metadata
library_name: transformers
license: apache-2.0
base_model: moussaKam/AraBART
tags:
- generated_from_trainer
model-index:
- name: resultsara_bertscore
results: []
resultsara_bertscore
This model is a fine-tuned version of moussaKam/AraBART on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.5748
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: 5e-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_steps: 500
- num_epochs: 3
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.7346 | 0.4263 | 500 | 0.5939 |
| 0.7367 | 0.8525 | 1000 | 0.5851 |
| 0.7042 | 1.2788 | 1500 | 0.5825 |
| 0.6854 | 1.7050 | 2000 | 0.5783 |
| 0.6767 | 2.1313 | 2500 | 0.5775 |
| 0.6561 | 2.5575 | 3000 | 0.5758 |
| 0.6562 | 2.9838 | 3500 | 0.5748 |
Framework versions
- Transformers 4.45.0.dev0
- Pytorch 2.4.0+cu121
- Datasets 2.21.0
- Tokenizers 0.19.1