初始化项目，由ModelHub XC社区提供模型

Model: ali-elganzory/Baguettotron-DPO-Tulu3-decontaminated Source: Original Platform
2026-05-01 10:51:28 +08:00
commit 07e2711cf5
14 changed files with 331114 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": 4.036165593823357,
+    "train_runtime": 7155.9863,
+    "train_samples": 272585,
+    "train_samples_per_second": 38.092,
+    "train_steps_per_second": 0.298
+}