{ "best_metric": 0.812045693397522, "best_model_checkpoint": "model/checkpoint-7764", "epoch": 2.0, "eval_steps": 100, "global_step": 7764, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 1.0, "grad_norm": 0.674655020236969, "learning_rate": 8.333333333333334e-06, "loss": 0.9449, "step": 3882 }, { "epoch": 1.0, "eval_accuracy": 0.7022153529108707, "eval_f1": 0.7081847210276373, "eval_loss": 0.822690486907959, "eval_precision": 0.7291759000665414, "eval_recall": 0.7022153529108707, "eval_runtime": 81.8846, "eval_samples_per_second": 94.816, "eval_steps_per_second": 5.935, "step": 3882 }, { "epoch": 2.0, "grad_norm": 42.98274612426758, "learning_rate": 6.666666666666667e-06, "loss": 0.7484, "step": 7764 }, { "epoch": 2.0, "eval_accuracy": 0.7163833075734157, "eval_f1": 0.7173737978381436, "eval_loss": 0.812045693397522, "eval_precision": 0.719085449369722, "eval_recall": 0.7163833075734157, "eval_runtime": 81.913, "eval_samples_per_second": 94.783, "eval_steps_per_second": 5.933, "step": 7764 } ], "logging_steps": 100, "max_steps": 23292, "num_input_tokens_seen": 0, "num_train_epochs": 6, "save_steps": 100, "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": 5.787710230624358e+16, "train_batch_size": 16, "trial_name": null, "trial_params": null }