{ "best_metric": 0.8685015290519877, "best_model_checkpoint": "brain-tumor-classification/checkpoint-69", "epoch": 3.0, "eval_steps": 500, "global_step": 69, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.43478260869565216, "grad_norm": 7.908116340637207, "learning_rate": 4.7580645161290326e-05, "loss": 0.623, "step": 10 }, { "epoch": 0.8695652173913043, "grad_norm": 10.378320693969727, "learning_rate": 3.951612903225806e-05, "loss": 0.5239, "step": 20 }, { "epoch": 1.0, "eval_accuracy": 0.7889908256880734, "eval_loss": 0.5283120274543762, "eval_runtime": 3.5122, "eval_samples_per_second": 93.103, "eval_steps_per_second": 3.132, "step": 23 }, { "epoch": 1.3043478260869565, "grad_norm": 5.665172100067139, "learning_rate": 3.1451612903225806e-05, "loss": 0.4202, "step": 30 }, { "epoch": 1.7391304347826086, "grad_norm": 9.73236083984375, "learning_rate": 2.338709677419355e-05, "loss": 0.3716, "step": 40 }, { "epoch": 2.0, "eval_accuracy": 0.8409785932721713, "eval_loss": 0.3933815658092499, "eval_runtime": 2.873, "eval_samples_per_second": 113.816, "eval_steps_per_second": 3.829, "step": 46 }, { "epoch": 2.1739130434782608, "grad_norm": 8.678784370422363, "learning_rate": 1.5322580645161292e-05, "loss": 0.3549, "step": 50 }, { "epoch": 2.608695652173913, "grad_norm": 5.479146957397461, "learning_rate": 7.258064516129033e-06, "loss": 0.2964, "step": 60 }, { "epoch": 3.0, "eval_accuracy": 0.8685015290519877, "eval_loss": 0.34957513213157654, "eval_runtime": 3.2055, "eval_samples_per_second": 102.012, "eval_steps_per_second": 3.432, "step": 69 }, { "epoch": 3.0, "step": 69, "total_flos": 2.2838958959910912e+17, "train_loss": 0.41367715683536255, "train_runtime": 173.7772, "train_samples_per_second": 50.703, "train_steps_per_second": 0.397 } ], "logging_steps": 10, "max_steps": 69, "num_input_tokens_seen": 0, "num_train_epochs": 3, "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": 2.2838958959910912e+17, "train_batch_size": 32, "trial_name": null, "trial_params": null }