Training in progress, step 500

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+wandb/run-20240118_004236-6kmvcnsc/run-6kmvcnsc.wandb filter=lfs diff=lfs merge=lfs -text

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:89d3caf5e753ddd28dbf20ba87dfc6dd20b3fbae2ebc67fe4cf6117f23cdb193
+oid sha256:31e4cf3612059e26c5e4cda65c13ec7c7ce40431058c90a0af3a6d315bd6d947
 size 328693404

runs/Jan18_01-20-04_455f56c2d2db/events.out.tfevents.1705540806.455f56c2d2db.26.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2f69a3138e5eb7ef7fa2b6bfd1a6d94b635ea2c8c0c26e38b05de50a0e8e401d
+size 4550

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d185bcfaec2357be8b96b5dc3047e3e4697610f1e4371979cf6bd680878743fa
+oid sha256:09e0e243d89e78290d9aee257a8f153a266de08d0fe6f41cc26a087e5415de13
 size 4283

wandb/debug.log

@@ -31,3 +31,82 @@ config: {}
 2024-01-18 00:50:15,569 INFO    MainThread:26 [jupyter.py:save_ipynb():373] not saving jupyter notebook
 2024-01-18 00:50:15,569 INFO    MainThread:26 [wandb_init.py:_pause_backend():437] pausing backend
 2024-01-18 00:50:15,577 INFO    MainThread:26 [wandb_init.py:_resume_backend():442] resuming backend
+2024-01-18 00:50:31,745 INFO    MainThread:26 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-01-18 00:50:31,745 INFO    MainThread:26 [wandb_init.py:_pause_backend():437] pausing backend
+2024-01-18 00:52:04,477 INFO    MainThread:26 [wandb_init.py:_resume_backend():442] resuming backend
+2024-01-18 00:52:04,478 INFO    MainThread:26 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-01-18 00:52:04,478 INFO    MainThread:26 [wandb_init.py:_pause_backend():437] pausing backend
+2024-01-18 00:52:04,806 INFO    MainThread:26 [wandb_init.py:_resume_backend():442] resuming backend
+2024-01-18 00:52:04,807 INFO    MainThread:26 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-01-18 00:52:04,808 INFO    MainThread:26 [wandb_init.py:_pause_backend():437] pausing backend
+2024-01-18 00:52:05,228 INFO    MainThread:26 [wandb_init.py:_resume_backend():442] resuming backend
+2024-01-18 00:52:05,739 INFO    MainThread:26 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-01-18 00:52:05,739 INFO    MainThread:26 [wandb_init.py:_pause_backend():437] pausing backend
+2024-01-18 00:52:09,038 INFO    MainThread:26 [wandb_init.py:_resume_backend():442] resuming backend
+2024-01-18 00:52:09,360 INFO    MainThread:26 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-01-18 00:52:09,361 INFO    MainThread:26 [wandb_init.py:_pause_backend():437] pausing backend
+2024-01-18 00:52:09,369 INFO    MainThread:26 [wandb_init.py:_resume_backend():442] resuming backend
+2024-01-18 00:52:09,431 INFO    MainThread:26 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-01-18 00:52:09,431 INFO    MainThread:26 [wandb_init.py:_pause_backend():437] pausing backend
+2024-01-18 00:52:12,944 INFO    MainThread:26 [wandb_init.py:_resume_backend():442] resuming backend
+2024-01-18 00:52:13,013 INFO    MainThread:26 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-01-18 00:52:13,013 INFO    MainThread:26 [wandb_init.py:_pause_backend():437] pausing backend
+2024-01-18 00:52:43,606 INFO    MainThread:26 [wandb_init.py:_resume_backend():442] resuming backend
+2024-01-18 00:52:43,675 INFO    MainThread:26 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-01-18 00:52:43,675 INFO    MainThread:26 [wandb_init.py:_pause_backend():437] pausing backend
+2024-01-18 00:53:47,849 INFO    MainThread:26 [wandb_init.py:_resume_backend():442] resuming backend
+2024-01-18 00:53:47,922 INFO    MainThread:26 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-01-18 00:53:47,922 INFO    MainThread:26 [wandb_init.py:_pause_backend():437] pausing backend
+2024-01-18 00:55:01,335 INFO    MainThread:26 [wandb_init.py:_resume_backend():442] resuming backend
+2024-01-18 00:55:05,847 INFO    MainThread:26 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-01-18 00:55:05,847 INFO    MainThread:26 [wandb_init.py:_pause_backend():437] pausing backend
+2024-01-18 00:56:38,379 INFO    MainThread:26 [wandb_init.py:_resume_backend():442] resuming backend
+2024-01-18 00:56:38,441 INFO    MainThread:26 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-01-18 00:56:38,441 INFO    MainThread:26 [wandb_init.py:_pause_backend():437] pausing backend
+2024-01-18 00:57:26,060 INFO    MainThread:26 [wandb_init.py:_resume_backend():442] resuming backend
+2024-01-18 00:57:26,127 INFO    MainThread:26 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-01-18 00:57:26,127 INFO    MainThread:26 [wandb_init.py:_pause_backend():437] pausing backend
+2024-01-18 01:00:33,963 INFO    MainThread:26 [wandb_init.py:_resume_backend():442] resuming backend
+2024-01-18 01:00:33,966 INFO    MainThread:26 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-01-18 01:00:33,967 INFO    MainThread:26 [wandb_init.py:_pause_backend():437] pausing backend
+2024-01-18 01:00:36,970 INFO    MainThread:26 [wandb_init.py:_resume_backend():442] resuming backend
+2024-01-18 01:00:37,038 INFO    MainThread:26 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-01-18 01:00:37,038 INFO    MainThread:26 [wandb_init.py:_pause_backend():437] pausing backend
+2024-01-18 01:13:04,835 INFO    MainThread:26 [wandb_init.py:_resume_backend():442] resuming backend
+2024-01-18 01:13:04,908 INFO    MainThread:26 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-01-18 01:13:04,908 INFO    MainThread:26 [wandb_init.py:_pause_backend():437] pausing backend
+2024-01-18 01:15:04,532 INFO    MainThread:26 [wandb_init.py:_resume_backend():442] resuming backend
+2024-01-18 01:15:05,754 INFO    MainThread:26 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-01-18 01:15:05,755 INFO    MainThread:26 [wandb_init.py:_pause_backend():437] pausing backend
+2024-01-18 01:15:31,194 INFO    MainThread:26 [wandb_init.py:_resume_backend():442] resuming backend
+2024-01-18 01:15:31,203 INFO    MainThread:26 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-01-18 01:15:31,203 INFO    MainThread:26 [wandb_init.py:_pause_backend():437] pausing backend
+2024-01-18 01:15:40,270 INFO    MainThread:26 [wandb_init.py:_resume_backend():442] resuming backend
+2024-01-18 01:15:40,332 INFO    MainThread:26 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-01-18 01:15:40,332 INFO    MainThread:26 [wandb_init.py:_pause_backend():437] pausing backend
+2024-01-18 01:16:17,736 INFO    MainThread:26 [wandb_init.py:_resume_backend():442] resuming backend
+2024-01-18 01:16:17,799 INFO    MainThread:26 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-01-18 01:16:17,800 INFO    MainThread:26 [wandb_init.py:_pause_backend():437] pausing backend
+2024-01-18 01:16:53,083 INFO    MainThread:26 [wandb_init.py:_resume_backend():442] resuming backend
+2024-01-18 01:16:54,090 INFO    MainThread:26 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-01-18 01:16:54,091 INFO    MainThread:26 [wandb_init.py:_pause_backend():437] pausing backend
+2024-01-18 01:17:15,597 INFO    MainThread:26 [wandb_init.py:_resume_backend():442] resuming backend
+2024-01-18 01:17:15,658 INFO    MainThread:26 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-01-18 01:17:15,658 INFO    MainThread:26 [wandb_init.py:_pause_backend():437] pausing backend
+2024-01-18 01:18:03,271 INFO    MainThread:26 [wandb_init.py:_resume_backend():442] resuming backend
+2024-01-18 01:18:27,461 INFO    MainThread:26 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-01-18 01:18:27,462 INFO    MainThread:26 [wandb_init.py:_pause_backend():437] pausing backend
+2024-01-18 01:18:45,833 INFO    MainThread:26 [wandb_init.py:_resume_backend():442] resuming backend
+2024-01-18 01:19:10,184 INFO    MainThread:26 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-01-18 01:19:10,185 INFO    MainThread:26 [wandb_init.py:_pause_backend():437] pausing backend
+2024-01-18 01:20:04,885 INFO    MainThread:26 [wandb_init.py:_resume_backend():442] resuming backend
+2024-01-18 01:20:04,890 INFO    MainThread:26 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-01-18 01:20:04,890 INFO    MainThread:26 [wandb_init.py:_pause_backend():437] pausing backend
+2024-01-18 01:20:05,188 INFO    MainThread:26 [wandb_init.py:_resume_backend():442] resuming backend
+2024-01-18 01:20:05,332 INFO    MainThread:26 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-01-18 01:20:05,333 INFO    MainThread:26 [wandb_init.py:_pause_backend():437] pausing backend
+2024-01-18 01:20:05,919 INFO    MainThread:26 [wandb_init.py:_resume_backend():442] resuming backend
+2024-01-18 01:20:05,920 INFO    MainThread:26 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-01-18 01:20:05,921 INFO    MainThread:26 [wandb_init.py:_pause_backend():437] pausing backend
+2024-01-18 01:20:06,232 INFO    MainThread:26 [wandb_init.py:_resume_backend():442] resuming backend
+2024-01-18 01:20:06,708 INFO    MainThread:26 [wandb_run.py:_config_callback():1342] config_cb None None {'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, '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, 'chunk_size_feed_forward': 0, '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': ['RobertaForMaskedLM'], 'finetuning_task': None, 'id2label': {0: 'LABEL_0', 1: 'LABEL_1'}, 'label2id': {'LABEL_0': 0, 'LABEL_1': 1}, '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': 'distilroberta-base', 'transformers_version': '4.36.2', 'model_type': 'roberta', 'vocab_size': 50265, 'hidden_size': 768, 'num_hidden_layers': 6, 'num_attention_heads': 12, 'hidden_act': 'gelu', 'intermediate_size': 3072, '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': False, 'do_predict': False, 'evaluation_strategy': 'no', 'prediction_loss_only': False, 'per_device_train_batch_size': 8, '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': 100, '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/Jan18_01-20-04_455f56c2d2db', 'logging_strategy': 'steps', 'logging_first_step': False, 'logging_steps': 500, 'logging_nan_inf_filter': True, 'save_strategy': 'steps', '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': False, 'metric_for_best_model': None, 'greater_is_better': None, 'ignore_data_skip': False, 'fsdp': [], 'fsdp_min_num_params': 0, 'fsdp_config': {'min_num_params': 0, 'xla': False, 'xla_fsdp_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-20240118_004236-6kmvcnsc/files/config.yaml

@@ -100,7 +100,7 @@ torchscript:
   value: false
 torch_dtype:
   desc: null
-  value: null
+  value: float32
 use_bfloat16:
   desc: null
   value: false
@@ -366,7 +366,7 @@ max_grad_norm:
   value: 1.0
 num_train_epochs:
   desc: null
-  value: 200
+  value: 100
 max_steps:
   desc: null
   value: -1
@@ -393,7 +393,7 @@ log_on_each_node:
   value: true
 logging_dir:
   desc: null
-  value: /kaggle/working/runs/Jan18_00-41-31_455f56c2d2db
+  value: /kaggle/working/runs/Jan18_01-20-04_455f56c2d2db
 logging_strategy:
   desc: null
   value: steps

wandb/run-20240118_004236-6kmvcnsc/files/wandb-summary.json

@@ -1 +1 @@
-{"train/loss": 1.1691, "train/learning_rate": 7.692307692307694e-07, "train/epoch": 200.0, "train/global_step": 2600, "_timestamp": 1705539015.5648096, "_runtime": 458.75253558158875, "_step": 5, "train/train_runtime": 481.0951, "train/train_samples_per_second": 85.638, "train/train_steps_per_second": 5.404, "train/total_flos": 532735580432880.0, "train/train_loss": 1.8117729509793794}
+{"train/loss": 0.9314, "train/learning_rate": 1.230769230769231e-05, "train/epoch": 38.46, "train/global_step": 500, "_timestamp": 1705540886.915172, "_runtime": 2330.10289812088, "_step": 6, "train/train_runtime": 481.0951, "train/train_samples_per_second": 85.638, "train/train_steps_per_second": 5.404, "train/total_flos": 532735580432880.0, "train/train_loss": 1.8117729509793794}

wandb/run-20240118_004236-6kmvcnsc/logs/debug.log

@@ -31,3 +31,82 @@ config: {}
 2024-01-18 00:50:15,569 INFO    MainThread:26 [jupyter.py:save_ipynb():373] not saving jupyter notebook
 2024-01-18 00:50:15,569 INFO    MainThread:26 [wandb_init.py:_pause_backend():437] pausing backend
 2024-01-18 00:50:15,577 INFO    MainThread:26 [wandb_init.py:_resume_backend():442] resuming backend
+2024-01-18 00:50:31,745 INFO    MainThread:26 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-01-18 00:50:31,745 INFO    MainThread:26 [wandb_init.py:_pause_backend():437] pausing backend
+2024-01-18 00:52:04,477 INFO    MainThread:26 [wandb_init.py:_resume_backend():442] resuming backend
+2024-01-18 00:52:04,478 INFO    MainThread:26 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-01-18 00:52:04,478 INFO    MainThread:26 [wandb_init.py:_pause_backend():437] pausing backend
+2024-01-18 00:52:04,806 INFO    MainThread:26 [wandb_init.py:_resume_backend():442] resuming backend
+2024-01-18 00:52:04,807 INFO    MainThread:26 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-01-18 00:52:04,808 INFO    MainThread:26 [wandb_init.py:_pause_backend():437] pausing backend
+2024-01-18 00:52:05,228 INFO    MainThread:26 [wandb_init.py:_resume_backend():442] resuming backend
+2024-01-18 00:52:05,739 INFO    MainThread:26 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-01-18 00:52:05,739 INFO    MainThread:26 [wandb_init.py:_pause_backend():437] pausing backend
+2024-01-18 00:52:09,038 INFO    MainThread:26 [wandb_init.py:_resume_backend():442] resuming backend
+2024-01-18 00:52:09,360 INFO    MainThread:26 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-01-18 00:52:09,361 INFO    MainThread:26 [wandb_init.py:_pause_backend():437] pausing backend
+2024-01-18 00:52:09,369 INFO    MainThread:26 [wandb_init.py:_resume_backend():442] resuming backend
+2024-01-18 00:52:09,431 INFO    MainThread:26 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-01-18 00:52:09,431 INFO    MainThread:26 [wandb_init.py:_pause_backend():437] pausing backend
+2024-01-18 00:52:12,944 INFO    MainThread:26 [wandb_init.py:_resume_backend():442] resuming backend
+2024-01-18 00:52:13,013 INFO    MainThread:26 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-01-18 00:52:13,013 INFO    MainThread:26 [wandb_init.py:_pause_backend():437] pausing backend
+2024-01-18 00:52:43,606 INFO    MainThread:26 [wandb_init.py:_resume_backend():442] resuming backend
+2024-01-18 00:52:43,675 INFO    MainThread:26 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-01-18 00:52:43,675 INFO    MainThread:26 [wandb_init.py:_pause_backend():437] pausing backend
+2024-01-18 00:53:47,849 INFO    MainThread:26 [wandb_init.py:_resume_backend():442] resuming backend
+2024-01-18 00:53:47,922 INFO    MainThread:26 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-01-18 00:53:47,922 INFO    MainThread:26 [wandb_init.py:_pause_backend():437] pausing backend
+2024-01-18 00:55:01,335 INFO    MainThread:26 [wandb_init.py:_resume_backend():442] resuming backend
+2024-01-18 00:55:05,847 INFO    MainThread:26 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-01-18 00:55:05,847 INFO    MainThread:26 [wandb_init.py:_pause_backend():437] pausing backend
+2024-01-18 00:56:38,379 INFO    MainThread:26 [wandb_init.py:_resume_backend():442] resuming backend
+2024-01-18 00:56:38,441 INFO    MainThread:26 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-01-18 00:56:38,441 INFO    MainThread:26 [wandb_init.py:_pause_backend():437] pausing backend
+2024-01-18 00:57:26,060 INFO    MainThread:26 [wandb_init.py:_resume_backend():442] resuming backend
+2024-01-18 00:57:26,127 INFO    MainThread:26 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-01-18 00:57:26,127 INFO    MainThread:26 [wandb_init.py:_pause_backend():437] pausing backend
+2024-01-18 01:00:33,963 INFO    MainThread:26 [wandb_init.py:_resume_backend():442] resuming backend
+2024-01-18 01:00:33,966 INFO    MainThread:26 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-01-18 01:00:33,967 INFO    MainThread:26 [wandb_init.py:_pause_backend():437] pausing backend
+2024-01-18 01:00:36,970 INFO    MainThread:26 [wandb_init.py:_resume_backend():442] resuming backend
+2024-01-18 01:00:37,038 INFO    MainThread:26 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-01-18 01:00:37,038 INFO    MainThread:26 [wandb_init.py:_pause_backend():437] pausing backend
+2024-01-18 01:13:04,835 INFO    MainThread:26 [wandb_init.py:_resume_backend():442] resuming backend
+2024-01-18 01:13:04,908 INFO    MainThread:26 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-01-18 01:13:04,908 INFO    MainThread:26 [wandb_init.py:_pause_backend():437] pausing backend
+2024-01-18 01:15:04,532 INFO    MainThread:26 [wandb_init.py:_resume_backend():442] resuming backend
+2024-01-18 01:15:05,754 INFO    MainThread:26 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-01-18 01:15:05,755 INFO    MainThread:26 [wandb_init.py:_pause_backend():437] pausing backend
+2024-01-18 01:15:31,194 INFO    MainThread:26 [wandb_init.py:_resume_backend():442] resuming backend
+2024-01-18 01:15:31,203 INFO    MainThread:26 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-01-18 01:15:31,203 INFO    MainThread:26 [wandb_init.py:_pause_backend():437] pausing backend
+2024-01-18 01:15:40,270 INFO    MainThread:26 [wandb_init.py:_resume_backend():442] resuming backend
+2024-01-18 01:15:40,332 INFO    MainThread:26 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-01-18 01:15:40,332 INFO    MainThread:26 [wandb_init.py:_pause_backend():437] pausing backend
+2024-01-18 01:16:17,736 INFO    MainThread:26 [wandb_init.py:_resume_backend():442] resuming backend
+2024-01-18 01:16:17,799 INFO    MainThread:26 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-01-18 01:16:17,800 INFO    MainThread:26 [wandb_init.py:_pause_backend():437] pausing backend
+2024-01-18 01:16:53,083 INFO    MainThread:26 [wandb_init.py:_resume_backend():442] resuming backend
+2024-01-18 01:16:54,090 INFO    MainThread:26 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-01-18 01:16:54,091 INFO    MainThread:26 [wandb_init.py:_pause_backend():437] pausing backend
+2024-01-18 01:17:15,597 INFO    MainThread:26 [wandb_init.py:_resume_backend():442] resuming backend
+2024-01-18 01:17:15,658 INFO    MainThread:26 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-01-18 01:17:15,658 INFO    MainThread:26 [wandb_init.py:_pause_backend():437] pausing backend
+2024-01-18 01:18:03,271 INFO    MainThread:26 [wandb_init.py:_resume_backend():442] resuming backend
+2024-01-18 01:18:27,461 INFO    MainThread:26 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-01-18 01:18:27,462 INFO    MainThread:26 [wandb_init.py:_pause_backend():437] pausing backend
+2024-01-18 01:18:45,833 INFO    MainThread:26 [wandb_init.py:_resume_backend():442] resuming backend
+2024-01-18 01:19:10,184 INFO    MainThread:26 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-01-18 01:19:10,185 INFO    MainThread:26 [wandb_init.py:_pause_backend():437] pausing backend
+2024-01-18 01:20:04,885 INFO    MainThread:26 [wandb_init.py:_resume_backend():442] resuming backend
+2024-01-18 01:20:04,890 INFO    MainThread:26 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-01-18 01:20:04,890 INFO    MainThread:26 [wandb_init.py:_pause_backend():437] pausing backend
+2024-01-18 01:20:05,188 INFO    MainThread:26 [wandb_init.py:_resume_backend():442] resuming backend
+2024-01-18 01:20:05,332 INFO    MainThread:26 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-01-18 01:20:05,333 INFO    MainThread:26 [wandb_init.py:_pause_backend():437] pausing backend
+2024-01-18 01:20:05,919 INFO    MainThread:26 [wandb_init.py:_resume_backend():442] resuming backend
+2024-01-18 01:20:05,920 INFO    MainThread:26 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-01-18 01:20:05,921 INFO    MainThread:26 [wandb_init.py:_pause_backend():437] pausing backend
+2024-01-18 01:20:06,232 INFO    MainThread:26 [wandb_init.py:_resume_backend():442] resuming backend
+2024-01-18 01:20:06,708 INFO    MainThread:26 [wandb_run.py:_config_callback():1342] config_cb None None {'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, '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, 'chunk_size_feed_forward': 0, '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': ['RobertaForMaskedLM'], 'finetuning_task': None, 'id2label': {0: 'LABEL_0', 1: 'LABEL_1'}, 'label2id': {'LABEL_0': 0, 'LABEL_1': 1}, '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': 'distilroberta-base', 'transformers_version': '4.36.2', 'model_type': 'roberta', 'vocab_size': 50265, 'hidden_size': 768, 'num_hidden_layers': 6, 'num_attention_heads': 12, 'hidden_act': 'gelu', 'intermediate_size': 3072, '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': False, 'do_predict': False, 'evaluation_strategy': 'no', 'prediction_loss_only': False, 'per_device_train_batch_size': 8, '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': 100, '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/Jan18_01-20-04_455f56c2d2db', 'logging_strategy': 'steps', 'logging_first_step': False, 'logging_steps': 500, 'logging_nan_inf_filter': True, 'save_strategy': 'steps', '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': False, 'metric_for_best_model': None, 'greater_is_better': None, 'ignore_data_skip': False, 'fsdp': [], 'fsdp_min_num_params': 0, 'fsdp_config': {'min_num_params': 0, 'xla': False, 'xla_fsdp_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}