dpo_06230018_policy2_0.01 / train_results.json
WDong's picture
Upload 17 files
c53888e verified
raw
history blame contribute delete
220 Bytes
{
"epoch": 2.994495412844037,
"total_flos": 7.837376281021809e+17,
"train_loss": 0.514469311225648,
"train_runtime": 8073.8639,
"train_samples_per_second": 1.619,
"train_steps_per_second": 0.051
}