Training in progress, step 500

README.md

@@ -4,9 +4,9 @@ library_name: transformers
 model_name: HidatoQwenModel
 tags:
 - generated_from_trainer
-- unsloth
 - trl
 - grpo
+- unsloth
 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/r0jkbel7) 
+[<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/lqdk5vbi) 
 
 
 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": [
-    "v_proj",
-    "up_proj",
-    "q_proj",
+    "gate_proj",
     "o_proj",
     "down_proj",
-    "gate_proj",
-    "k_proj"
+    "k_proj",
+    "q_proj",
+    "v_proj",
+    "up_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:b64e8d9a481be2c08a2b76fe91d22222a86eab94fb01519f87ff2bacc137e426
+oid sha256:2f84978949dc655ad48467679e1b1c52a29931c495ad93f911cfc67c0d247d08
 size 479005064

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:69e5dc3e19cfd62768ab2832bf066a1c9a0e00b77417281ca069afc828d33475
+oid sha256:b514fa71385449f8951385b20da2defc14e4b5d6eeb97fadabf5a2fcc59964da
 size 7185