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 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
] train_df = pd.DataFrame(train_data) train_df.columns = ["text", "labels"] # Preparing eval data 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,)