PseudoTerminal X
commited on
Commit
•
03bde3c
1
Parent(s):
3f7f6ea
Trained for 0 epochs and 1000 steps.
Browse filesTrained with datasets ['text-embeds-sd3-nofilter', 'photo-concept-bucket', 'dalle3']
Learning rate 1e-06, batch size 6, and 2 gradient accumulation steps.
Used DDPM noise scheduler for training with epsilon prediction type and rescaled_betas_zero_snr=False
Using 'trailing' timestep spacing.
Base model: stabilityai/stable-diffusion-3-medium-diffusers
VAE: None
- README.md +3 -3
- optimizer.bin +1 -1
- random_states_0.pkl +2 -2
- scheduler.bin +1 -1
- training_state-dalle3.json +0 -0
- training_state-photo-concept-bucket.json +0 -0
- training_state.json +1 -1
- transformer/diffusion_pytorch_model.safetensors +1 -1
README.md
CHANGED
@@ -1164,7 +1164,7 @@ You may reuse the base model text encoder for inference.
|
|
1164 |
## Training settings
|
1165 |
|
1166 |
- Training epochs: 0
|
1167 |
-
- Training steps:
|
1168 |
- Learning rate: 1e-06
|
1169 |
- Effective batch size: 96
|
1170 |
- Micro-batch size: 6
|
@@ -1182,7 +1182,7 @@ You may reuse the base model text encoder for inference.
|
|
1182 |
### photo-concept-bucket
|
1183 |
- Repeats: 0
|
1184 |
- Total number of images: ~557568
|
1185 |
-
- Total number of aspect buckets:
|
1186 |
- Resolution: 1.0 megapixels
|
1187 |
- Cropped: False
|
1188 |
- Crop style: None
|
@@ -1190,7 +1190,7 @@ You may reuse the base model text encoder for inference.
|
|
1190 |
### dalle3
|
1191 |
- Repeats: 0
|
1192 |
- Total number of images: ~984960
|
1193 |
-
- Total number of aspect buckets:
|
1194 |
- Resolution: 1.0 megapixels
|
1195 |
- Cropped: False
|
1196 |
- Crop style: None
|
|
|
1164 |
## Training settings
|
1165 |
|
1166 |
- Training epochs: 0
|
1167 |
+
- Training steps: 1000
|
1168 |
- Learning rate: 1e-06
|
1169 |
- Effective batch size: 96
|
1170 |
- Micro-batch size: 6
|
|
|
1182 |
### photo-concept-bucket
|
1183 |
- Repeats: 0
|
1184 |
- Total number of images: ~557568
|
1185 |
+
- Total number of aspect buckets: 10
|
1186 |
- Resolution: 1.0 megapixels
|
1187 |
- Cropped: False
|
1188 |
- Crop style: None
|
|
|
1190 |
### dalle3
|
1191 |
- Repeats: 0
|
1192 |
- Total number of images: ~984960
|
1193 |
+
- Total number of aspect buckets: 2
|
1194 |
- Resolution: 1.0 megapixels
|
1195 |
- Cropped: False
|
1196 |
- Crop style: None
|
optimizer.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 12170595712
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cfe3cf63492fc14997c24a60075a4dd14eaddcdadd381aa5de22ecc113f18727
|
3 |
size 12170595712
|
random_states_0.pkl
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:92551ec7c7d3ef4a8231bfd2ba4e14249518be35519f29449341b107a8ebbf33
|
3 |
+
size 16100
|
scheduler.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1128
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:35dcdfcefe3a591b7e0d35f7d0939e6fac496e4940e8b5a3b65b8f2b9f73d553
|
3 |
size 1128
|
training_state-dalle3.json
CHANGED
The diff for this file is too large to render.
See raw diff
|
|
training_state-photo-concept-bucket.json
CHANGED
The diff for this file is too large to render.
See raw diff
|
|
training_state.json
CHANGED
@@ -1 +1 @@
|
|
1 |
-
{"global_step":
|
|
|
1 |
+
{"global_step": 1000, "epoch_step": 1000, "epoch": 1, "exhausted_backends": [], "repeats": {}}
|
transformer/diffusion_pytorch_model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4169982088
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1d642e76b512091f56d0a3d919a907a719e3a0d0e6c13ee430a8fbc56358b3e5
|
3 |
size 4169982088
|