|
--- |
|
license: apache-2.0 |
|
base_model: drewcurran/translation_model |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- bleu |
|
model-index: |
|
- name: translation_model |
|
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. --> |
|
|
|
# translation_model |
|
|
|
This model is a fine-tuned version of [drewcurran/translation_model](https://huggingface.co/drewcurran/translation_model) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 1.9529 |
|
- Bleu: 1.2244 |
|
- Gen Len: 18.0659 |
|
|
|
## 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 |
|
- mixed_precision_training: Native AMP |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Bleu | Gen Len | |
|
|:-------------:|:-----:|:-----:|:---------------:|:------:|:-------:| |
|
| 2.5538 | 1.0 | 4674 | 2.2471 | 0.7389 | 18.1428 | |
|
| 2.4606 | 2.0 | 9348 | 2.1615 | 0.8787 | 18.1105 | |
|
| 2.3877 | 3.0 | 14022 | 2.0981 | 0.963 | 18.0917 | |
|
| 2.3433 | 4.0 | 18696 | 2.0538 | 1.0353 | 18.0855 | |
|
| 2.2914 | 5.0 | 23370 | 2.0186 | 1.0902 | 18.0692 | |
|
| 2.2565 | 6.0 | 28044 | 1.9939 | 1.1566 | 18.0789 | |
|
| 2.2539 | 7.0 | 32718 | 1.9756 | 1.1935 | 18.0686 | |
|
| 2.2262 | 8.0 | 37392 | 1.9628 | 1.1998 | 18.0759 | |
|
| 2.2097 | 9.0 | 42066 | 1.9556 | 1.2209 | 18.0706 | |
|
| 2.2021 | 10.0 | 46740 | 1.9529 | 1.2244 | 18.0659 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.40.1 |
|
- Pytorch 2.3.0+cu121 |
|
- Datasets 2.19.0 |
|
- Tokenizers 0.19.1 |
|
|
