nash_dpo_merge_iter_5 / train_results.json
YYYYYYibo's picture
Model save
035485f verified
raw
history blame contribute delete
194 Bytes
{
"epoch": 1.0,
"train_loss": 0.5790139436721802,
"train_runtime": 8829.5489,
"train_samples": 25000,
"train_samples_per_second": 2.831,
"train_steps_per_second": 0.022
}