初始化项目，由ModelHub XC社区提供模型

Model: W-61/mistral-7b-base-beta-dpo-hh-helpful-4xh200-batch-64 Source: Original Platform
2026-04-22 11:00:42 +08:00
commit 097e33be47
20 changed files with 297992 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": 4.511853932745809,
+    "train_runtime": 2770.5528,
+    "train_samples": 43598,
+    "train_samples_per_second": 15.736,
+    "train_steps_per_second": 0.246
+}