metadata
license: mit
base_model: cointegrated/rut5-small
tags:
- generated_from_trainer
model-index:
- name: text-normalization-ru-new
results: []
text-normalization-ru-new
This model is a fine-tuned version of cointegrated/rut5-small on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.0985
- Mean Distance: 0
- Max Distance: 9
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: 0.001
- train_batch_size: 30
- eval_batch_size: 30
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 30
Training results
| Training Loss | Epoch | Step | Validation Loss | Mean Distance | Max Distance |
|---|---|---|---|---|---|
| 0.181 | 1.0 | 2598 | 0.2140 | 4 | 36 |
| 0.1067 | 2.0 | 5196 | 0.1416 | 2 | 29 |
| 0.0801 | 3.0 | 7794 | 0.1098 | 2 | 22 |
| 0.0575 | 4.0 | 10392 | 0.1081 | 2 | 18 |
| 0.0452 | 5.0 | 12990 | 0.0897 | 1 | 14 |
| 0.0372 | 6.0 | 15588 | 0.0720 | 1 | 15 |
| 0.0323 | 7.0 | 18186 | 0.0840 | 1 | 12 |
| 0.0267 | 8.0 | 20784 | 0.0768 | 1 | 16 |
| 0.0231 | 9.0 | 23382 | 0.0697 | 1 | 10 |
| 0.0199 | 10.0 | 25980 | 0.0717 | 1 | 9 |
| 0.0168 | 11.0 | 28578 | 0.0812 | 1 | 16 |
| 0.0148 | 12.0 | 31176 | 0.0961 | 1 | 12 |
| 0.0128 | 13.0 | 33774 | 0.0823 | 1 | 9 |
| 0.0112 | 14.0 | 36372 | 0.0766 | 1 | 12 |
| 0.0093 | 15.0 | 38970 | 0.0713 | 1 | 9 |
| 0.0083 | 16.0 | 41568 | 0.0847 | 1 | 14 |
| 0.0076 | 17.0 | 44166 | 0.0863 | 1 | 11 |
| 0.0064 | 18.0 | 46764 | 0.0830 | 1 | 14 |
| 0.0054 | 19.0 | 49362 | 0.0884 | 1 | 11 |
| 0.0052 | 20.0 | 51960 | 0.0821 | 1 | 10 |
| 0.0045 | 21.0 | 54558 | 0.0915 | 1 | 14 |
| 0.0037 | 22.0 | 57156 | 0.0931 | 1 | 14 |
| 0.0036 | 23.0 | 59754 | 0.0941 | 1 | 9 |
| 0.0028 | 24.0 | 62352 | 0.0861 | 1 | 13 |
| 0.0026 | 25.0 | 64950 | 0.0912 | 1 | 12 |
| 0.0024 | 26.0 | 67548 | 0.0916 | 0 | 9 |
| 0.002 | 27.0 | 70146 | 0.0888 | 0 | 9 |
| 0.0017 | 28.0 | 72744 | 0.0888 | 0 | 9 |
| 0.0017 | 29.0 | 75342 | 0.0952 | 0 | 9 |
| 0.0014 | 30.0 | 77940 | 0.0985 | 0 | 9 |
Framework versions
- Transformers 4.32.1
- Pytorch 2.0.1+cu117
- Datasets 2.14.4
- Tokenizers 0.13.3