Phil Wang
|
708809ed6c
|
lower beta2 for adam down to 0.99, based on https://openreview.net/forum?id=2LdBqxc1Yv
|
2022-06-03 10:26:28 -07:00 |
|
Aidan Dempster
|
09534119a1
|
Fixed non deterministic optimizer creation (#130)
|
2022-05-31 09:03:20 -07:00 |
|
zion
|
1ed0f9d80b
|
use deterministic optimizer params (#116)
|
2022-05-25 09:31:43 -07:00 |
|
Phil Wang
|
857b9fbf1e
|
allow for one to stop grouping out weight decayable parameters, to debug optimizer state dict problem
|
2022-05-24 21:42:32 -07:00 |
|
Aidan Dempster
|
022c94e443
|
Added single GPU training script for decoder (#108)
Added config files for training
Changed example image generation to be more efficient
Added configuration description to README
Removed unused import
|
2022-05-20 19:46:19 -07:00 |
|
Phil Wang
|
c7ea8748db
|
default decoder learning rate to what was in the paper
|
2022-05-16 13:33:54 -07:00 |
|
Phil Wang
|
e697183849
|
be able to customize adam eps
|
2022-05-14 13:55:04 -07:00 |
|
Phil Wang
|
591d37e266
|
lower default initial learning rate to what Jonathan Ho had in his original repo
|
2022-05-14 13:22:43 -07:00 |
|
Phil Wang
|
5063d192b6
|
now completely OpenAI CLIP compatible for training
just take care of the logic for AdamW and transformers
used namedtuples for clip adapter embedding outputs
|
2022-04-29 13:05:01 -07:00 |
|