Model save

README.md

@@ -1,11 +1,9 @@
 ---
 base_model: Qwen/Qwen2.5-1.5B-Instruct
-datasets: HuggingFaceH4/Bespoke-Stratos-17k
 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 [HuggingFaceH4/Bespoke-Stratos-17k](https://huggingface.co/datasets/HuggingFaceH4/Bespoke-Stratos-17k) 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/jjh233/huggingface/runs/mt4uvcrz) 
+[<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/jjh233/huggingface/runs/l9e79305) 
 
 
 This model was trained with SFT.

all_results.json

@@ -4,10 +4,10 @@
     "eval_samples": 100,
     "eval_samples_per_second": 4.944,
     "eval_steps_per_second": 1.265,
-    "total_flos": 6.960985517882081e+17,
-    "train_loss": 0.8210960451450108,
-    "train_runtime": 16213.9925,
+    "total_flos": 65635690217472.0,
+    "train_loss": 0.7333491018714284,
+    "train_runtime": 2770.9424,
     "train_samples": 16610,
-    "train_samples_per_second": 1.334,
-    "train_steps_per_second": 0.083
+    "train_samples_per_second": 31.21,
+    "train_steps_per_second": 0.244
 }

train_results.json

@@ -1,8 +1,8 @@
 {
-    "total_flos": 6.960985517882081e+17,
-    "train_loss": 0.8210960451450108,
-    "train_runtime": 16213.9925,
+    "total_flos": 65635690217472.0,
+    "train_loss": 0.7333491018714284,
+    "train_runtime": 2770.9424,
     "train_samples": 16610,
-    "train_samples_per_second": 1.334,
-    "train_steps_per_second": 0.083
+    "train_samples_per_second": 31.21,
+    "train_steps_per_second": 0.244
 }