Model save

README.md

@@ -1,11 +1,9 @@
 ---
 base_model: open-r1/Qwen2.5-Math-7B-RoPE-300k
-datasets: open-r1/Mixture-of-Thoughts
 library_name: transformers
 model_name: OpenR1-Distill-7B
 tags:
 - generated_from_trainer
-- open-r1
 - trl
 - sft
 licence: license
@@ -13,7 +11,7 @@ licence: license
 
 # Model Card for OpenR1-Distill-7B
 
-This model is a fine-tuned version of [open-r1/Qwen2.5-Math-7B-RoPE-300k](https://huggingface.co/open-r1/Qwen2.5-Math-7B-RoPE-300k) on the [open-r1/Mixture-of-Thoughts](https://huggingface.co/datasets/open-r1/Mixture-of-Thoughts) dataset.
+This model is a fine-tuned version of [open-r1/Qwen2.5-Math-7B-RoPE-300k](https://huggingface.co/open-r1/Qwen2.5-Math-7B-RoPE-300k).
 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/huggingface/open-r1/runs/5dap8z38) 
+[<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/huggingface/open-r1/runs/3wa69lj4) 
 
 
 This model was trained with SFT.

all_results.json

@@ -1,8 +1,8 @@
 {
-    "total_flos": 3.886169068471593e+20,
-    "train_loss": 0.5261877428531647,
-    "train_runtime": 254522.3147,
+    "total_flos": 3.879283297703449e+20,
+    "train_loss": 0.5371873642375808,
+    "train_runtime": 251254.6794,
     "train_samples": 349317,
-    "train_samples_per_second": 1.258,
+    "train_samples_per_second": 1.271,
     "train_steps_per_second": 0.01
 }

train_results.json

@@ -1,8 +1,8 @@
 {
-    "total_flos": 3.886169068471593e+20,
-    "train_loss": 0.5261877428531647,
-    "train_runtime": 254522.3147,
+    "total_flos": 3.879283297703449e+20,
+    "train_loss": 0.5371873642375808,
+    "train_runtime": 251254.6794,
     "train_samples": 349317,
-    "train_samples_per_second": 1.258,
+    "train_samples_per_second": 1.271,
     "train_steps_per_second": 0.01
 }