Trained for 0 epochs and 250 steps.

Trained with datasets ['text-embeds', 'pacs']
Learning rate 0.0001, batch size 4, 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: /ephemeral/shashmi/llava_lets_go/chimaa_finetuner/stable-diffusion-3.5-medium
VAE: None

pytorch_lora_weights.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f5ee776252350d1477cee44e8c9e77c3e307ef9e63993315868c7161d4cf0fee
+size 116431016