metadata
base_model: UBC-NLP/MARBERT
tags:
- generated_from_trainer
metrics:
- accuracy
- precision
- recall
- f1
model-index:
- name: marbert-fully-supervised-arabic-propaganda
results: []
marbert-fully-supervised-arabic-propaganda
This model is a fine-tuned version of UBC-NLP/MARBERT on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.0833
- Accuracy: 0.9310
- Precision: 0.65
- Recall: 0.6341
- F1: 0.6420
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: 3e-05
- train_batch_size: 32
- eval_batch_size: 32
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 |
|---|---|---|---|---|---|---|---|
| 0.0618 | 1.0 | 40 | 0.7104 | 0.9429 | 0.8696 | 0.4878 | 0.625 |
| 0.0232 | 2.0 | 80 | 0.6505 | 0.9357 | 0.675 | 0.6585 | 0.6667 |
| 0.1792 | 3.0 | 120 | 0.9647 | 0.9357 | 0.6842 | 0.6341 | 0.6582 |
| 0.0015 | 4.0 | 160 | 1.1154 | 0.9381 | 0.7027 | 0.6341 | 0.6667 |
| 0.0017 | 5.0 | 200 | 1.0833 | 0.9310 | 0.65 | 0.6341 | 0.6420 |
Framework versions
- Transformers 4.32.1
- Pytorch 2.1.0
- Datasets 2.14.6
- Tokenizers 0.13.3