初始化项目，由ModelHub XC社区提供模型

Model: W-61/mistral-7b-base-epsilon-dpo-hh-helpful-4xh200-batch-64 Source: Original Platform
2026-04-22 12:22:48 +08:00
commit 0fcf19d1a3
20 changed files with 302827 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": 0.6833117403385398,
+    "train_runtime": 3053.5655,
+    "train_samples": 43598,
+    "train_samples_per_second": 14.278,
+    "train_steps_per_second": 0.223
+}