metadata
library_name: transformers
license: mit
base_model: ArabicNLP/mT5-base_ar
tags:
- generated_from_trainer
model-index:
- name: generative_qa_model
results: []
generative_qa_model
This model is a fine-tuned version of ArabicNLP/mT5-base_ar on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.8481
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: 1e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- 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
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 13.9393 | 1.0 | 648 | 6.9092 |
| 5.0306 | 2.0 | 1296 | 2.7919 |
| 2.7294 | 3.0 | 1944 | 2.0758 |
| 2.067 | 4.0 | 2592 | 1.2531 |
| 1.5678 | 5.0 | 3240 | 0.9861 |
| 1.3934 | 6.0 | 3888 | 0.9093 |
| 1.2198 | 7.0 | 4536 | 0.8782 |
| 1.1412 | 8.0 | 5184 | 0.8594 |
| 1.1309 | 9.0 | 5832 | 0.8506 |
| 1.1577 | 10.0 | 6480 | 0.8481 |
Framework versions
- Transformers 4.47.1
- Pytorch 2.5.1+cu124
- Datasets 3.2.0
- Tokenizers 0.21.0