{ "best_metric": 0.6392687559127808, "best_model_checkpoint": "output_pipe/H3K4me1/origin/checkpoint-200", "epoch": 4.0, "eval_steps": 200, "global_step": 396, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 1.0101010101010102, "grad_norm": 353510.4375, "learning_rate": 2.5664739884393065e-05, "loss": 0.6454, "step": 100 }, { "epoch": 2.0202020202020203, "grad_norm": 115586.625, "learning_rate": 1.6994219653179194e-05, "loss": 0.5503, "step": 200 }, { "epoch": 2.0202020202020203, "eval_accuracy": 0.6587752525252525, "eval_f1": 0.6579564589157687, "eval_loss": 0.6392687559127808, "eval_matthews_correlation": 0.33407782782047885, "eval_precision": 0.6689849910588868, "eval_recall": 0.6651152483156877, "eval_runtime": 2.4782, "eval_samples_per_second": 1278.369, "eval_steps_per_second": 5.246, "step": 200 }, { "epoch": 3.0303030303030303, "grad_norm": 317173.96875, "learning_rate": 8.323699421965318e-06, "loss": 0.3415, "step": 300 }, { "epoch": 4.0, "step": 396, "total_flos": 2.5075203932046744e+16, "train_loss": 0.4151653569154065, "train_runtime": 239.6045, "train_samples_per_second": 423.047, "train_steps_per_second": 1.653 } ], "logging_steps": 100, "max_steps": 396, "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": 2.5075203932046744e+16, "train_batch_size": 64, "trial_name": null, "trial_params": null }