toilaluan commited on
Commit
12fe4cb
·
verified ·
1 Parent(s): d75879d

Trained for 3 epochs and 4000 steps.

Browse files

Trained with datasets ['text-embeds', 'mj-v6']
Learning rate 8e-06, batch size 32, and 4 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: PixArt-alpha/PixArt-Sigma-XL-2-1024-MS
VAE: madebyollin/sdxl-vae-fp16-fix

README.md CHANGED
@@ -211,7 +211,7 @@ You may reuse the base model text encoder for inference.
211
  ## Training settings
212
 
213
  - Training epochs: 3
214
- - Training steps: 3500
215
  - Learning rate: 8e-06
216
  - Effective batch size: 128
217
  - Micro-batch size: 32
 
211
  ## Training settings
212
 
213
  - Training epochs: 3
214
+ - Training steps: 4000
215
  - Learning rate: 8e-06
216
  - Effective batch size: 128
217
  - Micro-batch size: 32
optimizer.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fdf25c6b3ce5e1782dcf79482e60e9412dc65d57fcdd527d093a2089e1266a1e
3
  size 3665677155
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:664ac8c09727af6e47e0611142340885e5f7256fab2f23b9f396ab042cf09466
3
  size 3665677155
random_states_0.pkl CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b5a357d361469b4f14e9f83db727fc543c6ad6f92c8d7b5b8788569c90812278
3
- size 14280
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4f61b896f3567a25eafb77371015f5cdac5af1d6c3642962ce5679c570d9273a
3
+ size 14344
scheduler.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:32c5484f657772c0e4b8347102a4bff0865f0eb2e4699a6081b826ee611a35f0
3
  size 1000
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9bc35c4fe64ca9260b42737f3bc4ae4d5e5918cfc8a4ac4e18fe27fe53d3195a
3
  size 1000
training_state-mj-v6.json CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ac9790ec78672ee24757746842ddc5c1e67845dc9bf6840bfae7ae80133b2bf0
3
- size 11305059
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f2c338fd8ace1ded0ed2cc1f95f2b27eb29f8a307b6594b6ae5faaa6bb65931a
3
+ size 16553059
training_state.json CHANGED
@@ -1 +1 @@
1
- {"global_step": 3500, "epoch_step": 105, "epoch": 4, "exhausted_backends": [], "repeats": {"mj-v6": 0}}
 
1
+ {"global_step": 4000, "epoch_step": 605, "epoch": 4, "exhausted_backends": [], "repeats": {"mj-v6": 0}}
transformer/diffusion_pytorch_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7b588665bcd6770db3571f10d1a611fcc326bd1882c1a6e9255a07594b1eb7a1
3
  size 1221780352
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9aa3365d24b5219374f6160de6aa245b84b9c8c4b1691f52e71ed9b2eb3de1d0
3
  size 1221780352