{ "epoch": 83.0, "eval_explained_variance": 0.4690297544002533, "eval_kl_divergence": 0.39311662316322327, "eval_loss": 0.46676135063171387, "eval_mae": 0.11432621628046036, "eval_rmse": 0.1546144038438797, "eval_runtime": 61.4305, "eval_samples_per_second": 38.369, "eval_steps_per_second": 1.205, "learning_rate": 1.0000000000000002e-06, "total_flos": 8.603009036605255e+19, "train_loss": 0.45949580130708517, "train_runtime": 19431.3015, "train_samples_per_second": 54.06, "train_steps_per_second": 1.691 }