初始化项目，由ModelHub XC社区提供模型

Model: raca-workspace-v1/grpo-tool-sat-sft-qwen3-1p7b-sft-20260419-075623-96e9 Source: Original Platform
2026-05-28 09:48:20 +08:00
commit c1b860e80a
20 changed files with 152612 additions and 0 deletions
--- a/train_results.json
+++ b/train_results.json
@@ -0,0 +1,8 @@
+{
+    "epoch": 2.0,
+    "total_flos": 7576988418048000.0,
+    "train_loss": 0.4733153915405273,
+    "train_runtime": 560.9841,
+    "train_samples_per_second": 28.521,
+    "train_steps_per_second": 1.783
+}