Model save

README.md

@@ -1,11 +1,8 @@
 ---
-base_model: Qwen/Qwen2.5-1.5B-Instruct
-datasets: Blancy/secondfiltered-math220k-difficulty_stratified_10k
 library_name: transformers
 model_name: Qwen2.5-1.5B-Open-R1-GRPO
 tags:
 - generated_from_trainer
-- open-r1
 - trl
 - grpo
 licence: license
@@ -13,7 +10,7 @@ licence: license
 
 # Model Card for Qwen2.5-1.5B-Open-R1-GRPO
 
-This model is a fine-tuned version of [Qwen/Qwen2.5-1.5B-Instruct](https://huggingface.co/Qwen/Qwen2.5-1.5B-Instruct) 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 [None](https://huggingface.co/None).
 It has been trained using [TRL](https://github.com/huggingface/trl).
 
 ## Quick start
@@ -29,7 +26,7 @@ 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/dexc0sil) 
+[<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/6b1srs5j) 
 
 
 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": 0.009060850272455024,
-    "train_runtime": 21549.2377,
+    "train_loss": 0.06767873773664092,
+    "train_runtime": 29303.3524,
     "train_samples": 10000,
-    "train_samples_per_second": 0.464,
-    "train_steps_per_second": 0.017
+    "train_samples_per_second": 0.341,
+    "train_steps_per_second": 0.012
 }

generation_config.json

@@ -1,14 +1,7 @@
 {
+  "_from_model_config": true,
   "bos_token_id": 151643,
-  "do_sample": true,
-  "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": "4.49.0"
+  "eos_token_id": 151645,
+  "transformers_version": "4.49.0",
+  "use_cache": false
 }

train_results.json

@@ -1,8 +1,8 @@
 {
     "total_flos": 0.0,
-    "train_loss": 0.009060850272455024,
-    "train_runtime": 21549.2377,
+    "train_loss": 0.06767873773664092,
+    "train_runtime": 29303.3524,
     "train_samples": 10000,
-    "train_samples_per_second": 0.464,
-    "train_steps_per_second": 0.017
+    "train_samples_per_second": 0.341,
+    "train_steps_per_second": 0.012
 }