TOTAL_BATCH_SIZE = 4096
LEARNING_RATE = 3e-3
WEIGHT_DECAY = 0.3

NUM_EPOCHS = 300
WARMUP_EPOCHS = 32

# data parallel only
TENSOR_PARALLEL_SIZE = 1    
TENSOR_PARALLEL_MODE = None

# parallelism setting
parallel = dict(
    pipeline=1,
    tensor=dict(mode=TENSOR_PARALLEL_MODE, size=TENSOR_PARALLEL_SIZE),
)

fp16 = dict(mode=AMP_TYPE.TORCH, ) # amp setting

gradient_accumulation = 2 # accumulate 2 steps for gradient update

BATCH_SIZE = TOTAL_BATCH_SIZE // gradient_accumulation # actual batch size for dataloader

clip_grad_norm = 1.0 # clip gradient with norm 1.0

$ DATA=/path/to/dataset python train.py --world_size=WORLD_SIZE \
                                        --rank=RANK \
                                        --local_rank=LOCAL_RANK \
                                        --host=MASTER_IP_ADDRESS \
                                        --port=MASTER_PORT \
                                        --config=CONFIG_FILE

$ DATA=/path/to/dataset torchrun --nproc_per_node=NUM_GPUS_PER_NODE \
                                 --nnodes=NUM_NODES \
                                 --node_rank=NODE_RANK \
                                 --master_addr=MASTER_IP_ADDRESS \
                                 --master_port=MASTER_PORT \
                                 train.py --config=CONFIG_FILE