Model save

README.md

@@ -1,10 +1,8 @@
 ---
-datasets: AI-MO/NuminaMath-TIR
 library_name: transformers
 model_name: Qwen2.5-1.5B-Open-R1-GRPO
 tags:
 - generated_from_trainer
-- open-r1
 - trl
 - grpo
 licence: license
@@ -12,7 +10,7 @@ licence: license
 
 # Model Card for Qwen2.5-1.5B-Open-R1-GRPO
 
-This model is a fine-tuned version of [None](https://huggingface.co/None) on the [AI-MO/NuminaMath-TIR](https://huggingface.co/datasets/AI-MO/NuminaMath-TIR) 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
@@ -28,7 +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/cuiluyi/huggingface/runs/8umvas3o) 
+[<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/cuiluyi/huggingface/runs/9ncklfe9) 
 
 
 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

@@ -5,9 +5,9 @@
     "eval_samples_per_second": 1.392,
     "eval_steps_per_second": 0.042,
     "total_flos": 0.0,
-    "train_loss": 0.18781427145004273,
-    "train_runtime": 152.7747,
-    "train_samples": 40,
-    "train_samples_per_second": 0.262,
-    "train_steps_per_second": 0.033
+    "train_loss": 69.57985635299504,
+    "train_runtime": 92793.5148,
+    "train_samples": 20000,
+    "train_samples_per_second": 0.216,
+    "train_steps_per_second": 0.027
 }

config.json

@@ -23,7 +23,7 @@
   "tie_word_embeddings": true,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.49.0.dev0",
-  "use_cache": true,
+  "use_cache": false,
   "use_sliding_window": false,
   "vocab_size": 151936
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:85140787fcc657cace5b37093a9535d9427b0666a514fe9c745e6455c09faca1
+oid sha256:fe5ff90e6cc385072d340acef1773b13964d4a238238ef410f97ad4c110a1a5b
 size 3087467144

train_results.json

@@ -1,8 +1,8 @@
 {
     "total_flos": 0.0,
-    "train_loss": 0.18781427145004273,
-    "train_runtime": 152.7747,
-    "train_samples": 40,
-    "train_samples_per_second": 0.262,
-    "train_steps_per_second": 0.033
+    "train_loss": 69.57985635299504,
+    "train_runtime": 92793.5148,
+    "train_samples": 20000,
+    "train_samples_per_second": 0.216,
+    "train_steps_per_second": 0.027
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6ce21fa7f51fcb230442286fefccb28ee28a79722c0af571013ec9df6748336c
+oid sha256:5b9291bb657e667f701884084c5707bb15083f7408ef7e815b662545c1c37e5a
 size 7480