metadata
license: apache-2.0
base_model: Helsinki-NLP/opus-mt-es-en
tags:
- generated_from_trainer
model-index:
- name: Model-es-qu
results: []
Model-es-qu
This model is a fine-tuned version of Helsinki-NLP/opus-mt-es-en on an unknown dataset. It achieves the following results on the evaluation set:
- BLEU: 15.47193377563526
- chrF: 49.809088254243925
- Loss: 0.2958
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: 0.00014023977100100803
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 16
- num_epochs: 6
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.3983 | 1.0 | 6422 | 0.3643 |
| 0.3285 | 2.0 | 12844 | 0.3257 |
| 0.2908 | 3.0 | 19266 | 0.3065 |
| 0.2537 | 4.0 | 25688 | 0.2981 |
| 0.2203 | 5.0 | 32110 | 0.2943 |
| 0.1969 | 6.0 | 38532 | 0.2958 |
Framework versions
- Transformers 4.43.3
- Pytorch 2.4.0+cu118
- Datasets 2.20.0
- Tokenizers 0.19.1