Training in progress, step 500

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d4434094bca63e9e821bb1f70f5ed72d4917ad890733308cc82c26e0065599b7
+oid sha256:9659a1167c2374a27093532a126925c2bfbe85954a9688d8b90235f6eb21fe52
 size 328693404

runs/Jan18_17-18-07_bddbbc3e305c/events.out.tfevents.1705598291.bddbbc3e305c.76.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2ce18ac198a7b113c65d5454781a605de679d6f97057ec0bad7226ec0ae7198b
-size 4679
+oid sha256:12746c2abbfd47e474fe5b02e73bd3d896cb2085cc4f42d1e6b3869b9813d7ac
+size 9141

wandb/debug-internal.log

@@ -151,3 +151,74 @@
 2024-01-18 17:21:51,772 DEBUG   HandlerThread:127 [handler.py:handle_request():146] handle_request: keepalive
 2024-01-18 17:21:55,051 DEBUG   HandlerThread:127 [handler.py:handle_request():146] handle_request: status_report
 2024-01-18 17:21:56,776 DEBUG   HandlerThread:127 [handler.py:handle_request():146] handle_request: keepalive
+2024-01-18 17:22:00,052 DEBUG   HandlerThread:127 [handler.py:handle_request():146] handle_request: status_report
+2024-01-18 17:22:00,481 DEBUG   SenderThread:127 [sender.py:send():382] send: stats
+2024-01-18 17:22:01,357 DEBUG   HandlerThread:127 [handler.py:handle_request():146] handle_request: pause
+2024-01-18 17:22:01,357 INFO    HandlerThread:127 [handler.py:handle_request_pause():708] stopping system metrics thread
+2024-01-18 17:22:01,357 INFO    HandlerThread:127 [system_monitor.py:finish():203] Stopping system monitor
+2024-01-18 17:22:01,358 DEBUG   SystemMonitor:127 [system_monitor.py:_start():179] Finished system metrics aggregation loop
+2024-01-18 17:22:01,358 INFO    HandlerThread:127 [interfaces.py:finish():202] Joined cpu monitor
+2024-01-18 17:22:01,358 DEBUG   SystemMonitor:127 [system_monitor.py:_start():183] Publishing last batch of metrics
+2024-01-18 17:22:01,359 INFO    HandlerThread:127 [interfaces.py:finish():202] Joined disk monitor
+2024-01-18 17:22:01,372 INFO    HandlerThread:127 [interfaces.py:finish():202] Joined gpu monitor
+2024-01-18 17:22:01,372 INFO    HandlerThread:127 [interfaces.py:finish():202] Joined memory monitor
+2024-01-18 17:22:01,372 INFO    HandlerThread:127 [interfaces.py:finish():202] Joined network monitor
+2024-01-18 17:22:01,373 DEBUG   SenderThread:127 [sender.py:send():382] send: stats
+2024-01-18 17:22:01,787 DEBUG   HandlerThread:127 [handler.py:handle_request():146] handle_request: keepalive
+2024-01-18 17:22:05,027 DEBUG   HandlerThread:127 [handler.py:handle_request():146] handle_request: resume
+2024-01-18 17:22:05,027 INFO    HandlerThread:127 [handler.py:handle_request_resume():699] starting system metrics thread
+2024-01-18 17:22:05,028 INFO    HandlerThread:127 [system_monitor.py:start():194] Starting system monitor
+2024-01-18 17:22:05,028 INFO    SystemMonitor:127 [system_monitor.py:_start():158] Starting system asset monitoring threads
+2024-01-18 17:22:05,028 INFO    SystemMonitor:127 [interfaces.py:start():190] Started cpu monitoring
+2024-01-18 17:22:05,029 INFO    SystemMonitor:127 [interfaces.py:start():190] Started disk monitoring
+2024-01-18 17:22:05,029 INFO    SystemMonitor:127 [interfaces.py:start():190] Started gpu monitoring
+2024-01-18 17:22:05,030 INFO    SystemMonitor:127 [interfaces.py:start():190] Started memory monitoring
+2024-01-18 17:22:05,030 INFO    SystemMonitor:127 [interfaces.py:start():190] Started network monitoring
+2024-01-18 17:22:05,374 DEBUG   HandlerThread:127 [handler.py:handle_request():146] handle_request: status_report
+2024-01-18 17:22:06,788 DEBUG   HandlerThread:127 [handler.py:handle_request():146] handle_request: keepalive
+2024-01-18 17:22:10,375 DEBUG   HandlerThread:127 [handler.py:handle_request():146] handle_request: status_report
+2024-01-18 17:22:11,789 DEBUG   HandlerThread:127 [handler.py:handle_request():146] handle_request: keepalive
+2024-01-18 17:22:15,376 DEBUG   HandlerThread:127 [handler.py:handle_request():146] handle_request: status_report
+2024-01-18 17:22:16,792 DEBUG   HandlerThread:127 [handler.py:handle_request():146] handle_request: keepalive
+2024-01-18 17:22:20,377 DEBUG   HandlerThread:127 [handler.py:handle_request():146] handle_request: status_report
+2024-01-18 17:22:21,793 DEBUG   HandlerThread:127 [handler.py:handle_request():146] handle_request: keepalive
+2024-01-18 17:22:25,377 DEBUG   HandlerThread:127 [handler.py:handle_request():146] handle_request: status_report
+2024-01-18 17:22:26,795 DEBUG   HandlerThread:127 [handler.py:handle_request():146] handle_request: keepalive
+2024-01-18 17:22:30,378 DEBUG   HandlerThread:127 [handler.py:handle_request():146] handle_request: status_report
+2024-01-18 17:22:31,797 DEBUG   HandlerThread:127 [handler.py:handle_request():146] handle_request: keepalive
+2024-01-18 17:22:35,379 DEBUG   HandlerThread:127 [handler.py:handle_request():146] handle_request: status_report
+2024-01-18 17:22:36,803 DEBUG   HandlerThread:127 [handler.py:handle_request():146] handle_request: keepalive
+2024-01-18 17:22:40,380 DEBUG   HandlerThread:127 [handler.py:handle_request():146] handle_request: status_report
+2024-01-18 17:22:41,804 DEBUG   HandlerThread:127 [handler.py:handle_request():146] handle_request: keepalive
+2024-01-18 17:22:45,381 DEBUG   HandlerThread:127 [handler.py:handle_request():146] handle_request: status_report
+2024-01-18 17:22:46,805 DEBUG   HandlerThread:127 [handler.py:handle_request():146] handle_request: keepalive
+2024-01-18 17:22:50,382 DEBUG   HandlerThread:127 [handler.py:handle_request():146] handle_request: status_report
+2024-01-18 17:22:51,807 DEBUG   HandlerThread:127 [handler.py:handle_request():146] handle_request: keepalive
+2024-01-18 17:22:55,382 DEBUG   HandlerThread:127 [handler.py:handle_request():146] handle_request: status_report
+2024-01-18 17:22:56,809 DEBUG   HandlerThread:127 [handler.py:handle_request():146] handle_request: keepalive
+2024-01-18 17:23:00,383 DEBUG   HandlerThread:127 [handler.py:handle_request():146] handle_request: status_report
+2024-01-18 17:23:01,809 DEBUG   HandlerThread:127 [handler.py:handle_request():146] handle_request: keepalive
+2024-01-18 17:23:05,031 DEBUG   SystemMonitor:127 [system_monitor.py:_start():172] Starting system metrics aggregation loop
+2024-01-18 17:23:05,032 DEBUG   SenderThread:127 [sender.py:send():382] send: stats
+2024-01-18 17:23:06,033 DEBUG   HandlerThread:127 [handler.py:handle_request():146] handle_request: status_report
+2024-01-18 17:23:06,813 DEBUG   HandlerThread:127 [handler.py:handle_request():146] handle_request: keepalive
+2024-01-18 17:23:11,034 DEBUG   HandlerThread:127 [handler.py:handle_request():146] handle_request: status_report
+2024-01-18 17:23:11,814 DEBUG   HandlerThread:127 [handler.py:handle_request():146] handle_request: keepalive
+2024-01-18 17:23:16,034 DEBUG   HandlerThread:127 [handler.py:handle_request():146] handle_request: status_report
+2024-01-18 17:23:16,818 DEBUG   HandlerThread:127 [handler.py:handle_request():146] handle_request: keepalive
+2024-01-18 17:23:21,035 DEBUG   HandlerThread:127 [handler.py:handle_request():146] handle_request: status_report
+2024-01-18 17:23:21,819 DEBUG   HandlerThread:127 [handler.py:handle_request():146] handle_request: keepalive
+2024-01-18 17:23:26,036 DEBUG   HandlerThread:127 [handler.py:handle_request():146] handle_request: status_report
+2024-01-18 17:23:26,750 DEBUG   HandlerThread:127 [handler.py:handle_request():146] handle_request: partial_history
+2024-01-18 17:23:26,752 DEBUG   SenderThread:127 [sender.py:send():382] send: history
+2024-01-18 17:23:26,752 DEBUG   SenderThread:127 [sender.py:send_request():409] send_request: summary_record
+2024-01-18 17:23:26,754 INFO    SenderThread:127 [sender.py:_save_file():1403] saving file wandb-summary.json with policy end
+2024-01-18 17:23:26,820 DEBUG   HandlerThread:127 [handler.py:handle_request():146] handle_request: keepalive
+2024-01-18 17:23:27,506 INFO    Thread-12 :127 [dir_watcher.py:_on_file_modified():288] file/dir modified: /kaggle/working/wandb/run-20240118_171829-uvan9htf/files/wandb-summary.json
+2024-01-18 17:23:28,506 INFO    Thread-12 :127 [dir_watcher.py:_on_file_modified():288] file/dir modified: /kaggle/working/wandb/run-20240118_171829-uvan9htf/files/output.log
+2024-01-18 17:23:31,837 DEBUG   HandlerThread:127 [handler.py:handle_request():146] handle_request: keepalive
+2024-01-18 17:23:32,021 DEBUG   HandlerThread:127 [handler.py:handle_request():146] handle_request: status_report
+2024-01-18 17:23:32,508 INFO    Thread-12 :127 [dir_watcher.py:_on_file_modified():288] file/dir modified: /kaggle/working/wandb/run-20240118_171829-uvan9htf/files/output.log
+2024-01-18 17:23:35,033 DEBUG   SenderThread:127 [sender.py:send():382] send: stats
+2024-01-18 17:23:36,839 DEBUG   HandlerThread:127 [handler.py:handle_request():146] handle_request: keepalive
+2024-01-18 17:23:37,034 DEBUG   HandlerThread:127 [handler.py:handle_request():146] handle_request: status_report

wandb/debug.log

@@ -28,3 +28,6 @@ config: {}
 2024-01-18 17:19:00,498 INFO    MainThread:76 [wandb_run.py:_redirect():2178] Redirects installed.
 2024-01-18 17:19:00,499 INFO    MainThread:76 [wandb_init.py:init():847] run started, returning control to user process
 2024-01-18 17:19:00,504 INFO    MainThread:76 [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': 200, '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_17-18-07_bddbbc3e305c', '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}
+2024-01-18 17:22:01,357 INFO    MainThread:76 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-01-18 17:22:01,357 INFO    MainThread:76 [wandb_init.py:_pause_backend():437] pausing backend
+2024-01-18 17:22:05,027 INFO    MainThread:76 [wandb_init.py:_resume_backend():442] resuming backend

wandb/run-20240118_171829-uvan9htf/files/output.log

@@ -3,4 +3,7 @@ You're using a PreTrainedTokenizerFast tokenizer. Please note that with a fast t
   warnings.warn('Was asked to gather along dimension 0, but all '
 /opt/conda/lib/python3.10/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.
   warnings.warn('Was asked to gather along dimension 0, but all '
+/opt/conda/lib/python3.10/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.
+  warnings.warn('Was asked to gather along dimension 0, but all '
+Checkpoint destination directory /kaggle/working/checkpoint-500 already exists and is non-empty.Saving will proceed but saved results may be invalid.
 /opt/conda/lib/python3.10/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector.

wandb/run-20240118_171829-uvan9htf/files/wandb-summary.json

@@ -1 +1 @@
-{"train/loss": 2.1719, "train/learning_rate": 1.230769230769231e-05, "train/epoch": 76.92, "train/global_step": 1000, "_timestamp": 1705598504.7095327, "_runtime": 195.3746588230133, "_step": 1}
+{"train/loss": 1.637, "train/learning_rate": 1.6153846153846154e-05, "train/epoch": 38.46, "train/global_step": 500, "_timestamp": 1705598606.7499511, "_runtime": 297.41507720947266, "_step": 2}

wandb/run-20240118_171829-uvan9htf/logs/debug-internal.log

@@ -151,3 +151,74 @@
 2024-01-18 17:21:51,772 DEBUG   HandlerThread:127 [handler.py:handle_request():146] handle_request: keepalive
 2024-01-18 17:21:55,051 DEBUG   HandlerThread:127 [handler.py:handle_request():146] handle_request: status_report
 2024-01-18 17:21:56,776 DEBUG   HandlerThread:127 [handler.py:handle_request():146] handle_request: keepalive
+2024-01-18 17:22:00,052 DEBUG   HandlerThread:127 [handler.py:handle_request():146] handle_request: status_report
+2024-01-18 17:22:00,481 DEBUG   SenderThread:127 [sender.py:send():382] send: stats
+2024-01-18 17:22:01,357 DEBUG   HandlerThread:127 [handler.py:handle_request():146] handle_request: pause
+2024-01-18 17:22:01,357 INFO    HandlerThread:127 [handler.py:handle_request_pause():708] stopping system metrics thread
+2024-01-18 17:22:01,357 INFO    HandlerThread:127 [system_monitor.py:finish():203] Stopping system monitor
+2024-01-18 17:22:01,358 DEBUG   SystemMonitor:127 [system_monitor.py:_start():179] Finished system metrics aggregation loop
+2024-01-18 17:22:01,358 INFO    HandlerThread:127 [interfaces.py:finish():202] Joined cpu monitor
+2024-01-18 17:22:01,358 DEBUG   SystemMonitor:127 [system_monitor.py:_start():183] Publishing last batch of metrics
+2024-01-18 17:22:01,359 INFO    HandlerThread:127 [interfaces.py:finish():202] Joined disk monitor
+2024-01-18 17:22:01,372 INFO    HandlerThread:127 [interfaces.py:finish():202] Joined gpu monitor
+2024-01-18 17:22:01,372 INFO    HandlerThread:127 [interfaces.py:finish():202] Joined memory monitor
+2024-01-18 17:22:01,372 INFO    HandlerThread:127 [interfaces.py:finish():202] Joined network monitor
+2024-01-18 17:22:01,373 DEBUG   SenderThread:127 [sender.py:send():382] send: stats
+2024-01-18 17:22:01,787 DEBUG   HandlerThread:127 [handler.py:handle_request():146] handle_request: keepalive
+2024-01-18 17:22:05,027 DEBUG   HandlerThread:127 [handler.py:handle_request():146] handle_request: resume
+2024-01-18 17:22:05,027 INFO    HandlerThread:127 [handler.py:handle_request_resume():699] starting system metrics thread
+2024-01-18 17:22:05,028 INFO    HandlerThread:127 [system_monitor.py:start():194] Starting system monitor
+2024-01-18 17:22:05,028 INFO    SystemMonitor:127 [system_monitor.py:_start():158] Starting system asset monitoring threads
+2024-01-18 17:22:05,028 INFO    SystemMonitor:127 [interfaces.py:start():190] Started cpu monitoring
+2024-01-18 17:22:05,029 INFO    SystemMonitor:127 [interfaces.py:start():190] Started disk monitoring
+2024-01-18 17:22:05,029 INFO    SystemMonitor:127 [interfaces.py:start():190] Started gpu monitoring
+2024-01-18 17:22:05,030 INFO    SystemMonitor:127 [interfaces.py:start():190] Started memory monitoring
+2024-01-18 17:22:05,030 INFO    SystemMonitor:127 [interfaces.py:start():190] Started network monitoring
+2024-01-18 17:22:05,374 DEBUG   HandlerThread:127 [handler.py:handle_request():146] handle_request: status_report
+2024-01-18 17:22:06,788 DEBUG   HandlerThread:127 [handler.py:handle_request():146] handle_request: keepalive
+2024-01-18 17:22:10,375 DEBUG   HandlerThread:127 [handler.py:handle_request():146] handle_request: status_report
+2024-01-18 17:22:11,789 DEBUG   HandlerThread:127 [handler.py:handle_request():146] handle_request: keepalive
+2024-01-18 17:22:15,376 DEBUG   HandlerThread:127 [handler.py:handle_request():146] handle_request: status_report
+2024-01-18 17:22:16,792 DEBUG   HandlerThread:127 [handler.py:handle_request():146] handle_request: keepalive
+2024-01-18 17:22:20,377 DEBUG   HandlerThread:127 [handler.py:handle_request():146] handle_request: status_report
+2024-01-18 17:22:21,793 DEBUG   HandlerThread:127 [handler.py:handle_request():146] handle_request: keepalive
+2024-01-18 17:22:25,377 DEBUG   HandlerThread:127 [handler.py:handle_request():146] handle_request: status_report
+2024-01-18 17:22:26,795 DEBUG   HandlerThread:127 [handler.py:handle_request():146] handle_request: keepalive
+2024-01-18 17:22:30,378 DEBUG   HandlerThread:127 [handler.py:handle_request():146] handle_request: status_report
+2024-01-18 17:22:31,797 DEBUG   HandlerThread:127 [handler.py:handle_request():146] handle_request: keepalive
+2024-01-18 17:22:35,379 DEBUG   HandlerThread:127 [handler.py:handle_request():146] handle_request: status_report
+2024-01-18 17:22:36,803 DEBUG   HandlerThread:127 [handler.py:handle_request():146] handle_request: keepalive
+2024-01-18 17:22:40,380 DEBUG   HandlerThread:127 [handler.py:handle_request():146] handle_request: status_report
+2024-01-18 17:22:41,804 DEBUG   HandlerThread:127 [handler.py:handle_request():146] handle_request: keepalive
+2024-01-18 17:22:45,381 DEBUG   HandlerThread:127 [handler.py:handle_request():146] handle_request: status_report
+2024-01-18 17:22:46,805 DEBUG   HandlerThread:127 [handler.py:handle_request():146] handle_request: keepalive
+2024-01-18 17:22:50,382 DEBUG   HandlerThread:127 [handler.py:handle_request():146] handle_request: status_report
+2024-01-18 17:22:51,807 DEBUG   HandlerThread:127 [handler.py:handle_request():146] handle_request: keepalive
+2024-01-18 17:22:55,382 DEBUG   HandlerThread:127 [handler.py:handle_request():146] handle_request: status_report
+2024-01-18 17:22:56,809 DEBUG   HandlerThread:127 [handler.py:handle_request():146] handle_request: keepalive
+2024-01-18 17:23:00,383 DEBUG   HandlerThread:127 [handler.py:handle_request():146] handle_request: status_report
+2024-01-18 17:23:01,809 DEBUG   HandlerThread:127 [handler.py:handle_request():146] handle_request: keepalive
+2024-01-18 17:23:05,031 DEBUG   SystemMonitor:127 [system_monitor.py:_start():172] Starting system metrics aggregation loop
+2024-01-18 17:23:05,032 DEBUG   SenderThread:127 [sender.py:send():382] send: stats
+2024-01-18 17:23:06,033 DEBUG   HandlerThread:127 [handler.py:handle_request():146] handle_request: status_report
+2024-01-18 17:23:06,813 DEBUG   HandlerThread:127 [handler.py:handle_request():146] handle_request: keepalive
+2024-01-18 17:23:11,034 DEBUG   HandlerThread:127 [handler.py:handle_request():146] handle_request: status_report
+2024-01-18 17:23:11,814 DEBUG   HandlerThread:127 [handler.py:handle_request():146] handle_request: keepalive
+2024-01-18 17:23:16,034 DEBUG   HandlerThread:127 [handler.py:handle_request():146] handle_request: status_report
+2024-01-18 17:23:16,818 DEBUG   HandlerThread:127 [handler.py:handle_request():146] handle_request: keepalive
+2024-01-18 17:23:21,035 DEBUG   HandlerThread:127 [handler.py:handle_request():146] handle_request: status_report
+2024-01-18 17:23:21,819 DEBUG   HandlerThread:127 [handler.py:handle_request():146] handle_request: keepalive
+2024-01-18 17:23:26,036 DEBUG   HandlerThread:127 [handler.py:handle_request():146] handle_request: status_report
+2024-01-18 17:23:26,750 DEBUG   HandlerThread:127 [handler.py:handle_request():146] handle_request: partial_history
+2024-01-18 17:23:26,752 DEBUG   SenderThread:127 [sender.py:send():382] send: history
+2024-01-18 17:23:26,752 DEBUG   SenderThread:127 [sender.py:send_request():409] send_request: summary_record
+2024-01-18 17:23:26,754 INFO    SenderThread:127 [sender.py:_save_file():1403] saving file wandb-summary.json with policy end
+2024-01-18 17:23:26,820 DEBUG   HandlerThread:127 [handler.py:handle_request():146] handle_request: keepalive
+2024-01-18 17:23:27,506 INFO    Thread-12 :127 [dir_watcher.py:_on_file_modified():288] file/dir modified: /kaggle/working/wandb/run-20240118_171829-uvan9htf/files/wandb-summary.json
+2024-01-18 17:23:28,506 INFO    Thread-12 :127 [dir_watcher.py:_on_file_modified():288] file/dir modified: /kaggle/working/wandb/run-20240118_171829-uvan9htf/files/output.log
+2024-01-18 17:23:31,837 DEBUG   HandlerThread:127 [handler.py:handle_request():146] handle_request: keepalive
+2024-01-18 17:23:32,021 DEBUG   HandlerThread:127 [handler.py:handle_request():146] handle_request: status_report
+2024-01-18 17:23:32,508 INFO    Thread-12 :127 [dir_watcher.py:_on_file_modified():288] file/dir modified: /kaggle/working/wandb/run-20240118_171829-uvan9htf/files/output.log
+2024-01-18 17:23:35,033 DEBUG   SenderThread:127 [sender.py:send():382] send: stats
+2024-01-18 17:23:36,839 DEBUG   HandlerThread:127 [handler.py:handle_request():146] handle_request: keepalive
+2024-01-18 17:23:37,034 DEBUG   HandlerThread:127 [handler.py:handle_request():146] handle_request: status_report

wandb/run-20240118_171829-uvan9htf/logs/debug.log

@@ -28,3 +28,6 @@ config: {}
 2024-01-18 17:19:00,498 INFO    MainThread:76 [wandb_run.py:_redirect():2178] Redirects installed.
 2024-01-18 17:19:00,499 INFO    MainThread:76 [wandb_init.py:init():847] run started, returning control to user process
 2024-01-18 17:19:00,504 INFO    MainThread:76 [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': 200, '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_17-18-07_bddbbc3e305c', '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}
+2024-01-18 17:22:01,357 INFO    MainThread:76 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-01-18 17:22:01,357 INFO    MainThread:76 [wandb_init.py:_pause_backend():437] pausing backend
+2024-01-18 17:22:05,027 INFO    MainThread:76 [wandb_init.py:_resume_backend():442] resuming backend