README.md

SmartBERT CodeBERT 16000

Trained on 16000 (1, 16000) smart contracts

Evaluated on 4000 (20000, 4000) smart contracts

Replace all the \n, \t in the function code with one space.

Base Model: CodeBERT-mlm-base

Training Setup

    training_args = TrainingArguments(
        output_dir=OUTPUT_DIR,
        overwrite_output_dir=True,
        num_train_epochs=20,
        per_device_train_batch_size=64,
        save_steps=10000,
        save_total_limit=2,
        evaluation_strategy="steps",
        eval_steps=10000,
        resume_from_checkpoint=checkpoint
    )