{ "best_global_step": 939, "best_metric": 1.0475715398788452, "best_model_checkpoint": "classifier-clinc-MBbase-distilled/run-3/checkpoint-939", "epoch": 3.0, "eval_steps": 500, "global_step": 939, "is_hyper_param_search": true, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 1.0, "eval_accuracy": 0.8803225806451613, "eval_loss": 2.851562261581421, "eval_runtime": 8.7066, "eval_samples_per_second": 356.05, "eval_steps_per_second": 11.141, "step": 313 }, { "epoch": 1.5974440894568689, "grad_norm": 22.713924407958984, "learning_rate": 1.468583599574015e-05, "loss": 7.2917, "step": 500 }, { "epoch": 2.0, "eval_accuracy": 0.9370967741935484, "eval_loss": 1.3482674360275269, "eval_runtime": 8.8149, "eval_samples_per_second": 351.677, "eval_steps_per_second": 11.004, "step": 626 }, { "epoch": 3.0, "eval_accuracy": 0.9458064516129032, "eval_loss": 1.0475715398788452, "eval_runtime": 9.4956, "eval_samples_per_second": 326.469, "eval_steps_per_second": 10.215, "step": 939 } ], "logging_steps": 500, "max_steps": 1878, "num_input_tokens_seen": 0, "num_train_epochs": 6, "save_steps": 500, "stateful_callbacks": { "EarlyStoppingCallback": { "args": { "early_stopping_patience": 2, "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": 222488892388608.0, "train_batch_size": 32, "trial_name": null, "trial_params": { "alpha": 0.3917157288742445, "num_train_epochs": 6, "temperature": 3.2114012903927867 } }