Model save

README.md

@@ -1,11 +1,9 @@
 ---
-base_model: Qwen/Qwen2.5-Math-1.5B
-datasets: Blancy/secondfiltered-math220k-difficulty_stratified_10k
+base_model: Qwen/Qwen3-1.7B
 library_name: transformers
 model_name: Qwen2.5-1.5B-Open-R1-GRPO
 tags:
 - generated_from_trainer
-- open-r1
 - trl
 - grpo
 licence: license
@@ -13,7 +11,7 @@ licence: license
 
 # Model Card for Qwen2.5-1.5B-Open-R1-GRPO
 
-This model is a fine-tuned version of [Qwen/Qwen2.5-Math-1.5B](https://huggingface.co/Qwen/Qwen2.5-Math-1.5B) on the [Blancy/secondfiltered-math220k-difficulty_stratified_10k](https://huggingface.co/datasets/Blancy/secondfiltered-math220k-difficulty_stratified_10k) dataset.
+This model is a fine-tuned version of [Qwen/Qwen3-1.7B](https://huggingface.co/Qwen/Qwen3-1.7B).
 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/224015062-chinese-university-of-hong-kong-shenzhen/huggingface/runs/o4fci5z3) 
+[<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/224015062-chinese-university-of-hong-kong-shenzhen/huggingface/runs/0lekld9d) 
 
 
 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).
@@ -37,7 +35,7 @@ This model was trained with GRPO, a method introduced in [DeepSeekMath: Pushing
 ### Framework versions
 
 - TRL: 0.15.2
-- Transformers: 4.49.0
+- Transformers: 4.52.3
 - Pytorch: 2.5.1
 - Datasets: 3.5.0
 - Tokenizers: 0.21.1

all_results.json

@@ -1,8 +1,8 @@
 {
     "total_flos": 0.0,
-    "train_loss": 0.14923175725754198,
-    "train_runtime": 53017.8845,
-    "train_samples": 10000,
-    "train_samples_per_second": 0.189,
-    "train_steps_per_second": 0.007
+    "train_loss": 0.06179468306791986,
+    "train_runtime": 15078.2099,
+    "train_samples": 1000,
+    "train_samples_per_second": 0.066,
+    "train_steps_per_second": 0.002
 }

generation_config.json

@@ -1,6 +1,13 @@
 {
   "bos_token_id": 151643,
-  "eos_token_id": 151643,
-  "max_new_tokens": 2048,
-  "transformers_version": "4.49.0"
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "temperature": 0.6,
+  "top_k": 20,
+  "top_p": 0.95,
+  "transformers_version": "4.52.3"
 }

train_results.json

@@ -1,8 +1,8 @@
 {
     "total_flos": 0.0,
-    "train_loss": 0.14923175725754198,
-    "train_runtime": 53017.8845,
-    "train_samples": 10000,
-    "train_samples_per_second": 0.189,
-    "train_steps_per_second": 0.007
+    "train_loss": 0.06179468306791986,
+    "train_runtime": 15078.2099,
+    "train_samples": 1000,
+    "train_samples_per_second": 0.066,
+    "train_steps_per_second": 0.002
 }