metadata

license: mit
base_model: cointegrated/rut5-small
tags:
  - generated_from_trainer
model-index:
  - name: text-normalization-ru-new
    results: []
language:
  - ru
pipeline_tag: text2text-generation

text-normalization-ru-new

This model is a fine-tuned version of cointegrated/rut5-small on the Google Kadle and Custom dataset. It achieves the following results on the evaluation set:

Loss: 0.0008
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: 150
eval_batch_size: 150
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: 15

Framework versions

Transformers 4.37.2
Pytorch 2.1.0+cu121
Datasets 2.16.1
Tokenizers 0.15.1