|
--- |
|
library_name: transformers |
|
license: apache-2.0 |
|
base_model: google-t5/t5-base |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- bleu |
|
model-index: |
|
- name: t5-small-spanish-yoremnokki |
|
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. --> |
|
|
|
# t5-small-spanish-yoremnokki |
|
|
|
This model is a fine-tuned version of [google-t5/t5-base](https://huggingface.co/google-t5/t5-base) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 1.8622 |
|
- Bleu: 10.7378 |
|
- Gen Len: 14.22 |
|
|
|
## 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: 1e-05 |
|
- train_batch_size: 16 |
|
- eval_batch_size: 16 |
|
- seed: 42 |
|
- gradient_accumulation_steps: 2 |
|
- total_train_batch_size: 32 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- num_epochs: 5 |
|
- mixed_precision_training: Native AMP |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Bleu | Gen Len | |
|
|:-------------:|:-----:|:----:|:---------------:|:-------:|:-------:| |
|
| 3.4879 | 1.0 | 839 | 2.3617 | 0.2661 | 14.6218 | |
|
| 2.4168 | 2.0 | 1678 | 2.0854 | 1.8065 | 14.3043 | |
|
| 2.2109 | 3.0 | 2517 | 1.9512 | 5.2629 | 14.2827 | |
|
| 2.1335 | 4.0 | 3356 | 1.8816 | 9.4622 | 14.23 | |
|
| 2.0758 | 5.0 | 4195 | 1.8622 | 10.7378 | 14.22 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.44.2 |
|
- Pytorch 2.4.1+cu121 |
|
- Datasets 3.0.1 |
|
- Tokenizers 0.19.1 |
|
|
