Training in progress, step 147

README.md

@@ -1,19 +1,17 @@
 ---
 base_model: deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B
-datasets: open-r1/OpenR1-Math-220k
 library_name: transformers
 model_name: DeepSeek-R1-Distill-Qwen-1.5B-GRPO
 tags:
 - generated_from_trainer
-- open-r1
-- trl
 - grpo
+- trl
 licence: license
 ---
 
 # Model Card for DeepSeek-R1-Distill-Qwen-1.5B-GRPO
 
-This model is a fine-tuned version of [deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B](https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B) on the [open-r1/OpenR1-Math-220k](https://huggingface.co/datasets/open-r1/OpenR1-Math-220k) dataset.
+This model is a fine-tuned version of [deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B](https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B).
 It has been trained using [TRL](https://github.com/huggingface/trl).
 
 ## Quick start
@@ -29,7 +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/garipovroma/huggingface/runs/open-r1-reprod) 
+[<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/garipovroma/huggingface/runs/acc_only_reward) 
 
 
 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).

config.json

@@ -22,7 +22,7 @@
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.52.3",
-  "use_cache": true,
+  "use_cache": false,
   "use_mrope": false,
   "use_sliding_window": false,
   "vocab_size": 151936

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0e7fdc66c057a938cb3488d1ecf9b30182e19c1e2d410070768f2e7a0b0fdb7e
+oid sha256:ee88924eb78329c2faa42b47ebfa9c3d1ccde655ccfabe083d9600fe90e15a2b
 size 3554214752

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cd598e9ac9f767548cf0ed026604f8f7d1dce79ad58249f9c4f01ba0d28167fc
+oid sha256:d6fbb8bfd7b5a1d54960dec715009aa357138f26a72168769bdb65abf4bbcb07
 size 10808