Training in progress, epoch 1

README.md

@@ -4,8 +4,8 @@ library_name: transformers
 model_name: DeepSeek-R1-Distill-Qwen-1.5B-GSPO-Basic
 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/leonwenderoth-tu-darmstadt/huggingface/runs/doctacqy) 
+[<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/leonwenderoth-tu-darmstadt/huggingface/runs/6bd0c08q) 
 
 
 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).

generation_config.json

@@ -2,7 +2,9 @@
   "_from_model_config": true,
   "bos_token_id": 151646,
   "do_sample": true,
-  "eos_token_id": 151643,
+  "eos_token_id": [
+    151643
+  ],
   "pad_token_id": 151643,
   "temperature": 0.6,
   "top_p": 0.95,

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4063875ab44841b5b9e89b6512782388e5a09a40182f73b3b4d92289c09be891
+oid sha256:881e0405a9463bd88293cd913673aa174b3f1f2dce1d0c587a3f817609456865
 size 3554214752

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ad85fddfd0c066756e452c5f3de99ac4c06e778d6db1a8c438765d1548d41a78
+oid sha256:4e5c0eb24ce25b866eb756ba2cfdbb5fcea4aef29550622de9bac93352cb0e93
 size 11345