$ python run.py [options]

Options:
  -h, --help            show this help message and exit
  --data_dir DATA_DIR   Path to datasets directory.
  --output_dir OUTPUT_DIR
                        The output directory where the model saves model checkpoints
  --lang {c,java}       Programming language.
  --expt_name EXPT_NAME
                        Name of experiment to log in Weights and Biases.
  --max_tokens MAX_TOKENS
                        Maximum number of tokens in a statement
  --max_stmts MAX_STMTS
                        Maxmimum number of statements
  --num_layers NUM_LAYERS
                        Number of layers for Transformer encoder
  --num_layers_stmt NUM_LAYERS_STMT
                        Number of layers for Self-Attention Network
  --forward_activation FORWARD_ACTIVATION
                        Non-linear activation function in encoder
  --hidden_size HIDDEN_SIZE
                        Hidden size of decoding MLP
  --intermediate_size INTERMEDIATE_SIZE
                        Dimensionality of feed-forward layer in Transformer
  --embedding_size EMBEDDING_SIZE
                        Dimensionality of encoder layers
  --num_heads NUM_HEADS
                        Number of attention heads
  --vocab_size VOCAB_SIZE
                        Vocabulary size
  --use_stmt_types      Use statement type information.
  --no_ssan             Do not use self-attention network for statement
                        encoding.
  --no_pe               Do not use statement-level position encoding.
  --no_tr               Do not use transformer encoder.
  --load_model_path LOAD_MODEL_PATH
                        Path to trained model: Should contain the .bin files
  --do_train            Whether to run training.
  --do_eval             Whether to run eval on the dev set.
  --do_eval_top_k       Whether to run eval on the partitioned dev set.
  --do_predict          Whether to predict on given dataset.
  --log_interval LOG_INTERVAL
  --train_batch_size TRAIN_BATCH_SIZE
                        Batch size per GPU/CPU for training.
  --eval_batch_size EVAL_BATCH_SIZE
                        Batch size per GPU/CPU for evaluation.
  --learning_rate LEARNING_RATE
                        The initial learning rate for Adam.
  --weight_decay WEIGHT_DECAY
                        Weight deay if we apply some.
  --dropout_rate DROPOUT_RATE
                        Dropout rate.
  --adam_epsilon ADAM_EPSILON
                        Epsilon for Adam optimizer.
  --num_train_epochs NUM_TRAIN_EPOCHS
                        Total number of training epochs to perform.
  --seed SEED           random seed for initialization