{ "best_metric": 0.8458569716644827, "best_model_checkpoint": "test-klue/ynat-hps/run-0/checkpoint-286", "epoch": 2.0, "eval_steps": 500, "global_step": 572, "is_hyper_param_search": true, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 1.0, "eval_f1": 0.8458569716644827, "eval_loss": 0.4643433094024658, "eval_runtime": 11.9209, "eval_samples_per_second": 763.955, "eval_steps_per_second": 1.51, "step": 286 }, { "epoch": 1.75, "learning_rate": 2.182945662118961e-05, "loss": 0.5512, "step": 500 }, { "epoch": 2.0, "eval_f1": 0.8390224039302817, "eval_loss": 0.5141279101371765, "eval_runtime": 12.9152, "eval_samples_per_second": 705.14, "eval_steps_per_second": 1.394, "step": 572 } ], "logging_steps": 500, "max_steps": 1144, "num_input_tokens_seen": 0, "num_train_epochs": 4, "save_steps": 500, "total_flos": 85625936799600.0, "train_batch_size": 16, "trial_name": null, "trial_params": { "learning_rate": 3.877779250720639e-05, "num_train_epochs": 4, "per_device_train_batch_size": 16, "seed": 6 } }