{ "best_metric": null, "best_model_checkpoint": null, "epoch": 9.425959091337543e-05, "eval_steps": 500, "global_step": 1, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 9.425959091337543e-05, "grad_norm": 0.1435546875, "learning_rate": 3.3333333333333337e-06, "loss": 2.8026, "step": 1 } ], "logging_steps": 1, "max_steps": 10609, "num_input_tokens_seen": 0, "num_train_epochs": 1, "save_steps": 1, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": false }, "attributes": {} } }, "total_flos": 1162982788694016.0, "train_batch_size": 36, "trial_name": null, "trial_params": null }