metadata
tags:
- generated_from_trainer
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: wolof-finetuned-ner
results: []
wolof-finetuned-ner
This model was trained from scratch on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.3950
- Precision: 0.7821
- Recall: 0.8912
- F1: 0.8331
- Accuracy: 0.9849
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: 2e-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: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| No log | 1.0 | 226 | 0.4169 | 0.7590 | 0.8571 | 0.8051 | 0.9842 |
| No log | 2.0 | 452 | 0.3715 | 0.7738 | 0.8844 | 0.8254 | 0.9856 |
| 0.5031 | 3.0 | 678 | 0.3746 | 0.7550 | 0.9014 | 0.8217 | 0.9840 |
| 0.5031 | 4.0 | 904 | 0.3983 | 0.7651 | 0.8639 | 0.8115 | 0.9840 |
| 0.0962 | 5.0 | 1130 | 0.3950 | 0.7821 | 0.8912 | 0.8331 | 0.9849 |
Framework versions
- Transformers 4.33.0
- Pytorch 2.0.0
- Datasets 2.1.0
- Tokenizers 0.13.3