|
|
--- |
|
|
license: apache-2.0 |
|
|
tags: |
|
|
- generated_from_trainer |
|
|
model-index: |
|
|
- name: paraphraser-spanish-mt5-small |
|
|
results: [] |
|
|
datasets: |
|
|
- paws |
|
|
- tapaco |
|
|
language: |
|
|
- es |
|
|
--- |
|
|
|
|
|
<!-- 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. --> |
|
|
|
|
|
# paraphraser-spanish-mt5-small |
|
|
|
|
|
This model is a fine-tuned version of [google/mt5-small](https://huggingface.co/google/mt5-small) on the None dataset. |
|
|
It achieves the following results on the evaluation set: |
|
|
- Loss: 1.4586 |
|
|
|
|
|
## 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: 10 |
|
|
- eval_batch_size: 10 |
|
|
- seed: 42 |
|
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
|
- lr_scheduler_type: linear |
|
|
- num_epochs: 1 |
|
|
|
|
|
### Training results |
|
|
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|
|:-------------:|:-----:|:-----:|:---------------:| |
|
|
| 3.5365 | 0.07 | 2000 | 1.7577 | |
|
|
| 2.5821 | 0.14 | 4000 | 1.6885 | |
|
|
| 2.3485 | 0.21 | 6000 | 1.6532 | |
|
|
| 2.2427 | 0.28 | 8000 | 1.5780 | |
|
|
| 2.1358 | 0.35 | 10000 | 1.5455 | |
|
|
| 2.0808 | 0.42 | 12000 | 1.5185 | |
|
|
| 2.0139 | 0.5 | 14000 | 1.5130 | |
|
|
| 1.9883 | 0.57 | 16000 | 1.5012 | |
|
|
| 1.969 | 0.64 | 18000 | 1.4911 | |
|
|
| 1.9697 | 0.71 | 20000 | 1.4706 | |
|
|
| 1.9552 | 0.78 | 22000 | 1.4653 | |
|
|
| 1.9264 | 0.85 | 24000 | 1.4669 | |
|
|
| 1.932 | 0.92 | 26000 | 1.4569 | |
|
|
| 1.9256 | 0.99 | 28000 | 1.4586 | |
|
|
|
|
|
|
|
|
### Framework versions |
|
|
|
|
|
- Transformers 4.26.0 |
|
|
- Pytorch 1.13.1+cu116 |
|
|
- Datasets 2.9.0 |
|
|
- Tokenizers 0.13.2 |
