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/yjx8f36a) 
+[<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/7wfak9dk) 
 
 
 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

@@ -25,16 +25,16 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "gate_proj",
+    "lm_head",
     "mlp1.3",
     "o_proj",
-    "v_proj",
-    "gate_proj",
     "mlp1.1",
-    "up_proj",
-    "lm_head",
     "down_proj",
-    "q_proj",
-    "k_proj"
+    "v_proj",
+    "up_proj",
+    "k_proj",
+    "q_proj"
   ],
   "target_parameters": null,
   "task_type": "CAUSAL_LM",

tokenizer.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9b536a0320fc6038134dd6bf6108025d41a5db099bb06b7d9bc2281bac37dbbb
-size 11418549
+oid sha256:f167a8394b8900bf9d8249a47d4d29e1c0242f557f27f602d8d7f66b7a4e9234
+size 11418382

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a65046b9c419c566b2d099809d60a8250090eac1f510e18d6902e72f683dfae8
+oid sha256:f7fa6818646f03342a1b07bb0fa908092aa048181bf992b8f6dd53019a5f3975
 size 8785