{ "best_metric": 0.32454729080200195, "best_model_checkpoint": "clasificacion-bananas/checkpoint-10", "epoch": 5.0, "eval_steps": 500, "global_step": 10, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.5, "grad_norm": 17.483074188232422, "learning_rate": 2.5e-05, "loss": 0.6514, "step": 1 }, { "epoch": 1.0, "grad_norm": 17.71515464782715, "learning_rate": 5e-05, "loss": 0.699, "step": 2 }, { "epoch": 1.0, "eval_accuracy": 0.5, "eval_auc": 0.0, "eval_f1": 0.0, "eval_loss": 0.6983617544174194, "eval_precision": 0.0, "eval_recall": 0.0, "eval_runtime": 0.0756, "eval_samples_per_second": 26.449, "eval_steps_per_second": 13.225, "step": 2 }, { "epoch": 1.5, "grad_norm": 18.718172073364258, "learning_rate": 4.722222222222222e-05, "loss": 0.7047, "step": 3 }, { "epoch": 2.0, "grad_norm": 15.484118461608887, "learning_rate": 4.4444444444444447e-05, "loss": 0.6165, "step": 4 }, { "epoch": 2.0, "eval_accuracy": 0.5, "eval_auc": 1.0, "eval_f1": 0.6666666666666666, "eval_loss": 0.6035097241401672, "eval_precision": 0.5, "eval_recall": 1.0, "eval_runtime": 0.0625, "eval_samples_per_second": 31.982, "eval_steps_per_second": 15.991, "step": 4 }, { "epoch": 2.5, "grad_norm": 16.05043601989746, "learning_rate": 4.166666666666667e-05, "loss": 0.5776, "step": 5 }, { "epoch": 3.0, "grad_norm": 16.094289779663086, "learning_rate": 3.888888888888889e-05, "loss": 0.6129, "step": 6 }, { "epoch": 3.0, "eval_accuracy": 0.0, "eval_auc": 0.0, "eval_f1": 0.0, "eval_loss": 0.7506046891212463, "eval_precision": 0.0, "eval_recall": 0.0, "eval_runtime": 0.0622, "eval_samples_per_second": 32.154, "eval_steps_per_second": 16.077, "step": 6 }, { "epoch": 3.5, "grad_norm": 14.702045440673828, "learning_rate": 3.611111111111111e-05, "loss": 0.5869, "step": 7 }, { "epoch": 4.0, "grad_norm": 15.221928596496582, "learning_rate": 3.3333333333333335e-05, "loss": 0.4532, "step": 8 }, { "epoch": 4.0, "eval_accuracy": 0.0, "eval_auc": 0.0, "eval_f1": 0.0, "eval_loss": 0.7223799824714661, "eval_precision": 0.0, "eval_recall": 0.0, "eval_runtime": 0.0638, "eval_samples_per_second": 31.339, "eval_steps_per_second": 15.669, "step": 8 }, { "epoch": 4.5, "grad_norm": 16.220394134521484, "learning_rate": 3.055555555555556e-05, "loss": 0.5442, "step": 9 }, { "epoch": 5.0, "grad_norm": 15.754592895507812, "learning_rate": 2.777777777777778e-05, "loss": 0.4644, "step": 10 }, { "epoch": 5.0, "eval_accuracy": 1.0, "eval_auc": 1.0, "eval_f1": 1.0, "eval_loss": 0.32454729080200195, "eval_precision": 1.0, "eval_recall": 1.0, "eval_runtime": 0.063, "eval_samples_per_second": 31.741, "eval_steps_per_second": 15.871, "step": 10 } ], "logging_steps": 1, "max_steps": 20, "num_input_tokens_seen": 0, "num_train_epochs": 10, "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": 105056336609280.0, "train_batch_size": 4, "trial_name": null, "trial_params": null }