{ "best_metric": 0.6762442588806152, "best_model_checkpoint": "output_pipe/H3K4me2/origin/checkpoint-200", "epoch": 4.0, "eval_steps": 200, "global_step": 384, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 1.0416666666666667, "grad_norm": 208060.03125, "learning_rate": 2.5508982035928146e-05, "loss": 0.6476, "step": 100 }, { "epoch": 2.0833333333333335, "grad_norm": 255772.234375, "learning_rate": 1.6526946107784433e-05, "loss": 0.5916, "step": 200 }, { "epoch": 2.0833333333333335, "eval_accuracy": 0.6370153144346693, "eval_f1": 0.6305820068773437, "eval_loss": 0.6762442588806152, "eval_matthews_correlation": 0.26327838046391366, "eval_precision": 0.6302158504464763, "eval_recall": 0.6330780880016458, "eval_runtime": 2.3659, "eval_samples_per_second": 1297.155, "eval_steps_per_second": 5.072, "step": 200 }, { "epoch": 3.125, "grad_norm": 300345.1875, "learning_rate": 7.544910179640718e-06, "loss": 0.4265, "step": 300 }, { "epoch": 4.0, "step": 384, "total_flos": 2.428755299759628e+16, "train_loss": 0.47508321205774945, "train_runtime": 232.2261, "train_samples_per_second": 422.778, "train_steps_per_second": 1.654 } ], "logging_steps": 100, "max_steps": 384, "num_input_tokens_seen": 0, "num_train_epochs": 4, "save_steps": 200, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": true }, "attributes": {} } }, "total_flos": 2.428755299759628e+16, "train_batch_size": 64, "trial_name": null, "trial_params": null }