|
--- |
|
library_name: transformers |
|
license: apache-2.0 |
|
base_model: google-t5/t5-base |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- bleu |
|
model-index: |
|
- name: t5-base-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-base-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: 1.7824 |
|
- Bleu: 12.9294 |
|
- Gen Len: 14.0092 |
|
|
|
## 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: 6 |
|
- mixed_precision_training: Native AMP |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Bleu | Gen Len | |
|
|:-------------:|:------:|:----:|:---------------:|:-------:|:-------:| |
|
| 3.4916 | 0.9994 | 846 | 2.3536 | 0.21 | 14.4369 | |
|
| 2.4194 | 2.0 | 1693 | 2.0655 | 2.0366 | 13.9808 | |
|
| 2.1821 | 2.9994 | 2539 | 1.9102 | 7.286 | 14.0406 | |
|
| 2.1132 | 4.0 | 3386 | 1.8290 | 12.0392 | 14.003 | |
|
| 2.0125 | 4.9994 | 4232 | 1.7935 | 12.8393 | 14.01 | |
|
| 1.9896 | 5.9965 | 5076 | 1.7824 | 12.9294 | 14.0092 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.44.2 |
|
- Pytorch 2.5.0+cu121 |
|
- Datasets 3.1.0 |
|
- Tokenizers 0.19.1 |
|
|
