{ "best_metric": 0.9442508710801394, "best_model_checkpoint": "brain-tumor-classification/checkpoint-200", "epoch": 4.938271604938271, "eval_steps": 500, "global_step": 200, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.9876543209876543, "grad_norm": 26.882118225097656, "learning_rate": 4.4444444444444447e-05, "loss": 0.87, "step": 40 }, { "epoch": 0.9876543209876543, "eval_accuracy": 0.8710801393728222, "eval_loss": 0.3874738812446594, "eval_runtime": 4.2257, "eval_samples_per_second": 67.917, "eval_steps_per_second": 4.26, "step": 40 }, { "epoch": 2.0, "grad_norm": 6.630888938903809, "learning_rate": 3.3055555555555553e-05, "loss": 0.426, "step": 81 }, { "epoch": 2.0, "eval_accuracy": 0.9024390243902439, "eval_loss": 0.22352387011051178, "eval_runtime": 2.3991, "eval_samples_per_second": 119.628, "eval_steps_per_second": 7.503, "step": 81 }, { "epoch": 2.9876543209876543, "grad_norm": 9.56891918182373, "learning_rate": 2.1944444444444445e-05, "loss": 0.292, "step": 121 }, { "epoch": 2.9876543209876543, "eval_accuracy": 0.926829268292683, "eval_loss": 0.2056380957365036, "eval_runtime": 2.3874, "eval_samples_per_second": 120.214, "eval_steps_per_second": 7.54, "step": 121 }, { "epoch": 4.0, "grad_norm": 7.695461273193359, "learning_rate": 1.0555555555555555e-05, "loss": 0.217, "step": 162 }, { "epoch": 4.0, "eval_accuracy": 0.9337979094076655, "eval_loss": 0.1578059196472168, "eval_runtime": 2.6136, "eval_samples_per_second": 109.811, "eval_steps_per_second": 6.887, "step": 162 }, { "epoch": 4.938271604938271, "grad_norm": 7.951013088226318, "learning_rate": 0.0, "loss": 0.1797, "step": 200 }, { "epoch": 4.938271604938271, "eval_accuracy": 0.9442508710801394, "eval_loss": 0.12732850015163422, "eval_runtime": 2.9064, "eval_samples_per_second": 98.748, "eval_steps_per_second": 6.193, "step": 200 }, { "epoch": 4.938271604938271, "step": 200, "total_flos": 3.1727957353537536e+17, "train_loss": 0.39835033178329465, "train_runtime": 251.5945, "train_samples_per_second": 51.333, "train_steps_per_second": 0.795 } ], "logging_steps": 10, "max_steps": 200, "num_input_tokens_seen": 0, "num_train_epochs": 5, "save_steps": 500, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": true }, "attributes": {} } }, "total_flos": 3.1727957353537536e+17, "train_batch_size": 16, "trial_name": null, "trial_params": null }