Update README.md

README.md

@@ -1,47 +1,46 @@
 ---
 license: mit
-base_model: ZhangShenao/0.001_2SELM_Zephyr_iter_1
+base_model: ZhangShenao/DPO-Zephyr-7B
 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_2
+- name: SELM-Zephyr-7B-iter-1
   results: []
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 should probably proofread and complete it, then remove this comment. -->
 
-# 0.001_2SELM_Zephyr_iter_2
-
-This model is a fine-tuned version of [ZhangShenao/0.001_2SELM_Zephyr_iter_1](https://huggingface.co/ZhangShenao/0.001_2SELM_Zephyr_iter_1) on the updated and the original datasets.
-
-## Model description
+Self-Exploring Language Models: Active Preference Elicitation for Online Alignment.
 
-More information needed
+# SELM-Zephyr-7B-iter-1
 
-## Intended uses & limitations
+This model is a fine-tuned version of [ZhangShenao/DPO-Zephyr-7B](https://huggingface.co/ZhangShenao/DPO-Zephyr-7B) using synthetic data based on on the HuggingFaceH4/ultrafeedback_binarized dataset.
 
-More information needed
+## Model description
 
-## Training and evaluation data
+- Model type: A 7B parameter Zephyr-based Self-Exploring Language Models (SELM).
+- License: MIT
 
-More information needed
+## Results
 
-## Training procedure
+|                                        | AlpacaEval 2.0 (LC WR) | MT-Bench (Average) |
+|----------------------------------------|------------------------|--------------------|
+| [SELM-Zephyr-7B-iter-3](https://huggingface.co/ZhangShenao/SELM-Zephyr-7B-iter-3) |     &emsp; &emsp; &emsp;&emsp;        24.00         |  &emsp; &emsp; &emsp;         7.48       |
+| [SELM-Zephyr-7B-iter-2](https://huggingface.co/ZhangShenao/SELM-Zephyr-7B-iter-2) |    &emsp; &emsp; &emsp;&emsp;         23.40         |  &emsp; &emsp; &emsp;         7.72       |
+| [SELM-Zephyr-7B-iter-1](https://huggingface.co/ZhangShenao/SELM-Zephyr-7B-iter-1) |    &emsp; &emsp; &emsp;&emsp;         20.28         |  &emsp; &emsp; &emsp;         7.42       |
+| [DPO-Zephyr-7B](https://huggingface.co/ZhangShenao/DPO-Zephyr-7B) |    &emsp; &emsp; &emsp;&emsp;         14.45         |  &emsp; &emsp; &emsp;        7.28        |
 
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 5e-07
+- alpha: 0.001
+- beta: 0.01
 - train_batch_size: 8
 - eval_batch_size: 8
 - seed: 42
@@ -49,16 +48,9 @@ The following hyperparameters were used during training:
 - num_devices: 8
 - gradient_accumulation_steps: 4
 - total_train_batch_size: 256
-- total_eval_batch_size: 64
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
-- lr_scheduler_type: cosine
-- lr_scheduler_warmup_ratio: 0.1
 - num_epochs: 1
 
-### Training results
-
-
-
 ### Framework versions
 
 - Transformers 4.40.2