Model save

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:88935bf475e67d3135fec89b5e656d0e8a87445bcf72f8a428c36e6599229dc2
+oid sha256:3e220abab935decacfd8145422b630f3df8eac46374c07227a37e2d7215fb26c
 size 328693404

runs/Jan12_02-28-34_ea19ce76d6cc/events.out.tfevents.1705026515.ea19ce76d6cc.10822.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0706f461f7cdfc8e6d0ec72985f42b8df67fbe5a9ff222d2c403ae7df55d9551
-size 5935
+oid sha256:c8eb0e9c429fdf44fa08903a59bbfd3e2af01cf3a4841ee505ff0b722410f15b
+size 6289

wandb/debug-internal.log

@@ -496,3 +496,48 @@
 2024-01-12 02:43:08,313 DEBUG   SenderThread:10874 [sender.py:send():382] send: stats
 2024-01-12 02:43:12,880 DEBUG   HandlerThread:10874 [handler.py:handle_request():146] handle_request: keepalive
 2024-01-12 02:43:13,314 DEBUG   HandlerThread:10874 [handler.py:handle_request():146] handle_request: status_report
+2024-01-12 02:43:17,886 DEBUG   HandlerThread:10874 [handler.py:handle_request():146] handle_request: keepalive
+2024-01-12 02:43:18,315 DEBUG   HandlerThread:10874 [handler.py:handle_request():146] handle_request: status_report
+2024-01-12 02:43:22,887 DEBUG   HandlerThread:10874 [handler.py:handle_request():146] handle_request: keepalive
+2024-01-12 02:43:23,316 DEBUG   HandlerThread:10874 [handler.py:handle_request():146] handle_request: status_report
+2024-01-12 02:43:27,888 DEBUG   HandlerThread:10874 [handler.py:handle_request():146] handle_request: keepalive
+2024-01-12 02:43:28,319 DEBUG   HandlerThread:10874 [handler.py:handle_request():146] handle_request: status_report
+2024-01-12 02:43:32,890 DEBUG   HandlerThread:10874 [handler.py:handle_request():146] handle_request: keepalive
+2024-01-12 02:43:33,320 DEBUG   HandlerThread:10874 [handler.py:handle_request():146] handle_request: status_report
+2024-01-12 02:43:37,891 DEBUG   HandlerThread:10874 [handler.py:handle_request():146] handle_request: keepalive
+2024-01-12 02:43:38,036 DEBUG   HandlerThread:10874 [handler.py:handle_request():146] handle_request: partial_history
+2024-01-12 02:43:38,038 DEBUG   SenderThread:10874 [sender.py:send():382] send: metric
+2024-01-12 02:43:38,038 DEBUG   SenderThread:10874 [sender.py:send():382] send: metric
+2024-01-12 02:43:38,038 DEBUG   SenderThread:10874 [sender.py:send():382] send: metric
+2024-01-12 02:43:38,039 DEBUG   SenderThread:10874 [sender.py:send():382] send: metric
+2024-01-12 02:43:38,039 DEBUG   SenderThread:10874 [sender.py:send():382] send: metric
+2024-01-12 02:43:38,039 DEBUG   SenderThread:10874 [sender.py:send():382] send: history
+2024-01-12 02:43:38,039 DEBUG   SenderThread:10874 [sender.py:send_request():409] send_request: summary_record
+2024-01-12 02:43:38,040 INFO    SenderThread:10874 [sender.py:_save_file():1403] saving file wandb-summary.json with policy end
+2024-01-12 02:43:38,041 DEBUG   HandlerThread:10874 [handler.py:handle_request():146] handle_request: pause
+2024-01-12 02:43:38,042 INFO    HandlerThread:10874 [handler.py:handle_request_pause():708] stopping system metrics thread
+2024-01-12 02:43:38,042 INFO    HandlerThread:10874 [system_monitor.py:finish():203] Stopping system monitor
+2024-01-12 02:43:38,042 DEBUG   SystemMonitor:10874 [system_monitor.py:_start():179] Finished system metrics aggregation loop
+2024-01-12 02:43:38,042 DEBUG   SystemMonitor:10874 [system_monitor.py:_start():183] Publishing last batch of metrics
+2024-01-12 02:43:38,044 INFO    HandlerThread:10874 [interfaces.py:finish():202] Joined cpu monitor
+2024-01-12 02:43:38,044 INFO    HandlerThread:10874 [interfaces.py:finish():202] Joined disk monitor
+2024-01-12 02:43:38,061 INFO    HandlerThread:10874 [interfaces.py:finish():202] Joined gpu monitor
+2024-01-12 02:43:38,061 INFO    HandlerThread:10874 [interfaces.py:finish():202] Joined memory monitor
+2024-01-12 02:43:38,061 INFO    HandlerThread:10874 [interfaces.py:finish():202] Joined network monitor
+2024-01-12 02:43:38,062 DEBUG   HandlerThread:10874 [handler.py:handle_request():146] handle_request: resume
+2024-01-12 02:43:38,062 INFO    HandlerThread:10874 [handler.py:handle_request_resume():699] starting system metrics thread
+2024-01-12 02:43:38,062 INFO    HandlerThread:10874 [system_monitor.py:start():194] Starting system monitor
+2024-01-12 02:43:38,062 INFO    SystemMonitor:10874 [system_monitor.py:_start():158] Starting system asset monitoring threads
+2024-01-12 02:43:38,063 INFO    SystemMonitor:10874 [interfaces.py:start():190] Started cpu monitoring
+2024-01-12 02:43:38,063 DEBUG   SenderThread:10874 [sender.py:send():382] send: stats
+2024-01-12 02:43:38,064 INFO    SystemMonitor:10874 [interfaces.py:start():190] Started disk monitoring
+2024-01-12 02:43:38,066 INFO    SystemMonitor:10874 [interfaces.py:start():190] Started gpu monitoring
+2024-01-12 02:43:38,067 INFO    SystemMonitor:10874 [interfaces.py:start():190] Started memory monitoring
+2024-01-12 02:43:38,067 INFO    SystemMonitor:10874 [interfaces.py:start():190] Started network monitoring
+2024-01-12 02:43:38,516 INFO    Thread-12 :10874 [dir_watcher.py:_on_file_modified():288] file/dir modified: /kaggle/working/wandb/run-20240112_022837-twhkj0lf/files/wandb-summary.json
+2024-01-12 02:43:39,071 DEBUG   HandlerThread:10874 [handler.py:handle_request():146] handle_request: status_report
+2024-01-12 02:43:40,517 INFO    Thread-12 :10874 [dir_watcher.py:_on_file_modified():288] file/dir modified: /kaggle/working/wandb/run-20240112_022837-twhkj0lf/files/config.yaml
+2024-01-12 02:43:42,958 DEBUG   HandlerThread:10874 [handler.py:handle_request():146] handle_request: keepalive
+2024-01-12 02:43:45,396 DEBUG   HandlerThread:10874 [handler.py:handle_request():146] handle_request: status_report
+2024-01-12 02:43:47,959 DEBUG   HandlerThread:10874 [handler.py:handle_request():146] handle_request: keepalive
+2024-01-12 02:43:50,397 DEBUG   HandlerThread:10874 [handler.py:handle_request():146] handle_request: status_report

wandb/debug.log

@@ -27,3 +27,6 @@ config: {}
 2024-01-12 02:29:08,295 INFO    MainThread:10822 [wandb_run.py:_redirect():2178] Redirects installed.
 2024-01-12 02:29:08,297 INFO    MainThread:10822 [wandb_init.py:init():847] run started, returning control to user process
 2024-01-12 02:29:08,305 INFO    MainThread:10822 [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, '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': 400, '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/Jan12_02-28-34_ea19ce76d6cc', '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}
+2024-01-12 02:43:38,041 INFO    MainThread:10822 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-01-12 02:43:38,041 INFO    MainThread:10822 [wandb_init.py:_pause_backend():437] pausing backend
+2024-01-12 02:43:38,047 INFO    MainThread:10822 [wandb_init.py:_resume_backend():442] resuming backend

wandb/run-20240112_022837-twhkj0lf/files/config.yaml

@@ -66,6 +66,26 @@ _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
 return_dict:
   desc: null
   value: true

wandb/run-20240112_022837-twhkj0lf/files/wandb-summary.json

@@ -1 +1 @@
-{"train/loss": 0.4462, "train/learning_rate": 7.692307692307694e-07, "train/epoch": 384.62, "train/global_step": 5000, "_timestamp": 1705027382.574807, "_runtime": 864.9158549308777, "_step": 9}
+{"train/loss": 0.4462, "train/learning_rate": 7.692307692307694e-07, "train/epoch": 400.0, "train/global_step": 5200, "_timestamp": 1705027418.0359502, "_runtime": 900.3769981861115, "_step": 10, "train/train_runtime": 902.4191, "train/train_samples_per_second": 88.651, "train/train_steps_per_second": 5.762, "train/total_flos": 998967541507056.0, "train/train_loss": 1.118890747657189}

wandb/run-20240112_022837-twhkj0lf/logs/debug-internal.log

@@ -496,3 +496,48 @@
 2024-01-12 02:43:08,313 DEBUG   SenderThread:10874 [sender.py:send():382] send: stats
 2024-01-12 02:43:12,880 DEBUG   HandlerThread:10874 [handler.py:handle_request():146] handle_request: keepalive
 2024-01-12 02:43:13,314 DEBUG   HandlerThread:10874 [handler.py:handle_request():146] handle_request: status_report
+2024-01-12 02:43:17,886 DEBUG   HandlerThread:10874 [handler.py:handle_request():146] handle_request: keepalive
+2024-01-12 02:43:18,315 DEBUG   HandlerThread:10874 [handler.py:handle_request():146] handle_request: status_report
+2024-01-12 02:43:22,887 DEBUG   HandlerThread:10874 [handler.py:handle_request():146] handle_request: keepalive
+2024-01-12 02:43:23,316 DEBUG   HandlerThread:10874 [handler.py:handle_request():146] handle_request: status_report
+2024-01-12 02:43:27,888 DEBUG   HandlerThread:10874 [handler.py:handle_request():146] handle_request: keepalive
+2024-01-12 02:43:28,319 DEBUG   HandlerThread:10874 [handler.py:handle_request():146] handle_request: status_report
+2024-01-12 02:43:32,890 DEBUG   HandlerThread:10874 [handler.py:handle_request():146] handle_request: keepalive
+2024-01-12 02:43:33,320 DEBUG   HandlerThread:10874 [handler.py:handle_request():146] handle_request: status_report
+2024-01-12 02:43:37,891 DEBUG   HandlerThread:10874 [handler.py:handle_request():146] handle_request: keepalive
+2024-01-12 02:43:38,036 DEBUG   HandlerThread:10874 [handler.py:handle_request():146] handle_request: partial_history
+2024-01-12 02:43:38,038 DEBUG   SenderThread:10874 [sender.py:send():382] send: metric
+2024-01-12 02:43:38,038 DEBUG   SenderThread:10874 [sender.py:send():382] send: metric
+2024-01-12 02:43:38,038 DEBUG   SenderThread:10874 [sender.py:send():382] send: metric
+2024-01-12 02:43:38,039 DEBUG   SenderThread:10874 [sender.py:send():382] send: metric
+2024-01-12 02:43:38,039 DEBUG   SenderThread:10874 [sender.py:send():382] send: metric
+2024-01-12 02:43:38,039 DEBUG   SenderThread:10874 [sender.py:send():382] send: history
+2024-01-12 02:43:38,039 DEBUG   SenderThread:10874 [sender.py:send_request():409] send_request: summary_record
+2024-01-12 02:43:38,040 INFO    SenderThread:10874 [sender.py:_save_file():1403] saving file wandb-summary.json with policy end
+2024-01-12 02:43:38,041 DEBUG   HandlerThread:10874 [handler.py:handle_request():146] handle_request: pause
+2024-01-12 02:43:38,042 INFO    HandlerThread:10874 [handler.py:handle_request_pause():708] stopping system metrics thread
+2024-01-12 02:43:38,042 INFO    HandlerThread:10874 [system_monitor.py:finish():203] Stopping system monitor
+2024-01-12 02:43:38,042 DEBUG   SystemMonitor:10874 [system_monitor.py:_start():179] Finished system metrics aggregation loop
+2024-01-12 02:43:38,042 DEBUG   SystemMonitor:10874 [system_monitor.py:_start():183] Publishing last batch of metrics
+2024-01-12 02:43:38,044 INFO    HandlerThread:10874 [interfaces.py:finish():202] Joined cpu monitor
+2024-01-12 02:43:38,044 INFO    HandlerThread:10874 [interfaces.py:finish():202] Joined disk monitor
+2024-01-12 02:43:38,061 INFO    HandlerThread:10874 [interfaces.py:finish():202] Joined gpu monitor
+2024-01-12 02:43:38,061 INFO    HandlerThread:10874 [interfaces.py:finish():202] Joined memory monitor
+2024-01-12 02:43:38,061 INFO    HandlerThread:10874 [interfaces.py:finish():202] Joined network monitor
+2024-01-12 02:43:38,062 DEBUG   HandlerThread:10874 [handler.py:handle_request():146] handle_request: resume
+2024-01-12 02:43:38,062 INFO    HandlerThread:10874 [handler.py:handle_request_resume():699] starting system metrics thread
+2024-01-12 02:43:38,062 INFO    HandlerThread:10874 [system_monitor.py:start():194] Starting system monitor
+2024-01-12 02:43:38,062 INFO    SystemMonitor:10874 [system_monitor.py:_start():158] Starting system asset monitoring threads
+2024-01-12 02:43:38,063 INFO    SystemMonitor:10874 [interfaces.py:start():190] Started cpu monitoring
+2024-01-12 02:43:38,063 DEBUG   SenderThread:10874 [sender.py:send():382] send: stats
+2024-01-12 02:43:38,064 INFO    SystemMonitor:10874 [interfaces.py:start():190] Started disk monitoring
+2024-01-12 02:43:38,066 INFO    SystemMonitor:10874 [interfaces.py:start():190] Started gpu monitoring
+2024-01-12 02:43:38,067 INFO    SystemMonitor:10874 [interfaces.py:start():190] Started memory monitoring
+2024-01-12 02:43:38,067 INFO    SystemMonitor:10874 [interfaces.py:start():190] Started network monitoring
+2024-01-12 02:43:38,516 INFO    Thread-12 :10874 [dir_watcher.py:_on_file_modified():288] file/dir modified: /kaggle/working/wandb/run-20240112_022837-twhkj0lf/files/wandb-summary.json
+2024-01-12 02:43:39,071 DEBUG   HandlerThread:10874 [handler.py:handle_request():146] handle_request: status_report
+2024-01-12 02:43:40,517 INFO    Thread-12 :10874 [dir_watcher.py:_on_file_modified():288] file/dir modified: /kaggle/working/wandb/run-20240112_022837-twhkj0lf/files/config.yaml
+2024-01-12 02:43:42,958 DEBUG   HandlerThread:10874 [handler.py:handle_request():146] handle_request: keepalive
+2024-01-12 02:43:45,396 DEBUG   HandlerThread:10874 [handler.py:handle_request():146] handle_request: status_report
+2024-01-12 02:43:47,959 DEBUG   HandlerThread:10874 [handler.py:handle_request():146] handle_request: keepalive
+2024-01-12 02:43:50,397 DEBUG   HandlerThread:10874 [handler.py:handle_request():146] handle_request: status_report

wandb/run-20240112_022837-twhkj0lf/logs/debug.log

@@ -27,3 +27,6 @@ config: {}
 2024-01-12 02:29:08,295 INFO    MainThread:10822 [wandb_run.py:_redirect():2178] Redirects installed.
 2024-01-12 02:29:08,297 INFO    MainThread:10822 [wandb_init.py:init():847] run started, returning control to user process
 2024-01-12 02:29:08,305 INFO    MainThread:10822 [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, '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': 400, '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/Jan12_02-28-34_ea19ce76d6cc', '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}
+2024-01-12 02:43:38,041 INFO    MainThread:10822 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-01-12 02:43:38,041 INFO    MainThread:10822 [wandb_init.py:_pause_backend():437] pausing backend
+2024-01-12 02:43:38,047 INFO    MainThread:10822 [wandb_init.py:_resume_backend():442] resuming backend