Training in progress, epoch 1
Browse files- model.safetensors +1 -1
- runs/Feb04_00-05-02_28d6b566919d/events.out.tfevents.1707005103.28d6b566919d.34.3 +2 -2
- runs/Feb04_00-59-14_28d6b566919d/events.out.tfevents.1707008356.28d6b566919d.34.4 +3 -0
- training_args.bin +1 -1
- wandb/debug-internal.log +0 -0
- wandb/debug.log +118 -0
- wandb/run-20240203_231535-ot9nmopj/files/config.yaml +21 -1
- wandb/run-20240203_231535-ot9nmopj/files/output.log +61 -0
- wandb/run-20240203_231535-ot9nmopj/files/wandb-summary.json +1 -1
- wandb/run-20240203_231535-ot9nmopj/logs/debug-internal.log +0 -0
- wandb/run-20240203_231535-ot9nmopj/logs/debug.log +118 -0
- wandb/run-20240203_231535-ot9nmopj/run-ot9nmopj.wandb +0 -0
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 265503852
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:eeccd595238857fc42a7f1455a23e94fbf9e969af629c0092b764500eabcf92e
|
| 3 |
size 265503852
|
runs/Feb04_00-05-02_28d6b566919d/events.out.tfevents.1707005103.28d6b566919d.34.3
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:302effd0c086c602853ae1c821cc83e3c611dbbf5812ebe7a185f750b7791079
|
| 3 |
+
size 6078
|
runs/Feb04_00-59-14_28d6b566919d/events.out.tfevents.1707008356.28d6b566919d.34.4
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4589d2dc22cc44b6247eb59af47b5aba755908220f2b73746dbc9da387d0761b
|
| 3 |
+
size 5252
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4728
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:36aaf048f2c997588c4ddbc4b0911fec1cf40f7fdde6f1b1c2a4c350ba7c08d9
|
| 3 |
size 4728
|
wandb/debug-internal.log
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|
wandb/debug.log
CHANGED
|
@@ -130,3 +130,121 @@ config: {}
|
|
| 130 |
2024-02-04 00:04:57,856 INFO MainThread:34 [wandb_init.py:_pause_backend():437] pausing backend
|
| 131 |
2024-02-04 00:05:02,036 INFO MainThread:34 [wandb_init.py:_resume_backend():442] resuming backend
|
| 132 |
2024-02-04 00:05:03,123 INFO MainThread:34 [wandb_run.py:_config_callback():1342] 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: 'LABEL_0', 1: 'LABEL_1', 2: 'LABEL_2', 3: 'LABEL_3', 4: 'LABEL_4', 5: 'LABEL_5', 6: 'LABEL_6', 7: 'LABEL_7', 8: 'LABEL_8', 9: 'LABEL_9', 10: 'LABEL_10', 11: 'LABEL_11', 12: 'LABEL_12'}, 'label2id': {'LABEL_0': 0, 'LABEL_1': 1, 'LABEL_2': 2, 'LABEL_3': 3, 'LABEL_4': 4, 'LABEL_5': 5, 'LABEL_6': 6, 'LABEL_7': 7, 'LABEL_8': 8, 'LABEL_9': 9, 'LABEL_10': 10, 'LABEL_11': 11, 'LABEL_12': 12}, '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-base-uncased', 'transformers_version': '4.37.0', 'model_type': 'distilbert', 'tie_weights_': True, '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': 32, 'per_device_eval_batch_size': 8, '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': 0.01, 'adam_beta1': 0.9, 'adam_beta2': 0.999, 'adam_epsilon': 1e-08, 'max_grad_norm': 1.0, 'num_train_epochs': 2, '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/Feb04_00-05-02_28d6b566919d', '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, '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, 'past_index': -1, 'run_name': '/kaggle/working', '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_grad_ckpt': False}, 'fsdp_transformer_layer_cls_to_wrap': 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': ['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': False, 'include_tokens_per_second': False, 'include_num_input_tokens_seen': False, 'neftune_noise_alpha': None}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 130 |
2024-02-04 00:04:57,856 INFO MainThread:34 [wandb_init.py:_pause_backend():437] pausing backend
|
| 131 |
2024-02-04 00:05:02,036 INFO MainThread:34 [wandb_init.py:_resume_backend():442] resuming backend
|
| 132 |
2024-02-04 00:05:03,123 INFO MainThread:34 [wandb_run.py:_config_callback():1342] 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: 'LABEL_0', 1: 'LABEL_1', 2: 'LABEL_2', 3: 'LABEL_3', 4: 'LABEL_4', 5: 'LABEL_5', 6: 'LABEL_6', 7: 'LABEL_7', 8: 'LABEL_8', 9: 'LABEL_9', 10: 'LABEL_10', 11: 'LABEL_11', 12: 'LABEL_12'}, 'label2id': {'LABEL_0': 0, 'LABEL_1': 1, 'LABEL_2': 2, 'LABEL_3': 3, 'LABEL_4': 4, 'LABEL_5': 5, 'LABEL_6': 6, 'LABEL_7': 7, 'LABEL_8': 8, 'LABEL_9': 9, 'LABEL_10': 10, 'LABEL_11': 11, 'LABEL_12': 12}, '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-base-uncased', 'transformers_version': '4.37.0', 'model_type': 'distilbert', 'tie_weights_': True, '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': 32, 'per_device_eval_batch_size': 8, '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': 0.01, 'adam_beta1': 0.9, 'adam_beta2': 0.999, 'adam_epsilon': 1e-08, 'max_grad_norm': 1.0, 'num_train_epochs': 2, '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/Feb04_00-05-02_28d6b566919d', '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, '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, 'past_index': -1, 'run_name': '/kaggle/working', '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_grad_ckpt': False}, 'fsdp_transformer_layer_cls_to_wrap': 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': ['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': False, 'include_tokens_per_second': False, 'include_num_input_tokens_seen': False, 'neftune_noise_alpha': None}
|
| 133 |
+
2024-02-04 00:11:02,634 INFO MainThread:34 [jupyter.py:save_ipynb():373] not saving jupyter notebook
|
| 134 |
+
2024-02-04 00:11:02,635 INFO MainThread:34 [wandb_init.py:_pause_backend():437] pausing backend
|
| 135 |
+
2024-02-04 00:17:49,706 INFO MainThread:34 [wandb_init.py:_resume_backend():442] resuming backend
|
| 136 |
+
2024-02-04 00:17:50,634 INFO MainThread:34 [jupyter.py:save_ipynb():373] not saving jupyter notebook
|
| 137 |
+
2024-02-04 00:17:50,634 INFO MainThread:34 [wandb_init.py:_pause_backend():437] pausing backend
|
| 138 |
+
2024-02-04 00:18:21,594 INFO MainThread:34 [wandb_init.py:_resume_backend():442] resuming backend
|
| 139 |
+
2024-02-04 00:18:21,598 INFO MainThread:34 [jupyter.py:save_ipynb():373] not saving jupyter notebook
|
| 140 |
+
2024-02-04 00:18:21,598 INFO MainThread:34 [wandb_init.py:_pause_backend():437] pausing backend
|
| 141 |
+
2024-02-04 00:18:33,886 INFO MainThread:34 [wandb_init.py:_resume_backend():442] resuming backend
|
| 142 |
+
2024-02-04 00:18:34,320 INFO MainThread:34 [jupyter.py:save_ipynb():373] not saving jupyter notebook
|
| 143 |
+
2024-02-04 00:18:34,320 INFO MainThread:34 [wandb_init.py:_pause_backend():437] pausing backend
|
| 144 |
+
2024-02-04 00:18:52,190 INFO MainThread:34 [wandb_init.py:_resume_backend():442] resuming backend
|
| 145 |
+
2024-02-04 00:18:52,361 INFO MainThread:34 [jupyter.py:save_ipynb():373] not saving jupyter notebook
|
| 146 |
+
2024-02-04 00:18:52,361 INFO MainThread:34 [wandb_init.py:_pause_backend():437] pausing backend
|
| 147 |
+
2024-02-04 00:19:07,653 INFO MainThread:34 [wandb_init.py:_resume_backend():442] resuming backend
|
| 148 |
+
2024-02-04 00:19:07,820 INFO MainThread:34 [jupyter.py:save_ipynb():373] not saving jupyter notebook
|
| 149 |
+
2024-02-04 00:19:07,820 INFO MainThread:34 [wandb_init.py:_pause_backend():437] pausing backend
|
| 150 |
+
2024-02-04 00:19:20,315 INFO MainThread:34 [wandb_init.py:_resume_backend():442] resuming backend
|
| 151 |
+
2024-02-04 00:19:20,378 INFO MainThread:34 [jupyter.py:save_ipynb():373] not saving jupyter notebook
|
| 152 |
+
2024-02-04 00:19:20,378 INFO MainThread:34 [wandb_init.py:_pause_backend():437] pausing backend
|
| 153 |
+
2024-02-04 00:22:35,590 INFO MainThread:34 [wandb_init.py:_resume_backend():442] resuming backend
|
| 154 |
+
2024-02-04 00:22:35,902 INFO MainThread:34 [jupyter.py:save_ipynb():373] not saving jupyter notebook
|
| 155 |
+
2024-02-04 00:22:35,902 INFO MainThread:34 [wandb_init.py:_pause_backend():437] pausing backend
|
| 156 |
+
2024-02-04 00:27:06,585 INFO MainThread:34 [wandb_init.py:_resume_backend():442] resuming backend
|
| 157 |
+
2024-02-04 00:27:06,603 INFO MainThread:34 [jupyter.py:save_ipynb():373] not saving jupyter notebook
|
| 158 |
+
2024-02-04 00:27:06,603 INFO MainThread:34 [wandb_init.py:_pause_backend():437] pausing backend
|
| 159 |
+
2024-02-04 00:27:27,151 INFO MainThread:34 [wandb_init.py:_resume_backend():442] resuming backend
|
| 160 |
+
2024-02-04 00:27:27,320 INFO MainThread:34 [jupyter.py:save_ipynb():373] not saving jupyter notebook
|
| 161 |
+
2024-02-04 00:27:27,320 INFO MainThread:34 [wandb_init.py:_pause_backend():437] pausing backend
|
| 162 |
+
2024-02-04 00:30:15,003 INFO MainThread:34 [wandb_init.py:_resume_backend():442] resuming backend
|
| 163 |
+
2024-02-04 00:30:15,171 INFO MainThread:34 [jupyter.py:save_ipynb():373] not saving jupyter notebook
|
| 164 |
+
2024-02-04 00:30:15,172 INFO MainThread:34 [wandb_init.py:_pause_backend():437] pausing backend
|
| 165 |
+
2024-02-04 00:30:22,788 INFO MainThread:34 [wandb_init.py:_resume_backend():442] resuming backend
|
| 166 |
+
2024-02-04 00:30:22,989 INFO MainThread:34 [jupyter.py:save_ipynb():373] not saving jupyter notebook
|
| 167 |
+
2024-02-04 00:30:22,989 INFO MainThread:34 [wandb_init.py:_pause_backend():437] pausing backend
|
| 168 |
+
2024-02-04 00:31:07,162 INFO MainThread:34 [wandb_init.py:_resume_backend():442] resuming backend
|
| 169 |
+
2024-02-04 00:31:07,168 INFO MainThread:34 [jupyter.py:save_ipynb():373] not saving jupyter notebook
|
| 170 |
+
2024-02-04 00:31:07,168 INFO MainThread:34 [wandb_init.py:_pause_backend():437] pausing backend
|
| 171 |
+
2024-02-04 00:31:29,611 INFO MainThread:34 [wandb_init.py:_resume_backend():442] resuming backend
|
| 172 |
+
2024-02-04 00:31:29,616 INFO MainThread:34 [jupyter.py:save_ipynb():373] not saving jupyter notebook
|
| 173 |
+
2024-02-04 00:31:29,616 INFO MainThread:34 [wandb_init.py:_pause_backend():437] pausing backend
|
| 174 |
+
2024-02-04 00:34:35,764 INFO MainThread:34 [wandb_init.py:_resume_backend():442] resuming backend
|
| 175 |
+
2024-02-04 00:34:35,815 INFO MainThread:34 [jupyter.py:save_ipynb():373] not saving jupyter notebook
|
| 176 |
+
2024-02-04 00:34:35,816 INFO MainThread:34 [wandb_init.py:_pause_backend():437] pausing backend
|
| 177 |
+
2024-02-04 00:34:46,344 INFO MainThread:34 [wandb_init.py:_resume_backend():442] resuming backend
|
| 178 |
+
2024-02-04 00:34:46,375 INFO MainThread:34 [jupyter.py:save_ipynb():373] not saving jupyter notebook
|
| 179 |
+
2024-02-04 00:34:46,376 INFO MainThread:34 [wandb_init.py:_pause_backend():437] pausing backend
|
| 180 |
+
2024-02-04 00:38:12,793 INFO MainThread:34 [wandb_init.py:_resume_backend():442] resuming backend
|
| 181 |
+
2024-02-04 00:38:12,915 INFO MainThread:34 [jupyter.py:save_ipynb():373] not saving jupyter notebook
|
| 182 |
+
2024-02-04 00:38:12,915 INFO MainThread:34 [wandb_init.py:_pause_backend():437] pausing backend
|
| 183 |
+
2024-02-04 00:39:13,170 INFO MainThread:34 [wandb_init.py:_resume_backend():442] resuming backend
|
| 184 |
+
2024-02-04 00:39:13,174 INFO MainThread:34 [jupyter.py:save_ipynb():373] not saving jupyter notebook
|
| 185 |
+
2024-02-04 00:39:13,175 INFO MainThread:34 [wandb_init.py:_pause_backend():437] pausing backend
|
| 186 |
+
2024-02-04 00:39:23,783 INFO MainThread:34 [wandb_init.py:_resume_backend():442] resuming backend
|
| 187 |
+
2024-02-04 00:39:25,327 INFO MainThread:34 [jupyter.py:save_ipynb():373] not saving jupyter notebook
|
| 188 |
+
2024-02-04 00:39:25,328 INFO MainThread:34 [wandb_init.py:_pause_backend():437] pausing backend
|
| 189 |
+
2024-02-04 00:43:25,968 INFO MainThread:34 [wandb_init.py:_resume_backend():442] resuming backend
|
| 190 |
+
2024-02-04 00:43:25,972 INFO MainThread:34 [jupyter.py:save_ipynb():373] not saving jupyter notebook
|
| 191 |
+
2024-02-04 00:43:25,972 INFO MainThread:34 [wandb_init.py:_pause_backend():437] pausing backend
|
| 192 |
+
2024-02-04 00:44:47,522 INFO MainThread:34 [wandb_init.py:_resume_backend():442] resuming backend
|
| 193 |
+
2024-02-04 00:44:47,696 INFO MainThread:34 [jupyter.py:save_ipynb():373] not saving jupyter notebook
|
| 194 |
+
2024-02-04 00:44:47,696 INFO MainThread:34 [wandb_init.py:_pause_backend():437] pausing backend
|
| 195 |
+
2024-02-04 00:44:57,307 INFO MainThread:34 [wandb_init.py:_resume_backend():442] resuming backend
|
| 196 |
+
2024-02-04 00:44:57,469 INFO MainThread:34 [jupyter.py:save_ipynb():373] not saving jupyter notebook
|
| 197 |
+
2024-02-04 00:44:57,469 INFO MainThread:34 [wandb_init.py:_pause_backend():437] pausing backend
|
| 198 |
+
2024-02-04 00:45:17,074 INFO MainThread:34 [wandb_init.py:_resume_backend():442] resuming backend
|
| 199 |
+
2024-02-04 00:45:17,122 INFO MainThread:34 [jupyter.py:save_ipynb():373] not saving jupyter notebook
|
| 200 |
+
2024-02-04 00:45:17,122 INFO MainThread:34 [wandb_init.py:_pause_backend():437] pausing backend
|
| 201 |
+
2024-02-04 00:45:33,895 INFO MainThread:34 [wandb_init.py:_resume_backend():442] resuming backend
|
| 202 |
+
2024-02-04 00:45:34,074 INFO MainThread:34 [jupyter.py:save_ipynb():373] not saving jupyter notebook
|
| 203 |
+
2024-02-04 00:45:34,075 INFO MainThread:34 [wandb_init.py:_pause_backend():437] pausing backend
|
| 204 |
+
2024-02-04 00:45:50,648 INFO MainThread:34 [wandb_init.py:_resume_backend():442] resuming backend
|
| 205 |
+
2024-02-04 00:45:50,654 INFO MainThread:34 [jupyter.py:save_ipynb():373] not saving jupyter notebook
|
| 206 |
+
2024-02-04 00:45:50,654 INFO MainThread:34 [wandb_init.py:_pause_backend():437] pausing backend
|
| 207 |
+
2024-02-04 00:46:03,249 INFO MainThread:34 [wandb_init.py:_resume_backend():442] resuming backend
|
| 208 |
+
2024-02-04 00:46:03,416 INFO MainThread:34 [jupyter.py:save_ipynb():373] not saving jupyter notebook
|
| 209 |
+
2024-02-04 00:46:03,417 INFO MainThread:34 [wandb_init.py:_pause_backend():437] pausing backend
|
| 210 |
+
2024-02-04 00:46:20,564 INFO MainThread:34 [wandb_init.py:_resume_backend():442] resuming backend
|
| 211 |
+
2024-02-04 00:46:20,568 INFO MainThread:34 [jupyter.py:save_ipynb():373] not saving jupyter notebook
|
| 212 |
+
2024-02-04 00:46:20,568 INFO MainThread:34 [wandb_init.py:_pause_backend():437] pausing backend
|
| 213 |
+
2024-02-04 00:46:38,083 INFO MainThread:34 [wandb_init.py:_resume_backend():442] resuming backend
|
| 214 |
+
2024-02-04 00:46:45,997 INFO MainThread:34 [jupyter.py:save_ipynb():373] not saving jupyter notebook
|
| 215 |
+
2024-02-04 00:46:45,998 INFO MainThread:34 [wandb_init.py:_pause_backend():437] pausing backend
|
| 216 |
+
2024-02-04 00:58:28,409 INFO MainThread:34 [wandb_init.py:_resume_backend():442] resuming backend
|
| 217 |
+
2024-02-04 00:58:53,821 INFO MainThread:34 [jupyter.py:save_ipynb():373] not saving jupyter notebook
|
| 218 |
+
2024-02-04 00:58:53,821 INFO MainThread:34 [wandb_init.py:_pause_backend():437] pausing backend
|
| 219 |
+
2024-02-04 00:58:53,831 INFO MainThread:34 [wandb_init.py:_resume_backend():442] resuming backend
|
| 220 |
+
2024-02-04 00:58:55,493 INFO MainThread:34 [jupyter.py:save_ipynb():373] not saving jupyter notebook
|
| 221 |
+
2024-02-04 00:58:55,494 INFO MainThread:34 [wandb_init.py:_pause_backend():437] pausing backend
|
| 222 |
+
2024-02-04 00:58:55,500 INFO MainThread:34 [wandb_init.py:_resume_backend():442] resuming backend
|
| 223 |
+
2024-02-04 00:58:55,675 INFO MainThread:34 [jupyter.py:save_ipynb():373] not saving jupyter notebook
|
| 224 |
+
2024-02-04 00:58:55,676 INFO MainThread:34 [wandb_init.py:_pause_backend():437] pausing backend
|
| 225 |
+
2024-02-04 00:58:55,684 INFO MainThread:34 [wandb_init.py:_resume_backend():442] resuming backend
|
| 226 |
+
2024-02-04 00:58:56,330 INFO MainThread:34 [jupyter.py:save_ipynb():373] not saving jupyter notebook
|
| 227 |
+
2024-02-04 00:58:56,330 INFO MainThread:34 [wandb_init.py:_pause_backend():437] pausing backend
|
| 228 |
+
2024-02-04 00:58:56,342 INFO MainThread:34 [wandb_init.py:_resume_backend():442] resuming backend
|
| 229 |
+
2024-02-04 00:58:56,344 INFO MainThread:34 [jupyter.py:save_ipynb():373] not saving jupyter notebook
|
| 230 |
+
2024-02-04 00:58:56,344 INFO MainThread:34 [wandb_init.py:_pause_backend():437] pausing backend
|
| 231 |
+
2024-02-04 00:58:56,354 INFO MainThread:34 [wandb_init.py:_resume_backend():442] resuming backend
|
| 232 |
+
2024-02-04 00:59:14,117 INFO MainThread:34 [jupyter.py:save_ipynb():373] not saving jupyter notebook
|
| 233 |
+
2024-02-04 00:59:14,117 INFO MainThread:34 [wandb_init.py:_pause_backend():437] pausing backend
|
| 234 |
+
2024-02-04 00:59:14,124 INFO MainThread:34 [wandb_init.py:_resume_backend():442] resuming backend
|
| 235 |
+
2024-02-04 00:59:14,158 INFO MainThread:34 [jupyter.py:save_ipynb():373] not saving jupyter notebook
|
| 236 |
+
2024-02-04 00:59:14,158 INFO MainThread:34 [wandb_init.py:_pause_backend():437] pausing backend
|
| 237 |
+
2024-02-04 00:59:14,165 INFO MainThread:34 [wandb_init.py:_resume_backend():442] resuming backend
|
| 238 |
+
2024-02-04 00:59:14,531 INFO MainThread:34 [jupyter.py:save_ipynb():373] not saving jupyter notebook
|
| 239 |
+
2024-02-04 00:59:14,531 INFO MainThread:34 [wandb_init.py:_pause_backend():437] pausing backend
|
| 240 |
+
2024-02-04 00:59:14,539 INFO MainThread:34 [wandb_init.py:_resume_backend():442] resuming backend
|
| 241 |
+
2024-02-04 00:59:14,541 INFO MainThread:34 [jupyter.py:save_ipynb():373] not saving jupyter notebook
|
| 242 |
+
2024-02-04 00:59:14,541 INFO MainThread:34 [wandb_init.py:_pause_backend():437] pausing backend
|
| 243 |
+
2024-02-04 00:59:14,549 INFO MainThread:34 [wandb_init.py:_resume_backend():442] resuming backend
|
| 244 |
+
2024-02-04 00:59:14,574 INFO MainThread:34 [jupyter.py:save_ipynb():373] not saving jupyter notebook
|
| 245 |
+
2024-02-04 00:59:14,574 INFO MainThread:34 [wandb_init.py:_pause_backend():437] pausing backend
|
| 246 |
+
2024-02-04 00:59:14,581 INFO MainThread:34 [wandb_init.py:_resume_backend():442] resuming backend
|
| 247 |
+
2024-02-04 00:59:14,795 INFO MainThread:34 [jupyter.py:save_ipynb():373] not saving jupyter notebook
|
| 248 |
+
2024-02-04 00:59:14,795 INFO MainThread:34 [wandb_init.py:_pause_backend():437] pausing backend
|
| 249 |
+
2024-02-04 00:59:14,802 INFO MainThread:34 [wandb_init.py:_resume_backend():442] resuming backend
|
| 250 |
+
2024-02-04 00:59:16,605 INFO MainThread:34 [wandb_run.py:_config_callback():1342] 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: 'LABEL_0', 1: 'LABEL_1', 2: 'LABEL_2', 3: 'LABEL_3', 4: 'LABEL_4', 5: 'LABEL_5', 6: 'LABEL_6', 7: 'LABEL_7', 8: 'LABEL_8', 9: 'LABEL_9', 10: 'LABEL_10', 11: 'LABEL_11', 12: 'LABEL_12'}, 'label2id': {'LABEL_0': 0, 'LABEL_1': 1, 'LABEL_2': 2, 'LABEL_3': 3, 'LABEL_4': 4, 'LABEL_5': 5, 'LABEL_6': 6, 'LABEL_7': 7, 'LABEL_8': 8, 'LABEL_9': 9, 'LABEL_10': 10, 'LABEL_11': 11, 'LABEL_12': 12}, '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-base-uncased', 'transformers_version': '4.37.0', 'model_type': 'distilbert', 'tie_weights_': True, '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': 32, 'per_device_eval_batch_size': 8, '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': 0.01, 'adam_beta1': 0.9, 'adam_beta2': 0.999, 'adam_epsilon': 1e-08, 'max_grad_norm': 1.0, 'num_train_epochs': 2, '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/Feb04_00-59-14_28d6b566919d', '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, '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, 'past_index': -1, 'run_name': '/kaggle/working', '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_grad_ckpt': False}, 'fsdp_transformer_layer_cls_to_wrap': 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': ['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': False, 'include_tokens_per_second': False, 'include_num_input_tokens_seen': False, 'neftune_noise_alpha': None}
|
wandb/run-20240203_231535-ot9nmopj/files/config.yaml
CHANGED
|
@@ -92,6 +92,26 @@ _wandb:
|
|
| 92 |
5: 1
|
| 93 |
6:
|
| 94 |
- 1
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 95 |
vocab_size:
|
| 96 |
desc: null
|
| 97 |
value: 30522
|
|
@@ -418,7 +438,7 @@ log_on_each_node:
|
|
| 418 |
value: true
|
| 419 |
logging_dir:
|
| 420 |
desc: null
|
| 421 |
-
value: /kaggle/working/runs/Feb04_00-
|
| 422 |
logging_strategy:
|
| 423 |
desc: null
|
| 424 |
value: steps
|
|
|
|
| 92 |
5: 1
|
| 93 |
6:
|
| 94 |
- 1
|
| 95 |
+
- 1: train/train_runtime
|
| 96 |
+
5: 1
|
| 97 |
+
6:
|
| 98 |
+
- 1
|
| 99 |
+
- 1: train/train_samples_per_second
|
| 100 |
+
5: 1
|
| 101 |
+
6:
|
| 102 |
+
- 1
|
| 103 |
+
- 1: train/train_steps_per_second
|
| 104 |
+
5: 1
|
| 105 |
+
6:
|
| 106 |
+
- 1
|
| 107 |
+
- 1: train/total_flos
|
| 108 |
+
5: 1
|
| 109 |
+
6:
|
| 110 |
+
- 1
|
| 111 |
+
- 1: train/train_loss
|
| 112 |
+
5: 1
|
| 113 |
+
6:
|
| 114 |
+
- 1
|
| 115 |
vocab_size:
|
| 116 |
desc: null
|
| 117 |
value: 30522
|
|
|
|
| 438 |
value: true
|
| 439 |
logging_dir:
|
| 440 |
desc: null
|
| 441 |
+
value: /kaggle/working/runs/Feb04_00-59-14_28d6b566919d
|
| 442 |
logging_strategy:
|
| 443 |
desc: null
|
| 444 |
value: steps
|
wandb/run-20240203_231535-ot9nmopj/files/output.log
CHANGED
|
@@ -59,3 +59,64 @@
|
|
| 59 |
/opt/conda/lib/python3.10/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.
|
| 60 |
warnings.warn('Was asked to gather along dimension 0, but all '
|
| 61 |
/opt/conda/lib/python3.10/site-packages/seqeval/metrics/v1.py:57: UndefinedMetricWarning: Precision and F-score are ill-defined and being set to 0.0 in labels with no predicted samples. Use `zero_division` parameter to control this behavior.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 59 |
/opt/conda/lib/python3.10/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.
|
| 60 |
warnings.warn('Was asked to gather along dimension 0, but all '
|
| 61 |
/opt/conda/lib/python3.10/site-packages/seqeval/metrics/v1.py:57: UndefinedMetricWarning: Precision and F-score are ill-defined and being set to 0.0 in labels with no predicted samples. Use `zero_division` parameter to control this behavior.
|
| 62 |
+
_warn_prf(average, modifier, msg_start, len(result))
|
| 63 |
+
huggingface/tokenizers: The current process just got forked, after parallelism has already been used. Disabling parallelism to avoid deadlocks...
|
| 64 |
+
To disable this warning, you can either:
|
| 65 |
+
- Avoid using `tokenizers` before the fork if possible
|
| 66 |
+
- Explicitly set the environment variable TOKENIZERS_PARALLELISM=(true | false)
|
| 67 |
+
Requirement already satisfied: evaluate in /opt/conda/lib/python3.10/site-packages (0.4.1)
|
| 68 |
+
Requirement already satisfied: datasets>=2.0.0 in /opt/conda/lib/python3.10/site-packages (from evaluate) (2.1.0)
|
| 69 |
+
Requirement already satisfied: numpy>=1.17 in /opt/conda/lib/python3.10/site-packages (from evaluate) (1.24.4)
|
| 70 |
+
Requirement already satisfied: dill in /opt/conda/lib/python3.10/site-packages (from evaluate) (0.3.7)
|
| 71 |
+
Requirement already satisfied: pandas in /opt/conda/lib/python3.10/site-packages (from evaluate) (2.1.4)
|
| 72 |
+
Requirement already satisfied: requests>=2.19.0 in /opt/conda/lib/python3.10/site-packages (from evaluate) (2.31.0)
|
| 73 |
+
Requirement already satisfied: tqdm>=4.62.1 in /opt/conda/lib/python3.10/site-packages (from evaluate) (4.66.1)
|
| 74 |
+
Requirement already satisfied: xxhash in /opt/conda/lib/python3.10/site-packages (from evaluate) (3.4.1)
|
| 75 |
+
Requirement already satisfied: multiprocess in /opt/conda/lib/python3.10/site-packages (from evaluate) (0.70.15)
|
| 76 |
+
Requirement already satisfied: fsspec>=2021.05.0 in /opt/conda/lib/python3.10/site-packages (from fsspec[http]>=2021.05.0->evaluate) (2023.12.2)
|
| 77 |
+
Requirement already satisfied: huggingface-hub>=0.7.0 in /opt/conda/lib/python3.10/site-packages (from evaluate) (0.20.3)
|
| 78 |
+
Requirement already satisfied: packaging in /opt/conda/lib/python3.10/site-packages (from evaluate) (21.3)
|
| 79 |
+
Requirement already satisfied: responses<0.19 in /opt/conda/lib/python3.10/site-packages (from evaluate) (0.18.0)
|
| 80 |
+
Requirement already satisfied: pyarrow>=5.0.0 in /opt/conda/lib/python3.10/site-packages (from datasets>=2.0.0->evaluate) (11.0.0)
|
| 81 |
+
Requirement already satisfied: aiohttp in /opt/conda/lib/python3.10/site-packages (from datasets>=2.0.0->evaluate) (3.9.1)
|
| 82 |
+
Requirement already satisfied: filelock in /opt/conda/lib/python3.10/site-packages (from huggingface-hub>=0.7.0->evaluate) (3.13.1)
|
| 83 |
+
Requirement already satisfied: pyyaml>=5.1 in /opt/conda/lib/python3.10/site-packages (from huggingface-hub>=0.7.0->evaluate) (6.0.1)
|
| 84 |
+
Requirement already satisfied: typing-extensions>=3.7.4.3 in /opt/conda/lib/python3.10/site-packages (from huggingface-hub>=0.7.0->evaluate) (4.9.0)
|
| 85 |
+
Requirement already satisfied: pyparsing!=3.0.5,>=2.0.2 in /opt/conda/lib/python3.10/site-packages (from packaging->evaluate) (3.1.1)
|
| 86 |
+
Requirement already satisfied: charset-normalizer<4,>=2 in /opt/conda/lib/python3.10/site-packages (from requests>=2.19.0->evaluate) (3.3.2)
|
| 87 |
+
Requirement already satisfied: idna<4,>=2.5 in /opt/conda/lib/python3.10/site-packages (from requests>=2.19.0->evaluate) (3.6)
|
| 88 |
+
Requirement already satisfied: urllib3<3,>=1.21.1 in /opt/conda/lib/python3.10/site-packages (from requests>=2.19.0->evaluate) (1.26.18)
|
| 89 |
+
Requirement already satisfied: certifi>=2017.4.17 in /opt/conda/lib/python3.10/site-packages (from requests>=2.19.0->evaluate) (2023.11.17)
|
| 90 |
+
Requirement already satisfied: python-dateutil>=2.8.2 in /opt/conda/lib/python3.10/site-packages (from pandas->evaluate) (2.8.2)
|
| 91 |
+
Requirement already satisfied: pytz>=2020.1 in /opt/conda/lib/python3.10/site-packages (from pandas->evaluate) (2023.3.post1)
|
| 92 |
+
Requirement already satisfied: tzdata>=2022.1 in /opt/conda/lib/python3.10/site-packages (from pandas->evaluate) (2023.4)
|
| 93 |
+
Requirement already satisfied: attrs>=17.3.0 in /opt/conda/lib/python3.10/site-packages (from aiohttp->datasets>=2.0.0->evaluate) (23.2.0)
|
| 94 |
+
Requirement already satisfied: multidict<7.0,>=4.5 in /opt/conda/lib/python3.10/site-packages (from aiohttp->datasets>=2.0.0->evaluate) (6.0.4)
|
| 95 |
+
Requirement already satisfied: yarl<2.0,>=1.0 in /opt/conda/lib/python3.10/site-packages (from aiohttp->datasets>=2.0.0->evaluate) (1.9.3)
|
| 96 |
+
Requirement already satisfied: frozenlist>=1.1.1 in /opt/conda/lib/python3.10/site-packages (from aiohttp->datasets>=2.0.0->evaluate) (1.4.1)
|
| 97 |
+
Requirement already satisfied: aiosignal>=1.1.2 in /opt/conda/lib/python3.10/site-packages (from aiohttp->datasets>=2.0.0->evaluate) (1.3.1)
|
| 98 |
+
Requirement already satisfied: async-timeout<5.0,>=4.0 in /opt/conda/lib/python3.10/site-packages (from aiohttp->datasets>=2.0.0->evaluate) (4.0.3)
|
| 99 |
+
Requirement already satisfied: six>=1.5 in /opt/conda/lib/python3.10/site-packages (from python-dateutil>=2.8.2->pandas->evaluate) (1.16.0)
|
| 100 |
+
huggingface/tokenizers: The current process just got forked, after parallelism has already been used. Disabling parallelism to avoid deadlocks...
|
| 101 |
+
To disable this warning, you can either:
|
| 102 |
+
- Avoid using `tokenizers` before the fork if possible
|
| 103 |
+
- Explicitly set the environment variable TOKENIZERS_PARALLELISM=(true | false)
|
| 104 |
+
Requirement already satisfied: seqeval in /opt/conda/lib/python3.10/site-packages (1.2.2)
|
| 105 |
+
Requirement already satisfied: numpy>=1.14.0 in /opt/conda/lib/python3.10/site-packages (from seqeval) (1.24.4)
|
| 106 |
+
Requirement already satisfied: scikit-learn>=0.21.3 in /opt/conda/lib/python3.10/site-packages (from seqeval) (1.2.2)
|
| 107 |
+
Requirement already satisfied: scipy>=1.3.2 in /opt/conda/lib/python3.10/site-packages (from scikit-learn>=0.21.3->seqeval) (1.11.4)
|
| 108 |
+
Requirement already satisfied: joblib>=1.1.1 in /opt/conda/lib/python3.10/site-packages (from scikit-learn>=0.21.3->seqeval) (1.3.2)
|
| 109 |
+
Requirement already satisfied: threadpoolctl>=2.0.0 in /opt/conda/lib/python3.10/site-packages (from scikit-learn>=0.21.3->seqeval) (3.2.0)
|
| 110 |
+
/kaggle/input/pii-detection-removal-from-educational-data/sample_submission.csv
|
| 111 |
+
/kaggle/input/pii-detection-removal-from-educational-data/train.json
|
| 112 |
+
/kaggle/input/pii-detection-removal-from-educational-data/test.json
|
| 113 |
+
Some weights of DistilBertForTokenClassification were not initialized from the model checkpoint at distilbert-base-uncased and are newly initialized: ['classifier.bias', 'classifier.weight']
|
| 114 |
+
You should probably TRAIN this model on a down-stream task to be able to use it for predictions and inference.
|
| 115 |
+
/opt/conda/lib/python3.10/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.
|
| 116 |
+
warnings.warn('Was asked to gather along dimension 0, but all '
|
| 117 |
+
/opt/conda/lib/python3.10/site-packages/seqeval/metrics/v1.py:57: UndefinedMetricWarning: Precision and F-score are ill-defined and being set to 0.0 in labels with no predicted samples. Use `zero_division` parameter to control this behavior.
|
| 118 |
+
_warn_prf(average, modifier, msg_start, len(result))
|
| 119 |
+
/opt/conda/lib/python3.10/site-packages/seqeval/metrics/v1.py:57: UndefinedMetricWarning: Precision and F-score are ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.
|
| 120 |
+
_warn_prf(average, modifier, msg_start, len(result))
|
| 121 |
+
Checkpoint destination directory /kaggle/working/checkpoint-86 already exists and is non-empty.Saving will proceed but saved results may be invalid.
|
| 122 |
+
/opt/conda/lib/python3.10/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.
|
wandb/run-20240203_231535-ot9nmopj/files/wandb-summary.json
CHANGED
|
@@ -1 +1 @@
|
|
| 1 |
-
{"eval/loss": 0.
|
|
|
|
| 1 |
+
{"eval/loss": 0.007691993843764067, "eval/precision": 0.0, "eval/recall": 0.0, "eval/f1": 0.0, "eval/accuracy": 0.9992554079209192, "eval/runtime": 33.0032, "eval/samples_per_second": 41.269, "eval/steps_per_second": 2.606, "train/epoch": 1.0, "train/global_step": 86, "_timestamp": 1707008523.8197095, "_runtime": 6388.504689455032, "_step": 3, "train/train_runtime": 351.5087, "train/train_samples_per_second": 30.981, "train/train_steps_per_second": 0.489, "train/total_flos": 1423095247411200.0, "train/train_loss": 0.000544964790690777}
|
wandb/run-20240203_231535-ot9nmopj/logs/debug-internal.log
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|
wandb/run-20240203_231535-ot9nmopj/logs/debug.log
CHANGED
|
@@ -130,3 +130,121 @@ config: {}
|
|
| 130 |
2024-02-04 00:04:57,856 INFO MainThread:34 [wandb_init.py:_pause_backend():437] pausing backend
|
| 131 |
2024-02-04 00:05:02,036 INFO MainThread:34 [wandb_init.py:_resume_backend():442] resuming backend
|
| 132 |
2024-02-04 00:05:03,123 INFO MainThread:34 [wandb_run.py:_config_callback():1342] 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: 'LABEL_0', 1: 'LABEL_1', 2: 'LABEL_2', 3: 'LABEL_3', 4: 'LABEL_4', 5: 'LABEL_5', 6: 'LABEL_6', 7: 'LABEL_7', 8: 'LABEL_8', 9: 'LABEL_9', 10: 'LABEL_10', 11: 'LABEL_11', 12: 'LABEL_12'}, 'label2id': {'LABEL_0': 0, 'LABEL_1': 1, 'LABEL_2': 2, 'LABEL_3': 3, 'LABEL_4': 4, 'LABEL_5': 5, 'LABEL_6': 6, 'LABEL_7': 7, 'LABEL_8': 8, 'LABEL_9': 9, 'LABEL_10': 10, 'LABEL_11': 11, 'LABEL_12': 12}, '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-base-uncased', 'transformers_version': '4.37.0', 'model_type': 'distilbert', 'tie_weights_': True, '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': 32, 'per_device_eval_batch_size': 8, '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': 0.01, 'adam_beta1': 0.9, 'adam_beta2': 0.999, 'adam_epsilon': 1e-08, 'max_grad_norm': 1.0, 'num_train_epochs': 2, '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/Feb04_00-05-02_28d6b566919d', '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, '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, 'past_index': -1, 'run_name': '/kaggle/working', '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_grad_ckpt': False}, 'fsdp_transformer_layer_cls_to_wrap': 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': ['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': False, 'include_tokens_per_second': False, 'include_num_input_tokens_seen': False, 'neftune_noise_alpha': None}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 130 |
2024-02-04 00:04:57,856 INFO MainThread:34 [wandb_init.py:_pause_backend():437] pausing backend
|
| 131 |
2024-02-04 00:05:02,036 INFO MainThread:34 [wandb_init.py:_resume_backend():442] resuming backend
|
| 132 |
2024-02-04 00:05:03,123 INFO MainThread:34 [wandb_run.py:_config_callback():1342] 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: 'LABEL_0', 1: 'LABEL_1', 2: 'LABEL_2', 3: 'LABEL_3', 4: 'LABEL_4', 5: 'LABEL_5', 6: 'LABEL_6', 7: 'LABEL_7', 8: 'LABEL_8', 9: 'LABEL_9', 10: 'LABEL_10', 11: 'LABEL_11', 12: 'LABEL_12'}, 'label2id': {'LABEL_0': 0, 'LABEL_1': 1, 'LABEL_2': 2, 'LABEL_3': 3, 'LABEL_4': 4, 'LABEL_5': 5, 'LABEL_6': 6, 'LABEL_7': 7, 'LABEL_8': 8, 'LABEL_9': 9, 'LABEL_10': 10, 'LABEL_11': 11, 'LABEL_12': 12}, '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-base-uncased', 'transformers_version': '4.37.0', 'model_type': 'distilbert', 'tie_weights_': True, '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': 32, 'per_device_eval_batch_size': 8, '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': 0.01, 'adam_beta1': 0.9, 'adam_beta2': 0.999, 'adam_epsilon': 1e-08, 'max_grad_norm': 1.0, 'num_train_epochs': 2, '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/Feb04_00-05-02_28d6b566919d', '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, '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, 'past_index': -1, 'run_name': '/kaggle/working', '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_grad_ckpt': False}, 'fsdp_transformer_layer_cls_to_wrap': 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': ['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': False, 'include_tokens_per_second': False, 'include_num_input_tokens_seen': False, 'neftune_noise_alpha': None}
|
| 133 |
+
2024-02-04 00:11:02,634 INFO MainThread:34 [jupyter.py:save_ipynb():373] not saving jupyter notebook
|
| 134 |
+
2024-02-04 00:11:02,635 INFO MainThread:34 [wandb_init.py:_pause_backend():437] pausing backend
|
| 135 |
+
2024-02-04 00:17:49,706 INFO MainThread:34 [wandb_init.py:_resume_backend():442] resuming backend
|
| 136 |
+
2024-02-04 00:17:50,634 INFO MainThread:34 [jupyter.py:save_ipynb():373] not saving jupyter notebook
|
| 137 |
+
2024-02-04 00:17:50,634 INFO MainThread:34 [wandb_init.py:_pause_backend():437] pausing backend
|
| 138 |
+
2024-02-04 00:18:21,594 INFO MainThread:34 [wandb_init.py:_resume_backend():442] resuming backend
|
| 139 |
+
2024-02-04 00:18:21,598 INFO MainThread:34 [jupyter.py:save_ipynb():373] not saving jupyter notebook
|
| 140 |
+
2024-02-04 00:18:21,598 INFO MainThread:34 [wandb_init.py:_pause_backend():437] pausing backend
|
| 141 |
+
2024-02-04 00:18:33,886 INFO MainThread:34 [wandb_init.py:_resume_backend():442] resuming backend
|
| 142 |
+
2024-02-04 00:18:34,320 INFO MainThread:34 [jupyter.py:save_ipynb():373] not saving jupyter notebook
|
| 143 |
+
2024-02-04 00:18:34,320 INFO MainThread:34 [wandb_init.py:_pause_backend():437] pausing backend
|
| 144 |
+
2024-02-04 00:18:52,190 INFO MainThread:34 [wandb_init.py:_resume_backend():442] resuming backend
|
| 145 |
+
2024-02-04 00:18:52,361 INFO MainThread:34 [jupyter.py:save_ipynb():373] not saving jupyter notebook
|
| 146 |
+
2024-02-04 00:18:52,361 INFO MainThread:34 [wandb_init.py:_pause_backend():437] pausing backend
|
| 147 |
+
2024-02-04 00:19:07,653 INFO MainThread:34 [wandb_init.py:_resume_backend():442] resuming backend
|
| 148 |
+
2024-02-04 00:19:07,820 INFO MainThread:34 [jupyter.py:save_ipynb():373] not saving jupyter notebook
|
| 149 |
+
2024-02-04 00:19:07,820 INFO MainThread:34 [wandb_init.py:_pause_backend():437] pausing backend
|
| 150 |
+
2024-02-04 00:19:20,315 INFO MainThread:34 [wandb_init.py:_resume_backend():442] resuming backend
|
| 151 |
+
2024-02-04 00:19:20,378 INFO MainThread:34 [jupyter.py:save_ipynb():373] not saving jupyter notebook
|
| 152 |
+
2024-02-04 00:19:20,378 INFO MainThread:34 [wandb_init.py:_pause_backend():437] pausing backend
|
| 153 |
+
2024-02-04 00:22:35,590 INFO MainThread:34 [wandb_init.py:_resume_backend():442] resuming backend
|
| 154 |
+
2024-02-04 00:22:35,902 INFO MainThread:34 [jupyter.py:save_ipynb():373] not saving jupyter notebook
|
| 155 |
+
2024-02-04 00:22:35,902 INFO MainThread:34 [wandb_init.py:_pause_backend():437] pausing backend
|
| 156 |
+
2024-02-04 00:27:06,585 INFO MainThread:34 [wandb_init.py:_resume_backend():442] resuming backend
|
| 157 |
+
2024-02-04 00:27:06,603 INFO MainThread:34 [jupyter.py:save_ipynb():373] not saving jupyter notebook
|
| 158 |
+
2024-02-04 00:27:06,603 INFO MainThread:34 [wandb_init.py:_pause_backend():437] pausing backend
|
| 159 |
+
2024-02-04 00:27:27,151 INFO MainThread:34 [wandb_init.py:_resume_backend():442] resuming backend
|
| 160 |
+
2024-02-04 00:27:27,320 INFO MainThread:34 [jupyter.py:save_ipynb():373] not saving jupyter notebook
|
| 161 |
+
2024-02-04 00:27:27,320 INFO MainThread:34 [wandb_init.py:_pause_backend():437] pausing backend
|
| 162 |
+
2024-02-04 00:30:15,003 INFO MainThread:34 [wandb_init.py:_resume_backend():442] resuming backend
|
| 163 |
+
2024-02-04 00:30:15,171 INFO MainThread:34 [jupyter.py:save_ipynb():373] not saving jupyter notebook
|
| 164 |
+
2024-02-04 00:30:15,172 INFO MainThread:34 [wandb_init.py:_pause_backend():437] pausing backend
|
| 165 |
+
2024-02-04 00:30:22,788 INFO MainThread:34 [wandb_init.py:_resume_backend():442] resuming backend
|
| 166 |
+
2024-02-04 00:30:22,989 INFO MainThread:34 [jupyter.py:save_ipynb():373] not saving jupyter notebook
|
| 167 |
+
2024-02-04 00:30:22,989 INFO MainThread:34 [wandb_init.py:_pause_backend():437] pausing backend
|
| 168 |
+
2024-02-04 00:31:07,162 INFO MainThread:34 [wandb_init.py:_resume_backend():442] resuming backend
|
| 169 |
+
2024-02-04 00:31:07,168 INFO MainThread:34 [jupyter.py:save_ipynb():373] not saving jupyter notebook
|
| 170 |
+
2024-02-04 00:31:07,168 INFO MainThread:34 [wandb_init.py:_pause_backend():437] pausing backend
|
| 171 |
+
2024-02-04 00:31:29,611 INFO MainThread:34 [wandb_init.py:_resume_backend():442] resuming backend
|
| 172 |
+
2024-02-04 00:31:29,616 INFO MainThread:34 [jupyter.py:save_ipynb():373] not saving jupyter notebook
|
| 173 |
+
2024-02-04 00:31:29,616 INFO MainThread:34 [wandb_init.py:_pause_backend():437] pausing backend
|
| 174 |
+
2024-02-04 00:34:35,764 INFO MainThread:34 [wandb_init.py:_resume_backend():442] resuming backend
|
| 175 |
+
2024-02-04 00:34:35,815 INFO MainThread:34 [jupyter.py:save_ipynb():373] not saving jupyter notebook
|
| 176 |
+
2024-02-04 00:34:35,816 INFO MainThread:34 [wandb_init.py:_pause_backend():437] pausing backend
|
| 177 |
+
2024-02-04 00:34:46,344 INFO MainThread:34 [wandb_init.py:_resume_backend():442] resuming backend
|
| 178 |
+
2024-02-04 00:34:46,375 INFO MainThread:34 [jupyter.py:save_ipynb():373] not saving jupyter notebook
|
| 179 |
+
2024-02-04 00:34:46,376 INFO MainThread:34 [wandb_init.py:_pause_backend():437] pausing backend
|
| 180 |
+
2024-02-04 00:38:12,793 INFO MainThread:34 [wandb_init.py:_resume_backend():442] resuming backend
|
| 181 |
+
2024-02-04 00:38:12,915 INFO MainThread:34 [jupyter.py:save_ipynb():373] not saving jupyter notebook
|
| 182 |
+
2024-02-04 00:38:12,915 INFO MainThread:34 [wandb_init.py:_pause_backend():437] pausing backend
|
| 183 |
+
2024-02-04 00:39:13,170 INFO MainThread:34 [wandb_init.py:_resume_backend():442] resuming backend
|
| 184 |
+
2024-02-04 00:39:13,174 INFO MainThread:34 [jupyter.py:save_ipynb():373] not saving jupyter notebook
|
| 185 |
+
2024-02-04 00:39:13,175 INFO MainThread:34 [wandb_init.py:_pause_backend():437] pausing backend
|
| 186 |
+
2024-02-04 00:39:23,783 INFO MainThread:34 [wandb_init.py:_resume_backend():442] resuming backend
|
| 187 |
+
2024-02-04 00:39:25,327 INFO MainThread:34 [jupyter.py:save_ipynb():373] not saving jupyter notebook
|
| 188 |
+
2024-02-04 00:39:25,328 INFO MainThread:34 [wandb_init.py:_pause_backend():437] pausing backend
|
| 189 |
+
2024-02-04 00:43:25,968 INFO MainThread:34 [wandb_init.py:_resume_backend():442] resuming backend
|
| 190 |
+
2024-02-04 00:43:25,972 INFO MainThread:34 [jupyter.py:save_ipynb():373] not saving jupyter notebook
|
| 191 |
+
2024-02-04 00:43:25,972 INFO MainThread:34 [wandb_init.py:_pause_backend():437] pausing backend
|
| 192 |
+
2024-02-04 00:44:47,522 INFO MainThread:34 [wandb_init.py:_resume_backend():442] resuming backend
|
| 193 |
+
2024-02-04 00:44:47,696 INFO MainThread:34 [jupyter.py:save_ipynb():373] not saving jupyter notebook
|
| 194 |
+
2024-02-04 00:44:47,696 INFO MainThread:34 [wandb_init.py:_pause_backend():437] pausing backend
|
| 195 |
+
2024-02-04 00:44:57,307 INFO MainThread:34 [wandb_init.py:_resume_backend():442] resuming backend
|
| 196 |
+
2024-02-04 00:44:57,469 INFO MainThread:34 [jupyter.py:save_ipynb():373] not saving jupyter notebook
|
| 197 |
+
2024-02-04 00:44:57,469 INFO MainThread:34 [wandb_init.py:_pause_backend():437] pausing backend
|
| 198 |
+
2024-02-04 00:45:17,074 INFO MainThread:34 [wandb_init.py:_resume_backend():442] resuming backend
|
| 199 |
+
2024-02-04 00:45:17,122 INFO MainThread:34 [jupyter.py:save_ipynb():373] not saving jupyter notebook
|
| 200 |
+
2024-02-04 00:45:17,122 INFO MainThread:34 [wandb_init.py:_pause_backend():437] pausing backend
|
| 201 |
+
2024-02-04 00:45:33,895 INFO MainThread:34 [wandb_init.py:_resume_backend():442] resuming backend
|
| 202 |
+
2024-02-04 00:45:34,074 INFO MainThread:34 [jupyter.py:save_ipynb():373] not saving jupyter notebook
|
| 203 |
+
2024-02-04 00:45:34,075 INFO MainThread:34 [wandb_init.py:_pause_backend():437] pausing backend
|
| 204 |
+
2024-02-04 00:45:50,648 INFO MainThread:34 [wandb_init.py:_resume_backend():442] resuming backend
|
| 205 |
+
2024-02-04 00:45:50,654 INFO MainThread:34 [jupyter.py:save_ipynb():373] not saving jupyter notebook
|
| 206 |
+
2024-02-04 00:45:50,654 INFO MainThread:34 [wandb_init.py:_pause_backend():437] pausing backend
|
| 207 |
+
2024-02-04 00:46:03,249 INFO MainThread:34 [wandb_init.py:_resume_backend():442] resuming backend
|
| 208 |
+
2024-02-04 00:46:03,416 INFO MainThread:34 [jupyter.py:save_ipynb():373] not saving jupyter notebook
|
| 209 |
+
2024-02-04 00:46:03,417 INFO MainThread:34 [wandb_init.py:_pause_backend():437] pausing backend
|
| 210 |
+
2024-02-04 00:46:20,564 INFO MainThread:34 [wandb_init.py:_resume_backend():442] resuming backend
|
| 211 |
+
2024-02-04 00:46:20,568 INFO MainThread:34 [jupyter.py:save_ipynb():373] not saving jupyter notebook
|
| 212 |
+
2024-02-04 00:46:20,568 INFO MainThread:34 [wandb_init.py:_pause_backend():437] pausing backend
|
| 213 |
+
2024-02-04 00:46:38,083 INFO MainThread:34 [wandb_init.py:_resume_backend():442] resuming backend
|
| 214 |
+
2024-02-04 00:46:45,997 INFO MainThread:34 [jupyter.py:save_ipynb():373] not saving jupyter notebook
|
| 215 |
+
2024-02-04 00:46:45,998 INFO MainThread:34 [wandb_init.py:_pause_backend():437] pausing backend
|
| 216 |
+
2024-02-04 00:58:28,409 INFO MainThread:34 [wandb_init.py:_resume_backend():442] resuming backend
|
| 217 |
+
2024-02-04 00:58:53,821 INFO MainThread:34 [jupyter.py:save_ipynb():373] not saving jupyter notebook
|
| 218 |
+
2024-02-04 00:58:53,821 INFO MainThread:34 [wandb_init.py:_pause_backend():437] pausing backend
|
| 219 |
+
2024-02-04 00:58:53,831 INFO MainThread:34 [wandb_init.py:_resume_backend():442] resuming backend
|
| 220 |
+
2024-02-04 00:58:55,493 INFO MainThread:34 [jupyter.py:save_ipynb():373] not saving jupyter notebook
|
| 221 |
+
2024-02-04 00:58:55,494 INFO MainThread:34 [wandb_init.py:_pause_backend():437] pausing backend
|
| 222 |
+
2024-02-04 00:58:55,500 INFO MainThread:34 [wandb_init.py:_resume_backend():442] resuming backend
|
| 223 |
+
2024-02-04 00:58:55,675 INFO MainThread:34 [jupyter.py:save_ipynb():373] not saving jupyter notebook
|
| 224 |
+
2024-02-04 00:58:55,676 INFO MainThread:34 [wandb_init.py:_pause_backend():437] pausing backend
|
| 225 |
+
2024-02-04 00:58:55,684 INFO MainThread:34 [wandb_init.py:_resume_backend():442] resuming backend
|
| 226 |
+
2024-02-04 00:58:56,330 INFO MainThread:34 [jupyter.py:save_ipynb():373] not saving jupyter notebook
|
| 227 |
+
2024-02-04 00:58:56,330 INFO MainThread:34 [wandb_init.py:_pause_backend():437] pausing backend
|
| 228 |
+
2024-02-04 00:58:56,342 INFO MainThread:34 [wandb_init.py:_resume_backend():442] resuming backend
|
| 229 |
+
2024-02-04 00:58:56,344 INFO MainThread:34 [jupyter.py:save_ipynb():373] not saving jupyter notebook
|
| 230 |
+
2024-02-04 00:58:56,344 INFO MainThread:34 [wandb_init.py:_pause_backend():437] pausing backend
|
| 231 |
+
2024-02-04 00:58:56,354 INFO MainThread:34 [wandb_init.py:_resume_backend():442] resuming backend
|
| 232 |
+
2024-02-04 00:59:14,117 INFO MainThread:34 [jupyter.py:save_ipynb():373] not saving jupyter notebook
|
| 233 |
+
2024-02-04 00:59:14,117 INFO MainThread:34 [wandb_init.py:_pause_backend():437] pausing backend
|
| 234 |
+
2024-02-04 00:59:14,124 INFO MainThread:34 [wandb_init.py:_resume_backend():442] resuming backend
|
| 235 |
+
2024-02-04 00:59:14,158 INFO MainThread:34 [jupyter.py:save_ipynb():373] not saving jupyter notebook
|
| 236 |
+
2024-02-04 00:59:14,158 INFO MainThread:34 [wandb_init.py:_pause_backend():437] pausing backend
|
| 237 |
+
2024-02-04 00:59:14,165 INFO MainThread:34 [wandb_init.py:_resume_backend():442] resuming backend
|
| 238 |
+
2024-02-04 00:59:14,531 INFO MainThread:34 [jupyter.py:save_ipynb():373] not saving jupyter notebook
|
| 239 |
+
2024-02-04 00:59:14,531 INFO MainThread:34 [wandb_init.py:_pause_backend():437] pausing backend
|
| 240 |
+
2024-02-04 00:59:14,539 INFO MainThread:34 [wandb_init.py:_resume_backend():442] resuming backend
|
| 241 |
+
2024-02-04 00:59:14,541 INFO MainThread:34 [jupyter.py:save_ipynb():373] not saving jupyter notebook
|
| 242 |
+
2024-02-04 00:59:14,541 INFO MainThread:34 [wandb_init.py:_pause_backend():437] pausing backend
|
| 243 |
+
2024-02-04 00:59:14,549 INFO MainThread:34 [wandb_init.py:_resume_backend():442] resuming backend
|
| 244 |
+
2024-02-04 00:59:14,574 INFO MainThread:34 [jupyter.py:save_ipynb():373] not saving jupyter notebook
|
| 245 |
+
2024-02-04 00:59:14,574 INFO MainThread:34 [wandb_init.py:_pause_backend():437] pausing backend
|
| 246 |
+
2024-02-04 00:59:14,581 INFO MainThread:34 [wandb_init.py:_resume_backend():442] resuming backend
|
| 247 |
+
2024-02-04 00:59:14,795 INFO MainThread:34 [jupyter.py:save_ipynb():373] not saving jupyter notebook
|
| 248 |
+
2024-02-04 00:59:14,795 INFO MainThread:34 [wandb_init.py:_pause_backend():437] pausing backend
|
| 249 |
+
2024-02-04 00:59:14,802 INFO MainThread:34 [wandb_init.py:_resume_backend():442] resuming backend
|
| 250 |
+
2024-02-04 00:59:16,605 INFO MainThread:34 [wandb_run.py:_config_callback():1342] 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: 'LABEL_0', 1: 'LABEL_1', 2: 'LABEL_2', 3: 'LABEL_3', 4: 'LABEL_4', 5: 'LABEL_5', 6: 'LABEL_6', 7: 'LABEL_7', 8: 'LABEL_8', 9: 'LABEL_9', 10: 'LABEL_10', 11: 'LABEL_11', 12: 'LABEL_12'}, 'label2id': {'LABEL_0': 0, 'LABEL_1': 1, 'LABEL_2': 2, 'LABEL_3': 3, 'LABEL_4': 4, 'LABEL_5': 5, 'LABEL_6': 6, 'LABEL_7': 7, 'LABEL_8': 8, 'LABEL_9': 9, 'LABEL_10': 10, 'LABEL_11': 11, 'LABEL_12': 12}, '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-base-uncased', 'transformers_version': '4.37.0', 'model_type': 'distilbert', 'tie_weights_': True, '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': 32, 'per_device_eval_batch_size': 8, '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': 0.01, 'adam_beta1': 0.9, 'adam_beta2': 0.999, 'adam_epsilon': 1e-08, 'max_grad_norm': 1.0, 'num_train_epochs': 2, '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/Feb04_00-59-14_28d6b566919d', '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, '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, 'past_index': -1, 'run_name': '/kaggle/working', '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_grad_ckpt': False}, 'fsdp_transformer_layer_cls_to_wrap': 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': ['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': False, 'include_tokens_per_second': False, 'include_num_input_tokens_seen': False, 'neftune_noise_alpha': None}
|
wandb/run-20240203_231535-ot9nmopj/run-ot9nmopj.wandb
CHANGED
|
Binary files a/wandb/run-20240203_231535-ot9nmopj/run-ot9nmopj.wandb and b/wandb/run-20240203_231535-ot9nmopj/run-ot9nmopj.wandb differ
|
|
|