Model save

README.md

@@ -1,11 +1,9 @@
 ---
-base_model: coolcui/DeepSeek-R1-Distill-Qwen-1.5B-GRPO
-datasets: chansung/verifiable-coding-problems-python
+base_model: Qwen/Qwen2.5-1.5B-Instruct
 library_name: transformers
 model_name: Qwen2.5-1.5B-CCRL-1
 tags:
 - generated_from_trainer
-- open-r1
 - trl
 - grpo
 licence: license
@@ -13,7 +11,7 @@ licence: license
 
 # Model Card for Qwen2.5-1.5B-CCRL-1
 
-This model is a fine-tuned version of [coolcui/DeepSeek-R1-Distill-Qwen-1.5B-GRPO](https://huggingface.co/coolcui/DeepSeek-R1-Distill-Qwen-1.5B-GRPO) on the [chansung/verifiable-coding-problems-python](https://huggingface.co/datasets/chansung/verifiable-coding-problems-python) dataset.
+This model is a fine-tuned version of [Qwen/Qwen2.5-1.5B-Instruct](https://huggingface.co/Qwen/Qwen2.5-1.5B-Instruct).
 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/chansung18/huggingface/runs/oyhi6d8w) 
+[<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/chansung18/huggingface/runs/d5cg4az4) 
 
 
 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).

all_results.json

@@ -1,8 +1,8 @@
 {
     "total_flos": 0.0,
-    "train_loss": 0.0,
-    "train_runtime": 295.3751,
+    "train_loss": 0.010024200768093579,
+    "train_runtime": 35564.3846,
     "train_samples": 949,
-    "train_samples_per_second": 21.667,
-    "train_steps_per_second": 0.169
+    "train_samples_per_second": 0.72,
+    "train_steps_per_second": 0.006
 }

generation_config.json

@@ -1,9 +1,14 @@
 {
-  "_from_model_config": true,
-  "bos_token_id": 151646,
+  "bos_token_id": 151643,
   "do_sample": true,
-  "eos_token_id": 151643,
-  "temperature": 0.6,
-  "top_p": 0.95,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "repetition_penalty": 1.1,
+  "temperature": 0.7,
+  "top_k": 20,
+  "top_p": 0.8,
   "transformers_version": "4.50.0"
 }

train_results.json

@@ -1,8 +1,8 @@
 {
     "total_flos": 0.0,
-    "train_loss": 0.0,
-    "train_runtime": 295.3751,
+    "train_loss": 0.010024200768093579,
+    "train_runtime": 35564.3846,
     "train_samples": 949,
-    "train_samples_per_second": 21.667,
-    "train_steps_per_second": 0.169
+    "train_samples_per_second": 0.72,
+    "train_steps_per_second": 0.006
 }