metadata
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: final_content_bert
results: []
final_content_bert
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: 1.6152
- Macro F1: 0.5213
- Macro Precision: 0.5425
- Macro Recall: 0.5095
- Accuracy: 0.5338
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 |
|---|---|---|---|---|---|---|---|
| 1.3421 | 1.0 | 857 | 1.2154 | 0.5000 | 0.5659 | 0.4801 | 0.5164 |
| 1.0055 | 2.0 | 1714 | 1.1822 | 0.5240 | 0.5613 | 0.5087 | 0.5410 |
| 0.8008 | 3.0 | 2571 | 1.2802 | 0.5120 | 0.5371 | 0.5012 | 0.5272 |
| 0.6593 | 4.0 | 3428 | 1.3946 | 0.5227 | 0.5451 | 0.5131 | 0.5391 |
| 0.5051 | 5.0 | 4285 | 1.5192 | 0.5192 | 0.5391 | 0.5101 | 0.5335 |
| 0.426 | 6.0 | 5142 | 1.6152 | 0.5213 | 0.5425 | 0.5095 | 0.5338 |
Framework versions
- Transformers 4.29.2
- Pytorch 2.0.1+cu117
- Datasets 3.0.2
- Tokenizers 0.13.3