{ "best_metric": null, "best_model_checkpoint": null, "epoch": 0.016817593790426907, "eval_steps": 10, "global_step": 13, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.00129366106080207, "eval_loss": 10.37984848022461, "eval_runtime": 2.2235, "eval_samples_per_second": 146.616, "eval_steps_per_second": 73.308, "step": 1 }, { "epoch": 0.00646830530401035, "grad_norm": 0.014315527863800526, "learning_rate": 5e-05, "loss": 10.379, "step": 5 }, { "epoch": 0.0129366106080207, "grad_norm": 0.012453961186110973, "learning_rate": 0.0001, "loss": 10.3812, "step": 10 }, { "epoch": 0.0129366106080207, "eval_loss": 10.379765510559082, "eval_runtime": 2.2571, "eval_samples_per_second": 144.431, "eval_steps_per_second": 72.215, "step": 10 } ], "logging_steps": 5, "max_steps": 50, "num_input_tokens_seen": 0, "num_train_epochs": 1, "save_steps": 13, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": false }, "attributes": {} } }, "total_flos": 336203612160.0, "train_batch_size": 2, "trial_name": null, "trial_params": null }