qwen_cpo_entropy_0_3 / all_results.json
yakazimir's picture
Model save
0aa2b6b verified
raw
history blame
231 Bytes
{
"epoch": 2.999297541394882,
"total_flos": 0.0,
"train_loss": 0.9803723535479859,
"train_runtime": 32947.1599,
"train_samples": 59790,
"train_samples_per_second": 5.444,
"train_steps_per_second": 0.17
}