Model monitor V2 job partially successful - explanation batch job failed

The source code was referred to: [model_monitoring_for_custom_model_batch_prediction_job.ipynb](https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/official/model_monitoring_v2/model_monitoring_for_custom_model_batch_prediction_job.ipynb)

The failure message:
Batch inference job batch_explain_for_baseline_stats_3538562669718011904 encountered the following errors:
Error occurred in Explanation validation. Invalid field `input_tensor_name` in input metadata for non-TF frameworks ('xgboost', 'scikit_learn', 'custom_container'). Valid set is: ('input_baselines', 'modality', 'group_name', 'encoding', 'index_feature_mapping').

The jupyter notebook code is:
`
from google.cloud.aiplatform_v1beta1.types import (ExplanationMetadata,
ExplanationParameters,
ExplanationSpec)

EXPLANATION_SPEC = ExplanationSpec(
parameters=ExplanationParameters(
{"sampled_shapley_attribution": {"path_count": 2}}
),
metadata=ExplanationMetadata(
inputs={
"cnt_ad_reward": ExplanationMetadata.InputMetadata(
{
"input_tensor_name": "cnt_ad_reward",
"encoding": "IDENTITY",
"modality": "numeric",
}
),
"cnt_challenge_a_friend": ExplanationMetadata.InputMetadata(
{
"input_tensor_name": "cnt_challenge_a_friend",
"encoding": "IDENTITY",
"modality": "numeric",
}
),
"cnt_completed_5_levels": ExplanationMetadata.InputMetadata(
{
"input_tensor_name": "cnt_completed_5_levels",
"encoding": "IDENTITY",
"modality": "numeric",
}
),
"cnt_level_complete_quickplay": ExplanationMetadata.InputMetadata(
{
"input_tensor_name": "cnt_level_complete_quickplay",
"encoding": "IDENTITY",
"modality": "numeric",
}
),
"cnt_level_end_quickplay": ExplanationMetadata.InputMetadata(
{
"input_tensor_name": "cnt_level_end_quickplay",
"encoding": "IDENTITY",
"modality": "numeric",
}
),
"cnt_level_reset_quickplay": ExplanationMetadata.InputMetadata(
{
"input_tensor_name": "cnt_level_reset_quickplay",
"encoding": "IDENTITY",
"modality": "numeric",
}
),
"cnt_level_start_quickplay": ExplanationMetadata.InputMetadata(
{
"input_tensor_name": "cnt_level_start_quickplay",
"encoding": "IDENTITY",
"modality": "numeric",
}
),
"cnt_post_score": ExplanationMetadata.InputMetadata(
{
"input_tensor_name": "cnt_post_score",
"encoding": "IDENTITY",
"modality": "numeric",
}
),
"cnt_spend_virtual_currency": ExplanationMetadata.InputMetadata(
{
"input_tensor_name": "cnt_spend_virtual_currency",
"encoding": "IDENTITY",
"modality": "numeric",
}
),
"cnt_use_extra_steps": ExplanationMetadata.InputMetadata(
{
"input_tensor_name": "cnt_use_extra_steps",
"encoding": "IDENTITY",
"modality": "numeric",
}
),
"cnt_user_engagement": ExplanationMetadata.InputMetadata(
{
"input_tensor_name": "cnt_user_engagement",
"encoding": "IDENTITY",
"modality": "numeric",
}
),
"country": ExplanationMetadata.InputMetadata(
{
"input_tensor_name": "country",
"encoding": "IDENTITY",
"modality": "categorical",
}
),
"dayofweek": ExplanationMetadata.InputMetadata(
{
"input_tensor_name": "dayofweek",
"encoding": "IDENTITY",
"modality": "numeric",
}
),
"julianday": ExplanationMetadata.InputMetadata(
{
"input_tensor_name": "julianday",
"encoding": "IDENTITY",
"modality": "numeric",
}
),
"language": ExplanationMetadata.InputMetadata(
{
"input_tensor_name": "language",
"encoding": "IDENTITY",
"modality": "categorical",
}
),
"month": ExplanationMetadata.InputMetadata(
{
"input_tensor_name": "month",
"encoding": "IDENTITY",
"modality": "numeric",
}
),
"operating_system": ExplanationMetadata.InputMetadata(
{
"input_tensor_name": "operating_system",
"encoding": "IDENTITY",
"modality": "categorical",
}
),
"user_pseudo_id": ExplanationMetadata.InputMetadata(
{
"input_tensor_name": "user_pseudo_id",
"encoding": "IDENTITY",
"modality": "categorical",
}
),
},
outputs={
"churned_probs": ExplanationMetadata.OutputMetadata(
{"output_tensor_name": "churned_probs"}
)
},
),
)

`