Files
llama-3-8b-base-new-dpo-hh-…/all_results.json
ModelHub XC 4c5ec42aaa 初始化项目,由ModelHub XC社区提供模型
Model: W-61/llama-3-8b-base-new-dpo-hh-harmless-s_star1.0-4xh200-batch-64-20260421-213851
Source: Original Platform
2026-04-26 08:53:18 +08:00

26 lines
976 B
JSON

{
"epoch": 0.999244142101285,
"eval_fcm_dpo/beta": 0.22239074110984802,
"eval_fcm_dpo/delta": 0.017137322574853897,
"eval_fcm_dpo/margin": 4.419626235961914,
"eval_fcm_dpo/q_t": 0.3427804410457611,
"eval_logits/chosen": 0.3007291853427887,
"eval_logits/rejected": 0.25601860880851746,
"eval_logps/chosen": -82.5825424194336,
"eval_logps/ref_chosen": -74.85946655273438,
"eval_logps/ref_rejected": -79.54898834228516,
"eval_logps/rejected": -91.69168853759766,
"eval_loss": 0.5452697277069092,
"eval_margin_dpo/margin_mean": 4.419626235961914,
"eval_margin_dpo/margin_std": 7.256680488586426,
"eval_runtime": 38.1623,
"eval_samples": 2303,
"eval_samples_per_second": 60.347,
"eval_steps_per_second": 1.887,
"total_flos": 0.0,
"train_loss": 1.0460260132617922,
"train_runtime": 1747.5645,
"train_samples": 42336,
"train_samples_per_second": 24.226,
"train_steps_per_second": 0.378
}