metadata
license: mit
base_model: alexue4/text-normalization-ru-new
tags:
- generated_from_trainer
model-index:
- name: text-normalization-ru-new
results: []
text-normalization-ru-new
This model is a fine-tuned version of alexue4/text-normalization-ru-new on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.0005
- Mean Distance: 0
- Max Distance: 3
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: 0.0001
- 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: 20
Training results
| Training Loss | Epoch | Step | Validation Loss | Mean Distance | Max Distance |
|---|---|---|---|---|---|
| 0.001 | 1.0 | 3459 | 0.0005 | 0 | 3 |
| 0.0007 | 2.0 | 6918 | 0.0005 | 0 | 3 |
| 0.0008 | 3.0 | 10377 | 0.0005 | 0 | 3 |
| 0.0007 | 4.0 | 13836 | 0.0006 | 0 | 3 |
| 0.0006 | 5.0 | 17295 | 0.0003 | 0 | 0 |
| 0.0006 | 6.0 | 20754 | 0.0003 | 0 | 0 |
| 0.0005 | 7.0 | 24213 | 0.0002 | 0 | 0 |
| 0.0006 | 8.0 | 27672 | 0.0005 | 0 | 3 |
| 0.0006 | 9.0 | 31131 | 0.0005 | 0 | 3 |
| 0.0005 | 10.0 | 34590 | 0.0006 | 0 | 3 |
| 0.0004 | 11.0 | 38049 | 0.0005 | 0 | 3 |
| 0.0005 | 12.0 | 41508 | 0.0004 | 0 | 0 |
| 0.0004 | 13.0 | 44967 | 0.0004 | 0 | 0 |
| 0.0004 | 14.0 | 48426 | 0.0005 | 0 | 0 |
| 0.0004 | 15.0 | 51885 | 0.0004 | 0 | 0 |
| 0.0004 | 16.0 | 55344 | 0.0005 | 0 | 3 |
| 0.0004 | 17.0 | 58803 | 0.0005 | 0 | 3 |
| 0.0004 | 18.0 | 62262 | 0.0005 | 0 | 3 |
| 0.0004 | 19.0 | 65721 | 0.0005 | 0 | 3 |
| 0.0004 | 20.0 | 69180 | 0.0005 | 0 | 3 |
Framework versions
- Transformers 4.32.1
- Pytorch 2.0.1+cu117
- Datasets 2.14.4
- Tokenizers 0.13.3