{ "best_metric": null, "best_model_checkpoint": null, "epoch": 0.10390689941812137, "eval_steps": 500, "global_step": 500, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.10390689941812137, "grad_norm": 3.488266944885254, "learning_rate": 1.9311443613189252e-05, "loss": 0.8436, "step": 500 } ], "logging_steps": 500, "max_steps": 14436, "num_input_tokens_seen": 0, "num_train_epochs": 3, "save_steps": 500, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": false }, "attributes": {} } }, "total_flos": 608957890560000.0, "train_batch_size": 2, "trial_name": null, "trial_params": null }