{ "best_metric": null, "best_model_checkpoint": null, "epoch": 1.9626666666666668, "eval_steps": 500, "global_step": 46, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 1.0666666666666667, "grad_norm": 1.848462462425232, "learning_rate": 5e-05, "loss": 4.7674, "step": 25 } ], "logging_steps": 25, "max_steps": 46, "num_input_tokens_seen": 0, "num_train_epochs": 2, "save_steps": 250, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": true }, "attributes": {} } }, "total_flos": 1.9977835647521664e+16, "train_batch_size": 4, "trial_name": null, "trial_params": null }