{ "best_metric": null, "best_model_checkpoint": null, "epoch": 0.0003070763379965631, "eval_steps": 10, "global_step": 13, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 2.3621256768966393e-05, "eval_loss": 2.5973010063171387, "eval_runtime": 1087.6377, "eval_samples_per_second": 16.39, "eval_steps_per_second": 8.195, "step": 1 }, { "epoch": 0.00011810628384483197, "grad_norm": 1.0713368654251099, "learning_rate": 5e-05, "loss": 2.5569, "step": 5 }, { "epoch": 0.00023621256768966393, "grad_norm": 1.5047534704208374, "learning_rate": 0.0001, "loss": 2.5144, "step": 10 }, { "epoch": 0.00023621256768966393, "eval_loss": 2.4695518016815186, "eval_runtime": 1090.9228, "eval_samples_per_second": 16.34, "eval_steps_per_second": 8.17, "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": 1988618012590080.0, "train_batch_size": 2, "trial_name": null, "trial_params": null }