metadata
license: apache-2.0
tags:
- generated_from_trainer
metrics:
- bleu
model-index:
- name: tokipona_to_eng_model_v0.1
results: []
tokipona_to_eng_model_v0.1
This model is a fine-tuned version of t5-small on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 4.0205
- Bleu: 0.5374
- Gen Len: 13.665
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 | 55 | 4.4955 | 0.3076 | 17.3941 |
| No log | 2.0 | 110 | 4.3058 | 0.3156 | 17.0246 |
| No log | 3.0 | 165 | 4.2148 | 0.5398 | 14.8128 |
| No log | 4.0 | 220 | 4.1636 | 0.4959 | 14.069 |
| No log | 5.0 | 275 | 4.1297 | 0.5139 | 13.9557 |
| No log | 6.0 | 330 | 4.1066 | 0.5229 | 14.2906 |
| No log | 7.0 | 385 | 4.0838 | 0.5232 | 14.3005 |
| No log | 8.0 | 440 | 4.0668 | 0.5211 | 14.2217 |
| No log | 9.0 | 495 | 4.0554 | 0.5184 | 14.2512 |
| 4.4686 | 10.0 | 550 | 4.0436 | 0.6523 | 14.0296 |
| 4.4686 | 11.0 | 605 | 4.0366 | 0.5346 | 13.7291 |
| 4.4686 | 12.0 | 660 | 4.0295 | 0.5335 | 13.6946 |
| 4.4686 | 13.0 | 715 | 4.0244 | 0.535 | 13.6798 |
| 4.4686 | 14.0 | 770 | 4.0213 | 0.5367 | 13.6798 |
| 4.4686 | 15.0 | 825 | 4.0205 | 0.5374 | 13.665 |
Framework versions
- Transformers 4.28.0
- Pytorch 2.0.0+cu118
- Datasets 2.11.0
- Tokenizers 0.13.3