ATASET = "task-focus + sample from remain datasets"
DATASET_FORMAT = 'input-output'
PER_DEVICE_TRAIN_BATCH_SIZE = 2
GRADIENT_ACCUMULATION_STEPS = 4
LEARNING_RATE = 0.0003
LR_SCHEDULER_TYPE = 'cosine'
WARMUP_RATIO = 0.03
LORA_R = 192
LORA_ALPHA = 64
LORA_DROPOUT = 0.1
TRAIN_ON_SOURCE = False
SOURCE_MAX_LENGTH = 1024
TARGET_MAX_LENGTH = 1024
LOGGING_STEPS = 20
SAVE_STEPS = 100
SAVE_TOTAL_LIMIT = 4