|
|
--- |
|
|
tags: |
|
|
- translation |
|
|
- generated_from_trainer |
|
|
metrics: |
|
|
- bleu |
|
|
model-index: |
|
|
- name: ar2enCkptfromgendata_01 |
|
|
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. --> |
|
|
|
|
|
# ar2enCkptfromgendata_01 |
|
|
|
|
|
This model is a fine-tuned version of [Botnoi/ckpt_marian_mt_ar_en_health](https://huggingface.co/Botnoi/ckpt_marian_mt_ar_en_health) on the None dataset. |
|
|
It achieves the following results on the evaluation set: |
|
|
- Loss: 0.6115 |
|
|
- Bleu: 59.8404 |
|
|
|
|
|
## 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: 10 |
|
|
|
|
|
### Training results |
|
|
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Bleu | |
|
|
|:-------------:|:-----:|:----:|:---------------:|:-------:| |
|
|
| 0.8149 | 1.0 | 151 | 0.6818 | 55.1419 | |
|
|
| 0.5402 | 2.0 | 302 | 0.6288 | 57.8755 | |
|
|
| 0.4761 | 3.0 | 453 | 0.6098 | 58.7418 | |
|
|
| 0.3477 | 4.0 | 604 | 0.6056 | 59.0117 | |
|
|
| 0.3204 | 5.0 | 755 | 0.6039 | 59.7086 | |
|
|
| 0.262 | 6.0 | 906 | 0.6030 | 59.5996 | |
|
|
| 0.2531 | 7.0 | 1057 | 0.6072 | 59.4558 | |
|
|
| 0.223 | 8.0 | 1208 | 0.6091 | 59.8874 | |
|
|
| 0.2101 | 9.0 | 1359 | 0.6108 | 59.7567 | |
|
|
| 0.2044 | 10.0 | 1510 | 0.6115 | 59.8404 | |
|
|
|
|
|
|
|
|
### Framework versions |
|
|
|
|
|
- Transformers 4.30.1 |
|
|
- Pytorch 2.0.1+cu118 |
|
|
- Datasets 2.12.0 |
|
|
- Tokenizers 0.13.3 |
|
|
|
