wxzhang/selective-pairrm-33045197-mt0
1
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity

初始化项目，由ModelHub XC社区提供模型

Browse Source 
Model: wxzhang/selective-pairrm-33045197-mt0
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-05-20 22:40:53 +08:00
commit 9e38bb0fd5
17 changed files with 92219 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

16
eval_results.json Normal file
View File

@@ -0,0 +1,16 @@
{
"epoch": 1.0,
"eval_logits/chosen": -3.170811176300049,
"eval_logits/rejected": -3.164327621459961,
"eval_logps/chosen": -401.41021728515625,
"eval_logps/rejected": -417.67462158203125,
"eval_loss": 0.682475209236145,
"eval_rewards/accuracies": 0.60546875,
"eval_rewards/chosen": -0.23294878005981445,
"eval_rewards/margins": 0.03622151538729668,
"eval_rewards/rejected": -0.26917028427124023,
"eval_runtime": 135.9607,
"eval_samples": 994,
"eval_samples_per_second": 7.355,
"eval_steps_per_second": 0.235
}