Files
llama-3-8b-base-new-dpo-hh-…/eval_results.json
ModelHub XC 73b3eb1f2d 初始化项目,由ModelHub XC社区提供模型
Model: jackf857/llama-3-8b-base-new-dpo-hh-harmless-4xh200-batch-64-q_t-0.5-s_star-0.4
Source: Original Platform
2026-05-14 07:01:43 +08:00

17 lines
642 B
JSON

{
"epoch": 0.999244142101285,
"eval_fcm_dpo/beta": 0.006462239660322666,
"eval_logits/chosen": 0.7311930656433105,
"eval_logits/rejected": 0.6827455759048462,
"eval_logps/chosen": -208.29672241210938,
"eval_logps/ref_chosen": -74.85946655273438,
"eval_logps/ref_rejected": -79.54898834228516,
"eval_logps/rejected": -270.3067932128906,
"eval_loss": 0.5738745331764221,
"eval_margin_dpo/margin_mean": 57.32048416137695,
"eval_margin_dpo/margin_std": 98.36843872070312,
"eval_runtime": 37.9174,
"eval_samples": 2303,
"eval_samples_per_second": 60.737,
"eval_steps_per_second": 1.899
}