xander
|
b51727219e
|
cleanup and try to fix last inference step
|
2024-05-14 11:42:57 +02:00 |
|
xander
|
0bd26033cd
|
add conv2 to lora layers
|
2024-04-29 20:12:08 +02:00 |
|
xander
|
7d78a3d76d
|
updates
|
2024-04-29 19:37:45 +02:00 |
|
xander
|
39ee9c9630
|
set defaults
|
2024-04-27 16:47:35 +02:00 |
|
xander
|
2e5912f629
|
improve token regularization
|
2024-04-26 13:32:01 +02:00 |
|
xander
|
37bcfe61c9
|
hyperparam tweaks
|
2024-04-26 08:45:29 +02:00 |
|
xander
|
f919e3e7a1
|
setup experiment run
|
2024-04-23 04:39:35 +02:00 |
|
xander
|
9ac8d69bfc
|
add experiments for debugging
|
2024-04-17 18:48:49 +02:00 |
|
xander
|
223969ed84
|
add std info to plots, change some defaults
|
2024-04-17 15:52:46 +02:00 |
|
xander
|
2a7c53a0c4
|
updates
|
2024-04-17 14:36:53 +02:00 |
|
xander
|
5181bbdff6
|
updates to test ti
|
2024-04-16 21:41:20 +02:00 |
|
aiXander
|
b8c668822b
|
setup for gridsearch
|
2024-04-15 16:10:36 -07:00 |
|
aiXander
|
c01a99c17f
|
add token warmup
|
2024-04-08 19:36:54 -07:00 |
|
aiXander
|
ceb91f16e2
|
fix reproducibility seed bug
|
2024-04-08 02:07:52 -07:00 |
|