metadata
tags:
- generated_from_trainer
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: AraBERT_token_classification__AraEval24_fixed
results: []
AraBERT_token_classification__AraEval24_fixed
This model is a fine-tuned version of aubmindlab/bert-base-arabert on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.8758
- Precision: 0.0901
- Recall: 0.0234
- F1: 0.0371
- Accuracy: 0.8606
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: 10
Training results
Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
---|---|---|---|---|---|---|---|
0.6563 | 1.0 | 2851 | 0.7705 | 0.0391 | 0.0006 | 0.0012 | 0.8632 |
0.5865 | 2.0 | 5702 | 0.8071 | 0.0909 | 0.0028 | 0.0055 | 0.8636 |
0.5382 | 3.0 | 8553 | 0.7815 | 0.0578 | 0.0012 | 0.0024 | 0.8634 |
0.5043 | 4.0 | 11404 | 0.7883 | 0.0798 | 0.0021 | 0.0041 | 0.8633 |
0.4445 | 5.0 | 14255 | 0.8188 | 0.0801 | 0.0031 | 0.0060 | 0.8637 |
0.4295 | 6.0 | 17106 | 0.8070 | 0.0877 | 0.0155 | 0.0263 | 0.8610 |
0.4096 | 7.0 | 19957 | 0.8184 | 0.0949 | 0.0135 | 0.0236 | 0.8627 |
0.3827 | 8.0 | 22808 | 0.8362 | 0.0818 | 0.0181 | 0.0296 | 0.8600 |
0.3525 | 9.0 | 25659 | 0.8458 | 0.0893 | 0.0254 | 0.0395 | 0.8599 |
0.3434 | 10.0 | 28510 | 0.8758 | 0.0901 | 0.0234 | 0.0371 | 0.8606 |
Framework versions
- Transformers 4.30.2
- Pytorch 1.12.1
- Datasets 2.13.2
- Tokenizers 0.13.3