Upload training_metrics.json with huggingface_hub

training_metrics.json

@@ -0,0 +1,14 @@
+{
+  "base_model": "Qwen/Qwen2.5-1.5B-Instruct",
+  "training_method": "GRPO with Unsloth",
+  "dataset_size": 1602,
+  "training_steps": 360,
+  "final_reward": 3.17,
+  "improvement": "+67%",
+  "key_achievements": [
+    "Foreign language bias detection",
+    "Structured reasoning output",
+    "67% reward improvement",
+    "46% reduction in output variance"
+  ]
+}