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: 0.0169
- 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 | Max Distance | Mean Distance |
|---|---|---|---|---|---|
| 0.001 | 1.0 | 13726 | 0.0114 | 5 | 0 |
| 0.0009 | 2.0 | 27452 | 0.0143 | 3 | 0 |
| 0.0008 | 3.0 | 41178 | 0.0145 | 3 | 0 |
| 0.0009 | 4.0 | 54904 | 0.0098 | 1 | 0 |
| 0.0007 | 5.0 | 68630 | 0.0130 | 2 | 0 |
| 0.0008 | 6.0 | 82356 | 0.0153 | 2 | 0 |
| 0.0007 | 7.0 | 96082 | 0.0128 | 2 | 0 |
| 0.0006 | 8.0 | 109808 | 0.0130 | 3 | 0 |
| 0.0006 | 9.0 | 123534 | 0.0158 | 5 | 0 |
| 0.0006 | 10.0 | 137260 | 0.0151 | 1 | 0 |
| 0.0005 | 11.0 | 150986 | 0.0167 | 1 | 0 |
| 0.0005 | 12.0 | 164712 | 0.0145 | 1 | 0 |
| 0.0005 | 13.0 | 178438 | 0.0160 | 1 | 0 |
| 0.0005 | 14.0 | 192164 | 0.0157 | 1 | 0 |
| 0.0004 | 15.0 | 205890 | 0.0157 | 1 | 0 |
| 0.0004 | 16.0 | 219616 | 0.0173 | 1 | 0 |
| 0.0004 | 17.0 | 233342 | 0.0159 | 1 | 0 |
| 0.0004 | 18.0 | 247068 | 0.0168 | 2 | 0 |
| 0.0004 | 19.0 | 260794 | 0.0168 | 0 | 1 |
| 0.0004 | 20.0 | 274520 | 0.0169 | 0 | 1 |
Framework versions
- Transformers 4.32.1
- Pytorch 2.0.1+cu117
- Datasets 2.14.4
- Tokenizers 0.13.3