qwen2.5-0.5b-expo-EXDPO2 / train_results.json
hZzy's picture
Model save
c863752 verified
raw
history blame contribute delete
230 Bytes
{
"epoch": 1.994962216624685,
"total_flos": 0.0,
"train_loss": 1.010300681672313,
"train_runtime": 13850.696,
"train_samples": 50802,
"train_samples_per_second": 7.336,
"train_steps_per_second": 0.038
}