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.

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

[docs] SmoothL1Loss correctly mentioned instead of Huber #1458

Merged
merged 6 commits into from
Oct 19, 2023

Conversation

ourownstory
Copy link
Owner

@ourownstory ourownstory commented Oct 18, 2023

  • Editing all files to mention SmoothL1Loss correctly instead of Huber loss.
  • Remains backwards compatible.
  • make beta of 1.0 explicit

@ourownstory ourownstory changed the title [Major] Smoothl1loss update beta from 1.0 to 0.1 [Major] SmoothL1Loss update beta from 1.0 to 0.1 Oct 18, 2023
@codecov
Copy link

codecov bot commented Oct 19, 2023

Codecov Report

Merging #1458 (30830af) into main (bf5794d) will not change coverage.
The diff coverage is 100.00%.

@@           Coverage Diff           @@
##             main    #1458   +/-   ##
=======================================
  Coverage   88.32%   88.32%           
=======================================
  Files          38       38           
  Lines        5097     5097           
=======================================
  Hits         4502     4502           
  Misses        595      595           
Files Coverage Δ
neuralprophet/configure.py 90.18% <100.00%> (ø)
neuralprophet/forecaster.py 87.24% <ø> (ø)

@github-actions
Copy link

github-actions bot commented Oct 19, 2023

Model Benchmark

Benchmark Metric main current diff
PeytonManning_test30 MAE_val - 0.9731 -
PeytonManning_test30 RMSE_val - 1.128 -
PeytonManning_test30 Loss_val - 0.0317 -
PeytonManning_test30 MAE - 0.33 -
PeytonManning_test30 RMSE - 0.4574 -
PeytonManning_test30 Loss - 0.0044 -
PeytonManning_test30 time - 66.69 -
YosemiteTemps MAE_val 1.34899 0.44287 -67.17% 🎉
YosemiteTemps RMSE_val 2.00817 0.62875 -68.69% 🎉
YosemiteTemps Loss_val 0.00078 7e-05 -91.32% 🎉
YosemiteTemps MAE 1.32133 0.80138 -39.35% 🎉
YosemiteTemps RMSE 2.13713 1.44081 -32.58% 🎉
YosemiteTemps Loss 0.00064 0.00027 -57.67% 🎉
YosemiteTemps time 70.56032 209.3 196.63%
YosemiteTemps_test20 MAE_val - 1.8 -
YosemiteTemps_test20 RMSE_val - 2.2687 -
YosemiteTemps_test20 Loss_val - 0.001 -
YosemiteTemps_test20 MAE - 0.8432 -
YosemiteTemps_test20 RMSE - 1.4617 -
YosemiteTemps_test20 Loss - 0.0003 -
YosemiteTemps_test20 time - 177.26 -
AirPassengers_test30 MAE_val - 25.3607 -
AirPassengers_test30 RMSE_val - 30.624 -
AirPassengers_test30 Loss_val - 0.0074 -
AirPassengers_test30 MAE - 5.3982 -
AirPassengers_test30 RMSE - 6.8828 -
AirPassengers_test30 Loss - 0.0002 -
AirPassengers_test30 time - 29.34 -
AirPassengers MAE_val 13.0627 30.1272 130.64%
AirPassengers RMSE_val 15.94532 31.014 94.5%
AirPassengers Loss_val 0.00131 0.00371 182.63%
AirPassengers MAE 9.88153 6.27639 -36.48% 🎉
AirPassengers RMSE 11.73543 7.88804 -32.78% 🎉
AirPassengers Loss 0.00052 0.00019 -62.92% 🎉
AirPassengers time 6.50659 30.66 371.21%
PeytonManning MAE_val 0.58162 0.34778 -40.21% 🎉
PeytonManning RMSE_val 0.72218 0.49928 -30.86% 🎉
PeytonManning Loss_val 0.01239 0.00595 -51.96% 🎉
PeytonManning MAE 0.41671 0.35123 -15.71% 🎉
PeytonManning RMSE 0.55961 0.48066 -14.11% 🎉
PeytonManning Loss 0.00612 0.0046 -24.8% 🎉
PeytonManning time 15.33097 74.85 388.23%
Model training plots

Model Training

PeytonManning

PeytonManning_test30

YosemiteTemps

YosemiteTemps_test20

AirPassengers

AirPassengers_test30

@ourownstory ourownstory changed the title [Major] SmoothL1Loss update beta from 1.0 to 0.1 [Major] SmoothL1Loss update beta from 1.0 to 0.3 Oct 19, 2023
@ourownstory ourownstory changed the title [Major] SmoothL1Loss update beta from 1.0 to 0.3 [Minor] SmoothL1Loss correctly mentioned instead of Huber Oct 19, 2023
@ourownstory ourownstory merged commit f08dcf8 into main Oct 19, 2023
13 checks passed
@ourownstory ourownstory deleted the smoothl1loss-update-beta-01 branch October 19, 2023 23:18
@ourownstory ourownstory changed the title [Minor] SmoothL1Loss correctly mentioned instead of Huber [docs] SmoothL1Loss correctly mentioned instead of Huber Dec 8, 2023
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

1 participant