ZhangShenao's picture
Update README.md
a8d656c verified
metadata
license: mit
base_model: ZhangShenao/SELM-Zephyr-7B-iter-2
tags:
  - alignment-handbook
  - dpo
  - trl
  - selm
datasets:
  - HuggingFaceH4/ultrafeedback_binarized
model-index:
  - name: SELM-Zephyr-7B-iter-3
    results: []

Self-Exploring Language Models: Active Preference Elicitation for Online Alignment.

SELM-Zephyr-7B-iter-3

This model is a fine-tuned version of ZhangShenao/SELM-Zephyr-7B-iter-2 using synthetic data based on on the HuggingFaceH4/ultrafeedback_binarized dataset.

Model description

  • Model type: A 7B parameter Zephyr-based Self-Exploring Language Models (SELM).
  • License: MIT

Results

AlpacaEval 2.0 (LC WR) MT-Bench (Average)
SELM-Zephyr-7B-iter-3        24.00       7.48
SELM-Zephyr-7B-iter-2        23.40       7.72
SELM-Zephyr-7B-iter-1        20.28       7.42
DPO-Zephyr-7B        14.45       7.28

Our model also ranks highly on WildBench! πŸ”₯

Training hyperparameters

The following hyperparameters were used during training:

  • alpha: 0.001
  • beta: 0.01
  • train_batch_size: 8
  • seed: 42
  • distributed_type: multi-GPU
  • num_devices: 8
  • gradient_accumulation_steps: 4
  • total_train_batch_size: 256
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • num_epochs: 1

Framework versions

  • Transformers 4.40.2
  • Pytorch 2.1.2+cu121
  • Datasets 2.14.6
  • Tokenizers 0.19.1