{ "best_global_step": null, "best_metric": null, "best_model_checkpoint": null, "epoch": 1.0, "eval_steps": 100, "global_step": 19, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.5263157894736842, "grad_norm": 0.9129361510276794, "learning_rate": 6.368314950360415e-05, "loss": 0.6959, "step": 10 } ], "logging_steps": 10, "max_steps": 19, "num_input_tokens_seen": 0, "num_train_epochs": 1, "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": 1.3314290917441536e+16, "train_batch_size": 4, "trial_name": null, "trial_params": null }