{ "best_metric": 0.5333191156387329, "best_model_checkpoint": "output_pipe/H3K79me3/origin/checkpoint-200", "epoch": 4.0, "eval_steps": 200, "global_step": 364, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 1.098901098901099, "grad_norm": 331204.25, "learning_rate": 2.5222929936305735e-05, "loss": 0.5877, "step": 100 }, { "epoch": 2.197802197802198, "grad_norm": 312119.6875, "learning_rate": 1.5668789808917198e-05, "loss": 0.4134, "step": 200 }, { "epoch": 2.197802197802198, "eval_accuracy": 0.794382801664355, "eval_f1": 0.793055137918913, "eval_loss": 0.5333191156387329, "eval_matthews_correlation": 0.5861258963393166, "eval_precision": 0.7929155319942546, "eval_recall": 0.7932104385354901, "eval_runtime": 2.2508, "eval_samples_per_second": 1281.349, "eval_steps_per_second": 5.332, "step": 200 }, { "epoch": 3.2967032967032965, "grad_norm": 240103.6875, "learning_rate": 6.114649681528663e-06, "loss": 0.2408, "step": 300 }, { "epoch": 4.0, "step": 364, "total_flos": 2.2827034430700696e+16, "train_loss": 0.3618728865633954, "train_runtime": 219.5271, "train_samples_per_second": 420.34, "train_steps_per_second": 1.658 } ], "logging_steps": 100, "max_steps": 364, "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": 2.2827034430700696e+16, "train_batch_size": 64, "trial_name": null, "trial_params": null }