metadata
license: apache-2.0
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: camelbert
results: []
camelbert
This model is a fine-tuned version of CAMeL-Lab/bert-base-arabic-camelbert-msa on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.9908
- Macro F1: 0.3402
- Macro Precision: 0.3848
- Macro Recall: 0.3256
- Accuracy: 0.4572
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: 5e-05
- train_batch_size: 64
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 6
Training results
| Training Loss | Epoch | Step | Validation Loss | Macro F1 | Macro Precision | Macro Recall | Accuracy |
|---|---|---|---|---|---|---|---|
| 1.7936 | 1.0 | 857 | 1.5955 | 0.3085 | 0.4058 | 0.2880 | 0.4518 |
| 1.3325 | 2.0 | 1714 | 1.5419 | 0.3263 | 0.4054 | 0.3128 | 0.4681 |
| 1.0848 | 3.0 | 2571 | 1.6263 | 0.3363 | 0.4061 | 0.3209 | 0.4632 |
| 0.8856 | 4.0 | 3428 | 1.7669 | 0.3410 | 0.4142 | 0.3250 | 0.4534 |
| 0.6869 | 5.0 | 4285 | 1.8975 | 0.3347 | 0.3785 | 0.3192 | 0.4555 |
| 0.5905 | 6.0 | 5142 | 1.9908 | 0.3402 | 0.3848 | 0.3256 | 0.4572 |
Framework versions
- Transformers 4.29.2
- Pytorch 2.0.1+cu117
- Datasets 3.0.2
- Tokenizers 0.13.3