|
|
--- |
|
|
license: apache-2.0 |
|
|
tags: |
|
|
- translation |
|
|
- generated_from_trainer |
|
|
metrics: |
|
|
- bleu |
|
|
model-index: |
|
|
- name: En-Zu_update |
|
|
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. --> |
|
|
|
|
|
# En-Zu_update |
|
|
|
|
|
This model is a fine-tuned version of [kabelomalapane/test_model1.2_updated](https://huggingface.co/kabelomalapane/test_model1.2_updated) on the None dataset. |
|
|
It achieves the following results on the evaluation set: |
|
|
- Loss: 1.7101 |
|
|
- Bleu: 11.8551 |
|
|
|
|
|
## 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: 32 |
|
|
- seed: 42 |
|
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
|
- lr_scheduler_type: linear |
|
|
- num_epochs: 10 |
|
|
|
|
|
### Training results |
|
|
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Bleu | |
|
|
|:-------------:|:-----:|:-----:|:---------------:|:-------:| |
|
|
| 1.9111 | 1.0 | 1173 | 1.7594 | 11.7012 | |
|
|
| 1.7191 | 2.0 | 2346 | 1.7279 | 12.0250 | |
|
|
| 1.5709 | 3.0 | 3519 | 1.7172 | 10.6222 | |
|
|
| 1.4924 | 4.0 | 4692 | 1.7042 | 11.4224 | |
|
|
| 1.4188 | 5.0 | 5865 | 1.7051 | 11.4330 | |
|
|
| 1.3566 | 6.0 | 7038 | 1.6972 | 11.5300 | |
|
|
| 1.3141 | 7.0 | 8211 | 1.7041 | 11.4339 | |
|
|
| 1.2641 | 8.0 | 9384 | 1.7064 | 11.4030 | |
|
|
| 1.2437 | 9.0 | 10557 | 1.7079 | 11.4014 | |
|
|
| 1.2333 | 10.0 | 11730 | 1.7101 | 11.5164 | |
|
|
|
|
|
|
|
|
### Framework versions |
|
|
|
|
|
- Transformers 4.21.0 |
|
|
- Pytorch 1.12.0+cu113 |
|
|
- Datasets 2.4.0 |
|
|
- Tokenizers 0.12.1 |
|
|
|
