metadata
base_model: aubmindlab/bert-base-arabertv02
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: darija_test3
results: []
darija_test3
This model is a fine-tuned version of aubmindlab/bert-base-arabertv02 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.4497
- Accuracy: 0.8177
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: 0.0003
- 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
- lr_scheduler_warmup_ratio: 0.05
- num_epochs: 10
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.4385 | 1.0 | 192 | 0.4618 | 0.8047 |
| 0.3433 | 2.0 | 384 | 0.4497 | 0.8177 |
| 0.6551 | 3.0 | 576 | 0.6499 | 0.6510 |
| 0.6284 | 4.0 | 768 | 0.6556 | 0.6510 |
| 0.6402 | 5.0 | 960 | 0.6473 | 0.6510 |
| 0.6538 | 6.0 | 1152 | 0.6470 | 0.6510 |
| 0.7309 | 7.0 | 1344 | 0.6477 | 0.6510 |
| 0.6416 | 8.0 | 1536 | 0.6472 | 0.6510 |
| 0.5665 | 9.0 | 1728 | 0.6625 | 0.6510 |
| 0.607 | 10.0 | 1920 | 0.6501 | 0.6510 |
Framework versions
- Transformers 4.42.4
- Pytorch 2.3.1+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1