hydra_train.log

[2024-06-15 00:51:54,525][fairseq_cli.train][INFO] - {'_name': None, 'common': {'_name': None, 'no_progress_bar': False, 'log_interval': 200, 'log_format': 'json', 'log_file': None, 'tensorboard_logdir': 'tblog', 'wandb_project': 'AVSP-LLM', 'azureml_logging': False, 'seed': 1337, 'cpu': False, 'tpu': False, 'bf16': False, 'memory_efficient_bf16': False, 'fp16': True, 'memory_efficient_fp16': False, 'fp16_no_flatten_grads': False, 'fp16_init_scale': 128, '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': '/home/theodore/Projects/VSP-LLM/src', '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': 'no_c10d', 'ddp_comm_hook': 'none', 'bucket_cap_mb': 25, 'fix_batches_to_gpus': False, 'find_unused_parameters': True, 'fast_stat_sync': False, 'heartbeat_timeout': -1, 'broadcast_buffers': False, 'slowmo_momentum': None, 'slowmo_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}, 'dataset': {'_name': None, 'num_workers': 0, 'skip_invalid_size_inputs_valid_test': False, 'max_tokens': None, 'batch_size': 1, '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': 1, 'validate_interval_updates': 0, 'validate_after_updates': 0, 'fixed_validation_seed': None, 'disable_validation': False, 'max_tokens_valid': None, 'batch_size_valid': 1, 'max_valid_steps': None, 'curriculum': 0, 'gen_subset': 'test', 'num_shards': 1, 'shard_id': 0}, 'optimization': {'_name': None, 'max_epoch': 0, 'max_update': 30000, 'stop_time_hours': 0.0, 'clip_norm': 0.0, 'sentence_avg': True, 'update_freq': [8], 'lr': [0.0005], 'stop_min_lr': -1.0, 'use_bmuf': False}, 'checkpoint': {'_name': None, 'save_dir': 'checkpoints', 'restore_file': 'checkpoint_last.pt', 'finetune_from_model': None, 'reset_dataloader': False, 'reset_lr_scheduler': False, 'reset_meters': False, 'reset_optimizer': False, 'optimizer_overrides': '{}', 'save_interval': 1, 'save_interval_updates': 2500, 'keep_interval_updates': 1, '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': 'accuracy', 'maximize_best_checkpoint_metric': True, '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, 'nbest': 1, 'max_len_a': 0.0, 'max_len_b': 200, 'min_len': 1, 'match_source_len': False, 'unnormalized': False, 'no_early_stop': False, 'no_beamable_mm': False, 'lenpen': 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}, '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': {'_name': 'vsp_llm', 'w2v_path': '/home/theodore/Projects/VSP-LLM/checkpoints/large_vox_iter5.pt', 'llm_ckpt_path': 'vilm/vinallama-2.7b', 'apply_mask': False, 'mask_selection': 'static', 'mask_length': 10, 'mask_other': 0, 'mask_prob': 0.75, 'mask_channel_selection': 'static', 'mask_channel_length': 64, 'mask_channel_other': 0, 'mask_channel_prob': 0.5, 'layerdrop': 0.1, 'dropout': 0.0, 'activation_dropout': 0.1, 'attention_dropout': 0.0, 'feature_grad_mult': 1.0, 'encoder_embed_dim': 1024, 'decoder_embed_dim': 4096, 'freeze_finetune_updates': 18000}, 'task': {'_name': 'vsp_llm_training', 'is_s2s': True, 'data': '/home/theodore/Projects/VSP-LLM/data/processed/vasr', 'label_dir': '/home/theodore/Projects/VSP-LLM/data/processed/vasr', 'normalize': True, 'labels': ['wrd'], 'single_target': True, 'fine_tuning': True, 'stack_order_audio': 4, 'max_sample_size': 500, 'modalities': ['video'], 'image_aug': True, 'pad_audio': True, 'random_crop': False, 'llm_ckpt_path': 'vilm/vinallama-2.7b'}, 'criterion': {'_name': 'decoder_only_language_modeling_loss', 'report_accuracy': True, 'label_smoothing': 0.1}, 'optimizer': {'_name': 'adam', 'adam_betas': '(0.9,0.98)', 'adam_eps': 1e-08, 'weight_decay': 0.0, 'use_old_adam': False, 'tpu': False, 'lr': [0.0005]}, 'lr_scheduler': {'_name': 'tri_stage', 'warmup_steps': 10000, 'hold_steps': 0, 'decay_steps': 20000, 'phase_ratio': None, 'init_lr_scale': 0.01, 'final_lr_scale': 0.05, 'max_update': 30000, 'lr': [0.0005]}, 'scoring': None, 'bpe': None, 'tokenizer': None, 'job_logging_cfg': {'version': 1, 'formatters': {'simple': {'format': '[%(asctime)s][%(name)s][%(levelname)s] - %(message)s'}}, 'handlers': {'console': {'class': 'logging.StreamHandler', 'formatter': 'simple', 'stream': 'ext://sys.stdout'}, 'file': {'class': 'logging.FileHandler', 'formatter': 'simple', 'filename': 'hydra_train.log'}}, 'root': {'level': 'INFO', 'handlers': ['console', 'file']}, 'disable_existing_loggers': False}}
[2024-06-15 00:51:54,528][src.vsp_llm_training][INFO] - current directory is /home/theodore/Projects/VSP-LLM/experiments/ViVSP-LLM_v1.0
[2024-06-15 00:51:54,528][src.vsp_llm_training][INFO] - AVHubertPretrainingTask Config {'_name': 'vsp_llm_training', 'data': '/home/theodore/Projects/VSP-LLM/data/processed/vasr', 'labels': ['wrd'], 'label_dir': '/home/theodore/Projects/VSP-LLM/data/processed/vasr', 'label_rate': -1, 'sample_rate': 16000, 'llm_ckpt_path': 'vilm/vinallama-2.7b', 'normalize': True, 'enable_padding': False, 'max_sample_size': 500, 'min_sample_size': None, 'max_trim_sample_size': '${task.max_sample_size}', 'single_target': True, 'random_crop': False, 'pad_audio': True, 'pdb': False, 'stack_order_audio': 4, 'skip_verify': False, 'image_aug': True, 'image_crop_size': 88, 'image_mean': 0.421, 'image_std': 0.165, 'modalities': ['video'], 'is_s2s': True, 'tokenizer_bpe_name': None, 'tokenizer_bpe_model': None, 'noise_wav': None, 'noise_prob': 0.0, 'noise_snr': '0', 'noise_num': 1, 'fine_tuning': True}
[2024-06-15 00:51:56,244][src.hubert_pretraining][INFO] - current directory is /home/theodore/Projects/VSP-LLM/experiments/ViVSP-LLM_v1.0
[2024-06-15 00:51:56,244][src.hubert_pretraining][INFO] - AVHubertPretrainingTask Config {'_name': 'av_hubert_pretraining', 'data': '/home/theodore/Projects/VSP-LLM/data/processed/vasr', 'labels': ['km'], 'label_dir': '/checkpoint/bshi/data/lrs3//video/hubert/stitch-iters/envox-iter4-l12c2000/', 'label_rate': 25, 'sample_rate': 25, 'normalize': True, 'enable_padding': False, 'max_sample_size': 2000, 'min_sample_size': 5, 'max_trim_sample_size': 400, 'single_target': False, 'random_crop': True, 'pad_audio': False, 'pdb': False, 'stack_order_audio': 4, 'skip_verify': False, 'image_aug': True, 'image_crop_size': 88, 'image_mean': 0.421, 'image_std': 0.165, 'modalities': ['audio', 'video'], 'is_s2s': False, 'tokenizer_bpe_name': None, 'tokenizer_bpe_model': None, 'noise_wav': None, 'noise_prob': 0.0, 'noise_snr': '0', 'noise_num': 1, 'fine_tuning': False}
[2024-06-15 00:51:56,247][src.hubert][INFO] - HubertModel Config: {'_name': 'av_hubert', 'label_rate': 25, 'input_modality': '${task.input_modality}', 'extractor_mode': default, 'encoder_layers': 24, 'encoder_embed_dim': 1024, 'encoder_ffn_embed_dim': 4096, 'encoder_attention_heads': 16, 'activation_fn': gelu, 'dropout': 0.0, 'attention_dropout': 0.0, 'activation_dropout': 0.1, 'encoder_layerdrop': 0.1, 'dropout_input': 0.0, 'dropout_features': 0.1, 'final_dim': 256, 'untie_final_proj': True, 'layer_norm_first': True, 'conv_feature_layers': '[(512,10,5)] + [(512,3,2)] * 4 + [(512,2,2)] * 2', 'conv_bias': False, 'logit_temp': 0.1, 'target_glu': False, 'feature_grad_mult': 1.0, 'mask_length_audio': 10, 'mask_prob_audio': 0.8, 'mask_length_image': 5, 'mask_prob_image': 0.3, 'mask_selection': static, 'mask_other': 0.0, 'no_mask_overlap': False, 'mask_min_space': 1, 'mask_channel_length': 10, 'mask_channel_prob': 0.0, 'mask_channel_selection': static, 'mask_channel_other': 0.0, 'no_mask_channel_overlap': False, 'mask_channel_min_space': 1, 'conv_pos': 128, 'conv_pos_groups': 16, 'latent_temp': [2.0, 0.5, 0.999995], 'skip_masked': False, 'skip_nomask': False, 'resnet_relu_type': 'prelu', 'resnet_weights': None, 'sim_type': 'cosine', 'sub_encoder_layers': 0, 'audio_feat_dim': 104, 'modality_dropout': 0.5, 'audio_dropout': 0.5, 'modality_fuse': 'concat', 'selection_type': 'same_seq', 'masking_type': 'input', 'decoder_embed_dim': 768, 'decoder_ffn_embed_dim': 3072, 'decoder_layers': 6, 'decoder_layerdrop': 0.0, 'decoder_attention_heads': 4, 'decoder_learned_pos': False, 'decoder_normalize_before': False, 'no_token_positional_embeddings': False, 'decoder_dropout': 0.1, 'decoder_attention_dropout': 0.1, 'decoder_activation_dropout': 0.0, 'max_target_positions': 2048, 'share_decoder_input_output_embed': False, 'no_scale_embedding': True}
[2024-06-15 00:52:00,287][fairseq_cli.train][INFO] - avhubert_llm_seq2seq_cluster_count(
  (encoder): HubertEncoderWrapper(
    (w2v_model): AVHubertModel(
      (feature_extractor_audio): SubModel(
        (proj): Linear(in_features=104, out_features=1024, bias=True)
      )
      (feature_extractor_video): SubModel(
        (resnet): ResEncoder(
          (frontend3D): Sequential(
            (0): Conv3d(1, 64, kernel_size=(5, 7, 7), stride=(1, 2, 2), padding=(2, 3, 3), bias=False)
            (1): BatchNorm3d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
            (2): PReLU(num_parameters=64)
            (3): MaxPool3d(kernel_size=(1, 3, 3), stride=(1, 2, 2), padding=(0, 1, 1), dilation=1, ceil_mode=False)
          )
          (trunk): ResNet(
            (layer1): Sequential(
              (0): BasicBlock(
                (conv1): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
                (bn1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                (relu1): PReLU(num_parameters=64)
                (relu2): PReLU(num_parameters=64)
                (conv2): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
                (bn2): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
              )
              (1): BasicBlock(
                (conv1): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
                (bn1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                (relu1): PReLU(num_parameters=64)
                (relu2): PReLU(num_parameters=64)
                (conv2): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
                (bn2): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
              )
            )
            (layer2): Sequential(
              (0): BasicBlock(
                (conv1): Conv2d(64, 128, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False)
                (bn1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                (relu1): PReLU(num_parameters=128)
                (relu2): PReLU(num_parameters=128)
                (conv2): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
                (bn2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                (downsample): Sequential(
                  (0): Conv2d(64, 128, kernel_size=(1, 1), stride=(2, 2), bias=False)
                  (1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                )
              )
              (1): BasicBlock(
                (conv1): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
                (bn1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                (relu1): PReLU(num_parameters=128)
                (relu2): PReLU(num_parameters=128)
                (conv2): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
                (bn2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
              )
            )
            (layer3): Sequential(
              (0): BasicBlock(
                (conv1): Conv2d(128, 256, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False)
                (bn1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                (relu1): PReLU(num_parameters=256)
                (relu2): PReLU(num_parameters=256)
                (conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
                (bn2): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                (downsample): Sequential(
                  (0): Conv2d(128, 256, kernel_size=(1, 1), stride=(2, 2), bias=False)
                  (1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                )
              )
              (1): BasicBlock(
                (conv1): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
                (bn1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                (relu1): PReLU(num_parameters=256)
                (relu2): PReLU(num_parameters=256)
                (conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
                (bn2): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
              )
            )
            (layer4): Sequential(
              (0): BasicBlock(
                (conv1): Conv2d(256, 512, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False)
                (bn1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                (relu1): PReLU(num_parameters=512)
                (relu2): PReLU(num_parameters=512)
                (conv2): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
                (bn2): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                (downsample): Sequential(
                  (0): Conv2d(256, 512, kernel_size=(1, 1), stride=(2, 2), bias=False)
                  (1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                )
              )
              (1): BasicBlock(
                (conv1): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
                (bn1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
                (relu1): PReLU(num_parameters=512)
                (relu2): PReLU(num_parameters=512)
                (conv2): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
                (bn2): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
              )
            )
            (avgpool): AdaptiveAvgPool2d(output_size=1)
          )
        )
        (proj): Linear(in_features=512, out_features=1024, bias=True)
      )
      (post_extract_proj): Linear(in_features=2048, out_features=1024, bias=True)
      (dropout_input): Dropout(p=0.0, inplace=False)
      (dropout_features): Dropout(p=0.1, inplace=False)
      (encoder): TransformerEncoder(
        (pos_conv): Sequential(
          (0): Conv1d(1024, 1024, kernel_size=(128,), stride=(1,), padding=(64,), groups=16)
          (1): SamePad()
          (2): GELU(approximate='none')
        )
        (layers): ModuleList(
          (0-23): 24 x TransformerSentenceEncoderLayer(
            (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)
            )
            (dropout1): Dropout(p=0.0, inplace=False)
            (dropout2): Dropout(p=0.1, inplace=False)
            (dropout3): Dropout(p=0.0, inplace=False)
            (self_attn_layer_norm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
            (fc1): Linear(in_features=1024, out_features=4096, bias=True)
            (fc2): Linear(in_features=4096, out_features=1024, bias=True)
            (final_layer_norm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
          )
        )
        (layer_norm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
      )
      (layer_norm): LayerNorm((2048,), eps=1e-05, elementwise_affine=True)
      (final_proj): None
    )
  )
  (decoder): PeftModelForCausalLM(
    (base_model): LoraModel(
      (model): LlamaForCausalLM(
        (model): LlamaModel(
          (embed_tokens): Embedding(46304, 2560, padding_idx=0)
          (layers): ModuleList(
            (0-31): 32 x LlamaDecoderLayer(
              (self_attn): LlamaSdpaAttention(
                (q_proj): lora.Linear4bit(
                  (base_layer): Linear4bit(in_features=2560, out_features=2560, bias=False)
                  (lora_dropout): ModuleDict(
                    (default): Dropout(p=0.05, inplace=False)
                  )
                  (lora_A): ModuleDict(
                    (default): Linear(in_features=2560, out_features=16, bias=False)
                  )
                  (lora_B): ModuleDict(
                    (default): Linear(in_features=16, out_features=2560, bias=False)
                  )
                  (lora_embedding_A): ParameterDict()
                  (lora_embedding_B): ParameterDict()
                )
                (k_proj): lora.Linear4bit(
                  (base_layer): Linear4bit(in_features=2560, out_features=2560, bias=False)
                  (lora_dropout): ModuleDict(
                    (default): Dropout(p=0.05, inplace=False)
                  )
                  (lora_A): ModuleDict(
                    (default): Linear(in_features=2560, out_features=16, bias=False)
                  )
                  (lora_B): ModuleDict(
                    (default): Linear(in_features=16, out_features=2560, bias=False)
                  )
                  (lora_embedding_A): ParameterDict()
                  (lora_embedding_B): ParameterDict()
                )
                (v_proj): lora.Linear4bit(
                  (base_layer): Linear4bit(in_features=2560, out_features=2560, bias=False)
                  (lora_dropout): ModuleDict(
                    (default): Dropout(p=0.05, inplace=False)
                  )
                  (lora_A): ModuleDict(
                    (default): Linear(in_features=2560, out_features=16, bias=False)
                  )
                  (lora_B): ModuleDict(
                    (default): Linear(in_features=16, out_features=2560, bias=False)
                  )
                  (lora_embedding_A): ParameterDict()
                  (lora_embedding_B): ParameterDict()
                )
                (o_proj): Linear4bit(in_features=2560, out_features=2560, bias=False)
                (rotary_emb): LlamaRotaryEmbedding()
              )
              (mlp): LlamaMLP(
                (gate_proj): Linear4bit(in_features=2560, out_features=6912, bias=False)
                (up_proj): Linear4bit(in_features=2560, out_features=6912, bias=False)
                (down_proj): Linear4bit(in_features=6912, out_features=2560, bias=False)
                (act_fn): SiLU()
              )
              (input_layernorm): LlamaRMSNorm()
              (post_attention_layernorm): LlamaRMSNorm()
            )
          )
          (norm): LlamaRMSNorm()
        )
        (lm_head): Linear(in_features=2560, out_features=46304, bias=False)
      )
    )
  )
  (avfeat_to_llm): Linear(in_features=1024, out_features=2560, bias=True)
)
[2024-06-15 00:52:00,292][fairseq_cli.train][INFO] - task: VSP_LLM_TrainingTask
[2024-06-15 00:52:00,292][fairseq_cli.train][INFO] - model: avhubert_llm_seq2seq_cluster_count
[2024-06-15 00:52:00,292][fairseq_cli.train][INFO] - criterion: decoder_only_language_modeling_loss
[2024-06-15 00:52:00,295][fairseq_cli.train][INFO] - num. shared model params: 1,841,644,264 (num. trained: 335,624,424)
[2024-06-15 00:52:00,298][fairseq_cli.train][INFO] - num. expert model params: 0 (num. trained: 0)
[2024-06-15 00:52:00,298][src.vsp_llm_training][INFO] - Using tokenizer
[2024-06-15 00:52:00,337][src.vsp_llm_dataset][INFO] - max_keep=500, min_keep=None, loaded 23990, skipped 0 short and 0 long and 0 unaligned, longest-loaded=76, shortest-loaded=76
[2024-06-15 00:52:00,715][src.vsp_llm_dataset][INFO] - /home/theodore/Projects/VSP-LLM/data/processed/vasr/valid.wrd is sequence label. skipped
[2024-06-15 00:52:00,715][src.vsp_llm_dataset][INFO] - image transform: Compose(
    Normalize(mean=0.0, std=255.0)
    <src.utils_vsp_llm.CenterCrop object at 0x79c6c3a19400>
    Normalize(mean=0.421, std=0.165)
)
[2024-06-15 00:52:00,715][src.vsp_llm_dataset][INFO] - pad_audio=True, random_crop=False, normalize=True, max_sample_size=500, seqs2seq data=True,
[2024-06-15 00:52:00,715][src.vsp_llm_dataset][INFO] - Noise wav: None->0 wav, Prob: 0.0, SNR: 0, Number of mixture: 1
[2024-06-15 00:52:00,892][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- encoder.w2v_model.feature_extractor_video.resnet.trunk.layer1.0.conv1.bias
[2024-06-15 00:52:00,892][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- encoder.w2v_model.feature_extractor_video.resnet.trunk.layer1.0.conv2.bias
[2024-06-15 00:52:00,892][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- encoder.w2v_model.feature_extractor_video.resnet.trunk.layer1.1.conv1.bias
[2024-06-15 00:52:00,892][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- encoder.w2v_model.feature_extractor_video.resnet.trunk.layer1.1.conv2.bias
[2024-06-15 00:52:00,892][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- encoder.w2v_model.feature_extractor_video.resnet.trunk.layer2.0.conv1.bias
[2024-06-15 00:52:00,892][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- encoder.w2v_model.feature_extractor_video.resnet.trunk.layer2.0.conv2.bias
[2024-06-15 00:52:00,892][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- encoder.w2v_model.feature_extractor_video.resnet.trunk.layer2.0.downsample.0.bias
[2024-06-15 00:52:00,892][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- encoder.w2v_model.feature_extractor_video.resnet.trunk.layer2.1.conv1.bias
[2024-06-15 00:52:00,892][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- encoder.w2v_model.feature_extractor_video.resnet.trunk.layer2.1.conv2.bias
[2024-06-15 00:52:00,892][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- encoder.w2v_model.feature_extractor_video.resnet.trunk.layer3.0.conv1.bias
[2024-06-15 00:52:00,892][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- encoder.w2v_model.feature_extractor_video.resnet.trunk.layer3.0.conv2.bias
[2024-06-15 00:52:00,892][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- encoder.w2v_model.feature_extractor_video.resnet.trunk.layer3.0.downsample.0.bias
[2024-06-15 00:52:00,892][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- encoder.w2v_model.feature_extractor_video.resnet.trunk.layer3.1.conv1.bias
[2024-06-15 00:52:00,892][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- encoder.w2v_model.feature_extractor_video.resnet.trunk.layer3.1.conv2.bias
[2024-06-15 00:52:00,893][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- encoder.w2v_model.feature_extractor_video.resnet.trunk.layer4.0.conv1.bias
[2024-06-15 00:52:00,893][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- encoder.w2v_model.feature_extractor_video.resnet.trunk.layer4.0.conv2.bias
[2024-06-15 00:52:00,893][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- encoder.w2v_model.feature_extractor_video.resnet.trunk.layer4.0.downsample.0.bias
[2024-06-15 00:52:00,893][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- encoder.w2v_model.feature_extractor_video.resnet.trunk.layer4.1.conv1.bias
[2024-06-15 00:52:00,893][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- encoder.w2v_model.feature_extractor_video.resnet.trunk.layer4.1.conv2.bias
[2024-06-15 00:52:00,893][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.0.self_attn.q_proj.base_layer.bias
[2024-06-15 00:52:00,893][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.0.self_attn.q_proj.lora_A.default.bias
[2024-06-15 00:52:00,893][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.0.self_attn.q_proj.lora_B.default.bias
[2024-06-15 00:52:00,893][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.0.self_attn.k_proj.base_layer.bias
[2024-06-15 00:52:00,893][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.0.self_attn.k_proj.lora_A.default.bias
[2024-06-15 00:52:00,893][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.0.self_attn.k_proj.lora_B.default.bias
[2024-06-15 00:52:00,893][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.0.self_attn.v_proj.base_layer.bias
[2024-06-15 00:52:00,893][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.0.self_attn.v_proj.lora_A.default.bias
[2024-06-15 00:52:00,893][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.0.self_attn.v_proj.lora_B.default.bias
[2024-06-15 00:52:00,893][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.0.self_attn.o_proj.bias
[2024-06-15 00:52:00,893][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.0.mlp.gate_proj.bias
[2024-06-15 00:52:00,893][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.0.mlp.up_proj.bias
[2024-06-15 00:52:00,893][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.0.mlp.down_proj.bias
[2024-06-15 00:52:00,893][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.1.self_attn.q_proj.base_layer.bias
[2024-06-15 00:52:00,893][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.1.self_attn.q_proj.lora_A.default.bias
[2024-06-15 00:52:00,893][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.1.self_attn.q_proj.lora_B.default.bias
[2024-06-15 00:52:00,893][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.1.self_attn.k_proj.base_layer.bias
[2024-06-15 00:52:00,893][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.1.self_attn.k_proj.lora_A.default.bias
[2024-06-15 00:52:00,893][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.1.self_attn.k_proj.lora_B.default.bias
[2024-06-15 00:52:00,893][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.1.self_attn.v_proj.base_layer.bias
[2024-06-15 00:52:00,893][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.1.self_attn.v_proj.lora_A.default.bias
[2024-06-15 00:52:00,893][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.1.self_attn.v_proj.lora_B.default.bias
[2024-06-15 00:52:00,893][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.1.self_attn.o_proj.bias
[2024-06-15 00:52:00,893][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.1.mlp.gate_proj.bias
[2024-06-15 00:52:00,893][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.1.mlp.up_proj.bias
[2024-06-15 00:52:00,893][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.1.mlp.down_proj.bias
[2024-06-15 00:52:00,893][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.2.self_attn.q_proj.base_layer.bias
[2024-06-15 00:52:00,893][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.2.self_attn.q_proj.lora_A.default.bias
[2024-06-15 00:52:00,893][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.2.self_attn.q_proj.lora_B.default.bias
[2024-06-15 00:52:00,893][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.2.self_attn.k_proj.base_layer.bias
[2024-06-15 00:52:00,893][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.2.self_attn.k_proj.lora_A.default.bias
[2024-06-15 00:52:00,893][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.2.self_attn.k_proj.lora_B.default.bias
[2024-06-15 00:52:00,893][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.2.self_attn.v_proj.base_layer.bias
[2024-06-15 00:52:00,893][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.2.self_attn.v_proj.lora_A.default.bias
[2024-06-15 00:52:00,893][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.2.self_attn.v_proj.lora_B.default.bias
[2024-06-15 00:52:00,893][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.2.self_attn.o_proj.bias
[2024-06-15 00:52:00,893][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.2.mlp.gate_proj.bias
[2024-06-15 00:52:00,893][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.2.mlp.up_proj.bias
[2024-06-15 00:52:00,893][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.2.mlp.down_proj.bias
[2024-06-15 00:52:00,894][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.3.self_attn.q_proj.base_layer.bias
[2024-06-15 00:52:00,894][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.3.self_attn.q_proj.lora_A.default.bias
[2024-06-15 00:52:00,894][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.3.self_attn.q_proj.lora_B.default.bias
[2024-06-15 00:52:00,894][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.3.self_attn.k_proj.base_layer.bias
[2024-06-15 00:52:00,894][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.3.self_attn.k_proj.lora_A.default.bias
[2024-06-15 00:52:00,894][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.3.self_attn.k_proj.lora_B.default.bias
[2024-06-15 00:52:00,894][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.3.self_attn.v_proj.base_layer.bias
[2024-06-15 00:52:00,894][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.3.self_attn.v_proj.lora_A.default.bias
[2024-06-15 00:52:00,894][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.3.self_attn.v_proj.lora_B.default.bias
[2024-06-15 00:52:00,894][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.3.self_attn.o_proj.bias
[2024-06-15 00:52:00,894][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.3.mlp.gate_proj.bias
[2024-06-15 00:52:00,894][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.3.mlp.up_proj.bias
[2024-06-15 00:52:00,894][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.3.mlp.down_proj.bias
[2024-06-15 00:52:00,894][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.4.self_attn.q_proj.base_layer.bias
[2024-06-15 00:52:00,894][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.4.self_attn.q_proj.lora_A.default.bias
[2024-06-15 00:52:00,894][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.4.self_attn.q_proj.lora_B.default.bias
[2024-06-15 00:52:00,894][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.4.self_attn.k_proj.base_layer.bias
[2024-06-15 00:52:00,894][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.4.self_attn.k_proj.lora_A.default.bias
[2024-06-15 00:52:00,894][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.4.self_attn.k_proj.lora_B.default.bias
[2024-06-15 00:52:00,894][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.4.self_attn.v_proj.base_layer.bias
[2024-06-15 00:52:00,894][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.4.self_attn.v_proj.lora_A.default.bias
[2024-06-15 00:52:00,894][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.4.self_attn.v_proj.lora_B.default.bias
[2024-06-15 00:52:00,894][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.4.self_attn.o_proj.bias
[2024-06-15 00:52:00,894][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.4.mlp.gate_proj.bias
[2024-06-15 00:52:00,894][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.4.mlp.up_proj.bias
[2024-06-15 00:52:00,894][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.4.mlp.down_proj.bias
[2024-06-15 00:52:00,894][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.5.self_attn.q_proj.base_layer.bias
[2024-06-15 00:52:00,894][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.5.self_attn.q_proj.lora_A.default.bias
[2024-06-15 00:52:00,894][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.5.self_attn.q_proj.lora_B.default.bias
[2024-06-15 00:52:00,894][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.5.self_attn.k_proj.base_layer.bias
[2024-06-15 00:52:00,894][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.5.self_attn.k_proj.lora_A.default.bias
[2024-06-15 00:52:00,894][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.5.self_attn.k_proj.lora_B.default.bias
[2024-06-15 00:52:00,894][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.5.self_attn.v_proj.base_layer.bias
[2024-06-15 00:52:00,894][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.5.self_attn.v_proj.lora_A.default.bias
[2024-06-15 00:52:00,894][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.5.self_attn.v_proj.lora_B.default.bias
[2024-06-15 00:52:00,894][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.5.self_attn.o_proj.bias
[2024-06-15 00:52:00,894][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.5.mlp.gate_proj.bias
[2024-06-15 00:52:00,894][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.5.mlp.up_proj.bias
[2024-06-15 00:52:00,894][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.5.mlp.down_proj.bias
[2024-06-15 00:52:00,894][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.6.self_attn.q_proj.base_layer.bias
[2024-06-15 00:52:00,894][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.6.self_attn.q_proj.lora_A.default.bias
[2024-06-15 00:52:00,894][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.6.self_attn.q_proj.lora_B.default.bias
[2024-06-15 00:52:00,894][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.6.self_attn.k_proj.base_layer.bias
[2024-06-15 00:52:00,894][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.6.self_attn.k_proj.lora_A.default.bias
[2024-06-15 00:52:00,894][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.6.self_attn.k_proj.lora_B.default.bias
[2024-06-15 00:52:00,894][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.6.self_attn.v_proj.base_layer.bias
[2024-06-15 00:52:00,894][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.6.self_attn.v_proj.lora_A.default.bias
[2024-06-15 00:52:00,894][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.6.self_attn.v_proj.lora_B.default.bias
[2024-06-15 00:52:00,894][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.6.self_attn.o_proj.bias
[2024-06-15 00:52:00,894][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.6.mlp.gate_proj.bias
[2024-06-15 00:52:00,894][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.6.mlp.up_proj.bias
[2024-06-15 00:52:00,894][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.6.mlp.down_proj.bias
[2024-06-15 00:52:00,894][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.7.self_attn.q_proj.base_layer.bias
[2024-06-15 00:52:00,894][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.7.self_attn.q_proj.lora_A.default.bias
[2024-06-15 00:52:00,894][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.7.self_attn.q_proj.lora_B.default.bias
[2024-06-15 00:52:00,895][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.7.self_attn.k_proj.base_layer.bias
[2024-06-15 00:52:00,895][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.7.self_attn.k_proj.lora_A.default.bias
[2024-06-15 00:52:00,895][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.7.self_attn.k_proj.lora_B.default.bias
[2024-06-15 00:52:00,895][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.7.self_attn.v_proj.base_layer.bias
[2024-06-15 00:52:00,895][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.7.self_attn.v_proj.lora_A.default.bias
[2024-06-15 00:52:00,895][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.7.self_attn.v_proj.lora_B.default.bias
[2024-06-15 00:52:00,895][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.7.self_attn.o_proj.bias
[2024-06-15 00:52:00,895][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.7.mlp.gate_proj.bias
[2024-06-15 00:52:00,895][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.7.mlp.up_proj.bias
[2024-06-15 00:52:00,895][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.7.mlp.down_proj.bias
[2024-06-15 00:52:00,895][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.8.self_attn.q_proj.base_layer.bias
[2024-06-15 00:52:00,895][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.8.self_attn.q_proj.lora_A.default.bias
[2024-06-15 00:52:00,895][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.8.self_attn.q_proj.lora_B.default.bias
[2024-06-15 00:52:00,895][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.8.self_attn.k_proj.base_layer.bias
[2024-06-15 00:52:00,895][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.8.self_attn.k_proj.lora_A.default.bias
[2024-06-15 00:52:00,895][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.8.self_attn.k_proj.lora_B.default.bias
[2024-06-15 00:52:00,895][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.8.self_attn.v_proj.base_layer.bias
[2024-06-15 00:52:00,895][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.8.self_attn.v_proj.lora_A.default.bias
[2024-06-15 00:52:00,895][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.8.self_attn.v_proj.lora_B.default.bias
[2024-06-15 00:52:00,895][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.8.self_attn.o_proj.bias
[2024-06-15 00:52:00,895][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.8.mlp.gate_proj.bias
[2024-06-15 00:52:00,895][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.8.mlp.up_proj.bias
[2024-06-15 00:52:00,895][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.8.mlp.down_proj.bias
[2024-06-15 00:52:00,895][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.9.self_attn.q_proj.base_layer.bias
[2024-06-15 00:52:00,895][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.9.self_attn.q_proj.lora_A.default.bias
[2024-06-15 00:52:00,895][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.9.self_attn.q_proj.lora_B.default.bias
[2024-06-15 00:52:00,895][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.9.self_attn.k_proj.base_layer.bias
[2024-06-15 00:52:00,895][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.9.self_attn.k_proj.lora_A.default.bias
[2024-06-15 00:52:00,895][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.9.self_attn.k_proj.lora_B.default.bias
[2024-06-15 00:52:00,895][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.9.self_attn.v_proj.base_layer.bias
[2024-06-15 00:52:00,895][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.9.self_attn.v_proj.lora_A.default.bias
[2024-06-15 00:52:00,895][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.9.self_attn.v_proj.lora_B.default.bias
[2024-06-15 00:52:00,895][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.9.self_attn.o_proj.bias
[2024-06-15 00:52:00,895][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.9.mlp.gate_proj.bias
[2024-06-15 00:52:00,895][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.9.mlp.up_proj.bias
[2024-06-15 00:52:00,895][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.9.mlp.down_proj.bias
[2024-06-15 00:52:00,895][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.10.self_attn.q_proj.base_layer.bias
[2024-06-15 00:52:00,895][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.10.self_attn.q_proj.lora_A.default.bias
[2024-06-15 00:52:00,895][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.10.self_attn.q_proj.lora_B.default.bias
[2024-06-15 00:52:00,895][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.10.self_attn.k_proj.base_layer.bias
[2024-06-15 00:52:00,895][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.10.self_attn.k_proj.lora_A.default.bias
[2024-06-15 00:52:00,895][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.10.self_attn.k_proj.lora_B.default.bias
[2024-06-15 00:52:00,895][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.10.self_attn.v_proj.base_layer.bias
[2024-06-15 00:52:00,895][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.10.self_attn.v_proj.lora_A.default.bias
[2024-06-15 00:52:00,895][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.10.self_attn.v_proj.lora_B.default.bias
[2024-06-15 00:52:00,895][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.10.self_attn.o_proj.bias
[2024-06-15 00:52:00,895][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.10.mlp.gate_proj.bias
[2024-06-15 00:52:00,895][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.10.mlp.up_proj.bias
[2024-06-15 00:52:00,895][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.10.mlp.down_proj.bias
[2024-06-15 00:52:00,895][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.11.self_attn.q_proj.base_layer.bias
[2024-06-15 00:52:00,895][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.11.self_attn.q_proj.lora_A.default.bias
[2024-06-15 00:52:00,896][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.11.self_attn.q_proj.lora_B.default.bias
[2024-06-15 00:52:00,896][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.11.self_attn.k_proj.base_layer.bias
[2024-06-15 00:52:00,896][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.11.self_attn.k_proj.lora_A.default.bias
[2024-06-15 00:52:00,896][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.11.self_attn.k_proj.lora_B.default.bias
[2024-06-15 00:52:00,896][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.11.self_attn.v_proj.base_layer.bias
[2024-06-15 00:52:00,896][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.11.self_attn.v_proj.lora_A.default.bias
[2024-06-15 00:52:00,896][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.11.self_attn.v_proj.lora_B.default.bias
[2024-06-15 00:52:00,896][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.11.self_attn.o_proj.bias
[2024-06-15 00:52:00,896][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.11.mlp.gate_proj.bias
[2024-06-15 00:52:00,896][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.11.mlp.up_proj.bias
[2024-06-15 00:52:00,896][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.11.mlp.down_proj.bias
[2024-06-15 00:52:00,896][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.12.self_attn.q_proj.base_layer.bias
[2024-06-15 00:52:00,896][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.12.self_attn.q_proj.lora_A.default.bias
[2024-06-15 00:52:00,896][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.12.self_attn.q_proj.lora_B.default.bias
[2024-06-15 00:52:00,896][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.12.self_attn.k_proj.base_layer.bias
[2024-06-15 00:52:00,896][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.12.self_attn.k_proj.lora_A.default.bias
[2024-06-15 00:52:00,896][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.12.self_attn.k_proj.lora_B.default.bias
[2024-06-15 00:52:00,896][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.12.self_attn.v_proj.base_layer.bias
[2024-06-15 00:52:00,896][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.12.self_attn.v_proj.lora_A.default.bias
[2024-06-15 00:52:00,896][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.12.self_attn.v_proj.lora_B.default.bias
[2024-06-15 00:52:00,896][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.12.self_attn.o_proj.bias
[2024-06-15 00:52:00,896][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.12.mlp.gate_proj.bias
[2024-06-15 00:52:00,896][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.12.mlp.up_proj.bias
[2024-06-15 00:52:00,896][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.12.mlp.down_proj.bias
[2024-06-15 00:52:00,896][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.13.self_attn.q_proj.base_layer.bias
[2024-06-15 00:52:00,896][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.13.self_attn.q_proj.lora_A.default.bias
[2024-06-15 00:52:00,896][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.13.self_attn.q_proj.lora_B.default.bias
[2024-06-15 00:52:00,896][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.13.self_attn.k_proj.base_layer.bias
[2024-06-15 00:52:00,896][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.13.self_attn.k_proj.lora_A.default.bias
[2024-06-15 00:52:00,896][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.13.self_attn.k_proj.lora_B.default.bias
[2024-06-15 00:52:00,896][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.13.self_attn.v_proj.base_layer.bias
[2024-06-15 00:52:00,896][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.13.self_attn.v_proj.lora_A.default.bias
[2024-06-15 00:52:00,896][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.13.self_attn.v_proj.lora_B.default.bias
[2024-06-15 00:52:00,896][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.13.self_attn.o_proj.bias
[2024-06-15 00:52:00,896][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.13.mlp.gate_proj.bias
[2024-06-15 00:52:00,896][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.13.mlp.up_proj.bias
[2024-06-15 00:52:00,896][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.13.mlp.down_proj.bias
[2024-06-15 00:52:00,896][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.14.self_attn.q_proj.base_layer.bias
[2024-06-15 00:52:00,896][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.14.self_attn.q_proj.lora_A.default.bias
[2024-06-15 00:52:00,896][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.14.self_attn.q_proj.lora_B.default.bias
[2024-06-15 00:52:00,896][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.14.self_attn.k_proj.base_layer.bias
[2024-06-15 00:52:00,896][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.14.self_attn.k_proj.lora_A.default.bias
[2024-06-15 00:52:00,896][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.14.self_attn.k_proj.lora_B.default.bias
[2024-06-15 00:52:00,896][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.14.self_attn.v_proj.base_layer.bias
[2024-06-15 00:52:00,896][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.14.self_attn.v_proj.lora_A.default.bias
[2024-06-15 00:52:00,896][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.14.self_attn.v_proj.lora_B.default.bias
[2024-06-15 00:52:00,896][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.14.self_attn.o_proj.bias
[2024-06-15 00:52:00,896][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.14.mlp.gate_proj.bias
[2024-06-15 00:52:00,896][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.14.mlp.up_proj.bias
[2024-06-15 00:52:00,896][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.14.mlp.down_proj.bias
[2024-06-15 00:52:00,896][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.15.self_attn.q_proj.base_layer.bias
[2024-06-15 00:52:00,896][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.15.self_attn.q_proj.lora_A.default.bias
[2024-06-15 00:52:00,896][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.15.self_attn.q_proj.lora_B.default.bias
[2024-06-15 00:52:00,896][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.15.self_attn.k_proj.base_layer.bias
[2024-06-15 00:52:00,897][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.15.self_attn.k_proj.lora_A.default.bias
[2024-06-15 00:52:00,897][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.15.self_attn.k_proj.lora_B.default.bias
[2024-06-15 00:52:00,897][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.15.self_attn.v_proj.base_layer.bias
[2024-06-15 00:52:00,897][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.15.self_attn.v_proj.lora_A.default.bias
[2024-06-15 00:52:00,897][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.15.self_attn.v_proj.lora_B.default.bias
[2024-06-15 00:52:00,897][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.15.self_attn.o_proj.bias
[2024-06-15 00:52:00,897][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.15.mlp.gate_proj.bias
[2024-06-15 00:52:00,897][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.15.mlp.up_proj.bias
[2024-06-15 00:52:00,897][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.15.mlp.down_proj.bias
[2024-06-15 00:52:00,897][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.16.self_attn.q_proj.base_layer.bias
[2024-06-15 00:52:00,897][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.16.self_attn.q_proj.lora_A.default.bias
[2024-06-15 00:52:00,897][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.16.self_attn.q_proj.lora_B.default.bias
[2024-06-15 00:52:00,897][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.16.self_attn.k_proj.base_layer.bias
[2024-06-15 00:52:00,897][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.16.self_attn.k_proj.lora_A.default.bias
[2024-06-15 00:52:00,897][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.16.self_attn.k_proj.lora_B.default.bias
[2024-06-15 00:52:00,897][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.16.self_attn.v_proj.base_layer.bias
[2024-06-15 00:52:00,897][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.16.self_attn.v_proj.lora_A.default.bias
[2024-06-15 00:52:00,897][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.16.self_attn.v_proj.lora_B.default.bias
[2024-06-15 00:52:00,897][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.16.self_attn.o_proj.bias
[2024-06-15 00:52:00,897][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.16.mlp.gate_proj.bias
[2024-06-15 00:52:00,897][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.16.mlp.up_proj.bias
[2024-06-15 00:52:00,897][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.16.mlp.down_proj.bias
[2024-06-15 00:52:00,897][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.17.self_attn.q_proj.base_layer.bias
[2024-06-15 00:52:00,897][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.17.self_attn.q_proj.lora_A.default.bias
[2024-06-15 00:52:00,897][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.17.self_attn.q_proj.lora_B.default.bias
[2024-06-15 00:52:00,897][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.17.self_attn.k_proj.base_layer.bias
[2024-06-15 00:52:00,897][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.17.self_attn.k_proj.lora_A.default.bias
[2024-06-15 00:52:00,897][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.17.self_attn.k_proj.lora_B.default.bias
[2024-06-15 00:52:00,897][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.17.self_attn.v_proj.base_layer.bias
[2024-06-15 00:52:00,897][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.17.self_attn.v_proj.lora_A.default.bias
[2024-06-15 00:52:00,897][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.17.self_attn.v_proj.lora_B.default.bias
[2024-06-15 00:52:00,897][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.17.self_attn.o_proj.bias
[2024-06-15 00:52:00,897][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.17.mlp.gate_proj.bias
[2024-06-15 00:52:00,897][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.17.mlp.up_proj.bias
[2024-06-15 00:52:00,897][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.17.mlp.down_proj.bias
[2024-06-15 00:52:00,897][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.18.self_attn.q_proj.base_layer.bias
[2024-06-15 00:52:00,897][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.18.self_attn.q_proj.lora_A.default.bias
[2024-06-15 00:52:00,897][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.18.self_attn.q_proj.lora_B.default.bias
[2024-06-15 00:52:00,897][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.18.self_attn.k_proj.base_layer.bias
[2024-06-15 00:52:00,897][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.18.self_attn.k_proj.lora_A.default.bias
[2024-06-15 00:52:00,897][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.18.self_attn.k_proj.lora_B.default.bias
[2024-06-15 00:52:00,897][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.18.self_attn.v_proj.base_layer.bias
[2024-06-15 00:52:00,897][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.18.self_attn.v_proj.lora_A.default.bias
[2024-06-15 00:52:00,897][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.18.self_attn.v_proj.lora_B.default.bias
[2024-06-15 00:52:00,897][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.18.self_attn.o_proj.bias
[2024-06-15 00:52:00,897][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.18.mlp.gate_proj.bias
[2024-06-15 00:52:00,897][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.18.mlp.up_proj.bias
[2024-06-15 00:52:00,897][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.18.mlp.down_proj.bias
[2024-06-15 00:52:00,897][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.19.self_attn.q_proj.base_layer.bias
[2024-06-15 00:52:00,897][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.19.self_attn.q_proj.lora_A.default.bias
[2024-06-15 00:52:00,897][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.19.self_attn.q_proj.lora_B.default.bias
[2024-06-15 00:52:00,897][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.19.self_attn.k_proj.base_layer.bias
[2024-06-15 00:52:00,898][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.19.self_attn.k_proj.lora_A.default.bias
[2024-06-15 00:52:00,898][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.19.self_attn.k_proj.lora_B.default.bias
[2024-06-15 00:52:00,898][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.19.self_attn.v_proj.base_layer.bias
[2024-06-15 00:52:00,898][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.19.self_attn.v_proj.lora_A.default.bias
[2024-06-15 00:52:00,898][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.19.self_attn.v_proj.lora_B.default.bias
[2024-06-15 00:52:00,898][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.19.self_attn.o_proj.bias
[2024-06-15 00:52:00,898][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.19.mlp.gate_proj.bias
[2024-06-15 00:52:00,898][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.19.mlp.up_proj.bias
[2024-06-15 00:52:00,898][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.19.mlp.down_proj.bias
[2024-06-15 00:52:00,898][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.20.self_attn.q_proj.base_layer.bias
[2024-06-15 00:52:00,898][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.20.self_attn.q_proj.lora_A.default.bias
[2024-06-15 00:52:00,898][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.20.self_attn.q_proj.lora_B.default.bias
[2024-06-15 00:52:00,898][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.20.self_attn.k_proj.base_layer.bias
[2024-06-15 00:52:00,898][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.20.self_attn.k_proj.lora_A.default.bias
[2024-06-15 00:52:00,898][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.20.self_attn.k_proj.lora_B.default.bias
[2024-06-15 00:52:00,898][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.20.self_attn.v_proj.base_layer.bias
[2024-06-15 00:52:00,898][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.20.self_attn.v_proj.lora_A.default.bias
[2024-06-15 00:52:00,898][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.20.self_attn.v_proj.lora_B.default.bias
[2024-06-15 00:52:00,898][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.20.self_attn.o_proj.bias
[2024-06-15 00:52:00,898][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.20.mlp.gate_proj.bias
[2024-06-15 00:52:00,898][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.20.mlp.up_proj.bias
[2024-06-15 00:52:00,898][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.20.mlp.down_proj.bias
[2024-06-15 00:52:00,898][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.21.self_attn.q_proj.base_layer.bias
[2024-06-15 00:52:00,898][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.21.self_attn.q_proj.lora_A.default.bias
[2024-06-15 00:52:00,898][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.21.self_attn.q_proj.lora_B.default.bias
[2024-06-15 00:52:00,898][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.21.self_attn.k_proj.base_layer.bias
[2024-06-15 00:52:00,898][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.21.self_attn.k_proj.lora_A.default.bias
[2024-06-15 00:52:00,898][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.21.self_attn.k_proj.lora_B.default.bias
[2024-06-15 00:52:00,898][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.21.self_attn.v_proj.base_layer.bias
[2024-06-15 00:52:00,898][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.21.self_attn.v_proj.lora_A.default.bias
[2024-06-15 00:52:00,898][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.21.self_attn.v_proj.lora_B.default.bias
[2024-06-15 00:52:00,898][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.21.self_attn.o_proj.bias
[2024-06-15 00:52:00,898][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.21.mlp.gate_proj.bias
[2024-06-15 00:52:00,898][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.21.mlp.up_proj.bias
[2024-06-15 00:52:00,898][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.21.mlp.down_proj.bias
[2024-06-15 00:52:00,898][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.22.self_attn.q_proj.base_layer.bias
[2024-06-15 00:52:00,898][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.22.self_attn.q_proj.lora_A.default.bias
[2024-06-15 00:52:00,898][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.22.self_attn.q_proj.lora_B.default.bias
[2024-06-15 00:52:00,898][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.22.self_attn.k_proj.base_layer.bias
[2024-06-15 00:52:00,898][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.22.self_attn.k_proj.lora_A.default.bias
[2024-06-15 00:52:00,898][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.22.self_attn.k_proj.lora_B.default.bias
[2024-06-15 00:52:00,898][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.22.self_attn.v_proj.base_layer.bias
[2024-06-15 00:52:00,898][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.22.self_attn.v_proj.lora_A.default.bias
[2024-06-15 00:52:00,898][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.22.self_attn.v_proj.lora_B.default.bias
[2024-06-15 00:52:00,898][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.22.self_attn.o_proj.bias
[2024-06-15 00:52:00,898][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.22.mlp.gate_proj.bias
[2024-06-15 00:52:00,898][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.22.mlp.up_proj.bias
[2024-06-15 00:52:00,898][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.22.mlp.down_proj.bias
[2024-06-15 00:52:00,898][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.23.self_attn.q_proj.base_layer.bias
[2024-06-15 00:52:00,898][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.23.self_attn.q_proj.lora_A.default.bias
[2024-06-15 00:52:00,898][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.23.self_attn.q_proj.lora_B.default.bias
[2024-06-15 00:52:00,898][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.23.self_attn.k_proj.base_layer.bias
[2024-06-15 00:52:00,899][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.23.self_attn.k_proj.lora_A.default.bias
[2024-06-15 00:52:00,899][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.23.self_attn.k_proj.lora_B.default.bias
[2024-06-15 00:52:00,899][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.23.self_attn.v_proj.base_layer.bias
[2024-06-15 00:52:00,899][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.23.self_attn.v_proj.lora_A.default.bias
[2024-06-15 00:52:00,899][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.23.self_attn.v_proj.lora_B.default.bias
[2024-06-15 00:52:00,899][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.23.self_attn.o_proj.bias
[2024-06-15 00:52:00,899][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.23.mlp.gate_proj.bias
[2024-06-15 00:52:00,899][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.23.mlp.up_proj.bias
[2024-06-15 00:52:00,899][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.23.mlp.down_proj.bias
[2024-06-15 00:52:00,899][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.24.self_attn.q_proj.base_layer.bias
[2024-06-15 00:52:00,899][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.24.self_attn.q_proj.lora_A.default.bias
[2024-06-15 00:52:00,899][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.24.self_attn.q_proj.lora_B.default.bias
[2024-06-15 00:52:00,899][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.24.self_attn.k_proj.base_layer.bias
[2024-06-15 00:52:00,899][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.24.self_attn.k_proj.lora_A.default.bias
[2024-06-15 00:52:00,899][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.24.self_attn.k_proj.lora_B.default.bias
[2024-06-15 00:52:00,899][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.24.self_attn.v_proj.base_layer.bias
[2024-06-15 00:52:00,899][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.24.self_attn.v_proj.lora_A.default.bias
[2024-06-15 00:52:00,899][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.24.self_attn.v_proj.lora_B.default.bias
[2024-06-15 00:52:00,899][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.24.self_attn.o_proj.bias
[2024-06-15 00:52:00,899][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.24.mlp.gate_proj.bias
[2024-06-15 00:52:00,899][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.24.mlp.up_proj.bias
[2024-06-15 00:52:00,899][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.24.mlp.down_proj.bias
[2024-06-15 00:52:00,899][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.25.self_attn.q_proj.base_layer.bias
[2024-06-15 00:52:00,899][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.25.self_attn.q_proj.lora_A.default.bias
[2024-06-15 00:52:00,899][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.25.self_attn.q_proj.lora_B.default.bias
[2024-06-15 00:52:00,899][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.25.self_attn.k_proj.base_layer.bias
[2024-06-15 00:52:00,899][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.25.self_attn.k_proj.lora_A.default.bias
[2024-06-15 00:52:00,899][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.25.self_attn.k_proj.lora_B.default.bias
[2024-06-15 00:52:00,899][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.25.self_attn.v_proj.base_layer.bias
[2024-06-15 00:52:00,899][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.25.self_attn.v_proj.lora_A.default.bias
[2024-06-15 00:52:00,899][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.25.self_attn.v_proj.lora_B.default.bias
[2024-06-15 00:52:00,899][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.25.self_attn.o_proj.bias
[2024-06-15 00:52:00,899][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.25.mlp.gate_proj.bias
[2024-06-15 00:52:00,899][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.25.mlp.up_proj.bias
[2024-06-15 00:52:00,899][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.25.mlp.down_proj.bias
[2024-06-15 00:52:00,899][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.26.self_attn.q_proj.base_layer.bias
[2024-06-15 00:52:00,899][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.26.self_attn.q_proj.lora_A.default.bias
[2024-06-15 00:52:00,899][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.26.self_attn.q_proj.lora_B.default.bias
[2024-06-15 00:52:00,899][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.26.self_attn.k_proj.base_layer.bias
[2024-06-15 00:52:00,899][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.26.self_attn.k_proj.lora_A.default.bias
[2024-06-15 00:52:00,899][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.26.self_attn.k_proj.lora_B.default.bias
[2024-06-15 00:52:00,899][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.26.self_attn.v_proj.base_layer.bias
[2024-06-15 00:52:00,899][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.26.self_attn.v_proj.lora_A.default.bias
[2024-06-15 00:52:00,899][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.26.self_attn.v_proj.lora_B.default.bias
[2024-06-15 00:52:00,899][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.26.self_attn.o_proj.bias
[2024-06-15 00:52:00,899][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.26.mlp.gate_proj.bias
[2024-06-15 00:52:00,899][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.26.mlp.up_proj.bias
[2024-06-15 00:52:00,899][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.26.mlp.down_proj.bias
[2024-06-15 00:52:00,899][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.27.self_attn.q_proj.base_layer.bias
[2024-06-15 00:52:00,900][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.27.self_attn.q_proj.lora_A.default.bias
[2024-06-15 00:52:00,900][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.27.self_attn.q_proj.lora_B.default.bias
[2024-06-15 00:52:00,900][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.27.self_attn.k_proj.base_layer.bias
[2024-06-15 00:52:00,900][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.27.self_attn.k_proj.lora_A.default.bias
[2024-06-15 00:52:00,900][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.27.self_attn.k_proj.lora_B.default.bias
[2024-06-15 00:52:00,900][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.27.self_attn.v_proj.base_layer.bias
[2024-06-15 00:52:00,900][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.27.self_attn.v_proj.lora_A.default.bias
[2024-06-15 00:52:00,900][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.27.self_attn.v_proj.lora_B.default.bias
[2024-06-15 00:52:00,900][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.27.self_attn.o_proj.bias
[2024-06-15 00:52:00,900][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.27.mlp.gate_proj.bias
[2024-06-15 00:52:00,900][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.27.mlp.up_proj.bias
[2024-06-15 00:52:00,900][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.27.mlp.down_proj.bias
[2024-06-15 00:52:00,900][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.28.self_attn.q_proj.base_layer.bias
[2024-06-15 00:52:00,900][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.28.self_attn.q_proj.lora_A.default.bias
[2024-06-15 00:52:00,900][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.28.self_attn.q_proj.lora_B.default.bias
[2024-06-15 00:52:00,900][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.28.self_attn.k_proj.base_layer.bias
[2024-06-15 00:52:00,900][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.28.self_attn.k_proj.lora_A.default.bias
[2024-06-15 00:52:00,900][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.28.self_attn.k_proj.lora_B.default.bias
[2024-06-15 00:52:00,900][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.28.self_attn.v_proj.base_layer.bias
[2024-06-15 00:52:00,900][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.28.self_attn.v_proj.lora_A.default.bias
[2024-06-15 00:52:00,900][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.28.self_attn.v_proj.lora_B.default.bias
[2024-06-15 00:52:00,900][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.28.self_attn.o_proj.bias
[2024-06-15 00:52:00,900][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.28.mlp.gate_proj.bias
[2024-06-15 00:52:00,900][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.28.mlp.up_proj.bias
[2024-06-15 00:52:00,900][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.28.mlp.down_proj.bias
[2024-06-15 00:52:00,900][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.29.self_attn.q_proj.base_layer.bias
[2024-06-15 00:52:00,900][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.29.self_attn.q_proj.lora_A.default.bias
[2024-06-15 00:52:00,900][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.29.self_attn.q_proj.lora_B.default.bias
[2024-06-15 00:52:00,900][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.29.self_attn.k_proj.base_layer.bias
[2024-06-15 00:52:00,900][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.29.self_attn.k_proj.lora_A.default.bias
[2024-06-15 00:52:00,900][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.29.self_attn.k_proj.lora_B.default.bias
[2024-06-15 00:52:00,900][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.29.self_attn.v_proj.base_layer.bias
[2024-06-15 00:52:00,900][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.29.self_attn.v_proj.lora_A.default.bias
[2024-06-15 00:52:00,900][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.29.self_attn.v_proj.lora_B.default.bias
[2024-06-15 00:52:00,900][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.29.self_attn.o_proj.bias
[2024-06-15 00:52:00,900][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.29.mlp.gate_proj.bias
[2024-06-15 00:52:00,900][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.29.mlp.up_proj.bias
[2024-06-15 00:52:00,900][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.29.mlp.down_proj.bias
[2024-06-15 00:52:00,900][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.30.self_attn.q_proj.base_layer.bias
[2024-06-15 00:52:00,900][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.30.self_attn.q_proj.lora_A.default.bias
[2024-06-15 00:52:00,900][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.30.self_attn.q_proj.lora_B.default.bias
[2024-06-15 00:52:00,900][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.30.self_attn.k_proj.base_layer.bias
[2024-06-15 00:52:00,900][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.30.self_attn.k_proj.lora_A.default.bias
[2024-06-15 00:52:00,900][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.30.self_attn.k_proj.lora_B.default.bias
[2024-06-15 00:52:00,900][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.30.self_attn.v_proj.base_layer.bias
[2024-06-15 00:52:00,900][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.30.self_attn.v_proj.lora_A.default.bias
[2024-06-15 00:52:00,900][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.30.self_attn.v_proj.lora_B.default.bias
[2024-06-15 00:52:00,900][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.30.self_attn.o_proj.bias
[2024-06-15 00:52:00,900][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.30.mlp.gate_proj.bias
[2024-06-15 00:52:00,900][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.30.mlp.up_proj.bias
[2024-06-15 00:52:00,900][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.30.mlp.down_proj.bias
[2024-06-15 00:52:00,900][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.31.self_attn.q_proj.base_layer.bias
[2024-06-15 00:52:00,900][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.31.self_attn.q_proj.lora_A.default.bias
[2024-06-15 00:52:00,900][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.31.self_attn.q_proj.lora_B.default.bias
[2024-06-15 00:52:00,901][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.31.self_attn.k_proj.base_layer.bias
[2024-06-15 00:52:00,901][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.31.self_attn.k_proj.lora_A.default.bias
[2024-06-15 00:52:00,901][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.31.self_attn.k_proj.lora_B.default.bias
[2024-06-15 00:52:00,901][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.31.self_attn.v_proj.base_layer.bias
[2024-06-15 00:52:00,901][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.31.self_attn.v_proj.lora_A.default.bias
[2024-06-15 00:52:00,901][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.31.self_attn.v_proj.lora_B.default.bias
[2024-06-15 00:52:00,901][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.31.self_attn.o_proj.bias
[2024-06-15 00:52:00,901][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.31.mlp.gate_proj.bias
[2024-06-15 00:52:00,901][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.31.mlp.up_proj.bias
[2024-06-15 00:52:00,901][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.model.layers.31.mlp.down_proj.bias
[2024-06-15 00:52:00,901][fairseq.trainer][INFO] - detected shared parameter: encoder.w2v_model.feature_extractor_video.resnet.frontend3D.0.bias <- decoder.base_model.model.lm_head.bias
[2024-06-15 00:52:00,901][fairseq.utils][INFO] - ***********************CUDA enviroments for all 1 workers***********************
[2024-06-15 00:52:00,901][fairseq.utils][INFO] - rank   0: capabilities =  8.6  ; total memory = 15.729 GB ; name = NVIDIA RTX A4000                        
[2024-06-15 00:52:00,901][fairseq.utils][INFO] - ***********************CUDA enviroments for all 1 workers***********************
[2024-06-15 00:52:00,901][fairseq_cli.train][INFO] - training on 1 devices (GPUs/TPUs)
[2024-06-15 00:52:00,901][fairseq_cli.train][INFO] - max tokens per device = None and max sentences per device = 1
[2024-06-15 00:52:00,901][fairseq.trainer][INFO] - Preparing to load checkpoint checkpoints/checkpoint_last.pt
[2024-06-15 00:52:00,902][fairseq.trainer][INFO] - No existing checkpoint found checkpoints/checkpoint_last.pt
[2024-06-15 00:52:00,902][fairseq.trainer][INFO] - loading train data for epoch 1
[2024-06-15 00:52:00,902][src.vsp_llm_training][INFO] - Using tokenizer
[2024-06-15 00:52:01,070][src.vsp_llm_dataset][INFO] - max_keep=500, min_keep=None, loaded 120686, skipped 0 short and 0 long and 0 unaligned, longest-loaded=76, shortest-loaded=73
[2024-06-15 00:52:01,427][src.vsp_llm_dataset][INFO] - /home/theodore/Projects/VSP-LLM/data/processed/vasr/train.wrd is sequence label. skipped
[2024-06-15 00:52:01,427][src.vsp_llm_dataset][INFO] - image transform: Compose(
    Normalize(mean=0.0, std=255.0)
    RandomCrop(size=(88, 88))
    <src.utils_vsp_llm.HorizontalFlip object at 0x79c6c3f2c430>
    Normalize(mean=0.421, std=0.165)
)
[2024-06-15 00:52:01,428][src.vsp_llm_dataset][INFO] - pad_audio=True, random_crop=False, normalize=True, max_sample_size=500, seqs2seq data=True,
[2024-06-15 00:52:01,428][src.vsp_llm_dataset][INFO] - Noise wav: None->0 wav, Prob: 0.0, SNR: 0, Number of mixture: 1
[2024-06-15 00:52:05,871][fairseq.trainer][INFO] - begin training epoch 1
[2024-06-15 00:52:05,871][fairseq_cli.train][INFO] - Start iterating over samples
[2024-06-15 00:57:31,626][train_inner][INFO] - {"epoch": 1, "update": 0.013, "loss": "7.653", "ntokens": "126.725", "acc_total": "126.725", "n_correct": "17.625", "wer_total": "126.725", "n_error": "109.03", "ppl": "201.3", "accuracy": "13.908", "wer": "86.037", "wps": "77.9", "ups": "0.61", "wpb": "126.7", "bsz": "8", "num_updates": "200", "lr": "1.49e-05", "gnorm": "8.816", "loss_scale": "128", "train_wall": "325", "gb_free": "7.1", "wall": "331"}
[2024-06-15 01:02:59,048][train_inner][INFO] - {"epoch": 1, "update": 0.027, "loss": "6.228", "ntokens": "126.93", "acc_total": "126.93", "n_correct": "25.55", "wer_total": "126.93", "n_error": "101.22", "ppl": "74.97", "accuracy": "20.129", "wer": "79.745", "wps": "77.5", "ups": "0.61", "wpb": "126.9", "bsz": "8", "num_updates": "400", "lr": "2.48e-05", "gnorm": "3.659", "loss_scale": "128", "train_wall": "327", "gb_free": "7.1", "wall": "658"}
[2024-06-15 01:08:26,785][train_inner][INFO] - {"epoch": 1, "update": 0.04, "loss": "6.1", "ntokens": "127.015", "acc_total": "127.015", "n_correct": "28.08", "wer_total": "127.015", "n_error": "98.67", "ppl": "68.61", "accuracy": "22.108", "wer": "77.684", "wps": "77.5", "ups": "0.61", "wpb": "127", "bsz": "8", "num_updates": "600", "lr": "3.47e-05", "gnorm": "3.642", "loss_scale": "128", "train_wall": "327", "gb_free": "7.1", "wall": "986"}
[2024-06-15 01:13:54,381][train_inner][INFO] - {"epoch": 1, "update": 0.053, "loss": "5.911", "ntokens": "126.865", "acc_total": "126.865", "n_correct": "29.77", "wer_total": "126.865", "n_error": "96.86", "ppl": "60.18", "accuracy": "23.466", "wer": "76.349", "wps": "77.5", "ups": "0.61", "wpb": "126.9", "bsz": "8", "num_updates": "800", "lr": "4.46e-05", "gnorm": "3.675", "loss_scale": "128", "train_wall": "327", "gb_free": "7.1", "wall": "1313"}
[2024-06-15 01:19:21,223][train_inner][INFO] - {"epoch": 1, "update": 0.066, "loss": "5.986", "ntokens": "127.025", "acc_total": "127.025", "n_correct": "29.68", "wer_total": "127.025", "n_error": "97.1", "ppl": "63.4", "accuracy": "23.365", "wer": "76.442", "wps": "77.7", "ups": "0.61", "wpb": "127", "bsz": "8", "num_updates": "1000", "lr": "5.45e-05", "gnorm": "3.383", "loss_scale": "128", "train_wall": "326", "gb_free": "7.1", "wall": "1640"}
[2024-06-15 01:24:48,144][train_inner][INFO] - {"epoch": 1, "update": 0.08, "loss": "5.935", "ntokens": "127.095", "acc_total": "127.095", "n_correct": "30", "wer_total": "127.095", "n_error": "96.86", "ppl": "61.2", "accuracy": "23.604", "wer": "76.211", "wps": "77.8", "ups": "0.61", "wpb": "127.1", "bsz": "8", "num_updates": "1200", "lr": "6.44e-05", "gnorm": "3.179", "loss_scale": "128", "train_wall": "326", "gb_free": "7.1", "wall": "1967"}
[2024-06-15 01:30:15,106][train_inner][INFO] - {"epoch": 1, "update": 0.093, "loss": "5.786", "ntokens": "127.62", "acc_total": "127.62", "n_correct": "31.32", "wer_total": "127.62", "n_error": "96.11", "ppl": "55.18", "accuracy": "24.542", "wer": "75.31", "wps": "78.1", "ups": "0.61", "wpb": "127.6", "bsz": "8", "num_updates": "1400", "lr": "7.43e-05", "gnorm": "2.971", "loss_scale": "128", "train_wall": "326", "gb_free": "7.1", "wall": "2294"}
[2024-06-15 01:35:42,869][train_inner][INFO] - {"epoch": 1, "update": 0.106, "loss": "5.816", "ntokens": "127.41", "acc_total": "127.41", "n_correct": "31.21", "wer_total": "127.41", "n_error": "95.89", "ppl": "56.32", "accuracy": "24.496", "wer": "75.261", "wps": "77.7", "ups": "0.61", "wpb": "127.4", "bsz": "8", "num_updates": "1600", "lr": "8.42e-05", "gnorm": "2.741", "loss_scale": "128", "train_wall": "327", "gb_free": "7.1", "wall": "2622"}
[2024-06-15 01:41:10,609][train_inner][INFO] - {"epoch": 1, "update": 0.119, "loss": "5.874", "ntokens": "126.56", "acc_total": "126.56", "n_correct": "30.68", "wer_total": "126.56", "n_error": "95.71", "ppl": "58.64", "accuracy": "24.241", "wer": "75.624", "wps": "77.2", "ups": "0.61", "wpb": "126.6", "bsz": "8", "num_updates": "1800", "lr": "9.41e-05", "gnorm": "2.591", "loss_scale": "128", "train_wall": "327", "gb_free": "7.1", "wall": "2950"}
[2024-06-15 01:46:38,036][train_inner][INFO] - {"epoch": 1, "update": 0.133, "loss": "5.789", "ntokens": "126.875", "acc_total": "126.875", "n_correct": "31.65", "wer_total": "126.875", "n_error": "95.06", "ppl": "55.3", "accuracy": "24.946", "wer": "74.924", "wps": "77.5", "ups": "0.61", "wpb": "126.9", "bsz": "8", "num_updates": "2000", "lr": "0.000104", "gnorm": "2.416", "loss_scale": "128", "train_wall": "327", "gb_free": "7.1", "wall": "3277"}
[2024-06-15 01:52:05,895][train_inner][INFO] - {"epoch": 1, "update": 0.146, "loss": "5.755", "ntokens": "128.2", "acc_total": "128.2", "n_correct": "31.92", "wer_total": "128.2", "n_error": "96", "ppl": "54", "accuracy": "24.899", "wer": "74.883", "wps": "78.2", "ups": "0.61", "wpb": "128.2", "bsz": "8", "num_updates": "2200", "lr": "0.0001139", "gnorm": "2.249", "loss_scale": "256", "train_wall": "327", "gb_free": "7.1", "wall": "3605"}
[2024-06-15 01:57:33,897][train_inner][INFO] - {"epoch": 1, "update": 0.159, "loss": "5.749", "ntokens": "127.775", "acc_total": "127.775", "n_correct": "32.21", "wer_total": "127.775", "n_error": "95.35", "ppl": "53.76", "accuracy": "25.208", "wer": "74.623", "wps": "77.9", "ups": "0.61", "wpb": "127.8", "bsz": "8", "num_updates": "2400", "lr": "0.0001238", "gnorm": "2.097", "loss_scale": "256", "train_wall": "327", "gb_free": "7.1", "wall": "3933"}
[2024-06-15 02:00:17,920][fairseq_cli.train][INFO] - begin validation on "valid" subset
[2024-06-15 02:42:01,030][valid][INFO] - {"epoch": 1, "valid_loss": "5.673", "valid_ntokens": "18.1585", "valid_acc_total": "18.1585", "valid_n_correct": "4.66215", "valid_wer_total": "18.1585", "valid_n_error": "13.4569", "valid_ppl": "51.02", "valid_accuracy": "25.675", "valid_wer": "74.108", "valid_wps": "174", "valid_wpb": "18.2", "valid_bsz": "1", "valid_num_updates": "2500"}
[2024-06-15 02:42:01,031][fairseq.checkpoint_utils][INFO] - Preparing to save checkpoint for epoch 1 @ 2500 updates
[2024-06-15 02:42:01,031][fairseq.trainer][INFO] - Saving checkpoint to checkpoints/checkpoint_1_2500.pt
[2024-06-15 02:42:04,118][fairseq.trainer][INFO] - Finished saving checkpoint to checkpoints/checkpoint_1_2500.pt
[2024-06-15 02:42:06,850][fairseq.checkpoint_utils][INFO] - Saved checkpoint checkpoints/checkpoint_1_2500.pt (epoch 1 @ 2500 updates, score 25.675) (writing took 5.819389069001772 seconds)
[2024-06-15 02:44:50,079][train_inner][INFO] - {"epoch": 1, "update": 0.172, "loss": "5.737", "ntokens": "126.92", "acc_total": "126.92", "n_correct": "31.765", "wer_total": "126.92", "n_error": "95.005", "ppl": "53.34", "accuracy": "25.028", "wer": "74.854", "wps": "9", "ups": "0.07", "wpb": "126.9", "bsz": "8", "num_updates": "2600", "lr": "0.0001337", "gnorm": "1.986", "loss_scale": "256", "train_wall": "327", "gb_free": "7.1", "wall": "6769"}
[2024-06-15 02:50:17,543][train_inner][INFO] - {"epoch": 1, "update": 0.186, "loss": "5.77", "ntokens": "125.685", "acc_total": "125.685", "n_correct": "31.445", "wer_total": "125.685", "n_error": "94.045", "ppl": "54.55", "accuracy": "25.019", "wer": "74.826", "wps": "76.8", "ups": "0.61", "wpb": "125.7", "bsz": "8", "num_updates": "2800", "lr": "0.0001436", "gnorm": "1.939", "loss_scale": "256", "train_wall": "327", "gb_free": "7.1", "wall": "7097"}
[2024-06-15 02:55:44,223][train_inner][INFO] - {"epoch": 1, "update": 0.199, "loss": "5.752", "ntokens": "127.19", "acc_total": "127.19", "n_correct": "32.58", "wer_total": "127.19", "n_error": "94.365", "ppl": "53.89", "accuracy": "25.615", "wer": "74.192", "wps": "77.9", "ups": "0.61", "wpb": "127.2", "bsz": "8", "num_updates": "3000", "lr": "0.0001535", "gnorm": "1.887", "loss_scale": "256", "train_wall": "326", "gb_free": "7.1", "wall": "7423"}
[2024-06-15 03:01:11,678][train_inner][INFO] - {"epoch": 1, "update": 0.212, "loss": "5.68", "ntokens": "126.535", "acc_total": "126.535", "n_correct": "32.935", "wer_total": "126.535", "n_error": "93.395", "ppl": "51.27", "accuracy": "26.028", "wer": "73.81", "wps": "77.3", "ups": "0.61", "wpb": "126.5", "bsz": "8", "num_updates": "3200", "lr": "0.0001634", "gnorm": "1.858", "loss_scale": "256", "train_wall": "327", "gb_free": "7.1", "wall": "7751"}
[2024-06-15 03:06:38,814][train_inner][INFO] - {"epoch": 1, "update": 0.225, "loss": "5.69", "ntokens": "126.53", "acc_total": "126.53", "n_correct": "32.885", "wer_total": "126.53", "n_error": "93.425", "ppl": "51.62", "accuracy": "25.99", "wer": "73.836", "wps": "77.4", "ups": "0.61", "wpb": "126.5", "bsz": "8", "num_updates": "3400", "lr": "0.0001733", "gnorm": "1.846", "loss_scale": "256", "train_wall": "326", "gb_free": "7.1", "wall": "8078"}
[2024-06-15 03:12:06,165][train_inner][INFO] - {"epoch": 1, "update": 0.239, "loss": "5.621", "ntokens": "127.025", "acc_total": "127.025", "n_correct": "33.72", "wer_total": "127.025", "n_error": "93.035", "ppl": "49.21", "accuracy": "26.546", "wer": "73.241", "wps": "77.6", "ups": "0.61", "wpb": "127", "bsz": "8", "num_updates": "3600", "lr": "0.0001832", "gnorm": "1.825", "loss_scale": "256", "train_wall": "327", "gb_free": "7.1", "wall": "8405"}
[2024-06-15 03:17:33,259][train_inner][INFO] - {"epoch": 1, "update": 0.252, "loss": "5.608", "ntokens": "127.35", "acc_total": "127.35", "n_correct": "34.315", "wer_total": "127.35", "n_error": "92.77", "ppl": "48.78", "accuracy": "26.945", "wer": "72.846", "wps": "77.9", "ups": "0.61", "wpb": "127.3", "bsz": "8", "num_updates": "3800", "lr": "0.0001931", "gnorm": "1.789", "loss_scale": "256", "train_wall": "326", "gb_free": "7.1", "wall": "8732"}
[2024-06-15 03:23:00,598][train_inner][INFO] - {"epoch": 1, "update": 0.265, "loss": "5.573", "ntokens": "127.785", "acc_total": "127.785", "n_correct": "34.91", "wer_total": "127.785", "n_error": "92.7", "ppl": "47.62", "accuracy": "27.319", "wer": "72.544", "wps": "78.1", "ups": "0.61", "wpb": "127.8", "bsz": "8", "num_updates": "4000", "lr": "0.000203", "gnorm": "1.862", "loss_scale": "256", "train_wall": "327", "gb_free": "7.1", "wall": "9060"}
[2024-06-15 03:28:27,968][train_inner][INFO] - {"epoch": 1, "update": 0.278, "loss": "5.554", "ntokens": "126.255", "acc_total": "126.255", "n_correct": "35.245", "wer_total": "126.255", "n_error": "90.78", "ppl": "46.98", "accuracy": "27.916", "wer": "71.902", "wps": "77.1", "ups": "0.61", "wpb": "126.3", "bsz": "8", "num_updates": "4200", "lr": "0.0002129", "gnorm": "1.88", "loss_scale": "512", "train_wall": "327", "gb_free": "7.1", "wall": "9387"}
[2024-06-15 03:33:55,493][train_inner][INFO] - {"epoch": 1, "update": 0.292, "loss": "5.508", "ntokens": "125.9", "acc_total": "125.9", "n_correct": "35.565", "wer_total": "125.9", "n_error": "90.105", "ppl": "45.51", "accuracy": "28.249", "wer": "71.569", "wps": "76.9", "ups": "0.61", "wpb": "125.9", "bsz": "8", "num_updates": "4400", "lr": "0.0002228", "gnorm": "1.905", "loss_scale": "512", "train_wall": "327", "gb_free": "7.1", "wall": "9715"}
[2024-06-15 03:39:23,422][train_inner][INFO] - {"epoch": 1, "update": 0.305, "loss": "5.413", "ntokens": "127.885", "acc_total": "127.885", "n_correct": "37.035", "wer_total": "127.885", "n_error": "90.61", "ppl": "42.59", "accuracy": "28.96", "wer": "70.853", "wps": "78", "ups": "0.61", "wpb": "127.9", "bsz": "8", "num_updates": "4600", "lr": "0.0002327", "gnorm": "1.974", "loss_scale": "512", "train_wall": "327", "gb_free": "7.1", "wall": "10043"}
[2024-06-15 03:44:51,684][train_inner][INFO] - {"epoch": 1, "update": 0.318, "loss": "5.426", "ntokens": "126.21", "acc_total": "126.21", "n_correct": "36.655", "wer_total": "126.21", "n_error": "89.27", "ppl": "42.99", "accuracy": "29.043", "wer": "70.731", "wps": "76.9", "ups": "0.61", "wpb": "126.2", "bsz": "8", "num_updates": "4800", "lr": "0.0002426", "gnorm": "2.073", "loss_scale": "512", "train_wall": "328", "gb_free": "7.1", "wall": "10371"}
[2024-06-15 03:50:19,993][train_inner][INFO] - {"epoch": 1, "update": 0.331, "loss": "5.367", "ntokens": "126.87", "acc_total": "126.87", "n_correct": "37.21", "wer_total": "126.87", "n_error": "89.44", "ppl": "41.27", "accuracy": "29.329", "wer": "70.497", "wps": "77.3", "ups": "0.61", "wpb": "126.9", "bsz": "8", "num_updates": "5000", "lr": "0.0002525", "gnorm": "2.106", "loss_scale": "512", "train_wall": "328", "gb_free": "7.1", "wall": "10699"}
[2024-06-15 03:50:19,993][fairseq_cli.train][INFO] - begin validation on "valid" subset
[2024-06-15 04:32:03,802][valid][INFO] - {"epoch": 1, "valid_loss": "5.233", "valid_ntokens": "18.1585", "valid_acc_total": "18.1585", "valid_n_correct": "5.49416", "valid_wer_total": "18.1585", "valid_n_error": "12.6286", "valid_ppl": "37.62", "valid_accuracy": "30.257", "valid_wer": "69.547", "valid_wps": "174", "valid_wpb": "18.2", "valid_bsz": "1", "valid_num_updates": "5000", "valid_best_accuracy": "30.257"}
[2024-06-15 04:32:03,803][fairseq.checkpoint_utils][INFO] - Preparing to save checkpoint for epoch 1 @ 5000 updates
[2024-06-15 04:32:03,803][fairseq.trainer][INFO] - Saving checkpoint to checkpoints/checkpoint_1_5000.pt
[2024-06-15 04:32:06,855][fairseq.trainer][INFO] - Finished saving checkpoint to checkpoints/checkpoint_1_5000.pt
[2024-06-15 04:32:10,884][fairseq.checkpoint_utils][INFO] - Saved checkpoint checkpoints/checkpoint_1_5000.pt (epoch 1 @ 5000 updates, score 30.257) (writing took 7.081204656002228 seconds)
[2024-06-15 04:37:38,555][train_inner][INFO] - {"epoch": 1, "update": 0.345, "loss": "5.211", "ntokens": "126.51", "acc_total": "126.51", "n_correct": "38.9", "wer_total": "126.51", "n_error": "87.38", "ppl": "37.05", "accuracy": "30.749", "wer": "69.07", "wps": "8.9", "ups": "0.07", "wpb": "126.5", "bsz": "8", "num_updates": "5200", "lr": "0.0002624", "gnorm": "2.145", "loss_scale": "512", "train_wall": "327", "gb_free": "7.1", "wall": "13538"}
[2024-06-15 04:43:06,135][train_inner][INFO] - {"epoch": 1, "update": 0.358, "loss": "5.241", "ntokens": "127.425", "acc_total": "127.425", "n_correct": "39.265", "wer_total": "127.425", "n_error": "87.925", "ppl": "37.82", "accuracy": "30.814", "wer": "69.001", "wps": "77.8", "ups": "0.61", "wpb": "127.4", "bsz": "8", "num_updates": "5400", "lr": "0.0002723", "gnorm": "2.165", "loss_scale": "512", "train_wall": "327", "gb_free": "7.1", "wall": "13865"}
[2024-06-15 04:48:34,257][train_inner][INFO] - {"epoch": 1, "update": 0.371, "loss": "5.172", "ntokens": "127.52", "acc_total": "127.52", "n_correct": "40.005", "wer_total": "127.52", "n_error": "87.32", "ppl": "36.05", "accuracy": "31.372", "wer": "68.476", "wps": "77.7", "ups": "0.61", "wpb": "127.5", "bsz": "8", "num_updates": "5600", "lr": "0.0002822", "gnorm": "2.246", "loss_scale": "512", "train_wall": "327", "gb_free": "7.1", "wall": "14193"}
[2024-06-15 04:54:02,100][train_inner][INFO] - {"epoch": 1, "update": 0.384, "loss": "5.259", "ntokens": "126.59", "acc_total": "126.59", "n_correct": "38.805", "wer_total": "126.59", "n_error": "87.57", "ppl": "38.29", "accuracy": "30.654", "wer": "69.176", "wps": "77.2", "ups": "0.61", "wpb": "126.6", "bsz": "8", "num_updates": "5800", "lr": "0.0002921", "gnorm": "2.254", "loss_scale": "512", "train_wall": "327", "gb_free": "7.1", "wall": "14521"}
[2024-06-15 04:59:29,936][train_inner][INFO] - {"epoch": 1, "update": 0.398, "loss": "5.138", "ntokens": "127.395", "acc_total": "127.395", "n_correct": "40.225", "wer_total": "127.395", "n_error": "86.99", "ppl": "35.2", "accuracy": "31.575", "wer": "68.284", "wps": "77.7", "ups": "0.61", "wpb": "127.4", "bsz": "8", "num_updates": "6000", "lr": "0.000302", "gnorm": "2.293", "loss_scale": "512", "train_wall": "327", "gb_free": "7.1", "wall": "14849"}
[2024-06-15 05:04:57,817][train_inner][INFO] - {"epoch": 1, "update": 0.411, "loss": "5.077", "ntokens": "126.995", "acc_total": "126.995", "n_correct": "40.72", "wer_total": "126.995", "n_error": "86.06", "ppl": "33.76", "accuracy": "32.064", "wer": "67.766", "wps": "77.5", "ups": "0.61", "wpb": "127", "bsz": "8", "num_updates": "6200", "lr": "0.0003119", "gnorm": "2.334", "loss_scale": "1024", "train_wall": "327", "gb_free": "7.1", "wall": "15177"}
[2024-06-15 05:10:25,543][train_inner][INFO] - {"epoch": 1, "update": 0.424, "loss": "5.079", "ntokens": "126.01", "acc_total": "126.01", "n_correct": "40.595", "wer_total": "126.01", "n_error": "85.16", "ppl": "33.8", "accuracy": "32.216", "wer": "67.582", "wps": "76.9", "ups": "0.61", "wpb": "126", "bsz": "8", "num_updates": "6400", "lr": "0.0003218", "gnorm": "2.416", "loss_scale": "1024", "train_wall": "327", "gb_free": "7.1", "wall": "15505"}
[2024-06-15 05:15:53,592][train_inner][INFO] - {"epoch": 1, "update": 0.437, "loss": "5.088", "ntokens": "126.33", "acc_total": "126.33", "n_correct": "40.64", "wer_total": "126.33", "n_error": "85.455", "ppl": "34.02", "accuracy": "32.17", "wer": "67.644", "wps": "77", "ups": "0.61", "wpb": "126.3", "bsz": "8", "num_updates": "6600", "lr": "0.0003317", "gnorm": "2.443", "loss_scale": "1024", "train_wall": "327", "gb_free": "7.1", "wall": "15833"}
[2024-06-15 05:21:21,694][train_inner][INFO] - {"epoch": 1, "update": 0.451, "loss": "5.004", "ntokens": "126.735", "acc_total": "126.735", "n_correct": "41.64", "wer_total": "126.735", "n_error": "84.865", "ppl": "32.09", "accuracy": "32.856", "wer": "66.963", "wps": "77.3", "ups": "0.61", "wpb": "126.7", "bsz": "8", "num_updates": "6800", "lr": "0.0003416", "gnorm": "2.415", "loss_scale": "1024", "train_wall": "327", "gb_free": "7.1", "wall": "16161"}
[2024-06-15 05:26:50,062][train_inner][INFO] - {"epoch": 1, "update": 0.464, "loss": "4.967", "ntokens": "126.98", "acc_total": "126.98", "n_correct": "42.295", "wer_total": "126.98", "n_error": "84.44", "ppl": "31.27", "accuracy": "33.308", "wer": "66.499", "wps": "77.3", "ups": "0.61", "wpb": "127", "bsz": "8", "num_updates": "7000", "lr": "0.0003515", "gnorm": "2.439", "loss_scale": "1024", "train_wall": "328", "gb_free": "7.1", "wall": "16489"}
[2024-06-15 05:32:17,794][train_inner][INFO] - {"epoch": 1, "update": 0.477, "loss": "5.046", "ntokens": "126.97", "acc_total": "126.97", "n_correct": "41.965", "wer_total": "126.97", "n_error": "84.74", "ppl": "33.03", "accuracy": "33.051", "wer": "66.74", "wps": "77.5", "ups": "0.61", "wpb": "127", "bsz": "8", "num_updates": "7200", "lr": "0.0003614", "gnorm": "2.468", "loss_scale": "1024", "train_wall": "327", "gb_free": "7.1", "wall": "16817"}
[2024-06-15 05:37:45,893][train_inner][INFO] - {"epoch": 1, "update": 0.491, "loss": "4.864", "ntokens": "127.45", "acc_total": "127.45", "n_correct": "43.48", "wer_total": "127.45", "n_error": "83.84", "ppl": "29.11", "accuracy": "34.115", "wer": "65.783", "wps": "77.7", "ups": "0.61", "wpb": "127.5", "bsz": "8", "num_updates": "7400", "lr": "0.0003713", "gnorm": "2.516", "loss_scale": "1024", "train_wall": "327", "gb_free": "7.1", "wall": "17145"}
[2024-06-15 05:40:29,805][fairseq_cli.train][INFO] - begin validation on "valid" subset
[2024-06-15 06:22:14,571][valid][INFO] - {"epoch": 1, "valid_loss": "4.745", "valid_ntokens": "18.1585", "valid_acc_total": "18.1585", "valid_n_correct": "6.38145", "valid_wer_total": "18.1585", "valid_n_error": "11.7444", "valid_ppl": "26.82", "valid_accuracy": "35.143", "valid_wer": "64.677", "valid_wps": "173.9", "valid_wpb": "18.2", "valid_bsz": "1", "valid_num_updates": "7500", "valid_best_accuracy": "35.143"}
[2024-06-15 06:22:14,572][fairseq.checkpoint_utils][INFO] - Preparing to save checkpoint for epoch 1 @ 7500 updates
[2024-06-15 06:22:14,572][fairseq.trainer][INFO] - Saving checkpoint to checkpoints/checkpoint_1_7500.pt
[2024-06-15 06:22:17,637][fairseq.trainer][INFO] - Finished saving checkpoint to checkpoints/checkpoint_1_7500.pt
[2024-06-15 06:22:22,127][fairseq.checkpoint_utils][INFO] - Saved checkpoint checkpoints/checkpoint_1_7500.pt (epoch 1 @ 7500 updates, score 35.143) (writing took 7.555394832001184 seconds)
[2024-06-15 06:25:05,820][train_inner][INFO] - {"epoch": 1, "update": 0.504, "loss": "4.928", "ntokens": "127.32", "acc_total": "127.32", "n_correct": "42.855", "wer_total": "127.32", "n_error": "84.285", "ppl": "30.44", "accuracy": "33.659", "wer": "66.199", "wps": "9", "ups": "0.07", "wpb": "127.3", "bsz": "8", "num_updates": "7600", "lr": "0.0003812", "gnorm": "2.522", "loss_scale": "1024", "train_wall": "327", "gb_free": "7.1", "wall": "19985"}
[2024-06-15 06:30:33,680][train_inner][INFO] - {"epoch": 1, "update": 0.517, "loss": "4.92", "ntokens": "127.11", "acc_total": "127.11", "n_correct": "42.74", "wer_total": "127.11", "n_error": "84.13", "ppl": "30.28", "accuracy": "33.624", "wer": "66.187", "wps": "77.5", "ups": "0.61", "wpb": "127.1", "bsz": "8", "num_updates": "7800", "lr": "0.0003911", "gnorm": "2.624", "loss_scale": "1024", "train_wall": "327", "gb_free": "7.1", "wall": "20313"}
[2024-06-15 06:36:00,672][train_inner][INFO] - {"epoch": 1, "update": 0.53, "loss": "4.876", "ntokens": "126.875", "acc_total": "126.875", "n_correct": "43.295", "wer_total": "126.875", "n_error": "83.335", "ppl": "29.36", "accuracy": "34.124", "wer": "65.683", "wps": "77.6", "ups": "0.61", "wpb": "126.9", "bsz": "8", "num_updates": "8000", "lr": "0.000401", "gnorm": "2.689", "loss_scale": "1024", "train_wall": "326", "gb_free": "7.1", "wall": "20640"}
[2024-06-15 06:41:28,018][train_inner][INFO] - {"epoch": 1, "update": 0.544, "loss": "4.824", "ntokens": "126.05", "acc_total": "126.05", "n_correct": "43.455", "wer_total": "126.05", "n_error": "82.415", "ppl": "28.33", "accuracy": "34.474", "wer": "65.383", "wps": "77", "ups": "0.61", "wpb": "126", "bsz": "8", "num_updates": "8200", "lr": "0.0004109", "gnorm": "2.749", "loss_scale": "2048", "train_wall": "327", "gb_free": "7.1", "wall": "20967"}
[2024-06-15 06:46:55,297][train_inner][INFO] - {"epoch": 1, "update": 0.557, "loss": "4.811", "ntokens": "126.785", "acc_total": "126.785", "n_correct": "44.405", "wer_total": "126.785", "n_error": "82.195", "ppl": "28.07", "accuracy": "35.024", "wer": "64.83", "wps": "77.5", "ups": "0.61", "wpb": "126.8", "bsz": "8", "num_updates": "8400", "lr": "0.0004208", "gnorm": "2.728", "loss_scale": "2048", "train_wall": "327", "gb_free": "7.1", "wall": "21294"}
[2024-06-15 06:52:22,803][train_inner][INFO] - {"epoch": 1, "update": 0.57, "loss": "4.802", "ntokens": "126.675", "acc_total": "126.675", "n_correct": "44.075", "wer_total": "126.675", "n_error": "82.47", "ppl": "27.89", "accuracy": "34.794", "wer": "65.104", "wps": "77.4", "ups": "0.61", "wpb": "126.7", "bsz": "8", "num_updates": "8600", "lr": "0.0004307", "gnorm": "2.78", "loss_scale": "2048", "train_wall": "327", "gb_free": "7.1", "wall": "21622"}
[2024-06-15 06:57:50,350][train_inner][INFO] - {"epoch": 1, "update": 0.583, "loss": "4.753", "ntokens": "127.09", "acc_total": "127.09", "n_correct": "45.335", "wer_total": "127.09", "n_error": "81.585", "ppl": "26.96", "accuracy": "35.672", "wer": "64.195", "wps": "77.6", "ups": "0.61", "wpb": "127.1", "bsz": "8", "num_updates": "8800", "lr": "0.0004406", "gnorm": "2.804", "loss_scale": "2048", "train_wall": "327", "gb_free": "7.1", "wall": "21949"}
[2024-06-15 07:03:17,610][train_inner][INFO] - {"epoch": 1, "update": 0.597, "loss": "4.738", "ntokens": "127.43", "acc_total": "127.43", "n_correct": "45.315", "wer_total": "127.43", "n_error": "81.94", "ppl": "26.68", "accuracy": "35.561", "wer": "64.302", "wps": "77.9", "ups": "0.61", "wpb": "127.4", "bsz": "8", "num_updates": "9000", "lr": "0.0004505", "gnorm": "2.828", "loss_scale": "2048", "train_wall": "327", "gb_free": "7.1", "wall": "22277"}
[2024-06-15 07:08:45,406][train_inner][INFO] - {"epoch": 1, "update": 0.61, "loss": "4.724", "ntokens": "127.145", "acc_total": "127.145", "n_correct": "45.305", "wer_total": "127.145", "n_error": "81.675", "ppl": "26.43", "accuracy": "35.633", "wer": "64.238", "wps": "77.6", "ups": "0.61", "wpb": "127.1", "bsz": "8", "num_updates": "9200", "lr": "0.0004604", "gnorm": "2.847", "loss_scale": "2048", "train_wall": "327", "gb_free": "7.1", "wall": "22605"}
[2024-06-15 07:14:13,843][train_inner][INFO] - {"epoch": 1, "update": 0.623, "loss": "4.756", "ntokens": "125.995", "acc_total": "125.995", "n_correct": "44.545", "wer_total": "125.995", "n_error": "81.32", "ppl": "27.02", "accuracy": "35.355", "wer": "64.542", "wps": "76.7", "ups": "0.61", "wpb": "126", "bsz": "8", "num_updates": "9400", "lr": "0.0004703", "gnorm": "2.896", "loss_scale": "2048", "train_wall": "328", "gb_free": "7.1", "wall": "22933"}
[2024-06-15 07:19:42,279][train_inner][INFO] - {"epoch": 1, "update": 0.636, "loss": "4.705", "ntokens": "126.87", "acc_total": "126.87", "n_correct": "45.44", "wer_total": "126.87", "n_error": "81.195", "ppl": "26.08", "accuracy": "35.816", "wer": "63.999", "wps": "77.3", "ups": "0.61", "wpb": "126.9", "bsz": "8", "num_updates": "9600", "lr": "0.0004802", "gnorm": "2.908", "loss_scale": "2048", "train_wall": "328", "gb_free": "7.1", "wall": "23261"}
[2024-06-15 07:25:10,873][train_inner][INFO] - {"epoch": 1, "update": 0.65, "loss": "4.664", "ntokens": "125.68", "acc_total": "125.68", "n_correct": "45.36", "wer_total": "125.68", "n_error": "80.145", "ppl": "25.36", "accuracy": "36.092", "wer": "63.769", "wps": "76.5", "ups": "0.61", "wpb": "125.7", "bsz": "8", "num_updates": "9800", "lr": "0.0004901", "gnorm": "2.981", "loss_scale": "2048", "train_wall": "328", "gb_free": "7.1", "wall": "23590"}
[2024-06-15 07:30:39,588][train_inner][INFO] - {"epoch": 1, "update": 0.663, "loss": "4.657", "ntokens": "127.56", "acc_total": "127.56", "n_correct": "46.315", "wer_total": "127.56", "n_error": "81.04", "ppl": "25.23", "accuracy": "36.308", "wer": "63.531", "wps": "77.6", "ups": "0.61", "wpb": "127.6", "bsz": "8", "num_updates": "10000", "lr": "0.0005", "gnorm": "2.947", "loss_scale": "2048", "train_wall": "328", "gb_free": "7.1", "wall": "23919"}
[2024-06-15 07:30:39,588][fairseq_cli.train][INFO] - begin validation on "valid" subset
[2024-06-15 08:12:27,401][valid][INFO] - {"epoch": 1, "valid_loss": "nan", "valid_ntokens": "18.1585", "valid_acc_total": "18.1585", "valid_n_correct": "6.78612", "valid_wer_total": "18.1585", "valid_n_error": "11.3423", "valid_ppl": "nan", "valid_accuracy": "37.372", "valid_wer": "62.463", "valid_wps": "173.7", "valid_wpb": "18.2", "valid_bsz": "1", "valid_num_updates": "10000", "valid_best_accuracy": "37.372"}
[2024-06-15 08:12:27,402][fairseq.checkpoint_utils][INFO] - Preparing to save checkpoint for epoch 1 @ 10000 updates
[2024-06-15 08:12:27,402][fairseq.trainer][INFO] - Saving checkpoint to checkpoints/checkpoint_1_10000.pt
[2024-06-15 08:12:30,492][fairseq.trainer][INFO] - Finished saving checkpoint to checkpoints/checkpoint_1_10000.pt
[2024-06-15 08:12:35,047][fairseq.checkpoint_utils][INFO] - Saved checkpoint checkpoints/checkpoint_1_10000.pt (epoch 1 @ 10000 updates, score 37.372) (writing took 7.64547687000595 seconds)
[2024-06-15 08:18:02,795][train_inner][INFO] - {"epoch": 1, "update": 0.676, "loss": "4.645", "ntokens": "126.605", "acc_total": "126.605", "n_correct": "45.85", "wer_total": "126.605", "n_error": "80.58", "ppl": "25.02", "accuracy": "36.215", "wer": "63.647", "wps": "8.9", "ups": "0.07", "wpb": "126.6", "bsz": "8", "num_updates": "10200", "lr": "0.000485243", "gnorm": "3.039", "loss_scale": "2048", "train_wall": "327", "gb_free": "7.1", "wall": "26762"}
[2024-06-15 08:23:31,088][train_inner][INFO] - {"epoch": 1, "update": 0.689, "loss": "4.622", "ntokens": "127.295", "acc_total": "127.295", "n_correct": "46.085", "wer_total": "127.295", "n_error": "81.06", "ppl": "24.63", "accuracy": "36.203", "wer": "63.679", "wps": "77.5", "ups": "0.61", "wpb": "127.3", "bsz": "8", "num_updates": "10400", "lr": "0.000470922", "gnorm": "2.937", "loss_scale": "4096", "train_wall": "328", "gb_free": "7.1", "wall": "27090"}
[2024-06-15 08:28:59,271][train_inner][INFO] - {"epoch": 1, "update": 0.703, "loss": "4.643", "ntokens": "127.73", "acc_total": "127.73", "n_correct": "46.63", "wer_total": "127.73", "n_error": "80.945", "ppl": "24.99", "accuracy": "36.507", "wer": "63.372", "wps": "77.8", "ups": "0.61", "wpb": "127.7", "bsz": "8", "num_updates": "10600", "lr": "0.000457024", "gnorm": "3.038", "loss_scale": "4096", "train_wall": "328", "gb_free": "7.1", "wall": "27418"}
[2024-06-15 08:33:43,250][fairseq.trainer][INFO] - NOTE: gradient overflow detected, ignoring gradient, setting loss scale to: 2048.0
[2024-06-15 08:34:29,263][train_inner][INFO] - {"epoch": 1, "update": 0.716, "loss": "4.582", "ntokens": "127.44", "acc_total": "127.44", "n_correct": "47.03", "wer_total": "127.44", "n_error": "80.25", "ppl": "23.95", "accuracy": "36.904", "wer": "62.971", "wps": "77.2", "ups": "0.61", "wpb": "127.4", "bsz": "8", "num_updates": "10800", "lr": "0.000443536", "gnorm": "3.134", "loss_scale": "2048", "train_wall": "329", "gb_free": "7.1", "wall": "27748"}
[2024-06-15 08:39:57,909][train_inner][INFO] - {"epoch": 1, "update": 0.729, "loss": "4.566", "ntokens": "126.09", "acc_total": "126.09", "n_correct": "46.735", "wer_total": "126.09", "n_error": "79.165", "ppl": "23.68", "accuracy": "37.065", "wer": "62.785", "wps": "76.7", "ups": "0.61", "wpb": "126.1", "bsz": "8", "num_updates": "11000", "lr": "0.000430446", "gnorm": "3.148", "loss_scale": "2048", "train_wall": "328", "gb_free": "7.1", "wall": "28077"}
[2024-06-15 08:45:26,093][train_inner][INFO] - {"epoch": 1, "update": 0.742, "loss": "4.472", "ntokens": "126.625", "acc_total": "126.625", "n_correct": "47.57", "wer_total": "126.625", "n_error": "78.885", "ppl": "22.19", "accuracy": "37.568", "wer": "62.298", "wps": "77.2", "ups": "0.61", "wpb": "126.6", "bsz": "8", "num_updates": "11200", "lr": "0.000417742", "gnorm": "3.088", "loss_scale": "2048", "train_wall": "328", "gb_free": "7.1", "wall": "28405"}
[2024-06-15 08:50:54,150][train_inner][INFO] - {"epoch": 1, "update": 0.756, "loss": "4.469", "ntokens": "125.82", "acc_total": "125.82", "n_correct": "48.31", "wer_total": "125.82", "n_error": "77.4", "ppl": "22.14", "accuracy": "38.396", "wer": "61.516", "wps": "76.7", "ups": "0.61", "wpb": "125.8", "bsz": "8", "num_updates": "11400", "lr": "0.000405413", "gnorm": "3.111", "loss_scale": "2048", "train_wall": "327", "gb_free": "7.1", "wall": "28733"}
[2024-06-15 08:56:22,194][train_inner][INFO] - {"epoch": 1, "update": 0.769, "loss": "4.457", "ntokens": "126.955", "acc_total": "126.955", "n_correct": "49.28", "wer_total": "126.955", "n_error": "77.545", "ppl": "21.96", "accuracy": "38.817", "wer": "61.081", "wps": "77.4", "ups": "0.61", "wpb": "127", "bsz": "8", "num_updates": "11600", "lr": "0.000393448", "gnorm": "3.091", "loss_scale": "2048", "train_wall": "327", "gb_free": "7.1", "wall": "29061"}
[2024-06-15 09:01:50,299][train_inner][INFO] - {"epoch": 1, "update": 0.782, "loss": "4.438", "ntokens": "126.705", "acc_total": "126.705", "n_correct": "49.115", "wer_total": "126.705", "n_error": "77.435", "ppl": "21.68", "accuracy": "38.763", "wer": "61.114", "wps": "77.2", "ups": "0.61", "wpb": "126.7", "bsz": "8", "num_updates": "11800", "lr": "0.000381836", "gnorm": "3.193", "loss_scale": "2048", "train_wall": "327", "gb_free": "7.1", "wall": "29389"}
[2024-06-15 09:07:18,644][train_inner][INFO] - {"epoch": 1, "update": 0.796, "loss": "4.405", "ntokens": "126.675", "acc_total": "126.675", "n_correct": "49.91", "wer_total": "126.675", "n_error": "76.635", "ppl": "21.18", "accuracy": "39.4", "wer": "60.497", "wps": "77.2", "ups": "0.61", "wpb": "126.7", "bsz": "8", "num_updates": "12000", "lr": "0.000370567", "gnorm": "3.159", "loss_scale": "2048", "train_wall": "328", "gb_free": "7.1", "wall": "29718"}
[2024-06-15 09:12:46,852][train_inner][INFO] - {"epoch": 1, "update": 0.809, "loss": "4.445", "ntokens": "126.855", "acc_total": "126.855", "n_correct": "48.58", "wer_total": "126.855", "n_error": "78.155", "ppl": "21.79", "accuracy": "38.296", "wer": "61.61", "wps": "77.3", "ups": "0.61", "wpb": "126.9", "bsz": "8", "num_updates": "12200", "lr": "0.000359631", "gnorm": "3.114", "loss_scale": "2048", "train_wall": "328", "gb_free": "7.1", "wall": "30046"}
[2024-06-15 09:18:15,100][train_inner][INFO] - {"epoch": 1, "update": 0.822, "loss": "4.335", "ntokens": "126.96", "acc_total": "126.96", "n_correct": "50.295", "wer_total": "126.96", "n_error": "76.545", "ppl": "20.18", "accuracy": "39.615", "wer": "60.291", "wps": "77.4", "ups": "0.61", "wpb": "127", "bsz": "8", "num_updates": "12400", "lr": "0.000349017", "gnorm": "3.303", "loss_scale": "2048", "train_wall": "328", "gb_free": "7.1", "wall": "30374"}
[2024-06-15 09:20:59,151][fairseq_cli.train][INFO] - begin validation on "valid" subset
[2024-06-15 10:02:49,198][valid][INFO] - {"epoch": 1, "valid_loss": "4.157", "valid_ntokens": "18.1585", "valid_acc_total": "18.1585", "valid_n_correct": "7.54602", "valid_wer_total": "18.1585", "valid_n_error": "10.5966", "valid_ppl": "17.84", "valid_accuracy": "41.556", "valid_wer": "58.356", "valid_wps": "173.6", "valid_wpb": "18.2", "valid_bsz": "1", "valid_num_updates": "12500", "valid_best_accuracy": "41.556"}
[2024-06-15 10:02:49,198][fairseq.checkpoint_utils][INFO] - Preparing to save checkpoint for epoch 1 @ 12500 updates
[2024-06-15 10:02:49,199][fairseq.trainer][INFO] - Saving checkpoint to checkpoints/checkpoint_1_12500.pt
[2024-06-15 10:02:52,296][fairseq.trainer][INFO] - Finished saving checkpoint to checkpoints/checkpoint_1_12500.pt
[2024-06-15 10:02:56,900][fairseq.checkpoint_utils][INFO] - Saved checkpoint checkpoints/checkpoint_1_12500.pt (epoch 1 @ 12500 updates, score 41.556) (writing took 7.702132188001997 seconds)
[2024-06-15 10:05:41,050][train_inner][INFO] - {"epoch": 1, "update": 0.835, "loss": "4.299", "ntokens": "126.58", "acc_total": "126.58", "n_correct": "50.21", "wer_total": "126.58", "n_error": "76.16", "ppl": "19.68", "accuracy": "39.667", "wer": "60.167", "wps": "8.9", "ups": "0.07", "wpb": "126.6", "bsz": "8", "num_updates": "12600", "lr": "0.000338716", "gnorm": "3.18", "loss_scale": "2048", "train_wall": "327", "gb_free": "7.1", "wall": "33220"}
[2024-06-15 10:11:09,864][train_inner][INFO] - {"epoch": 1, "update": 0.849, "loss": "4.263", "ntokens": "127.335", "acc_total": "127.335", "n_correct": "51.71", "wer_total": "127.335", "n_error": "75.485", "ppl": "19.19", "accuracy": "40.609", "wer": "59.281", "wps": "77.5", "ups": "0.61", "wpb": "127.3", "bsz": "8", "num_updates": "12800", "lr": "0.00032872", "gnorm": "3.097", "loss_scale": "2048", "train_wall": "328", "gb_free": "7.1", "wall": "33549"}
[2024-06-15 10:16:38,835][train_inner][INFO] - {"epoch": 1, "update": 0.862, "loss": "4.286", "ntokens": "125.99", "acc_total": "125.99", "n_correct": "50.86", "wer_total": "125.99", "n_error": "74.965", "ppl": "19.51", "accuracy": "40.368", "wer": "59.501", "wps": "76.6", "ups": "0.61", "wpb": "126", "bsz": "8", "num_updates": "13000", "lr": "0.000319018", "gnorm": "3.164", "loss_scale": "4096", "train_wall": "328", "gb_free": "7.1", "wall": "33878"}
[2024-06-15 10:22:07,667][train_inner][INFO] - {"epoch": 1, "update": 0.875, "loss": "4.294", "ntokens": "126.805", "acc_total": "126.805", "n_correct": "51.445", "wer_total": "126.805", "n_error": "75.255", "ppl": "19.61", "accuracy": "40.57", "wer": "59.347", "wps": "77.1", "ups": "0.61", "wpb": "126.8", "bsz": "8", "num_updates": "13200", "lr": "0.000309603", "gnorm": "3.153", "loss_scale": "4096", "train_wall": "328", "gb_free": "7.1", "wall": "34207"}
[2024-06-15 10:27:36,369][train_inner][INFO] - {"epoch": 1, "update": 0.888, "loss": "4.285", "ntokens": "127.435", "acc_total": "127.435", "n_correct": "51.365", "wer_total": "127.435", "n_error": "75.88", "ppl": "19.5", "accuracy": "40.307", "wer": "59.544", "wps": "77.5", "ups": "0.61", "wpb": "127.4", "bsz": "8", "num_updates": "13400", "lr": "0.000300466", "gnorm": "3.203", "loss_scale": "4096", "train_wall": "328", "gb_free": "7.1", "wall": "34535"}
[2024-06-15 10:33:05,101][train_inner][INFO] - {"epoch": 1, "update": 0.902, "loss": "4.187", "ntokens": "127.015", "acc_total": "127.015", "n_correct": "51.92", "wer_total": "127.015", "n_error": "74.94", "ppl": "18.22", "accuracy": "40.877", "wer": "59.001", "wps": "77.3", "ups": "0.61", "wpb": "127", "bsz": "8", "num_updates": "13600", "lr": "0.000291598", "gnorm": "3.184", "loss_scale": "4096", "train_wall": "328", "gb_free": "7.1", "wall": "34864"}
[2024-06-15 10:38:33,858][train_inner][INFO] - {"epoch": 1, "update": 0.915, "loss": "4.136", "ntokens": "126.965", "acc_total": "126.965", "n_correct": "52.4", "wer_total": "126.965", "n_error": "74.45", "ppl": "17.59", "accuracy": "41.271", "wer": "58.638", "wps": "77.2", "ups": "0.61", "wpb": "127", "bsz": "8", "num_updates": "13800", "lr": "0.000282992", "gnorm": "3.112", "loss_scale": "4096", "train_wall": "328", "gb_free": "7.1", "wall": "35193"}
[2024-06-15 10:44:02,817][train_inner][INFO] - {"epoch": 1, "update": 0.928, "loss": "4.194", "ntokens": "127.145", "acc_total": "127.145", "n_correct": "52.18", "wer_total": "127.145", "n_error": "74.86", "ppl": "18.31", "accuracy": "41.04", "wer": "58.878", "wps": "77.3", "ups": "0.61", "wpb": "127.1", "bsz": "8", "num_updates": "14000", "lr": "0.00027464", "gnorm": "3.171", "loss_scale": "4096", "train_wall": "328", "gb_free": "7.1", "wall": "35522"}
[2024-06-15 10:49:31,903][train_inner][INFO] - {"epoch": 1, "update": 0.941, "loss": "4.123", "ntokens": "125.985", "acc_total": "125.985", "n_correct": "52.37", "wer_total": "125.985", "n_error": "73.455", "ppl": "17.43", "accuracy": "41.568", "wer": "58.305", "wps": "76.6", "ups": "0.61", "wpb": "126", "bsz": "8", "num_updates": "14200", "lr": "0.000266535", "gnorm": "3.163", "loss_scale": "4096", "train_wall": "328", "gb_free": "7.1", "wall": "35851"}
[2024-06-15 10:55:01,055][train_inner][INFO] - {"epoch": 1, "update": 0.955, "loss": "4.159", "ntokens": "126.93", "acc_total": "126.93", "n_correct": "52.635", "wer_total": "126.93", "n_error": "74.17", "ppl": "17.87", "accuracy": "41.468", "wer": "58.434", "wps": "77.1", "ups": "0.61", "wpb": "126.9", "bsz": "8", "num_updates": "14400", "lr": "0.000258668", "gnorm": "3.167", "loss_scale": "4096", "train_wall": "328", "gb_free": "7.1", "wall": "36180"}
[2024-06-15 11:00:30,248][train_inner][INFO] - {"epoch": 1, "update": 0.968, "loss": "4.072", "ntokens": "127.5", "acc_total": "127.5", "n_correct": "53.815", "wer_total": "127.5", "n_error": "73.54", "ppl": "16.82", "accuracy": "42.208", "wer": "57.678", "wps": "77.5", "ups": "0.61", "wpb": "127.5", "bsz": "8", "num_updates": "14600", "lr": "0.000251034", "gnorm": "3.16", "loss_scale": "4096", "train_wall": "329", "gb_free": "7.1", "wall": "36509"}
[2024-06-15 11:05:59,133][train_inner][INFO] - {"epoch": 1, "update": 0.981, "loss": "4.135", "ntokens": "127.32", "acc_total": "127.32", "n_correct": "53.82", "wer_total": "127.32", "n_error": "73.335", "ppl": "17.57", "accuracy": "42.271", "wer": "57.599", "wps": "77.4", "ups": "0.61", "wpb": "127.3", "bsz": "8", "num_updates": "14800", "lr": "0.000243626", "gnorm": "3.076", "loss_scale": "4096", "train_wall": "328", "gb_free": "7.1", "wall": "36838"}
[2024-06-15 11:07:54,203][fairseq.trainer][INFO] - NOTE: gradient overflow detected, ignoring gradient, setting loss scale to: 4096.0
[2024-06-15 11:11:29,547][train_inner][INFO] - {"epoch": 1, "update": 0.994, "loss": "4.106", "ntokens": "127.335", "acc_total": "127.335", "n_correct": "53.96", "wer_total": "127.335", "n_error": "73.26", "ppl": "17.21", "accuracy": "42.376", "wer": "57.533", "wps": "77.1", "ups": "0.61", "wpb": "127.3", "bsz": "8", "num_updates": "15000", "lr": "0.000236435", "gnorm": "3.198", "loss_scale": "4096", "train_wall": "330", "gb_free": "7.1", "wall": "37169"}
[2024-06-15 11:11:29,548][fairseq_cli.train][INFO] - begin validation on "valid" subset
[2024-06-15 11:53:19,331][valid][INFO] - {"epoch": 1, "valid_loss": "3.869", "valid_ntokens": "18.1585", "valid_acc_total": "18.1585", "valid_n_correct": "8.30025", "valid_wer_total": "18.1585", "valid_n_error": "9.84531", "valid_ppl": "14.61", "valid_accuracy": "45.71", "valid_wer": "54.219", "valid_wps": "173.6", "valid_wpb": "18.2", "valid_bsz": "1", "valid_num_updates": "15000", "valid_best_accuracy": "45.71"}
[2024-06-15 11:53:19,332][fairseq.checkpoint_utils][INFO] - Preparing to save checkpoint for epoch 1 @ 15000 updates
[2024-06-15 11:53:19,332][fairseq.trainer][INFO] - Saving checkpoint to checkpoints/checkpoint_1_15000.pt
[2024-06-15 11:53:22,475][fairseq.trainer][INFO] - Finished saving checkpoint to checkpoints/checkpoint_1_15000.pt
[2024-06-15 11:53:27,056][fairseq.checkpoint_utils][INFO] - Saved checkpoint checkpoints/checkpoint_1_15000.pt (epoch 1 @ 15000 updates, score 45.71) (writing took 7.724081863998435 seconds)
[2024-06-15 11:55:44,650][fairseq_cli.train][INFO] - begin validation on "valid" subset
[2024-06-15 12:37:40,852][valid][INFO] - {"epoch": 1, "valid_loss": "3.934", "valid_ntokens": "18.1585", "valid_acc_total": "18.1585", "valid_n_correct": "8.07703", "valid_wer_total": "18.1585", "valid_n_error": "10.0708", "valid_ppl": "15.29", "valid_accuracy": "44.481", "valid_wer": "55.461", "valid_wps": "173.1", "valid_wpb": "18.2", "valid_bsz": "1", "valid_num_updates": "15084", "valid_best_accuracy": "45.71"}
[2024-06-15 12:37:40,853][fairseq.checkpoint_utils][INFO] - Preparing to save checkpoint for epoch 1 @ 15084 updates
[2024-06-15 12:37:40,854][fairseq.trainer][INFO] - Saving checkpoint to checkpoints/checkpoint_last.pt
[2024-06-15 12:37:44,845][fairseq.trainer][INFO] - Finished saving checkpoint to checkpoints/checkpoint_last.pt
[2024-06-15 12:37:44,927][fairseq.checkpoint_utils][INFO] - Saved checkpoint checkpoints/checkpoint_last.pt (epoch 1 @ 15084 updates, score 44.481) (writing took 4.0730797330033965 seconds)
[2024-06-15 12:37:44,927][fairseq_cli.train][INFO] - end of epoch 1 (average epoch stats below)
[2024-06-15 12:37:44,974][train][INFO] - {"epoch": 1, "train_loss": "5.024", "train_ntokens": "126.898", "train_acc_total": "126.898", "train_n_correct": "41.6332", "train_wer_total": "126.898", "train_n_error": "85.0752", "train_ppl": "32.53", "train_accuracy": "32.808", "train_wer": "67.042", "train_wps": "45.2", "train_ups": "0.36", "train_wpb": "126.9", "train_bsz": "8", "train_num_updates": "15084", "train_lr": "0.000233479", "train_gnorm": "2.791", "train_loss_scale": "4096", "train_train_wall": "24685", "train_gb_free": "7.1", "train_wall": "42344"}
[2024-06-15 12:37:45,036][fairseq.trainer][INFO] - begin training epoch 2
[2024-06-15 12:37:45,036][fairseq_cli.train][INFO] - Start iterating over samples
[2024-06-15 12:40:56,327][train_inner][INFO] - {"epoch": 2, "update": 1.008, "loss": "3.989", "ntokens": "127.05", "acc_total": "127.05", "n_correct": "55.155", "wer_total": "127.05", "n_error": "71.745", "ppl": "15.88", "accuracy": "43.412", "wer": "56.47", "wps": "4.7", "ups": "0.04", "wpb": "127", "bsz": "8", "num_updates": "15200", "lr": "0.000229457", "gnorm": "3.173", "loss_scale": "4096", "train_wall": "328", "gb_free": "7.1", "wall": "42535"}
[2024-06-15 12:46:26,336][train_inner][INFO] - {"epoch": 2, "update": 1.021, "loss": "3.916", "ntokens": "126.32", "acc_total": "126.32", "n_correct": "55.42", "wer_total": "126.32", "n_error": "70.775", "ppl": "15.09", "accuracy": "43.873", "wer": "56.028", "wps": "76.6", "ups": "0.61", "wpb": "126.3", "bsz": "8", "num_updates": "15400", "lr": "0.000222685", "gnorm": "3.188", "loss_scale": "4096", "train_wall": "329", "gb_free": "7.1", "wall": "42865"}
[2024-06-15 12:49:36,050][fairseq.trainer][INFO] - NOTE: gradient overflow detected, ignoring gradient, setting loss scale to: 2048.0
[2024-06-15 12:51:57,888][train_inner][INFO] - {"epoch": 2, "update": 1.034, "loss": "3.852", "ntokens": "126.99", "acc_total": "126.99", "n_correct": "56.285", "wer_total": "126.99", "n_error": "70.59", "ppl": "14.44", "accuracy": "44.322", "wer": "55.587", "wps": "76.6", "ups": "0.6", "wpb": "127", "bsz": "8", "num_updates": "15600", "lr": "0.000216113", "gnorm": "3.202", "loss_scale": "2048", "train_wall": "331", "gb_free": "7.1", "wall": "43197"}
[2024-06-15 12:57:27,900][train_inner][INFO] - {"epoch": 2, "update": 1.048, "loss": "3.939", "ntokens": "125.545", "acc_total": "125.545", "n_correct": "55.04", "wer_total": "125.545", "n_error": "70.435", "ppl": "15.34", "accuracy": "43.841", "wer": "56.103", "wps": "76.1", "ups": "0.61", "wpb": "125.5", "bsz": "8", "num_updates": "15800", "lr": "0.000209735", "gnorm": "3.164", "loss_scale": "2048", "train_wall": "329", "gb_free": "7.1", "wall": "43527"}
[2024-06-15 13:02:58,399][train_inner][INFO] - {"epoch": 2, "update": 1.061, "loss": "3.912", "ntokens": "127.405", "acc_total": "127.405", "n_correct": "55.825", "wer_total": "127.405", "n_error": "71.48", "ppl": "15.05", "accuracy": "43.817", "wer": "56.105", "wps": "77.1", "ups": "0.61", "wpb": "127.4", "bsz": "8", "num_updates": "16000", "lr": "0.000203545", "gnorm": "3.117", "loss_scale": "2048", "train_wall": "330", "gb_free": "7.1", "wall": "43857"}
[2024-06-15 13:08:28,729][train_inner][INFO] - {"epoch": 2, "update": 1.074, "loss": "3.792", "ntokens": "126.915", "acc_total": "126.915", "n_correct": "57.17", "wer_total": "126.915", "n_error": "69.665", "ppl": "13.86", "accuracy": "45.046", "wer": "54.891", "wps": "76.8", "ups": "0.61", "wpb": "126.9", "bsz": "8", "num_updates": "16200", "lr": "0.000197538", "gnorm": "3.212", "loss_scale": "2048", "train_wall": "330", "gb_free": "7.1", "wall": "44188"}
[2024-06-15 13:13:58,953][train_inner][INFO] - {"epoch": 2, "update": 1.087, "loss": "3.824", "ntokens": "127.14", "acc_total": "127.14", "n_correct": "57.16", "wer_total": "127.14", "n_error": "69.875", "ppl": "14.16", "accuracy": "44.958", "wer": "54.959", "wps": "77", "ups": "0.61", "wpb": "127.1", "bsz": "8", "num_updates": "16400", "lr": "0.000191708", "gnorm": "3.17", "loss_scale": "2048", "train_wall": "330", "gb_free": "7.1", "wall": "44518"}
[2024-06-15 13:19:29,290][train_inner][INFO] - {"epoch": 2, "update": 1.101, "loss": "3.815", "ntokens": "127.51", "acc_total": "127.51", "n_correct": "56.95", "wer_total": "127.51", "n_error": "70.48", "ppl": "14.08", "accuracy": "44.663", "wer": "55.274", "wps": "77.2", "ups": "0.61", "wpb": "127.5", "bsz": "8", "num_updates": "16600", "lr": "0.00018605", "gnorm": "3.267", "loss_scale": "2048", "train_wall": "330", "gb_free": "7.1", "wall": "44848"}
[2024-06-15 13:24:59,424][train_inner][INFO] - {"epoch": 2, "update": 1.114, "loss": "3.866", "ntokens": "126.405", "acc_total": "126.405", "n_correct": "56.575", "wer_total": "126.405", "n_error": "69.705", "ppl": "14.58", "accuracy": "44.757", "wer": "55.144", "wps": "76.6", "ups": "0.61", "wpb": "126.4", "bsz": "8", "num_updates": "16800", "lr": "0.000180559", "gnorm": "3.169", "loss_scale": "2048", "train_wall": "329", "gb_free": "7.1", "wall": "45179"}
[2024-06-15 13:30:30,077][train_inner][INFO] - {"epoch": 2, "update": 1.127, "loss": "3.777", "ntokens": "127.925", "acc_total": "127.925", "n_correct": "57.855", "wer_total": "127.925", "n_error": "69.93", "ppl": "13.71", "accuracy": "45.226", "wer": "54.665", "wps": "77.4", "ups": "0.6", "wpb": "127.9", "bsz": "8", "num_updates": "17000", "lr": "0.00017523", "gnorm": "3.094", "loss_scale": "2048", "train_wall": "330", "gb_free": "7.1", "wall": "45509"}
[2024-06-15 13:36:00,474][train_inner][INFO] - {"epoch": 2, "update": 1.14, "loss": "3.799", "ntokens": "126.125", "acc_total": "126.125", "n_correct": "56.745", "wer_total": "126.125", "n_error": "69.26", "ppl": "13.92", "accuracy": "44.991", "wer": "54.914", "wps": "76.3", "ups": "0.61", "wpb": "126.1", "bsz": "8", "num_updates": "17200", "lr": "0.000170059", "gnorm": "3.071", "loss_scale": "2048", "train_wall": "330", "gb_free": "7.1", "wall": "45840"}
[2024-06-15 13:41:30,986][train_inner][INFO] - {"epoch": 2, "update": 1.154, "loss": "3.836", "ntokens": "127.245", "acc_total": "127.245", "n_correct": "56.795", "wer_total": "127.245", "n_error": "70.305", "ppl": "14.28", "accuracy": "44.634", "wer": "55.252", "wps": "77", "ups": "0.61", "wpb": "127.2", "bsz": "8", "num_updates": "17400", "lr": "0.00016504", "gnorm": "3.196", "loss_scale": "2048", "train_wall": "330", "gb_free": "7.1", "wall": "46170"}
[2024-06-15 13:44:16,283][fairseq_cli.train][INFO] - begin validation on "valid" subset
[2024-06-15 14:26:22,025][valid][INFO] - {"epoch": 2, "valid_loss": "3.71", "valid_ntokens": "18.1585", "valid_acc_total": "18.1585", "valid_n_correct": "8.39466", "valid_wer_total": "18.1585", "valid_n_error": "9.75169", "valid_ppl": "13.09", "valid_accuracy": "46.23", "valid_wer": "53.703", "valid_wps": "172.5", "valid_wpb": "18.2", "valid_bsz": "1", "valid_num_updates": "17500", "valid_best_accuracy": "46.23"}
[2024-06-15 14:26:22,026][fairseq.checkpoint_utils][INFO] - Preparing to save checkpoint for epoch 2 @ 17500 updates
[2024-06-15 14:26:22,026][fairseq.trainer][INFO] - Saving checkpoint to checkpoints/checkpoint_2_17500.pt
[2024-06-15 14:26:25,119][fairseq.trainer][INFO] - Finished saving checkpoint to checkpoints/checkpoint_2_17500.pt
[2024-06-15 14:26:29,631][fairseq.checkpoint_utils][INFO] - Saved checkpoint checkpoints/checkpoint_2_17500.pt (epoch 2 @ 17500 updates, score 46.23) (writing took 7.605056370986858 seconds)
[2024-06-15 14:29:14,647][train_inner][INFO] - {"epoch": 2, "update": 1.167, "loss": "3.825", "ntokens": "126.2", "acc_total": "126.2", "n_correct": "56.37", "wer_total": "126.2", "n_error": "69.715", "ppl": "14.17", "accuracy": "44.667", "wer": "55.242", "wps": "8.8", "ups": "0.07", "wpb": "126.2", "bsz": "8", "num_updates": "17600", "lr": "0.000160169", "gnorm": "3.168", "loss_scale": "4096", "train_wall": "330", "gb_free": "7.1", "wall": "49034"}
[2024-06-15 14:34:45,124][train_inner][INFO] - {"epoch": 2, "update": 1.18, "loss": "3.708", "ntokens": "128.29", "acc_total": "128.29", "n_correct": "58.2", "wer_total": "128.29", "n_error": "69.975", "ppl": "13.07", "accuracy": "45.366", "wer": "54.544", "wps": "77.6", "ups": "0.61", "wpb": "128.3", "bsz": "8", "num_updates": "17800", "lr": "0.000155442", "gnorm": "3.116", "loss_scale": "4096", "train_wall": "330", "gb_free": "7.1", "wall": "49364"}
[2024-06-15 14:40:15,790][train_inner][INFO] - {"epoch": 2, "update": 1.193, "loss": "3.778", "ntokens": "126.235", "acc_total": "126.235", "n_correct": "57.005", "wer_total": "126.235", "n_error": "69.12", "ppl": "13.71", "accuracy": "45.158", "wer": "54.755", "wps": "76.4", "ups": "0.6", "wpb": "126.2", "bsz": "8", "num_updates": "18000", "lr": "0.000150854", "gnorm": "3.134", "loss_scale": "4096", "train_wall": "330", "gb_free": "7.1", "wall": "49695"}
[2024-06-15 14:40:43,494][fairseq.trainer][INFO] - NOTE: gradient overflow detected, ignoring gradient, setting loss scale to: 2048.0
[2024-06-15 14:46:24,845][train_inner][INFO] - {"epoch": 2, "update": 1.207, "loss": "3.704", "ntokens": "127.64", "acc_total": "127.64", "n_correct": "59.155", "wer_total": "127.64", "n_error": "68.36", "ppl": "13.03", "accuracy": "46.345", "wer": "53.557", "wps": "69.2", "ups": "0.54", "wpb": "127.6", "bsz": "8", "num_updates": "18200", "lr": "0.000146402", "gnorm": "4.037", "loss_scale": "2048", "train_wall": "368", "gb_free": "6.5", "wall": "50064"}
[2024-06-15 14:52:31,650][train_inner][INFO] - {"epoch": 2, "update": 1.22, "loss": "3.596", "ntokens": "126.27", "acc_total": "126.27", "n_correct": "60.195", "wer_total": "126.27", "n_error": "65.985", "ppl": "12.09", "accuracy": "47.672", "wer": "52.257", "wps": "68.8", "ups": "0.55", "wpb": "126.3", "bsz": "8", "num_updates": "18400", "lr": "0.000142081", "gnorm": "4", "loss_scale": "2048", "train_wall": "366", "gb_free": "6.5", "wall": "50431"}
[2024-06-15 14:58:38,777][train_inner][INFO] - {"epoch": 2, "update": 1.233, "loss": "3.618", "ntokens": "126.87", "acc_total": "126.87", "n_correct": "60.02", "wer_total": "126.87", "n_error": "66.725", "ppl": "12.28", "accuracy": "47.308", "wer": "52.593", "wps": "69.1", "ups": "0.54", "wpb": "126.9", "bsz": "8", "num_updates": "18600", "lr": "0.000137888", "gnorm": "3.911", "loss_scale": "2048", "train_wall": "366", "gb_free": "6.5", "wall": "50798"}
[2024-06-15 15:04:45,951][train_inner][INFO] - {"epoch": 2, "update": 1.246, "loss": "3.585", "ntokens": "127.155", "acc_total": "127.155", "n_correct": "60.365", "wer_total": "127.155", "n_error": "66.69", "ppl": "12", "accuracy": "47.474", "wer": "52.448", "wps": "69.3", "ups": "0.54", "wpb": "127.2", "bsz": "8", "num_updates": "18800", "lr": "0.000133819", "gnorm": "3.882", "loss_scale": "2048", "train_wall": "366", "gb_free": "6.5", "wall": "51165"}
[2024-06-15 15:05:51,881][fairseq.trainer][INFO] - NOTE: gradient overflow detected, ignoring gradient, setting loss scale to: 1024.0
[2024-06-15 15:10:55,054][train_inner][INFO] - {"epoch": 2, "update": 1.26, "loss": "3.486", "ntokens": "127.67", "acc_total": "127.67", "n_correct": "61.87", "wer_total": "127.67", "n_error": "65.705", "ppl": "11.2", "accuracy": "48.461", "wer": "51.465", "wps": "69.2", "ups": "0.54", "wpb": "127.7", "bsz": "8", "num_updates": "19000", "lr": "0.000129869", "gnorm": "3.796", "loss_scale": "1024", "train_wall": "368", "gb_free": "6.5", "wall": "51534"}
[2024-06-15 15:17:02,719][train_inner][INFO] - {"epoch": 2, "update": 1.273, "loss": "3.551", "ntokens": "127.085", "acc_total": "127.085", "n_correct": "61.405", "wer_total": "127.085", "n_error": "65.595", "ppl": "11.72", "accuracy": "48.318", "wer": "51.615", "wps": "69.1", "ups": "0.54", "wpb": "127.1", "bsz": "8", "num_updates": "19200", "lr": "0.000126036", "gnorm": "3.852", "loss_scale": "1024", "train_wall": "367", "gb_free": "6.5", "wall": "51902"}
[2024-06-15 15:23:10,172][train_inner][INFO] - {"epoch": 2, "update": 1.286, "loss": "3.416", "ntokens": "125.85", "acc_total": "125.85", "n_correct": "62.16", "wer_total": "125.85", "n_error": "63.565", "ppl": "10.67", "accuracy": "49.392", "wer": "50.509", "wps": "68.5", "ups": "0.54", "wpb": "125.8", "bsz": "8", "num_updates": "19400", "lr": "0.000122317", "gnorm": "3.839", "loss_scale": "1024", "train_wall": "367", "gb_free": "6.5", "wall": "52269"}
[2024-06-15 15:29:17,336][train_inner][INFO] - {"epoch": 2, "update": 1.3, "loss": "3.403", "ntokens": "125.665", "acc_total": "125.665", "n_correct": "62.6", "wer_total": "125.665", "n_error": "62.995", "ppl": "10.58", "accuracy": "49.815", "wer": "50.129", "wps": "68.5", "ups": "0.54", "wpb": "125.7", "bsz": "8", "num_updates": "19600", "lr": "0.000118707", "gnorm": "3.905", "loss_scale": "1024", "train_wall": "366", "gb_free": "6.5", "wall": "52636"}
[2024-06-15 15:35:24,299][train_inner][INFO] - {"epoch": 2, "update": 1.313, "loss": "3.369", "ntokens": "127.615", "acc_total": "127.615", "n_correct": "63.715", "wer_total": "127.615", "n_error": "63.77", "ppl": "10.33", "accuracy": "49.928", "wer": "49.971", "wps": "69.6", "ups": "0.55", "wpb": "127.6", "bsz": "8", "num_updates": "19800", "lr": "0.000115203", "gnorm": "3.849", "loss_scale": "1024", "train_wall": "366", "gb_free": "6.5", "wall": "53003"}
[2024-06-15 15:41:31,714][train_inner][INFO] - {"epoch": 2, "update": 1.326, "loss": "3.41", "ntokens": "126.165", "acc_total": "126.165", "n_correct": "63.24", "wer_total": "126.165", "n_error": "62.86", "ppl": "10.63", "accuracy": "50.125", "wer": "49.824", "wps": "68.7", "ups": "0.54", "wpb": "126.2", "bsz": "8", "num_updates": "20000", "lr": "0.000111803", "gnorm": "3.831", "loss_scale": "1024", "train_wall": "367", "gb_free": "6.5", "wall": "53371"}
[2024-06-15 15:41:31,715][fairseq_cli.train][INFO] - begin validation on "valid" subset
[2024-06-15 16:23:36,861][valid][INFO] - {"epoch": 2, "valid_loss": "3.303", "valid_ntokens": "18.1585", "valid_acc_total": "18.1585", "valid_n_correct": "9.36219", "valid_wer_total": "18.1585", "valid_n_error": "8.78666", "valid_ppl": "9.87", "valid_accuracy": "51.558", "valid_wer": "48.389", "valid_wps": "172.5", "valid_wpb": "18.2", "valid_bsz": "1", "valid_num_updates": "20000", "valid_best_accuracy": "51.558"}
[2024-06-15 16:23:36,862][fairseq.checkpoint_utils][INFO] - Preparing to save checkpoint for epoch 2 @ 20000 updates
[2024-06-15 16:23:36,862][fairseq.trainer][INFO] - Saving checkpoint to checkpoints/checkpoint_2_20000.pt
[2024-06-15 16:23:39,976][fairseq.trainer][INFO] - Finished saving checkpoint to checkpoints/checkpoint_2_20000.pt
[2024-06-15 16:23:44,513][fairseq.checkpoint_utils][INFO] - Saved checkpoint checkpoints/checkpoint_2_20000.pt (epoch 2 @ 20000 updates, score 51.558) (writing took 7.6514022090123035 seconds)
[2024-06-15 16:29:51,067][train_inner][INFO] - {"epoch": 2, "update": 1.339, "loss": "3.417", "ntokens": "126.37", "acc_total": "126.37", "n_correct": "63.25", "wer_total": "126.37", "n_error": "63.01", "ppl": "10.68", "accuracy": "50.051", "wer": "49.862", "wps": "8.7", "ups": "0.07", "wpb": "126.4", "bsz": "8", "num_updates": "20200", "lr": "0.000108504", "gnorm": "3.781", "loss_scale": "1024", "train_wall": "366", "gb_free": "6.5", "wall": "56270"}
[2024-06-15 16:35:57,981][train_inner][INFO] - {"epoch": 2, "update": 1.353, "loss": "3.456", "ntokens": "127.095", "acc_total": "127.095", "n_correct": "63.395", "wer_total": "127.095", "n_error": "63.635", "ppl": "10.98", "accuracy": "49.88", "wer": "50.069", "wps": "69.3", "ups": "0.55", "wpb": "127.1", "bsz": "8", "num_updates": "20400", "lr": "0.000105301", "gnorm": "3.821", "loss_scale": "1024", "train_wall": "366", "gb_free": "6.5", "wall": "56637"}
[2024-06-15 16:42:04,351][train_inner][INFO] - {"epoch": 2, "update": 1.366, "loss": "3.345", "ntokens": "126.5", "acc_total": "126.5", "n_correct": "64.715", "wer_total": "126.5", "n_error": "61.725", "ppl": "10.16", "accuracy": "51.158", "wer": "48.794", "wps": "69.1", "ups": "0.55", "wpb": "126.5", "bsz": "8", "num_updates": "20600", "lr": "0.000102194", "gnorm": "3.739", "loss_scale": "1024", "train_wall": "366", "gb_free": "6.5", "wall": "57003"}
[2024-06-15 16:48:11,054][train_inner][INFO] - {"epoch": 2, "update": 1.379, "loss": "3.321", "ntokens": "127.265", "acc_total": "127.265", "n_correct": "65.52", "wer_total": "127.265", "n_error": "61.65", "ppl": "10", "accuracy": "51.483", "wer": "48.442", "wps": "69.4", "ups": "0.55", "wpb": "127.3", "bsz": "8", "num_updates": "20800", "lr": "9.91776e-05", "gnorm": "3.775", "loss_scale": "1024", "train_wall": "366", "gb_free": "6.5", "wall": "57370"}
[2024-06-15 16:54:17,492][train_inner][INFO] - {"epoch": 2, "update": 1.392, "loss": "3.347", "ntokens": "127.405", "acc_total": "127.405", "n_correct": "65.225", "wer_total": "127.405", "n_error": "62.115", "ppl": "10.18", "accuracy": "51.195", "wer": "48.754", "wps": "69.5", "ups": "0.55", "wpb": "127.4", "bsz": "8", "num_updates": "21000", "lr": "9.62506e-05", "gnorm": "3.741", "loss_scale": "2048", "train_wall": "366", "gb_free": "6.5", "wall": "57737"}
[2024-06-15 17:00:24,227][train_inner][INFO] - {"epoch": 2, "update": 1.406, "loss": "3.296", "ntokens": "126.7", "acc_total": "126.7", "n_correct": "64.905", "wer_total": "126.7", "n_error": "61.76", "ppl": "9.82", "accuracy": "51.227", "wer": "48.745", "wps": "69.1", "ups": "0.55", "wpb": "126.7", "bsz": "8", "num_updates": "21200", "lr": "9.341e-05", "gnorm": "3.83", "loss_scale": "2048", "train_wall": "366", "gb_free": "6.5", "wall": "58103"}
[2024-06-15 17:06:30,559][train_inner][INFO] - {"epoch": 2, "update": 1.419, "loss": "3.322", "ntokens": "127.32", "acc_total": "127.32", "n_correct": "64.895", "wer_total": "127.32", "n_error": "62.35", "ppl": "10", "accuracy": "50.97", "wer": "48.971", "wps": "69.5", "ups": "0.55", "wpb": "127.3", "bsz": "8", "num_updates": "21400", "lr": "9.06532e-05", "gnorm": "3.802", "loss_scale": "2048", "train_wall": "366", "gb_free": "6.5", "wall": "58470"}
[2024-06-15 17:12:36,881][train_inner][INFO] - {"epoch": 2, "update": 1.432, "loss": "3.296", "ntokens": "126.805", "acc_total": "126.805", "n_correct": "64.87", "wer_total": "126.805", "n_error": "61.84", "ppl": "9.82", "accuracy": "51.157", "wer": "48.768", "wps": "69.2", "ups": "0.55", "wpb": "126.8", "bsz": "8", "num_updates": "21600", "lr": "8.79777e-05", "gnorm": "3.746", "loss_scale": "2048", "train_wall": "366", "gb_free": "6.5", "wall": "58836"}
[2024-06-15 17:18:43,129][train_inner][INFO] - {"epoch": 2, "update": 1.445, "loss": "3.258", "ntokens": "125.555", "acc_total": "125.555", "n_correct": "64.77", "wer_total": "125.555", "n_error": "60.72", "ppl": "9.57", "accuracy": "51.587", "wer": "48.361", "wps": "68.6", "ups": "0.55", "wpb": "125.6", "bsz": "8", "num_updates": "21800", "lr": "8.53812e-05", "gnorm": "3.738", "loss_scale": "2048", "train_wall": "366", "gb_free": "6.5", "wall": "59202"}
[2024-06-15 17:24:49,544][train_inner][INFO] - {"epoch": 2, "update": 1.459, "loss": "3.341", "ntokens": "127.64", "acc_total": "127.64", "n_correct": "65.975", "wer_total": "127.64", "n_error": "61.58", "ppl": "10.13", "accuracy": "51.688", "wer": "48.245", "wps": "69.7", "ups": "0.55", "wpb": "127.6", "bsz": "8", "num_updates": "22000", "lr": "8.28614e-05", "gnorm": "3.777", "loss_scale": "2048", "train_wall": "366", "gb_free": "6.5", "wall": "59569"}
[2024-06-15 17:30:56,010][train_inner][INFO] - {"epoch": 2, "update": 1.472, "loss": "3.186", "ntokens": "126.515", "acc_total": "126.515", "n_correct": "66.4", "wer_total": "126.515", "n_error": "60.07", "ppl": "9.1", "accuracy": "52.484", "wer": "47.481", "wps": "69", "ups": "0.55", "wpb": "126.5", "bsz": "8", "num_updates": "22200", "lr": "8.04159e-05", "gnorm": "3.794", "loss_scale": "2048", "train_wall": "366", "gb_free": "6.5", "wall": "59935"}
[2024-06-15 17:37:02,111][train_inner][INFO] - {"epoch": 2, "update": 1.485, "loss": "3.225", "ntokens": "127.11", "acc_total": "127.11", "n_correct": "66.67", "wer_total": "127.11", "n_error": "60.36", "ppl": "9.35", "accuracy": "52.451", "wer": "47.486", "wps": "69.4", "ups": "0.55", "wpb": "127.1", "bsz": "8", "num_updates": "22400", "lr": "7.80425e-05", "gnorm": "3.73", "loss_scale": "2048", "train_wall": "365", "gb_free": "6.5", "wall": "60301"}
[2024-06-15 17:40:05,040][fairseq_cli.train][INFO] - begin validation on "valid" subset
[2024-06-15 18:22:05,253][valid][INFO] - {"epoch": 2, "valid_loss": "3.131", "valid_ntokens": "18.1585", "valid_acc_total": "18.1585", "valid_n_correct": "9.73314", "valid_wer_total": "18.1585", "valid_n_error": "8.41546", "valid_ppl": "8.76", "valid_accuracy": "53.601", "valid_wer": "46.345", "valid_wps": "172.9", "valid_wpb": "18.2", "valid_bsz": "1", "valid_num_updates": "22500", "valid_best_accuracy": "53.601"}
[2024-06-15 18:22:05,253][fairseq.checkpoint_utils][INFO] - Preparing to save checkpoint for epoch 2 @ 22500 updates
[2024-06-15 18:22:05,253][fairseq.trainer][INFO] - Saving checkpoint to checkpoints/checkpoint_2_22500.pt
[2024-06-15 18:22:08,349][fairseq.trainer][INFO] - Finished saving checkpoint to checkpoints/checkpoint_2_22500.pt
[2024-06-15 18:22:12,995][fairseq.checkpoint_utils][INFO] - Saved checkpoint checkpoints/checkpoint_2_22500.pt (epoch 2 @ 22500 updates, score 53.601) (writing took 7.7415905879752245 seconds)
[2024-06-15 18:25:15,506][train_inner][INFO] - {"epoch": 2, "update": 1.498, "loss": "3.221", "ntokens": "126.78", "acc_total": "126.78", "n_correct": "67.3", "wer_total": "126.78", "n_error": "59.43", "ppl": "9.33", "accuracy": "53.084", "wer": "46.876", "wps": "8.8", "ups": "0.07", "wpb": "126.8", "bsz": "8", "num_updates": "22600", "lr": "7.57393e-05", "gnorm": "3.821", "loss_scale": "2048", "train_wall": "365", "gb_free": "6.5", "wall": "63195"}
[2024-06-15 18:28:55,083][fairseq.trainer][INFO] - NOTE: gradient overflow detected, ignoring gradient, setting loss scale to: 1024.0
[2024-06-15 18:31:23,449][train_inner][INFO] - {"epoch": 2, "update": 1.512, "loss": "3.244", "ntokens": "126.64", "acc_total": "126.64", "n_correct": "66.505", "wer_total": "126.64", "n_error": "60.04", "ppl": "9.47", "accuracy": "52.515", "wer": "47.41", "wps": "68.8", "ups": "0.54", "wpb": "126.6", "bsz": "8", "num_updates": "22800", "lr": "7.3504e-05", "gnorm": "3.771", "loss_scale": "1024", "train_wall": "367", "gb_free": "6.5", "wall": "63563"}
[2024-06-15 18:37:29,523][train_inner][INFO] - {"epoch": 2, "update": 1.525, "loss": "3.269", "ntokens": "126.155", "acc_total": "126.155", "n_correct": "66.6", "wer_total": "126.155", "n_error": "59.525", "ppl": "9.64", "accuracy": "52.792", "wer": "47.184", "wps": "68.9", "ups": "0.55", "wpb": "126.2", "bsz": "8", "num_updates": "23000", "lr": "7.13346e-05", "gnorm": "3.81", "loss_scale": "1024", "train_wall": "365", "gb_free": "6.5", "wall": "63929"}
[2024-06-15 18:43:35,841][train_inner][INFO] - {"epoch": 2, "update": 1.538, "loss": "3.166", "ntokens": "126.97", "acc_total": "126.97", "n_correct": "68.74", "wer_total": "126.97", "n_error": "58.145", "ppl": "8.98", "accuracy": "54.139", "wer": "45.794", "wps": "69.3", "ups": "0.55", "wpb": "127", "bsz": "8", "num_updates": "23200", "lr": "6.92293e-05", "gnorm": "3.723", "loss_scale": "1024", "train_wall": "366", "gb_free": "6.5", "wall": "64295"}
[2024-06-15 18:49:41,585][train_inner][INFO] - {"epoch": 2, "update": 1.552, "loss": "3.098", "ntokens": "126.29", "acc_total": "126.29", "n_correct": "68.515", "wer_total": "126.29", "n_error": "57.74", "ppl": "8.56", "accuracy": "54.252", "wer": "45.72", "wps": "69.1", "ups": "0.55", "wpb": "126.3", "bsz": "8", "num_updates": "23400", "lr": "6.71862e-05", "gnorm": "3.828", "loss_scale": "1024", "train_wall": "365", "gb_free": "6.5", "wall": "64661"}
[2024-06-15 18:55:47,236][train_inner][INFO] - {"epoch": 2, "update": 1.565, "loss": "3.298", "ntokens": "126.595", "acc_total": "126.595", "n_correct": "66.37", "wer_total": "126.595", "n_error": "60.185", "ppl": "9.84", "accuracy": "52.427", "wer": "47.541", "wps": "69.2", "ups": "0.55", "wpb": "126.6", "bsz": "8", "num_updates": "23600", "lr": "6.52033e-05", "gnorm": "3.813", "loss_scale": "1024", "train_wall": "365", "gb_free": "6.5", "wall": "65026"}
[2024-06-15 19:01:52,797][train_inner][INFO] - {"epoch": 2, "update": 1.578, "loss": "3.186", "ntokens": "127.175", "acc_total": "127.175", "n_correct": "68.385", "wer_total": "127.175", "n_error": "58.74", "ppl": "9.1", "accuracy": "53.772", "wer": "46.188", "wps": "69.6", "ups": "0.55", "wpb": "127.2", "bsz": "8", "num_updates": "23800", "lr": "6.3279e-05", "gnorm": "3.773", "loss_scale": "1024", "train_wall": "365", "gb_free": "6.5", "wall": "65392"}
[2024-06-15 19:07:58,141][train_inner][INFO] - {"epoch": 2, "update": 1.591, "loss": "3.173", "ntokens": "126.775", "acc_total": "126.775", "n_correct": "68.5", "wer_total": "126.775", "n_error": "58.25", "ppl": "9.02", "accuracy": "54.033", "wer": "45.948", "wps": "69.4", "ups": "0.55", "wpb": "126.8", "bsz": "8", "num_updates": "24000", "lr": "6.14114e-05", "gnorm": "3.754", "loss_scale": "1024", "train_wall": "365", "gb_free": "6.5", "wall": "65757"}
[2024-06-15 19:14:03,725][train_inner][INFO] - {"epoch": 2, "update": 1.605, "loss": "3.119", "ntokens": "126.17", "acc_total": "126.17", "n_correct": "68.96", "wer_total": "126.17", "n_error": "57.165", "ppl": "8.69", "accuracy": "54.656", "wer": "45.308", "wps": "69", "ups": "0.55", "wpb": "126.2", "bsz": "8", "num_updates": "24200", "lr": "5.9599e-05", "gnorm": "3.771", "loss_scale": "1024", "train_wall": "365", "gb_free": "6.5", "wall": "66123"}
[2024-06-15 19:20:09,217][train_inner][INFO] - {"epoch": 2, "update": 1.618, "loss": "3.154", "ntokens": "127.2", "acc_total": "127.2", "n_correct": "68.555", "wer_total": "127.2", "n_error": "58.595", "ppl": "8.9", "accuracy": "53.895", "wer": "46.065", "wps": "69.6", "ups": "0.55", "wpb": "127.2", "bsz": "8", "num_updates": "24400", "lr": "5.784e-05", "gnorm": "3.826", "loss_scale": "1024", "train_wall": "365", "gb_free": "6.5", "wall": "66488"}
[2024-06-15 19:26:14,776][train_inner][INFO] - {"epoch": 2, "update": 1.631, "loss": "3.209", "ntokens": "127.38", "acc_total": "127.38", "n_correct": "67.34", "wer_total": "127.38", "n_error": "59.995", "ppl": "9.25", "accuracy": "52.865", "wer": "47.099", "wps": "69.7", "ups": "0.55", "wpb": "127.4", "bsz": "8", "num_updates": "24600", "lr": "5.6133e-05", "gnorm": "3.751", "loss_scale": "1024", "train_wall": "365", "gb_free": "6.5", "wall": "66854"}
[2024-06-15 19:32:20,366][train_inner][INFO] - {"epoch": 2, "update": 1.644, "loss": "3.106", "ntokens": "127.26", "acc_total": "127.26", "n_correct": "69.355", "wer_total": "127.26", "n_error": "57.855", "ppl": "8.61", "accuracy": "54.499", "wer": "45.462", "wps": "69.6", "ups": "0.55", "wpb": "127.3", "bsz": "8", "num_updates": "24800", "lr": "5.44763e-05", "gnorm": "3.78", "loss_scale": "2048", "train_wall": "365", "gb_free": "6.5", "wall": "67219"}
[2024-06-15 19:38:26,343][train_inner][INFO] - {"epoch": 2, "update": 1.658, "loss": "3.193", "ntokens": "125.92", "acc_total": "125.92", "n_correct": "67.235", "wer_total": "125.92", "n_error": "58.615", "ppl": "9.15", "accuracy": "53.395", "wer": "46.549", "wps": "68.8", "ups": "0.55", "wpb": "125.9", "bsz": "8", "num_updates": "25000", "lr": "5.28686e-05", "gnorm": "3.758", "loss_scale": "2048", "train_wall": "365", "gb_free": "6.5", "wall": "67585"}
[2024-06-15 19:38:26,343][fairseq_cli.train][INFO] - begin validation on "valid" subset
[2024-06-15 20:20:28,477][valid][INFO] - {"epoch": 2, "valid_loss": "3.029", "valid_ntokens": "18.1585", "valid_acc_total": "18.1585", "valid_n_correct": "10.2083", "valid_wer_total": "18.1585", "valid_n_error": "7.9431", "valid_ppl": "8.16", "valid_accuracy": "56.218", "valid_wer": "43.743", "valid_wps": "172.7", "valid_wpb": "18.2", "valid_bsz": "1", "valid_num_updates": "25000", "valid_best_accuracy": "56.218"}
[2024-06-15 20:20:28,477][fairseq.checkpoint_utils][INFO] - Preparing to save checkpoint for epoch 2 @ 25000 updates
[2024-06-15 20:20:28,478][fairseq.trainer][INFO] - Saving checkpoint to checkpoints/checkpoint_2_25000.pt
[2024-06-15 20:20:31,577][fairseq.trainer][INFO] - Finished saving checkpoint to checkpoints/checkpoint_2_25000.pt
[2024-06-15 20:20:36,233][fairseq.checkpoint_utils][INFO] - Saved checkpoint checkpoints/checkpoint_2_25000.pt (epoch 2 @ 25000 updates, score 56.218) (writing took 7.755430594988866 seconds)
[2024-06-15 20:26:41,751][train_inner][INFO] - {"epoch": 2, "update": 1.671, "loss": "3.067", "ntokens": "127.44", "acc_total": "127.44", "n_correct": "70.06", "wer_total": "127.44", "n_error": "57.335", "ppl": "8.38", "accuracy": "54.975", "wer": "44.99", "wps": "8.8", "ups": "0.07", "wpb": "127.4", "bsz": "8", "num_updates": "25200", "lr": "5.13083e-05", "gnorm": "3.825", "loss_scale": "2048", "train_wall": "365", "gb_free": "6.5", "wall": "70481"}
[2024-06-15 20:32:47,584][train_inner][INFO] - {"epoch": 2, "update": 1.684, "loss": "3.124", "ntokens": "125.36", "acc_total": "125.36", "n_correct": "68.16", "wer_total": "125.36", "n_error": "57.115", "ppl": "8.72", "accuracy": "54.371", "wer": "45.561", "wps": "68.5", "ups": "0.55", "wpb": "125.4", "bsz": "8", "num_updates": "25400", "lr": "4.9794e-05", "gnorm": "3.752", "loss_scale": "2048", "train_wall": "365", "gb_free": "6.5", "wall": "70847"}
[2024-06-15 20:38:53,215][train_inner][INFO] - {"epoch": 2, "update": 1.697, "loss": "3.056", "ntokens": "127.07", "acc_total": "127.07", "n_correct": "68.69", "wer_total": "127.07", "n_error": "58.32", "ppl": "8.32", "accuracy": "54.057", "wer": "45.896", "wps": "69.5", "ups": "0.55", "wpb": "127.1", "bsz": "8", "num_updates": "25600", "lr": "4.83244e-05", "gnorm": "3.772", "loss_scale": "2048", "train_wall": "365", "gb_free": "6.5", "wall": "71212"}
[2024-06-15 20:44:59,014][train_inner][INFO] - {"epoch": 2, "update": 1.711, "loss": "3.05", "ntokens": "127.055", "acc_total": "127.055", "n_correct": "69.53", "wer_total": "127.055", "n_error": "57.46", "ppl": "8.28", "accuracy": "54.724", "wer": "45.225", "wps": "69.5", "ups": "0.55", "wpb": "127.1", "bsz": "8", "num_updates": "25800", "lr": "4.68982e-05", "gnorm": "3.75", "loss_scale": "2048", "train_wall": "365", "gb_free": "6.5", "wall": "71578"}
[2024-06-15 20:51:04,571][train_inner][INFO] - {"epoch": 2, "update": 1.724, "loss": "3.091", "ntokens": "126.935", "acc_total": "126.935", "n_correct": "69.135", "wer_total": "126.935", "n_error": "57.745", "ppl": "8.52", "accuracy": "54.465", "wer": "45.492", "wps": "69.4", "ups": "0.55", "wpb": "126.9", "bsz": "8", "num_updates": "26000", "lr": "4.55141e-05", "gnorm": "3.751", "loss_scale": "2048", "train_wall": "365", "gb_free": "6.5", "wall": "71944"}
[2024-06-15 20:57:09,808][train_inner][INFO] - {"epoch": 2, "update": 1.737, "loss": "3.133", "ntokens": "126.305", "acc_total": "126.305", "n_correct": "69.275", "wer_total": "126.305", "n_error": "57.005", "ppl": "8.77", "accuracy": "54.847", "wer": "45.133", "wps": "69.2", "ups": "0.55", "wpb": "126.3", "bsz": "8", "num_updates": "26200", "lr": "4.41708e-05", "gnorm": "3.723", "loss_scale": "2048", "train_wall": "364", "gb_free": "6.5", "wall": "72309"}
[2024-06-15 21:03:15,053][train_inner][INFO] - {"epoch": 2, "update": 1.75, "loss": "3.039", "ntokens": "127.47", "acc_total": "127.47", "n_correct": "70.465", "wer_total": "127.47", "n_error": "56.965", "ppl": "8.22", "accuracy": "55.28", "wer": "44.689", "wps": "69.8", "ups": "0.55", "wpb": "127.5", "bsz": "8", "num_updates": "26400", "lr": "4.28672e-05", "gnorm": "3.721", "loss_scale": "2048", "train_wall": "365", "gb_free": "6.5", "wall": "72674"}
[2024-06-15 21:09:20,113][train_inner][INFO] - {"epoch": 2, "update": 1.764, "loss": "3.045", "ntokens": "126.6", "acc_total": "126.6", "n_correct": "68.91", "wer_total": "126.6", "n_error": "57.625", "ppl": "8.26", "accuracy": "54.431", "wer": "45.517", "wps": "69.4", "ups": "0.55", "wpb": "126.6", "bsz": "8", "num_updates": "26600", "lr": "4.16021e-05", "gnorm": "3.773", "loss_scale": "2048", "train_wall": "364", "gb_free": "6.5", "wall": "73039"}
[2024-06-15 21:15:24,791][train_inner][INFO] - {"epoch": 2, "update": 1.777, "loss": "2.986", "ntokens": "126.565", "acc_total": "126.565", "n_correct": "69.745", "wer_total": "126.565", "n_error": "56.76", "ppl": "7.92", "accuracy": "55.106", "wer": "44.847", "wps": "69.4", "ups": "0.55", "wpb": "126.6", "bsz": "8", "num_updates": "26800", "lr": "4.03743e-05", "gnorm": "3.756", "loss_scale": "2048", "train_wall": "364", "gb_free": "6.5", "wall": "73404"}
[2024-06-15 21:21:29,264][train_inner][INFO] - {"epoch": 2, "update": 1.79, "loss": "3.08", "ntokens": "127.69", "acc_total": "127.69", "n_correct": "69.645", "wer_total": "127.69", "n_error": "57.975", "ppl": "8.45", "accuracy": "54.542", "wer": "45.403", "wps": "70.1", "ups": "0.55", "wpb": "127.7", "bsz": "8", "num_updates": "27000", "lr": "3.91827e-05", "gnorm": "3.743", "loss_scale": "4096", "train_wall": "364", "gb_free": "6.5", "wall": "73768"}
[2024-06-15 21:27:33,660][train_inner][INFO] - {"epoch": 2, "update": 1.803, "loss": "3.051", "ntokens": "127.97", "acc_total": "127.97", "n_correct": "70.395", "wer_total": "127.97", "n_error": "57.49", "ppl": "8.29", "accuracy": "55.009", "wer": "44.925", "wps": "70.2", "ups": "0.55", "wpb": "128", "bsz": "8", "num_updates": "27200", "lr": "3.80263e-05", "gnorm": "3.71", "loss_scale": "4096", "train_wall": "364", "gb_free": "6.5", "wall": "74133"}
[2024-06-15 21:30:26,633][fairseq.trainer][INFO] - NOTE: gradient overflow detected, ignoring gradient, setting loss scale to: 2048.0
[2024-06-15 21:33:39,845][train_inner][INFO] - {"epoch": 2, "update": 1.817, "loss": "3.119", "ntokens": "126.675", "acc_total": "126.675", "n_correct": "69.2", "wer_total": "126.675", "n_error": "57.415", "ppl": "8.69", "accuracy": "54.628", "wer": "45.325", "wps": "69.2", "ups": "0.55", "wpb": "126.7", "bsz": "8", "num_updates": "27400", "lr": "3.6904e-05", "gnorm": "3.819", "loss_scale": "2048", "train_wall": "365", "gb_free": "6.5", "wall": "74499"}
[2024-06-15 21:36:42,097][fairseq_cli.train][INFO] - begin validation on "valid" subset
[2024-06-15 22:18:36,263][valid][INFO] - {"epoch": 2, "valid_loss": "2.937", "valid_ntokens": "18.1585", "valid_acc_total": "18.1585", "valid_n_correct": "10.1775", "valid_wer_total": "18.1585", "valid_n_error": "7.97278", "valid_ppl": "7.66", "valid_accuracy": "56.048", "valid_wer": "43.907", "valid_wps": "173.3", "valid_wpb": "18.2", "valid_bsz": "1", "valid_num_updates": "27500", "valid_best_accuracy": "56.218"}
[2024-06-15 22:18:36,264][fairseq.checkpoint_utils][INFO] - Preparing to save checkpoint for epoch 2 @ 27500 updates
[2024-06-15 22:18:36,264][fairseq.trainer][INFO] - Saving checkpoint to checkpoints/checkpoint_2_27500.pt
[2024-06-15 22:18:39,470][fairseq.trainer][INFO] - Finished saving checkpoint to checkpoints/checkpoint_2_27500.pt
[2024-06-15 22:18:41,886][fairseq.checkpoint_utils][INFO] - Saved checkpoint checkpoints/checkpoint_2_27500.pt (epoch 2 @ 27500 updates, score 56.048) (writing took 5.621618739998667 seconds)
[2024-06-15 22:21:43,623][train_inner][INFO] - {"epoch": 2, "update": 1.83, "loss": "3.039", "ntokens": "126.45", "acc_total": "126.45", "n_correct": "69.105", "wer_total": "126.45", "n_error": "57.275", "ppl": "8.22", "accuracy": "54.65", "wer": "45.295", "wps": "8.8", "ups": "0.07", "wpb": "126.5", "bsz": "8", "num_updates": "27600", "lr": "3.58149e-05", "gnorm": "3.756", "loss_scale": "2048", "train_wall": "363", "gb_free": "6.5", "wall": "77383"}
[2024-06-15 22:27:47,691][train_inner][INFO] - {"epoch": 2, "update": 1.843, "loss": "3.061", "ntokens": "127.465", "acc_total": "127.465", "n_correct": "69.745", "wer_total": "127.465", "n_error": "57.66", "ppl": "8.35", "accuracy": "54.717", "wer": "45.236", "wps": "70", "ups": "0.55", "wpb": "127.5", "bsz": "8", "num_updates": "27800", "lr": "3.47579e-05", "gnorm": "3.727", "loss_scale": "2048", "train_wall": "363", "gb_free": "6.5", "wall": "77747"}
[2024-06-15 22:33:51,437][train_inner][INFO] - {"epoch": 2, "update": 1.856, "loss": "3.037", "ntokens": "127.49", "acc_total": "127.49", "n_correct": "70.505", "wer_total": "127.49", "n_error": "56.905", "ppl": "8.21", "accuracy": "55.302", "wer": "44.635", "wps": "70.1", "ups": "0.55", "wpb": "127.5", "bsz": "8", "num_updates": "28000", "lr": "3.37321e-05", "gnorm": "3.71", "loss_scale": "2048", "train_wall": "363", "gb_free": "6.5", "wall": "78111"}
[2024-06-15 22:39:55,210][train_inner][INFO] - {"epoch": 2, "update": 1.87, "loss": "3.016", "ntokens": "127.75", "acc_total": "127.75", "n_correct": "70.755", "wer_total": "127.75", "n_error": "56.925", "ppl": "8.09", "accuracy": "55.386", "wer": "44.56", "wps": "70.2", "ups": "0.55", "wpb": "127.8", "bsz": "8", "num_updates": "28200", "lr": "3.27365e-05", "gnorm": "3.758", "loss_scale": "2048", "train_wall": "363", "gb_free": "6.5", "wall": "78474"}
[2024-06-15 22:45:58,863][train_inner][INFO] - {"epoch": 2, "update": 1.883, "loss": "2.992", "ntokens": "127.125", "acc_total": "127.125", "n_correct": "69.96", "wer_total": "127.125", "n_error": "57.105", "ppl": "7.96", "accuracy": "55.032", "wer": "44.92", "wps": "69.9", "ups": "0.55", "wpb": "127.1", "bsz": "8", "num_updates": "28400", "lr": "3.17704e-05", "gnorm": "3.851", "loss_scale": "2048", "train_wall": "363", "gb_free": "6.5", "wall": "78838"}
[2024-06-15 22:52:02,677][train_inner][INFO] - {"epoch": 2, "update": 1.896, "loss": "3.044", "ntokens": "128.015", "acc_total": "128.015", "n_correct": "71.02", "wer_total": "128.015", "n_error": "56.965", "ppl": "8.25", "accuracy": "55.478", "wer": "44.499", "wps": "70.4", "ups": "0.55", "wpb": "128", "bsz": "8", "num_updates": "28600", "lr": "3.08327e-05", "gnorm": "3.835", "loss_scale": "2048", "train_wall": "363", "gb_free": "6.5", "wall": "79202"}
[2024-06-15 22:58:06,658][train_inner][INFO] - {"epoch": 2, "update": 1.91, "loss": "2.994", "ntokens": "126.755", "acc_total": "126.755", "n_correct": "70.175", "wer_total": "126.755", "n_error": "56.515", "ppl": "7.96", "accuracy": "55.363", "wer": "44.586", "wps": "69.6", "ups": "0.55", "wpb": "126.8", "bsz": "8", "num_updates": "28800", "lr": "2.99228e-05", "gnorm": "3.736", "loss_scale": "2048", "train_wall": "363", "gb_free": "6.5", "wall": "79566"}
[2024-06-15 23:04:10,640][train_inner][INFO] - {"epoch": 2, "update": 1.923, "loss": "2.957", "ntokens": "127.74", "acc_total": "127.74", "n_correct": "72.31", "wer_total": "127.74", "n_error": "55.395", "ppl": "7.77", "accuracy": "56.607", "wer": "43.365", "wps": "70.2", "ups": "0.55", "wpb": "127.7", "bsz": "8", "num_updates": "29000", "lr": "2.90397e-05", "gnorm": "3.723", "loss_scale": "2048", "train_wall": "363", "gb_free": "6.5", "wall": "79930"}
[2024-06-15 23:10:14,620][train_inner][INFO] - {"epoch": 2, "update": 1.936, "loss": "3.027", "ntokens": "126.765", "acc_total": "126.765", "n_correct": "70.3", "wer_total": "126.765", "n_error": "56.41", "ppl": "8.15", "accuracy": "55.457", "wer": "44.5", "wps": "69.7", "ups": "0.55", "wpb": "126.8", "bsz": "8", "num_updates": "29200", "lr": "2.81826e-05", "gnorm": "3.804", "loss_scale": "2048", "train_wall": "363", "gb_free": "6.5", "wall": "80294"}
[2024-06-15 23:16:18,545][train_inner][INFO] - {"epoch": 2, "update": 1.949, "loss": "3.051", "ntokens": "127.17", "acc_total": "127.17", "n_correct": "70.715", "wer_total": "127.17", "n_error": "56.435", "ppl": "8.29", "accuracy": "55.607", "wer": "44.378", "wps": "69.9", "ups": "0.55", "wpb": "127.2", "bsz": "8", "num_updates": "29400", "lr": "2.73509e-05", "gnorm": "3.761", "loss_scale": "4096", "train_wall": "363", "gb_free": "6.5", "wall": "80658"}
[2024-06-15 23:22:22,933][train_inner][INFO] - {"epoch": 2, "update": 1.963, "loss": "2.951", "ntokens": "127.1", "acc_total": "127.1", "n_correct": "71.52", "wer_total": "127.1", "n_error": "55.515", "ppl": "7.73", "accuracy": "56.271", "wer": "43.678", "wps": "69.8", "ups": "0.55", "wpb": "127.1", "bsz": "8", "num_updates": "29600", "lr": "2.65436e-05", "gnorm": "3.781", "loss_scale": "4096", "train_wall": "364", "gb_free": "6.5", "wall": "81022"}
[2024-06-15 23:28:27,792][train_inner][INFO] - {"epoch": 2, "update": 1.976, "loss": "2.994", "ntokens": "126.885", "acc_total": "126.885", "n_correct": "71.245", "wer_total": "126.885", "n_error": "55.59", "ppl": "7.97", "accuracy": "56.149", "wer": "43.811", "wps": "69.6", "ups": "0.55", "wpb": "126.9", "bsz": "8", "num_updates": "29800", "lr": "2.57603e-05", "gnorm": "3.778", "loss_scale": "4096", "train_wall": "364", "gb_free": "6.5", "wall": "81387"}
[2024-06-15 23:34:08,766][fairseq.trainer][INFO] - NOTE: gradient overflow detected, ignoring gradient, setting loss scale to: 2048.0
[2024-06-15 23:34:34,272][train_inner][INFO] - {"epoch": 2, "update": 1.989, "loss": "3.001", "ntokens": "126.935", "acc_total": "126.935", "n_correct": "70.18", "wer_total": "126.935", "n_error": "56.71", "ppl": "8.01", "accuracy": "55.288", "wer": "44.676", "wps": "69.3", "ups": "0.55", "wpb": "126.9", "bsz": "8", "num_updates": "30000", "lr": "2.5e-05", "gnorm": "3.752", "loss_scale": "2048", "train_wall": "366", "gb_free": "6.5", "wall": "81753"}
[2024-06-15 23:34:34,272][fairseq_cli.train][INFO] - Stopping training due to num_updates: 30000 >= max_update: 30000
[2024-06-15 23:34:34,272][fairseq_cli.train][INFO] - begin validation on "valid" subset
[2024-06-16 00:16:26,410][valid][INFO] - {"epoch": 2, "valid_loss": "2.918", "valid_ntokens": "18.1585", "valid_acc_total": "18.1585", "valid_n_correct": "10.2358", "valid_wer_total": "18.1585", "valid_n_error": "7.91417", "valid_ppl": "7.56", "valid_accuracy": "56.369", "valid_wer": "43.584", "valid_wps": "173.4", "valid_wpb": "18.2", "valid_bsz": "1", "valid_num_updates": "30000", "valid_best_accuracy": "56.369"}
[2024-06-16 00:16:26,411][fairseq.checkpoint_utils][INFO] - Preparing to save checkpoint for epoch 2 @ 30000 updates
[2024-06-16 00:16:26,411][fairseq.trainer][INFO] - Saving checkpoint to checkpoints/checkpoint_2_30000.pt
[2024-06-16 00:16:29,520][fairseq.trainer][INFO] - Finished saving checkpoint to checkpoints/checkpoint_2_30000.pt
[2024-06-16 00:16:33,910][fairseq.checkpoint_utils][INFO] - Saved checkpoint checkpoints/checkpoint_2_30000.pt (epoch 2 @ 30000 updates, score 56.369) (writing took 7.499138368002605 seconds)
[2024-06-16 00:16:34,081][fairseq_cli.train][INFO] - end of epoch 2 (average epoch stats below)
[2024-06-16 00:16:34,097][train][INFO] - {"epoch": 2, "train_loss": "3.33", "train_ntokens": "126.909", "train_acc_total": "126.909", "train_n_correct": "65.0846", "train_wer_total": "126.909", "train_n_error": "61.7495", "train_ppl": "10.05", "train_accuracy": "51.285", "train_wer": "48.657", "train_wps": "45.1", "train_ups": "0.36", "train_wpb": "126.9", "train_bsz": "8", "train_num_updates": "30000", "train_lr": "2.5e-05", "train_gnorm": "3.667", "train_loss_scale": "2048", "train_train_wall": "26712", "train_gb_free": "6.5", "train_wall": "84273"}
[2024-06-16 00:16:34,097][fairseq_cli.train][INFO] - done training in 84272.5 seconds