qwen2.5-0.5b-expo-DPO-ES-TRY2 / all_results.json
hZzy's picture
End of training
ec33645 verified
{
"epoch": 2.9976381672177608,
"eval_dpo_loss": 0.8798040151596069,
"eval_dpo_wo_beta": -5.900633335113525,
"eval_logits": -2.0008888244628906,
"eval_logps": -117.1633071899414,
"eval_loss": 0.8436967730522156,
"eval_objective": 0.8798040151596069,
"eval_ranking_idealized": 0.5888429880142212,
"eval_ranking_idealized_expo": 0.5092975497245789,
"eval_ranking_simple": 0.5402892827987671,
"eval_regularize": 0.8798040151596069,
"eval_runtime": 210.7851,
"eval_samples": 5790,
"eval_samples_per_second": 27.469,
"eval_steps_per_second": 1.148,
"total_flos": 0.0,
"train_loss": 0.023984534440167023,
"train_runtime": 3310.3799,
"train_samples": 50802,
"train_samples_per_second": 46.039,
"train_steps_per_second": 0.159
}