|
--- |
|
base_model: JunxiongWang/mamba_0_875_sft |
|
tags: |
|
- mamba |
|
- alignment-handbook |
|
- generated_from_trainer |
|
datasets: |
|
- HuggingFaceH4/ultrafeedback_binarized |
|
model-index: |
|
- name: mamba_0_875_dpo_ep1 |
|
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. --> |
|
|
|
# mamba_0_875_dpo_ep1 |
|
|
|
This model is a fine-tuned version of [JunxiongWang/mamba_0_875_sft](https://huggingface.co/JunxiongWang/mamba_0_875_sft) 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 |
|
|
|
### Training hyperparameters |
|
|
|
The following hyperparameters were used during training: |
|
- learning_rate: 5e-07 |
|
- train_batch_size: 4 |
|
- eval_batch_size: 8 |
|
- seed: 42 |
|
- distributed_type: multi-GPU |
|
- num_devices: 8 |
|
- total_train_batch_size: 32 |
|
- 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 4.41.2 |
|
- Pytorch 2.1.0+cu118 |
|
- Datasets 2.20.0 |
|
- Tokenizers 0.19.1 |
|
|
|
[MambaInLlama](arxiv.org/abs/2408.15237) |
|
|
|
``` |
|
@article{junxiongdaniele2024mambainllama, |
|
title = {The Mamba in the Llama: Distilling and Accelerating Hybrid Models}, |
|
author = {Junxiong Wang and Daniele Paliotta and Avner May and Alexander M. Rush and Tri Dao}, |
|
journal = {arXiv preprint arXiv:2408.15237}, |
|
year = {2024} |
|
} |
|
``` |
