metadata
language:
- es
- maq
license: apache-2.0
tags:
- generated_from_trainer
metrics:
- bleu
model-index:
- name: byt5-base-es_maq
results: []
byt5-base-es_maq
This model is a fine-tuned version of google/byt5-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.7257
- Bleu: 9.3405
- Gen Len: 99.8552
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: 16
- eval_batch_size: 16
- seed: 65
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10.0
Training results
| Training Loss | Epoch | Step | Validation Loss | Bleu | Gen Len |
|---|---|---|---|---|---|
| No log | 1.0 | 398 | 0.9986 | 0.0463 | 19.0 |
| 1.43 | 2.0 | 796 | 0.8809 | 0.5462 | 19.0 |
| 0.9934 | 3.0 | 1194 | 0.8291 | 0.4119 | 19.0 |
| 0.8998 | 4.0 | 1592 | 0.7965 | 0.4437 | 19.0 |
| 0.8998 | 5.0 | 1990 | 0.7747 | 0.3303 | 19.0 |
| 0.851 | 6.0 | 2388 | 0.7562 | 0.3764 | 19.0 |
| 0.8139 | 7.0 | 2786 | 0.7415 | 0.3244 | 19.0 |
| 0.7865 | 8.0 | 3184 | 0.7341 | 0.4334 | 19.0 |
| 0.7767 | 9.0 | 3582 | 0.7294 | 0.3918 | 19.0 |
| 0.7767 | 10.0 | 3980 | 0.7257 | 0.3979 | 19.0 |
Framework versions
- Transformers 4.27.4
- Pytorch 2.0.0+cu118
- Datasets 2.11.0
- Tokenizers 0.13.3