Trained for 3 epochs and 3500 steps.

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

@@ -1005,8 +1005,8 @@ You may reuse the base model text encoder for inference.
 
 ## Training settings
 
-- Training epochs: 2
-- Training steps: 3000
+- Training epochs: 3
+- Training steps: 3500
 - Learning rate: 4e-07
 - Effective batch size: 512
   - Micro-batch size: 32

optimizer.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8ab9b102aff07e517f5345ddd45c70793c00077462adf5dea0b955f8b3e948ea
+oid sha256:4edaaf19920d3d6a46607c022d3b6b470ec450aaf717922999e16391b0b1b46e
 size 5451415117

random_states_0.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4ccdb88b01409cd41df0e75c40e1eb331096dd75696ab1c559761ad15bd2ea84
-size 16036
+oid sha256:1495b449207bdadd4ea0402389981ad0a4d56b4e73903a636cc36f0d41548c26
+size 16100

scheduler.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bd715e43acb21f986ef7e34ee58add68ace71b6684ab7ebbe6dad0839b03952d
+oid sha256:636a5983c58cb34c8629f71677861a6d1f13f0369fb3fbe0365526df69f97f6a
 size 1000

training_state-photo-concept-bucket.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:45a0771be28fcee90692f2c3b7c3cbc8ea287404f2e58a98c250c4d5aa884916
-size 7966137
+oid sha256:5a3a37ef39f79119c29bd9150bbe4d8becca363bb2e476841b4a5f68fda61faf
+size 5364416

training_state.json

@@ -1 +1 @@
-{"global_step": 3000, "epoch_step": 816, "epoch": 3, "exhausted_backends": [], "repeats": {"photo-concept-bucket": 0}}
+{"global_step": 3500, "epoch_step": 224, "epoch": 4, "exhausted_backends": [], "repeats": {"photo-concept-bucket": 0}}

transformer/diffusion_pytorch_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dc7fae450519f04192ef3f1945f5587bf670ca96eb64785dd79125a087c1e7e9
+oid sha256:207d463be1d711e9f7466b69c1bf137ea0a09b860c6af833155dee9e09e9bf6b
 size 1816969728