mirror of
https://github.com/Vision-CAIR/MiniGPT-4.git
synced 2025-04-05 18:40:46 +00:00
5295 lines
205 KiB
Plaintext
5295 lines
205 KiB
Plaintext
digraph {
|
|
graph [size="739.65,739.65"]
|
|
node [align=left fontname=monospace fontsize=10 height=0.2 ranksep=0.1 shape=box style=filled]
|
|
140202223089520 [label="
|
|
(1, 46, 768)" fillcolor=darkolivegreen1]
|
|
140202228657312 [label=CatBackward0]
|
|
140202228615488 -> 140202228657312
|
|
140202228615488 [label=NativeLayerNormBackward0]
|
|
140202228614096 -> 140202228615488
|
|
140202228614096 [label=AddBackward0]
|
|
140202223538720 -> 140202228614096
|
|
140202223538720 [label=NativeDropoutBackward0]
|
|
140202223538912 -> 140202223538720
|
|
140202223538912 [label=ViewBackward0]
|
|
140202223539008 -> 140202223538912
|
|
140202223539008 [label=AddmmBackward0]
|
|
140202223539104 -> 140202223539008
|
|
140202223539104 [label=ToCopyBackward0]
|
|
140202223539296 -> 140202223539104
|
|
140202228893712 [label="encoder.layer.11.experts.dense2.bias
|
|
(768)" fillcolor=lightblue]
|
|
140202228893712 -> 140202223539296
|
|
140202223539296 [label=AccumulateGrad]
|
|
140202223538864 -> 140202223539008
|
|
140202223538864 [label=ViewBackward0]
|
|
140202223539152 -> 140202223538864
|
|
140202223539152 [label=GeluBackward0]
|
|
140202223539248 -> 140202223539152
|
|
140202223539248 [label=ViewBackward0]
|
|
140202223539680 -> 140202223539248
|
|
140202223539680 [label=AddmmBackward0]
|
|
140202223539584 -> 140202223539680
|
|
140202223539584 [label=ToCopyBackward0]
|
|
140202223538528 -> 140202223539584
|
|
140202228893952 [label="encoder.layer.11.experts.dense1.bias
|
|
(3072)" fillcolor=lightblue]
|
|
140202228893952 -> 140202223538528
|
|
140202223538528 [label=AccumulateGrad]
|
|
140202223539440 -> 140202223539680
|
|
140202223539440 [label=ViewBackward0]
|
|
140202223538288 -> 140202223539440
|
|
140202223538288 [label=ToCopyBackward0]
|
|
140202223538480 -> 140202223538288
|
|
140202223538480 [label=SliceBackward0]
|
|
140202223538336 -> 140202223538480
|
|
140202223538336 [label=SliceBackward0]
|
|
140202223539776 -> 140202223538336
|
|
140202223539776 [label=SliceBackward0]
|
|
140202223539872 -> 140202223539776
|
|
140202223539872 [label=SliceBackward0]
|
|
140202223539968 -> 140202223539872
|
|
140202223539968 [label=SliceBackward0]
|
|
140202223540064 -> 140202223539968
|
|
140202223540064 [label=NativeLayerNormBackward0]
|
|
140202223540160 -> 140202223540064
|
|
140202223540160 [label=AddBackward0]
|
|
140202223540352 -> 140202223540160
|
|
140202223540352 [label=NativeDropoutBackward0]
|
|
140202223540304 -> 140202223540352
|
|
140202223540304 [label=ViewBackward0]
|
|
140202223540400 -> 140202223540304
|
|
140202223540400 [label=AddmmBackward0]
|
|
140202223540496 -> 140202223540400
|
|
140202223540496 [label=ToCopyBackward0]
|
|
140202223540688 -> 140202223540496
|
|
140202228904080 [label="encoder.layer.11.attention.output.dense.bias
|
|
(768)" fillcolor=lightblue]
|
|
140202228904080 -> 140202223540688
|
|
140202223540688 [label=AccumulateGrad]
|
|
140202223540640 -> 140202223540400
|
|
140202223540640 [label=ViewBackward0]
|
|
140202223540928 -> 140202223540640
|
|
140202223540928 [label=ViewBackward0]
|
|
140202223541024 -> 140202223540928
|
|
140202223541024 [label=CloneBackward0]
|
|
140202223541120 -> 140202223541024
|
|
140202223541120 [label=PermuteBackward0]
|
|
140202223541216 -> 140202223541120
|
|
140202223541216 [label=UnsafeViewBackward0]
|
|
140202223541312 -> 140202223541216
|
|
140202223541312 [label=BmmBackward0]
|
|
140202223541408 -> 140202223541312
|
|
140202223541408 [label=ReshapeAliasBackward0]
|
|
140202223541504 -> 140202223541408
|
|
140202223541504 [label=ExpandBackward0]
|
|
140202223541600 -> 140202223541504
|
|
140202223541600 [label=ToCopyBackward0]
|
|
140202223541792 -> 140202223541600
|
|
140202223541792 [label=NativeDropoutBackward0]
|
|
140202223541984 -> 140202223541792
|
|
140202223541984 [label=SoftmaxBackward0]
|
|
140202223542080 -> 140202223541984
|
|
140202223542080 [label=AddBackward0]
|
|
140202223541264 -> 140202223542080
|
|
140202223541264 [label=DivBackward0]
|
|
140202223575296 -> 140202223541264
|
|
140202223575296 [label=UnsafeViewBackward0]
|
|
140202223575392 -> 140202223575296
|
|
140202223575392 [label=BmmBackward0]
|
|
140202223575584 -> 140202223575392
|
|
140202223575584 [label=ReshapeAliasBackward0]
|
|
140202223575968 -> 140202223575584
|
|
140202223575968 [label=ExpandBackward0]
|
|
140202223576160 -> 140202223575968
|
|
140202223576160 [label=PermuteBackward0]
|
|
140202223576208 -> 140202223576160
|
|
140202223576208 [label=ViewBackward0]
|
|
140202223576448 -> 140202223576208
|
|
140202223576448 [label=ViewBackward0]
|
|
140202223576640 -> 140202223576448
|
|
140202223576640 [label=AddmmBackward0]
|
|
140202223576688 -> 140202223576640
|
|
140202223576688 [label=ToCopyBackward0]
|
|
140202223577120 -> 140202223576688
|
|
140202228906560 [label="encoder.layer.11.attention.self.query.bias
|
|
(768)" fillcolor=lightblue]
|
|
140202228906560 -> 140202223577120
|
|
140202223577120 [label=AccumulateGrad]
|
|
140202223576544 -> 140202223576640
|
|
140202223576544 [label=ViewBackward0]
|
|
140202223577024 -> 140202223576544
|
|
140202223577024 [label=ToCopyBackward0]
|
|
140202223540112 -> 140202223577024
|
|
140202223540112 [label=CatBackward0]
|
|
140202223577408 -> 140202223540112
|
|
140202223577408 [label=NativeLayerNormBackward0]
|
|
140202223577504 -> 140202223577408
|
|
140202223577504 [label=AddBackward0]
|
|
140202223577792 -> 140202223577504
|
|
140202223577792 [label=SumBackward1]
|
|
140202223578128 -> 140202223577792
|
|
140202223578128 [label=MulBackward0]
|
|
140202223578368 -> 140202223578128
|
|
140202223578368 [label=PermuteBackward0]
|
|
140202223578464 -> 140202223578368
|
|
140202223578464 [label=CatBackward0]
|
|
140202223578656 -> 140202223578464
|
|
140202223578656 [label=UnsqueezeBackward0]
|
|
140202223578944 -> 140202223578656
|
|
140202223578944 [label=NativeDropoutBackward0]
|
|
140202223578752 -> 140202223578944
|
|
140202223578752 [label=ViewBackward0]
|
|
140202223079536 -> 140202223578752
|
|
140202223079536 [label=AddmmBackward0]
|
|
140202223079776 -> 140202223079536
|
|
140202223079776 [label=ToCopyBackward0]
|
|
140202223080064 -> 140202223079776
|
|
140202228905360 [label="encoder.layer.10.experts.experts.0.dense2.bias
|
|
(768)" fillcolor=lightblue]
|
|
140202228905360 -> 140202223080064
|
|
140202223080064 [label=AccumulateGrad]
|
|
140202223079872 -> 140202223079536
|
|
140202223079872 [label=ViewBackward0]
|
|
140202223080352 -> 140202223079872
|
|
140202223080352 [label=GeluBackward0]
|
|
140202223080400 -> 140202223080352
|
|
140202223080400 [label=ViewBackward0]
|
|
140202223080640 -> 140202223080400
|
|
140202223080640 [label=AddmmBackward0]
|
|
140202223080832 -> 140202223080640
|
|
140202223080832 [label=ToCopyBackward0]
|
|
140202223081120 -> 140202223080832
|
|
140202228905280 [label="encoder.layer.10.experts.experts.0.dense1.bias
|
|
(3072)" fillcolor=lightblue]
|
|
140202228905280 -> 140202223081120
|
|
140202223081120 [label=AccumulateGrad]
|
|
140202223080544 -> 140202223080640
|
|
140202223080544 [label=ViewBackward0]
|
|
140202223081024 -> 140202223080544
|
|
140202223081024 [label=ToCopyBackward0]
|
|
140202223577888 -> 140202223081024
|
|
140202223577888 [label=SliceBackward0]
|
|
140202223081360 -> 140202223577888
|
|
140202223081360 [label=SliceBackward0]
|
|
140202223081600 -> 140202223081360
|
|
140202223081600 [label=NativeLayerNormBackward0]
|
|
140202223081792 -> 140202223081600
|
|
140202223081792 [label=AddBackward0]
|
|
140202223082080 -> 140202223081792
|
|
140202223082080 [label=NativeDropoutBackward0]
|
|
140202223082176 -> 140202223082080
|
|
140202223082176 [label=ViewBackward0]
|
|
140202223082368 -> 140202223082176
|
|
140202223082368 [label=AddmmBackward0]
|
|
140202223082464 -> 140202223082368
|
|
140202223082464 [label=ToCopyBackward0]
|
|
140202223082848 -> 140202223082464
|
|
140202228924880 [label="encoder.layer.10.crossattention.output.dense.bias
|
|
(768)" fillcolor=lightblue]
|
|
140202228924880 -> 140202223082848
|
|
140202223082848 [label=AccumulateGrad]
|
|
140202223082560 -> 140202223082368
|
|
140202223082560 [label=ViewBackward0]
|
|
140202223083040 -> 140202223082560
|
|
140202223083040 [label=ViewBackward0]
|
|
140202223083232 -> 140202223083040
|
|
140202223083232 [label=CloneBackward0]
|
|
140202223083280 -> 140202223083232
|
|
140202223083280 [label=PermuteBackward0]
|
|
140202223083424 -> 140202223083280
|
|
140202223083424 [label=UnsafeViewBackward0]
|
|
140202223082800 -> 140202223083424
|
|
140202223082800 [label=BmmBackward0]
|
|
140202223108400 -> 140202223082800
|
|
140202223108400 [label=ReshapeAliasBackward0]
|
|
140202223108544 -> 140202223108400
|
|
140202223108544 [label=ExpandBackward0]
|
|
140202223108736 -> 140202223108544
|
|
140202223108736 [label=ToCopyBackward0]
|
|
140202223108928 -> 140202223108736
|
|
140202223108928 [label=NativeDropoutBackward0]
|
|
140202223109024 -> 140202223108928
|
|
140202223109024 [label=SoftmaxBackward0]
|
|
140202223109216 -> 140202223109024
|
|
140202223109216 [label=AddBackward0]
|
|
140202223109408 -> 140202223109216
|
|
140202223109408 [label=DivBackward0]
|
|
140202223109504 -> 140202223109408
|
|
140202223109504 [label=UnsafeViewBackward0]
|
|
140202223109696 -> 140202223109504
|
|
140202223109696 [label=BmmBackward0]
|
|
140202223109888 -> 140202223109696
|
|
140202223109888 [label=ReshapeAliasBackward0]
|
|
140202223110272 -> 140202223109888
|
|
140202223110272 [label=ExpandBackward0]
|
|
140202223110320 -> 140202223110272
|
|
140202223110320 [label=PermuteBackward0]
|
|
140202223110560 -> 140202223110320
|
|
140202223110560 [label=ViewBackward0]
|
|
140202223110752 -> 140202223110560
|
|
140202223110752 [label=ViewBackward0]
|
|
140202223110800 -> 140202223110752
|
|
140202223110800 [label=AddmmBackward0]
|
|
140202223111040 -> 140202223110800
|
|
140202223111040 [label=ToCopyBackward0]
|
|
140202223111280 -> 140202223111040
|
|
140202228925600 [label="encoder.layer.10.crossattention.self.query.bias
|
|
(768)" fillcolor=lightblue]
|
|
140202228925600 -> 140202223111280
|
|
140202223111280 [label=AccumulateGrad]
|
|
140202223110848 -> 140202223110800
|
|
140202223110848 [label=ViewBackward0]
|
|
140202223111328 -> 140202223110848
|
|
140202223111328 [label=ToCopyBackward0]
|
|
140202223081888 -> 140202223111328
|
|
140202223081888 [label=SliceBackward0]
|
|
140202223111712 -> 140202223081888
|
|
140202223111712 [label=SliceBackward0]
|
|
140202223111760 -> 140202223111712
|
|
140202223111760 [label=SliceBackward0]
|
|
140202223112000 -> 140202223111760
|
|
140202223112000 [label=NativeLayerNormBackward0]
|
|
140202223112096 -> 140202223112000
|
|
140202223112096 [label=AddBackward0]
|
|
140202223137120 -> 140202223112096
|
|
140202223137120 [label=NativeDropoutBackward0]
|
|
140202223137216 -> 140202223137120
|
|
140202223137216 [label=ViewBackward0]
|
|
140202223137408 -> 140202223137216
|
|
140202223137408 [label=AddmmBackward0]
|
|
140202223137504 -> 140202223137408
|
|
140202223137504 [label=ToCopyBackward0]
|
|
140202223137888 -> 140202223137504
|
|
140202228926080 [label="encoder.layer.10.attention.output.dense.bias
|
|
(768)" fillcolor=lightblue]
|
|
140202228926080 -> 140202223137888
|
|
140202223137888 [label=AccumulateGrad]
|
|
140202223137600 -> 140202223137408
|
|
140202223137600 [label=ViewBackward0]
|
|
140202223138080 -> 140202223137600
|
|
140202223138080 [label=ViewBackward0]
|
|
140202223138272 -> 140202223138080
|
|
140202223138272 [label=CloneBackward0]
|
|
140202223138320 -> 140202223138272
|
|
140202223138320 [label=PermuteBackward0]
|
|
140202223138560 -> 140202223138320
|
|
140202223138560 [label=UnsafeViewBackward0]
|
|
140202223138752 -> 140202223138560
|
|
140202223138752 [label=BmmBackward0]
|
|
140202223138800 -> 140202223138752
|
|
140202223138800 [label=ReshapeAliasBackward0]
|
|
140202223138944 -> 140202223138800
|
|
140202223138944 [label=ExpandBackward0]
|
|
140202223139136 -> 140202223138944
|
|
140202223139136 [label=ToCopyBackward0]
|
|
140202223139328 -> 140202223139136
|
|
140202223139328 [label=NativeDropoutBackward0]
|
|
140202223139424 -> 140202223139328
|
|
140202223139424 [label=SoftmaxBackward0]
|
|
140202223139616 -> 140202223139424
|
|
140202223139616 [label=AddBackward0]
|
|
140202223139808 -> 140202223139616
|
|
140202223139808 [label=DivBackward0]
|
|
140202223139904 -> 140202223139808
|
|
140202223139904 [label=UnsafeViewBackward0]
|
|
140202223140096 -> 140202223139904
|
|
140202223140096 [label=BmmBackward0]
|
|
140202223140288 -> 140202223140096
|
|
140202223140288 [label=ReshapeAliasBackward0]
|
|
140202223140672 -> 140202223140288
|
|
140202223140672 [label=ExpandBackward0]
|
|
140202223140720 -> 140202223140672
|
|
140202223140720 [label=PermuteBackward0]
|
|
140202223140768 -> 140202223140720
|
|
140202223140768 [label=ViewBackward0]
|
|
140202223169888 -> 140202223140768
|
|
140202223169888 [label=ViewBackward0]
|
|
140202223169936 -> 140202223169888
|
|
140202223169936 [label=AddmmBackward0]
|
|
140202223170176 -> 140202223169936
|
|
140202223170176 [label=ToCopyBackward0]
|
|
140202223170416 -> 140202223170176
|
|
140202228926800 [label="encoder.layer.10.attention.self.query.bias
|
|
(768)" fillcolor=lightblue]
|
|
140202228926800 -> 140202223170416
|
|
140202223170416 [label=AccumulateGrad]
|
|
140202223169984 -> 140202223169936
|
|
140202223169984 [label=ViewBackward0]
|
|
140202223170464 -> 140202223169984
|
|
140202223170464 [label=ToCopyBackward0]
|
|
140202223136928 -> 140202223170464
|
|
140202223136928 [label=CatBackward0]
|
|
140202223170848 -> 140202223136928
|
|
140202223170848 [label=NativeLayerNormBackward0]
|
|
140202223170944 -> 140202223170848
|
|
140202223170944 [label=AddBackward0]
|
|
140202223171232 -> 140202223170944
|
|
140202223171232 [label=NativeDropoutBackward0]
|
|
140202223171616 -> 140202223171232
|
|
140202223171616 [label=ViewBackward0]
|
|
140202223171808 -> 140202223171616
|
|
140202223171808 [label=AddmmBackward0]
|
|
140202223171856 -> 140202223171808
|
|
140202223171856 [label=ToCopyBackward0]
|
|
140202223172288 -> 140202223171856
|
|
140202228927280 [label="encoder.layer.9.experts.dense2.bias
|
|
(768)" fillcolor=lightblue]
|
|
140202228927280 -> 140202223172288
|
|
140202223172288 [label=AccumulateGrad]
|
|
140202223171712 -> 140202223171808
|
|
140202223171712 [label=ViewBackward0]
|
|
140202223172192 -> 140202223171712
|
|
140202223172192 [label=GeluBackward0]
|
|
140202223172384 -> 140202223172192
|
|
140202223172384 [label=ViewBackward0]
|
|
140202223172480 -> 140202223172384
|
|
140202223172480 [label=AddmmBackward0]
|
|
140202223172672 -> 140202223172480
|
|
140202223172672 [label=ToCopyBackward0]
|
|
140202223172960 -> 140202223172672
|
|
140202228927520 [label="encoder.layer.9.experts.dense1.bias
|
|
(3072)" fillcolor=lightblue]
|
|
140202228927520 -> 140202223172960
|
|
140202223172960 [label=AccumulateGrad]
|
|
140202223172768 -> 140202223172480
|
|
140202223172768 [label=ViewBackward0]
|
|
140202223173248 -> 140202223172768
|
|
140202223173248 [label=ToCopyBackward0]
|
|
140202223171328 -> 140202223173248
|
|
140202223171328 [label=SliceBackward0]
|
|
140202223173344 -> 140202223171328
|
|
140202223173344 [label=SliceBackward0]
|
|
140202223173440 -> 140202223173344
|
|
140202223173440 [label=SliceBackward0]
|
|
140202223172864 -> 140202223173440
|
|
140202223172864 [label=SliceBackward0]
|
|
140202223194368 -> 140202223172864
|
|
140202223194368 [label=SliceBackward0]
|
|
140202223194464 -> 140202223194368
|
|
140202223194464 [label=NativeLayerNormBackward0]
|
|
140202223194656 -> 140202223194464
|
|
140202223194656 [label=AddBackward0]
|
|
140202223194944 -> 140202223194656
|
|
140202223194944 [label=NativeDropoutBackward0]
|
|
140202223195280 -> 140202223194944
|
|
140202223195280 [label=ViewBackward0]
|
|
140202223195520 -> 140202223195280
|
|
140202223195520 [label=AddmmBackward0]
|
|
140202223195712 -> 140202223195520
|
|
140202223195712 [label=ToCopyBackward0]
|
|
140202223196000 -> 140202223195712
|
|
140202228933472 [label="encoder.layer.9.attention.output.dense.bias
|
|
(768)" fillcolor=lightblue]
|
|
140202228933472 -> 140202223196000
|
|
140202223196000 [label=AccumulateGrad]
|
|
140202223195424 -> 140202223195520
|
|
140202223195424 [label=ViewBackward0]
|
|
140202223195904 -> 140202223195424
|
|
140202223195904 [label=ViewBackward0]
|
|
140202223196096 -> 140202223195904
|
|
140202223196096 [label=CloneBackward0]
|
|
140202223196288 -> 140202223196096
|
|
140202223196288 [label=PermuteBackward0]
|
|
140202223196384 -> 140202223196288
|
|
140202223196384 [label=UnsafeViewBackward0]
|
|
140202223196576 -> 140202223196384
|
|
140202223196576 [label=BmmBackward0]
|
|
140202223196768 -> 140202223196576
|
|
140202223196768 [label=ReshapeAliasBackward0]
|
|
140202223197152 -> 140202223196768
|
|
140202223197152 [label=ExpandBackward0]
|
|
140202223197200 -> 140202223197152
|
|
140202223197200 [label=ToCopyBackward0]
|
|
140202223197440 -> 140202223197200
|
|
140202223197440 [label=NativeDropoutBackward0]
|
|
140202223197632 -> 140202223197440
|
|
140202223197632 [label=SoftmaxBackward0]
|
|
140202223197680 -> 140202223197632
|
|
140202223197680 [label=AddBackward0]
|
|
140202223197920 -> 140202223197680
|
|
140202223197920 [label=DivBackward0]
|
|
140202223198112 -> 140202223197920
|
|
140202223198112 [label=UnsafeViewBackward0]
|
|
140202223198016 -> 140202223198112
|
|
140202223198016 [label=BmmBackward0]
|
|
140202223227136 -> 140202223198016
|
|
140202223227136 [label=ReshapeAliasBackward0]
|
|
140202223227232 -> 140202223227136
|
|
140202223227232 [label=ExpandBackward0]
|
|
140202223227424 -> 140202223227232
|
|
140202223227424 [label=PermuteBackward0]
|
|
140202223227520 -> 140202223227424
|
|
140202223227520 [label=ViewBackward0]
|
|
140202223227712 -> 140202223227520
|
|
140202223227712 [label=ViewBackward0]
|
|
140202223227904 -> 140202223227712
|
|
140202223227904 [label=AddmmBackward0]
|
|
140202223228000 -> 140202223227904
|
|
140202223228000 [label=ToCopyBackward0]
|
|
140202223228384 -> 140202223228000
|
|
140202228936032 [label="encoder.layer.9.attention.self.query.bias
|
|
(768)" fillcolor=lightblue]
|
|
140202228936032 -> 140202223228384
|
|
140202223228384 [label=AccumulateGrad]
|
|
140202223228096 -> 140202223227904
|
|
140202223228096 [label=ViewBackward0]
|
|
140202223228576 -> 140202223228096
|
|
140202223228576 [label=ToCopyBackward0]
|
|
140202223195040 -> 140202223228576
|
|
140202223195040 [label=CatBackward0]
|
|
140202223228672 -> 140202223195040
|
|
140202223228672 [label=NativeLayerNormBackward0]
|
|
140202223229056 -> 140202223228672
|
|
140202223229056 [label=AddBackward0]
|
|
140202223229296 -> 140202223229056
|
|
140202223229296 [label=SumBackward1]
|
|
140202223229440 -> 140202223229296
|
|
140202223229440 [label=MulBackward0]
|
|
140202223229632 -> 140202223229440
|
|
140202223229632 [label=PermuteBackward0]
|
|
140202223230016 -> 140202223229632
|
|
140202223230016 [label=CatBackward0]
|
|
140202223230208 -> 140202223230016
|
|
140202223230208 [label=UnsqueezeBackward0]
|
|
140202223230496 -> 140202223230208
|
|
140202223230496 [label=NativeDropoutBackward0]
|
|
140202223230688 -> 140202223230496
|
|
140202223230688 [label=ViewBackward0]
|
|
140202223230736 -> 140202223230688
|
|
140202223230736 [label=AddmmBackward0]
|
|
140202223230880 -> 140202223230736
|
|
140202223230880 [label=ToCopyBackward0]
|
|
140202223247664 -> 140202223230880
|
|
140202228934832 [label="encoder.layer.8.experts.experts.0.dense2.bias
|
|
(768)" fillcolor=lightblue]
|
|
140202228934832 -> 140202223247664
|
|
140202223247664 [label=AccumulateGrad]
|
|
140202223230784 -> 140202223230736
|
|
140202223230784 [label=ViewBackward0]
|
|
140202223247712 -> 140202223230784
|
|
140202223247712 [label=GeluBackward0]
|
|
140202223247808 -> 140202223247712
|
|
140202223247808 [label=ViewBackward0]
|
|
140202223248000 -> 140202223247808
|
|
140202223248000 [label=AddmmBackward0]
|
|
140202223248192 -> 140202223248000
|
|
140202223248192 [label=ToCopyBackward0]
|
|
140202223248480 -> 140202223248192
|
|
140202228935152 [label="encoder.layer.8.experts.experts.0.dense1.bias
|
|
(3072)" fillcolor=lightblue]
|
|
140202228935152 -> 140202223248480
|
|
140202223248480 [label=AccumulateGrad]
|
|
140202223248144 -> 140202223248000
|
|
140202223248144 [label=ViewBackward0]
|
|
140202223248624 -> 140202223248144
|
|
140202223248624 [label=ToCopyBackward0]
|
|
140202223229152 -> 140202223248624
|
|
140202223229152 [label=SliceBackward0]
|
|
140202223248768 -> 140202223229152
|
|
140202223248768 [label=SliceBackward0]
|
|
140202223248960 -> 140202223248768
|
|
140202223248960 [label=NativeLayerNormBackward0]
|
|
140202223249152 -> 140202223248960
|
|
140202223249152 [label=AddBackward0]
|
|
140202223249440 -> 140202223249152
|
|
140202223249440 [label=NativeDropoutBackward0]
|
|
140202223249824 -> 140202223249440
|
|
140202223249824 [label=ViewBackward0]
|
|
140202223250016 -> 140202223249824
|
|
140202223250016 [label=AddmmBackward0]
|
|
140202223250064 -> 140202223250016
|
|
140202223250064 [label=ToCopyBackward0]
|
|
140202223250496 -> 140202223250064
|
|
140202228950656 [label="encoder.layer.8.crossattention.output.dense.bias
|
|
(768)" fillcolor=lightblue]
|
|
140202228950656 -> 140202223250496
|
|
140202223250496 [label=AccumulateGrad]
|
|
140202223249920 -> 140202223250016
|
|
140202223249920 [label=ViewBackward0]
|
|
140202223250400 -> 140202223249920
|
|
140202223250400 [label=ViewBackward0]
|
|
140202223250592 -> 140202223250400
|
|
140202223250592 [label=CloneBackward0]
|
|
140202223250688 -> 140202223250592
|
|
140202223250688 [label=PermuteBackward0]
|
|
140202223250976 -> 140202223250688
|
|
140202223250976 [label=UnsafeViewBackward0]
|
|
140202223251264 -> 140202223250976
|
|
140202223251264 [label=BmmBackward0]
|
|
140202223251360 -> 140202223251264
|
|
140202223251360 [label=ReshapeAliasBackward0]
|
|
140202223284384 -> 140202223251360
|
|
140202223284384 [label=ExpandBackward0]
|
|
140202223284480 -> 140202223284384
|
|
140202223284480 [label=ToCopyBackward0]
|
|
140202223284672 -> 140202223284480
|
|
140202223284672 [label=NativeDropoutBackward0]
|
|
140202223284864 -> 140202223284672
|
|
140202223284864 [label=SoftmaxBackward0]
|
|
140202223284960 -> 140202223284864
|
|
140202223284960 [label=AddBackward0]
|
|
140202223285152 -> 140202223284960
|
|
140202223285152 [label=DivBackward0]
|
|
140202223285344 -> 140202223285152
|
|
140202223285344 [label=UnsafeViewBackward0]
|
|
140202223285440 -> 140202223285344
|
|
140202223285440 [label=BmmBackward0]
|
|
140202223285632 -> 140202223285440
|
|
140202223285632 [label=ReshapeAliasBackward0]
|
|
140202223286016 -> 140202223285632
|
|
140202223286016 [label=ExpandBackward0]
|
|
140202223286208 -> 140202223286016
|
|
140202223286208 [label=PermuteBackward0]
|
|
140202223286256 -> 140202223286208
|
|
140202223286256 [label=ViewBackward0]
|
|
140202223286496 -> 140202223286256
|
|
140202223286496 [label=ViewBackward0]
|
|
140202223286688 -> 140202223286496
|
|
140202223286688 [label=AddmmBackward0]
|
|
140202223286736 -> 140202223286688
|
|
140202223286736 [label=ToCopyBackward0]
|
|
140202223287168 -> 140202223286736
|
|
140202228951376 [label="encoder.layer.8.crossattention.self.query.bias
|
|
(768)" fillcolor=lightblue]
|
|
140202228951376 -> 140202223287168
|
|
140202223287168 [label=AccumulateGrad]
|
|
140202223286592 -> 140202223286688
|
|
140202223286592 [label=ViewBackward0]
|
|
140202223287072 -> 140202223286592
|
|
140202223287072 [label=ToCopyBackward0]
|
|
140202223249536 -> 140202223287072
|
|
140202223249536 [label=SliceBackward0]
|
|
140202223287456 -> 140202223249536
|
|
140202223287456 [label=SliceBackward0]
|
|
140202223287648 -> 140202223287456
|
|
140202223287648 [label=SliceBackward0]
|
|
140202223287696 -> 140202223287648
|
|
140202223287696 [label=NativeLayerNormBackward0]
|
|
140202223287936 -> 140202223287696
|
|
140202223287936 [label=AddBackward0]
|
|
140202223288176 -> 140202223287936
|
|
140202223288176 [label=NativeDropoutBackward0]
|
|
140202223288224 -> 140202223288176
|
|
140202223288224 [label=ViewBackward0]
|
|
140202223313152 -> 140202223288224
|
|
140202223313152 [label=AddmmBackward0]
|
|
140202223313344 -> 140202223313152
|
|
140202223313344 [label=ToCopyBackward0]
|
|
140202223313632 -> 140202223313344
|
|
140202228951856 [label="encoder.layer.8.attention.output.dense.bias
|
|
(768)" fillcolor=lightblue]
|
|
140202228951856 -> 140202223313632
|
|
140202223313632 [label=AccumulateGrad]
|
|
140202223313296 -> 140202223313152
|
|
140202223313296 [label=ViewBackward0]
|
|
140202223313776 -> 140202223313296
|
|
140202223313776 [label=ViewBackward0]
|
|
140202223314016 -> 140202223313776
|
|
140202223314016 [label=CloneBackward0]
|
|
140202223314208 -> 140202223314016
|
|
140202223314208 [label=PermuteBackward0]
|
|
140202223314256 -> 140202223314208
|
|
140202223314256 [label=UnsafeViewBackward0]
|
|
140202223314496 -> 140202223314256
|
|
140202223314496 [label=BmmBackward0]
|
|
140202223314688 -> 140202223314496
|
|
140202223314688 [label=ReshapeAliasBackward0]
|
|
140202223314784 -> 140202223314688
|
|
140202223314784 [label=ExpandBackward0]
|
|
140202223314880 -> 140202223314784
|
|
140202223314880 [label=ToCopyBackward0]
|
|
140202223315072 -> 140202223314880
|
|
140202223315072 [label=NativeDropoutBackward0]
|
|
140202223315264 -> 140202223315072
|
|
140202223315264 [label=SoftmaxBackward0]
|
|
140202223315360 -> 140202223315264
|
|
140202223315360 [label=AddBackward0]
|
|
140202223315552 -> 140202223315360
|
|
140202223315552 [label=DivBackward0]
|
|
140202223315744 -> 140202223315552
|
|
140202223315744 [label=UnsafeViewBackward0]
|
|
140202223315840 -> 140202223315744
|
|
140202223315840 [label=BmmBackward0]
|
|
140202223316032 -> 140202223315840
|
|
140202223316032 [label=ReshapeAliasBackward0]
|
|
140202223316416 -> 140202223316032
|
|
140202223316416 [label=ExpandBackward0]
|
|
140202223316608 -> 140202223316416
|
|
140202223316608 [label=PermuteBackward0]
|
|
140202223316656 -> 140202223316608
|
|
140202223316656 [label=ViewBackward0]
|
|
140202223316896 -> 140202223316656
|
|
140202223316896 [label=ViewBackward0]
|
|
140202223316800 -> 140202223316896
|
|
140202223316800 [label=AddmmBackward0]
|
|
140202222817488 -> 140202223316800
|
|
140202222817488 [label=ToCopyBackward0]
|
|
140202222817920 -> 140202222817488
|
|
140202228952576 [label="encoder.layer.8.attention.self.query.bias
|
|
(768)" fillcolor=lightblue]
|
|
140202228952576 -> 140202222817920
|
|
140202222817920 [label=AccumulateGrad]
|
|
140202222817344 -> 140202223316800
|
|
140202222817344 [label=ViewBackward0]
|
|
140202222817824 -> 140202222817344
|
|
140202222817824 [label=ToCopyBackward0]
|
|
140202223288032 -> 140202222817824
|
|
140202223288032 [label=CatBackward0]
|
|
140202222818208 -> 140202223288032
|
|
140202222818208 [label=NativeLayerNormBackward0]
|
|
140202222818304 -> 140202222818208
|
|
140202222818304 [label=AddBackward0]
|
|
140202222818592 -> 140202222818304
|
|
140202222818592 [label=NativeDropoutBackward0]
|
|
140202222818928 -> 140202222818592
|
|
140202222818928 [label=ViewBackward0]
|
|
140202222819168 -> 140202222818928
|
|
140202222819168 [label=AddmmBackward0]
|
|
140202222819360 -> 140202222819168
|
|
140202222819360 [label=ToCopyBackward0]
|
|
140202222819648 -> 140202222819360
|
|
140202228952976 [label="encoder.layer.7.experts.dense2.bias
|
|
(768)" fillcolor=lightblue]
|
|
140202228952976 -> 140202222819648
|
|
140202222819648 [label=AccumulateGrad]
|
|
140202222819072 -> 140202222819168
|
|
140202222819072 [label=ViewBackward0]
|
|
140202222819552 -> 140202222819072
|
|
140202222819552 [label=GeluBackward0]
|
|
140202222819744 -> 140202222819552
|
|
140202222819744 [label=ViewBackward0]
|
|
140202222819936 -> 140202222819744
|
|
140202222819936 [label=AddmmBackward0]
|
|
140202222820032 -> 140202222819936
|
|
140202222820032 [label=ToCopyBackward0]
|
|
140202222820416 -> 140202222820032
|
|
140202228965680 [label="encoder.layer.7.experts.dense1.bias
|
|
(3072)" fillcolor=lightblue]
|
|
140202228965680 -> 140202222820416
|
|
140202222820416 [label=AccumulateGrad]
|
|
140202222820128 -> 140202222819936
|
|
140202222820128 [label=ViewBackward0]
|
|
140202222820608 -> 140202222820128
|
|
140202222820608 [label=ToCopyBackward0]
|
|
140202222818688 -> 140202222820608
|
|
140202222818688 [label=SliceBackward0]
|
|
140202222820704 -> 140202222818688
|
|
140202222820704 [label=SliceBackward0]
|
|
140202222820896 -> 140202222820704
|
|
140202222820896 [label=SliceBackward0]
|
|
140202222820992 -> 140202222820896
|
|
140202222820992 [label=SliceBackward0]
|
|
140202222821184 -> 140202222820992
|
|
140202222821184 [label=SliceBackward0]
|
|
140202222820224 -> 140202222821184
|
|
140202222820224 [label=NativeLayerNormBackward0]
|
|
140202222841968 -> 140202222820224
|
|
140202222841968 [label=AddBackward0]
|
|
140202222842400 -> 140202222841968
|
|
140202222842400 [label=NativeDropoutBackward0]
|
|
140202222842784 -> 140202222842400
|
|
140202222842784 [label=ViewBackward0]
|
|
140202222842832 -> 140202222842784
|
|
140202222842832 [label=AddmmBackward0]
|
|
140202222843072 -> 140202222842832
|
|
140202222843072 [label=ToCopyBackward0]
|
|
140202222843312 -> 140202222843072
|
|
140202228967040 [label="encoder.layer.7.attention.output.dense.bias
|
|
(768)" fillcolor=lightblue]
|
|
140202228967040 -> 140202222843312
|
|
140202222843312 [label=AccumulateGrad]
|
|
140202222842880 -> 140202222842832
|
|
140202222842880 [label=ViewBackward0]
|
|
140202222843360 -> 140202222842880
|
|
140202222843360 [label=ViewBackward0]
|
|
140202222843456 -> 140202222843360
|
|
140202222843456 [label=CloneBackward0]
|
|
140202222843648 -> 140202222843456
|
|
140202222843648 [label=PermuteBackward0]
|
|
140202222843840 -> 140202222843648
|
|
140202222843840 [label=UnsafeViewBackward0]
|
|
140202222843936 -> 140202222843840
|
|
140202222843936 [label=BmmBackward0]
|
|
140202222844128 -> 140202222843936
|
|
140202222844128 [label=ReshapeAliasBackward0]
|
|
140202222844512 -> 140202222844128
|
|
140202222844512 [label=ExpandBackward0]
|
|
140202222844704 -> 140202222844512
|
|
140202222844704 [label=ToCopyBackward0]
|
|
140202222844752 -> 140202222844704
|
|
140202222844752 [label=NativeDropoutBackward0]
|
|
140202222844992 -> 140202222844752
|
|
140202222844992 [label=SoftmaxBackward0]
|
|
140202222845184 -> 140202222844992
|
|
140202222845184 [label=AddBackward0]
|
|
140202222845232 -> 140202222845184
|
|
140202222845232 [label=DivBackward0]
|
|
140202222845472 -> 140202222845232
|
|
140202222845472 [label=UnsafeViewBackward0]
|
|
140202222845664 -> 140202222845472
|
|
140202222845664 [label=BmmBackward0]
|
|
140202222845712 -> 140202222845664
|
|
140202222845712 [label=ReshapeAliasBackward0]
|
|
140202222845856 -> 140202222845712
|
|
140202222845856 [label=ExpandBackward0]
|
|
140202222870688 -> 140202222845856
|
|
140202222870688 [label=PermuteBackward0]
|
|
140202222870880 -> 140202222870688
|
|
140202222870880 [label=ViewBackward0]
|
|
140202222870976 -> 140202222870880
|
|
140202222870976 [label=ViewBackward0]
|
|
140202222871168 -> 140202222870976
|
|
140202222871168 [label=AddmmBackward0]
|
|
140202222871360 -> 140202222871168
|
|
140202222871360 [label=ToCopyBackward0]
|
|
140202222871648 -> 140202222871360
|
|
140202228982304 [label="encoder.layer.7.attention.self.query.bias
|
|
(768)" fillcolor=lightblue]
|
|
140202228982304 -> 140202222871648
|
|
140202222871648 [label=AccumulateGrad]
|
|
140202222871312 -> 140202222871168
|
|
140202222871312 [label=ViewBackward0]
|
|
140202222871792 -> 140202222871312
|
|
140202222871792 [label=ToCopyBackward0]
|
|
140202222842352 -> 140202222871792
|
|
140202222842352 [label=CatBackward0]
|
|
140202222871936 -> 140202222842352
|
|
140202222871936 [label=NativeLayerNormBackward0]
|
|
140202222872272 -> 140202222871936
|
|
140202222872272 [label=AddBackward0]
|
|
140202222872704 -> 140202222872272
|
|
140202222872704 [label=SumBackward1]
|
|
140202222872800 -> 140202222872704
|
|
140202222872800 [label=MulBackward0]
|
|
140202222872896 -> 140202222872800
|
|
140202222872896 [label=PermuteBackward0]
|
|
140202222873232 -> 140202222872896
|
|
140202222873232 [label=CatBackward0]
|
|
140202222873472 -> 140202222873232
|
|
140202222873472 [label=UnsqueezeBackward0]
|
|
140202222873712 -> 140202222873472
|
|
140202222873712 [label=NativeDropoutBackward0]
|
|
140202222873952 -> 140202222873712
|
|
140202222873952 [label=ViewBackward0]
|
|
140202222874144 -> 140202222873952
|
|
140202222874144 [label=AddmmBackward0]
|
|
140202222874192 -> 140202222874144
|
|
140202222874192 [label=ToCopyBackward0]
|
|
140202222874528 -> 140202222874192
|
|
140202228968800 [label="encoder.layer.6.experts.experts.0.dense2.bias
|
|
(768)" fillcolor=lightblue]
|
|
140202228968800 -> 140202222874528
|
|
140202222874528 [label=AccumulateGrad]
|
|
140202222874048 -> 140202222874144
|
|
140202222874048 [label=ViewBackward0]
|
|
140202222874432 -> 140202222874048
|
|
140202222874432 [label=GeluBackward0]
|
|
140202222903456 -> 140202222874432
|
|
140202222903456 [label=ViewBackward0]
|
|
140202222903552 -> 140202222903456
|
|
140202222903552 [label=AddmmBackward0]
|
|
140202222903744 -> 140202222903552
|
|
140202222903744 [label=ToCopyBackward0]
|
|
140202222904032 -> 140202222903744
|
|
140202228968720 [label="encoder.layer.6.experts.experts.0.dense1.bias
|
|
(3072)" fillcolor=lightblue]
|
|
140202228968720 -> 140202222904032
|
|
140202222904032 [label=AccumulateGrad]
|
|
140202222903840 -> 140202222903552
|
|
140202222903840 [label=ViewBackward0]
|
|
140202222904320 -> 140202222903840
|
|
140202222904320 [label=ToCopyBackward0]
|
|
140202222872416 -> 140202222904320
|
|
140202222872416 [label=SliceBackward0]
|
|
140202222904416 -> 140202222872416
|
|
140202222904416 [label=SliceBackward0]
|
|
140202222904512 -> 140202222904416
|
|
140202222904512 [label=NativeLayerNormBackward0]
|
|
140202222904896 -> 140202222904512
|
|
140202222904896 [label=AddBackward0]
|
|
140202222905184 -> 140202222904896
|
|
140202222905184 [label=NativeDropoutBackward0]
|
|
140202222905280 -> 140202222905184
|
|
140202222905280 [label=ViewBackward0]
|
|
140202222905328 -> 140202222905280
|
|
140202222905328 [label=AddmmBackward0]
|
|
140202222905568 -> 140202222905328
|
|
140202222905568 [label=ToCopyBackward0]
|
|
140202222905808 -> 140202222905568
|
|
140202228984224 [label="encoder.layer.6.crossattention.output.dense.bias
|
|
(768)" fillcolor=lightblue]
|
|
140202228984224 -> 140202222905808
|
|
140202222905808 [label=AccumulateGrad]
|
|
140202222905664 -> 140202222905328
|
|
140202222905664 [label=ViewBackward0]
|
|
140202222906144 -> 140202222905664
|
|
140202222906144 [label=ViewBackward0]
|
|
140202222906336 -> 140202222906144
|
|
140202222906336 [label=CloneBackward0]
|
|
140202222906432 -> 140202222906336
|
|
140202222906432 [label=PermuteBackward0]
|
|
140202222906624 -> 140202222906432
|
|
140202222906624 [label=UnsafeViewBackward0]
|
|
140202222906816 -> 140202222906624
|
|
140202222906816 [label=BmmBackward0]
|
|
140202222906912 -> 140202222906816
|
|
140202222906912 [label=ReshapeAliasBackward0]
|
|
140202222907008 -> 140202222906912
|
|
140202222907008 [label=ExpandBackward0]
|
|
140202222907200 -> 140202222907008
|
|
140202222907200 [label=ToCopyBackward0]
|
|
140202222907248 -> 140202222907200
|
|
140202222907248 [label=NativeDropoutBackward0]
|
|
140202222932128 -> 140202222907248
|
|
140202222932128 [label=SoftmaxBackward0]
|
|
140202222932320 -> 140202222932128
|
|
140202222932320 [label=AddBackward0]
|
|
140202222932368 -> 140202222932320
|
|
140202222932368 [label=DivBackward0]
|
|
140202222932608 -> 140202222932368
|
|
140202222932608 [label=UnsafeViewBackward0]
|
|
140202222932800 -> 140202222932608
|
|
140202222932800 [label=BmmBackward0]
|
|
140202222932848 -> 140202222932800
|
|
140202222932848 [label=ReshapeAliasBackward0]
|
|
140202222933376 -> 140202222932848
|
|
140202222933376 [label=ExpandBackward0]
|
|
140202222933472 -> 140202222933376
|
|
140202222933472 [label=PermuteBackward0]
|
|
140202222933664 -> 140202222933472
|
|
140202222933664 [label=ViewBackward0]
|
|
140202222933856 -> 140202222933664
|
|
140202222933856 [label=ViewBackward0]
|
|
140202222933952 -> 140202222933856
|
|
140202222933952 [label=AddmmBackward0]
|
|
140202222934144 -> 140202222933952
|
|
140202222934144 [label=ToCopyBackward0]
|
|
140202222934432 -> 140202222934144
|
|
140202228984944 [label="encoder.layer.6.crossattention.self.query.bias
|
|
(768)" fillcolor=lightblue]
|
|
140202228984944 -> 140202222934432
|
|
140202222934432 [label=AccumulateGrad]
|
|
140202222933808 -> 140202222933952
|
|
140202222933808 [label=ViewBackward0]
|
|
140202222934288 -> 140202222933808
|
|
140202222934288 [label=ToCopyBackward0]
|
|
140202222904848 -> 140202222934288
|
|
140202222904848 [label=SliceBackward0]
|
|
140202222934816 -> 140202222904848
|
|
140202222934816 [label=SliceBackward0]
|
|
140202222934912 -> 140202222934816
|
|
140202222934912 [label=SliceBackward0]
|
|
140202222935104 -> 140202222934912
|
|
140202222935104 [label=NativeLayerNormBackward0]
|
|
140202222935296 -> 140202222935104
|
|
140202222935296 [label=AddBackward0]
|
|
140202222935584 -> 140202222935296
|
|
140202222935584 [label=NativeDropoutBackward0]
|
|
140202222935680 -> 140202222935584
|
|
140202222935680 [label=ViewBackward0]
|
|
140202222935728 -> 140202222935680
|
|
140202222935728 [label=AddmmBackward0]
|
|
140202222935968 -> 140202222935728
|
|
140202222935968 [label=ToCopyBackward0]
|
|
140202222960848 -> 140202222935968
|
|
140202228985424 [label="encoder.layer.6.attention.output.dense.bias
|
|
(768)" fillcolor=lightblue]
|
|
140202228985424 -> 140202222960848
|
|
140202222960848 [label=AccumulateGrad]
|
|
140202222935488 -> 140202222935728
|
|
140202222935488 [label=ViewBackward0]
|
|
140202222961184 -> 140202222935488
|
|
140202222961184 [label=ViewBackward0]
|
|
140202222961376 -> 140202222961184
|
|
140202222961376 [label=CloneBackward0]
|
|
140202222961472 -> 140202222961376
|
|
140202222961472 [label=PermuteBackward0]
|
|
140202222961664 -> 140202222961472
|
|
140202222961664 [label=UnsafeViewBackward0]
|
|
140202222961856 -> 140202222961664
|
|
140202222961856 [label=BmmBackward0]
|
|
140202222961952 -> 140202222961856
|
|
140202222961952 [label=ReshapeAliasBackward0]
|
|
140202222962048 -> 140202222961952
|
|
140202222962048 [label=ExpandBackward0]
|
|
140202222962240 -> 140202222962048
|
|
140202222962240 [label=ToCopyBackward0]
|
|
140202222962288 -> 140202222962240
|
|
140202222962288 [label=NativeDropoutBackward0]
|
|
140202222962528 -> 140202222962288
|
|
140202222962528 [label=SoftmaxBackward0]
|
|
140202222962720 -> 140202222962528
|
|
140202222962720 [label=AddBackward0]
|
|
140202222962768 -> 140202222962720
|
|
140202222962768 [label=DivBackward0]
|
|
140202222963008 -> 140202222962768
|
|
140202222963008 [label=UnsafeViewBackward0]
|
|
140202222963200 -> 140202222963008
|
|
140202222963200 [label=BmmBackward0]
|
|
140202222963248 -> 140202222963200
|
|
140202222963248 [label=ReshapeAliasBackward0]
|
|
140202222963776 -> 140202222963248
|
|
140202222963776 [label=ExpandBackward0]
|
|
140202222963872 -> 140202222963776
|
|
140202222963872 [label=PermuteBackward0]
|
|
140202222964064 -> 140202222963872
|
|
140202222964064 [label=ViewBackward0]
|
|
140202222964256 -> 140202222964064
|
|
140202222964256 [label=ViewBackward0]
|
|
140202222964352 -> 140202222964256
|
|
140202222964352 [label=AddmmBackward0]
|
|
140202222964544 -> 140202222964352
|
|
140202222964544 [label=ToCopyBackward0]
|
|
140202222964640 -> 140202222964544
|
|
140202228986240 [label="encoder.layer.6.attention.self.query.bias
|
|
(768)" fillcolor=lightblue]
|
|
140202228986240 -> 140202222964640
|
|
140202222964640 [label=AccumulateGrad]
|
|
140202222964208 -> 140202222964352
|
|
140202222964208 [label=ViewBackward0]
|
|
140202222988064 -> 140202222964208
|
|
140202222988064 [label=ToCopyBackward0]
|
|
140202222935248 -> 140202222988064
|
|
140202222935248 [label=CatBackward0]
|
|
140202222988736 -> 140202222935248
|
|
140202222988736 [label=NativeLayerNormBackward0]
|
|
140202222985280 -> 140202222988736
|
|
140202222985280 [label=AddBackward0]
|
|
140202222985472 -> 140202222985280
|
|
140202222985472 [label=NativeDropoutBackward0]
|
|
140202222985856 -> 140202222985472
|
|
140202222985856 [label=ViewBackward0]
|
|
140202222986048 -> 140202222985856
|
|
140202222986048 [label=AddmmBackward0]
|
|
140202222986240 -> 140202222986048
|
|
140202222986240 [label=ToCopyBackward0]
|
|
140202222987680 -> 140202222986240
|
|
140202228986720 [label="encoder.layer.5.experts.dense2.bias
|
|
(768)" fillcolor=lightblue]
|
|
140202228986720 -> 140202222987680
|
|
140202222987680 [label=AccumulateGrad]
|
|
140202222985952 -> 140202222986048
|
|
140202222985952 [label=ViewBackward0]
|
|
140202222986432 -> 140202222985952
|
|
140202222986432 [label=GeluBackward0]
|
|
140202222986624 -> 140202222986432
|
|
140202222986624 [label=ViewBackward0]
|
|
140202222986672 -> 140202222986624
|
|
140202222986672 [label=AddmmBackward0]
|
|
140202222986912 -> 140202222986672
|
|
140202222986912 [label=ToCopyBackward0]
|
|
140202222989072 -> 140202222986912
|
|
140202228986960 [label="encoder.layer.5.experts.dense1.bias
|
|
(3072)" fillcolor=lightblue]
|
|
140202228986960 -> 140202222989072
|
|
140202222989072 [label=AccumulateGrad]
|
|
140202222986816 -> 140202222986672
|
|
140202222986816 [label=ViewBackward0]
|
|
140202222988832 -> 140202222986816
|
|
140202222988832 [label=ToCopyBackward0]
|
|
140202222985568 -> 140202222988832
|
|
140202222985568 [label=SliceBackward0]
|
|
140202222987632 -> 140202222985568
|
|
140202222987632 [label=SliceBackward0]
|
|
140202222989216 -> 140202222987632
|
|
140202222989216 [label=SliceBackward0]
|
|
140202222987872 -> 140202222989216
|
|
140202222987872 [label=SliceBackward0]
|
|
140202222987968 -> 140202222987872
|
|
140202222987968 [label=SliceBackward0]
|
|
140202222988352 -> 140202222987968
|
|
140202222988352 [label=NativeLayerNormBackward0]
|
|
140202222987584 -> 140202222988352
|
|
140202222987584 [label=AddBackward0]
|
|
140202224191520 -> 140202222987584
|
|
140202224191520 [label=NativeDropoutBackward0]
|
|
140202224191280 -> 140202224191520
|
|
140202224191280 [label=ViewBackward0]
|
|
140202224191184 -> 140202224191280
|
|
140202224191184 [label=AddmmBackward0]
|
|
140202224191088 -> 140202224191184
|
|
140202224191088 [label=ToCopyBackward0]
|
|
140202224190896 -> 140202224191088
|
|
140202228988880 [label="encoder.layer.5.attention.output.dense.bias
|
|
(768)" fillcolor=lightblue]
|
|
140202228988880 -> 140202224190896
|
|
140202224190896 [label=AccumulateGrad]
|
|
140202224191232 -> 140202224191184
|
|
140202224191232 [label=ViewBackward0]
|
|
140202224190944 -> 140202224191232
|
|
140202224190944 [label=ViewBackward0]
|
|
140202224190848 -> 140202224190944
|
|
140202224190848 [label=CloneBackward0]
|
|
140202224190752 -> 140202224190848
|
|
140202224190752 [label=PermuteBackward0]
|
|
140202224190656 -> 140202224190752
|
|
140202224190656 [label=UnsafeViewBackward0]
|
|
140202224190560 -> 140202224190656
|
|
140202224190560 [label=BmmBackward0]
|
|
140202224190464 -> 140202224190560
|
|
140202224190464 [label=ReshapeAliasBackward0]
|
|
140202224190224 -> 140202224190464
|
|
140202224190224 [label=ExpandBackward0]
|
|
140202224190128 -> 140202224190224
|
|
140202224190128 [label=ToCopyBackward0]
|
|
140202224190032 -> 140202224190128
|
|
140202224190032 [label=NativeDropoutBackward0]
|
|
140202224189936 -> 140202224190032
|
|
140202224189936 [label=SoftmaxBackward0]
|
|
140202224189840 -> 140202224189936
|
|
140202224189840 [label=AddBackward0]
|
|
140202224189744 -> 140202224189840
|
|
140202224189744 [label=DivBackward0]
|
|
140202224189648 -> 140202224189744
|
|
140202224189648 [label=UnsafeViewBackward0]
|
|
140202224189552 -> 140202224189648
|
|
140202224189552 [label=BmmBackward0]
|
|
140202224189504 -> 140202224189552
|
|
140202224189504 [label=ReshapeAliasBackward0]
|
|
140202224191808 -> 140202224189504
|
|
140202224191808 [label=ExpandBackward0]
|
|
140202224191904 -> 140202224191808
|
|
140202224191904 [label=PermuteBackward0]
|
|
140202224192000 -> 140202224191904
|
|
140202224192000 [label=ViewBackward0]
|
|
140202224192096 -> 140202224192000
|
|
140202224192096 [label=ViewBackward0]
|
|
140202224192192 -> 140202224192096
|
|
140202224192192 [label=AddmmBackward0]
|
|
140202224192288 -> 140202224192192
|
|
140202224192288 [label=ToCopyBackward0]
|
|
140202224192480 -> 140202224192288
|
|
140202228989600 [label="encoder.layer.5.attention.self.query.bias
|
|
(768)" fillcolor=lightblue]
|
|
140202228989600 -> 140202224192480
|
|
140202224192480 [label=AccumulateGrad]
|
|
140202224192240 -> 140202224192192
|
|
140202224192240 [label=ViewBackward0]
|
|
140202224192576 -> 140202224192240
|
|
140202224192576 [label=ToCopyBackward0]
|
|
140202224191472 -> 140202224192576
|
|
140202224191472 [label=CatBackward0]
|
|
140202224192720 -> 140202224191472
|
|
140202224192720 [label=NativeLayerNormBackward0]
|
|
140202224192864 -> 140202224192720
|
|
140202224192864 [label=AddBackward0]
|
|
140202224193056 -> 140202224192864
|
|
140202224193056 [label=NativeDropoutBackward0]
|
|
140202224193200 -> 140202224193056
|
|
140202224193200 [label=ViewBackward0]
|
|
140202224193296 -> 140202224193200
|
|
140202224193296 [label=AddmmBackward0]
|
|
140202224193392 -> 140202224193296
|
|
140202224193392 [label=ToCopyBackward0]
|
|
140202224193488 -> 140202224193392
|
|
140202229010656 [label="encoder.layer.4.experts.dense2.bias
|
|
(768)" fillcolor=lightblue]
|
|
140202229010656 -> 140202224193488
|
|
140202224193488 [label=AccumulateGrad]
|
|
140202224193344 -> 140202224193296
|
|
140202224193344 [label=ViewBackward0]
|
|
140210811924640 -> 140202224193344
|
|
140210811924640 [label=GeluBackward0]
|
|
140210811924736 -> 140210811924640
|
|
140210811924736 [label=ViewBackward0]
|
|
140210811924832 -> 140210811924736
|
|
140210811924832 [label=AddmmBackward0]
|
|
140210811924928 -> 140210811924832
|
|
140210811924928 [label=ToCopyBackward0]
|
|
140210811925120 -> 140210811924928
|
|
140202229010896 [label="encoder.layer.4.experts.dense1.bias
|
|
(3072)" fillcolor=lightblue]
|
|
140202229010896 -> 140210811925120
|
|
140210811925120 [label=AccumulateGrad]
|
|
140210811924880 -> 140210811924832
|
|
140210811924880 [label=ViewBackward0]
|
|
140210811925168 -> 140210811924880
|
|
140210811925168 [label=ToCopyBackward0]
|
|
140202224193008 -> 140210811925168
|
|
140202224193008 [label=SliceBackward0]
|
|
140210811925312 -> 140202224193008
|
|
140210811925312 [label=SliceBackward0]
|
|
140210811925408 -> 140210811925312
|
|
140210811925408 [label=NativeLayerNormBackward0]
|
|
140210811925504 -> 140210811925408
|
|
140210811925504 [label=AddBackward0]
|
|
140210811925696 -> 140210811925504
|
|
140210811925696 [label=NativeDropoutBackward0]
|
|
140210811925840 -> 140210811925696
|
|
140210811925840 [label=ViewBackward0]
|
|
140210811925936 -> 140210811925840
|
|
140210811925936 [label=AddmmBackward0]
|
|
140210811926032 -> 140210811925936
|
|
140210811926032 [label=ToCopyBackward0]
|
|
140210811926224 -> 140210811926032
|
|
140202229012816 [label="encoder.layer.4.crossattention.output.dense.bias
|
|
(768)" fillcolor=lightblue]
|
|
140202229012816 -> 140210811926224
|
|
140210811926224 [label=AccumulateGrad]
|
|
140210811925984 -> 140210811925936
|
|
140210811925984 [label=ViewBackward0]
|
|
140210811926272 -> 140210811925984
|
|
140210811926272 [label=ViewBackward0]
|
|
140210811926368 -> 140210811926272
|
|
140210811926368 [label=CloneBackward0]
|
|
140210811926464 -> 140210811926368
|
|
140210811926464 [label=PermuteBackward0]
|
|
140210811926560 -> 140210811926464
|
|
140210811926560 [label=UnsafeViewBackward0]
|
|
140210811926656 -> 140210811926560
|
|
140210811926656 [label=BmmBackward0]
|
|
140210811926752 -> 140210811926656
|
|
140210811926752 [label=ReshapeAliasBackward0]
|
|
140210811926896 -> 140210811926752
|
|
140210811926896 [label=ExpandBackward0]
|
|
140210811926992 -> 140210811926896
|
|
140210811926992 [label=ToCopyBackward0]
|
|
140210811927088 -> 140210811926992
|
|
140210811927088 [label=NativeDropoutBackward0]
|
|
140210811927184 -> 140210811927088
|
|
140210811927184 [label=SoftmaxBackward0]
|
|
140210811927280 -> 140210811927184
|
|
140210811927280 [label=AddBackward0]
|
|
140210811927376 -> 140210811927280
|
|
140210811927376 [label=DivBackward0]
|
|
140210811927472 -> 140210811927376
|
|
140210811927472 [label=UnsafeViewBackward0]
|
|
140210811927568 -> 140210811927472
|
|
140210811927568 [label=BmmBackward0]
|
|
140210811927664 -> 140210811927568
|
|
140210811927664 [label=ReshapeAliasBackward0]
|
|
140210811927808 -> 140210811927664
|
|
140210811927808 [label=ExpandBackward0]
|
|
140210811927904 -> 140210811927808
|
|
140210811927904 [label=PermuteBackward0]
|
|
140210811928000 -> 140210811927904
|
|
140210811928000 [label=ViewBackward0]
|
|
140210811928096 -> 140210811928000
|
|
140210811928096 [label=ViewBackward0]
|
|
140210811928192 -> 140210811928096
|
|
140210811928192 [label=AddmmBackward0]
|
|
140210811928288 -> 140210811928192
|
|
140210811928288 [label=ToCopyBackward0]
|
|
140210811928480 -> 140210811928288
|
|
140202229013536 [label="encoder.layer.4.crossattention.self.query.bias
|
|
(768)" fillcolor=lightblue]
|
|
140202229013536 -> 140210811928480
|
|
140210811928480 [label=AccumulateGrad]
|
|
140210811928240 -> 140210811928192
|
|
140210811928240 [label=ViewBackward0]
|
|
140210811928384 -> 140210811928240
|
|
140210811928384 [label=ToCopyBackward0]
|
|
140210811925648 -> 140210811928384
|
|
140210811925648 [label=SliceBackward0]
|
|
140210811941024 -> 140210811925648
|
|
140210811941024 [label=SliceBackward0]
|
|
140210811941120 -> 140210811941024
|
|
140210811941120 [label=SliceBackward0]
|
|
140210811941216 -> 140210811941120
|
|
140210811941216 [label=NativeLayerNormBackward0]
|
|
140210811941312 -> 140210811941216
|
|
140210811941312 [label=AddBackward0]
|
|
140210811941504 -> 140210811941312
|
|
140210811941504 [label=NativeDropoutBackward0]
|
|
140210811941648 -> 140210811941504
|
|
140210811941648 [label=ViewBackward0]
|
|
140210811941744 -> 140210811941648
|
|
140210811941744 [label=AddmmBackward0]
|
|
140210811941840 -> 140210811941744
|
|
140210811941840 [label=ToCopyBackward0]
|
|
140210811942032 -> 140210811941840
|
|
140202229014016 [label="encoder.layer.4.attention.output.dense.bias
|
|
(768)" fillcolor=lightblue]
|
|
140202229014016 -> 140210811942032
|
|
140210811942032 [label=AccumulateGrad]
|
|
140210811941792 -> 140210811941744
|
|
140210811941792 [label=ViewBackward0]
|
|
140210811942080 -> 140210811941792
|
|
140210811942080 [label=ViewBackward0]
|
|
140210811942176 -> 140210811942080
|
|
140210811942176 [label=CloneBackward0]
|
|
140210811942272 -> 140210811942176
|
|
140210811942272 [label=PermuteBackward0]
|
|
140210811942368 -> 140210811942272
|
|
140210811942368 [label=UnsafeViewBackward0]
|
|
140210811942464 -> 140210811942368
|
|
140210811942464 [label=BmmBackward0]
|
|
140210811942560 -> 140210811942464
|
|
140210811942560 [label=ReshapeAliasBackward0]
|
|
140210811942704 -> 140210811942560
|
|
140210811942704 [label=ExpandBackward0]
|
|
140210811942800 -> 140210811942704
|
|
140210811942800 [label=ToCopyBackward0]
|
|
140210811942896 -> 140210811942800
|
|
140210811942896 [label=NativeDropoutBackward0]
|
|
140210811942992 -> 140210811942896
|
|
140210811942992 [label=SoftmaxBackward0]
|
|
140210811943088 -> 140210811942992
|
|
140210811943088 [label=AddBackward0]
|
|
140210811943184 -> 140210811943088
|
|
140210811943184 [label=DivBackward0]
|
|
140210811943280 -> 140210811943184
|
|
140210811943280 [label=UnsafeViewBackward0]
|
|
140210811943376 -> 140210811943280
|
|
140210811943376 [label=BmmBackward0]
|
|
140210811943472 -> 140210811943376
|
|
140210811943472 [label=ReshapeAliasBackward0]
|
|
140210811943616 -> 140210811943472
|
|
140210811943616 [label=ExpandBackward0]
|
|
140210811943712 -> 140210811943616
|
|
140210811943712 [label=PermuteBackward0]
|
|
140210811943808 -> 140210811943712
|
|
140210811943808 [label=ViewBackward0]
|
|
140210811943904 -> 140210811943808
|
|
140210811943904 [label=ViewBackward0]
|
|
140210811944000 -> 140210811943904
|
|
140210811944000 [label=AddmmBackward0]
|
|
140210811944096 -> 140210811944000
|
|
140210811944096 [label=ToCopyBackward0]
|
|
140210811944288 -> 140210811944096
|
|
140202229023024 [label="encoder.layer.4.attention.self.query.bias
|
|
(768)" fillcolor=lightblue]
|
|
140202229023024 -> 140210811944288
|
|
140210811944288 [label=AccumulateGrad]
|
|
140210811944048 -> 140210811944000
|
|
140210811944048 [label=ViewBackward0]
|
|
140210811944336 -> 140210811944048
|
|
140210811944336 [label=ToCopyBackward0]
|
|
140210811941456 -> 140210811944336
|
|
140210811941456 [label=CatBackward0]
|
|
140210811944480 -> 140210811941456
|
|
140210811944480 [label=NativeLayerNormBackward0]
|
|
140210811944624 -> 140210811944480
|
|
140210811944624 [label=AddBackward0]
|
|
140210811944816 -> 140210811944624
|
|
140210811944816 [label=NativeDropoutBackward0]
|
|
140210811944912 -> 140210811944816
|
|
140210811944912 [label=ViewBackward0]
|
|
140210811957408 -> 140210811944912
|
|
140210811957408 [label=AddmmBackward0]
|
|
140210811957504 -> 140210811957408
|
|
140210811957504 [label=ToCopyBackward0]
|
|
140210811957696 -> 140210811957504
|
|
140202229023504 [label="encoder.layer.3.experts.dense2.bias
|
|
(768)" fillcolor=lightblue]
|
|
140202229023504 -> 140210811957696
|
|
140210811957696 [label=AccumulateGrad]
|
|
140210811957456 -> 140210811957408
|
|
140210811957456 [label=ViewBackward0]
|
|
140210811957744 -> 140210811957456
|
|
140210811957744 [label=GeluBackward0]
|
|
140210811957840 -> 140210811957744
|
|
140210811957840 [label=ViewBackward0]
|
|
140210811957936 -> 140210811957840
|
|
140210811957936 [label=AddmmBackward0]
|
|
140210811958032 -> 140210811957936
|
|
140210811958032 [label=ToCopyBackward0]
|
|
140210811958224 -> 140210811958032
|
|
140202229023744 [label="encoder.layer.3.experts.dense1.bias
|
|
(3072)" fillcolor=lightblue]
|
|
140202229023744 -> 140210811958224
|
|
140210811958224 [label=AccumulateGrad]
|
|
140210811957984 -> 140210811957936
|
|
140210811957984 [label=ViewBackward0]
|
|
140210811958272 -> 140210811957984
|
|
140210811958272 [label=ToCopyBackward0]
|
|
140210811944768 -> 140210811958272
|
|
140210811944768 [label=SliceBackward0]
|
|
140210811958416 -> 140210811944768
|
|
140210811958416 [label=SliceBackward0]
|
|
140210811958512 -> 140210811958416
|
|
140210811958512 [label=SliceBackward0]
|
|
140210811958608 -> 140210811958512
|
|
140210811958608 [label=SliceBackward0]
|
|
140210811958704 -> 140210811958608
|
|
140210811958704 [label=SliceBackward0]
|
|
140210811958800 -> 140210811958704
|
|
140210811958800 [label=NativeLayerNormBackward0]
|
|
140210811958896 -> 140210811958800
|
|
140210811958896 [label=AddBackward0]
|
|
140210811959088 -> 140210811958896
|
|
140210811959088 [label=NativeDropoutBackward0]
|
|
140210811959232 -> 140210811959088
|
|
140210811959232 [label=ViewBackward0]
|
|
140210811959328 -> 140210811959232
|
|
140210811959328 [label=AddmmBackward0]
|
|
140210811959424 -> 140210811959328
|
|
140210811959424 [label=ToCopyBackward0]
|
|
140210811959616 -> 140210811959424
|
|
140202229025664 [label="encoder.layer.3.attention.output.dense.bias
|
|
(768)" fillcolor=lightblue]
|
|
140202229025664 -> 140210811959616
|
|
140210811959616 [label=AccumulateGrad]
|
|
140210811959376 -> 140210811959328
|
|
140210811959376 [label=ViewBackward0]
|
|
140210811959664 -> 140210811959376
|
|
140210811959664 [label=ViewBackward0]
|
|
140210811959760 -> 140210811959664
|
|
140210811959760 [label=CloneBackward0]
|
|
140210811959856 -> 140210811959760
|
|
140210811959856 [label=PermuteBackward0]
|
|
140210811959952 -> 140210811959856
|
|
140210811959952 [label=UnsafeViewBackward0]
|
|
140210811960048 -> 140210811959952
|
|
140210811960048 [label=BmmBackward0]
|
|
140210811960144 -> 140210811960048
|
|
140210811960144 [label=ReshapeAliasBackward0]
|
|
140210811960288 -> 140210811960144
|
|
140210811960288 [label=ExpandBackward0]
|
|
140210811960384 -> 140210811960288
|
|
140210811960384 [label=ToCopyBackward0]
|
|
140210811960480 -> 140210811960384
|
|
140210811960480 [label=NativeDropoutBackward0]
|
|
140210811960576 -> 140210811960480
|
|
140210811960576 [label=SoftmaxBackward0]
|
|
140210811960672 -> 140210811960576
|
|
140210811960672 [label=AddBackward0]
|
|
140210811960768 -> 140210811960672
|
|
140210811960768 [label=DivBackward0]
|
|
140210811960864 -> 140210811960768
|
|
140210811960864 [label=UnsafeViewBackward0]
|
|
140210811960960 -> 140210811960864
|
|
140210811960960 [label=BmmBackward0]
|
|
140210811961056 -> 140210811960960
|
|
140210811961056 [label=ReshapeAliasBackward0]
|
|
140210811961200 -> 140210811961056
|
|
140210811961200 [label=ExpandBackward0]
|
|
140210811961296 -> 140210811961200
|
|
140210811961296 [label=PermuteBackward0]
|
|
140210811961104 -> 140210811961296
|
|
140210811961104 [label=ViewBackward0]
|
|
140210811973840 -> 140210811961104
|
|
140210811973840 [label=ViewBackward0]
|
|
140210811973936 -> 140210811973840
|
|
140210811973936 [label=AddmmBackward0]
|
|
140210811974032 -> 140210811973936
|
|
140210811974032 [label=ToCopyBackward0]
|
|
140210811974224 -> 140210811974032
|
|
140202229026384 [label="encoder.layer.3.attention.self.query.bias
|
|
(768)" fillcolor=lightblue]
|
|
140202229026384 -> 140210811974224
|
|
140210811974224 [label=AccumulateGrad]
|
|
140210811973984 -> 140210811973936
|
|
140210811973984 [label=ViewBackward0]
|
|
140210811974272 -> 140210811973984
|
|
140210811974272 [label=ToCopyBackward0]
|
|
140210811959040 -> 140210811974272
|
|
140210811959040 [label=CatBackward0]
|
|
140210811974416 -> 140210811959040
|
|
140210811974416 [label=NativeLayerNormBackward0]
|
|
140210811974560 -> 140210811974416
|
|
140210811974560 [label=AddBackward0]
|
|
140210811974752 -> 140210811974560
|
|
140210811974752 [label=NativeDropoutBackward0]
|
|
140210811974896 -> 140210811974752
|
|
140210811974896 [label=ViewBackward0]
|
|
140210811974992 -> 140210811974896
|
|
140210811974992 [label=AddmmBackward0]
|
|
140210811975088 -> 140210811974992
|
|
140210811975088 [label=ToCopyBackward0]
|
|
140210811975280 -> 140210811975088
|
|
140202229039248 [label="encoder.layer.2.experts.dense2.bias
|
|
(768)" fillcolor=lightblue]
|
|
140202229039248 -> 140210811975280
|
|
140210811975280 [label=AccumulateGrad]
|
|
140210811975040 -> 140210811974992
|
|
140210811975040 [label=ViewBackward0]
|
|
140210811975328 -> 140210811975040
|
|
140210811975328 [label=GeluBackward0]
|
|
140210811975424 -> 140210811975328
|
|
140210811975424 [label=ViewBackward0]
|
|
140210811975520 -> 140210811975424
|
|
140210811975520 [label=AddmmBackward0]
|
|
140210811975616 -> 140210811975520
|
|
140210811975616 [label=ToCopyBackward0]
|
|
140210811975808 -> 140210811975616
|
|
140202229039488 [label="encoder.layer.2.experts.dense1.bias
|
|
(3072)" fillcolor=lightblue]
|
|
140202229039488 -> 140210811975808
|
|
140210811975808 [label=AccumulateGrad]
|
|
140210811975568 -> 140210811975520
|
|
140210811975568 [label=ViewBackward0]
|
|
140210811975856 -> 140210811975568
|
|
140210811975856 [label=ToCopyBackward0]
|
|
140210811974704 -> 140210811975856
|
|
140210811974704 [label=SliceBackward0]
|
|
140210811976000 -> 140210811974704
|
|
140210811976000 [label=SliceBackward0]
|
|
140210811976096 -> 140210811976000
|
|
140210811976096 [label=NativeLayerNormBackward0]
|
|
140210811976192 -> 140210811976096
|
|
140210811976192 [label=AddBackward0]
|
|
140210811976384 -> 140210811976192
|
|
140210811976384 [label=NativeDropoutBackward0]
|
|
140210811976528 -> 140210811976384
|
|
140210811976528 [label=ViewBackward0]
|
|
140210811976624 -> 140210811976528
|
|
140210811976624 [label=AddmmBackward0]
|
|
140210811976720 -> 140210811976624
|
|
140210811976720 [label=ToCopyBackward0]
|
|
140210811976912 -> 140210811976720
|
|
140202229041408 [label="encoder.layer.2.crossattention.output.dense.bias
|
|
(768)" fillcolor=lightblue]
|
|
140202229041408 -> 140210811976912
|
|
140210811976912 [label=AccumulateGrad]
|
|
140210811976672 -> 140210811976624
|
|
140210811976672 [label=ViewBackward0]
|
|
140210811976960 -> 140210811976672
|
|
140210811976960 [label=ViewBackward0]
|
|
140210811977056 -> 140210811976960
|
|
140210811977056 [label=CloneBackward0]
|
|
140210811977152 -> 140210811977056
|
|
140210811977152 [label=PermuteBackward0]
|
|
140210811977248 -> 140210811977152
|
|
140210811977248 [label=UnsafeViewBackward0]
|
|
140210811977344 -> 140210811977248
|
|
140210811977344 [label=BmmBackward0]
|
|
140210811977440 -> 140210811977344
|
|
140210811977440 [label=ReshapeAliasBackward0]
|
|
140210811977584 -> 140210811977440
|
|
140210811977584 [label=ExpandBackward0]
|
|
140210811977680 -> 140210811977584
|
|
140210811977680 [label=ToCopyBackward0]
|
|
140210811977488 -> 140210811977680
|
|
140210811977488 [label=NativeDropoutBackward0]
|
|
140210811994320 -> 140210811977488
|
|
140210811994320 [label=SoftmaxBackward0]
|
|
140210811994416 -> 140210811994320
|
|
140210811994416 [label=AddBackward0]
|
|
140210811994512 -> 140210811994416
|
|
140210811994512 [label=DivBackward0]
|
|
140210811994608 -> 140210811994512
|
|
140210811994608 [label=UnsafeViewBackward0]
|
|
140210811994704 -> 140210811994608
|
|
140210811994704 [label=BmmBackward0]
|
|
140210811994800 -> 140210811994704
|
|
140210811994800 [label=ReshapeAliasBackward0]
|
|
140210811994944 -> 140210811994800
|
|
140210811994944 [label=ExpandBackward0]
|
|
140210811995040 -> 140210811994944
|
|
140210811995040 [label=PermuteBackward0]
|
|
140210811995136 -> 140210811995040
|
|
140210811995136 [label=ViewBackward0]
|
|
140210811995232 -> 140210811995136
|
|
140210811995232 [label=ViewBackward0]
|
|
140210811995328 -> 140210811995232
|
|
140210811995328 [label=AddmmBackward0]
|
|
140210811995424 -> 140210811995328
|
|
140210811995424 [label=ToCopyBackward0]
|
|
140210811995616 -> 140210811995424
|
|
140202229042128 [label="encoder.layer.2.crossattention.self.query.bias
|
|
(768)" fillcolor=lightblue]
|
|
140202229042128 -> 140210811995616
|
|
140210811995616 [label=AccumulateGrad]
|
|
140210811995376 -> 140210811995328
|
|
140210811995376 [label=ViewBackward0]
|
|
140210811995664 -> 140210811995376
|
|
140210811995664 [label=ToCopyBackward0]
|
|
140210811976336 -> 140210811995664
|
|
140210811976336 [label=SliceBackward0]
|
|
140210811995808 -> 140210811976336
|
|
140210811995808 [label=SliceBackward0]
|
|
140210811995904 -> 140210811995808
|
|
140210811995904 [label=SliceBackward0]
|
|
140210811996000 -> 140210811995904
|
|
140210811996000 [label=NativeLayerNormBackward0]
|
|
140210811996096 -> 140210811996000
|
|
140210811996096 [label=AddBackward0]
|
|
140210811996288 -> 140210811996096
|
|
140210811996288 [label=NativeDropoutBackward0]
|
|
140210811996432 -> 140210811996288
|
|
140210811996432 [label=ViewBackward0]
|
|
140210811996528 -> 140210811996432
|
|
140210811996528 [label=AddmmBackward0]
|
|
140210811996624 -> 140210811996528
|
|
140210811996624 [label=ToCopyBackward0]
|
|
140210811996816 -> 140210811996624
|
|
140202229042608 [label="encoder.layer.2.attention.output.dense.bias
|
|
(768)" fillcolor=lightblue]
|
|
140202229042608 -> 140210811996816
|
|
140210811996816 [label=AccumulateGrad]
|
|
140210811996576 -> 140210811996528
|
|
140210811996576 [label=ViewBackward0]
|
|
140210811996864 -> 140210811996576
|
|
140210811996864 [label=ViewBackward0]
|
|
140210811996960 -> 140210811996864
|
|
140210811996960 [label=CloneBackward0]
|
|
140210811997056 -> 140210811996960
|
|
140210811997056 [label=PermuteBackward0]
|
|
140210811997152 -> 140210811997056
|
|
140210811997152 [label=UnsafeViewBackward0]
|
|
140210811997248 -> 140210811997152
|
|
140210811997248 [label=BmmBackward0]
|
|
140210811997344 -> 140210811997248
|
|
140210811997344 [label=ReshapeAliasBackward0]
|
|
140210811997488 -> 140210811997344
|
|
140210811997488 [label=ExpandBackward0]
|
|
140210811997584 -> 140210811997488
|
|
140210811997584 [label=ToCopyBackward0]
|
|
140210811997680 -> 140210811997584
|
|
140210811997680 [label=NativeDropoutBackward0]
|
|
140210811997776 -> 140210811997680
|
|
140210811997776 [label=SoftmaxBackward0]
|
|
140210811997872 -> 140210811997776
|
|
140210811997872 [label=AddBackward0]
|
|
140210811997968 -> 140210811997872
|
|
140210811997968 [label=DivBackward0]
|
|
140210811998064 -> 140210811997968
|
|
140210811998064 [label=UnsafeViewBackward0]
|
|
140210811998160 -> 140210811998064
|
|
140210811998160 [label=BmmBackward0]
|
|
140210811997392 -> 140210811998160
|
|
140210811997392 [label=ReshapeAliasBackward0]
|
|
140210812006656 -> 140210811997392
|
|
140210812006656 [label=ExpandBackward0]
|
|
140210812006752 -> 140210812006656
|
|
140210812006752 [label=PermuteBackward0]
|
|
140210812006848 -> 140210812006752
|
|
140210812006848 [label=ViewBackward0]
|
|
140210812006944 -> 140210812006848
|
|
140210812006944 [label=ViewBackward0]
|
|
140210812007040 -> 140210812006944
|
|
140210812007040 [label=AddmmBackward0]
|
|
140210812007136 -> 140210812007040
|
|
140210812007136 [label=ToCopyBackward0]
|
|
140210812007328 -> 140210812007136
|
|
140202229047520 [label="encoder.layer.2.attention.self.query.bias
|
|
(768)" fillcolor=lightblue]
|
|
140202229047520 -> 140210812007328
|
|
140210812007328 [label=AccumulateGrad]
|
|
140210812007088 -> 140210812007040
|
|
140210812007088 [label=ViewBackward0]
|
|
140210812007376 -> 140210812007088
|
|
140210812007376 [label=ToCopyBackward0]
|
|
140210811996240 -> 140210812007376
|
|
140210811996240 [label=CatBackward0]
|
|
140210812007520 -> 140210811996240
|
|
140210812007520 [label=NativeLayerNormBackward0]
|
|
140210812007664 -> 140210812007520
|
|
140210812007664 [label=AddBackward0]
|
|
140210812007856 -> 140210812007664
|
|
140210812007856 [label=NativeDropoutBackward0]
|
|
140210812008000 -> 140210812007856
|
|
140210812008000 [label=ViewBackward0]
|
|
140210812008096 -> 140210812008000
|
|
140210812008096 [label=AddmmBackward0]
|
|
140210812008192 -> 140210812008096
|
|
140210812008192 [label=ToCopyBackward0]
|
|
140210812008384 -> 140210812008192
|
|
140202229048000 [label="encoder.layer.1.experts.dense2.bias
|
|
(768)" fillcolor=lightblue]
|
|
140202229048000 -> 140210812008384
|
|
140210812008384 [label=AccumulateGrad]
|
|
140210812008144 -> 140210812008096
|
|
140210812008144 [label=ViewBackward0]
|
|
140210812008432 -> 140210812008144
|
|
140210812008432 [label=GeluBackward0]
|
|
140210812008528 -> 140210812008432
|
|
140210812008528 [label=ViewBackward0]
|
|
140210812008624 -> 140210812008528
|
|
140210812008624 [label=AddmmBackward0]
|
|
140210812008720 -> 140210812008624
|
|
140210812008720 [label=ToCopyBackward0]
|
|
140210812008912 -> 140210812008720
|
|
140202229048240 [label="encoder.layer.1.experts.dense1.bias
|
|
(3072)" fillcolor=lightblue]
|
|
140202229048240 -> 140210812008912
|
|
140210812008912 [label=AccumulateGrad]
|
|
140210812008672 -> 140210812008624
|
|
140210812008672 [label=ViewBackward0]
|
|
140210812008960 -> 140210812008672
|
|
140210812008960 [label=ToCopyBackward0]
|
|
140210812007808 -> 140210812008960
|
|
140210812007808 [label=SliceBackward0]
|
|
140210812009104 -> 140210812007808
|
|
140210812009104 [label=SliceBackward0]
|
|
140210812009200 -> 140210812009104
|
|
140210812009200 [label=SliceBackward0]
|
|
140210812009296 -> 140210812009200
|
|
140210812009296 [label=SliceBackward0]
|
|
140210812009392 -> 140210812009296
|
|
140210812009392 [label=SliceBackward0]
|
|
140210812009488 -> 140210812009392
|
|
140210812009488 [label=NativeLayerNormBackward0]
|
|
140210812009584 -> 140210812009488
|
|
140210812009584 [label=AddBackward0]
|
|
140210812009776 -> 140210812009584
|
|
140210812009776 [label=NativeDropoutBackward0]
|
|
140210812009920 -> 140210812009776
|
|
140210812009920 [label=ViewBackward0]
|
|
140210812010016 -> 140210812009920
|
|
140210812010016 [label=AddmmBackward0]
|
|
140210812010112 -> 140210812010016
|
|
140210812010112 [label=ToCopyBackward0]
|
|
140210812010304 -> 140210812010112
|
|
140202229050160 [label="encoder.layer.1.attention.output.dense.bias
|
|
(768)" fillcolor=lightblue]
|
|
140202229050160 -> 140210812010304
|
|
140210812010304 [label=AccumulateGrad]
|
|
140210812010064 -> 140210812010016
|
|
140210812010064 [label=ViewBackward0]
|
|
140210812010352 -> 140210812010064
|
|
140210812010352 [label=ViewBackward0]
|
|
140210812010448 -> 140210812010352
|
|
140210812010448 [label=CloneBackward0]
|
|
140210812010256 -> 140210812010448
|
|
140210812010256 [label=PermuteBackward0]
|
|
140210812022992 -> 140210812010256
|
|
140210812022992 [label=UnsafeViewBackward0]
|
|
140210812023088 -> 140210812022992
|
|
140210812023088 [label=BmmBackward0]
|
|
140210812023184 -> 140210812023088
|
|
140210812023184 [label=ReshapeAliasBackward0]
|
|
140210812023328 -> 140210812023184
|
|
140210812023328 [label=ExpandBackward0]
|
|
140210812023424 -> 140210812023328
|
|
140210812023424 [label=ToCopyBackward0]
|
|
140210812023520 -> 140210812023424
|
|
140210812023520 [label=NativeDropoutBackward0]
|
|
140210812023616 -> 140210812023520
|
|
140210812023616 [label=SoftmaxBackward0]
|
|
140210812023712 -> 140210812023616
|
|
140210812023712 [label=AddBackward0]
|
|
140210812023808 -> 140210812023712
|
|
140210812023808 [label=DivBackward0]
|
|
140210812023904 -> 140210812023808
|
|
140210812023904 [label=UnsafeViewBackward0]
|
|
140210812024000 -> 140210812023904
|
|
140210812024000 [label=BmmBackward0]
|
|
140210812024096 -> 140210812024000
|
|
140210812024096 [label=ReshapeAliasBackward0]
|
|
140210812024240 -> 140210812024096
|
|
140210812024240 [label=ExpandBackward0]
|
|
140210812024336 -> 140210812024240
|
|
140210812024336 [label=PermuteBackward0]
|
|
140210812024432 -> 140210812024336
|
|
140210812024432 [label=ViewBackward0]
|
|
140210812024528 -> 140210812024432
|
|
140210812024528 [label=ViewBackward0]
|
|
140210812024624 -> 140210812024528
|
|
140210812024624 [label=AddmmBackward0]
|
|
140210812024720 -> 140210812024624
|
|
140210812024720 [label=ToCopyBackward0]
|
|
140210812024912 -> 140210812024720
|
|
140202229050880 [label="encoder.layer.1.attention.self.query.bias
|
|
(768)" fillcolor=lightblue]
|
|
140202229050880 -> 140210812024912
|
|
140210812024912 [label=AccumulateGrad]
|
|
140210812024672 -> 140210812024624
|
|
140210812024672 [label=ViewBackward0]
|
|
140210812024960 -> 140210812024672
|
|
140210812024960 [label=ToCopyBackward0]
|
|
140210812009728 -> 140210812024960
|
|
140210812009728 [label=CatBackward0]
|
|
140210812025104 -> 140210812009728
|
|
140210812025104 [label=NativeLayerNormBackward0]
|
|
140210812025248 -> 140210812025104
|
|
140210812025248 [label=AddBackward0]
|
|
140210812025440 -> 140210812025248
|
|
140210812025440 [label=NativeDropoutBackward0]
|
|
140210812025584 -> 140210812025440
|
|
140210812025584 [label=ViewBackward0]
|
|
140210812025680 -> 140210812025584
|
|
140210812025680 [label=AddmmBackward0]
|
|
140210812025776 -> 140210812025680
|
|
140210812025776 [label=ToCopyBackward0]
|
|
140210812025968 -> 140210812025776
|
|
140202229067840 [label="encoder.layer.0.experts.dense2.bias
|
|
(768)" fillcolor=lightblue]
|
|
140202229067840 -> 140210812025968
|
|
140210812025968 [label=AccumulateGrad]
|
|
140210812025728 -> 140210812025680
|
|
140210812025728 [label=ViewBackward0]
|
|
140210812026016 -> 140210812025728
|
|
140210812026016 [label=GeluBackward0]
|
|
140210812026112 -> 140210812026016
|
|
140210812026112 [label=ViewBackward0]
|
|
140210812026208 -> 140210812026112
|
|
140210812026208 [label=AddmmBackward0]
|
|
140210812026304 -> 140210812026208
|
|
140210812026304 [label=ToCopyBackward0]
|
|
140210812026496 -> 140210812026304
|
|
140202229068080 [label="encoder.layer.0.experts.dense1.bias
|
|
(3072)" fillcolor=lightblue]
|
|
140202229068080 -> 140210812026496
|
|
140210812026496 [label=AccumulateGrad]
|
|
140210812026256 -> 140210812026208
|
|
140210812026256 [label=ViewBackward0]
|
|
140210812026544 -> 140210812026256
|
|
140210812026544 [label=ToCopyBackward0]
|
|
140210812025392 -> 140210812026544
|
|
140210812025392 [label=SliceBackward0]
|
|
140210812026688 -> 140210812025392
|
|
140210812026688 [label=SliceBackward0]
|
|
140210812026784 -> 140210812026688
|
|
140210812026784 [label=NativeLayerNormBackward0]
|
|
140210812026832 -> 140210812026784
|
|
140210812026832 [label=AddBackward0]
|
|
140210812039424 -> 140210812026832
|
|
140210812039424 [label=NativeDropoutBackward0]
|
|
140210812039568 -> 140210812039424
|
|
140210812039568 [label=ViewBackward0]
|
|
140210812039664 -> 140210812039568
|
|
140210812039664 [label=AddmmBackward0]
|
|
140210812039760 -> 140210812039664
|
|
140210812039760 [label=ToCopyBackward0]
|
|
140210812039952 -> 140210812039760
|
|
140202229070000 [label="encoder.layer.0.crossattention.output.dense.bias
|
|
(768)" fillcolor=lightblue]
|
|
140202229070000 -> 140210812039952
|
|
140210812039952 [label=AccumulateGrad]
|
|
140210812039712 -> 140210812039664
|
|
140210812039712 [label=ViewBackward0]
|
|
140210812040000 -> 140210812039712
|
|
140210812040000 [label=ViewBackward0]
|
|
140210812040096 -> 140210812040000
|
|
140210812040096 [label=CloneBackward0]
|
|
140210812040192 -> 140210812040096
|
|
140210812040192 [label=PermuteBackward0]
|
|
140210812040288 -> 140210812040192
|
|
140210812040288 [label=UnsafeViewBackward0]
|
|
140210812040384 -> 140210812040288
|
|
140210812040384 [label=BmmBackward0]
|
|
140210812040480 -> 140210812040384
|
|
140210812040480 [label=ReshapeAliasBackward0]
|
|
140210812040624 -> 140210812040480
|
|
140210812040624 [label=ExpandBackward0]
|
|
140210812040720 -> 140210812040624
|
|
140210812040720 [label=ToCopyBackward0]
|
|
140210812040816 -> 140210812040720
|
|
140210812040816 [label=NativeDropoutBackward0]
|
|
140210812040912 -> 140210812040816
|
|
140210812040912 [label=SoftmaxBackward0]
|
|
140210812041008 -> 140210812040912
|
|
140210812041008 [label=AddBackward0]
|
|
140210812041104 -> 140210812041008
|
|
140210812041104 [label=DivBackward0]
|
|
140210812041200 -> 140210812041104
|
|
140210812041200 [label=UnsafeViewBackward0]
|
|
140210812041296 -> 140210812041200
|
|
140210812041296 [label=BmmBackward0]
|
|
140210812041392 -> 140210812041296
|
|
140210812041392 [label=ReshapeAliasBackward0]
|
|
140210812041536 -> 140210812041392
|
|
140210812041536 [label=ExpandBackward0]
|
|
140210812041632 -> 140210812041536
|
|
140210812041632 [label=PermuteBackward0]
|
|
140210812041728 -> 140210812041632
|
|
140210812041728 [label=ViewBackward0]
|
|
140210812041824 -> 140210812041728
|
|
140210812041824 [label=ViewBackward0]
|
|
140210812041920 -> 140210812041824
|
|
140210812041920 [label=AddmmBackward0]
|
|
140210812042016 -> 140210812041920
|
|
140210812042016 [label=ToCopyBackward0]
|
|
140210812042208 -> 140210812042016
|
|
140202229070720 [label="encoder.layer.0.crossattention.self.query.bias
|
|
(768)" fillcolor=lightblue]
|
|
140202229070720 -> 140210812042208
|
|
140210812042208 [label=AccumulateGrad]
|
|
140210812041968 -> 140210812041920
|
|
140210812041968 [label=ViewBackward0]
|
|
140210812042256 -> 140210812041968
|
|
140210812042256 [label=ToCopyBackward0]
|
|
140210812039376 -> 140210812042256
|
|
140210812039376 [label=SliceBackward0]
|
|
140210812042400 -> 140210812039376
|
|
140210812042400 [label=SliceBackward0]
|
|
140210812042496 -> 140210812042400
|
|
140210812042496 [label=SliceBackward0]
|
|
140210812042592 -> 140210812042496
|
|
140210812042592 [label=NativeLayerNormBackward0]
|
|
140210812042688 -> 140210812042592
|
|
140210812042688 [label=AddBackward0]
|
|
140210812042880 -> 140210812042688
|
|
140210812042880 [label=NativeDropoutBackward0]
|
|
140210812043024 -> 140210812042880
|
|
140210812043024 [label=ViewBackward0]
|
|
140210812043120 -> 140210812043024
|
|
140210812043120 [label=AddmmBackward0]
|
|
140210812043216 -> 140210812043120
|
|
140210812043216 [label=ToCopyBackward0]
|
|
140210812051664 -> 140210812043216
|
|
140202229071200 [label="encoder.layer.0.attention.output.dense.bias
|
|
(768)" fillcolor=lightblue]
|
|
140202229071200 -> 140210812051664
|
|
140210812051664 [label=AccumulateGrad]
|
|
140210812043168 -> 140210812043120
|
|
140210812043168 [label=ViewBackward0]
|
|
140210812051712 -> 140210812043168
|
|
140210812051712 [label=ViewBackward0]
|
|
140210812051808 -> 140210812051712
|
|
140210812051808 [label=CloneBackward0]
|
|
140210812051904 -> 140210812051808
|
|
140210812051904 [label=PermuteBackward0]
|
|
140210812052000 -> 140210812051904
|
|
140210812052000 [label=UnsafeViewBackward0]
|
|
140210812052096 -> 140210812052000
|
|
140210812052096 [label=BmmBackward0]
|
|
140210812052192 -> 140210812052096
|
|
140210812052192 [label=ReshapeAliasBackward0]
|
|
140210812052336 -> 140210812052192
|
|
140210812052336 [label=ExpandBackward0]
|
|
140210812052432 -> 140210812052336
|
|
140210812052432 [label=ToCopyBackward0]
|
|
140210812052528 -> 140210812052432
|
|
140210812052528 [label=NativeDropoutBackward0]
|
|
140210812052624 -> 140210812052528
|
|
140210812052624 [label=SoftmaxBackward0]
|
|
140210812052720 -> 140210812052624
|
|
140210812052720 [label=AddBackward0]
|
|
140210812052816 -> 140210812052720
|
|
140210812052816 [label=DivBackward0]
|
|
140210812052912 -> 140210812052816
|
|
140210812052912 [label=UnsafeViewBackward0]
|
|
140210812053008 -> 140210812052912
|
|
140210812053008 [label=BmmBackward0]
|
|
140210812053104 -> 140210812053008
|
|
140210812053104 [label=ReshapeAliasBackward0]
|
|
140210812053248 -> 140210812053104
|
|
140210812053248 [label=ExpandBackward0]
|
|
140210812053344 -> 140210812053248
|
|
140210812053344 [label=PermuteBackward0]
|
|
140210812053440 -> 140210812053344
|
|
140210812053440 [label=ViewBackward0]
|
|
140210812053536 -> 140210812053440
|
|
140210812053536 [label=ViewBackward0]
|
|
140210812053632 -> 140210812053536
|
|
140210812053632 [label=AddmmBackward0]
|
|
140210812053728 -> 140210812053632
|
|
140210812053728 [label=ToCopyBackward0]
|
|
140210812053920 -> 140210812053728
|
|
140202228734688 [label="encoder.layer.0.attention.self.query.bias
|
|
(768)" fillcolor=lightblue]
|
|
140202228734688 -> 140210812053920
|
|
140210812053920 [label=AccumulateGrad]
|
|
140210812053680 -> 140210812053632
|
|
140210812053680 [label=ViewBackward0]
|
|
140210812053968 -> 140210812053680
|
|
140210812053968 [label=ToCopyBackward0]
|
|
140210812042832 -> 140210812053968
|
|
140210812042832 [label=NativeDropoutBackward0]
|
|
140210812054112 -> 140210812042832
|
|
140210812054112 [label=NativeLayerNormBackward0]
|
|
140210812054208 -> 140210812054112
|
|
140210812054208 [label=CatBackward0]
|
|
140210812054400 -> 140210812054208
|
|
140210812054400 [label=ExpandBackward0]
|
|
140210812054544 -> 140210812054400
|
|
140202228561216 [label="
|
|
(1, 32, 768)" fillcolor=lightblue]
|
|
140202228561216 -> 140210812054544
|
|
140210812054544 [label=AccumulateGrad]
|
|
140210812054352 -> 140210812054208
|
|
140210812054352 [label=AddBackward0]
|
|
140210812054592 -> 140210812054352
|
|
140210812054592 [label=EmbeddingBackward0]
|
|
140210812054736 -> 140210812054592
|
|
140202228561776 [label="embeddings.word_embeddings.weight
|
|
(30523, 768)" fillcolor=lightblue]
|
|
140202228561776 -> 140210812054736
|
|
140210812054736 [label=AccumulateGrad]
|
|
140210812054640 -> 140210812054352
|
|
140210812054640 [label=EmbeddingBackward0]
|
|
140210812054784 -> 140210812054640
|
|
140202228735888 [label="embeddings.position_embeddings.weight
|
|
(512, 768)" fillcolor=lightblue]
|
|
140202228735888 -> 140210812054784
|
|
140210812054784 [label=AccumulateGrad]
|
|
140210812054160 -> 140210812054112
|
|
140202228560576 [label="embeddings.LayerNorm.weight
|
|
(768)" fillcolor=lightblue]
|
|
140202228560576 -> 140210812054160
|
|
140210812054160 [label=AccumulateGrad]
|
|
140210812053824 -> 140210812054112
|
|
140202228560336 [label="embeddings.LayerNorm.bias
|
|
(768)" fillcolor=lightblue]
|
|
140202228560336 -> 140210812053824
|
|
140210812053824 [label=AccumulateGrad]
|
|
140210812053152 -> 140210812053632
|
|
140210812053152 [label=TBackward0]
|
|
140210812053872 -> 140210812053152
|
|
140210812053872 [label=ToCopyBackward0]
|
|
140210812054304 -> 140210812053872
|
|
140202228560096 [label="encoder.layer.0.attention.self.query.weight
|
|
(768, 768)" fillcolor=lightblue]
|
|
140202228560096 -> 140210812054304
|
|
140210812054304 [label=AccumulateGrad]
|
|
140210812053056 -> 140210812053008
|
|
140210812053056 [label=ReshapeAliasBackward0]
|
|
140210812053392 -> 140210812053056
|
|
140210812053392 [label=ExpandBackward0]
|
|
140210812053584 -> 140210812053392
|
|
140210812053584 [label=TransposeBackward0]
|
|
140210812054064 -> 140210812053584
|
|
140210812054064 [label=PermuteBackward0]
|
|
140210812054832 -> 140210812054064
|
|
140210812054832 [label=ViewBackward0]
|
|
140210812054016 -> 140210812054832
|
|
140210812054016 [label=ViewBackward0]
|
|
140210812054448 -> 140210812054016
|
|
140210812054448 [label=AddmmBackward0]
|
|
140210812054928 -> 140210812054448
|
|
140210812054928 [label=ToCopyBackward0]
|
|
140210812055120 -> 140210812054928
|
|
140202229071680 [label="encoder.layer.0.attention.self.key.bias
|
|
(768)" fillcolor=lightblue]
|
|
140202229071680 -> 140210812055120
|
|
140210812055120 [label=AccumulateGrad]
|
|
140210812054688 -> 140210812054448
|
|
140210812054688 [label=ViewBackward0]
|
|
140210812055168 -> 140210812054688
|
|
140210812055168 [label=ToCopyBackward0]
|
|
140210812042832 -> 140210812055168
|
|
140210812053200 -> 140210812054448
|
|
140210812053200 [label=TBackward0]
|
|
140210812055024 -> 140210812053200
|
|
140210812055024 [label=ToCopyBackward0]
|
|
140210812055312 -> 140210812055024
|
|
140202228734048 [label="encoder.layer.0.attention.self.key.weight
|
|
(768, 768)" fillcolor=lightblue]
|
|
140202228734048 -> 140210812055312
|
|
140210812055312 [label=AccumulateGrad]
|
|
140210812052144 -> 140210812052096
|
|
140210812052144 [label=ReshapeAliasBackward0]
|
|
140210812052480 -> 140210812052144
|
|
140210812052480 [label=ExpandBackward0]
|
|
140210812052672 -> 140210812052480
|
|
140210812052672 [label=PermuteBackward0]
|
|
140210812052864 -> 140210812052672
|
|
140210812052864 [label=ViewBackward0]
|
|
140210812052240 -> 140210812052864
|
|
140210812052240 [label=ViewBackward0]
|
|
140210812053488 -> 140210812052240
|
|
140210812053488 [label=AddmmBackward0]
|
|
140210812054256 -> 140210812053488
|
|
140210812054256 [label=ToCopyBackward0]
|
|
140210812055264 -> 140210812054256
|
|
140202229071440 [label="encoder.layer.0.attention.self.value.bias
|
|
(768)" fillcolor=lightblue]
|
|
140202229071440 -> 140210812055264
|
|
140210812055264 [label=AccumulateGrad]
|
|
140210812053776 -> 140210812053488
|
|
140210812053776 [label=ViewBackward0]
|
|
140210812055072 -> 140210812053776
|
|
140210812055072 [label=ToCopyBackward0]
|
|
140210812042832 -> 140210812055072
|
|
140210812052288 -> 140210812053488
|
|
140210812052288 [label=TBackward0]
|
|
140210812054880 -> 140210812052288
|
|
140210812054880 [label=ToCopyBackward0]
|
|
140210812055216 -> 140210812054880
|
|
140202229071760 [label="encoder.layer.0.attention.self.value.weight
|
|
(768, 768)" fillcolor=lightblue]
|
|
140202229071760 -> 140210812055216
|
|
140210812055216 [label=AccumulateGrad]
|
|
140210812042928 -> 140210812043120
|
|
140210812042928 [label=TBackward0]
|
|
140210812051856 -> 140210812042928
|
|
140210812051856 [label=ToCopyBackward0]
|
|
140210812052048 -> 140210812051856
|
|
140202229071520 [label="encoder.layer.0.attention.output.dense.weight
|
|
(768, 768)" fillcolor=lightblue]
|
|
140202229071520 -> 140210812052048
|
|
140210812052048 [label=AccumulateGrad]
|
|
140210812042832 -> 140210812042688
|
|
140210812042640 -> 140210812042592
|
|
140202229071280 [label="encoder.layer.0.attention.output.LayerNorm.weight
|
|
(768)" fillcolor=lightblue]
|
|
140202229071280 -> 140210812042640
|
|
140210812042640 [label=AccumulateGrad]
|
|
140210812042112 -> 140210812042592
|
|
140202229070960 [label="encoder.layer.0.attention.output.LayerNorm.bias
|
|
(768)" fillcolor=lightblue]
|
|
140202229070960 -> 140210812042112
|
|
140210812042112 [label=AccumulateGrad]
|
|
140210812041440 -> 140210812041920
|
|
140210812041440 [label=TBackward0]
|
|
140210812042160 -> 140210812041440
|
|
140210812042160 [label=ToCopyBackward0]
|
|
140210812042544 -> 140210812042160
|
|
140202229071040 [label="encoder.layer.0.crossattention.self.query.weight
|
|
(768, 768)" fillcolor=lightblue]
|
|
140202229071040 -> 140210812042544
|
|
140210812042544 [label=AccumulateGrad]
|
|
140210812041344 -> 140210812041296
|
|
140210812041344 [label=ReshapeAliasBackward0]
|
|
140210812041680 -> 140210812041344
|
|
140210812041680 [label=ExpandBackward0]
|
|
140210812041872 -> 140210812041680
|
|
140210812041872 [label=TransposeBackward0]
|
|
140210812042352 -> 140210812041872
|
|
140210812042352 [label=PermuteBackward0]
|
|
140210812042784 -> 140210812042352
|
|
140210812042784 [label=ViewBackward0]
|
|
140210812042304 -> 140210812042784
|
|
140210812042304 [label=ViewBackward0]
|
|
140210812043072 -> 140210812042304
|
|
140210812043072 [label=AddmmBackward0]
|
|
140210812041488 -> 140210812043072
|
|
140210812041488 [label=ToCopyBackward0]
|
|
140210812051760 -> 140210812041488
|
|
140202229070480 [label="encoder.layer.0.crossattention.self.key.bias
|
|
(768)" fillcolor=lightblue]
|
|
140202229070480 -> 140210812051760
|
|
140210812051760 [label=AccumulateGrad]
|
|
140210812051568 -> 140210812043072
|
|
140210812051568 [label=ViewBackward0]
|
|
140210812052576 -> 140210812051568
|
|
140210812052576 [label=ToCopyBackward0]
|
|
140210812052960 -> 140210812052576
|
|
140210812052960 [label=NativeLayerNormBackward0]
|
|
140210812054496 -> 140210812052960
|
|
140202228735248 [label="
|
|
(1408)" fillcolor=lightblue]
|
|
140202228735248 -> 140210812054496
|
|
140210812054496 [label=AccumulateGrad]
|
|
140210812053296 -> 140210812052960
|
|
140202228735488 [label="
|
|
(1408)" fillcolor=lightblue]
|
|
140202228735488 -> 140210812053296
|
|
140210812053296 [label=AccumulateGrad]
|
|
140210812051520 -> 140210812043072
|
|
140210812051520 [label=TBackward0]
|
|
140210812051616 -> 140210812051520
|
|
140210812051616 [label=ToCopyBackward0]
|
|
140210812054976 -> 140210812051616
|
|
140202229070800 [label="encoder.layer.0.crossattention.self.key.weight
|
|
(768, 1408)" fillcolor=lightblue]
|
|
140202229070800 -> 140210812054976
|
|
140210812054976 [label=AccumulateGrad]
|
|
140210812040432 -> 140210812040384
|
|
140210812040432 [label=ReshapeAliasBackward0]
|
|
140210812040768 -> 140210812040432
|
|
140210812040768 [label=ExpandBackward0]
|
|
140210812040960 -> 140210812040768
|
|
140210812040960 [label=PermuteBackward0]
|
|
140210812041152 -> 140210812040960
|
|
140210812041152 [label=ViewBackward0]
|
|
140210812040528 -> 140210812041152
|
|
140210812040528 [label=ViewBackward0]
|
|
140210812041776 -> 140210812040528
|
|
140210812041776 [label=AddmmBackward0]
|
|
140210812042448 -> 140210812041776
|
|
140210812042448 [label=ToCopyBackward0]
|
|
140210812042976 -> 140210812042448
|
|
140202229070240 [label="encoder.layer.0.crossattention.self.value.bias
|
|
(768)" fillcolor=lightblue]
|
|
140202229070240 -> 140210812042976
|
|
140210812042976 [label=AccumulateGrad]
|
|
140210812042064 -> 140210812041776
|
|
140210812042064 [label=ViewBackward0]
|
|
140210812055360 -> 140210812042064
|
|
140210812055360 [label=ToCopyBackward0]
|
|
140210812052960 -> 140210812055360
|
|
140210812040576 -> 140210812041776
|
|
140210812040576 [label=TBackward0]
|
|
140210812051952 -> 140210812040576
|
|
140210812051952 [label=ToCopyBackward0]
|
|
140210812052768 -> 140210812051952
|
|
140202229070560 [label="encoder.layer.0.crossattention.self.value.weight
|
|
(768, 1408)" fillcolor=lightblue]
|
|
140202229070560 -> 140210812052768
|
|
140210812052768 [label=AccumulateGrad]
|
|
140210812039472 -> 140210812039664
|
|
140210812039472 [label=TBackward0]
|
|
140210812040144 -> 140210812039472
|
|
140210812040144 [label=ToCopyBackward0]
|
|
140210812040336 -> 140210812040144
|
|
140202229070320 [label="encoder.layer.0.crossattention.output.dense.weight
|
|
(768, 768)" fillcolor=lightblue]
|
|
140202229070320 -> 140210812040336
|
|
140210812040336 [label=AccumulateGrad]
|
|
140210812039376 -> 140210812026832
|
|
140210812026400 -> 140210812026784
|
|
140202229070080 [label="encoder.layer.0.crossattention.output.LayerNorm.weight
|
|
(768)" fillcolor=lightblue]
|
|
140202229070080 -> 140210812026400
|
|
140210812026400 [label=AccumulateGrad]
|
|
140210812039232 -> 140210812026784
|
|
140202229069760 [label="encoder.layer.0.crossattention.output.LayerNorm.bias
|
|
(768)" fillcolor=lightblue]
|
|
140202229069760 -> 140210812039232
|
|
140210812039232 [label=AccumulateGrad]
|
|
140210812025920 -> 140210812026208
|
|
140210812025920 [label=TBackward0]
|
|
140210812026448 -> 140210812025920
|
|
140210812026448 [label=ToCopyBackward0]
|
|
140210812026736 -> 140210812026448
|
|
140202229068400 [label="encoder.layer.0.experts.dense1.weight
|
|
(3072, 768)" fillcolor=lightblue]
|
|
140202229068400 -> 140210812026736
|
|
140210812026736 [label=AccumulateGrad]
|
|
140210812025488 -> 140210812025680
|
|
140210812025488 [label=TBackward0]
|
|
140210812026160 -> 140210812025488
|
|
140210812026160 [label=ToCopyBackward0]
|
|
140210812026640 -> 140210812026160
|
|
140202229068160 [label="encoder.layer.0.experts.dense2.weight
|
|
(768, 3072)" fillcolor=lightblue]
|
|
140202229068160 -> 140210812026640
|
|
140210812026640 [label=AccumulateGrad]
|
|
140210812025392 -> 140210812025248
|
|
140210812025200 -> 140210812025104
|
|
140202229067920 [label="encoder.layer.0.expert_ln.weight
|
|
(768)" fillcolor=lightblue]
|
|
140202229067920 -> 140210812025200
|
|
140210812025200 [label=AccumulateGrad]
|
|
140210812025152 -> 140210812025104
|
|
140202229051120 [label="encoder.layer.0.expert_ln.bias
|
|
(768)" fillcolor=lightblue]
|
|
140202229051120 -> 140210812025152
|
|
140210812025152 [label=AccumulateGrad]
|
|
140210812024864 -> 140210812009728
|
|
140210812024864 [label=NativeLayerNormBackward0]
|
|
140210812025536 -> 140210812024864
|
|
140210812025536 [label=AddBackward0]
|
|
140210812026352 -> 140210812025536
|
|
140210812026352 [label=NativeDropoutBackward0]
|
|
140210812026064 -> 140210812026352
|
|
140210812026064 [label=ViewBackward0]
|
|
140210812039280 -> 140210812026064
|
|
140210812039280 [label=AddmmBackward0]
|
|
140210812039808 -> 140210812039280
|
|
140210812039808 [label=ToCopyBackward0]
|
|
140210812039904 -> 140210812039808
|
|
140202229069280 [label="encoder.layer.0.output.dense.bias
|
|
(768)" fillcolor=lightblue]
|
|
140202229069280 -> 140210812039904
|
|
140210812039904 [label=AccumulateGrad]
|
|
140210812039616 -> 140210812039280
|
|
140210812039616 [label=ViewBackward0]
|
|
140210812040048 -> 140210812039616
|
|
140210812040048 [label=GeluBackward0]
|
|
140210812041056 -> 140210812040048
|
|
140210812041056 [label=ViewBackward0]
|
|
140210812041584 -> 140210812041056
|
|
140210812041584 [label=AddmmBackward0]
|
|
140210812042736 -> 140210812041584
|
|
140210812042736 [label=ToCopyBackward0]
|
|
140210812055456 -> 140210812042736
|
|
140202229069520 [label="encoder.layer.0.intermediate.dense.bias
|
|
(3072)" fillcolor=lightblue]
|
|
140202229069520 -> 140210812055456
|
|
140210812055456 [label=AccumulateGrad]
|
|
140210812040672 -> 140210812041584
|
|
140210812040672 [label=ViewBackward0]
|
|
140210812055408 -> 140210812040672
|
|
140210812055408 [label=ToCopyBackward0]
|
|
140210812025872 -> 140210812055408
|
|
140210812025872 [label=SliceBackward0]
|
|
140210812092672 -> 140210812025872
|
|
140210812092672 [label=SliceBackward0]
|
|
140210812092768 -> 140210812092672
|
|
140210812092768 [label=SliceBackward0]
|
|
140210812042592 -> 140210812092768
|
|
140210812055504 -> 140210812041584
|
|
140210812055504 [label=TBackward0]
|
|
140210812092576 -> 140210812055504
|
|
140210812092576 [label=ToCopyBackward0]
|
|
140210812092864 -> 140210812092576
|
|
140202229069840 [label="encoder.layer.0.intermediate.dense.weight
|
|
(3072, 768)" fillcolor=lightblue]
|
|
140202229069840 -> 140210812092864
|
|
140210812092864 [label=AccumulateGrad]
|
|
140210812039520 -> 140210812039280
|
|
140210812039520 [label=TBackward0]
|
|
140210812041248 -> 140210812039520
|
|
140210812041248 [label=ToCopyBackward0]
|
|
140210812052384 -> 140210812041248
|
|
140202229069600 [label="encoder.layer.0.output.dense.weight
|
|
(768, 3072)" fillcolor=lightblue]
|
|
140202229069600 -> 140210812052384
|
|
140210812052384 [label=AccumulateGrad]
|
|
140210812025872 -> 140210812025536
|
|
140210812025344 -> 140210812024864
|
|
140202229069360 [label="encoder.layer.0.output.LayerNorm.weight
|
|
(768)" fillcolor=lightblue]
|
|
140202229069360 -> 140210812025344
|
|
140210812025344 [label=AccumulateGrad]
|
|
140210812025296 -> 140210812024864
|
|
140202229069040 [label="encoder.layer.0.output.LayerNorm.bias
|
|
(768)" fillcolor=lightblue]
|
|
140202229069040 -> 140210812025296
|
|
140210812025296 [label=AccumulateGrad]
|
|
140210812024144 -> 140210812024624
|
|
140210812024144 [label=TBackward0]
|
|
140210812024816 -> 140210812024144
|
|
140210812024816 [label=ToCopyBackward0]
|
|
140210812025824 -> 140210812024816
|
|
140202229051200 [label="encoder.layer.1.attention.self.query.weight
|
|
(768, 768)" fillcolor=lightblue]
|
|
140202229051200 -> 140210812025824
|
|
140210812025824 [label=AccumulateGrad]
|
|
140210812024048 -> 140210812024000
|
|
140210812024048 [label=ReshapeAliasBackward0]
|
|
140210812024384 -> 140210812024048
|
|
140210812024384 [label=ExpandBackward0]
|
|
140210812024576 -> 140210812024384
|
|
140210812024576 [label=TransposeBackward0]
|
|
140210812025056 -> 140210812024576
|
|
140210812025056 [label=PermuteBackward0]
|
|
140210812026592 -> 140210812025056
|
|
140210812026592 [label=ViewBackward0]
|
|
140210812025008 -> 140210812026592
|
|
140210812025008 [label=ViewBackward0]
|
|
140210812040240 -> 140210812025008
|
|
140210812040240 [label=AddmmBackward0]
|
|
140210812040864 -> 140210812040240
|
|
140210812040864 [label=ToCopyBackward0]
|
|
140210812092528 -> 140210812040864
|
|
140202229050640 [label="encoder.layer.1.attention.self.key.bias
|
|
(768)" fillcolor=lightblue]
|
|
140202229050640 -> 140210812092528
|
|
140210812092528 [label=AccumulateGrad]
|
|
140210812039328 -> 140210812040240
|
|
140210812039328 [label=ViewBackward0]
|
|
140210812092912 -> 140210812039328
|
|
140210812092912 [label=ToCopyBackward0]
|
|
140210812009728 -> 140210812092912
|
|
140210812092480 -> 140210812040240
|
|
140210812092480 [label=TBackward0]
|
|
140210812092624 -> 140210812092480
|
|
140210812092624 [label=ToCopyBackward0]
|
|
140210812093056 -> 140210812092624
|
|
140202229050960 [label="encoder.layer.1.attention.self.key.weight
|
|
(768, 768)" fillcolor=lightblue]
|
|
140202229050960 -> 140210812093056
|
|
140210812093056 [label=AccumulateGrad]
|
|
140210812023136 -> 140210812023088
|
|
140210812023136 [label=ReshapeAliasBackward0]
|
|
140210812023472 -> 140210812023136
|
|
140210812023472 [label=ExpandBackward0]
|
|
140210812023664 -> 140210812023472
|
|
140210812023664 [label=PermuteBackward0]
|
|
140210812023856 -> 140210812023664
|
|
140210812023856 [label=ViewBackward0]
|
|
140210812023232 -> 140210812023856
|
|
140210812023232 [label=ViewBackward0]
|
|
140210812024480 -> 140210812023232
|
|
140210812024480 [label=AddmmBackward0]
|
|
140210812025632 -> 140210812024480
|
|
140210812025632 [label=ToCopyBackward0]
|
|
140210812039856 -> 140210812025632
|
|
140202229050400 [label="encoder.layer.1.attention.self.value.bias
|
|
(768)" fillcolor=lightblue]
|
|
140202229050400 -> 140210812039856
|
|
140210812039856 [label=AccumulateGrad]
|
|
140210812024768 -> 140210812024480
|
|
140210812024768 [label=ViewBackward0]
|
|
140210812092816 -> 140210812024768
|
|
140210812092816 [label=ToCopyBackward0]
|
|
140210812009728 -> 140210812092816
|
|
140210812023280 -> 140210812024480
|
|
140210812023280 [label=TBackward0]
|
|
140210812092720 -> 140210812023280
|
|
140210812092720 [label=ToCopyBackward0]
|
|
140210812092960 -> 140210812092720
|
|
140202229050720 [label="encoder.layer.1.attention.self.value.weight
|
|
(768, 768)" fillcolor=lightblue]
|
|
140202229050720 -> 140210812092960
|
|
140210812092960 [label=AccumulateGrad]
|
|
140210812009824 -> 140210812010016
|
|
140210812009824 [label=TBackward0]
|
|
140210812010208 -> 140210812009824
|
|
140210812010208 [label=ToCopyBackward0]
|
|
140210812023040 -> 140210812010208
|
|
140202229050480 [label="encoder.layer.1.attention.output.dense.weight
|
|
(768, 768)" fillcolor=lightblue]
|
|
140202229050480 -> 140210812023040
|
|
140210812023040 [label=AccumulateGrad]
|
|
140210812009728 -> 140210812009584
|
|
140210812009536 -> 140210812009488
|
|
140202229050240 [label="encoder.layer.1.attention.output.LayerNorm.weight
|
|
(768)" fillcolor=lightblue]
|
|
140202229050240 -> 140210812009536
|
|
140210812009536 [label=AccumulateGrad]
|
|
140210812008816 -> 140210812009488
|
|
140202229049920 [label="encoder.layer.1.attention.output.LayerNorm.bias
|
|
(768)" fillcolor=lightblue]
|
|
140202229049920 -> 140210812008816
|
|
140210812008816 [label=AccumulateGrad]
|
|
140210812008336 -> 140210812008624
|
|
140210812008336 [label=TBackward0]
|
|
140210812008864 -> 140210812008336
|
|
140210812008864 [label=ToCopyBackward0]
|
|
140210812009248 -> 140210812008864
|
|
140202229048560 [label="encoder.layer.1.experts.dense1.weight
|
|
(3072, 768)" fillcolor=lightblue]
|
|
140202229048560 -> 140210812009248
|
|
140210812009248 [label=AccumulateGrad]
|
|
140210812007904 -> 140210812008096
|
|
140210812007904 [label=TBackward0]
|
|
140210812008576 -> 140210812007904
|
|
140210812008576 [label=ToCopyBackward0]
|
|
140210812009056 -> 140210812008576
|
|
140202229048320 [label="encoder.layer.1.experts.dense2.weight
|
|
(768, 3072)" fillcolor=lightblue]
|
|
140202229048320 -> 140210812009056
|
|
140210812009056 [label=AccumulateGrad]
|
|
140210812007808 -> 140210812007664
|
|
140210812007616 -> 140210812007520
|
|
140202229048080 [label="encoder.layer.1.expert_ln.weight
|
|
(768)" fillcolor=lightblue]
|
|
140202229048080 -> 140210812007616
|
|
140210812007616 [label=AccumulateGrad]
|
|
140210812007568 -> 140210812007520
|
|
140202229047760 [label="encoder.layer.1.expert_ln.bias
|
|
(768)" fillcolor=lightblue]
|
|
140202229047760 -> 140210812007568
|
|
140210812007568 [label=AccumulateGrad]
|
|
140210812007280 -> 140210811996240
|
|
140210812007280 [label=NativeLayerNormBackward0]
|
|
140210812007952 -> 140210812007280
|
|
140210812007952 [label=AddBackward0]
|
|
140210812008768 -> 140210812007952
|
|
140210812008768 [label=NativeDropoutBackward0]
|
|
140210812008480 -> 140210812008768
|
|
140210812008480 [label=ViewBackward0]
|
|
140210812009008 -> 140210812008480
|
|
140210812009008 [label=AddmmBackward0]
|
|
140210812009680 -> 140210812009008
|
|
140210812009680 [label=ToCopyBackward0]
|
|
140210812010400 -> 140210812009680
|
|
140202229049440 [label="encoder.layer.1.output.dense.bias
|
|
(768)" fillcolor=lightblue]
|
|
140202229049440 -> 140210812010400
|
|
140210812010400 [label=AccumulateGrad]
|
|
140210812009632 -> 140210812009008
|
|
140210812009632 [label=ViewBackward0]
|
|
140210812009968 -> 140210812009632
|
|
140210812009968 [label=GeluBackward0]
|
|
140210812022848 -> 140210812009968
|
|
140210812022848 [label=ViewBackward0]
|
|
140210812023568 -> 140210812022848
|
|
140210812023568 [label=AddmmBackward0]
|
|
140210812023952 -> 140210812023568
|
|
140210812023952 [label=ToCopyBackward0]
|
|
140210812024192 -> 140210812023952
|
|
140202229049680 [label="encoder.layer.1.intermediate.dense.bias
|
|
(3072)" fillcolor=lightblue]
|
|
140202229049680 -> 140210812024192
|
|
140210812024192 [label=AccumulateGrad]
|
|
140210812023760 -> 140210812023568
|
|
140210812023760 [label=ViewBackward0]
|
|
140210812093248 -> 140210812023760
|
|
140210812093248 [label=ToCopyBackward0]
|
|
140210812008288 -> 140210812093248
|
|
140210812008288 [label=SliceBackward0]
|
|
140210812093296 -> 140210812008288
|
|
140210812093296 [label=SliceBackward0]
|
|
140210812093392 -> 140210812093296
|
|
140210812093392 [label=SliceBackward0]
|
|
140210812009488 -> 140210812093392
|
|
140210812023376 -> 140210812023568
|
|
140210812023376 [label=TBackward0]
|
|
140210812093008 -> 140210812023376
|
|
140210812093008 [label=ToCopyBackward0]
|
|
140210812093488 -> 140210812093008
|
|
140202229050000 [label="encoder.layer.1.intermediate.dense.weight
|
|
(3072, 768)" fillcolor=lightblue]
|
|
140202229050000 -> 140210812093488
|
|
140210812093488 [label=AccumulateGrad]
|
|
140210812009440 -> 140210812009008
|
|
140210812009440 [label=TBackward0]
|
|
140210812010160 -> 140210812009440
|
|
140210812010160 [label=ToCopyBackward0]
|
|
140210812024288 -> 140210812010160
|
|
140202229049760 [label="encoder.layer.1.output.dense.weight
|
|
(768, 3072)" fillcolor=lightblue]
|
|
140202229049760 -> 140210812024288
|
|
140210812024288 [label=AccumulateGrad]
|
|
140210812008288 -> 140210812007952
|
|
140210812007760 -> 140210812007280
|
|
140202229049520 [label="encoder.layer.1.output.LayerNorm.weight
|
|
(768)" fillcolor=lightblue]
|
|
140202229049520 -> 140210812007760
|
|
140210812007760 [label=AccumulateGrad]
|
|
140210812007712 -> 140210812007280
|
|
140202229049200 [label="encoder.layer.1.output.LayerNorm.bias
|
|
(768)" fillcolor=lightblue]
|
|
140202229049200 -> 140210812007712
|
|
140210812007712 [label=AccumulateGrad]
|
|
140210812006560 -> 140210812007040
|
|
140210812006560 [label=TBackward0]
|
|
140210812007232 -> 140210812006560
|
|
140210812007232 [label=ToCopyBackward0]
|
|
140210812008240 -> 140210812007232
|
|
140202229047840 [label="encoder.layer.2.attention.self.query.weight
|
|
(768, 768)" fillcolor=lightblue]
|
|
140202229047840 -> 140210812008240
|
|
140210812008240 [label=AccumulateGrad]
|
|
140210812006464 -> 140210811998160
|
|
140210812006464 [label=ReshapeAliasBackward0]
|
|
140210812006800 -> 140210812006464
|
|
140210812006800 [label=ExpandBackward0]
|
|
140210812006992 -> 140210812006800
|
|
140210812006992 [label=TransposeBackward0]
|
|
140210812007472 -> 140210812006992
|
|
140210812007472 [label=PermuteBackward0]
|
|
140210812009344 -> 140210812007472
|
|
140210812009344 [label=ViewBackward0]
|
|
140210812007424 -> 140210812009344
|
|
140210812007424 [label=ViewBackward0]
|
|
140210812009872 -> 140210812007424
|
|
140210812009872 [label=AddmmBackward0]
|
|
140210812022944 -> 140210812009872
|
|
140210812022944 [label=ToCopyBackward0]
|
|
140210812093200 -> 140210812022944
|
|
140202229047360 [label="encoder.layer.2.attention.self.key.bias
|
|
(768)" fillcolor=lightblue]
|
|
140202229047360 -> 140210812093200
|
|
140210812093200 [label=AccumulateGrad]
|
|
140210812022896 -> 140210812009872
|
|
140210812022896 [label=ViewBackward0]
|
|
140210812093536 -> 140210812022896
|
|
140210812093536 [label=ToCopyBackward0]
|
|
140210811996240 -> 140210812093536
|
|
140210812093104 -> 140210812009872
|
|
140210812093104 [label=TBackward0]
|
|
140210812093152 -> 140210812093104
|
|
140210812093152 [label=ToCopyBackward0]
|
|
140210812093680 -> 140210812093152
|
|
140202229047600 [label="encoder.layer.2.attention.self.key.weight
|
|
(768, 768)" fillcolor=lightblue]
|
|
140202229047600 -> 140210812093680
|
|
140210812093680 [label=AccumulateGrad]
|
|
140210811997296 -> 140210811997248
|
|
140210811997296 [label=ReshapeAliasBackward0]
|
|
140210811997632 -> 140210811997296
|
|
140210811997632 [label=ExpandBackward0]
|
|
140210811997824 -> 140210811997632
|
|
140210811997824 [label=PermuteBackward0]
|
|
140210811998016 -> 140210811997824
|
|
140210811998016 [label=ViewBackward0]
|
|
140210811998112 -> 140210811998016
|
|
140210811998112 [label=ViewBackward0]
|
|
140210812006896 -> 140210811998112
|
|
140210812006896 [label=AddmmBackward0]
|
|
140210812008048 -> 140210812006896
|
|
140210812008048 [label=ToCopyBackward0]
|
|
140210812006608 -> 140210812008048
|
|
140202229042848 [label="encoder.layer.2.attention.self.value.bias
|
|
(768)" fillcolor=lightblue]
|
|
140202229042848 -> 140210812006608
|
|
140210812006608 [label=AccumulateGrad]
|
|
140210812007184 -> 140210812006896
|
|
140210812007184 [label=ViewBackward0]
|
|
140210812093440 -> 140210812007184
|
|
140210812093440 [label=ToCopyBackward0]
|
|
140210811996240 -> 140210812093440
|
|
140210812006512 -> 140210812006896
|
|
140210812006512 [label=TBackward0]
|
|
140210812093344 -> 140210812006512
|
|
140210812093344 [label=ToCopyBackward0]
|
|
140210812093584 -> 140210812093344
|
|
140202229043088 [label="encoder.layer.2.attention.self.value.weight
|
|
(768, 768)" fillcolor=lightblue]
|
|
140202229043088 -> 140210812093584
|
|
140210812093584 [label=AccumulateGrad]
|
|
140210811996336 -> 140210811996528
|
|
140210811996336 [label=TBackward0]
|
|
140210811997008 -> 140210811996336
|
|
140210811997008 [label=ToCopyBackward0]
|
|
140210811997200 -> 140210811997008
|
|
140202229042928 [label="encoder.layer.2.attention.output.dense.weight
|
|
(768, 768)" fillcolor=lightblue]
|
|
140202229042928 -> 140210811997200
|
|
140210811997200 [label=AccumulateGrad]
|
|
140210811996240 -> 140210811996096
|
|
140210811996048 -> 140210811996000
|
|
140202229042688 [label="encoder.layer.2.attention.output.LayerNorm.weight
|
|
(768)" fillcolor=lightblue]
|
|
140202229042688 -> 140210811996048
|
|
140210811996048 [label=AccumulateGrad]
|
|
140210811995520 -> 140210811996000
|
|
140202229042368 [label="encoder.layer.2.attention.output.LayerNorm.bias
|
|
(768)" fillcolor=lightblue]
|
|
140202229042368 -> 140210811995520
|
|
140210811995520 [label=AccumulateGrad]
|
|
140210811994848 -> 140210811995328
|
|
140210811994848 [label=TBackward0]
|
|
140210811995568 -> 140210811994848
|
|
140210811995568 [label=ToCopyBackward0]
|
|
140210811995952 -> 140210811995568
|
|
140202229042448 [label="encoder.layer.2.crossattention.self.query.weight
|
|
(768, 768)" fillcolor=lightblue]
|
|
140202229042448 -> 140210811995952
|
|
140210811995952 [label=AccumulateGrad]
|
|
140210811994752 -> 140210811994704
|
|
140210811994752 [label=ReshapeAliasBackward0]
|
|
140210811995088 -> 140210811994752
|
|
140210811995088 [label=ExpandBackward0]
|
|
140210811995280 -> 140210811995088
|
|
140210811995280 [label=TransposeBackward0]
|
|
140210811995760 -> 140210811995280
|
|
140210811995760 [label=PermuteBackward0]
|
|
140210811996192 -> 140210811995760
|
|
140210811996192 [label=ViewBackward0]
|
|
140210811995712 -> 140210811996192
|
|
140210811995712 [label=ViewBackward0]
|
|
140210811996480 -> 140210811995712
|
|
140210811996480 [label=AddmmBackward0]
|
|
140210811996720 -> 140210811996480
|
|
140210811996720 [label=ToCopyBackward0]
|
|
140210811996912 -> 140210811996720
|
|
140202229041888 [label="encoder.layer.2.crossattention.self.key.bias
|
|
(768)" fillcolor=lightblue]
|
|
140202229041888 -> 140210811996912
|
|
140210811996912 [label=AccumulateGrad]
|
|
140210811996672 -> 140210811996480
|
|
140210811996672 [label=ViewBackward0]
|
|
140210811997728 -> 140210811996672
|
|
140210811997728 [label=ToCopyBackward0]
|
|
140210812052960 -> 140210811997728
|
|
140210811994896 -> 140210811996480
|
|
140210811994896 [label=TBackward0]
|
|
140210811997536 -> 140210811994896
|
|
140210811997536 [label=ToCopyBackward0]
|
|
140210811996768 -> 140210811997536
|
|
140202229042208 [label="encoder.layer.2.crossattention.self.key.weight
|
|
(768, 1408)" fillcolor=lightblue]
|
|
140202229042208 -> 140210811996768
|
|
140210811996768 [label=AccumulateGrad]
|
|
140210811977392 -> 140210811977344
|
|
140210811977392 [label=ReshapeAliasBackward0]
|
|
140210811977632 -> 140210811977392
|
|
140210811977632 [label=ExpandBackward0]
|
|
140210811994368 -> 140210811977632
|
|
140210811994368 [label=PermuteBackward0]
|
|
140210811994560 -> 140210811994368
|
|
140210811994560 [label=ViewBackward0]
|
|
140210811994176 -> 140210811994560
|
|
140210811994176 [label=ViewBackward0]
|
|
140210811995184 -> 140210811994176
|
|
140210811995184 [label=AddmmBackward0]
|
|
140210811995856 -> 140210811995184
|
|
140210811995856 [label=ToCopyBackward0]
|
|
140210811997440 -> 140210811995856
|
|
140202229041648 [label="encoder.layer.2.crossattention.self.value.bias
|
|
(768)" fillcolor=lightblue]
|
|
140202229041648 -> 140210811997440
|
|
140210811997440 [label=AccumulateGrad]
|
|
140210811995472 -> 140210811995184
|
|
140210811995472 [label=ViewBackward0]
|
|
140210811996384 -> 140210811995472
|
|
140210811996384 [label=ToCopyBackward0]
|
|
140210812052960 -> 140210811996384
|
|
140210811994224 -> 140210811995184
|
|
140210811994224 [label=TBackward0]
|
|
140210812009152 -> 140210811994224
|
|
140210812009152 [label=ToCopyBackward0]
|
|
140210811997104 -> 140210812009152
|
|
140202229041968 [label="encoder.layer.2.crossattention.self.value.weight
|
|
(768, 1408)" fillcolor=lightblue]
|
|
140202229041968 -> 140210811997104
|
|
140210811997104 [label=AccumulateGrad]
|
|
140210811976432 -> 140210811976624
|
|
140210811976432 [label=TBackward0]
|
|
140210811977104 -> 140210811976432
|
|
140210811977104 [label=ToCopyBackward0]
|
|
140210811977296 -> 140210811977104
|
|
140202229041728 [label="encoder.layer.2.crossattention.output.dense.weight
|
|
(768, 768)" fillcolor=lightblue]
|
|
140202229041728 -> 140210811977296
|
|
140210811977296 [label=AccumulateGrad]
|
|
140210811976336 -> 140210811976192
|
|
140210811976144 -> 140210811976096
|
|
140202229041488 [label="encoder.layer.2.crossattention.output.LayerNorm.weight
|
|
(768)" fillcolor=lightblue]
|
|
140202229041488 -> 140210811976144
|
|
140210811976144 [label=AccumulateGrad]
|
|
140210811975712 -> 140210811976096
|
|
140202229041168 [label="encoder.layer.2.crossattention.output.LayerNorm.bias
|
|
(768)" fillcolor=lightblue]
|
|
140202229041168 -> 140210811975712
|
|
140210811975712 [label=AccumulateGrad]
|
|
140210811975232 -> 140210811975520
|
|
140210811975232 [label=TBackward0]
|
|
140210811975760 -> 140210811975232
|
|
140210811975760 [label=ToCopyBackward0]
|
|
140210811976240 -> 140210811975760
|
|
140202229039808 [label="encoder.layer.2.experts.dense1.weight
|
|
(3072, 768)" fillcolor=lightblue]
|
|
140202229039808 -> 140210811976240
|
|
140210811976240 [label=AccumulateGrad]
|
|
140210811974800 -> 140210811974992
|
|
140210811974800 [label=TBackward0]
|
|
140210811975472 -> 140210811974800
|
|
140210811975472 [label=ToCopyBackward0]
|
|
140210811975952 -> 140210811975472
|
|
140202229039568 [label="encoder.layer.2.experts.dense2.weight
|
|
(768, 3072)" fillcolor=lightblue]
|
|
140202229039568 -> 140210811975952
|
|
140210811975952 [label=AccumulateGrad]
|
|
140210811974704 -> 140210811974560
|
|
140210811974512 -> 140210811974416
|
|
140202229039328 [label="encoder.layer.2.expert_ln.weight
|
|
(768)" fillcolor=lightblue]
|
|
140202229039328 -> 140210811974512
|
|
140210811974512 [label=AccumulateGrad]
|
|
140210811974464 -> 140210811974416
|
|
140202229026624 [label="encoder.layer.2.expert_ln.bias
|
|
(768)" fillcolor=lightblue]
|
|
140202229026624 -> 140210811974464
|
|
140210811974464 [label=AccumulateGrad]
|
|
140210811974176 -> 140210811959040
|
|
140210811974176 [label=NativeLayerNormBackward0]
|
|
140210811974848 -> 140210811974176
|
|
140210811974848 [label=AddBackward0]
|
|
140210811975664 -> 140210811974848
|
|
140210811975664 [label=NativeDropoutBackward0]
|
|
140210811975376 -> 140210811975664
|
|
140210811975376 [label=ViewBackward0]
|
|
140210811975904 -> 140210811975376
|
|
140210811975904 [label=AddmmBackward0]
|
|
140210811976768 -> 140210811975904
|
|
140210811976768 [label=ToCopyBackward0]
|
|
140210811976864 -> 140210811976768
|
|
140202229040688 [label="encoder.layer.2.output.dense.bias
|
|
(768)" fillcolor=lightblue]
|
|
140202229040688 -> 140210811976864
|
|
140210811976864 [label=AccumulateGrad]
|
|
140210811976576 -> 140210811975904
|
|
140210811976576 [label=ViewBackward0]
|
|
140210812006704 -> 140210811976576
|
|
140210812006704 [label=GeluBackward0]
|
|
140210811977200 -> 140210812006704
|
|
140210811977200 [label=ViewBackward0]
|
|
140210811994656 -> 140210811977200
|
|
140210811994656 [label=AddmmBackward0]
|
|
140210811996144 -> 140210811994656
|
|
140210811996144 [label=ToCopyBackward0]
|
|
140210812093728 -> 140210811996144
|
|
140202229040928 [label="encoder.layer.2.intermediate.dense.bias
|
|
(3072)" fillcolor=lightblue]
|
|
140202229040928 -> 140210812093728
|
|
140210812093728 [label=AccumulateGrad]
|
|
140210811994992 -> 140210811994656
|
|
140210811994992 [label=ViewBackward0]
|
|
140210812093824 -> 140210811994992
|
|
140210812093824 [label=ToCopyBackward0]
|
|
140210811975184 -> 140210812093824
|
|
140210811975184 [label=SliceBackward0]
|
|
140210812093968 -> 140210811975184
|
|
140210812093968 [label=SliceBackward0]
|
|
140210812094064 -> 140210812093968
|
|
140210812094064 [label=SliceBackward0]
|
|
140210811996000 -> 140210812094064
|
|
140210811994272 -> 140210811994656
|
|
140210811994272 [label=TBackward0]
|
|
140210812093632 -> 140210811994272
|
|
140210812093632 [label=ToCopyBackward0]
|
|
140210812094160 -> 140210812093632
|
|
140202229041248 [label="encoder.layer.2.intermediate.dense.weight
|
|
(3072, 768)" fillcolor=lightblue]
|
|
140202229041248 -> 140210812094160
|
|
140210812094160 [label=AccumulateGrad]
|
|
140210811976480 -> 140210811975904
|
|
140210811976480 [label=TBackward0]
|
|
140210811977536 -> 140210811976480
|
|
140210811977536 [label=ToCopyBackward0]
|
|
140210811997920 -> 140210811977536
|
|
140202229041008 [label="encoder.layer.2.output.dense.weight
|
|
(768, 3072)" fillcolor=lightblue]
|
|
140202229041008 -> 140210811997920
|
|
140210811997920 [label=AccumulateGrad]
|
|
140210811975184 -> 140210811974848
|
|
140210811974656 -> 140210811974176
|
|
140202229040768 [label="encoder.layer.2.output.LayerNorm.weight
|
|
(768)" fillcolor=lightblue]
|
|
140202229040768 -> 140210811974656
|
|
140210811974656 [label=AccumulateGrad]
|
|
140210811974608 -> 140210811974176
|
|
140202229040448 [label="encoder.layer.2.output.LayerNorm.bias
|
|
(768)" fillcolor=lightblue]
|
|
140202229040448 -> 140210811974608
|
|
140210811974608 [label=AccumulateGrad]
|
|
140210811973696 -> 140210811973936
|
|
140210811973696 [label=TBackward0]
|
|
140210811974128 -> 140210811973696
|
|
140210811974128 [label=ToCopyBackward0]
|
|
140210811975136 -> 140210811974128
|
|
140202229026704 [label="encoder.layer.3.attention.self.query.weight
|
|
(768, 768)" fillcolor=lightblue]
|
|
140202229026704 -> 140210811975136
|
|
140210811975136 [label=AccumulateGrad]
|
|
140210811961008 -> 140210811960960
|
|
140210811961008 [label=ReshapeAliasBackward0]
|
|
140210811961248 -> 140210811961008
|
|
140210811961248 [label=ExpandBackward0]
|
|
140210811973888 -> 140210811961248
|
|
140210811973888 [label=TransposeBackward0]
|
|
140210811974368 -> 140210811973888
|
|
140210811974368 [label=PermuteBackward0]
|
|
140210811976288 -> 140210811974368
|
|
140210811976288 [label=ViewBackward0]
|
|
140210811974320 -> 140210811976288
|
|
140210811974320 [label=ViewBackward0]
|
|
140210811977008 -> 140210811974320
|
|
140210811977008 [label=AddmmBackward0]
|
|
140210811994464 -> 140210811977008
|
|
140210811994464 [label=ToCopyBackward0]
|
|
140210812093776 -> 140210811994464
|
|
140202229026144 [label="encoder.layer.3.attention.self.key.bias
|
|
(768)" fillcolor=lightblue]
|
|
140202229026144 -> 140210812093776
|
|
140210812093776 [label=AccumulateGrad]
|
|
140210811973744 -> 140210811977008
|
|
140210811973744 [label=ViewBackward0]
|
|
140210812094208 -> 140210811973744
|
|
140210812094208 [label=ToCopyBackward0]
|
|
140210811959040 -> 140210812094208
|
|
140210812093872 -> 140210811977008
|
|
140210812093872 [label=TBackward0]
|
|
140210812093920 -> 140210812093872
|
|
140210812093920 [label=ToCopyBackward0]
|
|
140210812094352 -> 140210812093920
|
|
140202229026464 [label="encoder.layer.3.attention.self.key.weight
|
|
(768, 768)" fillcolor=lightblue]
|
|
140202229026464 -> 140210812094352
|
|
140210812094352 [label=AccumulateGrad]
|
|
140210811960096 -> 140210811960048
|
|
140210811960096 [label=ReshapeAliasBackward0]
|
|
140210811960432 -> 140210811960096
|
|
140210811960432 [label=ExpandBackward0]
|
|
140210811960624 -> 140210811960432
|
|
140210811960624 [label=PermuteBackward0]
|
|
140210811960816 -> 140210811960624
|
|
140210811960816 [label=ViewBackward0]
|
|
140210811960192 -> 140210811960816
|
|
140210811960192 [label=ViewBackward0]
|
|
140210811961152 -> 140210811960192
|
|
140210811961152 [label=AddmmBackward0]
|
|
140210811974944 -> 140210811961152
|
|
140210811974944 [label=ToCopyBackward0]
|
|
140210811976816 -> 140210811974944
|
|
140202229025904 [label="encoder.layer.3.attention.self.value.bias
|
|
(768)" fillcolor=lightblue]
|
|
140202229025904 -> 140210811976816
|
|
140210811976816 [label=AccumulateGrad]
|
|
140210811974080 -> 140210811961152
|
|
140210811974080 [label=ViewBackward0]
|
|
140210812094112 -> 140210811974080
|
|
140210812094112 [label=ToCopyBackward0]
|
|
140210811959040 -> 140210812094112
|
|
140210811973792 -> 140210811961152
|
|
140210811973792 [label=TBackward0]
|
|
140210812094016 -> 140210811973792
|
|
140210812094016 [label=ToCopyBackward0]
|
|
140210812094256 -> 140210812094016
|
|
140202229026224 [label="encoder.layer.3.attention.self.value.weight
|
|
(768, 768)" fillcolor=lightblue]
|
|
140202229026224 -> 140210812094256
|
|
140210812094256 [label=AccumulateGrad]
|
|
140210811959136 -> 140210811959328
|
|
140210811959136 [label=TBackward0]
|
|
140210811959808 -> 140210811959136
|
|
140210811959808 [label=ToCopyBackward0]
|
|
140210811960000 -> 140210811959808
|
|
140202229025984 [label="encoder.layer.3.attention.output.dense.weight
|
|
(768, 768)" fillcolor=lightblue]
|
|
140202229025984 -> 140210811960000
|
|
140210811960000 [label=AccumulateGrad]
|
|
140210811959040 -> 140210811958896
|
|
140210811958848 -> 140210811958800
|
|
140202229025744 [label="encoder.layer.3.attention.output.LayerNorm.weight
|
|
(768)" fillcolor=lightblue]
|
|
140202229025744 -> 140210811958848
|
|
140210811958848 [label=AccumulateGrad]
|
|
140210811958128 -> 140210811958800
|
|
140202229025424 [label="encoder.layer.3.attention.output.LayerNorm.bias
|
|
(768)" fillcolor=lightblue]
|
|
140202229025424 -> 140210811958128
|
|
140210811958128 [label=AccumulateGrad]
|
|
140210811957648 -> 140210811957936
|
|
140210811957648 [label=TBackward0]
|
|
140210811958176 -> 140210811957648
|
|
140210811958176 [label=ToCopyBackward0]
|
|
140210811958560 -> 140210811958176
|
|
140202229024064 [label="encoder.layer.3.experts.dense1.weight
|
|
(3072, 768)" fillcolor=lightblue]
|
|
140202229024064 -> 140210811958560
|
|
140210811958560 [label=AccumulateGrad]
|
|
140210811957312 -> 140210811957408
|
|
140210811957312 [label=TBackward0]
|
|
140210811957888 -> 140210811957312
|
|
140210811957888 [label=ToCopyBackward0]
|
|
140210811958368 -> 140210811957888
|
|
140202229023824 [label="encoder.layer.3.experts.dense2.weight
|
|
(768, 3072)" fillcolor=lightblue]
|
|
140202229023824 -> 140210811958368
|
|
140210811958368 [label=AccumulateGrad]
|
|
140210811944768 -> 140210811944624
|
|
140210811944576 -> 140210811944480
|
|
140202229023584 [label="encoder.layer.3.expert_ln.weight
|
|
(768)" fillcolor=lightblue]
|
|
140202229023584 -> 140210811944576
|
|
140210811944576 [label=AccumulateGrad]
|
|
140210811944528 -> 140210811944480
|
|
140202229023264 [label="encoder.layer.3.expert_ln.bias
|
|
(768)" fillcolor=lightblue]
|
|
140202229023264 -> 140210811944528
|
|
140210811944528 [label=AccumulateGrad]
|
|
140210811944240 -> 140210811941456
|
|
140210811944240 [label=NativeLayerNormBackward0]
|
|
140210811944864 -> 140210811944240
|
|
140210811944864 [label=AddBackward0]
|
|
140210811958080 -> 140210811944864
|
|
140210811958080 [label=NativeDropoutBackward0]
|
|
140210811957792 -> 140210811958080
|
|
140210811957792 [label=ViewBackward0]
|
|
140210811958320 -> 140210811957792
|
|
140210811958320 [label=AddmmBackward0]
|
|
140210811958992 -> 140210811958320
|
|
140210811958992 [label=ToCopyBackward0]
|
|
140210811959520 -> 140210811958992
|
|
140202229024944 [label="encoder.layer.3.output.dense.bias
|
|
(768)" fillcolor=lightblue]
|
|
140202229024944 -> 140210811959520
|
|
140210811959520 [label=AccumulateGrad]
|
|
140210811958944 -> 140210811958320
|
|
140210811958944 [label=ViewBackward0]
|
|
140210811959904 -> 140210811958944
|
|
140210811959904 [label=GeluBackward0]
|
|
140210811959568 -> 140210811959904
|
|
140210811959568 [label=ViewBackward0]
|
|
140210811960528 -> 140210811959568
|
|
140210811960528 [label=AddmmBackward0]
|
|
140210811960912 -> 140210811960528
|
|
140210811960912 [label=ToCopyBackward0]
|
|
140210811976048 -> 140210811960912
|
|
140202229025184 [label="encoder.layer.3.intermediate.dense.bias
|
|
(3072)" fillcolor=lightblue]
|
|
140202229025184 -> 140210811976048
|
|
140210811976048 [label=AccumulateGrad]
|
|
140210811960720 -> 140210811960528
|
|
140210811960720 [label=ViewBackward0]
|
|
140210812094544 -> 140210811960720
|
|
140210812094544 [label=ToCopyBackward0]
|
|
140210811957600 -> 140210812094544
|
|
140210811957600 [label=SliceBackward0]
|
|
140210812094592 -> 140210811957600
|
|
140210812094592 [label=SliceBackward0]
|
|
140210812094688 -> 140210812094592
|
|
140210812094688 [label=SliceBackward0]
|
|
140210811958800 -> 140210812094688
|
|
140210811959472 -> 140210811960528
|
|
140210811959472 [label=TBackward0]
|
|
140210812094304 -> 140210811959472
|
|
140210812094304 [label=ToCopyBackward0]
|
|
140210812094784 -> 140210812094304
|
|
140202229025504 [label="encoder.layer.3.intermediate.dense.weight
|
|
(3072, 768)" fillcolor=lightblue]
|
|
140202229025504 -> 140210812094784
|
|
140210812094784 [label=AccumulateGrad]
|
|
140210811958752 -> 140210811958320
|
|
140210811958752 [label=TBackward0]
|
|
140210811959712 -> 140210811958752
|
|
140210811959712 [label=ToCopyBackward0]
|
|
140210811960240 -> 140210811959712
|
|
140202229025264 [label="encoder.layer.3.output.dense.weight
|
|
(768, 3072)" fillcolor=lightblue]
|
|
140202229025264 -> 140210811960240
|
|
140210811960240 [label=AccumulateGrad]
|
|
140210811957600 -> 140210811944864
|
|
140210811944720 -> 140210811944240
|
|
140202229025024 [label="encoder.layer.3.output.LayerNorm.weight
|
|
(768)" fillcolor=lightblue]
|
|
140202229025024 -> 140210811944720
|
|
140210811944720 [label=AccumulateGrad]
|
|
140210811944672 -> 140210811944240
|
|
140202229024704 [label="encoder.layer.3.output.LayerNorm.bias
|
|
(768)" fillcolor=lightblue]
|
|
140202229024704 -> 140210811944672
|
|
140210811944672 [label=AccumulateGrad]
|
|
140210811943520 -> 140210811944000
|
|
140210811943520 [label=TBackward0]
|
|
140210811944192 -> 140210811943520
|
|
140210811944192 [label=ToCopyBackward0]
|
|
140210811944384 -> 140210811944192
|
|
140202229023344 [label="encoder.layer.4.attention.self.query.weight
|
|
(768, 768)" fillcolor=lightblue]
|
|
140202229023344 -> 140210811944384
|
|
140210811944384 [label=AccumulateGrad]
|
|
140210811943424 -> 140210811943376
|
|
140210811943424 [label=ReshapeAliasBackward0]
|
|
140210811943760 -> 140210811943424
|
|
140210811943760 [label=ExpandBackward0]
|
|
140210811943952 -> 140210811943760
|
|
140210811943952 [label=TransposeBackward0]
|
|
140210811944432 -> 140210811943952
|
|
140210811944432 [label=PermuteBackward0]
|
|
140210811943568 -> 140210811944432
|
|
140210811943568 [label=ViewBackward0]
|
|
140210811957360 -> 140210811943568
|
|
140210811957360 [label=ViewBackward0]
|
|
140210811959280 -> 140210811957360
|
|
140210811959280 [label=AddmmBackward0]
|
|
140210811960336 -> 140210811959280
|
|
140210811960336 [label=ToCopyBackward0]
|
|
140210812094496 -> 140210811960336
|
|
140202229022784 [label="encoder.layer.4.attention.self.key.bias
|
|
(768)" fillcolor=lightblue]
|
|
140202229022784 -> 140210812094496
|
|
140210812094496 [label=AccumulateGrad]
|
|
140210811957552 -> 140210811959280
|
|
140210811957552 [label=ViewBackward0]
|
|
140210812094832 -> 140210811957552
|
|
140210812094832 [label=ToCopyBackward0]
|
|
140210811941456 -> 140210812094832
|
|
140210812094400 -> 140210811959280
|
|
140210812094400 [label=TBackward0]
|
|
140210812094448 -> 140210812094400
|
|
140210812094448 [label=ToCopyBackward0]
|
|
140210812094976 -> 140210812094448
|
|
140202229023104 [label="encoder.layer.4.attention.self.key.weight
|
|
(768, 768)" fillcolor=lightblue]
|
|
140202229023104 -> 140210812094976
|
|
140210812094976 [label=AccumulateGrad]
|
|
140210811942512 -> 140210811942464
|
|
140210811942512 [label=ReshapeAliasBackward0]
|
|
140210811942848 -> 140210811942512
|
|
140210811942848 [label=ExpandBackward0]
|
|
140210811943040 -> 140210811942848
|
|
140210811943040 [label=PermuteBackward0]
|
|
140210811943232 -> 140210811943040
|
|
140210811943232 [label=ViewBackward0]
|
|
140210811942608 -> 140210811943232
|
|
140210811942608 [label=ViewBackward0]
|
|
140210811943856 -> 140210811942608
|
|
140210811943856 [label=AddmmBackward0]
|
|
140210811944144 -> 140210811943856
|
|
140210811944144 [label=ToCopyBackward0]
|
|
140210811959184 -> 140210811944144
|
|
140202229014256 [label="encoder.layer.4.attention.self.value.bias
|
|
(768)" fillcolor=lightblue]
|
|
140202229014256 -> 140210811959184
|
|
140210811959184 [label=AccumulateGrad]
|
|
140210811942656 -> 140210811943856
|
|
140210811942656 [label=ViewBackward0]
|
|
140210812094736 -> 140210811942656
|
|
140210812094736 [label=ToCopyBackward0]
|
|
140210811941456 -> 140210812094736
|
|
140210811958656 -> 140210811943856
|
|
140210811958656 [label=TBackward0]
|
|
140210812094640 -> 140210811958656
|
|
140210812094640 [label=ToCopyBackward0]
|
|
140210812094880 -> 140210812094640
|
|
140202229022864 [label="encoder.layer.4.attention.self.value.weight
|
|
(768, 768)" fillcolor=lightblue]
|
|
140202229022864 -> 140210812094880
|
|
140210812094880 [label=AccumulateGrad]
|
|
140210811941552 -> 140210811941744
|
|
140210811941552 [label=TBackward0]
|
|
140210811942224 -> 140210811941552
|
|
140210811942224 [label=ToCopyBackward0]
|
|
140210811942416 -> 140210811942224
|
|
140202229014336 [label="encoder.layer.4.attention.output.dense.weight
|
|
(768, 768)" fillcolor=lightblue]
|
|
140202229014336 -> 140210811942416
|
|
140210811942416 [label=AccumulateGrad]
|
|
140210811941456 -> 140210811941312
|
|
140210811941264 -> 140210811941216
|
|
140202229014096 [label="encoder.layer.4.attention.output.LayerNorm.weight
|
|
(768)" fillcolor=lightblue]
|
|
140202229014096 -> 140210811941264
|
|
140210811941264 [label=AccumulateGrad]
|
|
140210811940976 -> 140210811941216
|
|
140202229013776 [label="encoder.layer.4.attention.output.LayerNorm.bias
|
|
(768)" fillcolor=lightblue]
|
|
140202229013776 -> 140210811940976
|
|
140210811940976 [label=AccumulateGrad]
|
|
140210811927712 -> 140210811928192
|
|
140210811927712 [label=TBackward0]
|
|
140210811928432 -> 140210811927712
|
|
140210811928432 [label=ToCopyBackward0]
|
|
140210811941168 -> 140210811928432
|
|
140202229013856 [label="encoder.layer.4.crossattention.self.query.weight
|
|
(768, 768)" fillcolor=lightblue]
|
|
140202229013856 -> 140210811941168
|
|
140210811941168 [label=AccumulateGrad]
|
|
140210811927616 -> 140210811927568
|
|
140210811927616 [label=ReshapeAliasBackward0]
|
|
140210811927952 -> 140210811927616
|
|
140210811927952 [label=ExpandBackward0]
|
|
140210811928144 -> 140210811927952
|
|
140210811928144 [label=TransposeBackward0]
|
|
140210811928528 -> 140210811928144
|
|
140210811928528 [label=PermuteBackward0]
|
|
140210811927760 -> 140210811928528
|
|
140210811927760 [label=ViewBackward0]
|
|
140210811940928 -> 140210811927760
|
|
140210811940928 [label=ViewBackward0]
|
|
140210811941696 -> 140210811940928
|
|
140210811941696 [label=AddmmBackward0]
|
|
140210811941936 -> 140210811941696
|
|
140210811941936 [label=ToCopyBackward0]
|
|
140210811942128 -> 140210811941936
|
|
140202229013296 [label="encoder.layer.4.crossattention.self.key.bias
|
|
(768)" fillcolor=lightblue]
|
|
140202229013296 -> 140210811942128
|
|
140210811942128 [label=AccumulateGrad]
|
|
140210811941888 -> 140210811941696
|
|
140210811941888 [label=ViewBackward0]
|
|
140210811942944 -> 140210811941888
|
|
140210811942944 [label=ToCopyBackward0]
|
|
140210812052960 -> 140210811942944
|
|
140210811941072 -> 140210811941696
|
|
140210811941072 [label=TBackward0]
|
|
140210811942752 -> 140210811941072
|
|
140210811942752 [label=ToCopyBackward0]
|
|
140210811943664 -> 140210811942752
|
|
140202229013616 [label="encoder.layer.4.crossattention.self.key.weight
|
|
(768, 1408)" fillcolor=lightblue]
|
|
140202229013616 -> 140210811943664
|
|
140210811943664 [label=AccumulateGrad]
|
|
140210811926704 -> 140210811926656
|
|
140210811926704 [label=ReshapeAliasBackward0]
|
|
140210811927040 -> 140210811926704
|
|
140210811927040 [label=ExpandBackward0]
|
|
140210811927232 -> 140210811927040
|
|
140210811927232 [label=PermuteBackward0]
|
|
140210811927424 -> 140210811927232
|
|
140210811927424 [label=ViewBackward0]
|
|
140210811926800 -> 140210811927424
|
|
140210811926800 [label=ViewBackward0]
|
|
140210811928048 -> 140210811926800
|
|
140210811928048 [label=AddmmBackward0]
|
|
140210811958464 -> 140210811928048
|
|
140210811958464 [label=ToCopyBackward0]
|
|
140210811942320 -> 140210811958464
|
|
140202229013056 [label="encoder.layer.4.crossattention.self.value.bias
|
|
(768)" fillcolor=lightblue]
|
|
140202229013056 -> 140210811942320
|
|
140210811942320 [label=AccumulateGrad]
|
|
140210811928336 -> 140210811928048
|
|
140210811928336 [label=ViewBackward0]
|
|
140210811943328 -> 140210811928336
|
|
140210811943328 [label=ToCopyBackward0]
|
|
140210812052960 -> 140210811943328
|
|
140210811926848 -> 140210811928048
|
|
140210811926848 [label=TBackward0]
|
|
140210811941360 -> 140210811926848
|
|
140210811941360 [label=ToCopyBackward0]
|
|
140210811941600 -> 140210811941360
|
|
140202229013376 [label="encoder.layer.4.crossattention.self.value.weight
|
|
(768, 1408)" fillcolor=lightblue]
|
|
140202229013376 -> 140210811941600
|
|
140210811941600 [label=AccumulateGrad]
|
|
140210811925744 -> 140210811925936
|
|
140210811925744 [label=TBackward0]
|
|
140210811926416 -> 140210811925744
|
|
140210811926416 [label=ToCopyBackward0]
|
|
140210811926608 -> 140210811926416
|
|
140202229013136 [label="encoder.layer.4.crossattention.output.dense.weight
|
|
(768, 768)" fillcolor=lightblue]
|
|
140202229013136 -> 140210811926608
|
|
140210811926608 [label=AccumulateGrad]
|
|
140210811925648 -> 140210811925504
|
|
140210811925456 -> 140210811925408
|
|
140202229012896 [label="encoder.layer.4.crossattention.output.LayerNorm.weight
|
|
(768)" fillcolor=lightblue]
|
|
140202229012896 -> 140210811925456
|
|
140210811925456 [label=AccumulateGrad]
|
|
140210811925024 -> 140210811925408
|
|
140202229012576 [label="encoder.layer.4.crossattention.output.LayerNorm.bias
|
|
(768)" fillcolor=lightblue]
|
|
140202229012576 -> 140210811925024
|
|
140210811925024 [label=AccumulateGrad]
|
|
140210811924592 -> 140210811924832
|
|
140210811924592 [label=TBackward0]
|
|
140210811925072 -> 140210811924592
|
|
140210811925072 [label=ToCopyBackward0]
|
|
140210811925552 -> 140210811925072
|
|
140202229011216 [label="encoder.layer.4.experts.dense1.weight
|
|
(3072, 768)" fillcolor=lightblue]
|
|
140202229011216 -> 140210811925552
|
|
140210811925552 [label=AccumulateGrad]
|
|
140202224193104 -> 140202224193296
|
|
140202224193104 [label=TBackward0]
|
|
140210811924784 -> 140202224193104
|
|
140210811924784 [label=ToCopyBackward0]
|
|
140210811925264 -> 140210811924784
|
|
140202229010976 [label="encoder.layer.4.experts.dense2.weight
|
|
(768, 3072)" fillcolor=lightblue]
|
|
140202229010976 -> 140210811925264
|
|
140210811925264 [label=AccumulateGrad]
|
|
140202224193008 -> 140202224192864
|
|
140202224192816 -> 140202224192720
|
|
140202229010736 [label="encoder.layer.4.expert_ln.weight
|
|
(768)" fillcolor=lightblue]
|
|
140202229010736 -> 140202224192816
|
|
140202224192816 [label=AccumulateGrad]
|
|
140202224192768 -> 140202224192720
|
|
140202229010496 [label="encoder.layer.4.expert_ln.bias
|
|
(768)" fillcolor=lightblue]
|
|
140202229010496 -> 140202224192768
|
|
140202224192768 [label=AccumulateGrad]
|
|
140202224192432 -> 140202224191472
|
|
140202224192432 [label=NativeLayerNormBackward0]
|
|
140202224193152 -> 140202224192432
|
|
140202224193152 [label=AddBackward0]
|
|
140202224193440 -> 140202224193152
|
|
140202224193440 [label=NativeDropoutBackward0]
|
|
140210811924688 -> 140202224193440
|
|
140210811924688 [label=ViewBackward0]
|
|
140210811925216 -> 140210811924688
|
|
140210811925216 [label=AddmmBackward0]
|
|
140210811926080 -> 140210811925216
|
|
140210811926080 [label=ToCopyBackward0]
|
|
140210811926176 -> 140210811926080
|
|
140202229012096 [label="encoder.layer.4.output.dense.bias
|
|
(768)" fillcolor=lightblue]
|
|
140202229012096 -> 140210811926176
|
|
140210811926176 [label=AccumulateGrad]
|
|
140210811925888 -> 140210811925216
|
|
140210811925888 [label=ViewBackward0]
|
|
140210811926320 -> 140210811925888
|
|
140210811926320 [label=GeluBackward0]
|
|
140210811927328 -> 140210811926320
|
|
140210811927328 [label=ViewBackward0]
|
|
140210811927856 -> 140210811927328
|
|
140210811927856 [label=AddmmBackward0]
|
|
140210811926944 -> 140210811927856
|
|
140210811926944 [label=ToCopyBackward0]
|
|
140210812095024 -> 140210811926944
|
|
140202229012336 [label="encoder.layer.4.intermediate.dense.bias
|
|
(3072)" fillcolor=lightblue]
|
|
140202229012336 -> 140210812095024
|
|
140210812095024 [label=AccumulateGrad]
|
|
140210811943136 -> 140210811927856
|
|
140210811943136 [label=ViewBackward0]
|
|
140210812095120 -> 140210811943136
|
|
140210812095120 [label=ToCopyBackward0]
|
|
140210811924976 -> 140210812095120
|
|
140210811924976 [label=SliceBackward0]
|
|
140210812095264 -> 140210811924976
|
|
140210812095264 [label=SliceBackward0]
|
|
140210812095360 -> 140210812095264
|
|
140210812095360 [label=SliceBackward0]
|
|
140210811941216 -> 140210812095360
|
|
140210811941408 -> 140210811927856
|
|
140210811941408 [label=TBackward0]
|
|
140210812094928 -> 140210811941408
|
|
140210812094928 [label=ToCopyBackward0]
|
|
140210812095456 -> 140210812094928
|
|
140202229012656 [label="encoder.layer.4.intermediate.dense.weight
|
|
(3072, 768)" fillcolor=lightblue]
|
|
140202229012656 -> 140210812095456
|
|
140210812095456 [label=AccumulateGrad]
|
|
140210811925792 -> 140210811925216
|
|
140210811925792 [label=TBackward0]
|
|
140210811927520 -> 140210811925792
|
|
140210811927520 [label=ToCopyBackward0]
|
|
140210811941984 -> 140210811927520
|
|
140202229012416 [label="encoder.layer.4.output.dense.weight
|
|
(768, 3072)" fillcolor=lightblue]
|
|
140202229012416 -> 140210811941984
|
|
140210811941984 [label=AccumulateGrad]
|
|
140210811924976 -> 140202224193152
|
|
140202224192960 -> 140202224192432
|
|
140202229012176 [label="encoder.layer.4.output.LayerNorm.weight
|
|
(768)" fillcolor=lightblue]
|
|
140202229012176 -> 140202224192960
|
|
140202224192960 [label=AccumulateGrad]
|
|
140202224192912 -> 140202224192432
|
|
140202229011856 [label="encoder.layer.4.output.LayerNorm.bias
|
|
(768)" fillcolor=lightblue]
|
|
140202229011856 -> 140202224192912
|
|
140202224192912 [label=AccumulateGrad]
|
|
140202224191712 -> 140202224192192
|
|
140202224191712 [label=TBackward0]
|
|
140202224192528 -> 140202224191712
|
|
140202224192528 [label=ToCopyBackward0]
|
|
140202224193248 -> 140202224192528
|
|
140202228989840 [label="encoder.layer.5.attention.self.query.weight
|
|
(768, 768)" fillcolor=lightblue]
|
|
140202228989840 -> 140202224193248
|
|
140202224193248 [label=AccumulateGrad]
|
|
140202224189600 -> 140202224189552
|
|
140202224189600 [label=ReshapeAliasBackward0]
|
|
140202224191952 -> 140202224189600
|
|
140202224191952 [label=ExpandBackward0]
|
|
140202224192144 -> 140202224191952
|
|
140202224192144 [label=TransposeBackward0]
|
|
140202224192672 -> 140202224192144
|
|
140202224192672 [label=PermuteBackward0]
|
|
140202224192624 -> 140202224192672
|
|
140202224192624 [label=ViewBackward0]
|
|
140210811924544 -> 140202224192624
|
|
140210811924544 [label=ViewBackward0]
|
|
140210811926512 -> 140210811924544
|
|
140210811926512 [label=AddmmBackward0]
|
|
140210811927136 -> 140210811926512
|
|
140210811927136 [label=ToCopyBackward0]
|
|
140210812095072 -> 140210811927136
|
|
140202228989360 [label="encoder.layer.5.attention.self.key.bias
|
|
(768)" fillcolor=lightblue]
|
|
140202228989360 -> 140210812095072
|
|
140210812095072 [label=AccumulateGrad]
|
|
140210811925600 -> 140210811926512
|
|
140210811925600 [label=ViewBackward0]
|
|
140210812095504 -> 140210811925600
|
|
140210812095504 [label=ToCopyBackward0]
|
|
140202224191472 -> 140210812095504
|
|
140210812095168 -> 140210811926512
|
|
140210812095168 [label=TBackward0]
|
|
140210812095216 -> 140210812095168
|
|
140210812095216 [label=ToCopyBackward0]
|
|
140210812095648 -> 140210812095216
|
|
140202228989680 [label="encoder.layer.5.attention.self.key.weight
|
|
(768, 768)" fillcolor=lightblue]
|
|
140202228989680 -> 140210812095648
|
|
140210812095648 [label=AccumulateGrad]
|
|
140202224190416 -> 140202224190560
|
|
140202224190416 [label=ReshapeAliasBackward0]
|
|
140202224190176 -> 140202224190416
|
|
140202224190176 [label=ExpandBackward0]
|
|
140202224189984 -> 140202224190176
|
|
140202224189984 [label=PermuteBackward0]
|
|
140202224189792 -> 140202224189984
|
|
140202224189792 [label=ViewBackward0]
|
|
140202224190320 -> 140202224189792
|
|
140202224190320 [label=ViewBackward0]
|
|
140202224192048 -> 140202224190320
|
|
140202224192048 [label=AddmmBackward0]
|
|
140202224191760 -> 140202224192048
|
|
140202224191760 [label=ToCopyBackward0]
|
|
140210811926128 -> 140202224191760
|
|
140202228989120 [label="encoder.layer.5.attention.self.value.bias
|
|
(768)" fillcolor=lightblue]
|
|
140202228989120 -> 140210811926128
|
|
140210811926128 [label=AccumulateGrad]
|
|
140202224192336 -> 140202224192048
|
|
140202224192336 [label=ViewBackward0]
|
|
140210812095408 -> 140202224192336
|
|
140210812095408 [label=ToCopyBackward0]
|
|
140202224191472 -> 140210812095408
|
|
140202224190368 -> 140202224192048
|
|
140202224190368 [label=TBackward0]
|
|
140210812095312 -> 140202224190368
|
|
140210812095312 [label=ToCopyBackward0]
|
|
140210812095552 -> 140210812095312
|
|
140202228989440 [label="encoder.layer.5.attention.self.value.weight
|
|
(768, 768)" fillcolor=lightblue]
|
|
140202228989440 -> 140210812095552
|
|
140210812095552 [label=AccumulateGrad]
|
|
140202224191376 -> 140202224191184
|
|
140202224191376 [label=TBackward0]
|
|
140202224190704 -> 140202224191376
|
|
140202224190704 [label=ToCopyBackward0]
|
|
140202224190512 -> 140202224190704
|
|
140202228989200 [label="encoder.layer.5.attention.output.dense.weight
|
|
(768, 768)" fillcolor=lightblue]
|
|
140202228989200 -> 140202224190512
|
|
140202224190512 [label=AccumulateGrad]
|
|
140202224191472 -> 140202222987584
|
|
140202222987152 -> 140202222988352
|
|
140202228988960 [label="encoder.layer.5.attention.output.LayerNorm.weight
|
|
(768)" fillcolor=lightblue]
|
|
140202228988960 -> 140202222987152
|
|
140202222987152 [label=AccumulateGrad]
|
|
140202222987104 -> 140202222988352
|
|
140202228988640 [label="encoder.layer.5.attention.output.LayerNorm.bias
|
|
(768)" fillcolor=lightblue]
|
|
140202228988640 -> 140202222987104
|
|
140202222987104 [label=AccumulateGrad]
|
|
140202222986192 -> 140202222986672
|
|
140202222986192 [label=TBackward0]
|
|
140202222987200 -> 140202222986192
|
|
140202222987200 [label=ToCopyBackward0]
|
|
140202222988544 -> 140202222987200
|
|
140202228987280 [label="encoder.layer.5.experts.dense1.weight
|
|
(3072, 768)" fillcolor=lightblue]
|
|
140202228987280 -> 140202222988544
|
|
140202222988544 [label=AccumulateGrad]
|
|
140202222985760 -> 140202222986048
|
|
140202222985760 [label=TBackward0]
|
|
140202222986720 -> 140202222985760
|
|
140202222986720 [label=ToCopyBackward0]
|
|
140202222987488 -> 140202222986720
|
|
140202228987040 [label="encoder.layer.5.experts.dense2.weight
|
|
(768, 3072)" fillcolor=lightblue]
|
|
140202228987040 -> 140202222987488
|
|
140202222987488 [label=AccumulateGrad]
|
|
140202222985568 -> 140202222985280
|
|
140202222988592 -> 140202222988736
|
|
140202228986800 [label="encoder.layer.5.expert_ln.weight
|
|
(768)" fillcolor=lightblue]
|
|
140202228986800 -> 140202222988592
|
|
140202222988592 [label=AccumulateGrad]
|
|
140202222987392 -> 140202222988736
|
|
140202228986480 [label="encoder.layer.5.expert_ln.bias
|
|
(768)" fillcolor=lightblue]
|
|
140202228986480 -> 140202222987392
|
|
140202222987392 [label=AccumulateGrad]
|
|
140202222988160 -> 140202222935248
|
|
140202222988160 [label=NativeLayerNormBackward0]
|
|
140202222985664 -> 140202222988160
|
|
140202222985664 [label=AddBackward0]
|
|
140202222987008 -> 140202222985664
|
|
140202222987008 [label=NativeDropoutBackward0]
|
|
140202222986528 -> 140202222987008
|
|
140202222986528 [label=ViewBackward0]
|
|
140202222988448 -> 140202222986528
|
|
140202222988448 [label=AddmmBackward0]
|
|
140202222988256 -> 140202222988448
|
|
140202222988256 [label=ToCopyBackward0]
|
|
140202224190992 -> 140202222988256
|
|
140202228988160 [label="encoder.layer.5.output.dense.bias
|
|
(768)" fillcolor=lightblue]
|
|
140202228988160 -> 140202224190992
|
|
140202224190992 [label=AccumulateGrad]
|
|
140202224191616 -> 140202222988448
|
|
140202224191616 [label=ViewBackward0]
|
|
140202224190608 -> 140202224191616
|
|
140202224190608 [label=GeluBackward0]
|
|
140202224191040 -> 140202224190608
|
|
140202224191040 [label=ViewBackward0]
|
|
140202224190080 -> 140202224191040
|
|
140202224190080 [label=AddmmBackward0]
|
|
140202224189696 -> 140202224190080
|
|
140202224189696 [label=ToCopyBackward0]
|
|
140210811925360 -> 140202224189696
|
|
140202228988400 [label="encoder.layer.5.intermediate.dense.bias
|
|
(3072)" fillcolor=lightblue]
|
|
140202228988400 -> 140210811925360
|
|
140210811925360 [label=AccumulateGrad]
|
|
140202224189888 -> 140202224190080
|
|
140202224189888 [label=ViewBackward0]
|
|
140210812095840 -> 140202224189888
|
|
140210812095840 [label=ToCopyBackward0]
|
|
140202222986336 -> 140210812095840
|
|
140202222986336 [label=SliceBackward0]
|
|
140210812095888 -> 140202222986336
|
|
140210812095888 [label=SliceBackward0]
|
|
140210812095984 -> 140210812095888
|
|
140210812095984 [label=SliceBackward0]
|
|
140202222988352 -> 140210812095984
|
|
140202224191136 -> 140202224190080
|
|
140202224191136 [label=TBackward0]
|
|
140210812095600 -> 140202224191136
|
|
140210812095600 [label=ToCopyBackward0]
|
|
140210812096080 -> 140210812095600
|
|
140202228988720 [label="encoder.layer.5.intermediate.dense.weight
|
|
(3072, 768)" fillcolor=lightblue]
|
|
140202228988720 -> 140210812096080
|
|
140210812096080 [label=AccumulateGrad]
|
|
140202224191568 -> 140202222988448
|
|
140202224191568 [label=TBackward0]
|
|
140202224190800 -> 140202224191568
|
|
140202224190800 [label=ToCopyBackward0]
|
|
140202224191856 -> 140202224190800
|
|
140202228988480 [label="encoder.layer.5.output.dense.weight
|
|
(768, 3072)" fillcolor=lightblue]
|
|
140202228988480 -> 140202224191856
|
|
140202224191856 [label=AccumulateGrad]
|
|
140202222986336 -> 140202222985664
|
|
140202222985376 -> 140202222988160
|
|
140202228988240 [label="encoder.layer.5.output.LayerNorm.weight
|
|
(768)" fillcolor=lightblue]
|
|
140202228988240 -> 140202222985376
|
|
140202222985376 [label=AccumulateGrad]
|
|
140202222985328 -> 140202222988160
|
|
140202228987920 [label="encoder.layer.5.output.LayerNorm.bias
|
|
(768)" fillcolor=lightblue]
|
|
140202228987920 -> 140202222985328
|
|
140202222985328 [label=AccumulateGrad]
|
|
140202222963584 -> 140202222964352
|
|
140202222963584 [label=TBackward0]
|
|
140202222988928 -> 140202222963584
|
|
140202222988928 [label=ToCopyBackward0]
|
|
140202222986144 -> 140202222988928
|
|
140202228986560 [label="encoder.layer.6.attention.self.query.weight
|
|
(768, 768)" fillcolor=lightblue]
|
|
140202228986560 -> 140202222986144
|
|
140202222986144 [label=AccumulateGrad]
|
|
140202222963392 -> 140202222963200
|
|
140202222963392 [label=ReshapeAliasBackward0]
|
|
140202222963728 -> 140202222963392
|
|
140202222963728 [label=ExpandBackward0]
|
|
140202222964160 -> 140202222963728
|
|
140202222964160 [label=TransposeBackward0]
|
|
140202222964448 -> 140202222964160
|
|
140202222964448 [label=PermuteBackward0]
|
|
140202222989120 -> 140202222964448
|
|
140202222989120 [label=ViewBackward0]
|
|
140202222988112 -> 140202222989120
|
|
140202222988112 [label=ViewBackward0]
|
|
140202222988640 -> 140202222988112
|
|
140202222988640 [label=AddmmBackward0]
|
|
140202224190272 -> 140202222988640
|
|
140202224190272 [label=ToCopyBackward0]
|
|
140210812095792 -> 140202224190272
|
|
140202228986000 [label="encoder.layer.6.attention.self.key.bias
|
|
(768)" fillcolor=lightblue]
|
|
140202228986000 -> 140210812095792
|
|
140210812095792 [label=AccumulateGrad]
|
|
140202224191424 -> 140202222988640
|
|
140202224191424 [label=ViewBackward0]
|
|
140210812096128 -> 140202224191424
|
|
140210812096128 [label=ToCopyBackward0]
|
|
140202222935248 -> 140210812096128
|
|
140210812095696 -> 140202222988640
|
|
140210812095696 [label=TBackward0]
|
|
140210812095744 -> 140210812095696
|
|
140210812095744 [label=ToCopyBackward0]
|
|
140210812096272 -> 140210812095744
|
|
140202228986320 [label="encoder.layer.6.attention.self.key.weight
|
|
(768, 768)" fillcolor=lightblue]
|
|
140202228986320 -> 140210812096272
|
|
140210812096272 [label=AccumulateGrad]
|
|
140202222961760 -> 140202222961856
|
|
140202222961760 [label=ReshapeAliasBackward0]
|
|
140202222962432 -> 140202222961760
|
|
140202222962432 [label=ExpandBackward0]
|
|
140202222962816 -> 140202222962432
|
|
140202222962816 [label=PermuteBackward0]
|
|
140202222963104 -> 140202222962816
|
|
140202222963104 [label=ViewBackward0]
|
|
140202222961808 -> 140202222963104
|
|
140202222961808 [label=ViewBackward0]
|
|
140202222963968 -> 140202222961808
|
|
140202222963968 [label=AddmmBackward0]
|
|
140202222963488 -> 140202222963968
|
|
140202222963488 [label=ToCopyBackward0]
|
|
140202224191328 -> 140202222963488
|
|
140202228985664 [label="encoder.layer.6.attention.self.value.bias
|
|
(768)" fillcolor=lightblue]
|
|
140202228985664 -> 140202224191328
|
|
140202224191328 [label=AccumulateGrad]
|
|
140202222962144 -> 140202222963968
|
|
140202222962144 [label=ViewBackward0]
|
|
140210812096032 -> 140202222962144
|
|
140210812096032 [label=ToCopyBackward0]
|
|
140202222935248 -> 140210812096032
|
|
140202222985712 -> 140202222963968
|
|
140202222985712 [label=TBackward0]
|
|
140210812095936 -> 140202222985712
|
|
140210812095936 [label=ToCopyBackward0]
|
|
140210812096176 -> 140210812095936
|
|
140202228986080 [label="encoder.layer.6.attention.self.value.weight
|
|
(768, 768)" fillcolor=lightblue]
|
|
140202228986080 -> 140210812096176
|
|
140210812096176 [label=AccumulateGrad]
|
|
140202222960704 -> 140202222935728
|
|
140202222960704 [label=TBackward0]
|
|
140202222961280 -> 140202222960704
|
|
140202222961280 [label=ToCopyBackward0]
|
|
140202222961568 -> 140202222961280
|
|
140202228985744 [label="encoder.layer.6.attention.output.dense.weight
|
|
(768, 768)" fillcolor=lightblue]
|
|
140202228985744 -> 140202222961568
|
|
140202222961568 [label=AccumulateGrad]
|
|
140202222935248 -> 140202222935296
|
|
140202222935008 -> 140202222935104
|
|
140202228985504 [label="encoder.layer.6.attention.output.LayerNorm.weight
|
|
(768)" fillcolor=lightblue]
|
|
140202228985504 -> 140202222935008
|
|
140202222935008 [label=AccumulateGrad]
|
|
140202222934336 -> 140202222935104
|
|
140202228985184 [label="encoder.layer.6.attention.output.LayerNorm.bias
|
|
(768)" fillcolor=lightblue]
|
|
140202228985184 -> 140202222934336
|
|
140202222934336 [label=AccumulateGrad]
|
|
140202222933184 -> 140202222933952
|
|
140202222933184 [label=TBackward0]
|
|
140202222934240 -> 140202222933184
|
|
140202222934240 [label=ToCopyBackward0]
|
|
140202222934768 -> 140202222934240
|
|
140202228985264 [label="encoder.layer.6.crossattention.self.query.weight
|
|
(768, 768)" fillcolor=lightblue]
|
|
140202228985264 -> 140202222934768
|
|
140202222934768 [label=AccumulateGrad]
|
|
140202222932992 -> 140202222932800
|
|
140202222932992 [label=ReshapeAliasBackward0]
|
|
140202222933328 -> 140202222932992
|
|
140202222933328 [label=ExpandBackward0]
|
|
140202222933760 -> 140202222933328
|
|
140202222933760 [label=TransposeBackward0]
|
|
140202222934528 -> 140202222933760
|
|
140202222934528 [label=PermuteBackward0]
|
|
140202222935392 -> 140202222934528
|
|
140202222935392 [label=ViewBackward0]
|
|
140202222934624 -> 140202222935392
|
|
140202222934624 [label=ViewBackward0]
|
|
140202222935872 -> 140202222934624
|
|
140202222935872 [label=AddmmBackward0]
|
|
140202222933088 -> 140202222935872
|
|
140202222933088 [label=ToCopyBackward0]
|
|
140202222961088 -> 140202222933088
|
|
140202228984704 [label="encoder.layer.6.crossattention.self.key.bias
|
|
(768)" fillcolor=lightblue]
|
|
140202228984704 -> 140202222961088
|
|
140202222961088 [label=AccumulateGrad]
|
|
140202222960800 -> 140202222935872
|
|
140202222960800 [label=ViewBackward0]
|
|
140202222962624 -> 140202222960800
|
|
140202222962624 [label=ToCopyBackward0]
|
|
140210812052960 -> 140202222962624
|
|
140202222960896 -> 140202222935872
|
|
140202222960896 [label=TBackward0]
|
|
140202222962336 -> 140202222960896
|
|
140202222962336 [label=ToCopyBackward0]
|
|
140202222963680 -> 140202222962336
|
|
140202228985024 [label="encoder.layer.6.crossattention.self.key.weight
|
|
(768, 1408)" fillcolor=lightblue]
|
|
140202228985024 -> 140202222963680
|
|
140202222963680 [label=AccumulateGrad]
|
|
140202222906720 -> 140202222906816
|
|
140202222906720 [label=ReshapeAliasBackward0]
|
|
140202222906768 -> 140202222906720
|
|
140202222906768 [label=ExpandBackward0]
|
|
140202222907104 -> 140202222906768
|
|
140202222907104 [label=PermuteBackward0]
|
|
140202222932704 -> 140202222907104
|
|
140202222932704 [label=ViewBackward0]
|
|
140202222932032 -> 140202222932704
|
|
140202222932032 [label=ViewBackward0]
|
|
140202222933568 -> 140202222932032
|
|
140202222933568 [label=AddmmBackward0]
|
|
140202222934720 -> 140202222933568
|
|
140202222934720 [label=ToCopyBackward0]
|
|
140202222987776 -> 140202222934720
|
|
140202228984464 [label="encoder.layer.6.crossattention.self.value.bias
|
|
(768)" fillcolor=lightblue]
|
|
140202228984464 -> 140202222987776
|
|
140202222987776 [label=AccumulateGrad]
|
|
140202222934048 -> 140202222933568
|
|
140202222934048 [label=ViewBackward0]
|
|
140202222935776 -> 140202222934048
|
|
140202222935776 [label=ToCopyBackward0]
|
|
140210812052960 -> 140202222935776
|
|
140202222932224 -> 140202222933568
|
|
140202222932224 [label=TBackward0]
|
|
140202222961328 -> 140202222932224
|
|
140202222961328 [label=ToCopyBackward0]
|
|
140202222960992 -> 140202222961328
|
|
140202228984784 [label="encoder.layer.6.crossattention.self.value.weight
|
|
(768, 1408)" fillcolor=lightblue]
|
|
140202228984784 -> 140202222960992
|
|
140202222960992 [label=AccumulateGrad]
|
|
140202222905088 -> 140202222905328
|
|
140202222905088 [label=TBackward0]
|
|
140202222906240 -> 140202222905088
|
|
140202222906240 [label=ToCopyBackward0]
|
|
140202222906528 -> 140202222906240
|
|
140202228984544 [label="encoder.layer.6.crossattention.output.dense.weight
|
|
(768, 768)" fillcolor=lightblue]
|
|
140202228984544 -> 140202222906528
|
|
140202222906528 [label=AccumulateGrad]
|
|
140202222904848 -> 140202222904896
|
|
140202222904704 -> 140202222904512
|
|
140202228984304 [label="encoder.layer.6.crossattention.output.LayerNorm.weight
|
|
(768)" fillcolor=lightblue]
|
|
140202228984304 -> 140202222904704
|
|
140202222904704 [label=AccumulateGrad]
|
|
140202222903936 -> 140202222904512
|
|
140202228983984 [label="encoder.layer.6.crossattention.output.LayerNorm.bias
|
|
(768)" fillcolor=lightblue]
|
|
140202228983984 -> 140202222903936
|
|
140202222903936 [label=AccumulateGrad]
|
|
140202222903408 -> 140202222903552
|
|
140202222903408 [label=TBackward0]
|
|
140202222904128 -> 140202222903408
|
|
140202222904128 [label=ToCopyBackward0]
|
|
140202222904800 -> 140202222904128
|
|
140202228968480 [label="encoder.layer.6.experts.experts.0.dense1.weight
|
|
(3072, 768)" fillcolor=lightblue]
|
|
140202228968480 -> 140202222904800
|
|
140202222904800 [label=AccumulateGrad]
|
|
140202222873664 -> 140202222874144
|
|
140202222873664 [label=TBackward0]
|
|
140202222874336 -> 140202222873664
|
|
140202222874336 [label=ToCopyBackward0]
|
|
140202222904368 -> 140202222874336
|
|
140202228968560 [label="encoder.layer.6.experts.experts.0.dense2.weight
|
|
(768, 3072)" fillcolor=lightblue]
|
|
140202228968560 -> 140202222904368
|
|
140202222904368 [label=AccumulateGrad]
|
|
140202222873280 -> 140202222873232
|
|
140202222873280 [label=UnsqueezeBackward0]
|
|
140202222873856 -> 140202222873280
|
|
140202222873856 [label=NativeDropoutBackward0]
|
|
140202222874240 -> 140202222873856
|
|
140202222874240 [label=ViewBackward0]
|
|
140202222905376 -> 140202222874240
|
|
140202222905376 [label=AddmmBackward0]
|
|
140202222903360 -> 140202222905376
|
|
140202222903360 [label=ToCopyBackward0]
|
|
140202222905856 -> 140202222903360
|
|
140202228968240 [label="encoder.layer.6.experts.experts.1.dense2.bias
|
|
(768)" fillcolor=lightblue]
|
|
140202228968240 -> 140202222905856
|
|
140202222905856 [label=AccumulateGrad]
|
|
140202222904608 -> 140202222905376
|
|
140202222904608 [label=ViewBackward0]
|
|
140202222905760 -> 140202222904608
|
|
140202222905760 [label=GeluBackward0]
|
|
140202222907296 -> 140202222905760
|
|
140202222907296 [label=ViewBackward0]
|
|
140202222906048 -> 140202222907296
|
|
140202222906048 [label=AddmmBackward0]
|
|
140202222905472 -> 140202222906048
|
|
140202222905472 [label=ToCopyBackward0]
|
|
140202222935200 -> 140202222905472
|
|
140202228969040 [label="encoder.layer.6.experts.experts.1.dense1.bias
|
|
(3072)" fillcolor=lightblue]
|
|
140202228969040 -> 140202222935200
|
|
140202222935200 [label=AccumulateGrad]
|
|
140202222932512 -> 140202222906048
|
|
140202222932512 [label=ViewBackward0]
|
|
140202222962912 -> 140202222932512
|
|
140202222962912 [label=ToCopyBackward0]
|
|
140202222872416 -> 140202222962912
|
|
140202222932416 -> 140202222906048
|
|
140202222932416 [label=TBackward0]
|
|
140202222933280 -> 140202222932416
|
|
140202222933280 [label=ToCopyBackward0]
|
|
140210812096320 -> 140202222933280
|
|
140202228968320 [label="encoder.layer.6.experts.experts.1.dense1.weight
|
|
(3072, 768)" fillcolor=lightblue]
|
|
140202228968320 -> 140210812096320
|
|
140210812096320 [label=AccumulateGrad]
|
|
140202222903648 -> 140202222905376
|
|
140202222903648 [label=TBackward0]
|
|
140202222905952 -> 140202222903648
|
|
140202222905952 [label=ToCopyBackward0]
|
|
140202222963296 -> 140202222905952
|
|
140202228968080 [label="encoder.layer.6.experts.experts.1.dense2.weight
|
|
(768, 3072)" fillcolor=lightblue]
|
|
140202228968080 -> 140202222963296
|
|
140202222963296 [label=AccumulateGrad]
|
|
140202222873184 -> 140202222873232
|
|
140202222873184 [label=UnsqueezeBackward0]
|
|
140202222932896 -> 140202222873184
|
|
140202222932896 [label=NativeDropoutBackward0]
|
|
140202222873760 -> 140202222932896
|
|
140202222873760 [label=ViewBackward0]
|
|
140202222906288 -> 140202222873760
|
|
140202222906288 [label=AddmmBackward0]
|
|
140202222903888 -> 140202222906288
|
|
140202222903888 [label=ToCopyBackward0]
|
|
140210812096224 -> 140202222903888
|
|
140202228967760 [label="encoder.layer.6.experts.experts.2.dense2.bias
|
|
(768)" fillcolor=lightblue]
|
|
140202228967760 -> 140210812096224
|
|
140210812096224 [label=AccumulateGrad]
|
|
140210812096464 -> 140202222906288
|
|
140210812096464 [label=ViewBackward0]
|
|
140210811723936 -> 140210812096464
|
|
140210811723936 [label=GeluBackward0]
|
|
140210811724032 -> 140210811723936
|
|
140210811724032 [label=ViewBackward0]
|
|
140210811724128 -> 140210811724032
|
|
140210811724128 [label=AddmmBackward0]
|
|
140210811724224 -> 140210811724128
|
|
140210811724224 [label=ToCopyBackward0]
|
|
140210811724416 -> 140210811724224
|
|
140202228968000 [label="encoder.layer.6.experts.experts.2.dense1.bias
|
|
(3072)" fillcolor=lightblue]
|
|
140202228968000 -> 140210811724416
|
|
140210811724416 [label=AccumulateGrad]
|
|
140210811724176 -> 140210811724128
|
|
140210811724176 [label=ViewBackward0]
|
|
140210811724464 -> 140210811724176
|
|
140210811724464 [label=ToCopyBackward0]
|
|
140202222872416 -> 140210811724464
|
|
140210811723888 -> 140210811724128
|
|
140210811723888 [label=TBackward0]
|
|
140210811724320 -> 140210811723888
|
|
140210811724320 [label=ToCopyBackward0]
|
|
140210811724608 -> 140210811724320
|
|
140202228967840 [label="encoder.layer.6.experts.experts.2.dense1.weight
|
|
(3072, 768)" fillcolor=lightblue]
|
|
140202228967840 -> 140210811724608
|
|
140210811724608 [label=AccumulateGrad]
|
|
140210812096368 -> 140202222906288
|
|
140210812096368 [label=TBackward0]
|
|
140210811724080 -> 140210812096368
|
|
140210811724080 [label=ToCopyBackward0]
|
|
140210811724560 -> 140210811724080
|
|
140202228967600 [label="encoder.layer.6.experts.experts.2.dense2.weight
|
|
(768, 3072)" fillcolor=lightblue]
|
|
140202228967600 -> 140210811724560
|
|
140210811724560 [label=AccumulateGrad]
|
|
140202222872992 -> 140202222872800
|
|
140202222872992 [label=UnsqueezeBackward0]
|
|
140202222873568 -> 140202222872992
|
|
140202222873568 [label=UnsqueezeBackward0]
|
|
140202222904224 -> 140202222873568
|
|
140202222904224 [label=SumBackward1]
|
|
140210812096416 -> 140202222904224
|
|
140210812096416 [label=MulBackward0]
|
|
140210811724704 -> 140210812096416
|
|
140210811724704 [label=UnsqueezeBackward0]
|
|
140210811723984 -> 140210811724704
|
|
140210811723984 [label=TopkBackward0]
|
|
140210811724512 -> 140210811723984
|
|
140210811724512 [label=SoftmaxBackward0]
|
|
140210811724800 -> 140210811724512
|
|
140210811724800 [label=MmBackward0]
|
|
140210811724896 -> 140210811724800
|
|
140210811724896 [label=ToCopyBackward0]
|
|
140210811725040 -> 140210811724896
|
|
140210811725040 [label=MeanBackward1]
|
|
140210811725136 -> 140210811725040
|
|
140210811725136 [label=MulBackward0]
|
|
140202222872416 -> 140210811725136
|
|
140210811724848 -> 140210811724800
|
|
140210811724848 [label=TBackward0]
|
|
140210811725232 -> 140210811724848
|
|
140210811725232 [label=ToCopyBackward0]
|
|
140210811724944 -> 140210811725232
|
|
140202228981824 [label="encoder.layer.6.experts.gate.weight
|
|
(3, 768)" fillcolor=lightblue]
|
|
140202228981824 -> 140210811724944
|
|
140210811724944 [label=AccumulateGrad]
|
|
140202222872416 -> 140202222872272
|
|
140202222872128 -> 140202222871936
|
|
140202228982144 [label="encoder.layer.6.expert_ln.weight
|
|
(768)" fillcolor=lightblue]
|
|
140202228982144 -> 140202222872128
|
|
140202222872128 [label=AccumulateGrad]
|
|
140202222872224 -> 140202222871936
|
|
140202228981904 [label="encoder.layer.6.expert_ln.bias
|
|
(768)" fillcolor=lightblue]
|
|
140202228981904 -> 140202222872224
|
|
140202222872224 [label=AccumulateGrad]
|
|
140202222871744 -> 140202222842352
|
|
140202222871744 [label=NativeLayerNormBackward0]
|
|
140202222904992 -> 140202222871744
|
|
140202222904992 [label=AddBackward0]
|
|
140202222873088 -> 140202222904992
|
|
140202222873088 [label=NativeDropoutBackward0]
|
|
140210811724656 -> 140202222873088
|
|
140210811724656 [label=ViewBackward0]
|
|
140210811723840 -> 140210811724656
|
|
140210811723840 [label=AddmmBackward0]
|
|
140210811725184 -> 140210811723840
|
|
140210811725184 [label=ToCopyBackward0]
|
|
140210811725376 -> 140210811725184
|
|
140202228983504 [label="encoder.layer.6.output.dense.bias
|
|
(768)" fillcolor=lightblue]
|
|
140202228983504 -> 140210811725376
|
|
140210811725376 [label=AccumulateGrad]
|
|
140210811725088 -> 140210811723840
|
|
140210811725088 [label=ViewBackward0]
|
|
140210811725424 -> 140210811725088
|
|
140210811725424 [label=GeluBackward0]
|
|
140210811725520 -> 140210811725424
|
|
140210811725520 [label=ViewBackward0]
|
|
140210811725616 -> 140210811725520
|
|
140210811725616 [label=AddmmBackward0]
|
|
140210811725712 -> 140210811725616
|
|
140210811725712 [label=ToCopyBackward0]
|
|
140210811725904 -> 140210811725712
|
|
140202228983744 [label="encoder.layer.6.intermediate.dense.bias
|
|
(3072)" fillcolor=lightblue]
|
|
140202228983744 -> 140210811725904
|
|
140210811725904 [label=AccumulateGrad]
|
|
140210811725664 -> 140210811725616
|
|
140210811725664 [label=ViewBackward0]
|
|
140210811725952 -> 140210811725664
|
|
140210811725952 [label=ToCopyBackward0]
|
|
140202222873376 -> 140210811725952
|
|
140202222873376 [label=SliceBackward0]
|
|
140210811726096 -> 140202222873376
|
|
140210811726096 [label=SliceBackward0]
|
|
140210811726192 -> 140210811726096
|
|
140210811726192 [label=SliceBackward0]
|
|
140202222935104 -> 140210811726192
|
|
140210811724992 -> 140210811725616
|
|
140210811724992 [label=TBackward0]
|
|
140210811725856 -> 140210811724992
|
|
140210811725856 [label=ToCopyBackward0]
|
|
140210811726288 -> 140210811725856
|
|
140202228984064 [label="encoder.layer.6.intermediate.dense.weight
|
|
(3072, 768)" fillcolor=lightblue]
|
|
140202228984064 -> 140210811726288
|
|
140210811726288 [label=AccumulateGrad]
|
|
140210811724272 -> 140210811723840
|
|
140210811724272 [label=TBackward0]
|
|
140210811725568 -> 140210811724272
|
|
140210811725568 [label=ToCopyBackward0]
|
|
140210811726048 -> 140210811725568
|
|
140202228983824 [label="encoder.layer.6.output.dense.weight
|
|
(768, 3072)" fillcolor=lightblue]
|
|
140202228983824 -> 140210811726048
|
|
140210811726048 [label=AccumulateGrad]
|
|
140202222873376 -> 140202222904992
|
|
140202222872512 -> 140202222871744
|
|
140202228983584 [label="encoder.layer.6.output.LayerNorm.weight
|
|
(768)" fillcolor=lightblue]
|
|
140202228983584 -> 140202222872512
|
|
140202222872512 [label=AccumulateGrad]
|
|
140202222872320 -> 140202222871744
|
|
140202228983264 [label="encoder.layer.6.output.LayerNorm.bias
|
|
(768)" fillcolor=lightblue]
|
|
140202228983264 -> 140202222872320
|
|
140202222872320 [label=AccumulateGrad]
|
|
140202222870592 -> 140202222871168
|
|
140202222870592 [label=TBackward0]
|
|
140202222871456 -> 140202222870592
|
|
140202222871456 [label=ToCopyBackward0]
|
|
140202222872608 -> 140202222871456
|
|
140202228982384 [label="encoder.layer.7.attention.self.query.weight
|
|
(768, 768)" fillcolor=lightblue]
|
|
140202228982384 -> 140202222872608
|
|
140202222872608 [label=AccumulateGrad]
|
|
140202222845568 -> 140202222845664
|
|
140202222845568 [label=ReshapeAliasBackward0]
|
|
140202222845760 -> 140202222845568
|
|
140202222845760 [label=ExpandBackward0]
|
|
140202222871264 -> 140202222845760
|
|
140202222871264 [label=TransposeBackward0]
|
|
140202222872032 -> 140202222871264
|
|
140202222872032 [label=PermuteBackward0]
|
|
140202222871840 -> 140202222872032
|
|
140202222871840 [label=ViewBackward0]
|
|
140202222870784 -> 140202222871840
|
|
140202222870784 [label=ViewBackward0]
|
|
140210811725280 -> 140202222870784
|
|
140210811725280 [label=AddmmBackward0]
|
|
140210811725808 -> 140210811725280
|
|
140210811725808 [label=ToCopyBackward0]
|
|
140210811726000 -> 140210811725808
|
|
140203184706720 [label="encoder.layer.7.attention.self.key.bias
|
|
(768)" fillcolor=lightblue]
|
|
140203184706720 -> 140210811726000
|
|
140210811726000 [label=AccumulateGrad]
|
|
140210811725760 -> 140210811725280
|
|
140210811725760 [label=ViewBackward0]
|
|
140210811726336 -> 140210811725760
|
|
140210811726336 [label=ToCopyBackward0]
|
|
140202222842352 -> 140210811726336
|
|
140210811724752 -> 140210811725280
|
|
140210811724752 [label=TBackward0]
|
|
140210811725472 -> 140210811724752
|
|
140210811725472 [label=ToCopyBackward0]
|
|
140210811726480 -> 140210811725472
|
|
140202228982624 [label="encoder.layer.7.attention.self.key.weight
|
|
(768, 768)" fillcolor=lightblue]
|
|
140202228982624 -> 140210811726480
|
|
140210811726480 [label=AccumulateGrad]
|
|
140202222844224 -> 140202222843936
|
|
140202222844224 [label=ReshapeAliasBackward0]
|
|
140202222844608 -> 140202222844224
|
|
140202222844608 [label=ExpandBackward0]
|
|
140202222844896 -> 140202222844608
|
|
140202222844896 [label=PermuteBackward0]
|
|
140202222845280 -> 140202222844896
|
|
140202222845280 [label=ViewBackward0]
|
|
140202222844272 -> 140202222845280
|
|
140202222844272 [label=ViewBackward0]
|
|
140202222844320 -> 140202222844272
|
|
140202222844320 [label=AddmmBackward0]
|
|
140202222872752 -> 140202222844320
|
|
140202222872752 [label=ToCopyBackward0]
|
|
140210811726432 -> 140202222872752
|
|
140202228969200 [label="encoder.layer.7.attention.self.value.bias
|
|
(768)" fillcolor=lightblue]
|
|
140202228969200 -> 140210811726432
|
|
140210811726432 [label=AccumulateGrad]
|
|
140202222871552 -> 140202222844320
|
|
140202222871552 [label=ViewBackward0]
|
|
140210811726240 -> 140202222871552
|
|
140210811726240 [label=ToCopyBackward0]
|
|
140202222842352 -> 140210811726240
|
|
140202222870832 -> 140202222844320
|
|
140202222870832 [label=TBackward0]
|
|
140210811725328 -> 140202222870832
|
|
140210811725328 [label=ToCopyBackward0]
|
|
140210811726384 -> 140210811725328
|
|
140202228969280 [label="encoder.layer.7.attention.self.value.weight
|
|
(768, 768)" fillcolor=lightblue]
|
|
140202228969280 -> 140210811726384
|
|
140210811726384 [label=AccumulateGrad]
|
|
140202222842592 -> 140202222842832
|
|
140202222842592 [label=TBackward0]
|
|
140202222843744 -> 140202222842592
|
|
140202222843744 [label=ToCopyBackward0]
|
|
140202222844032 -> 140202222843744
|
|
140202228968960 [label="encoder.layer.7.attention.output.dense.weight
|
|
(768, 768)" fillcolor=lightblue]
|
|
140202228968960 -> 140202222844032
|
|
140202222844032 [label=AccumulateGrad]
|
|
140202222842352 -> 140202222841968
|
|
140202222842112 -> 140202222820224
|
|
140202228967520 [label="encoder.layer.7.attention.output.LayerNorm.weight
|
|
(768)" fillcolor=lightblue]
|
|
140202228967520 -> 140202222842112
|
|
140202222842112 [label=AccumulateGrad]
|
|
140202222842016 -> 140202222820224
|
|
140202228967280 [label="encoder.layer.7.attention.output.LayerNorm.bias
|
|
(768)" fillcolor=lightblue]
|
|
140202228967280 -> 140202222842016
|
|
140202222842016 [label=AccumulateGrad]
|
|
140202222819456 -> 140202222819936
|
|
140202222819456 [label=TBackward0]
|
|
140202222820368 -> 140202222819456
|
|
140202222820368 [label=ToCopyBackward0]
|
|
140202222821088 -> 140202222820368
|
|
140202228965600 [label="encoder.layer.7.experts.dense1.weight
|
|
(3072, 768)" fillcolor=lightblue]
|
|
140202228965600 -> 140202222821088
|
|
140202222821088 [label=AccumulateGrad]
|
|
140202222818880 -> 140202222819168
|
|
140202222818880 [label=TBackward0]
|
|
140202222819888 -> 140202222818880
|
|
140202222819888 [label=ToCopyBackward0]
|
|
140202222820800 -> 140202222819888
|
|
140202228965440 [label="encoder.layer.7.experts.dense2.weight
|
|
(768, 3072)" fillcolor=lightblue]
|
|
140202228965440 -> 140202222820800
|
|
140202222820800 [label=AccumulateGrad]
|
|
140202222818688 -> 140202222818304
|
|
140202222818400 -> 140202222818208
|
|
140202228952736 [label="encoder.layer.7.expert_ln.weight
|
|
(768)" fillcolor=lightblue]
|
|
140202228952736 -> 140202222818400
|
|
140202222818400 [label=AccumulateGrad]
|
|
140202222818112 -> 140202222818208
|
|
140202228952816 [label="encoder.layer.7.expert_ln.bias
|
|
(768)" fillcolor=lightblue]
|
|
140202228952816 -> 140202222818112
|
|
140202222818112 [label=AccumulateGrad]
|
|
140202222817632 -> 140202223288032
|
|
140202222817632 [label=NativeLayerNormBackward0]
|
|
140202222818784 -> 140202222817632
|
|
140202222818784 [label=AddBackward0]
|
|
140202222820320 -> 140202222818784
|
|
140202222820320 [label=NativeDropoutBackward0]
|
|
140202222819840 -> 140202222820320
|
|
140202222819840 [label=ViewBackward0]
|
|
140202222820512 -> 140202222819840
|
|
140202222820512 [label=AddmmBackward0]
|
|
140202222842208 -> 140202222820512
|
|
140202222842208 [label=ToCopyBackward0]
|
|
140202222843264 -> 140202222842208
|
|
140202228966880 [label="encoder.layer.7.output.dense.bias
|
|
(768)" fillcolor=lightblue]
|
|
140202228966880 -> 140202222843264
|
|
140202222843264 [label=AccumulateGrad]
|
|
140202222842304 -> 140202222820512
|
|
140202222842304 [label=ViewBackward0]
|
|
140202222843792 -> 140202222842304
|
|
140202222843792 [label=GeluBackward0]
|
|
140202222843168 -> 140202222843792
|
|
140202222843168 [label=ViewBackward0]
|
|
140202222844800 -> 140202222843168
|
|
140202222844800 [label=AddmmBackward0]
|
|
140202222845376 -> 140202222844800
|
|
140202222845376 [label=ToCopyBackward0]
|
|
140210811726144 -> 140202222845376
|
|
140202228967120 [label="encoder.layer.7.intermediate.dense.bias
|
|
(3072)" fillcolor=lightblue]
|
|
140202228967120 -> 140210811726144
|
|
140210811726144 [label=AccumulateGrad]
|
|
140202222845088 -> 140202222844800
|
|
140202222845088 [label=ViewBackward0]
|
|
140210811726672 -> 140202222845088
|
|
140210811726672 [label=ToCopyBackward0]
|
|
140202222819408 -> 140210811726672
|
|
140202222819408 [label=SliceBackward0]
|
|
140210811726720 -> 140202222819408
|
|
140210811726720 [label=SliceBackward0]
|
|
140210811726816 -> 140210811726720
|
|
140210811726816 [label=SliceBackward0]
|
|
140202222820224 -> 140210811726816
|
|
140202222842976 -> 140202222844800
|
|
140202222842976 [label=TBackward0]
|
|
140210811726528 -> 140202222842976
|
|
140210811726528 [label=ToCopyBackward0]
|
|
140210811726912 -> 140210811726528
|
|
140202228967360 [label="encoder.layer.7.intermediate.dense.weight
|
|
(3072, 768)" fillcolor=lightblue]
|
|
140202228967360 -> 140210811726912
|
|
140210811726912 [label=AccumulateGrad]
|
|
140202222841920 -> 140202222820512
|
|
140202222841920 [label=TBackward0]
|
|
140202222843552 -> 140202222841920
|
|
140202222843552 [label=ToCopyBackward0]
|
|
140202222871072 -> 140202222843552
|
|
140202228966800 [label="encoder.layer.7.output.dense.weight
|
|
(768, 3072)" fillcolor=lightblue]
|
|
140202228966800 -> 140202222871072
|
|
140202222871072 [label=AccumulateGrad]
|
|
140202222819408 -> 140202222818784
|
|
140202222818496 -> 140202222817632
|
|
140202228966560 [label="encoder.layer.7.output.LayerNorm.weight
|
|
(768)" fillcolor=lightblue]
|
|
140202228966560 -> 140202222818496
|
|
140202222818496 [label=AccumulateGrad]
|
|
140202222818448 -> 140202222817632
|
|
140202228966640 [label="encoder.layer.7.output.LayerNorm.bias
|
|
(768)" fillcolor=lightblue]
|
|
140202228966640 -> 140202222818448
|
|
140202222818448 [label=AccumulateGrad]
|
|
140202222817440 -> 140202223316800
|
|
140202222817440 [label=TBackward0]
|
|
140202222817728 -> 140202222817440
|
|
140202222817728 [label=ToCopyBackward0]
|
|
140202222819264 -> 140202222817728
|
|
140202228952496 [label="encoder.layer.8.attention.self.query.weight
|
|
(768, 768)" fillcolor=lightblue]
|
|
140202228952496 -> 140202222819264
|
|
140202222819264 [label=AccumulateGrad]
|
|
140202223316128 -> 140202223315840
|
|
140202223316128 [label=ReshapeAliasBackward0]
|
|
140202223316512 -> 140202223316128
|
|
140202223316512 [label=ExpandBackward0]
|
|
140202223316176 -> 140202223316512
|
|
140202223316176 [label=TransposeBackward0]
|
|
140202223316224 -> 140202223316176
|
|
140202223316224 [label=PermuteBackward0]
|
|
140202222821280 -> 140202223316224
|
|
140202222821280 [label=ViewBackward0]
|
|
140202222817968 -> 140202222821280
|
|
140202222817968 [label=ViewBackward0]
|
|
140202222817536 -> 140202222817968
|
|
140202222817536 [label=AddmmBackward0]
|
|
140202222844416 -> 140202222817536
|
|
140202222844416 [label=ToCopyBackward0]
|
|
140210811726624 -> 140202222844416
|
|
140202228952336 [label="encoder.layer.8.attention.self.key.bias
|
|
(768)" fillcolor=lightblue]
|
|
140202228952336 -> 140210811726624
|
|
140210811726624 [label=AccumulateGrad]
|
|
140202222842496 -> 140202222817536
|
|
140202222842496 [label=ViewBackward0]
|
|
140210811726960 -> 140202222842496
|
|
140210811726960 [label=ToCopyBackward0]
|
|
140202223288032 -> 140210811726960
|
|
140210811724368 -> 140202222817536
|
|
140210811724368 [label=TBackward0]
|
|
140210811726576 -> 140210811724368
|
|
140210811726576 [label=ToCopyBackward0]
|
|
140210811727104 -> 140210811726576
|
|
140202228952256 [label="encoder.layer.8.attention.self.key.weight
|
|
(768, 768)" fillcolor=lightblue]
|
|
140202228952256 -> 140210811727104
|
|
140210811727104 [label=AccumulateGrad]
|
|
140202223314400 -> 140202223314496
|
|
140202223314400 [label=ReshapeAliasBackward0]
|
|
140202223315168 -> 140202223314400
|
|
140202223315168 [label=ExpandBackward0]
|
|
140202223315456 -> 140202223315168
|
|
140202223315456 [label=PermuteBackward0]
|
|
140202223315696 -> 140202223315456
|
|
140202223315696 [label=ViewBackward0]
|
|
140202223314592 -> 140202223315696
|
|
140202223314592 [label=ViewBackward0]
|
|
140202223316704 -> 140202223314592
|
|
140202223316704 [label=AddmmBackward0]
|
|
140202223314736 -> 140202223316704
|
|
140202223314736 [label=ToCopyBackward0]
|
|
140202222842688 -> 140202223314736
|
|
140202228952096 [label="encoder.layer.8.attention.self.value.bias
|
|
(768)" fillcolor=lightblue]
|
|
140202228952096 -> 140202222842688
|
|
140202222842688 [label=AccumulateGrad]
|
|
140202222818976 -> 140202223316704
|
|
140202222818976 [label=ViewBackward0]
|
|
140210811726864 -> 140202222818976
|
|
140210811726864 [label=ToCopyBackward0]
|
|
140202223288032 -> 140210811726864
|
|
140202222818016 -> 140202223316704
|
|
140202222818016 [label=TBackward0]
|
|
140210811726768 -> 140202222818016
|
|
140210811726768 [label=ToCopyBackward0]
|
|
140210811727008 -> 140210811726768
|
|
140202228952016 [label="encoder.layer.8.attention.self.value.weight
|
|
(768, 768)" fillcolor=lightblue]
|
|
140202228952016 -> 140210811727008
|
|
140210811727008 [label=AccumulateGrad]
|
|
140202223313056 -> 140202223313152
|
|
140202223313056 [label=TBackward0]
|
|
140202223313920 -> 140202223313056
|
|
140202223313920 [label=ToCopyBackward0]
|
|
140202223314304 -> 140202223313920
|
|
140202228951776 [label="encoder.layer.8.attention.output.dense.weight
|
|
(768, 768)" fillcolor=lightblue]
|
|
140202228951776 -> 140202223314304
|
|
140202223314304 [label=AccumulateGrad]
|
|
140202223288032 -> 140202223287936
|
|
140202223287744 -> 140202223287696
|
|
140202228951536 [label="encoder.layer.8.attention.output.LayerNorm.weight
|
|
(768)" fillcolor=lightblue]
|
|
140202228951536 -> 140202223287744
|
|
140202223287744 [label=AccumulateGrad]
|
|
140202223286976 -> 140202223287696
|
|
140202228951616 [label="encoder.layer.8.attention.output.LayerNorm.bias
|
|
(768)" fillcolor=lightblue]
|
|
140202228951616 -> 140202223286976
|
|
140202223286976 [label=AccumulateGrad]
|
|
140202223285776 -> 140202223286688
|
|
140202223285776 [label=TBackward0]
|
|
140202223286880 -> 140202223285776
|
|
140202223286880 [label=ToCopyBackward0]
|
|
140202223287552 -> 140202223286880
|
|
140202228951296 [label="encoder.layer.8.crossattention.self.query.weight
|
|
(768, 768)" fillcolor=lightblue]
|
|
140202228951296 -> 140202223287552
|
|
140202223287552 [label=AccumulateGrad]
|
|
140202223285728 -> 140202223285440
|
|
140202223285728 [label=ReshapeAliasBackward0]
|
|
140202223286112 -> 140202223285728
|
|
140202223286112 [label=ExpandBackward0]
|
|
140202223286400 -> 140202223286112
|
|
140202223286400 [label=TransposeBackward0]
|
|
140202223287264 -> 140202223286400
|
|
140202223287264 [label=PermuteBackward0]
|
|
140202223288128 -> 140202223287264
|
|
140202223288128 [label=ViewBackward0]
|
|
140202223287216 -> 140202223288128
|
|
140202223287216 [label=ViewBackward0]
|
|
140202223285824 -> 140202223287216
|
|
140202223285824 [label=AddmmBackward0]
|
|
140202223313440 -> 140202223285824
|
|
140202223313440 [label=ToCopyBackward0]
|
|
140202223313824 -> 140202223313440
|
|
140202228951136 [label="encoder.layer.8.crossattention.self.key.bias
|
|
(768)" fillcolor=lightblue]
|
|
140202228951136 -> 140202223313824
|
|
140202223313824 [label=AccumulateGrad]
|
|
140202223313536 -> 140202223285824
|
|
140202223313536 [label=ViewBackward0]
|
|
140202223315216 -> 140202223313536
|
|
140202223315216 [label=ToCopyBackward0]
|
|
140210812052960 -> 140202223315216
|
|
140202223312960 -> 140202223285824
|
|
140202223312960 [label=TBackward0]
|
|
140202223314976 -> 140202223312960
|
|
140202223314976 [label=ToCopyBackward0]
|
|
140202223316320 -> 140202223314976
|
|
140202228951056 [label="encoder.layer.8.crossattention.self.key.weight
|
|
(768, 1408)" fillcolor=lightblue]
|
|
140202228951056 -> 140202223316320
|
|
140202223316320 [label=AccumulateGrad]
|
|
140202223251168 -> 140202223251264
|
|
140202223251168 [label=ReshapeAliasBackward0]
|
|
140202223284768 -> 140202223251168
|
|
140202223284768 [label=ExpandBackward0]
|
|
140202223285056 -> 140202223284768
|
|
140202223285056 [label=PermuteBackward0]
|
|
140202223285296 -> 140202223285056
|
|
140202223285296 [label=ViewBackward0]
|
|
140202223284288 -> 140202223285296
|
|
140202223284288 [label=ViewBackward0]
|
|
140202223286304 -> 140202223284288
|
|
140202223286304 [label=AddmmBackward0]
|
|
140202223287360 -> 140202223286304
|
|
140202223287360 [label=ToCopyBackward0]
|
|
140202222820848 -> 140202223287360
|
|
140202228950896 [label="encoder.layer.8.crossattention.self.value.bias
|
|
(768)" fillcolor=lightblue]
|
|
140202228950896 -> 140202222820848
|
|
140202222820848 [label=AccumulateGrad]
|
|
140202223286784 -> 140202223286304
|
|
140202223286784 [label=ViewBackward0]
|
|
140202223315936 -> 140202223286784
|
|
140202223315936 [label=ToCopyBackward0]
|
|
140210812052960 -> 140202223315936
|
|
140202223284336 -> 140202223286304
|
|
140202223284336 [label=TBackward0]
|
|
140202223313248 -> 140202223284336
|
|
140202223313248 [label=ToCopyBackward0]
|
|
140202223314112 -> 140202223313248
|
|
140202228950816 [label="encoder.layer.8.crossattention.self.value.weight
|
|
(768, 1408)" fillcolor=lightblue]
|
|
140202228950816 -> 140202223314112
|
|
140202223314112 [label=AccumulateGrad]
|
|
140202223249584 -> 140202223250016
|
|
140202223249584 [label=TBackward0]
|
|
140202223250784 -> 140202223249584
|
|
140202223250784 [label=ToCopyBackward0]
|
|
140202223251072 -> 140202223250784
|
|
140202228950576 [label="encoder.layer.8.crossattention.output.dense.weight
|
|
(768, 768)" fillcolor=lightblue]
|
|
140202228950576 -> 140202223251072
|
|
140202223251072 [label=AccumulateGrad]
|
|
140202223249536 -> 140202223249152
|
|
140202223249104 -> 140202223248960
|
|
140202228950336 [label="encoder.layer.8.crossattention.output.LayerNorm.weight
|
|
(768)" fillcolor=lightblue]
|
|
140202228950336 -> 140202223249104
|
|
140202223249104 [label=AccumulateGrad]
|
|
140202223248288 -> 140202223248960
|
|
140202228950416 [label="encoder.layer.8.crossattention.output.LayerNorm.bias
|
|
(768)" fillcolor=lightblue]
|
|
140202228950416 -> 140202223248288
|
|
140202223248288 [label=AccumulateGrad]
|
|
140202223247520 -> 140202223248000
|
|
140202223247520 [label=TBackward0]
|
|
140202223248576 -> 140202223247520
|
|
140202223248576 [label=ToCopyBackward0]
|
|
140202223249344 -> 140202223248576
|
|
140202228934912 [label="encoder.layer.8.experts.experts.0.dense1.weight
|
|
(3072, 768)" fillcolor=lightblue]
|
|
140202228934912 -> 140202223249344
|
|
140202223249344 [label=AccumulateGrad]
|
|
140202223230256 -> 140202223230736
|
|
140202223230256 [label=TBackward0]
|
|
140202223248096 -> 140202223230256
|
|
140202223248096 [label=ToCopyBackward0]
|
|
140202223248864 -> 140202223248096
|
|
140202228934592 [label="encoder.layer.8.experts.experts.0.dense2.weight
|
|
(768, 3072)" fillcolor=lightblue]
|
|
140202228934592 -> 140202223248864
|
|
140202223248864 [label=AccumulateGrad]
|
|
140202223229920 -> 140202223230016
|
|
140202223229920 [label=UnsqueezeBackward0]
|
|
140202223230592 -> 140202223229920
|
|
140202223230592 [label=NativeDropoutBackward0]
|
|
140202223230304 -> 140202223230592
|
|
140202223230304 [label=ViewBackward0]
|
|
140202223249632 -> 140202223230304
|
|
140202223249632 [label=AddmmBackward0]
|
|
140202223247904 -> 140202223249632
|
|
140202223247904 [label=ToCopyBackward0]
|
|
140202223250112 -> 140202223247904
|
|
140202228934672 [label="encoder.layer.8.experts.experts.1.dense2.bias
|
|
(768)" fillcolor=lightblue]
|
|
140202228934672 -> 140202223250112
|
|
140202223250112 [label=AccumulateGrad]
|
|
140202223249056 -> 140202223249632
|
|
140202223249056 [label=ViewBackward0]
|
|
140202223250304 -> 140202223249056
|
|
140202223250304 [label=GeluBackward0]
|
|
140202223251024 -> 140202223250304
|
|
140202223251024 [label=ViewBackward0]
|
|
140202223250544 -> 140202223251024
|
|
140202223250544 [label=AddmmBackward0]
|
|
140202223285248 -> 140202223250544
|
|
140202223285248 [label=ToCopyBackward0]
|
|
140202223287840 -> 140202223285248
|
|
140202228935072 [label="encoder.layer.8.experts.experts.1.dense1.bias
|
|
(3072)" fillcolor=lightblue]
|
|
140202228935072 -> 140202223287840
|
|
140202223287840 [label=AccumulateGrad]
|
|
140202223284816 -> 140202223250544
|
|
140202223284816 [label=ViewBackward0]
|
|
140202223315648 -> 140202223284816
|
|
140202223315648 [label=ToCopyBackward0]
|
|
140202223229152 -> 140202223315648
|
|
140202223284576 -> 140202223250544
|
|
140202223284576 [label=TBackward0]
|
|
140202223285920 -> 140202223284576
|
|
140202223285920 [label=ToCopyBackward0]
|
|
140210811727152 -> 140202223285920
|
|
140202228934352 [label="encoder.layer.8.experts.experts.1.dense1.weight
|
|
(3072, 768)" fillcolor=lightblue]
|
|
140202228934352 -> 140210811727152
|
|
140210811727152 [label=AccumulateGrad]
|
|
140202223247424 -> 140202223249632
|
|
140202223247424 [label=TBackward0]
|
|
140202223249728 -> 140202223247424
|
|
140202223249728 [label=ToCopyBackward0]
|
|
140202223313728 -> 140202223249728
|
|
140202228934112 [label="encoder.layer.8.experts.experts.1.dense2.weight
|
|
(768, 3072)" fillcolor=lightblue]
|
|
140202228934112 -> 140202223313728
|
|
140202223313728 [label=AccumulateGrad]
|
|
140202223229776 -> 140202223230016
|
|
140202223229776 [label=UnsqueezeBackward0]
|
|
140202223285536 -> 140202223229776
|
|
140202223285536 [label=NativeDropoutBackward0]
|
|
140202223249248 -> 140202223285536
|
|
140202223249248 [label=ViewBackward0]
|
|
140202223250208 -> 140202223249248
|
|
140202223250208 [label=AddmmBackward0]
|
|
140202223247616 -> 140202223250208
|
|
140202223247616 [label=ToCopyBackward0]
|
|
140210811727392 -> 140202223247616
|
|
140202228934192 [label="encoder.layer.8.experts.experts.2.dense2.bias
|
|
(768)" fillcolor=lightblue]
|
|
140202228934192 -> 140210811727392
|
|
140210811727392 [label=AccumulateGrad]
|
|
140210811727296 -> 140202223250208
|
|
140210811727296 [label=ViewBackward0]
|
|
140210811727440 -> 140210811727296
|
|
140210811727440 [label=GeluBackward0]
|
|
140210811727536 -> 140210811727440
|
|
140210811727536 [label=ViewBackward0]
|
|
140210811727632 -> 140210811727536
|
|
140210811727632 [label=AddmmBackward0]
|
|
140210811727728 -> 140210811727632
|
|
140210811727728 [label=ToCopyBackward0]
|
|
140210811727824 -> 140210811727728
|
|
140202228934432 [label="encoder.layer.8.experts.experts.2.dense1.bias
|
|
(3072)" fillcolor=lightblue]
|
|
140202228934432 -> 140210811727824
|
|
140210811727824 [label=AccumulateGrad]
|
|
140210811727680 -> 140210811727632
|
|
140210811727680 [label=ViewBackward0]
|
|
140210811781280 -> 140210811727680
|
|
140210811781280 [label=ToCopyBackward0]
|
|
140202223229152 -> 140210811781280
|
|
140210811727344 -> 140210811727632
|
|
140210811727344 [label=TBackward0]
|
|
140210811781232 -> 140210811727344
|
|
140210811781232 [label=ToCopyBackward0]
|
|
140210811781424 -> 140210811781232
|
|
140202228933872 [label="encoder.layer.8.experts.experts.2.dense1.weight
|
|
(3072, 768)" fillcolor=lightblue]
|
|
140202228933872 -> 140210811781424
|
|
140210811781424 [label=AccumulateGrad]
|
|
140210811727200 -> 140202223250208
|
|
140210811727200 [label=TBackward0]
|
|
140210811727584 -> 140210811727200
|
|
140210811727584 [label=ToCopyBackward0]
|
|
140210811727776 -> 140210811727584
|
|
140202228933632 [label="encoder.layer.8.experts.experts.2.dense2.weight
|
|
(768, 3072)" fillcolor=lightblue]
|
|
140202228933632 -> 140210811727776
|
|
140210811727776 [label=AccumulateGrad]
|
|
140202223229728 -> 140202223229440
|
|
140202223229728 [label=UnsqueezeBackward0]
|
|
140202223230400 -> 140202223229728
|
|
140202223230400 [label=UnsqueezeBackward0]
|
|
140202223248672 -> 140202223230400
|
|
140202223248672 [label=SumBackward1]
|
|
140202223229824 -> 140202223248672
|
|
140202223229824 [label=MulBackward0]
|
|
140210811727488 -> 140202223229824
|
|
140210811727488 [label=UnsqueezeBackward0]
|
|
140210811781376 -> 140210811727488
|
|
140210811781376 [label=TopkBackward0]
|
|
140210811781328 -> 140210811781376
|
|
140210811781328 [label=SoftmaxBackward0]
|
|
140210811781616 -> 140210811781328
|
|
140210811781616 [label=MmBackward0]
|
|
140210811781712 -> 140210811781616
|
|
140210811781712 [label=ToCopyBackward0]
|
|
140210811781856 -> 140210811781712
|
|
140210811781856 [label=MeanBackward1]
|
|
140210811781952 -> 140210811781856
|
|
140210811781952 [label=MulBackward0]
|
|
140202223229152 -> 140210811781952
|
|
140210811781664 -> 140210811781616
|
|
140210811781664 [label=TBackward0]
|
|
140210811782048 -> 140210811781664
|
|
140210811782048 [label=ToCopyBackward0]
|
|
140210811781760 -> 140210811782048
|
|
140202228935872 [label="encoder.layer.8.experts.gate.weight
|
|
(3, 768)" fillcolor=lightblue]
|
|
140202228935872 -> 140210811781760
|
|
140210811781760 [label=AccumulateGrad]
|
|
140202223229152 -> 140202223229056
|
|
140202223228864 -> 140202223228672
|
|
140202228935792 [label="encoder.layer.8.expert_ln.weight
|
|
(768)" fillcolor=lightblue]
|
|
140202228935792 -> 140202223228864
|
|
140202223228864 [label=AccumulateGrad]
|
|
140202223228816 -> 140202223228672
|
|
140202228935552 [label="encoder.layer.8.expert_ln.bias
|
|
(768)" fillcolor=lightblue]
|
|
140202228935552 -> 140202223228816
|
|
140202223228816 [label=AccumulateGrad]
|
|
140202223228336 -> 140202223195040
|
|
140202223228336 [label=NativeLayerNormBackward0]
|
|
140202223229536 -> 140202223228336
|
|
140202223229536 [label=AddBackward0]
|
|
140202223248384 -> 140202223229536
|
|
140202223248384 [label=NativeDropoutBackward0]
|
|
140210811727248 -> 140202223248384
|
|
140210811727248 [label=ViewBackward0]
|
|
140210811781520 -> 140210811727248
|
|
140210811781520 [label=AddmmBackward0]
|
|
140210811782000 -> 140210811781520
|
|
140210811782000 [label=ToCopyBackward0]
|
|
140210811782192 -> 140210811782000
|
|
140202228949936 [label="encoder.layer.8.output.dense.bias
|
|
(768)" fillcolor=lightblue]
|
|
140202228949936 -> 140210811782192
|
|
140210811782192 [label=AccumulateGrad]
|
|
140210811781904 -> 140210811781520
|
|
140210811781904 [label=ViewBackward0]
|
|
140210811782240 -> 140210811781904
|
|
140210811782240 [label=GeluBackward0]
|
|
140210811782336 -> 140210811782240
|
|
140210811782336 [label=ViewBackward0]
|
|
140210811782432 -> 140210811782336
|
|
140210811782432 [label=AddmmBackward0]
|
|
140210811782528 -> 140210811782432
|
|
140210811782528 [label=ToCopyBackward0]
|
|
140210811782720 -> 140210811782528
|
|
140202228950176 [label="encoder.layer.8.intermediate.dense.bias
|
|
(3072)" fillcolor=lightblue]
|
|
140202228950176 -> 140210811782720
|
|
140210811782720 [label=AccumulateGrad]
|
|
140210811782480 -> 140210811782432
|
|
140210811782480 [label=ViewBackward0]
|
|
140210811782768 -> 140210811782480
|
|
140210811782768 [label=ToCopyBackward0]
|
|
140202223230112 -> 140210811782768
|
|
140202223230112 [label=SliceBackward0]
|
|
140210811782912 -> 140202223230112
|
|
140210811782912 [label=SliceBackward0]
|
|
140210811783008 -> 140210811782912
|
|
140210811783008 [label=SliceBackward0]
|
|
140202223287696 -> 140210811783008
|
|
140210811781808 -> 140210811782432
|
|
140210811781808 [label=TBackward0]
|
|
140210811782672 -> 140210811781808
|
|
140210811782672 [label=ToCopyBackward0]
|
|
140210811783104 -> 140210811782672
|
|
140202228950096 [label="encoder.layer.8.intermediate.dense.weight
|
|
(3072, 768)" fillcolor=lightblue]
|
|
140202228950096 -> 140210811783104
|
|
140210811783104 [label=AccumulateGrad]
|
|
140210811781184 -> 140210811781520
|
|
140210811781184 [label=TBackward0]
|
|
140210811782384 -> 140210811781184
|
|
140210811782384 [label=ToCopyBackward0]
|
|
140210811782864 -> 140210811782384
|
|
140202228949856 [label="encoder.layer.8.output.dense.weight
|
|
(768, 3072)" fillcolor=lightblue]
|
|
140202228949856 -> 140210811782864
|
|
140210811782864 [label=AccumulateGrad]
|
|
140202223230112 -> 140202223229536
|
|
140202223229248 -> 140202223228336
|
|
140202228949616 [label="encoder.layer.8.output.LayerNorm.weight
|
|
(768)" fillcolor=lightblue]
|
|
140202228949616 -> 140202223229248
|
|
140202223229248 [label=AccumulateGrad]
|
|
140202223228960 -> 140202223228336
|
|
140202228949696 [label="encoder.layer.8.output.LayerNorm.bias
|
|
(768)" fillcolor=lightblue]
|
|
140202228949696 -> 140202223228960
|
|
140202223228960 [label=AccumulateGrad]
|
|
140202223226992 -> 140202223227904
|
|
140202223226992 [label=TBackward0]
|
|
140202223228192 -> 140202223226992
|
|
140202223228192 [label=ToCopyBackward0]
|
|
140210811727056 -> 140202223228192
|
|
140202228936112 [label="encoder.layer.9.attention.self.query.weight
|
|
(768, 768)" fillcolor=lightblue]
|
|
140202228936112 -> 140210811727056
|
|
140210811727056 [label=AccumulateGrad]
|
|
140202223226944 -> 140202223198016
|
|
140202223226944 [label=ReshapeAliasBackward0]
|
|
140202223227616 -> 140202223226944
|
|
140202223227616 [label=ExpandBackward0]
|
|
140202223227856 -> 140202223227616
|
|
140202223227856 [label=TransposeBackward0]
|
|
140202223228768 -> 140202223227856
|
|
140202223228768 [label=PermuteBackward0]
|
|
140202223228480 -> 140202223228768
|
|
140202223228480 [label=ViewBackward0]
|
|
140202223227328 -> 140202223228480
|
|
140202223227328 [label=ViewBackward0]
|
|
140210811782096 -> 140202223227328
|
|
140210811782096 [label=AddmmBackward0]
|
|
140210811782624 -> 140210811782096
|
|
140210811782624 [label=ToCopyBackward0]
|
|
140210811782816 -> 140210811782624
|
|
140202228936272 [label="encoder.layer.9.attention.self.key.bias
|
|
(768)" fillcolor=lightblue]
|
|
140202228936272 -> 140210811782816
|
|
140210811782816 [label=AccumulateGrad]
|
|
140210811782576 -> 140210811782096
|
|
140210811782576 [label=ViewBackward0]
|
|
140210811783152 -> 140210811782576
|
|
140210811783152 [label=ToCopyBackward0]
|
|
140202223195040 -> 140210811783152
|
|
140210811781568 -> 140210811782096
|
|
140210811781568 [label=TBackward0]
|
|
140210811782288 -> 140210811781568
|
|
140210811782288 [label=ToCopyBackward0]
|
|
140210811783296 -> 140210811782288
|
|
140202228936352 [label="encoder.layer.9.attention.self.key.weight
|
|
(768, 768)" fillcolor=lightblue]
|
|
140202228936352 -> 140210811783296
|
|
140210811783296 [label=AccumulateGrad]
|
|
140202223196720 -> 140202223196576
|
|
140202223196720 [label=ReshapeAliasBackward0]
|
|
140202223197248 -> 140202223196720
|
|
140202223197248 [label=ExpandBackward0]
|
|
140202223197536 -> 140202223197248
|
|
140202223197536 [label=PermuteBackward0]
|
|
140202223197824 -> 140202223197536
|
|
140202223197824 [label=ViewBackward0]
|
|
140202223196960 -> 140202223197824
|
|
140202223196960 [label=ViewBackward0]
|
|
140202223227808 -> 140202223196960
|
|
140202223227808 [label=AddmmBackward0]
|
|
140202223229344 -> 140202223227808
|
|
140202223229344 [label=ToCopyBackward0]
|
|
140210811783248 -> 140202223229344
|
|
140202228935312 [label="encoder.layer.9.attention.self.value.bias
|
|
(768)" fillcolor=lightblue]
|
|
140202228935312 -> 140210811783248
|
|
140210811783248 [label=AccumulateGrad]
|
|
140202223228288 -> 140202223227808
|
|
140202223228288 [label=ViewBackward0]
|
|
140210811783056 -> 140202223228288
|
|
140210811783056 [label=ToCopyBackward0]
|
|
140202223195040 -> 140210811783056
|
|
140202223227040 -> 140202223227808
|
|
140202223227040 [label=TBackward0]
|
|
140210811782144 -> 140202223227040
|
|
140210811782144 [label=ToCopyBackward0]
|
|
140210811783200 -> 140210811782144
|
|
140202228935632 [label="encoder.layer.9.attention.self.value.weight
|
|
(768, 768)" fillcolor=lightblue]
|
|
140202228935632 -> 140210811783200
|
|
140210811783200 [label=AccumulateGrad]
|
|
140202223195232 -> 140202223195520
|
|
140202223195232 [label=TBackward0]
|
|
140202223196240 -> 140202223195232
|
|
140202223196240 [label=ToCopyBackward0]
|
|
140202223196672 -> 140202223196240
|
|
140202228935392 [label="encoder.layer.9.attention.output.dense.weight
|
|
(768, 768)" fillcolor=lightblue]
|
|
140202228935392 -> 140202223196672
|
|
140202223196672 [label=AccumulateGrad]
|
|
140202223195040 -> 140202223194656
|
|
140202223194752 -> 140202223194464
|
|
140202228933952 [label="encoder.layer.9.attention.output.LayerNorm.weight
|
|
(768)" fillcolor=lightblue]
|
|
140202228933952 -> 140202223194752
|
|
140202223194752 [label=AccumulateGrad]
|
|
140202223194272 -> 140202223194464
|
|
140202228933712 [label="encoder.layer.9.attention.output.LayerNorm.bias
|
|
(768)" fillcolor=lightblue]
|
|
140202228933712 -> 140202223194272
|
|
140202223194272 [label=AccumulateGrad]
|
|
140202223172000 -> 140202223172480
|
|
140202223172000 [label=TBackward0]
|
|
140202223173056 -> 140202223172000
|
|
140202223173056 [label=ToCopyBackward0]
|
|
140202223173536 -> 140202223173056
|
|
140202228927840 [label="encoder.layer.9.experts.dense1.weight
|
|
(3072, 768)" fillcolor=lightblue]
|
|
140202228927840 -> 140202223173536
|
|
140202223173536 [label=AccumulateGrad]
|
|
140202223171376 -> 140202223171808
|
|
140202223171376 [label=TBackward0]
|
|
140202223172576 -> 140202223171376
|
|
140202223172576 [label=ToCopyBackward0]
|
|
140202223173296 -> 140202223172576
|
|
140202228927600 [label="encoder.layer.9.experts.dense2.weight
|
|
(768, 3072)" fillcolor=lightblue]
|
|
140202228927600 -> 140202223173296
|
|
140202223173296 [label=AccumulateGrad]
|
|
140202223171328 -> 140202223170944
|
|
140202223170896 -> 140202223170848
|
|
140202228927360 [label="encoder.layer.9.expert_ln.weight
|
|
(768)" fillcolor=lightblue]
|
|
140202228927360 -> 140202223170896
|
|
140202223170896 [label=AccumulateGrad]
|
|
140202223170752 -> 140202223170848
|
|
140202228927040 [label="encoder.layer.9.expert_ln.bias
|
|
(768)" fillcolor=lightblue]
|
|
140202228927040 -> 140202223170752
|
|
140202223170752 [label=AccumulateGrad]
|
|
140202223170272 -> 140202223136928
|
|
140202223170272 [label=NativeLayerNormBackward0]
|
|
140202223171424 -> 140202223170272
|
|
140202223171424 [label=AddBackward0]
|
|
140202223172816 -> 140202223171424
|
|
140202223172816 [label=NativeDropoutBackward0]
|
|
140202223172336 -> 140202223172816
|
|
140202223172336 [label=ViewBackward0]
|
|
140202223194176 -> 140202223172336
|
|
140202223194176 [label=AddmmBackward0]
|
|
140202223194848 -> 140202223194176
|
|
140202223194848 [label=ToCopyBackward0]
|
|
140202223195760 -> 140202223194848
|
|
140202228932912 [label="encoder.layer.9.output.dense.bias
|
|
(768)" fillcolor=lightblue]
|
|
140202228932912 -> 140202223195760
|
|
140202223195760 [label=AccumulateGrad]
|
|
140202223194800 -> 140202223194176
|
|
140202223194800 [label=ViewBackward0]
|
|
140202223196480 -> 140202223194800
|
|
140202223196480 [label=GeluBackward0]
|
|
140202223195808 -> 140202223196480
|
|
140202223195808 [label=ViewBackward0]
|
|
140202223197344 -> 140202223195808
|
|
140202223197344 [label=AddmmBackward0]
|
|
140202223196864 -> 140202223197344
|
|
140202223196864 [label=ToCopyBackward0]
|
|
140210811782960 -> 140202223196864
|
|
140202228933152 [label="encoder.layer.9.intermediate.dense.bias
|
|
(3072)" fillcolor=lightblue]
|
|
140202228933152 -> 140210811782960
|
|
140210811782960 [label=AccumulateGrad]
|
|
140202223197728 -> 140202223197344
|
|
140202223197728 [label=ViewBackward0]
|
|
140210811783488 -> 140202223197728
|
|
140210811783488 [label=ToCopyBackward0]
|
|
140202223172096 -> 140210811783488
|
|
140202223172096 [label=SliceBackward0]
|
|
140210811783536 -> 140202223172096
|
|
140210811783536 [label=SliceBackward0]
|
|
140210811783632 -> 140210811783536
|
|
140210811783632 [label=SliceBackward0]
|
|
140202223194464 -> 140210811783632
|
|
140202223195616 -> 140202223197344
|
|
140202223195616 [label=TBackward0]
|
|
140210811783344 -> 140202223195616
|
|
140210811783344 [label=ToCopyBackward0]
|
|
140210811783728 -> 140210811783344
|
|
140202228933392 [label="encoder.layer.9.intermediate.dense.weight
|
|
(3072, 768)" fillcolor=lightblue]
|
|
140202228933392 -> 140210811783728
|
|
140210811783728 [label=AccumulateGrad]
|
|
140202223194560 -> 140202223194176
|
|
140202223194560 [label=TBackward0]
|
|
140202223196192 -> 140202223194560
|
|
140202223196192 [label=ToCopyBackward0]
|
|
140202223227376 -> 140202223196192
|
|
140202228933232 [label="encoder.layer.9.output.dense.weight
|
|
(768, 3072)" fillcolor=lightblue]
|
|
140202228933232 -> 140202223227376
|
|
140202223227376 [label=AccumulateGrad]
|
|
140202223172096 -> 140202223171424
|
|
140202223171040 -> 140202223170272
|
|
140202228932992 [label="encoder.layer.9.output.LayerNorm.weight
|
|
(768)" fillcolor=lightblue]
|
|
140202228932992 -> 140202223171040
|
|
140202223171040 [label=AccumulateGrad]
|
|
140202223171136 -> 140202223170272
|
|
140202228932672 [label="encoder.layer.9.output.LayerNorm.bias
|
|
(768)" fillcolor=lightblue]
|
|
140202228932672 -> 140202223171136
|
|
140202223171136 [label=AccumulateGrad]
|
|
140202223169696 -> 140202223169936
|
|
140202223169696 [label=TBackward0]
|
|
140202223170368 -> 140202223169696
|
|
140202223170368 [label=ToCopyBackward0]
|
|
140202223171904 -> 140202223170368
|
|
140202228927120 [label="encoder.layer.10.attention.self.query.weight
|
|
(768, 768)" fillcolor=lightblue]
|
|
140202228927120 -> 140202223171904
|
|
140202223171904 [label=AccumulateGrad]
|
|
140202223140240 -> 140202223140096
|
|
140202223140240 [label=ReshapeAliasBackward0]
|
|
140202223140480 -> 140202223140240
|
|
140202223140480 [label=ExpandBackward0]
|
|
140202223140384 -> 140202223140480
|
|
140202223140384 [label=TransposeBackward0]
|
|
140202223170560 -> 140202223140384
|
|
140202223170560 [label=PermuteBackward0]
|
|
140202223173152 -> 140202223170560
|
|
140202223173152 [label=ViewBackward0]
|
|
140202223170656 -> 140202223173152
|
|
140202223170656 [label=ViewBackward0]
|
|
140202223195328 -> 140202223170656
|
|
140202223195328 [label=AddmmBackward0]
|
|
140202223197056 -> 140202223195328
|
|
140202223197056 [label=ToCopyBackward0]
|
|
140210811783440 -> 140202223197056
|
|
140202228926560 [label="encoder.layer.10.attention.self.key.bias
|
|
(768)" fillcolor=lightblue]
|
|
140202228926560 -> 140210811783440
|
|
140210811783440 [label=AccumulateGrad]
|
|
140202223194320 -> 140202223195328
|
|
140202223194320 [label=ViewBackward0]
|
|
140210811783776 -> 140202223194320
|
|
140210811783776 [label=ToCopyBackward0]
|
|
140202223136928 -> 140210811783776
|
|
140210811781472 -> 140202223195328
|
|
140210811781472 [label=TBackward0]
|
|
140210811783392 -> 140210811781472
|
|
140210811783392 [label=ToCopyBackward0]
|
|
140210811783920 -> 140210811783392
|
|
140202228926880 [label="encoder.layer.10.attention.self.key.weight
|
|
(768, 768)" fillcolor=lightblue]
|
|
140202228926880 -> 140210811783920
|
|
140210811783920 [label=AccumulateGrad]
|
|
140202223138656 -> 140202223138752
|
|
140202223138656 [label=ReshapeAliasBackward0]
|
|
140202223139280 -> 140202223138656
|
|
140202223139280 [label=ExpandBackward0]
|
|
140202223139712 -> 140202223139280
|
|
140202223139712 [label=PermuteBackward0]
|
|
140202223140000 -> 140202223139712
|
|
140202223140000 [label=ViewBackward0]
|
|
140202223138848 -> 140202223140000
|
|
140202223138848 [label=ViewBackward0]
|
|
140202223140576 -> 140202223138848
|
|
140202223140576 [label=AddmmBackward0]
|
|
140202223171520 -> 140202223140576
|
|
140202223171520 [label=ToCopyBackward0]
|
|
140202223195136 -> 140202223171520
|
|
140202228926320 [label="encoder.layer.10.attention.self.value.bias
|
|
(768)" fillcolor=lightblue]
|
|
140202228926320 -> 140202223195136
|
|
140202223195136 [label=AccumulateGrad]
|
|
140202223170080 -> 140202223140576
|
|
140202223170080 [label=ViewBackward0]
|
|
140210811783680 -> 140202223170080
|
|
140210811783680 [label=ToCopyBackward0]
|
|
140202223136928 -> 140210811783680
|
|
140202223169792 -> 140202223140576
|
|
140202223169792 [label=TBackward0]
|
|
140210811783584 -> 140202223169792
|
|
140210811783584 [label=ToCopyBackward0]
|
|
140210811783824 -> 140210811783584
|
|
140202228926640 [label="encoder.layer.10.attention.self.value.weight
|
|
(768, 768)" fillcolor=lightblue]
|
|
140202228926640 -> 140210811783824
|
|
140210811783824 [label=AccumulateGrad]
|
|
140202223137024 -> 140202223137408
|
|
140202223137024 [label=TBackward0]
|
|
140202223138176 -> 140202223137024
|
|
140202223138176 [label=ToCopyBackward0]
|
|
140202223138464 -> 140202223138176
|
|
140202228926400 [label="encoder.layer.10.attention.output.dense.weight
|
|
(768, 768)" fillcolor=lightblue]
|
|
140202228926400 -> 140202223138464
|
|
140202223138464 [label=AccumulateGrad]
|
|
140202223136928 -> 140202223112096
|
|
140202223111904 -> 140202223112000
|
|
140202228926160 [label="encoder.layer.10.attention.output.LayerNorm.weight
|
|
(768)" fillcolor=lightblue]
|
|
140202228926160 -> 140202223111904
|
|
140202223111904 [label=AccumulateGrad]
|
|
140202223111232 -> 140202223112000
|
|
140202228925840 [label="encoder.layer.10.attention.output.LayerNorm.bias
|
|
(768)" fillcolor=lightblue]
|
|
140202228925840 -> 140202223111232
|
|
140202223111232 [label=AccumulateGrad]
|
|
140202223110080 -> 140202223110800
|
|
140202223110080 [label=TBackward0]
|
|
140202223111136 -> 140202223110080
|
|
140202223111136 [label=ToCopyBackward0]
|
|
140202223111808 -> 140202223111136
|
|
140202228925920 [label="encoder.layer.10.crossattention.self.query.weight
|
|
(768, 768)" fillcolor=lightblue]
|
|
140202228925920 -> 140202223111808
|
|
140202223111808 [label=AccumulateGrad]
|
|
140202223109840 -> 140202223109696
|
|
140202223109840 [label=ReshapeAliasBackward0]
|
|
140202223110368 -> 140202223109840
|
|
140202223110368 [label=ExpandBackward0]
|
|
140202223110656 -> 140202223110368
|
|
140202223110656 [label=TransposeBackward0]
|
|
140202223111424 -> 140202223110656
|
|
140202223111424 [label=PermuteBackward0]
|
|
140202223111520 -> 140202223111424
|
|
140202223111520 [label=ViewBackward0]
|
|
140202223109984 -> 140202223111520
|
|
140202223109984 [label=ViewBackward0]
|
|
140202223137360 -> 140202223109984
|
|
140202223137360 [label=AddmmBackward0]
|
|
140202223137696 -> 140202223137360
|
|
140202223137696 [label=ToCopyBackward0]
|
|
140202223137984 -> 140202223137696
|
|
140202228925360 [label="encoder.layer.10.crossattention.self.key.bias
|
|
(768)" fillcolor=lightblue]
|
|
140202228925360 -> 140202223137984
|
|
140202223137984 [label=AccumulateGrad]
|
|
140202223137792 -> 140202223137360
|
|
140202223137792 [label=ViewBackward0]
|
|
140202223139520 -> 140202223137792
|
|
140202223139520 [label=ToCopyBackward0]
|
|
140210812052960 -> 140202223139520
|
|
140202223136880 -> 140202223137360
|
|
140202223136880 [label=TBackward0]
|
|
140202223139232 -> 140202223136880
|
|
140202223139232 [label=ToCopyBackward0]
|
|
140202223139040 -> 140202223139232
|
|
140202228925680 [label="encoder.layer.10.crossattention.self.key.weight
|
|
(768, 1408)" fillcolor=lightblue]
|
|
140202228925680 -> 140202223139040
|
|
140202223139040 [label=AccumulateGrad]
|
|
140202223108256 -> 140202223082800
|
|
140202223108256 [label=ReshapeAliasBackward0]
|
|
140202223108880 -> 140202223108256
|
|
140202223108880 [label=ExpandBackward0]
|
|
140202223109312 -> 140202223108880
|
|
140202223109312 [label=PermuteBackward0]
|
|
140202223109600 -> 140202223109312
|
|
140202223109600 [label=ViewBackward0]
|
|
140202223108448 -> 140202223109600
|
|
140202223108448 [label=ViewBackward0]
|
|
140202223110464 -> 140202223108448
|
|
140202223110464 [label=AddmmBackward0]
|
|
140202223111616 -> 140202223110464
|
|
140202223111616 [label=ToCopyBackward0]
|
|
140202223138368 -> 140202223111616
|
|
140202228925120 [label="encoder.layer.10.crossattention.self.value.bias
|
|
(768)" fillcolor=lightblue]
|
|
140202228925120 -> 140202223138368
|
|
140202223138368 [label=AccumulateGrad]
|
|
140202223110944 -> 140202223110464
|
|
140202223110944 [label=ViewBackward0]
|
|
140202223140192 -> 140202223110944
|
|
140202223140192 [label=ToCopyBackward0]
|
|
140210812052960 -> 140202223140192
|
|
140202223108640 -> 140202223110464
|
|
140202223108640 [label=TBackward0]
|
|
140202223136832 -> 140202223108640
|
|
140202223136832 [label=ToCopyBackward0]
|
|
140202223137312 -> 140202223136832
|
|
140202228925440 [label="encoder.layer.10.crossattention.self.value.weight
|
|
(768, 1408)" fillcolor=lightblue]
|
|
140202228925440 -> 140202223137312
|
|
140202223137312 [label=AccumulateGrad]
|
|
140202223081984 -> 140202223082368
|
|
140202223081984 [label=TBackward0]
|
|
140202223083136 -> 140202223081984
|
|
140202223083136 [label=ToCopyBackward0]
|
|
140202223083328 -> 140202223083136
|
|
140202228925200 [label="encoder.layer.10.crossattention.output.dense.weight
|
|
(768, 768)" fillcolor=lightblue]
|
|
140202228925200 -> 140202223083328
|
|
140202223083328 [label=AccumulateGrad]
|
|
140202223081888 -> 140202223081792
|
|
140202223081504 -> 140202223081600
|
|
140202228924960 [label="encoder.layer.10.crossattention.output.LayerNorm.weight
|
|
(768)" fillcolor=lightblue]
|
|
140202228924960 -> 140202223081504
|
|
140202223081504 [label=AccumulateGrad]
|
|
140202223080880 -> 140202223081600
|
|
140202228924640 [label="encoder.layer.10.crossattention.output.LayerNorm.bias
|
|
(768)" fillcolor=lightblue]
|
|
140202228924640 -> 140202223080880
|
|
140202223080880 [label=AccumulateGrad]
|
|
140202223080160 -> 140202223080640
|
|
140202223080160 [label=TBackward0]
|
|
140202223080928 -> 140202223080160
|
|
140202223080928 [label=ToCopyBackward0]
|
|
140202223081696 -> 140202223080928
|
|
140202228905040 [label="encoder.layer.10.experts.experts.0.dense1.weight
|
|
(3072, 768)" fillcolor=lightblue]
|
|
140202228905040 -> 140202223081696
|
|
140202223081696 [label=AccumulateGrad]
|
|
140202223079584 -> 140202223079536
|
|
140202223079584 [label=TBackward0]
|
|
140202223080448 -> 140202223079584
|
|
140202223080448 [label=ToCopyBackward0]
|
|
140202223081216 -> 140202223080448
|
|
140202228905120 [label="encoder.layer.10.experts.experts.0.dense2.weight
|
|
(768, 3072)" fillcolor=lightblue]
|
|
140202228905120 -> 140202223081216
|
|
140202223081216 [label=AccumulateGrad]
|
|
140202223578608 -> 140202223578464
|
|
140202223578608 [label=UnsqueezeBackward0]
|
|
140202223579040 -> 140202223578608
|
|
140202223579040 [label=NativeDropoutBackward0]
|
|
140202223079968 -> 140202223579040
|
|
140202223079968 [label=ViewBackward0]
|
|
140202223082272 -> 140202223079968
|
|
140202223082272 [label=AddmmBackward0]
|
|
140202223080256 -> 140202223082272
|
|
140202223080256 [label=ToCopyBackward0]
|
|
140202223082752 -> 140202223080256
|
|
140202228904800 [label="encoder.layer.10.experts.experts.1.dense2.bias
|
|
(768)" fillcolor=lightblue]
|
|
140202228904800 -> 140202223082752
|
|
140202223082752 [label=AccumulateGrad]
|
|
140202223081408 -> 140202223082272
|
|
140202223081408 [label=ViewBackward0]
|
|
140202223082656 -> 140202223081408
|
|
140202223082656 [label=GeluBackward0]
|
|
140202223081312 -> 140202223082656
|
|
140202223081312 [label=ViewBackward0]
|
|
140202223108352 -> 140202223081312
|
|
140202223108352 [label=AddmmBackward0]
|
|
140202223109360 -> 140202223108352
|
|
140202223109360 [label=ToCopyBackward0]
|
|
140202223169600 -> 140202223109360
|
|
140202228905600 [label="encoder.layer.10.experts.experts.1.dense1.bias
|
|
(3072)" fillcolor=lightblue]
|
|
140202228905600 -> 140202223169600
|
|
140202223169600 [label=AccumulateGrad]
|
|
140202223109120 -> 140202223108352
|
|
140202223109120 [label=ViewBackward0]
|
|
140202223139760 -> 140202223109120
|
|
140202223139760 [label=ToCopyBackward0]
|
|
140202223577888 -> 140202223139760
|
|
140202223108832 -> 140202223108352
|
|
140202223108832 [label=TBackward0]
|
|
140202223110176 -> 140202223108832
|
|
140202223110176 [label=ToCopyBackward0]
|
|
140210811783968 -> 140202223110176
|
|
140202228904880 [label="encoder.layer.10.experts.experts.1.dense1.weight
|
|
(3072, 768)" fillcolor=lightblue]
|
|
140202228904880 -> 140210811783968
|
|
140210811783968 [label=AccumulateGrad]
|
|
140202223079488 -> 140202223082272
|
|
140202223079488 [label=TBackward0]
|
|
140202223082320 -> 140202223079488
|
|
140202223082320 [label=ToCopyBackward0]
|
|
140202223137840 -> 140202223082320
|
|
140202228904640 [label="encoder.layer.10.experts.experts.1.dense2.weight
|
|
(768, 3072)" fillcolor=lightblue]
|
|
140202228904640 -> 140202223137840
|
|
140202223137840 [label=AccumulateGrad]
|
|
140202223578272 -> 140202223578464
|
|
140202223578272 [label=UnsqueezeBackward0]
|
|
140202223080736 -> 140202223578272
|
|
140202223080736 [label=NativeDropoutBackward0]
|
|
140202223082944 -> 140202223080736
|
|
140202223082944 [label=ViewBackward0]
|
|
140202223108160 -> 140202223082944
|
|
140202223108160 [label=AddmmBackward0]
|
|
140202223079680 -> 140202223108160
|
|
140202223079680 [label=ToCopyBackward0]
|
|
140210811784208 -> 140202223079680
|
|
140202228895552 [label="encoder.layer.10.experts.experts.2.dense2.bias
|
|
(768)" fillcolor=lightblue]
|
|
140202228895552 -> 140210811784208
|
|
140210811784208 [label=AccumulateGrad]
|
|
140210811784112 -> 140202223108160
|
|
140210811784112 [label=ViewBackward0]
|
|
140210811784256 -> 140210811784112
|
|
140210811784256 [label=GeluBackward0]
|
|
140210811784352 -> 140210811784256
|
|
140210811784352 [label=ViewBackward0]
|
|
140210811784448 -> 140210811784352
|
|
140210811784448 [label=AddmmBackward0]
|
|
140210811784544 -> 140210811784448
|
|
140210811784544 [label=ToCopyBackward0]
|
|
140210811784736 -> 140210811784544
|
|
140202228904560 [label="encoder.layer.10.experts.experts.2.dense1.bias
|
|
(3072)" fillcolor=lightblue]
|
|
140202228904560 -> 140210811784736
|
|
140210811784736 [label=AccumulateGrad]
|
|
140210811784496 -> 140210811784448
|
|
140210811784496 [label=ViewBackward0]
|
|
140210811784784 -> 140210811784496
|
|
140210811784784 [label=ToCopyBackward0]
|
|
140202223577888 -> 140210811784784
|
|
140210811784160 -> 140210811784448
|
|
140210811784160 [label=TBackward0]
|
|
140210811784640 -> 140210811784160
|
|
140210811784640 [label=ToCopyBackward0]
|
|
140210811784928 -> 140210811784640
|
|
140202228904400 [label="encoder.layer.10.experts.experts.2.dense1.weight
|
|
(3072, 768)" fillcolor=lightblue]
|
|
140202228904400 -> 140210811784928
|
|
140210811784928 [label=AccumulateGrad]
|
|
140210811784016 -> 140202223108160
|
|
140210811784016 [label=TBackward0]
|
|
140210811784400 -> 140210811784016
|
|
140210811784400 [label=ToCopyBackward0]
|
|
140210811784880 -> 140210811784400
|
|
140202228904320 [label="encoder.layer.10.experts.experts.2.dense2.weight
|
|
(768, 3072)" fillcolor=lightblue]
|
|
140202228904320 -> 140210811784880
|
|
140210811784880 [label=AccumulateGrad]
|
|
140202223578176 -> 140202223578128
|
|
140202223578176 [label=UnsqueezeBackward0]
|
|
140202223578848 -> 140202223578176
|
|
140202223578848 [label=UnsqueezeBackward0]
|
|
140202223109792 -> 140202223578848
|
|
140202223109792 [label=SumBackward1]
|
|
140202223079920 -> 140202223109792
|
|
140202223079920 [label=MulBackward0]
|
|
140210811785024 -> 140202223079920
|
|
140210811785024 [label=UnsqueezeBackward0]
|
|
140210811784304 -> 140210811785024
|
|
140210811784304 [label=TopkBackward0]
|
|
140210811784832 -> 140210811784304
|
|
140210811784832 [label=SoftmaxBackward0]
|
|
140210811785120 -> 140210811784832
|
|
140210811785120 [label=MmBackward0]
|
|
140210811785168 -> 140210811785120
|
|
140210811785168 [label=ToCopyBackward0]
|
|
140210811850960 -> 140210811785168
|
|
140210811850960 [label=MeanBackward1]
|
|
140210811851056 -> 140210811850960
|
|
140210811851056 [label=MulBackward0]
|
|
140202223577888 -> 140210811851056
|
|
140210811784064 -> 140210811785120
|
|
140210811784064 [label=TBackward0]
|
|
140210811851152 -> 140210811784064
|
|
140210811851152 [label=ToCopyBackward0]
|
|
140210811850864 -> 140210811851152
|
|
140202228906000 [label="encoder.layer.10.experts.gate.weight
|
|
(3, 768)" fillcolor=lightblue]
|
|
140202228906000 -> 140210811850864
|
|
140210811850864 [label=AccumulateGrad]
|
|
140202223577888 -> 140202223577504
|
|
140202223577600 -> 140202223577408
|
|
140202228906320 [label="encoder.layer.10.expert_ln.weight
|
|
(768)" fillcolor=lightblue]
|
|
140202228906320 -> 140202223577600
|
|
140202223577600 [label=AccumulateGrad]
|
|
140202223577312 -> 140202223577408
|
|
140202228906080 [label="encoder.layer.10.expert_ln.bias
|
|
(768)" fillcolor=lightblue]
|
|
140202228906080 -> 140202223577312
|
|
140202223577312 [label=AccumulateGrad]
|
|
140202223576832 -> 140202223540112
|
|
140202223576832 [label=NativeLayerNormBackward0]
|
|
140202223577984 -> 140202223576832
|
|
140202223577984 [label=AddBackward0]
|
|
140202223081840 -> 140202223577984
|
|
140202223081840 [label=NativeDropoutBackward0]
|
|
140210811784976 -> 140202223081840
|
|
140210811784976 [label=ViewBackward0]
|
|
140210811785072 -> 140210811784976
|
|
140210811785072 [label=AddmmBackward0]
|
|
140210811851104 -> 140210811785072
|
|
140210811851104 [label=ToCopyBackward0]
|
|
140210811851296 -> 140210811851104
|
|
140202228907680 [label="encoder.layer.10.output.dense.bias
|
|
(768)" fillcolor=lightblue]
|
|
140202228907680 -> 140210811851296
|
|
140210811851296 [label=AccumulateGrad]
|
|
140210811851008 -> 140210811785072
|
|
140210811851008 [label=ViewBackward0]
|
|
140210811851344 -> 140210811851008
|
|
140210811851344 [label=GeluBackward0]
|
|
140210811851440 -> 140210811851344
|
|
140210811851440 [label=ViewBackward0]
|
|
140210811851536 -> 140210811851440
|
|
140210811851536 [label=AddmmBackward0]
|
|
140210811851632 -> 140210811851536
|
|
140210811851632 [label=ToCopyBackward0]
|
|
140210811851824 -> 140210811851632
|
|
140202228924480 [label="encoder.layer.10.intermediate.dense.bias
|
|
(3072)" fillcolor=lightblue]
|
|
140202228924480 -> 140210811851824
|
|
140210811851824 [label=AccumulateGrad]
|
|
140210811851584 -> 140210811851536
|
|
140210811851584 [label=ViewBackward0]
|
|
140210811851872 -> 140210811851584
|
|
140210811851872 [label=ToCopyBackward0]
|
|
140202223578560 -> 140210811851872
|
|
140202223578560 [label=SliceBackward0]
|
|
140210811852016 -> 140202223578560
|
|
140210811852016 [label=SliceBackward0]
|
|
140210811852112 -> 140210811852016
|
|
140210811852112 [label=SliceBackward0]
|
|
140202223112000 -> 140210811852112
|
|
140210811850912 -> 140210811851536
|
|
140210811850912 [label=TBackward0]
|
|
140210811851776 -> 140210811850912
|
|
140210811851776 [label=ToCopyBackward0]
|
|
140210811852208 -> 140210811851776
|
|
140202228924720 [label="encoder.layer.10.intermediate.dense.weight
|
|
(3072, 768)" fillcolor=lightblue]
|
|
140202228924720 -> 140210811852208
|
|
140210811852208 [label=AccumulateGrad]
|
|
140210811850816 -> 140210811785072
|
|
140210811850816 [label=TBackward0]
|
|
140210811851488 -> 140210811850816
|
|
140210811851488 [label=ToCopyBackward0]
|
|
140210811851968 -> 140210811851488
|
|
140202228907920 [label="encoder.layer.10.output.dense.weight
|
|
(768, 3072)" fillcolor=lightblue]
|
|
140202228907920 -> 140210811851968
|
|
140210811851968 [label=AccumulateGrad]
|
|
140202223578560 -> 140202223577984
|
|
140202223577696 -> 140202223576832
|
|
140202228907760 [label="encoder.layer.10.output.LayerNorm.weight
|
|
(768)" fillcolor=lightblue]
|
|
140202228907760 -> 140202223577696
|
|
140202223577696 [label=AccumulateGrad]
|
|
140202223577648 -> 140202223576832
|
|
140202228907440 [label="encoder.layer.10.output.LayerNorm.bias
|
|
(768)" fillcolor=lightblue]
|
|
140202228907440 -> 140202223577648
|
|
140202223577648 [label=AccumulateGrad]
|
|
140202223575728 -> 140202223576640
|
|
140202223575728 [label=TBackward0]
|
|
140202223576928 -> 140202223575728
|
|
140202223576928 [label=ToCopyBackward0]
|
|
140202223578080 -> 140202223576928
|
|
140202228906240 [label="encoder.layer.11.attention.self.query.weight
|
|
(768, 768)" fillcolor=lightblue]
|
|
140202228906240 -> 140202223578080
|
|
140202223578080 [label=AccumulateGrad]
|
|
140202223575680 -> 140202223575392
|
|
140202223575680 [label=ReshapeAliasBackward0]
|
|
140202223576064 -> 140202223575680
|
|
140202223576064 [label=ExpandBackward0]
|
|
140202223576352 -> 140202223576064
|
|
140202223576352 [label=TransposeBackward0]
|
|
140202223577216 -> 140202223576352
|
|
140202223577216 [label=PermuteBackward0]
|
|
140202223577168 -> 140202223577216
|
|
140202223577168 [label=ViewBackward0]
|
|
140210811783872 -> 140202223577168
|
|
140210811783872 [label=ViewBackward0]
|
|
140210811784592 -> 140210811783872
|
|
140210811784592 [label=AddmmBackward0]
|
|
140210811851728 -> 140210811784592
|
|
140210811851728 [label=ToCopyBackward0]
|
|
140210811851920 -> 140210811851728
|
|
140202228906800 [label="encoder.layer.11.attention.self.key.bias
|
|
(768)" fillcolor=lightblue]
|
|
140202228906800 -> 140210811851920
|
|
140210811851920 [label=AccumulateGrad]
|
|
140210811851680 -> 140210811784592
|
|
140210811851680 [label=ViewBackward0]
|
|
140210811852256 -> 140210811851680
|
|
140210811852256 [label=ToCopyBackward0]
|
|
140202223540112 -> 140210811852256
|
|
140210811851248 -> 140210811784592
|
|
140210811851248 [label=TBackward0]
|
|
140210811851392 -> 140210811851248
|
|
140210811851392 [label=ToCopyBackward0]
|
|
140210811852400 -> 140210811851392
|
|
140202228906480 [label="encoder.layer.11.attention.self.key.weight
|
|
(768, 768)" fillcolor=lightblue]
|
|
140202228906480 -> 140210811852400
|
|
140210811852400 [label=AccumulateGrad]
|
|
140202223541168 -> 140202223541312
|
|
140202223541168 [label=ReshapeAliasBackward0]
|
|
140202223541888 -> 140202223541168
|
|
140202223541888 [label=ExpandBackward0]
|
|
140202223542176 -> 140202223541888
|
|
140202223542176 [label=PermuteBackward0]
|
|
140202223541456 -> 140202223542176
|
|
140202223541456 [label=ViewBackward0]
|
|
140202223575200 -> 140202223541456
|
|
140202223575200 [label=ViewBackward0]
|
|
140202223576256 -> 140202223575200
|
|
140202223576256 [label=AddmmBackward0]
|
|
140202223575776 -> 140202223576256
|
|
140202223575776 [label=ToCopyBackward0]
|
|
140210811852352 -> 140202223575776
|
|
140202228905840 [label="encoder.layer.11.attention.self.value.bias
|
|
(768)" fillcolor=lightblue]
|
|
140202228905840 -> 140210811852352
|
|
140210811852352 [label=AccumulateGrad]
|
|
140202223576736 -> 140202223576256
|
|
140202223576736 [label=ViewBackward0]
|
|
140210811852160 -> 140202223576736
|
|
140210811852160 [label=ToCopyBackward0]
|
|
140202223540112 -> 140210811852160
|
|
140202223575104 -> 140202223576256
|
|
140202223575104 [label=TBackward0]
|
|
140210811851200 -> 140202223575104
|
|
140210811851200 [label=ToCopyBackward0]
|
|
140210811852304 -> 140210811851200
|
|
140202228905760 [label="encoder.layer.11.attention.self.value.weight
|
|
(768, 768)" fillcolor=lightblue]
|
|
140202228905760 -> 140210811852304
|
|
140210811852304 [label=AccumulateGrad]
|
|
140202223540208 -> 140202223540400
|
|
140202223540208 [label=TBackward0]
|
|
140202223540880 -> 140202223540208
|
|
140202223540880 [label=ToCopyBackward0]
|
|
140202223541072 -> 140202223540880
|
|
140202228905520 [label="encoder.layer.11.attention.output.dense.weight
|
|
(768, 768)" fillcolor=lightblue]
|
|
140202228905520 -> 140202223541072
|
|
140202223541072 [label=AccumulateGrad]
|
|
140202223540112 -> 140202223540160
|
|
140202223539920 -> 140202223540064
|
|
140202228904160 [label="encoder.layer.11.attention.output.LayerNorm.weight
|
|
(768)" fillcolor=lightblue]
|
|
140202228904160 -> 140202223539920
|
|
140202223539920 [label=AccumulateGrad]
|
|
140202223538576 -> 140202223540064
|
|
140202228895312 [label="encoder.layer.11.attention.output.LayerNorm.bias
|
|
(768)" fillcolor=lightblue]
|
|
140202228895312 -> 140202223538576
|
|
140202223538576 [label=AccumulateGrad]
|
|
140202223539056 -> 140202223539680
|
|
140202223539056 [label=TBackward0]
|
|
140202223538384 -> 140202223539056
|
|
140202223538384 [label=ToCopyBackward0]
|
|
140202223539632 -> 140202223538384
|
|
140202228893872 [label="encoder.layer.11.experts.dense1.weight
|
|
(3072, 768)" fillcolor=lightblue]
|
|
140202228893872 -> 140202223539632
|
|
140202223539632 [label=AccumulateGrad]
|
|
140202223539344 -> 140202223539008
|
|
140202223539344 [label=TBackward0]
|
|
140202223539488 -> 140202223539344
|
|
140202223539488 [label=ToCopyBackward0]
|
|
140202223538240 -> 140202223539488
|
|
140202228893632 [label="encoder.layer.11.experts.dense2.weight
|
|
(768, 3072)" fillcolor=lightblue]
|
|
140202228893632 -> 140202223538240
|
|
140202223538240 [label=AccumulateGrad]
|
|
140202223538480 -> 140202228614096
|
|
140202228614192 -> 140202228615488
|
|
140202228893392 [label="encoder.layer.11.expert_ln.weight
|
|
(768)" fillcolor=lightblue]
|
|
140202228893392 -> 140202228614192
|
|
140202228614192 [label=AccumulateGrad]
|
|
140202228614336 -> 140202228615488
|
|
140202228893472 [label="encoder.layer.11.expert_ln.bias
|
|
(768)" fillcolor=lightblue]
|
|
140202228893472 -> 140202228614336
|
|
140202228614336 [label=AccumulateGrad]
|
|
140202228614480 -> 140202228657312
|
|
140202228614480 [label=NativeLayerNormBackward0]
|
|
140202228614432 -> 140202228614480
|
|
140202228614432 [label=AddBackward0]
|
|
140202223538816 -> 140202228614432
|
|
140202223538816 [label=NativeDropoutBackward0]
|
|
140202223539392 -> 140202223538816
|
|
140202223539392 [label=ViewBackward0]
|
|
140202223538432 -> 140202223539392
|
|
140202223538432 [label=AddmmBackward0]
|
|
140202223540256 -> 140202223538432
|
|
140202223540256 [label=ToCopyBackward0]
|
|
140202223540592 -> 140202223540256
|
|
140202228895152 [label="encoder.layer.11.output.dense.bias
|
|
(768)" fillcolor=lightblue]
|
|
140202228895152 -> 140202223540592
|
|
140202223540592 [label=AccumulateGrad]
|
|
140202223540016 -> 140202223538432
|
|
140202223540016 [label=ViewBackward0]
|
|
140202223540976 -> 140202223540016
|
|
140202223540976 [label=GeluBackward0]
|
|
140202223540832 -> 140202223540976
|
|
140202223540832 [label=ViewBackward0]
|
|
140202223541936 -> 140202223540832
|
|
140202223541936 [label=AddmmBackward0]
|
|
140202223540736 -> 140202223541936
|
|
140202223540736 [label=ToCopyBackward0]
|
|
140210811784688 -> 140202223540736
|
|
140202228895392 [label="encoder.layer.11.intermediate.dense.bias
|
|
(3072)" fillcolor=lightblue]
|
|
140202228895392 -> 140210811784688
|
|
140210811784688 [label=AccumulateGrad]
|
|
140202223575488 -> 140202223541936
|
|
140202223575488 [label=ViewBackward0]
|
|
140210811852592 -> 140202223575488
|
|
140210811852592 [label=ToCopyBackward0]
|
|
140202223539200 -> 140210811852592
|
|
140202223539200 [label=SliceBackward0]
|
|
140210811852640 -> 140202223539200
|
|
140210811852640 [label=SliceBackward0]
|
|
140210811852736 -> 140210811852640
|
|
140210811852736 [label=SliceBackward0]
|
|
140202223540064 -> 140210811852736
|
|
140202223575248 -> 140202223541936
|
|
140202223575248 [label=TBackward0]
|
|
140210811852064 -> 140202223575248
|
|
140210811852064 [label=ToCopyBackward0]
|
|
140210811852832 -> 140210811852064
|
|
140202228895632 [label="encoder.layer.11.intermediate.dense.weight
|
|
(3072, 768)" fillcolor=lightblue]
|
|
140202228895632 -> 140210811852832
|
|
140210811852832 [label=AccumulateGrad]
|
|
140202223539824 -> 140202223538432
|
|
140202223539824 [label=TBackward0]
|
|
140202223540784 -> 140202223539824
|
|
140202223540784 [label=ToCopyBackward0]
|
|
140202223575872 -> 140202223540784
|
|
140202228895072 [label="encoder.layer.11.output.dense.weight
|
|
(768, 3072)" fillcolor=lightblue]
|
|
140202228895072 -> 140202223575872
|
|
140202223575872 [label=AccumulateGrad]
|
|
140202223539200 -> 140202228614432
|
|
140202223538672 -> 140202228614480
|
|
140202228894832 [label="encoder.layer.11.output.LayerNorm.weight
|
|
(768)" fillcolor=lightblue]
|
|
140202228894832 -> 140202223538672
|
|
140202223538672 [label=AccumulateGrad]
|
|
140202223538624 -> 140202228614480
|
|
140202228894912 [label="encoder.layer.11.output.LayerNorm.bias
|
|
(768)" fillcolor=lightblue]
|
|
140202228894912 -> 140202223538624
|
|
140202223538624 [label=AccumulateGrad]
|
|
140202228657312 -> 140202223089520
|
|
}
|