Downloads · 30 days
8
27% of all-time downloads
afro-xlmr-base-swa-MICRO
sercetexam9/afro-xlmr-base-swa-MICRO
afro-xlmr-base-swa-MICRO is a text classification model from sercetexam9. Use it when you need a label for a piece of text. It is set up for transformers. The card lists the license as mit.
should probably proofread and complete it, then remove this comment. --
All-time downloads
30
Public
Parameters
278M
11.1 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors1.1 GB · 98%
At a glance
- Task
- Text Classification
- Library
- transformers
- License
- mit
- Model type
- xlm-roberta
- Access
- Public
- Created
- Jan 31, 2025
- Updated
- Jan 31, 2025
- SHA
- 9a744a4c
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. -->
afro-xlmr-base-swa-MICRO
This model is a fine-tuned version of Davlan/afro-xlmr-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.4736
- F1: 0.3374
- Roc Auc: 0.6294
- Accuracy: 0.5186
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: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 100
- num_epochs: 20
Training results
| Training Loss | Epoch | Step | Validation Loss | F1 | Roc Auc | Accuracy |
|---|---|---|---|---|---|---|
| 0.2025 | 1.0 | 863 | 0.2450 | 0.2098 | 0.5611 | 0.5431 |
| 0.1567 | 2.0 | 1726 | 0.2529 | 0.2813 | 0.5946 | 0.5304 |
| 0.0859 | 3.0 | 2589 | 0.3181 | 0.3301 | 0.6296 | 0.5005 |
| 0.0479 | 4.0 | 3452 | 0.3607 | 0.3040 | 0.6095 | 0.5113 |
| 0.0306 | 5.0 | 4315 | 0.4196 | 0.3085 | 0.6148 | 0.4941 |
| 0.0273 | 6.0 | 5178 | 0.4736 | 0.3374 | 0.6294 | 0.5186 |
| 0.0141 | 7.0 | 6041 | 0.5191 | 0.3296 | 0.6255 | 0.5150 |
| 0.0125 | 8.0 | 6904 | 0.5558 | 0.3158 | 0.6157 | 0.5168 |
| 0.0028 | 9.0 | 7767 | 0.5914 | 0.3214 | 0.6175 | 0.5177 |
| 0.0082 | 10.0 | 8630 | 0.6335 | 0.3248 | 0.6233 | 0.5041 |
Framework versions
- Transformers 4.45.1
- Pytorch 2.4.0
- Datasets 3.0.1
- Tokenizers 0.20.0
- Task
- Text Classification
- Library
- transformers
- Type
- xlm-roberta
- License
- mit
- Created
- Jan 31, 2025
- Updated
- Jan 31, 2025