Skip to main content

Table 1 The common parameters of the Python classes in transformers-sklearn

From: Transformers-sklearn: a toolkit for medical language understanding with transformer-based models

Name

Function

model_type

Specifies which type of model initialization style should be used

model_name_or_path

Specifies which pre-trained model should be used

max_seq_length

Sets the max length of the sequence that could be accepted

per_gpu_train_batch_size

Sets the batch size per GPU

learning_rate

Sets the learning rate of the model

num_train_epochs

Sets the number of training epochs of the model

no_cuda

Sets whether the GPU is used for training or predicting