metadata
license: mit
base_model: Davlan/afro-xlmr-base
tags:
- generated_from_trainer
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: no_repeats
results: []
no_repeats
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: 0.1658
- Precision: 0.7350
- Recall: 0.5701
- F1: 0.6421
- Accuracy: 0.9596
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: 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 |
|---|---|---|---|---|---|---|---|
| 0.1578 | 1.0 | 1283 | 0.1410 | 0.7141 | 0.4748 | 0.5704 | 0.9540 |
| 0.1189 | 2.0 | 2566 | 0.1336 | 0.7023 | 0.5501 | 0.6170 | 0.9568 |
| 0.0929 | 3.0 | 3849 | 0.1406 | 0.7380 | 0.5433 | 0.6259 | 0.9584 |
| 0.0725 | 4.0 | 5132 | 0.1512 | 0.7283 | 0.5751 | 0.6427 | 0.9591 |
| 0.057 | 5.0 | 6415 | 0.1658 | 0.7350 | 0.5701 | 0.6421 | 0.9596 |
Framework versions
- Transformers 4.31.0
- Pytorch 2.0.1+cu118
- Datasets 2.14.0
- Tokenizers 0.13.3