{ "best_metric": null, "best_model_checkpoint": null, "epoch": 5.0, "eval_steps": 500, "global_step": 8385, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 5.0, "grad_norm": 11.265508651733398, "learning_rate": 4.918234353866962e-09, "loss": 1.2181, "step": 8385 } ], "logging_steps": -8385, "max_steps": 8385, "num_input_tokens_seen": 0, "num_train_epochs": 5, "save_steps": 500, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": true }, "attributes": {} } }, "total_flos": 1.8667811211575296e+16, "train_batch_size": 4, "trial_name": null, "trial_params": null }