Training in progress, step 10

README.md

@@ -4,8 +4,8 @@ library_name: transformers
 model_name: Qwen2-0.5B-GRPO-test
 tags:
 - generated_from_trainer
-- grpo
 - trl
+- grpo
 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/kamathis/huggingface/runs/s8xon7m0) 
+[<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/kamathis/huggingface/runs/8nvz6dpk) 
 
 
 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_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:005cd724acd4e8fea651b4a62f349ca1fb1c550246fcea4e0bbd12e3e1893699
+oid sha256:b4505c0a8745770ff1e84b6019e61c1585f5921dd8eee0d4260f45ee054fb1a1
 size 2175168

tokenizer.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7eb286f12ea1478a062a5ba7b56eab18f376828c62272626dd3ce0155da912fb
+oid sha256:608e4e7c10b6bf39aea5409e2c54b0bbde12907a6c1a3b2e732a282f95823a6c
 size 11418530

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:05824945c300a7bcc48b50c2358ac4cf7a33fcf82afc3f80b9ab503c0ff0a000
+oid sha256:1612b67bba67493407a654d419ec16e1b6408df3546dcbe1b447d04dd62e8dcf
 size 6776