NYUAD-ComNets commited on
Commit
713f465
·
verified ·
1 Parent(s): e74983c

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +8 -2
README.md CHANGED
@@ -18,8 +18,14 @@ from PIL import Image
18
  ### Training hyperparameters
19
 
20
 
21
-
22
-
 
 
 
 
 
 
23
 
24
 
25
 
 
18
  ### Training hyperparameters
19
 
20
 
21
+ - Low-Rank Adaptation (LoRA)
22
+ - training = 7 epochs
23
+ - learning rate = 0.0002
24
+ - batch sizes = 1 per device
25
+ - gradient accumulation steps = 1.
26
+ - The optimizer "paged_adamw_32bit"
27
+ - 10 warmup steps
28
+ - 4-bit quantization with the NormalFloat 4 format
29
 
30
 
31