PseudoTerminal X commited on
Commit
e64c98d
1 Parent(s): 03828d7

Trained for 0 epochs and 1500 steps.

Browse files

Trained 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 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: 1000
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: 10
1186
  - Resolution: 1.0 megapixels
1187
  - Cropped: False
1188
  - Crop style: None
 
1164
  ## Training settings
1165
 
1166
  - Training epochs: 0
1167
+ - Training steps: 1500
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: 7
1186
  - Resolution: 1.0 megapixels
1187
  - Cropped: False
1188
  - Crop style: None
optimizer.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:08602cda47da4b8cb32402aa293ddefeab0ccdf59515a1f7e61ededdd61b90ae
3
  size 12170595712
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9ac9249a50f951af9d8473f2c25018d58672709357de563ebfa3f4ab3a801589
3
  size 12170595712
random_states_0.pkl CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ffbbcf958e88145cf3feed3080d97f85c5adda60deb45a7cb1630bad6926d334
3
- size 16036
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:21768a37d2d43ccd3cde775fbdbaf398ae5c83f7529123d32ab88f4d06a3b709
3
+ size 16100
scheduler.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:35dcdfcefe3a591b7e0d35f7d0939e6fac496e4940e8b5a3b65b8f2b9f73d553
3
  size 1128
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f17b16004b11e75605c2a22b7257acadf0dfb90d6a2a4129c992664bccc47570
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": 1000, "epoch_step": 1000, "epoch": 1, "exhausted_backends": [], "repeats": {}}
 
1
+ {"global_step": 1500, "epoch_step": 1500, "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 sha256:844f0c8c4d265bb15bd48340ba34369d9074e9e887fba44f95a324e6acdd8f49
3
  size 4169982088
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:39e1f75b887fa18a8b859ef2683c91e1f73608fa21ae80250eaf1db3efba5638
3
  size 4169982088