qwen2.5-0.5b-expo-DPO-ES-0.01 / train_results.json
hZzy's picture
Model save
020572d verified
raw
history blame
234 Bytes
{
"epoch": 1.5588096362777515,
"total_flos": 0.0,
"train_loss": 0.17483963706276634,
"train_runtime": 6877.8936,
"train_samples": 50802,
"train_samples_per_second": 36.931,
"train_steps_per_second": 0.256
}