metadata
license: apache-2.0
tags:
- generated_from_trainer
metrics:
- rouge
model-index:
- name: AraBART-finetuned-wiki-ar
results: []
AraBART-finetuned-wiki-ar
This model is a fine-tuned version of moussaKam/AraBART on the https://huggingface.co/datasets/arbml/wiki_lingua_ar dataset. It achieves the following results on the evaluation set:
- Loss: 2.6184
- Rouge1: 0.87
- Rouge2: 0.1157
- Rougel: 0.8635
- Rougelsum: 0.8783
- Gen Len: 19.3131
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: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 1
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
|---|---|---|---|---|---|---|---|---|
| 2.9386 | 1.0 | 2556 | 2.6184 | 0.87 | 0.1157 | 0.8635 | 0.8783 | 19.3131 |
Framework versions
- Transformers 4.25.1
- Pytorch 1.13.0+cu116
- Datasets 2.7.1
- Tokenizers 0.13.2