metadata
base_model: malmarjeh/t5-arabic-text-summarization
tags:
- generated_from_trainer
model-index:
- name: t5-arabic-text-summarization-finetuned-xsum
results: []
t5-arabic-text-summarization-finetuned-xsum
This model is a fine-tuned version of malmarjeh/t5-arabic-text-summarization on the None dataset. It achieves the following results on the evaluation set:
- Loss: 2.5723
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: 1
- eval_batch_size: 1
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 4.7847 | 1.0 | 840 | 3.4060 |
| 3.9577 | 2.0 | 1680 | 3.1634 |
| 3.6274 | 3.0 | 2520 | 2.9916 |
| 3.5127 | 4.0 | 3360 | 2.8185 |
| 3.324 | 5.0 | 4200 | 2.7196 |
| 3.2254 | 6.0 | 5040 | 2.6812 |
| 3.2065 | 7.0 | 5880 | 2.6396 |
| 3.1036 | 8.0 | 6720 | 2.5930 |
| 3.0984 | 9.0 | 7560 | 2.5850 |
| 2.9747 | 10.0 | 8400 | 2.5723 |
Framework versions
- Transformers 4.36.2
- Pytorch 2.0.0+cu118
- Datasets 2.16.1
- Tokenizers 0.15.0