metadata

license: apache-2.0
base_model: anferico/bert-for-patents
tags:
  - generated_from_keras_callback
model-index:
  - name: BERT_for_Patents_PatentAbstract2IncomeGroup_2500
    results: []

BERT_for_Patents_PatentAbstract2IncomeGroup_2500

This model is a fine-tuned version of anferico/bert-for-patents on a small subset (2500 samples) of the Google Patents Public Dataset. It uses patent abstracts to predict the income group of the country that has filed the patent. This is a proof-of-concept for a future text classification task.

It achieves the following results on the evaluation set:

Train Loss: 0.0345
Validation Loss: 0.3008
Train Accuracy: 0.9028
Epoch: 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:

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': 2e-05, 'decay_steps': 448, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}}, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False}
training_precision: float32

Training results

Train Loss	Validation Loss	Train Accuracy	Epoch
0.4100	0.3570	0.8401	0
0.2116	0.2951	0.8683	1
0.0859	0.2870	0.8934	2
0.0345	0.3008	0.9028	3

Framework versions

Transformers 4.31.0
TensorFlow 2.12.0
Datasets 2.14.0
Tokenizers 0.13.3