metadata
tags:
- generated_from_trainer
model-index:
- name: bert-base-arabertv02-finetuned-sandouq
results: []
language:
- ar
fill-mask:
- example1: صندوق [MASK]
bert-base-arabertv02-finetuned-sandouq
This model is a fine-tuned version of aubmindlab/bert-base-arabertv02 on an ٍSandouq financial dataset. It achieves the following results on the evaluation set:
- Loss: 2.9575
Model description
This is AraBert model which fine-tuned on financial dataset for financial purpous
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: 15
- eval_batch_size: 15
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- num_epochs: 8
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 3.3856 | 1.0 | 334 | 3.2282 |
| 3.2555 | 2.0 | 668 | 3.1496 |
| 3.1479 | 3.0 | 1002 | 3.1036 |
| 3.0899 | 4.0 | 1336 | 3.0090 |
| 3.025 | 5.0 | 1670 | 3.0105 |
| 2.9823 | 6.0 | 2004 | 3.0245 |
| 2.9893 | 7.0 | 2338 | 2.9781 |
| 2.9614 | 8.0 | 2672 | 2.9572 |
Framework versions
- Transformers 4.30.2
- Pytorch 2.0.1+cu118
- Datasets 2.13.0
- Tokenizers 0.13.3