metadata

license: apache-2.0
base_model: bert-base-multilingual-cased
tags:
  - generated_from_keras_callback
model-index:
  - name: >-
      bert-base-multilingual-cased-finetuned-openalex-topic-classification-title-abstract
    results: []

bert-base-multilingual-cased-finetuned-openalex-topic-classification-title-abstract

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: 2.4942
Train Categorical Accuracy: 0.0002
Train Top 2 Categorical Accuracy: 0.0005
Train Top 10 Categorical Accuracy: 0.0024
Validation Loss: 3.0737
Validation Categorical Accuracy: 0.0003
Validation Top 2 Categorical Accuracy: 0.0006
Validation Top 10 Categorical Accuracy: 0.0028
Train Accuracy: 0.4846
Epoch: 7

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': {'module': 'transformers.optimization_tf', 'class_name': 'WarmUp', 'config': {'initial_learning_rate': 6e-05, 'decay_schedule_fn': {'module': 'keras.optimizers.schedules', 'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 6e-05, 'decay_steps': 335420, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}, 'registered_name': None}, 'warmup_steps': 500, 'power': 1.0, 'name': None}, 'registered_name': 'WarmUp'}, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False}
training_precision: float32

Training results

Train Loss	Train Categorical Accuracy	Train Top 2 Categorical Accuracy	Train Top 10 Categorical Accuracy	Validation Loss	Validation Categorical Accuracy	Validation Top 2 Categorical Accuracy	Validation Top 10 Categorical Accuracy	Train Accuracy	Epoch
4.8075	0.0001	0.0002	0.0020	3.6686	0.0000	0.0001	0.0017	0.3839	0
3.4867	0.0002	0.0004	0.0028	3.3360	0.0001	0.0002	0.0014	0.4337	1
3.1865	0.0002	0.0004	0.0027	3.2005	0.0002	0.0005	0.0033	0.4556	2
2.9969	0.0002	0.0005	0.0027	3.1379	0.0001	0.0002	0.0014	0.4675	3
2.8489	0.0002	0.0004	0.0025	3.0900	0.0002	0.0005	0.0031	0.4746	4
2.7212	0.0002	0.0005	0.0025	3.0744	0.0002	0.0003	0.0021	0.4799	5
2.6035	0.0002	0.0004	0.0025	3.0660	0.0002	0.0004	0.0023	0.4831	6
2.4942	0.0002	0.0005	0.0024	3.0737	0.0003	0.0006	0.0028	0.4846	7

Framework versions

Transformers 4.35.2
TensorFlow 2.13.0
Datasets 2.15.0
Tokenizers 0.15.0