{ "best_metric": null, "best_model_checkpoint": null, "epoch": 0.989010989010989, "eval_steps": 500, "global_step": 45, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.6593406593406593, "grad_norm": 0.4532944858074188, "learning_rate": 9.677419354838711e-05, "loss": 2.5406, "step": 30 } ], "logging_steps": 30, "max_steps": 45, "num_input_tokens_seen": 0, "num_train_epochs": 1, "save_steps": 1000, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": true }, "attributes": {} } }, "total_flos": 4515344316628992.0, "train_batch_size": 8, "trial_name": null, "trial_params": null }