eegmp_preproc/data/outputs/history/log_sub-005_ica1_17-Nov-2021.txt

Input data size [72,904000] = 72 channels, 904000 frames
Finding 72 ICA components using extended ICA.
Kurtosis will be calculated initially every 1 blocks using 6000 data points.
Decomposing 174 frames per ICA weight ((5184)^2 = 904000 weights, Initial learning rate will be 0.001, block size 69.
Learning rate will be multiplied by 0.98 whenever angledelta >= 60 deg.
More than 32 channels: default stopping weight change 1E-7
Training will end when wchange < 1e-07 or after 512 steps.
Online bias adjustment will be used.
Removing mean of each channel ...
Final training data range: -1.98244 to 2.44712
Computing the sphering matrix...
Starting weights are the identity matrix ...
Sphering the data ...
Beginning ICA training ... first training step may be slow ...
Lowering learning rate to 0.0009 and starting again.
Lowering learning rate to 0.00081 and starting again.
Lowering learning rate to 0.000729 and starting again.
Lowering learning rate to 0.0006561 and starting again.
Lowering learning rate to 0.00059049 and starting again.
Lowering learning rate to 0.000531441 and starting again.
Lowering learning rate to 0.000478297 and starting again.
Lowering learning rate to 0.000430467 and starting again.
Lowering learning rate to 0.00038742 and starting again.
Lowering learning rate to 0.000348678 and starting again.
Lowering learning rate to 0.000313811 and starting again.
Lowering learning rate to 0.00028243 and starting again.
Lowering learning rate to 0.000254187 and starting again.
Lowering learning rate to 0.000228768 and starting again.
Lowering learning rate to 0.000205891 and starting again.
Lowering learning rate to 0.000185302 and starting again.
Lowering learning rate to 0.000166772 and starting again.
Lowering learning rate to 0.000150095 and starting again.
Lowering learning rate to 0.000135085 and starting again.
Lowering learning rate to 0.000121577 and starting again.
Lowering learning rate to 0.000109419 and starting again.
Lowering learning rate to 9.84771e-05 and starting again.
Lowering learning rate to 8.86294e-05 and starting again.
Lowering learning rate to 7.97664e-05 and starting again.
Lowering learning rate to 7.17898e-05 and starting again.
Lowering learning rate to 6.46108e-05 and starting again.
Lowering learning rate to 5.81497e-05 and starting again.
Lowering learning rate to 5.23348e-05 and starting again.
Lowering learning rate to 4.71013e-05 and starting again.
Lowering learning rate to 4.23912e-05 and starting again.
Lowering learning rate to 3.8152e-05 and starting again.
Lowering learning rate to 3.43368e-05 and starting again.
Lowering learning rate to 3.09032e-05 and starting again.
Lowering learning rate to 2.78128e-05 and starting again.
Lowering learning rate to 2.50316e-05 and starting again.
Lowering learning rate to 2.25284e-05 and starting again.
Lowering learning rate to 2.02756e-05 and starting again.
step 1 - lrate 0.000020, wchange 8057740819946669.00000000, angledelta  0.0 deg
Lowering learning rate to 1.45984e-05 and starting again.
step 1 - lrate 0.000015, wchange 286132361274.43481445, angledelta  0.0 deg
Lowering learning rate to 1.05109e-05 and starting again.
step 1 - lrate 0.000011, wchange 177756972.97832173, angledelta  0.0 deg
step 2 - lrate 0.000011, wchange 30864619015017808.00000000, angledelta  0.0 deg
Lowering learning rate to 7.56781e-06 and starting again.
step 1 - lrate 0.000008, wchange 870176.88279466, angledelta  0.0 deg
step 2 - lrate 0.000008, wchange 758785101210.97692871, angledelta  0.0 deg
Lowering learning rate to 5.44882e-06 and starting again.
step 1 - lrate 0.000005, wchange 18697.11590776, angledelta  0.0 deg
step 2 - lrate 0.000005, wchange 353710040.56801736, angledelta  0.0 deg
step 3 - lrate 0.000005, wchange 6700937966308.15039062, angledelta  2.2 deg
step 4 - lrate 0.000004, wchange 17041452059844714.00000000, angledelta  2.2 deg
Lowering learning rate to 3.13852e-06 and starting again.
step 1 - lrate 0.000003, wchange 284.43930247, angledelta  0.0 deg
step 2 - lrate 0.000003, wchange 75092.99967143, angledelta  0.0 deg
step 3 - lrate 0.000003, wchange 21858996.45542961, angledelta 17.8 deg
step 4 - lrate 0.000003, wchange 6362987495.67738628, angledelta 17.8 deg
step 5 - lrate 0.000003, wchange 540286009563.06170654, angledelta 17.8 deg
step 6 - lrate 0.000002, wchange 17788884027207.72656250, angledelta 17.8 deg
step 7 - lrate 0.000002, wchange 271873380970728.43750000, angledelta 17.8 deg
step 8 - lrate 0.000001, wchange 2224858964834985.50000000, angledelta 17.8 deg
step 9 - lrate 0.000001, wchange 10749555839408678.00000000, angledelta 17.8 deg
runica(): QUITTING - weight matrix may not be invertible!