dpo_06221544_policy2 / train_results.json
WDong's picture
Upload 17 files
39b42fa verified
raw
history blame
220 Bytes
{
"epoch": 2.994495412844037,
"total_flos": 7.837376281021809e+17,
"train_loss": 0.220101895632551,
"train_runtime": 8071.0106,
"train_samples_per_second": 1.619,
"train_steps_per_second": 0.051
}