result
This model is a fine-tuned version of salti/AraElectra-base-finetuned-ARCD on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.1367
- F1-macro: 0.9578
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: 8e-05
- train_batch_size: 64
- eval_batch_size: 128
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 4
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | F1-macro |
|---|---|---|---|---|
| 0.7796 | 1.0 | 1467 | 0.4553 | 0.8396 |
| 0.3442 | 2.0 | 2934 | 0.2594 | 0.9112 |
| 0.1483 | 3.0 | 4401 | 0.1557 | 0.9468 |
| 0.0662 | 4.0 | 5868 | 0.1367 | 0.9578 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.13.0
- Datasets 2.1.0
- Tokenizers 0.13.2