metadata
license: mit
base_model: ZhangShenao/SELM-Phi-3-mini-4k-instruct-iter-2
tags:
- alignment-handbook
- dpo
- trl
- selm
datasets:
- HuggingFaceH4/ultrafeedback_binarized
model-index:
- name: SELM-Phi-3-mini-4k-instruct-iter-3
results: []
Self-Exploring Language Models: Active Preference Elicitation for Online Alignment.
SELM-Phi-3-mini-4k-instruct-iter-3
This model is a fine-tuned version of ZhangShenao/SELM-Phi-3-mini-4k-instruct-iter-2 using synthetic data based on on the HuggingFaceH4/ultrafeedback_binarized dataset.
Model description
- Model type: A 3.8B parameter Phi3-instruct-based Self-Exploring Language Models (SELM).
- License: MIT
Results
AlpacaEval 2.0 (LC WR) | MT-Bench (Average) | |
---|---|---|
SELM-Phi-3-mini-4k-instruct-iter-3 | β β ββ 27.98 | β β β 8.32 |
SELM-Phi-3-mini-4k-instruct-iter-2 | β β ββ 26.79 | β β β 8.44 |
SELM-Phi-3-mini-4k-instruct-iter-1 | β β ββ 27.33 | β β β 8.37 |
Phi-3-mini-4k-instruct | β β ββ 23.05 | β β β 8.12 |
Training hyperparameters
The following hyperparameters were used during training:
- alpha: 0.001
- beta: 0.01
- train_batch_size: 4
- seed: 42
- distributed_type: multi-GPU
- num_devices: 8
- gradient_accumulation_steps: 4
- total_train_batch_size: 128
- 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