qwen2.5-0.5b-expo-L1EXPO-ES-10 / train_results.json
hZzy's picture
Model save
f3678be verified
raw
history blame contribute delete
231 Bytes
{
"epoch": 3.4057628719886632,
"total_flos": 0.0,
"train_loss": 2.660881093343099,
"train_runtime": 6833.7834,
"train_samples": 50802,
"train_samples_per_second": 37.17,
"train_steps_per_second": 0.258
}