qwen2.5-0.5b-expo-DPO-ES-TRY1 / all_results.json
hZzy's picture
End of training
63d5d66 verified
raw
history blame contribute delete
801 Bytes
{
"epoch": 1.83656117146906,
"eval_dpo_loss": 0.6925506591796875,
"eval_dpo_wo_beta": -0.9551481008529663,
"eval_logits": -1.5338705778121948,
"eval_logps": -91.41157531738281,
"eval_loss": 0.6866393685340881,
"eval_objective": 0.6925506591796875,
"eval_ranking_idealized": 0.5888429880142212,
"eval_ranking_idealized_expo": 0.5092975497245789,
"eval_ranking_simple": 0.5051652789115906,
"eval_regularize": 0.6925506591796875,
"eval_runtime": 210.7989,
"eval_samples": 5790,
"eval_samples_per_second": 27.467,
"eval_steps_per_second": 1.148,
"total_flos": 0.0,
"train_loss": 0.29064991334338247,
"train_runtime": 6418.0206,
"train_samples": 50802,
"train_samples_per_second": 15.831,
"train_steps_per_second": 0.055
}