Skip to content

Sinusoid example #126

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

Merged
merged 1 commit into from
Jan 19, 2025
Merged

Sinusoid example #126

merged 1 commit into from
Jan 19, 2025

Conversation

huttarichard
Copy link
Contributor

Simple example of cosinus prediction with FC layers.

Library is amazing, please continue it's development, I absolutely love it.

Epoch 10: Avg Loss 0.024422
Epoch 20: Avg Loss 0.003512
Epoch 30: Avg Loss 0.000928
Epoch 40: Avg Loss 0.000302
Epoch 50: Avg Loss 0.000128
Epoch 60: Avg Loss 0.000084
Epoch 70: Avg Loss 0.000051
Epoch 80: Avg Loss 0.000052
Epoch 90: Avg Loss 0.000050
Epoch 100: Avg Loss 0.000043
Epoch 110: Avg Loss 0.000050
Epoch 120: Avg Loss 0.000031
Epoch 130: Avg Loss 0.000035
Epoch 140: Avg Loss 0.000035
Epoch 150: Avg Loss 0.000034
Epoch 160: Avg Loss 0.000024
Epoch 170: Avg Loss 0.000021
Epoch 180: Avg Loss 0.000022
Epoch 190: Avg Loss 0.000016
Epoch 200: Avg Loss 0.000020
Epoch 210: Avg Loss 0.000016
Epoch 220: Avg Loss 0.000016
Epoch 230: Avg Loss 0.000014
Epoch 240: Avg Loss 0.000010

Evaluation:
sin(-3.142) = -1.012 (predicted) vs -1.000 (actual)
sin(-1.571) = -0.001 (predicted) vs 0.000 (actual)
sin(0.000) = 0.999 (predicted) vs 1.000 (actual)
sin(1.571) = -0.001 (predicted) vs 0.000 (actual)
sin(3.142) = -1.000 (predicted) vs -1.000 (actual)

@matteo-grella matteo-grella merged commit ce6cb99 into nlpodyssey:main Jan 19, 2025
4 of 5 checks passed
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.

2 participants