Skip to content
GitLab
Explore
Sign in
Primary navigation
Search or go to…
Project
B
Beit Project
Manage
Activity
Members
Labels
Plan
Issues
Issue boards
Milestones
Wiki
Code
Merge requests
Repository
Branches
Commits
Tags
Repository graph
Compare revisions
Snippets
Build
Pipelines
Jobs
Pipeline schedules
Artifacts
Deploy
Releases
Package Registry
Container Registry
Model registry
Operate
Environments
Terraform modules
Monitor
Incidents
Analyze
Value stream analytics
Contributor analytics
CI/CD analytics
Repository analytics
Issue analytics
Model experiments
Help
Help
Support
GitLab documentation
Compare GitLab plans
Community forum
Contribute to GitLab
Provide feedback
Terms and privacy
Keyboard shortcuts
?
Snippets
Groups
Projects
Show more breadcrumbs
fskeese
Beit Project
Commits
9eb978f7
Commit
9eb978f7
authored
3 years ago
by
CheesyData
Browse files
Options
Downloads
Patches
Plain Diff
Changed Readme for pretraining
parent
4a8f3f6a
No related branches found
Branches containing commit
No related tags found
No related merge requests found
Changes
1
Hide whitespace changes
Inline
Side-by-side
Showing
1 changed file
readme_pretraining.md
+2
-1
2 additions, 1 deletion
readme_pretraining.md
with
2 additions
and
1 deletion
readme_pretraining.md
+
2
−
1
View file @
9eb978f7
...
...
@@ -10,7 +10,8 @@ Pretraining auf open-images
-
-
Lernrate pro GPU: 9,375e-5
-
Data_Path sollte open-images/train sein, dieser wird aber auch am Ende des Entpackprozesses ausgeprinted
-
Ordner für Output und Tokenizer bereits im Ordner enthalten, müssen nur noch Path angegeben werden
-
mkdir Output
-
Ordner für Output erstellt und Tokenizer bereits im Ordner enthalten, müssen nur noch Path angegeben werden im untenstehenden Befehl
-
ImageNet 22k hat 14M Bilder, open-images etwa 9M --> Verhältnis von 9/14 ~ 0,64 --> 0,64
*
150 Epochen ~ 96 Epochen
...
...
This diff is collapsed.
Click to expand it.
Preview
0%
Loading
Try again
or
attach a new file
.
Cancel
You are about to add
0
people
to the discussion. Proceed with caution.
Finish editing this message first!
Save comment
Cancel
Please
register
or
sign in
to comment