summaryrefslogtreecommitdiffstats
path: root/training/lr.py
Commit message (Expand)AuthorAgeFilesLines
* Restored LR finderVolpeon2023-01-201-234/+32
* UpdateVolpeon2023-01-171-1/+1
* UpdateVolpeon2023-01-151-14/+15
* More modularizationVolpeon2023-01-131-5/+9
* UpdateVolpeon2023-01-121-4/+7
* FixVolpeon2023-01-111-2/+2
* Added arg to disable tag shufflingVolpeon2023-01-101-10/+10
* Use context manager for EMA, on_train/eval hooksVolpeon2023-01-061-26/+25
* Fix LR finderVolpeon2023-01-051-7/+23
* UpdateVolpeon2023-01-041-1/+6
* Better eval generatorVolpeon2023-01-041-3/+3
* Fixed reproducibility, more consistant validationVolpeon2023-01-041-3/+3
* Added vector dropoutVolpeon2023-01-031-3/+6
* Fixed LR finderVolpeon2023-01-021-17/+21
* UpdateVolpeon2023-01-021-2/+31
* UpdatesVolpeon2023-01-011-0/+6
* Training script improvementsVolpeon2022-12-301-5/+8
* UpdateVolpeon2022-12-291-8/+5
* Training improvementsVolpeon2022-12-291-3/+4
* Updated 1-cycle schedulerVolpeon2022-12-281-6/+8
* Integrated updates from diffusersVolpeon2022-12-281-10/+36
* Improved learning rate finderVolpeon2022-12-271-13/+25
* Added validation phase to learn rate finderVolpeon2022-12-271-11/+23
* Added learning rate finderVolpeon2022-12-271-0/+115