| { | |
| "best_metric": 0.8134122644816508, | |
| "best_model_checkpoint": "tmp_ner_fantastic-bale-13_29/run-67/checkpoint-323", | |
| "epoch": 17.0, | |
| "eval_steps": 500, | |
| "global_step": 323, | |
| "is_hyper_param_search": true, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.8623242503421675, | |
| "eval_loss": 0.7986403703689575, | |
| "eval_macro_f1": 0.04409872183381453, | |
| "eval_macro_precision": 0.04106305954010322, | |
| "eval_macro_recall": 0.047619047619047616, | |
| "eval_runtime": 0.7532, | |
| "eval_samples_per_second": 132.763, | |
| "eval_steps_per_second": 17.259, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.9034465596615653, | |
| "eval_loss": 0.3603612184524536, | |
| "eval_macro_f1": 0.12106609239101934, | |
| "eval_macro_precision": 0.1259515690157799, | |
| "eval_macro_recall": 0.14408855709243762, | |
| "eval_runtime": 0.7511, | |
| "eval_samples_per_second": 133.136, | |
| "eval_steps_per_second": 17.308, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.9519410227696902, | |
| "eval_loss": 0.18390077352523804, | |
| "eval_macro_f1": 0.3148808447564158, | |
| "eval_macro_precision": 0.3747061248934609, | |
| "eval_macro_recall": 0.3212448125969776, | |
| "eval_runtime": 0.7242, | |
| "eval_samples_per_second": 138.085, | |
| "eval_steps_per_second": 17.951, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.965036705238273, | |
| "eval_loss": 0.1359422653913498, | |
| "eval_macro_f1": 0.494219195343988, | |
| "eval_macro_precision": 0.5137741995898872, | |
| "eval_macro_recall": 0.5215328224472264, | |
| "eval_runtime": 0.7408, | |
| "eval_samples_per_second": 134.981, | |
| "eval_steps_per_second": 17.547, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_accuracy": 0.9700447928331467, | |
| "eval_loss": 0.11635323613882065, | |
| "eval_macro_f1": 0.5902868533471133, | |
| "eval_macro_precision": 0.6804922518993798, | |
| "eval_macro_recall": 0.6058126722062964, | |
| "eval_runtime": 0.7171, | |
| "eval_samples_per_second": 139.455, | |
| "eval_steps_per_second": 18.129, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_accuracy": 0.9751461988304093, | |
| "eval_loss": 0.11470664292573929, | |
| "eval_macro_f1": 0.6704539076542243, | |
| "eval_macro_precision": 0.701121495572558, | |
| "eval_macro_recall": 0.6900336890446782, | |
| "eval_runtime": 0.7646, | |
| "eval_samples_per_second": 130.796, | |
| "eval_steps_per_second": 17.003, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_accuracy": 0.9759549583177802, | |
| "eval_loss": 0.11508199572563171, | |
| "eval_macro_f1": 0.7577631140226684, | |
| "eval_macro_precision": 0.8839369325293773, | |
| "eval_macro_recall": 0.7206940753172821, | |
| "eval_runtime": 0.7145, | |
| "eval_samples_per_second": 139.954, | |
| "eval_steps_per_second": 18.194, | |
| "step": 133 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 0.9711024013935549, | |
| "eval_loss": 0.12795516848564148, | |
| "eval_macro_f1": 0.7437555649029086, | |
| "eval_macro_precision": 0.7355731767766348, | |
| "eval_macro_recall": 0.7848058983150393, | |
| "eval_runtime": 0.7219, | |
| "eval_samples_per_second": 138.514, | |
| "eval_steps_per_second": 18.007, | |
| "step": 152 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_accuracy": 0.9756750031106134, | |
| "eval_loss": 0.11990169435739517, | |
| "eval_macro_f1": 0.7767197416060247, | |
| "eval_macro_precision": 0.7831564923466648, | |
| "eval_macro_recall": 0.8015624788490757, | |
| "eval_runtime": 0.7239, | |
| "eval_samples_per_second": 138.14, | |
| "eval_steps_per_second": 17.958, | |
| "step": 171 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_accuracy": 0.9740885902700013, | |
| "eval_loss": 0.1274283081293106, | |
| "eval_macro_f1": 0.7875252140074755, | |
| "eval_macro_precision": 0.7618302095117122, | |
| "eval_macro_recall": 0.8457597210340326, | |
| "eval_runtime": 0.721, | |
| "eval_samples_per_second": 138.693, | |
| "eval_steps_per_second": 18.03, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "eval_accuracy": 0.975799427647132, | |
| "eval_loss": 0.12168442457914352, | |
| "eval_macro_f1": 0.787208882069088, | |
| "eval_macro_precision": 0.7591686050582892, | |
| "eval_macro_recall": 0.8584845414175304, | |
| "eval_runtime": 0.7385, | |
| "eval_samples_per_second": 135.405, | |
| "eval_steps_per_second": 17.603, | |
| "step": 209 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_accuracy": 0.9761415951225582, | |
| "eval_loss": 0.13082729279994965, | |
| "eval_macro_f1": 0.7949954841060296, | |
| "eval_macro_precision": 0.7671102748848504, | |
| "eval_macro_recall": 0.8572876125725459, | |
| "eval_runtime": 0.7165, | |
| "eval_samples_per_second": 139.577, | |
| "eval_steps_per_second": 18.145, | |
| "step": 228 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "eval_accuracy": 0.9758927460495209, | |
| "eval_loss": 0.13127866387367249, | |
| "eval_macro_f1": 0.7913277905680408, | |
| "eval_macro_precision": 0.7593907970089686, | |
| "eval_macro_recall": 0.8538236917477225, | |
| "eval_runtime": 0.7592, | |
| "eval_samples_per_second": 131.72, | |
| "eval_steps_per_second": 17.124, | |
| "step": 247 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "eval_accuracy": 0.9762038073908175, | |
| "eval_loss": 0.139426127076149, | |
| "eval_macro_f1": 0.794994965810495, | |
| "eval_macro_precision": 0.7684245960923229, | |
| "eval_macro_recall": 0.8567043677879977, | |
| "eval_runtime": 0.7554, | |
| "eval_samples_per_second": 132.38, | |
| "eval_steps_per_second": 17.209, | |
| "step": 266 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "eval_accuracy": 0.9767015055368918, | |
| "eval_loss": 0.13470035791397095, | |
| "eval_macro_f1": 0.8042100829526746, | |
| "eval_macro_precision": 0.7791800304712903, | |
| "eval_macro_recall": 0.8620026752410235, | |
| "eval_runtime": 0.7309, | |
| "eval_samples_per_second": 136.825, | |
| "eval_steps_per_second": 17.787, | |
| "step": 285 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "eval_accuracy": 0.9766392932686325, | |
| "eval_loss": 0.14018748700618744, | |
| "eval_macro_f1": 0.8049061480916583, | |
| "eval_macro_precision": 0.7872742624263276, | |
| "eval_macro_recall": 0.8567333662215458, | |
| "eval_runtime": 0.7278, | |
| "eval_samples_per_second": 137.407, | |
| "eval_steps_per_second": 17.863, | |
| "step": 304 | |
| }, | |
| { | |
| "epoch": 17.0, | |
| "eval_accuracy": 0.976421550329725, | |
| "eval_loss": 0.14483144879341125, | |
| "eval_macro_f1": 0.8134122644816508, | |
| "eval_macro_precision": 0.7925941282025739, | |
| "eval_macro_recall": 0.8662779355061373, | |
| "eval_runtime": 0.7265, | |
| "eval_samples_per_second": 137.647, | |
| "eval_steps_per_second": 17.894, | |
| "step": 323 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 608, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 32, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 3, | |
| "early_stopping_threshold": 0.001 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 0 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 0, | |
| "train_batch_size": 16, | |
| "trial_name": null, | |
| "trial_params": { | |
| "learning_rate": 9.821730986128684e-05, | |
| "per_device_train_batch_size": 16, | |
| "warmup_ratio": 0.10342300416492177, | |
| "weight_decay": 0.2819767106649835 | |
| } | |
| } | |