SIA86's picture
Update README.md
a8c4e67
|
raw
history blame
3.65 kB
metadata
license: apache-2.0
base_model: bert-base-multilingual-cased
tags:
  - generated_from_keras_callback
model-index:
  - name: SIA86/bert-cased-text-classification
    results: []
widget:
  - text: Не могу отправить письмо с электронной почты.
    example_title: Пример 1
  - text: Прошу установить AutoCad на мой компьютер.
    example_title: Пример 2

SIA86/bert-cased-text-classification

This model is a fine-tuned version of bert-base-multilingual-cased on an unknown dataset. It achieves the following results on the evaluation set:

  • Train Loss: 0.0719
  • Train Accuracy: 0.9772
  • Validation Loss: 0.8075
  • Validation Accuracy: 0.8485
  • Epoch: 19

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:

  • optimizer: {'name': 'Adam', 'weight_decay': None, 'clipnorm': None, 'global_clipnorm': None, 'clipvalue': None, 'use_ema': False, 'ema_momentum': 0.99, 'ema_overwrite_frequency': None, 'jit_compile': True, 'is_legacy_optimizer': False, 'learning_rate': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 5e-05, 'decay_steps': 2320, 'end_learning_rate': 0, 'power': 1.0, 'cycle': False, 'name': None}}, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False}
  • training_precision: float32

Training results

Train Loss Train Accuracy Validation Loss Validation Accuracy Epoch
2.8423 0.2313 2.5340 0.3593 0
2.4502 0.3181 2.3051 0.3333 1
2.2064 0.3648 1.9143 0.4416 2
1.6431 0.5494 1.5876 0.5411 3
1.1282 0.6960 1.4404 0.6190 4
0.8128 0.7861 1.0982 0.7143 5
0.6016 0.8534 1.0513 0.7532 6
0.4495 0.8947 0.9108 0.7879 7
0.2991 0.9414 0.8437 0.8182 8
0.2068 0.9609 0.7936 0.8182 9
0.1594 0.9729 0.8264 0.8182 10
0.1364 0.9707 0.7984 0.8312 11
0.1217 0.9707 0.7948 0.8268 12
0.1053 0.9729 0.7847 0.8398 13
0.0968 0.9729 0.7850 0.8398 14
0.0879 0.9739 0.7976 0.8442 15
0.0821 0.9718 0.8005 0.8442 16
0.0770 0.9750 0.7967 0.8485 17
0.0772 0.9772 0.8043 0.8485 18
0.0719 0.9772 0.8075 0.8485 19

Framework versions

  • Transformers 4.31.0
  • TensorFlow 2.12.0
  • Datasets 2.14.1
  • Tokenizers 0.13.3