Model save

README.md

@@ -1,11 +1,9 @@
 ---
-base_model: Qwen/Qwen2.5-1.5B-Instruct
-datasets: AI-MO/NuminaMath-TIR
+base_model: deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B
 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/Qwen2.5-1.5B-Instruct](https://huggingface.co/Qwen/Qwen2.5-1.5B-Instruct) on the [AI-MO/NuminaMath-TIR](https://huggingface.co/datasets/AI-MO/NuminaMath-TIR) 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/tumei-srcb/huggingface/runs/xl3jic9e) 
+[<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/tumei-srcb/huggingface/runs/fv2zx1t7) 
 
 
 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

@@ -1,13 +1,8 @@
 {
-    "eval_loss": 0.04973834753036499,
-    "eval_runtime": 50.7229,
-    "eval_samples": 99,
-    "eval_samples_per_second": 1.952,
-    "eval_steps_per_second": 0.02,
     "total_flos": 0.0,
-    "train_loss": 8.08613164653672,
-    "train_runtime": 45851.9446,
+    "train_loss": 0.07406271367912713,
+    "train_runtime": 428031.3102,
     "train_samples": 72441,
-    "train_samples_per_second": 1.58,
-    "train_steps_per_second": 0.006
+    "train_samples_per_second": 0.169,
+    "train_steps_per_second": 0.005
 }

generation_config.json

@@ -1,14 +1,9 @@
 {
-  "bos_token_id": 151643,
+  "_from_model_config": true,
+  "bos_token_id": 151646,
   "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,
+  "eos_token_id": 151643,
+  "temperature": 0.6,
+  "top_p": 0.95,
   "transformers_version": "4.49.0.dev0"
 }

train_results.json

@@ -1,8 +1,8 @@
 {
     "total_flos": 0.0,
-    "train_loss": 8.08613164653672,
-    "train_runtime": 45851.9446,
+    "train_loss": 0.07406271367912713,
+    "train_runtime": 428031.3102,
     "train_samples": 72441,
-    "train_samples_per_second": 1.58,
-    "train_steps_per_second": 0.006
+    "train_samples_per_second": 0.169,
+    "train_steps_per_second": 0.005
 }