mamba_0_5_dpo_ep1 / README.md
JunxiongWang's picture
Update README.md
1bf7360 verified
metadata
base_model: JunxiongWang/mamba_0_5_sft
tags:
  - mamba
  - alignment-handbook
  - generated_from_trainer
datasets:
  - HuggingFaceH4/ultrafeedback_binarized
model-index:
  - name: mamba_0_5_dpo_ep1
    results: []

Please check here for details.

mamba_0_5_dpo_ep1

This model is a fine-tuned version of JunxiongWang/mamba_0_5_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

@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}
}