Training in progress, step 50

README.md

@@ -4,8 +4,8 @@ library_name: transformers
 model_name: HidatoQwenModel
 tags:
 - generated_from_trainer
-- unsloth
 - grpo
+- unsloth
 - trl
 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/x14d9l69) 
+[<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/onz28ocl) 
 
 
 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",
-    "q_proj",
     "up_proj",
-    "down_proj",
-    "k_proj",
     "v_proj",
-    "o_proj"
+    "k_proj",
+    "o_proj",
+    "q_proj",
+    "down_proj",
+    "gate_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:c041870b85072c4d503edce19e68b99c3ad75909a8cdccfc493e7be663904f1f
+oid sha256:fec3f6924a8ada062600830651538c8edb8dd597330fe896e37cb38c4a81764e
 size 479005064

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9f47ca104107db0990f56443d657e8d76852d3f24fa0efb2dba9b148ff6bf368
+oid sha256:ff3d6b5a2d5b1afe28df818e016de8bf6321ed47dfea7e0e25d0233e5768c027
 size 7185