wiki_lingua-ar-8-3-5.6e-05-mt5-small-finetuned
This model is a fine-tuned version of google/mt5-small on the wiki_lingua dataset. It achieves the following results on the evaluation set:
- Loss: 2.5040
- Rouge1: 0.4632
- Rouge2: 0.1185
- Rougel: 0.4644
- Rougelsum: 0.47
Baseline Results
- Rouge1: 1.55
- Rouge2: 0.48
- Rougel: 1.51
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: 5.6e-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: 3
Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum |
|---|---|---|---|---|---|---|---|
| 3.981 | 1.0 | 2499 | 2.6174 | 0.4085 | 0.1027 | 0.4062 | 0.4141 |
| 3.0985 | 2.0 | 4998 | 2.5261 | 0.5131 | 0.1541 | 0.5113 | 0.5154 |
| 2.9914 | 3.0 | 7497 | 2.5040 | 0.4632 | 0.1185 | 0.4644 | 0.47 |
Framework versions
- Transformers 4.27.4
- Pytorch 1.13.0
- Datasets 2.1.0
- Tokenizers 0.13.2