{ | |
"epoch": 94.0, | |
"eval_explained_variance": 0.4649323523044586, | |
"eval_kl_divergence": 0.3295058012008667, | |
"eval_loss": 0.46722450852394104, | |
"eval_mae": 0.11545699089765549, | |
"eval_rmse": 0.15503521263599396, | |
"eval_runtime": 63.8487, | |
"eval_samples_per_second": 36.915, | |
"eval_steps_per_second": 2.318, | |
"learning_rate": 1.0000000000000002e-07, | |
"total_flos": 9.743166860733663e+19, | |
"train_loss": 0.46343856458701926, | |
"train_runtime": 26810.1674, | |
"train_samples_per_second": 39.181, | |
"train_steps_per_second": 2.451 | |
} |