diff --git "a/registers/log.txt" "b/registers/log.txt" new file mode 100644--- /dev/null +++ "b/registers/log.txt" @@ -0,0 +1,2455 @@ +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: 256 +Node Batch: 256 +Device Batch: 64 +Loading dataset +Loading dataset +DiT: Input of shape (1, 32, 32, 4) dtype float32 +DiT: After patch embed, shape is (1, 256, 768) dtype bfloat16 +DiT: Patch Embed of shape (1, 260, 768) dtype bfloat16 +DiT: Conditioning of shape (1, 768) dtype float32 +selfh idden 768 +self heads 12 +hw_swq 16 +xshape (1, 260, 768) + + DiT Summary  +┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┓ +┃ path  ┃ module  ┃ inputs  ┃ outputs  ┃ params  ┃ +┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┩ +│ │ DiT │ - float32[1,32,32,4] │ bfloat16[1,32,32,4] │ │ +│ │ │ - float32[1] │ │ │ +│ │ │ - float32[1] │ │ │ +│ │ │ - int32[1] │ │ │ +├─────────────────────────────────┼───────────────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤ +│ PatchEmbed_0 │ PatchEmbed │ float32[1,32,32,4] │ bfloat16[1,256,768] │ │ +├─────────────────────────────────┼───────────────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤ +│ PatchEmbed_0/Conv_0 │ Conv │ float32[1,32,32,4] │ bfloat16[1,16,16,768] │ bias: float32[768] │ +│ │ │ │ │ kernel: float32[2,2,4,768] │ +│ │ │ │ │ │ +│ │ │ │ │ 13,056 (52.2 KB) │ +├─────────────────────────────────┼───────────────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤ +│ PatchEmbed_1 │ PatchEmbed │ float32[1,32,32,4] │ bfloat16[1,256,768] │ │ +├─────────────────────────────────┼────────────────���──────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤ +│ PatchEmbed_1/Conv_0 │ Conv │ float32[1,32,32,4] │ bfloat16[1,16,16,768] │ bias: float32[768] │ +│ │ │ │ │ kernel: float32[2,2,4,768] │ +│ │ │ │ │ │ +│ │ │ │ │ 13,056 (52.2 KB) │ +├─────────────────────────────────┼───────────────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤ +│ TimestepEmbedder_0 │ TimestepEmbedder │ float32[1] │ float32[1,768] │ │ +├─────────────────────────────────┼───────────────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤ +│ TimestepEmbedder_0/Dense_0 │ Dense │ bfloat16[1,256] │ bfloat16[1,768] │ bias: float32[768] │ +│ │ │ │ │ kernel: float32[256,768] │ +│ │ │ │ │ │ +│ │ │ │ │ 197,376 (789.5 KB) │ +├─────────────────────────────────┼───────────────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤ +│ TimestepEmbedder_0/Dense_1 │ Dense │ bfloat16[1,768] │ float32[1,768] │ bias: float32[768] │ +│ │ │ │ │ kernel: float32[768,768] │ +│ │ │ │ │ │ +│ │ │ │ │ 590,592 (2.4 MB) │ +├─────────────────────────────────┼───────────────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤ +│ TimestepEmbedder_1 │ TimestepEmbedder │ float32[1] │ float32[1,768] │ │ +├─────────────────────────────────┼───────────────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤ +│ TimestepEmbedder_1/Dense_0 │ Dense │ bfloat16[1,256] │ bfloat16[1,768] │ bias: float32[768] │ +│ │ │ │ │ kernel: float32[256,768] ��� +│ │ │ │ │ │ +│ │ │ │ │ 197,376 (789.5 KB) │ +├─────────────────────────────────┼───────────────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤ +│ TimestepEmbedder_1/Dense_1 │ Dense │ bfloat16[1,768] │ float32[1,768] │ bias: float32[768] │ +│ │ │ │ │ kernel: float32[768,768] │ +│ │ │ │ │ │ +│ │ │ │ │ 590,592 (2.4 MB) │ +├─────────────────────────────────┼───────────────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤ +│ LabelEmbedder_0 │ LabelEmbedder │ int32[1] │ bfloat16[1,768] │ │ +├─────────────────────────────────┼───────────────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤ +│ LabelEmbedder_0/Embed_0 │ Embed │ int32[1] │ bfloat16[1,768] │ embedding: float32[1001,768] │ +│ │ │ │ │ │ +│ │ │ │ │ 768,768 (3.1 MB) │ +├─────────────────────────────────┼───────────────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤ +│ DiTBlock_0 │ DiTBlock │ - bfloat16[1,260,768] │ float32[1,260,768] │ │ +│ │ │ - float32[1,768] │ │ │ +├─────────────────────────────────┼───────────────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤ +│ DiTBlock_0/Dense_0 │ Dense │ float32[1,768] │ bfloat16[1,4608] │ bias: float32[4608] │ +│ │ │ │ │ kernel: float32[768,4608] │ +│ │ │ │ │ │ +│ │ │ │ │ 3,543,552 (14.2 MB) │ +├─────────────────────────────────┼───────────────────────────┼───────────────────────┼──────���────────────────┼──────────────────────────────┤ +│ DiTBlock_0/Dense_1 │ Dense │ bfloat16[1,260,768] │ bfloat16[1,260,768] │ bias: float32[768] │ +│ │ │ │ │ kernel: float32[768,768] │ +│ │ │ │ │ │ +│ │ │ │ │ 590,592 (2.4 MB) │ +├─────────────────────────────────┼───────────────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤ +│ DiTBlock_0/Dense_2 │ Dense │ bfloat16[1,260,768] │ bfloat16[1,260,768] │ bias: float32[768] │ +│ │ │ │ │ kernel: float32[768,768] │ +│ │ │ │ │ │ +│ │ │ │ │ 590,592 (2.4 MB) │ +├─────────────────────────────────┼───────────────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤ +│ DiTBlock_0/Dense_3 │ Dense │ bfloat16[1,260,768] │ bfloat16[1,260,768] │ bias: float32[768] │ +│ │ │ │ │ kernel: float32[768,768] │ +│ │ │ │ │ │ +│ │ │ │ │ 590,592 (2.4 MB) │ +├─────────────────────────────────┼───────────────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤ +│ VisionRotaryEmbeddingFast_0 │ VisionRotaryEmbeddingFast │ bfloat16[1,260,12,64] │ float32[1,256,12,64] │ │ +├─────────────────────────────────┼───────────────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤ +│ DiTBlock_0/Dense_4 │ Dense │ float32[1,260,768] │ bfloat16[1,260,768] │ bias: float32[768] │ +│ │ │ │ │ kernel: float32[768,768] │ +│ │ │ │ │ │ +│ │ │ │ │ 590,592 (2.4 MB) │ +├─────────────────────────────────┼───────────────────────────┼───────────────────────┼───────────────────────┼───────────────────��──────────┤ +│ DiTBlock_0/SwiGLUFFN_0 │ SwiGLUFFN │ bfloat16[1,260,768] │ float32[1,260,768] │ │ +├─────────────────────────────────┼───────────────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤ +│ DiTBlock_0/SwiGLUFFN_0/Dense_0 │ Dense │ bfloat16[1,260,768] │ float32[1,260,4096] │ bias: float32[4096] │ +│ │ │ │ │ kernel: float32[768,4096] │ +│ │ │ │ │ │ +│ │ │ │ │ 3,149,824 (12.6 MB) │ +├─────────────────────────────────┼───────────────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤ +│ DiTBlock_0/SwiGLUFFN_0/Dense_1 │ Dense │ float32[1,260,2048] │ float32[1,260,768] │ bias: float32[768] │ +│ │ │ │ │ kernel: float32[2048,768] │ +│ │ │ │ │ │ +│ │ │ │ │ 1,573,632 (6.3 MB) │ +├─────────────────────────────────┼───────────────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤ +│ DiTBlock_1 │ DiTBlock │ - float32[1,260,768] │ float32[1,260,768] │ │ +│ │ │ - float32[1,768] │ │ │ +├─────────────────────────────────┼───────────────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤ +│ DiTBlock_1/Dense_0 │ Dense │ float32[1,768] │ bfloat16[1,4608] │ bias: float32[4608] │ +│ │ │ │ │ kernel: float32[768,4608] │ +│ │ │ │ │ │ +│ │ │ │ │ 3,543,552 (14.2 MB) │ +├─────────────────────────────────┼───────────────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤ +│ DiTBlock_1/Dense_1 │ Dense │ bfloat16[1,260,768] │ bfloat16[1,260,768] │ bias: float32[768] │ +│ │ │ │ │ kernel: float32[768,768] │ +│ │ │ │ │ │ +│ │ │ │ │ 590,592 (2.4 MB) │ +├─────────────────────────────────┼───────────────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤ +│ DiTBlock_1/Dense_2 │ Dense │ bfloat16[1,260,768] │ bfloat16[1,260,768] │ bias: float32[768] │ +│ │ │ │ │ kernel: float32[768,768] │ +│ │ │ │ │ │ +│ │ │ │ │ 590,592 (2.4 MB) │ +├─────────────────────────────────┼───────────────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤ +│ DiTBlock_1/Dense_3 │ Dense │ bfloat16[1,260,768] │ bfloat16[1,260,768] │ bias: float32[768] │ +│ │ │ │ │ kernel: float32[768,768] │ +│ │ │ │ │ │ +│ │ │ │ │ 590,592 (2.4 MB) │ +├─────────────────────────────────┼───────────────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤ +│ DiTBlock_1/Dense_4 │ Dense │ float32[1,260,768] │ bfloat16[1,260,768] │ bias: float32[768] │ +│ │ │ │ │ kernel: float32[768,768] │ +│ │ │ │ │ │ +│ │ │ │ │ 590,592 (2.4 MB) │ +├─────────────────────────────────┼───────────────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤ +│ DiTBlock_1/SwiGLUFFN_0 │ SwiGLUFFN │ bfloat16[1,260,768] │ float32[1,260,768] │ │ +├─────────────────────────────────┼───────────────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤ +│ DiTBlock_1/SwiGLUFFN_0/Dense_0 │ Dense │ bfloat16[1,260,768] │ float32[1,260,4096] │ bias: float32[4096] │ +│ │ │ │ │ kernel: float32[768,4096] │ +│ │ │ │ │ │ +│ │ │ │ │ 3,149,824 (12.6 MB) │ +├─────────────────────────────────┼───────────────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤ +│ DiTBlock_1/SwiGLUFFN_0/Dense_1 │ Dense │ float32[1,260,2048] │ float32[1,260,768] │ bias: float32[768] │ +│ │ │ │ │ kernel: float32[2048,768] │ +│ │ │ │ │ │ +│ │ │ │ │ 1,573,632 (6.3 MB) │ +├─────────────────────────────────┼───────────────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤ +│ DiTBlock_2 │ DiTBlock │ - float32[1,260,768] │ float32[1,260,768] │ │ +│ │ │ - float32[1,768] │ │ │ +├─────────────────────────────────┼───────────────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤ +│ DiTBlock_2/Dense_0 │ Dense │ float32[1,768] │ bfloat16[1,4608] │ bias: float32[4608] │ +│ │ │ │ │ kernel: float32[768,4608] │ +│ │ │ │ │ │ +│ │ │ │ │ 3,543,552 (14.2 MB) │ +├─────────────────────────────────┼───────────────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤ +│ DiTBlock_2/Dense_1 │ Dense │ bfloat16[1,260,768] │ bfloat16[1,260,768] │ bias: float32[768] │ +│ │ │ │ │ kernel: float32[768,768] │ +│ │ │ │ │ │ +│ │ │ │ │ 590,592 (2.4 MB) │ +├─────────────────────────────────┼───────────────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤ +│ DiTBlock_2/Dense_2 │ Dense │ bfloat16[1,260,768] │ bfloat16[1,260,768] │ bias: float32[768] │ +│ │ │ │ │ kernel: float32[768,768] │ +│ │ │ │ │ │ +│ │ │ │ │ 590,592 (2.4 MB) │ +├─────────────────────────────────┼───────────────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤ +│ DiTBlock_2/Dense_3 │ Dense │ bfloat16[1,260,768] │ bfloat16[1,260,768] │ bias: float32[768] │ +│ │ │ │ │ kernel: float32[768,768] │ +│ │ │ │ │ │ +│ │ │ │ │ 590,592 (2.4 MB) │ +├─────────────────────────────────┼───────────────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤ +│ DiTBlock_2/Dense_4 │ Dense │ float32[1,260,768] │ bfloat16[1,260,768] │ bias: float32[768] │ +│ │ │ │ │ kernel: float32[768,768] │ +│ │ │ │ │ │ +│ │ │ │ │ 590,592 (2.4 MB) │ +├─────────────────────────────────┼───────────────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤ +│ DiTBlock_2/SwiGLUFFN_0 │ SwiGLUFFN │ bfloat16[1,260,768] │ float32[1,260,768] │ │ +├─────────────────────────────────┼───────────────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤ +│ DiTBlock_2/SwiGLUFFN_0/Dense_0 │ Dense │ bfloat16[1,260,768] │ float32[1,260,4096] │ bias: float32[4096] │ +│ │ │ │ │ kernel: float32[768,4096] │ +│ │ │ │ │ │ +│ │ │ │ │ 3,149,824 (12.6 MB) │ +├─────────────────────────────────┼───────────────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤ +│ DiTBlock_2/SwiGLUFFN_0/Dense_1 │ Dense │ float32[1,260,2048] │ float32[1,260,768] │ bias: float32[768] │ +│ │ │ │ │ kernel: float32[2048,768] │ +│ │ │ │ │ │ +│ │ │ │ │ 1,573,632 (6.3 MB) │ +├─────────────────────────────────┼───────────────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤ +│ DiTBlock_3 │ DiTBlock │ - float32[1,260,768] │ float32[1,260,768] │ │ +│ │ │ - float32[1,768] │ │ │ +├─────────────────────────────────┼───────────────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤ +│ DiTBlock_3/Dense_0 │ Dense │ float32[1,768] │ bfloat16[1,4608] │ bias: float32[4608] │ +│ │ │ │ │ kernel: float32[768,4608] │ +│ │ │ │ │ │ +│ │ │ │ │ 3,543,552 (14.2 MB) │ +├─────────────────────────────────┼───────────────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤ +│ DiTBlock_3/Dense_1 │ Dense │ bfloat16[1,260,768] │ bfloat16[1,260,768] │ bias: float32[768] │ +│ │ │ │ │ kernel: float32[768,768] │ +│ │ │ │ │ │ +│ │ │ │ │ 590,592 (2.4 MB) │ +├─────────────────────────────────┼───────────────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤ +│ DiTBlock_3/Dense_2 │ Dense │ bfloat16[1,260,768] │ bfloat16[1,260,768] │ bias: float32[768] │ +│ │ │ │ │ kernel: float32[768,768] │ +│ │ │ │ │ │ +│ │ │ │ │ 590,592 (2.4 MB) │ +├─────────────────────────────────┼───────────────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤ +│ DiTBlock_3/Dense_3 │ Dense │ bfloat16[1,260,768] │ bfloat16[1,260,768] │ bias: float32[768] │ +│ │ │ │ │ kernel: float32[768,768] │ +│ │ │ │ │ │ +│ │ │ │ │ 590,592 (2.4 MB) │ +├─────────────────────────────────┼───────────────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤ +│ DiTBlock_3/Dense_4 │ Dense │ float32[1,260,768] │ bfloat16[1,260,768] │ bias: float32[768] │ +│ │ │ │ │ kernel: float32[768,768] │ +│ │ │ │ │ │ +│ │ │ │ │ 590,592 (2.4 MB) │ +├─────────────────────────────────┼───────────────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤ +│ DiTBlock_3/SwiGLUFFN_0 │ SwiGLUFFN │ bfloat16[1,260,768] │ float32[1,260,768] │ │ +├─────────────────────────────────┼───────────────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤ +│ DiTBlock_3/SwiGLUFFN_0/Dense_0 │ Dense │ bfloat16[1,260,768] │ float32[1,260,4096] │ bias: float32[4096] │ +│ │ │ │ │ kernel: float32[768,4096] │ +│ │ │ │ │ │ +│ │ │ │ │ 3,149,824 (12.6 MB) │ +├─────────────────────────────────┼───────────────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤ +│ DiTBlock_3/SwiGLUFFN_0/Dense_1 │ Dense │ float32[1,260,2048] │ float32[1,260,768] │ bias: float32[768] │ +│ │ │ │ │ kernel: float32[2048,768] │ +│ │ │ │ │ │ +│ │ │ │ │ 1,573,632 (6.3 MB) │ +├─────────────────────────────────┼───────────────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤ +│ DiTBlock_4 │ DiTBlock │ - float32[1,260,768] │ float32[1,260,768] │ │ +│ │ │ - float32[1,768] │ │ │ +├─────────────────────────────────┼───────────────────────────┼───────────────────────┼────────────────���──────┼──────────────────────────────┤ +│ DiTBlock_4/Dense_0 │ Dense │ float32[1,768] │ bfloat16[1,4608] │ bias: float32[4608] │ +│ │ │ │ │ kernel: float32[768,4608] │ +│ │ │ │ │ │ +│ │ │ │ │ 3,543,552 (14.2 MB) │ +├─────────────────────────────────┼───────────────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤ +│ DiTBlock_4/Dense_1 │ Dense │ bfloat16[1,260,768] │ bfloat16[1,260,768] │ bias: float32[768] │ +│ │ │ │ │ kernel: float32[768,768] │ +│ │ │ │ │ │ +│ │ │ │ │ 590,592 (2.4 MB) │ +├─────────────────────────────────┼───────────────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤ +│ DiTBlock_4/Dense_2 │ Dense │ bfloat16[1,260,768] │ bfloat16[1,260,768] │ bias: float32[768] │ +│ │ │ │ │ kernel: float32[768,768] │ +│ │ │ │ │ │ +│ │ │ │ │ 590,592 (2.4 MB) │ +├─────────────────────────────────┼───────────────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤ +│ DiTBlock_4/Dense_3 │ Dense │ bfloat16[1,260,768] │ bfloat16[1,260,768] │ bias: float32[768] │ +│ │ │ │ │ kernel: float32[768,768] │ +│ │ │ │ │ │ +│ │ │ │ │ 590,592 (2.4 MB) │ +├─────────────────────────────────┼───────────────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤ +│ DiTBlock_4/Dense_4 │ Dense │ float32[1,260,768] │ bfloat16[1,260,768] │ bias: float32[768] │ +│ │ │ │ │ kernel: float32[768,768] │ +│ │ │ │ │ │ +│ │ │ �� │ 590,592 (2.4 MB) │ +├─────────────────────────────────┼───────────────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤ +│ DiTBlock_4/SwiGLUFFN_0 │ SwiGLUFFN │ bfloat16[1,260,768] │ float32[1,260,768] │ │ +├─────────────────────────────────┼───────────────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤ +│ DiTBlock_4/SwiGLUFFN_0/Dense_0 │ Dense │ bfloat16[1,260,768] │ float32[1,260,4096] │ bias: float32[4096] │ +│ │ │ │ │ kernel: float32[768,4096] │ +│ │ │ │ │ │ +│ │ │ │ │ 3,149,824 (12.6 MB) │ +├─────────────────────────────────┼───────────────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤ +│ DiTBlock_4/SwiGLUFFN_0/Dense_1 │ Dense │ float32[1,260,2048] │ float32[1,260,768] │ bias: float32[768] │ +│ │ │ │ │ kernel: float32[2048,768] │ +│ │ │ │ │ │ +│ │ │ │ │ 1,573,632 (6.3 MB) │ +├─────────────────────────────────┼───────────────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤ +│ DiTBlock_5 │ DiTBlock │ - float32[1,260,768] │ float32[1,260,768] │ │ +│ │ │ - float32[1,768] │ │ │ +├─────────────────────────────────┼───────────────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤ +│ DiTBlock_5/Dense_0 │ Dense │ float32[1,768] │ bfloat16[1,4608] │ bias: float32[4608] │ +│ │ │ │ │ kernel: float32[768,4608] │ +│ │ │ │ │ │ +│ │ │ │ │ 3,543,552 (14.2 MB) │ +├─────────────────────────────────┼───────────────────────────┼───────────────────────┼───────────────────────┼────────────���─────────────────┤ +│ DiTBlock_5/Dense_1 │ Dense │ bfloat16[1,260,768] │ bfloat16[1,260,768] │ bias: float32[768] │ +│ │ │ │ │ kernel: float32[768,768] │ +│ │ │ │ │ │ +│ │ │ │ │ 590,592 (2.4 MB) │ +├─────────────────────────────────┼───────────────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤ +│ DiTBlock_5/Dense_2 │ Dense │ bfloat16[1,260,768] │ bfloat16[1,260,768] │ bias: float32[768] │ +│ │ │ │ │ kernel: float32[768,768] │ +│ │ │ │ │ │ +│ │ │ │ │ 590,592 (2.4 MB) │ +├─────────────────────────────────┼───────────────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤ +│ DiTBlock_5/Dense_3 │ Dense │ bfloat16[1,260,768] │ bfloat16[1,260,768] │ bias: float32[768] │ +│ │ │ │ │ kernel: float32[768,768] │ +│ │ │ │ │ │ +│ │ │ │ │ 590,592 (2.4 MB) │ +├─────────────────────────────────┼───────────────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤ +│ DiTBlock_5/Dense_4 │ Dense │ float32[1,260,768] │ bfloat16[1,260,768] │ bias: float32[768] │ +│ │ │ │ │ kernel: float32[768,768] │ +│ │ │ │ │ │ +│ │ │ │ │ 590,592 (2.4 MB) │ +├─────────────────────────────────┼───────────────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤ +│ DiTBlock_5/SwiGLUFFN_0 │ SwiGLUFFN │ bfloat16[1,260,768] │ float32[1,260,768] │ │ +├─────────────────────────────────┼───────────────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤ +│ DiTBlock_5/SwiGLUFFN_0/Dense_0 │ Dense │ bfloat16[1,260,768] │ float32[1,260,4096] │ bias: float32[4096] │ +│ │ │ │ │ kernel: float32[768,4096] │ +│ │ │ │ │ │ +│ │ │ │ │ 3,149,824 (12.6 MB) │ +├─────────────────────────────────┼───────────────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤ +│ DiTBlock_5/SwiGLUFFN_0/Dense_1 │ Dense │ float32[1,260,2048] │ float32[1,260,768] │ bias: float32[768] │ +│ │ │ │ │ kernel: float32[2048,768] │ +│ │ │ │ │ │ +│ │ │ │ │ 1,573,632 (6.3 MB) │ +├─────────────────────────────────┼───────────────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤ +│ DiTBlock_6 │ DiTBlock │ - float32[1,260,768] │ float32[1,260,768] │ │ +│ │ │ - float32[1,768] │ │ │ +├─────────────────────────────────┼───────────────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤ +│ DiTBlock_6/Dense_0 │ Dense │ float32[1,768] │ bfloat16[1,4608] │ bias: float32[4608] │ +│ │ │ │ │ kernel: float32[768,4608] │ +│ │ │ │ │ │ +│ │ │ │ │ 3,543,552 (14.2 MB) │ +├─────────────────────────────────┼───────────────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤ +│ DiTBlock_6/Dense_1 │ Dense │ bfloat16[1,260,768] │ bfloat16[1,260,768] │ bias: float32[768] │ +│ │ │ │ │ kernel: float32[768,768] │ +│ │ │ │ │ │ +│ │ │ │ │ 590,592 (2.4 MB) │ +├─────────────────────────────────┼───────────────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤ +�� DiTBlock_6/Dense_2 │ Dense │ bfloat16[1,260,768] │ bfloat16[1,260,768] │ bias: float32[768] │ +│ │ │ │ │ kernel: float32[768,768] │ +│ │ │ │ │ │ +│ │ │ │ │ 590,592 (2.4 MB) │ +├─────────────────────────────────┼───────────────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤ +│ DiTBlock_6/Dense_3 │ Dense │ bfloat16[1,260,768] │ bfloat16[1,260,768] │ bias: float32[768] │ +│ │ │ │ │ kernel: float32[768,768] │ +│ │ │ │ │ │ +│ │ │ │ │ 590,592 (2.4 MB) │ +├─────────────────────────────────┼───────────────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤ +│ DiTBlock_6/Dense_4 │ Dense │ float32[1,260,768] │ bfloat16[1,260,768] │ bias: float32[768] │ +│ │ │ │ │ kernel: float32[768,768] │ +│ │ │ │ │ │ +│ │ │ │ │ 590,592 (2.4 MB) │ +├─────────────────────────────────┼───────────────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤ +│ DiTBlock_6/SwiGLUFFN_0 │ SwiGLUFFN │ bfloat16[1,260,768] │ float32[1,260,768] │ │ +├─────────────────────────────────┼───────────────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤ +│ DiTBlock_6/SwiGLUFFN_0/Dense_0 │ Dense │ bfloat16[1,260,768] │ float32[1,260,4096] │ bias: float32[4096] │ +│ │ │ │ │ kernel: float32[768,4096] │ +│ │ │ │ │ │ +│ │ │ │ │ 3,149,824 (12.6 MB) │ +├─────────────────────────────────┼───────────────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤ +│ DiTBlock_6/SwiGLUFFN_0/Dense_1 │ Dense │ float32[1,260,2048] │ float32[1,260,768] │ bias: float32[768] │ +│ │ │ │ │ kernel: float32[2048,768] │ +│ │ │ │ │ │ +│ │ │ │ │ 1,573,632 (6.3 MB) │ +├─────────────────────────────────┼───────────────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤ +│ DiTBlock_7 │ DiTBlock │ - float32[1,260,768] │ float32[1,260,768] │ │ +│ │ │ - float32[1,768] │ │ │ +├─────────────────────────────────┼───────────────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤ +│ DiTBlock_7/Dense_0 │ Dense │ float32[1,768] │ bfloat16[1,4608] │ bias: float32[4608] │ +│ │ │ │ │ kernel: float32[768,4608] │ +│ │ │ │ │ │ +│ │ │ │ │ 3,543,552 (14.2 MB) │ +├─────────────────────────────────┼───────────────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤ +│ DiTBlock_7/Dense_1 │ Dense │ bfloat16[1,260,768] │ bfloat16[1,260,768] │ bias: float32[768] │ +│ │ │ │ │ kernel: float32[768,768] │ +│ │ │ │ │ │ +│ │ │ │ │ 590,592 (2.4 MB) │ +├─────────────────────────────────┼───────────────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤ +│ DiTBlock_7/Dense_2 │ Dense │ bfloat16[1,260,768] │ bfloat16[1,260,768] │ bias: float32[768] │ +│ │ │ │ │ kernel: float32[768,768] │ +│ │ │ │ │ │ +│ │ │ │ │ 590,592 (2.4 MB) │ +├─────────────────────────────────┼───────────────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤ +│ DiTBlock_7/Dense_3 │ Dense │ bfloat16[1,260,768] │ bfloat16[1,260,768] │ bias: float32[768] │ +│ │ │ │ │ kernel: float32[768,768] │ +│ │ │ │ │ │ +│ │ │ │ │ 590,592 (2.4 MB) │ +├─────────────────────────────────┼───────────────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤ +│ DiTBlock_7/Dense_4 │ Dense │ float32[1,260,768] │ bfloat16[1,260,768] │ bias: float32[768] │ +│ │ │ │ │ kernel: float32[768,768] │ +│ │ │ │ │ │ +│ │ │ │ │ 590,592 (2.4 MB) │ +├─────────────────────────────────┼───────────────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤ +│ DiTBlock_7/SwiGLUFFN_0 │ SwiGLUFFN │ bfloat16[1,260,768] │ float32[1,260,768] │ │ +├─────────────────────────────────┼───────────────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤ +│ DiTBlock_7/SwiGLUFFN_0/Dense_0 │ Dense │ bfloat16[1,260,768] │ float32[1,260,4096] │ bias: float32[4096] │ +│ │ │ │ │ kernel: float32[768,4096] │ +│ │ │ │ │ │ +│ │ │ │ │ 3,149,824 (12.6 MB) │ +├─────────────────────────────────┼───────────────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤ +│ DiTBlock_7/SwiGLUFFN_0/Dense_1 │ Dense │ float32[1,260,2048] │ float32[1,260,768] │ bias: float32[768] │ +│ │ │ │ │ kernel: float32[2048,768] │ +│ │ │ │ │ │ +│ │ │ │ │ 1,573,632 (6.3 MB) │ +├─────────────────────────────────┼───────────────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤ +│ DiTBlock_8 │ DiTBlock │ - float32[1,260,768] │ float32[1,260,768] │ │ +�� │ │ - float32[1,768] │ │ │ +├─────────────────────────────────┼───────────────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤ +│ DiTBlock_8/Dense_0 │ Dense │ float32[1,768] │ bfloat16[1,4608] │ bias: float32[4608] │ +│ │ │ │ │ kernel: float32[768,4608] │ +│ │ │ │ │ │ +│ │ │ │ │ 3,543,552 (14.2 MB) │ +├─────────────────────────────────┼───────────────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤ +│ DiTBlock_8/Dense_1 │ Dense │ bfloat16[1,260,768] │ bfloat16[1,260,768] │ bias: float32[768] │ +│ │ │ │ │ kernel: float32[768,768] │ +│ │ │ │ │ │ +│ │ │ │ │ 590,592 (2.4 MB) │ +├─────────────────────────────────┼───────────────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤ +│ DiTBlock_8/Dense_2 │ Dense │ bfloat16[1,260,768] │ bfloat16[1,260,768] │ bias: float32[768] │ +│ │ │ │ │ kernel: float32[768,768] │ +│ │ │ │ │ │ +│ │ │ │ │ 590,592 (2.4 MB) │ +├─────────────────────────────────┼───────────────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤ +│ DiTBlock_8/Dense_3 │ Dense │ bfloat16[1,260,768] │ bfloat16[1,260,768] │ bias: float32[768] │ +│ │ │ │ │ kernel: float32[768,768] │ +│ │ │ │ │ │ +│ │ │ │ │ 590,592 (2.4 MB) │ +├─────────────────────────────────┼───────────────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤ +│ DiTBlock_8/Dense_4 │ Dense │ float32[1,260,768] │ bfloat16[1,260,768] │ bias: float32[768] │ +│ │ │ │ │ kernel: float32[768,768] │ +│ │ │ │ │ │ +│ │ │ │ │ 590,592 (2.4 MB) │ +├─────────────────────────────────┼───────────────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤ +│ DiTBlock_8/SwiGLUFFN_0 │ SwiGLUFFN │ bfloat16[1,260,768] │ float32[1,260,768] │ │ +├─────────────────────────────────┼───────────────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤ +│ DiTBlock_8/SwiGLUFFN_0/Dense_0 │ Dense │ bfloat16[1,260,768] │ float32[1,260,4096] │ bias: float32[4096] │ +│ │ │ │ │ kernel: float32[768,4096] │ +│ │ │ │ │ │ +│ │ │ │ │ 3,149,824 (12.6 MB) │ +├─────────────────────────────────┼───────────────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤ +│ DiTBlock_8/SwiGLUFFN_0/Dense_1 │ Dense │ float32[1,260,2048] │ float32[1,260,768] │ bias: float32[768] │ +│ │ │ │ │ kernel: float32[2048,768] │ +│ │ │ │ │ │ +│ │ │ │ │ 1,573,632 (6.3 MB) │ +├─────────────────────────────────┼───────────────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤ +│ DiTBlock_9 │ DiTBlock │ - float32[1,260,768] │ float32[1,260,768] │ │ +│ │ │ - float32[1,768] │ │ │ +├─────────────────────────────────┼───────────────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤ +│ DiTBlock_9/Dense_0 │ Dense │ float32[1,768] │ bfloat16[1,4608] │ bias: float32[4608] │ +│ │ │ │ │ kernel: float32[768,4608] │ +│ │ │ │ │ │ +│ │ │ │ │ 3,543,552 (14.2 MB) │ +├─────────────────────────────────┼───────────────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤ +│ DiTBlock_9/Dense_1 │ Dense │ bfloat16[1,260,768] │ bfloat16[1,260,768] │ bias: float32[768] │ +│ │ │ │ │ kernel: float32[768,768] │ +│ │ │ │ │ │ +│ │ │ │ │ 590,592 (2.4 MB) │ +├─────────────────────────────────┼───────────────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤ +│ DiTBlock_9/Dense_2 │ Dense │ bfloat16[1,260,768] │ bfloat16[1,260,768] │ bias: float32[768] │ +│ │ │ │ │ kernel: float32[768,768] │ +│ │ │ │ │ │ +│ │ │ │ │ 590,592 (2.4 MB) │ +├─────────────────────────────────┼───────────────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤ +│ DiTBlock_9/Dense_3 │ Dense │ bfloat16[1,260,768] │ bfloat16[1,260,768] │ bias: float32[768] │ +│ │ │ │ │ kernel: float32[768,768] │ +│ │ │ │ │ │ +│ │ │ │ │ 590,592 (2.4 MB) │ +├─────────────────────────────────┼───────────────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤ +│ DiTBlock_9/Dense_4 │ Dense │ float32[1,260,768] │ bfloat16[1,260,768] │ bias: float32[768] │ +│ │ │ │ │ kernel: float32[768,768] │ +│ │ │ │ │ │ +│ │ │ │ │ 590,592 (2.4 MB) │ +├─────────────────────────────────┼───────────────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤ +│ DiTBlock_9/SwiGLUFFN_0 │ SwiGLUFFN │ bfloat16[1,260,768] │ float32[1,260,768] │ │ +├──���──────────────────────────────┼───────────────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤ +│ DiTBlock_9/SwiGLUFFN_0/Dense_0 │ Dense │ bfloat16[1,260,768] │ float32[1,260,4096] │ bias: float32[4096] │ +│ │ │ │ │ kernel: float32[768,4096] │ +│ │ │ │ │ │ +│ │ │ │ │ 3,149,824 (12.6 MB) │ +├─────────────────────────────────┼───────────────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤ +│ DiTBlock_9/SwiGLUFFN_0/Dense_1 │ Dense │ float32[1,260,2048] │ float32[1,260,768] │ bias: float32[768] │ +│ │ │ │ │ kernel: float32[2048,768] │ +│ │ │ │ │ │ +│ │ │ │ │ 1,573,632 (6.3 MB) │ +├─────────────────────────────────┼───────────────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤ +│ DiTBlock_10 │ DiTBlock │ - float32[1,260,768] │ float32[1,260,768] │ │ +│ │ │ - float32[1,768] │ │ │ +├─────────────────────────────────┼───────────────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤ +│ DiTBlock_10/Dense_0 │ Dense │ float32[1,768] │ bfloat16[1,4608] │ bias: float32[4608] │ +│ │ │ │ │ kernel: float32[768,4608] │ +│ │ │ │ │ │ +│ │ │ │ │ 3,543,552 (14.2 MB) │ +├─────────────────────────────────┼───────────────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤ +│ DiTBlock_10/Dense_1 │ Dense │ bfloat16[1,260,768] │ bfloat16[1,260,768] │ bias: float32[768] │ +│ │ │ │ │ kernel: float32[768,768] │ +│ │ │ │ │ │ +│ │ │ │ │ 590,592 (2.4 MB) │ +├─────────────────────────────────┼───────────────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤ +│ DiTBlock_10/Dense_2 │ Dense │ bfloat16[1,260,768] │ bfloat16[1,260,768] │ bias: float32[768] │ +│ │ │ │ │ kernel: float32[768,768] │ +│ │ │ │ │ │ +│ │ │ │ │ 590,592 (2.4 MB) │ +├─────────────────────────────────┼───────────────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤ +│ DiTBlock_10/Dense_3 │ Dense │ bfloat16[1,260,768] │ bfloat16[1,260,768] │ bias: float32[768] │ +│ │ │ │ │ kernel: float32[768,768] │ +│ │ │ │ │ │ +│ │ │ │ │ 590,592 (2.4 MB) │ +├─────────────────────────────────┼───────────────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤ +│ DiTBlock_10/Dense_4 │ Dense │ float32[1,260,768] │ bfloat16[1,260,768] │ bias: float32[768] │ +│ │ │ │ │ kernel: float32[768,768] │ +│ │ │ │ │ │ +│ │ │ │ │ 590,592 (2.4 MB) │ +├─────────────────────────────────┼───────────────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤ +│ DiTBlock_10/SwiGLUFFN_0 │ SwiGLUFFN │ bfloat16[1,260,768] │ float32[1,260,768] │ │ +├─────────────────────────────────┼───────────────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤ +│ DiTBlock_10/SwiGLUFFN_0/Dense_0 │ Dense │ bfloat16[1,260,768] │ float32[1,260,4096] │ bias: float32[4096] │ +│ │ │ │ │ kernel: float32[768,4096] │ +│ │ │ │ │ │ +│ │ │ │ │ 3,149,824 (12.6 MB) │ +├──────────────────────���──────────┼───────────────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤ +│ DiTBlock_10/SwiGLUFFN_0/Dense_1 │ Dense │ float32[1,260,2048] │ float32[1,260,768] │ bias: float32[768] │ +│ │ │ │ │ kernel: float32[2048,768] │ +│ │ │ │ │ │ +│ │ │ │ │ 1,573,632 (6.3 MB) │ +├─────────────────────────────────┼───────────────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤ +│ DiTBlock_11 │ DiTBlock │ - float32[1,260,768] │ float32[1,260,768] │ │ +│ │ │ - float32[1,768] │ │ │ +├─────────────────────────────────┼───────────────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤ +│ DiTBlock_11/Dense_0 │ Dense │ float32[1,768] │ bfloat16[1,4608] │ bias: float32[4608] │ +│ │ │ │ │ kernel: float32[768,4608] │ +│ │ │ │ │ │ +│ │ │ │ │ 3,543,552 (14.2 MB) │ +├─────────────────────────────────┼───────────────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤ +│ DiTBlock_11/Dense_1 │ Dense │ bfloat16[1,260,768] │ bfloat16[1,260,768] │ bias: float32[768] │ +│ │ │ │ │ kernel: float32[768,768] │ +│ │ │ │ │ │ +│ │ │ │ │ 590,592 (2.4 MB) │ +├─────────────────────────────────┼───────────────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤ +│ DiTBlock_11/Dense_2 │ Dense │ bfloat16[1,260,768] │ bfloat16[1,260,768] │ bias: float32[768] │ +│ │ │ │ │ kernel: float32[768,768] │ +│ │ │ │ │ │ +│ │ │ │ │ 590,592 (2.4 MB) │ +├─────────────────────────────────┼───────────────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤ +│ DiTBlock_11/Dense_3 │ Dense │ bfloat16[1,260,768] │ bfloat16[1,260,768] │ bias: float32[768] │ +│ │ │ │ │ kernel: float32[768,768] │ +│ │ │ │ │ │ +│ │ │ │ │ 590,592 (2.4 MB) │ +├─────────────────────────────────┼───────────────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤ +│ DiTBlock_11/Dense_4 │ Dense │ float32[1,260,768] │ bfloat16[1,260,768] │ bias: float32[768] │ +│ │ │ │ │ kernel: float32[768,768] │ +│ │ │ │ │ │ +│ │ │ │ │ 590,592 (2.4 MB) │ +├─────────────────────────────────┼───────────────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤ +│ DiTBlock_11/SwiGLUFFN_0 │ SwiGLUFFN │ bfloat16[1,260,768] │ float32[1,260,768] │ │ +├─────────────────────────────────┼───────────────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤ +│ DiTBlock_11/SwiGLUFFN_0/Dense_0 │ Dense │ bfloat16[1,260,768] │ float32[1,260,4096] │ bias: float32[4096] │ +│ │ │ │ │ kernel: float32[768,4096] │ +│ │ │ │ │ │ +│ │ │ │ │ 3,149,824 (12.6 MB) │ +├─────────────────────────────────┼───────────────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤ +│ DiTBlock_11/SwiGLUFFN_0/Dense_1 │ Dense │ float32[1,260,2048] │ float32[1,260,768] │ bias: float32[768] │ +│ │ │ │ │ kernel: float32[2048,768] │ +│ │ │ │ │ │ +│ │ │ │ │ 1,573,632 (6.3 MB) │ +├─────────────────────────────────┼────────���──────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤ +│ FinalLayer_0 │ FinalLayer │ - float32[1,260,768] │ bfloat16[1,260,16] │ │ +│ │ │ - float32[1,768] │ │ │ +├─────────────────────────────────┼───────────────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤ +│ FinalLayer_0/Dense_0 │ Dense │ float32[1,768] │ bfloat16[1,1536] │ bias: float32[1536] │ +│ │ │ │ │ kernel: float32[768,1536] │ +│ │ │ │ │ │ +│ │ │ │ │ 1,181,184 (4.7 MB) │ +├─────────────────────────────────┼───────────────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤ +│ FinalLayer_0/Dense_1 │ Dense │ bfloat16[1,260,768] │ bfloat16[1,260,16] │ bias: float32[16] │ +│ │ │ │ │ kernel: float32[768,16] │ +│ │ │ │ │ │ +│ │ │ │ │ 12,304 (49.2 KB) │ +├─────────────────────────────────┼───────────────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤ +│ Embed_0 │ Embed │ int32[1] │ float32[1,1] │ embedding: float32[256,1] │ +│ │ │ │ │ │ +│ │ │ │ │ 256 (1.0 KB) │ +├─────────────────────────────────┼───────────────────────────┼───────────────────────┼───────────────────────┼──────────────────────────────┤ +│   │   │   │  Total │ 131,117,072 (524.5 MB)  │ +└─────────────────────────────────┴───────────────────────────┴───────────────────────┴───────────────────────┴──────────────────────────────┘ +  + Total Parameters: 131,117,072 (524.5 MB)  + + +DiT: Input of shape (1, 32, 32, 4) dtype float32 +DiT: After patch embed, shape is (1, 256, 768) dtype bfloat16 +DiT: Patch Embed of shape (1, 260, 768) dtype bfloat16 +DiT: Conditioning of shape (1, 768) dtype float32 +selfh idden 768 +self heads 12 +hw_swq 16 +xshape (1, 260, 768) +Loaded checkpoint from 6040 seconds ago. + + parameter shapes: +('PatchEmbed_0', 'Conv_0', 'kernel'): (2, 2, 4, 768) +('PatchEmbed_0', 'Conv_0', 'bias'): (768,) +('PatchEmbed_1', 'Conv_0', 'kernel'): (2, 2, 4, 768) +('PatchEmbed_1', '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', 'SwiGLUFFN_0', 'Dense_0', 'kernel'): (768, 4096) +('DiTBlock_0', 'SwiGLUFFN_0', 'Dense_0', 'bias'): (4096,) +('DiTBlock_0', 'SwiGLUFFN_0', 'Dense_1', 'kernel'): (2048, 768) +('DiTBlock_0', 'SwiGLUFFN_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', 'SwiGLUFFN_0', 'Dense_0', 'kernel'): (768, 4096) +('DiTBlock_1', 'SwiGLUFFN_0', 'Dense_0', 'bias'): (4096,) +('DiTBlock_1', 'SwiGLUFFN_0', 'Dense_1', 'kernel'): (2048, 768) +('DiTBlock_1', 'SwiGLUFFN_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', 'SwiGLUFFN_0', 'Dense_0', 'kernel'): (768, 4096) +('DiTBlock_2', 'SwiGLUFFN_0', 'Dense_0', 'bias'): (4096,) +('DiTBlock_2', 'SwiGLUFFN_0', 'Dense_1', 'kernel'): (2048, 768) +('DiTBlock_2', 'SwiGLUFFN_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', 'SwiGLUFFN_0', 'Dense_0', 'kernel'): (768, 4096) +('DiTBlock_3', 'SwiGLUFFN_0', 'Dense_0', 'bias'): (4096,) +('DiTBlock_3', 'SwiGLUFFN_0', 'Dense_1', 'kernel'): (2048, 768) +('DiTBlock_3', 'SwiGLUFFN_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', 'SwiGLUFFN_0', 'Dense_0', 'kernel'): (768, 4096) +('DiTBlock_4', 'SwiGLUFFN_0', 'Dense_0', 'bias'): (4096,) +('DiTBlock_4', 'SwiGLUFFN_0', 'Dense_1', 'kernel'): (2048, 768) +('DiTBlock_4', 'SwiGLUFFN_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', 'SwiGLUFFN_0', 'Dense_0', 'kernel'): (768, 4096) +('DiTBlock_5', 'SwiGLUFFN_0', 'Dense_0', 'bias'): (4096,) +('DiTBlock_5', 'SwiGLUFFN_0', 'Dense_1', 'kernel'): (2048, 768) +('DiTBlock_5', 'SwiGLUFFN_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', 'SwiGLUFFN_0', 'Dense_0', 'kernel'): (768, 4096) +('DiTBlock_6', 'SwiGLUFFN_0', 'Dense_0', 'bias'): (4096,) +('DiTBlock_6', 'SwiGLUFFN_0', 'Dense_1', 'kernel'): (2048, 768) +('DiTBlock_6', 'SwiGLUFFN_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', 'SwiGLUFFN_0', 'Dense_0', 'kernel'): (768, 4096) +('DiTBlock_7', 'SwiGLUFFN_0', 'Dense_0', 'bias'): (4096,) +('DiTBlock_7', 'SwiGLUFFN_0', 'Dense_1', 'kernel'): (2048, 768) +('DiTBlock_7', 'SwiGLUFFN_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', 'SwiGLUFFN_0', 'Dense_0', 'kernel'): (768, 4096) +('DiTBlock_8', 'SwiGLUFFN_0', 'Dense_0', 'bias'): (4096,) +('DiTBlock_8', 'SwiGLUFFN_0', 'Dense_1', 'kernel'): (2048, 768) +('DiTBlock_8', 'SwiGLUFFN_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', 'SwiGLUFFN_0', 'Dense_0', 'kernel'): (768, 4096) +('DiTBlock_9', 'SwiGLUFFN_0', 'Dense_0', 'bias'): (4096,) +('DiTBlock_9', 'SwiGLUFFN_0', 'Dense_1', 'kernel'): (2048, 768) +('DiTBlock_9', 'SwiGLUFFN_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', 'SwiGLUFFN_0', 'Dense_0', 'kernel'): (768, 4096) +('DiTBlock_10', 'SwiGLUFFN_0', 'Dense_0', 'bias'): (4096,) +('DiTBlock_10', 'SwiGLUFFN_0', 'Dense_1', 'kernel'): (2048, 768) +('DiTBlock_10', 'SwiGLUFFN_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', 'SwiGLUFFN_0', 'Dense_0', 'kernel'): (768, 4096) +('DiTBlock_11', 'SwiGLUFFN_0', 'Dense_0', 'bias'): (4096,) +('DiTBlock_11', 'SwiGLUFFN_0', 'Dense_1', 'kernel'): (2048, 768) +('DiTBlock_11', 'SwiGLUFFN_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) + + 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', 'SwiGLUFFN_0', 'Dense_0', 'bias'): (1, 4096) +('DiTBlock_0', 'SwiGLUFFN_0', 'Dense_0', 'kernel'): (1, 768, 4096) +('DiTBlock_0', 'SwiGLUFFN_0', 'Dense_1', 'bias'): (1, 768) +('DiTBlock_0', 'SwiGLUFFN_0', 'Dense_1', 'kernel'): (1, 2048, 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', 'SwiGLUFFN_0', 'Dense_0', 'bias'): (1, 4096) +('DiTBlock_1', 'SwiGLUFFN_0', 'Dense_0', 'kernel'): (1, 768, 4096) +('DiTBlock_1', 'SwiGLUFFN_0', 'Dense_1', 'bias'): (1, 768) +('DiTBlock_1', 'SwiGLUFFN_0', 'Dense_1', 'kernel'): (1, 2048, 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', 'SwiGLUFFN_0', 'Dense_0', 'bias'): (1, 4096) +('DiTBlock_10', 'SwiGLUFFN_0', 'Dense_0', 'kernel'): (1, 768, 4096) +('DiTBlock_10', 'SwiGLUFFN_0', 'Dense_1', 'bias'): (1, 768) +('DiTBlock_10', 'SwiGLUFFN_0', 'Dense_1', 'kernel'): (1, 2048, 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', 'SwiGLUFFN_0', 'Dense_0', 'bias'): (1, 4096) +('DiTBlock_11', 'SwiGLUFFN_0', 'Dense_0', 'kernel'): (1, 768, 4096) +('DiTBlock_11', 'SwiGLUFFN_0', 'Dense_1', 'bias'): (1, 768) +('DiTBlock_11', 'SwiGLUFFN_0', 'Dense_1', 'kernel'): (1, 2048, 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', 'SwiGLUFFN_0', 'Dense_0', 'bias'): (1, 4096) +('DiTBlock_2', 'SwiGLUFFN_0', 'Dense_0', 'kernel'): (1, 768, 4096) +('DiTBlock_2', 'SwiGLUFFN_0', 'Dense_1', 'bias'): (1, 768) +('DiTBlock_2', 'SwiGLUFFN_0', 'Dense_1', 'kernel'): (1, 2048, 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', 'SwiGLUFFN_0', 'Dense_0', 'bias'): (1, 4096) +('DiTBlock_3', 'SwiGLUFFN_0', 'Dense_0', 'kernel'): (1, 768, 4096) +('DiTBlock_3', 'SwiGLUFFN_0', 'Dense_1', 'bias'): (1, 768) +('DiTBlock_3', 'SwiGLUFFN_0', 'Dense_1', 'kernel'): (1, 2048, 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', 'SwiGLUFFN_0', 'Dense_0', 'bias'): (1, 4096) +('DiTBlock_4', 'SwiGLUFFN_0', 'Dense_0', 'kernel'): (1, 768, 4096) +('DiTBlock_4', 'SwiGLUFFN_0', 'Dense_1', 'bias'): (1, 768) +('DiTBlock_4', 'SwiGLUFFN_0', 'Dense_1', 'kernel'): (1, 2048, 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', 'SwiGLUFFN_0', 'Dense_0', 'bias'): (1, 4096) +('DiTBlock_5', 'SwiGLUFFN_0', 'Dense_0', 'kernel'): (1, 768, 4096) +('DiTBlock_5', 'SwiGLUFFN_0', 'Dense_1', 'bias'): (1, 768) +('DiTBlock_5', 'SwiGLUFFN_0', 'Dense_1', 'kernel'): (1, 2048, 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', 'SwiGLUFFN_0', 'Dense_0', 'bias'): (1, 4096) +('DiTBlock_6', 'SwiGLUFFN_0', 'Dense_0', 'kernel'): (1, 768, 4096) +('DiTBlock_6', 'SwiGLUFFN_0', 'Dense_1', 'bias'): (1, 768) +('DiTBlock_6', 'SwiGLUFFN_0', 'Dense_1', 'kernel'): (1, 2048, 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', 'SwiGLUFFN_0', 'Dense_0', 'bias'): (1, 4096) +('DiTBlock_7', 'SwiGLUFFN_0', 'Dense_0', 'kernel'): (1, 768, 4096) +('DiTBlock_7', 'SwiGLUFFN_0', 'Dense_1', 'bias'): (1, 768) +('DiTBlock_7', 'SwiGLUFFN_0', 'Dense_1', 'kernel'): (1, 2048, 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', 'SwiGLUFFN_0', 'Dense_0', 'bias'): (1, 4096) +('DiTBlock_8', 'SwiGLUFFN_0', 'Dense_0', 'kernel'): (1, 768, 4096) +('DiTBlock_8', 'SwiGLUFFN_0', 'Dense_1', 'bias'): (1, 768) +('DiTBlock_8', 'SwiGLUFFN_0', 'Dense_1', 'kernel'): (1, 2048, 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', 'SwiGLUFFN_0', 'Dense_0', 'bias'): (1, 4096) +('DiTBlock_9', 'SwiGLUFFN_0', 'Dense_0', 'kernel'): (1, 768, 4096) +('DiTBlock_9', 'SwiGLUFFN_0', 'Dense_1', 'bias'): (1, 768) +('DiTBlock_9', 'SwiGLUFFN_0', 'Dense_1', 'kernel'): (1, 2048, 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) +('PatchEmbed_1', 'Conv_0', 'bias'): (1, 768) +('PatchEmbed_1', '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', 'SwiGLUFFN_0', 'Dense_0', 'bias'): (1, 4096) +('DiTBlock_0', 'SwiGLUFFN_0', 'Dense_0', 'kernel'): (1, 768, 4096) +('DiTBlock_0', 'SwiGLUFFN_0', 'Dense_1', 'bias'): (1, 768) +('DiTBlock_0', 'SwiGLUFFN_0', 'Dense_1', 'kernel'): (1, 2048, 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', 'SwiGLUFFN_0', 'Dense_0', 'bias'): (1, 4096) +('DiTBlock_1', 'SwiGLUFFN_0', 'Dense_0', 'kernel'): (1, 768, 4096) +('DiTBlock_1', 'SwiGLUFFN_0', 'Dense_1', 'bias'): (1, 768) +('DiTBlock_1', 'SwiGLUFFN_0', 'Dense_1', 'kernel'): (1, 2048, 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', 'SwiGLUFFN_0', 'Dense_0', 'bias'): (1, 4096) +('DiTBlock_10', 'SwiGLUFFN_0', 'Dense_0', 'kernel'): (1, 768, 4096) +('DiTBlock_10', 'SwiGLUFFN_0', 'Dense_1', 'bias'): (1, 768) +('DiTBlock_10', 'SwiGLUFFN_0', 'Dense_1', 'kernel'): (1, 2048, 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', 'SwiGLUFFN_0', 'Dense_0', 'bias'): (1, 4096) +('DiTBlock_11', 'SwiGLUFFN_0', 'Dense_0', 'kernel'): (1, 768, 4096) +('DiTBlock_11', 'SwiGLUFFN_0', 'Dense_1', 'bias'): (1, 768) +('DiTBlock_11', 'SwiGLUFFN_0', 'Dense_1', 'kernel'): (1, 2048, 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', 'SwiGLUFFN_0', 'Dense_0', 'bias'): (1, 4096) +('DiTBlock_2', 'SwiGLUFFN_0', 'Dense_0', 'kernel'): (1, 768, 4096) +('DiTBlock_2', 'SwiGLUFFN_0', 'Dense_1', 'bias'): (1, 768) +('DiTBlock_2', 'SwiGLUFFN_0', 'Dense_1', 'kernel'): (1, 2048, 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', 'SwiGLUFFN_0', 'Dense_0', 'bias'): (1, 4096) +('DiTBlock_3', 'SwiGLUFFN_0', 'Dense_0', 'kernel'): (1, 768, 4096) +('DiTBlock_3', 'SwiGLUFFN_0', 'Dense_1', 'bias'): (1, 768) +('DiTBlock_3', 'SwiGLUFFN_0', 'Dense_1', 'kernel'): (1, 2048, 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', 'SwiGLUFFN_0', 'Dense_0', 'bias'): (1, 4096) +('DiTBlock_4', 'SwiGLUFFN_0', 'Dense_0', 'kernel'): (1, 768, 4096) +('DiTBlock_4', 'SwiGLUFFN_0', 'Dense_1', 'bias'): (1, 768) +('DiTBlock_4', 'SwiGLUFFN_0', 'Dense_1', 'kernel'): (1, 2048, 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', 'SwiGLUFFN_0', 'Dense_0', 'bias'): (1, 4096) +('DiTBlock_5', 'SwiGLUFFN_0', 'Dense_0', 'kernel'): (1, 768, 4096) +('DiTBlock_5', 'SwiGLUFFN_0', 'Dense_1', 'bias'): (1, 768) +('DiTBlock_5', 'SwiGLUFFN_0', 'Dense_1', 'kernel'): (1, 2048, 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', 'SwiGLUFFN_0', 'Dense_0', 'bias'): (1, 4096) +('DiTBlock_6', 'SwiGLUFFN_0', 'Dense_0', 'kernel'): (1, 768, 4096) +('DiTBlock_6', 'SwiGLUFFN_0', 'Dense_1', 'bias'): (1, 768) +('DiTBlock_6', 'SwiGLUFFN_0', 'Dense_1', 'kernel'): (1, 2048, 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', 'SwiGLUFFN_0', 'Dense_0', 'bias'): (1, 4096) +('DiTBlock_7', 'SwiGLUFFN_0', 'Dense_0', 'kernel'): (1, 768, 4096) +('DiTBlock_7', 'SwiGLUFFN_0', 'Dense_1', 'bias'): (1, 768) +('DiTBlock_7', 'SwiGLUFFN_0', 'Dense_1', 'kernel'): (1, 2048, 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', 'SwiGLUFFN_0', 'Dense_0', 'bias'): (1, 4096) +('DiTBlock_8', 'SwiGLUFFN_0', 'Dense_0', 'kernel'): (1, 768, 4096) +('DiTBlock_8', 'SwiGLUFFN_0', 'Dense_1', 'bias'): (1, 768) +('DiTBlock_8', 'SwiGLUFFN_0', 'Dense_1', 'kernel'): (1, 2048, 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', 'SwiGLUFFN_0', 'Dense_0', 'bias'): (1, 4096) +('DiTBlock_9', 'SwiGLUFFN_0', 'Dense_0', 'kernel'): (1, 768, 4096) +('DiTBlock_9', 'SwiGLUFFN_0', 'Dense_1', 'bias'): (1, 768) +('DiTBlock_9', 'SwiGLUFFN_0', 'Dense_1', 'kernel'): (1, 2048, 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) +('PatchEmbed_1', 'Conv_0', 'bias'): (1, 768) +('PatchEmbed_1', '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', 'SwiGLUFFN_0', 'Dense_0', 'bias'): (1, 4096) +('DiTBlock_0', 'SwiGLUFFN_0', 'Dense_0', 'kernel'): (1, 768, 4096) +('DiTBlock_0', 'SwiGLUFFN_0', 'Dense_1', 'bias'): (1, 768) +('DiTBlock_0', 'SwiGLUFFN_0', 'Dense_1', 'kernel'): (1, 2048, 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', 'SwiGLUFFN_0', 'Dense_0', 'bias'): (1, 4096) +('DiTBlock_1', 'SwiGLUFFN_0', 'Dense_0', 'kernel'): (1, 768, 4096) +('DiTBlock_1', 'SwiGLUFFN_0', 'Dense_1', 'bias'): (1, 768) +('DiTBlock_1', 'SwiGLUFFN_0', 'Dense_1', 'kernel'): (1, 2048, 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', 'SwiGLUFFN_0', 'Dense_0', 'bias'): (1, 4096) +('DiTBlock_10', 'SwiGLUFFN_0', 'Dense_0', 'kernel'): (1, 768, 4096) +('DiTBlock_10', 'SwiGLUFFN_0', 'Dense_1', 'bias'): (1, 768) +('DiTBlock_10', 'SwiGLUFFN_0', 'Dense_1', 'kernel'): (1, 2048, 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', 'SwiGLUFFN_0', 'Dense_0', 'bias'): (1, 4096) +('DiTBlock_11', 'SwiGLUFFN_0', 'Dense_0', 'kernel'): (1, 768, 4096) +('DiTBlock_11', 'SwiGLUFFN_0', 'Dense_1', 'bias'): (1, 768) +('DiTBlock_11', 'SwiGLUFFN_0', 'Dense_1', 'kernel'): (1, 2048, 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', 'SwiGLUFFN_0', 'Dense_0', 'bias'): (1, 4096) +('DiTBlock_2', 'SwiGLUFFN_0', 'Dense_0', 'kernel'): (1, 768, 4096) +('DiTBlock_2', 'SwiGLUFFN_0', 'Dense_1', 'bias'): (1, 768) +('DiTBlock_2', 'SwiGLUFFN_0', 'Dense_1', 'kernel'): (1, 2048, 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', 'SwiGLUFFN_0', 'Dense_0', 'bias'): (1, 4096) +('DiTBlock_3', 'SwiGLUFFN_0', 'Dense_0', 'kernel'): (1, 768, 4096) +('DiTBlock_3', 'SwiGLUFFN_0', 'Dense_1', 'bias'): (1, 768) +('DiTBlock_3', 'SwiGLUFFN_0', 'Dense_1', 'kernel'): (1, 2048, 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', 'SwiGLUFFN_0', 'Dense_0', 'bias'): (1, 4096) +('DiTBlock_4', 'SwiGLUFFN_0', 'Dense_0', 'kernel'): (1, 768, 4096) +('DiTBlock_4', 'SwiGLUFFN_0', 'Dense_1', 'bias'): (1, 768) +('DiTBlock_4', 'SwiGLUFFN_0', 'Dense_1', 'kernel'): (1, 2048, 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', 'SwiGLUFFN_0', 'Dense_0', 'bias'): (1, 4096) +('DiTBlock_5', 'SwiGLUFFN_0', 'Dense_0', 'kernel'): (1, 768, 4096) +('DiTBlock_5', 'SwiGLUFFN_0', 'Dense_1', 'bias'): (1, 768) +('DiTBlock_5', 'SwiGLUFFN_0', 'Dense_1', 'kernel'): (1, 2048, 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', 'SwiGLUFFN_0', 'Dense_0', 'bias'): (1, 4096) +('DiTBlock_6', 'SwiGLUFFN_0', 'Dense_0', 'kernel'): (1, 768, 4096) +('DiTBlock_6', 'SwiGLUFFN_0', 'Dense_1', 'bias'): (1, 768) +('DiTBlock_6', 'SwiGLUFFN_0', 'Dense_1', 'kernel'): (1, 2048, 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', 'SwiGLUFFN_0', 'Dense_0', 'bias'): (1, 4096) +('DiTBlock_7', 'SwiGLUFFN_0', 'Dense_0', 'kernel'): (1, 768, 4096) +('DiTBlock_7', 'SwiGLUFFN_0', 'Dense_1', 'bias'): (1, 768) +('DiTBlock_7', 'SwiGLUFFN_0', 'Dense_1', 'kernel'): (1, 2048, 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', 'SwiGLUFFN_0', 'Dense_0', 'bias'): (1, 4096) +('DiTBlock_8', 'SwiGLUFFN_0', 'Dense_0', 'kernel'): (1, 768, 4096) +('DiTBlock_8', 'SwiGLUFFN_0', 'Dense_1', 'bias'): (1, 768) +('DiTBlock_8', 'SwiGLUFFN_0', 'Dense_1', 'kernel'): (1, 2048, 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', 'SwiGLUFFN_0', 'Dense_0', 'bias'): (1, 4096) +('DiTBlock_9', 'SwiGLUFFN_0', 'Dense_0', 'kernel'): (1, 768, 4096) +('DiTBlock_9', 'SwiGLUFFN_0', 'Dense_1', 'bias'): (1, 768) +('DiTBlock_9', 'SwiGLUFFN_0', 'Dense_1', 'kernel'): (1, 2048, 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) +('PatchEmbed_1', 'Conv_0', 'bias'): (1, 768) +('PatchEmbed_1', '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', 'SwiGLUFFN_0', 'Dense_0', 'bias'): (1, 4096) +('DiTBlock_0', 'SwiGLUFFN_0', 'Dense_0', 'kernel'): (1, 768, 4096) +('DiTBlock_0', 'SwiGLUFFN_0', 'Dense_1', 'bias'): (1, 768) +('DiTBlock_0', 'SwiGLUFFN_0', 'Dense_1', 'kernel'): (1, 2048, 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', 'SwiGLUFFN_0', 'Dense_0', 'bias'): (1, 4096) +('DiTBlock_1', 'SwiGLUFFN_0', 'Dense_0', 'kernel'): (1, 768, 4096) +('DiTBlock_1', 'SwiGLUFFN_0', 'Dense_1', 'bias'): (1, 768) +('DiTBlock_1', 'SwiGLUFFN_0', 'Dense_1', 'kernel'): (1, 2048, 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', 'SwiGLUFFN_0', 'Dense_0', 'bias'): (1, 4096) +('DiTBlock_10', 'SwiGLUFFN_0', 'Dense_0', 'kernel'): (1, 768, 4096) +('DiTBlock_10', 'SwiGLUFFN_0', 'Dense_1', 'bias'): (1, 768) +('DiTBlock_10', 'SwiGLUFFN_0', 'Dense_1', 'kernel'): (1, 2048, 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', 'SwiGLUFFN_0', 'Dense_0', 'bias'): (1, 4096) +('DiTBlock_11', 'SwiGLUFFN_0', 'Dense_0', 'kernel'): (1, 768, 4096) +('DiTBlock_11', 'SwiGLUFFN_0', 'Dense_1', 'bias'): (1, 768) +('DiTBlock_11', 'SwiGLUFFN_0', 'Dense_1', 'kernel'): (1, 2048, 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', 'SwiGLUFFN_0', 'Dense_0', 'bias'): (1, 4096) +('DiTBlock_2', 'SwiGLUFFN_0', 'Dense_0', 'kernel'): (1, 768, 4096) +('DiTBlock_2', 'SwiGLUFFN_0', 'Dense_1', 'bias'): (1, 768) +('DiTBlock_2', 'SwiGLUFFN_0', 'Dense_1', 'kernel'): (1, 2048, 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', 'SwiGLUFFN_0', 'Dense_0', 'bias'): (1, 4096) +('DiTBlock_3', 'SwiGLUFFN_0', 'Dense_0', 'kernel'): (1, 768, 4096) +('DiTBlock_3', 'SwiGLUFFN_0', 'Dense_1', 'bias'): (1, 768) +('DiTBlock_3', 'SwiGLUFFN_0', 'Dense_1', 'kernel'): (1, 2048, 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', 'SwiGLUFFN_0', 'Dense_0', 'bias'): (1, 4096) +('DiTBlock_4', 'SwiGLUFFN_0', 'Dense_0', 'kernel'): (1, 768, 4096) +('DiTBlock_4', 'SwiGLUFFN_0', 'Dense_1', 'bias'): (1, 768) +('DiTBlock_4', 'SwiGLUFFN_0', 'Dense_1', 'kernel'): (1, 2048, 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', 'SwiGLUFFN_0', 'Dense_0', 'bias'): (1, 4096) +('DiTBlock_5', 'SwiGLUFFN_0', 'Dense_0', 'kernel'): (1, 768, 4096) +('DiTBlock_5', 'SwiGLUFFN_0', 'Dense_1', 'bias'): (1, 768) +('DiTBlock_5', 'SwiGLUFFN_0', 'Dense_1', 'kernel'): (1, 2048, 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', 'SwiGLUFFN_0', 'Dense_0', 'bias'): (1, 4096) +('DiTBlock_6', 'SwiGLUFFN_0', 'Dense_0', 'kernel'): (1, 768, 4096) +('DiTBlock_6', 'SwiGLUFFN_0', 'Dense_1', 'bias'): (1, 768) +('DiTBlock_6', 'SwiGLUFFN_0', 'Dense_1', 'kernel'): (1, 2048, 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', 'SwiGLUFFN_0', 'Dense_0', 'bias'): (1, 4096) +('DiTBlock_7', 'SwiGLUFFN_0', 'Dense_0', 'kernel'): (1, 768, 4096) +('DiTBlock_7', 'SwiGLUFFN_0', 'Dense_1', 'bias'): (1, 768) +('DiTBlock_7', 'SwiGLUFFN_0', 'Dense_1', 'kernel'): (1, 2048, 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', 'SwiGLUFFN_0', 'Dense_0', 'bias'): (1, 4096) +('DiTBlock_8', 'SwiGLUFFN_0', 'Dense_0', 'kernel'): (1, 768, 4096) +('DiTBlock_8', 'SwiGLUFFN_0', 'Dense_1', 'bias'): (1, 768) +('DiTBlock_8', 'SwiGLUFFN_0', 'Dense_1', 'kernel'): (1, 2048, 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', 'SwiGLUFFN_0', 'Dense_0', 'bias'): (1, 4096) +('DiTBlock_9', 'SwiGLUFFN_0', 'Dense_0', 'kernel'): (1, 768, 4096) +('DiTBlock_9', 'SwiGLUFFN_0', 'Dense_1', 'bias'): (1, 768) +('DiTBlock_9', 'SwiGLUFFN_0', 'Dense_1', 'kernel'): (1, 2048, 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) +('PatchEmbed_1', 'Conv_0', 'bias'): (1, 768) +('PatchEmbed_1', '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', 'SwiGLUFFN_0', 'Dense_0', 'bias'): (4096,) +('DiTBlock_0', 'SwiGLUFFN_0', 'Dense_0', 'kernel'): (768, 4096) +('DiTBlock_0', 'SwiGLUFFN_0', 'Dense_1', 'bias'): (768,) +('DiTBlock_0', 'SwiGLUFFN_0', 'Dense_1', 'kernel'): (2048, 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', 'SwiGLUFFN_0', 'Dense_0', 'bias'): (4096,) +('DiTBlock_1', 'SwiGLUFFN_0', 'Dense_0', 'kernel'): (768, 4096) +('DiTBlock_1', 'SwiGLUFFN_0', 'Dense_1', 'bias'): (768,) +('DiTBlock_1', 'SwiGLUFFN_0', 'Dense_1', 'kernel'): (2048, 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', 'SwiGLUFFN_0', 'Dense_0', 'bias'): (4096,) +('DiTBlock_10', 'SwiGLUFFN_0', 'Dense_0', 'kernel'): (768, 4096) +('DiTBlock_10', 'SwiGLUFFN_0', 'Dense_1', 'bias'): (768,) +('DiTBlock_10', 'SwiGLUFFN_0', 'Dense_1', 'kernel'): (2048, 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', 'SwiGLUFFN_0', 'Dense_0', 'bias'): (4096,) +('DiTBlock_11', 'SwiGLUFFN_0', 'Dense_0', 'kernel'): (768, 4096) +('DiTBlock_11', 'SwiGLUFFN_0', 'Dense_1', 'bias'): (768,) +('DiTBlock_11', 'SwiGLUFFN_0', 'Dense_1', 'kernel'): (2048, 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', 'SwiGLUFFN_0', 'Dense_0', 'bias'): (4096,) +('DiTBlock_2', 'SwiGLUFFN_0', 'Dense_0', 'kernel'): (768, 4096) +('DiTBlock_2', 'SwiGLUFFN_0', 'Dense_1', 'bias'): (768,) +('DiTBlock_2', 'SwiGLUFFN_0', 'Dense_1', 'kernel'): (2048, 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', 'SwiGLUFFN_0', 'Dense_0', 'bias'): (4096,) +('DiTBlock_3', 'SwiGLUFFN_0', 'Dense_0', 'kernel'): (768, 4096) +('DiTBlock_3', 'SwiGLUFFN_0', 'Dense_1', 'bias'): (768,) +('DiTBlock_3', 'SwiGLUFFN_0', 'Dense_1', 'kernel'): (2048, 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', 'SwiGLUFFN_0', 'Dense_0', 'bias'): (4096,) +('DiTBlock_4', 'SwiGLUFFN_0', 'Dense_0', 'kernel'): (768, 4096) +('DiTBlock_4', 'SwiGLUFFN_0', 'Dense_1', 'bias'): (768,) +('DiTBlock_4', 'SwiGLUFFN_0', 'Dense_1', 'kernel'): (2048, 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', 'SwiGLUFFN_0', 'Dense_0', 'bias'): (4096,) +('DiTBlock_5', 'SwiGLUFFN_0', 'Dense_0', 'kernel'): (768, 4096) +('DiTBlock_5', 'SwiGLUFFN_0', 'Dense_1', 'bias'): (768,) +('DiTBlock_5', 'SwiGLUFFN_0', 'Dense_1', 'kernel'): (2048, 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', 'SwiGLUFFN_0', 'Dense_0', 'bias'): (4096,) +('DiTBlock_6', 'SwiGLUFFN_0', 'Dense_0', 'kernel'): (768, 4096) +('DiTBlock_6', 'SwiGLUFFN_0', 'Dense_1', 'bias'): (768,) +('DiTBlock_6', 'SwiGLUFFN_0', 'Dense_1', 'kernel'): (2048, 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', 'SwiGLUFFN_0', 'Dense_0', 'bias'): (4096,) +('DiTBlock_7', 'SwiGLUFFN_0', 'Dense_0', 'kernel'): (768, 4096) +('DiTBlock_7', 'SwiGLUFFN_0', 'Dense_1', 'bias'): (768,) +('DiTBlock_7', 'SwiGLUFFN_0', 'Dense_1', 'kernel'): (2048, 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', 'SwiGLUFFN_0', 'Dense_0', 'bias'): (4096,) +('DiTBlock_8', 'SwiGLUFFN_0', 'Dense_0', 'kernel'): (768, 4096) +('DiTBlock_8', 'SwiGLUFFN_0', 'Dense_1', 'bias'): (768,) +('DiTBlock_8', 'SwiGLUFFN_0', 'Dense_1', 'kernel'): (2048, 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', 'SwiGLUFFN_0', 'Dense_0', 'bias'): (4096,) +('DiTBlock_9', 'SwiGLUFFN_0', 'Dense_0', 'kernel'): (768, 4096) +('DiTBlock_9', 'SwiGLUFFN_0', 'Dense_1', 'bias'): (768,) +('DiTBlock_9', 'SwiGLUFFN_0', 'Dense_1', 'kernel'): (2048, 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) +('PatchEmbed_1', 'Conv_0', 'bias'): (768,) +('PatchEmbed_1', '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 +Calc FID for CFG 1.0 and denoise_timesteps 128 +DiT: Input of shape (256, 32, 32, 4) dtype float32 +DiT: After patch embed, shape is (256, 256, 768) dtype bfloat16 +DiT: Patch Embed of shape (256, 260, 768) dtype bfloat16 +DiT: Conditioning of shape (256, 768) dtype float32 +selfh idden 768 +self heads 12 +hw_swq 16 +xshape (256, 260, 768) +FID is 24.715682983398438 +Calc FID for CFG 1.0 and denoise_timesteps 64 +DiT: Input of shape (256, 32, 32, 4) dtype float32 +DiT: After patch embed, shape is (256, 256, 768) dtype bfloat16 +DiT: Patch Embed of shape (256, 260, 768) dtype bfloat16 +DiT: Conditioning of shape (256, 768) dtype float32 +selfh idden 768 +self heads 12 +hw_swq 16 +xshape (256, 260, 768) +FID is 9.955840110778809 +Calc FID for CFG 1.0 and denoise_timesteps 32 +DiT: Input of shape (256, 32, 32, 4) dtype float32 +DiT: After patch embed, shape is (256, 256, 768) dtype bfloat16 +DiT: Patch Embed of shape (256, 260, 768) dtype bfloat16 +DiT: Conditioning of shape (256, 768) dtype float32 +selfh idden 768 +self heads 12 +hw_swq 16 +xshape (256, 260, 768) +FID is 9.729120254516602 +Calc FID for CFG 1.0 and denoise_timesteps 16 +DiT: Input of shape (256, 32, 32, 4) dtype float32 +DiT: After patch embed, shape is (256, 256, 768) dtype bfloat16 +DiT: Patch Embed of shape (256, 260, 768) dtype bfloat16 +DiT: Conditioning of shape (256, 768) dtype float32 +selfh idden 768 +self heads 12 +hw_swq 16 +xshape (256, 260, 768) +FID is 10.908047676086426 +Calc FID for CFG 1.0 and denoise_timesteps 8 +DiT: Input of shape (256, 32, 32, 4) dtype float32 +DiT: After patch embed, shape is (256, 256, 768) dtype bfloat16 +DiT: Patch Embed of shape (256, 260, 768) dtype bfloat16 +DiT: Conditioning of shape (256, 768) dtype float32 +selfh idden 768 +self heads 12 +hw_swq 16 +xshape (256, 260, 768) +FID is 11.92203426361084 +Calc FID for CFG 1.0 and denoise_timesteps 4 +DiT: Input of shape (256, 32, 32, 4) dtype float32 +DiT: After patch embed, shape is (256, 256, 768) dtype bfloat16 +DiT: Patch Embed of shape (256, 260, 768) dtype bfloat16 +DiT: Conditioning of shape (256, 768) dtype float32 +selfh idden 768 +self heads 12 +hw_swq 16 +xshape (256, 260, 768) +FID is 13.520551681518555 +Calc FID for CFG 1.0 and denoise_timesteps 2 +DiT: Input of shape (256, 32, 32, 4) dtype float32 +DiT: After patch embed, shape is (256, 256, 768) dtype bfloat16 +DiT: Patch Embed of shape (256, 260, 768) dtype bfloat16 +DiT: Conditioning of shape (256, 768) dtype float32 +selfh idden 768 +self heads 12 +hw_swq 16 +xshape (256, 260, 768) +FID is 17.19525909423828 +Calc FID for CFG 1.0 and denoise_timesteps 1 +DiT: Input of shape (256, 32, 32, 4) dtype float32 +DiT: After patch embed, shape is (256, 256, 768) dtype bfloat16 +DiT: Patch Embed of shape (256, 260, 768) dtype bfloat16 +DiT: Conditioning of shape (256, 768) dtype float32 +selfh idden 768 +self heads 12 +hw_swq 16 +xshape (256, 260, 768) +FID is 27.250843048095703 +Calc FID for CFG 1.25 and denoise_timesteps 128 +DiT: Input of shape (256, 32, 32, 4) dtype float32 +DiT: After patch embed, shape is (256, 256, 768) dtype bfloat16 +DiT: Patch Embed of shape (256, 260, 768) dtype bfloat16 +DiT: Conditioning of shape (256, 768) dtype float32 +selfh idden 768 +self heads 12 +hw_swq 16 +xshape (256, 260, 768) +FID is 12.47612476348877 +Calc FID for CFG 1.25 and denoise_timesteps 64 +DiT: Input of shape (256, 32, 32, 4) dtype float32 +DiT: After patch embed, shape is (256, 256, 768) dtype bfloat16 +DiT: Patch Embed of shape (256, 260, 768) dtype bfloat16 +DiT: Conditioning of shape (256, 768) dtype float32 +selfh idden 768 +self heads 12 +hw_swq 16 +xshape (256, 260, 768) +FID is 6.298523426055908 +Calc FID for CFG 1.25 and denoise_timesteps 32 +DiT: Input of shape (256, 32, 32, 4) dtype float32 +DiT: After patch embed, shape is (256, 256, 768) dtype bfloat16 +DiT: Patch Embed of shape (256, 260, 768) dtype bfloat16 +DiT: Conditioning of shape (256, 768) dtype float32 +selfh idden 768 +self heads 12 +hw_swq 16 +xshape (256, 260, 768) +FID is 6.690338611602783 +Calc FID for CFG 1.25 and denoise_timesteps 16 +DiT: Input of shape (256, 32, 32, 4) dtype float32 +DiT: After patch embed, shape is (256, 256, 768) dtype bfloat16 +DiT: Patch Embed of shape (256, 260, 768) dtype bfloat16 +DiT: Conditioning of shape (256, 768) dtype float32 +selfh idden 768 +self heads 12 +hw_swq 16 +xshape (256, 260, 768) +FID is 7.361817836761475 +Calc FID for CFG 1.25 and denoise_timesteps 8 +DiT: Input of shape (256, 32, 32, 4) dtype float32 +DiT: After patch embed, shape is (256, 256, 768) dtype bfloat16 +DiT: Patch Embed of shape (256, 260, 768) dtype bfloat16 +DiT: Conditioning of shape (256, 768) dtype float32 +selfh idden 768 +self heads 12 +hw_swq 16 +xshape (256, 260, 768) +FID is 8.35059928894043 +Calc FID for CFG 1.25 and denoise_timesteps 4 +DiT: Input of shape (256, 32, 32, 4) dtype float32 +DiT: After patch embed, shape is (256, 256, 768) dtype bfloat16 +DiT: Patch Embed of shape (256, 260, 768) dtype bfloat16 +DiT: Conditioning of shape (256, 768) dtype float32 +selfh idden 768 +self heads 12 +hw_swq 16 +xshape (256, 260, 768) +FID is 9.583683967590332 +Calc FID for CFG 1.25 and denoise_timesteps 2 +DiT: Input of shape (256, 32, 32, 4) dtype float32 +DiT: After patch embed, shape is (256, 256, 768) dtype bfloat16 +DiT: Patch Embed of shape (256, 260, 768) dtype bfloat16 +DiT: Conditioning of shape (256, 768) dtype float32 +selfh idden 768 +self heads 12 +hw_swq 16 +xshape (256, 260, 768) +FID is 12.433704376220703 +Calc FID for CFG 1.25 and denoise_timesteps 1 +DiT: Input of shape (256, 32, 32, 4) dtype float32 +DiT: After patch embed, shape is (256, 256, 768) dtype bfloat16 +DiT: Patch Embed of shape (256, 260, 768) dtype bfloat16 +DiT: Conditioning of shape (256, 768) dtype float32 +selfh idden 768 +self heads 12 +hw_swq 16 +xshape (256, 260, 768) +FID is 19.964120864868164 +Calc FID for CFG 1.5 and denoise_timesteps 128 +DiT: Input of shape (256, 32, 32, 4) dtype float32 +DiT: After patch embed, shape is (256, 256, 768) dtype bfloat16 +DiT: Patch Embed of shape (256, 260, 768) dtype bfloat16 +DiT: Conditioning of shape (256, 768) dtype float32 +selfh idden 768 +self heads 12 +hw_swq 16 +xshape (256, 260, 768) +FID is 7.054877758026123 +Calc FID for CFG 1.5 and denoise_timesteps 64 +DiT: Input of shape (256, 32, 32, 4) dtype float32 +DiT: After patch embed, shape is (256, 256, 768) dtype bfloat16 +DiT: Patch Embed of shape (256, 260, 768) dtype bfloat16 +DiT: Conditioning of shape (256, 768) dtype float32 +selfh idden 768 +self heads 12 +hw_swq 16 +xshape (256, 260, 768) +FID is 6.7037506103515625 +Calc FID for CFG 1.5 and denoise_timesteps 32 +DiT: Input of shape (256, 32, 32, 4) dtype float32 +DiT: After patch embed, shape is (256, 256, 768) dtype bfloat16 +DiT: Patch Embed of shape (256, 260, 768) dtype bfloat16 +DiT: Conditioning of shape (256, 768) dtype float32 +selfh idden 768 +self heads 12 +hw_swq 16 +xshape (256, 260, 768) +FID is 7.221983909606934 +Calc FID for CFG 1.5 and denoise_timesteps 16 +DiT: Input of shape (256, 32, 32, 4) dtype float32 +DiT: After patch embed, shape is (256, 256, 768) dtype bfloat16 +DiT: Patch Embed of shape (256, 260, 768) dtype bfloat16 +DiT: Conditioning of shape (256, 768) dtype float32 +selfh idden 768 +self heads 12 +hw_swq 16 +xshape (256, 260, 768) +FID is 7.493730068206787 +Calc FID for CFG 1.5 and denoise_timesteps 8 +DiT: Input of shape (256, 32, 32, 4) dtype float32 +DiT: After patch embed, shape is (256, 256, 768) dtype bfloat16 +DiT: Patch Embed of shape (256, 260, 768) dtype bfloat16 +DiT: Conditioning of shape (256, 768) dtype float32 +selfh idden 768 +self heads 12 +hw_swq 16 +xshape (256, 260, 768) +FID is 8.149055480957031 +Calc FID for CFG 1.5 and denoise_timesteps 4 +DiT: Input of shape (256, 32, 32, 4) dtype float32 +DiT: After patch embed, shape is (256, 256, 768) dtype bfloat16 +DiT: Patch Embed of shape (256, 260, 768) dtype bfloat16 +DiT: Conditioning of shape (256, 768) dtype float32 +selfh idden 768 +self heads 12 +hw_swq 16 +xshape (256, 260, 768) +FID is 9.056492805480957 +Calc FID for CFG 1.5 and denoise_timesteps 2 +DiT: Input of shape (256, 32, 32, 4) dtype float32 +DiT: After patch embed, shape is (256, 256, 768) dtype bfloat16 +DiT: Patch Embed of shape (256, 260, 768) dtype bfloat16 +DiT: Conditioning of shape (256, 768) dtype float32 +selfh idden 768 +self heads 12 +hw_swq 16 +xshape (256, 260, 768) +FID is 11.344828605651855 +Calc FID for CFG 1.5 and denoise_timesteps 1 +DiT: Input of shape (256, 32, 32, 4) dtype float32 +DiT: After patch embed, shape is (256, 256, 768) dtype bfloat16 +DiT: Patch Embed of shape (256, 260, 768) dtype bfloat16 +DiT: Conditioning of shape (256, 768) dtype float32 +selfh idden 768 +self heads 12 +hw_swq 16 +xshape (256, 260, 768) +FID is 19.46041488647461 +Calc FID for CFG 1.75 and denoise_timesteps 128 +DiT: Input of shape (256, 32, 32, 4) dtype float32 +DiT: After patch embed, shape is (256, 256, 768) dtype bfloat16 +DiT: Patch Embed of shape (256, 260, 768) dtype bfloat16 +DiT: Conditioning of shape (256, 768) dtype float32 +selfh idden 768 +self heads 12 +hw_swq 16 +xshape (256, 260, 768) +FID is 5.365168571472168 +Calc FID for CFG 1.75 and denoise_timesteps 64 +DiT: Input of shape (256, 32, 32, 4) dtype float32 +DiT: After patch embed, shape is (256, 256, 768) dtype bfloat16 +DiT: Patch Embed of shape (256, 260, 768) dtype bfloat16 +DiT: Conditioning of shape (256, 768) dtype float32 +selfh idden 768 +self heads 12 +hw_swq 16 +xshape (256, 260, 768) +FID is 8.315924644470215 +Calc FID for CFG 1.75 and denoise_timesteps 32 +DiT: Input of shape (256, 32, 32, 4) dtype float32 +DiT: After patch embed, shape is (256, 256, 768) dtype bfloat16 +DiT: Patch Embed of shape (256, 260, 768) dtype bfloat16 +DiT: Conditioning of shape (256, 768) dtype float32 +selfh idden 768 +self heads 12 +hw_swq 16 +xshape (256, 260, 768) +FID is 8.780521392822266 +Calc FID for CFG 1.75 and denoise_timesteps 16 +DiT: Input of shape (256, 32, 32, 4) dtype float32 +DiT: After patch embed, shape is (256, 256, 768) dtype bfloat16 +DiT: Patch Embed of shape (256, 260, 768) dtype bfloat16 +DiT: Conditioning of shape (256, 768) dtype float32 +selfh idden 768 +self heads 12 +hw_swq 16 +xshape (256, 260, 768) +FID is 8.692272186279297 +Calc FID for CFG 1.75 and denoise_timesteps 8 +DiT: Input of shape (256, 32, 32, 4) dtype float32 +DiT: After patch embed, shape is (256, 256, 768) dtype bfloat16 +DiT: Patch Embed of shape (256, 260, 768) dtype bfloat16 +DiT: Conditioning of shape (256, 768) dtype float32 +selfh idden 768 +self heads 12 +hw_swq 16 +xshape (256, 260, 768) +FID is 9.109457969665527 +Calc FID for CFG 1.75 and denoise_timesteps 4 +DiT: Input of shape (256, 32, 32, 4) dtype float32 +DiT: After patch embed, shape is (256, 256, 768) dtype bfloat16 +DiT: Patch Embed of shape (256, 260, 768) dtype bfloat16 +DiT: Conditioning of shape (256, 768) dtype float32 +selfh idden 768 +self heads 12 +hw_swq 16 +xshape (256, 260, 768) +FID is 9.634443283081055 +Calc FID for CFG 1.75 and denoise_timesteps 2 +DiT: Input of shape (256, 32, 32, 4) dtype float32 +DiT: After patch embed, shape is (256, 256, 768) dtype bfloat16 +DiT: Patch Embed of shape (256, 260, 768) dtype bfloat16 +DiT: Conditioning of shape (256, 768) dtype float32 +selfh idden 768 +self heads 12 +hw_swq 16 +xshape (256, 260, 768) +FID is 11.575997352600098 +Calc FID for CFG 1.75 and denoise_timesteps 1 +DiT: Input of shape (256, 32, 32, 4) dtype float32 +DiT: After patch embed, shape is (256, 256, 768) dtype bfloat16 +DiT: Patch Embed of shape (256, 260, 768) dtype bfloat16 +DiT: Conditioning of shape (256, 768) dtype float32 +selfh idden 768 +self heads 12 +hw_swq 16 +xshape (256, 260, 768) +FID is 22.301528930664062 +Calc FID for CFG 2.0 and denoise_timesteps 128 +DiT: Input of shape (256, 32, 32, 4) dtype float32 +DiT: After patch embed, shape is (256, 256, 768) dtype bfloat16 +DiT: Patch Embed of shape (256, 260, 768) dtype bfloat16 +DiT: Conditioning of shape (256, 768) dtype float32 +selfh idden 768 +self heads 12 +hw_swq 16 +xshape (256, 260, 768) +FID is 5.619327068328857 +Calc FID for CFG 2.0 and denoise_timesteps 64 +DiT: Input of shape (256, 32, 32, 4) dtype float32 +DiT: After patch embed, shape is (256, 256, 768) dtype bfloat16 +DiT: Patch Embed of shape (256, 260, 768) dtype bfloat16 +DiT: Conditioning of shape (256, 768) dtype float32 +selfh idden 768 +self heads 12 +hw_swq 16 +xshape (256, 260, 768) +FID is 10.156737327575684 +Calc FID for CFG 2.0 and denoise_timesteps 32 +DiT: Input of shape (256, 32, 32, 4) dtype float32 +DiT: After patch embed, shape is (256, 256, 768) dtype bfloat16 +DiT: Patch Embed of shape (256, 260, 768) dtype bfloat16 +DiT: Conditioning of shape (256, 768) dtype float32 +selfh idden 768 +self heads 12 +hw_swq 16 +xshape (256, 260, 768) +FID is 10.538402557373047 +Calc FID for CFG 2.0 and denoise_timesteps 16 +DiT: Input of shape (256, 32, 32, 4) dtype float32 +DiT: After patch embed, shape is (256, 256, 768) dtype bfloat16 +DiT: Patch Embed of shape (256, 260, 768) dtype bfloat16 +DiT: Conditioning of shape (256, 768) dtype float32 +selfh idden 768 +self heads 12 +hw_swq 16 +xshape (256, 260, 768) +FID is 10.216460227966309 +Calc FID for CFG 2.0 and denoise_timesteps 8 +DiT: Input of shape (256, 32, 32, 4) dtype float32 +DiT: After patch embed, shape is (256, 256, 768) dtype bfloat16 +DiT: Patch Embed of shape (256, 260, 768) dtype bfloat16 +DiT: Conditioning of shape (256, 768) dtype float32 +selfh idden 768 +self heads 12 +hw_swq 16 +xshape (256, 260, 768) +FID is 10.310005187988281 +Calc FID for CFG 2.0 and denoise_timesteps 4 +DiT: Input of shape (256, 32, 32, 4) dtype float32 +DiT: After patch embed, shape is (256, 256, 768) dtype bfloat16 +DiT: Patch Embed of shape (256, 260, 768) dtype bfloat16 +DiT: Conditioning of shape (256, 768) dtype float32 +selfh idden 768 +self heads 12 +hw_swq 16 +xshape (256, 260, 768) +FID is 10.5565824508667 +Calc FID for CFG 2.0 and denoise_timesteps 2 +DiT: Input of shape (256, 32, 32, 4) dtype float32 +DiT: After patch embed, shape is (256, 256, 768) dtype bfloat16 +DiT: Patch Embed of shape (256, 260, 768) dtype bfloat16 +DiT: Conditioning of shape (256, 768) dtype float32 +selfh idden 768 +self heads 12 +hw_swq 16 +xshape (256, 260, 768) +FID is 12.3935546875 +Calc FID for CFG 2.0 and denoise_timesteps 1 +DiT: Input of shape (256, 32, 32, 4) dtype float32 +DiT: After patch embed, shape is (256, 256, 768) dtype bfloat16 +DiT: Patch Embed of shape (256, 260, 768) dtype bfloat16 +DiT: Conditioning of shape (256, 768) dtype float32 +selfh idden 768 +self heads 12 +hw_swq 16 +xshape (256, 260, 768) +FID is 27.251195907592773 +Calc FID for CFG 2.25 and denoise_timesteps 128 +DiT: Input of shape (256, 32, 32, 4) dtype float32 +DiT: After patch embed, shape is (256, 256, 768) dtype bfloat16 +DiT: Patch Embed of shape (256, 260, 768) dtype bfloat16 +DiT: Conditioning of shape (256, 768) dtype float32 +selfh idden 768 +self heads 12 +hw_swq 16 +xshape (256, 260, 768) +FID is 6.64461612701416 +Calc FID for CFG 2.25 and denoise_timesteps 64 +DiT: Input of shape (256, 32, 32, 4) dtype float32 +DiT: After patch embed, shape is (256, 256, 768) dtype bfloat16 +DiT: Patch Embed of shape (256, 260, 768) dtype bfloat16 +DiT: Conditioning of shape (256, 768) dtype float32 +selfh idden 768 +self heads 12 +hw_swq 16 +xshape (256, 260, 768) +FID is 11.948240280151367 +Calc FID for CFG 2.25 and denoise_timesteps 32 +DiT: Input of shape (256, 32, 32, 4) dtype float32 +DiT: After patch embed, shape is (256, 256, 768) dtype bfloat16 +DiT: Patch Embed of shape (256, 260, 768) dtype bfloat16 +DiT: Conditioning of shape (256, 768) dtype float32 +selfh idden 768 +self heads 12 +hw_swq 16 +xshape (256, 260, 768) +FID is 12.189653396606445 +Calc FID for CFG 2.25 and denoise_timesteps 16 +DiT: Input of shape (256, 32, 32, 4) dtype float32 +DiT: After patch embed, shape is (256, 256, 768) dtype bfloat16 +DiT: Patch Embed of shape (256, 260, 768) dtype bfloat16 +DiT: Conditioning of shape (256, 768) dtype float32 +selfh idden 768 +self heads 12 +hw_swq 16 +xshape (256, 260, 768) +FID is 11.650171279907227 +Calc FID for CFG 2.25 and denoise_timesteps 8 +DiT: Input of shape (256, 32, 32, 4) dtype float32 +DiT: After patch embed, shape is (256, 256, 768) dtype bfloat16 +DiT: Patch Embed of shape (256, 260, 768) dtype bfloat16 +DiT: Conditioning of shape (256, 768) dtype float32 +selfh idden 768 +self heads 12 +hw_swq 16 +xshape (256, 260, 768) +FID is 11.508974075317383 +Calc FID for CFG 2.25 and denoise_timesteps 4 +DiT: Input of shape (256, 32, 32, 4) dtype float32 +DiT: After patch embed, shape is (256, 256, 768) dtype bfloat16 +DiT: Patch Embed of shape (256, 260, 768) dtype bfloat16 +DiT: Conditioning of shape (256, 768) dtype float32 +selfh idden 768 +self heads 12 +hw_swq 16 +xshape (256, 260, 768) +FID is 11.556058883666992 +Calc FID for CFG 2.25 and denoise_timesteps 2 +DiT: Input of shape (256, 32, 32, 4) dtype float32 +DiT: After patch embed, shape is (256, 256, 768) dtype bfloat16 +DiT: Patch Embed of shape (256, 260, 768) dtype bfloat16 +DiT: Conditioning of shape (256, 768) dtype float32 +selfh idden 768 +self heads 12 +hw_swq 16 +xshape (256, 260, 768) +FID is 13.568729400634766 +Calc FID for CFG 2.25 and denoise_timesteps 1 +DiT: Input of shape (256, 32, 32, 4) dtype float32 +DiT: After patch embed, shape is (256, 256, 768) dtype bfloat16 +DiT: Patch Embed of shape (256, 260, 768) dtype bfloat16 +DiT: Conditioning of shape (256, 768) dtype float32 +selfh idden 768 +self heads 12 +hw_swq 16 +xshape (256, 260, 768) +FID is 33.30046081542969 +Calc FID for CFG 2.5 and denoise_timesteps 128 +DiT: Input of shape (256, 32, 32, 4) dtype float32 +DiT: After patch embed, shape is (256, 256, 768) dtype bfloat16 +DiT: Patch Embed of shape (256, 260, 768) dtype bfloat16 +DiT: Conditioning of shape (256, 768) dtype float32 +selfh idden 768 +self heads 12 +hw_swq 16 +xshape (256, 260, 768) +FID is 7.966775894165039 +Calc FID for CFG 2.5 and denoise_timesteps 64 +DiT: Input of shape (256, 32, 32, 4) dtype float32 +DiT: After patch embed, shape is (256, 256, 768) dtype bfloat16 +DiT: Patch Embed of shape (256, 260, 768) dtype bfloat16 +DiT: Conditioning of shape (256, 768) dtype float32 +selfh idden 768 +self heads 12 +hw_swq 16 +xshape (256, 260, 768) +FID is 13.521624565124512 +Calc FID for CFG 2.5 and denoise_timesteps 32 +DiT: Input of shape (256, 32, 32, 4) dtype float32 +DiT: After patch embed, shape is (256, 256, 768) dtype bfloat16 +DiT: Patch Embed of shape (256, 260, 768) dtype bfloat16 +DiT: Conditioning of shape (256, 768) dtype float32 +selfh idden 768 +self heads 12 +hw_swq 16 +xshape (256, 260, 768) +FID is 13.653636932373047 +Calc FID for CFG 2.5 and denoise_timesteps 16 +DiT: Input of shape (256, 32, 32, 4) dtype float32 +DiT: After patch embed, shape is (256, 256, 768) dtype bfloat16 +DiT: Patch Embed of shape (256, 260, 768) dtype bfloat16 +DiT: Conditioning of shape (256, 768) dtype float32 +selfh idden 768 +self heads 12 +hw_swq 16 +xshape (256, 260, 768) +FID is 12.969107627868652 +Calc FID for CFG 2.5 and denoise_timesteps 8 +DiT: Input of shape (256, 32, 32, 4) dtype float32 +DiT: After patch embed, shape is (256, 256, 768) dtype bfloat16 +DiT: Patch Embed of shape (256, 260, 768) dtype bfloat16 +DiT: Conditioning of shape (256, 768) dtype float32 +selfh idden 768 +self heads 12 +hw_swq 16 +xshape (256, 260, 768) +FID is 12.682522773742676 +Calc FID for CFG 2.5 and denoise_timesteps 4 +DiT: Input of shape (256, 32, 32, 4) dtype float32 +DiT: After patch embed, shape is (256, 256, 768) dtype bfloat16 +DiT: Patch Embed of shape (256, 260, 768) dtype bfloat16 +DiT: Conditioning of shape (256, 768) dtype float32 +selfh idden 768 +self heads 12 +hw_swq 16 +xshape (256, 260, 768) +FID is 12.577970504760742 +Calc FID for CFG 2.5 and denoise_timesteps 2 +DiT: Input of shape (256, 32, 32, 4) dtype float32 +DiT: After patch embed, shape is (256, 256, 768) dtype bfloat16 +DiT: Patch Embed of shape (256, 260, 768) dtype bfloat16 +DiT: Conditioning of shape (256, 768) dtype float32 +selfh idden 768 +self heads 12 +hw_swq 16 +xshape (256, 260, 768) +FID is 15.12047004699707 +Calc FID for CFG 2.5 and denoise_timesteps 1 +DiT: Input of shape (256, 32, 32, 4) dtype float32 +DiT: After patch embed, shape is (256, 256, 768) dtype bfloat16 +DiT: Patch Embed of shape (256, 260, 768) dtype bfloat16 +DiT: Conditioning of shape (256, 768) dtype float32 +selfh idden 768 +self heads 12 +hw_swq 16 +xshape (256, 260, 768) +FID is 39.63566970825195 +Calc FID for CFG 2.75 and denoise_timesteps 128 +DiT: Input of shape (256, 32, 32, 4) dtype float32 +DiT: After patch embed, shape is (256, 256, 768) dtype bfloat16 +DiT: Patch Embed of shape (256, 260, 768) dtype bfloat16 +DiT: Conditioning of shape (256, 768) dtype float32 +selfh idden 768 +self heads 12 +hw_swq 16 +xshape (256, 260, 768) +FID is 9.372184753417969 +Calc FID for CFG 2.75 and denoise_timesteps 64 +DiT: Input of shape (256, 32, 32, 4) dtype float32 +DiT: After patch embed, shape is (256, 256, 768) dtype bfloat16 +DiT: Patch Embed of shape (256, 260, 768) dtype bfloat16 +DiT: Conditioning of shape (256, 768) dtype float32 +selfh idden 768 +self heads 12 +hw_swq 16 +xshape (256, 260, 768) +FID is 14.885001182556152 +Calc FID for CFG 2.75 and denoise_timesteps 32 +DiT: Input of shape (256, 32, 32, 4) dtype float32 +DiT: After patch embed, shape is (256, 256, 768) dtype bfloat16 +DiT: Patch Embed of shape (256, 260, 768) dtype bfloat16 +DiT: Conditioning of shape (256, 768) dtype float32 +selfh idden 768 +self heads 12 +hw_swq 16 +xshape (256, 260, 768) +FID is 14.964982986450195 +Calc FID for CFG 2.75 and denoise_timesteps 16 +DiT: Input of shape (256, 32, 32, 4) dtype float32 +DiT: After patch embed, shape is (256, 256, 768) dtype bfloat16 +DiT: Patch Embed of shape (256, 260, 768) dtype bfloat16 +DiT: Conditioning of shape (256, 768) dtype float32 +selfh idden 768 +self heads 12 +hw_swq 16 +xshape (256, 260, 768) +FID is 14.1913480758667 +Calc FID for CFG 2.75 and denoise_timesteps 8 +DiT: Input of shape (256, 32, 32, 4) dtype float32 +DiT: After patch embed, shape is (256, 256, 768) dtype bfloat16 +DiT: Patch Embed of shape (256, 260, 768) dtype bfloat16 +DiT: Conditioning of shape (256, 768) dtype float32 +selfh idden 768 +self heads 12 +hw_swq 16 +xshape (256, 260, 768) +FID is 13.701543807983398 +Calc FID for CFG 2.75 and denoise_timesteps 4 +DiT: Input of shape (256, 32, 32, 4) dtype float32 +DiT: After patch embed, shape is (256, 256, 768) dtype bfloat16 +DiT: Patch Embed of shape (256, 260, 768) dtype bfloat16 +DiT: Conditioning of shape (256, 768) dtype float32 +selfh idden 768 +self heads 12 +hw_swq 16 +xshape (256, 260, 768) +FID is 13.627029418945312 +Calc FID for CFG 2.75 and denoise_timesteps 2 +DiT: Input of shape (256, 32, 32, 4) dtype float32 +DiT: After patch embed, shape is (256, 256, 768) dtype bfloat16 +DiT: Patch Embed of shape (256, 260, 768) dtype bfloat16 +DiT: Conditioning of shape (256, 768) dtype float32 +selfh idden 768 +self heads 12 +hw_swq 16 +xshape (256, 260, 768) +FID is 17.040306091308594 +Calc FID for CFG 2.75 and denoise_timesteps 1 +DiT: Input of shape (256, 32, 32, 4) dtype float32 +DiT: After patch embed, shape is (256, 256, 768) dtype bfloat16 +DiT: Patch Embed of shape (256, 260, 768) dtype bfloat16 +DiT: Conditioning of shape (256, 768) dtype float32 +selfh idden 768 +self heads 12 +hw_swq 16 +xshape (256, 260, 768) +FID is 45.759521484375 +Calc FID for CFG 3.0 and denoise_timesteps 128 +DiT: Input of shape (256, 32, 32, 4) dtype float32 +DiT: After patch embed, shape is (256, 256, 768) dtype bfloat16 +DiT: Patch Embed of shape (256, 260, 768) dtype bfloat16 +DiT: Conditioning of shape (256, 768) dtype float32 +selfh idden 768 +self heads 12 +hw_swq 16 +xshape (256, 260, 768) +FID is 10.7019681930542 +Calc FID for CFG 3.0 and denoise_timesteps 64 +DiT: Input of shape (256, 32, 32, 4) dtype float32 +DiT: After patch embed, shape is (256, 256, 768) dtype bfloat16 +DiT: Patch Embed of shape (256, 260, 768) dtype bfloat16 +DiT: Conditioning of shape (256, 768) dtype float32 +selfh idden 768 +self heads 12 +hw_swq 16 +xshape (256, 260, 768) +FID is 16.036701202392578 +Calc FID for CFG 3.0 and denoise_timesteps 32 +DiT: Input of shape (256, 32, 32, 4) dtype float32 +DiT: After patch embed, shape is (256, 256, 768) dtype bfloat16 +DiT: Patch Embed of shape (256, 260, 768) dtype bfloat16 +DiT: Conditioning of shape (256, 768) dtype float32 +selfh idden 768 +self heads 12 +hw_swq 16 +xshape (256, 260, 768) +FID is 16.075788497924805 +Calc FID for CFG 3.0 and denoise_timesteps 16 +DiT: Input of shape (256, 32, 32, 4) dtype float32 +DiT: After patch embed, shape is (256, 256, 768) dtype bfloat16 +DiT: Patch Embed of shape (256, 260, 768) dtype bfloat16 +DiT: Conditioning of shape (256, 768) dtype float32 +selfh idden 768 +self heads 12 +hw_swq 16 +xshape (256, 260, 768) +FID is 15.228286743164062 +Calc FID for CFG 3.0 and denoise_timesteps 8 +DiT: Input of shape (256, 32, 32, 4) dtype float32 +DiT: After patch embed, shape is (256, 256, 768) dtype bfloat16 +DiT: Patch Embed of shape (256, 260, 768) dtype bfloat16 +DiT: Conditioning of shape (256, 768) dtype float32 +selfh idden 768 +self heads 12 +hw_swq 16 +xshape (256, 260, 768) +FID is 14.650333404541016 +Calc FID for CFG 3.0 and denoise_timesteps 4 +DiT: Input of shape (256, 32, 32, 4) dtype float32 +DiT: After patch embed, shape is (256, 256, 768) dtype bfloat16 +DiT: Patch Embed of shape (256, 260, 768) dtype bfloat16 +DiT: Conditioning of shape (256, 768) dtype float32 +selfh idden 768 +self heads 12 +hw_swq 16 +xshape (256, 260, 768) +FID is 14.675650596618652 +Calc FID for CFG 3.0 and denoise_timesteps 2 +DiT: Input of shape (256, 32, 32, 4) dtype float32 +DiT: After patch embed, shape is (256, 256, 768) dtype bfloat16 +DiT: Patch Embed of shape (256, 260, 768) dtype bfloat16 +DiT: Conditioning of shape (256, 768) dtype float32 +selfh idden 768 +self heads 12 +hw_swq 16 +xshape (256, 260, 768) +FID is 19.33051300048828 +Calc FID for CFG 3.0 and denoise_timesteps 1 +DiT: Input of shape (256, 32, 32, 4) dtype float32 +DiT: After patch embed, shape is (256, 256, 768) dtype bfloat16 +DiT: Patch Embed of shape (256, 260, 768) dtype bfloat16 +DiT: Conditioning of shape (256, 768) dtype float32 +selfh idden 768 +self heads 12 +hw_swq 16 +xshape (256, 260, 768) +FID is 51.551055908203125