Model save

README.md

@@ -1,6 +1,5 @@
 ---
 base_model: CohenQu/llama3_3b-finemath-4plus-flexible-ordering.02.02_long
-datasets: HuggingFaceTB/smoltalk
 library_name: transformers
 model_name: sft_llama3_3b-finemath-4plus-flexible-ordering.02.02_long-40000_numina-cot-100k_orchard
 tags:
@@ -12,7 +11,7 @@ licence: license
 
 # Model Card for sft_llama3_3b-finemath-4plus-flexible-ordering.02.02_long-40000_numina-cot-100k_orchard
 
-This model is a fine-tuned version of [CohenQu/llama3_3b-finemath-4plus-flexible-ordering.02.02_long](https://huggingface.co/CohenQu/llama3_3b-finemath-4plus-flexible-ordering.02.02_long) on the [HuggingFaceTB/smoltalk](https://huggingface.co/datasets/HuggingFaceTB/smoltalk) dataset.
+This model is a fine-tuned version of [CohenQu/llama3_3b-finemath-4plus-flexible-ordering.02.02_long](https://huggingface.co/CohenQu/llama3_3b-finemath-4plus-flexible-ordering.02.02_long).
 It has been trained using [TRL](https://github.com/huggingface/trl).
 
 ## Quick start
@@ -28,7 +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/yuxiao98/flexible-ordering/runs/x7ic5dzg) 
+[<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/yuxiao98/flexible-ordering/runs/cm90biec) 
 
 
 This model was trained with SFT.

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:13ba708645c7f09ebbf5757c26f5037a57177a8c41036eafc6e88c288877daea
+oid sha256:426d224d8c6126edfc9103a1d2fe3b1520faee53a505c7223396c884796c9507
 size 6072