qwen2.5-0.5b-expo-DPO-ES-1 / eval_results.json
hZzy's picture
End of training
dee307d verified
raw
history blame
596 Bytes
{
"epoch": 2.69248937175248,
"eval_dpo_loss": 2.2471413612365723,
"eval_logits": -0.6650525331497192,
"eval_logps": -83.28822326660156,
"eval_loss": 2.3242855072021484,
"eval_objective": 2.2471413612365723,
"eval_ranking_idealized": 0.5295031070709229,
"eval_ranking_idealized_expo": 0.5212215185165405,
"eval_ranking_simple": 0.5377846956253052,
"eval_regularize": 2.2471413612365723,
"eval_runtime": 314.6348,
"eval_samples": 5790,
"eval_samples_per_second": 18.402,
"eval_steps_per_second": 1.535,
"eval_wo_beta": 6.681451797485352
}