alea31415 commited on
Commit
be78d19
·
1 Parent(s): 03034e0

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +2 -2
README.md CHANGED
@@ -54,12 +54,12 @@ The model is trained on runpod using 3090 and cost me around 15 dollors.
54
 
55
  #### Hyperparameter specification
56
 
57
- The model is trained for 48000 steps, at batch size 4, lr 1e-6, resolution 512, and conditional dropping rate of 10%.
58
 
59
  Note that as a consequence of the weighting scheme which translates into a number of different multiply for each image,
60
  the count of repeat and epoch has a quite different meaning here.
61
  For example, depending on the weighting, I have around 300K images (some images are used multiple times) in an epoch,
62
- and therefore I did not even finish an entire epoch with the 48000 steps at batch size 4.
63
 
64
  ### Failures
65
 
 
54
 
55
  #### Hyperparameter specification
56
 
57
+ The model is trained for 50000 steps, at batch size 4, lr 1e-6, resolution 512, and conditional dropping rate of 10%.
58
 
59
  Note that as a consequence of the weighting scheme which translates into a number of different multiply for each image,
60
  the count of repeat and epoch has a quite different meaning here.
61
  For example, depending on the weighting, I have around 300K images (some images are used multiple times) in an epoch,
62
+ and therefore I did not even finish an entire epoch with the 50000 steps at batch size 4.
63
 
64
  ### Failures
65