{ "best_metric": 0.6690925359725952, "best_model_checkpoint": "autotrain-pbcst-o4o6d/checkpoint-3", "epoch": 3.0, "eval_steps": 500, "global_step": 3, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 1.0, "grad_norm": 9.92590045928955, "learning_rate": 5e-05, "loss": 0.8149, "step": 1 }, { "epoch": 1.0, "eval_accuracy": 0.5, "eval_auc": 1.0, "eval_f1": 0.6666666666666666, "eval_loss": 0.701653242111206, "eval_precision": 0.5, "eval_recall": 1.0, "eval_runtime": 0.3426, "eval_samples_per_second": 5.838, "eval_steps_per_second": 2.919, "step": 1 }, { "epoch": 2.0, "grad_norm": 11.032135963439941, "learning_rate": 2.5e-05, "loss": 0.9129, "step": 2 }, { "epoch": 2.0, "eval_accuracy": 1.0, "eval_auc": 0.0, "eval_f1": 1.0, "eval_loss": 0.6734181046485901, "eval_precision": 1.0, "eval_recall": 1.0, "eval_runtime": 0.3745, "eval_samples_per_second": 5.341, "eval_steps_per_second": 2.67, "step": 2 }, { "epoch": 3.0, "grad_norm": 7.524375915527344, "learning_rate": 0.0, "loss": 0.5785, "step": 3 }, { "epoch": 3.0, "eval_accuracy": 0.5, "eval_auc": 0.0, "eval_f1": 0.0, "eval_loss": 0.6690925359725952, "eval_precision": 0.0, "eval_recall": 0.0, "eval_runtime": 0.3472, "eval_samples_per_second": 5.761, "eval_steps_per_second": 2.88, "step": 3 } ], "logging_steps": 1, "max_steps": 3, "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": true }, "attributes": {} } }, "total_flos": 789333166080.0, "train_batch_size": 8, "trial_name": null, "trial_params": null }