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-Distill
 tags:
 - generated_from_trainer
-- open-r1
 - trl
 - sft
 licence: license
@@ -13,7 +11,7 @@ licence: license
 
 # Model Card for Qwen2.5-1.5B-Open-R1-Distill
 
-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

all_results.json

@@ -1,8 +1,8 @@
 {
-    "total_flos": 5026145964392448.0,
-    "train_loss": 0.41604289600059846,
-    "train_runtime": 88628.0241,
+    "total_flos": 5731176614461440.0,
+    "train_loss": 0.4375836861247418,
+    "train_runtime": 77494.5958,
     "train_samples": 93733,
-    "train_samples_per_second": 5.288,
-    "train_steps_per_second": 0.083
+    "train_samples_per_second": 6.048,
+    "train_steps_per_second": 0.047
 }

train_results.json

@@ -1,8 +1,8 @@
 {
-    "total_flos": 5026145964392448.0,
-    "train_loss": 0.41604289600059846,
-    "train_runtime": 88628.0241,
+    "total_flos": 5731176614461440.0,
+    "train_loss": 0.4375836861247418,
+    "train_runtime": 77494.5958,
     "train_samples": 93733,
-    "train_samples_per_second": 5.288,
-    "train_steps_per_second": 0.083
+    "train_samples_per_second": 6.048,
+    "train_steps_per_second": 0.047
 }