|
--- |
|
metrics: |
|
- bleu |
|
tags: |
|
- generated_from_trainer |
|
model-index: |
|
- name: mt5-small-ainu |
|
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. --> |
|
|
|
# mt5-small-ainu |
|
|
|
This model was trained from scratch on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 1.8639 |
|
- Bleu: 19.8267 |
|
|
|
## 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: 0.0006 |
|
- train_batch_size: 32 |
|
- eval_batch_size: 32 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- num_epochs: 20 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Bleu | |
|
|:-------------:|:-----:|:-----:|:---------------:|:-------:| |
|
| 2.4842 | 1.0 | 4670 | 2.1813 | 8.3904 | |
|
| 2.0771 | 2.0 | 9340 | 1.9269 | 5.7433 | |
|
| 1.8222 | 3.0 | 14010 | 1.8170 | 12.8222 | |
|
| 1.6758 | 4.0 | 18680 | 1.7569 | 14.3024 | |
|
| 1.5447 | 5.0 | 23350 | 1.7277 | 12.3842 | |
|
| 1.4545 | 6.0 | 28020 | 1.7188 | 14.1082 | |
|
| 1.3417 | 7.0 | 32690 | 1.7104 | 16.6177 | |
|
| 1.2347 | 8.0 | 37360 | 1.7262 | 17.4827 | |
|
| 1.1565 | 9.0 | 42030 | 1.7268 | 17.7124 | |
|
| 1.081 | 10.0 | 46700 | 1.7581 | 18.6729 | |
|
| 1.02 | 11.0 | 51370 | 1.7768 | 20.2419 | |
|
| 0.9513 | 12.0 | 56040 | 1.8162 | 20.0469 | |
|
| 0.8934 | 13.0 | 60710 | 1.8370 | 19.7150 | |
|
| 0.8343 | 14.0 | 65380 | 1.8639 | 19.8267 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.40.1 |
|
- Pytorch 2.1.2 |
|
- Datasets 2.19.0 |
|
- Tokenizers 0.19.1 |
|
|