{ "best_global_step": null, "best_metric": null, "best_model_checkpoint": null, "epoch": 2.0, "eval_steps": 500, "global_step": 99632, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 1.0, "grad_norm": 0.006972933188080788, "learning_rate": 1.1111433287237365e-05, "loss": 0.4105, "step": 49816 }, { "epoch": 2.0, "grad_norm": 4.4481204497515137e-08, "learning_rate": 2.230450104831155e-10, "loss": 0.1797, "step": 99632 } ], "logging_steps": 49816, "max_steps": 99632, "num_input_tokens_seen": 0, "num_train_epochs": 2, "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": 0.0, "train_batch_size": 1, "trial_name": null, "trial_params": null }