qwen2.5-0.5b-expo-DPO-noES-0.1 / all_results.json
hZzy's picture
Model save
3678860 verified
raw
history blame
232 Bytes
{
"epoch": 2.992914501653283,
"total_flos": 0.0,
"train_loss": 0.37872021553586377,
"train_runtime": 34657.2213,
"train_samples": 50802,
"train_samples_per_second": 4.398,
"train_steps_per_second": 0.03
}