metadata
license: mit
base_model: xlm-roberta-base
tags:
- generated_from_trainer
datasets:
- masakhaner2
metrics:
- f1
model-index:
- name: xlm-roberta-base-finetuned-wolof
results:
- task:
name: Token Classification
type: token-classification
dataset:
name: masakhaner2
type: masakhaner2
config: wol
split: validation
args: wol
metrics:
- name: F1
type: f1
value: 0.8614609571788412
xlm-roberta-base-finetuned-wolof
This model is a fine-tuned version of xlm-roberta-base on the masakhaner2 dataset. It achieves the following results on the evaluation set:
- Loss: 0.6731
- F1: 0.8615
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: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 15
Training results
Training Loss | Epoch | Step | Validation Loss | F1 |
---|---|---|---|---|
0.6468 | 1.0 | 739 | 0.3680 | 0.7084 |
0.3085 | 2.0 | 1478 | 0.3194 | 0.7394 |
0.2155 | 3.0 | 2217 | 0.4131 | 0.7670 |
0.157 | 4.0 | 2956 | 0.3638 | 0.8077 |
0.1061 | 5.0 | 3695 | 0.3636 | 0.7819 |
0.08 | 6.0 | 4434 | 0.4743 | 0.8586 |
0.0593 | 7.0 | 5173 | 0.3827 | 0.8184 |
0.0332 | 8.0 | 5912 | 0.4892 | 0.8502 |
0.0244 | 9.0 | 6651 | 0.5380 | 0.8387 |
0.0206 | 10.0 | 7390 | 0.5505 | 0.8653 |
0.0119 | 11.0 | 8129 | 0.5966 | 0.8647 |
0.0064 | 12.0 | 8868 | 0.5154 | 0.8657 |
0.0036 | 13.0 | 9607 | 0.6321 | 0.8653 |
0.0028 | 14.0 | 10346 | 0.6662 | 0.8656 |
0.0014 | 15.0 | 11085 | 0.6731 | 0.8615 |
Framework versions
- Transformers 4.33.0
- Pytorch 2.0.0
- Datasets 2.1.0
- Tokenizers 0.13.3