初始化项目，由ModelHub XC社区提供模型

Model: W-61/mistral-7b-base-epsilon-dpo-hh-harmless-4xh200-batch-64 Source: Original Platform
2026-04-22 12:12:09 +08:00
commit 4ced85fa16
20 changed files with 302255 additions and 0 deletions
--- a/train_results.json
+++ b/train_results.json
@@ -0,0 +1,9 @@
+{
+    "epoch": 0.999244142101285,
+    "total_flos": 0.0,
+    "train_loss": 1.0336073330418967,
+    "train_runtime": 2985.5995,
+    "train_samples": 42336,
+    "train_samples_per_second": 14.18,
+    "train_steps_per_second": 0.221
+}