metadata
tags:
- generated_from_trainer
metrics:
- accuracy
- precision
- recall
model-index:
- name: ArBERT-finetuned-fnd
results: []
ArBERT-finetuned-fnd
This model is a fine-tuned version of UBC-NLP/ARBERT on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.4747
- Macro F1: 0.7661
- Accuracy: 0.7773
- Precision: 0.7748
- Recall: 0.7619
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: 16
- 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: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Macro F1 | Accuracy | Precision | Recall |
|---|---|---|---|---|---|---|---|
| 0.5038 | 1.0 | 1597 | 0.4701 | 0.7596 | 0.7662 | 0.7595 | 0.7597 |
| 0.379 | 2.0 | 3194 | 0.4747 | 0.7661 | 0.7773 | 0.7748 | 0.7619 |
| 0.2462 | 3.0 | 4791 | 0.6113 | 0.7530 | 0.7629 | 0.7573 | 0.7504 |
Framework versions
- Transformers 4.20.1
- Pytorch 1.11.0
- Datasets 2.1.0
- Tokenizers 0.12.1