Files
llama-3-8b-base-new-dpo-har…/eval_results.json
ModelHub XC d5bfea8476 初始化项目,由ModelHub XC社区提供模型
Model: jackf857/llama-3-8b-base-new-dpo-harmless-s_star0.4-q_t0.4
Source: Original Platform
2026-05-14 11:41:38 +08:00

17 lines
642 B
JSON

{
"epoch": 0.999244142101285,
"eval_fcm_dpo/beta": 0.003048304468393326,
"eval_logits/chosen": 0.9178658127784729,
"eval_logits/rejected": 0.8999158143997192,
"eval_logps/chosen": -279.8544006347656,
"eval_logps/ref_chosen": -74.85946655273438,
"eval_logps/ref_rejected": -79.54898834228516,
"eval_logps/rejected": -365.8829650878906,
"eval_loss": 0.6095079779624939,
"eval_margin_dpo/margin_mean": 81.33904266357422,
"eval_margin_dpo/margin_std": 169.26637268066406,
"eval_runtime": 38.7977,
"eval_samples": 2303,
"eval_samples_per_second": 59.359,
"eval_steps_per_second": 1.856
}