{ "best_metric": null, "best_model_checkpoint": null, "epoch": 2.0, "eval_steps": 500, "global_step": 848, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 1.179245283018868, "grad_norm": 16.47541046142578, "learning_rate": 2.0518867924528304e-05, "loss": 1.7593, "step": 500 }, { "epoch": 2.0, "step": 848, "total_flos": 1.260270189771264e+16, "train_loss": 1.4897090983840655, "train_runtime": 4249.2251, "train_samples_per_second": 6.375, "train_steps_per_second": 0.2 } ], "logging_steps": 500, "max_steps": 848, "num_input_tokens_seen": 0, "num_train_epochs": 2, "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": 1.260270189771264e+16, "train_batch_size": 32, "trial_name": null, "trial_params": null }