Add V0_1 LoRA checkpoint and version note
Browse files
MaxiMin-HHH-R2V-ThisIsFine_LoRA_V0_1.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d5442fe0f63abf503d42e26af5f61477441b9b67bd440c01a9376d74c5415251
|
| 3 |
+
size 596428480
|
README.md
CHANGED
|
@@ -1,3 +1,5 @@
|
|
|
|
|
|
|
|
| 1 |
Current V0 went through :
|
| 2 |
- 100 initial steps at LR 5e-5 (batch size 8)
|
| 3 |
- 1100 more steps at LR 1e-4 (batch size 32)
|
|
|
|
| 1 |
+
V0_1: 2,800 more training steps compared to V0.
|
| 2 |
+
|
| 3 |
Current V0 went through :
|
| 4 |
- 100 initial steps at LR 5e-5 (batch size 8)
|
| 5 |
- 1100 more steps at LR 1e-4 (batch size 32)
|