{ "best_metric": null, "best_model_checkpoint": null, "epoch": 0.9696969696969697, "eval_steps": 500, "global_step": 8, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.12121212121212122, "grad_norm": 3.3049814701080322, "learning_rate": 0.0002, "loss": 4.8222, "step": 1 }, { "epoch": 0.24242424242424243, "grad_norm": 3.172274112701416, "learning_rate": 0.0001900968867902419, "loss": 4.9618, "step": 2 }, { "epoch": 0.36363636363636365, "grad_norm": 1.6254035234451294, "learning_rate": 0.00016234898018587337, "loss": 3.2341, "step": 3 }, { "epoch": 0.48484848484848486, "grad_norm": 1.523720145225525, "learning_rate": 0.00012225209339563145, "loss": 2.9603, "step": 4 }, { "epoch": 0.6060606060606061, "grad_norm": 1.194486379623413, "learning_rate": 7.774790660436858e-05, "loss": 2.4278, "step": 5 }, { "epoch": 0.7272727272727273, "grad_norm": 1.3157984018325806, "learning_rate": 3.7651019814126654e-05, "loss": 1.9683, "step": 6 }, { "epoch": 0.8484848484848485, "grad_norm": 1.3595160245895386, "learning_rate": 9.903113209758096e-06, "loss": 2.2561, "step": 7 }, { "epoch": 0.9696969696969697, "grad_norm": 1.2659095525741577, "learning_rate": 0.0, "loss": 2.2029, "step": 8 } ], "logging_steps": 1, "max_steps": 8, "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": 222371544858624.0, "train_batch_size": 1, "trial_name": null, "trial_params": null }