Skip to content

TinyStories run-1 from Tessa (val_loss 3.0604) #25

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

Open
ESeoni wants to merge 1 commit into
base: main
Choose a base branch
from
Open

TinyStories run-1 from Tessa (val_loss 3.0604) #25

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
58 changes: 58 additions & 0 deletions projects/gpt2-tinystories/run-1.json
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,58 @@
{
"version": 1,
"project": "gpt2-tinystories",
"peerId": "12D3KooWLncdTy2tZ6kWYEk2B9JH1wMGwUkNUbcAyVYhUaT2j1Cb",
"runNumber": 1,
"hypothesis": "Increase layers to 4 and hidden dim to 128 \u2014 more capacity may reduce val_loss at this dataset scale.",
"result": {
"valLoss": 3.0604,
"trainLoss": 3.0493,
"durationSec": 75.0,
"lossCurve": [
[
50,
4.4686
],
[
100,
4.2196
],
[
150,
3.9897
],
[
200,
3.7638
],
[
250,
3.5668
],
[
300,
3.4452
],
[
350,
3.337
],
[
400,
3.2284
],
[
450,
3.1339
],
[
500,
3.0493
]
]
},
"improvement": "Increased depth from 2 to 4 layers and width from 64 to 128d. val_loss: 3.0604",
"isNewBest": true,
"gpu": null,
"inspiredBy": null
}