Model save

README.md

@@ -25,7 +25,7 @@ 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/minhdeptrai/huggingface/runs/dzyx463z) 
+[<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/minhdeptrai/huggingface/runs/5kp5aj86) 
 
 
 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

@@ -26,15 +26,15 @@
   "revision": null,
   "target_modules": [
     "v_proj",
+    "gate_proj",
+    "down_proj",
+    "q_proj",
+    "mlp1.1",
     "mlp1.3",
+    "lm_head",
     "k_proj",
     "o_proj",
-    "q_proj",
-    "gate_proj",
-    "lm_head",
-    "mlp1.1",
-    "up_proj",
-    "down_proj"
+    "up_proj"
   ],
   "target_parameters": null,
   "task_type": "CAUSAL_LM",

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1bc84c87a9c87d26dcb76c9153087bb5b35d942db6a858d8e4b9246649c94ff0
+oid sha256:49df9fc80406de38bb5066fc400de41486488e29e27ff2a44b0ce32847991f8e
 size 8785