Model save

README.md

@@ -1,11 +1,9 @@
 ---
 base_model: Qwen/Qwen2.5-1.5B-Instruct
-datasets: open-r1/OpenR1-Math-220k
 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 [open-r1/OpenR1-Math-220k](https://huggingface.co/datasets/open-r1/OpenR1-Math-220k) 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/yuzhao/huggingface/runs/w8qxsdmi) 
+[<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/yuzhao/huggingface/runs/4s6qznff) 
 
 
 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": 1.2128,
+    "train_runtime": 1.2538,
     "train_samples": 8000,
-    "train_samples_per_second": 6596.084,
-    "train_steps_per_second": 549.124
+    "train_samples_per_second": 6380.488,
+    "train_steps_per_second": 531.176
 }

config.json

@@ -22,7 +22,7 @@
   "tie_word_embeddings": true,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.51.2",
-  "use_cache": true,
+  "use_cache": false,
   "use_sliding_window": false,
   "vocab_size": 151936
 }

train_results.json

@@ -1,8 +1,8 @@
 {
     "total_flos": 0.0,
     "train_loss": 0.0,
-    "train_runtime": 1.2128,
+    "train_runtime": 1.2538,
     "train_samples": 8000,
-    "train_samples_per_second": 6596.084,
-    "train_steps_per_second": 549.124
+    "train_samples_per_second": 6380.488,
+    "train_steps_per_second": 531.176
 }

trainer_state.json

@@ -17996,9 +17996,9 @@
       "step": 666,
       "total_flos": 0.0,
       "train_loss": 0.0,
-      "train_runtime": 1.2128,
-      "train_samples_per_second": 6596.084,
-      "train_steps_per_second": 549.124
+      "train_runtime": 1.2538,
+      "train_samples_per_second": 6380.488,
+      "train_steps_per_second": 531.176
     }
   ],
   "logging_steps": 1,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4304b77281afaab7e91d8dbeab625a8c3e81e715223fcee23b0d527a2ac3d848
+oid sha256:79a6bbc9ef71a3349cad0494254594b09b474e70678cf8ad7d44af9a7a0658cd
 size 8440