Downloads · 30 days
4
16% of all-time downloads
afri-berta-tigrigna
Elu-dan/afri-berta-tigrigna
afri-berta-tigrigna is a token classification model from Elu-dan. Use it when you need labels on individual words, such as names. It is set up for transformers.
should probably proofread and complete it, then remove this comment. --
All-time downloads
25
Public
Parameters
111M
445 MB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors444 MB · 99%
At a glance
- Task
- Token Classification
- Library
- transformers
- Model type
- xlm-roberta
- Access
- Public
- Created
- Jun 21, 2025
- Updated
- Jun 21, 2025
- SHA
- 1d977757
Try a prompt
Base models
Model card
From the Hugging Face model README
<!-- 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. -->
afri-berta-tigrigna
This model is a fine-tuned version of castorini/afriberta_base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.1654
- Precision: 0.7259
- Recall: 0.7586
- F1: 0.7419
- Accuracy: 0.9538
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: 2e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| 0.1746 | 1.0 | 286 | 0.1831 | 0.6558 | 0.6617 | 0.6587 | 0.9408 |
| 0.1317 | 2.0 | 572 | 0.1671 | 0.6651 | 0.7194 | 0.6912 | 0.9445 |
| 0.1011 | 3.0 | 858 | 0.1604 | 0.7133 | 0.7254 | 0.7193 | 0.9507 |
| 0.0833 | 4.0 | 1144 | 0.1679 | 0.7046 | 0.7572 | 0.7300 | 0.9514 |
| 0.059 | 5.0 | 1430 | 0.1681 | 0.7185 | 0.7592 | 0.7383 | 0.9528 |
Framework versions
- Transformers 4.52.4
- Pytorch 2.6.0+cu124
- Datasets 2.14.4
- Tokenizers 0.21.1
- Task
- Token Classification
- Library
- transformers
- Type
- xlm-roberta
- Created
- Jun 21, 2025
- Updated
- Jun 21, 2025