{ "epoch": 62.0, "eval_explained_variance": 0.38597723841667175, "eval_kl_divergence": 0.9802031517028809, "eval_loss": 0.40605100989341736, "eval_mae": 0.1445874720811844, "eval_rmse": 0.2018682211637497, "eval_runtime": 61.1056, "eval_samples_per_second": 38.573, "eval_steps_per_second": 2.422, "learning_rate": 1.0000000000000002e-06, "total_flos": 6.42634409963284e+19, "train_loss": 0.3985773164651095, "train_runtime": 16834.9641, "train_samples_per_second": 62.397, "train_steps_per_second": 3.903 }