metadata
license: mit
base_model: Davlan/afro-xlmr-base
tags:
- generated_from_trainer
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: angela_untranslated_punc_eval
results: []
angela_untranslated_punc_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: 0.5952
- Precision: 0.3916
- Recall: 0.1193
- F1: 0.1829
- Accuracy: 0.8778
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 |
|---|---|---|---|---|---|---|---|
| 0.1532 | 1.0 | 1283 | 0.3419 | 0.3699 | 0.0649 | 0.1105 | 0.8780 |
| 0.1318 | 2.0 | 2566 | 0.3842 | 0.3875 | 0.0632 | 0.1087 | 0.8785 |
| 0.1097 | 3.0 | 3849 | 0.4611 | 0.4008 | 0.1028 | 0.1637 | 0.8786 |
| 0.09 | 4.0 | 5132 | 0.5673 | 0.4044 | 0.1059 | 0.1679 | 0.8788 |
| 0.0731 | 5.0 | 6415 | 0.5952 | 0.3916 | 0.1193 | 0.1829 | 0.8778 |
Framework versions
- Transformers 4.31.0
- Pytorch 2.0.1+cu118
- Datasets 2.14.3
- Tokenizers 0.13.3