Training in progress, step 1000

README.md

@@ -4,8 +4,8 @@ library_name: transformers
 model_name: HidatoQwenModel02
 tags:
 - generated_from_trainer
-- unsloth
 - trl
+- unsloth
 - grpo
 licence: license
 ---
@@ -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/michlea-hse-spb/huggingface/runs/f6c890qi) 
+[<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/michlea-hse-spb/huggingface/runs/nhip0tuq) 
 
 
 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

@@ -29,13 +29,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "gate_proj",
-    "down_proj",
-    "up_proj",
     "k_proj",
     "q_proj",
-    "o_proj",
-    "v_proj"
+    "down_proj",
+    "v_proj",
+    "gate_proj",
+    "up_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 sha256:453d00e01dcce0746ed06c4237d2834a4a7988227fc423b44543ac193a263f0d
+oid sha256:124759c7d6754f00b7ed87a84c1891798374c210e28b301e906700a510c788e0
 size 479005064

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ec227df07ddb3a48dcdf4236bd3674a6689ab60586bf5669c82e5a9ec5065ba5
+oid sha256:529ceca764f83140181f4f905c941481306ce3c3569336785d9b7e258e3dd833
 size 7121