Training in progress, epoch 1

README.md

@@ -4,8 +4,8 @@ library_name: transformers
 model_name: DeepSeek-R1-Distill-Qwen-1.5B-long-context-Staged-3
 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/fc57hsig) 
+[<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/246b2vud) 
 
 
 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 sha256:24723cb3f5b2365983a353f0e7e2aeeafaa08c81df5ce9ded6e10419997f3085
+oid sha256:bc1ca87990fea1040e6374dc3acff06b3c664e3a7a53aabccea686427d19a9fd
 size 3554214752

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cf629971546ff57c827d1dc5f8fbbd35af06ee5ef708fd8b13a1c5f9803362c8
-size 9233
+oid sha256:005a59a0b64fd8a0ed463b7f69afe9cd2012acff88ad0242bf219752b4c93551
+size 11409