{ "best_metric": null, "best_model_checkpoint": null, "epoch": 2.0, "eval_steps": 500, "global_step": 3694, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.2707092582566324, "grad_norm": 21.4527587890625, "learning_rate": 2.5939361126150515e-05, "loss": 1.2393, "step": 500 }, { "epoch": 0.5414185165132648, "grad_norm": 19.001697540283203, "learning_rate": 2.187872225230103e-05, "loss": 0.9569, "step": 1000 }, { "epoch": 0.8121277747698972, "grad_norm": 13.545599937438965, "learning_rate": 1.7818083378451544e-05, "loss": 0.8955, "step": 1500 }, { "epoch": 1.0828370330265296, "grad_norm": 14.762840270996094, "learning_rate": 1.3757444504602057e-05, "loss": 0.7921, "step": 2000 }, { "epoch": 1.353546291283162, "grad_norm": 23.409305572509766, "learning_rate": 9.696805630752573e-06, "loss": 0.6574, "step": 2500 }, { "epoch": 1.6242555495397943, "grad_norm": 15.587923049926758, "learning_rate": 5.636166756903086e-06, "loss": 0.6549, "step": 3000 }, { "epoch": 1.8949648077964265, "grad_norm": 14.118770599365234, "learning_rate": 1.5755278830536005e-06, "loss": 0.6304, "step": 3500 }, { "epoch": 2.0, "step": 3694, "total_flos": 2936196213553152.0, "train_loss": 0.8232728455217709, "train_runtime": 1379.4371, "train_samples_per_second": 128.513, "train_steps_per_second": 2.678 } ], "logging_steps": 500, "max_steps": 3694, "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": 2936196213553152.0, "train_batch_size": 48, "trial_name": null, "trial_params": null }