Training in progress, epoch 1

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:db18a2fa5759bcda6556cf606b69ba1426d08b1c4826aa94b4d8f7928cde32bf
+oid sha256:1f7da727958b65542249e558b0eb2f6eb4d3c54f857853c697e21464087694cc
 size 502675828

runs/Apr10_15-06-31_9088970cc926/events.out.tfevents.1712761592.9088970cc926.34.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ae3b5b714ffae5c3d4f2e003e44a80936fc088a063b7d6e54d640eabc907ffa
+size 5845

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a9f444053445bba34dd52346fc9f9984273e38d3d4d249cb9183e6bca3f637ff
+oid sha256:89a2ed4d7d292fe5780011c7f589882560b0e4256bbecfb8bacfeeb6dd55757e
 size 4920

wandb/debug-internal.log

@@ -230,3 +230,95 @@ subprocess.TimeoutExpired: Command '['conda', 'env', 'export']' timed out after
 2024-04-10 15:05:56,996 DEBUG   HandlerThread:100 [handler.py:handle_request():146] handle_request: stop_status
 2024-04-10 15:05:56,997 DEBUG   SenderThread:100 [sender.py:send_request():406] send_request: stop_status
 2024-04-10 15:05:58,215 DEBUG   HandlerThread:100 [handler.py:handle_request():146] handle_request: status_report
+2024-04-10 15:06:03,216 DEBUG   HandlerThread:100 [handler.py:handle_request():146] handle_request: status_report
+2024-04-10 15:06:08,217 DEBUG   HandlerThread:100 [handler.py:handle_request():146] handle_request: status_report
+2024-04-10 15:06:11,977 DEBUG   HandlerThread:100 [handler.py:handle_request():146] handle_request: internal_messages
+2024-04-10 15:06:11,996 DEBUG   HandlerThread:100 [handler.py:handle_request():146] handle_request: stop_status
+2024-04-10 15:06:11,996 DEBUG   SenderThread:100 [sender.py:send_request():406] send_request: stop_status
+2024-04-10 15:06:13,275 DEBUG   HandlerThread:100 [handler.py:handle_request():146] handle_request: status_report
+2024-04-10 15:06:18,276 DEBUG   HandlerThread:100 [handler.py:handle_request():146] handle_request: status_report
+2024-04-10 15:06:23,277 DEBUG   HandlerThread:100 [handler.py:handle_request():146] handle_request: status_report
+2024-04-10 15:06:23,666 DEBUG   HandlerThread:100 [handler.py:handle_request():146] handle_request: pause
+2024-04-10 15:06:23,667 INFO    HandlerThread:100 [handler.py:handle_request_pause():708] stopping system metrics thread
+2024-04-10 15:06:23,667 INFO    HandlerThread:100 [system_monitor.py:finish():203] Stopping system monitor
+2024-04-10 15:06:23,667 DEBUG   SystemMonitor:100 [system_monitor.py:_start():179] Finished system metrics aggregation loop
+2024-04-10 15:06:23,667 DEBUG   SystemMonitor:100 [system_monitor.py:_start():183] Publishing last batch of metrics
+2024-04-10 15:06:23,668 INFO    HandlerThread:100 [interfaces.py:finish():202] Joined cpu monitor
+2024-04-10 15:06:23,669 INFO    HandlerThread:100 [interfaces.py:finish():202] Joined disk monitor
+2024-04-10 15:06:23,673 INFO    HandlerThread:100 [interfaces.py:finish():202] Joined gpu monitor
+2024-04-10 15:06:23,674 INFO    HandlerThread:100 [interfaces.py:finish():202] Joined memory monitor
+2024-04-10 15:06:23,674 INFO    HandlerThread:100 [interfaces.py:finish():202] Joined network monitor
+2024-04-10 15:06:23,674 DEBUG   SenderThread:100 [sender.py:send():379] send: stats
+2024-04-10 15:06:26,978 DEBUG   HandlerThread:100 [handler.py:handle_request():146] handle_request: internal_messages
+2024-04-10 15:06:26,996 DEBUG   HandlerThread:100 [handler.py:handle_request():146] handle_request: stop_status
+2024-04-10 15:06:26,997 DEBUG   SenderThread:100 [sender.py:send_request():406] send_request: stop_status
+2024-04-10 15:06:29,233 DEBUG   HandlerThread:100 [handler.py:handle_request():146] handle_request: status_report
+2024-04-10 15:06:30,823 DEBUG   HandlerThread:100 [handler.py:handle_request():146] handle_request: resume
+2024-04-10 15:06:30,823 INFO    HandlerThread:100 [handler.py:handle_request_resume():699] starting system metrics thread
+2024-04-10 15:06:30,823 INFO    HandlerThread:100 [system_monitor.py:start():194] Starting system monitor
+2024-04-10 15:06:30,823 INFO    SystemMonitor:100 [system_monitor.py:_start():158] Starting system asset monitoring threads
+2024-04-10 15:06:30,824 INFO    SystemMonitor:100 [interfaces.py:start():190] Started cpu monitoring
+2024-04-10 15:06:30,825 INFO    SystemMonitor:100 [interfaces.py:start():190] Started disk monitoring
+2024-04-10 15:06:30,826 INFO    SystemMonitor:100 [interfaces.py:start():190] Started gpu monitoring
+2024-04-10 15:06:30,826 INFO    SystemMonitor:100 [interfaces.py:start():190] Started memory monitoring
+2024-04-10 15:06:30,827 INFO    SystemMonitor:100 [interfaces.py:start():190] Started network monitoring
+2024-04-10 15:06:32,242 DEBUG   SenderThread:100 [sender.py:send():379] send: config
+2024-04-10 15:06:32,243 DEBUG   SenderThread:100 [sender.py:send():379] send: metric
+2024-04-10 15:06:32,243 DEBUG   SenderThread:100 [sender.py:send():379] send: metric
+2024-04-10 15:06:32,243 WARNING SenderThread:100 [sender.py:send_metric():1341] Seen metric with glob (shouldn't happen)
+2024-04-10 15:06:34,244 DEBUG   HandlerThread:100 [handler.py:handle_request():146] handle_request: status_report
+2024-04-10 15:06:34,766 INFO    Thread-12 :100 [dir_watcher.py:_on_file_modified():288] file/dir modified: /kaggle/working/wandb/run-20240410_150123-cuua991r/files/output.log
+2024-04-10 15:06:39,250 DEBUG   HandlerThread:100 [handler.py:handle_request():146] handle_request: status_report
+2024-04-10 15:06:39,768 INFO    Thread-12 :100 [dir_watcher.py:_on_file_modified():288] file/dir modified: /kaggle/working/wandb/run-20240410_150123-cuua991r/files/config.yaml
+2024-04-10 15:06:41,978 DEBUG   HandlerThread:100 [handler.py:handle_request():146] handle_request: internal_messages
+2024-04-10 15:06:41,996 DEBUG   HandlerThread:100 [handler.py:handle_request():146] handle_request: stop_status
+2024-04-10 15:06:41,997 DEBUG   SenderThread:100 [sender.py:send_request():406] send_request: stop_status
+2024-04-10 15:06:45,276 DEBUG   HandlerThread:100 [handler.py:handle_request():146] handle_request: status_report
+2024-04-10 15:06:50,277 DEBUG   HandlerThread:100 [handler.py:handle_request():146] handle_request: status_report
+2024-04-10 15:06:55,277 DEBUG   HandlerThread:100 [handler.py:handle_request():146] handle_request: status_report
+2024-04-10 15:06:56,977 DEBUG   HandlerThread:100 [handler.py:handle_request():146] handle_request: internal_messages
+2024-04-10 15:06:56,996 DEBUG   HandlerThread:100 [handler.py:handle_request():146] handle_request: stop_status
+2024-04-10 15:06:56,997 DEBUG   SenderThread:100 [sender.py:send_request():406] send_request: stop_status
+2024-04-10 15:07:01,236 DEBUG   HandlerThread:100 [handler.py:handle_request():146] handle_request: status_report
+2024-04-10 15:07:06,237 DEBUG   HandlerThread:100 [handler.py:handle_request():146] handle_request: status_report
+2024-04-10 15:07:11,238 DEBUG   HandlerThread:100 [handler.py:handle_request():146] handle_request: status_report
+2024-04-10 15:07:11,985 DEBUG   HandlerThread:100 [handler.py:handle_request():146] handle_request: internal_messages
+2024-04-10 15:07:11,997 DEBUG   HandlerThread:100 [handler.py:handle_request():146] handle_request: stop_status
+2024-04-10 15:07:11,997 DEBUG   SenderThread:100 [sender.py:send_request():406] send_request: stop_status
+2024-04-10 15:07:17,194 DEBUG   HandlerThread:100 [handler.py:handle_request():146] handle_request: status_report
+2024-04-10 15:07:22,195 DEBUG   HandlerThread:100 [handler.py:handle_request():146] handle_request: status_report
+2024-04-10 15:07:26,698 DEBUG   HandlerThread:100 [handler.py:handle_request():146] handle_request: partial_history
+2024-04-10 15:07:26,699 DEBUG   SenderThread:100 [sender.py:send():379] send: history
+2024-04-10 15:07:26,699 DEBUG   SenderThread:100 [sender.py:send_request():406] send_request: summary_record
+2024-04-10 15:07:26,700 INFO    SenderThread:100 [sender.py:_save_file():1390] saving file wandb-summary.json with policy end
+2024-04-10 15:07:26,786 INFO    Thread-12 :100 [dir_watcher.py:_on_file_modified():288] file/dir modified: /kaggle/working/wandb/run-20240410_150123-cuua991r/files/wandb-summary.json
+2024-04-10 15:07:26,982 DEBUG   HandlerThread:100 [handler.py:handle_request():146] handle_request: internal_messages
+2024-04-10 15:07:26,997 DEBUG   HandlerThread:100 [handler.py:handle_request():146] handle_request: stop_status
+2024-04-10 15:07:26,997 DEBUG   SenderThread:100 [sender.py:send_request():406] send_request: stop_status
+2024-04-10 15:07:27,274 DEBUG   HandlerThread:100 [handler.py:handle_request():146] handle_request: status_report
+2024-04-10 15:07:29,557 DEBUG   HandlerThread:100 [handler.py:handle_request():146] handle_request: partial_history
+2024-04-10 15:07:29,558 DEBUG   SenderThread:100 [sender.py:send():379] send: history
+2024-04-10 15:07:29,559 DEBUG   SenderThread:100 [sender.py:send_request():406] send_request: summary_record
+2024-04-10 15:07:29,559 INFO    SenderThread:100 [sender.py:_save_file():1390] saving file wandb-summary.json with policy end
+2024-04-10 15:07:29,787 INFO    Thread-12 :100 [dir_watcher.py:_on_file_modified():288] file/dir modified: /kaggle/working/wandb/run-20240410_150123-cuua991r/files/wandb-summary.json
+2024-04-10 15:07:30,828 DEBUG   SystemMonitor:100 [system_monitor.py:_start():172] Starting system metrics aggregation loop
+2024-04-10 15:07:30,829 DEBUG   SenderThread:100 [sender.py:send():379] send: stats
+2024-04-10 15:07:32,789 INFO    Thread-12 :100 [dir_watcher.py:_on_file_modified():288] file/dir modified: /kaggle/working/wandb/run-20240410_150123-cuua991r/files/output.log
+2024-04-10 15:07:32,830 DEBUG   HandlerThread:100 [handler.py:handle_request():146] handle_request: status_report
+2024-04-10 15:07:37,831 DEBUG   HandlerThread:100 [handler.py:handle_request():146] handle_request: status_report
+2024-04-10 15:07:41,982 DEBUG   HandlerThread:100 [handler.py:handle_request():146] handle_request: internal_messages
+2024-04-10 15:07:41,997 DEBUG   HandlerThread:100 [handler.py:handle_request():146] handle_request: stop_status
+2024-04-10 15:07:41,997 DEBUG   SenderThread:100 [sender.py:send_request():406] send_request: stop_status
+2024-04-10 15:07:43,201 DEBUG   HandlerThread:100 [handler.py:handle_request():146] handle_request: status_report
+2024-04-10 15:07:48,203 DEBUG   HandlerThread:100 [handler.py:handle_request():146] handle_request: status_report
+2024-04-10 15:07:53,204 DEBUG   HandlerThread:100 [handler.py:handle_request():146] handle_request: status_report
+2024-04-10 15:07:56,982 DEBUG   HandlerThread:100 [handler.py:handle_request():146] handle_request: internal_messages
+2024-04-10 15:07:56,997 DEBUG   HandlerThread:100 [handler.py:handle_request():146] handle_request: stop_status
+2024-04-10 15:07:56,997 DEBUG   SenderThread:100 [sender.py:send_request():406] send_request: stop_status
+2024-04-10 15:07:58,276 DEBUG   HandlerThread:100 [handler.py:handle_request():146] handle_request: status_report
+2024-04-10 15:08:00,830 DEBUG   SenderThread:100 [sender.py:send():379] send: stats
+2024-04-10 15:08:03,831 DEBUG   HandlerThread:100 [handler.py:handle_request():146] handle_request: status_report
+2024-04-10 15:08:08,832 DEBUG   HandlerThread:100 [handler.py:handle_request():146] handle_request: status_report
+2024-04-10 15:08:11,983 DEBUG   HandlerThread:100 [handler.py:handle_request():146] handle_request: internal_messages
+2024-04-10 15:08:11,997 DEBUG   HandlerThread:100 [handler.py:handle_request():146] handle_request: stop_status
+2024-04-10 15:08:11,998 DEBUG   SenderThread:100 [sender.py:send_request():406] send_request: stop_status

wandb/debug.log

@@ -30,3 +30,7 @@ config: {}
 2024-04-10 15:01:41,747 INFO    MainThread:34 [wandb_run.py:_redirect():2268] Redirects installed.
 2024-04-10 15:01:41,749 INFO    MainThread:34 [wandb_init.py:init():848] run started, returning control to user process
 2024-04-10 15:01:41,754 INFO    MainThread:34 [wandb_run.py:_config_callback():1347] 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': None, 'finetuning_task': None, 'id2label': {0: 'Documentation Replication on Other Examples', 1: 'Requesting (Additional) Resources', 2: 'Inadequate Examples', 3: 'Documentation Ambiguity', 4: 'Documentation Completeness', 5: 'Lack of Alternative Solutions/Documentation', 6: 'Documentation Replicability'}, 'label2id': {'Documentation Replication on Other Examples': 0, 'Requesting (Additional) Resources': 1, 'Inadequate Examples': 2, 'Documentation Ambiguity': 3, 'Documentation Completeness': 4, 'Lack of Alternative Solutions/Documentation': 5, 'Documentation Replicability': 6}, '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': 'mmukh/SOBertBase', 'transformers_version': '4.39.3', 'model_type': 'megatron-bert', 'tokenizer_type': 'SentencePieceTokenizer', 'vocab_size': 50048, 'hidden_size': 768, 'num_hidden_layers': 12, 'num_attention_heads': 12, 'hidden_act': 'gelu', 'intermediate_size': 3072, 'hidden_dropout_prob': 0.1, 'attention_probs_dropout_prob': 0.1, 'max_position_embeddings': 2048, 'type_vocab_size': 2, 'initializer_range': 0.02, 'layer_norm_eps': 1e-12, 'position_embedding_type': 'absolute', 'use_cache': 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': 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': 0.0, 'adam_beta1': 0.9, 'adam_beta2': 0.999, 'adam_epsilon': 1e-08, 'max_grad_norm': 1.0, 'num_train_epochs': 5, '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/Apr10_14-58-13_9088970cc926', 'logging_strategy': 'epoch', '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': True, '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, 'dataloader_prefetch_factor': None, '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_v2': False, 'xla_fsdp_grad_ckpt': False}, 'fsdp_transformer_layer_cls_to_wrap': None, 'accelerator_config': {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True}, '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': None, 'include_tokens_per_second': False, 'include_num_input_tokens_seen': False, 'neftune_noise_alpha': None, 'optim_target_modules': None}
+2024-04-10 15:06:23,666 INFO    MainThread:34 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-04-10 15:06:23,666 INFO    MainThread:34 [wandb_init.py:_pause_backend():438] pausing backend
+2024-04-10 15:06:30,822 INFO    MainThread:34 [wandb_init.py:_resume_backend():443] resuming backend
+2024-04-10 15:06:32,237 INFO    MainThread:34 [wandb_run.py:_config_callback():1347] 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': None, 'finetuning_task': None, 'id2label': {0: 'Documentation Replication on Other Examples', 1: 'Requesting (Additional) Resources', 2: 'Inadequate Examples', 3: 'Documentation Ambiguity', 4: 'Documentation Completeness', 5: 'Lack of Alternative Solutions/Documentation', 6: 'Documentation Replicability'}, 'label2id': {'Documentation Replication on Other Examples': 0, 'Requesting (Additional) Resources': 1, 'Inadequate Examples': 2, 'Documentation Ambiguity': 3, 'Documentation Completeness': 4, 'Lack of Alternative Solutions/Documentation': 5, 'Documentation Replicability': 6}, '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': 'mmukh/SOBertBase', 'transformers_version': '4.39.3', 'model_type': 'megatron-bert', 'tokenizer_type': 'SentencePieceTokenizer', 'vocab_size': 50048, 'hidden_size': 768, 'num_hidden_layers': 12, 'num_attention_heads': 12, 'hidden_act': 'gelu', 'intermediate_size': 3072, 'hidden_dropout_prob': 0.1, 'attention_probs_dropout_prob': 0.1, 'max_position_embeddings': 2048, 'type_vocab_size': 2, 'initializer_range': 0.02, 'layer_norm_eps': 1e-12, 'position_embedding_type': 'absolute', 'use_cache': 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': 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': 1e-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': 10, '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/Apr10_15-06-31_9088970cc926', 'logging_strategy': 'epoch', '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': True, '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, 'dataloader_prefetch_factor': None, '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_v2': False, 'xla_fsdp_grad_ckpt': False}, 'fsdp_transformer_layer_cls_to_wrap': None, 'accelerator_config': {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True}, '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': None, 'include_tokens_per_second': False, 'include_num_input_tokens_seen': False, 'neftune_noise_alpha': None, 'optim_target_modules': None}

wandb/run-20240410_150123-cuua991r/files/config.yaml

@@ -377,10 +377,10 @@ eval_delay:
   value: 0
 learning_rate:
   desc: null
-  value: 2.0e-05
+  value: 1.0e-05
 weight_decay:
   desc: null
-  value: 0.0
+  value: 0.01
 adam_beta1:
   desc: null
   value: 0.9
@@ -395,7 +395,7 @@ max_grad_norm:
   value: 1.0
 num_train_epochs:
   desc: null
-  value: 5
+  value: 10
 max_steps:
   desc: null
   value: -1
@@ -422,7 +422,7 @@ log_on_each_node:
   value: true
 logging_dir:
   desc: null
-  value: /kaggle/working/runs/Apr10_14-58-13_9088970cc926
+  value: /kaggle/working/runs/Apr10_15-06-31_9088970cc926
 logging_strategy:
   desc: null
   value: epoch

wandb/run-20240410_150123-cuua991r/files/output.log

@@ -4,4 +4,11 @@
   _warn_prf(average, modifier, msg_start, len(result))
 /opt/conda/lib/python3.10/site-packages/sklearn/metrics/_classification.py:1344: UndefinedMetricWarning: Precision is 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/sklearn/metrics/_classification.py:1344: UndefinedMetricWarning: Precision is 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))
+Some weights of MegatronBertForSequenceClassification were not initialized from the model checkpoint at mmukh/SOBertBase and are newly initialized: ['bert.embeddings.token_type_embeddings.weight', 'bert.pooler.dense.bias', 'bert.pooler.dense.weight', 'classifier.bias', 'classifier.weight']
+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/accelerate/accelerator.py:432: FutureWarning: Passing the following arguments to `Accelerator` is deprecated and will be removed in version 1.0 of Accelerate: dict_keys(['dispatch_batches', 'split_batches', 'even_batches', 'use_seedable_sampler']). Please pass an `accelerate.DataLoaderConfiguration` instead:
+dataloader_config = DataLoaderConfiguration(dispatch_batches=None, split_batches=False, even_batches=True, use_seedable_sampler=True)
+  warnings.warn(
 /opt/conda/lib/python3.10/site-packages/sklearn/metrics/_classification.py:1344: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 in labels with no predicted samples. Use `zero_division` parameter to control this behavior.

wandb/run-20240410_150123-cuua991r/files/wandb-summary.json

@@ -1 +1 @@
-{"train/loss": 1.6949, "train/grad_norm": 8.816020011901855, "train/learning_rate": 4.067796610169492e-06, "train/epoch": 4.0, "train/global_step": 472, "_timestamp": 1712761540.7952058, "_runtime": 257.2444739341736, "_step": 7, "eval/loss": 1.831845998764038, "eval/accuracy": 0.24647887323943662, "eval/precision": 0.2143956274963212, "eval/recall": 0.24647887323943662, "eval/f1": 0.19645709307390735, "eval/runtime": 2.837, "eval/samples_per_second": 50.052, "eval/steps_per_second": 6.345}
+{"train/loss": 1.9466, "train/grad_norm": 6.16647481918335, "train/learning_rate": 9.008474576271187e-06, "train/epoch": 1.0, "train/global_step": 118, "_timestamp": 1712761649.556628, "_runtime": 366.0058960914612, "_step": 9, "eval/loss": 1.884623408317566, "eval/accuracy": 0.3028169014084507, "eval/precision": 0.21421540500035863, "eval/recall": 0.3028169014084507, "eval/f1": 0.20265131813759552, "eval/runtime": 2.8549, "eval/samples_per_second": 49.739, "eval/steps_per_second": 6.305}

wandb/run-20240410_150123-cuua991r/logs/debug-internal.log

@@ -230,3 +230,95 @@ subprocess.TimeoutExpired: Command '['conda', 'env', 'export']' timed out after
 2024-04-10 15:05:56,996 DEBUG   HandlerThread:100 [handler.py:handle_request():146] handle_request: stop_status
 2024-04-10 15:05:56,997 DEBUG   SenderThread:100 [sender.py:send_request():406] send_request: stop_status
 2024-04-10 15:05:58,215 DEBUG   HandlerThread:100 [handler.py:handle_request():146] handle_request: status_report
+2024-04-10 15:06:03,216 DEBUG   HandlerThread:100 [handler.py:handle_request():146] handle_request: status_report
+2024-04-10 15:06:08,217 DEBUG   HandlerThread:100 [handler.py:handle_request():146] handle_request: status_report
+2024-04-10 15:06:11,977 DEBUG   HandlerThread:100 [handler.py:handle_request():146] handle_request: internal_messages
+2024-04-10 15:06:11,996 DEBUG   HandlerThread:100 [handler.py:handle_request():146] handle_request: stop_status
+2024-04-10 15:06:11,996 DEBUG   SenderThread:100 [sender.py:send_request():406] send_request: stop_status
+2024-04-10 15:06:13,275 DEBUG   HandlerThread:100 [handler.py:handle_request():146] handle_request: status_report
+2024-04-10 15:06:18,276 DEBUG   HandlerThread:100 [handler.py:handle_request():146] handle_request: status_report
+2024-04-10 15:06:23,277 DEBUG   HandlerThread:100 [handler.py:handle_request():146] handle_request: status_report
+2024-04-10 15:06:23,666 DEBUG   HandlerThread:100 [handler.py:handle_request():146] handle_request: pause
+2024-04-10 15:06:23,667 INFO    HandlerThread:100 [handler.py:handle_request_pause():708] stopping system metrics thread
+2024-04-10 15:06:23,667 INFO    HandlerThread:100 [system_monitor.py:finish():203] Stopping system monitor
+2024-04-10 15:06:23,667 DEBUG   SystemMonitor:100 [system_monitor.py:_start():179] Finished system metrics aggregation loop
+2024-04-10 15:06:23,667 DEBUG   SystemMonitor:100 [system_monitor.py:_start():183] Publishing last batch of metrics
+2024-04-10 15:06:23,668 INFO    HandlerThread:100 [interfaces.py:finish():202] Joined cpu monitor
+2024-04-10 15:06:23,669 INFO    HandlerThread:100 [interfaces.py:finish():202] Joined disk monitor
+2024-04-10 15:06:23,673 INFO    HandlerThread:100 [interfaces.py:finish():202] Joined gpu monitor
+2024-04-10 15:06:23,674 INFO    HandlerThread:100 [interfaces.py:finish():202] Joined memory monitor
+2024-04-10 15:06:23,674 INFO    HandlerThread:100 [interfaces.py:finish():202] Joined network monitor
+2024-04-10 15:06:23,674 DEBUG   SenderThread:100 [sender.py:send():379] send: stats
+2024-04-10 15:06:26,978 DEBUG   HandlerThread:100 [handler.py:handle_request():146] handle_request: internal_messages
+2024-04-10 15:06:26,996 DEBUG   HandlerThread:100 [handler.py:handle_request():146] handle_request: stop_status
+2024-04-10 15:06:26,997 DEBUG   SenderThread:100 [sender.py:send_request():406] send_request: stop_status
+2024-04-10 15:06:29,233 DEBUG   HandlerThread:100 [handler.py:handle_request():146] handle_request: status_report
+2024-04-10 15:06:30,823 DEBUG   HandlerThread:100 [handler.py:handle_request():146] handle_request: resume
+2024-04-10 15:06:30,823 INFO    HandlerThread:100 [handler.py:handle_request_resume():699] starting system metrics thread
+2024-04-10 15:06:30,823 INFO    HandlerThread:100 [system_monitor.py:start():194] Starting system monitor
+2024-04-10 15:06:30,823 INFO    SystemMonitor:100 [system_monitor.py:_start():158] Starting system asset monitoring threads
+2024-04-10 15:06:30,824 INFO    SystemMonitor:100 [interfaces.py:start():190] Started cpu monitoring
+2024-04-10 15:06:30,825 INFO    SystemMonitor:100 [interfaces.py:start():190] Started disk monitoring
+2024-04-10 15:06:30,826 INFO    SystemMonitor:100 [interfaces.py:start():190] Started gpu monitoring
+2024-04-10 15:06:30,826 INFO    SystemMonitor:100 [interfaces.py:start():190] Started memory monitoring
+2024-04-10 15:06:30,827 INFO    SystemMonitor:100 [interfaces.py:start():190] Started network monitoring
+2024-04-10 15:06:32,242 DEBUG   SenderThread:100 [sender.py:send():379] send: config
+2024-04-10 15:06:32,243 DEBUG   SenderThread:100 [sender.py:send():379] send: metric
+2024-04-10 15:06:32,243 DEBUG   SenderThread:100 [sender.py:send():379] send: metric
+2024-04-10 15:06:32,243 WARNING SenderThread:100 [sender.py:send_metric():1341] Seen metric with glob (shouldn't happen)
+2024-04-10 15:06:34,244 DEBUG   HandlerThread:100 [handler.py:handle_request():146] handle_request: status_report
+2024-04-10 15:06:34,766 INFO    Thread-12 :100 [dir_watcher.py:_on_file_modified():288] file/dir modified: /kaggle/working/wandb/run-20240410_150123-cuua991r/files/output.log
+2024-04-10 15:06:39,250 DEBUG   HandlerThread:100 [handler.py:handle_request():146] handle_request: status_report
+2024-04-10 15:06:39,768 INFO    Thread-12 :100 [dir_watcher.py:_on_file_modified():288] file/dir modified: /kaggle/working/wandb/run-20240410_150123-cuua991r/files/config.yaml
+2024-04-10 15:06:41,978 DEBUG   HandlerThread:100 [handler.py:handle_request():146] handle_request: internal_messages
+2024-04-10 15:06:41,996 DEBUG   HandlerThread:100 [handler.py:handle_request():146] handle_request: stop_status
+2024-04-10 15:06:41,997 DEBUG   SenderThread:100 [sender.py:send_request():406] send_request: stop_status
+2024-04-10 15:06:45,276 DEBUG   HandlerThread:100 [handler.py:handle_request():146] handle_request: status_report
+2024-04-10 15:06:50,277 DEBUG   HandlerThread:100 [handler.py:handle_request():146] handle_request: status_report
+2024-04-10 15:06:55,277 DEBUG   HandlerThread:100 [handler.py:handle_request():146] handle_request: status_report
+2024-04-10 15:06:56,977 DEBUG   HandlerThread:100 [handler.py:handle_request():146] handle_request: internal_messages
+2024-04-10 15:06:56,996 DEBUG   HandlerThread:100 [handler.py:handle_request():146] handle_request: stop_status
+2024-04-10 15:06:56,997 DEBUG   SenderThread:100 [sender.py:send_request():406] send_request: stop_status
+2024-04-10 15:07:01,236 DEBUG   HandlerThread:100 [handler.py:handle_request():146] handle_request: status_report
+2024-04-10 15:07:06,237 DEBUG   HandlerThread:100 [handler.py:handle_request():146] handle_request: status_report
+2024-04-10 15:07:11,238 DEBUG   HandlerThread:100 [handler.py:handle_request():146] handle_request: status_report
+2024-04-10 15:07:11,985 DEBUG   HandlerThread:100 [handler.py:handle_request():146] handle_request: internal_messages
+2024-04-10 15:07:11,997 DEBUG   HandlerThread:100 [handler.py:handle_request():146] handle_request: stop_status
+2024-04-10 15:07:11,997 DEBUG   SenderThread:100 [sender.py:send_request():406] send_request: stop_status
+2024-04-10 15:07:17,194 DEBUG   HandlerThread:100 [handler.py:handle_request():146] handle_request: status_report
+2024-04-10 15:07:22,195 DEBUG   HandlerThread:100 [handler.py:handle_request():146] handle_request: status_report
+2024-04-10 15:07:26,698 DEBUG   HandlerThread:100 [handler.py:handle_request():146] handle_request: partial_history
+2024-04-10 15:07:26,699 DEBUG   SenderThread:100 [sender.py:send():379] send: history
+2024-04-10 15:07:26,699 DEBUG   SenderThread:100 [sender.py:send_request():406] send_request: summary_record
+2024-04-10 15:07:26,700 INFO    SenderThread:100 [sender.py:_save_file():1390] saving file wandb-summary.json with policy end
+2024-04-10 15:07:26,786 INFO    Thread-12 :100 [dir_watcher.py:_on_file_modified():288] file/dir modified: /kaggle/working/wandb/run-20240410_150123-cuua991r/files/wandb-summary.json
+2024-04-10 15:07:26,982 DEBUG   HandlerThread:100 [handler.py:handle_request():146] handle_request: internal_messages
+2024-04-10 15:07:26,997 DEBUG   HandlerThread:100 [handler.py:handle_request():146] handle_request: stop_status
+2024-04-10 15:07:26,997 DEBUG   SenderThread:100 [sender.py:send_request():406] send_request: stop_status
+2024-04-10 15:07:27,274 DEBUG   HandlerThread:100 [handler.py:handle_request():146] handle_request: status_report
+2024-04-10 15:07:29,557 DEBUG   HandlerThread:100 [handler.py:handle_request():146] handle_request: partial_history
+2024-04-10 15:07:29,558 DEBUG   SenderThread:100 [sender.py:send():379] send: history
+2024-04-10 15:07:29,559 DEBUG   SenderThread:100 [sender.py:send_request():406] send_request: summary_record
+2024-04-10 15:07:29,559 INFO    SenderThread:100 [sender.py:_save_file():1390] saving file wandb-summary.json with policy end
+2024-04-10 15:07:29,787 INFO    Thread-12 :100 [dir_watcher.py:_on_file_modified():288] file/dir modified: /kaggle/working/wandb/run-20240410_150123-cuua991r/files/wandb-summary.json
+2024-04-10 15:07:30,828 DEBUG   SystemMonitor:100 [system_monitor.py:_start():172] Starting system metrics aggregation loop
+2024-04-10 15:07:30,829 DEBUG   SenderThread:100 [sender.py:send():379] send: stats
+2024-04-10 15:07:32,789 INFO    Thread-12 :100 [dir_watcher.py:_on_file_modified():288] file/dir modified: /kaggle/working/wandb/run-20240410_150123-cuua991r/files/output.log
+2024-04-10 15:07:32,830 DEBUG   HandlerThread:100 [handler.py:handle_request():146] handle_request: status_report
+2024-04-10 15:07:37,831 DEBUG   HandlerThread:100 [handler.py:handle_request():146] handle_request: status_report
+2024-04-10 15:07:41,982 DEBUG   HandlerThread:100 [handler.py:handle_request():146] handle_request: internal_messages
+2024-04-10 15:07:41,997 DEBUG   HandlerThread:100 [handler.py:handle_request():146] handle_request: stop_status
+2024-04-10 15:07:41,997 DEBUG   SenderThread:100 [sender.py:send_request():406] send_request: stop_status
+2024-04-10 15:07:43,201 DEBUG   HandlerThread:100 [handler.py:handle_request():146] handle_request: status_report
+2024-04-10 15:07:48,203 DEBUG   HandlerThread:100 [handler.py:handle_request():146] handle_request: status_report
+2024-04-10 15:07:53,204 DEBUG   HandlerThread:100 [handler.py:handle_request():146] handle_request: status_report
+2024-04-10 15:07:56,982 DEBUG   HandlerThread:100 [handler.py:handle_request():146] handle_request: internal_messages
+2024-04-10 15:07:56,997 DEBUG   HandlerThread:100 [handler.py:handle_request():146] handle_request: stop_status
+2024-04-10 15:07:56,997 DEBUG   SenderThread:100 [sender.py:send_request():406] send_request: stop_status
+2024-04-10 15:07:58,276 DEBUG   HandlerThread:100 [handler.py:handle_request():146] handle_request: status_report
+2024-04-10 15:08:00,830 DEBUG   SenderThread:100 [sender.py:send():379] send: stats
+2024-04-10 15:08:03,831 DEBUG   HandlerThread:100 [handler.py:handle_request():146] handle_request: status_report
+2024-04-10 15:08:08,832 DEBUG   HandlerThread:100 [handler.py:handle_request():146] handle_request: status_report
+2024-04-10 15:08:11,983 DEBUG   HandlerThread:100 [handler.py:handle_request():146] handle_request: internal_messages
+2024-04-10 15:08:11,997 DEBUG   HandlerThread:100 [handler.py:handle_request():146] handle_request: stop_status
+2024-04-10 15:08:11,998 DEBUG   SenderThread:100 [sender.py:send_request():406] send_request: stop_status

wandb/run-20240410_150123-cuua991r/logs/debug.log

@@ -30,3 +30,7 @@ config: {}
 2024-04-10 15:01:41,747 INFO    MainThread:34 [wandb_run.py:_redirect():2268] Redirects installed.
 2024-04-10 15:01:41,749 INFO    MainThread:34 [wandb_init.py:init():848] run started, returning control to user process
 2024-04-10 15:01:41,754 INFO    MainThread:34 [wandb_run.py:_config_callback():1347] 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': None, 'finetuning_task': None, 'id2label': {0: 'Documentation Replication on Other Examples', 1: 'Requesting (Additional) Resources', 2: 'Inadequate Examples', 3: 'Documentation Ambiguity', 4: 'Documentation Completeness', 5: 'Lack of Alternative Solutions/Documentation', 6: 'Documentation Replicability'}, 'label2id': {'Documentation Replication on Other Examples': 0, 'Requesting (Additional) Resources': 1, 'Inadequate Examples': 2, 'Documentation Ambiguity': 3, 'Documentation Completeness': 4, 'Lack of Alternative Solutions/Documentation': 5, 'Documentation Replicability': 6}, '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': 'mmukh/SOBertBase', 'transformers_version': '4.39.3', 'model_type': 'megatron-bert', 'tokenizer_type': 'SentencePieceTokenizer', 'vocab_size': 50048, 'hidden_size': 768, 'num_hidden_layers': 12, 'num_attention_heads': 12, 'hidden_act': 'gelu', 'intermediate_size': 3072, 'hidden_dropout_prob': 0.1, 'attention_probs_dropout_prob': 0.1, 'max_position_embeddings': 2048, 'type_vocab_size': 2, 'initializer_range': 0.02, 'layer_norm_eps': 1e-12, 'position_embedding_type': 'absolute', 'use_cache': 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': 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': 0.0, 'adam_beta1': 0.9, 'adam_beta2': 0.999, 'adam_epsilon': 1e-08, 'max_grad_norm': 1.0, 'num_train_epochs': 5, '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/Apr10_14-58-13_9088970cc926', 'logging_strategy': 'epoch', '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': True, '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, 'dataloader_prefetch_factor': None, '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_v2': False, 'xla_fsdp_grad_ckpt': False}, 'fsdp_transformer_layer_cls_to_wrap': None, 'accelerator_config': {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True}, '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': None, 'include_tokens_per_second': False, 'include_num_input_tokens_seen': False, 'neftune_noise_alpha': None, 'optim_target_modules': None}
+2024-04-10 15:06:23,666 INFO    MainThread:34 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-04-10 15:06:23,666 INFO    MainThread:34 [wandb_init.py:_pause_backend():438] pausing backend
+2024-04-10 15:06:30,822 INFO    MainThread:34 [wandb_init.py:_resume_backend():443] resuming backend
+2024-04-10 15:06:32,237 INFO    MainThread:34 [wandb_run.py:_config_callback():1347] 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': None, 'finetuning_task': None, 'id2label': {0: 'Documentation Replication on Other Examples', 1: 'Requesting (Additional) Resources', 2: 'Inadequate Examples', 3: 'Documentation Ambiguity', 4: 'Documentation Completeness', 5: 'Lack of Alternative Solutions/Documentation', 6: 'Documentation Replicability'}, 'label2id': {'Documentation Replication on Other Examples': 0, 'Requesting (Additional) Resources': 1, 'Inadequate Examples': 2, 'Documentation Ambiguity': 3, 'Documentation Completeness': 4, 'Lack of Alternative Solutions/Documentation': 5, 'Documentation Replicability': 6}, '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': 'mmukh/SOBertBase', 'transformers_version': '4.39.3', 'model_type': 'megatron-bert', 'tokenizer_type': 'SentencePieceTokenizer', 'vocab_size': 50048, 'hidden_size': 768, 'num_hidden_layers': 12, 'num_attention_heads': 12, 'hidden_act': 'gelu', 'intermediate_size': 3072, 'hidden_dropout_prob': 0.1, 'attention_probs_dropout_prob': 0.1, 'max_position_embeddings': 2048, 'type_vocab_size': 2, 'initializer_range': 0.02, 'layer_norm_eps': 1e-12, 'position_embedding_type': 'absolute', 'use_cache': 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': 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': 1e-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': 10, '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/Apr10_15-06-31_9088970cc926', 'logging_strategy': 'epoch', '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': True, '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, 'dataloader_prefetch_factor': None, '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_v2': False, 'xla_fsdp_grad_ckpt': False}, 'fsdp_transformer_layer_cls_to_wrap': None, 'accelerator_config': {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True}, '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': None, 'include_tokens_per_second': False, 'include_num_input_tokens_seen': False, 'neftune_noise_alpha': None, 'optim_target_modules': None}