AssertionError: Time difference between steps has been idenfied as larger than 1 - set allow_missing_timesteps=True

[sathmikaDev]

train_dataset = TimeSeriesDataSet(
    Final_DF[lambda x: x.time_idx <= training_cutoff],
    time_idx="time_idx",
    target="target",
    group_ids=["group_id"],
    max_encoder_length=max_encoder_length,
    min_encoder_length=max_encoder_length//2, 
    max_prediction_length=max_prediction_length,
    min_prediction_length=max_prediction_length,
    static_reals=[],  # Add any static features like group-level metadata
    time_varying_known_reals=[
        "time_idx",
        "Dollar_Index",
        "Gold_Price",
        "Interest_Rate",
        "US_10_Year",
        "VIX_Value",
        "month",
        "day_of_week",
        "year",
        "month",
        "day_of_year",
        "quarter",
    ],
    time_varying_unknown_categoricals=[],
    time_varying_unknown_reals=["target", "lag_1", "lag_3", "lag_7", "ma_3", "ma_7"],
    target_normalizer=GroupNormalizer(
        groups=["group_id"], transformation="softplus"
    ),
    add_relative_time_idx=True,
    add_target_scales=True,
    add_encoder_length=True,
)

# create validation set (predict=True) which means to predict the last max_prediction_length points in time
# for each series
validation = TimeSeriesDataSet.from_dataset(training, Final_DF, predict=True, stop_randomization=True)

# create dataloaders for model
batch_size = 128  # set this between 32 to 128
train_dataloader = training.to_dataloader(train=True, batch_size=batch_size, num_workers=0)
val_dataloader = validation.to_dataloader(train=False, batch_size=batch_size * 10, num_workers=0)

I'm trying to build a TFT model to predict cryptocurrency prices which is generalized across multiple cryptocurrencies. I'm having this AssertionError when creating the dataset.

here I have attached my what my dataset looks like.

[Sohaib-Ahmed21]

@sathmikaDev you have not mentioned which AssertionError are you specifically getting.