初始化项目，由ModelHub XC社区提供模型

Model: shubhamrgandhi/qwen3-4b-instruct-2507-full-sft-prm-r2egym-swebench-instructions-k5-qwen-only Source: Original Platform
2026-07-29 07:44:13 +08:00
commit 6d79867f72
14 changed files with 919 additions and 0 deletions
--- a/train_results.json
+++ b/train_results.json
@@ -0,0 +1,8 @@
+{
+    "epoch": 3.0,
+    "total_flos": 3.143410755085271e+17,
+    "train_loss": 0.2539728307061725,
+    "train_runtime": 24192.1432,
+    "train_samples_per_second": 0.237,
+    "train_steps_per_second": 0.03
+}