Model save

README.md

@@ -28,7 +28,7 @@ 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/amaydle/huggingface/runs/lu2v1lzz) 
+[<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/amaydle/huggingface/runs/h0wfc037) 
 
 
 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).

checkpoint/adapter_config.json

@@ -24,13 +24,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "o_proj",
+    "v_proj",
+    "gate_proj",
     "up_proj",
     "k_proj",
     "down_proj",
-    "v_proj",
-    "q_proj",
-    "o_proj",
-    "gate_proj"
+    "q_proj"
   ],
   "task_type": "CAUSAL_LM",
   "trainable_token_indices": null,

checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dd42b3df8a02b7ee0a6b096ce836b5ec5a3f25acfdbb6d0333bf587411034539
+oid sha256:858adc85d4457fa72eac7402455de39cb267db05c527e476cd842c3791f77f26
 size 323014168

checkpoint/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:57bb32944b4909f64f0eb8ed21145c642815076c1009a4a62802d30e85506632
+oid sha256:4725bcc241f4eb6d47fff0068f6dcfa907f087b17a95cfd1e285e032bab79413
 size 5944