初始化项目，由ModelHub XC社区提供模型

Model: ShenaoZhang/0.001_idpo_noreplacerej_iter_1 Source: Original Platform
2026-05-05 14:32:04 +08:00
commit ab4f5f096b
16 changed files with 91919 additions and 0 deletions
--- a/all_results.json
+++ b/all_results.json
@@ -0,0 +1,8 @@
+{
+    "epoch": 1.0,
+    "train_loss": 0.6063382550605438,
+    "train_runtime": 2647.1387,
+    "train_samples": 20378,
+    "train_samples_per_second": 7.698,
+    "train_steps_per_second": 0.06
+}