{ "best_metric": 0.6264824271202087, "best_model_checkpoint": "output/checkpoint-50", "epoch": 0.040108292389451516, "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": 0.0, "loss": 1.6453, "step": 1 }, { "epoch": 0.04, "learning_rate": 9.777777777777779e-06, "loss": 1.3216, "step": 50 }, { "epoch": 0.04, "eval_accuracy": 0.8057142857142857, "eval_loss": 0.6264824271202087, "eval_runtime": 28.8159, "eval_samples_per_second": 6.073, "eval_steps_per_second": 1.527, "step": 50 } ], "logging_steps": 50, "max_steps": 1246, "num_train_epochs": 1, "save_steps": 50, "total_flos": 1.843789564379136e+16, "trial_name": null, "trial_params": null }