| { | |
| "best_metric": 0.8353803157806396, | |
| "best_model_checkpoint": "sbert-ru-huawei-gradient-accumulation/checkpoint-304", | |
| "epoch": 0.9991783073130649, | |
| "eval_steps": 500, | |
| "global_step": 304, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.08216926869350863, | |
| "grad_norm": 20.81386947631836, | |
| "learning_rate": 1.25e-05, | |
| "loss": 0.7474, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.16433853738701726, | |
| "grad_norm": 24.849594116210938, | |
| "learning_rate": 2.554347826086957e-05, | |
| "loss": 0.7068, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.2465078060805259, | |
| "grad_norm": 14.201815605163574, | |
| "learning_rate": 3.91304347826087e-05, | |
| "loss": 0.6739, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.3286770747740345, | |
| "grad_norm": 19.431638717651367, | |
| "learning_rate": 4.9995413210794864e-05, | |
| "loss": 0.6802, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.4108463434675431, | |
| "grad_norm": 17.281723022460938, | |
| "learning_rate": 4.9835052243991874e-05, | |
| "loss": 0.6518, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.4930156121610518, | |
| "grad_norm": 21.763912200927734, | |
| "learning_rate": 4.944703213375648e-05, | |
| "loss": 0.6609, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.5751848808545604, | |
| "grad_norm": 35.13481903076172, | |
| "learning_rate": 4.8834909801373264e-05, | |
| "loss": 0.6544, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.657354149548069, | |
| "grad_norm": 24.737939834594727, | |
| "learning_rate": 4.800429647908354e-05, | |
| "loss": 0.6358, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.7395234182415776, | |
| "grad_norm": 22.52487564086914, | |
| "learning_rate": 4.6962806272773564e-05, | |
| "loss": 0.6558, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 0.8216926869350862, | |
| "grad_norm": 18.9419002532959, | |
| "learning_rate": 4.5719986364624866e-05, | |
| "loss": 0.628, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.903861955628595, | |
| "grad_norm": 21.046478271484375, | |
| "learning_rate": 4.428722949554857e-05, | |
| "loss": 0.6414, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 0.9860312243221035, | |
| "grad_norm": 23.134496688842773, | |
| "learning_rate": 4.267766952966369e-05, | |
| "loss": 0.6489, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.9991783073130649, | |
| "eval_accuracy": 0.6643378197883489, | |
| "eval_f1_macro": 0.48932255599208974, | |
| "eval_f1_micro": 0.6643378197883489, | |
| "eval_f1_weighted": 0.6590895238835833, | |
| "eval_loss": 0.8353803157806396, | |
| "eval_precision_macro": 0.5100466324017191, | |
| "eval_precision_micro": 0.6643378197883489, | |
| "eval_precision_weighted": 0.6607527574495663, | |
| "eval_recall_macro": 0.48717407338779406, | |
| "eval_recall_micro": 0.6643378197883489, | |
| "eval_recall_weighted": 0.6643378197883489, | |
| "eval_runtime": 61.8774, | |
| "eval_samples_per_second": 157.295, | |
| "eval_steps_per_second": 4.929, | |
| "step": 304 | |
| } | |
| ], | |
| "logging_steps": 25, | |
| "max_steps": 912, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 5, | |
| "early_stopping_threshold": 0.01 | |
| }, | |
| "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": 1.8146751147933696e+16, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |