Update README.md

README.md

@@ -1,19 +1,15 @@
 ---
 license: mit
-base_model: ZhangShenao/0.001_2SELM_Zephyr_iter_2
+base_model: ZhangShenao/SELM-Zephyr-7B-iter-1
 tags:
 - alignment-handbook
-- trl
 - dpo
-- generated_from_trainer
 - trl
-- dpo
-- generated_from_trainer
+- selm
 datasets:
-- updated
-- original
+- HuggingFaceH4/ultrafeedback_binarized
 model-index:
-- name: 0.001_2SELM_Zephyr_iter_3
+- name: SELM-Zephyr-7B-iter-2
   results: []
 ---
 
@@ -22,26 +18,18 @@ should probably proofread and complete it, then remove this comment. -->
 
 # 0.001_2SELM_Zephyr_iter_3
 
-This model is a fine-tuned version of [ZhangShenao/0.001_2SELM_Zephyr_iter_2](https://huggingface.co/ZhangShenao/0.001_2SELM_Zephyr_iter_2) on the updated and the original datasets.
+This model is a fine-tuned version of [ZhangShenao/SELM-Zephyr-7B-iter-1](https://huggingface.co/ZhangShenao/SELM-Zephyr-7B-iter-1) using synthetic data based on on the HuggingFaceH4/ultrafeedback_binarized dataset.
 
 ## Model description
 
-More information needed
-
-## Intended uses & limitations
-
-More information needed
-
-## Training and evaluation data
-
-More information needed
-
-## Training procedure
+- Model type: A 7B parameter Zephyr-based Self-Exploring Language Models (SELM).
+- Language(s) (NLP): Primarily English
+- License: MIT
 
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 5e-07
+- alpha: 0.001
 - train_batch_size: 8
 - eval_batch_size: 8
 - seed: 42
@@ -55,9 +43,13 @@ The following hyperparameters were used during training:
 - lr_scheduler_warmup_ratio: 0.1
 - num_epochs: 1
 
-### Training results
-
+## Results
 
+| AlpacaEval 2.0 (LC Win Rate)                | MT-Bench (Average)                   |
+|---------------------------|---------------|
+SELM-Zephyr-7B-iter-3 (https://huggingface.co/ZhangShenao/SELM-Zephyr-7B-iter-3)   24.00    7.48  |
+SELM-Zephyr-7B-iter-2 (https://huggingface.co/ZhangShenao/SELM-Zephyr-7B-iter-2)   23.40    7.72  |
+SELM-Zephyr-7B-iter-1 (https://huggingface.co/ZhangShenao/SELM-Zephyr-7B-iter-1)   20.28    -  |
 
 ### Framework versions