qwen2.5-0.5b-expo-DPO-ES-1 / train_results.json
hZzy's picture
Model save
0200f4d verified
raw
history blame
231 Bytes
{
"epoch": 2.69248937175248,
"total_flos": 0.0,
"train_loss": 0.7490891541932758,
"train_runtime": 28216.8085,
"train_samples": 50802,
"train_samples_per_second": 9.002,
"train_steps_per_second": 0.062
}