qwen2.5-0.5b-expo-DPO-ES-TRY1 / train_results.json
hZzy's picture
Model save
10246fa verified
raw
history blame
232 Bytes
{
"epoch": 1.83656117146906,
"total_flos": 0.0,
"train_loss": 0.29064991334338247,
"train_runtime": 6418.0206,
"train_samples": 50802,
"train_samples_per_second": 15.831,
"train_steps_per_second": 0.055
}