Namespace(aa='rand-m9-mstd0.5-inc1', auto_resume=True, batch_size=256, cfg_path='iFormer_m_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=1e-06, 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_m', 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=16)
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 0x7f4d07231c10>
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 0x7f4d072adb80>
---------------------------
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 0x7f4d072ada00>
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, 192, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False)
        (bn): BatchNorm2d(192, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      )
    )
    (3): Sequential(
      (0): Conv2d_BN(
        (c): Conv2d(192, 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(192, 192, kernel_size=(7, 7), stride=(1, 1), padding=(3, 3), groups=192, bias=False)
                (bn): BatchNorm2d(192, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
              )
              (1): Conv2d_BN(
                (c): Conv2d(192, 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)
              )
              (2): GELU(approximate='none')
              (3): Conv2d_BN(
                (c): Conv2d(768, 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)
              )
            )
          )
        )
      )
      (1): BasicBlock(
        (block): ConvBlock(
          (token_channel_mixer): Residual(
            (m): Sequential(
              (0): Conv2d_BN(
                (c): Conv2d(192, 192, kernel_size=(7, 7), stride=(1, 1), padding=(3, 3), groups=192, bias=False)
                (bn): BatchNorm2d(192, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
              )
              (1): Conv2d_BN(
                (c): Conv2d(192, 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)
              )
              (2): GELU(approximate='none')
              (3): Conv2d_BN(
                (c): Conv2d(768, 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): BasicBlock(
        (block): ConvBlock(
          (token_channel_mixer): Residual(
            (m): Sequential(
              (0): Conv2d_BN(
                (c): Conv2d(192, 192, kernel_size=(7, 7), stride=(1, 1), padding=(3, 3), groups=192, bias=False)
                (bn): BatchNorm2d(192, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
              )
              (1): Conv2d_BN(
                (c): Conv2d(192, 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)
              )
              (2): GELU(approximate='none')
              (3): Conv2d_BN(
                (c): Conv2d(768, 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)
              )
            )
          )
        )
      )
      (3): BasicBlock(
        (block): ConvBlock(
          (token_channel_mixer): Residual(
            (m): Sequential(
              (0): Conv2d_BN(
                (c): Conv2d(192, 192, kernel_size=(7, 7), stride=(1, 1), padding=(3, 3), groups=192, bias=False)
                (bn): BatchNorm2d(192, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
              )
              (1): Conv2d_BN(
                (c): Conv2d(192, 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)
              )
              (2): GELU(approximate='none')
              (3): Conv2d_BN(
                (c): Conv2d(768, 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)
              )
            )
          )
        )
      )
      (4): BasicBlock(
        (block): ConvBlock(
          (token_channel_mixer): Residual(
            (m): Sequential(
              (0): Conv2d_BN(
                (c): Conv2d(192, 192, kernel_size=(7, 7), stride=(1, 1), padding=(3, 3), groups=192, bias=False)
                (bn): BatchNorm2d(192, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
              )
              (1): Conv2d_BN(
                (c): Conv2d(192, 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)
              )
              (2): GELU(approximate='none')
              (3): Conv2d_BN(
                (c): Conv2d(768, 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)
              )
            )
          )
        )
      )
      (5): BasicBlock(
        (block): ConvBlock(
          (token_channel_mixer): Residual(
            (m): Sequential(
              (0): Conv2d_BN(
                (c): Conv2d(192, 192, kernel_size=(7, 7), stride=(1, 1), padding=(3, 3), groups=192, bias=False)
                (bn): BatchNorm2d(192, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
              )
              (1): Conv2d_BN(
                (c): Conv2d(192, 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)
              )
              (2): GELU(approximate='none')
              (3): Conv2d_BN(
                (c): Conv2d(768, 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)
              )
            )
          )
        )
      )
      (6): BasicBlock(
        (block): ConvBlock(
          (token_channel_mixer): Residual(
            (m): Sequential(
              (0): Conv2d_BN(
                (c): Conv2d(192, 192, kernel_size=(7, 7), stride=(1, 1), padding=(3, 3), groups=192, bias=False)
                (bn): BatchNorm2d(192, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
              )
              (1): Conv2d_BN(
                (c): Conv2d(192, 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)
              )
              (2): GELU(approximate='none')
              (3): Conv2d_BN(
                (c): Conv2d(768, 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)
              )
            )
          )
        )
      )
      (7): BasicBlock(
        (block): ConvBlock(
          (token_channel_mixer): Residual(
            (m): Sequential(
              (0): Conv2d_BN(
                (c): Conv2d(192, 192, kernel_size=(7, 7), stride=(1, 1), padding=(3, 3), groups=192, bias=False)
                (bn): BatchNorm2d(192, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
              )
              (1): Conv2d_BN(
                (c): Conv2d(192, 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)
              )
              (2): GELU(approximate='none')
              (3): Conv2d_BN(
                (c): Conv2d(768, 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)
              )
            )
          )
        )
      )
      (8): BasicBlock(
        (block): ConvBlock(
          (token_channel_mixer): Residual(
            (m): Sequential(
              (0): Conv2d_BN(
                (c): Conv2d(192, 192, kernel_size=(7, 7), stride=(1, 1), padding=(3, 3), groups=192, bias=False)
                (bn): BatchNorm2d(192, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
              )
              (1): Conv2d_BN(
                (c): Conv2d(192, 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)
              )
              (2): GELU(approximate='none')
              (3): Conv2d_BN(
                (c): Conv2d(768, 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)
              )
            )
          )
        )
      )
      (9): BasicBlock(
        (block): RepCPE(
          (cpe): Residual(
            (m): Conv2d_BN(
              (c): Conv2d(192, 192, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=192, bias=False)
              (bn): BatchNorm2d(192, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
            )
          )
        )
      )
      (10): BasicBlock(
        (block): GAUFused2dv2(
          (token_channel_mixer): Residual(
            (m): GAU2dv2(
              (q): Conv2d_BN(
                (c): Conv2d(192, 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(192, 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)
              )
              (gate_act): Sigmoid()
              (attn_drop): Dropout(p=0.0, inplace=False)
              (proj): Conv2d_BN(
                (c): Conv2d(192, 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)
              )
              (v_gate): Conv2d_BN(
                (c): Conv2d(192, 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)
              )
            )
          )
        )
      )
      (11): BasicBlock(
        (block): FFN2d(
          (channel_mixer): Residual(
            (m): Sequential(
              (0): Conv2d_BN(
                (c): Conv2d(192, 576, kernel_size=(1, 1), stride=(1, 1), bias=False)
                (bn): BatchNorm2d(576, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
              )
              (1): GELU(approximate='none')
              (2): Conv2d_BN(
                (c): Conv2d(576, 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)
              )
            )
          )
        )
      )
      (12): BasicBlock(
        (block): RepCPE(
          (cpe): Residual(
            (m): Conv2d_BN(
              (c): Conv2d(192, 192, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=192, bias=False)
              (bn): BatchNorm2d(192, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
            )
          )
        )
      )
      (13): BasicBlock(
        (block): GAUFused2dv2(
          (token_channel_mixer): Residual(
            (m): GAU2dv2(
              (q): Conv2d_BN(
                (c): Conv2d(192, 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(192, 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)
              )
              (gate_act): Sigmoid()
              (attn_drop): Dropout(p=0.0, inplace=False)
              (proj): Conv2d_BN(
                (c): Conv2d(192, 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)
              )
              (v_gate): Conv2d_BN(
                (c): Conv2d(192, 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)
              )
            )
          )
        )
      )
      (14): BasicBlock(
        (block): FFN2d(
          (channel_mixer): Residual(
            (m): Sequential(
              (0): Conv2d_BN(
                (c): Conv2d(192, 576, kernel_size=(1, 1), stride=(1, 1), bias=False)
                (bn): BatchNorm2d(576, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
              )
              (1): GELU(approximate='none')
              (2): Conv2d_BN(
                (c): Conv2d(576, 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)
              )
            )
          )
        )
      )
      (15): BasicBlock(
        (block): RepCPE(
          (cpe): Residual(
            (m): Conv2d_BN(
              (c): Conv2d(192, 192, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=192, bias=False)
              (bn): BatchNorm2d(192, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
            )
          )
        )
      )
      (16): BasicBlock(
        (block): GAUFused2dv2(
          (token_channel_mixer): Residual(
            (m): GAU2dv2(
              (q): Conv2d_BN(
                (c): Conv2d(192, 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(192, 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)
              )
              (gate_act): Sigmoid()
              (attn_drop): Dropout(p=0.0, inplace=False)
              (proj): Conv2d_BN(
                (c): Conv2d(192, 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)
              )
              (v_gate): Conv2d_BN(
                (c): Conv2d(192, 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)
              )
            )
          )
        )
      )
      (17): BasicBlock(
        (block): FFN2d(
          (channel_mixer): Residual(
            (m): Sequential(
              (0): Conv2d_BN(
                (c): Conv2d(192, 576, kernel_size=(1, 1), stride=(1, 1), bias=False)
                (bn): BatchNorm2d(576, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
              )
              (1): GELU(approximate='none')
              (2): Conv2d_BN(
                (c): Conv2d(576, 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)
              )
            )
          )
        )
      )
      (18): BasicBlock(
        (block): RepCPE(
          (cpe): Residual(
            (m): Conv2d_BN(
              (c): Conv2d(192, 192, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=192, bias=False)
              (bn): BatchNorm2d(192, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
            )
          )
        )
      )
      (19): BasicBlock(
        (block): GAUFused2dv2(
          (token_channel_mixer): Residual(
            (m): GAU2dv2(
              (q): Conv2d_BN(
                (c): Conv2d(192, 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(192, 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)
              )
              (gate_act): Sigmoid()
              (attn_drop): Dropout(p=0.0, inplace=False)
              (proj): Conv2d_BN(
                (c): Conv2d(192, 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)
              )
              (v_gate): Conv2d_BN(
                (c): Conv2d(192, 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)
              )
            )
          )
        )
      )
      (20): BasicBlock(
        (block): FFN2d(
          (channel_mixer): Residual(
            (m): Sequential(
              (0): Conv2d_BN(
                (c): Conv2d(192, 576, kernel_size=(1, 1), stride=(1, 1), bias=False)
                (bn): BatchNorm2d(576, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
              )
              (1): GELU(approximate='none')
              (2): Conv2d_BN(
                (c): Conv2d(576, 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)
              )
            )
          )
        )
      )
      (21): BasicBlock(
        (block): ConvBlock(
          (token_channel_mixer): Residual(
            (m): Sequential(
              (0): Conv2d_BN(
                (c): Conv2d(192, 192, kernel_size=(7, 7), stride=(1, 1), padding=(3, 3), groups=192, bias=False)
                (bn): BatchNorm2d(192, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
              )
              (1): Conv2d_BN(
                (c): Conv2d(192, 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)
              )
              (2): GELU(approximate='none')
              (3): Conv2d_BN(
                (c): Conv2d(768, 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)
              )
            )
          )
        )
      )
    )
    (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): GAUFused2dv2(
          (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)
              )
              (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)
              )
              (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)
              )
            )
          )
        )
      )
      (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): GAUFused2dv2(
          (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)
              )
              (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)
              )
              (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)
              )
            )
          )
        )
      )
      (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: 9293192
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.token_channel_mixer.m.0.c.weight",
      "stages.2.8.block.token_channel_mixer.m.1.c.weight",
      "stages.2.8.block.token_channel_mixer.m.3.c.weight",
      "stages.2.9.block.cpe.m.c.weight",
      "stages.2.10.block.token_channel_mixer.m.q.c.weight",
      "stages.2.10.block.token_channel_mixer.m.k.c.weight",
      "stages.2.10.block.token_channel_mixer.m.proj.c.weight",
      "stages.2.10.block.token_channel_mixer.m.v_gate.c.weight",
      "stages.2.11.block.channel_mixer.m.0.c.weight",
      "stages.2.11.block.channel_mixer.m.2.c.weight",
      "stages.2.12.block.cpe.m.c.weight",
      "stages.2.13.block.token_channel_mixer.m.q.c.weight",
      "stages.2.13.block.token_channel_mixer.m.k.c.weight",
      "stages.2.13.block.token_channel_mixer.m.proj.c.weight",
      "stages.2.13.block.token_channel_mixer.m.v_gate.c.weight",
      "stages.2.14.block.channel_mixer.m.0.c.weight",
      "stages.2.14.block.channel_mixer.m.2.c.weight",
      "stages.2.15.block.cpe.m.c.weight",
      "stages.2.16.block.token_channel_mixer.m.q.c.weight",
      "stages.2.16.block.token_channel_mixer.m.k.c.weight",
      "stages.2.16.block.token_channel_mixer.m.proj.c.weight",
      "stages.2.16.block.token_channel_mixer.m.v_gate.c.weight",
      "stages.2.17.block.channel_mixer.m.0.c.weight",
      "stages.2.17.block.channel_mixer.m.2.c.weight",
      "stages.2.18.block.cpe.m.c.weight",
      "stages.2.19.block.token_channel_mixer.m.q.c.weight",
      "stages.2.19.block.token_channel_mixer.m.k.c.weight",
      "stages.2.19.block.token_channel_mixer.m.proj.c.weight",
      "stages.2.19.block.token_channel_mixer.m.v_gate.c.weight",
      "stages.2.20.block.channel_mixer.m.0.c.weight",
      "stages.2.20.block.channel_mixer.m.2.c.weight",
      "stages.2.21.block.token_channel_mixer.m.0.c.weight",
      "stages.2.21.block.token_channel_mixer.m.1.c.weight",
      "stages.2.21.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.proj.c.weight",
      "stages.3.1.block.token_channel_mixer.m.v_gate.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.proj.c.weight",
      "stages.3.4.block.token_channel_mixer.m.v_gate.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.token_channel_mixer.m.0.bn.weight",
      "stages.2.8.block.token_channel_mixer.m.0.bn.bias",
      "stages.2.8.block.token_channel_mixer.m.1.bn.weight",
      "stages.2.8.block.token_channel_mixer.m.1.bn.bias",
      "stages.2.8.block.token_channel_mixer.m.3.bn.weight",
      "stages.2.8.block.token_channel_mixer.m.3.bn.bias",
      "stages.2.9.block.cpe.m.bn.weight",
      "stages.2.9.block.cpe.m.bn.bias",
      "stages.2.10.block.token_channel_mixer.m.q.bn.weight",
      "stages.2.10.block.token_channel_mixer.m.q.bn.bias",
      "stages.2.10.block.token_channel_mixer.m.k.bn.weight",
      "stages.2.10.block.token_channel_mixer.m.k.bn.bias",
      "stages.2.10.block.token_channel_mixer.m.proj.bn.weight",
      "stages.2.10.block.token_channel_mixer.m.proj.bn.bias",
      "stages.2.10.block.token_channel_mixer.m.v_gate.bn.weight",
      "stages.2.10.block.token_channel_mixer.m.v_gate.bn.bias",
      "stages.2.11.block.channel_mixer.m.0.bn.weight",
      "stages.2.11.block.channel_mixer.m.0.bn.bias",
      "stages.2.11.block.channel_mixer.m.2.bn.weight",
      "stages.2.11.block.channel_mixer.m.2.bn.bias",
      "stages.2.12.block.cpe.m.bn.weight",
      "stages.2.12.block.cpe.m.bn.bias",
      "stages.2.13.block.token_channel_mixer.m.q.bn.weight",
      "stages.2.13.block.token_channel_mixer.m.q.bn.bias",
      "stages.2.13.block.token_channel_mixer.m.k.bn.weight",
      "stages.2.13.block.token_channel_mixer.m.k.bn.bias",
      "stages.2.13.block.token_channel_mixer.m.proj.bn.weight",
      "stages.2.13.block.token_channel_mixer.m.proj.bn.bias",
      "stages.2.13.block.token_channel_mixer.m.v_gate.bn.weight",
      "stages.2.13.block.token_channel_mixer.m.v_gate.bn.bias",
      "stages.2.14.block.channel_mixer.m.0.bn.weight",
      "stages.2.14.block.channel_mixer.m.0.bn.bias",
      "stages.2.14.block.channel_mixer.m.2.bn.weight",
      "stages.2.14.block.channel_mixer.m.2.bn.bias",
      "stages.2.15.block.cpe.m.bn.weight",
      "stages.2.15.block.cpe.m.bn.bias",
      "stages.2.16.block.token_channel_mixer.m.q.bn.weight",
      "stages.2.16.block.token_channel_mixer.m.q.bn.bias",
      "stages.2.16.block.token_channel_mixer.m.k.bn.weight",
      "stages.2.16.block.token_channel_mixer.m.k.bn.bias",
      "stages.2.16.block.token_channel_mixer.m.proj.bn.weight",
      "stages.2.16.block.token_channel_mixer.m.proj.bn.bias",
      "stages.2.16.block.token_channel_mixer.m.v_gate.bn.weight",
      "stages.2.16.block.token_channel_mixer.m.v_gate.bn.bias",
      "stages.2.17.block.channel_mixer.m.0.bn.weight",
      "stages.2.17.block.channel_mixer.m.0.bn.bias",
      "stages.2.17.block.channel_mixer.m.2.bn.weight",
      "stages.2.17.block.channel_mixer.m.2.bn.bias",
      "stages.2.18.block.cpe.m.bn.weight",
      "stages.2.18.block.cpe.m.bn.bias",
      "stages.2.19.block.token_channel_mixer.m.q.bn.weight",
      "stages.2.19.block.token_channel_mixer.m.q.bn.bias",
      "stages.2.19.block.token_channel_mixer.m.k.bn.weight",
      "stages.2.19.block.token_channel_mixer.m.k.bn.bias",
      "stages.2.19.block.token_channel_mixer.m.proj.bn.weight",
      "stages.2.19.block.token_channel_mixer.m.proj.bn.bias",
      "stages.2.19.block.token_channel_mixer.m.v_gate.bn.weight",
      "stages.2.19.block.token_channel_mixer.m.v_gate.bn.bias",
      "stages.2.20.block.channel_mixer.m.0.bn.weight",
      "stages.2.20.block.channel_mixer.m.0.bn.bias",
      "stages.2.20.block.channel_mixer.m.2.bn.weight",
      "stages.2.20.block.channel_mixer.m.2.bn.bias",
      "stages.2.21.block.token_channel_mixer.m.0.bn.weight",
      "stages.2.21.block.token_channel_mixer.m.0.bn.bias",
      "stages.2.21.block.token_channel_mixer.m.1.bn.weight",
      "stages.2.21.block.token_channel_mixer.m.1.bn.bias",
      "stages.2.21.block.token_channel_mixer.m.3.bn.weight",
      "stages.2.21.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.proj.bn.weight",
      "stages.3.1.block.token_channel_mixer.m.proj.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.3.2.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.proj.bn.weight",
      "stages.3.4.block.token_channel_mixer.m.proj.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.3.5.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: checkpoint-1.pth
Resume checkpoint checkpoint-1.pth
With optim & sched!
Start training for 300 epochs
Epoch: [2]  [  0/312]  eta: 4:48:12  lr: 0.000400  min_lr: 0.000400  loss: 6.3473 (6.3473)  weight_decay: 0.0500 (0.0500)  time: 55.4257  data: 13.3526  max mem: 42573
Epoch: [2]  [ 10/312]  eta: 0:31:18  lr: 0.000406  min_lr: 0.000406  loss: 6.2674 (6.1729)  weight_decay: 0.0500 (0.0500)  time: 6.2201  data: 1.2143  max mem: 42573
Epoch: [2]  [ 20/312]  eta: 0:18:05  lr: 0.000413  min_lr: 0.000413  loss: 6.1618 (6.1397)  weight_decay: 0.0500 (0.0500)  time: 1.1303  data: 0.0005  max mem: 42573
Epoch: [2]  [ 30/312]  eta: 0:13:17  lr: 0.000419  min_lr: 0.000419  loss: 6.1359 (6.1254)  weight_decay: 0.0500 (0.0500)  time: 0.9601  data: 0.0005  max mem: 42573
Epoch: [2]  [ 40/312]  eta: 0:10:44  lr: 0.000426  min_lr: 0.000426  loss: 6.0942 (6.0877)  weight_decay: 0.0500 (0.0500)  time: 0.9587  data: 0.0005  max mem: 42573
Epoch: [2]  [ 50/312]  eta: 0:09:08  lr: 0.000432  min_lr: 0.000432  loss: 6.0283 (6.0825)  weight_decay: 0.0500 (0.0500)  time: 0.9601  data: 0.0004  max mem: 42573
Epoch: [2]  [ 60/312]  eta: 0:07:53  lr: 0.000439  min_lr: 0.000439  loss: 5.9784 (6.0516)  weight_decay: 0.0500 (0.0500)  time: 0.8714  data: 0.0004  max mem: 42573
Epoch: [2]  [ 70/312]  eta: 0:06:45  lr: 0.000445  min_lr: 0.000445  loss: 5.9301 (6.0304)  weight_decay: 0.0500 (0.0500)  time: 0.6074  data: 0.0005  max mem: 42573
Epoch: [2]  [ 80/312]  eta: 0:05:53  lr: 0.000451  min_lr: 0.000451  loss: 5.9301 (6.0228)  weight_decay: 0.0500 (0.0500)  time: 0.4342  data: 0.0005  max mem: 42573
Epoch: [2]  [ 90/312]  eta: 0:05:11  lr: 0.000458  min_lr: 0.000458  loss: 6.0516 (6.0167)  weight_decay: 0.0500 (0.0500)  time: 0.4343  data: 0.0004  max mem: 42573
Epoch: [2]  [100/312]  eta: 0:04:37  lr: 0.000464  min_lr: 0.000464  loss: 6.0586 (6.0148)  weight_decay: 0.0500 (0.0500)  time: 0.4341  data: 0.0004  max mem: 42573
Epoch: [2]  [110/312]  eta: 0:04:08  lr: 0.000471  min_lr: 0.000471  loss: 5.9300 (6.0069)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0004  max mem: 42573
Epoch: [2]  [120/312]  eta: 0:03:43  lr: 0.000477  min_lr: 0.000477  loss: 5.9300 (6.0002)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0004  max mem: 42573
Epoch: [2]  [130/312]  eta: 0:03:21  lr: 0.000483  min_lr: 0.000483  loss: 5.9122 (5.9861)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [2]  [140/312]  eta: 0:03:02  lr: 0.000490  min_lr: 0.000490  loss: 5.8019 (5.9758)  weight_decay: 0.0500 (0.0500)  time: 0.4361  data: 0.0004  max mem: 42573
Epoch: [2]  [150/312]  eta: 0:02:44  lr: 0.000496  min_lr: 0.000496  loss: 5.8440 (5.9670)  weight_decay: 0.0500 (0.0500)  time: 0.4359  data: 0.0004  max mem: 42573
Epoch: [2]  [160/312]  eta: 0:02:29  lr: 0.000503  min_lr: 0.000503  loss: 5.9673 (5.9640)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [2]  [170/312]  eta: 0:02:14  lr: 0.000509  min_lr: 0.000509  loss: 5.9429 (5.9570)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [2]  [180/312]  eta: 0:02:01  lr: 0.000515  min_lr: 0.000515  loss: 5.7542 (5.9423)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [2]  [190/312]  eta: 0:01:49  lr: 0.000522  min_lr: 0.000522  loss: 5.6486 (5.9347)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0005  max mem: 42573
Epoch: [2]  [200/312]  eta: 0:01:37  lr: 0.000528  min_lr: 0.000528  loss: 5.6437 (5.9199)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0005  max mem: 42573
Epoch: [2]  [210/312]  eta: 0:01:26  lr: 0.000535  min_lr: 0.000535  loss: 5.6437 (5.9083)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0005  max mem: 42573
Epoch: [2]  [220/312]  eta: 0:01:16  lr: 0.000541  min_lr: 0.000541  loss: 5.6674 (5.8969)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0005  max mem: 42573
Epoch: [2]  [230/312]  eta: 0:01:06  lr: 0.000548  min_lr: 0.000548  loss: 5.7687 (5.8917)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0005  max mem: 42573
Epoch: [2]  [240/312]  eta: 0:00:57  lr: 0.000554  min_lr: 0.000554  loss: 5.7665 (5.8821)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [2]  [250/312]  eta: 0:00:48  lr: 0.000560  min_lr: 0.000560  loss: 5.5841 (5.8712)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [2]  [260/312]  eta: 0:00:40  lr: 0.000567  min_lr: 0.000567  loss: 5.4436 (5.8592)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [2]  [270/312]  eta: 0:00:31  lr: 0.000573  min_lr: 0.000573  loss: 5.4447 (5.8481)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [2]  [280/312]  eta: 0:00:23  lr: 0.000580  min_lr: 0.000580  loss: 5.7623 (5.8477)  weight_decay: 0.0500 (0.0500)  time: 0.4351  data: 0.0009  max mem: 42573
Epoch: [2]  [290/312]  eta: 0:00:16  lr: 0.000586  min_lr: 0.000586  loss: 5.8624 (5.8381)  weight_decay: 0.0500 (0.0500)  time: 0.4345  data: 0.0008  max mem: 42573
Epoch: [2]  [300/312]  eta: 0:00:08  lr: 0.000592  min_lr: 0.000592  loss: 5.4333 (5.8263)  weight_decay: 0.0500 (0.0500)  time: 0.4324  data: 0.0001  max mem: 42573
Epoch: [2]  [310/312]  eta: 0:00:01  lr: 0.000599  min_lr: 0.000599  loss: 5.5614 (5.8209)  weight_decay: 0.0500 (0.0500)  time: 0.4325  data: 0.0001  max mem: 42573
Epoch: [2]  [311/312]  eta: 0:00:00  lr: 0.000599  min_lr: 0.000599  loss: 5.6197 (5.8211)  weight_decay: 0.0500 (0.0500)  time: 0.4325  data: 0.0001  max mem: 42573
Epoch: [2] Total time: 0:03:44 (0.7199 s / it)
Averaged stats: lr: 0.000599  min_lr: 0.000599  loss: 5.6197 (5.8331)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:15  loss: 3.9940 (3.9940)  acc1: 21.6146 (21.6146)  acc5: 44.7917 (44.7917)  time: 8.3481  data: 4.4638  max mem: 42573
Test:  [8/9]  eta: 0:00:01  loss: 4.1395 (4.1743)  acc1: 17.1875 (17.8240)  acc5: 40.3646 (37.9520)  time: 1.1768  data: 0.4961  max mem: 42573
Test: Total time: 0:00:10 (1.1837 s / it)
* Acc@1 16.934 Acc@5 37.822 loss 4.171
Accuracy of the model on the 50000 test images: 16.9%
Max accuracy: 16.93%
Epoch: [3]  [  0/312]  eta: 1:25:18  lr: 0.000600  min_lr: 0.000600  loss: 5.8201 (5.8201)  weight_decay: 0.0500 (0.0500)  time: 16.4065  data: 9.0737  max mem: 42573
Epoch: [3]  [ 10/312]  eta: 0:11:59  lr: 0.000607  min_lr: 0.000607  loss: 5.8508 (5.7985)  weight_decay: 0.0500 (0.0500)  time: 2.3815  data: 0.8254  max mem: 42573
Epoch: [3]  [ 20/312]  eta: 0:08:20  lr: 0.000613  min_lr: 0.000613  loss: 5.8552 (5.7330)  weight_decay: 0.0500 (0.0500)  time: 0.9784  data: 0.0005  max mem: 42573
Epoch: [3]  [ 30/312]  eta: 0:06:56  lr: 0.000619  min_lr: 0.000619  loss: 5.7837 (5.7155)  weight_decay: 0.0500 (0.0500)  time: 0.9772  data: 0.0004  max mem: 42573
Epoch: [3]  [ 40/312]  eta: 0:06:08  lr: 0.000626  min_lr: 0.000626  loss: 5.6929 (5.6788)  weight_decay: 0.0500 (0.0500)  time: 0.9755  data: 0.0004  max mem: 42573
Epoch: [3]  [ 50/312]  eta: 0:05:13  lr: 0.000632  min_lr: 0.000632  loss: 5.5115 (5.6569)  weight_decay: 0.0500 (0.0500)  time: 0.7672  data: 0.0004  max mem: 42573
Epoch: [3]  [ 60/312]  eta: 0:04:30  lr: 0.000639  min_lr: 0.000639  loss: 5.4931 (5.6278)  weight_decay: 0.0500 (0.0500)  time: 0.4970  data: 0.0003  max mem: 42573
Epoch: [3]  [ 70/312]  eta: 0:03:57  lr: 0.000645  min_lr: 0.000645  loss: 5.4931 (5.6032)  weight_decay: 0.0500 (0.0500)  time: 0.4341  data: 0.0004  max mem: 42573
Epoch: [3]  [ 80/312]  eta: 0:03:32  lr: 0.000651  min_lr: 0.000651  loss: 5.3666 (5.5851)  weight_decay: 0.0500 (0.0500)  time: 0.4342  data: 0.0004  max mem: 42573
Epoch: [3]  [ 90/312]  eta: 0:03:11  lr: 0.000658  min_lr: 0.000658  loss: 5.5836 (5.5941)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [3]  [100/312]  eta: 0:02:53  lr: 0.000664  min_lr: 0.000664  loss: 5.6254 (5.5939)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [3]  [110/312]  eta: 0:02:38  lr: 0.000671  min_lr: 0.000671  loss: 5.4613 (5.5716)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0004  max mem: 42573
Epoch: [3]  [120/312]  eta: 0:02:25  lr: 0.000677  min_lr: 0.000677  loss: 5.4803 (5.5804)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0004  max mem: 42573
Epoch: [3]  [130/312]  eta: 0:02:13  lr: 0.000683  min_lr: 0.000683  loss: 5.6129 (5.5801)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0004  max mem: 42573
Epoch: [3]  [140/312]  eta: 0:02:02  lr: 0.000690  min_lr: 0.000690  loss: 5.3950 (5.5602)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [3]  [150/312]  eta: 0:01:52  lr: 0.000696  min_lr: 0.000696  loss: 5.2232 (5.5402)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [3]  [160/312]  eta: 0:01:42  lr: 0.000703  min_lr: 0.000703  loss: 5.1854 (5.5243)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0004  max mem: 42573
Epoch: [3]  [170/312]  eta: 0:01:33  lr: 0.000709  min_lr: 0.000709  loss: 5.3449 (5.5174)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0003  max mem: 42573
Epoch: [3]  [180/312]  eta: 0:01:25  lr: 0.000715  min_lr: 0.000715  loss: 5.3684 (5.5168)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [3]  [190/312]  eta: 0:01:17  lr: 0.000722  min_lr: 0.000722  loss: 5.3612 (5.5066)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0004  max mem: 42573
Epoch: [3]  [200/312]  eta: 0:01:10  lr: 0.000728  min_lr: 0.000728  loss: 5.5143 (5.5156)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0005  max mem: 42573
Epoch: [3]  [210/312]  eta: 0:01:03  lr: 0.000735  min_lr: 0.000735  loss: 5.6025 (5.5046)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0005  max mem: 42573
Epoch: [3]  [220/312]  eta: 0:00:56  lr: 0.000741  min_lr: 0.000741  loss: 5.4515 (5.4974)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [3]  [230/312]  eta: 0:00:49  lr: 0.000748  min_lr: 0.000748  loss: 5.4714 (5.4901)  weight_decay: 0.0500 (0.0500)  time: 0.4341  data: 0.0004  max mem: 42573
Epoch: [3]  [240/312]  eta: 0:00:42  lr: 0.000754  min_lr: 0.000754  loss: 5.4776 (5.4867)  weight_decay: 0.0500 (0.0500)  time: 0.4341  data: 0.0004  max mem: 42573
Epoch: [3]  [250/312]  eta: 0:00:36  lr: 0.000760  min_lr: 0.000760  loss: 5.5544 (5.4889)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0004  max mem: 42573
Epoch: [3]  [260/312]  eta: 0:00:30  lr: 0.000767  min_lr: 0.000767  loss: 5.5451 (5.4853)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [3]  [270/312]  eta: 0:00:24  lr: 0.000773  min_lr: 0.000773  loss: 5.5148 (5.4819)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [3]  [280/312]  eta: 0:00:18  lr: 0.000780  min_lr: 0.000780  loss: 5.5148 (5.4773)  weight_decay: 0.0500 (0.0500)  time: 0.4352  data: 0.0010  max mem: 42573
Epoch: [3]  [290/312]  eta: 0:00:12  lr: 0.000786  min_lr: 0.000786  loss: 5.2752 (5.4683)  weight_decay: 0.0500 (0.0500)  time: 0.4344  data: 0.0008  max mem: 42573
Epoch: [3]  [300/312]  eta: 0:00:06  lr: 0.000792  min_lr: 0.000792  loss: 5.2524 (5.4644)  weight_decay: 0.0500 (0.0500)  time: 0.4324  data: 0.0001  max mem: 42573
Epoch: [3]  [310/312]  eta: 0:00:01  lr: 0.000799  min_lr: 0.000799  loss: 5.4373 (5.4632)  weight_decay: 0.0500 (0.0500)  time: 0.4386  data: 0.0001  max mem: 42573
Epoch: [3]  [311/312]  eta: 0:00:00  lr: 0.000799  min_lr: 0.000799  loss: 5.4373 (5.4631)  weight_decay: 0.0500 (0.0500)  time: 0.4386  data: 0.0001  max mem: 42573
Epoch: [3] Total time: 0:02:55 (0.5623 s / it)
Averaged stats: lr: 0.000799  min_lr: 0.000799  loss: 5.4373 (5.4495)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:00:40  loss: 3.4145 (3.4145)  acc1: 29.9479 (29.9479)  acc5: 54.1667 (54.1667)  time: 4.5288  data: 4.4202  max mem: 42573
Test:  [8/9]  eta: 0:00:00  loss: 3.7536 (3.6859)  acc1: 22.1354 (23.7120)  acc5: 46.8750 (46.1120)  time: 0.5799  data: 0.4912  max mem: 42573
Test: Total time: 0:00:05 (0.5868 s / it)
* Acc@1 24.244 Acc@5 47.500 loss 3.653
Accuracy of the model on the 50000 test images: 24.2%
Max accuracy: 24.24%
Epoch: [4]  [  0/312]  eta: 0:52:01  lr: 0.000800  min_lr: 0.000800  loss: 5.4971 (5.4971)  weight_decay: 0.0500 (0.0500)  time: 10.0041  data: 8.0463  max mem: 42573
Epoch: [4]  [ 10/312]  eta: 0:07:17  lr: 0.000807  min_lr: 0.000807  loss: 5.2329 (5.2921)  weight_decay: 0.0500 (0.0500)  time: 1.4474  data: 0.7318  max mem: 42573
Epoch: [4]  [ 20/312]  eta: 0:04:41  lr: 0.000813  min_lr: 0.000813  loss: 5.0332 (5.1248)  weight_decay: 0.0500 (0.0500)  time: 0.5126  data: 0.0004  max mem: 42573
Epoch: [4]  [ 30/312]  eta: 0:03:43  lr: 0.000819  min_lr: 0.000819  loss: 5.1849 (5.1765)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [4]  [ 40/312]  eta: 0:03:11  lr: 0.000826  min_lr: 0.000826  loss: 5.1822 (5.1300)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [4]  [ 50/312]  eta: 0:02:50  lr: 0.000832  min_lr: 0.000832  loss: 5.1611 (5.1694)  weight_decay: 0.0500 (0.0500)  time: 0.4343  data: 0.0005  max mem: 42573
Epoch: [4]  [ 60/312]  eta: 0:02:35  lr: 0.000839  min_lr: 0.000839  loss: 5.2760 (5.1597)  weight_decay: 0.0500 (0.0500)  time: 0.4346  data: 0.0005  max mem: 42573
Epoch: [4]  [ 70/312]  eta: 0:02:23  lr: 0.000845  min_lr: 0.000845  loss: 5.0401 (5.1454)  weight_decay: 0.0500 (0.0500)  time: 0.4341  data: 0.0004  max mem: 42573
Epoch: [4]  [ 80/312]  eta: 0:02:12  lr: 0.000851  min_lr: 0.000851  loss: 4.9122 (5.1405)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [4]  [ 90/312]  eta: 0:02:03  lr: 0.000858  min_lr: 0.000858  loss: 4.8336 (5.1266)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [4]  [100/312]  eta: 0:01:55  lr: 0.000864  min_lr: 0.000864  loss: 4.9154 (5.1152)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [4]  [110/312]  eta: 0:01:47  lr: 0.000871  min_lr: 0.000871  loss: 5.1414 (5.1292)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [4]  [120/312]  eta: 0:01:41  lr: 0.000877  min_lr: 0.000877  loss: 5.3840 (5.1411)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [4]  [130/312]  eta: 0:01:34  lr: 0.000883  min_lr: 0.000883  loss: 5.2229 (5.1331)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [4]  [140/312]  eta: 0:01:28  lr: 0.000890  min_lr: 0.000890  loss: 5.1564 (5.1449)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0004  max mem: 42573
Epoch: [4]  [150/312]  eta: 0:01:22  lr: 0.000896  min_lr: 0.000896  loss: 5.2420 (5.1465)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0004  max mem: 42573
Epoch: [4]  [160/312]  eta: 0:01:16  lr: 0.000903  min_lr: 0.000903  loss: 5.2170 (5.1398)  weight_decay: 0.0500 (0.0500)  time: 0.4345  data: 0.0004  max mem: 42573
Epoch: [4]  [170/312]  eta: 0:01:10  lr: 0.000909  min_lr: 0.000909  loss: 5.0885 (5.1426)  weight_decay: 0.0500 (0.0500)  time: 0.4343  data: 0.0004  max mem: 42573
Epoch: [4]  [180/312]  eta: 0:01:05  lr: 0.000916  min_lr: 0.000916  loss: 5.0485 (5.1300)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [4]  [190/312]  eta: 0:01:00  lr: 0.000922  min_lr: 0.000922  loss: 4.7890 (5.1141)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [4]  [200/312]  eta: 0:00:54  lr: 0.000928  min_lr: 0.000928  loss: 4.7931 (5.1136)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [4]  [210/312]  eta: 0:00:49  lr: 0.000935  min_lr: 0.000935  loss: 4.9525 (5.0981)  weight_decay: 0.0500 (0.0500)  time: 0.4344  data: 0.0004  max mem: 42573
Epoch: [4]  [220/312]  eta: 0:00:44  lr: 0.000941  min_lr: 0.000941  loss: 4.6450 (5.0902)  weight_decay: 0.0500 (0.0500)  time: 0.4343  data: 0.0004  max mem: 42573
Epoch: [4]  [230/312]  eta: 0:00:39  lr: 0.000948  min_lr: 0.000948  loss: 5.0497 (5.0935)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [4]  [240/312]  eta: 0:00:34  lr: 0.000954  min_lr: 0.000954  loss: 5.1244 (5.0895)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [4]  [250/312]  eta: 0:00:29  lr: 0.000960  min_lr: 0.000960  loss: 5.0931 (5.0879)  weight_decay: 0.0500 (0.0500)  time: 0.4366  data: 0.0004  max mem: 42573
Epoch: [4]  [260/312]  eta: 0:00:24  lr: 0.000967  min_lr: 0.000967  loss: 5.0177 (5.0759)  weight_decay: 0.0500 (0.0500)  time: 0.4366  data: 0.0003  max mem: 42573
Epoch: [4]  [270/312]  eta: 0:00:19  lr: 0.000973  min_lr: 0.000973  loss: 4.8068 (5.0687)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0003  max mem: 42573
Epoch: [4]  [280/312]  eta: 0:00:15  lr: 0.000980  min_lr: 0.000980  loss: 5.1398 (5.0636)  weight_decay: 0.0500 (0.0500)  time: 0.4347  data: 0.0009  max mem: 42573
Epoch: [4]  [290/312]  eta: 0:00:10  lr: 0.000986  min_lr: 0.000986  loss: 5.1699 (5.0579)  weight_decay: 0.0500 (0.0500)  time: 0.4341  data: 0.0008  max mem: 42573
Epoch: [4]  [300/312]  eta: 0:00:05  lr: 0.000992  min_lr: 0.000992  loss: 5.1642 (5.0619)  weight_decay: 0.0500 (0.0500)  time: 0.4325  data: 0.0001  max mem: 42573
Epoch: [4]  [310/312]  eta: 0:00:00  lr: 0.000999  min_lr: 0.000999  loss: 5.1170 (5.0593)  weight_decay: 0.0500 (0.0500)  time: 0.4324  data: 0.0001  max mem: 42573
Epoch: [4]  [311/312]  eta: 0:00:00  lr: 0.001000  min_lr: 0.001000  loss: 5.1146 (5.0571)  weight_decay: 0.0500 (0.0500)  time: 0.4324  data: 0.0001  max mem: 42573
Epoch: [4] Total time: 0:02:27 (0.4729 s / it)
Averaged stats: lr: 0.001000  min_lr: 0.001000  loss: 5.1146 (5.0873)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:00:41  loss: 3.0345 (3.0345)  acc1: 40.3646 (40.3646)  acc5: 62.2396 (62.2396)  time: 4.6026  data: 4.4930  max mem: 42573
Test:  [8/9]  eta: 0:00:00  loss: 3.1795 (3.1680)  acc1: 32.5521 (31.9360)  acc5: 60.1562 (56.4480)  time: 0.5867  data: 0.4993  max mem: 42573
Test: Total time: 0:00:05 (0.5968 s / it)
* Acc@1 32.400 Acc@5 57.234 loss 3.149
Accuracy of the model on the 50000 test images: 32.4%
Max accuracy: 32.40%
Epoch: [5]  [  0/312]  eta: 0:50:00  lr: 0.001000  min_lr: 0.001000  loss: 5.3581 (5.3581)  weight_decay: 0.0500 (0.0500)  time: 9.6159  data: 7.2616  max mem: 42573
Epoch: [5]  [ 10/312]  eta: 0:07:20  lr: 0.001007  min_lr: 0.001007  loss: 5.0098 (4.8302)  weight_decay: 0.0500 (0.0500)  time: 1.4598  data: 0.6605  max mem: 42573
Epoch: [5]  [ 20/312]  eta: 0:04:43  lr: 0.001013  min_lr: 0.001013  loss: 4.6122 (4.7753)  weight_decay: 0.0500 (0.0500)  time: 0.5387  data: 0.0004  max mem: 42573
Epoch: [5]  [ 30/312]  eta: 0:03:44  lr: 0.001019  min_lr: 0.001019  loss: 4.9054 (4.8582)  weight_decay: 0.0500 (0.0500)  time: 0.4332  data: 0.0004  max mem: 42573
Epoch: [5]  [ 40/312]  eta: 0:03:12  lr: 0.001026  min_lr: 0.001026  loss: 5.0510 (4.9036)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0003  max mem: 42573
Epoch: [5]  [ 50/312]  eta: 0:02:51  lr: 0.001032  min_lr: 0.001032  loss: 5.1274 (4.9071)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0003  max mem: 42573
Epoch: [5]  [ 60/312]  eta: 0:02:35  lr: 0.001039  min_lr: 0.001039  loss: 5.1274 (4.8981)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [5]  [ 70/312]  eta: 0:02:23  lr: 0.001045  min_lr: 0.001045  loss: 4.9305 (4.8964)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [5]  [ 80/312]  eta: 0:02:12  lr: 0.001051  min_lr: 0.001051  loss: 4.9305 (4.9072)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [5]  [ 90/312]  eta: 0:02:03  lr: 0.001058  min_lr: 0.001058  loss: 4.8201 (4.8731)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [5]  [100/312]  eta: 0:01:55  lr: 0.001064  min_lr: 0.001064  loss: 4.8201 (4.8730)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0005  max mem: 42573
Epoch: [5]  [110/312]  eta: 0:01:48  lr: 0.001071  min_lr: 0.001071  loss: 5.0442 (4.8769)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [5]  [120/312]  eta: 0:01:41  lr: 0.001077  min_lr: 0.001077  loss: 5.0541 (4.8862)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [5]  [130/312]  eta: 0:01:34  lr: 0.001084  min_lr: 0.001084  loss: 4.9901 (4.8823)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [5]  [140/312]  eta: 0:01:28  lr: 0.001090  min_lr: 0.001090  loss: 4.7774 (4.8704)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [5]  [150/312]  eta: 0:01:22  lr: 0.001096  min_lr: 0.001096  loss: 4.6662 (4.8691)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [5]  [160/312]  eta: 0:01:16  lr: 0.001103  min_lr: 0.001103  loss: 4.7449 (4.8589)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [5]  [170/312]  eta: 0:01:10  lr: 0.001109  min_lr: 0.001109  loss: 4.9390 (4.8583)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [5]  [180/312]  eta: 0:01:05  lr: 0.001116  min_lr: 0.001116  loss: 4.9488 (4.8542)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [5]  [190/312]  eta: 0:01:00  lr: 0.001122  min_lr: 0.001122  loss: 4.8363 (4.8504)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0004  max mem: 42573
Epoch: [5]  [200/312]  eta: 0:00:54  lr: 0.001128  min_lr: 0.001128  loss: 4.7108 (4.8458)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [5]  [210/312]  eta: 0:00:49  lr: 0.001135  min_lr: 0.001135  loss: 4.8760 (4.8466)  weight_decay: 0.0500 (0.0500)  time: 0.4417  data: 0.0004  max mem: 42573
Epoch: [5]  [220/312]  eta: 0:00:44  lr: 0.001141  min_lr: 0.001141  loss: 4.8948 (4.8436)  weight_decay: 0.0500 (0.0500)  time: 0.4417  data: 0.0004  max mem: 42573
Epoch: [5]  [230/312]  eta: 0:00:39  lr: 0.001148  min_lr: 0.001148  loss: 4.6936 (4.8310)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [5]  [240/312]  eta: 0:00:34  lr: 0.001154  min_lr: 0.001154  loss: 4.8182 (4.8377)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0003  max mem: 42573
Epoch: [5]  [250/312]  eta: 0:00:29  lr: 0.001160  min_lr: 0.001160  loss: 5.0894 (4.8462)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [5]  [260/312]  eta: 0:00:24  lr: 0.001167  min_lr: 0.001167  loss: 4.9917 (4.8400)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [5]  [270/312]  eta: 0:00:19  lr: 0.001173  min_lr: 0.001173  loss: 4.7516 (4.8407)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [5]  [280/312]  eta: 0:00:15  lr: 0.001180  min_lr: 0.001180  loss: 4.8756 (4.8361)  weight_decay: 0.0500 (0.0500)  time: 0.4349  data: 0.0010  max mem: 42573
Epoch: [5]  [290/312]  eta: 0:00:10  lr: 0.001186  min_lr: 0.001186  loss: 4.7311 (4.8277)  weight_decay: 0.0500 (0.0500)  time: 0.4345  data: 0.0009  max mem: 42573
Epoch: [5]  [300/312]  eta: 0:00:05  lr: 0.001192  min_lr: 0.001192  loss: 4.6877 (4.8218)  weight_decay: 0.0500 (0.0500)  time: 0.4326  data: 0.0001  max mem: 42573
Epoch: [5]  [310/312]  eta: 0:00:00  lr: 0.001199  min_lr: 0.001199  loss: 4.7250 (4.8185)  weight_decay: 0.0500 (0.0500)  time: 0.4325  data: 0.0001  max mem: 42573
Epoch: [5]  [311/312]  eta: 0:00:00  lr: 0.001200  min_lr: 0.001200  loss: 4.7250 (4.8167)  weight_decay: 0.0500 (0.0500)  time: 0.4324  data: 0.0001  max mem: 42573
Epoch: [5] Total time: 0:02:27 (0.4733 s / it)
Averaged stats: lr: 0.001200  min_lr: 0.001200  loss: 4.7250 (4.7895)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:00:40  loss: 2.4762 (2.4762)  acc1: 46.6146 (46.6146)  acc5: 68.7500 (68.7500)  time: 4.5483  data: 4.4395  max mem: 42573
Test:  [8/9]  eta: 0:00:00  loss: 2.8881 (2.7680)  acc1: 37.5000 (38.3360)  acc5: 62.7604 (63.2960)  time: 0.5857  data: 0.4934  max mem: 42573
Test: Total time: 0:00:05 (0.5929 s / it)
* Acc@1 38.956 Acc@5 64.284 loss 2.757
Accuracy of the model on the 50000 test images: 39.0%
Max accuracy: 38.96%
Epoch: [6]  [  0/312]  eta: 0:49:14  lr: 0.001200  min_lr: 0.001200  loss: 3.9007 (3.9007)  weight_decay: 0.0500 (0.0500)  time: 9.4704  data: 7.0829  max mem: 42573
Epoch: [6]  [ 10/312]  eta: 0:07:04  lr: 0.001207  min_lr: 0.001207  loss: 4.6617 (4.5352)  weight_decay: 0.0500 (0.0500)  time: 1.4055  data: 0.7797  max mem: 42573
Epoch: [6]  [ 20/312]  eta: 0:04:35  lr: 0.001213  min_lr: 0.001213  loss: 4.8046 (4.6613)  weight_decay: 0.0500 (0.0500)  time: 0.5160  data: 0.0748  max mem: 42573
Epoch: [6]  [ 30/312]  eta: 0:03:39  lr: 0.001219  min_lr: 0.001219  loss: 4.8201 (4.6889)  weight_decay: 0.0500 (0.0500)  time: 0.4330  data: 0.0003  max mem: 42573
Epoch: [6]  [ 40/312]  eta: 0:03:08  lr: 0.001226  min_lr: 0.001226  loss: 4.8201 (4.7169)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [6]  [ 50/312]  eta: 0:02:48  lr: 0.001232  min_lr: 0.001232  loss: 4.7221 (4.6956)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [6]  [ 60/312]  eta: 0:02:33  lr: 0.001239  min_lr: 0.001239  loss: 4.6316 (4.6778)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [6]  [ 70/312]  eta: 0:02:21  lr: 0.001245  min_lr: 0.001245  loss: 4.4059 (4.6413)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [6]  [ 80/312]  eta: 0:02:11  lr: 0.001251  min_lr: 0.001251  loss: 4.5115 (4.6259)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [6]  [ 90/312]  eta: 0:02:02  lr: 0.001258  min_lr: 0.001258  loss: 4.7603 (4.6218)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [6]  [100/312]  eta: 0:01:54  lr: 0.001264  min_lr: 0.001264  loss: 4.7711 (4.6271)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0003  max mem: 42573
Epoch: [6]  [110/312]  eta: 0:01:47  lr: 0.001271  min_lr: 0.001271  loss: 4.7711 (4.6373)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [6]  [120/312]  eta: 0:01:40  lr: 0.001277  min_lr: 0.001277  loss: 4.8607 (4.6521)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [6]  [130/312]  eta: 0:01:33  lr: 0.001284  min_lr: 0.001284  loss: 4.8210 (4.6572)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [6]  [140/312]  eta: 0:01:27  lr: 0.001290  min_lr: 0.001290  loss: 4.8210 (4.6551)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [6]  [150/312]  eta: 0:01:21  lr: 0.001296  min_lr: 0.001296  loss: 4.6648 (4.6472)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [6]  [160/312]  eta: 0:01:16  lr: 0.001303  min_lr: 0.001303  loss: 4.8130 (4.6613)  weight_decay: 0.0500 (0.0500)  time: 0.4407  data: 0.0004  max mem: 42573
Epoch: [6]  [170/312]  eta: 0:01:10  lr: 0.001309  min_lr: 0.001309  loss: 4.7697 (4.6527)  weight_decay: 0.0500 (0.0500)  time: 0.4406  data: 0.0004  max mem: 42573
Epoch: [6]  [180/312]  eta: 0:01:05  lr: 0.001316  min_lr: 0.001316  loss: 4.4347 (4.6431)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [6]  [190/312]  eta: 0:00:59  lr: 0.001322  min_lr: 0.001322  loss: 4.4347 (4.6393)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [6]  [200/312]  eta: 0:00:54  lr: 0.001328  min_lr: 0.001328  loss: 4.8083 (4.6378)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [6]  [210/312]  eta: 0:00:49  lr: 0.001335  min_lr: 0.001335  loss: 4.6493 (4.6334)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [6]  [220/312]  eta: 0:00:44  lr: 0.001341  min_lr: 0.001341  loss: 4.6493 (4.6344)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [6]  [230/312]  eta: 0:00:39  lr: 0.001348  min_lr: 0.001348  loss: 4.6287 (4.6211)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [6]  [240/312]  eta: 0:00:34  lr: 0.001354  min_lr: 0.001354  loss: 4.1905 (4.6019)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [6]  [250/312]  eta: 0:00:29  lr: 0.001360  min_lr: 0.001360  loss: 4.1694 (4.5892)  weight_decay: 0.0500 (0.0500)  time: 0.4343  data: 0.0003  max mem: 42573
Epoch: [6]  [260/312]  eta: 0:00:24  lr: 0.001367  min_lr: 0.001367  loss: 4.4348 (4.5930)  weight_decay: 0.0500 (0.0500)  time: 0.4342  data: 0.0004  max mem: 42573
Epoch: [6]  [270/312]  eta: 0:00:19  lr: 0.001373  min_lr: 0.001373  loss: 4.7532 (4.5948)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [6]  [280/312]  eta: 0:00:15  lr: 0.001380  min_lr: 0.001380  loss: 4.4999 (4.5870)  weight_decay: 0.0500 (0.0500)  time: 0.4342  data: 0.0009  max mem: 42573
Epoch: [6]  [290/312]  eta: 0:00:10  lr: 0.001386  min_lr: 0.001386  loss: 4.4667 (4.5839)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0008  max mem: 42573
Epoch: [6]  [300/312]  eta: 0:00:05  lr: 0.001393  min_lr: 0.001393  loss: 4.4948 (4.5735)  weight_decay: 0.0500 (0.0500)  time: 0.4325  data: 0.0001  max mem: 42573
Epoch: [6]  [310/312]  eta: 0:00:00  lr: 0.001399  min_lr: 0.001399  loss: 4.5172 (4.5741)  weight_decay: 0.0500 (0.0500)  time: 0.4324  data: 0.0001  max mem: 42573
Epoch: [6]  [311/312]  eta: 0:00:00  lr: 0.001400  min_lr: 0.001400  loss: 4.4704 (4.5722)  weight_decay: 0.0500 (0.0500)  time: 0.4324  data: 0.0001  max mem: 42573
Epoch: [6] Total time: 0:02:27 (0.4714 s / it)
Averaged stats: lr: 0.001400  min_lr: 0.001400  loss: 4.4704 (4.5511)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:00:42  loss: 2.2888 (2.2888)  acc1: 51.3021 (51.3021)  acc5: 73.4375 (73.4375)  time: 4.7330  data: 4.6236  max mem: 42573
Test:  [8/9]  eta: 0:00:00  loss: 2.6976 (2.5324)  acc1: 42.4479 (42.6880)  acc5: 67.9688 (67.9680)  time: 0.6024  data: 0.5138  max mem: 42573
Test: Total time: 0:00:05 (0.6135 s / it)
* Acc@1 43.368 Acc@5 68.882 loss 2.506
Accuracy of the model on the 50000 test images: 43.4%
Max accuracy: 43.37%
Epoch: [7]  [  0/312]  eta: 0:49:48  lr: 0.001400  min_lr: 0.001400  loss: 3.4814 (3.4814)  weight_decay: 0.0500 (0.0500)  time: 9.5789  data: 7.5783  max mem: 42573
Epoch: [7]  [ 10/312]  eta: 0:07:10  lr: 0.001407  min_lr: 0.001407  loss: 3.9893 (4.0350)  weight_decay: 0.0500 (0.0500)  time: 1.4251  data: 0.6892  max mem: 42573
Epoch: [7]  [ 20/312]  eta: 0:04:38  lr: 0.001413  min_lr: 0.001413  loss: 4.0821 (4.1939)  weight_decay: 0.0500 (0.0500)  time: 0.5214  data: 0.0003  max mem: 42573
Epoch: [7]  [ 30/312]  eta: 0:03:41  lr: 0.001419  min_lr: 0.001419  loss: 4.4750 (4.2831)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0003  max mem: 42573
Epoch: [7]  [ 40/312]  eta: 0:03:10  lr: 0.001426  min_lr: 0.001426  loss: 4.4772 (4.3753)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0003  max mem: 42573
Epoch: [7]  [ 50/312]  eta: 0:02:49  lr: 0.001432  min_lr: 0.001432  loss: 4.5455 (4.3983)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [7]  [ 60/312]  eta: 0:02:34  lr: 0.001439  min_lr: 0.001439  loss: 4.3795 (4.3851)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [7]  [ 70/312]  eta: 0:02:22  lr: 0.001445  min_lr: 0.001445  loss: 4.4589 (4.4023)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [7]  [ 80/312]  eta: 0:02:11  lr: 0.001452  min_lr: 0.001452  loss: 4.4875 (4.4070)  weight_decay: 0.0500 (0.0500)  time: 0.4351  data: 0.0004  max mem: 42573
Epoch: [7]  [ 90/312]  eta: 0:02:02  lr: 0.001458  min_lr: 0.001458  loss: 4.1889 (4.3623)  weight_decay: 0.0500 (0.0500)  time: 0.4349  data: 0.0004  max mem: 42573
Epoch: [7]  [100/312]  eta: 0:01:54  lr: 0.001464  min_lr: 0.001464  loss: 3.9367 (4.3335)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0004  max mem: 42573
Epoch: [7]  [110/312]  eta: 0:01:47  lr: 0.001471  min_lr: 0.001471  loss: 4.1403 (4.3332)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0004  max mem: 42573
Epoch: [7]  [120/312]  eta: 0:01:40  lr: 0.001477  min_lr: 0.001477  loss: 4.3746 (4.3336)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [7]  [130/312]  eta: 0:01:34  lr: 0.001484  min_lr: 0.001484  loss: 4.4426 (4.3351)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [7]  [140/312]  eta: 0:01:27  lr: 0.001490  min_lr: 0.001490  loss: 4.6630 (4.3567)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [7]  [150/312]  eta: 0:01:21  lr: 0.001496  min_lr: 0.001496  loss: 4.4774 (4.3507)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0003  max mem: 42573
Epoch: [7]  [160/312]  eta: 0:01:16  lr: 0.001503  min_lr: 0.001503  loss: 4.1755 (4.3426)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0003  max mem: 42573
Epoch: [7]  [170/312]  eta: 0:01:10  lr: 0.001509  min_lr: 0.001509  loss: 4.5453 (4.3543)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [7]  [180/312]  eta: 0:01:05  lr: 0.001516  min_lr: 0.001516  loss: 4.5453 (4.3515)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [7]  [190/312]  eta: 0:00:59  lr: 0.001522  min_lr: 0.001522  loss: 4.1729 (4.3434)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [7]  [200/312]  eta: 0:00:54  lr: 0.001528  min_lr: 0.001528  loss: 4.1729 (4.3446)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0003  max mem: 42573
Epoch: [7]  [210/312]  eta: 0:00:49  lr: 0.001535  min_lr: 0.001535  loss: 4.5013 (4.3456)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0004  max mem: 42573
Epoch: [7]  [220/312]  eta: 0:00:44  lr: 0.001541  min_lr: 0.001541  loss: 4.5342 (4.3507)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0004  max mem: 42573
Epoch: [7]  [230/312]  eta: 0:00:39  lr: 0.001548  min_lr: 0.001548  loss: 4.3424 (4.3424)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [7]  [240/312]  eta: 0:00:34  lr: 0.001554  min_lr: 0.001554  loss: 4.5034 (4.3503)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [7]  [250/312]  eta: 0:00:29  lr: 0.001561  min_lr: 0.001561  loss: 4.5665 (4.3443)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [7]  [260/312]  eta: 0:00:24  lr: 0.001567  min_lr: 0.001567  loss: 4.2705 (4.3452)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0003  max mem: 42573
Epoch: [7]  [270/312]  eta: 0:00:19  lr: 0.001573  min_lr: 0.001573  loss: 4.5305 (4.3498)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0003  max mem: 42573
Epoch: [7]  [280/312]  eta: 0:00:15  lr: 0.001580  min_lr: 0.001580  loss: 4.3418 (4.3433)  weight_decay: 0.0500 (0.0500)  time: 0.4348  data: 0.0009  max mem: 42573
Epoch: [7]  [290/312]  eta: 0:00:10  lr: 0.001586  min_lr: 0.001586  loss: 4.2127 (4.3360)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0008  max mem: 42573
Epoch: [7]  [300/312]  eta: 0:00:05  lr: 0.001593  min_lr: 0.001593  loss: 4.0952 (4.3306)  weight_decay: 0.0500 (0.0500)  time: 0.4324  data: 0.0001  max mem: 42573
Epoch: [7]  [310/312]  eta: 0:00:00  lr: 0.001599  min_lr: 0.001599  loss: 4.1608 (4.3243)  weight_decay: 0.0500 (0.0500)  time: 0.4324  data: 0.0001  max mem: 42573
Epoch: [7]  [311/312]  eta: 0:00:00  lr: 0.001600  min_lr: 0.001600  loss: 4.1608 (4.3215)  weight_decay: 0.0500 (0.0500)  time: 0.4324  data: 0.0001  max mem: 42573
Epoch: [7] Total time: 0:02:27 (0.4719 s / it)
Averaged stats: lr: 0.001600  min_lr: 0.001600  loss: 4.1608 (4.3468)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:00:39  loss: 2.0207 (2.0207)  acc1: 55.4688 (55.4688)  acc5: 77.3438 (77.3438)  time: 4.3964  data: 4.2875  max mem: 42573
Test:  [8/9]  eta: 0:00:00  loss: 2.5666 (2.3448)  acc1: 44.2708 (46.4960)  acc5: 69.2708 (71.0400)  time: 0.5704  data: 0.4829  max mem: 42573
Test: Total time: 0:00:05 (0.5783 s / it)
* Acc@1 46.850 Acc@5 72.072 loss 2.331
Accuracy of the model on the 50000 test images: 46.9%
Max accuracy: 46.85%
Epoch: [8]  [  0/312]  eta: 0:52:31  lr: 0.001600  min_lr: 0.001600  loss: 4.9789 (4.9789)  weight_decay: 0.0500 (0.0500)  time: 10.1005  data: 7.9024  max mem: 42573
Epoch: [8]  [ 10/312]  eta: 0:07:26  lr: 0.001607  min_lr: 0.001607  loss: 4.5344 (4.4369)  weight_decay: 0.0500 (0.0500)  time: 1.4793  data: 0.7845  max mem: 42573
Epoch: [8]  [ 20/312]  eta: 0:04:47  lr: 0.001613  min_lr: 0.001613  loss: 4.3700 (4.3019)  weight_decay: 0.0500 (0.0500)  time: 0.5299  data: 0.0365  max mem: 42573
Epoch: [8]  [ 30/312]  eta: 0:03:47  lr: 0.001619  min_lr: 0.001619  loss: 4.1856 (4.2606)  weight_decay: 0.0500 (0.0500)  time: 0.4381  data: 0.0003  max mem: 42573
Epoch: [8]  [ 40/312]  eta: 0:03:14  lr: 0.001626  min_lr: 0.001626  loss: 4.3506 (4.2873)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [8]  [ 50/312]  eta: 0:02:53  lr: 0.001632  min_lr: 0.001632  loss: 3.9816 (4.2142)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0004  max mem: 42573
Epoch: [8]  [ 60/312]  eta: 0:02:37  lr: 0.001639  min_lr: 0.001639  loss: 3.8961 (4.1778)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [8]  [ 70/312]  eta: 0:02:24  lr: 0.001645  min_lr: 0.001645  loss: 4.1362 (4.1775)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [8]  [ 80/312]  eta: 0:02:14  lr: 0.001652  min_lr: 0.001652  loss: 4.1362 (4.1548)  weight_decay: 0.0500 (0.0500)  time: 0.4378  data: 0.0004  max mem: 42573
Epoch: [8]  [ 90/312]  eta: 0:02:04  lr: 0.001658  min_lr: 0.001658  loss: 3.9992 (4.1563)  weight_decay: 0.0500 (0.0500)  time: 0.4378  data: 0.0004  max mem: 42573
Epoch: [8]  [100/312]  eta: 0:01:56  lr: 0.001664  min_lr: 0.001664  loss: 3.9992 (4.1438)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0004  max mem: 42573
Epoch: [8]  [110/312]  eta: 0:01:48  lr: 0.001671  min_lr: 0.001671  loss: 4.0783 (4.1423)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0004  max mem: 42573
Epoch: [8]  [120/312]  eta: 0:01:41  lr: 0.001677  min_lr: 0.001677  loss: 4.2006 (4.1403)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [8]  [130/312]  eta: 0:01:35  lr: 0.001684  min_lr: 0.001684  loss: 4.2203 (4.1406)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [8]  [140/312]  eta: 0:01:28  lr: 0.001690  min_lr: 0.001690  loss: 4.3330 (4.1611)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [8]  [150/312]  eta: 0:01:22  lr: 0.001696  min_lr: 0.001696  loss: 4.3676 (4.1617)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [8]  [160/312]  eta: 0:01:16  lr: 0.001703  min_lr: 0.001703  loss: 4.4544 (4.1766)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [8]  [170/312]  eta: 0:01:11  lr: 0.001709  min_lr: 0.001709  loss: 4.5011 (4.1836)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [8]  [180/312]  eta: 0:01:05  lr: 0.001716  min_lr: 0.001716  loss: 4.1935 (4.1787)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [8]  [190/312]  eta: 0:01:00  lr: 0.001722  min_lr: 0.001722  loss: 3.8804 (4.1688)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [8]  [200/312]  eta: 0:00:55  lr: 0.001728  min_lr: 0.001728  loss: 4.2167 (4.1789)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0003  max mem: 42573
Epoch: [8]  [210/312]  eta: 0:00:49  lr: 0.001735  min_lr: 0.001735  loss: 4.3027 (4.1687)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0003  max mem: 42573
Epoch: [8]  [220/312]  eta: 0:00:44  lr: 0.001741  min_lr: 0.001741  loss: 4.3270 (4.1817)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0003  max mem: 42573
Epoch: [8]  [230/312]  eta: 0:00:39  lr: 0.001748  min_lr: 0.001748  loss: 4.3847 (4.1777)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [8]  [240/312]  eta: 0:00:34  lr: 0.001754  min_lr: 0.001754  loss: 4.1538 (4.1737)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [8]  [250/312]  eta: 0:00:29  lr: 0.001761  min_lr: 0.001761  loss: 4.2538 (4.1736)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [8]  [260/312]  eta: 0:00:24  lr: 0.001767  min_lr: 0.001767  loss: 4.3173 (4.1798)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [8]  [270/312]  eta: 0:00:20  lr: 0.001773  min_lr: 0.001773  loss: 4.3690 (4.1851)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [8]  [280/312]  eta: 0:00:15  lr: 0.001780  min_lr: 0.001780  loss: 4.3556 (4.1853)  weight_decay: 0.0500 (0.0500)  time: 0.4346  data: 0.0010  max mem: 42573
Epoch: [8]  [290/312]  eta: 0:00:10  lr: 0.001786  min_lr: 0.001786  loss: 4.3556 (4.1870)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0009  max mem: 42573
Epoch: [8]  [300/312]  eta: 0:00:05  lr: 0.001793  min_lr: 0.001793  loss: 4.3439 (4.1826)  weight_decay: 0.0500 (0.0500)  time: 0.4325  data: 0.0001  max mem: 42573
Epoch: [8]  [310/312]  eta: 0:00:00  lr: 0.001799  min_lr: 0.001799  loss: 4.1161 (4.1813)  weight_decay: 0.0500 (0.0500)  time: 0.4324  data: 0.0001  max mem: 42573
Epoch: [8]  [311/312]  eta: 0:00:00  lr: 0.001800  min_lr: 0.001800  loss: 4.0404 (4.1790)  weight_decay: 0.0500 (0.0500)  time: 0.4324  data: 0.0001  max mem: 42573
Epoch: [8] Total time: 0:02:27 (0.4740 s / it)
Averaged stats: lr: 0.001800  min_lr: 0.001800  loss: 4.0404 (4.1806)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:00:39  loss: 1.8648 (1.8648)  acc1: 59.6354 (59.6354)  acc5: 79.4271 (79.4271)  time: 4.3768  data: 4.2673  max mem: 42573
Test:  [8/9]  eta: 0:00:00  loss: 2.2599 (2.1504)  acc1: 50.2604 (50.8480)  acc5: 73.1771 (74.4960)  time: 0.5629  data: 0.4742  max mem: 42573
Test: Total time: 0:00:05 (0.5715 s / it)
* Acc@1 50.180 Acc@5 74.796 loss 2.168
Accuracy of the model on the 50000 test images: 50.2%
Max accuracy: 50.18%
Epoch: [9]  [  0/312]  eta: 0:48:52  lr: 0.001800  min_lr: 0.001800  loss: 4.5477 (4.5477)  weight_decay: 0.0500 (0.0500)  time: 9.4002  data: 7.4029  max mem: 42573
Epoch: [9]  [ 10/312]  eta: 0:06:59  lr: 0.001807  min_lr: 0.001807  loss: 4.5669 (4.3942)  weight_decay: 0.0500 (0.0500)  time: 1.3897  data: 0.6734  max mem: 42573
Epoch: [9]  [ 20/312]  eta: 0:04:32  lr: 0.001813  min_lr: 0.001813  loss: 4.2562 (4.1801)  weight_decay: 0.0500 (0.0500)  time: 0.5111  data: 0.0004  max mem: 42573
Epoch: [9]  [ 30/312]  eta: 0:03:37  lr: 0.001820  min_lr: 0.001820  loss: 4.0895 (4.1530)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [9]  [ 40/312]  eta: 0:03:07  lr: 0.001826  min_lr: 0.001826  loss: 3.9291 (4.0588)  weight_decay: 0.0500 (0.0500)  time: 0.4332  data: 0.0004  max mem: 42573
Epoch: [9]  [ 50/312]  eta: 0:02:48  lr: 0.001832  min_lr: 0.001832  loss: 3.8723 (4.0200)  weight_decay: 0.0500 (0.0500)  time: 0.4384  data: 0.0004  max mem: 42573
Epoch: [9]  [ 60/312]  eta: 0:02:33  lr: 0.001839  min_lr: 0.001839  loss: 3.8615 (4.0180)  weight_decay: 0.0500 (0.0500)  time: 0.4387  data: 0.0004  max mem: 42573
Epoch: [9]  [ 70/312]  eta: 0:02:21  lr: 0.001845  min_lr: 0.001845  loss: 3.8615 (4.0089)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0004  max mem: 42573
Epoch: [9]  [ 80/312]  eta: 0:02:11  lr: 0.001852  min_lr: 0.001852  loss: 4.1306 (4.0204)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0004  max mem: 42573
Epoch: [9]  [ 90/312]  eta: 0:02:02  lr: 0.001858  min_lr: 0.001858  loss: 4.2460 (4.0366)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [9]  [100/312]  eta: 0:01:54  lr: 0.001864  min_lr: 0.001864  loss: 4.0892 (4.0298)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [9]  [110/312]  eta: 0:01:46  lr: 0.001871  min_lr: 0.001871  loss: 3.8243 (4.0294)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0003  max mem: 42573
Epoch: [9]  [120/312]  eta: 0:01:40  lr: 0.001877  min_lr: 0.001877  loss: 4.1902 (4.0319)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0003  max mem: 42573
Epoch: [9]  [130/312]  eta: 0:01:33  lr: 0.001884  min_lr: 0.001884  loss: 4.1902 (4.0348)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [9]  [140/312]  eta: 0:01:27  lr: 0.001890  min_lr: 0.001890  loss: 4.2777 (4.0544)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [9]  [150/312]  eta: 0:01:21  lr: 0.001896  min_lr: 0.001896  loss: 4.2256 (4.0574)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [9]  [160/312]  eta: 0:01:15  lr: 0.001903  min_lr: 0.001903  loss: 4.1477 (4.0552)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [9]  [170/312]  eta: 0:01:10  lr: 0.001909  min_lr: 0.001909  loss: 4.0599 (4.0572)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [9]  [180/312]  eta: 0:01:04  lr: 0.001916  min_lr: 0.001916  loss: 3.9538 (4.0495)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [9]  [190/312]  eta: 0:00:59  lr: 0.001922  min_lr: 0.001922  loss: 3.9538 (4.0467)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [9]  [200/312]  eta: 0:00:54  lr: 0.001929  min_lr: 0.001929  loss: 4.1952 (4.0520)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [9]  [210/312]  eta: 0:00:49  lr: 0.001935  min_lr: 0.001935  loss: 4.1171 (4.0437)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [9]  [220/312]  eta: 0:00:44  lr: 0.001941  min_lr: 0.001941  loss: 4.2288 (4.0478)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [9]  [230/312]  eta: 0:00:39  lr: 0.001948  min_lr: 0.001948  loss: 4.3634 (4.0479)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [9]  [240/312]  eta: 0:00:34  lr: 0.001954  min_lr: 0.001954  loss: 3.7779 (4.0428)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0003  max mem: 42573
Epoch: [9]  [250/312]  eta: 0:00:29  lr: 0.001961  min_lr: 0.001961  loss: 4.0215 (4.0436)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0003  max mem: 42573
Epoch: [9]  [260/312]  eta: 0:00:24  lr: 0.001967  min_lr: 0.001967  loss: 4.1397 (4.0459)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [9]  [270/312]  eta: 0:00:19  lr: 0.001973  min_lr: 0.001973  loss: 4.2280 (4.0537)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [9]  [280/312]  eta: 0:00:15  lr: 0.001980  min_lr: 0.001980  loss: 3.9557 (4.0400)  weight_decay: 0.0500 (0.0500)  time: 0.4341  data: 0.0010  max mem: 42573
Epoch: [9]  [290/312]  eta: 0:00:10  lr: 0.001986  min_lr: 0.001986  loss: 3.6185 (4.0370)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0008  max mem: 42573
Epoch: [9]  [300/312]  eta: 0:00:05  lr: 0.001993  min_lr: 0.001993  loss: 4.0543 (4.0356)  weight_decay: 0.0500 (0.0500)  time: 0.4324  data: 0.0001  max mem: 42573
Epoch: [9]  [310/312]  eta: 0:00:00  lr: 0.001999  min_lr: 0.001999  loss: 4.0462 (4.0362)  weight_decay: 0.0500 (0.0500)  time: 0.4325  data: 0.0001  max mem: 42573
Epoch: [9]  [311/312]  eta: 0:00:00  lr: 0.002000  min_lr: 0.002000  loss: 4.0462 (4.0350)  weight_decay: 0.0500 (0.0500)  time: 0.4325  data: 0.0001  max mem: 42573
Epoch: [9] Total time: 0:02:26 (0.4707 s / it)
Averaged stats: lr: 0.002000  min_lr: 0.002000  loss: 4.0462 (4.0432)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:00:42  loss: 1.7847 (1.7847)  acc1: 61.1979 (61.1979)  acc5: 78.9062 (78.9062)  time: 4.7352  data: 4.6200  max mem: 42573
Test:  [8/9]  eta: 0:00:00  loss: 2.3120 (2.0876)  acc1: 48.9583 (50.4640)  acc5: 75.2604 (75.5840)  time: 0.6015  data: 0.5134  max mem: 42573
Test: Total time: 0:00:05 (0.6098 s / it)
* Acc@1 51.492 Acc@5 76.186 loss 2.088
Accuracy of the model on the 50000 test images: 51.5%
Max accuracy: 51.49%
Epoch: [10]  [  0/312]  eta: 0:52:48  lr: 0.002000  min_lr: 0.002000  loss: 3.6862 (3.6862)  weight_decay: 0.0500 (0.0500)  time: 10.1539  data: 8.7896  max mem: 42573
Epoch: [10]  [ 10/312]  eta: 0:07:26  lr: 0.002007  min_lr: 0.002007  loss: 3.7372 (3.9515)  weight_decay: 0.0500 (0.0500)  time: 1.4771  data: 0.7994  max mem: 42573
Epoch: [10]  [ 20/312]  eta: 0:04:46  lr: 0.002013  min_lr: 0.002013  loss: 3.9592 (4.0301)  weight_decay: 0.0500 (0.0500)  time: 0.5214  data: 0.0004  max mem: 42573
Epoch: [10]  [ 30/312]  eta: 0:03:46  lr: 0.002020  min_lr: 0.002020  loss: 4.2410 (4.0778)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0003  max mem: 42573
Epoch: [10]  [ 40/312]  eta: 0:03:14  lr: 0.002026  min_lr: 0.002026  loss: 4.2110 (4.0685)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0003  max mem: 42573
Epoch: [10]  [ 50/312]  eta: 0:02:52  lr: 0.002032  min_lr: 0.002032  loss: 3.8924 (4.0297)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [10]  [ 60/312]  eta: 0:02:36  lr: 0.002039  min_lr: 0.002039  loss: 4.2929 (4.0738)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [10]  [ 70/312]  eta: 0:02:24  lr: 0.002045  min_lr: 0.002045  loss: 4.3045 (4.0925)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [10]  [ 80/312]  eta: 0:02:13  lr: 0.002052  min_lr: 0.002052  loss: 4.1904 (4.0769)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [10]  [ 90/312]  eta: 0:02:04  lr: 0.002058  min_lr: 0.002058  loss: 4.0099 (4.0680)  weight_decay: 0.0500 (0.0500)  time: 0.4342  data: 0.0004  max mem: 42573
Epoch: [10]  [100/312]  eta: 0:01:56  lr: 0.002064  min_lr: 0.002064  loss: 3.9700 (4.0444)  weight_decay: 0.0500 (0.0500)  time: 0.4344  data: 0.0004  max mem: 42573
Epoch: [10]  [110/312]  eta: 0:01:48  lr: 0.002071  min_lr: 0.002071  loss: 4.0082 (4.0413)  weight_decay: 0.0500 (0.0500)  time: 0.4342  data: 0.0004  max mem: 42573
Epoch: [10]  [120/312]  eta: 0:01:41  lr: 0.002077  min_lr: 0.002077  loss: 4.0082 (4.0286)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0004  max mem: 42573
Epoch: [10]  [130/312]  eta: 0:01:34  lr: 0.002084  min_lr: 0.002084  loss: 4.0743 (4.0233)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [10]  [140/312]  eta: 0:01:28  lr: 0.002090  min_lr: 0.002090  loss: 4.0992 (4.0197)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0004  max mem: 42573
Epoch: [10]  [150/312]  eta: 0:01:22  lr: 0.002096  min_lr: 0.002096  loss: 4.2095 (4.0259)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [10]  [160/312]  eta: 0:01:16  lr: 0.002103  min_lr: 0.002103  loss: 4.2305 (4.0190)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [10]  [170/312]  eta: 0:01:11  lr: 0.002109  min_lr: 0.002109  loss: 4.0465 (4.0192)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [10]  [180/312]  eta: 0:01:05  lr: 0.002116  min_lr: 0.002116  loss: 4.1871 (4.0217)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [10]  [190/312]  eta: 0:01:00  lr: 0.002122  min_lr: 0.002122  loss: 4.1720 (4.0212)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0003  max mem: 42573
Epoch: [10]  [200/312]  eta: 0:00:54  lr: 0.002129  min_lr: 0.002129  loss: 4.0982 (4.0185)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0003  max mem: 42573
Epoch: [10]  [210/312]  eta: 0:00:49  lr: 0.002135  min_lr: 0.002135  loss: 4.2336 (4.0318)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0003  max mem: 42573
Epoch: [10]  [220/312]  eta: 0:00:44  lr: 0.002141  min_lr: 0.002141  loss: 4.2115 (4.0250)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [10]  [230/312]  eta: 0:00:39  lr: 0.002148  min_lr: 0.002148  loss: 3.9378 (4.0228)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [10]  [240/312]  eta: 0:00:34  lr: 0.002154  min_lr: 0.002154  loss: 3.8831 (4.0162)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [10]  [250/312]  eta: 0:00:29  lr: 0.002161  min_lr: 0.002161  loss: 3.8790 (4.0085)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [10]  [260/312]  eta: 0:00:24  lr: 0.002167  min_lr: 0.002167  loss: 3.7926 (3.9988)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [10]  [270/312]  eta: 0:00:19  lr: 0.002173  min_lr: 0.002173  loss: 3.9567 (3.9985)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [10]  [280/312]  eta: 0:00:15  lr: 0.002180  min_lr: 0.002180  loss: 4.1120 (3.9953)  weight_decay: 0.0500 (0.0500)  time: 0.4342  data: 0.0009  max mem: 42573
Epoch: [10]  [290/312]  eta: 0:00:10  lr: 0.002186  min_lr: 0.002186  loss: 3.7199 (3.9830)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0008  max mem: 42573
Epoch: [10]  [300/312]  eta: 0:00:05  lr: 0.002193  min_lr: 0.002193  loss: 3.5797 (3.9778)  weight_decay: 0.0500 (0.0500)  time: 0.4324  data: 0.0001  max mem: 42573
Epoch: [10]  [310/312]  eta: 0:00:00  lr: 0.002199  min_lr: 0.002199  loss: 4.0125 (3.9775)  weight_decay: 0.0500 (0.0500)  time: 0.4323  data: 0.0001  max mem: 42573
Epoch: [10]  [311/312]  eta: 0:00:00  lr: 0.002200  min_lr: 0.002200  loss: 4.0125 (3.9783)  weight_decay: 0.0500 (0.0500)  time: 0.4323  data: 0.0001  max mem: 42573
Epoch: [10] Total time: 0:02:27 (0.4736 s / it)
Averaged stats: lr: 0.002200  min_lr: 0.002200  loss: 4.0125 (3.9249)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:00:41  loss: 1.6106 (1.6106)  acc1: 62.7604 (62.7604)  acc5: 83.0729 (83.0729)  time: 4.5558  data: 4.4400  max mem: 42573
Test:  [8/9]  eta: 0:00:00  loss: 2.1049 (1.9389)  acc1: 51.0417 (53.4720)  acc5: 78.9062 (78.2720)  time: 0.5816  data: 0.4934  max mem: 42573
Test: Total time: 0:00:05 (0.5884 s / it)
* Acc@1 54.706 Acc@5 78.630 loss 1.932
Accuracy of the model on the 50000 test images: 54.7%
Max accuracy: 54.71%
Epoch: [11]  [  0/312]  eta: 0:49:07  lr: 0.002200  min_lr: 0.002200  loss: 4.2030 (4.2030)  weight_decay: 0.0500 (0.0500)  time: 9.4472  data: 7.3430  max mem: 42573
Epoch: [11]  [ 10/312]  eta: 0:07:30  lr: 0.002207  min_lr: 0.002207  loss: 3.9888 (3.8995)  weight_decay: 0.0500 (0.0500)  time: 1.4910  data: 0.6858  max mem: 42573
Epoch: [11]  [ 20/312]  eta: 0:04:48  lr: 0.002213  min_lr: 0.002213  loss: 3.9214 (3.8737)  weight_decay: 0.0500 (0.0500)  time: 0.5643  data: 0.0102  max mem: 42573
Epoch: [11]  [ 30/312]  eta: 0:03:48  lr: 0.002220  min_lr: 0.002220  loss: 3.8405 (3.8278)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [11]  [ 40/312]  eta: 0:03:15  lr: 0.002226  min_lr: 0.002226  loss: 3.5649 (3.7859)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0003  max mem: 42573
Epoch: [11]  [ 50/312]  eta: 0:02:53  lr: 0.002232  min_lr: 0.002232  loss: 3.3929 (3.7158)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [11]  [ 60/312]  eta: 0:02:37  lr: 0.002239  min_lr: 0.002239  loss: 3.3679 (3.7138)  weight_decay: 0.0500 (0.0500)  time: 0.4341  data: 0.0004  max mem: 42573
Epoch: [11]  [ 70/312]  eta: 0:02:24  lr: 0.002245  min_lr: 0.002245  loss: 3.6336 (3.7118)  weight_decay: 0.0500 (0.0500)  time: 0.4342  data: 0.0003  max mem: 42573
Epoch: [11]  [ 80/312]  eta: 0:02:13  lr: 0.002252  min_lr: 0.002252  loss: 3.5910 (3.7011)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [11]  [ 90/312]  eta: 0:02:04  lr: 0.002258  min_lr: 0.002258  loss: 3.9254 (3.7348)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [11]  [100/312]  eta: 0:01:56  lr: 0.002264  min_lr: 0.002264  loss: 3.8975 (3.7270)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [11]  [110/312]  eta: 0:01:48  lr: 0.002271  min_lr: 0.002271  loss: 3.8314 (3.7445)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0003  max mem: 42573
Epoch: [11]  [120/312]  eta: 0:01:41  lr: 0.002277  min_lr: 0.002277  loss: 3.9358 (3.7583)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0003  max mem: 42573
Epoch: [11]  [130/312]  eta: 0:01:35  lr: 0.002284  min_lr: 0.002284  loss: 3.9628 (3.7744)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [11]  [140/312]  eta: 0:01:28  lr: 0.002290  min_lr: 0.002290  loss: 3.8693 (3.7659)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [11]  [150/312]  eta: 0:01:22  lr: 0.002297  min_lr: 0.002297  loss: 3.5628 (3.7657)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [11]  [160/312]  eta: 0:01:16  lr: 0.002303  min_lr: 0.002303  loss: 3.8331 (3.7710)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [11]  [170/312]  eta: 0:01:11  lr: 0.002309  min_lr: 0.002309  loss: 3.9983 (3.7847)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [11]  [180/312]  eta: 0:01:05  lr: 0.002316  min_lr: 0.002316  loss: 3.8562 (3.7760)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0005  max mem: 42573
Epoch: [11]  [190/312]  eta: 0:01:00  lr: 0.002322  min_lr: 0.002322  loss: 3.7935 (3.7787)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [11]  [200/312]  eta: 0:00:55  lr: 0.002329  min_lr: 0.002329  loss: 3.7935 (3.7797)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [11]  [210/312]  eta: 0:00:49  lr: 0.002335  min_lr: 0.002335  loss: 3.8640 (3.7865)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [11]  [220/312]  eta: 0:00:44  lr: 0.002341  min_lr: 0.002341  loss: 3.8498 (3.7802)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [11]  [230/312]  eta: 0:00:39  lr: 0.002348  min_lr: 0.002348  loss: 3.8612 (3.7918)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [11]  [240/312]  eta: 0:00:34  lr: 0.002354  min_lr: 0.002354  loss: 4.0495 (3.7889)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [11]  [250/312]  eta: 0:00:29  lr: 0.002361  min_lr: 0.002361  loss: 3.7488 (3.7883)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [11]  [260/312]  eta: 0:00:24  lr: 0.002367  min_lr: 0.002367  loss: 3.7297 (3.7810)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [11]  [270/312]  eta: 0:00:20  lr: 0.002373  min_lr: 0.002373  loss: 3.8544 (3.7823)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [11]  [280/312]  eta: 0:00:15  lr: 0.002380  min_lr: 0.002380  loss: 3.7118 (3.7723)  weight_decay: 0.0500 (0.0500)  time: 0.4343  data: 0.0009  max mem: 42573
Epoch: [11]  [290/312]  eta: 0:00:10  lr: 0.002386  min_lr: 0.002386  loss: 3.9265 (3.7799)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0008  max mem: 42573
Epoch: [11]  [300/312]  eta: 0:00:05  lr: 0.002393  min_lr: 0.002393  loss: 4.0003 (3.7755)  weight_decay: 0.0500 (0.0500)  time: 0.4324  data: 0.0001  max mem: 42573
Epoch: [11]  [310/312]  eta: 0:00:00  lr: 0.002399  min_lr: 0.002399  loss: 3.7808 (3.7762)  weight_decay: 0.0500 (0.0500)  time: 0.4323  data: 0.0001  max mem: 42573
Epoch: [11]  [311/312]  eta: 0:00:00  lr: 0.002400  min_lr: 0.002400  loss: 3.7808 (3.7774)  weight_decay: 0.0500 (0.0500)  time: 0.4324  data: 0.0001  max mem: 42573
Epoch: [11] Total time: 0:02:27 (0.4743 s / it)
Averaged stats: lr: 0.002400  min_lr: 0.002400  loss: 3.7808 (3.8169)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:00:40  loss: 1.5892 (1.5892)  acc1: 66.1458 (66.1458)  acc5: 83.3333 (83.3333)  time: 4.4476  data: 4.3390  max mem: 42573
Test:  [8/9]  eta: 0:00:00  loss: 2.0752 (1.9069)  acc1: 53.9062 (54.9440)  acc5: 78.1250 (79.1680)  time: 0.5706  data: 0.4822  max mem: 42573
Test: Total time: 0:00:05 (0.5789 s / it)
* Acc@1 55.864 Acc@5 79.444 loss 1.895
Accuracy of the model on the 50000 test images: 55.9%
Max accuracy: 55.86%
Epoch: [12]  [  0/312]  eta: 0:49:51  lr: 0.002400  min_lr: 0.002400  loss: 3.9713 (3.9713)  weight_decay: 0.0500 (0.0500)  time: 9.5868  data: 7.8224  max mem: 42573
Epoch: [12]  [ 10/312]  eta: 0:07:16  lr: 0.002407  min_lr: 0.002407  loss: 3.7044 (3.7293)  weight_decay: 0.0500 (0.0500)  time: 1.4444  data: 0.7115  max mem: 42573
Epoch: [12]  [ 20/312]  eta: 0:04:41  lr: 0.002413  min_lr: 0.002413  loss: 3.6242 (3.6047)  weight_decay: 0.0500 (0.0500)  time: 0.5316  data: 0.0004  max mem: 42573
Epoch: [12]  [ 30/312]  eta: 0:03:43  lr: 0.002420  min_lr: 0.002420  loss: 3.5442 (3.6388)  weight_decay: 0.0500 (0.0500)  time: 0.4332  data: 0.0003  max mem: 42573
Epoch: [12]  [ 40/312]  eta: 0:03:11  lr: 0.002426  min_lr: 0.002426  loss: 3.8245 (3.6531)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0003  max mem: 42573
Epoch: [12]  [ 50/312]  eta: 0:02:50  lr: 0.002432  min_lr: 0.002432  loss: 3.8636 (3.6829)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [12]  [ 60/312]  eta: 0:02:35  lr: 0.002439  min_lr: 0.002439  loss: 3.9370 (3.7119)  weight_decay: 0.0500 (0.0500)  time: 0.4343  data: 0.0004  max mem: 42573
Epoch: [12]  [ 70/312]  eta: 0:02:22  lr: 0.002445  min_lr: 0.002445  loss: 3.8080 (3.6955)  weight_decay: 0.0500 (0.0500)  time: 0.4357  data: 0.0004  max mem: 42573
Epoch: [12]  [ 80/312]  eta: 0:02:12  lr: 0.002452  min_lr: 0.002452  loss: 3.8080 (3.7103)  weight_decay: 0.0500 (0.0500)  time: 0.4354  data: 0.0004  max mem: 42573
Epoch: [12]  [ 90/312]  eta: 0:02:03  lr: 0.002458  min_lr: 0.002458  loss: 3.9933 (3.7172)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0004  max mem: 42573
Epoch: [12]  [100/312]  eta: 0:01:55  lr: 0.002464  min_lr: 0.002464  loss: 3.9933 (3.7258)  weight_decay: 0.0500 (0.0500)  time: 0.4341  data: 0.0004  max mem: 42573
Epoch: [12]  [110/312]  eta: 0:01:47  lr: 0.002471  min_lr: 0.002471  loss: 3.9400 (3.7348)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0004  max mem: 42573
Epoch: [12]  [120/312]  eta: 0:01:40  lr: 0.002477  min_lr: 0.002477  loss: 4.0476 (3.7665)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [12]  [130/312]  eta: 0:01:34  lr: 0.002484  min_lr: 0.002484  loss: 4.0271 (3.7634)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [12]  [140/312]  eta: 0:01:28  lr: 0.002490  min_lr: 0.002490  loss: 3.6005 (3.7649)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [12]  [150/312]  eta: 0:01:22  lr: 0.002497  min_lr: 0.002497  loss: 3.6005 (3.7556)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [12]  [160/312]  eta: 0:01:16  lr: 0.002503  min_lr: 0.002503  loss: 3.5116 (3.7512)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [12]  [170/312]  eta: 0:01:10  lr: 0.002509  min_lr: 0.002509  loss: 3.6402 (3.7532)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0003  max mem: 42573
Epoch: [12]  [180/312]  eta: 0:01:05  lr: 0.002516  min_lr: 0.002516  loss: 3.8625 (3.7562)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [12]  [190/312]  eta: 0:01:00  lr: 0.002522  min_lr: 0.002522  loss: 4.0721 (3.7692)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [12]  [200/312]  eta: 0:00:54  lr: 0.002529  min_lr: 0.002529  loss: 3.9395 (3.7702)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [12]  [210/312]  eta: 0:00:49  lr: 0.002535  min_lr: 0.002535  loss: 3.6040 (3.7551)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [12]  [220/312]  eta: 0:00:44  lr: 0.002541  min_lr: 0.002541  loss: 3.3131 (3.7447)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [12]  [230/312]  eta: 0:00:39  lr: 0.002548  min_lr: 0.002548  loss: 3.7163 (3.7465)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [12]  [240/312]  eta: 0:00:34  lr: 0.002554  min_lr: 0.002554  loss: 3.9134 (3.7488)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [12]  [250/312]  eta: 0:00:29  lr: 0.002561  min_lr: 0.002561  loss: 3.9134 (3.7478)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [12]  [260/312]  eta: 0:00:24  lr: 0.002567  min_lr: 0.002567  loss: 3.9172 (3.7493)  weight_decay: 0.0500 (0.0500)  time: 0.4355  data: 0.0004  max mem: 42573
Epoch: [12]  [270/312]  eta: 0:00:19  lr: 0.002573  min_lr: 0.002573  loss: 4.0457 (3.7550)  weight_decay: 0.0500 (0.0500)  time: 0.4356  data: 0.0004  max mem: 42573
Epoch: [12]  [280/312]  eta: 0:00:15  lr: 0.002580  min_lr: 0.002580  loss: 3.7179 (3.7446)  weight_decay: 0.0500 (0.0500)  time: 0.4352  data: 0.0009  max mem: 42573
Epoch: [12]  [290/312]  eta: 0:00:10  lr: 0.002586  min_lr: 0.002586  loss: 3.7179 (3.7500)  weight_decay: 0.0500 (0.0500)  time: 0.4345  data: 0.0008  max mem: 42573
Epoch: [12]  [300/312]  eta: 0:00:05  lr: 0.002593  min_lr: 0.002593  loss: 3.9168 (3.7484)  weight_decay: 0.0500 (0.0500)  time: 0.4325  data: 0.0001  max mem: 42573
Epoch: [12]  [310/312]  eta: 0:00:00  lr: 0.002599  min_lr: 0.002599  loss: 3.6137 (3.7419)  weight_decay: 0.0500 (0.0500)  time: 0.4324  data: 0.0001  max mem: 42573
Epoch: [12]  [311/312]  eta: 0:00:00  lr: 0.002600  min_lr: 0.002600  loss: 3.6137 (3.7413)  weight_decay: 0.0500 (0.0500)  time: 0.4323  data: 0.0001  max mem: 42573
Epoch: [12] Total time: 0:02:27 (0.4728 s / it)
Averaged stats: lr: 0.002600  min_lr: 0.002600  loss: 3.6137 (3.7385)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:00:42  loss: 1.4258 (1.4258)  acc1: 65.3646 (65.3646)  acc5: 86.1979 (86.1979)  time: 4.6813  data: 4.5724  max mem: 42573
Test:  [8/9]  eta: 0:00:00  loss: 1.8816 (1.7340)  acc1: 55.7292 (57.7280)  acc5: 79.9479 (81.1520)  time: 0.5969  data: 0.5081  max mem: 42573
Test: Total time: 0:00:05 (0.6041 s / it)
* Acc@1 58.412 Acc@5 81.454 loss 1.765
Accuracy of the model on the 50000 test images: 58.4%
Max accuracy: 58.41%
Epoch: [13]  [  0/312]  eta: 0:50:04  lr: 0.002600  min_lr: 0.002600  loss: 4.1928 (4.1928)  weight_decay: 0.0500 (0.0500)  time: 9.6292  data: 6.5109  max mem: 42573
Epoch: [13]  [ 10/312]  eta: 0:07:20  lr: 0.002607  min_lr: 0.002607  loss: 3.6049 (3.6615)  weight_decay: 0.0500 (0.0500)  time: 1.4578  data: 0.6079  max mem: 42573
Epoch: [13]  [ 20/312]  eta: 0:04:43  lr: 0.002613  min_lr: 0.002613  loss: 3.6049 (3.6249)  weight_decay: 0.0500 (0.0500)  time: 0.5369  data: 0.0090  max mem: 42573
Epoch: [13]  [ 30/312]  eta: 0:03:44  lr: 0.002620  min_lr: 0.002620  loss: 3.7375 (3.6608)  weight_decay: 0.0500 (0.0500)  time: 0.4332  data: 0.0004  max mem: 42573
Epoch: [13]  [ 40/312]  eta: 0:03:12  lr: 0.002626  min_lr: 0.002626  loss: 3.4478 (3.5928)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [13]  [ 50/312]  eta: 0:02:51  lr: 0.002632  min_lr: 0.002632  loss: 3.5342 (3.6017)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [13]  [ 60/312]  eta: 0:02:35  lr: 0.002639  min_lr: 0.002639  loss: 3.6715 (3.6135)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [13]  [ 70/312]  eta: 0:02:23  lr: 0.002645  min_lr: 0.002645  loss: 3.5956 (3.6153)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [13]  [ 80/312]  eta: 0:02:12  lr: 0.002652  min_lr: 0.002652  loss: 3.6898 (3.6211)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [13]  [ 90/312]  eta: 0:02:03  lr: 0.002658  min_lr: 0.002658  loss: 3.5629 (3.6106)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0003  max mem: 42573
Epoch: [13]  [100/312]  eta: 0:01:55  lr: 0.002665  min_lr: 0.002665  loss: 3.5936 (3.6184)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [13]  [110/312]  eta: 0:01:48  lr: 0.002671  min_lr: 0.002671  loss: 3.5878 (3.6016)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [13]  [120/312]  eta: 0:01:41  lr: 0.002677  min_lr: 0.002677  loss: 3.5246 (3.6010)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [13]  [130/312]  eta: 0:01:34  lr: 0.002684  min_lr: 0.002684  loss: 3.8939 (3.6224)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [13]  [140/312]  eta: 0:01:28  lr: 0.002690  min_lr: 0.002690  loss: 3.9213 (3.6283)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [13]  [150/312]  eta: 0:01:22  lr: 0.002697  min_lr: 0.002697  loss: 3.8058 (3.6386)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [13]  [160/312]  eta: 0:01:16  lr: 0.002703  min_lr: 0.002703  loss: 3.8058 (3.6455)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [13]  [170/312]  eta: 0:01:10  lr: 0.002709  min_lr: 0.002709  loss: 3.6046 (3.6359)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [13]  [180/312]  eta: 0:01:05  lr: 0.002716  min_lr: 0.002716  loss: 3.7174 (3.6485)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [13]  [190/312]  eta: 0:01:00  lr: 0.002722  min_lr: 0.002722  loss: 3.7753 (3.6552)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [13]  [200/312]  eta: 0:00:54  lr: 0.002729  min_lr: 0.002729  loss: 3.7920 (3.6672)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [13]  [210/312]  eta: 0:00:49  lr: 0.002735  min_lr: 0.002735  loss: 3.7119 (3.6641)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [13]  [220/312]  eta: 0:00:44  lr: 0.002741  min_lr: 0.002741  loss: 3.6614 (3.6704)  weight_decay: 0.0500 (0.0500)  time: 0.4404  data: 0.0003  max mem: 42573
Epoch: [13]  [230/312]  eta: 0:00:39  lr: 0.002748  min_lr: 0.002748  loss: 3.7105 (3.6681)  weight_decay: 0.0500 (0.0500)  time: 0.4403  data: 0.0004  max mem: 42573
Epoch: [13]  [240/312]  eta: 0:00:34  lr: 0.002754  min_lr: 0.002754  loss: 3.8591 (3.6709)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [13]  [250/312]  eta: 0:00:29  lr: 0.002761  min_lr: 0.002761  loss: 3.8836 (3.6738)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [13]  [260/312]  eta: 0:00:24  lr: 0.002767  min_lr: 0.002767  loss: 3.8761 (3.6739)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [13]  [270/312]  eta: 0:00:19  lr: 0.002774  min_lr: 0.002774  loss: 3.8761 (3.6748)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [13]  [280/312]  eta: 0:00:15  lr: 0.002780  min_lr: 0.002780  loss: 3.7201 (3.6682)  weight_decay: 0.0500 (0.0500)  time: 0.4345  data: 0.0009  max mem: 42573
Epoch: [13]  [290/312]  eta: 0:00:10  lr: 0.002786  min_lr: 0.002786  loss: 3.8749 (3.6754)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0008  max mem: 42573
Epoch: [13]  [300/312]  eta: 0:00:05  lr: 0.002793  min_lr: 0.002793  loss: 3.8749 (3.6777)  weight_decay: 0.0500 (0.0500)  time: 0.4325  data: 0.0001  max mem: 42573
Epoch: [13]  [310/312]  eta: 0:00:00  lr: 0.002799  min_lr: 0.002799  loss: 3.8645 (3.6828)  weight_decay: 0.0500 (0.0500)  time: 0.4324  data: 0.0001  max mem: 42573
Epoch: [13]  [311/312]  eta: 0:00:00  lr: 0.002800  min_lr: 0.002800  loss: 3.8645 (3.6829)  weight_decay: 0.0500 (0.0500)  time: 0.4324  data: 0.0001  max mem: 42573
Epoch: [13] Total time: 0:02:27 (0.4731 s / it)
Averaged stats: lr: 0.002800  min_lr: 0.002800  loss: 3.8645 (3.6581)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:00:42  loss: 1.5152 (1.5152)  acc1: 65.1042 (65.1042)  acc5: 84.1146 (84.1146)  time: 4.7421  data: 4.6327  max mem: 42573
Test:  [8/9]  eta: 0:00:00  loss: 1.9373 (1.7624)  acc1: 55.9896 (57.9520)  acc5: 80.2083 (81.1200)  time: 0.6091  data: 0.5148  max mem: 42573
Test: Total time: 0:00:05 (0.6225 s / it)
* Acc@1 58.826 Acc@5 81.632 loss 1.743
Accuracy of the model on the 50000 test images: 58.8%
Max accuracy: 58.83%
Epoch: [14]  [  0/312]  eta: 0:50:14  lr: 0.002800  min_lr: 0.002800  loss: 3.8690 (3.8690)  weight_decay: 0.0500 (0.0500)  time: 9.6618  data: 7.2554  max mem: 42573
Epoch: [14]  [ 10/312]  eta: 0:07:23  lr: 0.002807  min_lr: 0.002807  loss: 3.5958 (3.4744)  weight_decay: 0.0500 (0.0500)  time: 1.4677  data: 0.7341  max mem: 42573
Epoch: [14]  [ 20/312]  eta: 0:04:44  lr: 0.002813  min_lr: 0.002813  loss: 3.6572 (3.5917)  weight_decay: 0.0500 (0.0500)  time: 0.5407  data: 0.0412  max mem: 42573
Epoch: [14]  [ 30/312]  eta: 0:03:45  lr: 0.002820  min_lr: 0.002820  loss: 3.9088 (3.6024)  weight_decay: 0.0500 (0.0500)  time: 0.4332  data: 0.0004  max mem: 42573
Epoch: [14]  [ 40/312]  eta: 0:03:13  lr: 0.002826  min_lr: 0.002826  loss: 3.8179 (3.6401)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [14]  [ 50/312]  eta: 0:02:52  lr: 0.002833  min_lr: 0.002833  loss: 3.8339 (3.6440)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0004  max mem: 42573
Epoch: [14]  [ 60/312]  eta: 0:02:36  lr: 0.002839  min_lr: 0.002839  loss: 3.7601 (3.6343)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [14]  [ 70/312]  eta: 0:02:23  lr: 0.002845  min_lr: 0.002845  loss: 3.4891 (3.5927)  weight_decay: 0.0500 (0.0500)  time: 0.4344  data: 0.0004  max mem: 42573
Epoch: [14]  [ 80/312]  eta: 0:02:13  lr: 0.002852  min_lr: 0.002852  loss: 3.6567 (3.6218)  weight_decay: 0.0500 (0.0500)  time: 0.4344  data: 0.0004  max mem: 42573
Epoch: [14]  [ 90/312]  eta: 0:02:04  lr: 0.002858  min_lr: 0.002858  loss: 3.7981 (3.6255)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0004  max mem: 42573
Epoch: [14]  [100/312]  eta: 0:01:55  lr: 0.002865  min_lr: 0.002865  loss: 3.5529 (3.5991)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [14]  [110/312]  eta: 0:01:48  lr: 0.002871  min_lr: 0.002871  loss: 3.7295 (3.6111)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [14]  [120/312]  eta: 0:01:41  lr: 0.002877  min_lr: 0.002877  loss: 3.6073 (3.5991)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [14]  [130/312]  eta: 0:01:34  lr: 0.002884  min_lr: 0.002884  loss: 3.6032 (3.5986)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [14]  [140/312]  eta: 0:01:28  lr: 0.002890  min_lr: 0.002890  loss: 3.6132 (3.5853)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [14]  [150/312]  eta: 0:01:22  lr: 0.002897  min_lr: 0.002897  loss: 3.5866 (3.5797)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [14]  [160/312]  eta: 0:01:16  lr: 0.002903  min_lr: 0.002903  loss: 3.4950 (3.5706)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [14]  [170/312]  eta: 0:01:11  lr: 0.002909  min_lr: 0.002909  loss: 3.5577 (3.5713)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [14]  [180/312]  eta: 0:01:05  lr: 0.002916  min_lr: 0.002916  loss: 3.5577 (3.5694)  weight_decay: 0.0500 (0.0500)  time: 0.4354  data: 0.0004  max mem: 42573
Epoch: [14]  [190/312]  eta: 0:01:00  lr: 0.002922  min_lr: 0.002922  loss: 3.7118 (3.5664)  weight_decay: 0.0500 (0.0500)  time: 0.4355  data: 0.0004  max mem: 42573
Epoch: [14]  [200/312]  eta: 0:00:54  lr: 0.002929  min_lr: 0.002929  loss: 3.7035 (3.5594)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [14]  [210/312]  eta: 0:00:49  lr: 0.002935  min_lr: 0.002935  loss: 3.5183 (3.5521)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [14]  [220/312]  eta: 0:00:44  lr: 0.002941  min_lr: 0.002941  loss: 3.5713 (3.5584)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [14]  [230/312]  eta: 0:00:39  lr: 0.002948  min_lr: 0.002948  loss: 3.6060 (3.5616)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [14]  [240/312]  eta: 0:00:34  lr: 0.002954  min_lr: 0.002954  loss: 3.7376 (3.5625)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [14]  [250/312]  eta: 0:00:29  lr: 0.002961  min_lr: 0.002961  loss: 3.7857 (3.5668)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [14]  [260/312]  eta: 0:00:24  lr: 0.002967  min_lr: 0.002967  loss: 3.8141 (3.5679)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [14]  [270/312]  eta: 0:00:19  lr: 0.002974  min_lr: 0.002974  loss: 3.4959 (3.5594)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0003  max mem: 42573
Epoch: [14]  [280/312]  eta: 0:00:15  lr: 0.002980  min_lr: 0.002980  loss: 3.7524 (3.5695)  weight_decay: 0.0500 (0.0500)  time: 0.4342  data: 0.0009  max mem: 42573
Epoch: [14]  [290/312]  eta: 0:00:10  lr: 0.002986  min_lr: 0.002986  loss: 3.7384 (3.5637)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0008  max mem: 42573
Epoch: [14]  [300/312]  eta: 0:00:05  lr: 0.002993  min_lr: 0.002993  loss: 3.7573 (3.5768)  weight_decay: 0.0500 (0.0500)  time: 0.4324  data: 0.0001  max mem: 42573
Epoch: [14]  [310/312]  eta: 0:00:00  lr: 0.002999  min_lr: 0.002999  loss: 3.9698 (3.5860)  weight_decay: 0.0500 (0.0500)  time: 0.4323  data: 0.0001  max mem: 42573
Epoch: [14]  [311/312]  eta: 0:00:00  lr: 0.003000  min_lr: 0.003000  loss: 3.9698 (3.5883)  weight_decay: 0.0500 (0.0500)  time: 0.4324  data: 0.0001  max mem: 42573
Epoch: [14] Total time: 0:02:27 (0.4734 s / it)
Averaged stats: lr: 0.003000  min_lr: 0.003000  loss: 3.9698 (3.5894)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:00:42  loss: 1.4315 (1.4315)  acc1: 66.9271 (66.9271)  acc5: 84.3750 (84.3750)  time: 4.7063  data: 4.5976  max mem: 42573
Test:  [8/9]  eta: 0:00:00  loss: 1.8834 (1.7368)  acc1: 58.0729 (59.1040)  acc5: 81.2500 (81.6320)  time: 0.5983  data: 0.5109  max mem: 42573
Test: Total time: 0:00:05 (0.6052 s / it)
* Acc@1 59.236 Acc@5 82.014 loss 1.744
Accuracy of the model on the 50000 test images: 59.2%
Max accuracy: 59.24%
Epoch: [15]  [  0/312]  eta: 0:46:39  lr: 0.003000  min_lr: 0.003000  loss: 3.9807 (3.9807)  weight_decay: 0.0500 (0.0500)  time: 8.9729  data: 7.6831  max mem: 42573
Epoch: [15]  [ 10/312]  eta: 0:06:41  lr: 0.003007  min_lr: 0.003007  loss: 3.0850 (3.3560)  weight_decay: 0.0500 (0.0500)  time: 1.3290  data: 0.6989  max mem: 42573
Epoch: [15]  [ 20/312]  eta: 0:04:23  lr: 0.003013  min_lr: 0.003013  loss: 3.0850 (3.3746)  weight_decay: 0.0500 (0.0500)  time: 0.5000  data: 0.0004  max mem: 42573
Epoch: [15]  [ 30/312]  eta: 0:03:31  lr: 0.003020  min_lr: 0.003020  loss: 3.0858 (3.3119)  weight_decay: 0.0500 (0.0500)  time: 0.4343  data: 0.0004  max mem: 42573
Epoch: [15]  [ 40/312]  eta: 0:03:03  lr: 0.003026  min_lr: 0.003026  loss: 3.2209 (3.3640)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0003  max mem: 42573
Epoch: [15]  [ 50/312]  eta: 0:02:44  lr: 0.003033  min_lr: 0.003033  loss: 3.2517 (3.3602)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [15]  [ 60/312]  eta: 0:02:30  lr: 0.003039  min_lr: 0.003039  loss: 3.3803 (3.3888)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [15]  [ 70/312]  eta: 0:02:18  lr: 0.003045  min_lr: 0.003045  loss: 3.4927 (3.4075)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0003  max mem: 42573
Epoch: [15]  [ 80/312]  eta: 0:02:08  lr: 0.003052  min_lr: 0.003052  loss: 3.5123 (3.4066)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [15]  [ 90/312]  eta: 0:02:00  lr: 0.003058  min_lr: 0.003058  loss: 3.5147 (3.4129)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [15]  [100/312]  eta: 0:01:52  lr: 0.003065  min_lr: 0.003065  loss: 3.5829 (3.4381)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [15]  [110/312]  eta: 0:01:45  lr: 0.003071  min_lr: 0.003071  loss: 3.7333 (3.4511)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [15]  [120/312]  eta: 0:01:38  lr: 0.003077  min_lr: 0.003077  loss: 3.7712 (3.4719)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [15]  [130/312]  eta: 0:01:32  lr: 0.003084  min_lr: 0.003084  loss: 3.7046 (3.4755)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [15]  [140/312]  eta: 0:01:26  lr: 0.003090  min_lr: 0.003090  loss: 3.5726 (3.4778)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [15]  [150/312]  eta: 0:01:20  lr: 0.003097  min_lr: 0.003097  loss: 3.5761 (3.4791)  weight_decay: 0.0500 (0.0500)  time: 0.4393  data: 0.0004  max mem: 42573
Epoch: [15]  [160/312]  eta: 0:01:15  lr: 0.003103  min_lr: 0.003103  loss: 3.6467 (3.4907)  weight_decay: 0.0500 (0.0500)  time: 0.4393  data: 0.0004  max mem: 42573
Epoch: [15]  [170/312]  eta: 0:01:09  lr: 0.003109  min_lr: 0.003109  loss: 3.8162 (3.4975)  weight_decay: 0.0500 (0.0500)  time: 0.4341  data: 0.0004  max mem: 42573
Epoch: [15]  [180/312]  eta: 0:01:04  lr: 0.003116  min_lr: 0.003116  loss: 3.4568 (3.4883)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [15]  [190/312]  eta: 0:00:59  lr: 0.003122  min_lr: 0.003122  loss: 3.4568 (3.4941)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [15]  [200/312]  eta: 0:00:54  lr: 0.003129  min_lr: 0.003129  loss: 3.8779 (3.5068)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [15]  [210/312]  eta: 0:00:49  lr: 0.003135  min_lr: 0.003135  loss: 3.4989 (3.4965)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0003  max mem: 42573
Epoch: [15]  [220/312]  eta: 0:00:44  lr: 0.003142  min_lr: 0.003142  loss: 3.3891 (3.4967)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0003  max mem: 42573
Epoch: [15]  [230/312]  eta: 0:00:39  lr: 0.003148  min_lr: 0.003148  loss: 3.5589 (3.4980)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [15]  [240/312]  eta: 0:00:34  lr: 0.003154  min_lr: 0.003154  loss: 3.6177 (3.5012)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [15]  [250/312]  eta: 0:00:29  lr: 0.003161  min_lr: 0.003161  loss: 3.2889 (3.4911)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [15]  [260/312]  eta: 0:00:24  lr: 0.003167  min_lr: 0.003167  loss: 3.6493 (3.4994)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [15]  [270/312]  eta: 0:00:19  lr: 0.003174  min_lr: 0.003174  loss: 3.7979 (3.5033)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [15]  [280/312]  eta: 0:00:15  lr: 0.003180  min_lr: 0.003180  loss: 3.6533 (3.4991)  weight_decay: 0.0500 (0.0500)  time: 0.4351  data: 0.0009  max mem: 42573
Epoch: [15]  [290/312]  eta: 0:00:10  lr: 0.003186  min_lr: 0.003186  loss: 3.3185 (3.4981)  weight_decay: 0.0500 (0.0500)  time: 0.4344  data: 0.0008  max mem: 42573
Epoch: [15]  [300/312]  eta: 0:00:05  lr: 0.003193  min_lr: 0.003193  loss: 3.5648 (3.5008)  weight_decay: 0.0500 (0.0500)  time: 0.4324  data: 0.0001  max mem: 42573
Epoch: [15]  [310/312]  eta: 0:00:00  lr: 0.003199  min_lr: 0.003199  loss: 3.6647 (3.5000)  weight_decay: 0.0500 (0.0500)  time: 0.4323  data: 0.0001  max mem: 42573
Epoch: [15]  [311/312]  eta: 0:00:00  lr: 0.003200  min_lr: 0.003200  loss: 3.6647 (3.5001)  weight_decay: 0.0500 (0.0500)  time: 0.4324  data: 0.0001  max mem: 42573
Epoch: [15] Total time: 0:02:26 (0.4689 s / it)
Averaged stats: lr: 0.003200  min_lr: 0.003200  loss: 3.6647 (3.5367)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:00:43  loss: 1.3355 (1.3355)  acc1: 68.7500 (68.7500)  acc5: 88.5417 (88.5417)  time: 4.8162  data: 4.7069  max mem: 42573
Test:  [8/9]  eta: 0:00:00  loss: 1.8678 (1.6583)  acc1: 58.3333 (59.7760)  acc5: 80.4688 (82.2720)  time: 0.6123  data: 0.5230  max mem: 42573
Test: Total time: 0:00:05 (0.6210 s / it)
* Acc@1 60.204 Acc@5 82.736 loss 1.650
Accuracy of the model on the 50000 test images: 60.2%
Max accuracy: 60.20%
Epoch: [16]  [  0/312]  eta: 0:50:32  lr: 0.003201  min_lr: 0.003201  loss: 3.7231 (3.7231)  weight_decay: 0.0500 (0.0500)  time: 9.7182  data: 8.6405  max mem: 42573
Epoch: [16]  [ 10/312]  eta: 0:07:18  lr: 0.003207  min_lr: 0.003207  loss: 3.7231 (3.5449)  weight_decay: 0.0500 (0.0500)  time: 1.4513  data: 0.7858  max mem: 42573
Epoch: [16]  [ 20/312]  eta: 0:04:42  lr: 0.003213  min_lr: 0.003213  loss: 3.6339 (3.4790)  weight_decay: 0.0500 (0.0500)  time: 0.5291  data: 0.0004  max mem: 42573
Epoch: [16]  [ 30/312]  eta: 0:03:44  lr: 0.003220  min_lr: 0.003220  loss: 3.7071 (3.5643)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [16]  [ 40/312]  eta: 0:03:12  lr: 0.003226  min_lr: 0.003226  loss: 3.7738 (3.6142)  weight_decay: 0.0500 (0.0500)  time: 0.4332  data: 0.0004  max mem: 42573
Epoch: [16]  [ 50/312]  eta: 0:02:51  lr: 0.003233  min_lr: 0.003233  loss: 3.6329 (3.5621)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [16]  [ 60/312]  eta: 0:02:35  lr: 0.003239  min_lr: 0.003239  loss: 3.5025 (3.5319)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [16]  [ 70/312]  eta: 0:02:23  lr: 0.003245  min_lr: 0.003245  loss: 3.6478 (3.5506)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [16]  [ 80/312]  eta: 0:02:12  lr: 0.003252  min_lr: 0.003252  loss: 3.8190 (3.5683)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0005  max mem: 42573
Epoch: [16]  [ 90/312]  eta: 0:02:03  lr: 0.003258  min_lr: 0.003258  loss: 3.6807 (3.5360)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [16]  [100/312]  eta: 0:01:55  lr: 0.003265  min_lr: 0.003265  loss: 3.6060 (3.5575)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [16]  [110/312]  eta: 0:01:47  lr: 0.003271  min_lr: 0.003271  loss: 3.7619 (3.5606)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [16]  [120/312]  eta: 0:01:41  lr: 0.003277  min_lr: 0.003277  loss: 3.5729 (3.5471)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0003  max mem: 42573
Epoch: [16]  [130/312]  eta: 0:01:34  lr: 0.003284  min_lr: 0.003284  loss: 3.5729 (3.5466)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [16]  [140/312]  eta: 0:01:28  lr: 0.003290  min_lr: 0.003290  loss: 3.7019 (3.5469)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [16]  [150/312]  eta: 0:01:22  lr: 0.003297  min_lr: 0.003297  loss: 3.7043 (3.5409)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [16]  [160/312]  eta: 0:01:16  lr: 0.003303  min_lr: 0.003303  loss: 3.7043 (3.5461)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [16]  [170/312]  eta: 0:01:10  lr: 0.003310  min_lr: 0.003310  loss: 3.4662 (3.5314)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [16]  [180/312]  eta: 0:01:05  lr: 0.003316  min_lr: 0.003316  loss: 3.4890 (3.5381)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [16]  [190/312]  eta: 0:01:00  lr: 0.003322  min_lr: 0.003322  loss: 3.6821 (3.5450)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [16]  [200/312]  eta: 0:00:54  lr: 0.003329  min_lr: 0.003329  loss: 3.6135 (3.5449)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0003  max mem: 42573
Epoch: [16]  [210/312]  eta: 0:00:49  lr: 0.003335  min_lr: 0.003335  loss: 3.6135 (3.5439)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [16]  [220/312]  eta: 0:00:44  lr: 0.003342  min_lr: 0.003342  loss: 3.6316 (3.5476)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [16]  [230/312]  eta: 0:00:39  lr: 0.003348  min_lr: 0.003348  loss: 3.7033 (3.5501)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [16]  [240/312]  eta: 0:00:34  lr: 0.003354  min_lr: 0.003354  loss: 3.5158 (3.5369)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [16]  [250/312]  eta: 0:00:29  lr: 0.003361  min_lr: 0.003361  loss: 3.3463 (3.5392)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0003  max mem: 42573
Epoch: [16]  [260/312]  eta: 0:00:24  lr: 0.003367  min_lr: 0.003367  loss: 3.5763 (3.5352)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [16]  [270/312]  eta: 0:00:19  lr: 0.003374  min_lr: 0.003374  loss: 3.6421 (3.5378)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [16]  [280/312]  eta: 0:00:15  lr: 0.003380  min_lr: 0.003380  loss: 3.5101 (3.5338)  weight_decay: 0.0500 (0.0500)  time: 0.4343  data: 0.0009  max mem: 42573
Epoch: [16]  [290/312]  eta: 0:00:10  lr: 0.003386  min_lr: 0.003386  loss: 3.5098 (3.5380)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0008  max mem: 42573
Epoch: [16]  [300/312]  eta: 0:00:05  lr: 0.003393  min_lr: 0.003393  loss: 3.6345 (3.5380)  weight_decay: 0.0500 (0.0500)  time: 0.4324  data: 0.0001  max mem: 42573
Epoch: [16]  [310/312]  eta: 0:00:00  lr: 0.003399  min_lr: 0.003399  loss: 3.6354 (3.5373)  weight_decay: 0.0500 (0.0500)  time: 0.4324  data: 0.0001  max mem: 42573
Epoch: [16]  [311/312]  eta: 0:00:00  lr: 0.003400  min_lr: 0.003400  loss: 3.6354 (3.5389)  weight_decay: 0.0500 (0.0500)  time: 0.4324  data: 0.0001  max mem: 42573
Epoch: [16] Total time: 0:02:27 (0.4726 s / it)
Averaged stats: lr: 0.003400  min_lr: 0.003400  loss: 3.6354 (3.5039)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:00:41  loss: 1.4330 (1.4330)  acc1: 67.7083 (67.7083)  acc5: 85.9375 (85.9375)  time: 4.6455  data: 4.5369  max mem: 42573
Test:  [8/9]  eta: 0:00:00  loss: 1.8675 (1.6754)  acc1: 60.6771 (60.0000)  acc5: 81.2500 (82.4960)  time: 0.5919  data: 0.5042  max mem: 42573
Test: Total time: 0:00:05 (0.5994 s / it)
* Acc@1 60.208 Acc@5 82.766 loss 1.686
Accuracy of the model on the 50000 test images: 60.2%
Max accuracy: 60.21%
Epoch: [17]  [  0/312]  eta: 0:50:42  lr: 0.003401  min_lr: 0.003401  loss: 3.2808 (3.2808)  weight_decay: 0.0500 (0.0500)  time: 9.7513  data: 6.8821  max mem: 42573
Epoch: [17]  [ 10/312]  eta: 0:07:25  lr: 0.003407  min_lr: 0.003407  loss: 3.6122 (3.5862)  weight_decay: 0.0500 (0.0500)  time: 1.4744  data: 0.7908  max mem: 42573
Epoch: [17]  [ 20/312]  eta: 0:04:45  lr: 0.003413  min_lr: 0.003413  loss: 3.7416 (3.6475)  weight_decay: 0.0500 (0.0500)  time: 0.5398  data: 0.0910  max mem: 42573
Epoch: [17]  [ 30/312]  eta: 0:03:46  lr: 0.003420  min_lr: 0.003420  loss: 3.4070 (3.5513)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [17]  [ 40/312]  eta: 0:03:14  lr: 0.003426  min_lr: 0.003426  loss: 3.5638 (3.5659)  weight_decay: 0.0500 (0.0500)  time: 0.4371  data: 0.0004  max mem: 42573
Epoch: [17]  [ 50/312]  eta: 0:02:52  lr: 0.003433  min_lr: 0.003433  loss: 3.5638 (3.5207)  weight_decay: 0.0500 (0.0500)  time: 0.4367  data: 0.0004  max mem: 42573
Epoch: [17]  [ 60/312]  eta: 0:02:36  lr: 0.003439  min_lr: 0.003439  loss: 3.5220 (3.5390)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [17]  [ 70/312]  eta: 0:02:24  lr: 0.003445  min_lr: 0.003445  loss: 3.6154 (3.5245)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [17]  [ 80/312]  eta: 0:02:13  lr: 0.003452  min_lr: 0.003452  loss: 3.5927 (3.5034)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [17]  [ 90/312]  eta: 0:02:04  lr: 0.003458  min_lr: 0.003458  loss: 3.5764 (3.4919)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0003  max mem: 42573
Epoch: [17]  [100/312]  eta: 0:01:56  lr: 0.003465  min_lr: 0.003465  loss: 3.5610 (3.4892)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [17]  [110/312]  eta: 0:01:48  lr: 0.003471  min_lr: 0.003471  loss: 3.6631 (3.4927)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0005  max mem: 42573
Epoch: [17]  [120/312]  eta: 0:01:41  lr: 0.003477  min_lr: 0.003477  loss: 3.5762 (3.4850)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0004  max mem: 42573
Epoch: [17]  [130/312]  eta: 0:01:34  lr: 0.003484  min_lr: 0.003484  loss: 3.5253 (3.4823)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0004  max mem: 42573
Epoch: [17]  [140/312]  eta: 0:01:28  lr: 0.003490  min_lr: 0.003490  loss: 3.5488 (3.4852)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [17]  [150/312]  eta: 0:01:22  lr: 0.003497  min_lr: 0.003497  loss: 3.4204 (3.4742)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [17]  [160/312]  eta: 0:01:16  lr: 0.003503  min_lr: 0.003503  loss: 3.4048 (3.4809)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [17]  [170/312]  eta: 0:01:11  lr: 0.003510  min_lr: 0.003510  loss: 3.7069 (3.4774)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0005  max mem: 42573
Epoch: [17]  [180/312]  eta: 0:01:05  lr: 0.003516  min_lr: 0.003516  loss: 3.2196 (3.4580)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0005  max mem: 42573
Epoch: [17]  [190/312]  eta: 0:01:00  lr: 0.003522  min_lr: 0.003522  loss: 3.0649 (3.4375)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [17]  [200/312]  eta: 0:00:54  lr: 0.003529  min_lr: 0.003529  loss: 3.0830 (3.4357)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [17]  [210/312]  eta: 0:00:49  lr: 0.003535  min_lr: 0.003535  loss: 3.5122 (3.4359)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [17]  [220/312]  eta: 0:00:44  lr: 0.003542  min_lr: 0.003542  loss: 3.0489 (3.4238)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [17]  [230/312]  eta: 0:00:39  lr: 0.003548  min_lr: 0.003548  loss: 3.0624 (3.4239)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [17]  [240/312]  eta: 0:00:34  lr: 0.003554  min_lr: 0.003554  loss: 3.5908 (3.4297)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [17]  [250/312]  eta: 0:00:29  lr: 0.003561  min_lr: 0.003561  loss: 3.6269 (3.4294)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [17]  [260/312]  eta: 0:00:24  lr: 0.003567  min_lr: 0.003567  loss: 3.6284 (3.4362)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [17]  [270/312]  eta: 0:00:20  lr: 0.003574  min_lr: 0.003574  loss: 3.5456 (3.4334)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [17]  [280/312]  eta: 0:00:15  lr: 0.003580  min_lr: 0.003580  loss: 3.5129 (3.4360)  weight_decay: 0.0500 (0.0500)  time: 0.4347  data: 0.0010  max mem: 42573
Epoch: [17]  [290/312]  eta: 0:00:10  lr: 0.003586  min_lr: 0.003586  loss: 3.3418 (3.4262)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0008  max mem: 42573
Epoch: [17]  [300/312]  eta: 0:00:05  lr: 0.003593  min_lr: 0.003593  loss: 3.6886 (3.4370)  weight_decay: 0.0500 (0.0500)  time: 0.4324  data: 0.0001  max mem: 42573
Epoch: [17]  [310/312]  eta: 0:00:00  lr: 0.003599  min_lr: 0.003599  loss: 3.7383 (3.4401)  weight_decay: 0.0500 (0.0500)  time: 0.4324  data: 0.0001  max mem: 42573
Epoch: [17]  [311/312]  eta: 0:00:00  lr: 0.003600  min_lr: 0.003600  loss: 3.7135 (3.4403)  weight_decay: 0.0500 (0.0500)  time: 0.4324  data: 0.0001  max mem: 42573
Epoch: [17] Total time: 0:02:27 (0.4737 s / it)
Averaged stats: lr: 0.003600  min_lr: 0.003600  loss: 3.7135 (3.4422)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:00:41  loss: 1.3799 (1.3799)  acc1: 67.7083 (67.7083)  acc5: 87.5000 (87.5000)  time: 4.6179  data: 4.5086  max mem: 42573
Test:  [8/9]  eta: 0:00:00  loss: 1.8481 (1.7144)  acc1: 58.8542 (59.5200)  acc5: 81.5104 (82.3680)  time: 0.5895  data: 0.5010  max mem: 42573
Test: Total time: 0:00:05 (0.5968 s / it)
* Acc@1 60.068 Acc@5 82.488 loss 1.695
Accuracy of the model on the 50000 test images: 60.1%
Max accuracy: 60.21%
Epoch: [18]  [  0/312]  eta: 0:51:57  lr: 0.003601  min_lr: 0.003601  loss: 3.3788 (3.3788)  weight_decay: 0.0500 (0.0500)  time: 9.9904  data: 7.7808  max mem: 42573
Epoch: [18]  [ 10/312]  eta: 0:07:30  lr: 0.003607  min_lr: 0.003607  loss: 3.5900 (3.5221)  weight_decay: 0.0500 (0.0500)  time: 1.4912  data: 0.7105  max mem: 42573
Epoch: [18]  [ 20/312]  eta: 0:04:48  lr: 0.003613  min_lr: 0.003613  loss: 3.5900 (3.5185)  weight_decay: 0.0500 (0.0500)  time: 0.5382  data: 0.0019  max mem: 42573
Epoch: [18]  [ 30/312]  eta: 0:03:48  lr: 0.003620  min_lr: 0.003620  loss: 3.5145 (3.4406)  weight_decay: 0.0500 (0.0500)  time: 0.4342  data: 0.0004  max mem: 42573
Epoch: [18]  [ 40/312]  eta: 0:03:15  lr: 0.003626  min_lr: 0.003626  loss: 3.3798 (3.4066)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [18]  [ 50/312]  eta: 0:02:53  lr: 0.003633  min_lr: 0.003633  loss: 3.4054 (3.3884)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [18]  [ 60/312]  eta: 0:02:37  lr: 0.003639  min_lr: 0.003639  loss: 3.3894 (3.3668)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0004  max mem: 42573
Epoch: [18]  [ 70/312]  eta: 0:02:24  lr: 0.003645  min_lr: 0.003645  loss: 3.4570 (3.3955)  weight_decay: 0.0500 (0.0500)  time: 0.4341  data: 0.0004  max mem: 42573
Epoch: [18]  [ 80/312]  eta: 0:02:14  lr: 0.003652  min_lr: 0.003652  loss: 3.5408 (3.3796)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [18]  [ 90/312]  eta: 0:02:04  lr: 0.003658  min_lr: 0.003658  loss: 3.4864 (3.3932)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [18]  [100/312]  eta: 0:01:56  lr: 0.003665  min_lr: 0.003665  loss: 3.3675 (3.3710)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [18]  [110/312]  eta: 0:01:48  lr: 0.003671  min_lr: 0.003671  loss: 3.3120 (3.3799)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [18]  [120/312]  eta: 0:01:41  lr: 0.003678  min_lr: 0.003678  loss: 3.5511 (3.3791)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [18]  [130/312]  eta: 0:01:35  lr: 0.003684  min_lr: 0.003684  loss: 3.3027 (3.3708)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [18]  [140/312]  eta: 0:01:28  lr: 0.003690  min_lr: 0.003690  loss: 3.3027 (3.3807)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [18]  [150/312]  eta: 0:01:22  lr: 0.003697  min_lr: 0.003697  loss: 3.5830 (3.3904)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [18]  [160/312]  eta: 0:01:16  lr: 0.003703  min_lr: 0.003703  loss: 3.5703 (3.3859)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [18]  [170/312]  eta: 0:01:11  lr: 0.003710  min_lr: 0.003710  loss: 3.5313 (3.4002)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [18]  [180/312]  eta: 0:01:05  lr: 0.003716  min_lr: 0.003716  loss: 3.5313 (3.4007)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [18]  [190/312]  eta: 0:01:00  lr: 0.003722  min_lr: 0.003722  loss: 3.5887 (3.4096)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [18]  [200/312]  eta: 0:00:55  lr: 0.003729  min_lr: 0.003729  loss: 3.4544 (3.3982)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [18]  [210/312]  eta: 0:00:49  lr: 0.003735  min_lr: 0.003735  loss: 3.5280 (3.4067)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [18]  [220/312]  eta: 0:00:44  lr: 0.003742  min_lr: 0.003742  loss: 3.6688 (3.4091)  weight_decay: 0.0500 (0.0500)  time: 0.4341  data: 0.0004  max mem: 42573
Epoch: [18]  [230/312]  eta: 0:00:39  lr: 0.003748  min_lr: 0.003748  loss: 3.5434 (3.4149)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [18]  [240/312]  eta: 0:00:34  lr: 0.003754  min_lr: 0.003754  loss: 3.4505 (3.4105)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [18]  [250/312]  eta: 0:00:29  lr: 0.003761  min_lr: 0.003761  loss: 3.6092 (3.4162)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [18]  [260/312]  eta: 0:00:24  lr: 0.003767  min_lr: 0.003767  loss: 3.5778 (3.4179)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [18]  [270/312]  eta: 0:00:20  lr: 0.003774  min_lr: 0.003774  loss: 3.4920 (3.4209)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [18]  [280/312]  eta: 0:00:15  lr: 0.003780  min_lr: 0.003780  loss: 3.5333 (3.4219)  weight_decay: 0.0500 (0.0500)  time: 0.4345  data: 0.0010  max mem: 42573
Epoch: [18]  [290/312]  eta: 0:00:10  lr: 0.003787  min_lr: 0.003787  loss: 3.5333 (3.4219)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0008  max mem: 42573
Epoch: [18]  [300/312]  eta: 0:00:05  lr: 0.003793  min_lr: 0.003793  loss: 3.3885 (3.4243)  weight_decay: 0.0500 (0.0500)  time: 0.4326  data: 0.0001  max mem: 42573
Epoch: [18]  [310/312]  eta: 0:00:00  lr: 0.003799  min_lr: 0.003799  loss: 3.5745 (3.4313)  weight_decay: 0.0500 (0.0500)  time: 0.4324  data: 0.0001  max mem: 42573
Epoch: [18]  [311/312]  eta: 0:00:00  lr: 0.003800  min_lr: 0.003800  loss: 3.5745 (3.4322)  weight_decay: 0.0500 (0.0500)  time: 0.4324  data: 0.0001  max mem: 42573
Epoch: [18] Total time: 0:02:27 (0.4742 s / it)
Averaged stats: lr: 0.003800  min_lr: 0.003800  loss: 3.5745 (3.4122)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:00:44  loss: 1.2607 (1.2607)  acc1: 69.2708 (69.2708)  acc5: 90.3646 (90.3646)  time: 4.9517  data: 4.8431  max mem: 42573
Test:  [8/9]  eta: 0:00:00  loss: 1.7879 (1.6283)  acc1: 59.3750 (60.4800)  acc5: 83.8542 (83.3280)  time: 0.6274  data: 0.5382  max mem: 42573
Test: Total time: 0:00:05 (0.6480 s / it)
* Acc@1 61.416 Acc@5 83.476 loss 1.632
Accuracy of the model on the 50000 test images: 61.4%
Max accuracy: 61.42%
Epoch: [19]  [  0/312]  eta: 0:47:08  lr: 0.003801  min_lr: 0.003801  loss: 3.2058 (3.2058)  weight_decay: 0.0500 (0.0500)  time: 9.0648  data: 6.4127  max mem: 42573
Epoch: [19]  [ 10/312]  eta: 0:07:20  lr: 0.003807  min_lr: 0.003807  loss: 3.2058 (3.2398)  weight_decay: 0.0500 (0.0500)  time: 1.4572  data: 0.6734  max mem: 42573
Epoch: [19]  [ 20/312]  eta: 0:04:43  lr: 0.003813  min_lr: 0.003813  loss: 3.1401 (3.2843)  weight_decay: 0.0500 (0.0500)  time: 0.5649  data: 0.0499  max mem: 42573
Epoch: [19]  [ 30/312]  eta: 0:03:44  lr: 0.003820  min_lr: 0.003820  loss: 3.0987 (3.2598)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [19]  [ 40/312]  eta: 0:03:12  lr: 0.003826  min_lr: 0.003826  loss: 3.5250 (3.3419)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0003  max mem: 42573
Epoch: [19]  [ 50/312]  eta: 0:02:51  lr: 0.003833  min_lr: 0.003833  loss: 3.6010 (3.3716)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [19]  [ 60/312]  eta: 0:02:35  lr: 0.003839  min_lr: 0.003839  loss: 3.4812 (3.3678)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [19]  [ 70/312]  eta: 0:02:23  lr: 0.003845  min_lr: 0.003845  loss: 3.2311 (3.3560)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0003  max mem: 42573
Epoch: [19]  [ 80/312]  eta: 0:02:12  lr: 0.003852  min_lr: 0.003852  loss: 3.3146 (3.3491)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [19]  [ 90/312]  eta: 0:02:03  lr: 0.003858  min_lr: 0.003858  loss: 3.4279 (3.3511)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [19]  [100/312]  eta: 0:01:55  lr: 0.003865  min_lr: 0.003865  loss: 3.4747 (3.3758)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [19]  [110/312]  eta: 0:01:48  lr: 0.003871  min_lr: 0.003871  loss: 3.5860 (3.3784)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [19]  [120/312]  eta: 0:01:41  lr: 0.003878  min_lr: 0.003878  loss: 3.3296 (3.3680)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [19]  [130/312]  eta: 0:01:34  lr: 0.003884  min_lr: 0.003884  loss: 3.4298 (3.3686)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [19]  [140/312]  eta: 0:01:28  lr: 0.003890  min_lr: 0.003890  loss: 3.4754 (3.3694)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [19]  [150/312]  eta: 0:01:22  lr: 0.003897  min_lr: 0.003897  loss: 3.4754 (3.3724)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0003  max mem: 42573
Epoch: [19]  [160/312]  eta: 0:01:16  lr: 0.003903  min_lr: 0.003903  loss: 3.6523 (3.3830)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [19]  [170/312]  eta: 0:01:10  lr: 0.003910  min_lr: 0.003910  loss: 3.6242 (3.3823)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [19]  [180/312]  eta: 0:01:05  lr: 0.003916  min_lr: 0.003916  loss: 3.2418 (3.3744)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [19]  [190/312]  eta: 0:01:00  lr: 0.003922  min_lr: 0.003922  loss: 3.5409 (3.3863)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [19]  [200/312]  eta: 0:00:54  lr: 0.003929  min_lr: 0.003929  loss: 3.5409 (3.3846)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [19]  [210/312]  eta: 0:00:49  lr: 0.003935  min_lr: 0.003935  loss: 3.1671 (3.3777)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [19]  [220/312]  eta: 0:00:44  lr: 0.003942  min_lr: 0.003942  loss: 3.5940 (3.3854)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [19]  [230/312]  eta: 0:00:39  lr: 0.003948  min_lr: 0.003948  loss: 3.3588 (3.3743)  weight_decay: 0.0500 (0.0500)  time: 0.4345  data: 0.0004  max mem: 42573
Epoch: [19]  [240/312]  eta: 0:00:34  lr: 0.003954  min_lr: 0.003954  loss: 3.2730 (3.3719)  weight_decay: 0.0500 (0.0500)  time: 0.4346  data: 0.0004  max mem: 42573
Epoch: [19]  [250/312]  eta: 0:00:29  lr: 0.003961  min_lr: 0.003961  loss: 3.3529 (3.3698)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0003  max mem: 42573
Epoch: [19]  [260/312]  eta: 0:00:24  lr: 0.003967  min_lr: 0.003967  loss: 3.3245 (3.3697)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0003  max mem: 42573
Epoch: [19]  [270/312]  eta: 0:00:19  lr: 0.003974  min_lr: 0.003974  loss: 3.2692 (3.3628)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [19]  [280/312]  eta: 0:00:15  lr: 0.003980  min_lr: 0.003980  loss: 3.3869 (3.3621)  weight_decay: 0.0500 (0.0500)  time: 0.4341  data: 0.0009  max mem: 42573
Epoch: [19]  [290/312]  eta: 0:00:10  lr: 0.003987  min_lr: 0.003987  loss: 3.5647 (3.3679)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0008  max mem: 42573
Epoch: [19]  [300/312]  eta: 0:00:05  lr: 0.003993  min_lr: 0.003993  loss: 3.3804 (3.3618)  weight_decay: 0.0500 (0.0500)  time: 0.4325  data: 0.0001  max mem: 42573
Epoch: [19]  [310/312]  eta: 0:00:00  lr: 0.003999  min_lr: 0.003999  loss: 3.3804 (3.3638)  weight_decay: 0.0500 (0.0500)  time: 0.4323  data: 0.0001  max mem: 42573
Epoch: [19]  [311/312]  eta: 0:00:00  lr: 0.004000  min_lr: 0.004000  loss: 3.4608 (3.3649)  weight_decay: 0.0500 (0.0500)  time: 0.4324  data: 0.0001  max mem: 42573
Epoch: [19] Total time: 0:02:27 (0.4727 s / it)
Averaged stats: lr: 0.004000  min_lr: 0.004000  loss: 3.4608 (3.3751)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:00:43  loss: 1.2087 (1.2087)  acc1: 70.8333 (70.8333)  acc5: 91.6667 (91.6667)  time: 4.8203  data: 4.7108  max mem: 42573
Test:  [8/9]  eta: 0:00:00  loss: 1.7923 (1.6541)  acc1: 60.1562 (59.5840)  acc5: 82.5521 (82.5600)  time: 0.6156  data: 0.5235  max mem: 42573
Test: Total time: 0:00:05 (0.6335 s / it)
* Acc@1 60.708 Acc@5 83.178 loss 1.651
Accuracy of the model on the 50000 test images: 60.7%
Max accuracy: 61.42%
Epoch: [20]  [  0/312]  eta: 0:48:44  lr: 0.004000  min_lr: 0.004000  loss: 2.8399 (2.8399)  weight_decay: 0.0500 (0.0500)  time: 9.3726  data: 7.4023  max mem: 42573
Epoch: [20]  [ 10/312]  eta: 0:07:31  lr: 0.004000  min_lr: 0.004000  loss: 3.5552 (3.4368)  weight_decay: 0.0500 (0.0500)  time: 1.4940  data: 0.7486  max mem: 42573
Epoch: [20]  [ 20/312]  eta: 0:04:48  lr: 0.004000  min_lr: 0.004000  loss: 3.5680 (3.4852)  weight_decay: 0.0500 (0.0500)  time: 0.5697  data: 0.0418  max mem: 42573
Epoch: [20]  [ 30/312]  eta: 0:03:48  lr: 0.004000  min_lr: 0.004000  loss: 3.5111 (3.4030)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0003  max mem: 42573
Epoch: [20]  [ 40/312]  eta: 0:03:15  lr: 0.004000  min_lr: 0.004000  loss: 3.2245 (3.3634)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0003  max mem: 42573
Epoch: [20]  [ 50/312]  eta: 0:02:53  lr: 0.004000  min_lr: 0.004000  loss: 3.2079 (3.3627)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [20]  [ 60/312]  eta: 0:02:37  lr: 0.004000  min_lr: 0.004000  loss: 3.2079 (3.3604)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [20]  [ 70/312]  eta: 0:02:24  lr: 0.004000  min_lr: 0.004000  loss: 3.5010 (3.3736)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [20]  [ 80/312]  eta: 0:02:14  lr: 0.004000  min_lr: 0.004000  loss: 3.5131 (3.3803)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [20]  [ 90/312]  eta: 0:02:04  lr: 0.004000  min_lr: 0.004000  loss: 3.5327 (3.3823)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [20]  [100/312]  eta: 0:01:56  lr: 0.004000  min_lr: 0.004000  loss: 3.3596 (3.3613)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [20]  [110/312]  eta: 0:01:48  lr: 0.004000  min_lr: 0.004000  loss: 3.2851 (3.3538)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [20]  [120/312]  eta: 0:01:41  lr: 0.004000  min_lr: 0.004000  loss: 3.0866 (3.3404)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [20]  [130/312]  eta: 0:01:35  lr: 0.004000  min_lr: 0.004000  loss: 3.3619 (3.3421)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [20]  [140/312]  eta: 0:01:28  lr: 0.004000  min_lr: 0.004000  loss: 3.4486 (3.3486)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0003  max mem: 42573
Epoch: [20]  [150/312]  eta: 0:01:22  lr: 0.004000  min_lr: 0.004000  loss: 3.4690 (3.3550)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [20]  [160/312]  eta: 0:01:16  lr: 0.004000  min_lr: 0.004000  loss: 3.4680 (3.3503)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [20]  [170/312]  eta: 0:01:11  lr: 0.004000  min_lr: 0.004000  loss: 3.4680 (3.3490)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [20]  [180/312]  eta: 0:01:05  lr: 0.004000  min_lr: 0.004000  loss: 3.2093 (3.3391)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [20]  [190/312]  eta: 0:01:00  lr: 0.004000  min_lr: 0.004000  loss: 3.3535 (3.3479)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [20]  [200/312]  eta: 0:00:55  lr: 0.004000  min_lr: 0.004000  loss: 3.4421 (3.3383)  weight_decay: 0.0500 (0.0500)  time: 0.4341  data: 0.0004  max mem: 42573
Epoch: [20]  [210/312]  eta: 0:00:49  lr: 0.004000  min_lr: 0.004000  loss: 3.5688 (3.3531)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0004  max mem: 42573
Epoch: [20]  [220/312]  eta: 0:00:44  lr: 0.004000  min_lr: 0.004000  loss: 3.6146 (3.3569)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [20]  [230/312]  eta: 0:00:39  lr: 0.004000  min_lr: 0.004000  loss: 3.4800 (3.3533)  weight_decay: 0.0500 (0.0500)  time: 0.4399  data: 0.0004  max mem: 42573
Epoch: [20]  [240/312]  eta: 0:00:34  lr: 0.004000  min_lr: 0.004000  loss: 3.2588 (3.3477)  weight_decay: 0.0500 (0.0500)  time: 0.4398  data: 0.0004  max mem: 42573
Epoch: [20]  [250/312]  eta: 0:00:29  lr: 0.004000  min_lr: 0.004000  loss: 3.5204 (3.3608)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [20]  [260/312]  eta: 0:00:24  lr: 0.004000  min_lr: 0.004000  loss: 3.6997 (3.3728)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0004  max mem: 42573
Epoch: [20]  [270/312]  eta: 0:00:20  lr: 0.004000  min_lr: 0.004000  loss: 3.6228 (3.3765)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0003  max mem: 42573
Epoch: [20]  [280/312]  eta: 0:00:15  lr: 0.004000  min_lr: 0.004000  loss: 3.2992 (3.3668)  weight_decay: 0.0500 (0.0500)  time: 0.4345  data: 0.0009  max mem: 42573
Epoch: [20]  [290/312]  eta: 0:00:10  lr: 0.004000  min_lr: 0.004000  loss: 3.0763 (3.3649)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0008  max mem: 42573
Epoch: [20]  [300/312]  eta: 0:00:05  lr: 0.004000  min_lr: 0.004000  loss: 3.5032 (3.3622)  weight_decay: 0.0500 (0.0500)  time: 0.4325  data: 0.0001  max mem: 42573
Epoch: [20]  [310/312]  eta: 0:00:00  lr: 0.004000  min_lr: 0.004000  loss: 3.5032 (3.3632)  weight_decay: 0.0500 (0.0500)  time: 0.4325  data: 0.0001  max mem: 42573
Epoch: [20]  [311/312]  eta: 0:00:00  lr: 0.004000  min_lr: 0.004000  loss: 3.5078 (3.3645)  weight_decay: 0.0500 (0.0500)  time: 0.4325  data: 0.0001  max mem: 42573
Epoch: [20] Total time: 0:02:28 (0.4747 s / it)
Averaged stats: lr: 0.004000  min_lr: 0.004000  loss: 3.5078 (3.3496)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:00:43  loss: 1.3060 (1.3060)  acc1: 68.7500 (68.7500)  acc5: 86.4583 (86.4583)  time: 4.7985  data: 4.6889  max mem: 42573
Test:  [8/9]  eta: 0:00:00  loss: 1.6591 (1.5779)  acc1: 61.9792 (61.8240)  acc5: 85.9375 (83.8720)  time: 0.6098  data: 0.5210  max mem: 42573
Test: Total time: 0:00:05 (0.6352 s / it)
* Acc@1 61.722 Acc@5 84.044 loss 1.609
Accuracy of the model on the 50000 test images: 61.7%
Max accuracy: 61.72%
Epoch: [21]  [  0/312]  eta: 0:47:44  lr: 0.004000  min_lr: 0.004000  loss: 3.4441 (3.4441)  weight_decay: 0.0500 (0.0500)  time: 9.1796  data: 7.3886  max mem: 42573
Epoch: [21]  [ 10/312]  eta: 0:07:16  lr: 0.004000  min_lr: 0.004000  loss: 3.5145 (3.4713)  weight_decay: 0.0500 (0.0500)  time: 1.4452  data: 0.6721  max mem: 42573
Epoch: [21]  [ 20/312]  eta: 0:04:41  lr: 0.004000  min_lr: 0.004000  loss: 3.5265 (3.4262)  weight_decay: 0.0500 (0.0500)  time: 0.5524  data: 0.0004  max mem: 42573
Epoch: [21]  [ 30/312]  eta: 0:03:43  lr: 0.004000  min_lr: 0.004000  loss: 3.3391 (3.3162)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [21]  [ 40/312]  eta: 0:03:11  lr: 0.004000  min_lr: 0.004000  loss: 3.4239 (3.3510)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [21]  [ 50/312]  eta: 0:02:50  lr: 0.004000  min_lr: 0.004000  loss: 3.5377 (3.3587)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [21]  [ 60/312]  eta: 0:02:35  lr: 0.004000  min_lr: 0.004000  loss: 3.3620 (3.3521)  weight_decay: 0.0500 (0.0500)  time: 0.4341  data: 0.0004  max mem: 42573
Epoch: [21]  [ 70/312]  eta: 0:02:22  lr: 0.004000  min_lr: 0.004000  loss: 3.3620 (3.3404)  weight_decay: 0.0500 (0.0500)  time: 0.4341  data: 0.0004  max mem: 42573
Epoch: [21]  [ 80/312]  eta: 0:02:12  lr: 0.004000  min_lr: 0.004000  loss: 3.5136 (3.3528)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [21]  [ 90/312]  eta: 0:02:03  lr: 0.004000  min_lr: 0.004000  loss: 3.3760 (3.3471)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [21]  [100/312]  eta: 0:01:55  lr: 0.004000  min_lr: 0.004000  loss: 3.3400 (3.3282)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [21]  [110/312]  eta: 0:01:47  lr: 0.004000  min_lr: 0.004000  loss: 3.1958 (3.3100)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [21]  [120/312]  eta: 0:01:40  lr: 0.004000  min_lr: 0.004000  loss: 3.1958 (3.3010)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [21]  [130/312]  eta: 0:01:34  lr: 0.004000  min_lr: 0.004000  loss: 3.1450 (3.2952)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0004  max mem: 42573
Epoch: [21]  [140/312]  eta: 0:01:28  lr: 0.004000  min_lr: 0.004000  loss: 3.4666 (3.3114)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0004  max mem: 42573
Epoch: [21]  [150/312]  eta: 0:01:22  lr: 0.004000  min_lr: 0.004000  loss: 3.5280 (3.3155)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [21]  [160/312]  eta: 0:01:16  lr: 0.004000  min_lr: 0.004000  loss: 3.4370 (3.3165)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [21]  [170/312]  eta: 0:01:10  lr: 0.004000  min_lr: 0.004000  loss: 3.4370 (3.3152)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [21]  [180/312]  eta: 0:01:05  lr: 0.004000  min_lr: 0.004000  loss: 3.0093 (3.3024)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [21]  [190/312]  eta: 0:01:00  lr: 0.004000  min_lr: 0.004000  loss: 3.3760 (3.3044)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [21]  [200/312]  eta: 0:00:54  lr: 0.004000  min_lr: 0.004000  loss: 3.3846 (3.2976)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [21]  [210/312]  eta: 0:00:49  lr: 0.004000  min_lr: 0.004000  loss: 3.0381 (3.2851)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [21]  [220/312]  eta: 0:00:44  lr: 0.004000  min_lr: 0.004000  loss: 3.0329 (3.2783)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [21]  [230/312]  eta: 0:00:39  lr: 0.004000  min_lr: 0.004000  loss: 3.1711 (3.2746)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [21]  [240/312]  eta: 0:00:34  lr: 0.004000  min_lr: 0.004000  loss: 3.3828 (3.2805)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [21]  [250/312]  eta: 0:00:29  lr: 0.004000  min_lr: 0.004000  loss: 3.6028 (3.2897)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [21]  [260/312]  eta: 0:00:24  lr: 0.004000  min_lr: 0.004000  loss: 3.5849 (3.2924)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [21]  [270/312]  eta: 0:00:19  lr: 0.004000  min_lr: 0.004000  loss: 3.5097 (3.2983)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0003  max mem: 42573
Epoch: [21]  [280/312]  eta: 0:00:15  lr: 0.004000  min_lr: 0.004000  loss: 3.3655 (3.2896)  weight_decay: 0.0500 (0.0500)  time: 0.4344  data: 0.0009  max mem: 42573
Epoch: [21]  [290/312]  eta: 0:00:10  lr: 0.004000  min_lr: 0.004000  loss: 2.9430 (3.2831)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0008  max mem: 42573
Epoch: [21]  [300/312]  eta: 0:00:05  lr: 0.004000  min_lr: 0.004000  loss: 3.2604 (3.2832)  weight_decay: 0.0500 (0.0500)  time: 0.4324  data: 0.0001  max mem: 42573
Epoch: [21]  [310/312]  eta: 0:00:00  lr: 0.003999  min_lr: 0.003999  loss: 3.4075 (3.2860)  weight_decay: 0.0500 (0.0500)  time: 0.4322  data: 0.0001  max mem: 42573
Epoch: [21]  [311/312]  eta: 0:00:00  lr: 0.003999  min_lr: 0.003999  loss: 3.2970 (3.2860)  weight_decay: 0.0500 (0.0500)  time: 0.4322  data: 0.0001  max mem: 42573
Epoch: [21] Total time: 0:02:27 (0.4723 s / it)
Averaged stats: lr: 0.003999  min_lr: 0.003999  loss: 3.2970 (3.2909)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:00:42  loss: 1.3304 (1.3304)  acc1: 71.6146 (71.6146)  acc5: 87.2396 (87.2396)  time: 4.7507  data: 4.6411  max mem: 42573
Test:  [8/9]  eta: 0:00:00  loss: 1.6910 (1.6071)  acc1: 63.0208 (62.7200)  acc5: 84.6354 (83.6480)  time: 0.6030  data: 0.5157  max mem: 42573
Test: Total time: 0:00:05 (0.6278 s / it)
* Acc@1 62.394 Acc@5 84.330 loss 1.595
Accuracy of the model on the 50000 test images: 62.4%
Max accuracy: 62.39%
Epoch: [22]  [  0/312]  eta: 0:49:13  lr: 0.003999  min_lr: 0.003999  loss: 3.7091 (3.7091)  weight_decay: 0.0500 (0.0500)  time: 9.4674  data: 6.4080  max mem: 42573
Epoch: [22]  [ 10/312]  eta: 0:07:19  lr: 0.003999  min_lr: 0.003999  loss: 3.6886 (3.5140)  weight_decay: 0.0500 (0.0500)  time: 1.4543  data: 0.7230  max mem: 42573
Epoch: [22]  [ 20/312]  eta: 0:04:42  lr: 0.003999  min_lr: 0.003999  loss: 3.3496 (3.3641)  weight_decay: 0.0500 (0.0500)  time: 0.5431  data: 0.0774  max mem: 42573
Epoch: [22]  [ 30/312]  eta: 0:03:44  lr: 0.003999  min_lr: 0.003999  loss: 3.3979 (3.4338)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [22]  [ 40/312]  eta: 0:03:12  lr: 0.003999  min_lr: 0.003999  loss: 3.4572 (3.3864)  weight_decay: 0.0500 (0.0500)  time: 0.4348  data: 0.0004  max mem: 42573
Epoch: [22]  [ 50/312]  eta: 0:02:51  lr: 0.003999  min_lr: 0.003999  loss: 3.4572 (3.3951)  weight_decay: 0.0500 (0.0500)  time: 0.4346  data: 0.0004  max mem: 42573
Epoch: [22]  [ 60/312]  eta: 0:02:35  lr: 0.003999  min_lr: 0.003999  loss: 3.5126 (3.4137)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0003  max mem: 42573
Epoch: [22]  [ 70/312]  eta: 0:02:23  lr: 0.003999  min_lr: 0.003999  loss: 3.6912 (3.4516)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0003  max mem: 42573
Epoch: [22]  [ 80/312]  eta: 0:02:12  lr: 0.003999  min_lr: 0.003999  loss: 3.5737 (3.4159)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0003  max mem: 42573
Epoch: [22]  [ 90/312]  eta: 0:02:03  lr: 0.003999  min_lr: 0.003999  loss: 3.3418 (3.4003)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0003  max mem: 42573
Epoch: [22]  [100/312]  eta: 0:01:55  lr: 0.003999  min_lr: 0.003999  loss: 3.4549 (3.3929)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0003  max mem: 42573
Epoch: [22]  [110/312]  eta: 0:01:48  lr: 0.003999  min_lr: 0.003999  loss: 3.4032 (3.3803)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0003  max mem: 42573
Epoch: [22]  [120/312]  eta: 0:01:41  lr: 0.003999  min_lr: 0.003999  loss: 3.4980 (3.3718)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0003  max mem: 42573
Epoch: [22]  [130/312]  eta: 0:01:34  lr: 0.003999  min_lr: 0.003999  loss: 3.3877 (3.3659)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0003  max mem: 42573
Epoch: [22]  [140/312]  eta: 0:01:28  lr: 0.003999  min_lr: 0.003999  loss: 3.3877 (3.3693)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0003  max mem: 42573
Epoch: [22]  [150/312]  eta: 0:01:22  lr: 0.003999  min_lr: 0.003999  loss: 3.3273 (3.3582)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0003  max mem: 42573
Epoch: [22]  [160/312]  eta: 0:01:16  lr: 0.003999  min_lr: 0.003999  loss: 3.2645 (3.3507)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0003  max mem: 42573
Epoch: [22]  [170/312]  eta: 0:01:10  lr: 0.003999  min_lr: 0.003999  loss: 3.2645 (3.3429)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0003  max mem: 42573
Epoch: [22]  [180/312]  eta: 0:01:05  lr: 0.003999  min_lr: 0.003999  loss: 3.4752 (3.3537)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0003  max mem: 42573
Epoch: [22]  [190/312]  eta: 0:01:00  lr: 0.003999  min_lr: 0.003999  loss: 3.4589 (3.3389)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0003  max mem: 42573
Epoch: [22]  [200/312]  eta: 0:00:54  lr: 0.003999  min_lr: 0.003999  loss: 3.1927 (3.3351)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0003  max mem: 42573
Epoch: [22]  [210/312]  eta: 0:00:49  lr: 0.003999  min_lr: 0.003999  loss: 3.1817 (3.3217)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0003  max mem: 42573
Epoch: [22]  [220/312]  eta: 0:00:44  lr: 0.003999  min_lr: 0.003999  loss: 3.0461 (3.3137)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0003  max mem: 42573
Epoch: [22]  [230/312]  eta: 0:00:39  lr: 0.003999  min_lr: 0.003999  loss: 3.0375 (3.3034)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0003  max mem: 42573
Epoch: [22]  [240/312]  eta: 0:00:34  lr: 0.003999  min_lr: 0.003999  loss: 2.9367 (3.2913)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0003  max mem: 42573
Epoch: [22]  [250/312]  eta: 0:00:29  lr: 0.003999  min_lr: 0.003999  loss: 3.1740 (3.2908)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0003  max mem: 42573
Epoch: [22]  [260/312]  eta: 0:00:24  lr: 0.003999  min_lr: 0.003999  loss: 3.3198 (3.2814)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0003  max mem: 42573
Epoch: [22]  [270/312]  eta: 0:00:19  lr: 0.003999  min_lr: 0.003999  loss: 3.3593 (3.2872)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0003  max mem: 42573
Epoch: [22]  [280/312]  eta: 0:00:15  lr: 0.003999  min_lr: 0.003999  loss: 3.3438 (3.2817)  weight_decay: 0.0500 (0.0500)  time: 0.4344  data: 0.0009  max mem: 42573
Epoch: [22]  [290/312]  eta: 0:00:10  lr: 0.003999  min_lr: 0.003999  loss: 3.2817 (3.2826)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0008  max mem: 42573
Epoch: [22]  [300/312]  eta: 0:00:05  lr: 0.003999  min_lr: 0.003999  loss: 3.4110 (3.2875)  weight_decay: 0.0500 (0.0500)  time: 0.4325  data: 0.0001  max mem: 42573
Epoch: [22]  [310/312]  eta: 0:00:00  lr: 0.003999  min_lr: 0.003999  loss: 3.4110 (3.2896)  weight_decay: 0.0500 (0.0500)  time: 0.4325  data: 0.0001  max mem: 42573
Epoch: [22]  [311/312]  eta: 0:00:00  lr: 0.003999  min_lr: 0.003999  loss: 3.4309 (3.2908)  weight_decay: 0.0500 (0.0500)  time: 0.4325  data: 0.0001  max mem: 42573
Epoch: [22] Total time: 0:02:27 (0.4728 s / it)
Averaged stats: lr: 0.003999  min_lr: 0.003999  loss: 3.4309 (3.2572)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:00:43  loss: 1.3088 (1.3088)  acc1: 66.6667 (66.6667)  acc5: 86.4583 (86.4583)  time: 4.8661  data: 4.7566  max mem: 42573
Test:  [8/9]  eta: 0:00:00  loss: 1.7112 (1.5741)  acc1: 62.2396 (61.3120)  acc5: 85.9375 (83.8400)  time: 0.6162  data: 0.5286  max mem: 42573
Test: Total time: 0:00:05 (0.6389 s / it)
* Acc@1 61.950 Acc@5 84.244 loss 1.576
Accuracy of the model on the 50000 test images: 62.0%
Max accuracy: 62.39%
Epoch: [23]  [  0/312]  eta: 0:50:11  lr: 0.003999  min_lr: 0.003999  loss: 2.8518 (2.8518)  weight_decay: 0.0500 (0.0500)  time: 9.6529  data: 6.7523  max mem: 42573
Epoch: [23]  [ 10/312]  eta: 0:07:13  lr: 0.003999  min_lr: 0.003999  loss: 2.9119 (3.0786)  weight_decay: 0.0500 (0.0500)  time: 1.4369  data: 0.7178  max mem: 42573
Epoch: [23]  [ 20/312]  eta: 0:04:40  lr: 0.003999  min_lr: 0.003999  loss: 3.3039 (3.2614)  weight_decay: 0.0500 (0.0500)  time: 0.5242  data: 0.0573  max mem: 42573
Epoch: [23]  [ 30/312]  eta: 0:03:42  lr: 0.003999  min_lr: 0.003999  loss: 3.4243 (3.1963)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0004  max mem: 42573
Epoch: [23]  [ 40/312]  eta: 0:03:11  lr: 0.003999  min_lr: 0.003999  loss: 3.2578 (3.2339)  weight_decay: 0.0500 (0.0500)  time: 0.4344  data: 0.0005  max mem: 42573
Epoch: [23]  [ 50/312]  eta: 0:02:50  lr: 0.003999  min_lr: 0.003999  loss: 3.4404 (3.2341)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0005  max mem: 42573
Epoch: [23]  [ 60/312]  eta: 0:02:34  lr: 0.003999  min_lr: 0.003999  loss: 3.1683 (3.2137)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [23]  [ 70/312]  eta: 0:02:22  lr: 0.003999  min_lr: 0.003999  loss: 3.3870 (3.2540)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0005  max mem: 42573
Epoch: [23]  [ 80/312]  eta: 0:02:12  lr: 0.003999  min_lr: 0.003999  loss: 3.3220 (3.2321)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [23]  [ 90/312]  eta: 0:02:03  lr: 0.003999  min_lr: 0.003999  loss: 3.2123 (3.2426)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [23]  [100/312]  eta: 0:01:55  lr: 0.003999  min_lr: 0.003999  loss: 3.2822 (3.2472)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [23]  [110/312]  eta: 0:01:47  lr: 0.003999  min_lr: 0.003999  loss: 3.2822 (3.2404)  weight_decay: 0.0500 (0.0500)  time: 0.4389  data: 0.0004  max mem: 42573
Epoch: [23]  [120/312]  eta: 0:01:40  lr: 0.003999  min_lr: 0.003999  loss: 3.2541 (3.2208)  weight_decay: 0.0500 (0.0500)  time: 0.4392  data: 0.0003  max mem: 42573
Epoch: [23]  [130/312]  eta: 0:01:34  lr: 0.003999  min_lr: 0.003999  loss: 3.0527 (3.2101)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0004  max mem: 42573
Epoch: [23]  [140/312]  eta: 0:01:28  lr: 0.003999  min_lr: 0.003999  loss: 3.2804 (3.2008)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [23]  [150/312]  eta: 0:01:22  lr: 0.003998  min_lr: 0.003998  loss: 3.3359 (3.2102)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [23]  [160/312]  eta: 0:01:16  lr: 0.003998  min_lr: 0.003998  loss: 3.4191 (3.2149)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [23]  [170/312]  eta: 0:01:10  lr: 0.003998  min_lr: 0.003998  loss: 3.4376 (3.2309)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [23]  [180/312]  eta: 0:01:05  lr: 0.003998  min_lr: 0.003998  loss: 3.4727 (3.2342)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [23]  [190/312]  eta: 0:01:00  lr: 0.003998  min_lr: 0.003998  loss: 3.2427 (3.2226)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [23]  [200/312]  eta: 0:00:54  lr: 0.003998  min_lr: 0.003998  loss: 2.9118 (3.2099)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [23]  [210/312]  eta: 0:00:49  lr: 0.003998  min_lr: 0.003998  loss: 2.9482 (3.2107)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [23]  [220/312]  eta: 0:00:44  lr: 0.003998  min_lr: 0.003998  loss: 3.1564 (3.2024)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [23]  [230/312]  eta: 0:00:39  lr: 0.003998  min_lr: 0.003998  loss: 3.3463 (3.2073)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [23]  [240/312]  eta: 0:00:34  lr: 0.003998  min_lr: 0.003998  loss: 3.5177 (3.2176)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [23]  [250/312]  eta: 0:00:29  lr: 0.003998  min_lr: 0.003998  loss: 3.4425 (3.2148)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0003  max mem: 42573
Epoch: [23]  [260/312]  eta: 0:00:24  lr: 0.003998  min_lr: 0.003998  loss: 3.3132 (3.2130)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0003  max mem: 42573
Epoch: [23]  [270/312]  eta: 0:00:19  lr: 0.003998  min_lr: 0.003998  loss: 3.2117 (3.2136)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0003  max mem: 42573
Epoch: [23]  [280/312]  eta: 0:00:15  lr: 0.003998  min_lr: 0.003998  loss: 3.1800 (3.2121)  weight_decay: 0.0500 (0.0500)  time: 0.4342  data: 0.0009  max mem: 42573
Epoch: [23]  [290/312]  eta: 0:00:10  lr: 0.003998  min_lr: 0.003998  loss: 3.3037 (3.2155)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0008  max mem: 42573
Epoch: [23]  [300/312]  eta: 0:00:05  lr: 0.003998  min_lr: 0.003998  loss: 2.9960 (3.2040)  weight_decay: 0.0500 (0.0500)  time: 0.4324  data: 0.0001  max mem: 42573
Epoch: [23]  [310/312]  eta: 0:00:00  lr: 0.003998  min_lr: 0.003998  loss: 2.9000 (3.2016)  weight_decay: 0.0500 (0.0500)  time: 0.4323  data: 0.0001  max mem: 42573
Epoch: [23]  [311/312]  eta: 0:00:00  lr: 0.003998  min_lr: 0.003998  loss: 2.9000 (3.2010)  weight_decay: 0.0500 (0.0500)  time: 0.4323  data: 0.0001  max mem: 42573
Epoch: [23] Total time: 0:02:27 (0.4724 s / it)
Averaged stats: lr: 0.003998  min_lr: 0.003998  loss: 2.9000 (3.2114)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:00:43  loss: 1.2945 (1.2945)  acc1: 71.8750 (71.8750)  acc5: 88.5417 (88.5417)  time: 4.8712  data: 4.7617  max mem: 42573
Test:  [8/9]  eta: 0:00:00  loss: 1.6647 (1.5567)  acc1: 61.7188 (62.5920)  acc5: 84.3750 (84.4480)  time: 0.6165  data: 0.5291  max mem: 42573
Test: Total time: 0:00:05 (0.6272 s / it)
* Acc@1 62.860 Acc@5 84.336 loss 1.563
Accuracy of the model on the 50000 test images: 62.9%
Max accuracy: 62.86%
Epoch: [24]  [  0/312]  eta: 0:49:18  lr: 0.003998  min_lr: 0.003998  loss: 2.8064 (2.8064)  weight_decay: 0.0500 (0.0500)  time: 9.4825  data: 8.9915  max mem: 42573
Epoch: [24]  [ 10/312]  eta: 0:07:06  lr: 0.003998  min_lr: 0.003998  loss: 3.2786 (3.2835)  weight_decay: 0.0500 (0.0500)  time: 1.4108  data: 0.8178  max mem: 42573
Epoch: [24]  [ 20/312]  eta: 0:04:36  lr: 0.003998  min_lr: 0.003998  loss: 3.2404 (3.1695)  weight_decay: 0.0500 (0.0500)  time: 0.5189  data: 0.0004  max mem: 42573
Epoch: [24]  [ 30/312]  eta: 0:03:40  lr: 0.003998  min_lr: 0.003998  loss: 3.2439 (3.1737)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0003  max mem: 42573
Epoch: [24]  [ 40/312]  eta: 0:03:09  lr: 0.003998  min_lr: 0.003998  loss: 3.2439 (3.1353)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0003  max mem: 42573
Epoch: [24]  [ 50/312]  eta: 0:02:48  lr: 0.003998  min_lr: 0.003998  loss: 3.0692 (3.1373)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [24]  [ 60/312]  eta: 0:02:33  lr: 0.003998  min_lr: 0.003998  loss: 3.1958 (3.1323)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [24]  [ 70/312]  eta: 0:02:21  lr: 0.003998  min_lr: 0.003998  loss: 3.1655 (3.1507)  weight_decay: 0.0500 (0.0500)  time: 0.4387  data: 0.0004  max mem: 42573
Epoch: [24]  [ 80/312]  eta: 0:02:11  lr: 0.003998  min_lr: 0.003998  loss: 3.1576 (3.1332)  weight_decay: 0.0500 (0.0500)  time: 0.4386  data: 0.0004  max mem: 42573
Epoch: [24]  [ 90/312]  eta: 0:02:02  lr: 0.003998  min_lr: 0.003998  loss: 2.9140 (3.1205)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [24]  [100/312]  eta: 0:01:54  lr: 0.003998  min_lr: 0.003998  loss: 3.2376 (3.1375)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [24]  [110/312]  eta: 0:01:47  lr: 0.003998  min_lr: 0.003998  loss: 3.2304 (3.1320)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [24]  [120/312]  eta: 0:01:40  lr: 0.003998  min_lr: 0.003998  loss: 3.1524 (3.1414)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [24]  [130/312]  eta: 0:01:34  lr: 0.003998  min_lr: 0.003998  loss: 3.1756 (3.1365)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [24]  [140/312]  eta: 0:01:27  lr: 0.003998  min_lr: 0.003998  loss: 2.8422 (3.1102)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [24]  [150/312]  eta: 0:01:21  lr: 0.003997  min_lr: 0.003997  loss: 2.8921 (3.1137)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [24]  [160/312]  eta: 0:01:16  lr: 0.003997  min_lr: 0.003997  loss: 3.2501 (3.1146)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [24]  [170/312]  eta: 0:01:10  lr: 0.003997  min_lr: 0.003997  loss: 3.3861 (3.1239)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [24]  [180/312]  eta: 0:01:05  lr: 0.003997  min_lr: 0.003997  loss: 3.3014 (3.1156)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [24]  [190/312]  eta: 0:00:59  lr: 0.003997  min_lr: 0.003997  loss: 3.3014 (3.1168)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [24]  [200/312]  eta: 0:00:54  lr: 0.003997  min_lr: 0.003997  loss: 3.3807 (3.1322)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [24]  [210/312]  eta: 0:00:49  lr: 0.003997  min_lr: 0.003997  loss: 3.2882 (3.1299)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [24]  [220/312]  eta: 0:00:44  lr: 0.003997  min_lr: 0.003997  loss: 3.1744 (3.1260)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [24]  [230/312]  eta: 0:00:39  lr: 0.003997  min_lr: 0.003997  loss: 3.2789 (3.1286)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [24]  [240/312]  eta: 0:00:34  lr: 0.003997  min_lr: 0.003997  loss: 3.3264 (3.1307)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [24]  [250/312]  eta: 0:00:29  lr: 0.003997  min_lr: 0.003997  loss: 3.0515 (3.1280)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [24]  [260/312]  eta: 0:00:24  lr: 0.003997  min_lr: 0.003997  loss: 3.0488 (3.1285)  weight_decay: 0.0500 (0.0500)  time: 0.4341  data: 0.0004  max mem: 42573
Epoch: [24]  [270/312]  eta: 0:00:19  lr: 0.003997  min_lr: 0.003997  loss: 3.3260 (3.1354)  weight_decay: 0.0500 (0.0500)  time: 0.4341  data: 0.0004  max mem: 42573
Epoch: [24]  [280/312]  eta: 0:00:15  lr: 0.003997  min_lr: 0.003997  loss: 3.3260 (3.1384)  weight_decay: 0.0500 (0.0500)  time: 0.4348  data: 0.0010  max mem: 42573
Epoch: [24]  [290/312]  eta: 0:00:10  lr: 0.003997  min_lr: 0.003997  loss: 3.5354 (3.1519)  weight_decay: 0.0500 (0.0500)  time: 0.4341  data: 0.0008  max mem: 42573
Epoch: [24]  [300/312]  eta: 0:00:05  lr: 0.003997  min_lr: 0.003997  loss: 3.5582 (3.1618)  weight_decay: 0.0500 (0.0500)  time: 0.4325  data: 0.0001  max mem: 42573
Epoch: [24]  [310/312]  eta: 0:00:00  lr: 0.003997  min_lr: 0.003997  loss: 3.5613 (3.1646)  weight_decay: 0.0500 (0.0500)  time: 0.4324  data: 0.0001  max mem: 42573
Epoch: [24]  [311/312]  eta: 0:00:00  lr: 0.003997  min_lr: 0.003997  loss: 3.5613 (3.1665)  weight_decay: 0.0500 (0.0500)  time: 0.4323  data: 0.0001  max mem: 42573
Epoch: [24] Total time: 0:02:27 (0.4715 s / it)
Averaged stats: lr: 0.003997  min_lr: 0.003997  loss: 3.5613 (3.1829)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:00:41  loss: 1.3479 (1.3479)  acc1: 68.7500 (68.7500)  acc5: 87.2396 (87.2396)  time: 4.6387  data: 4.5301  max mem: 42573
Test:  [8/9]  eta: 0:00:00  loss: 1.5889 (1.5746)  acc1: 62.7604 (61.9200)  acc5: 84.1146 (83.9040)  time: 0.5923  data: 0.5034  max mem: 42573
Test: Total time: 0:00:05 (0.6013 s / it)
* Acc@1 62.474 Acc@5 84.366 loss 1.577
Accuracy of the model on the 50000 test images: 62.5%
Max accuracy: 62.86%
Epoch: [25]  [  0/312]  eta: 0:48:51  lr: 0.003997  min_lr: 0.003997  loss: 3.2011 (3.2011)  weight_decay: 0.0500 (0.0500)  time: 9.3964  data: 8.5050  max mem: 42573
Epoch: [25]  [ 10/312]  eta: 0:07:10  lr: 0.003997  min_lr: 0.003997  loss: 2.8038 (2.8242)  weight_decay: 0.0500 (0.0500)  time: 1.4265  data: 0.7816  max mem: 42573
Epoch: [25]  [ 20/312]  eta: 0:04:38  lr: 0.003997  min_lr: 0.003997  loss: 2.9973 (3.0432)  weight_decay: 0.0500 (0.0500)  time: 0.5315  data: 0.0048  max mem: 42573
Epoch: [25]  [ 30/312]  eta: 0:03:41  lr: 0.003997  min_lr: 0.003997  loss: 3.1628 (3.0398)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [25]  [ 40/312]  eta: 0:03:10  lr: 0.003997  min_lr: 0.003997  loss: 3.0518 (3.0688)  weight_decay: 0.0500 (0.0500)  time: 0.4375  data: 0.0004  max mem: 42573
Epoch: [25]  [ 50/312]  eta: 0:02:50  lr: 0.003997  min_lr: 0.003997  loss: 3.0928 (3.0921)  weight_decay: 0.0500 (0.0500)  time: 0.4374  data: 0.0004  max mem: 42573
Epoch: [25]  [ 60/312]  eta: 0:02:34  lr: 0.003997  min_lr: 0.003997  loss: 3.2057 (3.1027)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [25]  [ 70/312]  eta: 0:02:22  lr: 0.003997  min_lr: 0.003997  loss: 3.1728 (3.1073)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [25]  [ 80/312]  eta: 0:02:12  lr: 0.003997  min_lr: 0.003997  loss: 3.1986 (3.1229)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [25]  [ 90/312]  eta: 0:02:03  lr: 0.003996  min_lr: 0.003996  loss: 3.5775 (3.1638)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [25]  [100/312]  eta: 0:01:55  lr: 0.003996  min_lr: 0.003996  loss: 3.5950 (3.1732)  weight_decay: 0.0500 (0.0500)  time: 0.4342  data: 0.0004  max mem: 42573
Epoch: [25]  [110/312]  eta: 0:01:47  lr: 0.003996  min_lr: 0.003996  loss: 2.9814 (3.1427)  weight_decay: 0.0500 (0.0500)  time: 0.4341  data: 0.0004  max mem: 42573
Epoch: [25]  [120/312]  eta: 0:01:40  lr: 0.003996  min_lr: 0.003996  loss: 3.2139 (3.1498)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [25]  [130/312]  eta: 0:01:34  lr: 0.003996  min_lr: 0.003996  loss: 3.2139 (3.1530)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [25]  [140/312]  eta: 0:01:28  lr: 0.003996  min_lr: 0.003996  loss: 3.0920 (3.1552)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0003  max mem: 42573
Epoch: [25]  [150/312]  eta: 0:01:22  lr: 0.003996  min_lr: 0.003996  loss: 3.0223 (3.1487)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [25]  [160/312]  eta: 0:01:16  lr: 0.003996  min_lr: 0.003996  loss: 3.0430 (3.1418)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0003  max mem: 42573
Epoch: [25]  [170/312]  eta: 0:01:10  lr: 0.003996  min_lr: 0.003996  loss: 3.2652 (3.1570)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [25]  [180/312]  eta: 0:01:05  lr: 0.003996  min_lr: 0.003996  loss: 3.2850 (3.1540)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [25]  [190/312]  eta: 0:00:59  lr: 0.003996  min_lr: 0.003996  loss: 3.0755 (3.1534)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [25]  [200/312]  eta: 0:00:54  lr: 0.003996  min_lr: 0.003996  loss: 3.2739 (3.1584)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [25]  [210/312]  eta: 0:00:49  lr: 0.003996  min_lr: 0.003996  loss: 3.3524 (3.1615)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0003  max mem: 42573
Epoch: [25]  [220/312]  eta: 0:00:44  lr: 0.003996  min_lr: 0.003996  loss: 3.2005 (3.1582)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [25]  [230/312]  eta: 0:00:39  lr: 0.003996  min_lr: 0.003996  loss: 3.0355 (3.1508)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [25]  [240/312]  eta: 0:00:34  lr: 0.003996  min_lr: 0.003996  loss: 3.1996 (3.1552)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [25]  [250/312]  eta: 0:00:29  lr: 0.003996  min_lr: 0.003996  loss: 3.3114 (3.1606)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [25]  [260/312]  eta: 0:00:24  lr: 0.003996  min_lr: 0.003996  loss: 3.2032 (3.1548)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [25]  [270/312]  eta: 0:00:19  lr: 0.003996  min_lr: 0.003996  loss: 2.8873 (3.1512)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [25]  [280/312]  eta: 0:00:15  lr: 0.003996  min_lr: 0.003996  loss: 3.1885 (3.1499)  weight_decay: 0.0500 (0.0500)  time: 0.4343  data: 0.0009  max mem: 42573
Epoch: [25]  [290/312]  eta: 0:00:10  lr: 0.003996  min_lr: 0.003996  loss: 3.4391 (3.1563)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0008  max mem: 42573
Epoch: [25]  [300/312]  eta: 0:00:05  lr: 0.003996  min_lr: 0.003996  loss: 3.3177 (3.1569)  weight_decay: 0.0500 (0.0500)  time: 0.4323  data: 0.0001  max mem: 42573
Epoch: [25]  [310/312]  eta: 0:00:00  lr: 0.003995  min_lr: 0.003995  loss: 3.1124 (3.1549)  weight_decay: 0.0500 (0.0500)  time: 0.4322  data: 0.0001  max mem: 42573
Epoch: [25]  [311/312]  eta: 0:00:00  lr: 0.003995  min_lr: 0.003995  loss: 3.1048 (3.1514)  weight_decay: 0.0500 (0.0500)  time: 0.4322  data: 0.0001  max mem: 42573
Epoch: [25] Total time: 0:02:27 (0.4718 s / it)
Averaged stats: lr: 0.003995  min_lr: 0.003995  loss: 3.1048 (3.1588)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:00:43  loss: 1.2077 (1.2077)  acc1: 70.5729 (70.5729)  acc5: 90.8854 (90.8854)  time: 4.8541  data: 4.7448  max mem: 42573
Test:  [8/9]  eta: 0:00:00  loss: 1.5484 (1.4716)  acc1: 65.1042 (63.8400)  acc5: 85.6771 (86.0480)  time: 0.6160  data: 0.5272  max mem: 42573
Test: Total time: 0:00:05 (0.6376 s / it)
* Acc@1 64.046 Acc@5 85.446 loss 1.490
Accuracy of the model on the 50000 test images: 64.0%
Max accuracy: 64.05%
Epoch: [26]  [  0/312]  eta: 0:48:53  lr: 0.003995  min_lr: 0.003995  loss: 3.6490 (3.6490)  weight_decay: 0.0500 (0.0500)  time: 9.4018  data: 8.7620  max mem: 42573
Epoch: [26]  [ 10/312]  eta: 0:07:23  lr: 0.003995  min_lr: 0.003995  loss: 3.2493 (3.1562)  weight_decay: 0.0500 (0.0500)  time: 1.4684  data: 0.7970  max mem: 42573
Epoch: [26]  [ 20/312]  eta: 0:04:44  lr: 0.003995  min_lr: 0.003995  loss: 3.0524 (3.0617)  weight_decay: 0.0500 (0.0500)  time: 0.5540  data: 0.0004  max mem: 42573
Epoch: [26]  [ 30/312]  eta: 0:03:45  lr: 0.003995  min_lr: 0.003995  loss: 3.0120 (3.0883)  weight_decay: 0.0500 (0.0500)  time: 0.4330  data: 0.0004  max mem: 42573
Epoch: [26]  [ 40/312]  eta: 0:03:13  lr: 0.003995  min_lr: 0.003995  loss: 3.2065 (3.0804)  weight_decay: 0.0500 (0.0500)  time: 0.4361  data: 0.0005  max mem: 42573
Epoch: [26]  [ 50/312]  eta: 0:02:52  lr: 0.003995  min_lr: 0.003995  loss: 2.9993 (3.0543)  weight_decay: 0.0500 (0.0500)  time: 0.4363  data: 0.0004  max mem: 42573
Epoch: [26]  [ 60/312]  eta: 0:02:36  lr: 0.003995  min_lr: 0.003995  loss: 3.1551 (3.1010)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [26]  [ 70/312]  eta: 0:02:23  lr: 0.003995  min_lr: 0.003995  loss: 3.2503 (3.0755)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [26]  [ 80/312]  eta: 0:02:13  lr: 0.003995  min_lr: 0.003995  loss: 2.8716 (3.0403)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [26]  [ 90/312]  eta: 0:02:04  lr: 0.003995  min_lr: 0.003995  loss: 3.1198 (3.0568)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [26]  [100/312]  eta: 0:01:55  lr: 0.003995  min_lr: 0.003995  loss: 3.1975 (3.0680)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0004  max mem: 42573
Epoch: [26]  [110/312]  eta: 0:01:48  lr: 0.003995  min_lr: 0.003995  loss: 3.1800 (3.0624)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [26]  [120/312]  eta: 0:01:41  lr: 0.003995  min_lr: 0.003995  loss: 2.9935 (3.0687)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [26]  [130/312]  eta: 0:01:34  lr: 0.003995  min_lr: 0.003995  loss: 3.3313 (3.0651)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [26]  [140/312]  eta: 0:01:28  lr: 0.003995  min_lr: 0.003995  loss: 3.4547 (3.0787)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [26]  [150/312]  eta: 0:01:22  lr: 0.003995  min_lr: 0.003995  loss: 3.4311 (3.0797)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [26]  [160/312]  eta: 0:01:16  lr: 0.003995  min_lr: 0.003995  loss: 3.1339 (3.0865)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [26]  [170/312]  eta: 0:01:11  lr: 0.003995  min_lr: 0.003995  loss: 3.1937 (3.0941)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [26]  [180/312]  eta: 0:01:05  lr: 0.003995  min_lr: 0.003995  loss: 3.4352 (3.1084)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [26]  [190/312]  eta: 0:01:00  lr: 0.003995  min_lr: 0.003995  loss: 3.2487 (3.0959)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [26]  [200/312]  eta: 0:00:54  lr: 0.003994  min_lr: 0.003994  loss: 2.9767 (3.0984)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [26]  [210/312]  eta: 0:00:49  lr: 0.003994  min_lr: 0.003994  loss: 3.2031 (3.1047)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [26]  [220/312]  eta: 0:00:44  lr: 0.003994  min_lr: 0.003994  loss: 3.3713 (3.1161)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0004  max mem: 42573
Epoch: [26]  [230/312]  eta: 0:00:39  lr: 0.003994  min_lr: 0.003994  loss: 2.9931 (3.1001)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0004  max mem: 42573
Epoch: [26]  [240/312]  eta: 0:00:34  lr: 0.003994  min_lr: 0.003994  loss: 2.7464 (3.0940)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [26]  [250/312]  eta: 0:00:29  lr: 0.003994  min_lr: 0.003994  loss: 3.1522 (3.0979)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [26]  [260/312]  eta: 0:00:24  lr: 0.003994  min_lr: 0.003994  loss: 3.1522 (3.0962)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [26]  [270/312]  eta: 0:00:19  lr: 0.003994  min_lr: 0.003994  loss: 3.1193 (3.0945)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [26]  [280/312]  eta: 0:00:15  lr: 0.003994  min_lr: 0.003994  loss: 3.1536 (3.0928)  weight_decay: 0.0500 (0.0500)  time: 0.4343  data: 0.0010  max mem: 42573
Epoch: [26]  [290/312]  eta: 0:00:10  lr: 0.003994  min_lr: 0.003994  loss: 3.1536 (3.0906)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0008  max mem: 42573
Epoch: [26]  [300/312]  eta: 0:00:05  lr: 0.003994  min_lr: 0.003994  loss: 3.1070 (3.0930)  weight_decay: 0.0500 (0.0500)  time: 0.4324  data: 0.0001  max mem: 42573
Epoch: [26]  [310/312]  eta: 0:00:00  lr: 0.003994  min_lr: 0.003994  loss: 2.9420 (3.0922)  weight_decay: 0.0500 (0.0500)  time: 0.4324  data: 0.0001  max mem: 42573
Epoch: [26]  [311/312]  eta: 0:00:00  lr: 0.003994  min_lr: 0.003994  loss: 2.9385 (3.0894)  weight_decay: 0.0500 (0.0500)  time: 0.4324  data: 0.0001  max mem: 42573
Epoch: [26] Total time: 0:02:27 (0.4733 s / it)
Averaged stats: lr: 0.003994  min_lr: 0.003994  loss: 2.9385 (3.1329)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:00:43  loss: 1.1569 (1.1569)  acc1: 71.8750 (71.8750)  acc5: 89.3229 (89.3229)  time: 4.8045  data: 4.6955  max mem: 42573
Test:  [8/9]  eta: 0:00:00  loss: 1.5615 (1.4425)  acc1: 63.2812 (64.3200)  acc5: 85.1562 (85.5680)  time: 0.6111  data: 0.5218  max mem: 42573
Test: Total time: 0:00:05 (0.6298 s / it)
* Acc@1 64.264 Acc@5 85.600 loss 1.475
Accuracy of the model on the 50000 test images: 64.3%
Max accuracy: 64.26%
Epoch: [27]  [  0/312]  eta: 0:48:52  lr: 0.003994  min_lr: 0.003994  loss: 3.6736 (3.6736)  weight_decay: 0.0500 (0.0500)  time: 9.3975  data: 6.2012  max mem: 42573
Epoch: [27]  [ 10/312]  eta: 0:07:26  lr: 0.003994  min_lr: 0.003994  loss: 3.1272 (3.1981)  weight_decay: 0.0500 (0.0500)  time: 1.4800  data: 0.6798  max mem: 42573
Epoch: [27]  [ 20/312]  eta: 0:04:46  lr: 0.003994  min_lr: 0.003994  loss: 3.1272 (3.2101)  weight_decay: 0.0500 (0.0500)  time: 0.5608  data: 0.0640  max mem: 42573
Epoch: [27]  [ 30/312]  eta: 0:03:46  lr: 0.003994  min_lr: 0.003994  loss: 3.1325 (3.1298)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [27]  [ 40/312]  eta: 0:03:14  lr: 0.003994  min_lr: 0.003994  loss: 3.1111 (3.1116)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [27]  [ 50/312]  eta: 0:02:52  lr: 0.003994  min_lr: 0.003994  loss: 3.3255 (3.1341)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [27]  [ 60/312]  eta: 0:02:36  lr: 0.003993  min_lr: 0.003993  loss: 3.2422 (3.1100)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [27]  [ 70/312]  eta: 0:02:24  lr: 0.003993  min_lr: 0.003993  loss: 3.2030 (3.1380)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [27]  [ 80/312]  eta: 0:02:13  lr: 0.003993  min_lr: 0.003993  loss: 3.2776 (3.1357)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0004  max mem: 42573
Epoch: [27]  [ 90/312]  eta: 0:02:04  lr: 0.003993  min_lr: 0.003993  loss: 3.2112 (3.1302)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0004  max mem: 42573
Epoch: [27]  [100/312]  eta: 0:01:56  lr: 0.003993  min_lr: 0.003993  loss: 3.2313 (3.1450)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [27]  [110/312]  eta: 0:01:48  lr: 0.003993  min_lr: 0.003993  loss: 3.2684 (3.1548)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [27]  [120/312]  eta: 0:01:41  lr: 0.003993  min_lr: 0.003993  loss: 3.0304 (3.1280)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [27]  [130/312]  eta: 0:01:34  lr: 0.003993  min_lr: 0.003993  loss: 2.9301 (3.1230)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [27]  [140/312]  eta: 0:01:28  lr: 0.003993  min_lr: 0.003993  loss: 3.1348 (3.1283)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [27]  [150/312]  eta: 0:01:22  lr: 0.003993  min_lr: 0.003993  loss: 3.1395 (3.1322)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [27]  [160/312]  eta: 0:01:16  lr: 0.003993  min_lr: 0.003993  loss: 3.2095 (3.1299)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [27]  [170/312]  eta: 0:01:11  lr: 0.003993  min_lr: 0.003993  loss: 2.9430 (3.1121)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [27]  [180/312]  eta: 0:01:05  lr: 0.003993  min_lr: 0.003993  loss: 2.9410 (3.1137)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [27]  [190/312]  eta: 0:01:00  lr: 0.003993  min_lr: 0.003993  loss: 2.9890 (3.1102)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [27]  [200/312]  eta: 0:00:54  lr: 0.003993  min_lr: 0.003993  loss: 2.9948 (3.1070)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [27]  [210/312]  eta: 0:00:49  lr: 0.003993  min_lr: 0.003993  loss: 3.0064 (3.1037)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [27]  [220/312]  eta: 0:00:44  lr: 0.003993  min_lr: 0.003993  loss: 3.0576 (3.1048)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0005  max mem: 42573
Epoch: [27]  [230/312]  eta: 0:00:39  lr: 0.003992  min_lr: 0.003992  loss: 2.8929 (3.0971)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [27]  [240/312]  eta: 0:00:34  lr: 0.003992  min_lr: 0.003992  loss: 3.0268 (3.0959)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [27]  [250/312]  eta: 0:00:29  lr: 0.003992  min_lr: 0.003992  loss: 3.0268 (3.0853)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [27]  [260/312]  eta: 0:00:24  lr: 0.003992  min_lr: 0.003992  loss: 3.1203 (3.0818)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [27]  [270/312]  eta: 0:00:20  lr: 0.003992  min_lr: 0.003992  loss: 3.3174 (3.0905)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [27]  [280/312]  eta: 0:00:15  lr: 0.003992  min_lr: 0.003992  loss: 3.4140 (3.0921)  weight_decay: 0.0500 (0.0500)  time: 0.4345  data: 0.0010  max mem: 42573
Epoch: [27]  [290/312]  eta: 0:00:10  lr: 0.003992  min_lr: 0.003992  loss: 3.2801 (3.0985)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0008  max mem: 42573
Epoch: [27]  [300/312]  eta: 0:00:05  lr: 0.003992  min_lr: 0.003992  loss: 3.2622 (3.0977)  weight_decay: 0.0500 (0.0500)  time: 0.4325  data: 0.0001  max mem: 42573
Epoch: [27]  [310/312]  eta: 0:00:00  lr: 0.003992  min_lr: 0.003992  loss: 3.1369 (3.0944)  weight_decay: 0.0500 (0.0500)  time: 0.4325  data: 0.0001  max mem: 42573
Epoch: [27]  [311/312]  eta: 0:00:00  lr: 0.003992  min_lr: 0.003992  loss: 3.1137 (3.0945)  weight_decay: 0.0500 (0.0500)  time: 0.4324  data: 0.0001  max mem: 42573
Epoch: [27] Total time: 0:02:27 (0.4738 s / it)
Averaged stats: lr: 0.003992  min_lr: 0.003992  loss: 3.1137 (3.1246)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:00:44  loss: 1.2214 (1.2214)  acc1: 72.1354 (72.1354)  acc5: 89.8438 (89.8438)  time: 4.9111  data: 4.8011  max mem: 42573
Test:  [8/9]  eta: 0:00:00  loss: 1.7531 (1.5530)  acc1: 61.4583 (62.2080)  acc5: 83.5938 (84.5440)  time: 0.6265  data: 0.5392  max mem: 42573
Test: Total time: 0:00:05 (0.6475 s / it)
* Acc@1 62.792 Acc@5 84.478 loss 1.565
Accuracy of the model on the 50000 test images: 62.8%
Max accuracy: 64.26%
Epoch: [28]  [  0/312]  eta: 0:54:48  lr: 0.003992  min_lr: 0.003992  loss: 3.3757 (3.3757)  weight_decay: 0.0500 (0.0500)  time: 10.5415  data: 7.6722  max mem: 42573
Epoch: [28]  [ 10/312]  eta: 0:07:43  lr: 0.003992  min_lr: 0.003992  loss: 3.2432 (3.1175)  weight_decay: 0.0500 (0.0500)  time: 1.5338  data: 0.7056  max mem: 42573
Epoch: [28]  [ 20/312]  eta: 0:04:54  lr: 0.003992  min_lr: 0.003992  loss: 2.9854 (3.0761)  weight_decay: 0.0500 (0.0500)  time: 0.5331  data: 0.0046  max mem: 42573
Epoch: [28]  [ 30/312]  eta: 0:03:52  lr: 0.003992  min_lr: 0.003992  loss: 2.9175 (3.0663)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [28]  [ 40/312]  eta: 0:03:18  lr: 0.003992  min_lr: 0.003992  loss: 2.9175 (3.0574)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [28]  [ 50/312]  eta: 0:02:55  lr: 0.003992  min_lr: 0.003992  loss: 3.0376 (3.0376)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [28]  [ 60/312]  eta: 0:02:39  lr: 0.003992  min_lr: 0.003992  loss: 3.1341 (3.0502)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [28]  [ 70/312]  eta: 0:02:26  lr: 0.003991  min_lr: 0.003991  loss: 3.1341 (3.0424)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [28]  [ 80/312]  eta: 0:02:15  lr: 0.003991  min_lr: 0.003991  loss: 3.1802 (3.0550)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0004  max mem: 42573
Epoch: [28]  [ 90/312]  eta: 0:02:05  lr: 0.003991  min_lr: 0.003991  loss: 3.2052 (3.0588)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [28]  [100/312]  eta: 0:01:57  lr: 0.003991  min_lr: 0.003991  loss: 2.9952 (3.0681)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0004  max mem: 42573
Epoch: [28]  [110/312]  eta: 0:01:49  lr: 0.003991  min_lr: 0.003991  loss: 3.1869 (3.0687)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0004  max mem: 42573
Epoch: [28]  [120/312]  eta: 0:01:42  lr: 0.003991  min_lr: 0.003991  loss: 2.7548 (3.0523)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0004  max mem: 42573
Epoch: [28]  [130/312]  eta: 0:01:35  lr: 0.003991  min_lr: 0.003991  loss: 2.7778 (3.0528)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [28]  [140/312]  eta: 0:01:29  lr: 0.003991  min_lr: 0.003991  loss: 3.2466 (3.0558)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [28]  [150/312]  eta: 0:01:23  lr: 0.003991  min_lr: 0.003991  loss: 3.2466 (3.0684)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [28]  [160/312]  eta: 0:01:17  lr: 0.003991  min_lr: 0.003991  loss: 3.3203 (3.0856)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [28]  [170/312]  eta: 0:01:11  lr: 0.003991  min_lr: 0.003991  loss: 3.2836 (3.0806)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [28]  [180/312]  eta: 0:01:06  lr: 0.003991  min_lr: 0.003991  loss: 3.0094 (3.0853)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0003  max mem: 42573
Epoch: [28]  [190/312]  eta: 0:01:00  lr: 0.003991  min_lr: 0.003991  loss: 2.9964 (3.0795)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0003  max mem: 42573
Epoch: [28]  [200/312]  eta: 0:00:55  lr: 0.003991  min_lr: 0.003991  loss: 2.9470 (3.0761)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [28]  [210/312]  eta: 0:00:50  lr: 0.003991  min_lr: 0.003991  loss: 3.1689 (3.0777)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [28]  [220/312]  eta: 0:00:44  lr: 0.003990  min_lr: 0.003990  loss: 3.1689 (3.0752)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0005  max mem: 42573
Epoch: [28]  [230/312]  eta: 0:00:39  lr: 0.003990  min_lr: 0.003990  loss: 3.1475 (3.0800)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [28]  [240/312]  eta: 0:00:34  lr: 0.003990  min_lr: 0.003990  loss: 3.1409 (3.0740)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [28]  [250/312]  eta: 0:00:29  lr: 0.003990  min_lr: 0.003990  loss: 3.1473 (3.0852)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [28]  [260/312]  eta: 0:00:24  lr: 0.003990  min_lr: 0.003990  loss: 3.3370 (3.0818)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0005  max mem: 42573
Epoch: [28]  [270/312]  eta: 0:00:20  lr: 0.003990  min_lr: 0.003990  loss: 3.0176 (3.0833)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [28]  [280/312]  eta: 0:00:15  lr: 0.003990  min_lr: 0.003990  loss: 3.1047 (3.0888)  weight_decay: 0.0500 (0.0500)  time: 0.4349  data: 0.0010  max mem: 42573
Epoch: [28]  [290/312]  eta: 0:00:10  lr: 0.003990  min_lr: 0.003990  loss: 3.1818 (3.0895)  weight_decay: 0.0500 (0.0500)  time: 0.4342  data: 0.0008  max mem: 42573
Epoch: [28]  [300/312]  eta: 0:00:05  lr: 0.003990  min_lr: 0.003990  loss: 3.1818 (3.0905)  weight_decay: 0.0500 (0.0500)  time: 0.4324  data: 0.0001  max mem: 42573
Epoch: [28]  [310/312]  eta: 0:00:00  lr: 0.003990  min_lr: 0.003990  loss: 2.9378 (3.0852)  weight_decay: 0.0500 (0.0500)  time: 0.4324  data: 0.0001  max mem: 42573
Epoch: [28]  [311/312]  eta: 0:00:00  lr: 0.003990  min_lr: 0.003990  loss: 2.9378 (3.0871)  weight_decay: 0.0500 (0.0500)  time: 0.4324  data: 0.0001  max mem: 42573
Epoch: [28] Total time: 0:02:28 (0.4758 s / it)
Averaged stats: lr: 0.003990  min_lr: 0.003990  loss: 2.9378 (3.0854)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:00:42  loss: 1.1949 (1.1949)  acc1: 72.3958 (72.3958)  acc5: 89.5833 (89.5833)  time: 4.7525  data: 4.6430  max mem: 42573
Test:  [8/9]  eta: 0:00:00  loss: 1.5792 (1.4739)  acc1: 63.8021 (64.7360)  acc5: 85.9375 (85.4720)  time: 0.6054  data: 0.5160  max mem: 42573
Test: Total time: 0:00:05 (0.6278 s / it)
* Acc@1 64.780 Acc@5 85.766 loss 1.474
Accuracy of the model on the 50000 test images: 64.8%
Max accuracy: 64.78%
Epoch: [29]  [  0/312]  eta: 0:48:52  lr: 0.003990  min_lr: 0.003990  loss: 3.0676 (3.0676)  weight_decay: 0.0500 (0.0500)  time: 9.3990  data: 6.9163  max mem: 42573
Epoch: [29]  [ 10/312]  eta: 0:07:18  lr: 0.003990  min_lr: 0.003990  loss: 3.0676 (2.9543)  weight_decay: 0.0500 (0.0500)  time: 1.4524  data: 0.6291  max mem: 42573
Epoch: [29]  [ 20/312]  eta: 0:04:43  lr: 0.003990  min_lr: 0.003990  loss: 3.2841 (3.1318)  weight_decay: 0.0500 (0.0500)  time: 0.5505  data: 0.0004  max mem: 42573
Epoch: [29]  [ 30/312]  eta: 0:03:45  lr: 0.003990  min_lr: 0.003990  loss: 3.2841 (3.1297)  weight_decay: 0.0500 (0.0500)  time: 0.4382  data: 0.0004  max mem: 42573
Epoch: [29]  [ 40/312]  eta: 0:03:12  lr: 0.003990  min_lr: 0.003990  loss: 3.0376 (3.1280)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [29]  [ 50/312]  eta: 0:02:51  lr: 0.003989  min_lr: 0.003989  loss: 3.0210 (3.0863)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [29]  [ 60/312]  eta: 0:02:35  lr: 0.003989  min_lr: 0.003989  loss: 2.8589 (3.0548)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [29]  [ 70/312]  eta: 0:02:23  lr: 0.003989  min_lr: 0.003989  loss: 2.9822 (3.0798)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [29]  [ 80/312]  eta: 0:02:12  lr: 0.003989  min_lr: 0.003989  loss: 3.1992 (3.0878)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [29]  [ 90/312]  eta: 0:02:03  lr: 0.003989  min_lr: 0.003989  loss: 3.1992 (3.0970)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0004  max mem: 42573
Epoch: [29]  [100/312]  eta: 0:01:55  lr: 0.003989  min_lr: 0.003989  loss: 3.1946 (3.1002)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [29]  [110/312]  eta: 0:01:48  lr: 0.003989  min_lr: 0.003989  loss: 3.1946 (3.1023)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [29]  [120/312]  eta: 0:01:41  lr: 0.003989  min_lr: 0.003989  loss: 3.2300 (3.1144)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [29]  [130/312]  eta: 0:01:34  lr: 0.003989  min_lr: 0.003989  loss: 3.2556 (3.1194)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [29]  [140/312]  eta: 0:01:28  lr: 0.003989  min_lr: 0.003989  loss: 3.2025 (3.1178)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [29]  [150/312]  eta: 0:01:22  lr: 0.003989  min_lr: 0.003989  loss: 3.0595 (3.1155)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [29]  [160/312]  eta: 0:01:16  lr: 0.003989  min_lr: 0.003989  loss: 3.0508 (3.1028)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [29]  [170/312]  eta: 0:01:10  lr: 0.003989  min_lr: 0.003989  loss: 3.2710 (3.1140)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0004  max mem: 42573
Epoch: [29]  [180/312]  eta: 0:01:05  lr: 0.003988  min_lr: 0.003988  loss: 3.2668 (3.1143)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [29]  [190/312]  eta: 0:01:00  lr: 0.003988  min_lr: 0.003988  loss: 3.1778 (3.1108)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [29]  [200/312]  eta: 0:00:54  lr: 0.003988  min_lr: 0.003988  loss: 3.1878 (3.1146)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [29]  [210/312]  eta: 0:00:49  lr: 0.003988  min_lr: 0.003988  loss: 3.2881 (3.1110)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0004  max mem: 42573
Epoch: [29]  [220/312]  eta: 0:00:44  lr: 0.003988  min_lr: 0.003988  loss: 3.2591 (3.1146)  weight_decay: 0.0500 (0.0500)  time: 0.4341  data: 0.0004  max mem: 42573
Epoch: [29]  [230/312]  eta: 0:00:39  lr: 0.003988  min_lr: 0.003988  loss: 3.1688 (3.1108)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [29]  [240/312]  eta: 0:00:34  lr: 0.003988  min_lr: 0.003988  loss: 2.9936 (3.0986)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0003  max mem: 42573
Epoch: [29]  [250/312]  eta: 0:00:29  lr: 0.003988  min_lr: 0.003988  loss: 3.0324 (3.1012)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0003  max mem: 42573
Epoch: [29]  [260/312]  eta: 0:00:24  lr: 0.003988  min_lr: 0.003988  loss: 3.1103 (3.0894)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [29]  [270/312]  eta: 0:00:19  lr: 0.003988  min_lr: 0.003988  loss: 2.7686 (3.0855)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [29]  [280/312]  eta: 0:00:15  lr: 0.003988  min_lr: 0.003988  loss: 3.2792 (3.0905)  weight_decay: 0.0500 (0.0500)  time: 0.4351  data: 0.0011  max mem: 42573
Epoch: [29]  [290/312]  eta: 0:00:10  lr: 0.003988  min_lr: 0.003988  loss: 3.0603 (3.0858)  weight_decay: 0.0500 (0.0500)  time: 0.4343  data: 0.0009  max mem: 42573
Epoch: [29]  [300/312]  eta: 0:00:05  lr: 0.003988  min_lr: 0.003988  loss: 3.0091 (3.0905)  weight_decay: 0.0500 (0.0500)  time: 0.4325  data: 0.0001  max mem: 42573
Epoch: [29]  [310/312]  eta: 0:00:00  lr: 0.003987  min_lr: 0.003987  loss: 3.1530 (3.0894)  weight_decay: 0.0500 (0.0500)  time: 0.4534  data: 0.0001  max mem: 42573
Epoch: [29]  [311/312]  eta: 0:00:00  lr: 0.003987  min_lr: 0.003987  loss: 3.0993 (3.0895)  weight_decay: 0.0500 (0.0500)  time: 0.4535  data: 0.0001  max mem: 42573
Epoch: [29] Total time: 0:02:28 (0.4744 s / it)
Averaged stats: lr: 0.003987  min_lr: 0.003987  loss: 3.0993 (3.0725)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:00:42  loss: 1.2174 (1.2174)  acc1: 72.1354 (72.1354)  acc5: 88.8021 (88.8021)  time: 4.6798  data: 4.5703  max mem: 42573
Test:  [8/9]  eta: 0:00:00  loss: 1.5416 (1.4384)  acc1: 64.5833 (65.9200)  acc5: 85.6771 (85.5680)  time: 0.5956  data: 0.5079  max mem: 42573
Test: Total time: 0:00:05 (0.6207 s / it)
* Acc@1 64.938 Acc@5 85.848 loss 1.483
Accuracy of the model on the 50000 test images: 64.9%
Max accuracy: 64.94%
Epoch: [30]  [  0/312]  eta: 0:48:23  lr: 0.003987  min_lr: 0.003987  loss: 3.4757 (3.4757)  weight_decay: 0.0500 (0.0500)  time: 9.3057  data: 7.4508  max mem: 42573
Epoch: [30]  [ 10/312]  eta: 0:07:09  lr: 0.003987  min_lr: 0.003987  loss: 3.2213 (3.1884)  weight_decay: 0.0500 (0.0500)  time: 1.4228  data: 0.7714  max mem: 42573
Epoch: [30]  [ 20/312]  eta: 0:04:37  lr: 0.003987  min_lr: 0.003987  loss: 3.0887 (3.1613)  weight_decay: 0.0500 (0.0500)  time: 0.5340  data: 0.0519  max mem: 42573
Epoch: [30]  [ 30/312]  eta: 0:03:41  lr: 0.003987  min_lr: 0.003987  loss: 3.2220 (3.1519)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [30]  [ 40/312]  eta: 0:03:10  lr: 0.003987  min_lr: 0.003987  loss: 3.1765 (3.1331)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [30]  [ 50/312]  eta: 0:02:49  lr: 0.003987  min_lr: 0.003987  loss: 3.1765 (3.1298)  weight_decay: 0.0500 (0.0500)  time: 0.4343  data: 0.0004  max mem: 42573
Epoch: [30]  [ 60/312]  eta: 0:02:34  lr: 0.003987  min_lr: 0.003987  loss: 3.2785 (3.1363)  weight_decay: 0.0500 (0.0500)  time: 0.4342  data: 0.0004  max mem: 42573
Epoch: [30]  [ 70/312]  eta: 0:02:22  lr: 0.003987  min_lr: 0.003987  loss: 2.9645 (3.1030)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [30]  [ 80/312]  eta: 0:02:11  lr: 0.003987  min_lr: 0.003987  loss: 2.9240 (3.0986)  weight_decay: 0.0500 (0.0500)  time: 0.4345  data: 0.0004  max mem: 42573
Epoch: [30]  [ 90/312]  eta: 0:02:02  lr: 0.003987  min_lr: 0.003987  loss: 3.1294 (3.0955)  weight_decay: 0.0500 (0.0500)  time: 0.4343  data: 0.0004  max mem: 42573
Epoch: [30]  [100/312]  eta: 0:01:54  lr: 0.003987  min_lr: 0.003987  loss: 3.1129 (3.0920)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0004  max mem: 42573
Epoch: [30]  [110/312]  eta: 0:01:47  lr: 0.003987  min_lr: 0.003987  loss: 3.0941 (3.0980)  weight_decay: 0.0500 (0.0500)  time: 0.4343  data: 0.0004  max mem: 42573
Epoch: [30]  [120/312]  eta: 0:01:40  lr: 0.003986  min_lr: 0.003986  loss: 3.0941 (3.0912)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0004  max mem: 42573
Epoch: [30]  [130/312]  eta: 0:01:34  lr: 0.003986  min_lr: 0.003986  loss: 2.9839 (3.0801)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [30]  [140/312]  eta: 0:01:27  lr: 0.003986  min_lr: 0.003986  loss: 3.1525 (3.0753)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [30]  [150/312]  eta: 0:01:21  lr: 0.003986  min_lr: 0.003986  loss: 3.1792 (3.0721)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [30]  [160/312]  eta: 0:01:16  lr: 0.003986  min_lr: 0.003986  loss: 3.0970 (3.0621)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [30]  [170/312]  eta: 0:01:10  lr: 0.003986  min_lr: 0.003986  loss: 2.9887 (3.0523)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [30]  [180/312]  eta: 0:01:05  lr: 0.003986  min_lr: 0.003986  loss: 3.2031 (3.0640)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [30]  [190/312]  eta: 0:00:59  lr: 0.003986  min_lr: 0.003986  loss: 3.2247 (3.0701)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0004  max mem: 42573
Epoch: [30]  [200/312]  eta: 0:00:54  lr: 0.003986  min_lr: 0.003986  loss: 3.2221 (3.0760)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [30]  [210/312]  eta: 0:00:49  lr: 0.003986  min_lr: 0.003986  loss: 3.1088 (3.0695)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [30]  [220/312]  eta: 0:00:44  lr: 0.003986  min_lr: 0.003986  loss: 2.8464 (3.0650)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [30]  [230/312]  eta: 0:00:39  lr: 0.003986  min_lr: 0.003986  loss: 3.3169 (3.0809)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [30]  [240/312]  eta: 0:00:34  lr: 0.003985  min_lr: 0.003985  loss: 3.2989 (3.0752)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0003  max mem: 42573
Epoch: [30]  [250/312]  eta: 0:00:29  lr: 0.003985  min_lr: 0.003985  loss: 3.1522 (3.0775)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [30]  [260/312]  eta: 0:00:24  lr: 0.003985  min_lr: 0.003985  loss: 3.1516 (3.0735)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [30]  [270/312]  eta: 0:00:19  lr: 0.003985  min_lr: 0.003985  loss: 2.8632 (3.0597)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0003  max mem: 42573
Epoch: [30]  [280/312]  eta: 0:00:15  lr: 0.003985  min_lr: 0.003985  loss: 2.8632 (3.0564)  weight_decay: 0.0500 (0.0500)  time: 0.4345  data: 0.0009  max mem: 42573
Epoch: [30]  [290/312]  eta: 0:00:10  lr: 0.003985  min_lr: 0.003985  loss: 3.2227 (3.0619)  weight_decay: 0.0500 (0.0500)  time: 0.4408  data: 0.0008  max mem: 42573
Epoch: [30]  [300/312]  eta: 0:00:05  lr: 0.003985  min_lr: 0.003985  loss: 3.2641 (3.0639)  weight_decay: 0.0500 (0.0500)  time: 0.4394  data: 0.0001  max mem: 42573
Epoch: [30]  [310/312]  eta: 0:00:00  lr: 0.003985  min_lr: 0.003985  loss: 2.9666 (3.0581)  weight_decay: 0.0500 (0.0500)  time: 0.4323  data: 0.0001  max mem: 42573
Epoch: [30]  [311/312]  eta: 0:00:00  lr: 0.003985  min_lr: 0.003985  loss: 2.9032 (3.0555)  weight_decay: 0.0500 (0.0500)  time: 0.4323  data: 0.0001  max mem: 42573
Epoch: [30] Total time: 0:02:27 (0.4722 s / it)
Averaged stats: lr: 0.003985  min_lr: 0.003985  loss: 2.9032 (3.0399)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:00:43  loss: 1.1372 (1.1372)  acc1: 73.1771 (73.1771)  acc5: 91.1458 (91.1458)  time: 4.8463  data: 4.7370  max mem: 42573
Test:  [8/9]  eta: 0:00:00  loss: 1.5691 (1.4741)  acc1: 65.8854 (64.3520)  acc5: 85.1562 (85.8240)  time: 0.6153  data: 0.5264  max mem: 42573
Test: Total time: 0:00:05 (0.6460 s / it)
* Acc@1 64.694 Acc@5 86.010 loss 1.463
Accuracy of the model on the 50000 test images: 64.7%
Max accuracy: 64.94%
Epoch: [31]  [  0/312]  eta: 0:50:26  lr: 0.003985  min_lr: 0.003985  loss: 2.3474 (2.3474)  weight_decay: 0.0500 (0.0500)  time: 9.7000  data: 6.5443  max mem: 42573
Epoch: [31]  [ 10/312]  eta: 0:07:11  lr: 0.003985  min_lr: 0.003985  loss: 3.1801 (2.9463)  weight_decay: 0.0500 (0.0500)  time: 1.4297  data: 0.7268  max mem: 42573
Epoch: [31]  [ 20/312]  eta: 0:04:38  lr: 0.003985  min_lr: 0.003985  loss: 3.1801 (2.9259)  weight_decay: 0.0500 (0.0500)  time: 0.5181  data: 0.0727  max mem: 42573
Epoch: [31]  [ 30/312]  eta: 0:03:41  lr: 0.003985  min_lr: 0.003985  loss: 3.0489 (2.9753)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0003  max mem: 42573
Epoch: [31]  [ 40/312]  eta: 0:03:10  lr: 0.003984  min_lr: 0.003984  loss: 3.2263 (3.0011)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0003  max mem: 42573
Epoch: [31]  [ 50/312]  eta: 0:02:49  lr: 0.003984  min_lr: 0.003984  loss: 3.1008 (3.0158)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0004  max mem: 42573
Epoch: [31]  [ 60/312]  eta: 0:02:34  lr: 0.003984  min_lr: 0.003984  loss: 3.1307 (3.0463)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [31]  [ 70/312]  eta: 0:02:22  lr: 0.003984  min_lr: 0.003984  loss: 3.0235 (3.0176)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [31]  [ 80/312]  eta: 0:02:12  lr: 0.003984  min_lr: 0.003984  loss: 2.8021 (3.0150)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [31]  [ 90/312]  eta: 0:02:03  lr: 0.003984  min_lr: 0.003984  loss: 2.9426 (3.0150)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [31]  [100/312]  eta: 0:01:54  lr: 0.003984  min_lr: 0.003984  loss: 3.0780 (3.0177)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0004  max mem: 42573
Epoch: [31]  [110/312]  eta: 0:01:47  lr: 0.003984  min_lr: 0.003984  loss: 2.8794 (3.0056)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0004  max mem: 42573
Epoch: [31]  [120/312]  eta: 0:01:40  lr: 0.003984  min_lr: 0.003984  loss: 2.8794 (3.0135)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [31]  [130/312]  eta: 0:01:34  lr: 0.003984  min_lr: 0.003984  loss: 3.1329 (3.0002)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [31]  [140/312]  eta: 0:01:27  lr: 0.003984  min_lr: 0.003984  loss: 2.9490 (2.9979)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [31]  [150/312]  eta: 0:01:22  lr: 0.003983  min_lr: 0.003983  loss: 2.9490 (3.0049)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [31]  [160/312]  eta: 0:01:16  lr: 0.003983  min_lr: 0.003983  loss: 3.1080 (3.0051)  weight_decay: 0.0500 (0.0500)  time: 0.4341  data: 0.0004  max mem: 42573
Epoch: [31]  [170/312]  eta: 0:01:10  lr: 0.003983  min_lr: 0.003983  loss: 3.2841 (3.0201)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0004  max mem: 42573
Epoch: [31]  [180/312]  eta: 0:01:05  lr: 0.003983  min_lr: 0.003983  loss: 3.1761 (3.0231)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [31]  [190/312]  eta: 0:00:59  lr: 0.003983  min_lr: 0.003983  loss: 3.0133 (3.0214)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [31]  [200/312]  eta: 0:00:54  lr: 0.003983  min_lr: 0.003983  loss: 2.8934 (3.0147)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [31]  [210/312]  eta: 0:00:49  lr: 0.003983  min_lr: 0.003983  loss: 2.9756 (3.0177)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [31]  [220/312]  eta: 0:00:44  lr: 0.003983  min_lr: 0.003983  loss: 3.1128 (3.0216)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [31]  [230/312]  eta: 0:00:39  lr: 0.003983  min_lr: 0.003983  loss: 3.1429 (3.0263)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [31]  [240/312]  eta: 0:00:34  lr: 0.003983  min_lr: 0.003983  loss: 3.1560 (3.0270)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0003  max mem: 42573
Epoch: [31]  [250/312]  eta: 0:00:29  lr: 0.003982  min_lr: 0.003982  loss: 3.0447 (3.0207)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [31]  [260/312]  eta: 0:00:24  lr: 0.003982  min_lr: 0.003982  loss: 3.1520 (3.0259)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0004  max mem: 42573
Epoch: [31]  [270/312]  eta: 0:00:19  lr: 0.003982  min_lr: 0.003982  loss: 3.1198 (3.0206)  weight_decay: 0.0500 (0.0500)  time: 0.4341  data: 0.0004  max mem: 42573
Epoch: [31]  [280/312]  eta: 0:00:15  lr: 0.003982  min_lr: 0.003982  loss: 2.8362 (3.0124)  weight_decay: 0.0500 (0.0500)  time: 0.4345  data: 0.0010  max mem: 42573
Epoch: [31]  [290/312]  eta: 0:00:10  lr: 0.003982  min_lr: 0.003982  loss: 2.8570 (3.0094)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0008  max mem: 42573
Epoch: [31]  [300/312]  eta: 0:00:05  lr: 0.003982  min_lr: 0.003982  loss: 2.8570 (3.0037)  weight_decay: 0.0500 (0.0500)  time: 0.4378  data: 0.0001  max mem: 42573
Epoch: [31]  [310/312]  eta: 0:00:00  lr: 0.003982  min_lr: 0.003982  loss: 2.9219 (3.0069)  weight_decay: 0.0500 (0.0500)  time: 0.4378  data: 0.0001  max mem: 42573
Epoch: [31]  [311/312]  eta: 0:00:00  lr: 0.003982  min_lr: 0.003982  loss: 2.9219 (3.0080)  weight_decay: 0.0500 (0.0500)  time: 0.4378  data: 0.0001  max mem: 42573
Epoch: [31] Total time: 0:02:27 (0.4722 s / it)
Averaged stats: lr: 0.003982  min_lr: 0.003982  loss: 2.9219 (3.0195)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:00:44  loss: 1.1249 (1.1249)  acc1: 72.9167 (72.9167)  acc5: 91.6667 (91.6667)  time: 4.9186  data: 4.8091  max mem: 42573
Test:  [8/9]  eta: 0:00:00  loss: 1.5780 (1.4531)  acc1: 63.5417 (65.0240)  acc5: 86.4583 (86.2720)  time: 0.6236  data: 0.5344  max mem: 42573
Test: Total time: 0:00:05 (0.6465 s / it)
* Acc@1 64.730 Acc@5 85.934 loss 1.462
Accuracy of the model on the 50000 test images: 64.7%
Max accuracy: 64.94%
Epoch: [32]  [  0/312]  eta: 0:51:17  lr: 0.003982  min_lr: 0.003982  loss: 3.6360 (3.6360)  weight_decay: 0.0500 (0.0500)  time: 9.8653  data: 6.9642  max mem: 42573
Epoch: [32]  [ 10/312]  eta: 0:07:11  lr: 0.003982  min_lr: 0.003982  loss: 3.1771 (3.1771)  weight_decay: 0.0500 (0.0500)  time: 1.4287  data: 0.6335  max mem: 42573
Epoch: [32]  [ 20/312]  eta: 0:04:38  lr: 0.003982  min_lr: 0.003982  loss: 3.1321 (3.0484)  weight_decay: 0.0500 (0.0500)  time: 0.5090  data: 0.0004  max mem: 42573
Epoch: [32]  [ 30/312]  eta: 0:03:41  lr: 0.003982  min_lr: 0.003982  loss: 3.1304 (3.0641)  weight_decay: 0.0500 (0.0500)  time: 0.4341  data: 0.0004  max mem: 42573
Epoch: [32]  [ 40/312]  eta: 0:03:10  lr: 0.003982  min_lr: 0.003982  loss: 3.2338 (3.0615)  weight_decay: 0.0500 (0.0500)  time: 0.4349  data: 0.0004  max mem: 42573
Epoch: [32]  [ 50/312]  eta: 0:02:49  lr: 0.003981  min_lr: 0.003981  loss: 3.2503 (3.0853)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0004  max mem: 42573
Epoch: [32]  [ 60/312]  eta: 0:02:34  lr: 0.003981  min_lr: 0.003981  loss: 3.4041 (3.1147)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [32]  [ 70/312]  eta: 0:02:22  lr: 0.003981  min_lr: 0.003981  loss: 3.2470 (3.1143)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [32]  [ 80/312]  eta: 0:02:12  lr: 0.003981  min_lr: 0.003981  loss: 3.0721 (3.1074)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [32]  [ 90/312]  eta: 0:02:03  lr: 0.003981  min_lr: 0.003981  loss: 3.0721 (3.0999)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [32]  [100/312]  eta: 0:01:54  lr: 0.003981  min_lr: 0.003981  loss: 2.8145 (3.0756)  weight_decay: 0.0500 (0.0500)  time: 0.4341  data: 0.0004  max mem: 42573
Epoch: [32]  [110/312]  eta: 0:01:47  lr: 0.003981  min_lr: 0.003981  loss: 3.0927 (3.0848)  weight_decay: 0.0500 (0.0500)  time: 0.4342  data: 0.0004  max mem: 42573
Epoch: [32]  [120/312]  eta: 0:01:40  lr: 0.003981  min_lr: 0.003981  loss: 3.1908 (3.0907)  weight_decay: 0.0500 (0.0500)  time: 0.4341  data: 0.0004  max mem: 42573
Epoch: [32]  [130/312]  eta: 0:01:34  lr: 0.003981  min_lr: 0.003981  loss: 3.1700 (3.0893)  weight_decay: 0.0500 (0.0500)  time: 0.4341  data: 0.0004  max mem: 42573
Epoch: [32]  [140/312]  eta: 0:01:27  lr: 0.003981  min_lr: 0.003981  loss: 3.0145 (3.0870)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [32]  [150/312]  eta: 0:01:22  lr: 0.003980  min_lr: 0.003980  loss: 2.7014 (3.0491)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0003  max mem: 42573
Epoch: [32]  [160/312]  eta: 0:01:16  lr: 0.003980  min_lr: 0.003980  loss: 2.5894 (3.0436)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0004  max mem: 42573
Epoch: [32]  [170/312]  eta: 0:01:10  lr: 0.003980  min_lr: 0.003980  loss: 3.0688 (3.0456)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0003  max mem: 42573
Epoch: [32]  [180/312]  eta: 0:01:05  lr: 0.003980  min_lr: 0.003980  loss: 3.1410 (3.0539)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0003  max mem: 42573
Epoch: [32]  [190/312]  eta: 0:00:59  lr: 0.003980  min_lr: 0.003980  loss: 3.0560 (3.0454)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [32]  [200/312]  eta: 0:00:54  lr: 0.003980  min_lr: 0.003980  loss: 3.0065 (3.0478)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [32]  [210/312]  eta: 0:00:49  lr: 0.003980  min_lr: 0.003980  loss: 3.0971 (3.0465)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [32]  [220/312]  eta: 0:00:44  lr: 0.003980  min_lr: 0.003980  loss: 3.0291 (3.0427)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0003  max mem: 42573
Epoch: [32]  [230/312]  eta: 0:00:39  lr: 0.003980  min_lr: 0.003980  loss: 2.9559 (3.0404)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0003  max mem: 42573
Epoch: [32]  [240/312]  eta: 0:00:34  lr: 0.003980  min_lr: 0.003980  loss: 3.0016 (3.0360)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0003  max mem: 42573
Epoch: [32]  [250/312]  eta: 0:00:29  lr: 0.003979  min_lr: 0.003979  loss: 3.0509 (3.0373)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [32]  [260/312]  eta: 0:00:24  lr: 0.003979  min_lr: 0.003979  loss: 2.9610 (3.0287)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [32]  [270/312]  eta: 0:00:19  lr: 0.003979  min_lr: 0.003979  loss: 2.9969 (3.0346)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [32]  [280/312]  eta: 0:00:15  lr: 0.003979  min_lr: 0.003979  loss: 2.9574 (3.0233)  weight_decay: 0.0500 (0.0500)  time: 0.4398  data: 0.0009  max mem: 42573
Epoch: [32]  [290/312]  eta: 0:00:10  lr: 0.003979  min_lr: 0.003979  loss: 2.8761 (3.0236)  weight_decay: 0.0500 (0.0500)  time: 0.4391  data: 0.0008  max mem: 42573
Epoch: [32]  [300/312]  eta: 0:00:05  lr: 0.003979  min_lr: 0.003979  loss: 3.1397 (3.0247)  weight_decay: 0.0500 (0.0500)  time: 0.4326  data: 0.0001  max mem: 42573
Epoch: [32]  [310/312]  eta: 0:00:00  lr: 0.003979  min_lr: 0.003979  loss: 3.1563 (3.0309)  weight_decay: 0.0500 (0.0500)  time: 0.4325  data: 0.0001  max mem: 42573
Epoch: [32]  [311/312]  eta: 0:00:00  lr: 0.003979  min_lr: 0.003979  loss: 3.1397 (3.0312)  weight_decay: 0.0500 (0.0500)  time: 0.4325  data: 0.0001  max mem: 42573
Epoch: [32] Total time: 0:02:27 (0.4722 s / it)
Averaged stats: lr: 0.003979  min_lr: 0.003979  loss: 3.1397 (3.0100)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:00:42  loss: 1.0636 (1.0636)  acc1: 72.1354 (72.1354)  acc5: 91.6667 (91.6667)  time: 4.6803  data: 4.5711  max mem: 42573
Test:  [8/9]  eta: 0:00:00  loss: 1.6220 (1.4908)  acc1: 63.2812 (64.4160)  acc5: 85.4167 (85.7920)  time: 0.5952  data: 0.5080  max mem: 42573
Test: Total time: 0:00:05 (0.6207 s / it)
* Acc@1 64.058 Acc@5 85.478 loss 1.507
Accuracy of the model on the 50000 test images: 64.1%
Max accuracy: 64.94%
Epoch: [33]  [  0/312]  eta: 0:47:39  lr: 0.003979  min_lr: 0.003979  loss: 2.6853 (2.6853)  weight_decay: 0.0500 (0.0500)  time: 9.1664  data: 6.0105  max mem: 42573
Epoch: [33]  [ 10/312]  eta: 0:07:09  lr: 0.003979  min_lr: 0.003979  loss: 3.1514 (3.1356)  weight_decay: 0.0500 (0.0500)  time: 1.4233  data: 0.7114  max mem: 42573
Epoch: [33]  [ 20/312]  eta: 0:04:37  lr: 0.003979  min_lr: 0.003979  loss: 3.1514 (3.0747)  weight_decay: 0.0500 (0.0500)  time: 0.5412  data: 0.0909  max mem: 42573
Epoch: [33]  [ 30/312]  eta: 0:03:41  lr: 0.003978  min_lr: 0.003978  loss: 3.1255 (3.0989)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [33]  [ 40/312]  eta: 0:03:10  lr: 0.003978  min_lr: 0.003978  loss: 3.1266 (3.1122)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [33]  [ 50/312]  eta: 0:02:49  lr: 0.003978  min_lr: 0.003978  loss: 3.0944 (3.0581)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [33]  [ 60/312]  eta: 0:02:34  lr: 0.003978  min_lr: 0.003978  loss: 2.9074 (3.0640)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [33]  [ 70/312]  eta: 0:02:22  lr: 0.003978  min_lr: 0.003978  loss: 3.0901 (3.0549)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [33]  [ 80/312]  eta: 0:02:11  lr: 0.003978  min_lr: 0.003978  loss: 2.9660 (3.0353)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [33]  [ 90/312]  eta: 0:02:02  lr: 0.003978  min_lr: 0.003978  loss: 2.9660 (3.0260)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [33]  [100/312]  eta: 0:01:54  lr: 0.003978  min_lr: 0.003978  loss: 2.9020 (3.0074)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [33]  [110/312]  eta: 0:01:47  lr: 0.003978  min_lr: 0.003978  loss: 2.8931 (3.0052)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0004  max mem: 42573
Epoch: [33]  [120/312]  eta: 0:01:40  lr: 0.003977  min_lr: 0.003977  loss: 3.0840 (3.0082)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [33]  [130/312]  eta: 0:01:34  lr: 0.003977  min_lr: 0.003977  loss: 3.1124 (3.0058)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [33]  [140/312]  eta: 0:01:27  lr: 0.003977  min_lr: 0.003977  loss: 2.8155 (2.9977)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [33]  [150/312]  eta: 0:01:21  lr: 0.003977  min_lr: 0.003977  loss: 3.0634 (3.0016)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [33]  [160/312]  eta: 0:01:16  lr: 0.003977  min_lr: 0.003977  loss: 3.0519 (2.9964)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0003  max mem: 42573
Epoch: [33]  [170/312]  eta: 0:01:10  lr: 0.003977  min_lr: 0.003977  loss: 3.0318 (2.9945)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [33]  [180/312]  eta: 0:01:05  lr: 0.003977  min_lr: 0.003977  loss: 2.8671 (2.9833)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [33]  [190/312]  eta: 0:00:59  lr: 0.003977  min_lr: 0.003977  loss: 2.8671 (2.9807)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [33]  [200/312]  eta: 0:00:54  lr: 0.003977  min_lr: 0.003977  loss: 2.8263 (2.9784)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [33]  [210/312]  eta: 0:00:49  lr: 0.003977  min_lr: 0.003977  loss: 3.1086 (2.9833)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [33]  [220/312]  eta: 0:00:44  lr: 0.003976  min_lr: 0.003976  loss: 3.1749 (2.9883)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [33]  [230/312]  eta: 0:00:39  lr: 0.003976  min_lr: 0.003976  loss: 3.0070 (2.9770)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0003  max mem: 42573
Epoch: [33]  [240/312]  eta: 0:00:34  lr: 0.003976  min_lr: 0.003976  loss: 2.9761 (2.9838)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [33]  [250/312]  eta: 0:00:29  lr: 0.003976  min_lr: 0.003976  loss: 3.2938 (2.9871)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0003  max mem: 42573
Epoch: [33]  [260/312]  eta: 0:00:24  lr: 0.003976  min_lr: 0.003976  loss: 3.1981 (2.9890)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [33]  [270/312]  eta: 0:00:19  lr: 0.003976  min_lr: 0.003976  loss: 3.0778 (2.9857)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0004  max mem: 42573
Epoch: [33]  [280/312]  eta: 0:00:15  lr: 0.003976  min_lr: 0.003976  loss: 3.0874 (2.9869)  weight_decay: 0.0500 (0.0500)  time: 0.4348  data: 0.0008  max mem: 42573
Epoch: [33]  [290/312]  eta: 0:00:10  lr: 0.003976  min_lr: 0.003976  loss: 2.8645 (2.9795)  weight_decay: 0.0500 (0.0500)  time: 0.4341  data: 0.0007  max mem: 42573
Epoch: [33]  [300/312]  eta: 0:00:05  lr: 0.003976  min_lr: 0.003976  loss: 2.8645 (2.9794)  weight_decay: 0.0500 (0.0500)  time: 0.4326  data: 0.0001  max mem: 42573
Epoch: [33]  [310/312]  eta: 0:00:00  lr: 0.003975  min_lr: 0.003975  loss: 3.0835 (2.9840)  weight_decay: 0.0500 (0.0500)  time: 0.4325  data: 0.0001  max mem: 42573
Epoch: [33]  [311/312]  eta: 0:00:00  lr: 0.003975  min_lr: 0.003975  loss: 3.0835 (2.9832)  weight_decay: 0.0500 (0.0500)  time: 0.4325  data: 0.0001  max mem: 42573
Epoch: [33] Total time: 0:02:27 (0.4715 s / it)
Averaged stats: lr: 0.003975  min_lr: 0.003975  loss: 3.0835 (2.9893)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:00:41  loss: 1.2327 (1.2327)  acc1: 70.5729 (70.5729)  acc5: 88.8021 (88.8021)  time: 4.5865  data: 4.4771  max mem: 42573
Test:  [8/9]  eta: 0:00:00  loss: 1.6934 (1.5212)  acc1: 63.5417 (63.6160)  acc5: 85.1562 (85.7280)  time: 0.5868  data: 0.4975  max mem: 42573
Test: Total time: 0:00:05 (0.6067 s / it)
* Acc@1 64.274 Acc@5 85.548 loss 1.524
Accuracy of the model on the 50000 test images: 64.3%
Max accuracy: 64.94%
Epoch: [34]  [  0/312]  eta: 0:50:01  lr: 0.003975  min_lr: 0.003975  loss: 2.5357 (2.5357)  weight_decay: 0.0500 (0.0500)  time: 9.6202  data: 7.6119  max mem: 42573
Epoch: [34]  [ 10/312]  eta: 0:07:23  lr: 0.003975  min_lr: 0.003975  loss: 2.8009 (2.7941)  weight_decay: 0.0500 (0.0500)  time: 1.4673  data: 0.7653  max mem: 42573
Epoch: [34]  [ 20/312]  eta: 0:04:44  lr: 0.003975  min_lr: 0.003975  loss: 2.9442 (2.8925)  weight_decay: 0.0500 (0.0500)  time: 0.5427  data: 0.0405  max mem: 42573
Epoch: [34]  [ 30/312]  eta: 0:03:45  lr: 0.003975  min_lr: 0.003975  loss: 3.1237 (2.9721)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0003  max mem: 42573
Epoch: [34]  [ 40/312]  eta: 0:03:13  lr: 0.003975  min_lr: 0.003975  loss: 3.1229 (2.9902)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [34]  [ 50/312]  eta: 0:02:52  lr: 0.003975  min_lr: 0.003975  loss: 3.1229 (3.0328)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [34]  [ 60/312]  eta: 0:02:36  lr: 0.003975  min_lr: 0.003975  loss: 3.2821 (3.0376)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [34]  [ 70/312]  eta: 0:02:23  lr: 0.003975  min_lr: 0.003975  loss: 3.0685 (3.0364)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [34]  [ 80/312]  eta: 0:02:13  lr: 0.003974  min_lr: 0.003974  loss: 3.0917 (3.0487)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [34]  [ 90/312]  eta: 0:02:03  lr: 0.003974  min_lr: 0.003974  loss: 3.1665 (3.0600)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [34]  [100/312]  eta: 0:01:55  lr: 0.003974  min_lr: 0.003974  loss: 3.0546 (3.0641)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0004  max mem: 42573
Epoch: [34]  [110/312]  eta: 0:01:48  lr: 0.003974  min_lr: 0.003974  loss: 3.0482 (3.0570)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [34]  [120/312]  eta: 0:01:41  lr: 0.003974  min_lr: 0.003974  loss: 2.9663 (3.0400)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [34]  [130/312]  eta: 0:01:34  lr: 0.003974  min_lr: 0.003974  loss: 3.0092 (3.0455)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [34]  [140/312]  eta: 0:01:28  lr: 0.003974  min_lr: 0.003974  loss: 3.0484 (3.0449)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0003  max mem: 42573
Epoch: [34]  [150/312]  eta: 0:01:22  lr: 0.003974  min_lr: 0.003974  loss: 2.9947 (3.0368)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0003  max mem: 42573
Epoch: [34]  [160/312]  eta: 0:01:16  lr: 0.003974  min_lr: 0.003974  loss: 2.9207 (3.0371)  weight_decay: 0.0500 (0.0500)  time: 0.4351  data: 0.0004  max mem: 42573
Epoch: [34]  [170/312]  eta: 0:01:11  lr: 0.003973  min_lr: 0.003973  loss: 3.0208 (3.0299)  weight_decay: 0.0500 (0.0500)  time: 0.4351  data: 0.0004  max mem: 42573
Epoch: [34]  [180/312]  eta: 0:01:05  lr: 0.003973  min_lr: 0.003973  loss: 2.7638 (3.0190)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0003  max mem: 42573
Epoch: [34]  [190/312]  eta: 0:01:00  lr: 0.003973  min_lr: 0.003973  loss: 2.9402 (3.0238)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [34]  [200/312]  eta: 0:00:54  lr: 0.003973  min_lr: 0.003973  loss: 3.1968 (3.0228)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [34]  [210/312]  eta: 0:00:49  lr: 0.003973  min_lr: 0.003973  loss: 3.2072 (3.0258)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [34]  [220/312]  eta: 0:00:44  lr: 0.003973  min_lr: 0.003973  loss: 3.1307 (3.0308)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [34]  [230/312]  eta: 0:00:39  lr: 0.003973  min_lr: 0.003973  loss: 2.9277 (3.0245)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [34]  [240/312]  eta: 0:00:34  lr: 0.003973  min_lr: 0.003973  loss: 2.8754 (3.0151)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [34]  [250/312]  eta: 0:00:29  lr: 0.003972  min_lr: 0.003972  loss: 2.8024 (3.0090)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [34]  [260/312]  eta: 0:00:24  lr: 0.003972  min_lr: 0.003972  loss: 2.9489 (3.0089)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [34]  [270/312]  eta: 0:00:19  lr: 0.003972  min_lr: 0.003972  loss: 3.2476 (3.0220)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [34]  [280/312]  eta: 0:00:15  lr: 0.003972  min_lr: 0.003972  loss: 3.2267 (3.0273)  weight_decay: 0.0500 (0.0500)  time: 0.4346  data: 0.0011  max mem: 42573
Epoch: [34]  [290/312]  eta: 0:00:10  lr: 0.003972  min_lr: 0.003972  loss: 3.0777 (3.0185)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0010  max mem: 42573
Epoch: [34]  [300/312]  eta: 0:00:05  lr: 0.003972  min_lr: 0.003972  loss: 2.9780 (3.0212)  weight_decay: 0.0500 (0.0500)  time: 0.4325  data: 0.0001  max mem: 42573
Epoch: [34]  [310/312]  eta: 0:00:00  lr: 0.003972  min_lr: 0.003972  loss: 2.9780 (3.0184)  weight_decay: 0.0500 (0.0500)  time: 0.4324  data: 0.0001  max mem: 42573
Epoch: [34]  [311/312]  eta: 0:00:00  lr: 0.003972  min_lr: 0.003972  loss: 3.1091 (3.0207)  weight_decay: 0.0500 (0.0500)  time: 0.4323  data: 0.0001  max mem: 42573
Epoch: [34] Total time: 0:02:27 (0.4733 s / it)
Averaged stats: lr: 0.003972  min_lr: 0.003972  loss: 3.1091 (2.9740)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:00:40  loss: 1.1704 (1.1704)  acc1: 71.8750 (71.8750)  acc5: 89.8438 (89.8438)  time: 4.5104  data: 4.4011  max mem: 42573
Test:  [8/9]  eta: 0:00:00  loss: 1.5285 (1.4627)  acc1: 63.5417 (64.5440)  acc5: 86.4583 (85.8560)  time: 0.5828  data: 0.4891  max mem: 42573
Test: Total time: 0:00:05 (0.5901 s / it)
* Acc@1 65.490 Acc@5 86.058 loss 1.464
Accuracy of the model on the 50000 test images: 65.5%
Max accuracy: 65.49%
Epoch: [35]  [  0/312]  eta: 0:47:06  lr: 0.003972  min_lr: 0.003972  loss: 2.7549 (2.7549)  weight_decay: 0.0500 (0.0500)  time: 9.0597  data: 8.3945  max mem: 42573
Epoch: [35]  [ 10/312]  eta: 0:07:16  lr: 0.003972  min_lr: 0.003972  loss: 3.5029 (3.2459)  weight_decay: 0.0500 (0.0500)  time: 1.4456  data: 0.7856  max mem: 42573
Epoch: [35]  [ 20/312]  eta: 0:04:41  lr: 0.003972  min_lr: 0.003972  loss: 2.9810 (2.9710)  weight_decay: 0.0500 (0.0500)  time: 0.5587  data: 0.0125  max mem: 42573
Epoch: [35]  [ 30/312]  eta: 0:03:43  lr: 0.003971  min_lr: 0.003971  loss: 2.7505 (2.9355)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [35]  [ 40/312]  eta: 0:03:11  lr: 0.003971  min_lr: 0.003971  loss: 2.9589 (2.9491)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0005  max mem: 42573
Epoch: [35]  [ 50/312]  eta: 0:02:50  lr: 0.003971  min_lr: 0.003971  loss: 3.0529 (2.9877)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [35]  [ 60/312]  eta: 0:02:35  lr: 0.003971  min_lr: 0.003971  loss: 3.2052 (3.0052)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [35]  [ 70/312]  eta: 0:02:22  lr: 0.003971  min_lr: 0.003971  loss: 3.0602 (3.0041)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [35]  [ 80/312]  eta: 0:02:12  lr: 0.003971  min_lr: 0.003971  loss: 2.9175 (2.9769)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [35]  [ 90/312]  eta: 0:02:03  lr: 0.003971  min_lr: 0.003971  loss: 2.5759 (2.9514)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [35]  [100/312]  eta: 0:01:55  lr: 0.003971  min_lr: 0.003971  loss: 3.0758 (2.9643)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [35]  [110/312]  eta: 0:01:47  lr: 0.003970  min_lr: 0.003970  loss: 2.8006 (2.9413)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0003  max mem: 42573
Epoch: [35]  [120/312]  eta: 0:01:40  lr: 0.003970  min_lr: 0.003970  loss: 2.8006 (2.9480)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0005  max mem: 42573
Epoch: [35]  [130/312]  eta: 0:01:34  lr: 0.003970  min_lr: 0.003970  loss: 3.0675 (2.9502)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0005  max mem: 42573
Epoch: [35]  [140/312]  eta: 0:01:28  lr: 0.003970  min_lr: 0.003970  loss: 2.7740 (2.9407)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0003  max mem: 42573
Epoch: [35]  [150/312]  eta: 0:01:22  lr: 0.003970  min_lr: 0.003970  loss: 2.8773 (2.9405)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [35]  [160/312]  eta: 0:01:16  lr: 0.003970  min_lr: 0.003970  loss: 2.9421 (2.9396)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [35]  [170/312]  eta: 0:01:10  lr: 0.003970  min_lr: 0.003970  loss: 2.8166 (2.9335)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0003  max mem: 42573
Epoch: [35]  [180/312]  eta: 0:01:05  lr: 0.003970  min_lr: 0.003970  loss: 3.0919 (2.9477)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [35]  [190/312]  eta: 0:01:00  lr: 0.003969  min_lr: 0.003969  loss: 3.1065 (2.9468)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [35]  [200/312]  eta: 0:00:54  lr: 0.003969  min_lr: 0.003969  loss: 2.9059 (2.9386)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [35]  [210/312]  eta: 0:00:49  lr: 0.003969  min_lr: 0.003969  loss: 3.0429 (2.9469)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [35]  [220/312]  eta: 0:00:44  lr: 0.003969  min_lr: 0.003969  loss: 3.0707 (2.9474)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [35]  [230/312]  eta: 0:00:39  lr: 0.003969  min_lr: 0.003969  loss: 2.9185 (2.9487)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [35]  [240/312]  eta: 0:00:34  lr: 0.003969  min_lr: 0.003969  loss: 2.8336 (2.9511)  weight_decay: 0.0500 (0.0500)  time: 0.4342  data: 0.0003  max mem: 42573
Epoch: [35]  [250/312]  eta: 0:00:29  lr: 0.003969  min_lr: 0.003969  loss: 2.8336 (2.9487)  weight_decay: 0.0500 (0.0500)  time: 0.4342  data: 0.0003  max mem: 42573
Epoch: [35]  [260/312]  eta: 0:00:24  lr: 0.003969  min_lr: 0.003969  loss: 3.1382 (2.9506)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0003  max mem: 42573
Epoch: [35]  [270/312]  eta: 0:00:19  lr: 0.003968  min_lr: 0.003968  loss: 2.5495 (2.9338)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0003  max mem: 42573
Epoch: [35]  [280/312]  eta: 0:00:15  lr: 0.003968  min_lr: 0.003968  loss: 2.5447 (2.9351)  weight_decay: 0.0500 (0.0500)  time: 0.4348  data: 0.0009  max mem: 42573
Epoch: [35]  [290/312]  eta: 0:00:10  lr: 0.003968  min_lr: 0.003968  loss: 3.1104 (2.9367)  weight_decay: 0.0500 (0.0500)  time: 0.4341  data: 0.0007  max mem: 42573
Epoch: [35]  [300/312]  eta: 0:00:05  lr: 0.003968  min_lr: 0.003968  loss: 2.9222 (2.9294)  weight_decay: 0.0500 (0.0500)  time: 0.4323  data: 0.0001  max mem: 42573
Epoch: [35]  [310/312]  eta: 0:00:00  lr: 0.003968  min_lr: 0.003968  loss: 2.8352 (2.9291)  weight_decay: 0.0500 (0.0500)  time: 0.4323  data: 0.0001  max mem: 42573
Epoch: [35]  [311/312]  eta: 0:00:00  lr: 0.003968  min_lr: 0.003968  loss: 2.8352 (2.9298)  weight_decay: 0.0500 (0.0500)  time: 0.4323  data: 0.0001  max mem: 42573
Epoch: [35] Total time: 0:02:27 (0.4724 s / it)
Averaged stats: lr: 0.003968  min_lr: 0.003968  loss: 2.8352 (2.9665)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:00:41  loss: 1.1790 (1.1790)  acc1: 72.9167 (72.9167)  acc5: 88.0208 (88.0208)  time: 4.5802  data: 4.4715  max mem: 42573
Test:  [8/9]  eta: 0:00:00  loss: 1.5381 (1.4421)  acc1: 64.8438 (64.7680)  acc5: 87.2396 (86.1760)  time: 0.5888  data: 0.4969  max mem: 42573
Test: Total time: 0:00:05 (0.5986 s / it)
* Acc@1 65.270 Acc@5 86.240 loss 1.438
Accuracy of the model on the 50000 test images: 65.3%
Max accuracy: 65.49%
Epoch: [36]  [  0/312]  eta: 0:50:39  lr: 0.003968  min_lr: 0.003968  loss: 3.3695 (3.3695)  weight_decay: 0.0500 (0.0500)  time: 9.7411  data: 7.9812  max mem: 42573
Epoch: [36]  [ 10/312]  eta: 0:07:13  lr: 0.003968  min_lr: 0.003968  loss: 2.8957 (2.9171)  weight_decay: 0.0500 (0.0500)  time: 1.4353  data: 0.7260  max mem: 42573
Epoch: [36]  [ 20/312]  eta: 0:04:39  lr: 0.003968  min_lr: 0.003968  loss: 2.7844 (2.9134)  weight_decay: 0.0500 (0.0500)  time: 0.5189  data: 0.0004  max mem: 42573
Epoch: [36]  [ 30/312]  eta: 0:03:42  lr: 0.003967  min_lr: 0.003967  loss: 3.2358 (3.0172)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [36]  [ 40/312]  eta: 0:03:11  lr: 0.003967  min_lr: 0.003967  loss: 3.0740 (2.9838)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [36]  [ 50/312]  eta: 0:02:50  lr: 0.003967  min_lr: 0.003967  loss: 2.7949 (2.9454)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [36]  [ 60/312]  eta: 0:02:34  lr: 0.003967  min_lr: 0.003967  loss: 2.9007 (2.9492)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [36]  [ 70/312]  eta: 0:02:22  lr: 0.003967  min_lr: 0.003967  loss: 3.0070 (2.9499)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [36]  [ 80/312]  eta: 0:02:12  lr: 0.003967  min_lr: 0.003967  loss: 3.0908 (2.9796)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [36]  [ 90/312]  eta: 0:02:03  lr: 0.003967  min_lr: 0.003967  loss: 3.0421 (2.9793)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [36]  [100/312]  eta: 0:01:55  lr: 0.003967  min_lr: 0.003967  loss: 3.0272 (2.9769)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [36]  [110/312]  eta: 0:01:47  lr: 0.003966  min_lr: 0.003966  loss: 3.1215 (2.9659)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [36]  [120/312]  eta: 0:01:40  lr: 0.003966  min_lr: 0.003966  loss: 3.1022 (2.9611)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [36]  [130/312]  eta: 0:01:34  lr: 0.003966  min_lr: 0.003966  loss: 3.1022 (2.9735)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [36]  [140/312]  eta: 0:01:28  lr: 0.003966  min_lr: 0.003966  loss: 3.0757 (2.9711)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [36]  [150/312]  eta: 0:01:22  lr: 0.003966  min_lr: 0.003966  loss: 3.0857 (2.9766)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [36]  [160/312]  eta: 0:01:16  lr: 0.003966  min_lr: 0.003966  loss: 2.9787 (2.9713)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [36]  [170/312]  eta: 0:01:10  lr: 0.003966  min_lr: 0.003966  loss: 2.9361 (2.9661)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [36]  [180/312]  eta: 0:01:05  lr: 0.003966  min_lr: 0.003966  loss: 3.0710 (2.9730)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [36]  [190/312]  eta: 0:00:59  lr: 0.003965  min_lr: 0.003965  loss: 2.9971 (2.9575)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [36]  [200/312]  eta: 0:00:54  lr: 0.003965  min_lr: 0.003965  loss: 2.9296 (2.9620)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0004  max mem: 42573
Epoch: [36]  [210/312]  eta: 0:00:49  lr: 0.003965  min_lr: 0.003965  loss: 3.1644 (2.9640)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0003  max mem: 42573
Epoch: [36]  [220/312]  eta: 0:00:44  lr: 0.003965  min_lr: 0.003965  loss: 2.9449 (2.9554)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [36]  [230/312]  eta: 0:00:39  lr: 0.003965  min_lr: 0.003965  loss: 3.0291 (2.9609)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [36]  [240/312]  eta: 0:00:34  lr: 0.003965  min_lr: 0.003965  loss: 3.1409 (2.9639)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [36]  [250/312]  eta: 0:00:29  lr: 0.003965  min_lr: 0.003965  loss: 3.1622 (2.9647)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [36]  [260/312]  eta: 0:00:24  lr: 0.003964  min_lr: 0.003964  loss: 3.1315 (2.9669)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0003  max mem: 42573
Epoch: [36]  [270/312]  eta: 0:00:19  lr: 0.003964  min_lr: 0.003964  loss: 3.1315 (2.9673)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [36]  [280/312]  eta: 0:00:15  lr: 0.003964  min_lr: 0.003964  loss: 3.0860 (2.9654)  weight_decay: 0.0500 (0.0500)  time: 0.4348  data: 0.0010  max mem: 42573
Epoch: [36]  [290/312]  eta: 0:00:10  lr: 0.003964  min_lr: 0.003964  loss: 3.0219 (2.9579)  weight_decay: 0.0500 (0.0500)  time: 0.4341  data: 0.0008  max mem: 42573
Epoch: [36]  [300/312]  eta: 0:00:05  lr: 0.003964  min_lr: 0.003964  loss: 2.9492 (2.9577)  weight_decay: 0.0500 (0.0500)  time: 0.4324  data: 0.0001  max mem: 42573
Epoch: [36]  [310/312]  eta: 0:00:00  lr: 0.003964  min_lr: 0.003964  loss: 2.9545 (2.9514)  weight_decay: 0.0500 (0.0500)  time: 0.4396  data: 0.0001  max mem: 42573
Epoch: [36]  [311/312]  eta: 0:00:00  lr: 0.003964  min_lr: 0.003964  loss: 2.9545 (2.9492)  weight_decay: 0.0500 (0.0500)  time: 0.4396  data: 0.0001  max mem: 42573
Epoch: [36] Total time: 0:02:27 (0.4724 s / it)
Averaged stats: lr: 0.003964  min_lr: 0.003964  loss: 2.9545 (2.9621)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:00:41  loss: 1.0779 (1.0779)  acc1: 73.9583 (73.9583)  acc5: 90.8854 (90.8854)  time: 4.6193  data: 4.5098  max mem: 42573
Test:  [8/9]  eta: 0:00:00  loss: 1.4871 (1.3543)  acc1: 65.3646 (66.4320)  acc5: 86.9792 (87.3280)  time: 0.6002  data: 0.5096  max mem: 42573
Test: Total time: 0:00:05 (0.6074 s / it)
* Acc@1 66.652 Acc@5 87.280 loss 1.366
Accuracy of the model on the 50000 test images: 66.7%
Max accuracy: 66.65%
Epoch: [37]  [  0/312]  eta: 0:49:09  lr: 0.003964  min_lr: 0.003964  loss: 2.3994 (2.3994)  weight_decay: 0.0500 (0.0500)  time: 9.4522  data: 6.8752  max mem: 42573
Epoch: [37]  [ 10/312]  eta: 0:07:00  lr: 0.003964  min_lr: 0.003964  loss: 2.6605 (2.7405)  weight_decay: 0.0500 (0.0500)  time: 1.3909  data: 0.7375  max mem: 42573
Epoch: [37]  [ 20/312]  eta: 0:04:32  lr: 0.003963  min_lr: 0.003963  loss: 2.7410 (2.7994)  weight_decay: 0.0500 (0.0500)  time: 0.5090  data: 0.0620  max mem: 42573
Epoch: [37]  [ 30/312]  eta: 0:03:38  lr: 0.003963  min_lr: 0.003963  loss: 3.0058 (2.9161)  weight_decay: 0.0500 (0.0500)  time: 0.4352  data: 0.0004  max mem: 42573
Epoch: [37]  [ 40/312]  eta: 0:03:08  lr: 0.003963  min_lr: 0.003963  loss: 3.0789 (2.9027)  weight_decay: 0.0500 (0.0500)  time: 0.4357  data: 0.0004  max mem: 42573
Epoch: [37]  [ 50/312]  eta: 0:02:47  lr: 0.003963  min_lr: 0.003963  loss: 3.0789 (2.9281)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0004  max mem: 42573
Epoch: [37]  [ 60/312]  eta: 0:02:32  lr: 0.003963  min_lr: 0.003963  loss: 3.1756 (2.9465)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [37]  [ 70/312]  eta: 0:02:20  lr: 0.003963  min_lr: 0.003963  loss: 3.0385 (2.9234)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [37]  [ 80/312]  eta: 0:02:10  lr: 0.003963  min_lr: 0.003963  loss: 3.0866 (2.9416)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [37]  [ 90/312]  eta: 0:02:02  lr: 0.003963  min_lr: 0.003963  loss: 3.1440 (2.9687)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [37]  [100/312]  eta: 0:01:54  lr: 0.003962  min_lr: 0.003962  loss: 3.0962 (2.9810)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [37]  [110/312]  eta: 0:01:46  lr: 0.003962  min_lr: 0.003962  loss: 3.0641 (2.9817)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0004  max mem: 42573
Epoch: [37]  [120/312]  eta: 0:01:40  lr: 0.003962  min_lr: 0.003962  loss: 2.9509 (2.9714)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [37]  [130/312]  eta: 0:01:33  lr: 0.003962  min_lr: 0.003962  loss: 2.8635 (2.9723)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [37]  [140/312]  eta: 0:01:27  lr: 0.003962  min_lr: 0.003962  loss: 3.0327 (2.9630)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [37]  [150/312]  eta: 0:01:21  lr: 0.003962  min_lr: 0.003962  loss: 3.0983 (2.9699)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0004  max mem: 42573
Epoch: [37]  [160/312]  eta: 0:01:15  lr: 0.003962  min_lr: 0.003962  loss: 3.0220 (2.9630)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0004  max mem: 42573
Epoch: [37]  [170/312]  eta: 0:01:10  lr: 0.003961  min_lr: 0.003961  loss: 2.7371 (2.9581)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [37]  [180/312]  eta: 0:01:04  lr: 0.003961  min_lr: 0.003961  loss: 3.1037 (2.9637)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [37]  [190/312]  eta: 0:00:59  lr: 0.003961  min_lr: 0.003961  loss: 2.9974 (2.9559)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [37]  [200/312]  eta: 0:00:54  lr: 0.003961  min_lr: 0.003961  loss: 2.9809 (2.9522)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [37]  [210/312]  eta: 0:00:49  lr: 0.003961  min_lr: 0.003961  loss: 3.0631 (2.9572)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [37]  [220/312]  eta: 0:00:44  lr: 0.003961  min_lr: 0.003961  loss: 3.0401 (2.9534)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [37]  [230/312]  eta: 0:00:39  lr: 0.003961  min_lr: 0.003961  loss: 3.0401 (2.9633)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [37]  [240/312]  eta: 0:00:34  lr: 0.003960  min_lr: 0.003960  loss: 2.9735 (2.9582)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [37]  [250/312]  eta: 0:00:29  lr: 0.003960  min_lr: 0.003960  loss: 2.9113 (2.9556)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0003  max mem: 42573
Epoch: [37]  [260/312]  eta: 0:00:24  lr: 0.003960  min_lr: 0.003960  loss: 2.8609 (2.9514)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0003  max mem: 42573
Epoch: [37]  [270/312]  eta: 0:00:19  lr: 0.003960  min_lr: 0.003960  loss: 2.8576 (2.9480)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0003  max mem: 42573
Epoch: [37]  [280/312]  eta: 0:00:15  lr: 0.003960  min_lr: 0.003960  loss: 3.0652 (2.9514)  weight_decay: 0.0500 (0.0500)  time: 0.4346  data: 0.0009  max mem: 42573
Epoch: [37]  [290/312]  eta: 0:00:10  lr: 0.003960  min_lr: 0.003960  loss: 3.1813 (2.9467)  weight_decay: 0.0500 (0.0500)  time: 0.4391  data: 0.0008  max mem: 42573
Epoch: [37]  [300/312]  eta: 0:00:05  lr: 0.003960  min_lr: 0.003960  loss: 2.9671 (2.9466)  weight_decay: 0.0500 (0.0500)  time: 0.4374  data: 0.0001  max mem: 42573
Epoch: [37]  [310/312]  eta: 0:00:00  lr: 0.003959  min_lr: 0.003959  loss: 3.2349 (2.9497)  weight_decay: 0.0500 (0.0500)  time: 0.4324  data: 0.0001  max mem: 42573
Epoch: [37]  [311/312]  eta: 0:00:00  lr: 0.003959  min_lr: 0.003959  loss: 3.2257 (2.9506)  weight_decay: 0.0500 (0.0500)  time: 0.4324  data: 0.0001  max mem: 42573
Epoch: [37] Total time: 0:02:26 (0.4709 s / it)
Averaged stats: lr: 0.003959  min_lr: 0.003959  loss: 3.2257 (2.9242)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:00:44  loss: 1.2496 (1.2496)  acc1: 70.0521 (70.0521)  acc5: 90.1042 (90.1042)  time: 4.8910  data: 4.7816  max mem: 42573
Test:  [8/9]  eta: 0:00:00  loss: 1.6061 (1.5298)  acc1: 63.0208 (62.3360)  acc5: 85.1562 (85.7600)  time: 0.6204  data: 0.5313  max mem: 42573
Test: Total time: 0:00:05 (0.6405 s / it)
* Acc@1 64.060 Acc@5 85.476 loss 1.525
Accuracy of the model on the 50000 test images: 64.1%
Max accuracy: 66.65%
Epoch: [38]  [  0/312]  eta: 0:50:25  lr: 0.003959  min_lr: 0.003959  loss: 2.9884 (2.9884)  weight_decay: 0.0500 (0.0500)  time: 9.6959  data: 6.6002  max mem: 42573
Epoch: [38]  [ 10/312]  eta: 0:07:21  lr: 0.003959  min_lr: 0.003959  loss: 2.6797 (2.7764)  weight_decay: 0.0500 (0.0500)  time: 1.4606  data: 0.7205  max mem: 42573
Epoch: [38]  [ 20/312]  eta: 0:04:43  lr: 0.003959  min_lr: 0.003959  loss: 2.6797 (2.8007)  weight_decay: 0.0500 (0.0500)  time: 0.5357  data: 0.0664  max mem: 42573
Epoch: [38]  [ 30/312]  eta: 0:03:45  lr: 0.003959  min_lr: 0.003959  loss: 3.0725 (2.8369)  weight_decay: 0.0500 (0.0500)  time: 0.4361  data: 0.0003  max mem: 42573
Epoch: [38]  [ 40/312]  eta: 0:03:13  lr: 0.003959  min_lr: 0.003959  loss: 3.1161 (2.8619)  weight_decay: 0.0500 (0.0500)  time: 0.4357  data: 0.0004  max mem: 42573
Epoch: [38]  [ 50/312]  eta: 0:02:51  lr: 0.003959  min_lr: 0.003959  loss: 2.8394 (2.8415)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [38]  [ 60/312]  eta: 0:02:36  lr: 0.003958  min_lr: 0.003958  loss: 3.0329 (2.8753)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [38]  [ 70/312]  eta: 0:02:23  lr: 0.003958  min_lr: 0.003958  loss: 3.1221 (2.9030)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [38]  [ 80/312]  eta: 0:02:13  lr: 0.003958  min_lr: 0.003958  loss: 3.1221 (2.9095)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0003  max mem: 42573
Epoch: [38]  [ 90/312]  eta: 0:02:03  lr: 0.003958  min_lr: 0.003958  loss: 3.0354 (2.9116)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0003  max mem: 42573
Epoch: [38]  [100/312]  eta: 0:01:55  lr: 0.003958  min_lr: 0.003958  loss: 2.9274 (2.9047)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0004  max mem: 42573
Epoch: [38]  [110/312]  eta: 0:01:48  lr: 0.003958  min_lr: 0.003958  loss: 2.9590 (2.9260)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0004  max mem: 42573
Epoch: [38]  [120/312]  eta: 0:01:41  lr: 0.003958  min_lr: 0.003958  loss: 3.0763 (2.9365)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [38]  [130/312]  eta: 0:01:34  lr: 0.003957  min_lr: 0.003957  loss: 2.9720 (2.9261)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [38]  [140/312]  eta: 0:01:28  lr: 0.003957  min_lr: 0.003957  loss: 3.0584 (2.9350)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0003  max mem: 42573
Epoch: [38]  [150/312]  eta: 0:01:22  lr: 0.003957  min_lr: 0.003957  loss: 3.0584 (2.9333)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0003  max mem: 42573
Epoch: [38]  [160/312]  eta: 0:01:16  lr: 0.003957  min_lr: 0.003957  loss: 2.9571 (2.9307)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [38]  [170/312]  eta: 0:01:11  lr: 0.003957  min_lr: 0.003957  loss: 2.8627 (2.9246)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [38]  [180/312]  eta: 0:01:05  lr: 0.003957  min_lr: 0.003957  loss: 2.8623 (2.9224)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [38]  [190/312]  eta: 0:01:00  lr: 0.003957  min_lr: 0.003957  loss: 3.0835 (2.9359)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [38]  [200/312]  eta: 0:00:54  lr: 0.003956  min_lr: 0.003956  loss: 3.0835 (2.9373)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [38]  [210/312]  eta: 0:00:49  lr: 0.003956  min_lr: 0.003956  loss: 2.7812 (2.9317)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0005  max mem: 42573
Epoch: [38]  [220/312]  eta: 0:00:44  lr: 0.003956  min_lr: 0.003956  loss: 3.0263 (2.9328)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [38]  [230/312]  eta: 0:00:39  lr: 0.003956  min_lr: 0.003956  loss: 3.1229 (2.9389)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [38]  [240/312]  eta: 0:00:34  lr: 0.003956  min_lr: 0.003956  loss: 3.0749 (2.9381)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [38]  [250/312]  eta: 0:00:29  lr: 0.003956  min_lr: 0.003956  loss: 3.1730 (2.9416)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [38]  [260/312]  eta: 0:00:24  lr: 0.003956  min_lr: 0.003956  loss: 3.2028 (2.9491)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0005  max mem: 42573
Epoch: [38]  [270/312]  eta: 0:00:19  lr: 0.003955  min_lr: 0.003955  loss: 3.2028 (2.9606)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0005  max mem: 42573
Epoch: [38]  [280/312]  eta: 0:00:15  lr: 0.003955  min_lr: 0.003955  loss: 3.1736 (2.9655)  weight_decay: 0.0500 (0.0500)  time: 0.4346  data: 0.0010  max mem: 42573
Epoch: [38]  [290/312]  eta: 0:00:10  lr: 0.003955  min_lr: 0.003955  loss: 2.9570 (2.9593)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0008  max mem: 42573
Epoch: [38]  [300/312]  eta: 0:00:05  lr: 0.003955  min_lr: 0.003955  loss: 2.9536 (2.9536)  weight_decay: 0.0500 (0.0500)  time: 0.4324  data: 0.0001  max mem: 42573
Epoch: [38]  [310/312]  eta: 0:00:00  lr: 0.003955  min_lr: 0.003955  loss: 2.9536 (2.9548)  weight_decay: 0.0500 (0.0500)  time: 0.4323  data: 0.0001  max mem: 42573
Epoch: [38]  [311/312]  eta: 0:00:00  lr: 0.003955  min_lr: 0.003955  loss: 2.9380 (2.9532)  weight_decay: 0.0500 (0.0500)  time: 0.4323  data: 0.0001  max mem: 42573
Epoch: [38] Total time: 0:02:27 (0.4730 s / it)
Averaged stats: lr: 0.003955  min_lr: 0.003955  loss: 2.9380 (2.9285)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:00:41  loss: 1.1031 (1.1031)  acc1: 71.8750 (71.8750)  acc5: 89.5833 (89.5833)  time: 4.6029  data: 4.4935  max mem: 42573
Test:  [8/9]  eta: 0:00:00  loss: 1.6420 (1.4537)  acc1: 62.7604 (64.8320)  acc5: 85.9375 (86.0480)  time: 0.5871  data: 0.4993  max mem: 42573
Test: Total time: 0:00:05 (0.6091 s / it)
* Acc@1 65.422 Acc@5 86.346 loss 1.446
Accuracy of the model on the 50000 test images: 65.4%
Max accuracy: 66.65%
Epoch: [39]  [  0/312]  eta: 0:51:40  lr: 0.003955  min_lr: 0.003955  loss: 3.5293 (3.5293)  weight_decay: 0.0500 (0.0500)  time: 9.9381  data: 6.6513  max mem: 42573
Epoch: [39]  [ 10/312]  eta: 0:07:51  lr: 0.003955  min_lr: 0.003955  loss: 3.0822 (3.0762)  weight_decay: 0.0500 (0.0500)  time: 1.5621  data: 0.7076  max mem: 42573
Epoch: [39]  [ 20/312]  eta: 0:04:59  lr: 0.003954  min_lr: 0.003954  loss: 3.0380 (2.9355)  weight_decay: 0.0500 (0.0500)  time: 0.5794  data: 0.0568  max mem: 42573
Epoch: [39]  [ 30/312]  eta: 0:03:55  lr: 0.003954  min_lr: 0.003954  loss: 2.7758 (2.9053)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [39]  [ 40/312]  eta: 0:03:20  lr: 0.003954  min_lr: 0.003954  loss: 2.7758 (2.8534)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [39]  [ 50/312]  eta: 0:02:57  lr: 0.003954  min_lr: 0.003954  loss: 2.8779 (2.8494)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [39]  [ 60/312]  eta: 0:02:40  lr: 0.003954  min_lr: 0.003954  loss: 2.9248 (2.8742)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [39]  [ 70/312]  eta: 0:02:27  lr: 0.003954  min_lr: 0.003954  loss: 2.9648 (2.8757)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [39]  [ 80/312]  eta: 0:02:16  lr: 0.003954  min_lr: 0.003954  loss: 2.8089 (2.8457)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [39]  [ 90/312]  eta: 0:02:06  lr: 0.003953  min_lr: 0.003953  loss: 2.8209 (2.8601)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [39]  [100/312]  eta: 0:01:58  lr: 0.003953  min_lr: 0.003953  loss: 2.8570 (2.8677)  weight_decay: 0.0500 (0.0500)  time: 0.4341  data: 0.0004  max mem: 42573
Epoch: [39]  [110/312]  eta: 0:01:50  lr: 0.003953  min_lr: 0.003953  loss: 3.1021 (2.8665)  weight_decay: 0.0500 (0.0500)  time: 0.4341  data: 0.0004  max mem: 42573
Epoch: [39]  [120/312]  eta: 0:01:42  lr: 0.003953  min_lr: 0.003953  loss: 3.1841 (2.8895)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [39]  [130/312]  eta: 0:01:36  lr: 0.003953  min_lr: 0.003953  loss: 2.8294 (2.8784)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [39]  [140/312]  eta: 0:01:29  lr: 0.003953  min_lr: 0.003953  loss: 2.6847 (2.8774)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [39]  [150/312]  eta: 0:01:23  lr: 0.003952  min_lr: 0.003952  loss: 2.9954 (2.8834)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [39]  [160/312]  eta: 0:01:17  lr: 0.003952  min_lr: 0.003952  loss: 2.9850 (2.8858)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [39]  [170/312]  eta: 0:01:11  lr: 0.003952  min_lr: 0.003952  loss: 2.9850 (2.8866)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [39]  [180/312]  eta: 0:01:06  lr: 0.003952  min_lr: 0.003952  loss: 2.8023 (2.8715)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [39]  [190/312]  eta: 0:01:00  lr: 0.003952  min_lr: 0.003952  loss: 2.8023 (2.8763)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [39]  [200/312]  eta: 0:00:55  lr: 0.003952  min_lr: 0.003952  loss: 2.8968 (2.8787)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [39]  [210/312]  eta: 0:00:50  lr: 0.003951  min_lr: 0.003951  loss: 2.8488 (2.8698)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0003  max mem: 42573
Epoch: [39]  [220/312]  eta: 0:00:45  lr: 0.003951  min_lr: 0.003951  loss: 2.8596 (2.8764)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [39]  [230/312]  eta: 0:00:39  lr: 0.003951  min_lr: 0.003951  loss: 2.9617 (2.8776)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0003  max mem: 42573
Epoch: [39]  [240/312]  eta: 0:00:34  lr: 0.003951  min_lr: 0.003951  loss: 2.9457 (2.8835)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [39]  [250/312]  eta: 0:00:29  lr: 0.003951  min_lr: 0.003951  loss: 2.9121 (2.8787)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0004  max mem: 42573
Epoch: [39]  [260/312]  eta: 0:00:25  lr: 0.003951  min_lr: 0.003951  loss: 2.8609 (2.8829)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [39]  [270/312]  eta: 0:00:20  lr: 0.003951  min_lr: 0.003951  loss: 3.1034 (2.8892)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0003  max mem: 42573
Epoch: [39]  [280/312]  eta: 0:00:15  lr: 0.003950  min_lr: 0.003950  loss: 3.1581 (2.8904)  weight_decay: 0.0500 (0.0500)  time: 0.4349  data: 0.0009  max mem: 42573
Epoch: [39]  [290/312]  eta: 0:00:10  lr: 0.003950  min_lr: 0.003950  loss: 2.7521 (2.8849)  weight_decay: 0.0500 (0.0500)  time: 0.4342  data: 0.0008  max mem: 42573
Epoch: [39]  [300/312]  eta: 0:00:05  lr: 0.003950  min_lr: 0.003950  loss: 2.8975 (2.8857)  weight_decay: 0.0500 (0.0500)  time: 0.4324  data: 0.0001  max mem: 42573
Epoch: [39]  [310/312]  eta: 0:00:00  lr: 0.003950  min_lr: 0.003950  loss: 3.0599 (2.8923)  weight_decay: 0.0500 (0.0500)  time: 0.4324  data: 0.0001  max mem: 42573
Epoch: [39]  [311/312]  eta: 0:00:00  lr: 0.003950  min_lr: 0.003950  loss: 3.0219 (2.8902)  weight_decay: 0.0500 (0.0500)  time: 0.4324  data: 0.0001  max mem: 42573
Epoch: [39] Total time: 0:02:28 (0.4765 s / it)
Averaged stats: lr: 0.003950  min_lr: 0.003950  loss: 3.0219 (2.9150)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:00:41  loss: 1.2663 (1.2663)  acc1: 70.5729 (70.5729)  acc5: 88.2812 (88.2812)  time: 4.6246  data: 4.5153  max mem: 42573
Test:  [8/9]  eta: 0:00:00  loss: 1.6607 (1.5200)  acc1: 61.9792 (63.6480)  acc5: 86.1979 (85.2800)  time: 0.5898  data: 0.5018  max mem: 42573
Test: Total time: 0:00:05 (0.5968 s / it)
* Acc@1 64.132 Acc@5 85.512 loss 1.519
Accuracy of the model on the 50000 test images: 64.1%
Max accuracy: 66.65%
Epoch: [40]  [  0/312]  eta: 0:48:06  lr: 0.003950  min_lr: 0.003950  loss: 2.1489 (2.1489)  weight_decay: 0.0500 (0.0500)  time: 9.2526  data: 8.0606  max mem: 42573
Epoch: [40]  [ 10/312]  eta: 0:07:17  lr: 0.003950  min_lr: 0.003950  loss: 2.8273 (2.6899)  weight_decay: 0.0500 (0.0500)  time: 1.4497  data: 0.7420  max mem: 42573
Epoch: [40]  [ 20/312]  eta: 0:04:43  lr: 0.003950  min_lr: 0.003950  loss: 2.8539 (2.7757)  weight_decay: 0.0500 (0.0500)  time: 0.5553  data: 0.0053  max mem: 42573
Epoch: [40]  [ 30/312]  eta: 0:03:44  lr: 0.003949  min_lr: 0.003949  loss: 2.8539 (2.7743)  weight_decay: 0.0500 (0.0500)  time: 0.4376  data: 0.0004  max mem: 42573
Epoch: [40]  [ 40/312]  eta: 0:03:12  lr: 0.003949  min_lr: 0.003949  loss: 2.9697 (2.8209)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [40]  [ 50/312]  eta: 0:02:51  lr: 0.003949  min_lr: 0.003949  loss: 2.9697 (2.8481)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [40]  [ 60/312]  eta: 0:02:35  lr: 0.003949  min_lr: 0.003949  loss: 2.8908 (2.8479)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0005  max mem: 42573
Epoch: [40]  [ 70/312]  eta: 0:02:23  lr: 0.003949  min_lr: 0.003949  loss: 2.9665 (2.8699)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0005  max mem: 42573
Epoch: [40]  [ 80/312]  eta: 0:02:12  lr: 0.003949  min_lr: 0.003949  loss: 2.7550 (2.8500)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0004  max mem: 42573
Epoch: [40]  [ 90/312]  eta: 0:02:03  lr: 0.003948  min_lr: 0.003948  loss: 2.8279 (2.8641)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [40]  [100/312]  eta: 0:01:55  lr: 0.003948  min_lr: 0.003948  loss: 3.0509 (2.8587)  weight_decay: 0.0500 (0.0500)  time: 0.4349  data: 0.0004  max mem: 42573
Epoch: [40]  [110/312]  eta: 0:01:48  lr: 0.003948  min_lr: 0.003948  loss: 3.0639 (2.8638)  weight_decay: 0.0500 (0.0500)  time: 0.4348  data: 0.0004  max mem: 42573
Epoch: [40]  [120/312]  eta: 0:01:41  lr: 0.003948  min_lr: 0.003948  loss: 3.0678 (2.8710)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [40]  [130/312]  eta: 0:01:34  lr: 0.003948  min_lr: 0.003948  loss: 2.6981 (2.8575)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [40]  [140/312]  eta: 0:01:28  lr: 0.003948  min_lr: 0.003948  loss: 2.6603 (2.8609)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [40]  [150/312]  eta: 0:01:22  lr: 0.003947  min_lr: 0.003947  loss: 3.0505 (2.8734)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0004  max mem: 42573
Epoch: [40]  [160/312]  eta: 0:01:16  lr: 0.003947  min_lr: 0.003947  loss: 3.0418 (2.8733)  weight_decay: 0.0500 (0.0500)  time: 0.4341  data: 0.0003  max mem: 42573
Epoch: [40]  [170/312]  eta: 0:01:10  lr: 0.003947  min_lr: 0.003947  loss: 2.8493 (2.8709)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [40]  [180/312]  eta: 0:01:05  lr: 0.003947  min_lr: 0.003947  loss: 2.9941 (2.8759)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [40]  [190/312]  eta: 0:01:00  lr: 0.003947  min_lr: 0.003947  loss: 2.9941 (2.8795)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [40]  [200/312]  eta: 0:00:54  lr: 0.003947  min_lr: 0.003947  loss: 2.9757 (2.8830)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [40]  [210/312]  eta: 0:00:49  lr: 0.003946  min_lr: 0.003946  loss: 2.9855 (2.8845)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [40]  [220/312]  eta: 0:00:44  lr: 0.003946  min_lr: 0.003946  loss: 2.9855 (2.8908)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [40]  [230/312]  eta: 0:00:39  lr: 0.003946  min_lr: 0.003946  loss: 2.8830 (2.8854)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0003  max mem: 42573
Epoch: [40]  [240/312]  eta: 0:00:34  lr: 0.003946  min_lr: 0.003946  loss: 2.6770 (2.8752)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [40]  [250/312]  eta: 0:00:29  lr: 0.003946  min_lr: 0.003946  loss: 2.6770 (2.8717)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [40]  [260/312]  eta: 0:00:24  lr: 0.003946  min_lr: 0.003946  loss: 2.8260 (2.8729)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [40]  [270/312]  eta: 0:00:19  lr: 0.003945  min_lr: 0.003945  loss: 2.7342 (2.8671)  weight_decay: 0.0500 (0.0500)  time: 0.4341  data: 0.0004  max mem: 42573
Epoch: [40]  [280/312]  eta: 0:00:15  lr: 0.003945  min_lr: 0.003945  loss: 2.6701 (2.8628)  weight_decay: 0.0500 (0.0500)  time: 0.4345  data: 0.0009  max mem: 42573
Epoch: [40]  [290/312]  eta: 0:00:10  lr: 0.003945  min_lr: 0.003945  loss: 2.7618 (2.8641)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0008  max mem: 42573
Epoch: [40]  [300/312]  eta: 0:00:05  lr: 0.003945  min_lr: 0.003945  loss: 2.7618 (2.8631)  weight_decay: 0.0500 (0.0500)  time: 0.4323  data: 0.0001  max mem: 42573
Epoch: [40]  [310/312]  eta: 0:00:00  lr: 0.003945  min_lr: 0.003945  loss: 2.9480 (2.8645)  weight_decay: 0.0500 (0.0500)  time: 0.4324  data: 0.0001  max mem: 42573
Epoch: [40]  [311/312]  eta: 0:00:00  lr: 0.003945  min_lr: 0.003945  loss: 2.9480 (2.8645)  weight_decay: 0.0500 (0.0500)  time: 0.4324  data: 0.0001  max mem: 42573
Epoch: [40] Total time: 0:02:27 (0.4728 s / it)
Averaged stats: lr: 0.003945  min_lr: 0.003945  loss: 2.9480 (2.8868)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:00:44  loss: 1.0843 (1.0843)  acc1: 76.3021 (76.3021)  acc5: 92.1875 (92.1875)  time: 4.9217  data: 4.8121  max mem: 42573
Test:  [8/9]  eta: 0:00:00  loss: 1.5204 (1.3467)  acc1: 65.1042 (66.7840)  acc5: 86.4583 (87.3280)  time: 0.6257  data: 0.5347  max mem: 42573
Test: Total time: 0:00:05 (0.6503 s / it)
* Acc@1 66.626 Acc@5 87.440 loss 1.366
Accuracy of the model on the 50000 test images: 66.6%
Max accuracy: 66.65%
Epoch: [41]  [  0/312]  eta: 0:49:31  lr: 0.003945  min_lr: 0.003945  loss: 3.3621 (3.3621)  weight_decay: 0.0500 (0.0500)  time: 9.5229  data: 7.4165  max mem: 42573
Epoch: [41]  [ 10/312]  eta: 0:07:24  lr: 0.003945  min_lr: 0.003945  loss: 2.7373 (2.8520)  weight_decay: 0.0500 (0.0500)  time: 1.4712  data: 0.6746  max mem: 42573
Epoch: [41]  [ 20/312]  eta: 0:04:45  lr: 0.003944  min_lr: 0.003944  loss: 2.5859 (2.7582)  weight_decay: 0.0500 (0.0500)  time: 0.5496  data: 0.0003  max mem: 42573
Epoch: [41]  [ 30/312]  eta: 0:03:46  lr: 0.003944  min_lr: 0.003944  loss: 2.5859 (2.7218)  weight_decay: 0.0500 (0.0500)  time: 0.4332  data: 0.0003  max mem: 42573
Epoch: [41]  [ 40/312]  eta: 0:03:13  lr: 0.003944  min_lr: 0.003944  loss: 2.5182 (2.7038)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0003  max mem: 42573
Epoch: [41]  [ 50/312]  eta: 0:02:52  lr: 0.003944  min_lr: 0.003944  loss: 2.7358 (2.7267)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [41]  [ 60/312]  eta: 0:02:36  lr: 0.003944  min_lr: 0.003944  loss: 2.8159 (2.7445)  weight_decay: 0.0500 (0.0500)  time: 0.4332  data: 0.0004  max mem: 42573
Epoch: [41]  [ 70/312]  eta: 0:02:23  lr: 0.003944  min_lr: 0.003944  loss: 2.8786 (2.7695)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0003  max mem: 42573
Epoch: [41]  [ 80/312]  eta: 0:02:13  lr: 0.003943  min_lr: 0.003943  loss: 2.9178 (2.7828)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0003  max mem: 42573
Epoch: [41]  [ 90/312]  eta: 0:02:04  lr: 0.003943  min_lr: 0.003943  loss: 3.0147 (2.8080)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [41]  [100/312]  eta: 0:01:55  lr: 0.003943  min_lr: 0.003943  loss: 3.0946 (2.8299)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [41]  [110/312]  eta: 0:01:48  lr: 0.003943  min_lr: 0.003943  loss: 2.8227 (2.8102)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [41]  [120/312]  eta: 0:01:41  lr: 0.003943  min_lr: 0.003943  loss: 2.8227 (2.8272)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [41]  [130/312]  eta: 0:01:34  lr: 0.003943  min_lr: 0.003943  loss: 2.9926 (2.8338)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0003  max mem: 42573
Epoch: [41]  [140/312]  eta: 0:01:28  lr: 0.003942  min_lr: 0.003942  loss: 2.8962 (2.8365)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0003  max mem: 42573
Epoch: [41]  [150/312]  eta: 0:01:22  lr: 0.003942  min_lr: 0.003942  loss: 2.8929 (2.8409)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0003  max mem: 42573
Epoch: [41]  [160/312]  eta: 0:01:16  lr: 0.003942  min_lr: 0.003942  loss: 3.0533 (2.8538)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [41]  [170/312]  eta: 0:01:11  lr: 0.003942  min_lr: 0.003942  loss: 3.0517 (2.8488)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [41]  [180/312]  eta: 0:01:05  lr: 0.003942  min_lr: 0.003942  loss: 3.0345 (2.8570)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [41]  [190/312]  eta: 0:01:00  lr: 0.003942  min_lr: 0.003942  loss: 3.0345 (2.8561)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [41]  [200/312]  eta: 0:00:54  lr: 0.003941  min_lr: 0.003941  loss: 2.7430 (2.8424)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [41]  [210/312]  eta: 0:00:49  lr: 0.003941  min_lr: 0.003941  loss: 2.7038 (2.8403)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [41]  [220/312]  eta: 0:00:44  lr: 0.003941  min_lr: 0.003941  loss: 3.0406 (2.8407)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [41]  [230/312]  eta: 0:00:39  lr: 0.003941  min_lr: 0.003941  loss: 2.8076 (2.8344)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0003  max mem: 42573
Epoch: [41]  [240/312]  eta: 0:00:34  lr: 0.003941  min_lr: 0.003941  loss: 2.8076 (2.8396)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [41]  [250/312]  eta: 0:00:29  lr: 0.003940  min_lr: 0.003940  loss: 2.7023 (2.8326)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [41]  [260/312]  eta: 0:00:24  lr: 0.003940  min_lr: 0.003940  loss: 2.8901 (2.8366)  weight_decay: 0.0500 (0.0500)  time: 0.4348  data: 0.0004  max mem: 42573
Epoch: [41]  [270/312]  eta: 0:00:19  lr: 0.003940  min_lr: 0.003940  loss: 2.6581 (2.8272)  weight_decay: 0.0500 (0.0500)  time: 0.4347  data: 0.0004  max mem: 42573
Epoch: [41]  [280/312]  eta: 0:00:15  lr: 0.003940  min_lr: 0.003940  loss: 2.7877 (2.8321)  weight_decay: 0.0500 (0.0500)  time: 0.4348  data: 0.0009  max mem: 42573
Epoch: [41]  [290/312]  eta: 0:00:10  lr: 0.003940  min_lr: 0.003940  loss: 2.8753 (2.8273)  weight_decay: 0.0500 (0.0500)  time: 0.4341  data: 0.0008  max mem: 42573
Epoch: [41]  [300/312]  eta: 0:00:05  lr: 0.003940  min_lr: 0.003940  loss: 3.0236 (2.8360)  weight_decay: 0.0500 (0.0500)  time: 0.4324  data: 0.0001  max mem: 42573
Epoch: [41]  [310/312]  eta: 0:00:00  lr: 0.003939  min_lr: 0.003939  loss: 3.0236 (2.8356)  weight_decay: 0.0500 (0.0500)  time: 0.4324  data: 0.0001  max mem: 42573
Epoch: [41]  [311/312]  eta: 0:00:00  lr: 0.003939  min_lr: 0.003939  loss: 3.0383 (2.8362)  weight_decay: 0.0500 (0.0500)  time: 0.4324  data: 0.0001  max mem: 42573
Epoch: [41] Total time: 0:02:27 (0.4734 s / it)
Averaged stats: lr: 0.003939  min_lr: 0.003939  loss: 3.0383 (2.8901)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:00:44  loss: 1.0581 (1.0581)  acc1: 76.8229 (76.8229)  acc5: 89.8438 (89.8438)  time: 4.9649  data: 4.8554  max mem: 42573
Test:  [8/9]  eta: 0:00:00  loss: 1.4497 (1.3818)  acc1: 64.3229 (66.3680)  acc5: 86.4583 (87.1680)  time: 0.6285  data: 0.5396  max mem: 42573
Test: Total time: 0:00:05 (0.6422 s / it)
* Acc@1 66.630 Acc@5 87.238 loss 1.389
Accuracy of the model on the 50000 test images: 66.6%
Max accuracy: 66.65%
Epoch: [42]  [  0/312]  eta: 0:52:00  lr: 0.003939  min_lr: 0.003939  loss: 2.4950 (2.4950)  weight_decay: 0.0500 (0.0500)  time: 10.0016  data: 6.3147  max mem: 42573
Epoch: [42]  [ 10/312]  eta: 0:07:24  lr: 0.003939  min_lr: 0.003939  loss: 2.9155 (2.7531)  weight_decay: 0.0500 (0.0500)  time: 1.4723  data: 0.7213  max mem: 42573
Epoch: [42]  [ 20/312]  eta: 0:04:45  lr: 0.003939  min_lr: 0.003939  loss: 2.9600 (2.8452)  weight_decay: 0.0500 (0.0500)  time: 0.5263  data: 0.0812  max mem: 42573
Epoch: [42]  [ 30/312]  eta: 0:03:46  lr: 0.003939  min_lr: 0.003939  loss: 2.9884 (2.8782)  weight_decay: 0.0500 (0.0500)  time: 0.4332  data: 0.0004  max mem: 42573
Epoch: [42]  [ 40/312]  eta: 0:03:13  lr: 0.003939  min_lr: 0.003939  loss: 3.0352 (2.9108)  weight_decay: 0.0500 (0.0500)  time: 0.4332  data: 0.0004  max mem: 42573
Epoch: [42]  [ 50/312]  eta: 0:02:52  lr: 0.003939  min_lr: 0.003939  loss: 3.0615 (2.9169)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [42]  [ 60/312]  eta: 0:02:36  lr: 0.003938  min_lr: 0.003938  loss: 2.8974 (2.8981)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [42]  [ 70/312]  eta: 0:02:23  lr: 0.003938  min_lr: 0.003938  loss: 2.8812 (2.8980)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [42]  [ 80/312]  eta: 0:02:13  lr: 0.003938  min_lr: 0.003938  loss: 2.8606 (2.8903)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [42]  [ 90/312]  eta: 0:02:04  lr: 0.003938  min_lr: 0.003938  loss: 2.8300 (2.8840)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [42]  [100/312]  eta: 0:01:55  lr: 0.003938  min_lr: 0.003938  loss: 2.9391 (2.9012)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [42]  [110/312]  eta: 0:01:48  lr: 0.003937  min_lr: 0.003937  loss: 3.1947 (2.9126)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0004  max mem: 42573
Epoch: [42]  [120/312]  eta: 0:01:41  lr: 0.003937  min_lr: 0.003937  loss: 2.8988 (2.9021)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [42]  [130/312]  eta: 0:01:34  lr: 0.003937  min_lr: 0.003937  loss: 2.6518 (2.8936)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [42]  [140/312]  eta: 0:01:28  lr: 0.003937  min_lr: 0.003937  loss: 2.9867 (2.8952)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0004  max mem: 42573
Epoch: [42]  [150/312]  eta: 0:01:22  lr: 0.003937  min_lr: 0.003937  loss: 3.0293 (2.8997)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0004  max mem: 42573
Epoch: [42]  [160/312]  eta: 0:01:16  lr: 0.003937  min_lr: 0.003937  loss: 2.9950 (2.8969)  weight_decay: 0.0500 (0.0500)  time: 0.4341  data: 0.0004  max mem: 42573
Epoch: [42]  [170/312]  eta: 0:01:11  lr: 0.003936  min_lr: 0.003936  loss: 2.9462 (2.8979)  weight_decay: 0.0500 (0.0500)  time: 0.4341  data: 0.0004  max mem: 42573
Epoch: [42]  [180/312]  eta: 0:01:05  lr: 0.003936  min_lr: 0.003936  loss: 2.9462 (2.8993)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [42]  [190/312]  eta: 0:01:00  lr: 0.003936  min_lr: 0.003936  loss: 2.9881 (2.9066)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0004  max mem: 42573
Epoch: [42]  [200/312]  eta: 0:00:54  lr: 0.003936  min_lr: 0.003936  loss: 3.1088 (2.9139)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0003  max mem: 42573
Epoch: [42]  [210/312]  eta: 0:00:49  lr: 0.003936  min_lr: 0.003936  loss: 3.0577 (2.9139)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0003  max mem: 42573
Epoch: [42]  [220/312]  eta: 0:00:44  lr: 0.003935  min_lr: 0.003935  loss: 3.0577 (2.9140)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [42]  [230/312]  eta: 0:00:39  lr: 0.003935  min_lr: 0.003935  loss: 3.0741 (2.9142)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [42]  [240/312]  eta: 0:00:34  lr: 0.003935  min_lr: 0.003935  loss: 3.1138 (2.9188)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [42]  [250/312]  eta: 0:00:29  lr: 0.003935  min_lr: 0.003935  loss: 3.0654 (2.9174)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [42]  [260/312]  eta: 0:00:24  lr: 0.003935  min_lr: 0.003935  loss: 3.0477 (2.9162)  weight_decay: 0.0500 (0.0500)  time: 0.4381  data: 0.0004  max mem: 42573
Epoch: [42]  [270/312]  eta: 0:00:20  lr: 0.003935  min_lr: 0.003935  loss: 2.5479 (2.9054)  weight_decay: 0.0500 (0.0500)  time: 0.4381  data: 0.0004  max mem: 42573
Epoch: [42]  [280/312]  eta: 0:00:15  lr: 0.003934  min_lr: 0.003934  loss: 2.7669 (2.9066)  weight_decay: 0.0500 (0.0500)  time: 0.4347  data: 0.0009  max mem: 42573
Epoch: [42]  [290/312]  eta: 0:00:10  lr: 0.003934  min_lr: 0.003934  loss: 3.1448 (2.9143)  weight_decay: 0.0500 (0.0500)  time: 0.4341  data: 0.0008  max mem: 42573
Epoch: [42]  [300/312]  eta: 0:00:05  lr: 0.003934  min_lr: 0.003934  loss: 2.8533 (2.9082)  weight_decay: 0.0500 (0.0500)  time: 0.4326  data: 0.0001  max mem: 42573
Epoch: [42]  [310/312]  eta: 0:00:00  lr: 0.003934  min_lr: 0.003934  loss: 2.7127 (2.9034)  weight_decay: 0.0500 (0.0500)  time: 0.4323  data: 0.0001  max mem: 42573
Epoch: [42]  [311/312]  eta: 0:00:00  lr: 0.003934  min_lr: 0.003934  loss: 2.7127 (2.9031)  weight_decay: 0.0500 (0.0500)  time: 0.4324  data: 0.0001  max mem: 42573
Epoch: [42] Total time: 0:02:27 (0.4736 s / it)
Averaged stats: lr: 0.003934  min_lr: 0.003934  loss: 2.7127 (2.8854)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:00:42  loss: 1.0566 (1.0566)  acc1: 75.0000 (75.0000)  acc5: 91.4062 (91.4062)  time: 4.7602  data: 4.6508  max mem: 42573
Test:  [8/9]  eta: 0:00:00  loss: 1.4019 (1.3298)  acc1: 68.7500 (66.8800)  acc5: 88.8021 (88.0320)  time: 0.6058  data: 0.5168  max mem: 42573
Test: Total time: 0:00:05 (0.6304 s / it)
* Acc@1 67.480 Acc@5 87.756 loss 1.336
Accuracy of the model on the 50000 test images: 67.5%
Max accuracy: 67.48%
Epoch: [43]  [  0/312]  eta: 0:50:18  lr: 0.003934  min_lr: 0.003934  loss: 2.2952 (2.2952)  weight_decay: 0.0500 (0.0500)  time: 9.6757  data: 6.5012  max mem: 42573
Epoch: [43]  [ 10/312]  eta: 0:07:19  lr: 0.003934  min_lr: 0.003934  loss: 2.2952 (2.6829)  weight_decay: 0.0500 (0.0500)  time: 1.4538  data: 0.6759  max mem: 42573
Epoch: [43]  [ 20/312]  eta: 0:04:42  lr: 0.003933  min_lr: 0.003933  loss: 2.9884 (2.8159)  weight_decay: 0.0500 (0.0500)  time: 0.5325  data: 0.0469  max mem: 42573
Epoch: [43]  [ 30/312]  eta: 0:03:44  lr: 0.003933  min_lr: 0.003933  loss: 3.0839 (2.8355)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0003  max mem: 42573
Epoch: [43]  [ 40/312]  eta: 0:03:12  lr: 0.003933  min_lr: 0.003933  loss: 3.0839 (2.8916)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0003  max mem: 42573
Epoch: [43]  [ 50/312]  eta: 0:02:51  lr: 0.003933  min_lr: 0.003933  loss: 2.9707 (2.8642)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [43]  [ 60/312]  eta: 0:02:35  lr: 0.003933  min_lr: 0.003933  loss: 2.8250 (2.8879)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0004  max mem: 42573
Epoch: [43]  [ 70/312]  eta: 0:02:23  lr: 0.003932  min_lr: 0.003932  loss: 2.7797 (2.8543)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [43]  [ 80/312]  eta: 0:02:12  lr: 0.003932  min_lr: 0.003932  loss: 2.7797 (2.8831)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [43]  [ 90/312]  eta: 0:02:03  lr: 0.003932  min_lr: 0.003932  loss: 3.0327 (2.8809)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [43]  [100/312]  eta: 0:01:55  lr: 0.003932  min_lr: 0.003932  loss: 3.0343 (2.8850)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [43]  [110/312]  eta: 0:01:48  lr: 0.003932  min_lr: 0.003932  loss: 3.0891 (2.8982)  weight_decay: 0.0500 (0.0500)  time: 0.4341  data: 0.0004  max mem: 42573
Epoch: [43]  [120/312]  eta: 0:01:41  lr: 0.003932  min_lr: 0.003932  loss: 3.1467 (2.9069)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [43]  [130/312]  eta: 0:01:34  lr: 0.003931  min_lr: 0.003931  loss: 3.1467 (2.9214)  weight_decay: 0.0500 (0.0500)  time: 0.4341  data: 0.0004  max mem: 42573
Epoch: [43]  [140/312]  eta: 0:01:28  lr: 0.003931  min_lr: 0.003931  loss: 2.9187 (2.9035)  weight_decay: 0.0500 (0.0500)  time: 0.4341  data: 0.0004  max mem: 42573
Epoch: [43]  [150/312]  eta: 0:01:22  lr: 0.003931  min_lr: 0.003931  loss: 2.8037 (2.9077)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0004  max mem: 42573
Epoch: [43]  [160/312]  eta: 0:01:16  lr: 0.003931  min_lr: 0.003931  loss: 3.0054 (2.9021)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0004  max mem: 42573
Epoch: [43]  [170/312]  eta: 0:01:10  lr: 0.003931  min_lr: 0.003931  loss: 3.0054 (2.9096)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [43]  [180/312]  eta: 0:01:05  lr: 0.003930  min_lr: 0.003930  loss: 3.0386 (2.9088)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0003  max mem: 42573
Epoch: [43]  [190/312]  eta: 0:01:00  lr: 0.003930  min_lr: 0.003930  loss: 2.7627 (2.8958)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0003  max mem: 42573
Epoch: [43]  [200/312]  eta: 0:00:54  lr: 0.003930  min_lr: 0.003930  loss: 2.7516 (2.8877)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [43]  [210/312]  eta: 0:00:49  lr: 0.003930  min_lr: 0.003930  loss: 2.7585 (2.8770)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [43]  [220/312]  eta: 0:00:44  lr: 0.003930  min_lr: 0.003930  loss: 3.0169 (2.8860)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0003  max mem: 42573
Epoch: [43]  [230/312]  eta: 0:00:39  lr: 0.003930  min_lr: 0.003930  loss: 3.1982 (2.9026)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [43]  [240/312]  eta: 0:00:34  lr: 0.003929  min_lr: 0.003929  loss: 3.0329 (2.9002)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0003  max mem: 42573
Epoch: [43]  [250/312]  eta: 0:00:29  lr: 0.003929  min_lr: 0.003929  loss: 2.8989 (2.9020)  weight_decay: 0.0500 (0.0500)  time: 0.4415  data: 0.0003  max mem: 42573
Epoch: [43]  [260/312]  eta: 0:00:24  lr: 0.003929  min_lr: 0.003929  loss: 2.9408 (2.9047)  weight_decay: 0.0500 (0.0500)  time: 0.4415  data: 0.0004  max mem: 42573
Epoch: [43]  [270/312]  eta: 0:00:19  lr: 0.003929  min_lr: 0.003929  loss: 2.9061 (2.9037)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [43]  [280/312]  eta: 0:00:15  lr: 0.003929  min_lr: 0.003929  loss: 2.5590 (2.8951)  weight_decay: 0.0500 (0.0500)  time: 0.4350  data: 0.0010  max mem: 42573
Epoch: [43]  [290/312]  eta: 0:00:10  lr: 0.003928  min_lr: 0.003928  loss: 2.9393 (2.8928)  weight_decay: 0.0500 (0.0500)  time: 0.4343  data: 0.0008  max mem: 42573
Epoch: [43]  [300/312]  eta: 0:00:05  lr: 0.003928  min_lr: 0.003928  loss: 3.0899 (2.8971)  weight_decay: 0.0500 (0.0500)  time: 0.4324  data: 0.0001  max mem: 42573
Epoch: [43]  [310/312]  eta: 0:00:00  lr: 0.003928  min_lr: 0.003928  loss: 3.0454 (2.8990)  weight_decay: 0.0500 (0.0500)  time: 0.4323  data: 0.0001  max mem: 42573
Epoch: [43]  [311/312]  eta: 0:00:00  lr: 0.003928  min_lr: 0.003928  loss: 3.0454 (2.9003)  weight_decay: 0.0500 (0.0500)  time: 0.4324  data: 0.0001  max mem: 42573
Epoch: [43] Total time: 0:02:27 (0.4732 s / it)
Averaged stats: lr: 0.003928  min_lr: 0.003928  loss: 3.0454 (2.8673)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:00:43  loss: 1.0767 (1.0767)  acc1: 72.3958 (72.3958)  acc5: 93.7500 (93.7500)  time: 4.8559  data: 4.7466  max mem: 42573
Test:  [8/9]  eta: 0:00:00  loss: 1.5267 (1.4668)  acc1: 65.3646 (64.5760)  acc5: 84.8958 (86.2400)  time: 0.6148  data: 0.5275  max mem: 42573
Test: Total time: 0:00:05 (0.6369 s / it)
* Acc@1 65.120 Acc@5 86.286 loss 1.461
Accuracy of the model on the 50000 test images: 65.1%
Max accuracy: 67.48%
Epoch: [44]  [  0/312]  eta: 0:50:10  lr: 0.003928  min_lr: 0.003928  loss: 3.4991 (3.4991)  weight_decay: 0.0500 (0.0500)  time: 9.6484  data: 8.8572  max mem: 42573
Epoch: [44]  [ 10/312]  eta: 0:07:18  lr: 0.003928  min_lr: 0.003928  loss: 2.6472 (2.7346)  weight_decay: 0.0500 (0.0500)  time: 1.4527  data: 0.8057  max mem: 42573
Epoch: [44]  [ 20/312]  eta: 0:04:42  lr: 0.003928  min_lr: 0.003928  loss: 2.6472 (2.8014)  weight_decay: 0.0500 (0.0500)  time: 0.5333  data: 0.0005  max mem: 42573
Epoch: [44]  [ 30/312]  eta: 0:03:44  lr: 0.003927  min_lr: 0.003927  loss: 2.8754 (2.8003)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [44]  [ 40/312]  eta: 0:03:12  lr: 0.003927  min_lr: 0.003927  loss: 2.8903 (2.8185)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [44]  [ 50/312]  eta: 0:02:51  lr: 0.003927  min_lr: 0.003927  loss: 3.1469 (2.8833)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [44]  [ 60/312]  eta: 0:02:35  lr: 0.003927  min_lr: 0.003927  loss: 2.8635 (2.8427)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [44]  [ 70/312]  eta: 0:02:23  lr: 0.003927  min_lr: 0.003927  loss: 2.6054 (2.8279)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [44]  [ 80/312]  eta: 0:02:12  lr: 0.003926  min_lr: 0.003926  loss: 2.9134 (2.8583)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [44]  [ 90/312]  eta: 0:02:03  lr: 0.003926  min_lr: 0.003926  loss: 2.8238 (2.8360)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [44]  [100/312]  eta: 0:01:55  lr: 0.003926  min_lr: 0.003926  loss: 2.8238 (2.8405)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [44]  [110/312]  eta: 0:01:47  lr: 0.003926  min_lr: 0.003926  loss: 3.0429 (2.8708)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [44]  [120/312]  eta: 0:01:41  lr: 0.003926  min_lr: 0.003926  loss: 3.0429 (2.8751)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [44]  [130/312]  eta: 0:01:34  lr: 0.003925  min_lr: 0.003925  loss: 2.7761 (2.8775)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0004  max mem: 42573
Epoch: [44]  [140/312]  eta: 0:01:28  lr: 0.003925  min_lr: 0.003925  loss: 2.6835 (2.8587)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [44]  [150/312]  eta: 0:01:22  lr: 0.003925  min_lr: 0.003925  loss: 2.8522 (2.8607)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [44]  [160/312]  eta: 0:01:16  lr: 0.003925  min_lr: 0.003925  loss: 2.9198 (2.8628)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [44]  [170/312]  eta: 0:01:10  lr: 0.003925  min_lr: 0.003925  loss: 2.8015 (2.8506)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0004  max mem: 42573
Epoch: [44]  [180/312]  eta: 0:01:05  lr: 0.003924  min_lr: 0.003924  loss: 2.8015 (2.8491)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [44]  [190/312]  eta: 0:01:00  lr: 0.003924  min_lr: 0.003924  loss: 3.0717 (2.8566)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [44]  [200/312]  eta: 0:00:54  lr: 0.003924  min_lr: 0.003924  loss: 2.8843 (2.8448)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [44]  [210/312]  eta: 0:00:49  lr: 0.003924  min_lr: 0.003924  loss: 2.5840 (2.8353)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [44]  [220/312]  eta: 0:00:44  lr: 0.003924  min_lr: 0.003924  loss: 2.7964 (2.8382)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0004  max mem: 42573
Epoch: [44]  [230/312]  eta: 0:00:39  lr: 0.003923  min_lr: 0.003923  loss: 2.9940 (2.8375)  weight_decay: 0.0500 (0.0500)  time: 0.4372  data: 0.0004  max mem: 42573
Epoch: [44]  [240/312]  eta: 0:00:34  lr: 0.003923  min_lr: 0.003923  loss: 2.9578 (2.8379)  weight_decay: 0.0500 (0.0500)  time: 0.4371  data: 0.0004  max mem: 42573
Epoch: [44]  [250/312]  eta: 0:00:29  lr: 0.003923  min_lr: 0.003923  loss: 3.0274 (2.8394)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [44]  [260/312]  eta: 0:00:24  lr: 0.003923  min_lr: 0.003923  loss: 3.0274 (2.8399)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [44]  [270/312]  eta: 0:00:19  lr: 0.003923  min_lr: 0.003923  loss: 3.0994 (2.8527)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [44]  [280/312]  eta: 0:00:15  lr: 0.003922  min_lr: 0.003922  loss: 3.0994 (2.8570)  weight_decay: 0.0500 (0.0500)  time: 0.4344  data: 0.0009  max mem: 42573
Epoch: [44]  [290/312]  eta: 0:00:10  lr: 0.003922  min_lr: 0.003922  loss: 2.8208 (2.8503)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0008  max mem: 42573
Epoch: [44]  [300/312]  eta: 0:00:05  lr: 0.003922  min_lr: 0.003922  loss: 2.4960 (2.8367)  weight_decay: 0.0500 (0.0500)  time: 0.4325  data: 0.0001  max mem: 42573
Epoch: [44]  [310/312]  eta: 0:00:00  lr: 0.003922  min_lr: 0.003922  loss: 2.5801 (2.8384)  weight_decay: 0.0500 (0.0500)  time: 0.4325  data: 0.0001  max mem: 42573
Epoch: [44]  [311/312]  eta: 0:00:00  lr: 0.003922  min_lr: 0.003922  loss: 2.6384 (2.8382)  weight_decay: 0.0500 (0.0500)  time: 0.4325  data: 0.0001  max mem: 42573
Epoch: [44] Total time: 0:02:27 (0.4727 s / it)
Averaged stats: lr: 0.003922  min_lr: 0.003922  loss: 2.6384 (2.8699)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:00:43  loss: 1.1633 (1.1633)  acc1: 75.7812 (75.7812)  acc5: 89.3229 (89.3229)  time: 4.8745  data: 4.7654  max mem: 42573
Test:  [8/9]  eta: 0:00:00  loss: 1.5739 (1.4134)  acc1: 64.0625 (65.6960)  acc5: 86.9792 (86.5920)  time: 0.6189  data: 0.5295  max mem: 42573
Test: Total time: 0:00:05 (0.6422 s / it)
* Acc@1 65.986 Acc@5 86.732 loss 1.430
Accuracy of the model on the 50000 test images: 66.0%
Max accuracy: 67.48%
Epoch: [45]  [  0/312]  eta: 0:49:25  lr: 0.003922  min_lr: 0.003922  loss: 3.0280 (3.0280)  weight_decay: 0.0500 (0.0500)  time: 9.5040  data: 8.0642  max mem: 42573
Epoch: [45]  [ 10/312]  eta: 0:07:04  lr: 0.003922  min_lr: 0.003922  loss: 2.7443 (2.7665)  weight_decay: 0.0500 (0.0500)  time: 1.4058  data: 0.7335  max mem: 42573
Epoch: [45]  [ 20/312]  eta: 0:04:35  lr: 0.003921  min_lr: 0.003921  loss: 3.0342 (2.9536)  weight_decay: 0.0500 (0.0500)  time: 0.5163  data: 0.0004  max mem: 42573
Epoch: [45]  [ 30/312]  eta: 0:03:39  lr: 0.003921  min_lr: 0.003921  loss: 3.1180 (2.9627)  weight_decay: 0.0500 (0.0500)  time: 0.4351  data: 0.0004  max mem: 42573
Epoch: [45]  [ 40/312]  eta: 0:03:09  lr: 0.003921  min_lr: 0.003921  loss: 2.8322 (2.9260)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [45]  [ 50/312]  eta: 0:02:48  lr: 0.003921  min_lr: 0.003921  loss: 2.9018 (2.9422)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [45]  [ 60/312]  eta: 0:02:33  lr: 0.003921  min_lr: 0.003921  loss: 2.9018 (2.9117)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [45]  [ 70/312]  eta: 0:02:21  lr: 0.003920  min_lr: 0.003920  loss: 2.6235 (2.8766)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [45]  [ 80/312]  eta: 0:02:11  lr: 0.003920  min_lr: 0.003920  loss: 2.8396 (2.8901)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [45]  [ 90/312]  eta: 0:02:02  lr: 0.003920  min_lr: 0.003920  loss: 2.9799 (2.8790)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [45]  [100/312]  eta: 0:01:54  lr: 0.003920  min_lr: 0.003920  loss: 2.8745 (2.8734)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0003  max mem: 42573
Epoch: [45]  [110/312]  eta: 0:01:47  lr: 0.003920  min_lr: 0.003920  loss: 2.6322 (2.8313)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0004  max mem: 42573
Epoch: [45]  [120/312]  eta: 0:01:40  lr: 0.003919  min_lr: 0.003919  loss: 2.7470 (2.8408)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0004  max mem: 42573
Epoch: [45]  [130/312]  eta: 0:01:33  lr: 0.003919  min_lr: 0.003919  loss: 2.8206 (2.8300)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [45]  [140/312]  eta: 0:01:27  lr: 0.003919  min_lr: 0.003919  loss: 2.7063 (2.8272)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [45]  [150/312]  eta: 0:01:21  lr: 0.003919  min_lr: 0.003919  loss: 2.7063 (2.8176)  weight_decay: 0.0500 (0.0500)  time: 0.4342  data: 0.0004  max mem: 42573
Epoch: [45]  [160/312]  eta: 0:01:16  lr: 0.003919  min_lr: 0.003919  loss: 2.6691 (2.8212)  weight_decay: 0.0500 (0.0500)  time: 0.4341  data: 0.0004  max mem: 42573
Epoch: [45]  [170/312]  eta: 0:01:10  lr: 0.003918  min_lr: 0.003918  loss: 2.9719 (2.8216)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [45]  [180/312]  eta: 0:01:05  lr: 0.003918  min_lr: 0.003918  loss: 2.6559 (2.8078)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0003  max mem: 42573
Epoch: [45]  [190/312]  eta: 0:00:59  lr: 0.003918  min_lr: 0.003918  loss: 2.6162 (2.8088)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [45]  [200/312]  eta: 0:00:54  lr: 0.003918  min_lr: 0.003918  loss: 2.9504 (2.8138)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [45]  [210/312]  eta: 0:00:49  lr: 0.003918  min_lr: 0.003918  loss: 3.0164 (2.8184)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [45]  [220/312]  eta: 0:00:44  lr: 0.003917  min_lr: 0.003917  loss: 2.9095 (2.8157)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0003  max mem: 42573
Epoch: [45]  [230/312]  eta: 0:00:39  lr: 0.003917  min_lr: 0.003917  loss: 2.5197 (2.8033)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0003  max mem: 42573
Epoch: [45]  [240/312]  eta: 0:00:34  lr: 0.003917  min_lr: 0.003917  loss: 2.4213 (2.7903)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0003  max mem: 42573
Epoch: [45]  [250/312]  eta: 0:00:29  lr: 0.003917  min_lr: 0.003917  loss: 2.8483 (2.7949)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [45]  [260/312]  eta: 0:00:24  lr: 0.003917  min_lr: 0.003917  loss: 3.0439 (2.7997)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [45]  [270/312]  eta: 0:00:19  lr: 0.003916  min_lr: 0.003916  loss: 3.0270 (2.8029)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [45]  [280/312]  eta: 0:00:15  lr: 0.003916  min_lr: 0.003916  loss: 2.9982 (2.8038)  weight_decay: 0.0500 (0.0500)  time: 0.4350  data: 0.0009  max mem: 42573
Epoch: [45]  [290/312]  eta: 0:00:10  lr: 0.003916  min_lr: 0.003916  loss: 2.6802 (2.7995)  weight_decay: 0.0500 (0.0500)  time: 0.4344  data: 0.0008  max mem: 42573
Epoch: [45]  [300/312]  eta: 0:00:05  lr: 0.003916  min_lr: 0.003916  loss: 2.7526 (2.8029)  weight_decay: 0.0500 (0.0500)  time: 0.4325  data: 0.0001  max mem: 42573
Epoch: [45]  [310/312]  eta: 0:00:00  lr: 0.003916  min_lr: 0.003916  loss: 2.8781 (2.8059)  weight_decay: 0.0500 (0.0500)  time: 0.4324  data: 0.0001  max mem: 42573
Epoch: [45]  [311/312]  eta: 0:00:00  lr: 0.003916  min_lr: 0.003916  loss: 2.8598 (2.8038)  weight_decay: 0.0500 (0.0500)  time: 0.4323  data: 0.0001  max mem: 42573
Epoch: [45] Total time: 0:02:26 (0.4709 s / it)
Averaged stats: lr: 0.003916  min_lr: 0.003916  loss: 2.8598 (2.8341)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:00:42  loss: 1.1651 (1.1651)  acc1: 74.7396 (74.7396)  acc5: 90.6250 (90.6250)  time: 4.7624  data: 4.6537  max mem: 42573
Test:  [8/9]  eta: 0:00:00  loss: 1.4137 (1.4005)  acc1: 67.1875 (66.3040)  acc5: 88.2812 (86.7520)  time: 0.6059  data: 0.5172  max mem: 42573
Test: Total time: 0:00:05 (0.6144 s / it)
* Acc@1 66.548 Acc@5 87.346 loss 1.386
Accuracy of the model on the 50000 test images: 66.5%
Max accuracy: 67.48%
Epoch: [46]  [  0/312]  eta: 0:49:50  lr: 0.003916  min_lr: 0.003916  loss: 2.9048 (2.9048)  weight_decay: 0.0500 (0.0500)  time: 9.5858  data: 6.2062  max mem: 42573
Epoch: [46]  [ 10/312]  eta: 0:07:30  lr: 0.003915  min_lr: 0.003915  loss: 2.9048 (2.8247)  weight_decay: 0.0500 (0.0500)  time: 1.4920  data: 0.5979  max mem: 42573
Epoch: [46]  [ 20/312]  eta: 0:04:48  lr: 0.003915  min_lr: 0.003915  loss: 2.8376 (2.8640)  weight_decay: 0.0500 (0.0500)  time: 0.5580  data: 0.0187  max mem: 42573
Epoch: [46]  [ 30/312]  eta: 0:03:48  lr: 0.003915  min_lr: 0.003915  loss: 2.8684 (2.8830)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [46]  [ 40/312]  eta: 0:03:15  lr: 0.003915  min_lr: 0.003915  loss: 2.9120 (2.8886)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0003  max mem: 42573
Epoch: [46]  [ 50/312]  eta: 0:02:53  lr: 0.003914  min_lr: 0.003914  loss: 3.1044 (2.9334)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0003  max mem: 42573
Epoch: [46]  [ 60/312]  eta: 0:02:37  lr: 0.003914  min_lr: 0.003914  loss: 3.1044 (2.9156)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [46]  [ 70/312]  eta: 0:02:24  lr: 0.003914  min_lr: 0.003914  loss: 2.8429 (2.9086)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [46]  [ 80/312]  eta: 0:02:13  lr: 0.003914  min_lr: 0.003914  loss: 2.6231 (2.8686)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [46]  [ 90/312]  eta: 0:02:04  lr: 0.003914  min_lr: 0.003914  loss: 2.6112 (2.8469)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [46]  [100/312]  eta: 0:01:56  lr: 0.003913  min_lr: 0.003913  loss: 2.8067 (2.8374)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [46]  [110/312]  eta: 0:01:48  lr: 0.003913  min_lr: 0.003913  loss: 2.9332 (2.8397)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [46]  [120/312]  eta: 0:01:41  lr: 0.003913  min_lr: 0.003913  loss: 2.9332 (2.8468)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [46]  [130/312]  eta: 0:01:35  lr: 0.003913  min_lr: 0.003913  loss: 2.9336 (2.8605)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [46]  [140/312]  eta: 0:01:28  lr: 0.003913  min_lr: 0.003913  loss: 2.9200 (2.8588)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [46]  [150/312]  eta: 0:01:22  lr: 0.003912  min_lr: 0.003912  loss: 2.8785 (2.8591)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [46]  [160/312]  eta: 0:01:16  lr: 0.003912  min_lr: 0.003912  loss: 2.8595 (2.8501)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [46]  [170/312]  eta: 0:01:11  lr: 0.003912  min_lr: 0.003912  loss: 2.9942 (2.8578)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0004  max mem: 42573
Epoch: [46]  [180/312]  eta: 0:01:05  lr: 0.003912  min_lr: 0.003912  loss: 2.9552 (2.8517)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0004  max mem: 42573
Epoch: [46]  [190/312]  eta: 0:01:00  lr: 0.003912  min_lr: 0.003912  loss: 2.8254 (2.8503)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [46]  [200/312]  eta: 0:00:55  lr: 0.003911  min_lr: 0.003911  loss: 2.8254 (2.8448)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0003  max mem: 42573
Epoch: [46]  [210/312]  eta: 0:00:49  lr: 0.003911  min_lr: 0.003911  loss: 2.7583 (2.8402)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [46]  [220/312]  eta: 0:00:44  lr: 0.003911  min_lr: 0.003911  loss: 2.7583 (2.8330)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [46]  [230/312]  eta: 0:00:39  lr: 0.003911  min_lr: 0.003911  loss: 2.7462 (2.8283)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [46]  [240/312]  eta: 0:00:34  lr: 0.003910  min_lr: 0.003910  loss: 2.8991 (2.8328)  weight_decay: 0.0500 (0.0500)  time: 0.4372  data: 0.0004  max mem: 42573
Epoch: [46]  [250/312]  eta: 0:00:29  lr: 0.003910  min_lr: 0.003910  loss: 2.8953 (2.8268)  weight_decay: 0.0500 (0.0500)  time: 0.4373  data: 0.0003  max mem: 42573
Epoch: [46]  [260/312]  eta: 0:00:24  lr: 0.003910  min_lr: 0.003910  loss: 2.8953 (2.8359)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0003  max mem: 42573
Epoch: [46]  [270/312]  eta: 0:00:20  lr: 0.003910  min_lr: 0.003910  loss: 3.1092 (2.8485)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0004  max mem: 42573
Epoch: [46]  [280/312]  eta: 0:00:15  lr: 0.003910  min_lr: 0.003910  loss: 3.0982 (2.8518)  weight_decay: 0.0500 (0.0500)  time: 0.4350  data: 0.0009  max mem: 42573
Epoch: [46]  [290/312]  eta: 0:00:10  lr: 0.003909  min_lr: 0.003909  loss: 3.0486 (2.8554)  weight_decay: 0.0500 (0.0500)  time: 0.4344  data: 0.0008  max mem: 42573
Epoch: [46]  [300/312]  eta: 0:00:05  lr: 0.003909  min_lr: 0.003909  loss: 2.9458 (2.8572)  weight_decay: 0.0500 (0.0500)  time: 0.4326  data: 0.0001  max mem: 42573
Epoch: [46]  [310/312]  eta: 0:00:00  lr: 0.003909  min_lr: 0.003909  loss: 2.7789 (2.8560)  weight_decay: 0.0500 (0.0500)  time: 0.4324  data: 0.0001  max mem: 42573
Epoch: [46]  [311/312]  eta: 0:00:00  lr: 0.003909  min_lr: 0.003909  loss: 2.8565 (2.8569)  weight_decay: 0.0500 (0.0500)  time: 0.4324  data: 0.0001  max mem: 42573
Epoch: [46] Total time: 0:02:27 (0.4743 s / it)
Averaged stats: lr: 0.003909  min_lr: 0.003909  loss: 2.8565 (2.8415)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:00:42  loss: 0.9754 (0.9754)  acc1: 77.0833 (77.0833)  acc5: 91.9271 (91.9271)  time: 4.7188  data: 4.6094  max mem: 42573
Test:  [8/9]  eta: 0:00:00  loss: 1.5359 (1.3810)  acc1: 63.8021 (66.4000)  acc5: 85.9375 (87.5520)  time: 0.6006  data: 0.5122  max mem: 42573
Test: Total time: 0:00:05 (0.6107 s / it)
* Acc@1 67.138 Acc@5 87.624 loss 1.364
Accuracy of the model on the 50000 test images: 67.1%
Max accuracy: 67.48%
Epoch: [47]  [  0/312]  eta: 0:50:29  lr: 0.003909  min_lr: 0.003909  loss: 2.1210 (2.1210)  weight_decay: 0.0500 (0.0500)  time: 9.7104  data: 8.2309  max mem: 42573
Epoch: [47]  [ 10/312]  eta: 0:07:35  lr: 0.003909  min_lr: 0.003909  loss: 2.7587 (2.8540)  weight_decay: 0.0500 (0.0500)  time: 1.5069  data: 0.7531  max mem: 42573
Epoch: [47]  [ 20/312]  eta: 0:04:50  lr: 0.003909  min_lr: 0.003909  loss: 2.7290 (2.7591)  weight_decay: 0.0500 (0.0500)  time: 0.5600  data: 0.0028  max mem: 42573
Epoch: [47]  [ 30/312]  eta: 0:03:49  lr: 0.003908  min_lr: 0.003908  loss: 2.9169 (2.8743)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [47]  [ 40/312]  eta: 0:03:16  lr: 0.003908  min_lr: 0.003908  loss: 3.0445 (2.8882)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [47]  [ 50/312]  eta: 0:02:54  lr: 0.003908  min_lr: 0.003908  loss: 2.9531 (2.9123)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [47]  [ 60/312]  eta: 0:02:38  lr: 0.003908  min_lr: 0.003908  loss: 2.8754 (2.8889)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [47]  [ 70/312]  eta: 0:02:25  lr: 0.003907  min_lr: 0.003907  loss: 2.5144 (2.8652)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [47]  [ 80/312]  eta: 0:02:14  lr: 0.003907  min_lr: 0.003907  loss: 2.5033 (2.8483)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [47]  [ 90/312]  eta: 0:02:05  lr: 0.003907  min_lr: 0.003907  loss: 2.8667 (2.8538)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [47]  [100/312]  eta: 0:01:56  lr: 0.003907  min_lr: 0.003907  loss: 2.9345 (2.8484)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [47]  [110/312]  eta: 0:01:49  lr: 0.003907  min_lr: 0.003907  loss: 3.0341 (2.8638)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [47]  [120/312]  eta: 0:01:42  lr: 0.003906  min_lr: 0.003906  loss: 3.0440 (2.8590)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [47]  [130/312]  eta: 0:01:35  lr: 0.003906  min_lr: 0.003906  loss: 2.9141 (2.8451)  weight_decay: 0.0500 (0.0500)  time: 0.4341  data: 0.0004  max mem: 42573
Epoch: [47]  [140/312]  eta: 0:01:29  lr: 0.003906  min_lr: 0.003906  loss: 2.6863 (2.8404)  weight_decay: 0.0500 (0.0500)  time: 0.4342  data: 0.0004  max mem: 42573
Epoch: [47]  [150/312]  eta: 0:01:22  lr: 0.003906  min_lr: 0.003906  loss: 3.0242 (2.8572)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0004  max mem: 42573
Epoch: [47]  [160/312]  eta: 0:01:17  lr: 0.003905  min_lr: 0.003905  loss: 3.0242 (2.8667)  weight_decay: 0.0500 (0.0500)  time: 0.4341  data: 0.0004  max mem: 42573
Epoch: [47]  [170/312]  eta: 0:01:11  lr: 0.003905  min_lr: 0.003905  loss: 2.6399 (2.8377)  weight_decay: 0.0500 (0.0500)  time: 0.4351  data: 0.0004  max mem: 42573
Epoch: [47]  [180/312]  eta: 0:01:05  lr: 0.003905  min_lr: 0.003905  loss: 2.3938 (2.8318)  weight_decay: 0.0500 (0.0500)  time: 0.4349  data: 0.0004  max mem: 42573
Epoch: [47]  [190/312]  eta: 0:01:00  lr: 0.003905  min_lr: 0.003905  loss: 2.8979 (2.8279)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [47]  [200/312]  eta: 0:00:55  lr: 0.003905  min_lr: 0.003905  loss: 2.9903 (2.8322)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0004  max mem: 42573
Epoch: [47]  [210/312]  eta: 0:00:49  lr: 0.003904  min_lr: 0.003904  loss: 2.9884 (2.8390)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0004  max mem: 42573
Epoch: [47]  [220/312]  eta: 0:00:44  lr: 0.003904  min_lr: 0.003904  loss: 2.8233 (2.8368)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [47]  [230/312]  eta: 0:00:39  lr: 0.003904  min_lr: 0.003904  loss: 2.7342 (2.8340)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [47]  [240/312]  eta: 0:00:34  lr: 0.003904  min_lr: 0.003904  loss: 2.6951 (2.8281)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [47]  [250/312]  eta: 0:00:29  lr: 0.003904  min_lr: 0.003904  loss: 2.7557 (2.8362)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [47]  [260/312]  eta: 0:00:24  lr: 0.003903  min_lr: 0.003903  loss: 2.9417 (2.8377)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [47]  [270/312]  eta: 0:00:20  lr: 0.003903  min_lr: 0.003903  loss: 2.7410 (2.8310)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [47]  [280/312]  eta: 0:00:15  lr: 0.003903  min_lr: 0.003903  loss: 2.8160 (2.8341)  weight_decay: 0.0500 (0.0500)  time: 0.4345  data: 0.0009  max mem: 42573
Epoch: [47]  [290/312]  eta: 0:00:10  lr: 0.003903  min_lr: 0.003903  loss: 2.9340 (2.8346)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0008  max mem: 42573
Epoch: [47]  [300/312]  eta: 0:00:05  lr: 0.003902  min_lr: 0.003902  loss: 2.9088 (2.8333)  weight_decay: 0.0500 (0.0500)  time: 0.4324  data: 0.0001  max mem: 42573
Epoch: [47]  [310/312]  eta: 0:00:00  lr: 0.003902  min_lr: 0.003902  loss: 2.8375 (2.8336)  weight_decay: 0.0500 (0.0500)  time: 0.4325  data: 0.0001  max mem: 42573
Epoch: [47]  [311/312]  eta: 0:00:00  lr: 0.003902  min_lr: 0.003902  loss: 2.8375 (2.8347)  weight_decay: 0.0500 (0.0500)  time: 0.4324  data: 0.0001  max mem: 42573
Epoch: [47] Total time: 0:02:28 (0.4746 s / it)
Averaged stats: lr: 0.003902  min_lr: 0.003902  loss: 2.8375 (2.8349)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:00:43  loss: 1.1181 (1.1181)  acc1: 76.5625 (76.5625)  acc5: 88.8021 (88.8021)  time: 4.7914  data: 4.6820  max mem: 42573
Test:  [8/9]  eta: 0:00:00  loss: 1.5294 (1.3938)  acc1: 66.6667 (67.5200)  acc5: 87.2396 (87.4240)  time: 0.6087  data: 0.5203  max mem: 42573
Test: Total time: 0:00:05 (0.6208 s / it)
* Acc@1 67.332 Acc@5 87.566 loss 1.385
Accuracy of the model on the 50000 test images: 67.3%
Max accuracy: 67.48%
Epoch: [48]  [  0/312]  eta: 0:51:23  lr: 0.003902  min_lr: 0.003902  loss: 2.7523 (2.7523)  weight_decay: 0.0500 (0.0500)  time: 9.8827  data: 8.0169  max mem: 42573
Epoch: [48]  [ 10/312]  eta: 0:07:38  lr: 0.003902  min_lr: 0.003902  loss: 2.9651 (2.7318)  weight_decay: 0.0500 (0.0500)  time: 1.5181  data: 0.7413  max mem: 42573
Epoch: [48]  [ 20/312]  eta: 0:04:52  lr: 0.003902  min_lr: 0.003902  loss: 2.9651 (2.7807)  weight_decay: 0.0500 (0.0500)  time: 0.5574  data: 0.0070  max mem: 42573
Epoch: [48]  [ 30/312]  eta: 0:03:50  lr: 0.003901  min_lr: 0.003901  loss: 2.9307 (2.8236)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [48]  [ 40/312]  eta: 0:03:17  lr: 0.003901  min_lr: 0.003901  loss: 2.9307 (2.8211)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0005  max mem: 42573
Epoch: [48]  [ 50/312]  eta: 0:02:54  lr: 0.003901  min_lr: 0.003901  loss: 2.9243 (2.8617)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0005  max mem: 42573
Epoch: [48]  [ 60/312]  eta: 0:02:38  lr: 0.003901  min_lr: 0.003901  loss: 2.8939 (2.8667)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [48]  [ 70/312]  eta: 0:02:25  lr: 0.003901  min_lr: 0.003901  loss: 2.8939 (2.8640)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [48]  [ 80/312]  eta: 0:02:14  lr: 0.003900  min_lr: 0.003900  loss: 2.9378 (2.8753)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [48]  [ 90/312]  eta: 0:02:05  lr: 0.003900  min_lr: 0.003900  loss: 2.9392 (2.8649)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [48]  [100/312]  eta: 0:01:56  lr: 0.003900  min_lr: 0.003900  loss: 2.9003 (2.8720)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [48]  [110/312]  eta: 0:01:49  lr: 0.003900  min_lr: 0.003900  loss: 2.9399 (2.8724)  weight_decay: 0.0500 (0.0500)  time: 0.4351  data: 0.0004  max mem: 42573
Epoch: [48]  [120/312]  eta: 0:01:42  lr: 0.003899  min_lr: 0.003899  loss: 3.0126 (2.8915)  weight_decay: 0.0500 (0.0500)  time: 0.4351  data: 0.0004  max mem: 42573
Epoch: [48]  [130/312]  eta: 0:01:35  lr: 0.003899  min_lr: 0.003899  loss: 2.9627 (2.8839)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0004  max mem: 42573
Epoch: [48]  [140/312]  eta: 0:01:29  lr: 0.003899  min_lr: 0.003899  loss: 2.9627 (2.8968)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [48]  [150/312]  eta: 0:01:23  lr: 0.003899  min_lr: 0.003899  loss: 2.9822 (2.8902)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [48]  [160/312]  eta: 0:01:17  lr: 0.003899  min_lr: 0.003899  loss: 2.8771 (2.8894)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [48]  [170/312]  eta: 0:01:11  lr: 0.003898  min_lr: 0.003898  loss: 2.9490 (2.8962)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [48]  [180/312]  eta: 0:01:05  lr: 0.003898  min_lr: 0.003898  loss: 2.9698 (2.8941)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [48]  [190/312]  eta: 0:01:00  lr: 0.003898  min_lr: 0.003898  loss: 2.9989 (2.8924)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [48]  [200/312]  eta: 0:00:55  lr: 0.003898  min_lr: 0.003898  loss: 2.9989 (2.8947)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [48]  [210/312]  eta: 0:00:50  lr: 0.003897  min_lr: 0.003897  loss: 2.7756 (2.8875)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [48]  [220/312]  eta: 0:00:44  lr: 0.003897  min_lr: 0.003897  loss: 2.7756 (2.8844)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [48]  [230/312]  eta: 0:00:39  lr: 0.003897  min_lr: 0.003897  loss: 2.9165 (2.8854)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [48]  [240/312]  eta: 0:00:34  lr: 0.003897  min_lr: 0.003897  loss: 2.8871 (2.8846)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [48]  [250/312]  eta: 0:00:29  lr: 0.003897  min_lr: 0.003897  loss: 3.1355 (2.8913)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [48]  [260/312]  eta: 0:00:24  lr: 0.003896  min_lr: 0.003896  loss: 3.1188 (2.8992)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [48]  [270/312]  eta: 0:00:20  lr: 0.003896  min_lr: 0.003896  loss: 2.9920 (2.8984)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [48]  [280/312]  eta: 0:00:15  lr: 0.003896  min_lr: 0.003896  loss: 2.7888 (2.8956)  weight_decay: 0.0500 (0.0500)  time: 0.4349  data: 0.0010  max mem: 42573
Epoch: [48]  [290/312]  eta: 0:00:10  lr: 0.003896  min_lr: 0.003896  loss: 2.8103 (2.8917)  weight_decay: 0.0500 (0.0500)  time: 0.4342  data: 0.0008  max mem: 42573
Epoch: [48]  [300/312]  eta: 0:00:05  lr: 0.003895  min_lr: 0.003895  loss: 2.7944 (2.8852)  weight_decay: 0.0500 (0.0500)  time: 0.4326  data: 0.0001  max mem: 42573
Epoch: [48]  [310/312]  eta: 0:00:00  lr: 0.003895  min_lr: 0.003895  loss: 2.7944 (2.8829)  weight_decay: 0.0500 (0.0500)  time: 0.4325  data: 0.0001  max mem: 42573
Epoch: [48]  [311/312]  eta: 0:00:00  lr: 0.003895  min_lr: 0.003895  loss: 2.8486 (2.8839)  weight_decay: 0.0500 (0.0500)  time: 0.4325  data: 0.0001  max mem: 42573
Epoch: [48] Total time: 0:02:28 (0.4748 s / it)
Averaged stats: lr: 0.003895  min_lr: 0.003895  loss: 2.8486 (2.8337)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:00:40  loss: 1.0262 (1.0262)  acc1: 74.4792 (74.4792)  acc5: 91.6667 (91.6667)  time: 4.4736  data: 4.3647  max mem: 42573
Test:  [8/9]  eta: 0:00:00  loss: 1.5308 (1.3378)  acc1: 65.3646 (66.8480)  acc5: 86.9792 (87.2320)  time: 0.5941  data: 0.5043  max mem: 42573
Test: Total time: 0:00:05 (0.6007 s / it)
* Acc@1 67.134 Acc@5 87.662 loss 1.349
Accuracy of the model on the 50000 test images: 67.1%
Max accuracy: 67.48%
Epoch: [49]  [  0/312]  eta: 0:48:18  lr: 0.003895  min_lr: 0.003895  loss: 3.2133 (3.2133)  weight_decay: 0.0500 (0.0500)  time: 9.2913  data: 5.8011  max mem: 42573
Epoch: [49]  [ 10/312]  eta: 0:07:29  lr: 0.003895  min_lr: 0.003895  loss: 2.8141 (2.8158)  weight_decay: 0.0500 (0.0500)  time: 1.4899  data: 0.6255  max mem: 42573
Epoch: [49]  [ 20/312]  eta: 0:04:48  lr: 0.003895  min_lr: 0.003895  loss: 2.7357 (2.7494)  weight_decay: 0.0500 (0.0500)  time: 0.5714  data: 0.0541  max mem: 42573
Epoch: [49]  [ 30/312]  eta: 0:03:47  lr: 0.003894  min_lr: 0.003894  loss: 2.4548 (2.6529)  weight_decay: 0.0500 (0.0500)  time: 0.4331  data: 0.0004  max mem: 42573
Epoch: [49]  [ 40/312]  eta: 0:03:14  lr: 0.003894  min_lr: 0.003894  loss: 2.6401 (2.6680)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [49]  [ 50/312]  eta: 0:02:53  lr: 0.003894  min_lr: 0.003894  loss: 2.7916 (2.6909)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [49]  [ 60/312]  eta: 0:02:37  lr: 0.003894  min_lr: 0.003894  loss: 2.7942 (2.6916)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [49]  [ 70/312]  eta: 0:02:24  lr: 0.003893  min_lr: 0.003893  loss: 2.9109 (2.7175)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [49]  [ 80/312]  eta: 0:02:13  lr: 0.003893  min_lr: 0.003893  loss: 2.9403 (2.7317)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [49]  [ 90/312]  eta: 0:02:04  lr: 0.003893  min_lr: 0.003893  loss: 2.8506 (2.7471)  weight_decay: 0.0500 (0.0500)  time: 0.4410  data: 0.0004  max mem: 42573
Epoch: [49]  [100/312]  eta: 0:01:56  lr: 0.003893  min_lr: 0.003893  loss: 2.9626 (2.7488)  weight_decay: 0.0500 (0.0500)  time: 0.4409  data: 0.0004  max mem: 42573
Epoch: [49]  [110/312]  eta: 0:01:48  lr: 0.003893  min_lr: 0.003893  loss: 2.5545 (2.7397)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [49]  [120/312]  eta: 0:01:41  lr: 0.003892  min_lr: 0.003892  loss: 2.6634 (2.7371)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [49]  [130/312]  eta: 0:01:35  lr: 0.003892  min_lr: 0.003892  loss: 2.9666 (2.7614)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [49]  [140/312]  eta: 0:01:28  lr: 0.003892  min_lr: 0.003892  loss: 2.9666 (2.7683)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [49]  [150/312]  eta: 0:01:22  lr: 0.003892  min_lr: 0.003892  loss: 2.9087 (2.7720)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [49]  [160/312]  eta: 0:01:17  lr: 0.003891  min_lr: 0.003891  loss: 2.5462 (2.7534)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [49]  [170/312]  eta: 0:01:11  lr: 0.003891  min_lr: 0.003891  loss: 2.7103 (2.7683)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [49]  [180/312]  eta: 0:01:05  lr: 0.003891  min_lr: 0.003891  loss: 3.0448 (2.7751)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [49]  [190/312]  eta: 0:01:00  lr: 0.003891  min_lr: 0.003891  loss: 2.9613 (2.7797)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [49]  [200/312]  eta: 0:00:55  lr: 0.003890  min_lr: 0.003890  loss: 2.8487 (2.7858)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [49]  [210/312]  eta: 0:00:49  lr: 0.003890  min_lr: 0.003890  loss: 2.8487 (2.7889)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0003  max mem: 42573
Epoch: [49]  [220/312]  eta: 0:00:44  lr: 0.003890  min_lr: 0.003890  loss: 2.8699 (2.7881)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0003  max mem: 42573
Epoch: [49]  [230/312]  eta: 0:00:39  lr: 0.003890  min_lr: 0.003890  loss: 2.9442 (2.7902)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [49]  [240/312]  eta: 0:00:34  lr: 0.003889  min_lr: 0.003889  loss: 3.0158 (2.7931)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [49]  [250/312]  eta: 0:00:29  lr: 0.003889  min_lr: 0.003889  loss: 3.0158 (2.8050)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [49]  [260/312]  eta: 0:00:24  lr: 0.003889  min_lr: 0.003889  loss: 3.0853 (2.8055)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [49]  [270/312]  eta: 0:00:20  lr: 0.003889  min_lr: 0.003889  loss: 2.8332 (2.7986)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [49]  [280/312]  eta: 0:00:15  lr: 0.003889  min_lr: 0.003889  loss: 2.8332 (2.8000)  weight_decay: 0.0500 (0.0500)  time: 0.4346  data: 0.0015  max mem: 42573
Epoch: [49]  [290/312]  eta: 0:00:10  lr: 0.003888  min_lr: 0.003888  loss: 2.9778 (2.8043)  weight_decay: 0.0500 (0.0500)  time: 0.4341  data: 0.0013  max mem: 42573
Epoch: [49]  [300/312]  eta: 0:00:05  lr: 0.003888  min_lr: 0.003888  loss: 2.9407 (2.8058)  weight_decay: 0.0500 (0.0500)  time: 0.4326  data: 0.0001  max mem: 42573
Epoch: [49]  [310/312]  eta: 0:00:00  lr: 0.003888  min_lr: 0.003888  loss: 2.7191 (2.8019)  weight_decay: 0.0500 (0.0500)  time: 0.4324  data: 0.0001  max mem: 42573
Epoch: [49]  [311/312]  eta: 0:00:00  lr: 0.003888  min_lr: 0.003888  loss: 2.7191 (2.8044)  weight_decay: 0.0500 (0.0500)  time: 0.4324  data: 0.0001  max mem: 42573
Epoch: [49] Total time: 0:02:27 (0.4743 s / it)
Averaged stats: lr: 0.003888  min_lr: 0.003888  loss: 2.7191 (2.8191)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:00:43  loss: 1.1095 (1.1095)  acc1: 72.9167 (72.9167)  acc5: 90.8854 (90.8854)  time: 4.7801  data: 4.6714  max mem: 42573
Test:  [8/9]  eta: 0:00:00  loss: 1.4899 (1.3374)  acc1: 66.1458 (67.1360)  acc5: 86.4583 (87.6160)  time: 0.6065  data: 0.5191  max mem: 42573
Test: Total time: 0:00:05 (0.6193 s / it)
* Acc@1 67.382 Acc@5 87.978 loss 1.345
Accuracy of the model on the 50000 test images: 67.4%
Max accuracy: 67.48%
Epoch: [50]  [  0/312]  eta: 0:49:24  lr: 0.003888  min_lr: 0.003888  loss: 2.7105 (2.7105)  weight_decay: 0.0500 (0.0500)  time: 9.5015  data: 7.6242  max mem: 42573
Epoch: [50]  [ 10/312]  eta: 0:07:07  lr: 0.003888  min_lr: 0.003888  loss: 2.9468 (2.8935)  weight_decay: 0.0500 (0.0500)  time: 1.4153  data: 0.6935  max mem: 42573
Epoch: [50]  [ 20/312]  eta: 0:04:36  lr: 0.003887  min_lr: 0.003887  loss: 3.0099 (2.8741)  weight_decay: 0.0500 (0.0500)  time: 0.5205  data: 0.0004  max mem: 42573
Epoch: [50]  [ 30/312]  eta: 0:03:40  lr: 0.003887  min_lr: 0.003887  loss: 3.0482 (2.9156)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [50]  [ 40/312]  eta: 0:03:09  lr: 0.003887  min_lr: 0.003887  loss: 3.0327 (2.8820)  weight_decay: 0.0500 (0.0500)  time: 0.4332  data: 0.0004  max mem: 42573
Epoch: [50]  [ 50/312]  eta: 0:02:49  lr: 0.003887  min_lr: 0.003887  loss: 2.7981 (2.8496)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [50]  [ 60/312]  eta: 0:02:33  lr: 0.003886  min_lr: 0.003886  loss: 2.8262 (2.8399)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [50]  [ 70/312]  eta: 0:02:21  lr: 0.003886  min_lr: 0.003886  loss: 2.9374 (2.8218)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [50]  [ 80/312]  eta: 0:02:11  lr: 0.003886  min_lr: 0.003886  loss: 2.6791 (2.8001)  weight_decay: 0.0500 (0.0500)  time: 0.4381  data: 0.0004  max mem: 42573
Epoch: [50]  [ 90/312]  eta: 0:02:02  lr: 0.003886  min_lr: 0.003886  loss: 2.5733 (2.7756)  weight_decay: 0.0500 (0.0500)  time: 0.4381  data: 0.0004  max mem: 42573
Epoch: [50]  [100/312]  eta: 0:01:54  lr: 0.003885  min_lr: 0.003885  loss: 2.8133 (2.7888)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [50]  [110/312]  eta: 0:01:47  lr: 0.003885  min_lr: 0.003885  loss: 2.9242 (2.7864)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0004  max mem: 42573
Epoch: [50]  [120/312]  eta: 0:01:40  lr: 0.003885  min_lr: 0.003885  loss: 2.9435 (2.8048)  weight_decay: 0.0500 (0.0500)  time: 0.4341  data: 0.0004  max mem: 42573
Epoch: [50]  [130/312]  eta: 0:01:34  lr: 0.003885  min_lr: 0.003885  loss: 2.9745 (2.7893)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0005  max mem: 42573
Epoch: [50]  [140/312]  eta: 0:01:27  lr: 0.003884  min_lr: 0.003884  loss: 2.9355 (2.8056)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [50]  [150/312]  eta: 0:01:21  lr: 0.003884  min_lr: 0.003884  loss: 2.9858 (2.8090)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [50]  [160/312]  eta: 0:01:16  lr: 0.003884  min_lr: 0.003884  loss: 2.7162 (2.7955)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [50]  [170/312]  eta: 0:01:10  lr: 0.003884  min_lr: 0.003884  loss: 2.9334 (2.8073)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [50]  [180/312]  eta: 0:01:05  lr: 0.003883  min_lr: 0.003883  loss: 2.9400 (2.8124)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [50]  [190/312]  eta: 0:00:59  lr: 0.003883  min_lr: 0.003883  loss: 2.8799 (2.8126)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [50]  [200/312]  eta: 0:00:54  lr: 0.003883  min_lr: 0.003883  loss: 2.9128 (2.8181)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0003  max mem: 42573
Epoch: [50]  [210/312]  eta: 0:00:49  lr: 0.003883  min_lr: 0.003883  loss: 2.9257 (2.8232)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0003  max mem: 42573
Epoch: [50]  [220/312]  eta: 0:00:44  lr: 0.003883  min_lr: 0.003883  loss: 2.9332 (2.8185)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [50]  [230/312]  eta: 0:00:39  lr: 0.003882  min_lr: 0.003882  loss: 2.8154 (2.8178)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [50]  [240/312]  eta: 0:00:34  lr: 0.003882  min_lr: 0.003882  loss: 2.9451 (2.8182)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0003  max mem: 42573
Epoch: [50]  [250/312]  eta: 0:00:29  lr: 0.003882  min_lr: 0.003882  loss: 2.9795 (2.8228)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0003  max mem: 42573
Epoch: [50]  [260/312]  eta: 0:00:24  lr: 0.003882  min_lr: 0.003882  loss: 2.9480 (2.8228)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0003  max mem: 42573
Epoch: [50]  [270/312]  eta: 0:00:19  lr: 0.003881  min_lr: 0.003881  loss: 3.0558 (2.8264)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [50]  [280/312]  eta: 0:00:15  lr: 0.003881  min_lr: 0.003881  loss: 3.0558 (2.8288)  weight_decay: 0.0500 (0.0500)  time: 0.4343  data: 0.0009  max mem: 42573
Epoch: [50]  [290/312]  eta: 0:00:10  lr: 0.003881  min_lr: 0.003881  loss: 2.8163 (2.8277)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0008  max mem: 42573
Epoch: [50]  [300/312]  eta: 0:00:05  lr: 0.003881  min_lr: 0.003881  loss: 2.9681 (2.8333)  weight_decay: 0.0500 (0.0500)  time: 0.4324  data: 0.0001  max mem: 42573
Epoch: [50]  [310/312]  eta: 0:00:00  lr: 0.003880  min_lr: 0.003880  loss: 3.0050 (2.8309)  weight_decay: 0.0500 (0.0500)  time: 0.4323  data: 0.0001  max mem: 42573
Epoch: [50]  [311/312]  eta: 0:00:00  lr: 0.003880  min_lr: 0.003880  loss: 2.9681 (2.8303)  weight_decay: 0.0500 (0.0500)  time: 0.4323  data: 0.0001  max mem: 42573
Epoch: [50] Total time: 0:02:27 (0.4714 s / it)
Averaged stats: lr: 0.003880  min_lr: 0.003880  loss: 2.9681 (2.8223)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:00:38  loss: 1.0825 (1.0825)  acc1: 74.4792 (74.4792)  acc5: 91.4062 (91.4062)  time: 4.3246  data: 4.2158  max mem: 42573
Test:  [8/9]  eta: 0:00:00  loss: 1.4892 (1.3568)  acc1: 65.1042 (66.5920)  acc5: 87.7604 (88.2880)  time: 0.5569  data: 0.4685  max mem: 42573
Test: Total time: 0:00:05 (0.5638 s / it)
* Acc@1 67.468 Acc@5 87.744 loss 1.385
Accuracy of the model on the 50000 test images: 67.5%
Max accuracy: 67.48%
Epoch: [51]  [  0/312]  eta: 0:50:31  lr: 0.003880  min_lr: 0.003880  loss: 3.1715 (3.1715)  weight_decay: 0.0500 (0.0500)  time: 9.7174  data: 5.9595  max mem: 42573
Epoch: [51]  [ 10/312]  eta: 0:07:27  lr: 0.003880  min_lr: 0.003880  loss: 2.9711 (2.9852)  weight_decay: 0.0500 (0.0500)  time: 1.4817  data: 0.7413  max mem: 42573
Epoch: [51]  [ 20/312]  eta: 0:04:46  lr: 0.003880  min_lr: 0.003880  loss: 2.8184 (2.7642)  weight_decay: 0.0500 (0.0500)  time: 0.5458  data: 0.1099  max mem: 42573
Epoch: [51]  [ 30/312]  eta: 0:03:47  lr: 0.003880  min_lr: 0.003880  loss: 2.8184 (2.7855)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0003  max mem: 42573
Epoch: [51]  [ 40/312]  eta: 0:03:14  lr: 0.003879  min_lr: 0.003879  loss: 2.9164 (2.7582)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [51]  [ 50/312]  eta: 0:02:52  lr: 0.003879  min_lr: 0.003879  loss: 2.6974 (2.7547)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [51]  [ 60/312]  eta: 0:02:36  lr: 0.003879  min_lr: 0.003879  loss: 2.6614 (2.7390)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [51]  [ 70/312]  eta: 0:02:24  lr: 0.003879  min_lr: 0.003879  loss: 2.9577 (2.7882)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [51]  [ 80/312]  eta: 0:02:13  lr: 0.003878  min_lr: 0.003878  loss: 2.9647 (2.7854)  weight_decay: 0.0500 (0.0500)  time: 0.4391  data: 0.0004  max mem: 42573
Epoch: [51]  [ 90/312]  eta: 0:02:04  lr: 0.003878  min_lr: 0.003878  loss: 2.8329 (2.7970)  weight_decay: 0.0500 (0.0500)  time: 0.4391  data: 0.0003  max mem: 42573
Epoch: [51]  [100/312]  eta: 0:01:56  lr: 0.003878  min_lr: 0.003878  loss: 2.8876 (2.8012)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0003  max mem: 42573
Epoch: [51]  [110/312]  eta: 0:01:48  lr: 0.003878  min_lr: 0.003878  loss: 2.6669 (2.7785)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [51]  [120/312]  eta: 0:01:41  lr: 0.003877  min_lr: 0.003877  loss: 2.4699 (2.7720)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [51]  [130/312]  eta: 0:01:35  lr: 0.003877  min_lr: 0.003877  loss: 2.8263 (2.7852)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [51]  [140/312]  eta: 0:01:28  lr: 0.003877  min_lr: 0.003877  loss: 2.8390 (2.7782)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0004  max mem: 42573
Epoch: [51]  [150/312]  eta: 0:01:22  lr: 0.003877  min_lr: 0.003877  loss: 2.6983 (2.7785)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [51]  [160/312]  eta: 0:01:16  lr: 0.003876  min_lr: 0.003876  loss: 2.8238 (2.7833)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [51]  [170/312]  eta: 0:01:11  lr: 0.003876  min_lr: 0.003876  loss: 2.8238 (2.7752)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [51]  [180/312]  eta: 0:01:05  lr: 0.003876  min_lr: 0.003876  loss: 2.4940 (2.7683)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [51]  [190/312]  eta: 0:01:00  lr: 0.003876  min_lr: 0.003876  loss: 2.4940 (2.7634)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [51]  [200/312]  eta: 0:00:55  lr: 0.003875  min_lr: 0.003875  loss: 2.6346 (2.7722)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0004  max mem: 42573
Epoch: [51]  [210/312]  eta: 0:00:49  lr: 0.003875  min_lr: 0.003875  loss: 3.0034 (2.7820)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [51]  [220/312]  eta: 0:00:44  lr: 0.003875  min_lr: 0.003875  loss: 3.0076 (2.7818)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [51]  [230/312]  eta: 0:00:39  lr: 0.003875  min_lr: 0.003875  loss: 2.9737 (2.7870)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [51]  [240/312]  eta: 0:00:34  lr: 0.003874  min_lr: 0.003874  loss: 2.9737 (2.7942)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0004  max mem: 42573
Epoch: [51]  [250/312]  eta: 0:00:29  lr: 0.003874  min_lr: 0.003874  loss: 2.8103 (2.7926)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [51]  [260/312]  eta: 0:00:24  lr: 0.003874  min_lr: 0.003874  loss: 2.8964 (2.7977)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [51]  [270/312]  eta: 0:00:20  lr: 0.003874  min_lr: 0.003874  loss: 2.8964 (2.7955)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0003  max mem: 42573
Epoch: [51]  [280/312]  eta: 0:00:15  lr: 0.003873  min_lr: 0.003873  loss: 2.9547 (2.8038)  weight_decay: 0.0500 (0.0500)  time: 0.4345  data: 0.0009  max mem: 42573
Epoch: [51]  [290/312]  eta: 0:00:10  lr: 0.003873  min_lr: 0.003873  loss: 3.0522 (2.8094)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0008  max mem: 42573
Epoch: [51]  [300/312]  eta: 0:00:05  lr: 0.003873  min_lr: 0.003873  loss: 3.0204 (2.8024)  weight_decay: 0.0500 (0.0500)  time: 0.4323  data: 0.0001  max mem: 42573
Epoch: [51]  [310/312]  eta: 0:00:00  lr: 0.003873  min_lr: 0.003873  loss: 2.4404 (2.7957)  weight_decay: 0.0500 (0.0500)  time: 0.4323  data: 0.0001  max mem: 42573
Epoch: [51]  [311/312]  eta: 0:00:00  lr: 0.003873  min_lr: 0.003873  loss: 2.6164 (2.7966)  weight_decay: 0.0500 (0.0500)  time: 0.4324  data: 0.0001  max mem: 42573
Epoch: [51] Total time: 0:02:27 (0.4740 s / it)
Averaged stats: lr: 0.003873  min_lr: 0.003873  loss: 2.6164 (2.8015)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:00:46  loss: 1.1734 (1.1734)  acc1: 72.9167 (72.9167)  acc5: 89.3229 (89.3229)  time: 5.1121  data: 5.0027  max mem: 42573
Test:  [8/9]  eta: 0:00:00  loss: 1.5252 (1.4063)  acc1: 64.5833 (66.2080)  acc5: 88.5417 (87.6480)  time: 0.6445  data: 0.5559  max mem: 42573
Test: Total time: 0:00:05 (0.6641 s / it)
* Acc@1 66.626 Acc@5 87.306 loss 1.412
Accuracy of the model on the 50000 test images: 66.6%
Max accuracy: 67.48%
Epoch: [52]  [  0/312]  eta: 0:49:52  lr: 0.003873  min_lr: 0.003873  loss: 2.7585 (2.7585)  weight_decay: 0.0500 (0.0500)  time: 9.5920  data: 7.6425  max mem: 42573
Epoch: [52]  [ 10/312]  eta: 0:07:34  lr: 0.003872  min_lr: 0.003872  loss: 2.8300 (2.7887)  weight_decay: 0.0500 (0.0500)  time: 1.5064  data: 0.6952  max mem: 42573
Epoch: [52]  [ 20/312]  eta: 0:04:50  lr: 0.003872  min_lr: 0.003872  loss: 2.8917 (2.8421)  weight_decay: 0.0500 (0.0500)  time: 0.5660  data: 0.0004  max mem: 42573
Epoch: [52]  [ 30/312]  eta: 0:03:49  lr: 0.003872  min_lr: 0.003872  loss: 2.8917 (2.8770)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [52]  [ 40/312]  eta: 0:03:16  lr: 0.003871  min_lr: 0.003871  loss: 2.8491 (2.8578)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [52]  [ 50/312]  eta: 0:02:54  lr: 0.003871  min_lr: 0.003871  loss: 2.5838 (2.7909)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [52]  [ 60/312]  eta: 0:02:38  lr: 0.003871  min_lr: 0.003871  loss: 2.7332 (2.8182)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [52]  [ 70/312]  eta: 0:02:25  lr: 0.003871  min_lr: 0.003871  loss: 2.9442 (2.8143)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [52]  [ 80/312]  eta: 0:02:14  lr: 0.003870  min_lr: 0.003870  loss: 2.8805 (2.8115)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0004  max mem: 42573
Epoch: [52]  [ 90/312]  eta: 0:02:05  lr: 0.003870  min_lr: 0.003870  loss: 2.8071 (2.7924)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0004  max mem: 42573
Epoch: [52]  [100/312]  eta: 0:01:56  lr: 0.003870  min_lr: 0.003870  loss: 2.8680 (2.7974)  weight_decay: 0.0500 (0.0500)  time: 0.4376  data: 0.0003  max mem: 42573
Epoch: [52]  [110/312]  eta: 0:01:49  lr: 0.003870  min_lr: 0.003870  loss: 2.8941 (2.8020)  weight_decay: 0.0500 (0.0500)  time: 0.4376  data: 0.0004  max mem: 42573
Epoch: [52]  [120/312]  eta: 0:01:42  lr: 0.003869  min_lr: 0.003869  loss: 2.9261 (2.8097)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [52]  [130/312]  eta: 0:01:35  lr: 0.003869  min_lr: 0.003869  loss: 2.8195 (2.8011)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [52]  [140/312]  eta: 0:01:29  lr: 0.003869  min_lr: 0.003869  loss: 2.8565 (2.8057)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [52]  [150/312]  eta: 0:01:23  lr: 0.003869  min_lr: 0.003869  loss: 2.9575 (2.8178)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [52]  [160/312]  eta: 0:01:17  lr: 0.003868  min_lr: 0.003868  loss: 2.9575 (2.8229)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0004  max mem: 42573
Epoch: [52]  [170/312]  eta: 0:01:11  lr: 0.003868  min_lr: 0.003868  loss: 2.8901 (2.8186)  weight_decay: 0.0500 (0.0500)  time: 0.4341  data: 0.0003  max mem: 42573
Epoch: [52]  [180/312]  eta: 0:01:05  lr: 0.003868  min_lr: 0.003868  loss: 2.8080 (2.8145)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0004  max mem: 42573
Epoch: [52]  [190/312]  eta: 0:01:00  lr: 0.003868  min_lr: 0.003868  loss: 2.7170 (2.8106)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [52]  [200/312]  eta: 0:00:55  lr: 0.003867  min_lr: 0.003867  loss: 2.9339 (2.8154)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [52]  [210/312]  eta: 0:00:49  lr: 0.003867  min_lr: 0.003867  loss: 2.9224 (2.8118)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0003  max mem: 42573
Epoch: [52]  [220/312]  eta: 0:00:44  lr: 0.003867  min_lr: 0.003867  loss: 2.9224 (2.8169)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [52]  [230/312]  eta: 0:00:39  lr: 0.003867  min_lr: 0.003867  loss: 2.8799 (2.8205)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [52]  [240/312]  eta: 0:00:34  lr: 0.003866  min_lr: 0.003866  loss: 2.8799 (2.8256)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [52]  [250/312]  eta: 0:00:29  lr: 0.003866  min_lr: 0.003866  loss: 2.9666 (2.8221)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [52]  [260/312]  eta: 0:00:24  lr: 0.003866  min_lr: 0.003866  loss: 2.9679 (2.8284)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [52]  [270/312]  eta: 0:00:20  lr: 0.003866  min_lr: 0.003866  loss: 2.9933 (2.8331)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0004  max mem: 42573
Epoch: [52]  [280/312]  eta: 0:00:15  lr: 0.003865  min_lr: 0.003865  loss: 2.9927 (2.8387)  weight_decay: 0.0500 (0.0500)  time: 0.4344  data: 0.0009  max mem: 42573
Epoch: [52]  [290/312]  eta: 0:00:10  lr: 0.003865  min_lr: 0.003865  loss: 2.9995 (2.8418)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0008  max mem: 42573
Epoch: [52]  [300/312]  eta: 0:00:05  lr: 0.003865  min_lr: 0.003865  loss: 3.0061 (2.8432)  weight_decay: 0.0500 (0.0500)  time: 0.4324  data: 0.0001  max mem: 42573
Epoch: [52]  [310/312]  eta: 0:00:00  lr: 0.003865  min_lr: 0.003865  loss: 2.9951 (2.8424)  weight_decay: 0.0500 (0.0500)  time: 0.4324  data: 0.0001  max mem: 42573
Epoch: [52]  [311/312]  eta: 0:00:00  lr: 0.003865  min_lr: 0.003865  loss: 2.6145 (2.8395)  weight_decay: 0.0500 (0.0500)  time: 0.4324  data: 0.0001  max mem: 42573
Epoch: [52] Total time: 0:02:28 (0.4745 s / it)
Averaged stats: lr: 0.003865  min_lr: 0.003865  loss: 2.6145 (2.8035)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:00:42  loss: 0.9977 (0.9977)  acc1: 77.3438 (77.3438)  acc5: 92.1875 (92.1875)  time: 4.7773  data: 4.6677  max mem: 42573
Test:  [8/9]  eta: 0:00:00  loss: 1.3336 (1.2821)  acc1: 67.9688 (67.5200)  acc5: 88.5417 (87.9360)  time: 0.6064  data: 0.5187  max mem: 42573
Test: Total time: 0:00:05 (0.6139 s / it)
* Acc@1 67.826 Acc@5 88.106 loss 1.310
Accuracy of the model on the 50000 test images: 67.8%
Max accuracy: 67.83%
Epoch: [53]  [  0/312]  eta: 0:47:10  lr: 0.003865  min_lr: 0.003865  loss: 3.0775 (3.0775)  weight_decay: 0.0500 (0.0500)  time: 9.0726  data: 6.4161  max mem: 42573
Epoch: [53]  [ 10/312]  eta: 0:06:54  lr: 0.003864  min_lr: 0.003864  loss: 2.7742 (2.7247)  weight_decay: 0.0500 (0.0500)  time: 1.3731  data: 0.7221  max mem: 42573
Epoch: [53]  [ 20/312]  eta: 0:04:30  lr: 0.003864  min_lr: 0.003864  loss: 2.5111 (2.5495)  weight_decay: 0.0500 (0.0500)  time: 0.5182  data: 0.0766  max mem: 42573
Epoch: [53]  [ 30/312]  eta: 0:03:36  lr: 0.003864  min_lr: 0.003864  loss: 2.6594 (2.6443)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [53]  [ 40/312]  eta: 0:03:06  lr: 0.003863  min_lr: 0.003863  loss: 2.7380 (2.6202)  weight_decay: 0.0500 (0.0500)  time: 0.4341  data: 0.0004  max mem: 42573
Epoch: [53]  [ 50/312]  eta: 0:02:46  lr: 0.003863  min_lr: 0.003863  loss: 2.6340 (2.6639)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [53]  [ 60/312]  eta: 0:02:32  lr: 0.003863  min_lr: 0.003863  loss: 2.8803 (2.6721)  weight_decay: 0.0500 (0.0500)  time: 0.4349  data: 0.0004  max mem: 42573
Epoch: [53]  [ 70/312]  eta: 0:02:20  lr: 0.003863  min_lr: 0.003863  loss: 2.8803 (2.6760)  weight_decay: 0.0500 (0.0500)  time: 0.4350  data: 0.0004  max mem: 42573
Epoch: [53]  [ 80/312]  eta: 0:02:10  lr: 0.003862  min_lr: 0.003862  loss: 2.5869 (2.6702)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0003  max mem: 42573
Epoch: [53]  [ 90/312]  eta: 0:02:01  lr: 0.003862  min_lr: 0.003862  loss: 2.8437 (2.6996)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [53]  [100/312]  eta: 0:01:53  lr: 0.003862  min_lr: 0.003862  loss: 2.8732 (2.6915)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [53]  [110/312]  eta: 0:01:46  lr: 0.003862  min_lr: 0.003862  loss: 2.7727 (2.7019)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [53]  [120/312]  eta: 0:01:39  lr: 0.003861  min_lr: 0.003861  loss: 2.7727 (2.7028)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [53]  [130/312]  eta: 0:01:33  lr: 0.003861  min_lr: 0.003861  loss: 2.8364 (2.7088)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [53]  [140/312]  eta: 0:01:27  lr: 0.003861  min_lr: 0.003861  loss: 2.8381 (2.7120)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [53]  [150/312]  eta: 0:01:21  lr: 0.003861  min_lr: 0.003861  loss: 2.7824 (2.7081)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [53]  [160/312]  eta: 0:01:15  lr: 0.003860  min_lr: 0.003860  loss: 2.8184 (2.7147)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [53]  [170/312]  eta: 0:01:10  lr: 0.003860  min_lr: 0.003860  loss: 2.9968 (2.7311)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [53]  [180/312]  eta: 0:01:04  lr: 0.003860  min_lr: 0.003860  loss: 2.9551 (2.7289)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [53]  [190/312]  eta: 0:00:59  lr: 0.003860  min_lr: 0.003860  loss: 2.8865 (2.7274)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [53]  [200/312]  eta: 0:00:54  lr: 0.003859  min_lr: 0.003859  loss: 2.6672 (2.7298)  weight_decay: 0.0500 (0.0500)  time: 0.4350  data: 0.0004  max mem: 42573
Epoch: [53]  [210/312]  eta: 0:00:49  lr: 0.003859  min_lr: 0.003859  loss: 2.6672 (2.7321)  weight_decay: 0.0500 (0.0500)  time: 0.4351  data: 0.0004  max mem: 42573
Epoch: [53]  [220/312]  eta: 0:00:44  lr: 0.003859  min_lr: 0.003859  loss: 2.7641 (2.7330)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0004  max mem: 42573
Epoch: [53]  [230/312]  eta: 0:00:39  lr: 0.003858  min_lr: 0.003858  loss: 2.9681 (2.7458)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [53]  [240/312]  eta: 0:00:34  lr: 0.003858  min_lr: 0.003858  loss: 3.0669 (2.7531)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0003  max mem: 42573
Epoch: [53]  [250/312]  eta: 0:00:29  lr: 0.003858  min_lr: 0.003858  loss: 2.9455 (2.7550)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0004  max mem: 42573
Epoch: [53]  [260/312]  eta: 0:00:24  lr: 0.003858  min_lr: 0.003858  loss: 2.8681 (2.7541)  weight_decay: 0.0500 (0.0500)  time: 0.4370  data: 0.0004  max mem: 42573
Epoch: [53]  [270/312]  eta: 0:00:19  lr: 0.003857  min_lr: 0.003857  loss: 2.7187 (2.7449)  weight_decay: 0.0500 (0.0500)  time: 0.4369  data: 0.0004  max mem: 42573
Epoch: [53]  [280/312]  eta: 0:00:15  lr: 0.003857  min_lr: 0.003857  loss: 2.7187 (2.7501)  weight_decay: 0.0500 (0.0500)  time: 0.4354  data: 0.0009  max mem: 42573
Epoch: [53]  [290/312]  eta: 0:00:10  lr: 0.003857  min_lr: 0.003857  loss: 2.9902 (2.7587)  weight_decay: 0.0500 (0.0500)  time: 0.4347  data: 0.0007  max mem: 42573
Epoch: [53]  [300/312]  eta: 0:00:05  lr: 0.003857  min_lr: 0.003857  loss: 2.9779 (2.7645)  weight_decay: 0.0500 (0.0500)  time: 0.4328  data: 0.0001  max mem: 42573
Epoch: [53]  [310/312]  eta: 0:00:00  lr: 0.003856  min_lr: 0.003856  loss: 2.9592 (2.7631)  weight_decay: 0.0500 (0.0500)  time: 0.4326  data: 0.0001  max mem: 42573
Epoch: [53]  [311/312]  eta: 0:00:00  lr: 0.003856  min_lr: 0.003856  loss: 2.9592 (2.7625)  weight_decay: 0.0500 (0.0500)  time: 0.4326  data: 0.0001  max mem: 42573
Epoch: [53] Total time: 0:02:26 (0.4701 s / it)
Averaged stats: lr: 0.003856  min_lr: 0.003856  loss: 2.9592 (2.8024)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:00:43  loss: 0.9801 (0.9801)  acc1: 76.8229 (76.8229)  acc5: 91.4062 (91.4062)  time: 4.8700  data: 4.7606  max mem: 42573
Test:  [8/9]  eta: 0:00:00  loss: 1.4742 (1.3752)  acc1: 64.3229 (66.1760)  acc5: 87.5000 (87.2320)  time: 0.6171  data: 0.5290  max mem: 42573
Test: Total time: 0:00:05 (0.6320 s / it)
* Acc@1 67.154 Acc@5 87.572 loss 1.358
Accuracy of the model on the 50000 test images: 67.2%
Max accuracy: 67.83%
Epoch: [54]  [  0/312]  eta: 0:46:53  lr: 0.003856  min_lr: 0.003856  loss: 2.9046 (2.9046)  weight_decay: 0.0500 (0.0500)  time: 9.0191  data: 6.4884  max mem: 42573
Epoch: [54]  [ 10/312]  eta: 0:06:52  lr: 0.003856  min_lr: 0.003856  loss: 2.9046 (2.7723)  weight_decay: 0.0500 (0.0500)  time: 1.3653  data: 0.7084  max mem: 42573
Epoch: [54]  [ 20/312]  eta: 0:04:29  lr: 0.003856  min_lr: 0.003856  loss: 2.8532 (2.7456)  weight_decay: 0.0500 (0.0500)  time: 0.5187  data: 0.0654  max mem: 42573
Epoch: [54]  [ 30/312]  eta: 0:03:35  lr: 0.003855  min_lr: 0.003855  loss: 2.5916 (2.7121)  weight_decay: 0.0500 (0.0500)  time: 0.4354  data: 0.0004  max mem: 42573
Epoch: [54]  [ 40/312]  eta: 0:03:06  lr: 0.003855  min_lr: 0.003855  loss: 2.6437 (2.7538)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [54]  [ 50/312]  eta: 0:02:46  lr: 0.003855  min_lr: 0.003855  loss: 2.9412 (2.7276)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0005  max mem: 42573
Epoch: [54]  [ 60/312]  eta: 0:02:31  lr: 0.003855  min_lr: 0.003855  loss: 2.8356 (2.7424)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [54]  [ 70/312]  eta: 0:02:19  lr: 0.003854  min_lr: 0.003854  loss: 2.7810 (2.7446)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [54]  [ 80/312]  eta: 0:02:10  lr: 0.003854  min_lr: 0.003854  loss: 2.6693 (2.7273)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [54]  [ 90/312]  eta: 0:02:01  lr: 0.003854  min_lr: 0.003854  loss: 2.7707 (2.7497)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [54]  [100/312]  eta: 0:01:53  lr: 0.003854  min_lr: 0.003854  loss: 2.8457 (2.7586)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [54]  [110/312]  eta: 0:01:46  lr: 0.003853  min_lr: 0.003853  loss: 2.7248 (2.7621)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [54]  [120/312]  eta: 0:01:39  lr: 0.003853  min_lr: 0.003853  loss: 2.7834 (2.7613)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0005  max mem: 42573
Epoch: [54]  [130/312]  eta: 0:01:33  lr: 0.003853  min_lr: 0.003853  loss: 2.6509 (2.7464)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [54]  [140/312]  eta: 0:01:27  lr: 0.003852  min_lr: 0.003852  loss: 2.8162 (2.7487)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [54]  [150/312]  eta: 0:01:21  lr: 0.003852  min_lr: 0.003852  loss: 2.8946 (2.7482)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [54]  [160/312]  eta: 0:01:15  lr: 0.003852  min_lr: 0.003852  loss: 2.8964 (2.7450)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [54]  [170/312]  eta: 0:01:10  lr: 0.003852  min_lr: 0.003852  loss: 2.8056 (2.7508)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [54]  [180/312]  eta: 0:01:04  lr: 0.003851  min_lr: 0.003851  loss: 2.7963 (2.7473)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0003  max mem: 42573
Epoch: [54]  [190/312]  eta: 0:00:59  lr: 0.003851  min_lr: 0.003851  loss: 2.8941 (2.7572)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [54]  [200/312]  eta: 0:00:54  lr: 0.003851  min_lr: 0.003851  loss: 2.8031 (2.7521)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [54]  [210/312]  eta: 0:00:49  lr: 0.003851  min_lr: 0.003851  loss: 2.7137 (2.7508)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [54]  [220/312]  eta: 0:00:44  lr: 0.003850  min_lr: 0.003850  loss: 2.8187 (2.7688)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [54]  [230/312]  eta: 0:00:39  lr: 0.003850  min_lr: 0.003850  loss: 2.8018 (2.7627)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [54]  [240/312]  eta: 0:00:34  lr: 0.003850  min_lr: 0.003850  loss: 2.6635 (2.7605)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [54]  [250/312]  eta: 0:00:29  lr: 0.003849  min_lr: 0.003849  loss: 2.9894 (2.7647)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [54]  [260/312]  eta: 0:00:24  lr: 0.003849  min_lr: 0.003849  loss: 2.7959 (2.7643)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0003  max mem: 42573
Epoch: [54]  [270/312]  eta: 0:00:19  lr: 0.003849  min_lr: 0.003849  loss: 2.7959 (2.7671)  weight_decay: 0.0500 (0.0500)  time: 0.4398  data: 0.0004  max mem: 42573
Epoch: [54]  [280/312]  eta: 0:00:15  lr: 0.003849  min_lr: 0.003849  loss: 2.9146 (2.7743)  weight_decay: 0.0500 (0.0500)  time: 0.4406  data: 0.0009  max mem: 42573
Epoch: [54]  [290/312]  eta: 0:00:10  lr: 0.003848  min_lr: 0.003848  loss: 3.0023 (2.7825)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0007  max mem: 42573
Epoch: [54]  [300/312]  eta: 0:00:05  lr: 0.003848  min_lr: 0.003848  loss: 2.9653 (2.7795)  weight_decay: 0.0500 (0.0500)  time: 0.4325  data: 0.0001  max mem: 42573
Epoch: [54]  [310/312]  eta: 0:00:00  lr: 0.003848  min_lr: 0.003848  loss: 2.5920 (2.7787)  weight_decay: 0.0500 (0.0500)  time: 0.4323  data: 0.0001  max mem: 42573
Epoch: [54]  [311/312]  eta: 0:00:00  lr: 0.003848  min_lr: 0.003848  loss: 2.5714 (2.7760)  weight_decay: 0.0500 (0.0500)  time: 0.4323  data: 0.0001  max mem: 42573
Epoch: [54] Total time: 0:02:26 (0.4700 s / it)
Averaged stats: lr: 0.003848  min_lr: 0.003848  loss: 2.5714 (2.7849)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:00:43  loss: 1.2937 (1.2937)  acc1: 70.5729 (70.5729)  acc5: 90.1042 (90.1042)  time: 4.8148  data: 4.7056  max mem: 42573
Test:  [8/9]  eta: 0:00:00  loss: 1.6900 (1.5248)  acc1: 62.2396 (64.1280)  acc5: 85.1562 (85.9840)  time: 0.6110  data: 0.5229  max mem: 42573
Test: Total time: 0:00:05 (0.6439 s / it)
* Acc@1 64.202 Acc@5 85.718 loss 1.539
Accuracy of the model on the 50000 test images: 64.2%
Max accuracy: 67.83%
Epoch: [55]  [  0/312]  eta: 0:49:27  lr: 0.003848  min_lr: 0.003848  loss: 3.0050 (3.0050)  weight_decay: 0.0500 (0.0500)  time: 9.5115  data: 6.4137  max mem: 42573
Epoch: [55]  [ 10/312]  eta: 0:07:25  lr: 0.003848  min_lr: 0.003848  loss: 2.8852 (2.7202)  weight_decay: 0.0500 (0.0500)  time: 1.4767  data: 0.6524  max mem: 42573
Epoch: [55]  [ 20/312]  eta: 0:04:46  lr: 0.003847  min_lr: 0.003847  loss: 2.5851 (2.6122)  weight_decay: 0.0500 (0.0500)  time: 0.5534  data: 0.0383  max mem: 42573
Epoch: [55]  [ 30/312]  eta: 0:03:46  lr: 0.003847  min_lr: 0.003847  loss: 2.6784 (2.6574)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0003  max mem: 42573
Epoch: [55]  [ 40/312]  eta: 0:03:14  lr: 0.003847  min_lr: 0.003847  loss: 2.7541 (2.6868)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [55]  [ 50/312]  eta: 0:02:52  lr: 0.003846  min_lr: 0.003846  loss: 2.9588 (2.7616)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [55]  [ 60/312]  eta: 0:02:36  lr: 0.003846  min_lr: 0.003846  loss: 2.9588 (2.7443)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0005  max mem: 42573
Epoch: [55]  [ 70/312]  eta: 0:02:24  lr: 0.003846  min_lr: 0.003846  loss: 2.6909 (2.7459)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [55]  [ 80/312]  eta: 0:02:13  lr: 0.003846  min_lr: 0.003846  loss: 2.8542 (2.7490)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [55]  [ 90/312]  eta: 0:02:04  lr: 0.003845  min_lr: 0.003845  loss: 2.8782 (2.7451)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [55]  [100/312]  eta: 0:01:56  lr: 0.003845  min_lr: 0.003845  loss: 2.8910 (2.7559)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [55]  [110/312]  eta: 0:01:48  lr: 0.003845  min_lr: 0.003845  loss: 3.0108 (2.7667)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [55]  [120/312]  eta: 0:01:41  lr: 0.003844  min_lr: 0.003844  loss: 2.9329 (2.7580)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [55]  [130/312]  eta: 0:01:34  lr: 0.003844  min_lr: 0.003844  loss: 2.8494 (2.7563)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0004  max mem: 42573
Epoch: [55]  [140/312]  eta: 0:01:28  lr: 0.003844  min_lr: 0.003844  loss: 2.7582 (2.7525)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [55]  [150/312]  eta: 0:01:22  lr: 0.003844  min_lr: 0.003844  loss: 2.7376 (2.7553)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [55]  [160/312]  eta: 0:01:16  lr: 0.003843  min_lr: 0.003843  loss: 2.8072 (2.7681)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [55]  [170/312]  eta: 0:01:11  lr: 0.003843  min_lr: 0.003843  loss: 3.0544 (2.7798)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [55]  [180/312]  eta: 0:01:05  lr: 0.003843  min_lr: 0.003843  loss: 2.9939 (2.7831)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [55]  [190/312]  eta: 0:01:00  lr: 0.003843  min_lr: 0.003843  loss: 2.6376 (2.7696)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [55]  [200/312]  eta: 0:00:54  lr: 0.003842  min_lr: 0.003842  loss: 2.6224 (2.7649)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0003  max mem: 42573
Epoch: [55]  [210/312]  eta: 0:00:49  lr: 0.003842  min_lr: 0.003842  loss: 2.8229 (2.7707)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0004  max mem: 42573
Epoch: [55]  [220/312]  eta: 0:00:44  lr: 0.003842  min_lr: 0.003842  loss: 2.8318 (2.7786)  weight_decay: 0.0500 (0.0500)  time: 0.4341  data: 0.0004  max mem: 42573
Epoch: [55]  [230/312]  eta: 0:00:39  lr: 0.003841  min_lr: 0.003841  loss: 2.9980 (2.7858)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0004  max mem: 42573
Epoch: [55]  [240/312]  eta: 0:00:34  lr: 0.003841  min_lr: 0.003841  loss: 3.0482 (2.7987)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [55]  [250/312]  eta: 0:00:29  lr: 0.003841  min_lr: 0.003841  loss: 2.8925 (2.7926)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [55]  [260/312]  eta: 0:00:24  lr: 0.003841  min_lr: 0.003841  loss: 2.4371 (2.7812)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0003  max mem: 42573
Epoch: [55]  [270/312]  eta: 0:00:19  lr: 0.003840  min_lr: 0.003840  loss: 2.6794 (2.7824)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [55]  [280/312]  eta: 0:00:15  lr: 0.003840  min_lr: 0.003840  loss: 2.6741 (2.7711)  weight_decay: 0.0500 (0.0500)  time: 0.4343  data: 0.0009  max mem: 42573
Epoch: [55]  [290/312]  eta: 0:00:10  lr: 0.003840  min_lr: 0.003840  loss: 2.6993 (2.7758)  weight_decay: 0.0500 (0.0500)  time: 0.4353  data: 0.0008  max mem: 42573
Epoch: [55]  [300/312]  eta: 0:00:05  lr: 0.003839  min_lr: 0.003839  loss: 2.9255 (2.7796)  weight_decay: 0.0500 (0.0500)  time: 0.4341  data: 0.0001  max mem: 42573
Epoch: [55]  [310/312]  eta: 0:00:00  lr: 0.003839  min_lr: 0.003839  loss: 2.9255 (2.7831)  weight_decay: 0.0500 (0.0500)  time: 0.4324  data: 0.0001  max mem: 42573
Epoch: [55]  [311/312]  eta: 0:00:00  lr: 0.003839  min_lr: 0.003839  loss: 2.9716 (2.7851)  weight_decay: 0.0500 (0.0500)  time: 0.4324  data: 0.0001  max mem: 42573
Epoch: [55] Total time: 0:02:27 (0.4735 s / it)
Averaged stats: lr: 0.003839  min_lr: 0.003839  loss: 2.9716 (2.7839)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:00:42  loss: 1.2561 (1.2561)  acc1: 73.4375 (73.4375)  acc5: 86.9792 (86.9792)  time: 4.7490  data: 4.6394  max mem: 42573
Test:  [8/9]  eta: 0:00:00  loss: 1.5756 (1.5191)  acc1: 63.5417 (64.3840)  acc5: 86.9792 (84.8960)  time: 0.6031  data: 0.5155  max mem: 42573
Test: Total time: 0:00:05 (0.6101 s / it)
* Acc@1 64.688 Acc@5 85.384 loss 1.540
Accuracy of the model on the 50000 test images: 64.7%
Max accuracy: 67.83%
Epoch: [56]  [  0/312]  eta: 0:48:56  lr: 0.003839  min_lr: 0.003839  loss: 3.3142 (3.3142)  weight_decay: 0.0500 (0.0500)  time: 9.4120  data: 6.2031  max mem: 42573
Epoch: [56]  [ 10/312]  eta: 0:07:30  lr: 0.003839  min_lr: 0.003839  loss: 2.6372 (2.6120)  weight_decay: 0.0500 (0.0500)  time: 1.4913  data: 0.6548  max mem: 42573
Epoch: [56]  [ 20/312]  eta: 0:04:48  lr: 0.003839  min_lr: 0.003839  loss: 2.6951 (2.7883)  weight_decay: 0.0500 (0.0500)  time: 0.5661  data: 0.0501  max mem: 42573
Epoch: [56]  [ 30/312]  eta: 0:03:48  lr: 0.003838  min_lr: 0.003838  loss: 2.9593 (2.7723)  weight_decay: 0.0500 (0.0500)  time: 0.4331  data: 0.0003  max mem: 42573
Epoch: [56]  [ 40/312]  eta: 0:03:15  lr: 0.003838  min_lr: 0.003838  loss: 2.7945 (2.7562)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0003  max mem: 42573
Epoch: [56]  [ 50/312]  eta: 0:02:53  lr: 0.003838  min_lr: 0.003838  loss: 2.7536 (2.7530)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0003  max mem: 42573
Epoch: [56]  [ 60/312]  eta: 0:02:37  lr: 0.003837  min_lr: 0.003837  loss: 2.5427 (2.7159)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [56]  [ 70/312]  eta: 0:02:24  lr: 0.003837  min_lr: 0.003837  loss: 2.8884 (2.7454)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [56]  [ 80/312]  eta: 0:02:13  lr: 0.003837  min_lr: 0.003837  loss: 2.8643 (2.7231)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [56]  [ 90/312]  eta: 0:02:04  lr: 0.003837  min_lr: 0.003837  loss: 2.5485 (2.7099)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [56]  [100/312]  eta: 0:01:56  lr: 0.003836  min_lr: 0.003836  loss: 2.8752 (2.7343)  weight_decay: 0.0500 (0.0500)  time: 0.4341  data: 0.0004  max mem: 42573
Epoch: [56]  [110/312]  eta: 0:01:49  lr: 0.003836  min_lr: 0.003836  loss: 3.0599 (2.7424)  weight_decay: 0.0500 (0.0500)  time: 0.4550  data: 0.0004  max mem: 42573
Epoch: [56]  [120/312]  eta: 0:01:42  lr: 0.003836  min_lr: 0.003836  loss: 2.7394 (2.7378)  weight_decay: 0.0500 (0.0500)  time: 0.4548  data: 0.0004  max mem: 42573
Epoch: [56]  [130/312]  eta: 0:01:35  lr: 0.003835  min_lr: 0.003835  loss: 2.9109 (2.7478)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [56]  [140/312]  eta: 0:01:29  lr: 0.003835  min_lr: 0.003835  loss: 2.8306 (2.7384)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [56]  [150/312]  eta: 0:01:23  lr: 0.003835  min_lr: 0.003835  loss: 2.5958 (2.7418)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0004  max mem: 42573
Epoch: [56]  [160/312]  eta: 0:01:17  lr: 0.003835  min_lr: 0.003835  loss: 2.8348 (2.7445)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [56]  [170/312]  eta: 0:01:11  lr: 0.003834  min_lr: 0.003834  loss: 2.8508 (2.7425)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [56]  [180/312]  eta: 0:01:06  lr: 0.003834  min_lr: 0.003834  loss: 2.6111 (2.7365)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [56]  [190/312]  eta: 0:01:00  lr: 0.003834  min_lr: 0.003834  loss: 2.5009 (2.7268)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [56]  [200/312]  eta: 0:00:55  lr: 0.003833  min_lr: 0.003833  loss: 2.7921 (2.7308)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [56]  [210/312]  eta: 0:00:50  lr: 0.003833  min_lr: 0.003833  loss: 2.8506 (2.7293)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [56]  [220/312]  eta: 0:00:44  lr: 0.003833  min_lr: 0.003833  loss: 2.7338 (2.7289)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [56]  [230/312]  eta: 0:00:39  lr: 0.003833  min_lr: 0.003833  loss: 2.7656 (2.7291)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [56]  [240/312]  eta: 0:00:34  lr: 0.003832  min_lr: 0.003832  loss: 2.8911 (2.7374)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [56]  [250/312]  eta: 0:00:29  lr: 0.003832  min_lr: 0.003832  loss: 2.8604 (2.7382)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0004  max mem: 42573
Epoch: [56]  [260/312]  eta: 0:00:24  lr: 0.003832  min_lr: 0.003832  loss: 2.7760 (2.7410)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [56]  [270/312]  eta: 0:00:20  lr: 0.003831  min_lr: 0.003831  loss: 2.9396 (2.7501)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [56]  [280/312]  eta: 0:00:15  lr: 0.003831  min_lr: 0.003831  loss: 2.7032 (2.7436)  weight_decay: 0.0500 (0.0500)  time: 0.4343  data: 0.0010  max mem: 42573
Epoch: [56]  [290/312]  eta: 0:00:10  lr: 0.003831  min_lr: 0.003831  loss: 2.6490 (2.7478)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0008  max mem: 42573
Epoch: [56]  [300/312]  eta: 0:00:05  lr: 0.003831  min_lr: 0.003831  loss: 2.9763 (2.7491)  weight_decay: 0.0500 (0.0500)  time: 0.4324  data: 0.0001  max mem: 42573
Epoch: [56]  [310/312]  eta: 0:00:00  lr: 0.003830  min_lr: 0.003830  loss: 2.8903 (2.7542)  weight_decay: 0.0500 (0.0500)  time: 0.4324  data: 0.0001  max mem: 42573
Epoch: [56]  [311/312]  eta: 0:00:00  lr: 0.003830  min_lr: 0.003830  loss: 2.9186 (2.7560)  weight_decay: 0.0500 (0.0500)  time: 0.4324  data: 0.0001  max mem: 42573
Epoch: [56] Total time: 0:02:28 (0.4753 s / it)
Averaged stats: lr: 0.003830  min_lr: 0.003830  loss: 2.9186 (2.7839)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:00:43  loss: 1.1573 (1.1573)  acc1: 73.6979 (73.6979)  acc5: 91.1458 (91.1458)  time: 4.7911  data: 4.6816  max mem: 42573
Test:  [8/9]  eta: 0:00:00  loss: 1.4864 (1.4355)  acc1: 66.1458 (67.0720)  acc5: 87.7604 (87.3920)  time: 0.6082  data: 0.5203  max mem: 42573
Test: Total time: 0:00:05 (0.6274 s / it)
* Acc@1 66.756 Acc@5 86.958 loss 1.444
Accuracy of the model on the 50000 test images: 66.8%
Max accuracy: 67.83%
Epoch: [57]  [  0/312]  eta: 0:50:16  lr: 0.003830  min_lr: 0.003830  loss: 3.4423 (3.4423)  weight_decay: 0.0500 (0.0500)  time: 9.6682  data: 6.4564  max mem: 42573
Epoch: [57]  [ 10/312]  eta: 0:07:22  lr: 0.003830  min_lr: 0.003830  loss: 2.7056 (2.7658)  weight_decay: 0.0500 (0.0500)  time: 1.4652  data: 0.7530  max mem: 42573
Epoch: [57]  [ 20/312]  eta: 0:04:44  lr: 0.003830  min_lr: 0.003830  loss: 2.6796 (2.7435)  weight_decay: 0.0500 (0.0500)  time: 0.5390  data: 0.0915  max mem: 42573
Epoch: [57]  [ 30/312]  eta: 0:03:45  lr: 0.003829  min_lr: 0.003829  loss: 2.5164 (2.6430)  weight_decay: 0.0500 (0.0500)  time: 0.4332  data: 0.0004  max mem: 42573
Epoch: [57]  [ 40/312]  eta: 0:03:13  lr: 0.003829  min_lr: 0.003829  loss: 2.6944 (2.6785)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [57]  [ 50/312]  eta: 0:02:51  lr: 0.003829  min_lr: 0.003829  loss: 2.7897 (2.7145)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [57]  [ 60/312]  eta: 0:02:36  lr: 0.003828  min_lr: 0.003828  loss: 2.7586 (2.7061)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [57]  [ 70/312]  eta: 0:02:23  lr: 0.003828  min_lr: 0.003828  loss: 2.6834 (2.6904)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [57]  [ 80/312]  eta: 0:02:13  lr: 0.003828  min_lr: 0.003828  loss: 2.6834 (2.6977)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [57]  [ 90/312]  eta: 0:02:03  lr: 0.003828  min_lr: 0.003828  loss: 2.8749 (2.7256)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [57]  [100/312]  eta: 0:01:55  lr: 0.003827  min_lr: 0.003827  loss: 2.9985 (2.7430)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [57]  [110/312]  eta: 0:01:48  lr: 0.003827  min_lr: 0.003827  loss: 2.8155 (2.7314)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0004  max mem: 42573
Epoch: [57]  [120/312]  eta: 0:01:41  lr: 0.003827  min_lr: 0.003827  loss: 2.6234 (2.7238)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0004  max mem: 42573
Epoch: [57]  [130/312]  eta: 0:01:34  lr: 0.003826  min_lr: 0.003826  loss: 2.8954 (2.7410)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0004  max mem: 42573
Epoch: [57]  [140/312]  eta: 0:01:28  lr: 0.003826  min_lr: 0.003826  loss: 2.8928 (2.7432)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [57]  [150/312]  eta: 0:01:22  lr: 0.003826  min_lr: 0.003826  loss: 2.8439 (2.7499)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [57]  [160/312]  eta: 0:01:16  lr: 0.003825  min_lr: 0.003825  loss: 2.8439 (2.7513)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [57]  [170/312]  eta: 0:01:11  lr: 0.003825  min_lr: 0.003825  loss: 2.8435 (2.7574)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [57]  [180/312]  eta: 0:01:05  lr: 0.003825  min_lr: 0.003825  loss: 2.8018 (2.7498)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [57]  [190/312]  eta: 0:01:00  lr: 0.003825  min_lr: 0.003825  loss: 2.6513 (2.7455)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [57]  [200/312]  eta: 0:00:54  lr: 0.003824  min_lr: 0.003824  loss: 2.6864 (2.7419)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [57]  [210/312]  eta: 0:00:49  lr: 0.003824  min_lr: 0.003824  loss: 2.9088 (2.7440)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [57]  [220/312]  eta: 0:00:44  lr: 0.003824  min_lr: 0.003824  loss: 2.7423 (2.7331)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [57]  [230/312]  eta: 0:00:39  lr: 0.003823  min_lr: 0.003823  loss: 2.6069 (2.7309)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [57]  [240/312]  eta: 0:00:34  lr: 0.003823  min_lr: 0.003823  loss: 2.8360 (2.7356)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [57]  [250/312]  eta: 0:00:29  lr: 0.003823  min_lr: 0.003823  loss: 2.8890 (2.7401)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0003  max mem: 42573
Epoch: [57]  [260/312]  eta: 0:00:24  lr: 0.003823  min_lr: 0.003823  loss: 2.8890 (2.7460)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0003  max mem: 42573
Epoch: [57]  [270/312]  eta: 0:00:19  lr: 0.003822  min_lr: 0.003822  loss: 2.9071 (2.7462)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [57]  [280/312]  eta: 0:00:15  lr: 0.003822  min_lr: 0.003822  loss: 2.7778 (2.7482)  weight_decay: 0.0500 (0.0500)  time: 0.4347  data: 0.0010  max mem: 42573
Epoch: [57]  [290/312]  eta: 0:00:10  lr: 0.003822  min_lr: 0.003822  loss: 2.6913 (2.7430)  weight_decay: 0.0500 (0.0500)  time: 0.4341  data: 0.0008  max mem: 42573
Epoch: [57]  [300/312]  eta: 0:00:05  lr: 0.003821  min_lr: 0.003821  loss: 2.5779 (2.7378)  weight_decay: 0.0500 (0.0500)  time: 0.4326  data: 0.0001  max mem: 42573
Epoch: [57]  [310/312]  eta: 0:00:00  lr: 0.003821  min_lr: 0.003821  loss: 2.7556 (2.7436)  weight_decay: 0.0500 (0.0500)  time: 0.4324  data: 0.0001  max mem: 42573
Epoch: [57]  [311/312]  eta: 0:00:00  lr: 0.003821  min_lr: 0.003821  loss: 2.7556 (2.7419)  weight_decay: 0.0500 (0.0500)  time: 0.4324  data: 0.0001  max mem: 42573
Epoch: [57] Total time: 0:02:27 (0.4730 s / it)
Averaged stats: lr: 0.003821  min_lr: 0.003821  loss: 2.7556 (2.7565)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:00:42  loss: 1.0827 (1.0827)  acc1: 76.3021 (76.3021)  acc5: 90.8854 (90.8854)  time: 4.6896  data: 4.5802  max mem: 42573
Test:  [8/9]  eta: 0:00:00  loss: 1.4114 (1.3627)  acc1: 68.7500 (66.6560)  acc5: 86.9792 (87.5520)  time: 0.5980  data: 0.5090  max mem: 42573
Test: Total time: 0:00:05 (0.6106 s / it)
* Acc@1 67.038 Acc@5 87.822 loss 1.365
Accuracy of the model on the 50000 test images: 67.0%
Max accuracy: 67.83%
Epoch: [58]  [  0/312]  eta: 0:52:11  lr: 0.003821  min_lr: 0.003821  loss: 2.5782 (2.5782)  weight_decay: 0.0500 (0.0500)  time: 10.0353  data: 7.4658  max mem: 42573
Epoch: [58]  [ 10/312]  eta: 0:07:37  lr: 0.003821  min_lr: 0.003821  loss: 3.0309 (2.7770)  weight_decay: 0.0500 (0.0500)  time: 1.5141  data: 0.6790  max mem: 42573
Epoch: [58]  [ 20/312]  eta: 0:04:51  lr: 0.003820  min_lr: 0.003820  loss: 3.0187 (2.7867)  weight_decay: 0.0500 (0.0500)  time: 0.5477  data: 0.0004  max mem: 42573
Epoch: [58]  [ 30/312]  eta: 0:03:50  lr: 0.003820  min_lr: 0.003820  loss: 2.6926 (2.6911)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [58]  [ 40/312]  eta: 0:03:16  lr: 0.003820  min_lr: 0.003820  loss: 2.6926 (2.7259)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0003  max mem: 42573
Epoch: [58]  [ 50/312]  eta: 0:02:54  lr: 0.003820  min_lr: 0.003820  loss: 2.9314 (2.7773)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0003  max mem: 42573
Epoch: [58]  [ 60/312]  eta: 0:02:38  lr: 0.003819  min_lr: 0.003819  loss: 2.8951 (2.7454)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [58]  [ 70/312]  eta: 0:02:25  lr: 0.003819  min_lr: 0.003819  loss: 2.8892 (2.7710)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0003  max mem: 42573
Epoch: [58]  [ 80/312]  eta: 0:02:14  lr: 0.003819  min_lr: 0.003819  loss: 2.7886 (2.7517)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [58]  [ 90/312]  eta: 0:02:05  lr: 0.003818  min_lr: 0.003818  loss: 2.5737 (2.7386)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [58]  [100/312]  eta: 0:01:56  lr: 0.003818  min_lr: 0.003818  loss: 2.9107 (2.7593)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [58]  [110/312]  eta: 0:01:49  lr: 0.003818  min_lr: 0.003818  loss: 2.9107 (2.7625)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [58]  [120/312]  eta: 0:01:42  lr: 0.003817  min_lr: 0.003817  loss: 2.9399 (2.7792)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [58]  [130/312]  eta: 0:01:35  lr: 0.003817  min_lr: 0.003817  loss: 2.9399 (2.7800)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [58]  [140/312]  eta: 0:01:29  lr: 0.003817  min_lr: 0.003817  loss: 2.8481 (2.7817)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [58]  [150/312]  eta: 0:01:23  lr: 0.003817  min_lr: 0.003817  loss: 2.9110 (2.7799)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0003  max mem: 42573
Epoch: [58]  [160/312]  eta: 0:01:17  lr: 0.003816  min_lr: 0.003816  loss: 2.6712 (2.7698)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [58]  [170/312]  eta: 0:01:11  lr: 0.003816  min_lr: 0.003816  loss: 2.7011 (2.7786)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [58]  [180/312]  eta: 0:01:05  lr: 0.003816  min_lr: 0.003816  loss: 2.7626 (2.7688)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [58]  [190/312]  eta: 0:01:00  lr: 0.003815  min_lr: 0.003815  loss: 2.8790 (2.7732)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [58]  [200/312]  eta: 0:00:55  lr: 0.003815  min_lr: 0.003815  loss: 2.9092 (2.7753)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0004  max mem: 42573
Epoch: [58]  [210/312]  eta: 0:00:49  lr: 0.003815  min_lr: 0.003815  loss: 2.8164 (2.7714)  weight_decay: 0.0500 (0.0500)  time: 0.4341  data: 0.0004  max mem: 42573
Epoch: [58]  [220/312]  eta: 0:00:44  lr: 0.003814  min_lr: 0.003814  loss: 2.4290 (2.7552)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [58]  [230/312]  eta: 0:00:39  lr: 0.003814  min_lr: 0.003814  loss: 2.4973 (2.7608)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [58]  [240/312]  eta: 0:00:34  lr: 0.003814  min_lr: 0.003814  loss: 2.9401 (2.7597)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0003  max mem: 42573
Epoch: [58]  [250/312]  eta: 0:00:29  lr: 0.003813  min_lr: 0.003813  loss: 2.8747 (2.7582)  weight_decay: 0.0500 (0.0500)  time: 0.4399  data: 0.0004  max mem: 42573
Epoch: [58]  [260/312]  eta: 0:00:24  lr: 0.003813  min_lr: 0.003813  loss: 2.7324 (2.7556)  weight_decay: 0.0500 (0.0500)  time: 0.4400  data: 0.0003  max mem: 42573
Epoch: [58]  [270/312]  eta: 0:00:20  lr: 0.003813  min_lr: 0.003813  loss: 2.7453 (2.7559)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0003  max mem: 42573
Epoch: [58]  [280/312]  eta: 0:00:15  lr: 0.003813  min_lr: 0.003813  loss: 2.9265 (2.7602)  weight_decay: 0.0500 (0.0500)  time: 0.4346  data: 0.0009  max mem: 42573
Epoch: [58]  [290/312]  eta: 0:00:10  lr: 0.003812  min_lr: 0.003812  loss: 2.9337 (2.7637)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0008  max mem: 42573
Epoch: [58]  [300/312]  eta: 0:00:05  lr: 0.003812  min_lr: 0.003812  loss: 2.9337 (2.7660)  weight_decay: 0.0500 (0.0500)  time: 0.4325  data: 0.0001  max mem: 42573
Epoch: [58]  [310/312]  eta: 0:00:00  lr: 0.003812  min_lr: 0.003812  loss: 2.5639 (2.7602)  weight_decay: 0.0500 (0.0500)  time: 0.4326  data: 0.0001  max mem: 42573
Epoch: [58]  [311/312]  eta: 0:00:00  lr: 0.003812  min_lr: 0.003812  loss: 2.8661 (2.7606)  weight_decay: 0.0500 (0.0500)  time: 0.4326  data: 0.0001  max mem: 42573
Epoch: [58] Total time: 0:02:28 (0.4750 s / it)
Averaged stats: lr: 0.003812  min_lr: 0.003812  loss: 2.8661 (2.7575)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:00:44  loss: 1.2206 (1.2206)  acc1: 72.6562 (72.6562)  acc5: 88.8021 (88.8021)  time: 4.9079  data: 4.7985  max mem: 42573
Test:  [8/9]  eta: 0:00:00  loss: 1.4835 (1.3763)  acc1: 66.4062 (66.8800)  acc5: 87.5000 (87.6800)  time: 0.6223  data: 0.5332  max mem: 42573
Test: Total time: 0:00:05 (0.6477 s / it)
* Acc@1 66.884 Acc@5 87.384 loss 1.391
Accuracy of the model on the 50000 test images: 66.9%
Max accuracy: 67.83%
Epoch: [59]  [  0/312]  eta: 0:51:56  lr: 0.003812  min_lr: 0.003812  loss: 2.2361 (2.2361)  weight_decay: 0.0500 (0.0500)  time: 9.9902  data: 8.2717  max mem: 42573
Epoch: [59]  [ 10/312]  eta: 0:07:24  lr: 0.003811  min_lr: 0.003811  loss: 2.8378 (2.7007)  weight_decay: 0.0500 (0.0500)  time: 1.4711  data: 0.7985  max mem: 42573
Epoch: [59]  [ 20/312]  eta: 0:04:45  lr: 0.003811  min_lr: 0.003811  loss: 2.8161 (2.7045)  weight_decay: 0.0500 (0.0500)  time: 0.5262  data: 0.0258  max mem: 42573
Epoch: [59]  [ 30/312]  eta: 0:03:46  lr: 0.003811  min_lr: 0.003811  loss: 2.8161 (2.7339)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [59]  [ 40/312]  eta: 0:03:13  lr: 0.003810  min_lr: 0.003810  loss: 2.7519 (2.6861)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [59]  [ 50/312]  eta: 0:02:52  lr: 0.003810  min_lr: 0.003810  loss: 2.6367 (2.6983)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [59]  [ 60/312]  eta: 0:02:36  lr: 0.003810  min_lr: 0.003810  loss: 2.9527 (2.7233)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [59]  [ 70/312]  eta: 0:02:23  lr: 0.003809  min_lr: 0.003809  loss: 2.7548 (2.7005)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [59]  [ 80/312]  eta: 0:02:13  lr: 0.003809  min_lr: 0.003809  loss: 2.7247 (2.7013)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [59]  [ 90/312]  eta: 0:02:04  lr: 0.003809  min_lr: 0.003809  loss: 2.7764 (2.7172)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [59]  [100/312]  eta: 0:01:55  lr: 0.003809  min_lr: 0.003809  loss: 2.9043 (2.7137)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0005  max mem: 42573
Epoch: [59]  [110/312]  eta: 0:01:48  lr: 0.003808  min_lr: 0.003808  loss: 2.9043 (2.7220)  weight_decay: 0.0500 (0.0500)  time: 0.4342  data: 0.0005  max mem: 42573
Epoch: [59]  [120/312]  eta: 0:01:41  lr: 0.003808  min_lr: 0.003808  loss: 2.9732 (2.7340)  weight_decay: 0.0500 (0.0500)  time: 0.4341  data: 0.0004  max mem: 42573
Epoch: [59]  [130/312]  eta: 0:01:34  lr: 0.003808  min_lr: 0.003808  loss: 2.9089 (2.7422)  weight_decay: 0.0500 (0.0500)  time: 0.4341  data: 0.0004  max mem: 42573
Epoch: [59]  [140/312]  eta: 0:01:28  lr: 0.003807  min_lr: 0.003807  loss: 2.8661 (2.7493)  weight_decay: 0.0500 (0.0500)  time: 0.4341  data: 0.0004  max mem: 42573
Epoch: [59]  [150/312]  eta: 0:01:22  lr: 0.003807  min_lr: 0.003807  loss: 2.6332 (2.7344)  weight_decay: 0.0500 (0.0500)  time: 0.4341  data: 0.0004  max mem: 42573
Epoch: [59]  [160/312]  eta: 0:01:16  lr: 0.003807  min_lr: 0.003807  loss: 2.6819 (2.7424)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [59]  [170/312]  eta: 0:01:11  lr: 0.003806  min_lr: 0.003806  loss: 2.6875 (2.7301)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [59]  [180/312]  eta: 0:01:05  lr: 0.003806  min_lr: 0.003806  loss: 2.5187 (2.7302)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [59]  [190/312]  eta: 0:01:00  lr: 0.003806  min_lr: 0.003806  loss: 2.7844 (2.7340)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [59]  [200/312]  eta: 0:00:54  lr: 0.003805  min_lr: 0.003805  loss: 2.7723 (2.7223)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [59]  [210/312]  eta: 0:00:49  lr: 0.003805  min_lr: 0.003805  loss: 2.6744 (2.7201)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [59]  [220/312]  eta: 0:00:44  lr: 0.003805  min_lr: 0.003805  loss: 2.8486 (2.7280)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [59]  [230/312]  eta: 0:00:39  lr: 0.003805  min_lr: 0.003805  loss: 2.8789 (2.7321)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [59]  [240/312]  eta: 0:00:34  lr: 0.003804  min_lr: 0.003804  loss: 2.8635 (2.7372)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [59]  [250/312]  eta: 0:00:29  lr: 0.003804  min_lr: 0.003804  loss: 2.6357 (2.7307)  weight_decay: 0.0500 (0.0500)  time: 0.4392  data: 0.0004  max mem: 42573
Epoch: [59]  [260/312]  eta: 0:00:24  lr: 0.003804  min_lr: 0.003804  loss: 2.6331 (2.7322)  weight_decay: 0.0500 (0.0500)  time: 0.4391  data: 0.0004  max mem: 42573
Epoch: [59]  [270/312]  eta: 0:00:20  lr: 0.003803  min_lr: 0.003803  loss: 2.7352 (2.7259)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0003  max mem: 42573
Epoch: [59]  [280/312]  eta: 0:00:15  lr: 0.003803  min_lr: 0.003803  loss: 2.9196 (2.7286)  weight_decay: 0.0500 (0.0500)  time: 0.4344  data: 0.0009  max mem: 42573
Epoch: [59]  [290/312]  eta: 0:00:10  lr: 0.003803  min_lr: 0.003803  loss: 2.9425 (2.7358)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0008  max mem: 42573
Epoch: [59]  [300/312]  eta: 0:00:05  lr: 0.003802  min_lr: 0.003802  loss: 2.9271 (2.7379)  weight_decay: 0.0500 (0.0500)  time: 0.4326  data: 0.0001  max mem: 42573
Epoch: [59]  [310/312]  eta: 0:00:00  lr: 0.003802  min_lr: 0.003802  loss: 2.9982 (2.7489)  weight_decay: 0.0500 (0.0500)  time: 0.4326  data: 0.0001  max mem: 42573
Epoch: [59]  [311/312]  eta: 0:00:00  lr: 0.003802  min_lr: 0.003802  loss: 2.9982 (2.7497)  weight_decay: 0.0500 (0.0500)  time: 0.4325  data: 0.0001  max mem: 42573
Epoch: [59] Total time: 0:02:27 (0.4737 s / it)
Averaged stats: lr: 0.003802  min_lr: 0.003802  loss: 2.9982 (2.7679)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:00:46  loss: 1.2513 (1.2513)  acc1: 75.2604 (75.2604)  acc5: 91.4062 (91.4062)  time: 5.2051  data: 5.0965  max mem: 42573
Test:  [8/9]  eta: 0:00:00  loss: 1.6090 (1.4687)  acc1: 65.3646 (66.2080)  acc5: 85.1562 (86.5280)  time: 0.6538  data: 0.5663  max mem: 42573
Test: Total time: 0:00:05 (0.6611 s / it)
* Acc@1 66.180 Acc@5 86.876 loss 1.468
Accuracy of the model on the 50000 test images: 66.2%
Max accuracy: 67.83%
Epoch: [60]  [  0/312]  eta: 0:47:29  lr: 0.003802  min_lr: 0.003802  loss: 3.3026 (3.3026)  weight_decay: 0.0500 (0.0500)  time: 9.1337  data: 7.3790  max mem: 42573
Epoch: [60]  [ 10/312]  eta: 0:07:10  lr: 0.003802  min_lr: 0.003802  loss: 3.0434 (2.9355)  weight_decay: 0.0500 (0.0500)  time: 1.4261  data: 0.6712  max mem: 42573
Epoch: [60]  [ 20/312]  eta: 0:04:38  lr: 0.003801  min_lr: 0.003801  loss: 2.8974 (2.8299)  weight_decay: 0.0500 (0.0500)  time: 0.5443  data: 0.0004  max mem: 42573
Epoch: [60]  [ 30/312]  eta: 0:03:41  lr: 0.003801  min_lr: 0.003801  loss: 2.8321 (2.8049)  weight_decay: 0.0500 (0.0500)  time: 0.4332  data: 0.0003  max mem: 42573
Epoch: [60]  [ 40/312]  eta: 0:03:10  lr: 0.003801  min_lr: 0.003801  loss: 2.7415 (2.7812)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [60]  [ 50/312]  eta: 0:02:49  lr: 0.003800  min_lr: 0.003800  loss: 2.7415 (2.7768)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [60]  [ 60/312]  eta: 0:02:34  lr: 0.003800  min_lr: 0.003800  loss: 2.8111 (2.7666)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [60]  [ 70/312]  eta: 0:02:22  lr: 0.003800  min_lr: 0.003800  loss: 2.7581 (2.7555)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [60]  [ 80/312]  eta: 0:02:11  lr: 0.003799  min_lr: 0.003799  loss: 2.7692 (2.7689)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [60]  [ 90/312]  eta: 0:02:02  lr: 0.003799  min_lr: 0.003799  loss: 2.7692 (2.7684)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [60]  [100/312]  eta: 0:01:54  lr: 0.003799  min_lr: 0.003799  loss: 2.8148 (2.7739)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0003  max mem: 42573
Epoch: [60]  [110/312]  eta: 0:01:47  lr: 0.003799  min_lr: 0.003799  loss: 2.8181 (2.7762)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0003  max mem: 42573
Epoch: [60]  [120/312]  eta: 0:01:40  lr: 0.003798  min_lr: 0.003798  loss: 2.8218 (2.7900)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [60]  [130/312]  eta: 0:01:34  lr: 0.003798  min_lr: 0.003798  loss: 2.9605 (2.7978)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [60]  [140/312]  eta: 0:01:27  lr: 0.003798  min_lr: 0.003798  loss: 2.9700 (2.8005)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [60]  [150/312]  eta: 0:01:21  lr: 0.003797  min_lr: 0.003797  loss: 2.9460 (2.8003)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [60]  [160/312]  eta: 0:01:16  lr: 0.003797  min_lr: 0.003797  loss: 2.9495 (2.8102)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [60]  [170/312]  eta: 0:01:10  lr: 0.003797  min_lr: 0.003797  loss: 2.9687 (2.8181)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [60]  [180/312]  eta: 0:01:05  lr: 0.003796  min_lr: 0.003796  loss: 2.9118 (2.8247)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [60]  [190/312]  eta: 0:00:59  lr: 0.003796  min_lr: 0.003796  loss: 2.8645 (2.8247)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [60]  [200/312]  eta: 0:00:54  lr: 0.003796  min_lr: 0.003796  loss: 2.8010 (2.8125)  weight_decay: 0.0500 (0.0500)  time: 0.4367  data: 0.0004  max mem: 42573
Epoch: [60]  [210/312]  eta: 0:00:49  lr: 0.003795  min_lr: 0.003795  loss: 2.5810 (2.8133)  weight_decay: 0.0500 (0.0500)  time: 0.4368  data: 0.0004  max mem: 42573
Epoch: [60]  [220/312]  eta: 0:00:44  lr: 0.003795  min_lr: 0.003795  loss: 2.8040 (2.8104)  weight_decay: 0.0500 (0.0500)  time: 0.4343  data: 0.0004  max mem: 42573
Epoch: [60]  [230/312]  eta: 0:00:39  lr: 0.003795  min_lr: 0.003795  loss: 2.8143 (2.8117)  weight_decay: 0.0500 (0.0500)  time: 0.4341  data: 0.0004  max mem: 42573
Epoch: [60]  [240/312]  eta: 0:00:34  lr: 0.003794  min_lr: 0.003794  loss: 2.9544 (2.8136)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [60]  [250/312]  eta: 0:00:29  lr: 0.003794  min_lr: 0.003794  loss: 2.6706 (2.8038)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [60]  [260/312]  eta: 0:00:24  lr: 0.003794  min_lr: 0.003794  loss: 2.4561 (2.7972)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [60]  [270/312]  eta: 0:00:19  lr: 0.003793  min_lr: 0.003793  loss: 2.6040 (2.7943)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [60]  [280/312]  eta: 0:00:15  lr: 0.003793  min_lr: 0.003793  loss: 2.8260 (2.7959)  weight_decay: 0.0500 (0.0500)  time: 0.4348  data: 0.0009  max mem: 42573
Epoch: [60]  [290/312]  eta: 0:00:10  lr: 0.003793  min_lr: 0.003793  loss: 2.9682 (2.7993)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0008  max mem: 42573
Epoch: [60]  [300/312]  eta: 0:00:05  lr: 0.003793  min_lr: 0.003793  loss: 3.0297 (2.7998)  weight_decay: 0.0500 (0.0500)  time: 0.4324  data: 0.0001  max mem: 42573
Epoch: [60]  [310/312]  eta: 0:00:00  lr: 0.003792  min_lr: 0.003792  loss: 2.8970 (2.8001)  weight_decay: 0.0500 (0.0500)  time: 0.4323  data: 0.0001  max mem: 42573
Epoch: [60]  [311/312]  eta: 0:00:00  lr: 0.003792  min_lr: 0.003792  loss: 2.8970 (2.7999)  weight_decay: 0.0500 (0.0500)  time: 0.4323  data: 0.0001  max mem: 42573
Epoch: [60] Total time: 0:02:27 (0.4721 s / it)
Averaged stats: lr: 0.003792  min_lr: 0.003792  loss: 2.8970 (2.7597)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:00:42  loss: 1.0762 (1.0762)  acc1: 75.0000 (75.0000)  acc5: 91.6667 (91.6667)  time: 4.6995  data: 4.5899  max mem: 42573
Test:  [8/9]  eta: 0:00:00  loss: 1.5074 (1.3754)  acc1: 65.1042 (66.6560)  acc5: 86.7188 (87.7760)  time: 0.5995  data: 0.5101  max mem: 42573
Test: Total time: 0:00:05 (0.6070 s / it)
* Acc@1 67.366 Acc@5 87.630 loss 1.395
Accuracy of the model on the 50000 test images: 67.4%
Max accuracy: 67.83%
Epoch: [61]  [  0/312]  eta: 0:48:34  lr: 0.003792  min_lr: 0.003792  loss: 2.7699 (2.7699)  weight_decay: 0.0500 (0.0500)  time: 9.3406  data: 5.7705  max mem: 42573
Epoch: [61]  [ 10/312]  eta: 0:07:18  lr: 0.003792  min_lr: 0.003792  loss: 3.1231 (2.8366)  weight_decay: 0.0500 (0.0500)  time: 1.4534  data: 0.5730  max mem: 42573
Epoch: [61]  [ 20/312]  eta: 0:04:42  lr: 0.003792  min_lr: 0.003792  loss: 2.6328 (2.7300)  weight_decay: 0.0500 (0.0500)  time: 0.5490  data: 0.0268  max mem: 42573
Epoch: [61]  [ 30/312]  eta: 0:03:44  lr: 0.003791  min_lr: 0.003791  loss: 2.6328 (2.7407)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0003  max mem: 42573
Epoch: [61]  [ 40/312]  eta: 0:03:12  lr: 0.003791  min_lr: 0.003791  loss: 2.6215 (2.7054)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [61]  [ 50/312]  eta: 0:02:51  lr: 0.003791  min_lr: 0.003791  loss: 2.5970 (2.6886)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [61]  [ 60/312]  eta: 0:02:35  lr: 0.003790  min_lr: 0.003790  loss: 2.5273 (2.6757)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0004  max mem: 42573
Epoch: [61]  [ 70/312]  eta: 0:02:23  lr: 0.003790  min_lr: 0.003790  loss: 2.8629 (2.7339)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [61]  [ 80/312]  eta: 0:02:12  lr: 0.003790  min_lr: 0.003790  loss: 2.9907 (2.7340)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [61]  [ 90/312]  eta: 0:02:03  lr: 0.003789  min_lr: 0.003789  loss: 2.6800 (2.7428)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [61]  [100/312]  eta: 0:01:55  lr: 0.003789  min_lr: 0.003789  loss: 2.8365 (2.7388)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [61]  [110/312]  eta: 0:01:48  lr: 0.003789  min_lr: 0.003789  loss: 2.8774 (2.7585)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [61]  [120/312]  eta: 0:01:41  lr: 0.003788  min_lr: 0.003788  loss: 2.8349 (2.7590)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [61]  [130/312]  eta: 0:01:34  lr: 0.003788  min_lr: 0.003788  loss: 2.5956 (2.7454)  weight_decay: 0.0500 (0.0500)  time: 0.4341  data: 0.0004  max mem: 42573
Epoch: [61]  [140/312]  eta: 0:01:28  lr: 0.003788  min_lr: 0.003788  loss: 2.4427 (2.7316)  weight_decay: 0.0500 (0.0500)  time: 0.4341  data: 0.0004  max mem: 42573
Epoch: [61]  [150/312]  eta: 0:01:22  lr: 0.003787  min_lr: 0.003787  loss: 2.7684 (2.7441)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [61]  [160/312]  eta: 0:01:16  lr: 0.003787  min_lr: 0.003787  loss: 2.7699 (2.7301)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0003  max mem: 42573
Epoch: [61]  [170/312]  eta: 0:01:10  lr: 0.003787  min_lr: 0.003787  loss: 2.6738 (2.7340)  weight_decay: 0.0500 (0.0500)  time: 0.4354  data: 0.0003  max mem: 42573
Epoch: [61]  [180/312]  eta: 0:01:05  lr: 0.003786  min_lr: 0.003786  loss: 2.6660 (2.7308)  weight_decay: 0.0500 (0.0500)  time: 0.4353  data: 0.0003  max mem: 42573
Epoch: [61]  [190/312]  eta: 0:01:00  lr: 0.003786  min_lr: 0.003786  loss: 2.6235 (2.7281)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [61]  [200/312]  eta: 0:00:54  lr: 0.003786  min_lr: 0.003786  loss: 2.9132 (2.7319)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [61]  [210/312]  eta: 0:00:49  lr: 0.003785  min_lr: 0.003785  loss: 2.8990 (2.7310)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0003  max mem: 42573
Epoch: [61]  [220/312]  eta: 0:00:44  lr: 0.003785  min_lr: 0.003785  loss: 2.7769 (2.7153)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [61]  [230/312]  eta: 0:00:39  lr: 0.003785  min_lr: 0.003785  loss: 2.4612 (2.7142)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [61]  [240/312]  eta: 0:00:34  lr: 0.003784  min_lr: 0.003784  loss: 2.7800 (2.7202)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [61]  [250/312]  eta: 0:00:29  lr: 0.003784  min_lr: 0.003784  loss: 2.9223 (2.7255)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [61]  [260/312]  eta: 0:00:24  lr: 0.003784  min_lr: 0.003784  loss: 2.7673 (2.7264)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [61]  [270/312]  eta: 0:00:19  lr: 0.003783  min_lr: 0.003783  loss: 2.7004 (2.7207)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [61]  [280/312]  eta: 0:00:15  lr: 0.003783  min_lr: 0.003783  loss: 2.7389 (2.7233)  weight_decay: 0.0500 (0.0500)  time: 0.4345  data: 0.0009  max mem: 42573
Epoch: [61]  [290/312]  eta: 0:00:10  lr: 0.003783  min_lr: 0.003783  loss: 2.9298 (2.7305)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0008  max mem: 42573
Epoch: [61]  [300/312]  eta: 0:00:05  lr: 0.003782  min_lr: 0.003782  loss: 2.8133 (2.7253)  weight_decay: 0.0500 (0.0500)  time: 0.4326  data: 0.0001  max mem: 42573
Epoch: [61]  [310/312]  eta: 0:00:00  lr: 0.003782  min_lr: 0.003782  loss: 2.4016 (2.7186)  weight_decay: 0.0500 (0.0500)  time: 0.4326  data: 0.0001  max mem: 42573
Epoch: [61]  [311/312]  eta: 0:00:00  lr: 0.003782  min_lr: 0.003782  loss: 2.4706 (2.7191)  weight_decay: 0.0500 (0.0500)  time: 0.4325  data: 0.0001  max mem: 42573
Epoch: [61] Total time: 0:02:27 (0.4727 s / it)
Averaged stats: lr: 0.003782  min_lr: 0.003782  loss: 2.4706 (2.7499)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:00:41  loss: 1.1313 (1.1313)  acc1: 73.6979 (73.6979)  acc5: 89.3229 (89.3229)  time: 4.6126  data: 4.5030  max mem: 42573
Test:  [8/9]  eta: 0:00:00  loss: 1.4560 (1.3404)  acc1: 65.8854 (66.7840)  acc5: 87.2396 (87.1680)  time: 0.5898  data: 0.5004  max mem: 42573
Test: Total time: 0:00:05 (0.5984 s / it)
* Acc@1 67.506 Acc@5 87.592 loss 1.325
Accuracy of the model on the 50000 test images: 67.5%
Max accuracy: 67.83%
Epoch: [62]  [  0/312]  eta: 0:47:42  lr: 0.003782  min_lr: 0.003782  loss: 2.5721 (2.5721)  weight_decay: 0.0500 (0.0500)  time: 9.1740  data: 7.5103  max mem: 42573
Epoch: [62]  [ 10/312]  eta: 0:07:05  lr: 0.003782  min_lr: 0.003782  loss: 2.6281 (2.7291)  weight_decay: 0.0500 (0.0500)  time: 1.4087  data: 0.6833  max mem: 42573
Epoch: [62]  [ 20/312]  eta: 0:04:35  lr: 0.003781  min_lr: 0.003781  loss: 2.5667 (2.6695)  weight_decay: 0.0500 (0.0500)  time: 0.5325  data: 0.0005  max mem: 42573
Epoch: [62]  [ 30/312]  eta: 0:03:39  lr: 0.003781  min_lr: 0.003781  loss: 2.6872 (2.6731)  weight_decay: 0.0500 (0.0500)  time: 0.4331  data: 0.0004  max mem: 42573
Epoch: [62]  [ 40/312]  eta: 0:03:09  lr: 0.003781  min_lr: 0.003781  loss: 2.5532 (2.6491)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [62]  [ 50/312]  eta: 0:02:48  lr: 0.003780  min_lr: 0.003780  loss: 2.8131 (2.6850)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [62]  [ 60/312]  eta: 0:02:33  lr: 0.003780  min_lr: 0.003780  loss: 2.8774 (2.6994)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [62]  [ 70/312]  eta: 0:02:21  lr: 0.003780  min_lr: 0.003780  loss: 2.8127 (2.7106)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [62]  [ 80/312]  eta: 0:02:11  lr: 0.003779  min_lr: 0.003779  loss: 2.8684 (2.7379)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [62]  [ 90/312]  eta: 0:02:02  lr: 0.003779  min_lr: 0.003779  loss: 2.8908 (2.7417)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [62]  [100/312]  eta: 0:01:54  lr: 0.003779  min_lr: 0.003779  loss: 2.6882 (2.7346)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [62]  [110/312]  eta: 0:01:47  lr: 0.003778  min_lr: 0.003778  loss: 2.6106 (2.7296)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [62]  [120/312]  eta: 0:01:40  lr: 0.003778  min_lr: 0.003778  loss: 2.8038 (2.7272)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [62]  [130/312]  eta: 0:01:33  lr: 0.003778  min_lr: 0.003778  loss: 2.6981 (2.7096)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0004  max mem: 42573
Epoch: [62]  [140/312]  eta: 0:01:27  lr: 0.003777  min_lr: 0.003777  loss: 2.6981 (2.7153)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [62]  [150/312]  eta: 0:01:21  lr: 0.003777  min_lr: 0.003777  loss: 2.8958 (2.7257)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [62]  [160/312]  eta: 0:01:16  lr: 0.003777  min_lr: 0.003777  loss: 2.9976 (2.7307)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [62]  [170/312]  eta: 0:01:10  lr: 0.003776  min_lr: 0.003776  loss: 2.9098 (2.7449)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0004  max mem: 42573
Epoch: [62]  [180/312]  eta: 0:01:05  lr: 0.003776  min_lr: 0.003776  loss: 2.9425 (2.7523)  weight_decay: 0.0500 (0.0500)  time: 0.4341  data: 0.0004  max mem: 42573
Epoch: [62]  [190/312]  eta: 0:00:59  lr: 0.003776  min_lr: 0.003776  loss: 2.8064 (2.7457)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0003  max mem: 42573
Epoch: [62]  [200/312]  eta: 0:00:54  lr: 0.003775  min_lr: 0.003775  loss: 2.6464 (2.7413)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [62]  [210/312]  eta: 0:00:49  lr: 0.003775  min_lr: 0.003775  loss: 2.8297 (2.7486)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [62]  [220/312]  eta: 0:00:44  lr: 0.003775  min_lr: 0.003775  loss: 2.6927 (2.7373)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [62]  [230/312]  eta: 0:00:39  lr: 0.003774  min_lr: 0.003774  loss: 2.5848 (2.7364)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [62]  [240/312]  eta: 0:00:34  lr: 0.003774  min_lr: 0.003774  loss: 2.5483 (2.7247)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [62]  [250/312]  eta: 0:00:29  lr: 0.003774  min_lr: 0.003774  loss: 2.6780 (2.7283)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [62]  [260/312]  eta: 0:00:24  lr: 0.003774  min_lr: 0.003774  loss: 2.8420 (2.7311)  weight_decay: 0.0500 (0.0500)  time: 0.4384  data: 0.0004  max mem: 42573
Epoch: [62]  [270/312]  eta: 0:00:19  lr: 0.003773  min_lr: 0.003773  loss: 3.0310 (2.7297)  weight_decay: 0.0500 (0.0500)  time: 0.4384  data: 0.0004  max mem: 42573
Epoch: [62]  [280/312]  eta: 0:00:15  lr: 0.003773  min_lr: 0.003773  loss: 2.9818 (2.7281)  weight_decay: 0.0500 (0.0500)  time: 0.4343  data: 0.0009  max mem: 42573
Epoch: [62]  [290/312]  eta: 0:00:10  lr: 0.003773  min_lr: 0.003773  loss: 2.9818 (2.7321)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0008  max mem: 42573
Epoch: [62]  [300/312]  eta: 0:00:05  lr: 0.003772  min_lr: 0.003772  loss: 2.8318 (2.7328)  weight_decay: 0.0500 (0.0500)  time: 0.4325  data: 0.0001  max mem: 42573
Epoch: [62]  [310/312]  eta: 0:00:00  lr: 0.003772  min_lr: 0.003772  loss: 2.8318 (2.7325)  weight_decay: 0.0500 (0.0500)  time: 0.4324  data: 0.0001  max mem: 42573
Epoch: [62]  [311/312]  eta: 0:00:00  lr: 0.003772  min_lr: 0.003772  loss: 2.8846 (2.7331)  weight_decay: 0.0500 (0.0500)  time: 0.4324  data: 0.0001  max mem: 42573
Epoch: [62] Total time: 0:02:27 (0.4713 s / it)
Averaged stats: lr: 0.003772  min_lr: 0.003772  loss: 2.8846 (2.7485)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:00:43  loss: 0.9606 (0.9606)  acc1: 77.0833 (77.0833)  acc5: 92.9688 (92.9688)  time: 4.7992  data: 4.6897  max mem: 42573
Test:  [8/9]  eta: 0:00:00  loss: 1.4205 (1.2927)  acc1: 67.4479 (68.3520)  acc5: 88.8021 (88.7680)  time: 0.6088  data: 0.5211  max mem: 42573
Test: Total time: 0:00:05 (0.6212 s / it)
* Acc@1 69.268 Acc@5 88.712 loss 1.266
Accuracy of the model on the 50000 test images: 69.3%
Max accuracy: 69.27%
Epoch: [63]  [  0/312]  eta: 0:47:00  lr: 0.003772  min_lr: 0.003772  loss: 2.9765 (2.9765)  weight_decay: 0.0500 (0.0500)  time: 9.0416  data: 6.6461  max mem: 42573
Epoch: [63]  [ 10/312]  eta: 0:06:58  lr: 0.003771  min_lr: 0.003771  loss: 2.3213 (2.5377)  weight_decay: 0.0500 (0.0500)  time: 1.3842  data: 0.7510  max mem: 42573
Epoch: [63]  [ 20/312]  eta: 0:04:31  lr: 0.003771  min_lr: 0.003771  loss: 2.6183 (2.6328)  weight_decay: 0.0500 (0.0500)  time: 0.5259  data: 0.0809  max mem: 42573
Epoch: [63]  [ 30/312]  eta: 0:03:37  lr: 0.003771  min_lr: 0.003771  loss: 2.7618 (2.6969)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0003  max mem: 42573
Epoch: [63]  [ 40/312]  eta: 0:03:07  lr: 0.003770  min_lr: 0.003770  loss: 2.8706 (2.7408)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0003  max mem: 42573
Epoch: [63]  [ 50/312]  eta: 0:02:47  lr: 0.003770  min_lr: 0.003770  loss: 2.8817 (2.7551)  weight_decay: 0.0500 (0.0500)  time: 0.4352  data: 0.0004  max mem: 42573
Epoch: [63]  [ 60/312]  eta: 0:02:32  lr: 0.003770  min_lr: 0.003770  loss: 2.6925 (2.7148)  weight_decay: 0.0500 (0.0500)  time: 0.4352  data: 0.0004  max mem: 42573
Epoch: [63]  [ 70/312]  eta: 0:02:20  lr: 0.003769  min_lr: 0.003769  loss: 2.8037 (2.7641)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [63]  [ 80/312]  eta: 0:02:10  lr: 0.003769  min_lr: 0.003769  loss: 3.0764 (2.7868)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [63]  [ 90/312]  eta: 0:02:01  lr: 0.003769  min_lr: 0.003769  loss: 2.8832 (2.7704)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [63]  [100/312]  eta: 0:01:53  lr: 0.003768  min_lr: 0.003768  loss: 2.6947 (2.7366)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [63]  [110/312]  eta: 0:01:46  lr: 0.003768  min_lr: 0.003768  loss: 2.5464 (2.7267)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0003  max mem: 42573
Epoch: [63]  [120/312]  eta: 0:01:39  lr: 0.003768  min_lr: 0.003768  loss: 2.6948 (2.7238)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [63]  [130/312]  eta: 0:01:33  lr: 0.003767  min_lr: 0.003767  loss: 2.7815 (2.7168)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0004  max mem: 42573
Epoch: [63]  [140/312]  eta: 0:01:27  lr: 0.003767  min_lr: 0.003767  loss: 2.9600 (2.7293)  weight_decay: 0.0500 (0.0500)  time: 0.4341  data: 0.0004  max mem: 42573
Epoch: [63]  [150/312]  eta: 0:01:21  lr: 0.003767  min_lr: 0.003767  loss: 2.9822 (2.7349)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [63]  [160/312]  eta: 0:01:15  lr: 0.003766  min_lr: 0.003766  loss: 2.9015 (2.7392)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [63]  [170/312]  eta: 0:01:10  lr: 0.003766  min_lr: 0.003766  loss: 2.8083 (2.7397)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0003  max mem: 42573
Epoch: [63]  [180/312]  eta: 0:01:04  lr: 0.003766  min_lr: 0.003766  loss: 2.9046 (2.7425)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [63]  [190/312]  eta: 0:00:59  lr: 0.003765  min_lr: 0.003765  loss: 2.9282 (2.7544)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0005  max mem: 42573
Epoch: [63]  [200/312]  eta: 0:00:54  lr: 0.003765  min_lr: 0.003765  loss: 2.8598 (2.7612)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0005  max mem: 42573
Epoch: [63]  [210/312]  eta: 0:00:49  lr: 0.003765  min_lr: 0.003765  loss: 2.8402 (2.7641)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [63]  [220/312]  eta: 0:00:44  lr: 0.003764  min_lr: 0.003764  loss: 2.8287 (2.7575)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [63]  [230/312]  eta: 0:00:39  lr: 0.003764  min_lr: 0.003764  loss: 2.8204 (2.7546)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [63]  [240/312]  eta: 0:00:34  lr: 0.003764  min_lr: 0.003764  loss: 2.8120 (2.7516)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [63]  [250/312]  eta: 0:00:29  lr: 0.003763  min_lr: 0.003763  loss: 2.5984 (2.7442)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [63]  [260/312]  eta: 0:00:24  lr: 0.003763  min_lr: 0.003763  loss: 2.8115 (2.7477)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [63]  [270/312]  eta: 0:00:19  lr: 0.003763  min_lr: 0.003763  loss: 2.7712 (2.7474)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [63]  [280/312]  eta: 0:00:15  lr: 0.003762  min_lr: 0.003762  loss: 2.7712 (2.7470)  weight_decay: 0.0500 (0.0500)  time: 0.4345  data: 0.0009  max mem: 42573
Epoch: [63]  [290/312]  eta: 0:00:10  lr: 0.003762  min_lr: 0.003762  loss: 2.6327 (2.7446)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0008  max mem: 42573
Epoch: [63]  [300/312]  eta: 0:00:05  lr: 0.003762  min_lr: 0.003762  loss: 2.5275 (2.7402)  weight_decay: 0.0500 (0.0500)  time: 0.4328  data: 0.0001  max mem: 42573
Epoch: [63]  [310/312]  eta: 0:00:00  lr: 0.003761  min_lr: 0.003761  loss: 2.7219 (2.7427)  weight_decay: 0.0500 (0.0500)  time: 0.4327  data: 0.0001  max mem: 42573
Epoch: [63]  [311/312]  eta: 0:00:00  lr: 0.003761  min_lr: 0.003761  loss: 2.7640 (2.7433)  weight_decay: 0.0500 (0.0500)  time: 0.4327  data: 0.0001  max mem: 42573
Epoch: [63] Total time: 0:02:26 (0.4703 s / it)
Averaged stats: lr: 0.003761  min_lr: 0.003761  loss: 2.7640 (2.7511)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:00:43  loss: 1.0402 (1.0402)  acc1: 74.4792 (74.4792)  acc5: 92.9688 (92.9688)  time: 4.7892  data: 4.6797  max mem: 42573
Test:  [8/9]  eta: 0:00:00  loss: 1.4596 (1.3251)  acc1: 65.1042 (66.2720)  acc5: 89.3229 (88.8320)  time: 0.6078  data: 0.5200  max mem: 42573
Test: Total time: 0:00:05 (0.6263 s / it)
* Acc@1 67.720 Acc@5 87.842 loss 1.337
Accuracy of the model on the 50000 test images: 67.7%
Max accuracy: 69.27%
Epoch: [64]  [  0/312]  eta: 0:47:00  lr: 0.003761  min_lr: 0.003761  loss: 2.9026 (2.9026)  weight_decay: 0.0500 (0.0500)  time: 9.0414  data: 7.5091  max mem: 42573
Epoch: [64]  [ 10/312]  eta: 0:07:21  lr: 0.003761  min_lr: 0.003761  loss: 2.9225 (2.8317)  weight_decay: 0.0500 (0.0500)  time: 1.4618  data: 0.6886  max mem: 42573
Epoch: [64]  [ 20/312]  eta: 0:04:43  lr: 0.003761  min_lr: 0.003761  loss: 2.9225 (2.8197)  weight_decay: 0.0500 (0.0500)  time: 0.5688  data: 0.0035  max mem: 42573
Epoch: [64]  [ 30/312]  eta: 0:03:45  lr: 0.003760  min_lr: 0.003760  loss: 2.6641 (2.7347)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [64]  [ 40/312]  eta: 0:03:13  lr: 0.003760  min_lr: 0.003760  loss: 2.6049 (2.7067)  weight_decay: 0.0500 (0.0500)  time: 0.4387  data: 0.0003  max mem: 42573
Epoch: [64]  [ 50/312]  eta: 0:02:52  lr: 0.003760  min_lr: 0.003760  loss: 2.4182 (2.6437)  weight_decay: 0.0500 (0.0500)  time: 0.4389  data: 0.0003  max mem: 42573
Epoch: [64]  [ 60/312]  eta: 0:02:36  lr: 0.003759  min_lr: 0.003759  loss: 2.6218 (2.6722)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0003  max mem: 42573
Epoch: [64]  [ 70/312]  eta: 0:02:23  lr: 0.003759  min_lr: 0.003759  loss: 2.9397 (2.6984)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0003  max mem: 42573
Epoch: [64]  [ 80/312]  eta: 0:02:13  lr: 0.003759  min_lr: 0.003759  loss: 2.9397 (2.7398)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [64]  [ 90/312]  eta: 0:02:04  lr: 0.003758  min_lr: 0.003758  loss: 2.8856 (2.7359)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [64]  [100/312]  eta: 0:01:55  lr: 0.003758  min_lr: 0.003758  loss: 2.7697 (2.7517)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [64]  [110/312]  eta: 0:01:48  lr: 0.003757  min_lr: 0.003757  loss: 2.9031 (2.7587)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [64]  [120/312]  eta: 0:01:41  lr: 0.003757  min_lr: 0.003757  loss: 2.9155 (2.7638)  weight_decay: 0.0500 (0.0500)  time: 0.4341  data: 0.0003  max mem: 42573
Epoch: [64]  [130/312]  eta: 0:01:34  lr: 0.003757  min_lr: 0.003757  loss: 2.9117 (2.7731)  weight_decay: 0.0500 (0.0500)  time: 0.4342  data: 0.0004  max mem: 42573
Epoch: [64]  [140/312]  eta: 0:01:28  lr: 0.003756  min_lr: 0.003756  loss: 2.9123 (2.7836)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0004  max mem: 42573
Epoch: [64]  [150/312]  eta: 0:01:22  lr: 0.003756  min_lr: 0.003756  loss: 2.9587 (2.7795)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [64]  [160/312]  eta: 0:01:16  lr: 0.003756  min_lr: 0.003756  loss: 2.7377 (2.7726)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [64]  [170/312]  eta: 0:01:11  lr: 0.003755  min_lr: 0.003755  loss: 2.7377 (2.7676)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [64]  [180/312]  eta: 0:01:05  lr: 0.003755  min_lr: 0.003755  loss: 2.9267 (2.7673)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [64]  [190/312]  eta: 0:01:00  lr: 0.003755  min_lr: 0.003755  loss: 2.9267 (2.7718)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [64]  [200/312]  eta: 0:00:54  lr: 0.003754  min_lr: 0.003754  loss: 2.8715 (2.7739)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [64]  [210/312]  eta: 0:00:49  lr: 0.003754  min_lr: 0.003754  loss: 2.8595 (2.7709)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [64]  [220/312]  eta: 0:00:44  lr: 0.003754  min_lr: 0.003754  loss: 2.8155 (2.7708)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [64]  [230/312]  eta: 0:00:39  lr: 0.003753  min_lr: 0.003753  loss: 2.8225 (2.7773)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [64]  [240/312]  eta: 0:00:34  lr: 0.003753  min_lr: 0.003753  loss: 2.8516 (2.7717)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [64]  [250/312]  eta: 0:00:29  lr: 0.003753  min_lr: 0.003753  loss: 2.7353 (2.7722)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [64]  [260/312]  eta: 0:00:24  lr: 0.003752  min_lr: 0.003752  loss: 2.7802 (2.7727)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [64]  [270/312]  eta: 0:00:19  lr: 0.003752  min_lr: 0.003752  loss: 2.7579 (2.7722)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0003  max mem: 42573
Epoch: [64]  [280/312]  eta: 0:00:15  lr: 0.003752  min_lr: 0.003752  loss: 2.6884 (2.7731)  weight_decay: 0.0500 (0.0500)  time: 0.4344  data: 0.0011  max mem: 42573
Epoch: [64]  [290/312]  eta: 0:00:10  lr: 0.003751  min_lr: 0.003751  loss: 2.9090 (2.7742)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0010  max mem: 42573
Epoch: [64]  [300/312]  eta: 0:00:05  lr: 0.003751  min_lr: 0.003751  loss: 2.8708 (2.7700)  weight_decay: 0.0500 (0.0500)  time: 0.4355  data: 0.0001  max mem: 42573
Epoch: [64]  [310/312]  eta: 0:00:00  lr: 0.003751  min_lr: 0.003751  loss: 2.6665 (2.7651)  weight_decay: 0.0500 (0.0500)  time: 0.4355  data: 0.0001  max mem: 42573
Epoch: [64]  [311/312]  eta: 0:00:00  lr: 0.003751  min_lr: 0.003751  loss: 2.6665 (2.7636)  weight_decay: 0.0500 (0.0500)  time: 0.4355  data: 0.0001  max mem: 42573
Epoch: [64] Total time: 0:02:27 (0.4736 s / it)
Averaged stats: lr: 0.003751  min_lr: 0.003751  loss: 2.6665 (2.7377)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:00:40  loss: 1.2153 (1.2153)  acc1: 72.1354 (72.1354)  acc5: 90.6250 (90.6250)  time: 4.5391  data: 4.4295  max mem: 42573
Test:  [8/9]  eta: 0:00:00  loss: 1.5401 (1.4074)  acc1: 66.4062 (66.1120)  acc5: 88.5417 (88.2880)  time: 0.5813  data: 0.4922  max mem: 42573
Test: Total time: 0:00:05 (0.5913 s / it)
* Acc@1 66.770 Acc@5 87.418 loss 1.430
Accuracy of the model on the 50000 test images: 66.8%
Max accuracy: 69.27%
Epoch: [65]  [  0/312]  eta: 0:50:24  lr: 0.003751  min_lr: 0.003751  loss: 2.2275 (2.2275)  weight_decay: 0.0500 (0.0500)  time: 9.6947  data: 8.3038  max mem: 42573
Epoch: [65]  [ 10/312]  eta: 0:06:59  lr: 0.003750  min_lr: 0.003750  loss: 2.7976 (2.6361)  weight_decay: 0.0500 (0.0500)  time: 1.3894  data: 0.7553  max mem: 42573
Epoch: [65]  [ 20/312]  eta: 0:04:32  lr: 0.003750  min_lr: 0.003750  loss: 2.7976 (2.6733)  weight_decay: 0.0500 (0.0500)  time: 0.4963  data: 0.0004  max mem: 42573
Epoch: [65]  [ 30/312]  eta: 0:03:37  lr: 0.003749  min_lr: 0.003749  loss: 2.7982 (2.6955)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0003  max mem: 42573
Epoch: [65]  [ 40/312]  eta: 0:03:07  lr: 0.003749  min_lr: 0.003749  loss: 2.7982 (2.7177)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0003  max mem: 42573
Epoch: [65]  [ 50/312]  eta: 0:02:47  lr: 0.003749  min_lr: 0.003749  loss: 2.9251 (2.7484)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [65]  [ 60/312]  eta: 0:02:32  lr: 0.003748  min_lr: 0.003748  loss: 2.6956 (2.7101)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [65]  [ 70/312]  eta: 0:02:20  lr: 0.003748  min_lr: 0.003748  loss: 2.6240 (2.7436)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [65]  [ 80/312]  eta: 0:02:10  lr: 0.003748  min_lr: 0.003748  loss: 2.8748 (2.7487)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0003  max mem: 42573
Epoch: [65]  [ 90/312]  eta: 0:02:01  lr: 0.003747  min_lr: 0.003747  loss: 2.7901 (2.7452)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [65]  [100/312]  eta: 0:01:53  lr: 0.003747  min_lr: 0.003747  loss: 2.7490 (2.7299)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [65]  [110/312]  eta: 0:01:46  lr: 0.003747  min_lr: 0.003747  loss: 2.8820 (2.7464)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [65]  [120/312]  eta: 0:01:39  lr: 0.003746  min_lr: 0.003746  loss: 2.8618 (2.7298)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0004  max mem: 42573
Epoch: [65]  [130/312]  eta: 0:01:33  lr: 0.003746  min_lr: 0.003746  loss: 2.5454 (2.7279)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [65]  [140/312]  eta: 0:01:27  lr: 0.003746  min_lr: 0.003746  loss: 2.5454 (2.7183)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [65]  [150/312]  eta: 0:01:21  lr: 0.003745  min_lr: 0.003745  loss: 2.6993 (2.7132)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [65]  [160/312]  eta: 0:01:15  lr: 0.003745  min_lr: 0.003745  loss: 2.6006 (2.7038)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [65]  [170/312]  eta: 0:01:10  lr: 0.003745  min_lr: 0.003745  loss: 2.6006 (2.6961)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [65]  [180/312]  eta: 0:01:04  lr: 0.003744  min_lr: 0.003744  loss: 2.8289 (2.7014)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [65]  [190/312]  eta: 0:00:59  lr: 0.003744  min_lr: 0.003744  loss: 2.8842 (2.6987)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [65]  [200/312]  eta: 0:00:54  lr: 0.003744  min_lr: 0.003744  loss: 2.6541 (2.6972)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [65]  [210/312]  eta: 0:00:49  lr: 0.003743  min_lr: 0.003743  loss: 2.7802 (2.7039)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [65]  [220/312]  eta: 0:00:44  lr: 0.003743  min_lr: 0.003743  loss: 2.7802 (2.7042)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [65]  [230/312]  eta: 0:00:39  lr: 0.003742  min_lr: 0.003742  loss: 2.9326 (2.7135)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [65]  [240/312]  eta: 0:00:34  lr: 0.003742  min_lr: 0.003742  loss: 2.9326 (2.7177)  weight_decay: 0.0500 (0.0500)  time: 0.4366  data: 0.0004  max mem: 42573
Epoch: [65]  [250/312]  eta: 0:00:29  lr: 0.003742  min_lr: 0.003742  loss: 2.6464 (2.7155)  weight_decay: 0.0500 (0.0500)  time: 0.4366  data: 0.0004  max mem: 42573
Epoch: [65]  [260/312]  eta: 0:00:24  lr: 0.003741  min_lr: 0.003741  loss: 2.7213 (2.7205)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [65]  [270/312]  eta: 0:00:19  lr: 0.003741  min_lr: 0.003741  loss: 2.7751 (2.7221)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [65]  [280/312]  eta: 0:00:15  lr: 0.003741  min_lr: 0.003741  loss: 2.7751 (2.7289)  weight_decay: 0.0500 (0.0500)  time: 0.4347  data: 0.0010  max mem: 42573
Epoch: [65]  [290/312]  eta: 0:00:10  lr: 0.003740  min_lr: 0.003740  loss: 2.6929 (2.7261)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0008  max mem: 42573
Epoch: [65]  [300/312]  eta: 0:00:05  lr: 0.003740  min_lr: 0.003740  loss: 2.8202 (2.7301)  weight_decay: 0.0500 (0.0500)  time: 0.4324  data: 0.0001  max mem: 42573
Epoch: [65]  [310/312]  eta: 0:00:00  lr: 0.003740  min_lr: 0.003740  loss: 2.7915 (2.7284)  weight_decay: 0.0500 (0.0500)  time: 0.4324  data: 0.0001  max mem: 42573
Epoch: [65]  [311/312]  eta: 0:00:00  lr: 0.003740  min_lr: 0.003740  loss: 2.7884 (2.7276)  weight_decay: 0.0500 (0.0500)  time: 0.4324  data: 0.0001  max mem: 42573
Epoch: [65] Total time: 0:02:26 (0.4706 s / it)
Averaged stats: lr: 0.003740  min_lr: 0.003740  loss: 2.7884 (2.7276)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:00:43  loss: 0.9967 (0.9967)  acc1: 75.5208 (75.5208)  acc5: 91.9271 (91.9271)  time: 4.8052  data: 4.6958  max mem: 42573
Test:  [8/9]  eta: 0:00:00  loss: 1.3812 (1.2986)  acc1: 66.9271 (67.4880)  acc5: 86.9792 (87.6480)  time: 0.6107  data: 0.5218  max mem: 42573
Test: Total time: 0:00:05 (0.6214 s / it)
* Acc@1 68.148 Acc@5 88.240 loss 1.286
Accuracy of the model on the 50000 test images: 68.1%
Max accuracy: 69.27%
Epoch: [66]  [  0/312]  eta: 0:48:04  lr: 0.003740  min_lr: 0.003740  loss: 2.5443 (2.5443)  weight_decay: 0.0500 (0.0500)  time: 9.2439  data: 7.7955  max mem: 42573
Epoch: [66]  [ 10/312]  eta: 0:07:05  lr: 0.003739  min_lr: 0.003739  loss: 2.6201 (2.6729)  weight_decay: 0.0500 (0.0500)  time: 1.4101  data: 0.7091  max mem: 42573
Epoch: [66]  [ 20/312]  eta: 0:04:35  lr: 0.003739  min_lr: 0.003739  loss: 2.6201 (2.6100)  weight_decay: 0.0500 (0.0500)  time: 0.5300  data: 0.0004  max mem: 42573
Epoch: [66]  [ 30/312]  eta: 0:03:39  lr: 0.003738  min_lr: 0.003738  loss: 2.5493 (2.6008)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0003  max mem: 42573
Epoch: [66]  [ 40/312]  eta: 0:03:09  lr: 0.003738  min_lr: 0.003738  loss: 2.5985 (2.6204)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [66]  [ 50/312]  eta: 0:02:48  lr: 0.003738  min_lr: 0.003738  loss: 2.8439 (2.6553)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [66]  [ 60/312]  eta: 0:02:33  lr: 0.003737  min_lr: 0.003737  loss: 2.8746 (2.6604)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [66]  [ 70/312]  eta: 0:02:21  lr: 0.003737  min_lr: 0.003737  loss: 2.8801 (2.7027)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [66]  [ 80/312]  eta: 0:02:11  lr: 0.003737  min_lr: 0.003737  loss: 2.9378 (2.7212)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0005  max mem: 42573
Epoch: [66]  [ 90/312]  eta: 0:02:02  lr: 0.003736  min_lr: 0.003736  loss: 2.8424 (2.7181)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0005  max mem: 42573
Epoch: [66]  [100/312]  eta: 0:01:54  lr: 0.003736  min_lr: 0.003736  loss: 2.8424 (2.7232)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [66]  [110/312]  eta: 0:01:47  lr: 0.003736  min_lr: 0.003736  loss: 2.8531 (2.7397)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [66]  [120/312]  eta: 0:01:40  lr: 0.003735  min_lr: 0.003735  loss: 2.7315 (2.7329)  weight_decay: 0.0500 (0.0500)  time: 0.4347  data: 0.0004  max mem: 42573
Epoch: [66]  [130/312]  eta: 0:01:33  lr: 0.003735  min_lr: 0.003735  loss: 2.8265 (2.7582)  weight_decay: 0.0500 (0.0500)  time: 0.4347  data: 0.0003  max mem: 42573
Epoch: [66]  [140/312]  eta: 0:01:27  lr: 0.003735  min_lr: 0.003735  loss: 3.0191 (2.7550)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0004  max mem: 42573
Epoch: [66]  [150/312]  eta: 0:01:21  lr: 0.003734  min_lr: 0.003734  loss: 2.5582 (2.7369)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0004  max mem: 42573
Epoch: [66]  [160/312]  eta: 0:01:16  lr: 0.003734  min_lr: 0.003734  loss: 2.5963 (2.7355)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0004  max mem: 42573
Epoch: [66]  [170/312]  eta: 0:01:10  lr: 0.003733  min_lr: 0.003733  loss: 2.6821 (2.7320)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [66]  [180/312]  eta: 0:01:05  lr: 0.003733  min_lr: 0.003733  loss: 2.6866 (2.7305)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [66]  [190/312]  eta: 0:00:59  lr: 0.003733  min_lr: 0.003733  loss: 2.6866 (2.7342)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [66]  [200/312]  eta: 0:00:54  lr: 0.003732  min_lr: 0.003732  loss: 2.8098 (2.7297)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [66]  [210/312]  eta: 0:00:49  lr: 0.003732  min_lr: 0.003732  loss: 2.7929 (2.7239)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [66]  [220/312]  eta: 0:00:44  lr: 0.003732  min_lr: 0.003732  loss: 2.5451 (2.7158)  weight_decay: 0.0500 (0.0500)  time: 0.4406  data: 0.0004  max mem: 42573
Epoch: [66]  [230/312]  eta: 0:00:39  lr: 0.003731  min_lr: 0.003731  loss: 2.5451 (2.7155)  weight_decay: 0.0500 (0.0500)  time: 0.4406  data: 0.0004  max mem: 42573
Epoch: [66]  [240/312]  eta: 0:00:34  lr: 0.003731  min_lr: 0.003731  loss: 2.7223 (2.7125)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [66]  [250/312]  eta: 0:00:29  lr: 0.003731  min_lr: 0.003731  loss: 2.7575 (2.7137)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [66]  [260/312]  eta: 0:00:24  lr: 0.003730  min_lr: 0.003730  loss: 2.7239 (2.7127)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [66]  [270/312]  eta: 0:00:19  lr: 0.003730  min_lr: 0.003730  loss: 2.7239 (2.7105)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [66]  [280/312]  eta: 0:00:15  lr: 0.003730  min_lr: 0.003730  loss: 2.8339 (2.7154)  weight_decay: 0.0500 (0.0500)  time: 0.4347  data: 0.0009  max mem: 42573
Epoch: [66]  [290/312]  eta: 0:00:10  lr: 0.003729  min_lr: 0.003729  loss: 2.8553 (2.7110)  weight_decay: 0.0500 (0.0500)  time: 0.4341  data: 0.0008  max mem: 42573
Epoch: [66]  [300/312]  eta: 0:00:05  lr: 0.003729  min_lr: 0.003729  loss: 2.5585 (2.7085)  weight_decay: 0.0500 (0.0500)  time: 0.4350  data: 0.0001  max mem: 42573
Epoch: [66]  [310/312]  eta: 0:00:00  lr: 0.003728  min_lr: 0.003728  loss: 2.7957 (2.7103)  weight_decay: 0.0500 (0.0500)  time: 0.4348  data: 0.0001  max mem: 42573
Epoch: [66]  [311/312]  eta: 0:00:00  lr: 0.003728  min_lr: 0.003728  loss: 2.8173 (2.7116)  weight_decay: 0.0500 (0.0500)  time: 0.4349  data: 0.0001  max mem: 42573
Epoch: [66] Total time: 0:02:27 (0.4718 s / it)
Averaged stats: lr: 0.003728  min_lr: 0.003728  loss: 2.8173 (2.7253)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:00:50  loss: 1.1549 (1.1549)  acc1: 75.0000 (75.0000)  acc5: 90.8854 (90.8854)  time: 5.6191  data: 5.5096  max mem: 42573
Test:  [8/9]  eta: 0:00:00  loss: 1.6188 (1.5037)  acc1: 61.7188 (64.6400)  acc5: 85.6771 (86.3360)  time: 0.6999  data: 0.6123  max mem: 42573
Test: Total time: 0:00:06 (0.7224 s / it)
* Acc@1 65.610 Acc@5 86.848 loss 1.476
Accuracy of the model on the 50000 test images: 65.6%
Max accuracy: 69.27%
Epoch: [67]  [  0/312]  eta: 0:47:56  lr: 0.003728  min_lr: 0.003728  loss: 3.1932 (3.1932)  weight_decay: 0.0500 (0.0500)  time: 9.2198  data: 7.0176  max mem: 42573
Epoch: [67]  [ 10/312]  eta: 0:07:06  lr: 0.003728  min_lr: 0.003728  loss: 2.9061 (2.7889)  weight_decay: 0.0500 (0.0500)  time: 1.4132  data: 0.7300  max mem: 42573
Epoch: [67]  [ 20/312]  eta: 0:04:36  lr: 0.003728  min_lr: 0.003728  loss: 2.8503 (2.7905)  weight_decay: 0.0500 (0.0500)  time: 0.5328  data: 0.0508  max mem: 42573
Epoch: [67]  [ 30/312]  eta: 0:03:40  lr: 0.003727  min_lr: 0.003727  loss: 2.7953 (2.7422)  weight_decay: 0.0500 (0.0500)  time: 0.4331  data: 0.0004  max mem: 42573
Epoch: [67]  [ 40/312]  eta: 0:03:09  lr: 0.003727  min_lr: 0.003727  loss: 2.7333 (2.7188)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [67]  [ 50/312]  eta: 0:02:48  lr: 0.003727  min_lr: 0.003727  loss: 2.7333 (2.7198)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [67]  [ 60/312]  eta: 0:02:33  lr: 0.003726  min_lr: 0.003726  loss: 2.7618 (2.7551)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [67]  [ 70/312]  eta: 0:02:21  lr: 0.003726  min_lr: 0.003726  loss: 2.4897 (2.7018)  weight_decay: 0.0500 (0.0500)  time: 0.4343  data: 0.0004  max mem: 42573
Epoch: [67]  [ 80/312]  eta: 0:02:11  lr: 0.003725  min_lr: 0.003725  loss: 2.3039 (2.6699)  weight_decay: 0.0500 (0.0500)  time: 0.4342  data: 0.0003  max mem: 42573
Epoch: [67]  [ 90/312]  eta: 0:02:02  lr: 0.003725  min_lr: 0.003725  loss: 2.4951 (2.6937)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0003  max mem: 42573
Epoch: [67]  [100/312]  eta: 0:01:54  lr: 0.003725  min_lr: 0.003725  loss: 2.8119 (2.6959)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0003  max mem: 42573
Epoch: [67]  [110/312]  eta: 0:01:47  lr: 0.003724  min_lr: 0.003724  loss: 2.7941 (2.7067)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0003  max mem: 42573
Epoch: [67]  [120/312]  eta: 0:01:40  lr: 0.003724  min_lr: 0.003724  loss: 2.7941 (2.7047)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [67]  [130/312]  eta: 0:01:33  lr: 0.003724  min_lr: 0.003724  loss: 2.5503 (2.6917)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [67]  [140/312]  eta: 0:01:27  lr: 0.003723  min_lr: 0.003723  loss: 2.7407 (2.6989)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [67]  [150/312]  eta: 0:01:21  lr: 0.003723  min_lr: 0.003723  loss: 2.9110 (2.7123)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0005  max mem: 42573
Epoch: [67]  [160/312]  eta: 0:01:16  lr: 0.003723  min_lr: 0.003723  loss: 2.7048 (2.7023)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [67]  [170/312]  eta: 0:01:10  lr: 0.003722  min_lr: 0.003722  loss: 2.5676 (2.6984)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [67]  [180/312]  eta: 0:01:05  lr: 0.003722  min_lr: 0.003722  loss: 2.7597 (2.7047)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [67]  [190/312]  eta: 0:00:59  lr: 0.003721  min_lr: 0.003721  loss: 2.8210 (2.7078)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [67]  [200/312]  eta: 0:00:54  lr: 0.003721  min_lr: 0.003721  loss: 2.8817 (2.7121)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [67]  [210/312]  eta: 0:00:49  lr: 0.003721  min_lr: 0.003721  loss: 2.8842 (2.7163)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0004  max mem: 42573
Epoch: [67]  [220/312]  eta: 0:00:44  lr: 0.003720  min_lr: 0.003720  loss: 2.7541 (2.7125)  weight_decay: 0.0500 (0.0500)  time: 0.4341  data: 0.0004  max mem: 42573
Epoch: [67]  [230/312]  eta: 0:00:39  lr: 0.003720  min_lr: 0.003720  loss: 2.7836 (2.7153)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [67]  [240/312]  eta: 0:00:34  lr: 0.003720  min_lr: 0.003720  loss: 2.8186 (2.7180)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [67]  [250/312]  eta: 0:00:29  lr: 0.003719  min_lr: 0.003719  loss: 2.8186 (2.7169)  weight_decay: 0.0500 (0.0500)  time: 0.4341  data: 0.0004  max mem: 42573
Epoch: [67]  [260/312]  eta: 0:00:24  lr: 0.003719  min_lr: 0.003719  loss: 3.0249 (2.7293)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [67]  [270/312]  eta: 0:00:19  lr: 0.003719  min_lr: 0.003719  loss: 3.0375 (2.7308)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [67]  [280/312]  eta: 0:00:15  lr: 0.003718  min_lr: 0.003718  loss: 2.5788 (2.7258)  weight_decay: 0.0500 (0.0500)  time: 0.4345  data: 0.0010  max mem: 42573
Epoch: [67]  [290/312]  eta: 0:00:10  lr: 0.003718  min_lr: 0.003718  loss: 2.8805 (2.7313)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0008  max mem: 42573
Epoch: [67]  [300/312]  eta: 0:00:05  lr: 0.003717  min_lr: 0.003717  loss: 2.8805 (2.7305)  weight_decay: 0.0500 (0.0500)  time: 0.4324  data: 0.0001  max mem: 42573
Epoch: [67]  [310/312]  eta: 0:00:00  lr: 0.003717  min_lr: 0.003717  loss: 2.8737 (2.7376)  weight_decay: 0.0500 (0.0500)  time: 0.4324  data: 0.0001  max mem: 42573
Epoch: [67]  [311/312]  eta: 0:00:00  lr: 0.003717  min_lr: 0.003717  loss: 2.8737 (2.7352)  weight_decay: 0.0500 (0.0500)  time: 0.4324  data: 0.0001  max mem: 42573
Epoch: [67] Total time: 0:02:27 (0.4715 s / it)
Averaged stats: lr: 0.003717  min_lr: 0.003717  loss: 2.8737 (2.7331)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:00:44  loss: 0.9586 (0.9586)  acc1: 76.8229 (76.8229)  acc5: 91.4062 (91.4062)  time: 4.9575  data: 4.8481  max mem: 42573
Test:  [8/9]  eta: 0:00:00  loss: 1.5065 (1.3468)  acc1: 67.4479 (66.8800)  acc5: 86.4583 (87.4560)  time: 0.6264  data: 0.5387  max mem: 42573
Test: Total time: 0:00:05 (0.6436 s / it)
* Acc@1 67.232 Acc@5 87.412 loss 1.369
Accuracy of the model on the 50000 test images: 67.2%
Max accuracy: 69.27%
Epoch: [68]  [  0/312]  eta: 0:49:20  lr: 0.003717  min_lr: 0.003717  loss: 2.9499 (2.9499)  weight_decay: 0.0500 (0.0500)  time: 9.4875  data: 8.7658  max mem: 42573
Epoch: [68]  [ 10/312]  eta: 0:07:35  lr: 0.003717  min_lr: 0.003717  loss: 2.9499 (2.8681)  weight_decay: 0.0500 (0.0500)  time: 1.5089  data: 0.7973  max mem: 42573
Epoch: [68]  [ 20/312]  eta: 0:04:50  lr: 0.003716  min_lr: 0.003716  loss: 2.8794 (2.8940)  weight_decay: 0.0500 (0.0500)  time: 0.5720  data: 0.0004  max mem: 42573
Epoch: [68]  [ 30/312]  eta: 0:03:49  lr: 0.003716  min_lr: 0.003716  loss: 2.8295 (2.8718)  weight_decay: 0.0500 (0.0500)  time: 0.4331  data: 0.0004  max mem: 42573
Epoch: [68]  [ 40/312]  eta: 0:03:16  lr: 0.003715  min_lr: 0.003715  loss: 2.8295 (2.8201)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [68]  [ 50/312]  eta: 0:02:54  lr: 0.003715  min_lr: 0.003715  loss: 2.6281 (2.7882)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [68]  [ 60/312]  eta: 0:02:38  lr: 0.003715  min_lr: 0.003715  loss: 2.8577 (2.8069)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [68]  [ 70/312]  eta: 0:02:25  lr: 0.003714  min_lr: 0.003714  loss: 2.9371 (2.8056)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [68]  [ 80/312]  eta: 0:02:14  lr: 0.003714  min_lr: 0.003714  loss: 2.6051 (2.7761)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [68]  [ 90/312]  eta: 0:02:05  lr: 0.003714  min_lr: 0.003714  loss: 2.7205 (2.7834)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [68]  [100/312]  eta: 0:01:56  lr: 0.003713  min_lr: 0.003713  loss: 2.7555 (2.7774)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [68]  [110/312]  eta: 0:01:49  lr: 0.003713  min_lr: 0.003713  loss: 2.8122 (2.7787)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [68]  [120/312]  eta: 0:01:42  lr: 0.003713  min_lr: 0.003713  loss: 2.8887 (2.7734)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [68]  [130/312]  eta: 0:01:35  lr: 0.003712  min_lr: 0.003712  loss: 2.8528 (2.7648)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [68]  [140/312]  eta: 0:01:29  lr: 0.003712  min_lr: 0.003712  loss: 2.7495 (2.7613)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [68]  [150/312]  eta: 0:01:22  lr: 0.003711  min_lr: 0.003711  loss: 2.7072 (2.7501)  weight_decay: 0.0500 (0.0500)  time: 0.4341  data: 0.0004  max mem: 42573
Epoch: [68]  [160/312]  eta: 0:01:17  lr: 0.003711  min_lr: 0.003711  loss: 2.7072 (2.7535)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0004  max mem: 42573
Epoch: [68]  [170/312]  eta: 0:01:11  lr: 0.003711  min_lr: 0.003711  loss: 2.8716 (2.7539)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [68]  [180/312]  eta: 0:01:05  lr: 0.003710  min_lr: 0.003710  loss: 2.7465 (2.7533)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0004  max mem: 42573
Epoch: [68]  [190/312]  eta: 0:01:00  lr: 0.003710  min_lr: 0.003710  loss: 2.7506 (2.7547)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0004  max mem: 42573
Epoch: [68]  [200/312]  eta: 0:00:55  lr: 0.003710  min_lr: 0.003710  loss: 2.9046 (2.7557)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [68]  [210/312]  eta: 0:00:49  lr: 0.003709  min_lr: 0.003709  loss: 2.5520 (2.7399)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [68]  [220/312]  eta: 0:00:44  lr: 0.003709  min_lr: 0.003709  loss: 2.7936 (2.7460)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [68]  [230/312]  eta: 0:00:39  lr: 0.003708  min_lr: 0.003708  loss: 2.9346 (2.7487)  weight_decay: 0.0500 (0.0500)  time: 0.4402  data: 0.0004  max mem: 42573
Epoch: [68]  [240/312]  eta: 0:00:34  lr: 0.003708  min_lr: 0.003708  loss: 2.9047 (2.7488)  weight_decay: 0.0500 (0.0500)  time: 0.4402  data: 0.0004  max mem: 42573
Epoch: [68]  [250/312]  eta: 0:00:29  lr: 0.003708  min_lr: 0.003708  loss: 2.8701 (2.7564)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [68]  [260/312]  eta: 0:00:24  lr: 0.003707  min_lr: 0.003707  loss: 2.8546 (2.7520)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [68]  [270/312]  eta: 0:00:20  lr: 0.003707  min_lr: 0.003707  loss: 2.7650 (2.7475)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [68]  [280/312]  eta: 0:00:15  lr: 0.003707  min_lr: 0.003707  loss: 2.6982 (2.7456)  weight_decay: 0.0500 (0.0500)  time: 0.4349  data: 0.0009  max mem: 42573
Epoch: [68]  [290/312]  eta: 0:00:10  lr: 0.003706  min_lr: 0.003706  loss: 2.5850 (2.7425)  weight_decay: 0.0500 (0.0500)  time: 0.4343  data: 0.0008  max mem: 42573
Epoch: [68]  [300/312]  eta: 0:00:05  lr: 0.003706  min_lr: 0.003706  loss: 2.6685 (2.7450)  weight_decay: 0.0500 (0.0500)  time: 0.4325  data: 0.0001  max mem: 42573
Epoch: [68]  [310/312]  eta: 0:00:00  lr: 0.003705  min_lr: 0.003705  loss: 2.6685 (2.7423)  weight_decay: 0.0500 (0.0500)  time: 0.4323  data: 0.0001  max mem: 42573
Epoch: [68]  [311/312]  eta: 0:00:00  lr: 0.003705  min_lr: 0.003705  loss: 2.6685 (2.7434)  weight_decay: 0.0500 (0.0500)  time: 0.4323  data: 0.0001  max mem: 42573
Epoch: [68] Total time: 0:02:28 (0.4749 s / it)
Averaged stats: lr: 0.003705  min_lr: 0.003705  loss: 2.6685 (2.7237)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:00:42  loss: 1.0790 (1.0790)  acc1: 75.0000 (75.0000)  acc5: 91.6667 (91.6667)  time: 4.7372  data: 4.6291  max mem: 42573
Test:  [8/9]  eta: 0:00:00  loss: 1.4413 (1.3312)  acc1: 65.3646 (67.4240)  acc5: 87.5000 (87.7120)  time: 0.6021  data: 0.5144  max mem: 42573
Test: Total time: 0:00:05 (0.6351 s / it)
* Acc@1 67.800 Acc@5 87.930 loss 1.346
Accuracy of the model on the 50000 test images: 67.8%
Max accuracy: 69.27%
Epoch: [69]  [  0/312]  eta: 0:50:31  lr: 0.003705  min_lr: 0.003705  loss: 2.5047 (2.5047)  weight_decay: 0.0500 (0.0500)  time: 9.7179  data: 6.8148  max mem: 42573
Epoch: [69]  [ 10/312]  eta: 0:07:21  lr: 0.003705  min_lr: 0.003705  loss: 2.5047 (2.6056)  weight_decay: 0.0500 (0.0500)  time: 1.4635  data: 0.6630  max mem: 42573
Epoch: [69]  [ 20/312]  eta: 0:04:44  lr: 0.003705  min_lr: 0.003705  loss: 2.8143 (2.7447)  weight_decay: 0.0500 (0.0500)  time: 0.5355  data: 0.0241  max mem: 42573
Epoch: [69]  [ 30/312]  eta: 0:03:45  lr: 0.003704  min_lr: 0.003704  loss: 2.8384 (2.7052)  weight_decay: 0.0500 (0.0500)  time: 0.4331  data: 0.0004  max mem: 42573
Epoch: [69]  [ 40/312]  eta: 0:03:13  lr: 0.003704  min_lr: 0.003704  loss: 2.5159 (2.6445)  weight_decay: 0.0500 (0.0500)  time: 0.4332  data: 0.0004  max mem: 42573
Epoch: [69]  [ 50/312]  eta: 0:02:51  lr: 0.003703  min_lr: 0.003703  loss: 2.7621 (2.6776)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0005  max mem: 42573
Epoch: [69]  [ 60/312]  eta: 0:02:36  lr: 0.003703  min_lr: 0.003703  loss: 2.7621 (2.6682)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [69]  [ 70/312]  eta: 0:02:23  lr: 0.003703  min_lr: 0.003703  loss: 2.6995 (2.6518)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [69]  [ 80/312]  eta: 0:02:13  lr: 0.003702  min_lr: 0.003702  loss: 2.6184 (2.6531)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0004  max mem: 42573
Epoch: [69]  [ 90/312]  eta: 0:02:03  lr: 0.003702  min_lr: 0.003702  loss: 2.6907 (2.6627)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [69]  [100/312]  eta: 0:01:55  lr: 0.003702  min_lr: 0.003702  loss: 2.7976 (2.6768)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [69]  [110/312]  eta: 0:01:48  lr: 0.003701  min_lr: 0.003701  loss: 2.7976 (2.6713)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0003  max mem: 42573
Epoch: [69]  [120/312]  eta: 0:01:41  lr: 0.003701  min_lr: 0.003701  loss: 2.6101 (2.6539)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0003  max mem: 42573
Epoch: [69]  [130/312]  eta: 0:01:34  lr: 0.003700  min_lr: 0.003700  loss: 2.6101 (2.6554)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [69]  [140/312]  eta: 0:01:28  lr: 0.003700  min_lr: 0.003700  loss: 2.7511 (2.6659)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0003  max mem: 42573
Epoch: [69]  [150/312]  eta: 0:01:22  lr: 0.003700  min_lr: 0.003700  loss: 2.7027 (2.6656)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [69]  [160/312]  eta: 0:01:16  lr: 0.003699  min_lr: 0.003699  loss: 2.7291 (2.6701)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [69]  [170/312]  eta: 0:01:10  lr: 0.003699  min_lr: 0.003699  loss: 2.7579 (2.6660)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [69]  [180/312]  eta: 0:01:05  lr: 0.003699  min_lr: 0.003699  loss: 2.6828 (2.6634)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [69]  [190/312]  eta: 0:01:00  lr: 0.003698  min_lr: 0.003698  loss: 2.8473 (2.6681)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [69]  [200/312]  eta: 0:00:54  lr: 0.003698  min_lr: 0.003698  loss: 2.8206 (2.6659)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0004  max mem: 42573
Epoch: [69]  [210/312]  eta: 0:00:49  lr: 0.003697  min_lr: 0.003697  loss: 2.6329 (2.6655)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [69]  [220/312]  eta: 0:00:44  lr: 0.003697  min_lr: 0.003697  loss: 2.5758 (2.6571)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [69]  [230/312]  eta: 0:00:39  lr: 0.003697  min_lr: 0.003697  loss: 2.5959 (2.6565)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [69]  [240/312]  eta: 0:00:34  lr: 0.003696  min_lr: 0.003696  loss: 2.6121 (2.6562)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [69]  [250/312]  eta: 0:00:29  lr: 0.003696  min_lr: 0.003696  loss: 2.8834 (2.6667)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [69]  [260/312]  eta: 0:00:24  lr: 0.003696  min_lr: 0.003696  loss: 2.9080 (2.6686)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [69]  [270/312]  eta: 0:00:19  lr: 0.003695  min_lr: 0.003695  loss: 2.7757 (2.6654)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0003  max mem: 42573
Epoch: [69]  [280/312]  eta: 0:00:15  lr: 0.003695  min_lr: 0.003695  loss: 2.7757 (2.6666)  weight_decay: 0.0500 (0.0500)  time: 0.4344  data: 0.0009  max mem: 42573
Epoch: [69]  [290/312]  eta: 0:00:10  lr: 0.003694  min_lr: 0.003694  loss: 2.8416 (2.6774)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0008  max mem: 42573
Epoch: [69]  [300/312]  eta: 0:00:05  lr: 0.003694  min_lr: 0.003694  loss: 3.0374 (2.6813)  weight_decay: 0.0500 (0.0500)  time: 0.4324  data: 0.0001  max mem: 42573
Epoch: [69]  [310/312]  eta: 0:00:00  lr: 0.003694  min_lr: 0.003694  loss: 2.8498 (2.6854)  weight_decay: 0.0500 (0.0500)  time: 0.4323  data: 0.0001  max mem: 42573
Epoch: [69]  [311/312]  eta: 0:00:00  lr: 0.003694  min_lr: 0.003694  loss: 2.8498 (2.6874)  weight_decay: 0.0500 (0.0500)  time: 0.4323  data: 0.0001  max mem: 42573
Epoch: [69] Total time: 0:02:27 (0.4729 s / it)
Averaged stats: lr: 0.003694  min_lr: 0.003694  loss: 2.8498 (2.7110)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:00:43  loss: 1.0396 (1.0396)  acc1: 75.7812 (75.7812)  acc5: 90.8854 (90.8854)  time: 4.8300  data: 4.7207  max mem: 42573
Test:  [8/9]  eta: 0:00:00  loss: 1.4426 (1.3178)  acc1: 67.9688 (66.9440)  acc5: 87.5000 (87.6800)  time: 0.6125  data: 0.5246  max mem: 42573
Test: Total time: 0:00:05 (0.6376 s / it)
* Acc@1 68.090 Acc@5 88.016 loss 1.320
Accuracy of the model on the 50000 test images: 68.1%
Max accuracy: 69.27%
Epoch: [70]  [  0/312]  eta: 0:53:01  lr: 0.003694  min_lr: 0.003694  loss: 2.8260 (2.8260)  weight_decay: 0.0500 (0.0500)  time: 10.1968  data: 7.1460  max mem: 42573
Epoch: [70]  [ 10/312]  eta: 0:07:42  lr: 0.003693  min_lr: 0.003693  loss: 2.8260 (2.7053)  weight_decay: 0.0500 (0.0500)  time: 1.5314  data: 0.7682  max mem: 42573
Epoch: [70]  [ 20/312]  eta: 0:04:54  lr: 0.003693  min_lr: 0.003693  loss: 2.7153 (2.7089)  weight_decay: 0.0500 (0.0500)  time: 0.5489  data: 0.0654  max mem: 42573
Epoch: [70]  [ 30/312]  eta: 0:03:52  lr: 0.003692  min_lr: 0.003692  loss: 2.7020 (2.7255)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [70]  [ 40/312]  eta: 0:03:18  lr: 0.003692  min_lr: 0.003692  loss: 2.7035 (2.7152)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [70]  [ 50/312]  eta: 0:02:55  lr: 0.003692  min_lr: 0.003692  loss: 2.7785 (2.7187)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [70]  [ 60/312]  eta: 0:02:39  lr: 0.003691  min_lr: 0.003691  loss: 2.8042 (2.7249)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [70]  [ 70/312]  eta: 0:02:26  lr: 0.003691  min_lr: 0.003691  loss: 2.9223 (2.7494)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [70]  [ 80/312]  eta: 0:02:15  lr: 0.003690  min_lr: 0.003690  loss: 2.6822 (2.7247)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [70]  [ 90/312]  eta: 0:02:05  lr: 0.003690  min_lr: 0.003690  loss: 2.5005 (2.6963)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [70]  [100/312]  eta: 0:01:57  lr: 0.003690  min_lr: 0.003690  loss: 2.2846 (2.6519)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [70]  [110/312]  eta: 0:01:49  lr: 0.003689  min_lr: 0.003689  loss: 2.4246 (2.6615)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [70]  [120/312]  eta: 0:01:42  lr: 0.003689  min_lr: 0.003689  loss: 2.8412 (2.6723)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [70]  [130/312]  eta: 0:01:35  lr: 0.003689  min_lr: 0.003689  loss: 2.8294 (2.6800)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0005  max mem: 42573
Epoch: [70]  [140/312]  eta: 0:01:29  lr: 0.003688  min_lr: 0.003688  loss: 2.8179 (2.6898)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0005  max mem: 42573
Epoch: [70]  [150/312]  eta: 0:01:23  lr: 0.003688  min_lr: 0.003688  loss: 2.8740 (2.7007)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [70]  [160/312]  eta: 0:01:17  lr: 0.003687  min_lr: 0.003687  loss: 2.7371 (2.7013)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [70]  [170/312]  eta: 0:01:11  lr: 0.003687  min_lr: 0.003687  loss: 2.6401 (2.6913)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [70]  [180/312]  eta: 0:01:06  lr: 0.003687  min_lr: 0.003687  loss: 2.6079 (2.6958)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [70]  [190/312]  eta: 0:01:00  lr: 0.003686  min_lr: 0.003686  loss: 2.6177 (2.6970)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0003  max mem: 42573
Epoch: [70]  [200/312]  eta: 0:00:55  lr: 0.003686  min_lr: 0.003686  loss: 2.6177 (2.6905)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0003  max mem: 42573
Epoch: [70]  [210/312]  eta: 0:00:50  lr: 0.003685  min_lr: 0.003685  loss: 2.7152 (2.6901)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [70]  [220/312]  eta: 0:00:44  lr: 0.003685  min_lr: 0.003685  loss: 2.7152 (2.6891)  weight_decay: 0.0500 (0.0500)  time: 0.4381  data: 0.0004  max mem: 42573
Epoch: [70]  [230/312]  eta: 0:00:39  lr: 0.003685  min_lr: 0.003685  loss: 2.6543 (2.6858)  weight_decay: 0.0500 (0.0500)  time: 0.4379  data: 0.0004  max mem: 42573
Epoch: [70]  [240/312]  eta: 0:00:34  lr: 0.003684  min_lr: 0.003684  loss: 2.6814 (2.6881)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [70]  [250/312]  eta: 0:00:29  lr: 0.003684  min_lr: 0.003684  loss: 2.6543 (2.6796)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [70]  [260/312]  eta: 0:00:24  lr: 0.003684  min_lr: 0.003684  loss: 2.6543 (2.6831)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [70]  [270/312]  eta: 0:00:20  lr: 0.003683  min_lr: 0.003683  loss: 2.8568 (2.6855)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0003  max mem: 42573
Epoch: [70]  [280/312]  eta: 0:00:15  lr: 0.003683  min_lr: 0.003683  loss: 2.5595 (2.6792)  weight_decay: 0.0500 (0.0500)  time: 0.4346  data: 0.0009  max mem: 42573
Epoch: [70]  [290/312]  eta: 0:00:10  lr: 0.003682  min_lr: 0.003682  loss: 2.3186 (2.6748)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0008  max mem: 42573
Epoch: [70]  [300/312]  eta: 0:00:05  lr: 0.003682  min_lr: 0.003682  loss: 2.6427 (2.6731)  weight_decay: 0.0500 (0.0500)  time: 0.4325  data: 0.0001  max mem: 42573
Epoch: [70]  [310/312]  eta: 0:00:00  lr: 0.003682  min_lr: 0.003682  loss: 2.8297 (2.6793)  weight_decay: 0.0500 (0.0500)  time: 0.4322  data: 0.0001  max mem: 42573
Epoch: [70]  [311/312]  eta: 0:00:00  lr: 0.003682  min_lr: 0.003682  loss: 2.8297 (2.6800)  weight_decay: 0.0500 (0.0500)  time: 0.4322  data: 0.0001  max mem: 42573
Epoch: [70] Total time: 0:02:28 (0.4754 s / it)
Averaged stats: lr: 0.003682  min_lr: 0.003682  loss: 2.8297 (2.7140)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:00:43  loss: 1.0343 (1.0343)  acc1: 73.9583 (73.9583)  acc5: 91.6667 (91.6667)  time: 4.7797  data: 4.6711  max mem: 42573
Test:  [8/9]  eta: 0:00:00  loss: 1.4354 (1.2914)  acc1: 67.9688 (68.0960)  acc5: 87.7604 (88.3520)  time: 0.6065  data: 0.5191  max mem: 42573
Test: Total time: 0:00:05 (0.6139 s / it)
* Acc@1 68.616 Acc@5 88.484 loss 1.296
Accuracy of the model on the 50000 test images: 68.6%
Max accuracy: 69.27%
Epoch: [71]  [  0/312]  eta: 0:51:36  lr: 0.003681  min_lr: 0.003681  loss: 2.0565 (2.0565)  weight_decay: 0.0500 (0.0500)  time: 9.9250  data: 6.5109  max mem: 42573
Epoch: [71]  [ 10/312]  eta: 0:07:23  lr: 0.003681  min_lr: 0.003681  loss: 2.3055 (2.4347)  weight_decay: 0.0500 (0.0500)  time: 1.4684  data: 0.6317  max mem: 42573
Epoch: [71]  [ 20/312]  eta: 0:04:44  lr: 0.003681  min_lr: 0.003681  loss: 2.3346 (2.5043)  weight_decay: 0.0500 (0.0500)  time: 0.5278  data: 0.0221  max mem: 42573
Epoch: [71]  [ 30/312]  eta: 0:03:45  lr: 0.003680  min_lr: 0.003680  loss: 2.4445 (2.5133)  weight_decay: 0.0500 (0.0500)  time: 0.4331  data: 0.0003  max mem: 42573
Epoch: [71]  [ 40/312]  eta: 0:03:13  lr: 0.003680  min_lr: 0.003680  loss: 2.6958 (2.6067)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [71]  [ 50/312]  eta: 0:02:52  lr: 0.003680  min_lr: 0.003680  loss: 2.8501 (2.6412)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [71]  [ 60/312]  eta: 0:02:36  lr: 0.003679  min_lr: 0.003679  loss: 2.8501 (2.6467)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [71]  [ 70/312]  eta: 0:02:23  lr: 0.003679  min_lr: 0.003679  loss: 2.5623 (2.6032)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [71]  [ 80/312]  eta: 0:02:13  lr: 0.003678  min_lr: 0.003678  loss: 2.2601 (2.5963)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [71]  [ 90/312]  eta: 0:02:04  lr: 0.003678  min_lr: 0.003678  loss: 2.4182 (2.5872)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [71]  [100/312]  eta: 0:01:55  lr: 0.003678  min_lr: 0.003678  loss: 2.7692 (2.6135)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [71]  [110/312]  eta: 0:01:48  lr: 0.003677  min_lr: 0.003677  loss: 2.8496 (2.6290)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [71]  [120/312]  eta: 0:01:41  lr: 0.003677  min_lr: 0.003677  loss: 2.8496 (2.6416)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [71]  [130/312]  eta: 0:01:34  lr: 0.003676  min_lr: 0.003676  loss: 2.5892 (2.6334)  weight_decay: 0.0500 (0.0500)  time: 0.4378  data: 0.0004  max mem: 42573
Epoch: [71]  [140/312]  eta: 0:01:28  lr: 0.003676  min_lr: 0.003676  loss: 2.4888 (2.6365)  weight_decay: 0.0500 (0.0500)  time: 0.4376  data: 0.0003  max mem: 42573
Epoch: [71]  [150/312]  eta: 0:01:22  lr: 0.003676  min_lr: 0.003676  loss: 2.6811 (2.6458)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [71]  [160/312]  eta: 0:01:16  lr: 0.003675  min_lr: 0.003675  loss: 2.6811 (2.6492)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [71]  [170/312]  eta: 0:01:11  lr: 0.003675  min_lr: 0.003675  loss: 2.8275 (2.6554)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [71]  [180/312]  eta: 0:01:05  lr: 0.003674  min_lr: 0.003674  loss: 2.8847 (2.6593)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [71]  [190/312]  eta: 0:01:00  lr: 0.003674  min_lr: 0.003674  loss: 2.8011 (2.6685)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [71]  [200/312]  eta: 0:00:54  lr: 0.003674  min_lr: 0.003674  loss: 2.8385 (2.6698)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [71]  [210/312]  eta: 0:00:49  lr: 0.003673  min_lr: 0.003673  loss: 2.8928 (2.6722)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0003  max mem: 42573
Epoch: [71]  [220/312]  eta: 0:00:44  lr: 0.003673  min_lr: 0.003673  loss: 2.7268 (2.6703)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [71]  [230/312]  eta: 0:00:39  lr: 0.003672  min_lr: 0.003672  loss: 2.7268 (2.6758)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [71]  [240/312]  eta: 0:00:34  lr: 0.003672  min_lr: 0.003672  loss: 2.8917 (2.6811)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [71]  [250/312]  eta: 0:00:29  lr: 0.003672  min_lr: 0.003672  loss: 2.8917 (2.6795)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [71]  [260/312]  eta: 0:00:24  lr: 0.003671  min_lr: 0.003671  loss: 2.8079 (2.6820)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [71]  [270/312]  eta: 0:00:19  lr: 0.003671  min_lr: 0.003671  loss: 2.5199 (2.6725)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [71]  [280/312]  eta: 0:00:15  lr: 0.003670  min_lr: 0.003670  loss: 2.7720 (2.6781)  weight_decay: 0.0500 (0.0500)  time: 0.4343  data: 0.0009  max mem: 42573
Epoch: [71]  [290/312]  eta: 0:00:10  lr: 0.003670  min_lr: 0.003670  loss: 2.9275 (2.6860)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0008  max mem: 42573
Epoch: [71]  [300/312]  eta: 0:00:05  lr: 0.003670  min_lr: 0.003670  loss: 2.9274 (2.6942)  weight_decay: 0.0500 (0.0500)  time: 0.4324  data: 0.0001  max mem: 42573
Epoch: [71]  [310/312]  eta: 0:00:00  lr: 0.003669  min_lr: 0.003669  loss: 2.8514 (2.6875)  weight_decay: 0.0500 (0.0500)  time: 0.4324  data: 0.0001  max mem: 42573
Epoch: [71]  [311/312]  eta: 0:00:00  lr: 0.003669  min_lr: 0.003669  loss: 2.6451 (2.6861)  weight_decay: 0.0500 (0.0500)  time: 0.4324  data: 0.0001  max mem: 42573
Epoch: [71] Total time: 0:02:27 (0.4734 s / it)
Averaged stats: lr: 0.003669  min_lr: 0.003669  loss: 2.6451 (2.7128)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:00:43  loss: 1.0842 (1.0842)  acc1: 73.6979 (73.6979)  acc5: 92.1875 (92.1875)  time: 4.8275  data: 4.7180  max mem: 42573
Test:  [8/9]  eta: 0:00:00  loss: 1.3696 (1.2797)  acc1: 69.7917 (68.6080)  acc5: 88.2812 (88.6400)  time: 0.6121  data: 0.5243  max mem: 42573
Test: Total time: 0:00:05 (0.6210 s / it)
* Acc@1 68.736 Acc@5 88.504 loss 1.274
Accuracy of the model on the 50000 test images: 68.7%
Max accuracy: 69.27%
Epoch: [72]  [  0/312]  eta: 0:50:30  lr: 0.003669  min_lr: 0.003669  loss: 3.0628 (3.0628)  weight_decay: 0.0500 (0.0500)  time: 9.7141  data: 8.4210  max mem: 42573
Epoch: [72]  [ 10/312]  eta: 0:07:26  lr: 0.003669  min_lr: 0.003669  loss: 2.7884 (2.6541)  weight_decay: 0.0500 (0.0500)  time: 1.4800  data: 0.7659  max mem: 42573
Epoch: [72]  [ 20/312]  eta: 0:04:46  lr: 0.003668  min_lr: 0.003668  loss: 2.3481 (2.6258)  weight_decay: 0.0500 (0.0500)  time: 0.5449  data: 0.0004  max mem: 42573
Epoch: [72]  [ 30/312]  eta: 0:03:46  lr: 0.003668  min_lr: 0.003668  loss: 2.6911 (2.7175)  weight_decay: 0.0500 (0.0500)  time: 0.4332  data: 0.0003  max mem: 42573
Epoch: [72]  [ 40/312]  eta: 0:03:14  lr: 0.003668  min_lr: 0.003668  loss: 2.8157 (2.7240)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [72]  [ 50/312]  eta: 0:02:52  lr: 0.003667  min_lr: 0.003667  loss: 2.6762 (2.6948)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [72]  [ 60/312]  eta: 0:02:36  lr: 0.003667  min_lr: 0.003667  loss: 2.8101 (2.7241)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [72]  [ 70/312]  eta: 0:02:24  lr: 0.003666  min_lr: 0.003666  loss: 2.8082 (2.6816)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [72]  [ 80/312]  eta: 0:02:13  lr: 0.003666  min_lr: 0.003666  loss: 2.7247 (2.7055)  weight_decay: 0.0500 (0.0500)  time: 0.4341  data: 0.0004  max mem: 42573
Epoch: [72]  [ 90/312]  eta: 0:02:04  lr: 0.003666  min_lr: 0.003666  loss: 2.8208 (2.7150)  weight_decay: 0.0500 (0.0500)  time: 0.4341  data: 0.0004  max mem: 42573
Epoch: [72]  [100/312]  eta: 0:01:56  lr: 0.003665  min_lr: 0.003665  loss: 2.6785 (2.7121)  weight_decay: 0.0500 (0.0500)  time: 0.4342  data: 0.0004  max mem: 42573
Epoch: [72]  [110/312]  eta: 0:01:48  lr: 0.003665  min_lr: 0.003665  loss: 2.6384 (2.6995)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0003  max mem: 42573
Epoch: [72]  [120/312]  eta: 0:01:41  lr: 0.003664  min_lr: 0.003664  loss: 2.5596 (2.6986)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [72]  [130/312]  eta: 0:01:34  lr: 0.003664  min_lr: 0.003664  loss: 2.4850 (2.6829)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [72]  [140/312]  eta: 0:01:28  lr: 0.003664  min_lr: 0.003664  loss: 2.6126 (2.6944)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [72]  [150/312]  eta: 0:01:22  lr: 0.003663  min_lr: 0.003663  loss: 2.8971 (2.7000)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [72]  [160/312]  eta: 0:01:16  lr: 0.003663  min_lr: 0.003663  loss: 2.8028 (2.6972)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [72]  [170/312]  eta: 0:01:11  lr: 0.003662  min_lr: 0.003662  loss: 2.8584 (2.7133)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [72]  [180/312]  eta: 0:01:05  lr: 0.003662  min_lr: 0.003662  loss: 2.9764 (2.7100)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [72]  [190/312]  eta: 0:01:00  lr: 0.003662  min_lr: 0.003662  loss: 2.5328 (2.7012)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [72]  [200/312]  eta: 0:00:54  lr: 0.003661  min_lr: 0.003661  loss: 2.5664 (2.6933)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [72]  [210/312]  eta: 0:00:49  lr: 0.003661  min_lr: 0.003661  loss: 2.8170 (2.6965)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [72]  [220/312]  eta: 0:00:44  lr: 0.003660  min_lr: 0.003660  loss: 2.8333 (2.6964)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [72]  [230/312]  eta: 0:00:39  lr: 0.003660  min_lr: 0.003660  loss: 2.8918 (2.7077)  weight_decay: 0.0500 (0.0500)  time: 0.4405  data: 0.0004  max mem: 42573
Epoch: [72]  [240/312]  eta: 0:00:34  lr: 0.003660  min_lr: 0.003660  loss: 2.8918 (2.7040)  weight_decay: 0.0500 (0.0500)  time: 0.4406  data: 0.0004  max mem: 42573
Epoch: [72]  [250/312]  eta: 0:00:29  lr: 0.003659  min_lr: 0.003659  loss: 2.3843 (2.7023)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0003  max mem: 42573
Epoch: [72]  [260/312]  eta: 0:00:24  lr: 0.003659  min_lr: 0.003659  loss: 2.5229 (2.6984)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0003  max mem: 42573
Epoch: [72]  [270/312]  eta: 0:00:20  lr: 0.003658  min_lr: 0.003658  loss: 2.7762 (2.7029)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [72]  [280/312]  eta: 0:00:15  lr: 0.003658  min_lr: 0.003658  loss: 2.8628 (2.6982)  weight_decay: 0.0500 (0.0500)  time: 0.4343  data: 0.0010  max mem: 42573
Epoch: [72]  [290/312]  eta: 0:00:10  lr: 0.003658  min_lr: 0.003658  loss: 2.4618 (2.6939)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0008  max mem: 42573
Epoch: [72]  [300/312]  eta: 0:00:05  lr: 0.003657  min_lr: 0.003657  loss: 2.3816 (2.6913)  weight_decay: 0.0500 (0.0500)  time: 0.4325  data: 0.0001  max mem: 42573
Epoch: [72]  [310/312]  eta: 0:00:00  lr: 0.003657  min_lr: 0.003657  loss: 2.7939 (2.6944)  weight_decay: 0.0500 (0.0500)  time: 0.4324  data: 0.0001  max mem: 42573
Epoch: [72]  [311/312]  eta: 0:00:00  lr: 0.003657  min_lr: 0.003657  loss: 2.7939 (2.6952)  weight_decay: 0.0500 (0.0500)  time: 0.4324  data: 0.0001  max mem: 42573
Epoch: [72] Total time: 0:02:27 (0.4740 s / it)
Averaged stats: lr: 0.003657  min_lr: 0.003657  loss: 2.7939 (2.7086)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:00:44  loss: 0.8657 (0.8657)  acc1: 78.3854 (78.3854)  acc5: 94.7917 (94.7917)  time: 4.9977  data: 4.8882  max mem: 42573
Test:  [8/9]  eta: 0:00:00  loss: 1.3206 (1.2206)  acc1: 68.2292 (69.1840)  acc5: 88.8021 (89.3760)  time: 0.6316  data: 0.5432  max mem: 42573
Test: Total time: 0:00:05 (0.6538 s / it)
* Acc@1 69.578 Acc@5 89.138 loss 1.222
Accuracy of the model on the 50000 test images: 69.6%
Max accuracy: 69.58%
Epoch: [73]  [  0/312]  eta: 0:47:38  lr: 0.003657  min_lr: 0.003657  loss: 2.1940 (2.1940)  weight_decay: 0.0500 (0.0500)  time: 9.1628  data: 8.7067  max mem: 42573
Epoch: [73]  [ 10/312]  eta: 0:07:13  lr: 0.003656  min_lr: 0.003656  loss: 2.5508 (2.5537)  weight_decay: 0.0500 (0.0500)  time: 1.4354  data: 0.7919  max mem: 42573
Epoch: [73]  [ 20/312]  eta: 0:04:39  lr: 0.003656  min_lr: 0.003656  loss: 2.7715 (2.6654)  weight_decay: 0.0500 (0.0500)  time: 0.5479  data: 0.0004  max mem: 42573
Epoch: [73]  [ 30/312]  eta: 0:03:42  lr: 0.003656  min_lr: 0.003656  loss: 2.9510 (2.7331)  weight_decay: 0.0500 (0.0500)  time: 0.4332  data: 0.0004  max mem: 42573
Epoch: [73]  [ 40/312]  eta: 0:03:10  lr: 0.003655  min_lr: 0.003655  loss: 2.9400 (2.7134)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [73]  [ 50/312]  eta: 0:02:50  lr: 0.003655  min_lr: 0.003655  loss: 2.8882 (2.7116)  weight_decay: 0.0500 (0.0500)  time: 0.4332  data: 0.0004  max mem: 42573
Epoch: [73]  [ 60/312]  eta: 0:02:34  lr: 0.003654  min_lr: 0.003654  loss: 2.7442 (2.6882)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0005  max mem: 42573
Epoch: [73]  [ 70/312]  eta: 0:02:22  lr: 0.003654  min_lr: 0.003654  loss: 2.7741 (2.6983)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [73]  [ 80/312]  eta: 0:02:12  lr: 0.003654  min_lr: 0.003654  loss: 2.7884 (2.6955)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [73]  [ 90/312]  eta: 0:02:03  lr: 0.003653  min_lr: 0.003653  loss: 2.5839 (2.6840)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [73]  [100/312]  eta: 0:01:55  lr: 0.003653  min_lr: 0.003653  loss: 2.7366 (2.6992)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [73]  [110/312]  eta: 0:01:47  lr: 0.003652  min_lr: 0.003652  loss: 2.9446 (2.7236)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [73]  [120/312]  eta: 0:01:40  lr: 0.003652  min_lr: 0.003652  loss: 2.9673 (2.7448)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [73]  [130/312]  eta: 0:01:34  lr: 0.003652  min_lr: 0.003652  loss: 2.9756 (2.7588)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [73]  [140/312]  eta: 0:01:28  lr: 0.003651  min_lr: 0.003651  loss: 2.7543 (2.7428)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [73]  [150/312]  eta: 0:01:22  lr: 0.003651  min_lr: 0.003651  loss: 2.4402 (2.7282)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [73]  [160/312]  eta: 0:01:16  lr: 0.003650  min_lr: 0.003650  loss: 2.5360 (2.7292)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [73]  [170/312]  eta: 0:01:10  lr: 0.003650  min_lr: 0.003650  loss: 2.7570 (2.7323)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [73]  [180/312]  eta: 0:01:05  lr: 0.003649  min_lr: 0.003649  loss: 2.9651 (2.7445)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [73]  [190/312]  eta: 0:00:59  lr: 0.003649  min_lr: 0.003649  loss: 2.9036 (2.7453)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [73]  [200/312]  eta: 0:00:54  lr: 0.003649  min_lr: 0.003649  loss: 2.5936 (2.7410)  weight_decay: 0.0500 (0.0500)  time: 0.4409  data: 0.0004  max mem: 42573
Epoch: [73]  [210/312]  eta: 0:00:49  lr: 0.003648  min_lr: 0.003648  loss: 2.7179 (2.7499)  weight_decay: 0.0500 (0.0500)  time: 0.4412  data: 0.0004  max mem: 42573
Epoch: [73]  [220/312]  eta: 0:00:44  lr: 0.003648  min_lr: 0.003648  loss: 2.8315 (2.7424)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0003  max mem: 42573
Epoch: [73]  [230/312]  eta: 0:00:39  lr: 0.003647  min_lr: 0.003647  loss: 2.7308 (2.7470)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0003  max mem: 42573
Epoch: [73]  [240/312]  eta: 0:00:34  lr: 0.003647  min_lr: 0.003647  loss: 2.8357 (2.7478)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [73]  [250/312]  eta: 0:00:29  lr: 0.003647  min_lr: 0.003647  loss: 2.8863 (2.7503)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [73]  [260/312]  eta: 0:00:24  lr: 0.003646  min_lr: 0.003646  loss: 2.8443 (2.7434)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [73]  [270/312]  eta: 0:00:19  lr: 0.003646  min_lr: 0.003646  loss: 2.6785 (2.7455)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [73]  [280/312]  eta: 0:00:15  lr: 0.003645  min_lr: 0.003645  loss: 2.8850 (2.7460)  weight_decay: 0.0500 (0.0500)  time: 0.4343  data: 0.0009  max mem: 42573
Epoch: [73]  [290/312]  eta: 0:00:10  lr: 0.003645  min_lr: 0.003645  loss: 2.9039 (2.7501)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0008  max mem: 42573
Epoch: [73]  [300/312]  eta: 0:00:05  lr: 0.003645  min_lr: 0.003645  loss: 2.8337 (2.7535)  weight_decay: 0.0500 (0.0500)  time: 0.4325  data: 0.0001  max mem: 42573
Epoch: [73]  [310/312]  eta: 0:00:00  lr: 0.003644  min_lr: 0.003644  loss: 2.8861 (2.7553)  weight_decay: 0.0500 (0.0500)  time: 0.4324  data: 0.0001  max mem: 42573
Epoch: [73]  [311/312]  eta: 0:00:00  lr: 0.003644  min_lr: 0.003644  loss: 2.8861 (2.7567)  weight_decay: 0.0500 (0.0500)  time: 0.4324  data: 0.0001  max mem: 42573
Epoch: [73] Total time: 0:02:27 (0.4726 s / it)
Averaged stats: lr: 0.003644  min_lr: 0.003644  loss: 2.8861 (2.7107)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:00:44  loss: 1.0373 (1.0373)  acc1: 75.2604 (75.2604)  acc5: 91.9271 (91.9271)  time: 4.9244  data: 4.8151  max mem: 42573
Test:  [8/9]  eta: 0:00:00  loss: 1.3172 (1.3038)  acc1: 68.2292 (68.9600)  acc5: 88.2812 (88.5120)  time: 0.6231  data: 0.5351  max mem: 42573
Test: Total time: 0:00:05 (0.6417 s / it)
* Acc@1 69.244 Acc@5 88.688 loss 1.307
Accuracy of the model on the 50000 test images: 69.2%
Max accuracy: 69.58%
Epoch: [74]  [  0/312]  eta: 0:48:41  lr: 0.003644  min_lr: 0.003644  loss: 2.1617 (2.1617)  weight_decay: 0.0500 (0.0500)  time: 9.3636  data: 7.5556  max mem: 42573
Epoch: [74]  [ 10/312]  eta: 0:07:11  lr: 0.003644  min_lr: 0.003644  loss: 2.8524 (2.5918)  weight_decay: 0.0500 (0.0500)  time: 1.4289  data: 0.7139  max mem: 42573
Epoch: [74]  [ 20/312]  eta: 0:04:38  lr: 0.003643  min_lr: 0.003643  loss: 2.8524 (2.6499)  weight_decay: 0.0500 (0.0500)  time: 0.5343  data: 0.0151  max mem: 42573
Epoch: [74]  [ 30/312]  eta: 0:03:41  lr: 0.003643  min_lr: 0.003643  loss: 2.5727 (2.6275)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [74]  [ 40/312]  eta: 0:03:10  lr: 0.003642  min_lr: 0.003642  loss: 2.7284 (2.6535)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0005  max mem: 42573
Epoch: [74]  [ 50/312]  eta: 0:02:49  lr: 0.003642  min_lr: 0.003642  loss: 2.8788 (2.7183)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0005  max mem: 42573
Epoch: [74]  [ 60/312]  eta: 0:02:34  lr: 0.003642  min_lr: 0.003642  loss: 2.8980 (2.7288)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [74]  [ 70/312]  eta: 0:02:22  lr: 0.003641  min_lr: 0.003641  loss: 2.6393 (2.7143)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [74]  [ 80/312]  eta: 0:02:11  lr: 0.003641  min_lr: 0.003641  loss: 2.5602 (2.6996)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [74]  [ 90/312]  eta: 0:02:02  lr: 0.003640  min_lr: 0.003640  loss: 2.5829 (2.6998)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [74]  [100/312]  eta: 0:01:54  lr: 0.003640  min_lr: 0.003640  loss: 2.5985 (2.6834)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [74]  [110/312]  eta: 0:01:47  lr: 0.003640  min_lr: 0.003640  loss: 2.6057 (2.6953)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [74]  [120/312]  eta: 0:01:40  lr: 0.003639  min_lr: 0.003639  loss: 2.9143 (2.6979)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [74]  [130/312]  eta: 0:01:34  lr: 0.003639  min_lr: 0.003639  loss: 2.2601 (2.6704)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [74]  [140/312]  eta: 0:01:27  lr: 0.003638  min_lr: 0.003638  loss: 2.6069 (2.6828)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [74]  [150/312]  eta: 0:01:21  lr: 0.003638  min_lr: 0.003638  loss: 2.8043 (2.6852)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [74]  [160/312]  eta: 0:01:16  lr: 0.003638  min_lr: 0.003638  loss: 2.8318 (2.6891)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [74]  [170/312]  eta: 0:01:10  lr: 0.003637  min_lr: 0.003637  loss: 2.8058 (2.6956)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [74]  [180/312]  eta: 0:01:05  lr: 0.003637  min_lr: 0.003637  loss: 2.7757 (2.7018)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [74]  [190/312]  eta: 0:00:59  lr: 0.003636  min_lr: 0.003636  loss: 2.9339 (2.7105)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [74]  [200/312]  eta: 0:00:54  lr: 0.003636  min_lr: 0.003636  loss: 2.8998 (2.7062)  weight_decay: 0.0500 (0.0500)  time: 0.4397  data: 0.0004  max mem: 42573
Epoch: [74]  [210/312]  eta: 0:00:49  lr: 0.003635  min_lr: 0.003635  loss: 2.4394 (2.6955)  weight_decay: 0.0500 (0.0500)  time: 0.4396  data: 0.0004  max mem: 42573
Epoch: [74]  [220/312]  eta: 0:00:44  lr: 0.003635  min_lr: 0.003635  loss: 2.4394 (2.6865)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [74]  [230/312]  eta: 0:00:39  lr: 0.003635  min_lr: 0.003635  loss: 2.5438 (2.6743)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [74]  [240/312]  eta: 0:00:34  lr: 0.003634  min_lr: 0.003634  loss: 2.5818 (2.6735)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [74]  [250/312]  eta: 0:00:29  lr: 0.003634  min_lr: 0.003634  loss: 2.6343 (2.6708)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [74]  [260/312]  eta: 0:00:24  lr: 0.003633  min_lr: 0.003633  loss: 2.8425 (2.6722)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [74]  [270/312]  eta: 0:00:19  lr: 0.003633  min_lr: 0.003633  loss: 2.7869 (2.6740)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [74]  [280/312]  eta: 0:00:15  lr: 0.003633  min_lr: 0.003633  loss: 2.7869 (2.6780)  weight_decay: 0.0500 (0.0500)  time: 0.4341  data: 0.0009  max mem: 42573
Epoch: [74]  [290/312]  eta: 0:00:10  lr: 0.003632  min_lr: 0.003632  loss: 2.8876 (2.6824)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0008  max mem: 42573
Epoch: [74]  [300/312]  eta: 0:00:05  lr: 0.003632  min_lr: 0.003632  loss: 2.9958 (2.6871)  weight_decay: 0.0500 (0.0500)  time: 0.4324  data: 0.0001  max mem: 42573
Epoch: [74]  [310/312]  eta: 0:00:00  lr: 0.003631  min_lr: 0.003631  loss: 2.6631 (2.6793)  weight_decay: 0.0500 (0.0500)  time: 0.4324  data: 0.0001  max mem: 42573
Epoch: [74]  [311/312]  eta: 0:00:00  lr: 0.003631  min_lr: 0.003631  loss: 2.6631 (2.6789)  weight_decay: 0.0500 (0.0500)  time: 0.4324  data: 0.0001  max mem: 42573
Epoch: [74] Total time: 0:02:27 (0.4720 s / it)
Averaged stats: lr: 0.003631  min_lr: 0.003631  loss: 2.6631 (2.6906)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:00:43  loss: 0.9470 (0.9470)  acc1: 76.5625 (76.5625)  acc5: 92.7083 (92.7083)  time: 4.8839  data: 4.7751  max mem: 42573
Test:  [8/9]  eta: 0:00:00  loss: 1.2981 (1.2422)  acc1: 69.2708 (68.2240)  acc5: 89.0625 (89.0240)  time: 0.6197  data: 0.5306  max mem: 42573
Test: Total time: 0:00:05 (0.6272 s / it)
* Acc@1 68.404 Acc@5 88.302 loss 1.281
Accuracy of the model on the 50000 test images: 68.4%
Max accuracy: 69.58%
Epoch: [75]  [  0/312]  eta: 0:50:03  lr: 0.003631  min_lr: 0.003631  loss: 3.2656 (3.2656)  weight_decay: 0.0500 (0.0500)  time: 9.6253  data: 6.8813  max mem: 42573
Epoch: [75]  [ 10/312]  eta: 0:07:22  lr: 0.003631  min_lr: 0.003631  loss: 2.8579 (2.8946)  weight_decay: 0.0500 (0.0500)  time: 1.4637  data: 0.8144  max mem: 42573
Epoch: [75]  [ 20/312]  eta: 0:04:44  lr: 0.003630  min_lr: 0.003630  loss: 2.8404 (2.7560)  weight_decay: 0.0500 (0.0500)  time: 0.5405  data: 0.1041  max mem: 42573
Epoch: [75]  [ 30/312]  eta: 0:03:45  lr: 0.003630  min_lr: 0.003630  loss: 2.9328 (2.8169)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [75]  [ 40/312]  eta: 0:03:13  lr: 0.003630  min_lr: 0.003630  loss: 2.9330 (2.8056)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [75]  [ 50/312]  eta: 0:02:51  lr: 0.003629  min_lr: 0.003629  loss: 2.6389 (2.7230)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [75]  [ 60/312]  eta: 0:02:36  lr: 0.003629  min_lr: 0.003629  loss: 2.4504 (2.7168)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [75]  [ 70/312]  eta: 0:02:23  lr: 0.003628  min_lr: 0.003628  loss: 2.7393 (2.7152)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [75]  [ 80/312]  eta: 0:02:13  lr: 0.003628  min_lr: 0.003628  loss: 2.8838 (2.7208)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [75]  [ 90/312]  eta: 0:02:03  lr: 0.003627  min_lr: 0.003627  loss: 2.8330 (2.7014)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0004  max mem: 42573
Epoch: [75]  [100/312]  eta: 0:01:55  lr: 0.003627  min_lr: 0.003627  loss: 2.3814 (2.6801)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0004  max mem: 42573
Epoch: [75]  [110/312]  eta: 0:01:48  lr: 0.003627  min_lr: 0.003627  loss: 2.6498 (2.6734)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [75]  [120/312]  eta: 0:01:41  lr: 0.003626  min_lr: 0.003626  loss: 2.7585 (2.6776)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [75]  [130/312]  eta: 0:01:34  lr: 0.003626  min_lr: 0.003626  loss: 2.8916 (2.6764)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [75]  [140/312]  eta: 0:01:28  lr: 0.003625  min_lr: 0.003625  loss: 2.8675 (2.6887)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [75]  [150/312]  eta: 0:01:22  lr: 0.003625  min_lr: 0.003625  loss: 2.6254 (2.6831)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [75]  [160/312]  eta: 0:01:16  lr: 0.003625  min_lr: 0.003625  loss: 2.6076 (2.6824)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0003  max mem: 42573
Epoch: [75]  [170/312]  eta: 0:01:10  lr: 0.003624  min_lr: 0.003624  loss: 2.7881 (2.6826)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [75]  [180/312]  eta: 0:01:05  lr: 0.003624  min_lr: 0.003624  loss: 2.7085 (2.6783)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [75]  [190/312]  eta: 0:01:00  lr: 0.003623  min_lr: 0.003623  loss: 2.7525 (2.6802)  weight_decay: 0.0500 (0.0500)  time: 0.4373  data: 0.0004  max mem: 42573
Epoch: [75]  [200/312]  eta: 0:00:54  lr: 0.003623  min_lr: 0.003623  loss: 2.7266 (2.6768)  weight_decay: 0.0500 (0.0500)  time: 0.4374  data: 0.0004  max mem: 42573
Epoch: [75]  [210/312]  eta: 0:00:49  lr: 0.003622  min_lr: 0.003622  loss: 2.6472 (2.6792)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [75]  [220/312]  eta: 0:00:44  lr: 0.003622  min_lr: 0.003622  loss: 2.8539 (2.6794)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [75]  [230/312]  eta: 0:00:39  lr: 0.003622  min_lr: 0.003622  loss: 2.8041 (2.6798)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [75]  [240/312]  eta: 0:00:34  lr: 0.003621  min_lr: 0.003621  loss: 2.8264 (2.6866)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [75]  [250/312]  eta: 0:00:29  lr: 0.003621  min_lr: 0.003621  loss: 2.6928 (2.6814)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [75]  [260/312]  eta: 0:00:24  lr: 0.003620  min_lr: 0.003620  loss: 2.6011 (2.6811)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0003  max mem: 42573
Epoch: [75]  [270/312]  eta: 0:00:19  lr: 0.003620  min_lr: 0.003620  loss: 2.7168 (2.6822)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0003  max mem: 42573
Epoch: [75]  [280/312]  eta: 0:00:15  lr: 0.003619  min_lr: 0.003619  loss: 2.6012 (2.6766)  weight_decay: 0.0500 (0.0500)  time: 0.4341  data: 0.0009  max mem: 42573
Epoch: [75]  [290/312]  eta: 0:00:10  lr: 0.003619  min_lr: 0.003619  loss: 2.4790 (2.6747)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0008  max mem: 42573
Epoch: [75]  [300/312]  eta: 0:00:05  lr: 0.003619  min_lr: 0.003619  loss: 2.7671 (2.6727)  weight_decay: 0.0500 (0.0500)  time: 0.4324  data: 0.0001  max mem: 42573
Epoch: [75]  [310/312]  eta: 0:00:00  lr: 0.003618  min_lr: 0.003618  loss: 2.8851 (2.6796)  weight_decay: 0.0500 (0.0500)  time: 0.4323  data: 0.0001  max mem: 42573
Epoch: [75]  [311/312]  eta: 0:00:00  lr: 0.003618  min_lr: 0.003618  loss: 2.8610 (2.6773)  weight_decay: 0.0500 (0.0500)  time: 0.4322  data: 0.0001  max mem: 42573
Epoch: [75] Total time: 0:02:27 (0.4730 s / it)
Averaged stats: lr: 0.003618  min_lr: 0.003618  loss: 2.8610 (2.6993)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:00:46  loss: 1.0265 (1.0265)  acc1: 75.0000 (75.0000)  acc5: 91.9271 (91.9271)  time: 5.1400  data: 5.0306  max mem: 42573
Test:  [8/9]  eta: 0:00:00  loss: 1.3702 (1.2677)  acc1: 67.4479 (67.5840)  acc5: 88.8021 (88.6400)  time: 0.6482  data: 0.5590  max mem: 42573
Test: Total time: 0:00:06 (0.6686 s / it)
* Acc@1 68.432 Acc@5 88.104 loss 1.300
Accuracy of the model on the 50000 test images: 68.4%
Max accuracy: 69.58%
Epoch: [76]  [  0/312]  eta: 0:50:17  lr: 0.003618  min_lr: 0.003618  loss: 2.5613 (2.5613)  weight_decay: 0.0500 (0.0500)  time: 9.6709  data: 6.0998  max mem: 42573
Epoch: [76]  [ 10/312]  eta: 0:07:37  lr: 0.003618  min_lr: 0.003618  loss: 2.8140 (2.6583)  weight_decay: 0.0500 (0.0500)  time: 1.5134  data: 0.7472  max mem: 42573
Epoch: [76]  [ 20/312]  eta: 0:04:51  lr: 0.003617  min_lr: 0.003617  loss: 2.8737 (2.7323)  weight_decay: 0.0500 (0.0500)  time: 0.5654  data: 0.1062  max mem: 42573
Epoch: [76]  [ 30/312]  eta: 0:03:50  lr: 0.003617  min_lr: 0.003617  loss: 2.6825 (2.6471)  weight_decay: 0.0500 (0.0500)  time: 0.4330  data: 0.0004  max mem: 42573
Epoch: [76]  [ 40/312]  eta: 0:03:16  lr: 0.003616  min_lr: 0.003616  loss: 2.5152 (2.6558)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0003  max mem: 42573
Epoch: [76]  [ 50/312]  eta: 0:02:54  lr: 0.003616  min_lr: 0.003616  loss: 2.5152 (2.6385)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [76]  [ 60/312]  eta: 0:02:38  lr: 0.003616  min_lr: 0.003616  loss: 2.7560 (2.6531)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0003  max mem: 42573
Epoch: [76]  [ 70/312]  eta: 0:02:25  lr: 0.003615  min_lr: 0.003615  loss: 2.8223 (2.6668)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0003  max mem: 42573
Epoch: [76]  [ 80/312]  eta: 0:02:14  lr: 0.003615  min_lr: 0.003615  loss: 2.6929 (2.6458)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [76]  [ 90/312]  eta: 0:02:05  lr: 0.003614  min_lr: 0.003614  loss: 2.5834 (2.6429)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [76]  [100/312]  eta: 0:01:56  lr: 0.003614  min_lr: 0.003614  loss: 2.5375 (2.6271)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [76]  [110/312]  eta: 0:01:49  lr: 0.003613  min_lr: 0.003613  loss: 2.8022 (2.6504)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [76]  [120/312]  eta: 0:01:42  lr: 0.003613  min_lr: 0.003613  loss: 2.9542 (2.6481)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [76]  [130/312]  eta: 0:01:35  lr: 0.003613  min_lr: 0.003613  loss: 2.7368 (2.6593)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0004  max mem: 42573
Epoch: [76]  [140/312]  eta: 0:01:29  lr: 0.003612  min_lr: 0.003612  loss: 2.7838 (2.6703)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0003  max mem: 42573
Epoch: [76]  [150/312]  eta: 0:01:22  lr: 0.003612  min_lr: 0.003612  loss: 2.7138 (2.6759)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0003  max mem: 42573
Epoch: [76]  [160/312]  eta: 0:01:17  lr: 0.003611  min_lr: 0.003611  loss: 2.6493 (2.6688)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [76]  [170/312]  eta: 0:01:11  lr: 0.003611  min_lr: 0.003611  loss: 2.7089 (2.6709)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [76]  [180/312]  eta: 0:01:05  lr: 0.003610  min_lr: 0.003610  loss: 2.8248 (2.6829)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [76]  [190/312]  eta: 0:01:00  lr: 0.003610  min_lr: 0.003610  loss: 2.8429 (2.6863)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [76]  [200/312]  eta: 0:00:55  lr: 0.003610  min_lr: 0.003610  loss: 2.5246 (2.6697)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [76]  [210/312]  eta: 0:00:50  lr: 0.003609  min_lr: 0.003609  loss: 2.6876 (2.6701)  weight_decay: 0.0500 (0.0500)  time: 0.4378  data: 0.0004  max mem: 42573
Epoch: [76]  [220/312]  eta: 0:00:44  lr: 0.003609  min_lr: 0.003609  loss: 2.7905 (2.6779)  weight_decay: 0.0500 (0.0500)  time: 0.4377  data: 0.0004  max mem: 42573
Epoch: [76]  [230/312]  eta: 0:00:39  lr: 0.003608  min_lr: 0.003608  loss: 2.8865 (2.6867)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [76]  [240/312]  eta: 0:00:34  lr: 0.003608  min_lr: 0.003608  loss: 2.9292 (2.6879)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [76]  [250/312]  eta: 0:00:29  lr: 0.003607  min_lr: 0.003607  loss: 2.7004 (2.6829)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [76]  [260/312]  eta: 0:00:24  lr: 0.003607  min_lr: 0.003607  loss: 2.7091 (2.6898)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [76]  [270/312]  eta: 0:00:20  lr: 0.003607  min_lr: 0.003607  loss: 2.7028 (2.6874)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [76]  [280/312]  eta: 0:00:15  lr: 0.003606  min_lr: 0.003606  loss: 2.6894 (2.6898)  weight_decay: 0.0500 (0.0500)  time: 0.4344  data: 0.0009  max mem: 42573
Epoch: [76]  [290/312]  eta: 0:00:10  lr: 0.003606  min_lr: 0.003606  loss: 2.7780 (2.6855)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0008  max mem: 42573
Epoch: [76]  [300/312]  eta: 0:00:05  lr: 0.003605  min_lr: 0.003605  loss: 2.6410 (2.6847)  weight_decay: 0.0500 (0.0500)  time: 0.4324  data: 0.0001  max mem: 42573
Epoch: [76]  [310/312]  eta: 0:00:00  lr: 0.003605  min_lr: 0.003605  loss: 2.6666 (2.6828)  weight_decay: 0.0500 (0.0500)  time: 0.4323  data: 0.0001  max mem: 42573
Epoch: [76]  [311/312]  eta: 0:00:00  lr: 0.003605  min_lr: 0.003605  loss: 2.2497 (2.6804)  weight_decay: 0.0500 (0.0500)  time: 0.4323  data: 0.0001  max mem: 42573
Epoch: [76] Total time: 0:02:28 (0.4749 s / it)
Averaged stats: lr: 0.003605  min_lr: 0.003605  loss: 2.2497 (2.6948)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:00:42  loss: 0.9911 (0.9911)  acc1: 76.8229 (76.8229)  acc5: 92.9688 (92.9688)  time: 4.7073  data: 4.5978  max mem: 42573
Test:  [8/9]  eta: 0:00:00  loss: 1.3168 (1.3104)  acc1: 69.0104 (68.2880)  acc5: 89.0625 (88.3200)  time: 0.5987  data: 0.5109  max mem: 42573
Test: Total time: 0:00:05 (0.6065 s / it)
* Acc@1 68.298 Acc@5 88.162 loss 1.333
Accuracy of the model on the 50000 test images: 68.3%
Max accuracy: 69.58%
Epoch: [77]  [  0/312]  eta: 0:49:47  lr: 0.003605  min_lr: 0.003605  loss: 2.8647 (2.8647)  weight_decay: 0.0500 (0.0500)  time: 9.5738  data: 9.0176  max mem: 42573
Epoch: [77]  [ 10/312]  eta: 0:07:15  lr: 0.003604  min_lr: 0.003604  loss: 2.6012 (2.5220)  weight_decay: 0.0500 (0.0500)  time: 1.4418  data: 0.8202  max mem: 42573
Epoch: [77]  [ 20/312]  eta: 0:04:40  lr: 0.003604  min_lr: 0.003604  loss: 2.4956 (2.5261)  weight_decay: 0.0500 (0.0500)  time: 0.5312  data: 0.0004  max mem: 42573
Epoch: [77]  [ 30/312]  eta: 0:03:43  lr: 0.003604  min_lr: 0.003604  loss: 2.6823 (2.5314)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [77]  [ 40/312]  eta: 0:03:11  lr: 0.003603  min_lr: 0.003603  loss: 2.6264 (2.5642)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [77]  [ 50/312]  eta: 0:02:50  lr: 0.003603  min_lr: 0.003603  loss: 2.6700 (2.6048)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0005  max mem: 42573
Epoch: [77]  [ 60/312]  eta: 0:02:35  lr: 0.003602  min_lr: 0.003602  loss: 2.8024 (2.6486)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [77]  [ 70/312]  eta: 0:02:22  lr: 0.003602  min_lr: 0.003602  loss: 2.8090 (2.6516)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [77]  [ 80/312]  eta: 0:02:12  lr: 0.003601  min_lr: 0.003601  loss: 2.8038 (2.6635)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [77]  [ 90/312]  eta: 0:02:03  lr: 0.003601  min_lr: 0.003601  loss: 2.8038 (2.6609)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [77]  [100/312]  eta: 0:01:55  lr: 0.003601  min_lr: 0.003601  loss: 2.5508 (2.6349)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [77]  [110/312]  eta: 0:01:47  lr: 0.003600  min_lr: 0.003600  loss: 2.3435 (2.6354)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [77]  [120/312]  eta: 0:01:40  lr: 0.003600  min_lr: 0.003600  loss: 2.7625 (2.6411)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [77]  [130/312]  eta: 0:01:34  lr: 0.003599  min_lr: 0.003599  loss: 2.7625 (2.6440)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [77]  [140/312]  eta: 0:01:28  lr: 0.003599  min_lr: 0.003599  loss: 2.7751 (2.6443)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0003  max mem: 42573
Epoch: [77]  [150/312]  eta: 0:01:22  lr: 0.003598  min_lr: 0.003598  loss: 2.7799 (2.6515)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0003  max mem: 42573
Epoch: [77]  [160/312]  eta: 0:01:16  lr: 0.003598  min_lr: 0.003598  loss: 2.7675 (2.6607)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [77]  [170/312]  eta: 0:01:10  lr: 0.003598  min_lr: 0.003598  loss: 2.7798 (2.6652)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [77]  [180/312]  eta: 0:01:05  lr: 0.003597  min_lr: 0.003597  loss: 2.7956 (2.6750)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [77]  [190/312]  eta: 0:00:59  lr: 0.003597  min_lr: 0.003597  loss: 2.7869 (2.6776)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [77]  [200/312]  eta: 0:00:54  lr: 0.003596  min_lr: 0.003596  loss: 2.7347 (2.6845)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [77]  [210/312]  eta: 0:00:49  lr: 0.003596  min_lr: 0.003596  loss: 2.9462 (2.6941)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [77]  [220/312]  eta: 0:00:44  lr: 0.003595  min_lr: 0.003595  loss: 2.9821 (2.6991)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0003  max mem: 42573
Epoch: [77]  [230/312]  eta: 0:00:39  lr: 0.003595  min_lr: 0.003595  loss: 2.7785 (2.6982)  weight_decay: 0.0500 (0.0500)  time: 0.4382  data: 0.0003  max mem: 42573
Epoch: [77]  [240/312]  eta: 0:00:34  lr: 0.003594  min_lr: 0.003594  loss: 2.6482 (2.6983)  weight_decay: 0.0500 (0.0500)  time: 0.4385  data: 0.0003  max mem: 42573
Epoch: [77]  [250/312]  eta: 0:00:29  lr: 0.003594  min_lr: 0.003594  loss: 2.6482 (2.6915)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [77]  [260/312]  eta: 0:00:24  lr: 0.003594  min_lr: 0.003594  loss: 2.6857 (2.6894)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [77]  [270/312]  eta: 0:00:19  lr: 0.003593  min_lr: 0.003593  loss: 2.9339 (2.6930)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [77]  [280/312]  eta: 0:00:15  lr: 0.003593  min_lr: 0.003593  loss: 2.9360 (2.7012)  weight_decay: 0.0500 (0.0500)  time: 0.4343  data: 0.0009  max mem: 42573
Epoch: [77]  [290/312]  eta: 0:00:10  lr: 0.003592  min_lr: 0.003592  loss: 2.7886 (2.7016)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0008  max mem: 42573
Epoch: [77]  [300/312]  eta: 0:00:05  lr: 0.003592  min_lr: 0.003592  loss: 2.6552 (2.7003)  weight_decay: 0.0500 (0.0500)  time: 0.4325  data: 0.0001  max mem: 42573
Epoch: [77]  [310/312]  eta: 0:00:00  lr: 0.003591  min_lr: 0.003591  loss: 2.6552 (2.6971)  weight_decay: 0.0500 (0.0500)  time: 0.4324  data: 0.0001  max mem: 42573
Epoch: [77]  [311/312]  eta: 0:00:00  lr: 0.003591  min_lr: 0.003591  loss: 2.6552 (2.6978)  weight_decay: 0.0500 (0.0500)  time: 0.4324  data: 0.0001  max mem: 42573
Epoch: [77] Total time: 0:02:27 (0.4724 s / it)
Averaged stats: lr: 0.003591  min_lr: 0.003591  loss: 2.6552 (2.6888)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:00:45  loss: 0.9365 (0.9365)  acc1: 76.8229 (76.8229)  acc5: 92.1875 (92.1875)  time: 5.0741  data: 4.9648  max mem: 42573
Test:  [8/9]  eta: 0:00:00  loss: 1.4053 (1.2702)  acc1: 66.9271 (68.8960)  acc5: 88.0208 (88.4480)  time: 0.6398  data: 0.5517  max mem: 42573
Test: Total time: 0:00:05 (0.6580 s / it)
* Acc@1 68.788 Acc@5 88.666 loss 1.275
Accuracy of the model on the 50000 test images: 68.8%
Max accuracy: 69.58%
Epoch: [78]  [  0/312]  eta: 0:48:46  lr: 0.003591  min_lr: 0.003591  loss: 2.8598 (2.8598)  weight_decay: 0.0500 (0.0500)  time: 9.3784  data: 6.7327  max mem: 42573
Epoch: [78]  [ 10/312]  eta: 0:07:00  lr: 0.003591  min_lr: 0.003591  loss: 2.9911 (2.7791)  weight_decay: 0.0500 (0.0500)  time: 1.3921  data: 0.6351  max mem: 42573
Epoch: [78]  [ 20/312]  eta: 0:04:33  lr: 0.003590  min_lr: 0.003590  loss: 2.7305 (2.6633)  weight_decay: 0.0500 (0.0500)  time: 0.5135  data: 0.0129  max mem: 42573
Epoch: [78]  [ 30/312]  eta: 0:03:38  lr: 0.003590  min_lr: 0.003590  loss: 2.6488 (2.6760)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0003  max mem: 42573
Epoch: [78]  [ 40/312]  eta: 0:03:07  lr: 0.003590  min_lr: 0.003590  loss: 2.6714 (2.6776)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0003  max mem: 42573
Epoch: [78]  [ 50/312]  eta: 0:02:47  lr: 0.003589  min_lr: 0.003589  loss: 2.7268 (2.6768)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0003  max mem: 42573
Epoch: [78]  [ 60/312]  eta: 0:02:32  lr: 0.003589  min_lr: 0.003589  loss: 2.7363 (2.6907)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0003  max mem: 42573
Epoch: [78]  [ 70/312]  eta: 0:02:20  lr: 0.003588  min_lr: 0.003588  loss: 2.5763 (2.6783)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0003  max mem: 42573
Epoch: [78]  [ 80/312]  eta: 0:02:10  lr: 0.003588  min_lr: 0.003588  loss: 2.5185 (2.6616)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0003  max mem: 42573
Epoch: [78]  [ 90/312]  eta: 0:02:01  lr: 0.003587  min_lr: 0.003587  loss: 2.5414 (2.6585)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [78]  [100/312]  eta: 0:01:54  lr: 0.003587  min_lr: 0.003587  loss: 2.6543 (2.6615)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [78]  [110/312]  eta: 0:01:47  lr: 0.003587  min_lr: 0.003587  loss: 2.6224 (2.6574)  weight_decay: 0.0500 (0.0500)  time: 0.4416  data: 0.0004  max mem: 42573
Epoch: [78]  [120/312]  eta: 0:01:40  lr: 0.003586  min_lr: 0.003586  loss: 2.6355 (2.6640)  weight_decay: 0.0500 (0.0500)  time: 0.4414  data: 0.0004  max mem: 42573
Epoch: [78]  [130/312]  eta: 0:01:33  lr: 0.003586  min_lr: 0.003586  loss: 2.7423 (2.6609)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [78]  [140/312]  eta: 0:01:27  lr: 0.003585  min_lr: 0.003585  loss: 2.5589 (2.6450)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [78]  [150/312]  eta: 0:01:21  lr: 0.003585  min_lr: 0.003585  loss: 2.7269 (2.6604)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [78]  [160/312]  eta: 0:01:16  lr: 0.003584  min_lr: 0.003584  loss: 2.9357 (2.6744)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0003  max mem: 42573
Epoch: [78]  [170/312]  eta: 0:01:10  lr: 0.003584  min_lr: 0.003584  loss: 2.8731 (2.6708)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0003  max mem: 42573
Epoch: [78]  [180/312]  eta: 0:01:05  lr: 0.003583  min_lr: 0.003583  loss: 2.7752 (2.6741)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [78]  [190/312]  eta: 0:00:59  lr: 0.003583  min_lr: 0.003583  loss: 2.9442 (2.6750)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [78]  [200/312]  eta: 0:00:54  lr: 0.003583  min_lr: 0.003583  loss: 2.6590 (2.6692)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0005  max mem: 42573
Epoch: [78]  [210/312]  eta: 0:00:49  lr: 0.003582  min_lr: 0.003582  loss: 2.7683 (2.6720)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0007  max mem: 42573
Epoch: [78]  [220/312]  eta: 0:00:44  lr: 0.003582  min_lr: 0.003582  loss: 2.7683 (2.6760)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0006  max mem: 42573
Epoch: [78]  [230/312]  eta: 0:00:39  lr: 0.003581  min_lr: 0.003581  loss: 2.6521 (2.6746)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [78]  [240/312]  eta: 0:00:34  lr: 0.003581  min_lr: 0.003581  loss: 2.6195 (2.6764)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [78]  [250/312]  eta: 0:00:29  lr: 0.003580  min_lr: 0.003580  loss: 2.7268 (2.6807)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [78]  [260/312]  eta: 0:00:24  lr: 0.003580  min_lr: 0.003580  loss: 2.7718 (2.6786)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [78]  [270/312]  eta: 0:00:19  lr: 0.003580  min_lr: 0.003580  loss: 2.7920 (2.6797)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [78]  [280/312]  eta: 0:00:15  lr: 0.003579  min_lr: 0.003579  loss: 2.7920 (2.6785)  weight_decay: 0.0500 (0.0500)  time: 0.4344  data: 0.0009  max mem: 42573
Epoch: [78]  [290/312]  eta: 0:00:10  lr: 0.003579  min_lr: 0.003579  loss: 2.8023 (2.6806)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0008  max mem: 42573
Epoch: [78]  [300/312]  eta: 0:00:05  lr: 0.003578  min_lr: 0.003578  loss: 2.8603 (2.6867)  weight_decay: 0.0500 (0.0500)  time: 0.4323  data: 0.0001  max mem: 42573
Epoch: [78]  [310/312]  eta: 0:00:00  lr: 0.003578  min_lr: 0.003578  loss: 2.8452 (2.6825)  weight_decay: 0.0500 (0.0500)  time: 0.4324  data: 0.0001  max mem: 42573
Epoch: [78]  [311/312]  eta: 0:00:00  lr: 0.003578  min_lr: 0.003578  loss: 2.8552 (2.6853)  weight_decay: 0.0500 (0.0500)  time: 0.4323  data: 0.0001  max mem: 42573
Epoch: [78] Total time: 0:02:26 (0.4711 s / it)
Averaged stats: lr: 0.003578  min_lr: 0.003578  loss: 2.8552 (2.6871)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:00:43  loss: 0.9475 (0.9475)  acc1: 77.6042 (77.6042)  acc5: 92.1875 (92.1875)  time: 4.8182  data: 4.7089  max mem: 42573
Test:  [8/9]  eta: 0:00:00  loss: 1.3811 (1.2660)  acc1: 66.9271 (68.8640)  acc5: 89.0625 (88.8960)  time: 0.6124  data: 0.5233  max mem: 42573
Test: Total time: 0:00:05 (0.6368 s / it)
* Acc@1 69.226 Acc@5 88.852 loss 1.288
Accuracy of the model on the 50000 test images: 69.2%
Max accuracy: 69.58%
Epoch: [79]  [  0/312]  eta: 0:48:15  lr: 0.003578  min_lr: 0.003578  loss: 3.0333 (3.0333)  weight_decay: 0.0500 (0.0500)  time: 9.2789  data: 6.7846  max mem: 42573
Epoch: [79]  [ 10/312]  eta: 0:07:13  lr: 0.003577  min_lr: 0.003577  loss: 2.4679 (2.4573)  weight_decay: 0.0500 (0.0500)  time: 1.4359  data: 0.7199  max mem: 42573
Epoch: [79]  [ 20/312]  eta: 0:04:39  lr: 0.003577  min_lr: 0.003577  loss: 2.5523 (2.5811)  weight_decay: 0.0500 (0.0500)  time: 0.5424  data: 0.0569  max mem: 42573
Epoch: [79]  [ 30/312]  eta: 0:03:43  lr: 0.003576  min_lr: 0.003576  loss: 2.8204 (2.6352)  weight_decay: 0.0500 (0.0500)  time: 0.4388  data: 0.0004  max mem: 42573
Epoch: [79]  [ 40/312]  eta: 0:03:11  lr: 0.003576  min_lr: 0.003576  loss: 2.7100 (2.6050)  weight_decay: 0.0500 (0.0500)  time: 0.4389  data: 0.0004  max mem: 42573
Epoch: [79]  [ 50/312]  eta: 0:02:50  lr: 0.003575  min_lr: 0.003575  loss: 2.6639 (2.6107)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [79]  [ 60/312]  eta: 0:02:35  lr: 0.003575  min_lr: 0.003575  loss: 2.5281 (2.6101)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [79]  [ 70/312]  eta: 0:02:22  lr: 0.003575  min_lr: 0.003575  loss: 2.8295 (2.6682)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [79]  [ 80/312]  eta: 0:02:12  lr: 0.003574  min_lr: 0.003574  loss: 2.8617 (2.6754)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [79]  [ 90/312]  eta: 0:02:03  lr: 0.003574  min_lr: 0.003574  loss: 2.7675 (2.6776)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [79]  [100/312]  eta: 0:01:55  lr: 0.003573  min_lr: 0.003573  loss: 2.7249 (2.6568)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [79]  [110/312]  eta: 0:01:47  lr: 0.003573  min_lr: 0.003573  loss: 2.7166 (2.6649)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [79]  [120/312]  eta: 0:01:40  lr: 0.003572  min_lr: 0.003572  loss: 2.7273 (2.6790)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [79]  [130/312]  eta: 0:01:34  lr: 0.003572  min_lr: 0.003572  loss: 2.8610 (2.6839)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0004  max mem: 42573
Epoch: [79]  [140/312]  eta: 0:01:28  lr: 0.003571  min_lr: 0.003571  loss: 2.9285 (2.7048)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [79]  [150/312]  eta: 0:01:22  lr: 0.003571  min_lr: 0.003571  loss: 2.7878 (2.6885)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [79]  [160/312]  eta: 0:01:16  lr: 0.003571  min_lr: 0.003571  loss: 2.6943 (2.6963)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [79]  [170/312]  eta: 0:01:10  lr: 0.003570  min_lr: 0.003570  loss: 2.7227 (2.6954)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [79]  [180/312]  eta: 0:01:05  lr: 0.003570  min_lr: 0.003570  loss: 2.7032 (2.6950)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [79]  [190/312]  eta: 0:01:00  lr: 0.003569  min_lr: 0.003569  loss: 2.7627 (2.6915)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [79]  [200/312]  eta: 0:00:54  lr: 0.003569  min_lr: 0.003569  loss: 2.6199 (2.6884)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [79]  [210/312]  eta: 0:00:49  lr: 0.003568  min_lr: 0.003568  loss: 2.6199 (2.6780)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [79]  [220/312]  eta: 0:00:44  lr: 0.003568  min_lr: 0.003568  loss: 2.6444 (2.6766)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [79]  [230/312]  eta: 0:00:39  lr: 0.003567  min_lr: 0.003567  loss: 2.6882 (2.6759)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [79]  [240/312]  eta: 0:00:34  lr: 0.003567  min_lr: 0.003567  loss: 2.7787 (2.6825)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0003  max mem: 42573
Epoch: [79]  [250/312]  eta: 0:00:29  lr: 0.003567  min_lr: 0.003567  loss: 2.7787 (2.6842)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [79]  [260/312]  eta: 0:00:24  lr: 0.003566  min_lr: 0.003566  loss: 2.7552 (2.6838)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [79]  [270/312]  eta: 0:00:19  lr: 0.003566  min_lr: 0.003566  loss: 2.7362 (2.6812)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [79]  [280/312]  eta: 0:00:15  lr: 0.003565  min_lr: 0.003565  loss: 2.7362 (2.6873)  weight_decay: 0.0500 (0.0500)  time: 0.4373  data: 0.0009  max mem: 42573
Epoch: [79]  [290/312]  eta: 0:00:10  lr: 0.003565  min_lr: 0.003565  loss: 2.8917 (2.6915)  weight_decay: 0.0500 (0.0500)  time: 0.4368  data: 0.0008  max mem: 42573
Epoch: [79]  [300/312]  eta: 0:00:05  lr: 0.003564  min_lr: 0.003564  loss: 2.8313 (2.6939)  weight_decay: 0.0500 (0.0500)  time: 0.4324  data: 0.0001  max mem: 42573
Epoch: [79]  [310/312]  eta: 0:00:00  lr: 0.003564  min_lr: 0.003564  loss: 2.6430 (2.6898)  weight_decay: 0.0500 (0.0500)  time: 0.4325  data: 0.0001  max mem: 42573
Epoch: [79]  [311/312]  eta: 0:00:00  lr: 0.003564  min_lr: 0.003564  loss: 2.7248 (2.6905)  weight_decay: 0.0500 (0.0500)  time: 0.4324  data: 0.0001  max mem: 42573
Epoch: [79] Total time: 0:02:27 (0.4724 s / it)
Averaged stats: lr: 0.003564  min_lr: 0.003564  loss: 2.7248 (2.6908)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:00:48  loss: 1.0444 (1.0444)  acc1: 75.2604 (75.2604)  acc5: 91.1458 (91.1458)  time: 5.3776  data: 5.2682  max mem: 42573
Test:  [8/9]  eta: 0:00:00  loss: 1.4334 (1.3140)  acc1: 67.9688 (68.1600)  acc5: 88.2812 (87.8720)  time: 0.6727  data: 0.5854  max mem: 42573
Test: Total time: 0:00:06 (0.6970 s / it)
* Acc@1 68.552 Acc@5 88.446 loss 1.293
Accuracy of the model on the 50000 test images: 68.6%
Max accuracy: 69.58%
Epoch: [80]  [  0/312]  eta: 0:49:12  lr: 0.003564  min_lr: 0.003564  loss: 1.8139 (1.8139)  weight_decay: 0.0500 (0.0500)  time: 9.4643  data: 6.9581  max mem: 42573
Epoch: [80]  [ 10/312]  eta: 0:07:15  lr: 0.003563  min_lr: 0.003563  loss: 2.8045 (2.6711)  weight_decay: 0.0500 (0.0500)  time: 1.4420  data: 0.7833  max mem: 42573
Epoch: [80]  [ 20/312]  eta: 0:04:40  lr: 0.003563  min_lr: 0.003563  loss: 2.7924 (2.5922)  weight_decay: 0.0500 (0.0500)  time: 0.5365  data: 0.0831  max mem: 42573
Epoch: [80]  [ 30/312]  eta: 0:03:43  lr: 0.003562  min_lr: 0.003562  loss: 2.6271 (2.6188)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0003  max mem: 42573
Epoch: [80]  [ 40/312]  eta: 0:03:11  lr: 0.003562  min_lr: 0.003562  loss: 2.6309 (2.6235)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [80]  [ 50/312]  eta: 0:02:50  lr: 0.003562  min_lr: 0.003562  loss: 2.3594 (2.5725)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [80]  [ 60/312]  eta: 0:02:35  lr: 0.003561  min_lr: 0.003561  loss: 2.5382 (2.6153)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [80]  [ 70/312]  eta: 0:02:22  lr: 0.003561  min_lr: 0.003561  loss: 2.7381 (2.6170)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [80]  [ 80/312]  eta: 0:02:12  lr: 0.003560  min_lr: 0.003560  loss: 2.7381 (2.6320)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [80]  [ 90/312]  eta: 0:02:03  lr: 0.003560  min_lr: 0.003560  loss: 2.6520 (2.6181)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [80]  [100/312]  eta: 0:01:55  lr: 0.003559  min_lr: 0.003559  loss: 2.6593 (2.6116)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0003  max mem: 42573
Epoch: [80]  [110/312]  eta: 0:01:47  lr: 0.003559  min_lr: 0.003559  loss: 2.6593 (2.6029)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0003  max mem: 42573
Epoch: [80]  [120/312]  eta: 0:01:40  lr: 0.003558  min_lr: 0.003558  loss: 2.2596 (2.5849)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0003  max mem: 42573
Epoch: [80]  [130/312]  eta: 0:01:34  lr: 0.003558  min_lr: 0.003558  loss: 2.5719 (2.5935)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [80]  [140/312]  eta: 0:01:28  lr: 0.003557  min_lr: 0.003557  loss: 2.7586 (2.6117)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [80]  [150/312]  eta: 0:01:22  lr: 0.003557  min_lr: 0.003557  loss: 2.7586 (2.6133)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [80]  [160/312]  eta: 0:01:16  lr: 0.003557  min_lr: 0.003557  loss: 2.6285 (2.6150)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0005  max mem: 42573
Epoch: [80]  [170/312]  eta: 0:01:10  lr: 0.003556  min_lr: 0.003556  loss: 2.7233 (2.6166)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0005  max mem: 42573
Epoch: [80]  [180/312]  eta: 0:01:05  lr: 0.003556  min_lr: 0.003556  loss: 2.8007 (2.6251)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [80]  [190/312]  eta: 0:00:59  lr: 0.003555  min_lr: 0.003555  loss: 2.8232 (2.6279)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [80]  [200/312]  eta: 0:00:54  lr: 0.003555  min_lr: 0.003555  loss: 2.8266 (2.6368)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [80]  [210/312]  eta: 0:00:49  lr: 0.003554  min_lr: 0.003554  loss: 2.8019 (2.6432)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [80]  [220/312]  eta: 0:00:44  lr: 0.003554  min_lr: 0.003554  loss: 2.7191 (2.6435)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [80]  [230/312]  eta: 0:00:39  lr: 0.003553  min_lr: 0.003553  loss: 2.5443 (2.6422)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [80]  [240/312]  eta: 0:00:34  lr: 0.003553  min_lr: 0.003553  loss: 2.8830 (2.6518)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [80]  [250/312]  eta: 0:00:29  lr: 0.003553  min_lr: 0.003553  loss: 2.8772 (2.6512)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [80]  [260/312]  eta: 0:00:24  lr: 0.003552  min_lr: 0.003552  loss: 2.7977 (2.6572)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [80]  [270/312]  eta: 0:00:19  lr: 0.003552  min_lr: 0.003552  loss: 2.7087 (2.6534)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [80]  [280/312]  eta: 0:00:15  lr: 0.003551  min_lr: 0.003551  loss: 2.5012 (2.6481)  weight_decay: 0.0500 (0.0500)  time: 0.4344  data: 0.0010  max mem: 42573
Epoch: [80]  [290/312]  eta: 0:00:10  lr: 0.003551  min_lr: 0.003551  loss: 2.7153 (2.6567)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0008  max mem: 42573
Epoch: [80]  [300/312]  eta: 0:00:05  lr: 0.003550  min_lr: 0.003550  loss: 2.7153 (2.6573)  weight_decay: 0.0500 (0.0500)  time: 0.4324  data: 0.0001  max mem: 42573
Epoch: [80]  [310/312]  eta: 0:00:00  lr: 0.003550  min_lr: 0.003550  loss: 2.6582 (2.6585)  weight_decay: 0.0500 (0.0500)  time: 0.4324  data: 0.0001  max mem: 42573
Epoch: [80]  [311/312]  eta: 0:00:00  lr: 0.003550  min_lr: 0.003550  loss: 2.6582 (2.6594)  weight_decay: 0.0500 (0.0500)  time: 0.4324  data: 0.0001  max mem: 42573
Epoch: [80] Total time: 0:02:27 (0.4722 s / it)
Averaged stats: lr: 0.003550  min_lr: 0.003550  loss: 2.6582 (2.6726)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:00:47  loss: 1.0878 (1.0878)  acc1: 76.3021 (76.3021)  acc5: 91.4062 (91.4062)  time: 5.2771  data: 5.1683  max mem: 42573
Test:  [8/9]  eta: 0:00:00  loss: 1.4807 (1.3996)  acc1: 64.5833 (66.1760)  acc5: 88.2812 (87.2000)  time: 0.6620  data: 0.5743  max mem: 42573
Test: Total time: 0:00:06 (0.6831 s / it)
* Acc@1 66.906 Acc@5 87.436 loss 1.390
Accuracy of the model on the 50000 test images: 66.9%
Max accuracy: 69.58%
Epoch: [81]  [  0/312]  eta: 0:47:50  lr: 0.003550  min_lr: 0.003550  loss: 2.2556 (2.2556)  weight_decay: 0.0500 (0.0500)  time: 9.1989  data: 6.2027  max mem: 42573
Epoch: [81]  [ 10/312]  eta: 0:07:10  lr: 0.003549  min_lr: 0.003549  loss: 2.9943 (2.8427)  weight_decay: 0.0500 (0.0500)  time: 1.4258  data: 0.5928  max mem: 42573
Epoch: [81]  [ 20/312]  eta: 0:04:39  lr: 0.003549  min_lr: 0.003549  loss: 2.9943 (2.7908)  weight_decay: 0.0500 (0.0500)  time: 0.5447  data: 0.0161  max mem: 42573
Epoch: [81]  [ 30/312]  eta: 0:03:42  lr: 0.003548  min_lr: 0.003548  loss: 2.7374 (2.7201)  weight_decay: 0.0500 (0.0500)  time: 0.4372  data: 0.0003  max mem: 42573
Epoch: [81]  [ 40/312]  eta: 0:03:10  lr: 0.003548  min_lr: 0.003548  loss: 2.6559 (2.7242)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0003  max mem: 42573
Epoch: [81]  [ 50/312]  eta: 0:02:50  lr: 0.003547  min_lr: 0.003547  loss: 2.8211 (2.7280)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [81]  [ 60/312]  eta: 0:02:34  lr: 0.003547  min_lr: 0.003547  loss: 2.7890 (2.7041)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [81]  [ 70/312]  eta: 0:02:22  lr: 0.003546  min_lr: 0.003546  loss: 2.8284 (2.7179)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [81]  [ 80/312]  eta: 0:02:12  lr: 0.003546  min_lr: 0.003546  loss: 2.8816 (2.7177)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [81]  [ 90/312]  eta: 0:02:03  lr: 0.003546  min_lr: 0.003546  loss: 2.8701 (2.7491)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [81]  [100/312]  eta: 0:01:54  lr: 0.003545  min_lr: 0.003545  loss: 2.9488 (2.7636)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [81]  [110/312]  eta: 0:01:47  lr: 0.003545  min_lr: 0.003545  loss: 2.8846 (2.7597)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [81]  [120/312]  eta: 0:01:40  lr: 0.003544  min_lr: 0.003544  loss: 2.6775 (2.7550)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [81]  [130/312]  eta: 0:01:34  lr: 0.003544  min_lr: 0.003544  loss: 2.8160 (2.7554)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [81]  [140/312]  eta: 0:01:27  lr: 0.003543  min_lr: 0.003543  loss: 2.4828 (2.7132)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [81]  [150/312]  eta: 0:01:22  lr: 0.003543  min_lr: 0.003543  loss: 2.3918 (2.7059)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0005  max mem: 42573
Epoch: [81]  [160/312]  eta: 0:01:16  lr: 0.003542  min_lr: 0.003542  loss: 2.6895 (2.6983)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [81]  [170/312]  eta: 0:01:10  lr: 0.003542  min_lr: 0.003542  loss: 2.7245 (2.7010)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [81]  [180/312]  eta: 0:01:05  lr: 0.003541  min_lr: 0.003541  loss: 2.7440 (2.6981)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [81]  [190/312]  eta: 0:00:59  lr: 0.003541  min_lr: 0.003541  loss: 2.6668 (2.6956)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [81]  [200/312]  eta: 0:00:54  lr: 0.003541  min_lr: 0.003541  loss: 2.7065 (2.6977)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [81]  [210/312]  eta: 0:00:49  lr: 0.003540  min_lr: 0.003540  loss: 2.8474 (2.7038)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [81]  [220/312]  eta: 0:00:44  lr: 0.003540  min_lr: 0.003540  loss: 2.8963 (2.7099)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [81]  [230/312]  eta: 0:00:39  lr: 0.003539  min_lr: 0.003539  loss: 2.8654 (2.7078)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [81]  [240/312]  eta: 0:00:34  lr: 0.003539  min_lr: 0.003539  loss: 2.8519 (2.7134)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [81]  [250/312]  eta: 0:00:29  lr: 0.003538  min_lr: 0.003538  loss: 2.8519 (2.7068)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [81]  [260/312]  eta: 0:00:24  lr: 0.003538  min_lr: 0.003538  loss: 2.6339 (2.7027)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [81]  [270/312]  eta: 0:00:19  lr: 0.003537  min_lr: 0.003537  loss: 2.5921 (2.6950)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [81]  [280/312]  eta: 0:00:15  lr: 0.003537  min_lr: 0.003537  loss: 2.6613 (2.6960)  weight_decay: 0.0500 (0.0500)  time: 0.4342  data: 0.0010  max mem: 42573
Epoch: [81]  [290/312]  eta: 0:00:10  lr: 0.003536  min_lr: 0.003536  loss: 2.6753 (2.6895)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0009  max mem: 42573
Epoch: [81]  [300/312]  eta: 0:00:05  lr: 0.003536  min_lr: 0.003536  loss: 2.7711 (2.6944)  weight_decay: 0.0500 (0.0500)  time: 0.4324  data: 0.0001  max mem: 42573
Epoch: [81]  [310/312]  eta: 0:00:00  lr: 0.003535  min_lr: 0.003535  loss: 2.8745 (2.7019)  weight_decay: 0.0500 (0.0500)  time: 0.4323  data: 0.0001  max mem: 42573
Epoch: [81]  [311/312]  eta: 0:00:00  lr: 0.003535  min_lr: 0.003535  loss: 2.8712 (2.7023)  weight_decay: 0.0500 (0.0500)  time: 0.4324  data: 0.0001  max mem: 42573
Epoch: [81] Total time: 0:02:27 (0.4718 s / it)
Averaged stats: lr: 0.003535  min_lr: 0.003535  loss: 2.8712 (2.6723)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:00:42  loss: 1.1193 (1.1193)  acc1: 74.7396 (74.7396)  acc5: 90.6250 (90.6250)  time: 4.7688  data: 4.6592  max mem: 42573
Test:  [8/9]  eta: 0:00:00  loss: 1.4927 (1.4256)  acc1: 64.8438 (66.1440)  acc5: 86.1979 (86.8160)  time: 0.6058  data: 0.5178  max mem: 42573
Test: Total time: 0:00:05 (0.6642 s / it)
* Acc@1 66.480 Acc@5 87.274 loss 1.423
Accuracy of the model on the 50000 test images: 66.5%
Max accuracy: 69.58%
Epoch: [82]  [  0/312]  eta: 0:47:28  lr: 0.003535  min_lr: 0.003535  loss: 2.7889 (2.7889)  weight_decay: 0.0500 (0.0500)  time: 9.1292  data: 6.1699  max mem: 42573
Epoch: [82]  [ 10/312]  eta: 0:07:04  lr: 0.003535  min_lr: 0.003535  loss: 2.8477 (2.6742)  weight_decay: 0.0500 (0.0500)  time: 1.4070  data: 0.6745  max mem: 42573
Epoch: [82]  [ 20/312]  eta: 0:04:35  lr: 0.003534  min_lr: 0.003534  loss: 2.8512 (2.8103)  weight_decay: 0.0500 (0.0500)  time: 0.5341  data: 0.0627  max mem: 42573
Epoch: [82]  [ 30/312]  eta: 0:03:39  lr: 0.003534  min_lr: 0.003534  loss: 2.8143 (2.6873)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [82]  [ 40/312]  eta: 0:03:08  lr: 0.003534  min_lr: 0.003534  loss: 2.7656 (2.7165)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [82]  [ 50/312]  eta: 0:02:48  lr: 0.003533  min_lr: 0.003533  loss: 2.7788 (2.7232)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [82]  [ 60/312]  eta: 0:02:33  lr: 0.003533  min_lr: 0.003533  loss: 2.7216 (2.6895)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [82]  [ 70/312]  eta: 0:02:21  lr: 0.003532  min_lr: 0.003532  loss: 2.7117 (2.6878)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0003  max mem: 42573
Epoch: [82]  [ 80/312]  eta: 0:02:11  lr: 0.003532  min_lr: 0.003532  loss: 2.7406 (2.6902)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0003  max mem: 42573
Epoch: [82]  [ 90/312]  eta: 0:02:02  lr: 0.003531  min_lr: 0.003531  loss: 2.7406 (2.6827)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [82]  [100/312]  eta: 0:01:54  lr: 0.003531  min_lr: 0.003531  loss: 2.6017 (2.6604)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [82]  [110/312]  eta: 0:01:47  lr: 0.003530  min_lr: 0.003530  loss: 2.3895 (2.6501)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [82]  [120/312]  eta: 0:01:40  lr: 0.003530  min_lr: 0.003530  loss: 2.6672 (2.6521)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [82]  [130/312]  eta: 0:01:33  lr: 0.003529  min_lr: 0.003529  loss: 2.7760 (2.6571)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [82]  [140/312]  eta: 0:01:27  lr: 0.003529  min_lr: 0.003529  loss: 2.7938 (2.6623)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0004  max mem: 42573
Epoch: [82]  [150/312]  eta: 0:01:21  lr: 0.003528  min_lr: 0.003528  loss: 2.7331 (2.6540)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [82]  [160/312]  eta: 0:01:16  lr: 0.003528  min_lr: 0.003528  loss: 2.1924 (2.6334)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0003  max mem: 42573
Epoch: [82]  [170/312]  eta: 0:01:10  lr: 0.003528  min_lr: 0.003528  loss: 2.4089 (2.6332)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0003  max mem: 42573
Epoch: [82]  [180/312]  eta: 0:01:05  lr: 0.003527  min_lr: 0.003527  loss: 2.5972 (2.6334)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [82]  [190/312]  eta: 0:00:59  lr: 0.003527  min_lr: 0.003527  loss: 2.5972 (2.6323)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [82]  [200/312]  eta: 0:00:54  lr: 0.003526  min_lr: 0.003526  loss: 2.6053 (2.6281)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [82]  [210/312]  eta: 0:00:49  lr: 0.003526  min_lr: 0.003526  loss: 2.7768 (2.6378)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [82]  [220/312]  eta: 0:00:44  lr: 0.003525  min_lr: 0.003525  loss: 2.8617 (2.6407)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0003  max mem: 42573
Epoch: [82]  [230/312]  eta: 0:00:39  lr: 0.003525  min_lr: 0.003525  loss: 2.6296 (2.6321)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [82]  [240/312]  eta: 0:00:34  lr: 0.003524  min_lr: 0.003524  loss: 2.6818 (2.6398)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0004  max mem: 42573
Epoch: [82]  [250/312]  eta: 0:00:29  lr: 0.003524  min_lr: 0.003524  loss: 2.8565 (2.6509)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0003  max mem: 42573
Epoch: [82]  [260/312]  eta: 0:00:24  lr: 0.003523  min_lr: 0.003523  loss: 2.9121 (2.6602)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [82]  [270/312]  eta: 0:00:19  lr: 0.003523  min_lr: 0.003523  loss: 2.8772 (2.6636)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [82]  [280/312]  eta: 0:00:15  lr: 0.003522  min_lr: 0.003522  loss: 2.8207 (2.6647)  weight_decay: 0.0500 (0.0500)  time: 0.4342  data: 0.0009  max mem: 42573
Epoch: [82]  [290/312]  eta: 0:00:10  lr: 0.003522  min_lr: 0.003522  loss: 2.7753 (2.6684)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0008  max mem: 42573
Epoch: [82]  [300/312]  eta: 0:00:05  lr: 0.003521  min_lr: 0.003521  loss: 2.6291 (2.6661)  weight_decay: 0.0500 (0.0500)  time: 0.4324  data: 0.0001  max mem: 42573
Epoch: [82]  [310/312]  eta: 0:00:00  lr: 0.003521  min_lr: 0.003521  loss: 2.6194 (2.6637)  weight_decay: 0.0500 (0.0500)  time: 0.4324  data: 0.0001  max mem: 42573
Epoch: [82]  [311/312]  eta: 0:00:00  lr: 0.003521  min_lr: 0.003521  loss: 2.6194 (2.6621)  weight_decay: 0.0500 (0.0500)  time: 0.4324  data: 0.0001  max mem: 42573
Epoch: [82] Total time: 0:02:26 (0.4710 s / it)
Averaged stats: lr: 0.003521  min_lr: 0.003521  loss: 2.6194 (2.6867)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:00:46  loss: 1.1430 (1.1430)  acc1: 73.4375 (73.4375)  acc5: 91.1458 (91.1458)  time: 5.1624  data: 5.0530  max mem: 42573
Test:  [8/9]  eta: 0:00:00  loss: 1.4000 (1.3331)  acc1: 68.2292 (67.1360)  acc5: 87.7604 (87.9360)  time: 0.6537  data: 0.5615  max mem: 42573
Test: Total time: 0:00:06 (0.6748 s / it)
* Acc@1 67.612 Acc@5 87.732 loss 1.350
Accuracy of the model on the 50000 test images: 67.6%
Max accuracy: 69.58%
Epoch: [83]  [  0/312]  eta: 0:49:16  lr: 0.003521  min_lr: 0.003521  loss: 3.3019 (3.3019)  weight_decay: 0.0500 (0.0500)  time: 9.4765  data: 6.6100  max mem: 42573
Epoch: [83]  [ 10/312]  eta: 0:07:00  lr: 0.003520  min_lr: 0.003520  loss: 2.8894 (2.8086)  weight_decay: 0.0500 (0.0500)  time: 1.3910  data: 0.6014  max mem: 42573
Epoch: [83]  [ 20/312]  eta: 0:04:35  lr: 0.003520  min_lr: 0.003520  loss: 2.6634 (2.7503)  weight_decay: 0.0500 (0.0500)  time: 0.5178  data: 0.0004  max mem: 42573
Epoch: [83]  [ 30/312]  eta: 0:03:39  lr: 0.003520  min_lr: 0.003520  loss: 2.8079 (2.7268)  weight_decay: 0.0500 (0.0500)  time: 0.4432  data: 0.0005  max mem: 42573
Epoch: [83]  [ 40/312]  eta: 0:03:09  lr: 0.003519  min_lr: 0.003519  loss: 2.7083 (2.6961)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0005  max mem: 42573
Epoch: [83]  [ 50/312]  eta: 0:02:48  lr: 0.003519  min_lr: 0.003519  loss: 2.5212 (2.6877)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [83]  [ 60/312]  eta: 0:02:33  lr: 0.003518  min_lr: 0.003518  loss: 2.5586 (2.6849)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [83]  [ 70/312]  eta: 0:02:21  lr: 0.003518  min_lr: 0.003518  loss: 2.7740 (2.6806)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [83]  [ 80/312]  eta: 0:02:11  lr: 0.003517  min_lr: 0.003517  loss: 2.7740 (2.6900)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [83]  [ 90/312]  eta: 0:02:02  lr: 0.003517  min_lr: 0.003517  loss: 2.8098 (2.7040)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0004  max mem: 42573
Epoch: [83]  [100/312]  eta: 0:01:54  lr: 0.003516  min_lr: 0.003516  loss: 2.7876 (2.6896)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [83]  [110/312]  eta: 0:01:47  lr: 0.003516  min_lr: 0.003516  loss: 2.5685 (2.6735)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [83]  [120/312]  eta: 0:01:40  lr: 0.003515  min_lr: 0.003515  loss: 2.5685 (2.6714)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [83]  [130/312]  eta: 0:01:33  lr: 0.003515  min_lr: 0.003515  loss: 2.8363 (2.6754)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [83]  [140/312]  eta: 0:01:27  lr: 0.003514  min_lr: 0.003514  loss: 2.6013 (2.6670)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [83]  [150/312]  eta: 0:01:21  lr: 0.003514  min_lr: 0.003514  loss: 2.5135 (2.6578)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [83]  [160/312]  eta: 0:01:16  lr: 0.003513  min_lr: 0.003513  loss: 2.6739 (2.6669)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [83]  [170/312]  eta: 0:01:10  lr: 0.003513  min_lr: 0.003513  loss: 2.8389 (2.6799)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [83]  [180/312]  eta: 0:01:05  lr: 0.003512  min_lr: 0.003512  loss: 2.8389 (2.6810)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [83]  [190/312]  eta: 0:00:59  lr: 0.003512  min_lr: 0.003512  loss: 2.6566 (2.6750)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [83]  [200/312]  eta: 0:00:54  lr: 0.003512  min_lr: 0.003512  loss: 2.4785 (2.6626)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [83]  [210/312]  eta: 0:00:49  lr: 0.003511  min_lr: 0.003511  loss: 2.6295 (2.6685)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [83]  [220/312]  eta: 0:00:44  lr: 0.003511  min_lr: 0.003511  loss: 2.8087 (2.6658)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [83]  [230/312]  eta: 0:00:39  lr: 0.003510  min_lr: 0.003510  loss: 2.4190 (2.6545)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [83]  [240/312]  eta: 0:00:34  lr: 0.003510  min_lr: 0.003510  loss: 2.4190 (2.6480)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [83]  [250/312]  eta: 0:00:29  lr: 0.003509  min_lr: 0.003509  loss: 2.6608 (2.6423)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [83]  [260/312]  eta: 0:00:24  lr: 0.003509  min_lr: 0.003509  loss: 2.4168 (2.6306)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [83]  [270/312]  eta: 0:00:19  lr: 0.003508  min_lr: 0.003508  loss: 2.3489 (2.6269)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [83]  [280/312]  eta: 0:00:15  lr: 0.003508  min_lr: 0.003508  loss: 2.7344 (2.6296)  weight_decay: 0.0500 (0.0500)  time: 0.4345  data: 0.0009  max mem: 42573
Epoch: [83]  [290/312]  eta: 0:00:10  lr: 0.003507  min_lr: 0.003507  loss: 2.8334 (2.6311)  weight_decay: 0.0500 (0.0500)  time: 0.4341  data: 0.0008  max mem: 42573
Epoch: [83]  [300/312]  eta: 0:00:05  lr: 0.003507  min_lr: 0.003507  loss: 2.7570 (2.6308)  weight_decay: 0.0500 (0.0500)  time: 0.4326  data: 0.0001  max mem: 42573
Epoch: [83]  [310/312]  eta: 0:00:00  lr: 0.003506  min_lr: 0.003506  loss: 2.7207 (2.6337)  weight_decay: 0.0500 (0.0500)  time: 0.4325  data: 0.0001  max mem: 42573
Epoch: [83]  [311/312]  eta: 0:00:00  lr: 0.003506  min_lr: 0.003506  loss: 2.7207 (2.6341)  weight_decay: 0.0500 (0.0500)  time: 0.4324  data: 0.0001  max mem: 42573
Epoch: [83] Total time: 0:02:26 (0.4708 s / it)
Averaged stats: lr: 0.003506  min_lr: 0.003506  loss: 2.7207 (2.6535)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:00:41  loss: 1.0792 (1.0792)  acc1: 77.0833 (77.0833)  acc5: 91.1458 (91.1458)  time: 4.6112  data: 4.5023  max mem: 42573
Test:  [8/9]  eta: 0:00:00  loss: 1.5314 (1.3811)  acc1: 64.5833 (66.2720)  acc5: 86.1979 (87.1680)  time: 0.5895  data: 0.5003  max mem: 42573
Test: Total time: 0:00:05 (0.5972 s / it)
* Acc@1 66.948 Acc@5 87.504 loss 1.387
Accuracy of the model on the 50000 test images: 66.9%
Max accuracy: 69.58%
Epoch: [84]  [  0/312]  eta: 0:49:18  lr: 0.003506  min_lr: 0.003506  loss: 2.1731 (2.1731)  weight_decay: 0.0500 (0.0500)  time: 9.4834  data: 8.9325  max mem: 42573
Epoch: [84]  [ 10/312]  eta: 0:07:17  lr: 0.003506  min_lr: 0.003506  loss: 2.6675 (2.6830)  weight_decay: 0.0500 (0.0500)  time: 1.4486  data: 0.8125  max mem: 42573
Epoch: [84]  [ 20/312]  eta: 0:04:41  lr: 0.003505  min_lr: 0.003505  loss: 2.6163 (2.6054)  weight_decay: 0.0500 (0.0500)  time: 0.5394  data: 0.0004  max mem: 42573
Epoch: [84]  [ 30/312]  eta: 0:03:43  lr: 0.003505  min_lr: 0.003505  loss: 2.8350 (2.7264)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [84]  [ 40/312]  eta: 0:03:11  lr: 0.003504  min_lr: 0.003504  loss: 2.8474 (2.7201)  weight_decay: 0.0500 (0.0500)  time: 0.4332  data: 0.0004  max mem: 42573
Epoch: [84]  [ 50/312]  eta: 0:02:50  lr: 0.003504  min_lr: 0.003504  loss: 2.7467 (2.7045)  weight_decay: 0.0500 (0.0500)  time: 0.4332  data: 0.0004  max mem: 42573
Epoch: [84]  [ 60/312]  eta: 0:02:35  lr: 0.003503  min_lr: 0.003503  loss: 2.7425 (2.6762)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [84]  [ 70/312]  eta: 0:02:22  lr: 0.003503  min_lr: 0.003503  loss: 2.7586 (2.6740)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [84]  [ 80/312]  eta: 0:02:12  lr: 0.003502  min_lr: 0.003502  loss: 2.7607 (2.6737)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [84]  [ 90/312]  eta: 0:02:03  lr: 0.003502  min_lr: 0.003502  loss: 2.8006 (2.6629)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [84]  [100/312]  eta: 0:01:55  lr: 0.003502  min_lr: 0.003502  loss: 2.5047 (2.6402)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [84]  [110/312]  eta: 0:01:47  lr: 0.003501  min_lr: 0.003501  loss: 2.4061 (2.6264)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [84]  [120/312]  eta: 0:01:40  lr: 0.003501  min_lr: 0.003501  loss: 2.5260 (2.6335)  weight_decay: 0.0500 (0.0500)  time: 0.4342  data: 0.0004  max mem: 42573
Epoch: [84]  [130/312]  eta: 0:01:34  lr: 0.003500  min_lr: 0.003500  loss: 2.7613 (2.6379)  weight_decay: 0.0500 (0.0500)  time: 0.4342  data: 0.0004  max mem: 42573
Epoch: [84]  [140/312]  eta: 0:01:28  lr: 0.003500  min_lr: 0.003500  loss: 2.7613 (2.6508)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0003  max mem: 42573
Epoch: [84]  [150/312]  eta: 0:01:22  lr: 0.003499  min_lr: 0.003499  loss: 3.0296 (2.6626)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [84]  [160/312]  eta: 0:01:16  lr: 0.003499  min_lr: 0.003499  loss: 2.7837 (2.6658)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [84]  [170/312]  eta: 0:01:10  lr: 0.003498  min_lr: 0.003498  loss: 2.7059 (2.6608)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [84]  [180/312]  eta: 0:01:05  lr: 0.003498  min_lr: 0.003498  loss: 2.6940 (2.6576)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [84]  [190/312]  eta: 0:01:00  lr: 0.003497  min_lr: 0.003497  loss: 2.5285 (2.6502)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [84]  [200/312]  eta: 0:00:54  lr: 0.003497  min_lr: 0.003497  loss: 2.5482 (2.6508)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0003  max mem: 42573
Epoch: [84]  [210/312]  eta: 0:00:49  lr: 0.003496  min_lr: 0.003496  loss: 2.5800 (2.6463)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [84]  [220/312]  eta: 0:00:44  lr: 0.003496  min_lr: 0.003496  loss: 2.6153 (2.6535)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [84]  [230/312]  eta: 0:00:39  lr: 0.003495  min_lr: 0.003495  loss: 2.6494 (2.6531)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [84]  [240/312]  eta: 0:00:34  lr: 0.003495  min_lr: 0.003495  loss: 2.6223 (2.6528)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0003  max mem: 42573
Epoch: [84]  [250/312]  eta: 0:00:29  lr: 0.003494  min_lr: 0.003494  loss: 2.6223 (2.6534)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [84]  [260/312]  eta: 0:00:24  lr: 0.003494  min_lr: 0.003494  loss: 2.7174 (2.6548)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [84]  [270/312]  eta: 0:00:19  lr: 0.003493  min_lr: 0.003493  loss: 2.9228 (2.6657)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [84]  [280/312]  eta: 0:00:15  lr: 0.003493  min_lr: 0.003493  loss: 2.9439 (2.6681)  weight_decay: 0.0500 (0.0500)  time: 0.4346  data: 0.0009  max mem: 42573
Epoch: [84]  [290/312]  eta: 0:00:10  lr: 0.003492  min_lr: 0.003492  loss: 2.8998 (2.6743)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0008  max mem: 42573
Epoch: [84]  [300/312]  eta: 0:00:05  lr: 0.003492  min_lr: 0.003492  loss: 2.5978 (2.6615)  weight_decay: 0.0500 (0.0500)  time: 0.4324  data: 0.0001  max mem: 42573
Epoch: [84]  [310/312]  eta: 0:00:00  lr: 0.003492  min_lr: 0.003492  loss: 2.3315 (2.6586)  weight_decay: 0.0500 (0.0500)  time: 0.4324  data: 0.0001  max mem: 42573
Epoch: [84]  [311/312]  eta: 0:00:00  lr: 0.003491  min_lr: 0.003491  loss: 2.3315 (2.6585)  weight_decay: 0.0500 (0.0500)  time: 0.4324  data: 0.0001  max mem: 42573
Epoch: [84] Total time: 0:02:27 (0.4723 s / it)
Averaged stats: lr: 0.003491  min_lr: 0.003491  loss: 2.3315 (2.6574)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:00:42  loss: 0.9686 (0.9686)  acc1: 75.2604 (75.2604)  acc5: 92.1875 (92.1875)  time: 4.7491  data: 4.6395  max mem: 42573
Test:  [8/9]  eta: 0:00:00  loss: 1.3174 (1.2742)  acc1: 70.0521 (68.7040)  acc5: 87.5000 (88.9600)  time: 0.6292  data: 0.5356  max mem: 42573
Test: Total time: 0:00:05 (0.6383 s / it)
* Acc@1 69.054 Acc@5 88.844 loss 1.259
Accuracy of the model on the 50000 test images: 69.1%
Max accuracy: 69.58%
Epoch: [85]  [  0/312]  eta: 0:48:06  lr: 0.003491  min_lr: 0.003491  loss: 2.9309 (2.9309)  weight_decay: 0.0500 (0.0500)  time: 9.2521  data: 8.3874  max mem: 42573
Epoch: [85]  [ 10/312]  eta: 0:07:02  lr: 0.003491  min_lr: 0.003491  loss: 2.3790 (2.3717)  weight_decay: 0.0500 (0.0500)  time: 1.4006  data: 0.7713  max mem: 42573
Epoch: [85]  [ 20/312]  eta: 0:04:34  lr: 0.003490  min_lr: 0.003490  loss: 2.5366 (2.4999)  weight_decay: 0.0500 (0.0500)  time: 0.5245  data: 0.0052  max mem: 42573
Epoch: [85]  [ 30/312]  eta: 0:03:39  lr: 0.003490  min_lr: 0.003490  loss: 2.5923 (2.5413)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0005  max mem: 42573
Epoch: [85]  [ 40/312]  eta: 0:03:08  lr: 0.003489  min_lr: 0.003489  loss: 2.6782 (2.5260)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [85]  [ 50/312]  eta: 0:02:48  lr: 0.003489  min_lr: 0.003489  loss: 2.7098 (2.5628)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [85]  [ 60/312]  eta: 0:02:33  lr: 0.003489  min_lr: 0.003489  loss: 2.3898 (2.5350)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [85]  [ 70/312]  eta: 0:02:21  lr: 0.003488  min_lr: 0.003488  loss: 2.5384 (2.5635)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [85]  [ 80/312]  eta: 0:02:11  lr: 0.003488  min_lr: 0.003488  loss: 2.7053 (2.5592)  weight_decay: 0.0500 (0.0500)  time: 0.4429  data: 0.0004  max mem: 42573
Epoch: [85]  [ 90/312]  eta: 0:02:02  lr: 0.003487  min_lr: 0.003487  loss: 2.4714 (2.5527)  weight_decay: 0.0500 (0.0500)  time: 0.4428  data: 0.0004  max mem: 42573
Epoch: [85]  [100/312]  eta: 0:01:54  lr: 0.003487  min_lr: 0.003487  loss: 2.5329 (2.5491)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [85]  [110/312]  eta: 0:01:47  lr: 0.003486  min_lr: 0.003486  loss: 2.5803 (2.5581)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [85]  [120/312]  eta: 0:01:40  lr: 0.003486  min_lr: 0.003486  loss: 2.7070 (2.5578)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [85]  [130/312]  eta: 0:01:33  lr: 0.003485  min_lr: 0.003485  loss: 2.7359 (2.5719)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [85]  [140/312]  eta: 0:01:27  lr: 0.003485  min_lr: 0.003485  loss: 2.7639 (2.5749)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [85]  [150/312]  eta: 0:01:21  lr: 0.003484  min_lr: 0.003484  loss: 2.7368 (2.5724)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0003  max mem: 42573
Epoch: [85]  [160/312]  eta: 0:01:16  lr: 0.003484  min_lr: 0.003484  loss: 2.5499 (2.5725)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0003  max mem: 42573
Epoch: [85]  [170/312]  eta: 0:01:10  lr: 0.003483  min_lr: 0.003483  loss: 2.5499 (2.5693)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0003  max mem: 42573
Epoch: [85]  [180/312]  eta: 0:01:05  lr: 0.003483  min_lr: 0.003483  loss: 2.7269 (2.5734)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0003  max mem: 42573
Epoch: [85]  [190/312]  eta: 0:00:59  lr: 0.003482  min_lr: 0.003482  loss: 2.7378 (2.5813)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0003  max mem: 42573
Epoch: [85]  [200/312]  eta: 0:00:54  lr: 0.003482  min_lr: 0.003482  loss: 2.7694 (2.5833)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [85]  [210/312]  eta: 0:00:49  lr: 0.003481  min_lr: 0.003481  loss: 2.5716 (2.5825)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [85]  [220/312]  eta: 0:00:44  lr: 0.003481  min_lr: 0.003481  loss: 2.5565 (2.5826)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [85]  [230/312]  eta: 0:00:39  lr: 0.003480  min_lr: 0.003480  loss: 2.6179 (2.5874)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [85]  [240/312]  eta: 0:00:34  lr: 0.003480  min_lr: 0.003480  loss: 2.6927 (2.5887)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [85]  [250/312]  eta: 0:00:29  lr: 0.003479  min_lr: 0.003479  loss: 2.4055 (2.5862)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0003  max mem: 42573
Epoch: [85]  [260/312]  eta: 0:00:24  lr: 0.003479  min_lr: 0.003479  loss: 2.4333 (2.5863)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0003  max mem: 42573
Epoch: [85]  [270/312]  eta: 0:00:19  lr: 0.003478  min_lr: 0.003478  loss: 2.7509 (2.5858)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [85]  [280/312]  eta: 0:00:15  lr: 0.003478  min_lr: 0.003478  loss: 2.8249 (2.5968)  weight_decay: 0.0500 (0.0500)  time: 0.4345  data: 0.0010  max mem: 42573
Epoch: [85]  [290/312]  eta: 0:00:10  lr: 0.003477  min_lr: 0.003477  loss: 2.8249 (2.5992)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0009  max mem: 42573
Epoch: [85]  [300/312]  eta: 0:00:05  lr: 0.003477  min_lr: 0.003477  loss: 2.8175 (2.6007)  weight_decay: 0.0500 (0.0500)  time: 0.4325  data: 0.0001  max mem: 42573
Epoch: [85]  [310/312]  eta: 0:00:00  lr: 0.003476  min_lr: 0.003476  loss: 2.5668 (2.5987)  weight_decay: 0.0500 (0.0500)  time: 0.4324  data: 0.0001  max mem: 42573
Epoch: [85]  [311/312]  eta: 0:00:00  lr: 0.003476  min_lr: 0.003476  loss: 2.6235 (2.5998)  weight_decay: 0.0500 (0.0500)  time: 0.4324  data: 0.0001  max mem: 42573
Epoch: [85] Total time: 0:02:27 (0.4714 s / it)
Averaged stats: lr: 0.003476  min_lr: 0.003476  loss: 2.6235 (2.6538)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:00:45  loss: 1.0283 (1.0283)  acc1: 76.3021 (76.3021)  acc5: 91.4062 (91.4062)  time: 5.0343  data: 4.9250  max mem: 42573
Test:  [8/9]  eta: 0:00:00  loss: 1.2736 (1.2852)  acc1: 69.2708 (68.5120)  acc5: 88.2812 (88.2560)  time: 0.6356  data: 0.5473  max mem: 42573
Test: Total time: 0:00:05 (0.6477 s / it)
* Acc@1 68.910 Acc@5 88.592 loss 1.260
Accuracy of the model on the 50000 test images: 68.9%
Max accuracy: 69.58%
Epoch: [86]  [  0/312]  eta: 0:50:26  lr: 0.003476  min_lr: 0.003476  loss: 2.5264 (2.5264)  weight_decay: 0.0500 (0.0500)  time: 9.6990  data: 8.1983  max mem: 42573
Epoch: [86]  [ 10/312]  eta: 0:06:58  lr: 0.003476  min_lr: 0.003476  loss: 2.7939 (2.7955)  weight_decay: 0.0500 (0.0500)  time: 1.3865  data: 0.7457  max mem: 42573
Epoch: [86]  [ 20/312]  eta: 0:04:32  lr: 0.003475  min_lr: 0.003475  loss: 2.7939 (2.7169)  weight_decay: 0.0500 (0.0500)  time: 0.4945  data: 0.0004  max mem: 42573
Epoch: [86]  [ 30/312]  eta: 0:03:38  lr: 0.003475  min_lr: 0.003475  loss: 2.7902 (2.6840)  weight_decay: 0.0500 (0.0500)  time: 0.4377  data: 0.0004  max mem: 42573
Epoch: [86]  [ 40/312]  eta: 0:03:08  lr: 0.003474  min_lr: 0.003474  loss: 2.7177 (2.6788)  weight_decay: 0.0500 (0.0500)  time: 0.4376  data: 0.0004  max mem: 42573
Epoch: [86]  [ 50/312]  eta: 0:02:47  lr: 0.003474  min_lr: 0.003474  loss: 2.8456 (2.7117)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [86]  [ 60/312]  eta: 0:02:32  lr: 0.003473  min_lr: 0.003473  loss: 2.8810 (2.7149)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [86]  [ 70/312]  eta: 0:02:20  lr: 0.003473  min_lr: 0.003473  loss: 2.8043 (2.7241)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [86]  [ 80/312]  eta: 0:02:10  lr: 0.003472  min_lr: 0.003472  loss: 2.8406 (2.7440)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [86]  [ 90/312]  eta: 0:02:02  lr: 0.003472  min_lr: 0.003472  loss: 2.6778 (2.7147)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [86]  [100/312]  eta: 0:01:54  lr: 0.003472  min_lr: 0.003472  loss: 2.5994 (2.7164)  weight_decay: 0.0500 (0.0500)  time: 0.4365  data: 0.0004  max mem: 42573
Epoch: [86]  [110/312]  eta: 0:01:46  lr: 0.003471  min_lr: 0.003471  loss: 2.5881 (2.6934)  weight_decay: 0.0500 (0.0500)  time: 0.4365  data: 0.0004  max mem: 42573
Epoch: [86]  [120/312]  eta: 0:01:40  lr: 0.003471  min_lr: 0.003471  loss: 2.7773 (2.7009)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [86]  [130/312]  eta: 0:01:33  lr: 0.003470  min_lr: 0.003470  loss: 2.8339 (2.6969)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [86]  [140/312]  eta: 0:01:27  lr: 0.003470  min_lr: 0.003470  loss: 2.6344 (2.7005)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [86]  [150/312]  eta: 0:01:21  lr: 0.003469  min_lr: 0.003469  loss: 2.6058 (2.6904)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [86]  [160/312]  eta: 0:01:15  lr: 0.003469  min_lr: 0.003469  loss: 2.7210 (2.6963)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [86]  [170/312]  eta: 0:01:10  lr: 0.003468  min_lr: 0.003468  loss: 2.9922 (2.6982)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [86]  [180/312]  eta: 0:01:04  lr: 0.003468  min_lr: 0.003468  loss: 2.8236 (2.6985)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [86]  [190/312]  eta: 0:00:59  lr: 0.003467  min_lr: 0.003467  loss: 2.5986 (2.6972)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [86]  [200/312]  eta: 0:00:54  lr: 0.003467  min_lr: 0.003467  loss: 2.4463 (2.6931)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [86]  [210/312]  eta: 0:00:49  lr: 0.003466  min_lr: 0.003466  loss: 2.8486 (2.6978)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0005  max mem: 42573
Epoch: [86]  [220/312]  eta: 0:00:44  lr: 0.003466  min_lr: 0.003466  loss: 2.7378 (2.6919)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0005  max mem: 42573
Epoch: [86]  [230/312]  eta: 0:00:39  lr: 0.003465  min_lr: 0.003465  loss: 2.6705 (2.6947)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0005  max mem: 42573
Epoch: [86]  [240/312]  eta: 0:00:34  lr: 0.003465  min_lr: 0.003465  loss: 2.6705 (2.6925)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [86]  [250/312]  eta: 0:00:29  lr: 0.003464  min_lr: 0.003464  loss: 2.6558 (2.6960)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [86]  [260/312]  eta: 0:00:24  lr: 0.003464  min_lr: 0.003464  loss: 2.8591 (2.6960)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [86]  [270/312]  eta: 0:00:19  lr: 0.003463  min_lr: 0.003463  loss: 2.4950 (2.6844)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [86]  [280/312]  eta: 0:00:15  lr: 0.003463  min_lr: 0.003463  loss: 2.4950 (2.6822)  weight_decay: 0.0500 (0.0500)  time: 0.4346  data: 0.0009  max mem: 42573
Epoch: [86]  [290/312]  eta: 0:00:10  lr: 0.003462  min_lr: 0.003462  loss: 2.6583 (2.6806)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0008  max mem: 42573
Epoch: [86]  [300/312]  eta: 0:00:05  lr: 0.003462  min_lr: 0.003462  loss: 2.7317 (2.6823)  weight_decay: 0.0500 (0.0500)  time: 0.4324  data: 0.0001  max mem: 42573
Epoch: [86]  [310/312]  eta: 0:00:00  lr: 0.003461  min_lr: 0.003461  loss: 2.7671 (2.6798)  weight_decay: 0.0500 (0.0500)  time: 0.4322  data: 0.0001  max mem: 42573
Epoch: [86]  [311/312]  eta: 0:00:00  lr: 0.003461  min_lr: 0.003461  loss: 2.7671 (2.6808)  weight_decay: 0.0500 (0.0500)  time: 0.4322  data: 0.0001  max mem: 42573
Epoch: [86] Total time: 0:02:26 (0.4707 s / it)
Averaged stats: lr: 0.003461  min_lr: 0.003461  loss: 2.7671 (2.6419)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:00:45  loss: 0.8761 (0.8761)  acc1: 79.1667 (79.1667)  acc5: 92.7083 (92.7083)  time: 5.0504  data: 4.9410  max mem: 42573
Test:  [8/9]  eta: 0:00:00  loss: 1.3608 (1.2158)  acc1: 69.0104 (69.9520)  acc5: 89.5833 (89.5040)  time: 0.6378  data: 0.5491  max mem: 42573
Test: Total time: 0:00:05 (0.6554 s / it)
* Acc@1 69.958 Acc@5 89.400 loss 1.221
Accuracy of the model on the 50000 test images: 70.0%
Max accuracy: 69.96%
Epoch: [87]  [  0/312]  eta: 0:47:56  lr: 0.003461  min_lr: 0.003461  loss: 2.3375 (2.3375)  weight_decay: 0.0500 (0.0500)  time: 9.2198  data: 6.1922  max mem: 42573
Epoch: [87]  [ 10/312]  eta: 0:07:19  lr: 0.003461  min_lr: 0.003461  loss: 2.5716 (2.6305)  weight_decay: 0.0500 (0.0500)  time: 1.4559  data: 0.6259  max mem: 42573
Epoch: [87]  [ 20/312]  eta: 0:04:42  lr: 0.003460  min_lr: 0.003460  loss: 2.6746 (2.7509)  weight_decay: 0.0500 (0.0500)  time: 0.5562  data: 0.0348  max mem: 42573
Epoch: [87]  [ 30/312]  eta: 0:03:44  lr: 0.003460  min_lr: 0.003460  loss: 2.8429 (2.7338)  weight_decay: 0.0500 (0.0500)  time: 0.4332  data: 0.0004  max mem: 42573
Epoch: [87]  [ 40/312]  eta: 0:03:12  lr: 0.003459  min_lr: 0.003459  loss: 2.6865 (2.7186)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [87]  [ 50/312]  eta: 0:02:51  lr: 0.003459  min_lr: 0.003459  loss: 2.7913 (2.7255)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [87]  [ 60/312]  eta: 0:02:35  lr: 0.003458  min_lr: 0.003458  loss: 2.6955 (2.7076)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [87]  [ 70/312]  eta: 0:02:23  lr: 0.003458  min_lr: 0.003458  loss: 2.7232 (2.7024)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [87]  [ 80/312]  eta: 0:02:12  lr: 0.003457  min_lr: 0.003457  loss: 2.7498 (2.6866)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [87]  [ 90/312]  eta: 0:02:03  lr: 0.003457  min_lr: 0.003457  loss: 2.6547 (2.6728)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0003  max mem: 42573
Epoch: [87]  [100/312]  eta: 0:01:55  lr: 0.003456  min_lr: 0.003456  loss: 2.5322 (2.6601)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [87]  [110/312]  eta: 0:01:48  lr: 0.003456  min_lr: 0.003456  loss: 2.4408 (2.6459)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [87]  [120/312]  eta: 0:01:41  lr: 0.003455  min_lr: 0.003455  loss: 2.3283 (2.6253)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [87]  [130/312]  eta: 0:01:34  lr: 0.003455  min_lr: 0.003455  loss: 2.6140 (2.6309)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [87]  [140/312]  eta: 0:01:28  lr: 0.003454  min_lr: 0.003454  loss: 2.8628 (2.6513)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [87]  [150/312]  eta: 0:01:22  lr: 0.003454  min_lr: 0.003454  loss: 2.8998 (2.6634)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [87]  [160/312]  eta: 0:01:16  lr: 0.003453  min_lr: 0.003453  loss: 2.8898 (2.6722)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [87]  [170/312]  eta: 0:01:10  lr: 0.003453  min_lr: 0.003453  loss: 2.7920 (2.6727)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [87]  [180/312]  eta: 0:01:05  lr: 0.003452  min_lr: 0.003452  loss: 2.5863 (2.6765)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [87]  [190/312]  eta: 0:01:00  lr: 0.003452  min_lr: 0.003452  loss: 2.6951 (2.6755)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [87]  [200/312]  eta: 0:00:54  lr: 0.003451  min_lr: 0.003451  loss: 2.6581 (2.6755)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [87]  [210/312]  eta: 0:00:49  lr: 0.003451  min_lr: 0.003451  loss: 2.7345 (2.6802)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0003  max mem: 42573
Epoch: [87]  [220/312]  eta: 0:00:44  lr: 0.003450  min_lr: 0.003450  loss: 2.6576 (2.6763)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0003  max mem: 42573
Epoch: [87]  [230/312]  eta: 0:00:39  lr: 0.003450  min_lr: 0.003450  loss: 2.4563 (2.6739)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [87]  [240/312]  eta: 0:00:34  lr: 0.003449  min_lr: 0.003449  loss: 2.5529 (2.6637)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [87]  [250/312]  eta: 0:00:29  lr: 0.003449  min_lr: 0.003449  loss: 2.5540 (2.6643)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [87]  [260/312]  eta: 0:00:24  lr: 0.003448  min_lr: 0.003448  loss: 2.6854 (2.6650)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [87]  [270/312]  eta: 0:00:19  lr: 0.003448  min_lr: 0.003448  loss: 2.7673 (2.6701)  weight_decay: 0.0500 (0.0500)  time: 0.4393  data: 0.0003  max mem: 42573
Epoch: [87]  [280/312]  eta: 0:00:15  lr: 0.003447  min_lr: 0.003447  loss: 2.7027 (2.6675)  weight_decay: 0.0500 (0.0500)  time: 0.4401  data: 0.0009  max mem: 42573
Epoch: [87]  [290/312]  eta: 0:00:10  lr: 0.003447  min_lr: 0.003447  loss: 2.6666 (2.6717)  weight_decay: 0.0500 (0.0500)  time: 0.4341  data: 0.0008  max mem: 42573
Epoch: [87]  [300/312]  eta: 0:00:05  lr: 0.003446  min_lr: 0.003446  loss: 2.6680 (2.6712)  weight_decay: 0.0500 (0.0500)  time: 0.4327  data: 0.0001  max mem: 42573
Epoch: [87]  [310/312]  eta: 0:00:00  lr: 0.003446  min_lr: 0.003446  loss: 2.7264 (2.6737)  weight_decay: 0.0500 (0.0500)  time: 0.4325  data: 0.0001  max mem: 42573
Epoch: [87]  [311/312]  eta: 0:00:00  lr: 0.003446  min_lr: 0.003446  loss: 2.6808 (2.6712)  weight_decay: 0.0500 (0.0500)  time: 0.4325  data: 0.0001  max mem: 42573
Epoch: [87] Total time: 0:02:27 (0.4731 s / it)
Averaged stats: lr: 0.003446  min_lr: 0.003446  loss: 2.6808 (2.6511)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:00:39  loss: 1.0352 (1.0352)  acc1: 74.7396 (74.7396)  acc5: 90.8854 (90.8854)  time: 4.3562  data: 4.2475  max mem: 42573
Test:  [8/9]  eta: 0:00:00  loss: 1.4868 (1.3048)  acc1: 65.6250 (68.3520)  acc5: 89.8438 (88.2880)  time: 0.5887  data: 0.4999  max mem: 42573
Test: Total time: 0:00:05 (0.5978 s / it)
* Acc@1 68.542 Acc@5 88.384 loss 1.309
Accuracy of the model on the 50000 test images: 68.5%
Max accuracy: 69.96%
Epoch: [88]  [  0/312]  eta: 0:48:54  lr: 0.003446  min_lr: 0.003446  loss: 1.5111 (1.5111)  weight_decay: 0.0500 (0.0500)  time: 9.4052  data: 7.9113  max mem: 42573
Epoch: [88]  [ 10/312]  eta: 0:07:14  lr: 0.003445  min_lr: 0.003445  loss: 2.4271 (2.3831)  weight_decay: 0.0500 (0.0500)  time: 1.4387  data: 0.7197  max mem: 42573
Epoch: [88]  [ 20/312]  eta: 0:04:40  lr: 0.003445  min_lr: 0.003445  loss: 2.6038 (2.5529)  weight_decay: 0.0500 (0.0500)  time: 0.5375  data: 0.0004  max mem: 42573
Epoch: [88]  [ 30/312]  eta: 0:03:42  lr: 0.003444  min_lr: 0.003444  loss: 2.7891 (2.6405)  weight_decay: 0.0500 (0.0500)  time: 0.4331  data: 0.0004  max mem: 42573
Epoch: [88]  [ 40/312]  eta: 0:03:11  lr: 0.003444  min_lr: 0.003444  loss: 2.7891 (2.6670)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0005  max mem: 42573
Epoch: [88]  [ 50/312]  eta: 0:02:50  lr: 0.003443  min_lr: 0.003443  loss: 2.7419 (2.6933)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0005  max mem: 42573
Epoch: [88]  [ 60/312]  eta: 0:02:34  lr: 0.003443  min_lr: 0.003443  loss: 2.7419 (2.6593)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [88]  [ 70/312]  eta: 0:02:22  lr: 0.003442  min_lr: 0.003442  loss: 2.7543 (2.6876)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [88]  [ 80/312]  eta: 0:02:12  lr: 0.003442  min_lr: 0.003442  loss: 2.8108 (2.6793)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [88]  [ 90/312]  eta: 0:02:03  lr: 0.003441  min_lr: 0.003441  loss: 2.6699 (2.6795)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [88]  [100/312]  eta: 0:01:55  lr: 0.003441  min_lr: 0.003441  loss: 2.6047 (2.6607)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [88]  [110/312]  eta: 0:01:47  lr: 0.003440  min_lr: 0.003440  loss: 2.5654 (2.6608)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [88]  [120/312]  eta: 0:01:40  lr: 0.003440  min_lr: 0.003440  loss: 2.8343 (2.6695)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0003  max mem: 42573
Epoch: [88]  [130/312]  eta: 0:01:34  lr: 0.003439  min_lr: 0.003439  loss: 2.8343 (2.6677)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [88]  [140/312]  eta: 0:01:28  lr: 0.003439  min_lr: 0.003439  loss: 2.5958 (2.6617)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [88]  [150/312]  eta: 0:01:22  lr: 0.003438  min_lr: 0.003438  loss: 2.5519 (2.6562)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [88]  [160/312]  eta: 0:01:16  lr: 0.003438  min_lr: 0.003438  loss: 2.6577 (2.6568)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [88]  [170/312]  eta: 0:01:10  lr: 0.003437  min_lr: 0.003437  loss: 2.6577 (2.6605)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0003  max mem: 42573
Epoch: [88]  [180/312]  eta: 0:01:05  lr: 0.003437  min_lr: 0.003437  loss: 2.6055 (2.6513)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [88]  [190/312]  eta: 0:00:59  lr: 0.003436  min_lr: 0.003436  loss: 2.4785 (2.6467)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0003  max mem: 42573
Epoch: [88]  [200/312]  eta: 0:00:54  lr: 0.003436  min_lr: 0.003436  loss: 2.7859 (2.6524)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [88]  [210/312]  eta: 0:00:49  lr: 0.003435  min_lr: 0.003435  loss: 2.7758 (2.6488)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [88]  [220/312]  eta: 0:00:44  lr: 0.003435  min_lr: 0.003435  loss: 2.7761 (2.6596)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0003  max mem: 42573
Epoch: [88]  [230/312]  eta: 0:00:39  lr: 0.003434  min_lr: 0.003434  loss: 2.7833 (2.6548)  weight_decay: 0.0500 (0.0500)  time: 0.4381  data: 0.0004  max mem: 42573
Epoch: [88]  [240/312]  eta: 0:00:34  lr: 0.003434  min_lr: 0.003434  loss: 2.5395 (2.6484)  weight_decay: 0.0500 (0.0500)  time: 0.4381  data: 0.0004  max mem: 42573
Epoch: [88]  [250/312]  eta: 0:00:29  lr: 0.003433  min_lr: 0.003433  loss: 2.7660 (2.6541)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [88]  [260/312]  eta: 0:00:24  lr: 0.003433  min_lr: 0.003433  loss: 2.9429 (2.6675)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [88]  [270/312]  eta: 0:00:19  lr: 0.003432  min_lr: 0.003432  loss: 2.7932 (2.6651)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0003  max mem: 42573
Epoch: [88]  [280/312]  eta: 0:00:15  lr: 0.003432  min_lr: 0.003432  loss: 2.7178 (2.6742)  weight_decay: 0.0500 (0.0500)  time: 0.4346  data: 0.0009  max mem: 42573
Epoch: [88]  [290/312]  eta: 0:00:10  lr: 0.003431  min_lr: 0.003431  loss: 2.8985 (2.6785)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0008  max mem: 42573
Epoch: [88]  [300/312]  eta: 0:00:05  lr: 0.003431  min_lr: 0.003431  loss: 2.7476 (2.6775)  weight_decay: 0.0500 (0.0500)  time: 0.4325  data: 0.0001  max mem: 42573
Epoch: [88]  [310/312]  eta: 0:00:00  lr: 0.003430  min_lr: 0.003430  loss: 2.7310 (2.6756)  weight_decay: 0.0500 (0.0500)  time: 0.4324  data: 0.0001  max mem: 42573
Epoch: [88]  [311/312]  eta: 0:00:00  lr: 0.003430  min_lr: 0.003430  loss: 2.7310 (2.6729)  weight_decay: 0.0500 (0.0500)  time: 0.4323  data: 0.0001  max mem: 42573
Epoch: [88] Total time: 0:02:27 (0.4723 s / it)
Averaged stats: lr: 0.003430  min_lr: 0.003430  loss: 2.7310 (2.6500)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:00:43  loss: 1.0317 (1.0317)  acc1: 75.7812 (75.7812)  acc5: 92.4479 (92.4479)  time: 4.8695  data: 4.7600  max mem: 42573
Test:  [8/9]  eta: 0:00:00  loss: 1.4458 (1.3328)  acc1: 68.2292 (67.6480)  acc5: 87.5000 (88.0960)  time: 0.6174  data: 0.5290  max mem: 42573
Test: Total time: 0:00:05 (0.6393 s / it)
* Acc@1 68.220 Acc@5 87.854 loss 1.321
Accuracy of the model on the 50000 test images: 68.2%
Max accuracy: 69.96%
Epoch: [89]  [  0/312]  eta: 0:48:53  lr: 0.003430  min_lr: 0.003430  loss: 2.2956 (2.2956)  weight_decay: 0.0500 (0.0500)  time: 9.4013  data: 8.4993  max mem: 42573
Epoch: [89]  [ 10/312]  eta: 0:07:06  lr: 0.003430  min_lr: 0.003430  loss: 2.8195 (2.8600)  weight_decay: 0.0500 (0.0500)  time: 1.4110  data: 0.7777  max mem: 42573
Epoch: [89]  [ 20/312]  eta: 0:04:36  lr: 0.003429  min_lr: 0.003429  loss: 2.8374 (2.8027)  weight_decay: 0.0500 (0.0500)  time: 0.5226  data: 0.0029  max mem: 42573
Epoch: [89]  [ 30/312]  eta: 0:03:39  lr: 0.003429  min_lr: 0.003429  loss: 2.6233 (2.7164)  weight_decay: 0.0500 (0.0500)  time: 0.4332  data: 0.0003  max mem: 42573
Epoch: [89]  [ 40/312]  eta: 0:03:09  lr: 0.003428  min_lr: 0.003428  loss: 2.6119 (2.6905)  weight_decay: 0.0500 (0.0500)  time: 0.4331  data: 0.0003  max mem: 42573
Epoch: [89]  [ 50/312]  eta: 0:02:48  lr: 0.003428  min_lr: 0.003428  loss: 2.6816 (2.6965)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [89]  [ 60/312]  eta: 0:02:33  lr: 0.003427  min_lr: 0.003427  loss: 2.7994 (2.7053)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0003  max mem: 42573
Epoch: [89]  [ 70/312]  eta: 0:02:21  lr: 0.003427  min_lr: 0.003427  loss: 2.6483 (2.6662)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0003  max mem: 42573
Epoch: [89]  [ 80/312]  eta: 0:02:11  lr: 0.003426  min_lr: 0.003426  loss: 2.5240 (2.6401)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [89]  [ 90/312]  eta: 0:02:02  lr: 0.003426  min_lr: 0.003426  loss: 2.3391 (2.6124)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [89]  [100/312]  eta: 0:01:54  lr: 0.003425  min_lr: 0.003425  loss: 2.3391 (2.5946)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [89]  [110/312]  eta: 0:01:47  lr: 0.003425  min_lr: 0.003425  loss: 2.6062 (2.6138)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0003  max mem: 42573
Epoch: [89]  [120/312]  eta: 0:01:40  lr: 0.003424  min_lr: 0.003424  loss: 2.8618 (2.6318)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [89]  [130/312]  eta: 0:01:33  lr: 0.003424  min_lr: 0.003424  loss: 2.8228 (2.6435)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [89]  [140/312]  eta: 0:01:27  lr: 0.003423  min_lr: 0.003423  loss: 2.7646 (2.6402)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [89]  [150/312]  eta: 0:01:21  lr: 0.003423  min_lr: 0.003423  loss: 2.7317 (2.6381)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [89]  [160/312]  eta: 0:01:16  lr: 0.003422  min_lr: 0.003422  loss: 2.5898 (2.6329)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [89]  [170/312]  eta: 0:01:10  lr: 0.003422  min_lr: 0.003422  loss: 2.5673 (2.6273)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0005  max mem: 42573
Epoch: [89]  [180/312]  eta: 0:01:05  lr: 0.003421  min_lr: 0.003421  loss: 2.8028 (2.6433)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [89]  [190/312]  eta: 0:00:59  lr: 0.003421  min_lr: 0.003421  loss: 2.8918 (2.6427)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [89]  [200/312]  eta: 0:00:54  lr: 0.003420  min_lr: 0.003420  loss: 2.6121 (2.6351)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [89]  [210/312]  eta: 0:00:49  lr: 0.003420  min_lr: 0.003420  loss: 2.4419 (2.6288)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [89]  [220/312]  eta: 0:00:44  lr: 0.003419  min_lr: 0.003419  loss: 2.7225 (2.6390)  weight_decay: 0.0500 (0.0500)  time: 0.4357  data: 0.0004  max mem: 42573
Epoch: [89]  [230/312]  eta: 0:00:39  lr: 0.003419  min_lr: 0.003419  loss: 2.7225 (2.6411)  weight_decay: 0.0500 (0.0500)  time: 0.4357  data: 0.0004  max mem: 42573
Epoch: [89]  [240/312]  eta: 0:00:34  lr: 0.003418  min_lr: 0.003418  loss: 2.6044 (2.6411)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0003  max mem: 42573
Epoch: [89]  [250/312]  eta: 0:00:29  lr: 0.003418  min_lr: 0.003418  loss: 2.8074 (2.6486)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [89]  [260/312]  eta: 0:00:24  lr: 0.003417  min_lr: 0.003417  loss: 2.8074 (2.6486)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [89]  [270/312]  eta: 0:00:19  lr: 0.003416  min_lr: 0.003416  loss: 2.7805 (2.6478)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [89]  [280/312]  eta: 0:00:15  lr: 0.003416  min_lr: 0.003416  loss: 2.7188 (2.6480)  weight_decay: 0.0500 (0.0500)  time: 0.4341  data: 0.0010  max mem: 42573
Epoch: [89]  [290/312]  eta: 0:00:10  lr: 0.003415  min_lr: 0.003415  loss: 2.5606 (2.6435)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0008  max mem: 42573
Epoch: [89]  [300/312]  eta: 0:00:05  lr: 0.003415  min_lr: 0.003415  loss: 2.5606 (2.6430)  weight_decay: 0.0500 (0.0500)  time: 0.4324  data: 0.0001  max mem: 42573
Epoch: [89]  [310/312]  eta: 0:00:00  lr: 0.003414  min_lr: 0.003414  loss: 2.7412 (2.6427)  weight_decay: 0.0500 (0.0500)  time: 0.4323  data: 0.0001  max mem: 42573
Epoch: [89]  [311/312]  eta: 0:00:00  lr: 0.003414  min_lr: 0.003414  loss: 2.7412 (2.6435)  weight_decay: 0.0500 (0.0500)  time: 0.4324  data: 0.0001  max mem: 42573
Epoch: [89] Total time: 0:02:27 (0.4712 s / it)
Averaged stats: lr: 0.003414  min_lr: 0.003414  loss: 2.7412 (2.6483)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:00:43  loss: 1.1415 (1.1415)  acc1: 74.4792 (74.4792)  acc5: 90.1042 (90.1042)  time: 4.8146  data: 4.7052  max mem: 42573
Test:  [8/9]  eta: 0:00:00  loss: 1.4445 (1.3330)  acc1: 67.9688 (68.2560)  acc5: 88.0208 (88.3840)  time: 0.6120  data: 0.5229  max mem: 42573
Test: Total time: 0:00:05 (0.6234 s / it)
* Acc@1 68.288 Acc@5 88.356 loss 1.345
Accuracy of the model on the 50000 test images: 68.3%
Max accuracy: 69.96%
Epoch: [90]  [  0/312]  eta: 0:51:43  lr: 0.003414  min_lr: 0.003414  loss: 2.0641 (2.0641)  weight_decay: 0.0500 (0.0500)  time: 9.9477  data: 8.6554  max mem: 42573
Epoch: [90]  [ 10/312]  eta: 0:07:46  lr: 0.003414  min_lr: 0.003414  loss: 2.3977 (2.4202)  weight_decay: 0.0500 (0.0500)  time: 1.5458  data: 0.7871  max mem: 42573
Epoch: [90]  [ 20/312]  eta: 0:04:56  lr: 0.003413  min_lr: 0.003413  loss: 2.5920 (2.5032)  weight_decay: 0.0500 (0.0500)  time: 0.5694  data: 0.0003  max mem: 42573
Epoch: [90]  [ 30/312]  eta: 0:03:53  lr: 0.003413  min_lr: 0.003413  loss: 2.7507 (2.5754)  weight_decay: 0.0500 (0.0500)  time: 0.4331  data: 0.0003  max mem: 42573
Epoch: [90]  [ 40/312]  eta: 0:03:19  lr: 0.003412  min_lr: 0.003412  loss: 2.8380 (2.6098)  weight_decay: 0.0500 (0.0500)  time: 0.4332  data: 0.0003  max mem: 42573
Epoch: [90]  [ 50/312]  eta: 0:02:56  lr: 0.003412  min_lr: 0.003412  loss: 2.7084 (2.5966)  weight_decay: 0.0500 (0.0500)  time: 0.4332  data: 0.0003  max mem: 42573
Epoch: [90]  [ 60/312]  eta: 0:02:39  lr: 0.003411  min_lr: 0.003411  loss: 2.4727 (2.5805)  weight_decay: 0.0500 (0.0500)  time: 0.4331  data: 0.0004  max mem: 42573
Epoch: [90]  [ 70/312]  eta: 0:02:26  lr: 0.003411  min_lr: 0.003411  loss: 2.7681 (2.6011)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [90]  [ 80/312]  eta: 0:02:15  lr: 0.003410  min_lr: 0.003410  loss: 2.8274 (2.6181)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [90]  [ 90/312]  eta: 0:02:06  lr: 0.003410  min_lr: 0.003410  loss: 2.8318 (2.6299)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [90]  [100/312]  eta: 0:01:57  lr: 0.003409  min_lr: 0.003409  loss: 2.9020 (2.6493)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0003  max mem: 42573
Epoch: [90]  [110/312]  eta: 0:01:49  lr: 0.003409  min_lr: 0.003409  loss: 2.6997 (2.6348)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [90]  [120/312]  eta: 0:01:42  lr: 0.003408  min_lr: 0.003408  loss: 2.6032 (2.6317)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [90]  [130/312]  eta: 0:01:35  lr: 0.003408  min_lr: 0.003408  loss: 2.5752 (2.6309)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0003  max mem: 42573
Epoch: [90]  [140/312]  eta: 0:01:29  lr: 0.003407  min_lr: 0.003407  loss: 2.5482 (2.6240)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0003  max mem: 42573
Epoch: [90]  [150/312]  eta: 0:01:23  lr: 0.003407  min_lr: 0.003407  loss: 2.6119 (2.6284)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [90]  [160/312]  eta: 0:01:17  lr: 0.003406  min_lr: 0.003406  loss: 2.7029 (2.6248)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [90]  [170/312]  eta: 0:01:11  lr: 0.003406  min_lr: 0.003406  loss: 2.5058 (2.6219)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0003  max mem: 42573
Epoch: [90]  [180/312]  eta: 0:01:06  lr: 0.003405  min_lr: 0.003405  loss: 2.6122 (2.6280)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0003  max mem: 42573
Epoch: [90]  [190/312]  eta: 0:01:00  lr: 0.003405  min_lr: 0.003405  loss: 2.6122 (2.6215)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [90]  [200/312]  eta: 0:00:55  lr: 0.003404  min_lr: 0.003404  loss: 2.6886 (2.6301)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [90]  [210/312]  eta: 0:00:50  lr: 0.003404  min_lr: 0.003404  loss: 2.8166 (2.6358)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [90]  [220/312]  eta: 0:00:44  lr: 0.003403  min_lr: 0.003403  loss: 2.6120 (2.6236)  weight_decay: 0.0500 (0.0500)  time: 0.4346  data: 0.0004  max mem: 42573
Epoch: [90]  [230/312]  eta: 0:00:39  lr: 0.003403  min_lr: 0.003403  loss: 2.3938 (2.6233)  weight_decay: 0.0500 (0.0500)  time: 0.4345  data: 0.0004  max mem: 42573
Epoch: [90]  [240/312]  eta: 0:00:34  lr: 0.003402  min_lr: 0.003402  loss: 2.7472 (2.6252)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [90]  [250/312]  eta: 0:00:29  lr: 0.003402  min_lr: 0.003402  loss: 2.7472 (2.6282)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [90]  [260/312]  eta: 0:00:24  lr: 0.003401  min_lr: 0.003401  loss: 2.6445 (2.6234)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0003  max mem: 42573
Epoch: [90]  [270/312]  eta: 0:00:20  lr: 0.003401  min_lr: 0.003401  loss: 2.6801 (2.6250)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0003  max mem: 42573
Epoch: [90]  [280/312]  eta: 0:00:15  lr: 0.003400  min_lr: 0.003400  loss: 2.6801 (2.6215)  weight_decay: 0.0500 (0.0500)  time: 0.4342  data: 0.0009  max mem: 42573
Epoch: [90]  [290/312]  eta: 0:00:10  lr: 0.003400  min_lr: 0.003400  loss: 2.4693 (2.6233)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0008  max mem: 42573
Epoch: [90]  [300/312]  eta: 0:00:05  lr: 0.003399  min_lr: 0.003399  loss: 2.6139 (2.6200)  weight_decay: 0.0500 (0.0500)  time: 0.4324  data: 0.0001  max mem: 42573
Epoch: [90]  [310/312]  eta: 0:00:00  lr: 0.003399  min_lr: 0.003399  loss: 2.5689 (2.6180)  weight_decay: 0.0500 (0.0500)  time: 0.4324  data: 0.0001  max mem: 42573
Epoch: [90]  [311/312]  eta: 0:00:00  lr: 0.003398  min_lr: 0.003398  loss: 2.4359 (2.6167)  weight_decay: 0.0500 (0.0500)  time: 0.4324  data: 0.0001  max mem: 42573
Epoch: [90] Total time: 0:02:28 (0.4757 s / it)
Averaged stats: lr: 0.003398  min_lr: 0.003398  loss: 2.4359 (2.6431)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:00:41  loss: 1.0548 (1.0548)  acc1: 77.0833 (77.0833)  acc5: 91.1458 (91.1458)  time: 4.5920  data: 4.4831  max mem: 42573
Test:  [8/9]  eta: 0:00:00  loss: 1.3914 (1.2942)  acc1: 67.9688 (69.1200)  acc5: 89.0625 (88.6080)  time: 0.5927  data: 0.5043  max mem: 42573
Test: Total time: 0:00:05 (0.6012 s / it)
* Acc@1 69.122 Acc@5 88.620 loss 1.309
Accuracy of the model on the 50000 test images: 69.1%
Max accuracy: 69.96%
Epoch: [91]  [  0/312]  eta: 0:48:50  lr: 0.003398  min_lr: 0.003398  loss: 3.1890 (3.1890)  weight_decay: 0.0500 (0.0500)  time: 9.3922  data: 8.5952  max mem: 42573
Epoch: [91]  [ 10/312]  eta: 0:07:20  lr: 0.003398  min_lr: 0.003398  loss: 2.7581 (2.7186)  weight_decay: 0.0500 (0.0500)  time: 1.4587  data: 0.7817  max mem: 42573
Epoch: [91]  [ 20/312]  eta: 0:04:43  lr: 0.003397  min_lr: 0.003397  loss: 2.7412 (2.6472)  weight_decay: 0.0500 (0.0500)  time: 0.5493  data: 0.0004  max mem: 42573
Epoch: [91]  [ 30/312]  eta: 0:03:44  lr: 0.003397  min_lr: 0.003397  loss: 2.5134 (2.6447)  weight_decay: 0.0500 (0.0500)  time: 0.4332  data: 0.0004  max mem: 42573
Epoch: [91]  [ 40/312]  eta: 0:03:12  lr: 0.003396  min_lr: 0.003396  loss: 2.7485 (2.6693)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [91]  [ 50/312]  eta: 0:02:51  lr: 0.003396  min_lr: 0.003396  loss: 2.7989 (2.6643)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [91]  [ 60/312]  eta: 0:02:35  lr: 0.003395  min_lr: 0.003395  loss: 2.7858 (2.6845)  weight_decay: 0.0500 (0.0500)  time: 0.4332  data: 0.0004  max mem: 42573
Epoch: [91]  [ 70/312]  eta: 0:02:23  lr: 0.003395  min_lr: 0.003395  loss: 2.7163 (2.6750)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [91]  [ 80/312]  eta: 0:02:12  lr: 0.003394  min_lr: 0.003394  loss: 2.8368 (2.6865)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [91]  [ 90/312]  eta: 0:02:03  lr: 0.003394  min_lr: 0.003394  loss: 2.8616 (2.7071)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [91]  [100/312]  eta: 0:01:55  lr: 0.003393  min_lr: 0.003393  loss: 2.8925 (2.7142)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [91]  [110/312]  eta: 0:01:48  lr: 0.003393  min_lr: 0.003393  loss: 2.8273 (2.7137)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [91]  [120/312]  eta: 0:01:41  lr: 0.003392  min_lr: 0.003392  loss: 2.8022 (2.7072)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [91]  [130/312]  eta: 0:01:34  lr: 0.003392  min_lr: 0.003392  loss: 2.6234 (2.6856)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [91]  [140/312]  eta: 0:01:28  lr: 0.003391  min_lr: 0.003391  loss: 2.3944 (2.6679)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [91]  [150/312]  eta: 0:01:22  lr: 0.003391  min_lr: 0.003391  loss: 2.5531 (2.6671)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [91]  [160/312]  eta: 0:01:16  lr: 0.003390  min_lr: 0.003390  loss: 2.7015 (2.6685)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [91]  [170/312]  eta: 0:01:10  lr: 0.003390  min_lr: 0.003390  loss: 2.6153 (2.6610)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [91]  [180/312]  eta: 0:01:05  lr: 0.003389  min_lr: 0.003389  loss: 2.6353 (2.6650)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0003  max mem: 42573
Epoch: [91]  [190/312]  eta: 0:01:00  lr: 0.003389  min_lr: 0.003389  loss: 2.6353 (2.6568)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0003  max mem: 42573
Epoch: [91]  [200/312]  eta: 0:00:54  lr: 0.003388  min_lr: 0.003388  loss: 2.7398 (2.6613)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0003  max mem: 42573
Epoch: [91]  [210/312]  eta: 0:00:49  lr: 0.003388  min_lr: 0.003388  loss: 2.7584 (2.6622)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [91]  [220/312]  eta: 0:00:44  lr: 0.003387  min_lr: 0.003387  loss: 2.5445 (2.6548)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0003  max mem: 42573
Epoch: [91]  [230/312]  eta: 0:00:39  lr: 0.003387  min_lr: 0.003387  loss: 2.5518 (2.6539)  weight_decay: 0.0500 (0.0500)  time: 0.4388  data: 0.0003  max mem: 42573
Epoch: [91]  [240/312]  eta: 0:00:34  lr: 0.003386  min_lr: 0.003386  loss: 2.6477 (2.6535)  weight_decay: 0.0500 (0.0500)  time: 0.4389  data: 0.0004  max mem: 42573
Epoch: [91]  [250/312]  eta: 0:00:29  lr: 0.003385  min_lr: 0.003385  loss: 2.6477 (2.6511)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0004  max mem: 42573
Epoch: [91]  [260/312]  eta: 0:00:24  lr: 0.003385  min_lr: 0.003385  loss: 2.3735 (2.6417)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0004  max mem: 42573
Epoch: [91]  [270/312]  eta: 0:00:19  lr: 0.003384  min_lr: 0.003384  loss: 2.6922 (2.6443)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [91]  [280/312]  eta: 0:00:15  lr: 0.003384  min_lr: 0.003384  loss: 2.7864 (2.6468)  weight_decay: 0.0500 (0.0500)  time: 0.4345  data: 0.0011  max mem: 42573
Epoch: [91]  [290/312]  eta: 0:00:10  lr: 0.003383  min_lr: 0.003383  loss: 2.6577 (2.6436)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0009  max mem: 42573
Epoch: [91]  [300/312]  eta: 0:00:05  lr: 0.003383  min_lr: 0.003383  loss: 2.5420 (2.6394)  weight_decay: 0.0500 (0.0500)  time: 0.4324  data: 0.0001  max mem: 42573
Epoch: [91]  [310/312]  eta: 0:00:00  lr: 0.003382  min_lr: 0.003382  loss: 2.7585 (2.6463)  weight_decay: 0.0500 (0.0500)  time: 0.4323  data: 0.0001  max mem: 42573
Epoch: [91]  [311/312]  eta: 0:00:00  lr: 0.003382  min_lr: 0.003382  loss: 2.5537 (2.6449)  weight_decay: 0.0500 (0.0500)  time: 0.4323  data: 0.0001  max mem: 42573
Epoch: [91] Total time: 0:02:27 (0.4729 s / it)
Averaged stats: lr: 0.003382  min_lr: 0.003382  loss: 2.5537 (2.6347)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:00:45  loss: 1.0070 (1.0070)  acc1: 75.5208 (75.5208)  acc5: 92.7083 (92.7083)  time: 5.0260  data: 4.9167  max mem: 42573
Test:  [8/9]  eta: 0:00:00  loss: 1.3331 (1.2375)  acc1: 68.7500 (68.8000)  acc5: 88.8021 (88.7680)  time: 0.6345  data: 0.5463  max mem: 42573
Test: Total time: 0:00:05 (0.6599 s / it)
* Acc@1 69.516 Acc@5 89.122 loss 1.231
Accuracy of the model on the 50000 test images: 69.5%
Max accuracy: 69.96%
Epoch: [92]  [  0/312]  eta: 0:46:47  lr: 0.003382  min_lr: 0.003382  loss: 2.0483 (2.0483)  weight_decay: 0.0500 (0.0500)  time: 8.9988  data: 8.3185  max mem: 42573
Epoch: [92]  [ 10/312]  eta: 0:06:56  lr: 0.003382  min_lr: 0.003382  loss: 2.8567 (2.8238)  weight_decay: 0.0500 (0.0500)  time: 1.3798  data: 0.7567  max mem: 42573
Epoch: [92]  [ 20/312]  eta: 0:04:31  lr: 0.003381  min_lr: 0.003381  loss: 2.6890 (2.6177)  weight_decay: 0.0500 (0.0500)  time: 0.5258  data: 0.0005  max mem: 42573
Epoch: [92]  [ 30/312]  eta: 0:03:36  lr: 0.003381  min_lr: 0.003381  loss: 2.5469 (2.6389)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [92]  [ 40/312]  eta: 0:03:07  lr: 0.003380  min_lr: 0.003380  loss: 2.6002 (2.6208)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [92]  [ 50/312]  eta: 0:02:47  lr: 0.003380  min_lr: 0.003380  loss: 2.4458 (2.6077)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [92]  [ 60/312]  eta: 0:02:32  lr: 0.003379  min_lr: 0.003379  loss: 2.2802 (2.5602)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [92]  [ 70/312]  eta: 0:02:20  lr: 0.003379  min_lr: 0.003379  loss: 2.7821 (2.6107)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [92]  [ 80/312]  eta: 0:02:10  lr: 0.003378  min_lr: 0.003378  loss: 2.8198 (2.5967)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0004  max mem: 42573
Epoch: [92]  [ 90/312]  eta: 0:02:01  lr: 0.003378  min_lr: 0.003378  loss: 2.7268 (2.6070)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [92]  [100/312]  eta: 0:01:53  lr: 0.003377  min_lr: 0.003377  loss: 2.6535 (2.6175)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [92]  [110/312]  eta: 0:01:46  lr: 0.003377  min_lr: 0.003377  loss: 2.5864 (2.6068)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [92]  [120/312]  eta: 0:01:39  lr: 0.003376  min_lr: 0.003376  loss: 2.4802 (2.6053)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [92]  [130/312]  eta: 0:01:33  lr: 0.003376  min_lr: 0.003376  loss: 2.7729 (2.6106)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [92]  [140/312]  eta: 0:01:27  lr: 0.003375  min_lr: 0.003375  loss: 2.6253 (2.6008)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [92]  [150/312]  eta: 0:01:21  lr: 0.003374  min_lr: 0.003374  loss: 2.7680 (2.6220)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [92]  [160/312]  eta: 0:01:15  lr: 0.003374  min_lr: 0.003374  loss: 2.8522 (2.6143)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [92]  [170/312]  eta: 0:01:10  lr: 0.003373  min_lr: 0.003373  loss: 2.5849 (2.6134)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [92]  [180/312]  eta: 0:01:04  lr: 0.003373  min_lr: 0.003373  loss: 2.8143 (2.6234)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [92]  [190/312]  eta: 0:00:59  lr: 0.003372  min_lr: 0.003372  loss: 2.8870 (2.6308)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [92]  [200/312]  eta: 0:00:54  lr: 0.003372  min_lr: 0.003372  loss: 2.7001 (2.6367)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0003  max mem: 42573
Epoch: [92]  [210/312]  eta: 0:00:49  lr: 0.003371  min_lr: 0.003371  loss: 2.6067 (2.6304)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0003  max mem: 42573
Epoch: [92]  [220/312]  eta: 0:00:44  lr: 0.003371  min_lr: 0.003371  loss: 2.5499 (2.6271)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [92]  [230/312]  eta: 0:00:39  lr: 0.003370  min_lr: 0.003370  loss: 2.6750 (2.6313)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [92]  [240/312]  eta: 0:00:34  lr: 0.003370  min_lr: 0.003370  loss: 2.6353 (2.6283)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0003  max mem: 42573
Epoch: [92]  [250/312]  eta: 0:00:29  lr: 0.003369  min_lr: 0.003369  loss: 2.5545 (2.6283)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [92]  [260/312]  eta: 0:00:24  lr: 0.003369  min_lr: 0.003369  loss: 2.6202 (2.6248)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [92]  [270/312]  eta: 0:00:19  lr: 0.003368  min_lr: 0.003368  loss: 2.4076 (2.6162)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [92]  [280/312]  eta: 0:00:15  lr: 0.003368  min_lr: 0.003368  loss: 2.6594 (2.6236)  weight_decay: 0.0500 (0.0500)  time: 0.4354  data: 0.0009  max mem: 42573
Epoch: [92]  [290/312]  eta: 0:00:10  lr: 0.003367  min_lr: 0.003367  loss: 2.8965 (2.6271)  weight_decay: 0.0500 (0.0500)  time: 0.4349  data: 0.0008  max mem: 42573
Epoch: [92]  [300/312]  eta: 0:00:05  lr: 0.003367  min_lr: 0.003367  loss: 2.6544 (2.6257)  weight_decay: 0.0500 (0.0500)  time: 0.4326  data: 0.0001  max mem: 42573
Epoch: [92]  [310/312]  eta: 0:00:00  lr: 0.003366  min_lr: 0.003366  loss: 2.5798 (2.6219)  weight_decay: 0.0500 (0.0500)  time: 0.4323  data: 0.0001  max mem: 42573
Epoch: [92]  [311/312]  eta: 0:00:00  lr: 0.003366  min_lr: 0.003366  loss: 2.5798 (2.6202)  weight_decay: 0.0500 (0.0500)  time: 0.4323  data: 0.0001  max mem: 42573
Epoch: [92] Total time: 0:02:26 (0.4702 s / it)
Averaged stats: lr: 0.003366  min_lr: 0.003366  loss: 2.5798 (2.6413)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:00:44  loss: 0.8580 (0.8580)  acc1: 78.6458 (78.6458)  acc5: 93.7500 (93.7500)  time: 4.9998  data: 4.8903  max mem: 42573
Test:  [8/9]  eta: 0:00:00  loss: 1.4130 (1.2932)  acc1: 66.1458 (67.5840)  acc5: 87.7604 (88.0640)  time: 0.6315  data: 0.5434  max mem: 42573
Test: Total time: 0:00:05 (0.6619 s / it)
* Acc@1 68.106 Acc@5 87.844 loss 1.331
Accuracy of the model on the 50000 test images: 68.1%
Max accuracy: 69.96%
Epoch: [93]  [  0/312]  eta: 0:50:23  lr: 0.003366  min_lr: 0.003366  loss: 2.5103 (2.5103)  weight_decay: 0.0500 (0.0500)  time: 9.6922  data: 6.5174  max mem: 42573
Epoch: [93]  [ 10/312]  eta: 0:07:18  lr: 0.003365  min_lr: 0.003365  loss: 2.6520 (2.5897)  weight_decay: 0.0500 (0.0500)  time: 1.4527  data: 0.6502  max mem: 42573
Epoch: [93]  [ 20/312]  eta: 0:04:42  lr: 0.003365  min_lr: 0.003365  loss: 2.6214 (2.5708)  weight_decay: 0.0500 (0.0500)  time: 0.5310  data: 0.0319  max mem: 42573
Epoch: [93]  [ 30/312]  eta: 0:03:44  lr: 0.003364  min_lr: 0.003364  loss: 2.5879 (2.5797)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0003  max mem: 42573
Epoch: [93]  [ 40/312]  eta: 0:03:12  lr: 0.003364  min_lr: 0.003364  loss: 2.5807 (2.5755)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [93]  [ 50/312]  eta: 0:02:51  lr: 0.003363  min_lr: 0.003363  loss: 2.5788 (2.5624)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [93]  [ 60/312]  eta: 0:02:35  lr: 0.003363  min_lr: 0.003363  loss: 2.5804 (2.5674)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [93]  [ 70/312]  eta: 0:02:23  lr: 0.003362  min_lr: 0.003362  loss: 2.6984 (2.5799)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [93]  [ 80/312]  eta: 0:02:12  lr: 0.003362  min_lr: 0.003362  loss: 2.7588 (2.5831)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [93]  [ 90/312]  eta: 0:02:03  lr: 0.003361  min_lr: 0.003361  loss: 2.7313 (2.5800)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [93]  [100/312]  eta: 0:01:55  lr: 0.003361  min_lr: 0.003361  loss: 2.7313 (2.5891)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [93]  [110/312]  eta: 0:01:47  lr: 0.003360  min_lr: 0.003360  loss: 2.7180 (2.5948)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [93]  [120/312]  eta: 0:01:41  lr: 0.003360  min_lr: 0.003360  loss: 2.7691 (2.6144)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [93]  [130/312]  eta: 0:01:34  lr: 0.003359  min_lr: 0.003359  loss: 2.6314 (2.6106)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [93]  [140/312]  eta: 0:01:28  lr: 0.003359  min_lr: 0.003359  loss: 2.5574 (2.6071)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [93]  [150/312]  eta: 0:01:22  lr: 0.003358  min_lr: 0.003358  loss: 2.5574 (2.6089)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [93]  [160/312]  eta: 0:01:16  lr: 0.003358  min_lr: 0.003358  loss: 2.5097 (2.6073)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [93]  [170/312]  eta: 0:01:10  lr: 0.003357  min_lr: 0.003357  loss: 2.7156 (2.6167)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [93]  [180/312]  eta: 0:01:05  lr: 0.003356  min_lr: 0.003356  loss: 2.7490 (2.6094)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0003  max mem: 42573
Epoch: [93]  [190/312]  eta: 0:01:00  lr: 0.003356  min_lr: 0.003356  loss: 2.7440 (2.6139)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0003  max mem: 42573
Epoch: [93]  [200/312]  eta: 0:00:54  lr: 0.003355  min_lr: 0.003355  loss: 2.7134 (2.6148)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [93]  [210/312]  eta: 0:00:49  lr: 0.003355  min_lr: 0.003355  loss: 2.6416 (2.6215)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [93]  [220/312]  eta: 0:00:44  lr: 0.003354  min_lr: 0.003354  loss: 2.7244 (2.6283)  weight_decay: 0.0500 (0.0500)  time: 0.4377  data: 0.0004  max mem: 42573
Epoch: [93]  [230/312]  eta: 0:00:39  lr: 0.003354  min_lr: 0.003354  loss: 2.7718 (2.6402)  weight_decay: 0.0500 (0.0500)  time: 0.4379  data: 0.0004  max mem: 42573
Epoch: [93]  [240/312]  eta: 0:00:34  lr: 0.003353  min_lr: 0.003353  loss: 2.7682 (2.6390)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0004  max mem: 42573
Epoch: [93]  [250/312]  eta: 0:00:29  lr: 0.003353  min_lr: 0.003353  loss: 2.7021 (2.6366)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [93]  [260/312]  eta: 0:00:24  lr: 0.003352  min_lr: 0.003352  loss: 2.6359 (2.6365)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [93]  [270/312]  eta: 0:00:19  lr: 0.003352  min_lr: 0.003352  loss: 2.7208 (2.6418)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [93]  [280/312]  eta: 0:00:15  lr: 0.003351  min_lr: 0.003351  loss: 2.6064 (2.6366)  weight_decay: 0.0500 (0.0500)  time: 0.4342  data: 0.0009  max mem: 42573
Epoch: [93]  [290/312]  eta: 0:00:10  lr: 0.003351  min_lr: 0.003351  loss: 2.5770 (2.6393)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0008  max mem: 42573
Epoch: [93]  [300/312]  eta: 0:00:05  lr: 0.003350  min_lr: 0.003350  loss: 2.6467 (2.6421)  weight_decay: 0.0500 (0.0500)  time: 0.4324  data: 0.0001  max mem: 42573
Epoch: [93]  [310/312]  eta: 0:00:00  lr: 0.003350  min_lr: 0.003350  loss: 2.7877 (2.6463)  weight_decay: 0.0500 (0.0500)  time: 0.4323  data: 0.0001  max mem: 42573
Epoch: [93]  [311/312]  eta: 0:00:00  lr: 0.003350  min_lr: 0.003350  loss: 2.8312 (2.6475)  weight_decay: 0.0500 (0.0500)  time: 0.4323  data: 0.0001  max mem: 42573
Epoch: [93] Total time: 0:02:27 (0.4728 s / it)
Averaged stats: lr: 0.003350  min_lr: 0.003350  loss: 2.8312 (2.6340)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:00:48  loss: 1.0130 (1.0130)  acc1: 75.2604 (75.2604)  acc5: 92.4479 (92.4479)  time: 5.3500  data: 5.2415  max mem: 42573
Test:  [8/9]  eta: 0:00:00  loss: 1.3755 (1.3015)  acc1: 66.6667 (68.1920)  acc5: 87.7604 (87.9360)  time: 0.6714  data: 0.5824  max mem: 42573
Test: Total time: 0:00:06 (0.6924 s / it)
* Acc@1 68.652 Acc@5 88.594 loss 1.286
Accuracy of the model on the 50000 test images: 68.7%
Max accuracy: 69.96%
Epoch: [94]  [  0/312]  eta: 0:49:59  lr: 0.003350  min_lr: 0.003350  loss: 3.2380 (3.2380)  weight_decay: 0.0500 (0.0500)  time: 9.6149  data: 7.6142  max mem: 42573
Epoch: [94]  [ 10/312]  eta: 0:07:24  lr: 0.003349  min_lr: 0.003349  loss: 2.7893 (2.5870)  weight_decay: 0.0500 (0.0500)  time: 1.4730  data: 0.7588  max mem: 42573
Epoch: [94]  [ 20/312]  eta: 0:04:45  lr: 0.003348  min_lr: 0.003348  loss: 2.7893 (2.6538)  weight_decay: 0.0500 (0.0500)  time: 0.5460  data: 0.0368  max mem: 42573
Epoch: [94]  [ 30/312]  eta: 0:03:46  lr: 0.003348  min_lr: 0.003348  loss: 2.8781 (2.7200)  weight_decay: 0.0500 (0.0500)  time: 0.4332  data: 0.0003  max mem: 42573
Epoch: [94]  [ 40/312]  eta: 0:03:13  lr: 0.003347  min_lr: 0.003347  loss: 2.7314 (2.6642)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [94]  [ 50/312]  eta: 0:02:52  lr: 0.003347  min_lr: 0.003347  loss: 2.6774 (2.6631)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [94]  [ 60/312]  eta: 0:02:36  lr: 0.003346  min_lr: 0.003346  loss: 2.6390 (2.6268)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0003  max mem: 42573
Epoch: [94]  [ 70/312]  eta: 0:02:23  lr: 0.003346  min_lr: 0.003346  loss: 2.5859 (2.6005)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0003  max mem: 42573
Epoch: [94]  [ 80/312]  eta: 0:02:13  lr: 0.003345  min_lr: 0.003345  loss: 2.4646 (2.5985)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [94]  [ 90/312]  eta: 0:02:04  lr: 0.003345  min_lr: 0.003345  loss: 2.7675 (2.6058)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [94]  [100/312]  eta: 0:01:55  lr: 0.003344  min_lr: 0.003344  loss: 2.8597 (2.6217)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [94]  [110/312]  eta: 0:01:48  lr: 0.003344  min_lr: 0.003344  loss: 2.7572 (2.6163)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [94]  [120/312]  eta: 0:01:41  lr: 0.003343  min_lr: 0.003343  loss: 2.6110 (2.6106)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [94]  [130/312]  eta: 0:01:34  lr: 0.003343  min_lr: 0.003343  loss: 2.8001 (2.6177)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [94]  [140/312]  eta: 0:01:28  lr: 0.003342  min_lr: 0.003342  loss: 2.8000 (2.6137)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [94]  [150/312]  eta: 0:01:22  lr: 0.003342  min_lr: 0.003342  loss: 2.7372 (2.6190)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [94]  [160/312]  eta: 0:01:16  lr: 0.003341  min_lr: 0.003341  loss: 2.8634 (2.6319)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [94]  [170/312]  eta: 0:01:11  lr: 0.003340  min_lr: 0.003340  loss: 2.8312 (2.6385)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [94]  [180/312]  eta: 0:01:05  lr: 0.003340  min_lr: 0.003340  loss: 2.6920 (2.6347)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [94]  [190/312]  eta: 0:01:00  lr: 0.003339  min_lr: 0.003339  loss: 2.5107 (2.6224)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [94]  [200/312]  eta: 0:00:54  lr: 0.003339  min_lr: 0.003339  loss: 2.4420 (2.6163)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0004  max mem: 42573
Epoch: [94]  [210/312]  eta: 0:00:49  lr: 0.003338  min_lr: 0.003338  loss: 2.4425 (2.6151)  weight_decay: 0.0500 (0.0500)  time: 0.4342  data: 0.0004  max mem: 42573
Epoch: [94]  [220/312]  eta: 0:00:44  lr: 0.003338  min_lr: 0.003338  loss: 2.5076 (2.6061)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [94]  [230/312]  eta: 0:00:39  lr: 0.003337  min_lr: 0.003337  loss: 2.5076 (2.6092)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [94]  [240/312]  eta: 0:00:34  lr: 0.003337  min_lr: 0.003337  loss: 2.4400 (2.6051)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [94]  [250/312]  eta: 0:00:29  lr: 0.003336  min_lr: 0.003336  loss: 2.4155 (2.5998)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [94]  [260/312]  eta: 0:00:24  lr: 0.003336  min_lr: 0.003336  loss: 2.7267 (2.6096)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [94]  [270/312]  eta: 0:00:19  lr: 0.003335  min_lr: 0.003335  loss: 2.6804 (2.6086)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [94]  [280/312]  eta: 0:00:15  lr: 0.003335  min_lr: 0.003335  loss: 2.6740 (2.6180)  weight_decay: 0.0500 (0.0500)  time: 0.4342  data: 0.0010  max mem: 42573
Epoch: [94]  [290/312]  eta: 0:00:10  lr: 0.003334  min_lr: 0.003334  loss: 2.8575 (2.6167)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0008  max mem: 42573
Epoch: [94]  [300/312]  eta: 0:00:05  lr: 0.003334  min_lr: 0.003334  loss: 2.7490 (2.6168)  weight_decay: 0.0500 (0.0500)  time: 0.4324  data: 0.0001  max mem: 42573
Epoch: [94]  [310/312]  eta: 0:00:00  lr: 0.003333  min_lr: 0.003333  loss: 2.7490 (2.6146)  weight_decay: 0.0500 (0.0500)  time: 0.4324  data: 0.0001  max mem: 42573
Epoch: [94]  [311/312]  eta: 0:00:00  lr: 0.003333  min_lr: 0.003333  loss: 2.6757 (2.6137)  weight_decay: 0.0500 (0.0500)  time: 0.4324  data: 0.0001  max mem: 42573
Epoch: [94] Total time: 0:02:27 (0.4733 s / it)
Averaged stats: lr: 0.003333  min_lr: 0.003333  loss: 2.6757 (2.6333)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:00:50  loss: 0.9810 (0.9810)  acc1: 76.8229 (76.8229)  acc5: 91.4062 (91.4062)  time: 5.6236  data: 5.5141  max mem: 42573
Test:  [8/9]  eta: 0:00:00  loss: 1.4371 (1.2482)  acc1: 68.4896 (69.1840)  acc5: 87.7604 (88.9600)  time: 0.7023  data: 0.6127  max mem: 42573
Test: Total time: 0:00:06 (0.7238 s / it)
* Acc@1 69.488 Acc@5 88.962 loss 1.241
Accuracy of the model on the 50000 test images: 69.5%
Max accuracy: 69.96%
Epoch: [95]  [  0/312]  eta: 0:44:12  lr: 0.003333  min_lr: 0.003333  loss: 2.7337 (2.7337)  weight_decay: 0.0500 (0.0500)  time: 8.5013  data: 7.9329  max mem: 42573
Epoch: [95]  [ 10/312]  eta: 0:06:25  lr: 0.003332  min_lr: 0.003332  loss: 2.7337 (2.6161)  weight_decay: 0.0500 (0.0500)  time: 1.2775  data: 0.7216  max mem: 42573
Epoch: [95]  [ 20/312]  eta: 0:04:18  lr: 0.003332  min_lr: 0.003332  loss: 2.6746 (2.6010)  weight_decay: 0.0500 (0.0500)  time: 0.5042  data: 0.0005  max mem: 42573
Epoch: [95]  [ 30/312]  eta: 0:03:28  lr: 0.003331  min_lr: 0.003331  loss: 2.5648 (2.6100)  weight_decay: 0.0500 (0.0500)  time: 0.4435  data: 0.0005  max mem: 42573
Epoch: [95]  [ 40/312]  eta: 0:03:00  lr: 0.003331  min_lr: 0.003331  loss: 2.6292 (2.6141)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [95]  [ 50/312]  eta: 0:02:42  lr: 0.003330  min_lr: 0.003330  loss: 2.8427 (2.6498)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [95]  [ 60/312]  eta: 0:02:28  lr: 0.003330  min_lr: 0.003330  loss: 2.6883 (2.6235)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [95]  [ 70/312]  eta: 0:02:17  lr: 0.003329  min_lr: 0.003329  loss: 2.6905 (2.6534)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [95]  [ 80/312]  eta: 0:02:07  lr: 0.003329  min_lr: 0.003329  loss: 2.7626 (2.6389)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [95]  [ 90/312]  eta: 0:01:59  lr: 0.003328  min_lr: 0.003328  loss: 2.4754 (2.6237)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [95]  [100/312]  eta: 0:01:51  lr: 0.003327  min_lr: 0.003327  loss: 2.6108 (2.6138)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [95]  [110/312]  eta: 0:01:44  lr: 0.003327  min_lr: 0.003327  loss: 2.5840 (2.6047)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0003  max mem: 42573
Epoch: [95]  [120/312]  eta: 0:01:38  lr: 0.003326  min_lr: 0.003326  loss: 2.5445 (2.5996)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0003  max mem: 42573
Epoch: [95]  [130/312]  eta: 0:01:32  lr: 0.003326  min_lr: 0.003326  loss: 2.7660 (2.6132)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0003  max mem: 42573
Epoch: [95]  [140/312]  eta: 0:01:26  lr: 0.003325  min_lr: 0.003325  loss: 2.7660 (2.6158)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0003  max mem: 42573
Epoch: [95]  [150/312]  eta: 0:01:20  lr: 0.003325  min_lr: 0.003325  loss: 2.6621 (2.6160)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [95]  [160/312]  eta: 0:01:14  lr: 0.003324  min_lr: 0.003324  loss: 2.5804 (2.6102)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [95]  [170/312]  eta: 0:01:09  lr: 0.003324  min_lr: 0.003324  loss: 2.4875 (2.6085)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [95]  [180/312]  eta: 0:01:04  lr: 0.003323  min_lr: 0.003323  loss: 2.4716 (2.5978)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0003  max mem: 42573
Epoch: [95]  [190/312]  eta: 0:00:58  lr: 0.003323  min_lr: 0.003323  loss: 2.7166 (2.6034)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [95]  [200/312]  eta: 0:00:53  lr: 0.003322  min_lr: 0.003322  loss: 2.7187 (2.5998)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [95]  [210/312]  eta: 0:00:48  lr: 0.003322  min_lr: 0.003322  loss: 2.6322 (2.6002)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [95]  [220/312]  eta: 0:00:43  lr: 0.003321  min_lr: 0.003321  loss: 2.7249 (2.6071)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [95]  [230/312]  eta: 0:00:38  lr: 0.003320  min_lr: 0.003320  loss: 2.6647 (2.6014)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [95]  [240/312]  eta: 0:00:34  lr: 0.003320  min_lr: 0.003320  loss: 2.7138 (2.6110)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0003  max mem: 42573
Epoch: [95]  [250/312]  eta: 0:00:29  lr: 0.003319  min_lr: 0.003319  loss: 2.6632 (2.6029)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [95]  [260/312]  eta: 0:00:24  lr: 0.003319  min_lr: 0.003319  loss: 2.6632 (2.6154)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [95]  [270/312]  eta: 0:00:19  lr: 0.003318  min_lr: 0.003318  loss: 2.9136 (2.6246)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [95]  [280/312]  eta: 0:00:14  lr: 0.003318  min_lr: 0.003318  loss: 2.8265 (2.6299)  weight_decay: 0.0500 (0.0500)  time: 0.4343  data: 0.0009  max mem: 42573
Epoch: [95]  [290/312]  eta: 0:00:10  lr: 0.003317  min_lr: 0.003317  loss: 2.7710 (2.6275)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0008  max mem: 42573
Epoch: [95]  [300/312]  eta: 0:00:05  lr: 0.003317  min_lr: 0.003317  loss: 2.6968 (2.6295)  weight_decay: 0.0500 (0.0500)  time: 0.4325  data: 0.0001  max mem: 42573
Epoch: [95]  [310/312]  eta: 0:00:00  lr: 0.003316  min_lr: 0.003316  loss: 2.7566 (2.6309)  weight_decay: 0.0500 (0.0500)  time: 0.4326  data: 0.0001  max mem: 42573
Epoch: [95]  [311/312]  eta: 0:00:00  lr: 0.003316  min_lr: 0.003316  loss: 2.7299 (2.6307)  weight_decay: 0.0500 (0.0500)  time: 0.4325  data: 0.0001  max mem: 42573
Epoch: [95] Total time: 0:02:25 (0.4672 s / it)
Averaged stats: lr: 0.003316  min_lr: 0.003316  loss: 2.7299 (2.6290)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:00:45  loss: 1.0444 (1.0444)  acc1: 74.7396 (74.7396)  acc5: 90.1042 (90.1042)  time: 5.1087  data: 4.9992  max mem: 42573
Test:  [8/9]  eta: 0:00:00  loss: 1.3365 (1.3080)  acc1: 69.7917 (68.5120)  acc5: 88.0208 (87.9360)  time: 0.6448  data: 0.5555  max mem: 42573
Test: Total time: 0:00:06 (0.6675 s / it)
* Acc@1 68.748 Acc@5 88.366 loss 1.301
Accuracy of the model on the 50000 test images: 68.7%
Max accuracy: 69.96%
Epoch: [96]  [  0/312]  eta: 0:47:57  lr: 0.003316  min_lr: 0.003316  loss: 2.7540 (2.7540)  weight_decay: 0.0500 (0.0500)  time: 9.2225  data: 7.7822  max mem: 42573
Epoch: [96]  [ 10/312]  eta: 0:06:52  lr: 0.003316  min_lr: 0.003316  loss: 2.7412 (2.7635)  weight_decay: 0.0500 (0.0500)  time: 1.3650  data: 0.7079  max mem: 42573
Epoch: [96]  [ 20/312]  eta: 0:04:29  lr: 0.003315  min_lr: 0.003315  loss: 2.7927 (2.7871)  weight_decay: 0.0500 (0.0500)  time: 0.5064  data: 0.0004  max mem: 42573
Epoch: [96]  [ 30/312]  eta: 0:03:35  lr: 0.003314  min_lr: 0.003314  loss: 2.7927 (2.6967)  weight_decay: 0.0500 (0.0500)  time: 0.4332  data: 0.0004  max mem: 42573
Epoch: [96]  [ 40/312]  eta: 0:03:05  lr: 0.003314  min_lr: 0.003314  loss: 2.4541 (2.6577)  weight_decay: 0.0500 (0.0500)  time: 0.4331  data: 0.0004  max mem: 42573
Epoch: [96]  [ 50/312]  eta: 0:02:46  lr: 0.003313  min_lr: 0.003313  loss: 2.5222 (2.6512)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [96]  [ 60/312]  eta: 0:02:31  lr: 0.003313  min_lr: 0.003313  loss: 2.5222 (2.6149)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [96]  [ 70/312]  eta: 0:02:19  lr: 0.003312  min_lr: 0.003312  loss: 2.7654 (2.6338)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [96]  [ 80/312]  eta: 0:02:09  lr: 0.003312  min_lr: 0.003312  loss: 2.7654 (2.6246)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [96]  [ 90/312]  eta: 0:02:01  lr: 0.003311  min_lr: 0.003311  loss: 2.5758 (2.6202)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [96]  [100/312]  eta: 0:01:53  lr: 0.003311  min_lr: 0.003311  loss: 2.7403 (2.6223)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [96]  [110/312]  eta: 0:01:46  lr: 0.003310  min_lr: 0.003310  loss: 2.7801 (2.6200)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0004  max mem: 42573
Epoch: [96]  [120/312]  eta: 0:01:39  lr: 0.003310  min_lr: 0.003310  loss: 2.4153 (2.5956)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0004  max mem: 42573
Epoch: [96]  [130/312]  eta: 0:01:33  lr: 0.003309  min_lr: 0.003309  loss: 2.4484 (2.6037)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [96]  [140/312]  eta: 0:01:27  lr: 0.003308  min_lr: 0.003308  loss: 2.7498 (2.6048)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [96]  [150/312]  eta: 0:01:21  lr: 0.003308  min_lr: 0.003308  loss: 2.7034 (2.6142)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0003  max mem: 42573
Epoch: [96]  [160/312]  eta: 0:01:15  lr: 0.003307  min_lr: 0.003307  loss: 2.7179 (2.6163)  weight_decay: 0.0500 (0.0500)  time: 0.4423  data: 0.0003  max mem: 42573
Epoch: [96]  [170/312]  eta: 0:01:10  lr: 0.003307  min_lr: 0.003307  loss: 2.8480 (2.6345)  weight_decay: 0.0500 (0.0500)  time: 0.4425  data: 0.0004  max mem: 42573
Epoch: [96]  [180/312]  eta: 0:01:04  lr: 0.003306  min_lr: 0.003306  loss: 2.8875 (2.6403)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [96]  [190/312]  eta: 0:00:59  lr: 0.003306  min_lr: 0.003306  loss: 2.7128 (2.6357)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [96]  [200/312]  eta: 0:00:54  lr: 0.003305  min_lr: 0.003305  loss: 2.5030 (2.6285)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [96]  [210/312]  eta: 0:00:49  lr: 0.003305  min_lr: 0.003305  loss: 2.5030 (2.6253)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [96]  [220/312]  eta: 0:00:44  lr: 0.003304  min_lr: 0.003304  loss: 2.5399 (2.6175)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [96]  [230/312]  eta: 0:00:39  lr: 0.003304  min_lr: 0.003304  loss: 2.5399 (2.6189)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [96]  [240/312]  eta: 0:00:34  lr: 0.003303  min_lr: 0.003303  loss: 2.5492 (2.6152)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [96]  [250/312]  eta: 0:00:29  lr: 0.003302  min_lr: 0.003302  loss: 2.5685 (2.6211)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [96]  [260/312]  eta: 0:00:24  lr: 0.003302  min_lr: 0.003302  loss: 2.7607 (2.6173)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [96]  [270/312]  eta: 0:00:19  lr: 0.003301  min_lr: 0.003301  loss: 2.4892 (2.6126)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [96]  [280/312]  eta: 0:00:15  lr: 0.003301  min_lr: 0.003301  loss: 2.4326 (2.6094)  weight_decay: 0.0500 (0.0500)  time: 0.4343  data: 0.0009  max mem: 42573
Epoch: [96]  [290/312]  eta: 0:00:10  lr: 0.003300  min_lr: 0.003300  loss: 2.3710 (2.6023)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0008  max mem: 42573
Epoch: [96]  [300/312]  eta: 0:00:05  lr: 0.003300  min_lr: 0.003300  loss: 2.3123 (2.5933)  weight_decay: 0.0500 (0.0500)  time: 0.4325  data: 0.0001  max mem: 42573
Epoch: [96]  [310/312]  eta: 0:00:00  lr: 0.003299  min_lr: 0.003299  loss: 2.8058 (2.6020)  weight_decay: 0.0500 (0.0500)  time: 0.4324  data: 0.0001  max mem: 42573
Epoch: [96]  [311/312]  eta: 0:00:00  lr: 0.003299  min_lr: 0.003299  loss: 2.8157 (2.6027)  weight_decay: 0.0500 (0.0500)  time: 0.4324  data: 0.0001  max mem: 42573
Epoch: [96] Total time: 0:02:26 (0.4699 s / it)
Averaged stats: lr: 0.003299  min_lr: 0.003299  loss: 2.8157 (2.6215)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:00:51  loss: 1.2240 (1.2240)  acc1: 74.7396 (74.7396)  acc5: 89.5833 (89.5833)  time: 5.7156  data: 5.6062  max mem: 42573
Test:  [8/9]  eta: 0:00:00  loss: 1.5586 (1.4396)  acc1: 66.9271 (67.0400)  acc5: 85.9375 (86.8800)  time: 0.7103  data: 0.6230  max mem: 42573
Test: Total time: 0:00:06 (0.7280 s / it)
* Acc@1 67.548 Acc@5 87.698 loss 1.433
Accuracy of the model on the 50000 test images: 67.5%
Max accuracy: 69.96%
Epoch: [97]  [  0/312]  eta: 0:44:02  lr: 0.003299  min_lr: 0.003299  loss: 2.5387 (2.5387)  weight_decay: 0.0500 (0.0500)  time: 8.4681  data: 7.4459  max mem: 42573
Epoch: [97]  [ 10/312]  eta: 0:06:37  lr: 0.003299  min_lr: 0.003299  loss: 2.5387 (2.6314)  weight_decay: 0.0500 (0.0500)  time: 1.3151  data: 0.6773  max mem: 42573
Epoch: [97]  [ 20/312]  eta: 0:04:21  lr: 0.003298  min_lr: 0.003298  loss: 2.5524 (2.5823)  weight_decay: 0.0500 (0.0500)  time: 0.5176  data: 0.0004  max mem: 42573
Epoch: [97]  [ 30/312]  eta: 0:03:30  lr: 0.003297  min_lr: 0.003297  loss: 2.7415 (2.6226)  weight_decay: 0.0500 (0.0500)  time: 0.4344  data: 0.0004  max mem: 42573
Epoch: [97]  [ 40/312]  eta: 0:03:02  lr: 0.003297  min_lr: 0.003297  loss: 2.7198 (2.6479)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [97]  [ 50/312]  eta: 0:02:43  lr: 0.003296  min_lr: 0.003296  loss: 2.7198 (2.6630)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [97]  [ 60/312]  eta: 0:02:29  lr: 0.003296  min_lr: 0.003296  loss: 2.8033 (2.6680)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [97]  [ 70/312]  eta: 0:02:18  lr: 0.003295  min_lr: 0.003295  loss: 2.6776 (2.6589)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [97]  [ 80/312]  eta: 0:02:08  lr: 0.003295  min_lr: 0.003295  loss: 2.6776 (2.6590)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [97]  [ 90/312]  eta: 0:01:59  lr: 0.003294  min_lr: 0.003294  loss: 2.5986 (2.6456)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [97]  [100/312]  eta: 0:01:52  lr: 0.003294  min_lr: 0.003294  loss: 2.5547 (2.6293)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [97]  [110/312]  eta: 0:01:45  lr: 0.003293  min_lr: 0.003293  loss: 2.5547 (2.6263)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [97]  [120/312]  eta: 0:01:38  lr: 0.003292  min_lr: 0.003292  loss: 2.5604 (2.6146)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [97]  [130/312]  eta: 0:01:32  lr: 0.003292  min_lr: 0.003292  loss: 2.6152 (2.6142)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [97]  [140/312]  eta: 0:01:26  lr: 0.003291  min_lr: 0.003291  loss: 2.4955 (2.5931)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [97]  [150/312]  eta: 0:01:20  lr: 0.003291  min_lr: 0.003291  loss: 2.4955 (2.5973)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [97]  [160/312]  eta: 0:01:15  lr: 0.003290  min_lr: 0.003290  loss: 2.7251 (2.6048)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [97]  [170/312]  eta: 0:01:09  lr: 0.003290  min_lr: 0.003290  loss: 2.7511 (2.6132)  weight_decay: 0.0500 (0.0500)  time: 0.4346  data: 0.0004  max mem: 42573
Epoch: [97]  [180/312]  eta: 0:01:04  lr: 0.003289  min_lr: 0.003289  loss: 2.6826 (2.6108)  weight_decay: 0.0500 (0.0500)  time: 0.4345  data: 0.0004  max mem: 42573
Epoch: [97]  [190/312]  eta: 0:00:59  lr: 0.003289  min_lr: 0.003289  loss: 2.7585 (2.6157)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [97]  [200/312]  eta: 0:00:53  lr: 0.003288  min_lr: 0.003288  loss: 2.8097 (2.6212)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [97]  [210/312]  eta: 0:00:48  lr: 0.003288  min_lr: 0.003288  loss: 2.7806 (2.6207)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [97]  [220/312]  eta: 0:00:43  lr: 0.003287  min_lr: 0.003287  loss: 2.5816 (2.6184)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [97]  [230/312]  eta: 0:00:39  lr: 0.003286  min_lr: 0.003286  loss: 2.5647 (2.6141)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [97]  [240/312]  eta: 0:00:34  lr: 0.003286  min_lr: 0.003286  loss: 2.6671 (2.6160)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [97]  [250/312]  eta: 0:00:29  lr: 0.003285  min_lr: 0.003285  loss: 2.6627 (2.6103)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [97]  [260/312]  eta: 0:00:24  lr: 0.003285  min_lr: 0.003285  loss: 2.4425 (2.6089)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0003  max mem: 42573
Epoch: [97]  [270/312]  eta: 0:00:19  lr: 0.003284  min_lr: 0.003284  loss: 2.6803 (2.6105)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [97]  [280/312]  eta: 0:00:14  lr: 0.003284  min_lr: 0.003284  loss: 2.6810 (2.6052)  weight_decay: 0.0500 (0.0500)  time: 0.4343  data: 0.0009  max mem: 42573
Epoch: [97]  [290/312]  eta: 0:00:10  lr: 0.003283  min_lr: 0.003283  loss: 2.6514 (2.6060)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0008  max mem: 42573
Epoch: [97]  [300/312]  eta: 0:00:05  lr: 0.003283  min_lr: 0.003283  loss: 2.6271 (2.6078)  weight_decay: 0.0500 (0.0500)  time: 0.4324  data: 0.0001  max mem: 42573
Epoch: [97]  [310/312]  eta: 0:00:00  lr: 0.003282  min_lr: 0.003282  loss: 2.8250 (2.6128)  weight_decay: 0.0500 (0.0500)  time: 0.4323  data: 0.0001  max mem: 42573
Epoch: [97]  [311/312]  eta: 0:00:00  lr: 0.003282  min_lr: 0.003282  loss: 2.8250 (2.6130)  weight_decay: 0.0500 (0.0500)  time: 0.4324  data: 0.0001  max mem: 42573
Epoch: [97] Total time: 0:02:25 (0.4679 s / it)
Averaged stats: lr: 0.003282  min_lr: 0.003282  loss: 2.8250 (2.6273)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:00:52  loss: 1.0872 (1.0872)  acc1: 73.4375 (73.4375)  acc5: 90.6250 (90.6250)  time: 5.8307  data: 5.7212  max mem: 42573
Test:  [8/9]  eta: 0:00:00  loss: 1.4019 (1.2736)  acc1: 67.9688 (68.1600)  acc5: 88.8021 (88.7360)  time: 0.7272  data: 0.6358  max mem: 42573
Test: Total time: 0:00:06 (0.7394 s / it)
* Acc@1 69.074 Acc@5 88.832 loss 1.268
Accuracy of the model on the 50000 test images: 69.1%
Max accuracy: 69.96%
Epoch: [98]  [  0/312]  eta: 0:46:41  lr: 0.003282  min_lr: 0.003282  loss: 3.1082 (3.1082)  weight_decay: 0.0500 (0.0500)  time: 8.9782  data: 6.0806  max mem: 42573
Epoch: [98]  [ 10/312]  eta: 0:06:45  lr: 0.003281  min_lr: 0.003281  loss: 2.9523 (2.7242)  weight_decay: 0.0500 (0.0500)  time: 1.3411  data: 0.6537  max mem: 42573
Epoch: [98]  [ 20/312]  eta: 0:04:25  lr: 0.003281  min_lr: 0.003281  loss: 2.9153 (2.7539)  weight_decay: 0.0500 (0.0500)  time: 0.5056  data: 0.0557  max mem: 42573
Epoch: [98]  [ 30/312]  eta: 0:03:33  lr: 0.003280  min_lr: 0.003280  loss: 2.7254 (2.6742)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0005  max mem: 42573
Epoch: [98]  [ 40/312]  eta: 0:03:04  lr: 0.003280  min_lr: 0.003280  loss: 2.6739 (2.6746)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0005  max mem: 42573
Epoch: [98]  [ 50/312]  eta: 0:02:44  lr: 0.003279  min_lr: 0.003279  loss: 2.6739 (2.6672)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [98]  [ 60/312]  eta: 0:02:30  lr: 0.003279  min_lr: 0.003279  loss: 2.5412 (2.6599)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [98]  [ 70/312]  eta: 0:02:18  lr: 0.003278  min_lr: 0.003278  loss: 2.6954 (2.6491)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [98]  [ 80/312]  eta: 0:02:09  lr: 0.003278  min_lr: 0.003278  loss: 2.6579 (2.6381)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [98]  [ 90/312]  eta: 0:02:00  lr: 0.003277  min_lr: 0.003277  loss: 2.4959 (2.6199)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [98]  [100/312]  eta: 0:01:52  lr: 0.003276  min_lr: 0.003276  loss: 2.6180 (2.6238)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [98]  [110/312]  eta: 0:01:45  lr: 0.003276  min_lr: 0.003276  loss: 2.7731 (2.6372)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [98]  [120/312]  eta: 0:01:39  lr: 0.003275  min_lr: 0.003275  loss: 2.7109 (2.6327)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [98]  [130/312]  eta: 0:01:32  lr: 0.003275  min_lr: 0.003275  loss: 2.4602 (2.6205)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [98]  [140/312]  eta: 0:01:26  lr: 0.003274  min_lr: 0.003274  loss: 2.5816 (2.6190)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [98]  [150/312]  eta: 0:01:20  lr: 0.003274  min_lr: 0.003274  loss: 2.8056 (2.6353)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [98]  [160/312]  eta: 0:01:15  lr: 0.003273  min_lr: 0.003273  loss: 2.9046 (2.6450)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [98]  [170/312]  eta: 0:01:09  lr: 0.003273  min_lr: 0.003273  loss: 2.8329 (2.6454)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [98]  [180/312]  eta: 0:01:04  lr: 0.003272  min_lr: 0.003272  loss: 2.7422 (2.6528)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [98]  [190/312]  eta: 0:00:59  lr: 0.003271  min_lr: 0.003271  loss: 2.7772 (2.6529)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [98]  [200/312]  eta: 0:00:54  lr: 0.003271  min_lr: 0.003271  loss: 2.7750 (2.6552)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [98]  [210/312]  eta: 0:00:49  lr: 0.003270  min_lr: 0.003270  loss: 2.7570 (2.6550)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [98]  [220/312]  eta: 0:00:44  lr: 0.003270  min_lr: 0.003270  loss: 2.7570 (2.6572)  weight_decay: 0.0500 (0.0500)  time: 0.4374  data: 0.0004  max mem: 42573
Epoch: [98]  [230/312]  eta: 0:00:39  lr: 0.003269  min_lr: 0.003269  loss: 2.6555 (2.6511)  weight_decay: 0.0500 (0.0500)  time: 0.4373  data: 0.0004  max mem: 42573
Epoch: [98]  [240/312]  eta: 0:00:34  lr: 0.003269  min_lr: 0.003269  loss: 2.7044 (2.6570)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [98]  [250/312]  eta: 0:00:29  lr: 0.003268  min_lr: 0.003268  loss: 2.7044 (2.6562)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [98]  [260/312]  eta: 0:00:24  lr: 0.003268  min_lr: 0.003268  loss: 2.6347 (2.6592)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [98]  [270/312]  eta: 0:00:19  lr: 0.003267  min_lr: 0.003267  loss: 2.3974 (2.6471)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [98]  [280/312]  eta: 0:00:15  lr: 0.003266  min_lr: 0.003266  loss: 2.3313 (2.6414)  weight_decay: 0.0500 (0.0500)  time: 0.4342  data: 0.0009  max mem: 42573
Epoch: [98]  [290/312]  eta: 0:00:10  lr: 0.003266  min_lr: 0.003266  loss: 2.5020 (2.6415)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0008  max mem: 42573
Epoch: [98]  [300/312]  eta: 0:00:05  lr: 0.003265  min_lr: 0.003265  loss: 2.7618 (2.6484)  weight_decay: 0.0500 (0.0500)  time: 0.4324  data: 0.0001  max mem: 42573
Epoch: [98]  [310/312]  eta: 0:00:00  lr: 0.003265  min_lr: 0.003265  loss: 2.8087 (2.6509)  weight_decay: 0.0500 (0.0500)  time: 0.4324  data: 0.0001  max mem: 42573
Epoch: [98]  [311/312]  eta: 0:00:00  lr: 0.003265  min_lr: 0.003265  loss: 2.8087 (2.6513)  weight_decay: 0.0500 (0.0500)  time: 0.4323  data: 0.0001  max mem: 42573
Epoch: [98] Total time: 0:02:26 (0.4689 s / it)
Averaged stats: lr: 0.003265  min_lr: 0.003265  loss: 2.8087 (2.6288)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:00:47  loss: 1.0018 (1.0018)  acc1: 76.8229 (76.8229)  acc5: 92.4479 (92.4479)  time: 5.3201  data: 5.2107  max mem: 42573
Test:  [8/9]  eta: 0:00:00  loss: 1.3118 (1.2767)  acc1: 69.7917 (68.6400)  acc5: 89.5833 (88.5120)  time: 0.6664  data: 0.5790  max mem: 42573
Test: Total time: 0:00:06 (0.6799 s / it)
* Acc@1 69.188 Acc@5 88.866 loss 1.261
Accuracy of the model on the 50000 test images: 69.2%
Max accuracy: 69.96%
Epoch: [99]  [  0/312]  eta: 0:46:20  lr: 0.003265  min_lr: 0.003265  loss: 2.8375 (2.8375)  weight_decay: 0.0500 (0.0500)  time: 8.9117  data: 8.0458  max mem: 42573
Epoch: [99]  [ 10/312]  eta: 0:07:08  lr: 0.003264  min_lr: 0.003264  loss: 2.7462 (2.5597)  weight_decay: 0.0500 (0.0500)  time: 1.4196  data: 0.7319  max mem: 42573
Epoch: [99]  [ 20/312]  eta: 0:04:37  lr: 0.003264  min_lr: 0.003264  loss: 2.5193 (2.5166)  weight_decay: 0.0500 (0.0500)  time: 0.5519  data: 0.0005  max mem: 42573
Epoch: [99]  [ 30/312]  eta: 0:03:40  lr: 0.003263  min_lr: 0.003263  loss: 2.5171 (2.5288)  weight_decay: 0.0500 (0.0500)  time: 0.4332  data: 0.0004  max mem: 42573
Epoch: [99]  [ 40/312]  eta: 0:03:09  lr: 0.003262  min_lr: 0.003262  loss: 2.6009 (2.5700)  weight_decay: 0.0500 (0.0500)  time: 0.4332  data: 0.0004  max mem: 42573
Epoch: [99]  [ 50/312]  eta: 0:02:49  lr: 0.003262  min_lr: 0.003262  loss: 2.6969 (2.5739)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [99]  [ 60/312]  eta: 0:02:34  lr: 0.003261  min_lr: 0.003261  loss: 2.6559 (2.5897)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [99]  [ 70/312]  eta: 0:02:21  lr: 0.003261  min_lr: 0.003261  loss: 2.6503 (2.5995)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [99]  [ 80/312]  eta: 0:02:11  lr: 0.003260  min_lr: 0.003260  loss: 2.6503 (2.6058)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [99]  [ 90/312]  eta: 0:02:02  lr: 0.003260  min_lr: 0.003260  loss: 2.6365 (2.5995)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [99]  [100/312]  eta: 0:01:54  lr: 0.003259  min_lr: 0.003259  loss: 2.6388 (2.6174)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [99]  [110/312]  eta: 0:01:47  lr: 0.003258  min_lr: 0.003258  loss: 2.6437 (2.6081)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [99]  [120/312]  eta: 0:01:40  lr: 0.003258  min_lr: 0.003258  loss: 2.4889 (2.6064)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [99]  [130/312]  eta: 0:01:33  lr: 0.003257  min_lr: 0.003257  loss: 2.4889 (2.6084)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0003  max mem: 42573
Epoch: [99]  [140/312]  eta: 0:01:27  lr: 0.003257  min_lr: 0.003257  loss: 2.4478 (2.6005)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [99]  [150/312]  eta: 0:01:21  lr: 0.003256  min_lr: 0.003256  loss: 2.2163 (2.5902)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0004  max mem: 42573
Epoch: [99]  [160/312]  eta: 0:01:16  lr: 0.003256  min_lr: 0.003256  loss: 2.6380 (2.6032)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [99]  [170/312]  eta: 0:01:10  lr: 0.003255  min_lr: 0.003255  loss: 2.8085 (2.6084)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0003  max mem: 42573
Epoch: [99]  [180/312]  eta: 0:01:05  lr: 0.003255  min_lr: 0.003255  loss: 2.8085 (2.6162)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [99]  [190/312]  eta: 0:00:59  lr: 0.003254  min_lr: 0.003254  loss: 2.5799 (2.6036)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [99]  [200/312]  eta: 0:00:54  lr: 0.003253  min_lr: 0.003253  loss: 2.5088 (2.6047)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [99]  [210/312]  eta: 0:00:49  lr: 0.003253  min_lr: 0.003253  loss: 2.6294 (2.6055)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [99]  [220/312]  eta: 0:00:44  lr: 0.003252  min_lr: 0.003252  loss: 2.7486 (2.6150)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [99]  [230/312]  eta: 0:00:39  lr: 0.003252  min_lr: 0.003252  loss: 2.7277 (2.6151)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [99]  [240/312]  eta: 0:00:34  lr: 0.003251  min_lr: 0.003251  loss: 2.5087 (2.6144)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [99]  [250/312]  eta: 0:00:29  lr: 0.003251  min_lr: 0.003251  loss: 2.3799 (2.6077)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [99]  [260/312]  eta: 0:00:24  lr: 0.003250  min_lr: 0.003250  loss: 2.1785 (2.5995)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [99]  [270/312]  eta: 0:00:19  lr: 0.003250  min_lr: 0.003250  loss: 2.2419 (2.5925)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [99]  [280/312]  eta: 0:00:15  lr: 0.003249  min_lr: 0.003249  loss: 2.3539 (2.5956)  weight_decay: 0.0500 (0.0500)  time: 0.4347  data: 0.0010  max mem: 42573
Epoch: [99]  [290/312]  eta: 0:00:10  lr: 0.003248  min_lr: 0.003248  loss: 2.7026 (2.5956)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0009  max mem: 42573
Epoch: [99]  [300/312]  eta: 0:00:05  lr: 0.003248  min_lr: 0.003248  loss: 2.5002 (2.5892)  weight_decay: 0.0500 (0.0500)  time: 0.4325  data: 0.0001  max mem: 42573
Epoch: [99]  [310/312]  eta: 0:00:00  lr: 0.003247  min_lr: 0.003247  loss: 2.4532 (2.5838)  weight_decay: 0.0500 (0.0500)  time: 0.4324  data: 0.0001  max mem: 42573
Epoch: [99]  [311/312]  eta: 0:00:00  lr: 0.003247  min_lr: 0.003247  loss: 2.5002 (2.5850)  weight_decay: 0.0500 (0.0500)  time: 0.4324  data: 0.0001  max mem: 42573
Epoch: [99] Total time: 0:02:27 (0.4713 s / it)
Averaged stats: lr: 0.003247  min_lr: 0.003247  loss: 2.5002 (2.6156)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:00:42  loss: 1.0500 (1.0500)  acc1: 75.0000 (75.0000)  acc5: 89.5833 (89.5833)  time: 4.7030  data: 4.5953  max mem: 42573
Test:  [8/9]  eta: 0:00:00  loss: 1.3388 (1.3005)  acc1: 67.9688 (68.6720)  acc5: 89.5833 (89.0240)  time: 0.5980  data: 0.5107  max mem: 42573
Test: Total time: 0:00:05 (0.6058 s / it)
* Acc@1 69.444 Acc@5 88.946 loss 1.270
Accuracy of the model on the 50000 test images: 69.4%
Max accuracy: 69.96%
Epoch: [100]  [  0/312]  eta: 0:48:26  lr: 0.003247  min_lr: 0.003247  loss: 2.7284 (2.7284)  weight_decay: 0.0500 (0.0500)  time: 9.3142  data: 7.0484  max mem: 42573
Epoch: [100]  [ 10/312]  eta: 0:07:24  lr: 0.003247  min_lr: 0.003247  loss: 2.6337 (2.5467)  weight_decay: 0.0500 (0.0500)  time: 1.4703  data: 0.6875  max mem: 42573
Epoch: [100]  [ 20/312]  eta: 0:04:45  lr: 0.003246  min_lr: 0.003246  loss: 2.6080 (2.6002)  weight_decay: 0.0500 (0.0500)  time: 0.5596  data: 0.0259  max mem: 42573
Epoch: [100]  [ 30/312]  eta: 0:03:45  lr: 0.003245  min_lr: 0.003245  loss: 2.7586 (2.6130)  weight_decay: 0.0500 (0.0500)  time: 0.4332  data: 0.0004  max mem: 42573
Epoch: [100]  [ 40/312]  eta: 0:03:13  lr: 0.003245  min_lr: 0.003245  loss: 2.7864 (2.6149)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [100]  [ 50/312]  eta: 0:02:52  lr: 0.003244  min_lr: 0.003244  loss: 2.7864 (2.6415)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [100]  [ 60/312]  eta: 0:02:36  lr: 0.003244  min_lr: 0.003244  loss: 2.7853 (2.6317)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [100]  [ 70/312]  eta: 0:02:23  lr: 0.003243  min_lr: 0.003243  loss: 2.5123 (2.6306)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [100]  [ 80/312]  eta: 0:02:13  lr: 0.003243  min_lr: 0.003243  loss: 2.7621 (2.6651)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [100]  [ 90/312]  eta: 0:02:04  lr: 0.003242  min_lr: 0.003242  loss: 2.8124 (2.6682)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [100]  [100/312]  eta: 0:01:55  lr: 0.003242  min_lr: 0.003242  loss: 2.6549 (2.6468)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [100]  [110/312]  eta: 0:01:48  lr: 0.003241  min_lr: 0.003241  loss: 2.1792 (2.6133)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [100]  [120/312]  eta: 0:01:41  lr: 0.003240  min_lr: 0.003240  loss: 2.3055 (2.6128)  weight_decay: 0.0500 (0.0500)  time: 0.4343  data: 0.0004  max mem: 42573
Epoch: [100]  [130/312]  eta: 0:01:34  lr: 0.003240  min_lr: 0.003240  loss: 2.6644 (2.6074)  weight_decay: 0.0500 (0.0500)  time: 0.4343  data: 0.0004  max mem: 42573
Epoch: [100]  [140/312]  eta: 0:01:28  lr: 0.003239  min_lr: 0.003239  loss: 2.6644 (2.6162)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [100]  [150/312]  eta: 0:01:22  lr: 0.003239  min_lr: 0.003239  loss: 2.6718 (2.6203)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [100]  [160/312]  eta: 0:01:16  lr: 0.003238  min_lr: 0.003238  loss: 2.6140 (2.6155)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [100]  [170/312]  eta: 0:01:11  lr: 0.003238  min_lr: 0.003238  loss: 2.6205 (2.6168)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0003  max mem: 42573
Epoch: [100]  [180/312]  eta: 0:01:05  lr: 0.003237  min_lr: 0.003237  loss: 2.8055 (2.6250)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [100]  [190/312]  eta: 0:01:00  lr: 0.003236  min_lr: 0.003236  loss: 2.9070 (2.6310)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [100]  [200/312]  eta: 0:00:54  lr: 0.003236  min_lr: 0.003236  loss: 2.8037 (2.6342)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [100]  [210/312]  eta: 0:00:49  lr: 0.003235  min_lr: 0.003235  loss: 2.7155 (2.6347)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [100]  [220/312]  eta: 0:00:44  lr: 0.003235  min_lr: 0.003235  loss: 2.7419 (2.6422)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [100]  [230/312]  eta: 0:00:39  lr: 0.003234  min_lr: 0.003234  loss: 2.8828 (2.6472)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [100]  [240/312]  eta: 0:00:34  lr: 0.003234  min_lr: 0.003234  loss: 2.9963 (2.6630)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0005  max mem: 42573
Epoch: [100]  [250/312]  eta: 0:00:29  lr: 0.003233  min_lr: 0.003233  loss: 2.9458 (2.6696)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0005  max mem: 42573
Epoch: [100]  [260/312]  eta: 0:00:24  lr: 0.003232  min_lr: 0.003232  loss: 2.9006 (2.6699)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [100]  [270/312]  eta: 0:00:19  lr: 0.003232  min_lr: 0.003232  loss: 2.7208 (2.6690)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [100]  [280/312]  eta: 0:00:15  lr: 0.003231  min_lr: 0.003231  loss: 2.7138 (2.6679)  weight_decay: 0.0500 (0.0500)  time: 0.4352  data: 0.0009  max mem: 42573
Epoch: [100]  [290/312]  eta: 0:00:10  lr: 0.003231  min_lr: 0.003231  loss: 2.7411 (2.6758)  weight_decay: 0.0500 (0.0500)  time: 0.4345  data: 0.0008  max mem: 42573
Epoch: [100]  [300/312]  eta: 0:00:05  lr: 0.003230  min_lr: 0.003230  loss: 2.8014 (2.6767)  weight_decay: 0.0500 (0.0500)  time: 0.4325  data: 0.0001  max mem: 42573
Epoch: [100]  [310/312]  eta: 0:00:00  lr: 0.003230  min_lr: 0.003230  loss: 2.7423 (2.6721)  weight_decay: 0.0500 (0.0500)  time: 0.4324  data: 0.0001  max mem: 42573
Epoch: [100]  [311/312]  eta: 0:00:00  lr: 0.003230  min_lr: 0.003230  loss: 2.7569 (2.6727)  weight_decay: 0.0500 (0.0500)  time: 0.4324  data: 0.0001  max mem: 42573
Epoch: [100] Total time: 0:02:27 (0.4733 s / it)
Averaged stats: lr: 0.003230  min_lr: 0.003230  loss: 2.7569 (2.6100)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:00:43  loss: 0.9974 (0.9974)  acc1: 75.2604 (75.2604)  acc5: 91.9271 (91.9271)  time: 4.8510  data: 4.7421  max mem: 42573
Test:  [8/9]  eta: 0:00:00  loss: 1.3919 (1.2749)  acc1: 65.8854 (68.6080)  acc5: 88.2812 (89.0880)  time: 0.6143  data: 0.5270  max mem: 42573
Test: Total time: 0:00:05 (0.6225 s / it)
* Acc@1 69.582 Acc@5 89.228 loss 1.255
Accuracy of the model on the 50000 test images: 69.6%
Max accuracy: 69.96%
Epoch: [101]  [  0/312]  eta: 0:51:20  lr: 0.003230  min_lr: 0.003230  loss: 2.5255 (2.5255)  weight_decay: 0.0500 (0.0500)  time: 9.8739  data: 6.5938  max mem: 42573
Epoch: [101]  [ 10/312]  eta: 0:07:00  lr: 0.003229  min_lr: 0.003229  loss: 2.4754 (2.4528)  weight_decay: 0.0500 (0.0500)  time: 1.3931  data: 0.6739  max mem: 42573
Epoch: [101]  [ 20/312]  eta: 0:04:33  lr: 0.003228  min_lr: 0.003228  loss: 2.5010 (2.5171)  weight_decay: 0.0500 (0.0500)  time: 0.4910  data: 0.0412  max mem: 42573
Epoch: [101]  [ 30/312]  eta: 0:03:38  lr: 0.003228  min_lr: 0.003228  loss: 2.7047 (2.5842)  weight_decay: 0.0500 (0.0500)  time: 0.4352  data: 0.0004  max mem: 42573
Epoch: [101]  [ 40/312]  eta: 0:03:08  lr: 0.003227  min_lr: 0.003227  loss: 2.6823 (2.5748)  weight_decay: 0.0500 (0.0500)  time: 0.4332  data: 0.0004  max mem: 42573
Epoch: [101]  [ 50/312]  eta: 0:02:47  lr: 0.003227  min_lr: 0.003227  loss: 2.7201 (2.5868)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0003  max mem: 42573
Epoch: [101]  [ 60/312]  eta: 0:02:32  lr: 0.003226  min_lr: 0.003226  loss: 2.6903 (2.5705)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0003  max mem: 42573
Epoch: [101]  [ 70/312]  eta: 0:02:21  lr: 0.003226  min_lr: 0.003226  loss: 2.5319 (2.5550)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0003  max mem: 42573
Epoch: [101]  [ 80/312]  eta: 0:02:10  lr: 0.003225  min_lr: 0.003225  loss: 2.5319 (2.5489)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0004  max mem: 42573
Epoch: [101]  [ 90/312]  eta: 0:02:02  lr: 0.003224  min_lr: 0.003224  loss: 2.5569 (2.5627)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [101]  [100/312]  eta: 0:01:54  lr: 0.003224  min_lr: 0.003224  loss: 2.6555 (2.5565)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [101]  [110/312]  eta: 0:01:46  lr: 0.003223  min_lr: 0.003223  loss: 2.6555 (2.5566)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0003  max mem: 42573
Epoch: [101]  [120/312]  eta: 0:01:40  lr: 0.003223  min_lr: 0.003223  loss: 2.5896 (2.5496)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0003  max mem: 42573
Epoch: [101]  [130/312]  eta: 0:01:33  lr: 0.003222  min_lr: 0.003222  loss: 2.6245 (2.5579)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [101]  [140/312]  eta: 0:01:27  lr: 0.003222  min_lr: 0.003222  loss: 2.6468 (2.5588)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0003  max mem: 42573
Epoch: [101]  [150/312]  eta: 0:01:21  lr: 0.003221  min_lr: 0.003221  loss: 2.6468 (2.5681)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [101]  [160/312]  eta: 0:01:15  lr: 0.003220  min_lr: 0.003220  loss: 2.8535 (2.5937)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [101]  [170/312]  eta: 0:01:10  lr: 0.003220  min_lr: 0.003220  loss: 2.9065 (2.6004)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [101]  [180/312]  eta: 0:01:04  lr: 0.003219  min_lr: 0.003219  loss: 2.7424 (2.6066)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [101]  [190/312]  eta: 0:00:59  lr: 0.003219  min_lr: 0.003219  loss: 2.5738 (2.6047)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [101]  [200/312]  eta: 0:00:54  lr: 0.003218  min_lr: 0.003218  loss: 2.6616 (2.6126)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [101]  [210/312]  eta: 0:00:49  lr: 0.003218  min_lr: 0.003218  loss: 2.6616 (2.6173)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [101]  [220/312]  eta: 0:00:44  lr: 0.003217  min_lr: 0.003217  loss: 2.7384 (2.6250)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [101]  [230/312]  eta: 0:00:39  lr: 0.003216  min_lr: 0.003216  loss: 2.8218 (2.6288)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [101]  [240/312]  eta: 0:00:34  lr: 0.003216  min_lr: 0.003216  loss: 2.8482 (2.6391)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [101]  [250/312]  eta: 0:00:29  lr: 0.003215  min_lr: 0.003215  loss: 2.8361 (2.6434)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [101]  [260/312]  eta: 0:00:24  lr: 0.003215  min_lr: 0.003215  loss: 2.7907 (2.6406)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0003  max mem: 42573
Epoch: [101]  [270/312]  eta: 0:00:19  lr: 0.003214  min_lr: 0.003214  loss: 2.7410 (2.6428)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0003  max mem: 42573
Epoch: [101]  [280/312]  eta: 0:00:15  lr: 0.003214  min_lr: 0.003214  loss: 2.6651 (2.6363)  weight_decay: 0.0500 (0.0500)  time: 0.4347  data: 0.0009  max mem: 42573
Epoch: [101]  [290/312]  eta: 0:00:10  lr: 0.003213  min_lr: 0.003213  loss: 2.6240 (2.6351)  weight_decay: 0.0500 (0.0500)  time: 0.4341  data: 0.0008  max mem: 42573
Epoch: [101]  [300/312]  eta: 0:00:05  lr: 0.003212  min_lr: 0.003212  loss: 2.6240 (2.6323)  weight_decay: 0.0500 (0.0500)  time: 0.4324  data: 0.0001  max mem: 42573
Epoch: [101]  [310/312]  eta: 0:00:00  lr: 0.003212  min_lr: 0.003212  loss: 2.4218 (2.6281)  weight_decay: 0.0500 (0.0500)  time: 0.4322  data: 0.0001  max mem: 42573
Epoch: [101]  [311/312]  eta: 0:00:00  lr: 0.003212  min_lr: 0.003212  loss: 2.4218 (2.6282)  weight_decay: 0.0500 (0.0500)  time: 0.4323  data: 0.0001  max mem: 42573
Epoch: [101] Total time: 0:02:26 (0.4706 s / it)
Averaged stats: lr: 0.003212  min_lr: 0.003212  loss: 2.4218 (2.6030)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:00:45  loss: 0.9990 (0.9990)  acc1: 77.8646 (77.8646)  acc5: 92.4479 (92.4479)  time: 5.0179  data: 4.9085  max mem: 42573
Test:  [8/9]  eta: 0:00:00  loss: 1.2212 (1.2146)  acc1: 72.6562 (70.4640)  acc5: 90.1042 (89.6320)  time: 0.6385  data: 0.5455  max mem: 42573
Test: Total time: 0:00:05 (0.6608 s / it)
* Acc@1 70.708 Acc@5 89.584 loss 1.198
Accuracy of the model on the 50000 test images: 70.7%
Max accuracy: 70.71%
Epoch: [102]  [  0/312]  eta: 0:47:55  lr: 0.003212  min_lr: 0.003212  loss: 1.9088 (1.9088)  weight_decay: 0.0500 (0.0500)  time: 9.2175  data: 7.1240  max mem: 42573
Epoch: [102]  [ 10/312]  eta: 0:06:56  lr: 0.003211  min_lr: 0.003211  loss: 2.4318 (2.3775)  weight_decay: 0.0500 (0.0500)  time: 1.3775  data: 0.6712  max mem: 42573
Epoch: [102]  [ 20/312]  eta: 0:04:30  lr: 0.003211  min_lr: 0.003211  loss: 2.4318 (2.4617)  weight_decay: 0.0500 (0.0500)  time: 0.5135  data: 0.0131  max mem: 42573
Epoch: [102]  [ 30/312]  eta: 0:03:36  lr: 0.003210  min_lr: 0.003210  loss: 2.6764 (2.5328)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0003  max mem: 42573
Epoch: [102]  [ 40/312]  eta: 0:03:06  lr: 0.003209  min_lr: 0.003209  loss: 2.7210 (2.5731)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0003  max mem: 42573
Epoch: [102]  [ 50/312]  eta: 0:02:46  lr: 0.003209  min_lr: 0.003209  loss: 2.6676 (2.5802)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [102]  [ 60/312]  eta: 0:02:32  lr: 0.003208  min_lr: 0.003208  loss: 2.7790 (2.5760)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [102]  [ 70/312]  eta: 0:02:20  lr: 0.003208  min_lr: 0.003208  loss: 2.7790 (2.5802)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [102]  [ 80/312]  eta: 0:02:10  lr: 0.003207  min_lr: 0.003207  loss: 2.7289 (2.6008)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0003  max mem: 42573
Epoch: [102]  [ 90/312]  eta: 0:02:01  lr: 0.003207  min_lr: 0.003207  loss: 2.6463 (2.5914)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0003  max mem: 42573
Epoch: [102]  [100/312]  eta: 0:01:53  lr: 0.003206  min_lr: 0.003206  loss: 2.2726 (2.5646)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [102]  [110/312]  eta: 0:01:46  lr: 0.003205  min_lr: 0.003205  loss: 2.5974 (2.5742)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [102]  [120/312]  eta: 0:01:39  lr: 0.003205  min_lr: 0.003205  loss: 2.5711 (2.5521)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [102]  [130/312]  eta: 0:01:33  lr: 0.003204  min_lr: 0.003204  loss: 2.6436 (2.5644)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [102]  [140/312]  eta: 0:01:27  lr: 0.003204  min_lr: 0.003204  loss: 2.7653 (2.5855)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [102]  [150/312]  eta: 0:01:21  lr: 0.003203  min_lr: 0.003203  loss: 2.5749 (2.5783)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [102]  [160/312]  eta: 0:01:15  lr: 0.003203  min_lr: 0.003203  loss: 2.5670 (2.5848)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [102]  [170/312]  eta: 0:01:10  lr: 0.003202  min_lr: 0.003202  loss: 2.7009 (2.5823)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [102]  [180/312]  eta: 0:01:04  lr: 0.003201  min_lr: 0.003201  loss: 2.5223 (2.5802)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [102]  [190/312]  eta: 0:00:59  lr: 0.003201  min_lr: 0.003201  loss: 2.7075 (2.5964)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [102]  [200/312]  eta: 0:00:54  lr: 0.003200  min_lr: 0.003200  loss: 2.7609 (2.5908)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [102]  [210/312]  eta: 0:00:49  lr: 0.003200  min_lr: 0.003200  loss: 2.5683 (2.5907)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [102]  [220/312]  eta: 0:00:44  lr: 0.003199  min_lr: 0.003199  loss: 2.5691 (2.5919)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [102]  [230/312]  eta: 0:00:39  lr: 0.003199  min_lr: 0.003199  loss: 2.7754 (2.5978)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [102]  [240/312]  eta: 0:00:34  lr: 0.003198  min_lr: 0.003198  loss: 2.8370 (2.6063)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [102]  [250/312]  eta: 0:00:29  lr: 0.003197  min_lr: 0.003197  loss: 2.7790 (2.6060)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [102]  [260/312]  eta: 0:00:24  lr: 0.003197  min_lr: 0.003197  loss: 2.6866 (2.6083)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [102]  [270/312]  eta: 0:00:19  lr: 0.003196  min_lr: 0.003196  loss: 2.7063 (2.6058)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [102]  [280/312]  eta: 0:00:15  lr: 0.003196  min_lr: 0.003196  loss: 2.7742 (2.6135)  weight_decay: 0.0500 (0.0500)  time: 0.4342  data: 0.0009  max mem: 42573
Epoch: [102]  [290/312]  eta: 0:00:10  lr: 0.003195  min_lr: 0.003195  loss: 2.8410 (2.6108)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0008  max mem: 42573
Epoch: [102]  [300/312]  eta: 0:00:05  lr: 0.003195  min_lr: 0.003195  loss: 2.7171 (2.6137)  weight_decay: 0.0500 (0.0500)  time: 0.4325  data: 0.0001  max mem: 42573
Epoch: [102]  [310/312]  eta: 0:00:00  lr: 0.003194  min_lr: 0.003194  loss: 2.7027 (2.6133)  weight_decay: 0.0500 (0.0500)  time: 0.4323  data: 0.0001  max mem: 42573
Epoch: [102]  [311/312]  eta: 0:00:00  lr: 0.003194  min_lr: 0.003194  loss: 2.6691 (2.6110)  weight_decay: 0.0500 (0.0500)  time: 0.4323  data: 0.0001  max mem: 42573
Epoch: [102] Total time: 0:02:26 (0.4697 s / it)
Averaged stats: lr: 0.003194  min_lr: 0.003194  loss: 2.6691 (2.6079)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:00:44  loss: 0.9711 (0.9711)  acc1: 78.6458 (78.6458)  acc5: 91.1458 (91.1458)  time: 4.9339  data: 4.8245  max mem: 42573
Test:  [8/9]  eta: 0:00:00  loss: 1.2581 (1.2422)  acc1: 70.0521 (69.9200)  acc5: 88.5417 (88.7680)  time: 0.6244  data: 0.5361  max mem: 42573
Test: Total time: 0:00:05 (0.6378 s / it)
* Acc@1 70.232 Acc@5 89.338 loss 1.220
Accuracy of the model on the 50000 test images: 70.2%
Max accuracy: 70.71%
Epoch: [103]  [  0/312]  eta: 0:50:37  lr: 0.003194  min_lr: 0.003194  loss: 2.4001 (2.4001)  weight_decay: 0.0500 (0.0500)  time: 9.7369  data: 7.4492  max mem: 42573
Epoch: [103]  [ 10/312]  eta: 0:07:26  lr: 0.003193  min_lr: 0.003193  loss: 2.7540 (2.7412)  weight_decay: 0.0500 (0.0500)  time: 1.4773  data: 0.6775  max mem: 42573
Epoch: [103]  [ 20/312]  eta: 0:04:46  lr: 0.003193  min_lr: 0.003193  loss: 2.6418 (2.6666)  weight_decay: 0.0500 (0.0500)  time: 0.5422  data: 0.0004  max mem: 42573
Epoch: [103]  [ 30/312]  eta: 0:03:46  lr: 0.003192  min_lr: 0.003192  loss: 2.6211 (2.6196)  weight_decay: 0.0500 (0.0500)  time: 0.4332  data: 0.0003  max mem: 42573
Epoch: [103]  [ 40/312]  eta: 0:03:14  lr: 0.003192  min_lr: 0.003192  loss: 2.2896 (2.5672)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [103]  [ 50/312]  eta: 0:02:52  lr: 0.003191  min_lr: 0.003191  loss: 2.5329 (2.5665)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [103]  [ 60/312]  eta: 0:02:36  lr: 0.003190  min_lr: 0.003190  loss: 2.7046 (2.5918)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [103]  [ 70/312]  eta: 0:02:24  lr: 0.003190  min_lr: 0.003190  loss: 2.8194 (2.6173)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [103]  [ 80/312]  eta: 0:02:13  lr: 0.003189  min_lr: 0.003189  loss: 2.8295 (2.6344)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0003  max mem: 42573
Epoch: [103]  [ 90/312]  eta: 0:02:04  lr: 0.003189  min_lr: 0.003189  loss: 2.6430 (2.6198)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [103]  [100/312]  eta: 0:01:56  lr: 0.003188  min_lr: 0.003188  loss: 2.4339 (2.6033)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [103]  [110/312]  eta: 0:01:48  lr: 0.003187  min_lr: 0.003187  loss: 2.3116 (2.5974)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [103]  [120/312]  eta: 0:01:41  lr: 0.003187  min_lr: 0.003187  loss: 2.5399 (2.5921)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [103]  [130/312]  eta: 0:01:34  lr: 0.003186  min_lr: 0.003186  loss: 2.6536 (2.6022)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0005  max mem: 42573
Epoch: [103]  [140/312]  eta: 0:01:28  lr: 0.003186  min_lr: 0.003186  loss: 2.7901 (2.6157)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0004  max mem: 42573
Epoch: [103]  [150/312]  eta: 0:01:22  lr: 0.003185  min_lr: 0.003185  loss: 2.7571 (2.6091)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [103]  [160/312]  eta: 0:01:16  lr: 0.003185  min_lr: 0.003185  loss: 2.6694 (2.6127)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [103]  [170/312]  eta: 0:01:11  lr: 0.003184  min_lr: 0.003184  loss: 2.8520 (2.6262)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [103]  [180/312]  eta: 0:01:05  lr: 0.003183  min_lr: 0.003183  loss: 2.6850 (2.6187)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [103]  [190/312]  eta: 0:01:00  lr: 0.003183  min_lr: 0.003183  loss: 2.6236 (2.6279)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [103]  [200/312]  eta: 0:00:54  lr: 0.003182  min_lr: 0.003182  loss: 2.8292 (2.6298)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [103]  [210/312]  eta: 0:00:49  lr: 0.003182  min_lr: 0.003182  loss: 2.7793 (2.6288)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [103]  [220/312]  eta: 0:00:44  lr: 0.003181  min_lr: 0.003181  loss: 2.4505 (2.6230)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [103]  [230/312]  eta: 0:00:39  lr: 0.003181  min_lr: 0.003181  loss: 2.4505 (2.6159)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0003  max mem: 42573
Epoch: [103]  [240/312]  eta: 0:00:34  lr: 0.003180  min_lr: 0.003180  loss: 2.5706 (2.6191)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [103]  [250/312]  eta: 0:00:29  lr: 0.003179  min_lr: 0.003179  loss: 2.8094 (2.6220)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [103]  [260/312]  eta: 0:00:24  lr: 0.003179  min_lr: 0.003179  loss: 2.8316 (2.6280)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0003  max mem: 42573
Epoch: [103]  [270/312]  eta: 0:00:19  lr: 0.003178  min_lr: 0.003178  loss: 2.8312 (2.6271)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0003  max mem: 42573
Epoch: [103]  [280/312]  eta: 0:00:15  lr: 0.003178  min_lr: 0.003178  loss: 2.7068 (2.6325)  weight_decay: 0.0500 (0.0500)  time: 0.4345  data: 0.0009  max mem: 42573
Epoch: [103]  [290/312]  eta: 0:00:10  lr: 0.003177  min_lr: 0.003177  loss: 2.7845 (2.6341)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0008  max mem: 42573
Epoch: [103]  [300/312]  eta: 0:00:05  lr: 0.003176  min_lr: 0.003176  loss: 2.6793 (2.6313)  weight_decay: 0.0500 (0.0500)  time: 0.4324  data: 0.0001  max mem: 42573
Epoch: [103]  [310/312]  eta: 0:00:00  lr: 0.003176  min_lr: 0.003176  loss: 2.7042 (2.6338)  weight_decay: 0.0500 (0.0500)  time: 0.4325  data: 0.0001  max mem: 42573
Epoch: [103]  [311/312]  eta: 0:00:00  lr: 0.003176  min_lr: 0.003176  loss: 2.6793 (2.6332)  weight_decay: 0.0500 (0.0500)  time: 0.4324  data: 0.0001  max mem: 42573
Epoch: [103] Total time: 0:02:27 (0.4732 s / it)
Averaged stats: lr: 0.003176  min_lr: 0.003176  loss: 2.6793 (2.6093)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:00:43  loss: 1.0785 (1.0785)  acc1: 75.7812 (75.7812)  acc5: 90.1042 (90.1042)  time: 4.8190  data: 4.7095  max mem: 42573
Test:  [8/9]  eta: 0:00:00  loss: 1.3049 (1.2755)  acc1: 67.7083 (68.0320)  acc5: 88.2812 (88.3840)  time: 0.6121  data: 0.5234  max mem: 42573
Test: Total time: 0:00:05 (0.6233 s / it)
* Acc@1 69.128 Acc@5 88.730 loss 1.270
Accuracy of the model on the 50000 test images: 69.1%
Max accuracy: 70.71%
Epoch: [104]  [  0/312]  eta: 0:48:34  lr: 0.003176  min_lr: 0.003176  loss: 3.2133 (3.2133)  weight_decay: 0.0500 (0.0500)  time: 9.3420  data: 8.5309  max mem: 42573
Epoch: [104]  [ 10/312]  eta: 0:07:32  lr: 0.003175  min_lr: 0.003175  loss: 2.9450 (2.7579)  weight_decay: 0.0500 (0.0500)  time: 1.4996  data: 0.7759  max mem: 42573
Epoch: [104]  [ 20/312]  eta: 0:04:49  lr: 0.003175  min_lr: 0.003175  loss: 2.6152 (2.6457)  weight_decay: 0.0500 (0.0500)  time: 0.5742  data: 0.0004  max mem: 42573
Epoch: [104]  [ 30/312]  eta: 0:03:48  lr: 0.003174  min_lr: 0.003174  loss: 2.4584 (2.5647)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [104]  [ 40/312]  eta: 0:03:15  lr: 0.003173  min_lr: 0.003173  loss: 2.5979 (2.5809)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [104]  [ 50/312]  eta: 0:02:54  lr: 0.003173  min_lr: 0.003173  loss: 2.7222 (2.5956)  weight_decay: 0.0500 (0.0500)  time: 0.4415  data: 0.0004  max mem: 42573
Epoch: [104]  [ 60/312]  eta: 0:02:38  lr: 0.003172  min_lr: 0.003172  loss: 2.6171 (2.5876)  weight_decay: 0.0500 (0.0500)  time: 0.4416  data: 0.0004  max mem: 42573
Epoch: [104]  [ 70/312]  eta: 0:02:25  lr: 0.003172  min_lr: 0.003172  loss: 2.3867 (2.5656)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [104]  [ 80/312]  eta: 0:02:14  lr: 0.003171  min_lr: 0.003171  loss: 2.3867 (2.5725)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [104]  [ 90/312]  eta: 0:02:05  lr: 0.003171  min_lr: 0.003171  loss: 2.5688 (2.5827)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [104]  [100/312]  eta: 0:01:56  lr: 0.003170  min_lr: 0.003170  loss: 2.7277 (2.5933)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [104]  [110/312]  eta: 0:01:49  lr: 0.003169  min_lr: 0.003169  loss: 2.7277 (2.6015)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [104]  [120/312]  eta: 0:01:42  lr: 0.003169  min_lr: 0.003169  loss: 2.7170 (2.6039)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [104]  [130/312]  eta: 0:01:35  lr: 0.003168  min_lr: 0.003168  loss: 2.7170 (2.6045)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [104]  [140/312]  eta: 0:01:29  lr: 0.003168  min_lr: 0.003168  loss: 2.6288 (2.5938)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [104]  [150/312]  eta: 0:01:23  lr: 0.003167  min_lr: 0.003167  loss: 2.6040 (2.5877)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [104]  [160/312]  eta: 0:01:17  lr: 0.003166  min_lr: 0.003166  loss: 2.3671 (2.5685)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0004  max mem: 42573
Epoch: [104]  [170/312]  eta: 0:01:11  lr: 0.003166  min_lr: 0.003166  loss: 2.4259 (2.5731)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [104]  [180/312]  eta: 0:01:05  lr: 0.003165  min_lr: 0.003165  loss: 2.6628 (2.5760)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0003  max mem: 42573
Epoch: [104]  [190/312]  eta: 0:01:00  lr: 0.003165  min_lr: 0.003165  loss: 2.5571 (2.5693)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0003  max mem: 42573
Epoch: [104]  [200/312]  eta: 0:00:55  lr: 0.003164  min_lr: 0.003164  loss: 2.6074 (2.5730)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [104]  [210/312]  eta: 0:00:49  lr: 0.003164  min_lr: 0.003164  loss: 2.7007 (2.5767)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [104]  [220/312]  eta: 0:00:44  lr: 0.003163  min_lr: 0.003163  loss: 2.4535 (2.5718)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [104]  [230/312]  eta: 0:00:39  lr: 0.003162  min_lr: 0.003162  loss: 2.4535 (2.5720)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [104]  [240/312]  eta: 0:00:34  lr: 0.003162  min_lr: 0.003162  loss: 2.5988 (2.5735)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [104]  [250/312]  eta: 0:00:29  lr: 0.003161  min_lr: 0.003161  loss: 2.6211 (2.5776)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0003  max mem: 42573
Epoch: [104]  [260/312]  eta: 0:00:24  lr: 0.003161  min_lr: 0.003161  loss: 2.7982 (2.5835)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0003  max mem: 42573
Epoch: [104]  [270/312]  eta: 0:00:20  lr: 0.003160  min_lr: 0.003160  loss: 2.6956 (2.5840)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0003  max mem: 42573
Epoch: [104]  [280/312]  eta: 0:00:15  lr: 0.003159  min_lr: 0.003159  loss: 2.6956 (2.5876)  weight_decay: 0.0500 (0.0500)  time: 0.4348  data: 0.0009  max mem: 42573
Epoch: [104]  [290/312]  eta: 0:00:10  lr: 0.003159  min_lr: 0.003159  loss: 2.6634 (2.5901)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0008  max mem: 42573
Epoch: [104]  [300/312]  eta: 0:00:05  lr: 0.003158  min_lr: 0.003158  loss: 2.7595 (2.5998)  weight_decay: 0.0500 (0.0500)  time: 0.4324  data: 0.0001  max mem: 42573
Epoch: [104]  [310/312]  eta: 0:00:00  lr: 0.003158  min_lr: 0.003158  loss: 2.7057 (2.5978)  weight_decay: 0.0500 (0.0500)  time: 0.4323  data: 0.0001  max mem: 42573
Epoch: [104]  [311/312]  eta: 0:00:00  lr: 0.003158  min_lr: 0.003158  loss: 2.6950 (2.5967)  weight_decay: 0.0500 (0.0500)  time: 0.4323  data: 0.0001  max mem: 42573
Epoch: [104] Total time: 0:02:28 (0.4747 s / it)
Averaged stats: lr: 0.003158  min_lr: 0.003158  loss: 2.6950 (2.6016)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:00:44  loss: 1.0047 (1.0047)  acc1: 77.3438 (77.3438)  acc5: 92.1875 (92.1875)  time: 4.8917  data: 4.7823  max mem: 42573
Test:  [8/9]  eta: 0:00:00  loss: 1.3241 (1.2574)  acc1: 69.2708 (69.5680)  acc5: 90.3646 (88.7040)  time: 0.6201  data: 0.5314  max mem: 42573
Test: Total time: 0:00:05 (0.6279 s / it)
* Acc@1 70.060 Acc@5 89.448 loss 1.232
Accuracy of the model on the 50000 test images: 70.1%
Max accuracy: 70.71%
Epoch: [105]  [  0/312]  eta: 0:47:12  lr: 0.003158  min_lr: 0.003158  loss: 3.3808 (3.3808)  weight_decay: 0.0500 (0.0500)  time: 9.0770  data: 8.2063  max mem: 42573
Epoch: [105]  [ 10/312]  eta: 0:07:19  lr: 0.003157  min_lr: 0.003157  loss: 2.9459 (2.7476)  weight_decay: 0.0500 (0.0500)  time: 1.4543  data: 0.7464  max mem: 42573
Epoch: [105]  [ 20/312]  eta: 0:04:42  lr: 0.003156  min_lr: 0.003156  loss: 2.8441 (2.7231)  weight_decay: 0.0500 (0.0500)  time: 0.5627  data: 0.0004  max mem: 42573
Epoch: [105]  [ 30/312]  eta: 0:03:44  lr: 0.003156  min_lr: 0.003156  loss: 2.7293 (2.7115)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0003  max mem: 42573
Epoch: [105]  [ 40/312]  eta: 0:03:12  lr: 0.003155  min_lr: 0.003155  loss: 2.6922 (2.6868)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [105]  [ 50/312]  eta: 0:02:51  lr: 0.003155  min_lr: 0.003155  loss: 2.7387 (2.6906)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0005  max mem: 42573
Epoch: [105]  [ 60/312]  eta: 0:02:35  lr: 0.003154  min_lr: 0.003154  loss: 2.8085 (2.6860)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [105]  [ 70/312]  eta: 0:02:23  lr: 0.003153  min_lr: 0.003153  loss: 2.7434 (2.6694)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [105]  [ 80/312]  eta: 0:02:12  lr: 0.003153  min_lr: 0.003153  loss: 2.5421 (2.6730)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [105]  [ 90/312]  eta: 0:02:03  lr: 0.003152  min_lr: 0.003152  loss: 2.6985 (2.6730)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [105]  [100/312]  eta: 0:01:55  lr: 0.003152  min_lr: 0.003152  loss: 2.6890 (2.6485)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [105]  [110/312]  eta: 0:01:48  lr: 0.003151  min_lr: 0.003151  loss: 2.5939 (2.6485)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0004  max mem: 42573
Epoch: [105]  [120/312]  eta: 0:01:41  lr: 0.003151  min_lr: 0.003151  loss: 2.6103 (2.6448)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0004  max mem: 42573
Epoch: [105]  [130/312]  eta: 0:01:34  lr: 0.003150  min_lr: 0.003150  loss: 2.7174 (2.6435)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [105]  [140/312]  eta: 0:01:28  lr: 0.003149  min_lr: 0.003149  loss: 2.8260 (2.6484)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [105]  [150/312]  eta: 0:01:22  lr: 0.003149  min_lr: 0.003149  loss: 2.7401 (2.6449)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [105]  [160/312]  eta: 0:01:16  lr: 0.003148  min_lr: 0.003148  loss: 2.6480 (2.6396)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [105]  [170/312]  eta: 0:01:10  lr: 0.003148  min_lr: 0.003148  loss: 2.7851 (2.6446)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [105]  [180/312]  eta: 0:01:05  lr: 0.003147  min_lr: 0.003147  loss: 2.7857 (2.6489)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0003  max mem: 42573
Epoch: [105]  [190/312]  eta: 0:01:00  lr: 0.003146  min_lr: 0.003146  loss: 2.7857 (2.6492)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [105]  [200/312]  eta: 0:00:54  lr: 0.003146  min_lr: 0.003146  loss: 2.7634 (2.6523)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [105]  [210/312]  eta: 0:00:49  lr: 0.003145  min_lr: 0.003145  loss: 2.7975 (2.6616)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0003  max mem: 42573
Epoch: [105]  [220/312]  eta: 0:00:44  lr: 0.003145  min_lr: 0.003145  loss: 2.6706 (2.6540)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0003  max mem: 42573
Epoch: [105]  [230/312]  eta: 0:00:39  lr: 0.003144  min_lr: 0.003144  loss: 2.5933 (2.6443)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [105]  [240/312]  eta: 0:00:34  lr: 0.003143  min_lr: 0.003143  loss: 2.4756 (2.6438)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [105]  [250/312]  eta: 0:00:29  lr: 0.003143  min_lr: 0.003143  loss: 2.6759 (2.6467)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [105]  [260/312]  eta: 0:00:24  lr: 0.003142  min_lr: 0.003142  loss: 2.7257 (2.6453)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0003  max mem: 42573
Epoch: [105]  [270/312]  eta: 0:00:19  lr: 0.003142  min_lr: 0.003142  loss: 2.7487 (2.6450)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [105]  [280/312]  eta: 0:00:15  lr: 0.003141  min_lr: 0.003141  loss: 2.6577 (2.6405)  weight_decay: 0.0500 (0.0500)  time: 0.4347  data: 0.0009  max mem: 42573
Epoch: [105]  [290/312]  eta: 0:00:10  lr: 0.003140  min_lr: 0.003140  loss: 2.4664 (2.6422)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0008  max mem: 42573
Epoch: [105]  [300/312]  eta: 0:00:05  lr: 0.003140  min_lr: 0.003140  loss: 2.7180 (2.6390)  weight_decay: 0.0500 (0.0500)  time: 0.4324  data: 0.0001  max mem: 42573
Epoch: [105]  [310/312]  eta: 0:00:00  lr: 0.003139  min_lr: 0.003139  loss: 2.7286 (2.6441)  weight_decay: 0.0500 (0.0500)  time: 0.4323  data: 0.0001  max mem: 42573
Epoch: [105]  [311/312]  eta: 0:00:00  lr: 0.003139  min_lr: 0.003139  loss: 2.7286 (2.6419)  weight_decay: 0.0500 (0.0500)  time: 0.4323  data: 0.0001  max mem: 42573
Epoch: [105] Total time: 0:02:27 (0.4725 s / it)
Averaged stats: lr: 0.003139  min_lr: 0.003139  loss: 2.7286 (2.5986)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:00:43  loss: 1.0099 (1.0099)  acc1: 77.6042 (77.6042)  acc5: 91.1458 (91.1458)  time: 4.7889  data: 4.6795  max mem: 42573
Test:  [8/9]  eta: 0:00:00  loss: 1.4212 (1.3011)  acc1: 70.0521 (68.8000)  acc5: 89.0625 (88.9920)  time: 0.6087  data: 0.5200  max mem: 42573
Test: Total time: 0:00:05 (0.6275 s / it)
* Acc@1 69.526 Acc@5 88.996 loss 1.303
Accuracy of the model on the 50000 test images: 69.5%
Max accuracy: 70.71%
Epoch: [106]  [  0/312]  eta: 0:50:45  lr: 0.003139  min_lr: 0.003139  loss: 1.9915 (1.9915)  weight_decay: 0.0500 (0.0500)  time: 9.7605  data: 6.1029  max mem: 42573
Epoch: [106]  [ 10/312]  eta: 0:07:35  lr: 0.003139  min_lr: 0.003139  loss: 2.5594 (2.4660)  weight_decay: 0.0500 (0.0500)  time: 1.5089  data: 0.7774  max mem: 42573
Epoch: [106]  [ 20/312]  eta: 0:04:51  lr: 0.003138  min_lr: 0.003138  loss: 2.5594 (2.5260)  weight_decay: 0.0500 (0.0500)  time: 0.5585  data: 0.1226  max mem: 42573
Epoch: [106]  [ 30/312]  eta: 0:03:49  lr: 0.003137  min_lr: 0.003137  loss: 2.6688 (2.5573)  weight_decay: 0.0500 (0.0500)  time: 0.4332  data: 0.0004  max mem: 42573
Epoch: [106]  [ 40/312]  eta: 0:03:16  lr: 0.003137  min_lr: 0.003137  loss: 2.6511 (2.5260)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [106]  [ 50/312]  eta: 0:02:54  lr: 0.003136  min_lr: 0.003136  loss: 2.4519 (2.5245)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [106]  [ 60/312]  eta: 0:02:38  lr: 0.003136  min_lr: 0.003136  loss: 2.5951 (2.5429)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [106]  [ 70/312]  eta: 0:02:25  lr: 0.003135  min_lr: 0.003135  loss: 2.6675 (2.5508)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [106]  [ 80/312]  eta: 0:02:14  lr: 0.003134  min_lr: 0.003134  loss: 2.5566 (2.5425)  weight_decay: 0.0500 (0.0500)  time: 0.4341  data: 0.0004  max mem: 42573
Epoch: [106]  [ 90/312]  eta: 0:02:05  lr: 0.003134  min_lr: 0.003134  loss: 2.5566 (2.5512)  weight_decay: 0.0500 (0.0500)  time: 0.4342  data: 0.0004  max mem: 42573
Epoch: [106]  [100/312]  eta: 0:01:56  lr: 0.003133  min_lr: 0.003133  loss: 2.5884 (2.5407)  weight_decay: 0.0500 (0.0500)  time: 0.4341  data: 0.0004  max mem: 42573
Epoch: [106]  [110/312]  eta: 0:01:49  lr: 0.003133  min_lr: 0.003133  loss: 2.4333 (2.5322)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0004  max mem: 42573
Epoch: [106]  [120/312]  eta: 0:01:42  lr: 0.003132  min_lr: 0.003132  loss: 2.6514 (2.5548)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [106]  [130/312]  eta: 0:01:35  lr: 0.003131  min_lr: 0.003131  loss: 2.7240 (2.5635)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0004  max mem: 42573
Epoch: [106]  [140/312]  eta: 0:01:29  lr: 0.003131  min_lr: 0.003131  loss: 2.6868 (2.5667)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0003  max mem: 42573
Epoch: [106]  [150/312]  eta: 0:01:22  lr: 0.003130  min_lr: 0.003130  loss: 2.5106 (2.5627)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [106]  [160/312]  eta: 0:01:17  lr: 0.003130  min_lr: 0.003130  loss: 2.4811 (2.5572)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [106]  [170/312]  eta: 0:01:11  lr: 0.003129  min_lr: 0.003129  loss: 2.3957 (2.5504)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0003  max mem: 42573
Epoch: [106]  [180/312]  eta: 0:01:05  lr: 0.003129  min_lr: 0.003129  loss: 2.3017 (2.5457)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [106]  [190/312]  eta: 0:01:00  lr: 0.003128  min_lr: 0.003128  loss: 2.8026 (2.5607)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [106]  [200/312]  eta: 0:00:55  lr: 0.003127  min_lr: 0.003127  loss: 2.8207 (2.5646)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [106]  [210/312]  eta: 0:00:49  lr: 0.003127  min_lr: 0.003127  loss: 2.5727 (2.5603)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [106]  [220/312]  eta: 0:00:44  lr: 0.003126  min_lr: 0.003126  loss: 2.5926 (2.5634)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [106]  [230/312]  eta: 0:00:39  lr: 0.003126  min_lr: 0.003126  loss: 2.6620 (2.5640)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [106]  [240/312]  eta: 0:00:34  lr: 0.003125  min_lr: 0.003125  loss: 2.6206 (2.5637)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [106]  [250/312]  eta: 0:00:29  lr: 0.003124  min_lr: 0.003124  loss: 2.4813 (2.5606)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [106]  [260/312]  eta: 0:00:24  lr: 0.003124  min_lr: 0.003124  loss: 2.4802 (2.5591)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0003  max mem: 42573
Epoch: [106]  [270/312]  eta: 0:00:20  lr: 0.003123  min_lr: 0.003123  loss: 2.6594 (2.5621)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [106]  [280/312]  eta: 0:00:15  lr: 0.003123  min_lr: 0.003123  loss: 2.7096 (2.5683)  weight_decay: 0.0500 (0.0500)  time: 0.4344  data: 0.0009  max mem: 42573
Epoch: [106]  [290/312]  eta: 0:00:10  lr: 0.003122  min_lr: 0.003122  loss: 2.6602 (2.5700)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0008  max mem: 42573
Epoch: [106]  [300/312]  eta: 0:00:05  lr: 0.003121  min_lr: 0.003121  loss: 2.5850 (2.5682)  weight_decay: 0.0500 (0.0500)  time: 0.4323  data: 0.0001  max mem: 42573
Epoch: [106]  [310/312]  eta: 0:00:00  lr: 0.003121  min_lr: 0.003121  loss: 2.5772 (2.5700)  weight_decay: 0.0500 (0.0500)  time: 0.4322  data: 0.0001  max mem: 42573
Epoch: [106]  [311/312]  eta: 0:00:00  lr: 0.003121  min_lr: 0.003121  loss: 2.5772 (2.5717)  weight_decay: 0.0500 (0.0500)  time: 0.4323  data: 0.0001  max mem: 42573
Epoch: [106] Total time: 0:02:28 (0.4746 s / it)
Averaged stats: lr: 0.003121  min_lr: 0.003121  loss: 2.5772 (2.6079)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:00:42  loss: 1.1673 (1.1673)  acc1: 76.3021 (76.3021)  acc5: 91.9271 (91.9271)  time: 4.6755  data: 4.5661  max mem: 42573
Test:  [8/9]  eta: 0:00:00  loss: 1.5558 (1.4230)  acc1: 65.6250 (67.3920)  acc5: 88.5417 (88.4800)  time: 0.5947  data: 0.5074  max mem: 42573
Test: Total time: 0:00:05 (0.6132 s / it)
* Acc@1 68.494 Acc@5 88.426 loss 1.409
Accuracy of the model on the 50000 test images: 68.5%
Max accuracy: 70.71%
Epoch: [107]  [  0/312]  eta: 0:47:46  lr: 0.003121  min_lr: 0.003121  loss: 1.8266 (1.8266)  weight_decay: 0.0500 (0.0500)  time: 9.1873  data: 6.1222  max mem: 42573
Epoch: [107]  [ 10/312]  eta: 0:07:33  lr: 0.003120  min_lr: 0.003120  loss: 2.8449 (2.5506)  weight_decay: 0.0500 (0.0500)  time: 1.5026  data: 0.6343  max mem: 42573
Epoch: [107]  [ 20/312]  eta: 0:04:50  lr: 0.003119  min_lr: 0.003119  loss: 2.8187 (2.6316)  weight_decay: 0.0500 (0.0500)  time: 0.5835  data: 0.0429  max mem: 42573
Epoch: [107]  [ 30/312]  eta: 0:03:49  lr: 0.003119  min_lr: 0.003119  loss: 2.5609 (2.6239)  weight_decay: 0.0500 (0.0500)  time: 0.4331  data: 0.0004  max mem: 42573
Epoch: [107]  [ 40/312]  eta: 0:03:15  lr: 0.003118  min_lr: 0.003118  loss: 2.5880 (2.6439)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [107]  [ 50/312]  eta: 0:02:53  lr: 0.003118  min_lr: 0.003118  loss: 2.6322 (2.6202)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [107]  [ 60/312]  eta: 0:02:37  lr: 0.003117  min_lr: 0.003117  loss: 2.6307 (2.6280)  weight_decay: 0.0500 (0.0500)  time: 0.4332  data: 0.0004  max mem: 42573
Epoch: [107]  [ 70/312]  eta: 0:02:24  lr: 0.003116  min_lr: 0.003116  loss: 2.7626 (2.6618)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [107]  [ 80/312]  eta: 0:02:14  lr: 0.003116  min_lr: 0.003116  loss: 2.7617 (2.6414)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [107]  [ 90/312]  eta: 0:02:04  lr: 0.003115  min_lr: 0.003115  loss: 2.8651 (2.6664)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [107]  [100/312]  eta: 0:01:56  lr: 0.003115  min_lr: 0.003115  loss: 2.8651 (2.6670)  weight_decay: 0.0500 (0.0500)  time: 0.4376  data: 0.0004  max mem: 42573
Epoch: [107]  [110/312]  eta: 0:01:49  lr: 0.003114  min_lr: 0.003114  loss: 2.6426 (2.6598)  weight_decay: 0.0500 (0.0500)  time: 0.4377  data: 0.0004  max mem: 42573
Epoch: [107]  [120/312]  eta: 0:01:42  lr: 0.003114  min_lr: 0.003114  loss: 2.5385 (2.6420)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0003  max mem: 42573
Epoch: [107]  [130/312]  eta: 0:01:35  lr: 0.003113  min_lr: 0.003113  loss: 2.5049 (2.6313)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [107]  [140/312]  eta: 0:01:29  lr: 0.003112  min_lr: 0.003112  loss: 2.7468 (2.6263)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [107]  [150/312]  eta: 0:01:22  lr: 0.003112  min_lr: 0.003112  loss: 2.5045 (2.6194)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [107]  [160/312]  eta: 0:01:17  lr: 0.003111  min_lr: 0.003111  loss: 2.5045 (2.6185)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [107]  [170/312]  eta: 0:01:11  lr: 0.003111  min_lr: 0.003111  loss: 2.6524 (2.6111)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [107]  [180/312]  eta: 0:01:05  lr: 0.003110  min_lr: 0.003110  loss: 2.7628 (2.6287)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [107]  [190/312]  eta: 0:01:00  lr: 0.003109  min_lr: 0.003109  loss: 2.8596 (2.6243)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [107]  [200/312]  eta: 0:00:55  lr: 0.003109  min_lr: 0.003109  loss: 2.4089 (2.6127)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [107]  [210/312]  eta: 0:00:49  lr: 0.003108  min_lr: 0.003108  loss: 2.5710 (2.6110)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0004  max mem: 42573
Epoch: [107]  [220/312]  eta: 0:00:44  lr: 0.003108  min_lr: 0.003108  loss: 2.5033 (2.6045)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [107]  [230/312]  eta: 0:00:39  lr: 0.003107  min_lr: 0.003107  loss: 2.3634 (2.6020)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [107]  [240/312]  eta: 0:00:34  lr: 0.003106  min_lr: 0.003106  loss: 2.5456 (2.5999)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [107]  [250/312]  eta: 0:00:29  lr: 0.003106  min_lr: 0.003106  loss: 2.5456 (2.6039)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [107]  [260/312]  eta: 0:00:24  lr: 0.003105  min_lr: 0.003105  loss: 2.6222 (2.6009)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [107]  [270/312]  eta: 0:00:20  lr: 0.003105  min_lr: 0.003105  loss: 2.7318 (2.6093)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [107]  [280/312]  eta: 0:00:15  lr: 0.003104  min_lr: 0.003104  loss: 2.7318 (2.6094)  weight_decay: 0.0500 (0.0500)  time: 0.4346  data: 0.0010  max mem: 42573
Epoch: [107]  [290/312]  eta: 0:00:10  lr: 0.003103  min_lr: 0.003103  loss: 2.7077 (2.6185)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0008  max mem: 42573
Epoch: [107]  [300/312]  eta: 0:00:05  lr: 0.003103  min_lr: 0.003103  loss: 2.8229 (2.6232)  weight_decay: 0.0500 (0.0500)  time: 0.4324  data: 0.0001  max mem: 42573
Epoch: [107]  [310/312]  eta: 0:00:00  lr: 0.003102  min_lr: 0.003102  loss: 2.5903 (2.6145)  weight_decay: 0.0500 (0.0500)  time: 0.4324  data: 0.0001  max mem: 42573
Epoch: [107]  [311/312]  eta: 0:00:00  lr: 0.003102  min_lr: 0.003102  loss: 2.5953 (2.6152)  weight_decay: 0.0500 (0.0500)  time: 0.4324  data: 0.0001  max mem: 42573
Epoch: [107] Total time: 0:02:28 (0.4745 s / it)
Averaged stats: lr: 0.003102  min_lr: 0.003102  loss: 2.5953 (2.5879)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:00:44  loss: 0.9739 (0.9739)  acc1: 75.5208 (75.5208)  acc5: 91.1458 (91.1458)  time: 4.9491  data: 4.8397  max mem: 42573
Test:  [8/9]  eta: 0:00:00  loss: 1.2649 (1.2220)  acc1: 67.4479 (68.6400)  acc5: 90.3646 (88.8640)  time: 0.6255  data: 0.5378  max mem: 42573
Test: Total time: 0:00:05 (0.6485 s / it)
* Acc@1 70.148 Acc@5 89.524 loss 1.203
Accuracy of the model on the 50000 test images: 70.1%
Max accuracy: 70.71%
Epoch: [108]  [  0/312]  eta: 0:48:52  lr: 0.003102  min_lr: 0.003102  loss: 2.0341 (2.0341)  weight_decay: 0.0500 (0.0500)  time: 9.3994  data: 6.7982  max mem: 42573
Epoch: [108]  [ 10/312]  eta: 0:07:07  lr: 0.003101  min_lr: 0.003101  loss: 2.6454 (2.6869)  weight_decay: 0.0500 (0.0500)  time: 1.4155  data: 0.6447  max mem: 42573
Epoch: [108]  [ 20/312]  eta: 0:04:36  lr: 0.003101  min_lr: 0.003101  loss: 2.8721 (2.7313)  weight_decay: 0.0500 (0.0500)  time: 0.5252  data: 0.0149  max mem: 42573
Epoch: [108]  [ 30/312]  eta: 0:03:40  lr: 0.003100  min_lr: 0.003100  loss: 2.7265 (2.6822)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [108]  [ 40/312]  eta: 0:03:09  lr: 0.003100  min_lr: 0.003100  loss: 2.7815 (2.7201)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [108]  [ 50/312]  eta: 0:02:49  lr: 0.003099  min_lr: 0.003099  loss: 2.7984 (2.7033)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [108]  [ 60/312]  eta: 0:02:33  lr: 0.003098  min_lr: 0.003098  loss: 2.6314 (2.6820)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [108]  [ 70/312]  eta: 0:02:21  lr: 0.003098  min_lr: 0.003098  loss: 2.3928 (2.6145)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [108]  [ 80/312]  eta: 0:02:11  lr: 0.003097  min_lr: 0.003097  loss: 2.2249 (2.5936)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [108]  [ 90/312]  eta: 0:02:02  lr: 0.003097  min_lr: 0.003097  loss: 2.6722 (2.6074)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [108]  [100/312]  eta: 0:01:54  lr: 0.003096  min_lr: 0.003096  loss: 2.6722 (2.6063)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [108]  [110/312]  eta: 0:01:47  lr: 0.003095  min_lr: 0.003095  loss: 2.5383 (2.5989)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [108]  [120/312]  eta: 0:01:40  lr: 0.003095  min_lr: 0.003095  loss: 2.6164 (2.6051)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [108]  [130/312]  eta: 0:01:34  lr: 0.003094  min_lr: 0.003094  loss: 2.6384 (2.6071)  weight_decay: 0.0500 (0.0500)  time: 0.4386  data: 0.0004  max mem: 42573
Epoch: [108]  [140/312]  eta: 0:01:27  lr: 0.003094  min_lr: 0.003094  loss: 2.5624 (2.5974)  weight_decay: 0.0500 (0.0500)  time: 0.4386  data: 0.0003  max mem: 42573
Epoch: [108]  [150/312]  eta: 0:01:21  lr: 0.003093  min_lr: 0.003093  loss: 2.3817 (2.5890)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [108]  [160/312]  eta: 0:01:16  lr: 0.003092  min_lr: 0.003092  loss: 2.5140 (2.5904)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [108]  [170/312]  eta: 0:01:10  lr: 0.003092  min_lr: 0.003092  loss: 2.6781 (2.6023)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [108]  [180/312]  eta: 0:01:05  lr: 0.003091  min_lr: 0.003091  loss: 2.7234 (2.5981)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [108]  [190/312]  eta: 0:00:59  lr: 0.003091  min_lr: 0.003091  loss: 2.5729 (2.5985)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [108]  [200/312]  eta: 0:00:54  lr: 0.003090  min_lr: 0.003090  loss: 2.5729 (2.6024)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [108]  [210/312]  eta: 0:00:49  lr: 0.003089  min_lr: 0.003089  loss: 2.6065 (2.6039)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [108]  [220/312]  eta: 0:00:44  lr: 0.003089  min_lr: 0.003089  loss: 2.6648 (2.6073)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [108]  [230/312]  eta: 0:00:39  lr: 0.003088  min_lr: 0.003088  loss: 2.6822 (2.6111)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [108]  [240/312]  eta: 0:00:34  lr: 0.003088  min_lr: 0.003088  loss: 2.6472 (2.6101)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [108]  [250/312]  eta: 0:00:29  lr: 0.003087  min_lr: 0.003087  loss: 2.7725 (2.6172)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [108]  [260/312]  eta: 0:00:24  lr: 0.003086  min_lr: 0.003086  loss: 2.8508 (2.6244)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [108]  [270/312]  eta: 0:00:19  lr: 0.003086  min_lr: 0.003086  loss: 2.7067 (2.6225)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [108]  [280/312]  eta: 0:00:15  lr: 0.003085  min_lr: 0.003085  loss: 2.7067 (2.6255)  weight_decay: 0.0500 (0.0500)  time: 0.4342  data: 0.0009  max mem: 42573
Epoch: [108]  [290/312]  eta: 0:00:10  lr: 0.003085  min_lr: 0.003085  loss: 2.7300 (2.6211)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0008  max mem: 42573
Epoch: [108]  [300/312]  eta: 0:00:05  lr: 0.003084  min_lr: 0.003084  loss: 2.2560 (2.6110)  weight_decay: 0.0500 (0.0500)  time: 0.4323  data: 0.0001  max mem: 42573
Epoch: [108]  [310/312]  eta: 0:00:00  lr: 0.003083  min_lr: 0.003083  loss: 2.5906 (2.6151)  weight_decay: 0.0500 (0.0500)  time: 0.4323  data: 0.0001  max mem: 42573
Epoch: [108]  [311/312]  eta: 0:00:00  lr: 0.003083  min_lr: 0.003083  loss: 2.6809 (2.6154)  weight_decay: 0.0500 (0.0500)  time: 0.4323  data: 0.0001  max mem: 42573
Epoch: [108] Total time: 0:02:27 (0.4716 s / it)
Averaged stats: lr: 0.003083  min_lr: 0.003083  loss: 2.6809 (2.5906)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:00:44  loss: 0.9516 (0.9516)  acc1: 75.5208 (75.5208)  acc5: 92.9688 (92.9688)  time: 4.9036  data: 4.7942  max mem: 42573
Test:  [8/9]  eta: 0:00:00  loss: 1.3288 (1.2195)  acc1: 69.2708 (68.9600)  acc5: 88.0208 (89.2800)  time: 0.6221  data: 0.5327  max mem: 42573
Test: Total time: 0:00:05 (0.6411 s / it)
* Acc@1 69.782 Acc@5 89.330 loss 1.229
Accuracy of the model on the 50000 test images: 69.8%
Max accuracy: 70.71%
Epoch: [109]  [  0/312]  eta: 0:45:38  lr: 0.003083  min_lr: 0.003083  loss: 2.8608 (2.8608)  weight_decay: 0.0500 (0.0500)  time: 8.7783  data: 6.1153  max mem: 42573
Epoch: [109]  [ 10/312]  eta: 0:06:56  lr: 0.003083  min_lr: 0.003083  loss: 2.5943 (2.6019)  weight_decay: 0.0500 (0.0500)  time: 1.3778  data: 0.6698  max mem: 42573
Epoch: [109]  [ 20/312]  eta: 0:04:31  lr: 0.003082  min_lr: 0.003082  loss: 2.5686 (2.5171)  weight_decay: 0.0500 (0.0500)  time: 0.5357  data: 0.0628  max mem: 42573
Epoch: [109]  [ 30/312]  eta: 0:03:36  lr: 0.003081  min_lr: 0.003081  loss: 2.2869 (2.4682)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [109]  [ 40/312]  eta: 0:03:06  lr: 0.003081  min_lr: 0.003081  loss: 2.5419 (2.4818)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [109]  [ 50/312]  eta: 0:02:46  lr: 0.003080  min_lr: 0.003080  loss: 2.5635 (2.4885)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [109]  [ 60/312]  eta: 0:02:32  lr: 0.003080  min_lr: 0.003080  loss: 2.6420 (2.4999)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [109]  [ 70/312]  eta: 0:02:20  lr: 0.003079  min_lr: 0.003079  loss: 2.5043 (2.5052)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [109]  [ 80/312]  eta: 0:02:10  lr: 0.003078  min_lr: 0.003078  loss: 2.4813 (2.5239)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [109]  [ 90/312]  eta: 0:02:01  lr: 0.003078  min_lr: 0.003078  loss: 2.7768 (2.5597)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [109]  [100/312]  eta: 0:01:53  lr: 0.003077  min_lr: 0.003077  loss: 2.8774 (2.5858)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [109]  [110/312]  eta: 0:01:46  lr: 0.003077  min_lr: 0.003077  loss: 2.7045 (2.5722)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [109]  [120/312]  eta: 0:01:39  lr: 0.003076  min_lr: 0.003076  loss: 2.7705 (2.5963)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [109]  [130/312]  eta: 0:01:33  lr: 0.003075  min_lr: 0.003075  loss: 2.8113 (2.6085)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [109]  [140/312]  eta: 0:01:27  lr: 0.003075  min_lr: 0.003075  loss: 2.7693 (2.6158)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [109]  [150/312]  eta: 0:01:21  lr: 0.003074  min_lr: 0.003074  loss: 2.7946 (2.6216)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [109]  [160/312]  eta: 0:01:15  lr: 0.003074  min_lr: 0.003074  loss: 2.8045 (2.6249)  weight_decay: 0.0500 (0.0500)  time: 0.4387  data: 0.0003  max mem: 42573
Epoch: [109]  [170/312]  eta: 0:01:10  lr: 0.003073  min_lr: 0.003073  loss: 2.7236 (2.6165)  weight_decay: 0.0500 (0.0500)  time: 0.4386  data: 0.0004  max mem: 42573
Epoch: [109]  [180/312]  eta: 0:01:04  lr: 0.003072  min_lr: 0.003072  loss: 2.5707 (2.6200)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [109]  [190/312]  eta: 0:00:59  lr: 0.003072  min_lr: 0.003072  loss: 2.7333 (2.6233)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0003  max mem: 42573
Epoch: [109]  [200/312]  eta: 0:00:54  lr: 0.003071  min_lr: 0.003071  loss: 2.6883 (2.6215)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [109]  [210/312]  eta: 0:00:49  lr: 0.003071  min_lr: 0.003071  loss: 2.6797 (2.6241)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [109]  [220/312]  eta: 0:00:44  lr: 0.003070  min_lr: 0.003070  loss: 2.7093 (2.6219)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [109]  [230/312]  eta: 0:00:39  lr: 0.003069  min_lr: 0.003069  loss: 2.7716 (2.6333)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [109]  [240/312]  eta: 0:00:34  lr: 0.003069  min_lr: 0.003069  loss: 2.8908 (2.6341)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [109]  [250/312]  eta: 0:00:29  lr: 0.003068  min_lr: 0.003068  loss: 2.7474 (2.6343)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [109]  [260/312]  eta: 0:00:24  lr: 0.003067  min_lr: 0.003067  loss: 2.4770 (2.6191)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [109]  [270/312]  eta: 0:00:19  lr: 0.003067  min_lr: 0.003067  loss: 2.1957 (2.6124)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [109]  [280/312]  eta: 0:00:15  lr: 0.003066  min_lr: 0.003066  loss: 2.6212 (2.6126)  weight_decay: 0.0500 (0.0500)  time: 0.4345  data: 0.0011  max mem: 42573
Epoch: [109]  [290/312]  eta: 0:00:10  lr: 0.003066  min_lr: 0.003066  loss: 2.6212 (2.6129)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0010  max mem: 42573
Epoch: [109]  [300/312]  eta: 0:00:05  lr: 0.003065  min_lr: 0.003065  loss: 2.5946 (2.6085)  weight_decay: 0.0500 (0.0500)  time: 0.4324  data: 0.0001  max mem: 42573
Epoch: [109]  [310/312]  eta: 0:00:00  lr: 0.003064  min_lr: 0.003064  loss: 2.4668 (2.6059)  weight_decay: 0.0500 (0.0500)  time: 0.4324  data: 0.0001  max mem: 42573
Epoch: [109]  [311/312]  eta: 0:00:00  lr: 0.003064  min_lr: 0.003064  loss: 2.4039 (2.6052)  weight_decay: 0.0500 (0.0500)  time: 0.4323  data: 0.0001  max mem: 42573
Epoch: [109] Total time: 0:02:26 (0.4702 s / it)
Averaged stats: lr: 0.003064  min_lr: 0.003064  loss: 2.4039 (2.5837)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:00:43  loss: 0.9111 (0.9111)  acc1: 76.8229 (76.8229)  acc5: 93.4896 (93.4896)  time: 4.8787  data: 4.7693  max mem: 42573
Test:  [8/9]  eta: 0:00:00  loss: 1.1916 (1.1575)  acc1: 70.3125 (70.3360)  acc5: 91.9271 (90.2720)  time: 0.6239  data: 0.5300  max mem: 42573
Test: Total time: 0:00:05 (0.6463 s / it)
* Acc@1 71.106 Acc@5 90.108 loss 1.169
Accuracy of the model on the 50000 test images: 71.1%
Max accuracy: 71.11%
Epoch: [110]  [  0/312]  eta: 0:49:27  lr: 0.003064  min_lr: 0.003064  loss: 3.0126 (3.0126)  weight_decay: 0.0500 (0.0500)  time: 9.5115  data: 9.0054  max mem: 42573
Epoch: [110]  [ 10/312]  eta: 0:07:32  lr: 0.003064  min_lr: 0.003064  loss: 2.7295 (2.5864)  weight_decay: 0.0500 (0.0500)  time: 1.4980  data: 0.8190  max mem: 42573
Epoch: [110]  [ 20/312]  eta: 0:04:49  lr: 0.003063  min_lr: 0.003063  loss: 2.6398 (2.5515)  weight_decay: 0.0500 (0.0500)  time: 0.5648  data: 0.0004  max mem: 42573
Epoch: [110]  [ 30/312]  eta: 0:03:48  lr: 0.003062  min_lr: 0.003062  loss: 2.4397 (2.4646)  weight_decay: 0.0500 (0.0500)  time: 0.4331  data: 0.0003  max mem: 42573
Epoch: [110]  [ 40/312]  eta: 0:03:15  lr: 0.003062  min_lr: 0.003062  loss: 2.4397 (2.4756)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [110]  [ 50/312]  eta: 0:02:53  lr: 0.003061  min_lr: 0.003061  loss: 2.7560 (2.5420)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0005  max mem: 42573
Epoch: [110]  [ 60/312]  eta: 0:02:37  lr: 0.003061  min_lr: 0.003061  loss: 2.6522 (2.5213)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [110]  [ 70/312]  eta: 0:02:24  lr: 0.003060  min_lr: 0.003060  loss: 2.4056 (2.5211)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [110]  [ 80/312]  eta: 0:02:14  lr: 0.003059  min_lr: 0.003059  loss: 2.6288 (2.5393)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [110]  [ 90/312]  eta: 0:02:04  lr: 0.003059  min_lr: 0.003059  loss: 2.5569 (2.5265)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [110]  [100/312]  eta: 0:01:56  lr: 0.003058  min_lr: 0.003058  loss: 2.5569 (2.5188)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [110]  [110/312]  eta: 0:01:48  lr: 0.003058  min_lr: 0.003058  loss: 2.7895 (2.5467)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [110]  [120/312]  eta: 0:01:41  lr: 0.003057  min_lr: 0.003057  loss: 2.6969 (2.5495)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [110]  [130/312]  eta: 0:01:35  lr: 0.003056  min_lr: 0.003056  loss: 2.6868 (2.5518)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [110]  [140/312]  eta: 0:01:28  lr: 0.003056  min_lr: 0.003056  loss: 2.7314 (2.5612)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [110]  [150/312]  eta: 0:01:22  lr: 0.003055  min_lr: 0.003055  loss: 2.7783 (2.5656)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0004  max mem: 42573
Epoch: [110]  [160/312]  eta: 0:01:16  lr: 0.003055  min_lr: 0.003055  loss: 2.7783 (2.5759)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [110]  [170/312]  eta: 0:01:11  lr: 0.003054  min_lr: 0.003054  loss: 2.8065 (2.5947)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [110]  [180/312]  eta: 0:01:05  lr: 0.003053  min_lr: 0.003053  loss: 2.7943 (2.6019)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [110]  [190/312]  eta: 0:01:00  lr: 0.003053  min_lr: 0.003053  loss: 2.7093 (2.5959)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0003  max mem: 42573
Epoch: [110]  [200/312]  eta: 0:00:55  lr: 0.003052  min_lr: 0.003052  loss: 2.5657 (2.6010)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0003  max mem: 42573
Epoch: [110]  [210/312]  eta: 0:00:49  lr: 0.003051  min_lr: 0.003051  loss: 2.6348 (2.5900)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [110]  [220/312]  eta: 0:00:44  lr: 0.003051  min_lr: 0.003051  loss: 2.4908 (2.5811)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [110]  [230/312]  eta: 0:00:39  lr: 0.003050  min_lr: 0.003050  loss: 2.4908 (2.5775)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0003  max mem: 42573
Epoch: [110]  [240/312]  eta: 0:00:34  lr: 0.003050  min_lr: 0.003050  loss: 2.6888 (2.5822)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [110]  [250/312]  eta: 0:00:29  lr: 0.003049  min_lr: 0.003049  loss: 2.7075 (2.5765)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [110]  [260/312]  eta: 0:00:24  lr: 0.003048  min_lr: 0.003048  loss: 2.1939 (2.5633)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [110]  [270/312]  eta: 0:00:20  lr: 0.003048  min_lr: 0.003048  loss: 2.3542 (2.5699)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [110]  [280/312]  eta: 0:00:15  lr: 0.003047  min_lr: 0.003047  loss: 2.7142 (2.5723)  weight_decay: 0.0500 (0.0500)  time: 0.4342  data: 0.0009  max mem: 42573
Epoch: [110]  [290/312]  eta: 0:00:10  lr: 0.003047  min_lr: 0.003047  loss: 2.6388 (2.5702)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0008  max mem: 42573
Epoch: [110]  [300/312]  eta: 0:00:05  lr: 0.003046  min_lr: 0.003046  loss: 2.6446 (2.5689)  weight_decay: 0.0500 (0.0500)  time: 0.4325  data: 0.0001  max mem: 42573
Epoch: [110]  [310/312]  eta: 0:00:00  lr: 0.003045  min_lr: 0.003045  loss: 2.7840 (2.5734)  weight_decay: 0.0500 (0.0500)  time: 0.4324  data: 0.0001  max mem: 42573
Epoch: [110]  [311/312]  eta: 0:00:00  lr: 0.003045  min_lr: 0.003045  loss: 2.6446 (2.5734)  weight_decay: 0.0500 (0.0500)  time: 0.4325  data: 0.0001  max mem: 42573
Epoch: [110] Total time: 0:02:27 (0.4741 s / it)
Averaged stats: lr: 0.003045  min_lr: 0.003045  loss: 2.6446 (2.5845)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:00:44  loss: 0.9795 (0.9795)  acc1: 76.3021 (76.3021)  acc5: 91.1458 (91.1458)  time: 4.9695  data: 4.8600  max mem: 42573
Test:  [8/9]  eta: 0:00:00  loss: 1.3629 (1.2864)  acc1: 68.7500 (68.4480)  acc5: 90.1042 (88.9920)  time: 0.6275  data: 0.5401  max mem: 42573
Test: Total time: 0:00:05 (0.6356 s / it)
* Acc@1 69.272 Acc@5 88.826 loss 1.287
Accuracy of the model on the 50000 test images: 69.3%
Max accuracy: 71.11%
Epoch: [111]  [  0/312]  eta: 0:49:43  lr: 0.003045  min_lr: 0.003045  loss: 2.0990 (2.0990)  weight_decay: 0.0500 (0.0500)  time: 9.5626  data: 8.9931  max mem: 42573
Epoch: [111]  [ 10/312]  eta: 0:07:26  lr: 0.003045  min_lr: 0.003045  loss: 2.5544 (2.5168)  weight_decay: 0.0500 (0.0500)  time: 1.4799  data: 0.8179  max mem: 42573
Epoch: [111]  [ 20/312]  eta: 0:04:46  lr: 0.003044  min_lr: 0.003044  loss: 2.5544 (2.5272)  weight_decay: 0.0500 (0.0500)  time: 0.5522  data: 0.0004  max mem: 42573
Epoch: [111]  [ 30/312]  eta: 0:03:46  lr: 0.003043  min_lr: 0.003043  loss: 2.6417 (2.5716)  weight_decay: 0.0500 (0.0500)  time: 0.4330  data: 0.0004  max mem: 42573
Epoch: [111]  [ 40/312]  eta: 0:03:14  lr: 0.003043  min_lr: 0.003043  loss: 2.6713 (2.5565)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [111]  [ 50/312]  eta: 0:02:52  lr: 0.003042  min_lr: 0.003042  loss: 2.5820 (2.5557)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [111]  [ 60/312]  eta: 0:02:36  lr: 0.003042  min_lr: 0.003042  loss: 2.5899 (2.5735)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [111]  [ 70/312]  eta: 0:02:24  lr: 0.003041  min_lr: 0.003041  loss: 2.6373 (2.5906)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [111]  [ 80/312]  eta: 0:02:13  lr: 0.003040  min_lr: 0.003040  loss: 2.3956 (2.5655)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [111]  [ 90/312]  eta: 0:02:04  lr: 0.003040  min_lr: 0.003040  loss: 2.5898 (2.5866)  weight_decay: 0.0500 (0.0500)  time: 0.4380  data: 0.0004  max mem: 42573
Epoch: [111]  [100/312]  eta: 0:01:56  lr: 0.003039  min_lr: 0.003039  loss: 2.6322 (2.5663)  weight_decay: 0.0500 (0.0500)  time: 0.4380  data: 0.0004  max mem: 42573
Epoch: [111]  [110/312]  eta: 0:01:48  lr: 0.003038  min_lr: 0.003038  loss: 2.5770 (2.5653)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0005  max mem: 42573
Epoch: [111]  [120/312]  eta: 0:01:41  lr: 0.003038  min_lr: 0.003038  loss: 2.6590 (2.5662)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [111]  [130/312]  eta: 0:01:35  lr: 0.003037  min_lr: 0.003037  loss: 2.7637 (2.5834)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [111]  [140/312]  eta: 0:01:28  lr: 0.003037  min_lr: 0.003037  loss: 2.5797 (2.5663)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [111]  [150/312]  eta: 0:01:22  lr: 0.003036  min_lr: 0.003036  loss: 2.4631 (2.5766)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0003  max mem: 42573
Epoch: [111]  [160/312]  eta: 0:01:16  lr: 0.003035  min_lr: 0.003035  loss: 2.7123 (2.5781)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [111]  [170/312]  eta: 0:01:11  lr: 0.003035  min_lr: 0.003035  loss: 2.5004 (2.5687)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [111]  [180/312]  eta: 0:01:05  lr: 0.003034  min_lr: 0.003034  loss: 2.7227 (2.5800)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [111]  [190/312]  eta: 0:01:00  lr: 0.003034  min_lr: 0.003034  loss: 2.5671 (2.5641)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [111]  [200/312]  eta: 0:00:55  lr: 0.003033  min_lr: 0.003033  loss: 2.2521 (2.5601)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [111]  [210/312]  eta: 0:00:49  lr: 0.003032  min_lr: 0.003032  loss: 2.4637 (2.5574)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [111]  [220/312]  eta: 0:00:44  lr: 0.003032  min_lr: 0.003032  loss: 2.3850 (2.5449)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [111]  [230/312]  eta: 0:00:39  lr: 0.003031  min_lr: 0.003031  loss: 2.6207 (2.5530)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0003  max mem: 42573
Epoch: [111]  [240/312]  eta: 0:00:34  lr: 0.003030  min_lr: 0.003030  loss: 2.7858 (2.5511)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [111]  [250/312]  eta: 0:00:29  lr: 0.003030  min_lr: 0.003030  loss: 2.6510 (2.5497)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [111]  [260/312]  eta: 0:00:24  lr: 0.003029  min_lr: 0.003029  loss: 2.4375 (2.5489)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [111]  [270/312]  eta: 0:00:20  lr: 0.003029  min_lr: 0.003029  loss: 2.7123 (2.5545)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [111]  [280/312]  eta: 0:00:15  lr: 0.003028  min_lr: 0.003028  loss: 2.6985 (2.5575)  weight_decay: 0.0500 (0.0500)  time: 0.4343  data: 0.0010  max mem: 42573
Epoch: [111]  [290/312]  eta: 0:00:10  lr: 0.003027  min_lr: 0.003027  loss: 2.5146 (2.5567)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0009  max mem: 42573
Epoch: [111]  [300/312]  eta: 0:00:05  lr: 0.003027  min_lr: 0.003027  loss: 2.6041 (2.5625)  weight_decay: 0.0500 (0.0500)  time: 0.4325  data: 0.0001  max mem: 42573
Epoch: [111]  [310/312]  eta: 0:00:00  lr: 0.003026  min_lr: 0.003026  loss: 2.7530 (2.5640)  weight_decay: 0.0500 (0.0500)  time: 0.4324  data: 0.0001  max mem: 42573
Epoch: [111]  [311/312]  eta: 0:00:00  lr: 0.003026  min_lr: 0.003026  loss: 2.7530 (2.5646)  weight_decay: 0.0500 (0.0500)  time: 0.4324  data: 0.0001  max mem: 42573
Epoch: [111] Total time: 0:02:27 (0.4736 s / it)
Averaged stats: lr: 0.003026  min_lr: 0.003026  loss: 2.7530 (2.5817)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:00:40  loss: 0.8928 (0.8928)  acc1: 77.8646 (77.8646)  acc5: 93.4896 (93.4896)  time: 4.4788  data: 4.3700  max mem: 42573
Test:  [8/9]  eta: 0:00:00  loss: 1.3510 (1.2579)  acc1: 67.7083 (69.0880)  acc5: 88.2812 (89.1520)  time: 0.5750  data: 0.4856  max mem: 42573
Test: Total time: 0:00:05 (0.5842 s / it)
* Acc@1 69.688 Acc@5 89.328 loss 1.246
Accuracy of the model on the 50000 test images: 69.7%
Max accuracy: 71.11%
Epoch: [112]  [  0/312]  eta: 0:52:39  lr: 0.003026  min_lr: 0.003026  loss: 2.7372 (2.7372)  weight_decay: 0.0500 (0.0500)  time: 10.1252  data: 8.2695  max mem: 42573
Epoch: [112]  [ 10/312]  eta: 0:07:32  lr: 0.003025  min_lr: 0.003025  loss: 2.7964 (2.7260)  weight_decay: 0.0500 (0.0500)  time: 1.4978  data: 0.7521  max mem: 42573
Epoch: [112]  [ 20/312]  eta: 0:04:49  lr: 0.003025  min_lr: 0.003025  loss: 2.7273 (2.5411)  weight_decay: 0.0500 (0.0500)  time: 0.5339  data: 0.0003  max mem: 42573
Epoch: [112]  [ 30/312]  eta: 0:03:48  lr: 0.003024  min_lr: 0.003024  loss: 2.4056 (2.5147)  weight_decay: 0.0500 (0.0500)  time: 0.4330  data: 0.0003  max mem: 42573
Epoch: [112]  [ 40/312]  eta: 0:03:15  lr: 0.003024  min_lr: 0.003024  loss: 2.7141 (2.5751)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [112]  [ 50/312]  eta: 0:02:53  lr: 0.003023  min_lr: 0.003023  loss: 2.8257 (2.6111)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [112]  [ 60/312]  eta: 0:02:37  lr: 0.003022  min_lr: 0.003022  loss: 2.7377 (2.6091)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [112]  [ 70/312]  eta: 0:02:24  lr: 0.003022  min_lr: 0.003022  loss: 2.5811 (2.6027)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [112]  [ 80/312]  eta: 0:02:14  lr: 0.003021  min_lr: 0.003021  loss: 2.5130 (2.6054)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [112]  [ 90/312]  eta: 0:02:04  lr: 0.003020  min_lr: 0.003020  loss: 2.6448 (2.6084)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [112]  [100/312]  eta: 0:01:56  lr: 0.003020  min_lr: 0.003020  loss: 2.6393 (2.5875)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [112]  [110/312]  eta: 0:01:48  lr: 0.003019  min_lr: 0.003019  loss: 2.4077 (2.5754)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [112]  [120/312]  eta: 0:01:41  lr: 0.003019  min_lr: 0.003019  loss: 2.4946 (2.5716)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [112]  [130/312]  eta: 0:01:35  lr: 0.003018  min_lr: 0.003018  loss: 2.6507 (2.5778)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0003  max mem: 42573
Epoch: [112]  [140/312]  eta: 0:01:28  lr: 0.003017  min_lr: 0.003017  loss: 2.5902 (2.5702)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0003  max mem: 42573
Epoch: [112]  [150/312]  eta: 0:01:22  lr: 0.003017  min_lr: 0.003017  loss: 2.4021 (2.5605)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [112]  [160/312]  eta: 0:01:16  lr: 0.003016  min_lr: 0.003016  loss: 2.5932 (2.5716)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [112]  [170/312]  eta: 0:01:11  lr: 0.003016  min_lr: 0.003016  loss: 2.8117 (2.5829)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [112]  [180/312]  eta: 0:01:05  lr: 0.003015  min_lr: 0.003015  loss: 2.7476 (2.5855)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [112]  [190/312]  eta: 0:01:00  lr: 0.003014  min_lr: 0.003014  loss: 2.5991 (2.5753)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [112]  [200/312]  eta: 0:00:55  lr: 0.003014  min_lr: 0.003014  loss: 2.5287 (2.5803)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [112]  [210/312]  eta: 0:00:49  lr: 0.003013  min_lr: 0.003013  loss: 2.5287 (2.5751)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [112]  [220/312]  eta: 0:00:44  lr: 0.003012  min_lr: 0.003012  loss: 2.6251 (2.5747)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0003  max mem: 42573
Epoch: [112]  [230/312]  eta: 0:00:39  lr: 0.003012  min_lr: 0.003012  loss: 2.7178 (2.5800)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0003  max mem: 42573
Epoch: [112]  [240/312]  eta: 0:00:34  lr: 0.003011  min_lr: 0.003011  loss: 2.7364 (2.5762)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0003  max mem: 42573
Epoch: [112]  [250/312]  eta: 0:00:29  lr: 0.003011  min_lr: 0.003011  loss: 2.5694 (2.5715)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0003  max mem: 42573
Epoch: [112]  [260/312]  eta: 0:00:24  lr: 0.003010  min_lr: 0.003010  loss: 2.5355 (2.5727)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [112]  [270/312]  eta: 0:00:20  lr: 0.003009  min_lr: 0.003009  loss: 2.5498 (2.5741)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [112]  [280/312]  eta: 0:00:15  lr: 0.003009  min_lr: 0.003009  loss: 2.5036 (2.5702)  weight_decay: 0.0500 (0.0500)  time: 0.4344  data: 0.0010  max mem: 42573
Epoch: [112]  [290/312]  eta: 0:00:10  lr: 0.003008  min_lr: 0.003008  loss: 2.5027 (2.5719)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0008  max mem: 42573
Epoch: [112]  [300/312]  eta: 0:00:05  lr: 0.003007  min_lr: 0.003007  loss: 2.5388 (2.5642)  weight_decay: 0.0500 (0.0500)  time: 0.4323  data: 0.0001  max mem: 42573
Epoch: [112]  [310/312]  eta: 0:00:00  lr: 0.003007  min_lr: 0.003007  loss: 2.5388 (2.5629)  weight_decay: 0.0500 (0.0500)  time: 0.4323  data: 0.0001  max mem: 42573
Epoch: [112]  [311/312]  eta: 0:00:00  lr: 0.003007  min_lr: 0.003007  loss: 2.5845 (2.5637)  weight_decay: 0.0500 (0.0500)  time: 0.4324  data: 0.0001  max mem: 42573
Epoch: [112] Total time: 0:02:27 (0.4740 s / it)
Averaged stats: lr: 0.003007  min_lr: 0.003007  loss: 2.5845 (2.5762)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:00:46  loss: 1.0113 (1.0113)  acc1: 76.3021 (76.3021)  acc5: 92.4479 (92.4479)  time: 5.1522  data: 5.0430  max mem: 42573
Test:  [8/9]  eta: 0:00:00  loss: 1.2743 (1.2511)  acc1: 68.7500 (69.0560)  acc5: 90.1042 (89.0880)  time: 0.6488  data: 0.5604  max mem: 42573
Test: Total time: 0:00:06 (0.6703 s / it)
* Acc@1 69.200 Acc@5 89.158 loss 1.245
Accuracy of the model on the 50000 test images: 69.2%
Max accuracy: 71.11%
Epoch: [113]  [  0/312]  eta: 0:51:33  lr: 0.003007  min_lr: 0.003007  loss: 2.7445 (2.7445)  weight_decay: 0.0500 (0.0500)  time: 9.9157  data: 8.7705  max mem: 42573
Epoch: [113]  [ 10/312]  eta: 0:07:07  lr: 0.003006  min_lr: 0.003006  loss: 2.3718 (2.3691)  weight_decay: 0.0500 (0.0500)  time: 1.4156  data: 0.7977  max mem: 42573
Epoch: [113]  [ 20/312]  eta: 0:04:36  lr: 0.003005  min_lr: 0.003005  loss: 2.3656 (2.4535)  weight_decay: 0.0500 (0.0500)  time: 0.4995  data: 0.0004  max mem: 42573
Epoch: [113]  [ 30/312]  eta: 0:03:40  lr: 0.003005  min_lr: 0.003005  loss: 2.4697 (2.4670)  weight_decay: 0.0500 (0.0500)  time: 0.4332  data: 0.0004  max mem: 42573
Epoch: [113]  [ 40/312]  eta: 0:03:09  lr: 0.003004  min_lr: 0.003004  loss: 2.5797 (2.5241)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [113]  [ 50/312]  eta: 0:02:49  lr: 0.003004  min_lr: 0.003004  loss: 2.6520 (2.5074)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0003  max mem: 42573
Epoch: [113]  [ 60/312]  eta: 0:02:33  lr: 0.003003  min_lr: 0.003003  loss: 2.6730 (2.5701)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [113]  [ 70/312]  eta: 0:02:21  lr: 0.003002  min_lr: 0.003002  loss: 2.8176 (2.5964)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [113]  [ 80/312]  eta: 0:02:11  lr: 0.003002  min_lr: 0.003002  loss: 2.8176 (2.6268)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0005  max mem: 42573
Epoch: [113]  [ 90/312]  eta: 0:02:02  lr: 0.003001  min_lr: 0.003001  loss: 2.7379 (2.6186)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0005  max mem: 42573
Epoch: [113]  [100/312]  eta: 0:01:54  lr: 0.003000  min_lr: 0.003000  loss: 2.6684 (2.6171)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [113]  [110/312]  eta: 0:01:47  lr: 0.003000  min_lr: 0.003000  loss: 2.4622 (2.5973)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [113]  [120/312]  eta: 0:01:40  lr: 0.002999  min_lr: 0.002999  loss: 2.4622 (2.5992)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [113]  [130/312]  eta: 0:01:33  lr: 0.002999  min_lr: 0.002999  loss: 2.8128 (2.6088)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [113]  [140/312]  eta: 0:01:27  lr: 0.002998  min_lr: 0.002998  loss: 2.8571 (2.6160)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [113]  [150/312]  eta: 0:01:21  lr: 0.002997  min_lr: 0.002997  loss: 2.7033 (2.6178)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [113]  [160/312]  eta: 0:01:16  lr: 0.002997  min_lr: 0.002997  loss: 2.4299 (2.6033)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [113]  [170/312]  eta: 0:01:10  lr: 0.002996  min_lr: 0.002996  loss: 2.3770 (2.5890)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [113]  [180/312]  eta: 0:01:05  lr: 0.002996  min_lr: 0.002996  loss: 2.6173 (2.5923)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [113]  [190/312]  eta: 0:00:59  lr: 0.002995  min_lr: 0.002995  loss: 2.6173 (2.5879)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [113]  [200/312]  eta: 0:00:54  lr: 0.002994  min_lr: 0.002994  loss: 2.5553 (2.5901)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [113]  [210/312]  eta: 0:00:49  lr: 0.002994  min_lr: 0.002994  loss: 2.5564 (2.5902)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [113]  [220/312]  eta: 0:00:44  lr: 0.002993  min_lr: 0.002993  loss: 2.6303 (2.5901)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [113]  [230/312]  eta: 0:00:39  lr: 0.002992  min_lr: 0.002992  loss: 2.6709 (2.5962)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [113]  [240/312]  eta: 0:00:34  lr: 0.002992  min_lr: 0.002992  loss: 2.7532 (2.5995)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [113]  [250/312]  eta: 0:00:29  lr: 0.002991  min_lr: 0.002991  loss: 2.6006 (2.5962)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [113]  [260/312]  eta: 0:00:24  lr: 0.002991  min_lr: 0.002991  loss: 2.4534 (2.5886)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0003  max mem: 42573
Epoch: [113]  [270/312]  eta: 0:00:19  lr: 0.002990  min_lr: 0.002990  loss: 2.6614 (2.5923)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0003  max mem: 42573
Epoch: [113]  [280/312]  eta: 0:00:15  lr: 0.002989  min_lr: 0.002989  loss: 2.5174 (2.5878)  weight_decay: 0.0500 (0.0500)  time: 0.4345  data: 0.0009  max mem: 42573
Epoch: [113]  [290/312]  eta: 0:00:10  lr: 0.002989  min_lr: 0.002989  loss: 2.6230 (2.5904)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0008  max mem: 42573
Epoch: [113]  [300/312]  eta: 0:00:05  lr: 0.002988  min_lr: 0.002988  loss: 2.7176 (2.5958)  weight_decay: 0.0500 (0.0500)  time: 0.4323  data: 0.0001  max mem: 42573
Epoch: [113]  [310/312]  eta: 0:00:00  lr: 0.002987  min_lr: 0.002987  loss: 2.6362 (2.5898)  weight_decay: 0.0500 (0.0500)  time: 0.4322  data: 0.0001  max mem: 42573
Epoch: [113]  [311/312]  eta: 0:00:00  lr: 0.002987  min_lr: 0.002987  loss: 2.6362 (2.5903)  weight_decay: 0.0500 (0.0500)  time: 0.4322  data: 0.0001  max mem: 42573
Epoch: [113] Total time: 0:02:26 (0.4710 s / it)
Averaged stats: lr: 0.002987  min_lr: 0.002987  loss: 2.6362 (2.5760)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:00:45  loss: 1.0311 (1.0311)  acc1: 76.8229 (76.8229)  acc5: 92.7083 (92.7083)  time: 5.0104  data: 4.8983  max mem: 42573
Test:  [8/9]  eta: 0:00:00  loss: 1.3729 (1.2473)  acc1: 68.2292 (68.9920)  acc5: 91.6667 (89.6960)  time: 0.6319  data: 0.5443  max mem: 42573
Test: Total time: 0:00:05 (0.6393 s / it)
* Acc@1 70.078 Acc@5 89.378 loss 1.258
Accuracy of the model on the 50000 test images: 70.1%
Max accuracy: 71.11%
Epoch: [114]  [  0/312]  eta: 0:49:48  lr: 0.002987  min_lr: 0.002987  loss: 2.7424 (2.7424)  weight_decay: 0.0500 (0.0500)  time: 9.5800  data: 7.6277  max mem: 42573
Epoch: [114]  [ 10/312]  eta: 0:07:15  lr: 0.002987  min_lr: 0.002987  loss: 2.7703 (2.8103)  weight_decay: 0.0500 (0.0500)  time: 1.4420  data: 0.6938  max mem: 42573
Epoch: [114]  [ 20/312]  eta: 0:04:40  lr: 0.002986  min_lr: 0.002986  loss: 2.7341 (2.7526)  weight_decay: 0.0500 (0.0500)  time: 0.5307  data: 0.0004  max mem: 42573
Epoch: [114]  [ 30/312]  eta: 0:03:43  lr: 0.002985  min_lr: 0.002985  loss: 2.7149 (2.7359)  weight_decay: 0.0500 (0.0500)  time: 0.4331  data: 0.0003  max mem: 42573
Epoch: [114]  [ 40/312]  eta: 0:03:11  lr: 0.002985  min_lr: 0.002985  loss: 2.4863 (2.6182)  weight_decay: 0.0500 (0.0500)  time: 0.4332  data: 0.0004  max mem: 42573
Epoch: [114]  [ 50/312]  eta: 0:02:50  lr: 0.002984  min_lr: 0.002984  loss: 2.3863 (2.6014)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [114]  [ 60/312]  eta: 0:02:35  lr: 0.002984  min_lr: 0.002984  loss: 2.6881 (2.6135)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0005  max mem: 42573
Epoch: [114]  [ 70/312]  eta: 0:02:22  lr: 0.002983  min_lr: 0.002983  loss: 2.5789 (2.5817)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [114]  [ 80/312]  eta: 0:02:12  lr: 0.002982  min_lr: 0.002982  loss: 2.3770 (2.5709)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [114]  [ 90/312]  eta: 0:02:03  lr: 0.002982  min_lr: 0.002982  loss: 2.6497 (2.5723)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0004  max mem: 42573
Epoch: [114]  [100/312]  eta: 0:01:55  lr: 0.002981  min_lr: 0.002981  loss: 2.7238 (2.5678)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0004  max mem: 42573
Epoch: [114]  [110/312]  eta: 0:01:47  lr: 0.002980  min_lr: 0.002980  loss: 2.6633 (2.5689)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [114]  [120/312]  eta: 0:01:40  lr: 0.002980  min_lr: 0.002980  loss: 2.5297 (2.5635)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [114]  [130/312]  eta: 0:01:34  lr: 0.002979  min_lr: 0.002979  loss: 2.6941 (2.5761)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [114]  [140/312]  eta: 0:01:28  lr: 0.002979  min_lr: 0.002979  loss: 2.5277 (2.5588)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [114]  [150/312]  eta: 0:01:22  lr: 0.002978  min_lr: 0.002978  loss: 2.5277 (2.5684)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [114]  [160/312]  eta: 0:01:16  lr: 0.002977  min_lr: 0.002977  loss: 2.5660 (2.5609)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [114]  [170/312]  eta: 0:01:10  lr: 0.002977  min_lr: 0.002977  loss: 2.5903 (2.5693)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [114]  [180/312]  eta: 0:01:05  lr: 0.002976  min_lr: 0.002976  loss: 2.7729 (2.5819)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [114]  [190/312]  eta: 0:00:59  lr: 0.002975  min_lr: 0.002975  loss: 2.8396 (2.5943)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [114]  [200/312]  eta: 0:00:54  lr: 0.002975  min_lr: 0.002975  loss: 2.6545 (2.5915)  weight_decay: 0.0500 (0.0500)  time: 0.4382  data: 0.0004  max mem: 42573
Epoch: [114]  [210/312]  eta: 0:00:49  lr: 0.002974  min_lr: 0.002974  loss: 2.6304 (2.5948)  weight_decay: 0.0500 (0.0500)  time: 0.4382  data: 0.0004  max mem: 42573
Epoch: [114]  [220/312]  eta: 0:00:44  lr: 0.002973  min_lr: 0.002973  loss: 2.7355 (2.5972)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0003  max mem: 42573
Epoch: [114]  [230/312]  eta: 0:00:39  lr: 0.002973  min_lr: 0.002973  loss: 2.8167 (2.6008)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0003  max mem: 42573
Epoch: [114]  [240/312]  eta: 0:00:34  lr: 0.002972  min_lr: 0.002972  loss: 2.7048 (2.6070)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0003  max mem: 42573
Epoch: [114]  [250/312]  eta: 0:00:29  lr: 0.002972  min_lr: 0.002972  loss: 2.6502 (2.6087)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [114]  [260/312]  eta: 0:00:24  lr: 0.002971  min_lr: 0.002971  loss: 2.7324 (2.6135)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [114]  [270/312]  eta: 0:00:19  lr: 0.002970  min_lr: 0.002970  loss: 2.7687 (2.6146)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0003  max mem: 42573
Epoch: [114]  [280/312]  eta: 0:00:15  lr: 0.002970  min_lr: 0.002970  loss: 2.6609 (2.6118)  weight_decay: 0.0500 (0.0500)  time: 0.4346  data: 0.0009  max mem: 42573
Epoch: [114]  [290/312]  eta: 0:00:10  lr: 0.002969  min_lr: 0.002969  loss: 2.5280 (2.6118)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0008  max mem: 42573
Epoch: [114]  [300/312]  eta: 0:00:05  lr: 0.002968  min_lr: 0.002968  loss: 2.7213 (2.6148)  weight_decay: 0.0500 (0.0500)  time: 0.4325  data: 0.0001  max mem: 42573
Epoch: [114]  [310/312]  eta: 0:00:00  lr: 0.002968  min_lr: 0.002968  loss: 2.8272 (2.6236)  weight_decay: 0.0500 (0.0500)  time: 0.4324  data: 0.0001  max mem: 42573
Epoch: [114]  [311/312]  eta: 0:00:00  lr: 0.002968  min_lr: 0.002968  loss: 2.7989 (2.6215)  weight_decay: 0.0500 (0.0500)  time: 0.4323  data: 0.0001  max mem: 42573
Epoch: [114] Total time: 0:02:27 (0.4723 s / it)
Averaged stats: lr: 0.002968  min_lr: 0.002968  loss: 2.7989 (2.5791)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:00:43  loss: 1.1143 (1.1143)  acc1: 76.0417 (76.0417)  acc5: 91.4062 (91.4062)  time: 4.8058  data: 4.6966  max mem: 42573
Test:  [8/9]  eta: 0:00:00  loss: 1.4707 (1.3332)  acc1: 67.7083 (69.3440)  acc5: 86.9792 (87.6480)  time: 0.6108  data: 0.5219  max mem: 42573
Test: Total time: 0:00:05 (0.6236 s / it)
* Acc@1 68.894 Acc@5 88.364 loss 1.333
Accuracy of the model on the 50000 test images: 68.9%
Max accuracy: 71.11%
Epoch: [115]  [  0/312]  eta: 0:52:05  lr: 0.002968  min_lr: 0.002968  loss: 3.0647 (3.0647)  weight_decay: 0.0500 (0.0500)  time: 10.0165  data: 7.1281  max mem: 42573
Epoch: [115]  [ 10/312]  eta: 0:07:35  lr: 0.002967  min_lr: 0.002967  loss: 2.6938 (2.5209)  weight_decay: 0.0500 (0.0500)  time: 1.5085  data: 0.6776  max mem: 42573
Epoch: [115]  [ 20/312]  eta: 0:04:50  lr: 0.002966  min_lr: 0.002966  loss: 2.3619 (2.4657)  weight_decay: 0.0500 (0.0500)  time: 0.5455  data: 0.0165  max mem: 42573
Epoch: [115]  [ 30/312]  eta: 0:03:49  lr: 0.002966  min_lr: 0.002966  loss: 2.5439 (2.4722)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [115]  [ 40/312]  eta: 0:03:16  lr: 0.002965  min_lr: 0.002965  loss: 2.5439 (2.4774)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [115]  [ 50/312]  eta: 0:02:54  lr: 0.002965  min_lr: 0.002965  loss: 2.4287 (2.4866)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [115]  [ 60/312]  eta: 0:02:38  lr: 0.002964  min_lr: 0.002964  loss: 2.5353 (2.5229)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [115]  [ 70/312]  eta: 0:02:25  lr: 0.002963  min_lr: 0.002963  loss: 2.5353 (2.5162)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [115]  [ 80/312]  eta: 0:02:14  lr: 0.002963  min_lr: 0.002963  loss: 2.6377 (2.5195)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [115]  [ 90/312]  eta: 0:02:05  lr: 0.002962  min_lr: 0.002962  loss: 2.5636 (2.5096)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [115]  [100/312]  eta: 0:01:56  lr: 0.002961  min_lr: 0.002961  loss: 2.3560 (2.4946)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [115]  [110/312]  eta: 0:01:49  lr: 0.002961  min_lr: 0.002961  loss: 2.4011 (2.4940)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [115]  [120/312]  eta: 0:01:42  lr: 0.002960  min_lr: 0.002960  loss: 2.4664 (2.4914)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [115]  [130/312]  eta: 0:01:35  lr: 0.002960  min_lr: 0.002960  loss: 2.5564 (2.4991)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [115]  [140/312]  eta: 0:01:29  lr: 0.002959  min_lr: 0.002959  loss: 2.3047 (2.4795)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0003  max mem: 42573
Epoch: [115]  [150/312]  eta: 0:01:22  lr: 0.002958  min_lr: 0.002958  loss: 2.3047 (2.4842)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0003  max mem: 42573
Epoch: [115]  [160/312]  eta: 0:01:17  lr: 0.002958  min_lr: 0.002958  loss: 2.6589 (2.4891)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0003  max mem: 42573
Epoch: [115]  [170/312]  eta: 0:01:11  lr: 0.002957  min_lr: 0.002957  loss: 2.5900 (2.4944)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [115]  [180/312]  eta: 0:01:05  lr: 0.002956  min_lr: 0.002956  loss: 2.6552 (2.5033)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [115]  [190/312]  eta: 0:01:00  lr: 0.002956  min_lr: 0.002956  loss: 2.6552 (2.5074)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [115]  [200/312]  eta: 0:00:55  lr: 0.002955  min_lr: 0.002955  loss: 2.4993 (2.5041)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [115]  [210/312]  eta: 0:00:49  lr: 0.002954  min_lr: 0.002954  loss: 2.5211 (2.5094)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [115]  [220/312]  eta: 0:00:44  lr: 0.002954  min_lr: 0.002954  loss: 2.6425 (2.5165)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [115]  [230/312]  eta: 0:00:39  lr: 0.002953  min_lr: 0.002953  loss: 2.7292 (2.5223)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0003  max mem: 42573
Epoch: [115]  [240/312]  eta: 0:00:34  lr: 0.002953  min_lr: 0.002953  loss: 2.6617 (2.5226)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0003  max mem: 42573
Epoch: [115]  [250/312]  eta: 0:00:29  lr: 0.002952  min_lr: 0.002952  loss: 2.5696 (2.5209)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [115]  [260/312]  eta: 0:00:24  lr: 0.002951  min_lr: 0.002951  loss: 2.7584 (2.5286)  weight_decay: 0.0500 (0.0500)  time: 0.4398  data: 0.0004  max mem: 42573
Epoch: [115]  [270/312]  eta: 0:00:20  lr: 0.002951  min_lr: 0.002951  loss: 2.8402 (2.5307)  weight_decay: 0.0500 (0.0500)  time: 0.4399  data: 0.0004  max mem: 42573
Epoch: [115]  [280/312]  eta: 0:00:15  lr: 0.002950  min_lr: 0.002950  loss: 2.3322 (2.5213)  weight_decay: 0.0500 (0.0500)  time: 0.4349  data: 0.0009  max mem: 42573
Epoch: [115]  [290/312]  eta: 0:00:10  lr: 0.002949  min_lr: 0.002949  loss: 2.4622 (2.5282)  weight_decay: 0.0500 (0.0500)  time: 0.4344  data: 0.0008  max mem: 42573
Epoch: [115]  [300/312]  eta: 0:00:05  lr: 0.002949  min_lr: 0.002949  loss: 2.7790 (2.5269)  weight_decay: 0.0500 (0.0500)  time: 0.4324  data: 0.0001  max mem: 42573
Epoch: [115]  [310/312]  eta: 0:00:00  lr: 0.002948  min_lr: 0.002948  loss: 2.6876 (2.5305)  weight_decay: 0.0500 (0.0500)  time: 0.4324  data: 0.0001  max mem: 42573
Epoch: [115]  [311/312]  eta: 0:00:00  lr: 0.002948  min_lr: 0.002948  loss: 2.7790 (2.5329)  weight_decay: 0.0500 (0.0500)  time: 0.4324  data: 0.0001  max mem: 42573
Epoch: [115] Total time: 0:02:28 (0.4750 s / it)
Averaged stats: lr: 0.002948  min_lr: 0.002948  loss: 2.7790 (2.5673)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:00:42  loss: 0.9549 (0.9549)  acc1: 77.8646 (77.8646)  acc5: 92.4479 (92.4479)  time: 4.7655  data: 4.6565  max mem: 42573
Test:  [8/9]  eta: 0:00:00  loss: 1.2752 (1.2505)  acc1: 67.7083 (69.9200)  acc5: 90.1042 (89.8560)  time: 0.6056  data: 0.5178  max mem: 42573
Test: Total time: 0:00:05 (0.6134 s / it)
* Acc@1 70.358 Acc@5 89.484 loss 1.270
Accuracy of the model on the 50000 test images: 70.4%
Max accuracy: 71.11%
Epoch: [116]  [  0/312]  eta: 0:49:45  lr: 0.002948  min_lr: 0.002948  loss: 2.0965 (2.0965)  weight_decay: 0.0500 (0.0500)  time: 9.5692  data: 7.1915  max mem: 42573
Epoch: [116]  [ 10/312]  eta: 0:07:04  lr: 0.002947  min_lr: 0.002947  loss: 2.6955 (2.6517)  weight_decay: 0.0500 (0.0500)  time: 1.4042  data: 0.6542  max mem: 42573
Epoch: [116]  [ 20/312]  eta: 0:04:35  lr: 0.002947  min_lr: 0.002947  loss: 2.7282 (2.6506)  weight_decay: 0.0500 (0.0500)  time: 0.5105  data: 0.0004  max mem: 42573
Epoch: [116]  [ 30/312]  eta: 0:03:39  lr: 0.002946  min_lr: 0.002946  loss: 2.8495 (2.6748)  weight_decay: 0.0500 (0.0500)  time: 0.4332  data: 0.0004  max mem: 42573
Epoch: [116]  [ 40/312]  eta: 0:03:08  lr: 0.002945  min_lr: 0.002945  loss: 2.8196 (2.7213)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [116]  [ 50/312]  eta: 0:02:48  lr: 0.002945  min_lr: 0.002945  loss: 2.7907 (2.6870)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [116]  [ 60/312]  eta: 0:02:33  lr: 0.002944  min_lr: 0.002944  loss: 2.6859 (2.7036)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [116]  [ 70/312]  eta: 0:02:21  lr: 0.002944  min_lr: 0.002944  loss: 2.6859 (2.6743)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [116]  [ 80/312]  eta: 0:02:11  lr: 0.002943  min_lr: 0.002943  loss: 2.3214 (2.6169)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [116]  [ 90/312]  eta: 0:02:02  lr: 0.002942  min_lr: 0.002942  loss: 2.5306 (2.6277)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [116]  [100/312]  eta: 0:01:54  lr: 0.002942  min_lr: 0.002942  loss: 2.5092 (2.5963)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [116]  [110/312]  eta: 0:01:47  lr: 0.002941  min_lr: 0.002941  loss: 2.3433 (2.5909)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [116]  [120/312]  eta: 0:01:40  lr: 0.002940  min_lr: 0.002940  loss: 2.6366 (2.5879)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [116]  [130/312]  eta: 0:01:33  lr: 0.002940  min_lr: 0.002940  loss: 2.7215 (2.5909)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [116]  [140/312]  eta: 0:01:27  lr: 0.002939  min_lr: 0.002939  loss: 2.7087 (2.5908)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0003  max mem: 42573
Epoch: [116]  [150/312]  eta: 0:01:21  lr: 0.002938  min_lr: 0.002938  loss: 2.4628 (2.5683)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [116]  [160/312]  eta: 0:01:15  lr: 0.002938  min_lr: 0.002938  loss: 2.4762 (2.5764)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [116]  [170/312]  eta: 0:01:10  lr: 0.002937  min_lr: 0.002937  loss: 2.5693 (2.5683)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0003  max mem: 42573
Epoch: [116]  [180/312]  eta: 0:01:05  lr: 0.002937  min_lr: 0.002937  loss: 2.6588 (2.5774)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0003  max mem: 42573
Epoch: [116]  [190/312]  eta: 0:00:59  lr: 0.002936  min_lr: 0.002936  loss: 2.7600 (2.5868)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [116]  [200/312]  eta: 0:00:54  lr: 0.002935  min_lr: 0.002935  loss: 2.4826 (2.5632)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [116]  [210/312]  eta: 0:00:49  lr: 0.002935  min_lr: 0.002935  loss: 2.2576 (2.5598)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [116]  [220/312]  eta: 0:00:44  lr: 0.002934  min_lr: 0.002934  loss: 2.5567 (2.5627)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [116]  [230/312]  eta: 0:00:39  lr: 0.002933  min_lr: 0.002933  loss: 2.7342 (2.5725)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [116]  [240/312]  eta: 0:00:34  lr: 0.002933  min_lr: 0.002933  loss: 2.7752 (2.5696)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [116]  [250/312]  eta: 0:00:29  lr: 0.002932  min_lr: 0.002932  loss: 2.4270 (2.5664)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0003  max mem: 42573
Epoch: [116]  [260/312]  eta: 0:00:24  lr: 0.002931  min_lr: 0.002931  loss: 2.5256 (2.5693)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0003  max mem: 42573
Epoch: [116]  [270/312]  eta: 0:00:19  lr: 0.002931  min_lr: 0.002931  loss: 2.6095 (2.5693)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0003  max mem: 42573
Epoch: [116]  [280/312]  eta: 0:00:15  lr: 0.002930  min_lr: 0.002930  loss: 2.6993 (2.5703)  weight_decay: 0.0500 (0.0500)  time: 0.4344  data: 0.0009  max mem: 42573
Epoch: [116]  [290/312]  eta: 0:00:10  lr: 0.002930  min_lr: 0.002930  loss: 2.4989 (2.5649)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0008  max mem: 42573
Epoch: [116]  [300/312]  eta: 0:00:05  lr: 0.002929  min_lr: 0.002929  loss: 2.4693 (2.5602)  weight_decay: 0.0500 (0.0500)  time: 0.4325  data: 0.0001  max mem: 42573
Epoch: [116]  [310/312]  eta: 0:00:00  lr: 0.002928  min_lr: 0.002928  loss: 2.5119 (2.5601)  weight_decay: 0.0500 (0.0500)  time: 0.4324  data: 0.0001  max mem: 42573
Epoch: [116]  [311/312]  eta: 0:00:00  lr: 0.002928  min_lr: 0.002928  loss: 2.5119 (2.5588)  weight_decay: 0.0500 (0.0500)  time: 0.4324  data: 0.0001  max mem: 42573
Epoch: [116] Total time: 0:02:26 (0.4706 s / it)
Averaged stats: lr: 0.002928  min_lr: 0.002928  loss: 2.5119 (2.5579)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:00:43  loss: 0.9461 (0.9461)  acc1: 77.6042 (77.6042)  acc5: 93.7500 (93.7500)  time: 4.8217  data: 4.7123  max mem: 42573
Test:  [8/9]  eta: 0:00:00  loss: 1.2985 (1.2282)  acc1: 69.2708 (69.6640)  acc5: 90.1042 (89.0240)  time: 0.6113  data: 0.5237  max mem: 42573
Test: Total time: 0:00:05 (0.6379 s / it)
* Acc@1 69.934 Acc@5 89.210 loss 1.217
Accuracy of the model on the 50000 test images: 69.9%
Max accuracy: 71.11%
Epoch: [117]  [  0/312]  eta: 0:46:57  lr: 0.002928  min_lr: 0.002928  loss: 2.0096 (2.0096)  weight_decay: 0.0500 (0.0500)  time: 9.0293  data: 6.5400  max mem: 42573
Epoch: [117]  [ 10/312]  eta: 0:07:40  lr: 0.002928  min_lr: 0.002928  loss: 2.0096 (2.2654)  weight_decay: 0.0500 (0.0500)  time: 1.5236  data: 0.7439  max mem: 42573
Epoch: [117]  [ 20/312]  eta: 0:04:53  lr: 0.002927  min_lr: 0.002927  loss: 2.4771 (2.3605)  weight_decay: 0.0500 (0.0500)  time: 0.6030  data: 0.0823  max mem: 42573
Epoch: [117]  [ 30/312]  eta: 0:03:51  lr: 0.002926  min_lr: 0.002926  loss: 2.6701 (2.4465)  weight_decay: 0.0500 (0.0500)  time: 0.4332  data: 0.0003  max mem: 42573
Epoch: [117]  [ 40/312]  eta: 0:03:17  lr: 0.002926  min_lr: 0.002926  loss: 2.6622 (2.4648)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0003  max mem: 42573
Epoch: [117]  [ 50/312]  eta: 0:02:55  lr: 0.002925  min_lr: 0.002925  loss: 2.4782 (2.4511)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [117]  [ 60/312]  eta: 0:02:38  lr: 0.002924  min_lr: 0.002924  loss: 2.5618 (2.4878)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [117]  [ 70/312]  eta: 0:02:25  lr: 0.002924  min_lr: 0.002924  loss: 2.5840 (2.4970)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [117]  [ 80/312]  eta: 0:02:14  lr: 0.002923  min_lr: 0.002923  loss: 2.6744 (2.5354)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [117]  [ 90/312]  eta: 0:02:05  lr: 0.002922  min_lr: 0.002922  loss: 2.7642 (2.5148)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [117]  [100/312]  eta: 0:01:57  lr: 0.002922  min_lr: 0.002922  loss: 2.1126 (2.4907)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [117]  [110/312]  eta: 0:01:49  lr: 0.002921  min_lr: 0.002921  loss: 2.5324 (2.5019)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [117]  [120/312]  eta: 0:01:42  lr: 0.002921  min_lr: 0.002921  loss: 2.6566 (2.4851)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [117]  [130/312]  eta: 0:01:35  lr: 0.002920  min_lr: 0.002920  loss: 2.6043 (2.4952)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [117]  [140/312]  eta: 0:01:29  lr: 0.002919  min_lr: 0.002919  loss: 2.6043 (2.4908)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [117]  [150/312]  eta: 0:01:23  lr: 0.002919  min_lr: 0.002919  loss: 2.6288 (2.5041)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0005  max mem: 42573
Epoch: [117]  [160/312]  eta: 0:01:17  lr: 0.002918  min_lr: 0.002918  loss: 2.6858 (2.5096)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [117]  [170/312]  eta: 0:01:11  lr: 0.002917  min_lr: 0.002917  loss: 2.7102 (2.5222)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [117]  [180/312]  eta: 0:01:05  lr: 0.002917  min_lr: 0.002917  loss: 2.6325 (2.5248)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [117]  [190/312]  eta: 0:01:00  lr: 0.002916  min_lr: 0.002916  loss: 2.5219 (2.5248)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [117]  [200/312]  eta: 0:00:55  lr: 0.002915  min_lr: 0.002915  loss: 2.3755 (2.5117)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [117]  [210/312]  eta: 0:00:50  lr: 0.002915  min_lr: 0.002915  loss: 2.5359 (2.5172)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [117]  [220/312]  eta: 0:00:44  lr: 0.002914  min_lr: 0.002914  loss: 2.5359 (2.5129)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [117]  [230/312]  eta: 0:00:39  lr: 0.002914  min_lr: 0.002914  loss: 2.3958 (2.5166)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [117]  [240/312]  eta: 0:00:34  lr: 0.002913  min_lr: 0.002913  loss: 2.5091 (2.5167)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [117]  [250/312]  eta: 0:00:29  lr: 0.002912  min_lr: 0.002912  loss: 2.5507 (2.5126)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [117]  [260/312]  eta: 0:00:24  lr: 0.002912  min_lr: 0.002912  loss: 2.6195 (2.5137)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [117]  [270/312]  eta: 0:00:20  lr: 0.002911  min_lr: 0.002911  loss: 2.5605 (2.5130)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0003  max mem: 42573
Epoch: [117]  [280/312]  eta: 0:00:15  lr: 0.002910  min_lr: 0.002910  loss: 2.6459 (2.5231)  weight_decay: 0.0500 (0.0500)  time: 0.4342  data: 0.0009  max mem: 42573
Epoch: [117]  [290/312]  eta: 0:00:10  lr: 0.002910  min_lr: 0.002910  loss: 2.7151 (2.5236)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0008  max mem: 42573
Epoch: [117]  [300/312]  eta: 0:00:05  lr: 0.002909  min_lr: 0.002909  loss: 2.4886 (2.5228)  weight_decay: 0.0500 (0.0500)  time: 0.4324  data: 0.0001  max mem: 42573
Epoch: [117]  [310/312]  eta: 0:00:00  lr: 0.002908  min_lr: 0.002908  loss: 2.4886 (2.5252)  weight_decay: 0.0500 (0.0500)  time: 0.4323  data: 0.0001  max mem: 42573
Epoch: [117]  [311/312]  eta: 0:00:00  lr: 0.002908  min_lr: 0.002908  loss: 2.5022 (2.5251)  weight_decay: 0.0500 (0.0500)  time: 0.4323  data: 0.0001  max mem: 42573
Epoch: [117] Total time: 0:02:28 (0.4749 s / it)
Averaged stats: lr: 0.002908  min_lr: 0.002908  loss: 2.5022 (2.5644)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:00:41  loss: 0.9271 (0.9271)  acc1: 78.6458 (78.6458)  acc5: 92.4479 (92.4479)  time: 4.6484  data: 4.5395  max mem: 42573
Test:  [8/9]  eta: 0:00:00  loss: 1.3054 (1.1743)  acc1: 69.5312 (70.6880)  acc5: 90.1042 (89.9200)  time: 0.6005  data: 0.5120  max mem: 42573
Test: Total time: 0:00:05 (0.6079 s / it)
* Acc@1 70.506 Acc@5 89.790 loss 1.181
Accuracy of the model on the 50000 test images: 70.5%
Max accuracy: 71.11%
Epoch: [118]  [  0/312]  eta: 0:50:01  lr: 0.002908  min_lr: 0.002908  loss: 2.5734 (2.5734)  weight_decay: 0.0500 (0.0500)  time: 9.6196  data: 8.8202  max mem: 42573
Epoch: [118]  [ 10/312]  eta: 0:07:14  lr: 0.002908  min_lr: 0.002908  loss: 2.5734 (2.4728)  weight_decay: 0.0500 (0.0500)  time: 1.4394  data: 0.8022  max mem: 42573
Epoch: [118]  [ 20/312]  eta: 0:04:40  lr: 0.002907  min_lr: 0.002907  loss: 2.5754 (2.5294)  weight_decay: 0.0500 (0.0500)  time: 0.5274  data: 0.0004  max mem: 42573
Epoch: [118]  [ 30/312]  eta: 0:03:43  lr: 0.002906  min_lr: 0.002906  loss: 2.6180 (2.5334)  weight_decay: 0.0500 (0.0500)  time: 0.4393  data: 0.0004  max mem: 42573
Epoch: [118]  [ 40/312]  eta: 0:03:12  lr: 0.002906  min_lr: 0.002906  loss: 2.5361 (2.5000)  weight_decay: 0.0500 (0.0500)  time: 0.4395  data: 0.0005  max mem: 42573
Epoch: [118]  [ 50/312]  eta: 0:02:51  lr: 0.002905  min_lr: 0.002905  loss: 2.5525 (2.5098)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [118]  [ 60/312]  eta: 0:02:35  lr: 0.002904  min_lr: 0.002904  loss: 2.6627 (2.5160)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [118]  [ 70/312]  eta: 0:02:23  lr: 0.002904  min_lr: 0.002904  loss: 2.6832 (2.5410)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [118]  [ 80/312]  eta: 0:02:12  lr: 0.002903  min_lr: 0.002903  loss: 2.7899 (2.5676)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [118]  [ 90/312]  eta: 0:02:03  lr: 0.002902  min_lr: 0.002902  loss: 2.7607 (2.5833)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [118]  [100/312]  eta: 0:01:55  lr: 0.002902  min_lr: 0.002902  loss: 2.7188 (2.5821)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [118]  [110/312]  eta: 0:01:47  lr: 0.002901  min_lr: 0.002901  loss: 2.7160 (2.5819)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [118]  [120/312]  eta: 0:01:41  lr: 0.002901  min_lr: 0.002901  loss: 2.4228 (2.5683)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [118]  [130/312]  eta: 0:01:34  lr: 0.002900  min_lr: 0.002900  loss: 2.2571 (2.5573)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [118]  [140/312]  eta: 0:01:28  lr: 0.002899  min_lr: 0.002899  loss: 2.5768 (2.5575)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [118]  [150/312]  eta: 0:01:22  lr: 0.002899  min_lr: 0.002899  loss: 2.4120 (2.5414)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [118]  [160/312]  eta: 0:01:16  lr: 0.002898  min_lr: 0.002898  loss: 2.4120 (2.5437)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [118]  [170/312]  eta: 0:01:10  lr: 0.002897  min_lr: 0.002897  loss: 2.4133 (2.5379)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [118]  [180/312]  eta: 0:01:05  lr: 0.002897  min_lr: 0.002897  loss: 2.5319 (2.5428)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [118]  [190/312]  eta: 0:01:00  lr: 0.002896  min_lr: 0.002896  loss: 2.6826 (2.5464)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [118]  [200/312]  eta: 0:00:54  lr: 0.002895  min_lr: 0.002895  loss: 2.5573 (2.5379)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [118]  [210/312]  eta: 0:00:49  lr: 0.002895  min_lr: 0.002895  loss: 2.5573 (2.5413)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [118]  [220/312]  eta: 0:00:44  lr: 0.002894  min_lr: 0.002894  loss: 2.7656 (2.5434)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0003  max mem: 42573
Epoch: [118]  [230/312]  eta: 0:00:39  lr: 0.002893  min_lr: 0.002893  loss: 2.7656 (2.5467)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0003  max mem: 42573
Epoch: [118]  [240/312]  eta: 0:00:34  lr: 0.002893  min_lr: 0.002893  loss: 2.7520 (2.5503)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0003  max mem: 42573
Epoch: [118]  [250/312]  eta: 0:00:29  lr: 0.002892  min_lr: 0.002892  loss: 2.6948 (2.5565)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0003  max mem: 42573
Epoch: [118]  [260/312]  eta: 0:00:24  lr: 0.002892  min_lr: 0.002892  loss: 2.6914 (2.5570)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0003  max mem: 42573
Epoch: [118]  [270/312]  eta: 0:00:19  lr: 0.002891  min_lr: 0.002891  loss: 2.5662 (2.5576)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0003  max mem: 42573
Epoch: [118]  [280/312]  eta: 0:00:15  lr: 0.002890  min_lr: 0.002890  loss: 2.5218 (2.5495)  weight_decay: 0.0500 (0.0500)  time: 0.4342  data: 0.0009  max mem: 42573
Epoch: [118]  [290/312]  eta: 0:00:10  lr: 0.002890  min_lr: 0.002890  loss: 2.3581 (2.5429)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0008  max mem: 42573
Epoch: [118]  [300/312]  eta: 0:00:05  lr: 0.002889  min_lr: 0.002889  loss: 2.6046 (2.5464)  weight_decay: 0.0500 (0.0500)  time: 0.4324  data: 0.0001  max mem: 42573
Epoch: [118]  [310/312]  eta: 0:00:00  lr: 0.002888  min_lr: 0.002888  loss: 2.6952 (2.5484)  weight_decay: 0.0500 (0.0500)  time: 0.4323  data: 0.0001  max mem: 42573
Epoch: [118]  [311/312]  eta: 0:00:00  lr: 0.002888  min_lr: 0.002888  loss: 2.5839 (2.5485)  weight_decay: 0.0500 (0.0500)  time: 0.4322  data: 0.0001  max mem: 42573
Epoch: [118] Total time: 0:02:27 (0.4723 s / it)
Averaged stats: lr: 0.002888  min_lr: 0.002888  loss: 2.5839 (2.5620)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:00:46  loss: 0.9369 (0.9369)  acc1: 75.7812 (75.7812)  acc5: 92.9688 (92.9688)  time: 5.2114  data: 5.1020  max mem: 42573
Test:  [8/9]  eta: 0:00:00  loss: 1.2954 (1.2140)  acc1: 67.9688 (69.4400)  acc5: 89.0625 (89.3120)  time: 0.6600  data: 0.5670  max mem: 42573
Test: Total time: 0:00:06 (0.6683 s / it)
* Acc@1 70.586 Acc@5 89.560 loss 1.206
Accuracy of the model on the 50000 test images: 70.6%
Max accuracy: 71.11%
Epoch: [119]  [  0/312]  eta: 0:47:15  lr: 0.002888  min_lr: 0.002888  loss: 3.3194 (3.3194)  weight_decay: 0.0500 (0.0500)  time: 9.0871  data: 8.2307  max mem: 42573
Epoch: [119]  [ 10/312]  eta: 0:07:13  lr: 0.002888  min_lr: 0.002888  loss: 2.7442 (2.6619)  weight_decay: 0.0500 (0.0500)  time: 1.4348  data: 0.7520  max mem: 42573
Epoch: [119]  [ 20/312]  eta: 0:04:39  lr: 0.002887  min_lr: 0.002887  loss: 2.7072 (2.6858)  weight_decay: 0.0500 (0.0500)  time: 0.5513  data: 0.0023  max mem: 42573
Epoch: [119]  [ 30/312]  eta: 0:03:42  lr: 0.002886  min_lr: 0.002886  loss: 2.5270 (2.5836)  weight_decay: 0.0500 (0.0500)  time: 0.4330  data: 0.0004  max mem: 42573
Epoch: [119]  [ 40/312]  eta: 0:03:10  lr: 0.002886  min_lr: 0.002886  loss: 2.5389 (2.5915)  weight_decay: 0.0500 (0.0500)  time: 0.4330  data: 0.0004  max mem: 42573
Epoch: [119]  [ 50/312]  eta: 0:02:50  lr: 0.002885  min_lr: 0.002885  loss: 2.5389 (2.5511)  weight_decay: 0.0500 (0.0500)  time: 0.4332  data: 0.0005  max mem: 42573
Epoch: [119]  [ 60/312]  eta: 0:02:34  lr: 0.002884  min_lr: 0.002884  loss: 2.3765 (2.5304)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [119]  [ 70/312]  eta: 0:02:22  lr: 0.002884  min_lr: 0.002884  loss: 2.6274 (2.5552)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [119]  [ 80/312]  eta: 0:02:12  lr: 0.002883  min_lr: 0.002883  loss: 2.6926 (2.5495)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [119]  [ 90/312]  eta: 0:02:03  lr: 0.002882  min_lr: 0.002882  loss: 2.7346 (2.5658)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [119]  [100/312]  eta: 0:01:55  lr: 0.002882  min_lr: 0.002882  loss: 2.8306 (2.5800)  weight_decay: 0.0500 (0.0500)  time: 0.4413  data: 0.0004  max mem: 42573
Epoch: [119]  [110/312]  eta: 0:01:47  lr: 0.002881  min_lr: 0.002881  loss: 2.7432 (2.5723)  weight_decay: 0.0500 (0.0500)  time: 0.4414  data: 0.0004  max mem: 42573
Epoch: [119]  [120/312]  eta: 0:01:40  lr: 0.002880  min_lr: 0.002880  loss: 2.5367 (2.5617)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [119]  [130/312]  eta: 0:01:34  lr: 0.002880  min_lr: 0.002880  loss: 2.4819 (2.5497)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [119]  [140/312]  eta: 0:01:28  lr: 0.002879  min_lr: 0.002879  loss: 2.4064 (2.5479)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [119]  [150/312]  eta: 0:01:22  lr: 0.002879  min_lr: 0.002879  loss: 2.6536 (2.5552)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [119]  [160/312]  eta: 0:01:16  lr: 0.002878  min_lr: 0.002878  loss: 2.7077 (2.5628)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0004  max mem: 42573
Epoch: [119]  [170/312]  eta: 0:01:10  lr: 0.002877  min_lr: 0.002877  loss: 2.6980 (2.5670)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [119]  [180/312]  eta: 0:01:05  lr: 0.002877  min_lr: 0.002877  loss: 2.4761 (2.5491)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [119]  [190/312]  eta: 0:01:00  lr: 0.002876  min_lr: 0.002876  loss: 2.4275 (2.5490)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [119]  [200/312]  eta: 0:00:54  lr: 0.002875  min_lr: 0.002875  loss: 2.4747 (2.5416)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0003  max mem: 42573
Epoch: [119]  [210/312]  eta: 0:00:49  lr: 0.002875  min_lr: 0.002875  loss: 2.4151 (2.5325)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [119]  [220/312]  eta: 0:00:44  lr: 0.002874  min_lr: 0.002874  loss: 2.5558 (2.5409)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [119]  [230/312]  eta: 0:00:39  lr: 0.002873  min_lr: 0.002873  loss: 2.5820 (2.5291)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0003  max mem: 42573
Epoch: [119]  [240/312]  eta: 0:00:34  lr: 0.002873  min_lr: 0.002873  loss: 2.5642 (2.5314)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [119]  [250/312]  eta: 0:00:29  lr: 0.002872  min_lr: 0.002872  loss: 2.7198 (2.5397)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [119]  [260/312]  eta: 0:00:24  lr: 0.002871  min_lr: 0.002871  loss: 2.8536 (2.5503)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [119]  [270/312]  eta: 0:00:19  lr: 0.002871  min_lr: 0.002871  loss: 2.7659 (2.5522)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [119]  [280/312]  eta: 0:00:15  lr: 0.002870  min_lr: 0.002870  loss: 2.4780 (2.5434)  weight_decay: 0.0500 (0.0500)  time: 0.4343  data: 0.0009  max mem: 42573
Epoch: [119]  [290/312]  eta: 0:00:10  lr: 0.002869  min_lr: 0.002869  loss: 2.3148 (2.5459)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0008  max mem: 42573
Epoch: [119]  [300/312]  eta: 0:00:05  lr: 0.002869  min_lr: 0.002869  loss: 2.3471 (2.5432)  weight_decay: 0.0500 (0.0500)  time: 0.4325  data: 0.0001  max mem: 42573
Epoch: [119]  [310/312]  eta: 0:00:00  lr: 0.002868  min_lr: 0.002868  loss: 2.3471 (2.5385)  weight_decay: 0.0500 (0.0500)  time: 0.4324  data: 0.0001  max mem: 42573
Epoch: [119]  [311/312]  eta: 0:00:00  lr: 0.002868  min_lr: 0.002868  loss: 2.3471 (2.5379)  weight_decay: 0.0500 (0.0500)  time: 0.4324  data: 0.0001  max mem: 42573
Epoch: [119] Total time: 0:02:27 (0.4722 s / it)
Averaged stats: lr: 0.002868  min_lr: 0.002868  loss: 2.3471 (2.5624)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:00:43  loss: 0.9173 (0.9173)  acc1: 78.1250 (78.1250)  acc5: 92.9688 (92.9688)  time: 4.8220  data: 4.7128  max mem: 42573
Test:  [8/9]  eta: 0:00:00  loss: 1.2938 (1.1650)  acc1: 67.9688 (70.4000)  acc5: 89.0625 (89.7280)  time: 0.6125  data: 0.5237  max mem: 42573
Test: Total time: 0:00:05 (0.6301 s / it)
* Acc@1 71.436 Acc@5 90.162 loss 1.156
Accuracy of the model on the 50000 test images: 71.4%
Max accuracy: 71.44%
Epoch: [120]  [  0/312]  eta: 0:44:08  lr: 0.002868  min_lr: 0.002868  loss: 2.7792 (2.7792)  weight_decay: 0.0500 (0.0500)  time: 8.4872  data: 7.1549  max mem: 42573
Epoch: [120]  [ 10/312]  eta: 0:07:03  lr: 0.002867  min_lr: 0.002867  loss: 2.6342 (2.6031)  weight_decay: 0.0500 (0.0500)  time: 1.4019  data: 0.6876  max mem: 42573
Epoch: [120]  [ 20/312]  eta: 0:04:34  lr: 0.002867  min_lr: 0.002867  loss: 2.5804 (2.5049)  weight_decay: 0.0500 (0.0500)  time: 0.5634  data: 0.0207  max mem: 42573
Epoch: [120]  [ 30/312]  eta: 0:03:39  lr: 0.002866  min_lr: 0.002866  loss: 2.6196 (2.5481)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [120]  [ 40/312]  eta: 0:03:08  lr: 0.002865  min_lr: 0.002865  loss: 2.6196 (2.5168)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [120]  [ 50/312]  eta: 0:02:48  lr: 0.002865  min_lr: 0.002865  loss: 2.6263 (2.5494)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [120]  [ 60/312]  eta: 0:02:33  lr: 0.002864  min_lr: 0.002864  loss: 2.6594 (2.5517)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [120]  [ 70/312]  eta: 0:02:21  lr: 0.002864  min_lr: 0.002864  loss: 2.6297 (2.5502)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [120]  [ 80/312]  eta: 0:02:11  lr: 0.002863  min_lr: 0.002863  loss: 2.6100 (2.5546)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [120]  [ 90/312]  eta: 0:02:02  lr: 0.002862  min_lr: 0.002862  loss: 2.5827 (2.5397)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [120]  [100/312]  eta: 0:01:54  lr: 0.002862  min_lr: 0.002862  loss: 2.6030 (2.5516)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [120]  [110/312]  eta: 0:01:46  lr: 0.002861  min_lr: 0.002861  loss: 2.6238 (2.5357)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0003  max mem: 42573
Epoch: [120]  [120/312]  eta: 0:01:40  lr: 0.002860  min_lr: 0.002860  loss: 2.7892 (2.5705)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0003  max mem: 42573
Epoch: [120]  [130/312]  eta: 0:01:33  lr: 0.002860  min_lr: 0.002860  loss: 2.6350 (2.5497)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [120]  [140/312]  eta: 0:01:27  lr: 0.002859  min_lr: 0.002859  loss: 2.4199 (2.5490)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [120]  [150/312]  eta: 0:01:21  lr: 0.002858  min_lr: 0.002858  loss: 2.5431 (2.5638)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0004  max mem: 42573
Epoch: [120]  [160/312]  eta: 0:01:15  lr: 0.002858  min_lr: 0.002858  loss: 2.5799 (2.5585)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [120]  [170/312]  eta: 0:01:10  lr: 0.002857  min_lr: 0.002857  loss: 2.5799 (2.5665)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [120]  [180/312]  eta: 0:01:05  lr: 0.002856  min_lr: 0.002856  loss: 2.7529 (2.5758)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [120]  [190/312]  eta: 0:00:59  lr: 0.002856  min_lr: 0.002856  loss: 2.7057 (2.5733)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [120]  [200/312]  eta: 0:00:54  lr: 0.002855  min_lr: 0.002855  loss: 2.6384 (2.5672)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0003  max mem: 42573
Epoch: [120]  [210/312]  eta: 0:00:49  lr: 0.002854  min_lr: 0.002854  loss: 2.5285 (2.5603)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [120]  [220/312]  eta: 0:00:44  lr: 0.002854  min_lr: 0.002854  loss: 2.5937 (2.5607)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0003  max mem: 42573
Epoch: [120]  [230/312]  eta: 0:00:39  lr: 0.002853  min_lr: 0.002853  loss: 2.3527 (2.5487)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [120]  [240/312]  eta: 0:00:34  lr: 0.002852  min_lr: 0.002852  loss: 2.3506 (2.5485)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [120]  [250/312]  eta: 0:00:29  lr: 0.002852  min_lr: 0.002852  loss: 2.6541 (2.5490)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0003  max mem: 42573
Epoch: [120]  [260/312]  eta: 0:00:24  lr: 0.002851  min_lr: 0.002851  loss: 2.6541 (2.5519)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [120]  [270/312]  eta: 0:00:19  lr: 0.002851  min_lr: 0.002851  loss: 2.5962 (2.5519)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [120]  [280/312]  eta: 0:00:15  lr: 0.002850  min_lr: 0.002850  loss: 2.4113 (2.5459)  weight_decay: 0.0500 (0.0500)  time: 0.4345  data: 0.0009  max mem: 42573
Epoch: [120]  [290/312]  eta: 0:00:10  lr: 0.002849  min_lr: 0.002849  loss: 2.4528 (2.5453)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0008  max mem: 42573
Epoch: [120]  [300/312]  eta: 0:00:05  lr: 0.002849  min_lr: 0.002849  loss: 2.5188 (2.5503)  weight_decay: 0.0500 (0.0500)  time: 0.4325  data: 0.0001  max mem: 42573
Epoch: [120]  [310/312]  eta: 0:00:00  lr: 0.002848  min_lr: 0.002848  loss: 2.5286 (2.5424)  weight_decay: 0.0500 (0.0500)  time: 0.4324  data: 0.0001  max mem: 42573
Epoch: [120]  [311/312]  eta: 0:00:00  lr: 0.002848  min_lr: 0.002848  loss: 2.4604 (2.5421)  weight_decay: 0.0500 (0.0500)  time: 0.4324  data: 0.0001  max mem: 42573
Epoch: [120] Total time: 0:02:26 (0.4707 s / it)
Averaged stats: lr: 0.002848  min_lr: 0.002848  loss: 2.4604 (2.5492)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:00:44  loss: 0.8936 (0.8936)  acc1: 81.2500 (81.2500)  acc5: 91.9271 (91.9271)  time: 4.9170  data: 4.8077  max mem: 42573
Test:  [8/9]  eta: 0:00:00  loss: 1.2481 (1.1631)  acc1: 69.5312 (70.5280)  acc5: 89.8438 (90.0800)  time: 0.6235  data: 0.5343  max mem: 42573
Test: Total time: 0:00:05 (0.6492 s / it)
* Acc@1 71.138 Acc@5 90.200 loss 1.158
Accuracy of the model on the 50000 test images: 71.1%
Max accuracy: 71.44%
Epoch: [121]  [  0/312]  eta: 0:45:41  lr: 0.002848  min_lr: 0.002848  loss: 2.6682 (2.6682)  weight_decay: 0.0500 (0.0500)  time: 8.7876  data: 6.5766  max mem: 42573
Epoch: [121]  [ 10/312]  eta: 0:06:53  lr: 0.002847  min_lr: 0.002847  loss: 2.9545 (2.7200)  weight_decay: 0.0500 (0.0500)  time: 1.3678  data: 0.7333  max mem: 42573
Epoch: [121]  [ 20/312]  eta: 0:04:30  lr: 0.002846  min_lr: 0.002846  loss: 2.7566 (2.6283)  weight_decay: 0.0500 (0.0500)  time: 0.5332  data: 0.0746  max mem: 42573
Epoch: [121]  [ 30/312]  eta: 0:03:36  lr: 0.002846  min_lr: 0.002846  loss: 2.6469 (2.6307)  weight_decay: 0.0500 (0.0500)  time: 0.4370  data: 0.0003  max mem: 42573
Epoch: [121]  [ 40/312]  eta: 0:03:06  lr: 0.002845  min_lr: 0.002845  loss: 2.5624 (2.5772)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0003  max mem: 42573
Epoch: [121]  [ 50/312]  eta: 0:02:46  lr: 0.002845  min_lr: 0.002845  loss: 2.5624 (2.6169)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [121]  [ 60/312]  eta: 0:02:32  lr: 0.002844  min_lr: 0.002844  loss: 2.6127 (2.5956)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [121]  [ 70/312]  eta: 0:02:20  lr: 0.002843  min_lr: 0.002843  loss: 2.3711 (2.5544)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [121]  [ 80/312]  eta: 0:02:10  lr: 0.002843  min_lr: 0.002843  loss: 2.3503 (2.5238)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [121]  [ 90/312]  eta: 0:02:01  lr: 0.002842  min_lr: 0.002842  loss: 2.5795 (2.5434)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0003  max mem: 42573
Epoch: [121]  [100/312]  eta: 0:01:53  lr: 0.002841  min_lr: 0.002841  loss: 2.6273 (2.5366)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [121]  [110/312]  eta: 0:01:46  lr: 0.002841  min_lr: 0.002841  loss: 2.5341 (2.5374)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [121]  [120/312]  eta: 0:01:39  lr: 0.002840  min_lr: 0.002840  loss: 2.4949 (2.5304)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [121]  [130/312]  eta: 0:01:33  lr: 0.002839  min_lr: 0.002839  loss: 2.4099 (2.5301)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0004  max mem: 42573
Epoch: [121]  [140/312]  eta: 0:01:27  lr: 0.002839  min_lr: 0.002839  loss: 2.5055 (2.5352)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0003  max mem: 42573
Epoch: [121]  [150/312]  eta: 0:01:21  lr: 0.002838  min_lr: 0.002838  loss: 2.5508 (2.5382)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0003  max mem: 42573
Epoch: [121]  [160/312]  eta: 0:01:15  lr: 0.002837  min_lr: 0.002837  loss: 2.6034 (2.5488)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [121]  [170/312]  eta: 0:01:10  lr: 0.002837  min_lr: 0.002837  loss: 2.6911 (2.5518)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0004  max mem: 42573
Epoch: [121]  [180/312]  eta: 0:01:04  lr: 0.002836  min_lr: 0.002836  loss: 2.6911 (2.5571)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [121]  [190/312]  eta: 0:00:59  lr: 0.002835  min_lr: 0.002835  loss: 2.7266 (2.5658)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0003  max mem: 42573
Epoch: [121]  [200/312]  eta: 0:00:54  lr: 0.002835  min_lr: 0.002835  loss: 2.7657 (2.5688)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0003  max mem: 42573
Epoch: [121]  [210/312]  eta: 0:00:49  lr: 0.002834  min_lr: 0.002834  loss: 2.4482 (2.5625)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0003  max mem: 42573
Epoch: [121]  [220/312]  eta: 0:00:44  lr: 0.002833  min_lr: 0.002833  loss: 2.7348 (2.5695)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [121]  [230/312]  eta: 0:00:39  lr: 0.002833  min_lr: 0.002833  loss: 2.7588 (2.5733)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [121]  [240/312]  eta: 0:00:34  lr: 0.002832  min_lr: 0.002832  loss: 2.5728 (2.5696)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [121]  [250/312]  eta: 0:00:29  lr: 0.002831  min_lr: 0.002831  loss: 2.3153 (2.5624)  weight_decay: 0.0500 (0.0500)  time: 0.4381  data: 0.0004  max mem: 42573
Epoch: [121]  [260/312]  eta: 0:00:24  lr: 0.002831  min_lr: 0.002831  loss: 2.4810 (2.5656)  weight_decay: 0.0500 (0.0500)  time: 0.4382  data: 0.0004  max mem: 42573
Epoch: [121]  [270/312]  eta: 0:00:19  lr: 0.002830  min_lr: 0.002830  loss: 2.7154 (2.5710)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0004  max mem: 42573
Epoch: [121]  [280/312]  eta: 0:00:15  lr: 0.002830  min_lr: 0.002830  loss: 2.5713 (2.5643)  weight_decay: 0.0500 (0.0500)  time: 0.4346  data: 0.0010  max mem: 42573
Epoch: [121]  [290/312]  eta: 0:00:10  lr: 0.002829  min_lr: 0.002829  loss: 2.5599 (2.5648)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0009  max mem: 42573
Epoch: [121]  [300/312]  eta: 0:00:05  lr: 0.002828  min_lr: 0.002828  loss: 2.6341 (2.5654)  weight_decay: 0.0500 (0.0500)  time: 0.4325  data: 0.0001  max mem: 42573
Epoch: [121]  [310/312]  eta: 0:00:00  lr: 0.002828  min_lr: 0.002828  loss: 2.4605 (2.5583)  weight_decay: 0.0500 (0.0500)  time: 0.4324  data: 0.0001  max mem: 42573
Epoch: [121]  [311/312]  eta: 0:00:00  lr: 0.002827  min_lr: 0.002827  loss: 2.4605 (2.5603)  weight_decay: 0.0500 (0.0500)  time: 0.4324  data: 0.0001  max mem: 42573
Epoch: [121] Total time: 0:02:26 (0.4700 s / it)
Averaged stats: lr: 0.002827  min_lr: 0.002827  loss: 2.4605 (2.5546)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:00:44  loss: 0.9621 (0.9621)  acc1: 76.3021 (76.3021)  acc5: 92.4479 (92.4479)  time: 4.9104  data: 4.8012  max mem: 42573
Test:  [8/9]  eta: 0:00:00  loss: 1.3196 (1.1849)  acc1: 69.2708 (70.3680)  acc5: 89.3229 (90.0800)  time: 0.6215  data: 0.5335  max mem: 42573
Test: Total time: 0:00:05 (0.6470 s / it)
* Acc@1 70.804 Acc@5 89.928 loss 1.177
Accuracy of the model on the 50000 test images: 70.8%
Max accuracy: 71.44%
Epoch: [122]  [  0/312]  eta: 0:45:41  lr: 0.002827  min_lr: 0.002827  loss: 2.8320 (2.8320)  weight_decay: 0.0500 (0.0500)  time: 8.7882  data: 7.1032  max mem: 42573
Epoch: [122]  [ 10/312]  eta: 0:07:12  lr: 0.002827  min_lr: 0.002827  loss: 2.6397 (2.4990)  weight_decay: 0.0500 (0.0500)  time: 1.4308  data: 0.7822  max mem: 42573
Epoch: [122]  [ 20/312]  eta: 0:04:39  lr: 0.002826  min_lr: 0.002826  loss: 2.4936 (2.4688)  weight_decay: 0.0500 (0.0500)  time: 0.5642  data: 0.0752  max mem: 42573
Epoch: [122]  [ 30/312]  eta: 0:03:41  lr: 0.002825  min_lr: 0.002825  loss: 2.5309 (2.4664)  weight_decay: 0.0500 (0.0500)  time: 0.4332  data: 0.0004  max mem: 42573
Epoch: [122]  [ 40/312]  eta: 0:03:10  lr: 0.002825  min_lr: 0.002825  loss: 2.4697 (2.4645)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [122]  [ 50/312]  eta: 0:02:49  lr: 0.002824  min_lr: 0.002824  loss: 2.4720 (2.4669)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [122]  [ 60/312]  eta: 0:02:34  lr: 0.002823  min_lr: 0.002823  loss: 2.4720 (2.4508)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [122]  [ 70/312]  eta: 0:02:22  lr: 0.002823  min_lr: 0.002823  loss: 2.4841 (2.4687)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [122]  [ 80/312]  eta: 0:02:11  lr: 0.002822  min_lr: 0.002822  loss: 2.4841 (2.4632)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [122]  [ 90/312]  eta: 0:02:03  lr: 0.002822  min_lr: 0.002822  loss: 2.4084 (2.4670)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [122]  [100/312]  eta: 0:01:54  lr: 0.002821  min_lr: 0.002821  loss: 2.5811 (2.4783)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [122]  [110/312]  eta: 0:01:47  lr: 0.002820  min_lr: 0.002820  loss: 2.5811 (2.4874)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [122]  [120/312]  eta: 0:01:40  lr: 0.002820  min_lr: 0.002820  loss: 2.5255 (2.4926)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [122]  [130/312]  eta: 0:01:34  lr: 0.002819  min_lr: 0.002819  loss: 2.6521 (2.4944)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [122]  [140/312]  eta: 0:01:27  lr: 0.002818  min_lr: 0.002818  loss: 2.6540 (2.5086)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [122]  [150/312]  eta: 0:01:22  lr: 0.002818  min_lr: 0.002818  loss: 2.8301 (2.5182)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0003  max mem: 42573
Epoch: [122]  [160/312]  eta: 0:01:16  lr: 0.002817  min_lr: 0.002817  loss: 2.4654 (2.5047)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0003  max mem: 42573
Epoch: [122]  [170/312]  eta: 0:01:10  lr: 0.002816  min_lr: 0.002816  loss: 2.4853 (2.5071)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [122]  [180/312]  eta: 0:01:05  lr: 0.002816  min_lr: 0.002816  loss: 2.5588 (2.5039)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [122]  [190/312]  eta: 0:00:59  lr: 0.002815  min_lr: 0.002815  loss: 2.5536 (2.5044)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [122]  [200/312]  eta: 0:00:54  lr: 0.002814  min_lr: 0.002814  loss: 2.7465 (2.5184)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [122]  [210/312]  eta: 0:00:49  lr: 0.002814  min_lr: 0.002814  loss: 2.7465 (2.5269)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [122]  [220/312]  eta: 0:00:44  lr: 0.002813  min_lr: 0.002813  loss: 2.5651 (2.5295)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0003  max mem: 42573
Epoch: [122]  [230/312]  eta: 0:00:39  lr: 0.002812  min_lr: 0.002812  loss: 2.5557 (2.5304)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [122]  [240/312]  eta: 0:00:34  lr: 0.002812  min_lr: 0.002812  loss: 2.3160 (2.5255)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0003  max mem: 42573
Epoch: [122]  [250/312]  eta: 0:00:29  lr: 0.002811  min_lr: 0.002811  loss: 2.4043 (2.5328)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0003  max mem: 42573
Epoch: [122]  [260/312]  eta: 0:00:24  lr: 0.002810  min_lr: 0.002810  loss: 2.6413 (2.5368)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [122]  [270/312]  eta: 0:00:19  lr: 0.002810  min_lr: 0.002810  loss: 2.6256 (2.5357)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [122]  [280/312]  eta: 0:00:15  lr: 0.002809  min_lr: 0.002809  loss: 2.6556 (2.5426)  weight_decay: 0.0500 (0.0500)  time: 0.4350  data: 0.0009  max mem: 42573
Epoch: [122]  [290/312]  eta: 0:00:10  lr: 0.002808  min_lr: 0.002808  loss: 2.7559 (2.5438)  weight_decay: 0.0500 (0.0500)  time: 0.4343  data: 0.0008  max mem: 42573
Epoch: [122]  [300/312]  eta: 0:00:05  lr: 0.002808  min_lr: 0.002808  loss: 2.6304 (2.5392)  weight_decay: 0.0500 (0.0500)  time: 0.4325  data: 0.0001  max mem: 42573
Epoch: [122]  [310/312]  eta: 0:00:00  lr: 0.002807  min_lr: 0.002807  loss: 2.3811 (2.5287)  weight_decay: 0.0500 (0.0500)  time: 0.4324  data: 0.0001  max mem: 42573
Epoch: [122]  [311/312]  eta: 0:00:00  lr: 0.002807  min_lr: 0.002807  loss: 2.0639 (2.5270)  weight_decay: 0.0500 (0.0500)  time: 0.4324  data: 0.0001  max mem: 42573
Epoch: [122] Total time: 0:02:27 (0.4718 s / it)
Averaged stats: lr: 0.002807  min_lr: 0.002807  loss: 2.0639 (2.5465)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:00:44  loss: 0.8045 (0.8045)  acc1: 77.6042 (77.6042)  acc5: 93.7500 (93.7500)  time: 4.9292  data: 4.8198  max mem: 42573
Test:  [8/9]  eta: 0:00:00  loss: 1.2157 (1.1098)  acc1: 70.8333 (71.2640)  acc5: 89.8438 (90.4960)  time: 0.6243  data: 0.5356  max mem: 42573
Test: Total time: 0:00:05 (0.6330 s / it)
* Acc@1 72.088 Acc@5 90.440 loss 1.114
Accuracy of the model on the 50000 test images: 72.1%
Max accuracy: 72.09%
Epoch: [123]  [  0/312]  eta: 0:45:48  lr: 0.002807  min_lr: 0.002807  loss: 2.4432 (2.4432)  weight_decay: 0.0500 (0.0500)  time: 8.8082  data: 7.1238  max mem: 42573
Epoch: [123]  [ 10/312]  eta: 0:06:48  lr: 0.002806  min_lr: 0.002806  loss: 2.6665 (2.5829)  weight_decay: 0.0500 (0.0500)  time: 1.3531  data: 0.6814  max mem: 42573
Epoch: [123]  [ 20/312]  eta: 0:04:27  lr: 0.002806  min_lr: 0.002806  loss: 2.6665 (2.5405)  weight_decay: 0.0500 (0.0500)  time: 0.5205  data: 0.0188  max mem: 42573
Epoch: [123]  [ 30/312]  eta: 0:03:34  lr: 0.002805  min_lr: 0.002805  loss: 2.4492 (2.5384)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [123]  [ 40/312]  eta: 0:03:05  lr: 0.002804  min_lr: 0.002804  loss: 2.4492 (2.5163)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [123]  [ 50/312]  eta: 0:02:45  lr: 0.002804  min_lr: 0.002804  loss: 2.5472 (2.5481)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [123]  [ 60/312]  eta: 0:02:31  lr: 0.002803  min_lr: 0.002803  loss: 2.5472 (2.5085)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [123]  [ 70/312]  eta: 0:02:19  lr: 0.002802  min_lr: 0.002802  loss: 2.4560 (2.5143)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [123]  [ 80/312]  eta: 0:02:09  lr: 0.002802  min_lr: 0.002802  loss: 2.4920 (2.5025)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [123]  [ 90/312]  eta: 0:02:00  lr: 0.002801  min_lr: 0.002801  loss: 2.4939 (2.4960)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0003  max mem: 42573
Epoch: [123]  [100/312]  eta: 0:01:53  lr: 0.002800  min_lr: 0.002800  loss: 2.6247 (2.5182)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0003  max mem: 42573
Epoch: [123]  [110/312]  eta: 0:01:46  lr: 0.002800  min_lr: 0.002800  loss: 2.6503 (2.5205)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [123]  [120/312]  eta: 0:01:39  lr: 0.002799  min_lr: 0.002799  loss: 2.6503 (2.5256)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [123]  [130/312]  eta: 0:01:32  lr: 0.002798  min_lr: 0.002798  loss: 2.8761 (2.5477)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [123]  [140/312]  eta: 0:01:26  lr: 0.002798  min_lr: 0.002798  loss: 2.7628 (2.5488)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [123]  [150/312]  eta: 0:01:21  lr: 0.002797  min_lr: 0.002797  loss: 2.6211 (2.5399)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [123]  [160/312]  eta: 0:01:15  lr: 0.002796  min_lr: 0.002796  loss: 2.5098 (2.5411)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [123]  [170/312]  eta: 0:01:09  lr: 0.002796  min_lr: 0.002796  loss: 2.7548 (2.5496)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [123]  [180/312]  eta: 0:01:04  lr: 0.002795  min_lr: 0.002795  loss: 2.6993 (2.5517)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [123]  [190/312]  eta: 0:00:59  lr: 0.002794  min_lr: 0.002794  loss: 2.6430 (2.5450)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0005  max mem: 42573
Epoch: [123]  [200/312]  eta: 0:00:54  lr: 0.002794  min_lr: 0.002794  loss: 2.1155 (2.5273)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [123]  [210/312]  eta: 0:00:49  lr: 0.002793  min_lr: 0.002793  loss: 2.5524 (2.5370)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [123]  [220/312]  eta: 0:00:44  lr: 0.002792  min_lr: 0.002792  loss: 2.5524 (2.5282)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [123]  [230/312]  eta: 0:00:39  lr: 0.002792  min_lr: 0.002792  loss: 2.3035 (2.5242)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [123]  [240/312]  eta: 0:00:34  lr: 0.002791  min_lr: 0.002791  loss: 2.4909 (2.5235)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [123]  [250/312]  eta: 0:00:29  lr: 0.002790  min_lr: 0.002790  loss: 2.5735 (2.5282)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0004  max mem: 42573
Epoch: [123]  [260/312]  eta: 0:00:24  lr: 0.002790  min_lr: 0.002790  loss: 2.4430 (2.5188)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [123]  [270/312]  eta: 0:00:19  lr: 0.002789  min_lr: 0.002789  loss: 2.5055 (2.5236)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [123]  [280/312]  eta: 0:00:15  lr: 0.002788  min_lr: 0.002788  loss: 2.5486 (2.5198)  weight_decay: 0.0500 (0.0500)  time: 0.4345  data: 0.0009  max mem: 42573
Epoch: [123]  [290/312]  eta: 0:00:10  lr: 0.002788  min_lr: 0.002788  loss: 2.5885 (2.5193)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0008  max mem: 42573
Epoch: [123]  [300/312]  eta: 0:00:05  lr: 0.002787  min_lr: 0.002787  loss: 2.5593 (2.5175)  weight_decay: 0.0500 (0.0500)  time: 0.4324  data: 0.0001  max mem: 42573
Epoch: [123]  [310/312]  eta: 0:00:00  lr: 0.002786  min_lr: 0.002786  loss: 2.4483 (2.5184)  weight_decay: 0.0500 (0.0500)  time: 0.4324  data: 0.0001  max mem: 42573
Epoch: [123]  [311/312]  eta: 0:00:00  lr: 0.002786  min_lr: 0.002786  loss: 2.5170 (2.5187)  weight_decay: 0.0500 (0.0500)  time: 0.4324  data: 0.0001  max mem: 42573
Epoch: [123] Total time: 0:02:26 (0.4690 s / it)
Averaged stats: lr: 0.002786  min_lr: 0.002786  loss: 2.5170 (2.5406)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:00:43  loss: 0.9240 (0.9240)  acc1: 77.0833 (77.0833)  acc5: 92.1875 (92.1875)  time: 4.8848  data: 4.7754  max mem: 42573
Test:  [8/9]  eta: 0:00:00  loss: 1.3138 (1.1839)  acc1: 70.3125 (70.7520)  acc5: 89.3229 (89.9200)  time: 0.6212  data: 0.5307  max mem: 42573
Test: Total time: 0:00:05 (0.6470 s / it)
* Acc@1 70.658 Acc@5 90.084 loss 1.194
Accuracy of the model on the 50000 test images: 70.7%
Max accuracy: 72.09%
Epoch: [124]  [  0/312]  eta: 0:49:36  lr: 0.002786  min_lr: 0.002786  loss: 3.0563 (3.0563)  weight_decay: 0.0500 (0.0500)  time: 9.5407  data: 6.6877  max mem: 42573
Epoch: [124]  [ 10/312]  eta: 0:07:31  lr: 0.002786  min_lr: 0.002786  loss: 2.6223 (2.4849)  weight_decay: 0.0500 (0.0500)  time: 1.4960  data: 0.7153  max mem: 42573
Epoch: [124]  [ 20/312]  eta: 0:04:49  lr: 0.002785  min_lr: 0.002785  loss: 2.4002 (2.4401)  weight_decay: 0.0500 (0.0500)  time: 0.5623  data: 0.0592  max mem: 42573
Epoch: [124]  [ 30/312]  eta: 0:03:48  lr: 0.002784  min_lr: 0.002784  loss: 2.5171 (2.4828)  weight_decay: 0.0500 (0.0500)  time: 0.4331  data: 0.0003  max mem: 42573
Epoch: [124]  [ 40/312]  eta: 0:03:15  lr: 0.002784  min_lr: 0.002784  loss: 2.6492 (2.5586)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [124]  [ 50/312]  eta: 0:02:53  lr: 0.002783  min_lr: 0.002783  loss: 2.6874 (2.5696)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [124]  [ 60/312]  eta: 0:02:38  lr: 0.002782  min_lr: 0.002782  loss: 2.7138 (2.5814)  weight_decay: 0.0500 (0.0500)  time: 0.4429  data: 0.0004  max mem: 42573
Epoch: [124]  [ 70/312]  eta: 0:02:25  lr: 0.002782  min_lr: 0.002782  loss: 2.7138 (2.5742)  weight_decay: 0.0500 (0.0500)  time: 0.4430  data: 0.0004  max mem: 42573
Epoch: [124]  [ 80/312]  eta: 0:02:14  lr: 0.002781  min_lr: 0.002781  loss: 2.6573 (2.5658)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [124]  [ 90/312]  eta: 0:02:05  lr: 0.002780  min_lr: 0.002780  loss: 2.6992 (2.5879)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [124]  [100/312]  eta: 0:01:56  lr: 0.002780  min_lr: 0.002780  loss: 2.7030 (2.5815)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0004  max mem: 42573
Epoch: [124]  [110/312]  eta: 0:01:49  lr: 0.002779  min_lr: 0.002779  loss: 2.5350 (2.5787)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [124]  [120/312]  eta: 0:01:42  lr: 0.002778  min_lr: 0.002778  loss: 2.5076 (2.5626)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [124]  [130/312]  eta: 0:01:35  lr: 0.002778  min_lr: 0.002778  loss: 2.5076 (2.5660)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0003  max mem: 42573
Epoch: [124]  [140/312]  eta: 0:01:29  lr: 0.002777  min_lr: 0.002777  loss: 2.7379 (2.5695)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [124]  [150/312]  eta: 0:01:22  lr: 0.002776  min_lr: 0.002776  loss: 2.7379 (2.5791)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0003  max mem: 42573
Epoch: [124]  [160/312]  eta: 0:01:17  lr: 0.002776  min_lr: 0.002776  loss: 2.5314 (2.5684)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0003  max mem: 42573
Epoch: [124]  [170/312]  eta: 0:01:11  lr: 0.002775  min_lr: 0.002775  loss: 2.5314 (2.5741)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [124]  [180/312]  eta: 0:01:05  lr: 0.002774  min_lr: 0.002774  loss: 2.6666 (2.5703)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [124]  [190/312]  eta: 0:01:00  lr: 0.002774  min_lr: 0.002774  loss: 2.5465 (2.5723)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [124]  [200/312]  eta: 0:00:55  lr: 0.002773  min_lr: 0.002773  loss: 2.5689 (2.5746)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [124]  [210/312]  eta: 0:00:49  lr: 0.002772  min_lr: 0.002772  loss: 2.7687 (2.5840)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [124]  [220/312]  eta: 0:00:44  lr: 0.002772  min_lr: 0.002772  loss: 2.6347 (2.5826)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [124]  [230/312]  eta: 0:00:39  lr: 0.002771  min_lr: 0.002771  loss: 2.4837 (2.5762)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [124]  [240/312]  eta: 0:00:34  lr: 0.002770  min_lr: 0.002770  loss: 2.3328 (2.5685)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [124]  [250/312]  eta: 0:00:29  lr: 0.002770  min_lr: 0.002770  loss: 2.3491 (2.5630)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [124]  [260/312]  eta: 0:00:24  lr: 0.002769  min_lr: 0.002769  loss: 2.3622 (2.5535)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [124]  [270/312]  eta: 0:00:20  lr: 0.002768  min_lr: 0.002768  loss: 2.3619 (2.5501)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [124]  [280/312]  eta: 0:00:15  lr: 0.002768  min_lr: 0.002768  loss: 2.4683 (2.5499)  weight_decay: 0.0500 (0.0500)  time: 0.4347  data: 0.0014  max mem: 42573
Epoch: [124]  [290/312]  eta: 0:00:10  lr: 0.002767  min_lr: 0.002767  loss: 2.5802 (2.5498)  weight_decay: 0.0500 (0.0500)  time: 0.4341  data: 0.0013  max mem: 42573
Epoch: [124]  [300/312]  eta: 0:00:05  lr: 0.002766  min_lr: 0.002766  loss: 2.5493 (2.5499)  weight_decay: 0.0500 (0.0500)  time: 0.4325  data: 0.0001  max mem: 42573
Epoch: [124]  [310/312]  eta: 0:00:00  lr: 0.002766  min_lr: 0.002766  loss: 2.6614 (2.5519)  weight_decay: 0.0500 (0.0500)  time: 0.4324  data: 0.0001  max mem: 42573
Epoch: [124]  [311/312]  eta: 0:00:00  lr: 0.002766  min_lr: 0.002766  loss: 2.6085 (2.5498)  weight_decay: 0.0500 (0.0500)  time: 0.4324  data: 0.0001  max mem: 42573
Epoch: [124] Total time: 0:02:28 (0.4746 s / it)
Averaged stats: lr: 0.002766  min_lr: 0.002766  loss: 2.6085 (2.5475)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:00:43  loss: 0.8582 (0.8582)  acc1: 77.3438 (77.3438)  acc5: 94.7917 (94.7917)  time: 4.8650  data: 4.7554  max mem: 42573
Test:  [8/9]  eta: 0:00:00  loss: 1.2790 (1.1621)  acc1: 68.7500 (70.0160)  acc5: 90.8854 (90.1760)  time: 0.6165  data: 0.5285  max mem: 42573
Test: Total time: 0:00:05 (0.6421 s / it)
* Acc@1 70.930 Acc@5 90.110 loss 1.166
Accuracy of the model on the 50000 test images: 70.9%
Max accuracy: 72.09%
Epoch: [125]  [  0/312]  eta: 0:47:42  lr: 0.002766  min_lr: 0.002766  loss: 2.4116 (2.4116)  weight_decay: 0.0500 (0.0500)  time: 9.1737  data: 8.1048  max mem: 42573
Epoch: [125]  [ 10/312]  eta: 0:06:58  lr: 0.002765  min_lr: 0.002765  loss: 2.6888 (2.4980)  weight_decay: 0.0500 (0.0500)  time: 1.3874  data: 0.7372  max mem: 42573
Epoch: [125]  [ 20/312]  eta: 0:04:32  lr: 0.002764  min_lr: 0.002764  loss: 2.7272 (2.5722)  weight_decay: 0.0500 (0.0500)  time: 0.5215  data: 0.0004  max mem: 42573
Epoch: [125]  [ 30/312]  eta: 0:03:37  lr: 0.002764  min_lr: 0.002764  loss: 2.6111 (2.4859)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [125]  [ 40/312]  eta: 0:03:07  lr: 0.002763  min_lr: 0.002763  loss: 2.4242 (2.4686)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [125]  [ 50/312]  eta: 0:02:47  lr: 0.002762  min_lr: 0.002762  loss: 2.5158 (2.4934)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [125]  [ 60/312]  eta: 0:02:32  lr: 0.002762  min_lr: 0.002762  loss: 2.7549 (2.5092)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [125]  [ 70/312]  eta: 0:02:20  lr: 0.002761  min_lr: 0.002761  loss: 2.5442 (2.4940)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [125]  [ 80/312]  eta: 0:02:10  lr: 0.002760  min_lr: 0.002760  loss: 2.4844 (2.4898)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [125]  [ 90/312]  eta: 0:02:01  lr: 0.002760  min_lr: 0.002760  loss: 2.4844 (2.4957)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [125]  [100/312]  eta: 0:01:53  lr: 0.002759  min_lr: 0.002759  loss: 2.4903 (2.5031)  weight_decay: 0.0500 (0.0500)  time: 0.4343  data: 0.0004  max mem: 42573
Epoch: [125]  [110/312]  eta: 0:01:46  lr: 0.002758  min_lr: 0.002758  loss: 2.4803 (2.4989)  weight_decay: 0.0500 (0.0500)  time: 0.4343  data: 0.0004  max mem: 42573
Epoch: [125]  [120/312]  eta: 0:01:39  lr: 0.002758  min_lr: 0.002758  loss: 2.3577 (2.4995)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0003  max mem: 42573
Epoch: [125]  [130/312]  eta: 0:01:33  lr: 0.002757  min_lr: 0.002757  loss: 2.7552 (2.5152)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [125]  [140/312]  eta: 0:01:27  lr: 0.002756  min_lr: 0.002756  loss: 2.8183 (2.5308)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [125]  [150/312]  eta: 0:01:21  lr: 0.002756  min_lr: 0.002756  loss: 2.6795 (2.5310)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [125]  [160/312]  eta: 0:01:15  lr: 0.002755  min_lr: 0.002755  loss: 2.5405 (2.5251)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [125]  [170/312]  eta: 0:01:10  lr: 0.002754  min_lr: 0.002754  loss: 2.2360 (2.5156)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [125]  [180/312]  eta: 0:01:04  lr: 0.002754  min_lr: 0.002754  loss: 2.4179 (2.5169)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [125]  [190/312]  eta: 0:00:59  lr: 0.002753  min_lr: 0.002753  loss: 2.5104 (2.5156)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [125]  [200/312]  eta: 0:00:54  lr: 0.002752  min_lr: 0.002752  loss: 2.5898 (2.5203)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [125]  [210/312]  eta: 0:00:49  lr: 0.002752  min_lr: 0.002752  loss: 2.5826 (2.5162)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [125]  [220/312]  eta: 0:00:44  lr: 0.002751  min_lr: 0.002751  loss: 2.3339 (2.5135)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [125]  [230/312]  eta: 0:00:39  lr: 0.002750  min_lr: 0.002750  loss: 2.5644 (2.5141)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0003  max mem: 42573
Epoch: [125]  [240/312]  eta: 0:00:34  lr: 0.002750  min_lr: 0.002750  loss: 2.6896 (2.5139)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [125]  [250/312]  eta: 0:00:29  lr: 0.002749  min_lr: 0.002749  loss: 2.4406 (2.5138)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [125]  [260/312]  eta: 0:00:24  lr: 0.002748  min_lr: 0.002748  loss: 2.5159 (2.5137)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [125]  [270/312]  eta: 0:00:19  lr: 0.002748  min_lr: 0.002748  loss: 2.5570 (2.5084)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [125]  [280/312]  eta: 0:00:15  lr: 0.002747  min_lr: 0.002747  loss: 2.5248 (2.5076)  weight_decay: 0.0500 (0.0500)  time: 0.4342  data: 0.0009  max mem: 42573
Epoch: [125]  [290/312]  eta: 0:00:10  lr: 0.002746  min_lr: 0.002746  loss: 2.5227 (2.5059)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0008  max mem: 42573
Epoch: [125]  [300/312]  eta: 0:00:05  lr: 0.002746  min_lr: 0.002746  loss: 2.6946 (2.5070)  weight_decay: 0.0500 (0.0500)  time: 0.4323  data: 0.0001  max mem: 42573
Epoch: [125]  [310/312]  eta: 0:00:00  lr: 0.002745  min_lr: 0.002745  loss: 2.5668 (2.5080)  weight_decay: 0.0500 (0.0500)  time: 0.4323  data: 0.0001  max mem: 42573
Epoch: [125]  [311/312]  eta: 0:00:00  lr: 0.002745  min_lr: 0.002745  loss: 2.5900 (2.5086)  weight_decay: 0.0500 (0.0500)  time: 0.4323  data: 0.0001  max mem: 42573
Epoch: [125] Total time: 0:02:26 (0.4702 s / it)
Averaged stats: lr: 0.002745  min_lr: 0.002745  loss: 2.5900 (2.5409)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:00:44  loss: 0.8681 (0.8681)  acc1: 78.3854 (78.3854)  acc5: 94.7917 (94.7917)  time: 4.9743  data: 4.8649  max mem: 42573
Test:  [8/9]  eta: 0:00:00  loss: 1.1726 (1.2137)  acc1: 70.0521 (70.3680)  acc5: 91.6667 (90.5920)  time: 0.6287  data: 0.5406  max mem: 42573
Test: Total time: 0:00:05 (0.6547 s / it)
* Acc@1 70.668 Acc@5 90.004 loss 1.231
Accuracy of the model on the 50000 test images: 70.7%
Max accuracy: 72.09%
Epoch: [126]  [  0/312]  eta: 0:51:44  lr: 0.002745  min_lr: 0.002745  loss: 1.8883 (1.8883)  weight_decay: 0.0500 (0.0500)  time: 9.9500  data: 7.3896  max mem: 42573
Epoch: [126]  [ 10/312]  eta: 0:07:39  lr: 0.002744  min_lr: 0.002744  loss: 2.3914 (2.5351)  weight_decay: 0.0500 (0.0500)  time: 1.5210  data: 0.7037  max mem: 42573
Epoch: [126]  [ 20/312]  eta: 0:04:52  lr: 0.002744  min_lr: 0.002744  loss: 2.5538 (2.5351)  weight_decay: 0.0500 (0.0500)  time: 0.5556  data: 0.0178  max mem: 42573
Epoch: [126]  [ 30/312]  eta: 0:03:51  lr: 0.002743  min_lr: 0.002743  loss: 2.7235 (2.5419)  weight_decay: 0.0500 (0.0500)  time: 0.4331  data: 0.0004  max mem: 42573
Epoch: [126]  [ 40/312]  eta: 0:03:17  lr: 0.002742  min_lr: 0.002742  loss: 2.7553 (2.5298)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [126]  [ 50/312]  eta: 0:02:54  lr: 0.002742  min_lr: 0.002742  loss: 2.8017 (2.5873)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [126]  [ 60/312]  eta: 0:02:38  lr: 0.002741  min_lr: 0.002741  loss: 2.6810 (2.5743)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [126]  [ 70/312]  eta: 0:02:25  lr: 0.002740  min_lr: 0.002740  loss: 2.5656 (2.5556)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0005  max mem: 42573
Epoch: [126]  [ 80/312]  eta: 0:02:14  lr: 0.002740  min_lr: 0.002740  loss: 2.2939 (2.5173)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0006  max mem: 42573
Epoch: [126]  [ 90/312]  eta: 0:02:05  lr: 0.002739  min_lr: 0.002739  loss: 2.2939 (2.5158)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0005  max mem: 42573
Epoch: [126]  [100/312]  eta: 0:01:57  lr: 0.002738  min_lr: 0.002738  loss: 2.5985 (2.5173)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [126]  [110/312]  eta: 0:01:49  lr: 0.002738  min_lr: 0.002738  loss: 2.7950 (2.5361)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [126]  [120/312]  eta: 0:01:42  lr: 0.002737  min_lr: 0.002737  loss: 2.7950 (2.5317)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [126]  [130/312]  eta: 0:01:35  lr: 0.002736  min_lr: 0.002736  loss: 2.2560 (2.5039)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [126]  [140/312]  eta: 0:01:29  lr: 0.002736  min_lr: 0.002736  loss: 2.0413 (2.4809)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [126]  [150/312]  eta: 0:01:23  lr: 0.002735  min_lr: 0.002735  loss: 2.2139 (2.4766)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [126]  [160/312]  eta: 0:01:17  lr: 0.002734  min_lr: 0.002734  loss: 2.3382 (2.4719)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [126]  [170/312]  eta: 0:01:11  lr: 0.002734  min_lr: 0.002734  loss: 2.3506 (2.4674)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0005  max mem: 42573
Epoch: [126]  [180/312]  eta: 0:01:05  lr: 0.002733  min_lr: 0.002733  loss: 2.5949 (2.4796)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [126]  [190/312]  eta: 0:01:00  lr: 0.002732  min_lr: 0.002732  loss: 2.7168 (2.4923)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0003  max mem: 42573
Epoch: [126]  [200/312]  eta: 0:00:55  lr: 0.002732  min_lr: 0.002732  loss: 2.7640 (2.4995)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0003  max mem: 42573
Epoch: [126]  [210/312]  eta: 0:00:50  lr: 0.002731  min_lr: 0.002731  loss: 2.7147 (2.5093)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [126]  [220/312]  eta: 0:00:44  lr: 0.002730  min_lr: 0.002730  loss: 2.6774 (2.5176)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [126]  [230/312]  eta: 0:00:39  lr: 0.002730  min_lr: 0.002730  loss: 2.6774 (2.5193)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [126]  [240/312]  eta: 0:00:34  lr: 0.002729  min_lr: 0.002729  loss: 2.5410 (2.5158)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [126]  [250/312]  eta: 0:00:29  lr: 0.002728  min_lr: 0.002728  loss: 2.4496 (2.5123)  weight_decay: 0.0500 (0.0500)  time: 0.4346  data: 0.0004  max mem: 42573
Epoch: [126]  [260/312]  eta: 0:00:24  lr: 0.002728  min_lr: 0.002728  loss: 2.4504 (2.5130)  weight_decay: 0.0500 (0.0500)  time: 0.4345  data: 0.0004  max mem: 42573
Epoch: [126]  [270/312]  eta: 0:00:20  lr: 0.002727  min_lr: 0.002727  loss: 2.7020 (2.5257)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0003  max mem: 42573
Epoch: [126]  [280/312]  eta: 0:00:15  lr: 0.002726  min_lr: 0.002726  loss: 2.6710 (2.5187)  weight_decay: 0.0500 (0.0500)  time: 0.4345  data: 0.0009  max mem: 42573
Epoch: [126]  [290/312]  eta: 0:00:10  lr: 0.002726  min_lr: 0.002726  loss: 2.3396 (2.5181)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0008  max mem: 42573
Epoch: [126]  [300/312]  eta: 0:00:05  lr: 0.002725  min_lr: 0.002725  loss: 2.6075 (2.5252)  weight_decay: 0.0500 (0.0500)  time: 0.4324  data: 0.0001  max mem: 42573
Epoch: [126]  [310/312]  eta: 0:00:00  lr: 0.002724  min_lr: 0.002724  loss: 2.5664 (2.5233)  weight_decay: 0.0500 (0.0500)  time: 0.4322  data: 0.0001  max mem: 42573
Epoch: [126]  [311/312]  eta: 0:00:00  lr: 0.002724  min_lr: 0.002724  loss: 2.5430 (2.5222)  weight_decay: 0.0500 (0.0500)  time: 0.4323  data: 0.0001  max mem: 42573
Epoch: [126] Total time: 0:02:28 (0.4749 s / it)
Averaged stats: lr: 0.002724  min_lr: 0.002724  loss: 2.5430 (2.5388)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:00:46  loss: 0.9052 (0.9052)  acc1: 77.0833 (77.0833)  acc5: 93.4896 (93.4896)  time: 5.1600  data: 5.0511  max mem: 42573
Test:  [8/9]  eta: 0:00:00  loss: 1.2697 (1.1695)  acc1: 69.5312 (71.0720)  acc5: 88.8021 (90.0800)  time: 0.6509  data: 0.5613  max mem: 42573
Test: Total time: 0:00:05 (0.6605 s / it)
* Acc@1 70.928 Acc@5 90.012 loss 1.197
Accuracy of the model on the 50000 test images: 70.9%
Max accuracy: 72.09%
Epoch: [127]  [  0/312]  eta: 0:48:48  lr: 0.002724  min_lr: 0.002724  loss: 2.7710 (2.7710)  weight_decay: 0.0500 (0.0500)  time: 9.3876  data: 8.5874  max mem: 42573
Epoch: [127]  [ 10/312]  eta: 0:07:28  lr: 0.002723  min_lr: 0.002723  loss: 2.3923 (2.4163)  weight_decay: 0.0500 (0.0500)  time: 1.4835  data: 0.7811  max mem: 42573
Epoch: [127]  [ 20/312]  eta: 0:04:47  lr: 0.002723  min_lr: 0.002723  loss: 2.2049 (2.3427)  weight_decay: 0.0500 (0.0500)  time: 0.5631  data: 0.0004  max mem: 42573
Epoch: [127]  [ 30/312]  eta: 0:03:47  lr: 0.002722  min_lr: 0.002722  loss: 2.3238 (2.4089)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [127]  [ 40/312]  eta: 0:03:14  lr: 0.002721  min_lr: 0.002721  loss: 2.6176 (2.4334)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0003  max mem: 42573
Epoch: [127]  [ 50/312]  eta: 0:02:52  lr: 0.002721  min_lr: 0.002721  loss: 2.7815 (2.5056)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [127]  [ 60/312]  eta: 0:02:36  lr: 0.002720  min_lr: 0.002720  loss: 2.7089 (2.4922)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [127]  [ 70/312]  eta: 0:02:24  lr: 0.002719  min_lr: 0.002719  loss: 2.5975 (2.5179)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [127]  [ 80/312]  eta: 0:02:13  lr: 0.002719  min_lr: 0.002719  loss: 2.6673 (2.5379)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [127]  [ 90/312]  eta: 0:02:04  lr: 0.002718  min_lr: 0.002718  loss: 2.7001 (2.5484)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [127]  [100/312]  eta: 0:01:56  lr: 0.002717  min_lr: 0.002717  loss: 2.5944 (2.5330)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0004  max mem: 42573
Epoch: [127]  [110/312]  eta: 0:01:48  lr: 0.002717  min_lr: 0.002717  loss: 2.6179 (2.5496)  weight_decay: 0.0500 (0.0500)  time: 0.4341  data: 0.0003  max mem: 42573
Epoch: [127]  [120/312]  eta: 0:01:41  lr: 0.002716  min_lr: 0.002716  loss: 2.7391 (2.5531)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0003  max mem: 42573
Epoch: [127]  [130/312]  eta: 0:01:34  lr: 0.002715  min_lr: 0.002715  loss: 2.5631 (2.5460)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [127]  [140/312]  eta: 0:01:28  lr: 0.002715  min_lr: 0.002715  loss: 2.4596 (2.5376)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [127]  [150/312]  eta: 0:01:22  lr: 0.002714  min_lr: 0.002714  loss: 2.3356 (2.5274)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0004  max mem: 42573
Epoch: [127]  [160/312]  eta: 0:01:16  lr: 0.002713  min_lr: 0.002713  loss: 2.4946 (2.5237)  weight_decay: 0.0500 (0.0500)  time: 0.4341  data: 0.0004  max mem: 42573
Epoch: [127]  [170/312]  eta: 0:01:11  lr: 0.002713  min_lr: 0.002713  loss: 2.4636 (2.5191)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0003  max mem: 42573
Epoch: [127]  [180/312]  eta: 0:01:05  lr: 0.002712  min_lr: 0.002712  loss: 2.4748 (2.5350)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [127]  [190/312]  eta: 0:01:00  lr: 0.002711  min_lr: 0.002711  loss: 2.4748 (2.5329)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [127]  [200/312]  eta: 0:00:55  lr: 0.002711  min_lr: 0.002711  loss: 2.5703 (2.5393)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [127]  [210/312]  eta: 0:00:49  lr: 0.002710  min_lr: 0.002710  loss: 2.6740 (2.5379)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0003  max mem: 42573
Epoch: [127]  [220/312]  eta: 0:00:44  lr: 0.002709  min_lr: 0.002709  loss: 2.6028 (2.5396)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [127]  [230/312]  eta: 0:00:39  lr: 0.002709  min_lr: 0.002709  loss: 2.5517 (2.5377)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [127]  [240/312]  eta: 0:00:34  lr: 0.002708  min_lr: 0.002708  loss: 2.5496 (2.5352)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [127]  [250/312]  eta: 0:00:29  lr: 0.002707  min_lr: 0.002707  loss: 2.5985 (2.5315)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0003  max mem: 42573
Epoch: [127]  [260/312]  eta: 0:00:24  lr: 0.002707  min_lr: 0.002707  loss: 2.6361 (2.5356)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0003  max mem: 42573
Epoch: [127]  [270/312]  eta: 0:00:20  lr: 0.002706  min_lr: 0.002706  loss: 2.6651 (2.5335)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [127]  [280/312]  eta: 0:00:15  lr: 0.002705  min_lr: 0.002705  loss: 2.5495 (2.5332)  weight_decay: 0.0500 (0.0500)  time: 0.4346  data: 0.0009  max mem: 42573
Epoch: [127]  [290/312]  eta: 0:00:10  lr: 0.002705  min_lr: 0.002705  loss: 2.4270 (2.5295)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0008  max mem: 42573
Epoch: [127]  [300/312]  eta: 0:00:05  lr: 0.002704  min_lr: 0.002704  loss: 2.3396 (2.5265)  weight_decay: 0.0500 (0.0500)  time: 0.4323  data: 0.0001  max mem: 42573
Epoch: [127]  [310/312]  eta: 0:00:00  lr: 0.002703  min_lr: 0.002703  loss: 2.5128 (2.5287)  weight_decay: 0.0500 (0.0500)  time: 0.4323  data: 0.0001  max mem: 42573
Epoch: [127]  [311/312]  eta: 0:00:00  lr: 0.002703  min_lr: 0.002703  loss: 2.5128 (2.5270)  weight_decay: 0.0500 (0.0500)  time: 0.4323  data: 0.0001  max mem: 42573
Epoch: [127] Total time: 0:02:27 (0.4736 s / it)
Averaged stats: lr: 0.002703  min_lr: 0.002703  loss: 2.5128 (2.5472)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:00:45  loss: 0.8977 (0.8977)  acc1: 78.1250 (78.1250)  acc5: 92.4479 (92.4479)  time: 5.0882  data: 4.9788  max mem: 42573
Test:  [8/9]  eta: 0:00:00  loss: 1.2628 (1.1787)  acc1: 68.7500 (70.0800)  acc5: 90.3646 (89.6960)  time: 0.6408  data: 0.5533  max mem: 42573
Test: Total time: 0:00:05 (0.6502 s / it)
* Acc@1 70.844 Acc@5 89.866 loss 1.187
Accuracy of the model on the 50000 test images: 70.8%
Max accuracy: 72.09%
Epoch: [128]  [  0/312]  eta: 0:50:27  lr: 0.002703  min_lr: 0.002703  loss: 2.3396 (2.3396)  weight_decay: 0.0500 (0.0500)  time: 9.7026  data: 8.0195  max mem: 42573
Epoch: [128]  [ 10/312]  eta: 0:07:07  lr: 0.002702  min_lr: 0.002702  loss: 2.4769 (2.5965)  weight_decay: 0.0500 (0.0500)  time: 1.4166  data: 0.7294  max mem: 42573
Epoch: [128]  [ 20/312]  eta: 0:04:36  lr: 0.002702  min_lr: 0.002702  loss: 2.3145 (2.4409)  weight_decay: 0.0500 (0.0500)  time: 0.5108  data: 0.0004  max mem: 42573
Epoch: [128]  [ 30/312]  eta: 0:03:40  lr: 0.002701  min_lr: 0.002701  loss: 2.1874 (2.4325)  weight_decay: 0.0500 (0.0500)  time: 0.4332  data: 0.0004  max mem: 42573
Epoch: [128]  [ 40/312]  eta: 0:03:09  lr: 0.002700  min_lr: 0.002700  loss: 2.6791 (2.4974)  weight_decay: 0.0500 (0.0500)  time: 0.4330  data: 0.0004  max mem: 42573
Epoch: [128]  [ 50/312]  eta: 0:02:49  lr: 0.002700  min_lr: 0.002700  loss: 2.6950 (2.5096)  weight_decay: 0.0500 (0.0500)  time: 0.4331  data: 0.0004  max mem: 42573
Epoch: [128]  [ 60/312]  eta: 0:02:33  lr: 0.002699  min_lr: 0.002699  loss: 2.5311 (2.4968)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [128]  [ 70/312]  eta: 0:02:21  lr: 0.002698  min_lr: 0.002698  loss: 2.5830 (2.5091)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [128]  [ 80/312]  eta: 0:02:11  lr: 0.002698  min_lr: 0.002698  loss: 2.6951 (2.5056)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [128]  [ 90/312]  eta: 0:02:02  lr: 0.002697  min_lr: 0.002697  loss: 2.7780 (2.5355)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [128]  [100/312]  eta: 0:01:54  lr: 0.002696  min_lr: 0.002696  loss: 2.7780 (2.5348)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [128]  [110/312]  eta: 0:01:47  lr: 0.002696  min_lr: 0.002696  loss: 2.6253 (2.5407)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [128]  [120/312]  eta: 0:01:40  lr: 0.002695  min_lr: 0.002695  loss: 2.5973 (2.5384)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [128]  [130/312]  eta: 0:01:33  lr: 0.002694  min_lr: 0.002694  loss: 2.5628 (2.5338)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [128]  [140/312]  eta: 0:01:27  lr: 0.002694  min_lr: 0.002694  loss: 2.5310 (2.5366)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [128]  [150/312]  eta: 0:01:21  lr: 0.002693  min_lr: 0.002693  loss: 2.5111 (2.5348)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [128]  [160/312]  eta: 0:01:16  lr: 0.002692  min_lr: 0.002692  loss: 2.4766 (2.5370)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [128]  [170/312]  eta: 0:01:10  lr: 0.002692  min_lr: 0.002692  loss: 2.6604 (2.5443)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [128]  [180/312]  eta: 0:01:05  lr: 0.002691  min_lr: 0.002691  loss: 2.6175 (2.5360)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [128]  [190/312]  eta: 0:00:59  lr: 0.002690  min_lr: 0.002690  loss: 2.6175 (2.5412)  weight_decay: 0.0500 (0.0500)  time: 0.4387  data: 0.0004  max mem: 42573
Epoch: [128]  [200/312]  eta: 0:00:54  lr: 0.002690  min_lr: 0.002690  loss: 2.7470 (2.5427)  weight_decay: 0.0500 (0.0500)  time: 0.4386  data: 0.0004  max mem: 42573
Epoch: [128]  [210/312]  eta: 0:00:49  lr: 0.002689  min_lr: 0.002689  loss: 2.7788 (2.5551)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0003  max mem: 42573
Epoch: [128]  [220/312]  eta: 0:00:44  lr: 0.002688  min_lr: 0.002688  loss: 2.6858 (2.5526)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0003  max mem: 42573
Epoch: [128]  [230/312]  eta: 0:00:39  lr: 0.002688  min_lr: 0.002688  loss: 2.4727 (2.5456)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0003  max mem: 42573
Epoch: [128]  [240/312]  eta: 0:00:34  lr: 0.002687  min_lr: 0.002687  loss: 2.4058 (2.5377)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [128]  [250/312]  eta: 0:00:29  lr: 0.002686  min_lr: 0.002686  loss: 2.4910 (2.5336)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [128]  [260/312]  eta: 0:00:24  lr: 0.002686  min_lr: 0.002686  loss: 2.5638 (2.5349)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [128]  [270/312]  eta: 0:00:19  lr: 0.002685  min_lr: 0.002685  loss: 2.7307 (2.5426)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0003  max mem: 42573
Epoch: [128]  [280/312]  eta: 0:00:15  lr: 0.002684  min_lr: 0.002684  loss: 2.7396 (2.5470)  weight_decay: 0.0500 (0.0500)  time: 0.4343  data: 0.0009  max mem: 42573
Epoch: [128]  [290/312]  eta: 0:00:10  lr: 0.002684  min_lr: 0.002684  loss: 2.6334 (2.5476)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0008  max mem: 42573
Epoch: [128]  [300/312]  eta: 0:00:05  lr: 0.002683  min_lr: 0.002683  loss: 2.5717 (2.5433)  weight_decay: 0.0500 (0.0500)  time: 0.4325  data: 0.0001  max mem: 42573
Epoch: [128]  [310/312]  eta: 0:00:00  lr: 0.002682  min_lr: 0.002682  loss: 2.6111 (2.5471)  weight_decay: 0.0500 (0.0500)  time: 0.4324  data: 0.0001  max mem: 42573
Epoch: [128]  [311/312]  eta: 0:00:00  lr: 0.002682  min_lr: 0.002682  loss: 2.6253 (2.5479)  weight_decay: 0.0500 (0.0500)  time: 0.4324  data: 0.0001  max mem: 42573
Epoch: [128] Total time: 0:02:27 (0.4717 s / it)
Averaged stats: lr: 0.002682  min_lr: 0.002682  loss: 2.6253 (2.5355)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:00:45  loss: 1.0054 (1.0054)  acc1: 76.0417 (76.0417)  acc5: 93.2292 (93.2292)  time: 5.0047  data: 4.8952  max mem: 42573
Test:  [8/9]  eta: 0:00:00  loss: 1.3206 (1.2069)  acc1: 70.3125 (69.9840)  acc5: 91.4062 (90.1440)  time: 0.6316  data: 0.5440  max mem: 42573
Test: Total time: 0:00:05 (0.6422 s / it)
* Acc@1 70.958 Acc@5 89.932 loss 1.199
Accuracy of the model on the 50000 test images: 71.0%
Max accuracy: 72.09%
Epoch: [129]  [  0/312]  eta: 0:46:17  lr: 0.002682  min_lr: 0.002682  loss: 2.5783 (2.5783)  weight_decay: 0.0500 (0.0500)  time: 8.9024  data: 8.0123  max mem: 42573
Epoch: [129]  [ 10/312]  eta: 0:06:48  lr: 0.002681  min_lr: 0.002681  loss: 2.5783 (2.5374)  weight_decay: 0.0500 (0.0500)  time: 1.3521  data: 0.7289  max mem: 42573
Epoch: [129]  [ 20/312]  eta: 0:04:27  lr: 0.002681  min_lr: 0.002681  loss: 2.6721 (2.5813)  weight_decay: 0.0500 (0.0500)  time: 0.5175  data: 0.0005  max mem: 42573
Epoch: [129]  [ 30/312]  eta: 0:03:34  lr: 0.002680  min_lr: 0.002680  loss: 2.7274 (2.5668)  weight_decay: 0.0500 (0.0500)  time: 0.4356  data: 0.0003  max mem: 42573
Epoch: [129]  [ 40/312]  eta: 0:03:05  lr: 0.002679  min_lr: 0.002679  loss: 2.5837 (2.5290)  weight_decay: 0.0500 (0.0500)  time: 0.4332  data: 0.0003  max mem: 42573
Epoch: [129]  [ 50/312]  eta: 0:02:45  lr: 0.002679  min_lr: 0.002679  loss: 2.5957 (2.5432)  weight_decay: 0.0500 (0.0500)  time: 0.4332  data: 0.0004  max mem: 42573
Epoch: [129]  [ 60/312]  eta: 0:02:31  lr: 0.002678  min_lr: 0.002678  loss: 2.7011 (2.5534)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [129]  [ 70/312]  eta: 0:02:19  lr: 0.002677  min_lr: 0.002677  loss: 2.6855 (2.5572)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [129]  [ 80/312]  eta: 0:02:09  lr: 0.002677  min_lr: 0.002677  loss: 2.5155 (2.5458)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [129]  [ 90/312]  eta: 0:02:00  lr: 0.002676  min_lr: 0.002676  loss: 2.5836 (2.5403)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [129]  [100/312]  eta: 0:01:53  lr: 0.002675  min_lr: 0.002675  loss: 2.7323 (2.5586)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [129]  [110/312]  eta: 0:01:46  lr: 0.002675  min_lr: 0.002675  loss: 2.7736 (2.5601)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [129]  [120/312]  eta: 0:01:39  lr: 0.002674  min_lr: 0.002674  loss: 2.6382 (2.5561)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [129]  [130/312]  eta: 0:01:32  lr: 0.002673  min_lr: 0.002673  loss: 2.6091 (2.5560)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [129]  [140/312]  eta: 0:01:26  lr: 0.002673  min_lr: 0.002673  loss: 2.6119 (2.5493)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [129]  [150/312]  eta: 0:01:21  lr: 0.002672  min_lr: 0.002672  loss: 2.5013 (2.5485)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [129]  [160/312]  eta: 0:01:15  lr: 0.002671  min_lr: 0.002671  loss: 2.4763 (2.5344)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0003  max mem: 42573
Epoch: [129]  [170/312]  eta: 0:01:09  lr: 0.002671  min_lr: 0.002671  loss: 2.4395 (2.5274)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [129]  [180/312]  eta: 0:01:04  lr: 0.002670  min_lr: 0.002670  loss: 2.4965 (2.5243)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [129]  [190/312]  eta: 0:00:59  lr: 0.002669  min_lr: 0.002669  loss: 2.6433 (2.5391)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [129]  [200/312]  eta: 0:00:54  lr: 0.002668  min_lr: 0.002668  loss: 2.6419 (2.5349)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [129]  [210/312]  eta: 0:00:49  lr: 0.002668  min_lr: 0.002668  loss: 2.6027 (2.5356)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [129]  [220/312]  eta: 0:00:44  lr: 0.002667  min_lr: 0.002667  loss: 2.5819 (2.5264)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [129]  [230/312]  eta: 0:00:39  lr: 0.002666  min_lr: 0.002666  loss: 2.5191 (2.5279)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [129]  [240/312]  eta: 0:00:34  lr: 0.002666  min_lr: 0.002666  loss: 2.5191 (2.5268)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0003  max mem: 42573
Epoch: [129]  [250/312]  eta: 0:00:29  lr: 0.002665  min_lr: 0.002665  loss: 2.6229 (2.5339)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0003  max mem: 42573
Epoch: [129]  [260/312]  eta: 0:00:24  lr: 0.002664  min_lr: 0.002664  loss: 2.5793 (2.5258)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0003  max mem: 42573
Epoch: [129]  [270/312]  eta: 0:00:19  lr: 0.002664  min_lr: 0.002664  loss: 2.2619 (2.5222)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0003  max mem: 42573
Epoch: [129]  [280/312]  eta: 0:00:15  lr: 0.002663  min_lr: 0.002663  loss: 2.3034 (2.5214)  weight_decay: 0.0500 (0.0500)  time: 0.4343  data: 0.0011  max mem: 42573
Epoch: [129]  [290/312]  eta: 0:00:10  lr: 0.002662  min_lr: 0.002662  loss: 2.5701 (2.5209)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0010  max mem: 42573
Epoch: [129]  [300/312]  eta: 0:00:05  lr: 0.002662  min_lr: 0.002662  loss: 2.5056 (2.5224)  weight_decay: 0.0500 (0.0500)  time: 0.4323  data: 0.0001  max mem: 42573
Epoch: [129]  [310/312]  eta: 0:00:00  lr: 0.002661  min_lr: 0.002661  loss: 2.5056 (2.5197)  weight_decay: 0.0500 (0.0500)  time: 0.4322  data: 0.0001  max mem: 42573
Epoch: [129]  [311/312]  eta: 0:00:00  lr: 0.002661  min_lr: 0.002661  loss: 2.5056 (2.5175)  weight_decay: 0.0500 (0.0500)  time: 0.4322  data: 0.0001  max mem: 42573
Epoch: [129] Total time: 0:02:26 (0.4690 s / it)
Averaged stats: lr: 0.002661  min_lr: 0.002661  loss: 2.5056 (2.5259)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:00:48  loss: 0.8660 (0.8660)  acc1: 78.6458 (78.6458)  acc5: 93.4896 (93.4896)  time: 5.3585  data: 5.2491  max mem: 42573
Test:  [8/9]  eta: 0:00:00  loss: 1.1643 (1.1247)  acc1: 71.3542 (70.6880)  acc5: 91.9271 (91.1360)  time: 0.6788  data: 0.5904  max mem: 42573
Test: Total time: 0:00:06 (0.6861 s / it)
* Acc@1 72.076 Acc@5 90.678 loss 1.118
Accuracy of the model on the 50000 test images: 72.1%
Max accuracy: 72.09%
Epoch: [130]  [  0/312]  eta: 0:49:23  lr: 0.002661  min_lr: 0.002661  loss: 2.7554 (2.7554)  weight_decay: 0.0500 (0.0500)  time: 9.4981  data: 7.5379  max mem: 42573
Epoch: [130]  [ 10/312]  eta: 0:06:41  lr: 0.002660  min_lr: 0.002660  loss: 2.8841 (2.7864)  weight_decay: 0.0500 (0.0500)  time: 1.3287  data: 0.6856  max mem: 42573
Epoch: [130]  [ 20/312]  eta: 0:04:23  lr: 0.002660  min_lr: 0.002660  loss: 2.7389 (2.6624)  weight_decay: 0.0500 (0.0500)  time: 0.4742  data: 0.0004  max mem: 42573
Epoch: [130]  [ 30/312]  eta: 0:03:32  lr: 0.002659  min_lr: 0.002659  loss: 2.4930 (2.5950)  weight_decay: 0.0500 (0.0500)  time: 0.4352  data: 0.0004  max mem: 42573
Epoch: [130]  [ 40/312]  eta: 0:03:03  lr: 0.002658  min_lr: 0.002658  loss: 2.4930 (2.5436)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [130]  [ 50/312]  eta: 0:02:44  lr: 0.002657  min_lr: 0.002657  loss: 2.6317 (2.5652)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [130]  [ 60/312]  eta: 0:02:30  lr: 0.002657  min_lr: 0.002657  loss: 2.6082 (2.5812)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [130]  [ 70/312]  eta: 0:02:18  lr: 0.002656  min_lr: 0.002656  loss: 2.6188 (2.5692)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [130]  [ 80/312]  eta: 0:02:08  lr: 0.002655  min_lr: 0.002655  loss: 2.3330 (2.5579)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [130]  [ 90/312]  eta: 0:02:00  lr: 0.002655  min_lr: 0.002655  loss: 2.2102 (2.5221)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0003  max mem: 42573
Epoch: [130]  [100/312]  eta: 0:01:52  lr: 0.002654  min_lr: 0.002654  loss: 2.2169 (2.5187)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [130]  [110/312]  eta: 0:01:45  lr: 0.002653  min_lr: 0.002653  loss: 2.3141 (2.5060)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [130]  [120/312]  eta: 0:01:38  lr: 0.002653  min_lr: 0.002653  loss: 2.3259 (2.5050)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [130]  [130/312]  eta: 0:01:32  lr: 0.002652  min_lr: 0.002652  loss: 2.6041 (2.5158)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [130]  [140/312]  eta: 0:01:26  lr: 0.002651  min_lr: 0.002651  loss: 2.7172 (2.5207)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [130]  [150/312]  eta: 0:01:20  lr: 0.002651  min_lr: 0.002651  loss: 2.6706 (2.5154)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [130]  [160/312]  eta: 0:01:15  lr: 0.002650  min_lr: 0.002650  loss: 2.6966 (2.5246)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [130]  [170/312]  eta: 0:01:09  lr: 0.002649  min_lr: 0.002649  loss: 2.6966 (2.5174)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0003  max mem: 42573
Epoch: [130]  [180/312]  eta: 0:01:04  lr: 0.002649  min_lr: 0.002649  loss: 2.6142 (2.5204)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [130]  [190/312]  eta: 0:00:59  lr: 0.002648  min_lr: 0.002648  loss: 2.6084 (2.5115)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [130]  [200/312]  eta: 0:00:54  lr: 0.002647  min_lr: 0.002647  loss: 2.3435 (2.5090)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0003  max mem: 42573
Epoch: [130]  [210/312]  eta: 0:00:49  lr: 0.002647  min_lr: 0.002647  loss: 2.6548 (2.5194)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0003  max mem: 42573
Epoch: [130]  [220/312]  eta: 0:00:44  lr: 0.002646  min_lr: 0.002646  loss: 2.6552 (2.5184)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0003  max mem: 42573
Epoch: [130]  [230/312]  eta: 0:00:39  lr: 0.002645  min_lr: 0.002645  loss: 2.5094 (2.5149)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0003  max mem: 42573
Epoch: [130]  [240/312]  eta: 0:00:34  lr: 0.002645  min_lr: 0.002645  loss: 2.5075 (2.5162)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [130]  [250/312]  eta: 0:00:29  lr: 0.002644  min_lr: 0.002644  loss: 2.3106 (2.5133)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [130]  [260/312]  eta: 0:00:24  lr: 0.002643  min_lr: 0.002643  loss: 2.3106 (2.5154)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0003  max mem: 42573
Epoch: [130]  [270/312]  eta: 0:00:19  lr: 0.002643  min_lr: 0.002643  loss: 2.5107 (2.5168)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [130]  [280/312]  eta: 0:00:15  lr: 0.002642  min_lr: 0.002642  loss: 2.5107 (2.5139)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0009  max mem: 42573
Epoch: [130]  [290/312]  eta: 0:00:10  lr: 0.002641  min_lr: 0.002641  loss: 2.5247 (2.5155)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0008  max mem: 42573
Epoch: [130]  [300/312]  eta: 0:00:05  lr: 0.002640  min_lr: 0.002640  loss: 2.4689 (2.5111)  weight_decay: 0.0500 (0.0500)  time: 0.4324  data: 0.0001  max mem: 42573
Epoch: [130]  [310/312]  eta: 0:00:00  lr: 0.002640  min_lr: 0.002640  loss: 2.3866 (2.5069)  weight_decay: 0.0500 (0.0500)  time: 0.4323  data: 0.0001  max mem: 42573
Epoch: [130]  [311/312]  eta: 0:00:00  lr: 0.002640  min_lr: 0.002640  loss: 2.3866 (2.5079)  weight_decay: 0.0500 (0.0500)  time: 0.4323  data: 0.0001  max mem: 42573
Epoch: [130] Total time: 0:02:26 (0.4683 s / it)
Averaged stats: lr: 0.002640  min_lr: 0.002640  loss: 2.3866 (2.5302)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:00:44  loss: 1.0176 (1.0176)  acc1: 75.2604 (75.2604)  acc5: 92.1875 (92.1875)  time: 4.9957  data: 4.8862  max mem: 42573
Test:  [8/9]  eta: 0:00:00  loss: 1.2031 (1.2046)  acc1: 70.3125 (70.1760)  acc5: 90.1042 (88.8640)  time: 0.6317  data: 0.5430  max mem: 42573
Test: Total time: 0:00:05 (0.6389 s / it)
* Acc@1 70.498 Acc@5 89.570 loss 1.212
Accuracy of the model on the 50000 test images: 70.5%
Max accuracy: 72.09%
Epoch: [131]  [  0/312]  eta: 0:47:40  lr: 0.002640  min_lr: 0.002640  loss: 2.5524 (2.5524)  weight_decay: 0.0500 (0.0500)  time: 9.1692  data: 6.7001  max mem: 42573
Epoch: [131]  [ 10/312]  eta: 0:07:06  lr: 0.002639  min_lr: 0.002639  loss: 2.5524 (2.5526)  weight_decay: 0.0500 (0.0500)  time: 1.4138  data: 0.6096  max mem: 42573
Epoch: [131]  [ 20/312]  eta: 0:04:36  lr: 0.002638  min_lr: 0.002638  loss: 2.6350 (2.6359)  weight_decay: 0.0500 (0.0500)  time: 0.5357  data: 0.0004  max mem: 42573
Epoch: [131]  [ 30/312]  eta: 0:03:40  lr: 0.002638  min_lr: 0.002638  loss: 2.6075 (2.6204)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [131]  [ 40/312]  eta: 0:03:09  lr: 0.002637  min_lr: 0.002637  loss: 2.7546 (2.6755)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [131]  [ 50/312]  eta: 0:02:48  lr: 0.002636  min_lr: 0.002636  loss: 2.8267 (2.6672)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [131]  [ 60/312]  eta: 0:02:33  lr: 0.002636  min_lr: 0.002636  loss: 2.6344 (2.6688)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [131]  [ 70/312]  eta: 0:02:21  lr: 0.002635  min_lr: 0.002635  loss: 2.6286 (2.6418)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [131]  [ 80/312]  eta: 0:02:11  lr: 0.002634  min_lr: 0.002634  loss: 2.4064 (2.6216)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [131]  [ 90/312]  eta: 0:02:02  lr: 0.002634  min_lr: 0.002634  loss: 2.4805 (2.5935)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [131]  [100/312]  eta: 0:01:54  lr: 0.002633  min_lr: 0.002633  loss: 2.4370 (2.5714)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [131]  [110/312]  eta: 0:01:47  lr: 0.002632  min_lr: 0.002632  loss: 2.4370 (2.5592)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [131]  [120/312]  eta: 0:01:40  lr: 0.002631  min_lr: 0.002631  loss: 2.4875 (2.5552)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [131]  [130/312]  eta: 0:01:33  lr: 0.002631  min_lr: 0.002631  loss: 2.4875 (2.5584)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [131]  [140/312]  eta: 0:01:27  lr: 0.002630  min_lr: 0.002630  loss: 2.7618 (2.5671)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [131]  [150/312]  eta: 0:01:21  lr: 0.002629  min_lr: 0.002629  loss: 2.7618 (2.5633)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [131]  [160/312]  eta: 0:01:16  lr: 0.002629  min_lr: 0.002629  loss: 2.3740 (2.5464)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [131]  [170/312]  eta: 0:01:10  lr: 0.002628  min_lr: 0.002628  loss: 2.3740 (2.5419)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [131]  [180/312]  eta: 0:01:05  lr: 0.002627  min_lr: 0.002627  loss: 2.4013 (2.5418)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [131]  [190/312]  eta: 0:00:59  lr: 0.002627  min_lr: 0.002627  loss: 2.4013 (2.5346)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [131]  [200/312]  eta: 0:00:54  lr: 0.002626  min_lr: 0.002626  loss: 2.5070 (2.5368)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [131]  [210/312]  eta: 0:00:49  lr: 0.002625  min_lr: 0.002625  loss: 2.6601 (2.5445)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [131]  [220/312]  eta: 0:00:44  lr: 0.002625  min_lr: 0.002625  loss: 2.7597 (2.5535)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [131]  [230/312]  eta: 0:00:39  lr: 0.002624  min_lr: 0.002624  loss: 2.6564 (2.5548)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [131]  [240/312]  eta: 0:00:34  lr: 0.002623  min_lr: 0.002623  loss: 2.5851 (2.5619)  weight_decay: 0.0500 (0.0500)  time: 0.4387  data: 0.0004  max mem: 42573
Epoch: [131]  [250/312]  eta: 0:00:29  lr: 0.002623  min_lr: 0.002623  loss: 2.5851 (2.5586)  weight_decay: 0.0500 (0.0500)  time: 0.4388  data: 0.0004  max mem: 42573
Epoch: [131]  [260/312]  eta: 0:00:24  lr: 0.002622  min_lr: 0.002622  loss: 2.5608 (2.5592)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0003  max mem: 42573
Epoch: [131]  [270/312]  eta: 0:00:19  lr: 0.002621  min_lr: 0.002621  loss: 2.6764 (2.5618)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0003  max mem: 42573
Epoch: [131]  [280/312]  eta: 0:00:15  lr: 0.002621  min_lr: 0.002621  loss: 2.6792 (2.5632)  weight_decay: 0.0500 (0.0500)  time: 0.4342  data: 0.0009  max mem: 42573
Epoch: [131]  [290/312]  eta: 0:00:10  lr: 0.002620  min_lr: 0.002620  loss: 2.5637 (2.5600)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0008  max mem: 42573
Epoch: [131]  [300/312]  eta: 0:00:05  lr: 0.002619  min_lr: 0.002619  loss: 2.3060 (2.5532)  weight_decay: 0.0500 (0.0500)  time: 0.4323  data: 0.0001  max mem: 42573
Epoch: [131]  [310/312]  eta: 0:00:00  lr: 0.002619  min_lr: 0.002619  loss: 2.2749 (2.5472)  weight_decay: 0.0500 (0.0500)  time: 0.4323  data: 0.0001  max mem: 42573
Epoch: [131]  [311/312]  eta: 0:00:00  lr: 0.002618  min_lr: 0.002618  loss: 2.2749 (2.5458)  weight_decay: 0.0500 (0.0500)  time: 0.4323  data: 0.0001  max mem: 42573
Epoch: [131] Total time: 0:02:27 (0.4713 s / it)
Averaged stats: lr: 0.002618  min_lr: 0.002618  loss: 2.2749 (2.5296)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:00:43  loss: 0.9433 (0.9433)  acc1: 77.3438 (77.3438)  acc5: 91.9271 (91.9271)  time: 4.7788  data: 4.6706  max mem: 42573
Test:  [8/9]  eta: 0:00:00  loss: 1.2445 (1.1756)  acc1: 70.5729 (70.4960)  acc5: 89.8438 (90.1440)  time: 0.6126  data: 0.5190  max mem: 42573
Test: Total time: 0:00:05 (0.6309 s / it)
* Acc@1 71.452 Acc@5 90.410 loss 1.169
Accuracy of the model on the 50000 test images: 71.5%
Max accuracy: 72.09%
Epoch: [132]  [  0/312]  eta: 0:52:03  lr: 0.002618  min_lr: 0.002618  loss: 2.1825 (2.1825)  weight_decay: 0.0500 (0.0500)  time: 10.0108  data: 8.3341  max mem: 42573
Epoch: [132]  [ 10/312]  eta: 0:07:01  lr: 0.002618  min_lr: 0.002618  loss: 2.7503 (2.6735)  weight_decay: 0.0500 (0.0500)  time: 1.3958  data: 0.7580  max mem: 42573
Epoch: [132]  [ 20/312]  eta: 0:04:33  lr: 0.002617  min_lr: 0.002617  loss: 2.7089 (2.6413)  weight_decay: 0.0500 (0.0500)  time: 0.4840  data: 0.0004  max mem: 42573
Epoch: [132]  [ 30/312]  eta: 0:03:38  lr: 0.002616  min_lr: 0.002616  loss: 2.5321 (2.5693)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0003  max mem: 42573
Epoch: [132]  [ 40/312]  eta: 0:03:08  lr: 0.002616  min_lr: 0.002616  loss: 2.5321 (2.5404)  weight_decay: 0.0500 (0.0500)  time: 0.4365  data: 0.0003  max mem: 42573
Epoch: [132]  [ 50/312]  eta: 0:02:48  lr: 0.002615  min_lr: 0.002615  loss: 2.6025 (2.5227)  weight_decay: 0.0500 (0.0500)  time: 0.4365  data: 0.0004  max mem: 42573
Epoch: [132]  [ 60/312]  eta: 0:02:33  lr: 0.002614  min_lr: 0.002614  loss: 2.5808 (2.5237)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [132]  [ 70/312]  eta: 0:02:21  lr: 0.002614  min_lr: 0.002614  loss: 2.4991 (2.5033)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [132]  [ 80/312]  eta: 0:02:11  lr: 0.002613  min_lr: 0.002613  loss: 2.4262 (2.4976)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [132]  [ 90/312]  eta: 0:02:02  lr: 0.002612  min_lr: 0.002612  loss: 2.6331 (2.5035)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0003  max mem: 42573
Epoch: [132]  [100/312]  eta: 0:01:54  lr: 0.002612  min_lr: 0.002612  loss: 2.5401 (2.4981)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [132]  [110/312]  eta: 0:01:46  lr: 0.002611  min_lr: 0.002611  loss: 2.5419 (2.5153)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [132]  [120/312]  eta: 0:01:40  lr: 0.002610  min_lr: 0.002610  loss: 2.5324 (2.5044)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [132]  [130/312]  eta: 0:01:33  lr: 0.002609  min_lr: 0.002609  loss: 2.3028 (2.4875)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [132]  [140/312]  eta: 0:01:27  lr: 0.002609  min_lr: 0.002609  loss: 2.3716 (2.4836)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [132]  [150/312]  eta: 0:01:21  lr: 0.002608  min_lr: 0.002608  loss: 2.4845 (2.4837)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [132]  [160/312]  eta: 0:01:15  lr: 0.002607  min_lr: 0.002607  loss: 2.6164 (2.4962)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [132]  [170/312]  eta: 0:01:10  lr: 0.002607  min_lr: 0.002607  loss: 2.6760 (2.5028)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [132]  [180/312]  eta: 0:01:05  lr: 0.002606  min_lr: 0.002606  loss: 2.4511 (2.4983)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [132]  [190/312]  eta: 0:00:59  lr: 0.002605  min_lr: 0.002605  loss: 2.6360 (2.5030)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [132]  [200/312]  eta: 0:00:54  lr: 0.002605  min_lr: 0.002605  loss: 2.5430 (2.4975)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [132]  [210/312]  eta: 0:00:49  lr: 0.002604  min_lr: 0.002604  loss: 2.3632 (2.4920)  weight_decay: 0.0500 (0.0500)  time: 0.4378  data: 0.0004  max mem: 42573
Epoch: [132]  [220/312]  eta: 0:00:44  lr: 0.002603  min_lr: 0.002603  loss: 2.3632 (2.4909)  weight_decay: 0.0500 (0.0500)  time: 0.4377  data: 0.0004  max mem: 42573
Epoch: [132]  [230/312]  eta: 0:00:39  lr: 0.002603  min_lr: 0.002603  loss: 2.4879 (2.4898)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [132]  [240/312]  eta: 0:00:34  lr: 0.002602  min_lr: 0.002602  loss: 2.4841 (2.4877)  weight_decay: 0.0500 (0.0500)  time: 0.4343  data: 0.0003  max mem: 42573
Epoch: [132]  [250/312]  eta: 0:00:29  lr: 0.002601  min_lr: 0.002601  loss: 2.5016 (2.4916)  weight_decay: 0.0500 (0.0500)  time: 0.4343  data: 0.0004  max mem: 42573
Epoch: [132]  [260/312]  eta: 0:00:24  lr: 0.002601  min_lr: 0.002601  loss: 2.5259 (2.4920)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [132]  [270/312]  eta: 0:00:19  lr: 0.002600  min_lr: 0.002600  loss: 2.4318 (2.4866)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [132]  [280/312]  eta: 0:00:15  lr: 0.002599  min_lr: 0.002599  loss: 2.2516 (2.4794)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0009  max mem: 42573
Epoch: [132]  [290/312]  eta: 0:00:10  lr: 0.002599  min_lr: 0.002599  loss: 2.3268 (2.4754)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0008  max mem: 42573
Epoch: [132]  [300/312]  eta: 0:00:05  lr: 0.002598  min_lr: 0.002598  loss: 2.4815 (2.4811)  weight_decay: 0.0500 (0.0500)  time: 0.4325  data: 0.0001  max mem: 42573
Epoch: [132]  [310/312]  eta: 0:00:00  lr: 0.002597  min_lr: 0.002597  loss: 2.7896 (2.4866)  weight_decay: 0.0500 (0.0500)  time: 0.4324  data: 0.0001  max mem: 42573
Epoch: [132]  [311/312]  eta: 0:00:00  lr: 0.002597  min_lr: 0.002597  loss: 2.8006 (2.4882)  weight_decay: 0.0500 (0.0500)  time: 0.4324  data: 0.0001  max mem: 42573
Epoch: [132] Total time: 0:02:26 (0.4710 s / it)
Averaged stats: lr: 0.002597  min_lr: 0.002597  loss: 2.8006 (2.5196)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:00:44  loss: 0.9397 (0.9397)  acc1: 78.9062 (78.9062)  acc5: 93.2292 (93.2292)  time: 4.8927  data: 4.7840  max mem: 42573
Test:  [8/9]  eta: 0:00:00  loss: 1.1546 (1.1463)  acc1: 71.6146 (71.2320)  acc5: 92.4479 (90.6880)  time: 0.6216  data: 0.5316  max mem: 42573
Test: Total time: 0:00:05 (0.6289 s / it)
* Acc@1 71.422 Acc@5 90.328 loss 1.155
Accuracy of the model on the 50000 test images: 71.4%
Max accuracy: 72.09%
Epoch: [133]  [  0/312]  eta: 0:50:19  lr: 0.002597  min_lr: 0.002597  loss: 1.8767 (1.8767)  weight_decay: 0.0500 (0.0500)  time: 9.6787  data: 8.1739  max mem: 42573
Epoch: [133]  [ 10/312]  eta: 0:07:24  lr: 0.002596  min_lr: 0.002596  loss: 2.3975 (2.4325)  weight_decay: 0.0500 (0.0500)  time: 1.4718  data: 0.7434  max mem: 42573
Epoch: [133]  [ 20/312]  eta: 0:04:45  lr: 0.002596  min_lr: 0.002596  loss: 2.3975 (2.3505)  weight_decay: 0.0500 (0.0500)  time: 0.5421  data: 0.0004  max mem: 42573
Epoch: [133]  [ 30/312]  eta: 0:03:46  lr: 0.002595  min_lr: 0.002595  loss: 2.4859 (2.4735)  weight_decay: 0.0500 (0.0500)  time: 0.4332  data: 0.0004  max mem: 42573
Epoch: [133]  [ 40/312]  eta: 0:03:13  lr: 0.002594  min_lr: 0.002594  loss: 2.6573 (2.4332)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0003  max mem: 42573
Epoch: [133]  [ 50/312]  eta: 0:02:52  lr: 0.002594  min_lr: 0.002594  loss: 2.4546 (2.4521)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [133]  [ 60/312]  eta: 0:02:36  lr: 0.002593  min_lr: 0.002593  loss: 2.4600 (2.4476)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [133]  [ 70/312]  eta: 0:02:23  lr: 0.002592  min_lr: 0.002592  loss: 2.2067 (2.4248)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [133]  [ 80/312]  eta: 0:02:13  lr: 0.002592  min_lr: 0.002592  loss: 2.3630 (2.4258)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [133]  [ 90/312]  eta: 0:02:04  lr: 0.002591  min_lr: 0.002591  loss: 2.5122 (2.4271)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [133]  [100/312]  eta: 0:01:55  lr: 0.002590  min_lr: 0.002590  loss: 2.5204 (2.4366)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0003  max mem: 42573
Epoch: [133]  [110/312]  eta: 0:01:48  lr: 0.002589  min_lr: 0.002589  loss: 2.6149 (2.4478)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [133]  [120/312]  eta: 0:01:41  lr: 0.002589  min_lr: 0.002589  loss: 2.6043 (2.4546)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [133]  [130/312]  eta: 0:01:34  lr: 0.002588  min_lr: 0.002588  loss: 2.5977 (2.4577)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0003  max mem: 42573
Epoch: [133]  [140/312]  eta: 0:01:28  lr: 0.002587  min_lr: 0.002587  loss: 2.5411 (2.4642)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0003  max mem: 42573
Epoch: [133]  [150/312]  eta: 0:01:22  lr: 0.002587  min_lr: 0.002587  loss: 2.5411 (2.4674)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [133]  [160/312]  eta: 0:01:16  lr: 0.002586  min_lr: 0.002586  loss: 2.6595 (2.4797)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0005  max mem: 42573
Epoch: [133]  [170/312]  eta: 0:01:11  lr: 0.002585  min_lr: 0.002585  loss: 2.5826 (2.4767)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [133]  [180/312]  eta: 0:01:05  lr: 0.002585  min_lr: 0.002585  loss: 2.5587 (2.4794)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [133]  [190/312]  eta: 0:01:00  lr: 0.002584  min_lr: 0.002584  loss: 2.5093 (2.4743)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [133]  [200/312]  eta: 0:00:54  lr: 0.002583  min_lr: 0.002583  loss: 2.5572 (2.4859)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [133]  [210/312]  eta: 0:00:49  lr: 0.002583  min_lr: 0.002583  loss: 2.6568 (2.4904)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [133]  [220/312]  eta: 0:00:44  lr: 0.002582  min_lr: 0.002582  loss: 2.7457 (2.4968)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [133]  [230/312]  eta: 0:00:39  lr: 0.002581  min_lr: 0.002581  loss: 2.6920 (2.4996)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [133]  [240/312]  eta: 0:00:34  lr: 0.002581  min_lr: 0.002581  loss: 2.7095 (2.5053)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [133]  [250/312]  eta: 0:00:29  lr: 0.002580  min_lr: 0.002580  loss: 2.8016 (2.5096)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [133]  [260/312]  eta: 0:00:24  lr: 0.002579  min_lr: 0.002579  loss: 2.6127 (2.5118)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [133]  [270/312]  eta: 0:00:19  lr: 0.002578  min_lr: 0.002578  loss: 2.7012 (2.5229)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [133]  [280/312]  eta: 0:00:15  lr: 0.002578  min_lr: 0.002578  loss: 2.7241 (2.5261)  weight_decay: 0.0500 (0.0500)  time: 0.4343  data: 0.0009  max mem: 42573
Epoch: [133]  [290/312]  eta: 0:00:10  lr: 0.002577  min_lr: 0.002577  loss: 2.5895 (2.5241)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0008  max mem: 42573
Epoch: [133]  [300/312]  eta: 0:00:05  lr: 0.002576  min_lr: 0.002576  loss: 2.4765 (2.5249)  weight_decay: 0.0500 (0.0500)  time: 0.4327  data: 0.0001  max mem: 42573
Epoch: [133]  [310/312]  eta: 0:00:00  lr: 0.002576  min_lr: 0.002576  loss: 2.4852 (2.5227)  weight_decay: 0.0500 (0.0500)  time: 0.4323  data: 0.0001  max mem: 42573
Epoch: [133]  [311/312]  eta: 0:00:00  lr: 0.002576  min_lr: 0.002576  loss: 2.4852 (2.5234)  weight_decay: 0.0500 (0.0500)  time: 0.4323  data: 0.0001  max mem: 42573
Epoch: [133] Total time: 0:02:27 (0.4732 s / it)
Averaged stats: lr: 0.002576  min_lr: 0.002576  loss: 2.4852 (2.5032)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:00:40  loss: 0.8552 (0.8552)  acc1: 80.9896 (80.9896)  acc5: 91.9271 (91.9271)  time: 4.5482  data: 4.4394  max mem: 42573
Test:  [8/9]  eta: 0:00:00  loss: 1.1903 (1.1280)  acc1: 72.9167 (71.7120)  acc5: 91.9271 (90.4960)  time: 0.5976  data: 0.5100  max mem: 42573
Test: Total time: 0:00:05 (0.6059 s / it)
* Acc@1 71.574 Acc@5 90.324 loss 1.142
Accuracy of the model on the 50000 test images: 71.6%
Max accuracy: 72.09%
Epoch: [134]  [  0/312]  eta: 0:45:29  lr: 0.002576  min_lr: 0.002576  loss: 2.0425 (2.0425)  weight_decay: 0.0500 (0.0500)  time: 8.7475  data: 7.0905  max mem: 42573
Epoch: [134]  [ 10/312]  eta: 0:06:58  lr: 0.002575  min_lr: 0.002575  loss: 2.6146 (2.5377)  weight_decay: 0.0500 (0.0500)  time: 1.3856  data: 0.7161  max mem: 42573
Epoch: [134]  [ 20/312]  eta: 0:04:32  lr: 0.002574  min_lr: 0.002574  loss: 2.5783 (2.5325)  weight_decay: 0.0500 (0.0500)  time: 0.5415  data: 0.0395  max mem: 42573
Epoch: [134]  [ 30/312]  eta: 0:03:37  lr: 0.002573  min_lr: 0.002573  loss: 2.5783 (2.5191)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [134]  [ 40/312]  eta: 0:03:07  lr: 0.002573  min_lr: 0.002573  loss: 2.3230 (2.4666)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0003  max mem: 42573
Epoch: [134]  [ 50/312]  eta: 0:02:47  lr: 0.002572  min_lr: 0.002572  loss: 2.4020 (2.4519)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [134]  [ 60/312]  eta: 0:02:32  lr: 0.002571  min_lr: 0.002571  loss: 2.4683 (2.4507)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [134]  [ 70/312]  eta: 0:02:20  lr: 0.002571  min_lr: 0.002571  loss: 2.4908 (2.4438)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [134]  [ 80/312]  eta: 0:02:10  lr: 0.002570  min_lr: 0.002570  loss: 2.4908 (2.4438)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0004  max mem: 42573
Epoch: [134]  [ 90/312]  eta: 0:02:01  lr: 0.002569  min_lr: 0.002569  loss: 2.6113 (2.4665)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [134]  [100/312]  eta: 0:01:53  lr: 0.002569  min_lr: 0.002569  loss: 2.6741 (2.4961)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [134]  [110/312]  eta: 0:01:46  lr: 0.002568  min_lr: 0.002568  loss: 2.7305 (2.5103)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [134]  [120/312]  eta: 0:01:39  lr: 0.002567  min_lr: 0.002567  loss: 2.7527 (2.5140)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [134]  [130/312]  eta: 0:01:33  lr: 0.002567  min_lr: 0.002567  loss: 2.5722 (2.5116)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [134]  [140/312]  eta: 0:01:27  lr: 0.002566  min_lr: 0.002566  loss: 2.5202 (2.5021)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [134]  [150/312]  eta: 0:01:21  lr: 0.002565  min_lr: 0.002565  loss: 2.5755 (2.5011)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [134]  [160/312]  eta: 0:01:15  lr: 0.002565  min_lr: 0.002565  loss: 2.4707 (2.4889)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [134]  [170/312]  eta: 0:01:10  lr: 0.002564  min_lr: 0.002564  loss: 2.4707 (2.4861)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0003  max mem: 42573
Epoch: [134]  [180/312]  eta: 0:01:04  lr: 0.002563  min_lr: 0.002563  loss: 2.5701 (2.4933)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [134]  [190/312]  eta: 0:00:59  lr: 0.002562  min_lr: 0.002562  loss: 2.7243 (2.5009)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0003  max mem: 42573
Epoch: [134]  [200/312]  eta: 0:00:54  lr: 0.002562  min_lr: 0.002562  loss: 2.5759 (2.5016)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0003  max mem: 42573
Epoch: [134]  [210/312]  eta: 0:00:49  lr: 0.002561  min_lr: 0.002561  loss: 2.4754 (2.5020)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [134]  [220/312]  eta: 0:00:44  lr: 0.002560  min_lr: 0.002560  loss: 2.5201 (2.5033)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [134]  [230/312]  eta: 0:00:39  lr: 0.002560  min_lr: 0.002560  loss: 2.5615 (2.5052)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [134]  [240/312]  eta: 0:00:34  lr: 0.002559  min_lr: 0.002559  loss: 2.3089 (2.4926)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [134]  [250/312]  eta: 0:00:29  lr: 0.002558  min_lr: 0.002558  loss: 2.2835 (2.4922)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [134]  [260/312]  eta: 0:00:24  lr: 0.002558  min_lr: 0.002558  loss: 2.5772 (2.4981)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [134]  [270/312]  eta: 0:00:19  lr: 0.002557  min_lr: 0.002557  loss: 2.5851 (2.4955)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0003  max mem: 42573
Epoch: [134]  [280/312]  eta: 0:00:15  lr: 0.002556  min_lr: 0.002556  loss: 2.4861 (2.4902)  weight_decay: 0.0500 (0.0500)  time: 0.4349  data: 0.0009  max mem: 42573
Epoch: [134]  [290/312]  eta: 0:00:10  lr: 0.002556  min_lr: 0.002556  loss: 2.4541 (2.4904)  weight_decay: 0.0500 (0.0500)  time: 0.4342  data: 0.0008  max mem: 42573
Epoch: [134]  [300/312]  eta: 0:00:05  lr: 0.002555  min_lr: 0.002555  loss: 2.5051 (2.4920)  weight_decay: 0.0500 (0.0500)  time: 0.4325  data: 0.0001  max mem: 42573
Epoch: [134]  [310/312]  eta: 0:00:00  lr: 0.002554  min_lr: 0.002554  loss: 2.5647 (2.4913)  weight_decay: 0.0500 (0.0500)  time: 0.4323  data: 0.0001  max mem: 42573
Epoch: [134]  [311/312]  eta: 0:00:00  lr: 0.002554  min_lr: 0.002554  loss: 2.5647 (2.4921)  weight_decay: 0.0500 (0.0500)  time: 0.4323  data: 0.0001  max mem: 42573
Epoch: [134] Total time: 0:02:26 (0.4703 s / it)
Averaged stats: lr: 0.002554  min_lr: 0.002554  loss: 2.5647 (2.5158)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:00:42  loss: 0.9418 (0.9418)  acc1: 79.6875 (79.6875)  acc5: 92.7083 (92.7083)  time: 4.7304  data: 4.6212  max mem: 42573
Test:  [8/9]  eta: 0:00:00  loss: 1.2777 (1.1610)  acc1: 70.3125 (70.7200)  acc5: 90.1042 (90.4000)  time: 0.6012  data: 0.5135  max mem: 42573
Test: Total time: 0:00:05 (0.6103 s / it)
* Acc@1 71.816 Acc@5 90.434 loss 1.153
Accuracy of the model on the 50000 test images: 71.8%
Max accuracy: 72.09%
Epoch: [135]  [  0/312]  eta: 0:51:26  lr: 0.002554  min_lr: 0.002554  loss: 1.5639 (1.5639)  weight_decay: 0.0500 (0.0500)  time: 9.8913  data: 6.4217  max mem: 42573
Epoch: [135]  [ 10/312]  eta: 0:07:35  lr: 0.002553  min_lr: 0.002553  loss: 2.5910 (2.3024)  weight_decay: 0.0500 (0.0500)  time: 1.5068  data: 0.6910  max mem: 42573
Epoch: [135]  [ 20/312]  eta: 0:04:50  lr: 0.002553  min_lr: 0.002553  loss: 2.6646 (2.4438)  weight_decay: 0.0500 (0.0500)  time: 0.5508  data: 0.0592  max mem: 42573
Epoch: [135]  [ 30/312]  eta: 0:03:49  lr: 0.002552  min_lr: 0.002552  loss: 2.6485 (2.3932)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0003  max mem: 42573
Epoch: [135]  [ 40/312]  eta: 0:03:16  lr: 0.002551  min_lr: 0.002551  loss: 2.4811 (2.4094)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0003  max mem: 42573
Epoch: [135]  [ 50/312]  eta: 0:02:54  lr: 0.002551  min_lr: 0.002551  loss: 2.4811 (2.4093)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [135]  [ 60/312]  eta: 0:02:37  lr: 0.002550  min_lr: 0.002550  loss: 2.5555 (2.4317)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [135]  [ 70/312]  eta: 0:02:25  lr: 0.002549  min_lr: 0.002549  loss: 2.7478 (2.4910)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [135]  [ 80/312]  eta: 0:02:14  lr: 0.002549  min_lr: 0.002549  loss: 2.6593 (2.4960)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [135]  [ 90/312]  eta: 0:02:05  lr: 0.002548  min_lr: 0.002548  loss: 2.5366 (2.5030)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [135]  [100/312]  eta: 0:01:56  lr: 0.002547  min_lr: 0.002547  loss: 2.6266 (2.5143)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0003  max mem: 42573
Epoch: [135]  [110/312]  eta: 0:01:49  lr: 0.002546  min_lr: 0.002546  loss: 2.4421 (2.4937)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [135]  [120/312]  eta: 0:01:41  lr: 0.002546  min_lr: 0.002546  loss: 2.3793 (2.4961)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [135]  [130/312]  eta: 0:01:35  lr: 0.002545  min_lr: 0.002545  loss: 2.5307 (2.5011)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [135]  [140/312]  eta: 0:01:28  lr: 0.002544  min_lr: 0.002544  loss: 2.4679 (2.4882)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [135]  [150/312]  eta: 0:01:22  lr: 0.002544  min_lr: 0.002544  loss: 2.2592 (2.4727)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [135]  [160/312]  eta: 0:01:17  lr: 0.002543  min_lr: 0.002543  loss: 2.3857 (2.4791)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [135]  [170/312]  eta: 0:01:11  lr: 0.002542  min_lr: 0.002542  loss: 2.6892 (2.4806)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [135]  [180/312]  eta: 0:01:05  lr: 0.002542  min_lr: 0.002542  loss: 2.6892 (2.4850)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [135]  [190/312]  eta: 0:01:00  lr: 0.002541  min_lr: 0.002541  loss: 2.4804 (2.4776)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [135]  [200/312]  eta: 0:00:55  lr: 0.002540  min_lr: 0.002540  loss: 2.3549 (2.4821)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [135]  [210/312]  eta: 0:00:49  lr: 0.002540  min_lr: 0.002540  loss: 2.3549 (2.4736)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [135]  [220/312]  eta: 0:00:44  lr: 0.002539  min_lr: 0.002539  loss: 2.3202 (2.4724)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0003  max mem: 42573
Epoch: [135]  [230/312]  eta: 0:00:39  lr: 0.002538  min_lr: 0.002538  loss: 2.4153 (2.4699)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0003  max mem: 42573
Epoch: [135]  [240/312]  eta: 0:00:34  lr: 0.002537  min_lr: 0.002537  loss: 2.4698 (2.4699)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [135]  [250/312]  eta: 0:00:29  lr: 0.002537  min_lr: 0.002537  loss: 2.6113 (2.4717)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [135]  [260/312]  eta: 0:00:24  lr: 0.002536  min_lr: 0.002536  loss: 2.5437 (2.4673)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [135]  [270/312]  eta: 0:00:20  lr: 0.002535  min_lr: 0.002535  loss: 2.4078 (2.4674)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0003  max mem: 42573
Epoch: [135]  [280/312]  eta: 0:00:15  lr: 0.002535  min_lr: 0.002535  loss: 2.3136 (2.4632)  weight_decay: 0.0500 (0.0500)  time: 0.4344  data: 0.0009  max mem: 42573
Epoch: [135]  [290/312]  eta: 0:00:10  lr: 0.002534  min_lr: 0.002534  loss: 2.5508 (2.4673)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0008  max mem: 42573
Epoch: [135]  [300/312]  eta: 0:00:05  lr: 0.002533  min_lr: 0.002533  loss: 2.5508 (2.4705)  weight_decay: 0.0500 (0.0500)  time: 0.4325  data: 0.0001  max mem: 42573
Epoch: [135]  [310/312]  eta: 0:00:00  lr: 0.002533  min_lr: 0.002533  loss: 2.4170 (2.4687)  weight_decay: 0.0500 (0.0500)  time: 0.4325  data: 0.0001  max mem: 42573
Epoch: [135]  [311/312]  eta: 0:00:00  lr: 0.002533  min_lr: 0.002533  loss: 2.4269 (2.4688)  weight_decay: 0.0500 (0.0500)  time: 0.4325  data: 0.0001  max mem: 42573
Epoch: [135] Total time: 0:02:28 (0.4744 s / it)
Averaged stats: lr: 0.002533  min_lr: 0.002533  loss: 2.4269 (2.5005)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:00:43  loss: 0.8789 (0.8789)  acc1: 79.1667 (79.1667)  acc5: 92.9688 (92.9688)  time: 4.8334  data: 4.7239  max mem: 42573
Test:  [8/9]  eta: 0:00:00  loss: 1.2791 (1.1898)  acc1: 70.5729 (70.6560)  acc5: 89.5833 (89.8880)  time: 0.6211  data: 0.5326  max mem: 42573
Test: Total time: 0:00:05 (0.6288 s / it)
* Acc@1 71.250 Acc@5 90.054 loss 1.183
Accuracy of the model on the 50000 test images: 71.3%
Max accuracy: 72.09%
Epoch: [136]  [  0/312]  eta: 0:53:21  lr: 0.002532  min_lr: 0.002532  loss: 3.1989 (3.1989)  weight_decay: 0.0500 (0.0500)  time: 10.2608  data: 6.6351  max mem: 42573
Epoch: [136]  [ 10/312]  eta: 0:07:48  lr: 0.002532  min_lr: 0.002532  loss: 2.6439 (2.4905)  weight_decay: 0.0500 (0.0500)  time: 1.5521  data: 0.6657  max mem: 42573
Epoch: [136]  [ 20/312]  eta: 0:04:57  lr: 0.002531  min_lr: 0.002531  loss: 2.5218 (2.4117)  weight_decay: 0.0500 (0.0500)  time: 0.5571  data: 0.0346  max mem: 42573
Epoch: [136]  [ 30/312]  eta: 0:03:54  lr: 0.002530  min_lr: 0.002530  loss: 2.2728 (2.3762)  weight_decay: 0.0500 (0.0500)  time: 0.4331  data: 0.0004  max mem: 42573
Epoch: [136]  [ 40/312]  eta: 0:03:19  lr: 0.002530  min_lr: 0.002530  loss: 2.3875 (2.4237)  weight_decay: 0.0500 (0.0500)  time: 0.4332  data: 0.0004  max mem: 42573
Epoch: [136]  [ 50/312]  eta: 0:02:56  lr: 0.002529  min_lr: 0.002529  loss: 2.5772 (2.4318)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [136]  [ 60/312]  eta: 0:02:40  lr: 0.002528  min_lr: 0.002528  loss: 2.5636 (2.4316)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [136]  [ 70/312]  eta: 0:02:26  lr: 0.002528  min_lr: 0.002528  loss: 2.5157 (2.4451)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [136]  [ 80/312]  eta: 0:02:15  lr: 0.002527  min_lr: 0.002527  loss: 2.5157 (2.4508)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [136]  [ 90/312]  eta: 0:02:06  lr: 0.002526  min_lr: 0.002526  loss: 2.5411 (2.4545)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [136]  [100/312]  eta: 0:01:57  lr: 0.002526  min_lr: 0.002526  loss: 2.7613 (2.4902)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [136]  [110/312]  eta: 0:01:49  lr: 0.002525  min_lr: 0.002525  loss: 2.7180 (2.4887)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [136]  [120/312]  eta: 0:01:42  lr: 0.002524  min_lr: 0.002524  loss: 2.4684 (2.4822)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [136]  [130/312]  eta: 0:01:35  lr: 0.002523  min_lr: 0.002523  loss: 2.4702 (2.4781)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [136]  [140/312]  eta: 0:01:29  lr: 0.002523  min_lr: 0.002523  loss: 2.4715 (2.4857)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [136]  [150/312]  eta: 0:01:23  lr: 0.002522  min_lr: 0.002522  loss: 2.5744 (2.4999)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0003  max mem: 42573
Epoch: [136]  [160/312]  eta: 0:01:17  lr: 0.002521  min_lr: 0.002521  loss: 2.5754 (2.5041)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [136]  [170/312]  eta: 0:01:11  lr: 0.002521  min_lr: 0.002521  loss: 2.6000 (2.5005)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [136]  [180/312]  eta: 0:01:06  lr: 0.002520  min_lr: 0.002520  loss: 2.6343 (2.5183)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0003  max mem: 42573
Epoch: [136]  [190/312]  eta: 0:01:00  lr: 0.002519  min_lr: 0.002519  loss: 2.7882 (2.5155)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [136]  [200/312]  eta: 0:00:55  lr: 0.002519  min_lr: 0.002519  loss: 2.5046 (2.5165)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [136]  [210/312]  eta: 0:00:50  lr: 0.002518  min_lr: 0.002518  loss: 2.5046 (2.5126)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [136]  [220/312]  eta: 0:00:45  lr: 0.002517  min_lr: 0.002517  loss: 2.5166 (2.5086)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [136]  [230/312]  eta: 0:00:39  lr: 0.002516  min_lr: 0.002516  loss: 2.5400 (2.5156)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [136]  [240/312]  eta: 0:00:34  lr: 0.002516  min_lr: 0.002516  loss: 2.6681 (2.5173)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [136]  [250/312]  eta: 0:00:29  lr: 0.002515  min_lr: 0.002515  loss: 2.6681 (2.5196)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [136]  [260/312]  eta: 0:00:24  lr: 0.002514  min_lr: 0.002514  loss: 2.6133 (2.5206)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [136]  [270/312]  eta: 0:00:20  lr: 0.002514  min_lr: 0.002514  loss: 2.3294 (2.5170)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [136]  [280/312]  eta: 0:00:15  lr: 0.002513  min_lr: 0.002513  loss: 2.5264 (2.5160)  weight_decay: 0.0500 (0.0500)  time: 0.4344  data: 0.0009  max mem: 42573
Epoch: [136]  [290/312]  eta: 0:00:10  lr: 0.002512  min_lr: 0.002512  loss: 2.4948 (2.5117)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0008  max mem: 42573
Epoch: [136]  [300/312]  eta: 0:00:05  lr: 0.002512  min_lr: 0.002512  loss: 2.4009 (2.5095)  weight_decay: 0.0500 (0.0500)  time: 0.4324  data: 0.0001  max mem: 42573
Epoch: [136]  [310/312]  eta: 0:00:00  lr: 0.002511  min_lr: 0.002511  loss: 2.5255 (2.5159)  weight_decay: 0.0500 (0.0500)  time: 0.4324  data: 0.0001  max mem: 42573
Epoch: [136]  [311/312]  eta: 0:00:00  lr: 0.002511  min_lr: 0.002511  loss: 2.5118 (2.5147)  weight_decay: 0.0500 (0.0500)  time: 0.4324  data: 0.0001  max mem: 42573
Epoch: [136] Total time: 0:02:28 (0.4761 s / it)
Averaged stats: lr: 0.002511  min_lr: 0.002511  loss: 2.5118 (2.5082)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:00:46  loss: 0.9323 (0.9323)  acc1: 77.0833 (77.0833)  acc5: 92.9688 (92.9688)  time: 5.1588  data: 5.0494  max mem: 42573
Test:  [8/9]  eta: 0:00:00  loss: 1.2252 (1.1552)  acc1: 71.8750 (71.6160)  acc5: 90.6250 (89.8880)  time: 0.6486  data: 0.5611  max mem: 42573
Test: Total time: 0:00:05 (0.6598 s / it)
* Acc@1 71.416 Acc@5 90.112 loss 1.161
Accuracy of the model on the 50000 test images: 71.4%
Max accuracy: 72.09%
Epoch: [137]  [  0/312]  eta: 0:50:25  lr: 0.002511  min_lr: 0.002511  loss: 3.0054 (3.0054)  weight_decay: 0.0500 (0.0500)  time: 9.6978  data: 6.9928  max mem: 42573
Epoch: [137]  [ 10/312]  eta: 0:07:37  lr: 0.002510  min_lr: 0.002510  loss: 2.4764 (2.4713)  weight_decay: 0.0500 (0.0500)  time: 1.5160  data: 0.6999  max mem: 42573
Epoch: [137]  [ 20/312]  eta: 0:04:52  lr: 0.002509  min_lr: 0.002509  loss: 2.4764 (2.5713)  weight_decay: 0.0500 (0.0500)  time: 0.5654  data: 0.0355  max mem: 42573
Epoch: [137]  [ 30/312]  eta: 0:03:50  lr: 0.002509  min_lr: 0.002509  loss: 2.5147 (2.5278)  weight_decay: 0.0500 (0.0500)  time: 0.4331  data: 0.0004  max mem: 42573
Epoch: [137]  [ 40/312]  eta: 0:03:16  lr: 0.002508  min_lr: 0.002508  loss: 2.3743 (2.4769)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [137]  [ 50/312]  eta: 0:02:54  lr: 0.002507  min_lr: 0.002507  loss: 2.3000 (2.4679)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [137]  [ 60/312]  eta: 0:02:38  lr: 0.002507  min_lr: 0.002507  loss: 2.7701 (2.5036)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [137]  [ 70/312]  eta: 0:02:25  lr: 0.002506  min_lr: 0.002506  loss: 2.7397 (2.5024)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [137]  [ 80/312]  eta: 0:02:14  lr: 0.002505  min_lr: 0.002505  loss: 2.6709 (2.5276)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [137]  [ 90/312]  eta: 0:02:05  lr: 0.002505  min_lr: 0.002505  loss: 2.5663 (2.5103)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0003  max mem: 42573
Epoch: [137]  [100/312]  eta: 0:01:56  lr: 0.002504  min_lr: 0.002504  loss: 2.4811 (2.5213)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0003  max mem: 42573
Epoch: [137]  [110/312]  eta: 0:01:49  lr: 0.002503  min_lr: 0.002503  loss: 2.5073 (2.5248)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [137]  [120/312]  eta: 0:01:42  lr: 0.002502  min_lr: 0.002502  loss: 2.6160 (2.5349)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [137]  [130/312]  eta: 0:01:35  lr: 0.002502  min_lr: 0.002502  loss: 2.3526 (2.5174)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [137]  [140/312]  eta: 0:01:29  lr: 0.002501  min_lr: 0.002501  loss: 2.6637 (2.5380)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [137]  [150/312]  eta: 0:01:23  lr: 0.002500  min_lr: 0.002500  loss: 2.6419 (2.5173)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [137]  [160/312]  eta: 0:01:17  lr: 0.002500  min_lr: 0.002500  loss: 2.2616 (2.5162)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0004  max mem: 42573
Epoch: [137]  [170/312]  eta: 0:01:11  lr: 0.002499  min_lr: 0.002499  loss: 2.6206 (2.5072)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0004  max mem: 42573
Epoch: [137]  [180/312]  eta: 0:01:05  lr: 0.002498  min_lr: 0.002498  loss: 2.5748 (2.5064)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [137]  [190/312]  eta: 0:01:00  lr: 0.002498  min_lr: 0.002498  loss: 2.6513 (2.5119)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0003  max mem: 42573
Epoch: [137]  [200/312]  eta: 0:00:55  lr: 0.002497  min_lr: 0.002497  loss: 2.6513 (2.5196)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0003  max mem: 42573
Epoch: [137]  [210/312]  eta: 0:00:49  lr: 0.002496  min_lr: 0.002496  loss: 2.7283 (2.5318)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [137]  [220/312]  eta: 0:00:44  lr: 0.002495  min_lr: 0.002495  loss: 2.6613 (2.5318)  weight_decay: 0.0500 (0.0500)  time: 0.4390  data: 0.0004  max mem: 42573
Epoch: [137]  [230/312]  eta: 0:00:39  lr: 0.002495  min_lr: 0.002495  loss: 2.5519 (2.5293)  weight_decay: 0.0500 (0.0500)  time: 0.4390  data: 0.0003  max mem: 42573
Epoch: [137]  [240/312]  eta: 0:00:34  lr: 0.002494  min_lr: 0.002494  loss: 2.5519 (2.5282)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [137]  [250/312]  eta: 0:00:29  lr: 0.002493  min_lr: 0.002493  loss: 2.5320 (2.5243)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [137]  [260/312]  eta: 0:00:24  lr: 0.002493  min_lr: 0.002493  loss: 2.5259 (2.5200)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [137]  [270/312]  eta: 0:00:20  lr: 0.002492  min_lr: 0.002492  loss: 2.5214 (2.5182)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [137]  [280/312]  eta: 0:00:15  lr: 0.002491  min_lr: 0.002491  loss: 2.5722 (2.5217)  weight_decay: 0.0500 (0.0500)  time: 0.4342  data: 0.0009  max mem: 42573
Epoch: [137]  [290/312]  eta: 0:00:10  lr: 0.002491  min_lr: 0.002491  loss: 2.7246 (2.5258)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0008  max mem: 42573
Epoch: [137]  [300/312]  eta: 0:00:05  lr: 0.002490  min_lr: 0.002490  loss: 2.5615 (2.5199)  weight_decay: 0.0500 (0.0500)  time: 0.4324  data: 0.0001  max mem: 42573
Epoch: [137]  [310/312]  eta: 0:00:00  lr: 0.002489  min_lr: 0.002489  loss: 2.4629 (2.5192)  weight_decay: 0.0500 (0.0500)  time: 0.4324  data: 0.0001  max mem: 42573
Epoch: [137]  [311/312]  eta: 0:00:00  lr: 0.002489  min_lr: 0.002489  loss: 2.4629 (2.5198)  weight_decay: 0.0500 (0.0500)  time: 0.4324  data: 0.0001  max mem: 42573
Epoch: [137] Total time: 0:02:28 (0.4752 s / it)
Averaged stats: lr: 0.002489  min_lr: 0.002489  loss: 2.4629 (2.5026)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:00:45  loss: 0.7618 (0.7618)  acc1: 80.4688 (80.4688)  acc5: 94.7917 (94.7917)  time: 5.0220  data: 4.9126  max mem: 42573
Test:  [8/9]  eta: 0:00:00  loss: 1.2323 (1.1339)  acc1: 71.6146 (71.3600)  acc5: 90.3646 (90.5600)  time: 0.6346  data: 0.5459  max mem: 42573
Test: Total time: 0:00:05 (0.6556 s / it)
* Acc@1 71.740 Acc@5 90.346 loss 1.127
Accuracy of the model on the 50000 test images: 71.7%
Max accuracy: 72.09%
Epoch: [138]  [  0/312]  eta: 0:51:08  lr: 0.002489  min_lr: 0.002489  loss: 2.8428 (2.8428)  weight_decay: 0.0500 (0.0500)  time: 9.8341  data: 6.9630  max mem: 42573
Epoch: [138]  [ 10/312]  eta: 0:07:31  lr: 0.002488  min_lr: 0.002488  loss: 2.4996 (2.3877)  weight_decay: 0.0500 (0.0500)  time: 1.4939  data: 0.6977  max mem: 42573
Epoch: [138]  [ 20/312]  eta: 0:04:48  lr: 0.002488  min_lr: 0.002488  loss: 2.4996 (2.4639)  weight_decay: 0.0500 (0.0500)  time: 0.5466  data: 0.0358  max mem: 42573
Epoch: [138]  [ 30/312]  eta: 0:03:48  lr: 0.002487  min_lr: 0.002487  loss: 2.6115 (2.4597)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0003  max mem: 42573
Epoch: [138]  [ 40/312]  eta: 0:03:15  lr: 0.002486  min_lr: 0.002486  loss: 2.4549 (2.4399)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0003  max mem: 42573
Epoch: [138]  [ 50/312]  eta: 0:02:53  lr: 0.002486  min_lr: 0.002486  loss: 2.4722 (2.4625)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0003  max mem: 42573
Epoch: [138]  [ 60/312]  eta: 0:02:37  lr: 0.002485  min_lr: 0.002485  loss: 2.6754 (2.4681)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0003  max mem: 42573
Epoch: [138]  [ 70/312]  eta: 0:02:24  lr: 0.002484  min_lr: 0.002484  loss: 2.7074 (2.4937)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0003  max mem: 42573
Epoch: [138]  [ 80/312]  eta: 0:02:13  lr: 0.002483  min_lr: 0.002483  loss: 2.7582 (2.5022)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [138]  [ 90/312]  eta: 0:02:04  lr: 0.002483  min_lr: 0.002483  loss: 2.5264 (2.5060)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0005  max mem: 42573
Epoch: [138]  [100/312]  eta: 0:01:56  lr: 0.002482  min_lr: 0.002482  loss: 2.3171 (2.4954)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [138]  [110/312]  eta: 0:01:48  lr: 0.002481  min_lr: 0.002481  loss: 2.5284 (2.5093)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [138]  [120/312]  eta: 0:01:41  lr: 0.002481  min_lr: 0.002481  loss: 2.5540 (2.5034)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [138]  [130/312]  eta: 0:01:35  lr: 0.002480  min_lr: 0.002480  loss: 2.0765 (2.4679)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [138]  [140/312]  eta: 0:01:28  lr: 0.002479  min_lr: 0.002479  loss: 2.4673 (2.4852)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [138]  [150/312]  eta: 0:01:22  lr: 0.002479  min_lr: 0.002479  loss: 2.6233 (2.4802)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [138]  [160/312]  eta: 0:01:16  lr: 0.002478  min_lr: 0.002478  loss: 2.4933 (2.4784)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [138]  [170/312]  eta: 0:01:11  lr: 0.002477  min_lr: 0.002477  loss: 2.5066 (2.4697)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [138]  [180/312]  eta: 0:01:05  lr: 0.002476  min_lr: 0.002476  loss: 2.3195 (2.4600)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [138]  [190/312]  eta: 0:01:00  lr: 0.002476  min_lr: 0.002476  loss: 2.3306 (2.4644)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [138]  [200/312]  eta: 0:00:55  lr: 0.002475  min_lr: 0.002475  loss: 2.5557 (2.4640)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0003  max mem: 42573
Epoch: [138]  [210/312]  eta: 0:00:49  lr: 0.002474  min_lr: 0.002474  loss: 2.6798 (2.4710)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [138]  [220/312]  eta: 0:00:44  lr: 0.002474  min_lr: 0.002474  loss: 2.7147 (2.4826)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [138]  [230/312]  eta: 0:00:39  lr: 0.002473  min_lr: 0.002473  loss: 2.6937 (2.4773)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [138]  [240/312]  eta: 0:00:34  lr: 0.002472  min_lr: 0.002472  loss: 2.5462 (2.4752)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [138]  [250/312]  eta: 0:00:29  lr: 0.002472  min_lr: 0.002472  loss: 2.6298 (2.4746)  weight_decay: 0.0500 (0.0500)  time: 0.4396  data: 0.0004  max mem: 42573
Epoch: [138]  [260/312]  eta: 0:00:24  lr: 0.002471  min_lr: 0.002471  loss: 2.4291 (2.4709)  weight_decay: 0.0500 (0.0500)  time: 0.4395  data: 0.0004  max mem: 42573
Epoch: [138]  [270/312]  eta: 0:00:20  lr: 0.002470  min_lr: 0.002470  loss: 2.3639 (2.4687)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0003  max mem: 42573
Epoch: [138]  [280/312]  eta: 0:00:15  lr: 0.002470  min_lr: 0.002470  loss: 2.2520 (2.4655)  weight_decay: 0.0500 (0.0500)  time: 0.4343  data: 0.0009  max mem: 42573
Epoch: [138]  [290/312]  eta: 0:00:10  lr: 0.002469  min_lr: 0.002469  loss: 2.5023 (2.4686)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0008  max mem: 42573
Epoch: [138]  [300/312]  eta: 0:00:05  lr: 0.002468  min_lr: 0.002468  loss: 2.5482 (2.4705)  weight_decay: 0.0500 (0.0500)  time: 0.4324  data: 0.0001  max mem: 42573
Epoch: [138]  [310/312]  eta: 0:00:00  lr: 0.002467  min_lr: 0.002467  loss: 2.6492 (2.4762)  weight_decay: 0.0500 (0.0500)  time: 0.4323  data: 0.0001  max mem: 42573
Epoch: [138]  [311/312]  eta: 0:00:00  lr: 0.002467  min_lr: 0.002467  loss: 2.6492 (2.4766)  weight_decay: 0.0500 (0.0500)  time: 0.4323  data: 0.0001  max mem: 42573
Epoch: [138] Total time: 0:02:28 (0.4744 s / it)
Averaged stats: lr: 0.002467  min_lr: 0.002467  loss: 2.6492 (2.4940)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:00:43  loss: 0.9841 (0.9841)  acc1: 77.6042 (77.6042)  acc5: 93.2292 (93.2292)  time: 4.8683  data: 4.7589  max mem: 42573
Test:  [8/9]  eta: 0:00:00  loss: 1.4433 (1.2646)  acc1: 70.3125 (70.9120)  acc5: 87.7604 (89.0880)  time: 0.6165  data: 0.5288  max mem: 42573
Test: Total time: 0:00:05 (0.6384 s / it)
* Acc@1 70.776 Acc@5 89.764 loss 1.249
Accuracy of the model on the 50000 test images: 70.8%
Max accuracy: 72.09%
Epoch: [139]  [  0/312]  eta: 0:50:35  lr: 0.002467  min_lr: 0.002467  loss: 2.8787 (2.8787)  weight_decay: 0.0500 (0.0500)  time: 9.7302  data: 7.2911  max mem: 42573
Epoch: [139]  [ 10/312]  eta: 0:07:27  lr: 0.002467  min_lr: 0.002467  loss: 2.3305 (2.3946)  weight_decay: 0.0500 (0.0500)  time: 1.4830  data: 0.6700  max mem: 42573
Epoch: [139]  [ 20/312]  eta: 0:04:47  lr: 0.002466  min_lr: 0.002466  loss: 2.4530 (2.4655)  weight_decay: 0.0500 (0.0500)  time: 0.5456  data: 0.0041  max mem: 42573
Epoch: [139]  [ 30/312]  eta: 0:03:47  lr: 0.002465  min_lr: 0.002465  loss: 2.4953 (2.4692)  weight_decay: 0.0500 (0.0500)  time: 0.4330  data: 0.0003  max mem: 42573
Epoch: [139]  [ 40/312]  eta: 0:03:14  lr: 0.002464  min_lr: 0.002464  loss: 2.5831 (2.4377)  weight_decay: 0.0500 (0.0500)  time: 0.4332  data: 0.0003  max mem: 42573
Epoch: [139]  [ 50/312]  eta: 0:02:52  lr: 0.002464  min_lr: 0.002464  loss: 2.3663 (2.4360)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [139]  [ 60/312]  eta: 0:02:36  lr: 0.002463  min_lr: 0.002463  loss: 2.4996 (2.4811)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [139]  [ 70/312]  eta: 0:02:24  lr: 0.002462  min_lr: 0.002462  loss: 2.6514 (2.4694)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0003  max mem: 42573
Epoch: [139]  [ 80/312]  eta: 0:02:13  lr: 0.002462  min_lr: 0.002462  loss: 2.6552 (2.4990)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [139]  [ 90/312]  eta: 0:02:04  lr: 0.002461  min_lr: 0.002461  loss: 2.6036 (2.4868)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [139]  [100/312]  eta: 0:01:56  lr: 0.002460  min_lr: 0.002460  loss: 2.4797 (2.4908)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [139]  [110/312]  eta: 0:01:48  lr: 0.002460  min_lr: 0.002460  loss: 2.5141 (2.4836)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [139]  [120/312]  eta: 0:01:41  lr: 0.002459  min_lr: 0.002459  loss: 2.6629 (2.4975)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [139]  [130/312]  eta: 0:01:34  lr: 0.002458  min_lr: 0.002458  loss: 2.7116 (2.5046)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [139]  [140/312]  eta: 0:01:28  lr: 0.002457  min_lr: 0.002457  loss: 2.6094 (2.4996)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [139]  [150/312]  eta: 0:01:22  lr: 0.002457  min_lr: 0.002457  loss: 2.1885 (2.4802)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [139]  [160/312]  eta: 0:01:16  lr: 0.002456  min_lr: 0.002456  loss: 2.4595 (2.4865)  weight_decay: 0.0500 (0.0500)  time: 0.4342  data: 0.0004  max mem: 42573
Epoch: [139]  [170/312]  eta: 0:01:11  lr: 0.002455  min_lr: 0.002455  loss: 2.5975 (2.4919)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [139]  [180/312]  eta: 0:01:05  lr: 0.002455  min_lr: 0.002455  loss: 2.4412 (2.4813)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [139]  [190/312]  eta: 0:01:00  lr: 0.002454  min_lr: 0.002454  loss: 2.2018 (2.4746)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [139]  [200/312]  eta: 0:00:54  lr: 0.002453  min_lr: 0.002453  loss: 2.0892 (2.4632)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [139]  [210/312]  eta: 0:00:49  lr: 0.002453  min_lr: 0.002453  loss: 2.3270 (2.4668)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [139]  [220/312]  eta: 0:00:44  lr: 0.002452  min_lr: 0.002452  loss: 2.5386 (2.4661)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [139]  [230/312]  eta: 0:00:39  lr: 0.002451  min_lr: 0.002451  loss: 2.5386 (2.4676)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [139]  [240/312]  eta: 0:00:34  lr: 0.002450  min_lr: 0.002450  loss: 2.5670 (2.4703)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [139]  [250/312]  eta: 0:00:29  lr: 0.002450  min_lr: 0.002450  loss: 2.5670 (2.4629)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [139]  [260/312]  eta: 0:00:24  lr: 0.002449  min_lr: 0.002449  loss: 2.5433 (2.4645)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [139]  [270/312]  eta: 0:00:19  lr: 0.002448  min_lr: 0.002448  loss: 2.5433 (2.4673)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [139]  [280/312]  eta: 0:00:15  lr: 0.002448  min_lr: 0.002448  loss: 2.5347 (2.4633)  weight_decay: 0.0500 (0.0500)  time: 0.4343  data: 0.0009  max mem: 42573
Epoch: [139]  [290/312]  eta: 0:00:10  lr: 0.002447  min_lr: 0.002447  loss: 2.5962 (2.4717)  weight_decay: 0.0500 (0.0500)  time: 0.4369  data: 0.0008  max mem: 42573
Epoch: [139]  [300/312]  eta: 0:00:05  lr: 0.002446  min_lr: 0.002446  loss: 2.6850 (2.4720)  weight_decay: 0.0500 (0.0500)  time: 0.4357  data: 0.0001  max mem: 42573
Epoch: [139]  [310/312]  eta: 0:00:00  lr: 0.002446  min_lr: 0.002446  loss: 2.4749 (2.4730)  weight_decay: 0.0500 (0.0500)  time: 0.4323  data: 0.0001  max mem: 42573
Epoch: [139]  [311/312]  eta: 0:00:00  lr: 0.002446  min_lr: 0.002446  loss: 2.4749 (2.4729)  weight_decay: 0.0500 (0.0500)  time: 0.4323  data: 0.0001  max mem: 42573
Epoch: [139] Total time: 0:02:27 (0.4738 s / it)
Averaged stats: lr: 0.002446  min_lr: 0.002446  loss: 2.4749 (2.5037)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:00:43  loss: 0.8772 (0.8772)  acc1: 78.3854 (78.3854)  acc5: 92.7083 (92.7083)  time: 4.7955  data: 4.6864  max mem: 42573
Test:  [8/9]  eta: 0:00:00  loss: 1.2018 (1.1443)  acc1: 72.1354 (71.8400)  acc5: 90.8854 (90.8160)  time: 0.6309  data: 0.5436  max mem: 42573
Test: Total time: 0:00:05 (0.6378 s / it)
* Acc@1 71.652 Acc@5 90.356 loss 1.158
Accuracy of the model on the 50000 test images: 71.7%
Max accuracy: 72.09%
Epoch: [140]  [  0/312]  eta: 0:49:18  lr: 0.002445  min_lr: 0.002445  loss: 2.4348 (2.4348)  weight_decay: 0.0500 (0.0500)  time: 9.4808  data: 8.1823  max mem: 42573
Epoch: [140]  [ 10/312]  eta: 0:07:13  lr: 0.002445  min_lr: 0.002445  loss: 2.5113 (2.4573)  weight_decay: 0.0500 (0.0500)  time: 1.4354  data: 0.7528  max mem: 42573
Epoch: [140]  [ 20/312]  eta: 0:04:39  lr: 0.002444  min_lr: 0.002444  loss: 2.6535 (2.5581)  weight_decay: 0.0500 (0.0500)  time: 0.5319  data: 0.0051  max mem: 42573
Epoch: [140]  [ 30/312]  eta: 0:03:42  lr: 0.002443  min_lr: 0.002443  loss: 2.7307 (2.5893)  weight_decay: 0.0500 (0.0500)  time: 0.4330  data: 0.0004  max mem: 42573
Epoch: [140]  [ 40/312]  eta: 0:03:10  lr: 0.002443  min_lr: 0.002443  loss: 2.6238 (2.5888)  weight_decay: 0.0500 (0.0500)  time: 0.4332  data: 0.0004  max mem: 42573
Epoch: [140]  [ 50/312]  eta: 0:02:50  lr: 0.002442  min_lr: 0.002442  loss: 2.6277 (2.5634)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [140]  [ 60/312]  eta: 0:02:34  lr: 0.002441  min_lr: 0.002441  loss: 2.6717 (2.5687)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [140]  [ 70/312]  eta: 0:02:22  lr: 0.002441  min_lr: 0.002441  loss: 2.3796 (2.5415)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [140]  [ 80/312]  eta: 0:02:12  lr: 0.002440  min_lr: 0.002440  loss: 2.3115 (2.5046)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [140]  [ 90/312]  eta: 0:02:03  lr: 0.002439  min_lr: 0.002439  loss: 2.5423 (2.5112)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [140]  [100/312]  eta: 0:01:55  lr: 0.002438  min_lr: 0.002438  loss: 2.5423 (2.4989)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [140]  [110/312]  eta: 0:01:47  lr: 0.002438  min_lr: 0.002438  loss: 2.4605 (2.4900)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [140]  [120/312]  eta: 0:01:40  lr: 0.002437  min_lr: 0.002437  loss: 2.6120 (2.5180)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [140]  [130/312]  eta: 0:01:34  lr: 0.002436  min_lr: 0.002436  loss: 2.7204 (2.5199)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [140]  [140/312]  eta: 0:01:28  lr: 0.002436  min_lr: 0.002436  loss: 2.5914 (2.5127)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0003  max mem: 42573
Epoch: [140]  [150/312]  eta: 0:01:22  lr: 0.002435  min_lr: 0.002435  loss: 2.4730 (2.5167)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [140]  [160/312]  eta: 0:01:16  lr: 0.002434  min_lr: 0.002434  loss: 2.6098 (2.5197)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [140]  [170/312]  eta: 0:01:10  lr: 0.002434  min_lr: 0.002434  loss: 2.5993 (2.5151)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [140]  [180/312]  eta: 0:01:05  lr: 0.002433  min_lr: 0.002433  loss: 2.6332 (2.5238)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [140]  [190/312]  eta: 0:00:59  lr: 0.002432  min_lr: 0.002432  loss: 2.7103 (2.5316)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [140]  [200/312]  eta: 0:00:54  lr: 0.002431  min_lr: 0.002431  loss: 2.7956 (2.5429)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [140]  [210/312]  eta: 0:00:49  lr: 0.002431  min_lr: 0.002431  loss: 2.6550 (2.5387)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0003  max mem: 42573
Epoch: [140]  [220/312]  eta: 0:00:44  lr: 0.002430  min_lr: 0.002430  loss: 2.5299 (2.5375)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [140]  [230/312]  eta: 0:00:39  lr: 0.002429  min_lr: 0.002429  loss: 2.5913 (2.5412)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [140]  [240/312]  eta: 0:00:34  lr: 0.002429  min_lr: 0.002429  loss: 2.6874 (2.5450)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [140]  [250/312]  eta: 0:00:29  lr: 0.002428  min_lr: 0.002428  loss: 2.5313 (2.5325)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [140]  [260/312]  eta: 0:00:24  lr: 0.002427  min_lr: 0.002427  loss: 2.5137 (2.5339)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [140]  [270/312]  eta: 0:00:19  lr: 0.002426  min_lr: 0.002426  loss: 2.6415 (2.5329)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [140]  [280/312]  eta: 0:00:15  lr: 0.002426  min_lr: 0.002426  loss: 2.6132 (2.5327)  weight_decay: 0.0500 (0.0500)  time: 0.4344  data: 0.0012  max mem: 42573
Epoch: [140]  [290/312]  eta: 0:00:10  lr: 0.002425  min_lr: 0.002425  loss: 2.5685 (2.5341)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0010  max mem: 42573
Epoch: [140]  [300/312]  eta: 0:00:05  lr: 0.002424  min_lr: 0.002424  loss: 2.5665 (2.5310)  weight_decay: 0.0500 (0.0500)  time: 0.4323  data: 0.0001  max mem: 42573
Epoch: [140]  [310/312]  eta: 0:00:00  lr: 0.002424  min_lr: 0.002424  loss: 2.5079 (2.5289)  weight_decay: 0.0500 (0.0500)  time: 0.4323  data: 0.0001  max mem: 42573
Epoch: [140]  [311/312]  eta: 0:00:00  lr: 0.002424  min_lr: 0.002424  loss: 2.5267 (2.5289)  weight_decay: 0.0500 (0.0500)  time: 0.4323  data: 0.0001  max mem: 42573
Epoch: [140] Total time: 0:02:27 (0.4718 s / it)
Averaged stats: lr: 0.002424  min_lr: 0.002424  loss: 2.5267 (2.5008)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:00:42  loss: 0.8456 (0.8456)  acc1: 79.1667 (79.1667)  acc5: 93.2292 (93.2292)  time: 4.6960  data: 4.5866  max mem: 42573
Test:  [8/9]  eta: 0:00:00  loss: 1.2240 (1.1133)  acc1: 69.0104 (71.3600)  acc5: 90.3646 (90.4960)  time: 0.6088  data: 0.5172  max mem: 42573
Test: Total time: 0:00:05 (0.6160 s / it)
* Acc@1 71.358 Acc@5 90.474 loss 1.129
Accuracy of the model on the 50000 test images: 71.4%
Max accuracy: 72.09%
Epoch: [141]  [  0/312]  eta: 0:48:35  lr: 0.002424  min_lr: 0.002424  loss: 2.8384 (2.8384)  weight_decay: 0.0500 (0.0500)  time: 9.3441  data: 5.6807  max mem: 42573
Epoch: [141]  [ 10/312]  eta: 0:07:28  lr: 0.002423  min_lr: 0.002423  loss: 2.4916 (2.4686)  weight_decay: 0.0500 (0.0500)  time: 1.4852  data: 0.7129  max mem: 42573
Epoch: [141]  [ 20/312]  eta: 0:04:47  lr: 0.002422  min_lr: 0.002422  loss: 2.5737 (2.5447)  weight_decay: 0.0500 (0.0500)  time: 0.5662  data: 0.1083  max mem: 42573
Epoch: [141]  [ 30/312]  eta: 0:03:47  lr: 0.002421  min_lr: 0.002421  loss: 2.5846 (2.5039)  weight_decay: 0.0500 (0.0500)  time: 0.4331  data: 0.0004  max mem: 42573
Epoch: [141]  [ 40/312]  eta: 0:03:15  lr: 0.002421  min_lr: 0.002421  loss: 2.5240 (2.4995)  weight_decay: 0.0500 (0.0500)  time: 0.4379  data: 0.0003  max mem: 42573
Epoch: [141]  [ 50/312]  eta: 0:02:53  lr: 0.002420  min_lr: 0.002420  loss: 2.5749 (2.5150)  weight_decay: 0.0500 (0.0500)  time: 0.4380  data: 0.0004  max mem: 42573
Epoch: [141]  [ 60/312]  eta: 0:02:37  lr: 0.002419  min_lr: 0.002419  loss: 2.6404 (2.5315)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [141]  [ 70/312]  eta: 0:02:24  lr: 0.002419  min_lr: 0.002419  loss: 2.6250 (2.5345)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [141]  [ 80/312]  eta: 0:02:13  lr: 0.002418  min_lr: 0.002418  loss: 2.5261 (2.5221)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [141]  [ 90/312]  eta: 0:02:04  lr: 0.002417  min_lr: 0.002417  loss: 2.4894 (2.5199)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [141]  [100/312]  eta: 0:01:56  lr: 0.002417  min_lr: 0.002417  loss: 2.5815 (2.5116)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [141]  [110/312]  eta: 0:01:48  lr: 0.002416  min_lr: 0.002416  loss: 2.5188 (2.5138)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [141]  [120/312]  eta: 0:01:41  lr: 0.002415  min_lr: 0.002415  loss: 2.4522 (2.4986)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0005  max mem: 42573
Epoch: [141]  [130/312]  eta: 0:01:35  lr: 0.002414  min_lr: 0.002414  loss: 2.3503 (2.4862)  weight_decay: 0.0500 (0.0500)  time: 0.4341  data: 0.0004  max mem: 42573
Epoch: [141]  [140/312]  eta: 0:01:28  lr: 0.002414  min_lr: 0.002414  loss: 2.4190 (2.4933)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0005  max mem: 42573
Epoch: [141]  [150/312]  eta: 0:01:22  lr: 0.002413  min_lr: 0.002413  loss: 2.4857 (2.4843)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0005  max mem: 42573
Epoch: [141]  [160/312]  eta: 0:01:16  lr: 0.002412  min_lr: 0.002412  loss: 2.5783 (2.4890)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [141]  [170/312]  eta: 0:01:11  lr: 0.002412  min_lr: 0.002412  loss: 2.6247 (2.4838)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [141]  [180/312]  eta: 0:01:05  lr: 0.002411  min_lr: 0.002411  loss: 2.4408 (2.4862)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [141]  [190/312]  eta: 0:01:00  lr: 0.002410  min_lr: 0.002410  loss: 2.5351 (2.4875)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [141]  [200/312]  eta: 0:00:55  lr: 0.002409  min_lr: 0.002409  loss: 2.5343 (2.4819)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0003  max mem: 42573
Epoch: [141]  [210/312]  eta: 0:00:49  lr: 0.002409  min_lr: 0.002409  loss: 2.2662 (2.4734)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0003  max mem: 42573
Epoch: [141]  [220/312]  eta: 0:00:44  lr: 0.002408  min_lr: 0.002408  loss: 2.5297 (2.4741)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [141]  [230/312]  eta: 0:00:39  lr: 0.002407  min_lr: 0.002407  loss: 2.6558 (2.4780)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [141]  [240/312]  eta: 0:00:34  lr: 0.002407  min_lr: 0.002407  loss: 2.6558 (2.4799)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [141]  [250/312]  eta: 0:00:29  lr: 0.002406  min_lr: 0.002406  loss: 2.5128 (2.4802)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [141]  [260/312]  eta: 0:00:24  lr: 0.002405  min_lr: 0.002405  loss: 2.4646 (2.4769)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [141]  [270/312]  eta: 0:00:20  lr: 0.002405  min_lr: 0.002405  loss: 2.2289 (2.4721)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [141]  [280/312]  eta: 0:00:15  lr: 0.002404  min_lr: 0.002404  loss: 2.6126 (2.4780)  weight_decay: 0.0500 (0.0500)  time: 0.4345  data: 0.0015  max mem: 42573
Epoch: [141]  [290/312]  eta: 0:00:10  lr: 0.002403  min_lr: 0.002403  loss: 2.6121 (2.4766)  weight_decay: 0.0500 (0.0500)  time: 0.4341  data: 0.0014  max mem: 42573
Epoch: [141]  [300/312]  eta: 0:00:05  lr: 0.002402  min_lr: 0.002402  loss: 2.5790 (2.4808)  weight_decay: 0.0500 (0.0500)  time: 0.4326  data: 0.0001  max mem: 42573
Epoch: [141]  [310/312]  eta: 0:00:00  lr: 0.002402  min_lr: 0.002402  loss: 2.5790 (2.4786)  weight_decay: 0.0500 (0.0500)  time: 0.4323  data: 0.0001  max mem: 42573
Epoch: [141]  [311/312]  eta: 0:00:00  lr: 0.002402  min_lr: 0.002402  loss: 2.6310 (2.4797)  weight_decay: 0.0500 (0.0500)  time: 0.4323  data: 0.0001  max mem: 42573
Epoch: [141] Total time: 0:02:27 (0.4739 s / it)
Averaged stats: lr: 0.002402  min_lr: 0.002402  loss: 2.6310 (2.5018)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:00:48  loss: 0.9253 (0.9253)  acc1: 76.5625 (76.5625)  acc5: 91.9271 (91.9271)  time: 5.3729  data: 5.2636  max mem: 42573
Test:  [8/9]  eta: 0:00:00  loss: 1.1452 (1.1150)  acc1: 72.9167 (71.5520)  acc5: 89.5833 (90.3680)  time: 0.6729  data: 0.5849  max mem: 42573
Test: Total time: 0:00:06 (0.6997 s / it)
* Acc@1 72.506 Acc@5 90.722 loss 1.107
Accuracy of the model on the 50000 test images: 72.5%
Max accuracy: 72.51%
Epoch: [142]  [  0/312]  eta: 0:49:25  lr: 0.002402  min_lr: 0.002402  loss: 2.0591 (2.0591)  weight_decay: 0.0500 (0.0500)  time: 9.5044  data: 7.3138  max mem: 42573
Epoch: [142]  [ 10/312]  eta: 0:07:18  lr: 0.002401  min_lr: 0.002401  loss: 2.6756 (2.6966)  weight_decay: 0.0500 (0.0500)  time: 1.4509  data: 0.6653  max mem: 42573
Epoch: [142]  [ 20/312]  eta: 0:04:42  lr: 0.002400  min_lr: 0.002400  loss: 2.6633 (2.6065)  weight_decay: 0.0500 (0.0500)  time: 0.5391  data: 0.0004  max mem: 42573
Epoch: [142]  [ 30/312]  eta: 0:03:43  lr: 0.002399  min_lr: 0.002399  loss: 2.5589 (2.5436)  weight_decay: 0.0500 (0.0500)  time: 0.4328  data: 0.0003  max mem: 42573
Epoch: [142]  [ 40/312]  eta: 0:03:12  lr: 0.002399  min_lr: 0.002399  loss: 2.6266 (2.5738)  weight_decay: 0.0500 (0.0500)  time: 0.4331  data: 0.0003  max mem: 42573
Epoch: [142]  [ 50/312]  eta: 0:02:50  lr: 0.002398  min_lr: 0.002398  loss: 2.6812 (2.5292)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [142]  [ 60/312]  eta: 0:02:35  lr: 0.002397  min_lr: 0.002397  loss: 2.5388 (2.5130)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [142]  [ 70/312]  eta: 0:02:23  lr: 0.002397  min_lr: 0.002397  loss: 2.5399 (2.5166)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [142]  [ 80/312]  eta: 0:02:12  lr: 0.002396  min_lr: 0.002396  loss: 2.5466 (2.5139)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [142]  [ 90/312]  eta: 0:02:03  lr: 0.002395  min_lr: 0.002395  loss: 2.4828 (2.4898)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [142]  [100/312]  eta: 0:01:55  lr: 0.002395  min_lr: 0.002395  loss: 2.4741 (2.4829)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [142]  [110/312]  eta: 0:01:47  lr: 0.002394  min_lr: 0.002394  loss: 2.6140 (2.4880)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [142]  [120/312]  eta: 0:01:40  lr: 0.002393  min_lr: 0.002393  loss: 2.6140 (2.4631)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [142]  [130/312]  eta: 0:01:34  lr: 0.002392  min_lr: 0.002392  loss: 2.2567 (2.4606)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [142]  [140/312]  eta: 0:01:28  lr: 0.002392  min_lr: 0.002392  loss: 2.6466 (2.4748)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [142]  [150/312]  eta: 0:01:22  lr: 0.002391  min_lr: 0.002391  loss: 2.6466 (2.4842)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [142]  [160/312]  eta: 0:01:16  lr: 0.002390  min_lr: 0.002390  loss: 2.4836 (2.4778)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [142]  [170/312]  eta: 0:01:10  lr: 0.002390  min_lr: 0.002390  loss: 2.4662 (2.4834)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [142]  [180/312]  eta: 0:01:05  lr: 0.002389  min_lr: 0.002389  loss: 2.6589 (2.4837)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [142]  [190/312]  eta: 0:01:00  lr: 0.002388  min_lr: 0.002388  loss: 2.4386 (2.4765)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [142]  [200/312]  eta: 0:00:54  lr: 0.002387  min_lr: 0.002387  loss: 2.4386 (2.4755)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [142]  [210/312]  eta: 0:00:49  lr: 0.002387  min_lr: 0.002387  loss: 2.5927 (2.4713)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [142]  [220/312]  eta: 0:00:44  lr: 0.002386  min_lr: 0.002386  loss: 2.5927 (2.4686)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [142]  [230/312]  eta: 0:00:39  lr: 0.002385  min_lr: 0.002385  loss: 2.6509 (2.4756)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [142]  [240/312]  eta: 0:00:34  lr: 0.002385  min_lr: 0.002385  loss: 2.6509 (2.4795)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [142]  [250/312]  eta: 0:00:29  lr: 0.002384  min_lr: 0.002384  loss: 2.5278 (2.4856)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [142]  [260/312]  eta: 0:00:24  lr: 0.002383  min_lr: 0.002383  loss: 2.5278 (2.4817)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [142]  [270/312]  eta: 0:00:19  lr: 0.002383  min_lr: 0.002383  loss: 2.5246 (2.4809)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [142]  [280/312]  eta: 0:00:15  lr: 0.002382  min_lr: 0.002382  loss: 2.5286 (2.4766)  weight_decay: 0.0500 (0.0500)  time: 0.4347  data: 0.0009  max mem: 42573
Epoch: [142]  [290/312]  eta: 0:00:10  lr: 0.002381  min_lr: 0.002381  loss: 2.5513 (2.4810)  weight_decay: 0.0500 (0.0500)  time: 0.4341  data: 0.0008  max mem: 42573
Epoch: [142]  [300/312]  eta: 0:00:05  lr: 0.002380  min_lr: 0.002380  loss: 2.6657 (2.4854)  weight_decay: 0.0500 (0.0500)  time: 0.4325  data: 0.0001  max mem: 42573
Epoch: [142]  [310/312]  eta: 0:00:00  lr: 0.002380  min_lr: 0.002380  loss: 2.5370 (2.4825)  weight_decay: 0.0500 (0.0500)  time: 0.4323  data: 0.0001  max mem: 42573
Epoch: [142]  [311/312]  eta: 0:00:00  lr: 0.002380  min_lr: 0.002380  loss: 2.5370 (2.4829)  weight_decay: 0.0500 (0.0500)  time: 0.4323  data: 0.0001  max mem: 42573
Epoch: [142] Total time: 0:02:27 (0.4723 s / it)
Averaged stats: lr: 0.002380  min_lr: 0.002380  loss: 2.5370 (2.4943)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:00:45  loss: 0.9205 (0.9205)  acc1: 77.8646 (77.8646)  acc5: 92.4479 (92.4479)  time: 5.0022  data: 4.8927  max mem: 42573
Test:  [8/9]  eta: 0:00:00  loss: 1.2108 (1.1413)  acc1: 72.1354 (71.5520)  acc5: 91.6667 (90.7840)  time: 0.6329  data: 0.5437  max mem: 42573
Test: Total time: 0:00:05 (0.6429 s / it)
* Acc@1 72.208 Acc@5 90.878 loss 1.148
Accuracy of the model on the 50000 test images: 72.2%
Max accuracy: 72.51%
Epoch: [143]  [  0/312]  eta: 0:48:06  lr: 0.002380  min_lr: 0.002380  loss: 2.7028 (2.7028)  weight_decay: 0.0500 (0.0500)  time: 9.2500  data: 7.4799  max mem: 42573
Epoch: [143]  [ 10/312]  eta: 0:07:09  lr: 0.002379  min_lr: 0.002379  loss: 2.7028 (2.6346)  weight_decay: 0.0500 (0.0500)  time: 1.4217  data: 0.7802  max mem: 42573
Epoch: [143]  [ 20/312]  eta: 0:04:37  lr: 0.002378  min_lr: 0.002378  loss: 2.4255 (2.5360)  weight_decay: 0.0500 (0.0500)  time: 0.5361  data: 0.0553  max mem: 42573
Epoch: [143]  [ 30/312]  eta: 0:03:41  lr: 0.002377  min_lr: 0.002377  loss: 2.3397 (2.4486)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [143]  [ 40/312]  eta: 0:03:09  lr: 0.002377  min_lr: 0.002377  loss: 2.3865 (2.5011)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [143]  [ 50/312]  eta: 0:02:49  lr: 0.002376  min_lr: 0.002376  loss: 2.5886 (2.5323)  weight_decay: 0.0500 (0.0500)  time: 0.4332  data: 0.0004  max mem: 42573
Epoch: [143]  [ 60/312]  eta: 0:02:34  lr: 0.002375  min_lr: 0.002375  loss: 2.5755 (2.5257)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [143]  [ 70/312]  eta: 0:02:21  lr: 0.002375  min_lr: 0.002375  loss: 2.5489 (2.5170)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [143]  [ 80/312]  eta: 0:02:11  lr: 0.002374  min_lr: 0.002374  loss: 2.5489 (2.5168)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0004  max mem: 42573
Epoch: [143]  [ 90/312]  eta: 0:02:02  lr: 0.002373  min_lr: 0.002373  loss: 2.6932 (2.5228)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [143]  [100/312]  eta: 0:01:54  lr: 0.002373  min_lr: 0.002373  loss: 2.6932 (2.5104)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0003  max mem: 42573
Epoch: [143]  [110/312]  eta: 0:01:47  lr: 0.002372  min_lr: 0.002372  loss: 2.5115 (2.5113)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [143]  [120/312]  eta: 0:01:40  lr: 0.002371  min_lr: 0.002371  loss: 2.5616 (2.5251)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [143]  [130/312]  eta: 0:01:34  lr: 0.002370  min_lr: 0.002370  loss: 2.5896 (2.5320)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [143]  [140/312]  eta: 0:01:27  lr: 0.002370  min_lr: 0.002370  loss: 2.5954 (2.5292)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0003  max mem: 42573
Epoch: [143]  [150/312]  eta: 0:01:21  lr: 0.002369  min_lr: 0.002369  loss: 2.4987 (2.5189)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0003  max mem: 42573
Epoch: [143]  [160/312]  eta: 0:01:16  lr: 0.002368  min_lr: 0.002368  loss: 2.5231 (2.5221)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0003  max mem: 42573
Epoch: [143]  [170/312]  eta: 0:01:10  lr: 0.002368  min_lr: 0.002368  loss: 2.6547 (2.5272)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [143]  [180/312]  eta: 0:01:05  lr: 0.002367  min_lr: 0.002367  loss: 2.6547 (2.5273)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [143]  [190/312]  eta: 0:00:59  lr: 0.002366  min_lr: 0.002366  loss: 2.7076 (2.5280)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [143]  [200/312]  eta: 0:00:54  lr: 0.002365  min_lr: 0.002365  loss: 2.7415 (2.5377)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [143]  [210/312]  eta: 0:00:49  lr: 0.002365  min_lr: 0.002365  loss: 2.8020 (2.5451)  weight_decay: 0.0500 (0.0500)  time: 0.4341  data: 0.0004  max mem: 42573
Epoch: [143]  [220/312]  eta: 0:00:44  lr: 0.002364  min_lr: 0.002364  loss: 2.5637 (2.5368)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0004  max mem: 42573
Epoch: [143]  [230/312]  eta: 0:00:39  lr: 0.002363  min_lr: 0.002363  loss: 2.3302 (2.5321)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [143]  [240/312]  eta: 0:00:34  lr: 0.002363  min_lr: 0.002363  loss: 2.5196 (2.5302)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [143]  [250/312]  eta: 0:00:29  lr: 0.002362  min_lr: 0.002362  loss: 2.5896 (2.5343)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [143]  [260/312]  eta: 0:00:24  lr: 0.002361  min_lr: 0.002361  loss: 2.5896 (2.5350)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [143]  [270/312]  eta: 0:00:19  lr: 0.002360  min_lr: 0.002360  loss: 2.4980 (2.5291)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [143]  [280/312]  eta: 0:00:15  lr: 0.002360  min_lr: 0.002360  loss: 2.5259 (2.5313)  weight_decay: 0.0500 (0.0500)  time: 0.4345  data: 0.0009  max mem: 42573
Epoch: [143]  [290/312]  eta: 0:00:10  lr: 0.002359  min_lr: 0.002359  loss: 2.5694 (2.5243)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0008  max mem: 42573
Epoch: [143]  [300/312]  eta: 0:00:05  lr: 0.002358  min_lr: 0.002358  loss: 2.3127 (2.5205)  weight_decay: 0.0500 (0.0500)  time: 0.4323  data: 0.0001  max mem: 42573
Epoch: [143]  [310/312]  eta: 0:00:00  lr: 0.002358  min_lr: 0.002358  loss: 2.6527 (2.5231)  weight_decay: 0.0500 (0.0500)  time: 0.4323  data: 0.0001  max mem: 42573
Epoch: [143]  [311/312]  eta: 0:00:00  lr: 0.002358  min_lr: 0.002358  loss: 2.6527 (2.5234)  weight_decay: 0.0500 (0.0500)  time: 0.4323  data: 0.0001  max mem: 42573
Epoch: [143] Total time: 0:02:27 (0.4714 s / it)
Averaged stats: lr: 0.002358  min_lr: 0.002358  loss: 2.6527 (2.4957)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:00:40  loss: 0.8892 (0.8892)  acc1: 79.6875 (79.6875)  acc5: 92.7083 (92.7083)  time: 4.5327  data: 4.4244  max mem: 42573
Test:  [8/9]  eta: 0:00:00  loss: 1.1943 (1.1259)  acc1: 71.8750 (71.4240)  acc5: 91.1458 (90.8480)  time: 0.5878  data: 0.4995  max mem: 42573
Test: Total time: 0:00:05 (0.5966 s / it)
* Acc@1 72.124 Acc@5 90.776 loss 1.127
Accuracy of the model on the 50000 test images: 72.1%
Max accuracy: 72.51%
Epoch: [144]  [  0/312]  eta: 0:51:05  lr: 0.002358  min_lr: 0.002358  loss: 1.6854 (1.6854)  weight_decay: 0.0500 (0.0500)  time: 9.8238  data: 6.5994  max mem: 42573
Epoch: [144]  [ 10/312]  eta: 0:07:09  lr: 0.002357  min_lr: 0.002357  loss: 2.4890 (2.4107)  weight_decay: 0.0500 (0.0500)  time: 1.4217  data: 0.7061  max mem: 42573
Epoch: [144]  [ 20/312]  eta: 0:04:37  lr: 0.002356  min_lr: 0.002356  loss: 2.4327 (2.3834)  weight_decay: 0.0500 (0.0500)  time: 0.5074  data: 0.0586  max mem: 42573
Epoch: [144]  [ 30/312]  eta: 0:03:41  lr: 0.002355  min_lr: 0.002355  loss: 2.4663 (2.4593)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [144]  [ 40/312]  eta: 0:03:09  lr: 0.002355  min_lr: 0.002355  loss: 2.5174 (2.4374)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [144]  [ 50/312]  eta: 0:02:49  lr: 0.002354  min_lr: 0.002354  loss: 2.6772 (2.5029)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [144]  [ 60/312]  eta: 0:02:34  lr: 0.002353  min_lr: 0.002353  loss: 2.7610 (2.5175)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [144]  [ 70/312]  eta: 0:02:21  lr: 0.002353  min_lr: 0.002353  loss: 2.6156 (2.5069)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [144]  [ 80/312]  eta: 0:02:11  lr: 0.002352  min_lr: 0.002352  loss: 2.6156 (2.5223)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0003  max mem: 42573
Epoch: [144]  [ 90/312]  eta: 0:02:02  lr: 0.002351  min_lr: 0.002351  loss: 2.5908 (2.5181)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [144]  [100/312]  eta: 0:01:54  lr: 0.002350  min_lr: 0.002350  loss: 2.4949 (2.5096)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [144]  [110/312]  eta: 0:01:47  lr: 0.002350  min_lr: 0.002350  loss: 2.3948 (2.4888)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [144]  [120/312]  eta: 0:01:40  lr: 0.002349  min_lr: 0.002349  loss: 2.2549 (2.4752)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [144]  [130/312]  eta: 0:01:34  lr: 0.002348  min_lr: 0.002348  loss: 2.5659 (2.4786)  weight_decay: 0.0500 (0.0500)  time: 0.4396  data: 0.0004  max mem: 42573
Epoch: [144]  [140/312]  eta: 0:01:27  lr: 0.002348  min_lr: 0.002348  loss: 2.5537 (2.4735)  weight_decay: 0.0500 (0.0500)  time: 0.4396  data: 0.0004  max mem: 42573
Epoch: [144]  [150/312]  eta: 0:01:22  lr: 0.002347  min_lr: 0.002347  loss: 2.5087 (2.4631)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0003  max mem: 42573
Epoch: [144]  [160/312]  eta: 0:01:16  lr: 0.002346  min_lr: 0.002346  loss: 2.5465 (2.4675)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [144]  [170/312]  eta: 0:01:10  lr: 0.002345  min_lr: 0.002345  loss: 2.5465 (2.4636)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [144]  [180/312]  eta: 0:01:05  lr: 0.002345  min_lr: 0.002345  loss: 2.4623 (2.4614)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [144]  [190/312]  eta: 0:00:59  lr: 0.002344  min_lr: 0.002344  loss: 2.6276 (2.4738)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [144]  [200/312]  eta: 0:00:54  lr: 0.002343  min_lr: 0.002343  loss: 2.6276 (2.4725)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [144]  [210/312]  eta: 0:00:49  lr: 0.002343  min_lr: 0.002343  loss: 2.5193 (2.4689)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [144]  [220/312]  eta: 0:00:44  lr: 0.002342  min_lr: 0.002342  loss: 2.4351 (2.4662)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [144]  [230/312]  eta: 0:00:39  lr: 0.002341  min_lr: 0.002341  loss: 2.2739 (2.4586)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [144]  [240/312]  eta: 0:00:34  lr: 0.002341  min_lr: 0.002341  loss: 2.6094 (2.4672)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [144]  [250/312]  eta: 0:00:29  lr: 0.002340  min_lr: 0.002340  loss: 2.6094 (2.4650)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [144]  [260/312]  eta: 0:00:24  lr: 0.002339  min_lr: 0.002339  loss: 2.3408 (2.4600)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0003  max mem: 42573
Epoch: [144]  [270/312]  eta: 0:00:19  lr: 0.002338  min_lr: 0.002338  loss: 2.4326 (2.4605)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [144]  [280/312]  eta: 0:00:15  lr: 0.002338  min_lr: 0.002338  loss: 2.6927 (2.4642)  weight_decay: 0.0500 (0.0500)  time: 0.4341  data: 0.0009  max mem: 42573
Epoch: [144]  [290/312]  eta: 0:00:10  lr: 0.002337  min_lr: 0.002337  loss: 2.5444 (2.4677)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0008  max mem: 42573
Epoch: [144]  [300/312]  eta: 0:00:05  lr: 0.002336  min_lr: 0.002336  loss: 2.5444 (2.4686)  weight_decay: 0.0500 (0.0500)  time: 0.4325  data: 0.0001  max mem: 42573
Epoch: [144]  [310/312]  eta: 0:00:00  lr: 0.002336  min_lr: 0.002336  loss: 2.5722 (2.4722)  weight_decay: 0.0500 (0.0500)  time: 0.4324  data: 0.0001  max mem: 42573
Epoch: [144]  [311/312]  eta: 0:00:00  lr: 0.002335  min_lr: 0.002335  loss: 2.5722 (2.4718)  weight_decay: 0.0500 (0.0500)  time: 0.4324  data: 0.0001  max mem: 42573
Epoch: [144] Total time: 0:02:27 (0.4718 s / it)
Averaged stats: lr: 0.002335  min_lr: 0.002335  loss: 2.5722 (2.4920)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:00:45  loss: 0.7968 (0.7968)  acc1: 80.2083 (80.2083)  acc5: 93.4896 (93.4896)  time: 5.0313  data: 4.9218  max mem: 42573
Test:  [8/9]  eta: 0:00:00  loss: 1.1717 (1.0964)  acc1: 72.1354 (72.8960)  acc5: 91.6667 (90.6240)  time: 0.6361  data: 0.5469  max mem: 42573
Test: Total time: 0:00:05 (0.6476 s / it)
* Acc@1 72.954 Acc@5 91.066 loss 1.098
Accuracy of the model on the 50000 test images: 73.0%
Max accuracy: 72.95%
Epoch: [145]  [  0/312]  eta: 0:41:01  lr: 0.002335  min_lr: 0.002335  loss: 1.9304 (1.9304)  weight_decay: 0.0500 (0.0500)  time: 7.8907  data: 7.3855  max mem: 42573
Epoch: [145]  [ 10/312]  eta: 0:06:26  lr: 0.002335  min_lr: 0.002335  loss: 2.6992 (2.5148)  weight_decay: 0.0500 (0.0500)  time: 1.2787  data: 0.7732  max mem: 42573
Epoch: [145]  [ 20/312]  eta: 0:04:15  lr: 0.002334  min_lr: 0.002334  loss: 2.5718 (2.4660)  weight_decay: 0.0500 (0.0500)  time: 0.5253  data: 0.0562  max mem: 42573
Epoch: [145]  [ 30/312]  eta: 0:03:26  lr: 0.002333  min_lr: 0.002333  loss: 2.5718 (2.5205)  weight_decay: 0.0500 (0.0500)  time: 0.4331  data: 0.0004  max mem: 42573
Epoch: [145]  [ 40/312]  eta: 0:02:59  lr: 0.002333  min_lr: 0.002333  loss: 2.6719 (2.5080)  weight_decay: 0.0500 (0.0500)  time: 0.4331  data: 0.0004  max mem: 42573
Epoch: [145]  [ 50/312]  eta: 0:02:41  lr: 0.002332  min_lr: 0.002332  loss: 2.5428 (2.5090)  weight_decay: 0.0500 (0.0500)  time: 0.4332  data: 0.0004  max mem: 42573
Epoch: [145]  [ 60/312]  eta: 0:02:27  lr: 0.002331  min_lr: 0.002331  loss: 2.3806 (2.4778)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [145]  [ 70/312]  eta: 0:02:16  lr: 0.002330  min_lr: 0.002330  loss: 2.4140 (2.4823)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [145]  [ 80/312]  eta: 0:02:07  lr: 0.002330  min_lr: 0.002330  loss: 2.4172 (2.4641)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [145]  [ 90/312]  eta: 0:01:58  lr: 0.002329  min_lr: 0.002329  loss: 2.5341 (2.4695)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [145]  [100/312]  eta: 0:01:51  lr: 0.002328  min_lr: 0.002328  loss: 2.5771 (2.4888)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [145]  [110/312]  eta: 0:01:44  lr: 0.002328  min_lr: 0.002328  loss: 2.7197 (2.5036)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [145]  [120/312]  eta: 0:01:37  lr: 0.002327  min_lr: 0.002327  loss: 2.7234 (2.5082)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [145]  [130/312]  eta: 0:01:31  lr: 0.002326  min_lr: 0.002326  loss: 2.5860 (2.5080)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [145]  [140/312]  eta: 0:01:25  lr: 0.002326  min_lr: 0.002326  loss: 2.5743 (2.5104)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [145]  [150/312]  eta: 0:01:20  lr: 0.002325  min_lr: 0.002325  loss: 2.4504 (2.5000)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [145]  [160/312]  eta: 0:01:14  lr: 0.002324  min_lr: 0.002324  loss: 2.4937 (2.5011)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [145]  [170/312]  eta: 0:01:09  lr: 0.002323  min_lr: 0.002323  loss: 2.5470 (2.5010)  weight_decay: 0.0500 (0.0500)  time: 0.4389  data: 0.0004  max mem: 42573
Epoch: [145]  [180/312]  eta: 0:01:04  lr: 0.002323  min_lr: 0.002323  loss: 2.5524 (2.4997)  weight_decay: 0.0500 (0.0500)  time: 0.4388  data: 0.0004  max mem: 42573
Epoch: [145]  [190/312]  eta: 0:00:58  lr: 0.002322  min_lr: 0.002322  loss: 2.6135 (2.5065)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [145]  [200/312]  eta: 0:00:53  lr: 0.002321  min_lr: 0.002321  loss: 2.5305 (2.4969)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [145]  [210/312]  eta: 0:00:48  lr: 0.002321  min_lr: 0.002321  loss: 2.3443 (2.4930)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0003  max mem: 42573
Epoch: [145]  [220/312]  eta: 0:00:43  lr: 0.002320  min_lr: 0.002320  loss: 2.5203 (2.4916)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [145]  [230/312]  eta: 0:00:38  lr: 0.002319  min_lr: 0.002319  loss: 2.4169 (2.4869)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [145]  [240/312]  eta: 0:00:34  lr: 0.002318  min_lr: 0.002318  loss: 2.2548 (2.4834)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [145]  [250/312]  eta: 0:00:29  lr: 0.002318  min_lr: 0.002318  loss: 2.2007 (2.4754)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [145]  [260/312]  eta: 0:00:24  lr: 0.002317  min_lr: 0.002317  loss: 2.4371 (2.4763)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [145]  [270/312]  eta: 0:00:19  lr: 0.002316  min_lr: 0.002316  loss: 2.5262 (2.4789)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [145]  [280/312]  eta: 0:00:14  lr: 0.002316  min_lr: 0.002316  loss: 2.5262 (2.4788)  weight_decay: 0.0500 (0.0500)  time: 0.4345  data: 0.0009  max mem: 42573
Epoch: [145]  [290/312]  eta: 0:00:10  lr: 0.002315  min_lr: 0.002315  loss: 2.5116 (2.4749)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0008  max mem: 42573
Epoch: [145]  [300/312]  eta: 0:00:05  lr: 0.002314  min_lr: 0.002314  loss: 2.6111 (2.4773)  weight_decay: 0.0500 (0.0500)  time: 0.4324  data: 0.0001  max mem: 42573
Epoch: [145]  [310/312]  eta: 0:00:00  lr: 0.002313  min_lr: 0.002313  loss: 2.3410 (2.4729)  weight_decay: 0.0500 (0.0500)  time: 0.4322  data: 0.0001  max mem: 42573
Epoch: [145]  [311/312]  eta: 0:00:00  lr: 0.002313  min_lr: 0.002313  loss: 2.5398 (2.4733)  weight_decay: 0.0500 (0.0500)  time: 0.4322  data: 0.0001  max mem: 42573
Epoch: [145] Total time: 0:02:25 (0.4667 s / it)
Averaged stats: lr: 0.002313  min_lr: 0.002313  loss: 2.5398 (2.4740)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:00:42  loss: 0.8854 (0.8854)  acc1: 78.6458 (78.6458)  acc5: 93.4896 (93.4896)  time: 4.7408  data: 4.6314  max mem: 42573
Test:  [8/9]  eta: 0:00:00  loss: 1.2430 (1.1912)  acc1: 69.5312 (70.5920)  acc5: 90.3646 (89.7280)  time: 0.6030  data: 0.5146  max mem: 42573
Test: Total time: 0:00:05 (0.6232 s / it)
* Acc@1 71.180 Acc@5 90.386 loss 1.167
Accuracy of the model on the 50000 test images: 71.2%
Max accuracy: 72.95%
Epoch: [146]  [  0/312]  eta: 0:46:35  lr: 0.002313  min_lr: 0.002313  loss: 2.6937 (2.6937)  weight_decay: 0.0500 (0.0500)  time: 8.9586  data: 8.3247  max mem: 42573
Epoch: [146]  [ 10/312]  eta: 0:07:04  lr: 0.002313  min_lr: 0.002313  loss: 2.6240 (2.4071)  weight_decay: 0.0500 (0.0500)  time: 1.4049  data: 0.7693  max mem: 42573
Epoch: [146]  [ 20/312]  eta: 0:04:35  lr: 0.002312  min_lr: 0.002312  loss: 2.6240 (2.5147)  weight_decay: 0.0500 (0.0500)  time: 0.5415  data: 0.0071  max mem: 42573
Epoch: [146]  [ 30/312]  eta: 0:03:39  lr: 0.002311  min_lr: 0.002311  loss: 2.5680 (2.5258)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [146]  [ 40/312]  eta: 0:03:08  lr: 0.002310  min_lr: 0.002310  loss: 2.5680 (2.5149)  weight_decay: 0.0500 (0.0500)  time: 0.4332  data: 0.0003  max mem: 42573
Epoch: [146]  [ 50/312]  eta: 0:02:48  lr: 0.002310  min_lr: 0.002310  loss: 2.5385 (2.5057)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [146]  [ 60/312]  eta: 0:02:33  lr: 0.002309  min_lr: 0.002309  loss: 2.3631 (2.4655)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [146]  [ 70/312]  eta: 0:02:21  lr: 0.002308  min_lr: 0.002308  loss: 2.4497 (2.4882)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [146]  [ 80/312]  eta: 0:02:11  lr: 0.002308  min_lr: 0.002308  loss: 2.6828 (2.5119)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0003  max mem: 42573
Epoch: [146]  [ 90/312]  eta: 0:02:02  lr: 0.002307  min_lr: 0.002307  loss: 2.5509 (2.5148)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0003  max mem: 42573
Epoch: [146]  [100/312]  eta: 0:01:54  lr: 0.002306  min_lr: 0.002306  loss: 2.4607 (2.5122)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [146]  [110/312]  eta: 0:01:47  lr: 0.002305  min_lr: 0.002305  loss: 2.5390 (2.5173)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [146]  [120/312]  eta: 0:01:40  lr: 0.002305  min_lr: 0.002305  loss: 2.5412 (2.5176)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [146]  [130/312]  eta: 0:01:33  lr: 0.002304  min_lr: 0.002304  loss: 2.5412 (2.5086)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [146]  [140/312]  eta: 0:01:27  lr: 0.002303  min_lr: 0.002303  loss: 2.3914 (2.5049)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [146]  [150/312]  eta: 0:01:21  lr: 0.002303  min_lr: 0.002303  loss: 2.5112 (2.5145)  weight_decay: 0.0500 (0.0500)  time: 0.4379  data: 0.0004  max mem: 42573
Epoch: [146]  [160/312]  eta: 0:01:16  lr: 0.002302  min_lr: 0.002302  loss: 2.6460 (2.5242)  weight_decay: 0.0500 (0.0500)  time: 0.4380  data: 0.0004  max mem: 42573
Epoch: [146]  [170/312]  eta: 0:01:10  lr: 0.002301  min_lr: 0.002301  loss: 2.6617 (2.5346)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [146]  [180/312]  eta: 0:01:05  lr: 0.002301  min_lr: 0.002301  loss: 2.5802 (2.5292)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [146]  [190/312]  eta: 0:00:59  lr: 0.002300  min_lr: 0.002300  loss: 2.5831 (2.5303)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [146]  [200/312]  eta: 0:00:54  lr: 0.002299  min_lr: 0.002299  loss: 2.5582 (2.5220)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [146]  [210/312]  eta: 0:00:49  lr: 0.002298  min_lr: 0.002298  loss: 2.5582 (2.5213)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [146]  [220/312]  eta: 0:00:44  lr: 0.002298  min_lr: 0.002298  loss: 2.6833 (2.5271)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0004  max mem: 42573
Epoch: [146]  [230/312]  eta: 0:00:39  lr: 0.002297  min_lr: 0.002297  loss: 2.5217 (2.5173)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [146]  [240/312]  eta: 0:00:34  lr: 0.002296  min_lr: 0.002296  loss: 2.4652 (2.5175)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [146]  [250/312]  eta: 0:00:29  lr: 0.002296  min_lr: 0.002296  loss: 2.4931 (2.5191)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0003  max mem: 42573
Epoch: [146]  [260/312]  eta: 0:00:24  lr: 0.002295  min_lr: 0.002295  loss: 2.4928 (2.5169)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [146]  [270/312]  eta: 0:00:19  lr: 0.002294  min_lr: 0.002294  loss: 2.4155 (2.5109)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [146]  [280/312]  eta: 0:00:15  lr: 0.002293  min_lr: 0.002293  loss: 2.5735 (2.5107)  weight_decay: 0.0500 (0.0500)  time: 0.4349  data: 0.0009  max mem: 42573
Epoch: [146]  [290/312]  eta: 0:00:10  lr: 0.002293  min_lr: 0.002293  loss: 2.5735 (2.5083)  weight_decay: 0.0500 (0.0500)  time: 0.4343  data: 0.0008  max mem: 42573
Epoch: [146]  [300/312]  eta: 0:00:05  lr: 0.002292  min_lr: 0.002292  loss: 2.4338 (2.5048)  weight_decay: 0.0500 (0.0500)  time: 0.4325  data: 0.0001  max mem: 42573
Epoch: [146]  [310/312]  eta: 0:00:00  lr: 0.002291  min_lr: 0.002291  loss: 2.5985 (2.5052)  weight_decay: 0.0500 (0.0500)  time: 0.4325  data: 0.0001  max mem: 42573
Epoch: [146]  [311/312]  eta: 0:00:00  lr: 0.002291  min_lr: 0.002291  loss: 2.4612 (2.5050)  weight_decay: 0.0500 (0.0500)  time: 0.4324  data: 0.0001  max mem: 42573
Epoch: [146] Total time: 0:02:27 (0.4713 s / it)
Averaged stats: lr: 0.002291  min_lr: 0.002291  loss: 2.4612 (2.4785)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:00:43  loss: 0.9246 (0.9246)  acc1: 76.8229 (76.8229)  acc5: 92.9688 (92.9688)  time: 4.8086  data: 4.6992  max mem: 42573
Test:  [8/9]  eta: 0:00:00  loss: 1.1940 (1.1595)  acc1: 71.6146 (71.0080)  acc5: 89.0625 (89.9840)  time: 0.6117  data: 0.5222  max mem: 42573
Test: Total time: 0:00:05 (0.6364 s / it)
* Acc@1 71.394 Acc@5 90.320 loss 1.134
Accuracy of the model on the 50000 test images: 71.4%
Max accuracy: 72.95%
Epoch: [147]  [  0/312]  eta: 0:51:05  lr: 0.002291  min_lr: 0.002291  loss: 1.7403 (1.7403)  weight_decay: 0.0500 (0.0500)  time: 9.8246  data: 6.9301  max mem: 42573
Epoch: [147]  [ 10/312]  eta: 0:07:35  lr: 0.002290  min_lr: 0.002290  loss: 1.9219 (2.1733)  weight_decay: 0.0500 (0.0500)  time: 1.5086  data: 0.6783  max mem: 42573
Epoch: [147]  [ 20/312]  eta: 0:04:50  lr: 0.002290  min_lr: 0.002290  loss: 2.5017 (2.3473)  weight_decay: 0.0500 (0.0500)  time: 0.5550  data: 0.0267  max mem: 42573
Epoch: [147]  [ 30/312]  eta: 0:03:49  lr: 0.002289  min_lr: 0.002289  loss: 2.5708 (2.4283)  weight_decay: 0.0500 (0.0500)  time: 0.4332  data: 0.0004  max mem: 42573
Epoch: [147]  [ 40/312]  eta: 0:03:16  lr: 0.002288  min_lr: 0.002288  loss: 2.5819 (2.4471)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [147]  [ 50/312]  eta: 0:02:54  lr: 0.002288  min_lr: 0.002288  loss: 2.5855 (2.4722)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [147]  [ 60/312]  eta: 0:02:38  lr: 0.002287  min_lr: 0.002287  loss: 2.7607 (2.5056)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [147]  [ 70/312]  eta: 0:02:25  lr: 0.002286  min_lr: 0.002286  loss: 2.7607 (2.5282)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [147]  [ 80/312]  eta: 0:02:14  lr: 0.002285  min_lr: 0.002285  loss: 2.6231 (2.5249)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [147]  [ 90/312]  eta: 0:02:05  lr: 0.002285  min_lr: 0.002285  loss: 2.3293 (2.4884)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [147]  [100/312]  eta: 0:01:56  lr: 0.002284  min_lr: 0.002284  loss: 2.2167 (2.4853)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [147]  [110/312]  eta: 0:01:49  lr: 0.002283  min_lr: 0.002283  loss: 2.5291 (2.4868)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [147]  [120/312]  eta: 0:01:42  lr: 0.002283  min_lr: 0.002283  loss: 2.4906 (2.4796)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [147]  [130/312]  eta: 0:01:35  lr: 0.002282  min_lr: 0.002282  loss: 2.4350 (2.4744)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [147]  [140/312]  eta: 0:01:29  lr: 0.002281  min_lr: 0.002281  loss: 2.1385 (2.4461)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0003  max mem: 42573
Epoch: [147]  [150/312]  eta: 0:01:22  lr: 0.002280  min_lr: 0.002280  loss: 2.5493 (2.4676)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [147]  [160/312]  eta: 0:01:17  lr: 0.002280  min_lr: 0.002280  loss: 2.8575 (2.4794)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [147]  [170/312]  eta: 0:01:11  lr: 0.002279  min_lr: 0.002279  loss: 2.5977 (2.4748)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [147]  [180/312]  eta: 0:01:05  lr: 0.002278  min_lr: 0.002278  loss: 2.4224 (2.4756)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [147]  [190/312]  eta: 0:01:00  lr: 0.002278  min_lr: 0.002278  loss: 2.6112 (2.4823)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [147]  [200/312]  eta: 0:00:55  lr: 0.002277  min_lr: 0.002277  loss: 2.6124 (2.4786)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0003  max mem: 42573
Epoch: [147]  [210/312]  eta: 0:00:49  lr: 0.002276  min_lr: 0.002276  loss: 2.4680 (2.4757)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0003  max mem: 42573
Epoch: [147]  [220/312]  eta: 0:00:44  lr: 0.002275  min_lr: 0.002275  loss: 2.5008 (2.4768)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [147]  [230/312]  eta: 0:00:39  lr: 0.002275  min_lr: 0.002275  loss: 2.5008 (2.4728)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [147]  [240/312]  eta: 0:00:34  lr: 0.002274  min_lr: 0.002274  loss: 2.2997 (2.4755)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [147]  [250/312]  eta: 0:00:29  lr: 0.002273  min_lr: 0.002273  loss: 2.6076 (2.4830)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [147]  [260/312]  eta: 0:00:24  lr: 0.002273  min_lr: 0.002273  loss: 2.6023 (2.4768)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [147]  [270/312]  eta: 0:00:20  lr: 0.002272  min_lr: 0.002272  loss: 2.4107 (2.4762)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0003  max mem: 42573
Epoch: [147]  [280/312]  eta: 0:00:15  lr: 0.002271  min_lr: 0.002271  loss: 2.4016 (2.4716)  weight_decay: 0.0500 (0.0500)  time: 0.4343  data: 0.0009  max mem: 42573
Epoch: [147]  [290/312]  eta: 0:00:10  lr: 0.002270  min_lr: 0.002270  loss: 2.1864 (2.4674)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0008  max mem: 42573
Epoch: [147]  [300/312]  eta: 0:00:05  lr: 0.002270  min_lr: 0.002270  loss: 2.1330 (2.4583)  weight_decay: 0.0500 (0.0500)  time: 0.4325  data: 0.0001  max mem: 42573
Epoch: [147]  [310/312]  eta: 0:00:00  lr: 0.002269  min_lr: 0.002269  loss: 2.2773 (2.4617)  weight_decay: 0.0500 (0.0500)  time: 0.4324  data: 0.0001  max mem: 42573
Epoch: [147]  [311/312]  eta: 0:00:00  lr: 0.002269  min_lr: 0.002269  loss: 2.4480 (2.4621)  weight_decay: 0.0500 (0.0500)  time: 0.4324  data: 0.0001  max mem: 42573
Epoch: [147] Total time: 0:02:28 (0.4745 s / it)
Averaged stats: lr: 0.002269  min_lr: 0.002269  loss: 2.4480 (2.4791)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:00:39  loss: 0.8660 (0.8660)  acc1: 81.2500 (81.2500)  acc5: 92.1875 (92.1875)  time: 4.4357  data: 4.3269  max mem: 42573
Test:  [8/9]  eta: 0:00:00  loss: 1.2282 (1.1407)  acc1: 72.3958 (72.5120)  acc5: 91.6667 (90.5920)  time: 0.5989  data: 0.5116  max mem: 42573
Test: Total time: 0:00:05 (0.6064 s / it)
* Acc@1 72.798 Acc@5 90.964 loss 1.120
Accuracy of the model on the 50000 test images: 72.8%
Max accuracy: 72.95%
Epoch: [148]  [  0/312]  eta: 0:51:52  lr: 0.002269  min_lr: 0.002269  loss: 3.0995 (3.0995)  weight_decay: 0.0500 (0.0500)  time: 9.9748  data: 8.3860  max mem: 42573
Epoch: [148]  [ 10/312]  eta: 0:07:24  lr: 0.002268  min_lr: 0.002268  loss: 2.6794 (2.5787)  weight_decay: 0.0500 (0.0500)  time: 1.4702  data: 0.7627  max mem: 42573
Epoch: [148]  [ 20/312]  eta: 0:04:45  lr: 0.002267  min_lr: 0.002267  loss: 2.2675 (2.3842)  weight_decay: 0.0500 (0.0500)  time: 0.5265  data: 0.0004  max mem: 42573
Epoch: [148]  [ 30/312]  eta: 0:03:45  lr: 0.002267  min_lr: 0.002267  loss: 2.2601 (2.4262)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0003  max mem: 42573
Epoch: [148]  [ 40/312]  eta: 0:03:13  lr: 0.002266  min_lr: 0.002266  loss: 2.6176 (2.4510)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0003  max mem: 42573
Epoch: [148]  [ 50/312]  eta: 0:02:52  lr: 0.002265  min_lr: 0.002265  loss: 2.5569 (2.4400)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [148]  [ 60/312]  eta: 0:02:36  lr: 0.002265  min_lr: 0.002265  loss: 2.4279 (2.4553)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [148]  [ 70/312]  eta: 0:02:23  lr: 0.002264  min_lr: 0.002264  loss: 2.4630 (2.4401)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [148]  [ 80/312]  eta: 0:02:13  lr: 0.002263  min_lr: 0.002263  loss: 2.2822 (2.4394)  weight_decay: 0.0500 (0.0500)  time: 0.4381  data: 0.0004  max mem: 42573
Epoch: [148]  [ 90/312]  eta: 0:02:04  lr: 0.002262  min_lr: 0.002262  loss: 2.5618 (2.4377)  weight_decay: 0.0500 (0.0500)  time: 0.4382  data: 0.0004  max mem: 42573
Epoch: [148]  [100/312]  eta: 0:01:56  lr: 0.002262  min_lr: 0.002262  loss: 2.4475 (2.4170)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0003  max mem: 42573
Epoch: [148]  [110/312]  eta: 0:01:48  lr: 0.002261  min_lr: 0.002261  loss: 2.3441 (2.4269)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [148]  [120/312]  eta: 0:01:41  lr: 0.002260  min_lr: 0.002260  loss: 2.6375 (2.4463)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [148]  [130/312]  eta: 0:01:34  lr: 0.002260  min_lr: 0.002260  loss: 2.5935 (2.4546)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [148]  [140/312]  eta: 0:01:28  lr: 0.002259  min_lr: 0.002259  loss: 2.5703 (2.4595)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [148]  [150/312]  eta: 0:01:22  lr: 0.002258  min_lr: 0.002258  loss: 2.7241 (2.4799)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [148]  [160/312]  eta: 0:01:16  lr: 0.002257  min_lr: 0.002257  loss: 2.4286 (2.4643)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0003  max mem: 42573
Epoch: [148]  [170/312]  eta: 0:01:11  lr: 0.002257  min_lr: 0.002257  loss: 2.4286 (2.4783)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [148]  [180/312]  eta: 0:01:05  lr: 0.002256  min_lr: 0.002256  loss: 2.6147 (2.4756)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [148]  [190/312]  eta: 0:01:00  lr: 0.002255  min_lr: 0.002255  loss: 2.6063 (2.4747)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [148]  [200/312]  eta: 0:00:54  lr: 0.002255  min_lr: 0.002255  loss: 2.3645 (2.4671)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [148]  [210/312]  eta: 0:00:49  lr: 0.002254  min_lr: 0.002254  loss: 2.4170 (2.4659)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [148]  [220/312]  eta: 0:00:44  lr: 0.002253  min_lr: 0.002253  loss: 2.4814 (2.4703)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [148]  [230/312]  eta: 0:00:39  lr: 0.002253  min_lr: 0.002253  loss: 2.6013 (2.4728)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [148]  [240/312]  eta: 0:00:34  lr: 0.002252  min_lr: 0.002252  loss: 2.4635 (2.4639)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [148]  [250/312]  eta: 0:00:29  lr: 0.002251  min_lr: 0.002251  loss: 2.3552 (2.4573)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [148]  [260/312]  eta: 0:00:24  lr: 0.002250  min_lr: 0.002250  loss: 2.3512 (2.4512)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [148]  [270/312]  eta: 0:00:19  lr: 0.002250  min_lr: 0.002250  loss: 2.5583 (2.4540)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [148]  [280/312]  eta: 0:00:15  lr: 0.002249  min_lr: 0.002249  loss: 2.6255 (2.4577)  weight_decay: 0.0500 (0.0500)  time: 0.4343  data: 0.0011  max mem: 42573
Epoch: [148]  [290/312]  eta: 0:00:10  lr: 0.002248  min_lr: 0.002248  loss: 2.5345 (2.4545)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0010  max mem: 42573
Epoch: [148]  [300/312]  eta: 0:00:05  lr: 0.002248  min_lr: 0.002248  loss: 2.5803 (2.4584)  weight_decay: 0.0500 (0.0500)  time: 0.4324  data: 0.0001  max mem: 42573
Epoch: [148]  [310/312]  eta: 0:00:00  lr: 0.002247  min_lr: 0.002247  loss: 2.4376 (2.4533)  weight_decay: 0.0500 (0.0500)  time: 0.4323  data: 0.0001  max mem: 42573
Epoch: [148]  [311/312]  eta: 0:00:00  lr: 0.002247  min_lr: 0.002247  loss: 2.4376 (2.4506)  weight_decay: 0.0500 (0.0500)  time: 0.4323  data: 0.0001  max mem: 42573
Epoch: [148] Total time: 0:02:27 (0.4734 s / it)
Averaged stats: lr: 0.002247  min_lr: 0.002247  loss: 2.4376 (2.4694)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:00:39  loss: 0.8790 (0.8790)  acc1: 78.3854 (78.3854)  acc5: 91.4062 (91.4062)  time: 4.3856  data: 4.2776  max mem: 42573
Test:  [8/9]  eta: 0:00:00  loss: 1.2028 (1.1649)  acc1: 71.8750 (70.6880)  acc5: 90.3646 (90.1760)  time: 0.5830  data: 0.4951  max mem: 42573
Test: Total time: 0:00:05 (0.5896 s / it)
* Acc@1 71.724 Acc@5 90.278 loss 1.165
Accuracy of the model on the 50000 test images: 71.7%
Max accuracy: 72.95%
Epoch: [149]  [  0/312]  eta: 0:50:03  lr: 0.002247  min_lr: 0.002247  loss: 1.9310 (1.9310)  weight_decay: 0.0500 (0.0500)  time: 9.6277  data: 9.1345  max mem: 42573
Epoch: [149]  [ 10/312]  eta: 0:07:15  lr: 0.002246  min_lr: 0.002246  loss: 2.0970 (2.2068)  weight_decay: 0.0500 (0.0500)  time: 1.4408  data: 0.8308  max mem: 42573
Epoch: [149]  [ 20/312]  eta: 0:04:40  lr: 0.002245  min_lr: 0.002245  loss: 2.3277 (2.3689)  weight_decay: 0.0500 (0.0500)  time: 0.5276  data: 0.0004  max mem: 42573
Epoch: [149]  [ 30/312]  eta: 0:03:43  lr: 0.002245  min_lr: 0.002245  loss: 2.5715 (2.3865)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0003  max mem: 42573
Epoch: [149]  [ 40/312]  eta: 0:03:11  lr: 0.002244  min_lr: 0.002244  loss: 2.5296 (2.3719)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0003  max mem: 42573
Epoch: [149]  [ 50/312]  eta: 0:02:50  lr: 0.002243  min_lr: 0.002243  loss: 2.3130 (2.3685)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [149]  [ 60/312]  eta: 0:02:34  lr: 0.002242  min_lr: 0.002242  loss: 2.5998 (2.4115)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [149]  [ 70/312]  eta: 0:02:22  lr: 0.002242  min_lr: 0.002242  loss: 2.6846 (2.4390)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [149]  [ 80/312]  eta: 0:02:12  lr: 0.002241  min_lr: 0.002241  loss: 2.6720 (2.4564)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [149]  [ 90/312]  eta: 0:02:03  lr: 0.002240  min_lr: 0.002240  loss: 2.6121 (2.4554)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [149]  [100/312]  eta: 0:01:55  lr: 0.002240  min_lr: 0.002240  loss: 2.5374 (2.4609)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0003  max mem: 42573
Epoch: [149]  [110/312]  eta: 0:01:47  lr: 0.002239  min_lr: 0.002239  loss: 2.6046 (2.4694)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [149]  [120/312]  eta: 0:01:40  lr: 0.002238  min_lr: 0.002238  loss: 2.5125 (2.4642)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [149]  [130/312]  eta: 0:01:34  lr: 0.002237  min_lr: 0.002237  loss: 2.5566 (2.4707)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [149]  [140/312]  eta: 0:01:28  lr: 0.002237  min_lr: 0.002237  loss: 2.6187 (2.4753)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [149]  [150/312]  eta: 0:01:22  lr: 0.002236  min_lr: 0.002236  loss: 2.6375 (2.4735)  weight_decay: 0.0500 (0.0500)  time: 0.4384  data: 0.0004  max mem: 42573
Epoch: [149]  [160/312]  eta: 0:01:16  lr: 0.002235  min_lr: 0.002235  loss: 2.5943 (2.4782)  weight_decay: 0.0500 (0.0500)  time: 0.4384  data: 0.0004  max mem: 42573
Epoch: [149]  [170/312]  eta: 0:01:10  lr: 0.002235  min_lr: 0.002235  loss: 2.5943 (2.4882)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [149]  [180/312]  eta: 0:01:05  lr: 0.002234  min_lr: 0.002234  loss: 2.4269 (2.4710)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0003  max mem: 42573
Epoch: [149]  [190/312]  eta: 0:01:00  lr: 0.002233  min_lr: 0.002233  loss: 2.4269 (2.4706)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0003  max mem: 42573
Epoch: [149]  [200/312]  eta: 0:00:54  lr: 0.002232  min_lr: 0.002232  loss: 2.5107 (2.4663)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [149]  [210/312]  eta: 0:00:49  lr: 0.002232  min_lr: 0.002232  loss: 2.4192 (2.4615)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [149]  [220/312]  eta: 0:00:44  lr: 0.002231  min_lr: 0.002231  loss: 2.4717 (2.4635)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [149]  [230/312]  eta: 0:00:39  lr: 0.002230  min_lr: 0.002230  loss: 2.6186 (2.4645)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0003  max mem: 42573
Epoch: [149]  [240/312]  eta: 0:00:34  lr: 0.002230  min_lr: 0.002230  loss: 2.6566 (2.4631)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [149]  [250/312]  eta: 0:00:29  lr: 0.002229  min_lr: 0.002229  loss: 2.6665 (2.4681)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [149]  [260/312]  eta: 0:00:24  lr: 0.002228  min_lr: 0.002228  loss: 2.6665 (2.4710)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [149]  [270/312]  eta: 0:00:19  lr: 0.002227  min_lr: 0.002227  loss: 2.4510 (2.4693)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [149]  [280/312]  eta: 0:00:15  lr: 0.002227  min_lr: 0.002227  loss: 2.5231 (2.4758)  weight_decay: 0.0500 (0.0500)  time: 0.4341  data: 0.0009  max mem: 42573
Epoch: [149]  [290/312]  eta: 0:00:10  lr: 0.002226  min_lr: 0.002226  loss: 2.6308 (2.4775)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0008  max mem: 42573
Epoch: [149]  [300/312]  eta: 0:00:05  lr: 0.002225  min_lr: 0.002225  loss: 2.3707 (2.4772)  weight_decay: 0.0500 (0.0500)  time: 0.4324  data: 0.0001  max mem: 42573
Epoch: [149]  [310/312]  eta: 0:00:00  lr: 0.002225  min_lr: 0.002225  loss: 2.5426 (2.4811)  weight_decay: 0.0500 (0.0500)  time: 0.4324  data: 0.0001  max mem: 42573
Epoch: [149]  [311/312]  eta: 0:00:00  lr: 0.002224  min_lr: 0.002224  loss: 2.5426 (2.4802)  weight_decay: 0.0500 (0.0500)  time: 0.4324  data: 0.0001  max mem: 42573
Epoch: [149] Total time: 0:02:27 (0.4722 s / it)
Averaged stats: lr: 0.002224  min_lr: 0.002224  loss: 2.5426 (2.4619)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:00:46  loss: 0.8582 (0.8582)  acc1: 78.9062 (78.9062)  acc5: 94.2708 (94.2708)  time: 5.1134  data: 5.0039  max mem: 42573
Test:  [8/9]  eta: 0:00:00  loss: 1.2829 (1.1614)  acc1: 70.3125 (71.0400)  acc5: 90.3646 (90.8480)  time: 0.6448  data: 0.5561  max mem: 42573
Test: Total time: 0:00:05 (0.6629 s / it)
* Acc@1 72.480 Acc@5 90.898 loss 1.145
Accuracy of the model on the 50000 test images: 72.5%
Max accuracy: 72.95%
Epoch: [150]  [  0/312]  eta: 0:48:05  lr: 0.002224  min_lr: 0.002224  loss: 2.4386 (2.4386)  weight_decay: 0.0500 (0.0500)  time: 9.2495  data: 7.4400  max mem: 42573
Epoch: [150]  [ 10/312]  eta: 0:06:58  lr: 0.002224  min_lr: 0.002224  loss: 2.4849 (2.4448)  weight_decay: 0.0500 (0.0500)  time: 1.3854  data: 0.7216  max mem: 42573
Epoch: [150]  [ 20/312]  eta: 0:04:32  lr: 0.002223  min_lr: 0.002223  loss: 2.6082 (2.6122)  weight_decay: 0.0500 (0.0500)  time: 0.5173  data: 0.0251  max mem: 42573
Epoch: [150]  [ 30/312]  eta: 0:03:37  lr: 0.002222  min_lr: 0.002222  loss: 2.5700 (2.5228)  weight_decay: 0.0500 (0.0500)  time: 0.4344  data: 0.0004  max mem: 42573
Epoch: [150]  [ 40/312]  eta: 0:03:07  lr: 0.002222  min_lr: 0.002222  loss: 2.4059 (2.5070)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [150]  [ 50/312]  eta: 0:02:47  lr: 0.002221  min_lr: 0.002221  loss: 2.6267 (2.5057)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [150]  [ 60/312]  eta: 0:02:32  lr: 0.002220  min_lr: 0.002220  loss: 2.5888 (2.4946)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [150]  [ 70/312]  eta: 0:02:20  lr: 0.002219  min_lr: 0.002219  loss: 2.3923 (2.4680)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [150]  [ 80/312]  eta: 0:02:10  lr: 0.002219  min_lr: 0.002219  loss: 2.3694 (2.4788)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [150]  [ 90/312]  eta: 0:02:01  lr: 0.002218  min_lr: 0.002218  loss: 2.3802 (2.4817)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [150]  [100/312]  eta: 0:01:53  lr: 0.002217  min_lr: 0.002217  loss: 2.4654 (2.4730)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [150]  [110/312]  eta: 0:01:46  lr: 0.002217  min_lr: 0.002217  loss: 2.6431 (2.4868)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [150]  [120/312]  eta: 0:01:39  lr: 0.002216  min_lr: 0.002216  loss: 2.6739 (2.4942)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [150]  [130/312]  eta: 0:01:33  lr: 0.002215  min_lr: 0.002215  loss: 2.3974 (2.4796)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [150]  [140/312]  eta: 0:01:27  lr: 0.002214  min_lr: 0.002214  loss: 2.5196 (2.4933)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [150]  [150/312]  eta: 0:01:21  lr: 0.002214  min_lr: 0.002214  loss: 2.5562 (2.4925)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [150]  [160/312]  eta: 0:01:15  lr: 0.002213  min_lr: 0.002213  loss: 2.5815 (2.5010)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [150]  [170/312]  eta: 0:01:10  lr: 0.002212  min_lr: 0.002212  loss: 2.6373 (2.4990)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [150]  [180/312]  eta: 0:01:04  lr: 0.002212  min_lr: 0.002212  loss: 2.5284 (2.4915)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [150]  [190/312]  eta: 0:00:59  lr: 0.002211  min_lr: 0.002211  loss: 2.5742 (2.4986)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [150]  [200/312]  eta: 0:00:54  lr: 0.002210  min_lr: 0.002210  loss: 2.6051 (2.5008)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [150]  [210/312]  eta: 0:00:49  lr: 0.002209  min_lr: 0.002209  loss: 2.4252 (2.4961)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [150]  [220/312]  eta: 0:00:44  lr: 0.002209  min_lr: 0.002209  loss: 2.3748 (2.4955)  weight_decay: 0.0500 (0.0500)  time: 0.4379  data: 0.0004  max mem: 42573
Epoch: [150]  [230/312]  eta: 0:00:39  lr: 0.002208  min_lr: 0.002208  loss: 2.5375 (2.4990)  weight_decay: 0.0500 (0.0500)  time: 0.4377  data: 0.0004  max mem: 42573
Epoch: [150]  [240/312]  eta: 0:00:34  lr: 0.002207  min_lr: 0.002207  loss: 2.6576 (2.5038)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [150]  [250/312]  eta: 0:00:29  lr: 0.002207  min_lr: 0.002207  loss: 2.5702 (2.4995)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0003  max mem: 42573
Epoch: [150]  [260/312]  eta: 0:00:24  lr: 0.002206  min_lr: 0.002206  loss: 2.3746 (2.4922)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0003  max mem: 42573
Epoch: [150]  [270/312]  eta: 0:00:19  lr: 0.002205  min_lr: 0.002205  loss: 2.3746 (2.4881)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0003  max mem: 42573
Epoch: [150]  [280/312]  eta: 0:00:15  lr: 0.002204  min_lr: 0.002204  loss: 2.5246 (2.4930)  weight_decay: 0.0500 (0.0500)  time: 0.4345  data: 0.0010  max mem: 42573
Epoch: [150]  [290/312]  eta: 0:00:10  lr: 0.002204  min_lr: 0.002204  loss: 2.5904 (2.4941)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0009  max mem: 42573
Epoch: [150]  [300/312]  eta: 0:00:05  lr: 0.002203  min_lr: 0.002203  loss: 2.3759 (2.4897)  weight_decay: 0.0500 (0.0500)  time: 0.4325  data: 0.0001  max mem: 42573
Epoch: [150]  [310/312]  eta: 0:00:00  lr: 0.002202  min_lr: 0.002202  loss: 2.3372 (2.4848)  weight_decay: 0.0500 (0.0500)  time: 0.4325  data: 0.0001  max mem: 42573
Epoch: [150]  [311/312]  eta: 0:00:00  lr: 0.002202  min_lr: 0.002202  loss: 2.3684 (2.4858)  weight_decay: 0.0500 (0.0500)  time: 0.4325  data: 0.0001  max mem: 42573
Epoch: [150] Total time: 0:02:26 (0.4704 s / it)
Averaged stats: lr: 0.002202  min_lr: 0.002202  loss: 2.3684 (2.4697)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:00:45  loss: 0.8221 (0.8221)  acc1: 80.9896 (80.9896)  acc5: 93.2292 (93.2292)  time: 5.0582  data: 4.9489  max mem: 42573
Test:  [8/9]  eta: 0:00:00  loss: 1.0366 (1.0739)  acc1: 75.2604 (72.9280)  acc5: 92.1875 (91.2960)  time: 0.6376  data: 0.5499  max mem: 42573
Test: Total time: 0:00:05 (0.6449 s / it)
* Acc@1 73.190 Acc@5 91.372 loss 1.049
Accuracy of the model on the 50000 test images: 73.2%
Max accuracy: 73.19%
Epoch: [151]  [  0/312]  eta: 0:45:55  lr: 0.002202  min_lr: 0.002202  loss: 2.8064 (2.8064)  weight_decay: 0.0500 (0.0500)  time: 8.8315  data: 8.3340  max mem: 42573
Epoch: [151]  [ 10/312]  eta: 0:07:00  lr: 0.002201  min_lr: 0.002201  loss: 2.2704 (2.2942)  weight_decay: 0.0500 (0.0500)  time: 1.3910  data: 0.7581  max mem: 42573
Epoch: [151]  [ 20/312]  eta: 0:04:32  lr: 0.002201  min_lr: 0.002201  loss: 2.1504 (2.3028)  weight_decay: 0.0500 (0.0500)  time: 0.5400  data: 0.0005  max mem: 42573
Epoch: [151]  [ 30/312]  eta: 0:03:37  lr: 0.002200  min_lr: 0.002200  loss: 2.3678 (2.3403)  weight_decay: 0.0500 (0.0500)  time: 0.4331  data: 0.0005  max mem: 42573
Epoch: [151]  [ 40/312]  eta: 0:03:07  lr: 0.002199  min_lr: 0.002199  loss: 2.5781 (2.3681)  weight_decay: 0.0500 (0.0500)  time: 0.4332  data: 0.0005  max mem: 42573
Epoch: [151]  [ 50/312]  eta: 0:02:47  lr: 0.002198  min_lr: 0.002198  loss: 2.6076 (2.3813)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [151]  [ 60/312]  eta: 0:02:32  lr: 0.002198  min_lr: 0.002198  loss: 2.5551 (2.3951)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [151]  [ 70/312]  eta: 0:02:20  lr: 0.002197  min_lr: 0.002197  loss: 2.4593 (2.3799)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [151]  [ 80/312]  eta: 0:02:10  lr: 0.002196  min_lr: 0.002196  loss: 2.5522 (2.4057)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [151]  [ 90/312]  eta: 0:02:01  lr: 0.002196  min_lr: 0.002196  loss: 2.6016 (2.4248)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [151]  [100/312]  eta: 0:01:54  lr: 0.002195  min_lr: 0.002195  loss: 2.4868 (2.4130)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [151]  [110/312]  eta: 0:01:46  lr: 0.002194  min_lr: 0.002194  loss: 2.4262 (2.4157)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [151]  [120/312]  eta: 0:01:39  lr: 0.002193  min_lr: 0.002193  loss: 2.6263 (2.4271)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [151]  [130/312]  eta: 0:01:33  lr: 0.002193  min_lr: 0.002193  loss: 2.4766 (2.4103)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [151]  [140/312]  eta: 0:01:27  lr: 0.002192  min_lr: 0.002192  loss: 2.2374 (2.4096)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [151]  [150/312]  eta: 0:01:21  lr: 0.002191  min_lr: 0.002191  loss: 2.6228 (2.4297)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [151]  [160/312]  eta: 0:01:15  lr: 0.002191  min_lr: 0.002191  loss: 2.6228 (2.4337)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [151]  [170/312]  eta: 0:01:10  lr: 0.002190  min_lr: 0.002190  loss: 2.4747 (2.4237)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [151]  [180/312]  eta: 0:01:04  lr: 0.002189  min_lr: 0.002189  loss: 2.4297 (2.4276)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [151]  [190/312]  eta: 0:00:59  lr: 0.002188  min_lr: 0.002188  loss: 2.4235 (2.4293)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [151]  [200/312]  eta: 0:00:54  lr: 0.002188  min_lr: 0.002188  loss: 2.4045 (2.4248)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [151]  [210/312]  eta: 0:00:49  lr: 0.002187  min_lr: 0.002187  loss: 2.3278 (2.4263)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [151]  [220/312]  eta: 0:00:44  lr: 0.002186  min_lr: 0.002186  loss: 2.1878 (2.4175)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [151]  [230/312]  eta: 0:00:39  lr: 0.002186  min_lr: 0.002186  loss: 2.5133 (2.4295)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [151]  [240/312]  eta: 0:00:34  lr: 0.002185  min_lr: 0.002185  loss: 2.6463 (2.4309)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [151]  [250/312]  eta: 0:00:29  lr: 0.002184  min_lr: 0.002184  loss: 2.4463 (2.4259)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [151]  [260/312]  eta: 0:00:24  lr: 0.002183  min_lr: 0.002183  loss: 2.1628 (2.4166)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [151]  [270/312]  eta: 0:00:19  lr: 0.002183  min_lr: 0.002183  loss: 2.1628 (2.4139)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0003  max mem: 42573
Epoch: [151]  [280/312]  eta: 0:00:15  lr: 0.002182  min_lr: 0.002182  loss: 2.5431 (2.4203)  weight_decay: 0.0500 (0.0500)  time: 0.4350  data: 0.0010  max mem: 42573
Epoch: [151]  [290/312]  eta: 0:00:10  lr: 0.002181  min_lr: 0.002181  loss: 2.6246 (2.4297)  weight_decay: 0.0500 (0.0500)  time: 0.4342  data: 0.0008  max mem: 42573
Epoch: [151]  [300/312]  eta: 0:00:05  lr: 0.002181  min_lr: 0.002181  loss: 2.6333 (2.4352)  weight_decay: 0.0500 (0.0500)  time: 0.4325  data: 0.0001  max mem: 42573
Epoch: [151]  [310/312]  eta: 0:00:00  lr: 0.002180  min_lr: 0.002180  loss: 2.6506 (2.4420)  weight_decay: 0.0500 (0.0500)  time: 0.4325  data: 0.0001  max mem: 42573
Epoch: [151]  [311/312]  eta: 0:00:00  lr: 0.002180  min_lr: 0.002180  loss: 2.6474 (2.4420)  weight_decay: 0.0500 (0.0500)  time: 0.4325  data: 0.0001  max mem: 42573
Epoch: [151] Total time: 0:02:26 (0.4702 s / it)
Averaged stats: lr: 0.002180  min_lr: 0.002180  loss: 2.6474 (2.4658)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:00:44  loss: 0.9071 (0.9071)  acc1: 78.1250 (78.1250)  acc5: 92.9688 (92.9688)  time: 4.9981  data: 4.8886  max mem: 42573
Test:  [8/9]  eta: 0:00:00  loss: 1.2045 (1.1350)  acc1: 71.6146 (72.0000)  acc5: 90.6250 (90.9760)  time: 0.6322  data: 0.5432  max mem: 42573
Test: Total time: 0:00:05 (0.6417 s / it)
* Acc@1 72.602 Acc@5 90.874 loss 1.131
Accuracy of the model on the 50000 test images: 72.6%
Max accuracy: 73.19%
Epoch: [152]  [  0/312]  eta: 0:50:06  lr: 0.002180  min_lr: 0.002180  loss: 1.9455 (1.9455)  weight_decay: 0.0500 (0.0500)  time: 9.6360  data: 7.8197  max mem: 42573
Epoch: [152]  [ 10/312]  eta: 0:07:15  lr: 0.002179  min_lr: 0.002179  loss: 2.5177 (2.3830)  weight_decay: 0.0500 (0.0500)  time: 1.4408  data: 0.7212  max mem: 42573
Epoch: [152]  [ 20/312]  eta: 0:04:40  lr: 0.002178  min_lr: 0.002178  loss: 2.5177 (2.4672)  weight_decay: 0.0500 (0.0500)  time: 0.5272  data: 0.0059  max mem: 42573
Epoch: [152]  [ 30/312]  eta: 0:03:43  lr: 0.002178  min_lr: 0.002178  loss: 2.5948 (2.5102)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [152]  [ 40/312]  eta: 0:03:11  lr: 0.002177  min_lr: 0.002177  loss: 2.5948 (2.5139)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [152]  [ 50/312]  eta: 0:02:50  lr: 0.002176  min_lr: 0.002176  loss: 2.4541 (2.4824)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [152]  [ 60/312]  eta: 0:02:34  lr: 0.002175  min_lr: 0.002175  loss: 2.5601 (2.4959)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [152]  [ 70/312]  eta: 0:02:22  lr: 0.002175  min_lr: 0.002175  loss: 2.5601 (2.4722)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [152]  [ 80/312]  eta: 0:02:12  lr: 0.002174  min_lr: 0.002174  loss: 2.4700 (2.4540)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [152]  [ 90/312]  eta: 0:02:03  lr: 0.002173  min_lr: 0.002173  loss: 2.6097 (2.4817)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [152]  [100/312]  eta: 0:01:55  lr: 0.002173  min_lr: 0.002173  loss: 2.6086 (2.4701)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [152]  [110/312]  eta: 0:01:47  lr: 0.002172  min_lr: 0.002172  loss: 2.3825 (2.4577)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [152]  [120/312]  eta: 0:01:40  lr: 0.002171  min_lr: 0.002171  loss: 2.3825 (2.4478)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [152]  [130/312]  eta: 0:01:34  lr: 0.002170  min_lr: 0.002170  loss: 2.5924 (2.4486)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [152]  [140/312]  eta: 0:01:28  lr: 0.002170  min_lr: 0.002170  loss: 2.6362 (2.4635)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [152]  [150/312]  eta: 0:01:22  lr: 0.002169  min_lr: 0.002169  loss: 2.6290 (2.4718)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [152]  [160/312]  eta: 0:01:16  lr: 0.002168  min_lr: 0.002168  loss: 2.5770 (2.4797)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [152]  [170/312]  eta: 0:01:10  lr: 0.002168  min_lr: 0.002168  loss: 2.5323 (2.4800)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [152]  [180/312]  eta: 0:01:05  lr: 0.002167  min_lr: 0.002167  loss: 2.3793 (2.4695)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [152]  [190/312]  eta: 0:00:59  lr: 0.002166  min_lr: 0.002166  loss: 2.1865 (2.4661)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [152]  [200/312]  eta: 0:00:54  lr: 0.002165  min_lr: 0.002165  loss: 2.4661 (2.4704)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [152]  [210/312]  eta: 0:00:49  lr: 0.002165  min_lr: 0.002165  loss: 2.6691 (2.4841)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [152]  [220/312]  eta: 0:00:44  lr: 0.002164  min_lr: 0.002164  loss: 2.6717 (2.4869)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [152]  [230/312]  eta: 0:00:39  lr: 0.002163  min_lr: 0.002163  loss: 2.6042 (2.4839)  weight_decay: 0.0500 (0.0500)  time: 0.4395  data: 0.0004  max mem: 42573
Epoch: [152]  [240/312]  eta: 0:00:34  lr: 0.002163  min_lr: 0.002163  loss: 2.5622 (2.4930)  weight_decay: 0.0500 (0.0500)  time: 0.4395  data: 0.0005  max mem: 42573
Epoch: [152]  [250/312]  eta: 0:00:29  lr: 0.002162  min_lr: 0.002162  loss: 2.5007 (2.4916)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [152]  [260/312]  eta: 0:00:24  lr: 0.002161  min_lr: 0.002161  loss: 2.3172 (2.4812)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [152]  [270/312]  eta: 0:00:19  lr: 0.002160  min_lr: 0.002160  loss: 2.2749 (2.4747)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [152]  [280/312]  eta: 0:00:15  lr: 0.002160  min_lr: 0.002160  loss: 2.5197 (2.4771)  weight_decay: 0.0500 (0.0500)  time: 0.4341  data: 0.0009  max mem: 42573
Epoch: [152]  [290/312]  eta: 0:00:10  lr: 0.002159  min_lr: 0.002159  loss: 2.5362 (2.4761)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0007  max mem: 42573
Epoch: [152]  [300/312]  eta: 0:00:05  lr: 0.002158  min_lr: 0.002158  loss: 2.5209 (2.4756)  weight_decay: 0.0500 (0.0500)  time: 0.4325  data: 0.0001  max mem: 42573
Epoch: [152]  [310/312]  eta: 0:00:00  lr: 0.002158  min_lr: 0.002158  loss: 2.5512 (2.4786)  weight_decay: 0.0500 (0.0500)  time: 0.4324  data: 0.0001  max mem: 42573
Epoch: [152]  [311/312]  eta: 0:00:00  lr: 0.002157  min_lr: 0.002157  loss: 2.5654 (2.4801)  weight_decay: 0.0500 (0.0500)  time: 0.4323  data: 0.0001  max mem: 42573
Epoch: [152] Total time: 0:02:27 (0.4722 s / it)
Averaged stats: lr: 0.002157  min_lr: 0.002157  loss: 2.5654 (2.4573)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:00:45  loss: 0.8305 (0.8305)  acc1: 80.9896 (80.9896)  acc5: 94.0104 (94.0104)  time: 5.0905  data: 4.9811  max mem: 42573
Test:  [8/9]  eta: 0:00:00  loss: 1.0917 (1.0749)  acc1: 71.8750 (72.2880)  acc5: 91.1458 (90.9120)  time: 0.6431  data: 0.5535  max mem: 42573
Test: Total time: 0:00:06 (0.6677 s / it)
* Acc@1 73.172 Acc@5 91.382 loss 1.082
Accuracy of the model on the 50000 test images: 73.2%
Max accuracy: 73.19%
Epoch: [153]  [  0/312]  eta: 0:46:45  lr: 0.002157  min_lr: 0.002157  loss: 2.0695 (2.0695)  weight_decay: 0.0500 (0.0500)  time: 8.9936  data: 8.1437  max mem: 42573
Epoch: [153]  [ 10/312]  eta: 0:06:56  lr: 0.002157  min_lr: 0.002157  loss: 2.2119 (2.2585)  weight_decay: 0.0500 (0.0500)  time: 1.3779  data: 0.7407  max mem: 42573
Epoch: [153]  [ 20/312]  eta: 0:04:31  lr: 0.002156  min_lr: 0.002156  loss: 2.1106 (2.2509)  weight_decay: 0.0500 (0.0500)  time: 0.5280  data: 0.0004  max mem: 42573
Epoch: [153]  [ 30/312]  eta: 0:03:37  lr: 0.002155  min_lr: 0.002155  loss: 2.5328 (2.3729)  weight_decay: 0.0500 (0.0500)  time: 0.4364  data: 0.0004  max mem: 42573
Epoch: [153]  [ 40/312]  eta: 0:03:07  lr: 0.002155  min_lr: 0.002155  loss: 2.5328 (2.3698)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [153]  [ 50/312]  eta: 0:02:47  lr: 0.002154  min_lr: 0.002154  loss: 2.5703 (2.4353)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [153]  [ 60/312]  eta: 0:02:32  lr: 0.002153  min_lr: 0.002153  loss: 2.5703 (2.4166)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [153]  [ 70/312]  eta: 0:02:20  lr: 0.002152  min_lr: 0.002152  loss: 2.4659 (2.4353)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [153]  [ 80/312]  eta: 0:02:10  lr: 0.002152  min_lr: 0.002152  loss: 2.3393 (2.4025)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0003  max mem: 42573
Epoch: [153]  [ 90/312]  eta: 0:02:01  lr: 0.002151  min_lr: 0.002151  loss: 2.2957 (2.4044)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [153]  [100/312]  eta: 0:01:53  lr: 0.002150  min_lr: 0.002150  loss: 2.5710 (2.4084)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [153]  [110/312]  eta: 0:01:46  lr: 0.002149  min_lr: 0.002149  loss: 2.6236 (2.4284)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [153]  [120/312]  eta: 0:01:39  lr: 0.002149  min_lr: 0.002149  loss: 2.5719 (2.4295)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [153]  [130/312]  eta: 0:01:33  lr: 0.002148  min_lr: 0.002148  loss: 2.5451 (2.4417)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [153]  [140/312]  eta: 0:01:27  lr: 0.002147  min_lr: 0.002147  loss: 2.5153 (2.4414)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [153]  [150/312]  eta: 0:01:21  lr: 0.002147  min_lr: 0.002147  loss: 2.5280 (2.4504)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0003  max mem: 42573
Epoch: [153]  [160/312]  eta: 0:01:15  lr: 0.002146  min_lr: 0.002146  loss: 2.5986 (2.4598)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0003  max mem: 42573
Epoch: [153]  [170/312]  eta: 0:01:10  lr: 0.002145  min_lr: 0.002145  loss: 2.5355 (2.4544)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [153]  [180/312]  eta: 0:01:04  lr: 0.002144  min_lr: 0.002144  loss: 2.5355 (2.4639)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [153]  [190/312]  eta: 0:00:59  lr: 0.002144  min_lr: 0.002144  loss: 2.3633 (2.4526)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [153]  [200/312]  eta: 0:00:54  lr: 0.002143  min_lr: 0.002143  loss: 2.3633 (2.4535)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [153]  [210/312]  eta: 0:00:49  lr: 0.002142  min_lr: 0.002142  loss: 2.5354 (2.4497)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [153]  [220/312]  eta: 0:00:44  lr: 0.002142  min_lr: 0.002142  loss: 2.5782 (2.4547)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [153]  [230/312]  eta: 0:00:39  lr: 0.002141  min_lr: 0.002141  loss: 2.5862 (2.4565)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [153]  [240/312]  eta: 0:00:34  lr: 0.002140  min_lr: 0.002140  loss: 2.5528 (2.4591)  weight_decay: 0.0500 (0.0500)  time: 0.4406  data: 0.0004  max mem: 42573
Epoch: [153]  [250/312]  eta: 0:00:29  lr: 0.002139  min_lr: 0.002139  loss: 2.5691 (2.4623)  weight_decay: 0.0500 (0.0500)  time: 0.4406  data: 0.0004  max mem: 42573
Epoch: [153]  [260/312]  eta: 0:00:24  lr: 0.002139  min_lr: 0.002139  loss: 2.5872 (2.4607)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [153]  [270/312]  eta: 0:00:19  lr: 0.002138  min_lr: 0.002138  loss: 2.4104 (2.4617)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [153]  [280/312]  eta: 0:00:15  lr: 0.002137  min_lr: 0.002137  loss: 2.4071 (2.4610)  weight_decay: 0.0500 (0.0500)  time: 0.4354  data: 0.0009  max mem: 42573
Epoch: [153]  [290/312]  eta: 0:00:10  lr: 0.002137  min_lr: 0.002137  loss: 2.5191 (2.4651)  weight_decay: 0.0500 (0.0500)  time: 0.4348  data: 0.0008  max mem: 42573
Epoch: [153]  [300/312]  eta: 0:00:05  lr: 0.002136  min_lr: 0.002136  loss: 2.6451 (2.4702)  weight_decay: 0.0500 (0.0500)  time: 0.4324  data: 0.0001  max mem: 42573
Epoch: [153]  [310/312]  eta: 0:00:00  lr: 0.002135  min_lr: 0.002135  loss: 2.4505 (2.4734)  weight_decay: 0.0500 (0.0500)  time: 0.4324  data: 0.0001  max mem: 42573
Epoch: [153]  [311/312]  eta: 0:00:00  lr: 0.002135  min_lr: 0.002135  loss: 2.4505 (2.4742)  weight_decay: 0.0500 (0.0500)  time: 0.4324  data: 0.0001  max mem: 42573
Epoch: [153] Total time: 0:02:26 (0.4707 s / it)
Averaged stats: lr: 0.002135  min_lr: 0.002135  loss: 2.4505 (2.4509)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:00:49  loss: 0.8523 (0.8523)  acc1: 78.9062 (78.9062)  acc5: 94.2708 (94.2708)  time: 5.4860  data: 5.3767  max mem: 42573
Test:  [8/9]  eta: 0:00:00  loss: 1.2366 (1.1399)  acc1: 72.1354 (72.6720)  acc5: 91.1458 (91.2000)  time: 0.6868  data: 0.5975  max mem: 42573
Test: Total time: 0:00:06 (0.7093 s / it)
* Acc@1 73.022 Acc@5 91.230 loss 1.119
Accuracy of the model on the 50000 test images: 73.0%
Max accuracy: 73.19%
Epoch: [154]  [  0/312]  eta: 0:46:02  lr: 0.002135  min_lr: 0.002135  loss: 2.8362 (2.8362)  weight_decay: 0.0500 (0.0500)  time: 8.8543  data: 7.9459  max mem: 42573
Epoch: [154]  [ 10/312]  eta: 0:07:03  lr: 0.002134  min_lr: 0.002134  loss: 2.5976 (2.5720)  weight_decay: 0.0500 (0.0500)  time: 1.4028  data: 0.7228  max mem: 42573
Epoch: [154]  [ 20/312]  eta: 0:04:34  lr: 0.002134  min_lr: 0.002134  loss: 2.5976 (2.5423)  weight_decay: 0.0500 (0.0500)  time: 0.5454  data: 0.0004  max mem: 42573
Epoch: [154]  [ 30/312]  eta: 0:03:39  lr: 0.002133  min_lr: 0.002133  loss: 2.4713 (2.4562)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0003  max mem: 42573
Epoch: [154]  [ 40/312]  eta: 0:03:08  lr: 0.002132  min_lr: 0.002132  loss: 2.3283 (2.4359)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [154]  [ 50/312]  eta: 0:02:48  lr: 0.002131  min_lr: 0.002131  loss: 2.6851 (2.4802)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [154]  [ 60/312]  eta: 0:02:33  lr: 0.002131  min_lr: 0.002131  loss: 2.7299 (2.4780)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [154]  [ 70/312]  eta: 0:02:21  lr: 0.002130  min_lr: 0.002130  loss: 2.4506 (2.4754)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [154]  [ 80/312]  eta: 0:02:11  lr: 0.002129  min_lr: 0.002129  loss: 2.3462 (2.4607)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [154]  [ 90/312]  eta: 0:02:02  lr: 0.002129  min_lr: 0.002129  loss: 2.3284 (2.4427)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0003  max mem: 42573
Epoch: [154]  [100/312]  eta: 0:01:54  lr: 0.002128  min_lr: 0.002128  loss: 2.4701 (2.4525)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0003  max mem: 42573
Epoch: [154]  [110/312]  eta: 0:01:47  lr: 0.002127  min_lr: 0.002127  loss: 2.6296 (2.4648)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [154]  [120/312]  eta: 0:01:40  lr: 0.002126  min_lr: 0.002126  loss: 2.5728 (2.4695)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [154]  [130/312]  eta: 0:01:33  lr: 0.002126  min_lr: 0.002126  loss: 2.5250 (2.4640)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [154]  [140/312]  eta: 0:01:27  lr: 0.002125  min_lr: 0.002125  loss: 2.5250 (2.4632)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [154]  [150/312]  eta: 0:01:21  lr: 0.002124  min_lr: 0.002124  loss: 2.5407 (2.4573)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [154]  [160/312]  eta: 0:01:15  lr: 0.002124  min_lr: 0.002124  loss: 2.5410 (2.4588)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [154]  [170/312]  eta: 0:01:10  lr: 0.002123  min_lr: 0.002123  loss: 2.5475 (2.4599)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [154]  [180/312]  eta: 0:01:05  lr: 0.002122  min_lr: 0.002122  loss: 2.5475 (2.4645)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0005  max mem: 42573
Epoch: [154]  [190/312]  eta: 0:00:59  lr: 0.002121  min_lr: 0.002121  loss: 2.5368 (2.4622)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [154]  [200/312]  eta: 0:00:54  lr: 0.002121  min_lr: 0.002121  loss: 2.5383 (2.4628)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [154]  [210/312]  eta: 0:00:49  lr: 0.002120  min_lr: 0.002120  loss: 2.5019 (2.4634)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [154]  [220/312]  eta: 0:00:44  lr: 0.002119  min_lr: 0.002119  loss: 2.5869 (2.4689)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0003  max mem: 42573
Epoch: [154]  [230/312]  eta: 0:00:39  lr: 0.002118  min_lr: 0.002118  loss: 2.5869 (2.4638)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [154]  [240/312]  eta: 0:00:34  lr: 0.002118  min_lr: 0.002118  loss: 2.5341 (2.4637)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [154]  [250/312]  eta: 0:00:29  lr: 0.002117  min_lr: 0.002117  loss: 2.5593 (2.4681)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [154]  [260/312]  eta: 0:00:24  lr: 0.002116  min_lr: 0.002116  loss: 2.5593 (2.4626)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [154]  [270/312]  eta: 0:00:19  lr: 0.002116  min_lr: 0.002116  loss: 2.5912 (2.4676)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [154]  [280/312]  eta: 0:00:15  lr: 0.002115  min_lr: 0.002115  loss: 2.5744 (2.4677)  weight_decay: 0.0500 (0.0500)  time: 0.4342  data: 0.0010  max mem: 42573
Epoch: [154]  [290/312]  eta: 0:00:10  lr: 0.002114  min_lr: 0.002114  loss: 2.5777 (2.4748)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0008  max mem: 42573
Epoch: [154]  [300/312]  eta: 0:00:05  lr: 0.002113  min_lr: 0.002113  loss: 2.6827 (2.4757)  weight_decay: 0.0500 (0.0500)  time: 0.4324  data: 0.0001  max mem: 42573
Epoch: [154]  [310/312]  eta: 0:00:00  lr: 0.002113  min_lr: 0.002113  loss: 2.4339 (2.4710)  weight_decay: 0.0500 (0.0500)  time: 0.4324  data: 0.0001  max mem: 42573
Epoch: [154]  [311/312]  eta: 0:00:00  lr: 0.002113  min_lr: 0.002113  loss: 2.4339 (2.4727)  weight_decay: 0.0500 (0.0500)  time: 0.4325  data: 0.0001  max mem: 42573
Epoch: [154] Total time: 0:02:26 (0.4707 s / it)
Averaged stats: lr: 0.002113  min_lr: 0.002113  loss: 2.4339 (2.4585)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:00:42  loss: 0.8255 (0.8255)  acc1: 79.1667 (79.1667)  acc5: 93.4896 (93.4896)  time: 4.7096  data: 4.6007  max mem: 42573
Test:  [8/9]  eta: 0:00:00  loss: 1.1700 (1.1034)  acc1: 72.3958 (72.9920)  acc5: 91.4062 (90.5600)  time: 0.6083  data: 0.5210  max mem: 42573
Test: Total time: 0:00:05 (0.6173 s / it)
* Acc@1 73.016 Acc@5 90.960 loss 1.089
Accuracy of the model on the 50000 test images: 73.0%
Max accuracy: 73.19%
Epoch: [155]  [  0/312]  eta: 0:49:20  lr: 0.002113  min_lr: 0.002113  loss: 2.3288 (2.3288)  weight_decay: 0.0500 (0.0500)  time: 9.4898  data: 8.1668  max mem: 42573
Epoch: [155]  [ 10/312]  eta: 0:07:15  lr: 0.002112  min_lr: 0.002112  loss: 2.5931 (2.5122)  weight_decay: 0.0500 (0.0500)  time: 1.4417  data: 0.7429  max mem: 42573
Epoch: [155]  [ 20/312]  eta: 0:04:40  lr: 0.002111  min_lr: 0.002111  loss: 2.6184 (2.5895)  weight_decay: 0.0500 (0.0500)  time: 0.5350  data: 0.0005  max mem: 42573
Epoch: [155]  [ 30/312]  eta: 0:03:43  lr: 0.002110  min_lr: 0.002110  loss: 2.6014 (2.5591)  weight_decay: 0.0500 (0.0500)  time: 0.4332  data: 0.0004  max mem: 42573
Epoch: [155]  [ 40/312]  eta: 0:03:11  lr: 0.002110  min_lr: 0.002110  loss: 2.6014 (2.5581)  weight_decay: 0.0500 (0.0500)  time: 0.4332  data: 0.0004  max mem: 42573
Epoch: [155]  [ 50/312]  eta: 0:02:50  lr: 0.002109  min_lr: 0.002109  loss: 2.6077 (2.5478)  weight_decay: 0.0500 (0.0500)  time: 0.4331  data: 0.0004  max mem: 42573
Epoch: [155]  [ 60/312]  eta: 0:02:34  lr: 0.002108  min_lr: 0.002108  loss: 2.6426 (2.5749)  weight_decay: 0.0500 (0.0500)  time: 0.4332  data: 0.0004  max mem: 42573
Epoch: [155]  [ 70/312]  eta: 0:02:22  lr: 0.002108  min_lr: 0.002108  loss: 2.5688 (2.5402)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [155]  [ 80/312]  eta: 0:02:12  lr: 0.002107  min_lr: 0.002107  loss: 2.2818 (2.5125)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [155]  [ 90/312]  eta: 0:02:03  lr: 0.002106  min_lr: 0.002106  loss: 2.2925 (2.5176)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [155]  [100/312]  eta: 0:01:55  lr: 0.002105  min_lr: 0.002105  loss: 2.4288 (2.5005)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [155]  [110/312]  eta: 0:01:47  lr: 0.002105  min_lr: 0.002105  loss: 2.3136 (2.4891)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [155]  [120/312]  eta: 0:01:40  lr: 0.002104  min_lr: 0.002104  loss: 2.4292 (2.4909)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [155]  [130/312]  eta: 0:01:34  lr: 0.002103  min_lr: 0.002103  loss: 2.4795 (2.4965)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [155]  [140/312]  eta: 0:01:28  lr: 0.002103  min_lr: 0.002103  loss: 2.6596 (2.5091)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0003  max mem: 42573
Epoch: [155]  [150/312]  eta: 0:01:22  lr: 0.002102  min_lr: 0.002102  loss: 2.6669 (2.5041)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [155]  [160/312]  eta: 0:01:16  lr: 0.002101  min_lr: 0.002101  loss: 2.5598 (2.4997)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [155]  [170/312]  eta: 0:01:10  lr: 0.002100  min_lr: 0.002100  loss: 2.5640 (2.5075)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [155]  [180/312]  eta: 0:01:05  lr: 0.002100  min_lr: 0.002100  loss: 2.5186 (2.5045)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [155]  [190/312]  eta: 0:00:59  lr: 0.002099  min_lr: 0.002099  loss: 2.2882 (2.4931)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [155]  [200/312]  eta: 0:00:54  lr: 0.002098  min_lr: 0.002098  loss: 2.3925 (2.4979)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [155]  [210/312]  eta: 0:00:49  lr: 0.002098  min_lr: 0.002098  loss: 2.6010 (2.4973)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [155]  [220/312]  eta: 0:00:44  lr: 0.002097  min_lr: 0.002097  loss: 2.4932 (2.4946)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [155]  [230/312]  eta: 0:00:39  lr: 0.002096  min_lr: 0.002096  loss: 2.4570 (2.4920)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0003  max mem: 42573
Epoch: [155]  [240/312]  eta: 0:00:34  lr: 0.002095  min_lr: 0.002095  loss: 2.3897 (2.4834)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [155]  [250/312]  eta: 0:00:29  lr: 0.002095  min_lr: 0.002095  loss: 2.3897 (2.4834)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [155]  [260/312]  eta: 0:00:24  lr: 0.002094  min_lr: 0.002094  loss: 2.5962 (2.4870)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [155]  [270/312]  eta: 0:00:19  lr: 0.002093  min_lr: 0.002093  loss: 2.6810 (2.4911)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [155]  [280/312]  eta: 0:00:15  lr: 0.002093  min_lr: 0.002093  loss: 2.6998 (2.4953)  weight_decay: 0.0500 (0.0500)  time: 0.4347  data: 0.0010  max mem: 42573
Epoch: [155]  [290/312]  eta: 0:00:10  lr: 0.002092  min_lr: 0.002092  loss: 2.5197 (2.4923)  weight_decay: 0.0500 (0.0500)  time: 0.4341  data: 0.0008  max mem: 42573
Epoch: [155]  [300/312]  eta: 0:00:05  lr: 0.002091  min_lr: 0.002091  loss: 2.4954 (2.4954)  weight_decay: 0.0500 (0.0500)  time: 0.4323  data: 0.0001  max mem: 42573
Epoch: [155]  [310/312]  eta: 0:00:00  lr: 0.002090  min_lr: 0.002090  loss: 2.5925 (2.4958)  weight_decay: 0.0500 (0.0500)  time: 0.4323  data: 0.0001  max mem: 42573
Epoch: [155]  [311/312]  eta: 0:00:00  lr: 0.002090  min_lr: 0.002090  loss: 2.5925 (2.4959)  weight_decay: 0.0500 (0.0500)  time: 0.4323  data: 0.0001  max mem: 42573
Epoch: [155] Total time: 0:02:27 (0.4720 s / it)
Averaged stats: lr: 0.002090  min_lr: 0.002090  loss: 2.5925 (2.4536)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:00:44  loss: 0.8283 (0.8283)  acc1: 79.4271 (79.4271)  acc5: 93.4896 (93.4896)  time: 4.9564  data: 4.8482  max mem: 42573
Test:  [8/9]  eta: 0:00:00  loss: 1.2653 (1.1202)  acc1: 72.1354 (72.2240)  acc5: 89.8438 (91.0080)  time: 0.6265  data: 0.5388  max mem: 42573
Test: Total time: 0:00:05 (0.6338 s / it)
* Acc@1 72.748 Acc@5 90.774 loss 1.125
Accuracy of the model on the 50000 test images: 72.7%
Max accuracy: 73.19%
Epoch: [156]  [  0/312]  eta: 0:48:39  lr: 0.002090  min_lr: 0.002090  loss: 2.6755 (2.6755)  weight_decay: 0.0500 (0.0500)  time: 9.3580  data: 5.8819  max mem: 42573
Epoch: [156]  [ 10/312]  eta: 0:07:06  lr: 0.002089  min_lr: 0.002089  loss: 2.6726 (2.4737)  weight_decay: 0.0500 (0.0500)  time: 1.4131  data: 0.6927  max mem: 42573
Epoch: [156]  [ 20/312]  eta: 0:04:36  lr: 0.002089  min_lr: 0.002089  loss: 2.4776 (2.4413)  weight_decay: 0.0500 (0.0500)  time: 0.5260  data: 0.0870  max mem: 42573
Epoch: [156]  [ 30/312]  eta: 0:03:40  lr: 0.002088  min_lr: 0.002088  loss: 2.4574 (2.4171)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [156]  [ 40/312]  eta: 0:03:09  lr: 0.002087  min_lr: 0.002087  loss: 2.4008 (2.4049)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [156]  [ 50/312]  eta: 0:02:49  lr: 0.002087  min_lr: 0.002087  loss: 2.1748 (2.3532)  weight_decay: 0.0500 (0.0500)  time: 0.4381  data: 0.0004  max mem: 42573
Epoch: [156]  [ 60/312]  eta: 0:02:34  lr: 0.002086  min_lr: 0.002086  loss: 2.1748 (2.3857)  weight_decay: 0.0500 (0.0500)  time: 0.4382  data: 0.0003  max mem: 42573
Epoch: [156]  [ 70/312]  eta: 0:02:21  lr: 0.002085  min_lr: 0.002085  loss: 2.3268 (2.3749)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [156]  [ 80/312]  eta: 0:02:11  lr: 0.002084  min_lr: 0.002084  loss: 2.3335 (2.3929)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0003  max mem: 42573
Epoch: [156]  [ 90/312]  eta: 0:02:02  lr: 0.002084  min_lr: 0.002084  loss: 2.4902 (2.3902)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [156]  [100/312]  eta: 0:01:54  lr: 0.002083  min_lr: 0.002083  loss: 2.2403 (2.3832)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [156]  [110/312]  eta: 0:01:47  lr: 0.002082  min_lr: 0.002082  loss: 2.5038 (2.4056)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [156]  [120/312]  eta: 0:01:40  lr: 0.002082  min_lr: 0.002082  loss: 2.5559 (2.4146)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [156]  [130/312]  eta: 0:01:34  lr: 0.002081  min_lr: 0.002081  loss: 2.3567 (2.4034)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [156]  [140/312]  eta: 0:01:27  lr: 0.002080  min_lr: 0.002080  loss: 2.4332 (2.4162)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0003  max mem: 42573
Epoch: [156]  [150/312]  eta: 0:01:21  lr: 0.002079  min_lr: 0.002079  loss: 2.4937 (2.4038)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [156]  [160/312]  eta: 0:01:16  lr: 0.002079  min_lr: 0.002079  loss: 2.3983 (2.4096)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [156]  [170/312]  eta: 0:01:10  lr: 0.002078  min_lr: 0.002078  loss: 2.5531 (2.4198)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [156]  [180/312]  eta: 0:01:05  lr: 0.002077  min_lr: 0.002077  loss: 2.6247 (2.4267)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0003  max mem: 42573
Epoch: [156]  [190/312]  eta: 0:00:59  lr: 0.002077  min_lr: 0.002077  loss: 2.6860 (2.4420)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0003  max mem: 42573
Epoch: [156]  [200/312]  eta: 0:00:54  lr: 0.002076  min_lr: 0.002076  loss: 2.6070 (2.4490)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0003  max mem: 42573
Epoch: [156]  [210/312]  eta: 0:00:49  lr: 0.002075  min_lr: 0.002075  loss: 2.5095 (2.4440)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [156]  [220/312]  eta: 0:00:44  lr: 0.002074  min_lr: 0.002074  loss: 2.3996 (2.4382)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [156]  [230/312]  eta: 0:00:39  lr: 0.002074  min_lr: 0.002074  loss: 2.5121 (2.4395)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [156]  [240/312]  eta: 0:00:34  lr: 0.002073  min_lr: 0.002073  loss: 2.6463 (2.4526)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [156]  [250/312]  eta: 0:00:29  lr: 0.002072  min_lr: 0.002072  loss: 2.6279 (2.4466)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [156]  [260/312]  eta: 0:00:24  lr: 0.002072  min_lr: 0.002072  loss: 2.2723 (2.4409)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [156]  [270/312]  eta: 0:00:19  lr: 0.002071  min_lr: 0.002071  loss: 2.1209 (2.4350)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0003  max mem: 42573
Epoch: [156]  [280/312]  eta: 0:00:15  lr: 0.002070  min_lr: 0.002070  loss: 2.2974 (2.4334)  weight_decay: 0.0500 (0.0500)  time: 0.4344  data: 0.0011  max mem: 42573
Epoch: [156]  [290/312]  eta: 0:00:10  lr: 0.002069  min_lr: 0.002069  loss: 2.5030 (2.4413)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0010  max mem: 42573
Epoch: [156]  [300/312]  eta: 0:00:05  lr: 0.002069  min_lr: 0.002069  loss: 2.5964 (2.4383)  weight_decay: 0.0500 (0.0500)  time: 0.4325  data: 0.0001  max mem: 42573
Epoch: [156]  [310/312]  eta: 0:00:00  lr: 0.002068  min_lr: 0.002068  loss: 2.4495 (2.4356)  weight_decay: 0.0500 (0.0500)  time: 0.4324  data: 0.0001  max mem: 42573
Epoch: [156]  [311/312]  eta: 0:00:00  lr: 0.002068  min_lr: 0.002068  loss: 2.5413 (2.4365)  weight_decay: 0.0500 (0.0500)  time: 0.4325  data: 0.0001  max mem: 42573
Epoch: [156] Total time: 0:02:27 (0.4713 s / it)
Averaged stats: lr: 0.002068  min_lr: 0.002068  loss: 2.5413 (2.4428)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:00:46  loss: 0.8667 (0.8667)  acc1: 78.3854 (78.3854)  acc5: 93.4896 (93.4896)  time: 5.2208  data: 5.1114  max mem: 42573
Test:  [8/9]  eta: 0:00:00  loss: 1.2865 (1.1523)  acc1: 69.7917 (71.1360)  acc5: 89.3229 (90.3040)  time: 0.6560  data: 0.5680  max mem: 42573
Test: Total time: 0:00:06 (0.6804 s / it)
* Acc@1 71.772 Acc@5 90.446 loss 1.126
Accuracy of the model on the 50000 test images: 71.8%
Max accuracy: 73.19%
Epoch: [157]  [  0/312]  eta: 0:49:04  lr: 0.002068  min_lr: 0.002068  loss: 2.6021 (2.6021)  weight_decay: 0.0500 (0.0500)  time: 9.4385  data: 7.6413  max mem: 42573
Epoch: [157]  [ 10/312]  eta: 0:07:20  lr: 0.002067  min_lr: 0.002067  loss: 2.6443 (2.5427)  weight_decay: 0.0500 (0.0500)  time: 1.4591  data: 0.6951  max mem: 42573
Epoch: [157]  [ 20/312]  eta: 0:04:43  lr: 0.002066  min_lr: 0.002066  loss: 2.6443 (2.5604)  weight_decay: 0.0500 (0.0500)  time: 0.5471  data: 0.0004  max mem: 42573
Epoch: [157]  [ 30/312]  eta: 0:03:44  lr: 0.002066  min_lr: 0.002066  loss: 2.6074 (2.5381)  weight_decay: 0.0500 (0.0500)  time: 0.4331  data: 0.0004  max mem: 42573
Epoch: [157]  [ 40/312]  eta: 0:03:12  lr: 0.002065  min_lr: 0.002065  loss: 2.7059 (2.5858)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [157]  [ 50/312]  eta: 0:02:51  lr: 0.002064  min_lr: 0.002064  loss: 2.7059 (2.5399)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [157]  [ 60/312]  eta: 0:02:35  lr: 0.002063  min_lr: 0.002063  loss: 2.4776 (2.5387)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0005  max mem: 42573
Epoch: [157]  [ 70/312]  eta: 0:02:23  lr: 0.002063  min_lr: 0.002063  loss: 2.4278 (2.5153)  weight_decay: 0.0500 (0.0500)  time: 0.4386  data: 0.0004  max mem: 42573
Epoch: [157]  [ 80/312]  eta: 0:02:13  lr: 0.002062  min_lr: 0.002062  loss: 2.7254 (2.5444)  weight_decay: 0.0500 (0.0500)  time: 0.4387  data: 0.0004  max mem: 42573
Epoch: [157]  [ 90/312]  eta: 0:02:03  lr: 0.002061  min_lr: 0.002061  loss: 2.6647 (2.5405)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [157]  [100/312]  eta: 0:01:55  lr: 0.002061  min_lr: 0.002061  loss: 2.5165 (2.5354)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [157]  [110/312]  eta: 0:01:48  lr: 0.002060  min_lr: 0.002060  loss: 2.4690 (2.5099)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [157]  [120/312]  eta: 0:01:41  lr: 0.002059  min_lr: 0.002059  loss: 2.5208 (2.5134)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [157]  [130/312]  eta: 0:01:34  lr: 0.002058  min_lr: 0.002058  loss: 2.5591 (2.5071)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [157]  [140/312]  eta: 0:01:28  lr: 0.002058  min_lr: 0.002058  loss: 2.3748 (2.5028)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [157]  [150/312]  eta: 0:01:22  lr: 0.002057  min_lr: 0.002057  loss: 2.5556 (2.5075)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [157]  [160/312]  eta: 0:01:16  lr: 0.002056  min_lr: 0.002056  loss: 2.4491 (2.4977)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [157]  [170/312]  eta: 0:01:11  lr: 0.002056  min_lr: 0.002056  loss: 2.2608 (2.4939)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [157]  [180/312]  eta: 0:01:05  lr: 0.002055  min_lr: 0.002055  loss: 2.3052 (2.4875)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [157]  [190/312]  eta: 0:01:00  lr: 0.002054  min_lr: 0.002054  loss: 2.2638 (2.4768)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0003  max mem: 42573
Epoch: [157]  [200/312]  eta: 0:00:54  lr: 0.002053  min_lr: 0.002053  loss: 2.4881 (2.4888)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [157]  [210/312]  eta: 0:00:49  lr: 0.002053  min_lr: 0.002053  loss: 2.6438 (2.4875)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [157]  [220/312]  eta: 0:00:44  lr: 0.002052  min_lr: 0.002052  loss: 2.3453 (2.4823)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [157]  [230/312]  eta: 0:00:39  lr: 0.002051  min_lr: 0.002051  loss: 2.4664 (2.4793)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [157]  [240/312]  eta: 0:00:34  lr: 0.002051  min_lr: 0.002051  loss: 2.5359 (2.4734)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [157]  [250/312]  eta: 0:00:29  lr: 0.002050  min_lr: 0.002050  loss: 2.5113 (2.4726)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [157]  [260/312]  eta: 0:00:24  lr: 0.002049  min_lr: 0.002049  loss: 2.5371 (2.4741)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [157]  [270/312]  eta: 0:00:19  lr: 0.002048  min_lr: 0.002048  loss: 2.5671 (2.4766)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [157]  [280/312]  eta: 0:00:15  lr: 0.002048  min_lr: 0.002048  loss: 2.3931 (2.4712)  weight_decay: 0.0500 (0.0500)  time: 0.4344  data: 0.0009  max mem: 42573
Epoch: [157]  [290/312]  eta: 0:00:10  lr: 0.002047  min_lr: 0.002047  loss: 2.3836 (2.4750)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0008  max mem: 42573
Epoch: [157]  [300/312]  eta: 0:00:05  lr: 0.002046  min_lr: 0.002046  loss: 2.3954 (2.4674)  weight_decay: 0.0500 (0.0500)  time: 0.4324  data: 0.0001  max mem: 42573
Epoch: [157]  [310/312]  eta: 0:00:00  lr: 0.002046  min_lr: 0.002046  loss: 2.3447 (2.4610)  weight_decay: 0.0500 (0.0500)  time: 0.4323  data: 0.0001  max mem: 42573
Epoch: [157]  [311/312]  eta: 0:00:00  lr: 0.002045  min_lr: 0.002045  loss: 2.1153 (2.4598)  weight_decay: 0.0500 (0.0500)  time: 0.4323  data: 0.0001  max mem: 42573
Epoch: [157] Total time: 0:02:27 (0.4729 s / it)
Averaged stats: lr: 0.002045  min_lr: 0.002045  loss: 2.1153 (2.4471)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:00:41  loss: 0.8796 (0.8796)  acc1: 79.6875 (79.6875)  acc5: 91.1458 (91.1458)  time: 4.6170  data: 4.5076  max mem: 42573
Test:  [8/9]  eta: 0:00:00  loss: 1.1731 (1.0908)  acc1: 72.3958 (72.8000)  acc5: 90.8854 (90.9760)  time: 0.5886  data: 0.5009  max mem: 42573
Test: Total time: 0:00:05 (0.5954 s / it)
* Acc@1 73.210 Acc@5 91.166 loss 1.087
Accuracy of the model on the 50000 test images: 73.2%
Max accuracy: 73.21%
Epoch: [158]  [  0/312]  eta: 0:48:03  lr: 0.002045  min_lr: 0.002045  loss: 2.4827 (2.4827)  weight_decay: 0.0500 (0.0500)  time: 9.2434  data: 8.7741  max mem: 42573
Epoch: [158]  [ 10/312]  eta: 0:07:04  lr: 0.002045  min_lr: 0.002045  loss: 2.5407 (2.6824)  weight_decay: 0.0500 (0.0500)  time: 1.4054  data: 0.7980  max mem: 42573
Epoch: [158]  [ 20/312]  eta: 0:04:35  lr: 0.002044  min_lr: 0.002044  loss: 2.4869 (2.5212)  weight_decay: 0.0500 (0.0500)  time: 0.5272  data: 0.0004  max mem: 42573
Epoch: [158]  [ 30/312]  eta: 0:03:39  lr: 0.002043  min_lr: 0.002043  loss: 2.1818 (2.4392)  weight_decay: 0.0500 (0.0500)  time: 0.4329  data: 0.0003  max mem: 42573
Epoch: [158]  [ 40/312]  eta: 0:03:08  lr: 0.002042  min_lr: 0.002042  loss: 2.1794 (2.4181)  weight_decay: 0.0500 (0.0500)  time: 0.4331  data: 0.0004  max mem: 42573
Epoch: [158]  [ 50/312]  eta: 0:02:48  lr: 0.002042  min_lr: 0.002042  loss: 2.3858 (2.4083)  weight_decay: 0.0500 (0.0500)  time: 0.4332  data: 0.0004  max mem: 42573
Epoch: [158]  [ 60/312]  eta: 0:02:33  lr: 0.002041  min_lr: 0.002041  loss: 2.4170 (2.4180)  weight_decay: 0.0500 (0.0500)  time: 0.4331  data: 0.0004  max mem: 42573
Epoch: [158]  [ 70/312]  eta: 0:02:21  lr: 0.002040  min_lr: 0.002040  loss: 2.4755 (2.4294)  weight_decay: 0.0500 (0.0500)  time: 0.4330  data: 0.0005  max mem: 42573
Epoch: [158]  [ 80/312]  eta: 0:02:11  lr: 0.002040  min_lr: 0.002040  loss: 2.5731 (2.4394)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0005  max mem: 42573
Epoch: [158]  [ 90/312]  eta: 0:02:02  lr: 0.002039  min_lr: 0.002039  loss: 2.6797 (2.4598)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [158]  [100/312]  eta: 0:01:54  lr: 0.002038  min_lr: 0.002038  loss: 2.6011 (2.4491)  weight_decay: 0.0500 (0.0500)  time: 0.4356  data: 0.0004  max mem: 42573
Epoch: [158]  [110/312]  eta: 0:01:47  lr: 0.002037  min_lr: 0.002037  loss: 2.5828 (2.4593)  weight_decay: 0.0500 (0.0500)  time: 0.4358  data: 0.0004  max mem: 42573
Epoch: [158]  [120/312]  eta: 0:01:40  lr: 0.002037  min_lr: 0.002037  loss: 2.5739 (2.4481)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [158]  [130/312]  eta: 0:01:33  lr: 0.002036  min_lr: 0.002036  loss: 2.5460 (2.4506)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [158]  [140/312]  eta: 0:01:27  lr: 0.002035  min_lr: 0.002035  loss: 2.5460 (2.4594)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [158]  [150/312]  eta: 0:01:21  lr: 0.002035  min_lr: 0.002035  loss: 2.4558 (2.4545)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [158]  [160/312]  eta: 0:01:16  lr: 0.002034  min_lr: 0.002034  loss: 2.3607 (2.4479)  weight_decay: 0.0500 (0.0500)  time: 0.4341  data: 0.0003  max mem: 42573
Epoch: [158]  [170/312]  eta: 0:01:10  lr: 0.002033  min_lr: 0.002033  loss: 2.3438 (2.4357)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [158]  [180/312]  eta: 0:01:05  lr: 0.002032  min_lr: 0.002032  loss: 2.3438 (2.4314)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [158]  [190/312]  eta: 0:00:59  lr: 0.002032  min_lr: 0.002032  loss: 2.3452 (2.4299)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [158]  [200/312]  eta: 0:00:54  lr: 0.002031  min_lr: 0.002031  loss: 2.2887 (2.4262)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [158]  [210/312]  eta: 0:00:49  lr: 0.002030  min_lr: 0.002030  loss: 2.5620 (2.4351)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [158]  [220/312]  eta: 0:00:44  lr: 0.002030  min_lr: 0.002030  loss: 2.7326 (2.4449)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [158]  [230/312]  eta: 0:00:39  lr: 0.002029  min_lr: 0.002029  loss: 2.6450 (2.4454)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [158]  [240/312]  eta: 0:00:34  lr: 0.002028  min_lr: 0.002028  loss: 2.5907 (2.4539)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [158]  [250/312]  eta: 0:00:29  lr: 0.002027  min_lr: 0.002027  loss: 2.6524 (2.4603)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [158]  [260/312]  eta: 0:00:24  lr: 0.002027  min_lr: 0.002027  loss: 2.3894 (2.4570)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [158]  [270/312]  eta: 0:00:19  lr: 0.002026  min_lr: 0.002026  loss: 2.5216 (2.4615)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [158]  [280/312]  eta: 0:00:15  lr: 0.002025  min_lr: 0.002025  loss: 2.4017 (2.4536)  weight_decay: 0.0500 (0.0500)  time: 0.4344  data: 0.0010  max mem: 42573
Epoch: [158]  [290/312]  eta: 0:00:10  lr: 0.002025  min_lr: 0.002025  loss: 2.3637 (2.4563)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0008  max mem: 42573
Epoch: [158]  [300/312]  eta: 0:00:05  lr: 0.002024  min_lr: 0.002024  loss: 2.5270 (2.4561)  weight_decay: 0.0500 (0.0500)  time: 0.4326  data: 0.0001  max mem: 42573
Epoch: [158]  [310/312]  eta: 0:00:00  lr: 0.002023  min_lr: 0.002023  loss: 2.6279 (2.4608)  weight_decay: 0.0500 (0.0500)  time: 0.4323  data: 0.0001  max mem: 42573
Epoch: [158]  [311/312]  eta: 0:00:00  lr: 0.002023  min_lr: 0.002023  loss: 2.6473 (2.4627)  weight_decay: 0.0500 (0.0500)  time: 0.4323  data: 0.0001  max mem: 42573
Epoch: [158] Total time: 0:02:26 (0.4707 s / it)
Averaged stats: lr: 0.002023  min_lr: 0.002023  loss: 2.6473 (2.4357)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:00:47  loss: 0.8774 (0.8774)  acc1: 78.3854 (78.3854)  acc5: 92.4479 (92.4479)  time: 5.3094  data: 5.2000  max mem: 42573
Test:  [8/9]  eta: 0:00:00  loss: 1.2026 (1.1224)  acc1: 71.8750 (71.4240)  acc5: 92.1875 (91.1040)  time: 0.6669  data: 0.5778  max mem: 42573
Test: Total time: 0:00:06 (0.6870 s / it)
* Acc@1 72.608 Acc@5 91.006 loss 1.118
Accuracy of the model on the 50000 test images: 72.6%
Max accuracy: 73.21%
Epoch: [159]  [  0/312]  eta: 0:48:56  lr: 0.002023  min_lr: 0.002023  loss: 2.7196 (2.7196)  weight_decay: 0.0500 (0.0500)  time: 9.4133  data: 7.8597  max mem: 42573
Epoch: [159]  [ 10/312]  eta: 0:06:53  lr: 0.002022  min_lr: 0.002022  loss: 2.6715 (2.4422)  weight_decay: 0.0500 (0.0500)  time: 1.3708  data: 0.7149  max mem: 42573
Epoch: [159]  [ 20/312]  eta: 0:04:29  lr: 0.002021  min_lr: 0.002021  loss: 2.2776 (2.4034)  weight_decay: 0.0500 (0.0500)  time: 0.5001  data: 0.0004  max mem: 42573
Epoch: [159]  [ 30/312]  eta: 0:03:36  lr: 0.002021  min_lr: 0.002021  loss: 2.5014 (2.4888)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0003  max mem: 42573
Epoch: [159]  [ 40/312]  eta: 0:03:06  lr: 0.002020  min_lr: 0.002020  loss: 2.5544 (2.4499)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [159]  [ 50/312]  eta: 0:02:46  lr: 0.002019  min_lr: 0.002019  loss: 2.3040 (2.4177)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [159]  [ 60/312]  eta: 0:02:31  lr: 0.002019  min_lr: 0.002019  loss: 2.2751 (2.3978)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0005  max mem: 42573
Epoch: [159]  [ 70/312]  eta: 0:02:20  lr: 0.002018  min_lr: 0.002018  loss: 2.5631 (2.4254)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [159]  [ 80/312]  eta: 0:02:10  lr: 0.002017  min_lr: 0.002017  loss: 2.6284 (2.4329)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [159]  [ 90/312]  eta: 0:02:01  lr: 0.002016  min_lr: 0.002016  loss: 2.4069 (2.4139)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [159]  [100/312]  eta: 0:01:53  lr: 0.002016  min_lr: 0.002016  loss: 2.2522 (2.4157)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [159]  [110/312]  eta: 0:01:46  lr: 0.002015  min_lr: 0.002015  loss: 2.5333 (2.4323)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [159]  [120/312]  eta: 0:01:39  lr: 0.002014  min_lr: 0.002014  loss: 2.5333 (2.4311)  weight_decay: 0.0500 (0.0500)  time: 0.4382  data: 0.0004  max mem: 42573
Epoch: [159]  [130/312]  eta: 0:01:33  lr: 0.002014  min_lr: 0.002014  loss: 2.5587 (2.4446)  weight_decay: 0.0500 (0.0500)  time: 0.4380  data: 0.0004  max mem: 42573
Epoch: [159]  [140/312]  eta: 0:01:27  lr: 0.002013  min_lr: 0.002013  loss: 2.4997 (2.4290)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0003  max mem: 42573
Epoch: [159]  [150/312]  eta: 0:01:21  lr: 0.002012  min_lr: 0.002012  loss: 2.3652 (2.4271)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [159]  [160/312]  eta: 0:01:15  lr: 0.002011  min_lr: 0.002011  loss: 2.4938 (2.4290)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [159]  [170/312]  eta: 0:01:10  lr: 0.002011  min_lr: 0.002011  loss: 2.6450 (2.4293)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [159]  [180/312]  eta: 0:01:04  lr: 0.002010  min_lr: 0.002010  loss: 2.6784 (2.4350)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [159]  [190/312]  eta: 0:00:59  lr: 0.002009  min_lr: 0.002009  loss: 2.5410 (2.4396)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [159]  [200/312]  eta: 0:00:54  lr: 0.002009  min_lr: 0.002009  loss: 2.5410 (2.4431)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [159]  [210/312]  eta: 0:00:49  lr: 0.002008  min_lr: 0.002008  loss: 2.5755 (2.4507)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [159]  [220/312]  eta: 0:00:44  lr: 0.002007  min_lr: 0.002007  loss: 2.5346 (2.4548)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [159]  [230/312]  eta: 0:00:39  lr: 0.002006  min_lr: 0.002006  loss: 2.6027 (2.4621)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [159]  [240/312]  eta: 0:00:34  lr: 0.002006  min_lr: 0.002006  loss: 2.6027 (2.4666)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0003  max mem: 42573
Epoch: [159]  [250/312]  eta: 0:00:29  lr: 0.002005  min_lr: 0.002005  loss: 2.4465 (2.4614)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0003  max mem: 42573
Epoch: [159]  [260/312]  eta: 0:00:24  lr: 0.002004  min_lr: 0.002004  loss: 2.3263 (2.4518)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0003  max mem: 42573
Epoch: [159]  [270/312]  eta: 0:00:19  lr: 0.002004  min_lr: 0.002004  loss: 2.3294 (2.4485)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0003  max mem: 42573
Epoch: [159]  [280/312]  eta: 0:00:15  lr: 0.002003  min_lr: 0.002003  loss: 2.5616 (2.4540)  weight_decay: 0.0500 (0.0500)  time: 0.4348  data: 0.0009  max mem: 42573
Epoch: [159]  [290/312]  eta: 0:00:10  lr: 0.002002  min_lr: 0.002002  loss: 2.5820 (2.4605)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0008  max mem: 42573
Epoch: [159]  [300/312]  eta: 0:00:05  lr: 0.002001  min_lr: 0.002001  loss: 2.5514 (2.4543)  weight_decay: 0.0500 (0.0500)  time: 0.4327  data: 0.0001  max mem: 42573
Epoch: [159]  [310/312]  eta: 0:00:00  lr: 0.002001  min_lr: 0.002001  loss: 2.5514 (2.4553)  weight_decay: 0.0500 (0.0500)  time: 0.4327  data: 0.0001  max mem: 42573
Epoch: [159]  [311/312]  eta: 0:00:00  lr: 0.002001  min_lr: 0.002001  loss: 2.3811 (2.4550)  weight_decay: 0.0500 (0.0500)  time: 0.4327  data: 0.0001  max mem: 42573
Epoch: [159] Total time: 0:02:26 (0.4699 s / it)
Averaged stats: lr: 0.002001  min_lr: 0.002001  loss: 2.3811 (2.4336)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:00:45  loss: 0.7671 (0.7671)  acc1: 80.2083 (80.2083)  acc5: 94.0104 (94.0104)  time: 5.0575  data: 4.9481  max mem: 42573
Test:  [8/9]  eta: 0:00:00  loss: 1.1201 (1.0509)  acc1: 72.9167 (73.6000)  acc5: 91.9271 (91.5840)  time: 0.6393  data: 0.5499  max mem: 42573
Test: Total time: 0:00:05 (0.6629 s / it)
* Acc@1 73.792 Acc@5 91.696 loss 1.043
Accuracy of the model on the 50000 test images: 73.8%
Max accuracy: 73.79%
Epoch: [160]  [  0/312]  eta: 0:49:51  lr: 0.002001  min_lr: 0.002001  loss: 2.8033 (2.8033)  weight_decay: 0.0500 (0.0500)  time: 9.5888  data: 8.9302  max mem: 42573
Epoch: [160]  [ 10/312]  eta: 0:07:21  lr: 0.002000  min_lr: 0.002000  loss: 2.5997 (2.6321)  weight_decay: 0.0500 (0.0500)  time: 1.4611  data: 0.8122  max mem: 42573
Epoch: [160]  [ 20/312]  eta: 0:04:43  lr: 0.001999  min_lr: 0.001999  loss: 2.4389 (2.4339)  weight_decay: 0.0500 (0.0500)  time: 0.5406  data: 0.0004  max mem: 42573
Epoch: [160]  [ 30/312]  eta: 0:03:44  lr: 0.001998  min_lr: 0.001998  loss: 2.1480 (2.3918)  weight_decay: 0.0500 (0.0500)  time: 0.4331  data: 0.0004  max mem: 42573
Epoch: [160]  [ 40/312]  eta: 0:03:12  lr: 0.001998  min_lr: 0.001998  loss: 2.4092 (2.4086)  weight_decay: 0.0500 (0.0500)  time: 0.4332  data: 0.0004  max mem: 42573
Epoch: [160]  [ 50/312]  eta: 0:02:51  lr: 0.001997  min_lr: 0.001997  loss: 2.4736 (2.4336)  weight_decay: 0.0500 (0.0500)  time: 0.4332  data: 0.0004  max mem: 42573
Epoch: [160]  [ 60/312]  eta: 0:02:35  lr: 0.001996  min_lr: 0.001996  loss: 2.5101 (2.4510)  weight_decay: 0.0500 (0.0500)  time: 0.4332  data: 0.0004  max mem: 42573
Epoch: [160]  [ 70/312]  eta: 0:02:23  lr: 0.001995  min_lr: 0.001995  loss: 2.5101 (2.4580)  weight_decay: 0.0500 (0.0500)  time: 0.4332  data: 0.0004  max mem: 42573
Epoch: [160]  [ 80/312]  eta: 0:02:12  lr: 0.001995  min_lr: 0.001995  loss: 2.6317 (2.4803)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [160]  [ 90/312]  eta: 0:02:03  lr: 0.001994  min_lr: 0.001994  loss: 2.6317 (2.4870)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [160]  [100/312]  eta: 0:01:55  lr: 0.001993  min_lr: 0.001993  loss: 2.7123 (2.5091)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [160]  [110/312]  eta: 0:01:48  lr: 0.001993  min_lr: 0.001993  loss: 2.6370 (2.4999)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [160]  [120/312]  eta: 0:01:41  lr: 0.001992  min_lr: 0.001992  loss: 2.5245 (2.4890)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [160]  [130/312]  eta: 0:01:34  lr: 0.001991  min_lr: 0.001991  loss: 2.5711 (2.4830)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [160]  [140/312]  eta: 0:01:28  lr: 0.001990  min_lr: 0.001990  loss: 2.4088 (2.4721)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [160]  [150/312]  eta: 0:01:22  lr: 0.001990  min_lr: 0.001990  loss: 2.4088 (2.4715)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [160]  [160/312]  eta: 0:01:16  lr: 0.001989  min_lr: 0.001989  loss: 2.6002 (2.4800)  weight_decay: 0.0500 (0.0500)  time: 0.4369  data: 0.0004  max mem: 42573
Epoch: [160]  [170/312]  eta: 0:01:10  lr: 0.001988  min_lr: 0.001988  loss: 2.5577 (2.4757)  weight_decay: 0.0500 (0.0500)  time: 0.4370  data: 0.0004  max mem: 42573
Epoch: [160]  [180/312]  eta: 0:01:05  lr: 0.001988  min_lr: 0.001988  loss: 2.4516 (2.4659)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [160]  [190/312]  eta: 0:01:00  lr: 0.001987  min_lr: 0.001987  loss: 2.4657 (2.4570)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [160]  [200/312]  eta: 0:00:54  lr: 0.001986  min_lr: 0.001986  loss: 2.2622 (2.4492)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [160]  [210/312]  eta: 0:00:49  lr: 0.001985  min_lr: 0.001985  loss: 2.3158 (2.4504)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [160]  [220/312]  eta: 0:00:44  lr: 0.001985  min_lr: 0.001985  loss: 2.5593 (2.4554)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [160]  [230/312]  eta: 0:00:39  lr: 0.001984  min_lr: 0.001984  loss: 2.5593 (2.4503)  weight_decay: 0.0500 (0.0500)  time: 0.4332  data: 0.0003  max mem: 42573
Epoch: [160]  [240/312]  eta: 0:00:34  lr: 0.001983  min_lr: 0.001983  loss: 2.2988 (2.4446)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [160]  [250/312]  eta: 0:00:29  lr: 0.001983  min_lr: 0.001983  loss: 2.4953 (2.4450)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [160]  [260/312]  eta: 0:00:24  lr: 0.001982  min_lr: 0.001982  loss: 2.6229 (2.4444)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [160]  [270/312]  eta: 0:00:19  lr: 0.001981  min_lr: 0.001981  loss: 2.4821 (2.4392)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [160]  [280/312]  eta: 0:00:15  lr: 0.001980  min_lr: 0.001980  loss: 2.4821 (2.4392)  weight_decay: 0.0500 (0.0500)  time: 0.4342  data: 0.0009  max mem: 42573
Epoch: [160]  [290/312]  eta: 0:00:10  lr: 0.001980  min_lr: 0.001980  loss: 2.3737 (2.4375)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0008  max mem: 42573
Epoch: [160]  [300/312]  eta: 0:00:05  lr: 0.001979  min_lr: 0.001979  loss: 2.3901 (2.4418)  weight_decay: 0.0500 (0.0500)  time: 0.4325  data: 0.0001  max mem: 42573
Epoch: [160]  [310/312]  eta: 0:00:00  lr: 0.001978  min_lr: 0.001978  loss: 2.3839 (2.4359)  weight_decay: 0.0500 (0.0500)  time: 0.4323  data: 0.0001  max mem: 42573
Epoch: [160]  [311/312]  eta: 0:00:00  lr: 0.001978  min_lr: 0.001978  loss: 2.3839 (2.4365)  weight_decay: 0.0500 (0.0500)  time: 0.4323  data: 0.0001  max mem: 42573
Epoch: [160] Total time: 0:02:27 (0.4729 s / it)
Averaged stats: lr: 0.001978  min_lr: 0.001978  loss: 2.3839 (2.4287)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:00:43  loss: 0.8155 (0.8155)  acc1: 80.7292 (80.7292)  acc5: 93.7500 (93.7500)  time: 4.8729  data: 4.7632  max mem: 42573
Test:  [8/9]  eta: 0:00:00  loss: 1.1386 (1.0958)  acc1: 73.4375 (72.1920)  acc5: 92.1875 (91.0720)  time: 0.6377  data: 0.5446  max mem: 42573
Test: Total time: 0:00:05 (0.6455 s / it)
* Acc@1 73.074 Acc@5 91.170 loss 1.090
Accuracy of the model on the 50000 test images: 73.1%
Max accuracy: 73.79%
Epoch: [161]  [  0/312]  eta: 0:48:57  lr: 0.001978  min_lr: 0.001978  loss: 3.1028 (3.1028)  weight_decay: 0.0500 (0.0500)  time: 9.4150  data: 8.6183  max mem: 42573
Epoch: [161]  [ 10/312]  eta: 0:06:58  lr: 0.001977  min_lr: 0.001977  loss: 2.3739 (2.4950)  weight_decay: 0.0500 (0.0500)  time: 1.3860  data: 0.7839  max mem: 42573
Epoch: [161]  [ 20/312]  eta: 0:04:32  lr: 0.001977  min_lr: 0.001977  loss: 2.3739 (2.4493)  weight_decay: 0.0500 (0.0500)  time: 0.5085  data: 0.0005  max mem: 42573
Epoch: [161]  [ 30/312]  eta: 0:03:37  lr: 0.001976  min_lr: 0.001976  loss: 2.3647 (2.3959)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0005  max mem: 42573
Epoch: [161]  [ 40/312]  eta: 0:03:07  lr: 0.001975  min_lr: 0.001975  loss: 2.5030 (2.4067)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [161]  [ 50/312]  eta: 0:02:47  lr: 0.001974  min_lr: 0.001974  loss: 2.6107 (2.4147)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [161]  [ 60/312]  eta: 0:02:32  lr: 0.001974  min_lr: 0.001974  loss: 2.4727 (2.4026)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [161]  [ 70/312]  eta: 0:02:20  lr: 0.001973  min_lr: 0.001973  loss: 2.4975 (2.4065)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [161]  [ 80/312]  eta: 0:02:10  lr: 0.001972  min_lr: 0.001972  loss: 2.5608 (2.4292)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [161]  [ 90/312]  eta: 0:02:01  lr: 0.001972  min_lr: 0.001972  loss: 2.5961 (2.4241)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [161]  [100/312]  eta: 0:01:53  lr: 0.001971  min_lr: 0.001971  loss: 2.2749 (2.4068)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [161]  [110/312]  eta: 0:01:46  lr: 0.001970  min_lr: 0.001970  loss: 2.1104 (2.3952)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [161]  [120/312]  eta: 0:01:39  lr: 0.001969  min_lr: 0.001969  loss: 2.3247 (2.3945)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [161]  [130/312]  eta: 0:01:33  lr: 0.001969  min_lr: 0.001969  loss: 2.4120 (2.4078)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [161]  [140/312]  eta: 0:01:27  lr: 0.001968  min_lr: 0.001968  loss: 2.4288 (2.4093)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [161]  [150/312]  eta: 0:01:21  lr: 0.001967  min_lr: 0.001967  loss: 2.2355 (2.3963)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [161]  [160/312]  eta: 0:01:15  lr: 0.001967  min_lr: 0.001967  loss: 2.3617 (2.4101)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [161]  [170/312]  eta: 0:01:10  lr: 0.001966  min_lr: 0.001966  loss: 2.5482 (2.4010)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [161]  [180/312]  eta: 0:01:04  lr: 0.001965  min_lr: 0.001965  loss: 2.5140 (2.4077)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [161]  [190/312]  eta: 0:00:59  lr: 0.001964  min_lr: 0.001964  loss: 2.5595 (2.4085)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0003  max mem: 42573
Epoch: [161]  [200/312]  eta: 0:00:54  lr: 0.001964  min_lr: 0.001964  loss: 2.5595 (2.4112)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0003  max mem: 42573
Epoch: [161]  [210/312]  eta: 0:00:49  lr: 0.001963  min_lr: 0.001963  loss: 2.5864 (2.4182)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0004  max mem: 42573
Epoch: [161]  [220/312]  eta: 0:00:44  lr: 0.001962  min_lr: 0.001962  loss: 2.5515 (2.4219)  weight_decay: 0.0500 (0.0500)  time: 0.4485  data: 0.0004  max mem: 42573
Epoch: [161]  [230/312]  eta: 0:00:39  lr: 0.001962  min_lr: 0.001962  loss: 2.4804 (2.4221)  weight_decay: 0.0500 (0.0500)  time: 0.4482  data: 0.0003  max mem: 42573
Epoch: [161]  [240/312]  eta: 0:00:34  lr: 0.001961  min_lr: 0.001961  loss: 2.5020 (2.4214)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [161]  [250/312]  eta: 0:00:29  lr: 0.001960  min_lr: 0.001960  loss: 2.3507 (2.4137)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [161]  [260/312]  eta: 0:00:24  lr: 0.001959  min_lr: 0.001959  loss: 2.4566 (2.4193)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [161]  [270/312]  eta: 0:00:19  lr: 0.001959  min_lr: 0.001959  loss: 2.6244 (2.4276)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [161]  [280/312]  eta: 0:00:15  lr: 0.001958  min_lr: 0.001958  loss: 2.5883 (2.4270)  weight_decay: 0.0500 (0.0500)  time: 0.4346  data: 0.0011  max mem: 42573
Epoch: [161]  [290/312]  eta: 0:00:10  lr: 0.001957  min_lr: 0.001957  loss: 2.5963 (2.4312)  weight_decay: 0.0500 (0.0500)  time: 0.4341  data: 0.0009  max mem: 42573
Epoch: [161]  [300/312]  eta: 0:00:05  lr: 0.001956  min_lr: 0.001956  loss: 2.6445 (2.4330)  weight_decay: 0.0500 (0.0500)  time: 0.4324  data: 0.0001  max mem: 42573
Epoch: [161]  [310/312]  eta: 0:00:00  lr: 0.001956  min_lr: 0.001956  loss: 2.6445 (2.4400)  weight_decay: 0.0500 (0.0500)  time: 0.4323  data: 0.0001  max mem: 42573
Epoch: [161]  [311/312]  eta: 0:00:00  lr: 0.001956  min_lr: 0.001956  loss: 2.4800 (2.4382)  weight_decay: 0.0500 (0.0500)  time: 0.4323  data: 0.0001  max mem: 42573
Epoch: [161] Total time: 0:02:26 (0.4711 s / it)
Averaged stats: lr: 0.001956  min_lr: 0.001956  loss: 2.4800 (2.4325)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:00:40  loss: 0.8551 (0.8551)  acc1: 80.7292 (80.7292)  acc5: 93.7500 (93.7500)  time: 4.4888  data: 4.3804  max mem: 42573
Test:  [8/9]  eta: 0:00:00  loss: 1.1451 (1.1073)  acc1: 73.9583 (73.4400)  acc5: 90.1042 (91.2000)  time: 0.5834  data: 0.4961  max mem: 42573
Test: Total time: 0:00:05 (0.5904 s / it)
* Acc@1 73.048 Acc@5 91.250 loss 1.106
Accuracy of the model on the 50000 test images: 73.0%
Max accuracy: 73.79%
Epoch: [162]  [  0/312]  eta: 0:52:13  lr: 0.001956  min_lr: 0.001956  loss: 2.1167 (2.1167)  weight_decay: 0.0500 (0.0500)  time: 10.0437  data: 5.9761  max mem: 42573
Epoch: [162]  [ 10/312]  eta: 0:07:28  lr: 0.001955  min_lr: 0.001955  loss: 2.5388 (2.5060)  weight_decay: 0.0500 (0.0500)  time: 1.4864  data: 0.7108  max mem: 42573
Epoch: [162]  [ 20/312]  eta: 0:04:47  lr: 0.001954  min_lr: 0.001954  loss: 2.6451 (2.6035)  weight_decay: 0.0500 (0.0500)  time: 0.5318  data: 0.0923  max mem: 42573
Epoch: [162]  [ 30/312]  eta: 0:03:47  lr: 0.001953  min_lr: 0.001953  loss: 2.6736 (2.6014)  weight_decay: 0.0500 (0.0500)  time: 0.4332  data: 0.0003  max mem: 42573
Epoch: [162]  [ 40/312]  eta: 0:03:14  lr: 0.001953  min_lr: 0.001953  loss: 2.6409 (2.5360)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [162]  [ 50/312]  eta: 0:02:53  lr: 0.001952  min_lr: 0.001952  loss: 2.3163 (2.4861)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [162]  [ 60/312]  eta: 0:02:37  lr: 0.001951  min_lr: 0.001951  loss: 2.5775 (2.5198)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [162]  [ 70/312]  eta: 0:02:24  lr: 0.001951  min_lr: 0.001951  loss: 2.6025 (2.5300)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [162]  [ 80/312]  eta: 0:02:13  lr: 0.001950  min_lr: 0.001950  loss: 2.5067 (2.4840)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [162]  [ 90/312]  eta: 0:02:04  lr: 0.001949  min_lr: 0.001949  loss: 2.1580 (2.4587)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [162]  [100/312]  eta: 0:01:56  lr: 0.001948  min_lr: 0.001948  loss: 2.2637 (2.4403)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [162]  [110/312]  eta: 0:01:48  lr: 0.001948  min_lr: 0.001948  loss: 2.4130 (2.4465)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0004  max mem: 42573
Epoch: [162]  [120/312]  eta: 0:01:41  lr: 0.001947  min_lr: 0.001947  loss: 2.4130 (2.4205)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [162]  [130/312]  eta: 0:01:35  lr: 0.001946  min_lr: 0.001946  loss: 2.2931 (2.4245)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [162]  [140/312]  eta: 0:01:28  lr: 0.001946  min_lr: 0.001946  loss: 2.6187 (2.4377)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [162]  [150/312]  eta: 0:01:22  lr: 0.001945  min_lr: 0.001945  loss: 2.5982 (2.4438)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [162]  [160/312]  eta: 0:01:16  lr: 0.001944  min_lr: 0.001944  loss: 2.4750 (2.4404)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [162]  [170/312]  eta: 0:01:11  lr: 0.001943  min_lr: 0.001943  loss: 2.4259 (2.4361)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [162]  [180/312]  eta: 0:01:05  lr: 0.001943  min_lr: 0.001943  loss: 2.4259 (2.4366)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [162]  [190/312]  eta: 0:01:00  lr: 0.001942  min_lr: 0.001942  loss: 2.2603 (2.4211)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [162]  [200/312]  eta: 0:00:55  lr: 0.001941  min_lr: 0.001941  loss: 2.3716 (2.4283)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [162]  [210/312]  eta: 0:00:49  lr: 0.001941  min_lr: 0.001941  loss: 2.4989 (2.4152)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [162]  [220/312]  eta: 0:00:44  lr: 0.001940  min_lr: 0.001940  loss: 2.3484 (2.4178)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [162]  [230/312]  eta: 0:00:39  lr: 0.001939  min_lr: 0.001939  loss: 2.4943 (2.4164)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0003  max mem: 42573
Epoch: [162]  [240/312]  eta: 0:00:34  lr: 0.001938  min_lr: 0.001938  loss: 2.4091 (2.4186)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [162]  [250/312]  eta: 0:00:29  lr: 0.001938  min_lr: 0.001938  loss: 2.5540 (2.4189)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [162]  [260/312]  eta: 0:00:24  lr: 0.001937  min_lr: 0.001937  loss: 2.3329 (2.4162)  weight_decay: 0.0500 (0.0500)  time: 0.4392  data: 0.0004  max mem: 42573
Epoch: [162]  [270/312]  eta: 0:00:20  lr: 0.001936  min_lr: 0.001936  loss: 2.4078 (2.4197)  weight_decay: 0.0500 (0.0500)  time: 0.4391  data: 0.0004  max mem: 42573
Epoch: [162]  [280/312]  eta: 0:00:15  lr: 0.001936  min_lr: 0.001936  loss: 2.5129 (2.4159)  weight_decay: 0.0500 (0.0500)  time: 0.4343  data: 0.0009  max mem: 42573
Epoch: [162]  [290/312]  eta: 0:00:10  lr: 0.001935  min_lr: 0.001935  loss: 2.5129 (2.4188)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0008  max mem: 42573
Epoch: [162]  [300/312]  eta: 0:00:05  lr: 0.001934  min_lr: 0.001934  loss: 2.4148 (2.4180)  weight_decay: 0.0500 (0.0500)  time: 0.4324  data: 0.0001  max mem: 42573
Epoch: [162]  [310/312]  eta: 0:00:00  lr: 0.001933  min_lr: 0.001933  loss: 2.3713 (2.4172)  weight_decay: 0.0500 (0.0500)  time: 0.4323  data: 0.0001  max mem: 42573
Epoch: [162]  [311/312]  eta: 0:00:00  lr: 0.001933  min_lr: 0.001933  loss: 2.3713 (2.4183)  weight_decay: 0.0500 (0.0500)  time: 0.4323  data: 0.0001  max mem: 42573
Epoch: [162] Total time: 0:02:27 (0.4740 s / it)
Averaged stats: lr: 0.001933  min_lr: 0.001933  loss: 2.3713 (2.4167)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:00:43  loss: 0.7753 (0.7753)  acc1: 80.4688 (80.4688)  acc5: 93.7500 (93.7500)  time: 4.8452  data: 4.7357  max mem: 42573
Test:  [8/9]  eta: 0:00:00  loss: 1.0787 (1.0263)  acc1: 75.5208 (74.6880)  acc5: 90.8854 (91.1680)  time: 0.6153  data: 0.5263  max mem: 42573
Test: Total time: 0:00:05 (0.6222 s / it)
* Acc@1 74.200 Acc@5 91.862 loss 1.013
Accuracy of the model on the 50000 test images: 74.2%
Max accuracy: 74.20%
Epoch: [163]  [  0/312]  eta: 0:47:17  lr: 0.001933  min_lr: 0.001933  loss: 2.0194 (2.0194)  weight_decay: 0.0500 (0.0500)  time: 9.0946  data: 8.4245  max mem: 42573
Epoch: [163]  [ 10/312]  eta: 0:07:00  lr: 0.001932  min_lr: 0.001932  loss: 2.5641 (2.3698)  weight_decay: 0.0500 (0.0500)  time: 1.3918  data: 0.7663  max mem: 42573
Epoch: [163]  [ 20/312]  eta: 0:04:33  lr: 0.001932  min_lr: 0.001932  loss: 2.5147 (2.3747)  weight_decay: 0.0500 (0.0500)  time: 0.5275  data: 0.0004  max mem: 42573
Epoch: [163]  [ 30/312]  eta: 0:03:38  lr: 0.001931  min_lr: 0.001931  loss: 2.4814 (2.3777)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [163]  [ 40/312]  eta: 0:03:07  lr: 0.001930  min_lr: 0.001930  loss: 2.5064 (2.4294)  weight_decay: 0.0500 (0.0500)  time: 0.4332  data: 0.0004  max mem: 42573
Epoch: [163]  [ 50/312]  eta: 0:02:47  lr: 0.001930  min_lr: 0.001930  loss: 2.5807 (2.4238)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0005  max mem: 42573
Epoch: [163]  [ 60/312]  eta: 0:02:32  lr: 0.001929  min_lr: 0.001929  loss: 2.5505 (2.4407)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [163]  [ 70/312]  eta: 0:02:20  lr: 0.001928  min_lr: 0.001928  loss: 2.5095 (2.4312)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [163]  [ 80/312]  eta: 0:02:10  lr: 0.001927  min_lr: 0.001927  loss: 2.0409 (2.4105)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [163]  [ 90/312]  eta: 0:02:01  lr: 0.001927  min_lr: 0.001927  loss: 2.0409 (2.4044)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [163]  [100/312]  eta: 0:01:54  lr: 0.001926  min_lr: 0.001926  loss: 2.4851 (2.4240)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0003  max mem: 42573
Epoch: [163]  [110/312]  eta: 0:01:46  lr: 0.001925  min_lr: 0.001925  loss: 2.6788 (2.4353)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0003  max mem: 42573
Epoch: [163]  [120/312]  eta: 0:01:39  lr: 0.001925  min_lr: 0.001925  loss: 2.4246 (2.4408)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [163]  [130/312]  eta: 0:01:33  lr: 0.001924  min_lr: 0.001924  loss: 2.3453 (2.4273)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [163]  [140/312]  eta: 0:01:27  lr: 0.001923  min_lr: 0.001923  loss: 2.5226 (2.4292)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [163]  [150/312]  eta: 0:01:21  lr: 0.001922  min_lr: 0.001922  loss: 2.5828 (2.4350)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [163]  [160/312]  eta: 0:01:15  lr: 0.001922  min_lr: 0.001922  loss: 2.5574 (2.4364)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [163]  [170/312]  eta: 0:01:10  lr: 0.001921  min_lr: 0.001921  loss: 2.6356 (2.4553)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [163]  [180/312]  eta: 0:01:04  lr: 0.001920  min_lr: 0.001920  loss: 2.7267 (2.4645)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [163]  [190/312]  eta: 0:00:59  lr: 0.001920  min_lr: 0.001920  loss: 2.6360 (2.4680)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [163]  [200/312]  eta: 0:00:54  lr: 0.001919  min_lr: 0.001919  loss: 2.5660 (2.4737)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [163]  [210/312]  eta: 0:00:49  lr: 0.001918  min_lr: 0.001918  loss: 2.6128 (2.4775)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0003  max mem: 42573
Epoch: [163]  [220/312]  eta: 0:00:44  lr: 0.001917  min_lr: 0.001917  loss: 2.6060 (2.4789)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [163]  [230/312]  eta: 0:00:39  lr: 0.001917  min_lr: 0.001917  loss: 2.6139 (2.4866)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [163]  [240/312]  eta: 0:00:34  lr: 0.001916  min_lr: 0.001916  loss: 2.5493 (2.4826)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [163]  [250/312]  eta: 0:00:29  lr: 0.001915  min_lr: 0.001915  loss: 2.4847 (2.4781)  weight_decay: 0.0500 (0.0500)  time: 0.4385  data: 0.0004  max mem: 42573
Epoch: [163]  [260/312]  eta: 0:00:24  lr: 0.001915  min_lr: 0.001915  loss: 2.4161 (2.4722)  weight_decay: 0.0500 (0.0500)  time: 0.4386  data: 0.0004  max mem: 42573
Epoch: [163]  [270/312]  eta: 0:00:19  lr: 0.001914  min_lr: 0.001914  loss: 2.4714 (2.4729)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [163]  [280/312]  eta: 0:00:15  lr: 0.001913  min_lr: 0.001913  loss: 2.5108 (2.4722)  weight_decay: 0.0500 (0.0500)  time: 0.4346  data: 0.0010  max mem: 42573
Epoch: [163]  [290/312]  eta: 0:00:10  lr: 0.001912  min_lr: 0.001912  loss: 2.5047 (2.4678)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0009  max mem: 42573
Epoch: [163]  [300/312]  eta: 0:00:05  lr: 0.001912  min_lr: 0.001912  loss: 2.4994 (2.4686)  weight_decay: 0.0500 (0.0500)  time: 0.4324  data: 0.0001  max mem: 42573
Epoch: [163]  [310/312]  eta: 0:00:00  lr: 0.001911  min_lr: 0.001911  loss: 2.6272 (2.4739)  weight_decay: 0.0500 (0.0500)  time: 0.4324  data: 0.0001  max mem: 42573
Epoch: [163]  [311/312]  eta: 0:00:00  lr: 0.001911  min_lr: 0.001911  loss: 2.6303 (2.4751)  weight_decay: 0.0500 (0.0500)  time: 0.4324  data: 0.0001  max mem: 42573
Epoch: [163] Total time: 0:02:26 (0.4706 s / it)
Averaged stats: lr: 0.001911  min_lr: 0.001911  loss: 2.6303 (2.4236)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:00:42  loss: 0.8240 (0.8240)  acc1: 78.3854 (78.3854)  acc5: 92.9688 (92.9688)  time: 4.7166  data: 4.6078  max mem: 42573
Test:  [8/9]  eta: 0:00:00  loss: 1.1218 (1.1406)  acc1: 71.8750 (71.7760)  acc5: 91.1458 (90.4640)  time: 0.6205  data: 0.5323  max mem: 42573
Test: Total time: 0:00:05 (0.6326 s / it)
* Acc@1 72.364 Acc@5 90.770 loss 1.134
Accuracy of the model on the 50000 test images: 72.4%
Max accuracy: 74.20%
Epoch: [164]  [  0/312]  eta: 0:52:19  lr: 0.001911  min_lr: 0.001911  loss: 2.6094 (2.6094)  weight_decay: 0.0500 (0.0500)  time: 10.0610  data: 6.7357  max mem: 42573
Epoch: [164]  [ 10/312]  eta: 0:08:00  lr: 0.001910  min_lr: 0.001910  loss: 2.6094 (2.5732)  weight_decay: 0.0500 (0.0500)  time: 1.5899  data: 0.6661  max mem: 42573
Epoch: [164]  [ 20/312]  eta: 0:05:03  lr: 0.001909  min_lr: 0.001909  loss: 2.4913 (2.4912)  weight_decay: 0.0500 (0.0500)  time: 0.5879  data: 0.0297  max mem: 42573
Epoch: [164]  [ 30/312]  eta: 0:03:57  lr: 0.001909  min_lr: 0.001909  loss: 2.4832 (2.5229)  weight_decay: 0.0500 (0.0500)  time: 0.4331  data: 0.0004  max mem: 42573
Epoch: [164]  [ 40/312]  eta: 0:03:22  lr: 0.001908  min_lr: 0.001908  loss: 2.6203 (2.5083)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0003  max mem: 42573
Epoch: [164]  [ 50/312]  eta: 0:02:58  lr: 0.001907  min_lr: 0.001907  loss: 2.5636 (2.4891)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [164]  [ 60/312]  eta: 0:02:41  lr: 0.001906  min_lr: 0.001906  loss: 2.1452 (2.4506)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [164]  [ 70/312]  eta: 0:02:28  lr: 0.001906  min_lr: 0.001906  loss: 2.3099 (2.4333)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [164]  [ 80/312]  eta: 0:02:17  lr: 0.001905  min_lr: 0.001905  loss: 2.3057 (2.4058)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0004  max mem: 42573
Epoch: [164]  [ 90/312]  eta: 0:02:07  lr: 0.001904  min_lr: 0.001904  loss: 2.0581 (2.3828)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0003  max mem: 42573
Epoch: [164]  [100/312]  eta: 0:01:58  lr: 0.001904  min_lr: 0.001904  loss: 2.4234 (2.3999)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [164]  [110/312]  eta: 0:01:50  lr: 0.001903  min_lr: 0.001903  loss: 2.2355 (2.3724)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0004  max mem: 42573
Epoch: [164]  [120/312]  eta: 0:01:43  lr: 0.001902  min_lr: 0.001902  loss: 2.2355 (2.3818)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0004  max mem: 42573
Epoch: [164]  [130/312]  eta: 0:01:36  lr: 0.001901  min_lr: 0.001901  loss: 2.6283 (2.3962)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [164]  [140/312]  eta: 0:01:30  lr: 0.001901  min_lr: 0.001901  loss: 2.6283 (2.3994)  weight_decay: 0.0500 (0.0500)  time: 0.4390  data: 0.0004  max mem: 42573
Epoch: [164]  [150/312]  eta: 0:01:24  lr: 0.001900  min_lr: 0.001900  loss: 2.6397 (2.4195)  weight_decay: 0.0500 (0.0500)  time: 0.4390  data: 0.0003  max mem: 42573
Epoch: [164]  [160/312]  eta: 0:01:18  lr: 0.001899  min_lr: 0.001899  loss: 2.6734 (2.4289)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0003  max mem: 42573
Epoch: [164]  [170/312]  eta: 0:01:12  lr: 0.001899  min_lr: 0.001899  loss: 2.5497 (2.4332)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [164]  [180/312]  eta: 0:01:06  lr: 0.001898  min_lr: 0.001898  loss: 2.5497 (2.4408)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [164]  [190/312]  eta: 0:01:01  lr: 0.001897  min_lr: 0.001897  loss: 2.5435 (2.4436)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [164]  [200/312]  eta: 0:00:55  lr: 0.001896  min_lr: 0.001896  loss: 2.5207 (2.4456)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [164]  [210/312]  eta: 0:00:50  lr: 0.001896  min_lr: 0.001896  loss: 2.4595 (2.4371)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [164]  [220/312]  eta: 0:00:45  lr: 0.001895  min_lr: 0.001895  loss: 2.1085 (2.4240)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [164]  [230/312]  eta: 0:00:40  lr: 0.001894  min_lr: 0.001894  loss: 2.2344 (2.4195)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [164]  [240/312]  eta: 0:00:35  lr: 0.001894  min_lr: 0.001894  loss: 2.2736 (2.4107)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [164]  [250/312]  eta: 0:00:30  lr: 0.001893  min_lr: 0.001893  loss: 2.3581 (2.4092)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [164]  [260/312]  eta: 0:00:25  lr: 0.001892  min_lr: 0.001892  loss: 2.3566 (2.4062)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [164]  [270/312]  eta: 0:00:20  lr: 0.001891  min_lr: 0.001891  loss: 2.4699 (2.4105)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [164]  [280/312]  eta: 0:00:15  lr: 0.001891  min_lr: 0.001891  loss: 2.4569 (2.4053)  weight_decay: 0.0500 (0.0500)  time: 0.4345  data: 0.0010  max mem: 42573
Epoch: [164]  [290/312]  eta: 0:00:10  lr: 0.001890  min_lr: 0.001890  loss: 2.5252 (2.4124)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0008  max mem: 42573
Epoch: [164]  [300/312]  eta: 0:00:05  lr: 0.001889  min_lr: 0.001889  loss: 2.6634 (2.4168)  weight_decay: 0.0500 (0.0500)  time: 0.4325  data: 0.0001  max mem: 42573
Epoch: [164]  [310/312]  eta: 0:00:00  lr: 0.001889  min_lr: 0.001889  loss: 2.5848 (2.4208)  weight_decay: 0.0500 (0.0500)  time: 0.4322  data: 0.0001  max mem: 42573
Epoch: [164]  [311/312]  eta: 0:00:00  lr: 0.001888  min_lr: 0.001888  loss: 2.5391 (2.4180)  weight_decay: 0.0500 (0.0500)  time: 0.4323  data: 0.0001  max mem: 42573
Epoch: [164] Total time: 0:02:29 (0.4779 s / it)
Averaged stats: lr: 0.001888  min_lr: 0.001888  loss: 2.5391 (2.4202)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:00:41  loss: 0.8506 (0.8506)  acc1: 79.4271 (79.4271)  acc5: 93.4896 (93.4896)  time: 4.6494  data: 4.5399  max mem: 42573
Test:  [8/9]  eta: 0:00:00  loss: 1.2515 (1.1572)  acc1: 72.1354 (71.5200)  acc5: 90.3646 (91.0720)  time: 0.5934  data: 0.5045  max mem: 42573
Test: Total time: 0:00:05 (0.6137 s / it)
* Acc@1 72.372 Acc@5 90.888 loss 1.151
Accuracy of the model on the 50000 test images: 72.4%
Max accuracy: 74.20%
Epoch: [165]  [  0/312]  eta: 0:48:45  lr: 0.001888  min_lr: 0.001888  loss: 2.1765 (2.1765)  weight_decay: 0.0500 (0.0500)  time: 9.3780  data: 7.8264  max mem: 42573
Epoch: [165]  [ 10/312]  eta: 0:07:20  lr: 0.001888  min_lr: 0.001888  loss: 2.7310 (2.6538)  weight_decay: 0.0500 (0.0500)  time: 1.4590  data: 0.7517  max mem: 42573
Epoch: [165]  [ 20/312]  eta: 0:04:43  lr: 0.001887  min_lr: 0.001887  loss: 2.6749 (2.5671)  weight_decay: 0.0500 (0.0500)  time: 0.5502  data: 0.0223  max mem: 42573
Epoch: [165]  [ 30/312]  eta: 0:03:44  lr: 0.001886  min_lr: 0.001886  loss: 2.6418 (2.5502)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0003  max mem: 42573
Epoch: [165]  [ 40/312]  eta: 0:03:12  lr: 0.001886  min_lr: 0.001886  loss: 2.6418 (2.5584)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0003  max mem: 42573
Epoch: [165]  [ 50/312]  eta: 0:02:51  lr: 0.001885  min_lr: 0.001885  loss: 2.5931 (2.5342)  weight_decay: 0.0500 (0.0500)  time: 0.4341  data: 0.0003  max mem: 42573
Epoch: [165]  [ 60/312]  eta: 0:02:35  lr: 0.001884  min_lr: 0.001884  loss: 2.4880 (2.5406)  weight_decay: 0.0500 (0.0500)  time: 0.4344  data: 0.0003  max mem: 42573
Epoch: [165]  [ 70/312]  eta: 0:02:23  lr: 0.001883  min_lr: 0.001883  loss: 2.4939 (2.5403)  weight_decay: 0.0500 (0.0500)  time: 0.4347  data: 0.0003  max mem: 42573
Epoch: [165]  [ 80/312]  eta: 0:02:12  lr: 0.001883  min_lr: 0.001883  loss: 2.4701 (2.5162)  weight_decay: 0.0500 (0.0500)  time: 0.4349  data: 0.0004  max mem: 42573
Epoch: [165]  [ 90/312]  eta: 0:02:03  lr: 0.001882  min_lr: 0.001882  loss: 2.4605 (2.5052)  weight_decay: 0.0500 (0.0500)  time: 0.4342  data: 0.0004  max mem: 42573
Epoch: [165]  [100/312]  eta: 0:01:55  lr: 0.001881  min_lr: 0.001881  loss: 2.5915 (2.5067)  weight_decay: 0.0500 (0.0500)  time: 0.4341  data: 0.0004  max mem: 42573
Epoch: [165]  [110/312]  eta: 0:01:48  lr: 0.001880  min_lr: 0.001880  loss: 2.4329 (2.4927)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0004  max mem: 42573
Epoch: [165]  [120/312]  eta: 0:01:41  lr: 0.001880  min_lr: 0.001880  loss: 2.4329 (2.5063)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0004  max mem: 42573
Epoch: [165]  [130/312]  eta: 0:01:34  lr: 0.001879  min_lr: 0.001879  loss: 2.4142 (2.4809)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [165]  [140/312]  eta: 0:01:28  lr: 0.001878  min_lr: 0.001878  loss: 2.1906 (2.4688)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [165]  [150/312]  eta: 0:01:22  lr: 0.001878  min_lr: 0.001878  loss: 2.4864 (2.4704)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [165]  [160/312]  eta: 0:01:16  lr: 0.001877  min_lr: 0.001877  loss: 2.4846 (2.4615)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [165]  [170/312]  eta: 0:01:10  lr: 0.001876  min_lr: 0.001876  loss: 2.4450 (2.4573)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [165]  [180/312]  eta: 0:01:05  lr: 0.001875  min_lr: 0.001875  loss: 2.5564 (2.4627)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [165]  [190/312]  eta: 0:01:00  lr: 0.001875  min_lr: 0.001875  loss: 2.5564 (2.4600)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0003  max mem: 42573
Epoch: [165]  [200/312]  eta: 0:00:54  lr: 0.001874  min_lr: 0.001874  loss: 2.4729 (2.4577)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [165]  [210/312]  eta: 0:00:49  lr: 0.001873  min_lr: 0.001873  loss: 2.4488 (2.4600)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [165]  [220/312]  eta: 0:00:44  lr: 0.001873  min_lr: 0.001873  loss: 2.2925 (2.4515)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [165]  [230/312]  eta: 0:00:39  lr: 0.001872  min_lr: 0.001872  loss: 2.4199 (2.4525)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [165]  [240/312]  eta: 0:00:34  lr: 0.001871  min_lr: 0.001871  loss: 2.5358 (2.4579)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [165]  [250/312]  eta: 0:00:29  lr: 0.001870  min_lr: 0.001870  loss: 2.5395 (2.4593)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [165]  [260/312]  eta: 0:00:24  lr: 0.001870  min_lr: 0.001870  loss: 2.5383 (2.4592)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [165]  [270/312]  eta: 0:00:19  lr: 0.001869  min_lr: 0.001869  loss: 2.5147 (2.4549)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [165]  [280/312]  eta: 0:00:15  lr: 0.001868  min_lr: 0.001868  loss: 2.3994 (2.4426)  weight_decay: 0.0500 (0.0500)  time: 0.4347  data: 0.0009  max mem: 42573
Epoch: [165]  [290/312]  eta: 0:00:10  lr: 0.001868  min_lr: 0.001868  loss: 2.3194 (2.4399)  weight_decay: 0.0500 (0.0500)  time: 0.4341  data: 0.0008  max mem: 42573
Epoch: [165]  [300/312]  eta: 0:00:05  lr: 0.001867  min_lr: 0.001867  loss: 2.4153 (2.4409)  weight_decay: 0.0500 (0.0500)  time: 0.4325  data: 0.0001  max mem: 42573
Epoch: [165]  [310/312]  eta: 0:00:00  lr: 0.001866  min_lr: 0.001866  loss: 2.5326 (2.4454)  weight_decay: 0.0500 (0.0500)  time: 0.4322  data: 0.0001  max mem: 42573
Epoch: [165]  [311/312]  eta: 0:00:00  lr: 0.001866  min_lr: 0.001866  loss: 2.5305 (2.4436)  weight_decay: 0.0500 (0.0500)  time: 0.4322  data: 0.0001  max mem: 42573
Epoch: [165] Total time: 0:02:27 (0.4731 s / it)
Averaged stats: lr: 0.001866  min_lr: 0.001866  loss: 2.5305 (2.4114)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:00:43  loss: 0.8472 (0.8472)  acc1: 78.9062 (78.9062)  acc5: 94.7917 (94.7917)  time: 4.8874  data: 4.7792  max mem: 42573
Test:  [8/9]  eta: 0:00:00  loss: 1.1463 (1.1187)  acc1: 71.0938 (71.8400)  acc5: 91.4062 (91.2320)  time: 0.6189  data: 0.5311  max mem: 42573
Test: Total time: 0:00:05 (0.6421 s / it)
* Acc@1 72.990 Acc@5 91.342 loss 1.085
Accuracy of the model on the 50000 test images: 73.0%
Max accuracy: 74.20%
Epoch: [166]  [  0/312]  eta: 0:51:26  lr: 0.001866  min_lr: 0.001866  loss: 2.6472 (2.6472)  weight_decay: 0.0500 (0.0500)  time: 9.8911  data: 6.8815  max mem: 42573
Epoch: [166]  [ 10/312]  eta: 0:07:37  lr: 0.001865  min_lr: 0.001865  loss: 2.4094 (2.3223)  weight_decay: 0.0500 (0.0500)  time: 1.5158  data: 0.6260  max mem: 42573
Epoch: [166]  [ 20/312]  eta: 0:04:52  lr: 0.001865  min_lr: 0.001865  loss: 2.4391 (2.4005)  weight_decay: 0.0500 (0.0500)  time: 0.5558  data: 0.0004  max mem: 42573
Epoch: [166]  [ 30/312]  eta: 0:03:50  lr: 0.001864  min_lr: 0.001864  loss: 2.5349 (2.4227)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0003  max mem: 42573
Epoch: [166]  [ 40/312]  eta: 0:03:16  lr: 0.001863  min_lr: 0.001863  loss: 2.3435 (2.3749)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [166]  [ 50/312]  eta: 0:02:54  lr: 0.001862  min_lr: 0.001862  loss: 2.2589 (2.3367)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [166]  [ 60/312]  eta: 0:02:38  lr: 0.001862  min_lr: 0.001862  loss: 2.2991 (2.3180)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [166]  [ 70/312]  eta: 0:02:25  lr: 0.001861  min_lr: 0.001861  loss: 2.2421 (2.2984)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [166]  [ 80/312]  eta: 0:02:14  lr: 0.001860  min_lr: 0.001860  loss: 1.9919 (2.2767)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [166]  [ 90/312]  eta: 0:02:05  lr: 0.001860  min_lr: 0.001860  loss: 2.3578 (2.2930)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [166]  [100/312]  eta: 0:01:56  lr: 0.001859  min_lr: 0.001859  loss: 2.4997 (2.3081)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [166]  [110/312]  eta: 0:01:49  lr: 0.001858  min_lr: 0.001858  loss: 2.4913 (2.3137)  weight_decay: 0.0500 (0.0500)  time: 0.4356  data: 0.0004  max mem: 42573
Epoch: [166]  [120/312]  eta: 0:01:42  lr: 0.001857  min_lr: 0.001857  loss: 2.5387 (2.3218)  weight_decay: 0.0500 (0.0500)  time: 0.4354  data: 0.0004  max mem: 42573
Epoch: [166]  [130/312]  eta: 0:01:35  lr: 0.001857  min_lr: 0.001857  loss: 2.6003 (2.3499)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0003  max mem: 42573
Epoch: [166]  [140/312]  eta: 0:01:29  lr: 0.001856  min_lr: 0.001856  loss: 2.5333 (2.3413)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [166]  [150/312]  eta: 0:01:23  lr: 0.001855  min_lr: 0.001855  loss: 2.1409 (2.3294)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [166]  [160/312]  eta: 0:01:17  lr: 0.001855  min_lr: 0.001855  loss: 2.5019 (2.3359)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0003  max mem: 42573
Epoch: [166]  [170/312]  eta: 0:01:11  lr: 0.001854  min_lr: 0.001854  loss: 2.5184 (2.3405)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [166]  [180/312]  eta: 0:01:05  lr: 0.001853  min_lr: 0.001853  loss: 2.5178 (2.3503)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [166]  [190/312]  eta: 0:01:00  lr: 0.001852  min_lr: 0.001852  loss: 2.6712 (2.3615)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [166]  [200/312]  eta: 0:00:55  lr: 0.001852  min_lr: 0.001852  loss: 2.4478 (2.3652)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [166]  [210/312]  eta: 0:00:50  lr: 0.001851  min_lr: 0.001851  loss: 2.4395 (2.3570)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [166]  [220/312]  eta: 0:00:44  lr: 0.001850  min_lr: 0.001850  loss: 2.4434 (2.3670)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0004  max mem: 42573
Epoch: [166]  [230/312]  eta: 0:00:39  lr: 0.001849  min_lr: 0.001849  loss: 2.4459 (2.3711)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [166]  [240/312]  eta: 0:00:34  lr: 0.001849  min_lr: 0.001849  loss: 2.3633 (2.3682)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [166]  [250/312]  eta: 0:00:29  lr: 0.001848  min_lr: 0.001848  loss: 2.5726 (2.3776)  weight_decay: 0.0500 (0.0500)  time: 0.4342  data: 0.0004  max mem: 42573
Epoch: [166]  [260/312]  eta: 0:00:24  lr: 0.001847  min_lr: 0.001847  loss: 2.6288 (2.3845)  weight_decay: 0.0500 (0.0500)  time: 0.4394  data: 0.0004  max mem: 42573
Epoch: [166]  [270/312]  eta: 0:00:20  lr: 0.001847  min_lr: 0.001847  loss: 2.5642 (2.3851)  weight_decay: 0.0500 (0.0500)  time: 0.4390  data: 0.0004  max mem: 42573
Epoch: [166]  [280/312]  eta: 0:00:15  lr: 0.001846  min_lr: 0.001846  loss: 2.5025 (2.3894)  weight_decay: 0.0500 (0.0500)  time: 0.4343  data: 0.0010  max mem: 42573
Epoch: [166]  [290/312]  eta: 0:00:10  lr: 0.001845  min_lr: 0.001845  loss: 2.4073 (2.3887)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0009  max mem: 42573
Epoch: [166]  [300/312]  eta: 0:00:05  lr: 0.001844  min_lr: 0.001844  loss: 2.4082 (2.3907)  weight_decay: 0.0500 (0.0500)  time: 0.4323  data: 0.0001  max mem: 42573
Epoch: [166]  [310/312]  eta: 0:00:00  lr: 0.001844  min_lr: 0.001844  loss: 2.4082 (2.3867)  weight_decay: 0.0500 (0.0500)  time: 0.4324  data: 0.0001  max mem: 42573
Epoch: [166]  [311/312]  eta: 0:00:00  lr: 0.001844  min_lr: 0.001844  loss: 2.4082 (2.3845)  weight_decay: 0.0500 (0.0500)  time: 0.4324  data: 0.0001  max mem: 42573
Epoch: [166] Total time: 0:02:28 (0.4753 s / it)
Averaged stats: lr: 0.001844  min_lr: 0.001844  loss: 2.4082 (2.4192)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:00:41  loss: 0.8445 (0.8445)  acc1: 80.4688 (80.4688)  acc5: 93.7500 (93.7500)  time: 4.6392  data: 4.5302  max mem: 42573
Test:  [8/9]  eta: 0:00:00  loss: 1.2133 (1.1173)  acc1: 71.3542 (72.6400)  acc5: 91.6667 (91.2000)  time: 0.5925  data: 0.5034  max mem: 42573
Test: Total time: 0:00:05 (0.5998 s / it)
* Acc@1 73.020 Acc@5 91.220 loss 1.096
Accuracy of the model on the 50000 test images: 73.0%
Max accuracy: 74.20%
Epoch: [167]  [  0/312]  eta: 0:50:42  lr: 0.001844  min_lr: 0.001844  loss: 2.0016 (2.0016)  weight_decay: 0.0500 (0.0500)  time: 9.7508  data: 8.7727  max mem: 42573
Epoch: [167]  [ 10/312]  eta: 0:07:28  lr: 0.001843  min_lr: 0.001843  loss: 2.1882 (2.2316)  weight_decay: 0.0500 (0.0500)  time: 1.4853  data: 0.7979  max mem: 42573
Epoch: [167]  [ 20/312]  eta: 0:04:47  lr: 0.001842  min_lr: 0.001842  loss: 2.4797 (2.3512)  weight_decay: 0.0500 (0.0500)  time: 0.5462  data: 0.0004  max mem: 42573
Epoch: [167]  [ 30/312]  eta: 0:03:47  lr: 0.001841  min_lr: 0.001841  loss: 2.4797 (2.3494)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0003  max mem: 42573
Epoch: [167]  [ 40/312]  eta: 0:03:14  lr: 0.001841  min_lr: 0.001841  loss: 2.4656 (2.3822)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [167]  [ 50/312]  eta: 0:02:53  lr: 0.001840  min_lr: 0.001840  loss: 2.6131 (2.4381)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [167]  [ 60/312]  eta: 0:02:37  lr: 0.001839  min_lr: 0.001839  loss: 2.6410 (2.4583)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [167]  [ 70/312]  eta: 0:02:24  lr: 0.001839  min_lr: 0.001839  loss: 2.3275 (2.4290)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [167]  [ 80/312]  eta: 0:02:13  lr: 0.001838  min_lr: 0.001838  loss: 2.4731 (2.4368)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [167]  [ 90/312]  eta: 0:02:04  lr: 0.001837  min_lr: 0.001837  loss: 2.3971 (2.4077)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [167]  [100/312]  eta: 0:01:56  lr: 0.001836  min_lr: 0.001836  loss: 2.1913 (2.4121)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0004  max mem: 42573
Epoch: [167]  [110/312]  eta: 0:01:48  lr: 0.001836  min_lr: 0.001836  loss: 2.4973 (2.4161)  weight_decay: 0.0500 (0.0500)  time: 0.4385  data: 0.0005  max mem: 42573
Epoch: [167]  [120/312]  eta: 0:01:41  lr: 0.001835  min_lr: 0.001835  loss: 2.5045 (2.4243)  weight_decay: 0.0500 (0.0500)  time: 0.4384  data: 0.0004  max mem: 42573
Epoch: [167]  [130/312]  eta: 0:01:35  lr: 0.001834  min_lr: 0.001834  loss: 2.5830 (2.4357)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [167]  [140/312]  eta: 0:01:28  lr: 0.001834  min_lr: 0.001834  loss: 2.5865 (2.4466)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [167]  [150/312]  eta: 0:01:22  lr: 0.001833  min_lr: 0.001833  loss: 2.4477 (2.4350)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [167]  [160/312]  eta: 0:01:16  lr: 0.001832  min_lr: 0.001832  loss: 2.5001 (2.4478)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [167]  [170/312]  eta: 0:01:11  lr: 0.001831  min_lr: 0.001831  loss: 2.5019 (2.4414)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [167]  [180/312]  eta: 0:01:05  lr: 0.001831  min_lr: 0.001831  loss: 2.2496 (2.4299)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [167]  [190/312]  eta: 0:01:00  lr: 0.001830  min_lr: 0.001830  loss: 2.4186 (2.4345)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [167]  [200/312]  eta: 0:00:55  lr: 0.001829  min_lr: 0.001829  loss: 2.4983 (2.4374)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [167]  [210/312]  eta: 0:00:49  lr: 0.001829  min_lr: 0.001829  loss: 2.4975 (2.4350)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [167]  [220/312]  eta: 0:00:44  lr: 0.001828  min_lr: 0.001828  loss: 2.2848 (2.4268)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [167]  [230/312]  eta: 0:00:39  lr: 0.001827  min_lr: 0.001827  loss: 2.2966 (2.4275)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0003  max mem: 42573
Epoch: [167]  [240/312]  eta: 0:00:34  lr: 0.001826  min_lr: 0.001826  loss: 2.3433 (2.4231)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [167]  [250/312]  eta: 0:00:29  lr: 0.001826  min_lr: 0.001826  loss: 2.1197 (2.4155)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [167]  [260/312]  eta: 0:00:24  lr: 0.001825  min_lr: 0.001825  loss: 2.4845 (2.4211)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [167]  [270/312]  eta: 0:00:20  lr: 0.001824  min_lr: 0.001824  loss: 2.5191 (2.4253)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [167]  [280/312]  eta: 0:00:15  lr: 0.001824  min_lr: 0.001824  loss: 2.4315 (2.4211)  weight_decay: 0.0500 (0.0500)  time: 0.4346  data: 0.0010  max mem: 42573
Epoch: [167]  [290/312]  eta: 0:00:10  lr: 0.001823  min_lr: 0.001823  loss: 2.0766 (2.4099)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0008  max mem: 42573
Epoch: [167]  [300/312]  eta: 0:00:05  lr: 0.001822  min_lr: 0.001822  loss: 2.1255 (2.4090)  weight_decay: 0.0500 (0.0500)  time: 0.4324  data: 0.0001  max mem: 42573
Epoch: [167]  [310/312]  eta: 0:00:00  lr: 0.001821  min_lr: 0.001821  loss: 2.4419 (2.4098)  weight_decay: 0.0500 (0.0500)  time: 0.4324  data: 0.0001  max mem: 42573
Epoch: [167]  [311/312]  eta: 0:00:00  lr: 0.001821  min_lr: 0.001821  loss: 2.4324 (2.4075)  weight_decay: 0.0500 (0.0500)  time: 0.4324  data: 0.0001  max mem: 42573
Epoch: [167] Total time: 0:02:27 (0.4740 s / it)
Averaged stats: lr: 0.001821  min_lr: 0.001821  loss: 2.4324 (2.4024)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:00:41  loss: 0.8517 (0.8517)  acc1: 79.4271 (79.4271)  acc5: 93.4896 (93.4896)  time: 4.6256  data: 4.5167  max mem: 42573
Test:  [8/9]  eta: 0:00:00  loss: 1.1926 (1.0938)  acc1: 72.6562 (72.5760)  acc5: 90.8854 (90.7520)  time: 0.5909  data: 0.5019  max mem: 42573
Test: Total time: 0:00:05 (0.5999 s / it)
* Acc@1 73.070 Acc@5 91.152 loss 1.087
Accuracy of the model on the 50000 test images: 73.1%
Max accuracy: 74.20%
Epoch: [168]  [  0/312]  eta: 0:54:01  lr: 0.001821  min_lr: 0.001821  loss: 2.4565 (2.4565)  weight_decay: 0.0500 (0.0500)  time: 10.3885  data: 9.0254  max mem: 42573
Epoch: [168]  [ 10/312]  eta: 0:07:49  lr: 0.001821  min_lr: 0.001821  loss: 2.4138 (2.3673)  weight_decay: 0.0500 (0.0500)  time: 1.5549  data: 0.8209  max mem: 42573
Epoch: [168]  [ 20/312]  eta: 0:04:58  lr: 0.001820  min_lr: 0.001820  loss: 2.3754 (2.3831)  weight_decay: 0.0500 (0.0500)  time: 0.5523  data: 0.0004  max mem: 42573
Epoch: [168]  [ 30/312]  eta: 0:03:54  lr: 0.001819  min_lr: 0.001819  loss: 2.3694 (2.3873)  weight_decay: 0.0500 (0.0500)  time: 0.4331  data: 0.0004  max mem: 42573
Epoch: [168]  [ 40/312]  eta: 0:03:19  lr: 0.001818  min_lr: 0.001818  loss: 2.2640 (2.3726)  weight_decay: 0.0500 (0.0500)  time: 0.4332  data: 0.0005  max mem: 42573
Epoch: [168]  [ 50/312]  eta: 0:02:56  lr: 0.001818  min_lr: 0.001818  loss: 2.4047 (2.3805)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [168]  [ 60/312]  eta: 0:02:40  lr: 0.001817  min_lr: 0.001817  loss: 2.2970 (2.3709)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [168]  [ 70/312]  eta: 0:02:26  lr: 0.001816  min_lr: 0.001816  loss: 2.2950 (2.3716)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [168]  [ 80/312]  eta: 0:02:15  lr: 0.001816  min_lr: 0.001816  loss: 2.4599 (2.3842)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [168]  [ 90/312]  eta: 0:02:06  lr: 0.001815  min_lr: 0.001815  loss: 2.2885 (2.3686)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [168]  [100/312]  eta: 0:01:57  lr: 0.001814  min_lr: 0.001814  loss: 2.5951 (2.4018)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [168]  [110/312]  eta: 0:01:50  lr: 0.001813  min_lr: 0.001813  loss: 2.5606 (2.4020)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [168]  [120/312]  eta: 0:01:42  lr: 0.001813  min_lr: 0.001813  loss: 2.5462 (2.4137)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [168]  [130/312]  eta: 0:01:36  lr: 0.001812  min_lr: 0.001812  loss: 2.6080 (2.4174)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [168]  [140/312]  eta: 0:01:29  lr: 0.001811  min_lr: 0.001811  loss: 2.6080 (2.4336)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [168]  [150/312]  eta: 0:01:23  lr: 0.001811  min_lr: 0.001811  loss: 2.5065 (2.4382)  weight_decay: 0.0500 (0.0500)  time: 0.4370  data: 0.0004  max mem: 42573
Epoch: [168]  [160/312]  eta: 0:01:17  lr: 0.001810  min_lr: 0.001810  loss: 2.4799 (2.4355)  weight_decay: 0.0500 (0.0500)  time: 0.4371  data: 0.0004  max mem: 42573
Epoch: [168]  [170/312]  eta: 0:01:11  lr: 0.001809  min_lr: 0.001809  loss: 2.4516 (2.4391)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [168]  [180/312]  eta: 0:01:06  lr: 0.001808  min_lr: 0.001808  loss: 2.5736 (2.4398)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [168]  [190/312]  eta: 0:01:00  lr: 0.001808  min_lr: 0.001808  loss: 2.5565 (2.4356)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [168]  [200/312]  eta: 0:00:55  lr: 0.001807  min_lr: 0.001807  loss: 2.3710 (2.4345)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [168]  [210/312]  eta: 0:00:50  lr: 0.001806  min_lr: 0.001806  loss: 2.3714 (2.4363)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [168]  [220/312]  eta: 0:00:45  lr: 0.001806  min_lr: 0.001806  loss: 2.4716 (2.4385)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0005  max mem: 42573
Epoch: [168]  [230/312]  eta: 0:00:39  lr: 0.001805  min_lr: 0.001805  loss: 2.4716 (2.4361)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [168]  [240/312]  eta: 0:00:34  lr: 0.001804  min_lr: 0.001804  loss: 2.3974 (2.4319)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [168]  [250/312]  eta: 0:00:29  lr: 0.001803  min_lr: 0.001803  loss: 2.4842 (2.4378)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [168]  [260/312]  eta: 0:00:25  lr: 0.001803  min_lr: 0.001803  loss: 2.4364 (2.4261)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [168]  [270/312]  eta: 0:00:20  lr: 0.001802  min_lr: 0.001802  loss: 2.1751 (2.4244)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [168]  [280/312]  eta: 0:00:15  lr: 0.001801  min_lr: 0.001801  loss: 2.3962 (2.4205)  weight_decay: 0.0500 (0.0500)  time: 0.4344  data: 0.0010  max mem: 42573
Epoch: [168]  [290/312]  eta: 0:00:10  lr: 0.001801  min_lr: 0.001801  loss: 2.5284 (2.4216)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0008  max mem: 42573
Epoch: [168]  [300/312]  eta: 0:00:05  lr: 0.001800  min_lr: 0.001800  loss: 2.5119 (2.4194)  weight_decay: 0.0500 (0.0500)  time: 0.4323  data: 0.0001  max mem: 42573
Epoch: [168]  [310/312]  eta: 0:00:00  lr: 0.001799  min_lr: 0.001799  loss: 2.4095 (2.4187)  weight_decay: 0.0500 (0.0500)  time: 0.4324  data: 0.0001  max mem: 42573
Epoch: [168]  [311/312]  eta: 0:00:00  lr: 0.001799  min_lr: 0.001799  loss: 2.4095 (2.4170)  weight_decay: 0.0500 (0.0500)  time: 0.4324  data: 0.0001  max mem: 42573
Epoch: [168] Total time: 0:02:28 (0.4764 s / it)
Averaged stats: lr: 0.001799  min_lr: 0.001799  loss: 2.4095 (2.4031)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:00:42  loss: 0.7536 (0.7536)  acc1: 79.1667 (79.1667)  acc5: 94.7917 (94.7917)  time: 4.7454  data: 4.6367  max mem: 42573
Test:  [8/9]  eta: 0:00:00  loss: 1.1538 (1.0914)  acc1: 72.3958 (72.0640)  acc5: 91.4062 (91.5840)  time: 0.6027  data: 0.5152  max mem: 42573
Test: Total time: 0:00:05 (0.6152 s / it)
* Acc@1 72.754 Acc@5 91.066 loss 1.086
Accuracy of the model on the 50000 test images: 72.8%
Max accuracy: 74.20%
Epoch: [169]  [  0/312]  eta: 0:50:09  lr: 0.001799  min_lr: 0.001799  loss: 2.5272 (2.5272)  weight_decay: 0.0500 (0.0500)  time: 9.6465  data: 8.0834  max mem: 42573
Epoch: [169]  [ 10/312]  eta: 0:07:15  lr: 0.001798  min_lr: 0.001798  loss: 2.4924 (2.4454)  weight_decay: 0.0500 (0.0500)  time: 1.4422  data: 0.7352  max mem: 42573
Epoch: [169]  [ 20/312]  eta: 0:04:40  lr: 0.001798  min_lr: 0.001798  loss: 2.4924 (2.5150)  weight_decay: 0.0500 (0.0500)  time: 0.5275  data: 0.0004  max mem: 42573
Epoch: [169]  [ 30/312]  eta: 0:03:43  lr: 0.001797  min_lr: 0.001797  loss: 2.6395 (2.5874)  weight_decay: 0.0500 (0.0500)  time: 0.4331  data: 0.0003  max mem: 42573
Epoch: [169]  [ 40/312]  eta: 0:03:11  lr: 0.001796  min_lr: 0.001796  loss: 2.5470 (2.5538)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0003  max mem: 42573
Epoch: [169]  [ 50/312]  eta: 0:02:50  lr: 0.001795  min_lr: 0.001795  loss: 2.4841 (2.5485)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [169]  [ 60/312]  eta: 0:02:35  lr: 0.001795  min_lr: 0.001795  loss: 2.5377 (2.5483)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [169]  [ 70/312]  eta: 0:02:22  lr: 0.001794  min_lr: 0.001794  loss: 2.4178 (2.5316)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [169]  [ 80/312]  eta: 0:02:12  lr: 0.001793  min_lr: 0.001793  loss: 2.3049 (2.5034)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [169]  [ 90/312]  eta: 0:02:03  lr: 0.001792  min_lr: 0.001792  loss: 2.3106 (2.4846)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [169]  [100/312]  eta: 0:01:55  lr: 0.001792  min_lr: 0.001792  loss: 2.3106 (2.4736)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [169]  [110/312]  eta: 0:01:47  lr: 0.001791  min_lr: 0.001791  loss: 2.4799 (2.4687)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0003  max mem: 42573
Epoch: [169]  [120/312]  eta: 0:01:40  lr: 0.001790  min_lr: 0.001790  loss: 2.5379 (2.4757)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0003  max mem: 42573
Epoch: [169]  [130/312]  eta: 0:01:34  lr: 0.001790  min_lr: 0.001790  loss: 2.6166 (2.4847)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [169]  [140/312]  eta: 0:01:28  lr: 0.001789  min_lr: 0.001789  loss: 2.6382 (2.4829)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [169]  [150/312]  eta: 0:01:22  lr: 0.001788  min_lr: 0.001788  loss: 2.6102 (2.4906)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [169]  [160/312]  eta: 0:01:16  lr: 0.001787  min_lr: 0.001787  loss: 2.5668 (2.4748)  weight_decay: 0.0500 (0.0500)  time: 0.4410  data: 0.0004  max mem: 42573
Epoch: [169]  [170/312]  eta: 0:01:10  lr: 0.001787  min_lr: 0.001787  loss: 2.4000 (2.4690)  weight_decay: 0.0500 (0.0500)  time: 0.4408  data: 0.0004  max mem: 42573
Epoch: [169]  [180/312]  eta: 0:01:05  lr: 0.001786  min_lr: 0.001786  loss: 2.4458 (2.4689)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [169]  [190/312]  eta: 0:01:00  lr: 0.001785  min_lr: 0.001785  loss: 2.4093 (2.4610)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [169]  [200/312]  eta: 0:00:54  lr: 0.001785  min_lr: 0.001785  loss: 2.4834 (2.4600)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [169]  [210/312]  eta: 0:00:49  lr: 0.001784  min_lr: 0.001784  loss: 2.5101 (2.4594)  weight_decay: 0.0500 (0.0500)  time: 0.4342  data: 0.0003  max mem: 42573
Epoch: [169]  [220/312]  eta: 0:00:44  lr: 0.001783  min_lr: 0.001783  loss: 2.4492 (2.4557)  weight_decay: 0.0500 (0.0500)  time: 0.4341  data: 0.0003  max mem: 42573
Epoch: [169]  [230/312]  eta: 0:00:39  lr: 0.001782  min_lr: 0.001782  loss: 2.5070 (2.4575)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [169]  [240/312]  eta: 0:00:34  lr: 0.001782  min_lr: 0.001782  loss: 2.4471 (2.4470)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [169]  [250/312]  eta: 0:00:29  lr: 0.001781  min_lr: 0.001781  loss: 2.1011 (2.4366)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [169]  [260/312]  eta: 0:00:24  lr: 0.001780  min_lr: 0.001780  loss: 2.4174 (2.4373)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [169]  [270/312]  eta: 0:00:19  lr: 0.001780  min_lr: 0.001780  loss: 2.4625 (2.4400)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0004  max mem: 42573
Epoch: [169]  [280/312]  eta: 0:00:15  lr: 0.001779  min_lr: 0.001779  loss: 2.5600 (2.4446)  weight_decay: 0.0500 (0.0500)  time: 0.4355  data: 0.0010  max mem: 42573
Epoch: [169]  [290/312]  eta: 0:00:10  lr: 0.001778  min_lr: 0.001778  loss: 2.6011 (2.4477)  weight_decay: 0.0500 (0.0500)  time: 0.4347  data: 0.0008  max mem: 42573
Epoch: [169]  [300/312]  eta: 0:00:05  lr: 0.001777  min_lr: 0.001777  loss: 2.6006 (2.4446)  weight_decay: 0.0500 (0.0500)  time: 0.4325  data: 0.0001  max mem: 42573
Epoch: [169]  [310/312]  eta: 0:00:00  lr: 0.001777  min_lr: 0.001777  loss: 2.7095 (2.4519)  weight_decay: 0.0500 (0.0500)  time: 0.4324  data: 0.0001  max mem: 42573
Epoch: [169]  [311/312]  eta: 0:00:00  lr: 0.001777  min_lr: 0.001777  loss: 2.7095 (2.4523)  weight_decay: 0.0500 (0.0500)  time: 0.4324  data: 0.0001  max mem: 42573
Epoch: [169] Total time: 0:02:27 (0.4725 s / it)
Averaged stats: lr: 0.001777  min_lr: 0.001777  loss: 2.7095 (2.4111)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:00:43  loss: 0.8026 (0.8026)  acc1: 79.6875 (79.6875)  acc5: 93.4896 (93.4896)  time: 4.8088  data: 4.7001  max mem: 42573
Test:  [8/9]  eta: 0:00:00  loss: 1.1662 (1.0883)  acc1: 72.6562 (72.6400)  acc5: 90.8854 (90.8800)  time: 0.6100  data: 0.5223  max mem: 42573
Test: Total time: 0:00:05 (0.6199 s / it)
* Acc@1 73.502 Acc@5 91.296 loss 1.059
Accuracy of the model on the 50000 test images: 73.5%
Max accuracy: 74.20%
Epoch: [170]  [  0/312]  eta: 0:52:33  lr: 0.001777  min_lr: 0.001777  loss: 2.5628 (2.5628)  weight_decay: 0.0500 (0.0500)  time: 10.1074  data: 8.2058  max mem: 42573
Epoch: [170]  [ 10/312]  eta: 0:07:41  lr: 0.001776  min_lr: 0.001776  loss: 2.5628 (2.3888)  weight_decay: 0.0500 (0.0500)  time: 1.5272  data: 0.7463  max mem: 42573
Epoch: [170]  [ 20/312]  eta: 0:04:53  lr: 0.001775  min_lr: 0.001775  loss: 2.4192 (2.3426)  weight_decay: 0.0500 (0.0500)  time: 0.5514  data: 0.0003  max mem: 42573
Epoch: [170]  [ 30/312]  eta: 0:03:51  lr: 0.001774  min_lr: 0.001774  loss: 2.4455 (2.3763)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0003  max mem: 42573
Epoch: [170]  [ 40/312]  eta: 0:03:17  lr: 0.001774  min_lr: 0.001774  loss: 2.4455 (2.3849)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [170]  [ 50/312]  eta: 0:02:55  lr: 0.001773  min_lr: 0.001773  loss: 2.5118 (2.4130)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [170]  [ 60/312]  eta: 0:02:38  lr: 0.001772  min_lr: 0.001772  loss: 2.5640 (2.4222)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [170]  [ 70/312]  eta: 0:02:25  lr: 0.001772  min_lr: 0.001772  loss: 2.3819 (2.3868)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [170]  [ 80/312]  eta: 0:02:15  lr: 0.001771  min_lr: 0.001771  loss: 2.2562 (2.3878)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [170]  [ 90/312]  eta: 0:02:05  lr: 0.001770  min_lr: 0.001770  loss: 2.1967 (2.3779)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [170]  [100/312]  eta: 0:01:57  lr: 0.001769  min_lr: 0.001769  loss: 2.4149 (2.3874)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [170]  [110/312]  eta: 0:01:49  lr: 0.001769  min_lr: 0.001769  loss: 2.5433 (2.3876)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0003  max mem: 42573
Epoch: [170]  [120/312]  eta: 0:01:42  lr: 0.001768  min_lr: 0.001768  loss: 2.5233 (2.3985)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0003  max mem: 42573
Epoch: [170]  [130/312]  eta: 0:01:35  lr: 0.001767  min_lr: 0.001767  loss: 2.5299 (2.4117)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0003  max mem: 42573
Epoch: [170]  [140/312]  eta: 0:01:29  lr: 0.001767  min_lr: 0.001767  loss: 2.5865 (2.4219)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0003  max mem: 42573
Epoch: [170]  [150/312]  eta: 0:01:23  lr: 0.001766  min_lr: 0.001766  loss: 2.6209 (2.4264)  weight_decay: 0.0500 (0.0500)  time: 0.4364  data: 0.0004  max mem: 42573
Epoch: [170]  [160/312]  eta: 0:01:17  lr: 0.001765  min_lr: 0.001765  loss: 2.5725 (2.4336)  weight_decay: 0.0500 (0.0500)  time: 0.4364  data: 0.0004  max mem: 42573
Epoch: [170]  [170/312]  eta: 0:01:11  lr: 0.001764  min_lr: 0.001764  loss: 2.5774 (2.4414)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [170]  [180/312]  eta: 0:01:06  lr: 0.001764  min_lr: 0.001764  loss: 2.5080 (2.4339)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [170]  [190/312]  eta: 0:01:00  lr: 0.001763  min_lr: 0.001763  loss: 2.5211 (2.4357)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [170]  [200/312]  eta: 0:00:55  lr: 0.001762  min_lr: 0.001762  loss: 2.5432 (2.4383)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [170]  [210/312]  eta: 0:00:50  lr: 0.001762  min_lr: 0.001762  loss: 2.4044 (2.4273)  weight_decay: 0.0500 (0.0500)  time: 0.4380  data: 0.0004  max mem: 42573
Epoch: [170]  [220/312]  eta: 0:00:44  lr: 0.001761  min_lr: 0.001761  loss: 2.3402 (2.4267)  weight_decay: 0.0500 (0.0500)  time: 0.4380  data: 0.0004  max mem: 42573
Epoch: [170]  [230/312]  eta: 0:00:39  lr: 0.001760  min_lr: 0.001760  loss: 2.3551 (2.4235)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [170]  [240/312]  eta: 0:00:34  lr: 0.001759  min_lr: 0.001759  loss: 2.2780 (2.4154)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0003  max mem: 42573
Epoch: [170]  [250/312]  eta: 0:00:29  lr: 0.001759  min_lr: 0.001759  loss: 2.1857 (2.4056)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0003  max mem: 42573
Epoch: [170]  [260/312]  eta: 0:00:24  lr: 0.001758  min_lr: 0.001758  loss: 2.2112 (2.3975)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0003  max mem: 42573
Epoch: [170]  [270/312]  eta: 0:00:20  lr: 0.001757  min_lr: 0.001757  loss: 2.3756 (2.3941)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0003  max mem: 42573
Epoch: [170]  [280/312]  eta: 0:00:15  lr: 0.001757  min_lr: 0.001757  loss: 2.4713 (2.4021)  weight_decay: 0.0500 (0.0500)  time: 0.4345  data: 0.0009  max mem: 42573
Epoch: [170]  [290/312]  eta: 0:00:10  lr: 0.001756  min_lr: 0.001756  loss: 2.5189 (2.4022)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0008  max mem: 42573
Epoch: [170]  [300/312]  eta: 0:00:05  lr: 0.001755  min_lr: 0.001755  loss: 2.5194 (2.4056)  weight_decay: 0.0500 (0.0500)  time: 0.4324  data: 0.0001  max mem: 42573
Epoch: [170]  [310/312]  eta: 0:00:00  lr: 0.001754  min_lr: 0.001754  loss: 2.5194 (2.4065)  weight_decay: 0.0500 (0.0500)  time: 0.4324  data: 0.0001  max mem: 42573
Epoch: [170]  [311/312]  eta: 0:00:00  lr: 0.001754  min_lr: 0.001754  loss: 2.5194 (2.4066)  weight_decay: 0.0500 (0.0500)  time: 0.4324  data: 0.0001  max mem: 42573
Epoch: [170] Total time: 0:02:28 (0.4758 s / it)
Averaged stats: lr: 0.001754  min_lr: 0.001754  loss: 2.5194 (2.3907)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:00:43  loss: 0.7731 (0.7731)  acc1: 81.2500 (81.2500)  acc5: 94.2708 (94.2708)  time: 4.8392  data: 4.7305  max mem: 42573
Test:  [8/9]  eta: 0:00:00  loss: 1.0660 (1.0441)  acc1: 71.8750 (72.8960)  acc5: 93.2292 (91.9040)  time: 0.6147  data: 0.5257  max mem: 42573
Test: Total time: 0:00:05 (0.6363 s / it)
* Acc@1 73.694 Acc@5 91.780 loss 1.045
Accuracy of the model on the 50000 test images: 73.7%
Max accuracy: 74.20%
Epoch: [171]  [  0/312]  eta: 0:51:22  lr: 0.001754  min_lr: 0.001754  loss: 2.4559 (2.4559)  weight_decay: 0.0500 (0.0500)  time: 9.8801  data: 7.1747  max mem: 42573
Epoch: [171]  [ 10/312]  eta: 0:07:39  lr: 0.001754  min_lr: 0.001754  loss: 2.4559 (2.3003)  weight_decay: 0.0500 (0.0500)  time: 1.5222  data: 0.7512  max mem: 42573
Epoch: [171]  [ 20/312]  eta: 0:04:53  lr: 0.001753  min_lr: 0.001753  loss: 2.4756 (2.3527)  weight_decay: 0.0500 (0.0500)  time: 0.5597  data: 0.0546  max mem: 42573
Epoch: [171]  [ 30/312]  eta: 0:03:51  lr: 0.001752  min_lr: 0.001752  loss: 2.5634 (2.4295)  weight_decay: 0.0500 (0.0500)  time: 0.4330  data: 0.0004  max mem: 42573
Epoch: [171]  [ 40/312]  eta: 0:03:17  lr: 0.001751  min_lr: 0.001751  loss: 2.3658 (2.3964)  weight_decay: 0.0500 (0.0500)  time: 0.4332  data: 0.0004  max mem: 42573
Epoch: [171]  [ 50/312]  eta: 0:02:55  lr: 0.001751  min_lr: 0.001751  loss: 2.1698 (2.3369)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0005  max mem: 42573
Epoch: [171]  [ 60/312]  eta: 0:02:38  lr: 0.001750  min_lr: 0.001750  loss: 2.1336 (2.3245)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [171]  [ 70/312]  eta: 0:02:25  lr: 0.001749  min_lr: 0.001749  loss: 2.3419 (2.3419)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [171]  [ 80/312]  eta: 0:02:14  lr: 0.001749  min_lr: 0.001749  loss: 2.3937 (2.3447)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [171]  [ 90/312]  eta: 0:02:05  lr: 0.001748  min_lr: 0.001748  loss: 2.3149 (2.3293)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0004  max mem: 42573
Epoch: [171]  [100/312]  eta: 0:01:57  lr: 0.001747  min_lr: 0.001747  loss: 2.2942 (2.3383)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [171]  [110/312]  eta: 0:01:49  lr: 0.001747  min_lr: 0.001747  loss: 2.3366 (2.3413)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0003  max mem: 42573
Epoch: [171]  [120/312]  eta: 0:01:42  lr: 0.001746  min_lr: 0.001746  loss: 2.2500 (2.3249)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [171]  [130/312]  eta: 0:01:35  lr: 0.001745  min_lr: 0.001745  loss: 2.4447 (2.3429)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [171]  [140/312]  eta: 0:01:29  lr: 0.001744  min_lr: 0.001744  loss: 2.5272 (2.3481)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [171]  [150/312]  eta: 0:01:23  lr: 0.001744  min_lr: 0.001744  loss: 2.5856 (2.3563)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [171]  [160/312]  eta: 0:01:17  lr: 0.001743  min_lr: 0.001743  loss: 2.5063 (2.3627)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [171]  [170/312]  eta: 0:01:11  lr: 0.001742  min_lr: 0.001742  loss: 2.3826 (2.3524)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [171]  [180/312]  eta: 0:01:05  lr: 0.001742  min_lr: 0.001742  loss: 2.1555 (2.3424)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [171]  [190/312]  eta: 0:01:00  lr: 0.001741  min_lr: 0.001741  loss: 2.2110 (2.3496)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [171]  [200/312]  eta: 0:00:55  lr: 0.001740  min_lr: 0.001740  loss: 2.4847 (2.3554)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [171]  [210/312]  eta: 0:00:50  lr: 0.001739  min_lr: 0.001739  loss: 2.4892 (2.3613)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [171]  [220/312]  eta: 0:00:44  lr: 0.001739  min_lr: 0.001739  loss: 2.4892 (2.3655)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [171]  [230/312]  eta: 0:00:39  lr: 0.001738  min_lr: 0.001738  loss: 2.3542 (2.3568)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [171]  [240/312]  eta: 0:00:34  lr: 0.001737  min_lr: 0.001737  loss: 2.4275 (2.3559)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0003  max mem: 42573
Epoch: [171]  [250/312]  eta: 0:00:29  lr: 0.001737  min_lr: 0.001737  loss: 2.4367 (2.3576)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0003  max mem: 42573
Epoch: [171]  [260/312]  eta: 0:00:24  lr: 0.001736  min_lr: 0.001736  loss: 2.5858 (2.3615)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0003  max mem: 42573
Epoch: [171]  [270/312]  eta: 0:00:20  lr: 0.001735  min_lr: 0.001735  loss: 2.5729 (2.3647)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0003  max mem: 42573
Epoch: [171]  [280/312]  eta: 0:00:15  lr: 0.001734  min_lr: 0.001734  loss: 2.4709 (2.3698)  weight_decay: 0.0500 (0.0500)  time: 0.4341  data: 0.0009  max mem: 42573
Epoch: [171]  [290/312]  eta: 0:00:10  lr: 0.001734  min_lr: 0.001734  loss: 2.6366 (2.3720)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0008  max mem: 42573
Epoch: [171]  [300/312]  eta: 0:00:05  lr: 0.001733  min_lr: 0.001733  loss: 2.3990 (2.3758)  weight_decay: 0.0500 (0.0500)  time: 0.4324  data: 0.0001  max mem: 42573
Epoch: [171]  [310/312]  eta: 0:00:00  lr: 0.001732  min_lr: 0.001732  loss: 2.5124 (2.3823)  weight_decay: 0.0500 (0.0500)  time: 0.4323  data: 0.0001  max mem: 42573
Epoch: [171]  [311/312]  eta: 0:00:00  lr: 0.001732  min_lr: 0.001732  loss: 2.5356 (2.3830)  weight_decay: 0.0500 (0.0500)  time: 0.4323  data: 0.0001  max mem: 42573
Epoch: [171] Total time: 0:02:28 (0.4749 s / it)
Averaged stats: lr: 0.001732  min_lr: 0.001732  loss: 2.5356 (2.3955)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:00:45  loss: 0.7959 (0.7959)  acc1: 82.0312 (82.0312)  acc5: 93.7500 (93.7500)  time: 5.0048  data: 4.8954  max mem: 42573
Test:  [8/9]  eta: 0:00:00  loss: 1.1135 (1.0478)  acc1: 72.6562 (73.3440)  acc5: 91.1458 (90.9760)  time: 0.6327  data: 0.5440  max mem: 42573
Test: Total time: 0:00:05 (0.6595 s / it)
* Acc@1 73.442 Acc@5 91.338 loss 1.058
Accuracy of the model on the 50000 test images: 73.4%
Max accuracy: 74.20%
Epoch: [172]  [  0/312]  eta: 0:50:39  lr: 0.001732  min_lr: 0.001732  loss: 1.4831 (1.4831)  weight_decay: 0.0500 (0.0500)  time: 9.7411  data: 8.5362  max mem: 42573
Epoch: [172]  [ 10/312]  eta: 0:07:41  lr: 0.001731  min_lr: 0.001731  loss: 2.5709 (2.3292)  weight_decay: 0.0500 (0.0500)  time: 1.5288  data: 0.7886  max mem: 42573
Epoch: [172]  [ 20/312]  eta: 0:04:54  lr: 0.001731  min_lr: 0.001731  loss: 2.5637 (2.4183)  weight_decay: 0.0500 (0.0500)  time: 0.5702  data: 0.0071  max mem: 42573
Epoch: [172]  [ 30/312]  eta: 0:03:51  lr: 0.001730  min_lr: 0.001730  loss: 2.4679 (2.3815)  weight_decay: 0.0500 (0.0500)  time: 0.4331  data: 0.0004  max mem: 42573
Epoch: [172]  [ 40/312]  eta: 0:03:17  lr: 0.001729  min_lr: 0.001729  loss: 2.4185 (2.3815)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [172]  [ 50/312]  eta: 0:02:55  lr: 0.001729  min_lr: 0.001729  loss: 2.4263 (2.3714)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [172]  [ 60/312]  eta: 0:02:38  lr: 0.001728  min_lr: 0.001728  loss: 2.5771 (2.3823)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [172]  [ 70/312]  eta: 0:02:25  lr: 0.001727  min_lr: 0.001727  loss: 2.6048 (2.3840)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [172]  [ 80/312]  eta: 0:02:15  lr: 0.001726  min_lr: 0.001726  loss: 2.6048 (2.4126)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [172]  [ 90/312]  eta: 0:02:05  lr: 0.001726  min_lr: 0.001726  loss: 2.5604 (2.3962)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [172]  [100/312]  eta: 0:01:57  lr: 0.001725  min_lr: 0.001725  loss: 2.3934 (2.3966)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [172]  [110/312]  eta: 0:01:49  lr: 0.001724  min_lr: 0.001724  loss: 2.3934 (2.3976)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [172]  [120/312]  eta: 0:01:42  lr: 0.001724  min_lr: 0.001724  loss: 2.4699 (2.4122)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [172]  [130/312]  eta: 0:01:35  lr: 0.001723  min_lr: 0.001723  loss: 2.5223 (2.4035)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [172]  [140/312]  eta: 0:01:29  lr: 0.001722  min_lr: 0.001722  loss: 2.3875 (2.3931)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [172]  [150/312]  eta: 0:01:23  lr: 0.001721  min_lr: 0.001721  loss: 2.4534 (2.3967)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [172]  [160/312]  eta: 0:01:17  lr: 0.001721  min_lr: 0.001721  loss: 2.4946 (2.3908)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [172]  [170/312]  eta: 0:01:11  lr: 0.001720  min_lr: 0.001720  loss: 2.1265 (2.3779)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [172]  [180/312]  eta: 0:01:06  lr: 0.001719  min_lr: 0.001719  loss: 2.2989 (2.3784)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [172]  [190/312]  eta: 0:01:00  lr: 0.001719  min_lr: 0.001719  loss: 2.5642 (2.3829)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [172]  [200/312]  eta: 0:00:55  lr: 0.001718  min_lr: 0.001718  loss: 2.5361 (2.3765)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [172]  [210/312]  eta: 0:00:50  lr: 0.001717  min_lr: 0.001717  loss: 2.4410 (2.3770)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [172]  [220/312]  eta: 0:00:44  lr: 0.001716  min_lr: 0.001716  loss: 2.4937 (2.3780)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0003  max mem: 42573
Epoch: [172]  [230/312]  eta: 0:00:39  lr: 0.001716  min_lr: 0.001716  loss: 2.4015 (2.3727)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [172]  [240/312]  eta: 0:00:34  lr: 0.001715  min_lr: 0.001715  loss: 2.4748 (2.3788)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [172]  [250/312]  eta: 0:00:29  lr: 0.001714  min_lr: 0.001714  loss: 2.4789 (2.3744)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [172]  [260/312]  eta: 0:00:24  lr: 0.001714  min_lr: 0.001714  loss: 2.3603 (2.3766)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [172]  [270/312]  eta: 0:00:20  lr: 0.001713  min_lr: 0.001713  loss: 2.4148 (2.3767)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [172]  [280/312]  eta: 0:00:15  lr: 0.001712  min_lr: 0.001712  loss: 2.3968 (2.3722)  weight_decay: 0.0500 (0.0500)  time: 0.4343  data: 0.0011  max mem: 42573
Epoch: [172]  [290/312]  eta: 0:00:10  lr: 0.001711  min_lr: 0.001711  loss: 2.4313 (2.3731)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0010  max mem: 42573
Epoch: [172]  [300/312]  eta: 0:00:05  lr: 0.001711  min_lr: 0.001711  loss: 2.4567 (2.3743)  weight_decay: 0.0500 (0.0500)  time: 0.4323  data: 0.0001  max mem: 42573
Epoch: [172]  [310/312]  eta: 0:00:00  lr: 0.001710  min_lr: 0.001710  loss: 2.3106 (2.3720)  weight_decay: 0.0500 (0.0500)  time: 0.4323  data: 0.0001  max mem: 42573
Epoch: [172]  [311/312]  eta: 0:00:00  lr: 0.001710  min_lr: 0.001710  loss: 2.3106 (2.3701)  weight_decay: 0.0500 (0.0500)  time: 0.4323  data: 0.0001  max mem: 42573
Epoch: [172] Total time: 0:02:28 (0.4752 s / it)
Averaged stats: lr: 0.001710  min_lr: 0.001710  loss: 2.3106 (2.3941)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:00:43  loss: 0.8293 (0.8293)  acc1: 80.4688 (80.4688)  acc5: 94.7917 (94.7917)  time: 4.8587  data: 4.7494  max mem: 42573
Test:  [8/9]  eta: 0:00:00  loss: 1.1889 (1.0598)  acc1: 72.3958 (74.1120)  acc5: 90.6250 (91.4880)  time: 0.6168  data: 0.5278  max mem: 42573
Test: Total time: 0:00:05 (0.6358 s / it)
* Acc@1 73.712 Acc@5 91.650 loss 1.051
Accuracy of the model on the 50000 test images: 73.7%
Max accuracy: 74.20%
Epoch: [173]  [  0/312]  eta: 0:50:06  lr: 0.001710  min_lr: 0.001710  loss: 2.5908 (2.5908)  weight_decay: 0.0500 (0.0500)  time: 9.6359  data: 7.7666  max mem: 42573
Epoch: [173]  [ 10/312]  eta: 0:07:08  lr: 0.001709  min_lr: 0.001709  loss: 2.5789 (2.5151)  weight_decay: 0.0500 (0.0500)  time: 1.4201  data: 0.7067  max mem: 42573
Epoch: [173]  [ 20/312]  eta: 0:04:37  lr: 0.001708  min_lr: 0.001708  loss: 2.4882 (2.4857)  weight_decay: 0.0500 (0.0500)  time: 0.5158  data: 0.0005  max mem: 42573
Epoch: [173]  [ 30/312]  eta: 0:03:40  lr: 0.001708  min_lr: 0.001708  loss: 2.2665 (2.3662)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [173]  [ 40/312]  eta: 0:03:09  lr: 0.001707  min_lr: 0.001707  loss: 2.0868 (2.3377)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [173]  [ 50/312]  eta: 0:02:49  lr: 0.001706  min_lr: 0.001706  loss: 2.3734 (2.3333)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [173]  [ 60/312]  eta: 0:02:34  lr: 0.001706  min_lr: 0.001706  loss: 2.4826 (2.3507)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [173]  [ 70/312]  eta: 0:02:21  lr: 0.001705  min_lr: 0.001705  loss: 2.4966 (2.3604)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [173]  [ 80/312]  eta: 0:02:11  lr: 0.001704  min_lr: 0.001704  loss: 2.3199 (2.3585)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [173]  [ 90/312]  eta: 0:02:02  lr: 0.001703  min_lr: 0.001703  loss: 2.3659 (2.3564)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0004  max mem: 42573
Epoch: [173]  [100/312]  eta: 0:01:54  lr: 0.001703  min_lr: 0.001703  loss: 2.4777 (2.3616)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0004  max mem: 42573
Epoch: [173]  [110/312]  eta: 0:01:47  lr: 0.001702  min_lr: 0.001702  loss: 2.2112 (2.3422)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [173]  [120/312]  eta: 0:01:40  lr: 0.001701  min_lr: 0.001701  loss: 2.2112 (2.3486)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [173]  [130/312]  eta: 0:01:33  lr: 0.001701  min_lr: 0.001701  loss: 2.3848 (2.3354)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [173]  [140/312]  eta: 0:01:27  lr: 0.001700  min_lr: 0.001700  loss: 2.4874 (2.3549)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0003  max mem: 42573
Epoch: [173]  [150/312]  eta: 0:01:21  lr: 0.001699  min_lr: 0.001699  loss: 2.5794 (2.3592)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0003  max mem: 42573
Epoch: [173]  [160/312]  eta: 0:01:16  lr: 0.001699  min_lr: 0.001699  loss: 2.4699 (2.3608)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [173]  [170/312]  eta: 0:01:10  lr: 0.001698  min_lr: 0.001698  loss: 2.4097 (2.3635)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [173]  [180/312]  eta: 0:01:05  lr: 0.001697  min_lr: 0.001697  loss: 2.5623 (2.3754)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [173]  [190/312]  eta: 0:00:59  lr: 0.001696  min_lr: 0.001696  loss: 2.4928 (2.3675)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [173]  [200/312]  eta: 0:00:54  lr: 0.001696  min_lr: 0.001696  loss: 2.4000 (2.3735)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [173]  [210/312]  eta: 0:00:49  lr: 0.001695  min_lr: 0.001695  loss: 2.4556 (2.3718)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [173]  [220/312]  eta: 0:00:44  lr: 0.001694  min_lr: 0.001694  loss: 2.5603 (2.3741)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0003  max mem: 42573
Epoch: [173]  [230/312]  eta: 0:00:39  lr: 0.001694  min_lr: 0.001694  loss: 2.5788 (2.3784)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [173]  [240/312]  eta: 0:00:34  lr: 0.001693  min_lr: 0.001693  loss: 2.6238 (2.3905)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [173]  [250/312]  eta: 0:00:29  lr: 0.001692  min_lr: 0.001692  loss: 2.5525 (2.3925)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [173]  [260/312]  eta: 0:00:24  lr: 0.001691  min_lr: 0.001691  loss: 2.4186 (2.3919)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [173]  [270/312]  eta: 0:00:19  lr: 0.001691  min_lr: 0.001691  loss: 2.4774 (2.3864)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [173]  [280/312]  eta: 0:00:15  lr: 0.001690  min_lr: 0.001690  loss: 2.3718 (2.3825)  weight_decay: 0.0500 (0.0500)  time: 0.4343  data: 0.0009  max mem: 42573
Epoch: [173]  [290/312]  eta: 0:00:10  lr: 0.001689  min_lr: 0.001689  loss: 2.1098 (2.3729)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0008  max mem: 42573
Epoch: [173]  [300/312]  eta: 0:00:05  lr: 0.001689  min_lr: 0.001689  loss: 2.3037 (2.3757)  weight_decay: 0.0500 (0.0500)  time: 0.4323  data: 0.0001  max mem: 42573
Epoch: [173]  [310/312]  eta: 0:00:00  lr: 0.001688  min_lr: 0.001688  loss: 2.3037 (2.3671)  weight_decay: 0.0500 (0.0500)  time: 0.4323  data: 0.0001  max mem: 42573
Epoch: [173]  [311/312]  eta: 0:00:00  lr: 0.001688  min_lr: 0.001688  loss: 2.3037 (2.3669)  weight_decay: 0.0500 (0.0500)  time: 0.4322  data: 0.0001  max mem: 42573
Epoch: [173] Total time: 0:02:27 (0.4713 s / it)
Averaged stats: lr: 0.001688  min_lr: 0.001688  loss: 2.3037 (2.3990)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:00:42  loss: 0.7403 (0.7403)  acc1: 82.2917 (82.2917)  acc5: 93.7500 (93.7500)  time: 4.7099  data: 4.6003  max mem: 42573
Test:  [8/9]  eta: 0:00:00  loss: 1.0203 (1.0141)  acc1: 73.9583 (74.5600)  acc5: 92.4528 (92.3200)  time: 0.6011  data: 0.5112  max mem: 42573
Test: Total time: 0:00:05 (0.6260 s / it)
* Acc@1 74.446 Acc@5 92.048 loss 1.020
Accuracy of the model on the 50000 test images: 74.4%
Max accuracy: 74.45%
Epoch: [174]  [  0/312]  eta: 0:51:01  lr: 0.001688  min_lr: 0.001688  loss: 2.3820 (2.3820)  weight_decay: 0.0500 (0.0500)  time: 9.8112  data: 8.6357  max mem: 42573
Epoch: [174]  [ 10/312]  eta: 0:07:18  lr: 0.001687  min_lr: 0.001687  loss: 2.3361 (2.2655)  weight_decay: 0.0500 (0.0500)  time: 1.4514  data: 0.7854  max mem: 42573
Epoch: [174]  [ 20/312]  eta: 0:04:42  lr: 0.001686  min_lr: 0.001686  loss: 2.3812 (2.3460)  weight_decay: 0.0500 (0.0500)  time: 0.5243  data: 0.0003  max mem: 42573
Epoch: [174]  [ 30/312]  eta: 0:03:44  lr: 0.001686  min_lr: 0.001686  loss: 2.5346 (2.3540)  weight_decay: 0.0500 (0.0500)  time: 0.4346  data: 0.0003  max mem: 42573
Epoch: [174]  [ 40/312]  eta: 0:03:12  lr: 0.001685  min_lr: 0.001685  loss: 2.5316 (2.4170)  weight_decay: 0.0500 (0.0500)  time: 0.4347  data: 0.0004  max mem: 42573
Epoch: [174]  [ 50/312]  eta: 0:02:51  lr: 0.001684  min_lr: 0.001684  loss: 2.4728 (2.4095)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [174]  [ 60/312]  eta: 0:02:35  lr: 0.001683  min_lr: 0.001683  loss: 2.4728 (2.4185)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [174]  [ 70/312]  eta: 0:02:23  lr: 0.001683  min_lr: 0.001683  loss: 2.5487 (2.4017)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [174]  [ 80/312]  eta: 0:02:12  lr: 0.001682  min_lr: 0.001682  loss: 2.5276 (2.4157)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [174]  [ 90/312]  eta: 0:02:03  lr: 0.001681  min_lr: 0.001681  loss: 2.4727 (2.4041)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [174]  [100/312]  eta: 0:01:55  lr: 0.001681  min_lr: 0.001681  loss: 2.3113 (2.4005)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [174]  [110/312]  eta: 0:01:48  lr: 0.001680  min_lr: 0.001680  loss: 2.3113 (2.3921)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [174]  [120/312]  eta: 0:01:41  lr: 0.001679  min_lr: 0.001679  loss: 2.5217 (2.3960)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [174]  [130/312]  eta: 0:01:34  lr: 0.001678  min_lr: 0.001678  loss: 2.5217 (2.3837)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [174]  [140/312]  eta: 0:01:28  lr: 0.001678  min_lr: 0.001678  loss: 2.3581 (2.3926)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [174]  [150/312]  eta: 0:01:22  lr: 0.001677  min_lr: 0.001677  loss: 2.4098 (2.3929)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [174]  [160/312]  eta: 0:01:16  lr: 0.001676  min_lr: 0.001676  loss: 2.5625 (2.4056)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [174]  [170/312]  eta: 0:01:10  lr: 0.001676  min_lr: 0.001676  loss: 2.6106 (2.4125)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [174]  [180/312]  eta: 0:01:05  lr: 0.001675  min_lr: 0.001675  loss: 2.6595 (2.4198)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [174]  [190/312]  eta: 0:01:00  lr: 0.001674  min_lr: 0.001674  loss: 2.5513 (2.4216)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [174]  [200/312]  eta: 0:00:54  lr: 0.001674  min_lr: 0.001674  loss: 2.4660 (2.4129)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [174]  [210/312]  eta: 0:00:49  lr: 0.001673  min_lr: 0.001673  loss: 2.4660 (2.4121)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [174]  [220/312]  eta: 0:00:44  lr: 0.001672  min_lr: 0.001672  loss: 2.6249 (2.4179)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [174]  [230/312]  eta: 0:00:39  lr: 0.001671  min_lr: 0.001671  loss: 2.4450 (2.4178)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [174]  [240/312]  eta: 0:00:34  lr: 0.001671  min_lr: 0.001671  loss: 2.4450 (2.4198)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [174]  [250/312]  eta: 0:00:29  lr: 0.001670  min_lr: 0.001670  loss: 2.4691 (2.4119)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [174]  [260/312]  eta: 0:00:24  lr: 0.001669  min_lr: 0.001669  loss: 2.3214 (2.4080)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [174]  [270/312]  eta: 0:00:19  lr: 0.001669  min_lr: 0.001669  loss: 2.4255 (2.4054)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [174]  [280/312]  eta: 0:00:15  lr: 0.001668  min_lr: 0.001668  loss: 2.4932 (2.4115)  weight_decay: 0.0500 (0.0500)  time: 0.4345  data: 0.0010  max mem: 42573
Epoch: [174]  [290/312]  eta: 0:00:10  lr: 0.001667  min_lr: 0.001667  loss: 2.4980 (2.4122)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0008  max mem: 42573
Epoch: [174]  [300/312]  eta: 0:00:05  lr: 0.001666  min_lr: 0.001666  loss: 2.3640 (2.4120)  weight_decay: 0.0500 (0.0500)  time: 0.4326  data: 0.0001  max mem: 42573
Epoch: [174]  [310/312]  eta: 0:00:00  lr: 0.001666  min_lr: 0.001666  loss: 2.3640 (2.4059)  weight_decay: 0.0500 (0.0500)  time: 0.4326  data: 0.0001  max mem: 42573
Epoch: [174]  [311/312]  eta: 0:00:00  lr: 0.001666  min_lr: 0.001666  loss: 2.3640 (2.4054)  weight_decay: 0.0500 (0.0500)  time: 0.4326  data: 0.0001  max mem: 42573
Epoch: [174] Total time: 0:02:27 (0.4726 s / it)
Averaged stats: lr: 0.001666  min_lr: 0.001666  loss: 2.3640 (2.3846)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:00:41  loss: 0.7788 (0.7788)  acc1: 80.2083 (80.2083)  acc5: 94.7917 (94.7917)  time: 4.6351  data: 4.5263  max mem: 42573
Test:  [8/9]  eta: 0:00:00  loss: 1.0769 (1.0173)  acc1: 74.4792 (74.2400)  acc5: 92.1875 (92.1600)  time: 0.5977  data: 0.5098  max mem: 42573
Test: Total time: 0:00:05 (0.6061 s / it)
* Acc@1 74.248 Acc@5 91.706 loss 1.027
Accuracy of the model on the 50000 test images: 74.2%
Max accuracy: 74.45%
Epoch: [175]  [  0/312]  eta: 0:49:18  lr: 0.001666  min_lr: 0.001666  loss: 2.9373 (2.9373)  weight_decay: 0.0500 (0.0500)  time: 9.4838  data: 6.4767  max mem: 42573
Epoch: [175]  [ 10/312]  eta: 0:07:13  lr: 0.001665  min_lr: 0.001665  loss: 2.3237 (2.2700)  weight_decay: 0.0500 (0.0500)  time: 1.4365  data: 0.6204  max mem: 42573
Epoch: [175]  [ 20/312]  eta: 0:04:39  lr: 0.001664  min_lr: 0.001664  loss: 2.3703 (2.2797)  weight_decay: 0.0500 (0.0500)  time: 0.5325  data: 0.0176  max mem: 42573
Epoch: [175]  [ 30/312]  eta: 0:03:42  lr: 0.001663  min_lr: 0.001663  loss: 2.4692 (2.2808)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [175]  [ 40/312]  eta: 0:03:11  lr: 0.001663  min_lr: 0.001663  loss: 2.4006 (2.2776)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [175]  [ 50/312]  eta: 0:02:50  lr: 0.001662  min_lr: 0.001662  loss: 2.4779 (2.3178)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [175]  [ 60/312]  eta: 0:02:34  lr: 0.001661  min_lr: 0.001661  loss: 2.6000 (2.3624)  weight_decay: 0.0500 (0.0500)  time: 0.4341  data: 0.0003  max mem: 42573
Epoch: [175]  [ 70/312]  eta: 0:02:22  lr: 0.001661  min_lr: 0.001661  loss: 2.4206 (2.3476)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0003  max mem: 42573
Epoch: [175]  [ 80/312]  eta: 0:02:12  lr: 0.001660  min_lr: 0.001660  loss: 2.4206 (2.3670)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0004  max mem: 42573
Epoch: [175]  [ 90/312]  eta: 0:02:03  lr: 0.001659  min_lr: 0.001659  loss: 2.5063 (2.3740)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0004  max mem: 42573
Epoch: [175]  [100/312]  eta: 0:01:55  lr: 0.001658  min_lr: 0.001658  loss: 2.5063 (2.3839)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0005  max mem: 42573
Epoch: [175]  [110/312]  eta: 0:01:47  lr: 0.001658  min_lr: 0.001658  loss: 2.5697 (2.3937)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [175]  [120/312]  eta: 0:01:40  lr: 0.001657  min_lr: 0.001657  loss: 2.4610 (2.3867)  weight_decay: 0.0500 (0.0500)  time: 0.4344  data: 0.0004  max mem: 42573
Epoch: [175]  [130/312]  eta: 0:01:34  lr: 0.001656  min_lr: 0.001656  loss: 2.2712 (2.3606)  weight_decay: 0.0500 (0.0500)  time: 0.4344  data: 0.0004  max mem: 42573
Epoch: [175]  [140/312]  eta: 0:01:28  lr: 0.001656  min_lr: 0.001656  loss: 2.2712 (2.3746)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [175]  [150/312]  eta: 0:01:22  lr: 0.001655  min_lr: 0.001655  loss: 2.2739 (2.3555)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [175]  [160/312]  eta: 0:01:16  lr: 0.001654  min_lr: 0.001654  loss: 2.3227 (2.3591)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [175]  [170/312]  eta: 0:01:10  lr: 0.001654  min_lr: 0.001654  loss: 2.4544 (2.3570)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [175]  [180/312]  eta: 0:01:05  lr: 0.001653  min_lr: 0.001653  loss: 2.3512 (2.3592)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [175]  [190/312]  eta: 0:00:59  lr: 0.001652  min_lr: 0.001652  loss: 2.1873 (2.3513)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [175]  [200/312]  eta: 0:00:54  lr: 0.001651  min_lr: 0.001651  loss: 2.3497 (2.3589)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0004  max mem: 42573
Epoch: [175]  [210/312]  eta: 0:00:49  lr: 0.001651  min_lr: 0.001651  loss: 2.4859 (2.3641)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [175]  [220/312]  eta: 0:00:44  lr: 0.001650  min_lr: 0.001650  loss: 2.5223 (2.3685)  weight_decay: 0.0500 (0.0500)  time: 0.4341  data: 0.0004  max mem: 42573
Epoch: [175]  [230/312]  eta: 0:00:39  lr: 0.001649  min_lr: 0.001649  loss: 2.5413 (2.3732)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0004  max mem: 42573
Epoch: [175]  [240/312]  eta: 0:00:34  lr: 0.001649  min_lr: 0.001649  loss: 2.3671 (2.3714)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [175]  [250/312]  eta: 0:00:29  lr: 0.001648  min_lr: 0.001648  loss: 2.4539 (2.3699)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [175]  [260/312]  eta: 0:00:24  lr: 0.001647  min_lr: 0.001647  loss: 2.4894 (2.3726)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [175]  [270/312]  eta: 0:00:19  lr: 0.001646  min_lr: 0.001646  loss: 2.4715 (2.3735)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [175]  [280/312]  eta: 0:00:15  lr: 0.001646  min_lr: 0.001646  loss: 2.4519 (2.3769)  weight_decay: 0.0500 (0.0500)  time: 0.4342  data: 0.0009  max mem: 42573
Epoch: [175]  [290/312]  eta: 0:00:10  lr: 0.001645  min_lr: 0.001645  loss: 2.5091 (2.3826)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0008  max mem: 42573
Epoch: [175]  [300/312]  eta: 0:00:05  lr: 0.001644  min_lr: 0.001644  loss: 2.4792 (2.3839)  weight_decay: 0.0500 (0.0500)  time: 0.4324  data: 0.0001  max mem: 42573
Epoch: [175]  [310/312]  eta: 0:00:00  lr: 0.001644  min_lr: 0.001644  loss: 2.4567 (2.3825)  weight_decay: 0.0500 (0.0500)  time: 0.4323  data: 0.0001  max mem: 42573
Epoch: [175]  [311/312]  eta: 0:00:00  lr: 0.001644  min_lr: 0.001644  loss: 2.4567 (2.3825)  weight_decay: 0.0500 (0.0500)  time: 0.4323  data: 0.0001  max mem: 42573
Epoch: [175] Total time: 0:02:27 (0.4721 s / it)
Averaged stats: lr: 0.001644  min_lr: 0.001644  loss: 2.4567 (2.3887)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:00:42  loss: 0.8034 (0.8034)  acc1: 79.9479 (79.9479)  acc5: 92.9688 (92.9688)  time: 4.7431  data: 4.6338  max mem: 42573
Test:  [8/9]  eta: 0:00:00  loss: 1.1590 (1.0658)  acc1: 72.1354 (72.8960)  acc5: 91.6667 (90.7520)  time: 0.6041  data: 0.5149  max mem: 42573
Test: Total time: 0:00:05 (0.6139 s / it)
* Acc@1 73.628 Acc@5 91.506 loss 1.051
Accuracy of the model on the 50000 test images: 73.6%
Max accuracy: 74.45%
Epoch: [176]  [  0/312]  eta: 0:50:27  lr: 0.001643  min_lr: 0.001643  loss: 2.1005 (2.1005)  weight_decay: 0.0500 (0.0500)  time: 9.7029  data: 7.4965  max mem: 42573
Epoch: [176]  [ 10/312]  eta: 0:07:42  lr: 0.001643  min_lr: 0.001643  loss: 2.4383 (2.3796)  weight_decay: 0.0500 (0.0500)  time: 1.5305  data: 0.6901  max mem: 42573
Epoch: [176]  [ 20/312]  eta: 0:04:54  lr: 0.001642  min_lr: 0.001642  loss: 2.4383 (2.3692)  weight_decay: 0.0500 (0.0500)  time: 0.5734  data: 0.0049  max mem: 42573
Epoch: [176]  [ 30/312]  eta: 0:03:52  lr: 0.001641  min_lr: 0.001641  loss: 2.4752 (2.3643)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0003  max mem: 42573
Epoch: [176]  [ 40/312]  eta: 0:03:17  lr: 0.001641  min_lr: 0.001641  loss: 2.5551 (2.3923)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0003  max mem: 42573
Epoch: [176]  [ 50/312]  eta: 0:02:55  lr: 0.001640  min_lr: 0.001640  loss: 2.5551 (2.3849)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [176]  [ 60/312]  eta: 0:02:39  lr: 0.001639  min_lr: 0.001639  loss: 2.1592 (2.3502)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [176]  [ 70/312]  eta: 0:02:26  lr: 0.001639  min_lr: 0.001639  loss: 2.1592 (2.3148)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0004  max mem: 42573
Epoch: [176]  [ 80/312]  eta: 0:02:15  lr: 0.001638  min_lr: 0.001638  loss: 2.2300 (2.3018)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [176]  [ 90/312]  eta: 0:02:05  lr: 0.001637  min_lr: 0.001637  loss: 2.3724 (2.3145)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0003  max mem: 42573
Epoch: [176]  [100/312]  eta: 0:01:57  lr: 0.001636  min_lr: 0.001636  loss: 2.6090 (2.3438)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [176]  [110/312]  eta: 0:01:49  lr: 0.001636  min_lr: 0.001636  loss: 2.4561 (2.3427)  weight_decay: 0.0500 (0.0500)  time: 0.4342  data: 0.0004  max mem: 42573
Epoch: [176]  [120/312]  eta: 0:01:42  lr: 0.001635  min_lr: 0.001635  loss: 2.2475 (2.3116)  weight_decay: 0.0500 (0.0500)  time: 0.4341  data: 0.0003  max mem: 42573
Epoch: [176]  [130/312]  eta: 0:01:35  lr: 0.001634  min_lr: 0.001634  loss: 1.9949 (2.3151)  weight_decay: 0.0500 (0.0500)  time: 0.4395  data: 0.0003  max mem: 42573
Epoch: [176]  [140/312]  eta: 0:01:29  lr: 0.001634  min_lr: 0.001634  loss: 2.3611 (2.3159)  weight_decay: 0.0500 (0.0500)  time: 0.4395  data: 0.0004  max mem: 42573
Epoch: [176]  [150/312]  eta: 0:01:23  lr: 0.001633  min_lr: 0.001633  loss: 2.4056 (2.3308)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [176]  [160/312]  eta: 0:01:17  lr: 0.001632  min_lr: 0.001632  loss: 2.2802 (2.3192)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [176]  [170/312]  eta: 0:01:11  lr: 0.001631  min_lr: 0.001631  loss: 2.0933 (2.3217)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [176]  [180/312]  eta: 0:01:06  lr: 0.001631  min_lr: 0.001631  loss: 2.4902 (2.3227)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [176]  [190/312]  eta: 0:01:00  lr: 0.001630  min_lr: 0.001630  loss: 2.5011 (2.3368)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [176]  [200/312]  eta: 0:00:55  lr: 0.001629  min_lr: 0.001629  loss: 2.4723 (2.3345)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [176]  [210/312]  eta: 0:00:50  lr: 0.001629  min_lr: 0.001629  loss: 2.2860 (2.3395)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [176]  [220/312]  eta: 0:00:44  lr: 0.001628  min_lr: 0.001628  loss: 2.5384 (2.3458)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [176]  [230/312]  eta: 0:00:39  lr: 0.001627  min_lr: 0.001627  loss: 2.5384 (2.3465)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [176]  [240/312]  eta: 0:00:34  lr: 0.001627  min_lr: 0.001627  loss: 2.3965 (2.3470)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0005  max mem: 42573
Epoch: [176]  [250/312]  eta: 0:00:29  lr: 0.001626  min_lr: 0.001626  loss: 2.3965 (2.3430)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [176]  [260/312]  eta: 0:00:24  lr: 0.001625  min_lr: 0.001625  loss: 2.4229 (2.3452)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [176]  [270/312]  eta: 0:00:20  lr: 0.001624  min_lr: 0.001624  loss: 2.6106 (2.3505)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [176]  [280/312]  eta: 0:00:15  lr: 0.001624  min_lr: 0.001624  loss: 2.6272 (2.3581)  weight_decay: 0.0500 (0.0500)  time: 0.4349  data: 0.0010  max mem: 42573
Epoch: [176]  [290/312]  eta: 0:00:10  lr: 0.001623  min_lr: 0.001623  loss: 2.5678 (2.3600)  weight_decay: 0.0500 (0.0500)  time: 0.4341  data: 0.0008  max mem: 42573
Epoch: [176]  [300/312]  eta: 0:00:05  lr: 0.001622  min_lr: 0.001622  loss: 2.5009 (2.3634)  weight_decay: 0.0500 (0.0500)  time: 0.4324  data: 0.0001  max mem: 42573
Epoch: [176]  [310/312]  eta: 0:00:00  lr: 0.001622  min_lr: 0.001622  loss: 2.5463 (2.3687)  weight_decay: 0.0500 (0.0500)  time: 0.4324  data: 0.0001  max mem: 42573
Epoch: [176]  [311/312]  eta: 0:00:00  lr: 0.001621  min_lr: 0.001621  loss: 2.5463 (2.3704)  weight_decay: 0.0500 (0.0500)  time: 0.4324  data: 0.0001  max mem: 42573
Epoch: [176] Total time: 0:02:28 (0.4759 s / it)
Averaged stats: lr: 0.001621  min_lr: 0.001621  loss: 2.5463 (2.3801)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:00:43  loss: 0.7888 (0.7888)  acc1: 81.2500 (81.2500)  acc5: 92.9688 (92.9688)  time: 4.8570  data: 4.7483  max mem: 42573
Test:  [8/9]  eta: 0:00:00  loss: 1.0789 (1.0278)  acc1: 73.6979 (73.5680)  acc5: 90.6250 (91.5840)  time: 0.6163  data: 0.5276  max mem: 42573
Test: Total time: 0:00:05 (0.6232 s / it)
* Acc@1 74.614 Acc@5 91.912 loss 1.019
Accuracy of the model on the 50000 test images: 74.6%
Max accuracy: 74.61%
Epoch: [177]  [  0/312]  eta: 0:45:58  lr: 0.001621  min_lr: 0.001621  loss: 2.7689 (2.7689)  weight_decay: 0.0500 (0.0500)  time: 8.8407  data: 8.3392  max mem: 42573
Epoch: [177]  [ 10/312]  eta: 0:06:47  lr: 0.001621  min_lr: 0.001621  loss: 2.2694 (2.2323)  weight_decay: 0.0500 (0.0500)  time: 1.3479  data: 0.8430  max mem: 42573
Epoch: [177]  [ 20/312]  eta: 0:04:26  lr: 0.001620  min_lr: 0.001620  loss: 2.2935 (2.2949)  weight_decay: 0.0500 (0.0500)  time: 0.5159  data: 0.0469  max mem: 42573
Epoch: [177]  [ 30/312]  eta: 0:03:33  lr: 0.001619  min_lr: 0.001619  loss: 2.4675 (2.3619)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [177]  [ 40/312]  eta: 0:03:04  lr: 0.001619  min_lr: 0.001619  loss: 2.4453 (2.3467)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0005  max mem: 42573
Epoch: [177]  [ 50/312]  eta: 0:02:45  lr: 0.001618  min_lr: 0.001618  loss: 2.2901 (2.3249)  weight_decay: 0.0500 (0.0500)  time: 0.4332  data: 0.0004  max mem: 42573
Epoch: [177]  [ 60/312]  eta: 0:02:30  lr: 0.001617  min_lr: 0.001617  loss: 2.2372 (2.3282)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [177]  [ 70/312]  eta: 0:02:19  lr: 0.001616  min_lr: 0.001616  loss: 2.2911 (2.3254)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [177]  [ 80/312]  eta: 0:02:09  lr: 0.001616  min_lr: 0.001616  loss: 2.3695 (2.3507)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [177]  [ 90/312]  eta: 0:02:00  lr: 0.001615  min_lr: 0.001615  loss: 2.4644 (2.3526)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [177]  [100/312]  eta: 0:01:53  lr: 0.001614  min_lr: 0.001614  loss: 2.1001 (2.3299)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [177]  [110/312]  eta: 0:01:45  lr: 0.001614  min_lr: 0.001614  loss: 2.0501 (2.3097)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [177]  [120/312]  eta: 0:01:39  lr: 0.001613  min_lr: 0.001613  loss: 2.3558 (2.3171)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [177]  [130/312]  eta: 0:01:32  lr: 0.001612  min_lr: 0.001612  loss: 2.3227 (2.3082)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [177]  [140/312]  eta: 0:01:26  lr: 0.001612  min_lr: 0.001612  loss: 2.1960 (2.3011)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [177]  [150/312]  eta: 0:01:21  lr: 0.001611  min_lr: 0.001611  loss: 2.1960 (2.3044)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [177]  [160/312]  eta: 0:01:15  lr: 0.001610  min_lr: 0.001610  loss: 2.3957 (2.3070)  weight_decay: 0.0500 (0.0500)  time: 0.4396  data: 0.0004  max mem: 42573
Epoch: [177]  [170/312]  eta: 0:01:10  lr: 0.001609  min_lr: 0.001609  loss: 2.2686 (2.2998)  weight_decay: 0.0500 (0.0500)  time: 0.4398  data: 0.0004  max mem: 42573
Epoch: [177]  [180/312]  eta: 0:01:04  lr: 0.001609  min_lr: 0.001609  loss: 2.2375 (2.3083)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0003  max mem: 42573
Epoch: [177]  [190/312]  eta: 0:00:59  lr: 0.001608  min_lr: 0.001608  loss: 2.4679 (2.3092)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0003  max mem: 42573
Epoch: [177]  [200/312]  eta: 0:00:54  lr: 0.001607  min_lr: 0.001607  loss: 2.3895 (2.3157)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [177]  [210/312]  eta: 0:00:49  lr: 0.001607  min_lr: 0.001607  loss: 2.3895 (2.3121)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [177]  [220/312]  eta: 0:00:44  lr: 0.001606  min_lr: 0.001606  loss: 2.3054 (2.3159)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0004  max mem: 42573
Epoch: [177]  [230/312]  eta: 0:00:39  lr: 0.001605  min_lr: 0.001605  loss: 2.4427 (2.3217)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0005  max mem: 42573
Epoch: [177]  [240/312]  eta: 0:00:34  lr: 0.001604  min_lr: 0.001604  loss: 2.2785 (2.3173)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [177]  [250/312]  eta: 0:00:29  lr: 0.001604  min_lr: 0.001604  loss: 2.5082 (2.3274)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [177]  [260/312]  eta: 0:00:24  lr: 0.001603  min_lr: 0.001603  loss: 2.5021 (2.3249)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0004  max mem: 42573
Epoch: [177]  [270/312]  eta: 0:00:19  lr: 0.001602  min_lr: 0.001602  loss: 2.3293 (2.3291)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [177]  [280/312]  eta: 0:00:15  lr: 0.001602  min_lr: 0.001602  loss: 2.5134 (2.3359)  weight_decay: 0.0500 (0.0500)  time: 0.4343  data: 0.0010  max mem: 42573
Epoch: [177]  [290/312]  eta: 0:00:10  lr: 0.001601  min_lr: 0.001601  loss: 2.4912 (2.3356)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0008  max mem: 42573
Epoch: [177]  [300/312]  eta: 0:00:05  lr: 0.001600  min_lr: 0.001600  loss: 2.4980 (2.3453)  weight_decay: 0.0500 (0.0500)  time: 0.4324  data: 0.0001  max mem: 42573
Epoch: [177]  [310/312]  eta: 0:00:00  lr: 0.001600  min_lr: 0.001600  loss: 2.5621 (2.3481)  weight_decay: 0.0500 (0.0500)  time: 0.4323  data: 0.0001  max mem: 42573
Epoch: [177]  [311/312]  eta: 0:00:00  lr: 0.001599  min_lr: 0.001599  loss: 2.5019 (2.3478)  weight_decay: 0.0500 (0.0500)  time: 0.4323  data: 0.0001  max mem: 42573
Epoch: [177] Total time: 0:02:26 (0.4692 s / it)
Averaged stats: lr: 0.001599  min_lr: 0.001599  loss: 2.5019 (2.3769)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:00:41  loss: 0.7522 (0.7522)  acc1: 81.7708 (81.7708)  acc5: 94.2708 (94.2708)  time: 4.6258  data: 4.5164  max mem: 42573
Test:  [8/9]  eta: 0:00:00  loss: 1.1263 (1.0223)  acc1: 73.1771 (73.6640)  acc5: 93.2292 (92.3840)  time: 0.5926  data: 0.5019  max mem: 42573
Test: Total time: 0:00:05 (0.6126 s / it)
* Acc@1 74.626 Acc@5 92.044 loss 1.016
Accuracy of the model on the 50000 test images: 74.6%
Max accuracy: 74.63%
Epoch: [178]  [  0/312]  eta: 0:49:20  lr: 0.001599  min_lr: 0.001599  loss: 2.8932 (2.8932)  weight_decay: 0.0500 (0.0500)  time: 9.4880  data: 6.3881  max mem: 42573
Epoch: [178]  [ 10/312]  eta: 0:07:22  lr: 0.001599  min_lr: 0.001599  loss: 2.4867 (2.3146)  weight_decay: 0.0500 (0.0500)  time: 1.4637  data: 0.6582  max mem: 42573
Epoch: [178]  [ 20/312]  eta: 0:04:44  lr: 0.001598  min_lr: 0.001598  loss: 2.1726 (2.3359)  weight_decay: 0.0500 (0.0500)  time: 0.5472  data: 0.0428  max mem: 42573
Epoch: [178]  [ 30/312]  eta: 0:03:45  lr: 0.001597  min_lr: 0.001597  loss: 2.5111 (2.3892)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [178]  [ 40/312]  eta: 0:03:13  lr: 0.001597  min_lr: 0.001597  loss: 2.4325 (2.3429)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0005  max mem: 42573
Epoch: [178]  [ 50/312]  eta: 0:02:51  lr: 0.001596  min_lr: 0.001596  loss: 2.3641 (2.3403)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [178]  [ 60/312]  eta: 0:02:36  lr: 0.001595  min_lr: 0.001595  loss: 2.3835 (2.3151)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [178]  [ 70/312]  eta: 0:02:23  lr: 0.001594  min_lr: 0.001594  loss: 2.3998 (2.3256)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [178]  [ 80/312]  eta: 0:02:13  lr: 0.001594  min_lr: 0.001594  loss: 2.4667 (2.3213)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [178]  [ 90/312]  eta: 0:02:03  lr: 0.001593  min_lr: 0.001593  loss: 2.3478 (2.3166)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0004  max mem: 42573
Epoch: [178]  [100/312]  eta: 0:01:55  lr: 0.001592  min_lr: 0.001592  loss: 2.3421 (2.3135)  weight_decay: 0.0500 (0.0500)  time: 0.4343  data: 0.0004  max mem: 42573
Epoch: [178]  [110/312]  eta: 0:01:48  lr: 0.001592  min_lr: 0.001592  loss: 2.3912 (2.3299)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0004  max mem: 42573
Epoch: [178]  [120/312]  eta: 0:01:41  lr: 0.001591  min_lr: 0.001591  loss: 2.6026 (2.3382)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [178]  [130/312]  eta: 0:01:34  lr: 0.001590  min_lr: 0.001590  loss: 2.3594 (2.3248)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [178]  [140/312]  eta: 0:01:28  lr: 0.001590  min_lr: 0.001590  loss: 2.3507 (2.3321)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [178]  [150/312]  eta: 0:01:22  lr: 0.001589  min_lr: 0.001589  loss: 2.4675 (2.3392)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0003  max mem: 42573
Epoch: [178]  [160/312]  eta: 0:01:16  lr: 0.001588  min_lr: 0.001588  loss: 2.3189 (2.3460)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0003  max mem: 42573
Epoch: [178]  [170/312]  eta: 0:01:11  lr: 0.001587  min_lr: 0.001587  loss: 2.3189 (2.3426)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0004  max mem: 42573
Epoch: [178]  [180/312]  eta: 0:01:05  lr: 0.001587  min_lr: 0.001587  loss: 2.3277 (2.3433)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [178]  [190/312]  eta: 0:01:00  lr: 0.001586  min_lr: 0.001586  loss: 2.3083 (2.3435)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [178]  [200/312]  eta: 0:00:54  lr: 0.001585  min_lr: 0.001585  loss: 2.3083 (2.3435)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [178]  [210/312]  eta: 0:00:49  lr: 0.001585  min_lr: 0.001585  loss: 2.4432 (2.3499)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [178]  [220/312]  eta: 0:00:44  lr: 0.001584  min_lr: 0.001584  loss: 2.5006 (2.3515)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [178]  [230/312]  eta: 0:00:39  lr: 0.001583  min_lr: 0.001583  loss: 2.4051 (2.3490)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0004  max mem: 42573
Epoch: [178]  [240/312]  eta: 0:00:34  lr: 0.001583  min_lr: 0.001583  loss: 2.3649 (2.3452)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [178]  [250/312]  eta: 0:00:29  lr: 0.001582  min_lr: 0.001582  loss: 2.3649 (2.3456)  weight_decay: 0.0500 (0.0500)  time: 0.4378  data: 0.0004  max mem: 42573
Epoch: [178]  [260/312]  eta: 0:00:24  lr: 0.001581  min_lr: 0.001581  loss: 2.4145 (2.3486)  weight_decay: 0.0500 (0.0500)  time: 0.4376  data: 0.0004  max mem: 42573
Epoch: [178]  [270/312]  eta: 0:00:19  lr: 0.001580  min_lr: 0.001580  loss: 2.3934 (2.3490)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [178]  [280/312]  eta: 0:00:15  lr: 0.001580  min_lr: 0.001580  loss: 2.4636 (2.3461)  weight_decay: 0.0500 (0.0500)  time: 0.4346  data: 0.0010  max mem: 42573
Epoch: [178]  [290/312]  eta: 0:00:10  lr: 0.001579  min_lr: 0.001579  loss: 2.5271 (2.3483)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0009  max mem: 42573
Epoch: [178]  [300/312]  eta: 0:00:05  lr: 0.001578  min_lr: 0.001578  loss: 2.4724 (2.3488)  weight_decay: 0.0500 (0.0500)  time: 0.4324  data: 0.0001  max mem: 42573
Epoch: [178]  [310/312]  eta: 0:00:00  lr: 0.001578  min_lr: 0.001578  loss: 2.3371 (2.3510)  weight_decay: 0.0500 (0.0500)  time: 0.4323  data: 0.0001  max mem: 42573
Epoch: [178]  [311/312]  eta: 0:00:00  lr: 0.001578  min_lr: 0.001578  loss: 2.2845 (2.3500)  weight_decay: 0.0500 (0.0500)  time: 0.4323  data: 0.0001  max mem: 42573
Epoch: [178] Total time: 0:02:27 (0.4732 s / it)
Averaged stats: lr: 0.001578  min_lr: 0.001578  loss: 2.2845 (2.3710)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:00:44  loss: 0.7471 (0.7471)  acc1: 82.8125 (82.8125)  acc5: 93.2292 (93.2292)  time: 4.9563  data: 4.8469  max mem: 42573
Test:  [8/9]  eta: 0:00:00  loss: 1.0973 (1.0725)  acc1: 72.1354 (73.3120)  acc5: 93.2292 (91.9360)  time: 0.6269  data: 0.5386  max mem: 42573
Test: Total time: 0:00:05 (0.6389 s / it)
* Acc@1 74.088 Acc@5 91.844 loss 1.045
Accuracy of the model on the 50000 test images: 74.1%
Max accuracy: 74.63%
Epoch: [179]  [  0/312]  eta: 0:48:08  lr: 0.001577  min_lr: 0.001577  loss: 2.4057 (2.4057)  weight_decay: 0.0500 (0.0500)  time: 9.2570  data: 6.8793  max mem: 42573
Epoch: [179]  [ 10/312]  eta: 0:07:10  lr: 0.001577  min_lr: 0.001577  loss: 2.4585 (2.4136)  weight_decay: 0.0500 (0.0500)  time: 1.4250  data: 0.6566  max mem: 42573
Epoch: [179]  [ 20/312]  eta: 0:04:38  lr: 0.001576  min_lr: 0.001576  loss: 2.2047 (2.3079)  weight_decay: 0.0500 (0.0500)  time: 0.5375  data: 0.0173  max mem: 42573
Epoch: [179]  [ 30/312]  eta: 0:03:41  lr: 0.001575  min_lr: 0.001575  loss: 2.2777 (2.3671)  weight_decay: 0.0500 (0.0500)  time: 0.4332  data: 0.0003  max mem: 42573
Epoch: [179]  [ 40/312]  eta: 0:03:10  lr: 0.001575  min_lr: 0.001575  loss: 2.3116 (2.3074)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [179]  [ 50/312]  eta: 0:02:49  lr: 0.001574  min_lr: 0.001574  loss: 2.2226 (2.3306)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [179]  [ 60/312]  eta: 0:02:34  lr: 0.001573  min_lr: 0.001573  loss: 2.5058 (2.3377)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [179]  [ 70/312]  eta: 0:02:22  lr: 0.001573  min_lr: 0.001573  loss: 2.2100 (2.3311)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [179]  [ 80/312]  eta: 0:02:11  lr: 0.001572  min_lr: 0.001572  loss: 2.2588 (2.3449)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [179]  [ 90/312]  eta: 0:02:02  lr: 0.001571  min_lr: 0.001571  loss: 2.4372 (2.3444)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [179]  [100/312]  eta: 0:01:54  lr: 0.001570  min_lr: 0.001570  loss: 2.3756 (2.3490)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [179]  [110/312]  eta: 0:01:47  lr: 0.001570  min_lr: 0.001570  loss: 2.4907 (2.3622)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [179]  [120/312]  eta: 0:01:40  lr: 0.001569  min_lr: 0.001569  loss: 2.5279 (2.3664)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [179]  [130/312]  eta: 0:01:34  lr: 0.001568  min_lr: 0.001568  loss: 2.4703 (2.3644)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [179]  [140/312]  eta: 0:01:27  lr: 0.001568  min_lr: 0.001568  loss: 2.4652 (2.3651)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [179]  [150/312]  eta: 0:01:21  lr: 0.001567  min_lr: 0.001567  loss: 2.5339 (2.3805)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0005  max mem: 42573
Epoch: [179]  [160/312]  eta: 0:01:16  lr: 0.001566  min_lr: 0.001566  loss: 2.4441 (2.3709)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [179]  [170/312]  eta: 0:01:10  lr: 0.001566  min_lr: 0.001566  loss: 2.2515 (2.3732)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [179]  [180/312]  eta: 0:01:05  lr: 0.001565  min_lr: 0.001565  loss: 2.2615 (2.3664)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [179]  [190/312]  eta: 0:00:59  lr: 0.001564  min_lr: 0.001564  loss: 2.4070 (2.3760)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [179]  [200/312]  eta: 0:00:54  lr: 0.001563  min_lr: 0.001563  loss: 2.5953 (2.3833)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [179]  [210/312]  eta: 0:00:49  lr: 0.001563  min_lr: 0.001563  loss: 2.5433 (2.3814)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [179]  [220/312]  eta: 0:00:44  lr: 0.001562  min_lr: 0.001562  loss: 2.5527 (2.3856)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [179]  [230/312]  eta: 0:00:39  lr: 0.001561  min_lr: 0.001561  loss: 2.5110 (2.3875)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [179]  [240/312]  eta: 0:00:34  lr: 0.001561  min_lr: 0.001561  loss: 2.4546 (2.3856)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [179]  [250/312]  eta: 0:00:29  lr: 0.001560  min_lr: 0.001560  loss: 2.5156 (2.3857)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [179]  [260/312]  eta: 0:00:24  lr: 0.001559  min_lr: 0.001559  loss: 2.5821 (2.3953)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [179]  [270/312]  eta: 0:00:19  lr: 0.001559  min_lr: 0.001559  loss: 2.5825 (2.3981)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [179]  [280/312]  eta: 0:00:15  lr: 0.001558  min_lr: 0.001558  loss: 2.4348 (2.3885)  weight_decay: 0.0500 (0.0500)  time: 0.4347  data: 0.0009  max mem: 42573
Epoch: [179]  [290/312]  eta: 0:00:10  lr: 0.001557  min_lr: 0.001557  loss: 2.4948 (2.3943)  weight_decay: 0.0500 (0.0500)  time: 0.4341  data: 0.0008  max mem: 42573
Epoch: [179]  [300/312]  eta: 0:00:05  lr: 0.001556  min_lr: 0.001556  loss: 2.5394 (2.3970)  weight_decay: 0.0500 (0.0500)  time: 0.4324  data: 0.0001  max mem: 42573
Epoch: [179]  [310/312]  eta: 0:00:00  lr: 0.001556  min_lr: 0.001556  loss: 2.5084 (2.3969)  weight_decay: 0.0500 (0.0500)  time: 0.4323  data: 0.0001  max mem: 42573
Epoch: [179]  [311/312]  eta: 0:00:00  lr: 0.001556  min_lr: 0.001556  loss: 2.5461 (2.3985)  weight_decay: 0.0500 (0.0500)  time: 0.4323  data: 0.0001  max mem: 42573
Epoch: [179] Total time: 0:02:27 (0.4716 s / it)
Averaged stats: lr: 0.001556  min_lr: 0.001556  loss: 2.5461 (2.3809)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:00:43  loss: 0.7655 (0.7655)  acc1: 80.9896 (80.9896)  acc5: 94.7917 (94.7917)  time: 4.8397  data: 4.7302  max mem: 42573
Test:  [8/9]  eta: 0:00:00  loss: 1.1285 (1.0328)  acc1: 73.1771 (73.3120)  acc5: 91.4062 (92.0640)  time: 0.6132  data: 0.5257  max mem: 42573
Test: Total time: 0:00:05 (0.6313 s / it)
* Acc@1 74.246 Acc@5 91.854 loss 1.030
Accuracy of the model on the 50000 test images: 74.2%
Max accuracy: 74.63%
Epoch: [180]  [  0/312]  eta: 0:49:33  lr: 0.001556  min_lr: 0.001556  loss: 2.5715 (2.5715)  weight_decay: 0.0500 (0.0500)  time: 9.5302  data: 8.1596  max mem: 42573
Epoch: [180]  [ 10/312]  eta: 0:07:18  lr: 0.001555  min_lr: 0.001555  loss: 2.3617 (2.2176)  weight_decay: 0.0500 (0.0500)  time: 1.4523  data: 0.7421  max mem: 42573
Epoch: [180]  [ 20/312]  eta: 0:04:42  lr: 0.001554  min_lr: 0.001554  loss: 2.3617 (2.3299)  weight_decay: 0.0500 (0.0500)  time: 0.5389  data: 0.0004  max mem: 42573
Epoch: [180]  [ 30/312]  eta: 0:03:44  lr: 0.001553  min_lr: 0.001553  loss: 2.5221 (2.3888)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [180]  [ 40/312]  eta: 0:03:12  lr: 0.001553  min_lr: 0.001553  loss: 2.4041 (2.3325)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [180]  [ 50/312]  eta: 0:02:51  lr: 0.001552  min_lr: 0.001552  loss: 2.3026 (2.3668)  weight_decay: 0.0500 (0.0500)  time: 0.4381  data: 0.0004  max mem: 42573
Epoch: [180]  [ 60/312]  eta: 0:02:35  lr: 0.001551  min_lr: 0.001551  loss: 2.4579 (2.3628)  weight_decay: 0.0500 (0.0500)  time: 0.4381  data: 0.0004  max mem: 42573
Epoch: [180]  [ 70/312]  eta: 0:02:23  lr: 0.001551  min_lr: 0.001551  loss: 2.4621 (2.3784)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [180]  [ 80/312]  eta: 0:02:12  lr: 0.001550  min_lr: 0.001550  loss: 2.4287 (2.3774)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [180]  [ 90/312]  eta: 0:02:03  lr: 0.001549  min_lr: 0.001549  loss: 2.4159 (2.3940)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [180]  [100/312]  eta: 0:01:55  lr: 0.001549  min_lr: 0.001549  loss: 2.5146 (2.3946)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [180]  [110/312]  eta: 0:01:48  lr: 0.001548  min_lr: 0.001548  loss: 2.2630 (2.3769)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [180]  [120/312]  eta: 0:01:41  lr: 0.001547  min_lr: 0.001547  loss: 2.1013 (2.3594)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0003  max mem: 42573
Epoch: [180]  [130/312]  eta: 0:01:34  lr: 0.001546  min_lr: 0.001546  loss: 2.2045 (2.3598)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [180]  [140/312]  eta: 0:01:28  lr: 0.001546  min_lr: 0.001546  loss: 2.3787 (2.3542)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [180]  [150/312]  eta: 0:01:22  lr: 0.001545  min_lr: 0.001545  loss: 2.4909 (2.3580)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [180]  [160/312]  eta: 0:01:16  lr: 0.001544  min_lr: 0.001544  loss: 2.5437 (2.3722)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [180]  [170/312]  eta: 0:01:10  lr: 0.001544  min_lr: 0.001544  loss: 2.4732 (2.3708)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [180]  [180/312]  eta: 0:01:05  lr: 0.001543  min_lr: 0.001543  loss: 2.3898 (2.3604)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [180]  [190/312]  eta: 0:01:00  lr: 0.001542  min_lr: 0.001542  loss: 2.2008 (2.3585)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0003  max mem: 42573
Epoch: [180]  [200/312]  eta: 0:00:54  lr: 0.001542  min_lr: 0.001542  loss: 2.4034 (2.3516)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [180]  [210/312]  eta: 0:00:49  lr: 0.001541  min_lr: 0.001541  loss: 2.4034 (2.3516)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [180]  [220/312]  eta: 0:00:44  lr: 0.001540  min_lr: 0.001540  loss: 2.4151 (2.3527)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [180]  [230/312]  eta: 0:00:39  lr: 0.001539  min_lr: 0.001539  loss: 2.4261 (2.3490)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [180]  [240/312]  eta: 0:00:34  lr: 0.001539  min_lr: 0.001539  loss: 2.4013 (2.3481)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0003  max mem: 42573
Epoch: [180]  [250/312]  eta: 0:00:29  lr: 0.001538  min_lr: 0.001538  loss: 2.4013 (2.3480)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0004  max mem: 42573
Epoch: [180]  [260/312]  eta: 0:00:24  lr: 0.001537  min_lr: 0.001537  loss: 2.1996 (2.3447)  weight_decay: 0.0500 (0.0500)  time: 0.4341  data: 0.0004  max mem: 42573
Epoch: [180]  [270/312]  eta: 0:00:19  lr: 0.001537  min_lr: 0.001537  loss: 2.1996 (2.3495)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [180]  [280/312]  eta: 0:00:15  lr: 0.001536  min_lr: 0.001536  loss: 2.4807 (2.3507)  weight_decay: 0.0500 (0.0500)  time: 0.4345  data: 0.0011  max mem: 42573
Epoch: [180]  [290/312]  eta: 0:00:10  lr: 0.001535  min_lr: 0.001535  loss: 2.1871 (2.3443)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0010  max mem: 42573
Epoch: [180]  [300/312]  eta: 0:00:05  lr: 0.001535  min_lr: 0.001535  loss: 2.1840 (2.3446)  weight_decay: 0.0500 (0.0500)  time: 0.4325  data: 0.0001  max mem: 42573
Epoch: [180]  [310/312]  eta: 0:00:00  lr: 0.001534  min_lr: 0.001534  loss: 2.3281 (2.3401)  weight_decay: 0.0500 (0.0500)  time: 0.4323  data: 0.0001  max mem: 42573
Epoch: [180]  [311/312]  eta: 0:00:00  lr: 0.001534  min_lr: 0.001534  loss: 2.3614 (2.3405)  weight_decay: 0.0500 (0.0500)  time: 0.4323  data: 0.0001  max mem: 42573
Epoch: [180] Total time: 0:02:27 (0.4728 s / it)
Averaged stats: lr: 0.001534  min_lr: 0.001534  loss: 2.3614 (2.3507)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:00:41  loss: 0.7315 (0.7315)  acc1: 81.7708 (81.7708)  acc5: 94.2708 (94.2708)  time: 4.6541  data: 4.5446  max mem: 42573
Test:  [8/9]  eta: 0:00:00  loss: 1.1704 (1.0667)  acc1: 72.3958 (73.0880)  acc5: 90.3646 (90.9120)  time: 0.5935  data: 0.5050  max mem: 42573
Test: Total time: 0:00:05 (0.6137 s / it)
* Acc@1 73.968 Acc@5 91.524 loss 1.051
Accuracy of the model on the 50000 test images: 74.0%
Max accuracy: 74.63%
Epoch: [181]  [  0/312]  eta: 0:50:35  lr: 0.001534  min_lr: 0.001534  loss: 2.7202 (2.7202)  weight_decay: 0.0500 (0.0500)  time: 9.7301  data: 7.1259  max mem: 42573
Epoch: [181]  [ 10/312]  eta: 0:07:38  lr: 0.001533  min_lr: 0.001533  loss: 2.5543 (2.3757)  weight_decay: 0.0500 (0.0500)  time: 1.5172  data: 0.6953  max mem: 42573
Epoch: [181]  [ 20/312]  eta: 0:04:52  lr: 0.001532  min_lr: 0.001532  loss: 2.4419 (2.4376)  weight_decay: 0.0500 (0.0500)  time: 0.5646  data: 0.0263  max mem: 42573
Epoch: [181]  [ 30/312]  eta: 0:03:50  lr: 0.001532  min_lr: 0.001532  loss: 2.3944 (2.3978)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [181]  [ 40/312]  eta: 0:03:16  lr: 0.001531  min_lr: 0.001531  loss: 2.4407 (2.3905)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [181]  [ 50/312]  eta: 0:02:54  lr: 0.001530  min_lr: 0.001530  loss: 2.5514 (2.4139)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [181]  [ 60/312]  eta: 0:02:38  lr: 0.001530  min_lr: 0.001530  loss: 2.3815 (2.3615)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [181]  [ 70/312]  eta: 0:02:25  lr: 0.001529  min_lr: 0.001529  loss: 2.3520 (2.3711)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [181]  [ 80/312]  eta: 0:02:14  lr: 0.001528  min_lr: 0.001528  loss: 2.4872 (2.3832)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [181]  [ 90/312]  eta: 0:02:05  lr: 0.001527  min_lr: 0.001527  loss: 2.5174 (2.3842)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [181]  [100/312]  eta: 0:01:56  lr: 0.001527  min_lr: 0.001527  loss: 2.4560 (2.3825)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0003  max mem: 42573
Epoch: [181]  [110/312]  eta: 0:01:49  lr: 0.001526  min_lr: 0.001526  loss: 2.4560 (2.3941)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0004  max mem: 42573
Epoch: [181]  [120/312]  eta: 0:01:42  lr: 0.001525  min_lr: 0.001525  loss: 2.5074 (2.3897)  weight_decay: 0.0500 (0.0500)  time: 0.4384  data: 0.0004  max mem: 42573
Epoch: [181]  [130/312]  eta: 0:01:35  lr: 0.001525  min_lr: 0.001525  loss: 2.5445 (2.4118)  weight_decay: 0.0500 (0.0500)  time: 0.4383  data: 0.0004  max mem: 42573
Epoch: [181]  [140/312]  eta: 0:01:29  lr: 0.001524  min_lr: 0.001524  loss: 2.5557 (2.4054)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0003  max mem: 42573
Epoch: [181]  [150/312]  eta: 0:01:23  lr: 0.001523  min_lr: 0.001523  loss: 2.5103 (2.4088)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0003  max mem: 42573
Epoch: [181]  [160/312]  eta: 0:01:17  lr: 0.001523  min_lr: 0.001523  loss: 2.4225 (2.4053)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [181]  [170/312]  eta: 0:01:11  lr: 0.001522  min_lr: 0.001522  loss: 2.4225 (2.4074)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [181]  [180/312]  eta: 0:01:06  lr: 0.001521  min_lr: 0.001521  loss: 2.2203 (2.3920)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [181]  [190/312]  eta: 0:01:00  lr: 0.001520  min_lr: 0.001520  loss: 2.3630 (2.3959)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [181]  [200/312]  eta: 0:00:55  lr: 0.001520  min_lr: 0.001520  loss: 2.4327 (2.3982)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [181]  [210/312]  eta: 0:00:50  lr: 0.001519  min_lr: 0.001519  loss: 2.4033 (2.4019)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0003  max mem: 42573
Epoch: [181]  [220/312]  eta: 0:00:44  lr: 0.001518  min_lr: 0.001518  loss: 2.3920 (2.3993)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [181]  [230/312]  eta: 0:00:39  lr: 0.001518  min_lr: 0.001518  loss: 2.3414 (2.3907)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [181]  [240/312]  eta: 0:00:34  lr: 0.001517  min_lr: 0.001517  loss: 2.2249 (2.3923)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [181]  [250/312]  eta: 0:00:29  lr: 0.001516  min_lr: 0.001516  loss: 2.2249 (2.3872)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [181]  [260/312]  eta: 0:00:24  lr: 0.001516  min_lr: 0.001516  loss: 2.3853 (2.3886)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [181]  [270/312]  eta: 0:00:20  lr: 0.001515  min_lr: 0.001515  loss: 2.3011 (2.3839)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [181]  [280/312]  eta: 0:00:15  lr: 0.001514  min_lr: 0.001514  loss: 2.1792 (2.3770)  weight_decay: 0.0500 (0.0500)  time: 0.4344  data: 0.0009  max mem: 42573
Epoch: [181]  [290/312]  eta: 0:00:10  lr: 0.001513  min_lr: 0.001513  loss: 2.2732 (2.3765)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0008  max mem: 42573
Epoch: [181]  [300/312]  eta: 0:00:05  lr: 0.001513  min_lr: 0.001513  loss: 2.3121 (2.3702)  weight_decay: 0.0500 (0.0500)  time: 0.4325  data: 0.0001  max mem: 42573
Epoch: [181]  [310/312]  eta: 0:00:00  lr: 0.001512  min_lr: 0.001512  loss: 2.2124 (2.3686)  weight_decay: 0.0500 (0.0500)  time: 0.4324  data: 0.0001  max mem: 42573
Epoch: [181]  [311/312]  eta: 0:00:00  lr: 0.001512  min_lr: 0.001512  loss: 2.2124 (2.3668)  weight_decay: 0.0500 (0.0500)  time: 0.4323  data: 0.0001  max mem: 42573
Epoch: [181] Total time: 0:02:28 (0.4749 s / it)
Averaged stats: lr: 0.001512  min_lr: 0.001512  loss: 2.2124 (2.3576)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:00:41  loss: 0.7727 (0.7727)  acc1: 83.0729 (83.0729)  acc5: 95.0521 (95.0521)  time: 4.5918  data: 4.4822  max mem: 42573
Test:  [8/9]  eta: 0:00:00  loss: 1.0402 (0.9849)  acc1: 75.0000 (75.1360)  acc5: 92.7083 (92.5760)  time: 0.5858  data: 0.4981  max mem: 42573
Test: Total time: 0:00:05 (0.6025 s / it)
* Acc@1 75.216 Acc@5 92.394 loss 0.987
Accuracy of the model on the 50000 test images: 75.2%
Max accuracy: 75.22%
Epoch: [182]  [  0/312]  eta: 0:49:10  lr: 0.001512  min_lr: 0.001512  loss: 2.4665 (2.4665)  weight_decay: 0.0500 (0.0500)  time: 9.4565  data: 8.2565  max mem: 42573
Epoch: [182]  [ 10/312]  eta: 0:07:17  lr: 0.001511  min_lr: 0.001511  loss: 2.4451 (2.3706)  weight_decay: 0.0500 (0.0500)  time: 1.4488  data: 0.7510  max mem: 42573
Epoch: [182]  [ 20/312]  eta: 0:04:41  lr: 0.001511  min_lr: 0.001511  loss: 2.3245 (2.3318)  weight_decay: 0.0500 (0.0500)  time: 0.5406  data: 0.0004  max mem: 42573
Epoch: [182]  [ 30/312]  eta: 0:03:43  lr: 0.001510  min_lr: 0.001510  loss: 2.4716 (2.4064)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [182]  [ 40/312]  eta: 0:03:11  lr: 0.001509  min_lr: 0.001509  loss: 2.5173 (2.3835)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [182]  [ 50/312]  eta: 0:02:50  lr: 0.001508  min_lr: 0.001508  loss: 2.3442 (2.3441)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [182]  [ 60/312]  eta: 0:02:35  lr: 0.001508  min_lr: 0.001508  loss: 2.3926 (2.3661)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [182]  [ 70/312]  eta: 0:02:22  lr: 0.001507  min_lr: 0.001507  loss: 2.3985 (2.3509)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [182]  [ 80/312]  eta: 0:02:12  lr: 0.001506  min_lr: 0.001506  loss: 2.5170 (2.3799)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [182]  [ 90/312]  eta: 0:02:03  lr: 0.001506  min_lr: 0.001506  loss: 2.5267 (2.4033)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [182]  [100/312]  eta: 0:01:55  lr: 0.001505  min_lr: 0.001505  loss: 2.3981 (2.3773)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [182]  [110/312]  eta: 0:01:47  lr: 0.001504  min_lr: 0.001504  loss: 2.3189 (2.3829)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [182]  [120/312]  eta: 0:01:40  lr: 0.001504  min_lr: 0.001504  loss: 2.5545 (2.3882)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [182]  [130/312]  eta: 0:01:34  lr: 0.001503  min_lr: 0.001503  loss: 2.4564 (2.3812)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [182]  [140/312]  eta: 0:01:28  lr: 0.001502  min_lr: 0.001502  loss: 2.3514 (2.3854)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [182]  [150/312]  eta: 0:01:22  lr: 0.001501  min_lr: 0.001501  loss: 2.3514 (2.3910)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [182]  [160/312]  eta: 0:01:16  lr: 0.001501  min_lr: 0.001501  loss: 2.7246 (2.4115)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [182]  [170/312]  eta: 0:01:10  lr: 0.001500  min_lr: 0.001500  loss: 2.6281 (2.4168)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [182]  [180/312]  eta: 0:01:05  lr: 0.001499  min_lr: 0.001499  loss: 2.4784 (2.4173)  weight_decay: 0.0500 (0.0500)  time: 0.4385  data: 0.0004  max mem: 42573
Epoch: [182]  [190/312]  eta: 0:01:00  lr: 0.001499  min_lr: 0.001499  loss: 2.3280 (2.4049)  weight_decay: 0.0500 (0.0500)  time: 0.4385  data: 0.0004  max mem: 42573
Epoch: [182]  [200/312]  eta: 0:00:54  lr: 0.001498  min_lr: 0.001498  loss: 2.3439 (2.4099)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [182]  [210/312]  eta: 0:00:49  lr: 0.001497  min_lr: 0.001497  loss: 2.4887 (2.4075)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [182]  [220/312]  eta: 0:00:44  lr: 0.001497  min_lr: 0.001497  loss: 2.4887 (2.4137)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [182]  [230/312]  eta: 0:00:39  lr: 0.001496  min_lr: 0.001496  loss: 2.5298 (2.4156)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [182]  [240/312]  eta: 0:00:34  lr: 0.001495  min_lr: 0.001495  loss: 2.4007 (2.4165)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [182]  [250/312]  eta: 0:00:29  lr: 0.001495  min_lr: 0.001495  loss: 2.4007 (2.4132)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [182]  [260/312]  eta: 0:00:24  lr: 0.001494  min_lr: 0.001494  loss: 2.4863 (2.4153)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [182]  [270/312]  eta: 0:00:19  lr: 0.001493  min_lr: 0.001493  loss: 2.3586 (2.4110)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0003  max mem: 42573
Epoch: [182]  [280/312]  eta: 0:00:15  lr: 0.001492  min_lr: 0.001492  loss: 2.2238 (2.4052)  weight_decay: 0.0500 (0.0500)  time: 0.4349  data: 0.0009  max mem: 42573
Epoch: [182]  [290/312]  eta: 0:00:10  lr: 0.001492  min_lr: 0.001492  loss: 2.5099 (2.4072)  weight_decay: 0.0500 (0.0500)  time: 0.4342  data: 0.0008  max mem: 42573
Epoch: [182]  [300/312]  eta: 0:00:05  lr: 0.001491  min_lr: 0.001491  loss: 2.4862 (2.3995)  weight_decay: 0.0500 (0.0500)  time: 0.4324  data: 0.0001  max mem: 42573
Epoch: [182]  [310/312]  eta: 0:00:00  lr: 0.001490  min_lr: 0.001490  loss: 2.4365 (2.4011)  weight_decay: 0.0500 (0.0500)  time: 0.4325  data: 0.0001  max mem: 42573
Epoch: [182]  [311/312]  eta: 0:00:00  lr: 0.001490  min_lr: 0.001490  loss: 2.4365 (2.3985)  weight_decay: 0.0500 (0.0500)  time: 0.4325  data: 0.0001  max mem: 42573
Epoch: [182] Total time: 0:02:27 (0.4726 s / it)
Averaged stats: lr: 0.001490  min_lr: 0.001490  loss: 2.4365 (2.3592)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:00:42  loss: 0.7013 (0.7013)  acc1: 83.3333 (83.3333)  acc5: 94.7917 (94.7917)  time: 4.7428  data: 4.6332  max mem: 42573
Test:  [8/9]  eta: 0:00:00  loss: 1.0424 (0.9960)  acc1: 75.2604 (75.0080)  acc5: 92.7083 (92.1920)  time: 0.6038  data: 0.5149  max mem: 42573
Test: Total time: 0:00:05 (0.6248 s / it)
* Acc@1 75.082 Acc@5 92.366 loss 1.002
Accuracy of the model on the 50000 test images: 75.1%
Max accuracy: 75.22%
Epoch: [183]  [  0/312]  eta: 0:50:13  lr: 0.001490  min_lr: 0.001490  loss: 2.6952 (2.6952)  weight_decay: 0.0500 (0.0500)  time: 9.6596  data: 8.2573  max mem: 42573
Epoch: [183]  [ 10/312]  eta: 0:07:18  lr: 0.001490  min_lr: 0.001490  loss: 2.5734 (2.4523)  weight_decay: 0.0500 (0.0500)  time: 1.4529  data: 0.8086  max mem: 42573
Epoch: [183]  [ 20/312]  eta: 0:04:42  lr: 0.001489  min_lr: 0.001489  loss: 2.5167 (2.4248)  weight_decay: 0.0500 (0.0500)  time: 0.5325  data: 0.0320  max mem: 42573
Epoch: [183]  [ 30/312]  eta: 0:03:44  lr: 0.001488  min_lr: 0.001488  loss: 2.5167 (2.4033)  weight_decay: 0.0500 (0.0500)  time: 0.4330  data: 0.0003  max mem: 42573
Epoch: [183]  [ 40/312]  eta: 0:03:12  lr: 0.001487  min_lr: 0.001487  loss: 2.3990 (2.4057)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0003  max mem: 42573
Epoch: [183]  [ 50/312]  eta: 0:02:51  lr: 0.001487  min_lr: 0.001487  loss: 2.4872 (2.4023)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0003  max mem: 42573
Epoch: [183]  [ 60/312]  eta: 0:02:35  lr: 0.001486  min_lr: 0.001486  loss: 2.4381 (2.3700)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0003  max mem: 42573
Epoch: [183]  [ 70/312]  eta: 0:02:23  lr: 0.001485  min_lr: 0.001485  loss: 2.2524 (2.3639)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [183]  [ 80/312]  eta: 0:02:12  lr: 0.001485  min_lr: 0.001485  loss: 2.4629 (2.3740)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0003  max mem: 42573
Epoch: [183]  [ 90/312]  eta: 0:02:03  lr: 0.001484  min_lr: 0.001484  loss: 2.3759 (2.3711)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [183]  [100/312]  eta: 0:01:55  lr: 0.001483  min_lr: 0.001483  loss: 2.1987 (2.3482)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [183]  [110/312]  eta: 0:01:47  lr: 0.001483  min_lr: 0.001483  loss: 2.1987 (2.3438)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [183]  [120/312]  eta: 0:01:41  lr: 0.001482  min_lr: 0.001482  loss: 2.4592 (2.3458)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [183]  [130/312]  eta: 0:01:34  lr: 0.001481  min_lr: 0.001481  loss: 2.5785 (2.3543)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [183]  [140/312]  eta: 0:01:28  lr: 0.001480  min_lr: 0.001480  loss: 2.5995 (2.3581)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [183]  [150/312]  eta: 0:01:22  lr: 0.001480  min_lr: 0.001480  loss: 2.4729 (2.3598)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [183]  [160/312]  eta: 0:01:16  lr: 0.001479  min_lr: 0.001479  loss: 2.4700 (2.3567)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [183]  [170/312]  eta: 0:01:10  lr: 0.001478  min_lr: 0.001478  loss: 2.4243 (2.3571)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [183]  [180/312]  eta: 0:01:05  lr: 0.001478  min_lr: 0.001478  loss: 2.4254 (2.3630)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [183]  [190/312]  eta: 0:01:00  lr: 0.001477  min_lr: 0.001477  loss: 2.4254 (2.3619)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [183]  [200/312]  eta: 0:00:54  lr: 0.001476  min_lr: 0.001476  loss: 2.2857 (2.3626)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [183]  [210/312]  eta: 0:00:49  lr: 0.001476  min_lr: 0.001476  loss: 2.3890 (2.3665)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [183]  [220/312]  eta: 0:00:44  lr: 0.001475  min_lr: 0.001475  loss: 2.3838 (2.3647)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0005  max mem: 42573
Epoch: [183]  [230/312]  eta: 0:00:39  lr: 0.001474  min_lr: 0.001474  loss: 2.3248 (2.3602)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0005  max mem: 42573
Epoch: [183]  [240/312]  eta: 0:00:34  lr: 0.001474  min_lr: 0.001474  loss: 2.4126 (2.3581)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [183]  [250/312]  eta: 0:00:29  lr: 0.001473  min_lr: 0.001473  loss: 2.5112 (2.3582)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [183]  [260/312]  eta: 0:00:24  lr: 0.001472  min_lr: 0.001472  loss: 2.4177 (2.3599)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [183]  [270/312]  eta: 0:00:19  lr: 0.001471  min_lr: 0.001471  loss: 2.3773 (2.3578)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [183]  [280/312]  eta: 0:00:15  lr: 0.001471  min_lr: 0.001471  loss: 2.3360 (2.3589)  weight_decay: 0.0500 (0.0500)  time: 0.4342  data: 0.0010  max mem: 42573
Epoch: [183]  [290/312]  eta: 0:00:10  lr: 0.001470  min_lr: 0.001470  loss: 2.3406 (2.3563)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0008  max mem: 42573
Epoch: [183]  [300/312]  eta: 0:00:05  lr: 0.001469  min_lr: 0.001469  loss: 2.3357 (2.3563)  weight_decay: 0.0500 (0.0500)  time: 0.4323  data: 0.0001  max mem: 42573
Epoch: [183]  [310/312]  eta: 0:00:00  lr: 0.001469  min_lr: 0.001469  loss: 2.4038 (2.3591)  weight_decay: 0.0500 (0.0500)  time: 0.4323  data: 0.0001  max mem: 42573
Epoch: [183]  [311/312]  eta: 0:00:00  lr: 0.001469  min_lr: 0.001469  loss: 2.4038 (2.3579)  weight_decay: 0.0500 (0.0500)  time: 0.4323  data: 0.0001  max mem: 42573
Epoch: [183] Total time: 0:02:27 (0.4724 s / it)
Averaged stats: lr: 0.001469  min_lr: 0.001469  loss: 2.4038 (2.3649)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:00:40  loss: 0.8323 (0.8323)  acc1: 79.6875 (79.6875)  acc5: 93.4896 (93.4896)  time: 4.4611  data: 4.3523  max mem: 42573
Test:  [8/9]  eta: 0:00:00  loss: 1.0959 (1.0423)  acc1: 73.6979 (73.5360)  acc5: 91.9271 (91.7120)  time: 0.5956  data: 0.5082  max mem: 42573
Test: Total time: 0:00:05 (0.6039 s / it)
* Acc@1 74.698 Acc@5 92.134 loss 1.022
Accuracy of the model on the 50000 test images: 74.7%
Max accuracy: 75.22%
Epoch: [184]  [  0/312]  eta: 0:51:20  lr: 0.001469  min_lr: 0.001469  loss: 2.7978 (2.7978)  weight_decay: 0.0500 (0.0500)  time: 9.8735  data: 7.2849  max mem: 42573
Epoch: [184]  [ 10/312]  eta: 0:07:32  lr: 0.001468  min_lr: 0.001468  loss: 2.4204 (2.4082)  weight_decay: 0.0500 (0.0500)  time: 1.4974  data: 0.7103  max mem: 42573
Epoch: [184]  [ 20/312]  eta: 0:04:49  lr: 0.001467  min_lr: 0.001467  loss: 2.3338 (2.3036)  weight_decay: 0.0500 (0.0500)  time: 0.5464  data: 0.0266  max mem: 42573
Epoch: [184]  [ 30/312]  eta: 0:03:48  lr: 0.001466  min_lr: 0.001466  loss: 2.3338 (2.2801)  weight_decay: 0.0500 (0.0500)  time: 0.4332  data: 0.0004  max mem: 42573
Epoch: [184]  [ 40/312]  eta: 0:03:15  lr: 0.001466  min_lr: 0.001466  loss: 2.4438 (2.3415)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [184]  [ 50/312]  eta: 0:02:53  lr: 0.001465  min_lr: 0.001465  loss: 2.5413 (2.3623)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [184]  [ 60/312]  eta: 0:02:37  lr: 0.001464  min_lr: 0.001464  loss: 2.5771 (2.3964)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [184]  [ 70/312]  eta: 0:02:24  lr: 0.001464  min_lr: 0.001464  loss: 2.5413 (2.3838)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [184]  [ 80/312]  eta: 0:02:14  lr: 0.001463  min_lr: 0.001463  loss: 2.3229 (2.3803)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [184]  [ 90/312]  eta: 0:02:04  lr: 0.001462  min_lr: 0.001462  loss: 2.1873 (2.3445)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [184]  [100/312]  eta: 0:01:56  lr: 0.001462  min_lr: 0.001462  loss: 2.4103 (2.3565)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [184]  [110/312]  eta: 0:01:48  lr: 0.001461  min_lr: 0.001461  loss: 2.4103 (2.3424)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [184]  [120/312]  eta: 0:01:41  lr: 0.001460  min_lr: 0.001460  loss: 2.4243 (2.3603)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [184]  [130/312]  eta: 0:01:35  lr: 0.001460  min_lr: 0.001460  loss: 2.5161 (2.3656)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [184]  [140/312]  eta: 0:01:28  lr: 0.001459  min_lr: 0.001459  loss: 2.4438 (2.3679)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [184]  [150/312]  eta: 0:01:22  lr: 0.001458  min_lr: 0.001458  loss: 2.2150 (2.3541)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [184]  [160/312]  eta: 0:01:16  lr: 0.001457  min_lr: 0.001457  loss: 2.2748 (2.3597)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [184]  [170/312]  eta: 0:01:11  lr: 0.001457  min_lr: 0.001457  loss: 2.3832 (2.3532)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0003  max mem: 42573
Epoch: [184]  [180/312]  eta: 0:01:05  lr: 0.001456  min_lr: 0.001456  loss: 2.4629 (2.3525)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [184]  [190/312]  eta: 0:01:00  lr: 0.001455  min_lr: 0.001455  loss: 2.5343 (2.3550)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [184]  [200/312]  eta: 0:00:55  lr: 0.001455  min_lr: 0.001455  loss: 2.5114 (2.3587)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0003  max mem: 42573
Epoch: [184]  [210/312]  eta: 0:00:49  lr: 0.001454  min_lr: 0.001454  loss: 2.3123 (2.3570)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [184]  [220/312]  eta: 0:00:44  lr: 0.001453  min_lr: 0.001453  loss: 2.3056 (2.3474)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [184]  [230/312]  eta: 0:00:39  lr: 0.001453  min_lr: 0.001453  loss: 2.4696 (2.3532)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [184]  [240/312]  eta: 0:00:34  lr: 0.001452  min_lr: 0.001452  loss: 2.4696 (2.3460)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [184]  [250/312]  eta: 0:00:29  lr: 0.001451  min_lr: 0.001451  loss: 2.1712 (2.3430)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [184]  [260/312]  eta: 0:00:24  lr: 0.001451  min_lr: 0.001451  loss: 2.3782 (2.3404)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [184]  [270/312]  eta: 0:00:20  lr: 0.001450  min_lr: 0.001450  loss: 2.4063 (2.3476)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [184]  [280/312]  eta: 0:00:15  lr: 0.001449  min_lr: 0.001449  loss: 2.4601 (2.3533)  weight_decay: 0.0500 (0.0500)  time: 0.4347  data: 0.0009  max mem: 42573
Epoch: [184]  [290/312]  eta: 0:00:10  lr: 0.001448  min_lr: 0.001448  loss: 2.4565 (2.3473)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0008  max mem: 42573
Epoch: [184]  [300/312]  eta: 0:00:05  lr: 0.001448  min_lr: 0.001448  loss: 2.3151 (2.3452)  weight_decay: 0.0500 (0.0500)  time: 0.4323  data: 0.0001  max mem: 42573
Epoch: [184]  [310/312]  eta: 0:00:00  lr: 0.001447  min_lr: 0.001447  loss: 2.3890 (2.3440)  weight_decay: 0.0500 (0.0500)  time: 0.4322  data: 0.0001  max mem: 42573
Epoch: [184]  [311/312]  eta: 0:00:00  lr: 0.001447  min_lr: 0.001447  loss: 2.4242 (2.3452)  weight_decay: 0.0500 (0.0500)  time: 0.4322  data: 0.0001  max mem: 42573
Epoch: [184] Total time: 0:02:27 (0.4741 s / it)
Averaged stats: lr: 0.001447  min_lr: 0.001447  loss: 2.4242 (2.3476)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:00:38  loss: 0.7387 (0.7387)  acc1: 80.4688 (80.4688)  acc5: 95.0521 (95.0521)  time: 4.3288  data: 4.2201  max mem: 42573
Test:  [8/9]  eta: 0:00:00  loss: 1.0469 (1.0150)  acc1: 73.6979 (74.4320)  acc5: 92.4479 (91.9680)  time: 0.5581  data: 0.4690  max mem: 42573
Test: Total time: 0:00:05 (0.5693 s / it)
* Acc@1 74.464 Acc@5 91.818 loss 1.028
Accuracy of the model on the 50000 test images: 74.5%
Max accuracy: 75.22%
Epoch: [185]  [  0/312]  eta: 0:51:07  lr: 0.001447  min_lr: 0.001447  loss: 1.8848 (1.8848)  weight_decay: 0.0500 (0.0500)  time: 9.8331  data: 7.1719  max mem: 42573
Epoch: [185]  [ 10/312]  eta: 0:07:11  lr: 0.001446  min_lr: 0.001446  loss: 2.5938 (2.3950)  weight_decay: 0.0500 (0.0500)  time: 1.4292  data: 0.6524  max mem: 42573
Epoch: [185]  [ 20/312]  eta: 0:04:38  lr: 0.001446  min_lr: 0.001446  loss: 2.4540 (2.3210)  weight_decay: 0.0500 (0.0500)  time: 0.5110  data: 0.0004  max mem: 42573
Epoch: [185]  [ 30/312]  eta: 0:03:41  lr: 0.001445  min_lr: 0.001445  loss: 2.5675 (2.4148)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [185]  [ 40/312]  eta: 0:03:10  lr: 0.001444  min_lr: 0.001444  loss: 2.3706 (2.3184)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0003  max mem: 42573
Epoch: [185]  [ 50/312]  eta: 0:02:49  lr: 0.001444  min_lr: 0.001444  loss: 2.3507 (2.3477)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [185]  [ 60/312]  eta: 0:02:34  lr: 0.001443  min_lr: 0.001443  loss: 2.4771 (2.3584)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [185]  [ 70/312]  eta: 0:02:22  lr: 0.001442  min_lr: 0.001442  loss: 2.4113 (2.3653)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [185]  [ 80/312]  eta: 0:02:11  lr: 0.001441  min_lr: 0.001441  loss: 2.4113 (2.3429)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [185]  [ 90/312]  eta: 0:02:02  lr: 0.001441  min_lr: 0.001441  loss: 1.9770 (2.3239)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [185]  [100/312]  eta: 0:01:54  lr: 0.001440  min_lr: 0.001440  loss: 2.1462 (2.3226)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [185]  [110/312]  eta: 0:01:47  lr: 0.001439  min_lr: 0.001439  loss: 2.3491 (2.3301)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0004  max mem: 42573
Epoch: [185]  [120/312]  eta: 0:01:40  lr: 0.001439  min_lr: 0.001439  loss: 2.3532 (2.3288)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0005  max mem: 42573
Epoch: [185]  [130/312]  eta: 0:01:34  lr: 0.001438  min_lr: 0.001438  loss: 2.1425 (2.3129)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [185]  [140/312]  eta: 0:01:27  lr: 0.001437  min_lr: 0.001437  loss: 2.2692 (2.3044)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [185]  [150/312]  eta: 0:01:21  lr: 0.001437  min_lr: 0.001437  loss: 2.2884 (2.2971)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [185]  [160/312]  eta: 0:01:16  lr: 0.001436  min_lr: 0.001436  loss: 2.4409 (2.3021)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [185]  [170/312]  eta: 0:01:10  lr: 0.001435  min_lr: 0.001435  loss: 2.4193 (2.3017)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [185]  [180/312]  eta: 0:01:05  lr: 0.001435  min_lr: 0.001435  loss: 2.4193 (2.3085)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [185]  [190/312]  eta: 0:00:59  lr: 0.001434  min_lr: 0.001434  loss: 2.5331 (2.3126)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [185]  [200/312]  eta: 0:00:54  lr: 0.001433  min_lr: 0.001433  loss: 2.4490 (2.3024)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [185]  [210/312]  eta: 0:00:49  lr: 0.001432  min_lr: 0.001432  loss: 2.3708 (2.3103)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [185]  [220/312]  eta: 0:00:44  lr: 0.001432  min_lr: 0.001432  loss: 2.4981 (2.3168)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [185]  [230/312]  eta: 0:00:39  lr: 0.001431  min_lr: 0.001431  loss: 2.5737 (2.3300)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0003  max mem: 42573
Epoch: [185]  [240/312]  eta: 0:00:34  lr: 0.001430  min_lr: 0.001430  loss: 2.5207 (2.3286)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [185]  [250/312]  eta: 0:00:29  lr: 0.001430  min_lr: 0.001430  loss: 2.3953 (2.3306)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [185]  [260/312]  eta: 0:00:24  lr: 0.001429  min_lr: 0.001429  loss: 2.2763 (2.3257)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [185]  [270/312]  eta: 0:00:19  lr: 0.001428  min_lr: 0.001428  loss: 2.2301 (2.3256)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [185]  [280/312]  eta: 0:00:15  lr: 0.001428  min_lr: 0.001428  loss: 2.2301 (2.3253)  weight_decay: 0.0500 (0.0500)  time: 0.4344  data: 0.0009  max mem: 42573
Epoch: [185]  [290/312]  eta: 0:00:10  lr: 0.001427  min_lr: 0.001427  loss: 2.5092 (2.3306)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0008  max mem: 42573
Epoch: [185]  [300/312]  eta: 0:00:05  lr: 0.001426  min_lr: 0.001426  loss: 2.4646 (2.3248)  weight_decay: 0.0500 (0.0500)  time: 0.4324  data: 0.0001  max mem: 42573
Epoch: [185]  [310/312]  eta: 0:00:00  lr: 0.001426  min_lr: 0.001426  loss: 2.2512 (2.3239)  weight_decay: 0.0500 (0.0500)  time: 0.4323  data: 0.0001  max mem: 42573
Epoch: [185]  [311/312]  eta: 0:00:00  lr: 0.001426  min_lr: 0.001426  loss: 2.2512 (2.3254)  weight_decay: 0.0500 (0.0500)  time: 0.4323  data: 0.0001  max mem: 42573
Epoch: [185] Total time: 0:02:27 (0.4716 s / it)
Averaged stats: lr: 0.001426  min_lr: 0.001426  loss: 2.2512 (2.3499)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:00:42  loss: 0.7438 (0.7438)  acc1: 82.8125 (82.8125)  acc5: 94.5312 (94.5312)  time: 4.6864  data: 4.5769  max mem: 42573
Test:  [8/9]  eta: 0:00:00  loss: 1.0353 (0.9906)  acc1: 74.2188 (74.0800)  acc5: 92.1875 (91.9040)  time: 0.5969  data: 0.5086  max mem: 42573
Test: Total time: 0:00:05 (0.6181 s / it)
* Acc@1 75.236 Acc@5 92.316 loss 0.979
Accuracy of the model on the 50000 test images: 75.2%
Max accuracy: 75.24%
Epoch: [186]  [  0/312]  eta: 0:48:50  lr: 0.001425  min_lr: 0.001425  loss: 2.8193 (2.8193)  weight_decay: 0.0500 (0.0500)  time: 9.3917  data: 7.2317  max mem: 42573
Epoch: [186]  [ 10/312]  eta: 0:07:26  lr: 0.001425  min_lr: 0.001425  loss: 2.4290 (2.4313)  weight_decay: 0.0500 (0.0500)  time: 1.4781  data: 0.7152  max mem: 42573
Epoch: [186]  [ 20/312]  eta: 0:04:46  lr: 0.001424  min_lr: 0.001424  loss: 2.2877 (2.3242)  weight_decay: 0.0500 (0.0500)  time: 0.5601  data: 0.0320  max mem: 42573
Epoch: [186]  [ 30/312]  eta: 0:03:46  lr: 0.001423  min_lr: 0.001423  loss: 2.2339 (2.3370)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [186]  [ 40/312]  eta: 0:03:14  lr: 0.001423  min_lr: 0.001423  loss: 2.3085 (2.3413)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [186]  [ 50/312]  eta: 0:02:52  lr: 0.001422  min_lr: 0.001422  loss: 2.3786 (2.3284)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [186]  [ 60/312]  eta: 0:02:36  lr: 0.001421  min_lr: 0.001421  loss: 2.1349 (2.2911)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [186]  [ 70/312]  eta: 0:02:24  lr: 0.001421  min_lr: 0.001421  loss: 2.1628 (2.2977)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0005  max mem: 42573
Epoch: [186]  [ 80/312]  eta: 0:02:13  lr: 0.001420  min_lr: 0.001420  loss: 2.2805 (2.2844)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [186]  [ 90/312]  eta: 0:02:04  lr: 0.001419  min_lr: 0.001419  loss: 2.0947 (2.2788)  weight_decay: 0.0500 (0.0500)  time: 0.4379  data: 0.0004  max mem: 42573
Epoch: [186]  [100/312]  eta: 0:01:56  lr: 0.001419  min_lr: 0.001419  loss: 2.2536 (2.2774)  weight_decay: 0.0500 (0.0500)  time: 0.4380  data: 0.0004  max mem: 42573
Epoch: [186]  [110/312]  eta: 0:01:48  lr: 0.001418  min_lr: 0.001418  loss: 2.4693 (2.2935)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [186]  [120/312]  eta: 0:01:41  lr: 0.001417  min_lr: 0.001417  loss: 2.4838 (2.2983)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [186]  [130/312]  eta: 0:01:35  lr: 0.001416  min_lr: 0.001416  loss: 2.3166 (2.3046)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [186]  [140/312]  eta: 0:01:28  lr: 0.001416  min_lr: 0.001416  loss: 2.3756 (2.3034)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [186]  [150/312]  eta: 0:01:22  lr: 0.001415  min_lr: 0.001415  loss: 2.3183 (2.3075)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [186]  [160/312]  eta: 0:01:16  lr: 0.001414  min_lr: 0.001414  loss: 2.4459 (2.3074)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [186]  [170/312]  eta: 0:01:11  lr: 0.001414  min_lr: 0.001414  loss: 2.4459 (2.3124)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [186]  [180/312]  eta: 0:01:05  lr: 0.001413  min_lr: 0.001413  loss: 2.4926 (2.3275)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [186]  [190/312]  eta: 0:01:00  lr: 0.001412  min_lr: 0.001412  loss: 2.4926 (2.3304)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [186]  [200/312]  eta: 0:00:55  lr: 0.001412  min_lr: 0.001412  loss: 2.4207 (2.3402)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0003  max mem: 42573
Epoch: [186]  [210/312]  eta: 0:00:49  lr: 0.001411  min_lr: 0.001411  loss: 2.5036 (2.3491)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [186]  [220/312]  eta: 0:00:44  lr: 0.001410  min_lr: 0.001410  loss: 2.4788 (2.3517)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [186]  [230/312]  eta: 0:00:39  lr: 0.001410  min_lr: 0.001410  loss: 2.4788 (2.3578)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [186]  [240/312]  eta: 0:00:34  lr: 0.001409  min_lr: 0.001409  loss: 2.4780 (2.3551)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [186]  [250/312]  eta: 0:00:29  lr: 0.001408  min_lr: 0.001408  loss: 2.4850 (2.3555)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0003  max mem: 42573
Epoch: [186]  [260/312]  eta: 0:00:24  lr: 0.001408  min_lr: 0.001408  loss: 2.4729 (2.3542)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [186]  [270/312]  eta: 0:00:20  lr: 0.001407  min_lr: 0.001407  loss: 2.4050 (2.3559)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0003  max mem: 42573
Epoch: [186]  [280/312]  eta: 0:00:15  lr: 0.001406  min_lr: 0.001406  loss: 2.5066 (2.3612)  weight_decay: 0.0500 (0.0500)  time: 0.4349  data: 0.0010  max mem: 42573
Epoch: [186]  [290/312]  eta: 0:00:10  lr: 0.001406  min_lr: 0.001406  loss: 2.5499 (2.3632)  weight_decay: 0.0500 (0.0500)  time: 0.4341  data: 0.0009  max mem: 42573
Epoch: [186]  [300/312]  eta: 0:00:05  lr: 0.001405  min_lr: 0.001405  loss: 2.3499 (2.3571)  weight_decay: 0.0500 (0.0500)  time: 0.4322  data: 0.0001  max mem: 42573
Epoch: [186]  [310/312]  eta: 0:00:00  lr: 0.001404  min_lr: 0.001404  loss: 2.2307 (2.3533)  weight_decay: 0.0500 (0.0500)  time: 0.4323  data: 0.0001  max mem: 42573
Epoch: [186]  [311/312]  eta: 0:00:00  lr: 0.001404  min_lr: 0.001404  loss: 2.2307 (2.3544)  weight_decay: 0.0500 (0.0500)  time: 0.4323  data: 0.0001  max mem: 42573
Epoch: [186] Total time: 0:02:27 (0.4737 s / it)
Averaged stats: lr: 0.001404  min_lr: 0.001404  loss: 2.2307 (2.3386)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:00:42  loss: 0.7155 (0.7155)  acc1: 81.7708 (81.7708)  acc5: 95.3125 (95.3125)  time: 4.7170  data: 4.6087  max mem: 42573
Test:  [8/9]  eta: 0:00:00  loss: 1.0955 (0.9967)  acc1: 74.4792 (74.3680)  acc5: 92.7083 (92.9280)  time: 0.6005  data: 0.5121  max mem: 42573
Test: Total time: 0:00:05 (0.6251 s / it)
* Acc@1 75.260 Acc@5 92.534 loss 1.003
Accuracy of the model on the 50000 test images: 75.3%
Max accuracy: 75.26%
Epoch: [187]  [  0/312]  eta: 0:48:49  lr: 0.001404  min_lr: 0.001404  loss: 1.8561 (1.8561)  weight_decay: 0.0500 (0.0500)  time: 9.3905  data: 8.1873  max mem: 42573
Epoch: [187]  [ 10/312]  eta: 0:06:54  lr: 0.001403  min_lr: 0.001403  loss: 2.4667 (2.4080)  weight_decay: 0.0500 (0.0500)  time: 1.3717  data: 0.7447  max mem: 42573
Epoch: [187]  [ 20/312]  eta: 0:04:30  lr: 0.001403  min_lr: 0.001403  loss: 2.3802 (2.2896)  weight_decay: 0.0500 (0.0500)  time: 0.5017  data: 0.0004  max mem: 42573
Epoch: [187]  [ 30/312]  eta: 0:03:36  lr: 0.001402  min_lr: 0.001402  loss: 2.3863 (2.3357)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [187]  [ 40/312]  eta: 0:03:06  lr: 0.001401  min_lr: 0.001401  loss: 2.4161 (2.3222)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [187]  [ 50/312]  eta: 0:02:46  lr: 0.001401  min_lr: 0.001401  loss: 2.4161 (2.3462)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [187]  [ 60/312]  eta: 0:02:31  lr: 0.001400  min_lr: 0.001400  loss: 2.3393 (2.3315)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [187]  [ 70/312]  eta: 0:02:20  lr: 0.001399  min_lr: 0.001399  loss: 2.4902 (2.3550)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0004  max mem: 42573
Epoch: [187]  [ 80/312]  eta: 0:02:10  lr: 0.001399  min_lr: 0.001399  loss: 2.5384 (2.3660)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0004  max mem: 42573
Epoch: [187]  [ 90/312]  eta: 0:02:01  lr: 0.001398  min_lr: 0.001398  loss: 2.3793 (2.3563)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [187]  [100/312]  eta: 0:01:53  lr: 0.001397  min_lr: 0.001397  loss: 2.3613 (2.3485)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [187]  [110/312]  eta: 0:01:46  lr: 0.001396  min_lr: 0.001396  loss: 2.1479 (2.3332)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [187]  [120/312]  eta: 0:01:39  lr: 0.001396  min_lr: 0.001396  loss: 2.3225 (2.3218)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [187]  [130/312]  eta: 0:01:33  lr: 0.001395  min_lr: 0.001395  loss: 2.5085 (2.3346)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [187]  [140/312]  eta: 0:01:27  lr: 0.001394  min_lr: 0.001394  loss: 2.3751 (2.3220)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [187]  [150/312]  eta: 0:01:21  lr: 0.001394  min_lr: 0.001394  loss: 2.1573 (2.3093)  weight_decay: 0.0500 (0.0500)  time: 0.4389  data: 0.0004  max mem: 42573
Epoch: [187]  [160/312]  eta: 0:01:15  lr: 0.001393  min_lr: 0.001393  loss: 1.9014 (2.2922)  weight_decay: 0.0500 (0.0500)  time: 0.4391  data: 0.0004  max mem: 42573
Epoch: [187]  [170/312]  eta: 0:01:10  lr: 0.001392  min_lr: 0.001392  loss: 2.3649 (2.3003)  weight_decay: 0.0500 (0.0500)  time: 0.4341  data: 0.0004  max mem: 42573
Epoch: [187]  [180/312]  eta: 0:01:04  lr: 0.001392  min_lr: 0.001392  loss: 2.4813 (2.2970)  weight_decay: 0.0500 (0.0500)  time: 0.4341  data: 0.0004  max mem: 42573
Epoch: [187]  [190/312]  eta: 0:00:59  lr: 0.001391  min_lr: 0.001391  loss: 2.4203 (2.2966)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [187]  [200/312]  eta: 0:00:54  lr: 0.001390  min_lr: 0.001390  loss: 2.3434 (2.2978)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [187]  [210/312]  eta: 0:00:49  lr: 0.001390  min_lr: 0.001390  loss: 2.2994 (2.2945)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [187]  [220/312]  eta: 0:00:44  lr: 0.001389  min_lr: 0.001389  loss: 2.3572 (2.2960)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [187]  [230/312]  eta: 0:00:39  lr: 0.001388  min_lr: 0.001388  loss: 2.5177 (2.3041)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [187]  [240/312]  eta: 0:00:34  lr: 0.001388  min_lr: 0.001388  loss: 2.5681 (2.3063)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [187]  [250/312]  eta: 0:00:29  lr: 0.001387  min_lr: 0.001387  loss: 2.4579 (2.3092)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [187]  [260/312]  eta: 0:00:24  lr: 0.001386  min_lr: 0.001386  loss: 2.4724 (2.3089)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [187]  [270/312]  eta: 0:00:19  lr: 0.001385  min_lr: 0.001385  loss: 2.2784 (2.3065)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0004  max mem: 42573
Epoch: [187]  [280/312]  eta: 0:00:15  lr: 0.001385  min_lr: 0.001385  loss: 2.1826 (2.3022)  weight_decay: 0.0500 (0.0500)  time: 0.4348  data: 0.0010  max mem: 42573
Epoch: [187]  [290/312]  eta: 0:00:10  lr: 0.001384  min_lr: 0.001384  loss: 2.2176 (2.3051)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0008  max mem: 42573
Epoch: [187]  [300/312]  eta: 0:00:05  lr: 0.001383  min_lr: 0.001383  loss: 2.2176 (2.3047)  weight_decay: 0.0500 (0.0500)  time: 0.4324  data: 0.0001  max mem: 42573
Epoch: [187]  [310/312]  eta: 0:00:00  lr: 0.001383  min_lr: 0.001383  loss: 2.2484 (2.3049)  weight_decay: 0.0500 (0.0500)  time: 0.4323  data: 0.0001  max mem: 42573
Epoch: [187]  [311/312]  eta: 0:00:00  lr: 0.001383  min_lr: 0.001383  loss: 2.2484 (2.3060)  weight_decay: 0.0500 (0.0500)  time: 0.4323  data: 0.0001  max mem: 42573
Epoch: [187] Total time: 0:02:26 (0.4701 s / it)
Averaged stats: lr: 0.001383  min_lr: 0.001383  loss: 2.2484 (2.3367)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:00:43  loss: 0.7262 (0.7262)  acc1: 80.4688 (80.4688)  acc5: 94.2708 (94.2708)  time: 4.7889  data: 4.6796  max mem: 42573
Test:  [8/9]  eta: 0:00:00  loss: 1.0743 (0.9758)  acc1: 75.5208 (75.0080)  acc5: 92.7083 (92.3520)  time: 0.6099  data: 0.5200  max mem: 42573
Test: Total time: 0:00:05 (0.6341 s / it)
* Acc@1 75.360 Acc@5 92.688 loss 0.963
Accuracy of the model on the 50000 test images: 75.4%
Max accuracy: 75.36%
Epoch: [188]  [  0/312]  eta: 0:48:23  lr: 0.001383  min_lr: 0.001383  loss: 2.8773 (2.8773)  weight_decay: 0.0500 (0.0500)  time: 9.3064  data: 6.4052  max mem: 42573
Epoch: [188]  [ 10/312]  eta: 0:07:09  lr: 0.001382  min_lr: 0.001382  loss: 2.4024 (2.4912)  weight_decay: 0.0500 (0.0500)  time: 1.4229  data: 0.6776  max mem: 42573
Epoch: [188]  [ 20/312]  eta: 0:04:37  lr: 0.001381  min_lr: 0.001381  loss: 2.4862 (2.5155)  weight_decay: 0.0500 (0.0500)  time: 0.5341  data: 0.0526  max mem: 42573
Epoch: [188]  [ 30/312]  eta: 0:03:41  lr: 0.001381  min_lr: 0.001381  loss: 2.4896 (2.4858)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [188]  [ 40/312]  eta: 0:03:10  lr: 0.001380  min_lr: 0.001380  loss: 2.4049 (2.4670)  weight_decay: 0.0500 (0.0500)  time: 0.4332  data: 0.0004  max mem: 42573
Epoch: [188]  [ 50/312]  eta: 0:02:49  lr: 0.001379  min_lr: 0.001379  loss: 2.3554 (2.4329)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [188]  [ 60/312]  eta: 0:02:34  lr: 0.001379  min_lr: 0.001379  loss: 2.1599 (2.4054)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [188]  [ 70/312]  eta: 0:02:21  lr: 0.001378  min_lr: 0.001378  loss: 2.4554 (2.4251)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [188]  [ 80/312]  eta: 0:02:11  lr: 0.001377  min_lr: 0.001377  loss: 2.5472 (2.4281)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [188]  [ 90/312]  eta: 0:02:02  lr: 0.001376  min_lr: 0.001376  loss: 2.2278 (2.3949)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [188]  [100/312]  eta: 0:01:54  lr: 0.001376  min_lr: 0.001376  loss: 2.2278 (2.4080)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0005  max mem: 42573
Epoch: [188]  [110/312]  eta: 0:01:47  lr: 0.001375  min_lr: 0.001375  loss: 2.4494 (2.3983)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0005  max mem: 42573
Epoch: [188]  [120/312]  eta: 0:01:40  lr: 0.001374  min_lr: 0.001374  loss: 2.0053 (2.3591)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [188]  [130/312]  eta: 0:01:34  lr: 0.001374  min_lr: 0.001374  loss: 2.1051 (2.3578)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [188]  [140/312]  eta: 0:01:27  lr: 0.001373  min_lr: 0.001373  loss: 2.3306 (2.3509)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [188]  [150/312]  eta: 0:01:21  lr: 0.001372  min_lr: 0.001372  loss: 2.3119 (2.3459)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [188]  [160/312]  eta: 0:01:16  lr: 0.001372  min_lr: 0.001372  loss: 2.4393 (2.3458)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [188]  [170/312]  eta: 0:01:10  lr: 0.001371  min_lr: 0.001371  loss: 2.5048 (2.3572)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [188]  [180/312]  eta: 0:01:05  lr: 0.001370  min_lr: 0.001370  loss: 2.4181 (2.3486)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [188]  [190/312]  eta: 0:00:59  lr: 0.001370  min_lr: 0.001370  loss: 2.2139 (2.3452)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [188]  [200/312]  eta: 0:00:54  lr: 0.001369  min_lr: 0.001369  loss: 2.3727 (2.3461)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [188]  [210/312]  eta: 0:00:49  lr: 0.001368  min_lr: 0.001368  loss: 2.4434 (2.3452)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [188]  [220/312]  eta: 0:00:44  lr: 0.001368  min_lr: 0.001368  loss: 2.3899 (2.3396)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [188]  [230/312]  eta: 0:00:39  lr: 0.001367  min_lr: 0.001367  loss: 2.3923 (2.3396)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [188]  [240/312]  eta: 0:00:34  lr: 0.001366  min_lr: 0.001366  loss: 2.5076 (2.3427)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [188]  [250/312]  eta: 0:00:29  lr: 0.001366  min_lr: 0.001366  loss: 2.5663 (2.3483)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [188]  [260/312]  eta: 0:00:24  lr: 0.001365  min_lr: 0.001365  loss: 2.2069 (2.3363)  weight_decay: 0.0500 (0.0500)  time: 0.4342  data: 0.0003  max mem: 42573
Epoch: [188]  [270/312]  eta: 0:00:19  lr: 0.001364  min_lr: 0.001364  loss: 2.2988 (2.3433)  weight_decay: 0.0500 (0.0500)  time: 0.4341  data: 0.0003  max mem: 42573
Epoch: [188]  [280/312]  eta: 0:00:15  lr: 0.001364  min_lr: 0.001364  loss: 2.5515 (2.3448)  weight_decay: 0.0500 (0.0500)  time: 0.4344  data: 0.0009  max mem: 42573
Epoch: [188]  [290/312]  eta: 0:00:10  lr: 0.001363  min_lr: 0.001363  loss: 2.4959 (2.3497)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0008  max mem: 42573
Epoch: [188]  [300/312]  eta: 0:00:05  lr: 0.001362  min_lr: 0.001362  loss: 2.3615 (2.3446)  weight_decay: 0.0500 (0.0500)  time: 0.4324  data: 0.0001  max mem: 42573
Epoch: [188]  [310/312]  eta: 0:00:00  lr: 0.001361  min_lr: 0.001361  loss: 2.2845 (2.3452)  weight_decay: 0.0500 (0.0500)  time: 0.4323  data: 0.0001  max mem: 42573
Epoch: [188]  [311/312]  eta: 0:00:00  lr: 0.001361  min_lr: 0.001361  loss: 2.2845 (2.3448)  weight_decay: 0.0500 (0.0500)  time: 0.4322  data: 0.0001  max mem: 42573
Epoch: [188] Total time: 0:02:27 (0.4715 s / it)
Averaged stats: lr: 0.001361  min_lr: 0.001361  loss: 2.2845 (2.3363)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:00:39  loss: 0.7642 (0.7642)  acc1: 81.7708 (81.7708)  acc5: 92.9688 (92.9688)  time: 4.4340  data: 4.3244  max mem: 42573
Test:  [8/9]  eta: 0:00:00  loss: 1.0405 (0.9729)  acc1: 75.5208 (75.2640)  acc5: 92.7083 (92.5440)  time: 0.5747  data: 0.4873  max mem: 42573
Test: Total time: 0:00:05 (0.5991 s / it)
* Acc@1 75.620 Acc@5 92.652 loss 0.972
Accuracy of the model on the 50000 test images: 75.6%
Max accuracy: 75.62%
Epoch: [189]  [  0/312]  eta: 0:48:13  lr: 0.001361  min_lr: 0.001361  loss: 2.1906 (2.1906)  weight_decay: 0.0500 (0.0500)  time: 9.2736  data: 7.0405  max mem: 42573
Epoch: [189]  [ 10/312]  eta: 0:07:16  lr: 0.001361  min_lr: 0.001361  loss: 2.1906 (2.2335)  weight_decay: 0.0500 (0.0500)  time: 1.4461  data: 0.7898  max mem: 42573
Epoch: [189]  [ 20/312]  eta: 0:04:41  lr: 0.001360  min_lr: 0.001360  loss: 2.2680 (2.2584)  weight_decay: 0.0500 (0.0500)  time: 0.5484  data: 0.0825  max mem: 42573
Epoch: [189]  [ 30/312]  eta: 0:03:43  lr: 0.001359  min_lr: 0.001359  loss: 2.2680 (2.2473)  weight_decay: 0.0500 (0.0500)  time: 0.4332  data: 0.0004  max mem: 42573
Epoch: [189]  [ 40/312]  eta: 0:03:11  lr: 0.001359  min_lr: 0.001359  loss: 2.2445 (2.2531)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [189]  [ 50/312]  eta: 0:02:50  lr: 0.001358  min_lr: 0.001358  loss: 2.2230 (2.2303)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [189]  [ 60/312]  eta: 0:02:35  lr: 0.001357  min_lr: 0.001357  loss: 2.1358 (2.2295)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [189]  [ 70/312]  eta: 0:02:22  lr: 0.001357  min_lr: 0.001357  loss: 2.2728 (2.2277)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [189]  [ 80/312]  eta: 0:02:12  lr: 0.001356  min_lr: 0.001356  loss: 2.1267 (2.2211)  weight_decay: 0.0500 (0.0500)  time: 0.4341  data: 0.0004  max mem: 42573
Epoch: [189]  [ 90/312]  eta: 0:02:03  lr: 0.001355  min_lr: 0.001355  loss: 2.4392 (2.2769)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [189]  [100/312]  eta: 0:01:55  lr: 0.001355  min_lr: 0.001355  loss: 2.6012 (2.2909)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [189]  [110/312]  eta: 0:01:47  lr: 0.001354  min_lr: 0.001354  loss: 2.3780 (2.2844)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [189]  [120/312]  eta: 0:01:40  lr: 0.001353  min_lr: 0.001353  loss: 2.3780 (2.3019)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [189]  [130/312]  eta: 0:01:34  lr: 0.001352  min_lr: 0.001352  loss: 2.5545 (2.3215)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [189]  [140/312]  eta: 0:01:28  lr: 0.001352  min_lr: 0.001352  loss: 2.4938 (2.3205)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0004  max mem: 42573
Epoch: [189]  [150/312]  eta: 0:01:22  lr: 0.001351  min_lr: 0.001351  loss: 2.4773 (2.3306)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [189]  [160/312]  eta: 0:01:16  lr: 0.001350  min_lr: 0.001350  loss: 2.4773 (2.3324)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [189]  [170/312]  eta: 0:01:10  lr: 0.001350  min_lr: 0.001350  loss: 2.3866 (2.3302)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [189]  [180/312]  eta: 0:01:05  lr: 0.001349  min_lr: 0.001349  loss: 2.1567 (2.3242)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [189]  [190/312]  eta: 0:01:00  lr: 0.001348  min_lr: 0.001348  loss: 2.3704 (2.3218)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [189]  [200/312]  eta: 0:00:54  lr: 0.001348  min_lr: 0.001348  loss: 2.3981 (2.3217)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [189]  [210/312]  eta: 0:00:49  lr: 0.001347  min_lr: 0.001347  loss: 2.2619 (2.3098)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [189]  [220/312]  eta: 0:00:44  lr: 0.001346  min_lr: 0.001346  loss: 2.1010 (2.3053)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [189]  [230/312]  eta: 0:00:39  lr: 0.001346  min_lr: 0.001346  loss: 2.1010 (2.3033)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [189]  [240/312]  eta: 0:00:34  lr: 0.001345  min_lr: 0.001345  loss: 2.2476 (2.3025)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [189]  [250/312]  eta: 0:00:29  lr: 0.001344  min_lr: 0.001344  loss: 2.2053 (2.2982)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [189]  [260/312]  eta: 0:00:24  lr: 0.001344  min_lr: 0.001344  loss: 2.1184 (2.2928)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [189]  [270/312]  eta: 0:00:19  lr: 0.001343  min_lr: 0.001343  loss: 2.3503 (2.2983)  weight_decay: 0.0500 (0.0500)  time: 0.4385  data: 0.0004  max mem: 42573
Epoch: [189]  [280/312]  eta: 0:00:15  lr: 0.001342  min_lr: 0.001342  loss: 2.3503 (2.2878)  weight_decay: 0.0500 (0.0500)  time: 0.4397  data: 0.0009  max mem: 42573
Epoch: [189]  [290/312]  eta: 0:00:10  lr: 0.001342  min_lr: 0.001342  loss: 1.9835 (2.2901)  weight_decay: 0.0500 (0.0500)  time: 0.4345  data: 0.0007  max mem: 42573
Epoch: [189]  [300/312]  eta: 0:00:05  lr: 0.001341  min_lr: 0.001341  loss: 2.3687 (2.2912)  weight_decay: 0.0500 (0.0500)  time: 0.4326  data: 0.0001  max mem: 42573
Epoch: [189]  [310/312]  eta: 0:00:00  lr: 0.001340  min_lr: 0.001340  loss: 2.1146 (2.2889)  weight_decay: 0.0500 (0.0500)  time: 0.4323  data: 0.0001  max mem: 42573
Epoch: [189]  [311/312]  eta: 0:00:00  lr: 0.001340  min_lr: 0.001340  loss: 2.1146 (2.2901)  weight_decay: 0.0500 (0.0500)  time: 0.4323  data: 0.0001  max mem: 42573
Epoch: [189] Total time: 0:02:27 (0.4729 s / it)
Averaged stats: lr: 0.001340  min_lr: 0.001340  loss: 2.1146 (2.3328)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:00:43  loss: 0.7351 (0.7351)  acc1: 82.5521 (82.5521)  acc5: 95.0521 (95.0521)  time: 4.8330  data: 4.7235  max mem: 42573
Test:  [8/9]  eta: 0:00:00  loss: 1.0767 (0.9722)  acc1: 74.2188 (75.4560)  acc5: 91.4062 (92.2240)  time: 0.6136  data: 0.5249  max mem: 42573
Test: Total time: 0:00:05 (0.6400 s / it)
* Acc@1 75.246 Acc@5 92.442 loss 0.973
Accuracy of the model on the 50000 test images: 75.2%
Max accuracy: 75.62%
Epoch: [190]  [  0/312]  eta: 0:51:50  lr: 0.001340  min_lr: 0.001340  loss: 2.4461 (2.4461)  weight_decay: 0.0500 (0.0500)  time: 9.9695  data: 6.7138  max mem: 42573
Epoch: [190]  [ 10/312]  eta: 0:07:31  lr: 0.001339  min_lr: 0.001339  loss: 2.4461 (2.3912)  weight_decay: 0.0500 (0.0500)  time: 1.4953  data: 0.6416  max mem: 42573
Epoch: [190]  [ 20/312]  eta: 0:04:48  lr: 0.001339  min_lr: 0.001339  loss: 2.4946 (2.4441)  weight_decay: 0.0500 (0.0500)  time: 0.5406  data: 0.0174  max mem: 42573
Epoch: [190]  [ 30/312]  eta: 0:03:48  lr: 0.001338  min_lr: 0.001338  loss: 2.4946 (2.4290)  weight_decay: 0.0500 (0.0500)  time: 0.4332  data: 0.0004  max mem: 42573
Epoch: [190]  [ 40/312]  eta: 0:03:15  lr: 0.001337  min_lr: 0.001337  loss: 2.4349 (2.4007)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0003  max mem: 42573
Epoch: [190]  [ 50/312]  eta: 0:02:53  lr: 0.001337  min_lr: 0.001337  loss: 2.4293 (2.4017)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [190]  [ 60/312]  eta: 0:02:37  lr: 0.001336  min_lr: 0.001336  loss: 2.3592 (2.3822)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [190]  [ 70/312]  eta: 0:02:24  lr: 0.001335  min_lr: 0.001335  loss: 2.3592 (2.3648)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [190]  [ 80/312]  eta: 0:02:14  lr: 0.001335  min_lr: 0.001335  loss: 2.2738 (2.3533)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [190]  [ 90/312]  eta: 0:02:04  lr: 0.001334  min_lr: 0.001334  loss: 2.2738 (2.3535)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [190]  [100/312]  eta: 0:01:56  lr: 0.001333  min_lr: 0.001333  loss: 2.4751 (2.3648)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [190]  [110/312]  eta: 0:01:48  lr: 0.001333  min_lr: 0.001333  loss: 2.4792 (2.3634)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [190]  [120/312]  eta: 0:01:41  lr: 0.001332  min_lr: 0.001332  loss: 2.3316 (2.3649)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [190]  [130/312]  eta: 0:01:35  lr: 0.001331  min_lr: 0.001331  loss: 2.3325 (2.3672)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [190]  [140/312]  eta: 0:01:28  lr: 0.001331  min_lr: 0.001331  loss: 2.5077 (2.3734)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [190]  [150/312]  eta: 0:01:22  lr: 0.001330  min_lr: 0.001330  loss: 2.5991 (2.3751)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [190]  [160/312]  eta: 0:01:16  lr: 0.001329  min_lr: 0.001329  loss: 2.2193 (2.3642)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [190]  [170/312]  eta: 0:01:11  lr: 0.001329  min_lr: 0.001329  loss: 2.1196 (2.3614)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [190]  [180/312]  eta: 0:01:05  lr: 0.001328  min_lr: 0.001328  loss: 2.1196 (2.3507)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [190]  [190/312]  eta: 0:01:00  lr: 0.001327  min_lr: 0.001327  loss: 2.2286 (2.3449)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [190]  [200/312]  eta: 0:00:55  lr: 0.001327  min_lr: 0.001327  loss: 2.2416 (2.3416)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [190]  [210/312]  eta: 0:00:49  lr: 0.001326  min_lr: 0.001326  loss: 2.3497 (2.3453)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [190]  [220/312]  eta: 0:00:44  lr: 0.001325  min_lr: 0.001325  loss: 2.3258 (2.3477)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [190]  [230/312]  eta: 0:00:39  lr: 0.001325  min_lr: 0.001325  loss: 2.3229 (2.3512)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [190]  [240/312]  eta: 0:00:34  lr: 0.001324  min_lr: 0.001324  loss: 2.4214 (2.3476)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [190]  [250/312]  eta: 0:00:29  lr: 0.001323  min_lr: 0.001323  loss: 2.3007 (2.3430)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0003  max mem: 42573
Epoch: [190]  [260/312]  eta: 0:00:24  lr: 0.001322  min_lr: 0.001322  loss: 2.1320 (2.3362)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [190]  [270/312]  eta: 0:00:20  lr: 0.001322  min_lr: 0.001322  loss: 2.2808 (2.3413)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [190]  [280/312]  eta: 0:00:15  lr: 0.001321  min_lr: 0.001321  loss: 2.4166 (2.3392)  weight_decay: 0.0500 (0.0500)  time: 0.4366  data: 0.0010  max mem: 42573
Epoch: [190]  [290/312]  eta: 0:00:10  lr: 0.001320  min_lr: 0.001320  loss: 2.2455 (2.3339)  weight_decay: 0.0500 (0.0500)  time: 0.4360  data: 0.0008  max mem: 42573
Epoch: [190]  [300/312]  eta: 0:00:05  lr: 0.001320  min_lr: 0.001320  loss: 2.3733 (2.3414)  weight_decay: 0.0500 (0.0500)  time: 0.4324  data: 0.0001  max mem: 42573
Epoch: [190]  [310/312]  eta: 0:00:00  lr: 0.001319  min_lr: 0.001319  loss: 2.5966 (2.3478)  weight_decay: 0.0500 (0.0500)  time: 0.4323  data: 0.0001  max mem: 42573
Epoch: [190]  [311/312]  eta: 0:00:00  lr: 0.001319  min_lr: 0.001319  loss: 2.5966 (2.3479)  weight_decay: 0.0500 (0.0500)  time: 0.4323  data: 0.0001  max mem: 42573
Epoch: [190] Total time: 0:02:27 (0.4741 s / it)
Averaged stats: lr: 0.001319  min_lr: 0.001319  loss: 2.5966 (2.3342)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:00:41  loss: 0.8166 (0.8166)  acc1: 78.1250 (78.1250)  acc5: 93.4896 (93.4896)  time: 4.6497  data: 4.5403  max mem: 42573
Test:  [8/9]  eta: 0:00:00  loss: 1.0379 (1.0038)  acc1: 75.5208 (74.8160)  acc5: 93.4896 (92.7360)  time: 0.5923  data: 0.5045  max mem: 42573
Test: Total time: 0:00:05 (0.6112 s / it)
* Acc@1 75.094 Acc@5 92.360 loss 1.002
Accuracy of the model on the 50000 test images: 75.1%
Max accuracy: 75.62%
Epoch: [191]  [  0/312]  eta: 0:52:57  lr: 0.001319  min_lr: 0.001319  loss: 2.1238 (2.1238)  weight_decay: 0.0500 (0.0500)  time: 10.1830  data: 6.7870  max mem: 42573
Epoch: [191]  [ 10/312]  eta: 0:07:51  lr: 0.001318  min_lr: 0.001318  loss: 2.0772 (2.1531)  weight_decay: 0.0500 (0.0500)  time: 1.5621  data: 0.6174  max mem: 42573
Epoch: [191]  [ 20/312]  eta: 0:04:59  lr: 0.001318  min_lr: 0.001318  loss: 2.2866 (2.2736)  weight_decay: 0.0500 (0.0500)  time: 0.5664  data: 0.0004  max mem: 42573
Epoch: [191]  [ 30/312]  eta: 0:03:55  lr: 0.001317  min_lr: 0.001317  loss: 2.4274 (2.2637)  weight_decay: 0.0500 (0.0500)  time: 0.4331  data: 0.0003  max mem: 42573
Epoch: [191]  [ 40/312]  eta: 0:03:20  lr: 0.001316  min_lr: 0.001316  loss: 2.2471 (2.2663)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [191]  [ 50/312]  eta: 0:02:57  lr: 0.001316  min_lr: 0.001316  loss: 2.2471 (2.2820)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [191]  [ 60/312]  eta: 0:02:40  lr: 0.001315  min_lr: 0.001315  loss: 2.3295 (2.2896)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [191]  [ 70/312]  eta: 0:02:27  lr: 0.001314  min_lr: 0.001314  loss: 2.4085 (2.2987)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [191]  [ 80/312]  eta: 0:02:16  lr: 0.001314  min_lr: 0.001314  loss: 2.4131 (2.3119)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0004  max mem: 42573
Epoch: [191]  [ 90/312]  eta: 0:02:06  lr: 0.001313  min_lr: 0.001313  loss: 2.4055 (2.2930)  weight_decay: 0.0500 (0.0500)  time: 0.4341  data: 0.0004  max mem: 42573
Epoch: [191]  [100/312]  eta: 0:01:57  lr: 0.001312  min_lr: 0.001312  loss: 2.3785 (2.3004)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [191]  [110/312]  eta: 0:01:50  lr: 0.001312  min_lr: 0.001312  loss: 2.4862 (2.3178)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0003  max mem: 42573
Epoch: [191]  [120/312]  eta: 0:01:42  lr: 0.001311  min_lr: 0.001311  loss: 2.5021 (2.3192)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [191]  [130/312]  eta: 0:01:36  lr: 0.001310  min_lr: 0.001310  loss: 2.3708 (2.3123)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0004  max mem: 42573
Epoch: [191]  [140/312]  eta: 0:01:29  lr: 0.001310  min_lr: 0.001310  loss: 2.2835 (2.3121)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [191]  [150/312]  eta: 0:01:23  lr: 0.001309  min_lr: 0.001309  loss: 2.3332 (2.3204)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0003  max mem: 42573
Epoch: [191]  [160/312]  eta: 0:01:17  lr: 0.001308  min_lr: 0.001308  loss: 2.4840 (2.3290)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [191]  [170/312]  eta: 0:01:11  lr: 0.001307  min_lr: 0.001307  loss: 2.4258 (2.3218)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [191]  [180/312]  eta: 0:01:06  lr: 0.001307  min_lr: 0.001307  loss: 2.1774 (2.3119)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [191]  [190/312]  eta: 0:01:00  lr: 0.001306  min_lr: 0.001306  loss: 2.3783 (2.3239)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [191]  [200/312]  eta: 0:00:55  lr: 0.001305  min_lr: 0.001305  loss: 2.3879 (2.3226)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [191]  [210/312]  eta: 0:00:50  lr: 0.001305  min_lr: 0.001305  loss: 2.3460 (2.3292)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [191]  [220/312]  eta: 0:00:45  lr: 0.001304  min_lr: 0.001304  loss: 2.2162 (2.3185)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [191]  [230/312]  eta: 0:00:39  lr: 0.001303  min_lr: 0.001303  loss: 2.3242 (2.3252)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [191]  [240/312]  eta: 0:00:34  lr: 0.001303  min_lr: 0.001303  loss: 2.5948 (2.3346)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0003  max mem: 42573
Epoch: [191]  [250/312]  eta: 0:00:29  lr: 0.001302  min_lr: 0.001302  loss: 2.5749 (2.3406)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0004  max mem: 42573
Epoch: [191]  [260/312]  eta: 0:00:25  lr: 0.001301  min_lr: 0.001301  loss: 2.4286 (2.3420)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [191]  [270/312]  eta: 0:00:20  lr: 0.001301  min_lr: 0.001301  loss: 2.4042 (2.3418)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0003  max mem: 42573
Epoch: [191]  [280/312]  eta: 0:00:15  lr: 0.001300  min_lr: 0.001300  loss: 2.3526 (2.3379)  weight_decay: 0.0500 (0.0500)  time: 0.4342  data: 0.0009  max mem: 42573
Epoch: [191]  [290/312]  eta: 0:00:10  lr: 0.001299  min_lr: 0.001299  loss: 2.3136 (2.3317)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0008  max mem: 42573
Epoch: [191]  [300/312]  eta: 0:00:05  lr: 0.001299  min_lr: 0.001299  loss: 2.3136 (2.3312)  weight_decay: 0.0500 (0.0500)  time: 0.4324  data: 0.0001  max mem: 42573
Epoch: [191]  [310/312]  eta: 0:00:00  lr: 0.001298  min_lr: 0.001298  loss: 2.2530 (2.3271)  weight_decay: 0.0500 (0.0500)  time: 0.4323  data: 0.0001  max mem: 42573
Epoch: [191]  [311/312]  eta: 0:00:00  lr: 0.001298  min_lr: 0.001298  loss: 2.2530 (2.3278)  weight_decay: 0.0500 (0.0500)  time: 0.4323  data: 0.0001  max mem: 42573
Epoch: [191] Total time: 0:02:28 (0.4764 s / it)
Averaged stats: lr: 0.001298  min_lr: 0.001298  loss: 2.2530 (2.3256)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:00:43  loss: 0.7051 (0.7051)  acc1: 83.3333 (83.3333)  acc5: 94.2708 (94.2708)  time: 4.7889  data: 4.6795  max mem: 42573
Test:  [8/9]  eta: 0:00:00  loss: 1.0267 (0.9758)  acc1: 75.2604 (75.3600)  acc5: 91.9271 (92.6720)  time: 0.6073  data: 0.5200  max mem: 42573
Test: Total time: 0:00:05 (0.6213 s / it)
* Acc@1 75.568 Acc@5 92.422 loss 0.988
Accuracy of the model on the 50000 test images: 75.6%
Max accuracy: 75.62%
Epoch: [192]  [  0/312]  eta: 0:51:15  lr: 0.001298  min_lr: 0.001298  loss: 2.5682 (2.5682)  weight_decay: 0.0500 (0.0500)  time: 9.8565  data: 8.4761  max mem: 42573
Epoch: [192]  [ 10/312]  eta: 0:07:23  lr: 0.001297  min_lr: 0.001297  loss: 2.4766 (2.2493)  weight_decay: 0.0500 (0.0500)  time: 1.4700  data: 0.7710  max mem: 42573
Epoch: [192]  [ 20/312]  eta: 0:04:45  lr: 0.001297  min_lr: 0.001297  loss: 2.1298 (2.2191)  weight_decay: 0.0500 (0.0500)  time: 0.5323  data: 0.0004  max mem: 42573
Epoch: [192]  [ 30/312]  eta: 0:03:46  lr: 0.001296  min_lr: 0.001296  loss: 2.3160 (2.2826)  weight_decay: 0.0500 (0.0500)  time: 0.4390  data: 0.0004  max mem: 42573
Epoch: [192]  [ 40/312]  eta: 0:03:14  lr: 0.001295  min_lr: 0.001295  loss: 2.4374 (2.3069)  weight_decay: 0.0500 (0.0500)  time: 0.4391  data: 0.0004  max mem: 42573
Epoch: [192]  [ 50/312]  eta: 0:02:52  lr: 0.001295  min_lr: 0.001295  loss: 2.3658 (2.3166)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [192]  [ 60/312]  eta: 0:02:36  lr: 0.001294  min_lr: 0.001294  loss: 2.3702 (2.3239)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [192]  [ 70/312]  eta: 0:02:24  lr: 0.001293  min_lr: 0.001293  loss: 2.5195 (2.3442)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [192]  [ 80/312]  eta: 0:02:13  lr: 0.001293  min_lr: 0.001293  loss: 2.5122 (2.3554)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [192]  [ 90/312]  eta: 0:02:04  lr: 0.001292  min_lr: 0.001292  loss: 2.5004 (2.3592)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [192]  [100/312]  eta: 0:01:56  lr: 0.001291  min_lr: 0.001291  loss: 2.5352 (2.3698)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [192]  [110/312]  eta: 0:01:48  lr: 0.001291  min_lr: 0.001291  loss: 2.4828 (2.3718)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0003  max mem: 42573
Epoch: [192]  [120/312]  eta: 0:01:41  lr: 0.001290  min_lr: 0.001290  loss: 2.4586 (2.3696)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [192]  [130/312]  eta: 0:01:34  lr: 0.001289  min_lr: 0.001289  loss: 2.4354 (2.3661)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [192]  [140/312]  eta: 0:01:28  lr: 0.001289  min_lr: 0.001289  loss: 2.4354 (2.3695)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [192]  [150/312]  eta: 0:01:22  lr: 0.001288  min_lr: 0.001288  loss: 2.4826 (2.3728)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [192]  [160/312]  eta: 0:01:16  lr: 0.001287  min_lr: 0.001287  loss: 2.4567 (2.3710)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [192]  [170/312]  eta: 0:01:11  lr: 0.001286  min_lr: 0.001286  loss: 2.2771 (2.3704)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [192]  [180/312]  eta: 0:01:05  lr: 0.001286  min_lr: 0.001286  loss: 2.2534 (2.3535)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [192]  [190/312]  eta: 0:01:00  lr: 0.001285  min_lr: 0.001285  loss: 2.0977 (2.3458)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [192]  [200/312]  eta: 0:00:54  lr: 0.001284  min_lr: 0.001284  loss: 2.3577 (2.3441)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [192]  [210/312]  eta: 0:00:49  lr: 0.001284  min_lr: 0.001284  loss: 2.4159 (2.3473)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0003  max mem: 42573
Epoch: [192]  [220/312]  eta: 0:00:44  lr: 0.001283  min_lr: 0.001283  loss: 2.4782 (2.3515)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [192]  [230/312]  eta: 0:00:39  lr: 0.001282  min_lr: 0.001282  loss: 2.3453 (2.3481)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [192]  [240/312]  eta: 0:00:34  lr: 0.001282  min_lr: 0.001282  loss: 2.3453 (2.3571)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0003  max mem: 42573
Epoch: [192]  [250/312]  eta: 0:00:29  lr: 0.001281  min_lr: 0.001281  loss: 2.5517 (2.3622)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [192]  [260/312]  eta: 0:00:24  lr: 0.001280  min_lr: 0.001280  loss: 2.3781 (2.3570)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [192]  [270/312]  eta: 0:00:19  lr: 0.001280  min_lr: 0.001280  loss: 2.1964 (2.3528)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [192]  [280/312]  eta: 0:00:15  lr: 0.001279  min_lr: 0.001279  loss: 2.4365 (2.3605)  weight_decay: 0.0500 (0.0500)  time: 0.4343  data: 0.0010  max mem: 42573
Epoch: [192]  [290/312]  eta: 0:00:10  lr: 0.001278  min_lr: 0.001278  loss: 2.4592 (2.3571)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0008  max mem: 42573
Epoch: [192]  [300/312]  eta: 0:00:05  lr: 0.001278  min_lr: 0.001278  loss: 2.3431 (2.3582)  weight_decay: 0.0500 (0.0500)  time: 0.4324  data: 0.0001  max mem: 42573
Epoch: [192]  [310/312]  eta: 0:00:00  lr: 0.001277  min_lr: 0.001277  loss: 2.3611 (2.3583)  weight_decay: 0.0500 (0.0500)  time: 0.4325  data: 0.0001  max mem: 42573
Epoch: [192]  [311/312]  eta: 0:00:00  lr: 0.001277  min_lr: 0.001277  loss: 2.3611 (2.3589)  weight_decay: 0.0500 (0.0500)  time: 0.4325  data: 0.0001  max mem: 42573
Epoch: [192] Total time: 0:02:27 (0.4735 s / it)
Averaged stats: lr: 0.001277  min_lr: 0.001277  loss: 2.3611 (2.3150)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:00:35  loss: 0.7336 (0.7336)  acc1: 80.9896 (80.9896)  acc5: 94.7917 (94.7917)  time: 3.9470  data: 3.8374  max mem: 42573
Test:  [8/9]  eta: 0:00:00  loss: 1.0123 (0.9292)  acc1: 74.2188 (74.8160)  acc5: 93.7500 (93.1840)  time: 0.5142  data: 0.4265  max mem: 42573
Test: Total time: 0:00:04 (0.5212 s / it)
* Acc@1 75.990 Acc@5 92.892 loss 0.932
Accuracy of the model on the 50000 test images: 76.0%
Max accuracy: 75.99%
Epoch: [193]  [  0/312]  eta: 0:50:28  lr: 0.001277  min_lr: 0.001277  loss: 2.2300 (2.2300)  weight_decay: 0.0500 (0.0500)  time: 9.7055  data: 8.0090  max mem: 42573
Epoch: [193]  [ 10/312]  eta: 0:07:30  lr: 0.001276  min_lr: 0.001276  loss: 2.5126 (2.4223)  weight_decay: 0.0500 (0.0500)  time: 1.4917  data: 0.7284  max mem: 42573
Epoch: [193]  [ 20/312]  eta: 0:04:48  lr: 0.001276  min_lr: 0.001276  loss: 2.3816 (2.2930)  weight_decay: 0.0500 (0.0500)  time: 0.5515  data: 0.0004  max mem: 42573
Epoch: [193]  [ 30/312]  eta: 0:03:48  lr: 0.001275  min_lr: 0.001275  loss: 2.3995 (2.3427)  weight_decay: 0.0500 (0.0500)  time: 0.4328  data: 0.0004  max mem: 42573
Epoch: [193]  [ 40/312]  eta: 0:03:15  lr: 0.001274  min_lr: 0.001274  loss: 2.4776 (2.4007)  weight_decay: 0.0500 (0.0500)  time: 0.4331  data: 0.0005  max mem: 42573
Epoch: [193]  [ 50/312]  eta: 0:02:53  lr: 0.001274  min_lr: 0.001274  loss: 2.3507 (2.3483)  weight_decay: 0.0500 (0.0500)  time: 0.4332  data: 0.0006  max mem: 42573
Epoch: [193]  [ 60/312]  eta: 0:02:37  lr: 0.001273  min_lr: 0.001273  loss: 2.1428 (2.3126)  weight_decay: 0.0500 (0.0500)  time: 0.4332  data: 0.0005  max mem: 42573
Epoch: [193]  [ 70/312]  eta: 0:02:24  lr: 0.001272  min_lr: 0.001272  loss: 2.1012 (2.2796)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [193]  [ 80/312]  eta: 0:02:13  lr: 0.001272  min_lr: 0.001272  loss: 2.2531 (2.2821)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [193]  [ 90/312]  eta: 0:02:04  lr: 0.001271  min_lr: 0.001271  loss: 2.2956 (2.2880)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [193]  [100/312]  eta: 0:01:56  lr: 0.001270  min_lr: 0.001270  loss: 2.0038 (2.2568)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [193]  [110/312]  eta: 0:01:48  lr: 0.001270  min_lr: 0.001270  loss: 2.0038 (2.2554)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [193]  [120/312]  eta: 0:01:41  lr: 0.001269  min_lr: 0.001269  loss: 2.2555 (2.2551)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [193]  [130/312]  eta: 0:01:35  lr: 0.001268  min_lr: 0.001268  loss: 2.3586 (2.2586)  weight_decay: 0.0500 (0.0500)  time: 0.4374  data: 0.0004  max mem: 42573
Epoch: [193]  [140/312]  eta: 0:01:28  lr: 0.001268  min_lr: 0.001268  loss: 2.3586 (2.2492)  weight_decay: 0.0500 (0.0500)  time: 0.4374  data: 0.0004  max mem: 42573
Epoch: [193]  [150/312]  eta: 0:01:22  lr: 0.001267  min_lr: 0.001267  loss: 2.3898 (2.2580)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [193]  [160/312]  eta: 0:01:16  lr: 0.001266  min_lr: 0.001266  loss: 2.4192 (2.2687)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0005  max mem: 42573
Epoch: [193]  [170/312]  eta: 0:01:11  lr: 0.001266  min_lr: 0.001266  loss: 2.3680 (2.2676)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0005  max mem: 42573
Epoch: [193]  [180/312]  eta: 0:01:05  lr: 0.001265  min_lr: 0.001265  loss: 2.3210 (2.2664)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [193]  [190/312]  eta: 0:01:00  lr: 0.001264  min_lr: 0.001264  loss: 2.2593 (2.2632)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [193]  [200/312]  eta: 0:00:55  lr: 0.001264  min_lr: 0.001264  loss: 2.2923 (2.2611)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [193]  [210/312]  eta: 0:00:49  lr: 0.001263  min_lr: 0.001263  loss: 2.3609 (2.2684)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [193]  [220/312]  eta: 0:00:44  lr: 0.001262  min_lr: 0.001262  loss: 2.5182 (2.2812)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [193]  [230/312]  eta: 0:00:39  lr: 0.001262  min_lr: 0.001262  loss: 2.4355 (2.2799)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [193]  [240/312]  eta: 0:00:34  lr: 0.001261  min_lr: 0.001261  loss: 2.4030 (2.2838)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [193]  [250/312]  eta: 0:00:29  lr: 0.001260  min_lr: 0.001260  loss: 2.3272 (2.2816)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [193]  [260/312]  eta: 0:00:24  lr: 0.001260  min_lr: 0.001260  loss: 2.2073 (2.2771)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [193]  [270/312]  eta: 0:00:20  lr: 0.001259  min_lr: 0.001259  loss: 2.5266 (2.2844)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [193]  [280/312]  eta: 0:00:15  lr: 0.001258  min_lr: 0.001258  loss: 2.5432 (2.2918)  weight_decay: 0.0500 (0.0500)  time: 0.4341  data: 0.0010  max mem: 42573
Epoch: [193]  [290/312]  eta: 0:00:10  lr: 0.001258  min_lr: 0.001258  loss: 2.4536 (2.2886)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0008  max mem: 42573
Epoch: [193]  [300/312]  eta: 0:00:05  lr: 0.001257  min_lr: 0.001257  loss: 2.3055 (2.2882)  weight_decay: 0.0500 (0.0500)  time: 0.4325  data: 0.0001  max mem: 42573
Epoch: [193]  [310/312]  eta: 0:00:00  lr: 0.001256  min_lr: 0.001256  loss: 2.3678 (2.2914)  weight_decay: 0.0500 (0.0500)  time: 0.4323  data: 0.0001  max mem: 42573
Epoch: [193]  [311/312]  eta: 0:00:00  lr: 0.001256  min_lr: 0.001256  loss: 2.3851 (2.2929)  weight_decay: 0.0500 (0.0500)  time: 0.4323  data: 0.0001  max mem: 42573
Epoch: [193] Total time: 0:02:27 (0.4741 s / it)
Averaged stats: lr: 0.001256  min_lr: 0.001256  loss: 2.3851 (2.3198)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:00:42  loss: 0.6783 (0.6783)  acc1: 81.5104 (81.5104)  acc5: 94.2708 (94.2708)  time: 4.6945  data: 4.5850  max mem: 42573
Test:  [8/9]  eta: 0:00:00  loss: 1.0201 (0.9675)  acc1: 75.7812 (75.1680)  acc5: 92.1875 (92.0640)  time: 0.5989  data: 0.5095  max mem: 42573
Test: Total time: 0:00:05 (0.6159 s / it)
* Acc@1 75.386 Acc@5 92.386 loss 0.975
Accuracy of the model on the 50000 test images: 75.4%
Max accuracy: 75.99%
Epoch: [194]  [  0/312]  eta: 0:50:20  lr: 0.001256  min_lr: 0.001256  loss: 1.4652 (1.4652)  weight_decay: 0.0500 (0.0500)  time: 9.6797  data: 6.4608  max mem: 42573
Epoch: [194]  [ 10/312]  eta: 0:07:21  lr: 0.001255  min_lr: 0.001255  loss: 2.0164 (2.0640)  weight_decay: 0.0500 (0.0500)  time: 1.4612  data: 0.6779  max mem: 42573
Epoch: [194]  [ 20/312]  eta: 0:04:43  lr: 0.001255  min_lr: 0.001255  loss: 2.2809 (2.1950)  weight_decay: 0.0500 (0.0500)  time: 0.5361  data: 0.0500  max mem: 42573
Epoch: [194]  [ 30/312]  eta: 0:03:45  lr: 0.001254  min_lr: 0.001254  loss: 2.2809 (2.1886)  weight_decay: 0.0500 (0.0500)  time: 0.4331  data: 0.0004  max mem: 42573
Epoch: [194]  [ 40/312]  eta: 0:03:12  lr: 0.001253  min_lr: 0.001253  loss: 2.2302 (2.2552)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [194]  [ 50/312]  eta: 0:02:51  lr: 0.001253  min_lr: 0.001253  loss: 2.4230 (2.2500)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [194]  [ 60/312]  eta: 0:02:35  lr: 0.001252  min_lr: 0.001252  loss: 2.3278 (2.2734)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [194]  [ 70/312]  eta: 0:02:23  lr: 0.001251  min_lr: 0.001251  loss: 2.3899 (2.3013)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [194]  [ 80/312]  eta: 0:02:12  lr: 0.001251  min_lr: 0.001251  loss: 2.4844 (2.3049)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [194]  [ 90/312]  eta: 0:02:03  lr: 0.001250  min_lr: 0.001250  loss: 2.4928 (2.3193)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [194]  [100/312]  eta: 0:01:55  lr: 0.001249  min_lr: 0.001249  loss: 2.5141 (2.3264)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [194]  [110/312]  eta: 0:01:48  lr: 0.001249  min_lr: 0.001249  loss: 2.3824 (2.3231)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0004  max mem: 42573
Epoch: [194]  [120/312]  eta: 0:01:41  lr: 0.001248  min_lr: 0.001248  loss: 2.3431 (2.3178)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0004  max mem: 42573
Epoch: [194]  [130/312]  eta: 0:01:34  lr: 0.001247  min_lr: 0.001247  loss: 2.3830 (2.3208)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [194]  [140/312]  eta: 0:01:28  lr: 0.001247  min_lr: 0.001247  loss: 2.4506 (2.3303)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [194]  [150/312]  eta: 0:01:22  lr: 0.001246  min_lr: 0.001246  loss: 2.5730 (2.3460)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [194]  [160/312]  eta: 0:01:16  lr: 0.001245  min_lr: 0.001245  loss: 2.5114 (2.3464)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0003  max mem: 42573
Epoch: [194]  [170/312]  eta: 0:01:11  lr: 0.001245  min_lr: 0.001245  loss: 2.2683 (2.3356)  weight_decay: 0.0500 (0.0500)  time: 0.4382  data: 0.0003  max mem: 42573
Epoch: [194]  [180/312]  eta: 0:01:05  lr: 0.001244  min_lr: 0.001244  loss: 2.2752 (2.3374)  weight_decay: 0.0500 (0.0500)  time: 0.4381  data: 0.0003  max mem: 42573
Epoch: [194]  [190/312]  eta: 0:01:00  lr: 0.001243  min_lr: 0.001243  loss: 2.3984 (2.3410)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [194]  [200/312]  eta: 0:00:54  lr: 0.001243  min_lr: 0.001243  loss: 2.3984 (2.3360)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [194]  [210/312]  eta: 0:00:49  lr: 0.001242  min_lr: 0.001242  loss: 2.3258 (2.3357)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [194]  [220/312]  eta: 0:00:44  lr: 0.001241  min_lr: 0.001241  loss: 2.4226 (2.3406)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [194]  [230/312]  eta: 0:00:39  lr: 0.001241  min_lr: 0.001241  loss: 2.4378 (2.3431)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [194]  [240/312]  eta: 0:00:34  lr: 0.001240  min_lr: 0.001240  loss: 2.4292 (2.3426)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [194]  [250/312]  eta: 0:00:29  lr: 0.001239  min_lr: 0.001239  loss: 2.3841 (2.3463)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [194]  [260/312]  eta: 0:00:24  lr: 0.001239  min_lr: 0.001239  loss: 2.3500 (2.3451)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [194]  [270/312]  eta: 0:00:19  lr: 0.001238  min_lr: 0.001238  loss: 2.2263 (2.3406)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [194]  [280/312]  eta: 0:00:15  lr: 0.001237  min_lr: 0.001237  loss: 2.3675 (2.3368)  weight_decay: 0.0500 (0.0500)  time: 0.4342  data: 0.0009  max mem: 42573
Epoch: [194]  [290/312]  eta: 0:00:10  lr: 0.001237  min_lr: 0.001237  loss: 2.3039 (2.3346)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0008  max mem: 42573
Epoch: [194]  [300/312]  eta: 0:00:05  lr: 0.001236  min_lr: 0.001236  loss: 2.2062 (2.3346)  weight_decay: 0.0500 (0.0500)  time: 0.4326  data: 0.0001  max mem: 42573
Epoch: [194]  [310/312]  eta: 0:00:00  lr: 0.001235  min_lr: 0.001235  loss: 2.5286 (2.3421)  weight_decay: 0.0500 (0.0500)  time: 0.4323  data: 0.0001  max mem: 42573
Epoch: [194]  [311/312]  eta: 0:00:00  lr: 0.001235  min_lr: 0.001235  loss: 2.5228 (2.3415)  weight_decay: 0.0500 (0.0500)  time: 0.4323  data: 0.0001  max mem: 42573
Epoch: [194] Total time: 0:02:27 (0.4732 s / it)
Averaged stats: lr: 0.001235  min_lr: 0.001235  loss: 2.5228 (2.3232)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:00:41  loss: 0.7248 (0.7248)  acc1: 83.0729 (83.0729)  acc5: 95.5729 (95.5729)  time: 4.6634  data: 4.5538  max mem: 42573
Test:  [8/9]  eta: 0:00:00  loss: 1.0478 (0.9855)  acc1: 73.9583 (74.9440)  acc5: 92.7083 (92.6400)  time: 0.5954  data: 0.5060  max mem: 42573
Test: Total time: 0:00:05 (0.6218 s / it)
* Acc@1 75.354 Acc@5 92.350 loss 0.978
Accuracy of the model on the 50000 test images: 75.4%
Max accuracy: 75.99%
Epoch: [195]  [  0/312]  eta: 0:49:25  lr: 0.001235  min_lr: 0.001235  loss: 1.8719 (1.8719)  weight_decay: 0.0500 (0.0500)  time: 9.5054  data: 5.8026  max mem: 42573
Epoch: [195]  [ 10/312]  eta: 0:07:31  lr: 0.001235  min_lr: 0.001235  loss: 1.9997 (2.1314)  weight_decay: 0.0500 (0.0500)  time: 1.4963  data: 0.7640  max mem: 42573
Epoch: [195]  [ 20/312]  eta: 0:04:49  lr: 0.001234  min_lr: 0.001234  loss: 2.1694 (2.2769)  weight_decay: 0.0500 (0.0500)  time: 0.5642  data: 0.1302  max mem: 42573
Epoch: [195]  [ 30/312]  eta: 0:03:48  lr: 0.001233  min_lr: 0.001233  loss: 2.3557 (2.2554)  weight_decay: 0.0500 (0.0500)  time: 0.4332  data: 0.0003  max mem: 42573
Epoch: [195]  [ 40/312]  eta: 0:03:15  lr: 0.001233  min_lr: 0.001233  loss: 2.3188 (2.2574)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [195]  [ 50/312]  eta: 0:02:53  lr: 0.001232  min_lr: 0.001232  loss: 2.3188 (2.2566)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [195]  [ 60/312]  eta: 0:02:37  lr: 0.001231  min_lr: 0.001231  loss: 2.2696 (2.2421)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0003  max mem: 42573
Epoch: [195]  [ 70/312]  eta: 0:02:24  lr: 0.001231  min_lr: 0.001231  loss: 2.1490 (2.2206)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [195]  [ 80/312]  eta: 0:02:14  lr: 0.001230  min_lr: 0.001230  loss: 2.3317 (2.2552)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [195]  [ 90/312]  eta: 0:02:04  lr: 0.001229  min_lr: 0.001229  loss: 2.4750 (2.2601)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [195]  [100/312]  eta: 0:01:56  lr: 0.001229  min_lr: 0.001229  loss: 2.3175 (2.2543)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [195]  [110/312]  eta: 0:01:48  lr: 0.001228  min_lr: 0.001228  loss: 2.1819 (2.2491)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [195]  [120/312]  eta: 0:01:41  lr: 0.001227  min_lr: 0.001227  loss: 2.3037 (2.2485)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [195]  [130/312]  eta: 0:01:35  lr: 0.001227  min_lr: 0.001227  loss: 2.4248 (2.2603)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [195]  [140/312]  eta: 0:01:28  lr: 0.001226  min_lr: 0.001226  loss: 2.4464 (2.2732)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [195]  [150/312]  eta: 0:01:22  lr: 0.001225  min_lr: 0.001225  loss: 2.3901 (2.2770)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [195]  [160/312]  eta: 0:01:16  lr: 0.001225  min_lr: 0.001225  loss: 2.2233 (2.2686)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0004  max mem: 42573
Epoch: [195]  [170/312]  eta: 0:01:11  lr: 0.001224  min_lr: 0.001224  loss: 2.2632 (2.2821)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [195]  [180/312]  eta: 0:01:05  lr: 0.001223  min_lr: 0.001223  loss: 2.5204 (2.2824)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [195]  [190/312]  eta: 0:01:00  lr: 0.001223  min_lr: 0.001223  loss: 2.4413 (2.2905)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [195]  [200/312]  eta: 0:00:55  lr: 0.001222  min_lr: 0.001222  loss: 2.3301 (2.2847)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0003  max mem: 42573
Epoch: [195]  [210/312]  eta: 0:00:49  lr: 0.001221  min_lr: 0.001221  loss: 2.0731 (2.2812)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [195]  [220/312]  eta: 0:00:44  lr: 0.001221  min_lr: 0.001221  loss: 2.4827 (2.2934)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [195]  [230/312]  eta: 0:00:39  lr: 0.001220  min_lr: 0.001220  loss: 2.4638 (2.2938)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [195]  [240/312]  eta: 0:00:34  lr: 0.001219  min_lr: 0.001219  loss: 2.3911 (2.2915)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [195]  [250/312]  eta: 0:00:29  lr: 0.001219  min_lr: 0.001219  loss: 2.4203 (2.2944)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0003  max mem: 42573
Epoch: [195]  [260/312]  eta: 0:00:24  lr: 0.001218  min_lr: 0.001218  loss: 2.4203 (2.2916)  weight_decay: 0.0500 (0.0500)  time: 0.4421  data: 0.0003  max mem: 42573
Epoch: [195]  [270/312]  eta: 0:00:20  lr: 0.001217  min_lr: 0.001217  loss: 2.3188 (2.2921)  weight_decay: 0.0500 (0.0500)  time: 0.4418  data: 0.0004  max mem: 42573
Epoch: [195]  [280/312]  eta: 0:00:15  lr: 0.001217  min_lr: 0.001217  loss: 2.0765 (2.2891)  weight_decay: 0.0500 (0.0500)  time: 0.4342  data: 0.0009  max mem: 42573
Epoch: [195]  [290/312]  eta: 0:00:10  lr: 0.001216  min_lr: 0.001216  loss: 2.0683 (2.2850)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0008  max mem: 42573
Epoch: [195]  [300/312]  eta: 0:00:05  lr: 0.001215  min_lr: 0.001215  loss: 2.2815 (2.2919)  weight_decay: 0.0500 (0.0500)  time: 0.4324  data: 0.0001  max mem: 42573
Epoch: [195]  [310/312]  eta: 0:00:00  lr: 0.001215  min_lr: 0.001215  loss: 2.4418 (2.2931)  weight_decay: 0.0500 (0.0500)  time: 0.4324  data: 0.0001  max mem: 42573
Epoch: [195]  [311/312]  eta: 0:00:00  lr: 0.001215  min_lr: 0.001215  loss: 2.4553 (2.2939)  weight_decay: 0.0500 (0.0500)  time: 0.4324  data: 0.0001  max mem: 42573
Epoch: [195] Total time: 0:02:28 (0.4747 s / it)
Averaged stats: lr: 0.001215  min_lr: 0.001215  loss: 2.4553 (2.3254)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:00:42  loss: 0.7066 (0.7066)  acc1: 81.7708 (81.7708)  acc5: 94.2708 (94.2708)  time: 4.6917  data: 4.5823  max mem: 42573
Test:  [8/9]  eta: 0:00:00  loss: 1.1168 (0.9980)  acc1: 74.2188 (74.6240)  acc5: 92.1875 (92.0960)  time: 0.5984  data: 0.5092  max mem: 42573
Test: Total time: 0:00:05 (0.6229 s / it)
* Acc@1 75.276 Acc@5 92.424 loss 0.996
Accuracy of the model on the 50000 test images: 75.3%
Max accuracy: 75.99%
Epoch: [196]  [  0/312]  eta: 0:50:45  lr: 0.001215  min_lr: 0.001215  loss: 2.4104 (2.4104)  weight_decay: 0.0500 (0.0500)  time: 9.7625  data: 6.1702  max mem: 42573
Epoch: [196]  [ 10/312]  eta: 0:07:26  lr: 0.001214  min_lr: 0.001214  loss: 2.5581 (2.4355)  weight_decay: 0.0500 (0.0500)  time: 1.4794  data: 0.6892  max mem: 42573
Epoch: [196]  [ 20/312]  eta: 0:04:46  lr: 0.001213  min_lr: 0.001213  loss: 2.5875 (2.4925)  weight_decay: 0.0500 (0.0500)  time: 0.5421  data: 0.0708  max mem: 42573
Epoch: [196]  [ 30/312]  eta: 0:03:46  lr: 0.001213  min_lr: 0.001213  loss: 2.5355 (2.4755)  weight_decay: 0.0500 (0.0500)  time: 0.4332  data: 0.0004  max mem: 42573
Epoch: [196]  [ 40/312]  eta: 0:03:14  lr: 0.001212  min_lr: 0.001212  loss: 2.3252 (2.3965)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [196]  [ 50/312]  eta: 0:02:52  lr: 0.001211  min_lr: 0.001211  loss: 2.1773 (2.3508)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [196]  [ 60/312]  eta: 0:02:36  lr: 0.001211  min_lr: 0.001211  loss: 2.2727 (2.3749)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [196]  [ 70/312]  eta: 0:02:24  lr: 0.001210  min_lr: 0.001210  loss: 2.4157 (2.3733)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [196]  [ 80/312]  eta: 0:02:13  lr: 0.001209  min_lr: 0.001209  loss: 2.2348 (2.3557)  weight_decay: 0.0500 (0.0500)  time: 0.4350  data: 0.0004  max mem: 42573
Epoch: [196]  [ 90/312]  eta: 0:02:04  lr: 0.001209  min_lr: 0.001209  loss: 2.3180 (2.3684)  weight_decay: 0.0500 (0.0500)  time: 0.4356  data: 0.0004  max mem: 42573
Epoch: [196]  [100/312]  eta: 0:01:56  lr: 0.001208  min_lr: 0.001208  loss: 2.2999 (2.3461)  weight_decay: 0.0500 (0.0500)  time: 0.4343  data: 0.0004  max mem: 42573
Epoch: [196]  [110/312]  eta: 0:01:48  lr: 0.001207  min_lr: 0.001207  loss: 2.2603 (2.3510)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [196]  [120/312]  eta: 0:01:41  lr: 0.001207  min_lr: 0.001207  loss: 2.4775 (2.3535)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [196]  [130/312]  eta: 0:01:34  lr: 0.001206  min_lr: 0.001206  loss: 2.4775 (2.3574)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [196]  [140/312]  eta: 0:01:28  lr: 0.001205  min_lr: 0.001205  loss: 2.4504 (2.3591)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [196]  [150/312]  eta: 0:01:22  lr: 0.001205  min_lr: 0.001205  loss: 2.4152 (2.3537)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [196]  [160/312]  eta: 0:01:16  lr: 0.001204  min_lr: 0.001204  loss: 2.3997 (2.3607)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [196]  [170/312]  eta: 0:01:11  lr: 0.001203  min_lr: 0.001203  loss: 2.4056 (2.3574)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [196]  [180/312]  eta: 0:01:05  lr: 0.001203  min_lr: 0.001203  loss: 2.2623 (2.3480)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [196]  [190/312]  eta: 0:01:00  lr: 0.001202  min_lr: 0.001202  loss: 2.3262 (2.3471)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [196]  [200/312]  eta: 0:00:54  lr: 0.001201  min_lr: 0.001201  loss: 2.3300 (2.3410)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0003  max mem: 42573
Epoch: [196]  [210/312]  eta: 0:00:49  lr: 0.001201  min_lr: 0.001201  loss: 2.4266 (2.3490)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0003  max mem: 42573
Epoch: [196]  [220/312]  eta: 0:00:44  lr: 0.001200  min_lr: 0.001200  loss: 2.5059 (2.3529)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [196]  [230/312]  eta: 0:00:39  lr: 0.001199  min_lr: 0.001199  loss: 2.5014 (2.3589)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [196]  [240/312]  eta: 0:00:34  lr: 0.001199  min_lr: 0.001199  loss: 2.3299 (2.3459)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [196]  [250/312]  eta: 0:00:29  lr: 0.001198  min_lr: 0.001198  loss: 2.0450 (2.3434)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [196]  [260/312]  eta: 0:00:24  lr: 0.001197  min_lr: 0.001197  loss: 2.2677 (2.3400)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [196]  [270/312]  eta: 0:00:20  lr: 0.001197  min_lr: 0.001197  loss: 2.4975 (2.3416)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [196]  [280/312]  eta: 0:00:15  lr: 0.001196  min_lr: 0.001196  loss: 2.5110 (2.3435)  weight_decay: 0.0500 (0.0500)  time: 0.4349  data: 0.0009  max mem: 42573
Epoch: [196]  [290/312]  eta: 0:00:10  lr: 0.001196  min_lr: 0.001196  loss: 2.5007 (2.3395)  weight_decay: 0.0500 (0.0500)  time: 0.4342  data: 0.0008  max mem: 42573
Epoch: [196]  [300/312]  eta: 0:00:05  lr: 0.001195  min_lr: 0.001195  loss: 2.3557 (2.3428)  weight_decay: 0.0500 (0.0500)  time: 0.4324  data: 0.0001  max mem: 42573
Epoch: [196]  [310/312]  eta: 0:00:00  lr: 0.001194  min_lr: 0.001194  loss: 2.3736 (2.3476)  weight_decay: 0.0500 (0.0500)  time: 0.4323  data: 0.0001  max mem: 42573
Epoch: [196]  [311/312]  eta: 0:00:00  lr: 0.001194  min_lr: 0.001194  loss: 2.3736 (2.3499)  weight_decay: 0.0500 (0.0500)  time: 0.4323  data: 0.0001  max mem: 42573
Epoch: [196] Total time: 0:02:27 (0.4736 s / it)
Averaged stats: lr: 0.001194  min_lr: 0.001194  loss: 2.3736 (2.3115)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:00:43  loss: 0.7240 (0.7240)  acc1: 82.2917 (82.2917)  acc5: 94.2708 (94.2708)  time: 4.8142  data: 4.7047  max mem: 42573
Test:  [8/9]  eta: 0:00:00  loss: 1.0009 (0.9683)  acc1: 74.2188 (75.0400)  acc5: 92.9688 (92.7360)  time: 0.6153  data: 0.5228  max mem: 42573
Test: Total time: 0:00:05 (0.6394 s / it)
* Acc@1 75.412 Acc@5 92.668 loss 0.966
Accuracy of the model on the 50000 test images: 75.4%
Max accuracy: 75.99%
Epoch: [197]  [  0/312]  eta: 0:50:43  lr: 0.001194  min_lr: 0.001194  loss: 1.5981 (1.5981)  weight_decay: 0.0500 (0.0500)  time: 9.7561  data: 7.2412  max mem: 42573
Epoch: [197]  [ 10/312]  eta: 0:07:42  lr: 0.001193  min_lr: 0.001193  loss: 2.4320 (2.3359)  weight_decay: 0.0500 (0.0500)  time: 1.5317  data: 0.8127  max mem: 42573
Epoch: [197]  [ 20/312]  eta: 0:04:54  lr: 0.001193  min_lr: 0.001193  loss: 2.1334 (2.2017)  weight_decay: 0.0500 (0.0500)  time: 0.5711  data: 0.0851  max mem: 42573
Epoch: [197]  [ 30/312]  eta: 0:03:52  lr: 0.001192  min_lr: 0.001192  loss: 2.1334 (2.2253)  weight_decay: 0.0500 (0.0500)  time: 0.4331  data: 0.0003  max mem: 42573
Epoch: [197]  [ 40/312]  eta: 0:03:17  lr: 0.001191  min_lr: 0.001191  loss: 2.2900 (2.2344)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [197]  [ 50/312]  eta: 0:02:55  lr: 0.001191  min_lr: 0.001191  loss: 2.2876 (2.2527)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [197]  [ 60/312]  eta: 0:02:39  lr: 0.001190  min_lr: 0.001190  loss: 2.3466 (2.2474)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [197]  [ 70/312]  eta: 0:02:26  lr: 0.001189  min_lr: 0.001189  loss: 2.4012 (2.2670)  weight_decay: 0.0500 (0.0500)  time: 0.4341  data: 0.0004  max mem: 42573
Epoch: [197]  [ 80/312]  eta: 0:02:15  lr: 0.001189  min_lr: 0.001189  loss: 2.3971 (2.2743)  weight_decay: 0.0500 (0.0500)  time: 0.4341  data: 0.0004  max mem: 42573
Epoch: [197]  [ 90/312]  eta: 0:02:05  lr: 0.001188  min_lr: 0.001188  loss: 2.3849 (2.2947)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [197]  [100/312]  eta: 0:01:57  lr: 0.001187  min_lr: 0.001187  loss: 2.2484 (2.2767)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [197]  [110/312]  eta: 0:01:49  lr: 0.001187  min_lr: 0.001187  loss: 2.2918 (2.2838)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [197]  [120/312]  eta: 0:01:42  lr: 0.001186  min_lr: 0.001186  loss: 2.3368 (2.2871)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [197]  [130/312]  eta: 0:01:35  lr: 0.001186  min_lr: 0.001186  loss: 2.3368 (2.2925)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [197]  [140/312]  eta: 0:01:29  lr: 0.001185  min_lr: 0.001185  loss: 2.3865 (2.3008)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [197]  [150/312]  eta: 0:01:23  lr: 0.001184  min_lr: 0.001184  loss: 2.3514 (2.3050)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0003  max mem: 42573
Epoch: [197]  [160/312]  eta: 0:01:17  lr: 0.001184  min_lr: 0.001184  loss: 2.2771 (2.3024)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [197]  [170/312]  eta: 0:01:11  lr: 0.001183  min_lr: 0.001183  loss: 2.1008 (2.2952)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [197]  [180/312]  eta: 0:01:06  lr: 0.001182  min_lr: 0.001182  loss: 2.3491 (2.2997)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0003  max mem: 42573
Epoch: [197]  [190/312]  eta: 0:01:00  lr: 0.001182  min_lr: 0.001182  loss: 2.4179 (2.2990)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [197]  [200/312]  eta: 0:00:55  lr: 0.001181  min_lr: 0.001181  loss: 2.5463 (2.3176)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [197]  [210/312]  eta: 0:00:50  lr: 0.001180  min_lr: 0.001180  loss: 2.4449 (2.3110)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [197]  [220/312]  eta: 0:00:44  lr: 0.001180  min_lr: 0.001180  loss: 2.2079 (2.3135)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [197]  [230/312]  eta: 0:00:39  lr: 0.001179  min_lr: 0.001179  loss: 2.2848 (2.3092)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [197]  [240/312]  eta: 0:00:34  lr: 0.001178  min_lr: 0.001178  loss: 2.2564 (2.3042)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [197]  [250/312]  eta: 0:00:29  lr: 0.001178  min_lr: 0.001178  loss: 2.1094 (2.2988)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0004  max mem: 42573
Epoch: [197]  [260/312]  eta: 0:00:24  lr: 0.001177  min_lr: 0.001177  loss: 2.1673 (2.2953)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [197]  [270/312]  eta: 0:00:20  lr: 0.001176  min_lr: 0.001176  loss: 2.3463 (2.2977)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [197]  [280/312]  eta: 0:00:15  lr: 0.001176  min_lr: 0.001176  loss: 2.4845 (2.3043)  weight_decay: 0.0500 (0.0500)  time: 0.4344  data: 0.0009  max mem: 42573
Epoch: [197]  [290/312]  eta: 0:00:10  lr: 0.001175  min_lr: 0.001175  loss: 2.4238 (2.3019)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0008  max mem: 42573
Epoch: [197]  [300/312]  eta: 0:00:05  lr: 0.001174  min_lr: 0.001174  loss: 2.2994 (2.2987)  weight_decay: 0.0500 (0.0500)  time: 0.4325  data: 0.0001  max mem: 42573
Epoch: [197]  [310/312]  eta: 0:00:00  lr: 0.001174  min_lr: 0.001174  loss: 2.4161 (2.2997)  weight_decay: 0.0500 (0.0500)  time: 0.4323  data: 0.0001  max mem: 42573
Epoch: [197]  [311/312]  eta: 0:00:00  lr: 0.001174  min_lr: 0.001174  loss: 2.4524 (2.3005)  weight_decay: 0.0500 (0.0500)  time: 0.4323  data: 0.0001  max mem: 42573
Epoch: [197] Total time: 0:02:28 (0.4753 s / it)
Averaged stats: lr: 0.001174  min_lr: 0.001174  loss: 2.4524 (2.3092)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:00:39  loss: 0.7126 (0.7126)  acc1: 83.5938 (83.5938)  acc5: 94.2708 (94.2708)  time: 4.3481  data: 4.2405  max mem: 42573
Test:  [8/9]  eta: 0:00:00  loss: 0.9636 (0.9479)  acc1: 76.0417 (75.6800)  acc5: 92.4479 (92.4800)  time: 0.5912  data: 0.4984  max mem: 42573
Test: Total time: 0:00:05 (0.6003 s / it)
* Acc@1 76.498 Acc@5 93.094 loss 0.934
Accuracy of the model on the 50000 test images: 76.5%
Max accuracy: 76.50%
Epoch: [198]  [  0/312]  eta: 0:51:28  lr: 0.001174  min_lr: 0.001174  loss: 1.7602 (1.7602)  weight_decay: 0.0500 (0.0500)  time: 9.8986  data: 7.1076  max mem: 42573
Epoch: [198]  [ 10/312]  eta: 0:07:21  lr: 0.001173  min_lr: 0.001173  loss: 2.3852 (2.2729)  weight_decay: 0.0500 (0.0500)  time: 1.4618  data: 0.7023  max mem: 42573
Epoch: [198]  [ 20/312]  eta: 0:04:43  lr: 0.001172  min_lr: 0.001172  loss: 2.1446 (2.1274)  weight_decay: 0.0500 (0.0500)  time: 0.5257  data: 0.0311  max mem: 42573
Epoch: [198]  [ 30/312]  eta: 0:03:45  lr: 0.001172  min_lr: 0.001172  loss: 2.1446 (2.2088)  weight_decay: 0.0500 (0.0500)  time: 0.4332  data: 0.0003  max mem: 42573
Epoch: [198]  [ 40/312]  eta: 0:03:12  lr: 0.001171  min_lr: 0.001171  loss: 2.2559 (2.1753)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0003  max mem: 42573
Epoch: [198]  [ 50/312]  eta: 0:02:51  lr: 0.001170  min_lr: 0.001170  loss: 2.1916 (2.1709)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [198]  [ 60/312]  eta: 0:02:35  lr: 0.001170  min_lr: 0.001170  loss: 2.2115 (2.1803)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [198]  [ 70/312]  eta: 0:02:23  lr: 0.001169  min_lr: 0.001169  loss: 2.2865 (2.2065)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [198]  [ 80/312]  eta: 0:02:12  lr: 0.001168  min_lr: 0.001168  loss: 2.2937 (2.2320)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [198]  [ 90/312]  eta: 0:02:03  lr: 0.001168  min_lr: 0.001168  loss: 2.3599 (2.2398)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [198]  [100/312]  eta: 0:01:55  lr: 0.001167  min_lr: 0.001167  loss: 2.2899 (2.2514)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [198]  [110/312]  eta: 0:01:48  lr: 0.001166  min_lr: 0.001166  loss: 2.2778 (2.2604)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0004  max mem: 42573
Epoch: [198]  [120/312]  eta: 0:01:41  lr: 0.001166  min_lr: 0.001166  loss: 2.3431 (2.2743)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0003  max mem: 42573
Epoch: [198]  [130/312]  eta: 0:01:34  lr: 0.001165  min_lr: 0.001165  loss: 2.3203 (2.2665)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0003  max mem: 42573
Epoch: [198]  [140/312]  eta: 0:01:28  lr: 0.001164  min_lr: 0.001164  loss: 2.0350 (2.2587)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [198]  [150/312]  eta: 0:01:22  lr: 0.001164  min_lr: 0.001164  loss: 2.2252 (2.2642)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [198]  [160/312]  eta: 0:01:16  lr: 0.001163  min_lr: 0.001163  loss: 2.4001 (2.2732)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [198]  [170/312]  eta: 0:01:10  lr: 0.001162  min_lr: 0.001162  loss: 2.2511 (2.2676)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [198]  [180/312]  eta: 0:01:05  lr: 0.001162  min_lr: 0.001162  loss: 2.2145 (2.2666)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [198]  [190/312]  eta: 0:01:00  lr: 0.001161  min_lr: 0.001161  loss: 2.3493 (2.2691)  weight_decay: 0.0500 (0.0500)  time: 0.4341  data: 0.0004  max mem: 42573
Epoch: [198]  [200/312]  eta: 0:00:54  lr: 0.001161  min_lr: 0.001161  loss: 2.3887 (2.2737)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0004  max mem: 42573
Epoch: [198]  [210/312]  eta: 0:00:49  lr: 0.001160  min_lr: 0.001160  loss: 2.4401 (2.2718)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [198]  [220/312]  eta: 0:00:44  lr: 0.001159  min_lr: 0.001159  loss: 2.4293 (2.2714)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [198]  [230/312]  eta: 0:00:39  lr: 0.001159  min_lr: 0.001159  loss: 2.3569 (2.2771)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [198]  [240/312]  eta: 0:00:34  lr: 0.001158  min_lr: 0.001158  loss: 2.3773 (2.2783)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [198]  [250/312]  eta: 0:00:29  lr: 0.001157  min_lr: 0.001157  loss: 2.3119 (2.2725)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [198]  [260/312]  eta: 0:00:24  lr: 0.001157  min_lr: 0.001157  loss: 2.2202 (2.2695)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [198]  [270/312]  eta: 0:00:19  lr: 0.001156  min_lr: 0.001156  loss: 2.2202 (2.2672)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0004  max mem: 42573
Epoch: [198]  [280/312]  eta: 0:00:15  lr: 0.001155  min_lr: 0.001155  loss: 2.2475 (2.2692)  weight_decay: 0.0500 (0.0500)  time: 0.4351  data: 0.0011  max mem: 42573
Epoch: [198]  [290/312]  eta: 0:00:10  lr: 0.001155  min_lr: 0.001155  loss: 2.3668 (2.2728)  weight_decay: 0.0500 (0.0500)  time: 0.4342  data: 0.0010  max mem: 42573
Epoch: [198]  [300/312]  eta: 0:00:05  lr: 0.001154  min_lr: 0.001154  loss: 2.3668 (2.2705)  weight_decay: 0.0500 (0.0500)  time: 0.4323  data: 0.0001  max mem: 42573
Epoch: [198]  [310/312]  eta: 0:00:00  lr: 0.001153  min_lr: 0.001153  loss: 2.2192 (2.2684)  weight_decay: 0.0500 (0.0500)  time: 0.4383  data: 0.0001  max mem: 42573
Epoch: [198]  [311/312]  eta: 0:00:00  lr: 0.001153  min_lr: 0.001153  loss: 2.2718 (2.2691)  weight_decay: 0.0500 (0.0500)  time: 0.4383  data: 0.0001  max mem: 42573
Epoch: [198] Total time: 0:02:27 (0.4731 s / it)
Averaged stats: lr: 0.001153  min_lr: 0.001153  loss: 2.2718 (2.2924)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:00:43  loss: 0.7295 (0.7295)  acc1: 81.2500 (81.2500)  acc5: 94.5312 (94.5312)  time: 4.7954  data: 4.6859  max mem: 42573
Test:  [8/9]  eta: 0:00:00  loss: 1.0008 (0.9522)  acc1: 76.3021 (75.5520)  acc5: 92.9688 (92.6400)  time: 0.6101  data: 0.5207  max mem: 42573
Test: Total time: 0:00:05 (0.6312 s / it)
* Acc@1 75.922 Acc@5 92.818 loss 0.948
Accuracy of the model on the 50000 test images: 75.9%
Max accuracy: 76.50%
Epoch: [199]  [  0/312]  eta: 0:51:53  lr: 0.001153  min_lr: 0.001153  loss: 2.2751 (2.2751)  weight_decay: 0.0500 (0.0500)  time: 9.9803  data: 7.8904  max mem: 42573
Epoch: [199]  [ 10/312]  eta: 0:07:21  lr: 0.001153  min_lr: 0.001153  loss: 2.3687 (2.2401)  weight_decay: 0.0500 (0.0500)  time: 1.4635  data: 0.7177  max mem: 42573
Epoch: [199]  [ 20/312]  eta: 0:04:44  lr: 0.001152  min_lr: 0.001152  loss: 2.3760 (2.3020)  weight_decay: 0.0500 (0.0500)  time: 0.5225  data: 0.0004  max mem: 42573
Epoch: [199]  [ 30/312]  eta: 0:03:45  lr: 0.001151  min_lr: 0.001151  loss: 2.0903 (2.2172)  weight_decay: 0.0500 (0.0500)  time: 0.4332  data: 0.0003  max mem: 42573
Epoch: [199]  [ 40/312]  eta: 0:03:13  lr: 0.001151  min_lr: 0.001151  loss: 2.0000 (2.1937)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0003  max mem: 42573
Epoch: [199]  [ 50/312]  eta: 0:02:51  lr: 0.001150  min_lr: 0.001150  loss: 2.3774 (2.2134)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0003  max mem: 42573
Epoch: [199]  [ 60/312]  eta: 0:02:36  lr: 0.001149  min_lr: 0.001149  loss: 2.3993 (2.2296)  weight_decay: 0.0500 (0.0500)  time: 0.4343  data: 0.0003  max mem: 42573
Epoch: [199]  [ 70/312]  eta: 0:02:23  lr: 0.001149  min_lr: 0.001149  loss: 2.3608 (2.2389)  weight_decay: 0.0500 (0.0500)  time: 0.4341  data: 0.0004  max mem: 42573
Epoch: [199]  [ 80/312]  eta: 0:02:13  lr: 0.001148  min_lr: 0.001148  loss: 2.3439 (2.2573)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [199]  [ 90/312]  eta: 0:02:03  lr: 0.001147  min_lr: 0.001147  loss: 2.3655 (2.2488)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0003  max mem: 42573
Epoch: [199]  [100/312]  eta: 0:01:55  lr: 0.001147  min_lr: 0.001147  loss: 2.3655 (2.2502)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0004  max mem: 42573
Epoch: [199]  [110/312]  eta: 0:01:48  lr: 0.001146  min_lr: 0.001146  loss: 2.4057 (2.2534)  weight_decay: 0.0500 (0.0500)  time: 0.4341  data: 0.0004  max mem: 42573
Epoch: [199]  [120/312]  eta: 0:01:41  lr: 0.001145  min_lr: 0.001145  loss: 2.3707 (2.2507)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [199]  [130/312]  eta: 0:01:34  lr: 0.001145  min_lr: 0.001145  loss: 2.4060 (2.2537)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [199]  [140/312]  eta: 0:01:28  lr: 0.001144  min_lr: 0.001144  loss: 2.3349 (2.2464)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0003  max mem: 42573
Epoch: [199]  [150/312]  eta: 0:01:22  lr: 0.001143  min_lr: 0.001143  loss: 2.2852 (2.2509)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0003  max mem: 42573
Epoch: [199]  [160/312]  eta: 0:01:16  lr: 0.001143  min_lr: 0.001143  loss: 2.2776 (2.2551)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0003  max mem: 42573
Epoch: [199]  [170/312]  eta: 0:01:11  lr: 0.001142  min_lr: 0.001142  loss: 2.2383 (2.2527)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [199]  [180/312]  eta: 0:01:05  lr: 0.001142  min_lr: 0.001142  loss: 2.2041 (2.2471)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0003  max mem: 42573
Epoch: [199]  [190/312]  eta: 0:01:00  lr: 0.001141  min_lr: 0.001141  loss: 2.3670 (2.2547)  weight_decay: 0.0500 (0.0500)  time: 0.4341  data: 0.0003  max mem: 42573
Epoch: [199]  [200/312]  eta: 0:00:54  lr: 0.001140  min_lr: 0.001140  loss: 2.5111 (2.2629)  weight_decay: 0.0500 (0.0500)  time: 0.4341  data: 0.0004  max mem: 42573
Epoch: [199]  [210/312]  eta: 0:00:49  lr: 0.001140  min_lr: 0.001140  loss: 2.4253 (2.2575)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [199]  [220/312]  eta: 0:00:44  lr: 0.001139  min_lr: 0.001139  loss: 2.4280 (2.2652)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0005  max mem: 42573
Epoch: [199]  [230/312]  eta: 0:00:39  lr: 0.001138  min_lr: 0.001138  loss: 2.4577 (2.2688)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [199]  [240/312]  eta: 0:00:34  lr: 0.001138  min_lr: 0.001138  loss: 2.4280 (2.2698)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [199]  [250/312]  eta: 0:00:29  lr: 0.001137  min_lr: 0.001137  loss: 2.3954 (2.2723)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [199]  [260/312]  eta: 0:00:24  lr: 0.001136  min_lr: 0.001136  loss: 2.3954 (2.2717)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [199]  [270/312]  eta: 0:00:19  lr: 0.001136  min_lr: 0.001136  loss: 2.3551 (2.2767)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [199]  [280/312]  eta: 0:00:15  lr: 0.001135  min_lr: 0.001135  loss: 2.4035 (2.2810)  weight_decay: 0.0500 (0.0500)  time: 0.4346  data: 0.0010  max mem: 42573
Epoch: [199]  [290/312]  eta: 0:00:10  lr: 0.001134  min_lr: 0.001134  loss: 2.4251 (2.2877)  weight_decay: 0.0500 (0.0500)  time: 0.4353  data: 0.0008  max mem: 42573
Epoch: [199]  [300/312]  eta: 0:00:05  lr: 0.001134  min_lr: 0.001134  loss: 2.4094 (2.2852)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0001  max mem: 42573
Epoch: [199]  [310/312]  eta: 0:00:00  lr: 0.001133  min_lr: 0.001133  loss: 2.1040 (2.2760)  weight_decay: 0.0500 (0.0500)  time: 0.4323  data: 0.0001  max mem: 42573
Epoch: [199]  [311/312]  eta: 0:00:00  lr: 0.001133  min_lr: 0.001133  loss: 2.1040 (2.2773)  weight_decay: 0.0500 (0.0500)  time: 0.4323  data: 0.0001  max mem: 42573
Epoch: [199] Total time: 0:02:27 (0.4731 s / it)
Averaged stats: lr: 0.001133  min_lr: 0.001133  loss: 2.1040 (2.2943)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:00:44  loss: 0.6670 (0.6670)  acc1: 84.3750 (84.3750)  acc5: 95.3125 (95.3125)  time: 4.9080  data: 4.7985  max mem: 42573
Test:  [8/9]  eta: 0:00:00  loss: 1.0054 (0.9520)  acc1: 76.3021 (75.8720)  acc5: 92.4479 (92.7040)  time: 0.6224  data: 0.5332  max mem: 42573
Test: Total time: 0:00:05 (0.6469 s / it)
* Acc@1 76.328 Acc@5 92.832 loss 0.934
Accuracy of the model on the 50000 test images: 76.3%
Max accuracy: 76.50%
Epoch: [200]  [  0/312]  eta: 0:48:47  lr: 0.001133  min_lr: 0.001133  loss: 2.4746 (2.4746)  weight_decay: 0.0500 (0.0500)  time: 9.3821  data: 6.1034  max mem: 42573
Epoch: [200]  [ 10/312]  eta: 0:07:17  lr: 0.001132  min_lr: 0.001132  loss: 2.4958 (2.5565)  weight_decay: 0.0500 (0.0500)  time: 1.4476  data: 0.7119  max mem: 42573
Epoch: [200]  [ 20/312]  eta: 0:04:41  lr: 0.001132  min_lr: 0.001132  loss: 2.4700 (2.3544)  weight_decay: 0.0500 (0.0500)  time: 0.5438  data: 0.0866  max mem: 42573
Epoch: [200]  [ 30/312]  eta: 0:03:43  lr: 0.001131  min_lr: 0.001131  loss: 2.4065 (2.3698)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0003  max mem: 42573
Epoch: [200]  [ 40/312]  eta: 0:03:11  lr: 0.001130  min_lr: 0.001130  loss: 2.4144 (2.3328)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [200]  [ 50/312]  eta: 0:02:50  lr: 0.001130  min_lr: 0.001130  loss: 2.4144 (2.3409)  weight_decay: 0.0500 (0.0500)  time: 0.4332  data: 0.0004  max mem: 42573
Epoch: [200]  [ 60/312]  eta: 0:02:35  lr: 0.001129  min_lr: 0.001129  loss: 2.3437 (2.3114)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [200]  [ 70/312]  eta: 0:02:22  lr: 0.001128  min_lr: 0.001128  loss: 2.2010 (2.2866)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [200]  [ 80/312]  eta: 0:02:12  lr: 0.001128  min_lr: 0.001128  loss: 2.1208 (2.2763)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [200]  [ 90/312]  eta: 0:02:03  lr: 0.001127  min_lr: 0.001127  loss: 2.2372 (2.2902)  weight_decay: 0.0500 (0.0500)  time: 0.4343  data: 0.0004  max mem: 42573
Epoch: [200]  [100/312]  eta: 0:01:55  lr: 0.001126  min_lr: 0.001126  loss: 2.2662 (2.2906)  weight_decay: 0.0500 (0.0500)  time: 0.4343  data: 0.0004  max mem: 42573
Epoch: [200]  [110/312]  eta: 0:01:47  lr: 0.001126  min_lr: 0.001126  loss: 2.4503 (2.3067)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0004  max mem: 42573
Epoch: [200]  [120/312]  eta: 0:01:40  lr: 0.001125  min_lr: 0.001125  loss: 2.5097 (2.3149)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [200]  [130/312]  eta: 0:01:34  lr: 0.001125  min_lr: 0.001125  loss: 2.2191 (2.3059)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0003  max mem: 42573
Epoch: [200]  [140/312]  eta: 0:01:28  lr: 0.001124  min_lr: 0.001124  loss: 2.2852 (2.3211)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0003  max mem: 42573
Epoch: [200]  [150/312]  eta: 0:01:22  lr: 0.001123  min_lr: 0.001123  loss: 2.4805 (2.3285)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [200]  [160/312]  eta: 0:01:16  lr: 0.001123  min_lr: 0.001123  loss: 2.4154 (2.3334)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [200]  [170/312]  eta: 0:01:10  lr: 0.001122  min_lr: 0.001122  loss: 2.4154 (2.3334)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0003  max mem: 42573
Epoch: [200]  [180/312]  eta: 0:01:05  lr: 0.001121  min_lr: 0.001121  loss: 2.4047 (2.3370)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [200]  [190/312]  eta: 0:01:00  lr: 0.001121  min_lr: 0.001121  loss: 2.4047 (2.3325)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [200]  [200/312]  eta: 0:00:54  lr: 0.001120  min_lr: 0.001120  loss: 2.2907 (2.3259)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [200]  [210/312]  eta: 0:00:49  lr: 0.001119  min_lr: 0.001119  loss: 2.2907 (2.3162)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0004  max mem: 42573
Epoch: [200]  [220/312]  eta: 0:00:44  lr: 0.001119  min_lr: 0.001119  loss: 2.3250 (2.3149)  weight_decay: 0.0500 (0.0500)  time: 0.4341  data: 0.0003  max mem: 42573
Epoch: [200]  [230/312]  eta: 0:00:39  lr: 0.001118  min_lr: 0.001118  loss: 2.3977 (2.3169)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0003  max mem: 42573
Epoch: [200]  [240/312]  eta: 0:00:34  lr: 0.001117  min_lr: 0.001117  loss: 2.4069 (2.3181)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0003  max mem: 42573
Epoch: [200]  [250/312]  eta: 0:00:29  lr: 0.001117  min_lr: 0.001117  loss: 2.3518 (2.3159)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0003  max mem: 42573
Epoch: [200]  [260/312]  eta: 0:00:24  lr: 0.001116  min_lr: 0.001116  loss: 2.3314 (2.3179)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0003  max mem: 42573
Epoch: [200]  [270/312]  eta: 0:00:19  lr: 0.001115  min_lr: 0.001115  loss: 2.4149 (2.3155)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0003  max mem: 42573
Epoch: [200]  [280/312]  eta: 0:00:15  lr: 0.001115  min_lr: 0.001115  loss: 2.4503 (2.3177)  weight_decay: 0.0500 (0.0500)  time: 0.4344  data: 0.0010  max mem: 42573
Epoch: [200]  [290/312]  eta: 0:00:10  lr: 0.001114  min_lr: 0.001114  loss: 2.3429 (2.3114)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0008  max mem: 42573
Epoch: [200]  [300/312]  eta: 0:00:05  lr: 0.001114  min_lr: 0.001114  loss: 2.2122 (2.3111)  weight_decay: 0.0500 (0.0500)  time: 0.4326  data: 0.0001  max mem: 42573
Epoch: [200]  [310/312]  eta: 0:00:00  lr: 0.001113  min_lr: 0.001113  loss: 2.3628 (2.3093)  weight_decay: 0.0500 (0.0500)  time: 0.4325  data: 0.0001  max mem: 42573
Epoch: [200]  [311/312]  eta: 0:00:00  lr: 0.001113  min_lr: 0.001113  loss: 2.2122 (2.3079)  weight_decay: 0.0500 (0.0500)  time: 0.4325  data: 0.0001  max mem: 42573
Epoch: [200] Total time: 0:02:27 (0.4724 s / it)
Averaged stats: lr: 0.001113  min_lr: 0.001113  loss: 2.2122 (2.2958)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:00:42  loss: 0.7392 (0.7392)  acc1: 81.2500 (81.2500)  acc5: 95.5729 (95.5729)  time: 4.7217  data: 4.6129  max mem: 42573
Test:  [8/9]  eta: 0:00:00  loss: 1.0009 (0.9531)  acc1: 75.7812 (74.9760)  acc5: 93.2292 (92.6400)  time: 0.6018  data: 0.5126  max mem: 42573
Test: Total time: 0:00:05 (0.6244 s / it)
* Acc@1 76.146 Acc@5 92.826 loss 0.939
Accuracy of the model on the 50000 test images: 76.1%
Max accuracy: 76.50%
Epoch: [201]  [  0/312]  eta: 0:49:55  lr: 0.001113  min_lr: 0.001113  loss: 2.5199 (2.5199)  weight_decay: 0.0500 (0.0500)  time: 9.6003  data: 7.3913  max mem: 42573
Epoch: [201]  [ 10/312]  eta: 0:07:34  lr: 0.001112  min_lr: 0.001112  loss: 2.4028 (2.1975)  weight_decay: 0.0500 (0.0500)  time: 1.5044  data: 0.6724  max mem: 42573
Epoch: [201]  [ 20/312]  eta: 0:04:50  lr: 0.001112  min_lr: 0.001112  loss: 2.1657 (2.1447)  weight_decay: 0.0500 (0.0500)  time: 0.5641  data: 0.0004  max mem: 42573
Epoch: [201]  [ 30/312]  eta: 0:03:49  lr: 0.001111  min_lr: 0.001111  loss: 2.1657 (2.1599)  weight_decay: 0.0500 (0.0500)  time: 0.4332  data: 0.0004  max mem: 42573
Epoch: [201]  [ 40/312]  eta: 0:03:16  lr: 0.001110  min_lr: 0.001110  loss: 2.2226 (2.1672)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [201]  [ 50/312]  eta: 0:02:54  lr: 0.001110  min_lr: 0.001110  loss: 2.2668 (2.1844)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [201]  [ 60/312]  eta: 0:02:37  lr: 0.001109  min_lr: 0.001109  loss: 2.2668 (2.1931)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [201]  [ 70/312]  eta: 0:02:25  lr: 0.001108  min_lr: 0.001108  loss: 2.1847 (2.2021)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [201]  [ 80/312]  eta: 0:02:14  lr: 0.001108  min_lr: 0.001108  loss: 2.3754 (2.2172)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0003  max mem: 42573
Epoch: [201]  [ 90/312]  eta: 0:02:05  lr: 0.001107  min_lr: 0.001107  loss: 2.3754 (2.2400)  weight_decay: 0.0500 (0.0500)  time: 0.4342  data: 0.0004  max mem: 42573
Epoch: [201]  [100/312]  eta: 0:01:56  lr: 0.001106  min_lr: 0.001106  loss: 2.4390 (2.2556)  weight_decay: 0.0500 (0.0500)  time: 0.4343  data: 0.0004  max mem: 42573
Epoch: [201]  [110/312]  eta: 0:01:49  lr: 0.001106  min_lr: 0.001106  loss: 2.3807 (2.2566)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0004  max mem: 42573
Epoch: [201]  [120/312]  eta: 0:01:41  lr: 0.001105  min_lr: 0.001105  loss: 2.2644 (2.2477)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [201]  [130/312]  eta: 0:01:35  lr: 0.001104  min_lr: 0.001104  loss: 2.2758 (2.2426)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0004  max mem: 42573
Epoch: [201]  [140/312]  eta: 0:01:28  lr: 0.001104  min_lr: 0.001104  loss: 2.2773 (2.2454)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [201]  [150/312]  eta: 0:01:22  lr: 0.001103  min_lr: 0.001103  loss: 2.2913 (2.2428)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [201]  [160/312]  eta: 0:01:17  lr: 0.001102  min_lr: 0.001102  loss: 2.2663 (2.2470)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [201]  [170/312]  eta: 0:01:11  lr: 0.001102  min_lr: 0.001102  loss: 2.1916 (2.2411)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0003  max mem: 42573
Epoch: [201]  [180/312]  eta: 0:01:05  lr: 0.001101  min_lr: 0.001101  loss: 2.1916 (2.2434)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0003  max mem: 42573
Epoch: [201]  [190/312]  eta: 0:01:00  lr: 0.001101  min_lr: 0.001101  loss: 2.3064 (2.2354)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [201]  [200/312]  eta: 0:00:55  lr: 0.001100  min_lr: 0.001100  loss: 2.2891 (2.2411)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [201]  [210/312]  eta: 0:00:49  lr: 0.001099  min_lr: 0.001099  loss: 2.5066 (2.2488)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [201]  [220/312]  eta: 0:00:44  lr: 0.001099  min_lr: 0.001099  loss: 2.4797 (2.2542)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [201]  [230/312]  eta: 0:00:39  lr: 0.001098  min_lr: 0.001098  loss: 2.3908 (2.2577)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [201]  [240/312]  eta: 0:00:34  lr: 0.001097  min_lr: 0.001097  loss: 2.3727 (2.2584)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [201]  [250/312]  eta: 0:00:29  lr: 0.001097  min_lr: 0.001097  loss: 2.4558 (2.2623)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [201]  [260/312]  eta: 0:00:24  lr: 0.001096  min_lr: 0.001096  loss: 2.4699 (2.2636)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0003  max mem: 42573
Epoch: [201]  [270/312]  eta: 0:00:20  lr: 0.001095  min_lr: 0.001095  loss: 2.3489 (2.2660)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0003  max mem: 42573
Epoch: [201]  [280/312]  eta: 0:00:15  lr: 0.001095  min_lr: 0.001095  loss: 2.4341 (2.2746)  weight_decay: 0.0500 (0.0500)  time: 0.4351  data: 0.0018  max mem: 42573
Epoch: [201]  [290/312]  eta: 0:00:10  lr: 0.001094  min_lr: 0.001094  loss: 2.2404 (2.2645)  weight_decay: 0.0500 (0.0500)  time: 0.4345  data: 0.0016  max mem: 42573
Epoch: [201]  [300/312]  eta: 0:00:05  lr: 0.001094  min_lr: 0.001094  loss: 2.2108 (2.2653)  weight_decay: 0.0500 (0.0500)  time: 0.4325  data: 0.0001  max mem: 42573
Epoch: [201]  [310/312]  eta: 0:00:00  lr: 0.001093  min_lr: 0.001093  loss: 2.2828 (2.2659)  weight_decay: 0.0500 (0.0500)  time: 0.4324  data: 0.0001  max mem: 42573
Epoch: [201]  [311/312]  eta: 0:00:00  lr: 0.001093  min_lr: 0.001093  loss: 2.2828 (2.2653)  weight_decay: 0.0500 (0.0500)  time: 0.4324  data: 0.0001  max mem: 42573
Epoch: [201] Total time: 0:02:28 (0.4744 s / it)
Averaged stats: lr: 0.001093  min_lr: 0.001093  loss: 2.2828 (2.2977)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:00:42  loss: 0.7238 (0.7238)  acc1: 84.3750 (84.3750)  acc5: 94.2708 (94.2708)  time: 4.7704  data: 4.6609  max mem: 42573
Test:  [8/9]  eta: 0:00:00  loss: 0.9722 (0.9316)  acc1: 75.7812 (75.7760)  acc5: 92.7083 (92.6080)  time: 0.6066  data: 0.5179  max mem: 42573
Test: Total time: 0:00:05 (0.6188 s / it)
* Acc@1 76.582 Acc@5 93.068 loss 0.918
Accuracy of the model on the 50000 test images: 76.6%
Max accuracy: 76.58%
Epoch: [202]  [  0/312]  eta: 0:51:16  lr: 0.001093  min_lr: 0.001093  loss: 2.8074 (2.8074)  weight_decay: 0.0500 (0.0500)  time: 9.8604  data: 9.3757  max mem: 42573
Epoch: [202]  [ 10/312]  eta: 0:07:22  lr: 0.001092  min_lr: 0.001092  loss: 2.3698 (2.2116)  weight_decay: 0.0500 (0.0500)  time: 1.4646  data: 0.8527  max mem: 42573
Epoch: [202]  [ 20/312]  eta: 0:04:44  lr: 0.001091  min_lr: 0.001091  loss: 2.2983 (2.2388)  weight_decay: 0.0500 (0.0500)  time: 0.5291  data: 0.0004  max mem: 42573
Epoch: [202]  [ 30/312]  eta: 0:03:45  lr: 0.001091  min_lr: 0.001091  loss: 2.2983 (2.2447)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0003  max mem: 42573
Epoch: [202]  [ 40/312]  eta: 0:03:13  lr: 0.001090  min_lr: 0.001090  loss: 2.3581 (2.2677)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0003  max mem: 42573
Epoch: [202]  [ 50/312]  eta: 0:02:51  lr: 0.001090  min_lr: 0.001090  loss: 2.3873 (2.2971)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0003  max mem: 42573
Epoch: [202]  [ 60/312]  eta: 0:02:36  lr: 0.001089  min_lr: 0.001089  loss: 2.3769 (2.2898)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [202]  [ 70/312]  eta: 0:02:23  lr: 0.001088  min_lr: 0.001088  loss: 2.2908 (2.2912)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [202]  [ 80/312]  eta: 0:02:13  lr: 0.001088  min_lr: 0.001088  loss: 2.3281 (2.2853)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [202]  [ 90/312]  eta: 0:02:03  lr: 0.001087  min_lr: 0.001087  loss: 2.2805 (2.2702)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [202]  [100/312]  eta: 0:01:55  lr: 0.001086  min_lr: 0.001086  loss: 2.2805 (2.2706)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [202]  [110/312]  eta: 0:01:48  lr: 0.001086  min_lr: 0.001086  loss: 2.3182 (2.2732)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0005  max mem: 42573
Epoch: [202]  [120/312]  eta: 0:01:41  lr: 0.001085  min_lr: 0.001085  loss: 2.0649 (2.2461)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [202]  [130/312]  eta: 0:01:34  lr: 0.001084  min_lr: 0.001084  loss: 2.1403 (2.2531)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [202]  [140/312]  eta: 0:01:28  lr: 0.001084  min_lr: 0.001084  loss: 2.4581 (2.2711)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [202]  [150/312]  eta: 0:01:22  lr: 0.001083  min_lr: 0.001083  loss: 2.4496 (2.2762)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [202]  [160/312]  eta: 0:01:16  lr: 0.001083  min_lr: 0.001083  loss: 2.2232 (2.2702)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [202]  [170/312]  eta: 0:01:11  lr: 0.001082  min_lr: 0.001082  loss: 2.2088 (2.2719)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0004  max mem: 42573
Epoch: [202]  [180/312]  eta: 0:01:05  lr: 0.001081  min_lr: 0.001081  loss: 2.3909 (2.2748)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [202]  [190/312]  eta: 0:01:00  lr: 0.001081  min_lr: 0.001081  loss: 2.0925 (2.2688)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [202]  [200/312]  eta: 0:00:54  lr: 0.001080  min_lr: 0.001080  loss: 2.0925 (2.2660)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0003  max mem: 42573
Epoch: [202]  [210/312]  eta: 0:00:49  lr: 0.001079  min_lr: 0.001079  loss: 2.3558 (2.2768)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [202]  [220/312]  eta: 0:00:44  lr: 0.001079  min_lr: 0.001079  loss: 2.3895 (2.2730)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [202]  [230/312]  eta: 0:00:39  lr: 0.001078  min_lr: 0.001078  loss: 2.1540 (2.2692)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0003  max mem: 42573
Epoch: [202]  [240/312]  eta: 0:00:34  lr: 0.001077  min_lr: 0.001077  loss: 2.2881 (2.2758)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [202]  [250/312]  eta: 0:00:29  lr: 0.001077  min_lr: 0.001077  loss: 2.2711 (2.2696)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [202]  [260/312]  eta: 0:00:24  lr: 0.001076  min_lr: 0.001076  loss: 2.2711 (2.2748)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [202]  [270/312]  eta: 0:00:19  lr: 0.001075  min_lr: 0.001075  loss: 2.6221 (2.2839)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [202]  [280/312]  eta: 0:00:15  lr: 0.001075  min_lr: 0.001075  loss: 2.3461 (2.2811)  weight_decay: 0.0500 (0.0500)  time: 0.4342  data: 0.0009  max mem: 42573
Epoch: [202]  [290/312]  eta: 0:00:10  lr: 0.001074  min_lr: 0.001074  loss: 2.4967 (2.2885)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0008  max mem: 42573
Epoch: [202]  [300/312]  eta: 0:00:05  lr: 0.001074  min_lr: 0.001074  loss: 2.4967 (2.2892)  weight_decay: 0.0500 (0.0500)  time: 0.4324  data: 0.0001  max mem: 42573
Epoch: [202]  [310/312]  eta: 0:00:00  lr: 0.001073  min_lr: 0.001073  loss: 2.2612 (2.2908)  weight_decay: 0.0500 (0.0500)  time: 0.4323  data: 0.0001  max mem: 42573
Epoch: [202]  [311/312]  eta: 0:00:00  lr: 0.001073  min_lr: 0.001073  loss: 2.2612 (2.2924)  weight_decay: 0.0500 (0.0500)  time: 0.4323  data: 0.0001  max mem: 42573
Epoch: [202] Total time: 0:02:27 (0.4730 s / it)
Averaged stats: lr: 0.001073  min_lr: 0.001073  loss: 2.2612 (2.2881)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:00:43  loss: 0.7053 (0.7053)  acc1: 82.8125 (82.8125)  acc5: 95.0521 (95.0521)  time: 4.8706  data: 4.7610  max mem: 42573
Test:  [8/9]  eta: 0:00:00  loss: 0.9986 (0.9297)  acc1: 74.4792 (75.6800)  acc5: 94.5312 (92.8960)  time: 0.6171  data: 0.5290  max mem: 42573
Test: Total time: 0:00:05 (0.6388 s / it)
* Acc@1 76.284 Acc@5 93.014 loss 0.929
Accuracy of the model on the 50000 test images: 76.3%
Max accuracy: 76.58%
Epoch: [203]  [  0/312]  eta: 0:53:06  lr: 0.001073  min_lr: 0.001073  loss: 2.2200 (2.2200)  weight_decay: 0.0500 (0.0500)  time: 10.2132  data: 7.6710  max mem: 42573
Epoch: [203]  [ 10/312]  eta: 0:07:37  lr: 0.001072  min_lr: 0.001072  loss: 2.2496 (2.2802)  weight_decay: 0.0500 (0.0500)  time: 1.5142  data: 0.7993  max mem: 42573
Epoch: [203]  [ 20/312]  eta: 0:04:51  lr: 0.001072  min_lr: 0.001072  loss: 2.2496 (2.3074)  weight_decay: 0.0500 (0.0500)  time: 0.5387  data: 0.0562  max mem: 42573
Epoch: [203]  [ 30/312]  eta: 0:03:50  lr: 0.001071  min_lr: 0.001071  loss: 2.2447 (2.2896)  weight_decay: 0.0500 (0.0500)  time: 0.4332  data: 0.0004  max mem: 42573
Epoch: [203]  [ 40/312]  eta: 0:03:16  lr: 0.001070  min_lr: 0.001070  loss: 2.2447 (2.2520)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [203]  [ 50/312]  eta: 0:02:54  lr: 0.001070  min_lr: 0.001070  loss: 2.1770 (2.2330)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [203]  [ 60/312]  eta: 0:02:38  lr: 0.001069  min_lr: 0.001069  loss: 2.2460 (2.2370)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [203]  [ 70/312]  eta: 0:02:25  lr: 0.001068  min_lr: 0.001068  loss: 2.4070 (2.2653)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [203]  [ 80/312]  eta: 0:02:14  lr: 0.001068  min_lr: 0.001068  loss: 2.4511 (2.2745)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [203]  [ 90/312]  eta: 0:02:05  lr: 0.001067  min_lr: 0.001067  loss: 2.2025 (2.2646)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [203]  [100/312]  eta: 0:01:56  lr: 0.001066  min_lr: 0.001066  loss: 2.2039 (2.2768)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [203]  [110/312]  eta: 0:01:49  lr: 0.001066  min_lr: 0.001066  loss: 2.4910 (2.2905)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [203]  [120/312]  eta: 0:01:42  lr: 0.001065  min_lr: 0.001065  loss: 2.3746 (2.2850)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [203]  [130/312]  eta: 0:01:35  lr: 0.001065  min_lr: 0.001065  loss: 2.1870 (2.2746)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [203]  [140/312]  eta: 0:01:29  lr: 0.001064  min_lr: 0.001064  loss: 2.1009 (2.2652)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [203]  [150/312]  eta: 0:01:22  lr: 0.001063  min_lr: 0.001063  loss: 2.3602 (2.2809)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [203]  [160/312]  eta: 0:01:17  lr: 0.001063  min_lr: 0.001063  loss: 2.4949 (2.2867)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0004  max mem: 42573
Epoch: [203]  [170/312]  eta: 0:01:11  lr: 0.001062  min_lr: 0.001062  loss: 2.4535 (2.2924)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [203]  [180/312]  eta: 0:01:05  lr: 0.001061  min_lr: 0.001061  loss: 2.4535 (2.2969)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [203]  [190/312]  eta: 0:01:00  lr: 0.001061  min_lr: 0.001061  loss: 2.4398 (2.3090)  weight_decay: 0.0500 (0.0500)  time: 0.4365  data: 0.0004  max mem: 42573
Epoch: [203]  [200/312]  eta: 0:00:55  lr: 0.001060  min_lr: 0.001060  loss: 2.4364 (2.3133)  weight_decay: 0.0500 (0.0500)  time: 0.4363  data: 0.0004  max mem: 42573
Epoch: [203]  [210/312]  eta: 0:00:50  lr: 0.001059  min_lr: 0.001059  loss: 2.3406 (2.3070)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [203]  [220/312]  eta: 0:00:44  lr: 0.001059  min_lr: 0.001059  loss: 2.3207 (2.3073)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [203]  [230/312]  eta: 0:00:39  lr: 0.001058  min_lr: 0.001058  loss: 2.3070 (2.3069)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [203]  [240/312]  eta: 0:00:34  lr: 0.001058  min_lr: 0.001058  loss: 2.3227 (2.3094)  weight_decay: 0.0500 (0.0500)  time: 0.4342  data: 0.0004  max mem: 42573
Epoch: [203]  [250/312]  eta: 0:00:29  lr: 0.001057  min_lr: 0.001057  loss: 2.3227 (2.3063)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0004  max mem: 42573
Epoch: [203]  [260/312]  eta: 0:00:24  lr: 0.001056  min_lr: 0.001056  loss: 2.3058 (2.3086)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [203]  [270/312]  eta: 0:00:20  lr: 0.001056  min_lr: 0.001056  loss: 2.4560 (2.3151)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0003  max mem: 42573
Epoch: [203]  [280/312]  eta: 0:00:15  lr: 0.001055  min_lr: 0.001055  loss: 2.4499 (2.3134)  weight_decay: 0.0500 (0.0500)  time: 0.4354  data: 0.0009  max mem: 42573
Epoch: [203]  [290/312]  eta: 0:00:10  lr: 0.001054  min_lr: 0.001054  loss: 2.3981 (2.3102)  weight_decay: 0.0500 (0.0500)  time: 0.4347  data: 0.0008  max mem: 42573
Epoch: [203]  [300/312]  eta: 0:00:05  lr: 0.001054  min_lr: 0.001054  loss: 2.4246 (2.3139)  weight_decay: 0.0500 (0.0500)  time: 0.4323  data: 0.0001  max mem: 42573
Epoch: [203]  [310/312]  eta: 0:00:00  lr: 0.001053  min_lr: 0.001053  loss: 2.4312 (2.3094)  weight_decay: 0.0500 (0.0500)  time: 0.4323  data: 0.0001  max mem: 42573
Epoch: [203]  [311/312]  eta: 0:00:00  lr: 0.001053  min_lr: 0.001053  loss: 2.4312 (2.3064)  weight_decay: 0.0500 (0.0500)  time: 0.4323  data: 0.0001  max mem: 42573
Epoch: [203] Total time: 0:02:28 (0.4749 s / it)
Averaged stats: lr: 0.001053  min_lr: 0.001053  loss: 2.4312 (2.2736)  weight_decay: 0.0500 (0.0500)
Epoch: [204]  [  0/312]  eta: 4:52:03  lr: 0.001053  min_lr: 0.001053  loss: 2.9953 (2.9953)  weight_decay: 0.0500 (0.0500)  time: 56.1650  data: 13.4057  max mem: 42573
Epoch: [204]  [ 10/312]  eta: 0:31:42  lr: 0.001052  min_lr: 0.001052  loss: 2.5745 (2.5635)  weight_decay: 0.0500 (0.0500)  time: 6.3011  data: 1.2191  max mem: 42573
Epoch: [204]  [ 20/312]  eta: 0:18:17  lr: 0.001052  min_lr: 0.001052  loss: 2.4460 (2.4603)  weight_decay: 0.0500 (0.0500)  time: 1.1381  data: 0.0005  max mem: 42573
Epoch: [204]  [ 30/312]  eta: 0:12:47  lr: 0.001051  min_lr: 0.001051  loss: 2.3832 (2.4680)  weight_decay: 0.0500 (0.0500)  time: 0.7510  data: 0.0005  max mem: 42573
Epoch: [204]  [ 40/312]  eta: 0:09:48  lr: 0.001050  min_lr: 0.001050  loss: 2.3832 (2.4161)  weight_decay: 0.0500 (0.0500)  time: 0.4876  data: 0.0005  max mem: 42573
Epoch: [204]  [ 50/312]  eta: 0:07:57  lr: 0.001050  min_lr: 0.001050  loss: 2.3682 (2.4065)  weight_decay: 0.0500 (0.0500)  time: 0.4348  data: 0.0004  max mem: 42573
Epoch: [204]  [ 60/312]  eta: 0:06:42  lr: 0.001049  min_lr: 0.001049  loss: 2.3584 (2.3845)  weight_decay: 0.0500 (0.0500)  time: 0.4347  data: 0.0004  max mem: 42573
Epoch: [204]  [ 70/312]  eta: 0:05:46  lr: 0.001049  min_lr: 0.001049  loss: 2.2551 (2.3554)  weight_decay: 0.0500 (0.0500)  time: 0.4345  data: 0.0004  max mem: 42573
Epoch: [204]  [ 80/312]  eta: 0:05:03  lr: 0.001048  min_lr: 0.001048  loss: 2.2551 (2.3484)  weight_decay: 0.0500 (0.0500)  time: 0.4347  data: 0.0005  max mem: 42573
Epoch: [204]  [ 90/312]  eta: 0:04:29  lr: 0.001047  min_lr: 0.001047  loss: 2.3029 (2.3419)  weight_decay: 0.0500 (0.0500)  time: 0.4348  data: 0.0005  max mem: 42573
Epoch: [204]  [100/312]  eta: 0:04:00  lr: 0.001047  min_lr: 0.001047  loss: 2.3532 (2.3467)  weight_decay: 0.0500 (0.0500)  time: 0.4347  data: 0.0005  max mem: 42573
Epoch: [204]  [110/312]  eta: 0:03:36  lr: 0.001046  min_lr: 0.001046  loss: 2.3572 (2.3445)  weight_decay: 0.0500 (0.0500)  time: 0.4358  data: 0.0004  max mem: 42573
Epoch: [204]  [120/312]  eta: 0:03:15  lr: 0.001045  min_lr: 0.001045  loss: 2.4149 (2.3468)  weight_decay: 0.0500 (0.0500)  time: 0.4354  data: 0.0004  max mem: 42573
Epoch: [204]  [130/312]  eta: 0:02:57  lr: 0.001045  min_lr: 0.001045  loss: 2.3965 (2.3409)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0004  max mem: 42573
Epoch: [204]  [140/312]  eta: 0:02:41  lr: 0.001044  min_lr: 0.001044  loss: 2.2948 (2.3339)  weight_decay: 0.0500 (0.0500)  time: 0.4341  data: 0.0004  max mem: 42573
Epoch: [204]  [150/312]  eta: 0:02:26  lr: 0.001044  min_lr: 0.001044  loss: 2.2247 (2.3245)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [204]  [160/312]  eta: 0:02:12  lr: 0.001043  min_lr: 0.001043  loss: 2.2723 (2.3264)  weight_decay: 0.0500 (0.0500)  time: 0.4341  data: 0.0004  max mem: 42573
Epoch: [204]  [170/312]  eta: 0:02:00  lr: 0.001042  min_lr: 0.001042  loss: 2.3078 (2.3235)  weight_decay: 0.0500 (0.0500)  time: 0.4343  data: 0.0005  max mem: 42573
Epoch: [204]  [180/312]  eta: 0:01:49  lr: 0.001042  min_lr: 0.001042  loss: 2.2562 (2.3112)  weight_decay: 0.0500 (0.0500)  time: 0.4413  data: 0.0004  max mem: 42573
Epoch: [204]  [190/312]  eta: 0:01:38  lr: 0.001041  min_lr: 0.001041  loss: 2.1292 (2.3097)  weight_decay: 0.0500 (0.0500)  time: 0.4414  data: 0.0004  max mem: 42573
Epoch: [204]  [200/312]  eta: 0:01:28  lr: 0.001040  min_lr: 0.001040  loss: 2.1292 (2.2979)  weight_decay: 0.0500 (0.0500)  time: 0.4341  data: 0.0004  max mem: 42573
Epoch: [204]  [210/312]  eta: 0:01:18  lr: 0.001040  min_lr: 0.001040  loss: 2.3194 (2.2936)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [204]  [220/312]  eta: 0:01:09  lr: 0.001039  min_lr: 0.001039  loss: 2.3215 (2.2913)  weight_decay: 0.0500 (0.0500)  time: 0.4342  data: 0.0004  max mem: 42573
Epoch: [204]  [230/312]  eta: 0:01:00  lr: 0.001038  min_lr: 0.001038  loss: 2.3298 (2.2887)  weight_decay: 0.0500 (0.0500)  time: 0.4341  data: 0.0004  max mem: 42573
Epoch: [204]  [240/312]  eta: 0:00:52  lr: 0.001038  min_lr: 0.001038  loss: 2.3814 (2.2877)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [204]  [250/312]  eta: 0:00:44  lr: 0.001037  min_lr: 0.001037  loss: 2.2397 (2.2833)  weight_decay: 0.0500 (0.0500)  time: 0.4341  data: 0.0004  max mem: 42573
Epoch: [204]  [260/312]  eta: 0:00:36  lr: 0.001037  min_lr: 0.001037  loss: 2.0383 (2.2778)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [204]  [270/312]  eta: 0:00:29  lr: 0.001036  min_lr: 0.001036  loss: 2.2224 (2.2738)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [204]  [280/312]  eta: 0:00:21  lr: 0.001035  min_lr: 0.001035  loss: 2.3037 (2.2762)  weight_decay: 0.0500 (0.0500)  time: 0.4349  data: 0.0010  max mem: 42573
Epoch: [204]  [290/312]  eta: 0:00:14  lr: 0.001035  min_lr: 0.001035  loss: 2.3056 (2.2713)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0009  max mem: 42573
Epoch: [204]  [300/312]  eta: 0:00:08  lr: 0.001034  min_lr: 0.001034  loss: 2.1250 (2.2666)  weight_decay: 0.0500 (0.0500)  time: 0.4321  data: 0.0001  max mem: 42573
Epoch: [204]  [310/312]  eta: 0:00:01  lr: 0.001033  min_lr: 0.001033  loss: 2.1774 (2.2668)  weight_decay: 0.0500 (0.0500)  time: 0.4321  data: 0.0001  max mem: 42573
Epoch: [204]  [311/312]  eta: 0:00:00  lr: 0.001033  min_lr: 0.001033  loss: 2.2026 (2.2680)  weight_decay: 0.0500 (0.0500)  time: 0.4321  data: 0.0001  max mem: 42573
Epoch: [204] Total time: 0:03:27 (0.6653 s / it)
Averaged stats: lr: 0.001033  min_lr: 0.001033  loss: 2.2026 (2.2795)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:01:09  loss: 0.7428 (0.7428)  acc1: 83.0729 (83.0729)  acc5: 94.0104 (94.0104)  time: 7.7417  data: 4.1592  max mem: 42573
Test:  [8/9]  eta: 0:00:01  loss: 0.9964 (0.9489)  acc1: 77.3438 (76.5120)  acc5: 92.9688 (92.6400)  time: 1.0976  data: 0.4622  max mem: 42573
Test: Total time: 0:00:09 (1.1049 s / it)
* Acc@1 76.412 Acc@5 93.102 loss 0.941
Accuracy of the model on the 50000 test images: 76.4%
Max accuracy: 76.41%
Epoch: [205]  [  0/312]  eta: 1:21:06  lr: 0.001033  min_lr: 0.001033  loss: 2.8028 (2.8028)  weight_decay: 0.0500 (0.0500)  time: 15.5975  data: 8.0981  max mem: 42573
Epoch: [205]  [ 10/312]  eta: 0:11:37  lr: 0.001033  min_lr: 0.001033  loss: 2.5696 (2.5586)  weight_decay: 0.0500 (0.0500)  time: 2.3094  data: 0.7367  max mem: 42573
Epoch: [205]  [ 20/312]  eta: 0:08:09  lr: 0.001032  min_lr: 0.001032  loss: 2.5507 (2.4200)  weight_decay: 0.0500 (0.0500)  time: 0.9806  data: 0.0005  max mem: 42573
Epoch: [205]  [ 30/312]  eta: 0:06:49  lr: 0.001031  min_lr: 0.001031  loss: 2.3704 (2.3842)  weight_decay: 0.0500 (0.0500)  time: 0.9796  data: 0.0004  max mem: 42573
Epoch: [205]  [ 40/312]  eta: 0:06:03  lr: 0.001031  min_lr: 0.001031  loss: 2.3615 (2.3703)  weight_decay: 0.0500 (0.0500)  time: 0.9773  data: 0.0004  max mem: 42573
Epoch: [205]  [ 50/312]  eta: 0:05:10  lr: 0.001030  min_lr: 0.001030  loss: 2.3478 (2.3390)  weight_decay: 0.0500 (0.0500)  time: 0.7770  data: 0.0004  max mem: 42573
Epoch: [205]  [ 60/312]  eta: 0:04:28  lr: 0.001030  min_lr: 0.001030  loss: 2.2066 (2.3103)  weight_decay: 0.0500 (0.0500)  time: 0.5059  data: 0.0004  max mem: 42573
Epoch: [205]  [ 70/312]  eta: 0:03:55  lr: 0.001029  min_lr: 0.001029  loss: 2.2220 (2.2839)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0004  max mem: 42573
Epoch: [205]  [ 80/312]  eta: 0:03:30  lr: 0.001028  min_lr: 0.001028  loss: 2.2220 (2.2730)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [205]  [ 90/312]  eta: 0:03:10  lr: 0.001028  min_lr: 0.001028  loss: 2.2946 (2.2856)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [205]  [100/312]  eta: 0:02:52  lr: 0.001027  min_lr: 0.001027  loss: 2.3823 (2.2988)  weight_decay: 0.0500 (0.0500)  time: 0.4341  data: 0.0004  max mem: 42573
Epoch: [205]  [110/312]  eta: 0:02:37  lr: 0.001026  min_lr: 0.001026  loss: 2.2999 (2.2847)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [205]  [120/312]  eta: 0:02:24  lr: 0.001026  min_lr: 0.001026  loss: 2.3183 (2.3043)  weight_decay: 0.0500 (0.0500)  time: 0.4341  data: 0.0004  max mem: 42573
Epoch: [205]  [130/312]  eta: 0:02:12  lr: 0.001025  min_lr: 0.001025  loss: 2.4288 (2.3079)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0004  max mem: 42573
Epoch: [205]  [140/312]  eta: 0:02:01  lr: 0.001025  min_lr: 0.001025  loss: 2.3392 (2.2964)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [205]  [150/312]  eta: 0:01:51  lr: 0.001024  min_lr: 0.001024  loss: 2.1024 (2.2837)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0004  max mem: 42573
Epoch: [205]  [160/312]  eta: 0:01:42  lr: 0.001023  min_lr: 0.001023  loss: 2.0788 (2.2689)  weight_decay: 0.0500 (0.0500)  time: 0.4341  data: 0.0004  max mem: 42573
Epoch: [205]  [170/312]  eta: 0:01:33  lr: 0.001023  min_lr: 0.001023  loss: 2.2372 (2.2756)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [205]  [180/312]  eta: 0:01:25  lr: 0.001022  min_lr: 0.001022  loss: 2.3581 (2.2761)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0004  max mem: 42573
Epoch: [205]  [190/312]  eta: 0:01:17  lr: 0.001021  min_lr: 0.001021  loss: 2.2006 (2.2696)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0004  max mem: 42573
Epoch: [205]  [200/312]  eta: 0:01:09  lr: 0.001021  min_lr: 0.001021  loss: 2.3525 (2.2858)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [205]  [210/312]  eta: 0:01:02  lr: 0.001020  min_lr: 0.001020  loss: 2.3527 (2.2793)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0004  max mem: 42573
Epoch: [205]  [220/312]  eta: 0:00:55  lr: 0.001019  min_lr: 0.001019  loss: 2.2937 (2.2771)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0004  max mem: 42573
Epoch: [205]  [230/312]  eta: 0:00:49  lr: 0.001019  min_lr: 0.001019  loss: 2.2937 (2.2723)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0004  max mem: 42573
Epoch: [205]  [240/312]  eta: 0:00:42  lr: 0.001018  min_lr: 0.001018  loss: 2.4256 (2.2775)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [205]  [250/312]  eta: 0:00:36  lr: 0.001018  min_lr: 0.001018  loss: 2.5475 (2.2835)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [205]  [260/312]  eta: 0:00:30  lr: 0.001017  min_lr: 0.001017  loss: 2.5075 (2.2850)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [205]  [270/312]  eta: 0:00:24  lr: 0.001016  min_lr: 0.001016  loss: 2.3969 (2.2928)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [205]  [280/312]  eta: 0:00:18  lr: 0.001016  min_lr: 0.001016  loss: 2.4538 (2.2916)  weight_decay: 0.0500 (0.0500)  time: 0.4343  data: 0.0010  max mem: 42573
Epoch: [205]  [290/312]  eta: 0:00:12  lr: 0.001015  min_lr: 0.001015  loss: 2.2678 (2.2890)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0008  max mem: 42573
Epoch: [205]  [300/312]  eta: 0:00:06  lr: 0.001014  min_lr: 0.001014  loss: 2.2598 (2.2893)  weight_decay: 0.0500 (0.0500)  time: 0.4320  data: 0.0001  max mem: 42573
Epoch: [205]  [310/312]  eta: 0:00:01  lr: 0.001014  min_lr: 0.001014  loss: 2.4031 (2.2957)  weight_decay: 0.0500 (0.0500)  time: 0.4320  data: 0.0001  max mem: 42573
Epoch: [205]  [311/312]  eta: 0:00:00  lr: 0.001014  min_lr: 0.001014  loss: 2.4739 (2.2965)  weight_decay: 0.0500 (0.0500)  time: 0.4320  data: 0.0001  max mem: 42573
Epoch: [205] Total time: 0:02:54 (0.5601 s / it)
Averaged stats: lr: 0.001014  min_lr: 0.001014  loss: 2.4739 (2.2778)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:00:39  loss: 0.6807 (0.6807)  acc1: 82.5521 (82.5521)  acc5: 95.0521 (95.0521)  time: 4.3617  data: 4.2540  max mem: 42573
Test:  [8/9]  eta: 0:00:00  loss: 0.9823 (0.9266)  acc1: 75.7812 (76.0960)  acc5: 94.2708 (93.7920)  time: 0.5614  data: 0.4728  max mem: 42573
Test: Total time: 0:00:05 (0.5685 s / it)
* Acc@1 76.680 Acc@5 93.228 loss 0.921
Accuracy of the model on the 50000 test images: 76.7%
Max accuracy: 76.68%
Epoch: [206]  [  0/312]  eta: 0:51:24  lr: 0.001014  min_lr: 0.001014  loss: 2.3187 (2.3187)  weight_decay: 0.0500 (0.0500)  time: 9.8852  data: 7.2855  max mem: 42573
Epoch: [206]  [ 10/312]  eta: 0:07:47  lr: 0.001013  min_lr: 0.001013  loss: 2.2667 (2.2704)  weight_decay: 0.0500 (0.0500)  time: 1.5492  data: 0.6669  max mem: 42573
Epoch: [206]  [ 20/312]  eta: 0:04:57  lr: 0.001012  min_lr: 0.001012  loss: 2.1718 (2.1757)  weight_decay: 0.0500 (0.0500)  time: 0.5743  data: 0.0027  max mem: 42573
Epoch: [206]  [ 30/312]  eta: 0:03:53  lr: 0.001012  min_lr: 0.001012  loss: 2.2011 (2.2286)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [206]  [ 40/312]  eta: 0:03:19  lr: 0.001011  min_lr: 0.001011  loss: 2.1691 (2.1842)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [206]  [ 50/312]  eta: 0:02:56  lr: 0.001011  min_lr: 0.001011  loss: 2.2801 (2.2545)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [206]  [ 60/312]  eta: 0:02:39  lr: 0.001010  min_lr: 0.001010  loss: 2.4289 (2.2540)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0004  max mem: 42573
Epoch: [206]  [ 70/312]  eta: 0:02:26  lr: 0.001009  min_lr: 0.001009  loss: 2.1464 (2.2390)  weight_decay: 0.0500 (0.0500)  time: 0.4344  data: 0.0004  max mem: 42573
Epoch: [206]  [ 80/312]  eta: 0:02:15  lr: 0.001009  min_lr: 0.001009  loss: 2.0599 (2.2301)  weight_decay: 0.0500 (0.0500)  time: 0.4346  data: 0.0004  max mem: 42573
Epoch: [206]  [ 90/312]  eta: 0:02:06  lr: 0.001008  min_lr: 0.001008  loss: 2.0010 (2.2101)  weight_decay: 0.0500 (0.0500)  time: 0.4349  data: 0.0004  max mem: 42573
Epoch: [206]  [100/312]  eta: 0:01:57  lr: 0.001007  min_lr: 0.001007  loss: 2.1941 (2.2075)  weight_decay: 0.0500 (0.0500)  time: 0.4348  data: 0.0004  max mem: 42573
Epoch: [206]  [110/312]  eta: 0:01:50  lr: 0.001007  min_lr: 0.001007  loss: 2.3411 (2.2250)  weight_decay: 0.0500 (0.0500)  time: 0.4343  data: 0.0004  max mem: 42573
Epoch: [206]  [120/312]  eta: 0:01:42  lr: 0.001006  min_lr: 0.001006  loss: 2.4569 (2.2350)  weight_decay: 0.0500 (0.0500)  time: 0.4364  data: 0.0004  max mem: 42573
Epoch: [206]  [130/312]  eta: 0:01:36  lr: 0.001006  min_lr: 0.001006  loss: 2.3146 (2.2272)  weight_decay: 0.0500 (0.0500)  time: 0.4362  data: 0.0004  max mem: 42573
Epoch: [206]  [140/312]  eta: 0:01:29  lr: 0.001005  min_lr: 0.001005  loss: 2.3851 (2.2437)  weight_decay: 0.0500 (0.0500)  time: 0.4342  data: 0.0004  max mem: 42573
Epoch: [206]  [150/312]  eta: 0:01:23  lr: 0.001004  min_lr: 0.001004  loss: 2.4167 (2.2522)  weight_decay: 0.0500 (0.0500)  time: 0.4342  data: 0.0004  max mem: 42573
Epoch: [206]  [160/312]  eta: 0:01:17  lr: 0.001004  min_lr: 0.001004  loss: 2.3804 (2.2497)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [206]  [170/312]  eta: 0:01:11  lr: 0.001003  min_lr: 0.001003  loss: 2.2366 (2.2557)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [206]  [180/312]  eta: 0:01:06  lr: 0.001002  min_lr: 0.001002  loss: 2.2180 (2.2511)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [206]  [190/312]  eta: 0:01:00  lr: 0.001002  min_lr: 0.001002  loss: 2.0687 (2.2356)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [206]  [200/312]  eta: 0:00:55  lr: 0.001001  min_lr: 0.001001  loss: 2.0413 (2.2353)  weight_decay: 0.0500 (0.0500)  time: 0.4344  data: 0.0004  max mem: 42573
Epoch: [206]  [210/312]  eta: 0:00:50  lr: 0.001001  min_lr: 0.001001  loss: 2.2023 (2.2295)  weight_decay: 0.0500 (0.0500)  time: 0.4345  data: 0.0004  max mem: 42573
Epoch: [206]  [220/312]  eta: 0:00:45  lr: 0.001000  min_lr: 0.001000  loss: 1.9682 (2.2254)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [206]  [230/312]  eta: 0:00:39  lr: 0.000999  min_lr: 0.000999  loss: 2.4200 (2.2327)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [206]  [240/312]  eta: 0:00:34  lr: 0.000999  min_lr: 0.000999  loss: 2.3167 (2.2296)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [206]  [250/312]  eta: 0:00:29  lr: 0.000998  min_lr: 0.000998  loss: 2.2945 (2.2325)  weight_decay: 0.0500 (0.0500)  time: 0.4435  data: 0.0004  max mem: 42573
Epoch: [206]  [260/312]  eta: 0:00:25  lr: 0.000998  min_lr: 0.000998  loss: 2.3138 (2.2304)  weight_decay: 0.0500 (0.0500)  time: 0.4435  data: 0.0004  max mem: 42573
Epoch: [206]  [270/312]  eta: 0:00:20  lr: 0.000997  min_lr: 0.000997  loss: 2.2941 (2.2312)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [206]  [280/312]  eta: 0:00:15  lr: 0.000996  min_lr: 0.000996  loss: 2.3767 (2.2337)  weight_decay: 0.0500 (0.0500)  time: 0.4347  data: 0.0015  max mem: 42573
Epoch: [206]  [290/312]  eta: 0:00:10  lr: 0.000996  min_lr: 0.000996  loss: 2.4944 (2.2337)  weight_decay: 0.0500 (0.0500)  time: 0.4341  data: 0.0014  max mem: 42573
Epoch: [206]  [300/312]  eta: 0:00:05  lr: 0.000995  min_lr: 0.000995  loss: 2.4621 (2.2422)  weight_decay: 0.0500 (0.0500)  time: 0.4321  data: 0.0001  max mem: 42573
Epoch: [206]  [310/312]  eta: 0:00:00  lr: 0.000994  min_lr: 0.000994  loss: 2.4086 (2.2434)  weight_decay: 0.0500 (0.0500)  time: 0.4319  data: 0.0001  max mem: 42573
Epoch: [206]  [311/312]  eta: 0:00:00  lr: 0.000994  min_lr: 0.000994  loss: 2.3652 (2.2415)  weight_decay: 0.0500 (0.0500)  time: 0.4320  data: 0.0001  max mem: 42573
Epoch: [206] Total time: 0:02:28 (0.4770 s / it)
Averaged stats: lr: 0.000994  min_lr: 0.000994  loss: 2.3652 (2.2654)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:00:40  loss: 0.6180 (0.6180)  acc1: 86.1979 (86.1979)  acc5: 96.3542 (96.3542)  time: 4.5315  data: 4.4236  max mem: 42573
Test:  [8/9]  eta: 0:00:00  loss: 1.0207 (0.9283)  acc1: 76.5625 (76.6720)  acc5: 93.2292 (93.1520)  time: 0.5807  data: 0.4916  max mem: 42573
Test: Total time: 0:00:05 (0.5887 s / it)
* Acc@1 76.768 Acc@5 93.170 loss 0.912
Accuracy of the model on the 50000 test images: 76.8%
Max accuracy: 76.77%
Epoch: [207]  [  0/312]  eta: 0:53:12  lr: 0.000994  min_lr: 0.000994  loss: 2.5813 (2.5813)  weight_decay: 0.0500 (0.0500)  time: 10.2327  data: 7.1074  max mem: 42573
Epoch: [207]  [ 10/312]  eta: 0:07:48  lr: 0.000994  min_lr: 0.000994  loss: 2.2499 (2.1485)  weight_decay: 0.0500 (0.0500)  time: 1.5512  data: 0.6465  max mem: 42573
Epoch: [207]  [ 20/312]  eta: 0:04:57  lr: 0.000993  min_lr: 0.000993  loss: 2.1309 (2.1175)  weight_decay: 0.0500 (0.0500)  time: 0.5582  data: 0.0004  max mem: 42573
Epoch: [207]  [ 30/312]  eta: 0:03:54  lr: 0.000992  min_lr: 0.000992  loss: 2.3154 (2.2011)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [207]  [ 40/312]  eta: 0:03:19  lr: 0.000992  min_lr: 0.000992  loss: 2.4366 (2.2437)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [207]  [ 50/312]  eta: 0:02:56  lr: 0.000991  min_lr: 0.000991  loss: 2.5303 (2.2566)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [207]  [ 60/312]  eta: 0:02:40  lr: 0.000991  min_lr: 0.000991  loss: 2.3904 (2.2491)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [207]  [ 70/312]  eta: 0:02:26  lr: 0.000990  min_lr: 0.000990  loss: 2.2244 (2.2472)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [207]  [ 80/312]  eta: 0:02:15  lr: 0.000989  min_lr: 0.000989  loss: 2.2830 (2.2626)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [207]  [ 90/312]  eta: 0:02:06  lr: 0.000989  min_lr: 0.000989  loss: 2.2830 (2.2461)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [207]  [100/312]  eta: 0:01:57  lr: 0.000988  min_lr: 0.000988  loss: 2.2930 (2.2539)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0005  max mem: 42573
Epoch: [207]  [110/312]  eta: 0:01:49  lr: 0.000987  min_lr: 0.000987  loss: 2.4020 (2.2614)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0005  max mem: 42573
Epoch: [207]  [120/312]  eta: 0:01:42  lr: 0.000987  min_lr: 0.000987  loss: 2.4114 (2.2683)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [207]  [130/312]  eta: 0:01:36  lr: 0.000986  min_lr: 0.000986  loss: 2.3909 (2.2698)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [207]  [140/312]  eta: 0:01:29  lr: 0.000986  min_lr: 0.000986  loss: 2.2339 (2.2589)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [207]  [150/312]  eta: 0:01:23  lr: 0.000985  min_lr: 0.000985  loss: 2.2339 (2.2567)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [207]  [160/312]  eta: 0:01:17  lr: 0.000984  min_lr: 0.000984  loss: 2.3231 (2.2606)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [207]  [170/312]  eta: 0:01:11  lr: 0.000984  min_lr: 0.000984  loss: 2.3965 (2.2631)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [207]  [180/312]  eta: 0:01:06  lr: 0.000983  min_lr: 0.000983  loss: 2.3965 (2.2692)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [207]  [190/312]  eta: 0:01:00  lr: 0.000982  min_lr: 0.000982  loss: 2.3795 (2.2711)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [207]  [200/312]  eta: 0:00:55  lr: 0.000982  min_lr: 0.000982  loss: 2.2147 (2.2680)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [207]  [210/312]  eta: 0:00:50  lr: 0.000981  min_lr: 0.000981  loss: 2.3454 (2.2698)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [207]  [220/312]  eta: 0:00:45  lr: 0.000981  min_lr: 0.000981  loss: 2.3574 (2.2692)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [207]  [230/312]  eta: 0:00:39  lr: 0.000980  min_lr: 0.000980  loss: 2.2839 (2.2631)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [207]  [240/312]  eta: 0:00:34  lr: 0.000979  min_lr: 0.000979  loss: 2.4859 (2.2740)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [207]  [250/312]  eta: 0:00:29  lr: 0.000979  min_lr: 0.000979  loss: 2.5321 (2.2844)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [207]  [260/312]  eta: 0:00:25  lr: 0.000978  min_lr: 0.000978  loss: 2.3899 (2.2809)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0005  max mem: 42573
Epoch: [207]  [270/312]  eta: 0:00:20  lr: 0.000978  min_lr: 0.000978  loss: 2.3461 (2.2885)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [207]  [280/312]  eta: 0:00:15  lr: 0.000977  min_lr: 0.000977  loss: 2.3664 (2.2892)  weight_decay: 0.0500 (0.0500)  time: 0.4345  data: 0.0009  max mem: 42573
Epoch: [207]  [290/312]  eta: 0:00:10  lr: 0.000976  min_lr: 0.000976  loss: 2.1870 (2.2838)  weight_decay: 0.0500 (0.0500)  time: 0.4341  data: 0.0008  max mem: 42573
Epoch: [207]  [300/312]  eta: 0:00:05  lr: 0.000976  min_lr: 0.000976  loss: 2.2005 (2.2806)  weight_decay: 0.0500 (0.0500)  time: 0.4321  data: 0.0001  max mem: 42573
Epoch: [207]  [310/312]  eta: 0:00:00  lr: 0.000975  min_lr: 0.000975  loss: 2.3228 (2.2820)  weight_decay: 0.0500 (0.0500)  time: 0.4319  data: 0.0001  max mem: 42573
Epoch: [207]  [311/312]  eta: 0:00:00  lr: 0.000975  min_lr: 0.000975  loss: 2.3228 (2.2808)  weight_decay: 0.0500 (0.0500)  time: 0.4320  data: 0.0001  max mem: 42573
Epoch: [207] Total time: 0:02:28 (0.4761 s / it)
Averaged stats: lr: 0.000975  min_lr: 0.000975  loss: 2.3228 (2.2612)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:00:42  loss: 0.7547 (0.7547)  acc1: 83.3333 (83.3333)  acc5: 94.5312 (94.5312)  time: 4.7500  data: 4.6423  max mem: 42573
Test:  [8/9]  eta: 0:00:00  loss: 0.9691 (0.9331)  acc1: 76.3021 (76.3200)  acc5: 92.9688 (92.8320)  time: 0.6047  data: 0.5159  max mem: 42573
Test: Total time: 0:00:05 (0.6153 s / it)
* Acc@1 76.284 Acc@5 93.048 loss 0.930
Accuracy of the model on the 50000 test images: 76.3%
Max accuracy: 76.77%
Epoch: [208]  [  0/312]  eta: 0:52:58  lr: 0.000975  min_lr: 0.000975  loss: 1.5455 (1.5455)  weight_decay: 0.0500 (0.0500)  time: 10.1871  data: 8.2321  max mem: 42573
Epoch: [208]  [ 10/312]  eta: 0:07:40  lr: 0.000974  min_lr: 0.000974  loss: 2.4060 (2.2456)  weight_decay: 0.0500 (0.0500)  time: 1.5241  data: 0.7487  max mem: 42573
Epoch: [208]  [ 20/312]  eta: 0:04:53  lr: 0.000974  min_lr: 0.000974  loss: 2.4493 (2.3408)  weight_decay: 0.0500 (0.0500)  time: 0.5454  data: 0.0004  max mem: 42573
Epoch: [208]  [ 30/312]  eta: 0:03:52  lr: 0.000973  min_lr: 0.000973  loss: 2.4698 (2.3612)  weight_decay: 0.0500 (0.0500)  time: 0.4397  data: 0.0003  max mem: 42573
Epoch: [208]  [ 40/312]  eta: 0:03:18  lr: 0.000972  min_lr: 0.000972  loss: 2.3961 (2.3543)  weight_decay: 0.0500 (0.0500)  time: 0.4398  data: 0.0004  max mem: 42573
Epoch: [208]  [ 50/312]  eta: 0:02:55  lr: 0.000972  min_lr: 0.000972  loss: 2.3343 (2.3445)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [208]  [ 60/312]  eta: 0:02:39  lr: 0.000971  min_lr: 0.000971  loss: 2.3181 (2.3300)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0004  max mem: 42573
Epoch: [208]  [ 70/312]  eta: 0:02:26  lr: 0.000971  min_lr: 0.000971  loss: 2.0745 (2.2985)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0004  max mem: 42573
Epoch: [208]  [ 80/312]  eta: 0:02:15  lr: 0.000970  min_lr: 0.000970  loss: 2.0745 (2.2927)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [208]  [ 90/312]  eta: 0:02:05  lr: 0.000969  min_lr: 0.000969  loss: 2.4404 (2.2931)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [208]  [100/312]  eta: 0:01:57  lr: 0.000969  min_lr: 0.000969  loss: 2.3996 (2.2944)  weight_decay: 0.0500 (0.0500)  time: 0.4344  data: 0.0004  max mem: 42573
Epoch: [208]  [110/312]  eta: 0:01:49  lr: 0.000968  min_lr: 0.000968  loss: 2.3996 (2.3068)  weight_decay: 0.0500 (0.0500)  time: 0.4351  data: 0.0003  max mem: 42573
Epoch: [208]  [120/312]  eta: 0:01:42  lr: 0.000968  min_lr: 0.000968  loss: 2.4801 (2.3133)  weight_decay: 0.0500 (0.0500)  time: 0.4344  data: 0.0004  max mem: 42573
Epoch: [208]  [130/312]  eta: 0:01:35  lr: 0.000967  min_lr: 0.000967  loss: 2.3765 (2.3175)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [208]  [140/312]  eta: 0:01:29  lr: 0.000966  min_lr: 0.000966  loss: 2.3765 (2.3193)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [208]  [150/312]  eta: 0:01:23  lr: 0.000966  min_lr: 0.000966  loss: 2.4184 (2.3157)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [208]  [160/312]  eta: 0:01:17  lr: 0.000965  min_lr: 0.000965  loss: 2.4129 (2.3229)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [208]  [170/312]  eta: 0:01:11  lr: 0.000964  min_lr: 0.000964  loss: 2.3515 (2.3180)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [208]  [180/312]  eta: 0:01:06  lr: 0.000964  min_lr: 0.000964  loss: 2.3269 (2.3136)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [208]  [190/312]  eta: 0:01:00  lr: 0.000963  min_lr: 0.000963  loss: 2.3377 (2.3115)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [208]  [200/312]  eta: 0:00:55  lr: 0.000963  min_lr: 0.000963  loss: 2.4433 (2.3162)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [208]  [210/312]  eta: 0:00:50  lr: 0.000962  min_lr: 0.000962  loss: 2.4135 (2.3165)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [208]  [220/312]  eta: 0:00:44  lr: 0.000961  min_lr: 0.000961  loss: 2.4210 (2.3198)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [208]  [230/312]  eta: 0:00:39  lr: 0.000961  min_lr: 0.000961  loss: 2.3460 (2.3088)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [208]  [240/312]  eta: 0:00:34  lr: 0.000960  min_lr: 0.000960  loss: 1.9582 (2.2961)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0003  max mem: 42573
Epoch: [208]  [250/312]  eta: 0:00:29  lr: 0.000960  min_lr: 0.000960  loss: 1.9718 (2.2858)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0003  max mem: 42573
Epoch: [208]  [260/312]  eta: 0:00:24  lr: 0.000959  min_lr: 0.000959  loss: 2.2093 (2.2908)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [208]  [270/312]  eta: 0:00:20  lr: 0.000958  min_lr: 0.000958  loss: 2.3757 (2.2938)  weight_decay: 0.0500 (0.0500)  time: 0.4463  data: 0.0004  max mem: 42573
Epoch: [208]  [280/312]  eta: 0:00:15  lr: 0.000958  min_lr: 0.000958  loss: 2.2986 (2.2933)  weight_decay: 0.0500 (0.0500)  time: 0.4468  data: 0.0010  max mem: 42573
Epoch: [208]  [290/312]  eta: 0:00:10  lr: 0.000957  min_lr: 0.000957  loss: 2.2234 (2.2901)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0008  max mem: 42573
Epoch: [208]  [300/312]  eta: 0:00:05  lr: 0.000956  min_lr: 0.000956  loss: 2.1863 (2.2832)  weight_decay: 0.0500 (0.0500)  time: 0.4321  data: 0.0001  max mem: 42573
Epoch: [208]  [310/312]  eta: 0:00:00  lr: 0.000956  min_lr: 0.000956  loss: 2.3503 (2.2856)  weight_decay: 0.0500 (0.0500)  time: 0.4320  data: 0.0001  max mem: 42573
Epoch: [208]  [311/312]  eta: 0:00:00  lr: 0.000956  min_lr: 0.000956  loss: 2.3408 (2.2842)  weight_decay: 0.0500 (0.0500)  time: 0.4320  data: 0.0001  max mem: 42573
Epoch: [208] Total time: 0:02:28 (0.4765 s / it)
Averaged stats: lr: 0.000956  min_lr: 0.000956  loss: 2.3408 (2.2585)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:00:39  loss: 0.7079 (0.7079)  acc1: 82.2917 (82.2917)  acc5: 93.7500 (93.7500)  time: 4.3862  data: 4.2796  max mem: 42573
Test:  [8/9]  eta: 0:00:00  loss: 0.9342 (0.9281)  acc1: 77.6042 (75.8720)  acc5: 93.2292 (92.8000)  time: 0.5636  data: 0.4756  max mem: 42573
Test: Total time: 0:00:05 (0.5702 s / it)
* Acc@1 76.720 Acc@5 93.264 loss 0.913
Accuracy of the model on the 50000 test images: 76.7%
Max accuracy: 76.77%
Epoch: [209]  [  0/312]  eta: 0:56:19  lr: 0.000956  min_lr: 0.000956  loss: 1.4473 (1.4473)  weight_decay: 0.0500 (0.0500)  time: 10.8320  data: 7.5425  max mem: 42573
Epoch: [209]  [ 10/312]  eta: 0:08:00  lr: 0.000955  min_lr: 0.000955  loss: 2.0562 (1.9508)  weight_decay: 0.0500 (0.0500)  time: 1.5894  data: 0.6862  max mem: 42573
Epoch: [209]  [ 20/312]  eta: 0:05:03  lr: 0.000955  min_lr: 0.000955  loss: 2.1244 (2.0514)  weight_decay: 0.0500 (0.0500)  time: 0.5493  data: 0.0005  max mem: 42573
Epoch: [209]  [ 30/312]  eta: 0:03:57  lr: 0.000954  min_lr: 0.000954  loss: 2.3692 (2.1601)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [209]  [ 40/312]  eta: 0:03:22  lr: 0.000953  min_lr: 0.000953  loss: 2.4272 (2.2352)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [209]  [ 50/312]  eta: 0:02:58  lr: 0.000953  min_lr: 0.000953  loss: 2.3453 (2.2514)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [209]  [ 60/312]  eta: 0:02:41  lr: 0.000952  min_lr: 0.000952  loss: 2.2488 (2.2485)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [209]  [ 70/312]  eta: 0:02:28  lr: 0.000951  min_lr: 0.000951  loss: 2.3574 (2.2637)  weight_decay: 0.0500 (0.0500)  time: 0.4348  data: 0.0004  max mem: 42573
Epoch: [209]  [ 80/312]  eta: 0:02:17  lr: 0.000951  min_lr: 0.000951  loss: 2.3762 (2.2634)  weight_decay: 0.0500 (0.0500)  time: 0.4348  data: 0.0004  max mem: 42573
Epoch: [209]  [ 90/312]  eta: 0:02:07  lr: 0.000950  min_lr: 0.000950  loss: 2.1406 (2.2226)  weight_decay: 0.0500 (0.0500)  time: 0.4342  data: 0.0004  max mem: 42573
Epoch: [209]  [100/312]  eta: 0:01:58  lr: 0.000950  min_lr: 0.000950  loss: 1.9271 (2.1972)  weight_decay: 0.0500 (0.0500)  time: 0.4342  data: 0.0004  max mem: 42573
Epoch: [209]  [110/312]  eta: 0:01:50  lr: 0.000949  min_lr: 0.000949  loss: 2.1321 (2.2076)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [209]  [120/312]  eta: 0:01:43  lr: 0.000948  min_lr: 0.000948  loss: 2.3315 (2.2115)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [209]  [130/312]  eta: 0:01:36  lr: 0.000948  min_lr: 0.000948  loss: 2.3232 (2.2133)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [209]  [140/312]  eta: 0:01:30  lr: 0.000947  min_lr: 0.000947  loss: 2.4534 (2.2350)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [209]  [150/312]  eta: 0:01:23  lr: 0.000947  min_lr: 0.000947  loss: 2.3303 (2.2323)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [209]  [160/312]  eta: 0:01:17  lr: 0.000946  min_lr: 0.000946  loss: 2.1585 (2.2290)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [209]  [170/312]  eta: 0:01:12  lr: 0.000945  min_lr: 0.000945  loss: 2.4334 (2.2416)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [209]  [180/312]  eta: 0:01:06  lr: 0.000945  min_lr: 0.000945  loss: 2.4334 (2.2367)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [209]  [190/312]  eta: 0:01:01  lr: 0.000944  min_lr: 0.000944  loss: 2.0317 (2.2317)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [209]  [200/312]  eta: 0:00:55  lr: 0.000944  min_lr: 0.000944  loss: 2.1631 (2.2346)  weight_decay: 0.0500 (0.0500)  time: 0.4349  data: 0.0004  max mem: 42573
Epoch: [209]  [210/312]  eta: 0:00:50  lr: 0.000943  min_lr: 0.000943  loss: 2.3900 (2.2409)  weight_decay: 0.0500 (0.0500)  time: 0.4352  data: 0.0004  max mem: 42573
Epoch: [209]  [220/312]  eta: 0:00:45  lr: 0.000942  min_lr: 0.000942  loss: 2.3900 (2.2451)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [209]  [230/312]  eta: 0:00:40  lr: 0.000942  min_lr: 0.000942  loss: 2.2705 (2.2394)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0003  max mem: 42573
Epoch: [209]  [240/312]  eta: 0:00:35  lr: 0.000941  min_lr: 0.000941  loss: 2.4088 (2.2465)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [209]  [250/312]  eta: 0:00:30  lr: 0.000940  min_lr: 0.000940  loss: 2.3950 (2.2431)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [209]  [260/312]  eta: 0:00:25  lr: 0.000940  min_lr: 0.000940  loss: 2.1796 (2.2460)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [209]  [270/312]  eta: 0:00:20  lr: 0.000939  min_lr: 0.000939  loss: 2.3706 (2.2509)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [209]  [280/312]  eta: 0:00:15  lr: 0.000939  min_lr: 0.000939  loss: 2.3169 (2.2490)  weight_decay: 0.0500 (0.0500)  time: 0.4348  data: 0.0009  max mem: 42573
Epoch: [209]  [290/312]  eta: 0:00:10  lr: 0.000938  min_lr: 0.000938  loss: 2.1071 (2.2431)  weight_decay: 0.0500 (0.0500)  time: 0.4344  data: 0.0008  max mem: 42573
Epoch: [209]  [300/312]  eta: 0:00:05  lr: 0.000937  min_lr: 0.000937  loss: 2.1071 (2.2413)  weight_decay: 0.0500 (0.0500)  time: 0.4322  data: 0.0001  max mem: 42573
Epoch: [209]  [310/312]  eta: 0:00:00  lr: 0.000937  min_lr: 0.000937  loss: 2.1684 (2.2376)  weight_decay: 0.0500 (0.0500)  time: 0.4319  data: 0.0001  max mem: 42573
Epoch: [209]  [311/312]  eta: 0:00:00  lr: 0.000937  min_lr: 0.000937  loss: 2.1684 (2.2367)  weight_decay: 0.0500 (0.0500)  time: 0.4319  data: 0.0001  max mem: 42573
Epoch: [209] Total time: 0:02:28 (0.4775 s / it)
Averaged stats: lr: 0.000937  min_lr: 0.000937  loss: 2.1684 (2.2544)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:00:42  loss: 0.6570 (0.6570)  acc1: 83.5938 (83.5938)  acc5: 95.3125 (95.3125)  time: 4.7754  data: 4.6671  max mem: 42573
Test:  [8/9]  eta: 0:00:00  loss: 0.9727 (0.8922)  acc1: 75.7812 (76.2880)  acc5: 94.7917 (93.7600)  time: 0.6077  data: 0.5186  max mem: 42573
Test: Total time: 0:00:05 (0.6235 s / it)
* Acc@1 76.990 Acc@5 93.442 loss 0.892
Accuracy of the model on the 50000 test images: 77.0%
Max accuracy: 76.99%
Epoch: [210]  [  0/312]  eta: 0:48:46  lr: 0.000937  min_lr: 0.000937  loss: 2.6839 (2.6839)  weight_decay: 0.0500 (0.0500)  time: 9.3793  data: 7.2973  max mem: 42573
Epoch: [210]  [ 10/312]  eta: 0:07:46  lr: 0.000936  min_lr: 0.000936  loss: 2.5166 (2.3963)  weight_decay: 0.0500 (0.0500)  time: 1.5437  data: 0.7362  max mem: 42573
Epoch: [210]  [ 20/312]  eta: 0:04:56  lr: 0.000935  min_lr: 0.000935  loss: 2.2868 (2.2840)  weight_decay: 0.0500 (0.0500)  time: 0.5965  data: 0.0402  max mem: 42573
Epoch: [210]  [ 30/312]  eta: 0:03:53  lr: 0.000935  min_lr: 0.000935  loss: 2.2510 (2.2621)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [210]  [ 40/312]  eta: 0:03:18  lr: 0.000934  min_lr: 0.000934  loss: 2.2557 (2.2595)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0004  max mem: 42573
Epoch: [210]  [ 50/312]  eta: 0:02:56  lr: 0.000934  min_lr: 0.000934  loss: 2.0458 (2.1966)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [210]  [ 60/312]  eta: 0:02:39  lr: 0.000933  min_lr: 0.000933  loss: 2.0293 (2.1787)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [210]  [ 70/312]  eta: 0:02:26  lr: 0.000932  min_lr: 0.000932  loss: 2.1372 (2.1849)  weight_decay: 0.0500 (0.0500)  time: 0.4354  data: 0.0004  max mem: 42573
Epoch: [210]  [ 80/312]  eta: 0:02:15  lr: 0.000932  min_lr: 0.000932  loss: 2.1433 (2.1693)  weight_decay: 0.0500 (0.0500)  time: 0.4360  data: 0.0004  max mem: 42573
Epoch: [210]  [ 90/312]  eta: 0:02:06  lr: 0.000931  min_lr: 0.000931  loss: 2.2665 (2.1796)  weight_decay: 0.0500 (0.0500)  time: 0.4350  data: 0.0004  max mem: 42573
Epoch: [210]  [100/312]  eta: 0:01:57  lr: 0.000931  min_lr: 0.000931  loss: 2.2494 (2.1666)  weight_decay: 0.0500 (0.0500)  time: 0.4363  data: 0.0004  max mem: 42573
Epoch: [210]  [110/312]  eta: 0:01:50  lr: 0.000930  min_lr: 0.000930  loss: 2.1073 (2.1686)  weight_decay: 0.0500 (0.0500)  time: 0.4357  data: 0.0004  max mem: 42573
Epoch: [210]  [120/312]  eta: 0:01:42  lr: 0.000929  min_lr: 0.000929  loss: 2.1073 (2.1671)  weight_decay: 0.0500 (0.0500)  time: 0.4341  data: 0.0004  max mem: 42573
Epoch: [210]  [130/312]  eta: 0:01:36  lr: 0.000929  min_lr: 0.000929  loss: 2.2102 (2.1670)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [210]  [140/312]  eta: 0:01:29  lr: 0.000928  min_lr: 0.000928  loss: 2.3941 (2.1885)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [210]  [150/312]  eta: 0:01:23  lr: 0.000928  min_lr: 0.000928  loss: 2.4124 (2.1929)  weight_decay: 0.0500 (0.0500)  time: 0.4347  data: 0.0004  max mem: 42573
Epoch: [210]  [160/312]  eta: 0:01:17  lr: 0.000927  min_lr: 0.000927  loss: 2.3887 (2.2059)  weight_decay: 0.0500 (0.0500)  time: 0.4344  data: 0.0004  max mem: 42573
Epoch: [210]  [170/312]  eta: 0:01:11  lr: 0.000926  min_lr: 0.000926  loss: 2.3828 (2.2125)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [210]  [180/312]  eta: 0:01:06  lr: 0.000926  min_lr: 0.000926  loss: 2.3326 (2.2140)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [210]  [190/312]  eta: 0:01:00  lr: 0.000925  min_lr: 0.000925  loss: 2.1271 (2.2060)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [210]  [200/312]  eta: 0:00:55  lr: 0.000925  min_lr: 0.000925  loss: 2.2595 (2.2178)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [210]  [210/312]  eta: 0:00:50  lr: 0.000924  min_lr: 0.000924  loss: 2.2868 (2.2137)  weight_decay: 0.0500 (0.0500)  time: 0.4347  data: 0.0004  max mem: 42573
Epoch: [210]  [220/312]  eta: 0:00:45  lr: 0.000923  min_lr: 0.000923  loss: 2.3004 (2.2270)  weight_decay: 0.0500 (0.0500)  time: 0.4346  data: 0.0004  max mem: 42573
Epoch: [210]  [230/312]  eta: 0:00:39  lr: 0.000923  min_lr: 0.000923  loss: 2.3976 (2.2208)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [210]  [240/312]  eta: 0:00:34  lr: 0.000922  min_lr: 0.000922  loss: 2.1365 (2.2207)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [210]  [250/312]  eta: 0:00:29  lr: 0.000922  min_lr: 0.000922  loss: 2.3711 (2.2250)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [210]  [260/312]  eta: 0:00:25  lr: 0.000921  min_lr: 0.000921  loss: 2.4036 (2.2297)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [210]  [270/312]  eta: 0:00:20  lr: 0.000920  min_lr: 0.000920  loss: 2.4339 (2.2353)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [210]  [280/312]  eta: 0:00:15  lr: 0.000920  min_lr: 0.000920  loss: 2.4015 (2.2360)  weight_decay: 0.0500 (0.0500)  time: 0.4355  data: 0.0009  max mem: 42573
Epoch: [210]  [290/312]  eta: 0:00:10  lr: 0.000919  min_lr: 0.000919  loss: 2.4454 (2.2410)  weight_decay: 0.0500 (0.0500)  time: 0.4347  data: 0.0008  max mem: 42573
Epoch: [210]  [300/312]  eta: 0:00:05  lr: 0.000918  min_lr: 0.000918  loss: 2.4677 (2.2408)  weight_decay: 0.0500 (0.0500)  time: 0.4321  data: 0.0001  max mem: 42573
Epoch: [210]  [310/312]  eta: 0:00:00  lr: 0.000918  min_lr: 0.000918  loss: 2.2366 (2.2394)  weight_decay: 0.0500 (0.0500)  time: 0.4321  data: 0.0001  max mem: 42573
Epoch: [210]  [311/312]  eta: 0:00:00  lr: 0.000918  min_lr: 0.000918  loss: 2.2068 (2.2377)  weight_decay: 0.0500 (0.0500)  time: 0.4321  data: 0.0001  max mem: 42573
Epoch: [210] Total time: 0:02:28 (0.4764 s / it)
Averaged stats: lr: 0.000918  min_lr: 0.000918  loss: 2.2068 (2.2511)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:00:39  loss: 0.6530 (0.6530)  acc1: 84.6354 (84.6354)  acc5: 96.0938 (96.0938)  time: 4.4037  data: 4.2959  max mem: 42573
Test:  [8/9]  eta: 0:00:00  loss: 0.9398 (0.8935)  acc1: 77.3438 (76.7360)  acc5: 94.0104 (93.6000)  time: 0.5658  data: 0.4774  max mem: 42573
Test: Total time: 0:00:05 (0.5820 s / it)
* Acc@1 77.200 Acc@5 93.510 loss 0.880
Accuracy of the model on the 50000 test images: 77.2%
Max accuracy: 77.20%
Epoch: [211]  [  0/312]  eta: 0:51:08  lr: 0.000918  min_lr: 0.000918  loss: 2.3403 (2.3403)  weight_decay: 0.0500 (0.0500)  time: 9.8347  data: 8.4783  max mem: 42573
Epoch: [211]  [ 10/312]  eta: 0:07:46  lr: 0.000917  min_lr: 0.000917  loss: 2.4371 (2.4534)  weight_decay: 0.0500 (0.0500)  time: 1.5437  data: 0.7712  max mem: 42573
Epoch: [211]  [ 20/312]  eta: 0:04:56  lr: 0.000917  min_lr: 0.000917  loss: 2.3437 (2.2455)  weight_decay: 0.0500 (0.0500)  time: 0.5739  data: 0.0004  max mem: 42573
Epoch: [211]  [ 30/312]  eta: 0:03:54  lr: 0.000916  min_lr: 0.000916  loss: 2.1323 (2.2601)  weight_decay: 0.0500 (0.0500)  time: 0.4380  data: 0.0003  max mem: 42573
Epoch: [211]  [ 40/312]  eta: 0:03:19  lr: 0.000915  min_lr: 0.000915  loss: 2.1652 (2.1916)  weight_decay: 0.0500 (0.0500)  time: 0.4381  data: 0.0004  max mem: 42573
Epoch: [211]  [ 50/312]  eta: 0:02:56  lr: 0.000915  min_lr: 0.000915  loss: 2.1632 (2.1939)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [211]  [ 60/312]  eta: 0:02:40  lr: 0.000914  min_lr: 0.000914  loss: 2.1257 (2.1882)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [211]  [ 70/312]  eta: 0:02:27  lr: 0.000914  min_lr: 0.000914  loss: 2.0848 (2.1941)  weight_decay: 0.0500 (0.0500)  time: 0.4375  data: 0.0004  max mem: 42573
Epoch: [211]  [ 80/312]  eta: 0:02:16  lr: 0.000913  min_lr: 0.000913  loss: 2.2986 (2.2139)  weight_decay: 0.0500 (0.0500)  time: 0.4378  data: 0.0004  max mem: 42573
Epoch: [211]  [ 90/312]  eta: 0:02:06  lr: 0.000912  min_lr: 0.000912  loss: 2.2986 (2.2248)  weight_decay: 0.0500 (0.0500)  time: 0.4341  data: 0.0004  max mem: 42573
Epoch: [211]  [100/312]  eta: 0:01:57  lr: 0.000912  min_lr: 0.000912  loss: 2.2611 (2.2116)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [211]  [110/312]  eta: 0:01:50  lr: 0.000911  min_lr: 0.000911  loss: 2.2333 (2.2131)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [211]  [120/312]  eta: 0:01:42  lr: 0.000911  min_lr: 0.000911  loss: 2.2330 (2.2087)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [211]  [130/312]  eta: 0:01:36  lr: 0.000910  min_lr: 0.000910  loss: 2.2870 (2.2135)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [211]  [140/312]  eta: 0:01:29  lr: 0.000909  min_lr: 0.000909  loss: 2.3135 (2.2257)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [211]  [150/312]  eta: 0:01:23  lr: 0.000909  min_lr: 0.000909  loss: 2.4835 (2.2378)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [211]  [160/312]  eta: 0:01:17  lr: 0.000908  min_lr: 0.000908  loss: 2.2946 (2.2342)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [211]  [170/312]  eta: 0:01:11  lr: 0.000908  min_lr: 0.000908  loss: 2.2421 (2.2340)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [211]  [180/312]  eta: 0:01:06  lr: 0.000907  min_lr: 0.000907  loss: 2.1969 (2.2327)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [211]  [190/312]  eta: 0:01:00  lr: 0.000906  min_lr: 0.000906  loss: 2.2374 (2.2316)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [211]  [200/312]  eta: 0:00:55  lr: 0.000906  min_lr: 0.000906  loss: 2.2680 (2.2367)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [211]  [210/312]  eta: 0:00:50  lr: 0.000905  min_lr: 0.000905  loss: 2.1623 (2.2290)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [211]  [220/312]  eta: 0:00:45  lr: 0.000905  min_lr: 0.000905  loss: 2.3245 (2.2341)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [211]  [230/312]  eta: 0:00:39  lr: 0.000904  min_lr: 0.000904  loss: 2.4407 (2.2356)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0003  max mem: 42573
Epoch: [211]  [240/312]  eta: 0:00:34  lr: 0.000903  min_lr: 0.000903  loss: 2.1307 (2.2311)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [211]  [250/312]  eta: 0:00:29  lr: 0.000903  min_lr: 0.000903  loss: 2.1275 (2.2340)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [211]  [260/312]  eta: 0:00:25  lr: 0.000902  min_lr: 0.000902  loss: 2.3833 (2.2377)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [211]  [270/312]  eta: 0:00:20  lr: 0.000902  min_lr: 0.000902  loss: 2.4593 (2.2456)  weight_decay: 0.0500 (0.0500)  time: 0.4352  data: 0.0004  max mem: 42573
Epoch: [211]  [280/312]  eta: 0:00:15  lr: 0.000901  min_lr: 0.000901  loss: 2.0821 (2.2376)  weight_decay: 0.0500 (0.0500)  time: 0.4357  data: 0.0009  max mem: 42573
Epoch: [211]  [290/312]  eta: 0:00:10  lr: 0.000900  min_lr: 0.000900  loss: 2.0509 (2.2379)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0008  max mem: 42573
Epoch: [211]  [300/312]  eta: 0:00:05  lr: 0.000900  min_lr: 0.000900  loss: 2.3653 (2.2385)  weight_decay: 0.0500 (0.0500)  time: 0.4321  data: 0.0001  max mem: 42573
Epoch: [211]  [310/312]  eta: 0:00:00  lr: 0.000899  min_lr: 0.000899  loss: 2.2321 (2.2421)  weight_decay: 0.0500 (0.0500)  time: 0.4320  data: 0.0001  max mem: 42573
Epoch: [211]  [311/312]  eta: 0:00:00  lr: 0.000899  min_lr: 0.000899  loss: 2.2321 (2.2414)  weight_decay: 0.0500 (0.0500)  time: 0.4321  data: 0.0001  max mem: 42573
Epoch: [211] Total time: 0:02:28 (0.4764 s / it)
Averaged stats: lr: 0.000899  min_lr: 0.000899  loss: 2.2321 (2.2527)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:00:38  loss: 0.6954 (0.6954)  acc1: 82.2917 (82.2917)  acc5: 95.3125 (95.3125)  time: 4.2980  data: 4.1903  max mem: 42573
Test:  [8/9]  eta: 0:00:00  loss: 0.9282 (0.9084)  acc1: 76.8229 (76.3840)  acc5: 93.2292 (93.2480)  time: 0.5540  data: 0.4657  max mem: 42573
Test: Total time: 0:00:05 (0.5610 s / it)
* Acc@1 77.234 Acc@5 93.528 loss 0.885
Accuracy of the model on the 50000 test images: 77.2%
Max accuracy: 77.23%
Epoch: [212]  [  0/312]  eta: 0:56:16  lr: 0.000899  min_lr: 0.000899  loss: 1.9082 (1.9082)  weight_decay: 0.0500 (0.0500)  time: 10.8206  data: 8.0933  max mem: 42573
Epoch: [212]  [ 10/312]  eta: 0:08:01  lr: 0.000898  min_lr: 0.000898  loss: 1.9475 (2.0722)  weight_decay: 0.0500 (0.0500)  time: 1.5937  data: 0.7361  max mem: 42573
Epoch: [212]  [ 20/312]  eta: 0:05:03  lr: 0.000898  min_lr: 0.000898  loss: 2.1994 (2.1819)  weight_decay: 0.0500 (0.0500)  time: 0.5520  data: 0.0004  max mem: 42573
Epoch: [212]  [ 30/312]  eta: 0:03:58  lr: 0.000897  min_lr: 0.000897  loss: 2.3429 (2.2619)  weight_decay: 0.0500 (0.0500)  time: 0.4331  data: 0.0003  max mem: 42573
Epoch: [212]  [ 40/312]  eta: 0:03:22  lr: 0.000897  min_lr: 0.000897  loss: 2.3872 (2.2674)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0003  max mem: 42573
Epoch: [212]  [ 50/312]  eta: 0:02:59  lr: 0.000896  min_lr: 0.000896  loss: 2.2759 (2.2587)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [212]  [ 60/312]  eta: 0:02:41  lr: 0.000895  min_lr: 0.000895  loss: 2.4368 (2.2935)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [212]  [ 70/312]  eta: 0:02:28  lr: 0.000895  min_lr: 0.000895  loss: 2.4702 (2.3047)  weight_decay: 0.0500 (0.0500)  time: 0.4347  data: 0.0003  max mem: 42573
Epoch: [212]  [ 80/312]  eta: 0:02:17  lr: 0.000894  min_lr: 0.000894  loss: 2.3182 (2.2947)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0003  max mem: 42573
Epoch: [212]  [ 90/312]  eta: 0:02:07  lr: 0.000894  min_lr: 0.000894  loss: 2.2581 (2.2943)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [212]  [100/312]  eta: 0:01:58  lr: 0.000893  min_lr: 0.000893  loss: 2.2581 (2.2807)  weight_decay: 0.0500 (0.0500)  time: 0.4341  data: 0.0004  max mem: 42573
Epoch: [212]  [110/312]  eta: 0:01:50  lr: 0.000892  min_lr: 0.000892  loss: 2.3018 (2.2858)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0003  max mem: 42573
Epoch: [212]  [120/312]  eta: 0:01:43  lr: 0.000892  min_lr: 0.000892  loss: 2.3018 (2.2789)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [212]  [130/312]  eta: 0:01:36  lr: 0.000891  min_lr: 0.000891  loss: 2.3106 (2.2806)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [212]  [140/312]  eta: 0:01:30  lr: 0.000891  min_lr: 0.000891  loss: 2.3106 (2.2820)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [212]  [150/312]  eta: 0:01:23  lr: 0.000890  min_lr: 0.000890  loss: 2.4260 (2.2959)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [212]  [160/312]  eta: 0:01:17  lr: 0.000889  min_lr: 0.000889  loss: 2.4746 (2.2900)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [212]  [170/312]  eta: 0:01:12  lr: 0.000889  min_lr: 0.000889  loss: 2.2687 (2.2886)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [212]  [180/312]  eta: 0:01:06  lr: 0.000888  min_lr: 0.000888  loss: 2.3621 (2.2911)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [212]  [190/312]  eta: 0:01:01  lr: 0.000888  min_lr: 0.000888  loss: 2.3899 (2.2949)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0003  max mem: 42573
Epoch: [212]  [200/312]  eta: 0:00:55  lr: 0.000887  min_lr: 0.000887  loss: 2.4709 (2.2983)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [212]  [210/312]  eta: 0:00:50  lr: 0.000886  min_lr: 0.000886  loss: 2.4875 (2.3067)  weight_decay: 0.0500 (0.0500)  time: 0.4399  data: 0.0004  max mem: 42573
Epoch: [212]  [220/312]  eta: 0:00:45  lr: 0.000886  min_lr: 0.000886  loss: 2.4049 (2.3043)  weight_decay: 0.0500 (0.0500)  time: 0.4396  data: 0.0004  max mem: 42573
Epoch: [212]  [230/312]  eta: 0:00:40  lr: 0.000885  min_lr: 0.000885  loss: 2.3821 (2.3077)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [212]  [240/312]  eta: 0:00:35  lr: 0.000885  min_lr: 0.000885  loss: 2.3546 (2.3045)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [212]  [250/312]  eta: 0:00:30  lr: 0.000884  min_lr: 0.000884  loss: 2.2104 (2.2983)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [212]  [260/312]  eta: 0:00:25  lr: 0.000883  min_lr: 0.000883  loss: 2.2714 (2.2947)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [212]  [270/312]  eta: 0:00:20  lr: 0.000883  min_lr: 0.000883  loss: 2.3006 (2.2967)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [212]  [280/312]  eta: 0:00:15  lr: 0.000882  min_lr: 0.000882  loss: 2.4208 (2.2974)  weight_decay: 0.0500 (0.0500)  time: 0.4344  data: 0.0009  max mem: 42573
Epoch: [212]  [290/312]  eta: 0:00:10  lr: 0.000882  min_lr: 0.000882  loss: 2.0639 (2.2898)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0008  max mem: 42573
Epoch: [212]  [300/312]  eta: 0:00:05  lr: 0.000881  min_lr: 0.000881  loss: 2.0252 (2.2856)  weight_decay: 0.0500 (0.0500)  time: 0.4321  data: 0.0001  max mem: 42573
Epoch: [212]  [310/312]  eta: 0:00:00  lr: 0.000880  min_lr: 0.000880  loss: 2.2562 (2.2844)  weight_decay: 0.0500 (0.0500)  time: 0.4320  data: 0.0001  max mem: 42573
Epoch: [212]  [311/312]  eta: 0:00:00  lr: 0.000880  min_lr: 0.000880  loss: 2.2562 (2.2843)  weight_decay: 0.0500 (0.0500)  time: 0.4320  data: 0.0001  max mem: 42573
Epoch: [212] Total time: 0:02:29 (0.4782 s / it)
Averaged stats: lr: 0.000880  min_lr: 0.000880  loss: 2.2562 (2.2481)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:00:41  loss: 0.6786 (0.6786)  acc1: 83.5938 (83.5938)  acc5: 94.0104 (94.0104)  time: 4.5869  data: 4.4791  max mem: 42573
Test:  [8/9]  eta: 0:00:00  loss: 0.9342 (0.8795)  acc1: 76.0417 (76.9280)  acc5: 93.2292 (93.2480)  time: 0.5870  data: 0.4978  max mem: 42573
Test: Total time: 0:00:05 (0.5946 s / it)
* Acc@1 77.178 Acc@5 93.458 loss 0.888
Accuracy of the model on the 50000 test images: 77.2%
Max accuracy: 77.23%
Epoch: [213]  [  0/312]  eta: 0:55:30  lr: 0.000880  min_lr: 0.000880  loss: 2.3247 (2.3247)  weight_decay: 0.0500 (0.0500)  time: 10.6762  data: 7.1271  max mem: 42573
Epoch: [213]  [ 10/312]  eta: 0:07:43  lr: 0.000880  min_lr: 0.000880  loss: 2.4931 (2.2642)  weight_decay: 0.0500 (0.0500)  time: 1.5356  data: 0.6484  max mem: 42573
Epoch: [213]  [ 20/312]  eta: 0:04:55  lr: 0.000879  min_lr: 0.000879  loss: 2.3875 (2.2824)  weight_decay: 0.0500 (0.0500)  time: 0.5274  data: 0.0005  max mem: 42573
Epoch: [213]  [ 30/312]  eta: 0:03:52  lr: 0.000879  min_lr: 0.000879  loss: 2.1219 (2.2195)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [213]  [ 40/312]  eta: 0:03:18  lr: 0.000878  min_lr: 0.000878  loss: 1.9788 (2.1995)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [213]  [ 50/312]  eta: 0:02:55  lr: 0.000877  min_lr: 0.000877  loss: 1.8612 (2.1420)  weight_decay: 0.0500 (0.0500)  time: 0.4342  data: 0.0004  max mem: 42573
Epoch: [213]  [ 60/312]  eta: 0:02:39  lr: 0.000877  min_lr: 0.000877  loss: 1.8184 (2.1313)  weight_decay: 0.0500 (0.0500)  time: 0.4365  data: 0.0004  max mem: 42573
Epoch: [213]  [ 70/312]  eta: 0:02:26  lr: 0.000876  min_lr: 0.000876  loss: 2.1184 (2.1305)  weight_decay: 0.0500 (0.0500)  time: 0.4366  data: 0.0004  max mem: 42573
Epoch: [213]  [ 80/312]  eta: 0:02:15  lr: 0.000876  min_lr: 0.000876  loss: 2.0888 (2.1252)  weight_decay: 0.0500 (0.0500)  time: 0.4343  data: 0.0004  max mem: 42573
Epoch: [213]  [ 90/312]  eta: 0:02:06  lr: 0.000875  min_lr: 0.000875  loss: 2.2772 (2.1553)  weight_decay: 0.0500 (0.0500)  time: 0.4341  data: 0.0004  max mem: 42573
Epoch: [213]  [100/312]  eta: 0:01:57  lr: 0.000874  min_lr: 0.000874  loss: 2.2772 (2.1461)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0004  max mem: 42573
Epoch: [213]  [110/312]  eta: 0:01:49  lr: 0.000874  min_lr: 0.000874  loss: 2.1821 (2.1576)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [213]  [120/312]  eta: 0:01:42  lr: 0.000873  min_lr: 0.000873  loss: 2.3851 (2.1687)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [213]  [130/312]  eta: 0:01:35  lr: 0.000873  min_lr: 0.000873  loss: 2.4350 (2.1853)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [213]  [140/312]  eta: 0:01:29  lr: 0.000872  min_lr: 0.000872  loss: 2.3182 (2.1836)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [213]  [150/312]  eta: 0:01:23  lr: 0.000871  min_lr: 0.000871  loss: 2.0447 (2.1839)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [213]  [160/312]  eta: 0:01:17  lr: 0.000871  min_lr: 0.000871  loss: 2.1816 (2.1888)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [213]  [170/312]  eta: 0:01:11  lr: 0.000870  min_lr: 0.000870  loss: 2.3110 (2.1973)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [213]  [180/312]  eta: 0:01:06  lr: 0.000870  min_lr: 0.000870  loss: 2.2252 (2.1890)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [213]  [190/312]  eta: 0:01:00  lr: 0.000869  min_lr: 0.000869  loss: 2.1304 (2.1929)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [213]  [200/312]  eta: 0:00:55  lr: 0.000868  min_lr: 0.000868  loss: 2.1669 (2.1910)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0003  max mem: 42573
Epoch: [213]  [210/312]  eta: 0:00:50  lr: 0.000868  min_lr: 0.000868  loss: 2.2408 (2.1998)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [213]  [220/312]  eta: 0:00:44  lr: 0.000867  min_lr: 0.000867  loss: 2.2949 (2.1947)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [213]  [230/312]  eta: 0:00:39  lr: 0.000867  min_lr: 0.000867  loss: 2.3262 (2.2023)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0003  max mem: 42573
Epoch: [213]  [240/312]  eta: 0:00:34  lr: 0.000866  min_lr: 0.000866  loss: 2.3497 (2.2014)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [213]  [250/312]  eta: 0:00:29  lr: 0.000865  min_lr: 0.000865  loss: 2.3298 (2.2041)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [213]  [260/312]  eta: 0:00:24  lr: 0.000865  min_lr: 0.000865  loss: 2.2066 (2.1988)  weight_decay: 0.0500 (0.0500)  time: 0.4357  data: 0.0004  max mem: 42573
Epoch: [213]  [270/312]  eta: 0:00:20  lr: 0.000864  min_lr: 0.000864  loss: 2.1969 (2.1989)  weight_decay: 0.0500 (0.0500)  time: 0.4356  data: 0.0004  max mem: 42573
Epoch: [213]  [280/312]  eta: 0:00:15  lr: 0.000864  min_lr: 0.000864  loss: 2.1027 (2.1924)  weight_decay: 0.0500 (0.0500)  time: 0.4342  data: 0.0011  max mem: 42573
Epoch: [213]  [290/312]  eta: 0:00:10  lr: 0.000863  min_lr: 0.000863  loss: 2.3812 (2.1995)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0010  max mem: 42573
Epoch: [213]  [300/312]  eta: 0:00:05  lr: 0.000863  min_lr: 0.000863  loss: 2.3647 (2.1980)  weight_decay: 0.0500 (0.0500)  time: 0.4323  data: 0.0001  max mem: 42573
Epoch: [213]  [310/312]  eta: 0:00:00  lr: 0.000862  min_lr: 0.000862  loss: 2.3011 (2.2012)  weight_decay: 0.0500 (0.0500)  time: 0.4321  data: 0.0001  max mem: 42573
Epoch: [213]  [311/312]  eta: 0:00:00  lr: 0.000862  min_lr: 0.000862  loss: 2.3011 (2.2024)  weight_decay: 0.0500 (0.0500)  time: 0.4322  data: 0.0001  max mem: 42573
Epoch: [213] Total time: 0:02:28 (0.4761 s / it)
Averaged stats: lr: 0.000862  min_lr: 0.000862  loss: 2.3011 (2.2428)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:00:39  loss: 0.7644 (0.7644)  acc1: 82.0312 (82.0312)  acc5: 93.2292 (93.2292)  time: 4.4065  data: 4.2986  max mem: 42573
Test:  [8/9]  eta: 0:00:00  loss: 0.9588 (0.9584)  acc1: 76.0417 (75.4880)  acc5: 92.9688 (92.8000)  time: 0.5653  data: 0.4777  max mem: 42573
Test: Total time: 0:00:05 (0.5728 s / it)
* Acc@1 76.286 Acc@5 93.126 loss 0.925
Accuracy of the model on the 50000 test images: 76.3%
Max accuracy: 77.23%
Epoch: [214]  [  0/312]  eta: 0:55:50  lr: 0.000862  min_lr: 0.000862  loss: 2.2630 (2.2630)  weight_decay: 0.0500 (0.0500)  time: 10.7404  data: 8.9381  max mem: 42573
Epoch: [214]  [ 10/312]  eta: 0:07:57  lr: 0.000861  min_lr: 0.000861  loss: 2.2112 (2.2210)  weight_decay: 0.0500 (0.0500)  time: 1.5819  data: 0.8129  max mem: 42573
Epoch: [214]  [ 20/312]  eta: 0:05:02  lr: 0.000861  min_lr: 0.000861  loss: 2.1586 (2.1264)  weight_decay: 0.0500 (0.0500)  time: 0.5498  data: 0.0004  max mem: 42573
Epoch: [214]  [ 30/312]  eta: 0:03:57  lr: 0.000860  min_lr: 0.000860  loss: 2.1165 (2.1751)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0003  max mem: 42573
Epoch: [214]  [ 40/312]  eta: 0:03:21  lr: 0.000859  min_lr: 0.000859  loss: 2.2910 (2.1676)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0003  max mem: 42573
Epoch: [214]  [ 50/312]  eta: 0:02:58  lr: 0.000859  min_lr: 0.000859  loss: 2.2413 (2.1988)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [214]  [ 60/312]  eta: 0:02:41  lr: 0.000858  min_lr: 0.000858  loss: 2.3085 (2.2131)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [214]  [ 70/312]  eta: 0:02:28  lr: 0.000858  min_lr: 0.000858  loss: 2.2358 (2.1981)  weight_decay: 0.0500 (0.0500)  time: 0.4343  data: 0.0004  max mem: 42573
Epoch: [214]  [ 80/312]  eta: 0:02:16  lr: 0.000857  min_lr: 0.000857  loss: 2.2358 (2.2162)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [214]  [ 90/312]  eta: 0:02:07  lr: 0.000857  min_lr: 0.000857  loss: 2.4327 (2.2218)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [214]  [100/312]  eta: 0:01:58  lr: 0.000856  min_lr: 0.000856  loss: 2.4327 (2.2342)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [214]  [110/312]  eta: 0:01:50  lr: 0.000855  min_lr: 0.000855  loss: 2.3345 (2.2384)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0003  max mem: 42573
Epoch: [214]  [120/312]  eta: 0:01:43  lr: 0.000855  min_lr: 0.000855  loss: 2.4136 (2.2617)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [214]  [130/312]  eta: 0:01:36  lr: 0.000854  min_lr: 0.000854  loss: 2.3892 (2.2610)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [214]  [140/312]  eta: 0:01:29  lr: 0.000854  min_lr: 0.000854  loss: 2.2053 (2.2648)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [214]  [150/312]  eta: 0:01:23  lr: 0.000853  min_lr: 0.000853  loss: 2.2292 (2.2596)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [214]  [160/312]  eta: 0:01:17  lr: 0.000852  min_lr: 0.000852  loss: 2.0814 (2.2533)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [214]  [170/312]  eta: 0:01:12  lr: 0.000852  min_lr: 0.000852  loss: 2.1770 (2.2566)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [214]  [180/312]  eta: 0:01:06  lr: 0.000851  min_lr: 0.000851  loss: 2.3146 (2.2591)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [214]  [190/312]  eta: 0:01:00  lr: 0.000851  min_lr: 0.000851  loss: 2.4301 (2.2699)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [214]  [200/312]  eta: 0:00:55  lr: 0.000850  min_lr: 0.000850  loss: 2.4094 (2.2728)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [214]  [210/312]  eta: 0:00:50  lr: 0.000849  min_lr: 0.000849  loss: 2.2049 (2.2617)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [214]  [220/312]  eta: 0:00:45  lr: 0.000849  min_lr: 0.000849  loss: 2.0727 (2.2510)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [214]  [230/312]  eta: 0:00:40  lr: 0.000848  min_lr: 0.000848  loss: 2.2284 (2.2533)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [214]  [240/312]  eta: 0:00:34  lr: 0.000848  min_lr: 0.000848  loss: 2.3992 (2.2541)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [214]  [250/312]  eta: 0:00:29  lr: 0.000847  min_lr: 0.000847  loss: 2.2442 (2.2541)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [214]  [260/312]  eta: 0:00:25  lr: 0.000846  min_lr: 0.000846  loss: 2.3815 (2.2559)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [214]  [270/312]  eta: 0:00:20  lr: 0.000846  min_lr: 0.000846  loss: 2.3815 (2.2612)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [214]  [280/312]  eta: 0:00:15  lr: 0.000845  min_lr: 0.000845  loss: 2.2372 (2.2554)  weight_decay: 0.0500 (0.0500)  time: 0.4392  data: 0.0009  max mem: 42573
Epoch: [214]  [290/312]  eta: 0:00:10  lr: 0.000845  min_lr: 0.000845  loss: 2.2372 (2.2599)  weight_decay: 0.0500 (0.0500)  time: 0.4392  data: 0.0008  max mem: 42573
Epoch: [214]  [300/312]  eta: 0:00:05  lr: 0.000844  min_lr: 0.000844  loss: 2.3889 (2.2579)  weight_decay: 0.0500 (0.0500)  time: 0.4327  data: 0.0001  max mem: 42573
Epoch: [214]  [310/312]  eta: 0:00:00  lr: 0.000844  min_lr: 0.000844  loss: 2.2883 (2.2554)  weight_decay: 0.0500 (0.0500)  time: 0.4321  data: 0.0001  max mem: 42573
Epoch: [214]  [311/312]  eta: 0:00:00  lr: 0.000844  min_lr: 0.000844  loss: 2.2883 (2.2548)  weight_decay: 0.0500 (0.0500)  time: 0.4321  data: 0.0001  max mem: 42573
Epoch: [214] Total time: 0:02:28 (0.4776 s / it)
Averaged stats: lr: 0.000844  min_lr: 0.000844  loss: 2.2883 (2.2440)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:00:40  loss: 0.6941 (0.6941)  acc1: 82.5521 (82.5521)  acc5: 94.7917 (94.7917)  time: 4.4497  data: 4.3419  max mem: 42573
Test:  [8/9]  eta: 0:00:00  loss: 0.9016 (0.9186)  acc1: 76.5625 (75.8080)  acc5: 93.4896 (93.3440)  time: 0.5725  data: 0.4825  max mem: 42573
Test: Total time: 0:00:05 (0.5795 s / it)
* Acc@1 76.824 Acc@5 93.350 loss 0.904
Accuracy of the model on the 50000 test images: 76.8%
Max accuracy: 77.23%
Epoch: [215]  [  0/312]  eta: 0:54:03  lr: 0.000843  min_lr: 0.000843  loss: 2.5753 (2.5753)  weight_decay: 0.0500 (0.0500)  time: 10.3967  data: 7.6858  max mem: 42573
Epoch: [215]  [ 10/312]  eta: 0:07:54  lr: 0.000843  min_lr: 0.000843  loss: 2.1600 (2.2064)  weight_decay: 0.0500 (0.0500)  time: 1.5702  data: 0.6990  max mem: 42573
Epoch: [215]  [ 20/312]  eta: 0:05:00  lr: 0.000842  min_lr: 0.000842  loss: 2.1600 (2.1932)  weight_decay: 0.0500 (0.0500)  time: 0.5606  data: 0.0003  max mem: 42573
Epoch: [215]  [ 30/312]  eta: 0:03:56  lr: 0.000842  min_lr: 0.000842  loss: 2.2968 (2.2411)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0003  max mem: 42573
Epoch: [215]  [ 40/312]  eta: 0:03:21  lr: 0.000841  min_lr: 0.000841  loss: 2.0775 (2.1830)  weight_decay: 0.0500 (0.0500)  time: 0.4352  data: 0.0004  max mem: 42573
Epoch: [215]  [ 50/312]  eta: 0:02:58  lr: 0.000841  min_lr: 0.000841  loss: 2.1094 (2.1867)  weight_decay: 0.0500 (0.0500)  time: 0.4355  data: 0.0004  max mem: 42573
Epoch: [215]  [ 60/312]  eta: 0:02:41  lr: 0.000840  min_lr: 0.000840  loss: 2.1919 (2.2023)  weight_decay: 0.0500 (0.0500)  time: 0.4361  data: 0.0004  max mem: 42573
Epoch: [215]  [ 70/312]  eta: 0:02:27  lr: 0.000839  min_lr: 0.000839  loss: 2.1676 (2.1998)  weight_decay: 0.0500 (0.0500)  time: 0.4356  data: 0.0004  max mem: 42573
Epoch: [215]  [ 80/312]  eta: 0:02:16  lr: 0.000839  min_lr: 0.000839  loss: 2.2498 (2.2115)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0004  max mem: 42573
Epoch: [215]  [ 90/312]  eta: 0:02:06  lr: 0.000838  min_lr: 0.000838  loss: 2.2129 (2.1980)  weight_decay: 0.0500 (0.0500)  time: 0.4341  data: 0.0004  max mem: 42573
Epoch: [215]  [100/312]  eta: 0:01:58  lr: 0.000838  min_lr: 0.000838  loss: 2.2129 (2.2011)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [215]  [110/312]  eta: 0:01:50  lr: 0.000837  min_lr: 0.000837  loss: 2.1516 (2.1926)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [215]  [120/312]  eta: 0:01:43  lr: 0.000836  min_lr: 0.000836  loss: 2.1550 (2.2010)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0004  max mem: 42573
Epoch: [215]  [130/312]  eta: 0:01:36  lr: 0.000836  min_lr: 0.000836  loss: 2.4891 (2.2180)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [215]  [140/312]  eta: 0:01:29  lr: 0.000835  min_lr: 0.000835  loss: 2.5231 (2.2256)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [215]  [150/312]  eta: 0:01:23  lr: 0.000835  min_lr: 0.000835  loss: 2.3909 (2.2334)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [215]  [160/312]  eta: 0:01:17  lr: 0.000834  min_lr: 0.000834  loss: 2.3880 (2.2397)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [215]  [170/312]  eta: 0:01:12  lr: 0.000833  min_lr: 0.000833  loss: 2.3079 (2.2316)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [215]  [180/312]  eta: 0:01:06  lr: 0.000833  min_lr: 0.000833  loss: 2.4053 (2.2410)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [215]  [190/312]  eta: 0:01:00  lr: 0.000832  min_lr: 0.000832  loss: 2.4105 (2.2446)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [215]  [200/312]  eta: 0:00:55  lr: 0.000832  min_lr: 0.000832  loss: 2.4029 (2.2553)  weight_decay: 0.0500 (0.0500)  time: 0.4390  data: 0.0004  max mem: 42573
Epoch: [215]  [210/312]  eta: 0:00:50  lr: 0.000831  min_lr: 0.000831  loss: 2.3176 (2.2541)  weight_decay: 0.0500 (0.0500)  time: 0.4391  data: 0.0004  max mem: 42573
Epoch: [215]  [220/312]  eta: 0:00:45  lr: 0.000831  min_lr: 0.000831  loss: 2.3153 (2.2591)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [215]  [230/312]  eta: 0:00:40  lr: 0.000830  min_lr: 0.000830  loss: 2.3315 (2.2574)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [215]  [240/312]  eta: 0:00:35  lr: 0.000829  min_lr: 0.000829  loss: 2.2996 (2.2577)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [215]  [250/312]  eta: 0:00:30  lr: 0.000829  min_lr: 0.000829  loss: 2.3019 (2.2575)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [215]  [260/312]  eta: 0:00:25  lr: 0.000828  min_lr: 0.000828  loss: 2.2840 (2.2558)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [215]  [270/312]  eta: 0:00:20  lr: 0.000828  min_lr: 0.000828  loss: 2.2795 (2.2534)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [215]  [280/312]  eta: 0:00:15  lr: 0.000827  min_lr: 0.000827  loss: 2.2795 (2.2518)  weight_decay: 0.0500 (0.0500)  time: 0.4349  data: 0.0021  max mem: 42573
Epoch: [215]  [290/312]  eta: 0:00:10  lr: 0.000827  min_lr: 0.000827  loss: 2.3766 (2.2580)  weight_decay: 0.0500 (0.0500)  time: 0.4342  data: 0.0019  max mem: 42573
Epoch: [215]  [300/312]  eta: 0:00:05  lr: 0.000826  min_lr: 0.000826  loss: 2.3766 (2.2600)  weight_decay: 0.0500 (0.0500)  time: 0.4321  data: 0.0001  max mem: 42573
Epoch: [215]  [310/312]  eta: 0:00:00  lr: 0.000825  min_lr: 0.000825  loss: 2.3012 (2.2618)  weight_decay: 0.0500 (0.0500)  time: 0.4321  data: 0.0001  max mem: 42573
Epoch: [215]  [311/312]  eta: 0:00:00  lr: 0.000825  min_lr: 0.000825  loss: 2.3012 (2.2619)  weight_decay: 0.0500 (0.0500)  time: 0.4321  data: 0.0001  max mem: 42573
Epoch: [215] Total time: 0:02:28 (0.4775 s / it)
Averaged stats: lr: 0.000825  min_lr: 0.000825  loss: 2.3012 (2.2335)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:00:41  loss: 0.6725 (0.6725)  acc1: 82.2917 (82.2917)  acc5: 94.7917 (94.7917)  time: 4.5679  data: 4.4600  max mem: 42573
Test:  [8/9]  eta: 0:00:00  loss: 0.9662 (0.9202)  acc1: 76.0417 (76.0320)  acc5: 93.2292 (93.3440)  time: 0.5826  data: 0.4956  max mem: 42573
Test: Total time: 0:00:05 (0.5922 s / it)
* Acc@1 77.062 Acc@5 93.432 loss 0.916
Accuracy of the model on the 50000 test images: 77.1%
Max accuracy: 77.23%
Epoch: [216]  [  0/312]  eta: 0:54:44  lr: 0.000825  min_lr: 0.000825  loss: 2.3841 (2.3841)  weight_decay: 0.0500 (0.0500)  time: 10.5275  data: 8.7079  max mem: 42573
Epoch: [216]  [ 10/312]  eta: 0:07:54  lr: 0.000825  min_lr: 0.000825  loss: 2.2443 (2.1204)  weight_decay: 0.0500 (0.0500)  time: 1.5714  data: 0.7920  max mem: 42573
Epoch: [216]  [ 20/312]  eta: 0:05:00  lr: 0.000824  min_lr: 0.000824  loss: 2.2936 (2.1899)  weight_decay: 0.0500 (0.0500)  time: 0.5547  data: 0.0004  max mem: 42573
Epoch: [216]  [ 30/312]  eta: 0:03:56  lr: 0.000823  min_lr: 0.000823  loss: 2.3104 (2.2184)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [216]  [ 40/312]  eta: 0:03:20  lr: 0.000823  min_lr: 0.000823  loss: 2.3249 (2.2269)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [216]  [ 50/312]  eta: 0:02:57  lr: 0.000822  min_lr: 0.000822  loss: 2.3420 (2.2375)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [216]  [ 60/312]  eta: 0:02:40  lr: 0.000822  min_lr: 0.000822  loss: 2.2286 (2.2368)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [216]  [ 70/312]  eta: 0:02:27  lr: 0.000821  min_lr: 0.000821  loss: 2.1561 (2.2024)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [216]  [ 80/312]  eta: 0:02:16  lr: 0.000821  min_lr: 0.000821  loss: 2.2710 (2.2258)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [216]  [ 90/312]  eta: 0:02:06  lr: 0.000820  min_lr: 0.000820  loss: 2.4072 (2.2350)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [216]  [100/312]  eta: 0:01:58  lr: 0.000819  min_lr: 0.000819  loss: 2.2816 (2.2226)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [216]  [110/312]  eta: 0:01:50  lr: 0.000819  min_lr: 0.000819  loss: 2.3387 (2.2306)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [216]  [120/312]  eta: 0:01:43  lr: 0.000818  min_lr: 0.000818  loss: 2.2350 (2.2189)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [216]  [130/312]  eta: 0:01:36  lr: 0.000818  min_lr: 0.000818  loss: 2.2350 (2.2246)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [216]  [140/312]  eta: 0:01:29  lr: 0.000817  min_lr: 0.000817  loss: 2.3916 (2.2151)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [216]  [150/312]  eta: 0:01:23  lr: 0.000817  min_lr: 0.000817  loss: 2.1454 (2.2110)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [216]  [160/312]  eta: 0:01:17  lr: 0.000816  min_lr: 0.000816  loss: 2.1454 (2.2018)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [216]  [170/312]  eta: 0:01:12  lr: 0.000815  min_lr: 0.000815  loss: 2.1650 (2.2057)  weight_decay: 0.0500 (0.0500)  time: 0.4409  data: 0.0004  max mem: 42573
Epoch: [216]  [180/312]  eta: 0:01:06  lr: 0.000815  min_lr: 0.000815  loss: 2.2655 (2.2042)  weight_decay: 0.0500 (0.0500)  time: 0.4409  data: 0.0004  max mem: 42573
Epoch: [216]  [190/312]  eta: 0:01:00  lr: 0.000814  min_lr: 0.000814  loss: 2.2655 (2.2010)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [216]  [200/312]  eta: 0:00:55  lr: 0.000814  min_lr: 0.000814  loss: 2.2186 (2.1920)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [216]  [210/312]  eta: 0:00:50  lr: 0.000813  min_lr: 0.000813  loss: 2.1960 (2.1903)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [216]  [220/312]  eta: 0:00:45  lr: 0.000812  min_lr: 0.000812  loss: 2.2162 (2.1942)  weight_decay: 0.0500 (0.0500)  time: 0.4332  data: 0.0003  max mem: 42573
Epoch: [216]  [230/312]  eta: 0:00:40  lr: 0.000812  min_lr: 0.000812  loss: 2.2533 (2.1986)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [216]  [240/312]  eta: 0:00:35  lr: 0.000811  min_lr: 0.000811  loss: 2.2975 (2.2006)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [216]  [250/312]  eta: 0:00:30  lr: 0.000811  min_lr: 0.000811  loss: 2.3570 (2.2050)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [216]  [260/312]  eta: 0:00:25  lr: 0.000810  min_lr: 0.000810  loss: 2.4098 (2.2068)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [216]  [270/312]  eta: 0:00:20  lr: 0.000810  min_lr: 0.000810  loss: 2.1009 (2.2026)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [216]  [280/312]  eta: 0:00:15  lr: 0.000809  min_lr: 0.000809  loss: 2.2334 (2.2101)  weight_decay: 0.0500 (0.0500)  time: 0.4343  data: 0.0014  max mem: 42573
Epoch: [216]  [290/312]  eta: 0:00:10  lr: 0.000808  min_lr: 0.000808  loss: 2.2830 (2.2068)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0013  max mem: 42573
Epoch: [216]  [300/312]  eta: 0:00:05  lr: 0.000808  min_lr: 0.000808  loss: 2.2910 (2.2149)  weight_decay: 0.0500 (0.0500)  time: 0.4321  data: 0.0001  max mem: 42573
Epoch: [216]  [310/312]  eta: 0:00:00  lr: 0.000807  min_lr: 0.000807  loss: 2.4484 (2.2227)  weight_decay: 0.0500 (0.0500)  time: 0.4320  data: 0.0001  max mem: 42573
Epoch: [216]  [311/312]  eta: 0:00:00  lr: 0.000807  min_lr: 0.000807  loss: 2.4484 (2.2241)  weight_decay: 0.0500 (0.0500)  time: 0.4320  data: 0.0001  max mem: 42573
Epoch: [216] Total time: 0:02:28 (0.4773 s / it)
Averaged stats: lr: 0.000807  min_lr: 0.000807  loss: 2.4484 (2.2253)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:00:39  loss: 0.7212 (0.7212)  acc1: 83.5938 (83.5938)  acc5: 94.0104 (94.0104)  time: 4.4213  data: 4.3128  max mem: 42573
Test:  [8/9]  eta: 0:00:00  loss: 0.9020 (0.9002)  acc1: 76.5625 (76.0960)  acc5: 94.0104 (93.5360)  time: 0.5671  data: 0.4793  max mem: 42573
Test: Total time: 0:00:05 (0.5792 s / it)
* Acc@1 77.552 Acc@5 93.692 loss 0.875
Accuracy of the model on the 50000 test images: 77.6%
Max accuracy: 77.55%
Epoch: [217]  [  0/312]  eta: 0:53:03  lr: 0.000807  min_lr: 0.000807  loss: 2.3118 (2.3118)  weight_decay: 0.0500 (0.0500)  time: 10.2048  data: 6.4355  max mem: 42573
Epoch: [217]  [ 10/312]  eta: 0:07:42  lr: 0.000807  min_lr: 0.000807  loss: 2.0322 (2.0139)  weight_decay: 0.0500 (0.0500)  time: 1.5314  data: 0.7581  max mem: 42573
Epoch: [217]  [ 20/312]  eta: 0:04:54  lr: 0.000806  min_lr: 0.000806  loss: 2.0322 (2.0649)  weight_decay: 0.0500 (0.0500)  time: 0.5485  data: 0.0954  max mem: 42573
Epoch: [217]  [ 30/312]  eta: 0:03:52  lr: 0.000805  min_lr: 0.000805  loss: 1.9894 (2.0249)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [217]  [ 40/312]  eta: 0:03:18  lr: 0.000805  min_lr: 0.000805  loss: 2.1235 (2.0795)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [217]  [ 50/312]  eta: 0:02:55  lr: 0.000804  min_lr: 0.000804  loss: 2.1900 (2.0661)  weight_decay: 0.0500 (0.0500)  time: 0.4344  data: 0.0004  max mem: 42573
Epoch: [217]  [ 60/312]  eta: 0:02:39  lr: 0.000804  min_lr: 0.000804  loss: 2.2158 (2.1062)  weight_decay: 0.0500 (0.0500)  time: 0.4342  data: 0.0004  max mem: 42573
Epoch: [217]  [ 70/312]  eta: 0:02:26  lr: 0.000803  min_lr: 0.000803  loss: 2.2354 (2.1185)  weight_decay: 0.0500 (0.0500)  time: 0.4343  data: 0.0004  max mem: 42573
Epoch: [217]  [ 80/312]  eta: 0:02:15  lr: 0.000803  min_lr: 0.000803  loss: 2.2083 (2.1139)  weight_decay: 0.0500 (0.0500)  time: 0.4348  data: 0.0004  max mem: 42573
Epoch: [217]  [ 90/312]  eta: 0:02:05  lr: 0.000802  min_lr: 0.000802  loss: 2.1518 (2.1194)  weight_decay: 0.0500 (0.0500)  time: 0.4344  data: 0.0004  max mem: 42573
Epoch: [217]  [100/312]  eta: 0:01:57  lr: 0.000801  min_lr: 0.000801  loss: 2.1546 (2.1440)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [217]  [110/312]  eta: 0:01:49  lr: 0.000801  min_lr: 0.000801  loss: 2.4037 (2.1500)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [217]  [120/312]  eta: 0:01:42  lr: 0.000800  min_lr: 0.000800  loss: 2.4097 (2.1666)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0004  max mem: 42573
Epoch: [217]  [130/312]  eta: 0:01:35  lr: 0.000800  min_lr: 0.000800  loss: 2.4005 (2.1684)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [217]  [140/312]  eta: 0:01:29  lr: 0.000799  min_lr: 0.000799  loss: 2.2059 (2.1668)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [217]  [150/312]  eta: 0:01:23  lr: 0.000799  min_lr: 0.000799  loss: 2.1400 (2.1659)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [217]  [160/312]  eta: 0:01:17  lr: 0.000798  min_lr: 0.000798  loss: 2.2958 (2.1770)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0005  max mem: 42573
Epoch: [217]  [170/312]  eta: 0:01:11  lr: 0.000797  min_lr: 0.000797  loss: 2.3641 (2.1784)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0005  max mem: 42573
Epoch: [217]  [180/312]  eta: 0:01:06  lr: 0.000797  min_lr: 0.000797  loss: 2.1080 (2.1707)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0005  max mem: 42573
Epoch: [217]  [190/312]  eta: 0:01:00  lr: 0.000796  min_lr: 0.000796  loss: 2.2858 (2.1782)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [217]  [200/312]  eta: 0:00:55  lr: 0.000796  min_lr: 0.000796  loss: 2.4720 (2.1903)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [217]  [210/312]  eta: 0:00:50  lr: 0.000795  min_lr: 0.000795  loss: 2.3505 (2.1861)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [217]  [220/312]  eta: 0:00:44  lr: 0.000794  min_lr: 0.000794  loss: 2.1115 (2.1840)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [217]  [230/312]  eta: 0:00:39  lr: 0.000794  min_lr: 0.000794  loss: 2.2067 (2.1857)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [217]  [240/312]  eta: 0:00:34  lr: 0.000793  min_lr: 0.000793  loss: 2.3268 (2.1902)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [217]  [250/312]  eta: 0:00:29  lr: 0.000793  min_lr: 0.000793  loss: 2.1276 (2.1824)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [217]  [260/312]  eta: 0:00:24  lr: 0.000792  min_lr: 0.000792  loss: 2.2959 (2.1897)  weight_decay: 0.0500 (0.0500)  time: 0.4361  data: 0.0004  max mem: 42573
Epoch: [217]  [270/312]  eta: 0:00:20  lr: 0.000792  min_lr: 0.000792  loss: 2.3275 (2.1909)  weight_decay: 0.0500 (0.0500)  time: 0.4361  data: 0.0004  max mem: 42573
Epoch: [217]  [280/312]  eta: 0:00:15  lr: 0.000791  min_lr: 0.000791  loss: 2.2181 (2.1881)  weight_decay: 0.0500 (0.0500)  time: 0.4346  data: 0.0010  max mem: 42573
Epoch: [217]  [290/312]  eta: 0:00:10  lr: 0.000790  min_lr: 0.000790  loss: 2.0568 (2.1862)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0009  max mem: 42573
Epoch: [217]  [300/312]  eta: 0:00:05  lr: 0.000790  min_lr: 0.000790  loss: 2.2583 (2.1874)  weight_decay: 0.0500 (0.0500)  time: 0.4322  data: 0.0001  max mem: 42573
Epoch: [217]  [310/312]  eta: 0:00:00  lr: 0.000789  min_lr: 0.000789  loss: 2.3409 (2.1866)  weight_decay: 0.0500 (0.0500)  time: 0.4321  data: 0.0001  max mem: 42573
Epoch: [217]  [311/312]  eta: 0:00:00  lr: 0.000789  min_lr: 0.000789  loss: 2.3409 (2.1865)  weight_decay: 0.0500 (0.0500)  time: 0.4321  data: 0.0001  max mem: 42573
Epoch: [217] Total time: 0:02:28 (0.4755 s / it)
Averaged stats: lr: 0.000789  min_lr: 0.000789  loss: 2.3409 (2.2285)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:00:39  loss: 0.6499 (0.6499)  acc1: 84.3750 (84.3750)  acc5: 95.0521 (95.0521)  time: 4.3622  data: 4.2550  max mem: 42573
Test:  [8/9]  eta: 0:00:00  loss: 0.8762 (0.8831)  acc1: 77.6042 (76.8640)  acc5: 93.7500 (93.4080)  time: 0.5684  data: 0.4774  max mem: 42573
Test: Total time: 0:00:05 (0.5753 s / it)
* Acc@1 77.522 Acc@5 93.602 loss 0.869
Accuracy of the model on the 50000 test images: 77.5%
Max accuracy: 77.55%
Epoch: [218]  [  0/312]  eta: 0:54:05  lr: 0.000789  min_lr: 0.000789  loss: 2.2962 (2.2962)  weight_decay: 0.0500 (0.0500)  time: 10.4029  data: 7.2339  max mem: 42573
Epoch: [218]  [ 10/312]  eta: 0:08:03  lr: 0.000789  min_lr: 0.000789  loss: 2.2962 (2.2395)  weight_decay: 0.0500 (0.0500)  time: 1.6015  data: 0.6645  max mem: 42573
Epoch: [218]  [ 20/312]  eta: 0:05:05  lr: 0.000788  min_lr: 0.000788  loss: 2.2919 (2.2080)  weight_decay: 0.0500 (0.0500)  time: 0.5772  data: 0.0040  max mem: 42573
Epoch: [218]  [ 30/312]  eta: 0:03:59  lr: 0.000788  min_lr: 0.000788  loss: 2.3755 (2.2652)  weight_decay: 0.0500 (0.0500)  time: 0.4344  data: 0.0004  max mem: 42573
Epoch: [218]  [ 40/312]  eta: 0:03:23  lr: 0.000787  min_lr: 0.000787  loss: 2.3973 (2.2849)  weight_decay: 0.0500 (0.0500)  time: 0.4364  data: 0.0004  max mem: 42573
Epoch: [218]  [ 50/312]  eta: 0:02:59  lr: 0.000786  min_lr: 0.000786  loss: 2.3490 (2.2471)  weight_decay: 0.0500 (0.0500)  time: 0.4356  data: 0.0004  max mem: 42573
Epoch: [218]  [ 60/312]  eta: 0:02:42  lr: 0.000786  min_lr: 0.000786  loss: 2.1980 (2.2235)  weight_decay: 0.0500 (0.0500)  time: 0.4341  data: 0.0004  max mem: 42573
Epoch: [218]  [ 70/312]  eta: 0:02:28  lr: 0.000785  min_lr: 0.000785  loss: 2.2787 (2.2326)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [218]  [ 80/312]  eta: 0:02:17  lr: 0.000785  min_lr: 0.000785  loss: 2.3692 (2.2403)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [218]  [ 90/312]  eta: 0:02:07  lr: 0.000784  min_lr: 0.000784  loss: 2.3007 (2.2168)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [218]  [100/312]  eta: 0:01:59  lr: 0.000784  min_lr: 0.000784  loss: 2.3419 (2.2372)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [218]  [110/312]  eta: 0:01:51  lr: 0.000783  min_lr: 0.000783  loss: 2.3848 (2.2403)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [218]  [120/312]  eta: 0:01:43  lr: 0.000782  min_lr: 0.000782  loss: 2.3848 (2.2410)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0003  max mem: 42573
Epoch: [218]  [130/312]  eta: 0:01:36  lr: 0.000782  min_lr: 0.000782  loss: 2.3465 (2.2401)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0003  max mem: 42573
Epoch: [218]  [140/312]  eta: 0:01:30  lr: 0.000781  min_lr: 0.000781  loss: 2.3671 (2.2422)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [218]  [150/312]  eta: 0:01:24  lr: 0.000781  min_lr: 0.000781  loss: 2.3711 (2.2399)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [218]  [160/312]  eta: 0:01:18  lr: 0.000780  min_lr: 0.000780  loss: 2.3139 (2.2447)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [218]  [170/312]  eta: 0:01:12  lr: 0.000780  min_lr: 0.000780  loss: 2.2304 (2.2358)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0003  max mem: 42573
Epoch: [218]  [180/312]  eta: 0:01:06  lr: 0.000779  min_lr: 0.000779  loss: 2.2700 (2.2374)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [218]  [190/312]  eta: 0:01:01  lr: 0.000778  min_lr: 0.000778  loss: 2.3039 (2.2402)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [218]  [200/312]  eta: 0:00:55  lr: 0.000778  min_lr: 0.000778  loss: 2.2702 (2.2411)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [218]  [210/312]  eta: 0:00:50  lr: 0.000777  min_lr: 0.000777  loss: 2.3789 (2.2425)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [218]  [220/312]  eta: 0:00:45  lr: 0.000777  min_lr: 0.000777  loss: 2.3216 (2.2470)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [218]  [230/312]  eta: 0:00:40  lr: 0.000776  min_lr: 0.000776  loss: 2.3559 (2.2495)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [218]  [240/312]  eta: 0:00:35  lr: 0.000776  min_lr: 0.000776  loss: 2.2390 (2.2409)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [218]  [250/312]  eta: 0:00:30  lr: 0.000775  min_lr: 0.000775  loss: 2.2377 (2.2479)  weight_decay: 0.0500 (0.0500)  time: 0.4332  data: 0.0004  max mem: 42573
Epoch: [218]  [260/312]  eta: 0:00:25  lr: 0.000774  min_lr: 0.000774  loss: 2.3489 (2.2476)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [218]  [270/312]  eta: 0:00:20  lr: 0.000774  min_lr: 0.000774  loss: 2.3391 (2.2473)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [218]  [280/312]  eta: 0:00:15  lr: 0.000773  min_lr: 0.000773  loss: 2.3391 (2.2466)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0010  max mem: 42573
Epoch: [218]  [290/312]  eta: 0:00:10  lr: 0.000773  min_lr: 0.000773  loss: 2.3337 (2.2510)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0008  max mem: 42573
Epoch: [218]  [300/312]  eta: 0:00:05  lr: 0.000772  min_lr: 0.000772  loss: 2.3371 (2.2534)  weight_decay: 0.0500 (0.0500)  time: 0.4320  data: 0.0001  max mem: 42573
Epoch: [218]  [310/312]  eta: 0:00:00  lr: 0.000772  min_lr: 0.000772  loss: 2.3879 (2.2527)  weight_decay: 0.0500 (0.0500)  time: 0.4320  data: 0.0001  max mem: 42573
Epoch: [218]  [311/312]  eta: 0:00:00  lr: 0.000772  min_lr: 0.000772  loss: 2.3879 (2.2538)  weight_decay: 0.0500 (0.0500)  time: 0.4319  data: 0.0001  max mem: 42573
Epoch: [218] Total time: 0:02:29 (0.4780 s / it)
Averaged stats: lr: 0.000772  min_lr: 0.000772  loss: 2.3879 (2.2354)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:00:41  loss: 0.6750 (0.6750)  acc1: 84.6354 (84.6354)  acc5: 95.8333 (95.8333)  time: 4.6095  data: 4.5012  max mem: 42573
Test:  [8/9]  eta: 0:00:00  loss: 0.9260 (0.8764)  acc1: 75.7812 (77.0240)  acc5: 94.2708 (93.6320)  time: 0.5876  data: 0.5002  max mem: 42573
Test: Total time: 0:00:05 (0.6024 s / it)
* Acc@1 77.528 Acc@5 93.550 loss 0.876
Accuracy of the model on the 50000 test images: 77.5%
Max accuracy: 77.55%
Epoch: [219]  [  0/312]  eta: 0:52:32  lr: 0.000771  min_lr: 0.000771  loss: 2.1791 (2.1791)  weight_decay: 0.0500 (0.0500)  time: 10.1028  data: 8.2005  max mem: 42573
Epoch: [219]  [ 10/312]  eta: 0:07:50  lr: 0.000771  min_lr: 0.000771  loss: 2.3682 (2.3089)  weight_decay: 0.0500 (0.0500)  time: 1.5595  data: 0.7458  max mem: 42573
Epoch: [219]  [ 20/312]  eta: 0:04:58  lr: 0.000770  min_lr: 0.000770  loss: 2.4426 (2.3613)  weight_decay: 0.0500 (0.0500)  time: 0.5692  data: 0.0004  max mem: 42573
Epoch: [219]  [ 30/312]  eta: 0:03:54  lr: 0.000770  min_lr: 0.000770  loss: 2.2701 (2.3054)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [219]  [ 40/312]  eta: 0:03:20  lr: 0.000769  min_lr: 0.000769  loss: 2.3024 (2.3038)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0004  max mem: 42573
Epoch: [219]  [ 50/312]  eta: 0:02:57  lr: 0.000769  min_lr: 0.000769  loss: 2.3024 (2.2643)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [219]  [ 60/312]  eta: 0:02:40  lr: 0.000768  min_lr: 0.000768  loss: 2.3136 (2.2905)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [219]  [ 70/312]  eta: 0:02:27  lr: 0.000767  min_lr: 0.000767  loss: 2.4311 (2.2810)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [219]  [ 80/312]  eta: 0:02:16  lr: 0.000767  min_lr: 0.000767  loss: 2.3677 (2.2575)  weight_decay: 0.0500 (0.0500)  time: 0.4342  data: 0.0004  max mem: 42573
Epoch: [219]  [ 90/312]  eta: 0:02:06  lr: 0.000766  min_lr: 0.000766  loss: 2.1815 (2.2478)  weight_decay: 0.0500 (0.0500)  time: 0.4346  data: 0.0004  max mem: 42573
Epoch: [219]  [100/312]  eta: 0:01:57  lr: 0.000766  min_lr: 0.000766  loss: 2.1428 (2.2414)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [219]  [110/312]  eta: 0:01:50  lr: 0.000765  min_lr: 0.000765  loss: 2.3241 (2.2427)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [219]  [120/312]  eta: 0:01:42  lr: 0.000765  min_lr: 0.000765  loss: 2.3597 (2.2373)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [219]  [130/312]  eta: 0:01:36  lr: 0.000764  min_lr: 0.000764  loss: 2.1822 (2.2339)  weight_decay: 0.0500 (0.0500)  time: 0.4350  data: 0.0005  max mem: 42573
Epoch: [219]  [140/312]  eta: 0:01:29  lr: 0.000764  min_lr: 0.000764  loss: 2.3074 (2.2352)  weight_decay: 0.0500 (0.0500)  time: 0.4346  data: 0.0004  max mem: 42573
Epoch: [219]  [150/312]  eta: 0:01:23  lr: 0.000763  min_lr: 0.000763  loss: 2.3074 (2.2258)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0003  max mem: 42573
Epoch: [219]  [160/312]  eta: 0:01:17  lr: 0.000762  min_lr: 0.000762  loss: 2.2506 (2.2285)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [219]  [170/312]  eta: 0:01:11  lr: 0.000762  min_lr: 0.000762  loss: 2.2876 (2.2278)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [219]  [180/312]  eta: 0:01:06  lr: 0.000761  min_lr: 0.000761  loss: 2.1417 (2.2193)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [219]  [190/312]  eta: 0:01:00  lr: 0.000761  min_lr: 0.000761  loss: 2.0050 (2.2080)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [219]  [200/312]  eta: 0:00:55  lr: 0.000760  min_lr: 0.000760  loss: 2.0069 (2.2082)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [219]  [210/312]  eta: 0:00:50  lr: 0.000760  min_lr: 0.000760  loss: 2.2986 (2.2060)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [219]  [220/312]  eta: 0:00:45  lr: 0.000759  min_lr: 0.000759  loss: 2.1530 (2.2014)  weight_decay: 0.0500 (0.0500)  time: 0.4332  data: 0.0004  max mem: 42573
Epoch: [219]  [230/312]  eta: 0:00:39  lr: 0.000758  min_lr: 0.000758  loss: 2.0235 (2.1996)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [219]  [240/312]  eta: 0:00:34  lr: 0.000758  min_lr: 0.000758  loss: 2.2531 (2.2031)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [219]  [250/312]  eta: 0:00:29  lr: 0.000757  min_lr: 0.000757  loss: 2.3104 (2.2019)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [219]  [260/312]  eta: 0:00:25  lr: 0.000757  min_lr: 0.000757  loss: 2.3489 (2.2118)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [219]  [270/312]  eta: 0:00:20  lr: 0.000756  min_lr: 0.000756  loss: 2.3856 (2.2125)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [219]  [280/312]  eta: 0:00:15  lr: 0.000756  min_lr: 0.000756  loss: 2.1962 (2.2128)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0009  max mem: 42573
Epoch: [219]  [290/312]  eta: 0:00:10  lr: 0.000755  min_lr: 0.000755  loss: 2.1016 (2.2087)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0008  max mem: 42573
Epoch: [219]  [300/312]  eta: 0:00:05  lr: 0.000755  min_lr: 0.000755  loss: 2.3401 (2.2162)  weight_decay: 0.0500 (0.0500)  time: 0.4321  data: 0.0001  max mem: 42573
Epoch: [219]  [310/312]  eta: 0:00:00  lr: 0.000754  min_lr: 0.000754  loss: 2.3427 (2.2179)  weight_decay: 0.0500 (0.0500)  time: 0.4321  data: 0.0001  max mem: 42573
Epoch: [219]  [311/312]  eta: 0:00:00  lr: 0.000754  min_lr: 0.000754  loss: 2.3421 (2.2175)  weight_decay: 0.0500 (0.0500)  time: 0.4321  data: 0.0001  max mem: 42573
Epoch: [219] Total time: 0:02:28 (0.4765 s / it)
Averaged stats: lr: 0.000754  min_lr: 0.000754  loss: 2.3421 (2.2185)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:00:39  loss: 0.7368 (0.7368)  acc1: 82.8125 (82.8125)  acc5: 93.7500 (93.7500)  time: 4.3345  data: 4.2265  max mem: 42573
Test:  [8/9]  eta: 0:00:00  loss: 0.8975 (0.8897)  acc1: 79.4271 (76.7680)  acc5: 93.4896 (93.3760)  time: 0.5592  data: 0.4697  max mem: 42573
Test: Total time: 0:00:05 (0.5677 s / it)
* Acc@1 77.574 Acc@5 93.636 loss 0.875
Accuracy of the model on the 50000 test images: 77.6%
Max accuracy: 77.57%
Epoch: [220]  [  0/312]  eta: 0:51:01  lr: 0.000754  min_lr: 0.000754  loss: 2.2583 (2.2583)  weight_decay: 0.0500 (0.0500)  time: 9.8134  data: 9.0413  max mem: 42573
Epoch: [220]  [ 10/312]  eta: 0:07:36  lr: 0.000753  min_lr: 0.000753  loss: 2.3179 (2.2836)  weight_decay: 0.0500 (0.0500)  time: 1.5121  data: 0.8223  max mem: 42573
Epoch: [220]  [ 20/312]  eta: 0:04:51  lr: 0.000753  min_lr: 0.000753  loss: 2.3179 (2.3078)  weight_decay: 0.0500 (0.0500)  time: 0.5580  data: 0.0004  max mem: 42573
Epoch: [220]  [ 30/312]  eta: 0:03:50  lr: 0.000752  min_lr: 0.000752  loss: 2.2394 (2.2594)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0003  max mem: 42573
Epoch: [220]  [ 40/312]  eta: 0:03:16  lr: 0.000752  min_lr: 0.000752  loss: 2.3006 (2.2318)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0003  max mem: 42573
Epoch: [220]  [ 50/312]  eta: 0:02:54  lr: 0.000751  min_lr: 0.000751  loss: 2.2741 (2.2289)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0003  max mem: 42573
Epoch: [220]  [ 60/312]  eta: 0:02:38  lr: 0.000750  min_lr: 0.000750  loss: 2.1930 (2.2138)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0003  max mem: 42573
Epoch: [220]  [ 70/312]  eta: 0:02:25  lr: 0.000750  min_lr: 0.000750  loss: 2.3321 (2.2310)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [220]  [ 80/312]  eta: 0:02:14  lr: 0.000749  min_lr: 0.000749  loss: 2.3204 (2.2116)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [220]  [ 90/312]  eta: 0:02:05  lr: 0.000749  min_lr: 0.000749  loss: 2.3204 (2.2191)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [220]  [100/312]  eta: 0:01:56  lr: 0.000748  min_lr: 0.000748  loss: 2.2745 (2.2020)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [220]  [110/312]  eta: 0:01:49  lr: 0.000748  min_lr: 0.000748  loss: 2.1650 (2.2037)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [220]  [120/312]  eta: 0:01:42  lr: 0.000747  min_lr: 0.000747  loss: 2.2342 (2.2072)  weight_decay: 0.0500 (0.0500)  time: 0.4369  data: 0.0004  max mem: 42573
Epoch: [220]  [130/312]  eta: 0:01:35  lr: 0.000747  min_lr: 0.000747  loss: 2.2342 (2.1984)  weight_decay: 0.0500 (0.0500)  time: 0.4368  data: 0.0004  max mem: 42573
Epoch: [220]  [140/312]  eta: 0:01:29  lr: 0.000746  min_lr: 0.000746  loss: 2.2821 (2.2091)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [220]  [150/312]  eta: 0:01:23  lr: 0.000745  min_lr: 0.000745  loss: 2.3254 (2.2165)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [220]  [160/312]  eta: 0:01:17  lr: 0.000745  min_lr: 0.000745  loss: 2.2961 (2.2140)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [220]  [170/312]  eta: 0:01:11  lr: 0.000744  min_lr: 0.000744  loss: 2.3203 (2.2227)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [220]  [180/312]  eta: 0:01:05  lr: 0.000744  min_lr: 0.000744  loss: 2.3203 (2.2201)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [220]  [190/312]  eta: 0:01:00  lr: 0.000743  min_lr: 0.000743  loss: 2.3093 (2.2254)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [220]  [200/312]  eta: 0:00:55  lr: 0.000743  min_lr: 0.000743  loss: 2.2673 (2.2177)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [220]  [210/312]  eta: 0:00:49  lr: 0.000742  min_lr: 0.000742  loss: 2.2673 (2.2248)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [220]  [220/312]  eta: 0:00:44  lr: 0.000742  min_lr: 0.000742  loss: 2.3948 (2.2262)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [220]  [230/312]  eta: 0:00:39  lr: 0.000741  min_lr: 0.000741  loss: 2.3427 (2.2347)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [220]  [240/312]  eta: 0:00:34  lr: 0.000740  min_lr: 0.000740  loss: 2.3733 (2.2309)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [220]  [250/312]  eta: 0:00:29  lr: 0.000740  min_lr: 0.000740  loss: 2.3917 (2.2375)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [220]  [260/312]  eta: 0:00:24  lr: 0.000739  min_lr: 0.000739  loss: 2.4370 (2.2382)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [220]  [270/312]  eta: 0:00:20  lr: 0.000739  min_lr: 0.000739  loss: 2.3875 (2.2413)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [220]  [280/312]  eta: 0:00:15  lr: 0.000738  min_lr: 0.000738  loss: 2.3087 (2.2411)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0009  max mem: 42573
Epoch: [220]  [290/312]  eta: 0:00:10  lr: 0.000738  min_lr: 0.000738  loss: 2.2546 (2.2398)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0008  max mem: 42573
Epoch: [220]  [300/312]  eta: 0:00:05  lr: 0.000737  min_lr: 0.000737  loss: 2.2415 (2.2446)  weight_decay: 0.0500 (0.0500)  time: 0.4322  data: 0.0001  max mem: 42573
Epoch: [220]  [310/312]  eta: 0:00:00  lr: 0.000736  min_lr: 0.000736  loss: 2.4193 (2.2475)  weight_decay: 0.0500 (0.0500)  time: 0.4322  data: 0.0001  max mem: 42573
Epoch: [220]  [311/312]  eta: 0:00:00  lr: 0.000736  min_lr: 0.000736  loss: 2.2975 (2.2474)  weight_decay: 0.0500 (0.0500)  time: 0.4322  data: 0.0001  max mem: 42573
Epoch: [220] Total time: 0:02:28 (0.4746 s / it)
Averaged stats: lr: 0.000736  min_lr: 0.000736  loss: 2.2975 (2.2243)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:00:40  loss: 0.7328 (0.7328)  acc1: 81.7708 (81.7708)  acc5: 94.5312 (94.5312)  time: 4.4847  data: 4.3778  max mem: 42573
Test:  [8/9]  eta: 0:00:00  loss: 0.8654 (0.8951)  acc1: 78.1250 (77.1200)  acc5: 94.5312 (93.7920)  time: 0.5734  data: 0.4865  max mem: 42573
Test: Total time: 0:00:05 (0.5816 s / it)
* Acc@1 77.774 Acc@5 93.678 loss 0.873
Accuracy of the model on the 50000 test images: 77.8%
Max accuracy: 77.77%
Epoch: [221]  [  0/312]  eta: 0:53:55  lr: 0.000736  min_lr: 0.000736  loss: 2.1990 (2.1990)  weight_decay: 0.0500 (0.0500)  time: 10.3707  data: 8.3163  max mem: 42573
Epoch: [221]  [ 10/312]  eta: 0:07:44  lr: 0.000736  min_lr: 0.000736  loss: 2.1851 (2.1255)  weight_decay: 0.0500 (0.0500)  time: 1.5376  data: 0.7931  max mem: 42573
Epoch: [221]  [ 20/312]  eta: 0:04:57  lr: 0.000735  min_lr: 0.000735  loss: 2.1273 (2.1271)  weight_decay: 0.0500 (0.0500)  time: 0.5513  data: 0.0206  max mem: 42573
Epoch: [221]  [ 30/312]  eta: 0:03:54  lr: 0.000735  min_lr: 0.000735  loss: 2.0320 (2.0936)  weight_decay: 0.0500 (0.0500)  time: 0.4424  data: 0.0004  max mem: 42573
Epoch: [221]  [ 40/312]  eta: 0:03:19  lr: 0.000734  min_lr: 0.000734  loss: 2.2613 (2.1378)  weight_decay: 0.0500 (0.0500)  time: 0.4347  data: 0.0004  max mem: 42573
Epoch: [221]  [ 50/312]  eta: 0:02:56  lr: 0.000734  min_lr: 0.000734  loss: 2.3439 (2.1678)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [221]  [ 60/312]  eta: 0:02:40  lr: 0.000733  min_lr: 0.000733  loss: 2.3537 (2.1649)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [221]  [ 70/312]  eta: 0:02:26  lr: 0.000732  min_lr: 0.000732  loss: 2.0814 (2.1621)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [221]  [ 80/312]  eta: 0:02:15  lr: 0.000732  min_lr: 0.000732  loss: 2.1578 (2.1570)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [221]  [ 90/312]  eta: 0:02:06  lr: 0.000731  min_lr: 0.000731  loss: 2.1692 (2.1569)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [221]  [100/312]  eta: 0:01:57  lr: 0.000731  min_lr: 0.000731  loss: 2.3383 (2.1769)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [221]  [110/312]  eta: 0:01:50  lr: 0.000730  min_lr: 0.000730  loss: 2.3737 (2.1819)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0003  max mem: 42573
Epoch: [221]  [120/312]  eta: 0:01:42  lr: 0.000730  min_lr: 0.000730  loss: 2.2440 (2.1685)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [221]  [130/312]  eta: 0:01:36  lr: 0.000729  min_lr: 0.000729  loss: 2.2440 (2.1747)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0003  max mem: 42573
Epoch: [221]  [140/312]  eta: 0:01:29  lr: 0.000729  min_lr: 0.000729  loss: 2.3555 (2.1812)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [221]  [150/312]  eta: 0:01:23  lr: 0.000728  min_lr: 0.000728  loss: 2.1967 (2.1873)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [221]  [160/312]  eta: 0:01:17  lr: 0.000727  min_lr: 0.000727  loss: 2.3682 (2.1978)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [221]  [170/312]  eta: 0:01:11  lr: 0.000727  min_lr: 0.000727  loss: 2.3880 (2.1992)  weight_decay: 0.0500 (0.0500)  time: 0.4332  data: 0.0004  max mem: 42573
Epoch: [221]  [180/312]  eta: 0:01:06  lr: 0.000726  min_lr: 0.000726  loss: 2.1340 (2.1914)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0003  max mem: 42573
Epoch: [221]  [190/312]  eta: 0:01:00  lr: 0.000726  min_lr: 0.000726  loss: 2.2700 (2.1989)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [221]  [200/312]  eta: 0:00:55  lr: 0.000725  min_lr: 0.000725  loss: 2.3742 (2.2015)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [221]  [210/312]  eta: 0:00:50  lr: 0.000725  min_lr: 0.000725  loss: 2.2011 (2.1999)  weight_decay: 0.0500 (0.0500)  time: 0.4332  data: 0.0004  max mem: 42573
Epoch: [221]  [220/312]  eta: 0:00:45  lr: 0.000724  min_lr: 0.000724  loss: 2.2291 (2.2081)  weight_decay: 0.0500 (0.0500)  time: 0.4332  data: 0.0004  max mem: 42573
Epoch: [221]  [230/312]  eta: 0:00:39  lr: 0.000724  min_lr: 0.000724  loss: 2.1840 (2.2015)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [221]  [240/312]  eta: 0:00:34  lr: 0.000723  min_lr: 0.000723  loss: 2.1636 (2.2012)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [221]  [250/312]  eta: 0:00:29  lr: 0.000722  min_lr: 0.000722  loss: 2.2554 (2.1974)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [221]  [260/312]  eta: 0:00:25  lr: 0.000722  min_lr: 0.000722  loss: 2.1655 (2.1988)  weight_decay: 0.0500 (0.0500)  time: 0.4379  data: 0.0004  max mem: 42573
Epoch: [221]  [270/312]  eta: 0:00:20  lr: 0.000721  min_lr: 0.000721  loss: 2.1655 (2.1932)  weight_decay: 0.0500 (0.0500)  time: 0.4377  data: 0.0004  max mem: 42573
Epoch: [221]  [280/312]  eta: 0:00:15  lr: 0.000721  min_lr: 0.000721  loss: 2.2093 (2.1922)  weight_decay: 0.0500 (0.0500)  time: 0.4348  data: 0.0010  max mem: 42573
Epoch: [221]  [290/312]  eta: 0:00:10  lr: 0.000720  min_lr: 0.000720  loss: 2.2128 (2.1980)  weight_decay: 0.0500 (0.0500)  time: 0.4342  data: 0.0008  max mem: 42573
Epoch: [221]  [300/312]  eta: 0:00:05  lr: 0.000720  min_lr: 0.000720  loss: 2.1940 (2.1951)  weight_decay: 0.0500 (0.0500)  time: 0.4323  data: 0.0001  max mem: 42573
Epoch: [221]  [310/312]  eta: 0:00:00  lr: 0.000719  min_lr: 0.000719  loss: 2.1292 (2.1958)  weight_decay: 0.0500 (0.0500)  time: 0.4322  data: 0.0001  max mem: 42573
Epoch: [221]  [311/312]  eta: 0:00:00  lr: 0.000719  min_lr: 0.000719  loss: 2.3668 (2.1968)  weight_decay: 0.0500 (0.0500)  time: 0.4322  data: 0.0001  max mem: 42573
Epoch: [221] Total time: 0:02:28 (0.4763 s / it)
Averaged stats: lr: 0.000719  min_lr: 0.000719  loss: 2.3668 (2.2151)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:00:42  loss: 0.6147 (0.6147)  acc1: 85.4167 (85.4167)  acc5: 95.8333 (95.8333)  time: 4.7133  data: 4.6055  max mem: 42573
Test:  [8/9]  eta: 0:00:00  loss: 0.8653 (0.8666)  acc1: 79.9479 (77.6320)  acc5: 94.0104 (93.8880)  time: 0.6008  data: 0.5118  max mem: 42573
Test: Total time: 0:00:05 (0.6175 s / it)
* Acc@1 77.744 Acc@5 93.654 loss 0.856
Accuracy of the model on the 50000 test images: 77.7%
Max accuracy: 77.77%
Epoch: [222]  [  0/312]  eta: 0:53:42  lr: 0.000719  min_lr: 0.000719  loss: 1.7303 (1.7303)  weight_decay: 0.0500 (0.0500)  time: 10.3272  data: 7.4860  max mem: 42573
Epoch: [222]  [ 10/312]  eta: 0:07:45  lr: 0.000719  min_lr: 0.000719  loss: 2.3895 (2.2494)  weight_decay: 0.0500 (0.0500)  time: 1.5428  data: 0.6890  max mem: 42573
Epoch: [222]  [ 20/312]  eta: 0:04:56  lr: 0.000718  min_lr: 0.000718  loss: 2.4013 (2.3239)  weight_decay: 0.0500 (0.0500)  time: 0.5488  data: 0.0048  max mem: 42573
Epoch: [222]  [ 30/312]  eta: 0:03:53  lr: 0.000717  min_lr: 0.000717  loss: 2.3201 (2.2573)  weight_decay: 0.0500 (0.0500)  time: 0.4341  data: 0.0004  max mem: 42573
Epoch: [222]  [ 40/312]  eta: 0:03:19  lr: 0.000717  min_lr: 0.000717  loss: 2.2293 (2.2261)  weight_decay: 0.0500 (0.0500)  time: 0.4352  data: 0.0004  max mem: 42573
Epoch: [222]  [ 50/312]  eta: 0:02:56  lr: 0.000716  min_lr: 0.000716  loss: 2.1598 (2.2354)  weight_decay: 0.0500 (0.0500)  time: 0.4345  data: 0.0004  max mem: 42573
Epoch: [222]  [ 60/312]  eta: 0:02:39  lr: 0.000716  min_lr: 0.000716  loss: 2.0899 (2.2286)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [222]  [ 70/312]  eta: 0:02:26  lr: 0.000715  min_lr: 0.000715  loss: 2.2041 (2.2336)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [222]  [ 80/312]  eta: 0:02:15  lr: 0.000715  min_lr: 0.000715  loss: 2.2891 (2.2418)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [222]  [ 90/312]  eta: 0:02:06  lr: 0.000714  min_lr: 0.000714  loss: 2.3673 (2.2411)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [222]  [100/312]  eta: 0:01:57  lr: 0.000714  min_lr: 0.000714  loss: 2.0941 (2.2196)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [222]  [110/312]  eta: 0:01:49  lr: 0.000713  min_lr: 0.000713  loss: 2.1417 (2.2193)  weight_decay: 0.0500 (0.0500)  time: 0.4332  data: 0.0004  max mem: 42573
Epoch: [222]  [120/312]  eta: 0:01:42  lr: 0.000712  min_lr: 0.000712  loss: 2.1482 (2.2102)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [222]  [130/312]  eta: 0:01:35  lr: 0.000712  min_lr: 0.000712  loss: 2.2298 (2.2102)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [222]  [140/312]  eta: 0:01:29  lr: 0.000711  min_lr: 0.000711  loss: 2.2908 (2.2161)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [222]  [150/312]  eta: 0:01:23  lr: 0.000711  min_lr: 0.000711  loss: 2.2163 (2.2175)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [222]  [160/312]  eta: 0:01:17  lr: 0.000710  min_lr: 0.000710  loss: 2.2163 (2.2159)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [222]  [170/312]  eta: 0:01:11  lr: 0.000710  min_lr: 0.000710  loss: 2.2673 (2.2127)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [222]  [180/312]  eta: 0:01:06  lr: 0.000709  min_lr: 0.000709  loss: 2.1899 (2.2074)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0003  max mem: 42573
Epoch: [222]  [190/312]  eta: 0:01:00  lr: 0.000709  min_lr: 0.000709  loss: 2.2615 (2.2135)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0003  max mem: 42573
Epoch: [222]  [200/312]  eta: 0:00:55  lr: 0.000708  min_lr: 0.000708  loss: 2.2282 (2.2045)  weight_decay: 0.0500 (0.0500)  time: 0.4332  data: 0.0003  max mem: 42573
Epoch: [222]  [210/312]  eta: 0:00:50  lr: 0.000708  min_lr: 0.000708  loss: 2.3744 (2.2178)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [222]  [220/312]  eta: 0:00:44  lr: 0.000707  min_lr: 0.000707  loss: 2.4421 (2.2213)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [222]  [230/312]  eta: 0:00:39  lr: 0.000706  min_lr: 0.000706  loss: 2.2732 (2.2182)  weight_decay: 0.0500 (0.0500)  time: 0.4420  data: 0.0003  max mem: 42573
Epoch: [222]  [240/312]  eta: 0:00:34  lr: 0.000706  min_lr: 0.000706  loss: 2.1282 (2.2157)  weight_decay: 0.0500 (0.0500)  time: 0.4420  data: 0.0003  max mem: 42573
Epoch: [222]  [250/312]  eta: 0:00:29  lr: 0.000705  min_lr: 0.000705  loss: 2.3147 (2.2275)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0003  max mem: 42573
Epoch: [222]  [260/312]  eta: 0:00:25  lr: 0.000705  min_lr: 0.000705  loss: 2.4897 (2.2376)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [222]  [270/312]  eta: 0:00:20  lr: 0.000704  min_lr: 0.000704  loss: 2.4122 (2.2396)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0003  max mem: 42573
Epoch: [222]  [280/312]  eta: 0:00:15  lr: 0.000704  min_lr: 0.000704  loss: 2.2329 (2.2291)  weight_decay: 0.0500 (0.0500)  time: 0.4360  data: 0.0009  max mem: 42573
Epoch: [222]  [290/312]  eta: 0:00:10  lr: 0.000703  min_lr: 0.000703  loss: 1.9170 (2.2285)  weight_decay: 0.0500 (0.0500)  time: 0.4353  data: 0.0007  max mem: 42573
Epoch: [222]  [300/312]  eta: 0:00:05  lr: 0.000703  min_lr: 0.000703  loss: 2.3195 (2.2271)  weight_decay: 0.0500 (0.0500)  time: 0.4322  data: 0.0001  max mem: 42573
Epoch: [222]  [310/312]  eta: 0:00:00  lr: 0.000702  min_lr: 0.000702  loss: 2.3731 (2.2303)  weight_decay: 0.0500 (0.0500)  time: 0.4321  data: 0.0001  max mem: 42573
Epoch: [222]  [311/312]  eta: 0:00:00  lr: 0.000702  min_lr: 0.000702  loss: 2.3844 (2.2312)  weight_decay: 0.0500 (0.0500)  time: 0.4321  data: 0.0001  max mem: 42573
Epoch: [222] Total time: 0:02:28 (0.4764 s / it)
Averaged stats: lr: 0.000702  min_lr: 0.000702  loss: 2.3844 (2.2222)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:00:39  loss: 0.6460 (0.6460)  acc1: 85.1562 (85.1562)  acc5: 94.7917 (94.7917)  time: 4.4358  data: 4.3274  max mem: 42573
Test:  [8/9]  eta: 0:00:00  loss: 0.8935 (0.8741)  acc1: 76.5625 (76.9920)  acc5: 94.2708 (93.5040)  time: 0.5681  data: 0.4809  max mem: 42573
Test: Total time: 0:00:05 (0.5747 s / it)
* Acc@1 77.754 Acc@5 93.812 loss 0.857
Accuracy of the model on the 50000 test images: 77.8%
Max accuracy: 77.77%
Epoch: [223]  [  0/312]  eta: 0:54:52  lr: 0.000702  min_lr: 0.000702  loss: 2.5274 (2.5274)  weight_decay: 0.0500 (0.0500)  time: 10.5522  data: 8.6208  max mem: 42573
Epoch: [223]  [ 10/312]  eta: 0:07:55  lr: 0.000701  min_lr: 0.000701  loss: 2.3370 (2.3154)  weight_decay: 0.0500 (0.0500)  time: 1.5739  data: 0.7840  max mem: 42573
Epoch: [223]  [ 20/312]  eta: 0:05:01  lr: 0.000701  min_lr: 0.000701  loss: 2.3103 (2.2715)  weight_decay: 0.0500 (0.0500)  time: 0.5555  data: 0.0004  max mem: 42573
Epoch: [223]  [ 30/312]  eta: 0:03:56  lr: 0.000700  min_lr: 0.000700  loss: 2.1804 (2.1813)  weight_decay: 0.0500 (0.0500)  time: 0.4350  data: 0.0004  max mem: 42573
Epoch: [223]  [ 40/312]  eta: 0:03:21  lr: 0.000700  min_lr: 0.000700  loss: 2.3506 (2.2331)  weight_decay: 0.0500 (0.0500)  time: 0.4342  data: 0.0003  max mem: 42573
Epoch: [223]  [ 50/312]  eta: 0:02:58  lr: 0.000699  min_lr: 0.000699  loss: 2.4082 (2.2300)  weight_decay: 0.0500 (0.0500)  time: 0.4341  data: 0.0004  max mem: 42573
Epoch: [223]  [ 60/312]  eta: 0:02:41  lr: 0.000699  min_lr: 0.000699  loss: 2.2471 (2.2417)  weight_decay: 0.0500 (0.0500)  time: 0.4341  data: 0.0004  max mem: 42573
Epoch: [223]  [ 70/312]  eta: 0:02:27  lr: 0.000698  min_lr: 0.000698  loss: 2.2471 (2.2426)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [223]  [ 80/312]  eta: 0:02:16  lr: 0.000698  min_lr: 0.000698  loss: 2.3661 (2.2505)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [223]  [ 90/312]  eta: 0:02:06  lr: 0.000697  min_lr: 0.000697  loss: 2.3139 (2.2517)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [223]  [100/312]  eta: 0:01:58  lr: 0.000696  min_lr: 0.000696  loss: 2.2880 (2.2369)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [223]  [110/312]  eta: 0:01:50  lr: 0.000696  min_lr: 0.000696  loss: 1.9485 (2.2200)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [223]  [120/312]  eta: 0:01:43  lr: 0.000695  min_lr: 0.000695  loss: 2.1340 (2.2114)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [223]  [130/312]  eta: 0:01:36  lr: 0.000695  min_lr: 0.000695  loss: 2.0929 (2.2058)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [223]  [140/312]  eta: 0:01:29  lr: 0.000694  min_lr: 0.000694  loss: 2.4150 (2.2247)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [223]  [150/312]  eta: 0:01:23  lr: 0.000694  min_lr: 0.000694  loss: 2.4165 (2.2296)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [223]  [160/312]  eta: 0:01:17  lr: 0.000693  min_lr: 0.000693  loss: 2.2749 (2.2295)  weight_decay: 0.0500 (0.0500)  time: 0.4384  data: 0.0004  max mem: 42573
Epoch: [223]  [170/312]  eta: 0:01:12  lr: 0.000693  min_lr: 0.000693  loss: 2.2205 (2.2268)  weight_decay: 0.0500 (0.0500)  time: 0.4382  data: 0.0004  max mem: 42573
Epoch: [223]  [180/312]  eta: 0:01:06  lr: 0.000692  min_lr: 0.000692  loss: 2.0000 (2.2209)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [223]  [190/312]  eta: 0:01:00  lr: 0.000692  min_lr: 0.000692  loss: 2.2306 (2.2226)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [223]  [200/312]  eta: 0:00:55  lr: 0.000691  min_lr: 0.000691  loss: 2.2306 (2.2189)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [223]  [210/312]  eta: 0:00:50  lr: 0.000690  min_lr: 0.000690  loss: 2.0198 (2.2099)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [223]  [220/312]  eta: 0:00:45  lr: 0.000690  min_lr: 0.000690  loss: 2.0110 (2.2066)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [223]  [230/312]  eta: 0:00:40  lr: 0.000689  min_lr: 0.000689  loss: 2.1007 (2.2058)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [223]  [240/312]  eta: 0:00:35  lr: 0.000689  min_lr: 0.000689  loss: 2.0837 (2.2082)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [223]  [250/312]  eta: 0:00:30  lr: 0.000688  min_lr: 0.000688  loss: 2.2966 (2.2150)  weight_decay: 0.0500 (0.0500)  time: 0.4332  data: 0.0004  max mem: 42573
Epoch: [223]  [260/312]  eta: 0:00:25  lr: 0.000688  min_lr: 0.000688  loss: 2.3429 (2.2174)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [223]  [270/312]  eta: 0:00:20  lr: 0.000687  min_lr: 0.000687  loss: 2.3429 (2.2224)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [223]  [280/312]  eta: 0:00:15  lr: 0.000687  min_lr: 0.000687  loss: 2.2624 (2.2150)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0009  max mem: 42573
Epoch: [223]  [290/312]  eta: 0:00:10  lr: 0.000686  min_lr: 0.000686  loss: 1.9805 (2.2092)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0008  max mem: 42573
Epoch: [223]  [300/312]  eta: 0:00:05  lr: 0.000686  min_lr: 0.000686  loss: 2.0972 (2.2076)  weight_decay: 0.0500 (0.0500)  time: 0.4322  data: 0.0001  max mem: 42573
Epoch: [223]  [310/312]  eta: 0:00:00  lr: 0.000685  min_lr: 0.000685  loss: 2.1650 (2.2115)  weight_decay: 0.0500 (0.0500)  time: 0.4320  data: 0.0001  max mem: 42573
Epoch: [223]  [311/312]  eta: 0:00:00  lr: 0.000685  min_lr: 0.000685  loss: 2.1650 (2.2117)  weight_decay: 0.0500 (0.0500)  time: 0.4320  data: 0.0001  max mem: 42573
Epoch: [223] Total time: 0:02:28 (0.4773 s / it)
Averaged stats: lr: 0.000685  min_lr: 0.000685  loss: 2.1650 (2.2087)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:00:39  loss: 0.6988 (0.6988)  acc1: 83.8542 (83.8542)  acc5: 94.7917 (94.7917)  time: 4.3880  data: 4.2742  max mem: 42573
Test:  [8/9]  eta: 0:00:00  loss: 0.9133 (0.8678)  acc1: 77.6042 (78.1760)  acc5: 94.7917 (93.7280)  time: 0.5630  data: 0.4750  max mem: 42573
Test: Total time: 0:00:05 (0.5714 s / it)
* Acc@1 78.196 Acc@5 94.002 loss 0.847
Accuracy of the model on the 50000 test images: 78.2%
Max accuracy: 78.20%
Epoch: [224]  [  0/312]  eta: 0:53:04  lr: 0.000685  min_lr: 0.000685  loss: 2.1763 (2.1763)  weight_decay: 0.0500 (0.0500)  time: 10.2056  data: 6.5945  max mem: 42573
Epoch: [224]  [ 10/312]  eta: 0:07:58  lr: 0.000684  min_lr: 0.000684  loss: 2.3976 (2.4065)  weight_decay: 0.0500 (0.0500)  time: 1.5847  data: 0.6120  max mem: 42573
Epoch: [224]  [ 20/312]  eta: 0:05:02  lr: 0.000684  min_lr: 0.000684  loss: 2.3391 (2.3193)  weight_decay: 0.0500 (0.0500)  time: 0.5779  data: 0.0071  max mem: 42573
Epoch: [224]  [ 30/312]  eta: 0:03:57  lr: 0.000683  min_lr: 0.000683  loss: 2.2824 (2.3540)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0003  max mem: 42573
Epoch: [224]  [ 40/312]  eta: 0:03:21  lr: 0.000683  min_lr: 0.000683  loss: 2.3501 (2.3093)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0003  max mem: 42573
Epoch: [224]  [ 50/312]  eta: 0:02:58  lr: 0.000682  min_lr: 0.000682  loss: 2.2379 (2.3097)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [224]  [ 60/312]  eta: 0:02:41  lr: 0.000682  min_lr: 0.000682  loss: 2.3298 (2.3172)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [224]  [ 70/312]  eta: 0:02:28  lr: 0.000681  min_lr: 0.000681  loss: 2.4242 (2.3486)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [224]  [ 80/312]  eta: 0:02:16  lr: 0.000681  min_lr: 0.000681  loss: 2.3678 (2.3204)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [224]  [ 90/312]  eta: 0:02:07  lr: 0.000680  min_lr: 0.000680  loss: 2.3487 (2.3092)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [224]  [100/312]  eta: 0:01:58  lr: 0.000680  min_lr: 0.000680  loss: 2.2432 (2.2979)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [224]  [110/312]  eta: 0:01:50  lr: 0.000679  min_lr: 0.000679  loss: 2.2432 (2.2885)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [224]  [120/312]  eta: 0:01:43  lr: 0.000678  min_lr: 0.000678  loss: 2.3916 (2.2846)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [224]  [130/312]  eta: 0:01:36  lr: 0.000678  min_lr: 0.000678  loss: 2.3424 (2.2805)  weight_decay: 0.0500 (0.0500)  time: 0.4396  data: 0.0004  max mem: 42573
Epoch: [224]  [140/312]  eta: 0:01:30  lr: 0.000677  min_lr: 0.000677  loss: 2.3424 (2.2824)  weight_decay: 0.0500 (0.0500)  time: 0.4398  data: 0.0004  max mem: 42573
Epoch: [224]  [150/312]  eta: 0:01:23  lr: 0.000677  min_lr: 0.000677  loss: 2.2117 (2.2755)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [224]  [160/312]  eta: 0:01:17  lr: 0.000676  min_lr: 0.000676  loss: 2.1048 (2.2686)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [224]  [170/312]  eta: 0:01:12  lr: 0.000676  min_lr: 0.000676  loss: 2.2139 (2.2669)  weight_decay: 0.0500 (0.0500)  time: 0.4332  data: 0.0004  max mem: 42573
Epoch: [224]  [180/312]  eta: 0:01:06  lr: 0.000675  min_lr: 0.000675  loss: 2.4362 (2.2794)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [224]  [190/312]  eta: 0:01:01  lr: 0.000675  min_lr: 0.000675  loss: 2.3583 (2.2689)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [224]  [200/312]  eta: 0:00:55  lr: 0.000674  min_lr: 0.000674  loss: 2.0865 (2.2632)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [224]  [210/312]  eta: 0:00:50  lr: 0.000674  min_lr: 0.000674  loss: 2.1923 (2.2531)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [224]  [220/312]  eta: 0:00:45  lr: 0.000673  min_lr: 0.000673  loss: 2.0903 (2.2470)  weight_decay: 0.0500 (0.0500)  time: 0.4332  data: 0.0004  max mem: 42573
Epoch: [224]  [230/312]  eta: 0:00:40  lr: 0.000673  min_lr: 0.000673  loss: 2.0538 (2.2394)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [224]  [240/312]  eta: 0:00:35  lr: 0.000672  min_lr: 0.000672  loss: 2.0638 (2.2309)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [224]  [250/312]  eta: 0:00:30  lr: 0.000671  min_lr: 0.000671  loss: 2.1941 (2.2335)  weight_decay: 0.0500 (0.0500)  time: 0.4331  data: 0.0004  max mem: 42573
Epoch: [224]  [260/312]  eta: 0:00:25  lr: 0.000671  min_lr: 0.000671  loss: 2.2876 (2.2275)  weight_decay: 0.0500 (0.0500)  time: 0.4332  data: 0.0004  max mem: 42573
Epoch: [224]  [270/312]  eta: 0:00:20  lr: 0.000670  min_lr: 0.000670  loss: 2.3069 (2.2301)  weight_decay: 0.0500 (0.0500)  time: 0.4332  data: 0.0003  max mem: 42573
Epoch: [224]  [280/312]  eta: 0:00:15  lr: 0.000670  min_lr: 0.000670  loss: 2.3069 (2.2271)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0009  max mem: 42573
Epoch: [224]  [290/312]  eta: 0:00:10  lr: 0.000669  min_lr: 0.000669  loss: 2.2160 (2.2257)  weight_decay: 0.0500 (0.0500)  time: 0.4345  data: 0.0008  max mem: 42573
Epoch: [224]  [300/312]  eta: 0:00:05  lr: 0.000669  min_lr: 0.000669  loss: 2.2930 (2.2302)  weight_decay: 0.0500 (0.0500)  time: 0.4332  data: 0.0001  max mem: 42573
Epoch: [224]  [310/312]  eta: 0:00:00  lr: 0.000668  min_lr: 0.000668  loss: 2.2930 (2.2304)  weight_decay: 0.0500 (0.0500)  time: 0.4320  data: 0.0001  max mem: 42573
Epoch: [224]  [311/312]  eta: 0:00:00  lr: 0.000668  min_lr: 0.000668  loss: 2.3533 (2.2310)  weight_decay: 0.0500 (0.0500)  time: 0.4320  data: 0.0001  max mem: 42573
Epoch: [224] Total time: 0:02:28 (0.4775 s / it)
Averaged stats: lr: 0.000668  min_lr: 0.000668  loss: 2.3533 (2.2089)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:00:40  loss: 0.7059 (0.7059)  acc1: 82.8125 (82.8125)  acc5: 95.3125 (95.3125)  time: 4.5094  data: 4.3986  max mem: 42573
Test:  [8/9]  eta: 0:00:00  loss: 0.8963 (0.8802)  acc1: 77.0833 (76.4480)  acc5: 93.4896 (93.7600)  time: 0.5765  data: 0.4888  max mem: 42573
Test: Total time: 0:00:05 (0.5835 s / it)
* Acc@1 78.062 Acc@5 93.890 loss 0.856
Accuracy of the model on the 50000 test images: 78.1%
Max accuracy: 78.20%
Epoch: [225]  [  0/312]  eta: 0:52:58  lr: 0.000668  min_lr: 0.000668  loss: 1.8992 (1.8992)  weight_decay: 0.0500 (0.0500)  time: 10.1860  data: 6.4837  max mem: 42573
Epoch: [225]  [ 10/312]  eta: 0:07:56  lr: 0.000668  min_lr: 0.000668  loss: 2.0278 (2.1296)  weight_decay: 0.0500 (0.0500)  time: 1.5767  data: 0.6508  max mem: 42573
Epoch: [225]  [ 20/312]  eta: 0:05:01  lr: 0.000667  min_lr: 0.000667  loss: 2.1449 (2.2489)  weight_decay: 0.0500 (0.0500)  time: 0.5747  data: 0.0339  max mem: 42573
Epoch: [225]  [ 30/312]  eta: 0:03:57  lr: 0.000667  min_lr: 0.000667  loss: 2.3093 (2.1784)  weight_decay: 0.0500 (0.0500)  time: 0.4357  data: 0.0003  max mem: 42573
Epoch: [225]  [ 40/312]  eta: 0:03:21  lr: 0.000666  min_lr: 0.000666  loss: 2.1653 (2.2059)  weight_decay: 0.0500 (0.0500)  time: 0.4362  data: 0.0003  max mem: 42573
Epoch: [225]  [ 50/312]  eta: 0:02:58  lr: 0.000665  min_lr: 0.000665  loss: 2.3597 (2.2055)  weight_decay: 0.0500 (0.0500)  time: 0.4351  data: 0.0004  max mem: 42573
Epoch: [225]  [ 60/312]  eta: 0:02:41  lr: 0.000665  min_lr: 0.000665  loss: 2.1717 (2.1909)  weight_decay: 0.0500 (0.0500)  time: 0.4345  data: 0.0004  max mem: 42573
Epoch: [225]  [ 70/312]  eta: 0:02:28  lr: 0.000664  min_lr: 0.000664  loss: 2.2949 (2.2173)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [225]  [ 80/312]  eta: 0:02:16  lr: 0.000664  min_lr: 0.000664  loss: 2.2982 (2.1998)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [225]  [ 90/312]  eta: 0:02:07  lr: 0.000663  min_lr: 0.000663  loss: 2.3569 (2.2069)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [225]  [100/312]  eta: 0:01:58  lr: 0.000663  min_lr: 0.000663  loss: 2.2721 (2.2054)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [225]  [110/312]  eta: 0:01:50  lr: 0.000662  min_lr: 0.000662  loss: 2.1667 (2.1977)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0003  max mem: 42573
Epoch: [225]  [120/312]  eta: 0:01:43  lr: 0.000662  min_lr: 0.000662  loss: 2.1142 (2.1842)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0003  max mem: 42573
Epoch: [225]  [130/312]  eta: 0:01:36  lr: 0.000661  min_lr: 0.000661  loss: 2.1142 (2.1801)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [225]  [140/312]  eta: 0:01:29  lr: 0.000661  min_lr: 0.000661  loss: 2.0880 (2.1700)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [225]  [150/312]  eta: 0:01:23  lr: 0.000660  min_lr: 0.000660  loss: 2.3589 (2.1798)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [225]  [160/312]  eta: 0:01:17  lr: 0.000660  min_lr: 0.000660  loss: 2.3908 (2.1864)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [225]  [170/312]  eta: 0:01:12  lr: 0.000659  min_lr: 0.000659  loss: 2.4041 (2.2051)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [225]  [180/312]  eta: 0:01:06  lr: 0.000659  min_lr: 0.000659  loss: 2.4041 (2.2072)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [225]  [190/312]  eta: 0:01:00  lr: 0.000658  min_lr: 0.000658  loss: 2.1481 (2.1991)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [225]  [200/312]  eta: 0:00:55  lr: 0.000657  min_lr: 0.000657  loss: 1.9586 (2.1878)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [225]  [210/312]  eta: 0:00:50  lr: 0.000657  min_lr: 0.000657  loss: 2.1441 (2.1862)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [225]  [220/312]  eta: 0:00:45  lr: 0.000656  min_lr: 0.000656  loss: 2.1441 (2.1792)  weight_decay: 0.0500 (0.0500)  time: 0.4332  data: 0.0004  max mem: 42573
Epoch: [225]  [230/312]  eta: 0:00:40  lr: 0.000656  min_lr: 0.000656  loss: 2.2056 (2.1845)  weight_decay: 0.0500 (0.0500)  time: 0.4426  data: 0.0004  max mem: 42573
Epoch: [225]  [240/312]  eta: 0:00:35  lr: 0.000655  min_lr: 0.000655  loss: 2.4475 (2.1938)  weight_decay: 0.0500 (0.0500)  time: 0.4427  data: 0.0004  max mem: 42573
Epoch: [225]  [250/312]  eta: 0:00:30  lr: 0.000655  min_lr: 0.000655  loss: 2.4069 (2.1952)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [225]  [260/312]  eta: 0:00:25  lr: 0.000654  min_lr: 0.000654  loss: 2.2986 (2.1944)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [225]  [270/312]  eta: 0:00:20  lr: 0.000654  min_lr: 0.000654  loss: 2.2726 (2.1947)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [225]  [280/312]  eta: 0:00:15  lr: 0.000653  min_lr: 0.000653  loss: 2.1253 (2.1922)  weight_decay: 0.0500 (0.0500)  time: 0.4342  data: 0.0011  max mem: 42573
Epoch: [225]  [290/312]  eta: 0:00:10  lr: 0.000653  min_lr: 0.000653  loss: 2.2839 (2.1946)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0009  max mem: 42573
Epoch: [225]  [300/312]  eta: 0:00:05  lr: 0.000652  min_lr: 0.000652  loss: 2.0212 (2.1875)  weight_decay: 0.0500 (0.0500)  time: 0.4321  data: 0.0001  max mem: 42573
Epoch: [225]  [310/312]  eta: 0:00:00  lr: 0.000652  min_lr: 0.000652  loss: 1.9800 (2.1870)  weight_decay: 0.0500 (0.0500)  time: 0.4321  data: 0.0001  max mem: 42573
Epoch: [225]  [311/312]  eta: 0:00:00  lr: 0.000652  min_lr: 0.000652  loss: 1.9800 (2.1868)  weight_decay: 0.0500 (0.0500)  time: 0.4321  data: 0.0001  max mem: 42573
Epoch: [225] Total time: 0:02:29 (0.4777 s / it)
Averaged stats: lr: 0.000652  min_lr: 0.000652  loss: 1.9800 (2.1962)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:00:39  loss: 0.6947 (0.6947)  acc1: 81.5104 (81.5104)  acc5: 94.5312 (94.5312)  time: 4.3602  data: 4.2524  max mem: 42573
Test:  [8/9]  eta: 0:00:00  loss: 0.8657 (0.8647)  acc1: 78.3854 (77.0560)  acc5: 93.2292 (93.4400)  time: 0.5602  data: 0.4726  max mem: 42573
Test: Total time: 0:00:05 (0.5700 s / it)
* Acc@1 78.020 Acc@5 93.894 loss 0.861
Accuracy of the model on the 50000 test images: 78.0%
Max accuracy: 78.20%
Epoch: [226]  [  0/312]  eta: 0:51:47  lr: 0.000651  min_lr: 0.000651  loss: 2.0625 (2.0625)  weight_decay: 0.0500 (0.0500)  time: 9.9605  data: 8.6314  max mem: 42573
Epoch: [226]  [ 10/312]  eta: 0:07:38  lr: 0.000651  min_lr: 0.000651  loss: 2.2636 (2.2877)  weight_decay: 0.0500 (0.0500)  time: 1.5190  data: 0.7890  max mem: 42573
Epoch: [226]  [ 20/312]  eta: 0:04:52  lr: 0.000650  min_lr: 0.000650  loss: 2.2221 (2.1845)  weight_decay: 0.0500 (0.0500)  time: 0.5538  data: 0.0026  max mem: 42573
Epoch: [226]  [ 30/312]  eta: 0:03:51  lr: 0.000650  min_lr: 0.000650  loss: 2.2039 (2.1874)  weight_decay: 0.0500 (0.0500)  time: 0.4358  data: 0.0004  max mem: 42573
Epoch: [226]  [ 40/312]  eta: 0:03:17  lr: 0.000649  min_lr: 0.000649  loss: 2.2039 (2.1500)  weight_decay: 0.0500 (0.0500)  time: 0.4361  data: 0.0003  max mem: 42573
Epoch: [226]  [ 50/312]  eta: 0:02:55  lr: 0.000649  min_lr: 0.000649  loss: 2.1228 (2.1585)  weight_decay: 0.0500 (0.0500)  time: 0.4360  data: 0.0004  max mem: 42573
Epoch: [226]  [ 60/312]  eta: 0:02:38  lr: 0.000648  min_lr: 0.000648  loss: 2.1292 (2.1557)  weight_decay: 0.0500 (0.0500)  time: 0.4360  data: 0.0004  max mem: 42573
Epoch: [226]  [ 70/312]  eta: 0:02:25  lr: 0.000648  min_lr: 0.000648  loss: 2.0871 (2.1695)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [226]  [ 80/312]  eta: 0:02:15  lr: 0.000647  min_lr: 0.000647  loss: 2.0693 (2.1497)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [226]  [ 90/312]  eta: 0:02:05  lr: 0.000647  min_lr: 0.000647  loss: 2.0693 (2.1412)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [226]  [100/312]  eta: 0:01:57  lr: 0.000646  min_lr: 0.000646  loss: 2.2112 (2.1496)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [226]  [110/312]  eta: 0:01:49  lr: 0.000646  min_lr: 0.000646  loss: 2.1928 (2.1464)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [226]  [120/312]  eta: 0:01:42  lr: 0.000645  min_lr: 0.000645  loss: 2.1907 (2.1520)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [226]  [130/312]  eta: 0:01:35  lr: 0.000645  min_lr: 0.000645  loss: 2.1835 (2.1482)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [226]  [140/312]  eta: 0:01:29  lr: 0.000644  min_lr: 0.000644  loss: 1.9423 (2.1293)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0003  max mem: 42573
Epoch: [226]  [150/312]  eta: 0:01:23  lr: 0.000644  min_lr: 0.000644  loss: 1.9420 (2.1352)  weight_decay: 0.0500 (0.0500)  time: 0.4368  data: 0.0004  max mem: 42573
Epoch: [226]  [160/312]  eta: 0:01:17  lr: 0.000643  min_lr: 0.000643  loss: 2.2340 (2.1376)  weight_decay: 0.0500 (0.0500)  time: 0.4368  data: 0.0004  max mem: 42573
Epoch: [226]  [170/312]  eta: 0:01:11  lr: 0.000642  min_lr: 0.000642  loss: 2.2358 (2.1441)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [226]  [180/312]  eta: 0:01:06  lr: 0.000642  min_lr: 0.000642  loss: 2.2358 (2.1389)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [226]  [190/312]  eta: 0:01:00  lr: 0.000641  min_lr: 0.000641  loss: 2.2892 (2.1383)  weight_decay: 0.0500 (0.0500)  time: 0.4332  data: 0.0004  max mem: 42573
Epoch: [226]  [200/312]  eta: 0:00:55  lr: 0.000641  min_lr: 0.000641  loss: 2.3432 (2.1498)  weight_decay: 0.0500 (0.0500)  time: 0.4331  data: 0.0004  max mem: 42573
Epoch: [226]  [210/312]  eta: 0:00:50  lr: 0.000640  min_lr: 0.000640  loss: 2.2861 (2.1470)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [226]  [220/312]  eta: 0:00:44  lr: 0.000640  min_lr: 0.000640  loss: 2.0478 (2.1381)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [226]  [230/312]  eta: 0:00:39  lr: 0.000639  min_lr: 0.000639  loss: 2.0502 (2.1428)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0005  max mem: 42573
Epoch: [226]  [240/312]  eta: 0:00:34  lr: 0.000639  min_lr: 0.000639  loss: 2.2605 (2.1444)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0005  max mem: 42573
Epoch: [226]  [250/312]  eta: 0:00:29  lr: 0.000638  min_lr: 0.000638  loss: 1.9701 (2.1411)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0005  max mem: 42573
Epoch: [226]  [260/312]  eta: 0:00:24  lr: 0.000638  min_lr: 0.000638  loss: 2.0794 (2.1419)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [226]  [270/312]  eta: 0:00:20  lr: 0.000637  min_lr: 0.000637  loss: 2.2089 (2.1443)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [226]  [280/312]  eta: 0:00:15  lr: 0.000637  min_lr: 0.000637  loss: 2.2089 (2.1435)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0009  max mem: 42573
Epoch: [226]  [290/312]  eta: 0:00:10  lr: 0.000636  min_lr: 0.000636  loss: 2.3317 (2.1579)  weight_decay: 0.0500 (0.0500)  time: 0.4331  data: 0.0008  max mem: 42573
Epoch: [226]  [300/312]  eta: 0:00:05  lr: 0.000636  min_lr: 0.000636  loss: 2.5553 (2.1655)  weight_decay: 0.0500 (0.0500)  time: 0.4321  data: 0.0001  max mem: 42573
Epoch: [226]  [310/312]  eta: 0:00:00  lr: 0.000635  min_lr: 0.000635  loss: 2.3490 (2.1707)  weight_decay: 0.0500 (0.0500)  time: 0.4320  data: 0.0001  max mem: 42573
Epoch: [226]  [311/312]  eta: 0:00:00  lr: 0.000635  min_lr: 0.000635  loss: 2.3490 (2.1724)  weight_decay: 0.0500 (0.0500)  time: 0.4320  data: 0.0001  max mem: 42573
Epoch: [226] Total time: 0:02:28 (0.4751 s / it)
Averaged stats: lr: 0.000635  min_lr: 0.000635  loss: 2.3490 (2.1928)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:00:42  loss: 0.6600 (0.6600)  acc1: 83.8542 (83.8542)  acc5: 95.3125 (95.3125)  time: 4.6936  data: 4.5858  max mem: 42573
Test:  [8/9]  eta: 0:00:00  loss: 0.8683 (0.8555)  acc1: 79.6875 (77.4720)  acc5: 93.7500 (93.9200)  time: 0.5972  data: 0.5096  max mem: 42573
Test: Total time: 0:00:05 (0.6089 s / it)
* Acc@1 78.254 Acc@5 94.042 loss 0.844
Accuracy of the model on the 50000 test images: 78.3%
Max accuracy: 78.25%
Epoch: [227]  [  0/312]  eta: 0:52:01  lr: 0.000635  min_lr: 0.000635  loss: 2.1404 (2.1404)  weight_decay: 0.0500 (0.0500)  time: 10.0046  data: 8.8478  max mem: 42573
Epoch: [227]  [ 10/312]  eta: 0:07:35  lr: 0.000634  min_lr: 0.000634  loss: 1.9511 (1.9043)  weight_decay: 0.0500 (0.0500)  time: 1.5067  data: 0.8047  max mem: 42573
Epoch: [227]  [ 20/312]  eta: 0:04:50  lr: 0.000634  min_lr: 0.000634  loss: 2.1549 (2.1022)  weight_decay: 0.0500 (0.0500)  time: 0.5452  data: 0.0004  max mem: 42573
Epoch: [227]  [ 30/312]  eta: 0:03:50  lr: 0.000633  min_lr: 0.000633  loss: 2.1723 (2.0816)  weight_decay: 0.0500 (0.0500)  time: 0.4394  data: 0.0004  max mem: 42573
Epoch: [227]  [ 40/312]  eta: 0:03:17  lr: 0.000633  min_lr: 0.000633  loss: 2.1462 (2.1263)  weight_decay: 0.0500 (0.0500)  time: 0.4402  data: 0.0004  max mem: 42573
Epoch: [227]  [ 50/312]  eta: 0:02:54  lr: 0.000632  min_lr: 0.000632  loss: 2.1864 (2.1393)  weight_decay: 0.0500 (0.0500)  time: 0.4341  data: 0.0004  max mem: 42573
Epoch: [227]  [ 60/312]  eta: 0:02:38  lr: 0.000632  min_lr: 0.000632  loss: 2.2104 (2.1527)  weight_decay: 0.0500 (0.0500)  time: 0.4343  data: 0.0004  max mem: 42573
Epoch: [227]  [ 70/312]  eta: 0:02:25  lr: 0.000631  min_lr: 0.000631  loss: 2.2305 (2.1607)  weight_decay: 0.0500 (0.0500)  time: 0.4346  data: 0.0004  max mem: 42573
Epoch: [227]  [ 80/312]  eta: 0:02:14  lr: 0.000631  min_lr: 0.000631  loss: 2.2309 (2.1687)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [227]  [ 90/312]  eta: 0:02:05  lr: 0.000630  min_lr: 0.000630  loss: 2.3692 (2.1992)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [227]  [100/312]  eta: 0:01:57  lr: 0.000630  min_lr: 0.000630  loss: 2.4097 (2.2032)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [227]  [110/312]  eta: 0:01:49  lr: 0.000629  min_lr: 0.000629  loss: 1.9817 (2.1782)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [227]  [120/312]  eta: 0:01:42  lr: 0.000629  min_lr: 0.000629  loss: 2.0819 (2.1763)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [227]  [130/312]  eta: 0:01:35  lr: 0.000628  min_lr: 0.000628  loss: 2.1624 (2.1789)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [227]  [140/312]  eta: 0:01:29  lr: 0.000628  min_lr: 0.000628  loss: 2.1551 (2.1862)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [227]  [150/312]  eta: 0:01:23  lr: 0.000627  min_lr: 0.000627  loss: 2.0851 (2.1832)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [227]  [160/312]  eta: 0:01:17  lr: 0.000627  min_lr: 0.000627  loss: 2.0686 (2.1761)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [227]  [170/312]  eta: 0:01:11  lr: 0.000626  min_lr: 0.000626  loss: 2.2789 (2.1930)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [227]  [180/312]  eta: 0:01:05  lr: 0.000626  min_lr: 0.000626  loss: 2.3639 (2.1920)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0003  max mem: 42573
Epoch: [227]  [190/312]  eta: 0:01:00  lr: 0.000625  min_lr: 0.000625  loss: 2.1048 (2.1878)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [227]  [200/312]  eta: 0:00:55  lr: 0.000625  min_lr: 0.000625  loss: 2.1272 (2.1899)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [227]  [210/312]  eta: 0:00:49  lr: 0.000624  min_lr: 0.000624  loss: 2.2390 (2.1923)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [227]  [220/312]  eta: 0:00:44  lr: 0.000624  min_lr: 0.000624  loss: 2.2007 (2.1893)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [227]  [230/312]  eta: 0:00:39  lr: 0.000623  min_lr: 0.000623  loss: 2.1144 (2.1841)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [227]  [240/312]  eta: 0:00:34  lr: 0.000622  min_lr: 0.000622  loss: 2.2013 (2.1851)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [227]  [250/312]  eta: 0:00:29  lr: 0.000622  min_lr: 0.000622  loss: 2.2347 (2.1863)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [227]  [260/312]  eta: 0:00:24  lr: 0.000621  min_lr: 0.000621  loss: 2.1392 (2.1819)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [227]  [270/312]  eta: 0:00:20  lr: 0.000621  min_lr: 0.000621  loss: 2.1392 (2.1779)  weight_decay: 0.0500 (0.0500)  time: 0.4372  data: 0.0004  max mem: 42573
Epoch: [227]  [280/312]  eta: 0:00:15  lr: 0.000620  min_lr: 0.000620  loss: 2.1422 (2.1765)  weight_decay: 0.0500 (0.0500)  time: 0.4376  data: 0.0009  max mem: 42573
Epoch: [227]  [290/312]  eta: 0:00:10  lr: 0.000620  min_lr: 0.000620  loss: 2.3692 (2.1831)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0008  max mem: 42573
Epoch: [227]  [300/312]  eta: 0:00:05  lr: 0.000619  min_lr: 0.000619  loss: 2.2730 (2.1838)  weight_decay: 0.0500 (0.0500)  time: 0.4321  data: 0.0001  max mem: 42573
Epoch: [227]  [310/312]  eta: 0:00:00  lr: 0.000619  min_lr: 0.000619  loss: 2.0339 (2.1812)  weight_decay: 0.0500 (0.0500)  time: 0.4320  data: 0.0001  max mem: 42573
Epoch: [227]  [311/312]  eta: 0:00:00  lr: 0.000619  min_lr: 0.000619  loss: 2.0094 (2.1786)  weight_decay: 0.0500 (0.0500)  time: 0.4320  data: 0.0001  max mem: 42573
Epoch: [227] Total time: 0:02:28 (0.4750 s / it)
Averaged stats: lr: 0.000619  min_lr: 0.000619  loss: 2.0094 (2.1914)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:00:39  loss: 0.6503 (0.6503)  acc1: 84.1146 (84.1146)  acc5: 95.0521 (95.0521)  time: 4.3569  data: 4.2490  max mem: 42573
Test:  [8/9]  eta: 0:00:00  loss: 0.8300 (0.8441)  acc1: 77.8646 (77.6320)  acc5: 94.0104 (94.0480)  time: 0.5612  data: 0.4722  max mem: 42573
Test: Total time: 0:00:05 (0.5695 s / it)
* Acc@1 78.554 Acc@5 94.224 loss 0.822
Accuracy of the model on the 50000 test images: 78.6%
Max accuracy: 78.55%
Epoch: [228]  [  0/312]  eta: 0:52:39  lr: 0.000619  min_lr: 0.000619  loss: 2.4674 (2.4674)  weight_decay: 0.0500 (0.0500)  time: 10.1280  data: 7.5499  max mem: 42573
Epoch: [228]  [ 10/312]  eta: 0:07:49  lr: 0.000618  min_lr: 0.000618  loss: 2.2702 (2.1777)  weight_decay: 0.0500 (0.0500)  time: 1.5557  data: 0.6867  max mem: 42573
Epoch: [228]  [ 20/312]  eta: 0:04:58  lr: 0.000618  min_lr: 0.000618  loss: 2.1597 (2.1180)  weight_decay: 0.0500 (0.0500)  time: 0.5658  data: 0.0003  max mem: 42573
Epoch: [228]  [ 30/312]  eta: 0:03:54  lr: 0.000617  min_lr: 0.000617  loss: 2.2271 (2.1540)  weight_decay: 0.0500 (0.0500)  time: 0.4332  data: 0.0003  max mem: 42573
Epoch: [228]  [ 40/312]  eta: 0:03:19  lr: 0.000617  min_lr: 0.000617  loss: 2.2527 (2.1563)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [228]  [ 50/312]  eta: 0:02:56  lr: 0.000616  min_lr: 0.000616  loss: 2.1399 (2.1377)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [228]  [ 60/312]  eta: 0:02:40  lr: 0.000616  min_lr: 0.000616  loss: 2.2006 (2.1669)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [228]  [ 70/312]  eta: 0:02:26  lr: 0.000615  min_lr: 0.000615  loss: 2.2198 (2.1401)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [228]  [ 80/312]  eta: 0:02:15  lr: 0.000615  min_lr: 0.000615  loss: 1.8859 (2.1108)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [228]  [ 90/312]  eta: 0:02:06  lr: 0.000614  min_lr: 0.000614  loss: 2.1623 (2.1259)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0003  max mem: 42573
Epoch: [228]  [100/312]  eta: 0:01:57  lr: 0.000614  min_lr: 0.000614  loss: 2.2930 (2.1381)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [228]  [110/312]  eta: 0:01:50  lr: 0.000613  min_lr: 0.000613  loss: 2.2691 (2.1383)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [228]  [120/312]  eta: 0:01:42  lr: 0.000612  min_lr: 0.000612  loss: 2.2691 (2.1428)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [228]  [130/312]  eta: 0:01:36  lr: 0.000612  min_lr: 0.000612  loss: 2.2881 (2.1423)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0004  max mem: 42573
Epoch: [228]  [140/312]  eta: 0:01:29  lr: 0.000611  min_lr: 0.000611  loss: 2.3347 (2.1494)  weight_decay: 0.0500 (0.0500)  time: 0.4359  data: 0.0004  max mem: 42573
Epoch: [228]  [150/312]  eta: 0:01:23  lr: 0.000611  min_lr: 0.000611  loss: 2.3042 (2.1515)  weight_decay: 0.0500 (0.0500)  time: 0.4356  data: 0.0004  max mem: 42573
Epoch: [228]  [160/312]  eta: 0:01:17  lr: 0.000610  min_lr: 0.000610  loss: 2.2235 (2.1526)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [228]  [170/312]  eta: 0:01:11  lr: 0.000610  min_lr: 0.000610  loss: 2.2235 (2.1570)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [228]  [180/312]  eta: 0:01:06  lr: 0.000609  min_lr: 0.000609  loss: 2.4251 (2.1718)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [228]  [190/312]  eta: 0:01:00  lr: 0.000609  min_lr: 0.000609  loss: 2.3671 (2.1635)  weight_decay: 0.0500 (0.0500)  time: 0.4332  data: 0.0004  max mem: 42573
Epoch: [228]  [200/312]  eta: 0:00:55  lr: 0.000608  min_lr: 0.000608  loss: 2.0570 (2.1657)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [228]  [210/312]  eta: 0:00:50  lr: 0.000608  min_lr: 0.000608  loss: 2.1843 (2.1694)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [228]  [220/312]  eta: 0:00:45  lr: 0.000607  min_lr: 0.000607  loss: 2.3271 (2.1802)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [228]  [230/312]  eta: 0:00:39  lr: 0.000607  min_lr: 0.000607  loss: 2.1859 (2.1682)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [228]  [240/312]  eta: 0:00:34  lr: 0.000606  min_lr: 0.000606  loss: 1.9007 (2.1621)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [228]  [250/312]  eta: 0:00:29  lr: 0.000606  min_lr: 0.000606  loss: 2.1284 (2.1637)  weight_decay: 0.0500 (0.0500)  time: 0.4332  data: 0.0004  max mem: 42573
Epoch: [228]  [260/312]  eta: 0:00:25  lr: 0.000605  min_lr: 0.000605  loss: 2.1284 (2.1640)  weight_decay: 0.0500 (0.0500)  time: 0.4332  data: 0.0004  max mem: 42573
Epoch: [228]  [270/312]  eta: 0:00:20  lr: 0.000605  min_lr: 0.000605  loss: 2.0887 (2.1650)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [228]  [280/312]  eta: 0:00:15  lr: 0.000604  min_lr: 0.000604  loss: 2.0842 (2.1622)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0011  max mem: 42573
Epoch: [228]  [290/312]  eta: 0:00:10  lr: 0.000604  min_lr: 0.000604  loss: 2.1291 (2.1646)  weight_decay: 0.0500 (0.0500)  time: 0.4332  data: 0.0010  max mem: 42573
Epoch: [228]  [300/312]  eta: 0:00:05  lr: 0.000603  min_lr: 0.000603  loss: 2.1291 (2.1653)  weight_decay: 0.0500 (0.0500)  time: 0.4320  data: 0.0001  max mem: 42573
Epoch: [228]  [310/312]  eta: 0:00:00  lr: 0.000603  min_lr: 0.000603  loss: 2.1037 (2.1643)  weight_decay: 0.0500 (0.0500)  time: 0.4320  data: 0.0001  max mem: 42573
Epoch: [228]  [311/312]  eta: 0:00:00  lr: 0.000603  min_lr: 0.000603  loss: 2.0480 (2.1620)  weight_decay: 0.0500 (0.0500)  time: 0.4320  data: 0.0001  max mem: 42573
Epoch: [228] Total time: 0:02:28 (0.4761 s / it)
Averaged stats: lr: 0.000603  min_lr: 0.000603  loss: 2.0480 (2.1874)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:00:40  loss: 0.6531 (0.6531)  acc1: 84.8958 (84.8958)  acc5: 96.6146 (96.6146)  time: 4.4769  data: 4.3700  max mem: 42573
Test:  [8/9]  eta: 0:00:00  loss: 0.8253 (0.8265)  acc1: 79.4271 (78.2720)  acc5: 94.0104 (94.4640)  time: 0.5728  data: 0.4857  max mem: 42573
Test: Total time: 0:00:05 (0.5801 s / it)
* Acc@1 78.452 Acc@5 94.142 loss 0.825
Accuracy of the model on the 50000 test images: 78.5%
Max accuracy: 78.55%
Epoch: [229]  [  0/312]  eta: 0:55:14  lr: 0.000603  min_lr: 0.000603  loss: 2.6357 (2.6357)  weight_decay: 0.0500 (0.0500)  time: 10.6242  data: 6.8677  max mem: 42573
Epoch: [229]  [ 10/312]  eta: 0:07:55  lr: 0.000602  min_lr: 0.000602  loss: 2.2357 (2.2228)  weight_decay: 0.0500 (0.0500)  time: 1.5741  data: 0.6434  max mem: 42573
Epoch: [229]  [ 20/312]  eta: 0:05:01  lr: 0.000602  min_lr: 0.000602  loss: 2.2263 (2.2392)  weight_decay: 0.0500 (0.0500)  time: 0.5514  data: 0.0106  max mem: 42573
Epoch: [229]  [ 30/312]  eta: 0:03:56  lr: 0.000601  min_lr: 0.000601  loss: 2.2263 (2.2103)  weight_decay: 0.0500 (0.0500)  time: 0.4342  data: 0.0004  max mem: 42573
Epoch: [229]  [ 40/312]  eta: 0:03:21  lr: 0.000601  min_lr: 0.000601  loss: 2.1856 (2.1975)  weight_decay: 0.0500 (0.0500)  time: 0.4344  data: 0.0004  max mem: 42573
Epoch: [229]  [ 50/312]  eta: 0:02:58  lr: 0.000600  min_lr: 0.000600  loss: 2.4201 (2.2194)  weight_decay: 0.0500 (0.0500)  time: 0.4346  data: 0.0004  max mem: 42573
Epoch: [229]  [ 60/312]  eta: 0:02:41  lr: 0.000600  min_lr: 0.000600  loss: 2.2877 (2.1956)  weight_decay: 0.0500 (0.0500)  time: 0.4344  data: 0.0004  max mem: 42573
Epoch: [229]  [ 70/312]  eta: 0:02:27  lr: 0.000599  min_lr: 0.000599  loss: 2.2935 (2.2188)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [229]  [ 80/312]  eta: 0:02:16  lr: 0.000598  min_lr: 0.000598  loss: 2.3136 (2.2125)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [229]  [ 90/312]  eta: 0:02:06  lr: 0.000598  min_lr: 0.000598  loss: 2.2889 (2.2056)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0004  max mem: 42573
Epoch: [229]  [100/312]  eta: 0:01:58  lr: 0.000597  min_lr: 0.000597  loss: 2.3279 (2.2126)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [229]  [110/312]  eta: 0:01:50  lr: 0.000597  min_lr: 0.000597  loss: 2.3726 (2.2252)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [229]  [120/312]  eta: 0:01:43  lr: 0.000596  min_lr: 0.000596  loss: 2.1248 (2.2063)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [229]  [130/312]  eta: 0:01:36  lr: 0.000596  min_lr: 0.000596  loss: 2.1248 (2.2064)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [229]  [140/312]  eta: 0:01:29  lr: 0.000595  min_lr: 0.000595  loss: 2.2022 (2.2082)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [229]  [150/312]  eta: 0:01:23  lr: 0.000595  min_lr: 0.000595  loss: 2.2306 (2.2113)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [229]  [160/312]  eta: 0:01:17  lr: 0.000594  min_lr: 0.000594  loss: 2.1858 (2.2003)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0005  max mem: 42573
Epoch: [229]  [170/312]  eta: 0:01:12  lr: 0.000594  min_lr: 0.000594  loss: 2.0771 (2.1854)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [229]  [180/312]  eta: 0:01:06  lr: 0.000593  min_lr: 0.000593  loss: 2.0366 (2.1827)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [229]  [190/312]  eta: 0:01:00  lr: 0.000593  min_lr: 0.000593  loss: 2.1654 (2.1793)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [229]  [200/312]  eta: 0:00:55  lr: 0.000592  min_lr: 0.000592  loss: 2.1654 (2.1764)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [229]  [210/312]  eta: 0:00:50  lr: 0.000592  min_lr: 0.000592  loss: 2.1135 (2.1737)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [229]  [220/312]  eta: 0:00:45  lr: 0.000591  min_lr: 0.000591  loss: 2.2215 (2.1763)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [229]  [230/312]  eta: 0:00:40  lr: 0.000591  min_lr: 0.000591  loss: 2.0731 (2.1681)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [229]  [240/312]  eta: 0:00:34  lr: 0.000590  min_lr: 0.000590  loss: 2.1484 (2.1701)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [229]  [250/312]  eta: 0:00:29  lr: 0.000590  min_lr: 0.000590  loss: 2.2179 (2.1612)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [229]  [260/312]  eta: 0:00:25  lr: 0.000589  min_lr: 0.000589  loss: 2.1697 (2.1593)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [229]  [270/312]  eta: 0:00:20  lr: 0.000589  min_lr: 0.000589  loss: 2.3792 (2.1669)  weight_decay: 0.0500 (0.0500)  time: 0.4381  data: 0.0004  max mem: 42573
Epoch: [229]  [280/312]  eta: 0:00:15  lr: 0.000588  min_lr: 0.000588  loss: 2.4066 (2.1692)  weight_decay: 0.0500 (0.0500)  time: 0.4382  data: 0.0012  max mem: 42573
Epoch: [229]  [290/312]  eta: 0:00:10  lr: 0.000588  min_lr: 0.000588  loss: 2.3168 (2.1763)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0010  max mem: 42573
Epoch: [229]  [300/312]  eta: 0:00:05  lr: 0.000587  min_lr: 0.000587  loss: 2.2998 (2.1767)  weight_decay: 0.0500 (0.0500)  time: 0.4321  data: 0.0001  max mem: 42573
Epoch: [229]  [310/312]  eta: 0:00:00  lr: 0.000587  min_lr: 0.000587  loss: 2.1939 (2.1738)  weight_decay: 0.0500 (0.0500)  time: 0.4320  data: 0.0001  max mem: 42573
Epoch: [229]  [311/312]  eta: 0:00:00  lr: 0.000587  min_lr: 0.000587  loss: 2.1939 (2.1742)  weight_decay: 0.0500 (0.0500)  time: 0.4320  data: 0.0001  max mem: 42573
Epoch: [229] Total time: 0:02:28 (0.4770 s / it)
Averaged stats: lr: 0.000587  min_lr: 0.000587  loss: 2.1939 (2.1955)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:00:39  loss: 0.6621 (0.6621)  acc1: 83.5938 (83.5938)  acc5: 95.0521 (95.0521)  time: 4.3349  data: 4.2263  max mem: 42573
Test:  [8/9]  eta: 0:00:00  loss: 0.8693 (0.8442)  acc1: 79.4271 (77.0560)  acc5: 94.7917 (94.1440)  time: 0.5641  data: 0.4756  max mem: 42573
Test: Total time: 0:00:05 (0.5731 s / it)
* Acc@1 78.344 Acc@5 94.136 loss 0.834
Accuracy of the model on the 50000 test images: 78.3%
Max accuracy: 78.55%
Epoch: [230]  [  0/312]  eta: 0:51:06  lr: 0.000587  min_lr: 0.000587  loss: 2.6192 (2.6192)  weight_decay: 0.0500 (0.0500)  time: 9.8271  data: 7.7347  max mem: 42573
Epoch: [230]  [ 10/312]  eta: 0:07:05  lr: 0.000586  min_lr: 0.000586  loss: 2.3210 (2.2196)  weight_decay: 0.0500 (0.0500)  time: 1.4098  data: 0.7036  max mem: 42573
Epoch: [230]  [ 20/312]  eta: 0:04:36  lr: 0.000586  min_lr: 0.000586  loss: 2.1628 (2.2071)  weight_decay: 0.0500 (0.0500)  time: 0.5026  data: 0.0004  max mem: 42573
Epoch: [230]  [ 30/312]  eta: 0:03:40  lr: 0.000585  min_lr: 0.000585  loss: 2.1628 (2.1819)  weight_decay: 0.0500 (0.0500)  time: 0.4355  data: 0.0004  max mem: 42573
Epoch: [230]  [ 40/312]  eta: 0:03:09  lr: 0.000585  min_lr: 0.000585  loss: 2.1861 (2.1648)  weight_decay: 0.0500 (0.0500)  time: 0.4342  data: 0.0003  max mem: 42573
Epoch: [230]  [ 50/312]  eta: 0:02:48  lr: 0.000584  min_lr: 0.000584  loss: 2.1861 (2.1469)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [230]  [ 60/312]  eta: 0:02:33  lr: 0.000584  min_lr: 0.000584  loss: 2.2038 (2.1610)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [230]  [ 70/312]  eta: 0:02:21  lr: 0.000583  min_lr: 0.000583  loss: 2.2221 (2.1561)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [230]  [ 80/312]  eta: 0:02:11  lr: 0.000583  min_lr: 0.000583  loss: 2.2853 (2.1644)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [230]  [ 90/312]  eta: 0:02:02  lr: 0.000582  min_lr: 0.000582  loss: 2.2484 (2.1652)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [230]  [100/312]  eta: 0:01:54  lr: 0.000582  min_lr: 0.000582  loss: 2.1695 (2.1634)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [230]  [110/312]  eta: 0:01:47  lr: 0.000581  min_lr: 0.000581  loss: 2.2461 (2.1626)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [230]  [120/312]  eta: 0:01:40  lr: 0.000581  min_lr: 0.000581  loss: 1.8762 (2.1448)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [230]  [130/312]  eta: 0:01:33  lr: 0.000580  min_lr: 0.000580  loss: 1.9358 (2.1458)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [230]  [140/312]  eta: 0:01:27  lr: 0.000580  min_lr: 0.000580  loss: 2.2633 (2.1498)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [230]  [150/312]  eta: 0:01:21  lr: 0.000579  min_lr: 0.000579  loss: 2.3032 (2.1621)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [230]  [160/312]  eta: 0:01:16  lr: 0.000579  min_lr: 0.000579  loss: 2.4049 (2.1747)  weight_decay: 0.0500 (0.0500)  time: 0.4332  data: 0.0004  max mem: 42573
Epoch: [230]  [170/312]  eta: 0:01:10  lr: 0.000578  min_lr: 0.000578  loss: 2.3320 (2.1767)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [230]  [180/312]  eta: 0:01:05  lr: 0.000578  min_lr: 0.000578  loss: 2.3256 (2.1844)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [230]  [190/312]  eta: 0:00:59  lr: 0.000577  min_lr: 0.000577  loss: 2.1102 (2.1779)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [230]  [200/312]  eta: 0:00:54  lr: 0.000577  min_lr: 0.000577  loss: 1.9994 (2.1756)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [230]  [210/312]  eta: 0:00:49  lr: 0.000576  min_lr: 0.000576  loss: 2.2571 (2.1783)  weight_decay: 0.0500 (0.0500)  time: 0.4364  data: 0.0004  max mem: 42573
Epoch: [230]  [220/312]  eta: 0:00:44  lr: 0.000575  min_lr: 0.000575  loss: 2.2610 (2.1755)  weight_decay: 0.0500 (0.0500)  time: 0.4363  data: 0.0004  max mem: 42573
Epoch: [230]  [230/312]  eta: 0:00:39  lr: 0.000575  min_lr: 0.000575  loss: 2.1344 (2.1786)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [230]  [240/312]  eta: 0:00:34  lr: 0.000574  min_lr: 0.000574  loss: 2.1344 (2.1739)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [230]  [250/312]  eta: 0:00:29  lr: 0.000574  min_lr: 0.000574  loss: 2.3670 (2.1812)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [230]  [260/312]  eta: 0:00:24  lr: 0.000573  min_lr: 0.000573  loss: 2.4469 (2.1770)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [230]  [270/312]  eta: 0:00:19  lr: 0.000573  min_lr: 0.000573  loss: 2.1211 (2.1779)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [230]  [280/312]  eta: 0:00:15  lr: 0.000572  min_lr: 0.000572  loss: 2.1794 (2.1810)  weight_decay: 0.0500 (0.0500)  time: 0.4342  data: 0.0011  max mem: 42573
Epoch: [230]  [290/312]  eta: 0:00:10  lr: 0.000572  min_lr: 0.000572  loss: 2.1889 (2.1822)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0010  max mem: 42573
Epoch: [230]  [300/312]  eta: 0:00:05  lr: 0.000571  min_lr: 0.000571  loss: 2.1889 (2.1837)  weight_decay: 0.0500 (0.0500)  time: 0.4323  data: 0.0001  max mem: 42573
Epoch: [230]  [310/312]  eta: 0:00:00  lr: 0.000571  min_lr: 0.000571  loss: 2.1504 (2.1790)  weight_decay: 0.0500 (0.0500)  time: 0.4321  data: 0.0001  max mem: 42573
Epoch: [230]  [311/312]  eta: 0:00:00  lr: 0.000571  min_lr: 0.000571  loss: 2.1504 (2.1798)  weight_decay: 0.0500 (0.0500)  time: 0.4321  data: 0.0001  max mem: 42573
Epoch: [230] Total time: 0:02:26 (0.4711 s / it)
Averaged stats: lr: 0.000571  min_lr: 0.000571  loss: 2.1504 (2.1807)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:00:41  loss: 0.6322 (0.6322)  acc1: 85.6771 (85.6771)  acc5: 95.3125 (95.3125)  time: 4.6421  data: 4.5335  max mem: 42573
Test:  [8/9]  eta: 0:00:00  loss: 0.8458 (0.8247)  acc1: 78.3854 (78.0480)  acc5: 94.7917 (94.1760)  time: 0.5918  data: 0.5038  max mem: 42573
Test: Total time: 0:00:05 (0.6003 s / it)
* Acc@1 78.628 Acc@5 94.322 loss 0.820
Accuracy of the model on the 50000 test images: 78.6%
Max accuracy: 78.63%
Epoch: [231]  [  0/312]  eta: 0:48:33  lr: 0.000571  min_lr: 0.000571  loss: 2.0913 (2.0913)  weight_decay: 0.0500 (0.0500)  time: 9.3381  data: 8.5789  max mem: 42573
Epoch: [231]  [ 10/312]  eta: 0:07:30  lr: 0.000570  min_lr: 0.000570  loss: 2.0913 (2.0577)  weight_decay: 0.0500 (0.0500)  time: 1.4934  data: 0.7802  max mem: 42573
Epoch: [231]  [ 20/312]  eta: 0:04:48  lr: 0.000570  min_lr: 0.000570  loss: 2.2608 (2.2140)  weight_decay: 0.0500 (0.0500)  time: 0.5710  data: 0.0004  max mem: 42573
Epoch: [231]  [ 30/312]  eta: 0:03:48  lr: 0.000569  min_lr: 0.000569  loss: 2.3450 (2.2310)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [231]  [ 40/312]  eta: 0:03:15  lr: 0.000569  min_lr: 0.000569  loss: 2.2601 (2.2312)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0003  max mem: 42573
Epoch: [231]  [ 50/312]  eta: 0:02:53  lr: 0.000568  min_lr: 0.000568  loss: 2.2601 (2.2064)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [231]  [ 60/312]  eta: 0:02:37  lr: 0.000568  min_lr: 0.000568  loss: 1.9099 (2.1751)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [231]  [ 70/312]  eta: 0:02:24  lr: 0.000567  min_lr: 0.000567  loss: 2.1969 (2.1959)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [231]  [ 80/312]  eta: 0:02:13  lr: 0.000567  min_lr: 0.000567  loss: 2.3754 (2.2038)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [231]  [ 90/312]  eta: 0:02:04  lr: 0.000566  min_lr: 0.000566  loss: 2.2090 (2.2068)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [231]  [100/312]  eta: 0:01:56  lr: 0.000566  min_lr: 0.000566  loss: 2.2044 (2.2046)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [231]  [110/312]  eta: 0:01:48  lr: 0.000565  min_lr: 0.000565  loss: 2.2257 (2.2043)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [231]  [120/312]  eta: 0:01:41  lr: 0.000565  min_lr: 0.000565  loss: 2.2916 (2.2113)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [231]  [130/312]  eta: 0:01:35  lr: 0.000564  min_lr: 0.000564  loss: 2.2916 (2.2213)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [231]  [140/312]  eta: 0:01:28  lr: 0.000564  min_lr: 0.000564  loss: 2.3258 (2.2226)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0003  max mem: 42573
Epoch: [231]  [150/312]  eta: 0:01:22  lr: 0.000563  min_lr: 0.000563  loss: 2.2851 (2.2203)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0003  max mem: 42573
Epoch: [231]  [160/312]  eta: 0:01:16  lr: 0.000563  min_lr: 0.000563  loss: 2.2260 (2.2068)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [231]  [170/312]  eta: 0:01:11  lr: 0.000562  min_lr: 0.000562  loss: 2.3059 (2.2203)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [231]  [180/312]  eta: 0:01:05  lr: 0.000562  min_lr: 0.000562  loss: 2.4471 (2.2216)  weight_decay: 0.0500 (0.0500)  time: 0.4379  data: 0.0004  max mem: 42573
Epoch: [231]  [190/312]  eta: 0:01:00  lr: 0.000561  min_lr: 0.000561  loss: 2.2411 (2.2174)  weight_decay: 0.0500 (0.0500)  time: 0.4379  data: 0.0004  max mem: 42573
Epoch: [231]  [200/312]  eta: 0:00:55  lr: 0.000561  min_lr: 0.000561  loss: 2.2428 (2.2205)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [231]  [210/312]  eta: 0:00:49  lr: 0.000560  min_lr: 0.000560  loss: 2.3266 (2.2147)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [231]  [220/312]  eta: 0:00:44  lr: 0.000560  min_lr: 0.000560  loss: 2.3019 (2.2192)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [231]  [230/312]  eta: 0:00:39  lr: 0.000559  min_lr: 0.000559  loss: 2.3019 (2.2170)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [231]  [240/312]  eta: 0:00:34  lr: 0.000559  min_lr: 0.000559  loss: 2.1766 (2.2070)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [231]  [250/312]  eta: 0:00:29  lr: 0.000558  min_lr: 0.000558  loss: 2.1835 (2.2078)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [231]  [260/312]  eta: 0:00:24  lr: 0.000558  min_lr: 0.000558  loss: 2.1956 (2.1974)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [231]  [270/312]  eta: 0:00:20  lr: 0.000557  min_lr: 0.000557  loss: 2.1577 (2.1957)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0003  max mem: 42573
Epoch: [231]  [280/312]  eta: 0:00:15  lr: 0.000557  min_lr: 0.000557  loss: 2.2718 (2.2010)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0009  max mem: 42573
Epoch: [231]  [290/312]  eta: 0:00:10  lr: 0.000556  min_lr: 0.000556  loss: 2.1332 (2.1960)  weight_decay: 0.0500 (0.0500)  time: 0.4331  data: 0.0008  max mem: 42573
Epoch: [231]  [300/312]  eta: 0:00:05  lr: 0.000556  min_lr: 0.000556  loss: 2.0612 (2.1973)  weight_decay: 0.0500 (0.0500)  time: 0.4321  data: 0.0001  max mem: 42573
Epoch: [231]  [310/312]  eta: 0:00:00  lr: 0.000555  min_lr: 0.000555  loss: 2.2648 (2.1971)  weight_decay: 0.0500 (0.0500)  time: 0.4320  data: 0.0001  max mem: 42573
Epoch: [231]  [311/312]  eta: 0:00:00  lr: 0.000555  min_lr: 0.000555  loss: 2.2648 (2.1975)  weight_decay: 0.0500 (0.0500)  time: 0.4320  data: 0.0001  max mem: 42573
Epoch: [231] Total time: 0:02:27 (0.4740 s / it)
Averaged stats: lr: 0.000555  min_lr: 0.000555  loss: 2.2648 (2.1823)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:00:42  loss: 0.6365 (0.6365)  acc1: 83.3333 (83.3333)  acc5: 95.3125 (95.3125)  time: 4.7129  data: 4.6045  max mem: 42573
Test:  [8/9]  eta: 0:00:00  loss: 0.7929 (0.8416)  acc1: 78.1250 (77.3760)  acc5: 95.0521 (94.4000)  time: 0.5999  data: 0.5117  max mem: 42573
Test: Total time: 0:00:05 (0.6101 s / it)
* Acc@1 78.448 Acc@5 94.228 loss 0.831
Accuracy of the model on the 50000 test images: 78.4%
Max accuracy: 78.63%
Epoch: [232]  [  0/312]  eta: 0:53:39  lr: 0.000555  min_lr: 0.000555  loss: 2.8600 (2.8600)  weight_decay: 0.0500 (0.0500)  time: 10.3187  data: 6.4303  max mem: 42573
Epoch: [232]  [ 10/312]  eta: 0:07:54  lr: 0.000555  min_lr: 0.000555  loss: 2.3656 (2.3167)  weight_decay: 0.0500 (0.0500)  time: 1.5724  data: 0.7720  max mem: 42573
Epoch: [232]  [ 20/312]  eta: 0:05:00  lr: 0.000554  min_lr: 0.000554  loss: 2.2771 (2.3024)  weight_decay: 0.0500 (0.0500)  time: 0.5659  data: 0.1032  max mem: 42573
Epoch: [232]  [ 30/312]  eta: 0:03:56  lr: 0.000554  min_lr: 0.000554  loss: 2.2896 (2.2881)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0003  max mem: 42573
Epoch: [232]  [ 40/312]  eta: 0:03:21  lr: 0.000553  min_lr: 0.000553  loss: 2.2896 (2.2776)  weight_decay: 0.0500 (0.0500)  time: 0.4341  data: 0.0004  max mem: 42573
Epoch: [232]  [ 50/312]  eta: 0:02:58  lr: 0.000553  min_lr: 0.000553  loss: 2.2976 (2.2686)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0004  max mem: 42573
Epoch: [232]  [ 60/312]  eta: 0:02:41  lr: 0.000552  min_lr: 0.000552  loss: 2.3158 (2.2634)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [232]  [ 70/312]  eta: 0:02:27  lr: 0.000552  min_lr: 0.000552  loss: 2.1994 (2.2294)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [232]  [ 80/312]  eta: 0:02:16  lr: 0.000551  min_lr: 0.000551  loss: 1.9787 (2.2149)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [232]  [ 90/312]  eta: 0:02:06  lr: 0.000551  min_lr: 0.000551  loss: 2.1255 (2.2092)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [232]  [100/312]  eta: 0:01:58  lr: 0.000550  min_lr: 0.000550  loss: 2.1947 (2.2067)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [232]  [110/312]  eta: 0:01:50  lr: 0.000550  min_lr: 0.000550  loss: 2.2308 (2.2159)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [232]  [120/312]  eta: 0:01:43  lr: 0.000549  min_lr: 0.000549  loss: 2.1772 (2.2030)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [232]  [130/312]  eta: 0:01:36  lr: 0.000549  min_lr: 0.000549  loss: 2.0160 (2.1982)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [232]  [140/312]  eta: 0:01:29  lr: 0.000548  min_lr: 0.000548  loss: 2.2629 (2.1963)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [232]  [150/312]  eta: 0:01:23  lr: 0.000548  min_lr: 0.000548  loss: 2.2629 (2.1929)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [232]  [160/312]  eta: 0:01:17  lr: 0.000547  min_lr: 0.000547  loss: 2.2221 (2.1863)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [232]  [170/312]  eta: 0:01:11  lr: 0.000547  min_lr: 0.000547  loss: 2.0980 (2.1806)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [232]  [180/312]  eta: 0:01:06  lr: 0.000546  min_lr: 0.000546  loss: 2.2789 (2.1848)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [232]  [190/312]  eta: 0:01:00  lr: 0.000546  min_lr: 0.000546  loss: 2.2656 (2.1859)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [232]  [200/312]  eta: 0:00:55  lr: 0.000545  min_lr: 0.000545  loss: 2.2337 (2.1912)  weight_decay: 0.0500 (0.0500)  time: 0.4331  data: 0.0004  max mem: 42573
Epoch: [232]  [210/312]  eta: 0:00:50  lr: 0.000545  min_lr: 0.000545  loss: 2.1885 (2.1847)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [232]  [220/312]  eta: 0:00:45  lr: 0.000544  min_lr: 0.000544  loss: 2.0772 (2.1821)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [232]  [230/312]  eta: 0:00:39  lr: 0.000544  min_lr: 0.000544  loss: 2.3237 (2.1945)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [232]  [240/312]  eta: 0:00:34  lr: 0.000543  min_lr: 0.000543  loss: 2.3237 (2.1908)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [232]  [250/312]  eta: 0:00:29  lr: 0.000543  min_lr: 0.000543  loss: 2.1428 (2.1904)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0003  max mem: 42573
Epoch: [232]  [260/312]  eta: 0:00:25  lr: 0.000542  min_lr: 0.000542  loss: 2.1714 (2.1899)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [232]  [270/312]  eta: 0:00:20  lr: 0.000542  min_lr: 0.000542  loss: 2.0155 (2.1779)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [232]  [280/312]  eta: 0:00:15  lr: 0.000541  min_lr: 0.000541  loss: 2.0272 (2.1766)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0009  max mem: 42573
Epoch: [232]  [290/312]  eta: 0:00:10  lr: 0.000541  min_lr: 0.000541  loss: 2.2641 (2.1785)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0008  max mem: 42573
Epoch: [232]  [300/312]  eta: 0:00:05  lr: 0.000540  min_lr: 0.000540  loss: 2.2934 (2.1796)  weight_decay: 0.0500 (0.0500)  time: 0.4322  data: 0.0001  max mem: 42573
Epoch: [232]  [310/312]  eta: 0:00:00  lr: 0.000540  min_lr: 0.000540  loss: 2.0152 (2.1750)  weight_decay: 0.0500 (0.0500)  time: 0.4321  data: 0.0001  max mem: 42573
Epoch: [232]  [311/312]  eta: 0:00:00  lr: 0.000540  min_lr: 0.000540  loss: 1.9778 (2.1727)  weight_decay: 0.0500 (0.0500)  time: 0.4322  data: 0.0001  max mem: 42573
Epoch: [232] Total time: 0:02:28 (0.4766 s / it)
Averaged stats: lr: 0.000540  min_lr: 0.000540  loss: 1.9778 (2.1670)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:00:41  loss: 0.6307 (0.6307)  acc1: 84.3750 (84.3750)  acc5: 95.5729 (95.5729)  time: 4.6633  data: 4.5552  max mem: 42573
Test:  [8/9]  eta: 0:00:00  loss: 0.8169 (0.8282)  acc1: 79.4271 (78.3360)  acc5: 94.2708 (94.5600)  time: 0.5952  data: 0.5062  max mem: 42573
Test: Total time: 0:00:05 (0.6125 s / it)
* Acc@1 78.704 Acc@5 94.406 loss 0.816
Accuracy of the model on the 50000 test images: 78.7%
Max accuracy: 78.70%
Epoch: [233]  [  0/312]  eta: 0:51:59  lr: 0.000540  min_lr: 0.000540  loss: 1.7674 (1.7674)  weight_decay: 0.0500 (0.0500)  time: 10.0000  data: 7.5439  max mem: 42573
Epoch: [233]  [ 10/312]  eta: 0:07:56  lr: 0.000539  min_lr: 0.000539  loss: 2.3097 (2.1547)  weight_decay: 0.0500 (0.0500)  time: 1.5767  data: 0.7043  max mem: 42573
Epoch: [233]  [ 20/312]  eta: 0:05:01  lr: 0.000539  min_lr: 0.000539  loss: 2.2399 (2.1487)  weight_decay: 0.0500 (0.0500)  time: 0.5837  data: 0.0103  max mem: 42573
Epoch: [233]  [ 30/312]  eta: 0:03:56  lr: 0.000538  min_lr: 0.000538  loss: 2.2399 (2.1650)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0003  max mem: 42573
Epoch: [233]  [ 40/312]  eta: 0:03:21  lr: 0.000538  min_lr: 0.000538  loss: 2.3024 (2.1713)  weight_decay: 0.0500 (0.0500)  time: 0.4355  data: 0.0003  max mem: 42573
Epoch: [233]  [ 50/312]  eta: 0:02:58  lr: 0.000537  min_lr: 0.000537  loss: 2.2357 (2.1714)  weight_decay: 0.0500 (0.0500)  time: 0.4356  data: 0.0004  max mem: 42573
Epoch: [233]  [ 60/312]  eta: 0:02:41  lr: 0.000537  min_lr: 0.000537  loss: 2.2357 (2.2005)  weight_decay: 0.0500 (0.0500)  time: 0.4341  data: 0.0004  max mem: 42573
Epoch: [233]  [ 70/312]  eta: 0:02:27  lr: 0.000536  min_lr: 0.000536  loss: 2.2007 (2.1629)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0004  max mem: 42573
Epoch: [233]  [ 80/312]  eta: 0:02:16  lr: 0.000536  min_lr: 0.000536  loss: 2.0139 (2.1585)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [233]  [ 90/312]  eta: 0:02:07  lr: 0.000535  min_lr: 0.000535  loss: 2.1808 (2.1554)  weight_decay: 0.0500 (0.0500)  time: 0.4343  data: 0.0004  max mem: 42573
Epoch: [233]  [100/312]  eta: 0:01:58  lr: 0.000535  min_lr: 0.000535  loss: 2.2545 (2.1572)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [233]  [110/312]  eta: 0:01:50  lr: 0.000534  min_lr: 0.000534  loss: 2.0547 (2.1478)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [233]  [120/312]  eta: 0:01:43  lr: 0.000534  min_lr: 0.000534  loss: 2.1141 (2.1542)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [233]  [130/312]  eta: 0:01:36  lr: 0.000533  min_lr: 0.000533  loss: 2.1603 (2.1409)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [233]  [140/312]  eta: 0:01:29  lr: 0.000533  min_lr: 0.000533  loss: 2.0758 (2.1442)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [233]  [150/312]  eta: 0:01:23  lr: 0.000533  min_lr: 0.000533  loss: 2.1714 (2.1505)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [233]  [160/312]  eta: 0:01:17  lr: 0.000532  min_lr: 0.000532  loss: 2.2243 (2.1483)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [233]  [170/312]  eta: 0:01:12  lr: 0.000532  min_lr: 0.000532  loss: 2.3266 (2.1574)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [233]  [180/312]  eta: 0:01:06  lr: 0.000531  min_lr: 0.000531  loss: 2.3072 (2.1596)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [233]  [190/312]  eta: 0:01:00  lr: 0.000531  min_lr: 0.000531  loss: 2.1979 (2.1614)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [233]  [200/312]  eta: 0:00:55  lr: 0.000530  min_lr: 0.000530  loss: 2.0571 (2.1530)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [233]  [210/312]  eta: 0:00:50  lr: 0.000530  min_lr: 0.000530  loss: 2.0919 (2.1539)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [233]  [220/312]  eta: 0:00:45  lr: 0.000529  min_lr: 0.000529  loss: 2.2605 (2.1607)  weight_decay: 0.0500 (0.0500)  time: 0.4332  data: 0.0004  max mem: 42573
Epoch: [233]  [230/312]  eta: 0:00:40  lr: 0.000529  min_lr: 0.000529  loss: 2.3567 (2.1677)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [233]  [240/312]  eta: 0:00:34  lr: 0.000528  min_lr: 0.000528  loss: 2.2991 (2.1659)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0003  max mem: 42573
Epoch: [233]  [250/312]  eta: 0:00:30  lr: 0.000528  min_lr: 0.000528  loss: 2.0535 (2.1640)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [233]  [260/312]  eta: 0:00:25  lr: 0.000527  min_lr: 0.000527  loss: 2.3158 (2.1679)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [233]  [270/312]  eta: 0:00:20  lr: 0.000527  min_lr: 0.000527  loss: 2.2052 (2.1640)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [233]  [280/312]  eta: 0:00:15  lr: 0.000526  min_lr: 0.000526  loss: 2.0172 (2.1584)  weight_decay: 0.0500 (0.0500)  time: 0.4347  data: 0.0018  max mem: 42573
Epoch: [233]  [290/312]  eta: 0:00:10  lr: 0.000526  min_lr: 0.000526  loss: 2.0838 (2.1558)  weight_decay: 0.0500 (0.0500)  time: 0.4341  data: 0.0017  max mem: 42573
Epoch: [233]  [300/312]  eta: 0:00:05  lr: 0.000525  min_lr: 0.000525  loss: 2.0531 (2.1519)  weight_decay: 0.0500 (0.0500)  time: 0.4322  data: 0.0001  max mem: 42573
Epoch: [233]  [310/312]  eta: 0:00:00  lr: 0.000525  min_lr: 0.000525  loss: 2.1968 (2.1545)  weight_decay: 0.0500 (0.0500)  time: 0.4321  data: 0.0001  max mem: 42573
Epoch: [233]  [311/312]  eta: 0:00:00  lr: 0.000525  min_lr: 0.000525  loss: 2.2263 (2.1551)  weight_decay: 0.0500 (0.0500)  time: 0.4321  data: 0.0001  max mem: 42573
Epoch: [233] Total time: 0:02:28 (0.4771 s / it)
Averaged stats: lr: 0.000525  min_lr: 0.000525  loss: 2.2263 (2.1646)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:00:41  loss: 0.6378 (0.6378)  acc1: 84.1146 (84.1146)  acc5: 95.3125 (95.3125)  time: 4.6188  data: 4.5118  max mem: 42573
Test:  [8/9]  eta: 0:00:00  loss: 0.8220 (0.8484)  acc1: 79.4271 (77.5360)  acc5: 94.2708 (94.0160)  time: 0.5888  data: 0.5014  max mem: 42573
Test: Total time: 0:00:05 (0.5977 s / it)
* Acc@1 78.700 Acc@5 94.256 loss 0.821
Accuracy of the model on the 50000 test images: 78.7%
Max accuracy: 78.70%
Epoch: [234]  [  0/312]  eta: 0:55:33  lr: 0.000525  min_lr: 0.000525  loss: 2.7040 (2.7040)  weight_decay: 0.0500 (0.0500)  time: 10.6859  data: 8.0027  max mem: 42573
Epoch: [234]  [ 10/312]  eta: 0:07:41  lr: 0.000524  min_lr: 0.000524  loss: 2.3648 (2.3193)  weight_decay: 0.0500 (0.0500)  time: 1.5270  data: 0.8121  max mem: 42573
Epoch: [234]  [ 20/312]  eta: 0:04:54  lr: 0.000524  min_lr: 0.000524  loss: 2.1789 (2.2050)  weight_decay: 0.0500 (0.0500)  time: 0.5235  data: 0.0467  max mem: 42573
Epoch: [234]  [ 30/312]  eta: 0:03:52  lr: 0.000523  min_lr: 0.000523  loss: 2.1541 (2.1940)  weight_decay: 0.0500 (0.0500)  time: 0.4360  data: 0.0003  max mem: 42573
Epoch: [234]  [ 40/312]  eta: 0:03:18  lr: 0.000523  min_lr: 0.000523  loss: 2.1672 (2.1850)  weight_decay: 0.0500 (0.0500)  time: 0.4359  data: 0.0003  max mem: 42573
Epoch: [234]  [ 50/312]  eta: 0:02:55  lr: 0.000522  min_lr: 0.000522  loss: 2.3313 (2.2025)  weight_decay: 0.0500 (0.0500)  time: 0.4352  data: 0.0004  max mem: 42573
Epoch: [234]  [ 60/312]  eta: 0:02:39  lr: 0.000522  min_lr: 0.000522  loss: 2.4327 (2.2288)  weight_decay: 0.0500 (0.0500)  time: 0.4342  data: 0.0004  max mem: 42573
Epoch: [234]  [ 70/312]  eta: 0:02:26  lr: 0.000521  min_lr: 0.000521  loss: 2.3489 (2.2399)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [234]  [ 80/312]  eta: 0:02:15  lr: 0.000521  min_lr: 0.000521  loss: 2.2738 (2.2366)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [234]  [ 90/312]  eta: 0:02:05  lr: 0.000520  min_lr: 0.000520  loss: 2.2738 (2.2359)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [234]  [100/312]  eta: 0:01:57  lr: 0.000520  min_lr: 0.000520  loss: 2.1332 (2.2151)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [234]  [110/312]  eta: 0:01:49  lr: 0.000519  min_lr: 0.000519  loss: 2.2369 (2.2270)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [234]  [120/312]  eta: 0:01:42  lr: 0.000519  min_lr: 0.000519  loss: 2.3055 (2.2305)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [234]  [130/312]  eta: 0:01:35  lr: 0.000518  min_lr: 0.000518  loss: 2.3222 (2.2329)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [234]  [140/312]  eta: 0:01:29  lr: 0.000518  min_lr: 0.000518  loss: 2.2765 (2.2276)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [234]  [150/312]  eta: 0:01:23  lr: 0.000517  min_lr: 0.000517  loss: 1.8252 (2.1973)  weight_decay: 0.0500 (0.0500)  time: 0.4332  data: 0.0004  max mem: 42573
Epoch: [234]  [160/312]  eta: 0:01:17  lr: 0.000517  min_lr: 0.000517  loss: 1.8252 (2.1928)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0003  max mem: 42573
Epoch: [234]  [170/312]  eta: 0:01:11  lr: 0.000516  min_lr: 0.000516  loss: 2.1942 (2.1913)  weight_decay: 0.0500 (0.0500)  time: 0.4332  data: 0.0004  max mem: 42573
Epoch: [234]  [180/312]  eta: 0:01:06  lr: 0.000516  min_lr: 0.000516  loss: 2.2199 (2.1977)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [234]  [190/312]  eta: 0:01:00  lr: 0.000515  min_lr: 0.000515  loss: 2.1669 (2.1914)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [234]  [200/312]  eta: 0:00:55  lr: 0.000515  min_lr: 0.000515  loss: 2.1363 (2.1928)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [234]  [210/312]  eta: 0:00:50  lr: 0.000514  min_lr: 0.000514  loss: 2.3289 (2.1924)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [234]  [220/312]  eta: 0:00:44  lr: 0.000514  min_lr: 0.000514  loss: 2.1068 (2.1880)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [234]  [230/312]  eta: 0:00:39  lr: 0.000514  min_lr: 0.000514  loss: 2.1202 (2.1857)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [234]  [240/312]  eta: 0:00:34  lr: 0.000513  min_lr: 0.000513  loss: 2.1202 (2.1799)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0005  max mem: 42573
Epoch: [234]  [250/312]  eta: 0:00:29  lr: 0.000513  min_lr: 0.000513  loss: 2.0905 (2.1804)  weight_decay: 0.0500 (0.0500)  time: 0.4332  data: 0.0005  max mem: 42573
Epoch: [234]  [260/312]  eta: 0:00:24  lr: 0.000512  min_lr: 0.000512  loss: 2.0975 (2.1768)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [234]  [270/312]  eta: 0:00:20  lr: 0.000512  min_lr: 0.000512  loss: 2.1024 (2.1793)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [234]  [280/312]  eta: 0:00:15  lr: 0.000511  min_lr: 0.000511  loss: 2.0161 (2.1677)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0014  max mem: 42573
Epoch: [234]  [290/312]  eta: 0:00:10  lr: 0.000511  min_lr: 0.000511  loss: 2.0190 (2.1695)  weight_decay: 0.0500 (0.0500)  time: 0.4332  data: 0.0012  max mem: 42573
Epoch: [234]  [300/312]  eta: 0:00:05  lr: 0.000510  min_lr: 0.000510  loss: 2.2064 (2.1736)  weight_decay: 0.0500 (0.0500)  time: 0.4347  data: 0.0001  max mem: 42573
Epoch: [234]  [310/312]  eta: 0:00:00  lr: 0.000510  min_lr: 0.000510  loss: 2.2709 (2.1790)  weight_decay: 0.0500 (0.0500)  time: 0.4346  data: 0.0001  max mem: 42573
Epoch: [234]  [311/312]  eta: 0:00:00  lr: 0.000510  min_lr: 0.000510  loss: 2.2709 (2.1799)  weight_decay: 0.0500 (0.0500)  time: 0.4317  data: 0.0001  max mem: 42573
Epoch: [234] Total time: 0:02:28 (0.4756 s / it)
Averaged stats: lr: 0.000510  min_lr: 0.000510  loss: 2.2709 (2.1665)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:00:38  loss: 0.6259 (0.6259)  acc1: 85.9375 (85.9375)  acc5: 95.5729 (95.5729)  time: 4.2960  data: 4.1881  max mem: 42573
Test:  [8/9]  eta: 0:00:00  loss: 0.8366 (0.8325)  acc1: 78.3854 (78.1760)  acc5: 95.3125 (94.5600)  time: 0.5559  data: 0.4654  max mem: 42573
Test: Total time: 0:00:05 (0.5630 s / it)
* Acc@1 78.710 Acc@5 94.410 loss 0.815
Accuracy of the model on the 50000 test images: 78.7%
Max accuracy: 78.71%
Epoch: [235]  [  0/312]  eta: 0:48:52  lr: 0.000510  min_lr: 0.000510  loss: 1.9823 (1.9823)  weight_decay: 0.0500 (0.0500)  time: 9.4004  data: 8.0082  max mem: 42573
Epoch: [235]  [ 10/312]  eta: 0:07:16  lr: 0.000509  min_lr: 0.000509  loss: 2.3496 (2.3392)  weight_decay: 0.0500 (0.0500)  time: 1.4444  data: 0.7855  max mem: 42573
Epoch: [235]  [ 20/312]  eta: 0:04:41  lr: 0.000509  min_lr: 0.000509  loss: 2.2963 (2.2606)  weight_decay: 0.0500 (0.0500)  time: 0.5410  data: 0.0318  max mem: 42573
Epoch: [235]  [ 30/312]  eta: 0:03:43  lr: 0.000508  min_lr: 0.000508  loss: 2.1479 (2.2636)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0003  max mem: 42573
Epoch: [235]  [ 40/312]  eta: 0:03:11  lr: 0.000508  min_lr: 0.000508  loss: 2.2742 (2.2739)  weight_decay: 0.0500 (0.0500)  time: 0.4345  data: 0.0004  max mem: 42573
Epoch: [235]  [ 50/312]  eta: 0:02:50  lr: 0.000507  min_lr: 0.000507  loss: 2.2742 (2.2174)  weight_decay: 0.0500 (0.0500)  time: 0.4350  data: 0.0004  max mem: 42573
Epoch: [235]  [ 60/312]  eta: 0:02:35  lr: 0.000507  min_lr: 0.000507  loss: 2.2870 (2.2326)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0004  max mem: 42573
Epoch: [235]  [ 70/312]  eta: 0:02:22  lr: 0.000506  min_lr: 0.000506  loss: 2.2870 (2.2191)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [235]  [ 80/312]  eta: 0:02:12  lr: 0.000506  min_lr: 0.000506  loss: 2.1562 (2.2042)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [235]  [ 90/312]  eta: 0:02:03  lr: 0.000505  min_lr: 0.000505  loss: 2.2524 (2.2010)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [235]  [100/312]  eta: 0:01:55  lr: 0.000505  min_lr: 0.000505  loss: 2.0892 (2.1819)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0003  max mem: 42573
Epoch: [235]  [110/312]  eta: 0:01:47  lr: 0.000504  min_lr: 0.000504  loss: 2.0726 (2.1803)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [235]  [120/312]  eta: 0:01:40  lr: 0.000504  min_lr: 0.000504  loss: 2.1956 (2.1814)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [235]  [130/312]  eta: 0:01:34  lr: 0.000503  min_lr: 0.000503  loss: 2.1698 (2.1755)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [235]  [140/312]  eta: 0:01:28  lr: 0.000503  min_lr: 0.000503  loss: 2.0545 (2.1663)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [235]  [150/312]  eta: 0:01:22  lr: 0.000502  min_lr: 0.000502  loss: 2.1896 (2.1676)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [235]  [160/312]  eta: 0:01:16  lr: 0.000502  min_lr: 0.000502  loss: 2.1896 (2.1651)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [235]  [170/312]  eta: 0:01:10  lr: 0.000501  min_lr: 0.000501  loss: 2.1592 (2.1642)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [235]  [180/312]  eta: 0:01:05  lr: 0.000501  min_lr: 0.000501  loss: 1.9869 (2.1540)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [235]  [190/312]  eta: 0:01:00  lr: 0.000501  min_lr: 0.000501  loss: 2.0462 (2.1523)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0003  max mem: 42573
Epoch: [235]  [200/312]  eta: 0:00:54  lr: 0.000500  min_lr: 0.000500  loss: 2.0473 (2.1511)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0003  max mem: 42573
Epoch: [235]  [210/312]  eta: 0:00:49  lr: 0.000500  min_lr: 0.000500  loss: 2.2882 (2.1544)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [235]  [220/312]  eta: 0:00:44  lr: 0.000499  min_lr: 0.000499  loss: 2.2882 (2.1583)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [235]  [230/312]  eta: 0:00:39  lr: 0.000499  min_lr: 0.000499  loss: 2.1162 (2.1530)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [235]  [240/312]  eta: 0:00:34  lr: 0.000498  min_lr: 0.000498  loss: 2.1030 (2.1564)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [235]  [250/312]  eta: 0:00:29  lr: 0.000498  min_lr: 0.000498  loss: 2.3012 (2.1596)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [235]  [260/312]  eta: 0:00:24  lr: 0.000497  min_lr: 0.000497  loss: 2.3046 (2.1618)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [235]  [270/312]  eta: 0:00:19  lr: 0.000497  min_lr: 0.000497  loss: 2.2340 (2.1612)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [235]  [280/312]  eta: 0:00:15  lr: 0.000496  min_lr: 0.000496  loss: 2.2108 (2.1615)  weight_decay: 0.0500 (0.0500)  time: 0.4345  data: 0.0009  max mem: 42573
Epoch: [235]  [290/312]  eta: 0:00:10  lr: 0.000496  min_lr: 0.000496  loss: 2.1080 (2.1567)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0008  max mem: 42573
Epoch: [235]  [300/312]  eta: 0:00:05  lr: 0.000495  min_lr: 0.000495  loss: 2.0311 (2.1577)  weight_decay: 0.0500 (0.0500)  time: 0.4323  data: 0.0001  max mem: 42573
Epoch: [235]  [310/312]  eta: 0:00:00  lr: 0.000495  min_lr: 0.000495  loss: 2.2611 (2.1628)  weight_decay: 0.0500 (0.0500)  time: 0.4322  data: 0.0001  max mem: 42573
Epoch: [235]  [311/312]  eta: 0:00:00  lr: 0.000495  min_lr: 0.000495  loss: 2.2611 (2.1615)  weight_decay: 0.0500 (0.0500)  time: 0.4323  data: 0.0001  max mem: 42573
Epoch: [235] Total time: 0:02:27 (0.4722 s / it)
Averaged stats: lr: 0.000495  min_lr: 0.000495  loss: 2.2611 (2.1577)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:00:43  loss: 0.6362 (0.6362)  acc1: 84.6354 (84.6354)  acc5: 95.8333 (95.8333)  time: 4.8209  data: 4.7125  max mem: 42573
Test:  [8/9]  eta: 0:00:00  loss: 0.8212 (0.8234)  acc1: 79.6875 (78.2720)  acc5: 94.5312 (94.3040)  time: 0.6117  data: 0.5237  max mem: 42573
Test: Total time: 0:00:05 (0.6311 s / it)
* Acc@1 79.146 Acc@5 94.410 loss 0.807
Accuracy of the model on the 50000 test images: 79.1%
Max accuracy: 79.15%
Epoch: [236]  [  0/312]  eta: 0:52:58  lr: 0.000495  min_lr: 0.000495  loss: 1.7923 (1.7923)  weight_decay: 0.0500 (0.0500)  time: 10.1867  data: 7.1304  max mem: 42573
Epoch: [236]  [ 10/312]  eta: 0:07:26  lr: 0.000494  min_lr: 0.000494  loss: 2.0403 (1.9856)  weight_decay: 0.0500 (0.0500)  time: 1.4794  data: 0.6704  max mem: 42573
Epoch: [236]  [ 20/312]  eta: 0:04:46  lr: 0.000494  min_lr: 0.000494  loss: 2.1057 (2.0687)  weight_decay: 0.0500 (0.0500)  time: 0.5210  data: 0.0124  max mem: 42573
Epoch: [236]  [ 30/312]  eta: 0:03:46  lr: 0.000493  min_lr: 0.000493  loss: 2.1648 (2.1336)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [236]  [ 40/312]  eta: 0:03:14  lr: 0.000493  min_lr: 0.000493  loss: 2.2050 (2.1579)  weight_decay: 0.0500 (0.0500)  time: 0.4341  data: 0.0004  max mem: 42573
Epoch: [236]  [ 50/312]  eta: 0:02:52  lr: 0.000492  min_lr: 0.000492  loss: 2.3494 (2.1993)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [236]  [ 60/312]  eta: 0:02:36  lr: 0.000492  min_lr: 0.000492  loss: 2.3213 (2.1950)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [236]  [ 70/312]  eta: 0:02:24  lr: 0.000491  min_lr: 0.000491  loss: 2.2249 (2.1884)  weight_decay: 0.0500 (0.0500)  time: 0.4371  data: 0.0004  max mem: 42573
Epoch: [236]  [ 80/312]  eta: 0:02:13  lr: 0.000491  min_lr: 0.000491  loss: 2.3105 (2.2084)  weight_decay: 0.0500 (0.0500)  time: 0.4368  data: 0.0004  max mem: 42573
Epoch: [236]  [ 90/312]  eta: 0:02:04  lr: 0.000490  min_lr: 0.000490  loss: 2.3109 (2.2119)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [236]  [100/312]  eta: 0:01:56  lr: 0.000490  min_lr: 0.000490  loss: 2.2149 (2.2116)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [236]  [110/312]  eta: 0:01:48  lr: 0.000490  min_lr: 0.000490  loss: 2.2716 (2.2085)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [236]  [120/312]  eta: 0:01:41  lr: 0.000489  min_lr: 0.000489  loss: 2.2390 (2.1969)  weight_decay: 0.0500 (0.0500)  time: 0.4347  data: 0.0004  max mem: 42573
Epoch: [236]  [130/312]  eta: 0:01:35  lr: 0.000489  min_lr: 0.000489  loss: 2.2746 (2.2055)  weight_decay: 0.0500 (0.0500)  time: 0.4350  data: 0.0004  max mem: 42573
Epoch: [236]  [140/312]  eta: 0:01:28  lr: 0.000488  min_lr: 0.000488  loss: 2.2746 (2.2068)  weight_decay: 0.0500 (0.0500)  time: 0.4341  data: 0.0004  max mem: 42573
Epoch: [236]  [150/312]  eta: 0:01:22  lr: 0.000488  min_lr: 0.000488  loss: 2.1571 (2.2019)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [236]  [160/312]  eta: 0:01:16  lr: 0.000487  min_lr: 0.000487  loss: 2.1392 (2.2013)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [236]  [170/312]  eta: 0:01:11  lr: 0.000487  min_lr: 0.000487  loss: 2.2064 (2.1985)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [236]  [180/312]  eta: 0:01:05  lr: 0.000486  min_lr: 0.000486  loss: 2.0329 (2.1878)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [236]  [190/312]  eta: 0:01:00  lr: 0.000486  min_lr: 0.000486  loss: 2.1676 (2.1970)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [236]  [200/312]  eta: 0:00:55  lr: 0.000485  min_lr: 0.000485  loss: 2.2870 (2.1926)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [236]  [210/312]  eta: 0:00:49  lr: 0.000485  min_lr: 0.000485  loss: 2.2870 (2.1932)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [236]  [220/312]  eta: 0:00:44  lr: 0.000484  min_lr: 0.000484  loss: 2.2789 (2.1976)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [236]  [230/312]  eta: 0:00:39  lr: 0.000484  min_lr: 0.000484  loss: 2.1035 (2.1926)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [236]  [240/312]  eta: 0:00:34  lr: 0.000483  min_lr: 0.000483  loss: 2.1130 (2.1862)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0003  max mem: 42573
Epoch: [236]  [250/312]  eta: 0:00:29  lr: 0.000483  min_lr: 0.000483  loss: 2.0852 (2.1798)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [236]  [260/312]  eta: 0:00:24  lr: 0.000482  min_lr: 0.000482  loss: 2.0852 (2.1790)  weight_decay: 0.0500 (0.0500)  time: 0.4332  data: 0.0004  max mem: 42573
Epoch: [236]  [270/312]  eta: 0:00:20  lr: 0.000482  min_lr: 0.000482  loss: 2.4083 (2.1914)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [236]  [280/312]  eta: 0:00:15  lr: 0.000482  min_lr: 0.000482  loss: 2.3776 (2.1965)  weight_decay: 0.0500 (0.0500)  time: 0.4350  data: 0.0010  max mem: 42573
Epoch: [236]  [290/312]  eta: 0:00:10  lr: 0.000481  min_lr: 0.000481  loss: 2.2052 (2.1877)  weight_decay: 0.0500 (0.0500)  time: 0.4341  data: 0.0008  max mem: 42573
Epoch: [236]  [300/312]  eta: 0:00:05  lr: 0.000481  min_lr: 0.000481  loss: 2.1653 (2.1889)  weight_decay: 0.0500 (0.0500)  time: 0.4321  data: 0.0001  max mem: 42573
Epoch: [236]  [310/312]  eta: 0:00:00  lr: 0.000480  min_lr: 0.000480  loss: 2.2631 (2.1872)  weight_decay: 0.0500 (0.0500)  time: 0.4321  data: 0.0001  max mem: 42573
Epoch: [236]  [311/312]  eta: 0:00:00  lr: 0.000480  min_lr: 0.000480  loss: 2.2813 (2.1896)  weight_decay: 0.0500 (0.0500)  time: 0.4321  data: 0.0001  max mem: 42573
Epoch: [236] Total time: 0:02:27 (0.4737 s / it)
Averaged stats: lr: 0.000480  min_lr: 0.000480  loss: 2.2813 (2.1521)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:00:38  loss: 0.6397 (0.6397)  acc1: 83.0729 (83.0729)  acc5: 95.8333 (95.8333)  time: 4.3317  data: 4.2235  max mem: 42573
Test:  [8/9]  eta: 0:00:00  loss: 0.7982 (0.8229)  acc1: 80.2083 (78.1760)  acc5: 95.5729 (94.4320)  time: 0.5570  data: 0.4693  max mem: 42573
Test: Total time: 0:00:05 (0.5686 s / it)
* Acc@1 79.006 Acc@5 94.442 loss 0.807
Accuracy of the model on the 50000 test images: 79.0%
Max accuracy: 79.15%
Epoch: [237]  [  0/312]  eta: 0:52:35  lr: 0.000480  min_lr: 0.000480  loss: 2.1097 (2.1097)  weight_decay: 0.0500 (0.0500)  time: 10.1138  data: 8.7084  max mem: 42573
Epoch: [237]  [ 10/312]  eta: 0:07:44  lr: 0.000480  min_lr: 0.000480  loss: 2.4931 (2.3677)  weight_decay: 0.0500 (0.0500)  time: 1.5368  data: 0.7920  max mem: 42573
Epoch: [237]  [ 20/312]  eta: 0:04:55  lr: 0.000479  min_lr: 0.000479  loss: 2.1196 (2.1290)  weight_decay: 0.0500 (0.0500)  time: 0.5564  data: 0.0004  max mem: 42573
Epoch: [237]  [ 30/312]  eta: 0:03:52  lr: 0.000479  min_lr: 0.000479  loss: 1.9547 (2.1228)  weight_decay: 0.0500 (0.0500)  time: 0.4343  data: 0.0004  max mem: 42573
Epoch: [237]  [ 40/312]  eta: 0:03:18  lr: 0.000478  min_lr: 0.000478  loss: 2.1282 (2.1405)  weight_decay: 0.0500 (0.0500)  time: 0.4343  data: 0.0004  max mem: 42573
Epoch: [237]  [ 50/312]  eta: 0:02:56  lr: 0.000478  min_lr: 0.000478  loss: 2.1545 (2.1732)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [237]  [ 60/312]  eta: 0:02:39  lr: 0.000477  min_lr: 0.000477  loss: 2.2824 (2.1867)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [237]  [ 70/312]  eta: 0:02:26  lr: 0.000477  min_lr: 0.000477  loss: 2.2509 (2.1834)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [237]  [ 80/312]  eta: 0:02:15  lr: 0.000476  min_lr: 0.000476  loss: 2.1374 (2.1569)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0004  max mem: 42573
Epoch: [237]  [ 90/312]  eta: 0:02:05  lr: 0.000476  min_lr: 0.000476  loss: 1.8193 (2.1295)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [237]  [100/312]  eta: 0:01:57  lr: 0.000475  min_lr: 0.000475  loss: 2.1097 (2.1365)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [237]  [110/312]  eta: 0:01:49  lr: 0.000475  min_lr: 0.000475  loss: 2.0656 (2.1191)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [237]  [120/312]  eta: 0:01:42  lr: 0.000474  min_lr: 0.000474  loss: 1.9385 (2.1281)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [237]  [130/312]  eta: 0:01:35  lr: 0.000474  min_lr: 0.000474  loss: 2.0616 (2.1230)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0003  max mem: 42573
Epoch: [237]  [140/312]  eta: 0:01:29  lr: 0.000474  min_lr: 0.000474  loss: 2.0533 (2.1224)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [237]  [150/312]  eta: 0:01:23  lr: 0.000473  min_lr: 0.000473  loss: 2.0701 (2.1225)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0006  max mem: 42573
Epoch: [237]  [160/312]  eta: 0:01:17  lr: 0.000473  min_lr: 0.000473  loss: 2.1782 (2.1248)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0006  max mem: 42573
Epoch: [237]  [170/312]  eta: 0:01:11  lr: 0.000472  min_lr: 0.000472  loss: 2.0784 (2.1205)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [237]  [180/312]  eta: 0:01:06  lr: 0.000472  min_lr: 0.000472  loss: 2.2668 (2.1328)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [237]  [190/312]  eta: 0:01:00  lr: 0.000471  min_lr: 0.000471  loss: 2.2668 (2.1339)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [237]  [200/312]  eta: 0:00:55  lr: 0.000471  min_lr: 0.000471  loss: 2.0959 (2.1269)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [237]  [210/312]  eta: 0:00:50  lr: 0.000470  min_lr: 0.000470  loss: 2.2325 (2.1368)  weight_decay: 0.0500 (0.0500)  time: 0.4358  data: 0.0004  max mem: 42573
Epoch: [237]  [220/312]  eta: 0:00:44  lr: 0.000470  min_lr: 0.000470  loss: 2.2614 (2.1377)  weight_decay: 0.0500 (0.0500)  time: 0.4357  data: 0.0004  max mem: 42573
Epoch: [237]  [230/312]  eta: 0:00:39  lr: 0.000469  min_lr: 0.000469  loss: 2.1258 (2.1367)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [237]  [240/312]  eta: 0:00:34  lr: 0.000469  min_lr: 0.000469  loss: 1.9842 (2.1371)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [237]  [250/312]  eta: 0:00:29  lr: 0.000468  min_lr: 0.000468  loss: 1.9845 (2.1339)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [237]  [260/312]  eta: 0:00:24  lr: 0.000468  min_lr: 0.000468  loss: 2.2776 (2.1376)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [237]  [270/312]  eta: 0:00:20  lr: 0.000468  min_lr: 0.000468  loss: 1.8847 (2.1243)  weight_decay: 0.0500 (0.0500)  time: 0.4371  data: 0.0004  max mem: 42573
Epoch: [237]  [280/312]  eta: 0:00:15  lr: 0.000467  min_lr: 0.000467  loss: 1.8784 (2.1273)  weight_decay: 0.0500 (0.0500)  time: 0.4380  data: 0.0009  max mem: 42573
Epoch: [237]  [290/312]  eta: 0:00:10  lr: 0.000467  min_lr: 0.000467  loss: 2.2414 (2.1300)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0008  max mem: 42573
Epoch: [237]  [300/312]  eta: 0:00:05  lr: 0.000466  min_lr: 0.000466  loss: 2.1506 (2.1238)  weight_decay: 0.0500 (0.0500)  time: 0.4322  data: 0.0001  max mem: 42573
Epoch: [237]  [310/312]  eta: 0:00:00  lr: 0.000466  min_lr: 0.000466  loss: 2.1586 (2.1245)  weight_decay: 0.0500 (0.0500)  time: 0.4321  data: 0.0001  max mem: 42573
Epoch: [237]  [311/312]  eta: 0:00:00  lr: 0.000466  min_lr: 0.000466  loss: 2.1586 (2.1251)  weight_decay: 0.0500 (0.0500)  time: 0.4321  data: 0.0001  max mem: 42573
Epoch: [237] Total time: 0:02:28 (0.4760 s / it)
Averaged stats: lr: 0.000466  min_lr: 0.000466  loss: 2.1586 (2.1565)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:00:40  loss: 0.5993 (0.5993)  acc1: 83.8542 (83.8542)  acc5: 95.8333 (95.8333)  time: 4.5408  data: 4.4325  max mem: 42573
Test:  [8/9]  eta: 0:00:00  loss: 0.7982 (0.8165)  acc1: 80.7292 (78.8800)  acc5: 95.3125 (94.5600)  time: 0.5820  data: 0.4926  max mem: 42573
Test: Total time: 0:00:05 (0.5906 s / it)
* Acc@1 79.148 Acc@5 94.412 loss 0.806
Accuracy of the model on the 50000 test images: 79.1%
Max accuracy: 79.15%
Epoch: [238]  [  0/312]  eta: 0:52:25  lr: 0.000466  min_lr: 0.000466  loss: 2.4491 (2.4491)  weight_decay: 0.0500 (0.0500)  time: 10.0818  data: 6.3106  max mem: 42573
Epoch: [238]  [ 10/312]  eta: 0:07:36  lr: 0.000465  min_lr: 0.000465  loss: 2.0957 (2.1029)  weight_decay: 0.0500 (0.0500)  time: 1.5111  data: 0.6370  max mem: 42573
Epoch: [238]  [ 20/312]  eta: 0:04:51  lr: 0.000465  min_lr: 0.000465  loss: 2.0760 (2.0846)  weight_decay: 0.0500 (0.0500)  time: 0.5446  data: 0.0350  max mem: 42573
Epoch: [238]  [ 30/312]  eta: 0:03:50  lr: 0.000464  min_lr: 0.000464  loss: 2.3252 (2.1962)  weight_decay: 0.0500 (0.0500)  time: 0.4343  data: 0.0004  max mem: 42573
Epoch: [238]  [ 40/312]  eta: 0:03:17  lr: 0.000464  min_lr: 0.000464  loss: 2.3117 (2.1667)  weight_decay: 0.0500 (0.0500)  time: 0.4386  data: 0.0004  max mem: 42573
Epoch: [238]  [ 50/312]  eta: 0:02:55  lr: 0.000463  min_lr: 0.000463  loss: 2.0543 (2.1397)  weight_decay: 0.0500 (0.0500)  time: 0.4400  data: 0.0004  max mem: 42573
Epoch: [238]  [ 60/312]  eta: 0:02:38  lr: 0.000463  min_lr: 0.000463  loss: 2.1480 (2.1393)  weight_decay: 0.0500 (0.0500)  time: 0.4348  data: 0.0004  max mem: 42573
Epoch: [238]  [ 70/312]  eta: 0:02:25  lr: 0.000462  min_lr: 0.000462  loss: 2.2688 (2.1479)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [238]  [ 80/312]  eta: 0:02:14  lr: 0.000462  min_lr: 0.000462  loss: 2.3387 (2.1756)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [238]  [ 90/312]  eta: 0:02:05  lr: 0.000461  min_lr: 0.000461  loss: 2.2460 (2.1702)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [238]  [100/312]  eta: 0:01:57  lr: 0.000461  min_lr: 0.000461  loss: 2.1675 (2.1757)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [238]  [110/312]  eta: 0:01:49  lr: 0.000461  min_lr: 0.000461  loss: 2.2329 (2.1658)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [238]  [120/312]  eta: 0:01:42  lr: 0.000460  min_lr: 0.000460  loss: 2.2013 (2.1607)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [238]  [130/312]  eta: 0:01:35  lr: 0.000460  min_lr: 0.000460  loss: 2.2598 (2.1692)  weight_decay: 0.0500 (0.0500)  time: 0.4418  data: 0.0004  max mem: 42573
Epoch: [238]  [140/312]  eta: 0:01:29  lr: 0.000459  min_lr: 0.000459  loss: 2.2643 (2.1685)  weight_decay: 0.0500 (0.0500)  time: 0.4416  data: 0.0004  max mem: 42573
Epoch: [238]  [150/312]  eta: 0:01:23  lr: 0.000459  min_lr: 0.000459  loss: 2.0274 (2.1700)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [238]  [160/312]  eta: 0:01:17  lr: 0.000458  min_lr: 0.000458  loss: 2.0274 (2.1644)  weight_decay: 0.0500 (0.0500)  time: 0.4331  data: 0.0003  max mem: 42573
Epoch: [238]  [170/312]  eta: 0:01:11  lr: 0.000458  min_lr: 0.000458  loss: 2.1258 (2.1600)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [238]  [180/312]  eta: 0:01:06  lr: 0.000457  min_lr: 0.000457  loss: 2.2736 (2.1643)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [238]  [190/312]  eta: 0:01:00  lr: 0.000457  min_lr: 0.000457  loss: 2.1719 (2.1510)  weight_decay: 0.0500 (0.0500)  time: 0.4331  data: 0.0004  max mem: 42573
Epoch: [238]  [200/312]  eta: 0:00:55  lr: 0.000456  min_lr: 0.000456  loss: 2.1425 (2.1521)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [238]  [210/312]  eta: 0:00:50  lr: 0.000456  min_lr: 0.000456  loss: 2.2607 (2.1519)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [238]  [220/312]  eta: 0:00:44  lr: 0.000456  min_lr: 0.000456  loss: 2.0321 (2.1435)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [238]  [230/312]  eta: 0:00:39  lr: 0.000455  min_lr: 0.000455  loss: 2.2006 (2.1481)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [238]  [240/312]  eta: 0:00:34  lr: 0.000455  min_lr: 0.000455  loss: 2.3535 (2.1512)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [238]  [250/312]  eta: 0:00:29  lr: 0.000454  min_lr: 0.000454  loss: 2.2482 (2.1505)  weight_decay: 0.0500 (0.0500)  time: 0.4332  data: 0.0004  max mem: 42573
Epoch: [238]  [260/312]  eta: 0:00:24  lr: 0.000454  min_lr: 0.000454  loss: 2.2482 (2.1559)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [238]  [270/312]  eta: 0:00:20  lr: 0.000453  min_lr: 0.000453  loss: 2.2601 (2.1570)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [238]  [280/312]  eta: 0:00:15  lr: 0.000453  min_lr: 0.000453  loss: 2.2336 (2.1564)  weight_decay: 0.0500 (0.0500)  time: 0.4342  data: 0.0009  max mem: 42573
Epoch: [238]  [290/312]  eta: 0:00:10  lr: 0.000452  min_lr: 0.000452  loss: 2.1479 (2.1531)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0008  max mem: 42573
Epoch: [238]  [300/312]  eta: 0:00:05  lr: 0.000452  min_lr: 0.000452  loss: 2.1879 (2.1549)  weight_decay: 0.0500 (0.0500)  time: 0.4321  data: 0.0001  max mem: 42573
Epoch: [238]  [310/312]  eta: 0:00:00  lr: 0.000451  min_lr: 0.000451  loss: 2.2240 (2.1507)  weight_decay: 0.0500 (0.0500)  time: 0.4321  data: 0.0001  max mem: 42573
Epoch: [238]  [311/312]  eta: 0:00:00  lr: 0.000451  min_lr: 0.000451  loss: 2.2240 (2.1493)  weight_decay: 0.0500 (0.0500)  time: 0.4322  data: 0.0001  max mem: 42573
Epoch: [238] Total time: 0:02:28 (0.4753 s / it)
Averaged stats: lr: 0.000451  min_lr: 0.000451  loss: 2.2240 (2.1593)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:00:41  loss: 0.5758 (0.5758)  acc1: 86.4583 (86.4583)  acc5: 96.3542 (96.3542)  time: 4.5792  data: 4.4709  max mem: 42573
Test:  [8/9]  eta: 0:00:00  loss: 0.8203 (0.8117)  acc1: 78.3854 (78.3680)  acc5: 95.0521 (94.7200)  time: 0.5847  data: 0.4968  max mem: 42573
Test: Total time: 0:00:05 (0.6006 s / it)
* Acc@1 79.216 Acc@5 94.554 loss 0.793
Accuracy of the model on the 50000 test images: 79.2%
Max accuracy: 79.22%
Epoch: [239]  [  0/312]  eta: 0:49:52  lr: 0.000451  min_lr: 0.000451  loss: 1.8017 (1.8017)  weight_decay: 0.0500 (0.0500)  time: 9.5913  data: 7.2027  max mem: 42573
Epoch: [239]  [ 10/312]  eta: 0:07:13  lr: 0.000451  min_lr: 0.000451  loss: 2.0087 (2.0203)  weight_decay: 0.0500 (0.0500)  time: 1.4356  data: 0.6633  max mem: 42573
Epoch: [239]  [ 20/312]  eta: 0:04:39  lr: 0.000450  min_lr: 0.000450  loss: 2.0500 (2.0504)  weight_decay: 0.0500 (0.0500)  time: 0.5266  data: 0.0049  max mem: 42573
Epoch: [239]  [ 30/312]  eta: 0:03:42  lr: 0.000450  min_lr: 0.000450  loss: 2.1327 (2.1318)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [239]  [ 40/312]  eta: 0:03:10  lr: 0.000449  min_lr: 0.000449  loss: 2.3330 (2.1294)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [239]  [ 50/312]  eta: 0:02:50  lr: 0.000449  min_lr: 0.000449  loss: 2.2536 (2.1522)  weight_decay: 0.0500 (0.0500)  time: 0.4332  data: 0.0004  max mem: 42573
Epoch: [239]  [ 60/312]  eta: 0:02:34  lr: 0.000449  min_lr: 0.000449  loss: 2.3671 (2.1736)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [239]  [ 70/312]  eta: 0:02:22  lr: 0.000448  min_lr: 0.000448  loss: 2.1488 (2.1397)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [239]  [ 80/312]  eta: 0:02:12  lr: 0.000448  min_lr: 0.000448  loss: 2.1540 (2.1482)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [239]  [ 90/312]  eta: 0:02:03  lr: 0.000447  min_lr: 0.000447  loss: 2.2959 (2.1720)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [239]  [100/312]  eta: 0:01:55  lr: 0.000447  min_lr: 0.000447  loss: 2.3925 (2.1819)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [239]  [110/312]  eta: 0:01:47  lr: 0.000446  min_lr: 0.000446  loss: 2.2352 (2.1812)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [239]  [120/312]  eta: 0:01:40  lr: 0.000446  min_lr: 0.000446  loss: 2.1569 (2.1705)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [239]  [130/312]  eta: 0:01:34  lr: 0.000445  min_lr: 0.000445  loss: 2.1167 (2.1752)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0003  max mem: 42573
Epoch: [239]  [140/312]  eta: 0:01:28  lr: 0.000445  min_lr: 0.000445  loss: 2.2050 (2.1727)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0003  max mem: 42573
Epoch: [239]  [150/312]  eta: 0:01:22  lr: 0.000445  min_lr: 0.000445  loss: 2.3000 (2.1780)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [239]  [160/312]  eta: 0:01:16  lr: 0.000444  min_lr: 0.000444  loss: 2.2637 (2.1698)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [239]  [170/312]  eta: 0:01:10  lr: 0.000444  min_lr: 0.000444  loss: 2.0782 (2.1684)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [239]  [180/312]  eta: 0:01:05  lr: 0.000443  min_lr: 0.000443  loss: 2.3030 (2.1732)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [239]  [190/312]  eta: 0:00:59  lr: 0.000443  min_lr: 0.000443  loss: 2.2958 (2.1692)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [239]  [200/312]  eta: 0:00:54  lr: 0.000442  min_lr: 0.000442  loss: 2.1283 (2.1653)  weight_decay: 0.0500 (0.0500)  time: 0.4332  data: 0.0004  max mem: 42573
Epoch: [239]  [210/312]  eta: 0:00:49  lr: 0.000442  min_lr: 0.000442  loss: 2.2240 (2.1694)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0003  max mem: 42573
Epoch: [239]  [220/312]  eta: 0:00:44  lr: 0.000441  min_lr: 0.000441  loss: 2.2311 (2.1658)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [239]  [230/312]  eta: 0:00:39  lr: 0.000441  min_lr: 0.000441  loss: 2.2739 (2.1740)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [239]  [240/312]  eta: 0:00:34  lr: 0.000440  min_lr: 0.000440  loss: 2.2748 (2.1708)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [239]  [250/312]  eta: 0:00:29  lr: 0.000440  min_lr: 0.000440  loss: 2.1454 (2.1672)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [239]  [260/312]  eta: 0:00:24  lr: 0.000440  min_lr: 0.000440  loss: 2.2022 (2.1640)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [239]  [270/312]  eta: 0:00:19  lr: 0.000439  min_lr: 0.000439  loss: 1.9700 (2.1568)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [239]  [280/312]  eta: 0:00:15  lr: 0.000439  min_lr: 0.000439  loss: 2.1121 (2.1592)  weight_decay: 0.0500 (0.0500)  time: 0.4343  data: 0.0017  max mem: 42573
Epoch: [239]  [290/312]  eta: 0:00:10  lr: 0.000438  min_lr: 0.000438  loss: 2.1578 (2.1544)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0016  max mem: 42573
Epoch: [239]  [300/312]  eta: 0:00:05  lr: 0.000438  min_lr: 0.000438  loss: 2.1567 (2.1555)  weight_decay: 0.0500 (0.0500)  time: 0.4322  data: 0.0001  max mem: 42573
Epoch: [239]  [310/312]  eta: 0:00:00  lr: 0.000437  min_lr: 0.000437  loss: 2.2295 (2.1594)  weight_decay: 0.0500 (0.0500)  time: 0.4320  data: 0.0001  max mem: 42573
Epoch: [239]  [311/312]  eta: 0:00:00  lr: 0.000437  min_lr: 0.000437  loss: 2.2295 (2.1605)  weight_decay: 0.0500 (0.0500)  time: 0.4319  data: 0.0001  max mem: 42573
Epoch: [239] Total time: 0:02:27 (0.4719 s / it)
Averaged stats: lr: 0.000437  min_lr: 0.000437  loss: 2.2295 (2.1361)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:00:40  loss: 0.5944 (0.5944)  acc1: 85.6771 (85.6771)  acc5: 95.5729 (95.5729)  time: 4.4651  data: 4.3573  max mem: 42573
Test:  [8/9]  eta: 0:00:00  loss: 0.8370 (0.8192)  acc1: 78.1250 (78.0160)  acc5: 95.0521 (94.4000)  time: 0.5723  data: 0.4842  max mem: 42573
Test: Total time: 0:00:05 (0.5800 s / it)
* Acc@1 78.980 Acc@5 94.448 loss 0.804
Accuracy of the model on the 50000 test images: 79.0%
Max accuracy: 79.22%
Epoch: [240]  [  0/312]  eta: 0:53:54  lr: 0.000437  min_lr: 0.000437  loss: 2.3158 (2.3158)  weight_decay: 0.0500 (0.0500)  time: 10.3676  data: 8.0822  max mem: 42573
Epoch: [240]  [ 10/312]  eta: 0:07:27  lr: 0.000437  min_lr: 0.000437  loss: 2.2089 (2.0462)  weight_decay: 0.0500 (0.0500)  time: 1.4830  data: 0.7441  max mem: 42573
Epoch: [240]  [ 20/312]  eta: 0:04:47  lr: 0.000436  min_lr: 0.000436  loss: 2.0807 (2.0621)  weight_decay: 0.0500 (0.0500)  time: 0.5158  data: 0.0053  max mem: 42573
Epoch: [240]  [ 30/312]  eta: 0:03:47  lr: 0.000436  min_lr: 0.000436  loss: 2.1538 (2.0644)  weight_decay: 0.0500 (0.0500)  time: 0.4356  data: 0.0004  max mem: 42573
Epoch: [240]  [ 40/312]  eta: 0:03:14  lr: 0.000435  min_lr: 0.000435  loss: 2.1538 (2.0839)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [240]  [ 50/312]  eta: 0:02:53  lr: 0.000435  min_lr: 0.000435  loss: 2.0718 (2.0516)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [240]  [ 60/312]  eta: 0:02:37  lr: 0.000435  min_lr: 0.000435  loss: 2.1902 (2.0864)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [240]  [ 70/312]  eta: 0:02:24  lr: 0.000434  min_lr: 0.000434  loss: 2.3158 (2.1078)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [240]  [ 80/312]  eta: 0:02:13  lr: 0.000434  min_lr: 0.000434  loss: 2.3155 (2.1182)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [240]  [ 90/312]  eta: 0:02:04  lr: 0.000433  min_lr: 0.000433  loss: 2.2048 (2.1198)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [240]  [100/312]  eta: 0:01:56  lr: 0.000433  min_lr: 0.000433  loss: 2.1669 (2.1152)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [240]  [110/312]  eta: 0:01:48  lr: 0.000432  min_lr: 0.000432  loss: 2.2691 (2.1326)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [240]  [120/312]  eta: 0:01:41  lr: 0.000432  min_lr: 0.000432  loss: 2.2749 (2.1411)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [240]  [130/312]  eta: 0:01:35  lr: 0.000431  min_lr: 0.000431  loss: 2.1815 (2.1357)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0005  max mem: 42573
Epoch: [240]  [140/312]  eta: 0:01:28  lr: 0.000431  min_lr: 0.000431  loss: 2.2699 (2.1435)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [240]  [150/312]  eta: 0:01:22  lr: 0.000431  min_lr: 0.000431  loss: 2.2432 (2.1447)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [240]  [160/312]  eta: 0:01:16  lr: 0.000430  min_lr: 0.000430  loss: 2.1281 (2.1419)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [240]  [170/312]  eta: 0:01:11  lr: 0.000430  min_lr: 0.000430  loss: 2.1445 (2.1412)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [240]  [180/312]  eta: 0:01:05  lr: 0.000429  min_lr: 0.000429  loss: 2.1450 (2.1402)  weight_decay: 0.0500 (0.0500)  time: 0.4398  data: 0.0004  max mem: 42573
Epoch: [240]  [190/312]  eta: 0:01:00  lr: 0.000429  min_lr: 0.000429  loss: 2.3671 (2.1522)  weight_decay: 0.0500 (0.0500)  time: 0.4395  data: 0.0004  max mem: 42573
Epoch: [240]  [200/312]  eta: 0:00:55  lr: 0.000428  min_lr: 0.000428  loss: 2.2944 (2.1529)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [240]  [210/312]  eta: 0:00:49  lr: 0.000428  min_lr: 0.000428  loss: 2.0287 (2.1502)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [240]  [220/312]  eta: 0:00:44  lr: 0.000427  min_lr: 0.000427  loss: 2.1978 (2.1525)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [240]  [230/312]  eta: 0:00:39  lr: 0.000427  min_lr: 0.000427  loss: 2.2470 (2.1586)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [240]  [240/312]  eta: 0:00:34  lr: 0.000427  min_lr: 0.000427  loss: 2.2545 (2.1561)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [240]  [250/312]  eta: 0:00:29  lr: 0.000426  min_lr: 0.000426  loss: 2.2545 (2.1589)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [240]  [260/312]  eta: 0:00:24  lr: 0.000426  min_lr: 0.000426  loss: 2.3766 (2.1642)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [240]  [270/312]  eta: 0:00:20  lr: 0.000425  min_lr: 0.000425  loss: 2.3884 (2.1724)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0005  max mem: 42573
Epoch: [240]  [280/312]  eta: 0:00:15  lr: 0.000425  min_lr: 0.000425  loss: 2.3540 (2.1780)  weight_decay: 0.0500 (0.0500)  time: 0.4342  data: 0.0017  max mem: 42573
Epoch: [240]  [290/312]  eta: 0:00:10  lr: 0.000424  min_lr: 0.000424  loss: 2.2017 (2.1712)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0015  max mem: 42573
Epoch: [240]  [300/312]  eta: 0:00:05  lr: 0.000424  min_lr: 0.000424  loss: 2.0350 (2.1677)  weight_decay: 0.0500 (0.0500)  time: 0.4321  data: 0.0001  max mem: 42573
Epoch: [240]  [310/312]  eta: 0:00:00  lr: 0.000423  min_lr: 0.000423  loss: 2.2210 (2.1704)  weight_decay: 0.0500 (0.0500)  time: 0.4320  data: 0.0001  max mem: 42573
Epoch: [240]  [311/312]  eta: 0:00:00  lr: 0.000423  min_lr: 0.000423  loss: 2.1164 (2.1694)  weight_decay: 0.0500 (0.0500)  time: 0.4321  data: 0.0001  max mem: 42573
Epoch: [240] Total time: 0:02:27 (0.4742 s / it)
Averaged stats: lr: 0.000423  min_lr: 0.000423  loss: 2.1164 (2.1497)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:00:39  loss: 0.6026 (0.6026)  acc1: 84.6354 (84.6354)  acc5: 95.8333 (95.8333)  time: 4.4093  data: 4.3016  max mem: 42573
Test:  [8/9]  eta: 0:00:00  loss: 0.8287 (0.8065)  acc1: 79.9479 (78.9120)  acc5: 95.5729 (94.7520)  time: 0.5846  data: 0.4952  max mem: 42573
Test: Total time: 0:00:05 (0.5933 s / it)
* Acc@1 79.392 Acc@5 94.530 loss 0.795
Accuracy of the model on the 50000 test images: 79.4%
Max accuracy: 79.39%
Epoch: [241]  [  0/312]  eta: 0:51:44  lr: 0.000423  min_lr: 0.000423  loss: 2.6675 (2.6675)  weight_decay: 0.0500 (0.0500)  time: 9.9514  data: 8.9768  max mem: 42573
Epoch: [241]  [ 10/312]  eta: 0:07:17  lr: 0.000423  min_lr: 0.000423  loss: 2.3880 (2.2861)  weight_decay: 0.0500 (0.0500)  time: 1.4494  data: 0.8165  max mem: 42573
Epoch: [241]  [ 20/312]  eta: 0:04:42  lr: 0.000422  min_lr: 0.000422  loss: 2.2846 (2.1413)  weight_decay: 0.0500 (0.0500)  time: 0.5167  data: 0.0004  max mem: 42573
Epoch: [241]  [ 30/312]  eta: 0:03:43  lr: 0.000422  min_lr: 0.000422  loss: 2.0398 (2.1394)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [241]  [ 40/312]  eta: 0:03:12  lr: 0.000422  min_lr: 0.000422  loss: 2.0398 (2.0827)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [241]  [ 50/312]  eta: 0:02:50  lr: 0.000421  min_lr: 0.000421  loss: 1.9840 (2.0700)  weight_decay: 0.0500 (0.0500)  time: 0.4332  data: 0.0004  max mem: 42573
Epoch: [241]  [ 60/312]  eta: 0:02:35  lr: 0.000421  min_lr: 0.000421  loss: 2.1858 (2.0979)  weight_decay: 0.0500 (0.0500)  time: 0.4332  data: 0.0004  max mem: 42573
Epoch: [241]  [ 70/312]  eta: 0:02:23  lr: 0.000420  min_lr: 0.000420  loss: 2.2109 (2.1020)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [241]  [ 80/312]  eta: 0:02:12  lr: 0.000420  min_lr: 0.000420  loss: 1.9979 (2.0816)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [241]  [ 90/312]  eta: 0:02:03  lr: 0.000419  min_lr: 0.000419  loss: 2.0058 (2.0882)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [241]  [100/312]  eta: 0:01:55  lr: 0.000419  min_lr: 0.000419  loss: 2.1570 (2.0962)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [241]  [110/312]  eta: 0:01:47  lr: 0.000418  min_lr: 0.000418  loss: 2.2869 (2.0987)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [241]  [120/312]  eta: 0:01:40  lr: 0.000418  min_lr: 0.000418  loss: 2.3796 (2.1207)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [241]  [130/312]  eta: 0:01:34  lr: 0.000418  min_lr: 0.000418  loss: 1.9670 (2.1103)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [241]  [140/312]  eta: 0:01:28  lr: 0.000417  min_lr: 0.000417  loss: 1.9420 (2.1120)  weight_decay: 0.0500 (0.0500)  time: 0.4331  data: 0.0004  max mem: 42573
Epoch: [241]  [150/312]  eta: 0:01:22  lr: 0.000417  min_lr: 0.000417  loss: 2.1562 (2.1187)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [241]  [160/312]  eta: 0:01:16  lr: 0.000416  min_lr: 0.000416  loss: 2.1165 (2.1162)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [241]  [170/312]  eta: 0:01:10  lr: 0.000416  min_lr: 0.000416  loss: 2.1910 (2.1182)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [241]  [180/312]  eta: 0:01:05  lr: 0.000415  min_lr: 0.000415  loss: 2.0301 (2.1069)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [241]  [190/312]  eta: 0:01:00  lr: 0.000415  min_lr: 0.000415  loss: 2.0301 (2.1070)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [241]  [200/312]  eta: 0:00:54  lr: 0.000415  min_lr: 0.000415  loss: 2.1877 (2.1099)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [241]  [210/312]  eta: 0:00:49  lr: 0.000414  min_lr: 0.000414  loss: 2.0337 (2.1005)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [241]  [220/312]  eta: 0:00:44  lr: 0.000414  min_lr: 0.000414  loss: 2.1547 (2.1047)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [241]  [230/312]  eta: 0:00:39  lr: 0.000413  min_lr: 0.000413  loss: 2.2303 (2.1039)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [241]  [240/312]  eta: 0:00:34  lr: 0.000413  min_lr: 0.000413  loss: 2.1865 (2.1101)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [241]  [250/312]  eta: 0:00:29  lr: 0.000412  min_lr: 0.000412  loss: 2.1343 (2.1066)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0003  max mem: 42573
Epoch: [241]  [260/312]  eta: 0:00:24  lr: 0.000412  min_lr: 0.000412  loss: 2.1153 (2.1124)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [241]  [270/312]  eta: 0:00:19  lr: 0.000411  min_lr: 0.000411  loss: 2.3000 (2.1192)  weight_decay: 0.0500 (0.0500)  time: 0.4421  data: 0.0004  max mem: 42573
Epoch: [241]  [280/312]  eta: 0:00:15  lr: 0.000411  min_lr: 0.000411  loss: 2.3000 (2.1175)  weight_decay: 0.0500 (0.0500)  time: 0.4426  data: 0.0011  max mem: 42573
Epoch: [241]  [290/312]  eta: 0:00:10  lr: 0.000411  min_lr: 0.000411  loss: 2.0797 (2.1150)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0010  max mem: 42573
Epoch: [241]  [300/312]  eta: 0:00:05  lr: 0.000410  min_lr: 0.000410  loss: 2.1140 (2.1168)  weight_decay: 0.0500 (0.0500)  time: 0.4321  data: 0.0001  max mem: 42573
Epoch: [241]  [310/312]  eta: 0:00:00  lr: 0.000410  min_lr: 0.000410  loss: 2.2194 (2.1233)  weight_decay: 0.0500 (0.0500)  time: 0.4321  data: 0.0001  max mem: 42573
Epoch: [241]  [311/312]  eta: 0:00:00  lr: 0.000410  min_lr: 0.000410  loss: 2.1731 (2.1213)  weight_decay: 0.0500 (0.0500)  time: 0.4321  data: 0.0001  max mem: 42573
Epoch: [241] Total time: 0:02:27 (0.4727 s / it)
Averaged stats: lr: 0.000410  min_lr: 0.000410  loss: 2.1731 (2.1407)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:00:38  loss: 0.6135 (0.6135)  acc1: 86.1979 (86.1979)  acc5: 96.3542 (96.3542)  time: 4.3179  data: 4.2099  max mem: 42573
Test:  [8/9]  eta: 0:00:00  loss: 0.8491 (0.8239)  acc1: 79.6875 (78.9440)  acc5: 94.5312 (94.5280)  time: 0.5563  data: 0.4678  max mem: 42573
Test: Total time: 0:00:05 (0.5643 s / it)
* Acc@1 78.998 Acc@5 94.466 loss 0.815
Accuracy of the model on the 50000 test images: 79.0%
Max accuracy: 79.39%
Epoch: [242]  [  0/312]  eta: 0:52:39  lr: 0.000410  min_lr: 0.000410  loss: 1.5814 (1.5814)  weight_decay: 0.0500 (0.0500)  time: 10.1258  data: 7.3322  max mem: 42573
Epoch: [242]  [ 10/312]  eta: 0:07:51  lr: 0.000409  min_lr: 0.000409  loss: 1.9522 (2.0029)  weight_decay: 0.0500 (0.0500)  time: 1.5625  data: 0.7003  max mem: 42573
Epoch: [242]  [ 20/312]  eta: 0:04:59  lr: 0.000409  min_lr: 0.000409  loss: 2.0674 (2.0726)  weight_decay: 0.0500 (0.0500)  time: 0.5695  data: 0.0187  max mem: 42573
Epoch: [242]  [ 30/312]  eta: 0:03:55  lr: 0.000408  min_lr: 0.000408  loss: 2.0674 (2.0622)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [242]  [ 40/312]  eta: 0:03:20  lr: 0.000408  min_lr: 0.000408  loss: 2.2740 (2.0837)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [242]  [ 50/312]  eta: 0:02:57  lr: 0.000407  min_lr: 0.000407  loss: 2.2740 (2.1107)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [242]  [ 60/312]  eta: 0:02:40  lr: 0.000407  min_lr: 0.000407  loss: 2.1923 (2.1138)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [242]  [ 70/312]  eta: 0:02:27  lr: 0.000407  min_lr: 0.000407  loss: 2.2178 (2.1329)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [242]  [ 80/312]  eta: 0:02:16  lr: 0.000406  min_lr: 0.000406  loss: 2.0503 (2.1138)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [242]  [ 90/312]  eta: 0:02:06  lr: 0.000406  min_lr: 0.000406  loss: 2.0412 (2.1227)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [242]  [100/312]  eta: 0:01:57  lr: 0.000405  min_lr: 0.000405  loss: 2.1948 (2.1158)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0003  max mem: 42573
Epoch: [242]  [110/312]  eta: 0:01:50  lr: 0.000405  min_lr: 0.000405  loss: 2.1948 (2.1247)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0003  max mem: 42573
Epoch: [242]  [120/312]  eta: 0:01:42  lr: 0.000404  min_lr: 0.000404  loss: 2.2382 (2.1290)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [242]  [130/312]  eta: 0:01:36  lr: 0.000404  min_lr: 0.000404  loss: 2.0179 (2.1183)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [242]  [140/312]  eta: 0:01:29  lr: 0.000404  min_lr: 0.000404  loss: 2.0179 (2.1156)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0003  max mem: 42573
Epoch: [242]  [150/312]  eta: 0:01:23  lr: 0.000403  min_lr: 0.000403  loss: 2.3013 (2.1247)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [242]  [160/312]  eta: 0:01:17  lr: 0.000403  min_lr: 0.000403  loss: 2.2624 (2.1268)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [242]  [170/312]  eta: 0:01:11  lr: 0.000402  min_lr: 0.000402  loss: 2.1099 (2.1253)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [242]  [180/312]  eta: 0:01:06  lr: 0.000402  min_lr: 0.000402  loss: 2.1434 (2.1236)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0003  max mem: 42573
Epoch: [242]  [190/312]  eta: 0:01:00  lr: 0.000401  min_lr: 0.000401  loss: 2.1581 (2.1262)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [242]  [200/312]  eta: 0:00:55  lr: 0.000401  min_lr: 0.000401  loss: 2.2389 (2.1314)  weight_decay: 0.0500 (0.0500)  time: 0.4382  data: 0.0004  max mem: 42573
Epoch: [242]  [210/312]  eta: 0:00:50  lr: 0.000401  min_lr: 0.000401  loss: 2.2834 (2.1336)  weight_decay: 0.0500 (0.0500)  time: 0.4384  data: 0.0003  max mem: 42573
Epoch: [242]  [220/312]  eta: 0:00:45  lr: 0.000400  min_lr: 0.000400  loss: 2.2957 (2.1402)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [242]  [230/312]  eta: 0:00:39  lr: 0.000400  min_lr: 0.000400  loss: 2.1706 (2.1349)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [242]  [240/312]  eta: 0:00:34  lr: 0.000399  min_lr: 0.000399  loss: 1.9846 (2.1265)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [242]  [250/312]  eta: 0:00:29  lr: 0.000399  min_lr: 0.000399  loss: 1.9251 (2.1199)  weight_decay: 0.0500 (0.0500)  time: 0.4332  data: 0.0004  max mem: 42573
Epoch: [242]  [260/312]  eta: 0:00:25  lr: 0.000398  min_lr: 0.000398  loss: 2.0368 (2.1218)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [242]  [270/312]  eta: 0:00:20  lr: 0.000398  min_lr: 0.000398  loss: 2.0368 (2.1157)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [242]  [280/312]  eta: 0:00:15  lr: 0.000398  min_lr: 0.000398  loss: 2.0058 (2.1127)  weight_decay: 0.0500 (0.0500)  time: 0.4343  data: 0.0009  max mem: 42573
Epoch: [242]  [290/312]  eta: 0:00:10  lr: 0.000397  min_lr: 0.000397  loss: 2.0160 (2.1118)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0008  max mem: 42573
Epoch: [242]  [300/312]  eta: 0:00:05  lr: 0.000397  min_lr: 0.000397  loss: 2.0131 (2.1092)  weight_decay: 0.0500 (0.0500)  time: 0.4323  data: 0.0001  max mem: 42573
Epoch: [242]  [310/312]  eta: 0:00:00  lr: 0.000396  min_lr: 0.000396  loss: 2.1117 (2.1117)  weight_decay: 0.0500 (0.0500)  time: 0.4322  data: 0.0001  max mem: 42573
Epoch: [242]  [311/312]  eta: 0:00:00  lr: 0.000396  min_lr: 0.000396  loss: 2.1117 (2.1115)  weight_decay: 0.0500 (0.0500)  time: 0.4322  data: 0.0001  max mem: 42573
Epoch: [242] Total time: 0:02:28 (0.4767 s / it)
Averaged stats: lr: 0.000396  min_lr: 0.000396  loss: 2.1117 (2.1275)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:00:41  loss: 0.6499 (0.6499)  acc1: 84.1146 (84.1146)  acc5: 95.3125 (95.3125)  time: 4.5751  data: 4.4673  max mem: 42573
Test:  [8/9]  eta: 0:00:00  loss: 0.8254 (0.7954)  acc1: 80.7292 (78.6880)  acc5: 95.3125 (94.5280)  time: 0.5849  data: 0.4964  max mem: 42573
Test: Total time: 0:00:05 (0.5928 s / it)
* Acc@1 79.276 Acc@5 94.624 loss 0.791
Accuracy of the model on the 50000 test images: 79.3%
Max accuracy: 79.39%
Epoch: [243]  [  0/312]  eta: 0:49:21  lr: 0.000396  min_lr: 0.000396  loss: 2.1940 (2.1940)  weight_decay: 0.0500 (0.0500)  time: 9.4935  data: 6.3960  max mem: 42573
Epoch: [243]  [ 10/312]  eta: 0:07:40  lr: 0.000396  min_lr: 0.000396  loss: 1.9316 (2.0086)  weight_decay: 0.0500 (0.0500)  time: 1.5246  data: 0.7843  max mem: 42573
Epoch: [243]  [ 20/312]  eta: 0:04:53  lr: 0.000395  min_lr: 0.000395  loss: 1.9656 (1.9908)  weight_decay: 0.0500 (0.0500)  time: 0.5803  data: 0.1117  max mem: 42573
Epoch: [243]  [ 30/312]  eta: 0:03:51  lr: 0.000395  min_lr: 0.000395  loss: 2.0059 (1.9776)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0003  max mem: 42573
Epoch: [243]  [ 40/312]  eta: 0:03:17  lr: 0.000394  min_lr: 0.000394  loss: 1.9235 (1.9810)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0003  max mem: 42573
Epoch: [243]  [ 50/312]  eta: 0:02:55  lr: 0.000394  min_lr: 0.000394  loss: 1.9744 (2.0063)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [243]  [ 60/312]  eta: 0:02:38  lr: 0.000394  min_lr: 0.000394  loss: 1.9887 (2.0107)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [243]  [ 70/312]  eta: 0:02:25  lr: 0.000393  min_lr: 0.000393  loss: 2.0966 (2.0338)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [243]  [ 80/312]  eta: 0:02:14  lr: 0.000393  min_lr: 0.000393  loss: 2.2500 (2.0439)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [243]  [ 90/312]  eta: 0:02:05  lr: 0.000392  min_lr: 0.000392  loss: 2.0682 (2.0557)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [243]  [100/312]  eta: 0:01:57  lr: 0.000392  min_lr: 0.000392  loss: 2.2779 (2.0757)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [243]  [110/312]  eta: 0:01:49  lr: 0.000391  min_lr: 0.000391  loss: 1.9983 (2.0624)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [243]  [120/312]  eta: 0:01:42  lr: 0.000391  min_lr: 0.000391  loss: 1.9776 (2.0788)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [243]  [130/312]  eta: 0:01:35  lr: 0.000391  min_lr: 0.000391  loss: 2.2465 (2.0862)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [243]  [140/312]  eta: 0:01:29  lr: 0.000390  min_lr: 0.000390  loss: 2.1831 (2.0889)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [243]  [150/312]  eta: 0:01:23  lr: 0.000390  min_lr: 0.000390  loss: 2.1683 (2.0934)  weight_decay: 0.0500 (0.0500)  time: 0.4384  data: 0.0004  max mem: 42573
Epoch: [243]  [160/312]  eta: 0:01:17  lr: 0.000389  min_lr: 0.000389  loss: 2.2354 (2.1009)  weight_decay: 0.0500 (0.0500)  time: 0.4380  data: 0.0004  max mem: 42573
Epoch: [243]  [170/312]  eta: 0:01:11  lr: 0.000389  min_lr: 0.000389  loss: 2.2364 (2.0976)  weight_decay: 0.0500 (0.0500)  time: 0.4331  data: 0.0004  max mem: 42573
Epoch: [243]  [180/312]  eta: 0:01:06  lr: 0.000388  min_lr: 0.000388  loss: 2.2422 (2.1048)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [243]  [190/312]  eta: 0:01:00  lr: 0.000388  min_lr: 0.000388  loss: 2.2178 (2.1039)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [243]  [200/312]  eta: 0:00:55  lr: 0.000388  min_lr: 0.000388  loss: 2.0215 (2.0921)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [243]  [210/312]  eta: 0:00:50  lr: 0.000387  min_lr: 0.000387  loss: 2.0041 (2.0896)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [243]  [220/312]  eta: 0:00:44  lr: 0.000387  min_lr: 0.000387  loss: 2.2377 (2.0899)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0005  max mem: 42573
Epoch: [243]  [230/312]  eta: 0:00:39  lr: 0.000386  min_lr: 0.000386  loss: 2.0864 (2.0845)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [243]  [240/312]  eta: 0:00:34  lr: 0.000386  min_lr: 0.000386  loss: 2.0864 (2.0896)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [243]  [250/312]  eta: 0:00:29  lr: 0.000385  min_lr: 0.000385  loss: 2.1240 (2.0854)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [243]  [260/312]  eta: 0:00:24  lr: 0.000385  min_lr: 0.000385  loss: 2.0981 (2.0897)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [243]  [270/312]  eta: 0:00:20  lr: 0.000385  min_lr: 0.000385  loss: 2.0981 (2.0824)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [243]  [280/312]  eta: 0:00:15  lr: 0.000384  min_lr: 0.000384  loss: 2.0620 (2.0843)  weight_decay: 0.0500 (0.0500)  time: 0.4344  data: 0.0009  max mem: 42573
Epoch: [243]  [290/312]  eta: 0:00:10  lr: 0.000384  min_lr: 0.000384  loss: 2.1446 (2.0806)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0008  max mem: 42573
Epoch: [243]  [300/312]  eta: 0:00:05  lr: 0.000383  min_lr: 0.000383  loss: 2.1967 (2.0861)  weight_decay: 0.0500 (0.0500)  time: 0.4322  data: 0.0001  max mem: 42573
Epoch: [243]  [310/312]  eta: 0:00:00  lr: 0.000383  min_lr: 0.000383  loss: 2.1655 (2.0855)  weight_decay: 0.0500 (0.0500)  time: 0.4320  data: 0.0001  max mem: 42573
Epoch: [243]  [311/312]  eta: 0:00:00  lr: 0.000383  min_lr: 0.000383  loss: 2.1967 (2.0860)  weight_decay: 0.0500 (0.0500)  time: 0.4320  data: 0.0001  max mem: 42573
Epoch: [243] Total time: 0:02:28 (0.4751 s / it)
Averaged stats: lr: 0.000383  min_lr: 0.000383  loss: 2.1967 (2.1320)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:00:43  loss: 0.6271 (0.6271)  acc1: 84.3750 (84.3750)  acc5: 96.0938 (96.0938)  time: 4.8576  data: 4.7494  max mem: 42573
Test:  [8/9]  eta: 0:00:00  loss: 0.8232 (0.7978)  acc1: 80.2083 (78.9120)  acc5: 95.8333 (94.6880)  time: 0.6166  data: 0.5278  max mem: 42573
Test: Total time: 0:00:05 (0.6391 s / it)
* Acc@1 79.490 Acc@5 94.680 loss 0.790
Accuracy of the model on the 50000 test images: 79.5%
Max accuracy: 79.49%
Epoch: [244]  [  0/312]  eta: 0:48:52  lr: 0.000383  min_lr: 0.000383  loss: 1.9278 (1.9278)  weight_decay: 0.0500 (0.0500)  time: 9.3987  data: 8.9275  max mem: 42573
Epoch: [244]  [ 10/312]  eta: 0:07:00  lr: 0.000382  min_lr: 0.000382  loss: 2.1507 (2.0304)  weight_decay: 0.0500 (0.0500)  time: 1.3923  data: 0.8120  max mem: 42573
Epoch: [244]  [ 20/312]  eta: 0:04:33  lr: 0.000382  min_lr: 0.000382  loss: 2.1757 (2.1294)  weight_decay: 0.0500 (0.0500)  time: 0.5129  data: 0.0004  max mem: 42573
Epoch: [244]  [ 30/312]  eta: 0:03:38  lr: 0.000382  min_lr: 0.000382  loss: 2.2436 (2.1275)  weight_decay: 0.0500 (0.0500)  time: 0.4346  data: 0.0004  max mem: 42573
Epoch: [244]  [ 40/312]  eta: 0:03:08  lr: 0.000381  min_lr: 0.000381  loss: 2.2108 (2.1530)  weight_decay: 0.0500 (0.0500)  time: 0.4352  data: 0.0004  max mem: 42573
Epoch: [244]  [ 50/312]  eta: 0:02:47  lr: 0.000381  min_lr: 0.000381  loss: 2.2361 (2.1555)  weight_decay: 0.0500 (0.0500)  time: 0.4342  data: 0.0004  max mem: 42573
Epoch: [244]  [ 60/312]  eta: 0:02:32  lr: 0.000380  min_lr: 0.000380  loss: 2.1132 (2.1349)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [244]  [ 70/312]  eta: 0:02:20  lr: 0.000380  min_lr: 0.000380  loss: 2.1132 (2.1367)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [244]  [ 80/312]  eta: 0:02:10  lr: 0.000379  min_lr: 0.000379  loss: 2.1126 (2.1268)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [244]  [ 90/312]  eta: 0:02:02  lr: 0.000379  min_lr: 0.000379  loss: 1.9817 (2.1181)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [244]  [100/312]  eta: 0:01:54  lr: 0.000379  min_lr: 0.000379  loss: 2.1950 (2.1385)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [244]  [110/312]  eta: 0:01:46  lr: 0.000378  min_lr: 0.000378  loss: 2.3426 (2.1486)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [244]  [120/312]  eta: 0:01:40  lr: 0.000378  min_lr: 0.000378  loss: 2.1466 (2.1475)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [244]  [130/312]  eta: 0:01:33  lr: 0.000377  min_lr: 0.000377  loss: 2.0624 (2.1383)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [244]  [140/312]  eta: 0:01:27  lr: 0.000377  min_lr: 0.000377  loss: 2.3029 (2.1436)  weight_decay: 0.0500 (0.0500)  time: 0.4435  data: 0.0004  max mem: 42573
Epoch: [244]  [150/312]  eta: 0:01:21  lr: 0.000377  min_lr: 0.000377  loss: 2.3069 (2.1466)  weight_decay: 0.0500 (0.0500)  time: 0.4436  data: 0.0004  max mem: 42573
Epoch: [244]  [160/312]  eta: 0:01:16  lr: 0.000376  min_lr: 0.000376  loss: 2.2044 (2.1397)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [244]  [170/312]  eta: 0:01:10  lr: 0.000376  min_lr: 0.000376  loss: 2.1958 (2.1417)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [244]  [180/312]  eta: 0:01:05  lr: 0.000375  min_lr: 0.000375  loss: 2.2118 (2.1441)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [244]  [190/312]  eta: 0:00:59  lr: 0.000375  min_lr: 0.000375  loss: 2.2118 (2.1471)  weight_decay: 0.0500 (0.0500)  time: 0.4332  data: 0.0004  max mem: 42573
Epoch: [244]  [200/312]  eta: 0:00:54  lr: 0.000374  min_lr: 0.000374  loss: 2.2400 (2.1498)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [244]  [210/312]  eta: 0:00:49  lr: 0.000374  min_lr: 0.000374  loss: 2.2513 (2.1500)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [244]  [220/312]  eta: 0:00:44  lr: 0.000374  min_lr: 0.000374  loss: 2.2443 (2.1513)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [244]  [230/312]  eta: 0:00:39  lr: 0.000373  min_lr: 0.000373  loss: 2.2363 (2.1496)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [244]  [240/312]  eta: 0:00:34  lr: 0.000373  min_lr: 0.000373  loss: 2.3196 (2.1547)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [244]  [250/312]  eta: 0:00:29  lr: 0.000372  min_lr: 0.000372  loss: 2.3068 (2.1550)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [244]  [260/312]  eta: 0:00:24  lr: 0.000372  min_lr: 0.000372  loss: 2.2464 (2.1543)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [244]  [270/312]  eta: 0:00:19  lr: 0.000372  min_lr: 0.000372  loss: 1.9805 (2.1482)  weight_decay: 0.0500 (0.0500)  time: 0.4332  data: 0.0004  max mem: 42573
Epoch: [244]  [280/312]  eta: 0:00:15  lr: 0.000371  min_lr: 0.000371  loss: 1.9991 (2.1500)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0010  max mem: 42573
Epoch: [244]  [290/312]  eta: 0:00:10  lr: 0.000371  min_lr: 0.000371  loss: 2.3322 (2.1580)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0008  max mem: 42573
Epoch: [244]  [300/312]  eta: 0:00:05  lr: 0.000370  min_lr: 0.000370  loss: 2.1040 (2.1501)  weight_decay: 0.0500 (0.0500)  time: 0.4321  data: 0.0001  max mem: 42573
Epoch: [244]  [310/312]  eta: 0:00:00  lr: 0.000370  min_lr: 0.000370  loss: 1.9348 (2.1471)  weight_decay: 0.0500 (0.0500)  time: 0.4320  data: 0.0001  max mem: 42573
Epoch: [244]  [311/312]  eta: 0:00:00  lr: 0.000370  min_lr: 0.000370  loss: 1.9348 (2.1467)  weight_decay: 0.0500 (0.0500)  time: 0.4320  data: 0.0001  max mem: 42573
Epoch: [244] Total time: 0:02:26 (0.4711 s / it)
Averaged stats: lr: 0.000370  min_lr: 0.000370  loss: 1.9348 (2.1320)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:00:39  loss: 0.5985 (0.5985)  acc1: 85.9375 (85.9375)  acc5: 96.3542 (96.3542)  time: 4.3837  data: 4.2756  max mem: 42573
Test:  [8/9]  eta: 0:00:00  loss: 0.8301 (0.7888)  acc1: 79.9479 (79.2640)  acc5: 94.5312 (94.5280)  time: 0.5912  data: 0.5029  max mem: 42573
Test: Total time: 0:00:05 (0.5985 s / it)
* Acc@1 79.500 Acc@5 94.638 loss 0.784
Accuracy of the model on the 50000 test images: 79.5%
Max accuracy: 79.50%
Epoch: [245]  [  0/312]  eta: 0:51:45  lr: 0.000370  min_lr: 0.000370  loss: 1.8465 (1.8465)  weight_decay: 0.0500 (0.0500)  time: 9.9525  data: 8.1615  max mem: 42573
Epoch: [245]  [ 10/312]  eta: 0:07:28  lr: 0.000369  min_lr: 0.000369  loss: 1.8465 (2.0163)  weight_decay: 0.0500 (0.0500)  time: 1.4860  data: 0.7808  max mem: 42573
Epoch: [245]  [ 20/312]  eta: 0:04:47  lr: 0.000369  min_lr: 0.000369  loss: 2.1627 (2.1154)  weight_decay: 0.0500 (0.0500)  time: 0.5368  data: 0.0215  max mem: 42573
Epoch: [245]  [ 30/312]  eta: 0:03:47  lr: 0.000369  min_lr: 0.000369  loss: 2.2662 (2.1232)  weight_decay: 0.0500 (0.0500)  time: 0.4343  data: 0.0004  max mem: 42573
Epoch: [245]  [ 40/312]  eta: 0:03:14  lr: 0.000368  min_lr: 0.000368  loss: 2.2248 (2.1642)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [245]  [ 50/312]  eta: 0:02:53  lr: 0.000368  min_lr: 0.000368  loss: 2.0849 (2.1374)  weight_decay: 0.0500 (0.0500)  time: 0.4332  data: 0.0004  max mem: 42573
Epoch: [245]  [ 60/312]  eta: 0:02:37  lr: 0.000367  min_lr: 0.000367  loss: 2.1134 (2.1600)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [245]  [ 70/312]  eta: 0:02:24  lr: 0.000367  min_lr: 0.000367  loss: 2.0462 (2.1228)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [245]  [ 80/312]  eta: 0:02:13  lr: 0.000366  min_lr: 0.000366  loss: 2.0518 (2.1376)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [245]  [ 90/312]  eta: 0:02:04  lr: 0.000366  min_lr: 0.000366  loss: 2.1348 (2.1374)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [245]  [100/312]  eta: 0:01:56  lr: 0.000366  min_lr: 0.000366  loss: 2.2115 (2.1444)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [245]  [110/312]  eta: 0:01:48  lr: 0.000365  min_lr: 0.000365  loss: 2.3397 (2.1564)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [245]  [120/312]  eta: 0:01:41  lr: 0.000365  min_lr: 0.000365  loss: 2.3397 (2.1631)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [245]  [130/312]  eta: 0:01:34  lr: 0.000364  min_lr: 0.000364  loss: 2.2259 (2.1719)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [245]  [140/312]  eta: 0:01:28  lr: 0.000364  min_lr: 0.000364  loss: 2.0782 (2.1544)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [245]  [150/312]  eta: 0:01:22  lr: 0.000364  min_lr: 0.000364  loss: 2.0760 (2.1550)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [245]  [160/312]  eta: 0:01:16  lr: 0.000363  min_lr: 0.000363  loss: 2.2243 (2.1506)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [245]  [170/312]  eta: 0:01:11  lr: 0.000363  min_lr: 0.000363  loss: 2.2022 (2.1553)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [245]  [180/312]  eta: 0:01:05  lr: 0.000362  min_lr: 0.000362  loss: 2.1944 (2.1541)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [245]  [190/312]  eta: 0:01:00  lr: 0.000362  min_lr: 0.000362  loss: 2.0502 (2.1436)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [245]  [200/312]  eta: 0:00:55  lr: 0.000362  min_lr: 0.000362  loss: 1.9609 (2.1365)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [245]  [210/312]  eta: 0:00:49  lr: 0.000361  min_lr: 0.000361  loss: 1.9609 (2.1248)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [245]  [220/312]  eta: 0:00:44  lr: 0.000361  min_lr: 0.000361  loss: 2.2009 (2.1332)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [245]  [230/312]  eta: 0:00:39  lr: 0.000360  min_lr: 0.000360  loss: 2.4828 (2.1482)  weight_decay: 0.0500 (0.0500)  time: 0.4332  data: 0.0003  max mem: 42573
Epoch: [245]  [240/312]  eta: 0:00:34  lr: 0.000360  min_lr: 0.000360  loss: 2.4495 (2.1496)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0003  max mem: 42573
Epoch: [245]  [250/312]  eta: 0:00:29  lr: 0.000359  min_lr: 0.000359  loss: 2.2326 (2.1487)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [245]  [260/312]  eta: 0:00:24  lr: 0.000359  min_lr: 0.000359  loss: 2.2362 (2.1528)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [245]  [270/312]  eta: 0:00:20  lr: 0.000359  min_lr: 0.000359  loss: 2.1969 (2.1502)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [245]  [280/312]  eta: 0:00:15  lr: 0.000358  min_lr: 0.000358  loss: 1.9305 (2.1422)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0009  max mem: 42573
Epoch: [245]  [290/312]  eta: 0:00:10  lr: 0.000358  min_lr: 0.000358  loss: 2.0900 (2.1389)  weight_decay: 0.0500 (0.0500)  time: 0.4332  data: 0.0008  max mem: 42573
Epoch: [245]  [300/312]  eta: 0:00:05  lr: 0.000357  min_lr: 0.000357  loss: 2.2602 (2.1417)  weight_decay: 0.0500 (0.0500)  time: 0.4321  data: 0.0001  max mem: 42573
Epoch: [245]  [310/312]  eta: 0:00:00  lr: 0.000357  min_lr: 0.000357  loss: 2.2612 (2.1451)  weight_decay: 0.0500 (0.0500)  time: 0.4321  data: 0.0001  max mem: 42573
Epoch: [245]  [311/312]  eta: 0:00:00  lr: 0.000357  min_lr: 0.000357  loss: 2.2612 (2.1462)  weight_decay: 0.0500 (0.0500)  time: 0.4320  data: 0.0001  max mem: 42573
Epoch: [245] Total time: 0:02:27 (0.4735 s / it)
Averaged stats: lr: 0.000357  min_lr: 0.000357  loss: 2.2612 (2.1203)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:00:43  loss: 0.6041 (0.6041)  acc1: 85.4167 (85.4167)  acc5: 96.0938 (96.0938)  time: 4.7807  data: 4.6726  max mem: 42573
Test:  [8/9]  eta: 0:00:00  loss: 0.8076 (0.7896)  acc1: 80.7292 (79.2640)  acc5: 94.5312 (94.5280)  time: 0.6080  data: 0.5192  max mem: 42573
Test: Total time: 0:00:05 (0.6341 s / it)
* Acc@1 79.326 Acc@5 94.596 loss 0.792
Accuracy of the model on the 50000 test images: 79.3%
Max accuracy: 79.50%
Epoch: [246]  [  0/312]  eta: 0:48:30  lr: 0.000357  min_lr: 0.000357  loss: 2.6904 (2.6904)  weight_decay: 0.0500 (0.0500)  time: 9.3288  data: 8.8314  max mem: 42573
Epoch: [246]  [ 10/312]  eta: 0:07:24  lr: 0.000356  min_lr: 0.000356  loss: 1.9746 (2.0485)  weight_decay: 0.0500 (0.0500)  time: 1.4732  data: 0.8033  max mem: 42573
Epoch: [246]  [ 20/312]  eta: 0:04:45  lr: 0.000356  min_lr: 0.000356  loss: 1.9746 (2.0956)  weight_decay: 0.0500 (0.0500)  time: 0.5603  data: 0.0004  max mem: 42573
Epoch: [246]  [ 30/312]  eta: 0:03:46  lr: 0.000356  min_lr: 0.000356  loss: 2.1250 (2.0754)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0003  max mem: 42573
Epoch: [246]  [ 40/312]  eta: 0:03:13  lr: 0.000355  min_lr: 0.000355  loss: 2.1800 (2.1088)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [246]  [ 50/312]  eta: 0:02:52  lr: 0.000355  min_lr: 0.000355  loss: 2.3673 (2.1679)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [246]  [ 60/312]  eta: 0:02:36  lr: 0.000354  min_lr: 0.000354  loss: 2.2991 (2.1335)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [246]  [ 70/312]  eta: 0:02:23  lr: 0.000354  min_lr: 0.000354  loss: 1.9574 (2.1264)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [246]  [ 80/312]  eta: 0:02:13  lr: 0.000354  min_lr: 0.000354  loss: 2.2296 (2.1441)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [246]  [ 90/312]  eta: 0:02:04  lr: 0.000353  min_lr: 0.000353  loss: 2.0776 (2.1247)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [246]  [100/312]  eta: 0:01:55  lr: 0.000353  min_lr: 0.000353  loss: 2.0509 (2.1213)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [246]  [110/312]  eta: 0:01:48  lr: 0.000352  min_lr: 0.000352  loss: 2.2658 (2.1485)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [246]  [120/312]  eta: 0:01:41  lr: 0.000352  min_lr: 0.000352  loss: 2.3674 (2.1505)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [246]  [130/312]  eta: 0:01:34  lr: 0.000352  min_lr: 0.000352  loss: 2.0890 (2.1506)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [246]  [140/312]  eta: 0:01:28  lr: 0.000351  min_lr: 0.000351  loss: 2.0048 (2.1323)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [246]  [150/312]  eta: 0:01:22  lr: 0.000351  min_lr: 0.000351  loss: 1.9571 (2.1313)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [246]  [160/312]  eta: 0:01:16  lr: 0.000350  min_lr: 0.000350  loss: 2.1762 (2.1337)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [246]  [170/312]  eta: 0:01:11  lr: 0.000350  min_lr: 0.000350  loss: 1.9642 (2.1235)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [246]  [180/312]  eta: 0:01:05  lr: 0.000350  min_lr: 0.000350  loss: 1.9642 (2.1200)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [246]  [190/312]  eta: 0:01:00  lr: 0.000349  min_lr: 0.000349  loss: 2.2679 (2.1280)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [246]  [200/312]  eta: 0:00:54  lr: 0.000349  min_lr: 0.000349  loss: 2.1001 (2.1165)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [246]  [210/312]  eta: 0:00:49  lr: 0.000348  min_lr: 0.000348  loss: 1.8501 (2.1060)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [246]  [220/312]  eta: 0:00:44  lr: 0.000348  min_lr: 0.000348  loss: 2.0126 (2.1083)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [246]  [230/312]  eta: 0:00:39  lr: 0.000348  min_lr: 0.000348  loss: 2.1285 (2.1083)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [246]  [240/312]  eta: 0:00:34  lr: 0.000347  min_lr: 0.000347  loss: 2.1620 (2.1108)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [246]  [250/312]  eta: 0:00:29  lr: 0.000347  min_lr: 0.000347  loss: 2.1977 (2.1117)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [246]  [260/312]  eta: 0:00:24  lr: 0.000346  min_lr: 0.000346  loss: 2.1977 (2.1118)  weight_decay: 0.0500 (0.0500)  time: 0.4332  data: 0.0004  max mem: 42573
Epoch: [246]  [270/312]  eta: 0:00:19  lr: 0.000346  min_lr: 0.000346  loss: 2.2610 (2.1182)  weight_decay: 0.0500 (0.0500)  time: 0.4332  data: 0.0004  max mem: 42573
Epoch: [246]  [280/312]  eta: 0:00:15  lr: 0.000346  min_lr: 0.000346  loss: 2.2610 (2.1207)  weight_decay: 0.0500 (0.0500)  time: 0.4405  data: 0.0010  max mem: 42573
Epoch: [246]  [290/312]  eta: 0:00:10  lr: 0.000345  min_lr: 0.000345  loss: 2.1046 (2.1155)  weight_decay: 0.0500 (0.0500)  time: 0.4398  data: 0.0008  max mem: 42573
Epoch: [246]  [300/312]  eta: 0:00:05  lr: 0.000345  min_lr: 0.000345  loss: 1.7588 (2.1039)  weight_decay: 0.0500 (0.0500)  time: 0.4320  data: 0.0001  max mem: 42573
Epoch: [246]  [310/312]  eta: 0:00:00  lr: 0.000344  min_lr: 0.000344  loss: 1.7588 (2.1024)  weight_decay: 0.0500 (0.0500)  time: 0.4321  data: 0.0001  max mem: 42573
Epoch: [246]  [311/312]  eta: 0:00:00  lr: 0.000344  min_lr: 0.000344  loss: 1.8087 (2.1018)  weight_decay: 0.0500 (0.0500)  time: 0.4321  data: 0.0001  max mem: 42573
Epoch: [246] Total time: 0:02:27 (0.4733 s / it)
Averaged stats: lr: 0.000344  min_lr: 0.000344  loss: 1.8087 (2.1285)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:00:42  loss: 0.5933 (0.5933)  acc1: 84.3750 (84.3750)  acc5: 97.1354 (97.1354)  time: 4.7594  data: 4.6509  max mem: 42573
Test:  [8/9]  eta: 0:00:00  loss: 0.8011 (0.7815)  acc1: 80.4688 (79.6160)  acc5: 95.5729 (95.0720)  time: 0.6053  data: 0.5168  max mem: 42573
Test: Total time: 0:00:05 (0.6286 s / it)
* Acc@1 79.670 Acc@5 94.874 loss 0.773
Accuracy of the model on the 50000 test images: 79.7%
Max accuracy: 79.67%
Epoch: [247]  [  0/312]  eta: 0:50:36  lr: 0.000344  min_lr: 0.000344  loss: 2.3065 (2.3065)  weight_decay: 0.0500 (0.0500)  time: 9.7319  data: 9.2675  max mem: 42573
Epoch: [247]  [ 10/312]  eta: 0:07:39  lr: 0.000344  min_lr: 0.000344  loss: 2.1859 (2.0623)  weight_decay: 0.0500 (0.0500)  time: 1.5222  data: 0.8429  max mem: 42573
Epoch: [247]  [ 20/312]  eta: 0:04:53  lr: 0.000343  min_lr: 0.000343  loss: 2.3072 (2.2200)  weight_decay: 0.0500 (0.0500)  time: 0.5670  data: 0.0004  max mem: 42573
Epoch: [247]  [ 30/312]  eta: 0:03:51  lr: 0.000343  min_lr: 0.000343  loss: 2.3232 (2.2279)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0003  max mem: 42573
Epoch: [247]  [ 40/312]  eta: 0:03:17  lr: 0.000343  min_lr: 0.000343  loss: 2.0262 (2.1920)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0004  max mem: 42573
Epoch: [247]  [ 50/312]  eta: 0:02:55  lr: 0.000342  min_lr: 0.000342  loss: 2.0998 (2.1977)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [247]  [ 60/312]  eta: 0:02:38  lr: 0.000342  min_lr: 0.000342  loss: 2.0998 (2.1709)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [247]  [ 70/312]  eta: 0:02:25  lr: 0.000341  min_lr: 0.000341  loss: 1.9599 (2.1400)  weight_decay: 0.0500 (0.0500)  time: 0.4332  data: 0.0004  max mem: 42573
Epoch: [247]  [ 80/312]  eta: 0:02:14  lr: 0.000341  min_lr: 0.000341  loss: 2.1932 (2.1499)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [247]  [ 90/312]  eta: 0:02:05  lr: 0.000341  min_lr: 0.000341  loss: 2.2707 (2.1433)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [247]  [100/312]  eta: 0:01:57  lr: 0.000340  min_lr: 0.000340  loss: 2.1064 (2.1334)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [247]  [110/312]  eta: 0:01:49  lr: 0.000340  min_lr: 0.000340  loss: 1.9299 (2.0968)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [247]  [120/312]  eta: 0:01:42  lr: 0.000339  min_lr: 0.000339  loss: 2.0920 (2.1058)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [247]  [130/312]  eta: 0:01:35  lr: 0.000339  min_lr: 0.000339  loss: 2.0920 (2.0966)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [247]  [140/312]  eta: 0:01:29  lr: 0.000339  min_lr: 0.000339  loss: 2.0526 (2.1012)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [247]  [150/312]  eta: 0:01:23  lr: 0.000338  min_lr: 0.000338  loss: 2.0617 (2.0917)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [247]  [160/312]  eta: 0:01:17  lr: 0.000338  min_lr: 0.000338  loss: 2.0617 (2.0928)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [247]  [170/312]  eta: 0:01:11  lr: 0.000337  min_lr: 0.000337  loss: 2.2262 (2.0941)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [247]  [180/312]  eta: 0:01:05  lr: 0.000337  min_lr: 0.000337  loss: 1.9231 (2.0833)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0003  max mem: 42573
Epoch: [247]  [190/312]  eta: 0:01:00  lr: 0.000337  min_lr: 0.000337  loss: 1.8738 (2.0803)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0003  max mem: 42573
Epoch: [247]  [200/312]  eta: 0:00:55  lr: 0.000336  min_lr: 0.000336  loss: 2.1887 (2.0847)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [247]  [210/312]  eta: 0:00:50  lr: 0.000336  min_lr: 0.000336  loss: 2.2601 (2.0895)  weight_decay: 0.0500 (0.0500)  time: 0.4372  data: 0.0004  max mem: 42573
Epoch: [247]  [220/312]  eta: 0:00:44  lr: 0.000335  min_lr: 0.000335  loss: 2.2586 (2.0874)  weight_decay: 0.0500 (0.0500)  time: 0.4371  data: 0.0004  max mem: 42573
Epoch: [247]  [230/312]  eta: 0:00:39  lr: 0.000335  min_lr: 0.000335  loss: 1.8402 (2.0775)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [247]  [240/312]  eta: 0:00:34  lr: 0.000335  min_lr: 0.000335  loss: 1.7936 (2.0665)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0003  max mem: 42573
Epoch: [247]  [250/312]  eta: 0:00:29  lr: 0.000334  min_lr: 0.000334  loss: 1.9544 (2.0675)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [247]  [260/312]  eta: 0:00:24  lr: 0.000334  min_lr: 0.000334  loss: 2.2347 (2.0719)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [247]  [270/312]  eta: 0:00:20  lr: 0.000333  min_lr: 0.000333  loss: 2.2758 (2.0772)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [247]  [280/312]  eta: 0:00:15  lr: 0.000333  min_lr: 0.000333  loss: 2.2682 (2.0782)  weight_decay: 0.0500 (0.0500)  time: 0.4341  data: 0.0010  max mem: 42573
Epoch: [247]  [290/312]  eta: 0:00:10  lr: 0.000333  min_lr: 0.000333  loss: 2.0998 (2.0738)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0008  max mem: 42573
Epoch: [247]  [300/312]  eta: 0:00:05  lr: 0.000332  min_lr: 0.000332  loss: 2.1377 (2.0796)  weight_decay: 0.0500 (0.0500)  time: 0.4322  data: 0.0001  max mem: 42573
Epoch: [247]  [310/312]  eta: 0:00:00  lr: 0.000332  min_lr: 0.000332  loss: 2.2609 (2.0823)  weight_decay: 0.0500 (0.0500)  time: 0.4320  data: 0.0001  max mem: 42573
Epoch: [247]  [311/312]  eta: 0:00:00  lr: 0.000332  min_lr: 0.000332  loss: 2.2455 (2.0802)  weight_decay: 0.0500 (0.0500)  time: 0.4320  data: 0.0001  max mem: 42573
Epoch: [247] Total time: 0:02:28 (0.4751 s / it)
Averaged stats: lr: 0.000332  min_lr: 0.000332  loss: 2.2455 (2.1035)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:00:42  loss: 0.6212 (0.6212)  acc1: 84.6354 (84.6354)  acc5: 96.3542 (96.3542)  time: 4.7425  data: 4.6343  max mem: 42573
Test:  [8/9]  eta: 0:00:00  loss: 0.8113 (0.8020)  acc1: 78.3854 (78.6240)  acc5: 95.3125 (94.7200)  time: 0.6093  data: 0.5150  max mem: 42573
Test: Total time: 0:00:05 (0.6188 s / it)
* Acc@1 79.598 Acc@5 94.688 loss 0.783
Accuracy of the model on the 50000 test images: 79.6%
Max accuracy: 79.67%
Epoch: [248]  [  0/312]  eta: 0:50:47  lr: 0.000332  min_lr: 0.000332  loss: 2.1957 (2.1957)  weight_decay: 0.0500 (0.0500)  time: 9.7667  data: 6.3509  max mem: 42573
Epoch: [248]  [ 10/312]  eta: 0:07:43  lr: 0.000331  min_lr: 0.000331  loss: 2.1429 (2.1187)  weight_decay: 0.0500 (0.0500)  time: 1.5332  data: 0.7182  max mem: 42573
Epoch: [248]  [ 20/312]  eta: 0:04:54  lr: 0.000331  min_lr: 0.000331  loss: 2.1717 (2.1657)  weight_decay: 0.0500 (0.0500)  time: 0.5713  data: 0.0777  max mem: 42573
Epoch: [248]  [ 30/312]  eta: 0:03:53  lr: 0.000331  min_lr: 0.000331  loss: 2.2016 (2.1662)  weight_decay: 0.0500 (0.0500)  time: 0.4383  data: 0.0004  max mem: 42573
Epoch: [248]  [ 40/312]  eta: 0:03:18  lr: 0.000330  min_lr: 0.000330  loss: 2.1367 (2.1628)  weight_decay: 0.0500 (0.0500)  time: 0.4386  data: 0.0004  max mem: 42573
Epoch: [248]  [ 50/312]  eta: 0:02:56  lr: 0.000330  min_lr: 0.000330  loss: 2.3189 (2.1974)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [248]  [ 60/312]  eta: 0:02:39  lr: 0.000329  min_lr: 0.000329  loss: 2.3030 (2.1725)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [248]  [ 70/312]  eta: 0:02:26  lr: 0.000329  min_lr: 0.000329  loss: 2.1275 (2.1673)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [248]  [ 80/312]  eta: 0:02:15  lr: 0.000329  min_lr: 0.000329  loss: 1.8995 (2.1360)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [248]  [ 90/312]  eta: 0:02:06  lr: 0.000328  min_lr: 0.000328  loss: 1.9071 (2.1217)  weight_decay: 0.0500 (0.0500)  time: 0.4343  data: 0.0004  max mem: 42573
Epoch: [248]  [100/312]  eta: 0:01:57  lr: 0.000328  min_lr: 0.000328  loss: 2.0591 (2.1155)  weight_decay: 0.0500 (0.0500)  time: 0.4361  data: 0.0004  max mem: 42573
Epoch: [248]  [110/312]  eta: 0:01:49  lr: 0.000327  min_lr: 0.000327  loss: 2.0749 (2.1197)  weight_decay: 0.0500 (0.0500)  time: 0.4351  data: 0.0004  max mem: 42573
Epoch: [248]  [120/312]  eta: 0:01:42  lr: 0.000327  min_lr: 0.000327  loss: 2.2342 (2.1226)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [248]  [130/312]  eta: 0:01:35  lr: 0.000327  min_lr: 0.000327  loss: 2.2409 (2.1336)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [248]  [140/312]  eta: 0:01:29  lr: 0.000326  min_lr: 0.000326  loss: 2.2409 (2.1330)  weight_decay: 0.0500 (0.0500)  time: 0.4347  data: 0.0004  max mem: 42573
Epoch: [248]  [150/312]  eta: 0:01:23  lr: 0.000326  min_lr: 0.000326  loss: 2.1531 (2.1317)  weight_decay: 0.0500 (0.0500)  time: 0.4348  data: 0.0003  max mem: 42573
Epoch: [248]  [160/312]  eta: 0:01:17  lr: 0.000325  min_lr: 0.000325  loss: 2.0424 (2.1269)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [248]  [170/312]  eta: 0:01:11  lr: 0.000325  min_lr: 0.000325  loss: 2.1650 (2.1347)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [248]  [180/312]  eta: 0:01:06  lr: 0.000325  min_lr: 0.000325  loss: 2.2552 (2.1316)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [248]  [190/312]  eta: 0:01:00  lr: 0.000324  min_lr: 0.000324  loss: 2.1302 (2.1279)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [248]  [200/312]  eta: 0:00:55  lr: 0.000324  min_lr: 0.000324  loss: 2.0868 (2.1197)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [248]  [210/312]  eta: 0:00:50  lr: 0.000323  min_lr: 0.000323  loss: 2.0391 (2.1178)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [248]  [220/312]  eta: 0:00:44  lr: 0.000323  min_lr: 0.000323  loss: 2.0304 (2.1120)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [248]  [230/312]  eta: 0:00:39  lr: 0.000323  min_lr: 0.000323  loss: 2.0194 (2.1075)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [248]  [240/312]  eta: 0:00:34  lr: 0.000322  min_lr: 0.000322  loss: 2.0977 (2.1100)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [248]  [250/312]  eta: 0:00:29  lr: 0.000322  min_lr: 0.000322  loss: 2.1602 (2.1053)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [248]  [260/312]  eta: 0:00:24  lr: 0.000322  min_lr: 0.000322  loss: 2.1967 (2.1099)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0003  max mem: 42573
Epoch: [248]  [270/312]  eta: 0:00:20  lr: 0.000321  min_lr: 0.000321  loss: 2.2725 (2.1192)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0003  max mem: 42573
Epoch: [248]  [280/312]  eta: 0:00:15  lr: 0.000321  min_lr: 0.000321  loss: 2.2877 (2.1211)  weight_decay: 0.0500 (0.0500)  time: 0.4344  data: 0.0009  max mem: 42573
Epoch: [248]  [290/312]  eta: 0:00:10  lr: 0.000320  min_lr: 0.000320  loss: 2.2140 (2.1242)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0008  max mem: 42573
Epoch: [248]  [300/312]  eta: 0:00:05  lr: 0.000320  min_lr: 0.000320  loss: 2.1232 (2.1253)  weight_decay: 0.0500 (0.0500)  time: 0.4321  data: 0.0001  max mem: 42573
Epoch: [248]  [310/312]  eta: 0:00:00  lr: 0.000320  min_lr: 0.000320  loss: 2.1150 (2.1245)  weight_decay: 0.0500 (0.0500)  time: 0.4321  data: 0.0001  max mem: 42573
Epoch: [248]  [311/312]  eta: 0:00:00  lr: 0.000320  min_lr: 0.000320  loss: 2.1232 (2.1253)  weight_decay: 0.0500 (0.0500)  time: 0.4321  data: 0.0001  max mem: 42573
Epoch: [248] Total time: 0:02:28 (0.4759 s / it)
Averaged stats: lr: 0.000320  min_lr: 0.000320  loss: 2.1232 (2.1103)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:00:43  loss: 0.6190 (0.6190)  acc1: 85.9375 (85.9375)  acc5: 96.0938 (96.0938)  time: 4.7894  data: 4.6810  max mem: 42573
Test:  [8/9]  eta: 0:00:00  loss: 0.8088 (0.7888)  acc1: 80.2083 (79.6160)  acc5: 95.3125 (95.0720)  time: 0.6077  data: 0.5202  max mem: 42573
Test: Total time: 0:00:05 (0.6232 s / it)
* Acc@1 79.860 Acc@5 94.850 loss 0.771
Accuracy of the model on the 50000 test images: 79.9%
Max accuracy: 79.86%
Epoch: [249]  [  0/312]  eta: 0:46:45  lr: 0.000320  min_lr: 0.000320  loss: 1.3914 (1.3914)  weight_decay: 0.0500 (0.0500)  time: 8.9931  data: 8.0653  max mem: 42573
Epoch: [249]  [ 10/312]  eta: 0:07:02  lr: 0.000319  min_lr: 0.000319  loss: 2.1150 (2.1127)  weight_decay: 0.0500 (0.0500)  time: 1.3989  data: 0.7336  max mem: 42573
Epoch: [249]  [ 20/312]  eta: 0:04:34  lr: 0.000319  min_lr: 0.000319  loss: 1.9535 (2.0536)  weight_decay: 0.0500 (0.0500)  time: 0.5365  data: 0.0004  max mem: 42573
Epoch: [249]  [ 30/312]  eta: 0:03:38  lr: 0.000318  min_lr: 0.000318  loss: 2.1352 (2.1148)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0003  max mem: 42573
Epoch: [249]  [ 40/312]  eta: 0:03:08  lr: 0.000318  min_lr: 0.000318  loss: 2.2081 (2.1336)  weight_decay: 0.0500 (0.0500)  time: 0.4332  data: 0.0003  max mem: 42573
Epoch: [249]  [ 50/312]  eta: 0:02:48  lr: 0.000318  min_lr: 0.000318  loss: 2.2795 (2.1629)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [249]  [ 60/312]  eta: 0:02:33  lr: 0.000317  min_lr: 0.000317  loss: 2.2603 (2.1440)  weight_decay: 0.0500 (0.0500)  time: 0.4332  data: 0.0003  max mem: 42573
Epoch: [249]  [ 70/312]  eta: 0:02:21  lr: 0.000317  min_lr: 0.000317  loss: 1.8586 (2.1208)  weight_decay: 0.0500 (0.0500)  time: 0.4331  data: 0.0003  max mem: 42573
Epoch: [249]  [ 80/312]  eta: 0:02:10  lr: 0.000316  min_lr: 0.000316  loss: 1.8586 (2.1105)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [249]  [ 90/312]  eta: 0:02:02  lr: 0.000316  min_lr: 0.000316  loss: 2.1847 (2.1168)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [249]  [100/312]  eta: 0:01:54  lr: 0.000316  min_lr: 0.000316  loss: 2.2242 (2.1204)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [249]  [110/312]  eta: 0:01:46  lr: 0.000315  min_lr: 0.000315  loss: 2.2658 (2.1319)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [249]  [120/312]  eta: 0:01:40  lr: 0.000315  min_lr: 0.000315  loss: 2.3019 (2.1347)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [249]  [130/312]  eta: 0:01:33  lr: 0.000314  min_lr: 0.000314  loss: 2.1830 (2.1246)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [249]  [140/312]  eta: 0:01:27  lr: 0.000314  min_lr: 0.000314  loss: 2.1380 (2.1237)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [249]  [150/312]  eta: 0:01:21  lr: 0.000314  min_lr: 0.000314  loss: 2.3257 (2.1381)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [249]  [160/312]  eta: 0:01:15  lr: 0.000313  min_lr: 0.000313  loss: 2.3257 (2.1491)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [249]  [170/312]  eta: 0:01:10  lr: 0.000313  min_lr: 0.000313  loss: 2.0165 (2.1265)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [249]  [180/312]  eta: 0:01:04  lr: 0.000313  min_lr: 0.000313  loss: 1.7535 (2.1210)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [249]  [190/312]  eta: 0:00:59  lr: 0.000312  min_lr: 0.000312  loss: 2.1471 (2.1177)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [249]  [200/312]  eta: 0:00:54  lr: 0.000312  min_lr: 0.000312  loss: 2.2178 (2.1218)  weight_decay: 0.0500 (0.0500)  time: 0.4332  data: 0.0003  max mem: 42573
Epoch: [249]  [210/312]  eta: 0:00:49  lr: 0.000311  min_lr: 0.000311  loss: 2.2178 (2.1251)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0003  max mem: 42573
Epoch: [249]  [220/312]  eta: 0:00:44  lr: 0.000311  min_lr: 0.000311  loss: 2.1083 (2.1202)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [249]  [230/312]  eta: 0:00:39  lr: 0.000311  min_lr: 0.000311  loss: 2.0876 (2.1167)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [249]  [240/312]  eta: 0:00:34  lr: 0.000310  min_lr: 0.000310  loss: 1.9395 (2.1132)  weight_decay: 0.0500 (0.0500)  time: 0.4367  data: 0.0003  max mem: 42573
Epoch: [249]  [250/312]  eta: 0:00:29  lr: 0.000310  min_lr: 0.000310  loss: 2.0570 (2.1176)  weight_decay: 0.0500 (0.0500)  time: 0.4366  data: 0.0004  max mem: 42573
Epoch: [249]  [260/312]  eta: 0:00:24  lr: 0.000309  min_lr: 0.000309  loss: 2.1251 (2.1184)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [249]  [270/312]  eta: 0:00:19  lr: 0.000309  min_lr: 0.000309  loss: 1.9896 (2.1110)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [249]  [280/312]  eta: 0:00:15  lr: 0.000309  min_lr: 0.000309  loss: 2.1023 (2.1151)  weight_decay: 0.0500 (0.0500)  time: 0.4344  data: 0.0009  max mem: 42573
Epoch: [249]  [290/312]  eta: 0:00:10  lr: 0.000308  min_lr: 0.000308  loss: 2.2359 (2.1154)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0008  max mem: 42573
Epoch: [249]  [300/312]  eta: 0:00:05  lr: 0.000308  min_lr: 0.000308  loss: 2.2359 (2.1157)  weight_decay: 0.0500 (0.0500)  time: 0.4322  data: 0.0001  max mem: 42573
Epoch: [249]  [310/312]  eta: 0:00:00  lr: 0.000308  min_lr: 0.000308  loss: 2.1836 (2.1157)  weight_decay: 0.0500 (0.0500)  time: 0.4322  data: 0.0001  max mem: 42573
Epoch: [249]  [311/312]  eta: 0:00:00  lr: 0.000308  min_lr: 0.000308  loss: 2.1836 (2.1163)  weight_decay: 0.0500 (0.0500)  time: 0.4322  data: 0.0001  max mem: 42573
Epoch: [249] Total time: 0:02:26 (0.4704 s / it)
Averaged stats: lr: 0.000308  min_lr: 0.000308  loss: 2.1836 (2.1124)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:00:42  loss: 0.5962 (0.5962)  acc1: 85.4167 (85.4167)  acc5: 95.5729 (95.5729)  time: 4.7370  data: 4.6287  max mem: 42573
Test:  [8/9]  eta: 0:00:00  loss: 0.8238 (0.7875)  acc1: 79.4271 (79.3920)  acc5: 95.3125 (94.6240)  time: 0.6015  data: 0.5144  max mem: 42573
Test: Total time: 0:00:05 (0.6224 s / it)
* Acc@1 79.852 Acc@5 94.788 loss 0.767
Accuracy of the model on the 50000 test images: 79.9%
Max accuracy: 79.86%
Epoch: [250]  [  0/312]  eta: 0:52:10  lr: 0.000307  min_lr: 0.000307  loss: 2.1861 (2.1861)  weight_decay: 0.0500 (0.0500)  time: 10.0328  data: 6.0641  max mem: 42573
Epoch: [250]  [ 10/312]  eta: 0:07:28  lr: 0.000307  min_lr: 0.000307  loss: 2.2500 (2.0790)  weight_decay: 0.0500 (0.0500)  time: 1.4854  data: 0.7278  max mem: 42573
Epoch: [250]  [ 20/312]  eta: 0:04:47  lr: 0.000307  min_lr: 0.000307  loss: 2.2021 (2.1036)  weight_decay: 0.0500 (0.0500)  time: 0.5318  data: 0.0973  max mem: 42573
Epoch: [250]  [ 30/312]  eta: 0:03:47  lr: 0.000306  min_lr: 0.000306  loss: 2.2072 (2.1334)  weight_decay: 0.0500 (0.0500)  time: 0.4331  data: 0.0004  max mem: 42573
Epoch: [250]  [ 40/312]  eta: 0:03:14  lr: 0.000306  min_lr: 0.000306  loss: 2.1891 (2.1219)  weight_decay: 0.0500 (0.0500)  time: 0.4331  data: 0.0004  max mem: 42573
Epoch: [250]  [ 50/312]  eta: 0:02:52  lr: 0.000306  min_lr: 0.000306  loss: 2.1525 (2.1517)  weight_decay: 0.0500 (0.0500)  time: 0.4331  data: 0.0004  max mem: 42573
Epoch: [250]  [ 60/312]  eta: 0:02:36  lr: 0.000305  min_lr: 0.000305  loss: 2.2373 (2.1544)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [250]  [ 70/312]  eta: 0:02:24  lr: 0.000305  min_lr: 0.000305  loss: 2.2220 (2.1455)  weight_decay: 0.0500 (0.0500)  time: 0.4383  data: 0.0004  max mem: 42573
Epoch: [250]  [ 80/312]  eta: 0:02:13  lr: 0.000304  min_lr: 0.000304  loss: 2.1558 (2.1598)  weight_decay: 0.0500 (0.0500)  time: 0.4383  data: 0.0004  max mem: 42573
Epoch: [250]  [ 90/312]  eta: 0:02:04  lr: 0.000304  min_lr: 0.000304  loss: 2.2114 (2.1521)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [250]  [100/312]  eta: 0:01:56  lr: 0.000304  min_lr: 0.000304  loss: 2.2771 (2.1650)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [250]  [110/312]  eta: 0:01:48  lr: 0.000303  min_lr: 0.000303  loss: 2.2150 (2.1634)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [250]  [120/312]  eta: 0:01:41  lr: 0.000303  min_lr: 0.000303  loss: 2.3091 (2.1828)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [250]  [130/312]  eta: 0:01:35  lr: 0.000303  min_lr: 0.000303  loss: 2.3091 (2.1740)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [250]  [140/312]  eta: 0:01:28  lr: 0.000302  min_lr: 0.000302  loss: 2.1829 (2.1815)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [250]  [150/312]  eta: 0:01:22  lr: 0.000302  min_lr: 0.000302  loss: 2.1459 (2.1728)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [250]  [160/312]  eta: 0:01:17  lr: 0.000301  min_lr: 0.000301  loss: 2.0555 (2.1701)  weight_decay: 0.0500 (0.0500)  time: 0.4408  data: 0.0004  max mem: 42573
Epoch: [250]  [170/312]  eta: 0:01:11  lr: 0.000301  min_lr: 0.000301  loss: 2.1757 (2.1734)  weight_decay: 0.0500 (0.0500)  time: 0.4408  data: 0.0004  max mem: 42573
Epoch: [250]  [180/312]  eta: 0:01:05  lr: 0.000301  min_lr: 0.000301  loss: 2.2486 (2.1738)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [250]  [190/312]  eta: 0:01:00  lr: 0.000300  min_lr: 0.000300  loss: 2.2259 (2.1722)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [250]  [200/312]  eta: 0:00:55  lr: 0.000300  min_lr: 0.000300  loss: 2.1353 (2.1721)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [250]  [210/312]  eta: 0:00:49  lr: 0.000299  min_lr: 0.000299  loss: 2.1562 (2.1671)  weight_decay: 0.0500 (0.0500)  time: 0.4332  data: 0.0004  max mem: 42573
Epoch: [250]  [220/312]  eta: 0:00:44  lr: 0.000299  min_lr: 0.000299  loss: 2.1562 (2.1647)  weight_decay: 0.0500 (0.0500)  time: 0.4332  data: 0.0004  max mem: 42573
Epoch: [250]  [230/312]  eta: 0:00:39  lr: 0.000299  min_lr: 0.000299  loss: 2.1300 (2.1640)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [250]  [240/312]  eta: 0:00:34  lr: 0.000298  min_lr: 0.000298  loss: 2.1741 (2.1635)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [250]  [250/312]  eta: 0:00:29  lr: 0.000298  min_lr: 0.000298  loss: 2.2669 (2.1668)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [250]  [260/312]  eta: 0:00:24  lr: 0.000298  min_lr: 0.000298  loss: 2.3633 (2.1740)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [250]  [270/312]  eta: 0:00:20  lr: 0.000297  min_lr: 0.000297  loss: 2.2537 (2.1706)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [250]  [280/312]  eta: 0:00:15  lr: 0.000297  min_lr: 0.000297  loss: 2.1465 (2.1675)  weight_decay: 0.0500 (0.0500)  time: 0.4344  data: 0.0009  max mem: 42573
Epoch: [250]  [290/312]  eta: 0:00:10  lr: 0.000296  min_lr: 0.000296  loss: 2.1434 (2.1641)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0008  max mem: 42573
Epoch: [250]  [300/312]  eta: 0:00:05  lr: 0.000296  min_lr: 0.000296  loss: 2.0525 (2.1586)  weight_decay: 0.0500 (0.0500)  time: 0.4320  data: 0.0001  max mem: 42573
Epoch: [250]  [310/312]  eta: 0:00:00  lr: 0.000296  min_lr: 0.000296  loss: 2.0525 (2.1555)  weight_decay: 0.0500 (0.0500)  time: 0.4321  data: 0.0001  max mem: 42573
Epoch: [250]  [311/312]  eta: 0:00:00  lr: 0.000296  min_lr: 0.000296  loss: 2.1868 (2.1565)  weight_decay: 0.0500 (0.0500)  time: 0.4321  data: 0.0001  max mem: 42573
Epoch: [250] Total time: 0:02:27 (0.4744 s / it)
Averaged stats: lr: 0.000296  min_lr: 0.000296  loss: 2.1868 (2.1123)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:00:41  loss: 0.5824 (0.5824)  acc1: 85.4167 (85.4167)  acc5: 95.8333 (95.8333)  time: 4.6646  data: 4.5561  max mem: 42573
Test:  [8/9]  eta: 0:00:00  loss: 0.7817 (0.7780)  acc1: 80.4688 (79.1040)  acc5: 95.0521 (95.0080)  time: 0.5945  data: 0.5063  max mem: 42573
Test: Total time: 0:00:05 (0.6044 s / it)
* Acc@1 79.854 Acc@5 94.910 loss 0.766
Accuracy of the model on the 50000 test images: 79.9%
Max accuracy: 79.86%
Epoch: [251]  [  0/312]  eta: 0:51:57  lr: 0.000296  min_lr: 0.000296  loss: 2.4458 (2.4458)  weight_decay: 0.0500 (0.0500)  time: 9.9910  data: 7.7456  max mem: 42573
Epoch: [251]  [ 10/312]  eta: 0:07:32  lr: 0.000295  min_lr: 0.000295  loss: 2.1449 (2.0914)  weight_decay: 0.0500 (0.0500)  time: 1.4974  data: 0.7172  max mem: 42573
Epoch: [251]  [ 20/312]  eta: 0:04:49  lr: 0.000295  min_lr: 0.000295  loss: 2.0647 (1.9943)  weight_decay: 0.0500 (0.0500)  time: 0.5411  data: 0.0074  max mem: 42573
Epoch: [251]  [ 30/312]  eta: 0:03:48  lr: 0.000295  min_lr: 0.000295  loss: 1.7197 (1.9232)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [251]  [ 40/312]  eta: 0:03:15  lr: 0.000294  min_lr: 0.000294  loss: 1.9866 (1.9471)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [251]  [ 50/312]  eta: 0:02:53  lr: 0.000294  min_lr: 0.000294  loss: 2.1104 (1.9730)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0003  max mem: 42573
Epoch: [251]  [ 60/312]  eta: 0:02:37  lr: 0.000293  min_lr: 0.000293  loss: 2.0752 (1.9817)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [251]  [ 70/312]  eta: 0:02:24  lr: 0.000293  min_lr: 0.000293  loss: 2.1894 (1.9989)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [251]  [ 80/312]  eta: 0:02:14  lr: 0.000293  min_lr: 0.000293  loss: 2.1894 (2.0108)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [251]  [ 90/312]  eta: 0:02:04  lr: 0.000292  min_lr: 0.000292  loss: 2.1308 (2.0251)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [251]  [100/312]  eta: 0:01:56  lr: 0.000292  min_lr: 0.000292  loss: 2.2338 (2.0235)  weight_decay: 0.0500 (0.0500)  time: 0.4393  data: 0.0003  max mem: 42573
Epoch: [251]  [110/312]  eta: 0:01:49  lr: 0.000292  min_lr: 0.000292  loss: 1.9799 (2.0200)  weight_decay: 0.0500 (0.0500)  time: 0.4392  data: 0.0004  max mem: 42573
Epoch: [251]  [120/312]  eta: 0:01:42  lr: 0.000291  min_lr: 0.000291  loss: 2.0258 (2.0256)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [251]  [130/312]  eta: 0:01:35  lr: 0.000291  min_lr: 0.000291  loss: 2.3000 (2.0482)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [251]  [140/312]  eta: 0:01:28  lr: 0.000290  min_lr: 0.000290  loss: 2.2066 (2.0559)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [251]  [150/312]  eta: 0:01:22  lr: 0.000290  min_lr: 0.000290  loss: 2.1525 (2.0583)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [251]  [160/312]  eta: 0:01:17  lr: 0.000290  min_lr: 0.000290  loss: 1.9505 (2.0454)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [251]  [170/312]  eta: 0:01:11  lr: 0.000289  min_lr: 0.000289  loss: 2.0269 (2.0582)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [251]  [180/312]  eta: 0:01:05  lr: 0.000289  min_lr: 0.000289  loss: 2.2827 (2.0669)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [251]  [190/312]  eta: 0:01:00  lr: 0.000289  min_lr: 0.000289  loss: 2.1918 (2.0681)  weight_decay: 0.0500 (0.0500)  time: 0.4341  data: 0.0004  max mem: 42573
Epoch: [251]  [200/312]  eta: 0:00:55  lr: 0.000288  min_lr: 0.000288  loss: 2.1444 (2.0734)  weight_decay: 0.0500 (0.0500)  time: 0.4342  data: 0.0004  max mem: 42573
Epoch: [251]  [210/312]  eta: 0:00:49  lr: 0.000288  min_lr: 0.000288  loss: 2.1444 (2.0737)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [251]  [220/312]  eta: 0:00:44  lr: 0.000287  min_lr: 0.000287  loss: 2.0467 (2.0761)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0003  max mem: 42573
Epoch: [251]  [230/312]  eta: 0:00:39  lr: 0.000287  min_lr: 0.000287  loss: 2.2427 (2.0752)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0003  max mem: 42573
Epoch: [251]  [240/312]  eta: 0:00:34  lr: 0.000287  min_lr: 0.000287  loss: 2.2427 (2.0757)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [251]  [250/312]  eta: 0:00:29  lr: 0.000286  min_lr: 0.000286  loss: 2.2498 (2.0816)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [251]  [260/312]  eta: 0:00:24  lr: 0.000286  min_lr: 0.000286  loss: 2.2461 (2.0814)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [251]  [270/312]  eta: 0:00:20  lr: 0.000286  min_lr: 0.000286  loss: 2.0689 (2.0765)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [251]  [280/312]  eta: 0:00:15  lr: 0.000285  min_lr: 0.000285  loss: 2.0689 (2.0793)  weight_decay: 0.0500 (0.0500)  time: 0.4343  data: 0.0009  max mem: 42573
Epoch: [251]  [290/312]  eta: 0:00:10  lr: 0.000285  min_lr: 0.000285  loss: 2.2241 (2.0822)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0008  max mem: 42573
Epoch: [251]  [300/312]  eta: 0:00:05  lr: 0.000284  min_lr: 0.000284  loss: 2.1469 (2.0844)  weight_decay: 0.0500 (0.0500)  time: 0.4322  data: 0.0001  max mem: 42573
Epoch: [251]  [310/312]  eta: 0:00:00  lr: 0.000284  min_lr: 0.000284  loss: 2.0178 (2.0786)  weight_decay: 0.0500 (0.0500)  time: 0.4320  data: 0.0001  max mem: 42573
Epoch: [251]  [311/312]  eta: 0:00:00  lr: 0.000284  min_lr: 0.000284  loss: 2.0178 (2.0809)  weight_decay: 0.0500 (0.0500)  time: 0.4320  data: 0.0001  max mem: 42573
Epoch: [251] Total time: 0:02:28 (0.4748 s / it)
Averaged stats: lr: 0.000284  min_lr: 0.000284  loss: 2.0178 (2.1023)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:00:41  loss: 0.5927 (0.5927)  acc1: 84.8958 (84.8958)  acc5: 95.5729 (95.5729)  time: 4.6171  data: 4.5090  max mem: 42573
Test:  [8/9]  eta: 0:00:00  loss: 0.7840 (0.7873)  acc1: 79.9479 (79.2000)  acc5: 95.3125 (94.5600)  time: 0.5901  data: 0.5011  max mem: 42573
Test: Total time: 0:00:05 (0.6090 s / it)
* Acc@1 79.718 Acc@5 94.782 loss 0.773
Accuracy of the model on the 50000 test images: 79.7%
Max accuracy: 79.86%
Epoch: [252]  [  0/312]  eta: 0:48:15  lr: 0.000284  min_lr: 0.000284  loss: 2.0508 (2.0508)  weight_decay: 0.0500 (0.0500)  time: 9.2796  data: 6.5370  max mem: 42573
Epoch: [252]  [ 10/312]  eta: 0:07:14  lr: 0.000284  min_lr: 0.000284  loss: 2.2631 (2.1361)  weight_decay: 0.0500 (0.0500)  time: 1.4403  data: 0.5947  max mem: 42573
Epoch: [252]  [ 20/312]  eta: 0:04:40  lr: 0.000283  min_lr: 0.000283  loss: 2.2936 (2.1441)  weight_decay: 0.0500 (0.0500)  time: 0.5456  data: 0.0004  max mem: 42573
Epoch: [252]  [ 30/312]  eta: 0:03:43  lr: 0.000283  min_lr: 0.000283  loss: 2.2995 (2.1893)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0004  max mem: 42573
Epoch: [252]  [ 40/312]  eta: 0:03:12  lr: 0.000283  min_lr: 0.000283  loss: 2.1974 (2.1565)  weight_decay: 0.0500 (0.0500)  time: 0.4390  data: 0.0004  max mem: 42573
Epoch: [252]  [ 50/312]  eta: 0:02:51  lr: 0.000282  min_lr: 0.000282  loss: 2.1241 (2.1371)  weight_decay: 0.0500 (0.0500)  time: 0.4390  data: 0.0004  max mem: 42573
Epoch: [252]  [ 60/312]  eta: 0:02:35  lr: 0.000282  min_lr: 0.000282  loss: 2.1603 (2.1384)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [252]  [ 70/312]  eta: 0:02:23  lr: 0.000281  min_lr: 0.000281  loss: 2.2116 (2.1200)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [252]  [ 80/312]  eta: 0:02:12  lr: 0.000281  min_lr: 0.000281  loss: 1.9780 (2.1059)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [252]  [ 90/312]  eta: 0:02:03  lr: 0.000281  min_lr: 0.000281  loss: 1.9780 (2.0821)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [252]  [100/312]  eta: 0:01:55  lr: 0.000280  min_lr: 0.000280  loss: 2.2029 (2.0909)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [252]  [110/312]  eta: 0:01:47  lr: 0.000280  min_lr: 0.000280  loss: 2.1933 (2.0863)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [252]  [120/312]  eta: 0:01:41  lr: 0.000280  min_lr: 0.000280  loss: 2.1683 (2.1048)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [252]  [130/312]  eta: 0:01:34  lr: 0.000279  min_lr: 0.000279  loss: 2.1683 (2.0930)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [252]  [140/312]  eta: 0:01:28  lr: 0.000279  min_lr: 0.000279  loss: 2.2590 (2.1095)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [252]  [150/312]  eta: 0:01:22  lr: 0.000279  min_lr: 0.000279  loss: 2.2590 (2.1082)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [252]  [160/312]  eta: 0:01:16  lr: 0.000278  min_lr: 0.000278  loss: 1.9818 (2.0989)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [252]  [170/312]  eta: 0:01:10  lr: 0.000278  min_lr: 0.000278  loss: 2.1291 (2.1072)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [252]  [180/312]  eta: 0:01:05  lr: 0.000277  min_lr: 0.000277  loss: 2.2384 (2.1126)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0003  max mem: 42573
Epoch: [252]  [190/312]  eta: 0:01:00  lr: 0.000277  min_lr: 0.000277  loss: 2.1855 (2.1113)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [252]  [200/312]  eta: 0:00:54  lr: 0.000277  min_lr: 0.000277  loss: 2.1392 (2.1114)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0003  max mem: 42573
Epoch: [252]  [210/312]  eta: 0:00:49  lr: 0.000276  min_lr: 0.000276  loss: 2.2402 (2.1152)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [252]  [220/312]  eta: 0:00:44  lr: 0.000276  min_lr: 0.000276  loss: 2.2436 (2.1115)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [252]  [230/312]  eta: 0:00:39  lr: 0.000276  min_lr: 0.000276  loss: 2.1032 (2.1094)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [252]  [240/312]  eta: 0:00:34  lr: 0.000275  min_lr: 0.000275  loss: 2.1297 (2.1065)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [252]  [250/312]  eta: 0:00:29  lr: 0.000275  min_lr: 0.000275  loss: 2.1328 (2.1074)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [252]  [260/312]  eta: 0:00:24  lr: 0.000275  min_lr: 0.000275  loss: 2.0778 (2.1076)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [252]  [270/312]  eta: 0:00:19  lr: 0.000274  min_lr: 0.000274  loss: 2.2283 (2.1104)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0003  max mem: 42573
Epoch: [252]  [280/312]  eta: 0:00:15  lr: 0.000274  min_lr: 0.000274  loss: 2.2283 (2.1090)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0009  max mem: 42573
Epoch: [252]  [290/312]  eta: 0:00:10  lr: 0.000273  min_lr: 0.000273  loss: 2.1278 (2.1067)  weight_decay: 0.0500 (0.0500)  time: 0.4332  data: 0.0008  max mem: 42573
Epoch: [252]  [300/312]  eta: 0:00:05  lr: 0.000273  min_lr: 0.000273  loss: 2.2196 (2.1121)  weight_decay: 0.0500 (0.0500)  time: 0.4320  data: 0.0001  max mem: 42573
Epoch: [252]  [310/312]  eta: 0:00:00  lr: 0.000273  min_lr: 0.000273  loss: 2.2721 (2.1111)  weight_decay: 0.0500 (0.0500)  time: 0.4320  data: 0.0001  max mem: 42573
Epoch: [252]  [311/312]  eta: 0:00:00  lr: 0.000273  min_lr: 0.000273  loss: 2.2627 (2.1103)  weight_decay: 0.0500 (0.0500)  time: 0.4320  data: 0.0001  max mem: 42573
Epoch: [252] Total time: 0:02:27 (0.4723 s / it)
Averaged stats: lr: 0.000273  min_lr: 0.000273  loss: 2.2627 (2.1075)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:00:41  loss: 0.5781 (0.5781)  acc1: 85.6771 (85.6771)  acc5: 96.6146 (96.6146)  time: 4.5647  data: 4.4564  max mem: 42573
Test:  [8/9]  eta: 0:00:00  loss: 0.7889 (0.7881)  acc1: 80.4688 (79.6160)  acc5: 94.7917 (94.6240)  time: 0.5827  data: 0.4952  max mem: 42573
Test: Total time: 0:00:05 (0.5929 s / it)
* Acc@1 79.808 Acc@5 94.846 loss 0.774
Accuracy of the model on the 50000 test images: 79.8%
Max accuracy: 79.86%
Epoch: [253]  [  0/312]  eta: 0:52:33  lr: 0.000273  min_lr: 0.000273  loss: 2.3704 (2.3704)  weight_decay: 0.0500 (0.0500)  time: 10.1081  data: 7.1695  max mem: 42573
Epoch: [253]  [ 10/312]  eta: 0:07:24  lr: 0.000272  min_lr: 0.000272  loss: 2.3025 (2.2450)  weight_decay: 0.0500 (0.0500)  time: 1.4728  data: 0.7018  max mem: 42573
Epoch: [253]  [ 20/312]  eta: 0:04:45  lr: 0.000272  min_lr: 0.000272  loss: 2.0014 (2.0705)  weight_decay: 0.0500 (0.0500)  time: 0.5216  data: 0.0277  max mem: 42573
Epoch: [253]  [ 30/312]  eta: 0:03:47  lr: 0.000272  min_lr: 0.000272  loss: 2.0755 (2.1008)  weight_decay: 0.0500 (0.0500)  time: 0.4390  data: 0.0004  max mem: 42573
Epoch: [253]  [ 40/312]  eta: 0:03:14  lr: 0.000271  min_lr: 0.000271  loss: 2.1640 (2.0573)  weight_decay: 0.0500 (0.0500)  time: 0.4386  data: 0.0004  max mem: 42573
Epoch: [253]  [ 50/312]  eta: 0:02:52  lr: 0.000271  min_lr: 0.000271  loss: 2.0548 (2.0556)  weight_decay: 0.0500 (0.0500)  time: 0.4332  data: 0.0004  max mem: 42573
Epoch: [253]  [ 60/312]  eta: 0:02:36  lr: 0.000270  min_lr: 0.000270  loss: 1.9529 (2.0413)  weight_decay: 0.0500 (0.0500)  time: 0.4332  data: 0.0004  max mem: 42573
Epoch: [253]  [ 70/312]  eta: 0:02:24  lr: 0.000270  min_lr: 0.000270  loss: 2.1704 (2.0742)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [253]  [ 80/312]  eta: 0:02:13  lr: 0.000270  min_lr: 0.000270  loss: 2.2049 (2.0864)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [253]  [ 90/312]  eta: 0:02:04  lr: 0.000269  min_lr: 0.000269  loss: 2.2685 (2.0993)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [253]  [100/312]  eta: 0:01:56  lr: 0.000269  min_lr: 0.000269  loss: 2.2090 (2.0974)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [253]  [110/312]  eta: 0:01:48  lr: 0.000269  min_lr: 0.000269  loss: 1.9334 (2.0783)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [253]  [120/312]  eta: 0:01:41  lr: 0.000268  min_lr: 0.000268  loss: 1.8524 (2.0736)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [253]  [130/312]  eta: 0:01:34  lr: 0.000268  min_lr: 0.000268  loss: 2.0383 (2.0810)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [253]  [140/312]  eta: 0:01:28  lr: 0.000268  min_lr: 0.000268  loss: 2.0383 (2.0728)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [253]  [150/312]  eta: 0:01:22  lr: 0.000267  min_lr: 0.000267  loss: 1.8391 (2.0712)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [253]  [160/312]  eta: 0:01:16  lr: 0.000267  min_lr: 0.000267  loss: 2.1467 (2.0761)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [253]  [170/312]  eta: 0:01:11  lr: 0.000267  min_lr: 0.000267  loss: 2.1809 (2.0672)  weight_decay: 0.0500 (0.0500)  time: 0.4332  data: 0.0004  max mem: 42573
Epoch: [253]  [180/312]  eta: 0:01:05  lr: 0.000266  min_lr: 0.000266  loss: 1.9207 (2.0629)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [253]  [190/312]  eta: 0:01:00  lr: 0.000266  min_lr: 0.000266  loss: 1.9207 (2.0613)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [253]  [200/312]  eta: 0:00:54  lr: 0.000265  min_lr: 0.000265  loss: 2.0650 (2.0694)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [253]  [210/312]  eta: 0:00:49  lr: 0.000265  min_lr: 0.000265  loss: 2.3296 (2.0793)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [253]  [220/312]  eta: 0:00:44  lr: 0.000265  min_lr: 0.000265  loss: 2.2868 (2.0780)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [253]  [230/312]  eta: 0:00:39  lr: 0.000264  min_lr: 0.000264  loss: 2.1989 (2.0850)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [253]  [240/312]  eta: 0:00:34  lr: 0.000264  min_lr: 0.000264  loss: 2.2931 (2.0902)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [253]  [250/312]  eta: 0:00:29  lr: 0.000264  min_lr: 0.000264  loss: 2.1013 (2.0892)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [253]  [260/312]  eta: 0:00:24  lr: 0.000263  min_lr: 0.000263  loss: 2.1067 (2.0924)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [253]  [270/312]  eta: 0:00:19  lr: 0.000263  min_lr: 0.000263  loss: 2.1285 (2.0898)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0003  max mem: 42573
Epoch: [253]  [280/312]  eta: 0:00:15  lr: 0.000263  min_lr: 0.000263  loss: 2.1809 (2.0957)  weight_decay: 0.0500 (0.0500)  time: 0.4345  data: 0.0009  max mem: 42573
Epoch: [253]  [290/312]  eta: 0:00:10  lr: 0.000262  min_lr: 0.000262  loss: 2.2552 (2.1009)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0008  max mem: 42573
Epoch: [253]  [300/312]  eta: 0:00:05  lr: 0.000262  min_lr: 0.000262  loss: 2.2023 (2.0939)  weight_decay: 0.0500 (0.0500)  time: 0.4322  data: 0.0001  max mem: 42573
Epoch: [253]  [310/312]  eta: 0:00:00  lr: 0.000262  min_lr: 0.000262  loss: 1.7608 (2.0901)  weight_decay: 0.0500 (0.0500)  time: 0.4320  data: 0.0001  max mem: 42573
Epoch: [253]  [311/312]  eta: 0:00:00  lr: 0.000261  min_lr: 0.000261  loss: 2.0928 (2.0906)  weight_decay: 0.0500 (0.0500)  time: 0.4321  data: 0.0001  max mem: 42573
Epoch: [253] Total time: 0:02:27 (0.4734 s / it)
Averaged stats: lr: 0.000261  min_lr: 0.000261  loss: 2.0928 (2.0924)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:00:42  loss: 0.5996 (0.5996)  acc1: 84.8958 (84.8958)  acc5: 96.3542 (96.3542)  time: 4.7509  data: 4.6425  max mem: 42573
Test:  [8/9]  eta: 0:00:00  loss: 0.7729 (0.7671)  acc1: 80.4688 (79.4880)  acc5: 95.5729 (95.2320)  time: 0.6037  data: 0.5159  max mem: 42573
Test: Total time: 0:00:05 (0.6245 s / it)
* Acc@1 80.142 Acc@5 94.978 loss 0.758
Accuracy of the model on the 50000 test images: 80.1%
Max accuracy: 80.14%
Epoch: [254]  [  0/312]  eta: 0:51:17  lr: 0.000261  min_lr: 0.000261  loss: 2.1534 (2.1534)  weight_decay: 0.0500 (0.0500)  time: 9.8624  data: 7.2813  max mem: 42573
Epoch: [254]  [ 10/312]  eta: 0:07:38  lr: 0.000261  min_lr: 0.000261  loss: 2.1534 (2.1053)  weight_decay: 0.0500 (0.0500)  time: 1.5175  data: 0.6881  max mem: 42573
Epoch: [254]  [ 20/312]  eta: 0:04:52  lr: 0.000261  min_lr: 0.000261  loss: 2.1631 (2.1499)  weight_decay: 0.0500 (0.0500)  time: 0.5582  data: 0.0146  max mem: 42573
Epoch: [254]  [ 30/312]  eta: 0:03:50  lr: 0.000260  min_lr: 0.000260  loss: 2.1631 (2.1837)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0005  max mem: 42573
Epoch: [254]  [ 40/312]  eta: 0:03:17  lr: 0.000260  min_lr: 0.000260  loss: 2.0475 (2.1477)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [254]  [ 50/312]  eta: 0:02:54  lr: 0.000260  min_lr: 0.000260  loss: 1.8730 (2.0844)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [254]  [ 60/312]  eta: 0:02:38  lr: 0.000259  min_lr: 0.000259  loss: 2.1406 (2.1077)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [254]  [ 70/312]  eta: 0:02:25  lr: 0.000259  min_lr: 0.000259  loss: 2.1716 (2.1091)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [254]  [ 80/312]  eta: 0:02:14  lr: 0.000259  min_lr: 0.000259  loss: 2.1716 (2.1056)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [254]  [ 90/312]  eta: 0:02:05  lr: 0.000258  min_lr: 0.000258  loss: 1.9658 (2.0838)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [254]  [100/312]  eta: 0:01:56  lr: 0.000258  min_lr: 0.000258  loss: 2.0928 (2.0890)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [254]  [110/312]  eta: 0:01:49  lr: 0.000258  min_lr: 0.000258  loss: 2.1862 (2.0967)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [254]  [120/312]  eta: 0:01:42  lr: 0.000257  min_lr: 0.000257  loss: 2.1667 (2.0995)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [254]  [130/312]  eta: 0:01:35  lr: 0.000257  min_lr: 0.000257  loss: 2.1571 (2.0918)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [254]  [140/312]  eta: 0:01:29  lr: 0.000257  min_lr: 0.000257  loss: 2.1743 (2.0935)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [254]  [150/312]  eta: 0:01:23  lr: 0.000256  min_lr: 0.000256  loss: 2.2399 (2.1013)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0003  max mem: 42573
Epoch: [254]  [160/312]  eta: 0:01:17  lr: 0.000256  min_lr: 0.000256  loss: 2.1992 (2.1017)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0003  max mem: 42573
Epoch: [254]  [170/312]  eta: 0:01:11  lr: 0.000255  min_lr: 0.000255  loss: 2.1137 (2.0994)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [254]  [180/312]  eta: 0:01:05  lr: 0.000255  min_lr: 0.000255  loss: 2.0881 (2.0943)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0003  max mem: 42573
Epoch: [254]  [190/312]  eta: 0:01:00  lr: 0.000255  min_lr: 0.000255  loss: 2.0328 (2.0875)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0003  max mem: 42573
Epoch: [254]  [200/312]  eta: 0:00:55  lr: 0.000254  min_lr: 0.000254  loss: 2.2733 (2.0956)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0003  max mem: 42573
Epoch: [254]  [210/312]  eta: 0:00:49  lr: 0.000254  min_lr: 0.000254  loss: 2.2512 (2.0938)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [254]  [220/312]  eta: 0:00:44  lr: 0.000254  min_lr: 0.000254  loss: 2.1478 (2.0988)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [254]  [230/312]  eta: 0:00:39  lr: 0.000253  min_lr: 0.000253  loss: 2.1877 (2.1027)  weight_decay: 0.0500 (0.0500)  time: 0.4348  data: 0.0004  max mem: 42573
Epoch: [254]  [240/312]  eta: 0:00:34  lr: 0.000253  min_lr: 0.000253  loss: 2.1553 (2.1048)  weight_decay: 0.0500 (0.0500)  time: 0.4350  data: 0.0004  max mem: 42573
Epoch: [254]  [250/312]  eta: 0:00:29  lr: 0.000253  min_lr: 0.000253  loss: 2.1553 (2.1014)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [254]  [260/312]  eta: 0:00:24  lr: 0.000252  min_lr: 0.000252  loss: 2.2302 (2.1065)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [254]  [270/312]  eta: 0:00:20  lr: 0.000252  min_lr: 0.000252  loss: 2.2539 (2.1103)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [254]  [280/312]  eta: 0:00:15  lr: 0.000252  min_lr: 0.000252  loss: 2.2540 (2.1162)  weight_decay: 0.0500 (0.0500)  time: 0.4348  data: 0.0009  max mem: 42573
Epoch: [254]  [290/312]  eta: 0:00:10  lr: 0.000251  min_lr: 0.000251  loss: 2.2445 (2.1175)  weight_decay: 0.0500 (0.0500)  time: 0.4343  data: 0.0008  max mem: 42573
Epoch: [254]  [300/312]  eta: 0:00:05  lr: 0.000251  min_lr: 0.000251  loss: 2.1553 (2.1187)  weight_decay: 0.0500 (0.0500)  time: 0.4324  data: 0.0001  max mem: 42573
Epoch: [254]  [310/312]  eta: 0:00:00  lr: 0.000251  min_lr: 0.000251  loss: 2.2359 (2.1188)  weight_decay: 0.0500 (0.0500)  time: 0.4322  data: 0.0001  max mem: 42573
Epoch: [254]  [311/312]  eta: 0:00:00  lr: 0.000251  min_lr: 0.000251  loss: 1.9385 (2.1165)  weight_decay: 0.0500 (0.0500)  time: 0.4322  data: 0.0001  max mem: 42573
Epoch: [254] Total time: 0:02:28 (0.4749 s / it)
Averaged stats: lr: 0.000251  min_lr: 0.000251  loss: 1.9385 (2.0959)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:00:43  loss: 0.5732 (0.5732)  acc1: 85.9375 (85.9375)  acc5: 96.6146 (96.6146)  time: 4.7983  data: 4.6898  max mem: 42573
Test:  [8/9]  eta: 0:00:00  loss: 0.7730 (0.7680)  acc1: 79.9479 (79.4880)  acc5: 95.5729 (95.2960)  time: 0.6094  data: 0.5212  max mem: 42573
Test: Total time: 0:00:05 (0.6322 s / it)
* Acc@1 80.206 Acc@5 94.962 loss 0.763
Accuracy of the model on the 50000 test images: 80.2%
Max accuracy: 80.21%
Epoch: [255]  [  0/312]  eta: 0:48:31  lr: 0.000250  min_lr: 0.000250  loss: 2.3135 (2.3135)  weight_decay: 0.0500 (0.0500)  time: 9.3313  data: 8.7366  max mem: 42573
Epoch: [255]  [ 10/312]  eta: 0:07:19  lr: 0.000250  min_lr: 0.000250  loss: 1.9731 (2.0154)  weight_decay: 0.0500 (0.0500)  time: 1.4564  data: 0.8221  max mem: 42573
Epoch: [255]  [ 20/312]  eta: 0:04:43  lr: 0.000250  min_lr: 0.000250  loss: 1.7007 (1.8801)  weight_decay: 0.0500 (0.0500)  time: 0.5511  data: 0.0155  max mem: 42573
Epoch: [255]  [ 30/312]  eta: 0:03:44  lr: 0.000249  min_lr: 0.000249  loss: 1.9413 (1.9508)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0004  max mem: 42573
Epoch: [255]  [ 40/312]  eta: 0:03:12  lr: 0.000249  min_lr: 0.000249  loss: 2.1125 (1.9544)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0004  max mem: 42573
Epoch: [255]  [ 50/312]  eta: 0:02:51  lr: 0.000249  min_lr: 0.000249  loss: 2.0790 (1.9938)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [255]  [ 60/312]  eta: 0:02:35  lr: 0.000248  min_lr: 0.000248  loss: 2.2830 (2.0007)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [255]  [ 70/312]  eta: 0:02:23  lr: 0.000248  min_lr: 0.000248  loss: 2.0294 (2.0003)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [255]  [ 80/312]  eta: 0:02:12  lr: 0.000248  min_lr: 0.000248  loss: 1.9354 (1.9959)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [255]  [ 90/312]  eta: 0:02:03  lr: 0.000247  min_lr: 0.000247  loss: 2.1732 (2.0242)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [255]  [100/312]  eta: 0:01:55  lr: 0.000247  min_lr: 0.000247  loss: 2.1119 (2.0201)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [255]  [110/312]  eta: 0:01:48  lr: 0.000247  min_lr: 0.000247  loss: 2.1111 (2.0314)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [255]  [120/312]  eta: 0:01:41  lr: 0.000246  min_lr: 0.000246  loss: 2.1525 (2.0292)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [255]  [130/312]  eta: 0:01:34  lr: 0.000246  min_lr: 0.000246  loss: 2.1379 (2.0328)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [255]  [140/312]  eta: 0:01:28  lr: 0.000246  min_lr: 0.000246  loss: 2.1323 (2.0349)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [255]  [150/312]  eta: 0:01:22  lr: 0.000245  min_lr: 0.000245  loss: 2.1290 (2.0341)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [255]  [160/312]  eta: 0:01:16  lr: 0.000245  min_lr: 0.000245  loss: 2.1697 (2.0424)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [255]  [170/312]  eta: 0:01:10  lr: 0.000245  min_lr: 0.000245  loss: 2.2716 (2.0564)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0005  max mem: 42573
Epoch: [255]  [180/312]  eta: 0:01:05  lr: 0.000244  min_lr: 0.000244  loss: 2.2211 (2.0539)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [255]  [190/312]  eta: 0:01:00  lr: 0.000244  min_lr: 0.000244  loss: 2.1972 (2.0504)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [255]  [200/312]  eta: 0:00:54  lr: 0.000244  min_lr: 0.000244  loss: 2.0390 (2.0530)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [255]  [210/312]  eta: 0:00:49  lr: 0.000243  min_lr: 0.000243  loss: 2.0435 (2.0571)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [255]  [220/312]  eta: 0:00:44  lr: 0.000243  min_lr: 0.000243  loss: 2.0503 (2.0582)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [255]  [230/312]  eta: 0:00:39  lr: 0.000243  min_lr: 0.000243  loss: 2.2349 (2.0656)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [255]  [240/312]  eta: 0:00:34  lr: 0.000242  min_lr: 0.000242  loss: 2.3106 (2.0704)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [255]  [250/312]  eta: 0:00:29  lr: 0.000242  min_lr: 0.000242  loss: 2.1175 (2.0721)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [255]  [260/312]  eta: 0:00:24  lr: 0.000242  min_lr: 0.000242  loss: 2.1514 (2.0691)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [255]  [270/312]  eta: 0:00:19  lr: 0.000241  min_lr: 0.000241  loss: 1.9668 (2.0609)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0005  max mem: 42573
Epoch: [255]  [280/312]  eta: 0:00:15  lr: 0.000241  min_lr: 0.000241  loss: 1.9559 (2.0639)  weight_decay: 0.0500 (0.0500)  time: 0.4346  data: 0.0010  max mem: 42573
Epoch: [255]  [290/312]  eta: 0:00:10  lr: 0.000240  min_lr: 0.000240  loss: 2.2429 (2.0700)  weight_decay: 0.0500 (0.0500)  time: 0.4342  data: 0.0008  max mem: 42573
Epoch: [255]  [300/312]  eta: 0:00:05  lr: 0.000240  min_lr: 0.000240  loss: 2.2089 (2.0738)  weight_decay: 0.0500 (0.0500)  time: 0.4323  data: 0.0001  max mem: 42573
Epoch: [255]  [310/312]  eta: 0:00:00  lr: 0.000240  min_lr: 0.000240  loss: 2.2067 (2.0741)  weight_decay: 0.0500 (0.0500)  time: 0.4321  data: 0.0001  max mem: 42573
Epoch: [255]  [311/312]  eta: 0:00:00  lr: 0.000240  min_lr: 0.000240  loss: 2.2067 (2.0736)  weight_decay: 0.0500 (0.0500)  time: 0.4321  data: 0.0001  max mem: 42573
Epoch: [255] Total time: 0:02:27 (0.4724 s / it)
Averaged stats: lr: 0.000240  min_lr: 0.000240  loss: 2.2067 (2.0978)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:00:40  loss: 0.5595 (0.5595)  acc1: 83.8542 (83.8542)  acc5: 96.0938 (96.0938)  time: 4.4613  data: 4.3539  max mem: 42573
Test:  [8/9]  eta: 0:00:00  loss: 0.7644 (0.7665)  acc1: 80.9896 (79.3280)  acc5: 95.0521 (95.0080)  time: 0.5723  data: 0.4839  max mem: 42573
Test: Total time: 0:00:05 (0.5839 s / it)
* Acc@1 80.012 Acc@5 95.022 loss 0.758
Accuracy of the model on the 50000 test images: 80.0%
Max accuracy: 80.21%
Epoch: [256]  [  0/312]  eta: 0:52:18  lr: 0.000240  min_lr: 0.000240  loss: 2.1660 (2.1660)  weight_decay: 0.0500 (0.0500)  time: 10.0600  data: 8.8891  max mem: 42573
Epoch: [256]  [ 10/312]  eta: 0:07:43  lr: 0.000239  min_lr: 0.000239  loss: 2.0946 (2.0200)  weight_decay: 0.0500 (0.0500)  time: 1.5340  data: 0.8084  max mem: 42573
Epoch: [256]  [ 20/312]  eta: 0:04:54  lr: 0.000239  min_lr: 0.000239  loss: 2.0009 (2.0016)  weight_decay: 0.0500 (0.0500)  time: 0.5574  data: 0.0003  max mem: 42573
Epoch: [256]  [ 30/312]  eta: 0:03:52  lr: 0.000239  min_lr: 0.000239  loss: 1.8729 (1.9839)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0003  max mem: 42573
Epoch: [256]  [ 40/312]  eta: 0:03:18  lr: 0.000238  min_lr: 0.000238  loss: 1.9610 (2.0395)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [256]  [ 50/312]  eta: 0:02:55  lr: 0.000238  min_lr: 0.000238  loss: 2.1286 (2.0195)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [256]  [ 60/312]  eta: 0:02:39  lr: 0.000238  min_lr: 0.000238  loss: 2.0709 (2.0402)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [256]  [ 70/312]  eta: 0:02:26  lr: 0.000237  min_lr: 0.000237  loss: 2.0913 (2.0447)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [256]  [ 80/312]  eta: 0:02:15  lr: 0.000237  min_lr: 0.000237  loss: 1.9976 (2.0332)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [256]  [ 90/312]  eta: 0:02:05  lr: 0.000237  min_lr: 0.000237  loss: 2.1148 (2.0498)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0004  max mem: 42573
Epoch: [256]  [100/312]  eta: 0:01:57  lr: 0.000236  min_lr: 0.000236  loss: 2.1512 (2.0536)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [256]  [110/312]  eta: 0:01:49  lr: 0.000236  min_lr: 0.000236  loss: 2.0714 (2.0554)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [256]  [120/312]  eta: 0:01:42  lr: 0.000236  min_lr: 0.000236  loss: 2.0800 (2.0525)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [256]  [130/312]  eta: 0:01:35  lr: 0.000235  min_lr: 0.000235  loss: 1.9059 (2.0411)  weight_decay: 0.0500 (0.0500)  time: 0.4422  data: 0.0004  max mem: 42573
Epoch: [256]  [140/312]  eta: 0:01:29  lr: 0.000235  min_lr: 0.000235  loss: 2.1561 (2.0443)  weight_decay: 0.0500 (0.0500)  time: 0.4422  data: 0.0004  max mem: 42573
Epoch: [256]  [150/312]  eta: 0:01:23  lr: 0.000235  min_lr: 0.000235  loss: 2.1575 (2.0415)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [256]  [160/312]  eta: 0:01:17  lr: 0.000234  min_lr: 0.000234  loss: 2.0995 (2.0392)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0003  max mem: 42573
Epoch: [256]  [170/312]  eta: 0:01:11  lr: 0.000234  min_lr: 0.000234  loss: 2.1120 (2.0445)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [256]  [180/312]  eta: 0:01:06  lr: 0.000234  min_lr: 0.000234  loss: 2.0561 (2.0436)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [256]  [190/312]  eta: 0:01:00  lr: 0.000233  min_lr: 0.000233  loss: 2.0867 (2.0535)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0003  max mem: 42573
Epoch: [256]  [200/312]  eta: 0:00:55  lr: 0.000233  min_lr: 0.000233  loss: 1.9717 (2.0486)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0003  max mem: 42573
Epoch: [256]  [210/312]  eta: 0:00:50  lr: 0.000233  min_lr: 0.000233  loss: 1.9286 (2.0487)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [256]  [220/312]  eta: 0:00:44  lr: 0.000232  min_lr: 0.000232  loss: 2.1919 (2.0653)  weight_decay: 0.0500 (0.0500)  time: 0.4332  data: 0.0004  max mem: 42573
Epoch: [256]  [230/312]  eta: 0:00:39  lr: 0.000232  min_lr: 0.000232  loss: 2.1605 (2.0576)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [256]  [240/312]  eta: 0:00:34  lr: 0.000232  min_lr: 0.000232  loss: 1.9607 (2.0547)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [256]  [250/312]  eta: 0:00:29  lr: 0.000231  min_lr: 0.000231  loss: 2.2341 (2.0587)  weight_decay: 0.0500 (0.0500)  time: 0.4332  data: 0.0004  max mem: 42573
Epoch: [256]  [260/312]  eta: 0:00:24  lr: 0.000231  min_lr: 0.000231  loss: 2.0422 (2.0595)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [256]  [270/312]  eta: 0:00:20  lr: 0.000231  min_lr: 0.000231  loss: 2.0166 (2.0601)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [256]  [280/312]  eta: 0:00:15  lr: 0.000230  min_lr: 0.000230  loss: 2.1676 (2.0668)  weight_decay: 0.0500 (0.0500)  time: 0.4345  data: 0.0009  max mem: 42573
Epoch: [256]  [290/312]  eta: 0:00:10  lr: 0.000230  min_lr: 0.000230  loss: 2.2515 (2.0726)  weight_decay: 0.0500 (0.0500)  time: 0.4430  data: 0.0008  max mem: 42573
Epoch: [256]  [300/312]  eta: 0:00:05  lr: 0.000230  min_lr: 0.000230  loss: 2.2242 (2.0728)  weight_decay: 0.0500 (0.0500)  time: 0.4413  data: 0.0001  max mem: 42573
Epoch: [256]  [310/312]  eta: 0:00:00  lr: 0.000229  min_lr: 0.000229  loss: 1.9377 (2.0704)  weight_decay: 0.0500 (0.0500)  time: 0.4321  data: 0.0001  max mem: 42573
Epoch: [256]  [311/312]  eta: 0:00:00  lr: 0.000229  min_lr: 0.000229  loss: 1.9122 (2.0683)  weight_decay: 0.0500 (0.0500)  time: 0.4321  data: 0.0001  max mem: 42573
Epoch: [256] Total time: 0:02:28 (0.4763 s / it)
Averaged stats: lr: 0.000229  min_lr: 0.000229  loss: 1.9122 (2.0843)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:00:41  loss: 0.5535 (0.5535)  acc1: 86.9792 (86.9792)  acc5: 96.6146 (96.6146)  time: 4.5802  data: 4.4719  max mem: 42573
Test:  [8/9]  eta: 0:00:00  loss: 0.7662 (0.7672)  acc1: 80.4688 (79.9360)  acc5: 94.7917 (94.7840)  time: 0.5856  data: 0.4970  max mem: 42573
Test: Total time: 0:00:05 (0.6068 s / it)
* Acc@1 80.126 Acc@5 95.040 loss 0.753
Accuracy of the model on the 50000 test images: 80.1%
Max accuracy: 80.21%
Epoch: [257]  [  0/312]  eta: 0:52:27  lr: 0.000229  min_lr: 0.000229  loss: 2.1637 (2.1637)  weight_decay: 0.0500 (0.0500)  time: 10.0884  data: 8.5381  max mem: 42573
Epoch: [257]  [ 10/312]  eta: 0:07:54  lr: 0.000229  min_lr: 0.000229  loss: 2.1391 (2.0453)  weight_decay: 0.0500 (0.0500)  time: 1.5696  data: 0.7766  max mem: 42573
Epoch: [257]  [ 20/312]  eta: 0:05:00  lr: 0.000229  min_lr: 0.000229  loss: 2.0411 (1.9548)  weight_decay: 0.0500 (0.0500)  time: 0.5762  data: 0.0004  max mem: 42573
Epoch: [257]  [ 30/312]  eta: 0:03:56  lr: 0.000228  min_lr: 0.000228  loss: 1.9779 (1.9873)  weight_decay: 0.0500 (0.0500)  time: 0.4357  data: 0.0004  max mem: 42573
Epoch: [257]  [ 40/312]  eta: 0:03:21  lr: 0.000228  min_lr: 0.000228  loss: 2.0216 (2.0133)  weight_decay: 0.0500 (0.0500)  time: 0.4356  data: 0.0003  max mem: 42573
Epoch: [257]  [ 50/312]  eta: 0:02:58  lr: 0.000228  min_lr: 0.000228  loss: 2.2187 (2.0622)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [257]  [ 60/312]  eta: 0:02:41  lr: 0.000227  min_lr: 0.000227  loss: 2.2187 (2.0446)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [257]  [ 70/312]  eta: 0:02:27  lr: 0.000227  min_lr: 0.000227  loss: 2.0402 (2.0513)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [257]  [ 80/312]  eta: 0:02:16  lr: 0.000227  min_lr: 0.000227  loss: 2.0716 (2.0533)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [257]  [ 90/312]  eta: 0:02:06  lr: 0.000226  min_lr: 0.000226  loss: 2.1454 (2.0575)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [257]  [100/312]  eta: 0:01:58  lr: 0.000226  min_lr: 0.000226  loss: 2.1270 (2.0613)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [257]  [110/312]  eta: 0:01:50  lr: 0.000226  min_lr: 0.000226  loss: 2.2400 (2.0668)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [257]  [120/312]  eta: 0:01:43  lr: 0.000225  min_lr: 0.000225  loss: 2.2400 (2.0590)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [257]  [130/312]  eta: 0:01:36  lr: 0.000225  min_lr: 0.000225  loss: 2.1025 (2.0591)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [257]  [140/312]  eta: 0:01:29  lr: 0.000225  min_lr: 0.000225  loss: 2.1025 (2.0547)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [257]  [150/312]  eta: 0:01:23  lr: 0.000224  min_lr: 0.000224  loss: 2.0758 (2.0579)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0003  max mem: 42573
Epoch: [257]  [160/312]  eta: 0:01:17  lr: 0.000224  min_lr: 0.000224  loss: 2.0758 (2.0661)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0003  max mem: 42573
Epoch: [257]  [170/312]  eta: 0:01:11  lr: 0.000224  min_lr: 0.000224  loss: 2.2832 (2.0787)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [257]  [180/312]  eta: 0:01:06  lr: 0.000223  min_lr: 0.000223  loss: 2.2196 (2.0803)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [257]  [190/312]  eta: 0:01:00  lr: 0.000223  min_lr: 0.000223  loss: 2.0966 (2.0700)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0003  max mem: 42573
Epoch: [257]  [200/312]  eta: 0:00:55  lr: 0.000223  min_lr: 0.000223  loss: 1.9651 (2.0656)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [257]  [210/312]  eta: 0:00:50  lr: 0.000222  min_lr: 0.000222  loss: 2.0957 (2.0726)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [257]  [220/312]  eta: 0:00:45  lr: 0.000222  min_lr: 0.000222  loss: 2.2004 (2.0783)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [257]  [230/312]  eta: 0:00:40  lr: 0.000222  min_lr: 0.000222  loss: 2.2326 (2.0826)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [257]  [240/312]  eta: 0:00:34  lr: 0.000221  min_lr: 0.000221  loss: 2.2701 (2.0941)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [257]  [250/312]  eta: 0:00:29  lr: 0.000221  min_lr: 0.000221  loss: 2.1293 (2.0861)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [257]  [260/312]  eta: 0:00:25  lr: 0.000221  min_lr: 0.000221  loss: 1.7452 (2.0773)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [257]  [270/312]  eta: 0:00:20  lr: 0.000220  min_lr: 0.000220  loss: 2.0314 (2.0795)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [257]  [280/312]  eta: 0:00:15  lr: 0.000220  min_lr: 0.000220  loss: 2.1235 (2.0713)  weight_decay: 0.0500 (0.0500)  time: 0.4344  data: 0.0010  max mem: 42573
Epoch: [257]  [290/312]  eta: 0:00:10  lr: 0.000220  min_lr: 0.000220  loss: 1.9956 (2.0729)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0008  max mem: 42573
Epoch: [257]  [300/312]  eta: 0:00:05  lr: 0.000219  min_lr: 0.000219  loss: 2.2359 (2.0769)  weight_decay: 0.0500 (0.0500)  time: 0.4322  data: 0.0001  max mem: 42573
Epoch: [257]  [310/312]  eta: 0:00:00  lr: 0.000219  min_lr: 0.000219  loss: 2.1989 (2.0794)  weight_decay: 0.0500 (0.0500)  time: 0.4320  data: 0.0001  max mem: 42573
Epoch: [257]  [311/312]  eta: 0:00:00  lr: 0.000219  min_lr: 0.000219  loss: 2.1989 (2.0811)  weight_decay: 0.0500 (0.0500)  time: 0.4320  data: 0.0001  max mem: 42573
Epoch: [257] Total time: 0:02:28 (0.4767 s / it)
Averaged stats: lr: 0.000219  min_lr: 0.000219  loss: 2.1989 (2.0860)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:00:45  loss: 0.5620 (0.5620)  acc1: 86.1979 (86.1979)  acc5: 95.8333 (95.8333)  time: 5.0927  data: 4.9844  max mem: 42573
Test:  [8/9]  eta: 0:00:00  loss: 0.7729 (0.7640)  acc1: 79.9479 (79.5520)  acc5: 95.8333 (95.0400)  time: 0.6422  data: 0.5539  max mem: 42573
Test: Total time: 0:00:05 (0.6624 s / it)
* Acc@1 80.270 Acc@5 95.038 loss 0.751
Accuracy of the model on the 50000 test images: 80.3%
Max accuracy: 80.27%
Epoch: [258]  [  0/312]  eta: 0:52:04  lr: 0.000219  min_lr: 0.000219  loss: 2.4812 (2.4812)  weight_decay: 0.0500 (0.0500)  time: 10.0134  data: 8.5324  max mem: 42573
Epoch: [258]  [ 10/312]  eta: 0:07:16  lr: 0.000219  min_lr: 0.000219  loss: 2.0024 (1.9788)  weight_decay: 0.0500 (0.0500)  time: 1.4452  data: 0.7762  max mem: 42573
Epoch: [258]  [ 20/312]  eta: 0:04:41  lr: 0.000218  min_lr: 0.000218  loss: 2.0689 (2.0990)  weight_decay: 0.0500 (0.0500)  time: 0.5112  data: 0.0005  max mem: 42573
Epoch: [258]  [ 30/312]  eta: 0:03:43  lr: 0.000218  min_lr: 0.000218  loss: 2.2148 (2.0830)  weight_decay: 0.0500 (0.0500)  time: 0.4362  data: 0.0004  max mem: 42573
Epoch: [258]  [ 40/312]  eta: 0:03:12  lr: 0.000218  min_lr: 0.000218  loss: 2.0732 (2.0711)  weight_decay: 0.0500 (0.0500)  time: 0.4363  data: 0.0004  max mem: 42573
Epoch: [258]  [ 50/312]  eta: 0:02:51  lr: 0.000217  min_lr: 0.000217  loss: 2.0621 (2.0747)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [258]  [ 60/312]  eta: 0:02:35  lr: 0.000217  min_lr: 0.000217  loss: 1.9498 (2.0438)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [258]  [ 70/312]  eta: 0:02:23  lr: 0.000217  min_lr: 0.000217  loss: 2.2229 (2.0697)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [258]  [ 80/312]  eta: 0:02:12  lr: 0.000216  min_lr: 0.000216  loss: 2.0621 (2.0532)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [258]  [ 90/312]  eta: 0:02:03  lr: 0.000216  min_lr: 0.000216  loss: 1.9946 (2.0428)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [258]  [100/312]  eta: 0:01:55  lr: 0.000216  min_lr: 0.000216  loss: 2.0810 (2.0598)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [258]  [110/312]  eta: 0:01:48  lr: 0.000215  min_lr: 0.000215  loss: 2.2169 (2.0674)  weight_decay: 0.0500 (0.0500)  time: 0.4370  data: 0.0004  max mem: 42573
Epoch: [258]  [120/312]  eta: 0:01:41  lr: 0.000215  min_lr: 0.000215  loss: 2.0351 (2.0627)  weight_decay: 0.0500 (0.0500)  time: 0.4368  data: 0.0004  max mem: 42573
Epoch: [258]  [130/312]  eta: 0:01:34  lr: 0.000215  min_lr: 0.000215  loss: 2.1548 (2.0702)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [258]  [140/312]  eta: 0:01:28  lr: 0.000214  min_lr: 0.000214  loss: 2.1099 (2.0601)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [258]  [150/312]  eta: 0:01:22  lr: 0.000214  min_lr: 0.000214  loss: 2.0127 (2.0651)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [258]  [160/312]  eta: 0:01:16  lr: 0.000214  min_lr: 0.000214  loss: 2.2286 (2.0660)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [258]  [170/312]  eta: 0:01:10  lr: 0.000213  min_lr: 0.000213  loss: 2.2058 (2.0622)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [258]  [180/312]  eta: 0:01:05  lr: 0.000213  min_lr: 0.000213  loss: 1.8712 (2.0530)  weight_decay: 0.0500 (0.0500)  time: 0.4332  data: 0.0004  max mem: 42573
Epoch: [258]  [190/312]  eta: 0:01:00  lr: 0.000213  min_lr: 0.000213  loss: 1.7448 (2.0432)  weight_decay: 0.0500 (0.0500)  time: 0.4332  data: 0.0004  max mem: 42573
Epoch: [258]  [200/312]  eta: 0:00:54  lr: 0.000212  min_lr: 0.000212  loss: 1.9815 (2.0453)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [258]  [210/312]  eta: 0:00:49  lr: 0.000212  min_lr: 0.000212  loss: 2.0453 (2.0431)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [258]  [220/312]  eta: 0:00:44  lr: 0.000212  min_lr: 0.000212  loss: 1.9418 (2.0456)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0003  max mem: 42573
Epoch: [258]  [230/312]  eta: 0:00:39  lr: 0.000211  min_lr: 0.000211  loss: 2.0562 (2.0454)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [258]  [240/312]  eta: 0:00:34  lr: 0.000211  min_lr: 0.000211  loss: 2.2060 (2.0551)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [258]  [250/312]  eta: 0:00:29  lr: 0.000211  min_lr: 0.000211  loss: 2.2693 (2.0565)  weight_decay: 0.0500 (0.0500)  time: 0.4343  data: 0.0004  max mem: 42573
Epoch: [258]  [260/312]  eta: 0:00:24  lr: 0.000211  min_lr: 0.000211  loss: 2.1618 (2.0590)  weight_decay: 0.0500 (0.0500)  time: 0.4344  data: 0.0004  max mem: 42573
Epoch: [258]  [270/312]  eta: 0:00:19  lr: 0.000210  min_lr: 0.000210  loss: 2.1733 (2.0650)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [258]  [280/312]  eta: 0:00:15  lr: 0.000210  min_lr: 0.000210  loss: 2.1132 (2.0616)  weight_decay: 0.0500 (0.0500)  time: 0.4344  data: 0.0009  max mem: 42573
Epoch: [258]  [290/312]  eta: 0:00:10  lr: 0.000210  min_lr: 0.000210  loss: 2.1132 (2.0644)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0008  max mem: 42573
Epoch: [258]  [300/312]  eta: 0:00:05  lr: 0.000209  min_lr: 0.000209  loss: 2.2576 (2.0659)  weight_decay: 0.0500 (0.0500)  time: 0.4321  data: 0.0001  max mem: 42573
Epoch: [258]  [310/312]  eta: 0:00:00  lr: 0.000209  min_lr: 0.000209  loss: 2.2495 (2.0701)  weight_decay: 0.0500 (0.0500)  time: 0.4320  data: 0.0001  max mem: 42573
Epoch: [258]  [311/312]  eta: 0:00:00  lr: 0.000209  min_lr: 0.000209  loss: 2.2576 (2.0714)  weight_decay: 0.0500 (0.0500)  time: 0.4320  data: 0.0001  max mem: 42573
Epoch: [258] Total time: 0:02:27 (0.4727 s / it)
Averaged stats: lr: 0.000209  min_lr: 0.000209  loss: 2.2576 (2.0893)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:00:42  loss: 0.5729 (0.5729)  acc1: 85.9375 (85.9375)  acc5: 96.3542 (96.3542)  time: 4.6808  data: 4.5726  max mem: 42573
Test:  [8/9]  eta: 0:00:00  loss: 0.7759 (0.7645)  acc1: 80.7292 (79.9360)  acc5: 95.0521 (94.8800)  time: 0.5965  data: 0.5082  max mem: 42573
Test: Total time: 0:00:05 (0.6187 s / it)
* Acc@1 80.114 Acc@5 95.080 loss 0.756
Accuracy of the model on the 50000 test images: 80.1%
Max accuracy: 80.27%
Epoch: [259]  [  0/312]  eta: 0:54:09  lr: 0.000209  min_lr: 0.000209  loss: 2.5508 (2.5508)  weight_decay: 0.0500 (0.0500)  time: 10.4147  data: 8.9667  max mem: 42573
Epoch: [259]  [ 10/312]  eta: 0:07:41  lr: 0.000209  min_lr: 0.000209  loss: 2.1356 (2.0921)  weight_decay: 0.0500 (0.0500)  time: 1.5274  data: 0.8155  max mem: 42573
Epoch: [259]  [ 20/312]  eta: 0:04:53  lr: 0.000208  min_lr: 0.000208  loss: 2.1266 (2.0592)  weight_decay: 0.0500 (0.0500)  time: 0.5360  data: 0.0004  max mem: 42573
Epoch: [259]  [ 30/312]  eta: 0:03:51  lr: 0.000208  min_lr: 0.000208  loss: 1.9307 (1.9822)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [259]  [ 40/312]  eta: 0:03:17  lr: 0.000208  min_lr: 0.000208  loss: 1.9226 (2.0081)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [259]  [ 50/312]  eta: 0:02:55  lr: 0.000207  min_lr: 0.000207  loss: 2.0840 (2.0322)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [259]  [ 60/312]  eta: 0:02:38  lr: 0.000207  min_lr: 0.000207  loss: 2.1201 (2.0337)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [259]  [ 70/312]  eta: 0:02:25  lr: 0.000207  min_lr: 0.000207  loss: 1.9138 (2.0208)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [259]  [ 80/312]  eta: 0:02:15  lr: 0.000206  min_lr: 0.000206  loss: 1.9138 (2.0298)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [259]  [ 90/312]  eta: 0:02:05  lr: 0.000206  min_lr: 0.000206  loss: 2.2001 (2.0510)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [259]  [100/312]  eta: 0:01:57  lr: 0.000206  min_lr: 0.000206  loss: 2.1907 (2.0623)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [259]  [110/312]  eta: 0:01:49  lr: 0.000205  min_lr: 0.000205  loss: 2.0469 (2.0540)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [259]  [120/312]  eta: 0:01:42  lr: 0.000205  min_lr: 0.000205  loss: 2.0672 (2.0494)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [259]  [130/312]  eta: 0:01:35  lr: 0.000205  min_lr: 0.000205  loss: 2.1693 (2.0631)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [259]  [140/312]  eta: 0:01:29  lr: 0.000204  min_lr: 0.000204  loss: 2.1413 (2.0629)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [259]  [150/312]  eta: 0:01:23  lr: 0.000204  min_lr: 0.000204  loss: 2.1413 (2.0692)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [259]  [160/312]  eta: 0:01:17  lr: 0.000204  min_lr: 0.000204  loss: 2.1815 (2.0687)  weight_decay: 0.0500 (0.0500)  time: 0.4331  data: 0.0004  max mem: 42573
Epoch: [259]  [170/312]  eta: 0:01:11  lr: 0.000203  min_lr: 0.000203  loss: 2.1571 (2.0740)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [259]  [180/312]  eta: 0:01:05  lr: 0.000203  min_lr: 0.000203  loss: 2.1149 (2.0679)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [259]  [190/312]  eta: 0:01:00  lr: 0.000203  min_lr: 0.000203  loss: 1.8926 (2.0646)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [259]  [200/312]  eta: 0:00:55  lr: 0.000203  min_lr: 0.000203  loss: 2.0930 (2.0628)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [259]  [210/312]  eta: 0:00:50  lr: 0.000202  min_lr: 0.000202  loss: 2.2065 (2.0642)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [259]  [220/312]  eta: 0:00:44  lr: 0.000202  min_lr: 0.000202  loss: 2.0311 (2.0552)  weight_decay: 0.0500 (0.0500)  time: 0.4353  data: 0.0004  max mem: 42573
Epoch: [259]  [230/312]  eta: 0:00:39  lr: 0.000202  min_lr: 0.000202  loss: 1.9137 (2.0553)  weight_decay: 0.0500 (0.0500)  time: 0.4356  data: 0.0004  max mem: 42573
Epoch: [259]  [240/312]  eta: 0:00:34  lr: 0.000201  min_lr: 0.000201  loss: 2.1249 (2.0592)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [259]  [250/312]  eta: 0:00:29  lr: 0.000201  min_lr: 0.000201  loss: 2.1208 (2.0629)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [259]  [260/312]  eta: 0:00:24  lr: 0.000201  min_lr: 0.000201  loss: 2.1410 (2.0674)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [259]  [270/312]  eta: 0:00:20  lr: 0.000200  min_lr: 0.000200  loss: 2.1831 (2.0680)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [259]  [280/312]  eta: 0:00:15  lr: 0.000200  min_lr: 0.000200  loss: 2.1396 (2.0703)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0009  max mem: 42573
Epoch: [259]  [290/312]  eta: 0:00:10  lr: 0.000200  min_lr: 0.000200  loss: 2.0527 (2.0636)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0008  max mem: 42573
Epoch: [259]  [300/312]  eta: 0:00:05  lr: 0.000199  min_lr: 0.000199  loss: 1.9019 (2.0566)  weight_decay: 0.0500 (0.0500)  time: 0.4321  data: 0.0001  max mem: 42573
Epoch: [259]  [310/312]  eta: 0:00:00  lr: 0.000199  min_lr: 0.000199  loss: 2.1079 (2.0612)  weight_decay: 0.0500 (0.0500)  time: 0.4321  data: 0.0001  max mem: 42573
Epoch: [259]  [311/312]  eta: 0:00:00  lr: 0.000199  min_lr: 0.000199  loss: 2.1079 (2.0589)  weight_decay: 0.0500 (0.0500)  time: 0.4321  data: 0.0001  max mem: 42573
Epoch: [259] Total time: 0:02:28 (0.4750 s / it)
Averaged stats: lr: 0.000199  min_lr: 0.000199  loss: 2.1079 (2.0693)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:00:45  loss: 0.5668 (0.5668)  acc1: 85.4167 (85.4167)  acc5: 96.3542 (96.3542)  time: 5.0028  data: 4.8945  max mem: 42573
Test:  [8/9]  eta: 0:00:00  loss: 0.7416 (0.7627)  acc1: 80.7292 (79.8400)  acc5: 96.0938 (94.9440)  time: 0.6327  data: 0.5439  max mem: 42573
Test: Total time: 0:00:05 (0.6498 s / it)
* Acc@1 80.302 Acc@5 95.098 loss 0.748
Accuracy of the model on the 50000 test images: 80.3%
Max accuracy: 80.30%
Epoch: [260]  [  0/312]  eta: 0:50:21  lr: 0.000199  min_lr: 0.000199  loss: 2.0692 (2.0692)  weight_decay: 0.0500 (0.0500)  time: 9.6844  data: 6.6919  max mem: 42573
Epoch: [260]  [ 10/312]  eta: 0:07:09  lr: 0.000199  min_lr: 0.000199  loss: 2.2040 (2.0549)  weight_decay: 0.0500 (0.0500)  time: 1.4221  data: 0.6384  max mem: 42573
Epoch: [260]  [ 20/312]  eta: 0:04:37  lr: 0.000198  min_lr: 0.000198  loss: 2.1885 (2.0602)  weight_decay: 0.0500 (0.0500)  time: 0.5145  data: 0.0167  max mem: 42573
Epoch: [260]  [ 30/312]  eta: 0:03:41  lr: 0.000198  min_lr: 0.000198  loss: 1.9949 (1.9888)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [260]  [ 40/312]  eta: 0:03:10  lr: 0.000198  min_lr: 0.000198  loss: 1.9949 (2.0173)  weight_decay: 0.0500 (0.0500)  time: 0.4342  data: 0.0005  max mem: 42573
Epoch: [260]  [ 50/312]  eta: 0:02:49  lr: 0.000197  min_lr: 0.000197  loss: 2.2310 (2.0642)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [260]  [ 60/312]  eta: 0:02:34  lr: 0.000197  min_lr: 0.000197  loss: 2.2028 (2.0489)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [260]  [ 70/312]  eta: 0:02:21  lr: 0.000197  min_lr: 0.000197  loss: 2.2146 (2.0698)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [260]  [ 80/312]  eta: 0:02:11  lr: 0.000197  min_lr: 0.000197  loss: 2.1353 (2.0518)  weight_decay: 0.0500 (0.0500)  time: 0.4332  data: 0.0004  max mem: 42573
Epoch: [260]  [ 90/312]  eta: 0:02:02  lr: 0.000196  min_lr: 0.000196  loss: 1.8358 (2.0386)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [260]  [100/312]  eta: 0:01:54  lr: 0.000196  min_lr: 0.000196  loss: 2.1785 (2.0548)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [260]  [110/312]  eta: 0:01:47  lr: 0.000196  min_lr: 0.000196  loss: 2.2363 (2.0592)  weight_decay: 0.0500 (0.0500)  time: 0.4381  data: 0.0004  max mem: 42573
Epoch: [260]  [120/312]  eta: 0:01:40  lr: 0.000195  min_lr: 0.000195  loss: 2.1708 (2.0670)  weight_decay: 0.0500 (0.0500)  time: 0.4380  data: 0.0004  max mem: 42573
Epoch: [260]  [130/312]  eta: 0:01:34  lr: 0.000195  min_lr: 0.000195  loss: 2.1708 (2.0723)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [260]  [140/312]  eta: 0:01:27  lr: 0.000195  min_lr: 0.000195  loss: 2.1505 (2.0732)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [260]  [150/312]  eta: 0:01:21  lr: 0.000194  min_lr: 0.000194  loss: 2.1723 (2.0711)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [260]  [160/312]  eta: 0:01:16  lr: 0.000194  min_lr: 0.000194  loss: 1.9629 (2.0653)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [260]  [170/312]  eta: 0:01:10  lr: 0.000194  min_lr: 0.000194  loss: 2.1278 (2.0742)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [260]  [180/312]  eta: 0:01:05  lr: 0.000193  min_lr: 0.000193  loss: 2.1118 (2.0655)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [260]  [190/312]  eta: 0:00:59  lr: 0.000193  min_lr: 0.000193  loss: 2.1118 (2.0672)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [260]  [200/312]  eta: 0:00:54  lr: 0.000193  min_lr: 0.000193  loss: 2.2518 (2.0710)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [260]  [210/312]  eta: 0:00:49  lr: 0.000193  min_lr: 0.000193  loss: 2.1939 (2.0666)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [260]  [220/312]  eta: 0:00:44  lr: 0.000192  min_lr: 0.000192  loss: 1.5315 (2.0510)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [260]  [230/312]  eta: 0:00:39  lr: 0.000192  min_lr: 0.000192  loss: 1.9583 (2.0552)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [260]  [240/312]  eta: 0:00:34  lr: 0.000192  min_lr: 0.000192  loss: 2.1175 (2.0558)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [260]  [250/312]  eta: 0:00:29  lr: 0.000191  min_lr: 0.000191  loss: 2.0761 (2.0549)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0003  max mem: 42573
Epoch: [260]  [260/312]  eta: 0:00:24  lr: 0.000191  min_lr: 0.000191  loss: 2.0560 (2.0534)  weight_decay: 0.0500 (0.0500)  time: 0.4375  data: 0.0003  max mem: 42573
Epoch: [260]  [270/312]  eta: 0:00:19  lr: 0.000191  min_lr: 0.000191  loss: 2.1741 (2.0579)  weight_decay: 0.0500 (0.0500)  time: 0.4374  data: 0.0004  max mem: 42573
Epoch: [260]  [280/312]  eta: 0:00:15  lr: 0.000190  min_lr: 0.000190  loss: 2.2012 (2.0624)  weight_decay: 0.0500 (0.0500)  time: 0.4344  data: 0.0009  max mem: 42573
Epoch: [260]  [290/312]  eta: 0:00:10  lr: 0.000190  min_lr: 0.000190  loss: 2.2012 (2.0657)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0008  max mem: 42573
Epoch: [260]  [300/312]  eta: 0:00:05  lr: 0.000190  min_lr: 0.000190  loss: 2.2221 (2.0669)  weight_decay: 0.0500 (0.0500)  time: 0.4321  data: 0.0001  max mem: 42573
Epoch: [260]  [310/312]  eta: 0:00:00  lr: 0.000189  min_lr: 0.000189  loss: 2.0315 (2.0625)  weight_decay: 0.0500 (0.0500)  time: 0.4321  data: 0.0001  max mem: 42573
Epoch: [260]  [311/312]  eta: 0:00:00  lr: 0.000189  min_lr: 0.000189  loss: 2.1046 (2.0629)  weight_decay: 0.0500 (0.0500)  time: 0.4321  data: 0.0001  max mem: 42573
Epoch: [260] Total time: 0:02:27 (0.4719 s / it)
Averaged stats: lr: 0.000189  min_lr: 0.000189  loss: 2.1046 (2.0691)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:00:42  loss: 0.5702 (0.5702)  acc1: 86.4583 (86.4583)  acc5: 96.3542 (96.3542)  time: 4.6707  data: 4.5623  max mem: 42573
Test:  [8/9]  eta: 0:00:00  loss: 0.7465 (0.7575)  acc1: 81.7708 (79.6160)  acc5: 95.8333 (95.2960)  time: 0.5940  data: 0.5070  max mem: 42573
Test: Total time: 0:00:05 (0.6030 s / it)
* Acc@1 80.406 Acc@5 95.210 loss 0.746
Accuracy of the model on the 50000 test images: 80.4%
Max accuracy: 80.41%
Epoch: [261]  [  0/312]  eta: 0:49:37  lr: 0.000189  min_lr: 0.000189  loss: 1.5659 (1.5659)  weight_decay: 0.0500 (0.0500)  time: 9.5440  data: 8.8705  max mem: 42573
Epoch: [261]  [ 10/312]  eta: 0:07:25  lr: 0.000189  min_lr: 0.000189  loss: 2.1157 (2.0613)  weight_decay: 0.0500 (0.0500)  time: 1.4765  data: 0.8068  max mem: 42573
Epoch: [261]  [ 20/312]  eta: 0:04:46  lr: 0.000189  min_lr: 0.000189  loss: 2.0404 (2.0414)  weight_decay: 0.0500 (0.0500)  time: 0.5514  data: 0.0004  max mem: 42573
Epoch: [261]  [ 30/312]  eta: 0:03:46  lr: 0.000188  min_lr: 0.000188  loss: 2.0732 (2.0674)  weight_decay: 0.0500 (0.0500)  time: 0.4332  data: 0.0003  max mem: 42573
Epoch: [261]  [ 40/312]  eta: 0:03:13  lr: 0.000188  min_lr: 0.000188  loss: 2.0732 (2.0203)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0003  max mem: 42573
Epoch: [261]  [ 50/312]  eta: 0:02:52  lr: 0.000188  min_lr: 0.000188  loss: 1.9018 (2.0190)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [261]  [ 60/312]  eta: 0:02:36  lr: 0.000188  min_lr: 0.000188  loss: 2.1165 (2.0359)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [261]  [ 70/312]  eta: 0:02:23  lr: 0.000187  min_lr: 0.000187  loss: 2.0498 (2.0190)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [261]  [ 80/312]  eta: 0:02:13  lr: 0.000187  min_lr: 0.000187  loss: 1.9824 (2.0177)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0003  max mem: 42573
Epoch: [261]  [ 90/312]  eta: 0:02:04  lr: 0.000187  min_lr: 0.000187  loss: 2.1188 (2.0333)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [261]  [100/312]  eta: 0:01:55  lr: 0.000186  min_lr: 0.000186  loss: 2.2042 (2.0204)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [261]  [110/312]  eta: 0:01:48  lr: 0.000186  min_lr: 0.000186  loss: 2.1484 (2.0305)  weight_decay: 0.0500 (0.0500)  time: 0.4332  data: 0.0004  max mem: 42573
Epoch: [261]  [120/312]  eta: 0:01:41  lr: 0.000186  min_lr: 0.000186  loss: 2.2342 (2.0393)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [261]  [130/312]  eta: 0:01:34  lr: 0.000185  min_lr: 0.000185  loss: 2.2337 (2.0514)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [261]  [140/312]  eta: 0:01:28  lr: 0.000185  min_lr: 0.000185  loss: 2.2337 (2.0595)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [261]  [150/312]  eta: 0:01:22  lr: 0.000185  min_lr: 0.000185  loss: 1.9959 (2.0454)  weight_decay: 0.0500 (0.0500)  time: 0.4425  data: 0.0004  max mem: 42573
Epoch: [261]  [160/312]  eta: 0:01:16  lr: 0.000185  min_lr: 0.000185  loss: 1.9730 (2.0520)  weight_decay: 0.0500 (0.0500)  time: 0.4425  data: 0.0004  max mem: 42573
Epoch: [261]  [170/312]  eta: 0:01:11  lr: 0.000184  min_lr: 0.000184  loss: 1.9512 (2.0413)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [261]  [180/312]  eta: 0:01:05  lr: 0.000184  min_lr: 0.000184  loss: 1.9095 (2.0414)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [261]  [190/312]  eta: 0:01:00  lr: 0.000184  min_lr: 0.000184  loss: 2.1722 (2.0471)  weight_decay: 0.0500 (0.0500)  time: 0.4332  data: 0.0004  max mem: 42573
Epoch: [261]  [200/312]  eta: 0:00:55  lr: 0.000183  min_lr: 0.000183  loss: 2.1125 (2.0375)  weight_decay: 0.0500 (0.0500)  time: 0.4332  data: 0.0003  max mem: 42573
Epoch: [261]  [210/312]  eta: 0:00:49  lr: 0.000183  min_lr: 0.000183  loss: 1.9381 (2.0351)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0003  max mem: 42573
Epoch: [261]  [220/312]  eta: 0:00:44  lr: 0.000183  min_lr: 0.000183  loss: 2.2414 (2.0423)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [261]  [230/312]  eta: 0:00:39  lr: 0.000182  min_lr: 0.000182  loss: 2.2504 (2.0455)  weight_decay: 0.0500 (0.0500)  time: 0.4331  data: 0.0004  max mem: 42573
Epoch: [261]  [240/312]  eta: 0:00:34  lr: 0.000182  min_lr: 0.000182  loss: 2.1302 (2.0492)  weight_decay: 0.0500 (0.0500)  time: 0.4332  data: 0.0005  max mem: 42573
Epoch: [261]  [250/312]  eta: 0:00:29  lr: 0.000182  min_lr: 0.000182  loss: 2.0097 (2.0464)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0005  max mem: 42573
Epoch: [261]  [260/312]  eta: 0:00:24  lr: 0.000182  min_lr: 0.000182  loss: 2.0385 (2.0475)  weight_decay: 0.0500 (0.0500)  time: 0.4364  data: 0.0004  max mem: 42573
Epoch: [261]  [270/312]  eta: 0:00:20  lr: 0.000181  min_lr: 0.000181  loss: 2.1742 (2.0425)  weight_decay: 0.0500 (0.0500)  time: 0.4363  data: 0.0004  max mem: 42573
Epoch: [261]  [280/312]  eta: 0:00:15  lr: 0.000181  min_lr: 0.000181  loss: 2.1578 (2.0433)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0010  max mem: 42573
Epoch: [261]  [290/312]  eta: 0:00:10  lr: 0.000181  min_lr: 0.000181  loss: 2.1846 (2.0481)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0008  max mem: 42573
Epoch: [261]  [300/312]  eta: 0:00:05  lr: 0.000180  min_lr: 0.000180  loss: 2.2578 (2.0498)  weight_decay: 0.0500 (0.0500)  time: 0.4320  data: 0.0001  max mem: 42573
Epoch: [261]  [310/312]  eta: 0:00:00  lr: 0.000180  min_lr: 0.000180  loss: 2.3102 (2.0579)  weight_decay: 0.0500 (0.0500)  time: 0.4320  data: 0.0001  max mem: 42573
Epoch: [261]  [311/312]  eta: 0:00:00  lr: 0.000180  min_lr: 0.000180  loss: 2.3100 (2.0586)  weight_decay: 0.0500 (0.0500)  time: 0.4320  data: 0.0001  max mem: 42573
Epoch: [261] Total time: 0:02:27 (0.4740 s / it)
Averaged stats: lr: 0.000180  min_lr: 0.000180  loss: 2.3100 (2.0788)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:00:42  loss: 0.5887 (0.5887)  acc1: 85.4167 (85.4167)  acc5: 96.3542 (96.3542)  time: 4.7169  data: 4.6087  max mem: 42573
Test:  [8/9]  eta: 0:00:00  loss: 0.7497 (0.7612)  acc1: 80.4688 (79.8400)  acc5: 95.5729 (95.1680)  time: 0.6008  data: 0.5121  max mem: 42573
Test: Total time: 0:00:05 (0.6237 s / it)
* Acc@1 80.268 Acc@5 95.132 loss 0.751
Accuracy of the model on the 50000 test images: 80.3%
Max accuracy: 80.41%
Epoch: [262]  [  0/312]  eta: 0:50:32  lr: 0.000180  min_lr: 0.000180  loss: 2.2614 (2.2614)  weight_decay: 0.0500 (0.0500)  time: 9.7199  data: 6.1545  max mem: 42573
Epoch: [262]  [ 10/312]  eta: 0:07:22  lr: 0.000180  min_lr: 0.000180  loss: 2.2614 (2.1626)  weight_decay: 0.0500 (0.0500)  time: 1.4664  data: 0.7184  max mem: 42573
Epoch: [262]  [ 20/312]  eta: 0:04:44  lr: 0.000179  min_lr: 0.000179  loss: 2.1441 (2.1100)  weight_decay: 0.0500 (0.0500)  time: 0.5375  data: 0.0876  max mem: 42573
Epoch: [262]  [ 30/312]  eta: 0:03:45  lr: 0.000179  min_lr: 0.000179  loss: 2.1150 (2.1056)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0004  max mem: 42573
Epoch: [262]  [ 40/312]  eta: 0:03:13  lr: 0.000179  min_lr: 0.000179  loss: 2.0814 (2.0814)  weight_decay: 0.0500 (0.0500)  time: 0.4344  data: 0.0004  max mem: 42573
Epoch: [262]  [ 50/312]  eta: 0:02:52  lr: 0.000179  min_lr: 0.000179  loss: 2.0929 (2.0859)  weight_decay: 0.0500 (0.0500)  time: 0.4342  data: 0.0004  max mem: 42573
Epoch: [262]  [ 60/312]  eta: 0:02:36  lr: 0.000178  min_lr: 0.000178  loss: 2.1706 (2.0796)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [262]  [ 70/312]  eta: 0:02:23  lr: 0.000178  min_lr: 0.000178  loss: 2.1676 (2.0730)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [262]  [ 80/312]  eta: 0:02:13  lr: 0.000178  min_lr: 0.000178  loss: 2.1369 (2.0826)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [262]  [ 90/312]  eta: 0:02:04  lr: 0.000177  min_lr: 0.000177  loss: 2.0903 (2.0813)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [262]  [100/312]  eta: 0:01:55  lr: 0.000177  min_lr: 0.000177  loss: 2.1914 (2.0876)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [262]  [110/312]  eta: 0:01:48  lr: 0.000177  min_lr: 0.000177  loss: 2.1914 (2.0890)  weight_decay: 0.0500 (0.0500)  time: 0.4428  data: 0.0004  max mem: 42573
Epoch: [262]  [120/312]  eta: 0:01:41  lr: 0.000176  min_lr: 0.000176  loss: 2.1249 (2.0988)  weight_decay: 0.0500 (0.0500)  time: 0.4428  data: 0.0004  max mem: 42573
Epoch: [262]  [130/312]  eta: 0:01:34  lr: 0.000176  min_lr: 0.000176  loss: 2.1681 (2.1040)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [262]  [140/312]  eta: 0:01:28  lr: 0.000176  min_lr: 0.000176  loss: 2.2055 (2.1057)  weight_decay: 0.0500 (0.0500)  time: 0.4331  data: 0.0004  max mem: 42573
Epoch: [262]  [150/312]  eta: 0:01:22  lr: 0.000176  min_lr: 0.000176  loss: 2.2528 (2.1081)  weight_decay: 0.0500 (0.0500)  time: 0.4331  data: 0.0004  max mem: 42573
Epoch: [262]  [160/312]  eta: 0:01:16  lr: 0.000175  min_lr: 0.000175  loss: 2.2805 (2.1155)  weight_decay: 0.0500 (0.0500)  time: 0.4332  data: 0.0004  max mem: 42573
Epoch: [262]  [170/312]  eta: 0:01:11  lr: 0.000175  min_lr: 0.000175  loss: 2.2360 (2.1201)  weight_decay: 0.0500 (0.0500)  time: 0.4332  data: 0.0004  max mem: 42573
Epoch: [262]  [180/312]  eta: 0:01:05  lr: 0.000175  min_lr: 0.000175  loss: 2.2360 (2.1275)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [262]  [190/312]  eta: 0:01:00  lr: 0.000174  min_lr: 0.000174  loss: 2.2934 (2.1297)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [262]  [200/312]  eta: 0:00:54  lr: 0.000174  min_lr: 0.000174  loss: 2.0865 (2.1214)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [262]  [210/312]  eta: 0:00:49  lr: 0.000174  min_lr: 0.000174  loss: 1.9421 (2.1224)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [262]  [220/312]  eta: 0:00:44  lr: 0.000174  min_lr: 0.000174  loss: 2.0285 (2.1180)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [262]  [230/312]  eta: 0:00:39  lr: 0.000173  min_lr: 0.000173  loss: 2.1383 (2.1192)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [262]  [240/312]  eta: 0:00:34  lr: 0.000173  min_lr: 0.000173  loss: 2.1891 (2.1197)  weight_decay: 0.0500 (0.0500)  time: 0.4332  data: 0.0004  max mem: 42573
Epoch: [262]  [250/312]  eta: 0:00:29  lr: 0.000173  min_lr: 0.000173  loss: 1.9258 (2.1104)  weight_decay: 0.0500 (0.0500)  time: 0.4332  data: 0.0004  max mem: 42573
Epoch: [262]  [260/312]  eta: 0:00:24  lr: 0.000172  min_lr: 0.000172  loss: 1.7667 (2.1072)  weight_decay: 0.0500 (0.0500)  time: 0.4331  data: 0.0004  max mem: 42573
Epoch: [262]  [270/312]  eta: 0:00:19  lr: 0.000172  min_lr: 0.000172  loss: 2.0211 (2.1057)  weight_decay: 0.0500 (0.0500)  time: 0.4332  data: 0.0004  max mem: 42573
Epoch: [262]  [280/312]  eta: 0:00:15  lr: 0.000172  min_lr: 0.000172  loss: 2.0383 (2.1047)  weight_decay: 0.0500 (0.0500)  time: 0.4342  data: 0.0009  max mem: 42573
Epoch: [262]  [290/312]  eta: 0:00:10  lr: 0.000171  min_lr: 0.000171  loss: 2.2087 (2.1072)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0008  max mem: 42573
Epoch: [262]  [300/312]  eta: 0:00:05  lr: 0.000171  min_lr: 0.000171  loss: 2.2563 (2.1064)  weight_decay: 0.0500 (0.0500)  time: 0.4321  data: 0.0001  max mem: 42573
Epoch: [262]  [310/312]  eta: 0:00:00  lr: 0.000171  min_lr: 0.000171  loss: 2.1801 (2.1065)  weight_decay: 0.0500 (0.0500)  time: 0.4321  data: 0.0001  max mem: 42573
Epoch: [262]  [311/312]  eta: 0:00:00  lr: 0.000171  min_lr: 0.000171  loss: 2.2161 (2.1070)  weight_decay: 0.0500 (0.0500)  time: 0.4321  data: 0.0001  max mem: 42573
Epoch: [262] Total time: 0:02:27 (0.4736 s / it)
Averaged stats: lr: 0.000171  min_lr: 0.000171  loss: 2.2161 (2.0735)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:00:39  loss: 0.5528 (0.5528)  acc1: 86.9792 (86.9792)  acc5: 97.1354 (97.1354)  time: 4.4220  data: 4.3142  max mem: 42573
Test:  [8/9]  eta: 0:00:00  loss: 0.7594 (0.7597)  acc1: 80.2083 (80.1280)  acc5: 95.5729 (95.1360)  time: 0.5776  data: 0.4892  max mem: 42573
Test: Total time: 0:00:05 (0.5854 s / it)
* Acc@1 80.526 Acc@5 95.162 loss 0.747
Accuracy of the model on the 50000 test images: 80.5%
Max accuracy: 80.53%
Epoch: [263]  [  0/312]  eta: 0:47:17  lr: 0.000171  min_lr: 0.000171  loss: 1.9689 (1.9689)  weight_decay: 0.0500 (0.0500)  time: 9.0936  data: 8.4973  max mem: 42573
Epoch: [263]  [ 10/312]  eta: 0:07:14  lr: 0.000171  min_lr: 0.000171  loss: 2.2867 (2.1722)  weight_decay: 0.0500 (0.0500)  time: 1.4397  data: 0.7729  max mem: 42573
Epoch: [263]  [ 20/312]  eta: 0:04:40  lr: 0.000170  min_lr: 0.000170  loss: 1.9736 (2.0577)  weight_decay: 0.0500 (0.0500)  time: 0.5536  data: 0.0004  max mem: 42573
Epoch: [263]  [ 30/312]  eta: 0:03:42  lr: 0.000170  min_lr: 0.000170  loss: 1.9736 (2.0747)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0007  max mem: 42573
Epoch: [263]  [ 40/312]  eta: 0:03:11  lr: 0.000170  min_lr: 0.000170  loss: 2.1102 (2.0453)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0008  max mem: 42573
Epoch: [263]  [ 50/312]  eta: 0:02:50  lr: 0.000169  min_lr: 0.000169  loss: 1.8762 (2.0287)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [263]  [ 60/312]  eta: 0:02:34  lr: 0.000169  min_lr: 0.000169  loss: 1.8874 (2.0125)  weight_decay: 0.0500 (0.0500)  time: 0.4332  data: 0.0004  max mem: 42573
Epoch: [263]  [ 70/312]  eta: 0:02:22  lr: 0.000169  min_lr: 0.000169  loss: 2.2413 (2.0585)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [263]  [ 80/312]  eta: 0:02:12  lr: 0.000169  min_lr: 0.000169  loss: 2.2568 (2.0584)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [263]  [ 90/312]  eta: 0:02:03  lr: 0.000168  min_lr: 0.000168  loss: 2.0206 (2.0659)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [263]  [100/312]  eta: 0:01:55  lr: 0.000168  min_lr: 0.000168  loss: 2.2292 (2.0723)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [263]  [110/312]  eta: 0:01:47  lr: 0.000168  min_lr: 0.000168  loss: 2.2292 (2.0843)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [263]  [120/312]  eta: 0:01:40  lr: 0.000167  min_lr: 0.000167  loss: 2.1438 (2.0852)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [263]  [130/312]  eta: 0:01:34  lr: 0.000167  min_lr: 0.000167  loss: 1.8706 (2.0712)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [263]  [140/312]  eta: 0:01:28  lr: 0.000167  min_lr: 0.000167  loss: 1.8201 (2.0559)  weight_decay: 0.0500 (0.0500)  time: 0.4332  data: 0.0004  max mem: 42573
Epoch: [263]  [150/312]  eta: 0:01:22  lr: 0.000167  min_lr: 0.000167  loss: 2.1170 (2.0665)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [263]  [160/312]  eta: 0:01:16  lr: 0.000166  min_lr: 0.000166  loss: 2.1422 (2.0548)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [263]  [170/312]  eta: 0:01:10  lr: 0.000166  min_lr: 0.000166  loss: 1.8573 (2.0569)  weight_decay: 0.0500 (0.0500)  time: 0.4332  data: 0.0004  max mem: 42573
Epoch: [263]  [180/312]  eta: 0:01:05  lr: 0.000166  min_lr: 0.000166  loss: 2.0207 (2.0550)  weight_decay: 0.0500 (0.0500)  time: 0.4332  data: 0.0004  max mem: 42573
Epoch: [263]  [190/312]  eta: 0:00:59  lr: 0.000165  min_lr: 0.000165  loss: 2.0645 (2.0568)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [263]  [200/312]  eta: 0:00:54  lr: 0.000165  min_lr: 0.000165  loss: 2.1795 (2.0610)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [263]  [210/312]  eta: 0:00:49  lr: 0.000165  min_lr: 0.000165  loss: 2.1795 (2.0606)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [263]  [220/312]  eta: 0:00:44  lr: 0.000165  min_lr: 0.000165  loss: 2.0729 (2.0479)  weight_decay: 0.0500 (0.0500)  time: 0.4342  data: 0.0004  max mem: 42573
Epoch: [263]  [230/312]  eta: 0:00:39  lr: 0.000164  min_lr: 0.000164  loss: 1.8021 (2.0466)  weight_decay: 0.0500 (0.0500)  time: 0.4341  data: 0.0004  max mem: 42573
Epoch: [263]  [240/312]  eta: 0:00:34  lr: 0.000164  min_lr: 0.000164  loss: 2.1481 (2.0519)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [263]  [250/312]  eta: 0:00:29  lr: 0.000164  min_lr: 0.000164  loss: 2.2084 (2.0557)  weight_decay: 0.0500 (0.0500)  time: 0.4393  data: 0.0004  max mem: 42573
Epoch: [263]  [260/312]  eta: 0:00:24  lr: 0.000163  min_lr: 0.000163  loss: 2.1414 (2.0563)  weight_decay: 0.0500 (0.0500)  time: 0.4391  data: 0.0004  max mem: 42573
Epoch: [263]  [270/312]  eta: 0:00:19  lr: 0.000163  min_lr: 0.000163  loss: 2.0599 (2.0515)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [263]  [280/312]  eta: 0:00:15  lr: 0.000163  min_lr: 0.000163  loss: 2.0799 (2.0540)  weight_decay: 0.0500 (0.0500)  time: 0.4341  data: 0.0010  max mem: 42573
Epoch: [263]  [290/312]  eta: 0:00:10  lr: 0.000163  min_lr: 0.000163  loss: 2.2475 (2.0596)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0008  max mem: 42573
Epoch: [263]  [300/312]  eta: 0:00:05  lr: 0.000162  min_lr: 0.000162  loss: 2.2475 (2.0555)  weight_decay: 0.0500 (0.0500)  time: 0.4323  data: 0.0001  max mem: 42573
Epoch: [263]  [310/312]  eta: 0:00:00  lr: 0.000162  min_lr: 0.000162  loss: 1.8099 (2.0507)  weight_decay: 0.0500 (0.0500)  time: 0.4322  data: 0.0001  max mem: 42573
Epoch: [263]  [311/312]  eta: 0:00:00  lr: 0.000162  min_lr: 0.000162  loss: 1.8099 (2.0499)  weight_decay: 0.0500 (0.0500)  time: 0.4322  data: 0.0001  max mem: 42573
Epoch: [263] Total time: 0:02:27 (0.4722 s / it)
Averaged stats: lr: 0.000162  min_lr: 0.000162  loss: 1.8099 (2.0686)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:00:41  loss: 0.5748 (0.5748)  acc1: 84.3750 (84.3750)  acc5: 96.6146 (96.6146)  time: 4.6551  data: 4.5468  max mem: 42573
Test:  [8/9]  eta: 0:00:00  loss: 0.7494 (0.7555)  acc1: 81.5104 (79.8720)  acc5: 95.5729 (95.4560)  time: 0.5934  data: 0.5053  max mem: 42573
Test: Total time: 0:00:05 (0.6071 s / it)
* Acc@1 80.504 Acc@5 95.232 loss 0.739
Accuracy of the model on the 50000 test images: 80.5%
Max accuracy: 80.53%
Epoch: [264]  [  0/312]  eta: 0:53:12  lr: 0.000162  min_lr: 0.000162  loss: 1.9978 (1.9978)  weight_decay: 0.0500 (0.0500)  time: 10.2339  data: 6.9422  max mem: 42573
Epoch: [264]  [ 10/312]  eta: 0:07:13  lr: 0.000162  min_lr: 0.000162  loss: 1.9978 (2.0353)  weight_decay: 0.0500 (0.0500)  time: 1.4360  data: 0.6814  max mem: 42573
Epoch: [264]  [ 20/312]  eta: 0:04:40  lr: 0.000161  min_lr: 0.000161  loss: 1.9515 (1.9696)  weight_decay: 0.0500 (0.0500)  time: 0.4956  data: 0.0279  max mem: 42573
Epoch: [264]  [ 30/312]  eta: 0:03:42  lr: 0.000161  min_lr: 0.000161  loss: 2.0191 (1.9919)  weight_decay: 0.0500 (0.0500)  time: 0.4344  data: 0.0004  max mem: 42573
Epoch: [264]  [ 40/312]  eta: 0:03:11  lr: 0.000161  min_lr: 0.000161  loss: 2.0191 (1.9843)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0005  max mem: 42573
Epoch: [264]  [ 50/312]  eta: 0:02:50  lr: 0.000160  min_lr: 0.000160  loss: 2.0719 (2.0154)  weight_decay: 0.0500 (0.0500)  time: 0.4329  data: 0.0004  max mem: 42573
Epoch: [264]  [ 60/312]  eta: 0:02:34  lr: 0.000160  min_lr: 0.000160  loss: 2.1992 (2.0335)  weight_decay: 0.0500 (0.0500)  time: 0.4331  data: 0.0004  max mem: 42573
Epoch: [264]  [ 70/312]  eta: 0:02:22  lr: 0.000160  min_lr: 0.000160  loss: 2.0603 (2.0417)  weight_decay: 0.0500 (0.0500)  time: 0.4330  data: 0.0004  max mem: 42573
Epoch: [264]  [ 80/312]  eta: 0:02:12  lr: 0.000160  min_lr: 0.000160  loss: 2.0944 (2.0520)  weight_decay: 0.0500 (0.0500)  time: 0.4329  data: 0.0004  max mem: 42573
Epoch: [264]  [ 90/312]  eta: 0:02:03  lr: 0.000159  min_lr: 0.000159  loss: 2.1733 (2.0610)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [264]  [100/312]  eta: 0:01:55  lr: 0.000159  min_lr: 0.000159  loss: 2.0910 (2.0487)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [264]  [110/312]  eta: 0:01:47  lr: 0.000159  min_lr: 0.000159  loss: 1.9283 (2.0417)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [264]  [120/312]  eta: 0:01:40  lr: 0.000159  min_lr: 0.000159  loss: 2.1219 (2.0379)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [264]  [130/312]  eta: 0:01:34  lr: 0.000158  min_lr: 0.000158  loss: 1.9274 (2.0212)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [264]  [140/312]  eta: 0:01:28  lr: 0.000158  min_lr: 0.000158  loss: 1.9492 (2.0249)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [264]  [150/312]  eta: 0:01:22  lr: 0.000158  min_lr: 0.000158  loss: 2.2129 (2.0327)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [264]  [160/312]  eta: 0:01:16  lr: 0.000157  min_lr: 0.000157  loss: 2.2129 (2.0340)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [264]  [170/312]  eta: 0:01:10  lr: 0.000157  min_lr: 0.000157  loss: 2.1410 (2.0487)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0003  max mem: 42573
Epoch: [264]  [180/312]  eta: 0:01:05  lr: 0.000157  min_lr: 0.000157  loss: 2.1548 (2.0547)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [264]  [190/312]  eta: 0:00:59  lr: 0.000157  min_lr: 0.000157  loss: 2.0859 (2.0503)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [264]  [200/312]  eta: 0:00:54  lr: 0.000156  min_lr: 0.000156  loss: 2.0856 (2.0478)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [264]  [210/312]  eta: 0:00:49  lr: 0.000156  min_lr: 0.000156  loss: 2.1487 (2.0537)  weight_decay: 0.0500 (0.0500)  time: 0.4378  data: 0.0004  max mem: 42573
Epoch: [264]  [220/312]  eta: 0:00:44  lr: 0.000156  min_lr: 0.000156  loss: 2.0662 (2.0464)  weight_decay: 0.0500 (0.0500)  time: 0.4376  data: 0.0004  max mem: 42573
Epoch: [264]  [230/312]  eta: 0:00:39  lr: 0.000155  min_lr: 0.000155  loss: 2.0286 (2.0485)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [264]  [240/312]  eta: 0:00:34  lr: 0.000155  min_lr: 0.000155  loss: 1.9669 (2.0379)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0003  max mem: 42573
Epoch: [264]  [250/312]  eta: 0:00:29  lr: 0.000155  min_lr: 0.000155  loss: 2.0644 (2.0441)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [264]  [260/312]  eta: 0:00:24  lr: 0.000155  min_lr: 0.000155  loss: 2.2801 (2.0480)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [264]  [270/312]  eta: 0:00:19  lr: 0.000154  min_lr: 0.000154  loss: 2.2592 (2.0448)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [264]  [280/312]  eta: 0:00:15  lr: 0.000154  min_lr: 0.000154  loss: 2.0503 (2.0423)  weight_decay: 0.0500 (0.0500)  time: 0.4343  data: 0.0009  max mem: 42573
Epoch: [264]  [290/312]  eta: 0:00:10  lr: 0.000154  min_lr: 0.000154  loss: 2.1496 (2.0473)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0008  max mem: 42573
Epoch: [264]  [300/312]  eta: 0:00:05  lr: 0.000154  min_lr: 0.000154  loss: 2.1496 (2.0481)  weight_decay: 0.0500 (0.0500)  time: 0.4320  data: 0.0001  max mem: 42573
Epoch: [264]  [310/312]  eta: 0:00:00  lr: 0.000153  min_lr: 0.000153  loss: 2.1378 (2.0465)  weight_decay: 0.0500 (0.0500)  time: 0.4320  data: 0.0001  max mem: 42573
Epoch: [264]  [311/312]  eta: 0:00:00  lr: 0.000153  min_lr: 0.000153  loss: 2.1408 (2.0468)  weight_decay: 0.0500 (0.0500)  time: 0.4320  data: 0.0001  max mem: 42573
Epoch: [264] Total time: 0:02:27 (0.4720 s / it)
Averaged stats: lr: 0.000153  min_lr: 0.000153  loss: 2.1408 (2.0659)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:00:42  loss: 0.5668 (0.5668)  acc1: 86.7188 (86.7188)  acc5: 95.5729 (95.5729)  time: 4.7293  data: 4.6209  max mem: 42573
Test:  [8/9]  eta: 0:00:00  loss: 0.7525 (0.7514)  acc1: 80.7292 (79.6800)  acc5: 95.5729 (95.0400)  time: 0.6021  data: 0.5135  max mem: 42573
Test: Total time: 0:00:05 (0.6225 s / it)
* Acc@1 80.404 Acc@5 95.182 loss 0.741
Accuracy of the model on the 50000 test images: 80.4%
Max accuracy: 80.53%
Epoch: [265]  [  0/312]  eta: 0:52:15  lr: 0.000153  min_lr: 0.000153  loss: 2.4390 (2.4390)  weight_decay: 0.0500 (0.0500)  time: 10.0491  data: 8.7866  max mem: 42573
Epoch: [265]  [ 10/312]  eta: 0:07:17  lr: 0.000153  min_lr: 0.000153  loss: 1.7432 (1.8564)  weight_decay: 0.0500 (0.0500)  time: 1.4493  data: 0.7992  max mem: 42573
Epoch: [265]  [ 20/312]  eta: 0:04:42  lr: 0.000153  min_lr: 0.000153  loss: 1.8606 (1.9292)  weight_decay: 0.0500 (0.0500)  time: 0.5118  data: 0.0004  max mem: 42573
Epoch: [265]  [ 30/312]  eta: 0:03:43  lr: 0.000152  min_lr: 0.000152  loss: 2.0828 (2.0071)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [265]  [ 40/312]  eta: 0:03:12  lr: 0.000152  min_lr: 0.000152  loss: 2.1918 (2.0535)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [265]  [ 50/312]  eta: 0:02:51  lr: 0.000152  min_lr: 0.000152  loss: 2.2127 (2.0676)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0003  max mem: 42573
Epoch: [265]  [ 60/312]  eta: 0:02:35  lr: 0.000152  min_lr: 0.000152  loss: 2.1039 (2.0551)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [265]  [ 70/312]  eta: 0:02:23  lr: 0.000151  min_lr: 0.000151  loss: 2.1519 (2.0873)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [265]  [ 80/312]  eta: 0:02:12  lr: 0.000151  min_lr: 0.000151  loss: 2.2617 (2.1063)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [265]  [ 90/312]  eta: 0:02:03  lr: 0.000151  min_lr: 0.000151  loss: 2.2408 (2.0954)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [265]  [100/312]  eta: 0:01:55  lr: 0.000150  min_lr: 0.000150  loss: 1.9903 (2.0689)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0003  max mem: 42573
Epoch: [265]  [110/312]  eta: 0:01:47  lr: 0.000150  min_lr: 0.000150  loss: 1.8653 (2.0647)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [265]  [120/312]  eta: 0:01:40  lr: 0.000150  min_lr: 0.000150  loss: 2.0742 (2.0614)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [265]  [130/312]  eta: 0:01:34  lr: 0.000150  min_lr: 0.000150  loss: 2.1431 (2.0552)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [265]  [140/312]  eta: 0:01:28  lr: 0.000149  min_lr: 0.000149  loss: 2.2144 (2.0625)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0003  max mem: 42573
Epoch: [265]  [150/312]  eta: 0:01:22  lr: 0.000149  min_lr: 0.000149  loss: 2.2144 (2.0666)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [265]  [160/312]  eta: 0:01:16  lr: 0.000149  min_lr: 0.000149  loss: 2.1839 (2.0691)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [265]  [170/312]  eta: 0:01:10  lr: 0.000149  min_lr: 0.000149  loss: 2.1107 (2.0715)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [265]  [180/312]  eta: 0:01:05  lr: 0.000148  min_lr: 0.000148  loss: 2.2093 (2.0757)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0003  max mem: 42573
Epoch: [265]  [190/312]  eta: 0:01:00  lr: 0.000148  min_lr: 0.000148  loss: 2.2040 (2.0822)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [265]  [200/312]  eta: 0:00:54  lr: 0.000148  min_lr: 0.000148  loss: 2.2179 (2.0915)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [265]  [210/312]  eta: 0:00:49  lr: 0.000147  min_lr: 0.000147  loss: 2.1879 (2.0911)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [265]  [220/312]  eta: 0:00:44  lr: 0.000147  min_lr: 0.000147  loss: 2.0189 (2.0849)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [265]  [230/312]  eta: 0:00:39  lr: 0.000147  min_lr: 0.000147  loss: 2.0607 (2.0814)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [265]  [240/312]  eta: 0:00:34  lr: 0.000147  min_lr: 0.000147  loss: 1.9450 (2.0757)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [265]  [250/312]  eta: 0:00:29  lr: 0.000146  min_lr: 0.000146  loss: 1.8547 (2.0675)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [265]  [260/312]  eta: 0:00:24  lr: 0.000146  min_lr: 0.000146  loss: 2.1969 (2.0704)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [265]  [270/312]  eta: 0:00:19  lr: 0.000146  min_lr: 0.000146  loss: 2.1259 (2.0706)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0003  max mem: 42573
Epoch: [265]  [280/312]  eta: 0:00:15  lr: 0.000146  min_lr: 0.000146  loss: 2.1172 (2.0717)  weight_decay: 0.0500 (0.0500)  time: 0.4344  data: 0.0009  max mem: 42573
Epoch: [265]  [290/312]  eta: 0:00:10  lr: 0.000145  min_lr: 0.000145  loss: 2.0814 (2.0687)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0008  max mem: 42573
Epoch: [265]  [300/312]  eta: 0:00:05  lr: 0.000145  min_lr: 0.000145  loss: 1.8929 (2.0632)  weight_decay: 0.0500 (0.0500)  time: 0.4321  data: 0.0001  max mem: 42573
Epoch: [265]  [310/312]  eta: 0:00:00  lr: 0.000145  min_lr: 0.000145  loss: 2.0639 (2.0669)  weight_decay: 0.0500 (0.0500)  time: 0.4320  data: 0.0001  max mem: 42573
Epoch: [265]  [311/312]  eta: 0:00:00  lr: 0.000145  min_lr: 0.000145  loss: 2.1132 (2.0673)  weight_decay: 0.0500 (0.0500)  time: 0.4320  data: 0.0001  max mem: 42573
Epoch: [265] Total time: 0:02:27 (0.4724 s / it)
Averaged stats: lr: 0.000145  min_lr: 0.000145  loss: 2.1132 (2.0688)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:00:42  loss: 0.5581 (0.5581)  acc1: 85.6771 (85.6771)  acc5: 96.3542 (96.3542)  time: 4.7365  data: 4.6283  max mem: 42573
Test:  [8/9]  eta: 0:00:00  loss: 0.7764 (0.7509)  acc1: 80.7292 (79.5520)  acc5: 95.0521 (95.0400)  time: 0.6015  data: 0.5143  max mem: 42573
Test: Total time: 0:00:05 (0.6266 s / it)
* Acc@1 80.480 Acc@5 95.226 loss 0.742
Accuracy of the model on the 50000 test images: 80.5%
Max accuracy: 80.53%
Epoch: [266]  [  0/312]  eta: 0:51:55  lr: 0.000145  min_lr: 0.000145  loss: 2.3254 (2.3254)  weight_decay: 0.0500 (0.0500)  time: 9.9841  data: 8.2464  max mem: 42573
Epoch: [266]  [ 10/312]  eta: 0:07:41  lr: 0.000144  min_lr: 0.000144  loss: 2.2058 (2.0924)  weight_decay: 0.0500 (0.0500)  time: 1.5280  data: 0.8450  max mem: 42573
Epoch: [266]  [ 20/312]  eta: 0:04:53  lr: 0.000144  min_lr: 0.000144  loss: 2.1891 (2.1048)  weight_decay: 0.0500 (0.0500)  time: 0.5577  data: 0.0526  max mem: 42573
Epoch: [266]  [ 30/312]  eta: 0:03:51  lr: 0.000144  min_lr: 0.000144  loss: 2.0160 (2.0470)  weight_decay: 0.0500 (0.0500)  time: 0.4331  data: 0.0004  max mem: 42573
Epoch: [266]  [ 40/312]  eta: 0:03:17  lr: 0.000144  min_lr: 0.000144  loss: 1.9839 (2.0321)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [266]  [ 50/312]  eta: 0:02:55  lr: 0.000143  min_lr: 0.000143  loss: 1.9476 (1.9941)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [266]  [ 60/312]  eta: 0:02:38  lr: 0.000143  min_lr: 0.000143  loss: 1.9800 (2.0134)  weight_decay: 0.0500 (0.0500)  time: 0.4332  data: 0.0004  max mem: 42573
Epoch: [266]  [ 70/312]  eta: 0:02:25  lr: 0.000143  min_lr: 0.000143  loss: 2.1735 (2.0304)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [266]  [ 80/312]  eta: 0:02:15  lr: 0.000143  min_lr: 0.000143  loss: 2.2505 (2.0724)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [266]  [ 90/312]  eta: 0:02:05  lr: 0.000142  min_lr: 0.000142  loss: 2.1832 (2.0642)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [266]  [100/312]  eta: 0:01:57  lr: 0.000142  min_lr: 0.000142  loss: 2.1799 (2.0808)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [266]  [110/312]  eta: 0:01:49  lr: 0.000142  min_lr: 0.000142  loss: 2.2497 (2.0866)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [266]  [120/312]  eta: 0:01:42  lr: 0.000142  min_lr: 0.000142  loss: 2.2266 (2.0877)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [266]  [130/312]  eta: 0:01:35  lr: 0.000141  min_lr: 0.000141  loss: 2.2602 (2.0894)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [266]  [140/312]  eta: 0:01:29  lr: 0.000141  min_lr: 0.000141  loss: 2.1864 (2.0964)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0003  max mem: 42573
Epoch: [266]  [150/312]  eta: 0:01:23  lr: 0.000141  min_lr: 0.000141  loss: 2.2662 (2.0950)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0003  max mem: 42573
Epoch: [266]  [160/312]  eta: 0:01:17  lr: 0.000140  min_lr: 0.000140  loss: 1.9791 (2.0859)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [266]  [170/312]  eta: 0:01:11  lr: 0.000140  min_lr: 0.000140  loss: 1.9791 (2.0817)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [266]  [180/312]  eta: 0:01:05  lr: 0.000140  min_lr: 0.000140  loss: 2.1025 (2.0822)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [266]  [190/312]  eta: 0:01:00  lr: 0.000140  min_lr: 0.000140  loss: 2.0802 (2.0865)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [266]  [200/312]  eta: 0:00:55  lr: 0.000139  min_lr: 0.000139  loss: 2.1937 (2.0895)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [266]  [210/312]  eta: 0:00:50  lr: 0.000139  min_lr: 0.000139  loss: 2.1937 (2.0897)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [266]  [220/312]  eta: 0:00:44  lr: 0.000139  min_lr: 0.000139  loss: 2.1578 (2.0930)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [266]  [230/312]  eta: 0:00:39  lr: 0.000139  min_lr: 0.000139  loss: 2.1486 (2.0970)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [266]  [240/312]  eta: 0:00:34  lr: 0.000138  min_lr: 0.000138  loss: 2.1140 (2.0903)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [266]  [250/312]  eta: 0:00:29  lr: 0.000138  min_lr: 0.000138  loss: 2.0070 (2.0905)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [266]  [260/312]  eta: 0:00:24  lr: 0.000138  min_lr: 0.000138  loss: 2.1208 (2.0916)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [266]  [270/312]  eta: 0:00:20  lr: 0.000138  min_lr: 0.000138  loss: 2.1416 (2.0917)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [266]  [280/312]  eta: 0:00:15  lr: 0.000137  min_lr: 0.000137  loss: 2.0790 (2.0898)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0009  max mem: 42573
Epoch: [266]  [290/312]  eta: 0:00:10  lr: 0.000137  min_lr: 0.000137  loss: 2.0412 (2.0889)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0008  max mem: 42573
Epoch: [266]  [300/312]  eta: 0:00:05  lr: 0.000137  min_lr: 0.000137  loss: 2.0412 (2.0840)  weight_decay: 0.0500 (0.0500)  time: 0.4321  data: 0.0001  max mem: 42573
Epoch: [266]  [310/312]  eta: 0:00:00  lr: 0.000137  min_lr: 0.000137  loss: 1.8667 (2.0775)  weight_decay: 0.0500 (0.0500)  time: 0.4321  data: 0.0001  max mem: 42573
Epoch: [266]  [311/312]  eta: 0:00:00  lr: 0.000137  min_lr: 0.000137  loss: 1.8667 (2.0754)  weight_decay: 0.0500 (0.0500)  time: 0.4321  data: 0.0001  max mem: 42573
Epoch: [266] Total time: 0:02:28 (0.4751 s / it)
Averaged stats: lr: 0.000137  min_lr: 0.000137  loss: 1.8667 (2.0598)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:00:42  loss: 0.5588 (0.5588)  acc1: 85.9375 (85.9375)  acc5: 96.0938 (96.0938)  time: 4.7055  data: 4.5971  max mem: 42573
Test:  [8/9]  eta: 0:00:00  loss: 0.7472 (0.7486)  acc1: 80.7292 (80.0320)  acc5: 95.3125 (95.0720)  time: 0.5979  data: 0.5109  max mem: 42573
Test: Total time: 0:00:05 (0.6068 s / it)
* Acc@1 80.626 Acc@5 95.270 loss 0.735
Accuracy of the model on the 50000 test images: 80.6%
Max accuracy: 80.63%
Epoch: [267]  [  0/312]  eta: 0:47:04  lr: 0.000136  min_lr: 0.000136  loss: 1.6012 (1.6012)  weight_decay: 0.0500 (0.0500)  time: 9.0530  data: 7.5947  max mem: 42573
Epoch: [267]  [ 10/312]  eta: 0:07:24  lr: 0.000136  min_lr: 0.000136  loss: 2.1560 (1.9932)  weight_decay: 0.0500 (0.0500)  time: 1.4721  data: 0.7189  max mem: 42573
Epoch: [267]  [ 20/312]  eta: 0:04:45  lr: 0.000136  min_lr: 0.000136  loss: 2.1560 (2.0145)  weight_decay: 0.0500 (0.0500)  time: 0.5734  data: 0.0159  max mem: 42573
Epoch: [267]  [ 30/312]  eta: 0:03:46  lr: 0.000136  min_lr: 0.000136  loss: 2.0856 (2.0340)  weight_decay: 0.0500 (0.0500)  time: 0.4330  data: 0.0004  max mem: 42573
Epoch: [267]  [ 40/312]  eta: 0:03:13  lr: 0.000135  min_lr: 0.000135  loss: 2.1286 (2.0432)  weight_decay: 0.0500 (0.0500)  time: 0.4332  data: 0.0005  max mem: 42573
Epoch: [267]  [ 50/312]  eta: 0:02:52  lr: 0.000135  min_lr: 0.000135  loss: 2.1783 (2.0653)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [267]  [ 60/312]  eta: 0:02:36  lr: 0.000135  min_lr: 0.000135  loss: 2.0618 (2.0277)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [267]  [ 70/312]  eta: 0:02:23  lr: 0.000135  min_lr: 0.000135  loss: 2.0363 (2.0578)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [267]  [ 80/312]  eta: 0:02:13  lr: 0.000134  min_lr: 0.000134  loss: 2.2042 (2.0563)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0003  max mem: 42573
Epoch: [267]  [ 90/312]  eta: 0:02:04  lr: 0.000134  min_lr: 0.000134  loss: 2.1260 (2.0555)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [267]  [100/312]  eta: 0:01:55  lr: 0.000134  min_lr: 0.000134  loss: 2.1226 (2.0424)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [267]  [110/312]  eta: 0:01:48  lr: 0.000134  min_lr: 0.000134  loss: 2.2244 (2.0658)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [267]  [120/312]  eta: 0:01:41  lr: 0.000133  min_lr: 0.000133  loss: 2.2448 (2.0496)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [267]  [130/312]  eta: 0:01:34  lr: 0.000133  min_lr: 0.000133  loss: 1.8640 (2.0497)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [267]  [140/312]  eta: 0:01:28  lr: 0.000133  min_lr: 0.000133  loss: 1.9444 (2.0380)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [267]  [150/312]  eta: 0:01:22  lr: 0.000133  min_lr: 0.000133  loss: 2.0570 (2.0389)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [267]  [160/312]  eta: 0:01:16  lr: 0.000132  min_lr: 0.000132  loss: 2.0481 (2.0299)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0003  max mem: 42573
Epoch: [267]  [170/312]  eta: 0:01:11  lr: 0.000132  min_lr: 0.000132  loss: 1.9887 (2.0231)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [267]  [180/312]  eta: 0:01:05  lr: 0.000132  min_lr: 0.000132  loss: 2.0919 (2.0281)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [267]  [190/312]  eta: 0:01:00  lr: 0.000132  min_lr: 0.000132  loss: 2.1809 (2.0305)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [267]  [200/312]  eta: 0:00:54  lr: 0.000131  min_lr: 0.000131  loss: 2.0216 (2.0288)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0003  max mem: 42573
Epoch: [267]  [210/312]  eta: 0:00:49  lr: 0.000131  min_lr: 0.000131  loss: 2.0358 (2.0349)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0003  max mem: 42573
Epoch: [267]  [220/312]  eta: 0:00:44  lr: 0.000131  min_lr: 0.000131  loss: 2.0057 (2.0328)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [267]  [230/312]  eta: 0:00:39  lr: 0.000131  min_lr: 0.000131  loss: 2.2147 (2.0421)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [267]  [240/312]  eta: 0:00:34  lr: 0.000130  min_lr: 0.000130  loss: 2.2810 (2.0473)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [267]  [250/312]  eta: 0:00:29  lr: 0.000130  min_lr: 0.000130  loss: 2.0991 (2.0459)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [267]  [260/312]  eta: 0:00:24  lr: 0.000130  min_lr: 0.000130  loss: 2.1835 (2.0517)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [267]  [270/312]  eta: 0:00:19  lr: 0.000130  min_lr: 0.000130  loss: 2.1229 (2.0533)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [267]  [280/312]  eta: 0:00:15  lr: 0.000129  min_lr: 0.000129  loss: 2.0891 (2.0572)  weight_decay: 0.0500 (0.0500)  time: 0.4342  data: 0.0009  max mem: 42573
Epoch: [267]  [290/312]  eta: 0:00:10  lr: 0.000129  min_lr: 0.000129  loss: 2.0311 (2.0533)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0008  max mem: 42573
Epoch: [267]  [300/312]  eta: 0:00:05  lr: 0.000129  min_lr: 0.000129  loss: 2.0185 (2.0549)  weight_decay: 0.0500 (0.0500)  time: 0.4323  data: 0.0001  max mem: 42573
Epoch: [267]  [310/312]  eta: 0:00:00  lr: 0.000129  min_lr: 0.000129  loss: 2.2316 (2.0553)  weight_decay: 0.0500 (0.0500)  time: 0.4321  data: 0.0001  max mem: 42573
Epoch: [267]  [311/312]  eta: 0:00:00  lr: 0.000129  min_lr: 0.000129  loss: 2.2301 (2.0551)  weight_decay: 0.0500 (0.0500)  time: 0.4321  data: 0.0001  max mem: 42573
Epoch: [267] Total time: 0:02:27 (0.4734 s / it)
Averaged stats: lr: 0.000129  min_lr: 0.000129  loss: 2.2301 (2.0542)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:00:44  loss: 0.5563 (0.5563)  acc1: 84.6354 (84.6354)  acc5: 96.0938 (96.0938)  time: 4.9965  data: 4.8882  max mem: 42573
Test:  [8/9]  eta: 0:00:00  loss: 0.7453 (0.7461)  acc1: 81.2500 (79.8400)  acc5: 95.3125 (95.2000)  time: 0.6320  data: 0.5432  max mem: 42573
Test: Total time: 0:00:05 (0.6568 s / it)
* Acc@1 80.496 Acc@5 95.294 loss 0.739
Accuracy of the model on the 50000 test images: 80.5%
Max accuracy: 80.63%
Epoch: [268]  [  0/312]  eta: 0:53:05  lr: 0.000128  min_lr: 0.000128  loss: 1.9401 (1.9401)  weight_decay: 0.0500 (0.0500)  time: 10.2100  data: 8.2150  max mem: 42573
Epoch: [268]  [ 10/312]  eta: 0:07:31  lr: 0.000128  min_lr: 0.000128  loss: 2.0154 (1.9962)  weight_decay: 0.0500 (0.0500)  time: 1.4957  data: 0.7868  max mem: 42573
Epoch: [268]  [ 20/312]  eta: 0:04:48  lr: 0.000128  min_lr: 0.000128  loss: 2.0154 (1.9798)  weight_decay: 0.0500 (0.0500)  time: 0.5286  data: 0.0222  max mem: 42573
Epoch: [268]  [ 30/312]  eta: 0:03:48  lr: 0.000128  min_lr: 0.000128  loss: 1.9874 (1.9735)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [268]  [ 40/312]  eta: 0:03:15  lr: 0.000127  min_lr: 0.000127  loss: 1.9729 (1.9908)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [268]  [ 50/312]  eta: 0:02:53  lr: 0.000127  min_lr: 0.000127  loss: 2.1674 (2.0226)  weight_decay: 0.0500 (0.0500)  time: 0.4331  data: 0.0004  max mem: 42573
Epoch: [268]  [ 60/312]  eta: 0:02:37  lr: 0.000127  min_lr: 0.000127  loss: 2.2161 (2.0244)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [268]  [ 70/312]  eta: 0:02:24  lr: 0.000127  min_lr: 0.000127  loss: 2.2218 (2.0596)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [268]  [ 80/312]  eta: 0:02:14  lr: 0.000126  min_lr: 0.000126  loss: 2.2279 (2.0733)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [268]  [ 90/312]  eta: 0:02:04  lr: 0.000126  min_lr: 0.000126  loss: 2.1910 (2.0636)  weight_decay: 0.0500 (0.0500)  time: 0.4352  data: 0.0004  max mem: 42573
Epoch: [268]  [100/312]  eta: 0:01:56  lr: 0.000126  min_lr: 0.000126  loss: 2.1910 (2.0760)  weight_decay: 0.0500 (0.0500)  time: 0.4353  data: 0.0004  max mem: 42573
Epoch: [268]  [110/312]  eta: 0:01:48  lr: 0.000126  min_lr: 0.000126  loss: 2.1925 (2.0877)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [268]  [120/312]  eta: 0:01:41  lr: 0.000125  min_lr: 0.000125  loss: 2.1281 (2.0815)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [268]  [130/312]  eta: 0:01:35  lr: 0.000125  min_lr: 0.000125  loss: 2.1361 (2.0986)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [268]  [140/312]  eta: 0:01:28  lr: 0.000125  min_lr: 0.000125  loss: 2.2420 (2.0952)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [268]  [150/312]  eta: 0:01:22  lr: 0.000125  min_lr: 0.000125  loss: 1.9153 (2.0770)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [268]  [160/312]  eta: 0:01:16  lr: 0.000124  min_lr: 0.000124  loss: 1.9386 (2.0734)  weight_decay: 0.0500 (0.0500)  time: 0.4332  data: 0.0004  max mem: 42573
Epoch: [268]  [170/312]  eta: 0:01:11  lr: 0.000124  min_lr: 0.000124  loss: 1.9976 (2.0699)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [268]  [180/312]  eta: 0:01:05  lr: 0.000124  min_lr: 0.000124  loss: 1.9976 (2.0668)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [268]  [190/312]  eta: 0:01:00  lr: 0.000124  min_lr: 0.000124  loss: 2.0986 (2.0691)  weight_decay: 0.0500 (0.0500)  time: 0.4332  data: 0.0004  max mem: 42573
Epoch: [268]  [200/312]  eta: 0:00:55  lr: 0.000123  min_lr: 0.000123  loss: 2.0986 (2.0642)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [268]  [210/312]  eta: 0:00:49  lr: 0.000123  min_lr: 0.000123  loss: 1.8996 (2.0581)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [268]  [220/312]  eta: 0:00:44  lr: 0.000123  min_lr: 0.000123  loss: 1.8386 (2.0507)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [268]  [230/312]  eta: 0:00:39  lr: 0.000123  min_lr: 0.000123  loss: 1.8695 (2.0503)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [268]  [240/312]  eta: 0:00:34  lr: 0.000123  min_lr: 0.000123  loss: 2.1709 (2.0502)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [268]  [250/312]  eta: 0:00:29  lr: 0.000122  min_lr: 0.000122  loss: 2.1786 (2.0512)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [268]  [260/312]  eta: 0:00:24  lr: 0.000122  min_lr: 0.000122  loss: 2.1435 (2.0530)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [268]  [270/312]  eta: 0:00:20  lr: 0.000122  min_lr: 0.000122  loss: 2.1326 (2.0513)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [268]  [280/312]  eta: 0:00:15  lr: 0.000122  min_lr: 0.000122  loss: 2.2171 (2.0551)  weight_decay: 0.0500 (0.0500)  time: 0.4342  data: 0.0009  max mem: 42573
Epoch: [268]  [290/312]  eta: 0:00:10  lr: 0.000121  min_lr: 0.000121  loss: 2.1351 (2.0503)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0008  max mem: 42573
Epoch: [268]  [300/312]  eta: 0:00:05  lr: 0.000121  min_lr: 0.000121  loss: 1.9523 (2.0486)  weight_decay: 0.0500 (0.0500)  time: 0.4322  data: 0.0001  max mem: 42573
Epoch: [268]  [310/312]  eta: 0:00:00  lr: 0.000121  min_lr: 0.000121  loss: 2.1251 (2.0485)  weight_decay: 0.0500 (0.0500)  time: 0.4322  data: 0.0001  max mem: 42573
Epoch: [268]  [311/312]  eta: 0:00:00  lr: 0.000121  min_lr: 0.000121  loss: 2.1461 (2.0494)  weight_decay: 0.0500 (0.0500)  time: 0.4322  data: 0.0001  max mem: 42573
Epoch: [268] Total time: 0:02:27 (0.4741 s / it)
Averaged stats: lr: 0.000121  min_lr: 0.000121  loss: 2.1461 (2.0550)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:00:39  loss: 0.5629 (0.5629)  acc1: 85.6771 (85.6771)  acc5: 96.0938 (96.0938)  time: 4.4000  data: 4.2916  max mem: 42573
Test:  [8/9]  eta: 0:00:00  loss: 0.7448 (0.7485)  acc1: 81.5104 (79.8720)  acc5: 95.3125 (95.3600)  time: 0.5721  data: 0.4850  max mem: 42573
Test: Total time: 0:00:05 (0.5798 s / it)
* Acc@1 80.764 Acc@5 95.380 loss 0.732
Accuracy of the model on the 50000 test images: 80.8%
Max accuracy: 80.76%
Epoch: [269]  [  0/312]  eta: 0:51:48  lr: 0.000121  min_lr: 0.000121  loss: 2.3675 (2.3675)  weight_decay: 0.0500 (0.0500)  time: 9.9633  data: 8.9610  max mem: 42573
Epoch: [269]  [ 10/312]  eta: 0:07:16  lr: 0.000120  min_lr: 0.000120  loss: 2.2710 (2.0852)  weight_decay: 0.0500 (0.0500)  time: 1.4466  data: 0.8150  max mem: 42573
Epoch: [269]  [ 20/312]  eta: 0:04:41  lr: 0.000120  min_lr: 0.000120  loss: 2.1509 (2.1045)  weight_decay: 0.0500 (0.0500)  time: 0.5141  data: 0.0004  max mem: 42573
Epoch: [269]  [ 30/312]  eta: 0:03:43  lr: 0.000120  min_lr: 0.000120  loss: 2.1489 (2.0694)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [269]  [ 40/312]  eta: 0:03:11  lr: 0.000120  min_lr: 0.000120  loss: 2.0858 (2.0605)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [269]  [ 50/312]  eta: 0:02:50  lr: 0.000120  min_lr: 0.000120  loss: 2.0831 (2.0689)  weight_decay: 0.0500 (0.0500)  time: 0.4332  data: 0.0004  max mem: 42573
Epoch: [269]  [ 60/312]  eta: 0:02:35  lr: 0.000119  min_lr: 0.000119  loss: 2.0831 (2.1000)  weight_decay: 0.0500 (0.0500)  time: 0.4346  data: 0.0004  max mem: 42573
Epoch: [269]  [ 70/312]  eta: 0:02:22  lr: 0.000119  min_lr: 0.000119  loss: 1.8494 (2.0561)  weight_decay: 0.0500 (0.0500)  time: 0.4347  data: 0.0004  max mem: 42573
Epoch: [269]  [ 80/312]  eta: 0:02:12  lr: 0.000119  min_lr: 0.000119  loss: 1.7308 (2.0260)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [269]  [ 90/312]  eta: 0:02:03  lr: 0.000119  min_lr: 0.000119  loss: 1.9894 (2.0498)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [269]  [100/312]  eta: 0:01:55  lr: 0.000118  min_lr: 0.000118  loss: 2.1625 (2.0498)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [269]  [110/312]  eta: 0:01:47  lr: 0.000118  min_lr: 0.000118  loss: 2.1455 (2.0608)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [269]  [120/312]  eta: 0:01:40  lr: 0.000118  min_lr: 0.000118  loss: 2.1315 (2.0578)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [269]  [130/312]  eta: 0:01:34  lr: 0.000118  min_lr: 0.000118  loss: 1.9826 (2.0521)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [269]  [140/312]  eta: 0:01:28  lr: 0.000117  min_lr: 0.000117  loss: 2.1802 (2.0601)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [269]  [150/312]  eta: 0:01:22  lr: 0.000117  min_lr: 0.000117  loss: 2.2375 (2.0695)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [269]  [160/312]  eta: 0:01:16  lr: 0.000117  min_lr: 0.000117  loss: 1.9778 (2.0622)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [269]  [170/312]  eta: 0:01:10  lr: 0.000117  min_lr: 0.000117  loss: 1.9187 (2.0570)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [269]  [180/312]  eta: 0:01:05  lr: 0.000116  min_lr: 0.000116  loss: 2.0517 (2.0611)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [269]  [190/312]  eta: 0:01:00  lr: 0.000116  min_lr: 0.000116  loss: 2.1130 (2.0644)  weight_decay: 0.0500 (0.0500)  time: 0.4332  data: 0.0004  max mem: 42573
Epoch: [269]  [200/312]  eta: 0:00:54  lr: 0.000116  min_lr: 0.000116  loss: 2.1628 (2.0700)  weight_decay: 0.0500 (0.0500)  time: 0.4331  data: 0.0004  max mem: 42573
Epoch: [269]  [210/312]  eta: 0:00:49  lr: 0.000116  min_lr: 0.000116  loss: 2.0677 (2.0690)  weight_decay: 0.0500 (0.0500)  time: 0.4332  data: 0.0003  max mem: 42573
Epoch: [269]  [220/312]  eta: 0:00:44  lr: 0.000115  min_lr: 0.000115  loss: 1.8869 (2.0626)  weight_decay: 0.0500 (0.0500)  time: 0.4332  data: 0.0004  max mem: 42573
Epoch: [269]  [230/312]  eta: 0:00:39  lr: 0.000115  min_lr: 0.000115  loss: 2.0825 (2.0655)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [269]  [240/312]  eta: 0:00:34  lr: 0.000115  min_lr: 0.000115  loss: 2.2092 (2.0683)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [269]  [250/312]  eta: 0:00:29  lr: 0.000115  min_lr: 0.000115  loss: 2.2025 (2.0678)  weight_decay: 0.0500 (0.0500)  time: 0.4332  data: 0.0004  max mem: 42573
Epoch: [269]  [260/312]  eta: 0:00:24  lr: 0.000114  min_lr: 0.000114  loss: 2.1976 (2.0760)  weight_decay: 0.0500 (0.0500)  time: 0.4332  data: 0.0004  max mem: 42573
Epoch: [269]  [270/312]  eta: 0:00:19  lr: 0.000114  min_lr: 0.000114  loss: 2.1244 (2.0763)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [269]  [280/312]  eta: 0:00:15  lr: 0.000114  min_lr: 0.000114  loss: 1.9858 (2.0697)  weight_decay: 0.0500 (0.0500)  time: 0.4372  data: 0.0009  max mem: 42573
Epoch: [269]  [290/312]  eta: 0:00:10  lr: 0.000114  min_lr: 0.000114  loss: 2.1628 (2.0740)  weight_decay: 0.0500 (0.0500)  time: 0.4364  data: 0.0008  max mem: 42573
Epoch: [269]  [300/312]  eta: 0:00:05  lr: 0.000113  min_lr: 0.000113  loss: 2.1766 (2.0738)  weight_decay: 0.0500 (0.0500)  time: 0.4320  data: 0.0001  max mem: 42573
Epoch: [269]  [310/312]  eta: 0:00:00  lr: 0.000113  min_lr: 0.000113  loss: 2.1444 (2.0778)  weight_decay: 0.0500 (0.0500)  time: 0.4320  data: 0.0001  max mem: 42573
Epoch: [269]  [311/312]  eta: 0:00:00  lr: 0.000113  min_lr: 0.000113  loss: 2.1444 (2.0762)  weight_decay: 0.0500 (0.0500)  time: 0.4320  data: 0.0001  max mem: 42573
Epoch: [269] Total time: 0:02:27 (0.4723 s / it)
Averaged stats: lr: 0.000113  min_lr: 0.000113  loss: 2.1444 (2.0618)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:00:40  loss: 0.5608 (0.5608)  acc1: 86.9792 (86.9792)  acc5: 96.3542 (96.3542)  time: 4.5541  data: 4.4458  max mem: 42573
Test:  [8/9]  eta: 0:00:00  loss: 0.7726 (0.7501)  acc1: 81.2500 (80.3840)  acc5: 95.3125 (95.0720)  time: 0.5815  data: 0.4941  max mem: 42573
Test: Total time: 0:00:05 (0.5886 s / it)
* Acc@1 80.616 Acc@5 95.338 loss 0.737
Accuracy of the model on the 50000 test images: 80.6%
Max accuracy: 80.76%
Epoch: [270]  [  0/312]  eta: 0:48:38  lr: 0.000113  min_lr: 0.000113  loss: 2.1453 (2.1453)  weight_decay: 0.0500 (0.0500)  time: 9.3547  data: 7.8339  max mem: 42573
Epoch: [270]  [ 10/312]  eta: 0:07:04  lr: 0.000113  min_lr: 0.000113  loss: 2.2454 (2.1831)  weight_decay: 0.0500 (0.0500)  time: 1.4073  data: 0.7948  max mem: 42573
Epoch: [270]  [ 20/312]  eta: 0:04:35  lr: 0.000113  min_lr: 0.000113  loss: 2.1874 (2.1623)  weight_decay: 0.0500 (0.0500)  time: 0.5230  data: 0.0456  max mem: 42573
Epoch: [270]  [ 30/312]  eta: 0:03:39  lr: 0.000112  min_lr: 0.000112  loss: 2.1874 (2.1604)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [270]  [ 40/312]  eta: 0:03:08  lr: 0.000112  min_lr: 0.000112  loss: 2.1571 (2.1145)  weight_decay: 0.0500 (0.0500)  time: 0.4332  data: 0.0004  max mem: 42573
Epoch: [270]  [ 50/312]  eta: 0:02:48  lr: 0.000112  min_lr: 0.000112  loss: 2.0483 (2.0803)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [270]  [ 60/312]  eta: 0:02:33  lr: 0.000112  min_lr: 0.000112  loss: 2.1594 (2.0990)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [270]  [ 70/312]  eta: 0:02:21  lr: 0.000112  min_lr: 0.000112  loss: 2.2255 (2.0966)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [270]  [ 80/312]  eta: 0:02:11  lr: 0.000111  min_lr: 0.000111  loss: 1.9634 (2.0760)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [270]  [ 90/312]  eta: 0:02:02  lr: 0.000111  min_lr: 0.000111  loss: 2.1193 (2.0864)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [270]  [100/312]  eta: 0:01:54  lr: 0.000111  min_lr: 0.000111  loss: 2.1201 (2.0828)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [270]  [110/312]  eta: 0:01:47  lr: 0.000111  min_lr: 0.000111  loss: 2.1117 (2.0852)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0003  max mem: 42573
Epoch: [270]  [120/312]  eta: 0:01:40  lr: 0.000110  min_lr: 0.000110  loss: 2.1117 (2.0781)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [270]  [130/312]  eta: 0:01:33  lr: 0.000110  min_lr: 0.000110  loss: 2.0869 (2.0717)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [270]  [140/312]  eta: 0:01:27  lr: 0.000110  min_lr: 0.000110  loss: 2.0812 (2.0724)  weight_decay: 0.0500 (0.0500)  time: 0.4331  data: 0.0004  max mem: 42573
Epoch: [270]  [150/312]  eta: 0:01:21  lr: 0.000110  min_lr: 0.000110  loss: 2.0098 (2.0636)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [270]  [160/312]  eta: 0:01:15  lr: 0.000109  min_lr: 0.000109  loss: 2.0572 (2.0638)  weight_decay: 0.0500 (0.0500)  time: 0.4332  data: 0.0004  max mem: 42573
Epoch: [270]  [170/312]  eta: 0:01:10  lr: 0.000109  min_lr: 0.000109  loss: 2.1521 (2.0659)  weight_decay: 0.0500 (0.0500)  time: 0.4332  data: 0.0004  max mem: 42573
Epoch: [270]  [180/312]  eta: 0:01:05  lr: 0.000109  min_lr: 0.000109  loss: 2.1948 (2.0674)  weight_decay: 0.0500 (0.0500)  time: 0.4332  data: 0.0004  max mem: 42573
Epoch: [270]  [190/312]  eta: 0:00:59  lr: 0.000109  min_lr: 0.000109  loss: 2.2578 (2.0705)  weight_decay: 0.0500 (0.0500)  time: 0.4331  data: 0.0004  max mem: 42573
Epoch: [270]  [200/312]  eta: 0:00:54  lr: 0.000109  min_lr: 0.000109  loss: 2.2830 (2.0722)  weight_decay: 0.0500 (0.0500)  time: 0.4332  data: 0.0004  max mem: 42573
Epoch: [270]  [210/312]  eta: 0:00:49  lr: 0.000108  min_lr: 0.000108  loss: 1.8443 (2.0605)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [270]  [220/312]  eta: 0:00:44  lr: 0.000108  min_lr: 0.000108  loss: 2.1564 (2.0666)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [270]  [230/312]  eta: 0:00:39  lr: 0.000108  min_lr: 0.000108  loss: 2.2080 (2.0711)  weight_decay: 0.0500 (0.0500)  time: 0.4404  data: 0.0004  max mem: 42573
Epoch: [270]  [240/312]  eta: 0:00:34  lr: 0.000108  min_lr: 0.000108  loss: 2.1820 (2.0696)  weight_decay: 0.0500 (0.0500)  time: 0.4402  data: 0.0004  max mem: 42573
Epoch: [270]  [250/312]  eta: 0:00:29  lr: 0.000107  min_lr: 0.000107  loss: 2.1656 (2.0753)  weight_decay: 0.0500 (0.0500)  time: 0.4332  data: 0.0004  max mem: 42573
Epoch: [270]  [260/312]  eta: 0:00:24  lr: 0.000107  min_lr: 0.000107  loss: 2.1135 (2.0715)  weight_decay: 0.0500 (0.0500)  time: 0.4332  data: 0.0004  max mem: 42573
Epoch: [270]  [270/312]  eta: 0:00:19  lr: 0.000107  min_lr: 0.000107  loss: 1.9989 (2.0672)  weight_decay: 0.0500 (0.0500)  time: 0.4330  data: 0.0004  max mem: 42573
Epoch: [270]  [280/312]  eta: 0:00:15  lr: 0.000107  min_lr: 0.000107  loss: 1.9886 (2.0634)  weight_decay: 0.0500 (0.0500)  time: 0.4341  data: 0.0010  max mem: 42573
Epoch: [270]  [290/312]  eta: 0:00:10  lr: 0.000106  min_lr: 0.000106  loss: 1.9012 (2.0609)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0008  max mem: 42573
Epoch: [270]  [300/312]  eta: 0:00:05  lr: 0.000106  min_lr: 0.000106  loss: 2.1879 (2.0646)  weight_decay: 0.0500 (0.0500)  time: 0.4321  data: 0.0001  max mem: 42573
Epoch: [270]  [310/312]  eta: 0:00:00  lr: 0.000106  min_lr: 0.000106  loss: 2.0537 (2.0624)  weight_decay: 0.0500 (0.0500)  time: 0.4321  data: 0.0001  max mem: 42573
Epoch: [270]  [311/312]  eta: 0:00:00  lr: 0.000106  min_lr: 0.000106  loss: 2.1457 (2.0634)  weight_decay: 0.0500 (0.0500)  time: 0.4321  data: 0.0001  max mem: 42573
Epoch: [270] Total time: 0:02:27 (0.4712 s / it)
Averaged stats: lr: 0.000106  min_lr: 0.000106  loss: 2.1457 (2.0542)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:00:41  loss: 0.5647 (0.5647)  acc1: 86.1979 (86.1979)  acc5: 95.8333 (95.8333)  time: 4.6540  data: 4.5458  max mem: 42573
Test:  [8/9]  eta: 0:00:00  loss: 0.7517 (0.7449)  acc1: 81.2500 (80.1280)  acc5: 95.5729 (95.2000)  time: 0.5943  data: 0.5052  max mem: 42573
Test: Total time: 0:00:05 (0.6204 s / it)
* Acc@1 80.662 Acc@5 95.352 loss 0.733
Accuracy of the model on the 50000 test images: 80.7%
Max accuracy: 80.76%
Epoch: [271]  [  0/312]  eta: 0:51:44  lr: 0.000106  min_lr: 0.000106  loss: 1.7055 (1.7055)  weight_decay: 0.0500 (0.0500)  time: 9.9504  data: 7.1938  max mem: 42573
Epoch: [271]  [ 10/312]  eta: 0:07:41  lr: 0.000106  min_lr: 0.000106  loss: 1.9609 (2.0013)  weight_decay: 0.0500 (0.0500)  time: 1.5282  data: 0.7408  max mem: 42573
Epoch: [271]  [ 20/312]  eta: 0:04:53  lr: 0.000105  min_lr: 0.000105  loss: 2.1283 (2.0586)  weight_decay: 0.0500 (0.0500)  time: 0.5594  data: 0.0479  max mem: 42573
Epoch: [271]  [ 30/312]  eta: 0:03:51  lr: 0.000105  min_lr: 0.000105  loss: 2.1495 (2.0152)  weight_decay: 0.0500 (0.0500)  time: 0.4330  data: 0.0003  max mem: 42573
Epoch: [271]  [ 40/312]  eta: 0:03:17  lr: 0.000105  min_lr: 0.000105  loss: 1.7716 (1.9726)  weight_decay: 0.0500 (0.0500)  time: 0.4332  data: 0.0003  max mem: 42573
Epoch: [271]  [ 50/312]  eta: 0:02:55  lr: 0.000105  min_lr: 0.000105  loss: 2.1563 (2.0168)  weight_decay: 0.0500 (0.0500)  time: 0.4331  data: 0.0003  max mem: 42573
Epoch: [271]  [ 60/312]  eta: 0:02:38  lr: 0.000105  min_lr: 0.000105  loss: 2.2267 (2.0090)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [271]  [ 70/312]  eta: 0:02:25  lr: 0.000104  min_lr: 0.000104  loss: 2.0936 (2.0070)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [271]  [ 80/312]  eta: 0:02:15  lr: 0.000104  min_lr: 0.000104  loss: 1.9734 (2.0022)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [271]  [ 90/312]  eta: 0:02:05  lr: 0.000104  min_lr: 0.000104  loss: 1.9734 (2.0065)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [271]  [100/312]  eta: 0:01:57  lr: 0.000104  min_lr: 0.000104  loss: 2.0954 (2.0127)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [271]  [110/312]  eta: 0:01:49  lr: 0.000103  min_lr: 0.000103  loss: 2.0964 (2.0111)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [271]  [120/312]  eta: 0:01:42  lr: 0.000103  min_lr: 0.000103  loss: 1.9941 (1.9993)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [271]  [130/312]  eta: 0:01:35  lr: 0.000103  min_lr: 0.000103  loss: 1.9941 (2.0015)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [271]  [140/312]  eta: 0:01:29  lr: 0.000103  min_lr: 0.000103  loss: 2.1008 (2.0107)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [271]  [150/312]  eta: 0:01:23  lr: 0.000102  min_lr: 0.000102  loss: 2.0631 (2.0095)  weight_decay: 0.0500 (0.0500)  time: 0.4444  data: 0.0004  max mem: 42573
Epoch: [271]  [160/312]  eta: 0:01:17  lr: 0.000102  min_lr: 0.000102  loss: 2.0629 (2.0128)  weight_decay: 0.0500 (0.0500)  time: 0.4442  data: 0.0004  max mem: 42573
Epoch: [271]  [170/312]  eta: 0:01:11  lr: 0.000102  min_lr: 0.000102  loss: 2.0616 (2.0069)  weight_decay: 0.0500 (0.0500)  time: 0.4332  data: 0.0004  max mem: 42573
Epoch: [271]  [180/312]  eta: 0:01:06  lr: 0.000102  min_lr: 0.000102  loss: 2.0388 (2.0039)  weight_decay: 0.0500 (0.0500)  time: 0.4331  data: 0.0004  max mem: 42573
Epoch: [271]  [190/312]  eta: 0:01:00  lr: 0.000102  min_lr: 0.000102  loss: 2.0521 (2.0067)  weight_decay: 0.0500 (0.0500)  time: 0.4332  data: 0.0004  max mem: 42573
Epoch: [271]  [200/312]  eta: 0:00:55  lr: 0.000101  min_lr: 0.000101  loss: 2.1485 (2.0079)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [271]  [210/312]  eta: 0:00:50  lr: 0.000101  min_lr: 0.000101  loss: 1.9683 (2.0047)  weight_decay: 0.0500 (0.0500)  time: 0.4332  data: 0.0004  max mem: 42573
Epoch: [271]  [220/312]  eta: 0:00:44  lr: 0.000101  min_lr: 0.000101  loss: 1.8654 (1.9972)  weight_decay: 0.0500 (0.0500)  time: 0.4332  data: 0.0004  max mem: 42573
Epoch: [271]  [230/312]  eta: 0:00:39  lr: 0.000101  min_lr: 0.000101  loss: 1.8781 (1.9974)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [271]  [240/312]  eta: 0:00:34  lr: 0.000100  min_lr: 0.000100  loss: 1.9982 (1.9996)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [271]  [250/312]  eta: 0:00:29  lr: 0.000100  min_lr: 0.000100  loss: 2.1415 (2.0060)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [271]  [260/312]  eta: 0:00:24  lr: 0.000100  min_lr: 0.000100  loss: 2.1415 (2.0060)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [271]  [270/312]  eta: 0:00:20  lr: 0.000100  min_lr: 0.000100  loss: 1.9872 (2.0044)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [271]  [280/312]  eta: 0:00:15  lr: 0.000100  min_lr: 0.000100  loss: 1.9259 (2.0036)  weight_decay: 0.0500 (0.0500)  time: 0.4341  data: 0.0009  max mem: 42573
Epoch: [271]  [290/312]  eta: 0:00:10  lr: 0.000099  min_lr: 0.000099  loss: 2.1612 (2.0121)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0008  max mem: 42573
Epoch: [271]  [300/312]  eta: 0:00:05  lr: 0.000099  min_lr: 0.000099  loss: 2.2152 (2.0138)  weight_decay: 0.0500 (0.0500)  time: 0.4321  data: 0.0001  max mem: 42573
Epoch: [271]  [310/312]  eta: 0:00:00  lr: 0.000099  min_lr: 0.000099  loss: 2.1686 (2.0162)  weight_decay: 0.0500 (0.0500)  time: 0.4318  data: 0.0001  max mem: 42573
Epoch: [271]  [311/312]  eta: 0:00:00  lr: 0.000099  min_lr: 0.000099  loss: 2.1686 (2.0178)  weight_decay: 0.0500 (0.0500)  time: 0.4318  data: 0.0001  max mem: 42573
Epoch: [271] Total time: 0:02:28 (0.4756 s / it)
Averaged stats: lr: 0.000099  min_lr: 0.000099  loss: 2.1686 (2.0440)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:00:41  loss: 0.5611 (0.5611)  acc1: 85.4167 (85.4167)  acc5: 96.0938 (96.0938)  time: 4.6547  data: 4.5467  max mem: 42573
Test:  [8/9]  eta: 0:00:00  loss: 0.7545 (0.7453)  acc1: 81.7708 (80.1920)  acc5: 95.5729 (95.1360)  time: 0.5922  data: 0.5053  max mem: 42573
Test: Total time: 0:00:05 (0.6152 s / it)
* Acc@1 80.624 Acc@5 95.316 loss 0.734
Accuracy of the model on the 50000 test images: 80.6%
Max accuracy: 80.76%
Epoch: [272]  [  0/312]  eta: 0:50:38  lr: 0.000099  min_lr: 0.000099  loss: 2.1178 (2.1178)  weight_decay: 0.0500 (0.0500)  time: 9.7374  data: 8.9502  max mem: 42573
Epoch: [272]  [ 10/312]  eta: 0:07:34  lr: 0.000099  min_lr: 0.000099  loss: 2.1646 (1.9982)  weight_decay: 0.0500 (0.0500)  time: 1.5055  data: 0.8140  max mem: 42573
Epoch: [272]  [ 20/312]  eta: 0:04:50  lr: 0.000098  min_lr: 0.000098  loss: 2.1547 (1.9925)  weight_decay: 0.0500 (0.0500)  time: 0.5579  data: 0.0004  max mem: 42573
Epoch: [272]  [ 30/312]  eta: 0:03:49  lr: 0.000098  min_lr: 0.000098  loss: 2.1547 (2.0406)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [272]  [ 40/312]  eta: 0:03:16  lr: 0.000098  min_lr: 0.000098  loss: 2.1210 (2.0367)  weight_decay: 0.0500 (0.0500)  time: 0.4331  data: 0.0004  max mem: 42573
Epoch: [272]  [ 50/312]  eta: 0:02:54  lr: 0.000098  min_lr: 0.000098  loss: 2.0980 (2.0356)  weight_decay: 0.0500 (0.0500)  time: 0.4332  data: 0.0004  max mem: 42573
Epoch: [272]  [ 60/312]  eta: 0:02:38  lr: 0.000098  min_lr: 0.000098  loss: 2.0966 (2.0471)  weight_decay: 0.0500 (0.0500)  time: 0.4366  data: 0.0004  max mem: 42573
Epoch: [272]  [ 70/312]  eta: 0:02:25  lr: 0.000097  min_lr: 0.000097  loss: 2.1581 (2.0632)  weight_decay: 0.0500 (0.0500)  time: 0.4366  data: 0.0004  max mem: 42573
Epoch: [272]  [ 80/312]  eta: 0:02:14  lr: 0.000097  min_lr: 0.000097  loss: 2.0399 (2.0412)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [272]  [ 90/312]  eta: 0:02:05  lr: 0.000097  min_lr: 0.000097  loss: 1.7761 (2.0232)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [272]  [100/312]  eta: 0:01:56  lr: 0.000097  min_lr: 0.000097  loss: 1.6804 (1.9861)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [272]  [110/312]  eta: 0:01:49  lr: 0.000096  min_lr: 0.000096  loss: 1.8578 (1.9990)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [272]  [120/312]  eta: 0:01:42  lr: 0.000096  min_lr: 0.000096  loss: 2.1976 (2.0081)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [272]  [130/312]  eta: 0:01:35  lr: 0.000096  min_lr: 0.000096  loss: 2.1781 (2.0142)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [272]  [140/312]  eta: 0:01:29  lr: 0.000096  min_lr: 0.000096  loss: 2.1090 (2.0231)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [272]  [150/312]  eta: 0:01:22  lr: 0.000096  min_lr: 0.000096  loss: 2.1759 (2.0334)  weight_decay: 0.0500 (0.0500)  time: 0.4331  data: 0.0004  max mem: 42573
Epoch: [272]  [160/312]  eta: 0:01:17  lr: 0.000095  min_lr: 0.000095  loss: 2.1728 (2.0352)  weight_decay: 0.0500 (0.0500)  time: 0.4331  data: 0.0005  max mem: 42573
Epoch: [272]  [170/312]  eta: 0:01:11  lr: 0.000095  min_lr: 0.000095  loss: 1.9924 (2.0275)  weight_decay: 0.0500 (0.0500)  time: 0.4332  data: 0.0004  max mem: 42573
Epoch: [272]  [180/312]  eta: 0:01:05  lr: 0.000095  min_lr: 0.000095  loss: 1.9443 (2.0352)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [272]  [190/312]  eta: 0:01:00  lr: 0.000095  min_lr: 0.000095  loss: 1.9443 (2.0317)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [272]  [200/312]  eta: 0:00:55  lr: 0.000094  min_lr: 0.000094  loss: 1.8698 (2.0287)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [272]  [210/312]  eta: 0:00:49  lr: 0.000094  min_lr: 0.000094  loss: 1.9957 (2.0274)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [272]  [220/312]  eta: 0:00:44  lr: 0.000094  min_lr: 0.000094  loss: 2.0694 (2.0260)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [272]  [230/312]  eta: 0:00:39  lr: 0.000094  min_lr: 0.000094  loss: 1.9779 (2.0217)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [272]  [240/312]  eta: 0:00:34  lr: 0.000094  min_lr: 0.000094  loss: 1.9779 (2.0222)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [272]  [250/312]  eta: 0:00:29  lr: 0.000093  min_lr: 0.000093  loss: 2.0546 (2.0160)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [272]  [260/312]  eta: 0:00:24  lr: 0.000093  min_lr: 0.000093  loss: 2.0668 (2.0174)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [272]  [270/312]  eta: 0:00:20  lr: 0.000093  min_lr: 0.000093  loss: 2.0990 (2.0202)  weight_decay: 0.0500 (0.0500)  time: 0.4345  data: 0.0004  max mem: 42573
Epoch: [272]  [280/312]  eta: 0:00:15  lr: 0.000093  min_lr: 0.000093  loss: 1.8949 (2.0156)  weight_decay: 0.0500 (0.0500)  time: 0.4350  data: 0.0009  max mem: 42573
Epoch: [272]  [290/312]  eta: 0:00:10  lr: 0.000093  min_lr: 0.000093  loss: 1.8577 (2.0134)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0008  max mem: 42573
Epoch: [272]  [300/312]  eta: 0:00:05  lr: 0.000092  min_lr: 0.000092  loss: 2.0020 (2.0114)  weight_decay: 0.0500 (0.0500)  time: 0.4321  data: 0.0001  max mem: 42573
Epoch: [272]  [310/312]  eta: 0:00:00  lr: 0.000092  min_lr: 0.000092  loss: 2.1632 (2.0170)  weight_decay: 0.0500 (0.0500)  time: 0.4320  data: 0.0001  max mem: 42573
Epoch: [272]  [311/312]  eta: 0:00:00  lr: 0.000092  min_lr: 0.000092  loss: 2.1986 (2.0176)  weight_decay: 0.0500 (0.0500)  time: 0.4320  data: 0.0001  max mem: 42573
Epoch: [272] Total time: 0:02:27 (0.4743 s / it)
Averaged stats: lr: 0.000092  min_lr: 0.000092  loss: 2.1986 (2.0481)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:00:41  loss: 0.5717 (0.5717)  acc1: 85.6771 (85.6771)  acc5: 95.8333 (95.8333)  time: 4.6474  data: 4.5391  max mem: 42573
Test:  [8/9]  eta: 0:00:00  loss: 0.7612 (0.7481)  acc1: 81.7708 (80.1600)  acc5: 95.3125 (95.0720)  time: 0.5971  data: 0.5101  max mem: 42573
Test: Total time: 0:00:05 (0.6202 s / it)
* Acc@1 80.672 Acc@5 95.304 loss 0.733
Accuracy of the model on the 50000 test images: 80.7%
Max accuracy: 80.76%
Epoch: [273]  [  0/312]  eta: 0:51:30  lr: 0.000092  min_lr: 0.000092  loss: 1.5270 (1.5270)  weight_decay: 0.0500 (0.0500)  time: 9.9044  data: 8.1085  max mem: 42573
Epoch: [273]  [ 10/312]  eta: 0:07:25  lr: 0.000092  min_lr: 0.000092  loss: 1.6513 (1.8224)  weight_decay: 0.0500 (0.0500)  time: 1.4746  data: 0.7771  max mem: 42573
Epoch: [273]  [ 20/312]  eta: 0:04:45  lr: 0.000092  min_lr: 0.000092  loss: 1.7955 (1.8941)  weight_decay: 0.0500 (0.0500)  time: 0.5323  data: 0.0222  max mem: 42573
Epoch: [273]  [ 30/312]  eta: 0:03:46  lr: 0.000091  min_lr: 0.000091  loss: 1.7955 (1.8655)  weight_decay: 0.0500 (0.0500)  time: 0.4332  data: 0.0003  max mem: 42573
Epoch: [273]  [ 40/312]  eta: 0:03:13  lr: 0.000091  min_lr: 0.000091  loss: 2.0627 (1.9438)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0003  max mem: 42573
Epoch: [273]  [ 50/312]  eta: 0:02:52  lr: 0.000091  min_lr: 0.000091  loss: 2.1743 (1.9799)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [273]  [ 60/312]  eta: 0:02:36  lr: 0.000091  min_lr: 0.000091  loss: 2.1496 (1.9999)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0003  max mem: 42573
Epoch: [273]  [ 70/312]  eta: 0:02:23  lr: 0.000091  min_lr: 0.000091  loss: 2.0314 (1.9582)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0003  max mem: 42573
Epoch: [273]  [ 80/312]  eta: 0:02:13  lr: 0.000090  min_lr: 0.000090  loss: 1.6529 (1.9476)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [273]  [ 90/312]  eta: 0:02:04  lr: 0.000090  min_lr: 0.000090  loss: 1.9945 (1.9405)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [273]  [100/312]  eta: 0:01:55  lr: 0.000090  min_lr: 0.000090  loss: 2.1147 (1.9568)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [273]  [110/312]  eta: 0:01:48  lr: 0.000090  min_lr: 0.000090  loss: 2.1570 (1.9701)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [273]  [120/312]  eta: 0:01:41  lr: 0.000089  min_lr: 0.000089  loss: 2.1570 (1.9821)  weight_decay: 0.0500 (0.0500)  time: 0.4332  data: 0.0004  max mem: 42573
Epoch: [273]  [130/312]  eta: 0:01:34  lr: 0.000089  min_lr: 0.000089  loss: 2.0135 (1.9804)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [273]  [140/312]  eta: 0:01:28  lr: 0.000089  min_lr: 0.000089  loss: 1.8988 (1.9820)  weight_decay: 0.0500 (0.0500)  time: 0.4332  data: 0.0004  max mem: 42573
Epoch: [273]  [150/312]  eta: 0:01:22  lr: 0.000089  min_lr: 0.000089  loss: 1.9956 (1.9916)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [273]  [160/312]  eta: 0:01:16  lr: 0.000089  min_lr: 0.000089  loss: 2.0716 (1.9938)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [273]  [170/312]  eta: 0:01:11  lr: 0.000088  min_lr: 0.000088  loss: 2.1094 (2.0014)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [273]  [180/312]  eta: 0:01:05  lr: 0.000088  min_lr: 0.000088  loss: 2.1148 (2.0025)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [273]  [190/312]  eta: 0:01:00  lr: 0.000088  min_lr: 0.000088  loss: 2.1258 (2.0126)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [273]  [200/312]  eta: 0:00:54  lr: 0.000088  min_lr: 0.000088  loss: 2.1367 (2.0161)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [273]  [210/312]  eta: 0:00:49  lr: 0.000088  min_lr: 0.000088  loss: 2.1367 (2.0156)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [273]  [220/312]  eta: 0:00:44  lr: 0.000087  min_lr: 0.000087  loss: 2.0546 (2.0140)  weight_decay: 0.0500 (0.0500)  time: 0.4332  data: 0.0004  max mem: 42573
Epoch: [273]  [230/312]  eta: 0:00:39  lr: 0.000087  min_lr: 0.000087  loss: 2.0641 (2.0190)  weight_decay: 0.0500 (0.0500)  time: 0.4332  data: 0.0004  max mem: 42573
Epoch: [273]  [240/312]  eta: 0:00:34  lr: 0.000087  min_lr: 0.000087  loss: 2.2173 (2.0230)  weight_decay: 0.0500 (0.0500)  time: 0.4332  data: 0.0004  max mem: 42573
Epoch: [273]  [250/312]  eta: 0:00:29  lr: 0.000087  min_lr: 0.000087  loss: 2.1864 (2.0228)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [273]  [260/312]  eta: 0:00:24  lr: 0.000087  min_lr: 0.000087  loss: 2.0927 (2.0257)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [273]  [270/312]  eta: 0:00:20  lr: 0.000086  min_lr: 0.000086  loss: 2.0897 (2.0174)  weight_decay: 0.0500 (0.0500)  time: 0.4424  data: 0.0004  max mem: 42573
Epoch: [273]  [280/312]  eta: 0:00:15  lr: 0.000086  min_lr: 0.000086  loss: 2.0940 (2.0210)  weight_decay: 0.0500 (0.0500)  time: 0.4431  data: 0.0010  max mem: 42573
Epoch: [273]  [290/312]  eta: 0:00:10  lr: 0.000086  min_lr: 0.000086  loss: 2.1747 (2.0291)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0009  max mem: 42573
Epoch: [273]  [300/312]  eta: 0:00:05  lr: 0.000086  min_lr: 0.000086  loss: 2.2630 (2.0356)  weight_decay: 0.0500 (0.0500)  time: 0.4324  data: 0.0001  max mem: 42573
Epoch: [273]  [310/312]  eta: 0:00:00  lr: 0.000086  min_lr: 0.000086  loss: 2.0922 (2.0316)  weight_decay: 0.0500 (0.0500)  time: 0.4321  data: 0.0001  max mem: 42573
Epoch: [273]  [311/312]  eta: 0:00:00  lr: 0.000085  min_lr: 0.000085  loss: 2.0107 (2.0304)  weight_decay: 0.0500 (0.0500)  time: 0.4321  data: 0.0001  max mem: 42573
Epoch: [273] Total time: 0:02:27 (0.4734 s / it)
Averaged stats: lr: 0.000085  min_lr: 0.000085  loss: 2.0107 (2.0490)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:00:38  loss: 0.5553 (0.5553)  acc1: 85.6771 (85.6771)  acc5: 96.0938 (96.0938)  time: 4.2756  data: 4.1678  max mem: 42573
Test:  [8/9]  eta: 0:00:00  loss: 0.7579 (0.7408)  acc1: 81.5104 (80.3200)  acc5: 96.0938 (95.3600)  time: 0.5694  data: 0.4822  max mem: 42573
Test: Total time: 0:00:05 (0.5770 s / it)
* Acc@1 80.746 Acc@5 95.366 loss 0.728
Accuracy of the model on the 50000 test images: 80.7%
Max accuracy: 80.76%
Epoch: [274]  [  0/312]  eta: 0:52:05  lr: 0.000085  min_lr: 0.000085  loss: 2.3356 (2.3356)  weight_decay: 0.0500 (0.0500)  time: 10.0162  data: 9.3667  max mem: 42573
Epoch: [274]  [ 10/312]  eta: 0:06:55  lr: 0.000085  min_lr: 0.000085  loss: 2.1877 (2.0354)  weight_decay: 0.0500 (0.0500)  time: 1.3751  data: 0.8560  max mem: 42573
Epoch: [274]  [ 20/312]  eta: 0:04:30  lr: 0.000085  min_lr: 0.000085  loss: 1.9021 (1.9987)  weight_decay: 0.0500 (0.0500)  time: 0.4726  data: 0.0027  max mem: 42573
Epoch: [274]  [ 30/312]  eta: 0:03:36  lr: 0.000085  min_lr: 0.000085  loss: 2.0696 (2.0673)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [274]  [ 40/312]  eta: 0:03:06  lr: 0.000085  min_lr: 0.000085  loss: 2.1333 (2.0602)  weight_decay: 0.0500 (0.0500)  time: 0.4330  data: 0.0003  max mem: 42573
Epoch: [274]  [ 50/312]  eta: 0:02:46  lr: 0.000084  min_lr: 0.000084  loss: 2.0930 (2.0444)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [274]  [ 60/312]  eta: 0:02:32  lr: 0.000084  min_lr: 0.000084  loss: 2.1458 (2.0741)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [274]  [ 70/312]  eta: 0:02:20  lr: 0.000084  min_lr: 0.000084  loss: 2.1232 (2.0458)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [274]  [ 80/312]  eta: 0:02:10  lr: 0.000084  min_lr: 0.000084  loss: 1.9200 (2.0593)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [274]  [ 90/312]  eta: 0:02:01  lr: 0.000084  min_lr: 0.000084  loss: 2.2025 (2.0685)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [274]  [100/312]  eta: 0:01:53  lr: 0.000083  min_lr: 0.000083  loss: 2.0680 (2.0634)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [274]  [110/312]  eta: 0:01:46  lr: 0.000083  min_lr: 0.000083  loss: 2.0193 (2.0508)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [274]  [120/312]  eta: 0:01:39  lr: 0.000083  min_lr: 0.000083  loss: 1.9704 (2.0473)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [274]  [130/312]  eta: 0:01:33  lr: 0.000083  min_lr: 0.000083  loss: 1.8934 (2.0386)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [274]  [140/312]  eta: 0:01:27  lr: 0.000083  min_lr: 0.000083  loss: 1.8934 (2.0497)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [274]  [150/312]  eta: 0:01:21  lr: 0.000082  min_lr: 0.000082  loss: 2.1542 (2.0506)  weight_decay: 0.0500 (0.0500)  time: 0.4332  data: 0.0004  max mem: 42573
Epoch: [274]  [160/312]  eta: 0:01:15  lr: 0.000082  min_lr: 0.000082  loss: 2.0460 (2.0490)  weight_decay: 0.0500 (0.0500)  time: 0.4331  data: 0.0004  max mem: 42573
Epoch: [274]  [170/312]  eta: 0:01:10  lr: 0.000082  min_lr: 0.000082  loss: 2.2705 (2.0629)  weight_decay: 0.0500 (0.0500)  time: 0.4332  data: 0.0004  max mem: 42573
Epoch: [274]  [180/312]  eta: 0:01:04  lr: 0.000082  min_lr: 0.000082  loss: 2.2380 (2.0625)  weight_decay: 0.0500 (0.0500)  time: 0.4332  data: 0.0004  max mem: 42573
Epoch: [274]  [190/312]  eta: 0:00:59  lr: 0.000082  min_lr: 0.000082  loss: 1.9395 (2.0532)  weight_decay: 0.0500 (0.0500)  time: 0.4332  data: 0.0004  max mem: 42573
Epoch: [274]  [200/312]  eta: 0:00:54  lr: 0.000081  min_lr: 0.000081  loss: 1.9008 (2.0456)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [274]  [210/312]  eta: 0:00:49  lr: 0.000081  min_lr: 0.000081  loss: 1.9968 (2.0454)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [274]  [220/312]  eta: 0:00:44  lr: 0.000081  min_lr: 0.000081  loss: 2.1264 (2.0446)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [274]  [230/312]  eta: 0:00:39  lr: 0.000081  min_lr: 0.000081  loss: 2.1498 (2.0509)  weight_decay: 0.0500 (0.0500)  time: 0.4367  data: 0.0004  max mem: 42573
Epoch: [274]  [240/312]  eta: 0:00:34  lr: 0.000081  min_lr: 0.000081  loss: 2.1498 (2.0452)  weight_decay: 0.0500 (0.0500)  time: 0.4367  data: 0.0004  max mem: 42573
Epoch: [274]  [250/312]  eta: 0:00:29  lr: 0.000080  min_lr: 0.000080  loss: 1.9524 (2.0418)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [274]  [260/312]  eta: 0:00:24  lr: 0.000080  min_lr: 0.000080  loss: 1.8952 (2.0404)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [274]  [270/312]  eta: 0:00:19  lr: 0.000080  min_lr: 0.000080  loss: 2.1277 (2.0445)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [274]  [280/312]  eta: 0:00:15  lr: 0.000080  min_lr: 0.000080  loss: 2.1277 (2.0380)  weight_decay: 0.0500 (0.0500)  time: 0.4344  data: 0.0009  max mem: 42573
Epoch: [274]  [290/312]  eta: 0:00:10  lr: 0.000080  min_lr: 0.000080  loss: 1.8656 (2.0362)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0008  max mem: 42573
Epoch: [274]  [300/312]  eta: 0:00:05  lr: 0.000079  min_lr: 0.000079  loss: 1.9253 (2.0337)  weight_decay: 0.0500 (0.0500)  time: 0.4322  data: 0.0001  max mem: 42573
Epoch: [274]  [310/312]  eta: 0:00:00  lr: 0.000079  min_lr: 0.000079  loss: 2.0949 (2.0373)  weight_decay: 0.0500 (0.0500)  time: 0.4321  data: 0.0001  max mem: 42573
Epoch: [274]  [311/312]  eta: 0:00:00  lr: 0.000079  min_lr: 0.000079  loss: 2.0949 (2.0391)  weight_decay: 0.0500 (0.0500)  time: 0.4321  data: 0.0001  max mem: 42573
Epoch: [274] Total time: 0:02:26 (0.4698 s / it)
Averaged stats: lr: 0.000079  min_lr: 0.000079  loss: 2.0949 (2.0485)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:00:42  loss: 0.5703 (0.5703)  acc1: 85.9375 (85.9375)  acc5: 96.3542 (96.3542)  time: 4.7544  data: 4.6461  max mem: 42573
Test:  [8/9]  eta: 0:00:00  loss: 0.7484 (0.7477)  acc1: 80.9896 (80.3200)  acc5: 95.5729 (95.1040)  time: 0.6034  data: 0.5163  max mem: 42573
Test: Total time: 0:00:05 (0.6177 s / it)
* Acc@1 80.688 Acc@5 95.316 loss 0.733
Accuracy of the model on the 50000 test images: 80.7%
Max accuracy: 80.76%
Epoch: [275]  [  0/312]  eta: 0:50:47  lr: 0.000079  min_lr: 0.000079  loss: 1.6412 (1.6412)  weight_decay: 0.0500 (0.0500)  time: 9.7672  data: 5.8317  max mem: 42573
Epoch: [275]  [ 10/312]  eta: 0:07:49  lr: 0.000079  min_lr: 0.000079  loss: 1.8169 (1.8823)  weight_decay: 0.0500 (0.0500)  time: 1.5533  data: 0.6568  max mem: 42573
Epoch: [275]  [ 20/312]  eta: 0:04:57  lr: 0.000079  min_lr: 0.000079  loss: 2.0976 (1.9891)  weight_decay: 0.0500 (0.0500)  time: 0.5823  data: 0.0698  max mem: 42573
Epoch: [275]  [ 30/312]  eta: 0:03:54  lr: 0.000079  min_lr: 0.000079  loss: 2.2424 (2.0438)  weight_decay: 0.0500 (0.0500)  time: 0.4329  data: 0.0004  max mem: 42573
Epoch: [275]  [ 40/312]  eta: 0:03:19  lr: 0.000078  min_lr: 0.000078  loss: 2.1265 (2.0219)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0005  max mem: 42573
Epoch: [275]  [ 50/312]  eta: 0:02:56  lr: 0.000078  min_lr: 0.000078  loss: 2.0780 (2.0247)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0005  max mem: 42573
Epoch: [275]  [ 60/312]  eta: 0:02:40  lr: 0.000078  min_lr: 0.000078  loss: 2.1335 (2.0168)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [275]  [ 70/312]  eta: 0:02:26  lr: 0.000078  min_lr: 0.000078  loss: 2.1335 (2.0306)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [275]  [ 80/312]  eta: 0:02:15  lr: 0.000078  min_lr: 0.000078  loss: 2.1030 (2.0318)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [275]  [ 90/312]  eta: 0:02:06  lr: 0.000077  min_lr: 0.000077  loss: 2.0292 (2.0273)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [275]  [100/312]  eta: 0:01:57  lr: 0.000077  min_lr: 0.000077  loss: 2.0561 (2.0430)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [275]  [110/312]  eta: 0:01:49  lr: 0.000077  min_lr: 0.000077  loss: 2.2722 (2.0635)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [275]  [120/312]  eta: 0:01:42  lr: 0.000077  min_lr: 0.000077  loss: 2.2336 (2.0745)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [275]  [130/312]  eta: 0:01:35  lr: 0.000077  min_lr: 0.000077  loss: 2.2219 (2.0900)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [275]  [140/312]  eta: 0:01:29  lr: 0.000076  min_lr: 0.000076  loss: 2.0968 (2.0780)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [275]  [150/312]  eta: 0:01:23  lr: 0.000076  min_lr: 0.000076  loss: 1.8169 (2.0673)  weight_decay: 0.0500 (0.0500)  time: 0.4332  data: 0.0004  max mem: 42573
Epoch: [275]  [160/312]  eta: 0:01:17  lr: 0.000076  min_lr: 0.000076  loss: 1.9470 (2.0695)  weight_decay: 0.0500 (0.0500)  time: 0.4332  data: 0.0004  max mem: 42573
Epoch: [275]  [170/312]  eta: 0:01:11  lr: 0.000076  min_lr: 0.000076  loss: 2.1731 (2.0753)  weight_decay: 0.0500 (0.0500)  time: 0.4424  data: 0.0004  max mem: 42573
Epoch: [275]  [180/312]  eta: 0:01:06  lr: 0.000076  min_lr: 0.000076  loss: 2.3409 (2.0876)  weight_decay: 0.0500 (0.0500)  time: 0.4425  data: 0.0004  max mem: 42573
Epoch: [275]  [190/312]  eta: 0:01:00  lr: 0.000075  min_lr: 0.000075  loss: 2.2441 (2.0895)  weight_decay: 0.0500 (0.0500)  time: 0.4332  data: 0.0003  max mem: 42573
Epoch: [275]  [200/312]  eta: 0:00:55  lr: 0.000075  min_lr: 0.000075  loss: 2.0422 (2.0866)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0003  max mem: 42573
Epoch: [275]  [210/312]  eta: 0:00:50  lr: 0.000075  min_lr: 0.000075  loss: 2.1445 (2.0914)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0003  max mem: 42573
Epoch: [275]  [220/312]  eta: 0:00:45  lr: 0.000075  min_lr: 0.000075  loss: 2.1445 (2.0849)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [275]  [230/312]  eta: 0:00:39  lr: 0.000075  min_lr: 0.000075  loss: 2.0361 (2.0847)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [275]  [240/312]  eta: 0:00:34  lr: 0.000074  min_lr: 0.000074  loss: 2.0940 (2.0868)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [275]  [250/312]  eta: 0:00:29  lr: 0.000074  min_lr: 0.000074  loss: 2.0940 (2.0877)  weight_decay: 0.0500 (0.0500)  time: 0.4331  data: 0.0004  max mem: 42573
Epoch: [275]  [260/312]  eta: 0:00:25  lr: 0.000074  min_lr: 0.000074  loss: 2.1164 (2.0836)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [275]  [270/312]  eta: 0:00:20  lr: 0.000074  min_lr: 0.000074  loss: 2.0064 (2.0860)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [275]  [280/312]  eta: 0:00:15  lr: 0.000074  min_lr: 0.000074  loss: 2.0667 (2.0842)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0010  max mem: 42573
Epoch: [275]  [290/312]  eta: 0:00:10  lr: 0.000073  min_lr: 0.000073  loss: 2.0667 (2.0851)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0009  max mem: 42573
Epoch: [275]  [300/312]  eta: 0:00:05  lr: 0.000073  min_lr: 0.000073  loss: 2.1876 (2.0875)  weight_decay: 0.0500 (0.0500)  time: 0.4321  data: 0.0001  max mem: 42573
Epoch: [275]  [310/312]  eta: 0:00:00  lr: 0.000073  min_lr: 0.000073  loss: 2.1986 (2.0909)  weight_decay: 0.0500 (0.0500)  time: 0.4320  data: 0.0001  max mem: 42573
Epoch: [275]  [311/312]  eta: 0:00:00  lr: 0.000073  min_lr: 0.000073  loss: 2.1986 (2.0917)  weight_decay: 0.0500 (0.0500)  time: 0.4320  data: 0.0001  max mem: 42573
Epoch: [275] Total time: 0:02:28 (0.4766 s / it)
Averaged stats: lr: 0.000073  min_lr: 0.000073  loss: 2.1986 (2.0491)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:00:39  loss: 0.5472 (0.5472)  acc1: 87.2396 (87.2396)  acc5: 96.0938 (96.0938)  time: 4.3381  data: 4.2296  max mem: 42573
Test:  [8/9]  eta: 0:00:00  loss: 0.7425 (0.7477)  acc1: 81.5104 (80.6720)  acc5: 96.0938 (95.2640)  time: 0.5848  data: 0.4971  max mem: 42573
Test: Total time: 0:00:05 (0.6058 s / it)
* Acc@1 80.754 Acc@5 95.376 loss 0.732
Accuracy of the model on the 50000 test images: 80.8%
Max accuracy: 80.76%
Epoch: [276]  [  0/312]  eta: 0:50:16  lr: 0.000073  min_lr: 0.000073  loss: 1.7303 (1.7303)  weight_decay: 0.0500 (0.0500)  time: 9.6670  data: 6.1063  max mem: 42573
Epoch: [276]  [ 10/312]  eta: 0:07:24  lr: 0.000073  min_lr: 0.000073  loss: 1.9924 (1.9345)  weight_decay: 0.0500 (0.0500)  time: 1.4713  data: 0.6572  max mem: 42573
Epoch: [276]  [ 20/312]  eta: 0:04:45  lr: 0.000073  min_lr: 0.000073  loss: 2.0844 (2.0000)  weight_decay: 0.0500 (0.0500)  time: 0.5425  data: 0.0563  max mem: 42573
Epoch: [276]  [ 30/312]  eta: 0:03:46  lr: 0.000072  min_lr: 0.000072  loss: 2.0668 (1.9699)  weight_decay: 0.0500 (0.0500)  time: 0.4331  data: 0.0003  max mem: 42573
Epoch: [276]  [ 40/312]  eta: 0:03:13  lr: 0.000072  min_lr: 0.000072  loss: 2.0914 (1.9936)  weight_decay: 0.0500 (0.0500)  time: 0.4332  data: 0.0004  max mem: 42573
Epoch: [276]  [ 50/312]  eta: 0:02:52  lr: 0.000072  min_lr: 0.000072  loss: 2.2047 (2.0506)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [276]  [ 60/312]  eta: 0:02:36  lr: 0.000072  min_lr: 0.000072  loss: 2.1989 (2.0577)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [276]  [ 70/312]  eta: 0:02:23  lr: 0.000072  min_lr: 0.000072  loss: 2.0491 (2.0492)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [276]  [ 80/312]  eta: 0:02:13  lr: 0.000072  min_lr: 0.000072  loss: 1.9301 (2.0324)  weight_decay: 0.0500 (0.0500)  time: 0.4400  data: 0.0004  max mem: 42573
Epoch: [276]  [ 90/312]  eta: 0:02:04  lr: 0.000071  min_lr: 0.000071  loss: 1.9967 (2.0382)  weight_decay: 0.0500 (0.0500)  time: 0.4401  data: 0.0004  max mem: 42573
Epoch: [276]  [100/312]  eta: 0:01:56  lr: 0.000071  min_lr: 0.000071  loss: 1.9856 (2.0213)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [276]  [110/312]  eta: 0:01:48  lr: 0.000071  min_lr: 0.000071  loss: 1.9448 (2.0303)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [276]  [120/312]  eta: 0:01:41  lr: 0.000071  min_lr: 0.000071  loss: 2.2193 (2.0310)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [276]  [130/312]  eta: 0:01:34  lr: 0.000071  min_lr: 0.000071  loss: 1.6378 (2.0051)  weight_decay: 0.0500 (0.0500)  time: 0.4332  data: 0.0004  max mem: 42573
Epoch: [276]  [140/312]  eta: 0:01:28  lr: 0.000070  min_lr: 0.000070  loss: 1.9190 (2.0165)  weight_decay: 0.0500 (0.0500)  time: 0.4330  data: 0.0004  max mem: 42573
Epoch: [276]  [150/312]  eta: 0:01:22  lr: 0.000070  min_lr: 0.000070  loss: 2.1628 (2.0208)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [276]  [160/312]  eta: 0:01:16  lr: 0.000070  min_lr: 0.000070  loss: 2.1397 (2.0228)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [276]  [170/312]  eta: 0:01:11  lr: 0.000070  min_lr: 0.000070  loss: 2.1323 (2.0307)  weight_decay: 0.0500 (0.0500)  time: 0.4332  data: 0.0004  max mem: 42573
Epoch: [276]  [180/312]  eta: 0:01:05  lr: 0.000070  min_lr: 0.000070  loss: 2.0707 (2.0353)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [276]  [190/312]  eta: 0:01:00  lr: 0.000069  min_lr: 0.000069  loss: 2.1206 (2.0411)  weight_decay: 0.0500 (0.0500)  time: 0.4332  data: 0.0004  max mem: 42573
Epoch: [276]  [200/312]  eta: 0:00:54  lr: 0.000069  min_lr: 0.000069  loss: 2.1221 (2.0391)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [276]  [210/312]  eta: 0:00:49  lr: 0.000069  min_lr: 0.000069  loss: 1.8847 (2.0321)  weight_decay: 0.0500 (0.0500)  time: 0.4332  data: 0.0004  max mem: 42573
Epoch: [276]  [220/312]  eta: 0:00:44  lr: 0.000069  min_lr: 0.000069  loss: 1.8499 (2.0246)  weight_decay: 0.0500 (0.0500)  time: 0.4331  data: 0.0004  max mem: 42573
Epoch: [276]  [230/312]  eta: 0:00:39  lr: 0.000069  min_lr: 0.000069  loss: 1.8499 (2.0162)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [276]  [240/312]  eta: 0:00:34  lr: 0.000069  min_lr: 0.000069  loss: 1.9545 (2.0141)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [276]  [250/312]  eta: 0:00:29  lr: 0.000068  min_lr: 0.000068  loss: 2.1358 (2.0141)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [276]  [260/312]  eta: 0:00:24  lr: 0.000068  min_lr: 0.000068  loss: 2.1358 (2.0172)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [276]  [270/312]  eta: 0:00:19  lr: 0.000068  min_lr: 0.000068  loss: 2.0954 (2.0180)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [276]  [280/312]  eta: 0:00:15  lr: 0.000068  min_lr: 0.000068  loss: 2.1437 (2.0230)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0010  max mem: 42573
Epoch: [276]  [290/312]  eta: 0:00:10  lr: 0.000068  min_lr: 0.000068  loss: 2.1579 (2.0261)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0008  max mem: 42573
Epoch: [276]  [300/312]  eta: 0:00:05  lr: 0.000067  min_lr: 0.000067  loss: 2.1678 (2.0278)  weight_decay: 0.0500 (0.0500)  time: 0.4322  data: 0.0001  max mem: 42573
Epoch: [276]  [310/312]  eta: 0:00:00  lr: 0.000067  min_lr: 0.000067  loss: 2.0908 (2.0215)  weight_decay: 0.0500 (0.0500)  time: 0.4321  data: 0.0001  max mem: 42573
Epoch: [276]  [311/312]  eta: 0:00:00  lr: 0.000067  min_lr: 0.000067  loss: 2.0908 (2.0212)  weight_decay: 0.0500 (0.0500)  time: 0.4321  data: 0.0001  max mem: 42573
Epoch: [276] Total time: 0:02:27 (0.4731 s / it)
Averaged stats: lr: 0.000067  min_lr: 0.000067  loss: 2.0908 (2.0335)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:00:41  loss: 0.5539 (0.5539)  acc1: 87.2396 (87.2396)  acc5: 96.0938 (96.0938)  time: 4.6042  data: 4.4958  max mem: 42573
Test:  [8/9]  eta: 0:00:00  loss: 0.7375 (0.7378)  acc1: 81.2500 (80.3520)  acc5: 95.8333 (95.2320)  time: 0.5874  data: 0.4996  max mem: 42573
Test: Total time: 0:00:05 (0.5977 s / it)
* Acc@1 80.898 Acc@5 95.366 loss 0.724
Accuracy of the model on the 50000 test images: 80.9%
Max accuracy: 80.90%
Epoch: [277]  [  0/312]  eta: 0:50:07  lr: 0.000067  min_lr: 0.000067  loss: 2.5645 (2.5645)  weight_decay: 0.0500 (0.0500)  time: 9.6387  data: 8.9852  max mem: 42573
Epoch: [277]  [ 10/312]  eta: 0:07:03  lr: 0.000067  min_lr: 0.000067  loss: 2.2616 (2.2614)  weight_decay: 0.0500 (0.0500)  time: 1.4008  data: 0.8209  max mem: 42573
Epoch: [277]  [ 20/312]  eta: 0:04:34  lr: 0.000067  min_lr: 0.000067  loss: 2.1157 (2.1048)  weight_decay: 0.0500 (0.0500)  time: 0.5051  data: 0.0024  max mem: 42573
Epoch: [277]  [ 30/312]  eta: 0:03:39  lr: 0.000067  min_lr: 0.000067  loss: 2.1750 (2.1439)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0003  max mem: 42573
Epoch: [277]  [ 40/312]  eta: 0:03:08  lr: 0.000066  min_lr: 0.000066  loss: 2.2253 (2.1408)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0003  max mem: 42573
Epoch: [277]  [ 50/312]  eta: 0:02:48  lr: 0.000066  min_lr: 0.000066  loss: 1.9954 (2.0750)  weight_decay: 0.0500 (0.0500)  time: 0.4330  data: 0.0003  max mem: 42573
Epoch: [277]  [ 60/312]  eta: 0:02:33  lr: 0.000066  min_lr: 0.000066  loss: 1.9054 (2.0756)  weight_decay: 0.0500 (0.0500)  time: 0.4331  data: 0.0004  max mem: 42573
Epoch: [277]  [ 70/312]  eta: 0:02:21  lr: 0.000066  min_lr: 0.000066  loss: 2.0130 (2.0665)  weight_decay: 0.0500 (0.0500)  time: 0.4330  data: 0.0004  max mem: 42573
Epoch: [277]  [ 80/312]  eta: 0:02:10  lr: 0.000066  min_lr: 0.000066  loss: 2.2095 (2.0736)  weight_decay: 0.0500 (0.0500)  time: 0.4330  data: 0.0004  max mem: 42573
Epoch: [277]  [ 90/312]  eta: 0:02:02  lr: 0.000066  min_lr: 0.000066  loss: 2.1566 (2.0544)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [277]  [100/312]  eta: 0:01:54  lr: 0.000065  min_lr: 0.000065  loss: 1.7690 (2.0315)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [277]  [110/312]  eta: 0:01:46  lr: 0.000065  min_lr: 0.000065  loss: 1.8897 (2.0221)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [277]  [120/312]  eta: 0:01:40  lr: 0.000065  min_lr: 0.000065  loss: 2.0710 (2.0237)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [277]  [130/312]  eta: 0:01:33  lr: 0.000065  min_lr: 0.000065  loss: 2.1059 (2.0239)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0003  max mem: 42573
Epoch: [277]  [140/312]  eta: 0:01:27  lr: 0.000065  min_lr: 0.000065  loss: 2.1059 (2.0335)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [277]  [150/312]  eta: 0:01:21  lr: 0.000064  min_lr: 0.000064  loss: 2.0833 (2.0267)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [277]  [160/312]  eta: 0:01:15  lr: 0.000064  min_lr: 0.000064  loss: 2.0252 (2.0298)  weight_decay: 0.0500 (0.0500)  time: 0.4332  data: 0.0004  max mem: 42573
Epoch: [277]  [170/312]  eta: 0:01:10  lr: 0.000064  min_lr: 0.000064  loss: 2.2094 (2.0328)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [277]  [180/312]  eta: 0:01:04  lr: 0.000064  min_lr: 0.000064  loss: 2.1630 (2.0305)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [277]  [190/312]  eta: 0:00:59  lr: 0.000064  min_lr: 0.000064  loss: 2.2354 (2.0348)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [277]  [200/312]  eta: 0:00:54  lr: 0.000064  min_lr: 0.000064  loss: 2.0584 (2.0297)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [277]  [210/312]  eta: 0:00:49  lr: 0.000063  min_lr: 0.000063  loss: 2.0038 (2.0297)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [277]  [220/312]  eta: 0:00:44  lr: 0.000063  min_lr: 0.000063  loss: 2.1564 (2.0334)  weight_decay: 0.0500 (0.0500)  time: 0.4332  data: 0.0004  max mem: 42573
Epoch: [277]  [230/312]  eta: 0:00:39  lr: 0.000063  min_lr: 0.000063  loss: 2.1901 (2.0327)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [277]  [240/312]  eta: 0:00:34  lr: 0.000063  min_lr: 0.000063  loss: 2.1901 (2.0408)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [277]  [250/312]  eta: 0:00:29  lr: 0.000063  min_lr: 0.000063  loss: 2.0635 (2.0352)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [277]  [260/312]  eta: 0:00:24  lr: 0.000063  min_lr: 0.000063  loss: 1.8770 (2.0329)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [277]  [270/312]  eta: 0:00:19  lr: 0.000062  min_lr: 0.000062  loss: 2.0110 (2.0314)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [277]  [280/312]  eta: 0:00:15  lr: 0.000062  min_lr: 0.000062  loss: 1.8735 (2.0250)  weight_decay: 0.0500 (0.0500)  time: 0.4345  data: 0.0011  max mem: 42573
Epoch: [277]  [290/312]  eta: 0:00:10  lr: 0.000062  min_lr: 0.000062  loss: 1.8725 (2.0235)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0010  max mem: 42573
Epoch: [277]  [300/312]  eta: 0:00:05  lr: 0.000062  min_lr: 0.000062  loss: 2.0991 (2.0224)  weight_decay: 0.0500 (0.0500)  time: 0.4321  data: 0.0001  max mem: 42573
Epoch: [277]  [310/312]  eta: 0:00:00  lr: 0.000062  min_lr: 0.000062  loss: 2.2083 (2.0298)  weight_decay: 0.0500 (0.0500)  time: 0.4321  data: 0.0001  max mem: 42573
Epoch: [277]  [311/312]  eta: 0:00:00  lr: 0.000062  min_lr: 0.000062  loss: 2.2070 (2.0276)  weight_decay: 0.0500 (0.0500)  time: 0.4321  data: 0.0001  max mem: 42573
Epoch: [277] Total time: 0:02:26 (0.4703 s / it)
Averaged stats: lr: 0.000062  min_lr: 0.000062  loss: 2.2070 (2.0424)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:00:43  loss: 0.5559 (0.5559)  acc1: 85.9375 (85.9375)  acc5: 95.8333 (95.8333)  time: 4.7808  data: 4.6725  max mem: 42573
Test:  [8/9]  eta: 0:00:00  loss: 0.7409 (0.7420)  acc1: 82.0312 (80.0320)  acc5: 95.5729 (95.0400)  time: 0.6064  data: 0.5192  max mem: 42573
Test: Total time: 0:00:05 (0.6271 s / it)
* Acc@1 80.760 Acc@5 95.332 loss 0.727
Accuracy of the model on the 50000 test images: 80.8%
Max accuracy: 80.90%
Epoch: [278]  [  0/312]  eta: 0:52:42  lr: 0.000062  min_lr: 0.000062  loss: 2.0182 (2.0182)  weight_decay: 0.0500 (0.0500)  time: 10.1350  data: 7.0490  max mem: 42573
Epoch: [278]  [ 10/312]  eta: 0:07:34  lr: 0.000061  min_lr: 0.000061  loss: 2.0895 (2.0040)  weight_decay: 0.0500 (0.0500)  time: 1.5038  data: 0.7807  max mem: 42573
Epoch: [278]  [ 20/312]  eta: 0:04:50  lr: 0.000061  min_lr: 0.000061  loss: 2.1405 (2.0862)  weight_decay: 0.0500 (0.0500)  time: 0.5368  data: 0.0771  max mem: 42573
Epoch: [278]  [ 30/312]  eta: 0:03:49  lr: 0.000061  min_lr: 0.000061  loss: 2.0995 (1.9940)  weight_decay: 0.0500 (0.0500)  time: 0.4331  data: 0.0004  max mem: 42573
Epoch: [278]  [ 40/312]  eta: 0:03:15  lr: 0.000061  min_lr: 0.000061  loss: 1.8805 (2.0089)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [278]  [ 50/312]  eta: 0:02:54  lr: 0.000061  min_lr: 0.000061  loss: 1.9187 (1.9966)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [278]  [ 60/312]  eta: 0:02:37  lr: 0.000061  min_lr: 0.000061  loss: 2.0953 (2.0124)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [278]  [ 70/312]  eta: 0:02:25  lr: 0.000060  min_lr: 0.000060  loss: 2.1257 (2.0181)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [278]  [ 80/312]  eta: 0:02:14  lr: 0.000060  min_lr: 0.000060  loss: 2.0363 (2.0068)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [278]  [ 90/312]  eta: 0:02:04  lr: 0.000060  min_lr: 0.000060  loss: 2.0551 (2.0090)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [278]  [100/312]  eta: 0:01:56  lr: 0.000060  min_lr: 0.000060  loss: 2.0551 (2.0001)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0003  max mem: 42573
Epoch: [278]  [110/312]  eta: 0:01:48  lr: 0.000060  min_lr: 0.000060  loss: 2.1847 (2.0213)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [278]  [120/312]  eta: 0:01:41  lr: 0.000060  min_lr: 0.000060  loss: 2.1731 (2.0165)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [278]  [130/312]  eta: 0:01:35  lr: 0.000059  min_lr: 0.000059  loss: 2.0433 (2.0177)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [278]  [140/312]  eta: 0:01:28  lr: 0.000059  min_lr: 0.000059  loss: 2.1407 (2.0276)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [278]  [150/312]  eta: 0:01:22  lr: 0.000059  min_lr: 0.000059  loss: 2.0909 (2.0345)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [278]  [160/312]  eta: 0:01:17  lr: 0.000059  min_lr: 0.000059  loss: 1.9910 (2.0305)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [278]  [170/312]  eta: 0:01:11  lr: 0.000059  min_lr: 0.000059  loss: 2.0824 (2.0345)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [278]  [180/312]  eta: 0:01:05  lr: 0.000058  min_lr: 0.000058  loss: 2.1915 (2.0420)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [278]  [190/312]  eta: 0:01:00  lr: 0.000058  min_lr: 0.000058  loss: 2.1618 (2.0437)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [278]  [200/312]  eta: 0:00:55  lr: 0.000058  min_lr: 0.000058  loss: 2.1193 (2.0301)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0003  max mem: 42573
Epoch: [278]  [210/312]  eta: 0:00:49  lr: 0.000058  min_lr: 0.000058  loss: 2.0688 (2.0290)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [278]  [220/312]  eta: 0:00:44  lr: 0.000058  min_lr: 0.000058  loss: 2.1253 (2.0332)  weight_decay: 0.0500 (0.0500)  time: 0.4399  data: 0.0004  max mem: 42573
Epoch: [278]  [230/312]  eta: 0:00:39  lr: 0.000058  min_lr: 0.000058  loss: 2.2144 (2.0402)  weight_decay: 0.0500 (0.0500)  time: 0.4399  data: 0.0004  max mem: 42573
Epoch: [278]  [240/312]  eta: 0:00:34  lr: 0.000057  min_lr: 0.000057  loss: 2.1937 (2.0411)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [278]  [250/312]  eta: 0:00:29  lr: 0.000057  min_lr: 0.000057  loss: 2.1203 (2.0371)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [278]  [260/312]  eta: 0:00:24  lr: 0.000057  min_lr: 0.000057  loss: 2.1640 (2.0421)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [278]  [270/312]  eta: 0:00:20  lr: 0.000057  min_lr: 0.000057  loss: 2.0852 (2.0399)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [278]  [280/312]  eta: 0:00:15  lr: 0.000057  min_lr: 0.000057  loss: 2.0600 (2.0422)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0009  max mem: 42573
Epoch: [278]  [290/312]  eta: 0:00:10  lr: 0.000057  min_lr: 0.000057  loss: 2.1749 (2.0389)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0008  max mem: 42573
Epoch: [278]  [300/312]  eta: 0:00:05  lr: 0.000056  min_lr: 0.000056  loss: 2.0924 (2.0355)  weight_decay: 0.0500 (0.0500)  time: 0.4321  data: 0.0001  max mem: 42573
Epoch: [278]  [310/312]  eta: 0:00:00  lr: 0.000056  min_lr: 0.000056  loss: 2.0266 (2.0328)  weight_decay: 0.0500 (0.0500)  time: 0.4321  data: 0.0001  max mem: 42573
Epoch: [278]  [311/312]  eta: 0:00:00  lr: 0.000056  min_lr: 0.000056  loss: 1.6856 (2.0303)  weight_decay: 0.0500 (0.0500)  time: 0.4321  data: 0.0001  max mem: 42573
Epoch: [278] Total time: 0:02:28 (0.4746 s / it)
Averaged stats: lr: 0.000056  min_lr: 0.000056  loss: 1.6856 (2.0413)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:00:40  loss: 0.5543 (0.5543)  acc1: 86.1979 (86.1979)  acc5: 96.3542 (96.3542)  time: 4.4545  data: 4.3465  max mem: 42573
Test:  [8/9]  eta: 0:00:00  loss: 0.7382 (0.7359)  acc1: 81.5104 (79.9360)  acc5: 96.0938 (95.2960)  time: 0.5720  data: 0.4830  max mem: 42573
Test: Total time: 0:00:05 (0.5935 s / it)
* Acc@1 80.836 Acc@5 95.364 loss 0.724
Accuracy of the model on the 50000 test images: 80.8%
Max accuracy: 80.90%
Epoch: [279]  [  0/312]  eta: 0:52:24  lr: 0.000056  min_lr: 0.000056  loss: 2.2205 (2.2205)  weight_decay: 0.0500 (0.0500)  time: 10.0786  data: 6.7820  max mem: 42573
Epoch: [279]  [ 10/312]  eta: 0:07:21  lr: 0.000056  min_lr: 0.000056  loss: 1.9008 (1.8653)  weight_decay: 0.0500 (0.0500)  time: 1.4634  data: 0.7609  max mem: 42573
Epoch: [279]  [ 20/312]  eta: 0:04:44  lr: 0.000056  min_lr: 0.000056  loss: 1.8283 (1.8804)  weight_decay: 0.0500 (0.0500)  time: 0.5175  data: 0.0796  max mem: 42573
Epoch: [279]  [ 30/312]  eta: 0:03:45  lr: 0.000056  min_lr: 0.000056  loss: 2.1169 (1.9057)  weight_decay: 0.0500 (0.0500)  time: 0.4330  data: 0.0004  max mem: 42573
Epoch: [279]  [ 40/312]  eta: 0:03:12  lr: 0.000056  min_lr: 0.000056  loss: 2.0470 (1.9264)  weight_decay: 0.0500 (0.0500)  time: 0.4329  data: 0.0004  max mem: 42573
Epoch: [279]  [ 50/312]  eta: 0:02:51  lr: 0.000055  min_lr: 0.000055  loss: 2.0774 (1.9527)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [279]  [ 60/312]  eta: 0:02:35  lr: 0.000055  min_lr: 0.000055  loss: 2.1232 (1.9918)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [279]  [ 70/312]  eta: 0:02:23  lr: 0.000055  min_lr: 0.000055  loss: 2.2058 (1.9960)  weight_decay: 0.0500 (0.0500)  time: 0.4332  data: 0.0004  max mem: 42573
Epoch: [279]  [ 80/312]  eta: 0:02:12  lr: 0.000055  min_lr: 0.000055  loss: 2.1192 (2.0062)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [279]  [ 90/312]  eta: 0:02:03  lr: 0.000055  min_lr: 0.000055  loss: 2.1192 (2.0059)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0003  max mem: 42573
Epoch: [279]  [100/312]  eta: 0:01:55  lr: 0.000055  min_lr: 0.000055  loss: 1.9598 (1.9902)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0003  max mem: 42573
Epoch: [279]  [110/312]  eta: 0:01:48  lr: 0.000054  min_lr: 0.000054  loss: 1.7213 (1.9902)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [279]  [120/312]  eta: 0:01:41  lr: 0.000054  min_lr: 0.000054  loss: 2.0702 (1.9972)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [279]  [130/312]  eta: 0:01:34  lr: 0.000054  min_lr: 0.000054  loss: 2.0180 (1.9997)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [279]  [140/312]  eta: 0:01:28  lr: 0.000054  min_lr: 0.000054  loss: 2.0971 (1.9991)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [279]  [150/312]  eta: 0:01:22  lr: 0.000054  min_lr: 0.000054  loss: 1.8919 (2.0054)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [279]  [160/312]  eta: 0:01:16  lr: 0.000054  min_lr: 0.000054  loss: 2.0512 (2.0132)  weight_decay: 0.0500 (0.0500)  time: 0.4332  data: 0.0004  max mem: 42573
Epoch: [279]  [170/312]  eta: 0:01:10  lr: 0.000053  min_lr: 0.000053  loss: 2.1006 (2.0161)  weight_decay: 0.0500 (0.0500)  time: 0.4332  data: 0.0004  max mem: 42573
Epoch: [279]  [180/312]  eta: 0:01:05  lr: 0.000053  min_lr: 0.000053  loss: 2.1808 (2.0238)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [279]  [190/312]  eta: 0:01:00  lr: 0.000053  min_lr: 0.000053  loss: 2.1965 (2.0276)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [279]  [200/312]  eta: 0:00:54  lr: 0.000053  min_lr: 0.000053  loss: 2.1354 (2.0343)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [279]  [210/312]  eta: 0:00:49  lr: 0.000053  min_lr: 0.000053  loss: 2.2520 (2.0431)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0003  max mem: 42573
Epoch: [279]  [220/312]  eta: 0:00:44  lr: 0.000053  min_lr: 0.000053  loss: 2.2115 (2.0448)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [279]  [230/312]  eta: 0:00:39  lr: 0.000052  min_lr: 0.000052  loss: 2.0156 (2.0444)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [279]  [240/312]  eta: 0:00:34  lr: 0.000052  min_lr: 0.000052  loss: 1.9884 (2.0452)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [279]  [250/312]  eta: 0:00:29  lr: 0.000052  min_lr: 0.000052  loss: 1.9323 (2.0375)  weight_decay: 0.0500 (0.0500)  time: 0.4332  data: 0.0004  max mem: 42573
Epoch: [279]  [260/312]  eta: 0:00:24  lr: 0.000052  min_lr: 0.000052  loss: 1.9323 (2.0370)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [279]  [270/312]  eta: 0:00:19  lr: 0.000052  min_lr: 0.000052  loss: 2.1788 (2.0402)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [279]  [280/312]  eta: 0:00:15  lr: 0.000052  min_lr: 0.000052  loss: 2.2634 (2.0472)  weight_decay: 0.0500 (0.0500)  time: 0.4343  data: 0.0009  max mem: 42573
Epoch: [279]  [290/312]  eta: 0:00:10  lr: 0.000051  min_lr: 0.000051  loss: 2.2090 (2.0463)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0008  max mem: 42573
Epoch: [279]  [300/312]  eta: 0:00:05  lr: 0.000051  min_lr: 0.000051  loss: 2.0963 (2.0487)  weight_decay: 0.0500 (0.0500)  time: 0.4320  data: 0.0001  max mem: 42573
Epoch: [279]  [310/312]  eta: 0:00:00  lr: 0.000051  min_lr: 0.000051  loss: 2.0896 (2.0465)  weight_decay: 0.0500 (0.0500)  time: 0.4319  data: 0.0001  max mem: 42573
Epoch: [279]  [311/312]  eta: 0:00:00  lr: 0.000051  min_lr: 0.000051  loss: 2.0896 (2.0471)  weight_decay: 0.0500 (0.0500)  time: 0.4319  data: 0.0001  max mem: 42573
Epoch: [279] Total time: 0:02:27 (0.4726 s / it)
Averaged stats: lr: 0.000051  min_lr: 0.000051  loss: 2.0896 (2.0376)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:00:41  loss: 0.5551 (0.5551)  acc1: 85.6771 (85.6771)  acc5: 96.0938 (96.0938)  time: 4.6117  data: 4.5034  max mem: 42573
Test:  [8/9]  eta: 0:00:00  loss: 0.7420 (0.7406)  acc1: 80.9896 (80.0320)  acc5: 95.5729 (95.2000)  time: 0.5887  data: 0.5005  max mem: 42573
Test: Total time: 0:00:05 (0.6122 s / it)
* Acc@1 80.842 Acc@5 95.398 loss 0.726
Accuracy of the model on the 50000 test images: 80.8%
Max accuracy: 80.90%
Epoch: [280]  [  0/312]  eta: 0:52:39  lr: 0.000051  min_lr: 0.000051  loss: 2.1304 (2.1304)  weight_decay: 0.0500 (0.0500)  time: 10.1278  data: 8.9267  max mem: 42573
Epoch: [280]  [ 10/312]  eta: 0:07:37  lr: 0.000051  min_lr: 0.000051  loss: 2.2482 (2.1139)  weight_decay: 0.0500 (0.0500)  time: 1.5159  data: 0.8120  max mem: 42573
Epoch: [280]  [ 20/312]  eta: 0:04:52  lr: 0.000051  min_lr: 0.000051  loss: 2.1382 (2.0285)  weight_decay: 0.0500 (0.0500)  time: 0.5438  data: 0.0004  max mem: 42573
Epoch: [280]  [ 30/312]  eta: 0:03:50  lr: 0.000051  min_lr: 0.000051  loss: 1.8795 (2.0177)  weight_decay: 0.0500 (0.0500)  time: 0.4331  data: 0.0004  max mem: 42573
Epoch: [280]  [ 40/312]  eta: 0:03:16  lr: 0.000050  min_lr: 0.000050  loss: 1.9736 (2.0188)  weight_decay: 0.0500 (0.0500)  time: 0.4331  data: 0.0004  max mem: 42573
Epoch: [280]  [ 50/312]  eta: 0:02:54  lr: 0.000050  min_lr: 0.000050  loss: 2.0462 (2.0154)  weight_decay: 0.0500 (0.0500)  time: 0.4331  data: 0.0004  max mem: 42573
Epoch: [280]  [ 60/312]  eta: 0:02:38  lr: 0.000050  min_lr: 0.000050  loss: 2.0399 (2.0189)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [280]  [ 70/312]  eta: 0:02:25  lr: 0.000050  min_lr: 0.000050  loss: 1.9854 (2.0191)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [280]  [ 80/312]  eta: 0:02:14  lr: 0.000050  min_lr: 0.000050  loss: 1.9285 (1.9954)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [280]  [ 90/312]  eta: 0:02:05  lr: 0.000050  min_lr: 0.000050  loss: 1.9285 (1.9941)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [280]  [100/312]  eta: 0:01:56  lr: 0.000050  min_lr: 0.000050  loss: 1.9532 (1.9960)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [280]  [110/312]  eta: 0:01:49  lr: 0.000049  min_lr: 0.000049  loss: 1.9167 (1.9920)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [280]  [120/312]  eta: 0:01:42  lr: 0.000049  min_lr: 0.000049  loss: 2.0784 (2.0042)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [280]  [130/312]  eta: 0:01:35  lr: 0.000049  min_lr: 0.000049  loss: 2.1635 (2.0058)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [280]  [140/312]  eta: 0:01:29  lr: 0.000049  min_lr: 0.000049  loss: 1.9000 (1.9947)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [280]  [150/312]  eta: 0:01:22  lr: 0.000049  min_lr: 0.000049  loss: 2.0682 (2.0089)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [280]  [160/312]  eta: 0:01:17  lr: 0.000049  min_lr: 0.000049  loss: 2.2171 (2.0171)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [280]  [170/312]  eta: 0:01:11  lr: 0.000048  min_lr: 0.000048  loss: 2.1269 (2.0141)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [280]  [180/312]  eta: 0:01:05  lr: 0.000048  min_lr: 0.000048  loss: 2.1934 (2.0199)  weight_decay: 0.0500 (0.0500)  time: 0.4376  data: 0.0004  max mem: 42573
Epoch: [280]  [190/312]  eta: 0:01:00  lr: 0.000048  min_lr: 0.000048  loss: 2.1483 (2.0207)  weight_decay: 0.0500 (0.0500)  time: 0.4374  data: 0.0004  max mem: 42573
Epoch: [280]  [200/312]  eta: 0:00:55  lr: 0.000048  min_lr: 0.000048  loss: 2.0701 (2.0139)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [280]  [210/312]  eta: 0:00:49  lr: 0.000048  min_lr: 0.000048  loss: 2.0814 (2.0205)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [280]  [220/312]  eta: 0:00:44  lr: 0.000048  min_lr: 0.000048  loss: 2.0940 (2.0233)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [280]  [230/312]  eta: 0:00:39  lr: 0.000048  min_lr: 0.000048  loss: 2.0940 (2.0222)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [280]  [240/312]  eta: 0:00:34  lr: 0.000047  min_lr: 0.000047  loss: 2.1013 (2.0223)  weight_decay: 0.0500 (0.0500)  time: 0.4331  data: 0.0004  max mem: 42573
Epoch: [280]  [250/312]  eta: 0:00:29  lr: 0.000047  min_lr: 0.000047  loss: 2.1388 (2.0285)  weight_decay: 0.0500 (0.0500)  time: 0.4332  data: 0.0004  max mem: 42573
Epoch: [280]  [260/312]  eta: 0:00:24  lr: 0.000047  min_lr: 0.000047  loss: 2.1388 (2.0300)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [280]  [270/312]  eta: 0:00:20  lr: 0.000047  min_lr: 0.000047  loss: 2.1868 (2.0323)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [280]  [280/312]  eta: 0:00:15  lr: 0.000047  min_lr: 0.000047  loss: 1.9999 (2.0293)  weight_decay: 0.0500 (0.0500)  time: 0.4341  data: 0.0009  max mem: 42573
Epoch: [280]  [290/312]  eta: 0:00:10  lr: 0.000047  min_lr: 0.000047  loss: 2.0919 (2.0314)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0008  max mem: 42573
Epoch: [280]  [300/312]  eta: 0:00:05  lr: 0.000046  min_lr: 0.000046  loss: 2.1298 (2.0347)  weight_decay: 0.0500 (0.0500)  time: 0.4320  data: 0.0001  max mem: 42573
Epoch: [280]  [310/312]  eta: 0:00:00  lr: 0.000046  min_lr: 0.000046  loss: 2.0828 (2.0287)  weight_decay: 0.0500 (0.0500)  time: 0.4319  data: 0.0001  max mem: 42573
Epoch: [280]  [311/312]  eta: 0:00:00  lr: 0.000046  min_lr: 0.000046  loss: 2.0905 (2.0308)  weight_decay: 0.0500 (0.0500)  time: 0.4319  data: 0.0001  max mem: 42573
Epoch: [280] Total time: 0:02:28 (0.4749 s / it)
Averaged stats: lr: 0.000046  min_lr: 0.000046  loss: 2.0905 (2.0377)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:00:42  loss: 0.5444 (0.5444)  acc1: 87.2396 (87.2396)  acc5: 96.3542 (96.3542)  time: 4.6811  data: 4.5726  max mem: 42573
Test:  [8/9]  eta: 0:00:00  loss: 0.7424 (0.7414)  acc1: 81.5104 (80.3520)  acc5: 95.8333 (95.4560)  time: 0.5964  data: 0.5082  max mem: 42573
Test: Total time: 0:00:05 (0.6043 s / it)
* Acc@1 80.848 Acc@5 95.348 loss 0.726
Accuracy of the model on the 50000 test images: 80.8%
Max accuracy: 80.90%
Epoch: [281]  [  0/312]  eta: 0:51:58  lr: 0.000046  min_lr: 0.000046  loss: 2.5208 (2.5208)  weight_decay: 0.0500 (0.0500)  time: 9.9957  data: 7.1283  max mem: 42573
Epoch: [281]  [ 10/312]  eta: 0:07:52  lr: 0.000046  min_lr: 0.000046  loss: 1.7865 (1.8318)  weight_decay: 0.0500 (0.0500)  time: 1.5657  data: 0.7525  max mem: 42573
Epoch: [281]  [ 20/312]  eta: 0:04:59  lr: 0.000046  min_lr: 0.000046  loss: 1.8335 (1.9430)  weight_decay: 0.0500 (0.0500)  time: 0.5778  data: 0.0577  max mem: 42573
Epoch: [281]  [ 30/312]  eta: 0:03:55  lr: 0.000046  min_lr: 0.000046  loss: 2.1339 (1.9990)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [281]  [ 40/312]  eta: 0:03:20  lr: 0.000046  min_lr: 0.000046  loss: 1.9913 (1.9793)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [281]  [ 50/312]  eta: 0:02:57  lr: 0.000046  min_lr: 0.000046  loss: 1.9913 (1.9828)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [281]  [ 60/312]  eta: 0:02:40  lr: 0.000045  min_lr: 0.000045  loss: 2.0384 (1.9883)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [281]  [ 70/312]  eta: 0:02:27  lr: 0.000045  min_lr: 0.000045  loss: 2.0876 (2.0215)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [281]  [ 80/312]  eta: 0:02:16  lr: 0.000045  min_lr: 0.000045  loss: 2.0876 (2.0210)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [281]  [ 90/312]  eta: 0:02:06  lr: 0.000045  min_lr: 0.000045  loss: 2.0644 (2.0245)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [281]  [100/312]  eta: 0:01:58  lr: 0.000045  min_lr: 0.000045  loss: 2.0158 (2.0088)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [281]  [110/312]  eta: 0:01:50  lr: 0.000045  min_lr: 0.000045  loss: 1.9739 (2.0128)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [281]  [120/312]  eta: 0:01:42  lr: 0.000044  min_lr: 0.000044  loss: 2.0246 (2.0259)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [281]  [130/312]  eta: 0:01:36  lr: 0.000044  min_lr: 0.000044  loss: 2.1498 (2.0263)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [281]  [140/312]  eta: 0:01:29  lr: 0.000044  min_lr: 0.000044  loss: 2.1887 (2.0445)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [281]  [150/312]  eta: 0:01:23  lr: 0.000044  min_lr: 0.000044  loss: 2.0980 (2.0324)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [281]  [160/312]  eta: 0:01:17  lr: 0.000044  min_lr: 0.000044  loss: 1.9671 (2.0384)  weight_decay: 0.0500 (0.0500)  time: 0.4379  data: 0.0004  max mem: 42573
Epoch: [281]  [170/312]  eta: 0:01:11  lr: 0.000044  min_lr: 0.000044  loss: 2.0592 (2.0388)  weight_decay: 0.0500 (0.0500)  time: 0.4378  data: 0.0004  max mem: 42573
Epoch: [281]  [180/312]  eta: 0:01:06  lr: 0.000044  min_lr: 0.000044  loss: 2.0979 (2.0419)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [281]  [190/312]  eta: 0:01:00  lr: 0.000043  min_lr: 0.000043  loss: 2.1071 (2.0436)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [281]  [200/312]  eta: 0:00:55  lr: 0.000043  min_lr: 0.000043  loss: 2.1071 (2.0433)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [281]  [210/312]  eta: 0:00:50  lr: 0.000043  min_lr: 0.000043  loss: 2.0970 (2.0343)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [281]  [220/312]  eta: 0:00:45  lr: 0.000043  min_lr: 0.000043  loss: 2.0091 (2.0342)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [281]  [230/312]  eta: 0:00:39  lr: 0.000043  min_lr: 0.000043  loss: 2.0479 (2.0333)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [281]  [240/312]  eta: 0:00:34  lr: 0.000043  min_lr: 0.000043  loss: 2.1340 (2.0382)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [281]  [250/312]  eta: 0:00:29  lr: 0.000043  min_lr: 0.000043  loss: 2.1340 (2.0397)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [281]  [260/312]  eta: 0:00:25  lr: 0.000042  min_lr: 0.000042  loss: 2.0759 (2.0383)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [281]  [270/312]  eta: 0:00:20  lr: 0.000042  min_lr: 0.000042  loss: 2.0312 (2.0369)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [281]  [280/312]  eta: 0:00:15  lr: 0.000042  min_lr: 0.000042  loss: 2.1108 (2.0409)  weight_decay: 0.0500 (0.0500)  time: 0.4349  data: 0.0009  max mem: 42573
Epoch: [281]  [290/312]  eta: 0:00:10  lr: 0.000042  min_lr: 0.000042  loss: 2.1251 (2.0425)  weight_decay: 0.0500 (0.0500)  time: 0.4341  data: 0.0008  max mem: 42573
Epoch: [281]  [300/312]  eta: 0:00:05  lr: 0.000042  min_lr: 0.000042  loss: 2.0654 (2.0459)  weight_decay: 0.0500 (0.0500)  time: 0.4321  data: 0.0001  max mem: 42573
Epoch: [281]  [310/312]  eta: 0:00:00  lr: 0.000042  min_lr: 0.000042  loss: 2.0141 (2.0439)  weight_decay: 0.0500 (0.0500)  time: 0.4321  data: 0.0001  max mem: 42573
Epoch: [281]  [311/312]  eta: 0:00:00  lr: 0.000042  min_lr: 0.000042  loss: 2.0311 (2.0445)  weight_decay: 0.0500 (0.0500)  time: 0.4321  data: 0.0001  max mem: 42573
Epoch: [281] Total time: 0:02:28 (0.4769 s / it)
Averaged stats: lr: 0.000042  min_lr: 0.000042  loss: 2.0311 (2.0426)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:00:43  loss: 0.5439 (0.5439)  acc1: 86.1979 (86.1979)  acc5: 96.3542 (96.3542)  time: 4.7885  data: 4.6802  max mem: 42573
Test:  [8/9]  eta: 0:00:00  loss: 0.7450 (0.7410)  acc1: 81.7708 (80.0960)  acc5: 96.0938 (95.2640)  time: 0.6089  data: 0.5201  max mem: 42573
Test: Total time: 0:00:05 (0.6325 s / it)
* Acc@1 80.866 Acc@5 95.396 loss 0.723
Accuracy of the model on the 50000 test images: 80.9%
Max accuracy: 80.90%
Epoch: [282]  [  0/312]  eta: 0:51:25  lr: 0.000042  min_lr: 0.000042  loss: 1.2990 (1.2990)  weight_decay: 0.0500 (0.0500)  time: 9.8891  data: 6.8993  max mem: 42573
Epoch: [282]  [ 10/312]  eta: 0:07:27  lr: 0.000041  min_lr: 0.000041  loss: 2.1283 (2.0066)  weight_decay: 0.0500 (0.0500)  time: 1.4822  data: 0.7193  max mem: 42573
Epoch: [282]  [ 20/312]  eta: 0:04:46  lr: 0.000041  min_lr: 0.000041  loss: 2.1077 (1.9521)  weight_decay: 0.0500 (0.0500)  time: 0.5375  data: 0.0508  max mem: 42573
Epoch: [282]  [ 30/312]  eta: 0:03:47  lr: 0.000041  min_lr: 0.000041  loss: 2.0244 (1.9669)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [282]  [ 40/312]  eta: 0:03:14  lr: 0.000041  min_lr: 0.000041  loss: 1.9501 (1.9805)  weight_decay: 0.0500 (0.0500)  time: 0.4332  data: 0.0004  max mem: 42573
Epoch: [282]  [ 50/312]  eta: 0:02:52  lr: 0.000041  min_lr: 0.000041  loss: 1.7239 (1.9370)  weight_decay: 0.0500 (0.0500)  time: 0.4332  data: 0.0004  max mem: 42573
Epoch: [282]  [ 60/312]  eta: 0:02:36  lr: 0.000041  min_lr: 0.000041  loss: 1.8601 (1.9757)  weight_decay: 0.0500 (0.0500)  time: 0.4332  data: 0.0004  max mem: 42573
Epoch: [282]  [ 70/312]  eta: 0:02:24  lr: 0.000041  min_lr: 0.000041  loss: 2.0706 (1.9790)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [282]  [ 80/312]  eta: 0:02:13  lr: 0.000040  min_lr: 0.000040  loss: 2.0854 (1.9929)  weight_decay: 0.0500 (0.0500)  time: 0.4332  data: 0.0004  max mem: 42573
Epoch: [282]  [ 90/312]  eta: 0:02:04  lr: 0.000040  min_lr: 0.000040  loss: 2.0865 (1.9841)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [282]  [100/312]  eta: 0:01:56  lr: 0.000040  min_lr: 0.000040  loss: 1.9734 (1.9762)  weight_decay: 0.0500 (0.0500)  time: 0.4377  data: 0.0004  max mem: 42573
Epoch: [282]  [110/312]  eta: 0:01:48  lr: 0.000040  min_lr: 0.000040  loss: 1.9734 (1.9696)  weight_decay: 0.0500 (0.0500)  time: 0.4375  data: 0.0004  max mem: 42573
Epoch: [282]  [120/312]  eta: 0:01:41  lr: 0.000040  min_lr: 0.000040  loss: 1.6776 (1.9597)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [282]  [130/312]  eta: 0:01:35  lr: 0.000040  min_lr: 0.000040  loss: 1.9873 (1.9693)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [282]  [140/312]  eta: 0:01:28  lr: 0.000040  min_lr: 0.000040  loss: 2.1618 (1.9839)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0003  max mem: 42573
Epoch: [282]  [150/312]  eta: 0:01:22  lr: 0.000040  min_lr: 0.000040  loss: 2.1618 (1.9843)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0003  max mem: 42573
Epoch: [282]  [160/312]  eta: 0:01:16  lr: 0.000039  min_lr: 0.000039  loss: 2.0797 (1.9826)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0003  max mem: 42573
Epoch: [282]  [170/312]  eta: 0:01:11  lr: 0.000039  min_lr: 0.000039  loss: 2.1203 (1.9855)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [282]  [180/312]  eta: 0:01:05  lr: 0.000039  min_lr: 0.000039  loss: 2.1369 (1.9919)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [282]  [190/312]  eta: 0:01:00  lr: 0.000039  min_lr: 0.000039  loss: 2.1657 (1.9936)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [282]  [200/312]  eta: 0:00:55  lr: 0.000039  min_lr: 0.000039  loss: 2.1474 (2.0030)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [282]  [210/312]  eta: 0:00:49  lr: 0.000039  min_lr: 0.000039  loss: 2.1474 (2.0094)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [282]  [220/312]  eta: 0:00:44  lr: 0.000039  min_lr: 0.000039  loss: 2.0639 (2.0072)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [282]  [230/312]  eta: 0:00:39  lr: 0.000038  min_lr: 0.000038  loss: 1.9357 (2.0047)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [282]  [240/312]  eta: 0:00:34  lr: 0.000038  min_lr: 0.000038  loss: 2.1742 (2.0137)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [282]  [250/312]  eta: 0:00:29  lr: 0.000038  min_lr: 0.000038  loss: 2.1510 (2.0107)  weight_decay: 0.0500 (0.0500)  time: 0.4331  data: 0.0004  max mem: 42573
Epoch: [282]  [260/312]  eta: 0:00:24  lr: 0.000038  min_lr: 0.000038  loss: 2.0801 (2.0139)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [282]  [270/312]  eta: 0:00:20  lr: 0.000038  min_lr: 0.000038  loss: 2.0616 (2.0088)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [282]  [280/312]  eta: 0:00:15  lr: 0.000038  min_lr: 0.000038  loss: 1.8304 (2.0046)  weight_decay: 0.0500 (0.0500)  time: 0.4343  data: 0.0009  max mem: 42573
Epoch: [282]  [290/312]  eta: 0:00:10  lr: 0.000038  min_lr: 0.000038  loss: 2.1388 (2.0124)  weight_decay: 0.0500 (0.0500)  time: 0.4364  data: 0.0008  max mem: 42573
Epoch: [282]  [300/312]  eta: 0:00:05  lr: 0.000037  min_lr: 0.000037  loss: 2.1728 (2.0134)  weight_decay: 0.0500 (0.0500)  time: 0.4347  data: 0.0001  max mem: 42573
Epoch: [282]  [310/312]  eta: 0:00:00  lr: 0.000037  min_lr: 0.000037  loss: 2.0194 (2.0146)  weight_decay: 0.0500 (0.0500)  time: 0.4321  data: 0.0001  max mem: 42573
Epoch: [282]  [311/312]  eta: 0:00:00  lr: 0.000037  min_lr: 0.000037  loss: 2.0194 (2.0151)  weight_decay: 0.0500 (0.0500)  time: 0.4321  data: 0.0001  max mem: 42573
Epoch: [282] Total time: 0:02:27 (0.4737 s / it)
Averaged stats: lr: 0.000037  min_lr: 0.000037  loss: 2.0194 (2.0285)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:00:41  loss: 0.5430 (0.5430)  acc1: 85.9375 (85.9375)  acc5: 96.3542 (96.3542)  time: 4.6495  data: 4.5413  max mem: 42573
Test:  [8/9]  eta: 0:00:00  loss: 0.7363 (0.7372)  acc1: 81.5104 (80.1920)  acc5: 95.8333 (95.3920)  time: 0.5924  data: 0.5047  max mem: 42573
Test: Total time: 0:00:05 (0.6063 s / it)
* Acc@1 80.868 Acc@5 95.440 loss 0.724
Accuracy of the model on the 50000 test images: 80.9%
Max accuracy: 80.90%
Epoch: [283]  [  0/312]  eta: 0:50:04  lr: 0.000037  min_lr: 0.000037  loss: 1.7375 (1.7375)  weight_decay: 0.0500 (0.0500)  time: 9.6285  data: 8.0071  max mem: 42573
Epoch: [283]  [ 10/312]  eta: 0:07:39  lr: 0.000037  min_lr: 0.000037  loss: 2.3358 (2.2026)  weight_decay: 0.0500 (0.0500)  time: 1.5215  data: 0.7469  max mem: 42573
Epoch: [283]  [ 20/312]  eta: 0:04:52  lr: 0.000037  min_lr: 0.000037  loss: 2.2467 (2.1426)  weight_decay: 0.0500 (0.0500)  time: 0.5717  data: 0.0106  max mem: 42573
Epoch: [283]  [ 30/312]  eta: 0:03:51  lr: 0.000037  min_lr: 0.000037  loss: 2.0720 (2.0851)  weight_decay: 0.0500 (0.0500)  time: 0.4332  data: 0.0003  max mem: 42573
Epoch: [283]  [ 40/312]  eta: 0:03:17  lr: 0.000037  min_lr: 0.000037  loss: 2.0339 (2.0768)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [283]  [ 50/312]  eta: 0:02:54  lr: 0.000037  min_lr: 0.000037  loss: 2.0564 (2.0735)  weight_decay: 0.0500 (0.0500)  time: 0.4331  data: 0.0004  max mem: 42573
Epoch: [283]  [ 60/312]  eta: 0:02:38  lr: 0.000036  min_lr: 0.000036  loss: 2.0564 (2.0572)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [283]  [ 70/312]  eta: 0:02:25  lr: 0.000036  min_lr: 0.000036  loss: 2.0975 (2.0527)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [283]  [ 80/312]  eta: 0:02:14  lr: 0.000036  min_lr: 0.000036  loss: 2.0975 (2.0608)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [283]  [ 90/312]  eta: 0:02:05  lr: 0.000036  min_lr: 0.000036  loss: 2.2985 (2.0909)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [283]  [100/312]  eta: 0:01:57  lr: 0.000036  min_lr: 0.000036  loss: 2.2643 (2.1067)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [283]  [110/312]  eta: 0:01:49  lr: 0.000036  min_lr: 0.000036  loss: 2.1678 (2.1044)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [283]  [120/312]  eta: 0:01:42  lr: 0.000036  min_lr: 0.000036  loss: 2.0789 (2.0995)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [283]  [130/312]  eta: 0:01:35  lr: 0.000036  min_lr: 0.000036  loss: 2.1099 (2.1078)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [283]  [140/312]  eta: 0:01:29  lr: 0.000035  min_lr: 0.000035  loss: 1.7466 (2.0684)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [283]  [150/312]  eta: 0:01:23  lr: 0.000035  min_lr: 0.000035  loss: 1.6314 (2.0649)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [283]  [160/312]  eta: 0:01:17  lr: 0.000035  min_lr: 0.000035  loss: 2.0126 (2.0561)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [283]  [170/312]  eta: 0:01:11  lr: 0.000035  min_lr: 0.000035  loss: 2.0995 (2.0581)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [283]  [180/312]  eta: 0:01:05  lr: 0.000035  min_lr: 0.000035  loss: 2.1249 (2.0567)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [283]  [190/312]  eta: 0:01:00  lr: 0.000035  min_lr: 0.000035  loss: 1.9738 (2.0562)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [283]  [200/312]  eta: 0:00:55  lr: 0.000035  min_lr: 0.000035  loss: 2.0822 (2.0547)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [283]  [210/312]  eta: 0:00:49  lr: 0.000034  min_lr: 0.000034  loss: 2.0844 (2.0578)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0003  max mem: 42573
Epoch: [283]  [220/312]  eta: 0:00:44  lr: 0.000034  min_lr: 0.000034  loss: 2.1707 (2.0625)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [283]  [230/312]  eta: 0:00:39  lr: 0.000034  min_lr: 0.000034  loss: 2.1707 (2.0600)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [283]  [240/312]  eta: 0:00:34  lr: 0.000034  min_lr: 0.000034  loss: 2.1932 (2.0642)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0003  max mem: 42573
Epoch: [283]  [250/312]  eta: 0:00:29  lr: 0.000034  min_lr: 0.000034  loss: 2.0524 (2.0581)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [283]  [260/312]  eta: 0:00:24  lr: 0.000034  min_lr: 0.000034  loss: 1.9804 (2.0554)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [283]  [270/312]  eta: 0:00:20  lr: 0.000034  min_lr: 0.000034  loss: 1.9022 (2.0483)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [283]  [280/312]  eta: 0:00:15  lr: 0.000034  min_lr: 0.000034  loss: 1.9022 (2.0480)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0009  max mem: 42573
Epoch: [283]  [290/312]  eta: 0:00:10  lr: 0.000033  min_lr: 0.000033  loss: 2.1144 (2.0426)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0008  max mem: 42573
Epoch: [283]  [300/312]  eta: 0:00:05  lr: 0.000033  min_lr: 0.000033  loss: 2.1067 (2.0438)  weight_decay: 0.0500 (0.0500)  time: 0.4321  data: 0.0001  max mem: 42573
Epoch: [283]  [310/312]  eta: 0:00:00  lr: 0.000033  min_lr: 0.000033  loss: 2.1825 (2.0514)  weight_decay: 0.0500 (0.0500)  time: 0.4382  data: 0.0001  max mem: 42573
Epoch: [283]  [311/312]  eta: 0:00:00  lr: 0.000033  min_lr: 0.000033  loss: 2.2089 (2.0519)  weight_decay: 0.0500 (0.0500)  time: 0.4382  data: 0.0001  max mem: 42573
Epoch: [283] Total time: 0:02:28 (0.4750 s / it)
Averaged stats: lr: 0.000033  min_lr: 0.000033  loss: 2.2089 (2.0304)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:00:42  loss: 0.5470 (0.5470)  acc1: 86.1979 (86.1979)  acc5: 96.3542 (96.3542)  time: 4.7039  data: 4.5957  max mem: 42573
Test:  [8/9]  eta: 0:00:00  loss: 0.7487 (0.7421)  acc1: 81.7708 (80.1280)  acc5: 96.0938 (95.3920)  time: 0.5979  data: 0.5107  max mem: 42573
Test: Total time: 0:00:05 (0.6100 s / it)
* Acc@1 80.924 Acc@5 95.418 loss 0.726
Accuracy of the model on the 50000 test images: 80.9%
Max accuracy: 80.92%
Epoch: [284]  [  0/312]  eta: 0:47:07  lr: 0.000033  min_lr: 0.000033  loss: 2.3251 (2.3251)  weight_decay: 0.0500 (0.0500)  time: 9.0636  data: 7.8067  max mem: 42573
Epoch: [284]  [ 10/312]  eta: 0:07:18  lr: 0.000033  min_lr: 0.000033  loss: 2.2265 (2.0909)  weight_decay: 0.0500 (0.0500)  time: 1.4534  data: 0.7311  max mem: 42573
Epoch: [284]  [ 20/312]  eta: 0:04:42  lr: 0.000033  min_lr: 0.000033  loss: 2.1983 (2.1801)  weight_decay: 0.0500 (0.0500)  time: 0.5628  data: 0.0120  max mem: 42573
Epoch: [284]  [ 30/312]  eta: 0:03:44  lr: 0.000033  min_lr: 0.000033  loss: 2.1212 (2.0570)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0003  max mem: 42573
Epoch: [284]  [ 40/312]  eta: 0:03:12  lr: 0.000033  min_lr: 0.000033  loss: 2.0060 (2.0831)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0003  max mem: 42573
Epoch: [284]  [ 50/312]  eta: 0:02:51  lr: 0.000032  min_lr: 0.000032  loss: 2.1669 (2.0831)  weight_decay: 0.0500 (0.0500)  time: 0.4331  data: 0.0003  max mem: 42573
Epoch: [284]  [ 60/312]  eta: 0:02:35  lr: 0.000032  min_lr: 0.000032  loss: 2.0828 (2.0590)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [284]  [ 70/312]  eta: 0:02:23  lr: 0.000032  min_lr: 0.000032  loss: 2.0828 (2.0543)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [284]  [ 80/312]  eta: 0:02:12  lr: 0.000032  min_lr: 0.000032  loss: 2.0988 (2.0581)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [284]  [ 90/312]  eta: 0:02:03  lr: 0.000032  min_lr: 0.000032  loss: 2.0988 (2.0537)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0003  max mem: 42573
Epoch: [284]  [100/312]  eta: 0:01:55  lr: 0.000032  min_lr: 0.000032  loss: 1.9098 (2.0282)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [284]  [110/312]  eta: 0:01:47  lr: 0.000032  min_lr: 0.000032  loss: 1.8203 (2.0199)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [284]  [120/312]  eta: 0:01:41  lr: 0.000032  min_lr: 0.000032  loss: 2.0205 (2.0203)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [284]  [130/312]  eta: 0:01:34  lr: 0.000031  min_lr: 0.000031  loss: 2.0914 (2.0291)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [284]  [140/312]  eta: 0:01:28  lr: 0.000031  min_lr: 0.000031  loss: 2.0914 (2.0323)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [284]  [150/312]  eta: 0:01:22  lr: 0.000031  min_lr: 0.000031  loss: 1.9648 (2.0235)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [284]  [160/312]  eta: 0:01:16  lr: 0.000031  min_lr: 0.000031  loss: 1.6143 (2.0042)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [284]  [170/312]  eta: 0:01:10  lr: 0.000031  min_lr: 0.000031  loss: 1.7654 (2.0063)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [284]  [180/312]  eta: 0:01:05  lr: 0.000031  min_lr: 0.000031  loss: 2.0677 (2.0045)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [284]  [190/312]  eta: 0:01:00  lr: 0.000031  min_lr: 0.000031  loss: 1.9412 (2.0022)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0003  max mem: 42573
Epoch: [284]  [200/312]  eta: 0:00:54  lr: 0.000031  min_lr: 0.000031  loss: 1.9412 (2.0008)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [284]  [210/312]  eta: 0:00:49  lr: 0.000030  min_lr: 0.000030  loss: 2.1633 (2.0087)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [284]  [220/312]  eta: 0:00:44  lr: 0.000030  min_lr: 0.000030  loss: 2.2427 (2.0129)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [284]  [230/312]  eta: 0:00:39  lr: 0.000030  min_lr: 0.000030  loss: 2.0258 (2.0063)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0003  max mem: 42573
Epoch: [284]  [240/312]  eta: 0:00:34  lr: 0.000030  min_lr: 0.000030  loss: 2.0057 (2.0132)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0003  max mem: 42573
Epoch: [284]  [250/312]  eta: 0:00:29  lr: 0.000030  min_lr: 0.000030  loss: 2.1650 (2.0221)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [284]  [260/312]  eta: 0:00:24  lr: 0.000030  min_lr: 0.000030  loss: 2.2198 (2.0299)  weight_decay: 0.0500 (0.0500)  time: 0.4441  data: 0.0003  max mem: 42573
Epoch: [284]  [270/312]  eta: 0:00:19  lr: 0.000030  min_lr: 0.000030  loss: 2.1978 (2.0345)  weight_decay: 0.0500 (0.0500)  time: 0.4439  data: 0.0004  max mem: 42573
Epoch: [284]  [280/312]  eta: 0:00:15  lr: 0.000030  min_lr: 0.000030  loss: 2.1581 (2.0376)  weight_decay: 0.0500 (0.0500)  time: 0.4342  data: 0.0016  max mem: 42573
Epoch: [284]  [290/312]  eta: 0:00:10  lr: 0.000030  min_lr: 0.000030  loss: 2.1581 (2.0391)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0015  max mem: 42573
Epoch: [284]  [300/312]  eta: 0:00:05  lr: 0.000029  min_lr: 0.000029  loss: 2.1874 (2.0371)  weight_decay: 0.0500 (0.0500)  time: 0.4322  data: 0.0001  max mem: 42573
Epoch: [284]  [310/312]  eta: 0:00:00  lr: 0.000029  min_lr: 0.000029  loss: 2.0370 (2.0349)  weight_decay: 0.0500 (0.0500)  time: 0.4321  data: 0.0001  max mem: 42573
Epoch: [284]  [311/312]  eta: 0:00:00  lr: 0.000029  min_lr: 0.000029  loss: 2.0370 (2.0332)  weight_decay: 0.0500 (0.0500)  time: 0.4321  data: 0.0001  max mem: 42573
Epoch: [284] Total time: 0:02:27 (0.4731 s / it)
Averaged stats: lr: 0.000029  min_lr: 0.000029  loss: 2.0370 (2.0452)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:00:41  loss: 0.5497 (0.5497)  acc1: 85.6771 (85.6771)  acc5: 96.3542 (96.3542)  time: 4.6400  data: 4.5329  max mem: 42573
Test:  [8/9]  eta: 0:00:00  loss: 0.7316 (0.7354)  acc1: 81.7708 (80.3520)  acc5: 96.0938 (95.4240)  time: 0.5911  data: 0.5037  max mem: 42573
Test: Total time: 0:00:05 (0.6110 s / it)
* Acc@1 80.864 Acc@5 95.454 loss 0.721
Accuracy of the model on the 50000 test images: 80.9%
Max accuracy: 80.92%
Epoch: [285]  [  0/312]  eta: 0:51:35  lr: 0.000029  min_lr: 0.000029  loss: 2.4522 (2.4522)  weight_decay: 0.0500 (0.0500)  time: 9.9226  data: 6.0572  max mem: 42573
Epoch: [285]  [ 10/312]  eta: 0:07:39  lr: 0.000029  min_lr: 0.000029  loss: 2.1773 (2.1278)  weight_decay: 0.0500 (0.0500)  time: 1.5210  data: 0.6167  max mem: 42573
Epoch: [285]  [ 20/312]  eta: 0:04:52  lr: 0.000029  min_lr: 0.000029  loss: 2.1331 (2.0803)  weight_decay: 0.0500 (0.0500)  time: 0.5569  data: 0.0365  max mem: 42573
Epoch: [285]  [ 30/312]  eta: 0:03:50  lr: 0.000029  min_lr: 0.000029  loss: 2.2154 (2.0951)  weight_decay: 0.0500 (0.0500)  time: 0.4331  data: 0.0003  max mem: 42573
Epoch: [285]  [ 40/312]  eta: 0:03:17  lr: 0.000029  min_lr: 0.000029  loss: 2.2117 (2.0699)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [285]  [ 50/312]  eta: 0:02:54  lr: 0.000029  min_lr: 0.000029  loss: 1.9500 (2.0518)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [285]  [ 60/312]  eta: 0:02:38  lr: 0.000029  min_lr: 0.000029  loss: 1.9766 (2.0515)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [285]  [ 70/312]  eta: 0:02:25  lr: 0.000028  min_lr: 0.000028  loss: 2.0985 (2.0429)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [285]  [ 80/312]  eta: 0:02:14  lr: 0.000028  min_lr: 0.000028  loss: 2.1535 (2.0590)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0003  max mem: 42573
Epoch: [285]  [ 90/312]  eta: 0:02:05  lr: 0.000028  min_lr: 0.000028  loss: 2.2030 (2.0629)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [285]  [100/312]  eta: 0:01:56  lr: 0.000028  min_lr: 0.000028  loss: 2.0736 (2.0476)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [285]  [110/312]  eta: 0:01:49  lr: 0.000028  min_lr: 0.000028  loss: 2.0026 (2.0329)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [285]  [120/312]  eta: 0:01:42  lr: 0.000028  min_lr: 0.000028  loss: 1.8724 (2.0229)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [285]  [130/312]  eta: 0:01:35  lr: 0.000028  min_lr: 0.000028  loss: 1.9690 (2.0227)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [285]  [140/312]  eta: 0:01:29  lr: 0.000028  min_lr: 0.000028  loss: 2.0835 (2.0167)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [285]  [150/312]  eta: 0:01:23  lr: 0.000027  min_lr: 0.000027  loss: 1.8773 (2.0087)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [285]  [160/312]  eta: 0:01:17  lr: 0.000027  min_lr: 0.000027  loss: 2.0734 (2.0183)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [285]  [170/312]  eta: 0:01:11  lr: 0.000027  min_lr: 0.000027  loss: 2.2173 (2.0349)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [285]  [180/312]  eta: 0:01:05  lr: 0.000027  min_lr: 0.000027  loss: 2.2063 (2.0368)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0003  max mem: 42573
Epoch: [285]  [190/312]  eta: 0:01:00  lr: 0.000027  min_lr: 0.000027  loss: 2.0305 (2.0309)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [285]  [200/312]  eta: 0:00:55  lr: 0.000027  min_lr: 0.000027  loss: 1.8212 (2.0210)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [285]  [210/312]  eta: 0:00:49  lr: 0.000027  min_lr: 0.000027  loss: 2.1300 (2.0276)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [285]  [220/312]  eta: 0:00:44  lr: 0.000027  min_lr: 0.000027  loss: 2.2385 (2.0283)  weight_decay: 0.0500 (0.0500)  time: 0.4332  data: 0.0004  max mem: 42573
Epoch: [285]  [230/312]  eta: 0:00:39  lr: 0.000027  min_lr: 0.000027  loss: 1.7559 (2.0187)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [285]  [240/312]  eta: 0:00:34  lr: 0.000026  min_lr: 0.000026  loss: 1.6949 (2.0148)  weight_decay: 0.0500 (0.0500)  time: 0.4355  data: 0.0004  max mem: 42573
Epoch: [285]  [250/312]  eta: 0:00:29  lr: 0.000026  min_lr: 0.000026  loss: 1.9996 (2.0078)  weight_decay: 0.0500 (0.0500)  time: 0.4354  data: 0.0004  max mem: 42573
Epoch: [285]  [260/312]  eta: 0:00:24  lr: 0.000026  min_lr: 0.000026  loss: 1.7724 (1.9972)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0003  max mem: 42573
Epoch: [285]  [270/312]  eta: 0:00:20  lr: 0.000026  min_lr: 0.000026  loss: 1.6875 (1.9942)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0003  max mem: 42573
Epoch: [285]  [280/312]  eta: 0:00:15  lr: 0.000026  min_lr: 0.000026  loss: 2.0534 (1.9974)  weight_decay: 0.0500 (0.0500)  time: 0.4341  data: 0.0009  max mem: 42573
Epoch: [285]  [290/312]  eta: 0:00:10  lr: 0.000026  min_lr: 0.000026  loss: 2.1224 (1.9968)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0008  max mem: 42573
Epoch: [285]  [300/312]  eta: 0:00:05  lr: 0.000026  min_lr: 0.000026  loss: 2.0758 (1.9979)  weight_decay: 0.0500 (0.0500)  time: 0.4321  data: 0.0001  max mem: 42573
Epoch: [285]  [310/312]  eta: 0:00:00  lr: 0.000026  min_lr: 0.000026  loss: 2.0973 (2.0008)  weight_decay: 0.0500 (0.0500)  time: 0.4320  data: 0.0001  max mem: 42573
Epoch: [285]  [311/312]  eta: 0:00:00  lr: 0.000026  min_lr: 0.000026  loss: 2.0513 (2.0008)  weight_decay: 0.0500 (0.0500)  time: 0.4320  data: 0.0001  max mem: 42573
Epoch: [285] Total time: 0:02:28 (0.4749 s / it)
Averaged stats: lr: 0.000026  min_lr: 0.000026  loss: 2.0513 (2.0191)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:00:43  loss: 0.5492 (0.5492)  acc1: 85.9375 (85.9375)  acc5: 95.8333 (95.8333)  time: 4.8613  data: 4.7529  max mem: 42573
Test:  [8/9]  eta: 0:00:00  loss: 0.7429 (0.7336)  acc1: 81.5104 (80.3840)  acc5: 95.8333 (95.2960)  time: 0.6158  data: 0.5282  max mem: 42573
Test: Total time: 0:00:05 (0.6369 s / it)
* Acc@1 80.948 Acc@5 95.402 loss 0.721
Accuracy of the model on the 50000 test images: 80.9%
Max accuracy: 80.95%
Epoch: [286]  [  0/312]  eta: 0:49:54  lr: 0.000026  min_lr: 0.000026  loss: 1.6731 (1.6731)  weight_decay: 0.0500 (0.0500)  time: 9.5988  data: 7.7047  max mem: 42573
Epoch: [286]  [ 10/312]  eta: 0:07:14  lr: 0.000026  min_lr: 0.000026  loss: 2.2251 (2.1650)  weight_decay: 0.0500 (0.0500)  time: 1.4374  data: 0.7009  max mem: 42573
Epoch: [286]  [ 20/312]  eta: 0:04:40  lr: 0.000025  min_lr: 0.000025  loss: 2.0140 (2.0248)  weight_decay: 0.0500 (0.0500)  time: 0.5270  data: 0.0005  max mem: 42573
Epoch: [286]  [ 30/312]  eta: 0:03:42  lr: 0.000025  min_lr: 0.000025  loss: 2.1122 (2.1276)  weight_decay: 0.0500 (0.0500)  time: 0.4332  data: 0.0004  max mem: 42573
Epoch: [286]  [ 40/312]  eta: 0:03:11  lr: 0.000025  min_lr: 0.000025  loss: 2.1489 (2.1111)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0005  max mem: 42573
Epoch: [286]  [ 50/312]  eta: 0:02:50  lr: 0.000025  min_lr: 0.000025  loss: 2.0874 (2.0939)  weight_decay: 0.0500 (0.0500)  time: 0.4331  data: 0.0004  max mem: 42573
Epoch: [286]  [ 60/312]  eta: 0:02:34  lr: 0.000025  min_lr: 0.000025  loss: 2.0392 (2.0614)  weight_decay: 0.0500 (0.0500)  time: 0.4332  data: 0.0004  max mem: 42573
Epoch: [286]  [ 70/312]  eta: 0:02:22  lr: 0.000025  min_lr: 0.000025  loss: 2.0392 (2.0568)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [286]  [ 80/312]  eta: 0:02:12  lr: 0.000025  min_lr: 0.000025  loss: 2.1637 (2.0551)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [286]  [ 90/312]  eta: 0:02:03  lr: 0.000025  min_lr: 0.000025  loss: 2.1345 (2.0392)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0003  max mem: 42573
Epoch: [286]  [100/312]  eta: 0:01:55  lr: 0.000025  min_lr: 0.000025  loss: 1.8215 (2.0241)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [286]  [110/312]  eta: 0:01:47  lr: 0.000024  min_lr: 0.000024  loss: 1.8184 (2.0106)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [286]  [120/312]  eta: 0:01:40  lr: 0.000024  min_lr: 0.000024  loss: 1.9669 (2.0117)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [286]  [130/312]  eta: 0:01:34  lr: 0.000024  min_lr: 0.000024  loss: 2.1285 (2.0182)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [286]  [140/312]  eta: 0:01:28  lr: 0.000024  min_lr: 0.000024  loss: 2.2014 (2.0279)  weight_decay: 0.0500 (0.0500)  time: 0.4332  data: 0.0004  max mem: 42573
Epoch: [286]  [150/312]  eta: 0:01:22  lr: 0.000024  min_lr: 0.000024  loss: 2.3066 (2.0377)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [286]  [160/312]  eta: 0:01:16  lr: 0.000024  min_lr: 0.000024  loss: 1.9867 (2.0373)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [286]  [170/312]  eta: 0:01:10  lr: 0.000024  min_lr: 0.000024  loss: 1.9777 (2.0332)  weight_decay: 0.0500 (0.0500)  time: 0.4332  data: 0.0004  max mem: 42573
Epoch: [286]  [180/312]  eta: 0:01:05  lr: 0.000024  min_lr: 0.000024  loss: 2.1719 (2.0291)  weight_decay: 0.0500 (0.0500)  time: 0.4332  data: 0.0004  max mem: 42573
Epoch: [286]  [190/312]  eta: 0:00:59  lr: 0.000024  min_lr: 0.000024  loss: 1.8708 (2.0240)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [286]  [200/312]  eta: 0:00:54  lr: 0.000023  min_lr: 0.000023  loss: 1.9198 (2.0231)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [286]  [210/312]  eta: 0:00:49  lr: 0.000023  min_lr: 0.000023  loss: 1.8957 (2.0185)  weight_decay: 0.0500 (0.0500)  time: 0.4372  data: 0.0003  max mem: 42573
Epoch: [286]  [220/312]  eta: 0:00:44  lr: 0.000023  min_lr: 0.000023  loss: 1.9775 (2.0222)  weight_decay: 0.0500 (0.0500)  time: 0.4373  data: 0.0003  max mem: 42573
Epoch: [286]  [230/312]  eta: 0:00:39  lr: 0.000023  min_lr: 0.000023  loss: 2.0087 (2.0202)  weight_decay: 0.0500 (0.0500)  time: 0.4332  data: 0.0004  max mem: 42573
Epoch: [286]  [240/312]  eta: 0:00:34  lr: 0.000023  min_lr: 0.000023  loss: 2.0065 (2.0195)  weight_decay: 0.0500 (0.0500)  time: 0.4332  data: 0.0004  max mem: 42573
Epoch: [286]  [250/312]  eta: 0:00:29  lr: 0.000023  min_lr: 0.000023  loss: 2.0065 (2.0204)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [286]  [260/312]  eta: 0:00:24  lr: 0.000023  min_lr: 0.000023  loss: 2.0579 (2.0215)  weight_decay: 0.0500 (0.0500)  time: 0.4332  data: 0.0004  max mem: 42573
Epoch: [286]  [270/312]  eta: 0:00:19  lr: 0.000023  min_lr: 0.000023  loss: 2.1222 (2.0304)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [286]  [280/312]  eta: 0:00:15  lr: 0.000023  min_lr: 0.000023  loss: 2.2784 (2.0289)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0009  max mem: 42573
Epoch: [286]  [290/312]  eta: 0:00:10  lr: 0.000022  min_lr: 0.000022  loss: 2.1189 (2.0327)  weight_decay: 0.0500 (0.0500)  time: 0.4332  data: 0.0008  max mem: 42573
Epoch: [286]  [300/312]  eta: 0:00:05  lr: 0.000022  min_lr: 0.000022  loss: 1.9340 (2.0201)  weight_decay: 0.0500 (0.0500)  time: 0.4320  data: 0.0001  max mem: 42573
Epoch: [286]  [310/312]  eta: 0:00:00  lr: 0.000022  min_lr: 0.000022  loss: 1.7393 (2.0174)  weight_decay: 0.0500 (0.0500)  time: 0.4319  data: 0.0001  max mem: 42573
Epoch: [286]  [311/312]  eta: 0:00:00  lr: 0.000022  min_lr: 0.000022  loss: 1.7393 (2.0173)  weight_decay: 0.0500 (0.0500)  time: 0.4319  data: 0.0001  max mem: 42573
Epoch: [286] Total time: 0:02:27 (0.4719 s / it)
Averaged stats: lr: 0.000022  min_lr: 0.000022  loss: 1.7393 (2.0220)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:00:43  loss: 0.5459 (0.5459)  acc1: 86.7188 (86.7188)  acc5: 96.3542 (96.3542)  time: 4.7848  data: 4.6765  max mem: 42573
Test:  [8/9]  eta: 0:00:00  loss: 0.7298 (0.7313)  acc1: 82.2917 (80.3840)  acc5: 96.0938 (95.3280)  time: 0.6068  data: 0.5197  max mem: 42573
Test: Total time: 0:00:05 (0.6216 s / it)
* Acc@1 80.980 Acc@5 95.434 loss 0.719
Accuracy of the model on the 50000 test images: 81.0%
Max accuracy: 80.98%
Epoch: [287]  [  0/312]  eta: 0:50:41  lr: 0.000022  min_lr: 0.000022  loss: 2.2781 (2.2781)  weight_decay: 0.0500 (0.0500)  time: 9.7492  data: 8.4668  max mem: 42573
Epoch: [287]  [ 10/312]  eta: 0:07:10  lr: 0.000022  min_lr: 0.000022  loss: 1.8516 (1.8150)  weight_decay: 0.0500 (0.0500)  time: 1.4264  data: 0.7786  max mem: 42573
Epoch: [287]  [ 20/312]  eta: 0:04:38  lr: 0.000022  min_lr: 0.000022  loss: 1.8878 (1.9398)  weight_decay: 0.0500 (0.0500)  time: 0.5137  data: 0.0051  max mem: 42573
Epoch: [287]  [ 30/312]  eta: 0:03:41  lr: 0.000022  min_lr: 0.000022  loss: 2.0983 (1.9596)  weight_decay: 0.0500 (0.0500)  time: 0.4332  data: 0.0004  max mem: 42573
Epoch: [287]  [ 40/312]  eta: 0:03:10  lr: 0.000022  min_lr: 0.000022  loss: 1.9801 (1.9495)  weight_decay: 0.0500 (0.0500)  time: 0.4332  data: 0.0004  max mem: 42573
Epoch: [287]  [ 50/312]  eta: 0:02:49  lr: 0.000022  min_lr: 0.000022  loss: 1.9801 (1.9531)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [287]  [ 60/312]  eta: 0:02:34  lr: 0.000022  min_lr: 0.000022  loss: 1.8468 (1.9326)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [287]  [ 70/312]  eta: 0:02:22  lr: 0.000022  min_lr: 0.000022  loss: 1.8468 (1.9544)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [287]  [ 80/312]  eta: 0:02:11  lr: 0.000021  min_lr: 0.000021  loss: 2.0866 (1.9526)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [287]  [ 90/312]  eta: 0:02:02  lr: 0.000021  min_lr: 0.000021  loss: 1.9444 (1.9410)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [287]  [100/312]  eta: 0:01:54  lr: 0.000021  min_lr: 0.000021  loss: 1.8978 (1.9386)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [287]  [110/312]  eta: 0:01:47  lr: 0.000021  min_lr: 0.000021  loss: 2.0756 (1.9474)  weight_decay: 0.0500 (0.0500)  time: 0.4332  data: 0.0004  max mem: 42573
Epoch: [287]  [120/312]  eta: 0:01:40  lr: 0.000021  min_lr: 0.000021  loss: 2.0764 (1.9470)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [287]  [130/312]  eta: 0:01:34  lr: 0.000021  min_lr: 0.000021  loss: 2.0565 (1.9583)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [287]  [140/312]  eta: 0:01:27  lr: 0.000021  min_lr: 0.000021  loss: 2.0565 (1.9623)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [287]  [150/312]  eta: 0:01:21  lr: 0.000021  min_lr: 0.000021  loss: 1.9465 (1.9604)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [287]  [160/312]  eta: 0:01:16  lr: 0.000021  min_lr: 0.000021  loss: 1.8963 (1.9569)  weight_decay: 0.0500 (0.0500)  time: 0.4332  data: 0.0004  max mem: 42573
Epoch: [287]  [170/312]  eta: 0:01:10  lr: 0.000020  min_lr: 0.000020  loss: 1.8963 (1.9523)  weight_decay: 0.0500 (0.0500)  time: 0.4332  data: 0.0003  max mem: 42573
Epoch: [287]  [180/312]  eta: 0:01:05  lr: 0.000020  min_lr: 0.000020  loss: 1.9779 (1.9543)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0003  max mem: 42573
Epoch: [287]  [190/312]  eta: 0:01:00  lr: 0.000020  min_lr: 0.000020  loss: 2.0399 (1.9622)  weight_decay: 0.0500 (0.0500)  time: 0.4603  data: 0.0004  max mem: 42573
Epoch: [287]  [200/312]  eta: 0:00:54  lr: 0.000020  min_lr: 0.000020  loss: 1.9980 (1.9622)  weight_decay: 0.0500 (0.0500)  time: 0.4602  data: 0.0004  max mem: 42573
Epoch: [287]  [210/312]  eta: 0:00:49  lr: 0.000020  min_lr: 0.000020  loss: 1.9721 (1.9633)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [287]  [220/312]  eta: 0:00:44  lr: 0.000020  min_lr: 0.000020  loss: 1.9883 (1.9631)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [287]  [230/312]  eta: 0:00:39  lr: 0.000020  min_lr: 0.000020  loss: 2.0196 (1.9649)  weight_decay: 0.0500 (0.0500)  time: 0.4332  data: 0.0004  max mem: 42573
Epoch: [287]  [240/312]  eta: 0:00:34  lr: 0.000020  min_lr: 0.000020  loss: 2.1176 (1.9669)  weight_decay: 0.0500 (0.0500)  time: 0.4332  data: 0.0004  max mem: 42573
Epoch: [287]  [250/312]  eta: 0:00:29  lr: 0.000020  min_lr: 0.000020  loss: 1.8811 (1.9651)  weight_decay: 0.0500 (0.0500)  time: 0.4331  data: 0.0004  max mem: 42573
Epoch: [287]  [260/312]  eta: 0:00:24  lr: 0.000020  min_lr: 0.000020  loss: 1.9212 (1.9636)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [287]  [270/312]  eta: 0:00:19  lr: 0.000020  min_lr: 0.000020  loss: 2.0842 (1.9637)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [287]  [280/312]  eta: 0:00:15  lr: 0.000019  min_lr: 0.000019  loss: 2.1170 (1.9720)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0009  max mem: 42573
Epoch: [287]  [290/312]  eta: 0:00:10  lr: 0.000019  min_lr: 0.000019  loss: 2.1207 (1.9731)  weight_decay: 0.0500 (0.0500)  time: 0.4332  data: 0.0008  max mem: 42573
Epoch: [287]  [300/312]  eta: 0:00:05  lr: 0.000019  min_lr: 0.000019  loss: 2.0388 (1.9726)  weight_decay: 0.0500 (0.0500)  time: 0.4321  data: 0.0001  max mem: 42573
Epoch: [287]  [310/312]  eta: 0:00:00  lr: 0.000019  min_lr: 0.000019  loss: 2.0087 (1.9712)  weight_decay: 0.0500 (0.0500)  time: 0.4321  data: 0.0001  max mem: 42573
Epoch: [287]  [311/312]  eta: 0:00:00  lr: 0.000019  min_lr: 0.000019  loss: 2.0153 (1.9719)  weight_decay: 0.0500 (0.0500)  time: 0.4321  data: 0.0001  max mem: 42573
Epoch: [287] Total time: 0:02:27 (0.4732 s / it)
Averaged stats: lr: 0.000019  min_lr: 0.000019  loss: 2.0153 (2.0241)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:00:39  loss: 0.5463 (0.5463)  acc1: 86.1979 (86.1979)  acc5: 96.6146 (96.6146)  time: 4.3770  data: 4.2684  max mem: 42573
Test:  [8/9]  eta: 0:00:00  loss: 0.7308 (0.7289)  acc1: 81.5104 (80.2240)  acc5: 96.3542 (95.4560)  time: 0.5622  data: 0.4743  max mem: 42573
Test: Total time: 0:00:05 (0.5708 s / it)
* Acc@1 81.036 Acc@5 95.436 loss 0.718
Accuracy of the model on the 50000 test images: 81.0%
Max accuracy: 81.04%
Epoch: [288]  [  0/312]  eta: 0:47:34  lr: 0.000019  min_lr: 0.000019  loss: 1.7295 (1.7295)  weight_decay: 0.0500 (0.0500)  time: 9.1486  data: 7.1457  max mem: 42573
Epoch: [288]  [ 10/312]  eta: 0:07:28  lr: 0.000019  min_lr: 0.000019  loss: 2.2220 (2.1027)  weight_decay: 0.0500 (0.0500)  time: 1.4857  data: 0.8145  max mem: 42573
Epoch: [288]  [ 20/312]  eta: 0:04:47  lr: 0.000019  min_lr: 0.000019  loss: 2.1729 (2.0427)  weight_decay: 0.0500 (0.0500)  time: 0.5762  data: 0.0909  max mem: 42573
Epoch: [288]  [ 30/312]  eta: 0:03:47  lr: 0.000019  min_lr: 0.000019  loss: 2.1082 (2.0081)  weight_decay: 0.0500 (0.0500)  time: 0.4331  data: 0.0004  max mem: 42573
Epoch: [288]  [ 40/312]  eta: 0:03:14  lr: 0.000019  min_lr: 0.000019  loss: 2.0975 (2.0265)  weight_decay: 0.0500 (0.0500)  time: 0.4332  data: 0.0004  max mem: 42573
Epoch: [288]  [ 50/312]  eta: 0:02:52  lr: 0.000019  min_lr: 0.000019  loss: 2.1991 (2.0602)  weight_decay: 0.0500 (0.0500)  time: 0.4331  data: 0.0004  max mem: 42573
Epoch: [288]  [ 60/312]  eta: 0:02:36  lr: 0.000019  min_lr: 0.000019  loss: 2.1846 (2.0639)  weight_decay: 0.0500 (0.0500)  time: 0.4332  data: 0.0004  max mem: 42573
Epoch: [288]  [ 70/312]  eta: 0:02:24  lr: 0.000018  min_lr: 0.000018  loss: 2.0738 (2.0753)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [288]  [ 80/312]  eta: 0:02:13  lr: 0.000018  min_lr: 0.000018  loss: 2.2181 (2.0973)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [288]  [ 90/312]  eta: 0:02:04  lr: 0.000018  min_lr: 0.000018  loss: 2.0847 (2.0749)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [288]  [100/312]  eta: 0:01:56  lr: 0.000018  min_lr: 0.000018  loss: 2.0596 (2.0744)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [288]  [110/312]  eta: 0:01:48  lr: 0.000018  min_lr: 0.000018  loss: 2.0596 (2.0614)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [288]  [120/312]  eta: 0:01:41  lr: 0.000018  min_lr: 0.000018  loss: 2.0604 (2.0692)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0003  max mem: 42573
Epoch: [288]  [130/312]  eta: 0:01:34  lr: 0.000018  min_lr: 0.000018  loss: 2.2072 (2.0667)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [288]  [140/312]  eta: 0:01:28  lr: 0.000018  min_lr: 0.000018  loss: 2.0777 (2.0694)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [288]  [150/312]  eta: 0:01:22  lr: 0.000018  min_lr: 0.000018  loss: 2.0777 (2.0592)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [288]  [160/312]  eta: 0:01:16  lr: 0.000018  min_lr: 0.000018  loss: 2.0883 (2.0603)  weight_decay: 0.0500 (0.0500)  time: 0.4332  data: 0.0004  max mem: 42573
Epoch: [288]  [170/312]  eta: 0:01:11  lr: 0.000017  min_lr: 0.000017  loss: 2.1935 (2.0667)  weight_decay: 0.0500 (0.0500)  time: 0.4332  data: 0.0003  max mem: 42573
Epoch: [288]  [180/312]  eta: 0:01:05  lr: 0.000017  min_lr: 0.000017  loss: 2.1467 (2.0654)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0003  max mem: 42573
Epoch: [288]  [190/312]  eta: 0:01:00  lr: 0.000017  min_lr: 0.000017  loss: 1.9915 (2.0635)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0003  max mem: 42573
Epoch: [288]  [200/312]  eta: 0:00:54  lr: 0.000017  min_lr: 0.000017  loss: 1.8421 (2.0588)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0003  max mem: 42573
Epoch: [288]  [210/312]  eta: 0:00:49  lr: 0.000017  min_lr: 0.000017  loss: 2.1111 (2.0614)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [288]  [220/312]  eta: 0:00:44  lr: 0.000017  min_lr: 0.000017  loss: 2.1111 (2.0560)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [288]  [230/312]  eta: 0:00:39  lr: 0.000017  min_lr: 0.000017  loss: 2.1583 (2.0610)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [288]  [240/312]  eta: 0:00:34  lr: 0.000017  min_lr: 0.000017  loss: 2.1114 (2.0567)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [288]  [250/312]  eta: 0:00:29  lr: 0.000017  min_lr: 0.000017  loss: 2.1114 (2.0594)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [288]  [260/312]  eta: 0:00:24  lr: 0.000017  min_lr: 0.000017  loss: 2.2002 (2.0618)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [288]  [270/312]  eta: 0:00:19  lr: 0.000017  min_lr: 0.000017  loss: 1.9676 (2.0516)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0003  max mem: 42573
Epoch: [288]  [280/312]  eta: 0:00:15  lr: 0.000016  min_lr: 0.000016  loss: 1.9333 (2.0494)  weight_decay: 0.0500 (0.0500)  time: 0.4341  data: 0.0009  max mem: 42573
Epoch: [288]  [290/312]  eta: 0:00:10  lr: 0.000016  min_lr: 0.000016  loss: 1.9333 (2.0474)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0008  max mem: 42573
Epoch: [288]  [300/312]  eta: 0:00:05  lr: 0.000016  min_lr: 0.000016  loss: 2.1036 (2.0499)  weight_decay: 0.0500 (0.0500)  time: 0.4322  data: 0.0001  max mem: 42573
Epoch: [288]  [310/312]  eta: 0:00:00  lr: 0.000016  min_lr: 0.000016  loss: 2.1684 (2.0473)  weight_decay: 0.0500 (0.0500)  time: 0.4321  data: 0.0001  max mem: 42573
Epoch: [288]  [311/312]  eta: 0:00:00  lr: 0.000016  min_lr: 0.000016  loss: 2.1684 (2.0482)  weight_decay: 0.0500 (0.0500)  time: 0.4320  data: 0.0001  max mem: 42573
Epoch: [288] Total time: 0:02:27 (0.4735 s / it)
Averaged stats: lr: 0.000016  min_lr: 0.000016  loss: 2.1684 (2.0139)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:00:42  loss: 0.5487 (0.5487)  acc1: 85.4167 (85.4167)  acc5: 96.3542 (96.3542)  time: 4.7068  data: 4.5986  max mem: 42573
Test:  [8/9]  eta: 0:00:00  loss: 0.7308 (0.7294)  acc1: 81.7708 (80.2560)  acc5: 96.0938 (95.3600)  time: 0.5981  data: 0.5110  max mem: 42573
Test: Total time: 0:00:05 (0.6168 s / it)
* Acc@1 81.040 Acc@5 95.476 loss 0.718
Accuracy of the model on the 50000 test images: 81.0%
Max accuracy: 81.04%
Epoch: [289]  [  0/312]  eta: 0:52:07  lr: 0.000016  min_lr: 0.000016  loss: 1.9173 (1.9173)  weight_decay: 0.0500 (0.0500)  time: 10.0236  data: 8.9860  max mem: 42573
Epoch: [289]  [ 10/312]  eta: 0:07:10  lr: 0.000016  min_lr: 0.000016  loss: 2.0335 (2.0697)  weight_decay: 0.0500 (0.0500)  time: 1.4249  data: 0.8174  max mem: 42573
Epoch: [289]  [ 20/312]  eta: 0:04:38  lr: 0.000016  min_lr: 0.000016  loss: 2.1955 (2.1598)  weight_decay: 0.0500 (0.0500)  time: 0.4990  data: 0.0005  max mem: 42573
Epoch: [289]  [ 30/312]  eta: 0:03:41  lr: 0.000016  min_lr: 0.000016  loss: 2.1713 (2.1397)  weight_decay: 0.0500 (0.0500)  time: 0.4332  data: 0.0004  max mem: 42573
Epoch: [289]  [ 40/312]  eta: 0:03:10  lr: 0.000016  min_lr: 0.000016  loss: 2.1173 (2.1176)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [289]  [ 50/312]  eta: 0:02:49  lr: 0.000016  min_lr: 0.000016  loss: 2.1813 (2.1159)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [289]  [ 60/312]  eta: 0:02:34  lr: 0.000016  min_lr: 0.000016  loss: 2.0748 (2.0988)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [289]  [ 70/312]  eta: 0:02:22  lr: 0.000016  min_lr: 0.000016  loss: 1.9828 (2.0924)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [289]  [ 80/312]  eta: 0:02:11  lr: 0.000016  min_lr: 0.000016  loss: 2.0981 (2.0765)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [289]  [ 90/312]  eta: 0:02:02  lr: 0.000015  min_lr: 0.000015  loss: 2.0409 (2.0583)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [289]  [100/312]  eta: 0:01:54  lr: 0.000015  min_lr: 0.000015  loss: 1.9763 (2.0504)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [289]  [110/312]  eta: 0:01:47  lr: 0.000015  min_lr: 0.000015  loss: 1.9763 (2.0397)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [289]  [120/312]  eta: 0:01:40  lr: 0.000015  min_lr: 0.000015  loss: 1.8243 (2.0197)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [289]  [130/312]  eta: 0:01:34  lr: 0.000015  min_lr: 0.000015  loss: 1.9052 (2.0293)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [289]  [140/312]  eta: 0:01:27  lr: 0.000015  min_lr: 0.000015  loss: 2.2340 (2.0479)  weight_decay: 0.0500 (0.0500)  time: 0.4332  data: 0.0004  max mem: 42573
Epoch: [289]  [150/312]  eta: 0:01:21  lr: 0.000015  min_lr: 0.000015  loss: 2.3054 (2.0595)  weight_decay: 0.0500 (0.0500)  time: 0.4332  data: 0.0004  max mem: 42573
Epoch: [289]  [160/312]  eta: 0:01:16  lr: 0.000015  min_lr: 0.000015  loss: 2.3003 (2.0662)  weight_decay: 0.0500 (0.0500)  time: 0.4332  data: 0.0004  max mem: 42573
Epoch: [289]  [170/312]  eta: 0:01:10  lr: 0.000015  min_lr: 0.000015  loss: 2.0690 (2.0645)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [289]  [180/312]  eta: 0:01:05  lr: 0.000015  min_lr: 0.000015  loss: 2.0226 (2.0683)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [289]  [190/312]  eta: 0:00:59  lr: 0.000015  min_lr: 0.000015  loss: 2.1139 (2.0694)  weight_decay: 0.0500 (0.0500)  time: 0.4332  data: 0.0004  max mem: 42573
Epoch: [289]  [200/312]  eta: 0:00:54  lr: 0.000014  min_lr: 0.000014  loss: 2.0489 (2.0683)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [289]  [210/312]  eta: 0:00:49  lr: 0.000014  min_lr: 0.000014  loss: 2.0890 (2.0711)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [289]  [220/312]  eta: 0:00:44  lr: 0.000014  min_lr: 0.000014  loss: 1.9773 (2.0682)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [289]  [230/312]  eta: 0:00:39  lr: 0.000014  min_lr: 0.000014  loss: 1.9773 (2.0638)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [289]  [240/312]  eta: 0:00:34  lr: 0.000014  min_lr: 0.000014  loss: 1.9994 (2.0544)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [289]  [250/312]  eta: 0:00:29  lr: 0.000014  min_lr: 0.000014  loss: 1.8444 (2.0526)  weight_decay: 0.0500 (0.0500)  time: 0.4331  data: 0.0004  max mem: 42573
Epoch: [289]  [260/312]  eta: 0:00:24  lr: 0.000014  min_lr: 0.000014  loss: 2.0971 (2.0525)  weight_decay: 0.0500 (0.0500)  time: 0.4332  data: 0.0004  max mem: 42573
Epoch: [289]  [270/312]  eta: 0:00:19  lr: 0.000014  min_lr: 0.000014  loss: 2.1424 (2.0554)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [289]  [280/312]  eta: 0:00:15  lr: 0.000014  min_lr: 0.000014  loss: 2.0302 (2.0542)  weight_decay: 0.0500 (0.0500)  time: 0.4344  data: 0.0009  max mem: 42573
Epoch: [289]  [290/312]  eta: 0:00:10  lr: 0.000014  min_lr: 0.000014  loss: 1.9753 (2.0541)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0008  max mem: 42573
Epoch: [289]  [300/312]  eta: 0:00:05  lr: 0.000014  min_lr: 0.000014  loss: 2.1538 (2.0540)  weight_decay: 0.0500 (0.0500)  time: 0.4323  data: 0.0001  max mem: 42573
Epoch: [289]  [310/312]  eta: 0:00:00  lr: 0.000014  min_lr: 0.000014  loss: 2.1538 (2.0562)  weight_decay: 0.0500 (0.0500)  time: 0.4322  data: 0.0001  max mem: 42573
Epoch: [289]  [311/312]  eta: 0:00:00  lr: 0.000014  min_lr: 0.000014  loss: 2.1445 (2.0542)  weight_decay: 0.0500 (0.0500)  time: 0.4322  data: 0.0001  max mem: 42573
Epoch: [289] Total time: 0:02:27 (0.4715 s / it)
Averaged stats: lr: 0.000014  min_lr: 0.000014  loss: 2.1445 (2.0240)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:00:42  loss: 0.5436 (0.5436)  acc1: 86.1979 (86.1979)  acc5: 96.3542 (96.3542)  time: 4.6795  data: 4.5714  max mem: 42573
Test:  [8/9]  eta: 0:00:00  loss: 0.7338 (0.7294)  acc1: 81.7708 (80.2560)  acc5: 96.0938 (95.3920)  time: 0.5969  data: 0.5080  max mem: 42573
Test: Total time: 0:00:05 (0.6201 s / it)
* Acc@1 81.048 Acc@5 95.472 loss 0.718
Accuracy of the model on the 50000 test images: 81.0%
Max accuracy: 81.05%
Epoch: [290]  [  0/312]  eta: 0:49:45  lr: 0.000014  min_lr: 0.000014  loss: 1.4251 (1.4251)  weight_decay: 0.0500 (0.0500)  time: 9.5679  data: 7.0722  max mem: 42573
Epoch: [290]  [ 10/312]  eta: 0:07:16  lr: 0.000013  min_lr: 0.000013  loss: 1.8748 (1.8376)  weight_decay: 0.0500 (0.0500)  time: 1.4445  data: 0.6433  max mem: 42573
Epoch: [290]  [ 20/312]  eta: 0:04:41  lr: 0.000013  min_lr: 0.000013  loss: 1.9951 (1.9617)  weight_decay: 0.0500 (0.0500)  time: 0.5327  data: 0.0004  max mem: 42573
Epoch: [290]  [ 30/312]  eta: 0:03:43  lr: 0.000013  min_lr: 0.000013  loss: 2.1209 (2.0440)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0003  max mem: 42573
Epoch: [290]  [ 40/312]  eta: 0:03:11  lr: 0.000013  min_lr: 0.000013  loss: 2.1447 (2.0578)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [290]  [ 50/312]  eta: 0:02:50  lr: 0.000013  min_lr: 0.000013  loss: 2.1001 (2.0686)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [290]  [ 60/312]  eta: 0:02:35  lr: 0.000013  min_lr: 0.000013  loss: 2.0866 (2.0292)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [290]  [ 70/312]  eta: 0:02:22  lr: 0.000013  min_lr: 0.000013  loss: 2.0866 (2.0535)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [290]  [ 80/312]  eta: 0:02:12  lr: 0.000013  min_lr: 0.000013  loss: 2.0987 (2.0423)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0003  max mem: 42573
Epoch: [290]  [ 90/312]  eta: 0:02:03  lr: 0.000013  min_lr: 0.000013  loss: 2.0969 (2.0487)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [290]  [100/312]  eta: 0:01:55  lr: 0.000013  min_lr: 0.000013  loss: 2.0969 (2.0349)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [290]  [110/312]  eta: 0:01:47  lr: 0.000013  min_lr: 0.000013  loss: 2.0274 (2.0367)  weight_decay: 0.0500 (0.0500)  time: 0.4383  data: 0.0004  max mem: 42573
Epoch: [290]  [120/312]  eta: 0:01:41  lr: 0.000013  min_lr: 0.000013  loss: 2.1608 (2.0463)  weight_decay: 0.0500 (0.0500)  time: 0.4383  data: 0.0004  max mem: 42573
Epoch: [290]  [130/312]  eta: 0:01:34  lr: 0.000013  min_lr: 0.000013  loss: 2.2246 (2.0493)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [290]  [140/312]  eta: 0:01:28  lr: 0.000012  min_lr: 0.000012  loss: 2.0229 (2.0480)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0005  max mem: 42573
Epoch: [290]  [150/312]  eta: 0:01:22  lr: 0.000012  min_lr: 0.000012  loss: 2.0138 (2.0444)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [290]  [160/312]  eta: 0:01:16  lr: 0.000012  min_lr: 0.000012  loss: 2.0896 (2.0469)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [290]  [170/312]  eta: 0:01:10  lr: 0.000012  min_lr: 0.000012  loss: 2.0896 (2.0497)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [290]  [180/312]  eta: 0:01:05  lr: 0.000012  min_lr: 0.000012  loss: 1.9446 (2.0406)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [290]  [190/312]  eta: 0:01:00  lr: 0.000012  min_lr: 0.000012  loss: 1.7868 (2.0357)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [290]  [200/312]  eta: 0:00:54  lr: 0.000012  min_lr: 0.000012  loss: 2.1085 (2.0373)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [290]  [210/312]  eta: 0:00:49  lr: 0.000012  min_lr: 0.000012  loss: 2.0883 (2.0334)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [290]  [220/312]  eta: 0:00:44  lr: 0.000012  min_lr: 0.000012  loss: 2.0672 (2.0398)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [290]  [230/312]  eta: 0:00:39  lr: 0.000012  min_lr: 0.000012  loss: 2.0874 (2.0361)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [290]  [240/312]  eta: 0:00:34  lr: 0.000012  min_lr: 0.000012  loss: 1.8908 (2.0304)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [290]  [250/312]  eta: 0:00:29  lr: 0.000012  min_lr: 0.000012  loss: 2.1026 (2.0334)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [290]  [260/312]  eta: 0:00:24  lr: 0.000012  min_lr: 0.000012  loss: 2.2174 (2.0438)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [290]  [270/312]  eta: 0:00:19  lr: 0.000011  min_lr: 0.000011  loss: 2.1814 (2.0426)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [290]  [280/312]  eta: 0:00:15  lr: 0.000011  min_lr: 0.000011  loss: 2.1457 (2.0475)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0009  max mem: 42573
Epoch: [290]  [290/312]  eta: 0:00:10  lr: 0.000011  min_lr: 0.000011  loss: 2.2162 (2.0496)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0008  max mem: 42573
Epoch: [290]  [300/312]  eta: 0:00:05  lr: 0.000011  min_lr: 0.000011  loss: 2.0942 (2.0461)  weight_decay: 0.0500 (0.0500)  time: 0.4322  data: 0.0001  max mem: 42573
Epoch: [290]  [310/312]  eta: 0:00:00  lr: 0.000011  min_lr: 0.000011  loss: 2.1018 (2.0453)  weight_decay: 0.0500 (0.0500)  time: 0.4321  data: 0.0001  max mem: 42573
Epoch: [290]  [311/312]  eta: 0:00:00  lr: 0.000011  min_lr: 0.000011  loss: 2.1018 (2.0428)  weight_decay: 0.0500 (0.0500)  time: 0.4321  data: 0.0001  max mem: 42573
Epoch: [290] Total time: 0:02:27 (0.4722 s / it)
Averaged stats: lr: 0.000011  min_lr: 0.000011  loss: 2.1018 (2.0224)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:00:39  loss: 0.5414 (0.5414)  acc1: 85.6771 (85.6771)  acc5: 96.8750 (96.8750)  time: 4.3531  data: 4.2447  max mem: 42573
Test:  [8/9]  eta: 0:00:00  loss: 0.7262 (0.7287)  acc1: 81.2500 (80.3520)  acc5: 96.0938 (95.4240)  time: 0.5955  data: 0.5069  max mem: 42573
Test: Total time: 0:00:05 (0.6029 s / it)
* Acc@1 81.068 Acc@5 95.466 loss 0.717
Accuracy of the model on the 50000 test images: 81.1%
Max accuracy: 81.07%
Epoch: [291]  [  0/312]  eta: 0:47:20  lr: 0.000011  min_lr: 0.000011  loss: 1.9662 (1.9662)  weight_decay: 0.0500 (0.0500)  time: 9.1050  data: 8.2314  max mem: 42573
Epoch: [291]  [ 10/312]  eta: 0:07:05  lr: 0.000011  min_lr: 0.000011  loss: 2.2143 (2.2389)  weight_decay: 0.0500 (0.0500)  time: 1.4082  data: 0.7526  max mem: 42573
Epoch: [291]  [ 20/312]  eta: 0:04:35  lr: 0.000011  min_lr: 0.000011  loss: 2.1522 (2.1748)  weight_decay: 0.0500 (0.0500)  time: 0.5360  data: 0.0025  max mem: 42573
Epoch: [291]  [ 30/312]  eta: 0:03:39  lr: 0.000011  min_lr: 0.000011  loss: 1.9935 (2.1067)  weight_decay: 0.0500 (0.0500)  time: 0.4332  data: 0.0004  max mem: 42573
Epoch: [291]  [ 40/312]  eta: 0:03:08  lr: 0.000011  min_lr: 0.000011  loss: 1.9728 (2.0711)  weight_decay: 0.0500 (0.0500)  time: 0.4331  data: 0.0004  max mem: 42573
Epoch: [291]  [ 50/312]  eta: 0:02:48  lr: 0.000011  min_lr: 0.000011  loss: 2.0283 (2.0762)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [291]  [ 60/312]  eta: 0:02:33  lr: 0.000011  min_lr: 0.000011  loss: 2.0999 (2.0718)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [291]  [ 70/312]  eta: 0:02:21  lr: 0.000011  min_lr: 0.000011  loss: 1.9312 (2.0433)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [291]  [ 80/312]  eta: 0:02:11  lr: 0.000011  min_lr: 0.000011  loss: 1.8195 (2.0251)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [291]  [ 90/312]  eta: 0:02:02  lr: 0.000011  min_lr: 0.000011  loss: 1.8028 (2.0073)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [291]  [100/312]  eta: 0:01:54  lr: 0.000010  min_lr: 0.000010  loss: 1.7514 (1.9907)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [291]  [110/312]  eta: 0:01:47  lr: 0.000010  min_lr: 0.000010  loss: 1.9902 (2.0063)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [291]  [120/312]  eta: 0:01:40  lr: 0.000010  min_lr: 0.000010  loss: 2.1525 (2.0185)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [291]  [130/312]  eta: 0:01:33  lr: 0.000010  min_lr: 0.000010  loss: 2.0914 (2.0186)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [291]  [140/312]  eta: 0:01:27  lr: 0.000010  min_lr: 0.000010  loss: 2.0170 (2.0153)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [291]  [150/312]  eta: 0:01:21  lr: 0.000010  min_lr: 0.000010  loss: 2.1163 (2.0126)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [291]  [160/312]  eta: 0:01:16  lr: 0.000010  min_lr: 0.000010  loss: 1.8881 (2.0071)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [291]  [170/312]  eta: 0:01:10  lr: 0.000010  min_lr: 0.000010  loss: 1.8881 (2.0069)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0003  max mem: 42573
Epoch: [291]  [180/312]  eta: 0:01:05  lr: 0.000010  min_lr: 0.000010  loss: 2.2055 (2.0206)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0003  max mem: 42573
Epoch: [291]  [190/312]  eta: 0:00:59  lr: 0.000010  min_lr: 0.000010  loss: 2.2051 (2.0197)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [291]  [200/312]  eta: 0:00:54  lr: 0.000010  min_lr: 0.000010  loss: 1.9293 (2.0113)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [291]  [210/312]  eta: 0:00:49  lr: 0.000010  min_lr: 0.000010  loss: 1.8371 (2.0065)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [291]  [220/312]  eta: 0:00:44  lr: 0.000010  min_lr: 0.000010  loss: 2.1290 (2.0155)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [291]  [230/312]  eta: 0:00:39  lr: 0.000010  min_lr: 0.000010  loss: 2.2014 (2.0160)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [291]  [240/312]  eta: 0:00:34  lr: 0.000010  min_lr: 0.000010  loss: 1.9180 (2.0179)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [291]  [250/312]  eta: 0:00:29  lr: 0.000009  min_lr: 0.000009  loss: 2.1321 (2.0247)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [291]  [260/312]  eta: 0:00:24  lr: 0.000009  min_lr: 0.000009  loss: 2.1778 (2.0250)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [291]  [270/312]  eta: 0:00:19  lr: 0.000009  min_lr: 0.000009  loss: 2.1778 (2.0237)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [291]  [280/312]  eta: 0:00:15  lr: 0.000009  min_lr: 0.000009  loss: 2.1149 (2.0234)  weight_decay: 0.0500 (0.0500)  time: 0.4341  data: 0.0014  max mem: 42573
Epoch: [291]  [290/312]  eta: 0:00:10  lr: 0.000009  min_lr: 0.000009  loss: 2.0385 (2.0214)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0013  max mem: 42573
Epoch: [291]  [300/312]  eta: 0:00:05  lr: 0.000009  min_lr: 0.000009  loss: 2.1006 (2.0195)  weight_decay: 0.0500 (0.0500)  time: 0.4324  data: 0.0001  max mem: 42573
Epoch: [291]  [310/312]  eta: 0:00:00  lr: 0.000009  min_lr: 0.000009  loss: 2.1036 (2.0193)  weight_decay: 0.0500 (0.0500)  time: 0.4321  data: 0.0001  max mem: 42573
Epoch: [291]  [311/312]  eta: 0:00:00  lr: 0.000009  min_lr: 0.000009  loss: 2.1036 (2.0204)  weight_decay: 0.0500 (0.0500)  time: 0.4322  data: 0.0001  max mem: 42573
Epoch: [291] Total time: 0:02:26 (0.4708 s / it)
Averaged stats: lr: 0.000009  min_lr: 0.000009  loss: 2.1036 (2.0288)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:00:42  loss: 0.5375 (0.5375)  acc1: 85.9375 (85.9375)  acc5: 96.6146 (96.6146)  time: 4.7222  data: 4.6138  max mem: 42573
Test:  [8/9]  eta: 0:00:00  loss: 0.7366 (0.7295)  acc1: 81.5104 (80.2240)  acc5: 96.0938 (95.3920)  time: 0.6016  data: 0.5127  max mem: 42573
Test: Total time: 0:00:05 (0.6111 s / it)
* Acc@1 81.034 Acc@5 95.438 loss 0.718
Accuracy of the model on the 50000 test images: 81.0%
Max accuracy: 81.07%
Epoch: [292]  [  0/312]  eta: 0:52:57  lr: 0.000009  min_lr: 0.000009  loss: 1.3439 (1.3439)  weight_decay: 0.0500 (0.0500)  time: 10.1846  data: 8.9038  max mem: 42573
Epoch: [292]  [ 10/312]  eta: 0:07:10  lr: 0.000009  min_lr: 0.000009  loss: 1.7970 (1.8028)  weight_decay: 0.0500 (0.0500)  time: 1.4245  data: 0.8099  max mem: 42573
Epoch: [292]  [ 20/312]  eta: 0:04:38  lr: 0.000009  min_lr: 0.000009  loss: 1.8654 (1.9024)  weight_decay: 0.0500 (0.0500)  time: 0.4911  data: 0.0004  max mem: 42573
Epoch: [292]  [ 30/312]  eta: 0:03:41  lr: 0.000009  min_lr: 0.000009  loss: 2.1050 (1.9615)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [292]  [ 40/312]  eta: 0:03:10  lr: 0.000009  min_lr: 0.000009  loss: 2.1930 (1.9956)  weight_decay: 0.0500 (0.0500)  time: 0.4330  data: 0.0004  max mem: 42573
Epoch: [292]  [ 50/312]  eta: 0:02:49  lr: 0.000009  min_lr: 0.000009  loss: 2.1433 (1.9938)  weight_decay: 0.0500 (0.0500)  time: 0.4330  data: 0.0004  max mem: 42573
Epoch: [292]  [ 60/312]  eta: 0:02:34  lr: 0.000009  min_lr: 0.000009  loss: 1.9681 (1.9825)  weight_decay: 0.0500 (0.0500)  time: 0.4331  data: 0.0004  max mem: 42573
Epoch: [292]  [ 70/312]  eta: 0:02:22  lr: 0.000009  min_lr: 0.000009  loss: 2.0745 (1.9817)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [292]  [ 80/312]  eta: 0:02:11  lr: 0.000009  min_lr: 0.000009  loss: 2.0889 (1.9972)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [292]  [ 90/312]  eta: 0:02:02  lr: 0.000008  min_lr: 0.000008  loss: 2.2315 (2.0090)  weight_decay: 0.0500 (0.0500)  time: 0.4332  data: 0.0004  max mem: 42573
Epoch: [292]  [100/312]  eta: 0:01:54  lr: 0.000008  min_lr: 0.000008  loss: 2.1844 (2.0204)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [292]  [110/312]  eta: 0:01:47  lr: 0.000008  min_lr: 0.000008  loss: 2.1178 (2.0072)  weight_decay: 0.0500 (0.0500)  time: 0.4348  data: 0.0004  max mem: 42573
Epoch: [292]  [120/312]  eta: 0:01:40  lr: 0.000008  min_lr: 0.000008  loss: 1.9372 (2.0030)  weight_decay: 0.0500 (0.0500)  time: 0.4348  data: 0.0004  max mem: 42573
Epoch: [292]  [130/312]  eta: 0:01:34  lr: 0.000008  min_lr: 0.000008  loss: 1.9535 (2.0042)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [292]  [140/312]  eta: 0:01:27  lr: 0.000008  min_lr: 0.000008  loss: 1.9650 (2.0001)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [292]  [150/312]  eta: 0:01:21  lr: 0.000008  min_lr: 0.000008  loss: 1.9862 (2.0039)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [292]  [160/312]  eta: 0:01:16  lr: 0.000008  min_lr: 0.000008  loss: 1.9540 (2.0009)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0003  max mem: 42573
Epoch: [292]  [170/312]  eta: 0:01:10  lr: 0.000008  min_lr: 0.000008  loss: 1.9515 (1.9988)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [292]  [180/312]  eta: 0:01:05  lr: 0.000008  min_lr: 0.000008  loss: 2.1095 (2.0050)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [292]  [190/312]  eta: 0:00:59  lr: 0.000008  min_lr: 0.000008  loss: 2.0443 (1.9992)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [292]  [200/312]  eta: 0:00:54  lr: 0.000008  min_lr: 0.000008  loss: 1.9796 (2.0030)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [292]  [210/312]  eta: 0:00:49  lr: 0.000008  min_lr: 0.000008  loss: 2.1806 (2.0077)  weight_decay: 0.0500 (0.0500)  time: 0.4332  data: 0.0004  max mem: 42573
Epoch: [292]  [220/312]  eta: 0:00:44  lr: 0.000008  min_lr: 0.000008  loss: 2.0004 (1.9965)  weight_decay: 0.0500 (0.0500)  time: 0.4332  data: 0.0004  max mem: 42573
Epoch: [292]  [230/312]  eta: 0:00:39  lr: 0.000008  min_lr: 0.000008  loss: 1.8285 (1.9983)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [292]  [240/312]  eta: 0:00:34  lr: 0.000008  min_lr: 0.000008  loss: 2.1176 (2.0005)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [292]  [250/312]  eta: 0:00:29  lr: 0.000008  min_lr: 0.000008  loss: 2.1722 (2.0028)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [292]  [260/312]  eta: 0:00:24  lr: 0.000007  min_lr: 0.000007  loss: 2.0880 (1.9986)  weight_decay: 0.0500 (0.0500)  time: 0.4332  data: 0.0004  max mem: 42573
Epoch: [292]  [270/312]  eta: 0:00:19  lr: 0.000007  min_lr: 0.000007  loss: 2.1465 (2.0014)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [292]  [280/312]  eta: 0:00:15  lr: 0.000007  min_lr: 0.000007  loss: 1.9553 (1.9999)  weight_decay: 0.0500 (0.0500)  time: 0.4341  data: 0.0009  max mem: 42573
Epoch: [292]  [290/312]  eta: 0:00:10  lr: 0.000007  min_lr: 0.000007  loss: 1.9448 (2.0002)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0008  max mem: 42573
Epoch: [292]  [300/312]  eta: 0:00:05  lr: 0.000007  min_lr: 0.000007  loss: 1.9448 (1.9973)  weight_decay: 0.0500 (0.0500)  time: 0.4321  data: 0.0001  max mem: 42573
Epoch: [292]  [310/312]  eta: 0:00:00  lr: 0.000007  min_lr: 0.000007  loss: 1.9291 (1.9961)  weight_decay: 0.0500 (0.0500)  time: 0.4320  data: 0.0001  max mem: 42573
Epoch: [292]  [311/312]  eta: 0:00:00  lr: 0.000007  min_lr: 0.000007  loss: 1.9064 (1.9943)  weight_decay: 0.0500 (0.0500)  time: 0.4321  data: 0.0001  max mem: 42573
Epoch: [292] Total time: 0:02:27 (0.4714 s / it)
Averaged stats: lr: 0.000007  min_lr: 0.000007  loss: 1.9064 (2.0229)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:00:43  loss: 0.5485 (0.5485)  acc1: 85.9375 (85.9375)  acc5: 96.3542 (96.3542)  time: 4.8068  data: 4.6986  max mem: 42573
Test:  [8/9]  eta: 0:00:00  loss: 0.7274 (0.7298)  acc1: 81.5104 (80.1920)  acc5: 96.0938 (95.3280)  time: 0.6095  data: 0.5221  max mem: 42573
Test: Total time: 0:00:05 (0.6343 s / it)
* Acc@1 81.018 Acc@5 95.474 loss 0.717
Accuracy of the model on the 50000 test images: 81.0%
Max accuracy: 81.07%
Epoch: [293]  [  0/312]  eta: 0:53:53  lr: 0.000007  min_lr: 0.000007  loss: 2.4295 (2.4295)  weight_decay: 0.0500 (0.0500)  time: 10.3635  data: 7.0736  max mem: 42573
Epoch: [293]  [ 10/312]  eta: 0:07:47  lr: 0.000007  min_lr: 0.000007  loss: 2.1541 (2.0983)  weight_decay: 0.0500 (0.0500)  time: 1.5465  data: 0.7615  max mem: 42573
Epoch: [293]  [ 20/312]  eta: 0:04:56  lr: 0.000007  min_lr: 0.000007  loss: 2.0180 (2.0458)  weight_decay: 0.0500 (0.0500)  time: 0.5489  data: 0.0654  max mem: 42573
Epoch: [293]  [ 30/312]  eta: 0:03:53  lr: 0.000007  min_lr: 0.000007  loss: 2.0092 (2.0285)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [293]  [ 40/312]  eta: 0:03:19  lr: 0.000007  min_lr: 0.000007  loss: 2.0623 (2.0575)  weight_decay: 0.0500 (0.0500)  time: 0.4352  data: 0.0004  max mem: 42573
Epoch: [293]  [ 50/312]  eta: 0:02:56  lr: 0.000007  min_lr: 0.000007  loss: 2.1431 (2.0482)  weight_decay: 0.0500 (0.0500)  time: 0.4348  data: 0.0004  max mem: 42573
Epoch: [293]  [ 60/312]  eta: 0:02:39  lr: 0.000007  min_lr: 0.000007  loss: 2.1431 (2.0646)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [293]  [ 70/312]  eta: 0:02:26  lr: 0.000007  min_lr: 0.000007  loss: 2.1284 (2.0629)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [293]  [ 80/312]  eta: 0:02:15  lr: 0.000007  min_lr: 0.000007  loss: 2.1986 (2.0779)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [293]  [ 90/312]  eta: 0:02:06  lr: 0.000007  min_lr: 0.000007  loss: 2.2662 (2.0968)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [293]  [100/312]  eta: 0:01:57  lr: 0.000007  min_lr: 0.000007  loss: 2.3138 (2.1078)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [293]  [110/312]  eta: 0:01:49  lr: 0.000007  min_lr: 0.000007  loss: 2.1870 (2.1071)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [293]  [120/312]  eta: 0:01:42  lr: 0.000007  min_lr: 0.000007  loss: 2.1069 (2.0993)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [293]  [130/312]  eta: 0:01:35  lr: 0.000006  min_lr: 0.000006  loss: 2.0327 (2.0823)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [293]  [140/312]  eta: 0:01:29  lr: 0.000006  min_lr: 0.000006  loss: 1.8750 (2.0628)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [293]  [150/312]  eta: 0:01:23  lr: 0.000006  min_lr: 0.000006  loss: 1.9070 (2.0622)  weight_decay: 0.0500 (0.0500)  time: 0.4332  data: 0.0004  max mem: 42573
Epoch: [293]  [160/312]  eta: 0:01:17  lr: 0.000006  min_lr: 0.000006  loss: 2.1161 (2.0599)  weight_decay: 0.0500 (0.0500)  time: 0.4332  data: 0.0004  max mem: 42573
Epoch: [293]  [170/312]  eta: 0:01:11  lr: 0.000006  min_lr: 0.000006  loss: 1.9789 (2.0540)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [293]  [180/312]  eta: 0:01:06  lr: 0.000006  min_lr: 0.000006  loss: 2.0687 (2.0590)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [293]  [190/312]  eta: 0:01:00  lr: 0.000006  min_lr: 0.000006  loss: 2.0687 (2.0501)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [293]  [200/312]  eta: 0:00:55  lr: 0.000006  min_lr: 0.000006  loss: 2.1299 (2.0558)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [293]  [210/312]  eta: 0:00:50  lr: 0.000006  min_lr: 0.000006  loss: 2.1567 (2.0566)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [293]  [220/312]  eta: 0:00:44  lr: 0.000006  min_lr: 0.000006  loss: 1.9616 (2.0500)  weight_decay: 0.0500 (0.0500)  time: 0.4332  data: 0.0004  max mem: 42573
Epoch: [293]  [230/312]  eta: 0:00:39  lr: 0.000006  min_lr: 0.000006  loss: 1.9927 (2.0497)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0003  max mem: 42573
Epoch: [293]  [240/312]  eta: 0:00:34  lr: 0.000006  min_lr: 0.000006  loss: 2.1261 (2.0520)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [293]  [250/312]  eta: 0:00:29  lr: 0.000006  min_lr: 0.000006  loss: 2.1804 (2.0501)  weight_decay: 0.0500 (0.0500)  time: 0.4331  data: 0.0004  max mem: 42573
Epoch: [293]  [260/312]  eta: 0:00:24  lr: 0.000006  min_lr: 0.000006  loss: 1.8973 (2.0402)  weight_decay: 0.0500 (0.0500)  time: 0.4332  data: 0.0004  max mem: 42573
Epoch: [293]  [270/312]  eta: 0:00:20  lr: 0.000006  min_lr: 0.000006  loss: 1.9115 (2.0414)  weight_decay: 0.0500 (0.0500)  time: 0.4371  data: 0.0004  max mem: 42573
Epoch: [293]  [280/312]  eta: 0:00:15  lr: 0.000006  min_lr: 0.000006  loss: 2.1112 (2.0422)  weight_decay: 0.0500 (0.0500)  time: 0.4380  data: 0.0009  max mem: 42573
Epoch: [293]  [290/312]  eta: 0:00:10  lr: 0.000006  min_lr: 0.000006  loss: 1.9781 (2.0418)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0008  max mem: 42573
Epoch: [293]  [300/312]  eta: 0:00:05  lr: 0.000006  min_lr: 0.000006  loss: 1.9766 (2.0370)  weight_decay: 0.0500 (0.0500)  time: 0.4321  data: 0.0001  max mem: 42573
Epoch: [293]  [310/312]  eta: 0:00:00  lr: 0.000006  min_lr: 0.000006  loss: 2.1172 (2.0400)  weight_decay: 0.0500 (0.0500)  time: 0.4321  data: 0.0001  max mem: 42573
Epoch: [293]  [311/312]  eta: 0:00:00  lr: 0.000006  min_lr: 0.000006  loss: 2.0913 (2.0381)  weight_decay: 0.0500 (0.0500)  time: 0.4321  data: 0.0001  max mem: 42573
Epoch: [293] Total time: 0:02:28 (0.4760 s / it)
Averaged stats: lr: 0.000006  min_lr: 0.000006  loss: 2.0913 (2.0188)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:00:41  loss: 0.5446 (0.5446)  acc1: 86.7188 (86.7188)  acc5: 96.6146 (96.6146)  time: 4.5605  data: 4.4523  max mem: 42573
Test:  [8/9]  eta: 0:00:00  loss: 0.7362 (0.7324)  acc1: 80.9896 (80.2240)  acc5: 95.8333 (95.3920)  time: 0.5817  data: 0.4948  max mem: 42573
Test: Total time: 0:00:05 (0.5915 s / it)
* Acc@1 80.946 Acc@5 95.436 loss 0.719
Accuracy of the model on the 50000 test images: 80.9%
Max accuracy: 81.07%
Epoch: [294]  [  0/312]  eta: 0:53:54  lr: 0.000006  min_lr: 0.000006  loss: 1.5305 (1.5305)  weight_decay: 0.0500 (0.0500)  time: 10.3673  data: 9.0134  max mem: 42573
Epoch: [294]  [ 10/312]  eta: 0:07:37  lr: 0.000005  min_lr: 0.000005  loss: 2.2460 (2.1875)  weight_decay: 0.0500 (0.0500)  time: 1.5142  data: 0.8198  max mem: 42573
Epoch: [294]  [ 20/312]  eta: 0:04:51  lr: 0.000005  min_lr: 0.000005  loss: 2.0657 (1.9949)  weight_decay: 0.0500 (0.0500)  time: 0.5310  data: 0.0004  max mem: 42573
Epoch: [294]  [ 30/312]  eta: 0:03:50  lr: 0.000005  min_lr: 0.000005  loss: 1.9852 (2.0151)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0003  max mem: 42573
Epoch: [294]  [ 40/312]  eta: 0:03:16  lr: 0.000005  min_lr: 0.000005  loss: 1.9852 (2.0152)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [294]  [ 50/312]  eta: 0:02:54  lr: 0.000005  min_lr: 0.000005  loss: 2.0110 (2.0084)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [294]  [ 60/312]  eta: 0:02:38  lr: 0.000005  min_lr: 0.000005  loss: 2.0110 (1.9678)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [294]  [ 70/312]  eta: 0:02:25  lr: 0.000005  min_lr: 0.000005  loss: 2.0914 (2.0062)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [294]  [ 80/312]  eta: 0:02:14  lr: 0.000005  min_lr: 0.000005  loss: 2.1962 (1.9961)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [294]  [ 90/312]  eta: 0:02:05  lr: 0.000005  min_lr: 0.000005  loss: 2.0875 (2.0003)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [294]  [100/312]  eta: 0:01:56  lr: 0.000005  min_lr: 0.000005  loss: 2.0875 (2.0087)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [294]  [110/312]  eta: 0:01:49  lr: 0.000005  min_lr: 0.000005  loss: 2.0172 (2.0054)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [294]  [120/312]  eta: 0:01:42  lr: 0.000005  min_lr: 0.000005  loss: 1.9962 (1.9993)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [294]  [130/312]  eta: 0:01:35  lr: 0.000005  min_lr: 0.000005  loss: 2.1382 (2.0027)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [294]  [140/312]  eta: 0:01:29  lr: 0.000005  min_lr: 0.000005  loss: 1.9547 (1.9932)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [294]  [150/312]  eta: 0:01:22  lr: 0.000005  min_lr: 0.000005  loss: 2.0932 (2.0053)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [294]  [160/312]  eta: 0:01:17  lr: 0.000005  min_lr: 0.000005  loss: 2.1877 (2.0013)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [294]  [170/312]  eta: 0:01:11  lr: 0.000005  min_lr: 0.000005  loss: 1.9834 (2.0003)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [294]  [180/312]  eta: 0:01:05  lr: 0.000005  min_lr: 0.000005  loss: 2.1245 (2.0117)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [294]  [190/312]  eta: 0:01:00  lr: 0.000005  min_lr: 0.000005  loss: 2.1245 (2.0192)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [294]  [200/312]  eta: 0:00:55  lr: 0.000005  min_lr: 0.000005  loss: 2.1108 (2.0231)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [294]  [210/312]  eta: 0:00:49  lr: 0.000005  min_lr: 0.000005  loss: 1.8700 (2.0167)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [294]  [220/312]  eta: 0:00:44  lr: 0.000005  min_lr: 0.000005  loss: 1.8233 (2.0140)  weight_decay: 0.0500 (0.0500)  time: 0.4364  data: 0.0004  max mem: 42573
Epoch: [294]  [230/312]  eta: 0:00:39  lr: 0.000004  min_lr: 0.000004  loss: 2.0112 (2.0154)  weight_decay: 0.0500 (0.0500)  time: 0.4364  data: 0.0004  max mem: 42573
Epoch: [294]  [240/312]  eta: 0:00:34  lr: 0.000004  min_lr: 0.000004  loss: 1.9990 (2.0131)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [294]  [250/312]  eta: 0:00:29  lr: 0.000004  min_lr: 0.000004  loss: 1.9587 (2.0125)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [294]  [260/312]  eta: 0:00:24  lr: 0.000004  min_lr: 0.000004  loss: 2.0011 (2.0083)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [294]  [270/312]  eta: 0:00:20  lr: 0.000004  min_lr: 0.000004  loss: 1.9053 (1.9991)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [294]  [280/312]  eta: 0:00:15  lr: 0.000004  min_lr: 0.000004  loss: 1.9606 (2.0056)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0009  max mem: 42573
Epoch: [294]  [290/312]  eta: 0:00:10  lr: 0.000004  min_lr: 0.000004  loss: 2.2098 (2.0092)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0008  max mem: 42573
Epoch: [294]  [300/312]  eta: 0:00:05  lr: 0.000004  min_lr: 0.000004  loss: 1.9977 (2.0068)  weight_decay: 0.0500 (0.0500)  time: 0.4322  data: 0.0001  max mem: 42573
Epoch: [294]  [310/312]  eta: 0:00:00  lr: 0.000004  min_lr: 0.000004  loss: 1.9605 (2.0029)  weight_decay: 0.0500 (0.0500)  time: 0.4322  data: 0.0001  max mem: 42573
Epoch: [294]  [311/312]  eta: 0:00:00  lr: 0.000004  min_lr: 0.000004  loss: 1.9605 (2.0011)  weight_decay: 0.0500 (0.0500)  time: 0.4322  data: 0.0001  max mem: 42573
Epoch: [294] Total time: 0:02:28 (0.4747 s / it)
Averaged stats: lr: 0.000004  min_lr: 0.000004  loss: 1.9605 (2.0259)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:00:40  loss: 0.5424 (0.5424)  acc1: 86.4583 (86.4583)  acc5: 96.6146 (96.6146)  time: 4.4788  data: 4.3702  max mem: 42573
Test:  [8/9]  eta: 0:00:00  loss: 0.7308 (0.7293)  acc1: 81.2500 (80.4800)  acc5: 96.3542 (95.4240)  time: 0.5750  data: 0.4857  max mem: 42573
Test: Total time: 0:00:05 (0.5827 s / it)
* Acc@1 81.036 Acc@5 95.466 loss 0.718
Accuracy of the model on the 50000 test images: 81.0%
Max accuracy: 81.07%
Epoch: [295]  [  0/312]  eta: 0:55:14  lr: 0.000004  min_lr: 0.000004  loss: 1.8204 (1.8204)  weight_decay: 0.0500 (0.0500)  time: 10.6218  data: 8.3874  max mem: 42573
Epoch: [295]  [ 10/312]  eta: 0:08:12  lr: 0.000004  min_lr: 0.000004  loss: 2.0504 (1.9865)  weight_decay: 0.0500 (0.0500)  time: 1.6297  data: 0.7628  max mem: 42573
Epoch: [295]  [ 20/312]  eta: 0:05:09  lr: 0.000004  min_lr: 0.000004  loss: 2.0338 (1.9720)  weight_decay: 0.0500 (0.0500)  time: 0.5817  data: 0.0003  max mem: 42573
Epoch: [295]  [ 30/312]  eta: 0:04:01  lr: 0.000004  min_lr: 0.000004  loss: 1.9760 (1.9746)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [295]  [ 40/312]  eta: 0:03:25  lr: 0.000004  min_lr: 0.000004  loss: 2.0884 (1.9662)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [295]  [ 50/312]  eta: 0:03:01  lr: 0.000004  min_lr: 0.000004  loss: 1.9112 (1.9603)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [295]  [ 60/312]  eta: 0:02:43  lr: 0.000004  min_lr: 0.000004  loss: 1.8671 (1.9584)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [295]  [ 70/312]  eta: 0:02:29  lr: 0.000004  min_lr: 0.000004  loss: 2.0996 (1.9732)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [295]  [ 80/312]  eta: 0:02:18  lr: 0.000004  min_lr: 0.000004  loss: 2.1236 (1.9786)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [295]  [ 90/312]  eta: 0:02:08  lr: 0.000004  min_lr: 0.000004  loss: 1.9956 (1.9704)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [295]  [100/312]  eta: 0:01:59  lr: 0.000004  min_lr: 0.000004  loss: 1.9737 (1.9796)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [295]  [110/312]  eta: 0:01:51  lr: 0.000004  min_lr: 0.000004  loss: 2.1459 (1.9837)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [295]  [120/312]  eta: 0:01:44  lr: 0.000004  min_lr: 0.000004  loss: 2.1761 (1.9969)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [295]  [130/312]  eta: 0:01:37  lr: 0.000004  min_lr: 0.000004  loss: 1.9871 (1.9946)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [295]  [140/312]  eta: 0:01:30  lr: 0.000004  min_lr: 0.000004  loss: 1.9720 (1.9923)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [295]  [150/312]  eta: 0:01:24  lr: 0.000004  min_lr: 0.000004  loss: 2.0111 (1.9981)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [295]  [160/312]  eta: 0:01:18  lr: 0.000004  min_lr: 0.000004  loss: 2.0997 (2.0022)  weight_decay: 0.0500 (0.0500)  time: 0.4339  data: 0.0004  max mem: 42573
Epoch: [295]  [170/312]  eta: 0:01:12  lr: 0.000003  min_lr: 0.000003  loss: 2.1194 (2.0118)  weight_decay: 0.0500 (0.0500)  time: 0.4422  data: 0.0004  max mem: 42573
Epoch: [295]  [180/312]  eta: 0:01:06  lr: 0.000003  min_lr: 0.000003  loss: 2.1356 (2.0055)  weight_decay: 0.0500 (0.0500)  time: 0.4423  data: 0.0003  max mem: 42573
Epoch: [295]  [190/312]  eta: 0:01:01  lr: 0.000003  min_lr: 0.000003  loss: 2.1082 (2.0142)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [295]  [200/312]  eta: 0:00:55  lr: 0.000003  min_lr: 0.000003  loss: 2.0992 (2.0143)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [295]  [210/312]  eta: 0:00:50  lr: 0.000003  min_lr: 0.000003  loss: 2.1263 (2.0183)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0003  max mem: 42573
Epoch: [295]  [220/312]  eta: 0:00:45  lr: 0.000003  min_lr: 0.000003  loss: 2.1416 (2.0255)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [295]  [230/312]  eta: 0:00:40  lr: 0.000003  min_lr: 0.000003  loss: 2.1587 (2.0351)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0003  max mem: 42573
Epoch: [295]  [240/312]  eta: 0:00:35  lr: 0.000003  min_lr: 0.000003  loss: 2.1619 (2.0327)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0003  max mem: 42573
Epoch: [295]  [250/312]  eta: 0:00:30  lr: 0.000003  min_lr: 0.000003  loss: 2.0878 (2.0324)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0003  max mem: 42573
Epoch: [295]  [260/312]  eta: 0:00:25  lr: 0.000003  min_lr: 0.000003  loss: 2.0491 (2.0308)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0003  max mem: 42573
Epoch: [295]  [270/312]  eta: 0:00:20  lr: 0.000003  min_lr: 0.000003  loss: 2.0502 (2.0355)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0003  max mem: 42573
Epoch: [295]  [280/312]  eta: 0:00:15  lr: 0.000003  min_lr: 0.000003  loss: 2.0427 (2.0296)  weight_decay: 0.0500 (0.0500)  time: 0.4343  data: 0.0009  max mem: 42573
Epoch: [295]  [290/312]  eta: 0:00:10  lr: 0.000003  min_lr: 0.000003  loss: 1.9093 (2.0317)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0008  max mem: 42573
Epoch: [295]  [300/312]  eta: 0:00:05  lr: 0.000003  min_lr: 0.000003  loss: 2.0954 (2.0331)  weight_decay: 0.0500 (0.0500)  time: 0.4321  data: 0.0001  max mem: 42573
Epoch: [295]  [310/312]  eta: 0:00:00  lr: 0.000003  min_lr: 0.000003  loss: 2.1416 (2.0361)  weight_decay: 0.0500 (0.0500)  time: 0.4320  data: 0.0001  max mem: 42573
Epoch: [295]  [311/312]  eta: 0:00:00  lr: 0.000003  min_lr: 0.000003  loss: 2.2225 (2.0372)  weight_decay: 0.0500 (0.0500)  time: 0.4320  data: 0.0001  max mem: 42573
Epoch: [295] Total time: 0:02:29 (0.4792 s / it)
Averaged stats: lr: 0.000003  min_lr: 0.000003  loss: 2.2225 (2.0202)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:00:40  loss: 0.5443 (0.5443)  acc1: 86.1979 (86.1979)  acc5: 96.0938 (96.0938)  time: 4.5489  data: 4.4408  max mem: 42573
Test:  [8/9]  eta: 0:00:00  loss: 0.7412 (0.7329)  acc1: 81.2500 (80.3840)  acc5: 96.0938 (95.3920)  time: 0.5852  data: 0.4935  max mem: 42573
Test: Total time: 0:00:05 (0.6038 s / it)
* Acc@1 80.986 Acc@5 95.442 loss 0.720
Accuracy of the model on the 50000 test images: 81.0%
Max accuracy: 81.07%
Epoch: [296]  [  0/312]  eta: 0:56:47  lr: 0.000003  min_lr: 0.000003  loss: 2.4386 (2.4386)  weight_decay: 0.0500 (0.0500)  time: 10.9206  data: 7.9388  max mem: 42573
Epoch: [296]  [ 10/312]  eta: 0:07:51  lr: 0.000003  min_lr: 0.000003  loss: 2.0803 (1.9425)  weight_decay: 0.0500 (0.0500)  time: 1.5608  data: 0.7309  max mem: 42573
Epoch: [296]  [ 20/312]  eta: 0:04:58  lr: 0.000003  min_lr: 0.000003  loss: 2.1350 (2.0500)  weight_decay: 0.0500 (0.0500)  time: 0.5291  data: 0.0052  max mem: 42573
Epoch: [296]  [ 30/312]  eta: 0:03:55  lr: 0.000003  min_lr: 0.000003  loss: 2.2556 (2.1079)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0003  max mem: 42573
Epoch: [296]  [ 40/312]  eta: 0:03:20  lr: 0.000003  min_lr: 0.000003  loss: 2.0266 (2.0644)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0003  max mem: 42573
Epoch: [296]  [ 50/312]  eta: 0:02:57  lr: 0.000003  min_lr: 0.000003  loss: 2.0750 (2.0727)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [296]  [ 60/312]  eta: 0:02:40  lr: 0.000003  min_lr: 0.000003  loss: 2.0360 (2.0354)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [296]  [ 70/312]  eta: 0:02:27  lr: 0.000003  min_lr: 0.000003  loss: 1.8350 (2.0120)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [296]  [ 80/312]  eta: 0:02:16  lr: 0.000003  min_lr: 0.000003  loss: 1.9350 (2.0068)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [296]  [ 90/312]  eta: 0:02:06  lr: 0.000003  min_lr: 0.000003  loss: 2.0772 (2.0146)  weight_decay: 0.0500 (0.0500)  time: 0.4417  data: 0.0004  max mem: 42573
Epoch: [296]  [100/312]  eta: 0:01:58  lr: 0.000003  min_lr: 0.000003  loss: 2.0926 (2.0206)  weight_decay: 0.0500 (0.0500)  time: 0.4417  data: 0.0004  max mem: 42573
Epoch: [296]  [110/312]  eta: 0:01:50  lr: 0.000003  min_lr: 0.000003  loss: 2.0878 (2.0184)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [296]  [120/312]  eta: 0:01:43  lr: 0.000003  min_lr: 0.000003  loss: 2.1020 (2.0146)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [296]  [130/312]  eta: 0:01:36  lr: 0.000003  min_lr: 0.000003  loss: 2.1213 (2.0183)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [296]  [140/312]  eta: 0:01:29  lr: 0.000003  min_lr: 0.000003  loss: 2.0604 (2.0121)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [296]  [150/312]  eta: 0:01:23  lr: 0.000003  min_lr: 0.000003  loss: 2.0223 (2.0197)  weight_decay: 0.0500 (0.0500)  time: 0.4340  data: 0.0004  max mem: 42573
Epoch: [296]  [160/312]  eta: 0:01:17  lr: 0.000003  min_lr: 0.000003  loss: 2.1551 (2.0307)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [296]  [170/312]  eta: 0:01:11  lr: 0.000003  min_lr: 0.000003  loss: 2.1448 (2.0356)  weight_decay: 0.0500 (0.0500)  time: 0.4332  data: 0.0004  max mem: 42573
Epoch: [296]  [180/312]  eta: 0:01:06  lr: 0.000002  min_lr: 0.000002  loss: 2.0504 (2.0326)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [296]  [190/312]  eta: 0:01:00  lr: 0.000002  min_lr: 0.000002  loss: 2.0029 (2.0226)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [296]  [200/312]  eta: 0:00:55  lr: 0.000002  min_lr: 0.000002  loss: 1.9008 (2.0186)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [296]  [210/312]  eta: 0:00:50  lr: 0.000002  min_lr: 0.000002  loss: 1.9104 (2.0169)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [296]  [220/312]  eta: 0:00:45  lr: 0.000002  min_lr: 0.000002  loss: 1.9900 (2.0107)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [296]  [230/312]  eta: 0:00:40  lr: 0.000002  min_lr: 0.000002  loss: 1.9900 (2.0125)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [296]  [240/312]  eta: 0:00:34  lr: 0.000002  min_lr: 0.000002  loss: 1.9696 (2.0077)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [296]  [250/312]  eta: 0:00:29  lr: 0.000002  min_lr: 0.000002  loss: 1.9411 (2.0040)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0003  max mem: 42573
Epoch: [296]  [260/312]  eta: 0:00:25  lr: 0.000002  min_lr: 0.000002  loss: 2.0776 (2.0093)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [296]  [270/312]  eta: 0:00:20  lr: 0.000002  min_lr: 0.000002  loss: 2.1044 (2.0080)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [296]  [280/312]  eta: 0:00:15  lr: 0.000002  min_lr: 0.000002  loss: 2.0634 (2.0147)  weight_decay: 0.0500 (0.0500)  time: 0.4343  data: 0.0009  max mem: 42573
Epoch: [296]  [290/312]  eta: 0:00:10  lr: 0.000002  min_lr: 0.000002  loss: 2.1178 (2.0122)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0008  max mem: 42573
Epoch: [296]  [300/312]  eta: 0:00:05  lr: 0.000002  min_lr: 0.000002  loss: 2.0488 (2.0125)  weight_decay: 0.0500 (0.0500)  time: 0.4320  data: 0.0001  max mem: 42573
Epoch: [296]  [310/312]  eta: 0:00:00  lr: 0.000002  min_lr: 0.000002  loss: 2.0104 (2.0094)  weight_decay: 0.0500 (0.0500)  time: 0.4320  data: 0.0001  max mem: 42573
Epoch: [296]  [311/312]  eta: 0:00:00  lr: 0.000002  min_lr: 0.000002  loss: 1.9835 (2.0083)  weight_decay: 0.0500 (0.0500)  time: 0.4320  data: 0.0001  max mem: 42573
Epoch: [296] Total time: 0:02:28 (0.4768 s / it)
Averaged stats: lr: 0.000002  min_lr: 0.000002  loss: 1.9835 (2.0231)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:00:43  loss: 0.5448 (0.5448)  acc1: 85.9375 (85.9375)  acc5: 96.6146 (96.6146)  time: 4.7893  data: 4.6811  max mem: 42573
Test:  [8/9]  eta: 0:00:00  loss: 0.7337 (0.7302)  acc1: 81.2500 (80.3520)  acc5: 95.8333 (95.3600)  time: 0.6088  data: 0.5202  max mem: 42573
Test: Total time: 0:00:05 (0.6158 s / it)
* Acc@1 81.004 Acc@5 95.464 loss 0.717
Accuracy of the model on the 50000 test images: 81.0%
Max accuracy: 81.07%
Epoch: [297]  [  0/312]  eta: 0:49:16  lr: 0.000002  min_lr: 0.000002  loss: 2.2834 (2.2834)  weight_decay: 0.0500 (0.0500)  time: 9.4758  data: 6.9924  max mem: 42573
Epoch: [297]  [ 10/312]  eta: 0:07:29  lr: 0.000002  min_lr: 0.000002  loss: 2.2834 (2.1179)  weight_decay: 0.0500 (0.0500)  time: 1.4872  data: 0.6361  max mem: 42573
Epoch: [297]  [ 20/312]  eta: 0:04:47  lr: 0.000002  min_lr: 0.000002  loss: 2.1003 (2.0935)  weight_decay: 0.0500 (0.0500)  time: 0.5608  data: 0.0004  max mem: 42573
Epoch: [297]  [ 30/312]  eta: 0:03:47  lr: 0.000002  min_lr: 0.000002  loss: 2.0611 (2.0535)  weight_decay: 0.0500 (0.0500)  time: 0.4332  data: 0.0004  max mem: 42573
Epoch: [297]  [ 40/312]  eta: 0:03:15  lr: 0.000002  min_lr: 0.000002  loss: 2.0883 (2.0523)  weight_decay: 0.0500 (0.0500)  time: 0.4392  data: 0.0005  max mem: 42573
Epoch: [297]  [ 50/312]  eta: 0:02:53  lr: 0.000002  min_lr: 0.000002  loss: 2.1448 (2.0691)  weight_decay: 0.0500 (0.0500)  time: 0.4392  data: 0.0005  max mem: 42573
Epoch: [297]  [ 60/312]  eta: 0:02:37  lr: 0.000002  min_lr: 0.000002  loss: 1.9788 (2.0382)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [297]  [ 70/312]  eta: 0:02:24  lr: 0.000002  min_lr: 0.000002  loss: 1.9788 (2.0495)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [297]  [ 80/312]  eta: 0:02:14  lr: 0.000002  min_lr: 0.000002  loss: 2.0804 (2.0353)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [297]  [ 90/312]  eta: 0:02:04  lr: 0.000002  min_lr: 0.000002  loss: 1.9500 (2.0197)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0005  max mem: 42573
Epoch: [297]  [100/312]  eta: 0:01:56  lr: 0.000002  min_lr: 0.000002  loss: 1.9763 (2.0231)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [297]  [110/312]  eta: 0:01:48  lr: 0.000002  min_lr: 0.000002  loss: 1.9763 (2.0141)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [297]  [120/312]  eta: 0:01:41  lr: 0.000002  min_lr: 0.000002  loss: 2.0416 (2.0098)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [297]  [130/312]  eta: 0:01:35  lr: 0.000002  min_lr: 0.000002  loss: 2.0595 (2.0198)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [297]  [140/312]  eta: 0:01:28  lr: 0.000002  min_lr: 0.000002  loss: 2.1938 (2.0216)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [297]  [150/312]  eta: 0:01:22  lr: 0.000002  min_lr: 0.000002  loss: 1.9926 (2.0192)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [297]  [160/312]  eta: 0:01:16  lr: 0.000002  min_lr: 0.000002  loss: 1.9624 (2.0160)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [297]  [170/312]  eta: 0:01:11  lr: 0.000002  min_lr: 0.000002  loss: 1.8990 (2.0161)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [297]  [180/312]  eta: 0:01:05  lr: 0.000002  min_lr: 0.000002  loss: 1.8990 (2.0078)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [297]  [190/312]  eta: 0:01:00  lr: 0.000002  min_lr: 0.000002  loss: 2.0703 (2.0121)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [297]  [200/312]  eta: 0:00:55  lr: 0.000002  min_lr: 0.000002  loss: 2.0703 (2.0085)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [297]  [210/312]  eta: 0:00:49  lr: 0.000002  min_lr: 0.000002  loss: 1.9535 (2.0059)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [297]  [220/312]  eta: 0:00:44  lr: 0.000002  min_lr: 0.000002  loss: 2.0883 (2.0089)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [297]  [230/312]  eta: 0:00:39  lr: 0.000002  min_lr: 0.000002  loss: 2.0883 (2.0030)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [297]  [240/312]  eta: 0:00:34  lr: 0.000002  min_lr: 0.000002  loss: 2.1164 (2.0077)  weight_decay: 0.0500 (0.0500)  time: 0.4332  data: 0.0004  max mem: 42573
Epoch: [297]  [250/312]  eta: 0:00:29  lr: 0.000002  min_lr: 0.000002  loss: 2.0099 (1.9989)  weight_decay: 0.0500 (0.0500)  time: 0.4332  data: 0.0004  max mem: 42573
Epoch: [297]  [260/312]  eta: 0:00:24  lr: 0.000002  min_lr: 0.000002  loss: 2.0145 (2.0056)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [297]  [270/312]  eta: 0:00:20  lr: 0.000002  min_lr: 0.000002  loss: 2.2133 (2.0144)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [297]  [280/312]  eta: 0:00:15  lr: 0.000002  min_lr: 0.000002  loss: 2.1972 (2.0190)  weight_decay: 0.0500 (0.0500)  time: 0.4345  data: 0.0009  max mem: 42573
Epoch: [297]  [290/312]  eta: 0:00:10  lr: 0.000002  min_lr: 0.000002  loss: 2.1161 (2.0184)  weight_decay: 0.0500 (0.0500)  time: 0.4341  data: 0.0008  max mem: 42573
Epoch: [297]  [300/312]  eta: 0:00:05  lr: 0.000002  min_lr: 0.000002  loss: 1.9973 (2.0194)  weight_decay: 0.0500 (0.0500)  time: 0.4323  data: 0.0001  max mem: 42573
Epoch: [297]  [310/312]  eta: 0:00:00  lr: 0.000002  min_lr: 0.000002  loss: 2.0081 (2.0193)  weight_decay: 0.0500 (0.0500)  time: 0.4320  data: 0.0001  max mem: 42573
Epoch: [297]  [311/312]  eta: 0:00:00  lr: 0.000002  min_lr: 0.000002  loss: 2.0076 (2.0192)  weight_decay: 0.0500 (0.0500)  time: 0.4320  data: 0.0001  max mem: 42573
Epoch: [297] Total time: 0:02:27 (0.4740 s / it)
Averaged stats: lr: 0.000002  min_lr: 0.000002  loss: 2.0076 (2.0233)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:00:44  loss: 0.5427 (0.5427)  acc1: 86.1979 (86.1979)  acc5: 96.6146 (96.6146)  time: 4.9266  data: 4.8188  max mem: 42573
Test:  [8/9]  eta: 0:00:00  loss: 0.7345 (0.7314)  acc1: 81.7708 (80.2880)  acc5: 96.3542 (95.3600)  time: 0.6236  data: 0.5355  max mem: 42573
Test: Total time: 0:00:05 (0.6339 s / it)
* Acc@1 81.038 Acc@5 95.454 loss 0.719
Accuracy of the model on the 50000 test images: 81.0%
Max accuracy: 81.07%
Epoch: [298]  [  0/312]  eta: 0:50:47  lr: 0.000002  min_lr: 0.000002  loss: 2.3268 (2.3268)  weight_decay: 0.0500 (0.0500)  time: 9.7668  data: 8.1680  max mem: 42573
Epoch: [298]  [ 10/312]  eta: 0:07:24  lr: 0.000001  min_lr: 0.000001  loss: 2.2862 (2.1908)  weight_decay: 0.0500 (0.0500)  time: 1.4734  data: 0.7711  max mem: 42573
Epoch: [298]  [ 20/312]  eta: 0:04:45  lr: 0.000001  min_lr: 0.000001  loss: 2.1567 (2.1835)  weight_decay: 0.0500 (0.0500)  time: 0.5383  data: 0.0159  max mem: 42573
Epoch: [298]  [ 30/312]  eta: 0:03:46  lr: 0.000001  min_lr: 0.000001  loss: 2.1567 (2.1132)  weight_decay: 0.0500 (0.0500)  time: 0.4331  data: 0.0003  max mem: 42573
Epoch: [298]  [ 40/312]  eta: 0:03:13  lr: 0.000001  min_lr: 0.000001  loss: 1.9834 (2.0722)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0003  max mem: 42573
Epoch: [298]  [ 50/312]  eta: 0:02:52  lr: 0.000001  min_lr: 0.000001  loss: 1.9874 (2.0691)  weight_decay: 0.0500 (0.0500)  time: 0.4382  data: 0.0004  max mem: 42573
Epoch: [298]  [ 60/312]  eta: 0:02:36  lr: 0.000001  min_lr: 0.000001  loss: 1.9874 (2.0396)  weight_decay: 0.0500 (0.0500)  time: 0.4382  data: 0.0004  max mem: 42573
Epoch: [298]  [ 70/312]  eta: 0:02:24  lr: 0.000001  min_lr: 0.000001  loss: 2.0967 (2.0473)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [298]  [ 80/312]  eta: 0:02:13  lr: 0.000001  min_lr: 0.000001  loss: 2.0431 (2.0359)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [298]  [ 90/312]  eta: 0:02:04  lr: 0.000001  min_lr: 0.000001  loss: 1.9282 (2.0340)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [298]  [100/312]  eta: 0:01:56  lr: 0.000001  min_lr: 0.000001  loss: 2.1623 (2.0395)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [298]  [110/312]  eta: 0:01:48  lr: 0.000001  min_lr: 0.000001  loss: 2.2330 (2.0401)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [298]  [120/312]  eta: 0:01:41  lr: 0.000001  min_lr: 0.000001  loss: 1.9439 (2.0208)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [298]  [130/312]  eta: 0:01:34  lr: 0.000001  min_lr: 0.000001  loss: 2.0417 (2.0227)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [298]  [140/312]  eta: 0:01:28  lr: 0.000001  min_lr: 0.000001  loss: 2.1672 (2.0230)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [298]  [150/312]  eta: 0:01:22  lr: 0.000001  min_lr: 0.000001  loss: 2.1536 (2.0305)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [298]  [160/312]  eta: 0:01:16  lr: 0.000001  min_lr: 0.000001  loss: 2.1501 (2.0267)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [298]  [170/312]  eta: 0:01:11  lr: 0.000001  min_lr: 0.000001  loss: 2.1250 (2.0375)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [298]  [180/312]  eta: 0:01:05  lr: 0.000001  min_lr: 0.000001  loss: 2.2919 (2.0433)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [298]  [190/312]  eta: 0:01:00  lr: 0.000001  min_lr: 0.000001  loss: 2.1679 (2.0363)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [298]  [200/312]  eta: 0:00:54  lr: 0.000001  min_lr: 0.000001  loss: 1.9241 (2.0305)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [298]  [210/312]  eta: 0:00:49  lr: 0.000001  min_lr: 0.000001  loss: 1.9705 (2.0260)  weight_decay: 0.0500 (0.0500)  time: 0.4333  data: 0.0004  max mem: 42573
Epoch: [298]  [220/312]  eta: 0:00:44  lr: 0.000001  min_lr: 0.000001  loss: 1.9995 (2.0205)  weight_decay: 0.0500 (0.0500)  time: 0.4332  data: 0.0003  max mem: 42573
Epoch: [298]  [230/312]  eta: 0:00:39  lr: 0.000001  min_lr: 0.000001  loss: 2.0119 (2.0230)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [298]  [240/312]  eta: 0:00:34  lr: 0.000001  min_lr: 0.000001  loss: 2.0655 (2.0239)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [298]  [250/312]  eta: 0:00:29  lr: 0.000001  min_lr: 0.000001  loss: 2.0766 (2.0291)  weight_decay: 0.0500 (0.0500)  time: 0.4396  data: 0.0004  max mem: 42573
Epoch: [298]  [260/312]  eta: 0:00:24  lr: 0.000001  min_lr: 0.000001  loss: 2.0835 (2.0266)  weight_decay: 0.0500 (0.0500)  time: 0.4396  data: 0.0004  max mem: 42573
Epoch: [298]  [270/312]  eta: 0:00:20  lr: 0.000001  min_lr: 0.000001  loss: 2.0281 (2.0223)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [298]  [280/312]  eta: 0:00:15  lr: 0.000001  min_lr: 0.000001  loss: 1.9716 (2.0198)  weight_decay: 0.0500 (0.0500)  time: 0.4341  data: 0.0011  max mem: 42573
Epoch: [298]  [290/312]  eta: 0:00:10  lr: 0.000001  min_lr: 0.000001  loss: 1.8964 (2.0141)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0010  max mem: 42573
Epoch: [298]  [300/312]  eta: 0:00:05  lr: 0.000001  min_lr: 0.000001  loss: 1.8054 (2.0077)  weight_decay: 0.0500 (0.0500)  time: 0.4323  data: 0.0001  max mem: 42573
Epoch: [298]  [310/312]  eta: 0:00:00  lr: 0.000001  min_lr: 0.000001  loss: 2.1201 (2.0149)  weight_decay: 0.0500 (0.0500)  time: 0.4320  data: 0.0001  max mem: 42573
Epoch: [298]  [311/312]  eta: 0:00:00  lr: 0.000001  min_lr: 0.000001  loss: 2.1755 (2.0157)  weight_decay: 0.0500 (0.0500)  time: 0.4320  data: 0.0001  max mem: 42573
Epoch: [298] Total time: 0:02:27 (0.4736 s / it)
Averaged stats: lr: 0.000001  min_lr: 0.000001  loss: 2.1755 (2.0221)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:00:43  loss: 0.5465 (0.5465)  acc1: 86.7188 (86.7188)  acc5: 96.3542 (96.3542)  time: 4.8396  data: 4.7314  max mem: 42573
Test:  [8/9]  eta: 0:00:00  loss: 0.7410 (0.7349)  acc1: 81.2500 (80.2240)  acc5: 95.8333 (95.3280)  time: 0.6139  data: 0.5258  max mem: 42573
Test: Total time: 0:00:05 (0.6379 s / it)
* Acc@1 80.918 Acc@5 95.448 loss 0.722
Accuracy of the model on the 50000 test images: 80.9%
Max accuracy: 81.07%
Epoch: [299]  [  0/312]  eta: 0:52:04  lr: 0.000001  min_lr: 0.000001  loss: 2.0764 (2.0764)  weight_decay: 0.0500 (0.0500)  time: 10.0160  data: 7.6353  max mem: 42573
Epoch: [299]  [ 10/312]  eta: 0:07:36  lr: 0.000001  min_lr: 0.000001  loss: 1.9750 (2.0503)  weight_decay: 0.0500 (0.0500)  time: 1.5118  data: 0.7435  max mem: 42573
Epoch: [299]  [ 20/312]  eta: 0:04:51  lr: 0.000001  min_lr: 0.000001  loss: 1.9387 (1.9765)  weight_decay: 0.0500 (0.0500)  time: 0.5472  data: 0.0274  max mem: 42573
Epoch: [299]  [ 30/312]  eta: 0:03:50  lr: 0.000001  min_lr: 0.000001  loss: 2.0476 (2.0128)  weight_decay: 0.0500 (0.0500)  time: 0.4332  data: 0.0004  max mem: 42573
Epoch: [299]  [ 40/312]  eta: 0:03:16  lr: 0.000001  min_lr: 0.000001  loss: 2.0835 (2.0321)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [299]  [ 50/312]  eta: 0:02:54  lr: 0.000001  min_lr: 0.000001  loss: 2.0835 (2.0464)  weight_decay: 0.0500 (0.0500)  time: 0.4332  data: 0.0004  max mem: 42573
Epoch: [299]  [ 60/312]  eta: 0:02:38  lr: 0.000001  min_lr: 0.000001  loss: 2.2154 (2.0603)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [299]  [ 70/312]  eta: 0:02:25  lr: 0.000001  min_lr: 0.000001  loss: 2.1012 (2.0505)  weight_decay: 0.0500 (0.0500)  time: 0.4337  data: 0.0004  max mem: 42573
Epoch: [299]  [ 80/312]  eta: 0:02:14  lr: 0.000001  min_lr: 0.000001  loss: 2.0769 (2.0565)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [299]  [ 90/312]  eta: 0:02:05  lr: 0.000001  min_lr: 0.000001  loss: 1.9743 (2.0458)  weight_decay: 0.0500 (0.0500)  time: 0.4338  data: 0.0004  max mem: 42573
Epoch: [299]  [100/312]  eta: 0:01:56  lr: 0.000001  min_lr: 0.000001  loss: 1.9401 (2.0391)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [299]  [110/312]  eta: 0:01:49  lr: 0.000001  min_lr: 0.000001  loss: 1.9176 (2.0321)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [299]  [120/312]  eta: 0:01:42  lr: 0.000001  min_lr: 0.000001  loss: 1.9008 (2.0247)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [299]  [130/312]  eta: 0:01:35  lr: 0.000001  min_lr: 0.000001  loss: 2.0558 (2.0262)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [299]  [140/312]  eta: 0:01:29  lr: 0.000001  min_lr: 0.000001  loss: 1.8799 (2.0058)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [299]  [150/312]  eta: 0:01:22  lr: 0.000001  min_lr: 0.000001  loss: 1.9065 (2.0149)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [299]  [160/312]  eta: 0:01:17  lr: 0.000001  min_lr: 0.000001  loss: 2.1720 (2.0191)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [299]  [170/312]  eta: 0:01:11  lr: 0.000001  min_lr: 0.000001  loss: 2.1827 (2.0287)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [299]  [180/312]  eta: 0:01:05  lr: 0.000001  min_lr: 0.000001  loss: 2.1726 (2.0257)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [299]  [190/312]  eta: 0:01:00  lr: 0.000001  min_lr: 0.000001  loss: 2.1427 (2.0292)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [299]  [200/312]  eta: 0:00:55  lr: 0.000001  min_lr: 0.000001  loss: 2.1476 (2.0315)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [299]  [210/312]  eta: 0:00:49  lr: 0.000001  min_lr: 0.000001  loss: 2.1387 (2.0320)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [299]  [220/312]  eta: 0:00:44  lr: 0.000001  min_lr: 0.000001  loss: 2.0149 (2.0322)  weight_decay: 0.0500 (0.0500)  time: 0.4389  data: 0.0003  max mem: 42573
Epoch: [299]  [230/312]  eta: 0:00:39  lr: 0.000001  min_lr: 0.000001  loss: 2.0123 (2.0274)  weight_decay: 0.0500 (0.0500)  time: 0.4390  data: 0.0004  max mem: 42573
Epoch: [299]  [240/312]  eta: 0:00:34  lr: 0.000001  min_lr: 0.000001  loss: 2.0197 (2.0281)  weight_decay: 0.0500 (0.0500)  time: 0.4336  data: 0.0004  max mem: 42573
Epoch: [299]  [250/312]  eta: 0:00:29  lr: 0.000001  min_lr: 0.000001  loss: 2.0015 (2.0211)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [299]  [260/312]  eta: 0:00:24  lr: 0.000001  min_lr: 0.000001  loss: 1.8575 (2.0189)  weight_decay: 0.0500 (0.0500)  time: 0.4335  data: 0.0004  max mem: 42573
Epoch: [299]  [270/312]  eta: 0:00:20  lr: 0.000001  min_lr: 0.000001  loss: 2.0218 (2.0182)  weight_decay: 0.0500 (0.0500)  time: 0.4334  data: 0.0004  max mem: 42573
Epoch: [299]  [280/312]  eta: 0:00:15  lr: 0.000001  min_lr: 0.000001  loss: 2.0218 (2.0133)  weight_decay: 0.0500 (0.0500)  time: 0.4346  data: 0.0009  max mem: 42573
Epoch: [299]  [290/312]  eta: 0:00:10  lr: 0.000001  min_lr: 0.000001  loss: 1.9496 (2.0116)  weight_decay: 0.0500 (0.0500)  time: 0.4341  data: 0.0008  max mem: 42573
Epoch: [299]  [300/312]  eta: 0:00:05  lr: 0.000001  min_lr: 0.000001  loss: 2.0116 (2.0127)  weight_decay: 0.0500 (0.0500)  time: 0.4321  data: 0.0001  max mem: 42573
Epoch: [299]  [310/312]  eta: 0:00:00  lr: 0.000001  min_lr: 0.000001  loss: 2.1538 (2.0184)  weight_decay: 0.0500 (0.0500)  time: 0.4321  data: 0.0001  max mem: 42573
Epoch: [299]  [311/312]  eta: 0:00:00  lr: 0.000001  min_lr: 0.000001  loss: 2.1538 (2.0184)  weight_decay: 0.0500 (0.0500)  time: 0.4320  data: 0.0001  max mem: 42573
Epoch: [299] Total time: 0:02:28 (0.4748 s / it)
Averaged stats: lr: 0.000001  min_lr: 0.000001  loss: 2.1538 (2.0259)  weight_decay: 0.0500 (0.0500)
Test:  [0/9]  eta: 0:00:40  loss: 0.5450 (0.5450)  acc1: 86.1979 (86.1979)  acc5: 96.3542 (96.3542)  time: 4.5141  data: 4.4057  max mem: 42573
Test:  [8/9]  eta: 0:00:00  loss: 0.7394 (0.7333)  acc1: 80.9896 (80.2880)  acc5: 96.3542 (95.3920)  time: 0.5782  data: 0.4896  max mem: 42573
Test: Total time: 0:00:05 (0.5871 s / it)
* Acc@1 80.992 Acc@5 95.446 loss 0.721
Accuracy of the model on the 50000 test images: 81.0%
Max accuracy: 81.07%