Trained for 5 epochs and 6500 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: 4
-- Training steps: 6000
+- Training epochs: 5
+- Training steps: 6500
 - Learning rate: 4e-07
 - Effective batch size: 512
   - Micro-batch size: 32
@@ -1023,7 +1023,7 @@ You may reuse the base model text encoder for inference.
 
 ### photo-concept-bucket
 - Repeats: 0
-- Total number of images: ~842600
+- Total number of images: ~559104
 - Total number of aspect buckets: 1
 - Resolution: 1.0 megapixels
 - Cropped: True

optimizer.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d6ce58989d26dafb9a704bee8888b6f0dc75e192f0e5831f3ab091e164de7634
+oid sha256:1238f19dcb9f1393fbb516cb160210ac993c4657a0e56477f55dac0096ba1a79
 size 5451415117

random_states_0.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:939489b6d84969757c0ff33ea1df0aa5a65d80fbe757720bf533a4a20057067d
+oid sha256:baa6a9bf814e0ed71183ec7e5da500f96a5c1f4c629e9c3e73ffcb7756645951
 size 16100

scheduler.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e361cefdc40fb670380cb05df7a013e87a783507c8ba1ea5a2380145ff9a8204
+oid sha256:140141a67564b5fcd24071ba92f8cce429f8384321c33661c79f107fed755349
 size 1000

training_state-photo-concept-bucket.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ff6048e9f43fcedca7bee71e4f719573ca33084cc277ee2e3567680672e83bab
-size 11552240
+oid sha256:8fa830db907788b7245ab18fc745dff4f887b342017c0db07796accf7b60a0ce
+size 6518044

training_state.json

@@ -1 +1 @@
-{"global_step": 6000, "epoch_step": 1316, "epoch": 5, "exhausted_backends": [], "repeats": {"photo-concept-bucket": 0}}
+{"global_step": 6500, "epoch_step": 486, "epoch": 6, "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 sha256:9f441543acdf07ee3acf79518dba5c5be037ff595e8eb4fd57bcfb032f7ef6a2
+oid sha256:bcdab254594a8b5405acbaa380bab8a790c981cba4cc452f98c2b94c6c0ec3ef
 size 1816969728