{ | |
"epoch": 79.0, | |
"eval_explained_variance": 0.46537885069847107, | |
"eval_kl_divergence": 0.35774946212768555, | |
"eval_loss": 0.46723154187202454, | |
"eval_mae": 0.11465383321046829, | |
"eval_rmse": 0.15526758134365082, | |
"eval_runtime": 55.2715, | |
"eval_samples_per_second": 42.644, | |
"eval_steps_per_second": 0.669, | |
"learning_rate": 1.0000000000000002e-06, | |
"total_flos": 8.188406191467658e+19, | |
"train_loss": 0.4591466036709872, | |
"train_runtime": 19731.8487, | |
"train_samples_per_second": 53.236, | |
"train_steps_per_second": 0.836 | |
} |