<!-- 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-igbo-2e-5
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: 0.2264
- Precision: 0.7551
- Recall: 0.5122
- F1: 0.6104
- Accuracy: 0.9274
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: 8
- 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 | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| 0.2433 | 1.0 | 1257 | 0.2406 | 0.7508 | 0.3936 | 0.5165 | 0.9160 |
| 0.203 | 2.0 | 2514 | 0.2336 | 0.7680 | 0.4294 | 0.5509 | 0.9206 |
| 0.1745 | 3.0 | 3771 | 0.2258 | 0.7637 | 0.4741 | 0.5850 | 0.9246 |
| 0.1585 | 4.0 | 5028 | 0.2276 | 0.7666 | 0.4908 | 0.5985 | 0.9264 |
| 0.1446 | 5.0 | 6285 | 0.2264 | 0.7551 | 0.5122 | 0.6104 | 0.9274 |
Framework versions
- Transformers 4.30.2
- Pytorch 2.0.1+cu118
- Datasets 2.13.1
- Tokenizers 0.13.3
