keep getting this error monitor

[Asif-Iqbal-Bhatti]

Hello developers,

I am getting this error

'''
025/11/16 10:50:05 I - New best test loss found (1.09429e-01), checkpointing
2025/11/16 10:50:05 I - Sharding callback duration: 24 microseconds
Traceback (most recent call last):
File "/home/2222/micromamba/envs/grace/bin/gracemaker", line 47, in
main(sys.argv[1:], strategy=strategy, strategy_desc=strategy_desc)
File "/home/2222/micromamba/envs/grace/lib/python3.11/site-packages/tensorpotential/cli/gracemaker.py", line 558, in main
train_adam(
File "/home/2222/micromamba/envs/grace/lib/python3.11/site-packages/tensorpotential/cli/train.py", line 579, in train_adam
callback_list.on_epoch_end(tp.epoch, epoch_end_metrics)
File "/home/2222/micromamba/envs/grace/lib/python3.11/site-packages/keras/src/callbacks/callback_list.py", line 171, in on_epoch_end
callback.on_epoch_end(epoch, logs)
File "/home/2222/micromamba/envs/grace/lib/python3.11/site-packages/tensorpotential/cli/train_callbacks.py", line 136, in on_epoch_end
if self.monitor_op(current, self.best):
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
TypeError: 'NoneType' object is not callable
'''

This is my input yaml file

"""
seed: 1
cutoff: 6.0

data:
filename: train_data.extxyz
test_filename: test_data.extxyz
#reference_energy: {Cl:}

reference_energy: {Al: -1.23, Li: -3.56}

save_dataset: False

stress_units: eV/A3 # eV/A3 (default) or GPa or kbar or -kbar

potential:

If elements not provided - determined automatically from data

preset: GRACE_1LAYER # LINEAR, FS, GRACE_1LAYER, GRACE_2LAYER

For custom model from model.py::custom_model

custom: model.custom_model

keywords-arguments that will be passed to preset or custom function

kwargs: {lmax: 3, n_rad_max: 20, max_order: 3, n_mlp_dens: 10}

#shift: False # True/False
scale: True # False/True or float
fit:
loss: {
energy: { weight: 1, type: huber , delta: 0.01 },
forces: { weight: 100, type: huber , delta: 0.01 },
stress: { weight: 0.1, type: huber , delta: 0.01 },

}

maxiter: 500 # Number of epochs / iterations

optimizer: Adam
opt_params: {
learning_rate: 0.01,
amsgrad: True,
use_ema: True,
ema_momentum: 0.99,
weight_decay: null,
clipvalue: 1.0,
}

for learning-rate reduction

learning_rate_reduction: { patience: 5, factor: 0.98, min: 5.0e-4, stop_at_min: True, resume_lr: True, }

optimizer: L-BFGS-B

opt_params: { "maxcor": 100, "maxls": 20 }

needed for low-energy tier metrics and for "convex_hull"-based distance of energy-based weighting scheme

compute_convex_hull: False
batch_size: 4 # Important hyperparameter for Adam and irrelevant (but must be) for L-BFGS-B
test_batch_size: 16 # test batch size (optional)

jit_compile: True
eval_init_stats: False # to evaluate initial metrics

train_max_n_buckets: 10 # max number of buckets (group of batches of same shape) in train set
test_max_n_buckets: 5 # same for test

checkpoint_freq: 2 # frequency for REGULAR checkpoints.

save_all_regular_checkpoints: True # to store ALL regular checkpoints

progressbar: True # show batch-evaluation progress bar
train_shuffle: True # shuffle train batches on every epoch

"""