qwen2.5-0.5b-expo-L2EXPO-ES-0.01 / train_results.json
hZzy's picture
Model save
e0d3a9c verified
raw
history blame contribute delete
233 Bytes
{
"epoch": 0.8502598016060463,
"total_flos": 0.0,
"train_loss": 0.3342974317073822,
"train_runtime": 8266.6282,
"train_samples": 50802,
"train_samples_per_second": 30.727,
"train_steps_per_second": 0.213
}