初始化项目，由ModelHub XC社区提供模型

Model: snorkelai/Snorkel-Mistral-PairRM-DPO Source: Original Platform
2026-06-21 19:41:06 +08:00
commit 36f13de528
17 changed files with 93228 additions and 0 deletions
--- a/train_results.json
+++ b/train_results.json
@@ -0,0 +1,8 @@
+{
+    "epoch": 3.0,
+    "train_loss": 0.23198359412724215,
+    "train_runtime": 18849.1473,
+    "train_samples": 19958,
+    "train_samples_per_second": 3.176,
+    "train_steps_per_second": 0.05
+}