Downloads · 30 days
6
13% of all-time downloads
Swahili-Classifier-cola
Mahloromela/Swahili-Classifier-cola
Swahili-Classifier-cola is a text classification model from Mahloromela. Use it when you need a label for a piece of text. It is set up for transformers.
should probably proofread and complete it, then remove this comment. --
All-time downloads
48
Public
Parameters
83.1M
5 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors332 MB · 98%
At a glance
- Task
- Text Classification
- Library
- transformers
- Model type
- xlm-roberta
- Access
- Public
- Created
- Oct 23, 2024
- Updated
- Oct 24, 2024
- SHA
- b409e83f
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. -->
Swahili-Classifier-cola
This model is a fine-tuned version of Mahloromela/Afriberta-Swahili-mlm_model on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.2529
- Accuracy: 0.9239
- Precision: 0.9072
- Recall: 0.9286
- F1: 0.9178
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: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 |
|---|---|---|---|---|---|---|---|
| 0.2814 | 1.0 | 1111 | 0.2625 | 0.9192 | 0.8940 | 0.9340 | 0.9136 |
| 0.2163 | 2.0 | 2222 | 0.2529 | 0.9239 | 0.9072 | 0.9286 | 0.9178 |
| 0.1654 | 3.0 | 3333 | 0.3101 | 0.9171 | 0.8809 | 0.9468 | 0.9127 |
| 0.1155 | 4.0 | 4444 | 0.3601 | 0.9142 | 0.9117 | 0.8996 | 0.9056 |
| 0.0844 | 5.0 | 5555 | 0.4159 | 0.9104 | 0.9000 | 0.9045 | 0.9023 |
Framework versions
- Transformers 4.44.2
- Pytorch 2.5.0+cu121
- Datasets 3.0.2
- Tokenizers 0.19.1
- Task
- Text Classification
- Library
- transformers
- Type
- xlm-roberta
- Created
- Oct 23, 2024
- Updated
- Oct 24, 2024