metadata
license: mit
base_model: Davlan/afro-xlmr-base
tags:
- generated_from_trainer
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: angela_punc_untranslated_eval
results: []
angela_punc_untranslated_eval
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: 0.1902
- Precision: 0.3889
- Recall: 0.2568
- F1: 0.3093
- Accuracy: 0.9517
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 |
|---|---|---|---|---|---|---|---|
| 0.1524 | 1.0 | 1283 | 0.1547 | 0.4163 | 0.1471 | 0.2174 | 0.9546 |
| 0.1295 | 2.0 | 2566 | 0.1518 | 0.4489 | 0.1943 | 0.2712 | 0.9556 |
| 0.1113 | 3.0 | 3849 | 0.1614 | 0.4152 | 0.2323 | 0.2979 | 0.9538 |
| 0.0896 | 4.0 | 5132 | 0.1784 | 0.4248 | 0.2346 | 0.3023 | 0.9542 |
| 0.073 | 5.0 | 6415 | 0.1902 | 0.3889 | 0.2568 | 0.3093 | 0.9517 |
Framework versions
- Transformers 4.32.0
- Pytorch 2.0.1+cu118
- Datasets 2.14.4
- Tokenizers 0.13.3