{ "best_metric": 2.6424405574798584, "best_model_checkpoint": "./outputs/checkpoint-100", "epoch": 0.07285974499089254, "eval_steps": 100, "global_step": 100, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.07, "learning_rate": 0.0002, "loss": 2.7406, "step": 100 }, { "epoch": 0.07, "eval_loss": 2.6424405574798584, "eval_runtime": 206.8728, "eval_samples_per_second": 30.328, "eval_steps_per_second": 3.795, "step": 100 } ], "logging_steps": 100, "max_steps": 4116, "num_train_epochs": 3, "save_steps": 100, "total_flos": 2917794121482240.0, "trial_name": null, "trial_params": null }