{ "best_metric": 0.6430063247680664, "best_model_checkpoint": "output/checkpoint-50", "epoch": 0.04008417677121956, "eval_steps": 50, "global_step": 50, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.0, "learning_rate": 4.444444444444445e-07, "loss": 0.5542, "step": 1 }, { "epoch": 0.04, "learning_rate": 2e-05, "loss": 0.554, "step": 50 }, { "epoch": 0.04, "eval_accuracy": 0.6626865671641791, "eval_loss": 0.6430063247680664, "eval_runtime": 61.7692, "eval_samples_per_second": 5.423, "eval_steps_per_second": 1.36, "step": 50 } ], "logging_steps": 50, "max_steps": 1247, "num_train_epochs": 1, "save_steps": 50, "total_flos": 1.859532185247744e+16, "trial_name": null, "trial_params": null }