|
--- |
|
base_model: facebook/mbart-large-50-many-to-many-mmt |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- bleu |
|
model-index: |
|
- name: mbart-large-50-many-to-many-mmt-finetuned-en-to-ta |
|
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-many-to-many-mmt-finetuned-en-to-ta |
|
|
|
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: 2.4647 |
|
- Bleu: 11.1468 |
|
- Gen Len: 13.55 |
|
|
|
## 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: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- num_epochs: 8 |
|
- mixed_precision_training: Native AMP |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Bleu | Gen Len | |
|
|:-------------:|:-----:|:----:|:---------------:|:-------:|:-------:| |
|
| No log | 1.0 | 5 | 4.5933 | 0.671 | 12.3 | |
|
| No log | 2.0 | 10 | 3.2502 | 1.6986 | 21.4 | |
|
| No log | 3.0 | 15 | 2.8232 | 2.4901 | 11.75 | |
|
| No log | 4.0 | 20 | 2.6240 | 5.2271 | 13.45 | |
|
| No log | 5.0 | 25 | 2.5471 | 3.0107 | 13.45 | |
|
| No log | 6.0 | 30 | 2.5015 | 5.5026 | 13.6 | |
|
| No log | 7.0 | 35 | 2.4671 | 6.4173 | 13.45 | |
|
| No log | 8.0 | 40 | 2.4647 | 11.1468 | 13.55 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.42.4 |
|
- Pytorch 2.3.1+cu121 |
|
- Datasets 2.20.0 |
|
- Tokenizers 0.19.1 |
|
|
