metadata
license: apache-2.0
tags:
- generated_from_trainer
model-index:
- name: polish_transliterator
results: []
polish_transliterator
This model is a fine-tuned version of t5-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.8067
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: 5e-06
- train_batch_size: 1
- eval_batch_size: 1
- 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 |
|---|---|---|---|
| 2.1007 | 1.0 | 572 | 1.4199 |
| 1.8529 | 2.0 | 1144 | 1.1556 |
| 1.5074 | 3.0 | 1716 | 0.9571 |
| 1.215 | 4.0 | 2288 | 0.9064 |
| 1.105 | 5.0 | 2860 | 0.8728 |
| 1.0574 | 6.0 | 3432 | 0.8465 |
| 0.8808 | 7.0 | 4004 | 0.8281 |
| 0.8468 | 8.0 | 4576 | 0.8177 |
| 0.8273 | 9.0 | 5148 | 0.8096 |
| 0.8472 | 10.0 | 5720 | 0.8067 |
Framework versions
- Transformers 4.28.0
- Pytorch 2.0.0+cu118
- Datasets 2.11.0
- Tokenizers 0.13.3