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: 0.0003
Mean Distance: 0
Max Distance: 0

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: 25

Training results

Training Loss	Epoch	Step	Validation Loss	Max Distance
0.0013	1.0	69	0.0028	2
0.0006	2.0	138	0.0026	3
0.0025	3.0	207	0.0039	3
0.0004	4.0	276	0.0037	3
0.0005	5.0	345	0.0091	3
0.0009	6.0	414	0.0006	0
0.0016	7.0	483	0.0003	0
0.0012	8.0	552	0.0111	5
0.0008	9.0	621	0.0004	0
0.0018	10.0	690	0.0003	0
0.0028	11.0	759	0.0003	0
0.0008	12.0	828	0.0003	0
0.001	13.0	897	0.0004	2
0.0026	14.0	966	0.0005	2
0.0015	15.0	1035	0.0007	3
0.0009	16.0	1104	0.0007	3
0.0014	17.0	1173	0.0003	0
0.001	18.0	1242	0.0004	0
0.0007	19.0	1311	0.0013	3
0.0013	20.0	1380	0.0013	3
0.0007	21.0	1449	0.0003	0
0.0016	22.0	1518	0.0003	0
0.0013	23.0	1587	0.0003	0
0.0004	24.0	1656	0.0003	0
0.001	25.0	1725	0.0003	0

Framework versions

Transformers 4.32.1
Pytorch 2.0.1+cu117
Datasets 2.14.4
Tokenizers 0.13.3