The training dataset distinguishes between the beginning and continuation of an entity so that if there are back-to-back entities of the same type, the model can output where the second entity begins. As in the dataset, each token will be classified as one of the following classes:

Entity	Description
O	Outside of a named entity
B-Generic_Info.ANNUAL_REVENUES	Beginning of annual revenues entity
I-Generic_Info.ANNUAL_REVENUES	Continuation of annual revenues entity
B-Parties.ACQUIRED_COMPANY	Beginning of acquired company entity
I-Parties.ACQUIRED_COMPANY	Continuation of acquired company entity
B-Parties.BUYING_COMPANY	Beginning of buying company entity
I-Parties.BUYING_COMPANY	Continuation of buying company entity
B-Parties.SELLING_COMPANY	Beginning of selling company entity
I-Parties.SELLING_COMPANY	Continuation of selling company entity
B-Advisors.GENERIC_CONSULTING_COMPANY	Beginning of generic consulting company entity
I-Advisors.GENERIC_CONSULTING_COMPANY	Continuation of generic consulting company entity
B-Advisors.LEGAL_CONSULTING_COMPANY	Beginning of legal consulting company entity
I-Advisors.LEGAL_CONSULTING_COMPANY	Continuation of legal consulting company entity

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

learning_rate: 5e-05
train_batch_size: 8
eval_batch_size: 8
seed: 42
optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: linear
num_epochs: 3.0

Training results

Framework versions

Transformers 4.48.0.dev0
Pytorch 2.5.1
Datasets 3.1.0
Tokenizers 0.21.0

whataboutyou-ai/financial_bert

financial_bert

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

whataboutyou-ai/
financial_bert