trinhxuankhai/mamba_text_classification

Mamba for Text Classification

This model was trained from scratch on IMDB dataset.

It achieves the following results on the evaluation set:

• Loss: 0.1696
• Accuracy: 0.94

It achieves the following results on the test set:

• Loss: 0.2068
• Accuracy: 0.94

Notebook

Detail on model and training code on colab.

Model description

Mamba model for text classification.

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

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.0128	0.1	625	0.3829	0.892
0.0087	0.2	1250	0.2733	0.912
0.1729	0.3	1875	0.1913	0.932
0.111	0.4	2500	0.2025	0.928
0.0007	0.5	3125	0.1799	0.944
0.0184	0.6	3750	0.1754	0.94
1.5296	0.7	4375	0.2080	0.928
0.0005	0.8	5000	0.1859	0.936
0.0011	0.9	5625	0.1664	0.944
0.0006	1.0	6250	0.1696	0.94

Framework versions

• Transformers 4.35.2
• Pytorch 2.1.0+cu121
• Datasets 2.17.0
• Tokenizers 0.15.2