初始化项目，由ModelHub XC社区提供模型

Model: W-61/qwen3-8b-base-new-dpo-ultrafeedback-4xh200-batch-128-q_t-0.45-s_star-0.5-20260430-194457 Source: Original Platform
2026-05-07 16:58:45 +08:00
commit 51d9aae23d
500 changed files with 166217 additions and 0 deletions
--- a/all_results.json
+++ b/all_results.json
@@ -0,0 +1,9 @@
+{
+    "epoch": 0.9989528795811519,
+    "total_flos": 0.0,
+    "train_loss": 4.685751873492195,
+    "train_runtime": 9606.4037,
+    "train_samples": 61135,
+    "train_samples_per_second": 6.364,
+    "train_steps_per_second": 0.05
+}