|
--- |
|
library_name: transformers |
|
base_model: facebook/mbart-large-50-many-to-many-mmt |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- bleu |
|
model-index: |
|
- name: mbart-large-50-finetuned-en-to-ba |
|
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. --> |
|
|
|
# mbart-large-50-finetuned-en-to-ba |
|
|
|
This model is a fine-tuned version of [facebook/mbart-large-50-many-to-many-mmt](https://huggingface.co/facebook/mbart-large-50-many-to-many-mmt) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 2.8138 |
|
- Bleu: 6.0837 |
|
- Gen Len: 46.235 |
|
|
|
## 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: 16 |
|
- eval_batch_size: 16 |
|
- seed: 0 |
|
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments |
|
- lr_scheduler_type: linear |
|
- training_steps: 12000 |
|
- mixed_precision_training: Native AMP |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Bleu | Gen Len | |
|
|:-------------:|:------:|:-----:|:---------------:|:------:|:-------:| |
|
| 1.9435 | 0.6949 | 1000 | 2.6296 | 3.6886 | 47.431 | |
|
| 1.2417 | 1.3899 | 2000 | 2.5577 | 4.294 | 52.199 | |
|
| 1.0716 | 2.0848 | 3000 | 2.5397 | 5.2872 | 50.81 | |
|
| 0.9341 | 2.7797 | 4000 | 2.5230 | 5.6413 | 46.144 | |
|
| 0.843 | 3.4746 | 5000 | 2.5927 | 5.891 | 47.693 | |
|
| 0.7785 | 4.1696 | 6000 | 2.6120 | 6.477 | 45.289 | |
|
| 0.7117 | 4.8645 | 7000 | 2.6530 | 6.1367 | 45.901 | |
|
| 0.6505 | 5.5594 | 8000 | 2.7041 | 6.0327 | 46.667 | |
|
| 0.6209 | 6.2543 | 9000 | 2.7524 | 6.4298 | 46.083 | |
|
| 0.5857 | 6.9493 | 10000 | 2.7564 | 6.2065 | 47.203 | |
|
| 0.5484 | 7.6442 | 11000 | 2.7948 | 6.5806 | 46.407 | |
|
| 0.5317 | 8.3391 | 12000 | 2.8138 | 6.0837 | 46.235 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.46.3 |
|
- Pytorch 2.4.0 |
|
- Datasets 3.1.0 |
|
- Tokenizers 0.20.3 |
|
|
