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
Downloads last month
16
Inference Examples
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.

Model tree for SIA86/bert-cased-text-classification

Finetuned
(551)
this model