初始化项目，由ModelHub XC社区提供模型

Model: jackf857/llama-3-8b-base-new-dpo-hh-harmless-4xh200-batch-64-q_t-0.5-s_star-0.85 Source: Original Platform
2026-05-10 13:48:09 +08:00
commit 732046cbcb
20 changed files with 15924 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": 1.0861937751748378,
+    "train_runtime": 1754.5635,
+    "train_samples": 42336,
+    "train_samples_per_second": 24.129,
+    "train_steps_per_second": 0.377
+}