dpo_06230018_policy2_0.6 / train_results.json
WDong's picture
Upload 17 files
9c7174e verified
raw
history blame contribute delete
221 Bytes
{
"epoch": 2.994495412844037,
"total_flos": 7.837376281021809e+17,
"train_loss": 0.11720214437923905,
"train_runtime": 8069.9016,
"train_samples_per_second": 1.62,
"train_steps_per_second": 0.051
}