|
--- |
|
license: apache-2.0 |
|
base_model: Helsinki-NLP/opus-mt-en-es |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- bleu |
|
model-index: |
|
- name: opus-mt-en-es-finetuned-es-to-pbb-v0.1 |
|
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. --> |
|
|
|
# opus-mt-en-es-finetuned-es-to-pbb-v0.1 |
|
|
|
This model is a fine-tuned version of [Helsinki-NLP/opus-mt-en-es](https://huggingface.co/Helsinki-NLP/opus-mt-en-es) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 1.7969 |
|
- Bleu: 1.5951 |
|
- Gen Len: 90.2946 |
|
|
|
## 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: 32 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- num_epochs: 10 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Bleu | Gen Len | |
|
|:-------------:|:-----:|:----:|:---------------:|:------:|:-------:| |
|
| No log | 1.0 | 194 | 2.5441 | 0.4291 | 116.186 | |
|
| No log | 2.0 | 388 | 2.2092 | 0.6579 | 93.4866 | |
|
| 2.6835 | 3.0 | 582 | 2.0599 | 0.698 | 96.8631 | |
|
| 2.6835 | 4.0 | 776 | 1.9695 | 1.0624 | 90.817 | |
|
| 2.6835 | 5.0 | 970 | 1.9087 | 1.0183 | 92.7232 | |
|
| 1.9199 | 6.0 | 1164 | 1.8623 | 1.2926 | 90.9807 | |
|
| 1.9199 | 7.0 | 1358 | 1.8342 | 1.3107 | 92.122 | |
|
| 1.7744 | 8.0 | 1552 | 1.8145 | 1.3784 | 90.314 | |
|
| 1.7744 | 9.0 | 1746 | 1.8020 | 1.4162 | 90.8006 | |
|
| 1.7744 | 10.0 | 1940 | 1.7969 | 1.5951 | 90.2946 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.31.0 |
|
- Pytorch 2.0.1+cu118 |
|
- Datasets 2.14.4 |
|
- Tokenizers 0.13.3 |
|
|
