Trained for 43 epochs and 2000 steps.

Trained with datasets ['text-embeds', 'mynewlora-sd35m']
Learning rate 0.0002, batch size 2, and 1 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: /my_volume/weights
VAE: None

pytorch_lora_weights.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:441011d401dce1e9f2f84797ef29f49e87269df18f4e5cd127e254b8d44bb712
+oid sha256:30c24367fda130774efd4682a59711a50b09e6c82c32a386d8d53ee57cb39770
 size 378576448