metadata
library_name: transformers
base_model: UBC-NLP/MARBERT
tags:
- generated_from_trainer
metrics:
- accuracy
- precision
- recall
- f1
model-index:
- name: UBC-NLP-MARBERT-arabic-fp16-allagree-cameltools
results: []
UBC-NLP-MARBERT-arabic-fp16-allagree-cameltools
This model is a fine-tuned version of UBC-NLP/MARBERT on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.2191
- Accuracy: 0.9384
- Precision: 0.9385
- Recall: 0.9384
- F1: 0.9384
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: 64
- eval_batch_size: 64
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 128
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.3
- num_epochs: 10
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 |
|---|---|---|---|---|---|---|---|
| 0.9917 | 0.7463 | 50 | 0.6973 | 0.7668 | 0.8138 | 0.7668 | 0.6876 |
| 0.3936 | 1.4925 | 100 | 0.2191 | 0.9384 | 0.9385 | 0.9384 | 0.9384 |
| 0.1789 | 2.2388 | 150 | 0.1868 | 0.9450 | 0.9448 | 0.9450 | 0.9448 |
| 0.1503 | 2.9851 | 200 | 0.2098 | 0.9291 | 0.9323 | 0.9291 | 0.9296 |
| 0.0871 | 3.7313 | 250 | 0.2069 | 0.9431 | 0.9435 | 0.9431 | 0.9433 |
| 0.0484 | 4.4776 | 300 | 0.2293 | 0.9506 | 0.9506 | 0.9506 | 0.9506 |
Framework versions
- Transformers 4.52.4
- Pytorch 2.7.0+cu126
- Datasets 3.6.0
- Tokenizers 0.21.1