{ "best_global_step": 1338, "best_metric": 0.8755686379448755, "best_model_checkpoint": "outputs/phobert-v1-spam-binary/checkpoint-1338", "epoch": 3.0, "eval_steps": 500, "global_step": 1338, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 1.0, "grad_norm": 1.1736655235290527, "learning_rate": 4.998771926094749e-05, "loss": 0.2942, "step": 446 }, { "epoch": 1.0, "eval_accuracy": 0.8954001260239446, "eval_f1": 0.8553584605653847, "eval_loss": 0.2888332009315491, "eval_precision": 0.9008187464709203, "eval_recall": 0.8281652630097888, "eval_runtime": 8.0411, "eval_samples_per_second": 197.361, "eval_steps_per_second": 6.218, "step": 446 }, { "epoch": 2.0, "grad_norm": 6.6384172439575195, "learning_rate": 4.995077872180951e-05, "loss": 0.2056, "step": 892 }, { "epoch": 2.0, "eval_accuracy": 0.9004410838059231, "eval_f1": 0.8694738266772165, "eval_loss": 0.26918283104896545, "eval_precision": 0.8846893183707398, "eval_recall": 0.8571948302546682, "eval_runtime": 6.1752, "eval_samples_per_second": 256.996, "eval_steps_per_second": 8.097, "step": 892 }, { "epoch": 3.0, "grad_norm": 6.173985958099365, "learning_rate": 4.988921477641713e-05, "loss": 0.1618, "step": 1338 }, { "epoch": 3.0, "eval_accuracy": 0.9023314429741651, "eval_f1": 0.8755686379448755, "eval_loss": 0.2585906982421875, "eval_precision": 0.8781387124505486, "eval_recall": 0.8731040582098852, "eval_runtime": 7.8981, "eval_samples_per_second": 200.934, "eval_steps_per_second": 6.331, "step": 1338 } ], "logging_steps": 446, "max_steps": 44600, "num_input_tokens_seen": 0, "num_train_epochs": 100, "save_steps": 500, "stateful_callbacks": { "EarlyStoppingCallback": { "args": { "early_stopping_patience": 5, "early_stopping_threshold": 0.0 }, "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": 0.0, "train_batch_size": 32, "trial_name": null, "trial_params": null }