End of training

README.md

@@ -1,9 +1,11 @@
 ---
 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
@@ -11,7 +13,7 @@ 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).
+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.
 It has been trained using [TRL](https://github.com/huggingface/trl).
 
 ## Quick start

all_results.json

@@ -1,4 +1,9 @@
 {
+    "eval_loss": 0.05640460178256035,
+    "eval_runtime": 10.2046,
+    "eval_samples": 99,
+    "eval_samples_per_second": 9.702,
+    "eval_steps_per_second": 0.392,
     "total_flos": 0.0,
     "train_loss": 0.049734286265447736,
     "train_runtime": 1467.0643,

config.json

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

eval_results.json

@@ -0,0 +1,7 @@
+{
+    "eval_loss": 0.05640460178256035,
+    "eval_runtime": 10.2046,
+    "eval_samples": 99,
+    "eval_samples_per_second": 9.702,
+    "eval_steps_per_second": 0.392
+}