{ "best_metric": null, "best_model_checkpoint": null, "epoch": 10.0, "eval_steps": 500, "global_step": 130, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 10.0, "step": 130, "total_flos": 239066361640260.0, "train_loss": 1.2736186100886417, "train_runtime": 133.9465, "train_samples_per_second": 30.684, "train_steps_per_second": 0.971 } ], "logging_steps": 500, "max_steps": 130, "num_input_tokens_seen": 0, "num_train_epochs": 10, "save_steps": 500, "total_flos": 239066361640260.0, "train_batch_size": 32, "trial_name": null, "trial_params": null }