|
--- |
|
license: apache-2.0 |
|
base_model: Helsinki-NLP/opus-mt-es-es |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- bleu |
|
model-index: |
|
- name: esp-to-lsm-model |
|
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. --> |
|
|
|
# esp-to-lsm-model |
|
|
|
This model is a fine-tuned version of [Helsinki-NLP/opus-mt-es-es](https://huggingface.co/Helsinki-NLP/opus-mt-es-es) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.4524 |
|
- Bleu: 68.8807 |
|
|
|
## 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: 1.5e-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: 20 |
|
- mixed_precision_training: Native AMP |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Bleu | |
|
|:-------------:|:-----:|:----:|:---------------:|:-------:| |
|
| 2.959 | 1.0 | 75 | 2.6073 | 14.3097 | |
|
| 1.9386 | 2.0 | 150 | 1.5408 | 44.9883 | |
|
| 1.1844 | 3.0 | 225 | 1.1446 | 60.7215 | |
|
| 0.9596 | 4.0 | 300 | 0.9445 | 49.9656 | |
|
| 0.8681 | 5.0 | 375 | 0.8136 | 51.1677 | |
|
| 0.6831 | 6.0 | 450 | 0.7128 | 38.5475 | |
|
| 0.5456 | 7.0 | 525 | 0.6493 | 49.2921 | |
|
| 0.4817 | 8.0 | 600 | 0.5980 | 67.6139 | |
|
| 0.4804 | 9.0 | 675 | 0.5642 | 74.1258 | |
|
| 0.3944 | 10.0 | 750 | 0.5409 | 73.4943 | |
|
| 0.3018 | 11.0 | 825 | 0.5166 | 56.0140 | |
|
| 0.2788 | 12.0 | 900 | 0.4993 | 75.9506 | |
|
| 0.2658 | 13.0 | 975 | 0.4861 | 76.3040 | |
|
| 0.2884 | 14.0 | 1050 | 0.4757 | 52.8020 | |
|
| 0.2473 | 15.0 | 1125 | 0.4648 | 67.2947 | |
|
| 0.3299 | 16.0 | 1200 | 0.4632 | 52.5347 | |
|
| 0.249 | 17.0 | 1275 | 0.4568 | 69.9258 | |
|
| 0.2294 | 18.0 | 1350 | 0.4550 | 69.4897 | |
|
| 0.2136 | 19.0 | 1425 | 0.4535 | 67.6997 | |
|
| 0.1977 | 20.0 | 1500 | 0.4524 | 68.8807 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.41.2 |
|
- Pytorch 2.3.0+cu121 |
|
- Datasets 2.20.0 |
|
- Tokenizers 0.19.1 |
|
|
