t5-russian-spell / README.md
Alikhan Urumov
update model card README.md
641de9d
|
raw
history blame
1.34 kB
metadata
tags:
  - generated_from_trainer
model-index:
  - name: t5-russian-spell
    results: []

t5-russian-spell

This model is a fine-tuned version of sberbank-ai/ruT5-base on the None dataset. It achieves the following results on the evaluation set:

  • eval_loss: 0.5568
  • eval_rouge1: 41.1665
  • eval_rouge2: 18.3827
  • eval_rougeL: 41.2147
  • eval_rougeLsum: 41.1122
  • eval_gen_len: 62.512
  • eval_runtime: 183.2248
  • eval_samples_per_second: 2.729
  • eval_steps_per_second: 0.344
  • epoch: 0.4
  • step: 5000

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: 0.0002
  • train_batch_size: 8
  • eval_batch_size: 8
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 1
  • mixed_precision_training: Native AMP

Framework versions

  • Transformers 4.17.0
  • Pytorch 1.10.0+cu111
  • Datasets 2.0.0
  • Tokenizers 0.11.6