286  loss: 1.8761 (1.8959)  weight_decay: 0.0500 (0.0500)  time: 1.0071  data: 0.0004  max mem: 78493
Epoch: [251]  [260/312]  eta: 0:00:56  lr: 0.000286  min_lr: 0.000286  loss: 1.8258 (1.8963)  weight_decay: 0.0500 (0.0500)  time: 1.0044  data: 0.0004  max mem: 78493
Epoch: [251]  [270/312]  eta: 0:00:45  lr: 0.000286  min_lr: 0.000286  loss: 2.0085 (1.9016)  weight_decay: 0.0500 (0.0500)  time: 1.0048  data: 0.0004  max mem: 78493
Epoch: [251]  [280/312]  eta: 0:00:34  lr: 0.000285  min_lr: 0.000285  loss: 2.0798 (1.9089)  weight_decay: 0.0500 (0.0500)  time: 1.0077  data: 0.0010  max mem: 78493
Epoch: [251]  [290/312]  eta: 0:00:23  lr: 0.000285  min_lr: 0.000285  loss: 1.9991 (1.9087)  weight_decay: 0.0500 (0.0500)  time: 1.0058  data: 0.0009  max mem: 78493
Epoch: [251]  [300/312]  eta: 0:00:12  lr: 0.000284  min_lr: 0.000284  loss: 1.9712 (1.9058)  weight_decay: 0.0500 (0.0500)  time: 1.0016  data: 0.0001  max mem: 78493
Epoch: [251]  [310/312]  eta: 0:00:02  lr: 0.000284  min_lr: 0.000284  loss: 1.9604 (1.9070)  weight_decay: 0.0500 (0.0500)  time: 1.0017  data: 0.0001  max mem: 78493
Epoch: [251]  [311/312]  eta: 0:00:01  lr: 0.000284  min_lr: 0.000284  loss: 1.9593 (1.9055)  weight_decay: 0.0500 (0.0500)  time: 1.0017  data: 0.0001  max mem: 78493
Epoch: [251] Total time: 0:05:34 (1.0719 s / it)
Averaged stats: lr: 0.000284  min_lr: 0.000284  loss: 1.9593 (1.9100)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:16  loss: 0.4849 (0.4849)  acc1: 87.6302 (87.6302)  acc5: 97.7865 (97.7865)  time: 8.5382  data: 8.2692  max mem: 78493
Test:  [8/9]  eta: 0:00:01  loss: 0.7493 (0.6896)  acc1: 81.7708 (81.4240)  acc5: 96.3542 (95.7440)  time: 1.1472  data: 0.9189  max mem: 78493
Test: Total time: 0:00:10 (1.1928 s / it)
* Acc@1 81.766 Acc@5 95.790 loss 0.685
Accuracy of the model on the 50000 test images: 81.8%
Max accuracy: 81.77%
Epoch: [252]  [  0/312]  eta: 1:24:05  lr: 0.000284  min_lr: 0.000284  loss: 1.5837 (1.5837)  weight_decay: 0.0500 (0.0500)  time: 16.1703  data: 12.3019  max mem: 78493
Epoch: [252]  [ 10/312]  eta: 0:13:04  lr: 0.000284  min_lr: 0.000284  loss: 2.0372 (1.9371)  weight_decay: 0.0500 (0.0500)  time: 2.5973  data: 1.2868  max mem: 78493
Epoch: [252]  [ 20/312]  eta: 0:08:59  lr: 0.000283  min_lr: 0.000283  loss: 1.9033 (1.8796)  weight_decay: 0.0500 (0.0500)  time: 1.1310  data: 0.0930  max mem: 78493
Epoch: [252]  [ 30/312]  eta: 0:07:24  lr: 0.000283  min_lr: 0.000283  loss: 1.8624 (1.9239)  weight_decay: 0.0500 (0.0500)  time: 1.0151  data: 0.0006  max mem: 78493
Epoch: [252]  [ 40/312]  eta: 0:06:31  lr: 0.000283  min_lr: 0.000283  loss: 2.0488 (1.9511)  weight_decay: 0.0500 (0.0500)  time: 1.0083  data: 0.0004  max mem: 78493
Epoch: [252]  [ 50/312]  eta: 0:05:54  lr: 0.000282  min_lr: 0.000282  loss: 1.9110 (1.9282)  weight_decay: 0.0500 (0.0500)  time: 1.0073  data: 0.0004  max mem: 78493
Epoch: [252]  [ 60/312]  eta: 0:05:26  lr: 0.000282  min_lr: 0.000282  loss: 1.8774 (1.9441)  weight_decay: 0.0500 (0.0500)  time: 1.0060  data: 0.0004  max mem: 78493
Epoch: [252]  [ 70/312]  eta: 0:05:03  lr: 0.000281  min_lr: 0.000281  loss: 1.8885 (1.9315)  weight_decay: 0.0500 (0.0500)  time: 1.0073  data: 0.0004  max mem: 78493
Epoch: [252]  [ 80/312]  eta: 0:04:44  lr: 0.000281  min_lr: 0.000281  loss: 1.9260 (1.9409)  weight_decay: 0.0500 (0.0500)  time: 1.0093  data: 0.0004  max mem: 78493
Epoch: [252]  [ 90/312]  eta: 0:04:26  lr: 0.000281  min_lr: 0.000281  loss: 1.9573 (1.9301)  weight_decay: 0.0500 (0.0500)  time: 1.0083  data: 0.0005  max mem: 78493
Epoch: [252]  [100/312]  eta: 0:04:10  lr: 0.000280  min_lr: 0.000280  loss: 1.8747 (1.9298)  weight_decay: 0.0500 (0.0500)  time: 1.0087  data: 0.0012  max mem: 78493
Epoch: [252]  [110/312]  eta: 0:03:55  lr: 0.000280  min_lr: 0.000280  loss: 1.9902 (1.9330)  weight_decay: 0.0500 (0.0500)  time: 1.0080  data: 0.0012  max mem: 78493
Epoch: [252]  [120/312]  eta: 0:03:41  lr: 0.000280  min_lr: 0.000280  loss: 1.9720 (1.9274)  weight_decay: 0.0500 (0.0500)  time: 1.0070  data: 0.0004  max mem: 78493
Epoch: [252]  [130/312]  eta: 0:03:27  lr: 0.000279  min_lr: 0.000279  loss: 2.0092 (1.9301)  weight_decay: 0.0500 (0.0500)  time: 1.0071  data: 0.0004  max mem: 78493
Epoch: [252]  [140/312]  eta: 0:03:14  lr: 0.000279  min_lr: 0.000279  loss: 2.0588 (1.9314)  weight_decay: 0.0500 (0.0500)  time: 1.0055  data: 0.0005  max mem: 78493
Epoch: [252]  [150/312]  eta: 0:03:02  lr: 0.000279  min_lr: 0.000279  loss: 1.9938 (1.9232)  weight_decay: 0.0500 (0.0500)  time: 1.0059  data: 0.0004  max mem: 78493
Epoch: [252]  [160/312]  eta: 0:02:49  lr: 0.000278  min_lr: 0.000278  loss: 1.8155 (1.9180)  weight_decay: 0.0500 (0.0500)  time: 1.0080  data: 0.0004  max mem: 78493
Epoch: [252]  [170/312]  eta: 0:02:37  lr: 0.000278  min_lr: 0.000278  loss: 1.7453 (1.9118)  weight_decay: 0.0500 (0.0500)  time: 1.0075  data: 0.0004  max mem: 78493
Epoch: [252]  [180/312]  eta: 0:02:25  lr: 0.000277  min_lr: 0.000277  loss: 1.7413 (1.9005)  weight_decay: 0.0500 (0.0500)  time: 1.0053  data: 0.0004  max mem: 78493
Epoch: [252]  [190/312]  eta: 0:02:14  lr: 0.000277  min_lr: 0.000277  loss: 1.8748 (1.9030)  weight_decay: 0.0500 (0.0500)  time: 1.0054  data: 0.0004  max mem: 78493
Epoch: [252]  [200/312]  eta: 0:02:02  lr: 0.000277  min_lr: 0.000277  loss: 1.9288 (1.8997)  weight_decay: 0.0500 (0.0500)  time: 1.0050  data: 0.0004  max mem: 78493
Epoch: [252]  [210/312]  eta: 0:01:51  lr: 0.000276  min_lr: 0.000276  loss: 1.8232 (1.8984)  weight_decay: 0.0500 (0.0500)  time: 1.0053  data: 0.0004  max mem: 78493
Epoch: [252]  [220/312]  eta: 0:01:39  lr: 0.000276  min_lr: 0.000276  loss: 1.9535 (1.9009)  weight_decay: 0.0500 (0.0500)  time: 1.0041  data: 0.0004  max mem: 78493
Epoch: [252]  [230/312]  eta: 0:01:28  lr: 0.000276  min_lr: 0.000276  loss: 1.9966 (1.8995)  weight_decay: 0.0500 (0.0500)  time: 1.0037  data: 0.0005  max mem: 78493
Epoch: [252]  [240/312]  eta: 0:01:17  lr: 0.000275  min_lr: 0.000275  loss: 1.9276 (1.9049)  weight_decay: 0.0500 (0.0500)  time: 1.0052  data: 0.0005  max mem: 78493
Epoch: [252]  [250/312]  eta: 0:01:06  lr: 0.000275  min_lr: 0.000275  loss: 1.9550 (1.9024)  weight_decay: 0.0500 (0.0500)  time: 1.0054  data: 0.0013  max mem: 78493
Epoch: [252]  [260/312]  eta: 0:00:55  lr: 0.000275  min_lr: 0.000275  loss: 1.7725 (1.9006)  weight_decay: 0.0500 (0.0500)  time: 1.0068  data: 0.0013  max mem: 78493
Epoch: [252]  [270/312]  eta: 0:00:45  lr: 0.000274  min_lr: 0.000274  loss: 1.7708 (1.8937)  weight_decay: 0.0500 (0.0500)  time: 1.0068  data: 0.0005  max mem: 78493
Epoch: [252]  [280/312]  eta: 0:00:34  lr: 0.000274  min_lr: 0.000274  loss: 1.9304 (1.8991)  weight_decay: 0.0500 (0.0500)  time: 1.0069  data: 0.0010  max mem: 78493
Epoch: [252]  [290/312]  eta: 0:00:23  lr: 0.000273  min_lr: 0.000273  loss: 2.0020 (1.8992)  weight_decay: 0.0500 (0.0500)  time: 1.0053  data: 0.0009  max mem: 78493
Epoch: [252]  [300/312]  eta: 0:00:12  lr: 0.000273  min_lr: 0.000273  loss: 2.0345 (1.9049)  weight_decay: 0.0500 (0.0500)  time: 1.0020  data: 0.0001  max mem: 78493
Epoch: [252]  [310/312]  eta: 0:00:02  lr: 0.000273  min_lr: 0.000273  loss: 1.9213 (1.9009)  weight_decay: 0.0500 (0.0500)  time: 1.0015  data: 0.0001  max mem: 78493
Epoch: [252]  [311/312]  eta: 0:00:01  lr: 0.000273  min_lr: 0.000273  loss: 1.8926 (1.9007)  weight_decay: 0.0500 (0.0500)  time: 1.0014  data: 0.0001  max mem: 78493
Epoch: [252] Total time: 0:05:33 (1.0687 s / it)
Averaged stats: lr: 0.000273  min_lr: 0.000273  loss: 1.8926 (1.9086)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:13  loss: 0.5015 (0.5015)  acc1: 87.3698 (87.3698)  acc5: 97.9167 (97.9167)  time: 8.2155  data: 7.9439  max mem: 78493
Test:  [8/9]  eta: 0:00:01  loss: 0.7370 (0.6871)  acc1: 81.9010 (81.6640)  acc5: 96.7448 (95.9520)  time: 1.1236  data: 0.8953  max mem: 78493
Test: Total time: 0:00:10 (1.1613 s / it)
* Acc@1 81.816 Acc@5 95.850 loss 0.681
Accuracy of the model on the 50000 test images: 81.8%
Max accuracy: 81.82%
Epoch: [253]  [  0/312]  eta: 1:27:11  lr: 0.000273  min_lr: 0.000273  loss: 2.2081 (2.2081)  weight_decay: 0.0500 (0.0500)  time: 16.7665  data: 15.7684  max mem: 78493
Epoch: [253]  [ 10/312]  eta: 0:13:39  lr: 0.000272  min_lr: 0.000272  loss: 1.7453 (1.8193)  weight_decay: 0.0500 (0.0500)  time: 2.7151  data: 1.4341  max mem: 78493
Epoch: [253]  [ 20/312]  eta: 0:09:15  lr: 0.000272  min_lr: 0.000272  loss: 1.8524 (1.9180)  weight_decay: 0.0500 (0.0500)  time: 1.1590  data: 0.0006  max mem: 78493
Epoch: [253]  [ 30/312]  eta: 0:07:35  lr: 0.000272  min_lr: 0.000272  loss: 1.9074 (1.8770)  weight_decay: 0.0500 (0.0500)  time: 1.0082  data: 0.0004  max mem: 78493
Epoch: [253]  [ 40/312]  eta: 0:06:38  lr: 0.000271  min_lr: 0.000271  loss: 1.6342 (1.8144)  weight_decay: 0.0500 (0.0500)  time: 1.0076  data: 0.0004  max mem: 78493
Epoch: [253]  [ 50/312]  eta: 0:06:00  lr: 0.000271  min_lr: 0.000271  loss: 1.7495 (1.8494)  weight_decay: 0.0500 (0.0500)  time: 1.0073  data: 0.0004  max mem: 78493
Epoch: [253]  [ 60/312]  eta: 0:05:31  lr: 0.000270  min_lr: 0.000270  loss: 1.9864 (1.8565)  weight_decay: 0.0500 (0.0500)  time: 1.0067  data: 0.0004  max mem: 78493
Epoch: [253]  [ 70/312]  eta: 0:05:07  lr: 0.000270  min_lr: 0.000270  loss: 1.9817 (1.8763)  weight_decay: 0.0500 (0.0500)  time: 1.0064  data: 0.0005  max mem: 78493
Epoch: [253]  [ 80/312]  eta: 0:04:47  lr: 0.000270  min_lr: 0.000270  loss: 1.9460 (1.8745)  weight_decay: 0.0500 (0.0500)  time: 1.0081  data: 0.0012  max mem: 78493
Epoch: [253]  [ 90/312]  eta: 0:04:29  lr: 0.000269  min_lr: 0.000269  loss: 1.9460 (1.8848)  weight_decay: 0.0500 (0.0500)  time: 1.0077  data: 0.0011  max mem: 78493
Epoch: [253]  [100/312]  eta: 0:04:13  lr: 0.000269  min_lr: 0.000269  loss: 1.9979 (1.8854)  weight_decay: 0.0500 (0.0500)  time: 1.0074  data: 0.0005  max mem: 78493
Epoch: [253]  [110/312]  eta: 0:03:57  lr: 0.000269  min_lr: 0.000269  loss: 1.9685 (1.8981)  weight_decay: 0.0500 (0.0500)  time: 1.0072  data: 0.0005  max mem: 78493
Epoch: [253]  [120/312]  eta: 0:03:43  lr: 0.000268  min_lr: 0.000268  loss: 1.8877 (1.8838)  weight_decay: 0.0500 (0.0500)  time: 1.0066  data: 0.0005  max mem: 78493
Epoch: [253]  [130/312]  eta: 0:03:29  lr: 0.000268  min_lr: 0.000268  loss: 1.8593 (1.8919)  weight_decay: 0.0500 (0.0500)  time: 1.0058  data: 0.0005  max mem: 78493
Epoch: [253]  [140/312]  eta: 0:03:16  lr: 0.000268  min_lr: 0.000268  loss: 2.0008 (1.8902)  weight_decay: 0.0500 (0.0500)  time: 1.0063  data: 0.0005  max mem: 78493
Epoch: [253]  [150/312]  eta: 0:03:03  lr: 0.000267  min_lr: 0.000267  loss: 1.9162 (1.8808)  weight_decay: 0.0500 (0.0500)  time: 1.0062  data: 0.0005  max mem: 78493
Epoch: [253]  [160/312]  eta: 0:02:50  lr: 0.000267  min_lr: 0.000267  loss: 1.7973 (1.8772)  weight_decay: 0.0500 (0.0500)  time: 1.0052  data: 0.0005  max mem: 78493
Epoch: [253]  [170/312]  eta: 0:02:38  lr: 0.000267  min_lr: 0.000267  loss: 1.7973 (1.8716)  weight_decay: 0.0500 (0.0500)  time: 1.0056  data: 0.0005  max mem: 78493
Epoch: [253]  [180/312]  eta: 0:02:26  lr: 0.000266  min_lr: 0.000266  loss: 1.7191 (1.8644)  weight_decay: 0.0500 (0.0500)  time: 1.0064  data: 0.0005  max mem: 78493
Epoch: [253]  [190/312]  eta: 0:02:14  lr: 0.000266  min_lr: 0.000266  loss: 1.9140 (1.8699)  weight_decay: 0.0500 (0.0500)  time: 1.0078  data: 0.0005  max mem: 78493
Epoch: [253]  [200/312]  eta: 0:02:03  lr: 0.000265  min_lr: 0.000265  loss: 2.0306 (1.8783)  weight_decay: 0.0500 (0.0500)  time: 1.0068  data: 0.0004  max mem: 78493
Epoch: [253]  [210/312]  eta: 0:01:51  lr: 0.000265  min_lr: 0.000265  loss: 2.0420 (1.8741)  weight_decay: 0.0500 (0.0500)  time: 1.0063  data: 0.0004  max mem: 78493
Epoch: [253]  [220/312]  eta: 0:01:40  lr: 0.000265  min_lr: 0.000265  loss: 1.7767 (1.8745)  weight_decay: 0.0500 (0.0500)  time: 1.0061  data: 0.0004  max mem: 78493
Epoch: [253]  [230/312]  eta: 0:01:29  lr: 0.000264  min_lr: 0.000264  loss: 2.0292 (1.8826)  weight_decay: 0.0500 (0.0500)  time: 1.0048  data: 0.0004  max mem: 78493
Epoch: [253]  [240/312]  eta: 0:01:18  lr: 0.000264  min_lr: 0.000264  loss: 2.0531 (1.8835)  weight_decay: 0.0500 (0.0500)  time: 1.0056  data: 0.0004  max mem: 78493
Epoch: [253]  [250/312]  eta: 0:01:07  lr: 0.000264  min_lr: 0.000264  loss: 1.8681 (1.8845)  weight_decay: 0.0500 (0.0500)  time: 1.0054  data: 0.0004  max mem: 78493
Epoch: [253]  [260/312]  eta: 0:00:56  lr: 0.000263  min_lr: 0.000263  loss: 2.0554 (1.8883)  weight_decay: 0.0500 (0.0500)  time: 1.0037  data: 0.0004  max mem: 78493
Epoch: [253]  [270/312]  eta: 0:00:45  lr: 0.000263  min_lr: 0.000263  loss: 2.0308 (1.8885)  weight_decay: 0.0500 (0.0500)  time: 1.0047  data: 0.0005  max mem: 78493
Epoch: [253]  [280/312]  eta: 0:00:34  lr: 0.000263  min_lr: 0.000263  loss: 1.9809 (1.8904)  weight_decay: 0.0500 (0.0500)  time: 1.0068  data: 0.0010  max mem: 78493
Epoch: [253]  [290/312]  eta: 0:00:23  lr: 0.000262  min_lr: 0.000262  loss: 2.0010 (1.8972)  weight_decay: 0.0500 (0.0500)  time: 1.0045  data: 0.0009  max mem: 78493
Epoch: [253]  [300/312]  eta: 0:00:12  lr: 0.000262  min_lr: 0.000262  loss: 2.0611 (1.9014)  weight_decay: 0.0500 (0.0500)  time: 1.0016  data: 0.0001  max mem: 78493
Epoch: [253]  [310/312]  eta: 0:00:02  lr: 0.000262  min_lr: 0.000262  loss: 2.1461 (1.9082)  weight_decay: 0.0500 (0.0500)  time: 1.0019  data: 0.0001  max mem: 78493
Epoch: [253]  [311/312]  eta: 0:00:01  lr: 0.000261  min_lr: 0.000261  loss: 2.1775 (1.9098)  weight_decay: 0.0500 (0.0500)  time: 1.0018  data: 0.0001  max mem: 78493
Epoch: [253] Total time: 0:05:34 (1.0717 s / it)
Averaged stats: lr: 0.000261  min_lr: 0.000261  loss: 2.1775 (1.9047)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:14  loss: 0.4911 (0.4911)  acc1: 86.9792 (86.9792)  acc5: 97.7865 (97.7865)  time: 8.3167  data: 8.0531  max mem: 78493
Test:  [8/9]  eta: 0:00:01  loss: 0.7519 (0.7008)  acc1: 81.2500 (80.9920)  acc5: 96.4844 (95.7600)  time: 1.1361  data: 0.8949  max mem: 78493
Test: Total time: 0:00:10 (1.1458 s / it)
* Acc@1 81.674 Acc@5 95.772 loss 0.689
Accuracy of the model on the 50000 test images: 81.7%
Max accuracy: 81.82%
Epoch: [254]  [  0/312]  eta: 1:21:05  lr: 0.000261  min_lr: 0.000261  loss: 2.2252 (2.2252)  weight_decay: 0.0500 (0.0500)  time: 15.5961  data: 13.3947  max mem: 78493
Epoch: [254]  [ 10/312]  eta: 0:13:14  lr: 0.000261  min_lr: 0.000261  loss: 2.1500 (1.9496)  weight_decay: 0.0500 (0.0500)  time: 2.6309  data: 1.2240  max mem: 78493
Epoch: [254]  [ 20/312]  eta: 0:09:03  lr: 0.000261  min_lr: 0.000261  loss: 1.9862 (1.8976)  weight_decay: 0.0500 (0.0500)  time: 1.1739  data: 0.0037  max mem: 78493
Epoch: [254]  [ 30/312]  eta: 0:07:27  lr: 0.000260  min_lr: 0.000260  loss: 2.0005 (1.9034)  weight_decay: 0.0500 (0.0500)  time: 1.0115  data: 0.0005  max mem: 78493
Epoch: [254]  [ 40/312]  eta: 0:06:32  lr: 0.000260  min_lr: 0.000260  loss: 1.9385 (1.8937)  weight_decay: 0.0500 (0.0500)  time: 1.0068  data: 0.0004  max mem: 78493
Epoch: [254]  [ 50/312]  eta: 0:05:56  lr: 0.000260  min_lr: 0.000260  loss: 1.7974 (1.8676)  weight_decay: 0.0500 (0.0500)  time: 1.0090  data: 0.0004  max mem: 78493
Epoch: [254]  [ 60/312]  eta: 0:05:28  lr: 0.000259  min_lr: 0.000259  loss: 1.8810 (1.8843)  weight_decay: 0.0500 (0.0500)  time: 1.0110  data: 0.0004  max mem: 78493
Epoch: [254]  [ 70/312]  eta: 0:05:05  lr: 0.000259  min_lr: 0.000259  loss: 1.9476 (1.8879)  weight_decay: 0.0500 (0.0500)  time: 1.0093  data: 0.0004  max mem: 78493
Epoch: [254]  [ 80/312]  eta: 0:04:45  lr: 0.000259  min_lr: 0.000259  loss: 1.9907 (1.9006)  weight_decay: 0.0500 (0.0500)  time: 1.0101  data: 0.0004  max mem: 78493
Epoch: [254]  [ 90/312]  eta: 0:04:27  lr: 0.000258  min_lr: 0.000258  loss: 1.9907 (1.8923)  weight_decay: 0.0500 (0.0500)  time: 1.0078  data: 0.0004  max mem: 78493
Epoch: [254]  [100/312]  eta: 0:04:11  lr: 0.000258  min_lr: 0.000258  loss: 1.9321 (1.8916)  weight_decay: 0.0500 (0.0500)  time: 1.0063  data: 0.0012  max mem: 78493
Epoch: [254]  [110/312]  eta: 0:03:56  lr: 0.000258  min_lr: 0.000258  loss: 2.0324 (1.8980)  weight_decay: 0.0500 (0.0500)  time: 1.0078  data: 0.0012  max mem: 78493
Epoch: [254]  [120/312]  eta: 0:03:41  lr: 0.000257  min_lr: 0.000257  loss: 2.0328 (1.9119)  weight_decay: 0.0500 (0.0500)  time: 1.0061  data: 0.0005  max mem: 78493
Epoch: [254]  [130/312]  eta: 0:03:28  lr: 0.000257  min_lr: 0.000257  loss: 2.1123 (1.9183)  weight_decay: 0.0500 (0.0500)  time: 1.0039  data: 0.0004  max mem: 78493
Epoch: [254]  [140/312]  eta: 0:03:15  lr: 0.000257  min_lr: 0.000257  loss: 1.8702 (1.9025)  weight_decay: 0.0500 (0.0500)  time: 1.0068  data: 0.0004  max mem: 78493
Epoch: [254]  [150/312]  eta: 0:03:02  lr: 0.000256  min_lr: 0.000256  loss: 1.7760 (1.9016)  weight_decay: 0.0500 (0.0500)  time: 1.0079  data: 0.0004  max mem: 78493
Epoch: [254]  [160/312]  eta: 0:02:50  lr: 0.000256  min_lr: 0.000256  loss: 1.8205 (1.8915)  weight_decay: 0.0500 (0.0500)  time: 1.0074  data: 0.0004  max mem: 78493
Epoch: [254]  [170/312]  eta: 0:02:37  lr: 0.000255  min_lr: 0.000255  loss: 1.8548 (1.8992)  weight_decay: 0.0500 (0.0500)  time: 1.0075  data: 0.0004  max mem: 78493
Epoch: [254]  [180/312]  eta: 0:02:26  lr: 0.000255  min_lr: 0.000255  loss: 2.0348 (1.9052)  weight_decay: 0.0500 (0.0500)  time: 1.0077  data: 0.0004  max mem: 78493
Epoch: [254]  [190/312]  eta: 0:02:14  lr: 0.000255  min_lr: 0.000255  loss: 2.0006 (1.9068)  weight_decay: 0.0500 (0.0500)  time: 1.0076  data: 0.0004  max mem: 78493
Epoch: [254]  [200/312]  eta: 0:02:02  lr: 0.000254  min_lr: 0.000254  loss: 2.0006 (1.9133)  weight_decay: 0.0500 (0.0500)  time: 1.0070  data: 0.0005  max mem: 78493
Epoch: [254]  [210/312]  eta: 0:01:51  lr: 0.000254  min_lr: 0.000254  loss: 2.0224 (1.9188)  weight_decay: 0.0500 (0.0500)  time: 1.0058  data: 0.0004  max mem: 78493
Epoch: [254]  [220/312]  eta: 0:01:40  lr: 0.000254  min_lr: 0.000254  loss: 2.0224 (1.9186)  weight_decay: 0.0500 (0.0500)  time: 1.0050  data: 0.0004  max mem: 78493
Epoch: [254]  [230/312]  eta: 0:01:28  lr: 0.000253  min_lr: 0.000253  loss: 1.9183 (1.9171)  weight_decay: 0.0500 (0.0500)  time: 1.0067  data: 0.0004  max mem: 78493
Epoch: [254]  [240/312]  eta: 0:01:17  lr: 0.000253  min_lr: 0.000253  loss: 1.9833 (1.9193)  weight_decay: 0.0500 (0.0500)  time: 1.0064  data: 0.0004  max mem: 78493
Epoch: [254]  [250/312]  eta: 0:01:06  lr: 0.000253  min_lr: 0.000253  loss: 1.9483 (1.9155)  weight_decay: 0.0500 (0.0500)  time: 1.0071  data: 0.0004  max mem: 78493
Epoch: [254]  [260/312]  eta: 0:00:55  lr: 0.000252  min_lr: 0.000252  loss: 1.9313 (1.9122)  weight_decay: 0.0500 (0.0500)  time: 1.0073  data: 0.0004  max mem: 78493
Epoch: [254]  [270/312]  eta: 0:00:45  lr: 0.000252  min_lr: 0.000252  loss: 2.0004 (1.9182)  weight_decay: 0.0500 (0.0500)  time: 1.0082  data: 0.0005  max mem: 78493
Epoch: [254]  [280/312]  eta: 0:00:34  lr: 0.000252  min_lr: 0.000252  loss: 1.9755 (1.9143)  weight_decay: 0.0500 (0.0500)  time: 1.0100  data: 0.0010  max mem: 78493
Epoch: [254]  [290/312]  eta: 0:00:23  lr: 0.000251  min_lr: 0.000251  loss: 1.8294 (1.9091)  weight_decay: 0.0500 (0.0500)  time: 1.0051  data: 0.0009  max mem: 78493
Epoch: [254]  [300/312]  eta: 0:00:12  lr: 0.000251  min_lr: 0.000251  loss: 1.7369 (1.9041)  weight_decay: 0.0500 (0.0500)  time: 1.0015  data: 0.0001  max mem: 78493
Epoch: [254]  [310/312]  eta: 0:00:02  lr: 0.000251  min_lr: 0.000251  loss: 1.7479 (1.8981)  weight_decay: 0.0500 (0.0500)  time: 1.0014  data: 0.0001  max mem: 78493
Epoch: [254]  [311/312]  eta: 0:00:01  lr: 0.000251  min_lr: 0.000251  loss: 1.7499 (1.8997)  weight_decay: 0.0500 (0.0500)  time: 1.0015  data: 0.0001  max mem: 78493
Epoch: [254] Total time: 0:05:33 (1.0700 s / it)
Averaged stats: lr: 0.000251  min_lr: 0.000251  loss: 1.7499 (1.8979)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:16  loss: 0.5007 (0.5007)  acc1: 87.6302 (87.6302)  acc5: 97.7865 (97.7865)  time: 8.4616  data: 8.1883  max mem: 78493
Test:  [8/9]  eta: 0:00:01  loss: 0.7486 (0.6926)  acc1: 82.8125 (81.3760)  acc5: 96.0938 (95.6480)  time: 1.1383  data: 0.9099  max mem: 78493
Test: Total time: 0:00:10 (1.1657 s / it)
* Acc@1 82.014 Acc@5 95.818 loss 0.681
Accuracy of the model on the 50000 test images: 82.0%
Max accuracy: 82.01%
Epoch: [255]  [  0/312]  eta: 1:19:04  lr: 0.000250  min_lr: 0.000250  loss: 2.3331 (2.3331)  weight_decay: 0.0500 (0.0500)  time: 15.2074  data: 13.4120  max mem: 78493
Epoch: [255]  [ 10/312]  eta: 0:12:51  lr: 0.000250  min_lr: 0.000250  loss: 2.0643 (2.0246)  weight_decay: 0.0500 (0.0500)  time: 2.5535  data: 1.4462  max mem: 78493
Epoch: [255]  [ 20/312]  eta: 0:08:51  lr: 0.000250  min_lr: 0.000250  loss: 1.9767 (1.9309)  weight_decay: 0.0500 (0.0500)  time: 1.1515  data: 0.1251  max mem: 78493
Epoch: [255]  [ 30/312]  eta: 0:07:19  lr: 0.000249  min_lr: 0.000249  loss: 1.9143 (1.9011)  weight_decay: 0.0500 (0.0500)  time: 1.0121  data: 0.0005  max mem: 78493
Epoch: [255]  [ 40/312]  eta: 0:06:27  lr: 0.000249  min_lr: 0.000249  loss: 1.7789 (1.8876)  weight_decay: 0.0500 (0.0500)  time: 1.0093  data: 0.0004  max mem: 78493
Epoch: [255]  [ 50/312]  eta: 0:05:51  lr: 0.000249  min_lr: 0.000249  loss: 1.8370 (1.8731)  weight_decay: 0.0500 (0.0500)  time: 1.0085  data: 0.0004  max mem: 78493
Epoch: [255]  [ 60/312]  eta: 0:05:24  lr: 0.000248  min_lr: 0.000248  loss: 1.9409 (1.8764)  weight_decay: 0.0500 (0.0500)  time: 1.0076  data: 0.0004  max mem: 78493
Epoch: [255]  [ 70/312]  eta: 0:05:02  lr: 0.000248  min_lr: 0.000248  loss: 1.9585 (1.8869)  weight_decay: 0.0500 (0.0500)  time: 1.0091  data: 0.0004  max mem: 78493
Epoch: [255]  [ 80/312]  eta: 0:04:42  lr: 0.000248  min_lr: 0.000248  loss: 1.7269 (1.8728)  weight_decay: 0.0500 (0.0500)  time: 1.0103  data: 0.0004  max mem: 78493
Epoch: [255]  [ 90/312]  eta: 0:04:25  lr: 0.000247  min_lr: 0.000247  loss: 1.7189 (1.8799)  weight_decay: 0.0500 (0.0500)  time: 1.0073  data: 0.0004  max mem: 78493
Epoch: [255]  [100/312]  eta: 0:04:09  lr: 0.000247  min_lr: 0.000247  loss: 1.9284 (1.8700)  weight_decay: 0.0500 (0.0500)  time: 1.0072  data: 0.0005  max mem: 78493
Epoch: [255]  [110/312]  eta: 0:03:54  lr: 0.000247  min_lr: 0.000247  loss: 1.8478 (1.8617)  weight_decay: 0.0500 (0.0500)  time: 1.0086  data: 0.0005  max mem: 78493
Epoch: [255]  [120/312]  eta: 0:03:40  lr: 0.000246  min_lr: 0.000246  loss: 1.8198 (1.8589)  weight_decay: 0.0500 (0.0500)  time: 1.0066  data: 0.0005  max mem: 78493
Epoch: [255]  [130/312]  eta: 0:03:27  lr: 0.000246  min_lr: 0.000246  loss: 1.8949 (1.8652)  weight_decay: 0.0500 (0.0500)  time: 1.0059  data: 0.0005  max mem: 78493
Epoch: [255]  [140/312]  eta: 0:03:14  lr: 0.000246  min_lr: 0.000246  loss: 1.8590 (1.8545)  weight_decay: 0.0500 (0.0500)  time: 1.0064  data: 0.0004  max mem: 78493
Epoch: [255]  [150/312]  eta: 0:03:01  lr: 0.000245  min_lr: 0.000245  loss: 1.6945 (1.8546)  weight_decay: 0.0500 (0.0500)  time: 1.0060  data: 0.0004  max mem: 78493
Epoch: [255]  [160/312]  eta: 0:02:49  lr: 0.000245  min_lr: 0.000245  loss: 1.8584 (1.8570)  weight_decay: 0.0500 (0.0500)  time: 1.0064  data: 0.0004  max mem: 78493
Epoch: [255]  [170/312]  eta: 0:02:37  lr: 0.000245  min_lr: 0.000245  loss: 1.7613 (1.8538)  weight_decay: 0.0500 (0.0500)  time: 1.0081  data: 0.0004  max mem: 78493
Epoch: [255]  [180/312]  eta: 0:02:25  lr: 0.000244  min_lr: 0.000244  loss: 1.8958 (1.8655)  weight_decay: 0.0500 (0.0500)  time: 1.0076  data: 0.0004  max mem: 78493
Epoch: [255]  [190/312]  eta: 0:02:13  lr: 0.000244  min_lr: 0.000244  loss: 1.9362 (1.8680)  weight_decay: 0.0500 (0.0500)  time: 1.0081  data: 0.0004  max mem: 78493
Epoch: [255]  [200/312]  eta: 0:02:02  lr: 0.000244  min_lr: 0.000244  loss: 1.9016 (1.8693)  weight_decay: 0.0500 (0.0500)  time: 1.0087  data: 0.0005  max mem: 78493
Epoch: [255]  [210/312]  eta: 0:01:51  lr: 0.000243  min_lr: 0.000243  loss: 1.6975 (1.8587)  weight_decay: 0.0500 (0.0500)  time: 1.0076  data: 0.0005  max mem: 78493
Epoch: [255]  [220/312]  eta: 0:01:39  lr: 0.000243  min_lr: 0.000243  loss: 1.8340 (1.8582)  weight_decay: 0.0500 (0.0500)  time: 1.0073  data: 0.0004  max mem: 78493
Epoch: [255]  [230/312]  eta: 0:01:28  lr: 0.000243  min_lr: 0.000243  loss: 1.9339 (1.8569)  weight_decay: 0.0500 (0.0500)  time: 1.0073  data: 0.0004  max mem: 78493
Epoch: [255]  [240/312]  eta: 0:01:17  lr: 0.000242  min_lr: 0.000242  loss: 1.9339 (1.8584)  weight_decay: 0.0500 (0.0500)  time: 1.0059  data: 0.0004  max mem: 78493
Epoch: [255]  [250/312]  eta: 0:01:06  lr: 0.000242  min_lr: 0.000242  loss: 2.0850 (1.8734)  weight_decay: 0.0500 (0.0500)  time: 1.0067  data: 0.0004  max mem: 78493
Epoch: [255]  [260/312]  eta: 0:00:55  lr: 0.000242  min_lr: 0.000242  loss: 2.1105 (1.8736)  weight_decay: 0.0500 (0.0500)  time: 1.0085  data: 0.0004  max mem: 78493
Epoch: [255]  [270/312]  eta: 0:00:44  lr: 0.000241  min_lr: 0.000241  loss: 1.8703 (1.8722)  weight_decay: 0.0500 (0.0500)  time: 1.0069  data: 0.0004  max mem: 78493
Epoch: [255]  [280/312]  eta: 0:00:34  lr: 0.000241  min_lr: 0.000241  loss: 1.8245 (1.8674)  weight_decay: 0.0500 (0.0500)  time: 1.0061  data: 0.0010  max mem: 78493
Epoch: [255]  [290/312]  eta: 0:00:23  lr: 0.000240  min_lr: 0.000240  loss: 1.8498 (1.8706)  weight_decay: 0.0500 (0.0500)  time: 1.0036  data: 0.0009  max mem: 78493
Epoch: [255]  [300/312]  eta: 0:00:12  lr: 0.000240  min_lr: 0.000240  loss: 2.0129 (1.8739)  weight_decay: 0.0500 (0.0500)  time: 1.0012  data: 0.0001  max mem: 78493
Epoch: [255]  [310/312]  eta: 0:00:02  lr: 0.000240  min_lr: 0.000240  loss: 1.9633 (1.8712)  weight_decay: 0.0500 (0.0500)  time: 1.0013  data: 0.0001  max mem: 78493
Epoch: [255]  [311/312]  eta: 0:00:01  lr: 0.000240  min_lr: 0.000240  loss: 1.9633 (1.8719)  weight_decay: 0.0500 (0.0500)  time: 1.0014  data: 0.0001  max mem: 78493
Epoch: [255] Total time: 0:05:33 (1.0674 s / it)
Averaged stats: lr: 0.000240  min_lr: 0.000240  loss: 1.9633 (1.8851)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:07  loss: 0.4887 (0.4887)  acc1: 87.3698 (87.3698)  acc5: 98.1771 (98.1771)  time: 7.5288  data: 7.2561  max mem: 78493
Test:  [8/9]  eta: 0:00:01  loss: 0.7522 (0.6899)  acc1: 81.2500 (81.6320)  acc5: 96.4844 (95.8720)  time: 1.0907  data: 0.8623  max mem: 78493
Test: Total time: 0:00:09 (1.1009 s / it)
* Acc@1 81.942 Acc@5 95.900 loss 0.681
Accuracy of the model on the 50000 test images: 81.9%
Max accuracy: 82.01%
Epoch: [256]  [  0/312]  eta: 1:26:39  lr: 0.000240  min_lr: 0.000240  loss: 1.8460 (1.8460)  weight_decay: 0.0500 (0.0500)  time: 16.6651  data: 15.1294  max mem: 78493
Epoch: [256]  [ 10/312]  eta: 0:12:40  lr: 0.000239  min_lr: 0.000239  loss: 1.8776 (1.8468)  weight_decay: 0.0500 (0.0500)  time: 2.5196  data: 1.3772  max mem: 78493
Epoch: [256]  [ 20/312]  eta: 0:08:49  lr: 0.000239  min_lr: 0.000239  loss: 1.8776 (1.8472)  weight_decay: 0.0500 (0.0500)  time: 1.0693  data: 0.0026  max mem: 78493
Epoch: [256]  [ 30/312]  eta: 0:07:17  lr: 0.000239  min_lr: 0.000239  loss: 1.8941 (1.8598)  weight_decay: 0.0500 (0.0500)  time: 1.0216  data: 0.0019  max mem: 78493
Epoch: [256]  [ 40/312]  eta: 0:06:26  lr: 0.000238  min_lr: 0.000238  loss: 1.8179 (1.8361)  weight_decay: 0.0500 (0.0500)  time: 1.0088  data: 0.0005  max mem: 78493
Epoch: [256]  [ 50/312]  eta: 0:05:50  lr: 0.000238  min_lr: 0.000238  loss: 1.8361 (1.8457)  weight_decay: 0.0500 (0.0500)  time: 1.0076  data: 0.0004  max mem: 78493
Epoch: [256]  [ 60/312]  eta: 0:05:23  lr: 0.000238  min_lr: 0.000238  loss: 1.9686 (1.8638)  weight_decay: 0.0500 (0.0500)  time: 1.0076  data: 0.0004  max mem: 78493
Epoch: [256]  [ 70/312]  eta: 0:05:01  lr: 0.000237  min_lr: 0.000237  loss: 2.0246 (1.8727)  weight_decay: 0.0500 (0.0500)  time: 1.0068  data: 0.0004  max mem: 78493
Epoch: [256]  [ 80/312]  eta: 0:04:42  lr: 0.000237  min_lr: 0.000237  loss: 2.0461 (1.8943)  weight_decay: 0.0500 (0.0500)  time: 1.0072  data: 0.0005  max mem: 78493
Epoch: [256]  [ 90/312]  eta: 0:04:24  lr: 0.000237  min_lr: 0.000237  loss: 1.9973 (1.8884)  weight_decay: 0.0500 (0.0500)  time: 1.0087  data: 0.0005  max mem: 78493
Epoch: [256]  [100/312]  eta: 0:04:09  lr: 0.000236  min_lr: 0.000236  loss: 1.9781 (1.9020)  weight_decay: 0.0500 (0.0500)  time: 1.0087  data: 0.0004  max mem: 78493
Epoch: [256]  [110/312]  eta: 0:03:54  lr: 0.000236  min_lr: 0.000236  loss: 2.0511 (1.9089)  weight_decay: 0.0500 (0.0500)  time: 1.0078  data: 0.0005  max mem: 78493
Epoch: [256]  [120/312]  eta: 0:03:40  lr: 0.000236  min_lr: 0.000236  loss: 1.9649 (1.9004)  weight_decay: 0.0500 (0.0500)  time: 1.0073  data: 0.0005  max mem: 78493
Epoch: [256]  [130/312]  eta: 0:03:26  lr: 0.000235  min_lr: 0.000235  loss: 1.9021 (1.9024)  weight_decay: 0.0500 (0.0500)  time: 1.0060  data: 0.0005  max mem: 78493
Epoch: [256]  [140/312]  eta: 0:03:13  lr: 0.000235  min_lr: 0.000235  loss: 1.9005 (1.9000)  weight_decay: 0.0500 (0.0500)  time: 1.0064  data: 0.0004  max mem: 78493
Epoch: [256]  [150/312]  eta: 0:03:01  lr: 0.000235  min_lr: 0.000235  loss: 1.9729 (1.9066)  weight_decay: 0.0500 (0.0500)  time: 1.0066  data: 0.0005  max mem: 78493
Epoch: [256]  [160/312]  eta: 0:02:49  lr: 0.000234  min_lr: 0.000234  loss: 1.9148 (1.8947)  weight_decay: 0.0500 (0.0500)  time: 1.0051  data: 0.0005  max mem: 78493
Epoch: [256]  [170/312]  eta: 0:02:37  lr: 0.000234  min_lr: 0.000234  loss: 1.6710 (1.8915)  weight_decay: 0.0500 (0.0500)  time: 1.0061  data: 0.0005  max mem: 78493
Epoch: [256]  [180/312]  eta: 0:02:25  lr: 0.000234  min_lr: 0.000234  loss: 1.9778 (1.8958)  weight_decay: 0.0500 (0.0500)  time: 1.0066  data: 0.0004  max mem: 78493
Epoch: [256]  [190/312]  eta: 0:02:13  lr: 0.000233  min_lr: 0.000233  loss: 1.8988 (1.8864)  weight_decay: 0.0500 (0.0500)  time: 1.0058  data: 0.0004  max mem: 78493
Epoch: [256]  [200/312]  eta: 0:02:02  lr: 0.000233  min_lr: 0.000233  loss: 1.9194 (1.8868)  weight_decay: 0.0500 (0.0500)  time: 1.0075  data: 0.0004  max mem: 78493
Epoch: [256]  [210/312]  eta: 0:01:50  lr: 0.000233  min_lr: 0.000233  loss: 1.9649 (1.8856)  weight_decay: 0.0500 (0.0500)  time: 1.0075  data: 0.0004  max mem: 78493
Epoch: [256]  [220/312]  eta: 0:01:39  lr: 0.000232  min_lr: 0.000232  loss: 2.0430 (1.8924)  weight_decay: 0.0500 (0.0500)  time: 1.0054  data: 0.0004  max mem: 78493
Epoch: [256]  [230/312]  eta: 0:01:28  lr: 0.000232  min_lr: 0.000232  loss: 1.8965 (1.8788)  weight_decay: 0.0500 (0.0500)  time: 1.0050  data: 0.0004  max mem: 78493
Epoch: [256]  [240/312]  eta: 0:01:17  lr: 0.000232  min_lr: 0.000232  loss: 1.6929 (1.8866)  weight_decay: 0.0500 (0.0500)  time: 1.0044  data: 0.0005  max mem: 78493
Epoch: [256]  [250/312]  eta: 0:01:06  lr: 0.000231  min_lr: 0.000231  loss: 1.9337 (1.8863)  weight_decay: 0.0500 (0.0500)  time: 1.0039  data: 0.0004  max mem: 78493
Epoch: [256]  [260/312]  eta: 0:00:55  lr: 0.000231  min_lr: 0.000231  loss: 1.9108 (1.8890)  weight_decay: 0.0500 (0.0500)  time: 1.0049  data: 0.0004  max mem: 78493
Epoch: [256]  [270/312]  eta: 0:00:44  lr: 0.000231  min_lr: 0.000231  loss: 1.9108 (1.8867)  weight_decay: 0.0500 (0.0500)  time: 1.0058  data: 0.0004  max mem: 78493
Epoch: [256]  [280/312]  eta: 0:00:34  lr: 0.000230  min_lr: 0.000230  loss: 1.8930 (1.8833)  weight_decay: 0.0500 (0.0500)  time: 1.0049  data: 0.0011  max mem: 78493
Epoch: [256]  [290/312]  eta: 0:00:23  lr: 0.000230  min_lr: 0.000230  loss: 1.9314 (1.8883)  weight_decay: 0.0500 (0.0500)  time: 1.0032  data: 0.0009  max mem: 78493
Epoch: [256]  [300/312]  eta: 0:00:12  lr: 0.000230  min_lr: 0.000230  loss: 1.9394 (1.8834)  weight_decay: 0.0500 (0.0500)  time: 1.0015  data: 0.0001  max mem: 78493
Epoch: [256]  [310/312]  eta: 0:00:02  lr: 0.000229  min_lr: 0.000229  loss: 1.5959 (1.8750)  weight_decay: 0.0500 (0.0500)  time: 1.0012  data: 0.0001  max mem: 78493
Epoch: [256]  [311/312]  eta: 0:00:01  lr: 0.000229  min_lr: 0.000229  loss: 1.5959 (1.8759)  weight_decay: 0.0500 (0.0500)  time: 1.0013  data: 0.0001  max mem: 78493
Epoch: [256] Total time: 0:05:32 (1.0661 s / it)
Averaged stats: lr: 0.000229  min_lr: 0.000229  loss: 1.5959 (1.8959)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:12  loss: 0.4836 (0.4836)  acc1: 87.7604 (87.7604)  acc5: 97.9167 (97.9167)  time: 8.0924  data: 7.8122  max mem: 78493
Test:  [8/9]  eta: 0:00:01  loss: 0.7309 (0.6850)  acc1: 82.0312 (81.8720)  acc5: 96.6146 (95.7760)  time: 1.1069  data: 0.8775  max mem: 78493
Test: Total time: 0:00:10 (1.1281 s / it)
* Acc@1 82.112 Acc@5 95.930 loss 0.676
Accuracy of the model on the 50000 test images: 82.1%
Max accuracy: 82.11%
Epoch: [257]  [  0/312]  eta: 1:21:31  lr: 0.000229  min_lr: 0.000229  loss: 2.1421 (2.1421)  weight_decay: 0.0500 (0.0500)  time: 15.6771  data: 12.9034  max mem: 78493
Epoch: [257]  [ 10/312]  eta: 0:13:07  lr: 0.000229  min_lr: 0.000229  loss: 1.6953 (1.8484)  weight_decay: 0.0500 (0.0500)  time: 2.6072  data: 1.4138  max mem: 78493
Epoch: [257]  [ 20/312]  eta: 0:08:59  lr: 0.000229  min_lr: 0.000229  loss: 1.7161 (1.8785)  weight_decay: 0.0500 (0.0500)  time: 1.1561  data: 0.1327  max mem: 78493
Epoch: [257]  [ 30/312]  eta: 0:07:24  lr: 0.000228  min_lr: 0.000228  loss: 1.9792 (1.8848)  weight_decay: 0.0500 (0.0500)  time: 1.0089  data: 0.0005  max mem: 78493
Epoch: [257]  [ 40/312]  eta: 0:06:30  lr: 0.000228  min_lr: 0.000228  loss: 1.9911 (1.8912)  weight_decay: 0.0500 (0.0500)  time: 1.0057  data: 0.0004  max mem: 78493
Epoch: [257]  [ 50/312]  eta: 0:05:54  lr: 0.000228  min_lr: 0.000228  loss: 2.0468 (1.8999)  weight_decay: 0.0500 (0.0500)  time: 1.0078  data: 0.0005  max mem: 78493
Epoch: [257]  [ 60/312]  eta: 0:05:27  lr: 0.000227  min_lr: 0.000227  loss: 2.0468 (1.8996)  weight_decay: 0.0500 (0.0500)  time: 1.0122  data: 0.0004  max mem: 78493
Epoch: [257]  [ 70/312]  eta: 0:05:04  lr: 0.000227  min_lr: 0.000227  loss: 2.0100 (1.9127)  weight_decay: 0.0500 (0.0500)  time: 1.0127  data: 0.0004  max mem: 78493
Epoch: [257]  [ 80/312]  eta: 0:04:44  lr: 0.000227  min_lr: 0.000227  loss: 1.9339 (1.9235)  weight_decay: 0.0500 (0.0500)  time: 1.0101  data: 0.0004  max mem: 78493
Epoch: [257]  [ 90/312]  eta: 0:04:26  lr: 0.000226  min_lr: 0.000226  loss: 1.8315 (1.9140)  weight_decay: 0.0500 (0.0500)  time: 1.0083  data: 0.0004  max mem: 78493
Epoch: [257]  [100/312]  eta: 0:04:10  lr: 0.000226  min_lr: 0.000226  loss: 1.8598 (1.9123)  weight_decay: 0.0500 (0.0500)  time: 1.0077  data: 0.0005  max mem: 78493
Epoch: [257]  [110/312]  eta: 0:03:55  lr: 0.000226  min_lr: 0.000226  loss: 1.8762 (1.9054)  weight_decay: 0.0500 (0.0500)  time: 1.0067  data: 0.0004  max mem: 78493
Epoch: [257]  [120/312]  eta: 0:03:41  lr: 0.000225  min_lr: 0.000225  loss: 1.9937 (1.9192)  weight_decay: 0.0500 (0.0500)  time: 1.0054  data: 0.0005  max mem: 78493
Epoch: [257]  [130/312]  eta: 0:03:27  lr: 0.000225  min_lr: 0.000225  loss: 1.9937 (1.9113)  weight_decay: 0.0500 (0.0500)  time: 1.0048  data: 0.0005  max mem: 78493
Epoch: [257]  [140/312]  eta: 0:03:14  lr: 0.000225  min_lr: 0.000225  loss: 1.9877 (1.9176)  weight_decay: 0.0500 (0.0500)  time: 1.0053  data: 0.0005  max mem: 78493
Epoch: [257]  [150/312]  eta: 0:03:02  lr: 0.000224  min_lr: 0.000224  loss: 2.0825 (1.9312)  weight_decay: 0.0500 (0.0500)  time: 1.0042  data: 0.0004  max mem: 78493
Epoch: [257]  [160/312]  eta: 0:02:49  lr: 0.000224  min_lr: 0.000224  loss: 2.0329 (1.9279)  weight_decay: 0.0500 (0.0500)  time: 1.0035  data: 0.0005  max mem: 78493
Epoch: [257]  [170/312]  eta: 0:02:37  lr: 0.000224  min_lr: 0.000224  loss: 1.9084 (1.9182)  weight_decay: 0.0500 (0.0500)  time: 1.0054  data: 0.0005  max mem: 78493
Epoch: [257]  [180/312]  eta: 0:02:25  lr: 0.000223  min_lr: 0.000223  loss: 1.7908 (1.9078)  weight_decay: 0.0500 (0.0500)  time: 1.0056  data: 0.0004  max mem: 78493
Epoch: [257]  [190/312]  eta: 0:02:14  lr: 0.000223  min_lr: 0.000223  loss: 1.6857 (1.9034)  weight_decay: 0.0500 (0.0500)  time: 1.0059  data: 0.0004  max mem: 78493
Epoch: [257]  [200/312]  eta: 0:02:02  lr: 0.000223  min_lr: 0.000223  loss: 1.7546 (1.9018)  weight_decay: 0.0500 (0.0500)  time: 1.0061  data: 0.0005  max mem: 78493
Epoch: [257]  [210/312]  eta: 0:01:51  lr: 0.000222  min_lr: 0.000222  loss: 1.9480 (1.9101)  weight_decay: 0.0500 (0.0500)  time: 1.0061  data: 0.0005  max mem: 78493
Epoch: [257]  [220/312]  eta: 0:01:39  lr: 0.000222  min_lr: 0.000222  loss: 1.9124 (1.9055)  weight_decay: 0.0500 (0.0500)  time: 1.0051  data: 0.0004  max mem: 78493
Epoch: [257]  [230/312]  eta: 0:01:28  lr: 0.000222  min_lr: 0.000222  loss: 1.9455 (1.9089)  weight_decay: 0.0500 (0.0500)  time: 1.0045  data: 0.0004  max mem: 78493
Epoch: [257]  [240/312]  eta: 0:01:17  lr: 0.000221  min_lr: 0.000221  loss: 1.9927 (1.9058)  weight_decay: 0.0500 (0.0500)  time: 1.0047  data: 0.0004  max mem: 78493
Epoch: [257]  [250/312]  eta: 0:01:06  lr: 0.000221  min_lr: 0.000221  loss: 1.8304 (1.9033)  weight_decay: 0.0500 (0.0500)  time: 1.0041  data: 0.0004  max mem: 78493
Epoch: [257]  [260/312]  eta: 0:00:55  lr: 0.000221  min_lr: 0.000221  loss: 1.8897 (1.9009)  weight_decay: 0.0500 (0.0500)  time: 1.0048  data: 0.0005  max mem: 78493
Epoch: [257]  [270/312]  eta: 0:00:45  lr: 0.000220  min_lr: 0.000220  loss: 1.8897 (1.8977)  weight_decay: 0.0500 (0.0500)  time: 1.0048  data: 0.0004  max mem: 78493
Epoch: [257]  [280/312]  eta: 0:00:34  lr: 0.000220  min_lr: 0.000220  loss: 1.8841 (1.8964)  weight_decay: 0.0500 (0.0500)  time: 1.0046  data: 0.0011  max mem: 78493
Epoch: [257]  [290/312]  eta: 0:00:23  lr: 0.000220  min_lr: 0.000220  loss: 1.8841 (1.8964)  weight_decay: 0.0500 (0.0500)  time: 1.0038  data: 0.0009  max mem: 78493
Epoch: [257]  [300/312]  eta: 0:00:12  lr: 0.000219  min_lr: 0.000219  loss: 1.7773 (1.8910)  weight_decay: 0.0500 (0.0500)  time: 1.0021  data: 0.0001  max mem: 78493
Epoch: [257]  [310/312]  eta: 0:00:02  lr: 0.000219  min_lr: 0.000219  loss: 1.8311 (1.8908)  weight_decay: 0.0500 (0.0500)  time: 1.0016  data: 0.0001  max mem: 78493
Epoch: [257]  [311/312]  eta: 0:00:01  lr: 0.000219  min_lr: 0.000219  loss: 1.9240 (1.8910)  weight_decay: 0.0500 (0.0500)  time: 1.0016  data: 0.0001  max mem: 78493
Epoch: [257] Total time: 0:05:33 (1.0680 s / it)
Averaged stats: lr: 0.000219  min_lr: 0.000219  loss: 1.9240 (1.8846)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:18  loss: 0.4984 (0.4984)  acc1: 86.8490 (86.8490)  acc5: 98.0469 (98.0469)  time: 8.7335  data: 8.4712  max mem: 78493
Test:  [8/9]  eta: 0:00:01  loss: 0.7123 (0.6847)  acc1: 82.1615 (82.0160)  acc5: 96.6146 (95.7760)  time: 1.1732  data: 0.9413  max mem: 78493
Test: Total time: 0:00:10 (1.2190 s / it)
* Acc@1 82.050 Acc@5 95.836 loss 0.679
Accuracy of the model on the 50000 test images: 82.1%
Max accuracy: 82.11%
Epoch: [258]  [  0/312]  eta: 1:26:28  lr: 0.000219  min_lr: 0.000219  loss: 2.2450 (2.2450)  weight_decay: 0.0500 (0.0500)  time: 16.6292  data: 13.5955  max mem: 78493
Epoch: [258]  [ 10/312]  eta: 0:13:09  lr: 0.000219  min_lr: 0.000219  loss: 2.0624 (1.8478)  weight_decay: 0.0500 (0.0500)  time: 2.6131  data: 1.2400  max mem: 78493
Epoch: [258]  [ 20/312]  eta: 0:09:02  lr: 0.000218  min_lr: 0.000218  loss: 2.0427 (1.9257)  weight_decay: 0.0500 (0.0500)  time: 1.1197  data: 0.0025  max mem: 78493
Epoch: [258]  [ 30/312]  eta: 0:07:26  lr: 0.000218  min_lr: 0.000218  loss: 2.0417 (1.9339)  weight_decay: 0.0500 (0.0500)  time: 1.0171  data: 0.0005  max mem: 78493
Epoch: [258]  [ 40/312]  eta: 0:06:32  lr: 0.000218  min_lr: 0.000218  loss: 1.9566 (1.9292)  weight_decay: 0.0500 (0.0500)  time: 1.0075  data: 0.0004  max mem: 78493
Epoch: [258]  [ 50/312]  eta: 0:05:55  lr: 0.000217  min_lr: 0.000217  loss: 1.8308 (1.8828)  weight_decay: 0.0500 (0.0500)  time: 1.0070  data: 0.0004  max mem: 78493
Epoch: [258]  [ 60/312]  eta: 0:05:27  lr: 0.000217  min_lr: 0.000217  loss: 1.7271 (1.8765)  weight_decay: 0.0500 (0.0500)  time: 1.0083  data: 0.0004  max mem: 78493
Epoch: [258]  [ 70/312]  eta: 0:05:04  lr: 0.000217  min_lr: 0.000217  loss: 1.9881 (1.8994)  weight_decay: 0.0500 (0.0500)  time: 1.0097  data: 0.0004  max mem: 78493
Epoch: [258]  [ 80/312]  eta: 0:04:45  lr: 0.000216  min_lr: 0.000216  loss: 2.0043 (1.8898)  weight_decay: 0.0500 (0.0500)  time: 1.0099  data: 0.0004  max mem: 78493
Epoch: [258]  [ 90/312]  eta: 0:04:27  lr: 0.000216  min_lr: 0.000216  loss: 2.0126 (1.9049)  weight_decay: 0.0500 (0.0500)  time: 1.0105  data: 0.0004  max mem: 78493
Epoch: [258]  [100/312]  eta: 0:04:11  lr: 0.000216  min_lr: 0.000216  loss: 2.0043 (1.8970)  weight_decay: 0.0500 (0.0500)  time: 1.0104  data: 0.0004  max mem: 78493
Epoch: [258]  [110/312]  eta: 0:03:56  lr: 0.000215  min_lr: 0.000215  loss: 1.9512 (1.8982)  weight_decay: 0.0500 (0.0500)  time: 1.0086  data: 0.0005  max mem: 78493
Epoch: [258]  [120/312]  eta: 0:03:41  lr: 0.000215  min_lr: 0.000215  loss: 1.9512 (1.9049)  weight_decay: 0.0500 (0.0500)  time: 1.0079  data: 0.0015  max mem: 78493
Epoch: [258]  [130/312]  eta: 0:03:28  lr: 0.000215  min_lr: 0.000215  loss: 1.9200 (1.8981)  weight_decay: 0.0500 (0.0500)  time: 1.0085  data: 0.0015  max mem: 78493
Epoch: [258]  [140/312]  eta: 0:03:15  lr: 0.000214  min_lr: 0.000214  loss: 1.9200 (1.8925)  weight_decay: 0.0500 (0.0500)  time: 1.0057  data: 0.0004  max mem: 78493
Epoch: [258]  [150/312]  eta: 0:03:02  lr: 0.000214  min_lr: 0.000214  loss: 1.9104 (1.8950)  weight_decay: 0.0500 (0.0500)  time: 1.0041  data: 0.0004  max mem: 78493
Epoch: [258]  [160/312]  eta: 0:02:50  lr: 0.000214  min_lr: 0.000214  loss: 2.1324 (1.9104)  weight_decay: 0.0500 (0.0500)  time: 1.0038  data: 0.0004  max mem: 78493
Epoch: [258]  [170/312]  eta: 0:02:37  lr: 0.000213  min_lr: 0.000213  loss: 2.1032 (1.9022)  weight_decay: 0.0500 (0.0500)  time: 1.0039  data: 0.0004  max mem: 78493
Epoch: [258]  [180/312]  eta: 0:02:25  lr: 0.000213  min_lr: 0.000213  loss: 1.7344 (1.8986)  weight_decay: 0.0500 (0.0500)  time: 1.0051  data: 0.0004  max mem: 78493
Epoch: [258]  [190/312]  eta: 0:02:14  lr: 0.000213  min_lr: 0.000213  loss: 1.8218 (1.8964)  weight_decay: 0.0500 (0.0500)  time: 1.0052  data: 0.0004  max mem: 78493
Epoch: [258]  [200/312]  eta: 0:02:02  lr: 0.000212  min_lr: 0.000212  loss: 1.8577 (1.8960)  weight_decay: 0.0500 (0.0500)  time: 1.0051  data: 0.0004  max mem: 78493
Epoch: [258]  [210/312]  eta: 0:01:51  lr: 0.000212  min_lr: 0.000212  loss: 1.7769 (1.8882)  weight_decay: 0.0500 (0.0500)  time: 1.0045  data: 0.0004  max mem: 78493
Epoch: [258]  [220/312]  eta: 0:01:40  lr: 0.000212  min_lr: 0.000212  loss: 1.7752 (1.8851)  weight_decay: 0.0500 (0.0500)  time: 1.0038  data: 0.0004  max mem: 78493
Epoch: [258]  [230/312]  eta: 0:01:28  lr: 0.000211  min_lr: 0.000211  loss: 1.8940 (1.8848)  weight_decay: 0.0500 (0.0500)  time: 1.0043  data: 0.0004  max mem: 78493
Epoch: [258]  [240/312]  eta: 0:01:17  lr: 0.000211  min_lr: 0.000211  loss: 1.9249 (1.8832)  weight_decay: 0.0500 (0.0500)  time: 1.0036  data: 0.0005  max mem: 78493
Epoch: [258]  [250/312]  eta: 0:01:06  lr: 0.000211  min_lr: 0.000211  loss: 1.9820 (1.8894)  weight_decay: 0.0500 (0.0500)  time: 1.0062  data: 0.0004  max mem: 78493
Epoch: [258]  [260/312]  eta: 0:00:55  lr: 0.000211  min_lr: 0.000211  loss: 2.0361 (1.8877)  weight_decay: 0.0500 (0.0500)  time: 1.0083  data: 0.0005  max mem: 78493
Epoch: [258]  [270/312]  eta: 0:00:45  lr: 0.000210  min_lr: 0.000210  loss: 1.7923 (1.8818)  weight_decay: 0.0500 (0.0500)  time: 1.0073  data: 0.0005  max mem: 78493
Epoch: [258]  [280/312]  eta: 0:00:34  lr: 0.000210  min_lr: 0.000210  loss: 1.7247 (1.8807)  weight_decay: 0.0500 (0.0500)  time: 1.0085  data: 0.0011  max mem: 78493
Epoch: [258]  [290/312]  eta: 0:00:23  lr: 0.000210  min_lr: 0.000210  loss: 1.9390 (1.8794)  weight_decay: 0.0500 (0.0500)  time: 1.0055  data: 0.0009  max mem: 78493
Epoch: [258]  [300/312]  eta: 0:00:12  lr: 0.000209  min_lr: 0.000209  loss: 1.9390 (1.8789)  weight_decay: 0.0500 (0.0500)  time: 1.0013  data: 0.0001  max mem: 78493
Epoch: [258]  [310/312]  eta: 0:00:02  lr: 0.000209  min_lr: 0.000209  loss: 1.9234 (1.8793)  weight_decay: 0.0500 (0.0500)  time: 1.0013  data: 0.0001  max mem: 78493
Epoch: [258]  [311/312]  eta: 0:00:01  lr: 0.000209  min_lr: 0.000209  loss: 2.0081 (1.8800)  weight_decay: 0.0500 (0.0500)  time: 1.0013  data: 0.0001  max mem: 78493
Epoch: [258] Total time: 0:05:33 (1.0692 s / it)
Averaged stats: lr: 0.000209  min_lr: 0.000209  loss: 2.0081 (1.8949)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:18  loss: 0.4824 (0.4824)  acc1: 88.0208 (88.0208)  acc5: 97.5260 (97.5260)  time: 8.7242  data: 8.4529  max mem: 78493
Test:  [8/9]  eta: 0:00:01  loss: 0.7415 (0.6793)  acc1: 82.5521 (81.6960)  acc5: 96.3542 (95.5840)  time: 1.1677  data: 0.9393  max mem: 78493
Test: Total time: 0:00:10 (1.1799 s / it)
* Acc@1 82.030 Acc@5 95.838 loss 0.673
Accuracy of the model on the 50000 test images: 82.0%
Max accuracy: 82.11%
Epoch: [259]  [  0/312]  eta: 1:27:51  lr: 0.000209  min_lr: 0.000209  loss: 2.0973 (2.0973)  weight_decay: 0.0500 (0.0500)  time: 16.8944  data: 13.5214  max mem: 78493
Epoch: [259]  [ 10/312]  eta: 0:13:07  lr: 0.000209  min_lr: 0.000209  loss: 1.8896 (1.9166)  weight_decay: 0.0500 (0.0500)  time: 2.6085  data: 1.3253  max mem: 78493
Epoch: [259]  [ 20/312]  eta: 0:08:59  lr: 0.000208  min_lr: 0.000208  loss: 1.8896 (1.9450)  weight_decay: 0.0500 (0.0500)  time: 1.0963  data: 0.0532  max mem: 78493
Epoch: [259]  [ 30/312]  eta: 0:07:24  lr: 0.000208  min_lr: 0.000208  loss: 1.8693 (1.9373)  weight_decay: 0.0500 (0.0500)  time: 1.0105  data: 0.0005  max mem: 78493
Epoch: [259]  [ 40/312]  eta: 0:06:31  lr: 0.000208  min_lr: 0.000208  loss: 1.8259 (1.9325)  weight_decay: 0.0500 (0.0500)  time: 1.0105  data: 0.0004  max mem: 78493
Epoch: [259]  [ 50/312]  eta: 0:05:55  lr: 0.000207  min_lr: 0.000207  loss: 1.9270 (1.9237)  weight_decay: 0.0500 (0.0500)  time: 1.0127  data: 0.0004  max mem: 78493
Epoch: [259]  [ 60/312]  eta: 0:05:27  lr: 0.000207  min_lr: 0.000207  loss: 2.0152 (1.9316)  weight_decay: 0.0500 (0.0500)  time: 1.0096  data: 0.0005  max mem: 78493
Epoch: [259]  [ 70/312]  eta: 0:05:04  lr: 0.000207  min_lr: 0.000207  loss: 1.9355 (1.9024)  weight_decay: 0.0500 (0.0500)  time: 1.0107  data: 0.0004  max mem: 78493
Epoch: [259]  [ 80/312]  eta: 0:04:44  lr: 0.000206  min_lr: 0.000206  loss: 1.9407 (1.9242)  weight_decay: 0.0500 (0.0500)  time: 1.0135  data: 0.0011  max mem: 78493
Epoch: [259]  [ 90/312]  eta: 0:04:27  lr: 0.000206  min_lr: 0.000206  loss: 1.9855 (1.9254)  weight_decay: 0.0500 (0.0500)  time: 1.0102  data: 0.0011  max mem: 78493
Epoch: [259]  [100/312]  eta: 0:04:11  lr: 0.000206  min_lr: 0.000206  loss: 2.0261 (1.9338)  weight_decay: 0.0500 (0.0500)  time: 1.0090  data: 0.0004  max mem: 78493
Epoch: [259]  [110/312]  eta: 0:03:56  lr: 0.000205  min_lr: 0.000205  loss: 2.0734 (1.9382)  weight_decay: 0.0500 (0.0500)  time: 1.0102  data: 0.0004  max mem: 78493
Epoch: [259]  [120/312]  eta: 0:03:41  lr: 0.000205  min_lr: 0.000205  loss: 1.9905 (1.9382)  weight_decay: 0.0500 (0.0500)  time: 1.0082  data: 0.0004  max mem: 78493
Epoch: [259]  [130/312]  eta: 0:03:28  lr: 0.000205  min_lr: 0.000205  loss: 1.9924 (1.9348)  weight_decay: 0.0500 (0.0500)  time: 1.0068  data: 0.0004  max mem: 78493
Epoch: [259]  [140/312]  eta: 0:03:15  lr: 0.000204  min_lr: 0.000204  loss: 1.9924 (1.9366)  weight_decay: 0.0500 (0.0500)  time: 1.0090  data: 0.0004  max mem: 78493
Epoch: [259]  [150/312]  eta: 0:03:02  lr: 0.000204  min_lr: 0.000204  loss: 2.0806 (1.9442)  weight_decay: 0.0500 (0.0500)  time: 1.0082  data: 0.0004  max mem: 78493
Epoch: [259]  [160/312]  eta: 0:02:50  lr: 0.000204  min_lr: 0.000204  loss: 2.0945 (1.9452)  weight_decay: 0.0500 (0.0500)  time: 1.0063  data: 0.0012  max mem: 78493
Epoch: [259]  [170/312]  eta: 0:02:37  lr: 0.000203  min_lr: 0.000203  loss: 1.9815 (1.9459)  weight_decay: 0.0500 (0.0500)  time: 1.0062  data: 0.0012  max mem: 78493
Epoch: [259]  [180/312]  eta: 0:02:26  lr: 0.000203  min_lr: 0.000203  loss: 1.9551 (1.9420)  weight_decay: 0.0500 (0.0500)  time: 1.0072  data: 0.0005  max mem: 78493
Epoch: [259]  [190/312]  eta: 0:02:14  lr: 0.000203  min_lr: 0.000203  loss: 1.9906 (1.9443)  weight_decay: 0.0500 (0.0500)  time: 1.0075  data: 0.0005  max mem: 78493
Epoch: [259]  [200/312]  eta: 0:02:02  lr: 0.000203  min_lr: 0.000203  loss: 2.0172 (1.9466)  weight_decay: 0.0500 (0.0500)  time: 1.0065  data: 0.0004  max mem: 78493
Epoch: [259]  [210/312]  eta: 0:01:51  lr: 0.000202  min_lr: 0.000202  loss: 2.0135 (1.9506)  weight_decay: 0.0500 (0.0500)  time: 1.0092  data: 0.0004  max mem: 78493
Epoch: [259]  [220/312]  eta: 0:01:40  lr: 0.000202  min_lr: 0.000202  loss: 1.8374 (1.9381)  weight_decay: 0.0500 (0.0500)  time: 1.0080  data: 0.0004  max mem: 78493
Epoch: [259]  [230/312]  eta: 0:01:28  lr: 0.000202  min_lr: 0.000202  loss: 1.8374 (1.9402)  weight_decay: 0.0500 (0.0500)  time: 1.0048  data: 0.0004  max mem: 78493
Epoch: [259]  [240/312]  eta: 0:01:17  lr: 0.000201  min_lr: 0.000201  loss: 2.0325 (1.9363)  weight_decay: 0.0500 (0.0500)  time: 1.0046  data: 0.0004  max mem: 78493
Epoch: [259]  [250/312]  eta: 0:01:06  lr: 0.000201  min_lr: 0.000201  loss: 1.7725 (1.9273)  weight_decay: 0.0500 (0.0500)  time: 1.0043  data: 0.0004  max mem: 78493
Epoch: [259]  [260/312]  eta: 0:00:55  lr: 0.000201  min_lr: 0.000201  loss: 1.8747 (1.9264)  weight_decay: 0.0500 (0.0500)  time: 1.0054  data: 0.0004  max mem: 78493
Epoch: [259]  [270/312]  eta: 0:00:45  lr: 0.000200  min_lr: 0.000200  loss: 1.9849 (1.9304)  weight_decay: 0.0500 (0.0500)  time: 1.0057  data: 0.0004  max mem: 78493
Epoch: [259]  [280/312]  eta: 0:00:34  lr: 0.000200  min_lr: 0.000200  loss: 1.9592 (1.9220)  weight_decay: 0.0500 (0.0500)  time: 1.0065  data: 0.0010  max mem: 78493
Epoch: [259]  [290/312]  eta: 0:00:23  lr: 0.000200  min_lr: 0.000200  loss: 1.8371 (1.9198)  weight_decay: 0.0500 (0.0500)  time: 1.0043  data: 0.0009  max mem: 78493
Epoch: [259]  [300/312]  eta: 0:00:12  lr: 0.000199  min_lr: 0.000199  loss: 1.8815 (1.9172)  weight_decay: 0.0500 (0.0500)  time: 1.0012  data: 0.0001  max mem: 78493
Epoch: [259]  [310/312]  eta: 0:00:02  lr: 0.000199  min_lr: 0.000199  loss: 1.8432 (1.9133)  weight_decay: 0.0500 (0.0500)  time: 1.0013  data: 0.0001  max mem: 78493
Epoch: [259]  [311/312]  eta: 0:00:01  lr: 0.000199  min_lr: 0.000199  loss: 1.8250 (1.9105)  weight_decay: 0.0500 (0.0500)  time: 1.0013  data: 0.0001  max mem: 78493
Epoch: [259] Total time: 0:05:33 (1.0697 s / it)
Averaged stats: lr: 0.000199  min_lr: 0.000199  loss: 1.8250 (1.8913)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:13  loss: 0.4897 (0.4897)  acc1: 87.1094 (87.1094)  acc5: 97.9167 (97.9167)  time: 8.1569  data: 7.8756  max mem: 78493
Test:  [8/9]  eta: 0:00:01  loss: 0.7334 (0.6810)  acc1: 82.0312 (81.5520)  acc5: 96.8750 (95.9680)  time: 1.1044  data: 0.8751  max mem: 78493
Test: Total time: 0:00:10 (1.1170 s / it)
* Acc@1 82.110 Acc@5 95.902 loss 0.677
Accuracy of the model on the 50000 test images: 82.1%
Max accuracy: 82.11%
Epoch: [260]  [  0/312]  eta: 1:27:28  lr: 0.000199  min_lr: 0.000199  loss: 2.0324 (2.0324)  weight_decay: 0.0500 (0.0500)  time: 16.8211  data: 13.2244  max mem: 78493
Epoch: [260]  [ 10/312]  eta: 0:13:01  lr: 0.000199  min_lr: 0.000199  loss: 2.0324 (1.9258)  weight_decay: 0.0500 (0.0500)  time: 2.5886  data: 1.3083  max mem: 78493
Epoch: [260]  [ 20/312]  eta: 0:08:59  lr: 0.000198  min_lr: 0.000198  loss: 1.9869 (1.9232)  weight_decay: 0.0500 (0.0500)  time: 1.0990  data: 0.0586  max mem: 78493
Epoch: [260]  [ 30/312]  eta: 0:07:24  lr: 0.000198  min_lr: 0.000198  loss: 1.9583 (1.9254)  weight_decay: 0.0500 (0.0500)  time: 1.0201  data: 0.0006  max mem: 78493
Epoch: [260]  [ 40/312]  eta: 0:06:31  lr: 0.000198  min_lr: 0.000198  loss: 1.9583 (1.9263)  weight_decay: 0.0500 (0.0500)  time: 1.0077  data: 0.0012  max mem: 78493
Epoch: [260]  [ 50/312]  eta: 0:05:54  lr: 0.000197  min_lr: 0.000197  loss: 1.8999 (1.8998)  weight_decay: 0.0500 (0.0500)  time: 1.0089  data: 0.0012  max mem: 78493
Epoch: [260]  [ 60/312]  eta: 0:05:26  lr: 0.000197  min_lr: 0.000197  loss: 1.9227 (1.9085)  weight_decay: 0.0500 (0.0500)  time: 1.0081  data: 0.0004  max mem: 78493
Epoch: [260]  [ 70/312]  eta: 0:05:04  lr: 0.000197  min_lr: 0.000197  loss: 1.9506 (1.9136)  weight_decay: 0.0500 (0.0500)  time: 1.0074  data: 0.0004  max mem: 78493
Epoch: [260]  [ 80/312]  eta: 0:04:44  lr: 0.000197  min_lr: 0.000197  loss: 1.7643 (1.8809)  weight_decay: 0.0500 (0.0500)  time: 1.0092  data: 0.0004  max mem: 78493
Epoch: [260]  [ 90/312]  eta: 0:04:26  lr: 0.000196  min_lr: 0.000196  loss: 1.7165 (1.8776)  weight_decay: 0.0500 (0.0500)  time: 1.0100  data: 0.0004  max mem: 78493
Epoch: [260]  [100/312]  eta: 0:04:10  lr: 0.000196  min_lr: 0.000196  loss: 1.8710 (1.8641)  weight_decay: 0.0500 (0.0500)  time: 1.0120  data: 0.0004  max mem: 78493
Epoch: [260]  [110/312]  eta: 0:03:55  lr: 0.000196  min_lr: 0.000196  loss: 1.7922 (1.8542)  weight_decay: 0.0500 (0.0500)  time: 1.0131  data: 0.0004  max mem: 78493
Epoch: [260]  [120/312]  eta: 0:03:41  lr: 0.000195  min_lr: 0.000195  loss: 1.8280 (1.8662)  weight_decay: 0.0500 (0.0500)  time: 1.0118  data: 0.0020  max mem: 78493
Epoch: [260]  [130/312]  eta: 0:03:28  lr: 0.000195  min_lr: 0.000195  loss: 1.8628 (1.8578)  weight_decay: 0.0500 (0.0500)  time: 1.0113  data: 0.0020  max mem: 78493
Epoch: [260]  [140/312]  eta: 0:03:15  lr: 0.000195  min_lr: 0.000195  loss: 1.9298 (1.8654)  weight_decay: 0.0500 (0.0500)  time: 1.0100  data: 0.0011  max mem: 78493
Epoch: [260]  [150/312]  eta: 0:03:02  lr: 0.000194  min_lr: 0.000194  loss: 2.0154 (1.8626)  weight_decay: 0.0500 (0.0500)  time: 1.0086  data: 0.0011  max mem: 78493
Epoch: [260]  [160/312]  eta: 0:02:50  lr: 0.000194  min_lr: 0.000194  loss: 1.7917 (1.8606)  weight_decay: 0.0500 (0.0500)  time: 1.0074  data: 0.0004  max mem: 78493
Epoch: [260]  [170/312]  eta: 0:02:37  lr: 0.000194  min_lr: 0.000194  loss: 1.7917 (1.8604)  weight_decay: 0.0500 (0.0500)  time: 1.0074  data: 0.0004  max mem: 78493
Epoch: [260]  [180/312]  eta: 0:02:26  lr: 0.000193  min_lr: 0.000193  loss: 1.9950 (1.8596)  weight_decay: 0.0500 (0.0500)  time: 1.0089  data: 0.0004  max mem: 78493
Epoch: [260]  [190/312]  eta: 0:02:14  lr: 0.000193  min_lr: 0.000193  loss: 1.9691 (1.8632)  weight_decay: 0.0500 (0.0500)  time: 1.0088  data: 0.0004  max mem: 78493
Epoch: [260]  [200/312]  eta: 0:02:02  lr: 0.000193  min_lr: 0.000193  loss: 1.7465 (1.8594)  weight_decay: 0.0500 (0.0500)  time: 1.0097  data: 0.0004  max mem: 78493
Epoch: [260]  [210/312]  eta: 0:01:51  lr: 0.000193  min_lr: 0.000193  loss: 1.6633 (1.8557)  weight_decay: 0.0500 (0.0500)  time: 1.0094  data: 0.0004  max mem: 78493
Epoch: [260]  [220/312]  eta: 0:01:40  lr: 0.000192  min_lr: 0.000192  loss: 1.8935 (1.8607)  weight_decay: 0.0500 (0.0500)  time: 1.0076  data: 0.0004  max mem: 78493
Epoch: [260]  [230/312]  eta: 0:01:28  lr: 0.000192  min_lr: 0.000192  loss: 1.8761 (1.8588)  weight_decay: 0.0500 (0.0500)  time: 1.0069  data: 0.0004  max mem: 78493
Epoch: [260]  [240/312]  eta: 0:01:17  lr: 0.000192  min_lr: 0.000192  loss: 1.9463 (1.8621)  weight_decay: 0.0500 (0.0500)  time: 1.0066  data: 0.0004  max mem: 78493
Epoch: [260]  [250/312]  eta: 0:01:06  lr: 0.000191  min_lr: 0.000191  loss: 2.0100 (1.8632)  weight_decay: 0.0500 (0.0500)  time: 1.0073  data: 0.0004  max mem: 78493
Epoch: [260]  [260/312]  eta: 0:00:55  lr: 0.000191  min_lr: 0.000191  loss: 1.9261 (1.8652)  weight_decay: 0.0500 (0.0500)  time: 1.0067  data: 0.0005  max mem: 78493
Epoch: [260]  [270/312]  eta: 0:00:45  lr: 0.000191  min_lr: 0.000191  loss: 1.8960 (1.8605)  weight_decay: 0.0500 (0.0500)  time: 1.0065  data: 0.0004  max mem: 78493
Epoch: [260]  [280/312]  eta: 0:00:34  lr: 0.000190  min_lr: 0.000190  loss: 1.8493 (1.8615)  weight_decay: 0.0500 (0.0500)  time: 1.0069  data: 0.0010  max mem: 78493
Epoch: [260]  [290/312]  eta: 0:00:23  lr: 0.000190  min_lr: 0.000190  loss: 1.8886 (1.8584)  weight_decay: 0.0500 (0.0500)  time: 1.0041  data: 0.0009  max mem: 78493
Epoch: [260]  [300/312]  eta: 0:00:12  lr: 0.000190  min_lr: 0.000190  loss: 1.7730 (1.8572)  weight_decay: 0.0500 (0.0500)  time: 1.0018  data: 0.0001  max mem: 78493
Epoch: [260]  [310/312]  eta: 0:00:02  lr: 0.000189  min_lr: 0.000189  loss: 1.8534 (1.8576)  weight_decay: 0.0500 (0.0500)  time: 1.0017  data: 0.0001  max mem: 78493
Epoch: [260]  [311/312]  eta: 0:00:01  lr: 0.000189  min_lr: 0.000189  loss: 1.8534 (1.8581)  weight_decay: 0.0500 (0.0500)  time: 1.0017  data: 0.0001  max mem: 78493
Epoch: [260] Total time: 0:05:33 (1.0702 s / it)
Averaged stats: lr: 0.000189  min_lr: 0.000189  loss: 1.8534 (1.8776)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:19  loss: 0.4977 (0.4977)  acc1: 88.1510 (88.1510)  acc5: 97.7865 (97.7865)  time: 8.8705  data: 8.5996  max mem: 78493
Test:  [8/9]  eta: 0:00:01  loss: 0.7386 (0.6863)  acc1: 82.2917 (81.5520)  acc5: 96.2240 (95.7600)  time: 1.1838  data: 0.9556  max mem: 78493
Test: Total time: 0:00:10 (1.1989 s / it)
* Acc@1 82.238 Acc@5 95.976 loss 0.675
Accuracy of the model on the 50000 test images: 82.2%
Max accuracy: 82.24%
Epoch: [261]  [  0/312]  eta: 1:22:54  lr: 0.000189  min_lr: 0.000189  loss: 2.0202 (2.0202)  weight_decay: 0.0500 (0.0500)  time: 15.9433  data: 12.3246  max mem: 78493
Epoch: [261]  [ 10/312]  eta: 0:12:58  lr: 0.000189  min_lr: 0.000189  loss: 1.8476 (1.8173)  weight_decay: 0.0500 (0.0500)  time: 2.5773  data: 1.3076  max mem: 78493
Epoch: [261]  [ 20/312]  eta: 0:08:55  lr: 0.000189  min_lr: 0.000189  loss: 1.8535 (1.9149)  weight_decay: 0.0500 (0.0500)  time: 1.1283  data: 0.1032  max mem: 78493
Epoch: [261]  [ 30/312]  eta: 0:07:22  lr: 0.000188  min_lr: 0.000188  loss: 2.0278 (1.9200)  weight_decay: 0.0500 (0.0500)  time: 1.0131  data: 0.0005  max mem: 78493
Epoch: [261]  [ 40/312]  eta: 0:06:29  lr: 0.000188  min_lr: 0.000188  loss: 2.0166 (1.9033)  weight_decay: 0.0500 (0.0500)  time: 1.0108  data: 0.0014  max mem: 78493
Epoch: [261]  [ 50/312]  eta: 0:05:53  lr: 0.000188  min_lr: 0.000188  loss: 2.0166 (1.8945)  weight_decay: 0.0500 (0.0500)  time: 1.0122  data: 0.0014  max mem: 78493
Epoch: [261]  [ 60/312]  eta: 0:05:26  lr: 0.000188  min_lr: 0.000188  loss: 1.9599 (1.8838)  weight_decay: 0.0500 (0.0500)  time: 1.0134  data: 0.0005  max mem: 78493
Epoch: [261]  [ 70/312]  eta: 0:05:03  lr: 0.000187  min_lr: 0.000187  loss: 1.7127 (1.8523)  weight_decay: 0.0500 (0.0500)  time: 1.0124  data: 0.0004  max mem: 78493
Epoch: [261]  [ 80/312]  eta: 0:04:44  lr: 0.000187  min_lr: 0.000187  loss: 1.6930 (1.8424)  weight_decay: 0.0500 (0.0500)  time: 1.0104  data: 0.0004  max mem: 78493
Epoch: [261]  [ 90/312]  eta: 0:04:26  lr: 0.000187  min_lr: 0.000187  loss: 1.8966 (1.8526)  weight_decay: 0.0500 (0.0500)  time: 1.0080  data: 0.0004  max mem: 78493
Epoch: [261]  [100/312]  eta: 0:04:10  lr: 0.000186  min_lr: 0.000186  loss: 2.0077 (1.8552)  weight_decay: 0.0500 (0.0500)  time: 1.0091  data: 0.0004  max mem: 78493
Epoch: [261]  [110/312]  eta: 0:03:55  lr: 0.000186  min_lr: 0.000186  loss: 1.8275 (1.8430)  weight_decay: 0.0500 (0.0500)  time: 1.0097  data: 0.0004  max mem: 78493
Epoch: [261]  [120/312]  eta: 0:03:41  lr: 0.000186  min_lr: 0.000186  loss: 1.7097 (1.8389)  weight_decay: 0.0500 (0.0500)  time: 1.0077  data: 0.0005  max mem: 78493
Epoch: [261]  [130/312]  eta: 0:03:27  lr: 0.000185  min_lr: 0.000185  loss: 2.0197 (1.8524)  weight_decay: 0.0500 (0.0500)  time: 1.0090  data: 0.0004  max mem: 78493
Epoch: [261]  [140/312]  eta: 0:03:14  lr: 0.000185  min_lr: 0.000185  loss: 2.0197 (1.8538)  weight_decay: 0.0500 (0.0500)  time: 1.0075  data: 0.0004  max mem: 78493
Epoch: [261]  [150/312]  eta: 0:03:02  lr: 0.000185  min_lr: 0.000185  loss: 1.8311 (1.8545)  weight_decay: 0.0500 (0.0500)  time: 1.0068  data: 0.0004  max mem: 78493
Epoch: [261]  [160/312]  eta: 0:02:49  lr: 0.000185  min_lr: 0.000185  loss: 1.8311 (1.8550)  weight_decay: 0.0500 (0.0500)  time: 1.0090  data: 0.0004  max mem: 78493
Epoch: [261]  [170/312]  eta: 0:02:37  lr: 0.000184  min_lr: 0.000184  loss: 1.8800 (1.8558)  weight_decay: 0.0500 (0.0500)  time: 1.0093  data: 0.0005  max mem: 78493
Epoch: [261]  [180/312]  eta: 0:02:25  lr: 0.000184  min_lr: 0.000184  loss: 1.9021 (1.8548)  weight_decay: 0.0500 (0.0500)  time: 1.0114  data: 0.0005  max mem: 78493
Epoch: [261]  [190/312]  eta: 0:02:14  lr: 0.000184  min_lr: 0.000184  loss: 1.9337 (1.8544)  weight_decay: 0.0500 (0.0500)  time: 1.0091  data: 0.0004  max mem: 78493
Epoch: [261]  [200/312]  eta: 0:02:02  lr: 0.000183  min_lr: 0.000183  loss: 2.0068 (1.8643)  weight_decay: 0.0500 (0.0500)  time: 1.0059  data: 0.0004  max mem: 78493
Epoch: [261]  [210/312]  eta: 0:01:51  lr: 0.000183  min_lr: 0.000183  loss: 1.9314 (1.8598)  weight_decay: 0.0500 (0.0500)  time: 1.0069  data: 0.0004  max mem: 78493
Epoch: [261]  [220/312]  eta: 0:01:40  lr: 0.000183  min_lr: 0.000183  loss: 1.8050 (1.8571)  weight_decay: 0.0500 (0.0500)  time: 1.0082  data: 0.0004  max mem: 78493
Epoch: [261]  [230/312]  eta: 0:01:28  lr: 0.000182  min_lr: 0.000182  loss: 2.0132 (1.8685)  weight_decay: 0.0500 (0.0500)  time: 1.0086  data: 0.0004  max mem: 78493
Epoch: [261]  [240/312]  eta: 0:01:17  lr: 0.000182  min_lr: 0.000182  loss: 2.0825 (1.8693)  weight_decay: 0.0500 (0.0500)  time: 1.0066  data: 0.0004  max mem: 78493
Epoch: [261]  [250/312]  eta: 0:01:06  lr: 0.000182  min_lr: 0.000182  loss: 2.0196 (1.8731)  weight_decay: 0.0500 (0.0500)  time: 1.0055  data: 0.0004  max mem: 78493
Epoch: [261]  [260/312]  eta: 0:00:55  lr: 0.000182  min_lr: 0.000182  loss: 2.0196 (1.8742)  weight_decay: 0.0500 (0.0500)  time: 1.0053  data: 0.0004  max mem: 78493
Epoch: [261]  [270/312]  eta: 0:00:45  lr: 0.000181  min_lr: 0.000181  loss: 1.9059 (1.8715)  weight_decay: 0.0500 (0.0500)  time: 1.0047  data: 0.0004  max mem: 78493
Epoch: [261]  [280/312]  eta: 0:00:34  lr: 0.000181  min_lr: 0.000181  loss: 1.9624 (1.8722)  weight_decay: 0.0500 (0.0500)  time: 1.0065  data: 0.0010  max mem: 78493
Epoch: [261]  [290/312]  eta: 0:00:23  lr: 0.000181  min_lr: 0.000181  loss: 1.9624 (1.8712)  weight_decay: 0.0500 (0.0500)  time: 1.0054  data: 0.0009  max mem: 78493
Epoch: [261]  [300/312]  eta: 0:00:12  lr: 0.000180  min_lr: 0.000180  loss: 1.8496 (1.8724)  weight_decay: 0.0500 (0.0500)  time: 1.0016  data: 0.0001  max mem: 78493
Epoch: [261]  [310/312]  eta: 0:00:02  lr: 0.000180  min_lr: 0.000180  loss: 1.9576 (1.8756)  weight_decay: 0.0500 (0.0500)  time: 1.0012  data: 0.0001  max mem: 78493
Epoch: [261]  [311/312]  eta: 0:00:01  lr: 0.000180  min_lr: 0.000180  loss: 1.9419 (1.8745)  weight_decay: 0.0500 (0.0500)  time: 1.0014  data: 0.0001  max mem: 78493
Epoch: [261] Total time: 0:05:33 (1.0693 s / it)
Averaged stats: lr: 0.000180  min_lr: 0.000180  loss: 1.9419 (1.8825)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:18  loss: 0.4932 (0.4932)  acc1: 87.1094 (87.1094)  acc5: 97.7865 (97.7865)  time: 8.7131  data: 8.4397  max mem: 78493
Test:  [8/9]  eta: 0:00:01  loss: 0.7336 (0.6782)  acc1: 81.6406 (81.8240)  acc5: 96.6146 (95.7440)  time: 1.1662  data: 0.9378  max mem: 78493
Test: Total time: 0:00:10 (1.1826 s / it)
* Acc@1 82.024 Acc@5 95.956 loss 0.670
Accuracy of the model on the 50000 test images: 82.0%
Max accuracy: 82.24%
Epoch: [262]  [  0/312]  eta: 1:24:30  lr: 0.000180  min_lr: 0.000180  loss: 1.7801 (1.7801)  weight_decay: 0.0500 (0.0500)  time: 16.2515  data: 12.1166  max mem: 78493
Epoch: [262]  [ 10/312]  eta: 0:13:25  lr: 0.000180  min_lr: 0.000180  loss: 1.8603 (1.7879)  weight_decay: 0.0500 (0.0500)  time: 2.6679  data: 1.3386  max mem: 78493
Epoch: [262]  [ 20/312]  eta: 0:09:08  lr: 0.000179  min_lr: 0.000179  loss: 1.8743 (1.8011)  weight_decay: 0.0500 (0.0500)  time: 1.1600  data: 0.1318  max mem: 78493
Epoch: [262]  [ 30/312]  eta: 0:07:30  lr: 0.000179  min_lr: 0.000179  loss: 1.8984 (1.8466)  weight_decay: 0.0500 (0.0500)  time: 1.0108  data: 0.0017  max mem: 78493
Epoch: [262]  [ 40/312]  eta: 0:06:35  lr: 0.000179  min_lr: 0.000179  loss: 1.9196 (1.8466)  weight_decay: 0.0500 (0.0500)  time: 1.0088  data: 0.0004  max mem: 78493
Epoch: [262]  [ 50/312]  eta: 0:05:58  lr: 0.000179  min_lr: 0.000179  loss: 1.9196 (1.8561)  weight_decay: 0.0500 (0.0500)  time: 1.0088  data: 0.0005  max mem: 78493
Epoch: [262]  [ 60/312]  eta: 0:05:29  lr: 0.000178  min_lr: 0.000178  loss: 2.0536 (1.8684)  weight_decay: 0.0500 (0.0500)  time: 1.0109  data: 0.0005  max mem: 78493
Epoch: [262]  [ 70/312]  eta: 0:05:06  lr: 0.000178  min_lr: 0.000178  loss: 2.0536 (1.8856)  weight_decay: 0.0500 (0.0500)  time: 1.0099  data: 0.0005  max mem: 78493
Epoch: [262]  [ 80/312]  eta: 0:04:46  lr: 0.000178  min_lr: 0.000178  loss: 2.0424 (1.8848)  weight_decay: 0.0500 (0.0500)  time: 1.0090  data: 0.0005  max mem: 78493
Epoch: [262]  [ 90/312]  eta: 0:04:28  lr: 0.000177  min_lr: 0.000177  loss: 1.9382 (1.8834)  weight_decay: 0.0500 (0.0500)  time: 1.0086  data: 0.0005  max mem: 78493
Epoch: [262]  [100/312]  eta: 0:04:12  lr: 0.000177  min_lr: 0.000177  loss: 1.8579 (1.8834)  weight_decay: 0.0500 (0.0500)  time: 1.0080  data: 0.0004  max mem: 78493
Epoch: [262]  [110/312]  eta: 0:03:57  lr: 0.000177  min_lr: 0.000177  loss: 1.9096 (1.8890)  weight_decay: 0.0500 (0.0500)  time: 1.0066  data: 0.0004  max mem: 78493
Epoch: [262]  [120/312]  eta: 0:03:42  lr: 0.000176  min_lr: 0.000176  loss: 1.9096 (1.8927)  weight_decay: 0.0500 (0.0500)  time: 1.0075  data: 0.0004  max mem: 78493
Epoch: [262]  [130/312]  eta: 0:03:28  lr: 0.000176  min_lr: 0.000176  loss: 1.9214 (1.8954)  weight_decay: 0.0500 (0.0500)  time: 1.0088  data: 0.0004  max mem: 78493
Epoch: [262]  [140/312]  eta: 0:03:15  lr: 0.000176  min_lr: 0.000176  loss: 1.8000 (1.8844)  weight_decay: 0.0500 (0.0500)  time: 1.0089  data: 0.0004  max mem: 78493
Epoch: [262]  [150/312]  eta: 0:03:03  lr: 0.000176  min_lr: 0.000176  loss: 1.7680 (1.8795)  weight_decay: 0.0500 (0.0500)  time: 1.0081  data: 0.0004  max mem: 78493
Epoch: [262]  [160/312]  eta: 0:02:50  lr: 0.000175  min_lr: 0.000175  loss: 1.9900 (1.8917)  weight_decay: 0.0500 (0.0500)  time: 1.0049  data: 0.0011  max mem: 78493
Epoch: [262]  [170/312]  eta: 0:02:38  lr: 0.000175  min_lr: 0.000175  loss: 2.0301 (1.8899)  weight_decay: 0.0500 (0.0500)  time: 1.0053  data: 0.0010  max mem: 78493
Epoch: [262]  [180/312]  eta: 0:02:26  lr: 0.000175  min_lr: 0.000175  loss: 1.7810 (1.8832)  weight_decay: 0.0500 (0.0500)  time: 1.0074  data: 0.0004  max mem: 78493
Epoch: [262]  [190/312]  eta: 0:02:14  lr: 0.000174  min_lr: 0.000174  loss: 1.9309 (1.8885)  weight_decay: 0.0500 (0.0500)  time: 1.0064  data: 0.0004  max mem: 78493
Epoch: [262]  [200/312]  eta: 0:02:03  lr: 0.000174  min_lr: 0.000174  loss: 1.9165 (1.8838)  weight_decay: 0.0500 (0.0500)  time: 1.0051  data: 0.0005  max mem: 78493
Epoch: [262]  [210/312]  eta: 0:01:51  lr: 0.000174  min_lr: 0.000174  loss: 1.9153 (1.8857)  weight_decay: 0.0500 (0.0500)  time: 1.0060  data: 0.0004  max mem: 78493
Epoch: [262]  [220/312]  eta: 0:01:40  lr: 0.000174  min_lr: 0.000174  loss: 1.9774 (1.8858)  weight_decay: 0.0500 (0.0500)  time: 1.0068  data: 0.0004  max mem: 78493
Epoch: [262]  [230/312]  eta: 0:01:29  lr: 0.000173  min_lr: 0.000173  loss: 2.0243 (1.8918)  weight_decay: 0.0500 (0.0500)  time: 1.0078  data: 0.0004  max mem: 78493
Epoch: [262]  [240/312]  eta: 0:01:18  lr: 0.000173  min_lr: 0.000173  loss: 1.9376 (1.8948)  weight_decay: 0.0500 (0.0500)  time: 1.0090  data: 0.0004  max mem: 78493
Epoch: [262]  [250/312]  eta: 0:01:07  lr: 0.000173  min_lr: 0.000173  loss: 1.9947 (1.9020)  weight_decay: 0.0500 (0.0500)  time: 1.0092  data: 0.0004  max mem: 78493
Epoch: [262]  [260/312]  eta: 0:00:56  lr: 0.000172  min_lr: 0.000172  loss: 2.0355 (1.9037)  weight_decay: 0.0500 (0.0500)  time: 1.0079  data: 0.0004  max mem: 78493
Epoch: [262]  [270/312]  eta: 0:00:45  lr: 0.000172  min_lr: 0.000172  loss: 1.9862 (1.9015)  weight_decay: 0.0500 (0.0500)  time: 1.0066  data: 0.0004  max mem: 78493
Epoch: [262]  [280/312]  eta: 0:00:34  lr: 0.000172  min_lr: 0.000172  loss: 2.0436 (1.9071)  weight_decay: 0.0500 (0.0500)  time: 1.0072  data: 0.0011  max mem: 78493
Epoch: [262]  [290/312]  eta: 0:00:23  lr: 0.000171  min_lr: 0.000171  loss: 1.9326 (1.9051)  weight_decay: 0.0500 (0.0500)  time: 1.0052  data: 0.0009  max mem: 78493
Epoch: [262]  [300/312]  eta: 0:00:12  lr: 0.000171  min_lr: 0.000171  loss: 1.9621 (1.9076)  weight_decay: 0.0500 (0.0500)  time: 1.0025  data: 0.0001  max mem: 78493
Epoch: [262]  [310/312]  eta: 0:00:02  lr: 0.000171  min_lr: 0.000171  loss: 2.0269 (1.9107)  weight_decay: 0.0500 (0.0500)  time: 1.0022  data: 0.0001  max mem: 78493
Epoch: [262]  [311/312]  eta: 0:00:01  lr: 0.000171  min_lr: 0.000171  loss: 2.0269 (1.9105)  weight_decay: 0.0500 (0.0500)  time: 1.0022  data: 0.0001  max mem: 78493
Epoch: [262] Total time: 0:05:34 (1.0718 s / it)
Averaged stats: lr: 0.000171  min_lr: 0.000171  loss: 2.0269 (1.8733)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:14  loss: 0.4864 (0.4864)  acc1: 87.3698 (87.3698)  acc5: 98.0469 (98.0469)  time: 8.2741  data: 8.0063  max mem: 78493
Test:  [8/9]  eta: 0:00:01  loss: 0.7338 (0.6785)  acc1: 81.3802 (81.7760)  acc5: 96.2240 (95.8080)  time: 1.1184  data: 0.8897  max mem: 78493
Test: Total time: 0:00:10 (1.1511 s / it)
* Acc@1 82.152 Acc@5 96.014 loss 0.666
Accuracy of the model on the 50000 test images: 82.2%
Max accuracy: 82.24%
Epoch: [263]  [  0/312]  eta: 1:24:21  lr: 0.000171  min_lr: 0.000171  loss: 1.7552 (1.7552)  weight_decay: 0.0500 (0.0500)  time: 16.2226  data: 11.5334  max mem: 78493
Epoch: [263]  [ 10/312]  eta: 0:13:24  lr: 0.000171  min_lr: 0.000171  loss: 1.9185 (1.9284)  weight_decay: 0.0500 (0.0500)  time: 2.6628  data: 1.0596  max mem: 78493
Epoch: [263]  [ 20/312]  eta: 0:09:10  lr: 0.000170  min_lr: 0.000170  loss: 1.9213 (1.9403)  weight_decay: 0.0500 (0.0500)  time: 1.1683  data: 0.0095  max mem: 78493
Epoch: [263]  [ 30/312]  eta: 0:07:32  lr: 0.000170  min_lr: 0.000170  loss: 2.0402 (2.0041)  weight_decay: 0.0500 (0.0500)  time: 1.0210  data: 0.0036  max mem: 78493
Epoch: [263]  [ 40/312]  eta: 0:06:36  lr: 0.000170  min_lr: 0.000170  loss: 2.0600 (1.9735)  weight_decay: 0.0500 (0.0500)  time: 1.0094  data: 0.0004  max mem: 78493
Epoch: [263]  [ 50/312]  eta: 0:05:58  lr: 0.000169  min_lr: 0.000169  loss: 1.8622 (1.9729)  weight_decay: 0.0500 (0.0500)  time: 1.0079  data: 0.0004  max mem: 78493
Epoch: [263]  [ 60/312]  eta: 0:05:30  lr: 0.000169  min_lr: 0.000169  loss: 1.8170 (1.9221)  weight_decay: 0.0500 (0.0500)  time: 1.0080  data: 0.0004  max mem: 78493
Epoch: [263]  [ 70/312]  eta: 0:05:06  lr: 0.000169  min_lr: 0.000169  loss: 1.9199 (1.9511)  weight_decay: 0.0500 (0.0500)  time: 1.0063  data: 0.0004  max mem: 78493
Epoch: [263]  [ 80/312]  eta: 0:04:46  lr: 0.000169  min_lr: 0.000169  loss: 2.0314 (1.9223)  weight_decay: 0.0500 (0.0500)  time: 1.0053  data: 0.0004  max mem: 78493
Epoch: [263]  [ 90/312]  eta: 0:04:28  lr: 0.000168  min_lr: 0.000168  loss: 1.8765 (1.9273)  weight_decay: 0.0500 (0.0500)  time: 1.0071  data: 0.0004  max mem: 78493
Epoch: [263]  [100/312]  eta: 0:04:12  lr: 0.000168  min_lr: 0.000168  loss: 1.7771 (1.9022)  weight_decay: 0.0500 (0.0500)  time: 1.0077  data: 0.0004  max mem: 78493
Epoch: [263]  [110/312]  eta: 0:03:57  lr: 0.000168  min_lr: 0.000168  loss: 1.7447 (1.9012)  weight_decay: 0.0500 (0.0500)  time: 1.0057  data: 0.0005  max mem: 78493
Epoch: [263]  [120/312]  eta: 0:03:42  lr: 0.000167  min_lr: 0.000167  loss: 1.9182 (1.9008)  weight_decay: 0.0500 (0.0500)  time: 1.0076  data: 0.0005  max mem: 78493
Epoch: [263]  [130/312]  eta: 0:03:28  lr: 0.000167  min_lr: 0.000167  loss: 1.8387 (1.8929)  weight_decay: 0.0500 (0.0500)  time: 1.0076  data: 0.0004  max mem: 78493
Epoch: [263]  [140/312]  eta: 0:03:15  lr: 0.000167  min_lr: 0.000167  loss: 1.8738 (1.8970)  weight_decay: 0.0500 (0.0500)  time: 1.0047  data: 0.0004  max mem: 78493
Epoch: [263]  [150/312]  eta: 0:03:02  lr: 0.000167  min_lr: 0.000167  loss: 1.9068 (1.8940)  weight_decay: 0.0500 (0.0500)  time: 1.0042  data: 0.0004  max mem: 78493
Epoch: [263]  [160/312]  eta: 0:02:50  lr: 0.000166  min_lr: 0.000166  loss: 1.8307 (1.8895)  weight_decay: 0.0500 (0.0500)  time: 1.0043  data: 0.0004  max mem: 78493
Epoch: [263]  [170/312]  eta: 0:02:38  lr: 0.000166  min_lr: 0.000166  loss: 1.8623 (1.8877)  weight_decay: 0.0500 (0.0500)  time: 1.0060  data: 0.0004  max mem: 78493
Epoch: [263]  [180/312]  eta: 0:02:26  lr: 0.000166  min_lr: 0.000166  loss: 2.0253 (1.8944)  weight_decay: 0.0500 (0.0500)  time: 1.0082  data: 0.0004  max mem: 78493
Epoch: [263]  [190/312]  eta: 0:02:14  lr: 0.000165  min_lr: 0.000165  loss: 1.9134 (1.8877)  weight_decay: 0.0500 (0.0500)  time: 1.0077  data: 0.0004  max mem: 78493
Epoch: [263]  [200/312]  eta: 0:02:03  lr: 0.000165  min_lr: 0.000165  loss: 1.8059 (1.8853)  weight_decay: 0.0500 (0.0500)  time: 1.0067  data: 0.0004  max mem: 78493
Epoch: [263]  [210/312]  eta: 0:01:51  lr: 0.000165  min_lr: 0.000165  loss: 1.9438 (1.8868)  weight_decay: 0.0500 (0.0500)  time: 1.0063  data: 0.0004  max mem: 78493
Epoch: [263]  [220/312]  eta: 0:01:40  lr: 0.000165  min_lr: 0.000165  loss: 1.9056 (1.8823)  weight_decay: 0.0500 (0.0500)  time: 1.0044  data: 0.0005  max mem: 78493
Epoch: [263]  [230/312]  eta: 0:01:29  lr: 0.000164  min_lr: 0.000164  loss: 1.8898 (1.8790)  weight_decay: 0.0500 (0.0500)  time: 1.0054  data: 0.0005  max mem: 78493
Epoch: [263]  [240/312]  eta: 0:01:17  lr: 0.000164  min_lr: 0.000164  loss: 2.0475 (1.8877)  weight_decay: 0.0500 (0.0500)  time: 1.0077  data: 0.0004  max mem: 78493
Epoch: [263]  [250/312]  eta: 0:01:06  lr: 0.000164  min_lr: 0.000164  loss: 2.0198 (1.8873)  weight_decay: 0.0500 (0.0500)  time: 1.0067  data: 0.0005  max mem: 78493
Epoch: [263]  [260/312]  eta: 0:00:56  lr: 0.000163  min_lr: 0.000163  loss: 1.8766 (1.8850)  weight_decay: 0.0500 (0.0500)  time: 1.0055  data: 0.0005  max mem: 78493
Epoch: [263]  [270/312]  eta: 0:00:45  lr: 0.000163  min_lr: 0.000163  loss: 1.8476 (1.8812)  weight_decay: 0.0500 (0.0500)  time: 1.0053  data: 0.0004  max mem: 78493
Epoch: [263]  [280/312]  eta: 0:00:34  lr: 0.000163  min_lr: 0.000163  loss: 1.7847 (1.8780)  weight_decay: 0.0500 (0.0500)  time: 1.0065  data: 0.0010  max mem: 78493
Epoch: [263]  [290/312]  eta: 0:00:23  lr: 0.000163  min_lr: 0.000163  loss: 1.7801 (1.8778)  weight_decay: 0.0500 (0.0500)  time: 1.0045  data: 0.0009  max mem: 78493
Epoch: [263]  [300/312]  eta: 0:00:12  lr: 0.000162  min_lr: 0.000162  loss: 1.9309 (1.8755)  weight_decay: 0.0500 (0.0500)  time: 1.0016  data: 0.0001  max mem: 78493
Epoch: [263]  [310/312]  eta: 0:00:02  lr: 0.000162  min_lr: 0.000162  loss: 1.9892 (1.8774)  weight_decay: 0.0500 (0.0500)  time: 1.0019  data: 0.0001  max mem: 78493
Epoch: [263]  [311/312]  eta: 0:00:01  lr: 0.000162  min_lr: 0.000162  loss: 1.9384 (1.8766)  weight_decay: 0.0500 (0.0500)  time: 1.0018  data: 0.0001  max mem: 78493
Epoch: [263] Total time: 0:05:34 (1.0710 s / it)
Averaged stats: lr: 0.000162  min_lr: 0.000162  loss: 1.9384 (1.8757)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:13  loss: 0.4890 (0.4890)  acc1: 87.1094 (87.1094)  acc5: 98.0469 (98.0469)  time: 8.1909  data: 7.9040  max mem: 78493
Test:  [8/9]  eta: 0:00:01  loss: 0.7430 (0.6828)  acc1: 82.0312 (81.5520)  acc5: 95.9635 (95.7600)  time: 1.1083  data: 0.8783  max mem: 78493
Test: Total time: 0:00:10 (1.1205 s / it)
* Acc@1 82.104 Acc@5 95.934 loss 0.672
Accuracy of the model on the 50000 test images: 82.1%
Max accuracy: 82.24%
Epoch: [264]  [  0/312]  eta: 1:24:23  lr: 0.000162  min_lr: 0.000162  loss: 1.5921 (1.5921)  weight_decay: 0.0500 (0.0500)  time: 16.2283  data: 13.1449  max mem: 78493
Epoch: [264]  [ 10/312]  eta: 0:12:30  lr: 0.000162  min_lr: 0.000162  loss: 1.8035 (1.8225)  weight_decay: 0.0500 (0.0500)  time: 2.4838  data: 1.2335  max mem: 78493
Epoch: [264]  [ 20/312]  eta: 0:08:44  lr: 0.000161  min_lr: 0.000161  loss: 1.9502 (1.8813)  weight_decay: 0.0500 (0.0500)  time: 1.0762  data: 0.0215  max mem: 78493
Epoch: [264]  [ 30/312]  eta: 0:07:15  lr: 0.000161  min_lr: 0.000161  loss: 1.8979 (1.7830)  weight_decay: 0.0500 (0.0500)  time: 1.0262  data: 0.0013  max mem: 78493
Epoch: [264]  [ 40/312]  eta: 0:06:24  lr: 0.000161  min_lr: 0.000161  loss: 1.7684 (1.8046)  weight_decay: 0.0500 (0.0500)  time: 1.0074  data: 0.0012  max mem: 78493
Epoch: [264]  [ 50/312]  eta: 0:05:49  lr: 0.000160  min_lr: 0.000160  loss: 2.0066 (1.8574)  weight_decay: 0.0500 (0.0500)  time: 1.0061  data: 0.0004  max mem: 78493
Epoch: [264]  [ 60/312]  eta: 0:05:22  lr: 0.000160  min_lr: 0.000160  loss: 2.0552 (1.8648)  weight_decay: 0.0500 (0.0500)  time: 1.0068  data: 0.0004  max mem: 78493
Epoch: [264]  [ 70/312]  eta: 0:05:00  lr: 0.000160  min_lr: 0.000160  loss: 2.0158 (1.8675)  weight_decay: 0.0500 (0.0500)  time: 1.0074  data: 0.0004  max mem: 78493
Epoch: [264]  [ 80/312]  eta: 0:04:41  lr: 0.000160  min_lr: 0.000160  loss: 1.9934 (1.8794)  weight_decay: 0.0500 (0.0500)  time: 1.0088  data: 0.0004  max mem: 78493
Epoch: [264]  [ 90/312]  eta: 0:04:24  lr: 0.000159  min_lr: 0.000159  loss: 1.9937 (1.8857)  weight_decay: 0.0500 (0.0500)  time: 1.0099  data: 0.0004  max mem: 78493
Epoch: [264]  [100/312]  eta: 0:04:08  lr: 0.000159  min_lr: 0.000159  loss: 1.9436 (1.8770)  weight_decay: 0.0500 (0.0500)  time: 1.0086  data: 0.0004  max mem: 78493
Epoch: [264]  [110/312]  eta: 0:03:53  lr: 0.000159  min_lr: 0.000159  loss: 1.9257 (1.8802)  weight_decay: 0.0500 (0.0500)  time: 1.0100  data: 0.0004  max mem: 78493
Epoch: [264]  [120/312]  eta: 0:03:39  lr: 0.000159  min_lr: 0.000159  loss: 1.7280 (1.8714)  weight_decay: 0.0500 (0.0500)  time: 1.0112  data: 0.0004  max mem: 78493
Epoch: [264]  [130/312]  eta: 0:03:26  lr: 0.000158  min_lr: 0.000158  loss: 1.7354 (1.8782)  weight_decay: 0.0500 (0.0500)  time: 1.0084  data: 0.0004  max mem: 78493
Epoch: [264]  [140/312]  eta: 0:03:13  lr: 0.000158  min_lr: 0.000158  loss: 2.0182 (1.8874)  weight_decay: 0.0500 (0.0500)  time: 1.0077  data: 0.0004  max mem: 78493
Epoch: [264]  [150/312]  eta: 0:03:01  lr: 0.000158  min_lr: 0.000158  loss: 1.9847 (1.8875)  weight_decay: 0.0500 (0.0500)  time: 1.0098  data: 0.0004  max mem: 78493
Epoch: [264]  [160/312]  eta: 0:02:48  lr: 0.000157  min_lr: 0.000157  loss: 1.8954 (1.8849)  weight_decay: 0.0500 (0.0500)  time: 1.0115  data: 0.0005  max mem: 78493
Epoch: [264]  [170/312]  eta: 0:02:36  lr: 0.000157  min_lr: 0.000157  loss: 2.0031 (1.8883)  weight_decay: 0.0500 (0.0500)  time: 1.0081  data: 0.0005  max mem: 78493
Epoch: [264]  [180/312]  eta: 0:02:25  lr: 0.000157  min_lr: 0.000157  loss: 2.0896 (1.9006)  weight_decay: 0.0500 (0.0500)  time: 1.0058  data: 0.0005  max mem: 78493
Epoch: [264]  [190/312]  eta: 0:02:13  lr: 0.000157  min_lr: 0.000157  loss: 2.0481 (1.8997)  weight_decay: 0.0500 (0.0500)  time: 1.0075  data: 0.0004  max mem: 78493
Epoch: [264]  [200/312]  eta: 0:02:02  lr: 0.000156  min_lr: 0.000156  loss: 1.8592 (1.8964)  weight_decay: 0.0500 (0.0500)  time: 1.0074  data: 0.0004  max mem: 78493
Epoch: [264]  [210/312]  eta: 0:01:50  lr: 0.000156  min_lr: 0.000156  loss: 1.9308 (1.8959)  weight_decay: 0.0500 (0.0500)  time: 1.0076  data: 0.0004  max mem: 78493
Epoch: [264]  [220/312]  eta: 0:01:39  lr: 0.000156  min_lr: 0.000156  loss: 1.9814 (1.8971)  weight_decay: 0.0500 (0.0500)  time: 1.0068  data: 0.0004  max mem: 78493
Epoch: [264]  [230/312]  eta: 0:01:28  lr: 0.000155  min_lr: 0.000155  loss: 1.9814 (1.8988)  weight_decay: 0.0500 (0.0500)  time: 1.0069  data: 0.0004  max mem: 78493
Epoch: [264]  [240/312]  eta: 0:01:17  lr: 0.000155  min_lr: 0.000155  loss: 1.9830 (1.9010)  weight_decay: 0.0500 (0.0500)  time: 1.0076  data: 0.0005  max mem: 78493
Epoch: [264]  [250/312]  eta: 0:01:06  lr: 0.000155  min_lr: 0.000155  loss: 2.0953 (1.9070)  weight_decay: 0.0500 (0.0500)  time: 1.0066  data: 0.0005  max mem: 78493
Epoch: [264]  [260/312]  eta: 0:00:55  lr: 0.000155  min_lr: 0.000155  loss: 1.9966 (1.9055)  weight_decay: 0.0500 (0.0500)  time: 1.0062  data: 0.0005  max mem: 78493
Epoch: [264]  [270/312]  eta: 0:00:44  lr: 0.000154  min_lr: 0.000154  loss: 1.9126 (1.8999)  weight_decay: 0.0500 (0.0500)  time: 1.0056  data: 0.0005  max mem: 78493
Epoch: [264]  [280/312]  eta: 0:00:34  lr: 0.000154  min_lr: 0.000154  loss: 1.9263 (1.9008)  weight_decay: 0.0500 (0.0500)  time: 1.0051  data: 0.0010  max mem: 78493
Epoch: [264]  [290/312]  eta: 0:00:23  lr: 0.000154  min_lr: 0.000154  loss: 1.9935 (1.8969)  weight_decay: 0.0500 (0.0500)  time: 1.0036  data: 0.0009  max mem: 78493
Epoch: [264]  [300/312]  eta: 0:00:12  lr: 0.000154  min_lr: 0.000154  loss: 1.7001 (1.8868)  weight_decay: 0.0500 (0.0500)  time: 1.0021  data: 0.0001  max mem: 78493
Epoch: [264]  [310/312]  eta: 0:00:02  lr: 0.000153  min_lr: 0.000153  loss: 1.9726 (1.8920)  weight_decay: 0.0500 (0.0500)  time: 1.0021  data: 0.0001  max mem: 78493
Epoch: [264]  [311/312]  eta: 0:00:01  lr: 0.000153  min_lr: 0.000153  loss: 1.9757 (1.8927)  weight_decay: 0.0500 (0.0500)  time: 1.0020  data: 0.0001  max mem: 78493
Epoch: [264] Total time: 0:05:32 (1.0659 s / it)
Averaged stats: lr: 0.000153  min_lr: 0.000153  loss: 1.9757 (1.8659)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:14  loss: 0.4795 (0.4795)  acc1: 87.8906 (87.8906)  acc5: 98.0469 (98.0469)  time: 8.3333  data: 8.0721  max mem: 78493
Test:  [8/9]  eta: 0:00:01  loss: 0.7308 (0.6759)  acc1: 82.5521 (81.9520)  acc5: 96.3542 (95.8240)  time: 1.1300  data: 0.8970  max mem: 78493
Test: Total time: 0:00:10 (1.1757 s / it)
* Acc@1 82.296 Acc@5 95.946 loss 0.667
Accuracy of the model on the 50000 test images: 82.3%
Max accuracy: 82.30%
Epoch: [265]  [  0/312]  eta: 1:24:20  lr: 0.000153  min_lr: 0.000153  loss: 2.3483 (2.3483)  weight_decay: 0.0500 (0.0500)  time: 16.2198  data: 15.2158  max mem: 78493
Epoch: [265]  [ 10/312]  eta: 0:13:02  lr: 0.000153  min_lr: 0.000153  loss: 2.0351 (1.8634)  weight_decay: 0.0500 (0.0500)  time: 2.5909  data: 1.3877  max mem: 78493
Epoch: [265]  [ 20/312]  eta: 0:08:57  lr: 0.000153  min_lr: 0.000153  loss: 2.0351 (1.9141)  weight_decay: 0.0500 (0.0500)  time: 1.1234  data: 0.0027  max mem: 78493
Epoch: [265]  [ 30/312]  eta: 0:07:23  lr: 0.000152  min_lr: 0.000152  loss: 1.9400 (1.9077)  weight_decay: 0.0500 (0.0500)  time: 1.0137  data: 0.0005  max mem: 78493
Epoch: [265]  [ 40/312]  eta: 0:06:30  lr: 0.000152  min_lr: 0.000152  loss: 1.9400 (1.9101)  weight_decay: 0.0500 (0.0500)  time: 1.0091  data: 0.0004  max mem: 78493
Epoch: [265]  [ 50/312]  eta: 0:05:54  lr: 0.000152  min_lr: 0.000152  loss: 1.9257 (1.8852)  weight_decay: 0.0500 (0.0500)  time: 1.0090  data: 0.0004  max mem: 78493
Epoch: [265]  [ 60/312]  eta: 0:05:26  lr: 0.000152  min_lr: 0.000152  loss: 1.7635 (1.8695)  weight_decay: 0.0500 (0.0500)  time: 1.0081  data: 0.0004  max mem: 78493
Epoch: [265]  [ 70/312]  eta: 0:05:03  lr: 0.000151  min_lr: 0.000151  loss: 1.7864 (1.8582)  weight_decay: 0.0500 (0.0500)  time: 1.0082  data: 0.0005  max mem: 78493
Epoch: [265]  [ 80/312]  eta: 0:04:44  lr: 0.000151  min_lr: 0.000151  loss: 1.9548 (1.8905)  weight_decay: 0.0500 (0.0500)  time: 1.0070  data: 0.0004  max mem: 78493
Epoch: [265]  [ 90/312]  eta: 0:04:26  lr: 0.000151  min_lr: 0.000151  loss: 2.0313 (1.8894)  weight_decay: 0.0500 (0.0500)  time: 1.0058  data: 0.0004  max mem: 78493
Epoch: [265]  [100/312]  eta: 0:04:10  lr: 0.000150  min_lr: 0.000150  loss: 1.9224 (1.8773)  weight_decay: 0.0500 (0.0500)  time: 1.0085  data: 0.0012  max mem: 78493
Epoch: [265]  [110/312]  eta: 0:03:55  lr: 0.000150  min_lr: 0.000150  loss: 1.9515 (1.8814)  weight_decay: 0.0500 (0.0500)  time: 1.0079  data: 0.0012  max mem: 78493
Epoch: [265]  [120/312]  eta: 0:03:41  lr: 0.000150  min_lr: 0.000150  loss: 1.9515 (1.8750)  weight_decay: 0.0500 (0.0500)  time: 1.0055  data: 0.0004  max mem: 78493
Epoch: [265]  [130/312]  eta: 0:03:27  lr: 0.000150  min_lr: 0.000150  loss: 2.0021 (1.8739)  weight_decay: 0.0500 (0.0500)  time: 1.0056  data: 0.0004  max mem: 78493
Epoch: [265]  [140/312]  eta: 0:03:14  lr: 0.000149  min_lr: 0.000149  loss: 1.9601 (1.8603)  weight_decay: 0.0500 (0.0500)  time: 1.0066  data: 0.0004  max mem: 78493
Epoch: [265]  [150/312]  eta: 0:03:02  lr: 0.000149  min_lr: 0.000149  loss: 1.9601 (1.8722)  weight_decay: 0.0500 (0.0500)  time: 1.0073  data: 0.0004  max mem: 78493
Epoch: [265]  [160/312]  eta: 0:02:49  lr: 0.000149  min_lr: 0.000149  loss: 2.0354 (1.8730)  weight_decay: 0.0500 (0.0500)  time: 1.0087  data: 0.0004  max mem: 78493
Epoch: [265]  [170/312]  eta: 0:02:37  lr: 0.000149  min_lr: 0.000149  loss: 1.9662 (1.8824)  weight_decay: 0.0500 (0.0500)  time: 1.0087  data: 0.0004  max mem: 78493
Epoch: [265]  [180/312]  eta: 0:02:25  lr: 0.000148  min_lr: 0.000148  loss: 1.9598 (1.8849)  weight_decay: 0.0500 (0.0500)  time: 1.0071  data: 0.0004  max mem: 78493
Epoch: [265]  [190/312]  eta: 0:02:14  lr: 0.000148  min_lr: 0.000148  loss: 1.9598 (1.8810)  weight_decay: 0.0500 (0.0500)  time: 1.0073  data: 0.0004  max mem: 78493
Epoch: [265]  [200/312]  eta: 0:02:02  lr: 0.000148  min_lr: 0.000148  loss: 1.9758 (1.8853)  weight_decay: 0.0500 (0.0500)  time: 1.0063  data: 0.0005  max mem: 78493
Epoch: [265]  [210/312]  eta: 0:01:51  lr: 0.000147  min_lr: 0.000147  loss: 1.9223 (1.8788)  weight_decay: 0.0500 (0.0500)  time: 1.0055  data: 0.0004  max mem: 78493
Epoch: [265]  [220/312]  eta: 0:01:39  lr: 0.000147  min_lr: 0.000147  loss: 1.8087 (1.8844)  weight_decay: 0.0500 (0.0500)  time: 1.0052  data: 0.0004  max mem: 78493
Epoch: [265]  [230/312]  eta: 0:01:28  lr: 0.000147  min_lr: 0.000147  loss: 1.9743 (1.8870)  weight_decay: 0.0500 (0.0500)  time: 1.0045  data: 0.0004  max mem: 78493
Epoch: [265]  [240/312]  eta: 0:01:17  lr: 0.000147  min_lr: 0.000147  loss: 1.7686 (1.8775)  weight_decay: 0.0500 (0.0500)  time: 1.0055  data: 0.0005  max mem: 78493
Epoch: [265]  [250/312]  eta: 0:01:06  lr: 0.000146  min_lr: 0.000146  loss: 1.9917 (1.8830)  weight_decay: 0.0500 (0.0500)  time: 1.0065  data: 0.0005  max mem: 78493
Epoch: [265]  [260/312]  eta: 0:00:55  lr: 0.000146  min_lr: 0.000146  loss: 2.0359 (1.8875)  weight_decay: 0.0500 (0.0500)  time: 1.0061  data: 0.0004  max mem: 78493
Epoch: [265]  [270/312]  eta: 0:00:45  lr: 0.000146  min_lr: 0.000146  loss: 1.9700 (1.8860)  weight_decay: 0.0500 (0.0500)  time: 1.0066  data: 0.0004  max mem: 78493
Epoch: [265]  [280/312]  eta: 0:00:34  lr: 0.000146  min_lr: 0.000146  loss: 1.9031 (1.8835)  weight_decay: 0.0500 (0.0500)  time: 1.0075  data: 0.0010  max mem: 78493
Epoch: [265]  [290/312]  eta: 0:00:23  lr: 0.000145  min_lr: 0.000145  loss: 1.9580 (1.8836)  weight_decay: 0.0500 (0.0500)  time: 1.0049  data: 0.0009  max mem: 78493
Epoch: [265]  [300/312]  eta: 0:00:12  lr: 0.000145  min_lr: 0.000145  loss: 1.8792 (1.8806)  weight_decay: 0.0500 (0.0500)  time: 1.0023  data: 0.0001  max mem: 78493
Epoch: [265]  [310/312]  eta: 0:00:02  lr: 0.000145  min_lr: 0.000145  loss: 1.8600 (1.8793)  weight_decay: 0.0500 (0.0500)  time: 1.0024  data: 0.0001  max mem: 78493
Epoch: [265]  [311/312]  eta: 0:00:01  lr: 0.000145  min_lr: 0.000145  loss: 1.7738 (1.8786)  weight_decay: 0.0500 (0.0500)  time: 1.0025  data: 0.0001  max mem: 78493
Epoch: [265] Total time: 0:05:33 (1.0684 s / it)
Averaged stats: lr: 0.000145  min_lr: 0.000145  loss: 1.7738 (1.8732)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:15  loss: 0.4810 (0.4810)  acc1: 86.9792 (86.9792)  acc5: 98.0469 (98.0469)  time: 8.3903  data: 8.1086  max mem: 78493
Test:  [8/9]  eta: 0:00:01  loss: 0.7171 (0.6757)  acc1: 82.0312 (81.9040)  acc5: 96.8750 (95.8400)  time: 1.1306  data: 0.9011  max mem: 78493
Test: Total time: 0:00:10 (1.1540 s / it)
* Acc@1 82.298 Acc@5 95.998 loss 0.667
Accuracy of the model on the 50000 test images: 82.3%
Max accuracy: 82.30%
Epoch: [266]  [  0/312]  eta: 1:21:15  lr: 0.000145  min_lr: 0.000145  loss: 1.9578 (1.9578)  weight_decay: 0.0500 (0.0500)  time: 15.6278  data: 14.6241  max mem: 78493
Epoch: [266]  [ 10/312]  eta: 0:12:16  lr: 0.000144  min_lr: 0.000144  loss: 1.9109 (1.9190)  weight_decay: 0.0500 (0.0500)  time: 2.4399  data: 1.4216  max mem: 78493
Epoch: [266]  [ 20/312]  eta: 0:08:38  lr: 0.000144  min_lr: 0.000144  loss: 1.8909 (1.8423)  weight_decay: 0.0500 (0.0500)  time: 1.0813  data: 0.0511  max mem: 78493
Epoch: [266]  [ 30/312]  eta: 0:07:10  lr: 0.000144  min_lr: 0.000144  loss: 1.8285 (1.8436)  weight_decay: 0.0500 (0.0500)  time: 1.0246  data: 0.0006  max mem: 78493
Epoch: [266]  [ 40/312]  eta: 0:06:21  lr: 0.000144  min_lr: 0.000144  loss: 1.8204 (1.8341)  weight_decay: 0.0500 (0.0500)  time: 1.0095  data: 0.0004  max mem: 78493
Epoch: [266]  [ 50/312]  eta: 0:05:46  lr: 0.000143  min_lr: 0.000143  loss: 1.8939 (1.8374)  weight_decay: 0.0500 (0.0500)  time: 1.0092  data: 0.0004  max mem: 78493
Epoch: [266]  [ 60/312]  eta: 0:05:20  lr: 0.000143  min_lr: 0.000143  loss: 1.8472 (1.8191)  weight_decay: 0.0500 (0.0500)  time: 1.0085  data: 0.0004  max mem: 78493
Epoch: [266]  [ 70/312]  eta: 0:04:58  lr: 0.000143  min_lr: 0.000143  loss: 1.7520 (1.7971)  weight_decay: 0.0500 (0.0500)  time: 1.0078  data: 0.0004  max mem: 78493
Epoch: [266]  [ 80/312]  eta: 0:04:39  lr: 0.000143  min_lr: 0.000143  loss: 1.9015 (1.8235)  weight_decay: 0.0500 (0.0500)  time: 1.0070  data: 0.0004  max mem: 78493
Epoch: [266]  [ 90/312]  eta: 0:04:23  lr: 0.000142  min_lr: 0.000142  loss: 2.0124 (1.8344)  weight_decay: 0.0500 (0.0500)  time: 1.0104  data: 0.0005  max mem: 78493
Epoch: [266]  [100/312]  eta: 0:04:07  lr: 0.000142  min_lr: 0.000142  loss: 2.0124 (1.8454)  weight_decay: 0.0500 (0.0500)  time: 1.0115  data: 0.0005  max mem: 78493
Epoch: [266]  [110/312]  eta: 0:03:53  lr: 0.000142  min_lr: 0.000142  loss: 1.9496 (1.8362)  weight_decay: 0.0500 (0.0500)  time: 1.0121  data: 0.0004  max mem: 78493
Epoch: [266]  [120/312]  eta: 0:03:39  lr: 0.000142  min_lr: 0.000142  loss: 1.8418 (1.8360)  weight_decay: 0.0500 (0.0500)  time: 1.0135  data: 0.0004  max mem: 78493
Epoch: [266]  [130/312]  eta: 0:03:26  lr: 0.000141  min_lr: 0.000141  loss: 1.9917 (1.8479)  weight_decay: 0.0500 (0.0500)  time: 1.0101  data: 0.0005  max mem: 78493
Epoch: [266]  [140/312]  eta: 0:03:13  lr: 0.000141  min_lr: 0.000141  loss: 2.0147 (1.8554)  weight_decay: 0.0500 (0.0500)  time: 1.0060  data: 0.0004  max mem: 78493
Epoch: [266]  [150/312]  eta: 0:03:00  lr: 0.000141  min_lr: 0.000141  loss: 1.9364 (1.8575)  weight_decay: 0.0500 (0.0500)  time: 1.0053  data: 0.0004  max mem: 78493
Epoch: [266]  [160/312]  eta: 0:02:48  lr: 0.000140  min_lr: 0.000140  loss: 1.8990 (1.8598)  weight_decay: 0.0500 (0.0500)  time: 1.0060  data: 0.0004  max mem: 78493
Epoch: [266]  [170/312]  eta: 0:02:36  lr: 0.000140  min_lr: 0.000140  loss: 1.9216 (1.8574)  weight_decay: 0.0500 (0.0500)  time: 1.0077  data: 0.0004  max mem: 78493
Epoch: [266]  [180/312]  eta: 0:02:24  lr: 0.000140  min_lr: 0.000140  loss: 2.0141 (1.8660)  weight_decay: 0.0500 (0.0500)  time: 1.0071  data: 0.0004  max mem: 78493
Epoch: [266]  [190/312]  eta: 0:02:13  lr: 0.000140  min_lr: 0.000140  loss: 1.8138 (1.8541)  weight_decay: 0.0500 (0.0500)  time: 1.0064  data: 0.0004  max mem: 78493
Epoch: [266]  [200/312]  eta: 0:02:01  lr: 0.000139  min_lr: 0.000139  loss: 1.7784 (1.8591)  weight_decay: 0.0500 (0.0500)  time: 1.0083  data: 0.0004  max mem: 78493
Epoch: [266]  [210/312]  eta: 0:01:50  lr: 0.000139  min_lr: 0.000139  loss: 1.9692 (1.8626)  weight_decay: 0.0500 (0.0500)  time: 1.0066  data: 0.0004  max mem: 78493
Epoch: [266]  [220/312]  eta: 0:01:39  lr: 0.000139  min_lr: 0.000139  loss: 2.0565 (1.8691)  weight_decay: 0.0500 (0.0500)  time: 1.0057  data: 0.0005  max mem: 78493
Epoch: [266]  [230/312]  eta: 0:01:28  lr: 0.000139  min_lr: 0.000139  loss: 1.9990 (1.8736)  weight_decay: 0.0500 (0.0500)  time: 1.0073  data: 0.0005  max mem: 78493
Epoch: [266]  [240/312]  eta: 0:01:17  lr: 0.000138  min_lr: 0.000138  loss: 1.9277 (1.8724)  weight_decay: 0.0500 (0.0500)  time: 1.0057  data: 0.0004  max mem: 78493
Epoch: [266]  [250/312]  eta: 0:01:06  lr: 0.000138  min_lr: 0.000138  loss: 1.9834 (1.8738)  weight_decay: 0.0500 (0.0500)  time: 1.0041  data: 0.0005  max mem: 78493
Epoch: [266]  [260/312]  eta: 0:00:55  lr: 0.000138  min_lr: 0.000138  loss: 1.7219 (1.8653)  weight_decay: 0.0500 (0.0500)  time: 1.0045  data: 0.0004  max mem: 78493
Epoch: [266]  [270/312]  eta: 0:00:44  lr: 0.000138  min_lr: 0.000138  loss: 1.8572 (1.8732)  weight_decay: 0.0500 (0.0500)  time: 1.0054  data: 0.0004  max mem: 78493
Epoch: [266]  [280/312]  eta: 0:00:34  lr: 0.000137  min_lr: 0.000137  loss: 2.0313 (1.8748)  weight_decay: 0.0500 (0.0500)  time: 1.0094  data: 0.0011  max mem: 78493
Epoch: [266]  [290/312]  eta: 0:00:23  lr: 0.000137  min_lr: 0.000137  loss: 1.9699 (1.8779)  weight_decay: 0.0500 (0.0500)  time: 1.0077  data: 0.0009  max mem: 78493
Epoch: [266]  [300/312]  eta: 0:00:12  lr: 0.000137  min_lr: 0.000137  loss: 1.9031 (1.8742)  weight_decay: 0.0500 (0.0500)  time: 1.0022  data: 0.0001  max mem: 78493
Epoch: [266]  [310/312]  eta: 0:00:02  lr: 0.000137  min_lr: 0.000137  loss: 1.8055 (1.8731)  weight_decay: 0.0500 (0.0500)  time: 1.0015  data: 0.0001  max mem: 78493
Epoch: [266]  [311/312]  eta: 0:00:01  lr: 0.000137  min_lr: 0.000137  loss: 1.8240 (1.8729)  weight_decay: 0.0500 (0.0500)  time: 1.0015  data: 0.0001  max mem: 78493
Epoch: [266] Total time: 0:05:32 (1.0645 s / it)
Averaged stats: lr: 0.000137  min_lr: 0.000137  loss: 1.8240 (1.8687)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:18  loss: 0.4922 (0.4922)  acc1: 87.5000 (87.5000)  acc5: 97.7865 (97.7865)  time: 8.7666  data: 8.4847  max mem: 78493
Test:  [8/9]  eta: 0:00:01  loss: 0.7359 (0.6826)  acc1: 82.1615 (81.6640)  acc5: 96.4844 (95.7440)  time: 1.1723  data: 0.9428  max mem: 78493
Test: Total time: 0:00:10 (1.1878 s / it)
* Acc@1 82.216 Acc@5 95.922 loss 0.672
Accuracy of the model on the 50000 test images: 82.2%
Max accuracy: 82.30%
Epoch: [267]  [  0/312]  eta: 1:26:38  lr: 0.000136  min_lr: 0.000136  loss: 2.0080 (2.0080)  weight_decay: 0.0500 (0.0500)  time: 16.6605  data: 11.3408  max mem: 78493
Epoch: [267]  [ 10/312]  eta: 0:14:08  lr: 0.000136  min_lr: 0.000136  loss: 1.9977 (1.9354)  weight_decay: 0.0500 (0.0500)  time: 2.8081  data: 1.2053  max mem: 78493
Epoch: [267]  [ 20/312]  eta: 0:09:29  lr: 0.000136  min_lr: 0.000136  loss: 1.9807 (1.9159)  weight_decay: 0.0500 (0.0500)  time: 1.2165  data: 0.0961  max mem: 78493
Epoch: [267]  [ 30/312]  eta: 0:07:44  lr: 0.000136  min_lr: 0.000136  loss: 1.8820 (1.8308)  weight_decay: 0.0500 (0.0500)  time: 1.0101  data: 0.0004  max mem: 78493
Epoch: [267]  [ 40/312]  eta: 0:06:45  lr: 0.000135  min_lr: 0.000135  loss: 1.7431 (1.8482)  weight_decay: 0.0500 (0.0500)  time: 1.0098  data: 0.0004  max mem: 78493
Epoch: [267]  [ 50/312]  eta: 0:06:06  lr: 0.000135  min_lr: 0.000135  loss: 1.7972 (1.8449)  weight_decay: 0.0500 (0.0500)  time: 1.0106  data: 0.0004  max mem: 78493
Epoch: [267]  [ 60/312]  eta: 0:05:36  lr: 0.000135  min_lr: 0.000135  loss: 1.7791 (1.8235)  weight_decay: 0.0500 (0.0500)  time: 1.0086  data: 0.0004  max mem: 78493
Epoch: [267]  [ 70/312]  eta: 0:05:11  lr: 0.000135  min_lr: 0.000135  loss: 1.8207 (1.8229)  weight_decay: 0.0500 (0.0500)  time: 1.0064  data: 0.0004  max mem: 78493
Epoch: [267]  [ 80/312]  eta: 0:04:50  lr: 0.000134  min_lr: 0.000134  loss: 1.8207 (1.8082)  weight_decay: 0.0500 (0.0500)  time: 1.0062  data: 0.0004  max mem: 78493
Epoch: [267]  [ 90/312]  eta: 0:04:32  lr: 0.000134  min_lr: 0.000134  loss: 1.9087 (1.8190)  weight_decay: 0.0500 (0.0500)  time: 1.0055  data: 0.0004  max mem: 78493
Epoch: [267]  [100/312]  eta: 0:04:15  lr: 0.000134  min_lr: 0.000134  loss: 1.9496 (1.8168)  weight_decay: 0.0500 (0.0500)  time: 1.0067  data: 0.0004  max mem: 78493
Epoch: [267]  [110/312]  eta: 0:03:59  lr: 0.000134  min_lr: 0.000134  loss: 1.9196 (1.8338)  weight_decay: 0.0500 (0.0500)  time: 1.0064  data: 0.0004  max mem: 78493
Epoch: [267]  [120/312]  eta: 0:03:44  lr: 0.000133  min_lr: 0.000133  loss: 1.9061 (1.8370)  weight_decay: 0.0500 (0.0500)  time: 1.0059  data: 0.0004  max mem: 78493
Epoch: [267]  [130/312]  eta: 0:03:30  lr: 0.000133  min_lr: 0.000133  loss: 1.8465 (1.8325)  weight_decay: 0.0500 (0.0500)  time: 1.0068  data: 0.0004  max mem: 78493
Epoch: [267]  [140/312]  eta: 0:03:17  lr: 0.000133  min_lr: 0.000133  loss: 1.6462 (1.8295)  weight_decay: 0.0500 (0.0500)  time: 1.0073  data: 0.0004  max mem: 78493
Epoch: [267]  [150/312]  eta: 0:03:04  lr: 0.000133  min_lr: 0.000133  loss: 1.8298 (1.8340)  weight_decay: 0.0500 (0.0500)  time: 1.0056  data: 0.0004  max mem: 78493
Epoch: [267]  [160/312]  eta: 0:02:51  lr: 0.000132  min_lr: 0.000132  loss: 2.0148 (1.8513)  weight_decay: 0.0500 (0.0500)  time: 1.0059  data: 0.0004  max mem: 78493
Epoch: [267]  [170/312]  eta: 0:02:39  lr: 0.000132  min_lr: 0.000132  loss: 2.0148 (1.8526)  weight_decay: 0.0500 (0.0500)  time: 1.0064  data: 0.0004  max mem: 78493
Epoch: [267]  [180/312]  eta: 0:02:27  lr: 0.000132  min_lr: 0.000132  loss: 1.9035 (1.8569)  weight_decay: 0.0500 (0.0500)  time: 1.0051  data: 0.0004  max mem: 78493
Epoch: [267]  [190/312]  eta: 0:02:15  lr: 0.000132  min_lr: 0.000132  loss: 1.8922 (1.8554)  weight_decay: 0.0500 (0.0500)  time: 1.0068  data: 0.0004  max mem: 78493
Epoch: [267]  [200/312]  eta: 0:02:03  lr: 0.000131  min_lr: 0.000131  loss: 1.9813 (1.8632)  weight_decay: 0.0500 (0.0500)  time: 1.0066  data: 0.0004  max mem: 78493
Epoch: [267]  [210/312]  eta: 0:01:52  lr: 0.000131  min_lr: 0.000131  loss: 1.9551 (1.8580)  weight_decay: 0.0500 (0.0500)  time: 1.0052  data: 0.0004  max mem: 78493
Epoch: [267]  [220/312]  eta: 0:01:40  lr: 0.000131  min_lr: 0.000131  loss: 1.6374 (1.8522)  weight_decay: 0.0500 (0.0500)  time: 1.0060  data: 0.0004  max mem: 78493
Epoch: [267]  [230/312]  eta: 0:01:29  lr: 0.000131  min_lr: 0.000131  loss: 1.9191 (1.8554)  weight_decay: 0.0500 (0.0500)  time: 1.0062  data: 0.0004  max mem: 78493
Epoch: [267]  [240/312]  eta: 0:01:18  lr: 0.000130  min_lr: 0.000130  loss: 1.9191 (1.8508)  weight_decay: 0.0500 (0.0500)  time: 1.0048  data: 0.0004  max mem: 78493
Epoch: [267]  [250/312]  eta: 0:01:07  lr: 0.000130  min_lr: 0.000130  loss: 1.8459 (1.8522)  weight_decay: 0.0500 (0.0500)  time: 1.0057  data: 0.0004  max mem: 78493
Epoch: [267]  [260/312]  eta: 0:00:56  lr: 0.000130  min_lr: 0.000130  loss: 1.9701 (1.8561)  weight_decay: 0.0500 (0.0500)  time: 1.0059  data: 0.0004  max mem: 78493
Epoch: [267]  [270/312]  eta: 0:00:45  lr: 0.000130  min_lr: 0.000130  loss: 2.0568 (1.8582)  weight_decay: 0.0500 (0.0500)  time: 1.0043  data: 0.0005  max mem: 78493
Epoch: [267]  [280/312]  eta: 0:00:34  lr: 0.000129  min_lr: 0.000129  loss: 2.0381 (1.8600)  weight_decay: 0.0500 (0.0500)  time: 1.0052  data: 0.0011  max mem: 78493
Epoch: [267]  [290/312]  eta: 0:00:23  lr: 0.000129  min_lr: 0.000129  loss: 2.0019 (1.8654)  weight_decay: 0.0500 (0.0500)  time: 1.0042  data: 0.0009  max mem: 78493
Epoch: [267]  [300/312]  eta: 0:00:12  lr: 0.000129  min_lr: 0.000129  loss: 1.9375 (1.8626)  weight_decay: 0.0500 (0.0500)  time: 1.0023  data: 0.0001  max mem: 78493
Epoch: [267]  [310/312]  eta: 0:00:02  lr: 0.000129  min_lr: 0.000129  loss: 1.9652 (1.8660)  weight_decay: 0.0500 (0.0500)  time: 1.0020  data: 0.0001  max mem: 78493
Epoch: [267]  [311/312]  eta: 0:00:01  lr: 0.000129  min_lr: 0.000129  loss: 1.9652 (1.8666)  weight_decay: 0.0500 (0.0500)  time: 1.0020  data: 0.0001  max mem: 78493
Epoch: [267] Total time: 0:05:35 (1.0754 s / it)
Averaged stats: lr: 0.000129  min_lr: 0.000129  loss: 1.9652 (1.8590)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:17  loss: 0.4874 (0.4874)  acc1: 87.2396 (87.2396)  acc5: 97.9167 (97.9167)  time: 8.6055  data: 8.3386  max mem: 78493
Test:  [8/9]  eta: 0:00:01  loss: 0.7237 (0.6766)  acc1: 82.1615 (81.6000)  acc5: 96.4844 (95.8560)  time: 1.1556  data: 0.9266  max mem: 78493
Test: Total time: 0:00:10 (1.1726 s / it)
* Acc@1 82.270 Acc@5 95.986 loss 0.666
Accuracy of the model on the 50000 test images: 82.3%
Max accuracy: 82.30%
Epoch: [268]  [  0/312]  eta: 1:20:11  lr: 0.000128  min_lr: 0.000128  loss: 1.6223 (1.6223)  weight_decay: 0.0500 (0.0500)  time: 15.4216  data: 14.4199  max mem: 78493
Epoch: [268]  [ 10/312]  eta: 0:13:00  lr: 0.000128  min_lr: 0.000128  loss: 2.0143 (1.9508)  weight_decay: 0.0500 (0.0500)  time: 2.5834  data: 1.3380  max mem: 78493
Epoch: [268]  [ 20/312]  eta: 0:08:57  lr: 0.000128  min_lr: 0.000128  loss: 1.9517 (1.8879)  weight_decay: 0.0500 (0.0500)  time: 1.1614  data: 0.0151  max mem: 78493
Epoch: [268]  [ 30/312]  eta: 0:07:23  lr: 0.000128  min_lr: 0.000128  loss: 1.7598 (1.8427)  weight_decay: 0.0500 (0.0500)  time: 1.0151  data: 0.0005  max mem: 78493
Epoch: [268]  [ 40/312]  eta: 0:06:30  lr: 0.000127  min_lr: 0.000127  loss: 1.7598 (1.8316)  weight_decay: 0.0500 (0.0500)  time: 1.0076  data: 0.0004  max mem: 78493
Epoch: [268]  [ 50/312]  eta: 0:05:53  lr: 0.000127  min_lr: 0.000127  loss: 1.9745 (1.8574)  weight_decay: 0.0500 (0.0500)  time: 1.0088  data: 0.0005  max mem: 78493
Epoch: [268]  [ 60/312]  eta: 0:05:26  lr: 0.000127  min_lr: 0.000127  loss: 1.9745 (1.8797)  weight_decay: 0.0500 (0.0500)  time: 1.0080  data: 0.0004  max mem: 78493
Epoch: [268]  [ 70/312]  eta: 0:05:03  lr: 0.000127  min_lr: 0.000127  loss: 1.9030 (1.8785)  weight_decay: 0.0500 (0.0500)  time: 1.0083  data: 0.0004  max mem: 78493
Epoch: [268]  [ 80/312]  eta: 0:04:43  lr: 0.000126  min_lr: 0.000126  loss: 1.9377 (1.8880)  weight_decay: 0.0500 (0.0500)  time: 1.0093  data: 0.0004  max mem: 78493
Epoch: [268]  [ 90/312]  eta: 0:04:26  lr: 0.000126  min_lr: 0.000126  loss: 1.9786 (1.8686)  weight_decay: 0.0500 (0.0500)  time: 1.0084  data: 0.0004  max mem: 78493
Epoch: [268]  [100/312]  eta: 0:04:10  lr: 0.000126  min_lr: 0.000126  loss: 1.8074 (1.8602)  weight_decay: 0.0500 (0.0500)  time: 1.0078  data: 0.0004  max mem: 78493
Epoch: [268]  [110/312]  eta: 0:03:55  lr: 0.000126  min_lr: 0.000126  loss: 1.8074 (1.8523)  weight_decay: 0.0500 (0.0500)  time: 1.0076  data: 0.0005  max mem: 78493
Epoch: [268]  [120/312]  eta: 0:03:41  lr: 0.000125  min_lr: 0.000125  loss: 1.7555 (1.8477)  weight_decay: 0.0500 (0.0500)  time: 1.0091  data: 0.0013  max mem: 78493
Epoch: [268]  [130/312]  eta: 0:03:27  lr: 0.000125  min_lr: 0.000125  loss: 1.9163 (1.8590)  weight_decay: 0.0500 (0.0500)  time: 1.0093  data: 0.0013  max mem: 78493
Epoch: [268]  [140/312]  eta: 0:03:14  lr: 0.000125  min_lr: 0.000125  loss: 1.9758 (1.8647)  weight_decay: 0.0500 (0.0500)  time: 1.0077  data: 0.0004  max mem: 78493
Epoch: [268]  [150/312]  eta: 0:03:02  lr: 0.000125  min_lr: 0.000125  loss: 1.9758 (1.8645)  weight_decay: 0.0500 (0.0500)  time: 1.0058  data: 0.0004  max mem: 78493
Epoch: [268]  [160/312]  eta: 0:02:49  lr: 0.000124  min_lr: 0.000124  loss: 1.9258 (1.8668)  weight_decay: 0.0500 (0.0500)  time: 1.0049  data: 0.0004  max mem: 78493
Epoch: [268]  [170/312]  eta: 0:02:37  lr: 0.000124  min_lr: 0.000124  loss: 1.9258 (1.8705)  weight_decay: 0.0500 (0.0500)  time: 1.0055  data: 0.0004  max mem: 78493
Epoch: [268]  [180/312]  eta: 0:02:25  lr: 0.000124  min_lr: 0.000124  loss: 1.9082 (1.8660)  weight_decay: 0.0500 (0.0500)  time: 1.0056  data: 0.0004  max mem: 78493
Epoch: [268]  [190/312]  eta: 0:02:14  lr: 0.000124  min_lr: 0.000124  loss: 2.0272 (1.8698)  weight_decay: 0.0500 (0.0500)  time: 1.0054  data: 0.0004  max mem: 78493
Epoch: [268]  [200/312]  eta: 0:02:02  lr: 0.000123  min_lr: 0.000123  loss: 2.0517 (1.8783)  weight_decay: 0.0500 (0.0500)  time: 1.0064  data: 0.0011  max mem: 78493
Epoch: [268]  [210/312]  eta: 0:01:51  lr: 0.000123  min_lr: 0.000123  loss: 2.0079 (1.8802)  weight_decay: 0.0500 (0.0500)  time: 1.0056  data: 0.0011  max mem: 78493
Epoch: [268]  [220/312]  eta: 0:01:39  lr: 0.000123  min_lr: 0.000123  loss: 1.7989 (1.8726)  weight_decay: 0.0500 (0.0500)  time: 1.0055  data: 0.0004  max mem: 78493
Epoch: [268]  [230/312]  eta: 0:01:28  lr: 0.000123  min_lr: 0.000123  loss: 1.7989 (1.8760)  weight_decay: 0.0500 (0.0500)  time: 1.0080  data: 0.0004  max mem: 78493
Epoch: [268]  [240/312]  eta: 0:01:17  lr: 0.000123  min_lr: 0.000123  loss: 1.9910 (1.8722)  weight_decay: 0.0500 (0.0500)  time: 1.0069  data: 0.0004  max mem: 78493
Epoch: [268]  [250/312]  eta: 0:01:06  lr: 0.000122  min_lr: 0.000122  loss: 1.9502 (1.8685)  weight_decay: 0.0500 (0.0500)  time: 1.0059  data: 0.0005  max mem: 78493
Epoch: [268]  [260/312]  eta: 0:00:55  lr: 0.000122  min_lr: 0.000122  loss: 1.9684 (1.8740)  weight_decay: 0.0500 (0.0500)  time: 1.0059  data: 0.0005  max mem: 78493
Epoch: [268]  [270/312]  eta: 0:00:45  lr: 0.000122  min_lr: 0.000122  loss: 2.0124 (1.8761)  weight_decay: 0.0500 (0.0500)  time: 1.0066  data: 0.0005  max mem: 78493
Epoch: [268]  [280/312]  eta: 0:00:34  lr: 0.000122  min_lr: 0.000122  loss: 1.9438 (1.8760)  weight_decay: 0.0500 (0.0500)  time: 1.0072  data: 0.0011  max mem: 78493
Epoch: [268]  [290/312]  eta: 0:00:23  lr: 0.000121  min_lr: 0.000121  loss: 1.7978 (1.8703)  weight_decay: 0.0500 (0.0500)  time: 1.0045  data: 0.0009  max mem: 78493
Epoch: [268]  [300/312]  eta: 0:00:12  lr: 0.000121  min_lr: 0.000121  loss: 1.7520 (1.8655)  weight_decay: 0.0500 (0.0500)  time: 1.0023  data: 0.0001  max mem: 78493
Epoch: [268]  [310/312]  eta: 0:00:02  lr: 0.000121  min_lr: 0.000121  loss: 1.7246 (1.8637)  weight_decay: 0.0500 (0.0500)  time: 1.0021  data: 0.0001  max mem: 78493
Epoch: [268]  [311/312]  eta: 0:00:01  lr: 0.000121  min_lr: 0.000121  loss: 1.7246 (1.8643)  weight_decay: 0.0500 (0.0500)  time: 1.0020  data: 0.0001  max mem: 78493
Epoch: [268] Total time: 0:05:33 (1.0682 s / it)
Averaged stats: lr: 0.000121  min_lr: 0.000121  loss: 1.7246 (1.8576)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:16  loss: 0.4866 (0.4866)  acc1: 87.2396 (87.2396)  acc5: 97.9167 (97.9167)  time: 8.5084  data: 8.2472  max mem: 78493
Test:  [8/9]  eta: 0:00:01  loss: 0.7300 (0.6770)  acc1: 82.8125 (81.9840)  acc5: 96.4844 (95.9200)  time: 1.1500  data: 0.9165  max mem: 78493
Test: Total time: 0:00:10 (1.1979 s / it)
* Acc@1 82.356 Acc@5 95.958 loss 0.665
Accuracy of the model on the 50000 test images: 82.4%
Max accuracy: 82.36%
Epoch: [269]  [  0/312]  eta: 1:19:26  lr: 0.000121  min_lr: 0.000121  loss: 1.9975 (1.9975)  weight_decay: 0.0500 (0.0500)  time: 15.2769  data: 13.9134  max mem: 78493
Epoch: [269]  [ 10/312]  eta: 0:12:12  lr: 0.000120  min_lr: 0.000120  loss: 2.0306 (1.9675)  weight_decay: 0.0500 (0.0500)  time: 2.4252  data: 1.2656  max mem: 78493
Epoch: [269]  [ 20/312]  eta: 0:08:39  lr: 0.000120  min_lr: 0.000120  loss: 1.9064 (1.8503)  weight_decay: 0.0500 (0.0500)  time: 1.1025  data: 0.0007  max mem: 78493
Epoch: [269]  [ 30/312]  eta: 0:07:11  lr: 0.000120  min_lr: 0.000120  loss: 1.7682 (1.8278)  weight_decay: 0.0500 (0.0500)  time: 1.0396  data: 0.0005  max mem: 78493
Epoch: [269]  [ 40/312]  eta: 0:06:21  lr: 0.000120  min_lr: 0.000120  loss: 1.8112 (1.8129)  weight_decay: 0.0500 (0.0500)  time: 1.0111  data: 0.0014  max mem: 78493
Epoch: [269]  [ 50/312]  eta: 0:05:47  lr: 0.000120  min_lr: 0.000120  loss: 1.8112 (1.8006)  weight_decay: 0.0500 (0.0500)  time: 1.0091  data: 0.0014  max mem: 78493
Epoch: [269]  [ 60/312]  eta: 0:05:20  lr: 0.000119  min_lr: 0.000119  loss: 1.8103 (1.8095)  weight_decay: 0.0500 (0.0500)  time: 1.0074  data: 0.0005  max mem: 78493
Epoch: [269]  [ 70/312]  eta: 0:04:59  lr: 0.000119  min_lr: 0.000119  loss: 1.8599 (1.8211)  weight_decay: 0.0500 (0.0500)  time: 1.0044  data: 0.0004  max mem: 78493
Epoch: [269]  [ 80/312]  eta: 0:04:40  lr: 0.000119  min_lr: 0.000119  loss: 1.8599 (1.8272)  weight_decay: 0.0500 (0.0500)  time: 1.0045  data: 0.0004  max mem: 78493
Epoch: [269]  [ 90/312]  eta: 0:04:23  lr: 0.000119  min_lr: 0.000119  loss: 2.0521 (1.8519)  weight_decay: 0.0500 (0.0500)  time: 1.0057  data: 0.0004  max mem: 78493
Epoch: [269]  [100/312]  eta: 0:04:07  lr: 0.000118  min_lr: 0.000118  loss: 1.9614 (1.8393)  weight_decay: 0.0500 (0.0500)  time: 1.0067  data: 0.0005  max mem: 78493
Epoch: [269]  [110/312]  eta: 0:03:52  lr: 0.000118  min_lr: 0.000118  loss: 1.9161 (1.8487)  weight_decay: 0.0500 (0.0500)  time: 1.0064  data: 0.0005  max mem: 78493
Epoch: [269]  [120/312]  eta: 0:03:39  lr: 0.000118  min_lr: 0.000118  loss: 2.0304 (1.8598)  weight_decay: 0.0500 (0.0500)  time: 1.0068  data: 0.0004  max mem: 78493
Epoch: [269]  [130/312]  eta: 0:03:25  lr: 0.000118  min_lr: 0.000118  loss: 1.8799 (1.8579)  weight_decay: 0.0500 (0.0500)  time: 1.0096  data: 0.0004  max mem: 78493
Epoch: [269]  [140/312]  eta: 0:03:13  lr: 0.000117  min_lr: 0.000117  loss: 1.8749 (1.8501)  weight_decay: 0.0500 (0.0500)  time: 1.0106  data: 0.0005  max mem: 78493
Epoch: [269]  [150/312]  eta: 0:03:00  lr: 0.000117  min_lr: 0.000117  loss: 1.8893 (1.8556)  weight_decay: 0.0500 (0.0500)  time: 1.0092  data: 0.0004  max mem: 78493
Epoch: [269]  [160/312]  eta: 0:02:48  lr: 0.000117  min_lr: 0.000117  loss: 2.0601 (1.8630)  weight_decay: 0.0500 (0.0500)  time: 1.0083  data: 0.0004  max mem: 78493
Epoch: [269]  [170/312]  eta: 0:02:36  lr: 0.000117  min_lr: 0.000117  loss: 2.0601 (1.8734)  weight_decay: 0.0500 (0.0500)  time: 1.0076  data: 0.0004  max mem: 78493
Epoch: [269]  [180/312]  eta: 0:02:24  lr: 0.000116  min_lr: 0.000116  loss: 1.8251 (1.8677)  weight_decay: 0.0500 (0.0500)  time: 1.0060  data: 0.0004  max mem: 78493
Epoch: [269]  [190/312]  eta: 0:02:13  lr: 0.000116  min_lr: 0.000116  loss: 1.7293 (1.8648)  weight_decay: 0.0500 (0.0500)  time: 1.0056  data: 0.0004  max mem: 78493
Epoch: [269]  [200/312]  eta: 0:02:01  lr: 0.000116  min_lr: 0.000116  loss: 1.9650 (1.8673)  weight_decay: 0.0500 (0.0500)  time: 1.0060  data: 0.0004  max mem: 78493
Epoch: [269]  [210/312]  eta: 0:01:50  lr: 0.000116  min_lr: 0.000116  loss: 1.9650 (1.8649)  weight_decay: 0.0500 (0.0500)  time: 1.0052  data: 0.0005  max mem: 78493
Epoch: [269]  [220/312]  eta: 0:01:39  lr: 0.000115  min_lr: 0.000115  loss: 1.8704 (1.8648)  weight_decay: 0.0500 (0.0500)  time: 1.0063  data: 0.0004  max mem: 78493
Epoch: [269]  [230/312]  eta: 0:01:28  lr: 0.000115  min_lr: 0.000115  loss: 1.8617 (1.8662)  weight_decay: 0.0500 (0.0500)  time: 1.0062  data: 0.0004  max mem: 78493
Epoch: [269]  [240/312]  eta: 0:01:17  lr: 0.000115  min_lr: 0.000115  loss: 1.8617 (1.8636)  weight_decay: 0.0500 (0.0500)  time: 1.0059  data: 0.0004  max mem: 78493
Epoch: [269]  [250/312]  eta: 0:01:06  lr: 0.000115  min_lr: 0.000115  loss: 1.9219 (1.8687)  weight_decay: 0.0500 (0.0500)  time: 1.0060  data: 0.0004  max mem: 78493
Epoch: [269]  [260/312]  eta: 0:00:55  lr: 0.000114  min_lr: 0.000114  loss: 1.9287 (1.8689)  weight_decay: 0.0500 (0.0500)  time: 1.0059  data: 0.0004  max mem: 78493
Epoch: [269]  [270/312]  eta: 0:00:44  lr: 0.000114  min_lr: 0.000114  loss: 1.7867 (1.8667)  weight_decay: 0.0500 (0.0500)  time: 1.0066  data: 0.0004  max mem: 78493
Epoch: [269]  [280/312]  eta: 0:00:34  lr: 0.000114  min_lr: 0.000114  loss: 1.8842 (1.8704)  weight_decay: 0.0500 (0.0500)  time: 1.0069  data: 0.0010  max mem: 78493
Epoch: [269]  [290/312]  eta: 0:00:23  lr: 0.000114  min_lr: 0.000114  loss: 1.8722 (1.8628)  weight_decay: 0.0500 (0.0500)  time: 1.0048  data: 0.0009  max mem: 78493
Epoch: [269]  [300/312]  eta: 0:00:12  lr: 0.000113  min_lr: 0.000113  loss: 1.8722 (1.8665)  weight_decay: 0.0500 (0.0500)  time: 1.0020  data: 0.0001  max mem: 78493
Epoch: [269]  [310/312]  eta: 0:00:02  lr: 0.000113  min_lr: 0.000113  loss: 2.0290 (1.8691)  weight_decay: 0.0500 (0.0500)  time: 1.0019  data: 0.0001  max mem: 78493
Epoch: [269]  [311/312]  eta: 0:00:01  lr: 0.000113  min_lr: 0.000113  loss: 2.0290 (1.8706)  weight_decay: 0.0500 (0.0500)  time: 1.0020  data: 0.0001  max mem: 78493
Epoch: [269] Total time: 0:05:31 (1.0640 s / it)
Averaged stats: lr: 0.000113  min_lr: 0.000113  loss: 2.0290 (1.8597)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:08  loss: 0.4932 (0.4932)  acc1: 87.3698 (87.3698)  acc5: 97.9167 (97.9167)  time: 7.5967  data: 7.3341  max mem: 78493
Test:  [8/9]  eta: 0:00:01  loss: 0.7449 (0.6788)  acc1: 81.2500 (81.5040)  acc5: 95.9635 (95.8560)  time: 1.1276  data: 0.9004  max mem: 78493
Test: Total time: 0:00:10 (1.1416 s / it)
* Acc@1 82.258 Acc@5 95.986 loss 0.665
Accuracy of the model on the 50000 test images: 82.3%
Max accuracy: 82.36%
Epoch: [270]  [  0/312]  eta: 1:24:43  lr: 0.000113  min_lr: 0.000113  loss: 1.9143 (1.9143)  weight_decay: 0.0500 (0.0500)  time: 16.2917  data: 12.9417  max mem: 78493
Epoch: [270]  [ 10/312]  eta: 0:12:55  lr: 0.000113  min_lr: 0.000113  loss: 1.8506 (1.8595)  weight_decay: 0.0500 (0.0500)  time: 2.5684  data: 1.3141  max mem: 78493
Epoch: [270]  [ 20/312]  eta: 0:08:53  lr: 0.000113  min_lr: 0.000113  loss: 1.8464 (1.8137)  weight_decay: 0.0500 (0.0500)  time: 1.1054  data: 0.0768  max mem: 78493
Epoch: [270]  [ 30/312]  eta: 0:07:21  lr: 0.000112  min_lr: 0.000112  loss: 1.8812 (1.8365)  weight_decay: 0.0500 (0.0500)  time: 1.0118  data: 0.0013  max mem: 78493
Epoch: [270]  [ 40/312]  eta: 0:06:28  lr: 0.000112  min_lr: 0.000112  loss: 1.9509 (1.8538)  weight_decay: 0.0500 (0.0500)  time: 1.0086  data: 0.0004  max mem: 78493
Epoch: [270]  [ 50/312]  eta: 0:05:52  lr: 0.000112  min_lr: 0.000112  loss: 1.9511 (1.8623)  weight_decay: 0.0500 (0.0500)  time: 1.0079  data: 0.0004  max mem: 78493
Epoch: [270]  [ 60/312]  eta: 0:05:25  lr: 0.000112  min_lr: 0.000112  loss: 1.9243 (1.8550)  weight_decay: 0.0500 (0.0500)  time: 1.0086  data: 0.0004  max mem: 78493
Epoch: [270]  [ 70/312]  eta: 0:05:02  lr: 0.000112  min_lr: 0.000112  loss: 1.8698 (1.8661)  weight_decay: 0.0500 (0.0500)  time: 1.0090  data: 0.0004  max mem: 78493
Epoch: [270]  [ 80/312]  eta: 0:04:43  lr: 0.000111  min_lr: 0.000111  loss: 1.8698 (1.8668)  weight_decay: 0.0500 (0.0500)  time: 1.0069  data: 0.0005  max mem: 78493
Epoch: [270]  [ 90/312]  eta: 0:04:25  lr: 0.000111  min_lr: 0.000111  loss: 1.9997 (1.8959)  weight_decay: 0.0500 (0.0500)  time: 1.0076  data: 0.0004  max mem: 78493
Epoch: [270]  [100/312]  eta: 0:04:09  lr: 0.000111  min_lr: 0.000111  loss: 1.9706 (1.8913)  weight_decay: 0.0500 (0.0500)  time: 1.0099  data: 0.0004  max mem: 78493
Epoch: [270]  [110/312]  eta: 0:03:54  lr: 0.000111  min_lr: 0.000111  loss: 1.8886 (1.8839)  weight_decay: 0.0500 (0.0500)  time: 1.0074  data: 0.0004  max mem: 78493
Epoch: [270]  [120/312]  eta: 0:03:40  lr: 0.000110  min_lr: 0.000110  loss: 1.8910 (1.8859)  weight_decay: 0.0500 (0.0500)  time: 1.0054  data: 0.0004  max mem: 78493
Epoch: [270]  [130/312]  eta: 0:03:27  lr: 0.000110  min_lr: 0.000110  loss: 1.8974 (1.8872)  weight_decay: 0.0500 (0.0500)  time: 1.0075  data: 0.0004  max mem: 78493
Epoch: [270]  [140/312]  eta: 0:03:14  lr: 0.000110  min_lr: 0.000110  loss: 1.9199 (1.8762)  weight_decay: 0.0500 (0.0500)  time: 1.0084  data: 0.0004  max mem: 78493
Epoch: [270]  [150/312]  eta: 0:03:01  lr: 0.000110  min_lr: 0.000110  loss: 1.8981 (1.8782)  weight_decay: 0.0500 (0.0500)  time: 1.0082  data: 0.0004  max mem: 78493
Epoch: [270]  [160/312]  eta: 0:02:49  lr: 0.000109  min_lr: 0.000109  loss: 1.8981 (1.8758)  weight_decay: 0.0500 (0.0500)  time: 1.0064  data: 0.0004  max mem: 78493
Epoch: [270]  [170/312]  eta: 0:02:37  lr: 0.000109  min_lr: 0.000109  loss: 1.8306 (1.8772)  weight_decay: 0.0500 (0.0500)  time: 1.0060  data: 0.0004  max mem: 78493
Epoch: [270]  [180/312]  eta: 0:02:25  lr: 0.000109  min_lr: 0.000109  loss: 1.9987 (1.8848)  weight_decay: 0.0500 (0.0500)  time: 1.0079  data: 0.0004  max mem: 78493
Epoch: [270]  [190/312]  eta: 0:02:13  lr: 0.000109  min_lr: 0.000109  loss: 1.9150 (1.8741)  weight_decay: 0.0500 (0.0500)  time: 1.0074  data: 0.0004  max mem: 78493
Epoch: [270]  [200/312]  eta: 0:02:02  lr: 0.000109  min_lr: 0.000109  loss: 1.7937 (1.8697)  weight_decay: 0.0500 (0.0500)  time: 1.0057  data: 0.0004  max mem: 78493
Epoch: [270]  [210/312]  eta: 0:01:51  lr: 0.000108  min_lr: 0.000108  loss: 1.7937 (1.8627)  weight_decay: 0.0500 (0.0500)  time: 1.0057  data: 0.0004  max mem: 78493
Epoch: [270]  [220/312]  eta: 0:01:39  lr: 0.000108  min_lr: 0.000108  loss: 1.8392 (1.8644)  weight_decay: 0.0500 (0.0500)  time: 1.0065  data: 0.0004  max mem: 78493
Epoch: [270]  [230/312]  eta: 0:01:28  lr: 0.000108  min_lr: 0.000108  loss: 1.9054 (1.8654)  weight_decay: 0.0500 (0.0500)  time: 1.0066  data: 0.0004  max mem: 78493
Epoch: [270]  [240/312]  eta: 0:01:17  lr: 0.000108  min_lr: 0.000108  loss: 1.9683 (1.8665)  weight_decay: 0.0500 (0.0500)  time: 1.0057  data: 0.0004  max mem: 78493
Epoch: [270]  [250/312]  eta: 0:01:06  lr: 0.000107  min_lr: 0.000107  loss: 1.8877 (1.8651)  weight_decay: 0.0500 (0.0500)  time: 1.0034  data: 0.0004  max mem: 78493
Epoch: [270]  [260/312]  eta: 0:00:55  lr: 0.000107  min_lr: 0.000107  loss: 1.9739 (1.8727)  weight_decay: 0.0500 (0.0500)  time: 1.0038  data: 0.0004  max mem: 78493
Epoch: [270]  [270/312]  eta: 0:00:44  lr: 0.000107  min_lr: 0.000107  loss: 2.0294 (1.8747)  weight_decay: 0.0500 (0.0500)  time: 1.0043  data: 0.0004  max mem: 78493
Epoch: [270]  [280/312]  eta: 0:00:34  lr: 0.000107  min_lr: 0.000107  loss: 1.7648 (1.8635)  weight_decay: 0.0500 (0.0500)  time: 1.0049  data: 0.0010  max mem: 78493
Epoch: [270]  [290/312]  eta: 0:00:23  lr: 0.000106  min_lr: 0.000106  loss: 1.6523 (1.8660)  weight_decay: 0.0500 (0.0500)  time: 1.0039  data: 0.0009  max mem: 78493
Epoch: [270]  [300/312]  eta: 0:00:12  lr: 0.000106  min_lr: 0.000106  loss: 1.9763 (1.8626)  weight_decay: 0.0500 (0.0500)  time: 1.0013  data: 0.0001  max mem: 78493
Epoch: [270]  [310/312]  eta: 0:00:02  lr: 0.000106  min_lr: 0.000106  loss: 1.8928 (1.8629)  weight_decay: 0.0500 (0.0500)  time: 1.0015  data: 0.0001  max mem: 78493
Epoch: [270]  [311/312]  eta: 0:00:01  lr: 0.000106  min_lr: 0.000106  loss: 1.8415 (1.8627)  weight_decay: 0.0500 (0.0500)  time: 1.0016  data: 0.0001  max mem: 78493
Epoch: [270] Total time: 0:05:32 (1.0672 s / it)
Averaged stats: lr: 0.000106  min_lr: 0.000106  loss: 1.8415 (1.8538)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:15  loss: 0.4780 (0.4780)  acc1: 87.6302 (87.6302)  acc5: 97.7865 (97.7865)  time: 8.4144  data: 8.1518  max mem: 78493
Test:  [8/9]  eta: 0:00:01  loss: 0.7372 (0.6717)  acc1: 81.9010 (81.8400)  acc5: 96.0938 (95.8720)  time: 1.1410  data: 0.9058  max mem: 78493
Test: Total time: 0:00:10 (1.1908 s / it)
* Acc@1 82.332 Acc@5 95.990 loss 0.663
Accuracy of the model on the 50000 test images: 82.3%
Max accuracy: 82.36%
Epoch: [271]  [  0/312]  eta: 1:19:37  lr: 0.000106  min_lr: 0.000106  loss: 1.4512 (1.4512)  weight_decay: 0.0500 (0.0500)  time: 15.3121  data: 11.4305  max mem: 78493
Epoch: [271]  [ 10/312]  eta: 0:13:12  lr: 0.000106  min_lr: 0.000106  loss: 1.8591 (1.8322)  weight_decay: 0.0500 (0.0500)  time: 2.6229  data: 1.3137  max mem: 78493
Epoch: [271]  [ 20/312]  eta: 0:09:01  lr: 0.000105  min_lr: 0.000105  loss: 1.9822 (1.8576)  weight_decay: 0.0500 (0.0500)  time: 1.1830  data: 0.1530  max mem: 78493
Epoch: [271]  [ 30/312]  eta: 0:07:25  lr: 0.000105  min_lr: 0.000105  loss: 2.0036 (1.8542)  weight_decay: 0.0500 (0.0500)  time: 1.0087  data: 0.0022  max mem: 78493
Epoch: [271]  [ 40/312]  eta: 0:06:31  lr: 0.000105  min_lr: 0.000105  loss: 1.9447 (1.8527)  weight_decay: 0.0500 (0.0500)  time: 1.0040  data: 0.0015  max mem: 78493
Epoch: [271]  [ 50/312]  eta: 0:05:54  lr: 0.000105  min_lr: 0.000105  loss: 1.9197 (1.8701)  weight_decay: 0.0500 (0.0500)  time: 1.0038  data: 0.0014  max mem: 78493
Epoch: [271]  [ 60/312]  eta: 0:05:27  lr: 0.000105  min_lr: 0.000105  loss: 1.9138 (1.8668)  weight_decay: 0.0500 (0.0500)  time: 1.0066  data: 0.0004  max mem: 78493
Epoch: [271]  [ 70/312]  eta: 0:05:04  lr: 0.000104  min_lr: 0.000104  loss: 1.8004 (1.8466)  weight_decay: 0.0500 (0.0500)  time: 1.0075  data: 0.0004  max mem: 78493
Epoch: [271]  [ 80/312]  eta: 0:04:44  lr: 0.000104  min_lr: 0.000104  loss: 1.9442 (1.8603)  weight_decay: 0.0500 (0.0500)  time: 1.0070  data: 0.0005  max mem: 78493
Epoch: [271]  [ 90/312]  eta: 0:04:26  lr: 0.000104  min_lr: 0.000104  loss: 2.0019 (1.8676)  weight_decay: 0.0500 (0.0500)  time: 1.0065  data: 0.0005  max mem: 78493
Epoch: [271]  [100/312]  eta: 0:04:10  lr: 0.000104  min_lr: 0.000104  loss: 1.9508 (1.8581)  weight_decay: 0.0500 (0.0500)  time: 1.0065  data: 0.0011  max mem: 78493
Epoch: [271]  [110/312]  eta: 0:03:55  lr: 0.000103  min_lr: 0.000103  loss: 1.9495 (1.8679)  weight_decay: 0.0500 (0.0500)  time: 1.0071  data: 0.0012  max mem: 78493
Epoch: [271]  [120/312]  eta: 0:03:41  lr: 0.000103  min_lr: 0.000103  loss: 2.0062 (1.8756)  weight_decay: 0.0500 (0.0500)  time: 1.0077  data: 0.0015  max mem: 78493
Epoch: [271]  [130/312]  eta: 0:03:27  lr: 0.000103  min_lr: 0.000103  loss: 2.0062 (1.8967)  weight_decay: 0.0500 (0.0500)  time: 1.0089  data: 0.0015  max mem: 78493
Epoch: [271]  [140/312]  eta: 0:03:14  lr: 0.000103  min_lr: 0.000103  loss: 2.1078 (1.8981)  weight_decay: 0.0500 (0.0500)  time: 1.0087  data: 0.0005  max mem: 78493
Epoch: [271]  [150/312]  eta: 0:03:02  lr: 0.000102  min_lr: 0.000102  loss: 1.9235 (1.8960)  weight_decay: 0.0500 (0.0500)  time: 1.0074  data: 0.0004  max mem: 78493
Epoch: [271]  [160/312]  eta: 0:02:49  lr: 0.000102  min_lr: 0.000102  loss: 1.9260 (1.8983)  weight_decay: 0.0500 (0.0500)  time: 1.0064  data: 0.0004  max mem: 78493
Epoch: [271]  [170/312]  eta: 0:02:37  lr: 0.000102  min_lr: 0.000102  loss: 2.0641 (1.9036)  weight_decay: 0.0500 (0.0500)  time: 1.0057  data: 0.0005  max mem: 78493
Epoch: [271]  [180/312]  eta: 0:02:25  lr: 0.000102  min_lr: 0.000102  loss: 1.7262 (1.8891)  weight_decay: 0.0500 (0.0500)  time: 1.0060  data: 0.0005  max mem: 78493
Epoch: [271]  [190/312]  eta: 0:02:14  lr: 0.000102  min_lr: 0.000102  loss: 1.7813 (1.8942)  weight_decay: 0.0500 (0.0500)  time: 1.0055  data: 0.0005  max mem: 78493
Epoch: [271]  [200/312]  eta: 0:02:02  lr: 0.000101  min_lr: 0.000101  loss: 1.9208 (1.8910)  weight_decay: 0.0500 (0.0500)  time: 1.0053  data: 0.0005  max mem: 78493
Epoch: [271]  [210/312]  eta: 0:01:51  lr: 0.000101  min_lr: 0.000101  loss: 1.7760 (1.8858)  weight_decay: 0.0500 (0.0500)  time: 1.0069  data: 0.0005  max mem: 78493
Epoch: [271]  [220/312]  eta: 0:01:40  lr: 0.000101  min_lr: 0.000101  loss: 1.7267 (1.8804)  weight_decay: 0.0500 (0.0500)  time: 1.0070  data: 0.0005  max mem: 78493
Epoch: [271]  [230/312]  eta: 0:01:28  lr: 0.000101  min_lr: 0.000101  loss: 1.8821 (1.8762)  weight_decay: 0.0500 (0.0500)  time: 1.0063  data: 0.0005  max mem: 78493
Epoch: [271]  [240/312]  eta: 0:01:17  lr: 0.000100  min_lr: 0.000100  loss: 1.9404 (1.8767)  weight_decay: 0.0500 (0.0500)  time: 1.0051  data: 0.0004  max mem: 78493
Epoch: [271]  [250/312]  eta: 0:01:06  lr: 0.000100  min_lr: 0.000100  loss: 1.9984 (1.8799)  weight_decay: 0.0500 (0.0500)  time: 1.0043  data: 0.0004  max mem: 78493
Epoch: [271]  [260/312]  eta: 0:00:55  lr: 0.000100  min_lr: 0.000100  loss: 2.0208 (1.8813)  weight_decay: 0.0500 (0.0500)  time: 1.0035  data: 0.0004  max mem: 78493
Epoch: [271]  [270/312]  eta: 0:00:45  lr: 0.000100  min_lr: 0.000100  loss: 2.0351 (1.8818)  weight_decay: 0.0500 (0.0500)  time: 1.0041  data: 0.0004  max mem: 78493
Epoch: [271]  [280/312]  eta: 0:00:34  lr: 0.000100  min_lr: 0.000100  loss: 1.8983 (1.8787)  weight_decay: 0.0500 (0.0500)  time: 1.0062  data: 0.0011  max mem: 78493
Epoch: [271]  [290/312]  eta: 0:00:23  lr: 0.000099  min_lr: 0.000099  loss: 1.8983 (1.8837)  weight_decay: 0.0500 (0.0500)  time: 1.0043  data: 0.0009  max mem: 78493
Epoch: [271]  [300/312]  eta: 0:00:12  lr: 0.000099  min_lr: 0.000099  loss: 1.9707 (1.8858)  weight_decay: 0.0500 (0.0500)  time: 1.0019  data: 0.0001  max mem: 78493
Epoch: [271]  [310/312]  eta: 0:00:02  lr: 0.000099  min_lr: 0.000099  loss: 1.9115 (1.8874)  weight_decay: 0.0500 (0.0500)  time: 1.0018  data: 0.0001  max mem: 78493
Epoch: [271]  [311/312]  eta: 0:00:01  lr: 0.000099  min_lr: 0.000099  loss: 1.9115 (1.8881)  weight_decay: 0.0500 (0.0500)  time: 1.0017  data: 0.0001  max mem: 78493
Epoch: [271] Total time: 0:05:33 (1.0686 s / it)
Averaged stats: lr: 0.000099  min_lr: 0.000099  loss: 1.9115 (1.8648)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:15  loss: 0.4861 (0.4861)  acc1: 87.3698 (87.3698)  acc5: 97.9167 (97.9167)  time: 8.4142  data: 8.1385  max mem: 78493
Test:  [8/9]  eta: 0:00:01  loss: 0.7306 (0.6734)  acc1: 82.0312 (81.9840)  acc5: 95.9635 (95.8880)  time: 1.1331  data: 0.9044  max mem: 78493
Test: Total time: 0:00:10 (1.1487 s / it)
* Acc@1 82.432 Acc@5 96.008 loss 0.661
Accuracy of the model on the 50000 test images: 82.4%
Max accuracy: 82.43%
Epoch: [272]  [  0/312]  eta: 1:28:30  lr: 0.000099  min_lr: 0.000099  loss: 1.7822 (1.7822)  weight_decay: 0.0500 (0.0500)  time: 17.0203  data: 16.0117  max mem: 78493
Epoch: [272]  [ 10/312]  eta: 0:13:21  lr: 0.000099  min_lr: 0.000099  loss: 1.6268 (1.6275)  weight_decay: 0.0500 (0.0500)  time: 2.6542  data: 1.4603  max mem: 78493
Epoch: [272]  [ 20/312]  eta: 0:09:08  lr: 0.000098  min_lr: 0.000098  loss: 1.6458 (1.7797)  weight_decay: 0.0500 (0.0500)  time: 1.1202  data: 0.0028  max mem: 78493
Epoch: [272]  [ 30/312]  eta: 0:07:30  lr: 0.000098  min_lr: 0.000098  loss: 1.9321 (1.8100)  weight_decay: 0.0500 (0.0500)  time: 1.0145  data: 0.0005  max mem: 78493
Epoch: [272]  [ 40/312]  eta: 0:06:35  lr: 0.000098  min_lr: 0.000098  loss: 1.8528 (1.7863)  weight_decay: 0.0500 (0.0500)  time: 1.0087  data: 0.0004  max mem: 78493
Epoch: [272]  [ 50/312]  eta: 0:05:57  lr: 0.000098  min_lr: 0.000098  loss: 1.8732 (1.8299)  weight_decay: 0.0500 (0.0500)  time: 1.0090  data: 0.0005  max mem: 78493
Epoch: [272]  [ 60/312]  eta: 0:05:29  lr: 0.000098  min_lr: 0.000098  loss: 2.0346 (1.8573)  weight_decay: 0.0500 (0.0500)  time: 1.0055  data: 0.0005  max mem: 78493
Epoch: [272]  [ 70/312]  eta: 0:05:06  lr: 0.000097  min_lr: 0.000097  loss: 2.0144 (1.8633)  weight_decay: 0.0500 (0.0500)  time: 1.0062  data: 0.0004  max mem: 78493
Epoch: [272]  [ 80/312]  eta: 0:04:46  lr: 0.000097  min_lr: 0.000097  loss: 1.9497 (1.8650)  weight_decay: 0.0500 (0.0500)  time: 1.0083  data: 0.0004  max mem: 78493
Epoch: [272]  [ 90/312]  eta: 0:04:28  lr: 0.000097  min_lr: 0.000097  loss: 1.9427 (1.8712)  weight_decay: 0.0500 (0.0500)  time: 1.0081  data: 0.0004  max mem: 78493
Epoch: [272]  [100/312]  eta: 0:04:11  lr: 0.000097  min_lr: 0.000097  loss: 1.9289 (1.8680)  weight_decay: 0.0500 (0.0500)  time: 1.0070  data: 0.0004  max mem: 78493
Epoch: [272]  [110/312]  eta: 0:03:56  lr: 0.000096  min_lr: 0.000096  loss: 1.8805 (1.8699)  weight_decay: 0.0500 (0.0500)  time: 1.0070  data: 0.0004  max mem: 78493
Epoch: [272]  [120/312]  eta: 0:03:42  lr: 0.000096  min_lr: 0.000096  loss: 1.8703 (1.8693)  weight_decay: 0.0500 (0.0500)  time: 1.0090  data: 0.0004  max mem: 78493
Epoch: [272]  [130/312]  eta: 0:03:28  lr: 0.000096  min_lr: 0.000096  loss: 1.7989 (1.8577)  weight_decay: 0.0500 (0.0500)  time: 1.0105  data: 0.0004  max mem: 78493
Epoch: [272]  [140/312]  eta: 0:03:15  lr: 0.000096  min_lr: 0.000096  loss: 1.8300 (1.8641)  weight_decay: 0.0500 (0.0500)  time: 1.0082  data: 0.0004  max mem: 78493
Epoch: [272]  [150/312]  eta: 0:03:02  lr: 0.000096  min_lr: 0.000096  loss: 1.8944 (1.8519)  weight_decay: 0.0500 (0.0500)  time: 1.0067  data: 0.0004  max mem: 78493
Epoch: [272]  [160/312]  eta: 0:02:50  lr: 0.000095  min_lr: 0.000095  loss: 1.8963 (1.8532)  weight_decay: 0.0500 (0.0500)  time: 1.0070  data: 0.0004  max mem: 78493
Epoch: [272]  [170/312]  eta: 0:02:38  lr: 0.000095  min_lr: 0.000095  loss: 1.9103 (1.8521)  weight_decay: 0.0500 (0.0500)  time: 1.0071  data: 0.0004  max mem: 78493
Epoch: [272]  [180/312]  eta: 0:02:26  lr: 0.000095  min_lr: 0.000095  loss: 1.8991 (1.8551)  weight_decay: 0.0500 (0.0500)  time: 1.0073  data: 0.0011  max mem: 78493
Epoch: [272]  [190/312]  eta: 0:02:14  lr: 0.000095  min_lr: 0.000095  loss: 1.8847 (1.8484)  weight_decay: 0.0500 (0.0500)  time: 1.0059  data: 0.0011  max mem: 78493
Epoch: [272]  [200/312]  eta: 0:02:03  lr: 0.000094  min_lr: 0.000094  loss: 1.7445 (1.8437)  weight_decay: 0.0500 (0.0500)  time: 1.0057  data: 0.0004  max mem: 78493
Epoch: [272]  [210/312]  eta: 0:01:51  lr: 0.000094  min_lr: 0.000094  loss: 1.9767 (1.8488)  weight_decay: 0.0500 (0.0500)  time: 1.0070  data: 0.0014  max mem: 78493
Epoch: [272]  [220/312]  eta: 0:01:40  lr: 0.000094  min_lr: 0.000094  loss: 1.9563 (1.8415)  weight_decay: 0.0500 (0.0500)  time: 1.0059  data: 0.0015  max mem: 78493
Epoch: [272]  [230/312]  eta: 0:01:29  lr: 0.000094  min_lr: 0.000094  loss: 1.6705 (1.8362)  weight_decay: 0.0500 (0.0500)  time: 1.0059  data: 0.0004  max mem: 78493
Epoch: [272]  [240/312]  eta: 0:01:17  lr: 0.000094  min_lr: 0.000094  loss: 1.9188 (1.8481)  weight_decay: 0.0500 (0.0500)  time: 1.0069  data: 0.0004  max mem: 78493
Epoch: [272]  [250/312]  eta: 0:01:06  lr: 0.000093  min_lr: 0.000093  loss: 2.1066 (1.8519)  weight_decay: 0.0500 (0.0500)  time: 1.0076  data: 0.0004  max mem: 78493
Epoch: [272]  [260/312]  eta: 0:00:56  lr: 0.000093  min_lr: 0.000093  loss: 1.8916 (1.8451)  weight_decay: 0.0500 (0.0500)  time: 1.0086  data: 0.0004  max mem: 78493
Epoch: [272]  [270/312]  eta: 0:00:45  lr: 0.000093  min_lr: 0.000093  loss: 1.8453 (1.8492)  weight_decay: 0.0500 (0.0500)  time: 1.0072  data: 0.0004  max mem: 78493
Epoch: [272]  [280/312]  eta: 0:00:34  lr: 0.000093  min_lr: 0.000093  loss: 1.9958 (1.8558)  weight_decay: 0.0500 (0.0500)  time: 1.0064  data: 0.0010  max mem: 78493
Epoch: [272]  [290/312]  eta: 0:00:23  lr: 0.000093  min_lr: 0.000093  loss: 1.9018 (1.8528)  weight_decay: 0.0500 (0.0500)  time: 1.0038  data: 0.0009  max mem: 78493
Epoch: [272]  [300/312]  eta: 0:00:12  lr: 0.000092  min_lr: 0.000092  loss: 1.8849 (1.8592)  weight_decay: 0.0500 (0.0500)  time: 1.0015  data: 0.0001  max mem: 78493
Epoch: [272]  [310/312]  eta: 0:00:02  lr: 0.000092  min_lr: 0.000092  loss: 1.9346 (1.8593)  weight_decay: 0.0500 (0.0500)  time: 1.0019  data: 0.0001  max mem: 78493
Epoch: [272]  [311/312]  eta: 0:00:01  lr: 0.000092  min_lr: 0.000092  loss: 1.9346 (1.8608)  weight_decay: 0.0500 (0.0500)  time: 1.0019  data: 0.0001  max mem: 78493
Epoch: [272] Total time: 0:05:34 (1.0710 s / it)
Averaged stats: lr: 0.000092  min_lr: 0.000092  loss: 1.9346 (1.8507)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:18  loss: 0.4835 (0.4835)  acc1: 87.7604 (87.7604)  acc5: 97.9167 (97.9167)  time: 8.6722  data: 8.4116  max mem: 78493
Test:  [8/9]  eta: 0:00:01  loss: 0.7411 (0.6786)  acc1: 82.4219 (82.0960)  acc5: 96.3542 (95.9360)  time: 1.1674  data: 0.9347  max mem: 78493
Test: Total time: 0:00:10 (1.2061 s / it)
* Acc@1 82.400 Acc@5 96.012 loss 0.663
Accuracy of the model on the 50000 test images: 82.4%
Max accuracy: 82.43%
Epoch: [273]  [  0/312]  eta: 1:21:31  lr: 0.000092  min_lr: 0.000092  loss: 2.0776 (2.0776)  weight_decay: 0.0500 (0.0500)  time: 15.6789  data: 12.1154  max mem: 78493
Epoch: [273]  [ 10/312]  eta: 0:13:12  lr: 0.000092  min_lr: 0.000092  loss: 1.8155 (1.8470)  weight_decay: 0.0500 (0.0500)  time: 2.6234  data: 1.3009  max mem: 78493
Epoch: [273]  [ 20/312]  eta: 0:09:04  lr: 0.000092  min_lr: 0.000092  loss: 1.7886 (1.7621)  weight_decay: 0.0500 (0.0500)  time: 1.1723  data: 0.1100  max mem: 78493
Epoch: [273]  [ 30/312]  eta: 0:07:27  lr: 0.000091  min_lr: 0.000091  loss: 1.7886 (1.7878)  weight_decay: 0.0500 (0.0500)  time: 1.0163  data: 0.0005  max mem: 78493
Epoch: [273]  [ 40/312]  eta: 0:06:33  lr: 0.000091  min_lr: 0.000091  loss: 1.9572 (1.8178)  weight_decay: 0.0500 (0.0500)  time: 1.0068  data: 0.0005  max mem: 78493
Epoch: [273]  [ 50/312]  eta: 0:05:56  lr: 0.000091  min_lr: 0.000091  loss: 1.9246 (1.8482)  weight_decay: 0.0500 (0.0500)  time: 1.0079  data: 0.0004  max mem: 78493
Epoch: [273]  [ 60/312]  eta: 0:05:28  lr: 0.000091  min_lr: 0.000091  loss: 1.9025 (1.8459)  weight_decay: 0.0500 (0.0500)  time: 1.0075  data: 0.0004  max mem: 78493
Epoch: [273]  [ 70/312]  eta: 0:05:05  lr: 0.000091  min_lr: 0.000091  loss: 1.8547 (1.8456)  weight_decay: 0.0500 (0.0500)  time: 1.0079  data: 0.0004  max mem: 78493
Epoch: [273]  [ 80/312]  eta: 0:04:45  lr: 0.000090  min_lr: 0.000090  loss: 1.8732 (1.8325)  weight_decay: 0.0500 (0.0500)  time: 1.0084  data: 0.0004  max mem: 78493
Epoch: [273]  [ 90/312]  eta: 0:04:27  lr: 0.000090  min_lr: 0.000090  loss: 1.7718 (1.8295)  weight_decay: 0.0500 (0.0500)  time: 1.0060  data: 0.0004  max mem: 78493
Epoch: [273]  [100/312]  eta: 0:04:11  lr: 0.000090  min_lr: 0.000090  loss: 1.8098 (1.8185)  weight_decay: 0.0500 (0.0500)  time: 1.0064  data: 0.0005  max mem: 78493
Epoch: [273]  [110/312]  eta: 0:03:56  lr: 0.000090  min_lr: 0.000090  loss: 1.8358 (1.8146)  weight_decay: 0.0500 (0.0500)  time: 1.0083  data: 0.0004  max mem: 78493
Epoch: [273]  [120/312]  eta: 0:03:41  lr: 0.000089  min_lr: 0.000089  loss: 1.8358 (1.8166)  weight_decay: 0.0500 (0.0500)  time: 1.0071  data: 0.0004  max mem: 78493
Epoch: [273]  [130/312]  eta: 0:03:28  lr: 0.000089  min_lr: 0.000089  loss: 1.7677 (1.8028)  weight_decay: 0.0500 (0.0500)  time: 1.0074  data: 0.0005  max mem: 78493
Epoch: [273]  [140/312]  eta: 0:03:15  lr: 0.000089  min_lr: 0.000089  loss: 1.7677 (1.8122)  weight_decay: 0.0500 (0.0500)  time: 1.0068  data: 0.0005  max mem: 78493
Epoch: [273]  [150/312]  eta: 0:03:02  lr: 0.000089  min_lr: 0.000089  loss: 1.8592 (1.8147)  weight_decay: 0.0500 (0.0500)  time: 1.0073  data: 0.0004  max mem: 78493
Epoch: [273]  [160/312]  eta: 0:02:50  lr: 0.000089  min_lr: 0.000089  loss: 1.8592 (1.8192)  weight_decay: 0.0500 (0.0500)  time: 1.0099  data: 0.0004  max mem: 78493
Epoch: [273]  [170/312]  eta: 0:02:37  lr: 0.000088  min_lr: 0.000088  loss: 1.8706 (1.8189)  weight_decay: 0.0500 (0.0500)  time: 1.0081  data: 0.0004  max mem: 78493
Epoch: [273]  [180/312]  eta: 0:02:26  lr: 0.000088  min_lr: 0.000088  loss: 1.9899 (1.8264)  weight_decay: 0.0500 (0.0500)  time: 1.0051  data: 0.0004  max mem: 78493
Epoch: [273]  [190/312]  eta: 0:02:14  lr: 0.000088  min_lr: 0.000088  loss: 1.9899 (1.8332)  weight_decay: 0.0500 (0.0500)  time: 1.0052  data: 0.0004  max mem: 78493
Epoch: [273]  [200/312]  eta: 0:02:02  lr: 0.000088  min_lr: 0.000088  loss: 1.8591 (1.8305)  weight_decay: 0.0500 (0.0500)  time: 1.0054  data: 0.0004  max mem: 78493
Epoch: [273]  [210/312]  eta: 0:01:51  lr: 0.000088  min_lr: 0.000088  loss: 1.6830 (1.8308)  weight_decay: 0.0500 (0.0500)  time: 1.0049  data: 0.0004  max mem: 78493
Epoch: [273]  [220/312]  eta: 0:01:40  lr: 0.000087  min_lr: 0.000087  loss: 1.8571 (1.8301)  weight_decay: 0.0500 (0.0500)  time: 1.0059  data: 0.0004  max mem: 78493
Epoch: [273]  [230/312]  eta: 0:01:28  lr: 0.000087  min_lr: 0.000087  loss: 1.9071 (1.8346)  weight_decay: 0.0500 (0.0500)  time: 1.0059  data: 0.0005  max mem: 78493
Epoch: [273]  [240/312]  eta: 0:01:17  lr: 0.000087  min_lr: 0.000087  loss: 1.8541 (1.8313)  weight_decay: 0.0500 (0.0500)  time: 1.0056  data: 0.0005  max mem: 78493
Epoch: [273]  [250/312]  eta: 0:01:06  lr: 0.000087  min_lr: 0.000087  loss: 1.8487 (1.8322)  weight_decay: 0.0500 (0.0500)  time: 1.0059  data: 0.0004  max mem: 78493
Epoch: [273]  [260/312]  eta: 0:00:55  lr: 0.000087  min_lr: 0.000087  loss: 1.9671 (1.8399)  weight_decay: 0.0500 (0.0500)  time: 1.0050  data: 0.0005  max mem: 78493
Epoch: [273]  [270/312]  eta: 0:00:45  lr: 0.000086  min_lr: 0.000086  loss: 2.1727 (1.8437)  weight_decay: 0.0500 (0.0500)  time: 1.0044  data: 0.0004  max mem: 78493
Epoch: [273]  [280/312]  eta: 0:00:34  lr: 0.000086  min_lr: 0.000086  loss: 1.9376 (1.8467)  weight_decay: 0.0500 (0.0500)  time: 1.0054  data: 0.0018  max mem: 78493
Epoch: [273]  [290/312]  eta: 0:00:23  lr: 0.000086  min_lr: 0.000086  loss: 2.0084 (1.8483)  weight_decay: 0.0500 (0.0500)  time: 1.0043  data: 0.0016  max mem: 78493
Epoch: [273]  [300/312]  eta: 0:00:12  lr: 0.000086  min_lr: 0.000086  loss: 1.9665 (1.8485)  weight_decay: 0.0500 (0.0500)  time: 1.0018  data: 0.0001  max mem: 78493
Epoch: [273]  [310/312]  eta: 0:00:02  lr: 0.000086  min_lr: 0.000086  loss: 1.8544 (1.8463)  weight_decay: 0.0500 (0.0500)  time: 1.0018  data: 0.0001  max mem: 78493
Epoch: [273]  [311/312]  eta: 0:00:01  lr: 0.000085  min_lr: 0.000085  loss: 1.9247 (1.8468)  weight_decay: 0.0500 (0.0500)  time: 1.0017  data: 0.0001  max mem: 78493
Epoch: [273] Total time: 0:05:33 (1.0694 s / it)
Averaged stats: lr: 0.000085  min_lr: 0.000085  loss: 1.9247 (1.8542)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:12  loss: 0.4771 (0.4771)  acc1: 88.0208 (88.0208)  acc5: 97.7865 (97.7865)  time: 8.0101  data: 7.7122  max mem: 78493
Test:  [8/9]  eta: 0:00:01  loss: 0.7285 (0.6729)  acc1: 82.2917 (82.0160)  acc5: 96.4844 (96.0640)  time: 1.0921  data: 0.8608  max mem: 78493
Test: Total time: 0:00:09 (1.1025 s / it)
* Acc@1 82.434 Acc@5 96.044 loss 0.660
Accuracy of the model on the 50000 test images: 82.4%
Max accuracy: 82.43%
Epoch: [274]  [  0/312]  eta: 1:21:54  lr: 0.000085  min_lr: 0.000085  loss: 2.0268 (2.0268)  weight_decay: 0.0500 (0.0500)  time: 15.7518  data: 13.1441  max mem: 78493
Epoch: [274]  [ 10/312]  eta: 0:12:32  lr: 0.000085  min_lr: 0.000085  loss: 1.9782 (1.8451)  weight_decay: 0.0500 (0.0500)  time: 2.4928  data: 1.2739  max mem: 78493
Epoch: [274]  [ 20/312]  eta: 0:08:44  lr: 0.000085  min_lr: 0.000085  loss: 1.9094 (1.7609)  weight_decay: 0.0500 (0.0500)  time: 1.0973  data: 0.0473  max mem: 78493
Epoch: [274]  [ 30/312]  eta: 0:07:14  lr: 0.000085  min_lr: 0.000085  loss: 1.7741 (1.7709)  weight_decay: 0.0500 (0.0500)  time: 1.0159  data: 0.0041  max mem: 78493
Epoch: [274]  [ 40/312]  eta: 0:06:23  lr: 0.000085  min_lr: 0.000085  loss: 1.9619 (1.8178)  weight_decay: 0.0500 (0.0500)  time: 1.0053  data: 0.0005  max mem: 78493
Epoch: [274]  [ 50/312]  eta: 0:05:48  lr: 0.000084  min_lr: 0.000084  loss: 2.0324 (1.8165)  weight_decay: 0.0500 (0.0500)  time: 1.0079  data: 0.0005  max mem: 78493
Epoch: [274]  [ 60/312]  eta: 0:05:22  lr: 0.000084  min_lr: 0.000084  loss: 1.9346 (1.8290)  weight_decay: 0.0500 (0.0500)  time: 1.0072  data: 0.0014  max mem: 78493
Epoch: [274]  [ 70/312]  eta: 0:05:00  lr: 0.000084  min_lr: 0.000084  loss: 1.9620 (1.8475)  weight_decay: 0.0500 (0.0500)  time: 1.0068  data: 0.0014  max mem: 78493
Epoch: [274]  [ 80/312]  eta: 0:04:41  lr: 0.000084  min_lr: 0.000084  loss: 1.9664 (1.8702)  weight_decay: 0.0500 (0.0500)  time: 1.0085  data: 0.0004  max mem: 78493
Epoch: [274]  [ 90/312]  eta: 0:04:24  lr: 0.000084  min_lr: 0.000084  loss: 2.0335 (1.8716)  weight_decay: 0.0500 (0.0500)  time: 1.0092  data: 0.0004  max mem: 78493
Epoch: [274]  [100/312]  eta: 0:04:08  lr: 0.000083  min_lr: 0.000083  loss: 1.9757 (1.8760)  weight_decay: 0.0500 (0.0500)  time: 1.0096  data: 0.0004  max mem: 78493
Epoch: [274]  [110/312]  eta: 0:03:53  lr: 0.000083  min_lr: 0.000083  loss: 1.9584 (1.8794)  weight_decay: 0.0500 (0.0500)  time: 1.0098  data: 0.0004  max mem: 78493
Epoch: [274]  [120/312]  eta: 0:03:39  lr: 0.000083  min_lr: 0.000083  loss: 1.9584 (1.8712)  weight_decay: 0.0500 (0.0500)  time: 1.0085  data: 0.0004  max mem: 78493
Epoch: [274]  [130/312]  eta: 0:03:26  lr: 0.000083  min_lr: 0.000083  loss: 1.8550 (1.8626)  weight_decay: 0.0500 (0.0500)  time: 1.0065  data: 0.0004  max mem: 78493
Epoch: [274]  [140/312]  eta: 0:03:13  lr: 0.000083  min_lr: 0.000083  loss: 1.9920 (1.8735)  weight_decay: 0.0500 (0.0500)  time: 1.0074  data: 0.0005  max mem: 78493
Epoch: [274]  [150/312]  eta: 0:03:00  lr: 0.000082  min_lr: 0.000082  loss: 1.9282 (1.8694)  weight_decay: 0.0500 (0.0500)  time: 1.0077  data: 0.0004  max mem: 78493
Epoch: [274]  [160/312]  eta: 0:02:48  lr: 0.000082  min_lr: 0.000082  loss: 1.8567 (1.8680)  weight_decay: 0.0500 (0.0500)  time: 1.0084  data: 0.0022  max mem: 78493
Epoch: [274]  [170/312]  eta: 0:02:36  lr: 0.000082  min_lr: 0.000082  loss: 1.9595 (1.8696)  weight_decay: 0.0500 (0.0500)  time: 1.0097  data: 0.0022  max mem: 78493
Epoch: [274]  [180/312]  eta: 0:02:25  lr: 0.000082  min_lr: 0.000082  loss: 1.9293 (1.8633)  weight_decay: 0.0500 (0.0500)  time: 1.0088  data: 0.0004  max mem: 78493
Epoch: [274]  [190/312]  eta: 0:02:13  lr: 0.000082  min_lr: 0.000082  loss: 1.7305 (1.8568)  weight_decay: 0.0500 (0.0500)  time: 1.0095  data: 0.0004  max mem: 78493
Epoch: [274]  [200/312]  eta: 0:02:02  lr: 0.000081  min_lr: 0.000081  loss: 1.7305 (1.8571)  weight_decay: 0.0500 (0.0500)  time: 1.0088  data: 0.0004  max mem: 78493
Epoch: [274]  [210/312]  eta: 0:01:50  lr: 0.000081  min_lr: 0.000081  loss: 1.9634 (1.8612)  weight_decay: 0.0500 (0.0500)  time: 1.0073  data: 0.0004  max mem: 78493
Epoch: [274]  [220/312]  eta: 0:01:39  lr: 0.000081  min_lr: 0.000081  loss: 1.9959 (1.8607)  weight_decay: 0.0500 (0.0500)  time: 1.0067  data: 0.0005  max mem: 78493
Epoch: [274]  [230/312]  eta: 0:01:28  lr: 0.000081  min_lr: 0.000081  loss: 1.9959 (1.8647)  weight_decay: 0.0500 (0.0500)  time: 1.0056  data: 0.0005  max mem: 78493
Epoch: [274]  [240/312]  eta: 0:01:17  lr: 0.000081  min_lr: 0.000081  loss: 1.9417 (1.8651)  weight_decay: 0.0500 (0.0500)  time: 1.0073  data: 0.0004  max mem: 78493
Epoch: [274]  [250/312]  eta: 0:01:06  lr: 0.000080  min_lr: 0.000080  loss: 1.9160 (1.8623)  weight_decay: 0.0500 (0.0500)  time: 1.0067  data: 0.0005  max mem: 78493
Epoch: [274]  [260/312]  eta: 0:00:55  lr: 0.000080  min_lr: 0.000080  loss: 2.0029 (1.8651)  weight_decay: 0.0500 (0.0500)  time: 1.0052  data: 0.0005  max mem: 78493
Epoch: [274]  [270/312]  eta: 0:00:44  lr: 0.000080  min_lr: 0.000080  loss: 2.0394 (1.8690)  weight_decay: 0.0500 (0.0500)  time: 1.0068  data: 0.0013  max mem: 78493
Epoch: [274]  [280/312]  eta: 0:00:34  lr: 0.000080  min_lr: 0.000080  loss: 1.9692 (1.8701)  weight_decay: 0.0500 (0.0500)  time: 1.0074  data: 0.0019  max mem: 78493
Epoch: [274]  [290/312]  eta: 0:00:23  lr: 0.000080  min_lr: 0.000080  loss: 1.9718 (1.8710)  weight_decay: 0.0500 (0.0500)  time: 1.0045  data: 0.0009  max mem: 78493
Epoch: [274]  [300/312]  eta: 0:00:12  lr: 0.000079  min_lr: 0.000079  loss: 1.9663 (1.8690)  weight_decay: 0.0500 (0.0500)  time: 1.0017  data: 0.0001  max mem: 78493
Epoch: [274]  [310/312]  eta: 0:00:02  lr: 0.000079  min_lr: 0.000079  loss: 1.8034 (1.8650)  weight_decay: 0.0500 (0.0500)  time: 1.0016  data: 0.0001  max mem: 78493
Epoch: [274]  [311/312]  eta: 0:00:01  lr: 0.000079  min_lr: 0.000079  loss: 1.8034 (1.8655)  weight_decay: 0.0500 (0.0500)  time: 1.0016  data: 0.0001  max mem: 78493
Epoch: [274] Total time: 0:05:32 (1.0660 s / it)
Averaged stats: lr: 0.000079  min_lr: 0.000079  loss: 1.8034 (1.8507)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:16  loss: 0.4873 (0.4873)  acc1: 87.6302 (87.6302)  acc5: 97.7865 (97.7865)  time: 8.5263  data: 8.2629  max mem: 78493
Test:  [8/9]  eta: 0:00:01  loss: 0.7309 (0.6728)  acc1: 82.1615 (81.9520)  acc5: 96.0938 (96.0000)  time: 1.1492  data: 0.9182  max mem: 78493
Test: Total time: 0:00:10 (1.1724 s / it)
* Acc@1 82.508 Acc@5 96.064 loss 0.661
Accuracy of the model on the 50000 test images: 82.5%
Max accuracy: 82.51%
Epoch: [275]  [  0/312]  eta: 1:19:46  lr: 0.000079  min_lr: 0.000079  loss: 1.2190 (1.2190)  weight_decay: 0.0500 (0.0500)  time: 15.3420  data: 12.9080  max mem: 78493
Epoch: [275]  [ 10/312]  eta: 0:13:17  lr: 0.000079  min_lr: 0.000079  loss: 1.6261 (1.6500)  weight_decay: 0.0500 (0.0500)  time: 2.6397  data: 1.4418  max mem: 78493
Epoch: [275]  [ 20/312]  eta: 0:09:04  lr: 0.000079  min_lr: 0.000079  loss: 1.9370 (1.8156)  weight_decay: 0.0500 (0.0500)  time: 1.1905  data: 0.1478  max mem: 78493
Epoch: [275]  [ 30/312]  eta: 0:07:27  lr: 0.000079  min_lr: 0.000079  loss: 1.9970 (1.8273)  weight_decay: 0.0500 (0.0500)  time: 1.0090  data: 0.0004  max mem: 78493
Epoch: [275]  [ 40/312]  eta: 0:06:33  lr: 0.000078  min_lr: 0.000078  loss: 1.9192 (1.8125)  weight_decay: 0.0500 (0.0500)  time: 1.0059  data: 0.0004  max mem: 78493
Epoch: [275]  [ 50/312]  eta: 0:05:56  lr: 0.000078  min_lr: 0.000078  loss: 1.9439 (1.8616)  weight_decay: 0.0500 (0.0500)  time: 1.0054  data: 0.0004  max mem: 78493
Epoch: [275]  [ 60/312]  eta: 0:05:28  lr: 0.000078  min_lr: 0.000078  loss: 1.9559 (1.8734)  weight_decay: 0.0500 (0.0500)  time: 1.0076  data: 0.0004  max mem: 78493
Epoch: [275]  [ 70/312]  eta: 0:05:05  lr: 0.000078  min_lr: 0.000078  loss: 1.9284 (1.8688)  weight_decay: 0.0500 (0.0500)  time: 1.0081  data: 0.0004  max mem: 78493
Epoch: [275]  [ 80/312]  eta: 0:04:45  lr: 0.000078  min_lr: 0.000078  loss: 1.8640 (1.8589)  weight_decay: 0.0500 (0.0500)  time: 1.0067  data: 0.0004  max mem: 78493
Epoch: [275]  [ 90/312]  eta: 0:04:27  lr: 0.000077  min_lr: 0.000077  loss: 1.6979 (1.8377)  weight_decay: 0.0500 (0.0500)  time: 1.0077  data: 0.0005  max mem: 78493
Epoch: [275]  [100/312]  eta: 0:04:11  lr: 0.000077  min_lr: 0.000077  loss: 1.7131 (1.8299)  weight_decay: 0.0500 (0.0500)  time: 1.0077  data: 0.0004  max mem: 78493
Epoch: [275]  [110/312]  eta: 0:03:56  lr: 0.000077  min_lr: 0.000077  loss: 1.8120 (1.8323)  weight_decay: 0.0500 (0.0500)  time: 1.0067  data: 0.0004  max mem: 78493
Epoch: [275]  [120/312]  eta: 0:03:41  lr: 0.000077  min_lr: 0.000077  loss: 1.8424 (1.8308)  weight_decay: 0.0500 (0.0500)  time: 1.0071  data: 0.0004  max mem: 78493
Epoch: [275]  [130/312]  eta: 0:03:28  lr: 0.000077  min_lr: 0.000077  loss: 1.7699 (1.8221)  weight_decay: 0.0500 (0.0500)  time: 1.0063  data: 0.0005  max mem: 78493
Epoch: [275]  [140/312]  eta: 0:03:15  lr: 0.000076  min_lr: 0.000076  loss: 1.8158 (1.8254)  weight_decay: 0.0500 (0.0500)  time: 1.0052  data: 0.0004  max mem: 78493
Epoch: [275]  [150/312]  eta: 0:03:02  lr: 0.000076  min_lr: 0.000076  loss: 2.0236 (1.8319)  weight_decay: 0.0500 (0.0500)  time: 1.0072  data: 0.0004  max mem: 78493
Epoch: [275]  [160/312]  eta: 0:02:50  lr: 0.000076  min_lr: 0.000076  loss: 2.0184 (1.8365)  weight_decay: 0.0500 (0.0500)  time: 1.0079  data: 0.0004  max mem: 78493
Epoch: [275]  [170/312]  eta: 0:02:37  lr: 0.000076  min_lr: 0.000076  loss: 1.7172 (1.8323)  weight_decay: 0.0500 (0.0500)  time: 1.0074  data: 0.0005  max mem: 78493
Epoch: [275]  [180/312]  eta: 0:02:26  lr: 0.000076  min_lr: 0.000076  loss: 1.8298 (1.8391)  weight_decay: 0.0500 (0.0500)  time: 1.0065  data: 0.0005  max mem: 78493
Epoch: [275]  [190/312]  eta: 0:02:14  lr: 0.000075  min_lr: 0.000075  loss: 1.9811 (1.8412)  weight_decay: 0.0500 (0.0500)  time: 1.0063  data: 0.0005  max mem: 78493
Epoch: [275]  [200/312]  eta: 0:02:02  lr: 0.000075  min_lr: 0.000075  loss: 1.9940 (1.8422)  weight_decay: 0.0500 (0.0500)  time: 1.0086  data: 0.0004  max mem: 78493
Epoch: [275]  [210/312]  eta: 0:01:51  lr: 0.000075  min_lr: 0.000075  loss: 1.9627 (1.8457)  weight_decay: 0.0500 (0.0500)  time: 1.0075  data: 0.0004  max mem: 78493
Epoch: [275]  [220/312]  eta: 0:01:40  lr: 0.000075  min_lr: 0.000075  loss: 1.9236 (1.8458)  weight_decay: 0.0500 (0.0500)  time: 1.0069  data: 0.0004  max mem: 78493
Epoch: [275]  [230/312]  eta: 0:01:28  lr: 0.000075  min_lr: 0.000075  loss: 1.8388 (1.8416)  weight_decay: 0.0500 (0.0500)  time: 1.0067  data: 0.0004  max mem: 78493
Epoch: [275]  [240/312]  eta: 0:01:17  lr: 0.000074  min_lr: 0.000074  loss: 1.9199 (1.8400)  weight_decay: 0.0500 (0.0500)  time: 1.0058  data: 0.0005  max mem: 78493
Epoch: [275]  [250/312]  eta: 0:01:06  lr: 0.000074  min_lr: 0.000074  loss: 1.7407 (1.8291)  weight_decay: 0.0500 (0.0500)  time: 1.0055  data: 0.0005  max mem: 78493
Epoch: [275]  [260/312]  eta: 0:00:55  lr: 0.000074  min_lr: 0.000074  loss: 1.7407 (1.8295)  weight_decay: 0.0500 (0.0500)  time: 1.0049  data: 0.0005  max mem: 78493
Epoch: [275]  [270/312]  eta: 0:00:45  lr: 0.000074  min_lr: 0.000074  loss: 1.9607 (1.8310)  weight_decay: 0.0500 (0.0500)  time: 1.0049  data: 0.0005  max mem: 78493
Epoch: [275]  [280/312]  eta: 0:00:34  lr: 0.000074  min_lr: 0.000074  loss: 1.8061 (1.8272)  weight_decay: 0.0500 (0.0500)  time: 1.0078  data: 0.0017  max mem: 78493
Epoch: [275]  [290/312]  eta: 0:00:23  lr: 0.000073  min_lr: 0.000073  loss: 1.7834 (1.8278)  weight_decay: 0.0500 (0.0500)  time: 1.0061  data: 0.0015  max mem: 78493
Epoch: [275]  [300/312]  eta: 0:00:12  lr: 0.000073  min_lr: 0.000073  loss: 1.8887 (1.8292)  weight_decay: 0.0500 (0.0500)  time: 1.0014  data: 0.0001  max mem: 78493
Epoch: [275]  [310/312]  eta: 0:00:02  lr: 0.000073  min_lr: 0.000073  loss: 1.8912 (1.8278)  weight_decay: 0.0500 (0.0500)  time: 1.0015  data: 0.0001  max mem: 78493
Epoch: [275]  [311/312]  eta: 0:00:01  lr: 0.000073  min_lr: 0.000073  loss: 1.8887 (1.8267)  weight_decay: 0.0500 (0.0500)  time: 1.0015  data: 0.0001  max mem: 78493
Epoch: [275] Total time: 0:05:33 (1.0698 s / it)
Averaged stats: lr: 0.000073  min_lr: 0.000073  loss: 1.8887 (1.8349)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:16  loss: 0.4809 (0.4809)  acc1: 87.7604 (87.7604)  acc5: 97.7865 (97.7865)  time: 8.5416  data: 8.2740  max mem: 78493
Test:  [8/9]  eta: 0:00:01  loss: 0.7248 (0.6697)  acc1: 82.0312 (82.0800)  acc5: 96.2240 (96.0320)  time: 1.1479  data: 0.9194  max mem: 78493
Test: Total time: 0:00:10 (1.1640 s / it)
* Acc@1 82.490 Acc@5 96.070 loss 0.660
Accuracy of the model on the 50000 test images: 82.5%
Max accuracy: 82.51%
Epoch: [276]  [  0/312]  eta: 1:25:39  lr: 0.000073  min_lr: 0.000073  loss: 2.1553 (2.1553)  weight_decay: 0.0500 (0.0500)  time: 16.4722  data: 13.1719  max mem: 78493
Epoch: [276]  [ 10/312]  eta: 0:12:45  lr: 0.000073  min_lr: 0.000073  loss: 1.9229 (1.9021)  weight_decay: 0.0500 (0.0500)  time: 2.5363  data: 1.1981  max mem: 78493
Epoch: [276]  [ 20/312]  eta: 0:08:54  lr: 0.000073  min_lr: 0.000073  loss: 1.8882 (1.8734)  weight_decay: 0.0500 (0.0500)  time: 1.1001  data: 0.0062  max mem: 78493
Epoch: [276]  [ 30/312]  eta: 0:07:21  lr: 0.000072  min_lr: 0.000072  loss: 1.6834 (1.8410)  weight_decay: 0.0500 (0.0500)  time: 1.0339  data: 0.0061  max mem: 78493
Epoch: [276]  [ 40/312]  eta: 0:06:29  lr: 0.000072  min_lr: 0.000072  loss: 1.7435 (1.8377)  weight_decay: 0.0500 (0.0500)  time: 1.0097  data: 0.0004  max mem: 78493
Epoch: [276]  [ 50/312]  eta: 0:05:53  lr: 0.000072  min_lr: 0.000072  loss: 1.9577 (1.8357)  weight_decay: 0.0500 (0.0500)  time: 1.0101  data: 0.0004  max mem: 78493
Epoch: [276]  [ 60/312]  eta: 0:05:25  lr: 0.000072  min_lr: 0.000072  loss: 1.6336 (1.8028)  weight_decay: 0.0500 (0.0500)  time: 1.0099  data: 0.0005  max mem: 78493
Epoch: [276]  [ 70/312]  eta: 0:05:03  lr: 0.000072  min_lr: 0.000072  loss: 1.7947 (1.8233)  weight_decay: 0.0500 (0.0500)  time: 1.0089  data: 0.0004  max mem: 78493
Epoch: [276]  [ 80/312]  eta: 0:04:43  lr: 0.000072  min_lr: 0.000072  loss: 1.9475 (1.8157)  weight_decay: 0.0500 (0.0500)  time: 1.0088  data: 0.0004  max mem: 78493
Epoch: [276]  [ 90/312]  eta: 0:04:26  lr: 0.000071  min_lr: 0.000071  loss: 1.8683 (1.8297)  weight_decay: 0.0500 (0.0500)  time: 1.0065  data: 0.0004  max mem: 78493
Epoch: [276]  [100/312]  eta: 0:04:10  lr: 0.000071  min_lr: 0.000071  loss: 1.8916 (1.8272)  weight_decay: 0.0500 (0.0500)  time: 1.0055  data: 0.0004  max mem: 78493
Epoch: [276]  [110/312]  eta: 0:03:55  lr: 0.000071  min_lr: 0.000071  loss: 1.8725 (1.8183)  weight_decay: 0.0500 (0.0500)  time: 1.0080  data: 0.0004  max mem: 78493
Epoch: [276]  [120/312]  eta: 0:03:41  lr: 0.000071  min_lr: 0.000071  loss: 1.7316 (1.8085)  weight_decay: 0.0500 (0.0500)  time: 1.0070  data: 0.0005  max mem: 78493
Epoch: [276]  [130/312]  eta: 0:03:27  lr: 0.000071  min_lr: 0.000071  loss: 1.8050 (1.8072)  weight_decay: 0.0500 (0.0500)  time: 1.0070  data: 0.0004  max mem: 78493
Epoch: [276]  [140/312]  eta: 0:03:14  lr: 0.000070  min_lr: 0.000070  loss: 1.8057 (1.8020)  weight_decay: 0.0500 (0.0500)  time: 1.0073  data: 0.0004  max mem: 78493
Epoch: [276]  [150/312]  eta: 0:03:01  lr: 0.000070  min_lr: 0.000070  loss: 1.9579 (1.8183)  weight_decay: 0.0500 (0.0500)  time: 1.0059  data: 0.0004  max mem: 78493
Epoch: [276]  [160/312]  eta: 0:02:49  lr: 0.000070  min_lr: 0.000070  loss: 1.9723 (1.8068)  weight_decay: 0.0500 (0.0500)  time: 1.0065  data: 0.0004  max mem: 78493
Epoch: [276]  [170/312]  eta: 0:02:37  lr: 0.000070  min_lr: 0.000070  loss: 1.6164 (1.8020)  weight_decay: 0.0500 (0.0500)  time: 1.0078  data: 0.0004  max mem: 78493
Epoch: [276]  [180/312]  eta: 0:02:25  lr: 0.000070  min_lr: 0.000070  loss: 1.7843 (1.8044)  weight_decay: 0.0500 (0.0500)  time: 1.0074  data: 0.0004  max mem: 78493
Epoch: [276]  [190/312]  eta: 0:02:13  lr: 0.000069  min_lr: 0.000069  loss: 1.9255 (1.8108)  weight_decay: 0.0500 (0.0500)  time: 1.0057  data: 0.0004  max mem: 78493
Epoch: [276]  [200/312]  eta: 0:02:02  lr: 0.000069  min_lr: 0.000069  loss: 1.9754 (1.8219)  weight_decay: 0.0500 (0.0500)  time: 1.0064  data: 0.0004  max mem: 78493
Epoch: [276]  [210/312]  eta: 0:01:51  lr: 0.000069  min_lr: 0.000069  loss: 2.0245 (1.8246)  weight_decay: 0.0500 (0.0500)  time: 1.0060  data: 0.0004  max mem: 78493
Epoch: [276]  [220/312]  eta: 0:01:39  lr: 0.000069  min_lr: 0.000069  loss: 1.8800 (1.8263)  weight_decay: 0.0500 (0.0500)  time: 1.0051  data: 0.0004  max mem: 78493
Epoch: [276]  [230/312]  eta: 0:01:28  lr: 0.000069  min_lr: 0.000069  loss: 1.8832 (1.8306)  weight_decay: 0.0500 (0.0500)  time: 1.0060  data: 0.0004  max mem: 78493
Epoch: [276]  [240/312]  eta: 0:01:17  lr: 0.000069  min_lr: 0.000069  loss: 1.9162 (1.8346)  weight_decay: 0.0500 (0.0500)  time: 1.0066  data: 0.0004  max mem: 78493
Epoch: [276]  [250/312]  eta: 0:01:06  lr: 0.000068  min_lr: 0.000068  loss: 1.7679 (1.8257)  weight_decay: 0.0500 (0.0500)  time: 1.0058  data: 0.0004  max mem: 78493
Epoch: [276]  [260/312]  eta: 0:00:55  lr: 0.000068  min_lr: 0.000068  loss: 1.7539 (1.8274)  weight_decay: 0.0500 (0.0500)  time: 1.0052  data: 0.0004  max mem: 78493
Epoch: [276]  [270/312]  eta: 0:00:44  lr: 0.000068  min_lr: 0.000068  loss: 1.9520 (1.8279)  weight_decay: 0.0500 (0.0500)  time: 1.0055  data: 0.0005  max mem: 78493
Epoch: [276]  [280/312]  eta: 0:00:34  lr: 0.000068  min_lr: 0.000068  loss: 1.9566 (1.8299)  weight_decay: 0.0500 (0.0500)  time: 1.0063  data: 0.0010  max mem: 78493
Epoch: [276]  [290/312]  eta: 0:00:23  lr: 0.000068  min_lr: 0.000068  loss: 1.9376 (1.8284)  weight_decay: 0.0500 (0.0500)  time: 1.0043  data: 0.0009  max mem: 78493
Epoch: [276]  [300/312]  eta: 0:00:12  lr: 0.000067  min_lr: 0.000067  loss: 1.7963 (1.8270)  weight_decay: 0.0500 (0.0500)  time: 1.0019  data: 0.0001  max mem: 78493
Epoch: [276]  [310/312]  eta: 0:00:02  lr: 0.000067  min_lr: 0.000067  loss: 1.9399 (1.8324)  weight_decay: 0.0500 (0.0500)  time: 1.0020  data: 0.0001  max mem: 78493
Epoch: [276]  [311/312]  eta: 0:00:01  lr: 0.000067  min_lr: 0.000067  loss: 1.9736 (1.8330)  weight_decay: 0.0500 (0.0500)  time: 1.0020  data: 0.0001  max mem: 78493
Epoch: [276] Total time: 0:05:33 (1.0680 s / it)
Averaged stats: lr: 0.000067  min_lr: 0.000067  loss: 1.9736 (1.8572)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:14  loss: 0.4860 (0.4860)  acc1: 87.8906 (87.8906)  acc5: 97.9167 (97.9167)  time: 8.2957  data: 8.0140  max mem: 78493
Test:  [8/9]  eta: 0:00:01  loss: 0.7307 (0.6691)  acc1: 82.6823 (82.1280)  acc5: 96.0938 (95.9840)  time: 1.1200  data: 0.8905  max mem: 78493
Test: Total time: 0:00:10 (1.1456 s / it)
* Acc@1 82.446 Acc@5 96.096 loss 0.657
Accuracy of the model on the 50000 test images: 82.4%
Max accuracy: 82.51%
Epoch: [277]  [  0/312]  eta: 1:27:40  lr: 0.000067  min_lr: 0.000067  loss: 2.0894 (2.0894)  weight_decay: 0.0500 (0.0500)  time: 16.8605  data: 15.2938  max mem: 78493
Epoch: [277]  [ 10/312]  eta: 0:13:07  lr: 0.000067  min_lr: 0.000067  loss: 1.7419 (1.8165)  weight_decay: 0.0500 (0.0500)  time: 2.6091  data: 1.3953  max mem: 78493
Epoch: [277]  [ 20/312]  eta: 0:09:00  lr: 0.000067  min_lr: 0.000067  loss: 1.9657 (1.9175)  weight_decay: 0.0500 (0.0500)  time: 1.1019  data: 0.0040  max mem: 78493
Epoch: [277]  [ 30/312]  eta: 0:07:25  lr: 0.000067  min_lr: 0.000067  loss: 2.0569 (1.8747)  weight_decay: 0.0500 (0.0500)  time: 1.0132  data: 0.0015  max mem: 78493
Epoch: [277]  [ 40/312]  eta: 0:06:31  lr: 0.000066  min_lr: 0.000066  loss: 1.8357 (1.8689)  weight_decay: 0.0500 (0.0500)  time: 1.0077  data: 0.0005  max mem: 78493
Epoch: [277]  [ 50/312]  eta: 0:05:55  lr: 0.000066  min_lr: 0.000066  loss: 1.7817 (1.8429)  weight_decay: 0.0500 (0.0500)  time: 1.0073  data: 0.0005  max mem: 78493
Epoch: [277]  [ 60/312]  eta: 0:05:27  lr: 0.000066  min_lr: 0.000066  loss: 1.8365 (1.8478)  weight_decay: 0.0500 (0.0500)  time: 1.0067  data: 0.0004  max mem: 78493
Epoch: [277]  [ 70/312]  eta: 0:05:04  lr: 0.000066  min_lr: 0.000066  loss: 1.7772 (1.8158)  weight_decay: 0.0500 (0.0500)  time: 1.0065  data: 0.0004  max mem: 78493
Epoch: [277]  [ 80/312]  eta: 0:04:44  lr: 0.000066  min_lr: 0.000066  loss: 1.5210 (1.7923)  weight_decay: 0.0500 (0.0500)  time: 1.0071  data: 0.0005  max mem: 78493
Epoch: [277]  [ 90/312]  eta: 0:04:26  lr: 0.000066  min_lr: 0.000066  loss: 1.7239 (1.8006)  weight_decay: 0.0500 (0.0500)  time: 1.0079  data: 0.0005  max mem: 78493
Epoch: [277]  [100/312]  eta: 0:04:10  lr: 0.000065  min_lr: 0.000065  loss: 1.9148 (1.8028)  weight_decay: 0.0500 (0.0500)  time: 1.0085  data: 0.0005  max mem: 78493
Epoch: [277]  [110/312]  eta: 0:03:55  lr: 0.000065  min_lr: 0.000065  loss: 1.8317 (1.7976)  weight_decay: 0.0500 (0.0500)  time: 1.0083  data: 0.0004  max mem: 78493
Epoch: [277]  [120/312]  eta: 0:03:41  lr: 0.000065  min_lr: 0.000065  loss: 1.9595 (1.8120)  weight_decay: 0.0500 (0.0500)  time: 1.0054  data: 0.0004  max mem: 78493
Epoch: [277]  [130/312]  eta: 0:03:27  lr: 0.000065  min_lr: 0.000065  loss: 1.9595 (1.8033)  weight_decay: 0.0500 (0.0500)  time: 1.0065  data: 0.0005  max mem: 78493
Epoch: [277]  [140/312]  eta: 0:03:14  lr: 0.000065  min_lr: 0.000065  loss: 1.7735 (1.7999)  weight_decay: 0.0500 (0.0500)  time: 1.0088  data: 0.0004  max mem: 78493
Epoch: [277]  [150/312]  eta: 0:03:02  lr: 0.000064  min_lr: 0.000064  loss: 1.8770 (1.8047)  weight_decay: 0.0500 (0.0500)  time: 1.0066  data: 0.0004  max mem: 78493
Epoch: [277]  [160/312]  eta: 0:02:49  lr: 0.000064  min_lr: 0.000064  loss: 1.8770 (1.8115)  weight_decay: 0.0500 (0.0500)  time: 1.0054  data: 0.0004  max mem: 78493
Epoch: [277]  [170/312]  eta: 0:02:37  lr: 0.000064  min_lr: 0.000064  loss: 1.8417 (1.8061)  weight_decay: 0.0500 (0.0500)  time: 1.0064  data: 0.0005  max mem: 78493
Epoch: [277]  [180/312]  eta: 0:02:25  lr: 0.000064  min_lr: 0.000064  loss: 1.9006 (1.8086)  weight_decay: 0.0500 (0.0500)  time: 1.0056  data: 0.0005  max mem: 78493
Epoch: [277]  [190/312]  eta: 0:02:14  lr: 0.000064  min_lr: 0.000064  loss: 1.9123 (1.8101)  weight_decay: 0.0500 (0.0500)  time: 1.0067  data: 0.0004  max mem: 78493
Epoch: [277]  [200/312]  eta: 0:02:02  lr: 0.000064  min_lr: 0.000064  loss: 1.9061 (1.8133)  weight_decay: 0.0500 (0.0500)  time: 1.0061  data: 0.0005  max mem: 78493
Epoch: [277]  [210/312]  eta: 0:01:51  lr: 0.000063  min_lr: 0.000063  loss: 1.8964 (1.8061)  weight_decay: 0.0500 (0.0500)  time: 1.0061  data: 0.0005  max mem: 78493
Epoch: [277]  [220/312]  eta: 0:01:40  lr: 0.000063  min_lr: 0.000063  loss: 2.0248 (1.8194)  weight_decay: 0.0500 (0.0500)  time: 1.0067  data: 0.0004  max mem: 78493
Epoch: [277]  [230/312]  eta: 0:01:28  lr: 0.000063  min_lr: 0.000063  loss: 2.0296 (1.8104)  weight_decay: 0.0500 (0.0500)  time: 1.0046  data: 0.0004  max mem: 78493
Epoch: [277]  [240/312]  eta: 0:01:17  lr: 0.000063  min_lr: 0.000063  loss: 1.6917 (1.8108)  weight_decay: 0.0500 (0.0500)  time: 1.0043  data: 0.0004  max mem: 78493
Epoch: [277]  [250/312]  eta: 0:01:06  lr: 0.000063  min_lr: 0.000063  loss: 1.9217 (1.8112)  weight_decay: 0.0500 (0.0500)  time: 1.0055  data: 0.0004  max mem: 78493
Epoch: [277]  [260/312]  eta: 0:00:55  lr: 0.000063  min_lr: 0.000063  loss: 1.9220 (1.8134)  weight_decay: 0.0500 (0.0500)  time: 1.0052  data: 0.0004  max mem: 78493
Epoch: [277]  [270/312]  eta: 0:00:45  lr: 0.000062  min_lr: 0.000062  loss: 1.6826 (1.8079)  weight_decay: 0.0500 (0.0500)  time: 1.0039  data: 0.0013  max mem: 78493
Epoch: [277]  [280/312]  eta: 0:00:34  lr: 0.000062  min_lr: 0.000062  loss: 1.6826 (1.8057)  weight_decay: 0.0500 (0.0500)  time: 1.0059  data: 0.0022  max mem: 78493
Epoch: [277]  [290/312]  eta: 0:00:23  lr: 0.000062  min_lr: 0.000062  loss: 1.7703 (1.8091)  weight_decay: 0.0500 (0.0500)  time: 1.0043  data: 0.0011  max mem: 78493
Epoch: [277]  [300/312]  eta: 0:00:12  lr: 0.000062  min_lr: 0.000062  loss: 1.9776 (1.8083)  weight_decay: 0.0500 (0.0500)  time: 1.0017  data: 0.0001  max mem: 78493
Epoch: [277]  [310/312]  eta: 0:00:02  lr: 0.000062  min_lr: 0.000062  loss: 1.9504 (1.8114)  weight_decay: 0.0500 (0.0500)  time: 1.0019  data: 0.0001  max mem: 78493
Epoch: [277]  [311/312]  eta: 0:00:01  lr: 0.000062  min_lr: 0.000062  loss: 1.8177 (1.8099)  weight_decay: 0.0500 (0.0500)  time: 1.0019  data: 0.0001  max mem: 78493
Epoch: [277] Total time: 0:05:33 (1.0685 s / it)
Averaged stats: lr: 0.000062  min_lr: 0.000062  loss: 1.8177 (1.8476)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:11  loss: 0.4907 (0.4907)  acc1: 87.5000 (87.5000)  acc5: 97.9167 (97.9167)  time: 7.9469  data: 7.6852  max mem: 78493
Test:  [8/9]  eta: 0:00:01  loss: 0.7319 (0.6728)  acc1: 81.9010 (81.7120)  acc5: 96.3542 (95.9840)  time: 1.0873  data: 0.8540  max mem: 78493
Test: Total time: 0:00:09 (1.1108 s / it)
* Acc@1 82.454 Acc@5 96.084 loss 0.658
Accuracy of the model on the 50000 test images: 82.5%
Max accuracy: 82.51%
Epoch: [278]  [  0/312]  eta: 1:26:18  lr: 0.000062  min_lr: 0.000062  loss: 1.1398 (1.1398)  weight_decay: 0.0500 (0.0500)  time: 16.5969  data: 11.6126  max mem: 78493
Epoch: [278]  [ 10/312]  eta: 0:13:55  lr: 0.000061  min_lr: 0.000061  loss: 1.9936 (1.8326)  weight_decay: 0.0500 (0.0500)  time: 2.7655  data: 1.2860  max mem: 78493
Epoch: [278]  [ 20/312]  eta: 0:09:22  lr: 0.000061  min_lr: 0.000061  loss: 1.8921 (1.7952)  weight_decay: 0.0500 (0.0500)  time: 1.1941  data: 0.1269  max mem: 78493
Epoch: [278]  [ 30/312]  eta: 0:07:40  lr: 0.000061  min_lr: 0.000061  loss: 1.7800 (1.7970)  weight_decay: 0.0500 (0.0500)  time: 1.0085  data: 0.0004  max mem: 78493
Epoch: [278]  [ 40/312]  eta: 0:06:42  lr: 0.000061  min_lr: 0.000061  loss: 1.7683 (1.7672)  weight_decay: 0.0500 (0.0500)  time: 1.0076  data: 0.0004  max mem: 78493
Epoch: [278]  [ 50/312]  eta: 0:06:03  lr: 0.000061  min_lr: 0.000061  loss: 1.9231 (1.8049)  weight_decay: 0.0500 (0.0500)  time: 1.0065  data: 0.0004  max mem: 78493
Epoch: [278]  [ 60/312]  eta: 0:05:33  lr: 0.000061  min_lr: 0.000061  loss: 1.9914 (1.8242)  weight_decay: 0.0500 (0.0500)  time: 1.0104  data: 0.0004  max mem: 78493
Epoch: [278]  [ 70/312]  eta: 0:05:09  lr: 0.000060  min_lr: 0.000060  loss: 1.7613 (1.7881)  weight_decay: 0.0500 (0.0500)  time: 1.0094  data: 0.0004  max mem: 78493
Epoch: [278]  [ 80/312]  eta: 0:04:49  lr: 0.000060  min_lr: 0.000060  loss: 1.7613 (1.8079)  weight_decay: 0.0500 (0.0500)  time: 1.0081  data: 0.0005  max mem: 78493
Epoch: [278]  [ 90/312]  eta: 0:04:30  lr: 0.000060  min_lr: 0.000060  loss: 1.9604 (1.8188)  weight_decay: 0.0500 (0.0500)  time: 1.0066  data: 0.0005  max mem: 78493
Epoch: [278]  [100/312]  eta: 0:04:14  lr: 0.000060  min_lr: 0.000060  loss: 1.9604 (1.8269)  weight_decay: 0.0500 (0.0500)  time: 1.0071  data: 0.0005  max mem: 78493
Epoch: [278]  [110/312]  eta: 0:03:58  lr: 0.000060  min_lr: 0.000060  loss: 2.0160 (1.8378)  weight_decay: 0.0500 (0.0500)  time: 1.0066  data: 0.0005  max mem: 78493
Epoch: [278]  [120/312]  eta: 0:03:44  lr: 0.000060  min_lr: 0.000060  loss: 1.7601 (1.8222)  weight_decay: 0.0500 (0.0500)  time: 1.0052  data: 0.0004  max mem: 78493
Epoch: [278]  [130/312]  eta: 0:03:30  lr: 0.000059  min_lr: 0.000059  loss: 1.7439 (1.8255)  weight_decay: 0.0500 (0.0500)  time: 1.0065  data: 0.0004  max mem: 78493
Epoch: [278]  [140/312]  eta: 0:03:16  lr: 0.000059  min_lr: 0.000059  loss: 1.9673 (1.8283)  weight_decay: 0.0500 (0.0500)  time: 1.0054  data: 0.0004  max mem: 78493
Epoch: [278]  [150/312]  eta: 0:03:03  lr: 0.000059  min_lr: 0.000059  loss: 1.8708 (1.8311)  weight_decay: 0.0500 (0.0500)  time: 1.0062  data: 0.0004  max mem: 78493
Epoch: [278]  [160/312]  eta: 0:02:51  lr: 0.000059  min_lr: 0.000059  loss: 1.9517 (1.8387)  weight_decay: 0.0500 (0.0500)  time: 1.0069  data: 0.0004  max mem: 78493
Epoch: [278]  [170/312]  eta: 0:02:39  lr: 0.000059  min_lr: 0.000059  loss: 2.0126 (1.8470)  weight_decay: 0.0500 (0.0500)  time: 1.0057  data: 0.0005  max mem: 78493
Epoch: [278]  [180/312]  eta: 0:02:27  lr: 0.000058  min_lr: 0.000058  loss: 1.9256 (1.8500)  weight_decay: 0.0500 (0.0500)  time: 1.0078  data: 0.0012  max mem: 78493
Epoch: [278]  [190/312]  eta: 0:02:15  lr: 0.000058  min_lr: 0.000058  loss: 1.9139 (1.8529)  weight_decay: 0.0500 (0.0500)  time: 1.0088  data: 0.0012  max mem: 78493
Epoch: [278]  [200/312]  eta: 0:02:03  lr: 0.000058  min_lr: 0.000058  loss: 1.9697 (1.8594)  weight_decay: 0.0500 (0.0500)  time: 1.0081  data: 0.0004  max mem: 78493
Epoch: [278]  [210/312]  eta: 0:01:52  lr: 0.000058  min_lr: 0.000058  loss: 1.9603 (1.8570)  weight_decay: 0.0500 (0.0500)  time: 1.0082  data: 0.0004  max mem: 78493
Epoch: [278]  [220/312]  eta: 0:01:40  lr: 0.000058  min_lr: 0.000058  loss: 1.7026 (1.8498)  weight_decay: 0.0500 (0.0500)  time: 1.0057  data: 0.0004  max mem: 78493
Epoch: [278]  [230/312]  eta: 0:01:29  lr: 0.000058  min_lr: 0.000058  loss: 1.6806 (1.8469)  weight_decay: 0.0500 (0.0500)  time: 1.0049  data: 0.0004  max mem: 78493
Epoch: [278]  [240/312]  eta: 0:01:18  lr: 0.000057  min_lr: 0.000057  loss: 1.9411 (1.8550)  weight_decay: 0.0500 (0.0500)  time: 1.0055  data: 0.0004  max mem: 78493
Epoch: [278]  [250/312]  eta: 0:01:07  lr: 0.000057  min_lr: 0.000057  loss: 2.0802 (1.8600)  weight_decay: 0.0500 (0.0500)  time: 1.0055  data: 0.0005  max mem: 78493
Epoch: [278]  [260/312]  eta: 0:00:56  lr: 0.000057  min_lr: 0.000057  loss: 2.0094 (1.8602)  weight_decay: 0.0500 (0.0500)  time: 1.0050  data: 0.0004  max mem: 78493
Epoch: [278]  [270/312]  eta: 0:00:45  lr: 0.000057  min_lr: 0.000057  loss: 1.8390 (1.8559)  weight_decay: 0.0500 (0.0500)  time: 1.0046  data: 0.0004  max mem: 78493
Epoch: [278]  [280/312]  eta: 0:00:34  lr: 0.000057  min_lr: 0.000057  loss: 1.6674 (1.8470)  weight_decay: 0.0500 (0.0500)  time: 1.0064  data: 0.0010  max mem: 78493
Epoch: [278]  [290/312]  eta: 0:00:23  lr: 0.000057  min_lr: 0.000057  loss: 1.7168 (1.8436)  weight_decay: 0.0500 (0.0500)  time: 1.0047  data: 0.0009  max mem: 78493
Epoch: [278]  [300/312]  eta: 0:00:12  lr: 0.000056  min_lr: 0.000056  loss: 1.8802 (1.8471)  weight_decay: 0.0500 (0.0500)  time: 1.0014  data: 0.0002  max mem: 78493
Epoch: [278]  [310/312]  eta: 0:00:02  lr: 0.000056  min_lr: 0.000056  loss: 1.9341 (1.8475)  weight_decay: 0.0500 (0.0500)  time: 1.0011  data: 0.0002  max mem: 78493
Epoch: [278]  [311/312]  eta: 0:00:01  lr: 0.000056  min_lr: 0.000056  loss: 1.9341 (1.8483)  weight_decay: 0.0500 (0.0500)  time: 1.0011  data: 0.0002  max mem: 78493
Epoch: [278] Total time: 0:05:35 (1.0739 s / it)
Averaged stats: lr: 0.000056  min_lr: 0.000056  loss: 1.9341 (1.8517)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:10  loss: 0.4890 (0.4890)  acc1: 87.5000 (87.5000)  acc5: 97.7865 (97.7865)  time: 7.8756  data: 7.5924  max mem: 78493
Test:  [8/9]  eta: 0:00:01  loss: 0.7363 (0.6738)  acc1: 82.0312 (81.9200)  acc5: 96.2240 (96.0000)  time: 1.1100  data: 0.8803  max mem: 78493
Test: Total time: 0:00:10 (1.1348 s / it)
* Acc@1 82.448 Acc@5 96.038 loss 0.660
Accuracy of the model on the 50000 test images: 82.4%
Max accuracy: 82.51%
Epoch: [279]  [  0/312]  eta: 1:25:18  lr: 0.000056  min_lr: 0.000056  loss: 1.5955 (1.5955)  weight_decay: 0.0500 (0.0500)  time: 16.4045  data: 14.0561  max mem: 78493
Epoch: [279]  [ 10/312]  eta: 0:13:37  lr: 0.000056  min_lr: 0.000056  loss: 1.6070 (1.6333)  weight_decay: 0.0500 (0.0500)  time: 2.7062  data: 1.2913  max mem: 78493
Epoch: [279]  [ 20/312]  eta: 0:09:14  lr: 0.000056  min_lr: 0.000056  loss: 1.7926 (1.7674)  weight_decay: 0.0500 (0.0500)  time: 1.1721  data: 0.0077  max mem: 78493
Epoch: [279]  [ 30/312]  eta: 0:07:34  lr: 0.000056  min_lr: 0.000056  loss: 1.8741 (1.7709)  weight_decay: 0.0500 (0.0500)  time: 1.0074  data: 0.0013  max mem: 78493
Epoch: [279]  [ 40/312]  eta: 0:06:38  lr: 0.000056  min_lr: 0.000056  loss: 1.7322 (1.7682)  weight_decay: 0.0500 (0.0500)  time: 1.0096  data: 0.0015  max mem: 78493
Epoch: [279]  [ 50/312]  eta: 0:06:00  lr: 0.000055  min_lr: 0.000055  loss: 1.8142 (1.7782)  weight_decay: 0.0500 (0.0500)  time: 1.0098  data: 0.0008  max mem: 78493
Epoch: [279]  [ 60/312]  eta: 0:05:31  lr: 0.000055  min_lr: 0.000055  loss: 1.7626 (1.7776)  weight_decay: 0.0500 (0.0500)  time: 1.0067  data: 0.0008  max mem: 78493
Epoch: [279]  [ 70/312]  eta: 0:05:07  lr: 0.000055  min_lr: 0.000055  loss: 1.9290 (1.8026)  weight_decay: 0.0500 (0.0500)  time: 1.0077  data: 0.0008  max mem: 78493
Epoch: [279]  [ 80/312]  eta: 0:04:47  lr: 0.000055  min_lr: 0.000055  loss: 2.0594 (1.8125)  weight_decay: 0.0500 (0.0500)  time: 1.0099  data: 0.0008  max mem: 78493
Epoch: [279]  [ 90/312]  eta: 0:04:29  lr: 0.000055  min_lr: 0.000055  loss: 1.8151 (1.7976)  weight_decay: 0.0500 (0.0500)  time: 1.0102  data: 0.0008  max mem: 78493
Epoch: [279]  [100/312]  eta: 0:04:13  lr: 0.000055  min_lr: 0.000055  loss: 1.7696 (1.8014)  weight_decay: 0.0500 (0.0500)  time: 1.0088  data: 0.0008  max mem: 78493
Epoch: [279]  [110/312]  eta: 0:03:57  lr: 0.000054  min_lr: 0.000054  loss: 1.8052 (1.8028)  weight_decay: 0.0500 (0.0500)  time: 1.0078  data: 0.0008  max mem: 78493
Epoch: [279]  [120/312]  eta: 0:03:43  lr: 0.000054  min_lr: 0.000054  loss: 1.8286 (1.7992)  weight_decay: 0.0500 (0.0500)  time: 1.0065  data: 0.0008  max mem: 78493
Epoch: [279]  [130/312]  eta: 0:03:29  lr: 0.000054  min_lr: 0.000054  loss: 1.9101 (1.8075)  weight_decay: 0.0500 (0.0500)  time: 1.0088  data: 0.0008  max mem: 78493
Epoch: [279]  [140/312]  eta: 0:03:16  lr: 0.000054  min_lr: 0.000054  loss: 1.9532 (1.8232)  weight_decay: 0.0500 (0.0500)  time: 1.0100  data: 0.0008  max mem: 78493
Epoch: [279]  [150/312]  eta: 0:03:03  lr: 0.000054  min_lr: 0.000054  loss: 2.0224 (1.8288)  weight_decay: 0.0500 (0.0500)  time: 1.0074  data: 0.0020  max mem: 78493
Epoch: [279]  [160/312]  eta: 0:02:50  lr: 0.000054  min_lr: 0.000054  loss: 1.8598 (1.8203)  weight_decay: 0.0500 (0.0500)  time: 1.0075  data: 0.0026  max mem: 78493
Epoch: [279]  [170/312]  eta: 0:02:38  lr: 0.000053  min_lr: 0.000053  loss: 1.6454 (1.8197)  weight_decay: 0.0500 (0.0500)  time: 1.0089  data: 0.0014  max mem: 78493
Epoch: [279]  [180/312]  eta: 0:02:26  lr: 0.000053  min_lr: 0.000053  loss: 1.8033 (1.8211)  weight_decay: 0.0500 (0.0500)  time: 1.0079  data: 0.0008  max mem: 78493
Epoch: [279]  [190/312]  eta: 0:02:14  lr: 0.000053  min_lr: 0.000053  loss: 1.8322 (1.8264)  weight_decay: 0.0500 (0.0500)  time: 1.0057  data: 0.0008  max mem: 78493
Epoch: [279]  [200/312]  eta: 0:02:03  lr: 0.000053  min_lr: 0.000053  loss: 2.0188 (1.8339)  weight_decay: 0.0500 (0.0500)  time: 1.0069  data: 0.0008  max mem: 78493
Epoch: [279]  [210/312]  eta: 0:01:51  lr: 0.000053  min_lr: 0.000053  loss: 2.0188 (1.8406)  weight_decay: 0.0500 (0.0500)  time: 1.0064  data: 0.0008  max mem: 78493
Epoch: [279]  [220/312]  eta: 0:01:40  lr: 0.000053  min_lr: 0.000053  loss: 2.0321 (1.8466)  weight_decay: 0.0500 (0.0500)  time: 1.0062  data: 0.0008  max mem: 78493
Epoch: [279]  [230/312]  eta: 0:01:29  lr: 0.000052  min_lr: 0.000052  loss: 1.9595 (1.8402)  weight_decay: 0.0500 (0.0500)  time: 1.0070  data: 0.0008  max mem: 78493
Epoch: [279]  [240/312]  eta: 0:01:18  lr: 0.000052  min_lr: 0.000052  loss: 1.9286 (1.8414)  weight_decay: 0.0500 (0.0500)  time: 1.0064  data: 0.0008  max mem: 78493
Epoch: [279]  [250/312]  eta: 0:01:07  lr: 0.000052  min_lr: 0.000052  loss: 1.9114 (1.8393)  weight_decay: 0.0500 (0.0500)  time: 1.0058  data: 0.0008  max mem: 78493
Epoch: [279]  [260/312]  eta: 0:00:56  lr: 0.000052  min_lr: 0.000052  loss: 1.9114 (1.8437)  weight_decay: 0.0500 (0.0500)  time: 1.0057  data: 0.0008  max mem: 78493
Epoch: [279]  [270/312]  eta: 0:00:45  lr: 0.000052  min_lr: 0.000052  loss: 1.9779 (1.8451)  weight_decay: 0.0500 (0.0500)  time: 1.0059  data: 0.0018  max mem: 78493
Epoch: [279]  [280/312]  eta: 0:00:34  lr: 0.000052  min_lr: 0.000052  loss: 1.8135 (1.8464)  weight_decay: 0.0500 (0.0500)  time: 1.0059  data: 0.0024  max mem: 78493
Epoch: [279]  [290/312]  eta: 0:00:23  lr: 0.000051  min_lr: 0.000051  loss: 1.8829 (1.8472)  weight_decay: 0.0500 (0.0500)  time: 1.0043  data: 0.0011  max mem: 78493
Epoch: [279]  [300/312]  eta: 0:00:12  lr: 0.000051  min_lr: 0.000051  loss: 1.9056 (1.8460)  weight_decay: 0.0500 (0.0500)  time: 1.0023  data: 0.0001  max mem: 78493
Epoch: [279]  [310/312]  eta: 0:00:02  lr: 0.000051  min_lr: 0.000051  loss: 1.9367 (1.8498)  weight_decay: 0.0500 (0.0500)  time: 1.0023  data: 0.0001  max mem: 78493
Epoch: [279]  [311/312]  eta: 0:00:01  lr: 0.000051  min_lr: 0.000051  loss: 1.9056 (1.8485)  weight_decay: 0.0500 (0.0500)  time: 1.0022  data: 0.0001  max mem: 78493
Epoch: [279] Total time: 0:05:34 (1.0726 s / it)
Averaged stats: lr: 0.000051  min_lr: 0.000051  loss: 1.9056 (1.8478)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:09  loss: 0.4894 (0.4894)  acc1: 87.2396 (87.2396)  acc5: 97.7865 (97.7865)  time: 7.7488  data: 7.4750  max mem: 78493
Test:  [8/9]  eta: 0:00:01  loss: 0.7212 (0.6683)  acc1: 81.7708 (81.9520)  acc5: 96.6146 (96.0640)  time: 1.0943  data: 0.8655  max mem: 78493
Test: Total time: 0:00:10 (1.1119 s / it)
* Acc@1 82.470 Acc@5 96.108 loss 0.657
Accuracy of the model on the 50000 test images: 82.5%
Max accuracy: 82.51%
Epoch: [280]  [  0/312]  eta: 1:19:00  lr: 0.000051  min_lr: 0.000051  loss: 2.2767 (2.2767)  weight_decay: 0.0500 (0.0500)  time: 15.1934  data: 12.5351  max mem: 78493
Epoch: [280]  [ 10/312]  eta: 0:13:46  lr: 0.000051  min_lr: 0.000051  loss: 2.1148 (1.9794)  weight_decay: 0.0500 (0.0500)  time: 2.7375  data: 1.2833  max mem: 78493
Epoch: [280]  [ 20/312]  eta: 0:09:18  lr: 0.000051  min_lr: 0.000051  loss: 1.9012 (1.8825)  weight_decay: 0.0500 (0.0500)  time: 1.2501  data: 0.0793  max mem: 78493
Epoch: [280]  [ 30/312]  eta: 0:07:37  lr: 0.000051  min_lr: 0.000051  loss: 1.9012 (1.8751)  weight_decay: 0.0500 (0.0500)  time: 1.0088  data: 0.0004  max mem: 78493
Epoch: [280]  [ 40/312]  eta: 0:06:40  lr: 0.000050  min_lr: 0.000050  loss: 1.8472 (1.8526)  weight_decay: 0.0500 (0.0500)  time: 1.0070  data: 0.0004  max mem: 78493
Epoch: [280]  [ 50/312]  eta: 0:06:01  lr: 0.000050  min_lr: 0.000050  loss: 1.8472 (1.8333)  weight_decay: 0.0500 (0.0500)  time: 1.0065  data: 0.0005  max mem: 78493
Epoch: [280]  [ 60/312]  eta: 0:05:32  lr: 0.000050  min_lr: 0.000050  loss: 1.8391 (1.8334)  weight_decay: 0.0500 (0.0500)  time: 1.0080  data: 0.0005  max mem: 78493
Epoch: [280]  [ 70/312]  eta: 0:05:08  lr: 0.000050  min_lr: 0.000050  loss: 1.8411 (1.8357)  weight_decay: 0.0500 (0.0500)  time: 1.0060  data: 0.0004  max mem: 78493
Epoch: [280]  [ 80/312]  eta: 0:04:48  lr: 0.000050  min_lr: 0.000050  loss: 1.9173 (1.8160)  weight_decay: 0.0500 (0.0500)  time: 1.0051  data: 0.0004  max mem: 78493
Epoch: [280]  [ 90/312]  eta: 0:04:29  lr: 0.000050  min_lr: 0.000050  loss: 1.8269 (1.8279)  weight_decay: 0.0500 (0.0500)  time: 1.0063  data: 0.0004  max mem: 78493
Epoch: [280]  [100/312]  eta: 0:04:13  lr: 0.000050  min_lr: 0.000050  loss: 1.9193 (1.8340)  weight_decay: 0.0500 (0.0500)  time: 1.0059  data: 0.0004  max mem: 78493
Epoch: [280]  [110/312]  eta: 0:03:58  lr: 0.000049  min_lr: 0.000049  loss: 1.7808 (1.8226)  weight_decay: 0.0500 (0.0500)  time: 1.0065  data: 0.0005  max mem: 78493
Epoch: [280]  [120/312]  eta: 0:03:43  lr: 0.000049  min_lr: 0.000049  loss: 1.7262 (1.8178)  weight_decay: 0.0500 (0.0500)  time: 1.0075  data: 0.0005  max mem: 78493
Epoch: [280]  [130/312]  eta: 0:03:29  lr: 0.000049  min_lr: 0.000049  loss: 1.8841 (1.8251)  weight_decay: 0.0500 (0.0500)  time: 1.0073  data: 0.0004  max mem: 78493
Epoch: [280]  [140/312]  eta: 0:03:16  lr: 0.000049  min_lr: 0.000049  loss: 1.9382 (1.8322)  weight_decay: 0.0500 (0.0500)  time: 1.0060  data: 0.0004  max mem: 78493
Epoch: [280]  [150/312]  eta: 0:03:03  lr: 0.000049  min_lr: 0.000049  loss: 1.7477 (1.8146)  weight_decay: 0.0500 (0.0500)  time: 1.0074  data: 0.0004  max mem: 78493
Epoch: [280]  [160/312]  eta: 0:02:51  lr: 0.000049  min_lr: 0.000049  loss: 1.6639 (1.8164)  weight_decay: 0.0500 (0.0500)  time: 1.0082  data: 0.0004  max mem: 78493
Epoch: [280]  [170/312]  eta: 0:02:38  lr: 0.000048  min_lr: 0.000048  loss: 1.9146 (1.8267)  weight_decay: 0.0500 (0.0500)  time: 1.0087  data: 0.0004  max mem: 78493
Epoch: [280]  [180/312]  eta: 0:02:26  lr: 0.000048  min_lr: 0.000048  loss: 1.9242 (1.8260)  weight_decay: 0.0500 (0.0500)  time: 1.0097  data: 0.0004  max mem: 78493
Epoch: [280]  [190/312]  eta: 0:02:15  lr: 0.000048  min_lr: 0.000048  loss: 1.9242 (1.8277)  weight_decay: 0.0500 (0.0500)  time: 1.0067  data: 0.0005  max mem: 78493
Epoch: [280]  [200/312]  eta: 0:02:03  lr: 0.000048  min_lr: 0.000048  loss: 1.8278 (1.8283)  weight_decay: 0.0500 (0.0500)  time: 1.0050  data: 0.0005  max mem: 78493
Epoch: [280]  [210/312]  eta: 0:01:51  lr: 0.000048  min_lr: 0.000048  loss: 1.8834 (1.8343)  weight_decay: 0.0500 (0.0500)  time: 1.0065  data: 0.0004  max mem: 78493
Epoch: [280]  [220/312]  eta: 0:01:40  lr: 0.000048  min_lr: 0.000048  loss: 2.0130 (1.8395)  weight_decay: 0.0500 (0.0500)  time: 1.0081  data: 0.0004  max mem: 78493
Epoch: [280]  [230/312]  eta: 0:01:29  lr: 0.000048  min_lr: 0.000048  loss: 1.9678 (1.8384)  weight_decay: 0.0500 (0.0500)  time: 1.0072  data: 0.0005  max mem: 78493
Epoch: [280]  [240/312]  eta: 0:01:18  lr: 0.000047  min_lr: 0.000047  loss: 1.8388 (1.8361)  weight_decay: 0.0500 (0.0500)  time: 1.0061  data: 0.0012  max mem: 78493
Epoch: [280]  [250/312]  eta: 0:01:07  lr: 0.000047  min_lr: 0.000047  loss: 1.9660 (1.8404)  weight_decay: 0.0500 (0.0500)  time: 1.0077  data: 0.0011  max mem: 78493
Epoch: [280]  [260/312]  eta: 0:00:56  lr: 0.000047  min_lr: 0.000047  loss: 1.9055 (1.8336)  weight_decay: 0.0500 (0.0500)  time: 1.0073  data: 0.0005  max mem: 78493
Epoch: [280]  [270/312]  eta: 0:00:45  lr: 0.000047  min_lr: 0.000047  loss: 1.8868 (1.8397)  weight_decay: 0.0500 (0.0500)  time: 1.0049  data: 0.0005  max mem: 78493
Epoch: [280]  [280/312]  eta: 0:00:34  lr: 0.000047  min_lr: 0.000047  loss: 1.9568 (1.8365)  weight_decay: 0.0500 (0.0500)  time: 1.0068  data: 0.0011  max mem: 78493
Epoch: [280]  [290/312]  eta: 0:00:23  lr: 0.000047  min_lr: 0.000047  loss: 1.7851 (1.8351)  weight_decay: 0.0500 (0.0500)  time: 1.0054  data: 0.0009  max mem: 78493
Epoch: [280]  [300/312]  eta: 0:00:12  lr: 0.000046  min_lr: 0.000046  loss: 1.8754 (1.8353)  weight_decay: 0.0500 (0.0500)  time: 1.0019  data: 0.0001  max mem: 78493
Epoch: [280]  [310/312]  eta: 0:00:02  lr: 0.000046  min_lr: 0.000046  loss: 1.8421 (1.8329)  weight_decay: 0.0500 (0.0500)  time: 1.0017  data: 0.0001  max mem: 78493
Epoch: [280]  [311/312]  eta: 0:00:01  lr: 0.000046  min_lr: 0.000046  loss: 1.8421 (1.8333)  weight_decay: 0.0500 (0.0500)  time: 1.0017  data: 0.0001  max mem: 78493
Epoch: [280] Total time: 0:05:34 (1.0734 s / it)
Averaged stats: lr: 0.000046  min_lr: 0.000046  loss: 1.8421 (1.8469)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:12  loss: 0.4856 (0.4856)  acc1: 87.6302 (87.6302)  acc5: 97.7865 (97.7865)  time: 8.0976  data: 7.8258  max mem: 78493
Test:  [8/9]  eta: 0:00:01  loss: 0.7277 (0.6682)  acc1: 82.1615 (82.0480)  acc5: 95.9635 (96.0000)  time: 1.0979  data: 0.8696  max mem: 78493
Test: Total time: 0:00:09 (1.1084 s / it)
* Acc@1 82.548 Acc@5 96.060 loss 0.655
Accuracy of the model on the 50000 test images: 82.5%
Max accuracy: 82.55%
Epoch: [281]  [  0/312]  eta: 1:35:14  lr: 0.000046  min_lr: 0.000046  loss: 1.8171 (1.8171)  weight_decay: 0.0500 (0.0500)  time: 18.3152  data: 17.0653  max mem: 78493
Epoch: [281]  [ 10/312]  eta: 0:14:07  lr: 0.000046  min_lr: 0.000046  loss: 1.7266 (1.7265)  weight_decay: 0.0500 (0.0500)  time: 2.8069  data: 1.5520  max mem: 78493
Epoch: [281]  [ 20/312]  eta: 0:09:29  lr: 0.000046  min_lr: 0.000046  loss: 1.7899 (1.7611)  weight_decay: 0.0500 (0.0500)  time: 1.1317  data: 0.0006  max mem: 78493
Epoch: [281]  [ 30/312]  eta: 0:07:43  lr: 0.000046  min_lr: 0.000046  loss: 1.8958 (1.8201)  weight_decay: 0.0500 (0.0500)  time: 1.0064  data: 0.0004  max mem: 78493
Epoch: [281]  [ 40/312]  eta: 0:06:45  lr: 0.000046  min_lr: 0.000046  loss: 1.9518 (1.8195)  weight_decay: 0.0500 (0.0500)  time: 1.0083  data: 0.0004  max mem: 78493
Epoch: [281]  [ 50/312]  eta: 0:06:05  lr: 0.000046  min_lr: 0.000046  loss: 1.9405 (1.8231)  weight_decay: 0.0500 (0.0500)  time: 1.0105  data: 0.0005  max mem: 78493
Epoch: [281]  [ 60/312]  eta: 0:05:35  lr: 0.000045  min_lr: 0.000045  loss: 1.9265 (1.8237)  weight_decay: 0.0500 (0.0500)  time: 1.0089  data: 0.0005  max mem: 78493
Epoch: [281]  [ 70/312]  eta: 0:05:11  lr: 0.000045  min_lr: 0.000045  loss: 1.7002 (1.8149)  weight_decay: 0.0500 (0.0500)  time: 1.0074  data: 0.0005  max mem: 78493
Epoch: [281]  [ 80/312]  eta: 0:04:50  lr: 0.000045  min_lr: 0.000045  loss: 1.7797 (1.8243)  weight_decay: 0.0500 (0.0500)  time: 1.0074  data: 0.0005  max mem: 78493
Epoch: [281]  [ 90/312]  eta: 0:04:32  lr: 0.000045  min_lr: 0.000045  loss: 2.0053 (1.8422)  weight_decay: 0.0500 (0.0500)  time: 1.0082  data: 0.0005  max mem: 78493
Epoch: [281]  [100/312]  eta: 0:04:15  lr: 0.000045  min_lr: 0.000045  loss: 2.0566 (1.8465)  weight_decay: 0.0500 (0.0500)  time: 1.0078  data: 0.0004  max mem: 78493
Epoch: [281]  [110/312]  eta: 0:03:59  lr: 0.000045  min_lr: 0.000045  loss: 2.0103 (1.8440)  weight_decay: 0.0500 (0.0500)  time: 1.0080  data: 0.0004  max mem: 78493
Epoch: [281]  [120/312]  eta: 0:03:44  lr: 0.000044  min_lr: 0.000044  loss: 1.9965 (1.8434)  weight_decay: 0.0500 (0.0500)  time: 1.0075  data: 0.0005  max mem: 78493
Epoch: [281]  [130/312]  eta: 0:03:30  lr: 0.000044  min_lr: 0.000044  loss: 1.8714 (1.8451)  weight_decay: 0.0500 (0.0500)  time: 1.0065  data: 0.0004  max mem: 78493
Epoch: [281]  [140/312]  eta: 0:03:17  lr: 0.000044  min_lr: 0.000044  loss: 1.8281 (1.8458)  weight_decay: 0.0500 (0.0500)  time: 1.0074  data: 0.0004  max mem: 78493
Epoch: [281]  [150/312]  eta: 0:03:04  lr: 0.000044  min_lr: 0.000044  loss: 1.7640 (1.8370)  weight_decay: 0.0500 (0.0500)  time: 1.0072  data: 0.0004  max mem: 78493
Epoch: [281]  [160/312]  eta: 0:02:51  lr: 0.000044  min_lr: 0.000044  loss: 1.8078 (1.8359)  weight_decay: 0.0500 (0.0500)  time: 1.0068  data: 0.0004  max mem: 78493
Epoch: [281]  [170/312]  eta: 0:02:39  lr: 0.000044  min_lr: 0.000044  loss: 1.8078 (1.8301)  weight_decay: 0.0500 (0.0500)  time: 1.0079  data: 0.0004  max mem: 78493
Epoch: [281]  [180/312]  eta: 0:02:27  lr: 0.000044  min_lr: 0.000044  loss: 1.8646 (1.8334)  weight_decay: 0.0500 (0.0500)  time: 1.0076  data: 0.0004  max mem: 78493
Epoch: [281]  [190/312]  eta: 0:02:15  lr: 0.000043  min_lr: 0.000043  loss: 1.8646 (1.8316)  weight_decay: 0.0500 (0.0500)  time: 1.0090  data: 0.0005  max mem: 78493
Epoch: [281]  [200/312]  eta: 0:02:03  lr: 0.000043  min_lr: 0.000043  loss: 1.9089 (1.8340)  weight_decay: 0.0500 (0.0500)  time: 1.0093  data: 0.0005  max mem: 78493
Epoch: [281]  [210/312]  eta: 0:01:52  lr: 0.000043  min_lr: 0.000043  loss: 1.9370 (1.8392)  weight_decay: 0.0500 (0.0500)  time: 1.0067  data: 0.0013  max mem: 78493
Epoch: [281]  [220/312]  eta: 0:01:40  lr: 0.000043  min_lr: 0.000043  loss: 2.0059 (1.8441)  weight_decay: 0.0500 (0.0500)  time: 1.0059  data: 0.0013  max mem: 78493
Epoch: [281]  [230/312]  eta: 0:01:29  lr: 0.000043  min_lr: 0.000043  loss: 2.0335 (1.8439)  weight_decay: 0.0500 (0.0500)  time: 1.0059  data: 0.0004  max mem: 78493
Epoch: [281]  [240/312]  eta: 0:01:18  lr: 0.000043  min_lr: 0.000043  loss: 1.6428 (1.8346)  weight_decay: 0.0500 (0.0500)  time: 1.0071  data: 0.0004  max mem: 78493
Epoch: [281]  [250/312]  eta: 0:01:07  lr: 0.000043  min_lr: 0.000043  loss: 1.7192 (1.8349)  weight_decay: 0.0500 (0.0500)  time: 1.0086  data: 0.0004  max mem: 78493
Epoch: [281]  [260/312]  eta: 0:00:56  lr: 0.000042  min_lr: 0.000042  loss: 1.9055 (1.8368)  weight_decay: 0.0500 (0.0500)  time: 1.0074  data: 0.0005  max mem: 78493
Epoch: [281]  [270/312]  eta: 0:00:45  lr: 0.000042  min_lr: 0.000042  loss: 1.8970 (1.8335)  weight_decay: 0.0500 (0.0500)  time: 1.0051  data: 0.0004  max mem: 78493
Epoch: [281]  [280/312]  eta: 0:00:34  lr: 0.000042  min_lr: 0.000042  loss: 1.8391 (1.8345)  weight_decay: 0.0500 (0.0500)  time: 1.0066  data: 0.0010  max mem: 78493
Epoch: [281]  [290/312]  eta: 0:00:23  lr: 0.000042  min_lr: 0.000042  loss: 1.9794 (1.8400)  weight_decay: 0.0500 (0.0500)  time: 1.0049  data: 0.0009  max mem: 78493
Epoch: [281]  [300/312]  eta: 0:00:12  lr: 0.000042  min_lr: 0.000042  loss: 1.9055 (1.8335)  weight_decay: 0.0500 (0.0500)  time: 1.0015  data: 0.0001  max mem: 78493
Epoch: [281]  [310/312]  eta: 0:00:02  lr: 0.000042  min_lr: 0.000042  loss: 1.9885 (1.8410)  weight_decay: 0.0500 (0.0500)  time: 1.0016  data: 0.0001  max mem: 78493
Epoch: [281]  [311/312]  eta: 0:00:01  lr: 0.000042  min_lr: 0.000042  loss: 2.0080 (1.8417)  weight_decay: 0.0500 (0.0500)  time: 1.0016  data: 0.0001  max mem: 78493
Epoch: [281] Total time: 0:05:35 (1.0761 s / it)
Averaged stats: lr: 0.000042  min_lr: 0.000042  loss: 2.0080 (1.8373)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:15  loss: 0.4831 (0.4831)  acc1: 87.6302 (87.6302)  acc5: 97.7865 (97.7865)  time: 8.3627  data: 8.0853  max mem: 78493
Test:  [8/9]  eta: 0:00:01  loss: 0.7225 (0.6692)  acc1: 82.5521 (82.0800)  acc5: 96.0938 (95.9520)  time: 1.1275  data: 0.8985  max mem: 78493
Test: Total time: 0:00:10 (1.1502 s / it)
* Acc@1 82.518 Acc@5 96.082 loss 0.655
Accuracy of the model on the 50000 test images: 82.5%
Max accuracy: 82.55%
Epoch: [282]  [  0/312]  eta: 1:25:54  lr: 0.000042  min_lr: 0.000042  loss: 2.0315 (2.0315)  weight_decay: 0.0500 (0.0500)  time: 16.5208  data: 14.8340  max mem: 78493
Epoch: [282]  [ 10/312]  eta: 0:12:49  lr: 0.000041  min_lr: 0.000041  loss: 2.0060 (1.9240)  weight_decay: 0.0500 (0.0500)  time: 2.5473  data: 1.3507  max mem: 78493
Epoch: [282]  [ 20/312]  eta: 0:08:54  lr: 0.000041  min_lr: 0.000041  loss: 1.9323 (1.8285)  weight_decay: 0.0500 (0.0500)  time: 1.0951  data: 0.0043  max mem: 78493
Epoch: [282]  [ 30/312]  eta: 0:07:21  lr: 0.000041  min_lr: 0.000041  loss: 1.8358 (1.8156)  weight_decay: 0.0500 (0.0500)  time: 1.0261  data: 0.0044  max mem: 78493
Epoch: [282]  [ 40/312]  eta: 0:06:28  lr: 0.000041  min_lr: 0.000041  loss: 1.8284 (1.7794)  weight_decay: 0.0500 (0.0500)  time: 1.0096  data: 0.0015  max mem: 78493
Epoch: [282]  [ 50/312]  eta: 0:05:52  lr: 0.000041  min_lr: 0.000041  loss: 1.7299 (1.7676)  weight_decay: 0.0500 (0.0500)  time: 1.0056  data: 0.0004  max mem: 78493
Epoch: [282]  [ 60/312]  eta: 0:05:25  lr: 0.000041  min_lr: 0.000041  loss: 1.7697 (1.7865)  weight_decay: 0.0500 (0.0500)  time: 1.0054  data: 0.0004  max mem: 78493
Epoch: [282]  [ 70/312]  eta: 0:05:02  lr: 0.000041  min_lr: 0.000041  loss: 1.8250 (1.7838)  weight_decay: 0.0500 (0.0500)  time: 1.0079  data: 0.0005  max mem: 78493
Epoch: [282]  [ 80/312]  eta: 0:04:43  lr: 0.000040  min_lr: 0.000040  loss: 1.8057 (1.7804)  weight_decay: 0.0500 (0.0500)  time: 1.0063  data: 0.0005  max mem: 78493
Epoch: [282]  [ 90/312]  eta: 0:04:25  lr: 0.000040  min_lr: 0.000040  loss: 1.8310 (1.7947)  weight_decay: 0.0500 (0.0500)  time: 1.0049  data: 0.0004  max mem: 78493
Epoch: [282]  [100/312]  eta: 0:04:09  lr: 0.000040  min_lr: 0.000040  loss: 1.9017 (1.7847)  weight_decay: 0.0500 (0.0500)  time: 1.0057  data: 0.0004  max mem: 78493
Epoch: [282]  [110/312]  eta: 0:03:54  lr: 0.000040  min_lr: 0.000040  loss: 1.7188 (1.7896)  weight_decay: 0.0500 (0.0500)  time: 1.0057  data: 0.0004  max mem: 78493
Epoch: [282]  [120/312]  eta: 0:03:40  lr: 0.000040  min_lr: 0.000040  loss: 1.7674 (1.7860)  weight_decay: 0.0500 (0.0500)  time: 1.0045  data: 0.0005  max mem: 78493
Epoch: [282]  [130/312]  eta: 0:03:27  lr: 0.000040  min_lr: 0.000040  loss: 1.8506 (1.7929)  weight_decay: 0.0500 (0.0500)  time: 1.0045  data: 0.0004  max mem: 78493
Epoch: [282]  [140/312]  eta: 0:03:14  lr: 0.000040  min_lr: 0.000040  loss: 1.9208 (1.7906)  weight_decay: 0.0500 (0.0500)  time: 1.0051  data: 0.0004  max mem: 78493
Epoch: [282]  [150/312]  eta: 0:03:01  lr: 0.000040  min_lr: 0.000040  loss: 1.6805 (1.7841)  weight_decay: 0.0500 (0.0500)  time: 1.0066  data: 0.0004  max mem: 78493
Epoch: [282]  [160/312]  eta: 0:02:49  lr: 0.000039  min_lr: 0.000039  loss: 1.6805 (1.7816)  weight_decay: 0.0500 (0.0500)  time: 1.0082  data: 0.0004  max mem: 78493
Epoch: [282]  [170/312]  eta: 0:02:37  lr: 0.000039  min_lr: 0.000039  loss: 1.9133 (1.7911)  weight_decay: 0.0500 (0.0500)  time: 1.0081  data: 0.0004  max mem: 78493
Epoch: [282]  [180/312]  eta: 0:02:25  lr: 0.000039  min_lr: 0.000039  loss: 1.9067 (1.7877)  weight_decay: 0.0500 (0.0500)  time: 1.0083  data: 0.0004  max mem: 78493
Epoch: [282]  [190/312]  eta: 0:02:13  lr: 0.000039  min_lr: 0.000039  loss: 1.9788 (1.7977)  weight_decay: 0.0500 (0.0500)  time: 1.0072  data: 0.0004  max mem: 78493
Epoch: [282]  [200/312]  eta: 0:02:02  lr: 0.000039  min_lr: 0.000039  loss: 1.9744 (1.7988)  weight_decay: 0.0500 (0.0500)  time: 1.0056  data: 0.0005  max mem: 78493
Epoch: [282]  [210/312]  eta: 0:01:51  lr: 0.000039  min_lr: 0.000039  loss: 1.9291 (1.8078)  weight_decay: 0.0500 (0.0500)  time: 1.0060  data: 0.0005  max mem: 78493
Epoch: [282]  [220/312]  eta: 0:01:39  lr: 0.000039  min_lr: 0.000039  loss: 1.9291 (1.8084)  weight_decay: 0.0500 (0.0500)  time: 1.0060  data: 0.0013  max mem: 78493
Epoch: [282]  [230/312]  eta: 0:01:28  lr: 0.000038  min_lr: 0.000038  loss: 1.7786 (1.8036)  weight_decay: 0.0500 (0.0500)  time: 1.0054  data: 0.0021  max mem: 78493
Epoch: [282]  [240/312]  eta: 0:01:17  lr: 0.000038  min_lr: 0.000038  loss: 1.6414 (1.8016)  weight_decay: 0.0500 (0.0500)  time: 1.0049  data: 0.0012  max mem: 78493
Epoch: [282]  [250/312]  eta: 0:01:06  lr: 0.000038  min_lr: 0.000038  loss: 1.8027 (1.7968)  weight_decay: 0.0500 (0.0500)  time: 1.0046  data: 0.0005  max mem: 78493
Epoch: [282]  [260/312]  eta: 0:00:55  lr: 0.000038  min_lr: 0.000038  loss: 1.7713 (1.7982)  weight_decay: 0.0500 (0.0500)  time: 1.0045  data: 0.0005  max mem: 78493
Epoch: [282]  [270/312]  eta: 0:00:44  lr: 0.000038  min_lr: 0.000038  loss: 1.7319 (1.7987)  weight_decay: 0.0500 (0.0500)  time: 1.0037  data: 0.0005  max mem: 78493
Epoch: [282]  [280/312]  eta: 0:00:34  lr: 0.000038  min_lr: 0.000038  loss: 1.7816 (1.8004)  weight_decay: 0.0500 (0.0500)  time: 1.0064  data: 0.0010  max mem: 78493
Epoch: [282]  [290/312]  eta: 0:00:23  lr: 0.000038  min_lr: 0.000038  loss: 1.9630 (1.8062)  weight_decay: 0.0500 (0.0500)  time: 1.0057  data: 0.0009  max mem: 78493
Epoch: [282]  [300/312]  eta: 0:00:12  lr: 0.000037  min_lr: 0.000037  loss: 2.0388 (1.8112)  weight_decay: 0.0500 (0.0500)  time: 1.0014  data: 0.0001  max mem: 78493
Epoch: [282]  [310/312]  eta: 0:00:02  lr: 0.000037  min_lr: 0.000037  loss: 1.9130 (1.8111)  weight_decay: 0.0500 (0.0500)  time: 1.0007  data: 0.0001  max mem: 78493
Epoch: [282]  [311/312]  eta: 0:00:01  lr: 0.000037  min_lr: 0.000037  loss: 1.8814 (1.8092)  weight_decay: 0.0500 (0.0500)  time: 1.0007  data: 0.0001  max mem: 78493
Epoch: [282] Total time: 0:05:32 (1.0667 s / it)
Averaged stats: lr: 0.000037  min_lr: 0.000037  loss: 1.8814 (1.8329)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:12  loss: 0.4814 (0.4814)  acc1: 88.0208 (88.0208)  acc5: 97.7865 (97.7865)  time: 8.0861  data: 7.8118  max mem: 78493
Test:  [8/9]  eta: 0:00:01  loss: 0.7236 (0.6699)  acc1: 82.2917 (82.0960)  acc5: 96.4844 (95.9840)  time: 1.0980  data: 0.8681  max mem: 78493
Test: Total time: 0:00:10 (1.1434 s / it)
* Acc@1 82.508 Acc@5 96.096 loss 0.655
Accuracy of the model on the 50000 test images: 82.5%
Max accuracy: 82.55%
Epoch: [283]  [  0/312]  eta: 1:28:49  lr: 0.000037  min_lr: 0.000037  loss: 1.2948 (1.2948)  weight_decay: 0.0500 (0.0500)  time: 17.0802  data: 14.3447  max mem: 78493
Epoch: [283]  [ 10/312]  eta: 0:13:17  lr: 0.000037  min_lr: 0.000037  loss: 1.9183 (1.8256)  weight_decay: 0.0500 (0.0500)  time: 2.6404  data: 1.3118  max mem: 78493
Epoch: [283]  [ 20/312]  eta: 0:09:06  lr: 0.000037  min_lr: 0.000037  loss: 1.9183 (1.7958)  weight_decay: 0.0500 (0.0500)  time: 1.1101  data: 0.0046  max mem: 78493
Epoch: [283]  [ 30/312]  eta: 0:07:28  lr: 0.000037  min_lr: 0.000037  loss: 1.9753 (1.8453)  weight_decay: 0.0500 (0.0500)  time: 1.0151  data: 0.0006  max mem: 78493
Epoch: [283]  [ 40/312]  eta: 0:06:34  lr: 0.000037  min_lr: 0.000037  loss: 1.8673 (1.7949)  weight_decay: 0.0500 (0.0500)  time: 1.0055  data: 0.0005  max mem: 78493
Epoch: [283]  [ 50/312]  eta: 0:05:56  lr: 0.000037  min_lr: 0.000037  loss: 1.6927 (1.7780)  weight_decay: 0.0500 (0.0500)  time: 1.0055  data: 0.0004  max mem: 78493
Epoch: [283]  [ 60/312]  eta: 0:05:28  lr: 0.000036  min_lr: 0.000036  loss: 1.8723 (1.8138)  weight_decay: 0.0500 (0.0500)  time: 1.0074  data: 0.0004  max mem: 78493
Epoch: [283]  [ 70/312]  eta: 0:05:05  lr: 0.000036  min_lr: 0.000036  loss: 1.9819 (1.8310)  weight_decay: 0.0500 (0.0500)  time: 1.0087  data: 0.0004  max mem: 78493
Epoch: [283]  [ 80/312]  eta: 0:04:45  lr: 0.000036  min_lr: 0.000036  loss: 1.8923 (1.8422)  weight_decay: 0.0500 (0.0500)  time: 1.0085  data: 0.0005  max mem: 78493
Epoch: [283]  [ 90/312]  eta: 0:04:27  lr: 0.000036  min_lr: 0.000036  loss: 1.9529 (1.8601)  weight_decay: 0.0500 (0.0500)  time: 1.0101  data: 0.0005  max mem: 78493
Epoch: [283]  [100/312]  eta: 0:04:11  lr: 0.000036  min_lr: 0.000036  loss: 1.9185 (1.8607)  weight_decay: 0.0500 (0.0500)  time: 1.0095  data: 0.0004  max mem: 78493
Epoch: [283]  [110/312]  eta: 0:03:56  lr: 0.000036  min_lr: 0.000036  loss: 2.0348 (1.8712)  weight_decay: 0.0500 (0.0500)  time: 1.0070  data: 0.0004  max mem: 78493
Epoch: [283]  [120/312]  eta: 0:03:42  lr: 0.000036  min_lr: 0.000036  loss: 1.9444 (1.8568)  weight_decay: 0.0500 (0.0500)  time: 1.0084  data: 0.0004  max mem: 78493
Epoch: [283]  [130/312]  eta: 0:03:28  lr: 0.000036  min_lr: 0.000036  loss: 1.7671 (1.8533)  weight_decay: 0.0500 (0.0500)  time: 1.0097  data: 0.0005  max mem: 78493
Epoch: [283]  [140/312]  eta: 0:03:15  lr: 0.000035  min_lr: 0.000035  loss: 2.0280 (1.8656)  weight_decay: 0.0500 (0.0500)  time: 1.0082  data: 0.0005  max mem: 78493
Epoch: [283]  [150/312]  eta: 0:03:02  lr: 0.000035  min_lr: 0.000035  loss: 1.9439 (1.8634)  weight_decay: 0.0500 (0.0500)  time: 1.0089  data: 0.0004  max mem: 78493
Epoch: [283]  [160/312]  eta: 0:02:50  lr: 0.000035  min_lr: 0.000035  loss: 1.9790 (1.8722)  weight_decay: 0.0500 (0.0500)  time: 1.0112  data: 0.0011  max mem: 78493
Epoch: [283]  [170/312]  eta: 0:02:38  lr: 0.000035  min_lr: 0.000035  loss: 1.9270 (1.8673)  weight_decay: 0.0500 (0.0500)  time: 1.0082  data: 0.0011  max mem: 78493
Epoch: [283]  [180/312]  eta: 0:02:26  lr: 0.000035  min_lr: 0.000035  loss: 1.9212 (1.8739)  weight_decay: 0.0500 (0.0500)  time: 1.0081  data: 0.0004  max mem: 78493
Epoch: [283]  [190/312]  eta: 0:02:14  lr: 0.000035  min_lr: 0.000035  loss: 1.9133 (1.8729)  weight_decay: 0.0500 (0.0500)  time: 1.0087  data: 0.0004  max mem: 78493
Epoch: [283]  [200/312]  eta: 0:02:03  lr: 0.000035  min_lr: 0.000035  loss: 1.8965 (1.8659)  weight_decay: 0.0500 (0.0500)  time: 1.0095  data: 0.0004  max mem: 78493
Epoch: [283]  [210/312]  eta: 0:01:51  lr: 0.000034  min_lr: 0.000034  loss: 1.9076 (1.8699)  weight_decay: 0.0500 (0.0500)  time: 1.0095  data: 0.0004  max mem: 78493
Epoch: [283]  [220/312]  eta: 0:01:40  lr: 0.000034  min_lr: 0.000034  loss: 1.9287 (1.8686)  weight_decay: 0.0500 (0.0500)  time: 1.0071  data: 0.0004  max mem: 78493
Epoch: [283]  [230/312]  eta: 0:01:29  lr: 0.000034  min_lr: 0.000034  loss: 1.9098 (1.8679)  weight_decay: 0.0500 (0.0500)  time: 1.0076  data: 0.0004  max mem: 78493
Epoch: [283]  [240/312]  eta: 0:01:18  lr: 0.000034  min_lr: 0.000034  loss: 1.8756 (1.8639)  weight_decay: 0.0500 (0.0500)  time: 1.0069  data: 0.0005  max mem: 78493
Epoch: [283]  [250/312]  eta: 0:01:06  lr: 0.000034  min_lr: 0.000034  loss: 1.9942 (1.8659)  weight_decay: 0.0500 (0.0500)  time: 1.0069  data: 0.0004  max mem: 78493
Epoch: [283]  [260/312]  eta: 0:00:56  lr: 0.000034  min_lr: 0.000034  loss: 1.9430 (1.8674)  weight_decay: 0.0500 (0.0500)  time: 1.0080  data: 0.0004  max mem: 78493
Epoch: [283]  [270/312]  eta: 0:00:45  lr: 0.000034  min_lr: 0.000034  loss: 1.8668 (1.8616)  weight_decay: 0.0500 (0.0500)  time: 1.0069  data: 0.0004  max mem: 78493
Epoch: [283]  [280/312]  eta: 0:00:34  lr: 0.000034  min_lr: 0.000034  loss: 1.8439 (1.8640)  weight_decay: 0.0500 (0.0500)  time: 1.0076  data: 0.0011  max mem: 78493
Epoch: [283]  [290/312]  eta: 0:00:23  lr: 0.000033  min_lr: 0.000033  loss: 1.8780 (1.8616)  weight_decay: 0.0500 (0.0500)  time: 1.0063  data: 0.0009  max mem: 78493
Epoch: [283]  [300/312]  eta: 0:00:12  lr: 0.000033  min_lr: 0.000033  loss: 2.0217 (1.8659)  weight_decay: 0.0500 (0.0500)  time: 1.0025  data: 0.0001  max mem: 78493
Epoch: [283]  [310/312]  eta: 0:00:02  lr: 0.000033  min_lr: 0.000033  loss: 2.0217 (1.8658)  weight_decay: 0.0500 (0.0500)  time: 1.0019  data: 0.0001  max mem: 78493
Epoch: [283]  [311/312]  eta: 0:00:01  lr: 0.000033  min_lr: 0.000033  loss: 2.0217 (1.8656)  weight_decay: 0.0500 (0.0500)  time: 1.0018  data: 0.0001  max mem: 78493
Epoch: [283] Total time: 0:05:34 (1.0715 s / it)
Averaged stats: lr: 0.000033  min_lr: 0.000033  loss: 2.0217 (1.8293)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:14  loss: 0.4776 (0.4776)  acc1: 87.7604 (87.7604)  acc5: 97.7865 (97.7865)  time: 8.2441  data: 7.9628  max mem: 78493
Test:  [8/9]  eta: 0:00:01  loss: 0.7134 (0.6659)  acc1: 82.5521 (82.4000)  acc5: 96.4844 (95.8880)  time: 1.1142  data: 0.8848  max mem: 78493
Test: Total time: 0:00:10 (1.1508 s / it)
* Acc@1 82.654 Acc@5 96.102 loss 0.654
Accuracy of the model on the 50000 test images: 82.7%
Max accuracy: 82.65%
Epoch: [284]  [  0/312]  eta: 1:19:54  lr: 0.000033  min_lr: 0.000033  loss: 1.7621 (1.7621)  weight_decay: 0.0500 (0.0500)  time: 15.3682  data: 14.3532  max mem: 78493
Epoch: [284]  [ 10/312]  eta: 0:12:48  lr: 0.000033  min_lr: 0.000033  loss: 1.9641 (1.9344)  weight_decay: 0.0500 (0.0500)  time: 2.5451  data: 1.3780  max mem: 78493
Epoch: [284]  [ 20/312]  eta: 0:08:51  lr: 0.000033  min_lr: 0.000033  loss: 1.9551 (1.9363)  weight_decay: 0.0500 (0.0500)  time: 1.1430  data: 0.0406  max mem: 78493
Epoch: [284]  [ 30/312]  eta: 0:07:19  lr: 0.000033  min_lr: 0.000033  loss: 1.9735 (1.9207)  weight_decay: 0.0500 (0.0500)  time: 1.0166  data: 0.0005  max mem: 78493
Epoch: [284]  [ 40/312]  eta: 0:06:27  lr: 0.000033  min_lr: 0.000033  loss: 1.9735 (1.8956)  weight_decay: 0.0500 (0.0500)  time: 1.0085  data: 0.0005  max mem: 78493
Epoch: [284]  [ 50/312]  eta: 0:05:51  lr: 0.000032  min_lr: 0.000032  loss: 1.9646 (1.8946)  weight_decay: 0.0500 (0.0500)  time: 1.0080  data: 0.0005  max mem: 78493
Epoch: [284]  [ 60/312]  eta: 0:05:24  lr: 0.000032  min_lr: 0.000032  loss: 1.8908 (1.8780)  weight_decay: 0.0500 (0.0500)  time: 1.0089  data: 0.0005  max mem: 78493
Epoch: [284]  [ 70/312]  eta: 0:05:02  lr: 0.000032  min_lr: 0.000032  loss: 1.9430 (1.8861)  weight_decay: 0.0500 (0.0500)  time: 1.0087  data: 0.0005  max mem: 78493
Epoch: [284]  [ 80/312]  eta: 0:04:42  lr: 0.000032  min_lr: 0.000032  loss: 1.9430 (1.8755)  weight_decay: 0.0500 (0.0500)  time: 1.0070  data: 0.0005  max mem: 78493
Epoch: [284]  [ 90/312]  eta: 0:04:25  lr: 0.000032  min_lr: 0.000032  loss: 2.0074 (1.8927)  weight_decay: 0.0500 (0.0500)  time: 1.0068  data: 0.0004  max mem: 78493
Epoch: [284]  [100/312]  eta: 0:04:09  lr: 0.000032  min_lr: 0.000032  loss: 2.0074 (1.8732)  weight_decay: 0.0500 (0.0500)  time: 1.0082  data: 0.0012  max mem: 78493
Epoch: [284]  [110/312]  eta: 0:03:54  lr: 0.000032  min_lr: 0.000032  loss: 1.8363 (1.8741)  weight_decay: 0.0500 (0.0500)  time: 1.0089  data: 0.0013  max mem: 78493
Epoch: [284]  [120/312]  eta: 0:03:40  lr: 0.000032  min_lr: 0.000032  loss: 1.9874 (1.8738)  weight_decay: 0.0500 (0.0500)  time: 1.0088  data: 0.0005  max mem: 78493
Epoch: [284]  [130/312]  eta: 0:03:27  lr: 0.000031  min_lr: 0.000031  loss: 1.9343 (1.8590)  weight_decay: 0.0500 (0.0500)  time: 1.0086  data: 0.0004  max mem: 78493
Epoch: [284]  [140/312]  eta: 0:03:14  lr: 0.000031  min_lr: 0.000031  loss: 1.7667 (1.8524)  weight_decay: 0.0500 (0.0500)  time: 1.0094  data: 0.0004  max mem: 78493
Epoch: [284]  [150/312]  eta: 0:03:01  lr: 0.000031  min_lr: 0.000031  loss: 1.8483 (1.8523)  weight_decay: 0.0500 (0.0500)  time: 1.0082  data: 0.0004  max mem: 78493
Epoch: [284]  [160/312]  eta: 0:02:49  lr: 0.000031  min_lr: 0.000031  loss: 1.8855 (1.8526)  weight_decay: 0.0500 (0.0500)  time: 1.0071  data: 0.0005  max mem: 78493
Epoch: [284]  [170/312]  eta: 0:02:37  lr: 0.000031  min_lr: 0.000031  loss: 1.7429 (1.8409)  weight_decay: 0.0500 (0.0500)  time: 1.0071  data: 0.0017  max mem: 78493
Epoch: [284]  [180/312]  eta: 0:02:25  lr: 0.000031  min_lr: 0.000031  loss: 1.7041 (1.8377)  weight_decay: 0.0500 (0.0500)  time: 1.0080  data: 0.0017  max mem: 78493
Epoch: [284]  [190/312]  eta: 0:02:13  lr: 0.000031  min_lr: 0.000031  loss: 1.8909 (1.8385)  weight_decay: 0.0500 (0.0500)  time: 1.0092  data: 0.0005  max mem: 78493
Epoch: [284]  [200/312]  eta: 0:02:02  lr: 0.000031  min_lr: 0.000031  loss: 1.8782 (1.8354)  weight_decay: 0.0500 (0.0500)  time: 1.0082  data: 0.0004  max mem: 78493
Epoch: [284]  [210/312]  eta: 0:01:51  lr: 0.000030  min_lr: 0.000030  loss: 1.8250 (1.8330)  weight_decay: 0.0500 (0.0500)  time: 1.0071  data: 0.0004  max mem: 78493
Epoch: [284]  [220/312]  eta: 0:01:39  lr: 0.000030  min_lr: 0.000030  loss: 1.8676 (1.8349)  weight_decay: 0.0500 (0.0500)  time: 1.0073  data: 0.0013  max mem: 78493
Epoch: [284]  [230/312]  eta: 0:01:28  lr: 0.000030  min_lr: 0.000030  loss: 1.8865 (1.8407)  weight_decay: 0.0500 (0.0500)  time: 1.0079  data: 0.0013  max mem: 78493
Epoch: [284]  [240/312]  eta: 0:01:17  lr: 0.000030  min_lr: 0.000030  loss: 1.8299 (1.8339)  weight_decay: 0.0500 (0.0500)  time: 1.0076  data: 0.0004  max mem: 78493
Epoch: [284]  [250/312]  eta: 0:01:06  lr: 0.000030  min_lr: 0.000030  loss: 1.7912 (1.8356)  weight_decay: 0.0500 (0.0500)  time: 1.0065  data: 0.0005  max mem: 78493
Epoch: [284]  [260/312]  eta: 0:00:55  lr: 0.000030  min_lr: 0.000030  loss: 1.8219 (1.8351)  weight_decay: 0.0500 (0.0500)  time: 1.0068  data: 0.0005  max mem: 78493
Epoch: [284]  [270/312]  eta: 0:00:44  lr: 0.000030  min_lr: 0.000030  loss: 1.8219 (1.8383)  weight_decay: 0.0500 (0.0500)  time: 1.0067  data: 0.0004  max mem: 78493
Epoch: [284]  [280/312]  eta: 0:00:34  lr: 0.000030  min_lr: 0.000030  loss: 1.9265 (1.8400)  weight_decay: 0.0500 (0.0500)  time: 1.0065  data: 0.0011  max mem: 78493
Epoch: [284]  [290/312]  eta: 0:00:23  lr: 0.000030  min_lr: 0.000030  loss: 1.8136 (1.8351)  weight_decay: 0.0500 (0.0500)  time: 1.0044  data: 0.0009  max mem: 78493
Epoch: [284]  [300/312]  eta: 0:00:12  lr: 0.000029  min_lr: 0.000029  loss: 1.8248 (1.8384)  weight_decay: 0.0500 (0.0500)  time: 1.0017  data: 0.0001  max mem: 78493
Epoch: [284]  [310/312]  eta: 0:00:02  lr: 0.000029  min_lr: 0.000029  loss: 1.9461 (1.8377)  weight_decay: 0.0500 (0.0500)  time: 1.0017  data: 0.0001  max mem: 78493
Epoch: [284]  [311/312]  eta: 0:00:01  lr: 0.000029  min_lr: 0.000029  loss: 1.9301 (1.8355)  weight_decay: 0.0500 (0.0500)  time: 1.0018  data: 0.0001  max mem: 78493
Epoch: [284] Total time: 0:05:33 (1.0676 s / it)
Averaged stats: lr: 0.000029  min_lr: 0.000029  loss: 1.9301 (1.8378)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:11  loss: 0.4820 (0.4820)  acc1: 87.8906 (87.8906)  acc5: 97.7865 (97.7865)  time: 7.8969  data: 7.6234  max mem: 78493
Test:  [8/9]  eta: 0:00:01  loss: 0.7175 (0.6691)  acc1: 81.9010 (82.0640)  acc5: 96.0938 (96.0160)  time: 1.0896  data: 0.8605  max mem: 78493
Test: Total time: 0:00:09 (1.1001 s / it)
* Acc@1 82.528 Acc@5 96.094 loss 0.655
Accuracy of the model on the 50000 test images: 82.5%
Max accuracy: 82.65%
Epoch: [285]  [  0/312]  eta: 1:26:04  lr: 0.000029  min_lr: 0.000029  loss: 1.4746 (1.4746)  weight_decay: 0.0500 (0.0500)  time: 16.5539  data: 11.6912  max mem: 78493
Epoch: [285]  [ 10/312]  eta: 0:13:27  lr: 0.000029  min_lr: 0.000029  loss: 1.9569 (1.8728)  weight_decay: 0.0500 (0.0500)  time: 2.6744  data: 1.2852  max mem: 78493
Epoch: [285]  [ 20/312]  eta: 0:09:10  lr: 0.000029  min_lr: 0.000029  loss: 1.8940 (1.8700)  weight_decay: 0.0500 (0.0500)  time: 1.1515  data: 0.1225  max mem: 78493
Epoch: [285]  [ 30/312]  eta: 0:07:31  lr: 0.000029  min_lr: 0.000029  loss: 1.8690 (1.8274)  weight_decay: 0.0500 (0.0500)  time: 1.0120  data: 0.0005  max mem: 78493
Epoch: [285]  [ 40/312]  eta: 0:06:36  lr: 0.000029  min_lr: 0.000029  loss: 1.8890 (1.8271)  weight_decay: 0.0500 (0.0500)  time: 1.0072  data: 0.0004  max mem: 78493
Epoch: [285]  [ 50/312]  eta: 0:05:58  lr: 0.000029  min_lr: 0.000029  loss: 1.8501 (1.8324)  weight_decay: 0.0500 (0.0500)  time: 1.0095  data: 0.0004  max mem: 78493
Epoch: [285]  [ 60/312]  eta: 0:05:30  lr: 0.000029  min_lr: 0.000029  loss: 1.8699 (1.8392)  weight_decay: 0.0500 (0.0500)  time: 1.0089  data: 0.0004  max mem: 78493
Epoch: [285]  [ 70/312]  eta: 0:05:06  lr: 0.000028  min_lr: 0.000028  loss: 1.9357 (1.8429)  weight_decay: 0.0500 (0.0500)  time: 1.0067  data: 0.0004  max mem: 78493
Epoch: [285]  [ 80/312]  eta: 0:04:46  lr: 0.000028  min_lr: 0.000028  loss: 1.9732 (1.8560)  weight_decay: 0.0500 (0.0500)  time: 1.0063  data: 0.0004  max mem: 78493
Epoch: [285]  [ 90/312]  eta: 0:04:28  lr: 0.000028  min_lr: 0.000028  loss: 1.9664 (1.8485)  weight_decay: 0.0500 (0.0500)  time: 1.0053  data: 0.0005  max mem: 78493
Epoch: [285]  [100/312]  eta: 0:04:12  lr: 0.000028  min_lr: 0.000028  loss: 1.7973 (1.8205)  weight_decay: 0.0500 (0.0500)  time: 1.0070  data: 0.0005  max mem: 78493
Epoch: [285]  [110/312]  eta: 0:03:57  lr: 0.000028  min_lr: 0.000028  loss: 1.8135 (1.8282)  weight_decay: 0.0500 (0.0500)  time: 1.0077  data: 0.0005  max mem: 78493
Epoch: [285]  [120/312]  eta: 0:03:42  lr: 0.000028  min_lr: 0.000028  loss: 1.8641 (1.8284)  weight_decay: 0.0500 (0.0500)  time: 1.0088  data: 0.0012  max mem: 78493
Epoch: [285]  [130/312]  eta: 0:03:29  lr: 0.000028  min_lr: 0.000028  loss: 1.8529 (1.8160)  weight_decay: 0.0500 (0.0500)  time: 1.0103  data: 0.0012  max mem: 78493
Epoch: [285]  [140/312]  eta: 0:03:15  lr: 0.000028  min_lr: 0.000028  loss: 1.8671 (1.8240)  weight_decay: 0.0500 (0.0500)  time: 1.0074  data: 0.0004  max mem: 78493
Epoch: [285]  [150/312]  eta: 0:03:02  lr: 0.000027  min_lr: 0.000027  loss: 1.8592 (1.8091)  weight_decay: 0.0500 (0.0500)  time: 1.0064  data: 0.0005  max mem: 78493
Epoch: [285]  [160/312]  eta: 0:02:50  lr: 0.000027  min_lr: 0.000027  loss: 1.7459 (1.8143)  weight_decay: 0.0500 (0.0500)  time: 1.0070  data: 0.0004  max mem: 78493
Epoch: [285]  [170/312]  eta: 0:02:38  lr: 0.000027  min_lr: 0.000027  loss: 1.9273 (1.8129)  weight_decay: 0.0500 (0.0500)  time: 1.0065  data: 0.0004  max mem: 78493
Epoch: [285]  [180/312]  eta: 0:02:26  lr: 0.000027  min_lr: 0.000027  loss: 1.7296 (1.8042)  weight_decay: 0.0500 (0.0500)  time: 1.0072  data: 0.0005  max mem: 78493
Epoch: [285]  [190/312]  eta: 0:02:14  lr: 0.000027  min_lr: 0.000027  loss: 1.6641 (1.8055)  weight_decay: 0.0500 (0.0500)  time: 1.0080  data: 0.0004  max mem: 78493
Epoch: [285]  [200/312]  eta: 0:02:03  lr: 0.000027  min_lr: 0.000027  loss: 1.8844 (1.8057)  weight_decay: 0.0500 (0.0500)  time: 1.0073  data: 0.0004  max mem: 78493
Epoch: [285]  [210/312]  eta: 0:01:51  lr: 0.000027  min_lr: 0.000027  loss: 1.9443 (1.8136)  weight_decay: 0.0500 (0.0500)  time: 1.0070  data: 0.0004  max mem: 78493
Epoch: [285]  [220/312]  eta: 0:01:40  lr: 0.000027  min_lr: 0.000027  loss: 2.0334 (1.8150)  weight_decay: 0.0500 (0.0500)  time: 1.0066  data: 0.0005  max mem: 78493
Epoch: [285]  [230/312]  eta: 0:01:29  lr: 0.000027  min_lr: 0.000027  loss: 1.8255 (1.8148)  weight_decay: 0.0500 (0.0500)  time: 1.0061  data: 0.0005  max mem: 78493
Epoch: [285]  [240/312]  eta: 0:01:18  lr: 0.000026  min_lr: 0.000026  loss: 1.8195 (1.8138)  weight_decay: 0.0500 (0.0500)  time: 1.0071  data: 0.0005  max mem: 78493
Epoch: [285]  [250/312]  eta: 0:01:07  lr: 0.000026  min_lr: 0.000026  loss: 1.6247 (1.8026)  weight_decay: 0.0500 (0.0500)  time: 1.0066  data: 0.0005  max mem: 78493
Epoch: [285]  [260/312]  eta: 0:00:56  lr: 0.000026  min_lr: 0.000026  loss: 1.6079 (1.8026)  weight_decay: 0.0500 (0.0500)  time: 1.0063  data: 0.0004  max mem: 78493
Epoch: [285]  [270/312]  eta: 0:00:45  lr: 0.000026  min_lr: 0.000026  loss: 1.9123 (1.8036)  weight_decay: 0.0500 (0.0500)  time: 1.0064  data: 0.0004  max mem: 78493
Epoch: [285]  [280/312]  eta: 0:00:34  lr: 0.000026  min_lr: 0.000026  loss: 1.8636 (1.8037)  weight_decay: 0.0500 (0.0500)  time: 1.0075  data: 0.0011  max mem: 78493
Epoch: [285]  [290/312]  eta: 0:00:23  lr: 0.000026  min_lr: 0.000026  loss: 1.8636 (1.8062)  weight_decay: 0.0500 (0.0500)  time: 1.0054  data: 0.0009  max mem: 78493
Epoch: [285]  [300/312]  eta: 0:00:12  lr: 0.000026  min_lr: 0.000026  loss: 1.8289 (1.8036)  weight_decay: 0.0500 (0.0500)  time: 1.0019  data: 0.0001  max mem: 78493
Epoch: [285]  [310/312]  eta: 0:00:02  lr: 0.000026  min_lr: 0.000026  loss: 1.6753 (1.8010)  weight_decay: 0.0500 (0.0500)  time: 1.0020  data: 0.0001  max mem: 78493
Epoch: [285]  [311/312]  eta: 0:00:01  lr: 0.000026  min_lr: 0.000026  loss: 1.6495 (1.8002)  weight_decay: 0.0500 (0.0500)  time: 1.0020  data: 0.0001  max mem: 78493
Epoch: [285] Total time: 0:05:34 (1.0715 s / it)
Averaged stats: lr: 0.000026  min_lr: 0.000026  loss: 1.6495 (1.8259)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:14  loss: 0.4817 (0.4817)  acc1: 87.7604 (87.7604)  acc5: 97.7865 (97.7865)  time: 8.2701  data: 8.0018  max mem: 78493
Test:  [8/9]  eta: 0:00:01  loss: 0.7225 (0.6688)  acc1: 82.0312 (82.1760)  acc5: 96.3542 (95.9200)  time: 1.1182  data: 0.8892  max mem: 78493
Test: Total time: 0:00:10 (1.1592 s / it)
* Acc@1 82.568 Acc@5 96.094 loss 0.654
Accuracy of the model on the 50000 test images: 82.6%
Max accuracy: 82.65%
Epoch: [286]  [  0/312]  eta: 1:24:38  lr: 0.000026  min_lr: 0.000026  loss: 1.4130 (1.4130)  weight_decay: 0.0500 (0.0500)  time: 16.2759  data: 12.9900  max mem: 78493
Epoch: [286]  [ 10/312]  eta: 0:12:59  lr: 0.000026  min_lr: 0.000026  loss: 1.7514 (1.7480)  weight_decay: 0.0500 (0.0500)  time: 2.5813  data: 1.1816  max mem: 78493
Epoch: [286]  [ 20/312]  eta: 0:08:56  lr: 0.000025  min_lr: 0.000025  loss: 1.7969 (1.7406)  weight_decay: 0.0500 (0.0500)  time: 1.1154  data: 0.0006  max mem: 78493
Epoch: [286]  [ 30/312]  eta: 0:07:22  lr: 0.000025  min_lr: 0.000025  loss: 1.7969 (1.7621)  weight_decay: 0.0500 (0.0500)  time: 1.0137  data: 0.0005  max mem: 78493
Epoch: [286]  [ 40/312]  eta: 0:06:29  lr: 0.000025  min_lr: 0.000025  loss: 1.9196 (1.7872)  weight_decay: 0.0500 (0.0500)  time: 1.0075  data: 0.0004  max mem: 78493
Epoch: [286]  [ 50/312]  eta: 0:05:53  lr: 0.000025  min_lr: 0.000025  loss: 1.9524 (1.8207)  weight_decay: 0.0500 (0.0500)  time: 1.0067  data: 0.0004  max mem: 78493
Epoch: [286]  [ 60/312]  eta: 0:05:25  lr: 0.000025  min_lr: 0.000025  loss: 1.9680 (1.8327)  weight_decay: 0.0500 (0.0500)  time: 1.0067  data: 0.0005  max mem: 78493
Epoch: [286]  [ 70/312]  eta: 0:05:03  lr: 0.000025  min_lr: 0.000025  loss: 1.8156 (1.8368)  weight_decay: 0.0500 (0.0500)  time: 1.0089  data: 0.0005  max mem: 78493
Epoch: [286]  [ 80/312]  eta: 0:04:43  lr: 0.000025  min_lr: 0.000025  loss: 1.8156 (1.8411)  weight_decay: 0.0500 (0.0500)  time: 1.0089  data: 0.0004  max mem: 78493
Epoch: [286]  [ 90/312]  eta: 0:04:26  lr: 0.000025  min_lr: 0.000025  loss: 1.7860 (1.8324)  weight_decay: 0.0500 (0.0500)  time: 1.0072  data: 0.0005  max mem: 78493
Epoch: [286]  [100/312]  eta: 0:04:10  lr: 0.000025  min_lr: 0.000025  loss: 1.7093 (1.8273)  weight_decay: 0.0500 (0.0500)  time: 1.0078  data: 0.0004  max mem: 78493
Epoch: [286]  [110/312]  eta: 0:03:55  lr: 0.000024  min_lr: 0.000024  loss: 1.7790 (1.8398)  weight_decay: 0.0500 (0.0500)  time: 1.0088  data: 0.0004  max mem: 78493
Epoch: [286]  [120/312]  eta: 0:03:41  lr: 0.000024  min_lr: 0.000024  loss: 1.7957 (1.8249)  weight_decay: 0.0500 (0.0500)  time: 1.0074  data: 0.0004  max mem: 78493
Epoch: [286]  [130/312]  eta: 0:03:27  lr: 0.000024  min_lr: 0.000024  loss: 1.6978 (1.8222)  weight_decay: 0.0500 (0.0500)  time: 1.0098  data: 0.0004  max mem: 78493
Epoch: [286]  [140/312]  eta: 0:03:14  lr: 0.000024  min_lr: 0.000024  loss: 1.8189 (1.8178)  weight_decay: 0.0500 (0.0500)  time: 1.0113  data: 0.0005  max mem: 78493
Epoch: [286]  [150/312]  eta: 0:03:02  lr: 0.000024  min_lr: 0.000024  loss: 1.9029 (1.8206)  weight_decay: 0.0500 (0.0500)  time: 1.0086  data: 0.0004  max mem: 78493
Epoch: [286]  [160/312]  eta: 0:02:49  lr: 0.000024  min_lr: 0.000024  loss: 1.9340 (1.8248)  weight_decay: 0.0500 (0.0500)  time: 1.0076  data: 0.0004  max mem: 78493
Epoch: [286]  [170/312]  eta: 0:02:37  lr: 0.000024  min_lr: 0.000024  loss: 1.7723 (1.8145)  weight_decay: 0.0500 (0.0500)  time: 1.0061  data: 0.0004  max mem: 78493
Epoch: [286]  [180/312]  eta: 0:02:25  lr: 0.000024  min_lr: 0.000024  loss: 1.8103 (1.8222)  weight_decay: 0.0500 (0.0500)  time: 1.0068  data: 0.0004  max mem: 78493
Epoch: [286]  [190/312]  eta: 0:02:14  lr: 0.000024  min_lr: 0.000024  loss: 1.9094 (1.8203)  weight_decay: 0.0500 (0.0500)  time: 1.0056  data: 0.0011  max mem: 78493
Epoch: [286]  [200/312]  eta: 0:02:02  lr: 0.000023  min_lr: 0.000023  loss: 2.0112 (1.8311)  weight_decay: 0.0500 (0.0500)  time: 1.0044  data: 0.0011  max mem: 78493
Epoch: [286]  [210/312]  eta: 0:01:51  lr: 0.000023  min_lr: 0.000023  loss: 1.9655 (1.8331)  weight_decay: 0.0500 (0.0500)  time: 1.0056  data: 0.0004  max mem: 78493
Epoch: [286]  [220/312]  eta: 0:01:39  lr: 0.000023  min_lr: 0.000023  loss: 1.8858 (1.8360)  weight_decay: 0.0500 (0.0500)  time: 1.0072  data: 0.0004  max mem: 78493
Epoch: [286]  [230/312]  eta: 0:01:28  lr: 0.000023  min_lr: 0.000023  loss: 1.9264 (1.8333)  weight_decay: 0.0500 (0.0500)  time: 1.0058  data: 0.0004  max mem: 78493
Epoch: [286]  [240/312]  eta: 0:01:17  lr: 0.000023  min_lr: 0.000023  loss: 1.9425 (1.8369)  weight_decay: 0.0500 (0.0500)  time: 1.0050  data: 0.0005  max mem: 78493
Epoch: [286]  [250/312]  eta: 0:01:06  lr: 0.000023  min_lr: 0.000023  loss: 1.9839 (1.8371)  weight_decay: 0.0500 (0.0500)  time: 1.0064  data: 0.0004  max mem: 78493
Epoch: [286]  [260/312]  eta: 0:00:55  lr: 0.000023  min_lr: 0.000023  loss: 1.8443 (1.8377)  weight_decay: 0.0500 (0.0500)  time: 1.0068  data: 0.0004  max mem: 78493
Epoch: [286]  [270/312]  eta: 0:00:45  lr: 0.000023  min_lr: 0.000023  loss: 1.7281 (1.8393)  weight_decay: 0.0500 (0.0500)  time: 1.0061  data: 0.0004  max mem: 78493
Epoch: [286]  [280/312]  eta: 0:00:34  lr: 0.000023  min_lr: 0.000023  loss: 1.9688 (1.8434)  weight_decay: 0.0500 (0.0500)  time: 1.0059  data: 0.0010  max mem: 78493
Epoch: [286]  [290/312]  eta: 0:00:23  lr: 0.000022  min_lr: 0.000022  loss: 1.9343 (1.8403)  weight_decay: 0.0500 (0.0500)  time: 1.0046  data: 0.0009  max mem: 78493
Epoch: [286]  [300/312]  eta: 0:00:12  lr: 0.000022  min_lr: 0.000022  loss: 1.6830 (1.8344)  weight_decay: 0.0500 (0.0500)  time: 1.0023  data: 0.0001  max mem: 78493
Epoch: [286]  [310/312]  eta: 0:00:02  lr: 0.000022  min_lr: 0.000022  loss: 1.8465 (1.8344)  weight_decay: 0.0500 (0.0500)  time: 1.0020  data: 0.0001  max mem: 78493
Epoch: [286]  [311/312]  eta: 0:00:01  lr: 0.000022  min_lr: 0.000022  loss: 1.8084 (1.8341)  weight_decay: 0.0500 (0.0500)  time: 1.0020  data: 0.0001  max mem: 78493
Epoch: [286] Total time: 0:05:33 (1.0683 s / it)
Averaged stats: lr: 0.000022  min_lr: 0.000022  loss: 1.8084 (1.8328)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:17  loss: 0.4786 (0.4786)  acc1: 88.0208 (88.0208)  acc5: 97.9167 (97.9167)  time: 8.6182  data: 8.3396  max mem: 78493
Test:  [8/9]  eta: 0:00:01  loss: 0.7184 (0.6680)  acc1: 82.5521 (82.0000)  acc5: 96.2240 (96.0320)  time: 1.1558  data: 0.9267  max mem: 78493
Test: Total time: 0:00:10 (1.1842 s / it)
* Acc@1 82.500 Acc@5 96.118 loss 0.655
Accuracy of the model on the 50000 test images: 82.5%
Max accuracy: 82.65%
Epoch: [287]  [  0/312]  eta: 1:27:44  lr: 0.000022  min_lr: 0.000022  loss: 1.7814 (1.7814)  weight_decay: 0.0500 (0.0500)  time: 16.8747  data: 13.5038  max mem: 78493
Epoch: [287]  [ 10/312]  eta: 0:13:11  lr: 0.000022  min_lr: 0.000022  loss: 1.9315 (1.9094)  weight_decay: 0.0500 (0.0500)  time: 2.6210  data: 1.2402  max mem: 78493
Epoch: [287]  [ 20/312]  eta: 0:09:03  lr: 0.000022  min_lr: 0.000022  loss: 1.8433 (1.8502)  weight_decay: 0.0500 (0.0500)  time: 1.1108  data: 0.0093  max mem: 78493
Epoch: [287]  [ 30/312]  eta: 0:07:27  lr: 0.000022  min_lr: 0.000022  loss: 1.7702 (1.8342)  weight_decay: 0.0500 (0.0500)  time: 1.0170  data: 0.0026  max mem: 78493
Epoch: [287]  [ 40/312]  eta: 0:06:33  lr: 0.000022  min_lr: 0.000022  loss: 1.8844 (1.8332)  weight_decay: 0.0500 (0.0500)  time: 1.0090  data: 0.0022  max mem: 78493
Epoch: [287]  [ 50/312]  eta: 0:05:56  lr: 0.000022  min_lr: 0.000022  loss: 1.9787 (1.8750)  weight_decay: 0.0500 (0.0500)  time: 1.0091  data: 0.0022  max mem: 78493
Epoch: [287]  [ 60/312]  eta: 0:05:28  lr: 0.000022  min_lr: 0.000022  loss: 2.0048 (1.8812)  weight_decay: 0.0500 (0.0500)  time: 1.0073  data: 0.0004  max mem: 78493
Epoch: [287]  [ 70/312]  eta: 0:05:05  lr: 0.000022  min_lr: 0.000022  loss: 2.0058 (1.8988)  weight_decay: 0.0500 (0.0500)  time: 1.0070  data: 0.0004  max mem: 78493
Epoch: [287]  [ 80/312]  eta: 0:04:45  lr: 0.000021  min_lr: 0.000021  loss: 2.0097 (1.9116)  weight_decay: 0.0500 (0.0500)  time: 1.0086  data: 0.0004  max mem: 78493
Epoch: [287]  [ 90/312]  eta: 0:04:27  lr: 0.000021  min_lr: 0.000021  loss: 1.7264 (1.8763)  weight_decay: 0.0500 (0.0500)  time: 1.0081  data: 0.0012  max mem: 78493
Epoch: [287]  [100/312]  eta: 0:04:11  lr: 0.000021  min_lr: 0.000021  loss: 1.7264 (1.8800)  weight_decay: 0.0500 (0.0500)  time: 1.0081  data: 0.0012  max mem: 78493
Epoch: [287]  [110/312]  eta: 0:03:56  lr: 0.000021  min_lr: 0.000021  loss: 2.0440 (1.8888)  weight_decay: 0.0500 (0.0500)  time: 1.0097  data: 0.0004  max mem: 78493
Epoch: [287]  [120/312]  eta: 0:03:42  lr: 0.000021  min_lr: 0.000021  loss: 1.9791 (1.8869)  weight_decay: 0.0500 (0.0500)  time: 1.0086  data: 0.0004  max mem: 78493
Epoch: [287]  [130/312]  eta: 0:03:28  lr: 0.000021  min_lr: 0.000021  loss: 1.8074 (1.8851)  weight_decay: 0.0500 (0.0500)  time: 1.0089  data: 0.0005  max mem: 78493
Epoch: [287]  [140/312]  eta: 0:03:15  lr: 0.000021  min_lr: 0.000021  loss: 1.8407 (1.8783)  weight_decay: 0.0500 (0.0500)  time: 1.0100  data: 0.0005  max mem: 78493
Epoch: [287]  [150/312]  eta: 0:03:02  lr: 0.000021  min_lr: 0.000021  loss: 1.8086 (1.8650)  weight_decay: 0.0500 (0.0500)  time: 1.0096  data: 0.0004  max mem: 78493
Epoch: [287]  [160/312]  eta: 0:02:50  lr: 0.000021  min_lr: 0.000021  loss: 1.8265 (1.8670)  weight_decay: 0.0500 (0.0500)  time: 1.0066  data: 0.0005  max mem: 78493
Epoch: [287]  [170/312]  eta: 0:02:38  lr: 0.000020  min_lr: 0.000020  loss: 1.8142 (1.8539)  weight_decay: 0.0500 (0.0500)  time: 1.0045  data: 0.0005  max mem: 78493
Epoch: [287]  [180/312]  eta: 0:02:26  lr: 0.000020  min_lr: 0.000020  loss: 1.8516 (1.8571)  weight_decay: 0.0500 (0.0500)  time: 1.0062  data: 0.0004  max mem: 78493
Epoch: [287]  [190/312]  eta: 0:02:14  lr: 0.000020  min_lr: 0.000020  loss: 1.9044 (1.8418)  weight_decay: 0.0500 (0.0500)  time: 1.0066  data: 0.0004  max mem: 78493
Epoch: [287]  [200/312]  eta: 0:02:02  lr: 0.000020  min_lr: 0.000020  loss: 1.8425 (1.8447)  weight_decay: 0.0500 (0.0500)  time: 1.0048  data: 0.0005  max mem: 78493
Epoch: [287]  [210/312]  eta: 0:01:51  lr: 0.000020  min_lr: 0.000020  loss: 1.8837 (1.8424)  weight_decay: 0.0500 (0.0500)  time: 1.0044  data: 0.0005  max mem: 78493
Epoch: [287]  [220/312]  eta: 0:01:40  lr: 0.000020  min_lr: 0.000020  loss: 1.9654 (1.8450)  weight_decay: 0.0500 (0.0500)  time: 1.0059  data: 0.0005  max mem: 78493
Epoch: [287]  [230/312]  eta: 0:01:28  lr: 0.000020  min_lr: 0.000020  loss: 2.0058 (1.8471)  weight_decay: 0.0500 (0.0500)  time: 1.0057  data: 0.0005  max mem: 78493
Epoch: [287]  [240/312]  eta: 0:01:17  lr: 0.000020  min_lr: 0.000020  loss: 1.9928 (1.8497)  weight_decay: 0.0500 (0.0500)  time: 1.0053  data: 0.0005  max mem: 78493
Epoch: [287]  [250/312]  eta: 0:01:06  lr: 0.000020  min_lr: 0.000020  loss: 1.9959 (1.8500)  weight_decay: 0.0500 (0.0500)  time: 1.0072  data: 0.0004  max mem: 78493
Epoch: [287]  [260/312]  eta: 0:00:55  lr: 0.000020  min_lr: 0.000020  loss: 1.9959 (1.8518)  weight_decay: 0.0500 (0.0500)  time: 1.0067  data: 0.0010  max mem: 78493
Epoch: [287]  [270/312]  eta: 0:00:45  lr: 0.000020  min_lr: 0.000020  loss: 2.0008 (1.8547)  weight_decay: 0.0500 (0.0500)  time: 1.0042  data: 0.0010  max mem: 78493
Epoch: [287]  [280/312]  eta: 0:00:34  lr: 0.000019  min_lr: 0.000019  loss: 1.8851 (1.8522)  weight_decay: 0.0500 (0.0500)  time: 1.0049  data: 0.0010  max mem: 78493
Epoch: [287]  [290/312]  eta: 0:00:23  lr: 0.000019  min_lr: 0.000019  loss: 1.8851 (1.8518)  weight_decay: 0.0500 (0.0500)  time: 1.0042  data: 0.0009  max mem: 78493
Epoch: [287]  [300/312]  eta: 0:00:12  lr: 0.000019  min_lr: 0.000019  loss: 1.9420 (1.8532)  weight_decay: 0.0500 (0.0500)  time: 1.0023  data: 0.0001  max mem: 78493
Epoch: [287]  [310/312]  eta: 0:00:02  lr: 0.000019  min_lr: 0.000019  loss: 1.8161 (1.8501)  weight_decay: 0.0500 (0.0500)  time: 1.0022  data: 0.0001  max mem: 78493
Epoch: [287]  [311/312]  eta: 0:00:01  lr: 0.000019  min_lr: 0.000019  loss: 1.8161 (1.8502)  weight_decay: 0.0500 (0.0500)  time: 1.0022  data: 0.0001  max mem: 78493
Epoch: [287] Total time: 0:05:33 (1.0698 s / it)
Averaged stats: lr: 0.000019  min_lr: 0.000019  loss: 1.8161 (1.8298)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:16  loss: 0.4783 (0.4783)  acc1: 87.8906 (87.8906)  acc5: 97.9167 (97.9167)  time: 8.5492  data: 8.2771  max mem: 78493
Test:  [8/9]  eta: 0:00:01  loss: 0.7180 (0.6679)  acc1: 82.4219 (82.2240)  acc5: 96.3542 (96.0160)  time: 1.1482  data: 0.9198  max mem: 78493
Test: Total time: 0:00:10 (1.1781 s / it)
* Acc@1 82.628 Acc@5 96.130 loss 0.655
Accuracy of the model on the 50000 test images: 82.6%
Max accuracy: 82.65%
Epoch: [288]  [  0/312]  eta: 1:22:24  lr: 0.000019  min_lr: 0.000019  loss: 1.0897 (1.0897)  weight_decay: 0.0500 (0.0500)  time: 15.8492  data: 11.2134  max mem: 78493
Epoch: [288]  [ 10/312]  eta: 0:13:17  lr: 0.000019  min_lr: 0.000019  loss: 1.8130 (1.6446)  weight_decay: 0.0500 (0.0500)  time: 2.6414  data: 1.2653  max mem: 78493
Epoch: [288]  [ 20/312]  eta: 0:09:06  lr: 0.000019  min_lr: 0.000019  loss: 1.8231 (1.7328)  weight_decay: 0.0500 (0.0500)  time: 1.1720  data: 0.1355  max mem: 78493
Epoch: [288]  [ 30/312]  eta: 0:07:28  lr: 0.000019  min_lr: 0.000019  loss: 1.7852 (1.7319)  weight_decay: 0.0500 (0.0500)  time: 1.0146  data: 0.0012  max mem: 78493
Epoch: [288]  [ 40/312]  eta: 0:06:33  lr: 0.000019  min_lr: 0.000019  loss: 1.7852 (1.7786)  weight_decay: 0.0500 (0.0500)  time: 1.0043  data: 0.0012  max mem: 78493
Epoch: [288]  [ 50/312]  eta: 0:05:56  lr: 0.000019  min_lr: 0.000019  loss: 2.0311 (1.7967)  weight_decay: 0.0500 (0.0500)  time: 1.0039  data: 0.0004  max mem: 78493
Epoch: [288]  [ 60/312]  eta: 0:05:28  lr: 0.000019  min_lr: 0.000019  loss: 2.0247 (1.8110)  weight_decay: 0.0500 (0.0500)  time: 1.0040  data: 0.0004  max mem: 78493
Epoch: [288]  [ 70/312]  eta: 0:05:05  lr: 0.000018  min_lr: 0.000018  loss: 1.9425 (1.8088)  weight_decay: 0.0500 (0.0500)  time: 1.0048  data: 0.0005  max mem: 78493
Epoch: [288]  [ 80/312]  eta: 0:04:45  lr: 0.000018  min_lr: 0.000018  loss: 1.7218 (1.7875)  weight_decay: 0.0500 (0.0500)  time: 1.0077  data: 0.0005  max mem: 78493
Epoch: [288]  [ 90/312]  eta: 0:04:27  lr: 0.000018  min_lr: 0.000018  loss: 1.7636 (1.8048)  weight_decay: 0.0500 (0.0500)  time: 1.0109  data: 0.0004  max mem: 78493
Epoch: [288]  [100/312]  eta: 0:04:11  lr: 0.000018  min_lr: 0.000018  loss: 2.0071 (1.8048)  weight_decay: 0.0500 (0.0500)  time: 1.0097  data: 0.0005  max mem: 78493
Epoch: [288]  [110/312]  eta: 0:03:56  lr: 0.000018  min_lr: 0.000018  loss: 1.9132 (1.8177)  weight_decay: 0.0500 (0.0500)  time: 1.0086  data: 0.0005  max mem: 78493
Epoch: [288]  [120/312]  eta: 0:03:42  lr: 0.000018  min_lr: 0.000018  loss: 1.9773 (1.8336)  weight_decay: 0.0500 (0.0500)  time: 1.0091  data: 0.0004  max mem: 78493
Epoch: [288]  [130/312]  eta: 0:03:28  lr: 0.000018  min_lr: 0.000018  loss: 1.8532 (1.8194)  weight_decay: 0.0500 (0.0500)  time: 1.0074  data: 0.0004  max mem: 78493
Epoch: [288]  [140/312]  eta: 0:03:15  lr: 0.000018  min_lr: 0.000018  loss: 1.5940 (1.8134)  weight_decay: 0.0500 (0.0500)  time: 1.0070  data: 0.0004  max mem: 78493
Epoch: [288]  [150/312]  eta: 0:03:02  lr: 0.000018  min_lr: 0.000018  loss: 1.6686 (1.8100)  weight_decay: 0.0500 (0.0500)  time: 1.0073  data: 0.0004  max mem: 78493
Epoch: [288]  [160/312]  eta: 0:02:50  lr: 0.000018  min_lr: 0.000018  loss: 1.6686 (1.7974)  weight_decay: 0.0500 (0.0500)  time: 1.0083  data: 0.0004  max mem: 78493
Epoch: [288]  [170/312]  eta: 0:02:38  lr: 0.000017  min_lr: 0.000017  loss: 1.8918 (1.8018)  weight_decay: 0.0500 (0.0500)  time: 1.0081  data: 0.0012  max mem: 78493
Epoch: [288]  [180/312]  eta: 0:02:26  lr: 0.000017  min_lr: 0.000017  loss: 1.9223 (1.7957)  weight_decay: 0.0500 (0.0500)  time: 1.0082  data: 0.0012  max mem: 78493
Epoch: [288]  [190/312]  eta: 0:02:14  lr: 0.000017  min_lr: 0.000017  loss: 1.9223 (1.7981)  weight_decay: 0.0500 (0.0500)  time: 1.0089  data: 0.0005  max mem: 78493
Epoch: [288]  [200/312]  eta: 0:02:02  lr: 0.000017  min_lr: 0.000017  loss: 1.9594 (1.7952)  weight_decay: 0.0500 (0.0500)  time: 1.0073  data: 0.0005  max mem: 78493
Epoch: [288]  [210/312]  eta: 0:01:51  lr: 0.000017  min_lr: 0.000017  loss: 1.8750 (1.7962)  weight_decay: 0.0500 (0.0500)  time: 1.0071  data: 0.0005  max mem: 78493
Epoch: [288]  [220/312]  eta: 0:01:40  lr: 0.000017  min_lr: 0.000017  loss: 1.8725 (1.7952)  weight_decay: 0.0500 (0.0500)  time: 1.0080  data: 0.0005  max mem: 78493
Epoch: [288]  [230/312]  eta: 0:01:29  lr: 0.000017  min_lr: 0.000017  loss: 1.8725 (1.7983)  weight_decay: 0.0500 (0.0500)  time: 1.0072  data: 0.0005  max mem: 78493
Epoch: [288]  [240/312]  eta: 0:01:17  lr: 0.000017  min_lr: 0.000017  loss: 1.8929 (1.7936)  weight_decay: 0.0500 (0.0500)  time: 1.0057  data: 0.0004  max mem: 78493
Epoch: [288]  [250/312]  eta: 0:01:06  lr: 0.000017  min_lr: 0.000017  loss: 1.9744 (1.8032)  weight_decay: 0.0500 (0.0500)  time: 1.0061  data: 0.0004  max mem: 78493
Epoch: [288]  [260/312]  eta: 0:00:55  lr: 0.000017  min_lr: 0.000017  loss: 1.9786 (1.8059)  weight_decay: 0.0500 (0.0500)  time: 1.0067  data: 0.0004  max mem: 78493
Epoch: [288]  [270/312]  eta: 0:00:45  lr: 0.000017  min_lr: 0.000017  loss: 1.8522 (1.8073)  weight_decay: 0.0500 (0.0500)  time: 1.0044  data: 0.0005  max mem: 78493
Epoch: [288]  [280/312]  eta: 0:00:34  lr: 0.000016  min_lr: 0.000016  loss: 1.8522 (1.8104)  weight_decay: 0.0500 (0.0500)  time: 1.0047  data: 0.0010  max mem: 78493
Epoch: [288]  [290/312]  eta: 0:00:23  lr: 0.000016  min_lr: 0.000016  loss: 1.8464 (1.8072)  weight_decay: 0.0500 (0.0500)  time: 1.0039  data: 0.0009  max mem: 78493
Epoch: [288]  [300/312]  eta: 0:00:12  lr: 0.000016  min_lr: 0.000016  loss: 1.7829 (1.8028)  weight_decay: 0.0500 (0.0500)  time: 1.0016  data: 0.0001  max mem: 78493
Epoch: [288]  [310/312]  eta: 0:00:02  lr: 0.000016  min_lr: 0.000016  loss: 1.7030 (1.7982)  weight_decay: 0.0500 (0.0500)  time: 1.0015  data: 0.0001  max mem: 78493
Epoch: [288]  [311/312]  eta: 0:00:01  lr: 0.000016  min_lr: 0.000016  loss: 1.6821 (1.7978)  weight_decay: 0.0500 (0.0500)  time: 1.0016  data: 0.0001  max mem: 78493
Epoch: [288] Total time: 0:05:33 (1.0699 s / it)
Averaged stats: lr: 0.000016  min_lr: 0.000016  loss: 1.6821 (1.8348)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:17  loss: 0.4809 (0.4809)  acc1: 87.8906 (87.8906)  acc5: 97.7865 (97.7865)  time: 8.6011  data: 8.3394  max mem: 78493
Test:  [8/9]  eta: 0:00:01  loss: 0.7241 (0.6699)  acc1: 82.1615 (82.0160)  acc5: 96.0938 (95.9840)  time: 1.1594  data: 0.9267  max mem: 78493
Test: Total time: 0:00:10 (1.2065 s / it)
* Acc@1 82.618 Acc@5 96.118 loss 0.656
Accuracy of the model on the 50000 test images: 82.6%
Max accuracy: 82.65%
Epoch: [289]  [  0/312]  eta: 1:27:57  lr: 0.000016  min_lr: 0.000016  loss: 2.0994 (2.0994)  weight_decay: 0.0500 (0.0500)  time: 16.9140  data: 15.0132  max mem: 78493
Epoch: [289]  [ 10/312]  eta: 0:13:11  lr: 0.000016  min_lr: 0.000016  loss: 1.9958 (1.9427)  weight_decay: 0.0500 (0.0500)  time: 2.6199  data: 1.3656  max mem: 78493
Epoch: [289]  [ 20/312]  eta: 0:09:02  lr: 0.000016  min_lr: 0.000016  loss: 1.8900 (1.8878)  weight_decay: 0.0500 (0.0500)  time: 1.1063  data: 0.0008  max mem: 78493
Epoch: [289]  [ 30/312]  eta: 0:07:27  lr: 0.000016  min_lr: 0.000016  loss: 1.9281 (1.8956)  weight_decay: 0.0500 (0.0500)  time: 1.0160  data: 0.0005  max mem: 78493
Epoch: [289]  [ 40/312]  eta: 0:06:32  lr: 0.000016  min_lr: 0.000016  loss: 1.9281 (1.8713)  weight_decay: 0.0500 (0.0500)  time: 1.0074  data: 0.0004  max mem: 78493
Epoch: [289]  [ 50/312]  eta: 0:05:55  lr: 0.000016  min_lr: 0.000016  loss: 1.7543 (1.8426)  weight_decay: 0.0500 (0.0500)  time: 1.0063  data: 0.0006  max mem: 78493
Epoch: [289]  [ 60/312]  eta: 0:05:27  lr: 0.000016  min_lr: 0.000016  loss: 1.6173 (1.8344)  weight_decay: 0.0500 (0.0500)  time: 1.0070  data: 0.0006  max mem: 78493
Epoch: [289]  [ 70/312]  eta: 0:05:04  lr: 0.000016  min_lr: 0.000016  loss: 1.9219 (1.8407)  weight_decay: 0.0500 (0.0500)  time: 1.0076  data: 0.0004  max mem: 78493
Epoch: [289]  [ 80/312]  eta: 0:04:45  lr: 0.000016  min_lr: 0.000016  loss: 1.9385 (1.8455)  weight_decay: 0.0500 (0.0500)  time: 1.0089  data: 0.0016  max mem: 78493
Epoch: [289]  [ 90/312]  eta: 0:04:27  lr: 0.000015  min_lr: 0.000015  loss: 1.8630 (1.8444)  weight_decay: 0.0500 (0.0500)  time: 1.0075  data: 0.0024  max mem: 78493
Epoch: [289]  [100/312]  eta: 0:04:11  lr: 0.000015  min_lr: 0.000015  loss: 1.9551 (1.8386)  weight_decay: 0.0500 (0.0500)  time: 1.0062  data: 0.0012  max mem: 78493
Epoch: [289]  [110/312]  eta: 0:03:56  lr: 0.000015  min_lr: 0.000015  loss: 1.9551 (1.8509)  weight_decay: 0.0500 (0.0500)  time: 1.0062  data: 0.0004  max mem: 78493
Epoch: [289]  [120/312]  eta: 0:03:41  lr: 0.000015  min_lr: 0.000015  loss: 1.9606 (1.8528)  weight_decay: 0.0500 (0.0500)  time: 1.0069  data: 0.0004  max mem: 78493
Epoch: [289]  [130/312]  eta: 0:03:28  lr: 0.000015  min_lr: 0.000015  loss: 1.7506 (1.8386)  weight_decay: 0.0500 (0.0500)  time: 1.0078  data: 0.0004  max mem: 78493
Epoch: [289]  [140/312]  eta: 0:03:15  lr: 0.000015  min_lr: 0.000015  loss: 1.6367 (1.8264)  weight_decay: 0.0500 (0.0500)  time: 1.0073  data: 0.0004  max mem: 78493
Epoch: [289]  [150/312]  eta: 0:03:02  lr: 0.000015  min_lr: 0.000015  loss: 1.9432 (1.8350)  weight_decay: 0.0500 (0.0500)  time: 1.0075  data: 0.0005  max mem: 78493
Epoch: [289]  [160/312]  eta: 0:02:49  lr: 0.000015  min_lr: 0.000015  loss: 1.9432 (1.8238)  weight_decay: 0.0500 (0.0500)  time: 1.0070  data: 0.0004  max mem: 78493
Epoch: [289]  [170/312]  eta: 0:02:37  lr: 0.000015  min_lr: 0.000015  loss: 1.6209 (1.8166)  weight_decay: 0.0500 (0.0500)  time: 1.0049  data: 0.0004  max mem: 78493
Epoch: [289]  [180/312]  eta: 0:02:25  lr: 0.000015  min_lr: 0.000015  loss: 2.0038 (1.8254)  weight_decay: 0.0500 (0.0500)  time: 1.0044  data: 0.0004  max mem: 78493
Epoch: [289]  [190/312]  eta: 0:02:14  lr: 0.000015  min_lr: 0.000015  loss: 1.9890 (1.8190)  weight_decay: 0.0500 (0.0500)  time: 1.0057  data: 0.0004  max mem: 78493
Epoch: [289]  [200/312]  eta: 0:02:02  lr: 0.000014  min_lr: 0.000014  loss: 1.7743 (1.8186)  weight_decay: 0.0500 (0.0500)  time: 1.0068  data: 0.0005  max mem: 78493
Epoch: [289]  [210/312]  eta: 0:01:51  lr: 0.000014  min_lr: 0.000014  loss: 1.9459 (1.8225)  weight_decay: 0.0500 (0.0500)  time: 1.0064  data: 0.0004  max mem: 78493
Epoch: [289]  [220/312]  eta: 0:01:40  lr: 0.000014  min_lr: 0.000014  loss: 1.9479 (1.8217)  weight_decay: 0.0500 (0.0500)  time: 1.0047  data: 0.0004  max mem: 78493
Epoch: [289]  [230/312]  eta: 0:01:28  lr: 0.000014  min_lr: 0.000014  loss: 1.8159 (1.8154)  weight_decay: 0.0500 (0.0500)  time: 1.0046  data: 0.0004  max mem: 78493
Epoch: [289]  [240/312]  eta: 0:01:17  lr: 0.000014  min_lr: 0.000014  loss: 1.9247 (1.8243)  weight_decay: 0.0500 (0.0500)  time: 1.0047  data: 0.0004  max mem: 78493
Epoch: [289]  [250/312]  eta: 0:01:06  lr: 0.000014  min_lr: 0.000014  loss: 1.9965 (1.8292)  weight_decay: 0.0500 (0.0500)  time: 1.0036  data: 0.0004  max mem: 78493
Epoch: [289]  [260/312]  eta: 0:00:55  lr: 0.000014  min_lr: 0.000014  loss: 1.9397 (1.8314)  weight_decay: 0.0500 (0.0500)  time: 1.0037  data: 0.0005  max mem: 78493
Epoch: [289]  [270/312]  eta: 0:00:45  lr: 0.000014  min_lr: 0.000014  loss: 1.9397 (1.8319)  weight_decay: 0.0500 (0.0500)  time: 1.0043  data: 0.0005  max mem: 78493
Epoch: [289]  [280/312]  eta: 0:00:34  lr: 0.000014  min_lr: 0.000014  loss: 2.0234 (1.8373)  weight_decay: 0.0500 (0.0500)  time: 1.0058  data: 0.0010  max mem: 78493
Epoch: [289]  [290/312]  eta: 0:00:23  lr: 0.000014  min_lr: 0.000014  loss: 1.7407 (1.8295)  weight_decay: 0.0500 (0.0500)  time: 1.0039  data: 0.0009  max mem: 78493
Epoch: [289]  [300/312]  eta: 0:00:12  lr: 0.000014  min_lr: 0.000014  loss: 1.7419 (1.8305)  weight_decay: 0.0500 (0.0500)  time: 1.0011  data: 0.0001  max mem: 78493
Epoch: [289]  [310/312]  eta: 0:00:02  lr: 0.000014  min_lr: 0.000014  loss: 1.8867 (1.8325)  weight_decay: 0.0500 (0.0500)  time: 1.0011  data: 0.0001  max mem: 78493
Epoch: [289]  [311/312]  eta: 0:00:01  lr: 0.000014  min_lr: 0.000014  loss: 1.9276 (1.8335)  weight_decay: 0.0500 (0.0500)  time: 1.0011  data: 0.0001  max mem: 78493
Epoch: [289] Total time: 0:05:33 (1.0688 s / it)
Averaged stats: lr: 0.000014  min_lr: 0.000014  loss: 1.9276 (1.8361)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:16  loss: 0.4798 (0.4798)  acc1: 87.7604 (87.7604)  acc5: 97.7865 (97.7865)  time: 8.4841  data: 8.2036  max mem: 78493
Test:  [8/9]  eta: 0:00:01  loss: 0.7212 (0.6671)  acc1: 82.4219 (82.1280)  acc5: 96.2240 (96.0160)  time: 1.1410  data: 0.9116  max mem: 78493
Test: Total time: 0:00:10 (1.1637 s / it)
* Acc@1 82.556 Acc@5 96.128 loss 0.654
Accuracy of the model on the 50000 test images: 82.6%
Max accuracy: 82.65%
Epoch: [290]  [  0/312]  eta: 1:27:03  lr: 0.000014  min_lr: 0.000014  loss: 1.9959 (1.9959)  weight_decay: 0.0500 (0.0500)  time: 16.7430  data: 15.7339  max mem: 78493
Epoch: [290]  [ 10/312]  eta: 0:13:06  lr: 0.000013  min_lr: 0.000013  loss: 1.9400 (1.8276)  weight_decay: 0.0500 (0.0500)  time: 2.6054  data: 1.4349  max mem: 78493
Epoch: [290]  [ 20/312]  eta: 0:09:01  lr: 0.000013  min_lr: 0.000013  loss: 1.8486 (1.8289)  weight_decay: 0.0500 (0.0500)  time: 1.1109  data: 0.0029  max mem: 78493
Epoch: [290]  [ 30/312]  eta: 0:07:25  lr: 0.000013  min_lr: 0.000013  loss: 1.8538 (1.8113)  weight_decay: 0.0500 (0.0500)  time: 1.0177  data: 0.0006  max mem: 78493
Epoch: [290]  [ 40/312]  eta: 0:06:31  lr: 0.000013  min_lr: 0.000013  loss: 1.8275 (1.7829)  weight_decay: 0.0500 (0.0500)  time: 1.0055  data: 0.0004  max mem: 78493
Epoch: [290]  [ 50/312]  eta: 0:05:55  lr: 0.000013  min_lr: 0.000013  loss: 1.8727 (1.8087)  weight_decay: 0.0500 (0.0500)  time: 1.0059  data: 0.0014  max mem: 78493
Epoch: [290]  [ 60/312]  eta: 0:05:27  lr: 0.000013  min_lr: 0.000013  loss: 1.8727 (1.8246)  weight_decay: 0.0500 (0.0500)  time: 1.0062  data: 0.0014  max mem: 78493
Epoch: [290]  [ 70/312]  eta: 0:05:04  lr: 0.000013  min_lr: 0.000013  loss: 1.9691 (1.8431)  weight_decay: 0.0500 (0.0500)  time: 1.0074  data: 0.0005  max mem: 78493
Epoch: [290]  [ 80/312]  eta: 0:04:44  lr: 0.000013  min_lr: 0.000013  loss: 1.9984 (1.8495)  weight_decay: 0.0500 (0.0500)  time: 1.0076  data: 0.0005  max mem: 78493
Epoch: [290]  [ 90/312]  eta: 0:04:27  lr: 0.000013  min_lr: 0.000013  loss: 1.7805 (1.8298)  weight_decay: 0.0500 (0.0500)  time: 1.0088  data: 0.0005  max mem: 78493
Epoch: [290]  [100/312]  eta: 0:04:10  lr: 0.000013  min_lr: 0.000013  loss: 1.6052 (1.8101)  weight_decay: 0.0500 (0.0500)  time: 1.0097  data: 0.0012  max mem: 78493
Epoch: [290]  [110/312]  eta: 0:03:55  lr: 0.000013  min_lr: 0.000013  loss: 1.7165 (1.8088)  weight_decay: 0.0500 (0.0500)  time: 1.0107  data: 0.0012  max mem: 78493
Epoch: [290]  [120/312]  eta: 0:03:41  lr: 0.000013  min_lr: 0.000013  loss: 1.8358 (1.8077)  weight_decay: 0.0500 (0.0500)  time: 1.0098  data: 0.0004  max mem: 78493
Epoch: [290]  [130/312]  eta: 0:03:28  lr: 0.000013  min_lr: 0.000013  loss: 1.9019 (1.8078)  weight_decay: 0.0500 (0.0500)  time: 1.0063  data: 0.0005  max mem: 78493
Epoch: [290]  [140/312]  eta: 0:03:15  lr: 0.000012  min_lr: 0.000012  loss: 1.8103 (1.8034)  weight_decay: 0.0500 (0.0500)  time: 1.0068  data: 0.0004  max mem: 78493
Epoch: [290]  [150/312]  eta: 0:03:02  lr: 0.000012  min_lr: 0.000012  loss: 1.8984 (1.8089)  weight_decay: 0.0500 (0.0500)  time: 1.0074  data: 0.0004  max mem: 78493
Epoch: [290]  [160/312]  eta: 0:02:49  lr: 0.000012  min_lr: 0.000012  loss: 1.8820 (1.8031)  weight_decay: 0.0500 (0.0500)  time: 1.0063  data: 0.0004  max mem: 78493
Epoch: [290]  [170/312]  eta: 0:02:37  lr: 0.000012  min_lr: 0.000012  loss: 1.8472 (1.8050)  weight_decay: 0.0500 (0.0500)  time: 1.0059  data: 0.0005  max mem: 78493
Epoch: [290]  [180/312]  eta: 0:02:25  lr: 0.000012  min_lr: 0.000012  loss: 1.8958 (1.8003)  weight_decay: 0.0500 (0.0500)  time: 1.0059  data: 0.0004  max mem: 78493
Epoch: [290]  [190/312]  eta: 0:02:14  lr: 0.000012  min_lr: 0.000012  loss: 1.6831 (1.7888)  weight_decay: 0.0500 (0.0500)  time: 1.0048  data: 0.0005  max mem: 78493
Epoch: [290]  [200/312]  eta: 0:02:02  lr: 0.000012  min_lr: 0.000012  loss: 1.7112 (1.7892)  weight_decay: 0.0500 (0.0500)  time: 1.0065  data: 0.0005  max mem: 78493
Epoch: [290]  [210/312]  eta: 0:01:51  lr: 0.000012  min_lr: 0.000012  loss: 1.7908 (1.7896)  weight_decay: 0.0500 (0.0500)  time: 1.0065  data: 0.0004  max mem: 78493
Epoch: [290]  [220/312]  eta: 0:01:40  lr: 0.000012  min_lr: 0.000012  loss: 1.9861 (1.8018)  weight_decay: 0.0500 (0.0500)  time: 1.0067  data: 0.0004  max mem: 78493
Epoch: [290]  [230/312]  eta: 0:01:28  lr: 0.000012  min_lr: 0.000012  loss: 2.0243 (1.8085)  weight_decay: 0.0500 (0.0500)  time: 1.0069  data: 0.0004  max mem: 78493
Epoch: [290]  [240/312]  eta: 0:01:17  lr: 0.000012  min_lr: 0.000012  loss: 1.9998 (1.8155)  weight_decay: 0.0500 (0.0500)  time: 1.0061  data: 0.0004  max mem: 78493
Epoch: [290]  [250/312]  eta: 0:01:06  lr: 0.000012  min_lr: 0.000012  loss: 1.9269 (1.8176)  weight_decay: 0.0500 (0.0500)  time: 1.0066  data: 0.0005  max mem: 78493
Epoch: [290]  [260/312]  eta: 0:00:55  lr: 0.000012  min_lr: 0.000012  loss: 1.8506 (1.8107)  weight_decay: 0.0500 (0.0500)  time: 1.0066  data: 0.0004  max mem: 78493
Epoch: [290]  [270/312]  eta: 0:00:45  lr: 0.000011  min_lr: 0.000011  loss: 1.7015 (1.8107)  weight_decay: 0.0500 (0.0500)  time: 1.0062  data: 0.0004  max mem: 78493
Epoch: [290]  [280/312]  eta: 0:00:34  lr: 0.000011  min_lr: 0.000011  loss: 1.9193 (1.8096)  weight_decay: 0.0500 (0.0500)  time: 1.0059  data: 0.0011  max mem: 78493
Epoch: [290]  [290/312]  eta: 0:00:23  lr: 0.000011  min_lr: 0.000011  loss: 1.8437 (1.8103)  weight_decay: 0.0500 (0.0500)  time: 1.0034  data: 0.0009  max mem: 78493
Epoch: [290]  [300/312]  eta: 0:00:12  lr: 0.000011  min_lr: 0.000011  loss: 1.9394 (1.8138)  weight_decay: 0.0500 (0.0500)  time: 1.0005  data: 0.0001  max mem: 78493
Epoch: [290]  [310/312]  eta: 0:00:02  lr: 0.000011  min_lr: 0.000011  loss: 1.9764 (1.8184)  weight_decay: 0.0500 (0.0500)  time: 1.0011  data: 0.0001  max mem: 78493
Epoch: [290]  [311/312]  eta: 0:00:01  lr: 0.000011  min_lr: 0.000011  loss: 1.9764 (1.8197)  weight_decay: 0.0500 (0.0500)  time: 1.0010  data: 0.0001  max mem: 78493
Epoch: [290] Total time: 0:05:33 (1.0689 s / it)
Averaged stats: lr: 0.000011  min_lr: 0.000011  loss: 1.9764 (1.8291)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:13  loss: 0.4823 (0.4823)  acc1: 87.2396 (87.2396)  acc5: 97.7865 (97.7865)  time: 8.1760  data: 7.9082  max mem: 78493
Test:  [8/9]  eta: 0:00:01  loss: 0.7209 (0.6682)  acc1: 82.0312 (82.0320)  acc5: 96.3542 (96.0160)  time: 1.1082  data: 0.8788  max mem: 78493
Test: Total time: 0:00:10 (1.1483 s / it)
* Acc@1 82.544 Acc@5 96.154 loss 0.654
Accuracy of the model on the 50000 test images: 82.5%
Max accuracy: 82.65%
Epoch: [291]  [  0/312]  eta: 1:27:02  lr: 0.000011  min_lr: 0.000011  loss: 1.8146 (1.8146)  weight_decay: 0.0500 (0.0500)  time: 16.7387  data: 15.2345  max mem: 78493
Epoch: [291]  [ 10/312]  eta: 0:12:56  lr: 0.000011  min_lr: 0.000011  loss: 1.7669 (1.7213)  weight_decay: 0.0500 (0.0500)  time: 2.5696  data: 1.3855  max mem: 78493
Epoch: [291]  [ 20/312]  eta: 0:08:56  lr: 0.000011  min_lr: 0.000011  loss: 1.7841 (1.7529)  weight_decay: 0.0500 (0.0500)  time: 1.0926  data: 0.0006  max mem: 78493
Epoch: [291]  [ 30/312]  eta: 0:07:22  lr: 0.000011  min_lr: 0.000011  loss: 1.9022 (1.7719)  weight_decay: 0.0500 (0.0500)  time: 1.0205  data: 0.0005  max mem: 78493
Epoch: [291]  [ 40/312]  eta: 0:06:29  lr: 0.000011  min_lr: 0.000011  loss: 1.9374 (1.8030)  weight_decay: 0.0500 (0.0500)  time: 1.0068  data: 0.0004  max mem: 78493
Epoch: [291]  [ 50/312]  eta: 0:05:53  lr: 0.000011  min_lr: 0.000011  loss: 1.8676 (1.7851)  weight_decay: 0.0500 (0.0500)  time: 1.0043  data: 0.0004  max mem: 78493
Epoch: [291]  [ 60/312]  eta: 0:05:25  lr: 0.000011  min_lr: 0.000011  loss: 1.9643 (1.7942)  weight_decay: 0.0500 (0.0500)  time: 1.0061  data: 0.0004  max mem: 78493
Epoch: [291]  [ 70/312]  eta: 0:05:03  lr: 0.000011  min_lr: 0.000011  loss: 2.0664 (1.8325)  weight_decay: 0.0500 (0.0500)  time: 1.0075  data: 0.0005  max mem: 78493
Epoch: [291]  [ 80/312]  eta: 0:04:43  lr: 0.000011  min_lr: 0.000011  loss: 2.0659 (1.8446)  weight_decay: 0.0500 (0.0500)  time: 1.0075  data: 0.0004  max mem: 78493
Epoch: [291]  [ 90/312]  eta: 0:04:26  lr: 0.000011  min_lr: 0.000011  loss: 2.0149 (1.8587)  weight_decay: 0.0500 (0.0500)  time: 1.0095  data: 0.0004  max mem: 78493
Epoch: [291]  [100/312]  eta: 0:04:10  lr: 0.000010  min_lr: 0.000010  loss: 2.0161 (1.8624)  weight_decay: 0.0500 (0.0500)  time: 1.0097  data: 0.0004  max mem: 78493
Epoch: [291]  [110/312]  eta: 0:03:55  lr: 0.000010  min_lr: 0.000010  loss: 1.9768 (1.8651)  weight_decay: 0.0500 (0.0500)  time: 1.0083  data: 0.0005  max mem: 78493
Epoch: [291]  [120/312]  eta: 0:03:41  lr: 0.000010  min_lr: 0.000010  loss: 1.7705 (1.8490)  weight_decay: 0.0500 (0.0500)  time: 1.0067  data: 0.0005  max mem: 78493
Epoch: [291]  [130/312]  eta: 0:03:27  lr: 0.000010  min_lr: 0.000010  loss: 1.9362 (1.8539)  weight_decay: 0.0500 (0.0500)  time: 1.0069  data: 0.0004  max mem: 78493
Epoch: [291]  [140/312]  eta: 0:03:14  lr: 0.000010  min_lr: 0.000010  loss: 1.9922 (1.8586)  weight_decay: 0.0500 (0.0500)  time: 1.0075  data: 0.0004  max mem: 78493
Epoch: [291]  [150/312]  eta: 0:03:01  lr: 0.000010  min_lr: 0.000010  loss: 1.8405 (1.8549)  weight_decay: 0.0500 (0.0500)  time: 1.0057  data: 0.0004  max mem: 78493
Epoch: [291]  [160/312]  eta: 0:02:49  lr: 0.000010  min_lr: 0.000010  loss: 1.9071 (1.8521)  weight_decay: 0.0500 (0.0500)  time: 1.0072  data: 0.0005  max mem: 78493
Epoch: [291]  [170/312]  eta: 0:02:37  lr: 0.000010  min_lr: 0.000010  loss: 1.8418 (1.8543)  weight_decay: 0.0500 (0.0500)  time: 1.0079  data: 0.0004  max mem: 78493
Epoch: [291]  [180/312]  eta: 0:02:25  lr: 0.000010  min_lr: 0.000010  loss: 1.8418 (1.8528)  weight_decay: 0.0500 (0.0500)  time: 1.0076  data: 0.0004  max mem: 78493
Epoch: [291]  [190/312]  eta: 0:02:14  lr: 0.000010  min_lr: 0.000010  loss: 1.8955 (1.8496)  weight_decay: 0.0500 (0.0500)  time: 1.0067  data: 0.0005  max mem: 78493
Epoch: [291]  [200/312]  eta: 0:02:02  lr: 0.000010  min_lr: 0.000010  loss: 1.8955 (1.8489)  weight_decay: 0.0500 (0.0500)  time: 1.0060  data: 0.0005  max mem: 78493
Epoch: [291]  [210/312]  eta: 0:01:51  lr: 0.000010  min_lr: 0.000010  loss: 1.8562 (1.8426)  weight_decay: 0.0500 (0.0500)  time: 1.0066  data: 0.0005  max mem: 78493
Epoch: [291]  [220/312]  eta: 0:01:39  lr: 0.000010  min_lr: 0.000010  loss: 1.7673 (1.8370)  weight_decay: 0.0500 (0.0500)  time: 1.0051  data: 0.0005  max mem: 78493
Epoch: [291]  [230/312]  eta: 0:01:28  lr: 0.000010  min_lr: 0.000010  loss: 1.6875 (1.8300)  weight_decay: 0.0500 (0.0500)  time: 1.0058  data: 0.0005  max mem: 78493
Epoch: [291]  [240/312]  eta: 0:01:17  lr: 0.000010  min_lr: 0.000010  loss: 1.7007 (1.8299)  weight_decay: 0.0500 (0.0500)  time: 1.0055  data: 0.0005  max mem: 78493
Epoch: [291]  [250/312]  eta: 0:01:06  lr: 0.000009  min_lr: 0.000009  loss: 1.9078 (1.8301)  weight_decay: 0.0500 (0.0500)  time: 1.0065  data: 0.0004  max mem: 78493
Epoch: [291]  [260/312]  eta: 0:00:55  lr: 0.000009  min_lr: 0.000009  loss: 1.9683 (1.8347)  weight_decay: 0.0500 (0.0500)  time: 1.0065  data: 0.0004  max mem: 78493
Epoch: [291]  [270/312]  eta: 0:00:44  lr: 0.000009  min_lr: 0.000009  loss: 1.9683 (1.8347)  weight_decay: 0.0500 (0.0500)  time: 1.0055  data: 0.0005  max mem: 78493
Epoch: [291]  [280/312]  eta: 0:00:34  lr: 0.000009  min_lr: 0.000009  loss: 1.9297 (1.8360)  weight_decay: 0.0500 (0.0500)  time: 1.0075  data: 0.0010  max mem: 78493
Epoch: [291]  [290/312]  eta: 0:00:23  lr: 0.000009  min_lr: 0.000009  loss: 2.0037 (1.8385)  weight_decay: 0.0500 (0.0500)  time: 1.0048  data: 0.0008  max mem: 78493
Epoch: [291]  [300/312]  eta: 0:00:12  lr: 0.000009  min_lr: 0.000009  loss: 2.0037 (1.8403)  weight_decay: 0.0500 (0.0500)  time: 1.0015  data: 0.0001  max mem: 78493
Epoch: [291]  [310/312]  eta: 0:00:02  lr: 0.000009  min_lr: 0.000009  loss: 1.9134 (1.8357)  weight_decay: 0.0500 (0.0500)  time: 1.0012  data: 0.0001  max mem: 78493
Epoch: [291]  [311/312]  eta: 0:00:01  lr: 0.000009  min_lr: 0.000009  loss: 1.9629 (1.8372)  weight_decay: 0.0500 (0.0500)  time: 1.0013  data: 0.0001  max mem: 78493
Epoch: [291] Total time: 0:05:33 (1.0675 s / it)
Averaged stats: lr: 0.000009  min_lr: 0.000009  loss: 1.9629 (1.8280)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:12  loss: 0.4801 (0.4801)  acc1: 87.3698 (87.3698)  acc5: 97.7865 (97.7865)  time: 8.0473  data: 7.7684  max mem: 78493
Test:  [8/9]  eta: 0:00:01  loss: 0.7200 (0.6675)  acc1: 82.4219 (82.1760)  acc5: 96.4844 (96.0000)  time: 1.0923  data: 0.8632  max mem: 78493
Test: Total time: 0:00:09 (1.1047 s / it)
* Acc@1 82.634 Acc@5 96.148 loss 0.655
Accuracy of the model on the 50000 test images: 82.6%
Max accuracy: 82.65%
Epoch: [292]  [  0/312]  eta: 1:24:21  lr: 0.000009  min_lr: 0.000009  loss: 2.3325 (2.3325)  weight_decay: 0.0500 (0.0500)  time: 16.2232  data: 11.9437  max mem: 78493
Epoch: [292]  [ 10/312]  eta: 0:13:20  lr: 0.000009  min_lr: 0.000009  loss: 1.7986 (1.7974)  weight_decay: 0.0500 (0.0500)  time: 2.6499  data: 1.2940  max mem: 78493
Epoch: [292]  [ 20/312]  eta: 0:09:08  lr: 0.000009  min_lr: 0.000009  loss: 1.7784 (1.7637)  weight_decay: 0.0500 (0.0500)  time: 1.1598  data: 0.1162  max mem: 78493
Epoch: [292]  [ 30/312]  eta: 0:07:30  lr: 0.000009  min_lr: 0.000009  loss: 1.8843 (1.8160)  weight_decay: 0.0500 (0.0500)  time: 1.0192  data: 0.0019  max mem: 78493
Epoch: [292]  [ 40/312]  eta: 0:06:35  lr: 0.000009  min_lr: 0.000009  loss: 1.9947 (1.8710)  weight_decay: 0.0500 (0.0500)  time: 1.0116  data: 0.0004  max mem: 78493
Epoch: [292]  [ 50/312]  eta: 0:05:58  lr: 0.000009  min_lr: 0.000009  loss: 1.9680 (1.8789)  weight_decay: 0.0500 (0.0500)  time: 1.0114  data: 0.0005  max mem: 78493
Epoch: [292]  [ 60/312]  eta: 0:05:29  lr: 0.000009  min_lr: 0.000009  loss: 1.9680 (1.8809)  weight_decay: 0.0500 (0.0500)  time: 1.0108  data: 0.0005  max mem: 78493
Epoch: [292]  [ 70/312]  eta: 0:05:06  lr: 0.000009  min_lr: 0.000009  loss: 1.9854 (1.8902)  weight_decay: 0.0500 (0.0500)  time: 1.0092  data: 0.0005  max mem: 78493
Epoch: [292]  [ 80/312]  eta: 0:04:46  lr: 0.000009  min_lr: 0.000009  loss: 1.9183 (1.8606)  weight_decay: 0.0500 (0.0500)  time: 1.0099  data: 0.0004  max mem: 78493
Epoch: [292]  [ 90/312]  eta: 0:04:28  lr: 0.000008  min_lr: 0.000008  loss: 1.7323 (1.8426)  weight_decay: 0.0500 (0.0500)  time: 1.0114  data: 0.0005  max mem: 78493
Epoch: [292]  [100/312]  eta: 0:04:12  lr: 0.000008  min_lr: 0.000008  loss: 1.7323 (1.8480)  weight_decay: 0.0500 (0.0500)  time: 1.0099  data: 0.0005  max mem: 78493
Epoch: [292]  [110/312]  eta: 0:03:57  lr: 0.000008  min_lr: 0.000008  loss: 1.8506 (1.8381)  weight_decay: 0.0500 (0.0500)  time: 1.0080  data: 0.0005  max mem: 78493
Epoch: [292]  [120/312]  eta: 0:03:42  lr: 0.000008  min_lr: 0.000008  loss: 1.7879 (1.8264)  weight_decay: 0.0500 (0.0500)  time: 1.0076  data: 0.0004  max mem: 78493
Epoch: [292]  [130/312]  eta: 0:03:29  lr: 0.000008  min_lr: 0.000008  loss: 1.8228 (1.8250)  weight_decay: 0.0500 (0.0500)  time: 1.0065  data: 0.0004  max mem: 78493
Epoch: [292]  [140/312]  eta: 0:03:15  lr: 0.000008  min_lr: 0.000008  loss: 1.8608 (1.8228)  weight_decay: 0.0500 (0.0500)  time: 1.0047  data: 0.0004  max mem: 78493
Epoch: [292]  [150/312]  eta: 0:03:02  lr: 0.000008  min_lr: 0.000008  loss: 1.9418 (1.8231)  weight_decay: 0.0500 (0.0500)  time: 1.0050  data: 0.0013  max mem: 78493
Epoch: [292]  [160/312]  eta: 0:02:50  lr: 0.000008  min_lr: 0.000008  loss: 1.9014 (1.8283)  weight_decay: 0.0500 (0.0500)  time: 1.0046  data: 0.0013  max mem: 78493
Epoch: [292]  [170/312]  eta: 0:02:38  lr: 0.000008  min_lr: 0.000008  loss: 1.9215 (1.8340)  weight_decay: 0.0500 (0.0500)  time: 1.0067  data: 0.0004  max mem: 78493
Epoch: [292]  [180/312]  eta: 0:02:26  lr: 0.000008  min_lr: 0.000008  loss: 1.8709 (1.8286)  weight_decay: 0.0500 (0.0500)  time: 1.0095  data: 0.0005  max mem: 78493
Epoch: [292]  [190/312]  eta: 0:02:14  lr: 0.000008  min_lr: 0.000008  loss: 1.8673 (1.8276)  weight_decay: 0.0500 (0.0500)  time: 1.0069  data: 0.0005  max mem: 78493
Epoch: [292]  [200/312]  eta: 0:02:03  lr: 0.000008  min_lr: 0.000008  loss: 1.9308 (1.8397)  weight_decay: 0.0500 (0.0500)  time: 1.0078  data: 0.0005  max mem: 78493
Epoch: [292]  [210/312]  eta: 0:01:51  lr: 0.000008  min_lr: 0.000008  loss: 1.9866 (1.8385)  weight_decay: 0.0500 (0.0500)  time: 1.0111  data: 0.0005  max mem: 78493
Epoch: [292]  [220/312]  eta: 0:01:40  lr: 0.000008  min_lr: 0.000008  loss: 1.9682 (1.8412)  weight_decay: 0.0500 (0.0500)  time: 1.0084  data: 0.0005  max mem: 78493
Epoch: [292]  [230/312]  eta: 0:01:29  lr: 0.000008  min_lr: 0.000008  loss: 1.6706 (1.8292)  weight_decay: 0.0500 (0.0500)  time: 1.0052  data: 0.0004  max mem: 78493
Epoch: [292]  [240/312]  eta: 0:01:18  lr: 0.000008  min_lr: 0.000008  loss: 1.6706 (1.8315)  weight_decay: 0.0500 (0.0500)  time: 1.0062  data: 0.0004  max mem: 78493
Epoch: [292]  [250/312]  eta: 0:01:07  lr: 0.000008  min_lr: 0.000008  loss: 1.6915 (1.8205)  weight_decay: 0.0500 (0.0500)  time: 1.0059  data: 0.0004  max mem: 78493
Epoch: [292]  [260/312]  eta: 0:00:56  lr: 0.000007  min_lr: 0.000007  loss: 1.5356 (1.8143)  weight_decay: 0.0500 (0.0500)  time: 1.0064  data: 0.0004  max mem: 78493
Epoch: [292]  [270/312]  eta: 0:00:45  lr: 0.000007  min_lr: 0.000007  loss: 1.8491 (1.8191)  weight_decay: 0.0500 (0.0500)  time: 1.0074  data: 0.0004  max mem: 78493
Epoch: [292]  [280/312]  eta: 0:00:34  lr: 0.000007  min_lr: 0.000007  loss: 1.9092 (1.8176)  weight_decay: 0.0500 (0.0500)  time: 1.0073  data: 0.0010  max mem: 78493
Epoch: [292]  [290/312]  eta: 0:00:23  lr: 0.000007  min_lr: 0.000007  loss: 1.7197 (1.8153)  weight_decay: 0.0500 (0.0500)  time: 1.0051  data: 0.0009  max mem: 78493
Epoch: [292]  [300/312]  eta: 0:00:12  lr: 0.000007  min_lr: 0.000007  loss: 1.9385 (1.8170)  weight_decay: 0.0500 (0.0500)  time: 1.0017  data: 0.0001  max mem: 78493
Epoch: [292]  [310/312]  eta: 0:00:02  lr: 0.000007  min_lr: 0.000007  loss: 1.8346 (1.8149)  weight_decay: 0.0500 (0.0500)  time: 1.0016  data: 0.0001  max mem: 78493
Epoch: [292]  [311/312]  eta: 0:00:01  lr: 0.000007  min_lr: 0.000007  loss: 1.8813 (1.8156)  weight_decay: 0.0500 (0.0500)  time: 1.0016  data: 0.0001  max mem: 78493
Epoch: [292] Total time: 0:05:34 (1.0716 s / it)
Averaged stats: lr: 0.000007  min_lr: 0.000007  loss: 1.8813 (1.8402)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:09  loss: 0.4809 (0.4809)  acc1: 87.6302 (87.6302)  acc5: 97.7865 (97.7865)  time: 7.7745  data: 7.4929  max mem: 78493
Test:  [8/9]  eta: 0:00:01  loss: 0.7195 (0.6678)  acc1: 82.4219 (82.0000)  acc5: 96.2240 (96.0000)  time: 1.1119  data: 0.8826  max mem: 78493
Test: Total time: 0:00:10 (1.1223 s / it)
* Acc@1 82.566 Acc@5 96.112 loss 0.655
Accuracy of the model on the 50000 test images: 82.6%
Max accuracy: 82.65%
Epoch: [293]  [  0/312]  eta: 1:23:17  lr: 0.000007  min_lr: 0.000007  loss: 1.4877 (1.4877)  weight_decay: 0.0500 (0.0500)  time: 16.0161  data: 13.6179  max mem: 78493
Epoch: [293]  [ 10/312]  eta: 0:12:46  lr: 0.000007  min_lr: 0.000007  loss: 1.6449 (1.7272)  weight_decay: 0.0500 (0.0500)  time: 2.5365  data: 1.2526  max mem: 78493
Epoch: [293]  [ 20/312]  eta: 0:08:51  lr: 0.000007  min_lr: 0.000007  loss: 1.6900 (1.7884)  weight_decay: 0.0500 (0.0500)  time: 1.1119  data: 0.0083  max mem: 78493
Epoch: [293]  [ 30/312]  eta: 0:07:20  lr: 0.000007  min_lr: 0.000007  loss: 1.9206 (1.7988)  weight_decay: 0.0500 (0.0500)  time: 1.0242  data: 0.0005  max mem: 78493
Epoch: [293]  [ 40/312]  eta: 0:06:27  lr: 0.000007  min_lr: 0.000007  loss: 1.9897 (1.8277)  weight_decay: 0.0500 (0.0500)  time: 1.0099  data: 0.0004  max mem: 78493
Epoch: [293]  [ 50/312]  eta: 0:05:52  lr: 0.000007  min_lr: 0.000007  loss: 1.9897 (1.8410)  weight_decay: 0.0500 (0.0500)  time: 1.0077  data: 0.0004  max mem: 78493
Epoch: [293]  [ 60/312]  eta: 0:05:24  lr: 0.000007  min_lr: 0.000007  loss: 1.9825 (1.8380)  weight_decay: 0.0500 (0.0500)  time: 1.0071  data: 0.0004  max mem: 78493
Epoch: [293]  [ 70/312]  eta: 0:05:02  lr: 0.000007  min_lr: 0.000007  loss: 1.8501 (1.8276)  weight_decay: 0.0500 (0.0500)  time: 1.0087  data: 0.0011  max mem: 78493
Epoch: [293]  [ 80/312]  eta: 0:04:42  lr: 0.000007  min_lr: 0.000007  loss: 1.7883 (1.8291)  weight_decay: 0.0500 (0.0500)  time: 1.0098  data: 0.0011  max mem: 78493
Epoch: [293]  [ 90/312]  eta: 0:04:25  lr: 0.000007  min_lr: 0.000007  loss: 1.7391 (1.8100)  weight_decay: 0.0500 (0.0500)  time: 1.0090  data: 0.0005  max mem: 78493
Epoch: [293]  [100/312]  eta: 0:04:09  lr: 0.000007  min_lr: 0.000007  loss: 1.7391 (1.8121)  weight_decay: 0.0500 (0.0500)  time: 1.0141  data: 0.0004  max mem: 78493
Epoch: [293]  [110/312]  eta: 0:03:55  lr: 0.000007  min_lr: 0.000007  loss: 1.9628 (1.8192)  weight_decay: 0.0500 (0.0500)  time: 1.0129  data: 0.0004  max mem: 78493
Epoch: [293]  [120/312]  eta: 0:03:40  lr: 0.000007  min_lr: 0.000007  loss: 1.9628 (1.8224)  weight_decay: 0.0500 (0.0500)  time: 1.0084  data: 0.0004  max mem: 78493
Epoch: [293]  [130/312]  eta: 0:03:27  lr: 0.000006  min_lr: 0.000006  loss: 1.9086 (1.8332)  weight_decay: 0.0500 (0.0500)  time: 1.0105  data: 0.0004  max mem: 78493
Epoch: [293]  [140/312]  eta: 0:03:14  lr: 0.000006  min_lr: 0.000006  loss: 1.8521 (1.8253)  weight_decay: 0.0500 (0.0500)  time: 1.0104  data: 0.0004  max mem: 78493
Epoch: [293]  [150/312]  eta: 0:03:01  lr: 0.000006  min_lr: 0.000006  loss: 1.8950 (1.8305)  weight_decay: 0.0500 (0.0500)  time: 1.0079  data: 0.0004  max mem: 78493
Epoch: [293]  [160/312]  eta: 0:02:49  lr: 0.000006  min_lr: 0.000006  loss: 2.0010 (1.8391)  weight_decay: 0.0500 (0.0500)  time: 1.0081  data: 0.0004  max mem: 78493
Epoch: [293]  [170/312]  eta: 0:02:37  lr: 0.000006  min_lr: 0.000006  loss: 1.9473 (1.8354)  weight_decay: 0.0500 (0.0500)  time: 1.0073  data: 0.0004  max mem: 78493
Epoch: [293]  [180/312]  eta: 0:02:25  lr: 0.000006  min_lr: 0.000006  loss: 1.9089 (1.8378)  weight_decay: 0.0500 (0.0500)  time: 1.0081  data: 0.0004  max mem: 78493
Epoch: [293]  [190/312]  eta: 0:02:14  lr: 0.000006  min_lr: 0.000006  loss: 1.9089 (1.8299)  weight_decay: 0.0500 (0.0500)  time: 1.0119  data: 0.0004  max mem: 78493
Epoch: [293]  [200/312]  eta: 0:02:02  lr: 0.000006  min_lr: 0.000006  loss: 1.7913 (1.8361)  weight_decay: 0.0500 (0.0500)  time: 1.0108  data: 0.0004  max mem: 78493
Epoch: [293]  [210/312]  eta: 0:01:51  lr: 0.000006  min_lr: 0.000006  loss: 1.7913 (1.8316)  weight_decay: 0.0500 (0.0500)  time: 1.0083  data: 0.0004  max mem: 78493
Epoch: [293]  [220/312]  eta: 0:01:39  lr: 0.000006  min_lr: 0.000006  loss: 1.6986 (1.8322)  weight_decay: 0.0500 (0.0500)  time: 1.0082  data: 0.0004  max mem: 78493
Epoch: [293]  [230/312]  eta: 0:01:28  lr: 0.000006  min_lr: 0.000006  loss: 1.6986 (1.8266)  weight_decay: 0.0500 (0.0500)  time: 1.0068  data: 0.0004  max mem: 78493
Epoch: [293]  [240/312]  eta: 0:01:17  lr: 0.000006  min_lr: 0.000006  loss: 1.9775 (1.8299)  weight_decay: 0.0500 (0.0500)  time: 1.0059  data: 0.0004  max mem: 78493
Epoch: [293]  [250/312]  eta: 0:01:06  lr: 0.000006  min_lr: 0.000006  loss: 1.9562 (1.8277)  weight_decay: 0.0500 (0.0500)  time: 1.0065  data: 0.0005  max mem: 78493
Epoch: [293]  [260/312]  eta: 0:00:55  lr: 0.000006  min_lr: 0.000006  loss: 1.8445 (1.8256)  weight_decay: 0.0500 (0.0500)  time: 1.0068  data: 0.0005  max mem: 78493
Epoch: [293]  [270/312]  eta: 0:00:45  lr: 0.000006  min_lr: 0.000006  loss: 1.8847 (1.8285)  weight_decay: 0.0500 (0.0500)  time: 1.0069  data: 0.0005  max mem: 78493
Epoch: [293]  [280/312]  eta: 0:00:34  lr: 0.000006  min_lr: 0.000006  loss: 1.9207 (1.8254)  weight_decay: 0.0500 (0.0500)  time: 1.0077  data: 0.0010  max mem: 78493
Epoch: [293]  [290/312]  eta: 0:00:23  lr: 0.000006  min_lr: 0.000006  loss: 1.8874 (1.8262)  weight_decay: 0.0500 (0.0500)  time: 1.0050  data: 0.0008  max mem: 78493
Epoch: [293]  [300/312]  eta: 0:00:12  lr: 0.000006  min_lr: 0.000006  loss: 1.9048 (1.8285)  weight_decay: 0.0500 (0.0500)  time: 1.0016  data: 0.0001  max mem: 78493
Epoch: [293]  [310/312]  eta: 0:00:02  lr: 0.000006  min_lr: 0.000006  loss: 1.7106 (1.8224)  weight_decay: 0.0500 (0.0500)  time: 1.0014  data: 0.0001  max mem: 78493
Epoch: [293]  [311/312]  eta: 0:00:01  lr: 0.000006  min_lr: 0.000006  loss: 1.7106 (1.8232)  weight_decay: 0.0500 (0.0500)  time: 1.0014  data: 0.0001  max mem: 78493
Epoch: [293] Total time: 0:05:33 (1.0687 s / it)
Averaged stats: lr: 0.000006  min_lr: 0.000006  loss: 1.7106 (1.8238)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:17  loss: 0.4803 (0.4803)  acc1: 87.7604 (87.7604)  acc5: 97.7865 (97.7865)  time: 8.6069  data: 8.3458  max mem: 78493
Test:  [8/9]  eta: 0:00:01  loss: 0.7181 (0.6665)  acc1: 82.5521 (82.1600)  acc5: 96.3542 (96.0000)  time: 1.1596  data: 0.9274  max mem: 78493
Test: Total time: 0:00:10 (1.2089 s / it)
* Acc@1 82.640 Acc@5 96.124 loss 0.654
Accuracy of the model on the 50000 test images: 82.6%
Max accuracy: 82.65%
Epoch: [294]  [  0/312]  eta: 1:25:02  lr: 0.000006  min_lr: 0.000006  loss: 1.8977 (1.8977)  weight_decay: 0.0500 (0.0500)  time: 16.3528  data: 15.3510  max mem: 78493
Epoch: [294]  [ 10/312]  eta: 0:13:37  lr: 0.000005  min_lr: 0.000005  loss: 1.8400 (1.8014)  weight_decay: 0.0500 (0.0500)  time: 2.7064  data: 1.3988  max mem: 78493
Epoch: [294]  [ 20/312]  eta: 0:09:14  lr: 0.000005  min_lr: 0.000005  loss: 1.6785 (1.7415)  weight_decay: 0.0500 (0.0500)  time: 1.1776  data: 0.0020  max mem: 78493
Epoch: [294]  [ 30/312]  eta: 0:07:34  lr: 0.000005  min_lr: 0.000005  loss: 1.8097 (1.7900)  weight_decay: 0.0500 (0.0500)  time: 1.0102  data: 0.0004  max mem: 78493
Epoch: [294]  [ 40/312]  eta: 0:06:38  lr: 0.000005  min_lr: 0.000005  loss: 1.8097 (1.7690)  weight_decay: 0.0500 (0.0500)  time: 1.0084  data: 0.0004  max mem: 78493
Epoch: [294]  [ 50/312]  eta: 0:06:00  lr: 0.000005  min_lr: 0.000005  loss: 1.6938 (1.7680)  weight_decay: 0.0500 (0.0500)  time: 1.0080  data: 0.0004  max mem: 78493
Epoch: [294]  [ 60/312]  eta: 0:05:31  lr: 0.000005  min_lr: 0.000005  loss: 1.8336 (1.7673)  weight_decay: 0.0500 (0.0500)  time: 1.0073  data: 0.0005  max mem: 78493
Epoch: [294]  [ 70/312]  eta: 0:05:07  lr: 0.000005  min_lr: 0.000005  loss: 1.8711 (1.7674)  weight_decay: 0.0500 (0.0500)  time: 1.0083  data: 0.0004  max mem: 78493
Epoch: [294]  [ 80/312]  eta: 0:04:47  lr: 0.000005  min_lr: 0.000005  loss: 1.9051 (1.7607)  weight_decay: 0.0500 (0.0500)  time: 1.0087  data: 0.0004  max mem: 78493
Epoch: [294]  [ 90/312]  eta: 0:04:29  lr: 0.000005  min_lr: 0.000005  loss: 1.7512 (1.7585)  weight_decay: 0.0500 (0.0500)  time: 1.0080  data: 0.0005  max mem: 78493
Epoch: [294]  [100/312]  eta: 0:04:12  lr: 0.000005  min_lr: 0.000005  loss: 1.8173 (1.7581)  weight_decay: 0.0500 (0.0500)  time: 1.0066  data: 0.0013  max mem: 78493
Epoch: [294]  [110/312]  eta: 0:03:57  lr: 0.000005  min_lr: 0.000005  loss: 1.8949 (1.7663)  weight_decay: 0.0500 (0.0500)  time: 1.0068  data: 0.0013  max mem: 78493
Epoch: [294]  [120/312]  eta: 0:03:43  lr: 0.000005  min_lr: 0.000005  loss: 1.8435 (1.7621)  weight_decay: 0.0500 (0.0500)  time: 1.0064  data: 0.0005  max mem: 78493
Epoch: [294]  [130/312]  eta: 0:03:29  lr: 0.000005  min_lr: 0.000005  loss: 1.6071 (1.7522)  weight_decay: 0.0500 (0.0500)  time: 1.0058  data: 0.0005  max mem: 78493
Epoch: [294]  [140/312]  eta: 0:03:16  lr: 0.000005  min_lr: 0.000005  loss: 1.5902 (1.7521)  weight_decay: 0.0500 (0.0500)  time: 1.0075  data: 0.0005  max mem: 78493
Epoch: [294]  [150/312]  eta: 0:03:03  lr: 0.000005  min_lr: 0.000005  loss: 1.8071 (1.7524)  weight_decay: 0.0500 (0.0500)  time: 1.0094  data: 0.0004  max mem: 78493
Epoch: [294]  [160/312]  eta: 0:02:50  lr: 0.000005  min_lr: 0.000005  loss: 1.8242 (1.7552)  weight_decay: 0.0500 (0.0500)  time: 1.0097  data: 0.0004  max mem: 78493
Epoch: [294]  [170/312]  eta: 0:02:38  lr: 0.000005  min_lr: 0.000005  loss: 1.8519 (1.7610)  weight_decay: 0.0500 (0.0500)  time: 1.0098  data: 0.0004  max mem: 78493
Epoch: [294]  [180/312]  eta: 0:02:26  lr: 0.000005  min_lr: 0.000005  loss: 1.8104 (1.7615)  weight_decay: 0.0500 (0.0500)  time: 1.0097  data: 0.0004  max mem: 78493
Epoch: [294]  [190/312]  eta: 0:02:14  lr: 0.000005  min_lr: 0.000005  loss: 1.6868 (1.7637)  weight_decay: 0.0500 (0.0500)  time: 1.0082  data: 0.0004  max mem: 78493
Epoch: [294]  [200/312]  eta: 0:02:03  lr: 0.000005  min_lr: 0.000005  loss: 1.6845 (1.7622)  weight_decay: 0.0500 (0.0500)  time: 1.0092  data: 0.0004  max mem: 78493
Epoch: [294]  [210/312]  eta: 0:01:51  lr: 0.000005  min_lr: 0.000005  loss: 1.7025 (1.7676)  weight_decay: 0.0500 (0.0500)  time: 1.0082  data: 0.0005  max mem: 78493
Epoch: [294]  [220/312]  eta: 0:01:40  lr: 0.000005  min_lr: 0.000005  loss: 1.9718 (1.7707)  weight_decay: 0.0500 (0.0500)  time: 1.0062  data: 0.0004  max mem: 78493
Epoch: [294]  [230/312]  eta: 0:01:29  lr: 0.000004  min_lr: 0.000004  loss: 1.7258 (1.7735)  weight_decay: 0.0500 (0.0500)  time: 1.0087  data: 0.0011  max mem: 78493
Epoch: [294]  [240/312]  eta: 0:01:18  lr: 0.000004  min_lr: 0.000004  loss: 1.8711 (1.7767)  weight_decay: 0.0500 (0.0500)  time: 1.0079  data: 0.0011  max mem: 78493
Epoch: [294]  [250/312]  eta: 0:01:07  lr: 0.000004  min_lr: 0.000004  loss: 1.8711 (1.7790)  weight_decay: 0.0500 (0.0500)  time: 1.0054  data: 0.0004  max mem: 78493
Epoch: [294]  [260/312]  eta: 0:00:56  lr: 0.000004  min_lr: 0.000004  loss: 1.9214 (1.7829)  weight_decay: 0.0500 (0.0500)  time: 1.0059  data: 0.0005  max mem: 78493
Epoch: [294]  [270/312]  eta: 0:00:45  lr: 0.000004  min_lr: 0.000004  loss: 1.9442 (1.7845)  weight_decay: 0.0500 (0.0500)  time: 1.0068  data: 0.0005  max mem: 78493
Epoch: [294]  [280/312]  eta: 0:00:34  lr: 0.000004  min_lr: 0.000004  loss: 1.9563 (1.7887)  weight_decay: 0.0500 (0.0500)  time: 1.0066  data: 0.0011  max mem: 78493
Epoch: [294]  [290/312]  eta: 0:00:23  lr: 0.000004  min_lr: 0.000004  loss: 1.9366 (1.7909)  weight_decay: 0.0500 (0.0500)  time: 1.0039  data: 0.0009  max mem: 78493
Epoch: [294]  [300/312]  eta: 0:00:12  lr: 0.000004  min_lr: 0.000004  loss: 1.6438 (1.7834)  weight_decay: 0.0500 (0.0500)  time: 1.0017  data: 0.0001  max mem: 78493
Epoch: [294]  [310/312]  eta: 0:00:02  lr: 0.000004  min_lr: 0.000004  loss: 1.7396 (1.7812)  weight_decay: 0.0500 (0.0500)  time: 1.0016  data: 0.0001  max mem: 78493
Epoch: [294]  [311/312]  eta: 0:00:01  lr: 0.000004  min_lr: 0.000004  loss: 1.7396 (1.7827)  weight_decay: 0.0500 (0.0500)  time: 1.0016  data: 0.0001  max mem: 78493
Epoch: [294] Total time: 0:05:34 (1.0729 s / it)
Averaged stats: lr: 0.000004  min_lr: 0.000004  loss: 1.7396 (1.8177)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:14  loss: 0.4787 (0.4787)  acc1: 87.6302 (87.6302)  acc5: 97.7865 (97.7865)  time: 8.2973  data: 8.0164  max mem: 78493
Test:  [8/9]  eta: 0:00:01  loss: 0.7183 (0.6659)  acc1: 82.2917 (82.0800)  acc5: 96.2240 (95.9680)  time: 1.1202  data: 0.8908  max mem: 78493
Test: Total time: 0:00:10 (1.1547 s / it)
* Acc@1 82.658 Acc@5 96.146 loss 0.653
Accuracy of the model on the 50000 test images: 82.7%
Max accuracy: 82.66%
Epoch: [295]  [  0/312]  eta: 1:22:21  lr: 0.000004  min_lr: 0.000004  loss: 1.9330 (1.9330)  weight_decay: 0.0500 (0.0500)  time: 15.8372  data: 14.8310  max mem: 78493
Epoch: [295]  [ 10/312]  eta: 0:13:11  lr: 0.000004  min_lr: 0.000004  loss: 1.7883 (1.7642)  weight_decay: 0.0500 (0.0500)  time: 2.6196  data: 1.3489  max mem: 78493
Epoch: [295]  [ 20/312]  eta: 0:09:01  lr: 0.000004  min_lr: 0.000004  loss: 1.6402 (1.7634)  weight_decay: 0.0500 (0.0500)  time: 1.1569  data: 0.0005  max mem: 78493
Epoch: [295]  [ 30/312]  eta: 0:07:26  lr: 0.000004  min_lr: 0.000004  loss: 1.7547 (1.8108)  weight_decay: 0.0500 (0.0500)  time: 1.0124  data: 0.0004  max mem: 78493
Epoch: [295]  [ 40/312]  eta: 0:06:32  lr: 0.000004  min_lr: 0.000004  loss: 1.8088 (1.8111)  weight_decay: 0.0500 (0.0500)  time: 1.0082  data: 0.0004  max mem: 78493
Epoch: [295]  [ 50/312]  eta: 0:05:55  lr: 0.000004  min_lr: 0.000004  loss: 1.8494 (1.8256)  weight_decay: 0.0500 (0.0500)  time: 1.0074  data: 0.0004  max mem: 78493
Epoch: [295]  [ 60/312]  eta: 0:05:27  lr: 0.000004  min_lr: 0.000004  loss: 1.9070 (1.8092)  weight_decay: 0.0500 (0.0500)  time: 1.0071  data: 0.0004  max mem: 78493
Epoch: [295]  [ 70/312]  eta: 0:05:04  lr: 0.000004  min_lr: 0.000004  loss: 1.6732 (1.7857)  weight_decay: 0.0500 (0.0500)  time: 1.0073  data: 0.0004  max mem: 78493
Epoch: [295]  [ 80/312]  eta: 0:04:44  lr: 0.000004  min_lr: 0.000004  loss: 1.7549 (1.7902)  weight_decay: 0.0500 (0.0500)  time: 1.0087  data: 0.0005  max mem: 78493
Epoch: [295]  [ 90/312]  eta: 0:04:27  lr: 0.000004  min_lr: 0.000004  loss: 1.7799 (1.7918)  weight_decay: 0.0500 (0.0500)  time: 1.0089  data: 0.0004  max mem: 78493
Epoch: [295]  [100/312]  eta: 0:04:11  lr: 0.000004  min_lr: 0.000004  loss: 1.8673 (1.7944)  weight_decay: 0.0500 (0.0500)  time: 1.0093  data: 0.0005  max mem: 78493
Epoch: [295]  [110/312]  eta: 0:03:56  lr: 0.000004  min_lr: 0.000004  loss: 1.9041 (1.7997)  weight_decay: 0.0500 (0.0500)  time: 1.0099  data: 0.0005  max mem: 78493
Epoch: [295]  [120/312]  eta: 0:03:41  lr: 0.000004  min_lr: 0.000004  loss: 1.9001 (1.8033)  weight_decay: 0.0500 (0.0500)  time: 1.0086  data: 0.0004  max mem: 78493
Epoch: [295]  [130/312]  eta: 0:03:28  lr: 0.000004  min_lr: 0.000004  loss: 1.9607 (1.8174)  weight_decay: 0.0500 (0.0500)  time: 1.0060  data: 0.0004  max mem: 78493
Epoch: [295]  [140/312]  eta: 0:03:15  lr: 0.000004  min_lr: 0.000004  loss: 1.9607 (1.8159)  weight_decay: 0.0500 (0.0500)  time: 1.0042  data: 0.0005  max mem: 78493
Epoch: [295]  [150/312]  eta: 0:03:02  lr: 0.000004  min_lr: 0.000004  loss: 1.7691 (1.8120)  weight_decay: 0.0500 (0.0500)  time: 1.0063  data: 0.0005  max mem: 78493
Epoch: [295]  [160/312]  eta: 0:02:49  lr: 0.000004  min_lr: 0.000004  loss: 1.9547 (1.8182)  weight_decay: 0.0500 (0.0500)  time: 1.0073  data: 0.0004  max mem: 78493
Epoch: [295]  [170/312]  eta: 0:02:37  lr: 0.000003  min_lr: 0.000003  loss: 1.9547 (1.8213)  weight_decay: 0.0500 (0.0500)  time: 1.0061  data: 0.0005  max mem: 78493
Epoch: [295]  [180/312]  eta: 0:02:25  lr: 0.000003  min_lr: 0.000003  loss: 1.9120 (1.8239)  weight_decay: 0.0500 (0.0500)  time: 1.0068  data: 0.0005  max mem: 78493
Epoch: [295]  [190/312]  eta: 0:02:14  lr: 0.000003  min_lr: 0.000003  loss: 1.9252 (1.8253)  weight_decay: 0.0500 (0.0500)  time: 1.0077  data: 0.0005  max mem: 78493
Epoch: [295]  [200/312]  eta: 0:02:02  lr: 0.000003  min_lr: 0.000003  loss: 1.9591 (1.8274)  weight_decay: 0.0500 (0.0500)  time: 1.0073  data: 0.0005  max mem: 78493
Epoch: [295]  [210/312]  eta: 0:01:51  lr: 0.000003  min_lr: 0.000003  loss: 1.8974 (1.8252)  weight_decay: 0.0500 (0.0500)  time: 1.0053  data: 0.0005  max mem: 78493
Epoch: [295]  [220/312]  eta: 0:01:40  lr: 0.000003  min_lr: 0.000003  loss: 1.8713 (1.8276)  weight_decay: 0.0500 (0.0500)  time: 1.0047  data: 0.0005  max mem: 78493
Epoch: [295]  [230/312]  eta: 0:01:28  lr: 0.000003  min_lr: 0.000003  loss: 1.9753 (1.8347)  weight_decay: 0.0500 (0.0500)  time: 1.0048  data: 0.0005  max mem: 78493
Epoch: [295]  [240/312]  eta: 0:01:17  lr: 0.000003  min_lr: 0.000003  loss: 1.9542 (1.8332)  weight_decay: 0.0500 (0.0500)  time: 1.0037  data: 0.0005  max mem: 78493
Epoch: [295]  [250/312]  eta: 0:01:06  lr: 0.000003  min_lr: 0.000003  loss: 1.6936 (1.8227)  weight_decay: 0.0500 (0.0500)  time: 1.0042  data: 0.0005  max mem: 78493
Epoch: [295]  [260/312]  eta: 0:00:55  lr: 0.000003  min_lr: 0.000003  loss: 1.6936 (1.8167)  weight_decay: 0.0500 (0.0500)  time: 1.0043  data: 0.0004  max mem: 78493
Epoch: [295]  [270/312]  eta: 0:00:45  lr: 0.000003  min_lr: 0.000003  loss: 1.8266 (1.8179)  weight_decay: 0.0500 (0.0500)  time: 1.0033  data: 0.0005  max mem: 78493
Epoch: [295]  [280/312]  eta: 0:00:34  lr: 0.000003  min_lr: 0.000003  loss: 1.9097 (1.8229)  weight_decay: 0.0500 (0.0500)  time: 1.0039  data: 0.0011  max mem: 78493
Epoch: [295]  [290/312]  eta: 0:00:23  lr: 0.000003  min_lr: 0.000003  loss: 1.8839 (1.8203)  weight_decay: 0.0500 (0.0500)  time: 1.0031  data: 0.0009  max mem: 78493
Epoch: [295]  [300/312]  eta: 0:00:12  lr: 0.000003  min_lr: 0.000003  loss: 1.8440 (1.8220)  weight_decay: 0.0500 (0.0500)  time: 1.0015  data: 0.0001  max mem: 78493
Epoch: [295]  [310/312]  eta: 0:00:02  lr: 0.000003  min_lr: 0.000003  loss: 1.8354 (1.8230)  weight_decay: 0.0500 (0.0500)  time: 1.0017  data: 0.0001  max mem: 78493
Epoch: [295]  [311/312]  eta: 0:00:01  lr: 0.000003  min_lr: 0.000003  loss: 1.8354 (1.8240)  weight_decay: 0.0500 (0.0500)  time: 1.0017  data: 0.0001  max mem: 78493
Epoch: [295] Total time: 0:05:33 (1.0685 s / it)
Averaged stats: lr: 0.000003  min_lr: 0.000003  loss: 1.8354 (1.8261)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:09  loss: 0.4804 (0.4804)  acc1: 87.6302 (87.6302)  acc5: 97.7865 (97.7865)  time: 7.7326  data: 7.4688  max mem: 78493
Test:  [8/9]  eta: 0:00:01  loss: 0.7181 (0.6665)  acc1: 82.4219 (82.0960)  acc5: 96.0938 (95.9360)  time: 1.0576  data: 0.8300  max mem: 78493
Test: Total time: 0:00:09 (1.0704 s / it)
* Acc@1 82.602 Acc@5 96.118 loss 0.653
Accuracy of the model on the 50000 test images: 82.6%
Max accuracy: 82.66%
Epoch: [296]  [  0/312]  eta: 1:24:45  lr: 0.000003  min_lr: 0.000003  loss: 1.3184 (1.3184)  weight_decay: 0.0500 (0.0500)  time: 16.2992  data: 14.5649  max mem: 78493
Epoch: [296]  [ 10/312]  eta: 0:12:21  lr: 0.000003  min_lr: 0.000003  loss: 1.8661 (1.8092)  weight_decay: 0.0500 (0.0500)  time: 2.4560  data: 1.3469  max mem: 78493
Epoch: [296]  [ 20/312]  eta: 0:08:39  lr: 0.000003  min_lr: 0.000003  loss: 1.7179 (1.7161)  weight_decay: 0.0500 (0.0500)  time: 1.0519  data: 0.0129  max mem: 78493
Epoch: [296]  [ 30/312]  eta: 0:07:11  lr: 0.000003  min_lr: 0.000003  loss: 1.6349 (1.7662)  weight_decay: 0.0500 (0.0500)  time: 1.0205  data: 0.0006  max mem: 78493
Epoch: [296]  [ 40/312]  eta: 0:06:21  lr: 0.000003  min_lr: 0.000003  loss: 1.9306 (1.7797)  weight_decay: 0.0500 (0.0500)  time: 1.0064  data: 0.0005  max mem: 78493
Epoch: [296]  [ 50/312]  eta: 0:05:47  lr: 0.000003  min_lr: 0.000003  loss: 1.8485 (1.7832)  weight_decay: 0.0500 (0.0500)  time: 1.0064  data: 0.0012  max mem: 78493
Epoch: [296]  [ 60/312]  eta: 0:05:20  lr: 0.000003  min_lr: 0.000003  loss: 1.8017 (1.7983)  weight_decay: 0.0500 (0.0500)  time: 1.0087  data: 0.0011  max mem: 78493
Epoch: [296]  [ 70/312]  eta: 0:04:59  lr: 0.000003  min_lr: 0.000003  loss: 1.5970 (1.7561)  weight_decay: 0.0500 (0.0500)  time: 1.0088  data: 0.0004  max mem: 78493
Epoch: [296]  [ 80/312]  eta: 0:04:40  lr: 0.000003  min_lr: 0.000003  loss: 1.5656 (1.7523)  weight_decay: 0.0500 (0.0500)  time: 1.0092  data: 0.0004  max mem: 78493
Epoch: [296]  [ 90/312]  eta: 0:04:23  lr: 0.000003  min_lr: 0.000003  loss: 1.8621 (1.7625)  weight_decay: 0.0500 (0.0500)  time: 1.0094  data: 0.0004  max mem: 78493
Epoch: [296]  [100/312]  eta: 0:04:07  lr: 0.000003  min_lr: 0.000003  loss: 1.8214 (1.7674)  weight_decay: 0.0500 (0.0500)  time: 1.0077  data: 0.0005  max mem: 78493
Epoch: [296]  [110/312]  eta: 0:03:53  lr: 0.000003  min_lr: 0.000003  loss: 1.9739 (1.7921)  weight_decay: 0.0500 (0.0500)  time: 1.0075  data: 0.0004  max mem: 78493
Epoch: [296]  [120/312]  eta: 0:03:39  lr: 0.000003  min_lr: 0.000003  loss: 1.9765 (1.7866)  weight_decay: 0.0500 (0.0500)  time: 1.0116  data: 0.0004  max mem: 78493
Epoch: [296]  [130/312]  eta: 0:03:25  lr: 0.000003  min_lr: 0.000003  loss: 1.6599 (1.7820)  weight_decay: 0.0500 (0.0500)  time: 1.0099  data: 0.0005  max mem: 78493
Epoch: [296]  [140/312]  eta: 0:03:13  lr: 0.000003  min_lr: 0.000003  loss: 1.9027 (1.7804)  weight_decay: 0.0500 (0.0500)  time: 1.0056  data: 0.0004  max mem: 78493
Epoch: [296]  [150/312]  eta: 0:03:00  lr: 0.000003  min_lr: 0.000003  loss: 1.9028 (1.7805)  weight_decay: 0.0500 (0.0500)  time: 1.0052  data: 0.0004  max mem: 78493
Epoch: [296]  [160/312]  eta: 0:02:48  lr: 0.000003  min_lr: 0.000003  loss: 1.8176 (1.7805)  weight_decay: 0.0500 (0.0500)  time: 1.0058  data: 0.0005  max mem: 78493
Epoch: [296]  [170/312]  eta: 0:02:36  lr: 0.000003  min_lr: 0.000003  loss: 1.8519 (1.7812)  weight_decay: 0.0500 (0.0500)  time: 1.0058  data: 0.0004  max mem: 78493
Epoch: [296]  [180/312]  eta: 0:02:24  lr: 0.000002  min_lr: 0.000002  loss: 1.9574 (1.7853)  weight_decay: 0.0500 (0.0500)  time: 1.0048  data: 0.0004  max mem: 78493
Epoch: [296]  [190/312]  eta: 0:02:13  lr: 0.000002  min_lr: 0.000002  loss: 1.7506 (1.7776)  weight_decay: 0.0500 (0.0500)  time: 1.0052  data: 0.0004  max mem: 78493
Epoch: [296]  [200/312]  eta: 0:02:01  lr: 0.000002  min_lr: 0.000002  loss: 1.8229 (1.7849)  weight_decay: 0.0500 (0.0500)  time: 1.0061  data: 0.0004  max mem: 78493
Epoch: [296]  [210/312]  eta: 0:01:50  lr: 0.000002  min_lr: 0.000002  loss: 1.8889 (1.7873)  weight_decay: 0.0500 (0.0500)  time: 1.0052  data: 0.0004  max mem: 78493
Epoch: [296]  [220/312]  eta: 0:01:39  lr: 0.000002  min_lr: 0.000002  loss: 1.8889 (1.7890)  weight_decay: 0.0500 (0.0500)  time: 1.0045  data: 0.0005  max mem: 78493
Epoch: [296]  [230/312]  eta: 0:01:28  lr: 0.000002  min_lr: 0.000002  loss: 1.8878 (1.7902)  weight_decay: 0.0500 (0.0500)  time: 1.0045  data: 0.0005  max mem: 78493
Epoch: [296]  [240/312]  eta: 0:01:17  lr: 0.000002  min_lr: 0.000002  loss: 1.7585 (1.7850)  weight_decay: 0.0500 (0.0500)  time: 1.0051  data: 0.0005  max mem: 78493
Epoch: [296]  [250/312]  eta: 0:01:06  lr: 0.000002  min_lr: 0.000002  loss: 1.5262 (1.7741)  weight_decay: 0.0500 (0.0500)  time: 1.0070  data: 0.0011  max mem: 78493
Epoch: [296]  [260/312]  eta: 0:00:55  lr: 0.000002  min_lr: 0.000002  loss: 1.5262 (1.7754)  weight_decay: 0.0500 (0.0500)  time: 1.0080  data: 0.0011  max mem: 78493
Epoch: [296]  [270/312]  eta: 0:00:44  lr: 0.000002  min_lr: 0.000002  loss: 1.7859 (1.7794)  weight_decay: 0.0500 (0.0500)  time: 1.0064  data: 0.0005  max mem: 78493
Epoch: [296]  [280/312]  eta: 0:00:34  lr: 0.000002  min_lr: 0.000002  loss: 1.9026 (1.7810)  weight_decay: 0.0500 (0.0500)  time: 1.0056  data: 0.0010  max mem: 78493
Epoch: [296]  [290/312]  eta: 0:00:23  lr: 0.000002  min_lr: 0.000002  loss: 1.9491 (1.7862)  weight_decay: 0.0500 (0.0500)  time: 1.0044  data: 0.0009  max mem: 78493
Epoch: [296]  [300/312]  eta: 0:00:12  lr: 0.000002  min_lr: 0.000002  loss: 1.9311 (1.7841)  weight_decay: 0.0500 (0.0500)  time: 1.0021  data: 0.0001  max mem: 78493
Epoch: [296]  [310/312]  eta: 0:00:02  lr: 0.000002  min_lr: 0.000002  loss: 1.9066 (1.7863)  weight_decay: 0.0500 (0.0500)  time: 1.0021  data: 0.0001  max mem: 78493
Epoch: [296]  [311/312]  eta: 0:00:01  lr: 0.000002  min_lr: 0.000002  loss: 1.9066 (1.7865)  weight_decay: 0.0500 (0.0500)  time: 1.0020  data: 0.0001  max mem: 78493
Epoch: [296] Total time: 0:05:31 (1.0639 s / it)
Averaged stats: lr: 0.000002  min_lr: 0.000002  loss: 1.9066 (1.8286)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:12  loss: 0.4799 (0.4799)  acc1: 87.6302 (87.6302)  acc5: 97.7865 (97.7865)  time: 8.0154  data: 7.7463  max mem: 78493
Test:  [8/9]  eta: 0:00:01  loss: 0.7193 (0.6664)  acc1: 82.4219 (82.0960)  acc5: 96.0938 (95.9360)  time: 1.0898  data: 0.8608  max mem: 78493
Test: Total time: 0:00:09 (1.1079 s / it)
* Acc@1 82.600 Acc@5 96.136 loss 0.653
Accuracy of the model on the 50000 test images: 82.6%
Max accuracy: 82.66%
Epoch: [297]  [  0/312]  eta: 1:18:39  lr: 0.000002  min_lr: 0.000002  loss: 2.2889 (2.2889)  weight_decay: 0.0500 (0.0500)  time: 15.1256  data: 14.0436  max mem: 78493
Epoch: [297]  [ 10/312]  eta: 0:13:26  lr: 0.000002  min_lr: 0.000002  loss: 2.0127 (2.0122)  weight_decay: 0.0500 (0.0500)  time: 2.6689  data: 1.3190  max mem: 78493
Epoch: [297]  [ 20/312]  eta: 0:09:09  lr: 0.000002  min_lr: 0.000002  loss: 1.9166 (1.8553)  weight_decay: 0.0500 (0.0500)  time: 1.2206  data: 0.0236  max mem: 78493
Epoch: [297]  [ 30/312]  eta: 0:07:30  lr: 0.000002  min_lr: 0.000002  loss: 1.7725 (1.8622)  weight_decay: 0.0500 (0.0500)  time: 1.0106  data: 0.0005  max mem: 78493
Epoch: [297]  [ 40/312]  eta: 0:06:35  lr: 0.000002  min_lr: 0.000002  loss: 1.8682 (1.8590)  weight_decay: 0.0500 (0.0500)  time: 1.0066  data: 0.0004  max mem: 78493
Epoch: [297]  [ 50/312]  eta: 0:05:58  lr: 0.000002  min_lr: 0.000002  loss: 1.8586 (1.8629)  weight_decay: 0.0500 (0.0500)  time: 1.0081  data: 0.0005  max mem: 78493
Epoch: [297]  [ 60/312]  eta: 0:05:29  lr: 0.000002  min_lr: 0.000002  loss: 1.9308 (1.8695)  weight_decay: 0.0500 (0.0500)  time: 1.0059  data: 0.0005  max mem: 78493
Epoch: [297]  [ 70/312]  eta: 0:05:06  lr: 0.000002  min_lr: 0.000002  loss: 1.9454 (1.8630)  weight_decay: 0.0500 (0.0500)  time: 1.0072  data: 0.0005  max mem: 78493
Epoch: [297]  [ 80/312]  eta: 0:04:46  lr: 0.000002  min_lr: 0.000002  loss: 1.9473 (1.8535)  weight_decay: 0.0500 (0.0500)  time: 1.0081  data: 0.0013  max mem: 78493
Epoch: [297]  [ 90/312]  eta: 0:04:28  lr: 0.000002  min_lr: 0.000002  loss: 1.8446 (1.8517)  weight_decay: 0.0500 (0.0500)  time: 1.0085  data: 0.0013  max mem: 78493
Epoch: [297]  [100/312]  eta: 0:04:12  lr: 0.000002  min_lr: 0.000002  loss: 1.8446 (1.8484)  weight_decay: 0.0500 (0.0500)  time: 1.0096  data: 0.0004  max mem: 78493
Epoch: [297]  [110/312]  eta: 0:03:56  lr: 0.000002  min_lr: 0.000002  loss: 1.9045 (1.8455)  weight_decay: 0.0500 (0.0500)  time: 1.0088  data: 0.0014  max mem: 78493
Epoch: [297]  [120/312]  eta: 0:03:42  lr: 0.000002  min_lr: 0.000002  loss: 1.8666 (1.8325)  weight_decay: 0.0500 (0.0500)  time: 1.0087  data: 0.0014  max mem: 78493
Epoch: [297]  [130/312]  eta: 0:03:28  lr: 0.000002  min_lr: 0.000002  loss: 1.6354 (1.8204)  weight_decay: 0.0500 (0.0500)  time: 1.0097  data: 0.0004  max mem: 78493
Epoch: [297]  [140/312]  eta: 0:03:15  lr: 0.000002  min_lr: 0.000002  loss: 1.8581 (1.8227)  weight_decay: 0.0500 (0.0500)  time: 1.0084  data: 0.0005  max mem: 78493
Epoch: [297]  [150/312]  eta: 0:03:03  lr: 0.000002  min_lr: 0.000002  loss: 1.8456 (1.8154)  weight_decay: 0.0500 (0.0500)  time: 1.0081  data: 0.0005  max mem: 78493
Epoch: [297]  [160/312]  eta: 0:02:50  lr: 0.000002  min_lr: 0.000002  loss: 1.8174 (1.8066)  weight_decay: 0.0500 (0.0500)  time: 1.0090  data: 0.0004  max mem: 78493
Epoch: [297]  [170/312]  eta: 0:02:38  lr: 0.000002  min_lr: 0.000002  loss: 1.8217 (1.8129)  weight_decay: 0.0500 (0.0500)  time: 1.0066  data: 0.0004  max mem: 78493
Epoch: [297]  [180/312]  eta: 0:02:26  lr: 0.000002  min_lr: 0.000002  loss: 1.9264 (1.8137)  weight_decay: 0.0500 (0.0500)  time: 1.0051  data: 0.0004  max mem: 78493
Epoch: [297]  [190/312]  eta: 0:02:14  lr: 0.000002  min_lr: 0.000002  loss: 1.8104 (1.8117)  weight_decay: 0.0500 (0.0500)  time: 1.0077  data: 0.0004  max mem: 78493
Epoch: [297]  [200/312]  eta: 0:02:03  lr: 0.000002  min_lr: 0.000002  loss: 1.8308 (1.8091)  weight_decay: 0.0500 (0.0500)  time: 1.0090  data: 0.0004  max mem: 78493
Epoch: [297]  [210/312]  eta: 0:01:51  lr: 0.000002  min_lr: 0.000002  loss: 1.8500 (1.8041)  weight_decay: 0.0500 (0.0500)  time: 1.0073  data: 0.0004  max mem: 78493
Epoch: [297]  [220/312]  eta: 0:01:40  lr: 0.000002  min_lr: 0.000002  loss: 1.8585 (1.8027)  weight_decay: 0.0500 (0.0500)  time: 1.0066  data: 0.0004  max mem: 78493
Epoch: [297]  [230/312]  eta: 0:01:29  lr: 0.000002  min_lr: 0.000002  loss: 1.8938 (1.8068)  weight_decay: 0.0500 (0.0500)  time: 1.0062  data: 0.0005  max mem: 78493
Epoch: [297]  [240/312]  eta: 0:01:18  lr: 0.000002  min_lr: 0.000002  loss: 1.9382 (1.8055)  weight_decay: 0.0500 (0.0500)  time: 1.0058  data: 0.0005  max mem: 78493
Epoch: [297]  [250/312]  eta: 0:01:07  lr: 0.000002  min_lr: 0.000002  loss: 1.6927 (1.8029)  weight_decay: 0.0500 (0.0500)  time: 1.0056  data: 0.0005  max mem: 78493
Epoch: [297]  [260/312]  eta: 0:00:56  lr: 0.000002  min_lr: 0.000002  loss: 1.8322 (1.8073)  weight_decay: 0.0500 (0.0500)  time: 1.0059  data: 0.0004  max mem: 78493
Epoch: [297]  [270/312]  eta: 0:00:45  lr: 0.000002  min_lr: 0.000002  loss: 1.8322 (1.8057)  weight_decay: 0.0500 (0.0500)  time: 1.0067  data: 0.0004  max mem: 78493
Epoch: [297]  [280/312]  eta: 0:00:34  lr: 0.000002  min_lr: 0.000002  loss: 1.9375 (1.8137)  weight_decay: 0.0500 (0.0500)  time: 1.0077  data: 0.0010  max mem: 78493
Epoch: [297]  [290/312]  eta: 0:00:23  lr: 0.000002  min_lr: 0.000002  loss: 1.9819 (1.8188)  weight_decay: 0.0500 (0.0500)  time: 1.0053  data: 0.0009  max mem: 78493
Epoch: [297]  [300/312]  eta: 0:00:12  lr: 0.000002  min_lr: 0.000002  loss: 1.9869 (1.8267)  weight_decay: 0.0500 (0.0500)  time: 1.0021  data: 0.0001  max mem: 78493
Epoch: [297]  [310/312]  eta: 0:00:02  lr: 0.000002  min_lr: 0.000002  loss: 1.9006 (1.8233)  weight_decay: 0.0500 (0.0500)  time: 1.0017  data: 0.0001  max mem: 78493
Epoch: [297]  [311/312]  eta: 0:00:01  lr: 0.000002  min_lr: 0.000002  loss: 1.9715 (1.8238)  weight_decay: 0.0500 (0.0500)  time: 1.0017  data: 0.0001  max mem: 78493
Epoch: [297] Total time: 0:05:34 (1.0715 s / it)
Averaged stats: lr: 0.000002  min_lr: 0.000002  loss: 1.9715 (1.8297)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:12  loss: 0.4799 (0.4799)  acc1: 87.8906 (87.8906)  acc5: 97.7865 (97.7865)  time: 8.0385  data: 7.7546  max mem: 78493
Test:  [8/9]  eta: 0:00:01  loss: 0.7187 (0.6657)  acc1: 82.1615 (82.1600)  acc5: 95.9635 (95.8720)  time: 1.0914  data: 0.8617  max mem: 78493
Test: Total time: 0:00:09 (1.1025 s / it)
* Acc@1 82.618 Acc@5 96.122 loss 0.653
Accuracy of the model on the 50000 test images: 82.6%
Max accuracy: 82.66%
Epoch: [298]  [  0/312]  eta: 1:23:43  lr: 0.000002  min_lr: 0.000002  loss: 1.9499 (1.9499)  weight_decay: 0.0500 (0.0500)  time: 16.1006  data: 14.9780  max mem: 78493
Epoch: [298]  [ 10/312]  eta: 0:13:16  lr: 0.000001  min_lr: 0.000001  loss: 1.9166 (1.9032)  weight_decay: 0.0500 (0.0500)  time: 2.6368  data: 1.3697  max mem: 78493
Epoch: [298]  [ 20/312]  eta: 0:09:06  lr: 0.000001  min_lr: 0.000001  loss: 1.9055 (1.8354)  weight_decay: 0.0500 (0.0500)  time: 1.1594  data: 0.0080  max mem: 78493
Epoch: [298]  [ 30/312]  eta: 0:07:29  lr: 0.000001  min_lr: 0.000001  loss: 1.8922 (1.8421)  weight_decay: 0.0500 (0.0500)  time: 1.0193  data: 0.0039  max mem: 78493
Epoch: [298]  [ 40/312]  eta: 0:06:34  lr: 0.000001  min_lr: 0.000001  loss: 1.9064 (1.8716)  weight_decay: 0.0500 (0.0500)  time: 1.0083  data: 0.0005  max mem: 78493
Epoch: [298]  [ 50/312]  eta: 0:05:57  lr: 0.000001  min_lr: 0.000001  loss: 1.9989 (1.8897)  weight_decay: 0.0500 (0.0500)  time: 1.0061  data: 0.0005  max mem: 78493
Epoch: [298]  [ 60/312]  eta: 0:05:28  lr: 0.000001  min_lr: 0.000001  loss: 1.9570 (1.8687)  weight_decay: 0.0500 (0.0500)  time: 1.0065  data: 0.0005  max mem: 78493
Epoch: [298]  [ 70/312]  eta: 0:05:05  lr: 0.000001  min_lr: 0.000001  loss: 1.8733 (1.8544)  weight_decay: 0.0500 (0.0500)  time: 1.0077  data: 0.0005  max mem: 78493
Epoch: [298]  [ 80/312]  eta: 0:04:45  lr: 0.000001  min_lr: 0.000001  loss: 1.6237 (1.8425)  weight_decay: 0.0500 (0.0500)  time: 1.0079  data: 0.0005  max mem: 78493
Epoch: [298]  [ 90/312]  eta: 0:04:27  lr: 0.000001  min_lr: 0.000001  loss: 1.6237 (1.8302)  weight_decay: 0.0500 (0.0500)  time: 1.0077  data: 0.0005  max mem: 78493
Epoch: [298]  [100/312]  eta: 0:04:11  lr: 0.000001  min_lr: 0.000001  loss: 1.6814 (1.8205)  weight_decay: 0.0500 (0.0500)  time: 1.0090  data: 0.0004  max mem: 78493
Epoch: [298]  [110/312]  eta: 0:03:56  lr: 0.000001  min_lr: 0.000001  loss: 1.6814 (1.8163)  weight_decay: 0.0500 (0.0500)  time: 1.0085  data: 0.0005  max mem: 78493
Epoch: [298]  [120/312]  eta: 0:03:42  lr: 0.000001  min_lr: 0.000001  loss: 1.8579 (1.8250)  weight_decay: 0.0500 (0.0500)  time: 1.0090  data: 0.0004  max mem: 78493
Epoch: [298]  [130/312]  eta: 0:03:28  lr: 0.000001  min_lr: 0.000001  loss: 1.9925 (1.8331)  weight_decay: 0.0500 (0.0500)  time: 1.0099  data: 0.0005  max mem: 78493
Epoch: [298]  [140/312]  eta: 0:03:15  lr: 0.000001  min_lr: 0.000001  loss: 1.9919 (1.8419)  weight_decay: 0.0500 (0.0500)  time: 1.0075  data: 0.0005  max mem: 78493
Epoch: [298]  [150/312]  eta: 0:03:02  lr: 0.000001  min_lr: 0.000001  loss: 1.9586 (1.8470)  weight_decay: 0.0500 (0.0500)  time: 1.0070  data: 0.0004  max mem: 78493
Epoch: [298]  [160/312]  eta: 0:02:50  lr: 0.000001  min_lr: 0.000001  loss: 1.9586 (1.8499)  weight_decay: 0.0500 (0.0500)  time: 1.0086  data: 0.0005  max mem: 78493
Epoch: [298]  [170/312]  eta: 0:02:38  lr: 0.000001  min_lr: 0.000001  loss: 1.9012 (1.8492)  weight_decay: 0.0500 (0.0500)  time: 1.0064  data: 0.0005  max mem: 78493
Epoch: [298]  [180/312]  eta: 0:02:26  lr: 0.000001  min_lr: 0.000001  loss: 1.8879 (1.8536)  weight_decay: 0.0500 (0.0500)  time: 1.0056  data: 0.0004  max mem: 78493
Epoch: [298]  [190/312]  eta: 0:02:14  lr: 0.000001  min_lr: 0.000001  loss: 1.8953 (1.8439)  weight_decay: 0.0500 (0.0500)  time: 1.0068  data: 0.0004  max mem: 78493
Epoch: [298]  [200/312]  eta: 0:02:02  lr: 0.000001  min_lr: 0.000001  loss: 1.9161 (1.8416)  weight_decay: 0.0500 (0.0500)  time: 1.0049  data: 0.0004  max mem: 78493
Epoch: [298]  [210/312]  eta: 0:01:51  lr: 0.000001  min_lr: 0.000001  loss: 1.8655 (1.8409)  weight_decay: 0.0500 (0.0500)  time: 1.0058  data: 0.0005  max mem: 78493
Epoch: [298]  [220/312]  eta: 0:01:40  lr: 0.000001  min_lr: 0.000001  loss: 1.7891 (1.8325)  weight_decay: 0.0500 (0.0500)  time: 1.0082  data: 0.0013  max mem: 78493
Epoch: [298]  [230/312]  eta: 0:01:29  lr: 0.000001  min_lr: 0.000001  loss: 1.8911 (1.8331)  weight_decay: 0.0500 (0.0500)  time: 1.0081  data: 0.0013  max mem: 78493
Epoch: [298]  [240/312]  eta: 0:01:17  lr: 0.000001  min_lr: 0.000001  loss: 1.9131 (1.8298)  weight_decay: 0.0500 (0.0500)  time: 1.0072  data: 0.0004  max mem: 78493
Epoch: [298]  [250/312]  eta: 0:01:06  lr: 0.000001  min_lr: 0.000001  loss: 1.6445 (1.8213)  weight_decay: 0.0500 (0.0500)  time: 1.0071  data: 0.0004  max mem: 78493
Epoch: [298]  [260/312]  eta: 0:00:56  lr: 0.000001  min_lr: 0.000001  loss: 1.7286 (1.8198)  weight_decay: 0.0500 (0.0500)  time: 1.0080  data: 0.0012  max mem: 78493
Epoch: [298]  [270/312]  eta: 0:00:45  lr: 0.000001  min_lr: 0.000001  loss: 1.9065 (1.8142)  weight_decay: 0.0500 (0.0500)  time: 1.0082  data: 0.0019  max mem: 78493
Epoch: [298]  [280/312]  eta: 0:00:34  lr: 0.000001  min_lr: 0.000001  loss: 1.9035 (1.8174)  weight_decay: 0.0500 (0.0500)  time: 1.0080  data: 0.0017  max mem: 78493
Epoch: [298]  [290/312]  eta: 0:00:23  lr: 0.000001  min_lr: 0.000001  loss: 1.9597 (1.8201)  weight_decay: 0.0500 (0.0500)  time: 1.0051  data: 0.0009  max mem: 78493
Epoch: [298]  [300/312]  eta: 0:00:12  lr: 0.000001  min_lr: 0.000001  loss: 1.9810 (1.8193)  weight_decay: 0.0500 (0.0500)  time: 1.0016  data: 0.0001  max mem: 78493
Epoch: [298]  [310/312]  eta: 0:00:02  lr: 0.000001  min_lr: 0.000001  loss: 1.8449 (1.8187)  weight_decay: 0.0500 (0.0500)  time: 1.0017  data: 0.0001  max mem: 78493
Epoch: [298]  [311/312]  eta: 0:00:01  lr: 0.000001  min_lr: 0.000001  loss: 1.8449 (1.8197)  weight_decay: 0.0500 (0.0500)  time: 1.0018  data: 0.0001  max mem: 78493
Epoch: [298] Total time: 0:05:34 (1.0715 s / it)
Averaged stats: lr: 0.000001  min_lr: 0.000001  loss: 1.8449 (1.8322)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:10  loss: 0.4803 (0.4803)  acc1: 87.3698 (87.3698)  acc5: 97.7865 (97.7865)  time: 7.7936  data: 7.5229  max mem: 78493
Test:  [8/9]  eta: 0:00:01  loss: 0.7178 (0.6668)  acc1: 82.4219 (82.0480)  acc5: 96.0938 (95.9360)  time: 1.0916  data: 0.8636  max mem: 78493
Test: Total time: 0:00:09 (1.1020 s / it)
* Acc@1 82.602 Acc@5 96.126 loss 0.653
Accuracy of the model on the 50000 test images: 82.6%
Max accuracy: 82.66%
Epoch: [299]  [  0/312]  eta: 1:25:35  lr: 0.000001  min_lr: 0.000001  loss: 2.1827 (2.1827)  weight_decay: 0.0500 (0.0500)  time: 16.4587  data: 12.4648  max mem: 78493
Epoch: [299]  [ 10/312]  eta: 0:13:11  lr: 0.000001  min_lr: 0.000001  loss: 1.6591 (1.6167)  weight_decay: 0.0500 (0.0500)  time: 2.6197  data: 1.2715  max mem: 78493
Epoch: [299]  [ 20/312]  eta: 0:09:02  lr: 0.000001  min_lr: 0.000001  loss: 1.6591 (1.6744)  weight_decay: 0.0500 (0.0500)  time: 1.1261  data: 0.0780  max mem: 78493
Epoch: [299]  [ 30/312]  eta: 0:07:26  lr: 0.000001  min_lr: 0.000001  loss: 1.8761 (1.7248)  weight_decay: 0.0500 (0.0500)  time: 1.0115  data: 0.0021  max mem: 78493
Epoch: [299]  [ 40/312]  eta: 0:06:32  lr: 0.000001  min_lr: 0.000001  loss: 1.8911 (1.7555)  weight_decay: 0.0500 (0.0500)  time: 1.0062  data: 0.0004  max mem: 78493
Epoch: [299]  [ 50/312]  eta: 0:05:55  lr: 0.000001  min_lr: 0.000001  loss: 1.8911 (1.7898)  weight_decay: 0.0500 (0.0500)  time: 1.0075  data: 0.0004  max mem: 78493
Epoch: [299]  [ 60/312]  eta: 0:05:27  lr: 0.000001  min_lr: 0.000001  loss: 1.8855 (1.7933)  weight_decay: 0.0500 (0.0500)  time: 1.0089  data: 0.0004  max mem: 78493
Epoch: [299]  [ 70/312]  eta: 0:05:04  lr: 0.000001  min_lr: 0.000001  loss: 1.8855 (1.8032)  weight_decay: 0.0500 (0.0500)  time: 1.0068  data: 0.0005  max mem: 78493
Epoch: [299]  [ 80/312]  eta: 0:04:44  lr: 0.000001  min_lr: 0.000001  loss: 1.8642 (1.7995)  weight_decay: 0.0500 (0.0500)  time: 1.0049  data: 0.0005  max mem: 78493
Epoch: [299]  [ 90/312]  eta: 0:04:26  lr: 0.000001  min_lr: 0.000001  loss: 1.6961 (1.7916)  weight_decay: 0.0500 (0.0500)  time: 1.0052  data: 0.0005  max mem: 78493
Epoch: [299]  [100/312]  eta: 0:04:10  lr: 0.000001  min_lr: 0.000001  loss: 1.7805 (1.7929)  weight_decay: 0.0500 (0.0500)  time: 1.0050  data: 0.0005  max mem: 78493
Epoch: [299]  [110/312]  eta: 0:03:55  lr: 0.000001  min_lr: 0.000001  loss: 1.7805 (1.7812)  weight_decay: 0.0500 (0.0500)  time: 1.0036  data: 0.0005  max mem: 78493
Epoch: [299]  [120/312]  eta: 0:03:41  lr: 0.000001  min_lr: 0.000001  loss: 1.6902 (1.7730)  weight_decay: 0.0500 (0.0500)  time: 1.0064  data: 0.0004  max mem: 78493
Epoch: [299]  [130/312]  eta: 0:03:27  lr: 0.000001  min_lr: 0.000001  loss: 1.7984 (1.7815)  weight_decay: 0.0500 (0.0500)  time: 1.0094  data: 0.0004  max mem: 78493
Epoch: [299]  [140/312]  eta: 0:03:14  lr: 0.000001  min_lr: 0.000001  loss: 1.8274 (1.7796)  weight_decay: 0.0500 (0.0500)  time: 1.0086  data: 0.0013  max mem: 78493
Epoch: [299]  [150/312]  eta: 0:03:02  lr: 0.000001  min_lr: 0.000001  loss: 1.9652 (1.7936)  weight_decay: 0.0500 (0.0500)  time: 1.0076  data: 0.0013  max mem: 78493
Epoch: [299]  [160/312]  eta: 0:02:49  lr: 0.000001  min_lr: 0.000001  loss: 2.0060 (1.8029)  weight_decay: 0.0500 (0.0500)  time: 1.0075  data: 0.0004  max mem: 78493
Epoch: [299]  [170/312]  eta: 0:02:37  lr: 0.000001  min_lr: 0.000001  loss: 1.9997 (1.8172)  weight_decay: 0.0500 (0.0500)  time: 1.0078  data: 0.0005  max mem: 78493
Epoch: [299]  [180/312]  eta: 0:02:25  lr: 0.000001  min_lr: 0.000001  loss: 1.9240 (1.8157)  weight_decay: 0.0500 (0.0500)  time: 1.0063  data: 0.0005  max mem: 78493
Epoch: [299]  [190/312]  eta: 0:02:14  lr: 0.000001  min_lr: 0.000001  loss: 1.9098 (1.8230)  weight_decay: 0.0500 (0.0500)  time: 1.0055  data: 0.0005  max mem: 78493
Epoch: [299]  [200/312]  eta: 0:02:02  lr: 0.000001  min_lr: 0.000001  loss: 2.0402 (1.8276)  weight_decay: 0.0500 (0.0500)  time: 1.0055  data: 0.0004  max mem: 78493
Epoch: [299]  [210/312]  eta: 0:01:51  lr: 0.000001  min_lr: 0.000001  loss: 1.9317 (1.8290)  weight_decay: 0.0500 (0.0500)  time: 1.0052  data: 0.0004  max mem: 78493
Epoch: [299]  [220/312]  eta: 0:01:40  lr: 0.000001  min_lr: 0.000001  loss: 1.7281 (1.8271)  weight_decay: 0.0500 (0.0500)  time: 1.0067  data: 0.0004  max mem: 78493
Epoch: [299]  [230/312]  eta: 0:01:28  lr: 0.000001  min_lr: 0.000001  loss: 1.8511 (1.8269)  weight_decay: 0.0500 (0.0500)  time: 1.0054  data: 0.0004  max mem: 78493
Epoch: [299]  [240/312]  eta: 0:01:17  lr: 0.000001  min_lr: 0.000001  loss: 1.9144 (1.8293)  weight_decay: 0.0500 (0.0500)  time: 1.0047  data: 0.0004  max mem: 78493
Epoch: [299]  [250/312]  eta: 0:01:06  lr: 0.000001  min_lr: 0.000001  loss: 1.9353 (1.8304)  weight_decay: 0.0500 (0.0500)  time: 1.0063  data: 0.0004  max mem: 78493
Epoch: [299]  [260/312]  eta: 0:00:55  lr: 0.000001  min_lr: 0.000001  loss: 1.7571 (1.8275)  weight_decay: 0.0500 (0.0500)  time: 1.0062  data: 0.0005  max mem: 78493
Epoch: [299]  [270/312]  eta: 0:00:45  lr: 0.000001  min_lr: 0.000001  loss: 1.6882 (1.8235)  weight_decay: 0.0500 (0.0500)  time: 1.0057  data: 0.0005  max mem: 78493
Epoch: [299]  [280/312]  eta: 0:00:34  lr: 0.000001  min_lr: 0.000001  loss: 1.7690 (1.8234)  weight_decay: 0.0500 (0.0500)  time: 1.0063  data: 0.0011  max mem: 78493
Epoch: [299]  [290/312]  eta: 0:00:23  lr: 0.000001  min_lr: 0.000001  loss: 1.8343 (1.8224)  weight_decay: 0.0500 (0.0500)  time: 1.0045  data: 0.0009  max mem: 78493
Epoch: [299]  [300/312]  eta: 0:00:12  lr: 0.000001  min_lr: 0.000001  loss: 1.7559 (1.8185)  weight_decay: 0.0500 (0.0500)  time: 1.0015  data: 0.0001  max mem: 78493
Epoch: [299]  [310/312]  eta: 0:00:02  lr: 0.000001  min_lr: 0.000001  loss: 1.7130 (1.8157)  weight_decay: 0.0500 (0.0500)  time: 1.0015  data: 0.0001  max mem: 78493
Epoch: [299]  [311/312]  eta: 0:00:01  lr: 0.000001  min_lr: 0.000001  loss: 1.7130 (1.8164)  weight_decay: 0.0500 (0.0500)  time: 1.0016  data: 0.0001  max mem: 78493
Epoch: [299] Total time: 0:05:33 (1.0686 s / it)
Averaged stats: lr: 0.000001  min_lr: 0.000001  loss: 1.7130 (1.8222)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:15  loss: 0.4788 (0.4788)  acc1: 87.7604 (87.7604)  acc5: 97.7865 (97.7865)  time: 8.3781  data: 8.1023  max mem: 78493
Test:  [8/9]  eta: 0:00:01  loss: 0.7201 (0.6664)  acc1: 82.4219 (82.2720)  acc5: 96.4844 (96.0160)  time: 1.1292  data: 0.9003  max mem: 78493
Test: Total time: 0:00:10 (1.1492 s / it)
* Acc@1 82.662 Acc@5 96.156 loss 0.654
Accuracy of the model on the 50000 test images: 82.7%
Max accuracy: 82.66%
Training time 1 day, 4:47:12