初始化项目，由ModelHub XC社区提供模型

Model: W-61/mistral-7b-base-beta-dpo-hh-harmless-4xh200-batch-64 Source: Original Platform
2026-05-30 22:35:26 +08:00
commit eb326fd6d8
20 changed files with 297560 additions and 0 deletions
--- a/train_results.json
+++ b/train_results.json
@@ -0,0 +1,9 @@
+{
+    "epoch": 0.999244142101285,
+    "total_flos": 0.0,
+    "train_loss": 1.3336656033181207,
+    "train_runtime": 3770.6222,
+    "train_samples": 42336,
+    "train_samples_per_second": 11.228,
+    "train_steps_per_second": 0.175
+}