{ "best_global_step": null, "best_metric": null, "best_model_checkpoint": null, "epoch": 3.0, "eval_steps": 500, "global_step": 123, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.024615384615384615, "grad_norm": 4.875, "learning_rate": 5e-05, "loss": 3.3438, "step": 1 }, { "epoch": 2.443076923076923, "grad_norm": 2.734375, "learning_rate": 9.756097560975611e-06, "loss": 1.404, "step": 100 } ], "logging_steps": 100, "max_steps": 123, "num_input_tokens_seen": 0, "num_train_epochs": 3, "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": 509519462400000.0, "train_batch_size": 1, "trial_name": null, "trial_params": null }