Upload folder using huggingface_hub

dad0ec1 verified 5 months ago

233 kB

	Using devices [TpuDevice(id=0, process_index=0, coords=(0,0,0), core_on_chip=0), TpuDevice(id=1, process_index=0, coords=(1,0,0), core_on_chip=0), TpuDevice(id=2, process_index=0, coords=(0,1,0), core_on_chip=0), TpuDevice(id=3, process_index=0, coords=(1,1,0), core_on_chip=0)]
	Device count 4
	Global device count 4
	Global Batch: 512
	Node Batch: 512
	Device Batch: 128
	/tmp/tmpnz136wdu
	Loading dataset
	Loading dataset
	creating model
	beta1: 0.9
	beta2: 0.999
	bootstrap_cfg: 1
	bootstrap_dt_bias: 0
	bootstrap_ema: 1
	bootstrap_every: 8
	cfg_scale: 1.5
	class_dropout_prob: 0.1
	denoise_timesteps: 128
	depth: 12
	dropout: 0.0
	dt_sampling: uniform
	hidden_size: 768
	lr: 0.0001
	mlp_ratio: 4
	num_classes: 1000
	num_heads: 12
	patch_size: 2
	sharding: dp
	t_sampling: discrete-dt
	target_update_rate: 0.999
	train_type: naive
	use_cosine: 0
	use_ema: 0
	use_stable_vae: 1
	warmup: 0
	weight_decay: 0.1

	Total devices TPU_0(process=0,(0,0,0,0))
	Initializing encoder.
	Incoming encoder shape (1, 256, 256, 3)
	Encoder layer (1, 256, 256, 128)
	doing downsample
	Encoder layer (1, 128, 128, 128)
	doing downsample
	Encoder layer (1, 64, 64, 256)
	doing downsample
	Encoder layer (1, 32, 32, 512)
	Encoder layer (1, 32, 32, 512)
	Encoder layer final (1, 32, 32, 512)
	Encoder layer final (1, 32, 32, 512)
	Final embeddings are size (1, 32, 32, 8)
	After quant (1, 32, 32, 4)
	encode finished
	Decoder incoming shape (1, 32, 32, 4)
	Decoder input (1, 32, 32, 512)
	Mid Block Decoder layer (1, 32, 32, 512)
	Mid Block Decoder layer (1, 32, 32, 512)
	Decoder layer (1, 64, 64, 512)
	Decoder layer (1, 128, 128, 512)
	Decoder layer (1, 256, 256, 256)
	Decoder layer (1, 256, 256, 128)
	Total num of VQVAE parameters: 67565323
	Disc shape (1, 128, 128, 128)
	Disc shape (1, 64, 64, 256)
	Disc shape (1, 32, 32, 512)
	Disc shape (1, 16, 16, 512)
	Disc shape (1, 8, 8, 512)
	Disc shape (1, 4, 4, 512)
	Total num of Discriminator parameters: 23998017
	Loaded checkpoint from 19102877 seconds ago.
	Loaded model with step 447001
	┌──────────────────────────────────────────────────────────────────────────────┐
	│ TPU 0 │
	├──────────────────────────────────────────────────────────────────────────────┤
	│ TPU 1 │
	├──────────────────────────────────────────────────────────────────────────────┤
	│ TPU 2 │
	├──────────────────────────────────────────────────────────────────────────────┤
	│ TPU 3 │
	└──────────────────────────────────────────────────────────────────────────────┘
	returning model
	model done
	Input to vae (4, 1, 256, 256, 3)
	encode image shape (1, 256, 256, 3)
	Initializing encoder.
	Incoming encoder shape (1, 256, 256, 3)
	Encoder layer (1, 256, 256, 128)
	doing downsample
	Encoder layer (1, 128, 128, 128)
	doing downsample
	Encoder layer (1, 64, 64, 256)
	doing downsample
	Encoder layer (1, 32, 32, 512)
	Encoder layer (1, 32, 32, 512)
	Encoder layer final (1, 32, 32, 512)
	Encoder layer final (1, 32, 32, 512)
	Final embeddings are size (1, 32, 32, 8)
	After quant (1, 32, 32, 4)
	output example shape (4, 1, 32, 32, 4)
	Test data shape (4, 256, 256, 3)
	x shape (4, 1, 256, 256, 3)
	encoded shape (4, 1, 32, 32, 4)
	z_vectors shape (1, 32, 32, 4)
	Decoder incoming shape (1, 32, 32, 4)
	Decoder input (1, 32, 32, 512)
	Mid Block Decoder layer (1, 32, 32, 512)
	Mid Block Decoder layer (1, 32, 32, 512)
	Decoder layer (1, 64, 64, 512)
	Decoder layer (1, 128, 128, 512)
	Decoder layer (1, 256, 256, 256)
	Decoder layer (1, 256, 256, 128)
	image shape (4, 1, 256, 256, 3)
	decoded img shape (256, 256, 3)
	obs shape (4, 32, 32, 4)
	DiT: Input of shape (4, 32, 32, 4) dtype float32
	DiT: After patch embed, shape is (4, 256, 768) dtype bfloat16
	DiT: Patch Embed of shape (4, 256, 768) dtype bfloat16
	DiT: Conditioning of shape (1, 768) dtype float32

	[3m DiT Summary [0m
	┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┓
	┃[1m [0m[1mpath [0m[1m [0m┃[1m [0m[1mmodule [0m[1m [0m┃[1m [0m[1minputs [0m[1m [0m┃[1m [0m[1moutputs [0m[1m [0m┃[1m [0m[1mparams [0m[1m [0m┃
	┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┩
	│ │ DiT │ - [2mfloat32[0m[4,32,32,4] │ [2mbfloat16[0m[4,32,32,4] │ │
	│ │ │ - [2mfloat32[0m[1] │ │ │
	│ │ │ - [2mfloat32[0m[1] │ │ │
	│ │ │ - [2mint32[0m[1] │ │ │
	├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤
	│ PatchEmbed_0 │ PatchEmbed │ [2mfloat32[0m[4,32,32,4] │ [2mbfloat16[0m[4,256,768] │ │
	├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤
	│ PatchEmbed_0/Conv_0 │ Conv │ [2mfloat32[0m[4,32,32,4] │ [2mbfloat16[0m[4,16,16,768] │ bias: [2mfloat32[0m[768] │
	│ │ │ │ │ kernel: [2mfloat32[0m[2,2,4,768] │
	│ │ │ │ │ │
	│ │ │ │ │ [1m13,056 [0m[1;2m(52.2 KB)[0m │
	├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤
	│ TimestepEmbedder_0 │ TimestepEmbedder │ [2mfloat32[0m[1] │ [2mfloat32[0m[1,768] │ │
	├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤
	│ TimestepEmbedder_0/Dense_0 │ Dense │ [2mbfloat16[0m[1,256] │ [2mbfloat16[0m[1,768] │ bias: [2mfloat32[0m[768] │
	│ │ │ │ │ kernel: [2mfloat32[0m[256,768] │
	│ │ │ │ │ │
	│ │ │ │ │ [1m197,376 [0m[1;2m(789.5 KB)[0m │
	├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤
	│ TimestepEmbedder_0/Dense_1 │ Dense │ [2mbfloat16[0m[1,768] │ [2mfloat32[0m[1,768] │ bias: [2mfloat32[0m[768] │
	│ │ │ │ │ kernel: [2mfloat32[0m[768,768] │
	│ │ │ │ │ │
	│ │ │ │ │ [1m590,592 [0m[1;2m(2.4 MB)[0m │
	├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤
	│ TimestepEmbedder_1 │ TimestepEmbedder │ [2mfloat32[0m[1] │ [2mfloat32[0m[1,768] │ │
	├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤
	│ TimestepEmbedder_1/Dense_0 │ Dense │ [2mbfloat16[0m[1,256] │ [2mbfloat16[0m[1,768] │ bias: [2mfloat32[0m[768] │
	│ │ │ │ │ kernel: [2mfloat32[0m[256,768] │
	│ │ │ │ │ │
	│ │ │ │ │ [1m197,376 [0m[1;2m(789.5 KB)[0m │
	├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤
	│ TimestepEmbedder_1/Dense_1 │ Dense │ [2mbfloat16[0m[1,768] │ [2mfloat32[0m[1,768] │ bias: [2mfloat32[0m[768] │
	│ │ │ │ │ kernel: [2mfloat32[0m[768,768] │
	│ │ │ │ │ │
	│ │ │ │ │ [1m590,592 [0m[1;2m(2.4 MB)[0m │
	├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤
	│ LabelEmbedder_0 │ LabelEmbedder │ [2mint32[0m[1] │ [2mbfloat16[0m[1,768] │ │
	├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤
	│ LabelEmbedder_0/Embed_0 │ Embed │ [2mint32[0m[1] │ [2mbfloat16[0m[1,768] │ embedding: [2mfloat32[0m[1001,768] │
	│ │ │ │ │ │
	│ │ │ │ │ [1m768,768 [0m[1;2m(3.1 MB)[0m │
	├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤
	│ DiTBlock_0 │ DiTBlock │ - [2mbfloat16[0m[4,256,768] │ [2mbfloat16[0m[4,256,768] │ │
	│ │ │ - [2mfloat32[0m[1,768] │ │ │
	├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤
	│ DiTBlock_0/Dense_0 │ Dense │ [2mfloat32[0m[1,768] │ [2mbfloat16[0m[1,4608] │ bias: [2mfloat32[0m[4608] │
	│ │ │ │ │ kernel: [2mfloat32[0m[768,4608] │
	│ │ │ │ │ │
	│ │ │ │ │ [1m3,543,552 [0m[1;2m(14.2 MB)[0m │
	├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤
	│ DiTBlock_0/LayerNorm_0 │ LayerNorm │ [2mbfloat16[0m[4,256,768] │ [2mbfloat16[0m[4,256,768] │ │
	├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤
	│ DiTBlock_0/Dense_1 │ Dense │ [2mbfloat16[0m[4,256,768] │ [2mbfloat16[0m[4,256,768] │ bias: [2mfloat32[0m[768] │
	│ │ │ │ │ kernel: [2mfloat32[0m[768,768] │
	│ │ │ │ │ │
	│ │ │ │ │ [1m590,592 [0m[1;2m(2.4 MB)[0m │
	├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤
	│ DiTBlock_0/Dense_2 │ Dense │ [2mbfloat16[0m[4,256,768] │ [2mbfloat16[0m[4,256,768] │ bias: [2mfloat32[0m[768] │
	│ │ │ │ │ kernel: [2mfloat32[0m[768,768] │
	│ │ │ │ │ │
	│ │ │ │ │ [1m590,592 [0m[1;2m(2.4 MB)[0m │
	├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤
	│ DiTBlock_0/Dense_3 │ Dense │ [2mbfloat16[0m[4,256,768] │ [2mbfloat16[0m[4,256,768] │ bias: [2mfloat32[0m[768] │
	│ │ │ │ │ kernel: [2mfloat32[0m[768,768] │
	│ │ │ │ │ │
	│ │ │ │ │ [1m590,592 [0m[1;2m(2.4 MB)[0m │
	├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤
	│ DiTBlock_0/Dense_4 │ Dense │ [2mfloat32[0m[4,256,768] │ [2mbfloat16[0m[4,256,768] │ bias: [2mfloat32[0m[768] │
	│ │ │ │ │ kernel: [2mfloat32[0m[768,768] │
	│ │ │ │ │ │
	│ │ │ │ │ [1m590,592 [0m[1;2m(2.4 MB)[0m │
	├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤
	│ DiTBlock_0/LayerNorm_1 │ LayerNorm │ [2mbfloat16[0m[4,256,768] │ [2mbfloat16[0m[4,256,768] │ │
	├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤
	│ DiTBlock_0/MlpBlock_0 │ MlpBlock │ [2mbfloat16[0m[4,256,768] │ [2mbfloat16[0m[4,256,768] │ │
	├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤
	│ DiTBlock_0/MlpBlock_0/Dense_0 │ Dense │ [2mbfloat16[0m[4,256,768] │ [2mbfloat16[0m[4,256,3072] │ bias: [2mfloat32[0m[3072] │
	│ │ │ │ │ kernel: [2mfloat32[0m[768,3072] │
	│ │ │ │ │ │
	│ │ │ │ │ [1m2,362,368 [0m[1;2m(9.4 MB)[0m │
	├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤
	│ DiTBlock_0/MlpBlock_0/Dropout_0 │ Dropout │ [2mbfloat16[0m[4,256,3072] │ [2mbfloat16[0m[4,256,3072] │ │
	├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤
	│ DiTBlock_0/MlpBlock_0/Dense_1 │ Dense │ [2mbfloat16[0m[4,256,3072] │ [2mbfloat16[0m[4,256,768] │ bias: [2mfloat32[0m[768] │
	│ │ │ │ │ kernel: [2mfloat32[0m[3072,768] │
	│ │ │ │ │ │
	│ │ │ │ │ [1m2,360,064 [0m[1;2m(9.4 MB)[0m │
	├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤
	│ DiTBlock_0/MlpBlock_0/Dropout_1 │ Dropout │ [2mbfloat16[0m[4,256,768] │ [2mbfloat16[0m[4,256,768] │ │
	├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤
	│ DiTBlock_1 │ DiTBlock │ - [2mbfloat16[0m[4,256,768] │ [2mbfloat16[0m[4,256,768] │ │
	│ │ │ - [2mfloat32[0m[1,768] │ │ │
	├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤
	│ DiTBlock_1/Dense_0 │ Dense │ [2mfloat32[0m[1,768] │ [2mbfloat16[0m[1,4608] │ bias: [2mfloat32[0m[4608] │
	│ │ │ │ │ kernel: [2mfloat32[0m[768,4608] │
	│ │ │ │ │ │
	│ │ │ │ │ [1m3,543,552 [0m[1;2m(14.2 MB)[0m │
	├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤
	│ DiTBlock_1/LayerNorm_0 │ LayerNorm │ [2mbfloat16[0m[4,256,768] │ [2mbfloat16[0m[4,256,768] │ │
	├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤
	│ DiTBlock_1/Dense_1 │ Dense │ [2mbfloat16[0m[4,256,768] │ [2mbfloat16[0m[4,256,768] │ bias: [2mfloat32[0m[768] │
	│ │ │ │ │ kernel: [2mfloat32[0m[768,768] │
	│ │ │ │ │ │
	│ │ │ │ │ [1m590,592 [0m[1;2m(2.4 MB)[0m │
	├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤
	│ DiTBlock_1/Dense_2 │ Dense │ [2mbfloat16[0m[4,256,768] │ [2mbfloat16[0m[4,256,768] │ bias: [2mfloat32[0m[768] │
	│ │ │ │ │ kernel: [2mfloat32[0m[768,768] │
	│ │ │ │ │ │
	│ │ │ │ │ [1m590,592 [0m[1;2m(2.4 MB)[0m │
	├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤
	│ DiTBlock_1/Dense_3 │ Dense │ [2mbfloat16[0m[4,256,768] │ [2mbfloat16[0m[4,256,768] │ bias: [2mfloat32[0m[768] │
	│ │ │ │ │ kernel: [2mfloat32[0m[768,768] │
	│ │ │ │ │ │
	│ │ │ │ │ [1m590,592 [0m[1;2m(2.4 MB)[0m │
	├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤
	│ DiTBlock_1/Dense_4 │ Dense │ [2mfloat32[0m[4,256,768] │ [2mbfloat16[0m[4,256,768] │ bias: [2mfloat32[0m[768] │
	│ │ │ │ │ kernel: [2mfloat32[0m[768,768] │
	│ │ │ │ │ │
	│ │ │ │ │ [1m590,592 [0m[1;2m(2.4 MB)[0m │
	├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤
	│ DiTBlock_1/LayerNorm_1 │ LayerNorm │ [2mbfloat16[0m[4,256,768] │ [2mbfloat16[0m[4,256,768] │ │
	├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤
	│ DiTBlock_1/MlpBlock_0 │ MlpBlock │ [2mbfloat16[0m[4,256,768] │ [2mbfloat16[0m[4,256,768] │ │
	├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤
	│ DiTBlock_1/MlpBlock_0/Dense_0 │ Dense │ [2mbfloat16[0m[4,256,768] │ [2mbfloat16[0m[4,256,3072] │ bias: [2mfloat32[0m[3072] │
	│ │ │ │ │ kernel: [2mfloat32[0m[768,3072] │
	│ │ │ │ │ │
	│ │ │ │ │ [1m2,362,368 [0m[1;2m(9.4 MB)[0m │
	├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤
	│ DiTBlock_1/MlpBlock_0/Dropout_0 │ Dropout │ [2mbfloat16[0m[4,256,3072] │ [2mbfloat16[0m[4,256,3072] │ │
	├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤
	│ DiTBlock_1/MlpBlock_0/Dense_1 │ Dense │ [2mbfloat16[0m[4,256,3072] │ [2mbfloat16[0m[4,256,768] │ bias: [2mfloat32[0m[768] │
	│ │ │ │ │ kernel: [2mfloat32[0m[3072,768] │
	│ │ │ │ │ │
	│ │ │ │ │ [1m2,360,064 [0m[1;2m(9.4 MB)[0m │
	├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤
	│ DiTBlock_1/MlpBlock_0/Dropout_1 │ Dropout │ [2mbfloat16[0m[4,256,768] │ [2mbfloat16[0m[4,256,768] │ │
	├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤
	│ DiTBlock_2 │ DiTBlock │ - [2mbfloat16[0m[4,256,768] │ [2mbfloat16[0m[4,256,768] │ │
	│ │ │ - [2mfloat32[0m[1,768] │ │ │
	├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤
	│ DiTBlock_2/Dense_0 │ Dense │ [2mfloat32[0m[1,768] │ [2mbfloat16[0m[1,4608] │ bias: [2mfloat32[0m[4608] │
	│ │ │ │ │ kernel: [2mfloat32[0m[768,4608] │
	│ │ │ │ │ │
	│ │ │ │ │ [1m3,543,552 [0m[1;2m(14.2 MB)[0m │
	├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤
	│ DiTBlock_2/LayerNorm_0 │ LayerNorm │ [2mbfloat16[0m[4,256,768] │ [2mbfloat16[0m[4,256,768] │ │
	├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤
	│ DiTBlock_2/Dense_1 │ Dense │ [2mbfloat16[0m[4,256,768] │ [2mbfloat16[0m[4,256,768] │ bias: [2mfloat32[0m[768] │
	│ │ │ │ │ kernel: [2mfloat32[0m[768,768] │
	│ │ │ │ │ │
	│ │ │ │ │ [1m590,592 [0m[1;2m(2.4 MB)[0m │
	├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤
	│ DiTBlock_2/Dense_2 │ Dense │ [2mbfloat16[0m[4,256,768] │ [2mbfloat16[0m[4,256,768] │ bias: [2mfloat32[0m[768] │
	│ │ │ │ │ kernel: [2mfloat32[0m[768,768] │
	│ │ │ │ │ │
	│ │ │ │ │ [1m590,592 [0m[1;2m(2.4 MB)[0m │
	├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤
	│ DiTBlock_2/Dense_3 │ Dense │ [2mbfloat16[0m[4,256,768] │ [2mbfloat16[0m[4,256,768] │ bias: [2mfloat32[0m[768] │
	│ │ │ │ │ kernel: [2mfloat32[0m[768,768] │
	│ │ │ │ │ │
	│ │ │ │ │ [1m590,592 [0m[1;2m(2.4 MB)[0m │
	├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤
	│ DiTBlock_2/Dense_4 │ Dense │ [2mfloat32[0m[4,256,768] │ [2mbfloat16[0m[4,256,768] │ bias: [2mfloat32[0m[768] │
	│ │ │ │ │ kernel: [2mfloat32[0m[768,768] │
	│ │ │ │ │ │
	│ │ │ │ │ [1m590,592 [0m[1;2m(2.4 MB)[0m │
	├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤
	│ DiTBlock_2/LayerNorm_1 │ LayerNorm │ [2mbfloat16[0m[4,256,768] │ [2mbfloat16[0m[4,256,768] │ │
	├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤
	│ DiTBlock_2/MlpBlock_0 │ MlpBlock │ [2mbfloat16[0m[4,256,768] │ [2mbfloat16[0m[4,256,768] │ │
	├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤
	│ DiTBlock_2/MlpBlock_0/Dense_0 │ Dense │ [2mbfloat16[0m[4,256,768] │ [2mbfloat16[0m[4,256,3072] │ bias: [2mfloat32[0m[3072] │
	│ │ │ │ │ kernel: [2mfloat32[0m[768,3072] │
	│ │ │ │ │ │
	│ │ │ │ │ [1m2,362,368 [0m[1;2m(9.4 MB)[0m │
	├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤
	│ DiTBlock_2/MlpBlock_0/Dropout_0 │ Dropout │ [2mbfloat16[0m[4,256,3072] │ [2mbfloat16[0m[4,256,3072] │ │
	├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤
	│ DiTBlock_2/MlpBlock_0/Dense_1 │ Dense │ [2mbfloat16[0m[4,256,3072] │ [2mbfloat16[0m[4,256,768] │ bias: [2mfloat32[0m[768] │
	│ │ │ │ │ kernel: [2mfloat32[0m[3072,768] │
	│ │ │ │ │ │
	│ │ │ │ │ [1m2,360,064 [0m[1;2m(9.4 MB)[0m │
	├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤
	│ DiTBlock_2/MlpBlock_0/Dropout_1 │ Dropout │ [2mbfloat16[0m[4,256,768] │ [2mbfloat16[0m[4,256,768] │ │
	├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤
	│ DiTBlock_3 │ DiTBlock │ - [2mbfloat16[0m[4,256,768] │ [2mbfloat16[0m[4,256,768] │ │
	│ │ │ - [2mfloat32[0m[1,768] │ │ │
	├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤
	│ DiTBlock_3/Dense_0 │ Dense │ [2mfloat32[0m[1,768] │ [2mbfloat16[0m[1,4608] │ bias: [2mfloat32[0m[4608] │
	│ │ │ │ │ kernel: [2mfloat32[0m[768,4608] │
	│ │ │ │ │ │
	│ │ │ │ │ [1m3,543,552 [0m[1;2m(14.2 MB)[0m │
	├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤
	│ DiTBlock_3/LayerNorm_0 │ LayerNorm │ [2mbfloat16[0m[4,256,768] │ [2mbfloat16[0m[4,256,768] │ │
	├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤
	│ DiTBlock_3/Dense_1 │ Dense │ [2mbfloat16[0m[4,256,768] │ [2mbfloat16[0m[4,256,768] │ bias: [2mfloat32[0m[768] │
	│ │ │ │ │ kernel: [2mfloat32[0m[768,768] │
	│ │ │ │ │ │
	│ │ │ │ │ [1m590,592 [0m[1;2m(2.4 MB)[0m │
	├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤
	│ DiTBlock_3/Dense_2 │ Dense │ [2mbfloat16[0m[4,256,768] │ [2mbfloat16[0m[4,256,768] │ bias: [2mfloat32[0m[768] │
	│ │ │ │ │ kernel: [2mfloat32[0m[768,768] │
	│ │ │ │ │ │
	│ │ │ │ │ [1m590,592 [0m[1;2m(2.4 MB)[0m │
	├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤
	│ DiTBlock_3/Dense_3 │ Dense │ [2mbfloat16[0m[4,256,768] │ [2mbfloat16[0m[4,256,768] │ bias: [2mfloat32[0m[768] │
	│ │ │ │ │ kernel: [2mfloat32[0m[768,768] │
	│ │ │ │ │ │
	│ │ │ │ │ [1m590,592 [0m[1;2m(2.4 MB)[0m │
	├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤
	│ DiTBlock_3/Dense_4 │ Dense │ [2mfloat32[0m[4,256,768] │ [2mbfloat16[0m[4,256,768] │ bias: [2mfloat32[0m[768] │
	│ │ │ │ │ kernel: [2mfloat32[0m[768,768] │
	│ │ │ │ │ │
	│ │ │ │ │ [1m590,592 [0m[1;2m(2.4 MB)[0m │
	├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤
	│ DiTBlock_3/LayerNorm_1 │ LayerNorm │ [2mbfloat16[0m[4,256,768] │ [2mbfloat16[0m[4,256,768] │ │
	├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤
	│ DiTBlock_3/MlpBlock_0 │ MlpBlock │ [2mbfloat16[0m[4,256,768] │ [2mbfloat16[0m[4,256,768] │ │
	├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤
	│ DiTBlock_3/MlpBlock_0/Dense_0 │ Dense │ [2mbfloat16[0m[4,256,768] │ [2mbfloat16[0m[4,256,3072] │ bias: [2mfloat32[0m[3072] │
	│ │ │ │ │ kernel: [2mfloat32[0m[768,3072] │
	│ │ │ │ │ │
	│ │ │ │ │ [1m2,362,368 [0m[1;2m(9.4 MB)[0m │
	├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤
	│ DiTBlock_3/MlpBlock_0/Dropout_0 │ Dropout │ [2mbfloat16[0m[4,256,3072] │ [2mbfloat16[0m[4,256,3072] │ │
	├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤
	│ DiTBlock_3/MlpBlock_0/Dense_1 │ Dense │ [2mbfloat16[0m[4,256,3072] │ [2mbfloat16[0m[4,256,768] │ bias: [2mfloat32[0m[768] │
	│ │ │ │ │ kernel: [2mfloat32[0m[3072,768] │
	│ │ │ │ │ │
	│ │ │ │ │ [1m2,360,064 [0m[1;2m(9.4 MB)[0m │
	├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤
	│ DiTBlock_3/MlpBlock_0/Dropout_1 │ Dropout │ [2mbfloat16[0m[4,256,768] │ [2mbfloat16[0m[4,256,768] │ │
	├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤
	│ DiTBlock_4 │ DiTBlock │ - [2mbfloat16[0m[4,256,768] │ [2mbfloat16[0m[4,256,768] │ │
	│ │ │ - [2mfloat32[0m[1,768] │ │ │
	├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤
	│ DiTBlock_4/Dense_0 │ Dense │ [2mfloat32[0m[1,768] │ [2mbfloat16[0m[1,4608] │ bias: [2mfloat32[0m[4608] │
	│ │ │ │ │ kernel: [2mfloat32[0m[768,4608] │
	│ │ │ │ │ │
	│ │ │ │ │ [1m3,543,552 [0m[1;2m(14.2 MB)[0m │
	├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤
	│ DiTBlock_4/LayerNorm_0 │ LayerNorm │ [2mbfloat16[0m[4,256,768] │ [2mbfloat16[0m[4,256,768] │ │
	├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤
	│ DiTBlock_4/Dense_1 │ Dense │ [2mbfloat16[0m[4,256,768] │ [2mbfloat16[0m[4,256,768] │ bias: [2mfloat32[0m[768] │
	│ │ │ │ │ kernel: [2mfloat32[0m[768,768] │
	│ │ │ │ │ │
	│ │ │ │ │ [1m590,592 [0m[1;2m(2.4 MB)[0m │
	├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤
	│ DiTBlock_4/Dense_2 │ Dense │ [2mbfloat16[0m[4,256,768] │ [2mbfloat16[0m[4,256,768] │ bias: [2mfloat32[0m[768] │
	│ │ │ │ │ kernel: [2mfloat32[0m[768,768] │
	│ │ │ │ │ │
	│ │ │ │ │ [1m590,592 [0m[1;2m(2.4 MB)[0m │
	├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤
	│ DiTBlock_4/Dense_3 │ Dense │ [2mbfloat16[0m[4,256,768] │ [2mbfloat16[0m[4,256,768] │ bias: [2mfloat32[0m[768] │
	│ │ │ │ │ kernel: [2mfloat32[0m[768,768] │
	│ │ │ │ │ │
	│ │ │ │ │ [1m590,592 [0m[1;2m(2.4 MB)[0m │
	├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤
	│ DiTBlock_4/Dense_4 │ Dense │ [2mfloat32[0m[4,256,768] │ [2mbfloat16[0m[4,256,768] │ bias: [2mfloat32[0m[768] │
	│ │ │ │ │ kernel: [2mfloat32[0m[768,768] │
	│ │ │ │ │ │
	│ │ │ │ │ [1m590,592 [0m[1;2m(2.4 MB)[0m │
	├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤
	│ DiTBlock_4/LayerNorm_1 │ LayerNorm │ [2mbfloat16[0m[4,256,768] │ [2mbfloat16[0m[4,256,768] │ │
	├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤
	│ DiTBlock_4/MlpBlock_0 │ MlpBlock │ [2mbfloat16[0m[4,256,768] │ [2mbfloat16[0m[4,256,768] │ │
	├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤
	│ DiTBlock_4/MlpBlock_0/Dense_0 │ Dense │ [2mbfloat16[0m[4,256,768] │ [2mbfloat16[0m[4,256,3072] │ bias: [2mfloat32[0m[3072] │
	│ │ │ │ │ kernel: [2mfloat32[0m[768,3072] │
	│ │ │ │ │ │
	│ │ │ │ │ [1m2,362,368 [0m[1;2m(9.4 MB)[0m │
	├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤
	│ DiTBlock_4/MlpBlock_0/Dropout_0 │ Dropout │ [2mbfloat16[0m[4,256,3072] │ [2mbfloat16[0m[4,256,3072] │ │
	├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤
	│ DiTBlock_4/MlpBlock_0/Dense_1 │ Dense │ [2mbfloat16[0m[4,256,3072] │ [2mbfloat16[0m[4,256,768] │ bias: [2mfloat32[0m[768] │
	│ │ │ │ │ kernel: [2mfloat32[0m[3072,768] │
	│ │ │ │ │ │
	│ │ │ │ │ [1m2,360,064 [0m[1;2m(9.4 MB)[0m │
	├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤
	│ DiTBlock_4/MlpBlock_0/Dropout_1 │ Dropout │ [2mbfloat16[0m[4,256,768] │ [2mbfloat16[0m[4,256,768] │ │
	├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤
	│ DiTBlock_5 │ DiTBlock │ - [2mbfloat16[0m[4,256,768] │ [2mbfloat16[0m[4,256,768] │ │
	│ │ │ - [2mfloat32[0m[1,768] │ │ │
	├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤
	│ DiTBlock_5/Dense_0 │ Dense │ [2mfloat32[0m[1,768] │ [2mbfloat16[0m[1,4608] │ bias: [2mfloat32[0m[4608] │
	│ │ │ │ │ kernel: [2mfloat32[0m[768,4608] │
	│ │ │ │ │ │
	│ │ │ │ │ [1m3,543,552 [0m[1;2m(14.2 MB)[0m │
	├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤
	│ DiTBlock_5/LayerNorm_0 │ LayerNorm │ [2mbfloat16[0m[4,256,768] │ [2mbfloat16[0m[4,256,768] │ │
	├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤
	│ DiTBlock_5/Dense_1 │ Dense │ [2mbfloat16[0m[4,256,768] │ [2mbfloat16[0m[4,256,768] │ bias: [2mfloat32[0m[768] │
	│ │ │ │ │ kernel: [2mfloat32[0m[768,768] │
	│ │ │ │ │ │
	│ │ │ │ │ [1m590,592 [0m[1;2m(2.4 MB)[0m │
	├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤
	│ DiTBlock_5/Dense_2 │ Dense │ [2mbfloat16[0m[4,256,768] │ [2mbfloat16[0m[4,256,768] │ bias: [2mfloat32[0m[768] │
	│ │ │ │ │ kernel: [2mfloat32[0m[768,768] │
	│ │ │ │ │ │
	│ │ │ │ │ [1m590,592 [0m[1;2m(2.4 MB)[0m │
	├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤
	│ DiTBlock_5/Dense_3 │ Dense │ [2mbfloat16[0m[4,256,768] │ [2mbfloat16[0m[4,256,768] │ bias: [2mfloat32[0m[768] │
	│ │ │ │ │ kernel: [2mfloat32[0m[768,768] │
	│ │ │ │ │ │
	│ │ │ │ │ [1m590,592 [0m[1;2m(2.4 MB)[0m │
	├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤
	│ DiTBlock_5/Dense_4 │ Dense │ [2mfloat32[0m[4,256,768] │ [2mbfloat16[0m[4,256,768] │ bias: [2mfloat32[0m[768] │
	│ │ │ │ │ kernel: [2mfloat32[0m[768,768] │
	│ │ │ │ │ │
	│ │ │ │ │ [1m590,592 [0m[1;2m(2.4 MB)[0m │
	├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤
	│ DiTBlock_5/LayerNorm_1 │ LayerNorm │ [2mbfloat16[0m[4,256,768] │ [2mbfloat16[0m[4,256,768] │ │
	├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤
	│ DiTBlock_5/MlpBlock_0 │ MlpBlock │ [2mbfloat16[0m[4,256,768] │ [2mbfloat16[0m[4,256,768] │ │
	├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤
	│ DiTBlock_5/MlpBlock_0/Dense_0 │ Dense │ [2mbfloat16[0m[4,256,768] │ [2mbfloat16[0m[4,256,3072] │ bias: [2mfloat32[0m[3072] │
	│ │ │ │ │ kernel: [2mfloat32[0m[768,3072] │
	│ │ │ │ │ │
	│ │ │ │ │ [1m2,362,368 [0m[1;2m(9.4 MB)[0m │
	├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤
	│ DiTBlock_5/MlpBlock_0/Dropout_0 │ Dropout │ [2mbfloat16[0m[4,256,3072] │ [2mbfloat16[0m[4,256,3072] │ │
	├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤
	│ DiTBlock_5/MlpBlock_0/Dense_1 │ Dense │ [2mbfloat16[0m[4,256,3072] │ [2mbfloat16[0m[4,256,768] │ bias: [2mfloat32[0m[768] │
	│ │ │ │ │ kernel: [2mfloat32[0m[3072,768] │
	│ │ │ │ │ │
	│ │ │ │ │ [1m2,360,064 [0m[1;2m(9.4 MB)[0m │
	├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤
	│ DiTBlock_5/MlpBlock_0/Dropout_1 │ Dropout │ [2mbfloat16[0m[4,256,768] │ [2mbfloat16[0m[4,256,768] │ │
	├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤
	│ DiTBlock_6 │ DiTBlock │ - [2mbfloat16[0m[4,256,768] │ [2mbfloat16[0m[4,256,768] │ │
	│ │ │ - [2mfloat32[0m[1,768] │ │ │
	├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤
	│ DiTBlock_6/Dense_0 │ Dense │ [2mfloat32[0m[1,768] │ [2mbfloat16[0m[1,4608] │ bias: [2mfloat32[0m[4608] │
	│ │ │ │ │ kernel: [2mfloat32[0m[768,4608] │
	│ │ │ │ │ │
	│ │ │ │ │ [1m3,543,552 [0m[1;2m(14.2 MB)[0m │
	├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤
	│ DiTBlock_6/LayerNorm_0 │ LayerNorm │ [2mbfloat16[0m[4,256,768] │ [2mbfloat16[0m[4,256,768] │ │
	├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤
	│ DiTBlock_6/Dense_1 │ Dense │ [2mbfloat16[0m[4,256,768] │ [2mbfloat16[0m[4,256,768] │ bias: [2mfloat32[0m[768] │
	│ │ │ │ │ kernel: [2mfloat32[0m[768,768] │
	│ │ │ │ │ │
	│ │ │ │ │ [1m590,592 [0m[1;2m(2.4 MB)[0m │
	├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤
	│ DiTBlock_6/Dense_2 │ Dense │ [2mbfloat16[0m[4,256,768] │ [2mbfloat16[0m[4,256,768] │ bias: [2mfloat32[0m[768] │
	│ │ │ │ │ kernel: [2mfloat32[0m[768,768] │
	│ │ │ │ │ │
	│ │ │ │ │ [1m590,592 [0m[1;2m(2.4 MB)[0m │
	├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤
	│ DiTBlock_6/Dense_3 │ Dense │ [2mbfloat16[0m[4,256,768] │ [2mbfloat16[0m[4,256,768] │ bias: [2mfloat32[0m[768] │
	│ │ │ │ │ kernel: [2mfloat32[0m[768,768] │
	│ │ │ │ │ │
	│ │ │ │ │ [1m590,592 [0m[1;2m(2.4 MB)[0m │
	├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤
	│ DiTBlock_6/Dense_4 │ Dense │ [2mfloat32[0m[4,256,768] │ [2mbfloat16[0m[4,256,768] │ bias: [2mfloat32[0m[768] │
	│ │ │ │ │ kernel: [2mfloat32[0m[768,768] │
	│ │ │ │ │ │
	│ │ │ │ │ [1m590,592 [0m[1;2m(2.4 MB)[0m │
	├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤
	│ DiTBlock_6/LayerNorm_1 │ LayerNorm │ [2mbfloat16[0m[4,256,768] │ [2mbfloat16[0m[4,256,768] │ │
	├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤
	│ DiTBlock_6/MlpBlock_0 │ MlpBlock │ [2mbfloat16[0m[4,256,768] │ [2mbfloat16[0m[4,256,768] │ │
	├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤
	│ DiTBlock_6/MlpBlock_0/Dense_0 │ Dense │ [2mbfloat16[0m[4,256,768] │ [2mbfloat16[0m[4,256,3072] │ bias: [2mfloat32[0m[3072] │
	│ │ │ │ │ kernel: [2mfloat32[0m[768,3072] │
	│ │ │ │ │ │
	│ │ │ │ │ [1m2,362,368 [0m[1;2m(9.4 MB)[0m │
	├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤
	│ DiTBlock_6/MlpBlock_0/Dropout_0 │ Dropout │ [2mbfloat16[0m[4,256,3072] │ [2mbfloat16[0m[4,256,3072] │ │
	├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤
	│ DiTBlock_6/MlpBlock_0/Dense_1 │ Dense │ [2mbfloat16[0m[4,256,3072] │ [2mbfloat16[0m[4,256,768] │ bias: [2mfloat32[0m[768] │
	│ │ │ │ │ kernel: [2mfloat32[0m[3072,768] │
	│ │ │ │ │ │
	│ │ │ │ │ [1m2,360,064 [0m[1;2m(9.4 MB)[0m │
	├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤
	│ DiTBlock_6/MlpBlock_0/Dropout_1 │ Dropout │ [2mbfloat16[0m[4,256,768] │ [2mbfloat16[0m[4,256,768] │ │
	├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤
	│ DiTBlock_7 │ DiTBlock │ - [2mbfloat16[0m[4,256,768] │ [2mbfloat16[0m[4,256,768] │ │
	│ │ │ - [2mfloat32[0m[1,768] │ │ │
	├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤
	│ DiTBlock_7/Dense_0 │ Dense │ [2mfloat32[0m[1,768] │ [2mbfloat16[0m[1,4608] │ bias: [2mfloat32[0m[4608] │
	│ │ │ │ │ kernel: [2mfloat32[0m[768,4608] │
	│ │ │ │ │ │
	│ │ │ │ │ [1m3,543,552 [0m[1;2m(14.2 MB)[0m │
	├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤
	│ DiTBlock_7/LayerNorm_0 │ LayerNorm │ [2mbfloat16[0m[4,256,768] │ [2mbfloat16[0m[4,256,768] │ │
	├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤
	│ DiTBlock_7/Dense_1 │ Dense │ [2mbfloat16[0m[4,256,768] │ [2mbfloat16[0m[4,256,768] │ bias: [2mfloat32[0m[768] │
	│ │ │ │ │ kernel: [2mfloat32[0m[768,768] │
	│ │ │ │ │ │
	│ │ │ │ │ [1m590,592 [0m[1;2m(2.4 MB)[0m │
	├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤
	│ DiTBlock_7/Dense_2 │ Dense │ [2mbfloat16[0m[4,256,768] │ [2mbfloat16[0m[4,256,768] │ bias: [2mfloat32[0m[768] │
	│ │ │ │ │ kernel: [2mfloat32[0m[768,768] │
	│ │ │ │ │ │
	│ │ │ │ │ [1m590,592 [0m[1;2m(2.4 MB)[0m │
	├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤
	│ DiTBlock_7/Dense_3 │ Dense │ [2mbfloat16[0m[4,256,768] │ [2mbfloat16[0m[4,256,768] │ bias: [2mfloat32[0m[768] │
	│ │ │ │ │ kernel: [2mfloat32[0m[768,768] │
	│ │ │ │ │ │
	│ │ │ │ │ [1m590,592 [0m[1;2m(2.4 MB)[0m │
	├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤
	│ DiTBlock_7/Dense_4 │ Dense │ [2mfloat32[0m[4,256,768] │ [2mbfloat16[0m[4,256,768] │ bias: [2mfloat32[0m[768] │
	│ │ │ │ │ kernel: [2mfloat32[0m[768,768] │
	│ │ │ │ │ │
	│ │ │ │ │ [1m590,592 [0m[1;2m(2.4 MB)[0m │
	├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤
	│ DiTBlock_7/LayerNorm_1 │ LayerNorm │ [2mbfloat16[0m[4,256,768] │ [2mbfloat16[0m[4,256,768] │ │
	├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤
	│ DiTBlock_7/MlpBlock_0 │ MlpBlock │ [2mbfloat16[0m[4,256,768] │ [2mbfloat16[0m[4,256,768] │ │
	├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤
	│ DiTBlock_7/MlpBlock_0/Dense_0 │ Dense │ [2mbfloat16[0m[4,256,768] │ [2mbfloat16[0m[4,256,3072] │ bias: [2mfloat32[0m[3072] │
	│ │ │ │ │ kernel: [2mfloat32[0m[768,3072] │
	│ │ │ │ │ │
	│ │ │ │ │ [1m2,362,368 [0m[1;2m(9.4 MB)[0m │
	├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤
	│ DiTBlock_7/MlpBlock_0/Dropout_0 │ Dropout │ [2mbfloat16[0m[4,256,3072] │ [2mbfloat16[0m[4,256,3072] │ │
	├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤
	│ DiTBlock_7/MlpBlock_0/Dense_1 │ Dense │ [2mbfloat16[0m[4,256,3072] │ [2mbfloat16[0m[4,256,768] │ bias: [2mfloat32[0m[768] │
	│ │ │ │ │ kernel: [2mfloat32[0m[3072,768] │
	│ │ │ │ │ │
	│ │ │ │ │ [1m2,360,064 [0m[1;2m(9.4 MB)[0m │
	├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤
	│ DiTBlock_7/MlpBlock_0/Dropout_1 │ Dropout │ [2mbfloat16[0m[4,256,768] │ [2mbfloat16[0m[4,256,768] │ │
	├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤
	│ DiTBlock_8 │ DiTBlock │ - [2mbfloat16[0m[4,256,768] │ [2mbfloat16[0m[4,256,768] │ │
	│ │ │ - [2mfloat32[0m[1,768] │ │ │
	├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤
	│ DiTBlock_8/Dense_0 │ Dense │ [2mfloat32[0m[1,768] │ [2mbfloat16[0m[1,4608] │ bias: [2mfloat32[0m[4608] │
	│ │ │ │ │ kernel: [2mfloat32[0m[768,4608] │
	│ │ │ │ │ │
	│ │ │ │ │ [1m3,543,552 [0m[1;2m(14.2 MB)[0m │
	├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤
	│ DiTBlock_8/LayerNorm_0 │ LayerNorm │ [2mbfloat16[0m[4,256,768] │ [2mbfloat16[0m[4,256,768] │ │
	├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤
	│ DiTBlock_8/Dense_1 │ Dense │ [2mbfloat16[0m[4,256,768] │ [2mbfloat16[0m[4,256,768] │ bias: [2mfloat32[0m[768] │
	│ │ │ │ │ kernel: [2mfloat32[0m[768,768] │
	│ │ │ │ │ │
	│ │ │ │ │ [1m590,592 [0m[1;2m(2.4 MB)[0m │
	├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤
	│ DiTBlock_8/Dense_2 │ Dense │ [2mbfloat16[0m[4,256,768] │ [2mbfloat16[0m[4,256,768] │ bias: [2mfloat32[0m[768] │
	│ │ │ │ │ kernel: [2mfloat32[0m[768,768] │
	│ │ │ │ │ │
	│ │ │ │ │ [1m590,592 [0m[1;2m(2.4 MB)[0m │
	├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤
	│ DiTBlock_8/Dense_3 │ Dense │ [2mbfloat16[0m[4,256,768] │ [2mbfloat16[0m[4,256,768] │ bias: [2mfloat32[0m[768] │
	│ │ │ │ │ kernel: [2mfloat32[0m[768,768] │
	│ │ │ │ │ │
	│ │ │ │ │ [1m590,592 [0m[1;2m(2.4 MB)[0m │
	├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤
	│ DiTBlock_8/Dense_4 │ Dense │ [2mfloat32[0m[4,256,768] │ [2mbfloat16[0m[4,256,768] │ bias: [2mfloat32[0m[768] │
	│ │ │ │ │ kernel: [2mfloat32[0m[768,768] │
	│ │ │ │ │ │
	│ │ │ │ │ [1m590,592 [0m[1;2m(2.4 MB)[0m │
	├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤
	│ DiTBlock_8/LayerNorm_1 │ LayerNorm │ [2mbfloat16[0m[4,256,768] │ [2mbfloat16[0m[4,256,768] │ │
	├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤
	│ DiTBlock_8/MlpBlock_0 │ MlpBlock │ [2mbfloat16[0m[4,256,768] │ [2mbfloat16[0m[4,256,768] │ │
	├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤
	│ DiTBlock_8/MlpBlock_0/Dense_0 │ Dense │ [2mbfloat16[0m[4,256,768] │ [2mbfloat16[0m[4,256,3072] │ bias: [2mfloat32[0m[3072] │
	│ │ │ │ │ kernel: [2mfloat32[0m[768,3072] │
	│ │ │ │ │ │
	│ │ │ │ │ [1m2,362,368 [0m[1;2m(9.4 MB)[0m │
	├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤
	│ DiTBlock_8/MlpBlock_0/Dropout_0 │ Dropout │ [2mbfloat16[0m[4,256,3072] │ [2mbfloat16[0m[4,256,3072] │ │
	├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤
	│ DiTBlock_8/MlpBlock_0/Dense_1 │ Dense │ [2mbfloat16[0m[4,256,3072] │ [2mbfloat16[0m[4,256,768] │ bias: [2mfloat32[0m[768] │
	│ │ │ │ │ kernel: [2mfloat32[0m[3072,768] │
	│ │ │ │ │ │
	│ │ │ │ │ [1m2,360,064 [0m[1;2m(9.4 MB)[0m │
	├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤
	│ DiTBlock_8/MlpBlock_0/Dropout_1 │ Dropout │ [2mbfloat16[0m[4,256,768] │ [2mbfloat16[0m[4,256,768] │ │
	├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤
	│ DiTBlock_9 │ DiTBlock │ - [2mbfloat16[0m[4,256,768] │ [2mbfloat16[0m[4,256,768] │ │
	│ │ │ - [2mfloat32[0m[1,768] │ │ │
	├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤
	│ DiTBlock_9/Dense_0 │ Dense │ [2mfloat32[0m[1,768] │ [2mbfloat16[0m[1,4608] │ bias: [2mfloat32[0m[4608] │
	│ │ │ │ │ kernel: [2mfloat32[0m[768,4608] │
	│ │ │ │ │ │
	│ │ │ │ │ [1m3,543,552 [0m[1;2m(14.2 MB)[0m │
	├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤
	│ DiTBlock_9/LayerNorm_0 │ LayerNorm │ [2mbfloat16[0m[4,256,768] │ [2mbfloat16[0m[4,256,768] │ │
	├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤
	│ DiTBlock_9/Dense_1 │ Dense │ [2mbfloat16[0m[4,256,768] │ [2mbfloat16[0m[4,256,768] │ bias: [2mfloat32[0m[768] │
	│ │ │ │ │ kernel: [2mfloat32[0m[768,768] │
	│ │ │ │ │ │
	│ │ │ │ │ [1m590,592 [0m[1;2m(2.4 MB)[0m │
	├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤
	│ DiTBlock_9/Dense_2 │ Dense │ [2mbfloat16[0m[4,256,768] │ [2mbfloat16[0m[4,256,768] │ bias: [2mfloat32[0m[768] │
	│ │ │ │ │ kernel: [2mfloat32[0m[768,768] │
	│ │ │ │ │ │
	│ │ │ │ │ [1m590,592 [0m[1;2m(2.4 MB)[0m │
	├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤
	│ DiTBlock_9/Dense_3 │ Dense │ [2mbfloat16[0m[4,256,768] │ [2mbfloat16[0m[4,256,768] │ bias: [2mfloat32[0m[768] │
	│ │ │ │ │ kernel: [2mfloat32[0m[768,768] │
	│ │ │ │ │ │
	│ │ │ │ │ [1m590,592 [0m[1;2m(2.4 MB)[0m │
	├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤
	│ DiTBlock_9/Dense_4 │ Dense │ [2mfloat32[0m[4,256,768] │ [2mbfloat16[0m[4,256,768] │ bias: [2mfloat32[0m[768] │
	│ │ │ │ │ kernel: [2mfloat32[0m[768,768] │
	│ │ │ │ │ │
	│ │ │ │ │ [1m590,592 [0m[1;2m(2.4 MB)[0m │
	├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤
	│ DiTBlock_9/LayerNorm_1 │ LayerNorm │ [2mbfloat16[0m[4,256,768] │ [2mbfloat16[0m[4,256,768] │ │
	├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤
	│ DiTBlock_9/MlpBlock_0 │ MlpBlock │ [2mbfloat16[0m[4,256,768] │ [2mbfloat16[0m[4,256,768] │ │
	├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤
	│ DiTBlock_9/MlpBlock_0/Dense_0 │ Dense │ [2mbfloat16[0m[4,256,768] │ [2mbfloat16[0m[4,256,3072] │ bias: [2mfloat32[0m[3072] │
	│ │ │ │ │ kernel: [2mfloat32[0m[768,3072] │
	│ │ │ │ │ │
	│ │ │ │ │ [1m2,362,368 [0m[1;2m(9.4 MB)[0m │
	├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤
	│ DiTBlock_9/MlpBlock_0/Dropout_0 │ Dropout │ [2mbfloat16[0m[4,256,3072] │ [2mbfloat16[0m[4,256,3072] │ │
	├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤
	│ DiTBlock_9/MlpBlock_0/Dense_1 │ Dense │ [2mbfloat16[0m[4,256,3072] │ [2mbfloat16[0m[4,256,768] │ bias: [2mfloat32[0m[768] │
	│ │ │ │ │ kernel: [2mfloat32[0m[3072,768] │
	│ │ │ │ │ │
	│ │ │ │ │ [1m2,360,064 [0m[1;2m(9.4 MB)[0m │
	├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤
	│ DiTBlock_9/MlpBlock_0/Dropout_1 │ Dropout │ [2mbfloat16[0m[4,256,768] │ [2mbfloat16[0m[4,256,768] │ │
	├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤
	│ DiTBlock_10 │ DiTBlock │ - [2mbfloat16[0m[4,256,768] │ [2mbfloat16[0m[4,256,768] │ │
	│ │ │ - [2mfloat32[0m[1,768] │ │ │
	├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤
	│ DiTBlock_10/Dense_0 │ Dense │ [2mfloat32[0m[1,768] │ [2mbfloat16[0m[1,4608] │ bias: [2mfloat32[0m[4608] │
	│ │ │ │ │ kernel: [2mfloat32[0m[768,4608] │
	│ │ │ │ │ │
	│ │ │ │ │ [1m3,543,552 [0m[1;2m(14.2 MB)[0m │
	├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤
	│ DiTBlock_10/LayerNorm_0 │ LayerNorm │ [2mbfloat16[0m[4,256,768] │ [2mbfloat16[0m[4,256,768] │ │
	├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤
	│ DiTBlock_10/Dense_1 │ Dense │ [2mbfloat16[0m[4,256,768] │ [2mbfloat16[0m[4,256,768] │ bias: [2mfloat32[0m[768] │
	│ │ │ │ │ kernel: [2mfloat32[0m[768,768] │
	│ │ │ │ │ │
	│ │ │ │ │ [1m590,592 [0m[1;2m(2.4 MB)[0m │
	├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤
	│ DiTBlock_10/Dense_2 │ Dense │ [2mbfloat16[0m[4,256,768] │ [2mbfloat16[0m[4,256,768] │ bias: [2mfloat32[0m[768] │
	│ │ │ │ │ kernel: [2mfloat32[0m[768,768] │
	│ │ │ │ │ │
	│ │ │ │ │ [1m590,592 [0m[1;2m(2.4 MB)[0m │
	├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤
	│ DiTBlock_10/Dense_3 │ Dense │ [2mbfloat16[0m[4,256,768] │ [2mbfloat16[0m[4,256,768] │ bias: [2mfloat32[0m[768] │
	│ │ │ │ │ kernel: [2mfloat32[0m[768,768] │
	│ │ │ │ │ │
	│ │ │ │ │ [1m590,592 [0m[1;2m(2.4 MB)[0m │
	├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤
	│ DiTBlock_10/Dense_4 │ Dense │ [2mfloat32[0m[4,256,768] │ [2mbfloat16[0m[4,256,768] │ bias: [2mfloat32[0m[768] │
	│ │ │ │ │ kernel: [2mfloat32[0m[768,768] │
	│ │ │ │ │ │
	│ │ │ │ │ [1m590,592 [0m[1;2m(2.4 MB)[0m │
	├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤
	│ DiTBlock_10/LayerNorm_1 │ LayerNorm │ [2mbfloat16[0m[4,256,768] │ [2mbfloat16[0m[4,256,768] │ │
	├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤
	│ DiTBlock_10/MlpBlock_0 │ MlpBlock │ [2mbfloat16[0m[4,256,768] │ [2mbfloat16[0m[4,256,768] │ │
	├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤
	│ DiTBlock_10/MlpBlock_0/Dense_0 │ Dense │ [2mbfloat16[0m[4,256,768] │ [2mbfloat16[0m[4,256,3072] │ bias: [2mfloat32[0m[3072] │
	│ │ │ │ │ kernel: [2mfloat32[0m[768,3072] │
	│ │ │ │ │ │
	│ │ │ │ │ [1m2,362,368 [0m[1;2m(9.4 MB)[0m │
	├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤
	│ DiTBlock_10/MlpBlock_0/Dropout_0 │ Dropout │ [2mbfloat16[0m[4,256,3072] │ [2mbfloat16[0m[4,256,3072] │ │
	├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤
	│ DiTBlock_10/MlpBlock_0/Dense_1 │ Dense │ [2mbfloat16[0m[4,256,3072] │ [2mbfloat16[0m[4,256,768] │ bias: [2mfloat32[0m[768] │
	│ │ │ │ │ kernel: [2mfloat32[0m[3072,768] │
	│ │ │ │ │ │
	│ │ │ │ │ [1m2,360,064 [0m[1;2m(9.4 MB)[0m │
	├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤
	│ DiTBlock_10/MlpBlock_0/Dropout_1 │ Dropout │ [2mbfloat16[0m[4,256,768] │ [2mbfloat16[0m[4,256,768] │ │
	├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤
	│ DiTBlock_11 │ DiTBlock │ - [2mbfloat16[0m[4,256,768] │ [2mbfloat16[0m[4,256,768] │ │
	│ │ │ - [2mfloat32[0m[1,768] │ │ │
	├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤
	│ DiTBlock_11/Dense_0 │ Dense │ [2mfloat32[0m[1,768] │ [2mbfloat16[0m[1,4608] │ bias: [2mfloat32[0m[4608] │
	│ │ │ │ │ kernel: [2mfloat32[0m[768,4608] │
	│ │ │ │ │ │
	│ │ │ │ │ [1m3,543,552 [0m[1;2m(14.2 MB)[0m │
	├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤
	│ DiTBlock_11/LayerNorm_0 │ LayerNorm │ [2mbfloat16[0m[4,256,768] │ [2mbfloat16[0m[4,256,768] │ │
	├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤
	│ DiTBlock_11/Dense_1 │ Dense │ [2mbfloat16[0m[4,256,768] │ [2mbfloat16[0m[4,256,768] │ bias: [2mfloat32[0m[768] │
	│ │ │ │ │ kernel: [2mfloat32[0m[768,768] │
	│ │ │ │ │ │
	│ │ │ │ │ [1m590,592 [0m[1;2m(2.4 MB)[0m │
	├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤
	│ DiTBlock_11/Dense_2 │ Dense │ [2mbfloat16[0m[4,256,768] │ [2mbfloat16[0m[4,256,768] │ bias: [2mfloat32[0m[768] │
	│ │ │ │ │ kernel: [2mfloat32[0m[768,768] │
	│ │ │ │ │ │
	│ │ │ │ │ [1m590,592 [0m[1;2m(2.4 MB)[0m │
	├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤
	│ DiTBlock_11/Dense_3 │ Dense │ [2mbfloat16[0m[4,256,768] │ [2mbfloat16[0m[4,256,768] │ bias: [2mfloat32[0m[768] │
	│ │ │ │ │ kernel: [2mfloat32[0m[768,768] │
	│ │ │ │ │ │
	│ │ │ │ │ [1m590,592 [0m[1;2m(2.4 MB)[0m │
	├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤
	│ DiTBlock_11/Dense_4 │ Dense │ [2mfloat32[0m[4,256,768] │ [2mbfloat16[0m[4,256,768] │ bias: [2mfloat32[0m[768] │
	│ │ │ │ │ kernel: [2mfloat32[0m[768,768] │
	│ │ │ │ │ │
	│ │ │ │ │ [1m590,592 [0m[1;2m(2.4 MB)[0m │
	├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤
	│ DiTBlock_11/LayerNorm_1 │ LayerNorm │ [2mbfloat16[0m[4,256,768] │ [2mbfloat16[0m[4,256,768] │ │
	├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤
	│ DiTBlock_11/MlpBlock_0 │ MlpBlock │ [2mbfloat16[0m[4,256,768] │ [2mbfloat16[0m[4,256,768] │ │
	├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤
	│ DiTBlock_11/MlpBlock_0/Dense_0 │ Dense │ [2mbfloat16[0m[4,256,768] │ [2mbfloat16[0m[4,256,3072] │ bias: [2mfloat32[0m[3072] │
	│ │ │ │ │ kernel: [2mfloat32[0m[768,3072] │
	│ │ │ │ │ │
	│ │ │ │ │ [1m2,362,368 [0m[1;2m(9.4 MB)[0m │
	├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤
	│ DiTBlock_11/MlpBlock_0/Dropout_0 │ Dropout │ [2mbfloat16[0m[4,256,3072] │ [2mbfloat16[0m[4,256,3072] │ │
	├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤
	│ DiTBlock_11/MlpBlock_0/Dense_1 │ Dense │ [2mbfloat16[0m[4,256,3072] │ [2mbfloat16[0m[4,256,768] │ bias: [2mfloat32[0m[768] │
	│ │ │ │ │ kernel: [2mfloat32[0m[3072,768] │
	│ │ │ │ │ │
	│ │ │ │ │ [1m2,360,064 [0m[1;2m(9.4 MB)[0m │
	├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤
	│ DiTBlock_11/MlpBlock_0/Dropout_1 │ Dropout │ [2mbfloat16[0m[4,256,768] │ [2mbfloat16[0m[4,256,768] │ │
	├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤
	│ FinalLayer_0 │ FinalLayer │ - [2mbfloat16[0m[4,256,768] │ [2mbfloat16[0m[4,256,16] │ │
	│ │ │ - [2mfloat32[0m[1,768] │ │ │
	├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤
	│ FinalLayer_0/Dense_0 │ Dense │ [2mfloat32[0m[1,768] │ [2mbfloat16[0m[1,1536] │ bias: [2mfloat32[0m[1536] │
	│ │ │ │ │ kernel: [2mfloat32[0m[768,1536] │
	│ │ │ │ │ │
	│ │ │ │ │ [1m1,181,184 [0m[1;2m(4.7 MB)[0m │
	├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤
	│ FinalLayer_0/LayerNorm_0 │ LayerNorm │ [2mbfloat16[0m[4,256,768] │ [2mbfloat16[0m[4,256,768] │ │
	├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤
	│ FinalLayer_0/Dense_1 │ Dense │ [2mbfloat16[0m[4,256,768] │ [2mbfloat16[0m[4,256,16] │ bias: [2mfloat32[0m[16] │
	│ │ │ │ │ kernel: [2mfloat32[0m[768,16] │
	│ │ │ │ │ │
	│ │ │ │ │ [1m12,304 [0m[1;2m(49.2 KB)[0m │
	├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤
	│ Embed_0 │ Embed │ [2mint32[0m[1] │ [2mfloat32[0m[1,1] │ embedding: [2mfloat32[0m[256,1] │
	│ │ │ │ │ │
	│ │ │ │ │ [1m256 [0m[1;2m(1.0 KB)[0m │
	├──────────────────────────────────┼──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤
	│[1m [0m[1m [0m[1m [0m│[1m [0m[1m [0m[1m [0m│[1m [0m[1m [0m[1m [0m│[1m [0m[1m Total[0m[1m [0m│[1m [0m[1m131,091,728 [0m[1;2m(524.4 MB)[0m[1m [0m[1m [0m│
	└──────────────────────────────────┴──────────────────┴───────────────────────┴───────────────────────┴──────────────────────────────┘
	[1m [0m
	[1m Total Parameters: 131,091,728 [0m[1;2m(524.4 MB)[0m[1m [0m


	DiT: Input of shape (4, 32, 32, 4) dtype float32
	DiT: After patch embed, shape is (4, 256, 768) dtype bfloat16
	DiT: Patch Embed of shape (4, 256, 768) dtype bfloat16
	DiT: Conditioning of shape (1, 768) dtype float32
	Loaded checkpoint from 109474 seconds ago.

	parameter shapes:
	('PatchEmbed_0', 'Conv_0', 'kernel'): (2, 2, 4, 768)
	('PatchEmbed_0', 'Conv_0', 'bias'): (768,)
	('TimestepEmbedder_0', 'Dense_0', 'kernel'): (256, 768)
	('TimestepEmbedder_0', 'Dense_0', 'bias'): (768,)
	('TimestepEmbedder_0', 'Dense_1', 'kernel'): (768, 768)
	('TimestepEmbedder_0', 'Dense_1', 'bias'): (768,)
	('TimestepEmbedder_1', 'Dense_0', 'kernel'): (256, 768)
	('TimestepEmbedder_1', 'Dense_0', 'bias'): (768,)
	('TimestepEmbedder_1', 'Dense_1', 'kernel'): (768, 768)
	('TimestepEmbedder_1', 'Dense_1', 'bias'): (768,)
	('LabelEmbedder_0', 'Embed_0', 'embedding'): (1001, 768)
	('DiTBlock_0', 'Dense_0', 'kernel'): (768, 4608)
	('DiTBlock_0', 'Dense_0', 'bias'): (4608,)
	('DiTBlock_0', 'Dense_1', 'kernel'): (768, 768)
	('DiTBlock_0', 'Dense_1', 'bias'): (768,)
	('DiTBlock_0', 'Dense_2', 'kernel'): (768, 768)
	('DiTBlock_0', 'Dense_2', 'bias'): (768,)
	('DiTBlock_0', 'Dense_3', 'kernel'): (768, 768)
	('DiTBlock_0', 'Dense_3', 'bias'): (768,)
	('DiTBlock_0', 'Dense_4', 'kernel'): (768, 768)
	('DiTBlock_0', 'Dense_4', 'bias'): (768,)
	('DiTBlock_0', 'MlpBlock_0', 'Dense_0', 'kernel'): (768, 3072)
	('DiTBlock_0', 'MlpBlock_0', 'Dense_0', 'bias'): (3072,)
	('DiTBlock_0', 'MlpBlock_0', 'Dense_1', 'kernel'): (3072, 768)
	('DiTBlock_0', 'MlpBlock_0', 'Dense_1', 'bias'): (768,)
	('DiTBlock_1', 'Dense_0', 'kernel'): (768, 4608)
	('DiTBlock_1', 'Dense_0', 'bias'): (4608,)
	('DiTBlock_1', 'Dense_1', 'kernel'): (768, 768)
	('DiTBlock_1', 'Dense_1', 'bias'): (768,)
	('DiTBlock_1', 'Dense_2', 'kernel'): (768, 768)
	('DiTBlock_1', 'Dense_2', 'bias'): (768,)
	('DiTBlock_1', 'Dense_3', 'kernel'): (768, 768)
	('DiTBlock_1', 'Dense_3', 'bias'): (768,)
	('DiTBlock_1', 'Dense_4', 'kernel'): (768, 768)
	('DiTBlock_1', 'Dense_4', 'bias'): (768,)
	('DiTBlock_1', 'MlpBlock_0', 'Dense_0', 'kernel'): (768, 3072)
	('DiTBlock_1', 'MlpBlock_0', 'Dense_0', 'bias'): (3072,)
	('DiTBlock_1', 'MlpBlock_0', 'Dense_1', 'kernel'): (3072, 768)
	('DiTBlock_1', 'MlpBlock_0', 'Dense_1', 'bias'): (768,)
	('DiTBlock_2', 'Dense_0', 'kernel'): (768, 4608)
	('DiTBlock_2', 'Dense_0', 'bias'): (4608,)
	('DiTBlock_2', 'Dense_1', 'kernel'): (768, 768)
	('DiTBlock_2', 'Dense_1', 'bias'): (768,)
	('DiTBlock_2', 'Dense_2', 'kernel'): (768, 768)
	('DiTBlock_2', 'Dense_2', 'bias'): (768,)
	('DiTBlock_2', 'Dense_3', 'kernel'): (768, 768)
	('DiTBlock_2', 'Dense_3', 'bias'): (768,)
	('DiTBlock_2', 'Dense_4', 'kernel'): (768, 768)
	('DiTBlock_2', 'Dense_4', 'bias'): (768,)
	('DiTBlock_2', 'MlpBlock_0', 'Dense_0', 'kernel'): (768, 3072)
	('DiTBlock_2', 'MlpBlock_0', 'Dense_0', 'bias'): (3072,)
	('DiTBlock_2', 'MlpBlock_0', 'Dense_1', 'kernel'): (3072, 768)
	('DiTBlock_2', 'MlpBlock_0', 'Dense_1', 'bias'): (768,)
	('DiTBlock_3', 'Dense_0', 'kernel'): (768, 4608)
	('DiTBlock_3', 'Dense_0', 'bias'): (4608,)
	('DiTBlock_3', 'Dense_1', 'kernel'): (768, 768)
	('DiTBlock_3', 'Dense_1', 'bias'): (768,)
	('DiTBlock_3', 'Dense_2', 'kernel'): (768, 768)
	('DiTBlock_3', 'Dense_2', 'bias'): (768,)
	('DiTBlock_3', 'Dense_3', 'kernel'): (768, 768)
	('DiTBlock_3', 'Dense_3', 'bias'): (768,)
	('DiTBlock_3', 'Dense_4', 'kernel'): (768, 768)
	('DiTBlock_3', 'Dense_4', 'bias'): (768,)
	('DiTBlock_3', 'MlpBlock_0', 'Dense_0', 'kernel'): (768, 3072)
	('DiTBlock_3', 'MlpBlock_0', 'Dense_0', 'bias'): (3072,)
	('DiTBlock_3', 'MlpBlock_0', 'Dense_1', 'kernel'): (3072, 768)
	('DiTBlock_3', 'MlpBlock_0', 'Dense_1', 'bias'): (768,)
	('DiTBlock_4', 'Dense_0', 'kernel'): (768, 4608)
	('DiTBlock_4', 'Dense_0', 'bias'): (4608,)
	('DiTBlock_4', 'Dense_1', 'kernel'): (768, 768)
	('DiTBlock_4', 'Dense_1', 'bias'): (768,)
	('DiTBlock_4', 'Dense_2', 'kernel'): (768, 768)
	('DiTBlock_4', 'Dense_2', 'bias'): (768,)
	('DiTBlock_4', 'Dense_3', 'kernel'): (768, 768)
	('DiTBlock_4', 'Dense_3', 'bias'): (768,)
	('DiTBlock_4', 'Dense_4', 'kernel'): (768, 768)
	('DiTBlock_4', 'Dense_4', 'bias'): (768,)
	('DiTBlock_4', 'MlpBlock_0', 'Dense_0', 'kernel'): (768, 3072)
	('DiTBlock_4', 'MlpBlock_0', 'Dense_0', 'bias'): (3072,)
	('DiTBlock_4', 'MlpBlock_0', 'Dense_1', 'kernel'): (3072, 768)
	('DiTBlock_4', 'MlpBlock_0', 'Dense_1', 'bias'): (768,)
	('DiTBlock_5', 'Dense_0', 'kernel'): (768, 4608)
	('DiTBlock_5', 'Dense_0', 'bias'): (4608,)
	('DiTBlock_5', 'Dense_1', 'kernel'): (768, 768)
	('DiTBlock_5', 'Dense_1', 'bias'): (768,)
	('DiTBlock_5', 'Dense_2', 'kernel'): (768, 768)
	('DiTBlock_5', 'Dense_2', 'bias'): (768,)
	('DiTBlock_5', 'Dense_3', 'kernel'): (768, 768)
	('DiTBlock_5', 'Dense_3', 'bias'): (768,)
	('DiTBlock_5', 'Dense_4', 'kernel'): (768, 768)
	('DiTBlock_5', 'Dense_4', 'bias'): (768,)
	('DiTBlock_5', 'MlpBlock_0', 'Dense_0', 'kernel'): (768, 3072)
	('DiTBlock_5', 'MlpBlock_0', 'Dense_0', 'bias'): (3072,)
	('DiTBlock_5', 'MlpBlock_0', 'Dense_1', 'kernel'): (3072, 768)
	('DiTBlock_5', 'MlpBlock_0', 'Dense_1', 'bias'): (768,)
	('DiTBlock_6', 'Dense_0', 'kernel'): (768, 4608)
	('DiTBlock_6', 'Dense_0', 'bias'): (4608,)
	('DiTBlock_6', 'Dense_1', 'kernel'): (768, 768)
	('DiTBlock_6', 'Dense_1', 'bias'): (768,)
	('DiTBlock_6', 'Dense_2', 'kernel'): (768, 768)
	('DiTBlock_6', 'Dense_2', 'bias'): (768,)
	('DiTBlock_6', 'Dense_3', 'kernel'): (768, 768)
	('DiTBlock_6', 'Dense_3', 'bias'): (768,)
	('DiTBlock_6', 'Dense_4', 'kernel'): (768, 768)
	('DiTBlock_6', 'Dense_4', 'bias'): (768,)
	('DiTBlock_6', 'MlpBlock_0', 'Dense_0', 'kernel'): (768, 3072)
	('DiTBlock_6', 'MlpBlock_0', 'Dense_0', 'bias'): (3072,)
	('DiTBlock_6', 'MlpBlock_0', 'Dense_1', 'kernel'): (3072, 768)
	('DiTBlock_6', 'MlpBlock_0', 'Dense_1', 'bias'): (768,)
	('DiTBlock_7', 'Dense_0', 'kernel'): (768, 4608)
	('DiTBlock_7', 'Dense_0', 'bias'): (4608,)
	('DiTBlock_7', 'Dense_1', 'kernel'): (768, 768)
	('DiTBlock_7', 'Dense_1', 'bias'): (768,)
	('DiTBlock_7', 'Dense_2', 'kernel'): (768, 768)
	('DiTBlock_7', 'Dense_2', 'bias'): (768,)
	('DiTBlock_7', 'Dense_3', 'kernel'): (768, 768)
	('DiTBlock_7', 'Dense_3', 'bias'): (768,)
	('DiTBlock_7', 'Dense_4', 'kernel'): (768, 768)
	('DiTBlock_7', 'Dense_4', 'bias'): (768,)
	('DiTBlock_7', 'MlpBlock_0', 'Dense_0', 'kernel'): (768, 3072)
	('DiTBlock_7', 'MlpBlock_0', 'Dense_0', 'bias'): (3072,)
	('DiTBlock_7', 'MlpBlock_0', 'Dense_1', 'kernel'): (3072, 768)
	('DiTBlock_7', 'MlpBlock_0', 'Dense_1', 'bias'): (768,)
	('DiTBlock_8', 'Dense_0', 'kernel'): (768, 4608)
	('DiTBlock_8', 'Dense_0', 'bias'): (4608,)
	('DiTBlock_8', 'Dense_1', 'kernel'): (768, 768)
	('DiTBlock_8', 'Dense_1', 'bias'): (768,)
	('DiTBlock_8', 'Dense_2', 'kernel'): (768, 768)
	('DiTBlock_8', 'Dense_2', 'bias'): (768,)
	('DiTBlock_8', 'Dense_3', 'kernel'): (768, 768)
	('DiTBlock_8', 'Dense_3', 'bias'): (768,)
	('DiTBlock_8', 'Dense_4', 'kernel'): (768, 768)
	('DiTBlock_8', 'Dense_4', 'bias'): (768,)
	('DiTBlock_8', 'MlpBlock_0', 'Dense_0', 'kernel'): (768, 3072)
	('DiTBlock_8', 'MlpBlock_0', 'Dense_0', 'bias'): (3072,)
	('DiTBlock_8', 'MlpBlock_0', 'Dense_1', 'kernel'): (3072, 768)
	('DiTBlock_8', 'MlpBlock_0', 'Dense_1', 'bias'): (768,)
	('DiTBlock_9', 'Dense_0', 'kernel'): (768, 4608)
	('DiTBlock_9', 'Dense_0', 'bias'): (4608,)
	('DiTBlock_9', 'Dense_1', 'kernel'): (768, 768)
	('DiTBlock_9', 'Dense_1', 'bias'): (768,)
	('DiTBlock_9', 'Dense_2', 'kernel'): (768, 768)
	('DiTBlock_9', 'Dense_2', 'bias'): (768,)
	('DiTBlock_9', 'Dense_3', 'kernel'): (768, 768)
	('DiTBlock_9', 'Dense_3', 'bias'): (768,)
	('DiTBlock_9', 'Dense_4', 'kernel'): (768, 768)
	('DiTBlock_9', 'Dense_4', 'bias'): (768,)
	('DiTBlock_9', 'MlpBlock_0', 'Dense_0', 'kernel'): (768, 3072)
	('DiTBlock_9', 'MlpBlock_0', 'Dense_0', 'bias'): (3072,)
	('DiTBlock_9', 'MlpBlock_0', 'Dense_1', 'kernel'): (3072, 768)
	('DiTBlock_9', 'MlpBlock_0', 'Dense_1', 'bias'): (768,)
	('DiTBlock_10', 'Dense_0', 'kernel'): (768, 4608)
	('DiTBlock_10', 'Dense_0', 'bias'): (4608,)
	('DiTBlock_10', 'Dense_1', 'kernel'): (768, 768)
	('DiTBlock_10', 'Dense_1', 'bias'): (768,)
	('DiTBlock_10', 'Dense_2', 'kernel'): (768, 768)
	('DiTBlock_10', 'Dense_2', 'bias'): (768,)
	('DiTBlock_10', 'Dense_3', 'kernel'): (768, 768)
	('DiTBlock_10', 'Dense_3', 'bias'): (768,)
	('DiTBlock_10', 'Dense_4', 'kernel'): (768, 768)
	('DiTBlock_10', 'Dense_4', 'bias'): (768,)
	('DiTBlock_10', 'MlpBlock_0', 'Dense_0', 'kernel'): (768, 3072)
	('DiTBlock_10', 'MlpBlock_0', 'Dense_0', 'bias'): (3072,)
	('DiTBlock_10', 'MlpBlock_0', 'Dense_1', 'kernel'): (3072, 768)
	('DiTBlock_10', 'MlpBlock_0', 'Dense_1', 'bias'): (768,)
	('DiTBlock_11', 'Dense_0', 'kernel'): (768, 4608)
	('DiTBlock_11', 'Dense_0', 'bias'): (4608,)
	('DiTBlock_11', 'Dense_1', 'kernel'): (768, 768)
	('DiTBlock_11', 'Dense_1', 'bias'): (768,)
	('DiTBlock_11', 'Dense_2', 'kernel'): (768, 768)
	('DiTBlock_11', 'Dense_2', 'bias'): (768,)
	('DiTBlock_11', 'Dense_3', 'kernel'): (768, 768)
	('DiTBlock_11', 'Dense_3', 'bias'): (768,)
	('DiTBlock_11', 'Dense_4', 'kernel'): (768, 768)
	('DiTBlock_11', 'Dense_4', 'bias'): (768,)
	('DiTBlock_11', 'MlpBlock_0', 'Dense_0', 'kernel'): (768, 3072)
	('DiTBlock_11', 'MlpBlock_0', 'Dense_0', 'bias'): (3072,)
	('DiTBlock_11', 'MlpBlock_0', 'Dense_1', 'kernel'): (3072, 768)
	('DiTBlock_11', 'MlpBlock_0', 'Dense_1', 'bias'): (768,)
	('FinalLayer_0', 'Dense_0', 'kernel'): (768, 1536)
	('FinalLayer_0', 'Dense_0', 'bias'): (1536,)
	('FinalLayer_0', 'Dense_1', 'kernel'): (768, 16)
	('FinalLayer_0', 'Dense_1', 'bias'): (16,)
	('Embed_0', 'embedding'): (256, 1)
	regular

	parameter shapes:
	('DiTBlock_0', 'Dense_0', 'bias'): (1, 4608)
	('DiTBlock_0', 'Dense_0', 'kernel'): (1, 768, 4608)
	('DiTBlock_0', 'Dense_1', 'bias'): (1, 768)
	('DiTBlock_0', 'Dense_1', 'kernel'): (1, 768, 768)
	('DiTBlock_0', 'Dense_2', 'bias'): (1, 768)
	('DiTBlock_0', 'Dense_2', 'kernel'): (1, 768, 768)
	('DiTBlock_0', 'Dense_3', 'bias'): (1, 768)
	('DiTBlock_0', 'Dense_3', 'kernel'): (1, 768, 768)
	('DiTBlock_0', 'Dense_4', 'bias'): (1, 768)
	('DiTBlock_0', 'Dense_4', 'kernel'): (1, 768, 768)
	('DiTBlock_0', 'MlpBlock_0', 'Dense_0', 'bias'): (1, 3072)
	('DiTBlock_0', 'MlpBlock_0', 'Dense_0', 'kernel'): (1, 768, 3072)
	('DiTBlock_0', 'MlpBlock_0', 'Dense_1', 'bias'): (1, 768)
	('DiTBlock_0', 'MlpBlock_0', 'Dense_1', 'kernel'): (1, 3072, 768)
	('DiTBlock_1', 'Dense_0', 'bias'): (1, 4608)
	('DiTBlock_1', 'Dense_0', 'kernel'): (1, 768, 4608)
	('DiTBlock_1', 'Dense_1', 'bias'): (1, 768)
	('DiTBlock_1', 'Dense_1', 'kernel'): (1, 768, 768)
	('DiTBlock_1', 'Dense_2', 'bias'): (1, 768)
	('DiTBlock_1', 'Dense_2', 'kernel'): (1, 768, 768)
	('DiTBlock_1', 'Dense_3', 'bias'): (1, 768)
	('DiTBlock_1', 'Dense_3', 'kernel'): (1, 768, 768)
	('DiTBlock_1', 'Dense_4', 'bias'): (1, 768)
	('DiTBlock_1', 'Dense_4', 'kernel'): (1, 768, 768)
	('DiTBlock_1', 'MlpBlock_0', 'Dense_0', 'bias'): (1, 3072)
	('DiTBlock_1', 'MlpBlock_0', 'Dense_0', 'kernel'): (1, 768, 3072)
	('DiTBlock_1', 'MlpBlock_0', 'Dense_1', 'bias'): (1, 768)
	('DiTBlock_1', 'MlpBlock_0', 'Dense_1', 'kernel'): (1, 3072, 768)
	('DiTBlock_10', 'Dense_0', 'bias'): (1, 4608)
	('DiTBlock_10', 'Dense_0', 'kernel'): (1, 768, 4608)
	('DiTBlock_10', 'Dense_1', 'bias'): (1, 768)
	('DiTBlock_10', 'Dense_1', 'kernel'): (1, 768, 768)
	('DiTBlock_10', 'Dense_2', 'bias'): (1, 768)
	('DiTBlock_10', 'Dense_2', 'kernel'): (1, 768, 768)
	('DiTBlock_10', 'Dense_3', 'bias'): (1, 768)
	('DiTBlock_10', 'Dense_3', 'kernel'): (1, 768, 768)
	('DiTBlock_10', 'Dense_4', 'bias'): (1, 768)
	('DiTBlock_10', 'Dense_4', 'kernel'): (1, 768, 768)
	('DiTBlock_10', 'MlpBlock_0', 'Dense_0', 'bias'): (1, 3072)
	('DiTBlock_10', 'MlpBlock_0', 'Dense_0', 'kernel'): (1, 768, 3072)
	('DiTBlock_10', 'MlpBlock_0', 'Dense_1', 'bias'): (1, 768)
	('DiTBlock_10', 'MlpBlock_0', 'Dense_1', 'kernel'): (1, 3072, 768)
	('DiTBlock_11', 'Dense_0', 'bias'): (1, 4608)
	('DiTBlock_11', 'Dense_0', 'kernel'): (1, 768, 4608)
	('DiTBlock_11', 'Dense_1', 'bias'): (1, 768)
	('DiTBlock_11', 'Dense_1', 'kernel'): (1, 768, 768)
	('DiTBlock_11', 'Dense_2', 'bias'): (1, 768)
	('DiTBlock_11', 'Dense_2', 'kernel'): (1, 768, 768)
	('DiTBlock_11', 'Dense_3', 'bias'): (1, 768)
	('DiTBlock_11', 'Dense_3', 'kernel'): (1, 768, 768)
	('DiTBlock_11', 'Dense_4', 'bias'): (1, 768)
	('DiTBlock_11', 'Dense_4', 'kernel'): (1, 768, 768)
	('DiTBlock_11', 'MlpBlock_0', 'Dense_0', 'bias'): (1, 3072)
	('DiTBlock_11', 'MlpBlock_0', 'Dense_0', 'kernel'): (1, 768, 3072)
	('DiTBlock_11', 'MlpBlock_0', 'Dense_1', 'bias'): (1, 768)
	('DiTBlock_11', 'MlpBlock_0', 'Dense_1', 'kernel'): (1, 3072, 768)
	('DiTBlock_2', 'Dense_0', 'bias'): (1, 4608)
	('DiTBlock_2', 'Dense_0', 'kernel'): (1, 768, 4608)
	('DiTBlock_2', 'Dense_1', 'bias'): (1, 768)
	('DiTBlock_2', 'Dense_1', 'kernel'): (1, 768, 768)
	('DiTBlock_2', 'Dense_2', 'bias'): (1, 768)
	('DiTBlock_2', 'Dense_2', 'kernel'): (1, 768, 768)
	('DiTBlock_2', 'Dense_3', 'bias'): (1, 768)
	('DiTBlock_2', 'Dense_3', 'kernel'): (1, 768, 768)
	('DiTBlock_2', 'Dense_4', 'bias'): (1, 768)
	('DiTBlock_2', 'Dense_4', 'kernel'): (1, 768, 768)
	('DiTBlock_2', 'MlpBlock_0', 'Dense_0', 'bias'): (1, 3072)
	('DiTBlock_2', 'MlpBlock_0', 'Dense_0', 'kernel'): (1, 768, 3072)
	('DiTBlock_2', 'MlpBlock_0', 'Dense_1', 'bias'): (1, 768)
	('DiTBlock_2', 'MlpBlock_0', 'Dense_1', 'kernel'): (1, 3072, 768)
	('DiTBlock_3', 'Dense_0', 'bias'): (1, 4608)
	('DiTBlock_3', 'Dense_0', 'kernel'): (1, 768, 4608)
	('DiTBlock_3', 'Dense_1', 'bias'): (1, 768)
	('DiTBlock_3', 'Dense_1', 'kernel'): (1, 768, 768)
	('DiTBlock_3', 'Dense_2', 'bias'): (1, 768)
	('DiTBlock_3', 'Dense_2', 'kernel'): (1, 768, 768)
	('DiTBlock_3', 'Dense_3', 'bias'): (1, 768)
	('DiTBlock_3', 'Dense_3', 'kernel'): (1, 768, 768)
	('DiTBlock_3', 'Dense_4', 'bias'): (1, 768)
	('DiTBlock_3', 'Dense_4', 'kernel'): (1, 768, 768)
	('DiTBlock_3', 'MlpBlock_0', 'Dense_0', 'bias'): (1, 3072)
	('DiTBlock_3', 'MlpBlock_0', 'Dense_0', 'kernel'): (1, 768, 3072)
	('DiTBlock_3', 'MlpBlock_0', 'Dense_1', 'bias'): (1, 768)
	('DiTBlock_3', 'MlpBlock_0', 'Dense_1', 'kernel'): (1, 3072, 768)
	('DiTBlock_4', 'Dense_0', 'bias'): (1, 4608)
	('DiTBlock_4', 'Dense_0', 'kernel'): (1, 768, 4608)
	('DiTBlock_4', 'Dense_1', 'bias'): (1, 768)
	('DiTBlock_4', 'Dense_1', 'kernel'): (1, 768, 768)
	('DiTBlock_4', 'Dense_2', 'bias'): (1, 768)
	('DiTBlock_4', 'Dense_2', 'kernel'): (1, 768, 768)
	('DiTBlock_4', 'Dense_3', 'bias'): (1, 768)
	('DiTBlock_4', 'Dense_3', 'kernel'): (1, 768, 768)
	('DiTBlock_4', 'Dense_4', 'bias'): (1, 768)
	('DiTBlock_4', 'Dense_4', 'kernel'): (1, 768, 768)
	('DiTBlock_4', 'MlpBlock_0', 'Dense_0', 'bias'): (1, 3072)
	('DiTBlock_4', 'MlpBlock_0', 'Dense_0', 'kernel'): (1, 768, 3072)
	('DiTBlock_4', 'MlpBlock_0', 'Dense_1', 'bias'): (1, 768)
	('DiTBlock_4', 'MlpBlock_0', 'Dense_1', 'kernel'): (1, 3072, 768)
	('DiTBlock_5', 'Dense_0', 'bias'): (1, 4608)
	('DiTBlock_5', 'Dense_0', 'kernel'): (1, 768, 4608)
	('DiTBlock_5', 'Dense_1', 'bias'): (1, 768)
	('DiTBlock_5', 'Dense_1', 'kernel'): (1, 768, 768)
	('DiTBlock_5', 'Dense_2', 'bias'): (1, 768)
	('DiTBlock_5', 'Dense_2', 'kernel'): (1, 768, 768)
	('DiTBlock_5', 'Dense_3', 'bias'): (1, 768)
	('DiTBlock_5', 'Dense_3', 'kernel'): (1, 768, 768)
	('DiTBlock_5', 'Dense_4', 'bias'): (1, 768)
	('DiTBlock_5', 'Dense_4', 'kernel'): (1, 768, 768)
	('DiTBlock_5', 'MlpBlock_0', 'Dense_0', 'bias'): (1, 3072)
	('DiTBlock_5', 'MlpBlock_0', 'Dense_0', 'kernel'): (1, 768, 3072)
	('DiTBlock_5', 'MlpBlock_0', 'Dense_1', 'bias'): (1, 768)
	('DiTBlock_5', 'MlpBlock_0', 'Dense_1', 'kernel'): (1, 3072, 768)
	('DiTBlock_6', 'Dense_0', 'bias'): (1, 4608)
	('DiTBlock_6', 'Dense_0', 'kernel'): (1, 768, 4608)
	('DiTBlock_6', 'Dense_1', 'bias'): (1, 768)
	('DiTBlock_6', 'Dense_1', 'kernel'): (1, 768, 768)
	('DiTBlock_6', 'Dense_2', 'bias'): (1, 768)
	('DiTBlock_6', 'Dense_2', 'kernel'): (1, 768, 768)
	('DiTBlock_6', 'Dense_3', 'bias'): (1, 768)
	('DiTBlock_6', 'Dense_3', 'kernel'): (1, 768, 768)
	('DiTBlock_6', 'Dense_4', 'bias'): (1, 768)
	('DiTBlock_6', 'Dense_4', 'kernel'): (1, 768, 768)
	('DiTBlock_6', 'MlpBlock_0', 'Dense_0', 'bias'): (1, 3072)
	('DiTBlock_6', 'MlpBlock_0', 'Dense_0', 'kernel'): (1, 768, 3072)
	('DiTBlock_6', 'MlpBlock_0', 'Dense_1', 'bias'): (1, 768)
	('DiTBlock_6', 'MlpBlock_0', 'Dense_1', 'kernel'): (1, 3072, 768)
	('DiTBlock_7', 'Dense_0', 'bias'): (1, 4608)
	('DiTBlock_7', 'Dense_0', 'kernel'): (1, 768, 4608)
	('DiTBlock_7', 'Dense_1', 'bias'): (1, 768)
	('DiTBlock_7', 'Dense_1', 'kernel'): (1, 768, 768)
	('DiTBlock_7', 'Dense_2', 'bias'): (1, 768)
	('DiTBlock_7', 'Dense_2', 'kernel'): (1, 768, 768)
	('DiTBlock_7', 'Dense_3', 'bias'): (1, 768)
	('DiTBlock_7', 'Dense_3', 'kernel'): (1, 768, 768)
	('DiTBlock_7', 'Dense_4', 'bias'): (1, 768)
	('DiTBlock_7', 'Dense_4', 'kernel'): (1, 768, 768)
	('DiTBlock_7', 'MlpBlock_0', 'Dense_0', 'bias'): (1, 3072)
	('DiTBlock_7', 'MlpBlock_0', 'Dense_0', 'kernel'): (1, 768, 3072)
	('DiTBlock_7', 'MlpBlock_0', 'Dense_1', 'bias'): (1, 768)
	('DiTBlock_7', 'MlpBlock_0', 'Dense_1', 'kernel'): (1, 3072, 768)
	('DiTBlock_8', 'Dense_0', 'bias'): (1, 4608)
	('DiTBlock_8', 'Dense_0', 'kernel'): (1, 768, 4608)
	('DiTBlock_8', 'Dense_1', 'bias'): (1, 768)
	('DiTBlock_8', 'Dense_1', 'kernel'): (1, 768, 768)
	('DiTBlock_8', 'Dense_2', 'bias'): (1, 768)
	('DiTBlock_8', 'Dense_2', 'kernel'): (1, 768, 768)
	('DiTBlock_8', 'Dense_3', 'bias'): (1, 768)
	('DiTBlock_8', 'Dense_3', 'kernel'): (1, 768, 768)
	('DiTBlock_8', 'Dense_4', 'bias'): (1, 768)
	('DiTBlock_8', 'Dense_4', 'kernel'): (1, 768, 768)
	('DiTBlock_8', 'MlpBlock_0', 'Dense_0', 'bias'): (1, 3072)
	('DiTBlock_8', 'MlpBlock_0', 'Dense_0', 'kernel'): (1, 768, 3072)
	('DiTBlock_8', 'MlpBlock_0', 'Dense_1', 'bias'): (1, 768)
	('DiTBlock_8', 'MlpBlock_0', 'Dense_1', 'kernel'): (1, 3072, 768)
	('DiTBlock_9', 'Dense_0', 'bias'): (1, 4608)
	('DiTBlock_9', 'Dense_0', 'kernel'): (1, 768, 4608)
	('DiTBlock_9', 'Dense_1', 'bias'): (1, 768)
	('DiTBlock_9', 'Dense_1', 'kernel'): (1, 768, 768)
	('DiTBlock_9', 'Dense_2', 'bias'): (1, 768)
	('DiTBlock_9', 'Dense_2', 'kernel'): (1, 768, 768)
	('DiTBlock_9', 'Dense_3', 'bias'): (1, 768)
	('DiTBlock_9', 'Dense_3', 'kernel'): (1, 768, 768)
	('DiTBlock_9', 'Dense_4', 'bias'): (1, 768)
	('DiTBlock_9', 'Dense_4', 'kernel'): (1, 768, 768)
	('DiTBlock_9', 'MlpBlock_0', 'Dense_0', 'bias'): (1, 3072)
	('DiTBlock_9', 'MlpBlock_0', 'Dense_0', 'kernel'): (1, 768, 3072)
	('DiTBlock_9', 'MlpBlock_0', 'Dense_1', 'bias'): (1, 768)
	('DiTBlock_9', 'MlpBlock_0', 'Dense_1', 'kernel'): (1, 3072, 768)
	('Embed_0', 'embedding'): (1, 256, 1)
	('FinalLayer_0', 'Dense_0', 'bias'): (1, 1536)
	('FinalLayer_0', 'Dense_0', 'kernel'): (1, 768, 1536)
	('FinalLayer_0', 'Dense_1', 'bias'): (1, 16)
	('FinalLayer_0', 'Dense_1', 'kernel'): (1, 768, 16)
	('LabelEmbedder_0', 'Embed_0', 'embedding'): (1, 1001, 768)
	('PatchEmbed_0', 'Conv_0', 'bias'): (1, 768)
	('PatchEmbed_0', 'Conv_0', 'kernel'): (1, 2, 2, 4, 768)
	('TimestepEmbedder_0', 'Dense_0', 'bias'): (1, 768)
	('TimestepEmbedder_0', 'Dense_0', 'kernel'): (1, 256, 768)
	('TimestepEmbedder_0', 'Dense_1', 'bias'): (1, 768)
	('TimestepEmbedder_0', 'Dense_1', 'kernel'): (1, 768, 768)
	('TimestepEmbedder_1', 'Dense_0', 'bias'): (1, 768)
	('TimestepEmbedder_1', 'Dense_0', 'kernel'): (1, 256, 768)
	('TimestepEmbedder_1', 'Dense_1', 'bias'): (1, 768)
	('TimestepEmbedder_1', 'Dense_1', 'kernel'): (1, 768, 768)
	flat

	parameter shapes:
	('DiTBlock_0', 'Dense_0', 'bias'): (1, 4608)
	('DiTBlock_0', 'Dense_0', 'kernel'): (1, 768, 4608)
	('DiTBlock_0', 'Dense_1', 'bias'): (1, 768)
	('DiTBlock_0', 'Dense_1', 'kernel'): (1, 768, 768)
	('DiTBlock_0', 'Dense_2', 'bias'): (1, 768)
	('DiTBlock_0', 'Dense_2', 'kernel'): (1, 768, 768)
	('DiTBlock_0', 'Dense_3', 'bias'): (1, 768)
	('DiTBlock_0', 'Dense_3', 'kernel'): (1, 768, 768)
	('DiTBlock_0', 'Dense_4', 'bias'): (1, 768)
	('DiTBlock_0', 'Dense_4', 'kernel'): (1, 768, 768)
	('DiTBlock_0', 'MlpBlock_0', 'Dense_0', 'bias'): (1, 3072)
	('DiTBlock_0', 'MlpBlock_0', 'Dense_0', 'kernel'): (1, 768, 3072)
	('DiTBlock_0', 'MlpBlock_0', 'Dense_1', 'bias'): (1, 768)
	('DiTBlock_0', 'MlpBlock_0', 'Dense_1', 'kernel'): (1, 3072, 768)
	('DiTBlock_1', 'Dense_0', 'bias'): (1, 4608)
	('DiTBlock_1', 'Dense_0', 'kernel'): (1, 768, 4608)
	('DiTBlock_1', 'Dense_1', 'bias'): (1, 768)
	('DiTBlock_1', 'Dense_1', 'kernel'): (1, 768, 768)
	('DiTBlock_1', 'Dense_2', 'bias'): (1, 768)
	('DiTBlock_1', 'Dense_2', 'kernel'): (1, 768, 768)
	('DiTBlock_1', 'Dense_3', 'bias'): (1, 768)
	('DiTBlock_1', 'Dense_3', 'kernel'): (1, 768, 768)
	('DiTBlock_1', 'Dense_4', 'bias'): (1, 768)
	('DiTBlock_1', 'Dense_4', 'kernel'): (1, 768, 768)
	('DiTBlock_1', 'MlpBlock_0', 'Dense_0', 'bias'): (1, 3072)
	('DiTBlock_1', 'MlpBlock_0', 'Dense_0', 'kernel'): (1, 768, 3072)
	('DiTBlock_1', 'MlpBlock_0', 'Dense_1', 'bias'): (1, 768)
	('DiTBlock_1', 'MlpBlock_0', 'Dense_1', 'kernel'): (1, 3072, 768)
	('DiTBlock_10', 'Dense_0', 'bias'): (1, 4608)
	('DiTBlock_10', 'Dense_0', 'kernel'): (1, 768, 4608)
	('DiTBlock_10', 'Dense_1', 'bias'): (1, 768)
	('DiTBlock_10', 'Dense_1', 'kernel'): (1, 768, 768)
	('DiTBlock_10', 'Dense_2', 'bias'): (1, 768)
	('DiTBlock_10', 'Dense_2', 'kernel'): (1, 768, 768)
	('DiTBlock_10', 'Dense_3', 'bias'): (1, 768)
	('DiTBlock_10', 'Dense_3', 'kernel'): (1, 768, 768)
	('DiTBlock_10', 'Dense_4', 'bias'): (1, 768)
	('DiTBlock_10', 'Dense_4', 'kernel'): (1, 768, 768)
	('DiTBlock_10', 'MlpBlock_0', 'Dense_0', 'bias'): (1, 3072)
	('DiTBlock_10', 'MlpBlock_0', 'Dense_0', 'kernel'): (1, 768, 3072)
	('DiTBlock_10', 'MlpBlock_0', 'Dense_1', 'bias'): (1, 768)
	('DiTBlock_10', 'MlpBlock_0', 'Dense_1', 'kernel'): (1, 3072, 768)
	('DiTBlock_11', 'Dense_0', 'bias'): (1, 4608)
	('DiTBlock_11', 'Dense_0', 'kernel'): (1, 768, 4608)
	('DiTBlock_11', 'Dense_1', 'bias'): (1, 768)
	('DiTBlock_11', 'Dense_1', 'kernel'): (1, 768, 768)
	('DiTBlock_11', 'Dense_2', 'bias'): (1, 768)
	('DiTBlock_11', 'Dense_2', 'kernel'): (1, 768, 768)
	('DiTBlock_11', 'Dense_3', 'bias'): (1, 768)
	('DiTBlock_11', 'Dense_3', 'kernel'): (1, 768, 768)
	('DiTBlock_11', 'Dense_4', 'bias'): (1, 768)
	('DiTBlock_11', 'Dense_4', 'kernel'): (1, 768, 768)
	('DiTBlock_11', 'MlpBlock_0', 'Dense_0', 'bias'): (1, 3072)
	('DiTBlock_11', 'MlpBlock_0', 'Dense_0', 'kernel'): (1, 768, 3072)
	('DiTBlock_11', 'MlpBlock_0', 'Dense_1', 'bias'): (1, 768)
	('DiTBlock_11', 'MlpBlock_0', 'Dense_1', 'kernel'): (1, 3072, 768)
	('DiTBlock_2', 'Dense_0', 'bias'): (1, 4608)
	('DiTBlock_2', 'Dense_0', 'kernel'): (1, 768, 4608)
	('DiTBlock_2', 'Dense_1', 'bias'): (1, 768)
	('DiTBlock_2', 'Dense_1', 'kernel'): (1, 768, 768)
	('DiTBlock_2', 'Dense_2', 'bias'): (1, 768)
	('DiTBlock_2', 'Dense_2', 'kernel'): (1, 768, 768)
	('DiTBlock_2', 'Dense_3', 'bias'): (1, 768)
	('DiTBlock_2', 'Dense_3', 'kernel'): (1, 768, 768)
	('DiTBlock_2', 'Dense_4', 'bias'): (1, 768)
	('DiTBlock_2', 'Dense_4', 'kernel'): (1, 768, 768)
	('DiTBlock_2', 'MlpBlock_0', 'Dense_0', 'bias'): (1, 3072)
	('DiTBlock_2', 'MlpBlock_0', 'Dense_0', 'kernel'): (1, 768, 3072)
	('DiTBlock_2', 'MlpBlock_0', 'Dense_1', 'bias'): (1, 768)
	('DiTBlock_2', 'MlpBlock_0', 'Dense_1', 'kernel'): (1, 3072, 768)
	('DiTBlock_3', 'Dense_0', 'bias'): (1, 4608)
	('DiTBlock_3', 'Dense_0', 'kernel'): (1, 768, 4608)
	('DiTBlock_3', 'Dense_1', 'bias'): (1, 768)
	('DiTBlock_3', 'Dense_1', 'kernel'): (1, 768, 768)
	('DiTBlock_3', 'Dense_2', 'bias'): (1, 768)
	('DiTBlock_3', 'Dense_2', 'kernel'): (1, 768, 768)
	('DiTBlock_3', 'Dense_3', 'bias'): (1, 768)
	('DiTBlock_3', 'Dense_3', 'kernel'): (1, 768, 768)
	('DiTBlock_3', 'Dense_4', 'bias'): (1, 768)
	('DiTBlock_3', 'Dense_4', 'kernel'): (1, 768, 768)
	('DiTBlock_3', 'MlpBlock_0', 'Dense_0', 'bias'): (1, 3072)
	('DiTBlock_3', 'MlpBlock_0', 'Dense_0', 'kernel'): (1, 768, 3072)
	('DiTBlock_3', 'MlpBlock_0', 'Dense_1', 'bias'): (1, 768)
	('DiTBlock_3', 'MlpBlock_0', 'Dense_1', 'kernel'): (1, 3072, 768)
	('DiTBlock_4', 'Dense_0', 'bias'): (1, 4608)
	('DiTBlock_4', 'Dense_0', 'kernel'): (1, 768, 4608)
	('DiTBlock_4', 'Dense_1', 'bias'): (1, 768)
	('DiTBlock_4', 'Dense_1', 'kernel'): (1, 768, 768)
	('DiTBlock_4', 'Dense_2', 'bias'): (1, 768)
	('DiTBlock_4', 'Dense_2', 'kernel'): (1, 768, 768)
	('DiTBlock_4', 'Dense_3', 'bias'): (1, 768)
	('DiTBlock_4', 'Dense_3', 'kernel'): (1, 768, 768)
	('DiTBlock_4', 'Dense_4', 'bias'): (1, 768)
	('DiTBlock_4', 'Dense_4', 'kernel'): (1, 768, 768)
	('DiTBlock_4', 'MlpBlock_0', 'Dense_0', 'bias'): (1, 3072)
	('DiTBlock_4', 'MlpBlock_0', 'Dense_0', 'kernel'): (1, 768, 3072)
	('DiTBlock_4', 'MlpBlock_0', 'Dense_1', 'bias'): (1, 768)
	('DiTBlock_4', 'MlpBlock_0', 'Dense_1', 'kernel'): (1, 3072, 768)
	('DiTBlock_5', 'Dense_0', 'bias'): (1, 4608)
	('DiTBlock_5', 'Dense_0', 'kernel'): (1, 768, 4608)
	('DiTBlock_5', 'Dense_1', 'bias'): (1, 768)
	('DiTBlock_5', 'Dense_1', 'kernel'): (1, 768, 768)
	('DiTBlock_5', 'Dense_2', 'bias'): (1, 768)
	('DiTBlock_5', 'Dense_2', 'kernel'): (1, 768, 768)
	('DiTBlock_5', 'Dense_3', 'bias'): (1, 768)
	('DiTBlock_5', 'Dense_3', 'kernel'): (1, 768, 768)
	('DiTBlock_5', 'Dense_4', 'bias'): (1, 768)
	('DiTBlock_5', 'Dense_4', 'kernel'): (1, 768, 768)
	('DiTBlock_5', 'MlpBlock_0', 'Dense_0', 'bias'): (1, 3072)
	('DiTBlock_5', 'MlpBlock_0', 'Dense_0', 'kernel'): (1, 768, 3072)
	('DiTBlock_5', 'MlpBlock_0', 'Dense_1', 'bias'): (1, 768)
	('DiTBlock_5', 'MlpBlock_0', 'Dense_1', 'kernel'): (1, 3072, 768)
	('DiTBlock_6', 'Dense_0', 'bias'): (1, 4608)
	('DiTBlock_6', 'Dense_0', 'kernel'): (1, 768, 4608)
	('DiTBlock_6', 'Dense_1', 'bias'): (1, 768)
	('DiTBlock_6', 'Dense_1', 'kernel'): (1, 768, 768)
	('DiTBlock_6', 'Dense_2', 'bias'): (1, 768)
	('DiTBlock_6', 'Dense_2', 'kernel'): (1, 768, 768)
	('DiTBlock_6', 'Dense_3', 'bias'): (1, 768)
	('DiTBlock_6', 'Dense_3', 'kernel'): (1, 768, 768)
	('DiTBlock_6', 'Dense_4', 'bias'): (1, 768)
	('DiTBlock_6', 'Dense_4', 'kernel'): (1, 768, 768)
	('DiTBlock_6', 'MlpBlock_0', 'Dense_0', 'bias'): (1, 3072)
	('DiTBlock_6', 'MlpBlock_0', 'Dense_0', 'kernel'): (1, 768, 3072)
	('DiTBlock_6', 'MlpBlock_0', 'Dense_1', 'bias'): (1, 768)
	('DiTBlock_6', 'MlpBlock_0', 'Dense_1', 'kernel'): (1, 3072, 768)
	('DiTBlock_7', 'Dense_0', 'bias'): (1, 4608)
	('DiTBlock_7', 'Dense_0', 'kernel'): (1, 768, 4608)
	('DiTBlock_7', 'Dense_1', 'bias'): (1, 768)
	('DiTBlock_7', 'Dense_1', 'kernel'): (1, 768, 768)
	('DiTBlock_7', 'Dense_2', 'bias'): (1, 768)
	('DiTBlock_7', 'Dense_2', 'kernel'): (1, 768, 768)
	('DiTBlock_7', 'Dense_3', 'bias'): (1, 768)
	('DiTBlock_7', 'Dense_3', 'kernel'): (1, 768, 768)
	('DiTBlock_7', 'Dense_4', 'bias'): (1, 768)
	('DiTBlock_7', 'Dense_4', 'kernel'): (1, 768, 768)
	('DiTBlock_7', 'MlpBlock_0', 'Dense_0', 'bias'): (1, 3072)
	('DiTBlock_7', 'MlpBlock_0', 'Dense_0', 'kernel'): (1, 768, 3072)
	('DiTBlock_7', 'MlpBlock_0', 'Dense_1', 'bias'): (1, 768)
	('DiTBlock_7', 'MlpBlock_0', 'Dense_1', 'kernel'): (1, 3072, 768)
	('DiTBlock_8', 'Dense_0', 'bias'): (1, 4608)
	('DiTBlock_8', 'Dense_0', 'kernel'): (1, 768, 4608)
	('DiTBlock_8', 'Dense_1', 'bias'): (1, 768)
	('DiTBlock_8', 'Dense_1', 'kernel'): (1, 768, 768)
	('DiTBlock_8', 'Dense_2', 'bias'): (1, 768)
	('DiTBlock_8', 'Dense_2', 'kernel'): (1, 768, 768)
	('DiTBlock_8', 'Dense_3', 'bias'): (1, 768)
	('DiTBlock_8', 'Dense_3', 'kernel'): (1, 768, 768)
	('DiTBlock_8', 'Dense_4', 'bias'): (1, 768)
	('DiTBlock_8', 'Dense_4', 'kernel'): (1, 768, 768)
	('DiTBlock_8', 'MlpBlock_0', 'Dense_0', 'bias'): (1, 3072)
	('DiTBlock_8', 'MlpBlock_0', 'Dense_0', 'kernel'): (1, 768, 3072)
	('DiTBlock_8', 'MlpBlock_0', 'Dense_1', 'bias'): (1, 768)
	('DiTBlock_8', 'MlpBlock_0', 'Dense_1', 'kernel'): (1, 3072, 768)
	('DiTBlock_9', 'Dense_0', 'bias'): (1, 4608)
	('DiTBlock_9', 'Dense_0', 'kernel'): (1, 768, 4608)
	('DiTBlock_9', 'Dense_1', 'bias'): (1, 768)
	('DiTBlock_9', 'Dense_1', 'kernel'): (1, 768, 768)
	('DiTBlock_9', 'Dense_2', 'bias'): (1, 768)
	('DiTBlock_9', 'Dense_2', 'kernel'): (1, 768, 768)
	('DiTBlock_9', 'Dense_3', 'bias'): (1, 768)
	('DiTBlock_9', 'Dense_3', 'kernel'): (1, 768, 768)
	('DiTBlock_9', 'Dense_4', 'bias'): (1, 768)
	('DiTBlock_9', 'Dense_4', 'kernel'): (1, 768, 768)
	('DiTBlock_9', 'MlpBlock_0', 'Dense_0', 'bias'): (1, 3072)
	('DiTBlock_9', 'MlpBlock_0', 'Dense_0', 'kernel'): (1, 768, 3072)
	('DiTBlock_9', 'MlpBlock_0', 'Dense_1', 'bias'): (1, 768)
	('DiTBlock_9', 'MlpBlock_0', 'Dense_1', 'kernel'): (1, 3072, 768)
	('Embed_0', 'embedding'): (1, 256, 1)
	('FinalLayer_0', 'Dense_0', 'bias'): (1, 1536)
	('FinalLayer_0', 'Dense_0', 'kernel'): (1, 768, 1536)
	('FinalLayer_0', 'Dense_1', 'bias'): (1, 16)
	('FinalLayer_0', 'Dense_1', 'kernel'): (1, 768, 16)
	('LabelEmbedder_0', 'Embed_0', 'embedding'): (1, 1001, 768)
	('PatchEmbed_0', 'Conv_0', 'bias'): (1, 768)
	('PatchEmbed_0', 'Conv_0', 'kernel'): (1, 2, 2, 4, 768)
	('TimestepEmbedder_0', 'Dense_0', 'bias'): (1, 768)
	('TimestepEmbedder_0', 'Dense_0', 'kernel'): (1, 256, 768)
	('TimestepEmbedder_0', 'Dense_1', 'bias'): (1, 768)
	('TimestepEmbedder_0', 'Dense_1', 'kernel'): (1, 768, 768)
	('TimestepEmbedder_1', 'Dense_0', 'bias'): (1, 768)
	('TimestepEmbedder_1', 'Dense_0', 'kernel'): (1, 256, 768)
	('TimestepEmbedder_1', 'Dense_1', 'bias'): (1, 768)
	('TimestepEmbedder_1', 'Dense_1', 'kernel'): (1, 768, 768)
	flat ema

	parameter shapes:
	('DiTBlock_0', 'Dense_0', 'bias'): (1, 4608)
	('DiTBlock_0', 'Dense_0', 'kernel'): (1, 768, 4608)
	('DiTBlock_0', 'Dense_1', 'bias'): (1, 768)
	('DiTBlock_0', 'Dense_1', 'kernel'): (1, 768, 768)
	('DiTBlock_0', 'Dense_2', 'bias'): (1, 768)
	('DiTBlock_0', 'Dense_2', 'kernel'): (1, 768, 768)
	('DiTBlock_0', 'Dense_3', 'bias'): (1, 768)
	('DiTBlock_0', 'Dense_3', 'kernel'): (1, 768, 768)
	('DiTBlock_0', 'Dense_4', 'bias'): (1, 768)
	('DiTBlock_0', 'Dense_4', 'kernel'): (1, 768, 768)
	('DiTBlock_0', 'MlpBlock_0', 'Dense_0', 'bias'): (1, 3072)
	('DiTBlock_0', 'MlpBlock_0', 'Dense_0', 'kernel'): (1, 768, 3072)
	('DiTBlock_0', 'MlpBlock_0', 'Dense_1', 'bias'): (1, 768)
	('DiTBlock_0', 'MlpBlock_0', 'Dense_1', 'kernel'): (1, 3072, 768)
	('DiTBlock_1', 'Dense_0', 'bias'): (1, 4608)
	('DiTBlock_1', 'Dense_0', 'kernel'): (1, 768, 4608)
	('DiTBlock_1', 'Dense_1', 'bias'): (1, 768)
	('DiTBlock_1', 'Dense_1', 'kernel'): (1, 768, 768)
	('DiTBlock_1', 'Dense_2', 'bias'): (1, 768)
	('DiTBlock_1', 'Dense_2', 'kernel'): (1, 768, 768)
	('DiTBlock_1', 'Dense_3', 'bias'): (1, 768)
	('DiTBlock_1', 'Dense_3', 'kernel'): (1, 768, 768)
	('DiTBlock_1', 'Dense_4', 'bias'): (1, 768)
	('DiTBlock_1', 'Dense_4', 'kernel'): (1, 768, 768)
	('DiTBlock_1', 'MlpBlock_0', 'Dense_0', 'bias'): (1, 3072)
	('DiTBlock_1', 'MlpBlock_0', 'Dense_0', 'kernel'): (1, 768, 3072)
	('DiTBlock_1', 'MlpBlock_0', 'Dense_1', 'bias'): (1, 768)
	('DiTBlock_1', 'MlpBlock_0', 'Dense_1', 'kernel'): (1, 3072, 768)
	('DiTBlock_10', 'Dense_0', 'bias'): (1, 4608)
	('DiTBlock_10', 'Dense_0', 'kernel'): (1, 768, 4608)
	('DiTBlock_10', 'Dense_1', 'bias'): (1, 768)
	('DiTBlock_10', 'Dense_1', 'kernel'): (1, 768, 768)
	('DiTBlock_10', 'Dense_2', 'bias'): (1, 768)
	('DiTBlock_10', 'Dense_2', 'kernel'): (1, 768, 768)
	('DiTBlock_10', 'Dense_3', 'bias'): (1, 768)
	('DiTBlock_10', 'Dense_3', 'kernel'): (1, 768, 768)
	('DiTBlock_10', 'Dense_4', 'bias'): (1, 768)
	('DiTBlock_10', 'Dense_4', 'kernel'): (1, 768, 768)
	('DiTBlock_10', 'MlpBlock_0', 'Dense_0', 'bias'): (1, 3072)
	('DiTBlock_10', 'MlpBlock_0', 'Dense_0', 'kernel'): (1, 768, 3072)
	('DiTBlock_10', 'MlpBlock_0', 'Dense_1', 'bias'): (1, 768)
	('DiTBlock_10', 'MlpBlock_0', 'Dense_1', 'kernel'): (1, 3072, 768)
	('DiTBlock_11', 'Dense_0', 'bias'): (1, 4608)
	('DiTBlock_11', 'Dense_0', 'kernel'): (1, 768, 4608)
	('DiTBlock_11', 'Dense_1', 'bias'): (1, 768)
	('DiTBlock_11', 'Dense_1', 'kernel'): (1, 768, 768)
	('DiTBlock_11', 'Dense_2', 'bias'): (1, 768)
	('DiTBlock_11', 'Dense_2', 'kernel'): (1, 768, 768)
	('DiTBlock_11', 'Dense_3', 'bias'): (1, 768)
	('DiTBlock_11', 'Dense_3', 'kernel'): (1, 768, 768)
	('DiTBlock_11', 'Dense_4', 'bias'): (1, 768)
	('DiTBlock_11', 'Dense_4', 'kernel'): (1, 768, 768)
	('DiTBlock_11', 'MlpBlock_0', 'Dense_0', 'bias'): (1, 3072)
	('DiTBlock_11', 'MlpBlock_0', 'Dense_0', 'kernel'): (1, 768, 3072)
	('DiTBlock_11', 'MlpBlock_0', 'Dense_1', 'bias'): (1, 768)
	('DiTBlock_11', 'MlpBlock_0', 'Dense_1', 'kernel'): (1, 3072, 768)
	('DiTBlock_2', 'Dense_0', 'bias'): (1, 4608)
	('DiTBlock_2', 'Dense_0', 'kernel'): (1, 768, 4608)
	('DiTBlock_2', 'Dense_1', 'bias'): (1, 768)
	('DiTBlock_2', 'Dense_1', 'kernel'): (1, 768, 768)
	('DiTBlock_2', 'Dense_2', 'bias'): (1, 768)
	('DiTBlock_2', 'Dense_2', 'kernel'): (1, 768, 768)
	('DiTBlock_2', 'Dense_3', 'bias'): (1, 768)
	('DiTBlock_2', 'Dense_3', 'kernel'): (1, 768, 768)
	('DiTBlock_2', 'Dense_4', 'bias'): (1, 768)
	('DiTBlock_2', 'Dense_4', 'kernel'): (1, 768, 768)
	('DiTBlock_2', 'MlpBlock_0', 'Dense_0', 'bias'): (1, 3072)
	('DiTBlock_2', 'MlpBlock_0', 'Dense_0', 'kernel'): (1, 768, 3072)
	('DiTBlock_2', 'MlpBlock_0', 'Dense_1', 'bias'): (1, 768)
	('DiTBlock_2', 'MlpBlock_0', 'Dense_1', 'kernel'): (1, 3072, 768)
	('DiTBlock_3', 'Dense_0', 'bias'): (1, 4608)
	('DiTBlock_3', 'Dense_0', 'kernel'): (1, 768, 4608)
	('DiTBlock_3', 'Dense_1', 'bias'): (1, 768)
	('DiTBlock_3', 'Dense_1', 'kernel'): (1, 768, 768)
	('DiTBlock_3', 'Dense_2', 'bias'): (1, 768)
	('DiTBlock_3', 'Dense_2', 'kernel'): (1, 768, 768)
	('DiTBlock_3', 'Dense_3', 'bias'): (1, 768)
	('DiTBlock_3', 'Dense_3', 'kernel'): (1, 768, 768)
	('DiTBlock_3', 'Dense_4', 'bias'): (1, 768)
	('DiTBlock_3', 'Dense_4', 'kernel'): (1, 768, 768)
	('DiTBlock_3', 'MlpBlock_0', 'Dense_0', 'bias'): (1, 3072)
	('DiTBlock_3', 'MlpBlock_0', 'Dense_0', 'kernel'): (1, 768, 3072)
	('DiTBlock_3', 'MlpBlock_0', 'Dense_1', 'bias'): (1, 768)
	('DiTBlock_3', 'MlpBlock_0', 'Dense_1', 'kernel'): (1, 3072, 768)
	('DiTBlock_4', 'Dense_0', 'bias'): (1, 4608)
	('DiTBlock_4', 'Dense_0', 'kernel'): (1, 768, 4608)
	('DiTBlock_4', 'Dense_1', 'bias'): (1, 768)
	('DiTBlock_4', 'Dense_1', 'kernel'): (1, 768, 768)
	('DiTBlock_4', 'Dense_2', 'bias'): (1, 768)
	('DiTBlock_4', 'Dense_2', 'kernel'): (1, 768, 768)
	('DiTBlock_4', 'Dense_3', 'bias'): (1, 768)
	('DiTBlock_4', 'Dense_3', 'kernel'): (1, 768, 768)
	('DiTBlock_4', 'Dense_4', 'bias'): (1, 768)
	('DiTBlock_4', 'Dense_4', 'kernel'): (1, 768, 768)
	('DiTBlock_4', 'MlpBlock_0', 'Dense_0', 'bias'): (1, 3072)
	('DiTBlock_4', 'MlpBlock_0', 'Dense_0', 'kernel'): (1, 768, 3072)
	('DiTBlock_4', 'MlpBlock_0', 'Dense_1', 'bias'): (1, 768)
	('DiTBlock_4', 'MlpBlock_0', 'Dense_1', 'kernel'): (1, 3072, 768)
	('DiTBlock_5', 'Dense_0', 'bias'): (1, 4608)
	('DiTBlock_5', 'Dense_0', 'kernel'): (1, 768, 4608)
	('DiTBlock_5', 'Dense_1', 'bias'): (1, 768)
	('DiTBlock_5', 'Dense_1', 'kernel'): (1, 768, 768)
	('DiTBlock_5', 'Dense_2', 'bias'): (1, 768)
	('DiTBlock_5', 'Dense_2', 'kernel'): (1, 768, 768)
	('DiTBlock_5', 'Dense_3', 'bias'): (1, 768)
	('DiTBlock_5', 'Dense_3', 'kernel'): (1, 768, 768)
	('DiTBlock_5', 'Dense_4', 'bias'): (1, 768)
	('DiTBlock_5', 'Dense_4', 'kernel'): (1, 768, 768)
	('DiTBlock_5', 'MlpBlock_0', 'Dense_0', 'bias'): (1, 3072)
	('DiTBlock_5', 'MlpBlock_0', 'Dense_0', 'kernel'): (1, 768, 3072)
	('DiTBlock_5', 'MlpBlock_0', 'Dense_1', 'bias'): (1, 768)
	('DiTBlock_5', 'MlpBlock_0', 'Dense_1', 'kernel'): (1, 3072, 768)
	('DiTBlock_6', 'Dense_0', 'bias'): (1, 4608)
	('DiTBlock_6', 'Dense_0', 'kernel'): (1, 768, 4608)
	('DiTBlock_6', 'Dense_1', 'bias'): (1, 768)
	('DiTBlock_6', 'Dense_1', 'kernel'): (1, 768, 768)
	('DiTBlock_6', 'Dense_2', 'bias'): (1, 768)
	('DiTBlock_6', 'Dense_2', 'kernel'): (1, 768, 768)
	('DiTBlock_6', 'Dense_3', 'bias'): (1, 768)
	('DiTBlock_6', 'Dense_3', 'kernel'): (1, 768, 768)
	('DiTBlock_6', 'Dense_4', 'bias'): (1, 768)
	('DiTBlock_6', 'Dense_4', 'kernel'): (1, 768, 768)
	('DiTBlock_6', 'MlpBlock_0', 'Dense_0', 'bias'): (1, 3072)
	('DiTBlock_6', 'MlpBlock_0', 'Dense_0', 'kernel'): (1, 768, 3072)
	('DiTBlock_6', 'MlpBlock_0', 'Dense_1', 'bias'): (1, 768)
	('DiTBlock_6', 'MlpBlock_0', 'Dense_1', 'kernel'): (1, 3072, 768)
	('DiTBlock_7', 'Dense_0', 'bias'): (1, 4608)
	('DiTBlock_7', 'Dense_0', 'kernel'): (1, 768, 4608)
	('DiTBlock_7', 'Dense_1', 'bias'): (1, 768)
	('DiTBlock_7', 'Dense_1', 'kernel'): (1, 768, 768)
	('DiTBlock_7', 'Dense_2', 'bias'): (1, 768)
	('DiTBlock_7', 'Dense_2', 'kernel'): (1, 768, 768)
	('DiTBlock_7', 'Dense_3', 'bias'): (1, 768)
	('DiTBlock_7', 'Dense_3', 'kernel'): (1, 768, 768)
	('DiTBlock_7', 'Dense_4', 'bias'): (1, 768)
	('DiTBlock_7', 'Dense_4', 'kernel'): (1, 768, 768)
	('DiTBlock_7', 'MlpBlock_0', 'Dense_0', 'bias'): (1, 3072)
	('DiTBlock_7', 'MlpBlock_0', 'Dense_0', 'kernel'): (1, 768, 3072)
	('DiTBlock_7', 'MlpBlock_0', 'Dense_1', 'bias'): (1, 768)
	('DiTBlock_7', 'MlpBlock_0', 'Dense_1', 'kernel'): (1, 3072, 768)
	('DiTBlock_8', 'Dense_0', 'bias'): (1, 4608)
	('DiTBlock_8', 'Dense_0', 'kernel'): (1, 768, 4608)
	('DiTBlock_8', 'Dense_1', 'bias'): (1, 768)
	('DiTBlock_8', 'Dense_1', 'kernel'): (1, 768, 768)
	('DiTBlock_8', 'Dense_2', 'bias'): (1, 768)
	('DiTBlock_8', 'Dense_2', 'kernel'): (1, 768, 768)
	('DiTBlock_8', 'Dense_3', 'bias'): (1, 768)
	('DiTBlock_8', 'Dense_3', 'kernel'): (1, 768, 768)
	('DiTBlock_8', 'Dense_4', 'bias'): (1, 768)
	('DiTBlock_8', 'Dense_4', 'kernel'): (1, 768, 768)
	('DiTBlock_8', 'MlpBlock_0', 'Dense_0', 'bias'): (1, 3072)
	('DiTBlock_8', 'MlpBlock_0', 'Dense_0', 'kernel'): (1, 768, 3072)
	('DiTBlock_8', 'MlpBlock_0', 'Dense_1', 'bias'): (1, 768)
	('DiTBlock_8', 'MlpBlock_0', 'Dense_1', 'kernel'): (1, 3072, 768)
	('DiTBlock_9', 'Dense_0', 'bias'): (1, 4608)
	('DiTBlock_9', 'Dense_0', 'kernel'): (1, 768, 4608)
	('DiTBlock_9', 'Dense_1', 'bias'): (1, 768)
	('DiTBlock_9', 'Dense_1', 'kernel'): (1, 768, 768)
	('DiTBlock_9', 'Dense_2', 'bias'): (1, 768)
	('DiTBlock_9', 'Dense_2', 'kernel'): (1, 768, 768)
	('DiTBlock_9', 'Dense_3', 'bias'): (1, 768)
	('DiTBlock_9', 'Dense_3', 'kernel'): (1, 768, 768)
	('DiTBlock_9', 'Dense_4', 'bias'): (1, 768)
	('DiTBlock_9', 'Dense_4', 'kernel'): (1, 768, 768)
	('DiTBlock_9', 'MlpBlock_0', 'Dense_0', 'bias'): (1, 3072)
	('DiTBlock_9', 'MlpBlock_0', 'Dense_0', 'kernel'): (1, 768, 3072)
	('DiTBlock_9', 'MlpBlock_0', 'Dense_1', 'bias'): (1, 768)
	('DiTBlock_9', 'MlpBlock_0', 'Dense_1', 'kernel'): (1, 3072, 768)
	('Embed_0', 'embedding'): (1, 256, 1)
	('FinalLayer_0', 'Dense_0', 'bias'): (1, 1536)
	('FinalLayer_0', 'Dense_0', 'kernel'): (1, 768, 1536)
	('FinalLayer_0', 'Dense_1', 'bias'): (1, 16)
	('FinalLayer_0', 'Dense_1', 'kernel'): (1, 768, 16)
	('LabelEmbedder_0', 'Embed_0', 'embedding'): (1, 1001, 768)
	('PatchEmbed_0', 'Conv_0', 'bias'): (1, 768)
	('PatchEmbed_0', 'Conv_0', 'kernel'): (1, 2, 2, 4, 768)
	('TimestepEmbedder_0', 'Dense_0', 'bias'): (1, 768)
	('TimestepEmbedder_0', 'Dense_0', 'kernel'): (1, 256, 768)
	('TimestepEmbedder_0', 'Dense_1', 'bias'): (1, 768)
	('TimestepEmbedder_0', 'Dense_1', 'kernel'): (1, 768, 768)
	('TimestepEmbedder_1', 'Dense_0', 'bias'): (1, 768)
	('TimestepEmbedder_1', 'Dense_0', 'kernel'): (1, 256, 768)
	('TimestepEmbedder_1', 'Dense_1', 'bias'): (1, 768)
	('TimestepEmbedder_1', 'Dense_1', 'kernel'): (1, 768, 768)

	parameter shapes:
	('DiTBlock_0', 'Dense_0', 'bias'): (1, 4608)
	('DiTBlock_0', 'Dense_0', 'kernel'): (1, 768, 4608)
	('DiTBlock_0', 'Dense_1', 'bias'): (1, 768)
	('DiTBlock_0', 'Dense_1', 'kernel'): (1, 768, 768)
	('DiTBlock_0', 'Dense_2', 'bias'): (1, 768)
	('DiTBlock_0', 'Dense_2', 'kernel'): (1, 768, 768)
	('DiTBlock_0', 'Dense_3', 'bias'): (1, 768)
	('DiTBlock_0', 'Dense_3', 'kernel'): (1, 768, 768)
	('DiTBlock_0', 'Dense_4', 'bias'): (1, 768)
	('DiTBlock_0', 'Dense_4', 'kernel'): (1, 768, 768)
	('DiTBlock_0', 'MlpBlock_0', 'Dense_0', 'bias'): (1, 3072)
	('DiTBlock_0', 'MlpBlock_0', 'Dense_0', 'kernel'): (1, 768, 3072)
	('DiTBlock_0', 'MlpBlock_0', 'Dense_1', 'bias'): (1, 768)
	('DiTBlock_0', 'MlpBlock_0', 'Dense_1', 'kernel'): (1, 3072, 768)
	('DiTBlock_1', 'Dense_0', 'bias'): (1, 4608)
	('DiTBlock_1', 'Dense_0', 'kernel'): (1, 768, 4608)
	('DiTBlock_1', 'Dense_1', 'bias'): (1, 768)
	('DiTBlock_1', 'Dense_1', 'kernel'): (1, 768, 768)
	('DiTBlock_1', 'Dense_2', 'bias'): (1, 768)
	('DiTBlock_1', 'Dense_2', 'kernel'): (1, 768, 768)
	('DiTBlock_1', 'Dense_3', 'bias'): (1, 768)
	('DiTBlock_1', 'Dense_3', 'kernel'): (1, 768, 768)
	('DiTBlock_1', 'Dense_4', 'bias'): (1, 768)
	('DiTBlock_1', 'Dense_4', 'kernel'): (1, 768, 768)
	('DiTBlock_1', 'MlpBlock_0', 'Dense_0', 'bias'): (1, 3072)
	('DiTBlock_1', 'MlpBlock_0', 'Dense_0', 'kernel'): (1, 768, 3072)
	('DiTBlock_1', 'MlpBlock_0', 'Dense_1', 'bias'): (1, 768)
	('DiTBlock_1', 'MlpBlock_0', 'Dense_1', 'kernel'): (1, 3072, 768)
	('DiTBlock_10', 'Dense_0', 'bias'): (1, 4608)
	('DiTBlock_10', 'Dense_0', 'kernel'): (1, 768, 4608)
	('DiTBlock_10', 'Dense_1', 'bias'): (1, 768)
	('DiTBlock_10', 'Dense_1', 'kernel'): (1, 768, 768)
	('DiTBlock_10', 'Dense_2', 'bias'): (1, 768)
	('DiTBlock_10', 'Dense_2', 'kernel'): (1, 768, 768)
	('DiTBlock_10', 'Dense_3', 'bias'): (1, 768)
	('DiTBlock_10', 'Dense_3', 'kernel'): (1, 768, 768)
	('DiTBlock_10', 'Dense_4', 'bias'): (1, 768)
	('DiTBlock_10', 'Dense_4', 'kernel'): (1, 768, 768)
	('DiTBlock_10', 'MlpBlock_0', 'Dense_0', 'bias'): (1, 3072)
	('DiTBlock_10', 'MlpBlock_0', 'Dense_0', 'kernel'): (1, 768, 3072)
	('DiTBlock_10', 'MlpBlock_0', 'Dense_1', 'bias'): (1, 768)
	('DiTBlock_10', 'MlpBlock_0', 'Dense_1', 'kernel'): (1, 3072, 768)
	('DiTBlock_11', 'Dense_0', 'bias'): (1, 4608)
	('DiTBlock_11', 'Dense_0', 'kernel'): (1, 768, 4608)
	('DiTBlock_11', 'Dense_1', 'bias'): (1, 768)
	('DiTBlock_11', 'Dense_1', 'kernel'): (1, 768, 768)
	('DiTBlock_11', 'Dense_2', 'bias'): (1, 768)
	('DiTBlock_11', 'Dense_2', 'kernel'): (1, 768, 768)
	('DiTBlock_11', 'Dense_3', 'bias'): (1, 768)
	('DiTBlock_11', 'Dense_3', 'kernel'): (1, 768, 768)
	('DiTBlock_11', 'Dense_4', 'bias'): (1, 768)
	('DiTBlock_11', 'Dense_4', 'kernel'): (1, 768, 768)
	('DiTBlock_11', 'MlpBlock_0', 'Dense_0', 'bias'): (1, 3072)
	('DiTBlock_11', 'MlpBlock_0', 'Dense_0', 'kernel'): (1, 768, 3072)
	('DiTBlock_11', 'MlpBlock_0', 'Dense_1', 'bias'): (1, 768)
	('DiTBlock_11', 'MlpBlock_0', 'Dense_1', 'kernel'): (1, 3072, 768)
	('DiTBlock_2', 'Dense_0', 'bias'): (1, 4608)
	('DiTBlock_2', 'Dense_0', 'kernel'): (1, 768, 4608)
	('DiTBlock_2', 'Dense_1', 'bias'): (1, 768)
	('DiTBlock_2', 'Dense_1', 'kernel'): (1, 768, 768)
	('DiTBlock_2', 'Dense_2', 'bias'): (1, 768)
	('DiTBlock_2', 'Dense_2', 'kernel'): (1, 768, 768)
	('DiTBlock_2', 'Dense_3', 'bias'): (1, 768)
	('DiTBlock_2', 'Dense_3', 'kernel'): (1, 768, 768)
	('DiTBlock_2', 'Dense_4', 'bias'): (1, 768)
	('DiTBlock_2', 'Dense_4', 'kernel'): (1, 768, 768)
	('DiTBlock_2', 'MlpBlock_0', 'Dense_0', 'bias'): (1, 3072)
	('DiTBlock_2', 'MlpBlock_0', 'Dense_0', 'kernel'): (1, 768, 3072)
	('DiTBlock_2', 'MlpBlock_0', 'Dense_1', 'bias'): (1, 768)
	('DiTBlock_2', 'MlpBlock_0', 'Dense_1', 'kernel'): (1, 3072, 768)
	('DiTBlock_3', 'Dense_0', 'bias'): (1, 4608)
	('DiTBlock_3', 'Dense_0', 'kernel'): (1, 768, 4608)
	('DiTBlock_3', 'Dense_1', 'bias'): (1, 768)
	('DiTBlock_3', 'Dense_1', 'kernel'): (1, 768, 768)
	('DiTBlock_3', 'Dense_2', 'bias'): (1, 768)
	('DiTBlock_3', 'Dense_2', 'kernel'): (1, 768, 768)
	('DiTBlock_3', 'Dense_3', 'bias'): (1, 768)
	('DiTBlock_3', 'Dense_3', 'kernel'): (1, 768, 768)
	('DiTBlock_3', 'Dense_4', 'bias'): (1, 768)
	('DiTBlock_3', 'Dense_4', 'kernel'): (1, 768, 768)
	('DiTBlock_3', 'MlpBlock_0', 'Dense_0', 'bias'): (1, 3072)
	('DiTBlock_3', 'MlpBlock_0', 'Dense_0', 'kernel'): (1, 768, 3072)
	('DiTBlock_3', 'MlpBlock_0', 'Dense_1', 'bias'): (1, 768)
	('DiTBlock_3', 'MlpBlock_0', 'Dense_1', 'kernel'): (1, 3072, 768)
	('DiTBlock_4', 'Dense_0', 'bias'): (1, 4608)
	('DiTBlock_4', 'Dense_0', 'kernel'): (1, 768, 4608)
	('DiTBlock_4', 'Dense_1', 'bias'): (1, 768)
	('DiTBlock_4', 'Dense_1', 'kernel'): (1, 768, 768)
	('DiTBlock_4', 'Dense_2', 'bias'): (1, 768)
	('DiTBlock_4', 'Dense_2', 'kernel'): (1, 768, 768)
	('DiTBlock_4', 'Dense_3', 'bias'): (1, 768)
	('DiTBlock_4', 'Dense_3', 'kernel'): (1, 768, 768)
	('DiTBlock_4', 'Dense_4', 'bias'): (1, 768)
	('DiTBlock_4', 'Dense_4', 'kernel'): (1, 768, 768)
	('DiTBlock_4', 'MlpBlock_0', 'Dense_0', 'bias'): (1, 3072)
	('DiTBlock_4', 'MlpBlock_0', 'Dense_0', 'kernel'): (1, 768, 3072)
	('DiTBlock_4', 'MlpBlock_0', 'Dense_1', 'bias'): (1, 768)
	('DiTBlock_4', 'MlpBlock_0', 'Dense_1', 'kernel'): (1, 3072, 768)
	('DiTBlock_5', 'Dense_0', 'bias'): (1, 4608)
	('DiTBlock_5', 'Dense_0', 'kernel'): (1, 768, 4608)
	('DiTBlock_5', 'Dense_1', 'bias'): (1, 768)
	('DiTBlock_5', 'Dense_1', 'kernel'): (1, 768, 768)
	('DiTBlock_5', 'Dense_2', 'bias'): (1, 768)
	('DiTBlock_5', 'Dense_2', 'kernel'): (1, 768, 768)
	('DiTBlock_5', 'Dense_3', 'bias'): (1, 768)
	('DiTBlock_5', 'Dense_3', 'kernel'): (1, 768, 768)
	('DiTBlock_5', 'Dense_4', 'bias'): (1, 768)
	('DiTBlock_5', 'Dense_4', 'kernel'): (1, 768, 768)
	('DiTBlock_5', 'MlpBlock_0', 'Dense_0', 'bias'): (1, 3072)
	('DiTBlock_5', 'MlpBlock_0', 'Dense_0', 'kernel'): (1, 768, 3072)
	('DiTBlock_5', 'MlpBlock_0', 'Dense_1', 'bias'): (1, 768)
	('DiTBlock_5', 'MlpBlock_0', 'Dense_1', 'kernel'): (1, 3072, 768)
	('DiTBlock_6', 'Dense_0', 'bias'): (1, 4608)
	('DiTBlock_6', 'Dense_0', 'kernel'): (1, 768, 4608)
	('DiTBlock_6', 'Dense_1', 'bias'): (1, 768)
	('DiTBlock_6', 'Dense_1', 'kernel'): (1, 768, 768)
	('DiTBlock_6', 'Dense_2', 'bias'): (1, 768)
	('DiTBlock_6', 'Dense_2', 'kernel'): (1, 768, 768)
	('DiTBlock_6', 'Dense_3', 'bias'): (1, 768)
	('DiTBlock_6', 'Dense_3', 'kernel'): (1, 768, 768)
	('DiTBlock_6', 'Dense_4', 'bias'): (1, 768)
	('DiTBlock_6', 'Dense_4', 'kernel'): (1, 768, 768)
	('DiTBlock_6', 'MlpBlock_0', 'Dense_0', 'bias'): (1, 3072)
	('DiTBlock_6', 'MlpBlock_0', 'Dense_0', 'kernel'): (1, 768, 3072)
	('DiTBlock_6', 'MlpBlock_0', 'Dense_1', 'bias'): (1, 768)
	('DiTBlock_6', 'MlpBlock_0', 'Dense_1', 'kernel'): (1, 3072, 768)
	('DiTBlock_7', 'Dense_0', 'bias'): (1, 4608)
	('DiTBlock_7', 'Dense_0', 'kernel'): (1, 768, 4608)
	('DiTBlock_7', 'Dense_1', 'bias'): (1, 768)
	('DiTBlock_7', 'Dense_1', 'kernel'): (1, 768, 768)
	('DiTBlock_7', 'Dense_2', 'bias'): (1, 768)
	('DiTBlock_7', 'Dense_2', 'kernel'): (1, 768, 768)
	('DiTBlock_7', 'Dense_3', 'bias'): (1, 768)
	('DiTBlock_7', 'Dense_3', 'kernel'): (1, 768, 768)
	('DiTBlock_7', 'Dense_4', 'bias'): (1, 768)
	('DiTBlock_7', 'Dense_4', 'kernel'): (1, 768, 768)
	('DiTBlock_7', 'MlpBlock_0', 'Dense_0', 'bias'): (1, 3072)
	('DiTBlock_7', 'MlpBlock_0', 'Dense_0', 'kernel'): (1, 768, 3072)
	('DiTBlock_7', 'MlpBlock_0', 'Dense_1', 'bias'): (1, 768)
	('DiTBlock_7', 'MlpBlock_0', 'Dense_1', 'kernel'): (1, 3072, 768)
	('DiTBlock_8', 'Dense_0', 'bias'): (1, 4608)
	('DiTBlock_8', 'Dense_0', 'kernel'): (1, 768, 4608)
	('DiTBlock_8', 'Dense_1', 'bias'): (1, 768)
	('DiTBlock_8', 'Dense_1', 'kernel'): (1, 768, 768)
	('DiTBlock_8', 'Dense_2', 'bias'): (1, 768)
	('DiTBlock_8', 'Dense_2', 'kernel'): (1, 768, 768)
	('DiTBlock_8', 'Dense_3', 'bias'): (1, 768)
	('DiTBlock_8', 'Dense_3', 'kernel'): (1, 768, 768)
	('DiTBlock_8', 'Dense_4', 'bias'): (1, 768)
	('DiTBlock_8', 'Dense_4', 'kernel'): (1, 768, 768)
	('DiTBlock_8', 'MlpBlock_0', 'Dense_0', 'bias'): (1, 3072)
	('DiTBlock_8', 'MlpBlock_0', 'Dense_0', 'kernel'): (1, 768, 3072)
	('DiTBlock_8', 'MlpBlock_0', 'Dense_1', 'bias'): (1, 768)
	('DiTBlock_8', 'MlpBlock_0', 'Dense_1', 'kernel'): (1, 3072, 768)
	('DiTBlock_9', 'Dense_0', 'bias'): (1, 4608)
	('DiTBlock_9', 'Dense_0', 'kernel'): (1, 768, 4608)
	('DiTBlock_9', 'Dense_1', 'bias'): (1, 768)
	('DiTBlock_9', 'Dense_1', 'kernel'): (1, 768, 768)
	('DiTBlock_9', 'Dense_2', 'bias'): (1, 768)
	('DiTBlock_9', 'Dense_2', 'kernel'): (1, 768, 768)
	('DiTBlock_9', 'Dense_3', 'bias'): (1, 768)
	('DiTBlock_9', 'Dense_3', 'kernel'): (1, 768, 768)
	('DiTBlock_9', 'Dense_4', 'bias'): (1, 768)
	('DiTBlock_9', 'Dense_4', 'kernel'): (1, 768, 768)
	('DiTBlock_9', 'MlpBlock_0', 'Dense_0', 'bias'): (1, 3072)
	('DiTBlock_9', 'MlpBlock_0', 'Dense_0', 'kernel'): (1, 768, 3072)
	('DiTBlock_9', 'MlpBlock_0', 'Dense_1', 'bias'): (1, 768)
	('DiTBlock_9', 'MlpBlock_0', 'Dense_1', 'kernel'): (1, 3072, 768)
	('Embed_0', 'embedding'): (1, 256, 1)
	('FinalLayer_0', 'Dense_0', 'bias'): (1, 1536)
	('FinalLayer_0', 'Dense_0', 'kernel'): (1, 768, 1536)
	('FinalLayer_0', 'Dense_1', 'bias'): (1, 16)
	('FinalLayer_0', 'Dense_1', 'kernel'): (1, 768, 16)
	('LabelEmbedder_0', 'Embed_0', 'embedding'): (1, 1001, 768)
	('PatchEmbed_0', 'Conv_0', 'bias'): (1, 768)
	('PatchEmbed_0', 'Conv_0', 'kernel'): (1, 2, 2, 4, 768)
	('TimestepEmbedder_0', 'Dense_0', 'bias'): (1, 768)
	('TimestepEmbedder_0', 'Dense_0', 'kernel'): (1, 256, 768)
	('TimestepEmbedder_0', 'Dense_1', 'bias'): (1, 768)
	('TimestepEmbedder_0', 'Dense_1', 'kernel'): (1, 768, 768)
	('TimestepEmbedder_1', 'Dense_0', 'bias'): (1, 768)
	('TimestepEmbedder_1', 'Dense_0', 'kernel'): (1, 256, 768)
	('TimestepEmbedder_1', 'Dense_1', 'bias'): (1, 768)
	('TimestepEmbedder_1', 'Dense_1', 'kernel'): (1, 768, 768)

	parameter shapes:
	('DiTBlock_0', 'Dense_0', 'bias'): (4608,)
	('DiTBlock_0', 'Dense_0', 'kernel'): (768, 4608)
	('DiTBlock_0', 'Dense_1', 'bias'): (768,)
	('DiTBlock_0', 'Dense_1', 'kernel'): (768, 768)
	('DiTBlock_0', 'Dense_2', 'bias'): (768,)
	('DiTBlock_0', 'Dense_2', 'kernel'): (768, 768)
	('DiTBlock_0', 'Dense_3', 'bias'): (768,)
	('DiTBlock_0', 'Dense_3', 'kernel'): (768, 768)
	('DiTBlock_0', 'Dense_4', 'bias'): (768,)
	('DiTBlock_0', 'Dense_4', 'kernel'): (768, 768)
	('DiTBlock_0', 'MlpBlock_0', 'Dense_0', 'bias'): (3072,)
	('DiTBlock_0', 'MlpBlock_0', 'Dense_0', 'kernel'): (768, 3072)
	('DiTBlock_0', 'MlpBlock_0', 'Dense_1', 'bias'): (768,)
	('DiTBlock_0', 'MlpBlock_0', 'Dense_1', 'kernel'): (3072, 768)
	('DiTBlock_1', 'Dense_0', 'bias'): (4608,)
	('DiTBlock_1', 'Dense_0', 'kernel'): (768, 4608)
	('DiTBlock_1', 'Dense_1', 'bias'): (768,)
	('DiTBlock_1', 'Dense_1', 'kernel'): (768, 768)
	('DiTBlock_1', 'Dense_2', 'bias'): (768,)
	('DiTBlock_1', 'Dense_2', 'kernel'): (768, 768)
	('DiTBlock_1', 'Dense_3', 'bias'): (768,)
	('DiTBlock_1', 'Dense_3', 'kernel'): (768, 768)
	('DiTBlock_1', 'Dense_4', 'bias'): (768,)
	('DiTBlock_1', 'Dense_4', 'kernel'): (768, 768)
	('DiTBlock_1', 'MlpBlock_0', 'Dense_0', 'bias'): (3072,)
	('DiTBlock_1', 'MlpBlock_0', 'Dense_0', 'kernel'): (768, 3072)
	('DiTBlock_1', 'MlpBlock_0', 'Dense_1', 'bias'): (768,)
	('DiTBlock_1', 'MlpBlock_0', 'Dense_1', 'kernel'): (3072, 768)
	('DiTBlock_10', 'Dense_0', 'bias'): (4608,)
	('DiTBlock_10', 'Dense_0', 'kernel'): (768, 4608)
	('DiTBlock_10', 'Dense_1', 'bias'): (768,)
	('DiTBlock_10', 'Dense_1', 'kernel'): (768, 768)
	('DiTBlock_10', 'Dense_2', 'bias'): (768,)
	('DiTBlock_10', 'Dense_2', 'kernel'): (768, 768)
	('DiTBlock_10', 'Dense_3', 'bias'): (768,)
	('DiTBlock_10', 'Dense_3', 'kernel'): (768, 768)
	('DiTBlock_10', 'Dense_4', 'bias'): (768,)
	('DiTBlock_10', 'Dense_4', 'kernel'): (768, 768)
	('DiTBlock_10', 'MlpBlock_0', 'Dense_0', 'bias'): (3072,)
	('DiTBlock_10', 'MlpBlock_0', 'Dense_0', 'kernel'): (768, 3072)
	('DiTBlock_10', 'MlpBlock_0', 'Dense_1', 'bias'): (768,)
	('DiTBlock_10', 'MlpBlock_0', 'Dense_1', 'kernel'): (3072, 768)
	('DiTBlock_11', 'Dense_0', 'bias'): (4608,)
	('DiTBlock_11', 'Dense_0', 'kernel'): (768, 4608)
	('DiTBlock_11', 'Dense_1', 'bias'): (768,)
	('DiTBlock_11', 'Dense_1', 'kernel'): (768, 768)
	('DiTBlock_11', 'Dense_2', 'bias'): (768,)
	('DiTBlock_11', 'Dense_2', 'kernel'): (768, 768)
	('DiTBlock_11', 'Dense_3', 'bias'): (768,)
	('DiTBlock_11', 'Dense_3', 'kernel'): (768, 768)
	('DiTBlock_11', 'Dense_4', 'bias'): (768,)
	('DiTBlock_11', 'Dense_4', 'kernel'): (768, 768)
	('DiTBlock_11', 'MlpBlock_0', 'Dense_0', 'bias'): (3072,)
	('DiTBlock_11', 'MlpBlock_0', 'Dense_0', 'kernel'): (768, 3072)
	('DiTBlock_11', 'MlpBlock_0', 'Dense_1', 'bias'): (768,)
	('DiTBlock_11', 'MlpBlock_0', 'Dense_1', 'kernel'): (3072, 768)
	('DiTBlock_2', 'Dense_0', 'bias'): (4608,)
	('DiTBlock_2', 'Dense_0', 'kernel'): (768, 4608)
	('DiTBlock_2', 'Dense_1', 'bias'): (768,)
	('DiTBlock_2', 'Dense_1', 'kernel'): (768, 768)
	('DiTBlock_2', 'Dense_2', 'bias'): (768,)
	('DiTBlock_2', 'Dense_2', 'kernel'): (768, 768)
	('DiTBlock_2', 'Dense_3', 'bias'): (768,)
	('DiTBlock_2', 'Dense_3', 'kernel'): (768, 768)
	('DiTBlock_2', 'Dense_4', 'bias'): (768,)
	('DiTBlock_2', 'Dense_4', 'kernel'): (768, 768)
	('DiTBlock_2', 'MlpBlock_0', 'Dense_0', 'bias'): (3072,)
	('DiTBlock_2', 'MlpBlock_0', 'Dense_0', 'kernel'): (768, 3072)
	('DiTBlock_2', 'MlpBlock_0', 'Dense_1', 'bias'): (768,)
	('DiTBlock_2', 'MlpBlock_0', 'Dense_1', 'kernel'): (3072, 768)
	('DiTBlock_3', 'Dense_0', 'bias'): (4608,)
	('DiTBlock_3', 'Dense_0', 'kernel'): (768, 4608)
	('DiTBlock_3', 'Dense_1', 'bias'): (768,)
	('DiTBlock_3', 'Dense_1', 'kernel'): (768, 768)
	('DiTBlock_3', 'Dense_2', 'bias'): (768,)
	('DiTBlock_3', 'Dense_2', 'kernel'): (768, 768)
	('DiTBlock_3', 'Dense_3', 'bias'): (768,)
	('DiTBlock_3', 'Dense_3', 'kernel'): (768, 768)
	('DiTBlock_3', 'Dense_4', 'bias'): (768,)
	('DiTBlock_3', 'Dense_4', 'kernel'): (768, 768)
	('DiTBlock_3', 'MlpBlock_0', 'Dense_0', 'bias'): (3072,)
	('DiTBlock_3', 'MlpBlock_0', 'Dense_0', 'kernel'): (768, 3072)
	('DiTBlock_3', 'MlpBlock_0', 'Dense_1', 'bias'): (768,)
	('DiTBlock_3', 'MlpBlock_0', 'Dense_1', 'kernel'): (3072, 768)
	('DiTBlock_4', 'Dense_0', 'bias'): (4608,)
	('DiTBlock_4', 'Dense_0', 'kernel'): (768, 4608)
	('DiTBlock_4', 'Dense_1', 'bias'): (768,)
	('DiTBlock_4', 'Dense_1', 'kernel'): (768, 768)
	('DiTBlock_4', 'Dense_2', 'bias'): (768,)
	('DiTBlock_4', 'Dense_2', 'kernel'): (768, 768)
	('DiTBlock_4', 'Dense_3', 'bias'): (768,)
	('DiTBlock_4', 'Dense_3', 'kernel'): (768, 768)
	('DiTBlock_4', 'Dense_4', 'bias'): (768,)
	('DiTBlock_4', 'Dense_4', 'kernel'): (768, 768)
	('DiTBlock_4', 'MlpBlock_0', 'Dense_0', 'bias'): (3072,)
	('DiTBlock_4', 'MlpBlock_0', 'Dense_0', 'kernel'): (768, 3072)
	('DiTBlock_4', 'MlpBlock_0', 'Dense_1', 'bias'): (768,)
	('DiTBlock_4', 'MlpBlock_0', 'Dense_1', 'kernel'): (3072, 768)
	('DiTBlock_5', 'Dense_0', 'bias'): (4608,)
	('DiTBlock_5', 'Dense_0', 'kernel'): (768, 4608)
	('DiTBlock_5', 'Dense_1', 'bias'): (768,)
	('DiTBlock_5', 'Dense_1', 'kernel'): (768, 768)
	('DiTBlock_5', 'Dense_2', 'bias'): (768,)
	('DiTBlock_5', 'Dense_2', 'kernel'): (768, 768)
	('DiTBlock_5', 'Dense_3', 'bias'): (768,)
	('DiTBlock_5', 'Dense_3', 'kernel'): (768, 768)
	('DiTBlock_5', 'Dense_4', 'bias'): (768,)
	('DiTBlock_5', 'Dense_4', 'kernel'): (768, 768)
	('DiTBlock_5', 'MlpBlock_0', 'Dense_0', 'bias'): (3072,)
	('DiTBlock_5', 'MlpBlock_0', 'Dense_0', 'kernel'): (768, 3072)
	('DiTBlock_5', 'MlpBlock_0', 'Dense_1', 'bias'): (768,)
	('DiTBlock_5', 'MlpBlock_0', 'Dense_1', 'kernel'): (3072, 768)
	('DiTBlock_6', 'Dense_0', 'bias'): (4608,)
	('DiTBlock_6', 'Dense_0', 'kernel'): (768, 4608)
	('DiTBlock_6', 'Dense_1', 'bias'): (768,)
	('DiTBlock_6', 'Dense_1', 'kernel'): (768, 768)
	('DiTBlock_6', 'Dense_2', 'bias'): (768,)
	('DiTBlock_6', 'Dense_2', 'kernel'): (768, 768)
	('DiTBlock_6', 'Dense_3', 'bias'): (768,)
	('DiTBlock_6', 'Dense_3', 'kernel'): (768, 768)
	('DiTBlock_6', 'Dense_4', 'bias'): (768,)
	('DiTBlock_6', 'Dense_4', 'kernel'): (768, 768)
	('DiTBlock_6', 'MlpBlock_0', 'Dense_0', 'bias'): (3072,)
	('DiTBlock_6', 'MlpBlock_0', 'Dense_0', 'kernel'): (768, 3072)
	('DiTBlock_6', 'MlpBlock_0', 'Dense_1', 'bias'): (768,)
	('DiTBlock_6', 'MlpBlock_0', 'Dense_1', 'kernel'): (3072, 768)
	('DiTBlock_7', 'Dense_0', 'bias'): (4608,)
	('DiTBlock_7', 'Dense_0', 'kernel'): (768, 4608)
	('DiTBlock_7', 'Dense_1', 'bias'): (768,)
	('DiTBlock_7', 'Dense_1', 'kernel'): (768, 768)
	('DiTBlock_7', 'Dense_2', 'bias'): (768,)
	('DiTBlock_7', 'Dense_2', 'kernel'): (768, 768)
	('DiTBlock_7', 'Dense_3', 'bias'): (768,)
	('DiTBlock_7', 'Dense_3', 'kernel'): (768, 768)
	('DiTBlock_7', 'Dense_4', 'bias'): (768,)
	('DiTBlock_7', 'Dense_4', 'kernel'): (768, 768)
	('DiTBlock_7', 'MlpBlock_0', 'Dense_0', 'bias'): (3072,)
	('DiTBlock_7', 'MlpBlock_0', 'Dense_0', 'kernel'): (768, 3072)
	('DiTBlock_7', 'MlpBlock_0', 'Dense_1', 'bias'): (768,)
	('DiTBlock_7', 'MlpBlock_0', 'Dense_1', 'kernel'): (3072, 768)
	('DiTBlock_8', 'Dense_0', 'bias'): (4608,)
	('DiTBlock_8', 'Dense_0', 'kernel'): (768, 4608)
	('DiTBlock_8', 'Dense_1', 'bias'): (768,)
	('DiTBlock_8', 'Dense_1', 'kernel'): (768, 768)
	('DiTBlock_8', 'Dense_2', 'bias'): (768,)
	('DiTBlock_8', 'Dense_2', 'kernel'): (768, 768)
	('DiTBlock_8', 'Dense_3', 'bias'): (768,)
	('DiTBlock_8', 'Dense_3', 'kernel'): (768, 768)
	('DiTBlock_8', 'Dense_4', 'bias'): (768,)
	('DiTBlock_8', 'Dense_4', 'kernel'): (768, 768)
	('DiTBlock_8', 'MlpBlock_0', 'Dense_0', 'bias'): (3072,)
	('DiTBlock_8', 'MlpBlock_0', 'Dense_0', 'kernel'): (768, 3072)
	('DiTBlock_8', 'MlpBlock_0', 'Dense_1', 'bias'): (768,)
	('DiTBlock_8', 'MlpBlock_0', 'Dense_1', 'kernel'): (3072, 768)
	('DiTBlock_9', 'Dense_0', 'bias'): (4608,)
	('DiTBlock_9', 'Dense_0', 'kernel'): (768, 4608)
	('DiTBlock_9', 'Dense_1', 'bias'): (768,)
	('DiTBlock_9', 'Dense_1', 'kernel'): (768, 768)
	('DiTBlock_9', 'Dense_2', 'bias'): (768,)
	('DiTBlock_9', 'Dense_2', 'kernel'): (768, 768)
	('DiTBlock_9', 'Dense_3', 'bias'): (768,)
	('DiTBlock_9', 'Dense_3', 'kernel'): (768, 768)
	('DiTBlock_9', 'Dense_4', 'bias'): (768,)
	('DiTBlock_9', 'Dense_4', 'kernel'): (768, 768)
	('DiTBlock_9', 'MlpBlock_0', 'Dense_0', 'bias'): (3072,)
	('DiTBlock_9', 'MlpBlock_0', 'Dense_0', 'kernel'): (768, 3072)
	('DiTBlock_9', 'MlpBlock_0', 'Dense_1', 'bias'): (768,)
	('DiTBlock_9', 'MlpBlock_0', 'Dense_1', 'kernel'): (3072, 768)
	('Embed_0', 'embedding'): (256, 1)
	('FinalLayer_0', 'Dense_0', 'bias'): (1536,)
	('FinalLayer_0', 'Dense_0', 'kernel'): (768, 1536)
	('FinalLayer_0', 'Dense_1', 'bias'): (16,)
	('FinalLayer_0', 'Dense_1', 'kernel'): (768, 16)
	('LabelEmbedder_0', 'Embed_0', 'embedding'): (1001, 768)
	('PatchEmbed_0', 'Conv_0', 'bias'): (768,)
	('PatchEmbed_0', 'Conv_0', 'kernel'): (2, 2, 4, 768)
	('TimestepEmbedder_0', 'Dense_0', 'bias'): (768,)
	('TimestepEmbedder_0', 'Dense_0', 'kernel'): (256, 768)
	('TimestepEmbedder_0', 'Dense_1', 'bias'): (768,)
	('TimestepEmbedder_0', 'Dense_1', 'kernel'): (768, 768)
	('TimestepEmbedder_1', 'Dense_0', 'bias'): (768,)
	('TimestepEmbedder_1', 'Dense_0', 'kernel'): (256, 768)
	('TimestepEmbedder_1', 'Dense_1', 'bias'): (768,)
	('TimestepEmbedder_1', 'Dense_1', 'kernel'): (768, 768)
	┌────────────────────────────────────────────────┐
	│ │
	│ │
	│ │
	│ │
	│ TPU 0,1,2,3 │
	│ │
	│ │
	│ │
	│ │
	└────────────────────────────────────────────────┘
	┌─────────────────────────────────────────────────────────────────────────┐
	│ │
	│ │
	│ │
	│ │
	│ TPU 0,1,2,3 │
	│ │
	│ │
	│ │
	│ │
	└─────────────────────────────────────────────────────────────────────────┘
	doing the else
	(512, 256, 256, 3)
	encode image shape (128, 256, 256, 3)
	Initializing encoder.
	Incoming encoder shape (128, 256, 256, 3)
	Encoder layer (128, 256, 256, 128)
	doing downsample
	Encoder layer (128, 128, 128, 128)
	doing downsample
	Encoder layer (128, 64, 64, 256)
	doing downsample
	Encoder layer (128, 32, 32, 512)
	Encoder layer (128, 32, 32, 512)
	Encoder layer final (128, 32, 32, 512)
	Encoder layer final (128, 32, 32, 512)
	Final embeddings are size (128, 32, 32, 8)
	After quant (128, 32, 32, 4)
	Calc FID for CFG 1.0 and denoise_timesteps 128
	DiT: Input of shape (512, 32, 32, 4) dtype float32
	DiT: After patch embed, shape is (512, 256, 768) dtype bfloat16
	DiT: Patch Embed of shape (512, 256, 768) dtype bfloat16
	DiT: Conditioning of shape (512, 768) dtype float32
	z_vectors shape (128, 32, 32, 4)
	Decoder incoming shape (128, 32, 32, 4)
	Decoder input (128, 32, 32, 512)
	Mid Block Decoder layer (128, 32, 32, 512)
	Mid Block Decoder layer (128, 32, 32, 512)
	Decoder layer (128, 64, 64, 512)
	Decoder layer (128, 128, 128, 512)
	Decoder layer (128, 256, 256, 256)
	Decoder layer (128, 256, 256, 128)
	FID is 27.316314697265625
	(512, 256, 256, 3)
	Calc FID for CFG 1.0 and denoise_timesteps 64
	DiT: Input of shape (512, 32, 32, 4) dtype float32
	DiT: After patch embed, shape is (512, 256, 768) dtype bfloat16
	DiT: Patch Embed of shape (512, 256, 768) dtype bfloat16
	DiT: Conditioning of shape (512, 768) dtype float32
	FID is 27.868749618530273
	(512, 256, 256, 3)
	Calc FID for CFG 1.0 and denoise_timesteps 32
	DiT: Input of shape (512, 32, 32, 4) dtype float32
	DiT: After patch embed, shape is (512, 256, 768) dtype bfloat16
	DiT: Patch Embed of shape (512, 256, 768) dtype bfloat16
	DiT: Conditioning of shape (512, 768) dtype float32
	FID is 29.53413963317871
	(512, 256, 256, 3)
	Calc FID for CFG 1.0 and denoise_timesteps 16
	DiT: Input of shape (512, 32, 32, 4) dtype float32
	DiT: After patch embed, shape is (512, 256, 768) dtype bfloat16
	DiT: Patch Embed of shape (512, 256, 768) dtype bfloat16
	DiT: Conditioning of shape (512, 768) dtype float32
	FID is 34.38279724121094
	(512, 256, 256, 3)
	Calc FID for CFG 1.0 and denoise_timesteps 8
	DiT: Input of shape (512, 32, 32, 4) dtype float32
	DiT: After patch embed, shape is (512, 256, 768) dtype bfloat16
	DiT: Patch Embed of shape (512, 256, 768) dtype bfloat16
	DiT: Conditioning of shape (512, 768) dtype float32
	FID is 50.080726623535156
	(512, 256, 256, 3)
	Calc FID for CFG 1.0 and denoise_timesteps 4
	DiT: Input of shape (512, 32, 32, 4) dtype float32
	DiT: After patch embed, shape is (512, 256, 768) dtype bfloat16
	DiT: Patch Embed of shape (512, 256, 768) dtype bfloat16
	DiT: Conditioning of shape (512, 768) dtype float32
	FID is 111.82022094726562
	(512, 256, 256, 3)
	Calc FID for CFG 1.0 and denoise_timesteps 2
	DiT: Input of shape (512, 32, 32, 4) dtype float32
	DiT: After patch embed, shape is (512, 256, 768) dtype bfloat16
	DiT: Patch Embed of shape (512, 256, 768) dtype bfloat16
	DiT: Conditioning of shape (512, 768) dtype float32
	FID is 253.1292724609375
	(512, 256, 256, 3)
	Calc FID for CFG 1.0 and denoise_timesteps 1
	DiT: Input of shape (512, 32, 32, 4) dtype float32
	DiT: After patch embed, shape is (512, 256, 768) dtype bfloat16
	DiT: Patch Embed of shape (512, 256, 768) dtype bfloat16
	DiT: Conditioning of shape (512, 768) dtype float32
	FID is 327.2395935058594
	(512, 256, 256, 3)
	Calc FID for CFG 1.25 and denoise_timesteps 128
	DiT: Input of shape (512, 32, 32, 4) dtype float32
	DiT: After patch embed, shape is (512, 256, 768) dtype bfloat16
	DiT: Patch Embed of shape (512, 256, 768) dtype bfloat16
	DiT: Conditioning of shape (512, 768) dtype float32
	FID is 15.7363862991333
	(512, 256, 256, 3)
	Calc FID for CFG 1.25 and denoise_timesteps 64
	DiT: Input of shape (512, 32, 32, 4) dtype float32
	DiT: After patch embed, shape is (512, 256, 768) dtype bfloat16
	DiT: Patch Embed of shape (512, 256, 768) dtype bfloat16
	DiT: Conditioning of shape (512, 768) dtype float32
	FID is 16.131431579589844
	(512, 256, 256, 3)
	Calc FID for CFG 1.25 and denoise_timesteps 32
	DiT: Input of shape (512, 32, 32, 4) dtype float32
	DiT: After patch embed, shape is (512, 256, 768) dtype bfloat16
	DiT: Patch Embed of shape (512, 256, 768) dtype bfloat16
	DiT: Conditioning of shape (512, 768) dtype float32
	FID is 17.277145385742188
	(512, 256, 256, 3)
	Calc FID for CFG 1.25 and denoise_timesteps 16
	DiT: Input of shape (512, 32, 32, 4) dtype float32
	DiT: After patch embed, shape is (512, 256, 768) dtype bfloat16
	DiT: Patch Embed of shape (512, 256, 768) dtype bfloat16
	DiT: Conditioning of shape (512, 768) dtype float32
	FID is 20.931257247924805
	(512, 256, 256, 3)
	Calc FID for CFG 1.25 and denoise_timesteps 8
	DiT: Input of shape (512, 32, 32, 4) dtype float32
	DiT: After patch embed, shape is (512, 256, 768) dtype bfloat16
	DiT: Patch Embed of shape (512, 256, 768) dtype bfloat16
	DiT: Conditioning of shape (512, 768) dtype float32
	FID is 33.693328857421875
	(512, 256, 256, 3)
	Calc FID for CFG 1.25 and denoise_timesteps 4
	DiT: Input of shape (512, 32, 32, 4) dtype float32
	DiT: After patch embed, shape is (512, 256, 768) dtype bfloat16
	DiT: Patch Embed of shape (512, 256, 768) dtype bfloat16
	DiT: Conditioning of shape (512, 768) dtype float32
	FID is 88.24979400634766
	(512, 256, 256, 3)
	Calc FID for CFG 1.25 and denoise_timesteps 2
	DiT: Input of shape (512, 32, 32, 4) dtype float32
	DiT: After patch embed, shape is (512, 256, 768) dtype bfloat16
	DiT: Patch Embed of shape (512, 256, 768) dtype bfloat16
	DiT: Conditioning of shape (512, 768) dtype float32
	FID is 243.46041870117188
	(512, 256, 256, 3)
	Calc FID for CFG 1.25 and denoise_timesteps 1
	DiT: Input of shape (512, 32, 32, 4) dtype float32
	DiT: After patch embed, shape is (512, 256, 768) dtype bfloat16
	DiT: Patch Embed of shape (512, 256, 768) dtype bfloat16
	DiT: Conditioning of shape (512, 768) dtype float32
	FID is 311.65679931640625
	(512, 256, 256, 3)
	Calc FID for CFG 1.5 and denoise_timesteps 128
	DiT: Input of shape (512, 32, 32, 4) dtype float32
	DiT: After patch embed, shape is (512, 256, 768) dtype bfloat16
	DiT: Patch Embed of shape (512, 256, 768) dtype bfloat16
	DiT: Conditioning of shape (512, 768) dtype float32
	FID is 9.977910995483398
	(512, 256, 256, 3)
	Calc FID for CFG 1.5 and denoise_timesteps 64
	DiT: Input of shape (512, 32, 32, 4) dtype float32
	DiT: After patch embed, shape is (512, 256, 768) dtype bfloat16
	DiT: Patch Embed of shape (512, 256, 768) dtype bfloat16
	DiT: Conditioning of shape (512, 768) dtype float32
	FID is 10.220792770385742
	(512, 256, 256, 3)
	Calc FID for CFG 1.5 and denoise_timesteps 32
	DiT: Input of shape (512, 32, 32, 4) dtype float32
	DiT: After patch embed, shape is (512, 256, 768) dtype bfloat16
	DiT: Patch Embed of shape (512, 256, 768) dtype bfloat16
	DiT: Conditioning of shape (512, 768) dtype float32
	FID is 10.951236724853516
	(512, 256, 256, 3)
	Calc FID for CFG 1.5 and denoise_timesteps 16
	DiT: Input of shape (512, 32, 32, 4) dtype float32
	DiT: After patch embed, shape is (512, 256, 768) dtype bfloat16
	DiT: Patch Embed of shape (512, 256, 768) dtype bfloat16
	DiT: Conditioning of shape (512, 768) dtype float32
	FID is 13.484875679016113
	(512, 256, 256, 3)
	Calc FID for CFG 1.5 and denoise_timesteps 8
	DiT: Input of shape (512, 32, 32, 4) dtype float32
	DiT: After patch embed, shape is (512, 256, 768) dtype bfloat16
	DiT: Patch Embed of shape (512, 256, 768) dtype bfloat16
	DiT: Conditioning of shape (512, 768) dtype float32
	FID is 23.276193618774414
	(512, 256, 256, 3)
	Calc FID for CFG 1.5 and denoise_timesteps 4
	DiT: Input of shape (512, 32, 32, 4) dtype float32
	DiT: After patch embed, shape is (512, 256, 768) dtype bfloat16
	DiT: Patch Embed of shape (512, 256, 768) dtype bfloat16
	DiT: Conditioning of shape (512, 768) dtype float32
	FID is 69.98013305664062
	(512, 256, 256, 3)
	Calc FID for CFG 1.5 and denoise_timesteps 2
	DiT: Input of shape (512, 32, 32, 4) dtype float32
	DiT: After patch embed, shape is (512, 256, 768) dtype bfloat16
	DiT: Patch Embed of shape (512, 256, 768) dtype bfloat16
	DiT: Conditioning of shape (512, 768) dtype float32
	FID is 235.39779663085938
	(512, 256, 256, 3)
	Calc FID for CFG 1.5 and denoise_timesteps 1
	DiT: Input of shape (512, 32, 32, 4) dtype float32
	DiT: After patch embed, shape is (512, 256, 768) dtype bfloat16
	DiT: Patch Embed of shape (512, 256, 768) dtype bfloat16
	DiT: Conditioning of shape (512, 768) dtype float32
	FID is 300.54022216796875
	(512, 256, 256, 3)
	Calc FID for CFG 1.75 and denoise_timesteps 128
	DiT: Input of shape (512, 32, 32, 4) dtype float32
	DiT: After patch embed, shape is (512, 256, 768) dtype bfloat16
	DiT: Patch Embed of shape (512, 256, 768) dtype bfloat16
	DiT: Conditioning of shape (512, 768) dtype float32
	FID is 7.69427490234375
	(512, 256, 256, 3)
	Calc FID for CFG 1.75 and denoise_timesteps 64
	DiT: Input of shape (512, 32, 32, 4) dtype float32
	DiT: After patch embed, shape is (512, 256, 768) dtype bfloat16
	DiT: Patch Embed of shape (512, 256, 768) dtype bfloat16
	DiT: Conditioning of shape (512, 768) dtype float32
	FID is 7.823149681091309
	(512, 256, 256, 3)
	Calc FID for CFG 1.75 and denoise_timesteps 32
	DiT: Input of shape (512, 32, 32, 4) dtype float32
	DiT: After patch embed, shape is (512, 256, 768) dtype bfloat16
	DiT: Patch Embed of shape (512, 256, 768) dtype bfloat16
	DiT: Conditioning of shape (512, 768) dtype float32
	FID is 8.250865936279297
	(512, 256, 256, 3)
	Calc FID for CFG 1.75 and denoise_timesteps 16
	DiT: Input of shape (512, 32, 32, 4) dtype float32
	DiT: After patch embed, shape is (512, 256, 768) dtype bfloat16
	DiT: Patch Embed of shape (512, 256, 768) dtype bfloat16
	DiT: Conditioning of shape (512, 768) dtype float32
	FID is 9.930144309997559
	(512, 256, 256, 3)
	Calc FID for CFG 1.75 and denoise_timesteps 8
	DiT: Input of shape (512, 32, 32, 4) dtype float32
	DiT: After patch embed, shape is (512, 256, 768) dtype bfloat16
	DiT: Patch Embed of shape (512, 256, 768) dtype bfloat16
	DiT: Conditioning of shape (512, 768) dtype float32
	FID is 17.071447372436523
	(512, 256, 256, 3)
	Calc FID for CFG 1.75 and denoise_timesteps 4
	DiT: Input of shape (512, 32, 32, 4) dtype float32
	DiT: After patch embed, shape is (512, 256, 768) dtype bfloat16
	DiT: Patch Embed of shape (512, 256, 768) dtype bfloat16
	DiT: Conditioning of shape (512, 768) dtype float32
	FID is 56.25336456298828
	(512, 256, 256, 3)
	Calc FID for CFG 1.75 and denoise_timesteps 2
	DiT: Input of shape (512, 32, 32, 4) dtype float32
	DiT: After patch embed, shape is (512, 256, 768) dtype bfloat16
	DiT: Patch Embed of shape (512, 256, 768) dtype bfloat16
	DiT: Conditioning of shape (512, 768) dtype float32
	FID is 228.31434631347656
	(512, 256, 256, 3)
	Calc FID for CFG 1.75 and denoise_timesteps 1
	DiT: Input of shape (512, 32, 32, 4) dtype float32
	DiT: After patch embed, shape is (512, 256, 768) dtype bfloat16
	DiT: Patch Embed of shape (512, 256, 768) dtype bfloat16
	DiT: Conditioning of shape (512, 768) dtype float32
	FID is 292.3569030761719
	(512, 256, 256, 3)
	Calc FID for CFG 2.0 and denoise_timesteps 128
	DiT: Input of shape (512, 32, 32, 4) dtype float32
	DiT: After patch embed, shape is (512, 256, 768) dtype bfloat16
	DiT: Patch Embed of shape (512, 256, 768) dtype bfloat16
	DiT: Conditioning of shape (512, 768) dtype float32
	FID is 7.303752422332764
	(512, 256, 256, 3)
	Calc FID for CFG 2.0 and denoise_timesteps 64
	DiT: Input of shape (512, 32, 32, 4) dtype float32
	DiT: After patch embed, shape is (512, 256, 768) dtype bfloat16
	DiT: Patch Embed of shape (512, 256, 768) dtype bfloat16
	DiT: Conditioning of shape (512, 768) dtype float32
	FID is 7.367008209228516
	(512, 256, 256, 3)
	Calc FID for CFG 2.0 and denoise_timesteps 32
	DiT: Input of shape (512, 32, 32, 4) dtype float32
	DiT: After patch embed, shape is (512, 256, 768) dtype bfloat16
	DiT: Patch Embed of shape (512, 256, 768) dtype bfloat16
	DiT: Conditioning of shape (512, 768) dtype float32
	FID is 7.5981035232543945
	(512, 256, 256, 3)
	Calc FID for CFG 2.0 and denoise_timesteps 16
	DiT: Input of shape (512, 32, 32, 4) dtype float32
	DiT: After patch embed, shape is (512, 256, 768) dtype bfloat16
	DiT: Patch Embed of shape (512, 256, 768) dtype bfloat16
	DiT: Conditioning of shape (512, 768) dtype float32
	FID is 8.63364315032959
	(512, 256, 256, 3)
	Calc FID for CFG 2.0 and denoise_timesteps 8
	DiT: Input of shape (512, 32, 32, 4) dtype float32
	DiT: After patch embed, shape is (512, 256, 768) dtype bfloat16
	DiT: Patch Embed of shape (512, 256, 768) dtype bfloat16
	DiT: Conditioning of shape (512, 768) dtype float32
	FID is 13.671175003051758
	(512, 256, 256, 3)
	Calc FID for CFG 2.0 and denoise_timesteps 4
	DiT: Input of shape (512, 32, 32, 4) dtype float32
	DiT: After patch embed, shape is (512, 256, 768) dtype bfloat16
	DiT: Patch Embed of shape (512, 256, 768) dtype bfloat16
	DiT: Conditioning of shape (512, 768) dtype float32
	FID is 46.0537109375
	(512, 256, 256, 3)
	Calc FID for CFG 2.0 and denoise_timesteps 2
	DiT: Input of shape (512, 32, 32, 4) dtype float32
	DiT: After patch embed, shape is (512, 256, 768) dtype bfloat16
	DiT: Patch Embed of shape (512, 256, 768) dtype bfloat16
	DiT: Conditioning of shape (512, 768) dtype float32
	FID is 222.12191772460938
	(512, 256, 256, 3)
	Calc FID for CFG 2.0 and denoise_timesteps 1
	DiT: Input of shape (512, 32, 32, 4) dtype float32
	DiT: After patch embed, shape is (512, 256, 768) dtype bfloat16
	DiT: Patch Embed of shape (512, 256, 768) dtype bfloat16
	DiT: Conditioning of shape (512, 768) dtype float32
	FID is 285.9088134765625
	(512, 256, 256, 3)
	Calc FID for CFG 2.25 and denoise_timesteps 128
	DiT: Input of shape (512, 32, 32, 4) dtype float32
	DiT: After patch embed, shape is (512, 256, 768) dtype bfloat16
	DiT: Patch Embed of shape (512, 256, 768) dtype bfloat16
	DiT: Conditioning of shape (512, 768) dtype float32
	FID is 7.90061092376709
	(512, 256, 256, 3)
	Calc FID for CFG 2.25 and denoise_timesteps 64
	DiT: Input of shape (512, 32, 32, 4) dtype float32
	DiT: After patch embed, shape is (512, 256, 768) dtype bfloat16
	DiT: Patch Embed of shape (512, 256, 768) dtype bfloat16
	DiT: Conditioning of shape (512, 768) dtype float32
	FID is 7.931853771209717
	(512, 256, 256, 3)
	Calc FID for CFG 2.25 and denoise_timesteps 32
	DiT: Input of shape (512, 32, 32, 4) dtype float32
	DiT: After patch embed, shape is (512, 256, 768) dtype bfloat16
	DiT: Patch Embed of shape (512, 256, 768) dtype bfloat16
	DiT: Conditioning of shape (512, 768) dtype float32
	FID is 8.034148216247559
	(512, 256, 256, 3)
	Calc FID for CFG 2.25 and denoise_timesteps 16
	DiT: Input of shape (512, 32, 32, 4) dtype float32
	DiT: After patch embed, shape is (512, 256, 768) dtype bfloat16
	DiT: Patch Embed of shape (512, 256, 768) dtype bfloat16
	DiT: Conditioning of shape (512, 768) dtype float32
	FID is 8.618682861328125
	(512, 256, 256, 3)
	Calc FID for CFG 2.25 and denoise_timesteps 8
	DiT: Input of shape (512, 32, 32, 4) dtype float32
	DiT: After patch embed, shape is (512, 256, 768) dtype bfloat16
	DiT: Patch Embed of shape (512, 256, 768) dtype bfloat16
	DiT: Conditioning of shape (512, 768) dtype float32
	FID is 12.026784896850586
	(512, 256, 256, 3)
	Calc FID for CFG 2.25 and denoise_timesteps 4
	DiT: Input of shape (512, 32, 32, 4) dtype float32
	DiT: After patch embed, shape is (512, 256, 768) dtype bfloat16
	DiT: Patch Embed of shape (512, 256, 768) dtype bfloat16
	DiT: Conditioning of shape (512, 768) dtype float32
	FID is 38.549720764160156
	(512, 256, 256, 3)
	Calc FID for CFG 2.25 and denoise_timesteps 2
	DiT: Input of shape (512, 32, 32, 4) dtype float32
	DiT: After patch embed, shape is (512, 256, 768) dtype bfloat16
	DiT: Patch Embed of shape (512, 256, 768) dtype bfloat16
	DiT: Conditioning of shape (512, 768) dtype float32
	FID is 216.67861938476562
	(512, 256, 256, 3)
	Calc FID for CFG 2.25 and denoise_timesteps 1
	DiT: Input of shape (512, 32, 32, 4) dtype float32
	DiT: After patch embed, shape is (512, 256, 768) dtype bfloat16
	DiT: Patch Embed of shape (512, 256, 768) dtype bfloat16
	DiT: Conditioning of shape (512, 768) dtype float32
	FID is 280.46441650390625
	(512, 256, 256, 3)
	Calc FID for CFG 2.5 and denoise_timesteps 128
	DiT: Input of shape (512, 32, 32, 4) dtype float32
	DiT: After patch embed, shape is (512, 256, 768) dtype bfloat16
	DiT: Patch Embed of shape (512, 256, 768) dtype bfloat16
	DiT: Conditioning of shape (512, 768) dtype float32
	FID is 8.945230484008789
	(512, 256, 256, 3)
	Calc FID for CFG 2.5 and denoise_timesteps 64
	DiT: Input of shape (512, 32, 32, 4) dtype float32
	DiT: After patch embed, shape is (512, 256, 768) dtype bfloat16
	DiT: Patch Embed of shape (512, 256, 768) dtype bfloat16
	DiT: Conditioning of shape (512, 768) dtype float32
	FID is 8.924515724182129
	(512, 256, 256, 3)
	Calc FID for CFG 2.5 and denoise_timesteps 32
	DiT: Input of shape (512, 32, 32, 4) dtype float32
	DiT: After patch embed, shape is (512, 256, 768) dtype bfloat16
	DiT: Patch Embed of shape (512, 256, 768) dtype bfloat16
	DiT: Conditioning of shape (512, 768) dtype float32
	FID is 8.97061824798584
	(512, 256, 256, 3)
	Calc FID for CFG 2.5 and denoise_timesteps 16
	DiT: Input of shape (512, 32, 32, 4) dtype float32
	DiT: After patch embed, shape is (512, 256, 768) dtype bfloat16
	DiT: Patch Embed of shape (512, 256, 768) dtype bfloat16
	DiT: Conditioning of shape (512, 768) dtype float32
	FID is 9.26997184753418
	(512, 256, 256, 3)
	Calc FID for CFG 2.5 and denoise_timesteps 8
	DiT: Input of shape (512, 32, 32, 4) dtype float32
	DiT: After patch embed, shape is (512, 256, 768) dtype bfloat16
	DiT: Patch Embed of shape (512, 256, 768) dtype bfloat16
	DiT: Conditioning of shape (512, 768) dtype float32
	FID is 11.45376205444336
	(512, 256, 256, 3)
	Calc FID for CFG 2.5 and denoise_timesteps 4
	DiT: Input of shape (512, 32, 32, 4) dtype float32
	DiT: After patch embed, shape is (512, 256, 768) dtype bfloat16
	DiT: Patch Embed of shape (512, 256, 768) dtype bfloat16
	DiT: Conditioning of shape (512, 768) dtype float32
	FID is 33.000457763671875
	(512, 256, 256, 3)
	Calc FID for CFG 2.5 and denoise_timesteps 2
	DiT: Input of shape (512, 32, 32, 4) dtype float32
	DiT: After patch embed, shape is (512, 256, 768) dtype bfloat16
	DiT: Patch Embed of shape (512, 256, 768) dtype bfloat16
	DiT: Conditioning of shape (512, 768) dtype float32
	FID is 211.93545532226562
	(512, 256, 256, 3)
	Calc FID for CFG 2.5 and denoise_timesteps 1
	DiT: Input of shape (512, 32, 32, 4) dtype float32
	DiT: After patch embed, shape is (512, 256, 768) dtype bfloat16
	DiT: Patch Embed of shape (512, 256, 768) dtype bfloat16
	DiT: Conditioning of shape (512, 768) dtype float32
	FID is 275.87335205078125
	(512, 256, 256, 3)
	Calc FID for CFG 2.75 and denoise_timesteps 128
	DiT: Input of shape (512, 32, 32, 4) dtype float32
	DiT: After patch embed, shape is (512, 256, 768) dtype bfloat16
	DiT: Patch Embed of shape (512, 256, 768) dtype bfloat16
	DiT: Conditioning of shape (512, 768) dtype float32
	FID is 10.144330978393555
	(512, 256, 256, 3)
	Calc FID for CFG 2.75 and denoise_timesteps 64
	DiT: Input of shape (512, 32, 32, 4) dtype float32
	DiT: After patch embed, shape is (512, 256, 768) dtype bfloat16
	DiT: Patch Embed of shape (512, 256, 768) dtype bfloat16
	DiT: Conditioning of shape (512, 768) dtype float32
	FID is 10.108360290527344
	(512, 256, 256, 3)
	Calc FID for CFG 2.75 and denoise_timesteps 32
	DiT: Input of shape (512, 32, 32, 4) dtype float32
	DiT: After patch embed, shape is (512, 256, 768) dtype bfloat16
	DiT: Patch Embed of shape (512, 256, 768) dtype bfloat16
	DiT: Conditioning of shape (512, 768) dtype float32
	FID is 10.096152305603027
	(512, 256, 256, 3)
	Calc FID for CFG 2.75 and denoise_timesteps 16
	DiT: Input of shape (512, 32, 32, 4) dtype float32
	DiT: After patch embed, shape is (512, 256, 768) dtype bfloat16
	DiT: Patch Embed of shape (512, 256, 768) dtype bfloat16
	DiT: Conditioning of shape (512, 768) dtype float32
	FID is 10.200900077819824
	(512, 256, 256, 3)
	Calc FID for CFG 2.75 and denoise_timesteps 8
	DiT: Input of shape (512, 32, 32, 4) dtype float32
	DiT: After patch embed, shape is (512, 256, 768) dtype bfloat16
	DiT: Patch Embed of shape (512, 256, 768) dtype bfloat16
	DiT: Conditioning of shape (512, 768) dtype float32
	FID is 11.562959671020508
	(512, 256, 256, 3)
	Calc FID for CFG 2.75 and denoise_timesteps 4
	DiT: Input of shape (512, 32, 32, 4) dtype float32
	DiT: After patch embed, shape is (512, 256, 768) dtype bfloat16
	DiT: Patch Embed of shape (512, 256, 768) dtype bfloat16
	DiT: Conditioning of shape (512, 768) dtype float32
	FID is 28.996597290039062
	(512, 256, 256, 3)
	Calc FID for CFG 2.75 and denoise_timesteps 2
	DiT: Input of shape (512, 32, 32, 4) dtype float32
	DiT: After patch embed, shape is (512, 256, 768) dtype bfloat16
	DiT: Patch Embed of shape (512, 256, 768) dtype bfloat16
	DiT: Conditioning of shape (512, 768) dtype float32
	FID is 207.7974090576172
	(512, 256, 256, 3)
	Calc FID for CFG 2.75 and denoise_timesteps 1
	DiT: Input of shape (512, 32, 32, 4) dtype float32
	DiT: After patch embed, shape is (512, 256, 768) dtype bfloat16
	DiT: Patch Embed of shape (512, 256, 768) dtype bfloat16
	DiT: Conditioning of shape (512, 768) dtype float32
	FID is 271.94140625
	(512, 256, 256, 3)
	Calc FID for CFG 3.0 and denoise_timesteps 128
	DiT: Input of shape (512, 32, 32, 4) dtype float32
	DiT: After patch embed, shape is (512, 256, 768) dtype bfloat16
	DiT: Patch Embed of shape (512, 256, 768) dtype bfloat16
	DiT: Conditioning of shape (512, 768) dtype float32
	FID is 11.38403606414795
	(512, 256, 256, 3)
	Calc FID for CFG 3.0 and denoise_timesteps 64
	DiT: Input of shape (512, 32, 32, 4) dtype float32
	DiT: After patch embed, shape is (512, 256, 768) dtype bfloat16
	DiT: Patch Embed of shape (512, 256, 768) dtype bfloat16
	DiT: Conditioning of shape (512, 768) dtype float32
	FID is 11.3347806930542
	(512, 256, 256, 3)
	Calc FID for CFG 3.0 and denoise_timesteps 32
	DiT: Input of shape (512, 32, 32, 4) dtype float32
	DiT: After patch embed, shape is (512, 256, 768) dtype bfloat16
	DiT: Patch Embed of shape (512, 256, 768) dtype bfloat16
	DiT: Conditioning of shape (512, 768) dtype float32
	FID is 11.267245292663574
	(512, 256, 256, 3)
	Calc FID for CFG 3.0 and denoise_timesteps 16
	DiT: Input of shape (512, 32, 32, 4) dtype float32
	DiT: After patch embed, shape is (512, 256, 768) dtype bfloat16
	DiT: Patch Embed of shape (512, 256, 768) dtype bfloat16
	DiT: Conditioning of shape (512, 768) dtype float32
	FID is 11.231882095336914
	(512, 256, 256, 3)
	Calc FID for CFG 3.0 and denoise_timesteps 8
	DiT: Input of shape (512, 32, 32, 4) dtype float32
	DiT: After patch embed, shape is (512, 256, 768) dtype bfloat16
	DiT: Patch Embed of shape (512, 256, 768) dtype bfloat16
	DiT: Conditioning of shape (512, 768) dtype float32
	FID is 12.002252578735352
	(512, 256, 256, 3)
	Calc FID for CFG 3.0 and denoise_timesteps 4
	DiT: Input of shape (512, 32, 32, 4) dtype float32
	DiT: After patch embed, shape is (512, 256, 768) dtype bfloat16
	DiT: Patch Embed of shape (512, 256, 768) dtype bfloat16
	DiT: Conditioning of shape (512, 768) dtype float32
	FID is 26.133153915405273
	(512, 256, 256, 3)
	Calc FID for CFG 3.0 and denoise_timesteps 2
	DiT: Input of shape (512, 32, 32, 4) dtype float32
	DiT: After patch embed, shape is (512, 256, 768) dtype bfloat16
	DiT: Patch Embed of shape (512, 256, 768) dtype bfloat16
	DiT: Conditioning of shape (512, 768) dtype float32
	FID is 204.17111206054688
	(512, 256, 256, 3)
	Calc FID for CFG 3.0 and denoise_timesteps 1
	DiT: Input of shape (512, 32, 32, 4) dtype float32
	DiT: After patch embed, shape is (512, 256, 768) dtype bfloat16
	DiT: Patch Embed of shape (512, 256, 768) dtype bfloat16
	DiT: Conditioning of shape (512, 768) dtype float32
	FID is 268.5279541015625
	[1;34mwandb[0m:
	[1;34mwandb[0m: 🚀 View run [33mshortcut_imagenet256[0m at: [34mhttps://wandb.ai/daniel-z-kaplan/shortcut/runs/shortcut_imagenet256_20250825_234212_345353_10[0m
	[1;34mwandb[0m: Find logs at: [1;35m../../../tmp/tmpnz136wdu/wandb/run-20250825_234212-shortcut_imagenet256_20250825_234212_345353_10/logs[0m