| | --- |
| | library_name: transformers |
| | base_model: aubmindlab/bert-base-arabertv02-twitter |
| | tags: |
| | - generated_from_trainer |
| | metrics: |
| | - accuracy |
| | model-index: |
| | - name: Arabertv2-fold5 |
| | 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. --> |
| |
|
| | # Arabertv2-fold5 |
| |
|
| | This model is a fine-tuned version of [aubmindlab/bert-base-arabertv02-twitter](https://huggingface.co/aubmindlab/bert-base-arabertv02-twitter) on an unknown dataset. |
| | It achieves the following results on the evaluation set: |
| | - Loss: 0.6600 |
| | - Accuracy: 0.8155 |
| | - Macro F1: 0.8151 |
| | - Weighted F1: 0.8151 |
| | - F1 Pro: 0.8037 |
| | - F1 Against: 0.8226 |
| | - F1 Neutral: 0.8190 |
| |
|
| | ## 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: 2e-05 |
| | - train_batch_size: 16 |
| | - eval_batch_size: 16 |
| | - seed: 42 |
| | - optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments |
| | - lr_scheduler_type: linear |
| | - num_epochs: 10 |
| | - mixed_precision_training: Native AMP |
| | |
| | ### Training results |
| | |
| | | Training Loss | Epoch | Step | Validation Loss | Accuracy | Macro F1 | Weighted F1 | F1 Pro | F1 Against | F1 Neutral | |
| | |:-------------:|:------:|:----:|:---------------:|:--------:|:--------:|:-----------:|:------:|:----------:|:----------:| |
| | | 0.9553 | 1.1628 | 50 | 0.7744 | 0.6667 | 0.6675 | 0.6667 | 0.6829 | 0.6387 | 0.6809 | |
| | | 0.6022 | 2.3256 | 100 | 0.5448 | 0.7619 | 0.7617 | 0.7620 | 0.7748 | 0.7603 | 0.75 | |
| | | 0.3637 | 3.4884 | 150 | 0.5355 | 0.7976 | 0.7961 | 0.7969 | 0.7961 | 0.8154 | 0.7767 | |
| | | 0.2713 | 4.6512 | 200 | 0.5420 | 0.8036 | 0.8031 | 0.8035 | 0.8037 | 0.8130 | 0.7925 | |
| | | 0.1627 | 5.8140 | 250 | 0.5662 | 0.7917 | 0.7914 | 0.7914 | 0.7748 | 0.8033 | 0.7961 | |
| | | 0.1126 | 6.9767 | 300 | 0.6165 | 0.8095 | 0.8095 | 0.8092 | 0.7963 | 0.8130 | 0.8190 | |
| | | 0.0886 | 8.1395 | 350 | 0.6597 | 0.8155 | 0.8151 | 0.8151 | 0.8037 | 0.8226 | 0.8190 | |
| | | 0.0803 | 9.3023 | 400 | 0.6821 | 0.8095 | 0.8089 | 0.8091 | 0.7963 | 0.8226 | 0.8077 | |
| | |
| | |
| | ### Framework versions |
| | |
| | - Transformers 5.0.0 |
| | - Pytorch 2.10.0+cu128 |
| | - Datasets 4.0.0 |
| | - Tokenizers 0.22.2 |
| | |
