Training in progress, epoch 1

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3dbd12cee44083ef051774cc071d72302ab54e3242ec6c5ff3af01d7d77d34db
+oid sha256:49ee3536b9708bac89c69b76a058e5be5398a0fba3d7cd2484aae9b6f88f0be7
 size 267832560

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a86d9039d7d29dc4e8edeb97896c20851dd693838ac9d5a1a14e01b643d083a6
+oid sha256:8a4ef8b53299293acc0eb0fbccea6e038f596dcf0cc74550d57f0bd42ce856d6
 size 5624

wandb/debug.log

@@ -55,3 +55,21 @@ config: {}
 2024-09-24 17:26:50,737 INFO    MainThread:48218 [wandb_run.py:_config_callback():1382] config_cb None None {'vocab_size': 30522, 'max_position_embeddings': 512, 'sinusoidal_pos_embds': False, 'n_layers': 6, 'n_heads': 12, 'dim': 768, 'hidden_dim': 3072, 'dropout': 0.1, 'attention_dropout': 0.1, 'activation': 'gelu', 'initializer_range': 0.02, 'qa_dropout': 0.1, 'seq_classif_dropout': 0.2, 'return_dict': True, 'output_hidden_states': False, 'output_attentions': False, 'torchscript': False, 'torch_dtype': None, 'use_bfloat16': False, 'tf_legacy_loss': False, 'pruned_heads': {}, 'tie_word_embeddings': True, 'chunk_size_feed_forward': 0, 'is_encoder_decoder': False, 'is_decoder': False, 'cross_attention_hidden_size': None, 'add_cross_attention': False, 'tie_encoder_decoder': False, 'max_length': 20, 'min_length': 0, 'do_sample': False, 'early_stopping': False, 'num_beams': 1, 'num_beam_groups': 1, 'diversity_penalty': 0.0, 'temperature': 1.0, 'top_k': 50, 'top_p': 1.0, 'typical_p': 1.0, 'repetition_penalty': 1.0, 'length_penalty': 1.0, 'no_repeat_ngram_size': 0, 'encoder_no_repeat_ngram_size': 0, 'bad_words_ids': None, 'num_return_sequences': 1, 'output_scores': False, 'return_dict_in_generate': False, 'forced_bos_token_id': None, 'forced_eos_token_id': None, 'remove_invalid_values': False, 'exponential_decay_length_penalty': None, 'suppress_tokens': None, 'begin_suppress_tokens': None, 'architectures': ['DistilBertForMaskedLM'], 'finetuning_task': None, 'id2label': {0: 'objeto', 1: 'outros'}, 'label2id': {'objeto': 0, 'outros': 1}, 'tokenizer_class': None, 'prefix': None, 'bos_token_id': None, 'pad_token_id': 0, 'eos_token_id': None, 'sep_token_id': None, 'decoder_start_token_id': None, 'task_specific_params': None, 'problem_type': None, '_name_or_path': 'distilbert/distilbert-base-uncased', 'transformers_version': '4.44.2', 'model_type': 'distilbert', 'tie_weights_': True, 'output_dir': '/Users/marcelovidigal/Library/CloudStorage/GoogleDrive-marcelovidigal@gmail.com/Meu Drive/projetos/python/retrieval_augmented_generation/modelos/doutorado/secoes_contrato_rotulos_classificacao_texto_v1', 'overwrite_output_dir': False, 'do_train': False, 'do_eval': True, 'do_predict': False, 'eval_strategy': 'epoch', 'prediction_loss_only': False, 'per_device_train_batch_size': 16, 'per_device_eval_batch_size': 16, 'per_gpu_train_batch_size': None, 'per_gpu_eval_batch_size': None, 'gradient_accumulation_steps': 1, 'eval_accumulation_steps': None, 'eval_delay': 0, 'torch_empty_cache_steps': None, 'learning_rate': 2e-05, 'weight_decay': 0.01, 'adam_beta1': 0.9, 'adam_beta2': 0.999, 'adam_epsilon': 1e-08, 'max_grad_norm': 1.0, 'num_train_epochs': 5, 'max_steps': -1, 'lr_scheduler_type': 'linear', 'lr_scheduler_kwargs': {}, 'warmup_ratio': 0.0, 'warmup_steps': 0, 'log_level': 'passive', 'log_level_replica': 'warning', 'log_on_each_node': True, 'logging_dir': '/Users/marcelovidigal/Library/CloudStorage/GoogleDrive-marcelovidigal@gmail.com/Meu Drive/projetos/python/retrieval_augmented_generation/modelos/doutorado/secoes_contrato_rotulos_classificacao_texto_v1/runs/Sep24_17-26-48_mace16.local', 'logging_strategy': 'steps', 'logging_first_step': False, 'logging_steps': 500, 'logging_nan_inf_filter': True, 'save_strategy': 'epoch', 'save_steps': 500, 'save_total_limit': None, 'save_safetensors': True, 'save_on_each_node': False, 'save_only_model': False, 'restore_callback_states_from_checkpoint': False, 'no_cuda': False, 'use_cpu': False, 'use_mps_device': False, 'seed': 42, 'data_seed': None, 'jit_mode_eval': False, 'use_ipex': False, 'bf16': False, 'fp16': False, 'fp16_opt_level': 'O1', 'half_precision_backend': 'auto', 'bf16_full_eval': False, 'fp16_full_eval': False, 'tf32': None, 'local_rank': 0, 'ddp_backend': None, 'tpu_num_cores': None, 'tpu_metrics_debug': False, 'debug': [], 'dataloader_drop_last': False, 'eval_steps': None, 'dataloader_num_workers': 0, 'dataloader_prefetch_factor': None, 'past_index': -1, 'run_name': 'secoes_contrato_rotulos_classificacao_texto_v1', 'disable_tqdm': False, 'remove_unused_columns': True, 'label_names': None, 'load_best_model_at_end': True, 'metric_for_best_model': 'loss', 'greater_is_better': False, 'ignore_data_skip': False, 'fsdp': [], 'fsdp_min_num_params': 0, 'fsdp_config': {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}, 'fsdp_transformer_layer_cls_to_wrap': None, 'accelerator_config': {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}, 'deepspeed': None, 'label_smoothing_factor': 0.0, 'optim': 'adamw_torch', 'optim_args': None, 'adafactor': False, 'group_by_length': False, 'length_column_name': 'length', 'report_to': ['wandb'], 'ddp_find_unused_parameters': None, 'ddp_bucket_cap_mb': None, 'ddp_broadcast_buffers': None, 'dataloader_pin_memory': True, 'dataloader_persistent_workers': False, 'skip_memory_metrics': True, 'use_legacy_prediction_loop': False, 'push_to_hub': True, 'resume_from_checkpoint': None, 'hub_model_id': None, 'hub_strategy': 'every_save', 'hub_token': '<HUB_TOKEN>', 'hub_private_repo': False, 'hub_always_push': False, 'gradient_checkpointing': False, 'gradient_checkpointing_kwargs': None, 'include_inputs_for_metrics': False, 'eval_do_concat_batches': True, 'fp16_backend': 'auto', 'evaluation_strategy': None, 'push_to_hub_model_id': None, 'push_to_hub_organization': None, 'push_to_hub_token': '<PUSH_TO_HUB_TOKEN>', 'mp_parameters': '', 'auto_find_batch_size': False, 'full_determinism': False, 'torchdynamo': None, 'ray_scope': 'last', 'ddp_timeout': 1800, 'torch_compile': False, 'torch_compile_backend': None, 'torch_compile_mode': None, 'dispatch_batches': None, 'split_batches': None, 'include_tokens_per_second': False, 'include_num_input_tokens_seen': False, 'neftune_noise_alpha': None, 'optim_target_modules': None, 'batch_eval_metrics': False, 'eval_on_start': False, 'eval_use_gather_object': False}
 2024-09-24 17:26:50,740 INFO    MainThread:48218 [wandb_config.py:__setitem__():151] config set model/num_parameters = 66955010 - <bound method Run._config_callback of <wandb.sdk.wandb_run.Run object at 0x13c481490>>
 2024-09-24 17:26:50,740 INFO    MainThread:48218 [wandb_run.py:_config_callback():1382] config_cb model/num_parameters 66955010 None
+2024-09-24 19:40:46,713 INFO    MainThread:48218 [jupyter.py:save_ipynb():372] not saving jupyter notebook
+2024-09-24 19:40:46,722 INFO    MainThread:48218 [wandb_init.py:_pause_backend():440] pausing backend
+2024-09-24 19:40:46,781 INFO    MainThread:48218 [wandb_init.py:_resume_backend():445] resuming backend
+2024-09-24 19:40:46,802 INFO    MainThread:48218 [jupyter.py:save_ipynb():372] not saving jupyter notebook
+2024-09-24 19:40:46,802 INFO    MainThread:48218 [wandb_init.py:_pause_backend():440] pausing backend
+2024-09-24 19:45:19,097 INFO    MainThread:48218 [wandb_init.py:_resume_backend():445] resuming backend
+2024-09-24 19:45:19,112 INFO    MainThread:48218 [jupyter.py:save_ipynb():372] not saving jupyter notebook
+2024-09-24 19:45:19,117 INFO    MainThread:48218 [wandb_init.py:_pause_backend():440] pausing backend
+2024-09-24 19:46:01,642 INFO    MainThread:48218 [wandb_init.py:_resume_backend():445] resuming backend
+2024-09-24 19:46:05,896 INFO    MainThread:48218 [wandb_run.py:_config_callback():1382] config_cb None None {'vocab_size': 30522, 'max_position_embeddings': 512, 'sinusoidal_pos_embds': False, 'n_layers': 6, 'n_heads': 12, 'dim': 768, 'hidden_dim': 3072, 'dropout': 0.1, 'attention_dropout': 0.1, 'activation': 'gelu', 'initializer_range': 0.02, 'qa_dropout': 0.1, 'seq_classif_dropout': 0.2, 'return_dict': True, 'output_hidden_states': False, 'output_attentions': False, 'torchscript': False, 'torch_dtype': None, 'use_bfloat16': False, 'tf_legacy_loss': False, 'pruned_heads': {}, 'tie_word_embeddings': True, 'chunk_size_feed_forward': 0, 'is_encoder_decoder': False, 'is_decoder': False, 'cross_attention_hidden_size': None, 'add_cross_attention': False, 'tie_encoder_decoder': False, 'max_length': 20, 'min_length': 0, 'do_sample': False, 'early_stopping': False, 'num_beams': 1, 'num_beam_groups': 1, 'diversity_penalty': 0.0, 'temperature': 1.0, 'top_k': 50, 'top_p': 1.0, 'typical_p': 1.0, 'repetition_penalty': 1.0, 'length_penalty': 1.0, 'no_repeat_ngram_size': 0, 'encoder_no_repeat_ngram_size': 0, 'bad_words_ids': None, 'num_return_sequences': 1, 'output_scores': False, 'return_dict_in_generate': False, 'forced_bos_token_id': None, 'forced_eos_token_id': None, 'remove_invalid_values': False, 'exponential_decay_length_penalty': None, 'suppress_tokens': None, 'begin_suppress_tokens': None, 'architectures': ['DistilBertForMaskedLM'], 'finetuning_task': None, 'id2label': {0: 'objeto', 1: 'outros'}, 'label2id': {'objeto': 0, 'outros': 1}, 'tokenizer_class': None, 'prefix': None, 'bos_token_id': None, 'pad_token_id': 0, 'eos_token_id': None, 'sep_token_id': None, 'decoder_start_token_id': None, 'task_specific_params': None, 'problem_type': None, '_name_or_path': 'distilbert/distilbert-base-uncased', 'transformers_version': '4.44.2', 'model_type': 'distilbert', 'tie_weights_': True, 'output_dir': '/Users/marcelovidigal/Library/CloudStorage/GoogleDrive-marcelovidigal@gmail.com/Meu Drive/projetos/python/retrieval_augmented_generation/modelos/doutorado/secoes_contrato_rotulos_classificacao_texto_v1', 'overwrite_output_dir': False, 'do_train': False, 'do_eval': True, 'do_predict': False, 'eval_strategy': 'epoch', 'prediction_loss_only': False, 'per_device_train_batch_size': 32, 'per_device_eval_batch_size': 32, 'per_gpu_train_batch_size': None, 'per_gpu_eval_batch_size': None, 'gradient_accumulation_steps': 1, 'eval_accumulation_steps': None, 'eval_delay': 0, 'torch_empty_cache_steps': None, 'learning_rate': 1e-06, 'weight_decay': 0.001, 'adam_beta1': 0.9, 'adam_beta2': 0.999, 'adam_epsilon': 1e-08, 'max_grad_norm': 1.0, 'num_train_epochs': 50, 'max_steps': -1, 'lr_scheduler_type': 'linear', 'lr_scheduler_kwargs': {}, 'warmup_ratio': 0.0, 'warmup_steps': 0, 'log_level': 'passive', 'log_level_replica': 'warning', 'log_on_each_node': True, 'logging_dir': '/Users/marcelovidigal/Library/CloudStorage/GoogleDrive-marcelovidigal@gmail.com/Meu Drive/projetos/python/retrieval_augmented_generation/modelos/doutorado/secoes_contrato_rotulos_classificacao_texto_v1/runs/Sep24_19-46-02_mace16.local', 'logging_strategy': 'steps', 'logging_first_step': False, 'logging_steps': 500, 'logging_nan_inf_filter': True, 'save_strategy': 'epoch', 'save_steps': 500, 'save_total_limit': None, 'save_safetensors': True, 'save_on_each_node': False, 'save_only_model': False, 'restore_callback_states_from_checkpoint': False, 'no_cuda': False, 'use_cpu': False, 'use_mps_device': False, 'seed': 42, 'data_seed': None, 'jit_mode_eval': False, 'use_ipex': False, 'bf16': False, 'fp16': False, 'fp16_opt_level': 'O1', 'half_precision_backend': 'auto', 'bf16_full_eval': False, 'fp16_full_eval': False, 'tf32': None, 'local_rank': 0, 'ddp_backend': None, 'tpu_num_cores': None, 'tpu_metrics_debug': False, 'debug': [], 'dataloader_drop_last': False, 'eval_steps': None, 'dataloader_num_workers': 0, 'dataloader_prefetch_factor': None, 'past_index': -1, 'run_name': 'secoes_contrato_rotulos_classificacao_texto_v1', 'disable_tqdm': False, 'remove_unused_columns': True, 'label_names': None, 'load_best_model_at_end': True, 'metric_for_best_model': 'loss', 'greater_is_better': False, 'ignore_data_skip': False, 'fsdp': [], 'fsdp_min_num_params': 0, 'fsdp_config': {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}, 'fsdp_transformer_layer_cls_to_wrap': None, 'accelerator_config': {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}, 'deepspeed': None, 'label_smoothing_factor': 0.0, 'optim': 'adamw_torch', 'optim_args': None, 'adafactor': False, 'group_by_length': False, 'length_column_name': 'length', 'report_to': ['wandb'], 'ddp_find_unused_parameters': None, 'ddp_bucket_cap_mb': None, 'ddp_broadcast_buffers': None, 'dataloader_pin_memory': True, 'dataloader_persistent_workers': False, 'skip_memory_metrics': True, 'use_legacy_prediction_loop': False, 'push_to_hub': True, 'resume_from_checkpoint': None, 'hub_model_id': None, 'hub_strategy': 'every_save', 'hub_token': '<HUB_TOKEN>', 'hub_private_repo': False, 'hub_always_push': False, 'gradient_checkpointing': False, 'gradient_checkpointing_kwargs': None, 'include_inputs_for_metrics': False, 'eval_do_concat_batches': True, 'fp16_backend': 'auto', 'evaluation_strategy': None, 'push_to_hub_model_id': None, 'push_to_hub_organization': None, 'push_to_hub_token': '<PUSH_TO_HUB_TOKEN>', 'mp_parameters': '', 'auto_find_batch_size': False, 'full_determinism': False, 'torchdynamo': None, 'ray_scope': 'last', 'ddp_timeout': 1800, 'torch_compile': False, 'torch_compile_backend': None, 'torch_compile_mode': None, 'dispatch_batches': None, 'split_batches': None, 'include_tokens_per_second': False, 'include_num_input_tokens_seen': False, 'neftune_noise_alpha': None, 'optim_target_modules': None, 'batch_eval_metrics': False, 'eval_on_start': False, 'eval_use_gather_object': False}
+2024-09-24 19:46:05,899 INFO    MainThread:48218 [wandb_config.py:__setitem__():151] config set model/num_parameters = 66955010 - <bound method Run._config_callback of <wandb.sdk.wandb_run.Run object at 0x13c481490>>
+2024-09-24 19:46:05,899 INFO    MainThread:48218 [wandb_run.py:_config_callback():1382] config_cb model/num_parameters 66955010 None
+2024-09-24 19:50:37,196 INFO    MainThread:48218 [jupyter.py:save_ipynb():372] not saving jupyter notebook
+2024-09-24 19:50:37,197 INFO    MainThread:48218 [wandb_init.py:_pause_backend():440] pausing backend
+2024-09-24 19:51:01,663 INFO    MainThread:48218 [wandb_init.py:_resume_backend():445] resuming backend
+2024-09-24 19:51:05,284 INFO    MainThread:48218 [wandb_run.py:_config_callback():1382] config_cb None None {'vocab_size': 30522, 'max_position_embeddings': 512, 'sinusoidal_pos_embds': False, 'n_layers': 6, 'n_heads': 12, 'dim': 768, 'hidden_dim': 3072, 'dropout': 0.1, 'attention_dropout': 0.1, 'activation': 'gelu', 'initializer_range': 0.02, 'qa_dropout': 0.1, 'seq_classif_dropout': 0.2, 'return_dict': True, 'output_hidden_states': False, 'output_attentions': False, 'torchscript': False, 'torch_dtype': None, 'use_bfloat16': False, 'tf_legacy_loss': False, 'pruned_heads': {}, 'tie_word_embeddings': True, 'chunk_size_feed_forward': 0, 'is_encoder_decoder': False, 'is_decoder': False, 'cross_attention_hidden_size': None, 'add_cross_attention': False, 'tie_encoder_decoder': False, 'max_length': 20, 'min_length': 0, 'do_sample': False, 'early_stopping': False, 'num_beams': 1, 'num_beam_groups': 1, 'diversity_penalty': 0.0, 'temperature': 1.0, 'top_k': 50, 'top_p': 1.0, 'typical_p': 1.0, 'repetition_penalty': 1.0, 'length_penalty': 1.0, 'no_repeat_ngram_size': 0, 'encoder_no_repeat_ngram_size': 0, 'bad_words_ids': None, 'num_return_sequences': 1, 'output_scores': False, 'return_dict_in_generate': False, 'forced_bos_token_id': None, 'forced_eos_token_id': None, 'remove_invalid_values': False, 'exponential_decay_length_penalty': None, 'suppress_tokens': None, 'begin_suppress_tokens': None, 'architectures': ['DistilBertForMaskedLM'], 'finetuning_task': None, 'id2label': {0: 'objeto', 1: 'outros'}, 'label2id': {'objeto': 0, 'outros': 1}, 'tokenizer_class': None, 'prefix': None, 'bos_token_id': None, 'pad_token_id': 0, 'eos_token_id': None, 'sep_token_id': None, 'decoder_start_token_id': None, 'task_specific_params': None, 'problem_type': None, '_name_or_path': 'distilbert/distilbert-base-uncased', 'transformers_version': '4.44.2', 'model_type': 'distilbert', 'tie_weights_': True, 'output_dir': '/Users/marcelovidigal/Library/CloudStorage/GoogleDrive-marcelovidigal@gmail.com/Meu Drive/projetos/python/retrieval_augmented_generation/modelos/doutorado/secoes_contrato_rotulos_classificacao_texto_v1', 'overwrite_output_dir': False, 'do_train': False, 'do_eval': True, 'do_predict': False, 'eval_strategy': 'epoch', 'prediction_loss_only': False, 'per_device_train_batch_size': 32, 'per_device_eval_batch_size': 32, 'per_gpu_train_batch_size': None, 'per_gpu_eval_batch_size': None, 'gradient_accumulation_steps': 1, 'eval_accumulation_steps': None, 'eval_delay': 0, 'torch_empty_cache_steps': None, 'learning_rate': 1e-05, 'weight_decay': 0.01, 'adam_beta1': 0.9, 'adam_beta2': 0.999, 'adam_epsilon': 1e-08, 'max_grad_norm': 1.0, 'num_train_epochs': 50, 'max_steps': -1, 'lr_scheduler_type': 'linear', 'lr_scheduler_kwargs': {}, 'warmup_ratio': 0.0, 'warmup_steps': 0, 'log_level': 'passive', 'log_level_replica': 'warning', 'log_on_each_node': True, 'logging_dir': '/Users/marcelovidigal/Library/CloudStorage/GoogleDrive-marcelovidigal@gmail.com/Meu Drive/projetos/python/retrieval_augmented_generation/modelos/doutorado/secoes_contrato_rotulos_classificacao_texto_v1/runs/Sep24_19-51-02_mace16.local', 'logging_strategy': 'steps', 'logging_first_step': False, 'logging_steps': 500, 'logging_nan_inf_filter': True, 'save_strategy': 'epoch', 'save_steps': 500, 'save_total_limit': None, 'save_safetensors': True, 'save_on_each_node': False, 'save_only_model': False, 'restore_callback_states_from_checkpoint': False, 'no_cuda': False, 'use_cpu': False, 'use_mps_device': False, 'seed': 42, 'data_seed': None, 'jit_mode_eval': False, 'use_ipex': False, 'bf16': False, 'fp16': False, 'fp16_opt_level': 'O1', 'half_precision_backend': 'auto', 'bf16_full_eval': False, 'fp16_full_eval': False, 'tf32': None, 'local_rank': 0, 'ddp_backend': None, 'tpu_num_cores': None, 'tpu_metrics_debug': False, 'debug': [], 'dataloader_drop_last': False, 'eval_steps': None, 'dataloader_num_workers': 0, 'dataloader_prefetch_factor': None, 'past_index': -1, 'run_name': 'secoes_contrato_rotulos_classificacao_texto_v1', 'disable_tqdm': False, 'remove_unused_columns': True, 'label_names': None, 'load_best_model_at_end': True, 'metric_for_best_model': 'loss', 'greater_is_better': False, 'ignore_data_skip': False, 'fsdp': [], 'fsdp_min_num_params': 0, 'fsdp_config': {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}, 'fsdp_transformer_layer_cls_to_wrap': None, 'accelerator_config': {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}, 'deepspeed': None, 'label_smoothing_factor': 0.0, 'optim': 'adamw_torch', 'optim_args': None, 'adafactor': False, 'group_by_length': False, 'length_column_name': 'length', 'report_to': ['wandb'], 'ddp_find_unused_parameters': None, 'ddp_bucket_cap_mb': None, 'ddp_broadcast_buffers': None, 'dataloader_pin_memory': True, 'dataloader_persistent_workers': False, 'skip_memory_metrics': True, 'use_legacy_prediction_loop': False, 'push_to_hub': True, 'resume_from_checkpoint': None, 'hub_model_id': None, 'hub_strategy': 'every_save', 'hub_token': '<HUB_TOKEN>', 'hub_private_repo': False, 'hub_always_push': False, 'gradient_checkpointing': False, 'gradient_checkpointing_kwargs': None, 'include_inputs_for_metrics': False, 'eval_do_concat_batches': True, 'fp16_backend': 'auto', 'evaluation_strategy': None, 'push_to_hub_model_id': None, 'push_to_hub_organization': None, 'push_to_hub_token': '<PUSH_TO_HUB_TOKEN>', 'mp_parameters': '', 'auto_find_batch_size': False, 'full_determinism': False, 'torchdynamo': None, 'ray_scope': 'last', 'ddp_timeout': 1800, 'torch_compile': False, 'torch_compile_backend': None, 'torch_compile_mode': None, 'dispatch_batches': None, 'split_batches': None, 'include_tokens_per_second': False, 'include_num_input_tokens_seen': False, 'neftune_noise_alpha': None, 'optim_target_modules': None, 'batch_eval_metrics': False, 'eval_on_start': False, 'eval_use_gather_object': False}
+2024-09-24 19:51:05,286 INFO    MainThread:48218 [wandb_config.py:__setitem__():151] config set model/num_parameters = 66955010 - <bound method Run._config_callback of <wandb.sdk.wandb_run.Run object at 0x13c481490>>
+2024-09-24 19:51:05,287 INFO    MainThread:48218 [wandb_run.py:_config_callback():1382] config_cb model/num_parameters 66955010 None

wandb/run-20240924_172630-x9iddikd/files/config.yaml

@@ -39,6 +39,7 @@ _wandb:
       - 7
       - 19
       - 23
+      - 62
       - 66
       4: 3.11.9
       5: 0.17.5
@@ -329,10 +330,10 @@ prediction_loss_only:
   value: false
 per_device_train_batch_size:
   desc: null
-  value: 16
+  value: 32
 per_device_eval_batch_size:
   desc: null
-  value: 16
+  value: 32
 per_gpu_train_batch_size:
   desc: null
   value: null
@@ -353,7 +354,7 @@ torch_empty_cache_steps:
   value: null
 learning_rate:
   desc: null
-  value: 2.0e-05
+  value: 1.0e-05
 weight_decay:
   desc: null
   value: 0.01
@@ -371,7 +372,7 @@ max_grad_norm:
   value: 1.0
 num_train_epochs:
   desc: null
-  value: 5
+  value: 50
 max_steps:
   desc: null
   value: -1
@@ -399,7 +400,7 @@ log_on_each_node:
 logging_dir:
   desc: null
   value: /Users/marcelovidigal/Library/CloudStorage/GoogleDrive-marcelovidigal@gmail.com/Meu
-    Drive/projetos/python/retrieval_augmented_generation/modelos/doutorado/secoes_contrato_rotulos_classificacao_texto_v1/runs/Sep24_17-26-48_mace16.local
+    Drive/projetos/python/retrieval_augmented_generation/modelos/doutorado/secoes_contrato_rotulos_classificacao_texto_v1/runs/Sep24_19-51-02_mace16.local
 logging_strategy:
   desc: null
   value: steps

wandb/run-20240924_172630-x9iddikd/files/output.log

@@ -26,3 +26,8 @@ You should probably TRAIN this model on a down-stream task to be able to use it
 {'loss': 0.0672, 'grad_norm': 1.1029362678527832, 'learning_rate': 4.000000000000001e-06, 'epoch': 4.0}
 {'eval_loss': 0.36123067140579224, 'eval_accuracy': 0.925, 'eval_runtime': 26.675, 'eval_samples_per_second': 37.488, 'eval_steps_per_second': 2.362, 'epoch': 4.0}
 {'eval_loss': 0.3963741362094879, 'eval_accuracy': 0.926, 'eval_runtime': 25.9784, 'eval_samples_per_second': 38.493, 'eval_steps_per_second': 2.425, 'epoch': 5.0}
+{'train_runtime': 8026.8642, 'train_samples_per_second': 2.492, 'train_steps_per_second': 0.156, 'train_loss': 0.11480112991333008, 'epoch': 5.0}
+Some weights of DistilBertForSequenceClassification were not initialized from the model checkpoint at distilbert/distilbert-base-uncased and are newly initialized: ['classifier.bias', 'classifier.weight', 'pre_classifier.bias', 'pre_classifier.weight']
+You should probably TRAIN this model on a down-stream task to be able to use it for predictions and inference.
+Some weights of DistilBertForSequenceClassification were not initialized from the model checkpoint at distilbert/distilbert-base-uncased and are newly initialized: ['classifier.bias', 'classifier.weight', 'pre_classifier.bias', 'pre_classifier.weight']
+You should probably TRAIN this model on a down-stream task to be able to use it for predictions and inference.

wandb/run-20240924_172630-x9iddikd/files/wandb-summary.json

@@ -1 +1 @@
-{"eval/loss": 0.3963741362094879, "eval/accuracy": 0.926, "eval/runtime": 25.9784, "eval/samples_per_second": 38.493, "eval/steps_per_second": 2.425, "train/epoch": 5.0, "train/global_step": 1250, "_timestamp": 1727217637.607487, "_runtime": 8046.734577894211, "_step": 7, "train/loss": 0.0672, "train/grad_norm": 1.1029362678527832, "train/learning_rate": 4.000000000000001e-06, "train_runtime": 8026.8642, "train_samples_per_second": 2.492, "train_steps_per_second": 0.156, "total_flos": 2396475988298112.0, "train_loss": 0.11480112991333008}
+{"eval/loss": 0.17208045721054077, "eval/accuracy": 0.939, "eval/runtime": 40.1609, "eval/samples_per_second": 24.9, "eval/steps_per_second": 0.797, "train/epoch": 1.0, "train/global_step": 125, "_timestamp": 1727220006.6581702, "_runtime": 10415.785261154175, "_step": 8, "train/loss": 0.0672, "train/grad_norm": 1.1029362678527832, "train/learning_rate": 4.000000000000001e-06, "train_runtime": 8026.8642, "train_samples_per_second": 2.492, "train_steps_per_second": 0.156, "total_flos": 2396475988298112.0, "train_loss": 0.11480112991333008}

wandb/run-20240924_172630-x9iddikd/logs/debug.log

@@ -55,3 +55,21 @@ config: {}
 2024-09-24 17:26:50,737 INFO    MainThread:48218 [wandb_run.py:_config_callback():1382] config_cb None None {'vocab_size': 30522, 'max_position_embeddings': 512, 'sinusoidal_pos_embds': False, 'n_layers': 6, 'n_heads': 12, 'dim': 768, 'hidden_dim': 3072, 'dropout': 0.1, 'attention_dropout': 0.1, 'activation': 'gelu', 'initializer_range': 0.02, 'qa_dropout': 0.1, 'seq_classif_dropout': 0.2, 'return_dict': True, 'output_hidden_states': False, 'output_attentions': False, 'torchscript': False, 'torch_dtype': None, 'use_bfloat16': False, 'tf_legacy_loss': False, 'pruned_heads': {}, 'tie_word_embeddings': True, 'chunk_size_feed_forward': 0, 'is_encoder_decoder': False, 'is_decoder': False, 'cross_attention_hidden_size': None, 'add_cross_attention': False, 'tie_encoder_decoder': False, 'max_length': 20, 'min_length': 0, 'do_sample': False, 'early_stopping': False, 'num_beams': 1, 'num_beam_groups': 1, 'diversity_penalty': 0.0, 'temperature': 1.0, 'top_k': 50, 'top_p': 1.0, 'typical_p': 1.0, 'repetition_penalty': 1.0, 'length_penalty': 1.0, 'no_repeat_ngram_size': 0, 'encoder_no_repeat_ngram_size': 0, 'bad_words_ids': None, 'num_return_sequences': 1, 'output_scores': False, 'return_dict_in_generate': False, 'forced_bos_token_id': None, 'forced_eos_token_id': None, 'remove_invalid_values': False, 'exponential_decay_length_penalty': None, 'suppress_tokens': None, 'begin_suppress_tokens': None, 'architectures': ['DistilBertForMaskedLM'], 'finetuning_task': None, 'id2label': {0: 'objeto', 1: 'outros'}, 'label2id': {'objeto': 0, 'outros': 1}, 'tokenizer_class': None, 'prefix': None, 'bos_token_id': None, 'pad_token_id': 0, 'eos_token_id': None, 'sep_token_id': None, 'decoder_start_token_id': None, 'task_specific_params': None, 'problem_type': None, '_name_or_path': 'distilbert/distilbert-base-uncased', 'transformers_version': '4.44.2', 'model_type': 'distilbert', 'tie_weights_': True, 'output_dir': '/Users/marcelovidigal/Library/CloudStorage/GoogleDrive-marcelovidigal@gmail.com/Meu Drive/projetos/python/retrieval_augmented_generation/modelos/doutorado/secoes_contrato_rotulos_classificacao_texto_v1', 'overwrite_output_dir': False, 'do_train': False, 'do_eval': True, 'do_predict': False, 'eval_strategy': 'epoch', 'prediction_loss_only': False, 'per_device_train_batch_size': 16, 'per_device_eval_batch_size': 16, 'per_gpu_train_batch_size': None, 'per_gpu_eval_batch_size': None, 'gradient_accumulation_steps': 1, 'eval_accumulation_steps': None, 'eval_delay': 0, 'torch_empty_cache_steps': None, 'learning_rate': 2e-05, 'weight_decay': 0.01, 'adam_beta1': 0.9, 'adam_beta2': 0.999, 'adam_epsilon': 1e-08, 'max_grad_norm': 1.0, 'num_train_epochs': 5, 'max_steps': -1, 'lr_scheduler_type': 'linear', 'lr_scheduler_kwargs': {}, 'warmup_ratio': 0.0, 'warmup_steps': 0, 'log_level': 'passive', 'log_level_replica': 'warning', 'log_on_each_node': True, 'logging_dir': '/Users/marcelovidigal/Library/CloudStorage/GoogleDrive-marcelovidigal@gmail.com/Meu Drive/projetos/python/retrieval_augmented_generation/modelos/doutorado/secoes_contrato_rotulos_classificacao_texto_v1/runs/Sep24_17-26-48_mace16.local', 'logging_strategy': 'steps', 'logging_first_step': False, 'logging_steps': 500, 'logging_nan_inf_filter': True, 'save_strategy': 'epoch', 'save_steps': 500, 'save_total_limit': None, 'save_safetensors': True, 'save_on_each_node': False, 'save_only_model': False, 'restore_callback_states_from_checkpoint': False, 'no_cuda': False, 'use_cpu': False, 'use_mps_device': False, 'seed': 42, 'data_seed': None, 'jit_mode_eval': False, 'use_ipex': False, 'bf16': False, 'fp16': False, 'fp16_opt_level': 'O1', 'half_precision_backend': 'auto', 'bf16_full_eval': False, 'fp16_full_eval': False, 'tf32': None, 'local_rank': 0, 'ddp_backend': None, 'tpu_num_cores': None, 'tpu_metrics_debug': False, 'debug': [], 'dataloader_drop_last': False, 'eval_steps': None, 'dataloader_num_workers': 0, 'dataloader_prefetch_factor': None, 'past_index': -1, 'run_name': 'secoes_contrato_rotulos_classificacao_texto_v1', 'disable_tqdm': False, 'remove_unused_columns': True, 'label_names': None, 'load_best_model_at_end': True, 'metric_for_best_model': 'loss', 'greater_is_better': False, 'ignore_data_skip': False, 'fsdp': [], 'fsdp_min_num_params': 0, 'fsdp_config': {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}, 'fsdp_transformer_layer_cls_to_wrap': None, 'accelerator_config': {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}, 'deepspeed': None, 'label_smoothing_factor': 0.0, 'optim': 'adamw_torch', 'optim_args': None, 'adafactor': False, 'group_by_length': False, 'length_column_name': 'length', 'report_to': ['wandb'], 'ddp_find_unused_parameters': None, 'ddp_bucket_cap_mb': None, 'ddp_broadcast_buffers': None, 'dataloader_pin_memory': True, 'dataloader_persistent_workers': False, 'skip_memory_metrics': True, 'use_legacy_prediction_loop': False, 'push_to_hub': True, 'resume_from_checkpoint': None, 'hub_model_id': None, 'hub_strategy': 'every_save', 'hub_token': '<HUB_TOKEN>', 'hub_private_repo': False, 'hub_always_push': False, 'gradient_checkpointing': False, 'gradient_checkpointing_kwargs': None, 'include_inputs_for_metrics': False, 'eval_do_concat_batches': True, 'fp16_backend': 'auto', 'evaluation_strategy': None, 'push_to_hub_model_id': None, 'push_to_hub_organization': None, 'push_to_hub_token': '<PUSH_TO_HUB_TOKEN>', 'mp_parameters': '', 'auto_find_batch_size': False, 'full_determinism': False, 'torchdynamo': None, 'ray_scope': 'last', 'ddp_timeout': 1800, 'torch_compile': False, 'torch_compile_backend': None, 'torch_compile_mode': None, 'dispatch_batches': None, 'split_batches': None, 'include_tokens_per_second': False, 'include_num_input_tokens_seen': False, 'neftune_noise_alpha': None, 'optim_target_modules': None, 'batch_eval_metrics': False, 'eval_on_start': False, 'eval_use_gather_object': False}
 2024-09-24 17:26:50,740 INFO    MainThread:48218 [wandb_config.py:__setitem__():151] config set model/num_parameters = 66955010 - <bound method Run._config_callback of <wandb.sdk.wandb_run.Run object at 0x13c481490>>
 2024-09-24 17:26:50,740 INFO    MainThread:48218 [wandb_run.py:_config_callback():1382] config_cb model/num_parameters 66955010 None
+2024-09-24 19:40:46,713 INFO    MainThread:48218 [jupyter.py:save_ipynb():372] not saving jupyter notebook
+2024-09-24 19:40:46,722 INFO    MainThread:48218 [wandb_init.py:_pause_backend():440] pausing backend
+2024-09-24 19:40:46,781 INFO    MainThread:48218 [wandb_init.py:_resume_backend():445] resuming backend
+2024-09-24 19:40:46,802 INFO    MainThread:48218 [jupyter.py:save_ipynb():372] not saving jupyter notebook
+2024-09-24 19:40:46,802 INFO    MainThread:48218 [wandb_init.py:_pause_backend():440] pausing backend
+2024-09-24 19:45:19,097 INFO    MainThread:48218 [wandb_init.py:_resume_backend():445] resuming backend
+2024-09-24 19:45:19,112 INFO    MainThread:48218 [jupyter.py:save_ipynb():372] not saving jupyter notebook
+2024-09-24 19:45:19,117 INFO    MainThread:48218 [wandb_init.py:_pause_backend():440] pausing backend
+2024-09-24 19:46:01,642 INFO    MainThread:48218 [wandb_init.py:_resume_backend():445] resuming backend
+2024-09-24 19:46:05,896 INFO    MainThread:48218 [wandb_run.py:_config_callback():1382] config_cb None None {'vocab_size': 30522, 'max_position_embeddings': 512, 'sinusoidal_pos_embds': False, 'n_layers': 6, 'n_heads': 12, 'dim': 768, 'hidden_dim': 3072, 'dropout': 0.1, 'attention_dropout': 0.1, 'activation': 'gelu', 'initializer_range': 0.02, 'qa_dropout': 0.1, 'seq_classif_dropout': 0.2, 'return_dict': True, 'output_hidden_states': False, 'output_attentions': False, 'torchscript': False, 'torch_dtype': None, 'use_bfloat16': False, 'tf_legacy_loss': False, 'pruned_heads': {}, 'tie_word_embeddings': True, 'chunk_size_feed_forward': 0, 'is_encoder_decoder': False, 'is_decoder': False, 'cross_attention_hidden_size': None, 'add_cross_attention': False, 'tie_encoder_decoder': False, 'max_length': 20, 'min_length': 0, 'do_sample': False, 'early_stopping': False, 'num_beams': 1, 'num_beam_groups': 1, 'diversity_penalty': 0.0, 'temperature': 1.0, 'top_k': 50, 'top_p': 1.0, 'typical_p': 1.0, 'repetition_penalty': 1.0, 'length_penalty': 1.0, 'no_repeat_ngram_size': 0, 'encoder_no_repeat_ngram_size': 0, 'bad_words_ids': None, 'num_return_sequences': 1, 'output_scores': False, 'return_dict_in_generate': False, 'forced_bos_token_id': None, 'forced_eos_token_id': None, 'remove_invalid_values': False, 'exponential_decay_length_penalty': None, 'suppress_tokens': None, 'begin_suppress_tokens': None, 'architectures': ['DistilBertForMaskedLM'], 'finetuning_task': None, 'id2label': {0: 'objeto', 1: 'outros'}, 'label2id': {'objeto': 0, 'outros': 1}, 'tokenizer_class': None, 'prefix': None, 'bos_token_id': None, 'pad_token_id': 0, 'eos_token_id': None, 'sep_token_id': None, 'decoder_start_token_id': None, 'task_specific_params': None, 'problem_type': None, '_name_or_path': 'distilbert/distilbert-base-uncased', 'transformers_version': '4.44.2', 'model_type': 'distilbert', 'tie_weights_': True, 'output_dir': '/Users/marcelovidigal/Library/CloudStorage/GoogleDrive-marcelovidigal@gmail.com/Meu Drive/projetos/python/retrieval_augmented_generation/modelos/doutorado/secoes_contrato_rotulos_classificacao_texto_v1', 'overwrite_output_dir': False, 'do_train': False, 'do_eval': True, 'do_predict': False, 'eval_strategy': 'epoch', 'prediction_loss_only': False, 'per_device_train_batch_size': 32, 'per_device_eval_batch_size': 32, 'per_gpu_train_batch_size': None, 'per_gpu_eval_batch_size': None, 'gradient_accumulation_steps': 1, 'eval_accumulation_steps': None, 'eval_delay': 0, 'torch_empty_cache_steps': None, 'learning_rate': 1e-06, 'weight_decay': 0.001, 'adam_beta1': 0.9, 'adam_beta2': 0.999, 'adam_epsilon': 1e-08, 'max_grad_norm': 1.0, 'num_train_epochs': 50, 'max_steps': -1, 'lr_scheduler_type': 'linear', 'lr_scheduler_kwargs': {}, 'warmup_ratio': 0.0, 'warmup_steps': 0, 'log_level': 'passive', 'log_level_replica': 'warning', 'log_on_each_node': True, 'logging_dir': '/Users/marcelovidigal/Library/CloudStorage/GoogleDrive-marcelovidigal@gmail.com/Meu Drive/projetos/python/retrieval_augmented_generation/modelos/doutorado/secoes_contrato_rotulos_classificacao_texto_v1/runs/Sep24_19-46-02_mace16.local', 'logging_strategy': 'steps', 'logging_first_step': False, 'logging_steps': 500, 'logging_nan_inf_filter': True, 'save_strategy': 'epoch', 'save_steps': 500, 'save_total_limit': None, 'save_safetensors': True, 'save_on_each_node': False, 'save_only_model': False, 'restore_callback_states_from_checkpoint': False, 'no_cuda': False, 'use_cpu': False, 'use_mps_device': False, 'seed': 42, 'data_seed': None, 'jit_mode_eval': False, 'use_ipex': False, 'bf16': False, 'fp16': False, 'fp16_opt_level': 'O1', 'half_precision_backend': 'auto', 'bf16_full_eval': False, 'fp16_full_eval': False, 'tf32': None, 'local_rank': 0, 'ddp_backend': None, 'tpu_num_cores': None, 'tpu_metrics_debug': False, 'debug': [], 'dataloader_drop_last': False, 'eval_steps': None, 'dataloader_num_workers': 0, 'dataloader_prefetch_factor': None, 'past_index': -1, 'run_name': 'secoes_contrato_rotulos_classificacao_texto_v1', 'disable_tqdm': False, 'remove_unused_columns': True, 'label_names': None, 'load_best_model_at_end': True, 'metric_for_best_model': 'loss', 'greater_is_better': False, 'ignore_data_skip': False, 'fsdp': [], 'fsdp_min_num_params': 0, 'fsdp_config': {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}, 'fsdp_transformer_layer_cls_to_wrap': None, 'accelerator_config': {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}, 'deepspeed': None, 'label_smoothing_factor': 0.0, 'optim': 'adamw_torch', 'optim_args': None, 'adafactor': False, 'group_by_length': False, 'length_column_name': 'length', 'report_to': ['wandb'], 'ddp_find_unused_parameters': None, 'ddp_bucket_cap_mb': None, 'ddp_broadcast_buffers': None, 'dataloader_pin_memory': True, 'dataloader_persistent_workers': False, 'skip_memory_metrics': True, 'use_legacy_prediction_loop': False, 'push_to_hub': True, 'resume_from_checkpoint': None, 'hub_model_id': None, 'hub_strategy': 'every_save', 'hub_token': '<HUB_TOKEN>', 'hub_private_repo': False, 'hub_always_push': False, 'gradient_checkpointing': False, 'gradient_checkpointing_kwargs': None, 'include_inputs_for_metrics': False, 'eval_do_concat_batches': True, 'fp16_backend': 'auto', 'evaluation_strategy': None, 'push_to_hub_model_id': None, 'push_to_hub_organization': None, 'push_to_hub_token': '<PUSH_TO_HUB_TOKEN>', 'mp_parameters': '', 'auto_find_batch_size': False, 'full_determinism': False, 'torchdynamo': None, 'ray_scope': 'last', 'ddp_timeout': 1800, 'torch_compile': False, 'torch_compile_backend': None, 'torch_compile_mode': None, 'dispatch_batches': None, 'split_batches': None, 'include_tokens_per_second': False, 'include_num_input_tokens_seen': False, 'neftune_noise_alpha': None, 'optim_target_modules': None, 'batch_eval_metrics': False, 'eval_on_start': False, 'eval_use_gather_object': False}
+2024-09-24 19:46:05,899 INFO    MainThread:48218 [wandb_config.py:__setitem__():151] config set model/num_parameters = 66955010 - <bound method Run._config_callback of <wandb.sdk.wandb_run.Run object at 0x13c481490>>
+2024-09-24 19:46:05,899 INFO    MainThread:48218 [wandb_run.py:_config_callback():1382] config_cb model/num_parameters 66955010 None
+2024-09-24 19:50:37,196 INFO    MainThread:48218 [jupyter.py:save_ipynb():372] not saving jupyter notebook
+2024-09-24 19:50:37,197 INFO    MainThread:48218 [wandb_init.py:_pause_backend():440] pausing backend
+2024-09-24 19:51:01,663 INFO    MainThread:48218 [wandb_init.py:_resume_backend():445] resuming backend
+2024-09-24 19:51:05,284 INFO    MainThread:48218 [wandb_run.py:_config_callback():1382] config_cb None None {'vocab_size': 30522, 'max_position_embeddings': 512, 'sinusoidal_pos_embds': False, 'n_layers': 6, 'n_heads': 12, 'dim': 768, 'hidden_dim': 3072, 'dropout': 0.1, 'attention_dropout': 0.1, 'activation': 'gelu', 'initializer_range': 0.02, 'qa_dropout': 0.1, 'seq_classif_dropout': 0.2, 'return_dict': True, 'output_hidden_states': False, 'output_attentions': False, 'torchscript': False, 'torch_dtype': None, 'use_bfloat16': False, 'tf_legacy_loss': False, 'pruned_heads': {}, 'tie_word_embeddings': True, 'chunk_size_feed_forward': 0, 'is_encoder_decoder': False, 'is_decoder': False, 'cross_attention_hidden_size': None, 'add_cross_attention': False, 'tie_encoder_decoder': False, 'max_length': 20, 'min_length': 0, 'do_sample': False, 'early_stopping': False, 'num_beams': 1, 'num_beam_groups': 1, 'diversity_penalty': 0.0, 'temperature': 1.0, 'top_k': 50, 'top_p': 1.0, 'typical_p': 1.0, 'repetition_penalty': 1.0, 'length_penalty': 1.0, 'no_repeat_ngram_size': 0, 'encoder_no_repeat_ngram_size': 0, 'bad_words_ids': None, 'num_return_sequences': 1, 'output_scores': False, 'return_dict_in_generate': False, 'forced_bos_token_id': None, 'forced_eos_token_id': None, 'remove_invalid_values': False, 'exponential_decay_length_penalty': None, 'suppress_tokens': None, 'begin_suppress_tokens': None, 'architectures': ['DistilBertForMaskedLM'], 'finetuning_task': None, 'id2label': {0: 'objeto', 1: 'outros'}, 'label2id': {'objeto': 0, 'outros': 1}, 'tokenizer_class': None, 'prefix': None, 'bos_token_id': None, 'pad_token_id': 0, 'eos_token_id': None, 'sep_token_id': None, 'decoder_start_token_id': None, 'task_specific_params': None, 'problem_type': None, '_name_or_path': 'distilbert/distilbert-base-uncased', 'transformers_version': '4.44.2', 'model_type': 'distilbert', 'tie_weights_': True, 'output_dir': '/Users/marcelovidigal/Library/CloudStorage/GoogleDrive-marcelovidigal@gmail.com/Meu Drive/projetos/python/retrieval_augmented_generation/modelos/doutorado/secoes_contrato_rotulos_classificacao_texto_v1', 'overwrite_output_dir': False, 'do_train': False, 'do_eval': True, 'do_predict': False, 'eval_strategy': 'epoch', 'prediction_loss_only': False, 'per_device_train_batch_size': 32, 'per_device_eval_batch_size': 32, 'per_gpu_train_batch_size': None, 'per_gpu_eval_batch_size': None, 'gradient_accumulation_steps': 1, 'eval_accumulation_steps': None, 'eval_delay': 0, 'torch_empty_cache_steps': None, 'learning_rate': 1e-05, 'weight_decay': 0.01, 'adam_beta1': 0.9, 'adam_beta2': 0.999, 'adam_epsilon': 1e-08, 'max_grad_norm': 1.0, 'num_train_epochs': 50, 'max_steps': -1, 'lr_scheduler_type': 'linear', 'lr_scheduler_kwargs': {}, 'warmup_ratio': 0.0, 'warmup_steps': 0, 'log_level': 'passive', 'log_level_replica': 'warning', 'log_on_each_node': True, 'logging_dir': '/Users/marcelovidigal/Library/CloudStorage/GoogleDrive-marcelovidigal@gmail.com/Meu Drive/projetos/python/retrieval_augmented_generation/modelos/doutorado/secoes_contrato_rotulos_classificacao_texto_v1/runs/Sep24_19-51-02_mace16.local', 'logging_strategy': 'steps', 'logging_first_step': False, 'logging_steps': 500, 'logging_nan_inf_filter': True, 'save_strategy': 'epoch', 'save_steps': 500, 'save_total_limit': None, 'save_safetensors': True, 'save_on_each_node': False, 'save_only_model': False, 'restore_callback_states_from_checkpoint': False, 'no_cuda': False, 'use_cpu': False, 'use_mps_device': False, 'seed': 42, 'data_seed': None, 'jit_mode_eval': False, 'use_ipex': False, 'bf16': False, 'fp16': False, 'fp16_opt_level': 'O1', 'half_precision_backend': 'auto', 'bf16_full_eval': False, 'fp16_full_eval': False, 'tf32': None, 'local_rank': 0, 'ddp_backend': None, 'tpu_num_cores': None, 'tpu_metrics_debug': False, 'debug': [], 'dataloader_drop_last': False, 'eval_steps': None, 'dataloader_num_workers': 0, 'dataloader_prefetch_factor': None, 'past_index': -1, 'run_name': 'secoes_contrato_rotulos_classificacao_texto_v1', 'disable_tqdm': False, 'remove_unused_columns': True, 'label_names': None, 'load_best_model_at_end': True, 'metric_for_best_model': 'loss', 'greater_is_better': False, 'ignore_data_skip': False, 'fsdp': [], 'fsdp_min_num_params': 0, 'fsdp_config': {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}, 'fsdp_transformer_layer_cls_to_wrap': None, 'accelerator_config': {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}, 'deepspeed': None, 'label_smoothing_factor': 0.0, 'optim': 'adamw_torch', 'optim_args': None, 'adafactor': False, 'group_by_length': False, 'length_column_name': 'length', 'report_to': ['wandb'], 'ddp_find_unused_parameters': None, 'ddp_bucket_cap_mb': None, 'ddp_broadcast_buffers': None, 'dataloader_pin_memory': True, 'dataloader_persistent_workers': False, 'skip_memory_metrics': True, 'use_legacy_prediction_loop': False, 'push_to_hub': True, 'resume_from_checkpoint': None, 'hub_model_id': None, 'hub_strategy': 'every_save', 'hub_token': '<HUB_TOKEN>', 'hub_private_repo': False, 'hub_always_push': False, 'gradient_checkpointing': False, 'gradient_checkpointing_kwargs': None, 'include_inputs_for_metrics': False, 'eval_do_concat_batches': True, 'fp16_backend': 'auto', 'evaluation_strategy': None, 'push_to_hub_model_id': None, 'push_to_hub_organization': None, 'push_to_hub_token': '<PUSH_TO_HUB_TOKEN>', 'mp_parameters': '', 'auto_find_batch_size': False, 'full_determinism': False, 'torchdynamo': None, 'ray_scope': 'last', 'ddp_timeout': 1800, 'torch_compile': False, 'torch_compile_backend': None, 'torch_compile_mode': None, 'dispatch_batches': None, 'split_batches': None, 'include_tokens_per_second': False, 'include_num_input_tokens_seen': False, 'neftune_noise_alpha': None, 'optim_target_modules': None, 'batch_eval_metrics': False, 'eval_on_start': False, 'eval_use_gather_object': False}
+2024-09-24 19:51:05,286 INFO    MainThread:48218 [wandb_config.py:__setitem__():151] config set model/num_parameters = 66955010 - <bound method Run._config_callback of <wandb.sdk.wandb_run.Run object at 0x13c481490>>
+2024-09-24 19:51:05,287 INFO    MainThread:48218 [wandb_run.py:_config_callback():1382] config_cb model/num_parameters 66955010 None