PseudoTerminal X commited on
Commit
4a04334
1 Parent(s): ef6a296

Trained for 4 epochs and 5000 steps.

Browse files

Trained with datasets ['text-embeds-pixart-nofilter', 'photo-concept-bucket']
Learning rate 4e-07, batch size 32, and 2 gradient accumulation steps.
Used DDPM noise scheduler for training with epsilon prediction type and rescaled_betas_zero_snr=False
Using 'linspace' timestep spacing.
Base model: terminusresearch/pixart-900m-1024
VAE: madebyollin/sdxl-vae-fp16-fix

README.md CHANGED
@@ -1006,7 +1006,7 @@ You may reuse the base model text encoder for inference.
1006
  ## Training settings
1007
 
1008
  - Training epochs: 4
1009
- - Training steps: 4500
1010
  - Learning rate: 4e-07
1011
  - Effective batch size: 512
1012
  - Micro-batch size: 32
 
1006
  ## Training settings
1007
 
1008
  - Training epochs: 4
1009
+ - Training steps: 5000
1010
  - Learning rate: 4e-07
1011
  - Effective batch size: 512
1012
  - Micro-batch size: 32
optimizer.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:58f94e3fc5c4c3bfa6c3ec918b0ae980070f88df16331e6c94c85fc3c941968b
3
  size 5451415117
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e43c0be0d4d9d1b646b52e57a6413b5cf96553adecdab07990e782ed8edac292
3
  size 5451415117
random_states_0.pkl CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5f1e9e93b6d752fb9ed18b629ee819f77d3a63e6ff4410278bc8c59b1f7e3ede
3
  size 16036
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a518b5660ab3decca6723356533425d97e789c442c88430c2bfe1209ae9329c8
3
  size 16036
scheduler.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a7968b8174f8d421a4a64525b8a2fbe0baabe3a7ad74b8d647a0c4aa16e0dbcf
3
  size 1000
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2ae859823923a893a2ee0ee95fc3669d8278594dd3edc1c5dfe81894d6b43dd7
3
  size 1000
training_state-photo-concept-bucket.json CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4b1828a96431c822cca4d9e5921885d784f45b1fc8435d7675524eed76f3729b
3
- size 4960101
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d2419897a82b66ad9b7a9bf24e057ca4e21fe3fc2485ea18539003a46e97aec4
3
+ size 7157496
training_state.json CHANGED
@@ -1 +1 @@
1
- {"global_step": 4500, "epoch_step": 132, "epoch": 5, "exhausted_backends": [], "repeats": {"photo-concept-bucket": 0}}
 
1
+ {"global_step": 5000, "epoch_step": 632, "epoch": 5, "exhausted_backends": [], "repeats": {"photo-concept-bucket": 0}}
transformer/diffusion_pytorch_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4f8ef65a630c6493d65aef9ad59f4839077c507ff634a725ee2fc21df9dea909
3
  size 1816969728
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:62acb7b0c9e20b0ebad897ebda2b754bd9b9e3669d820d1b1fc977aa6e77c015
3
  size 1816969728