qwen_uncCPO_entropy_0_01 / train_results.json
yakazimir's picture
Model save
d149a0a verified
raw
history blame
233 Bytes
{
"epoch": 2.999297541394882,
"total_flos": 0.0,
"train_loss": 0.05868237358195538,
"train_runtime": 34511.7277,
"train_samples": 59790,
"train_samples_per_second": 5.197,
"train_steps_per_second": 0.162
}