metadata
library_name: transformers
license: apache-2.0
base_model: answerdotai/ModernBERT-base
tags:
- generated_from_trainer
metrics:
- accuracy
- f1
model-index:
- name: ModernBert_Swahili_News_Classification
results: []
ModernBert_Swahili_News_Classification
This model is a fine-tuned version of answerdotai/ModernBERT-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.6722
- Accuracy: 0.8670
- F1: 0.8739
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: 8
- eval_batch_size: 4
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 100
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
|---|---|---|---|---|---|
| 0.812 | 1.0 | 515 | 0.5333 | 0.7874 | 0.7784 |
| 0.4801 | 2.0 | 1030 | 0.4012 | 0.8544 | 0.8570 |
| 0.3646 | 3.0 | 1545 | 0.5835 | 0.8282 | 0.8250 |
| 0.272 | 4.0 | 2060 | 0.5662 | 0.8641 | 0.8682 |
| 0.165 | 5.0 | 2575 | 0.6722 | 0.8670 | 0.8739 |
Framework versions
- Transformers 4.52.3
- Pytorch 2.6.0+cu124
- Datasets 3.6.0
- Tokenizers 0.21.1