metadata
license: mit
base_model: Davlan/afro-xlmr-base
tags:
- generated_from_trainer
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: angela_untranslated_entities_test
results: []
angela_untranslated_entities_test
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: 0.1681
- Precision: 0.4056
- Recall: 0.2198
- F1: 0.2851
- Accuracy: 0.9528
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 |
|---|---|---|---|---|---|---|---|
| 0.1724 | 1.0 | 1283 | 0.1654 | 0.4156 | 0.1148 | 0.1800 | 0.9550 |
| 0.1583 | 2.0 | 2566 | 0.1551 | 0.4532 | 0.1307 | 0.2029 | 0.9558 |
| 0.147 | 3.0 | 3849 | 0.1576 | 0.4250 | 0.2063 | 0.2778 | 0.9542 |
| 0.1367 | 4.0 | 5132 | 0.1627 | 0.4105 | 0.2133 | 0.2807 | 0.9534 |
| 0.1215 | 5.0 | 6415 | 0.1681 | 0.4056 | 0.2198 | 0.2851 | 0.9528 |
Framework versions
- Transformers 4.31.0
- Pytorch 2.0.1+cu118
- Datasets 2.14.1
- Tokenizers 0.13.3