Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

feat(cloud-micro): write 1st/last cost, fewer JSON #175

Merged
merged 1 commit into from
Jul 15, 2024
Merged

feat(cloud-micro): write 1st/last cost, fewer JSON #175

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
47 changes: 25 additions & 22 deletions cloud-microphysics/app/train-cloud-microphysics.f90
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -344,31 +344,34 @@ subroutine read_train_write(training_configuration, base_name, plot_unit, previo

call system_clock(start_training)

do epoch = previous_epoch + 1, previous_epoch + num_epochs

if (size(bins)>1) call shuffle(input_output_pairs) ! set up for stochastic gradient descent
mini_batches = [(mini_batch_t(input_output_pairs(bins(b)%first():bins(b)%last())), b = 1, size(bins))]
call trainable_engine%train(mini_batches, cost, adam, learning_rate)
if (mod(epoch,report_interval)==0) print *, epoch, sum(cost)/size(cost)
if (mod(epoch,report_interval)==0) write(plot_unit,*) epoch, sum(cost)/size(cost)

open(newunit=network_unit, file=network_file, form='formatted', status='unknown', iostat=io_status, action='write')
associate(inference_engine => trainable_engine%to_inference_engine())
associate(json_file => inference_engine%to_json())
call json_file%write_lines(string_t(network_file))
end associate
end associate
close(network_unit)
associate(starting_epoch => previous_epoch + 1, ending_epoch => previous_epoch + num_epochs)
do epoch = starting_epoch, ending_epoch

if (size(bins)>1) call shuffle(input_output_pairs) ! set up for stochastic gradient descent
mini_batches = [(mini_batch_t(input_output_pairs(bins(b)%first():bins(b)%last())), b = 1, size(bins))]
call trainable_engine%train(mini_batches, cost, adam, learning_rate)
if (any(epoch == [starting_epoch, ending_epoch]) .or. mod(epoch, report_interval)==0) then
print *, epoch, sum(cost)/size(cost)
write(plot_unit,*) epoch, sum(cost)/size(cost)
open(newunit=network_unit, file=network_file, form='formatted', status='unknown', iostat=io_status, action='write')
associate(inference_engine => trainable_engine%to_inference_engine())
associate(json_file => inference_engine%to_json())
call json_file%write_lines(string_t(network_file))
end associate
end associate
close(network_unit)
end if

inquire(file="stop", exist=stop_requested)
inquire(file="stop", exist=stop_requested)

graceful_exit: &
if (stop_requested) then
print *,'Shutting down because a file named "stop" was found.'
return
end if graceful_exit
graceful_exit: &
if (stop_requested) then
print *,'Shutting down because a file named "stop" was found.'
return
end if graceful_exit

end do
end do
end associate
end associate

call system_clock(finish_training)
Expand Down
Loading