0.001_idpo_iter_2 / train_results.json
ShenaoZhang's picture
Model save
a44ff62 verified
{
"epoch": 1.0,
"train_loss": 0.6627466093819097,
"train_runtime": 2639.006,
"train_samples": 20378,
"train_samples_per_second": 7.722,
"train_steps_per_second": 0.06
}