metadata
library_name: transformers
base_model: aubmindlab/bert-base-arabertv02-twitter
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: Model4_withclasess-arabertv2_base_T2_WS_A100v2
results: []
Model4_withclasess-arabertv2_base_T2_WS_A100v2
This model is a fine-tuned version of aubmindlab/bert-base-arabertv02-twitter on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.0602
- F1-micro: 0.8238
- Roc Auc: 0.8998
- Accuracy: 0.7891
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: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 15
Training results
| Training Loss | Epoch | Step | Validation Loss | F1-micro | Roc Auc | Accuracy |
|---|---|---|---|---|---|---|
| 0.0282 | 1.0 | 507 | 0.0602 | 0.8238 | 0.8998 | 0.7891 |
| 0.0169 | 2.0 | 1014 | 0.0640 | 0.8215 | 0.8973 | 0.7765 |
| 0.0163 | 3.0 | 1521 | 0.0669 | 0.8178 | 0.8949 | 0.7716 |
| 0.0102 | 4.0 | 2028 | 0.0731 | 0.8190 | 0.9019 | 0.7877 |
Framework versions
- Transformers 4.46.3
- Pytorch 2.5.1+cu121
- Datasets 3.2.0
- Tokenizers 0.20.3