{ "best_metric": null, "best_model_checkpoint": null, "epoch": 0.12012012012012012, "eval_steps": 500, "global_step": 10, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.012012012012012012, "grad_norm": 0.0, "learning_rate": 0.0001, "loss": 0.0, "step": 1 }, { "epoch": 0.024024024024024024, "grad_norm": 0.0, "learning_rate": 0.0002, "loss": 0.0, "step": 2 }, { "epoch": 0.036036036036036036, "grad_norm": 0.0, "learning_rate": 0.0001923879532511287, "loss": 0.0, "step": 3 }, { "epoch": 0.04804804804804805, "grad_norm": 0.0, "learning_rate": 0.00017071067811865476, "loss": 0.0, "step": 4 }, { "epoch": 0.06006006006006006, "grad_norm": 0.0, "learning_rate": 0.000138268343236509, "loss": 0.0, "step": 5 }, { "epoch": 0.07207207207207207, "grad_norm": 0.0, "learning_rate": 0.0001, "loss": 0.0, "step": 6 }, { "epoch": 0.08408408408408409, "grad_norm": 0.0, "learning_rate": 6.173165676349103e-05, "loss": 0.0, "step": 7 }, { "epoch": 0.0960960960960961, "grad_norm": 0.0, "learning_rate": 2.9289321881345254e-05, "loss": 0.0, "step": 8 }, { "epoch": 0.10810810810810811, "grad_norm": 0.0, "learning_rate": 7.612046748871327e-06, "loss": 0.0, "step": 9 }, { "epoch": 0.12012012012012012, "grad_norm": 0.0, "learning_rate": 0.0, "loss": 0.0, "step": 10 }, { "epoch": 0.12012012012012012, "eval_loss": NaN, "eval_runtime": 1.3032, "eval_samples_per_second": 13.813, "eval_steps_per_second": 13.813, "step": 10 } ], "logging_steps": 1, "max_steps": 10, "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": 1849564248145920.0, "train_batch_size": 1, "trial_name": null, "trial_params": null }