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 the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.0152
- Mean Distance: 0
- Max Distance: 1
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: 15
- eval_batch_size: 15
- 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 |
|---|---|---|---|---|---|
| 0.0005 | 1.0 | 13747 | 0.0151 | 0 | 3 |
| 0.0005 | 2.0 | 27494 | 0.0173 | 0 | 3 |
| 0.0006 | 3.0 | 41241 | 0.0136 | 0 | 3 |
| 0.0007 | 4.0 | 54988 | 0.0141 | 0 | 2 |
| 0.0006 | 5.0 | 68735 | 0.0155 | 0 | 4 |
| 0.0005 | 6.0 | 82482 | 0.0183 | 0 | 4 |
| 0.0005 | 7.0 | 96229 | 0.0218 | 0 | 4 |
| 0.0005 | 8.0 | 109976 | 0.0162 | 0 | 1 |
| 0.0005 | 9.0 | 123723 | 0.0147 | 0 | 3 |
| 0.0005 | 10.0 | 137470 | 0.0188 | 0 | 5 |
| 0.0004 | 11.0 | 151217 | 0.0168 | 0 | 1 |
| 0.0004 | 12.0 | 164964 | 0.0172 | 0 | 4 |
| 0.0004 | 13.0 | 178711 | 0.0168 | 0 | 3 |
| 0.0004 | 14.0 | 192458 | 0.0162 | 0 | 2 |
| 0.0004 | 15.0 | 206205 | 0.0165 | 0 | 2 |
| 0.0003 | 16.0 | 219952 | 0.0151 | 0 | 3 |
| 0.0004 | 17.0 | 233699 | 0.0137 | 0 | 1 |
| 0.0003 | 18.0 | 247446 | 0.0146 | 0 | 3 |
| 0.0003 | 19.0 | 261193 | 0.0152 | 0 | 1 |
| 0.0003 | 20.0 | 274940 | 0.0152 | 0 | 1 |
Framework versions
- Transformers 4.32.1
- Pytorch 2.0.1+cu117
- Datasets 2.14.4
- Tokenizers 0.13.3