metadata
license: apache-2.0
tags:
- generated_from_trainer
metrics:
- bleu
model-index:
- name: tokipona_to_eng_model_v0.4
results: []
tokipona_to_eng_model_v0.4
This model is a fine-tuned version of t5-small on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 3.8256
- Bleu: 0.6866
- Gen Len: 12.7094
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: 15
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Bleu | Gen Len |
|---|---|---|---|---|---|
| No log | 1.0 | 61 | 3.9664 | 0.2896 | 14.4631 |
| No log | 2.0 | 122 | 3.9429 | 0.4145 | 14.1527 |
| No log | 3.0 | 183 | 3.9243 | 0.5075 | 14.3103 |
| No log | 4.0 | 244 | 3.9089 | 0.4954 | 14.3498 |
| No log | 5.0 | 305 | 3.8915 | 0.4979 | 13.8966 |
| No log | 6.0 | 366 | 3.8795 | 0.6291 | 13.2611 |
| No log | 7.0 | 427 | 3.8690 | 0.6926 | 13.4138 |
| No log | 8.0 | 488 | 3.8568 | 0.6898 | 13.0493 |
| 4.0338 | 9.0 | 549 | 3.8464 | 0.7046 | 12.9212 |
| 4.0338 | 10.0 | 610 | 3.8395 | 0.6875 | 12.734 |
| 4.0338 | 11.0 | 671 | 3.8343 | 0.6789 | 12.9557 |
| 4.0338 | 12.0 | 732 | 3.8306 | 0.6854 | 12.8571 |
| 4.0338 | 13.0 | 793 | 3.8279 | 0.6854 | 12.8571 |
| 4.0338 | 14.0 | 854 | 3.8265 | 0.6855 | 12.7044 |
| 4.0338 | 15.0 | 915 | 3.8256 | 0.6866 | 12.7094 |
Framework versions
- Transformers 4.28.1
- Pytorch 2.0.0+cu118
- Datasets 2.11.0
- Tokenizers 0.13.3