初始化项目，由ModelHub XC社区提供模型

Model: Lansechen/Qwen2.5-7B-Open-R1-GRPO-math-lighteval-1epochstop-withformat Source: Original Platform
2026-06-07 22:56:24 +08:00
commit 9f04346d79
19 changed files with 153138 additions and 0 deletions
--- a/train_results.json
+++ b/train_results.json
@@ -0,0 +1,8 @@
+{
+    "total_flos": 0.0,
+    "train_loss": 0.02949339959234225,
+    "train_runtime": 14062.8623,
+    "train_samples": 7500,
+    "train_samples_per_second": 0.533,
+    "train_steps_per_second": 0.005
+}