|
--- |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- accuracy |
|
- precision |
|
- recall |
|
model-index: |
|
- name: ArBERT-finetuned-fnd |
|
results: [] |
|
--- |
|
|
|
<!-- 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. --> |
|
|
|
# ArBERT-finetuned-fnd |
|
|
|
This model is a fine-tuned version of [UBC-NLP/ARBERT](https://huggingface.co/UBC-NLP/ARBERT) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.4693 |
|
- Macro F1: 0.7725 |
|
- Accuracy: 0.7821 |
|
- Precision: 0.7781 |
|
- Recall: 0.7693 |
|
|
|
## 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 | |
|
|:-------------:|:-----:|:----:|:---------------:|:--------:|:--------:|:---------:|:------:| |
|
| 0.5049 | 1.0 | 1597 | 0.4705 | 0.7588 | 0.7680 | 0.7623 | 0.7566 | |
|
| 0.3867 | 2.0 | 3194 | 0.4693 | 0.7725 | 0.7821 | 0.7781 | 0.7693 | |
|
| 0.2613 | 3.0 | 4791 | 0.6281 | 0.7573 | 0.7671 | 0.7618 | 0.7547 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.20.1 |
|
- Pytorch 1.11.0 |
|
- Datasets 2.1.0 |
|
- Tokenizers 0.12.1 |
|
|