# number of runs of continuation method runs
n_continuation = 1
# number of points that hopefully belong to the pareto front for grad continuation
n_pareto = 40
# number of points that hopefully belong to the pareto front for prox continuation
n_pareto = 2
# numper of iterations for prediction for loss
n_predictor = 10000
# number of training epochs for corrector for loss
n_corr = 200
# numper of iterations for prediction for l1-norm
n_predictor = 10000
# number of training epochs for corrector for l1-norm
n_corr = 200
# number of training epochs for first run
n_corr_first = 10000

Training loss after start iteration = 1.0921226739883423
Test loss after start iteration = 1.0954259634017944
L1 norm after start iteration = 0.7482698559761047
Training accuracy after start iteration = 36.666666666666664
Testing accuracy after start iteration = 32.5

Training loss after grad continuation = 1.0335667133331299
Test loss after grad continuation = 1.0313419103622437
L1 norm after grad continuation = 1.7548620700836182
Training accuracy after grad continuation = 66.66666666666667
Testing accuracy after grad continuation = 66.66666666666667

Training loss after prox continuation = 1.0986119508743286
Test loss after prox continuation = 1.0986119508743286
L1 norm after prox continuation = 0.0
Training accuracy after prox continuation = 30.0
Testing accuracy after prox continuation = 30.0

Total computation time for deterministic Train/Test = 29.57177996635437

