Training in progress, epoch 1

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "distilbert-base-cased",
+  "_name_or_path": "malduwais/distilbert-base-uncased-finetuned-ner",
   "activation": "gelu",
   "architectures": [
     "DistilBertForTokenClassification"
@@ -43,7 +43,6 @@
   "model_type": "distilbert",
   "n_heads": 12,
   "n_layers": 6,
-  "output_past": true,
   "pad_token_id": 0,
   "qa_dropout": 0.1,
   "seq_classif_dropout": 0.2,
@@ -51,5 +50,5 @@
   "tie_weights_": true,
   "torch_dtype": "float32",
   "transformers_version": "4.37.0",
-  "vocab_size": 28996
+  "vocab_size": 30522
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d407f007d3a12dcf37c0555b41ef3e0d01362fdbe80b80a85ebe2a18cbc1f890
-size 260815972
+oid sha256:c5d090b056880087d5aed195f9a8c3e36331b8b7c96499819f589c02c77b7406
+size 265503852

runs/Feb24_18-50-16_ff5231669072/events.out.tfevents.1708800621.ff5231669072.34.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:31a0838a79c0afff5e10aa06ed8631e51dbb2f346712e38e71d866c41dca6edc
-size 5318
+oid sha256:00eb3bc6c437613cb7624009818ea99164a04cd91ea6b56847c4e1e2015c2eed
+size 6190

runs/Feb24_19-24-42_ff5231669072/events.out.tfevents.1708802688.ff5231669072.34.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cb34fa2731f1d6c093820bb98aea3ddfdcf588db1402cd50badc187a84f2e6c2
+size 4983

runs/Feb24_19-24-54_ff5231669072/events.out.tfevents.1708802699.ff5231669072.34.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a86744c434f05e9ce4026dba6200e7ed26fd99811a1bb7225b4fc0446f70e7cc
+size 4983

runs/Feb24_19-30-22_ff5231669072/events.out.tfevents.1708803027.ff5231669072.34.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e3df88387dbcbcf308a10c51593aba8cf78e187038dd55edefdf7e8fd3079d59
+size 5360

special_tokens_map.json

@@ -1,7 +1,37 @@
 {
-  "cls_token": "[CLS]",
-  "mask_token": "[MASK]",
-  "pad_token": "[PAD]",
-  "sep_token": "[SEP]",
-  "unk_token": "[UNK]"
+  "cls_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "[MASK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "[SEP]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "[UNK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
 }

tokenizer_config.json

@@ -43,14 +43,18 @@
   },
   "clean_up_tokenization_spaces": true,
   "cls_token": "[CLS]",
-  "do_lower_case": false,
+  "do_lower_case": true,
   "is_split_into_words": true,
   "mask_token": "[MASK]",
+  "max_length": 512,
   "model_max_length": 512,
   "pad_token": "[PAD]",
   "sep_token": "[SEP]",
+  "stride": 0,
   "strip_accents": null,
   "tokenize_chinese_chars": true,
   "tokenizer_class": "DistilBertTokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
   "unk_token": "[UNK]"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:25ea335f4adb58975c959cc9b95e250ff329df438a096abe66e8084ba1257a4d
+oid sha256:18a2e3fefe3cc351914bc8ae2056f061b37c6ce4139b103ffce8a8856dfc11d8
 size 4728

wandb/debug.log

@@ -29,3 +29,144 @@ config: {}
 2024-02-24 18:50:51,949 INFO    MainThread:34 [wandb_run.py:_redirect():2178] Redirects installed.
 2024-02-24 18:50:51,950 INFO    MainThread:34 [wandb_init.py:init():847] run started, returning control to user process
 2024-02-24 18:50:51,956 INFO    MainThread:34 [wandb_run.py:_config_callback():1342] config_cb None None {'vocab_size': 28996, '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-cased', 'transformers_version': '4.37.0', 'model_type': 'distilbert', 'output_past': True, '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/Feb24_18-50-16_ff5231669072', '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}
+2024-02-24 18:57:14,450 INFO    MainThread:34 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-02-24 18:57:14,451 INFO    MainThread:34 [wandb_init.py:_pause_backend():437] pausing backend
+2024-02-24 18:57:14,456 INFO    MainThread:34 [wandb_init.py:_resume_backend():442] resuming backend
+2024-02-24 18:57:14,764 INFO    MainThread:34 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-02-24 18:57:14,764 INFO    MainThread:34 [wandb_init.py:_pause_backend():437] pausing backend
+2024-02-24 18:57:14,769 INFO    MainThread:34 [wandb_init.py:_resume_backend():442] resuming backend
+2024-02-24 18:57:14,774 INFO    MainThread:34 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-02-24 18:57:14,774 INFO    MainThread:34 [wandb_init.py:_pause_backend():437] pausing backend
+2024-02-24 18:57:14,780 INFO    MainThread:34 [wandb_init.py:_resume_backend():442] resuming backend
+2024-02-24 18:57:15,111 INFO    MainThread:34 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-02-24 18:57:15,112 INFO    MainThread:34 [wandb_init.py:_pause_backend():437] pausing backend
+2024-02-24 19:16:37,055 INFO    MainThread:34 [wandb_init.py:_resume_backend():442] resuming backend
+2024-02-24 19:16:37,851 INFO    MainThread:34 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-02-24 19:16:37,851 INFO    MainThread:34 [wandb_init.py:_pause_backend():437] pausing backend
+2024-02-24 19:16:45,072 INFO    MainThread:34 [wandb_init.py:_resume_backend():442] resuming backend
+2024-02-24 19:16:45,074 INFO    MainThread:34 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-02-24 19:16:45,074 INFO    MainThread:34 [wandb_init.py:_pause_backend():437] pausing backend
+2024-02-24 19:16:47,316 INFO    MainThread:34 [wandb_init.py:_resume_backend():442] resuming backend
+2024-02-24 19:16:48,322 INFO    MainThread:34 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-02-24 19:16:48,322 INFO    MainThread:34 [wandb_init.py:_pause_backend():437] pausing backend
+2024-02-24 19:17:23,661 INFO    MainThread:34 [wandb_init.py:_resume_backend():442] resuming backend
+2024-02-24 19:17:31,220 INFO    MainThread:34 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-02-24 19:17:31,221 INFO    MainThread:34 [wandb_init.py:_pause_backend():437] pausing backend
+2024-02-24 19:18:36,781 INFO    MainThread:34 [wandb_init.py:_resume_backend():442] resuming backend
+2024-02-24 19:18:38,339 INFO    MainThread:34 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-02-24 19:18:38,339 INFO    MainThread:34 [wandb_init.py:_pause_backend():437] pausing backend
+2024-02-24 19:18:53,063 INFO    MainThread:34 [wandb_init.py:_resume_backend():442] resuming backend
+2024-02-24 19:18:53,734 INFO    MainThread:34 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-02-24 19:18:53,734 INFO    MainThread:34 [wandb_init.py:_pause_backend():437] pausing backend
+2024-02-24 19:18:56,646 INFO    MainThread:34 [wandb_init.py:_resume_backend():442] resuming backend
+2024-02-24 19:19:01,360 INFO    MainThread:34 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-02-24 19:19:01,360 INFO    MainThread:34 [wandb_init.py:_pause_backend():437] pausing backend
+2024-02-24 19:19:01,371 INFO    MainThread:34 [wandb_init.py:_resume_backend():442] resuming backend
+2024-02-24 19:19:01,374 INFO    MainThread:34 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-02-24 19:19:01,375 INFO    MainThread:34 [wandb_init.py:_pause_backend():437] pausing backend
+2024-02-24 19:19:05,298 INFO    MainThread:34 [wandb_init.py:_resume_backend():442] resuming backend
+2024-02-24 19:19:11,995 INFO    MainThread:34 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-02-24 19:19:11,995 INFO    MainThread:34 [wandb_init.py:_pause_backend():437] pausing backend
+2024-02-24 19:19:12,001 INFO    MainThread:34 [wandb_init.py:_resume_backend():442] resuming backend
+2024-02-24 19:19:51,045 INFO    MainThread:34 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-02-24 19:19:51,045 INFO    MainThread:34 [wandb_init.py:_pause_backend():437] pausing backend
+2024-02-24 19:19:51,054 INFO    MainThread:34 [wandb_init.py:_resume_backend():442] resuming backend
+2024-02-24 19:19:51,081 INFO    MainThread:34 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-02-24 19:19:51,081 INFO    MainThread:34 [wandb_init.py:_pause_backend():437] pausing backend
+2024-02-24 19:19:51,088 INFO    MainThread:34 [wandb_init.py:_resume_backend():442] resuming backend
+2024-02-24 19:19:51,095 INFO    MainThread:34 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-02-24 19:19:51,095 INFO    MainThread:34 [wandb_init.py:_pause_backend():437] pausing backend
+2024-02-24 19:19:51,106 INFO    MainThread:34 [wandb_init.py:_resume_backend():442] resuming backend
+2024-02-24 19:19:51,978 INFO    MainThread:34 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-02-24 19:19:51,978 INFO    MainThread:34 [wandb_init.py:_pause_backend():437] pausing backend
+2024-02-24 19:19:51,984 INFO    MainThread:34 [wandb_init.py:_resume_backend():442] resuming backend
+2024-02-24 19:19:52,402 INFO    MainThread:34 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-02-24 19:19:52,402 INFO    MainThread:34 [wandb_init.py:_pause_backend():437] pausing backend
+2024-02-24 19:19:52,416 INFO    MainThread:34 [wandb_init.py:_resume_backend():442] resuming backend
+2024-02-24 19:19:52,419 INFO    MainThread:34 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-02-24 19:19:52,419 INFO    MainThread:34 [wandb_init.py:_pause_backend():437] pausing backend
+2024-02-24 19:19:52,426 INFO    MainThread:34 [wandb_init.py:_resume_backend():442] resuming backend
+2024-02-24 19:19:52,489 INFO    MainThread:34 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-02-24 19:19:52,489 INFO    MainThread:34 [wandb_init.py:_pause_backend():437] pausing backend
+2024-02-24 19:19:52,494 INFO    MainThread:34 [wandb_init.py:_resume_backend():442] resuming backend
+2024-02-24 19:19:52,496 INFO    MainThread:34 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-02-24 19:19:52,496 INFO    MainThread:34 [wandb_init.py:_pause_backend():437] pausing backend
+2024-02-24 19:19:52,504 INFO    MainThread:34 [wandb_init.py:_resume_backend():442] resuming backend
+2024-02-24 19:19:53,650 INFO    MainThread:34 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-02-24 19:19:53,650 INFO    MainThread:34 [wandb_init.py:_pause_backend():437] pausing backend
+2024-02-24 19:22:09,466 INFO    MainThread:34 [wandb_init.py:_resume_backend():442] resuming backend
+2024-02-24 19:22:09,487 INFO    MainThread:34 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-02-24 19:22:09,487 INFO    MainThread:34 [wandb_init.py:_pause_backend():437] pausing backend
+2024-02-24 19:24:04,362 INFO    MainThread:34 [wandb_init.py:_resume_backend():442] resuming backend
+2024-02-24 19:24:08,582 INFO    MainThread:34 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-02-24 19:24:08,583 INFO    MainThread:34 [wandb_init.py:_pause_backend():437] pausing backend
+2024-02-24 19:24:26,820 INFO    MainThread:34 [wandb_init.py:_resume_backend():442] resuming backend
+2024-02-24 19:24:26,822 INFO    MainThread:34 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-02-24 19:24:26,822 INFO    MainThread:34 [wandb_init.py:_pause_backend():437] pausing backend
+2024-02-24 19:24:30,441 INFO    MainThread:34 [wandb_init.py:_resume_backend():442] resuming backend
+2024-02-24 19:24:30,447 INFO    MainThread:34 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-02-24 19:24:30,449 INFO    MainThread:34 [wandb_init.py:_pause_backend():437] pausing backend
+2024-02-24 19:24:40,382 INFO    MainThread:34 [wandb_init.py:_resume_backend():442] resuming backend
+2024-02-24 19:24:40,572 INFO    MainThread:34 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-02-24 19:24:40,573 INFO    MainThread:34 [wandb_init.py:_pause_backend():437] pausing backend
+2024-02-24 19:24:42,828 INFO    MainThread:34 [wandb_init.py:_resume_backend():442] resuming backend
+2024-02-24 19:24:48,476 INFO    MainThread:34 [wandb_run.py:_config_callback():1342] config_cb None None {'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': ['RobertaForTokenClassification'], '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': 0, 'pad_token_id': 1, 'eos_token_id': 2, 'sep_token_id': None, 'decoder_start_token_id': None, 'task_specific_params': None, 'problem_type': None, '_name_or_path': 'Jean-Baptiste/roberta-large-ner-english', 'transformers_version': '4.37.0', 'gradient_checkpointing': False, 'model_type': 'roberta', 'vocab_size': 50265, 'hidden_size': 1024, 'num_hidden_layers': 24, 'num_attention_heads': 16, 'hidden_act': 'gelu', 'intermediate_size': 4096, 'hidden_dropout_prob': 0.1, 'attention_probs_dropout_prob': 0.1, 'max_position_embeddings': 514, 'type_vocab_size': 1, 'initializer_range': 0.02, 'layer_norm_eps': 1e-05, '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': 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/Feb24_19-24-42_ff5231669072', '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_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}
+2024-02-24 19:24:50,854 INFO    MainThread:34 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-02-24 19:24:50,854 INFO    MainThread:34 [wandb_init.py:_pause_backend():437] pausing backend
+2024-02-24 19:24:54,667 INFO    MainThread:34 [wandb_init.py:_resume_backend():442] resuming backend
+2024-02-24 19:24:59,384 INFO    MainThread:34 [wandb_run.py:_config_callback():1342] config_cb None None {'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': ['RobertaForTokenClassification'], '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': 0, 'pad_token_id': 1, 'eos_token_id': 2, 'sep_token_id': None, 'decoder_start_token_id': None, 'task_specific_params': None, 'problem_type': None, '_name_or_path': 'Jean-Baptiste/roberta-large-ner-english', 'transformers_version': '4.37.0', 'gradient_checkpointing': False, 'model_type': 'roberta', 'vocab_size': 50265, 'hidden_size': 1024, 'num_hidden_layers': 24, 'num_attention_heads': 16, 'hidden_act': 'gelu', 'intermediate_size': 4096, 'hidden_dropout_prob': 0.1, 'attention_probs_dropout_prob': 0.1, 'max_position_embeddings': 514, 'type_vocab_size': 1, 'initializer_range': 0.02, 'layer_norm_eps': 1e-05, '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': 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/Feb24_19-24-54_ff5231669072', '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_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}
+2024-02-24 19:25:00,103 INFO    MainThread:34 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-02-24 19:25:00,103 INFO    MainThread:34 [wandb_init.py:_pause_backend():437] pausing backend
+2024-02-24 19:28:22,439 INFO    MainThread:34 [wandb_init.py:_resume_backend():442] resuming backend
+2024-02-24 19:28:23,332 INFO    MainThread:34 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-02-24 19:28:23,333 INFO    MainThread:34 [wandb_init.py:_pause_backend():437] pausing backend
+2024-02-24 19:28:26,996 INFO    MainThread:34 [wandb_init.py:_resume_backend():442] resuming backend
+2024-02-24 19:28:27,642 INFO    MainThread:34 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-02-24 19:28:27,642 INFO    MainThread:34 [wandb_init.py:_pause_backend():437] pausing backend
+2024-02-24 19:28:30,742 INFO    MainThread:34 [wandb_init.py:_resume_backend():442] resuming backend
+2024-02-24 19:28:30,743 INFO    MainThread:34 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-02-24 19:28:30,744 INFO    MainThread:34 [wandb_init.py:_pause_backend():437] pausing backend
+2024-02-24 19:28:32,538 INFO    MainThread:34 [wandb_init.py:_resume_backend():442] resuming backend
+2024-02-24 19:28:38,902 INFO    MainThread:34 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-02-24 19:28:38,902 INFO    MainThread:34 [wandb_init.py:_pause_backend():437] pausing backend
+2024-02-24 19:28:38,908 INFO    MainThread:34 [wandb_init.py:_resume_backend():442] resuming backend
+2024-02-24 19:29:15,794 INFO    MainThread:34 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-02-24 19:29:15,794 INFO    MainThread:34 [wandb_init.py:_pause_backend():437] pausing backend
+2024-02-24 19:29:15,802 INFO    MainThread:34 [wandb_init.py:_resume_backend():442] resuming backend
+2024-02-24 19:29:15,845 INFO    MainThread:34 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-02-24 19:29:15,845 INFO    MainThread:34 [wandb_init.py:_pause_backend():437] pausing backend
+2024-02-24 19:29:15,852 INFO    MainThread:34 [wandb_init.py:_resume_backend():442] resuming backend
+2024-02-24 19:29:15,856 INFO    MainThread:34 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-02-24 19:29:15,857 INFO    MainThread:34 [wandb_init.py:_pause_backend():437] pausing backend
+2024-02-24 19:29:15,865 INFO    MainThread:34 [wandb_init.py:_resume_backend():442] resuming backend
+2024-02-24 19:29:16,721 INFO    MainThread:34 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-02-24 19:29:16,721 INFO    MainThread:34 [wandb_init.py:_pause_backend():437] pausing backend
+2024-02-24 19:29:16,729 INFO    MainThread:34 [wandb_init.py:_resume_backend():442] resuming backend
+2024-02-24 19:29:17,115 INFO    MainThread:34 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-02-24 19:29:17,116 INFO    MainThread:34 [wandb_init.py:_pause_backend():437] pausing backend
+2024-02-24 19:29:17,126 INFO    MainThread:34 [wandb_init.py:_resume_backend():442] resuming backend
+2024-02-24 19:29:17,129 INFO    MainThread:34 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-02-24 19:29:17,129 INFO    MainThread:34 [wandb_init.py:_pause_backend():437] pausing backend
+2024-02-24 19:29:17,135 INFO    MainThread:34 [wandb_init.py:_resume_backend():442] resuming backend
+2024-02-24 19:29:17,192 INFO    MainThread:34 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-02-24 19:29:17,192 INFO    MainThread:34 [wandb_init.py:_pause_backend():437] pausing backend
+2024-02-24 19:29:17,197 INFO    MainThread:34 [wandb_init.py:_resume_backend():442] resuming backend
+2024-02-24 19:29:17,198 INFO    MainThread:34 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-02-24 19:29:17,199 INFO    MainThread:34 [wandb_init.py:_pause_backend():437] pausing backend
+2024-02-24 19:29:33,485 INFO    MainThread:34 [wandb_init.py:_resume_backend():442] resuming backend
+2024-02-24 19:29:38,958 INFO    MainThread:34 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-02-24 19:29:38,959 INFO    MainThread:34 [wandb_init.py:_pause_backend():437] pausing backend
+2024-02-24 19:29:53,503 INFO    MainThread:34 [wandb_init.py:_resume_backend():442] resuming backend
+2024-02-24 19:29:54,037 INFO    MainThread:34 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-02-24 19:29:54,037 INFO    MainThread:34 [wandb_init.py:_pause_backend():437] pausing backend
+2024-02-24 19:30:15,599 INFO    MainThread:34 [wandb_init.py:_resume_backend():442] resuming backend
+2024-02-24 19:30:16,368 INFO    MainThread:34 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-02-24 19:30:16,368 INFO    MainThread:34 [wandb_init.py:_pause_backend():437] pausing backend
+2024-02-24 19:30:18,566 INFO    MainThread:34 [wandb_init.py:_resume_backend():442] resuming backend
+2024-02-24 19:30:18,569 INFO    MainThread:34 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-02-24 19:30:18,569 INFO    MainThread:34 [wandb_init.py:_pause_backend():437] pausing backend
+2024-02-24 19:30:20,487 INFO    MainThread:34 [wandb_init.py:_resume_backend():442] resuming backend
+2024-02-24 19:30:20,495 INFO    MainThread:34 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-02-24 19:30:20,495 INFO    MainThread:34 [wandb_init.py:_pause_backend():437] pausing backend
+2024-02-24 19:30:22,138 INFO    MainThread:34 [wandb_init.py:_resume_backend():442] resuming backend
+2024-02-24 19:30:27,097 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': 'float32', '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': ['DistilBertForTokenClassification'], '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': 'malduwais/distilbert-base-uncased-finetuned-ner', '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/Feb24_19-30-22_ff5231669072', '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-20240224_185021-766tgrrc/files/config.yaml

@@ -96,9 +96,29 @@ _wandb:
       5: 1
       6:
       - 1
+    - 1: train/train_runtime
+      5: 1
+      6:
+      - 1
+    - 1: train/train_samples_per_second
+      5: 1
+      6:
+      - 1
+    - 1: train/train_steps_per_second
+      5: 1
+      6:
+      - 1
+    - 1: train/total_flos
+      5: 1
+      6:
+      - 1
+    - 1: train/train_loss
+      5: 1
+      6:
+      - 1
 vocab_size:
   desc: null
-  value: 28996
+  value: 30522
 max_position_embeddings:
   desc: null
   value: 512
@@ -149,7 +169,7 @@ torchscript:
   value: false
 torch_dtype:
   desc: null
-  value: null
+  value: float32
 use_bfloat16:
   desc: null
   value: false
@@ -258,7 +278,7 @@ begin_suppress_tokens:
 architectures:
   desc: null
   value:
-  - DistilBertForMaskedLM
+  - DistilBertForTokenClassification
 finetuning_task:
   desc: null
   value: null
@@ -323,7 +343,7 @@ problem_type:
   value: null
 _name_or_path:
   desc: null
-  value: distilbert-base-cased
+  value: malduwais/distilbert-base-uncased-finetuned-ner
 transformers_version:
   desc: null
   value: 4.37.0
@@ -425,7 +445,7 @@ log_on_each_node:
   value: true
 logging_dir:
   desc: null
-  value: /kaggle/working/runs/Feb24_18-50-16_ff5231669072
+  value: /kaggle/working/runs/Feb24_19-30-22_ff5231669072
 logging_strategy:
   desc: null
   value: steps
@@ -695,3 +715,39 @@ include_num_input_tokens_seen:
 neftune_noise_alpha:
   desc: null
   value: null
+hidden_size:
+  desc: null
+  value: 1024
+num_hidden_layers:
+  desc: null
+  value: 24
+num_attention_heads:
+  desc: null
+  value: 16
+hidden_act:
+  desc: null
+  value: gelu
+intermediate_size:
+  desc: null
+  value: 4096
+hidden_dropout_prob:
+  desc: null
+  value: 0.1
+attention_probs_dropout_prob:
+  desc: null
+  value: 0.1
+type_vocab_size:
+  desc: null
+  value: 1
+layer_norm_eps:
+  desc: null
+  value: 1.0e-05
+position_embedding_type:
+  desc: null
+  value: absolute
+use_cache:
+  desc: null
+  value: true
+classifier_dropout:
+  desc: null
+  value: null

wandb/run-20240224_185021-766tgrrc/files/output.log

@@ -1 +1,28 @@
 /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.
+  _warn_prf(average, modifier, msg_start, len(result))
+/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.
+  _warn_prf(average, modifier, msg_start, len(result))
+Token will not been saved to git credential helper. Pass `add_to_git_credential=True` if you want to set the git credential as well.
+Token is valid (permission: write).
+Your token has been saved to /root/.cache/huggingface/token
+Login successful
+wandb: WARNING Calling wandb.login() after wandb.init() has no effect.
+Some weights of RobertaForTokenClassification were not initialized from the model checkpoint at Jean-Baptiste/roberta-large-ner-english and are newly initialized because the shapes did not match:
+- classifier.bias: found shape torch.Size([5]) in the checkpoint and torch.Size([13]) in the model instantiated
+- classifier.weight: found shape torch.Size([5, 1024]) in the checkpoint and torch.Size([13, 1024]) in the model instantiated
+You should probably TRAIN this model on a down-stream task to be able to use it for predictions and inference.
+Token will not been saved to git credential helper. Pass `add_to_git_credential=True` if you want to set the git credential as well.
+Token is valid (permission: write).
+Your token has been saved to /root/.cache/huggingface/token
+Login successful
+wandb: WARNING Calling wandb.login() after wandb.init() has no effect.
+Some weights of DistilBertForTokenClassification were not initialized from the model checkpoint at malduwais/distilbert-base-uncased-finetuned-ner and are newly initialized because the shapes did not match:
+- classifier.bias: found shape torch.Size([9]) in the checkpoint and torch.Size([13]) in the model instantiated
+- classifier.weight: found shape torch.Size([9, 768]) in the checkpoint and torch.Size([13, 768]) in the model instantiated
+You should probably TRAIN this model on a down-stream task to be able to use it for predictions and inference.
+Some weights of DistilBertForTokenClassification were not initialized from the model checkpoint at malduwais/distilbert-base-uncased-finetuned-ner and are newly initialized because the shapes did not match:
+- classifier.bias: found shape torch.Size([9]) in the checkpoint and torch.Size([13]) in the model instantiated
+- classifier.weight: found shape torch.Size([9, 768]) in the checkpoint and torch.Size([13, 768]) in the model instantiated
+You should probably TRAIN this model on a down-stream task to be able to use it for predictions and inference.
+/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.
+  _warn_prf(average, modifier, msg_start, len(result))

wandb/run-20240224_185021-766tgrrc/files/wandb-summary.json

@@ -1 +1 @@
-{"eval/loss": 0.3269957900047302, "eval/precision": 0.015558860542272051, "eval/recall": 0.5714285714285714, "eval/f1": 0.030292905668782715, "eval/accuracy": 0.9845650700610603, "eval/f5": 0.05554421074127016, "eval/runtime": 33.847, "eval/samples_per_second": 40.24, "eval/steps_per_second": 2.541, "train/epoch": 1.0, "train/global_step": 86, "_timestamp": 1708800836.8129733, "_runtime": 215.53317022323608, "_step": 0}
+{"eval/loss": 0.22381609678268433, "eval/precision": 0.020591422820870103, "eval/recall": 0.532, "eval/f1": 0.03964823371590401, "eval/accuracy": 0.9889450542396816, "eval/f5": 0.0627901487135101, "eval/runtime": 33.9777, "eval/samples_per_second": 40.085, "eval/steps_per_second": 2.531, "train/epoch": 1.0, "train/global_step": 86, "_timestamp": 1708803214.5390868, "_runtime": 2593.2592837810516, "_step": 3, "train/train_runtime": 406.6055, "train/train_samples_per_second": 26.783, "train/train_steps_per_second": 0.423, "train/total_flos": 1423095247411200.0, "train/train_loss": 0.9756098902502726}

wandb/run-20240224_185021-766tgrrc/logs/debug.log

@@ -29,3 +29,144 @@ config: {}
 2024-02-24 18:50:51,949 INFO    MainThread:34 [wandb_run.py:_redirect():2178] Redirects installed.
 2024-02-24 18:50:51,950 INFO    MainThread:34 [wandb_init.py:init():847] run started, returning control to user process
 2024-02-24 18:50:51,956 INFO    MainThread:34 [wandb_run.py:_config_callback():1342] config_cb None None {'vocab_size': 28996, '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-cased', 'transformers_version': '4.37.0', 'model_type': 'distilbert', 'output_past': True, '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/Feb24_18-50-16_ff5231669072', '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}
+2024-02-24 18:57:14,450 INFO    MainThread:34 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-02-24 18:57:14,451 INFO    MainThread:34 [wandb_init.py:_pause_backend():437] pausing backend
+2024-02-24 18:57:14,456 INFO    MainThread:34 [wandb_init.py:_resume_backend():442] resuming backend
+2024-02-24 18:57:14,764 INFO    MainThread:34 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-02-24 18:57:14,764 INFO    MainThread:34 [wandb_init.py:_pause_backend():437] pausing backend
+2024-02-24 18:57:14,769 INFO    MainThread:34 [wandb_init.py:_resume_backend():442] resuming backend
+2024-02-24 18:57:14,774 INFO    MainThread:34 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-02-24 18:57:14,774 INFO    MainThread:34 [wandb_init.py:_pause_backend():437] pausing backend
+2024-02-24 18:57:14,780 INFO    MainThread:34 [wandb_init.py:_resume_backend():442] resuming backend
+2024-02-24 18:57:15,111 INFO    MainThread:34 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-02-24 18:57:15,112 INFO    MainThread:34 [wandb_init.py:_pause_backend():437] pausing backend
+2024-02-24 19:16:37,055 INFO    MainThread:34 [wandb_init.py:_resume_backend():442] resuming backend
+2024-02-24 19:16:37,851 INFO    MainThread:34 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-02-24 19:16:37,851 INFO    MainThread:34 [wandb_init.py:_pause_backend():437] pausing backend
+2024-02-24 19:16:45,072 INFO    MainThread:34 [wandb_init.py:_resume_backend():442] resuming backend
+2024-02-24 19:16:45,074 INFO    MainThread:34 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-02-24 19:16:45,074 INFO    MainThread:34 [wandb_init.py:_pause_backend():437] pausing backend
+2024-02-24 19:16:47,316 INFO    MainThread:34 [wandb_init.py:_resume_backend():442] resuming backend
+2024-02-24 19:16:48,322 INFO    MainThread:34 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-02-24 19:16:48,322 INFO    MainThread:34 [wandb_init.py:_pause_backend():437] pausing backend
+2024-02-24 19:17:23,661 INFO    MainThread:34 [wandb_init.py:_resume_backend():442] resuming backend
+2024-02-24 19:17:31,220 INFO    MainThread:34 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-02-24 19:17:31,221 INFO    MainThread:34 [wandb_init.py:_pause_backend():437] pausing backend
+2024-02-24 19:18:36,781 INFO    MainThread:34 [wandb_init.py:_resume_backend():442] resuming backend
+2024-02-24 19:18:38,339 INFO    MainThread:34 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-02-24 19:18:38,339 INFO    MainThread:34 [wandb_init.py:_pause_backend():437] pausing backend
+2024-02-24 19:18:53,063 INFO    MainThread:34 [wandb_init.py:_resume_backend():442] resuming backend
+2024-02-24 19:18:53,734 INFO    MainThread:34 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-02-24 19:18:53,734 INFO    MainThread:34 [wandb_init.py:_pause_backend():437] pausing backend
+2024-02-24 19:18:56,646 INFO    MainThread:34 [wandb_init.py:_resume_backend():442] resuming backend
+2024-02-24 19:19:01,360 INFO    MainThread:34 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-02-24 19:19:01,360 INFO    MainThread:34 [wandb_init.py:_pause_backend():437] pausing backend
+2024-02-24 19:19:01,371 INFO    MainThread:34 [wandb_init.py:_resume_backend():442] resuming backend
+2024-02-24 19:19:01,374 INFO    MainThread:34 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-02-24 19:19:01,375 INFO    MainThread:34 [wandb_init.py:_pause_backend():437] pausing backend
+2024-02-24 19:19:05,298 INFO    MainThread:34 [wandb_init.py:_resume_backend():442] resuming backend
+2024-02-24 19:19:11,995 INFO    MainThread:34 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-02-24 19:19:11,995 INFO    MainThread:34 [wandb_init.py:_pause_backend():437] pausing backend
+2024-02-24 19:19:12,001 INFO    MainThread:34 [wandb_init.py:_resume_backend():442] resuming backend
+2024-02-24 19:19:51,045 INFO    MainThread:34 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-02-24 19:19:51,045 INFO    MainThread:34 [wandb_init.py:_pause_backend():437] pausing backend
+2024-02-24 19:19:51,054 INFO    MainThread:34 [wandb_init.py:_resume_backend():442] resuming backend
+2024-02-24 19:19:51,081 INFO    MainThread:34 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-02-24 19:19:51,081 INFO    MainThread:34 [wandb_init.py:_pause_backend():437] pausing backend
+2024-02-24 19:19:51,088 INFO    MainThread:34 [wandb_init.py:_resume_backend():442] resuming backend
+2024-02-24 19:19:51,095 INFO    MainThread:34 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-02-24 19:19:51,095 INFO    MainThread:34 [wandb_init.py:_pause_backend():437] pausing backend
+2024-02-24 19:19:51,106 INFO    MainThread:34 [wandb_init.py:_resume_backend():442] resuming backend
+2024-02-24 19:19:51,978 INFO    MainThread:34 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-02-24 19:19:51,978 INFO    MainThread:34 [wandb_init.py:_pause_backend():437] pausing backend
+2024-02-24 19:19:51,984 INFO    MainThread:34 [wandb_init.py:_resume_backend():442] resuming backend
+2024-02-24 19:19:52,402 INFO    MainThread:34 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-02-24 19:19:52,402 INFO    MainThread:34 [wandb_init.py:_pause_backend():437] pausing backend
+2024-02-24 19:19:52,416 INFO    MainThread:34 [wandb_init.py:_resume_backend():442] resuming backend
+2024-02-24 19:19:52,419 INFO    MainThread:34 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-02-24 19:19:52,419 INFO    MainThread:34 [wandb_init.py:_pause_backend():437] pausing backend
+2024-02-24 19:19:52,426 INFO    MainThread:34 [wandb_init.py:_resume_backend():442] resuming backend
+2024-02-24 19:19:52,489 INFO    MainThread:34 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-02-24 19:19:52,489 INFO    MainThread:34 [wandb_init.py:_pause_backend():437] pausing backend
+2024-02-24 19:19:52,494 INFO    MainThread:34 [wandb_init.py:_resume_backend():442] resuming backend
+2024-02-24 19:19:52,496 INFO    MainThread:34 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-02-24 19:19:52,496 INFO    MainThread:34 [wandb_init.py:_pause_backend():437] pausing backend
+2024-02-24 19:19:52,504 INFO    MainThread:34 [wandb_init.py:_resume_backend():442] resuming backend
+2024-02-24 19:19:53,650 INFO    MainThread:34 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-02-24 19:19:53,650 INFO    MainThread:34 [wandb_init.py:_pause_backend():437] pausing backend
+2024-02-24 19:22:09,466 INFO    MainThread:34 [wandb_init.py:_resume_backend():442] resuming backend
+2024-02-24 19:22:09,487 INFO    MainThread:34 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-02-24 19:22:09,487 INFO    MainThread:34 [wandb_init.py:_pause_backend():437] pausing backend
+2024-02-24 19:24:04,362 INFO    MainThread:34 [wandb_init.py:_resume_backend():442] resuming backend
+2024-02-24 19:24:08,582 INFO    MainThread:34 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-02-24 19:24:08,583 INFO    MainThread:34 [wandb_init.py:_pause_backend():437] pausing backend
+2024-02-24 19:24:26,820 INFO    MainThread:34 [wandb_init.py:_resume_backend():442] resuming backend
+2024-02-24 19:24:26,822 INFO    MainThread:34 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-02-24 19:24:26,822 INFO    MainThread:34 [wandb_init.py:_pause_backend():437] pausing backend
+2024-02-24 19:24:30,441 INFO    MainThread:34 [wandb_init.py:_resume_backend():442] resuming backend
+2024-02-24 19:24:30,447 INFO    MainThread:34 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-02-24 19:24:30,449 INFO    MainThread:34 [wandb_init.py:_pause_backend():437] pausing backend
+2024-02-24 19:24:40,382 INFO    MainThread:34 [wandb_init.py:_resume_backend():442] resuming backend
+2024-02-24 19:24:40,572 INFO    MainThread:34 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-02-24 19:24:40,573 INFO    MainThread:34 [wandb_init.py:_pause_backend():437] pausing backend
+2024-02-24 19:24:42,828 INFO    MainThread:34 [wandb_init.py:_resume_backend():442] resuming backend
+2024-02-24 19:24:48,476 INFO    MainThread:34 [wandb_run.py:_config_callback():1342] config_cb None None {'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': ['RobertaForTokenClassification'], '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': 0, 'pad_token_id': 1, 'eos_token_id': 2, 'sep_token_id': None, 'decoder_start_token_id': None, 'task_specific_params': None, 'problem_type': None, '_name_or_path': 'Jean-Baptiste/roberta-large-ner-english', 'transformers_version': '4.37.0', 'gradient_checkpointing': False, 'model_type': 'roberta', 'vocab_size': 50265, 'hidden_size': 1024, 'num_hidden_layers': 24, 'num_attention_heads': 16, 'hidden_act': 'gelu', 'intermediate_size': 4096, 'hidden_dropout_prob': 0.1, 'attention_probs_dropout_prob': 0.1, 'max_position_embeddings': 514, 'type_vocab_size': 1, 'initializer_range': 0.02, 'layer_norm_eps': 1e-05, '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': 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/Feb24_19-24-42_ff5231669072', '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_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}
+2024-02-24 19:24:50,854 INFO    MainThread:34 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-02-24 19:24:50,854 INFO    MainThread:34 [wandb_init.py:_pause_backend():437] pausing backend
+2024-02-24 19:24:54,667 INFO    MainThread:34 [wandb_init.py:_resume_backend():442] resuming backend
+2024-02-24 19:24:59,384 INFO    MainThread:34 [wandb_run.py:_config_callback():1342] config_cb None None {'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': ['RobertaForTokenClassification'], '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': 0, 'pad_token_id': 1, 'eos_token_id': 2, 'sep_token_id': None, 'decoder_start_token_id': None, 'task_specific_params': None, 'problem_type': None, '_name_or_path': 'Jean-Baptiste/roberta-large-ner-english', 'transformers_version': '4.37.0', 'gradient_checkpointing': False, 'model_type': 'roberta', 'vocab_size': 50265, 'hidden_size': 1024, 'num_hidden_layers': 24, 'num_attention_heads': 16, 'hidden_act': 'gelu', 'intermediate_size': 4096, 'hidden_dropout_prob': 0.1, 'attention_probs_dropout_prob': 0.1, 'max_position_embeddings': 514, 'type_vocab_size': 1, 'initializer_range': 0.02, 'layer_norm_eps': 1e-05, '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': 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/Feb24_19-24-54_ff5231669072', '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_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}
+2024-02-24 19:25:00,103 INFO    MainThread:34 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-02-24 19:25:00,103 INFO    MainThread:34 [wandb_init.py:_pause_backend():437] pausing backend
+2024-02-24 19:28:22,439 INFO    MainThread:34 [wandb_init.py:_resume_backend():442] resuming backend
+2024-02-24 19:28:23,332 INFO    MainThread:34 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-02-24 19:28:23,333 INFO    MainThread:34 [wandb_init.py:_pause_backend():437] pausing backend
+2024-02-24 19:28:26,996 INFO    MainThread:34 [wandb_init.py:_resume_backend():442] resuming backend
+2024-02-24 19:28:27,642 INFO    MainThread:34 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-02-24 19:28:27,642 INFO    MainThread:34 [wandb_init.py:_pause_backend():437] pausing backend
+2024-02-24 19:28:30,742 INFO    MainThread:34 [wandb_init.py:_resume_backend():442] resuming backend
+2024-02-24 19:28:30,743 INFO    MainThread:34 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-02-24 19:28:30,744 INFO    MainThread:34 [wandb_init.py:_pause_backend():437] pausing backend
+2024-02-24 19:28:32,538 INFO    MainThread:34 [wandb_init.py:_resume_backend():442] resuming backend
+2024-02-24 19:28:38,902 INFO    MainThread:34 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-02-24 19:28:38,902 INFO    MainThread:34 [wandb_init.py:_pause_backend():437] pausing backend
+2024-02-24 19:28:38,908 INFO    MainThread:34 [wandb_init.py:_resume_backend():442] resuming backend
+2024-02-24 19:29:15,794 INFO    MainThread:34 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-02-24 19:29:15,794 INFO    MainThread:34 [wandb_init.py:_pause_backend():437] pausing backend
+2024-02-24 19:29:15,802 INFO    MainThread:34 [wandb_init.py:_resume_backend():442] resuming backend
+2024-02-24 19:29:15,845 INFO    MainThread:34 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-02-24 19:29:15,845 INFO    MainThread:34 [wandb_init.py:_pause_backend():437] pausing backend
+2024-02-24 19:29:15,852 INFO    MainThread:34 [wandb_init.py:_resume_backend():442] resuming backend
+2024-02-24 19:29:15,856 INFO    MainThread:34 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-02-24 19:29:15,857 INFO    MainThread:34 [wandb_init.py:_pause_backend():437] pausing backend
+2024-02-24 19:29:15,865 INFO    MainThread:34 [wandb_init.py:_resume_backend():442] resuming backend
+2024-02-24 19:29:16,721 INFO    MainThread:34 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-02-24 19:29:16,721 INFO    MainThread:34 [wandb_init.py:_pause_backend():437] pausing backend
+2024-02-24 19:29:16,729 INFO    MainThread:34 [wandb_init.py:_resume_backend():442] resuming backend
+2024-02-24 19:29:17,115 INFO    MainThread:34 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-02-24 19:29:17,116 INFO    MainThread:34 [wandb_init.py:_pause_backend():437] pausing backend
+2024-02-24 19:29:17,126 INFO    MainThread:34 [wandb_init.py:_resume_backend():442] resuming backend
+2024-02-24 19:29:17,129 INFO    MainThread:34 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-02-24 19:29:17,129 INFO    MainThread:34 [wandb_init.py:_pause_backend():437] pausing backend
+2024-02-24 19:29:17,135 INFO    MainThread:34 [wandb_init.py:_resume_backend():442] resuming backend
+2024-02-24 19:29:17,192 INFO    MainThread:34 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-02-24 19:29:17,192 INFO    MainThread:34 [wandb_init.py:_pause_backend():437] pausing backend
+2024-02-24 19:29:17,197 INFO    MainThread:34 [wandb_init.py:_resume_backend():442] resuming backend
+2024-02-24 19:29:17,198 INFO    MainThread:34 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-02-24 19:29:17,199 INFO    MainThread:34 [wandb_init.py:_pause_backend():437] pausing backend
+2024-02-24 19:29:33,485 INFO    MainThread:34 [wandb_init.py:_resume_backend():442] resuming backend
+2024-02-24 19:29:38,958 INFO    MainThread:34 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-02-24 19:29:38,959 INFO    MainThread:34 [wandb_init.py:_pause_backend():437] pausing backend
+2024-02-24 19:29:53,503 INFO    MainThread:34 [wandb_init.py:_resume_backend():442] resuming backend
+2024-02-24 19:29:54,037 INFO    MainThread:34 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-02-24 19:29:54,037 INFO    MainThread:34 [wandb_init.py:_pause_backend():437] pausing backend
+2024-02-24 19:30:15,599 INFO    MainThread:34 [wandb_init.py:_resume_backend():442] resuming backend
+2024-02-24 19:30:16,368 INFO    MainThread:34 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-02-24 19:30:16,368 INFO    MainThread:34 [wandb_init.py:_pause_backend():437] pausing backend
+2024-02-24 19:30:18,566 INFO    MainThread:34 [wandb_init.py:_resume_backend():442] resuming backend
+2024-02-24 19:30:18,569 INFO    MainThread:34 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-02-24 19:30:18,569 INFO    MainThread:34 [wandb_init.py:_pause_backend():437] pausing backend
+2024-02-24 19:30:20,487 INFO    MainThread:34 [wandb_init.py:_resume_backend():442] resuming backend
+2024-02-24 19:30:20,495 INFO    MainThread:34 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-02-24 19:30:20,495 INFO    MainThread:34 [wandb_init.py:_pause_backend():437] pausing backend
+2024-02-24 19:30:22,138 INFO    MainThread:34 [wandb_init.py:_resume_backend():442] resuming backend
+2024-02-24 19:30:27,097 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': 'float32', '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': ['DistilBertForTokenClassification'], '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': 'malduwais/distilbert-base-uncased-finetuned-ner', '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/Feb24_19-30-22_ff5231669072', '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}