|
--- |
|
base_model: SI2M-Lab/DarijaBERT |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- accuracy |
|
model-index: |
|
- name: darija_test5 |
|
results: [] |
|
--- |
|
|
|
<!-- This model card has been generated automatically according to the information the Trainer had access to. You |
|
should probably proofread and complete it, then remove this comment. --> |
|
|
|
# darija_test5 |
|
|
|
This model is a fine-tuned version of [SI2M-Lab/DarijaBERT](https://huggingface.co/SI2M-Lab/DarijaBERT) on the None dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 1.1195 |
|
- Accuracy: 0.8508 |
|
|
|
## 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 | |
|
|:-------------:|:-----:|:----:|:---------------:|:--------:| |
|
| 0.0554 | 1.0 | 214 | 1.1195 | 0.8508 | |
|
| 0.5871 | 2.0 | 428 | 0.6734 | 0.6131 | |
|
| 0.7418 | 3.0 | 642 | 0.7144 | 0.6131 | |
|
| 0.7406 | 4.0 | 856 | 0.7020 | 0.6131 | |
|
| 0.6984 | 5.0 | 1070 | 0.6787 | 0.6131 | |
|
| 0.7168 | 6.0 | 1284 | 0.6678 | 0.6131 | |
|
| 0.6719 | 7.0 | 1498 | 0.6676 | 0.6131 | |
|
| 0.72 | 8.0 | 1712 | 0.6701 | 0.6131 | |
|
| 0.5586 | 9.0 | 1926 | 0.6686 | 0.6131 | |
|
| 0.7321 | 10.0 | 2140 | 0.6693 | 0.6131 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.42.4 |
|
- Pytorch 2.4.0+cu121 |
|
- Datasets 2.21.0 |
|
- Tokenizers 0.19.1 |
|
|
