what is the problem about 'train_state_unpadded_shape_dtype_struct'?

[baowanli719]

Restoring checkpoint from /opt/tfm/timesfm-1.0-200m/checkpoints/.
WARNING:absl:No registered CheckpointArgs found for handler type: <class 'paxml.checkpoints.FlaxCheckpointHandler'>
WARNING:absl:Configured CheckpointManager using deprecated legacy API. Please follow the instructions at https://orbax.readthedocs.io/en/latest/api_refactor.html to migrate by May 1st, 2024.
WARNING:absl:train_state_unpadded_shape_dtype_struct is not provided. We assume train_state is unpadded.
ERROR:absl:For checkpoint version > 1.0, we require users to provide
train_state_unpadded_shape_dtype_struct during checkpoint
saving/restoring, to avoid potential silent bugs when loading
checkpoints to incompatible unpadded shapes of TrainState.
Restored checkpoint in 0.50 seconds.
Jitting decoding.
Jitted decoding in 11.02 seconds.
Traceback (most recent call last):
File "/opt/tfm/timesfm/test.py", line 71, in
point_forecast, experimental_quantile_forecast = tfm.forecast(
File "/opt/tfm/timesfm/src/timesfm.py", line 430, in forecast
inp_min = np.min([np.min(ts) for ts in inputs])
File "/opt/tfm/timesfm/src/timesfm.py", line 430, in
inp_min = np.min([np.min(ts) for ts in inputs])
File "/home/anaconda3/envs/tfm_env/lib/python3.10/site-packages/numpy/core/fromnumeric.py", line 2953, in min
return _wrapreduction(a, np.minimum, 'min', axis, None, out,
File "/home/anaconda3/envs/tfm_env/lib/python3.10/site-packages/numpy/core/fromnumeric.py", line 88, in _wrapreduction
return ufunc.reduce(obj, axis, dtype, out, **passkwargs)
TypeError: '<=' not supported between instances of 'str' and 'float