Hidden markovs model training with fmri time series(statistical help)

I am beginner in machine learning…I am using Hidden markovs model to analyse the brain states in OSL dynamics tool box . Hidden Markov Model (HMM) — OSL Dynamics
q1) I have converted fmri data into time series using aal atlas and done the normalization and also done the frequency filteration for the time series data. But after the training i am getting loss function (screen shot attached)… how to know the training is bad or not ?is it only by getting free energy or by the function get_likelihood ? on epochs its reducing from 122 to 108 like that … but usually the loss should be shown as in percentage ? am i doing something wrong on taking the time series? or any other steps to do for better training? attached the image after the training…

q2) I have trained the model with the fmri time series using AAL parcellation. after training i tried to validate the model with other test data (fmri time series) . I was having an issue while trying to get the likelihood using the get_likelihood function.When i prepare the data for training it is an np_array with shape (time points, n_channels). However the get likelihood function expects a np_array with following shape (batch _size, seq_length, n_channels). Is there some step that i am missing in between to get this type of nparray. While i try to reshape my prepared data manually it throws error inside the get_likelihood function. If any one knows to use it would be a great help.

the function of get_likelihood is in this given link
https://osl-dynamics.readthedocs.io/en/latest/autoapi/osl_dynamics/models/hmm/index.html#osl_dynamics.models.hmm.Model.get_likelihood

Epoch 1/20
3/3 [==============================] - 15s 4s/step - rho: 0.2853 - lr: 0.0100 - loss: 163.0395
Epoch 2/20
3/3 [==============================] - 16s 5s/step - rho: 0.1866 - lr: 0.0090 - loss: 161.9918
Epoch 3/20
3/3 [==============================] - 16s 4s/step - rho: 0.1436 - lr: 0.0082 - loss: 162.2520
Epoch 4/20
3/3 [==============================] - 14s 4s/step - rho: 0.1187 - lr: 0.0074 - loss: 161.7673
Epoch 5/20
3/3 [==============================] - 14s 4s/step - rho: 0.1022 - lr: 0.0067 - loss: 161.3089
Epoch 6/20
3/3 [==============================] - 14s 4s/step - rho: 0.0904 - lr: 0.0061 - loss: 161.4916
Epoch 7/20
3/3 [==============================] - 14s 4s/step - rho: 0.0814 - lr: 0.0055 - loss: 161.3081
Epoch 8/20
3/3 [==============================] - 14s 4s/step - rho: 0.0743 - lr: 0.0050 - loss: 161.8166
Epoch 9/20
3/3 [==============================] - 14s 6s/step - rho: 0.0686 - lr: 0.0045 - loss: 160.8360
Epoch 10/20
3/3 [==============================] - 14s 4s/step - rho: 0.0638 - lr: 0.0041 - loss: 161.1361
Epoch 11/20
3/3 [==============================] - 14s 6s/step - rho: 0.0597 - lr: 0.0037 - loss: 160.6548
Epoch 12/20
3/3 [==============================] - 17s 5s/step - rho: 0.0563 - lr: 0.0033 - loss: 160.5306
Epoch 13/20
3/3 [==============================] - 17s 8s/step - rho: 0.0532 - lr: 0.0030 - loss: 160.7460
Epoch 14/20
3/3 [==============================] - 20s 5s/step - rho: 0.0506 - lr: 0.0027 - loss: 160.7003
Epoch 15/20
3/3 [==============================] - 19s 5s/step - rho: 0.0482 - lr: 0.0025 - loss: 160.7620
Epoch 16/20
3/3 [==============================] - 18s 8s/step - rho: 0.0461 - lr: 0.0022 - loss: 160.1311
Epoch 17/20
3/3 [==============================] - 18s 5s/step - rho: 0.0442 - lr: 0.0020 - loss: 160.9921
Epoch 18/20
3/3 [==============================] - 19s 6s/step - rho: 0.0425 - lr: 0.0018 - loss: 161.1282
Epoch 19/20
3/3 [==============================] - 16s 4s/step - rho: 0.0410 - lr: 0.0017 - loss: 160.2256
Epoch 20/20