mamba_text_classification

<!-- 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_text_classification

This model was trained from scratch on IMDB dataset. It achieves the following results on the evaluation set:

• Loss: 0.2454
• Accuracy: 0.932

Installation

conda create -n mamba_env python=3.10

conda activate mamba_env

pip install torch torchvision --extra-index-url https://download.pytorch.org/whl/cu122
pip install 'causal-conv1d>=1.4.0'
pip install mamba-ssm==2.2.1
pip install datasets scikit-learn

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-05
• train_batch_size: 4
• eval_batch_size: 16
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: cosine
• lr_scheduler_warmup_ratio: 0.01
• num_epochs: 1

Training results

Framework versions

• Transformers 4.45.1
• Pytorch 2.4.1+cu121
• Datasets 3.0.1
• Tokenizers 0.20.0