{ "best_metric": null, "best_model_checkpoint": null, "epoch": 0.0007490566567728766, "eval_steps": 8, "global_step": 20, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 3.7452832838643834e-05, "eval_loss": 1.7370612621307373, "eval_runtime": 474.9951, "eval_samples_per_second": 23.67, "eval_steps_per_second": 11.836, "step": 1 }, { "epoch": 0.0001123584985159315, "grad_norm": 0.28893381357192993, "learning_rate": 3e-05, "loss": 1.5635, "step": 3 }, { "epoch": 0.000224716997031863, "grad_norm": 0.2005578577518463, "learning_rate": 6e-05, "loss": 1.6927, "step": 6 }, { "epoch": 0.00029962266270915067, "eval_loss": 1.7258363962173462, "eval_runtime": 473.4423, "eval_samples_per_second": 23.747, "eval_steps_per_second": 11.875, "step": 8 }, { "epoch": 0.00033707549554779447, "grad_norm": 0.25112399458885193, "learning_rate": 9e-05, "loss": 1.9006, "step": 9 }, { "epoch": 0.000449433994063726, "grad_norm": 0.22203008830547333, "learning_rate": 9.755282581475769e-05, "loss": 1.5323, "step": 12 }, { "epoch": 0.0005617924925796575, "grad_norm": 0.24594427645206451, "learning_rate": 8.535533905932738e-05, "loss": 1.684, "step": 15 }, { "epoch": 0.0005992453254183013, "eval_loss": 1.6712545156478882, "eval_runtime": 475.179, "eval_samples_per_second": 23.661, "eval_steps_per_second": 11.831, "step": 16 }, { "epoch": 0.0006741509910955889, "grad_norm": 0.277011901140213, "learning_rate": 6.545084971874738e-05, "loss": 1.7029, "step": 18 } ], "logging_steps": 3, "max_steps": 30, "num_input_tokens_seen": 0, "num_train_epochs": 1, "save_steps": 10, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": false }, "attributes": {} } }, "total_flos": 1119438539587584.0, "train_batch_size": 2, "trial_name": null, "trial_params": null }