add all ckpt

ckpt/en-ja.E18-D4/checkpoint_average_10.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:60c08c98f817eeadd91f0a13ddff443c365743b22203651ad51ddd1fba472426
+size 6463756207

ckpt/en-ja.E18-D4/spm.en.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:caf40e08541345a137a05112c6c6d7a5b51573bad7a0fb33764b470b6d77f093
+size 490166

ckpt/en-ja.E18-D4/spm.ja.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:875b526987ac0059d64b1c5cd1efc6e8abe5704c6376086fb75440d5a4a723b9
+size 830465

ckpt/en-ja.do01.ado01/checkpoint_average_10.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4c75f0298d7a89c95a72af6f9a2340a50be075804160024f69a738d070cd1328
+size 4045848291

ckpt/en-ja.do01.ado01/spm.en.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:caf40e08541345a137a05112c6c6d7a5b51573bad7a0fb33764b470b6d77f093
+size 490166

ckpt/en-ja.do01.ado01/spm.ja.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:875b526987ac0059d64b1c5cd1efc6e8abe5704c6376086fb75440d5a4a723b9
+size 830465

ckpt/en-ja.do01.ado01/train.log

@@ -0,0 +1,61 @@
+{'_name': None, 'common': {'_name': None, 'no_progress_bar': False, 'log_interval': 100, 'log_format': 'simple', 'log_file': 'chkpt/en-ja.do01.ado01/train.log', 'aim_repo': None, 'aim_run_hash': None, 'tensorboard_logdir': None, 'wandb_project': 'wmt23', 'azureml_logging': False, 'seed': 0, 'cpu': False, 'tpu': False, 'bf16': False, 'memory_efficient_bf16': False, 'fp16': True, 'memory_efficient_fp16': False, 'fp16_no_flatten_grads': False, 'fp16_init_scale': 8, 'fp16_scale_window': None, 'fp16_scale_tolerance': 0.0, 'on_cpu_convert_precision': False, 'min_loss_scale': 0.0001, 'threshold_loss_scale': None, 'amp': False, 'amp_batch_retries': 2, 'amp_init_scale': 128, 'amp_scale_window': None, 'user_dir': None, 'empty_cache_freq': 0, 'all_gather_list_size': 16384, 'model_parallel_size': 1, 'quantization_config_path': None, 'profile': False, 'reset_logging': False, 'suppress_crashes': False, 'use_plasma_view': False, 'plasma_path': '/tmp/plasma'}, 'common_eval': {'_name': None, 'path': None, 'post_process': None, 'quiet': False, 'model_overrides': '{}', 'results_path': None}, 'distributed_training': {'_name': None, 'distributed_world_size': 1, 'distributed_num_procs': 1, 'distributed_rank': 0, 'distributed_backend': 'nccl', 'distributed_init_method': None, 'distributed_port': -1, 'device_id': 0, 'distributed_no_spawn': False, 'ddp_backend': 'pytorch_ddp', 'ddp_comm_hook': 'none', 'bucket_cap_mb': 25, 'fix_batches_to_gpus': False, 'find_unused_parameters': False, 'gradient_as_bucket_view': False, 'fast_stat_sync': False, 'heartbeat_timeout': -1, 'broadcast_buffers': False, 'slowmo_momentum': None, 'slowmo_base_algorithm': 'localsgd', 'localsgd_frequency': 3, 'nprocs_per_node': 1, 'pipeline_model_parallel': False, 'pipeline_balance': None, 'pipeline_devices': None, 'pipeline_chunks': 0, 'pipeline_encoder_balance': None, 'pipeline_encoder_devices': None, 'pipeline_decoder_balance': None, 'pipeline_decoder_devices': None, 'pipeline_checkpoint': 'never', 'zero_sharding': 'none', 'fp16': True, 'memory_efficient_fp16': False, 'tpu': False, 'no_reshard_after_forward': False, 'fp32_reduce_scatter': False, 'cpu_offload': False, 'use_sharded_state': False, 'not_fsdp_flatten_parameters': False}, 'dataset': {'_name': None, 'num_workers': 0, 'skip_invalid_size_inputs_valid_test': False, 'max_tokens': 16384, 'batch_size': None, 'required_batch_size_multiple': 8, 'required_seq_len_multiple': 1, 'dataset_impl': None, 'data_buffer_size': 10, 'train_subset': 'train', 'valid_subset': 'valid', 'combine_valid_subsets': None, 'ignore_unused_valid_subsets': False, 'validate_interval': 100000, 'validate_interval_updates': 0, 'validate_after_updates': 0, 'fixed_validation_seed': None, 'disable_validation': False, 'max_tokens_valid': 16384, 'batch_size_valid': None, 'max_valid_steps': None, 'curriculum': 0, 'gen_subset': 'test', 'num_shards': 1, 'shard_id': 0, 'grouped_shuffling': False, 'update_epoch_batch_itr': False, 'update_ordered_indices_seed': False}, 'optimization': {'_name': None, 'max_epoch': 0, 'max_update': 60000, 'stop_time_hours': 0.0, 'clip_norm': 1.0, 'sentence_avg': False, 'update_freq': [4], 'lr': [0.001], 'stop_min_lr': -1.0, 'use_bmuf': False, 'skip_remainder_batch': False, 'debug_param_names': False}, 'checkpoint': {'_name': None, 'save_dir': 'chkpt/en-ja.do01.ado01', 'restore_file': 'checkpoint_last.pt', 'continue_once': None, 'finetune_from_model': None, 'reset_dataloader': False, 'reset_lr_scheduler': False, 'reset_meters': False, 'reset_optimizer': False, 'optimizer_overrides': '{}', 'save_interval': 100000, 'save_interval_updates': 1000, 'keep_interval_updates': 10, 'keep_interval_updates_pattern': -1, 'keep_last_epochs': -1, 'keep_best_checkpoints': -1, 'no_save': False, 'no_epoch_checkpoints': True, 'no_last_checkpoints': False, 'no_save_optimizer_state': False, 'best_checkpoint_metric': 'loss', 'maximize_best_checkpoint_metric': False, 'patience': -1, 'checkpoint_suffix': '', 'checkpoint_shard_count': 1, 'load_checkpoint_on_all_dp_ranks': False, 'write_checkpoints_asynchronously': False, 'model_parallel_size': 1}, 'bmuf': {'_name': None, 'block_lr': 1.0, 'block_momentum': 0.875, 'global_sync_iter': 50, 'warmup_iterations': 500, 'use_nbm': False, 'average_sync': False, 'distributed_world_size': 1}, 'generation': {'_name': None, 'beam': 5, 'beam_mt': 0, 'nbest': 1, 'max_len_a': 0.0, 'max_len_b': 200, 'max_len_a_mt': 0.0, 'max_len_b_mt': 200, 'min_len': 1, 'match_source_len': False, 'unnormalized': False, 'no_early_stop': False, 'no_beamable_mm': False, 'lenpen': 1.0, 'lenpen_mt': 1.0, 'unkpen': 0.0, 'replace_unk': None, 'sacrebleu': False, 'score_reference': False, 'prefix_size': 0, 'no_repeat_ngram_size': 0, 'sampling': False, 'sampling_topk': -1, 'sampling_topp': -1.0, 'constraints': None, 'temperature': 1.0, 'diverse_beam_groups': -1, 'diverse_beam_strength': 0.5, 'diversity_rate': -1.0, 'print_alignment': None, 'print_step': False, 'lm_path': None, 'lm_weight': 0.0, 'iter_decode_eos_penalty': 0.0, 'iter_decode_max_iter': 10, 'iter_decode_force_max_iter': False, 'iter_decode_with_beam': 1, 'iter_decode_with_external_reranker': False, 'retain_iter_history': False, 'retain_dropout': False, 'retain_dropout_modules': None, 'decoding_format': None, 'no_seed_provided': False, 'eos_token': None}, 'eval_lm': {'_name': None, 'output_word_probs': False, 'output_word_stats': False, 'context_window': 0, 'softmax_batch': 9223372036854775807}, 'interactive': {'_name': None, 'buffer_size': 0, 'input': '-'}, 'model': Namespace(no_progress_bar=False, log_interval=100, log_format='simple', log_file='chkpt/en-ja.do01.ado01/train.log', aim_repo=None, aim_run_hash=None, tensorboard_logdir=None, wandb_project='wmt23', azureml_logging=False, seed=0, cpu=False, tpu=False, bf16=False, memory_efficient_bf16=False, fp16=True, memory_efficient_fp16=False, fp16_no_flatten_grads=False, fp16_init_scale=8, fp16_scale_window=None, fp16_scale_tolerance=0.0, on_cpu_convert_precision=False, min_loss_scale=0.0001, threshold_loss_scale=None, amp=False, amp_batch_retries=2, amp_init_scale=128, amp_scale_window=None, user_dir=None, empty_cache_freq=0, all_gather_list_size=16384, model_parallel_size=1, quantization_config_path=None, profile=False, reset_logging=False, suppress_crashes=False, use_plasma_view=False, plasma_path='/tmp/plasma', criterion='label_smoothed_cross_entropy', tokenizer=None, bpe=None, optimizer='adam', lr_scheduler='inverse_sqrt', scoring='bleu', task='translation', num_workers=0, skip_invalid_size_inputs_valid_test=False, max_tokens=16384, batch_size=None, required_batch_size_multiple=8, required_seq_len_multiple=1, dataset_impl=None, data_buffer_size=10, train_subset='train', valid_subset='valid', combine_valid_subsets=None, ignore_unused_valid_subsets=False, validate_interval=100000, validate_interval_updates=0, validate_after_updates=0, fixed_validation_seed=None, disable_validation=False, max_tokens_valid=16384, batch_size_valid=None, max_valid_steps=None, curriculum=0, gen_subset='test', num_shards=1, shard_id=0, grouped_shuffling=False, update_epoch_batch_itr=False, update_ordered_indices_seed=False, distributed_world_size=1, distributed_num_procs=1, distributed_rank=0, distributed_backend='nccl', distributed_init_method=None, distributed_port=-1, device_id=0, distributed_no_spawn=False, ddp_backend='pytorch_ddp', ddp_comm_hook='none', bucket_cap_mb=25, fix_batches_to_gpus=False, find_unused_parameters=False, gradient_as_bucket_view=False, fast_stat_sync=False, heartbeat_timeout=-1, broadcast_buffers=False, slowmo_momentum=None, slowmo_base_algorithm='localsgd', localsgd_frequency=3, nprocs_per_node=1, pipeline_model_parallel=False, pipeline_balance=None, pipeline_devices=None, pipeline_chunks=0, pipeline_encoder_balance=None, pipeline_encoder_devices=None, pipeline_decoder_balance=None, pipeline_decoder_devices=None, pipeline_checkpoint='never', zero_sharding='none', no_reshard_after_forward=False, fp32_reduce_scatter=False, cpu_offload=False, use_sharded_state=False, not_fsdp_flatten_parameters=False, arch='transformer_vaswani_wmt_en_de_big', max_epoch=0, max_update=60000, stop_time_hours=0, clip_norm=1.0, sentence_avg=False, update_freq=[4], lr=[0.001], stop_min_lr=-1.0, use_bmuf=False, skip_remainder_batch=False, debug_param_names=False, save_dir='chkpt/en-ja.do01.ado01', restore_file='checkpoint_last.pt', continue_once=None, finetune_from_model=None, reset_dataloader=False, reset_lr_scheduler=False, reset_meters=False, reset_optimizer=False, optimizer_overrides='{}', save_interval=100000, save_interval_updates=1000, keep_interval_updates=10, keep_interval_updates_pattern=-1, keep_last_epochs=-1, keep_best_checkpoints=-1, no_save=False, no_epoch_checkpoints=True, no_last_checkpoints=False, no_save_optimizer_state=False, best_checkpoint_metric='loss', maximize_best_checkpoint_metric=False, patience=-1, checkpoint_suffix='', checkpoint_shard_count=1, load_checkpoint_on_all_dp_ranks=False, write_checkpoints_asynchronously=False, store_ema=False, ema_decay=0.9999, ema_start_update=0, ema_seed_model=None, ema_update_freq=1, ema_fp32=False, data='binarized/en-ja/', source_lang=None, target_lang=None, load_alignments=False, left_pad_source=True, left_pad_target=False, upsample_primary=-1, truncate_source=False, num_batch_buckets=0, eval_bleu=False, eval_bleu_args='{}', eval_bleu_detok='space', eval_bleu_detok_args='{}', eval_tokenized_bleu=False, eval_bleu_remove_bpe=None, eval_bleu_print_samples=False, label_smoothing=0.1, report_accuracy=False, ignore_prefix_size=0, adam_betas='(0.9, 0.98)', adam_eps=1e-08, weight_decay=0.0, use_old_adam=False, fp16_adam_stats=False, warmup_updates=4000, warmup_init_lr=-1, pad=1, eos=2, unk=3, encoder_ffn_embed_dim=8192, decoder_ffn_embed_dim=8192, dropout=0.1, attention_dropout=0.1, share_decoder_input_output_embed=True, no_seed_provided=False, encoder_embed_dim=1024, encoder_attention_heads=16, encoder_normalize_before=False, decoder_embed_dim=1024, decoder_attention_heads=16, encoder_embed_path=None, encoder_layers=6, encoder_learned_pos=False, decoder_embed_path=None, decoder_layers=6, decoder_normalize_before=False, decoder_learned_pos=False, activation_dropout=0.0, activation_fn='relu', adaptive_softmax_cutoff=None, adaptive_softmax_dropout=0, share_all_embeddings=False, merge_src_tgt_embed=False, no_token_positional_embeddings=False, adaptive_input=False, no_cross_attention=False, cross_self_attention=False, decoder_output_dim=1024, decoder_input_dim=1024, no_scale_embedding=False, layernorm_embedding=False, tie_adaptive_weights=False, checkpoint_activations=False, offload_activations=False, encoder_layers_to_keep=None, decoder_layers_to_keep=None, encoder_layerdrop=0, decoder_layerdrop=0, quant_noise_pq=0, quant_noise_pq_block_size=8, quant_noise_scalar=0, _name='transformer_vaswani_wmt_en_de_big'), 'task': {'_name': 'translation', 'data': 'binarized/en-ja/', 'source_lang': None, 'target_lang': None, 'load_alignments': False, 'left_pad_source': True, 'left_pad_target': False, 'max_source_positions': 1024, 'max_target_positions': 1024, 'upsample_primary': -1, 'truncate_source': False, 'num_batch_buckets': 0, 'train_subset': 'train', 'dataset_impl': None, 'required_seq_len_multiple': 1, 'eval_bleu': False, 'eval_bleu_args': '{}', 'eval_bleu_detok': 'space', 'eval_bleu_detok_args': '{}', 'eval_tokenized_bleu': False, 'eval_bleu_remove_bpe': None, 'eval_bleu_print_samples': False}, 'criterion': {'_name': 'label_smoothed_cross_entropy', 'label_smoothing': 0.1, 'report_accuracy': False, 'ignore_prefix_size': 0, 'sentence_avg': False}, 'optimizer': {'_name': 'adam', 'adam_betas': '(0.9, 0.98)', 'adam_eps': 1e-08, 'weight_decay': 0.0, 'use_old_adam': False, 'fp16_adam_stats': False, 'tpu': False, 'lr': [0.001]}, 'lr_scheduler': {'_name': 'inverse_sqrt', 'warmup_updates': 4000, 'warmup_init_lr': -1.0, 'lr': [0.001]}, 'scoring': {'_name': 'bleu', 'pad': 1, 'eos': 2, 'unk': 3}, 'bpe': None, 'tokenizer': None, 'ema': {'_name': None, 'store_ema': False, 'ema_decay': 0.9999, 'ema_start_update': 0, 'ema_seed_model': None, 'ema_update_freq': 1, 'ema_fp32': False}}
+TransformerModel(
+  (encoder): TransformerEncoderBase(
+    (dropout_module): FairseqDropout()
+    (embed_tokens): Embedding(16000, 1024, padding_idx=1)
+    (embed_positions): SinusoidalPositionalEmbedding()
+    (layers): ModuleList(
+      (0-5): 6 x TransformerEncoderLayerBase(
+        (self_attn): MultiheadAttention(
+          (dropout_module): FairseqDropout()
+          (k_proj): Linear(in_features=1024, out_features=1024, bias=True)
+          (v_proj): Linear(in_features=1024, out_features=1024, bias=True)
+          (q_proj): Linear(in_features=1024, out_features=1024, bias=True)
+          (out_proj): Linear(in_features=1024, out_features=1024, bias=True)
+        )
+        (self_attn_layer_norm): FusedLayerNorm(torch.Size([1024]), eps=1e-05, elementwise_affine=True)
+        (dropout_module): FairseqDropout()
+        (activation_dropout_module): FairseqDropout()
+        (fc1): Linear(in_features=1024, out_features=8192, bias=True)
+        (fc2): Linear(in_features=8192, out_features=1024, bias=True)
+        (final_layer_norm): FusedLayerNorm(torch.Size([1024]), eps=1e-05, elementwise_affine=True)
+      )
+    )
+  )
+  (decoder): TransformerDecoderBase(
+    (dropout_module): FairseqDropout()
+    (embed_tokens): Embedding(32000, 1024, padding_idx=1)
+    (embed_positions): SinusoidalPositionalEmbedding()
+    (layers): ModuleList(
+      (0-5): 6 x TransformerDecoderLayerBase(
+        (dropout_module): FairseqDropout()
+        (self_attn): MultiheadAttention(
+          (dropout_module): FairseqDropout()
+          (k_proj): Linear(in_features=1024, out_features=1024, bias=True)
+          (v_proj): Linear(in_features=1024, out_features=1024, bias=True)
+          (q_proj): Linear(in_features=1024, out_features=1024, bias=True)
+          (out_proj): Linear(in_features=1024, out_features=1024, bias=True)
+        )
+        (activation_dropout_module): FairseqDropout()
+        (self_attn_layer_norm): FusedLayerNorm(torch.Size([1024]), eps=1e-05, elementwise_affine=True)
+        (encoder_attn): MultiheadAttention(
+          (dropout_module): FairseqDropout()
+          (k_proj): Linear(in_features=1024, out_features=1024, bias=True)
+          (v_proj): Linear(in_features=1024, out_features=1024, bias=True)
+          (q_proj): Linear(in_features=1024, out_features=1024, bias=True)
+          (out_proj): Linear(in_features=1024, out_features=1024, bias=True)
+        )
+        (encoder_attn_layer_norm): FusedLayerNorm(torch.Size([1024]), eps=1e-05, elementwise_affine=True)
+        (fc1): Linear(in_features=1024, out_features=8192, bias=True)
+        (fc2): Linear(in_features=8192, out_features=1024, bias=True)
+        (final_layer_norm): FusedLayerNorm(torch.Size([1024]), eps=1e-05, elementwise_affine=True)
+      )
+    )
+    (output_projection): Linear(in_features=1024, out_features=32000, bias=False)
+  )
+)
+task: TranslationTask
+model: TransformerModel
+criterion: LabelSmoothedCrossEntropyCriterion
+num. shared model params: 326,221,824 (num. trained: 326,221,824)
+num. expert model params: 0 (num. trained: 0)

ckpt/en-ja.do02.ado00/checkpoint_average_10.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:087b7a7388c7f2227a3f4ff7f0ead14c0f5f1d075ac550cdaaf6c355c2c05be3
+size 4045848291

ckpt/en-ja.do02.ado00/spm.en.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:caf40e08541345a137a05112c6c6d7a5b51573bad7a0fb33764b470b6d77f093
+size 490166

ckpt/en-ja.do02.ado00/spm.ja.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:875b526987ac0059d64b1c5cd1efc6e8abe5704c6376086fb75440d5a4a723b9
+size 830465

ckpt/en-ja.do02.ado01/checkpoint_average_10.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3c242b7d7fb780fece31114e895acdef9b26e8a1de773aaad93f9631b64dc421
+size 4045848291

ckpt/en-ja.do02.ado01/spm.en.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:caf40e08541345a137a05112c6c6d7a5b51573bad7a0fb33764b470b6d77f093
+size 490166

ckpt/en-ja.do02.ado01/spm.ja.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:875b526987ac0059d64b1c5cd1efc6e8abe5704c6376086fb75440d5a4a723b9
+size 830465

ckpt/en-ja.do03.ado00/checkpoint_average_10.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d1ac3e2df34fbbf221f088b36cfa599bf26cbbfb04b589b75633a04043a9a522
+size 4045848291

ckpt/en-ja.do03.ado00/spm.en.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:caf40e08541345a137a05112c6c6d7a5b51573bad7a0fb33764b470b6d77f093
+size 490166

ckpt/en-ja.do03.ado00/spm.ja.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:875b526987ac0059d64b1c5cd1efc6e8abe5704c6376086fb75440d5a4a723b9
+size 830465

ckpt/en-ja.do03.ado01/checkpoint_average_10.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0ccb81e013ab584e0c3ff78e9165817c5d6d280c5b1814399d4d1bcd315b21c3
+size 4045848291

ckpt/en-ja.do03.ado01/spm.en.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:caf40e08541345a137a05112c6c6d7a5b51573bad7a0fb33764b470b6d77f093
+size 490166

ckpt/en-ja.do03.ado01/spm.ja.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:875b526987ac0059d64b1c5cd1efc6e8abe5704c6376086fb75440d5a4a723b9
+size 830465

ckpt/ja-en.E18-D4/checkpoint_average_10.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:680a2503448219f90e7600715b16c43e5ec32e3505024cf4e6c4220164882d7c
+size 6398219951