Update README.md

README.md

@@ -7,9 +7,9 @@ language:
 base_model: mistralai/Mistral-7B-v0.1
 pipeline_tag: text-generation
 ---
-# Model Card for a quick test model
+# zephyr-7b-sft-full-spin-iter1
 
-This model card aims a quick sanity check and will be updated with more info later.
+This model is a self-play fine-tuned model at iteration 1 from [alignment-handbook/zephyr-7b-sft-full](https://huggingface.co/alignment-handbook/zephyr-7b-sft-full) using synthetic data based on on the [HuggingFaceH4/ultrachat_200k](https://huggingface.co/datasets/HuggingFaceH4/ultrachat_200k) dataset.
 
 ## Model Details
 
@@ -18,4 +18,41 @@ This model card aims a quick sanity check and will be updated with more info lat
 - Model type: A 7B parameter GPT-like model fine-tuned on synthetic datasets.
 - Language(s) (NLP): Primarily English
 - License: MIT
-- Finetuned from model: mistralai/Mistral-7B-v0.1
+- Finetuned from model: alignment-handbook/zephyr-7b-sft-full (based on mistralai/Mistral-7B-v0.1)
+
+### Training hyperparameters
+The following hyperparameters were used during training:
+
+learning_rate: 5e-07
+train_batch_size: 8
+seed: 42
+distributed_type: multi-GPU
+num_devices: 8
+total_train_batch_size: 64
+optimizer: RMSProp 
+lr_scheduler_type: linear 
+lr_scheduler_warmup_ratio: 0.1
+num_epochs: 2.0
+
+## Citation
+```
+@misc{chen2024selfplay,
+      title={Self-Play Fine-Tuning Converts Weak Language Models to Strong Language Models}, 
+      author={Zixiang Chen and Yihe Deng and Huizhuo Yuan and Kaixuan Ji and Quanquan Gu},
+      year={2024},
+      eprint={2401.01335},
+      archivePrefix={arXiv},
+      primaryClass={cs.LG}
+}
+```
+
+# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
+| Metric                | Value                     |
+|-----------------------|---------------------------|
+| Avg.                  | 62.86   |
+| ARC (25-shot)         | 65.87          |
+| HellaSwag (10-shot)   | 85.44    |
+| MMLU (5-shot)         | 60.95         |
+| TruthfulQA (0-shot)   | 57.39   |
+| Winogrande (5-shot)   | 76.64   |
+| GSM8K (5-shot)        | 30.86        |