# 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,)
# Train the model
model.train_model(train_df, eval_df=eval_df)
# Evaluate the model
"save": model_saves[int(sys.argv[2])]
}
df = pd.read_csv("data.csv")
train_df = df.iloc[:wandb_config["samples"], :]
train_df.columns = ["text", "labels"]
eval_df = df.iloc[wandb_config["samples"]:, :]
eval_df.columns = ["text", "labels"]
model_args = ClassificationArgs()
model_args.num_train_epochs = wandb_config["epochs"]
model_args.eval_batch_size = wandb_config["eval_batch_size"]
model_args.train_batch_size = wandb_config["train_batch_size"]
model_args.wandb_project = "transformer-aes"
model_args.wandb_kwargs = {
"name": "{}-{}".format(wandb_config["model"], wandb_config["samples"])
}
model_args.learning_rate = wandb_config["lr"]
model_args.model = wandb_config["model"]
model_args.samples = wandb_config["samples"]
# model_args.max_seq_length = wandb_config["max_seq_length"]
model_args.regression = True
model_args.no_save = True
model_args.overwrite_output_dir = True
model_args.logging_steps = 1
model_args.evaluate_during_training = True
model_args.evaluate_during_training_verbose = True