Model save

README.md

@@ -1,11 +1,9 @@
 ---
 base_model: Qwen/Qwen2.5-1.5B-Instruct
-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
@@ -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 [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/cool_research/huggingface/runs/thbka916) 
+[<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/cool_research/huggingface/runs/lflxos4b) 
 
 
 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": 3.423,
     "eval_steps_per_second": 0.138,
     "total_flos": 0.0,
-    "train_loss": 3.155133654368477,
-    "train_runtime": 37019.9061,
+    "train_loss": 27.60521244561175,
+    "train_runtime": 16907.8148,
     "train_samples": 72441,
-    "train_samples_per_second": 1.957,
-    "train_steps_per_second": 0.017
+    "train_samples_per_second": 4.284,
+    "train_steps_per_second": 0.038
 }

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 sha256:60e2d5ab8ef1619f8e3a496d5f75c868a2df9ff2dd918566582c889603f7a631
+oid sha256:2d95d69c9e3057893916b71e2f2b6bb10502be13bd41fc36df510535ed5d26a9
 size 3087467144

train_results.json

@@ -1,8 +1,8 @@
 {
     "total_flos": 0.0,
-    "train_loss": 3.155133654368477,
-    "train_runtime": 37019.9061,
+    "train_loss": 27.60521244561175,
+    "train_runtime": 16907.8148,
     "train_samples": 72441,
-    "train_samples_per_second": 1.957,
-    "train_steps_per_second": 0.017
+    "train_samples_per_second": 4.284,
+    "train_steps_per_second": 0.038
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5e937fb58e271bdbe82314a46d509b39ec894311a1f62a38fd2628d962720b86
+oid sha256:3052fc42194c87c66393e2fa10e2869b4fa094d39fdc42958dff7155a9650c61
 size 7480