Model card auto-generated by SimpleTuner
Browse files
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:
|
| 69 |
-
- Micro-batch size:
|
| 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
|