End of training

README.md

@@ -1,14 +1,16 @@
 ---
+datasets: HuggingFaceH4/Bespoke-Stratos-17k
 library_name: transformers
 model_name: Qwen2.5-1.5B-Open-R1-Distill
 tags:
 - generated_from_trainer
+- open-r1
 licence: license
 ---
 
 # Model Card for Qwen2.5-1.5B-Open-R1-Distill
 
-This model is a fine-tuned version of [None](https://huggingface.co/None).
+This model is a fine-tuned version of [None](https://huggingface.co/None) on the [HuggingFaceH4/Bespoke-Stratos-17k](https://huggingface.co/datasets/HuggingFaceH4/Bespoke-Stratos-17k) dataset.
 It has been trained using [TRL](https://github.com/huggingface/trl).
 
 ## Quick start

all_results.json

@@ -1,4 +1,9 @@
 {
+    "eval_loss": 0.8818749785423279,
+    "eval_runtime": 22.8006,
+    "eval_samples": 100,
+    "eval_samples_per_second": 4.386,
+    "eval_steps_per_second": 0.57,
     "total_flos": 0.0,
     "train_loss": 0.8600422314672648,
     "train_runtime": 45916.2025,

eval_results.json

@@ -1,7 +1,7 @@
 {
-    "eval_loss": 0.9327651262283325,
-    "eval_runtime": 8.8796,
+    "eval_loss": 0.8818749785423279,
+    "eval_runtime": 22.8006,
     "eval_samples": 100,
-    "eval_samples_per_second": 7.433,
-    "eval_steps_per_second": 0.563
+    "eval_samples_per_second": 4.386,
+    "eval_steps_per_second": 0.57
 }