|
--- |
|
license: mit |
|
base_model: alexue4/text-normalization-ru-new |
|
tags: |
|
- generated_from_trainer |
|
model-index: |
|
- name: text-normalization-ru-new |
|
results: [] |
|
--- |
|
|
|
<!-- This model card has been generated automatically according to the information the Trainer had access to. You |
|
should probably proofread and complete it, then remove this comment. --> |
|
|
|
# text-normalization-ru-new |
|
|
|
This model is a fine-tuned version of [alexue4/text-normalization-ru-new](https://huggingface.co/alexue4/text-normalization-ru-new) on the None dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.0480 |
|
- Mean Distance: 0 |
|
- Max Distance: 40 |
|
|
|
## 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: 10 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Mean Distance | Max Distance | |
|
|:-------------:|:-----:|:------:|:---------------:|:-------------:|:------------:| |
|
| 0.0163 | 1.0 | 23701 | 0.0428 | 0 | 43 | |
|
| 0.0132 | 2.0 | 47402 | 0.0420 | 0 | 44 | |
|
| 0.0111 | 3.0 | 71103 | 0.0444 | 0 | 35 | |
|
| 0.0095 | 4.0 | 94804 | 0.0449 | 0 | 43 | |
|
| 0.0088 | 5.0 | 118505 | 0.0446 | 0 | 40 | |
|
| 0.0076 | 6.0 | 142206 | 0.0462 | 0 | 33 | |
|
| 0.0074 | 7.0 | 165907 | 0.0466 | 0 | 38 | |
|
| 0.0068 | 8.0 | 189608 | 0.0478 | 0 | 39 | |
|
| 0.0069 | 9.0 | 213309 | 0.0489 | 0 | 39 | |
|
| 0.0061 | 10.0 | 237010 | 0.0480 | 0 | 40 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.32.1 |
|
- Pytorch 2.0.1+cu117 |
|
- Datasets 2.14.4 |
|
- Tokenizers 0.13.3 |
|
|
