Training in progress, step 50

README.md

@@ -4,8 +4,8 @@ library_name: transformers
 model_name: qwen2-0.5b-instruct-math-grpo
 tags:
 - generated_from_trainer
-- trl
 - grpo
+- trl
 licence: license
 ---
 
@@ -27,7 +27,7 @@ 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/larryl729-team/huggingface/runs/ag7e6i97) 
+[<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/larryl729-team/huggingface/runs/cy045ruw) 
 
 
 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

@@ -25,8 +25,8 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "v_proj",
-    "q_proj"
+    "q_proj",
+    "v_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:ec163ceb3294632d9cf9f547569f1e7ecfac1edcaf1c8f53418777b8556e6a7a
+oid sha256:dcfdf39deddf9f8c0a5aa26826c3dc939f03b2a8a597d55dc194b15c4bfb1777
 size 2175168

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bb808c7160f18a6abda421ac98dcca486c73d61f7a33f1f551245e2786dd43eb
+oid sha256:7ddbe7ca9580ec98a22f2c147fae18c89bb1aaf6d0a4d948efc4df365ea42db3
 size 6929