{ "best_metric": null, "best_model_checkpoint": null, "epoch": 0.9985185185185185, "eval_steps": 500, "global_step": 337, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.5925925925925926, "grad_norm": 0.5267816185951233, "learning_rate": 7.1055176048263085e-06, "loss": 0.4109, "step": 200 } ], "logging_steps": 200, "max_steps": 337, "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": 4.461058902036173e+17, "train_batch_size": 1, "trial_name": null, "trial_params": null }