metadata
library_name: transformers
base_model: aubmindlab/bert-base-arabertv02-twitter
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: Model4_arabertv2_base_T1_WS_A100_2nd_F1
results: []
Model4_arabertv2_base_T1_WS_A100_2nd_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: 0.2587
- F1 Micro: 0.8495
- F1 Macro: 0.7753
- Roc Auc: 0.9091
- Accuracy: 0.8254
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 | F1 Macro | Roc Auc | Accuracy |
|---|---|---|---|---|---|---|---|
| 0.0226 | 1.0 | 507 | 0.2380 | 0.8341 | 0.7767 | 0.9012 | 0.8094 |
| 0.0303 | 2.0 | 1014 | 0.2433 | 0.8341 | 0.7606 | 0.8980 | 0.8094 |
| 0.0179 | 3.0 | 1521 | 0.2635 | 0.8308 | 0.7540 | 0.8987 | 0.8024 |
| 0.0141 | 4.0 | 2028 | 0.2587 | 0.8495 | 0.7753 | 0.9091 | 0.8254 |
| 0.0083 | 5.0 | 2535 | 0.2919 | 0.8353 | 0.7731 | 0.9017 | 0.8059 |
| 0.0066 | 6.0 | 3042 | 0.2922 | 0.8329 | 0.7611 | 0.9006 | 0.8045 |
| 0.0054 | 7.0 | 3549 | 0.3193 | 0.8358 | 0.7752 | 0.9016 | 0.8128 |
Framework versions
- Transformers 4.46.3
- Pytorch 2.5.1+cu121
- Datasets 3.2.0
- Tokenizers 0.20.3