|
--- |
|
language: |
|
- en |
|
- bgc |
|
license: apache-2.0 |
|
base_model: google/mt5-base |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- bleu |
|
model-index: |
|
- name: tst-translation |
|
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. --> |
|
|
|
# tst-translation |
|
|
|
This model is a fine-tuned version of [google/mt5-base](https://huggingface.co/google/mt5-base) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 2.8421 |
|
- Bleu: 13.1948 |
|
- Gen Len: 49.9179 |
|
|
|
## 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: 0.0005 |
|
- train_batch_size: 8 |
|
- eval_batch_size: 16 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- num_epochs: 20.0 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Bleu | Gen Len | |
|
|:-------------:|:-------:|:----:|:---------------:|:-------:|:-------:| |
|
| 3.4257 | 1.9900 | 400 | 2.1087 | 4.1008 | 77.8284 | |
|
| 1.8571 | 3.9801 | 800 | 1.9292 | 8.6198 | 61.1418 | |
|
| 1.2467 | 5.9701 | 1200 | 1.9779 | 10.7074 | 48.3184 | |
|
| 0.8749 | 7.9602 | 1600 | 2.0539 | 11.8538 | 49.3483 | |
|
| 0.6141 | 9.9502 | 2000 | 2.1948 | 12.4452 | 51.1269 | |
|
| 0.4446 | 11.9403 | 2400 | 2.3902 | 12.3052 | 48.0995 | |
|
| 0.3251 | 13.9303 | 2800 | 2.5698 | 12.5824 | 49.1244 | |
|
| 0.2501 | 15.9204 | 3200 | 2.6631 | 13.0619 | 50.6095 | |
|
| 0.1986 | 17.9104 | 3600 | 2.7877 | 13.0557 | 51.1443 | |
|
| 0.1692 | 19.9005 | 4000 | 2.8421 | 13.1948 | 49.9179 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.43.0.dev0 |
|
- Pytorch 2.3.0+cu121 |
|
- Datasets 2.20.0 |
|
- Tokenizers 0.19.1 |
|
|
