| { | |
| "best_metric": 0.8025602601482168, | |
| "best_model_checkpoint": "tmp_ner_fantastic-bale-17_39/run-51/checkpoint-351", | |
| "epoch": 13.0, | |
| "eval_steps": 500, | |
| "global_step": 351, | |
| "is_hyper_param_search": true, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.8966935526948346, | |
| "eval_loss": 0.3334161937236786, | |
| "eval_macro_f1": 0.3481690804569024, | |
| "eval_macro_precision": 0.381260717978419, | |
| "eval_macro_recall": 0.35979719914273406, | |
| "eval_runtime": 0.6891, | |
| "eval_samples_per_second": 206.072, | |
| "eval_steps_per_second": 26.122, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.930559264996528, | |
| "eval_loss": 0.21216891705989838, | |
| "eval_macro_f1": 0.6053382787959644, | |
| "eval_macro_precision": 0.6107512517099946, | |
| "eval_macro_recall": 0.6460256647872952, | |
| "eval_runtime": 0.6859, | |
| "eval_samples_per_second": 207.037, | |
| "eval_steps_per_second": 26.244, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.9471716254473586, | |
| "eval_loss": 0.17325381934642792, | |
| "eval_macro_f1": 0.654390209074469, | |
| "eval_macro_precision": 0.8778760893535847, | |
| "eval_macro_recall": 0.6000593968379591, | |
| "eval_runtime": 0.6857, | |
| "eval_samples_per_second": 207.088, | |
| "eval_steps_per_second": 26.251, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.9528337161476417, | |
| "eval_loss": 0.15815088152885437, | |
| "eval_macro_f1": 0.780354726682967, | |
| "eval_macro_precision": 0.7951782992828399, | |
| "eval_macro_recall": 0.7756083475295977, | |
| "eval_runtime": 0.6835, | |
| "eval_samples_per_second": 207.761, | |
| "eval_steps_per_second": 26.336, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_accuracy": 0.9519256449975962, | |
| "eval_loss": 0.17041093111038208, | |
| "eval_macro_f1": 0.7750872516025015, | |
| "eval_macro_precision": 0.819684829234941, | |
| "eval_macro_recall": 0.7465932066328682, | |
| "eval_runtime": 0.6848, | |
| "eval_samples_per_second": 207.368, | |
| "eval_steps_per_second": 26.286, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_accuracy": 0.9541156989477058, | |
| "eval_loss": 0.18207110464572906, | |
| "eval_macro_f1": 0.7757922057464975, | |
| "eval_macro_precision": 0.8139015262713462, | |
| "eval_macro_recall": 0.7479356706189721, | |
| "eval_runtime": 0.6847, | |
| "eval_samples_per_second": 207.398, | |
| "eval_steps_per_second": 26.29, | |
| "step": 162 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_accuracy": 0.9547032743977352, | |
| "eval_loss": 0.1869019716978073, | |
| "eval_macro_f1": 0.7909756567968369, | |
| "eval_macro_precision": 0.818653317630622, | |
| "eval_macro_recall": 0.7694133266548752, | |
| "eval_runtime": 0.6858, | |
| "eval_samples_per_second": 207.047, | |
| "eval_steps_per_second": 26.245, | |
| "step": 189 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 0.9542225308477111, | |
| "eval_loss": 0.19935451447963715, | |
| "eval_macro_f1": 0.7742556094296894, | |
| "eval_macro_precision": 0.829305822509576, | |
| "eval_macro_recall": 0.7366273963466895, | |
| "eval_runtime": 0.6857, | |
| "eval_samples_per_second": 207.102, | |
| "eval_steps_per_second": 26.252, | |
| "step": 216 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_accuracy": 0.9549169381977458, | |
| "eval_loss": 0.19827748835086823, | |
| "eval_macro_f1": 0.7890513633726142, | |
| "eval_macro_precision": 0.8190924393392907, | |
| "eval_macro_recall": 0.7654512068808164, | |
| "eval_runtime": 0.6844, | |
| "eval_samples_per_second": 207.478, | |
| "eval_steps_per_second": 26.3, | |
| "step": 243 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_accuracy": 0.9539554510976977, | |
| "eval_loss": 0.21724671125411987, | |
| "eval_macro_f1": 0.7951226311261627, | |
| "eval_macro_precision": 0.8076887756893915, | |
| "eval_macro_recall": 0.7863682941618138, | |
| "eval_runtime": 0.6853, | |
| "eval_samples_per_second": 207.214, | |
| "eval_steps_per_second": 26.267, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "eval_accuracy": 0.9528871320976443, | |
| "eval_loss": 0.24698173999786377, | |
| "eval_macro_f1": 0.7700880502690434, | |
| "eval_macro_precision": 0.837595387901314, | |
| "eval_macro_recall": 0.7281291396407018, | |
| "eval_runtime": 0.6867, | |
| "eval_samples_per_second": 206.792, | |
| "eval_steps_per_second": 26.213, | |
| "step": 297 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_accuracy": 0.9551306019977566, | |
| "eval_loss": 0.23617151379585266, | |
| "eval_macro_f1": 0.7840279783447406, | |
| "eval_macro_precision": 0.8305447049199165, | |
| "eval_macro_recall": 0.7522814462795042, | |
| "eval_runtime": 0.6856, | |
| "eval_samples_per_second": 207.122, | |
| "eval_steps_per_second": 26.255, | |
| "step": 324 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "eval_accuracy": 0.9563591688478179, | |
| "eval_loss": 0.22979934513568878, | |
| "eval_macro_f1": 0.8025602601482168, | |
| "eval_macro_precision": 0.8255341113341885, | |
| "eval_macro_recall": 0.784416544697495, | |
| "eval_runtime": 0.6867, | |
| "eval_samples_per_second": 206.792, | |
| "eval_steps_per_second": 26.213, | |
| "step": 351 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 864, | |
| "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": 4.312024782506724e-05, | |
| "per_device_train_batch_size": 16, | |
| "warmup_ratio": 0.00046632724074153857, | |
| "weight_decay": 0.004637010897989902 | |
| } | |
| } | |