metadata
library_name: transformers
base_model: aubmindlab/bert-base-arabertv02-twitter
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: fold_4
results: []
fold_4
This model is a fine-tuned version of aubmindlab/bert-base-arabertv02-twitter on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.4181
- Accuracy: 0.8452
- Macro F1: 0.8447
- Weighted F1: 0.8452
- F1 Pro: 0.8421
- F1 Against: 0.8571
- F1 Neutral: 0.8350
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: 3e-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: 5
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Macro F1 | Weighted F1 | F1 Pro | F1 Against | F1 Neutral |
|---|---|---|---|---|---|---|---|---|---|
| 0.8777 | 1.1628 | 50 | 0.5462 | 0.8095 | 0.8101 | 0.8102 | 0.8468 | 0.7874 | 0.7959 |
| 0.4709 | 2.3256 | 100 | 0.4626 | 0.8274 | 0.8277 | 0.8275 | 0.8571 | 0.8034 | 0.8224 |
| 0.27 | 3.4884 | 150 | 0.4181 | 0.8452 | 0.8447 | 0.8452 | 0.8421 | 0.8571 | 0.8350 |
| 0.2101 | 4.6512 | 200 | 0.5017 | 0.8095 | 0.8088 | 0.8094 | 0.8421 | 0.8 | 0.7843 |
Framework versions
- Transformers 4.57.3
- Pytorch 2.9.0+cu126
- Datasets 4.0.0
- Tokenizers 0.22.2