|
--- |
|
license: cc-by-nc-4.0 |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- bleu |
|
model-index: |
|
- name: easyword_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. --> |
|
|
|
# easyword_model |
|
|
|
This model is a fine-tuned version of [facebook/nllb-200-distilled-600M](https://huggingface.co/facebook/nllb-200-distilled-600M) on the None dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 2.7704 |
|
- Bleu: 9.5346 |
|
- Gen Len: 6.2609 |
|
|
|
## 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 | |
|
|:-------------:|:-----:|:----:|:---------------:|:------:|:-------:| |
|
| No log | 1.0 | 31 | 3.4204 | 4.1421 | 6.7329 | |
|
| No log | 2.0 | 62 | 3.2154 | 4.8111 | 5.9255 | |
|
| No log | 3.0 | 93 | 3.1073 | 5.8324 | 5.9317 | |
|
| No log | 4.0 | 124 | 3.0242 | 8.0401 | 5.8944 | |
|
| No log | 5.0 | 155 | 2.9829 | 5.0246 | 6.0435 | |
|
| No log | 6.0 | 186 | 2.9363 | 8.2048 | 5.9752 | |
|
| No log | 7.0 | 217 | 2.9103 | 5.9443 | 6.0186 | |
|
| No log | 8.0 | 248 | 2.8834 | 6.0896 | 6.0373 | |
|
| No log | 9.0 | 279 | 2.8792 | 6.0346 | 6.0621 | |
|
| No log | 10.0 | 310 | 2.8772 | 6.0639 | 6.0497 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.29.2 |
|
- Pytorch 2.0.1+cu117 |
|
- Datasets 2.12.0 |
|
- Tokenizers 0.13.3 |
|
|
