初始化项目，由ModelHub XC社区提供模型

Model: varshak1/open_reward_agent_sft_lf Source: Original Platform
2026-06-16 07:50:16 +08:00
commit ce5246e3fd
14 changed files with 528 additions and 0 deletions
--- a/train_results.json
+++ b/train_results.json
@@ -0,0 +1,8 @@
+{
+    "epoch": 1.0,
+    "total_flos": 2.640143661303595e+18,
+    "train_loss": 0.9932206619076612,
+    "train_runtime": 1797.9362,
+    "train_samples_per_second": 7.286,
+    "train_steps_per_second": 0.114
+}