Model save

README.md

@@ -38,7 +38,7 @@ The following hyperparameters were used during training:
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 200
+- num_epochs: 100
 
 ### Training results
 

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fa7381cca6912fbc05b87a20e7c4ea6b59aa8622db87b9f4a7f460af97065715
+oid sha256:461ebc813d97dd353a1d8ae01f63c00d6811f44026e7a05344862c9d243e9429
 size 328693404

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:733aceeb969b36181910bd1616e938b7b53032da8c7f4678ebad281d1c708653
-size 4707
+oid sha256:99da6e901c1e1e9c2fcdd3a9b64b58e1bb91f45a16c28d9820734b11466026b2
+size 5061

wandb/debug-internal.log

@@ -1674,3 +1674,57 @@
 2024-01-18 01:22:58,263 DEBUG   HandlerThread:98 [handler.py:handle_request():146] handle_request: status_report
 2024-01-18 01:23:00,764 DEBUG   HandlerThread:98 [handler.py:handle_request():146] handle_request: keepalive
 2024-01-18 01:23:03,264 DEBUG   HandlerThread:98 [handler.py:handle_request():146] handle_request: status_report
+2024-01-18 01:23:05,765 DEBUG   HandlerThread:98 [handler.py:handle_request():146] handle_request: keepalive
+2024-01-18 01:23:06,241 DEBUG   SenderThread:98 [sender.py:send():382] send: stats
+2024-01-18 01:23:09,242 DEBUG   HandlerThread:98 [handler.py:handle_request():146] handle_request: status_report
+2024-01-18 01:23:10,766 DEBUG   HandlerThread:98 [handler.py:handle_request():146] handle_request: keepalive
+2024-01-18 01:23:14,243 DEBUG   HandlerThread:98 [handler.py:handle_request():146] handle_request: status_report
+2024-01-18 01:23:15,767 DEBUG   HandlerThread:98 [handler.py:handle_request():146] handle_request: keepalive
+2024-01-18 01:23:19,244 DEBUG   HandlerThread:98 [handler.py:handle_request():146] handle_request: status_report
+2024-01-18 01:23:20,768 DEBUG   HandlerThread:98 [handler.py:handle_request():146] handle_request: keepalive
+2024-01-18 01:23:24,245 DEBUG   HandlerThread:98 [handler.py:handle_request():146] handle_request: status_report
+2024-01-18 01:23:25,769 DEBUG   HandlerThread:98 [handler.py:handle_request():146] handle_request: keepalive
+2024-01-18 01:23:29,246 DEBUG   HandlerThread:98 [handler.py:handle_request():146] handle_request: status_report
+2024-01-18 01:23:30,770 DEBUG   HandlerThread:98 [handler.py:handle_request():146] handle_request: keepalive
+2024-01-18 01:23:34,247 DEBUG   HandlerThread:98 [handler.py:handle_request():146] handle_request: status_report
+2024-01-18 01:23:35,771 DEBUG   HandlerThread:98 [handler.py:handle_request():146] handle_request: keepalive
+2024-01-18 01:23:36,242 DEBUG   SenderThread:98 [sender.py:send():382] send: stats
+2024-01-18 01:23:40,243 DEBUG   HandlerThread:98 [handler.py:handle_request():146] handle_request: status_report
+2024-01-18 01:23:40,774 DEBUG   HandlerThread:98 [handler.py:handle_request():146] handle_request: keepalive
+2024-01-18 01:23:42,811 DEBUG   HandlerThread:98 [handler.py:handle_request():146] handle_request: partial_history
+2024-01-18 01:23:42,813 DEBUG   SenderThread:98 [sender.py:send():382] send: history
+2024-01-18 01:23:42,813 DEBUG   SenderThread:98 [sender.py:send_request():409] send_request: summary_record
+2024-01-18 01:23:42,813 INFO    SenderThread:98 [sender.py:_save_file():1403] saving file wandb-summary.json with policy end
+2024-01-18 01:23:42,816 DEBUG   HandlerThread:98 [handler.py:handle_request():146] handle_request: pause
+2024-01-18 01:23:42,816 INFO    HandlerThread:98 [handler.py:handle_request_pause():708] stopping system metrics thread
+2024-01-18 01:23:42,816 INFO    HandlerThread:98 [system_monitor.py:finish():203] Stopping system monitor
+2024-01-18 01:23:42,816 DEBUG   SystemMonitor:98 [system_monitor.py:_start():179] Finished system metrics aggregation loop
+2024-01-18 01:23:42,816 DEBUG   SystemMonitor:98 [system_monitor.py:_start():183] Publishing last batch of metrics
+2024-01-18 01:23:42,818 INFO    HandlerThread:98 [interfaces.py:finish():202] Joined cpu monitor
+2024-01-18 01:23:42,819 INFO    HandlerThread:98 [interfaces.py:finish():202] Joined disk monitor
+2024-01-18 01:23:42,828 INFO    HandlerThread:98 [interfaces.py:finish():202] Joined gpu monitor
+2024-01-18 01:23:42,828 INFO    HandlerThread:98 [interfaces.py:finish():202] Joined memory monitor
+2024-01-18 01:23:42,829 INFO    HandlerThread:98 [interfaces.py:finish():202] Joined network monitor
+2024-01-18 01:23:42,829 DEBUG   SenderThread:98 [sender.py:send():382] send: stats
+2024-01-18 01:23:43,376 INFO    Thread-12 :98 [dir_watcher.py:_on_file_modified():288] file/dir modified: /kaggle/working/wandb/run-20240118_004236-6kmvcnsc/files/wandb-summary.json
+2024-01-18 01:23:45,775 DEBUG   HandlerThread:98 [handler.py:handle_request():146] handle_request: keepalive
+2024-01-18 01:23:45,830 DEBUG   HandlerThread:98 [handler.py:handle_request():146] handle_request: status_report
+2024-01-18 01:23:50,776 DEBUG   HandlerThread:98 [handler.py:handle_request():146] handle_request: keepalive
+2024-01-18 01:23:50,831 DEBUG   HandlerThread:98 [handler.py:handle_request():146] handle_request: status_report
+2024-01-18 01:23:55,777 DEBUG   HandlerThread:98 [handler.py:handle_request():146] handle_request: keepalive
+2024-01-18 01:23:55,831 DEBUG   HandlerThread:98 [handler.py:handle_request():146] handle_request: status_report
+2024-01-18 01:24:00,159 DEBUG   HandlerThread:98 [handler.py:handle_request():146] handle_request: resume
+2024-01-18 01:24:00,159 INFO    HandlerThread:98 [handler.py:handle_request_resume():699] starting system metrics thread
+2024-01-18 01:24:00,159 INFO    HandlerThread:98 [system_monitor.py:start():194] Starting system monitor
+2024-01-18 01:24:00,159 INFO    SystemMonitor:98 [system_monitor.py:_start():158] Starting system asset monitoring threads
+2024-01-18 01:24:00,160 INFO    SystemMonitor:98 [interfaces.py:start():190] Started cpu monitoring
+2024-01-18 01:24:00,161 INFO    SystemMonitor:98 [interfaces.py:start():190] Started disk monitoring
+2024-01-18 01:24:00,161 INFO    SystemMonitor:98 [interfaces.py:start():190] Started gpu monitoring
+2024-01-18 01:24:00,165 INFO    SystemMonitor:98 [interfaces.py:start():190] Started memory monitoring
+2024-01-18 01:24:00,166 INFO    SystemMonitor:98 [interfaces.py:start():190] Started network monitoring
+2024-01-18 01:24:00,832 DEBUG   HandlerThread:98 [handler.py:handle_request():146] handle_request: status_report
+2024-01-18 01:24:01,069 DEBUG   HandlerThread:98 [handler.py:handle_request():146] handle_request: keepalive
+2024-01-18 01:24:05,833 DEBUG   HandlerThread:98 [handler.py:handle_request():146] handle_request: status_report
+2024-01-18 01:24:06,070 DEBUG   HandlerThread:98 [handler.py:handle_request():146] handle_request: keepalive
+2024-01-18 01:24:10,834 DEBUG   HandlerThread:98 [handler.py:handle_request():146] handle_request: status_report
+2024-01-18 01:24:11,071 DEBUG   HandlerThread:98 [handler.py:handle_request():146] handle_request: keepalive

wandb/debug.log

@@ -110,3 +110,6 @@ config: {}
 2024-01-18 01:20:05,921 INFO    MainThread:26 [wandb_init.py:_pause_backend():437] pausing backend
 2024-01-18 01:20:06,232 INFO    MainThread:26 [wandb_init.py:_resume_backend():442] resuming backend
 2024-01-18 01:20:06,708 INFO    MainThread:26 [wandb_run.py:_config_callback():1342] config_cb None None {'return_dict': True, 'output_hidden_states': False, 'output_attentions': False, 'torchscript': False, 'torch_dtype': 'float32', 'use_bfloat16': False, 'tf_legacy_loss': False, 'pruned_heads': {}, 'tie_word_embeddings': True, 'is_encoder_decoder': False, 'is_decoder': False, 'cross_attention_hidden_size': None, 'add_cross_attention': False, 'tie_encoder_decoder': False, 'max_length': 20, 'min_length': 0, 'do_sample': False, 'early_stopping': False, 'num_beams': 1, 'num_beam_groups': 1, 'diversity_penalty': 0.0, 'temperature': 1.0, 'top_k': 50, 'top_p': 1.0, 'typical_p': 1.0, 'repetition_penalty': 1.0, 'length_penalty': 1.0, 'no_repeat_ngram_size': 0, 'encoder_no_repeat_ngram_size': 0, 'bad_words_ids': None, 'num_return_sequences': 1, 'chunk_size_feed_forward': 0, 'output_scores': False, 'return_dict_in_generate': False, 'forced_bos_token_id': None, 'forced_eos_token_id': None, 'remove_invalid_values': False, 'exponential_decay_length_penalty': None, 'suppress_tokens': None, 'begin_suppress_tokens': None, 'architectures': ['RobertaForMaskedLM'], 'finetuning_task': None, 'id2label': {0: 'LABEL_0', 1: 'LABEL_1'}, 'label2id': {'LABEL_0': 0, 'LABEL_1': 1}, 'tokenizer_class': None, 'prefix': None, 'bos_token_id': 0, 'pad_token_id': 1, 'eos_token_id': 2, 'sep_token_id': None, 'decoder_start_token_id': None, 'task_specific_params': None, 'problem_type': None, '_name_or_path': 'distilroberta-base', 'transformers_version': '4.36.2', 'model_type': 'roberta', 'vocab_size': 50265, 'hidden_size': 768, 'num_hidden_layers': 6, 'num_attention_heads': 12, 'hidden_act': 'gelu', 'intermediate_size': 3072, 'hidden_dropout_prob': 0.1, 'attention_probs_dropout_prob': 0.1, 'max_position_embeddings': 514, 'type_vocab_size': 1, 'initializer_range': 0.02, 'layer_norm_eps': 1e-05, 'position_embedding_type': 'absolute', 'use_cache': True, 'classifier_dropout': None, 'output_dir': '/kaggle/working', 'overwrite_output_dir': False, 'do_train': False, 'do_eval': False, 'do_predict': False, 'evaluation_strategy': 'no', 'prediction_loss_only': False, 'per_device_train_batch_size': 8, 'per_device_eval_batch_size': 8, 'per_gpu_train_batch_size': None, 'per_gpu_eval_batch_size': None, 'gradient_accumulation_steps': 1, 'eval_accumulation_steps': None, 'eval_delay': 0, 'learning_rate': 2e-05, 'weight_decay': 0.01, 'adam_beta1': 0.9, 'adam_beta2': 0.999, 'adam_epsilon': 1e-08, 'max_grad_norm': 1.0, 'num_train_epochs': 100, 'max_steps': -1, 'lr_scheduler_type': 'linear', 'lr_scheduler_kwargs': {}, 'warmup_ratio': 0.0, 'warmup_steps': 0, 'log_level': 'passive', 'log_level_replica': 'warning', 'log_on_each_node': True, 'logging_dir': '/kaggle/working/runs/Jan18_01-20-04_455f56c2d2db', 'logging_strategy': 'steps', 'logging_first_step': False, 'logging_steps': 500, 'logging_nan_inf_filter': True, 'save_strategy': 'steps', 'save_steps': 500, 'save_total_limit': None, 'save_safetensors': True, 'save_on_each_node': False, 'save_only_model': False, 'no_cuda': False, 'use_cpu': False, 'use_mps_device': False, 'seed': 42, 'data_seed': None, 'jit_mode_eval': False, 'use_ipex': False, 'bf16': False, 'fp16': False, 'fp16_opt_level': 'O1', 'half_precision_backend': 'auto', 'bf16_full_eval': False, 'fp16_full_eval': False, 'tf32': None, 'local_rank': 0, 'ddp_backend': None, 'tpu_num_cores': None, 'tpu_metrics_debug': False, 'debug': [], 'dataloader_drop_last': False, 'eval_steps': None, 'dataloader_num_workers': 0, 'past_index': -1, 'run_name': '/kaggle/working', 'disable_tqdm': False, 'remove_unused_columns': True, 'label_names': None, 'load_best_model_at_end': False, 'metric_for_best_model': None, 'greater_is_better': None, 'ignore_data_skip': False, 'fsdp': [], 'fsdp_min_num_params': 0, 'fsdp_config': {'min_num_params': 0, 'xla': False, 'xla_fsdp_grad_ckpt': False}, 'fsdp_transformer_layer_cls_to_wrap': None, 'deepspeed': None, 'label_smoothing_factor': 0.0, 'optim': 'adamw_torch', 'optim_args': None, 'adafactor': False, 'group_by_length': False, 'length_column_name': 'length', 'report_to': ['tensorboard', 'wandb'], 'ddp_find_unused_parameters': None, 'ddp_bucket_cap_mb': None, 'ddp_broadcast_buffers': None, 'dataloader_pin_memory': True, 'dataloader_persistent_workers': False, 'skip_memory_metrics': True, 'use_legacy_prediction_loop': False, 'push_to_hub': True, 'resume_from_checkpoint': None, 'hub_model_id': None, 'hub_strategy': 'every_save', 'hub_token': '<HUB_TOKEN>', 'hub_private_repo': False, 'hub_always_push': False, 'gradient_checkpointing': False, 'gradient_checkpointing_kwargs': None, 'include_inputs_for_metrics': False, 'fp16_backend': 'auto', 'push_to_hub_model_id': None, 'push_to_hub_organization': None, 'push_to_hub_token': '<PUSH_TO_HUB_TOKEN>', 'mp_parameters': '', 'auto_find_batch_size': False, 'full_determinism': False, 'torchdynamo': None, 'ray_scope': 'last', 'ddp_timeout': 1800, 'torch_compile': False, 'torch_compile_backend': None, 'torch_compile_mode': None, 'dispatch_batches': None, 'split_batches': False, 'include_tokens_per_second': False, 'include_num_input_tokens_seen': False, 'neftune_noise_alpha': None}
+2024-01-18 01:23:42,815 INFO    MainThread:26 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-01-18 01:23:42,815 INFO    MainThread:26 [wandb_init.py:_pause_backend():437] pausing backend
+2024-01-18 01:24:00,158 INFO    MainThread:26 [wandb_init.py:_resume_backend():442] resuming backend

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

@@ -1 +1 @@
-{"train/loss": 0.5876, "train/learning_rate": 4.615384615384616e-06, "train/epoch": 76.92, "train/global_step": 1000, "_timestamp": 1705540970.0977304, "_runtime": 2413.285456418991, "_step": 7, "train/train_runtime": 481.0951, "train/train_samples_per_second": 85.638, "train/train_steps_per_second": 5.404, "train/total_flos": 532735580432880.0, "train/train_loss": 1.8117729509793794}
+{"train/loss": 0.5876, "train/learning_rate": 4.615384615384616e-06, "train/epoch": 100.0, "train/global_step": 1300, "_timestamp": 1705541022.8112755, "_runtime": 2465.9990015029907, "_step": 8, "train/train_runtime": 216.1142, "train/train_samples_per_second": 95.32, "train/train_steps_per_second": 6.015, "train/total_flos": 267158340516672.0, "train/train_loss": 0.6962077214167668}

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

@@ -1674,3 +1674,57 @@
 2024-01-18 01:22:58,263 DEBUG   HandlerThread:98 [handler.py:handle_request():146] handle_request: status_report
 2024-01-18 01:23:00,764 DEBUG   HandlerThread:98 [handler.py:handle_request():146] handle_request: keepalive
 2024-01-18 01:23:03,264 DEBUG   HandlerThread:98 [handler.py:handle_request():146] handle_request: status_report
+2024-01-18 01:23:05,765 DEBUG   HandlerThread:98 [handler.py:handle_request():146] handle_request: keepalive
+2024-01-18 01:23:06,241 DEBUG   SenderThread:98 [sender.py:send():382] send: stats
+2024-01-18 01:23:09,242 DEBUG   HandlerThread:98 [handler.py:handle_request():146] handle_request: status_report
+2024-01-18 01:23:10,766 DEBUG   HandlerThread:98 [handler.py:handle_request():146] handle_request: keepalive
+2024-01-18 01:23:14,243 DEBUG   HandlerThread:98 [handler.py:handle_request():146] handle_request: status_report
+2024-01-18 01:23:15,767 DEBUG   HandlerThread:98 [handler.py:handle_request():146] handle_request: keepalive
+2024-01-18 01:23:19,244 DEBUG   HandlerThread:98 [handler.py:handle_request():146] handle_request: status_report
+2024-01-18 01:23:20,768 DEBUG   HandlerThread:98 [handler.py:handle_request():146] handle_request: keepalive
+2024-01-18 01:23:24,245 DEBUG   HandlerThread:98 [handler.py:handle_request():146] handle_request: status_report
+2024-01-18 01:23:25,769 DEBUG   HandlerThread:98 [handler.py:handle_request():146] handle_request: keepalive
+2024-01-18 01:23:29,246 DEBUG   HandlerThread:98 [handler.py:handle_request():146] handle_request: status_report
+2024-01-18 01:23:30,770 DEBUG   HandlerThread:98 [handler.py:handle_request():146] handle_request: keepalive
+2024-01-18 01:23:34,247 DEBUG   HandlerThread:98 [handler.py:handle_request():146] handle_request: status_report
+2024-01-18 01:23:35,771 DEBUG   HandlerThread:98 [handler.py:handle_request():146] handle_request: keepalive
+2024-01-18 01:23:36,242 DEBUG   SenderThread:98 [sender.py:send():382] send: stats
+2024-01-18 01:23:40,243 DEBUG   HandlerThread:98 [handler.py:handle_request():146] handle_request: status_report
+2024-01-18 01:23:40,774 DEBUG   HandlerThread:98 [handler.py:handle_request():146] handle_request: keepalive
+2024-01-18 01:23:42,811 DEBUG   HandlerThread:98 [handler.py:handle_request():146] handle_request: partial_history
+2024-01-18 01:23:42,813 DEBUG   SenderThread:98 [sender.py:send():382] send: history
+2024-01-18 01:23:42,813 DEBUG   SenderThread:98 [sender.py:send_request():409] send_request: summary_record
+2024-01-18 01:23:42,813 INFO    SenderThread:98 [sender.py:_save_file():1403] saving file wandb-summary.json with policy end
+2024-01-18 01:23:42,816 DEBUG   HandlerThread:98 [handler.py:handle_request():146] handle_request: pause
+2024-01-18 01:23:42,816 INFO    HandlerThread:98 [handler.py:handle_request_pause():708] stopping system metrics thread
+2024-01-18 01:23:42,816 INFO    HandlerThread:98 [system_monitor.py:finish():203] Stopping system monitor
+2024-01-18 01:23:42,816 DEBUG   SystemMonitor:98 [system_monitor.py:_start():179] Finished system metrics aggregation loop
+2024-01-18 01:23:42,816 DEBUG   SystemMonitor:98 [system_monitor.py:_start():183] Publishing last batch of metrics
+2024-01-18 01:23:42,818 INFO    HandlerThread:98 [interfaces.py:finish():202] Joined cpu monitor
+2024-01-18 01:23:42,819 INFO    HandlerThread:98 [interfaces.py:finish():202] Joined disk monitor
+2024-01-18 01:23:42,828 INFO    HandlerThread:98 [interfaces.py:finish():202] Joined gpu monitor
+2024-01-18 01:23:42,828 INFO    HandlerThread:98 [interfaces.py:finish():202] Joined memory monitor
+2024-01-18 01:23:42,829 INFO    HandlerThread:98 [interfaces.py:finish():202] Joined network monitor
+2024-01-18 01:23:42,829 DEBUG   SenderThread:98 [sender.py:send():382] send: stats
+2024-01-18 01:23:43,376 INFO    Thread-12 :98 [dir_watcher.py:_on_file_modified():288] file/dir modified: /kaggle/working/wandb/run-20240118_004236-6kmvcnsc/files/wandb-summary.json
+2024-01-18 01:23:45,775 DEBUG   HandlerThread:98 [handler.py:handle_request():146] handle_request: keepalive
+2024-01-18 01:23:45,830 DEBUG   HandlerThread:98 [handler.py:handle_request():146] handle_request: status_report
+2024-01-18 01:23:50,776 DEBUG   HandlerThread:98 [handler.py:handle_request():146] handle_request: keepalive
+2024-01-18 01:23:50,831 DEBUG   HandlerThread:98 [handler.py:handle_request():146] handle_request: status_report
+2024-01-18 01:23:55,777 DEBUG   HandlerThread:98 [handler.py:handle_request():146] handle_request: keepalive
+2024-01-18 01:23:55,831 DEBUG   HandlerThread:98 [handler.py:handle_request():146] handle_request: status_report
+2024-01-18 01:24:00,159 DEBUG   HandlerThread:98 [handler.py:handle_request():146] handle_request: resume
+2024-01-18 01:24:00,159 INFO    HandlerThread:98 [handler.py:handle_request_resume():699] starting system metrics thread
+2024-01-18 01:24:00,159 INFO    HandlerThread:98 [system_monitor.py:start():194] Starting system monitor
+2024-01-18 01:24:00,159 INFO    SystemMonitor:98 [system_monitor.py:_start():158] Starting system asset monitoring threads
+2024-01-18 01:24:00,160 INFO    SystemMonitor:98 [interfaces.py:start():190] Started cpu monitoring
+2024-01-18 01:24:00,161 INFO    SystemMonitor:98 [interfaces.py:start():190] Started disk monitoring
+2024-01-18 01:24:00,161 INFO    SystemMonitor:98 [interfaces.py:start():190] Started gpu monitoring
+2024-01-18 01:24:00,165 INFO    SystemMonitor:98 [interfaces.py:start():190] Started memory monitoring
+2024-01-18 01:24:00,166 INFO    SystemMonitor:98 [interfaces.py:start():190] Started network monitoring
+2024-01-18 01:24:00,832 DEBUG   HandlerThread:98 [handler.py:handle_request():146] handle_request: status_report
+2024-01-18 01:24:01,069 DEBUG   HandlerThread:98 [handler.py:handle_request():146] handle_request: keepalive
+2024-01-18 01:24:05,833 DEBUG   HandlerThread:98 [handler.py:handle_request():146] handle_request: status_report
+2024-01-18 01:24:06,070 DEBUG   HandlerThread:98 [handler.py:handle_request():146] handle_request: keepalive
+2024-01-18 01:24:10,834 DEBUG   HandlerThread:98 [handler.py:handle_request():146] handle_request: status_report
+2024-01-18 01:24:11,071 DEBUG   HandlerThread:98 [handler.py:handle_request():146] handle_request: keepalive

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

@@ -110,3 +110,6 @@ config: {}
 2024-01-18 01:20:05,921 INFO    MainThread:26 [wandb_init.py:_pause_backend():437] pausing backend
 2024-01-18 01:20:06,232 INFO    MainThread:26 [wandb_init.py:_resume_backend():442] resuming backend
 2024-01-18 01:20:06,708 INFO    MainThread:26 [wandb_run.py:_config_callback():1342] config_cb None None {'return_dict': True, 'output_hidden_states': False, 'output_attentions': False, 'torchscript': False, 'torch_dtype': 'float32', 'use_bfloat16': False, 'tf_legacy_loss': False, 'pruned_heads': {}, 'tie_word_embeddings': True, 'is_encoder_decoder': False, 'is_decoder': False, 'cross_attention_hidden_size': None, 'add_cross_attention': False, 'tie_encoder_decoder': False, 'max_length': 20, 'min_length': 0, 'do_sample': False, 'early_stopping': False, 'num_beams': 1, 'num_beam_groups': 1, 'diversity_penalty': 0.0, 'temperature': 1.0, 'top_k': 50, 'top_p': 1.0, 'typical_p': 1.0, 'repetition_penalty': 1.0, 'length_penalty': 1.0, 'no_repeat_ngram_size': 0, 'encoder_no_repeat_ngram_size': 0, 'bad_words_ids': None, 'num_return_sequences': 1, 'chunk_size_feed_forward': 0, 'output_scores': False, 'return_dict_in_generate': False, 'forced_bos_token_id': None, 'forced_eos_token_id': None, 'remove_invalid_values': False, 'exponential_decay_length_penalty': None, 'suppress_tokens': None, 'begin_suppress_tokens': None, 'architectures': ['RobertaForMaskedLM'], 'finetuning_task': None, 'id2label': {0: 'LABEL_0', 1: 'LABEL_1'}, 'label2id': {'LABEL_0': 0, 'LABEL_1': 1}, 'tokenizer_class': None, 'prefix': None, 'bos_token_id': 0, 'pad_token_id': 1, 'eos_token_id': 2, 'sep_token_id': None, 'decoder_start_token_id': None, 'task_specific_params': None, 'problem_type': None, '_name_or_path': 'distilroberta-base', 'transformers_version': '4.36.2', 'model_type': 'roberta', 'vocab_size': 50265, 'hidden_size': 768, 'num_hidden_layers': 6, 'num_attention_heads': 12, 'hidden_act': 'gelu', 'intermediate_size': 3072, 'hidden_dropout_prob': 0.1, 'attention_probs_dropout_prob': 0.1, 'max_position_embeddings': 514, 'type_vocab_size': 1, 'initializer_range': 0.02, 'layer_norm_eps': 1e-05, 'position_embedding_type': 'absolute', 'use_cache': True, 'classifier_dropout': None, 'output_dir': '/kaggle/working', 'overwrite_output_dir': False, 'do_train': False, 'do_eval': False, 'do_predict': False, 'evaluation_strategy': 'no', 'prediction_loss_only': False, 'per_device_train_batch_size': 8, 'per_device_eval_batch_size': 8, 'per_gpu_train_batch_size': None, 'per_gpu_eval_batch_size': None, 'gradient_accumulation_steps': 1, 'eval_accumulation_steps': None, 'eval_delay': 0, 'learning_rate': 2e-05, 'weight_decay': 0.01, 'adam_beta1': 0.9, 'adam_beta2': 0.999, 'adam_epsilon': 1e-08, 'max_grad_norm': 1.0, 'num_train_epochs': 100, 'max_steps': -1, 'lr_scheduler_type': 'linear', 'lr_scheduler_kwargs': {}, 'warmup_ratio': 0.0, 'warmup_steps': 0, 'log_level': 'passive', 'log_level_replica': 'warning', 'log_on_each_node': True, 'logging_dir': '/kaggle/working/runs/Jan18_01-20-04_455f56c2d2db', 'logging_strategy': 'steps', 'logging_first_step': False, 'logging_steps': 500, 'logging_nan_inf_filter': True, 'save_strategy': 'steps', 'save_steps': 500, 'save_total_limit': None, 'save_safetensors': True, 'save_on_each_node': False, 'save_only_model': False, 'no_cuda': False, 'use_cpu': False, 'use_mps_device': False, 'seed': 42, 'data_seed': None, 'jit_mode_eval': False, 'use_ipex': False, 'bf16': False, 'fp16': False, 'fp16_opt_level': 'O1', 'half_precision_backend': 'auto', 'bf16_full_eval': False, 'fp16_full_eval': False, 'tf32': None, 'local_rank': 0, 'ddp_backend': None, 'tpu_num_cores': None, 'tpu_metrics_debug': False, 'debug': [], 'dataloader_drop_last': False, 'eval_steps': None, 'dataloader_num_workers': 0, 'past_index': -1, 'run_name': '/kaggle/working', 'disable_tqdm': False, 'remove_unused_columns': True, 'label_names': None, 'load_best_model_at_end': False, 'metric_for_best_model': None, 'greater_is_better': None, 'ignore_data_skip': False, 'fsdp': [], 'fsdp_min_num_params': 0, 'fsdp_config': {'min_num_params': 0, 'xla': False, 'xla_fsdp_grad_ckpt': False}, 'fsdp_transformer_layer_cls_to_wrap': None, 'deepspeed': None, 'label_smoothing_factor': 0.0, 'optim': 'adamw_torch', 'optim_args': None, 'adafactor': False, 'group_by_length': False, 'length_column_name': 'length', 'report_to': ['tensorboard', 'wandb'], 'ddp_find_unused_parameters': None, 'ddp_bucket_cap_mb': None, 'ddp_broadcast_buffers': None, 'dataloader_pin_memory': True, 'dataloader_persistent_workers': False, 'skip_memory_metrics': True, 'use_legacy_prediction_loop': False, 'push_to_hub': True, 'resume_from_checkpoint': None, 'hub_model_id': None, 'hub_strategy': 'every_save', 'hub_token': '<HUB_TOKEN>', 'hub_private_repo': False, 'hub_always_push': False, 'gradient_checkpointing': False, 'gradient_checkpointing_kwargs': None, 'include_inputs_for_metrics': False, 'fp16_backend': 'auto', 'push_to_hub_model_id': None, 'push_to_hub_organization': None, 'push_to_hub_token': '<PUSH_TO_HUB_TOKEN>', 'mp_parameters': '', 'auto_find_batch_size': False, 'full_determinism': False, 'torchdynamo': None, 'ray_scope': 'last', 'ddp_timeout': 1800, 'torch_compile': False, 'torch_compile_backend': None, 'torch_compile_mode': None, 'dispatch_batches': None, 'split_batches': False, 'include_tokens_per_second': False, 'include_num_input_tokens_seen': False, 'neftune_noise_alpha': None}
+2024-01-18 01:23:42,815 INFO    MainThread:26 [jupyter.py:save_ipynb():373] not saving jupyter notebook
+2024-01-18 01:23:42,815 INFO    MainThread:26 [wandb_init.py:_pause_backend():437] pausing backend
+2024-01-18 01:24:00,158 INFO    MainThread:26 [wandb_init.py:_resume_backend():442] resuming backend

wandb/run-20240118_004236-6kmvcnsc/run-6kmvcnsc.wandb

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dc03a0bd222233001c3a8c64a974ecaecac37739453441ebf3b2ebad73ca87be
-size 4122780
+oid sha256:18df35fb40d2472ff7263753e428a29196319ed2bcff346c2128ca2d4a5c384c
+size 4126518