quzo commited on
Commit
986ac26
·
verified ·
1 Parent(s): a79fa16

Model card auto-generated by SimpleTuner

Browse files
Files changed (1) hide show
  1. README.md +2 -2
README.md CHANGED
@@ -65,8 +65,8 @@ You may reuse the base model text encoder for inference.
65
  - Learning rate schedule: polynomial
66
  - Warmup steps: 100
67
  - Max grad value: 2.0
68
- - Effective batch size: 2
69
- - Micro-batch size: 2
70
  - Gradient accumulation steps: 1
71
  - Number of GPUs: 1
72
  - Gradient checkpointing: True
 
65
  - Learning rate schedule: polynomial
66
  - Warmup steps: 100
67
  - Max grad value: 2.0
68
+ - Effective batch size: 1
69
+ - Micro-batch size: 1
70
  - Gradient accumulation steps: 1
71
  - Number of GPUs: 1
72
  - Gradient checkpointing: True