Training in progress, step 250

README.md

@@ -27,7 +27,7 @@ print(output["generated_text"])
 
 ## Training procedure
 
-[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/mlebar-university-of-chicago/huggingface/runs/81xgnibd) 
+[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/mlebar-university-of-chicago/huggingface/runs/rr4qvts9) 
 
 
 This model was trained with GRPO, a method introduced in [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://huggingface.co/papers/2402.03300).

adapter_config.json

@@ -25,10 +25,10 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "v_proj",
-    "o_proj",
     "k_proj",
-    "q_proj"
+    "v_proj",
+    "q_proj",
+    "o_proj"
   ],
   "target_parameters": null,
   "task_type": "CAUSAL_LM",

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c47ac5c418e03790b2784c47d0bd94334e10fed220ae475547f82cbb13603ebc
+oid sha256:d1a699fc6a37a0ffeabc416db2012370e719baa92bb55714a667162c43fef0da
 size 54560368

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3c2707f3bed6e825b1ab329ee8fd67eda78289534601eaeed56112c8ee2b8341
+oid sha256:79e2ec1c0606fbd546153bb5ba34117f0f7d64aa73946dc6a4869e293a71fa49
 size 7057

wandb_run_info.json

@@ -0,0 +1 @@
+{"run_id": "rr4qvts9", "project": "huggingface"}