{ "best_metric": null, "best_model_checkpoint": null, "epoch": 2.8235294117647056, "eval_steps": 500, "global_step": 12, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 2.3529411764705883, "grad_norm": 0.4619706869125366, "learning_rate": 1.6666666666666667e-05, "loss": 3.7791, "step": 10 } ], "logging_steps": 10, "max_steps": 12, "num_input_tokens_seen": 0, "num_train_epochs": 3, "save_steps": 100, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": true }, "attributes": {} } }, "total_flos": 205756924428288.0, "train_batch_size": 4, "trial_name": null, "trial_params": null }