初始化项目，由ModelHub XC社区提供模型

Model: jackf857/qwen3-8b-base-margin-dpo-hh-helpful-4xh200-batch-64-20260423-233948 Source: Original Platform
2026-05-09 21:17:36 +08:00
commit ed60227d3e
24 changed files with 165072 additions and 0 deletions
--- a/train_results.json
+++ b/train_results.json
@@ -0,0 +1,9 @@
+{
+    "epoch": 1.0,
+    "total_flos": 0.0,
+    "train_loss": 0.7553340482816823,
+    "train_runtime": 3298.7616,
+    "train_samples": 43598,
+    "train_samples_per_second": 13.216,
+    "train_steps_per_second": 0.206
+}