def hyperargs(): # type: () -> {}
"""
Builds different sets of arguments for the classifier. Must be the same for
training and predicting.
:return: the labeled arguments
:rtype: {}
"""
retdict = {}
for curwindow in [128, 64, 32, 256]:
for curstride in [0.7, 0.8, 0.9]:
accargs = ClassificationArgs()
accargs.num_train_epochs = 5
accargs.fp16 = False
accargs.overwrite_output_dir = True
accargs.evaluate_during_training = False
accargs.sliding_window = True
accargs.max_seq_length = curwindow
accargs.stride = curstride
accargs.labels_list = [1, 0]
accargs.save_eval_checkpoints = False
accargs.save_model_every_epoch = False
accargs.silent = True
accargs.manual_seed = 18
retdict['basic5epochs' + str(curwindow) + 'win' +
str(int(curstride * 10.0)) + 'stride'] = accargs
return retdict
def transformer2(model_name, train_df, eval_df, epochs, labels):
logging.basicConfig(level=logging.INFO)
transformers_logger = logging.getLogger("transformers")
transformers_logger.setLevel(logging.WARNING)
model_args = ClassificationArgs()
model_args.num_train_epochs=epochs
model_args.labels_list = [0, 1, 2, 3, 4]
model_args.reprocess_input_data=True
model_args.overwrite_output_dir=True
model = ClassificationModel(model_name, 'bert-base-cased', num_labels=labels, args=model_args)
# You can set class weights by using the optional weight argument
# Train the model
model.train_model(train_df)
# Evaluate the model
result, model_outputs, wrong_predictions = model.eval_model(eval_df)
# You can set class weights by using the optional weight argument
return model, result, model_outputs, wrong_predictions
def buildbertargs(): # type: () -> ClassificationArgs
"""
Builds arguments for the classifier. Must be the same for
training and predicting.
:return: the arguments
:rtype: ClassificationArgs
"""
accargs = ClassificationArgs()
accargs.num_train_epochs = 5
accargs.fp16 = False
accargs.overwrite_output_dir = True
accargs.evaluate_during_training = False
accargs.sliding_window = True
accargs.max_seq_length = 256
accargs.stride = 0.9
accargs.labels_list = [1, 0]
accargs.save_model_every_epoch = False
accargs.silent = True
accargs.manual_seed = 18
return accargs
eval_data = [
["Theoden was the king of Rohan", "true"],
["Merry was the king of Rohan", "false"],
]
eval_df = pd.DataFrame(eval_data)
eval_df.columns = ["text", "labels"]
model_args = ClassificationArgs()
model_args.reprocess_input_data = True
model_args.overwrite_output_dir = True
model_args.evaluate_during_training = True
model_args.manual_seed = 4
model_args.use_multiprocessing = True
model_args.train_batch_size = 16
model_args.eval_batch_size = 8
model_args.labels_list = ["true", "false"]
model_args.wandb_project = "Simple Sweep"
def train():
# Initialize a new wandb run
wandb.init()
# Create a TransformerModel
model = ClassificationModel("roberta", "roberta-base", use_cuda=True, args=model_args, sweep_config=wandb.config,)
# Train the model
model.train_model(train_df, eval_df=eval_df)
# Evaluate the model
model.eval_model(eval_df)
model_args.evaluate_during_training = True
model_args.evaluate_during_training_silent = False
model_args.evaluate_during_training_steps = 1000
model_args.learning_rate = 4e-4
model_args.manual_seed = 4
model_args.max_seq_length = 256
model_args.multiprocessing_chunksize = 5000
model_args.no_cache = True
model_args.no_save = True
model_args.num_train_epochs = 10
model_args.overwrite_output_dir = True
model_args.reprocess_input_data = True
model_args.train_batch_size = 16
model_args.gradient_accumulation_steps = 2
model_args.train_custom_parameters_only = False
model_args.labels_list = ["not_entailment", "entailment"]
model_args.wandb_project = "RTE - Hyperparameter Optimization"
def train():
# Initialize a new wandb run
wandb.init()
# Create a TransformerModel
model = ClassificationModel(
"roberta",
"roberta-large",
use_cuda=True,
args=model_args,
sweep_config=wandb.config,
)