qwen2.5-0.5b-expo-L2EXPO-25-3 / train_results.json
hZzy's picture
Model save
6444666 verified
{
"epoch": 2.987152034261242,
"total_flos": 0.0,
"train_loss": 0.27528571787700856,
"train_runtime": 19429.5857,
"train_samples": 44816,
"train_samples_per_second": 6.92,
"train_steps_per_second": 0.024
}