|
--- |
|
license: mit |
|
base_model: flax-community/spanish-t5-small |
|
tags: |
|
- translation |
|
- generated_from_trainer |
|
model-index: |
|
- name: st5s-es-inclusivo |
|
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. --> |
|
|
|
# st5s-es-inclusivo |
|
|
|
This model is a fine-tuned version of [flax-community/spanish-t5-small](https://huggingface.co/flax-community/spanish-t5-small) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.1779 |
|
- Score: 55.1958 |
|
|
|
## 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: 32 |
|
- eval_batch_size: 64 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- num_epochs: 12 |
|
- mixed_precision_training: Native AMP |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Score | |
|
|:-------------:|:-----:|:----:|:---------------:|:-------:| |
|
| No log | 1.0 | 105 | 0.5096 | 21.7567 | |
|
| No log | 2.0 | 210 | 0.3781 | 38.3010 | |
|
| No log | 3.0 | 315 | 0.2693 | 49.1274 | |
|
| No log | 4.0 | 420 | 0.2274 | 52.3318 | |
|
| 0.5095 | 5.0 | 525 | 0.2107 | 52.9045 | |
|
| 0.5095 | 6.0 | 630 | 0.1982 | 54.1138 | |
|
| 0.5095 | 7.0 | 735 | 0.1903 | 54.5379 | |
|
| 0.5095 | 8.0 | 840 | 0.1861 | 54.7896 | |
|
| 0.5095 | 9.0 | 945 | 0.1815 | 55.0080 | |
|
| 0.1941 | 10.0 | 1050 | 0.1796 | 55.2191 | |
|
| 0.1941 | 11.0 | 1155 | 0.1784 | 55.1849 | |
|
| 0.1941 | 12.0 | 1260 | 0.1779 | 55.1958 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.39.2 |
|
- Pytorch 2.2.2+cu121 |
|
- Datasets 2.18.0 |
|
- Tokenizers 0.15.2 |
|
|
