metadata
library_name: transformers
license: apache-2.0
base_model: Helsinki-NLP/opus-mt-es-en
tags:
- generated_from_trainer
metrics:
- bleu
model-index:
- name: MarianMT-finetuned-ES-ZAP-v1
results: []
MarianMT-finetuned-ES-ZAP-v1
This model is a fine-tuned version of Helsinki-NLP/opus-mt-es-en on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.2261
- Bleu: 23.5794
- Meteor: 0.4931
- Ter: 61.1641
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: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 50
Training results
| Training Loss | Epoch | Step | Validation Loss | Bleu | Meteor | Ter |
|---|---|---|---|---|---|---|
| 1.3343 | 1.0 | 179 | 0.5869 | 0.7144 | 0.1048 | 130.4389 |
| 0.4974 | 2.0 | 358 | 0.4479 | 3.9306 | 0.2073 | 99.8092 |
| 0.3872 | 3.0 | 537 | 0.3787 | 7.0159 | 0.2451 | 87.6908 |
| 0.3262 | 4.0 | 716 | 0.3448 | 8.6827 | 0.2893 | 83.6832 |
| 0.287 | 5.0 | 895 | 0.3189 | 10.0091 | 0.3152 | 79.0076 |
| 0.2561 | 6.0 | 1074 | 0.2985 | 11.7958 | 0.3400 | 77.1947 |
| 0.2307 | 7.0 | 1253 | 0.2865 | 13.6671 | 0.3672 | 72.8053 |
| 0.2102 | 8.0 | 1432 | 0.2743 | 12.9624 | 0.3759 | 72.8053 |
| 0.1928 | 9.0 | 1611 | 0.2644 | 17.1984 | 0.4046 | 68.5115 |
| 0.1782 | 10.0 | 1790 | 0.2577 | 15.8617 | 0.4150 | 68.1298 |
| 0.1644 | 11.0 | 1969 | 0.2522 | 16.6175 | 0.4242 | 66.5076 |
| 0.1515 | 12.0 | 2148 | 0.2471 | 18.3496 | 0.4332 | 67.0802 |
| 0.1414 | 13.0 | 2327 | 0.2418 | 19.8334 | 0.4531 | 64.5038 |
| 0.1324 | 14.0 | 2506 | 0.2392 | 19.7102 | 0.4520 | 65.2672 |
| 0.1244 | 15.0 | 2685 | 0.2369 | 20.3396 | 0.4657 | 63.0725 |
| 0.1163 | 16.0 | 2864 | 0.2343 | 20.8757 | 0.4650 | 63.0725 |
| 0.109 | 17.0 | 3043 | 0.2320 | 22.3445 | 0.4777 | 62.4046 |
| 0.1031 | 18.0 | 3222 | 0.2306 | 22.4122 | 0.4838 | 61.6412 |
| 0.0956 | 19.0 | 3401 | 0.2290 | 22.9322 | 0.4817 | 61.2595 |
| 0.0906 | 20.0 | 3580 | 0.2284 | 23.1472 | 0.4888 | 60.8779 |
| 0.0854 | 21.0 | 3759 | 0.2261 | 23.5794 | 0.4931 | 61.1641 |
| 0.0817 | 22.0 | 3938 | 0.2272 | 24.8709 | 0.4949 | 59.9237 |
Framework versions
- Transformers 4.56.1
- Pytorch 2.8.0+cu126
- Datasets 4.0.0
- Tokenizers 0.22.0