{ | |
"epoch": 62.0, | |
"eval_explained_variance": 0.6593042016029358, | |
"eval_kl_divergence": 0.11466515809297562, | |
"eval_loss": 0.45506975054740906, | |
"eval_mae": 0.06304711848497391, | |
"eval_rmse": 0.08664286881685257, | |
"eval_runtime": 26.2102, | |
"eval_samples_per_second": 179.244, | |
"eval_steps_per_second": 2.823, | |
"learning_rate": 1.0000000000000002e-07, | |
"total_flos": 9.42369297866869e+19, | |
"train_loss": 0.4754439868851833, | |
"train_runtime": 8961.4221, | |
"train_samples_per_second": 235.894, | |
"train_steps_per_second": 3.699 | |
} |