初始化项目，由ModelHub XC社区提供模型

Model: jackf857/llama-3-8b-base-new-dpo-hh-helpful-s_star1.0-4xh200-batch-64-20260421-233802 Source: Original Platform
2026-05-30 03:50:21 +08:00
commit fd963e80d1
702 changed files with 17688 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": 0.846195821282447,
+    "train_runtime": 1845.654,
+    "train_samples": 43598,
+    "train_samples_per_second": 23.622,
+    "train_steps_per_second": 0.369
+}