|
--- |
|
language: |
|
- es |
|
- maz |
|
license: apache-2.0 |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- bleu |
|
model-index: |
|
- name: byt5-base-es_maz |
|
results: [] |
|
--- |
|
|
|
<!-- This model card has been generated automatically according to the information the Trainer had access to. You |
|
should probably proofread and complete it, then remove this comment. --> |
|
|
|
# byt5-base-es_maz |
|
|
|
This model is a fine-tuned version of [google/byt5-base](https://huggingface.co/google/byt5-base) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.7418 |
|
- Bleu: 6.8783 |
|
- Gen Len: 99.7771 |
|
|
|
## 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 | 393 | 1.0332 | 0.0452 | 19.0 | |
|
| 1.5229 | 2.0 | 786 | 0.9129 | 0.1159 | 19.0 | |
|
| 1.0464 | 3.0 | 1179 | 0.8561 | 0.1479 | 19.0 | |
|
| 0.9477 | 4.0 | 1572 | 0.8148 | 0.1678 | 19.0 | |
|
| 0.9477 | 5.0 | 1965 | 0.7879 | 0.1791 | 19.0 | |
|
| 0.8888 | 6.0 | 2358 | 0.7708 | 0.1628 | 19.0 | |
|
| 0.8517 | 7.0 | 2751 | 0.7597 | 0.1582 | 19.0 | |
|
| 0.8279 | 8.0 | 3144 | 0.7492 | 0.1683 | 19.0 | |
|
| 0.8107 | 9.0 | 3537 | 0.7442 | 0.1704 | 19.0 | |
|
| 0.8107 | 10.0 | 3930 | 0.7418 | 0.1683 | 19.0 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.27.4 |
|
- Pytorch 2.0.0+cu118 |
|
- Datasets 2.11.0 |
|
- Tokenizers 0.13.3 |
|
|
