Training in progress, step 150

README.md

@@ -4,8 +4,8 @@ library_name: transformers
 model_name: HidatoQwenModel
 tags:
 - generated_from_trainer
-- trl
 - unsloth
+- trl
 - 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/racczvqo) 
+[<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/ku48q24w) 
 
 
 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

@@ -29,12 +29,12 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "k_proj",
-    "v_proj",
-    "down_proj",
-    "o_proj",
-    "q_proj",
     "gate_proj",
+    "q_proj",
+    "o_proj",
+    "down_proj",
+    "v_proj",
+    "k_proj",
     "up_proj"
   ],
   "target_parameters": null,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:88ef13566dfe7223b70a4107006f5165c1806ee6438844d3d711ab6a22118dc3
+oid sha256:18afebf0548342b00a2015af1313255dd0e3c62a517bcef8e61dfcb3eb359cae
 size 479005064

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f18a71f74bd1cc228a9ef8062ae9c9645b1826cc2f504f90e029cfe47c9da483
+oid sha256:0ff775a2c79e40807adb3d5f6a6e250aa684dd84c0a70868ed2f337c10df1083
 size 7185