Training in progress, epoch 4

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9a46b31286363bfff34a61f058fdeb17c4332abbcbc9258b7dad384971cb0c20
+oid sha256:739b8ecb468d2ad4f97c4976018339aa8d0fd95bbca80100cff676ceac0aa080
 size 596114452

runs/Mar06_15-36-27_64d026e37c1e/events.out.tfevents.1709739388.64d026e37c1e.34.1

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:10be525aec7a18c3ee177737e4c8a6319142cbac826c19b085a9b63679820151
-size 7297
+oid sha256:791b09c3b4de8e56b419c3da16da787c29901f846787ef9f1a05e13bc057f902
+size 7967

wandb/debug-internal.log

@@ -227,3 +227,40 @@
 2024-03-06 15:38:18,278 DEBUG   HandlerThread:135 [handler.py:handle_request():146] handle_request: keepalive
 2024-03-06 15:38:22,738 DEBUG   HandlerThread:135 [handler.py:handle_request():146] handle_request: status_report
 2024-03-06 15:38:23,279 DEBUG   HandlerThread:135 [handler.py:handle_request():146] handle_request: keepalive
+2024-03-06 15:38:26,953 DEBUG   SenderThread:135 [sender.py:send():382] send: stats
+2024-03-06 15:38:27,953 DEBUG   HandlerThread:135 [handler.py:handle_request():146] handle_request: status_report
+2024-03-06 15:38:28,280 DEBUG   HandlerThread:135 [handler.py:handle_request():146] handle_request: keepalive
+2024-03-06 15:38:32,954 DEBUG   HandlerThread:135 [handler.py:handle_request():146] handle_request: status_report
+2024-03-06 15:38:33,281 DEBUG   HandlerThread:135 [handler.py:handle_request():146] handle_request: keepalive
+2024-03-06 15:38:37,955 DEBUG   HandlerThread:135 [handler.py:handle_request():146] handle_request: status_report
+2024-03-06 15:38:38,282 DEBUG   HandlerThread:135 [handler.py:handle_request():146] handle_request: keepalive
+2024-03-06 15:38:39,248 DEBUG   HandlerThread:135 [handler.py:handle_request():146] handle_request: partial_history
+2024-03-06 15:38:39,249 DEBUG   SenderThread:135 [sender.py:send():382] send: history
+2024-03-06 15:38:39,249 DEBUG   SenderThread:135 [sender.py:send_request():409] send_request: summary_record
+2024-03-06 15:38:39,251 INFO    SenderThread:135 [sender.py:_save_file():1403] saving file wandb-summary.json with policy end
+2024-03-06 15:38:39,578 INFO    Thread-12 :135 [dir_watcher.py:_on_file_modified():288] file/dir modified: /kaggle/working/wandb/run-20240306_153450-l1uc7yan/files/wandb-summary.json
+2024-03-06 15:38:41,286 DEBUG   HandlerThread:135 [handler.py:handle_request():146] handle_request: partial_history
+2024-03-06 15:38:41,288 DEBUG   SenderThread:135 [sender.py:send():382] send: history
+2024-03-06 15:38:41,288 DEBUG   SenderThread:135 [sender.py:send_request():409] send_request: summary_record
+2024-03-06 15:38:41,289 INFO    SenderThread:135 [sender.py:_save_file():1403] saving file wandb-summary.json with policy end
+2024-03-06 15:38:41,580 INFO    Thread-12 :135 [dir_watcher.py:_on_file_modified():288] file/dir modified: /kaggle/working/wandb/run-20240306_153450-l1uc7yan/files/wandb-summary.json
+2024-03-06 15:38:43,289 DEBUG   HandlerThread:135 [handler.py:handle_request():146] handle_request: status_report
+2024-03-06 15:38:43,495 DEBUG   HandlerThread:135 [handler.py:handle_request():146] handle_request: keepalive
+2024-03-06 15:38:43,581 INFO    Thread-12 :135 [dir_watcher.py:_on_file_modified():288] file/dir modified: /kaggle/working/wandb/run-20240306_153450-l1uc7yan/files/output.log
+2024-03-06 15:38:48,290 DEBUG   HandlerThread:135 [handler.py:handle_request():146] handle_request: status_report
+2024-03-06 15:38:48,758 DEBUG   HandlerThread:135 [handler.py:handle_request():146] handle_request: keepalive
+2024-03-06 15:38:49,494 DEBUG   HandlerThread:135 [handler.py:handle_request():146] handle_request: pause
+2024-03-06 15:38:49,494 INFO    HandlerThread:135 [handler.py:handle_request_pause():708] stopping system metrics thread
+2024-03-06 15:38:49,494 INFO    HandlerThread:135 [system_monitor.py:finish():203] Stopping system monitor
+2024-03-06 15:38:49,495 DEBUG   SystemMonitor:135 [system_monitor.py:_start():179] Finished system metrics aggregation loop
+2024-03-06 15:38:49,495 DEBUG   SystemMonitor:135 [system_monitor.py:_start():183] Publishing last batch of metrics
+2024-03-06 15:38:49,497 INFO    HandlerThread:135 [interfaces.py:finish():202] Joined cpu monitor
+2024-03-06 15:38:49,498 INFO    HandlerThread:135 [interfaces.py:finish():202] Joined disk monitor
+2024-03-06 15:38:49,502 INFO    HandlerThread:135 [interfaces.py:finish():202] Joined gpu monitor
+2024-03-06 15:38:49,503 INFO    HandlerThread:135 [interfaces.py:finish():202] Joined memory monitor
+2024-03-06 15:38:49,503 INFO    HandlerThread:135 [interfaces.py:finish():202] Joined network monitor
+2024-03-06 15:38:49,503 DEBUG   SenderThread:135 [sender.py:send():382] send: stats
+2024-03-06 15:38:53,505 DEBUG   HandlerThread:135 [handler.py:handle_request():146] handle_request: status_report
+2024-03-06 15:38:53,759 DEBUG   HandlerThread:135 [handler.py:handle_request():146] handle_request: keepalive
+2024-03-06 15:38:58,506 DEBUG   HandlerThread:135 [handler.py:handle_request():146] handle_request: status_report
+2024-03-06 15:38:58,760 DEBUG   HandlerThread:135 [handler.py:handle_request():146] handle_request: keepalive

wandb/debug.log

@@ -36,3 +36,5 @@ config: {}
 2024-03-06 15:36:22,920 INFO    MainThread:34 [wandb_init.py:_pause_backend():437] pausing backend
 2024-03-06 15:36:26,943 INFO    MainThread:34 [wandb_init.py:_resume_backend():442] resuming backend
 2024-03-06 15:36:28,071 INFO    MainThread:34 [wandb_run.py:_config_callback():1343] config_cb None None {'return_dict': True, 'output_hidden_states': True, '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': ['BertModel'], 'finetuning_task': None, 'id2label': {0: 'Documentation Ambiguity', 1: 'Documentation Completeness', 2: 'Documentation Replicability', 3: 'Documentation Replication on Other Examples', 4: 'Inadequate Examples', 5: 'Lack of Alternative Solutions/Documentation', 6: 'Requesting (Additional) Documentation/Examples'}, 'label2id': {'Documentation Ambiguity': 0, 'Documentation Completeness': 1, 'Documentation Replicability': 2, 'Documentation Replication on Other Examples': 3, 'Inadequate Examples': 4, 'Lack of Alternative Solutions/Documentation': 5, 'Requesting (Additional) Documentation/Examples': 6}, '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': 'lanwuwei/BERTOverflow_stackoverflow_github', 'transformers_version': '4.38.1', '_num_labels': 51, 'model_type': 'bert', 'output_past': True, 'vocab_size': 82000, 'hidden_size': 768, 'num_hidden_layers': 12, 'num_attention_heads': 12, 'hidden_act': 'gelu', 'intermediate_size': 3072, 'hidden_dropout_prob': 0.1, 'attention_probs_dropout_prob': 0.1, 'max_position_embeddings': 512, 'type_vocab_size': 2, 'initializer_range': 0.02, 'layer_norm_eps': 1e-12, 'position_embedding_type': 'absolute', 'use_cache': True, 'classifier_dropout': None, 'output_dir': '/kaggle/working/', 'overwrite_output_dir': False, 'do_train': False, 'do_eval': True, 'do_predict': False, 'evaluation_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, 'learning_rate': 2e-05, 'weight_decay': 0.0, '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': '/kaggle/working/runs/Mar06_15-36-27_64d026e37c1e', 'logging_strategy': 'epoch', '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, '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': True, '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': '/kaggle/working/', 'disable_tqdm': False, 'remove_unused_columns': True, 'label_names': None, 'load_best_model_at_end': False, 'metric_for_best_model': None, 'greater_is_better': None, '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}, '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': ['tensorboard', '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, 'fp16_backend': 'auto', '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}
+2024-03-06 15:38:49,493 INFO    MainThread:34 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-03-06 15:38:49,493 INFO    MainThread:34 [wandb_init.py:_pause_backend():437] pausing backend

wandb/run-20240306_153450-l1uc7yan/files/output.log

@@ -4,4 +4,6 @@ You should probably TRAIN this model on a down-stream task to be able to use it
   _warn_prf(average, modifier, msg_start, len(result))
 /opt/conda/lib/python3.10/site-packages/sklearn/metrics/_classification.py:1344: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 in labels with no predicted samples. Use `zero_division` parameter to control this behavior.
   _warn_prf(average, modifier, msg_start, len(result))
+/opt/conda/lib/python3.10/site-packages/sklearn/metrics/_classification.py:1344: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 in labels with no predicted samples. Use `zero_division` parameter to control this behavior.
+  _warn_prf(average, modifier, msg_start, len(result))
 /opt/conda/lib/python3.10/site-packages/sklearn/metrics/_classification.py:1344: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 in labels with no predicted samples. Use `zero_division` parameter to control this behavior.

wandb/run-20240306_153450-l1uc7yan/files/wandb-summary.json

@@ -1 +1 @@
-{"train/loss": 1.7988, "train/grad_norm": 3.493379592895508, "train/learning_rate": 8.000000000000001e-06, "train/epoch": 3.0, "train/global_step": 93, "_timestamp": 1709739485.7324972, "_runtime": 194.81821131706238, "_step": 6, "eval/loss": 1.7901660203933716, "eval/accuracy": 0.34545454545454546, "eval/precision": 0.11933884297520661, "eval/recall": 0.34545454545454546, "eval/f1": 0.17739557739557738, "eval/runtime": 2.0141, "eval/samples_per_second": 27.307, "eval/steps_per_second": 1.986}
+{"train/loss": 1.7889, "train/grad_norm": 4.259123802185059, "train/learning_rate": 4.000000000000001e-06, "train/epoch": 4.0, "train/global_step": 124, "_timestamp": 1709739521.286102, "_runtime": 230.37181615829468, "_step": 8, "eval/loss": 1.7660495042800903, "eval/accuracy": 0.34545454545454546, "eval/precision": 0.11933884297520661, "eval/recall": 0.34545454545454546, "eval/f1": 0.17739557739557738, "eval/runtime": 2.0346, "eval/samples_per_second": 27.032, "eval/steps_per_second": 1.966}

wandb/run-20240306_153450-l1uc7yan/logs/debug-internal.log

@@ -227,3 +227,40 @@
 2024-03-06 15:38:18,278 DEBUG   HandlerThread:135 [handler.py:handle_request():146] handle_request: keepalive
 2024-03-06 15:38:22,738 DEBUG   HandlerThread:135 [handler.py:handle_request():146] handle_request: status_report
 2024-03-06 15:38:23,279 DEBUG   HandlerThread:135 [handler.py:handle_request():146] handle_request: keepalive
+2024-03-06 15:38:26,953 DEBUG   SenderThread:135 [sender.py:send():382] send: stats
+2024-03-06 15:38:27,953 DEBUG   HandlerThread:135 [handler.py:handle_request():146] handle_request: status_report
+2024-03-06 15:38:28,280 DEBUG   HandlerThread:135 [handler.py:handle_request():146] handle_request: keepalive
+2024-03-06 15:38:32,954 DEBUG   HandlerThread:135 [handler.py:handle_request():146] handle_request: status_report
+2024-03-06 15:38:33,281 DEBUG   HandlerThread:135 [handler.py:handle_request():146] handle_request: keepalive
+2024-03-06 15:38:37,955 DEBUG   HandlerThread:135 [handler.py:handle_request():146] handle_request: status_report
+2024-03-06 15:38:38,282 DEBUG   HandlerThread:135 [handler.py:handle_request():146] handle_request: keepalive
+2024-03-06 15:38:39,248 DEBUG   HandlerThread:135 [handler.py:handle_request():146] handle_request: partial_history
+2024-03-06 15:38:39,249 DEBUG   SenderThread:135 [sender.py:send():382] send: history
+2024-03-06 15:38:39,249 DEBUG   SenderThread:135 [sender.py:send_request():409] send_request: summary_record
+2024-03-06 15:38:39,251 INFO    SenderThread:135 [sender.py:_save_file():1403] saving file wandb-summary.json with policy end
+2024-03-06 15:38:39,578 INFO    Thread-12 :135 [dir_watcher.py:_on_file_modified():288] file/dir modified: /kaggle/working/wandb/run-20240306_153450-l1uc7yan/files/wandb-summary.json
+2024-03-06 15:38:41,286 DEBUG   HandlerThread:135 [handler.py:handle_request():146] handle_request: partial_history
+2024-03-06 15:38:41,288 DEBUG   SenderThread:135 [sender.py:send():382] send: history
+2024-03-06 15:38:41,288 DEBUG   SenderThread:135 [sender.py:send_request():409] send_request: summary_record
+2024-03-06 15:38:41,289 INFO    SenderThread:135 [sender.py:_save_file():1403] saving file wandb-summary.json with policy end
+2024-03-06 15:38:41,580 INFO    Thread-12 :135 [dir_watcher.py:_on_file_modified():288] file/dir modified: /kaggle/working/wandb/run-20240306_153450-l1uc7yan/files/wandb-summary.json
+2024-03-06 15:38:43,289 DEBUG   HandlerThread:135 [handler.py:handle_request():146] handle_request: status_report
+2024-03-06 15:38:43,495 DEBUG   HandlerThread:135 [handler.py:handle_request():146] handle_request: keepalive
+2024-03-06 15:38:43,581 INFO    Thread-12 :135 [dir_watcher.py:_on_file_modified():288] file/dir modified: /kaggle/working/wandb/run-20240306_153450-l1uc7yan/files/output.log
+2024-03-06 15:38:48,290 DEBUG   HandlerThread:135 [handler.py:handle_request():146] handle_request: status_report
+2024-03-06 15:38:48,758 DEBUG   HandlerThread:135 [handler.py:handle_request():146] handle_request: keepalive
+2024-03-06 15:38:49,494 DEBUG   HandlerThread:135 [handler.py:handle_request():146] handle_request: pause
+2024-03-06 15:38:49,494 INFO    HandlerThread:135 [handler.py:handle_request_pause():708] stopping system metrics thread
+2024-03-06 15:38:49,494 INFO    HandlerThread:135 [system_monitor.py:finish():203] Stopping system monitor
+2024-03-06 15:38:49,495 DEBUG   SystemMonitor:135 [system_monitor.py:_start():179] Finished system metrics aggregation loop
+2024-03-06 15:38:49,495 DEBUG   SystemMonitor:135 [system_monitor.py:_start():183] Publishing last batch of metrics
+2024-03-06 15:38:49,497 INFO    HandlerThread:135 [interfaces.py:finish():202] Joined cpu monitor
+2024-03-06 15:38:49,498 INFO    HandlerThread:135 [interfaces.py:finish():202] Joined disk monitor
+2024-03-06 15:38:49,502 INFO    HandlerThread:135 [interfaces.py:finish():202] Joined gpu monitor
+2024-03-06 15:38:49,503 INFO    HandlerThread:135 [interfaces.py:finish():202] Joined memory monitor
+2024-03-06 15:38:49,503 INFO    HandlerThread:135 [interfaces.py:finish():202] Joined network monitor
+2024-03-06 15:38:49,503 DEBUG   SenderThread:135 [sender.py:send():382] send: stats
+2024-03-06 15:38:53,505 DEBUG   HandlerThread:135 [handler.py:handle_request():146] handle_request: status_report
+2024-03-06 15:38:53,759 DEBUG   HandlerThread:135 [handler.py:handle_request():146] handle_request: keepalive
+2024-03-06 15:38:58,506 DEBUG   HandlerThread:135 [handler.py:handle_request():146] handle_request: status_report
+2024-03-06 15:38:58,760 DEBUG   HandlerThread:135 [handler.py:handle_request():146] handle_request: keepalive

wandb/run-20240306_153450-l1uc7yan/logs/debug.log

@@ -36,3 +36,5 @@ config: {}
 2024-03-06 15:36:22,920 INFO    MainThread:34 [wandb_init.py:_pause_backend():437] pausing backend
 2024-03-06 15:36:26,943 INFO    MainThread:34 [wandb_init.py:_resume_backend():442] resuming backend
 2024-03-06 15:36:28,071 INFO    MainThread:34 [wandb_run.py:_config_callback():1343] config_cb None None {'return_dict': True, 'output_hidden_states': True, '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': ['BertModel'], 'finetuning_task': None, 'id2label': {0: 'Documentation Ambiguity', 1: 'Documentation Completeness', 2: 'Documentation Replicability', 3: 'Documentation Replication on Other Examples', 4: 'Inadequate Examples', 5: 'Lack of Alternative Solutions/Documentation', 6: 'Requesting (Additional) Documentation/Examples'}, 'label2id': {'Documentation Ambiguity': 0, 'Documentation Completeness': 1, 'Documentation Replicability': 2, 'Documentation Replication on Other Examples': 3, 'Inadequate Examples': 4, 'Lack of Alternative Solutions/Documentation': 5, 'Requesting (Additional) Documentation/Examples': 6}, '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': 'lanwuwei/BERTOverflow_stackoverflow_github', 'transformers_version': '4.38.1', '_num_labels': 51, 'model_type': 'bert', 'output_past': True, 'vocab_size': 82000, 'hidden_size': 768, 'num_hidden_layers': 12, 'num_attention_heads': 12, 'hidden_act': 'gelu', 'intermediate_size': 3072, 'hidden_dropout_prob': 0.1, 'attention_probs_dropout_prob': 0.1, 'max_position_embeddings': 512, 'type_vocab_size': 2, 'initializer_range': 0.02, 'layer_norm_eps': 1e-12, 'position_embedding_type': 'absolute', 'use_cache': True, 'classifier_dropout': None, 'output_dir': '/kaggle/working/', 'overwrite_output_dir': False, 'do_train': False, 'do_eval': True, 'do_predict': False, 'evaluation_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, 'learning_rate': 2e-05, 'weight_decay': 0.0, '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': '/kaggle/working/runs/Mar06_15-36-27_64d026e37c1e', 'logging_strategy': 'epoch', '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, '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': True, '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': '/kaggle/working/', 'disable_tqdm': False, 'remove_unused_columns': True, 'label_names': None, 'load_best_model_at_end': False, 'metric_for_best_model': None, 'greater_is_better': None, '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}, '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': ['tensorboard', '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, 'fp16_backend': 'auto', '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}
+2024-03-06 15:38:49,493 INFO    MainThread:34 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-03-06 15:38:49,493 INFO    MainThread:34 [wandb_init.py:_pause_backend():437] pausing backend