初始化项目，由ModelHub XC社区提供模型

Model: jackf857/llama-3-8b-base-margin-dpo-hh-harmless-beta0.01 Source: Original Platform
2026-05-10 11:52:05 +08:00
commit 6d01dcb874
681 changed files with 15240 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": 1.1443162902220294,
+    "train_runtime": 1702.0491,
+    "train_samples": 42336,
+    "train_samples_per_second": 24.874,
+    "train_steps_per_second": 0.388
+}