vubacktracking/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: 0.1901
• Accuracy: 0.9536

It achieves the following results on the evaluation set:

• Loss: 0.1981
• Accuracy: 0.94

Model description

Mamba model for text classification

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

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.0205	0.1	625	0.2462	0.928
0.671	0.2	1250	0.1958	0.9408
0.5961	0.3	1875	0.2661	0.9344
0.0167	0.4	2500	0.2171	0.9412
0.0007	0.5	3125	0.2095	0.9448
2.6807	0.6	3750	0.1888	0.9492
0.0155	0.7	4375	0.2249	0.95
0.0021	0.8	5000	0.1991	0.9528
0.0134	0.9	5625	0.1920	0.9524
0.1525	1.0	6250	0.1901	0.9536

Framework versions

• Transformers 4.40.0
• Pytorch 2.2.1+cu121
• Datasets 2.19.0
• Tokenizers 0.19.1