<!-- 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. -->
depressionDetectionArabert
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: 0.4586
- Macro F1: 0.9279
- Precision: 0.9281
- Recall: 0.9279
- Kappa: 0.8558
- Accuracy: 0.9279
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: 128
- seed: 25
- gradient_accumulation_steps: 2
- total_train_batch_size: 32
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 8
Training results
Training Loss | Epoch | Step | Validation Loss | Macro F1 | Precision | Recall | Kappa | Accuracy |
---|---|---|---|---|---|---|---|---|
No log | 1.0 | 407 | 0.2285 | 0.9143 | 0.9181 | 0.9144 | 0.8289 | 0.9144 |
0.2459 | 2.0 | 815 | 0.2124 | 0.9264 | 0.9269 | 0.9264 | 0.8528 | 0.9264 |
0.1306 | 3.0 | 1222 | 0.2439 | 0.9285 | 0.9287 | 0.9285 | 0.8570 | 0.9285 |
0.0747 | 4.0 | 1630 | 0.3240 | 0.9270 | 0.9272 | 0.9270 | 0.8540 | 0.9270 |
0.0328 | 5.0 | 2037 | 0.3850 | 0.9273 | 0.9275 | 0.9273 | 0.8546 | 0.9273 |
0.0328 | 6.0 | 2445 | 0.4129 | 0.9279 | 0.9280 | 0.9279 | 0.8558 | 0.9279 |
0.0213 | 7.0 | 2852 | 0.4541 | 0.9273 | 0.9273 | 0.9273 | 0.8545 | 0.9273 |
0.0108 | 7.99 | 3256 | 0.4586 | 0.9279 | 0.9281 | 0.9279 | 0.8558 | 0.9279 |
Framework versions
- Transformers 4.28.1
- Pytorch 2.0.0+cu118
- Tokenizers 0.13.3