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_F1
results: []
Model4_withclasess-arabertv2_base_T2_WS_A100v2_F1
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: 0.0813
- F1-micro: 0.8359
- Roc Auc: 0.9123
- Accuracy: 0.7975
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 |
|---|---|---|---|---|---|---|
| 0.0095 | 1.0 | 507 | 0.0767 | 0.8272 | 0.9095 | 0.7863 |
| 0.0108 | 2.0 | 1014 | 0.0763 | 0.8237 | 0.9074 | 0.7842 |
| 0.0108 | 3.0 | 1521 | 0.0749 | 0.8199 | 0.9029 | 0.7793 |
| 0.0069 | 4.0 | 2028 | 0.0841 | 0.8299 | 0.9076 | 0.7961 |
| 0.0057 | 5.0 | 2535 | 0.0835 | 0.8286 | 0.9105 | 0.7947 |
| 0.0037 | 6.0 | 3042 | 0.0813 | 0.8359 | 0.9123 | 0.7975 |
| 0.0029 | 7.0 | 3549 | 0.0875 | 0.8240 | 0.9081 | 0.7828 |
| 0.0023 | 8.0 | 4056 | 0.0928 | 0.8334 | 0.9136 | 0.8010 |
| 0.002 | 9.0 | 4563 | 0.0961 | 0.8159 | 0.9063 | 0.7730 |
Framework versions
- Transformers 4.46.3
- Pytorch 2.5.1+cu121
- Datasets 3.2.0
- Tokenizers 0.20.3