初始化项目，由ModelHub XC社区提供模型

Model: ali-elganzory/Qwen3-1.7B-Base-DPO-Tulu3-decontaminated-masked Source: Original Platform
2026-08-26 19:57:01 +08:00
commit 1cb70daf8b
17 changed files with 155228 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": 3.058436307772784,
+    "train_runtime": 6320.6844,
+    "train_samples": 272585,
+    "train_samples_per_second": 43.126,
+    "train_steps_per_second": 0.337
+}