tinygrad Tests

Output from tinygrad test scripts.

test_assign.py

....
----------------------------------------------------------------------
Ran 4 tests in 0.247s

OK

test_conv.py

.............s
----------------------------------------------------------------------
Ran 14 tests in 0.616s

OK (skipped=1)
(1, 16, 64, 128)
[[[[  0.   2.   4.   6.]
   [  8.  10.  12.  14.]]

  [[ 16.  18.  20.  22.]
   [ 24.  26.  28.  30.]]

  [[ 32.  34.  36.  38.]
   [ 40.  42.  44.  46.]]

  [[ 48.  50.  52.  54.]
   [ 56.  58.  60.  62.]]

  [[ 64.  66.  68.  70.]
   [ 72.  74.  76.  78.]]

  [[ 80.  82.  84.  86.]
   [ 88.  90.  92.  94.]]

  [[ 96.  98. 100. 102.]
   [104. 106. 108. 110.]]

  [[112. 114. 116. 118.]
   [120. 122. 124. 126.]]]]
(1, 12, 128, 256)
[[[[ 0.93149185  0.2806782   0.8056647   0.41214436  0.15504545]
   [ 0.62593424  0.31054336  0.5603988   0.23496133  0.7643574 ]
   [ 0.33112532  0.92565084  0.06013149  0.35230464  0.8359076 ]
   [ 0.03753501  0.11257637  0.8517584   0.31205297  0.2338121 ]
   [ 0.5579621   0.30820632  0.7866557   0.86819595  0.5399461 ]]

  [[ 2.118766    2.820211    2.9798832   2.840959    2.9189024 ]
   [ 2.9207013   2.2554026   2.9757376   2.7623498   2.9114668 ]
   [ 2.702383    2.1741352   2.454306    2.237937    2.2713687 ]
   [ 2.9474719   2.55361     2.5134242   2.8316839   2.898455  ]
   [ 2.9178374   2.6610773   2.3675396   2.2355099   2.849178  ]]

  [[ 4.667576    4.1636677   4.1796637   4.2359447   4.648137  ]
   [ 4.2159333   4.4855537   4.6304245   4.666215    4.5467167 ]
   [ 4.0116334   4.6793327   4.0639677   4.9461346   4.1767063 ]
   [ 4.1363883   4.2080407   4.9258995   4.4663424   4.65409   ]
   [ 4.0414352   4.7688603   4.0794125   4.7419724   4.702286  ]]

  [[ 6.6014137   6.8497806   6.5368705   6.1036687   6.875553  ]
   [ 6.725318    6.1032476   6.77197     6.7689934   6.8288307 ]
   [ 6.8870053   6.823203    6.591322    6.9067283   6.0349364 ]
   [ 6.3511214   6.9073553   6.370795    6.1766405   6.6361146 ]
   [ 6.203563    6.215101    6.3605976   6.1132      6.545439  ]]

  [[ 8.008588    8.197271    8.035969    8.758807    8.864654  ]
   [ 8.15585     8.980614    8.728106    8.08209     8.551898  ]
   [ 8.510533    8.040758    8.200823    8.798664    8.371699  ]
   [ 8.275993    8.2857895   8.323525    8.21355     8.000079  ]
   [ 8.271421    8.952141    8.569697    8.767508    8.597761  ]]

  [[10.100012   10.998785   10.802147   10.663872   10.724545  ]
   [10.257475   10.818329   10.174393   10.802899   10.843636  ]
   [10.500741   10.969423   10.043892   10.181596   10.658959  ]
   [10.735225   10.995212   10.76931    10.137385   10.948263  ]
   [10.290034   10.417219   10.158831   10.666708   10.760326  ]]

  [[12.860636   12.685801   12.822651   12.416732   12.358686  ]
   [12.074683   12.158253   12.184881   12.791336   12.933141  ]
   [12.210114   12.003366   12.003986   12.61767    12.052004  ]
   [12.512547   12.105045   12.474449   12.496885   12.412529  ]
   [12.256023   12.575817   12.5210085  12.726767   12.204369  ]]

  [[14.612148   14.328089   14.722721   14.709069   14.475655  ]
   [14.102378   14.145342   14.766401   14.537128   14.516569  ]
   [14.042732   14.191367   14.124958   14.788248   14.82028   ]
   [14.172691   14.88889    14.993577   14.581903   14.392723  ]
   [14.217729   14.764521   14.192541   14.960721   14.391001  ]]]]

test_conv_shapetracker.py

.
----------------------------------------------------------------------
Ran 1 test in 0.148s

OK
ScheduleItem(ast=LazyOp(op=BufferOps.STORE, src=(LazyOp(op=BinaryOps.ADD, src=(LazyOp(op=ReduceOps.SUM, src=(LazyOp(op=BinaryOps.MUL, src=(LazyOp(op=BufferOps.LOAD, src=(), arg=MemBuffer(idx=1, dtype=dtypes.float, st=ShapeTracker(views=(View(shape=(1, 1, 32, 8, 8, 16, 3, 3), strides=(0, 0, 0, 10, 1, 100, 10, 1), offset=0, mask=None, contiguous=False),)))), LazyOp(op=BufferOps.LOAD, src=(), arg=MemBuffer(idx=2, dtype=dtypes.float, st=ShapeTracker(views=(View(shape=(1, 1, 32, 8, 8, 16, 3, 3), strides=(0, 0, 144, 0, 0, 9, 3, 1), offset=0, mask=None, contiguous=False),))))), arg=None),), arg=(1, 1, 32, 8, 8, 1, 1, 1)), LazyOp(op=BufferOps.LOAD, src=(), arg=MemBuffer(idx=3, dtype=dtypes.float, st=ShapeTracker(views=(View(shape=(1, 1, 32, 8, 8, 1, 1, 1), strides=(0, 0, 1, 0, 0, 0, 0, 0), offset=0, mask=None, contiguous=False),))))), arg=None),), arg=MemBuffer(idx=0, dtype=dtypes.float, st=ShapeTracker(views=(View(shape=(1, 1, 32, 8, 8, 1, 1, 1), strides=(0, 0, 64, 8, 1, 0, 0, 0), offset=0, mask=None, contiguous=True),)))), out=<LB HIP (1, 32, 8, 8) contig:True (<BinaryOps.ADD: 1>, None)>, inputs=(<LB HIP (1, 16, 10, 10) contig:True (<LoadOps.EMPTY: 1>, None)>, <LB HIP (32, 16, 3, 3) contig:True (<BinaryOps.ADD: 1>, None)>, <LB HIP (32,) contig:True (<BinaryOps.ADD: 1>, None)>), var_vals={})
ShapeTracker(views=(View(shape=(1, 32, 8, 8), strides=(0, 64, 8, 1), offset=0, mask=None, contiguous=True),))
ShapeTracker(views=(View(shape=(1, 16, 10, 10), strides=(0, 100, 10, 1), offset=0, mask=None, contiguous=True),))
ShapeTracker(views=(View(shape=(32, 16, 3, 3), strides=(144, 9, 3, 1), offset=0, mask=None, contiguous=True),))
ShapeTracker(views=(View(shape=(32,), strides=(1,), offset=0, mask=None, contiguous=True),))

test_copy_speed.py

s....
----------------------------------------------------------------------
Ran 5 tests in 8.933s

OK (skipped=1)
buffer: 1.07 GB
queue: 397.35 ms
sync:  439.41 ms @ 2.44 GB/s
queue: 181.69 ms
sync:  223.78 ms @ 4.80 GB/s
queue: 181.46 ms
sync:  223.29 ms @ 4.81 GB/s
fresh copy
queue: 181.36 ms
sync:  223.19 ms @ 4.81 GB/s
queue: 180.45 ms
sync:  222.57 ms @ 4.82 GB/s
queue: 179.46 ms
sync:  221.52 ms @ 4.85 GB/s
buffer: 1.07 GB
sync:  505.38 ms @ 2.12 GB/s
sync:  500.41 ms @ 2.15 GB/s
sync:  536.86 ms @ 2.00 GB/s
queue: 187.57 ms
sync:  229.64 ms @ 4.68 GB/s
queue: 184.20 ms
sync:  226.16 ms @ 4.75 GB/s
queue: 184.30 ms
sync:  226.17 ms @ 4.75 GB/s

test_custom_function.py

sss
----------------------------------------------------------------------
Ran 3 tests in 0.000s

OK (skipped=3)

test_device_speed.py

....
----------------------------------------------------------------------
Ran 4 tests in 0.368s

OK
compiler  22.39 ms
compiler  18.14 ms
launch 1000x   4.15 ms
launch 1000x with wait  41.12 ms
n:    1000  tm:   4.28ms  tot:   4.78ms ops_hip.py:46:__call__                             

test_dtype_alu.py

Traceback (most recent call last):
  File "/home/jebba/devel/tinygrad/tinygrad/test/test_dtype_alu.py", line 10, in <module>
    from test.test_dtype import is_dtype_supported
ModuleNotFoundError: No module named 'test.test_dtype'

test_dtype.py

..........ssss...s........s...........................................................................................................................
----------------------------------------------------------------------
Ran 149 tests in 6.435s

OK (skipped=6)

test_fusion_op.py

test_contiguous_add (__main__.TestFusionOp) ... ok
test_expand_fuse (__main__.TestFusionOp) ... ok
test_recursive_add (__main__.TestFusionOp) ... ok
test_recursive_add_cmp (__main__.TestFusionOp) ... ok

----------------------------------------------------------------------
Ran 4 tests in 0.481s

OK

test_gc.py

..
----------------------------------------------------------------------
Ran 2 tests in 0.206s

OK
3
4

test_image_dtype.py

sssssssss.
----------------------------------------------------------------------
Ran 10 tests in 0.000s

OK (skipped=9)
<((((((gidx0[0-511]*4)%32)*8)%64)+(((gidx0[0-511]//8)%32)//4))%64)> <((gidx0[0-511]//2)%4)> 0 63 0 3 <(gidx0[0-511]<256)>

test_jit.py

Traceback (most recent call last):
  File "/home/jebba/devel/tinygrad/tinygrad/test/test_jit.py", line 5, in <module>
    from test.helpers import assert_jit_cache_len
ModuleNotFoundError: No module named 'test.helpers'

test_kernel_cache.py

s
----------------------------------------------------------------------
Ran 1 test in 0.146s

OK (skipped=1)

test_lazybuffer.py

........
----------------------------------------------------------------------
Ran 8 tests in 0.415s

OK
(1,) (-8,) True
(1,) (-8,) True
(4,) (4,) True
(3,) (4,) True
(2,) (8,) False
(2,) (8,) False
(1, 1) (-32, -8) True
(1, 1) (-32, -8) True
(4, 4) (16, 4) True
(3, 3) (16, 4) False
(2, 2) (32, 8) False
(2, 2) (32, 8) False
(1, 1, 1) (-128, -32, -8) True
(1, 1, 1) (-128, -32, -8) True
(4, 4, 4) (64, 16, 4) True
(3, 3, 3) (64, 16, 4) False
(2, 2, 2) (128, 32, 8) False
(2, 2, 2) (128, 32, 8) False

test_lazyop.py

..
----------------------------------------------------------------------
Ran 2 tests in 0.156s

OK

test_linearizer_failures.py

Traceback (most recent call last):
  File "/home/jebba/devel/tinygrad/tinygrad/test/test_linearizer_failures.py", line 8, in <module>
    from test.external.fuzz_linearizer import run_linearizer, get_fuzz_rawbufs, get_fuzz_rawbuf_like
ModuleNotFoundError: No module named 'test.external'

test_linearizer.py

................s........................
----------------------------------------------------------------------
Ran 41 tests in 15.010s

OK (skipped=1)

test_masked_st.py

...
----------------------------------------------------------------------
Ran 3 tests in 0.469s

OK

test_method_cache.py

....
----------------------------------------------------------------------
Ran 4 tests in 2.570s

OK

test_multitensor.py

....
https://download.pytorch.org/models/resnet18-5c106cde.pth:   0%|          | 0.00/46.8M [00:00<?, ?B/s]
https://download.pytorch.org/models/resnet18-5c106cde.pth:   0%|          | 32.8k/46.8M [00:00<03:16, 238kB/s]
https://download.pytorch.org/models/resnet18-5c106cde.pth:   0%|          | 98.3k/46.8M [00:00<02:08, 362kB/s]
https://download.pytorch.org/models/resnet18-5c106cde.pth:   0%|          | 197k/46.8M [00:00<01:22, 568kB/s] 
https://download.pytorch.org/models/resnet18-5c106cde.pth:   1%|          | 328k/46.8M [00:00<00:58, 796kB/s]
https://download.pytorch.org/models/resnet18-5c106cde.pth:   1%|          | 524k/46.8M [00:00<00:39, 1.17MB/s]
https://download.pytorch.org/models/resnet18-5c106cde.pth:   2%|▏         | 852k/46.8M [00:00<00:25, 1.80MB/s]
https://download.pytorch.org/models/resnet18-5c106cde.pth:   3%|▎         | 1.36M/46.8M [00:00<00:16, 2.81MB/s]
https://download.pytorch.org/models/resnet18-5c106cde.pth:   4%|▍         | 2.10M/46.8M [00:00<00:10, 4.19MB/s]
https://download.pytorch.org/models/resnet18-5c106cde.pth:   7%|▋         | 3.06M/46.8M [00:01<00:07, 5.83MB/s]
https://download.pytorch.org/models/resnet18-5c106cde.pth:  10%|▉         | 4.51M/46.8M [00:01<00:05, 8.42MB/s]
https://download.pytorch.org/models/resnet18-5c106cde.pth:  15%|█▍        | 6.86M/46.8M [00:01<00:03, 13.0MB/s]
https://download.pytorch.org/models/resnet18-5c106cde.pth:  18%|█▊        | 8.36M/46.8M [00:01<00:02, 13.5MB/s]
https://download.pytorch.org/models/resnet18-5c106cde.pth:  22%|██▏       | 10.4M/46.8M [00:01<00:02, 15.5MB/s]
https://download.pytorch.org/models/resnet18-5c106cde.pth:  26%|██▌       | 12.2M/46.8M [00:01<00:03, 9.01MB/s]
https://download.pytorch.org/models/resnet18-5c106cde.pth:  32%|███▏      | 15.1M/46.8M [00:01<00:02, 11.4MB/s]
https://download.pytorch.org/models/resnet18-5c106cde.pth:  35%|███▌      | 16.5M/46.8M [00:02<00:03, 8.59MB/s]
https://download.pytorch.org/models/resnet18-5c106cde.pth:  39%|███▉      | 18.5M/46.8M [00:02<00:02, 9.81MB/s]
https://download.pytorch.org/models/resnet18-5c106cde.pth:  43%|████▎     | 20.1M/46.8M [00:02<00:02, 11.0MB/s]
https://download.pytorch.org/models/resnet18-5c106cde.pth:  46%|████▌     | 21.4M/46.8M [00:02<00:02, 11.2MB/s]
https://download.pytorch.org/models/resnet18-5c106cde.pth:  50%|████▉     | 23.4M/46.8M [00:02<00:01, 13.1MB/s]
https://download.pytorch.org/models/resnet18-5c106cde.pth:  54%|█████▎    | 25.1M/46.8M [00:02<00:01, 14.1MB/s]
https://download.pytorch.org/models/resnet18-5c106cde.pth:  58%|█████▊    | 27.1M/46.8M [00:03<00:01, 10.6MB/s]
https://download.pytorch.org/models/resnet18-5c106cde.pth:  65%|██████▍   | 30.2M/46.8M [00:03<00:01, 13.4MB/s]
https://download.pytorch.org/models/resnet18-5c106cde.pth:  68%|██████▊   | 31.8M/46.8M [00:03<00:01, 10.8MB/s]
https://download.pytorch.org/models/resnet18-5c106cde.pth:  71%|███████▏  | 33.4M/46.8M [00:03<00:01, 11.0MB/s]
https://download.pytorch.org/models/resnet18-5c106cde.pth:  75%|███████▌  | 35.2M/46.8M [00:03<00:01, 11.3MB/s]
https://download.pytorch.org/models/resnet18-5c106cde.pth:  79%|███████▉  | 37.0M/46.8M [00:03<00:00, 12.6MB/s]
https://download.pytorch.org/models/resnet18-5c106cde.pth:  84%|████████▎ | 39.2M/46.8M [00:03<00:00, 14.7MB/s]
https://download.pytorch.org/models/resnet18-5c106cde.pth:  88%|████████▊ | 41.0M/46.8M [00:04<00:00, 15.6MB/s]
https://download.pytorch.org/models/resnet18-5c106cde.pth:  92%|█████████▏| 43.1M/46.8M [00:04<00:00, 16.8MB/s]
https://download.pytorch.org/models/resnet18-5c106cde.pth:  96%|█████████▌| 44.9M/46.8M [00:04<00:00, 12.2MB/s]
https://download.pytorch.org/models/resnet18-5c106cde.pth: 100%|██████████| 46.8M/46.8M [00:04<00:00, 10.6MB/s]
.................s........................
----------------------------------------------------------------------
Ran 46 tests in 45.744s

OK (skipped=1)
i=0
i=1
i=2
i=3

test_net_speed.py

torch forward pass:  21.182 ms
torch backward pass: 58.428 ms
n:       4  tm: 166.20ms  tot: 166.79ms hip_comgr.py:17:compile_hip                        <- 100% ops_hip.py:19:compile
n:       4  tm:  30.54ms  tot:  30.54ms ~:0:<method 'commit' of 'sqlite3.Connection' objects> <- 100% helpers.py:151:diskcache_put
n:    2235  tm:   6.98ms  tot:  14.25ms linearizer.py:446:uop                              <-  65% linearizer.py:39:uop_alu_idx
n:   31058  tm:   6.68ms  tot:  12.00ms ~:0:<built-in method builtins.hash>                <-  73% <string>:2:__hash__
n:    6349  tm:   4.67ms  tot:  26.61ms symbolic.py:14:render                              <-  36% symbolic.py:324:<listcomp>
n:       5  tm:   4.59ms  tot:   4.60ms ops_hip.py:91:<lambda>                             <- 100% helpers.py:209:init_c_var
n:   19971  tm:   4.17ms  tot:   4.17ms uops.py:60:<genexpr>                               <- 100% ~:0:<built-in method builtins.any>
n:       4  tm:   3.97ms  tot:   3.98ms ops_hip.py:40:<lambda>                             <- 100% helpers.py:209:init_c_var
n:    2060  tm:   3.86ms  tot:  11.91ms ~:0:<built-in method builtins.any>                 <-  96% uops.py:50:fix_loop_scope
n:     825  tm:   3.80ms  tot:  13.97ms lazy.py:156:_recursive_lazyop                      <-  83% lazy.py:189:<genexpr>
n:       5  tm:   3.76ms  tot:   3.76ms ~:0:<method 'random' of 'numpy.random._generator.Generator' objects> <- 100% tensor.py:978:custom_random
n:    1229  tm:   3.30ms  tot:   5.76ms linearizer.py:404:get_recursive_parents            <-  76% linearizer.py:406:<listcomp>
n:     840  tm:   2.68ms  tot:   4.42ms lazy.py:211:_recurse_lb                            <-  95% lazy.py:211:_recurse_lb
n:     980  tm:   2.50ms  tot:   5.23ms lazy.py:28:__init__                                <- 100% lazy.py:18:create_lazybuffer
n:    6133  tm:   2.50ms  tot:   7.57ms ~:0:<method 'get' of 'dict' objects>               <-  61% linearizer.py:446:uop
n:     933  tm:   2.50ms  tot:   4.72ms ops.py:55:cached_compare                           <-  81% ops.py:59:<genexpr>
n:   23852  tm:   2.45ms  tot:   2.45ms uops.py:64:<genexpr>                               <-  98% ~:0:<built-in method builtins.any>
n:    9257  tm:   2.38ms  tot:   3.36ms enum.py:783:__hash__                               <-  42% ~:0:<method 'get' of 'dict' objects>
n:    1005  tm:   2.37ms  tot:  11.44ms lazy.py:18:create_lazybuffer                       <-  51% lazy.py:141:_view
n:   17870  tm:   2.28ms  tot:   2.29ms ~:0:<built-in method builtins.isinstance>          <-  33% enum.py:396:__contains__
n:    1317  tm:   2.22ms  tot:   7.22ms functools.py:961:__get__                           <-  75% ops.py:65:__hash__
n:       4  tm:   2.15ms  tot:   4.80ms cstyle.py:90:uops_to_cstyle                        <- 100% ops_hip.py:18:render
n:       8  tm:   2.06ms  tot:   2.06ms ~:0:<method 'execute' of 'sqlite3.Cursor' objects> <-  69% helpers.py:138:diskcache_get
n:       4  tm:   2.01ms  tot:  18.22ms uops.py:50:fix_loop_scope                          <- 100% linearizer.py:396:uoptimize
n:    2036  tm:   2.01ms  tot:   2.02ms ~:0:<method 'index' of 'list' objects>             <-  95% linearizer.py:446:uop
n:    1555  tm:   1.94ms  tot:   4.53ms symbolic.py:320:<lambda>                           <- 100% symbolic.py:14:render
n:    1400  tm:   1.85ms  tot:   1.85ms ~:0:<method 'union' of 'set' objects>              <-  98% linearizer.py:404:get_recursive_parents
n:     130  tm:   1.83ms  tot:   2.00ms ops_hip.py:46:__call__                             <- 100% device.py:298:__call__
n:      12  tm:   1.83ms  tot:  29.29ms linearizer.py:69:global_load                       <-  84% linearizer.py:315:<dictcomp>
n:     405  tm:   1.82ms  tot:   1.82ms ~:0:<built-in method builtins.sorted>              <-  88% linearizer.py:396:uoptimize
n:    1154  tm:   1.79ms  tot:  16.57ms linearizer.py:39:uop_alu_idx                       <-  57% linearizer.py:60:<lambda>
n:       4  tm:   1.70ms  tot:   3.52ms uops.py:25:get_recursive_children                  <- 100% linearizer.py:396:uoptimize
n:      20  tm:   1.70ms  tot: 308.39ms realize.py:42:run_schedule                         <- 100% tensor.py:115:realize
n:    1486  tm:   1.69ms  tot:   2.82ms shapetracker.py:171:simplify                       <-  74% shapetracker.py:98:__add__
n:   14887  tm:   1.56ms  tot:   1.56ms ~:0:<built-in method builtins.len>                 <-  17% linearizer.py:446:uop
n:     475  tm:   1.47ms  tot:  16.00ms tensor.py:30:apply                                 <-  31% tensor.py:303:reshape
n:    4632  tm:   1.42ms  tot:   5.94ms <string>:2:__hash__                                <-  30% lazy.py:156:_recursive_lazyop
n:     300  tm:   1.38ms  tot:  18.89ms lazy.py:193:_recursive_schedule                    <-  83% lazy.py:208:<genexpr>
n:    2695  tm:   1.37ms  tot:   2.96ms shapetracker.py:116:size                           <-  38% lazy.py:18:create_lazybuffer
n:     655  tm:   1.37ms  tot:   2.38ms helpers.py:33:merge_dicts                          <-  78% shapetracker.py:131:unbind
n:    7165  tm:   1.35ms  tot:   1.35ms lazy.py:52:base                                    <-  34% lazy.py:211:_recurse_lb
n:    2102  tm:   1.33ms  tot:   6.32ms ~:0:<built-in method builtins.all>                 <-  35% ops.py:55:cached_compare
n:     240  tm:   1.31ms  tot:   6.82ms lazy.py:105:e                                      <-  18% mlops.py:113:forward
n:    5590  tm:   1.13ms  tot:   1.41ms tensor.py:274:_deepwalk                            <-  94% tensor.py:274:_deepwalk
n:      20  tm:   1.10ms  tot:  26.34ms lazy.py:245:create_schedule                        <- 100% lazy.py:79:schedule
n:    2281  tm:   1.08ms  tot:   1.83ms enum.py:396:__contains__                           <-  24% lazy.py:245:create_schedule
n:       5  tm:   1.04ms  tot:  14.31ms tensor.py:282:backward                             
n:    2452  tm:   1.04ms  tot:   1.04ms uops.py:31:<listcomp>                              <- 100% uops.py:25:get_recursive_children
n:     580  tm:   1.01ms  tot:   7.73ms lazy.py:141:_view                                  <-  56% lazy.py:146:reshape
n:     520  tm:   0.91ms  tot:   3.80ms shapetracker.py:131:unbind                         <-  77% lazy.py:156:_recursive_lazyop
n:     130  tm:   0.81ms  tot:   4.16ms device.py:298:__call__                             <- 100% device.py:44:exec
n:      85  tm:   0.76ms  tot:   5.13ms tensor.py:787:_broadcasted                         <-  51% tensor.py:820:mul
n:    1130  tm:   0.75ms  tot:  12.62ms lazy.py:189:<genexpr>                              <- 100% lazy.py:156:_recursive_lazyop
n:     358  tm:   0.75ms  tot:   7.10ms symbolic.py:324:<listcomp>                         <- 100% symbolic.py:324:<lambda>
n:     135  tm:   0.75ms  tot: 288.66ms realize.py:24:lower_schedule_item                  <- 100% realize.py:42:run_schedule
n:     330  tm:   0.71ms  tot:   1.62ms tensor.py:59:__init__                              <-  73% tensor.py:292:<listcomp>
n:    1555  tm:   0.71ms  tot:   0.85ms symbolic.py:307:sym_render                         <- 100% symbolic.py:320:<lambda>
n:     422  tm:   0.69ms  tot:   1.26ms shapetracker.py:184:reshape                        <-  73% lazy.py:146:reshape
n:     475  tm:   0.68ms  tot:   0.95ms tensor.py:21:__init__                              <- 100% tensor.py:30:apply
n:    1229  tm:   0.65ms  tot:   4.25ms linearizer.py:406:<listcomp>                       <- 100% linearizer.py:404:get_recursive_parents
n:    1758  tm:   0.60ms  tot:   0.60ms symbolic.py:318:<lambda>                           <- 100% symbolic.py:14:render
n:     950  tm:   0.59ms  tot:   0.62ms ~:0:<built-in method builtins.max>                 <-  86% tensor.py:449:<genexpr>
n:     473  tm:   0.59ms  tot:   3.34ms shapetracker.py:98:__add__                         <-  78% lazy.py:156:_recursive_lazyop
n:    1740  tm:   0.58ms  tot:   3.90ms ops.py:59:<genexpr>                                <- 100% ~:0:<built-in method builtins.all>
n:     650  tm:   0.58ms  tot:   0.85ms shapetracker.py:107:from_shape                     <-  35% lazy.py:105:e
n:    1091  tm:   0.56ms  tot:   5.87ms ops.py:65:__hash__                                 <-  79% ~:0:<built-in method builtins.hash>
n:     983  tm:   0.56ms  tot:   2.11ms ~:0:<method 'pop' of 'dict' objects>               <- 100% lazy.py:46:__del__
n:     135  tm:   0.56ms  tot:   1.21ms device.py:75:__init__                              <- 100% realize.py:42:run_schedule
n:     135  tm:   0.55ms  tot:  14.44ms device.py:44:exec                                  <- 100% realize.py:42:run_schedule
n:    2864  tm:   0.54ms  tot:   0.54ms shapetracker.py:113:shape                          <-  38% lazy.py:28:__init__
n:     863  tm:   0.52ms  tot:  14.93ms ~:0:<built-in method _functools.reduce>            <-  65% helpers.py:13:prod
n:     567  tm:   0.52ms  tot:  10.31ms linearizer.py:60:<lambda>                          <- 100% symbolic.py:14:render
n:     358  tm:   0.52ms  tot:   7.87ms symbolic.py:324:<lambda>                           <- 100% symbolic.py:14:render
n:     702  tm:   0.51ms  tot:   3.74ms linearizer.py:44:const                             <-  99% linearizer.py:59:<lambda>
n:       4  tm:   0.51ms  tot:   1.09ms uops.py:70:uops_type_verify                        <- 100% linearizer.py:396:uoptimize
n:       4  tm:   0.49ms  tot:  25.35ms linearizer.py:396:uoptimize                        <- 100% linearizer.py:163:linearize
n:    2452  tm:   0.48ms  tot:   0.48ms ~:0:<method 'intersection' of 'set' objects>       <- 100% uops.py:25:get_recursive_children
n:     866  tm:   0.48ms  tot:   0.56ms symbolic.py:145:__init__                           <-  67% linearizer.py:39:uop_alu_idx
n:      61  tm:   0.46ms  tot:   3.45ms shapetracker.py:85:_expr_view                      <- 100% shapetracker.py:154:expr_idxs
n:     983  tm:   0.46ms  tot:   2.57ms lazy.py:46:__del__                                 <-  56% realize.py:42:run_schedule
n:     160  tm:   0.45ms  tot:   4.59ms tensor.py:303:reshape                              <-  23% tensor.py:602:_pool
n:     957  tm:   0.45ms  tot:   5.37ms ops.py:63:hash                                     <- 100% functools.py:961:__get__
n:      63  tm:   0.44ms  tot:   2.31ms symbolic.py:91:sum                                 <-  97% shapetracker.py:85:_expr_view
n:       5  tm:   0.43ms  tot:   5.16ms ops_hip.py:119:copyin                              <- 100% device.py:95:copyin
n:    4337  tm:   0.43ms  tot:   0.43ms ~:0:<built-in method builtins.id>                  <-  87% ops.py:55:cached_compare
n:     190  tm:   0.42ms  tot:   2.62ms tensor.py:307:expand                               <-  86% tensor.py:787:_broadcasted
n:      20  tm:   0.42ms  tot:   5.98ms tensor.py:602:_pool                                <-  60% tensor.py:645:conv2d
n:      70  tm:   0.42ms  tot:   1.57ms tensor.py:312:shrink                               <-  86% tensor.py:447:slice
n:    2500  tm:   0.40ms  tot:   0.40ms tensor.py:103:shape                                <-  24% tensor.py:282:backward
n:     740  tm:   0.40ms  tot:   0.49ms shapetracker.py:110:contiguous                     <-  76% lazy.py:141:_view
n:      60  tm:   0.39ms  tot:   2.64ms tensor.py:447:slice                                <-  84% tensor.py:602:_pool
n:    3521  tm:   0.38ms  tot:   0.47ms ~:0:<method 'add' of 'set' objects>                <-  36% uops.py:25:get_recursive_children
n:      90  tm:   0.38ms  tot:   3.09ms lazy.py:126:r                                      <-  41% mlops.py:170:backward
n:    1370  tm:   0.37ms  tot:   0.63ms helpers.py:22:<genexpr>                            <- 100% ~:0:<built-in method builtins.all>
n:     520  tm:   0.37ms  tot:   0.73ms shapetracker.py:132:<listcomp>                     <- 100% shapetracker.py:131:unbind
n:     721  tm:   0.36ms  tot:   0.70ms helpers.py:13:prod                                 <-  60% lazy.py:211:_recurse_lb
n:     910  tm:   0.35ms  tot:   0.44ms symbolic.py:308:sym_infer                          <-  48% device.py:294:<listcomp>
n:    2914  tm:   0.34ms  tot:   0.34ms ~:0:<method 'append' of 'list' objects>            <-  19% uops.py:50:fix_loop_scope
n:     587  tm:   0.33ms  tot:  14.40ms linearizer.py:65:<lambda>                          <- 100% ~:0:<built-in method _functools.reduce>
n:     229  tm:   0.33ms  tot:  19.14ms helpers.py:28:<listcomp>                           <- 100% helpers.py:28:flatten
n:      10  tm:   0.32ms  tot:   1.50ms tensor.py:349:__getitem__                          <- 100% tensor.py:225:randn
n:     655  tm:   0.32ms  tot:   0.38ms helpers.py:34:<listcomp>                           <- 100% helpers.py:33:merge_dicts
n:     346  tm:   0.31ms  tot:   0.31ms dtype.py:15:__repr__                               <- 100% linearizer.py:69:global_load
n:     674  tm:   0.31ms  tot:   0.31ms <string>:2:__init__                                <- 100% linearizer.py:446:uop
n:     270  tm:   0.30ms  tot:   1.13ms tensor.py:292:<listcomp>                           <- 100% tensor.py:282:backward
n:     137  tm:   0.30ms  tot:   0.67ms kernel.py:157:first_reduce                         <-  28% kernel.py:473:hand_coded_optimizations
n:     600  tm:   0.29ms  tot:   0.29ms device.py:23:canonicalize                          <-  53% device.py:24:__getitem__
n:     655  tm:   0.28ms  tot:   0.33ms helpers.py:35:<dictcomp>                           <- 100% helpers.py:33:merge_dicts
n:     480  tm:   0.28ms  tot:   1.17ms helpers.py:22:all_same                             <- 100% lazy.py:105:e
n:     415  tm:   0.27ms  tot:  15.77ms lazy.py:208:<genexpr>                              <- 100% helpers.py:28:<listcomp>
n:      18  tm:   0.27ms  tot:   1.77ms linearizer.py:476:ast_parse                        <-  94% linearizer.py:163:linearize
n:     135  tm:   0.27ms  tot:   0.55ms device.py:85:__del__                               <-  53% realize.py:42:run_schedule
n:      40  tm:   0.27ms  tot:   2.98ms tensor.py:528:_reduce                              <-  74% tensor.py:535:sum
n:     694  tm:   0.26ms  tot:   3.96ms linearizer.py:59:<lambda>                          <- 100% symbolic.py:14:render
n:     130  tm:   0.26ms  tot:   0.36ms .
----------------------------------------------------------------------
Ran 1 test in 2.513s

OK
device.py:53:update_stats                          <- 100% device.py:298:__call__
n:     420  tm:   0.25ms  tot:   0.42ms symbolic.py:162:__init__                           <-  54% symbolic.py:43:__mul__
n:     980  tm:   0.25ms  tot:   0.25ms lazy.py:22:<genexpr>                               <- 100% lazy.py:18:create_lazybuffer
n:       4  tm:   0.24ms  tot:   3.60ms kernel.py:473:hand_coded_optimizations             <- 100% device.py:323:get_linearizer
forward pass:  11.336 ms, 0.54x off baseline 21.182 ms
backward pass: 63.670 ms, 1.09x off baseline 58.428 ms

test_nn.py

....s..........
----------------------------------------------------------------------
Ran 15 tests in 5.124s

OK (skipped=1)

test_ops.py

test_abs (__main__.TestOps) ... ok
test_acosh (__main__.TestOps) ... ok
test_add (__main__.TestOps) ... ok
test_add3 (__main__.TestOps) ... ok
test_arange (__main__.TestOps) ... ok
test_arange_big (__main__.TestOps) ... ok
test_argmax (__main__.TestOps) ... ok
test_argmin (__main__.TestOps) ... ok
test_asinh (__main__.TestOps) ... ok
test_asymmetric_padding_conv1d (__main__.TestOps) ... ok
test_asymmetric_padding_conv2d (__main__.TestOps) ... ok
test_atanh (__main__.TestOps) ... ok
test_avgpool2d (__main__.TestOps) ... ok
test_bias_conv_transpose2d (__main__.TestOps) ... ok
test_biased_conv2d (__main__.TestOps) ... ok
test_big_gemm (__main__.TestOps) ... ok
test_binary_crossentropy (__main__.TestOps) ... ok
test_broadcast_full (__main__.TestOps) ... ok
test_broadcast_partial (__main__.TestOps) ... 
testing                               [(45, 65)]   torch/tinygrad fp: 1.10 / 274.38 ms  bp: 2.97 / 72.02 ms 
testing                                     [()]   torch/tinygrad fp: 0.05 / 31.24 ms  bp: 0.82 / 35.69 ms 
testing                               [(45, 65)]   torch/tinygrad fp: 0.09 / 41.45 ms  bp: 0.42 / 43.49 ms 
testing                               [(45, 65)]   torch/tinygrad fp: 0.05 / 0.72 ms  bp: 0.30 / 0.96 ms 
testing                               [(45, 65)]   torch/tinygrad fp: 0.03 / 0.56 ms  bp: 0.15 / 0.90 ms 
testing                     [(45, 68), (45, 68)]   torch/tinygrad fp: 0.01 / 31.67 ms  bp: 0.38 / 62.31 ms 
testing                     [(45, 68), (45, 68)]   torch/tinygrad fp: 0.03 / 0.56 ms  bp: 0.41 / 1.16 ms 
testing                                 [(), ()]   torch/tinygrad fp: 0.02 / 28.57 ms  bp: 0.35 / 31.53 ms 
testing           [(45, 65), (45, 65), (45, 65)]   torch/tinygrad fp: 0.05 / 35.83 ms  bp: 0.50 / 35.02 ms 
testing                                       []   torch/tinygrad fp: 1.00 / 9.23 ms  bp: nan / nan ms 
testing                                       []   torch/tinygrad fp: 0.03 / 29.04 ms  bp: nan / nan ms 
testing                                       []   torch/tinygrad fp: 0.05 / 31.99 ms  bp: nan / nan ms 
testing                                       []   torch/tinygrad fp: 0.06 / 30.63 ms  bp: nan / nan ms 
testing                                       []   torch/tinygrad fp: 0.05 / 44.94 ms  bp: nan / nan ms 
testing                               [(10, 20)]   torch/tinygrad fp: 0.04 / 124.22 ms  bp: nan / nan ms 
testing                               [(10, 20)]   torch/tinygrad fp: 0.54 / 83.47 ms  bp: nan / nan ms 
testing                               [(10, 20)]   torch/tinygrad fp: 0.04 / 135.08 ms  bp: nan / nan ms 
testing                               [(10, 20)]   torch/tinygrad fp: 0.03 / 2.52 ms  bp: nan / nan ms 
testing                               [(10, 20)]   torch/tinygrad fp: 0.07 / 82.27 ms  bp: nan / nan ms 
testing                               [(10, 20)]   torch/tinygrad fp: 0.05 / 83.28 ms  bp: nan / nan ms 
testing                               [(10, 20)]   torch/tinygrad fp: 0.04 / 91.50 ms  bp: nan / nan ms 
testing                               [(10, 20)]   torch/tinygrad fp: 0.04 / 2.54 ms  bp: nan / nan ms 
testing                               [(45, 65)]   torch/tinygrad fp: 0.18 / 35.88 ms  bp: 0.38 / 45.25 ms 
testing                               [(45, 65)]   torch/tinygrad fp: 0.06 / 0.71 ms  bp: 0.30 / 0.95 ms 
testing                               [(45, 65)]   torch/tinygrad fp: 0.03 / 0.55 ms  bp: 0.15 / 0.90 ms 
testing                   [(1, 1, 3), (1, 1, 2)]   torch/tinygrad fp: 3.76 / 32.43 ms  bp: 1.16 / 166.36 ms 
testing                   [(1, 1, 3), (1, 1, 2)]   torch/tinygrad fp: 0.69 / 1.24 ms  bp: 0.55 / 2.76 ms 
testing                   [(1, 1, 4), (1, 1, 2)]   torch/tinygrad fp: 0.08 / 34.08 ms  bp: 0.57 / 175.78 ms 
testing                   [(1, 1, 4), (1, 1, 2)]   torch/tinygrad fp: 0.73 / 1.93 ms  bp: 0.36 / 1.32 ms 
testing                   [(1, 1, 3), (1, 1, 2)]   torch/tinygrad fp: 0.07 / 37.77 ms  bp: 0.58 / 222.52 ms 
testing                   [(1, 1, 3), (1, 1, 2)]   torch/tinygrad fp: 0.61 / 1.13 ms  bp: 0.34 / 1.33 ms 
testing                   [(1, 1, 4), (1, 1, 2)]   torch/tinygrad fp: 0.07 / 34.23 ms  bp: 0.54 / 176.36 ms 
testing                   [(1, 1, 4), (1, 1, 2)]   torch/tinygrad fp: 0.72 / 1.08 ms  bp: 0.51 / 2.35 ms 
testing                   [(1, 1, 3), (1, 1, 2)]   torch/tinygrad fp: 0.12 / 35.00 ms  bp: 0.54 / 32.13 ms 
testing                   [(1, 1, 3), (1, 1, 2)]   torch/tinygrad fp: 0.26 / 1.04 ms  bp: 0.49 / 2.33 ms 
testing                   [(1, 1, 4), (1, 1, 2)]   torch/tinygrad fp: 0.12 / 36.29 ms  bp: 0.93 / 39.74 ms 
testing                   [(1, 1, 4), (1, 1, 2)]   torch/tinygrad fp: 0.29 / 1.17 ms  bp: 0.52 / 2.34 ms 
testing             [(1, 1, 3, 3), (1, 1, 2, 2)]   torch/tinygrad fp: 0.31 / 43.43 ms  bp: 0.53 / 188.32 ms 
testing             [(1, 1, 3, 3), (1, 1, 2, 2)]   torch/tinygrad fp: 0.62 / 1.11 ms  bp: 0.34 / 1.34 ms 
testing             [(1, 1, 4, 4), (1, 1, 2, 2)]   torch/tinygrad fp: 0.07 / 46.20 ms  bp: 0.69 / 214.38 ms 
testing             [(1, 1, 4, 4), (1, 1, 2, 2)]   torch/tinygrad fp: 0.71 / 1.13 ms  bp: 0.49 / 2.42 ms 
testing             [(1, 1, 3, 3), (1, 1, 2, 2)]   torch/tinygrad fp: 0.07 / 52.55 ms  bp: 0.69 / 238.50 ms 
testing             [(1, 1, 3, 3), (1, 1, 2, 2)]   torch/tinygrad fp: 0.80 / 1.94 ms  bp: 0.37 / 1.31 ms 
testing             [(1, 1, 4, 4), (1, 1, 2, 2)]   torch/tinygrad fp: 0.07 / 57.95 ms  bp: 0.73 / 273.45 ms 
testing             [(1, 1, 4, 4), (1, 1, 2, 2)]   torch/tinygrad fp: 0.74 / 1.98 ms  bp: 0.36 / 1.32 ms 
testing             [(1, 1, 3, 3), (1, 1, 2, 2)]   torch/tinygrad fp: 0.07 / 49.75 ms  bp: 0.70 / 231.92 ms 
testing             [(1, 1, 3, 3), (1, 1, 2, 2)]   torch/tinygrad fp: 0.60 / 1.58 ms  bp: 0.51 / 1.97 ms 
testing             [(1, 1, 4, 4), (1, 1, 2, 2)]   torch/tinygrad fp: 0.07 / 54.22 ms  bp: 0.70 / 247.08 ms 
testing             [(1, 1, 4, 4), (1, 1, 2, 2)]   torch/tinygrad fp: 0.87 / 1.14 ms  bp: 0.51 / 2.39 ms 
testing                               [(45, 65)]   torch/tinygrad fp: 0.06 / 34.52 ms  bp: 0.87 / 44.86 ms 
testing                               [(45, 65)]   torch/tinygrad fp: 0.04 / 1.40 ms  bp: 0.43 / 1.75 ms 
testing                               [(45, 65)]   torch/tinygrad fp: 0.04 / 1.37 ms  bp: 0.16 / 2.04 ms 
testing                       [(32, 2, 111, 28)]   torch/tinygrad fp: 1.88 / 39.39 ms  bp: 1.04 / 68.19 ms 
testing                       [(32, 2, 111, 28)]   torch/tinygrad fp: 0.11 / 47.78 ms  bp: 0.75 / 68.58 ms 
testing                       [(32, 2, 111, 28)]   torch/tinygrad fp: 0.25 / 46.25 ms  bp: 0.92 / 66.66 ms 
testing                       [(32, 2, 111, 28)]   torch/tinygrad fp: 0.13 / 65.93 ms  bp: 0.55 / 65.15 ms 
testing                       [(32, 2, 111, 28)]   torch/tinygrad fp: 0.15 / 44.11 ms  bp: 0.84 / 69.02 ms 
testing       [(2, 4, 9, 9), (4, 4, 3, 3), (4,)]   torch/tinygrad fp: 9.65 / 88.07 ms  bp: 8.84 / 588.17 ms 
testing       [(1, 8, 5, 5), (8, 8, 1, 1), (8,)]   torch/tinygrad fp: 0.73 / 84.25 ms  bp: 1.05 / 319.61 ms 
testing                 [(256, 256), (256, 256)]   torch/tinygrad fp: 0.43 / 58.65 ms  bp: 1.75 / 179.26 ms 
testing                     [(32, 10), (32, 10)]   torch/tinygrad fp: 0.69 / 48.21 ms  bp: 1.82 / 131.25 ms 
testing                     [(32, 10), (32, 10)]   torch/tinygrad fp: 0.78 / 48.61 ms  bp: 0.44 / 93.52 ms 
testing                     [(32, 10), (32, 10)]   torch/tinygrad fp: 0.91 / 4.41 ms  bp: 0.32 / 2.52 ms 
testing                     [(32, 10), (32, 10)]   torch/tinygrad fp: 0.07 / 2.55 ms  bp: 0.29 / 2.77 ms 
testing         ((5, 13, 24, 16), (5, 1, 24, 1))   torch/tinygrad fp: 0.04 / 34.86 ms  bp: 0.60 / 110.37 ms 
testing       ((1, 3, 1, 7, 1), (2, 1, 5, 1, 8))   torch/tinygrad fp: 0.05 / 38.69 ms  bp: 0.37 / 134.94 ms 
testing         ((5, 13, 24, 16), (5, 1, 24, 1))   torch/tinygrad fp: 0.12 / 35.86 ms  bp: 0.43 / 44.61 ms 
testing       ((1, 3, 1, 7, 1), (2, 1, 5, 1, 8))   torch/tinygrad fp: 0.05 / 36.51 ms  bp: 0.53 / 43.43 ms 
testing         ((5, 13, 24, 16), (5, 1, 24, 1))   torch/tinygrad fp: 0.11 / 36.20 ms  bp: 0.43 / 92.23 ms 
testing       ((1, 3, 1, 7, 1), (2, 1, 5, 1, 8))   torch/tinygrad fp: 0.04 / 38.25 ms  bp: 0.52 / 124.60 ms 
testing         ((5, 13, 24, 16), (5, 1, 24, 1))   torch/tinygrad fp: 0.07 / 34.09 ms  bp: 0.47 / 102.60 ms 
testing       ((1, 3, 1, 7, 1), (2, 1, 5, 1, 8))   torch/tinygrad fp: 0.05 / 38.71 ms  bp: 0.55 / 110.68 ms 
testing         ((5, 13, 24, 16), (5, 1, 24, 1))   torch/tinygrad fp: 0.26 / 181.80 ms  bp: 1.61 / 608.16 ms 
testing       ((1, 3, 1, 7, 1), (2, 1, 5, 1, 8))   torch/tinygrad fp: 0.10 / 285.05 ms  bp: 0.74 / 639.73 ms 
testing         ((1, 32, 32, 32), (1, 32, 1, 1))   torch/tinygrad fp: 0.05 / 42.04 ms  bp: 1.36 / 109.44 ms 
testing  ((5, 13, 24, 16, 2), (1, 13, 24, 1, 1))   torch/tinygrad fp: 0.06 / 38.75 ms  bp: 0.96 / 140.31 ms ok
test_broadcast_simple (__main__.TestOps) ... ok
test_broadcastdot (__main__.TestOps) ... ok
test_broadcasted_add (__main__.TestOps) ... ok
test_broadcasted_add_2 (__main__.TestOps) ... ok
test_cat (__main__.TestOps) ... ok
test_ceil (__main__.TestOps) ... ok
test_celu (__main__.TestOps) ... ok
test_chunk (__main__.TestOps) ... ok
test_clip (__main__.TestOps) ... ok
test_cmp_eq (__main__.TestOps) ... ok
test_cmp_eq_backwards (__main__.TestOps) ... ok
test_cmp_ge (__main__.TestOps) ... ok
test_cmp_gt (__main__.TestOps) ... 
testing                         ((4, 1), (4, 5))   torch/tinygrad fp: 0.03 / 32.05 ms  bp: 0.35 / 66.01 ms 
testing                         ((1, 4), (5, 4))   torch/tinygrad fp: 0.03 / 31.42 ms  bp: 0.35 / 65.41 ms 
testing         ((1, 32, 32, 32), (1, 32, 1, 1))   torch/tinygrad fp: 0.05 / 34.31 ms  bp: 0.89 / 41.59 ms 
testing  ((5, 13, 24, 16, 2), (1, 13, 24, 1, 1))   torch/tinygrad fp: 0.07 / 36.52 ms  bp: 0.83 / 71.04 ms 
testing                         ((4, 1), (4, 5))   torch/tinygrad fp: 0.03 / 31.60 ms  bp: 0.35 / 32.79 ms 
testing                         ((1, 4), (5, 4))   torch/tinygrad fp: 0.04 / 30.99 ms  bp: 0.43 / 32.65 ms 
testing         ((1, 32, 32, 32), (1, 32, 1, 1))   torch/tinygrad fp: 0.05 / 33.67 ms  bp: 1.01 / 79.26 ms 
testing  ((5, 13, 24, 16, 2), (1, 13, 24, 1, 1))   torch/tinygrad fp: 0.07 / 33.91 ms  bp: 0.97 / 115.20 ms 
testing                         ((4, 1), (4, 5))   torch/tinygrad fp: 0.03 / 31.67 ms  bp: 0.35 / 67.09 ms 
testing                         ((1, 4), (5, 4))   torch/tinygrad fp: 0.04 / 31.32 ms  bp: 0.35 / 66.97 ms 
testing         ((1, 32, 32, 32), (1, 32, 1, 1))   torch/tinygrad fp: 0.05 / 35.09 ms  bp: 0.94 / 81.19 ms 
testing  ((5, 13, 24, 16, 2), (1, 13, 24, 1, 1))   torch/tinygrad fp: 0.07 / 36.14 ms  bp: 0.92 / 144.17 ms 
testing                         ((4, 1), (4, 5))   torch/tinygrad fp: 0.05 / 36.88 ms  bp: 0.50 / 82.38 ms 
testing                         ((1, 4), (5, 4))   torch/tinygrad fp: 0.03 / 36.76 ms  bp: 0.48 / 75.85 ms 
testing         ((1, 32, 32, 32), (1, 32, 1, 1))   torch/tinygrad fp: 0.41 / 180.36 ms  bp: 1.99 / 283.26 ms 
testing  ((5, 13, 24, 16, 2), (1, 13, 24, 1, 1))   torch/tinygrad fp: 0.39 / 173.64 ms  bp: 2.62 / 1090.50 ms 
testing                         ((4, 1), (4, 5))   torch/tinygrad fp: 0.04 / 166.98 ms  bp: 0.42 / 571.41 ms 
testing                         ((1, 4), (5, 4))   torch/tinygrad fp: 0.04 / 208.33 ms  bp: 0.59 / 571.61 ms 
testing                      [(45, 65), (45, 1)]   torch/tinygrad fp: 0.09 / 40.35 ms  bp: 0.49 / 88.63 ms 
testing                           [(45, 65), ()]   torch/tinygrad fp: 0.03 / 36.81 ms  bp: 0.49 / 75.74 ms 
testing                 [(10, 45, 65), (65, 45)]   torch/tinygrad fp: 1.01 / 54.18 ms  bp: 1.61 / 155.03 ms 
testing                      [(45, 65), (45, 1)]   torch/tinygrad fp: 0.05 / 35.61 ms  bp: 0.45 / 40.84 ms 
testing                           [(45, 65), ()]   torch/tinygrad fp: 0.04 / 34.02 ms  bp: 0.47 / 40.82 ms 
testing                        [(45, 65), (65,)]   torch/tinygrad fp: 0.05 / 35.53 ms  bp: 0.46 / 36.74 ms 
testing  [(45, 65, 9), (45, 65, 9), (45, 65, 9)]   torch/tinygrad fp: 0.58 / 44.99 ms  bp: 1.87 / 65.84 ms 
testing  [(45, 65, 9), (45, 65, 9), (45, 65, 9)]   torch/tinygrad fp: 0.14 / 40.29 ms  bp: 1.35 / 33.46 ms 
testing  [(45, 65, 9), (45, 65, 9), (45, 65, 9)]   torch/tinygrad fp: 0.10 / 40.47 ms  bp: 1.84 / 31.34 ms 
testing  [(45, 65, 9), (45, 65, 9), (45, 65, 9)]   torch/tinygrad fp: 0.13 / 1.92 ms  bp: 1.05 / 0.73 ms 
testing  [(45, 65, 9), (45, 65, 9), (45, 65, 9)]   torch/tinygrad fp: 0.07 / 0.82 ms  bp: 1.12 / 0.70 ms 
testing     [(45, 0, 9), (45, 0, 9), (45, 0, 9)]   torch/tinygrad fp: 0.01 / 0.24 ms  bp: 0.15 / 0.45 ms 
testing     [(45, 0, 9), (45, 1, 9), (45, 2, 9)]   torch/tinygrad fp: 0.03 / 36.09 ms  bp: 0.43 / 63.46 ms 
testing     [(45, 0, 9), (45, 0, 9), (45, 0, 9)]   torch/tinygrad fp: 0.07 / 0.20 ms  bp: 0.40 / 0.66 ms 
testing                               [(45, 35)]   torch/tinygrad fp: 0.07 / 33.66 ms  bp: nan / nan ms 
testing                                     None   torch/tinygrad fp: 0.02 / 31.26 ms  bp: nan / nan ms 
testing                               [(45, 65)]   torch/tinygrad fp: 0.13 / 41.93 ms  bp: 0.53 / 40.49 ms 
testing                                     [()]   torch/tinygrad fp: 0.04 / 29.13 ms  bp: 0.31 / 32.11 ms 
testing                               [(45, 65)]   torch/tinygrad fp: 0.05 / 37.48 ms  bp: 0.33 / 41.11 ms 
testing                                     [()]   torch/tinygrad fp: 0.04 / 29.21 ms  bp: 0.30 / 31.25 ms 
testing                               [(45, 65)]   torch/tinygrad fp: 0.05 / 36.46 ms  bp: 0.33 / 41.53 ms 
testing                                     [()]   torch/tinygrad fp: 0.04 / 28.87 ms  bp: 0.31 / 31.15 ms 
testing                               [(45, 65)]   torch/tinygrad fp: 0.05 / 37.68 ms  bp: 0.33 / 40.90 ms 
testing                                     [()]   torch/tinygrad fp: 0.04 / 30.01 ms  bp: 0.30 / 30.41 ms 
testing                                       []   torch/tinygrad fp: 0.00 / 32.14 ms  bp: nan / nan ms 
testing                                       []   torch/tinygrad fp: 0.00 / 0.02 ms  bp: nan / nan ms 
testing                                       []   torch/tinygrad fp: 0.00 / 0.02 ms  bp: nan / nan ms 
testing                                       []   torch/tinygrad fp: 0.00 / 0.02 ms  bp: nan / nan ms 
testing                                       []   torch/tinygrad fp: 0.00 / 0.02 ms  bp: nan / nan ms 
testing                                       []   torch/tinygrad fp: 0.00 / 0.22 ms  bp: nan / nan ms 
testing                                       []   torch/tinygrad fp: 0.00 / 0.02 ms  bp: nan / nan ms 
testing                                       []   torch/tinygrad fp: 0.00 / 0.01 ms  bp: nan / nan ms 
testing                                       []   torch/tinygrad fp: 0.00 / 0.01 ms  bp: nan / nan ms 
testing                                       []   torch/tinygrad fp: 0.00 / 0.19 ms  bp: nan / nan ms 
testing                                       []   torch/tinygrad fp: 0.00 / 0.02 ms  bp: nan / nan ms 
testing                                       []   torch/tinygrad fp: 0.00 / 0.02 ms  bp: nan / nan ms 
testing                                       []   torch/tinygrad fp: 0.00 / 0.21 ms  bp: nan / nan ms 
testing                                       []   torch/tinygrad fp: 0.00 / 0.02 ms  bp: nan / nan ms 
testing                                       []   torch/tinygrad fp: 0.00 / 0.02 ms  bp: nan / nan ms 
testing                               [(45, 65)]   torch/tinygrad fp: 0.05 / 34.19 ms  bp: 0.37 / 44.19 ms 
testing                               [(45, 65)]   torch/tinygrad fp: 0.04 / 39.49 ms  bp: 0.51 / 42.30 ms 
testing                               [(45, 65)]   torch/tinygrad fp: 0.04 / 41.17 ms  bp: 0.51 / 43.56 ms 
testing                               [(45, 65)]   torch/tinygrad fp: 0.04 / 41.14 ms  bp: 0.40 / 44.57 ms 
testing                               [(45, 65)]   torch/tinygrad fp: 0.04 / 39.28 ms  bp: 0.51 / 41.32 ms 
testing                               [(45, 65)]   torch/tinygrad fp: 0.04 / 38.17 ms  bp: 0.51 / 43.36 ms 
testing                   [(3, 4, 5), (3, 4, 5)]   torch/tinygrad fp: 0.05 / 37.87 ms  bp: nan / nan ms 
testing                        [(3, 4, 5), (5,)]   torch/tinygrad fp: 0.03 / 33.15 ms  bp: nan / nan ms 
testing                        [(5,), (3, 4, 5)]   torch/tinygrad fp: 0.02 / 32.50 ms  bp: nan / nan ms 
testing                                     None   torch/tinygrad fp: 0.03 / 31.70 ms  bp: nan / nan ms 
testing                                     None   torch/tinygrad fp: 0.07 / 31.52 ms  bp: nan / nan ms 
testing                                     None   torch/tinygrad fp: 0.06 / 33.83 ms  bp: nan / nan ms 
testing                   [(3, 4, 5), (3, 4, 5)]   torch/tinygrad fp: 0.04 / 37.61 ms  bp: nan / nan ms 
testing                        [(3, 4, 5), (5,)]   torch/tinygrad fp: 0.02 / 30.90 ms  bp: nan / nan ms 
testing                        [(5,), (3, 4, 5)]   torch/tinygrad fp: 0.02 / 35.01 ms  bp: nan / nan ms 
testing                                     None   torch/tinygrad fp: 0.03 / 32.34 ms  bp: nan / nan ms 
testing                                     None   torch/tinygrad fp: 0.07 / 33.37 ms  bp: nan / nan ms 
testing                                     None   torch/tinygrad fp: 0.02 / 29.35 ms  bp: nan / nan ms 
testing                                     None   torch/tinygrad fp: 0.08 / 32.75 ms  bp: nan / nan ms ok
test_cmp_le (__main__.TestOps) ... ok
test_cmp_lt (__main__.TestOps) ... ok
test_cmp_lt_backwards (__main__.TestOps) ... ok
test_conv1d (__main__.TestOps) ... ok
test_conv2d (__main__.TestOps) ... ok
test_conv2d_bs_1_cin_1 (__main__.TestOps) ... ok
test_conv2d_bs_4_cin_1 (__main__.TestOps) ... ok
test_conv2d_bs_4_cin_3 (__main__.TestOps) ... 
testing                   [(3, 4, 5), (3, 4, 5)]   torch/tinygrad fp: 0.05 / 32.47 ms  bp: nan / nan ms 
testing                        [(3, 4, 5), (5,)]   torch/tinygrad fp: 0.03 / 34.57 ms  bp: nan / nan ms 
testing                        [(5,), (3, 4, 5)]   torch/tinygrad fp: 0.03 / 34.95 ms  bp: nan / nan ms 
testing                                     None   torch/tinygrad fp: 0.03 / 31.43 ms  bp: nan / nan ms 
testing                                     None   torch/tinygrad fp: 0.08 / 33.50 ms  bp: nan / nan ms 
testing                                     None   torch/tinygrad fp: 0.02 / 34.69 ms  bp: nan / nan ms 
testing                                     None   torch/tinygrad fp: 0.10 / 30.24 ms  bp: nan / nan ms 
testing                   [(3, 4, 5), (3, 4, 5)]   torch/tinygrad fp: 0.02 / 0.69 ms  bp: nan / nan ms 
testing                        [(3, 4, 5), (5,)]   torch/tinygrad fp: 0.02 / 1.08 ms  bp: nan / nan ms 
testing                        [(5,), (3, 4, 5)]   torch/tinygrad fp: 0.02 / 1.09 ms  bp: nan / nan ms 
testing                                     None   torch/tinygrad fp: 0.01 / 0.53 ms  bp: nan / nan ms 
testing                                     None   torch/tinygrad fp: 0.03 / 0.46 ms  bp: nan / nan ms 
testing                                     None   torch/tinygrad fp: 0.01 / 0.53 ms  bp: nan / nan ms 
testing                                     None   torch/tinygrad fp: 0.02 / 0.45 ms  bp: nan / nan ms 
testing                   [(3, 4, 5), (3, 4, 5)]   torch/tinygrad fp: 0.01 / 0.43 ms  bp: nan / nan ms 
testing                        [(3, 4, 5), (5,)]   torch/tinygrad fp: 0.01 / 0.47 ms  bp: nan / nan ms 
testing                        [(5,), (3, 4, 5)]   torch/tinygrad fp: 0.01 / 0.46 ms  bp: nan / nan ms 
testing                                     None   torch/tinygrad fp: 0.01 / 0.43 ms  bp: nan / nan ms 
testing                                     None   torch/tinygrad fp: 0.02 / 0.35 ms  bp: nan / nan ms 
testing                                     None   torch/tinygrad fp: 0.01 / 0.43 ms  bp: nan / nan ms 
testing                                     None   torch/tinygrad fp: 0.02 / 0.35 ms  bp: nan / nan ms 
testing                  [(1, 1, 11), (6, 1, 1)]   torch/tinygrad fp: 0.15 / 37.24 ms  bp: 0.52 / 111.10 ms 
testing                  [(1, 1, 11), (6, 1, 2)]   torch/tinygrad fp: 0.54 / 36.08 ms  bp: 0.91 / 181.22 ms 
testing                  [(1, 1, 11), (6, 1, 5)]   torch/tinygrad fp: 0.53 / 36.68 ms  bp: 0.48 / 189.09 ms 
testing                  [(1, 3, 11), (6, 3, 1)]   torch/tinygrad fp: 0.12 / 37.79 ms  bp: 0.93 / 111.67 ms 
testing                  [(1, 3, 11), (6, 3, 2)]   torch/tinygrad fp: 0.68 / 43.57 ms  bp: 0.87 / 124.63 ms 
testing                  [(1, 3, 11), (6, 3, 5)]   torch/tinygrad fp: 0.62 / 45.75 ms  bp: 0.82 / 124.54 ms 
testing                  [(1, 3, 11), (6, 1, 5)]   torch/tinygrad fp: 2.74 / 39.13 ms  bp: 15.96 / 79.12 ms 
testing                  [(8, 1, 11), (6, 1, 1)]   torch/tinygrad fp: 1.07 / 36.85 ms  bp: 1.60 / 118.48 ms 
testing                  [(8, 1, 11), (6, 1, 2)]   torch/tinygrad fp: 1.75 / 41.32 ms  bp: 5.41 / 221.93 ms 
testing                  [(8, 1, 11), (6, 1, 5)]   torch/tinygrad fp: 1.33 / 45.73 ms  bp: 4.47 / 216.04 ms 
testing                  [(8, 3, 11), (6, 3, 1)]   torch/tinygrad fp: 1.11 / 37.79 ms  bp: 1.93 / 154.14 ms 
testing                  [(8, 3, 11), (6, 3, 2)]   torch/tinygrad fp: 1.03 / 46.68 ms  bp: 4.44 / 162.10 ms 
testing                  [(8, 3, 11), (6, 3, 5)]   torch/tinygrad fp: 0.52 / 48.88 ms  bp: 4.04 / 155.53 ms 
testing                  [(8, 3, 11), (6, 1, 5)]   torch/tinygrad fp: 1.08 / 42.62 ms  bp: 1.90 / 100.44 ms 
testing            [(1, 3, 11, 7), (6, 3, 1, 1)]   torch/tinygrad fp: 0.15 / 40.57 ms  bp: 1.55 / 153.87 ms 
testing            [(1, 3, 11, 7), (6, 3, 1, 2)]   torch/tinygrad fp: 0.81 / 43.90 ms  bp: 0.80 / 237.36 ms 
testing            [(1, 3, 11, 7), (6, 3, 1, 3)]   torch/tinygrad fp: 0.65 / 45.73 ms  bp: 1.15 / 323.98 ms 
testing            [(1, 3, 11, 7), (6, 3, 1, 5)]   torch/tinygrad fp: 0.77 / 47.18 ms  bp: 1.02 / 228.86 ms 
testing            [(1, 3, 11, 7), (6, 3, 2, 1)]   torch/tinygrad fp: 0.61 / 41.89 ms  bp: 1.16 / 222.69 ms 
testing            [(1, 3, 11, 7), (6, 3, 2, 2)]   torch/tinygrad fp: 0.67 / 47.22 ms  bp: 0.99 / 251.86 ms 
testing            [(1, 3, 11, 7), (6, 3, 2, 3)]   torch/tinygrad fp: 0.61 / 52.96 ms  bp: 0.97 / 242.36 ms 
testing            [(1, 3, 11, 7), (6, 3, 2, 5)]   torch/tinygrad fp: 0.68 / 59.27 ms  bp: 1.17 / 247.31 ms 
testing            [(1, 3, 11, 7), (6, 3, 3, 1)]   torch/tinygrad fp: 0.91 / 43.56 ms  bp: 1.11 / 227.47 ms 
testing            [(1, 3, 11, 7), (6, 3, 3, 2)]   torch/tinygrad fp: 0.63 / 48.15 ms  bp: 2.46 / 248.86 ms 
testing            [(1, 3, 11, 7), (6, 3, 3, 3)]   torch/tinygrad fp: 0.63 / 53.20 ms  bp: 0.97 / 267.75 ms 
testing            [(1, 3, 11, 7), (6, 1, 3, 3)]   torch/tinygrad fp: 1.12 / 45.19 ms  bp: 1.68 / 106.01 ms 
testing            [(1, 3, 11, 7), (6, 3, 3, 5)]   torch/tinygrad fp: 0.76 / 70.38 ms  bp: 0.96 / 254.48 ms 
testing            [(1, 1, 11, 7), (6, 1, 1, 1)]   torch/tinygrad fp: 0.11 / 34.44 ms  bp: 0.41 / 82.46 ms 
testing            [(1, 1, 11, 7), (6, 1, 1, 2)]   torch/tinygrad fp: 0.68 / 39.67 ms  bp: 0.95 / 147.50 ms 
testing            [(1, 1, 11, 7), (6, 1, 1, 3)]   torch/tinygrad fp: 0.64 / 41.96 ms  bp: 0.61 / 166.73 ms 
testing            [(1, 1, 11, 7), (6, 1, 1, 5)]   torch/tinygrad fp: 0.67 / 42.95 ms  bp: 0.60 / 152.46 ms 
testing            [(1, 1, 11, 7), (6, 1, 2, 1)]   torch/tinygrad fp: 0.55 / 38.33 ms  bp: 0.57 / 150.87 ms 
testing            [(1, 1, 11, 7), (6, 1, 2, 2)]   torch/tinygrad fp: 0.56 / 43.52 ms  bp: 0.57 / 182.84 ms 
testing            [(1, 1, 11, 7), (6, 1, 2, 3)]   torch/tinygrad fp: 0.82 / 44.14 ms  bp: 0.61 / 181.07 ms 
testing            [(1, 1, 11, 7), (6, 1, 2, 5)]   torch/tinygrad fp: 0.75 / 48.85 ms  bp: 1.10 / 178.09 ms 
testing            [(1, 1, 11, 7), (6, 1, 3, 1)]   torch/tinygrad fp: 0.62 / 37.96 ms  bp: 0.71 / 155.37 ms 
testing            [(1, 1, 11, 7), (6, 1, 3, 2)]   torch/tinygrad fp: 0.82 / 42.50 ms  bp: 0.57 / 177.24 ms 
testing            [(1, 1, 11, 7), (6, 1, 3, 3)]   torch/tinygrad fp: 1.05 / 47.47 ms  bp: 0.73 / 184.41 ms 
testing            [(1, 1, 11, 7), (6, 1, 3, 5)]   torch/tinygrad fp: 0.98 / 48.05 ms  bp: 0.75 / 179.54 ms 
testing            [(4, 1, 11, 7), (6, 1, 1, 1)]   torch/tinygrad fp: 1.03 / 36.03 ms  bp: 2.14 / 146.14 ms 
testing            [(4, 1, 11, 7), (6, 1, 1, 2)]   torch/tinygrad fp: 7.84 / 44.53 ms  bp: 6.49 / 286.22 ms 
testing            [(4, 1, 11, 7), (6, 1, 1, 3)]   torch/tinygrad fp: 8.04 / 46.36 ms  bp: 7.57 / 379.04 ms 
testing            [(4, 1, 11, 7), (6, 1, 1, 5)]   torch/tinygrad fp: 7.95 / 43.72 ms  bp: 8.32 / 241.89 ms 
testing            [(4, 1, 11, 7), (6, 1, 2, 1)]   torch/tinygrad fp: 7.78 / 42.22 ms  bp: 6.10 / 221.43 ms 
testing            [(4, 1, 11, 7), (6, 1, 2, 2)]   torch/tinygrad fp: 7.88 / 47.10 ms  bp: 6.58 / 298.08 ms 
testing            [(4, 1, 11, 7), (6, 1, 2, 3)]   torch/tinygrad fp: 8.22 / 53.12 ms  bp: 8.54 / 286.46 ms 
testing            [(4, 1, 11, 7), (6, 1, 2, 5)]   torch/tinygrad fp: 1.38 / 50.81 ms  bp: 4.69 / 263.61 ms 
testing            [(4, 1, 11, 7), (6, 1, 3, 1)]   torch/tinygrad fp: 6.71 / 45.55 ms  bp: 8.12 / 245.75 ms 
testing            [(4, 1, 11, 7), (6, 1, 3, 2)]   torch/tinygrad fp: 7.79 / 52.28 ms  bp: 6.60 / 289.34 ms 
testing            [(4, 1, 11, 7), (6, 1, 3, 3)]   torch/tinygrad fp: 7.95 / 49.97 ms  bp: 8.61 / 292.65 ms 
testing            [(4, 1, 11, 7), (6, 1, 3, 5)]   torch/tinygrad fp: 1.53 / 51.54 ms  bp: 3.62 / 253.00 ms 
testing            [(4, 3, 11, 7), (6, 3, 1, 1)]   torch/tinygrad fp: 1.31 / 42.52 ms  bp: 2.85 / 142.72 ms 
testing            [(4, 3, 11, 7), (6, 3, 1, 2)]   torch/tinygrad fp: 7.04 / 50.24 ms  bp: 7.89 / 249.81 ms 
testing            [(4, 3, 11, 7), (6, 3, 1, 3)]   torch/tinygrad fp: 8.07 / 55.10 ms  bp: 7.51 / 207.53 ms 
testing            [(4, 3, 11, 7), (6, 3, 1, 5)]   torch/tinygrad fp: 6.98 / 46.51 ms  bp: 6.38 / 171.73 ms ok
test_cos (__main__.TestOps) ... ok
test_cosh (__main__.TestOps) ... ok
test_cumsum (__main__.TestOps) ... ok
test_depthwise_conv2d (__main__.TestOps) ... ok
test_detach (__main__.TestOps) ... ok
test_dilated_conv2d (__main__.TestOps) ... ok
test_dilated_conv_transpose2d (__main__.TestOps) ... ok
test_div (__main__.TestOps) ... ok
test_div_int (__main__.TestOps) ... ok
test_div_naninf (__main__.TestOps) ... ok
test_dot (__main__.TestOps) ... ok
test_dot_1d (__main__.TestOps) ... ok
test_double_slice (__main__.TestOps) ... ok
test_einsum (__main__.TestOps) ... 
testing            [(4, 3, 11, 7), (6, 3, 2, 1)]   torch/tinygrad fp: 7.19 / 43.42 ms  bp: 6.12 / 222.04 ms 
testing            [(4, 3, 11, 7), (6, 3, 2, 2)]   torch/tinygrad fp: 7.69 / 53.65 ms  bp: 7.11 / 274.44 ms 
testing            [(4, 3, 11, 7), (6, 3, 2, 3)]   torch/tinygrad fp: 7.44 / 63.84 ms  bp: 8.43 / 276.03 ms 
testing            [(4, 3, 11, 7), (6, 3, 2, 5)]   torch/tinygrad fp: 0.74 / 68.32 ms  bp: 4.53 / 216.95 ms 
testing            [(4, 3, 11, 7), (6, 3, 3, 1)]   torch/tinygrad fp: 6.48 / 51.98 ms  bp: 8.24 / 198.30 ms 
testing            [(4, 3, 11, 7), (6, 3, 3, 2)]   torch/tinygrad fp: 7.73 / 60.76 ms  bp: 6.55 / 273.77 ms 
testing            [(4, 3, 11, 7), (6, 3, 3, 3)]   torch/tinygrad fp: 7.72 / 69.95 ms  bp: 9.28 / 269.61 ms 
testing            [(4, 3, 11, 7), (6, 1, 3, 3)]   torch/tinygrad fp: 1.09 / 55.02 ms  bp: 2.51 / 127.54 ms 
testing            [(4, 3, 11, 7), (6, 3, 3, 5)]   torch/tinygrad fp: 1.26 / 74.04 ms  bp: 4.02 / 340.67 ms 
testing                               [(45, 65)]   torch/tinygrad fp: 0.52 / 72.30 ms  bp: 1.44 / 75.65 ms 
testing                                     [()]   torch/tinygrad fp: 0.04 / 36.64 ms  bp: 0.50 / 33.98 ms 
testing                               [(45, 65)]   torch/tinygrad fp: 0.07 / 36.85 ms  bp: 0.36 / 37.82 ms 
testing                               [(45, 65)]   torch/tinygrad fp: 0.04 / 1.28 ms  bp: nan / nan ms 
testing                               [(45, 65)]   torch/tinygrad fp: 0.03 / 1.12 ms  bp: nan / nan ms 
testing                                     [20]   torch/tinygrad fp: 0.76 / 51.37 ms  bp: 1.07 / 92.34 ms 
testing                               [(20, 30)]   torch/tinygrad fp: 0.04 / 54.08 ms  bp: 0.36 / 138.65 ms 
testing                               [(20, 30)]   torch/tinygrad fp: 0.04 / 63.68 ms  bp: 0.36 / 111.71 ms 
testing                           [(20, 30, 40)]   torch/tinygrad fp: 0.06 / 64.62 ms  bp: 0.62 / 117.41 ms 
testing                           [(20, 30, 40)]   torch/tinygrad fp: 0.06 / 0.77 ms  bp: 0.54 / 2.01 ms 
testing         [(1, 32, 32, 32), (32, 1, 1, 1)]   torch/tinygrad fp: 2.75 / 34.97 ms  bp: 2.45 / 83.54 ms 
testing                           [(4, 3, 6, 6)]   torch/tinygrad fp: 0.00 / 0.28 ms  bp: nan / nan ms 
testing                                     [()]   torch/tinygrad fp: 0.00 / 0.02 ms  bp: nan / nan ms 
testing           [(4, 3, 11, 28), (4, 3, 3, 3)]   torch/tinygrad fp: 2.89 / 65.03 ms  bp: 2.42 / 323.32 ms 
testing           [(4, 3, 11, 28), (4, 3, 3, 3)]   torch/tinygrad fp: 1.11 / 76.09 ms  bp: 3.04 / 348.79 ms 
testing             [(2, 4, 9, 9), (4, 4, 3, 3)]   torch/tinygrad fp: 8.77 / 86.07 ms  bp: 7.96 / 522.15 ms 
testing             [(2, 4, 9, 9), (4, 4, 3, 3)]   torch/tinygrad fp: 8.49 / 86.99 ms  bp: 8.20 / 485.13 ms 
testing             [(2, 4, 9, 9), (4, 4, 3, 3)]   torch/tinygrad fp: 8.56 / 90.34 ms  bp: 7.78 / 545.21 ms 
testing             [(2, 4, 9, 9), (4, 4, 3, 3)]   torch/tinygrad fp: 7.87 / 86.27 ms  bp: 7.78 / 2.03 ms 
testing                     [(45, 65), (45, 65)]   torch/tinygrad fp: 0.03 / 35.49 ms  bp: 0.36 / 77.28 ms 
testing                     [(45, 65), (45, 65)]   torch/tinygrad fp: 0.03 / 0.56 ms  bp: 0.41 / 1.66 ms 
testing                                 [(), ()]   torch/tinygrad fp: 0.03 / 30.55 ms  bp: 0.34 / 62.13 ms 
testing                                     None   torch/tinygrad fp: 0.09 / 33.00 ms  bp: nan / nan ms 
testing                                     None   torch/tinygrad fp: 0.10 / 29.16 ms  bp: nan / nan ms 
testing                               [(45, 65)]   torch/tinygrad fp: 0.05 / 0.07 ms  bp: 0.34 / 0.47 ms 
testing                               [(45, 65)]   torch/tinygrad fp: 0.02 / 0.05 ms  bp: 0.14 / 0.35 ms 
testing                               [(45, 65)]   torch/tinygrad fp: 0.02 / 31.67 ms  bp: 0.49 / 33.73 ms 
testing                               [(45, 65)]   torch/tinygrad fp: 0.11 / 34.22 ms  bp: 0.49 / 35.53 ms 
testing                               [(45, 65)]   torch/tinygrad fp: 0.07 / 35.97 ms  bp: 0.36 / 34.15 ms 
testing                               [(45, 65)]   torch/tinygrad fp: 0.07 / 30.84 ms  bp: 0.49 / 33.91 ms 
testing                    [(45, 65), (65, 100)]   torch/tinygrad fp: 0.55 / 48.82 ms  bp: 1.28 / 159.41 ms 
testing              [(8, 45, 65), (8, 65, 100)]   torch/tinygrad fp: 0.77 / 53.60 ms  bp: 1.67 / 170.05 ms 
testing                         [(2, 4), (1, 3)]   torch/tinygrad exception: mat1 and mat2 shapes cannot be multiplied (2x4 and 1x3) / Input Tensor shapes (2, 4) and (1, 3) cannot be multiplied (4 != 1)
testing                         [(2, 1), (4, 3)]   torch/tinygrad exception: mat1 and mat2 shapes cannot be multiplied (2x1 and 4x3) / Input Tensor shapes (2, 1) and (4, 3) cannot be multiplied (1 != 4)
testing                                 [65, 65]   torch/tinygrad fp: 0.04 / 36.67 ms  bp: 0.46 / 32.04 ms 
testing                           [65, (65, 45)]   torch/tinygrad fp: 0.09 / 47.72 ms  bp: 0.40 / 145.33 ms 
testing                           [(45, 65), 65]   torch/tinygrad fp: 0.06 / 45.94 ms  bp: 0.52 / 44.23 ms 
testing                        [(8, 45, 65), 65]   torch/tinygrad fp: 0.10 / 45.78 ms  bp: 0.57 / 116.35 ms 
testing                        [65, (8, 65, 45)]   torch/tinygrad fp: 0.17 / 50.26 ms  bp: 0.46 / 107.73 ms 
testing                              [4, (1, 2)]   torch/tinygrad exception: mat1 and mat2 shapes cannot be multiplied (1x4 and 1x2) / Input Tensor shapes (4,) and (1, 2) cannot be multiplied (4 != 1)
testing                              [(2, 1), 4]   torch/tinygrad exception: size mismatch, got input (2), mat (2x1), vec (4) / Input Tensor shapes (2, 1) and (4,) cannot be multiplied (1 != 4)
testing                                   [1, 4]   torch/tinygrad exception: inconsistent tensor size, expected tensor [1] and src [4] to have the same number of elements, but got 1 and 4 elements respectively / Input Tensor shapes (1,) and (4,) cannot be multiplied (1 != 4)
testing                                 [(4, 4)]   torch/tinygrad fp: 0.03 / 0.48 ms  bp: 0.51 / 35.52 ms 
testing                                 [(4, 4)]   torch/tinygrad fp: 0.05 / 0.69 ms  bp: 0.48 / 32.85 ms 
testing                                 [(4, 4)]   torch/tinygrad fp: 0.07 / 0.69 ms  bp: 0.36 / 28.34 ms 
testing                                 [(4, 4)]   torch/tinygrad fp: 0.07 / 0.68 ms  bp: 0.36 / 35.15 ms 
testing                             [(150, 150)]   torch/tinygrad fp: 7.33 / 0.44 ms  bp: 0.61 / 69.67 ms 
testing                             [(150, 150)]   torch/tinygrad fp: 0.06 / 0.34 ms  bp: 0.34 / 0.79 ms 
testing                             [(150, 150)]   torch/tinygrad fp: 0.02 / 0.28 ms  bp: 0.22 / 0.61 ms 
testing                           [(20, 30, 40)]   torch/tinygrad fp: 0.02 / 0.30 ms  bp: 0.41 / 35.24 ms 
testing                           [(20, 30, 40)]   torch/tinygrad fp: 0.08 / 0.68 ms  bp: 0.59 / 39.09 ms 
testing                           [(20, 30, 40)]   torch/tinygrad fp: 0.08 / 48.43 ms  bp: 0.36 / 0.55 ms 
testing                               [(50, 50)]   torch/tinygrad fp: 0.09 / 43.21 ms  bp: 0.48 / 64.04 ms 
testing                               [(15, 15)]   torch/tinygrad fp: 0.11 / 39.62 ms  bp: 0.34 / 61.93 ms 
testing                        [(15, 20), (20,)]   torch/tinygrad fp: 0.11 / 40.39 ms  bp: 0.41 / 75.50 ms 
testing                     [(15, 20), (20, 30)]   torch/tinygrad fp: 0.92 / 49.77 ms  bp: 1.07 / 162.91 ms 
testing                                 [30, 30]   torch/tinygrad fp: 0.11 / 36.05 ms  bp: 0.51 / 35.40 ms 
testing                     [(30, 40), (30, 40)]   torch/tinygrad fp: 0.11 / 33.29 ms  bp: 0.35 / 35.37 ms 
testing                           [(15,), (15,)]   torch/tinygrad fp: 0.09 / 37.47 ms  bp: 0.40 / 122.34 ms 
testing             [(10, 20, 30), (10, 30, 40)]   torch/tinygrad fp: 0.65 / 192.17 ms  bp: 1.35 / 399.60 ms 
testing             [(10, 20, 25), (10, 25, 32)]   torch/tinygrad fp: 0.64 / 161.05 ms  bp: 1.26 / 259.97 ms 
testing             [(20, 10, 25), (10, 25, 32)]   torch/tinygrad fp: 0.65 / 149.23 ms  bp: 1.27 / 67.01 ms ok
test_einsum_arity_check1 (__main__.TestOps) ... ok
test_einsum_arity_check2 (__main__.TestOps) ... ok
test_einsum_shape_check (__main__.TestOps) ... ok
test_elu (__main__.TestOps) ... ok
test_empty_0 (__main__.TestOps) ... ok
test_exp (__main__.TestOps) ... ok
test_exp2 (__main__.TestOps) ... ok
test_expand (__main__.TestOps) ... ok
test_eye (__main__.TestOps) ... ok
test_fancy_conv2d (__main__.TestOps) ... ok
test_flatten (__main__.TestOps) ... ok
test_flip (__main__.TestOps) ... ok
test_flip_eye_crash (__main__.TestOps) ... ok
test_floor (__main__.TestOps) ... ok
test_full (__main__.TestOps) ... ok
test_full_like (__main__.TestOps) ... ok
test_gather (__main__.TestOps) ... ok
test_gelu (__main__.TestOps) ... ok
test_gemm (__main__.TestOps) ... ok
test_gemm_with_zeros_shape (__main__.TestOps) ... ok
test_global_avgpool2d (__main__.TestOps) ... ok
test_grouped_conv2d (__main__.TestOps) ... ok
test_grouped_conv_transpose2d (__main__.TestOps) ... ok
test_hardswish (__main__.TestOps) ... ok
test_hardtanh (__main__.TestOps) ... ok
test_inf_where (__main__.TestOps) ... ok
test_large_bs_conv (__main__.TestOps) ... skipped 'slow'
test_large_ic_conv (__main__.TestOps) ... skipped 'slow'
test_large_input_conv2d (__main__.TestOps) ... ok
test_leakyrelu (__main__.TestOps) ... ok
test_log (__main__.TestOps) ... 
testing      [(3, 5, 8, 10), (11, 13, 5, 16, 8)]   torch/tinygrad fp: 1.11 / 82.43 ms  bp: 2.88 / 229.94 ms 
testing      [(3, 8, 10, 5), (11, 5, 13, 16, 8)]   torch/tinygrad fp: 0.54 / 84.30 ms  bp: 3.21 / 289.49 ms 
testing              [(2, 3), (5, 3, 7), (2, 7)]   torch/tinygrad fp: 0.97 / 44.04 ms  bp: 0.48 / 193.63 ms 
testing                               [(45, 65)]   torch/tinygrad fp: 0.10 / 37.95 ms  bp: 0.46 / 41.29 ms 
testing                               [(45, 65)]   torch/tinygrad fp: 0.05 / 40.07 ms  bp: 0.34 / 43.34 ms 
testing                                     [()]   torch/tinygrad fp: 0.04 / 33.19 ms  bp: 0.42 / 37.12 ms 
testing                                       []   torch/tinygrad fp: 0.17 / 35.73 ms  bp: nan / nan ms 
testing                               [(45, 65)]   torch/tinygrad fp: 1.05 / 33.91 ms  bp: 0.45 / 37.97 ms 
testing                                     [()]   torch/tinygrad fp: 0.05 / 30.55 ms  bp: 0.31 / 29.55 ms 
testing                               [(45, 65)]   torch/tinygrad fp: 0.07 / 36.09 ms  bp: 0.34 / 33.18 ms 
testing                                     [()]   torch/tinygrad fp: 0.03 / 29.86 ms  bp: 0.46 / 31.38 ms 
testing                           [(4, 3, 1, 6)]   torch/tinygrad fp: 0.04 / 0.31 ms  bp: 0.48 / 63.45 ms 
testing                           [(1, 1, 1, 1)]   torch/tinygrad fp: 0.03 / 0.27 ms  bp: 0.45 / 38.57 ms 
testing                                     [()]   torch/tinygrad fp: 0.04 / 0.03 ms  bp: 0.36 / 29.73 ms 
testing                                       []   torch/tinygrad fp: 0.11 / 0.28 ms  bp: nan / nan ms 
testing                                       []   torch/tinygrad fp: 0.04 / 0.26 ms  bp: nan / nan ms 
testing                                       []   torch/tinygrad fp: 0.06 / 0.40 ms  bp: nan / nan ms 
testing           [(2, 3, 11, 28), (3, 1, 3, 3)]   torch/tinygrad fp: 1.23 / 51.07 ms  bp: 3.18 / 306.70 ms 
testing                           [(4, 3, 6, 6)]   torch/tinygrad fp: 0.07 / 0.48 ms  bp: 0.37 / 71.67 ms 
testing                           [(4, 3, 6, 6)]   torch/tinygrad fp: 0.03 / 0.29 ms  bp: 0.38 / 38.83 ms 
testing                           [(4, 3, 6, 6)]   torch/tinygrad fp: 0.04 / 0.56 ms  bp: 0.43 / 38.56 ms 
testing                           [(4, 3, 6, 6)]   torch/tinygrad fp: 0.01 / 0.47 ms  bp: 0.43 / 35.24 ms 
testing                           [(4, 3, 6, 6)]   torch/tinygrad fp: 0.03 / 0.29 ms  bp: 0.27 / 33.90 ms 
testing                           [(4, 3, 6, 6)]   torch/tinygrad fp: 0.03 / 0.29 ms  bp: 0.29 / 38.43 ms 
testing                           [(4, 3, 6, 6)]   torch/tinygrad fp: 0.03 / 0.27 ms  bp: 0.26 / 0.67 ms 
testing                                     [()]   torch/tinygrad fp: 0.01 / 0.04 ms  bp: 0.43 / 32.45 ms 
testing                                   [(1,)]   torch/tinygrad fp: 0.01 / 0.39 ms  bp: 0.38 / 28.50 ms 
testing                           [(4, 3, 6, 6)]   torch/tinygrad fp: 0.06 / 0.47 ms  bp: 0.45 / 37.88 ms 
testing                           [(4, 3, 6, 6)]   torch/tinygrad fp: 0.04 / 0.40 ms  bp: 0.45 / 39.64 ms 
testing                           [(4, 3, 6, 6)]   torch/tinygrad fp: 0.05 / 0.46 ms  bp: 0.37 / 39.40 ms 
testing                           [(4, 3, 6, 6)]   torch/tinygrad fp: 0.04 / 0.28 ms  bp: 0.56 / 36.39 ms 
testing                           [(4, 3, 6, 6)]   torch/tinygrad fp: 0.04 / 0.29 ms  bp: 0.46 / 39.63 ms 
testing                           [(4, 3, 6, 6)]   torch/tinygrad fp: 0.04 / 0.26 ms  bp: 0.26 / 0.67 ms 
testing                                     [()]   torch/tinygrad fp: 0.01 / 0.03 ms  bp: 0.13 / 0.35 ms 
testing                                   [(1,)]   torch/tinygrad fp: 0.01 / 0.19 ms  bp: 0.13 / 0.41 ms 
testing                           [(4, 3, 6, 6)]   torch/tinygrad fp: 0.01 / 0.20 ms  bp: 0.14 / 0.58 ms 
testing                                       []   torch/tinygrad fp: 0.07 / 47.83 ms  bp: nan / nan ms 
testing                               [(45, 35)]   torch/tinygrad fp: 0.03 / 33.76 ms  bp: nan / nan ms 
testing                                     None   torch/tinygrad fp: 0.03 / 34.23 ms  bp: nan / nan ms 
testing                                       []   torch/tinygrad fp: 0.11 / 0.15 ms  bp: nan / nan ms 
testing                                       []   torch/tinygrad fp: 0.07 / 0.10 ms  bp: nan / nan ms 
testing                              [(4, 5, 6)]   torch/tinygrad fp: 0.32 / 75.26 ms  bp: 0.85 / 74.45 ms 
testing                              [(4, 5, 6)]   torch/tinygrad fp: 0.05 / 46.39 ms  bp: 0.47 / 78.34 ms 
testing                              [(4, 5, 6)]   torch/tinygrad fp: 0.04 / 74.49 ms  bp: 0.40 / 78.96 ms 
testing                              [(3, 4, 5)]   torch/tinygrad fp: 0.05 / 69.28 ms  bp: 0.35 / 36.20 ms 
testing                              [(4, 5, 6)]   torch/tinygrad exception: Index tensor must have the same number of dimensions as input tensor / self.ndim must equal idx.ndim
testing                              [(2, 1, 1)]   torch/tinygrad exception: Size does not match at dimension 1 expected index [3, 4, 5] to be smaller than self [2, 1, 1] apart from dimension 0 / all dim of idx.shape must be smaller than self.shape
testing                               [(45, 65)]   torch/tinygrad fp: 0.06 / 38.59 ms  bp: 0.51 / 47.80 ms 
testing                               [(45, 65)]   torch/tinygrad fp: 0.06 / 1.38 ms  bp: 0.29 / 2.03 ms 
testing                               [(45, 65)]   torch/tinygrad fp: 0.06 / 2.27 ms  bp: 0.30 / 2.87 ms 
testing                     [(64, 64), (64, 64)]   torch/tinygrad fp: 2.46 / 58.41 ms  bp: 1.52 / 175.96 ms 
testing                         [(8, 8), (8, 0)]   torch/tinygrad fp: 0.03 / 0.46 ms  bp: 0.38 / 1.10 ms 
testing                         [(0, 8), (8, 8)]   torch/tinygrad fp: 0.02 / 0.88 ms  bp: 0.27 / 1.04 ms 
testing                         [(0, 8), (8, 0)]   torch/tinygrad fp: 0.02 / 0.55 ms  bp: 0.25 / 1.07 ms 
testing                         [(8, 0), (0, 8)]   torch/tinygrad fp: 0.01 / 0.31 ms  bp: 0.15 / 0.64 ms 
testing                         [(0, 0), (0, 0)]   torch/tinygrad fp: 0.01 / 0.31 ms  bp: 0.14 / 0.54 ms 
testing                              [0, (0, 8)]   torch/tinygrad fp: 0.03 / 0.24 ms  bp: 0.50 / 1.06 ms 
testing                                   [0, 0]   torch/tinygrad fp: 0.04 / 0.30 ms  bp: 0.32 / 0.43 ms 
testing                       [(32, 2, 111, 28)]   torch/tinygrad fp: 0.17 / 41.49 ms  bp: 0.51 / 65.78 ms 
testing           [(4, 15, 5, 5), (35, 3, 3, 3)]   torch/tinygrad fp: 1.37 / 66.96 ms  bp: 1.39 / 350.21 ms 
testing             [(2, 4, 9, 9), (4, 4, 3, 3)]   torch/tinygrad fp: 1.42 / 93.12 ms  bp: 1.77 / 408.59 ms 
testing                               [(45, 65)]   torch/tinygrad fp: 0.57 / 40.79 ms  bp: 0.51 / 41.34 ms 
testing                                     [()]   torch/tinygrad fp: 0.04 / 33.89 ms  bp: 0.46 / 34.06 ms 
testing                               [(45, 65)]   torch/tinygrad fp: 0.09 / 40.08 ms  bp: 0.48 / 42.10 ms 
testing                                     [()]   torch/tinygrad fp: 0.06 / 32.92 ms  bp: 0.32 / 30.80 ms 
testing                               [(45, 65)]   torch/tinygrad fp: 0.05 / 42.73 ms  bp: 0.45 / 41.54 ms 
testing                                     [()]   torch/tinygrad fp: 0.04 / 30.38 ms  bp: 0.42 / 35.60 ms 
testing                               [(45, 65)]   torch/tinygrad fp: 0.05 / 36.58 ms  bp: 0.45 / 43.20 ms 
testing                                     [()]   torch/tinygrad fp: 0.05 / 34.76 ms  bp: 0.42 / 34.34 ms 
testing                               [(45, 65)]   torch/tinygrad fp: 0.05 / 35.75 ms  bp: 0.46 / 45.63 ms 
testing                                     [()]   torch/tinygrad fp: 0.06 / 33.76 ms  bp: 0.31 / 29.99 ms 
testing         [(4, 16, 64, 64), (6, 16, 5, 2)]   torch/tinygrad fp: 1.69 / 81.08 ms  bp: 3.67 / 405.19 ms 
testing                               [(45, 65)]   torch/tinygrad fp: 0.11 / 39.60 ms  bp: 0.99 / 41.28 ms 
testing                                     [()]   torch/tinygrad fp: 0.04 / 34.55 ms  bp: 0.42 / 39.32 ms ok
test_log2 (__main__.TestOps) ... ok
test_log_softmax (__main__.TestOps) ... ok
test_log_softmax_other_axis (__main__.TestOps) ... ok
test_logical_not (__main__.TestOps) ... ok
test_matmul (__main__.TestOps) ... ok
test_matmul_batched (__main__.TestOps) ... ok
test_matmul_batched_vector (__main__.TestOps) ... ok
test_matmul_simple (__main__.TestOps) ... ok
test_matvec (__main__.TestOps) ... ok
test_matvecmat (__main__.TestOps) ... ok
test_max (__main__.TestOps) ... ok
test_max_dont_collapse (__main__.TestOps) ... ok
test_max_inf (__main__.TestOps) ... skipped 'this test is broken #862'
test_maximum (__main__.TestOps) ... ok
test_maxpool2d (__main__.TestOps) ... ok
test_maxpool2d_bigger_stride (__main__.TestOps) ... ok
test_maxpool2d_dilation (__main__.TestOps) ... ok
test_maxpool2d_simple (__main__.TestOps) ... ok
test_maxpool2d_smaller_stride (__main__.TestOps) ... ok
test_maxpool2d_unit_stride (__main__.TestOps) ... ok
test_mean (__main__.TestOps) ... ok
test_mean_axis (__main__.TestOps) ... ok
test_mean_zero_axis (__main__.TestOps) ... ok
test_medium_grouped_conv2d (__main__.TestOps) ... ok
test_min (__main__.TestOps) ... ok
test_minimum (__main__.TestOps) ... ok
test_mish (__main__.TestOps) ... ok
test_mul (__main__.TestOps) ... ok
test_mul_naninf (__main__.TestOps) ... ok
test_mulacc_with_zero_strides (__main__.TestOps) ... 
testing                               [(45, 65)]   torch/tinygrad fp: 1.19 / 40.40 ms  bp: 0.33 / 0.74 ms 
testing                                     [()]   torch/tinygrad fp: 0.02 / 28.66 ms  bp: 0.33 / 31.93 ms 
testing                               [(45, 65)]   torch/tinygrad fp: 0.66 / 32.79 ms  bp: 0.46 / 39.44 ms 
testing                                     [()]   torch/tinygrad fp: 0.03 / 34.39 ms  bp: 0.32 / 32.69 ms 
testing                               [(45, 65)]   torch/tinygrad fp: 0.56 / 123.85 ms  bp: 0.79 / 215.87 ms 
testing                                     [()]   torch/tinygrad fp: 0.07 / 32.07 ms  bp: 0.34 / 36.17 ms 
testing                           [(10, 10, 10)]   torch/tinygrad fp: 0.07 / 115.69 ms  bp: 0.45 / 249.51 ms 
testing                           [(10, 10, 10)]   torch/tinygrad fp: 0.50 / 121.71 ms  bp: 0.77 / 393.33 ms 
testing                           [(10, 10, 10)]   torch/tinygrad fp: 0.48 / 128.55 ms  bp: 1.20 / 218.74 ms 
testing                                     None   torch/tinygrad fp: 0.06 / 34.28 ms  bp: nan / nan ms 
testing                                     None   torch/tinygrad fp: 0.03 / 30.14 ms  bp: nan / nan ms 
testing                           [64, (64, 99)]   torch/tinygrad fp: 0.08 / 43.28 ms  bp: 0.54 / 148.02 ms 
testing                        [3, (1, 3, 3, 5)]   torch/tinygrad fp: 0.10 / 37.99 ms  bp: 0.40 / 105.27 ms 
testing                   [(4, 3), (1, 3, 3, 5)]   torch/tinygrad fp: 0.18 / 40.37 ms  bp: 0.59 / 117.61 ms 
testing                              [4, (4, 4)]   torch/tinygrad fp: 0.07 / 32.06 ms  bp: 0.37 / 103.74 ms 
testing                   [(1, 128), (128, 128)]   torch/tinygrad fp: 0.09 / 70.29 ms  bp: 0.51 / 175.28 ms 
testing       [(1, 128), (128, 128), (128, 128)]   torch/tinygrad fp: 0.10 / 64.20 ms  bp: 0.41 / 107.67 ms 
testing                                [(45, 3)]   torch/tinygrad fp: 0.09 / 35.14 ms  bp: 0.69 / 67.63 ms 
testing                                [(45, 3)]   torch/tinygrad fp: 0.06 / 38.55 ms  bp: 0.51 / 32.56 ms 
testing                                     None   torch/tinygrad fp: 0.12 / 37.08 ms  bp: 0.38 / 95.17 ms 
testing                           [(3, 4, 5, 6)]   torch/tinygrad fp: 0.63 / 38.61 ms  bp: 0.44 / 132.31 ms 
testing                                     [()]   torch/tinygrad fp: 0.04 / 0.07 ms  bp: 0.42 / 32.22 ms 
testing                                       []   torch/tinygrad fp: 0.59 / 35.15 ms  bp: nan / nan ms 
testing                     [(45, 65), (45, 65)]   torch/tinygrad fp: 0.25 / 39.36 ms  bp: 0.69 / 76.39 ms 
testing                                 [(), ()]   torch/tinygrad fp: 0.03 / 32.51 ms  bp: 0.49 / 62.08 ms 
testing                                     None   torch/tinygrad fp: 0.04 / 64.21 ms  bp: 0.38 / 111.05 ms 
testing                                     None   torch/tinygrad fp: 0.06 / 35.43 ms  bp: 0.52 / 75.70 ms 
testing                                     None   torch/tinygrad fp: 0.03 / 67.43 ms  bp: nan / nan ms 
testing                                     None   torch/tinygrad fp: 0.03 / 33.76 ms  bp: nan / nan ms 
testing                       [(32, 2, 110, 28)]   torch/tinygrad fp: 0.22 / 35.78 ms  bp: 1.36 / 106.11 ms 
testing                       [(32, 2, 110, 28)]   torch/tinygrad fp: 0.17 / 44.27 ms  bp: 0.72 / 160.88 ms 
testing                       [(32, 2, 110, 28)]   torch/tinygrad fp: 0.14 / 0.82 ms  bp: 0.74 / 1.08 ms 
testing                       [(32, 2, 110, 28)]   torch/tinygrad fp: 0.09 / 0.67 ms  bp: 0.36 / 1.03 ms 
testing                       [(32, 2, 110, 28)]   torch/tinygrad fp: 0.11 / 38.58 ms  bp: 0.60 / 138.89 ms 
testing                       [(32, 2, 110, 28)]   torch/tinygrad fp: 0.16 / 40.72 ms  bp: 0.54 / 114.63 ms 
testing                       [(32, 2, 110, 28)]   torch/tinygrad fp: 0.16 / 40.81 ms  bp: 0.91 / 105.90 ms 
testing                       [(32, 2, 110, 28)]   torch/tinygrad fp: 0.16 / 37.63 ms  bp: 0.61 / 143.05 ms 
testing                       [(32, 2, 110, 28)]   torch/tinygrad fp: 0.18 / 40.00 ms  bp: 0.82 / 109.17 ms 
testing                       [(32, 2, 110, 28)]   torch/tinygrad fp: 0.18 / 1.42 ms  bp: 0.93 / 1.24 ms 
testing                       [(32, 2, 110, 28)]   torch/tinygrad fp: 0.10 / 37.15 ms  bp: 0.57 / 110.55 ms 
testing                       [(32, 2, 110, 28)]   torch/tinygrad fp: 0.16 / 44.19 ms  bp: 0.53 / 261.40 ms 
testing                       [(32, 2, 110, 28)]   torch/tinygrad fp: 0.16 / 48.99 ms  bp: 0.93 / 286.91 ms 
testing                       [(32, 2, 110, 28)]   torch/tinygrad fp: 0.14 / 47.38 ms  bp: 1.28 / 222.56 ms 
testing                       [(32, 2, 110, 28)]   torch/tinygrad fp: 0.16 / 47.17 ms  bp: 1.26 / 210.27 ms 
testing                           [(1, 1, 2, 3)]   torch/tinygrad fp: 0.06 / 37.13 ms  bp: 0.49 / 107.80 ms 
testing                       [(32, 2, 110, 28)]   torch/tinygrad fp: 0.23 / 43.79 ms  bp: 1.06 / 262.65 ms 
testing                       [(32, 2, 110, 28)]   torch/tinygrad fp: 0.22 / 48.12 ms  bp: 0.59 / 269.33 ms 
testing                       [(32, 2, 110, 28)]   torch/tinygrad fp: 0.23 / 47.87 ms  bp: 1.44 / 276.76 ms 
testing                       [(32, 2, 110, 28)]   torch/tinygrad fp: 0.20 / 50.37 ms  bp: 0.91 / 280.33 ms 
testing                       [(32, 2, 110, 28)]   torch/tinygrad fp: 0.68 / 52.98 ms  bp: 1.13 / 270.82 ms 
testing                           [(3, 4, 5, 6)]   torch/tinygrad fp: 0.08 / 43.81 ms  bp: 0.46 / 32.73 ms 
testing                                     [()]   torch/tinygrad fp: 0.06 / 0.09 ms  bp: 0.22 / 0.39 ms 
testing                           [(3, 4, 5, 6)]   torch/tinygrad fp: 0.04 / 47.99 ms  bp: 0.45 / 67.66 ms 
testing                        [(1, 0, 3, 0, 5)]   torch/tinygrad fp: 0.07 / 34.42 ms  bp: 0.33 / 0.52 ms 
testing             [(1, 4, 1, 1), (4, 2, 1, 1)]   torch/tinygrad fp: 0.91 / 37.69 ms  bp: 1.56 / 107.79 ms 
testing                                 [(3, 3)]   torch/tinygrad fp: 0.53 / 35.60 ms  bp: 0.36 / 134.32 ms 
testing                                [(45, 3)]   torch/tinygrad fp: 0.03 / 38.13 ms  bp: 0.49 / 114.83 ms 
testing                                [(45, 3)]   torch/tinygrad fp: 0.06 / 35.87 ms  bp: 0.52 / 34.37 ms 
testing                                     [()]   torch/tinygrad fp: 0.05 / 31.25 ms  bp: 0.36 / 29.54 ms 
testing                     [(45, 65), (45, 65)]   torch/tinygrad fp: 0.05 / 40.97 ms  bp: 0.60 / 82.37 ms 
testing                                 [(), ()]   torch/tinygrad fp: 0.04 / 33.33 ms  bp: 0.48 / 65.47 ms 
testing                                     None   torch/tinygrad fp: 0.04 / 92.02 ms  bp: 0.37 / 108.07 ms 
testing                                     None   torch/tinygrad fp: 0.05 / 36.54 ms  bp: 0.50 / 74.98 ms 
testing                                     None   torch/tinygrad fp: 0.03 / 92.96 ms  bp: nan / nan ms 
testing                                     None   torch/tinygrad fp: 0.03 / 35.23 ms  bp: nan / nan ms 
testing                               [(45, 65)]   torch/tinygrad fp: 0.08 / 38.07 ms  bp: 0.37 / 46.87 ms 
testing                                     [()]   torch/tinygrad fp: 0.03 / 33.94 ms  bp: 0.32 / 33.47 ms 
testing                     [(64, 64), (64, 64)]   torch/tinygrad fp: 0.03 / 33.30 ms  bp: 0.57 / 35.01 ms 
testing                     [(64, 64), (64, 64)]   torch/tinygrad fp: 0.04 / 0.95 ms  bp: 0.39 / 1.44 ms 
testing                                 [(), ()]   torch/tinygrad fp: 0.02 / 28.47 ms  bp: 0.42 / 63.71 ms 
testing                               [(45, 65)]   torch/tinygrad fp: 0.05 / 31.78 ms  bp: 0.44 / 33.91 ms 
testing                               [(45, 65)]   torch/tinygrad fp: 0.05 / 31.93 ms  bp: 0.45 / 36.99 ms 
testing                               [(45, 65)]   torch/tinygrad fp: 0.05 / 35.00 ms  bp: 0.44 / 35.35 ms 
testing                                       []   torch/tinygrad fp: 0.14 / 32.54 ms  bp: nan / nan ms 
testing                                       []   torch/tinygrad fp: 0.14 / 32.23 ms  bp: nan / nan ms ok
test_multicat (__main__.TestOps) ... ok
test_multidot (__main__.TestOps) ... ok
test_multinomial (__main__.TestOps) ... ok
test_neg (__main__.TestOps) ... ok
test_negative_padding_conv2d (__main__.TestOps) ... ok
test_nested_conv2d (__main__.TestOps) ... ok
test_one_hot (__main__.TestOps) ... ok
test_ones (__main__.TestOps) ... ok
test_ones_like (__main__.TestOps) ... ok
test_output_padded_conv_transpose2d (__main__.TestOps) ... ok
test_pad (__main__.TestOps) ... ok
test_pad2d (__main__.TestOps) ... ok
test_pad_slice (__main__.TestOps) ... ok
test_padded_conv2d_1x1 (__main__.TestOps) ... ok
test_padded_conv2d_bs1 (__main__.TestOps) ... ok
test_padded_conv2d_p21 (__main__.TestOps) ... ok
test_padded_conv2d_p22 (__main__.TestOps) ... ok
test_padded_conv3d (__main__.TestOps) ... ok
test_padded_conv_transpose2d (__main__.TestOps) ... 
testing                                       []   torch/tinygrad fp: 0.08 / 29.95 ms  bp: nan / nan ms 
testing           [(45, 65), (45, 65), (45, 65)]   torch/tinygrad fp: 0.04 / 42.37 ms  bp: 0.37 / 65.54 ms 
testing           [(45, 65), (45, 65), (45, 65)]   torch/tinygrad fp: 0.04 / 37.53 ms  bp: 0.49 / 37.15 ms 
testing           [(45, 65), (45, 65), (45, 65)]   torch/tinygrad fp: 0.04 / 0.85 ms  bp: 0.31 / 0.70 ms 
testing             [(10, 45, 65), (10, 65, 45)]   torch/tinygrad fp: 0.66 / 59.88 ms  bp: 1.29 / 105.76 ms 
testing         [(3, 3, 45, 65), (3, 3, 65, 45)]   torch/tinygrad fp: 0.71 / 60.27 ms  bp: 0.93 / 170.64 ms 
testing                                [(1000,)]   torch/tinygrad fp: 1.12 / 164.43 ms  bp: nan / nan ms 
testing                               [(45, 65)]   torch/tinygrad fp: 0.03 / 31.37 ms  bp: 0.33 / 33.25 ms 
testing                               [(45, 65)]   torch/tinygrad fp: 0.03 / 0.37 ms  bp: 0.27 / 0.65 ms 
testing                                     [()]   torch/tinygrad fp: 0.01 / 27.85 ms  bp: 0.31 / 0.47 ms 
testing           [(1, 1, 10, 10), (1, 1, 3, 3)]   torch/tinygrad fp: 0.56 / 46.08 ms  bp: 0.89 / 149.55 ms 
testing           [(1, 1, 10, 10), (1, 1, 3, 3)]   torch/tinygrad fp: 0.60 / 43.55 ms  bp: 1.15 / 213.90 ms 
testing [(1, 32, 9, 9), (32, 32, 3, 3), (32, 32, 3, 3)]   torch/tinygrad fp: 0.83 / 122.80 ms  bp: 1.21 / 882.45 ms 
testing                                       []   torch/tinygrad fp: 0.62 / 39.59 ms  bp: nan / nan ms 
testing                                       []   torch/tinygrad fp: 0.18 / 69.45 ms  bp: nan / nan ms 
testing                                       []   torch/tinygrad fp: 0.05 / 0.11 ms  bp: nan / nan ms 
testing                                       []   torch/tinygrad fp: 0.06 / 0.17 ms  bp: nan / nan ms 
testing                                       []   torch/tinygrad fp: 0.02 / 0.07 ms  bp: nan / nan ms 
testing                                       []   torch/tinygrad fp: 0.03 / 0.10 ms  bp: nan / nan ms 
testing       [(2, 4, 6, 5), (4, 4, 3, 3), (4,)]   torch/tinygrad fp: 1.84 / 136.01 ms  bp: 8.12 / 623.57 ms 
testing       [(2, 4, 6, 5), (4, 4, 3, 3), (4,)]   torch/tinygrad fp: 0.99 / 142.59 ms  bp: 7.78 / 409.52 ms 
testing                                 [(3, 3)]   torch/tinygrad fp: 0.11 / 0.56 ms  bp: 0.34 / 38.45 ms 
testing                                 [(3, 3)]   torch/tinygrad fp: 0.08 / 77.20 ms  bp: 0.34 / 33.91 ms 
testing                                 [(3, 3)]   torch/tinygrad fp: 0.08 / 38.92 ms  bp: 0.46 / 1.28 ms 
testing                                 [(3, 3)]   torch/tinygrad fp: 0.07 / 39.38 ms  bp: 0.34 / 0.77 ms 
testing                                 [(3, 3)]   torch/tinygrad fp: 0.04 / 40.87 ms  bp: 0.46 / 36.21 ms 
testing                                 [(3, 3)]   torch/tinygrad fp: 0.05 / 0.26 ms  bp: 0.38 / 36.30 ms 
testing                           [(3, 3, 3, 3)]   torch/tinygrad fp: 0.08 / 0.33 ms  bp: 0.35 / 70.80 ms 
testing                           [(3, 3, 3, 3)]   torch/tinygrad fp: 0.07 / 0.38 ms  bp: 0.35 / 32.03 ms 
testing                           [(3, 3, 3, 3)]   torch/tinygrad fp: 0.11 / 43.90 ms  bp: 0.35 / 33.97 ms 
testing                           [(3, 3, 3, 3)]   torch/tinygrad fp: 0.07 / 46.68 ms  bp: 0.46 / 40.85 ms 
testing                                      [1]   torch/tinygrad fp: 0.12 / 0.67 ms  bp: 0.49 / 30.88 ms 
testing                                      [4]   torch/tinygrad fp: 0.09 / 0.43 ms  bp: 0.27 / 0.48 ms 
testing                                      [4]   torch/tinygrad fp: 0.11 / 0.64 ms  bp: 0.39 / 31.48 ms 
testing                                      [4]   torch/tinygrad fp: 0.09 / 0.40 ms  bp: 0.38 / 0.85 ms 
testing                                      [4]   torch/tinygrad fp: 0.05 / 0.52 ms  bp: 0.35 / 67.54 ms 
testing                                 [(5, 5)]   torch/tinygrad fp: 0.11 / 0.73 ms  bp: 0.56 / 35.10 ms 
testing                                 [(2, 2)]   torch/tinygrad fp: 0.13 / 0.72 ms  bp: 0.36 / 28.56 ms 
testing                                 [(4, 4)]   torch/tinygrad fp: 0.12 / 0.68 ms  bp: 0.39 / 0.85 ms 
testing                                 [(4, 4)]   torch/tinygrad fp: 0.11 / 0.80 ms  bp: 0.39 / 31.53 ms 
testing                                 [(4, 4)]   torch/tinygrad fp: 0.08 / 0.39 ms  bp: 0.35 / 61.89 ms 
testing                                 [(4, 4)]   torch/tinygrad fp: 0.10 / 0.43 ms  bp: 0.28 / 0.52 ms 
testing                                 [(4, 4)]   torch/tinygrad fp: 0.07 / 0.59 ms  bp: 0.37 / 31.12 ms 
testing                                 [(4, 4)]   torch/tinygrad fp: 0.10 / 0.79 ms  bp: 0.36 / 63.79 ms 
testing                                 [(4, 4)]   torch/tinygrad fp: 0.14 / 0.72 ms  bp: 0.37 / 58.14 ms 
testing                                 [(4, 4)]   torch/tinygrad fp: 0.10 / 0.43 ms  bp: 0.50 / 35.16 ms 
testing                                 [(3, 3)]   torch/tinygrad fp: 0.09 / 0.54 ms  bp: 0.36 / 31.41 ms 
testing                                 [(3, 3)]   torch/tinygrad fp: 0.10 / 0.44 ms  bp: 0.49 / 35.33 ms 
testing                              [(3, 3, 3)]   torch/tinygrad fp: 0.24 / 0.67 ms  bp: 0.51 / 63.67 ms 
testing                              [(3, 3, 3)]   torch/tinygrad fp: 0.14 / 0.88 ms  bp: 0.56 / 41.83 ms 
testing                                      [1]   torch/tinygrad fp: 0.09 / 34.63 ms  bp: 0.47 / 1.01 ms 
testing                                      [4]   torch/tinygrad fp: 0.07 / 33.02 ms  bp: 0.45 / 0.85 ms 
testing                                      [4]   torch/tinygrad fp: 0.07 / 36.83 ms  bp: 0.37 / 0.76 ms 
testing                                      [4]   torch/tinygrad fp: 0.08 / 35.91 ms  bp: 0.47 / 31.01 ms 
testing                                      [4]   torch/tinygrad fp: 0.09 / 1.45 ms  bp: 0.47 / 35.31 ms 
testing                                 [(5, 5)]   torch/tinygrad fp: 0.09 / 41.65 ms  bp: 0.36 / 32.07 ms 
testing                                 [(2, 2)]   torch/tinygrad fp: 0.10 / 33.83 ms  bp: 0.49 / 30.97 ms 
testing                                 [(4, 4)]   torch/tinygrad fp: 0.09 / 39.67 ms  bp: 0.36 / 0.51 ms 
testing                                 [(4, 4)]   torch/tinygrad fp: 0.05 / 39.94 ms  bp: 0.37 / 31.51 ms 
testing                                 [(4, 4)]   torch/tinygrad fp: 0.08 / 185.57 ms  bp: 0.48 / 37.50 ms 
testing                                 [(4, 4)]   torch/tinygrad fp: 0.10 / 43.03 ms  bp: 0.49 / 35.18 ms 
testing                                 [(4, 4)]   torch/tinygrad fp: 0.14 / 1.91 ms  bp: 0.51 / 36.56 ms 
testing                                 [(4, 4)]   torch/tinygrad fp: 0.09 / 39.09 ms  bp: 0.58 / 34.50 ms 
testing                                 [(4, 4)]   torch/tinygrad fp: 0.14 / 1.82 ms  bp: 0.38 / 33.40 ms 
testing                                 [(4, 4)]   torch/tinygrad fp: 0.10 / 0.91 ms  bp: 0.51 / 34.72 ms 
testing                                 [(3, 3)]   torch/tinygrad fp: 0.09 / 41.15 ms  bp: 0.49 / 37.85 ms 
testing                                 [(3, 3)]   torch/tinygrad fp: 0.13 / 42.65 ms  bp: 0.55 / 35.53 ms 
testing                              [(3, 3, 3)]   torch/tinygrad fp: 0.13 / 51.20 ms  bp: 0.51 / 36.86 ms 
testing                              [(3, 3, 3)]   torch/tinygrad fp: 0.10 / 1.07 ms  bp: 0.37 / 34.00 ms 
testing           [(4, 3, 11, 28), (4, 3, 1, 1)]   torch/tinygrad fp: 1.31 / 58.74 ms  bp: 1.32 / 521.02 ms 
testing           [(1, 3, 11, 28), (4, 3, 3, 3)]   torch/tinygrad fp: 1.03 / 100.25 ms  bp: 1.19 / 455.32 ms 
testing           [(4, 3, 11, 28), (4, 3, 3, 3)]   torch/tinygrad fp: 1.34 / 133.70 ms  bp: 3.54 / 485.34 ms 
testing           [(4, 3, 11, 28), (4, 3, 3, 3)]   torch/tinygrad fp: 1.23 / 159.07 ms  bp: 2.38 / 494.72 ms 
testing       [(1, 4, 9, 9, 9), (4, 4, 3, 3, 3)]   torch/tinygrad fp: 1.40 / 133.49 ms  bp: 2.25 / 545.51 ms 
testing             [(2, 4, 9, 9), (4, 4, 3, 3)]   torch/tinygrad fp: 2.79 / 82.26 ms  bp: 6.30 / 351.26 ms 
testing             [(2, 4, 9, 9), (4, 4, 3, 3)]   torch/tinygrad fp: 1.64 / 80.11 ms  bp: 4.51 / 263.02 ms ok
test_padding_add (__main__.TestOps) ... ok
test_pow (__main__.TestOps) ... ok
test_pow_const (__main__.TestOps) ... ok
test_pow_full (__main__.TestOps) ... ok
test_quick_gelu (__main__.TestOps) ... ok
test_relu (__main__.TestOps) ... ok
test_relu6 (__main__.TestOps) ... ok
test_relu_exact (__main__.TestOps) ... ok
test_relu_maximum_exact (__main__.TestOps) ... ok
test_repeat (__main__.TestOps) ... ok
test_reshape (__main__.TestOps) ... ok
test_round (__main__.TestOps) ... ok
test_rsqrt (__main__.TestOps) ... ok
test_scalar_div (__main__.TestOps) ... ok
test_scalar_mul (__main__.TestOps) ... ok
test_scalar_rsub (__main__.TestOps) ... ok
test_scalar_sub (__main__.TestOps) ... ok
test_scaled_product_attention (__main__.TestOps) ... ok
test_scaled_product_attention_causal (__main__.TestOps) ... 
testing             [(2, 4, 9, 9), (4, 4, 3, 3)]   torch/tinygrad fp: 2.27 / 61.09 ms  bp: 4.43 / 295.81 ms 
testing             [(2, 4, 9, 9), (4, 4, 3, 3)]   torch/tinygrad fp: 6.29 / 88.40 ms  bp: 7.97 / 351.38 ms 
testing             [(2, 4, 9, 9), (4, 4, 3, 3)]   torch/tinygrad fp: 7.72 / 1.99 ms  bp: 6.49 / 2.60 ms 
testing                     [(64, 64), (60, 60)]   torch/tinygrad fp: 0.06 / 44.30 ms  bp: 0.36 / 0.79 ms 
testing                               [(45, 65)]   torch/tinygrad fp: 0.08 / 36.32 ms  bp: 0.45 / 0.77 ms 
testing                               [(45, 65)]   torch/tinygrad fp: 0.03 / 35.97 ms  bp: 0.46 / 38.66 ms 
testing                               [(45, 65)]   torch/tinygrad fp: 0.05 / 35.80 ms  bp: 0.45 / 38.34 ms 
testing                               [(45, 65)]   torch/tinygrad fp: 0.04 / 33.37 ms  bp: 0.45 / 39.52 ms 
testing                               [(45, 65)]   torch/tinygrad fp: 0.04 / 38.31 ms  bp: 0.56 / 43.05 ms 
testing                                     [()]   torch/tinygrad fp: 0.04 / 38.04 ms  bp: 0.31 / 31.03 ms 
testing                                     [()]   torch/tinygrad fp: 0.04 / 30.47 ms  bp: 0.42 / 35.17 ms 
testing                               [(45, 65)]   torch/tinygrad fp: 0.06 / 1.28 ms  bp: 0.44 / 1.80 ms 
testing                                     [()]   torch/tinygrad fp: 0.01 / 30.63 ms  bp: 0.43 / 34.70 ms 
testing                               [(45, 65)]   torch/tinygrad fp: 0.10 / 53.13 ms  bp: 0.49 / 72.95 ms 
testing                               [(45, 65)]   torch/tinygrad fp: 0.09 / 50.77 ms  bp: 0.50 / 75.59 ms 
testing                                     [()]   torch/tinygrad fp: 0.06 / 35.03 ms  bp: 0.31 / 43.04 ms 
testing                                     [()]   torch/tinygrad fp: 0.04 / 37.31 ms  bp: 0.31 / 48.72 ms 
testing                                       []   torch/tinygrad fp: 0.05 / 43.23 ms  bp: 0.54 / 2.90 ms 
testing                               [(45, 65)]   torch/tinygrad fp: 0.03 / 0.82 ms  bp: 0.15 / 0.73 ms 
testing                               [(45, 65)]   torch/tinygrad fp: 0.02 / 33.80 ms  bp: 0.35 / 43.44 ms 
testing                               [(45, 65)]   torch/tinygrad fp: 0.07 / 34.47 ms  bp: 0.45 / 0.80 ms 
testing                               [(45, 65)]   torch/tinygrad fp: 0.03 / 1.06 ms  bp: 0.27 / 1.24 ms 
testing                               [(45, 65)]   torch/tinygrad fp: 0.06 / 0.48 ms  bp: 0.16 / 0.68 ms 
testing                                     [()]   torch/tinygrad fp: 0.01 / 0.27 ms  bp: 0.14 / 0.56 ms 
testing                                     [()]   torch/tinygrad fp: 0.02 / 0.24 ms  bp: 0.14 / 0.44 ms 
testing                                     None   torch/tinygrad fp: 0.02 / 60.36 ms  bp: nan / nan ms 
testing                     [(45, 65), (45, 65)]   torch/tinygrad fp: 0.06 / 94.00 ms  bp: 1.16 / 261.04 ms 
testing                     [(45, 65), (45, 65)]   torch/tinygrad fp: 0.05 / 4.47 ms  bp: 0.87 / 7.78 ms 
testing                               [(45, 65)]   torch/tinygrad fp: 0.05 / 38.57 ms  bp: 0.35 / 42.01 ms 
testing                               [(45, 65)]   torch/tinygrad fp: 0.08 / 0.74 ms  bp: 0.28 / 0.95 ms 
testing                               [(45, 65)]   torch/tinygrad fp: 0.03 / 0.59 ms  bp: 0.16 / 0.90 ms 
testing                                     [()]   torch/tinygrad fp: 0.03 / 31.06 ms  bp: 0.33 / 35.14 ms 
testing                               [(64, 64)]   torch/tinygrad fp: 0.03 / 34.11 ms  bp: 0.33 / 36.44 ms 
testing                                     [()]   torch/tinygrad fp: 0.03 / 29.59 ms  bp: 0.31 / 30.05 ms 
testing                               [(45, 65)]   torch/tinygrad fp: 0.05 / 35.11 ms  bp: 0.33 / 38.14 ms 
testing                                     [()]   torch/tinygrad fp: 0.04 / 31.12 ms  bp: 0.31 / 32.47 ms 
testing                                     None   torch/tinygrad fp: 0.04 / 31.76 ms  bp: 0.33 / 32.25 ms 
testing                                     None   torch/tinygrad fp: 0.09 / 31.23 ms  bp: 0.34 / 32.71 ms 
testing                              [(4, 6, 3)]   torch/tinygrad fp: 0.07 / 0.37 ms  bp: 0.48 / 67.76 ms 
testing                                     [()]   torch/tinygrad fp: 0.06 / 0.14 ms  bp: 0.35 / 68.04 ms 
testing                              [(4, 6, 3)]   torch/tinygrad fp: 0.08 / 0.37 ms  bp: 0.58 / 71.53 ms 
testing                                     [()]   torch/tinygrad fp: 0.08 / 0.25 ms  bp: 0.33 / 71.13 ms 
testing                              [(4, 6, 3)]   torch/tinygrad fp: 0.06 / 0.38 ms  bp: 0.35 / 70.98 ms 
testing                                     [()]   torch/tinygrad fp: 0.08 / 0.26 ms  bp: 0.46 / 67.91 ms 
testing                              [(4, 6, 3)]   torch/tinygrad fp: 0.40 / 0.66 ms  bp: 0.43 / 39.09 ms 
testing                                     [()]   torch/tinygrad fp: 0.06 / 0.16 ms  bp: 0.35 / 63.51 ms 
testing                           [(4, 3, 6, 6)]   torch/tinygrad fp: 0.03 / 0.25 ms  bp: 0.26 / 0.67 ms 
testing                           [(4, 3, 6, 6)]   torch/tinygrad fp: 0.01 / 0.22 ms  bp: 0.14 / 33.96 ms 
testing                                     [()]   torch/tinygrad fp: 0.03 / 0.02 ms  bp: 0.24 / 0.40 ms 
testing                                   [(1,)]   torch/tinygrad fp: 0.01 / 0.25 ms  bp: 0.20 / 0.37 ms 
testing                                     [()]   torch/tinygrad fp: 0.01 / 0.03 ms  bp: 0.13 / 0.42 ms 
testing                                     [()]   torch/tinygrad fp: 0.01 / 0.03 ms  bp: 0.31 / 28.44 ms 
testing                               [(45, 35)]   torch/tinygrad fp: 0.04 / 39.84 ms  bp: nan / nan ms 
testing                                     None   torch/tinygrad fp: 0.02 / 34.26 ms  bp: nan / nan ms 
testing                                     None   torch/tinygrad fp: 0.03 / 34.87 ms  bp: nan / nan ms 
testing                               [(45, 65)]   torch/tinygrad fp: 0.03 / 35.28 ms  bp: 0.33 / 36.74 ms 
testing                                     [()]   torch/tinygrad fp: 0.03 / 28.67 ms  bp: 0.31 / 30.56 ms 
testing                               [(45, 65)]   torch/tinygrad fp: 0.05 / 32.93 ms  bp: 0.32 / 34.46 ms 
testing                               [(45, 65)]   torch/tinygrad fp: 0.04 / 0.24 ms  bp: 0.25 / 0.65 ms 
testing                               [(45, 65)]   torch/tinygrad fp: 0.04 / 33.85 ms  bp: 0.34 / 35.01 ms 
testing                               [(45, 65)]   torch/tinygrad fp: 0.04 / 32.15 ms  bp: 0.44 / 38.93 ms 
testing                               [(45, 65)]   torch/tinygrad fp: 0.10 / 35.32 ms  bp: 0.46 / 37.03 ms 
testing                                     [()]   torch/tinygrad fp: 0.05 / 31.38 ms  bp: 0.30 / 0.50 ms 
testing                                     [()]   torch/tinygrad fp: 0.03 / 29.11 ms  bp: 0.45 / 32.42 ms 
testing                               [(45, 65)]   torch/tinygrad fp: 0.05 / 36.84 ms  bp: 0.32 / 35.27 ms 
testing                               [(45, 65)]   torch/tinygrad fp: 0.05 / 0.45 ms  bp: 0.25 / 0.65 ms 
testing                               [(45, 65)]   torch/tinygrad fp: 0.02 / 36.33 ms  bp: 0.32 / 37.29 ms 
testing                               [(45, 65)]   torch/tinygrad fp: 0.05 / 37.23 ms  bp: 0.32 / 0.75 ms 
testing                                     [()]   torch/tinygrad fp: 0.02 / 28.82 ms  bp: 0.40 / 30.99 ms 
testing                                     [()]   torch/tinygrad fp: 0.04 / 33.10 ms  bp: 0.41 / 0.90 ms 
testing                               [(45, 65)]   torch/tinygrad fp: 0.10 / 36.23 ms  bp: 0.32 / 1.10 ms 
testing                                     [()]   torch/tinygrad fp: 0.04 / 29.87 ms  bp: 0.30 / 0.49 ms 
testing                               [(45, 65)]   torch/tinygrad fp: 0.04 / 36.64 ms  bp: 0.33 / 0.78 ms 
testing                                     [()]   torch/tinygrad fp: 0.02 / 28.78 ms  bp: 0.39 / 0.77 ms 
testing [(32, 8, 16, 64), (32, 8, 16, 64), (32, 8, 16, 64)]   torch/tinygrad fp: 1.33 / 377.01 ms  bp: 4.37 / 1145.82 ms 
testing [(32, 8, 16, 64), (32, 8, 16, 64), (32, 8, 16, 64), (32, 8, 16, 16)]   torch/tinygrad fp: 0.92 / 72.14 ms  bp: 2.71 / 47.94 ms ok
test_sd_big_conv (__main__.TestOps) ... skipped 'very slow'
test_sigmoid (__main__.TestOps) ... ok
test_sign (__main__.TestOps) ... ok
test_simple_conv2d (__main__.TestOps) ... ok
test_simple_conv2d_1x1 (__main__.TestOps) ... ok
test_simple_conv2d_1x1_m4 (__main__.TestOps) ... ok
test_simple_conv2d_batched (__main__.TestOps) ... ok
test_simple_conv2d_m4 (__main__.TestOps) ... ok
test_simple_conv2d_nhwc (__main__.TestOps) ... ok
test_simple_conv3d (__main__.TestOps) ... ok
test_simple_conv_transpose2d (__main__.TestOps) ... ok
test_simple_conv_transpose3d (__main__.TestOps) ... ok
test_simple_cumsum (__main__.TestOps) ... ok
test_simple_grouped_conv2d (__main__.TestOps) ... ok
test_simple_padding_conv1d (__main__.TestOps) ... ok
test_simple_padding_conv2d (__main__.TestOps) ... ok
test_simple_repeat (__main__.TestOps) ... ok
test_sin (__main__.TestOps) ... ok
test_sinh (__main__.TestOps) ... ok
test_slice_both_endpoints_out_of_bounds (__main__.TestOps) ... ok
test_slice_ellipsis (__main__.TestOps) ... ok
test_slice_empty (__main__.TestOps) ... ok
test_slice_errors (__main__.TestOps) ... ok
test_slice_fancy_indexing_dim_collapse_int (__main__.TestOps) ... ok
test_slice_fancy_indexing_dim_inject_and_collapse (__main__.TestOps) ... ok
test_slice_fancy_indexing_dim_inject_none (__main__.TestOps) ... ok
test_slice_fancy_indexing_errors (__main__.TestOps) ... ok
test_slice_fancy_indexing_list_indices (__main__.TestOps) ... ok
test_slice_fancy_indexing_list_with_tensors (__main__.TestOps) ... ok
test_slice_fancy_indexing_no_dim_collapse (__main__.TestOps) ... ok
test_slice_fancy_indexing_tuple_indices (__main__.TestOps) ... ok
test_slice_fancy_indexing_with_tensors (__main__.TestOps) ... ok
test_slice_in_bounds_1dim (__main__.TestOps) ... 
testing [(32, 8, 16, 64), (32, 8, 16, 64), (32, 8, 16, 64)]   torch/tinygrad fp: 0.39 / 255.00 ms  bp: 2.63 / 3.28 ms 
testing                               [(45, 65)]   torch/tinygrad fp: 0.03 / 38.86 ms  bp: 0.47 / 39.94 ms 
testing                               [(45, 65)]   torch/tinygrad fp: 0.03 / 0.84 ms  bp: 0.26 / 0.74 ms 
testing                               [(45, 65)]   torch/tinygrad fp: 0.01 / 0.50 ms  bp: 0.27 / 1.36 ms 
testing                                     [()]   torch/tinygrad fp: 0.02 / 34.45 ms  bp: 0.31 / 33.45 ms 
testing                               [(45, 65)]   torch/tinygrad fp: 0.04 / 41.24 ms  bp: 0.45 / 46.31 ms 
testing                                     [()]   torch/tinygrad fp: 0.03 / 33.88 ms  bp: 0.31 / 38.57 ms 
testing             [(1, 4, 9, 9), (4, 4, 3, 3)]   torch/tinygrad fp: 0.66 / 55.25 ms  bp: 1.04 / 258.30 ms 
testing             [(1, 4, 9, 9), (4, 4, 1, 1)]   torch/tinygrad fp: 0.11 / 41.51 ms  bp: 0.86 / 119.28 ms 
testing        [(1, 16, 32, 32), (16, 16, 1, 1)]   torch/tinygrad fp: 0.79 / 107.76 ms  bp: 1.60 / 228.31 ms 
testing             [(2, 4, 9, 9), (4, 4, 3, 3)]   torch/tinygrad fp: 1.03 / 57.30 ms  bp: 4.28 / 43.03 ms 
testing        [(1, 16, 18, 18), (16, 16, 3, 3)]   torch/tinygrad fp: 0.36 / 97.09 ms  bp: 1.29 / 287.46 ms 
testing          [(2, 9, 9, 10), (3, 3, 10, 20)]   torch/tinygrad fp: 4.52 / 63.56 ms  bp: 3.84 / 324.84 ms 
testing       [(1, 4, 9, 9, 9), (4, 4, 3, 3, 3)]   torch/tinygrad fp: 3.42 / 109.55 ms  bp: 1.75 / 404.14 ms 
testing             [(2, 4, 9, 9), (4, 4, 3, 3)]   torch/tinygrad fp: 8.55 / 2.08 ms  bp: 5.56 / 1.45 ms 
testing       [(2, 4, 9, 9, 9), (4, 4, 3, 3, 3)]   torch/tinygrad fp: 1.00 / 148.57 ms  bp: 2.53 / 661.21 ms 
testing                                    [512]   torch/tinygrad fp: 0.04 / 60.89 ms  bp: 0.49 / 116.30 ms 
testing                                   [1022]   torch/tinygrad fp: 0.03 / 133.21 ms  bp: 0.46 / 235.55 ms 
testing             [(1, 4, 1, 1), (2, 2, 1, 1)]   torch/tinygrad fp: 0.88 / 33.22 ms  bp: 1.79 / 65.05 ms 
testing                  [(6, 2, 11), (6, 2, 5)]   torch/tinygrad fp: 1.41 / 56.73 ms  bp: 3.99 / 207.75 ms 
testing                                     None   torch/tinygrad fp: 0.16 / 38.50 ms  bp: 0.56 / 107.65 ms 
testing                                 [(3, 3)]   torch/tinygrad fp: 0.06 / 0.36 ms  bp: 0.33 / 34.70 ms 
testing                               [(45, 65)]   torch/tinygrad fp: 0.82 / 55.29 ms  bp: 0.78 / 74.13 ms 
testing                                     [()]   torch/tinygrad fp: 0.03 / 33.77 ms  bp: 0.31 / 37.99 ms 
testing                               [(45, 65)]   torch/tinygrad fp: 0.04 / 37.79 ms  bp: 0.47 / 43.02 ms 
testing                               [(45, 65)]   torch/tinygrad fp: 0.03 / 0.74 ms  bp: nan / nan ms 
testing                               [(45, 65)]   torch/tinygrad fp: 0.02 / 0.62 ms  bp: nan / nan ms 
testing                              [(3, 3, 3)]   torch/tinygrad fp: 0.04 / 0.26 ms  bp: 0.35 / 0.83 ms 
testing                              [(3, 3, 3)]   torch/tinygrad fp: 0.04 / 0.26 ms  bp: 0.36 / 0.81 ms 
testing                           [(3, 3, 3, 3)]   torch/tinygrad fp: 0.03 / 0.63 ms  bp: 0.44 / 67.20 ms 
testing                           [(3, 3, 3, 3)]   torch/tinygrad fp: 0.04 / 0.39 ms  bp: 0.44 / 33.83 ms 
testing                           [(3, 3, 3, 3)]   torch/tinygrad fp: 0.04 / 0.42 ms  bp: 0.33 / 37.89 ms 
testing                           [(3, 3, 3, 3)]   torch/tinygrad fp: 0.04 / 0.37 ms  bp: 0.33 / 33.76 ms 
testing                           [(3, 3, 3, 3)]   torch/tinygrad fp: 0.05 / 0.39 ms  bp: 0.34 / 33.53 ms 
testing                               [(10, 10)]   torch/tinygrad fp: 0.04 / 0.26 ms  bp: 0.35 / 0.84 ms 
testing                     [(2, 5, 6, 5, 3, 4)]   torch/tinygrad fp: 0.18 / 458.74 ms  bp: 0.43 / 241.57 ms 
testing                     [(2, 5, 6, 5, 3, 4)]   torch/tinygrad fp: 0.11 / 299.45 ms  bp: 0.55 / 191.30 ms 
testing                     [(2, 5, 6, 5, 3, 4)]   torch/tinygrad fp: 0.10 / 160.66 ms  bp: 0.57 / 150.13 ms 
testing                     [(2, 5, 6, 5, 3, 4)]   torch/tinygrad fp: 0.10 / 119.88 ms  bp: 0.55 / 111.76 ms 
testing                     [(2, 5, 6, 5, 3, 4)]   torch/tinygrad fp: 0.10 / 81.51 ms  bp: 0.41 / 80.55 ms 
testing                     [(2, 5, 6, 5, 3, 4)]   torch/tinygrad fp: 0.15 / 162.66 ms  bp: 0.57 / 117.02 ms 
testing                     [(2, 5, 6, 5, 3, 4)]   torch/tinygrad fp: 0.11 / 195.57 ms  bp: 0.57 / 164.23 ms 
testing                     [(2, 5, 6, 5, 3, 4)]   torch/tinygrad fp: 0.10 / 110.37 ms  bp: 0.56 / 115.74 ms 
testing                     [(2, 5, 6, 5, 3, 4)]   torch/tinygrad fp: 0.66 / 391.07 ms  bp: 0.64 / 262.75 ms 
testing                     [(2, 5, 6, 5, 3, 4)]   torch/tinygrad fp: 0.10 / 332.13 ms  bp: 0.55 / 208.59 ms 
testing                     [(2, 5, 6, 5, 3, 4)]   torch/tinygrad fp: 0.16 / 257.31 ms  bp: 0.57 / 233.14 ms 
testing                     [(2, 5, 6, 5, 3, 4)]   torch/tinygrad fp: 1.03 / 207.28 ms  bp: 0.58 / 217.17 ms 
testing                     [(2, 5, 6, 5, 3, 4)]   torch/tinygrad fp: 0.60 / 185.84 ms  bp: 0.59 / 173.98 ms 
testing                     [(2, 5, 6, 5, 3, 4)]   torch/tinygrad fp: 0.10 / 102.66 ms  bp: 0.50 / 71.47 ms 
testing                     [(2, 5, 6, 5, 3, 4)]   torch/tinygrad fp: 0.12 / 122.42 ms  bp: 0.59 / 114.81 ms 
testing                     [(2, 5, 6, 5, 3, 4)]   torch/tinygrad fp: 0.18 / 192.30 ms  bp: 0.54 / 77.15 ms 
testing                     [(2, 5, 6, 5, 3, 4)]   torch/tinygrad fp: 0.13 / 239.34 ms  bp: 0.58 / 208.85 ms 
testing                     [(2, 5, 6, 5, 3, 4)]   torch/tinygrad fp: 0.10 / 275.62 ms  bp: 0.37 / 232.37 ms 
testing                     [(2, 5, 6, 5, 3, 4)]   torch/tinygrad fp: 0.16 / 113.83 ms  bp: 0.53 / 78.94 ms 
testing                     [(2, 5, 6, 5, 3, 4)]   torch/tinygrad fp: 0.17 / 213.64 ms  bp: 0.52 / 226.69 ms 
testing                     [(2, 5, 6, 5, 3, 4)]   torch/tinygrad fp: 0.49 / 2.61 ms  bp: 0.41 / 35.04 ms 
testing                     [(2, 5, 6, 5, 3, 4)]   torch/tinygrad fp: 0.08 / 39.96 ms  bp: 0.36 / 71.61 ms 
testing                     [(2, 5, 6, 5, 3, 4)]   torch/tinygrad fp: 0.09 / 108.49 ms  bp: 0.50 / 75.38 ms 
testing                     [(2, 5, 6, 5, 3, 4)]   torch/tinygrad fp: 0.09 / 5.96 ms  bp: 0.42 / 1.76 ms 
testing                     [(2, 5, 6, 5, 3, 4)]   torch/tinygrad fp: 0.08 / 47.99 ms  bp: 0.57 / 46.75 ms 
testing                     [(2, 5, 6, 5, 3, 4)]   torch/tinygrad fp: 0.20 / 12.91 ms  bp: 0.32 / 1.54 ms 
testing                     [(2, 5, 6, 5, 3, 4)]   torch/tinygrad fp: 0.07 / 132.19 ms  bp: 0.66 / 177.95 ms 
testing                     [(2, 5, 6, 5, 3, 4)]   torch/tinygrad fp: 0.08 / 4.66 ms  bp: 0.44 / 35.75 ms 
testing                     [(2, 5, 6, 5, 3, 4)]   torch/tinygrad fp: 0.52 / 124.70 ms  bp: 0.53 / 116.88 ms 
testing                     [(2, 5, 6, 5, 3, 4)]   torch/tinygrad fp: 0.58 / 158.52 ms  bp: 0.41 / 157.03 ms 
testing                     [(2, 5, 6, 5, 3, 4)]   torch/tinygrad fp: 0.10 / 73.21 ms  bp: 0.50 / 70.53 ms 
testing                     [(2, 5, 6, 5, 3, 4)]   torch/tinygrad fp: 0.12 / 6.63 ms  bp: 0.31 / 1.37 ms 
testing                     [(2, 5, 6, 5, 3, 4)]   torch/tinygrad fp: 0.08 / 5.48 ms  bp: 0.21 / 1.36 ms 
testing                     [(2, 5, 6, 5, 3, 4)]   torch/tinygrad fp: 0.06 / 5.75 ms  bp: 0.21 / 1.38 ms 
testing                     [(2, 5, 6, 5, 3, 4)]   torch/tinygrad fp: 0.06 / 171.58 ms  bp: 0.52 / 155.77 ms 
testing                     [(2, 5, 6, 5, 3, 4)]   torch/tinygrad fp: 0.19 / 270.86 ms  bp: 0.56 / 199.26 ms 
testing                                 [(2, 3)]   torch/tinygrad fp: 0.09 / 75.91 ms  bp: 0.47 / 74.44 ms 
testing                                 [(2, 3)]   torch/tinygrad fp: 0.09 / 112.47 ms  bp: 0.47 / 74.93 ms 
testing                                 [(2, 3)]   torch/tinygrad fp: 0.12 / 172.46 ms  bp: 0.45 / 71.11 ms 
testing                                 [(2, 3)]   torch/tinygrad fp: 0.09 / 6.44 ms  bp: 0.26 / 0.93 ms ok
test_slice_in_bounds_multidim (__main__.TestOps) ... ok
test_slice_int_indexing (__main__.TestOps) ... ok
test_slice_negative_strides (__main__.TestOps) ... ok
test_slice_on_0dim_tensor (__main__.TestOps) ... ok
test_slice_one_endpoint_out_of_bounds (__main__.TestOps) ... ok
test_slice_start_gt_end (__main__.TestOps) ... ok
test_slice_stride_gt_one (__main__.TestOps) ... ok
test_slice_with_none (__main__.TestOps) ... ok
test_slice_zero_in_shape (__main__.TestOps) ... ok
test_small_cumsum (__main__.TestOps) ... ok
test_small_gemm (__main__.TestOps) ... ok
test_small_gemm_eye (__main__.TestOps) ... ok
test_small_gemm_range (__main__.TestOps) ... ok
test_softmax (__main__.TestOps) ... ok
test_softplus (__main__.TestOps) ... ok
test_softsign (__main__.TestOps) ... ok
test_split (__main__.TestOps) ... ok
test_sqrt (__main__.TestOps) ... ok
test_squeeze (__main__.TestOps) ... 
testing                                      [3]   torch/tinygrad fp: 0.02 / 0.26 ms  bp: 0.31 / 31.80 ms 
testing                                      [3]   torch/tinygrad fp: 0.03 / 0.34 ms  bp: 0.32 / 30.84 ms 
testing                                      [3]   torch/tinygrad fp: 0.03 / 0.34 ms  bp: 0.31 / 32.07 ms 
testing                              [(3, 3, 3)]   torch/tinygrad fp: 0.03 / 0.35 ms  bp: 0.32 / 31.76 ms 
testing                              [(3, 3, 3)]   torch/tinygrad fp: 0.05 / 0.39 ms  bp: 0.33 / 31.82 ms 
testing                              [(3, 3, 3)]   torch/tinygrad fp: 0.04 / 0.35 ms  bp: 0.33 / 31.06 ms 
testing                              [(3, 3, 3)]   torch/tinygrad fp: 0.04 / 0.36 ms  bp: 0.33 / 31.74 ms 
testing                                      [3]   torch/tinygrad fp: 0.03 / 0.35 ms  bp: 0.25 / 0.45 ms 
testing                                      [3]   torch/tinygrad fp: 0.04 / 0.68 ms  bp: 0.38 / 0.94 ms 
testing                                      [3]   torch/tinygrad fp: 0.04 / 0.55 ms  bp: 0.35 / 0.78 ms 
testing                                      [3]   torch/tinygrad fp: 0.02 / 0.46 ms  bp: 0.13 / 0.38 ms 
testing                               [(10, 10)]   torch/tinygrad fp: 0.01 / 0.29 ms  bp: 0.31 / 31.69 ms 
testing                              [(3, 3, 3)]   torch/tinygrad fp: 0.04 / 0.39 ms  bp: 0.34 / 33.30 ms 
testing                                     [()]   torch/tinygrad fp: 0.02 / 0.07 ms  bp: 0.25 / 0.47 ms 
testing                              [(3, 3, 3)]   torch/tinygrad fp: 0.02 / 0.27 ms  bp: 0.26 / 1.09 ms 
testing                              [(3, 3, 3)]   torch/tinygrad fp: 0.02 / 0.40 ms  bp: 0.25 / 1.07 ms 
testing                              [(3, 3, 3)]   torch/tinygrad fp: 0.02 / 0.49 ms  bp: 0.42 / 36.40 ms 
testing                              [(3, 3, 3)]   torch/tinygrad fp: 0.08 / 0.65 ms  bp: 0.40 / 32.11 ms 
testing                              [(3, 3, 3)]   torch/tinygrad fp: 0.03 / 0.33 ms  bp: 0.38 / 1.18 ms 
testing                              [(3, 3, 3)]   torch/tinygrad fp: 0.02 / 0.19 ms  bp: 0.24 / 0.70 ms 
testing                             [(7, 5, 10)]   torch/tinygrad fp: 0.02 / 0.41 ms  bp: 0.33 / 34.20 ms 
testing                             [(7, 5, 10)]   torch/tinygrad fp: 0.04 / 0.67 ms  bp: 0.46 / 39.58 ms 
testing                             [(7, 5, 10)]   torch/tinygrad fp: 0.07 / 0.91 ms  bp: 0.48 / 36.74 ms 
testing                             [(7, 5, 10)]   torch/tinygrad fp: 0.09 / 0.75 ms  bp: 0.51 / 35.71 ms 
testing                              [(3, 3, 3)]   torch/tinygrad fp: 0.02 / 0.32 ms  bp: 0.38 / 36.63 ms 
testing                              [(3, 3, 3)]   torch/tinygrad fp: 0.05 / 0.58 ms  bp: 0.44 / 37.44 ms 
testing                              [(3, 3, 3)]   torch/tinygrad fp: 0.06 / 0.56 ms  bp: 0.33 / 32.24 ms 
testing                              [(3, 3, 3)]   torch/tinygrad fp: 0.06 / 0.33 ms  bp: 0.47 / 30.82 ms 
testing                              [(3, 3, 3)]   torch/tinygrad fp: 0.08 / 0.63 ms  bp: 0.36 / 35.50 ms 
testing                               [(10, 10)]   torch/tinygrad fp: 0.04 / 0.21 ms  bp: 0.35 / 0.78 ms 
testing                              [(3, 3, 3)]   torch/tinygrad fp: 0.02 / 0.19 ms  bp: 0.24 / 0.69 ms 
testing                                     [10]   torch/tinygrad fp: 0.03 / 41.44 ms  bp: 0.43 / 84.64 ms 
testing                         [(8, 8), (8, 8)]   torch/tinygrad fp: 0.06 / 39.59 ms  bp: 0.34 / 118.06 ms 
testing                                     None   torch/tinygrad fp: 0.06 / 1.50 ms  bp: 0.43 / 1.49 ms 
testing                                     None   torch/tinygrad fp: 0.02 / 0.58 ms  bp: 0.15 / 0.92 ms 
testing                               [(45, 65)]   torch/tinygrad fp: 0.50 / 39.80 ms  bp: 1.30 / 145.00 ms 
testing                                     [()]   torch/tinygrad fp: 0.05 / 33.68 ms  bp: 0.43 / 34.89 ms 
testing                               [(45, 65)]   torch/tinygrad fp: 0.10 / 40.53 ms  bp: 0.33 / 42.18 ms 
testing                                     [()]   torch/tinygrad fp: 0.04 / 34.34 ms  bp: 0.29 / 30.31 ms 
testing                               [(45, 65)]   torch/tinygrad fp: 0.11 / 38.39 ms  bp: 0.49 / 46.65 ms 
testing                                     [()]   torch/tinygrad fp: 0.07 / 32.69 ms  bp: 0.44 / 35.63 ms 
testing                                       []   torch/tinygrad fp: 0.00 / 0.20 ms  bp: nan / nan ms 
testing                                       []   torch/tinygrad fp: 0.00 / 0.02 ms  bp: nan / nan ms 
testing                                       []   torch/tinygrad fp: 0.00 / 0.36 ms  bp: nan / nan ms 
testing                                       []   torch/tinygrad fp: 0.00 / 0.02 ms  bp: nan / nan ms 
testing                                       []   torch/tinygrad fp: 0.00 / 0.01 ms  bp: nan / nan ms 
testing                                       []   torch/tinygrad fp: 0.00 / 0.19 ms  bp: nan / nan ms 
testing                                       []   torch/tinygrad fp: 0.00 / 0.02 ms  bp: nan / nan ms 
testing                                       []   torch/tinygrad fp: 0.00 / 0.01 ms  bp: nan / nan ms 
testing                                       []   torch/tinygrad fp: 0.00 / 0.01 ms  bp: nan / nan ms 
testing                                       []   torch/tinygrad fp: 0.00 / 39.51 ms  bp: nan / nan ms 
testing                                       []   torch/tinygrad fp: 0.00 / 0.02 ms  bp: nan / nan ms 
testing                                       []   torch/tinygrad fp: 0.00 / 0.02 ms  bp: nan / nan ms 
testing                                       []   torch/tinygrad fp: 0.00 / 0.39 ms  bp: nan / nan ms 
testing                                       []   torch/tinygrad fp: 0.00 / 0.02 ms  bp: nan / nan ms 
testing                                       []   torch/tinygrad fp: 0.00 / 154.02 ms  bp: nan / nan ms 
testing                                       []   torch/tinygrad fp: 0.00 / 0.02 ms  bp: nan / nan ms 
testing                                       []   torch/tinygrad fp: 0.00 / 0.02 ms  bp: nan / nan ms 
testing                                       []   torch/tinygrad fp: 0.00 / 0.02 ms  bp: nan / nan ms 
testing                               [(45, 65)]   torch/tinygrad fp: 0.51 / 33.00 ms  bp: 0.32 / 37.97 ms 
testing                                     [()]   torch/tinygrad fp: 0.04 / 33.59 ms  bp: 0.30 / 29.80 ms 
testing                           [(1, 3, 6, 6)]   torch/tinygrad fp: 0.05 / 0.51 ms  bp: 0.36 / 68.11 ms 
testing                           [(4, 3, 1, 6)]   torch/tinygrad fp: 0.04 / 0.43 ms  bp: 0.35 / 66.74 ms 
testing                           [(4, 3, 6, 6)]   torch/tinygrad fp: 0.03 / 0.24 ms  bp: 0.24 / 0.68 ms 
testing                           [(4, 3, 6, 6)]   torch/tinygrad exception: Dimension out of range (expected to be in range of [-4, 3], but got 50) / dim=50 out of range [-4, 3]
testing                           [(4, 3, 6, 6)]   torch/tinygrad exception: Dimension out of range (expected to be in range of [-4, 3], but got -50) / dim=-50 out of range [-4, 3]
testing                           [(4, 3, 6, 1)]   torch/tinygrad fp: 0.01 / 0.24 ms  bp: 0.16 / 33.53 ms 
testing                           [(4, 3, 6, 6)]   torch/tinygrad fp: 0.03 / 0.26 ms  bp: 0.39 / 1.26 ms 
testing                           [(1, 3, 6, 6)]   torch/tinygrad fp: 0.02 / 0.38 ms  bp: 0.26 / 1.19 ms 
testing                              [(2, 3, 1)]   torch/tinygrad fp: 0.02 / 0.41 ms  bp: 0.13 / 0.78 ms 
testing                                     [()]   torch/tinygrad fp: 0.02 / 0.01 ms  bp: 0.13 / 0.35 ms 
testing                                     [()]   torch/tinygrad fp: 0.01 / 0.01 ms  bp: 0.12 / 0.34 ms 
testing                                     [()]   torch/tinygrad fp: 0.01 / 0.02 ms  bp: 0.12 / 0.34 ms 
testing                                     [()]   torch/tinygrad exception: Dimension out of range (expected to be in range of [-1, 0], but got 10) / dim=10 out of range [-1, 0]ok
test_stack (__main__.TestOps) ... ok
test_stack_slice (__main__.TestOps) ... ok
test_std (__main__.TestOps) ... ok
test_std_axis (__main__.TestOps) ... ok
test_std_keepdim (__main__.TestOps) ... ok
test_std_zero_axis (__main__.TestOps) ... /home/jebba/devel/tinygrad/tinygrad/test/test_ops.py:737: UserWarning: std(): degrees of freedom is <= 0. Correction should be strictly less than the reduction factor (input numel divided by output numel). (Triggered internally at ../aten/src/ATen/native/ReduceOps.cpp:1776.)
  helper_test_op([(1,0,3,0,5)], lambda x: x.std(axis=(1,3)))
/home/jebba/devel/tinygrad/tinygrad/test/test_ops.py:738: UserWarning: std(): degrees of freedom is <= 0. Correction should be strictly less than the reduction factor (input numel divided by output numel). (Triggered internally at ../aten/src/ATen/native/ReduceOps.cpp:1776.)
  helper_test_op([(1,0,3,0,5)], lambda x: x.std(axis=(1,3), correction=0))
/home/jebba/devel/tinygrad/tinygrad/test/test_ops.py:739: UserWarning: std(): degrees of freedom is <= 0. Correction should be strictly less than the reduction factor (input numel divided by output numel). (Triggered internally at ../aten/src/ATen/native/ReduceOps.cpp:1776.)
  helper_test_op([(1,0,3,0,5)], lambda x: x.std(axis=(1,3), correction=5))
ok
test_strided_conv1d_simple (__main__.TestOps) ... ok
test_strided_conv2d (__main__.TestOps) ... ok
test_strided_conv2d_simple (__main__.TestOps) ... ok
test_strided_conv_transpose2d (__main__.TestOps) ... ok
test_sub (__main__.TestOps) ... ok
test_sum (__main__.TestOps) ... ok
test_sum_cat_collapse (__main__.TestOps) ... ok
test_sum_collapse (__main__.TestOps) ... ok
test_sum_collapse_neg (__main__.TestOps) ... ok
test_sum_fake (__main__.TestOps) ... ok
test_sum_full (__main__.TestOps) ... ok
test_sum_pad_collapse (__main__.TestOps) ... ok
test_sum_relu (__main__.TestOps) ... ok
test_sum_simple (__main__.TestOps) ... ok
test_sum_with_zeros_shape (__main__.TestOps) ... ok
test_tan (__main__.TestOps) ... ok
test_tanh (__main__.TestOps) ... ok
test_tiny_add (__main__.TestOps) ... ok
test_topo_sort (__main__.TestOps) ... ok
test_transpose (__main__.TestOps) ... ok
test_tril (__main__.TestOps) ... ok
test_triu (__main__.TestOps) ... 
testing                                     [()]   torch/tinygrad exception: Dimension out of range (expected to be in range of [-1, 0], but got 1) / dim=1 out of range [-1, 0]
testing                                     [()]   torch/tinygrad exception: Dimension out of range (expected to be in range of [-1, 0], but got -2) / dim=-2 out of range [-1, 0]
testing  [(45, 65, 3), (45, 65, 3), (45, 65, 3)]   torch/tinygrad fp: 0.14 / 36.45 ms  bp: 0.57 / 71.16 ms 
testing  [(45, 65, 3), (45, 65, 3), (45, 65, 3)]   torch/tinygrad fp: 0.14 / 40.95 ms  bp: 0.58 / 35.23 ms 
testing  [(45, 65, 3), (45, 65, 3), (45, 65, 3)]   torch/tinygrad fp: 0.05 / 43.31 ms  bp: 0.58 / 36.28 ms 
testing  [(45, 65, 3), (45, 65, 3), (45, 65, 3)]   torch/tinygrad fp: 0.09 / 43.29 ms  bp: 0.61 / 1.59 ms 
testing                                      [4]   torch/tinygrad fp: 0.08 / 33.87 ms  bp: 0.37 / 33.00 ms 
testing                                      [5]   torch/tinygrad fp: 0.07 / 36.43 ms  bp: 0.48 / 34.73 ms 
testing                                 [(4, 4)]   torch/tinygrad fp: 0.07 / 36.37 ms  bp: 0.35 / 35.27 ms 
testing                           [(15, 25, 35)]   torch/tinygrad fp: 0.14 / 85.43 ms  bp: 0.37 / 108.65 ms 
testing                           [(15, 25, 35)]   torch/tinygrad fp: 0.10 / 45.41 ms  bp: 0.52 / 32.96 ms 
testing                           [(15, 25, 35)]   torch/tinygrad fp: 0.14 / 43.99 ms  bp: 0.54 / 32.74 ms 
testing                           [(15, 25, 35)]   torch/tinygrad fp: 0.25 / 84.39 ms  bp: 0.64 / 146.46 ms 
testing                           [(15, 25, 35)]   torch/tinygrad fp: 0.18 / 91.72 ms  bp: 0.40 / 151.29 ms 
testing                           [(15, 25, 35)]   torch/tinygrad fp: 0.20 / 96.37 ms  bp: 0.38 / 122.56 ms 
testing                           [(15, 25, 35)]   torch/tinygrad fp: 0.25 / 43.63 ms  bp: 0.54 / 35.12 ms 
testing                           [(15, 25, 35)]   torch/tinygrad fp: 0.18 / 44.77 ms  bp: 0.54 / 35.72 ms 
testing                           [(15, 25, 35)]   torch/tinygrad fp: 0.14 / 45.48 ms  bp: 0.38 / 33.76 ms 
testing                           [(15, 25, 35)]   torch/tinygrad fp: 0.10 / 0.88 ms  bp: 0.28 / 30.59 ms 
testing                           [(15, 25, 35)]   torch/tinygrad fp: 0.24 / 1.29 ms  bp: 0.61 / 37.75 ms 
testing                        [(1, 0, 3, 0, 5)]   torch/tinygrad fp: 0.15 / 35.19 ms  bp: 0.53 / 1.18 ms 
testing                        [(1, 0, 3, 0, 5)]   torch/tinygrad fp: 0.12 / 0.87 ms  bp: 0.34 / 1.04 ms 
testing                        [(1, 0, 3, 0, 5)]   torch/tinygrad fp: 0.08 / 0.83 ms  bp: 0.37 / 1.18 ms 
testing                   [(2, 1, 5), (1, 1, 3)]   torch/tinygrad fp: 1.53 / 39.05 ms  bp: 6.15 / 148.02 ms 
testing           [(4, 3, 11, 28), (4, 3, 3, 3)]   torch/tinygrad fp: 7.18 / 329.65 ms  bp: 2.06 / 378.92 ms 
testing           [(4, 3, 11, 28), (4, 3, 3, 3)]   torch/tinygrad fp: 7.46 / 78.65 ms  bp: 2.17 / 360.57 ms 
testing             [(2, 1, 5, 1), (1, 1, 3, 1)]   torch/tinygrad fp: 1.59 / 42.13 ms  bp: 7.48 / 185.11 ms 
testing             [(2, 4, 4, 5), (4, 4, 3, 3)]   torch/tinygrad fp: 1.57 / 117.11 ms  bp: 7.11 / 148.49 ms 
testing             [(2, 4, 4, 5), (4, 4, 3, 3)]   torch/tinygrad fp: 1.24 / 83.35 ms  bp: 8.29 / 347.02 ms 
testing             [(2, 4, 4, 5), (4, 4, 3, 3)]   torch/tinygrad fp: 1.69 / 154.44 ms  bp: 5.52 / 291.23 ms 
testing                     [(45, 65), (45, 65)]   torch/tinygrad fp: 0.03 / 38.79 ms  bp: 0.44 / 1.54 ms 
testing                     [(45, 65), (45, 65)]   torch/tinygrad fp: 0.03 / 0.87 ms  bp: 0.15 / 0.69 ms 
testing                                 [(), ()]   torch/tinygrad fp: 0.01 / 30.96 ms  bp: 0.31 / 36.25 ms 
testing                                [(45, 3)]   torch/tinygrad fp: 0.05 / 41.76 ms  bp: 0.31 / 0.49 ms 
testing                           [(3, 4, 5, 6)]   torch/tinygrad fp: 0.05 / 40.19 ms  bp: 0.44 / 1.29 ms 
testing                           [(3, 4, 5, 6)]   torch/tinygrad fp: 0.06 / 41.38 ms  bp: 0.45 / 35.80 ms 
testing                           [(3, 4, 5, 6)]   torch/tinygrad fp: 0.05 / 42.90 ms  bp: 0.44 / 35.91 ms 
testing                           [(3, 4, 5, 6)]   torch/tinygrad fp: 0.05 / 46.07 ms  bp: 0.44 / 33.85 ms 
testing                           [(3, 4, 5, 6)]   torch/tinygrad fp: 0.05 / 34.51 ms  bp: 0.46 / 1.28 ms 
testing                                     [()]   torch/tinygrad fp: 0.04 / 0.07 ms  bp: 0.23 / 0.57 ms 
testing                                       []   torch/tinygrad fp: 0.64 / 45.47 ms  bp: nan / nan ms 
testing                                       []   torch/tinygrad fp: 0.54 / 36.11 ms  bp: nan / nan ms 
testing                                       []   torch/tinygrad fp: 0.08 / 31.31 ms  bp: nan / nan ms 
testing                               [(256, 1)]   torch/tinygrad fp: 0.04 / 0.32 ms  bp: 0.25 / 69.35 ms 
testing                                  [16384]   torch/tinygrad fp: 0.04 / 45.59 ms  bp: 0.42 / 0.82 ms 
testing                                       []   torch/tinygrad fp: 0.77 / 42.79 ms  bp: nan / nan ms 
testing                              [(3, 4, 5)]   torch/tinygrad fp: 0.06 / 40.20 ms  bp: 0.45 / 37.75 ms 
testing                                     None   torch/tinygrad fp: 0.06 / 33.89 ms  bp: 0.31 / 0.72 ms 
testing                                 [(4, 0)]   torch/tinygrad fp: 0.04 / 0.12 ms  bp: 0.24 / 0.41 ms 
testing                                 [(4, 0)]   torch/tinygrad fp: 0.02 / 0.07 ms  bp: 0.43 / 0.78 ms 
testing                                 [(4, 0)]   torch/tinygrad fp: 0.03 / 0.12 ms  bp: 0.27 / 0.42 ms 
testing                               [(45, 65)]   torch/tinygrad fp: 0.78 / 105.30 ms  bp: 0.49 / 134.78 ms 
testing                                     [()]   torch/tinygrad fp: 0.04 / 48.96 ms  bp: 0.31 / 51.03 ms 
testing                               [(45, 65)]   torch/tinygrad fp: 1.24 / 43.09 ms  bp: 0.46 / 42.62 ms 
testing                               [(45, 65)]   torch/tinygrad fp: 0.64 / 0.90 ms  bp: 0.38 / 1.80 ms 
testing                               [(45, 65)]   torch/tinygrad fp: 0.05 / 1.40 ms  bp: 0.15 / 1.08 ms 
testing                                   [3, 3]   torch/tinygrad fp: 0.01 / 31.36 ms  bp: nan / nan ms 
testing                               [(45, 65)]   torch/tinygrad fp: 0.06 / 34.24 ms  bp: 0.33 / 37.47 ms 
testing                                     [()]   torch/tinygrad fp: 0.04 / 28.99 ms  bp: 0.32 / 35.06 ms 
testing                                 [(3, 3)]   torch/tinygrad fp: 0.04 / 0.44 ms  bp: 0.44 / 38.20 ms 
testing                              [(3, 3, 3)]   torch/tinygrad fp: 0.05 / 0.44 ms  bp: 0.39 / 34.64 ms 
testing                              [(3, 3, 3)]   torch/tinygrad fp: 0.03 / 0.27 ms  bp: 0.44 / 39.61 ms 
testing                           [(1, 2, 3, 4)]   torch/tinygrad fp: 0.03 / 0.27 ms  bp: 0.44 / 38.33 ms 
testing                           [(3, 4, 5, 6)]   torch/tinygrad fp: 0.03 / 0.30 ms  bp: 0.45 / 39.80 ms 
testing                                     [()]   torch/tinygrad fp: 0.03 / 0.05 ms  bp: 0.24 / 0.41 ms 
testing                                 [(3, 3)]   torch/tinygrad fp: 0.52 / 77.03 ms  bp: 0.75 / 34.64 ms 
testing                                 [(3, 3)]   torch/tinygrad fp: 0.12 / 36.35 ms  bp: 0.45 / 1.09 ms 
testing                                 [(3, 3)]   torch/tinygrad fp: 0.04 / 3.22 ms  bp: 0.28 / 1.45 ms 
testing                              [(5, 3, 3)]   torch/tinygrad fp: 0.05 / 69.07 ms  bp: 0.42 / 34.97 ms 
testing                              [(5, 0, 3)]   torch/tinygrad fp: 0.02 / 0.29 ms  bp: 0.25 / 0.38 ms 
testing                              [(5, 3, 3)]   torch/tinygrad fp: 0.12 / 2.03 ms  bp: 0.17 / 0.76 ms 
testing                                 [(3, 3)]   torch/tinygrad fp: 0.05 / 35.36 ms  bp: 0.43 / 35.92 ms 
testing                                 [(3, 3)]   torch/tinygrad fp: 0.13 / 2.75 ms  bp: 0.41 / 1.68 ms 
testing                                 [(3, 3)]   torch/tinygrad fp: 0.04 / 33.96 ms  bp: 0.42 / 0.98 ms ok
test_trunc (__main__.TestOps) ... ok
test_unflatten (__main__.TestOps) ... ok
test_unsqueeze (__main__.TestOps) ... ok
test_var (__main__.TestOps) ... ok
test_var_axis (__main__.TestOps) ... ok
test_var_keepdim (__main__.TestOps) ... ok
test_var_zero_axis (__main__.TestOps) ... /home/jebba/devel/tinygrad/tinygrad/test/test_ops.py:718: UserWarning: var(): degrees of freedom is <= 0. Correction should be strictly less than the reduction factor (input numel divided by output numel). (Triggered internally at ../aten/src/ATen/native/ReduceOps.cpp:1776.)
  helper_test_op([(1,0,3,0,5)], lambda x: x.var(axis=(1,3)))
/home/jebba/devel/tinygrad/tinygrad/test/test_ops.py:719: UserWarning: var(): degrees of freedom is <= 0. Correction should be strictly less than the reduction factor (input numel divided by output numel). (Triggered internally at ../aten/src/ATen/native/ReduceOps.cpp:1776.)
  helper_test_op([(1,0,3,0,5)], lambda x: x.var(axis=(1,3), correction=0))
/home/jebba/devel/tinygrad/tinygrad/test/test_ops.py:720: UserWarning: var(): degrees of freedom is <= 0. Correction should be strictly less than the reduction factor (input numel divided by output numel). (Triggered internally at ../aten/src/ATen/native/ReduceOps.cpp:1776.)
  helper_test_op([(1,0,3,0,5)], lambda x: x.var(axis=(1,3), correction=5))
ok
test_where (__main__.TestOps) ... ok
test_where_permute (__main__.TestOps) ... ok
test_xor (__main__.TestOps) ... ok
test_zeros (__main__.TestOps) ... ok
test_zeros_like (__main__.TestOps) ... ok

----------------------------------------------------------------------
Ran 245 tests in 117.045s

OK (skipped=4)

testing                              [(5, 3, 3)]   torch/tinygrad fp: 0.03 / 36.30 ms  bp: 0.42 / 39.01 ms 
testing                              [(5, 0, 3)]   torch/tinygrad fp: 0.02 / 0.25 ms  bp: 0.25 / 0.38 ms 
testing                              [(5, 3, 3)]   torch/tinygrad fp: 0.12 / 2.15 ms  bp: 0.18 / 0.81 ms 
testing                               [(45, 35)]   torch/tinygrad fp: 0.29 / 38.56 ms  bp: nan / nan ms 
testing                                     None   torch/tinygrad fp: 0.03 / 32.54 ms  bp: nan / nan ms 
testing                           [(4, 3, 6, 6)]   torch/tinygrad fp: 0.08 / 0.47 ms  bp: 0.37 / 39.23 ms 
testing                           [(4, 3, 6, 6)]   torch/tinygrad fp: 0.05 / 0.48 ms  bp: 0.37 / 39.22 ms 
testing                           [(4, 3, 6, 6)]   torch/tinygrad fp: 0.05 / 0.48 ms  bp: 0.38 / 35.46 ms 
testing                           [(4, 3, 6, 6)]   torch/tinygrad fp: 0.03 / 0.29 ms  bp: 0.26 / 38.56 ms 
testing                           [(4, 3, 6, 6)]   torch/tinygrad fp: 0.03 / 0.48 ms  bp: 0.37 / 39.66 ms 
testing                           [(4, 3, 6, 6)]   torch/tinygrad fp: 0.03 / 0.43 ms  bp: 0.37 / 1.20 ms 
testing                           [(4, 3, 6, 6)]   torch/tinygrad fp: 0.01 / 0.29 ms  bp: 0.14 / 34.60 ms 
testing                                     [()]   torch/tinygrad fp: 0.03 / 0.04 ms  bp: 0.25 / 0.48 ms 
testing                           [(15, 25, 35)]   torch/tinygrad fp: 0.23 / 39.10 ms  bp: 0.46 / 34.52 ms 
testing                           [(15, 25, 35)]   torch/tinygrad fp: 0.10 / 43.80 ms  bp: 0.50 / 33.42 ms 
testing                           [(15, 25, 35)]   torch/tinygrad fp: 0.10 / 44.02 ms  bp: 0.46 / 33.38 ms 
testing                           [(15, 25, 35)]   torch/tinygrad fp: 0.25 / 38.82 ms  bp: 0.49 / 36.97 ms 
testing                           [(15, 25, 35)]   torch/tinygrad fp: 0.30 / 45.83 ms  bp: 0.60 / 36.66 ms 
testing                           [(15, 25, 35)]   torch/tinygrad fp: 0.13 / 39.34 ms  bp: 0.49 / 38.40 ms 
testing                           [(15, 25, 35)]   torch/tinygrad fp: 0.45 / 43.32 ms  bp: 0.49 / 36.70 ms 
testing                           [(15, 25, 35)]   torch/tinygrad fp: 0.18 / 45.29 ms  bp: 0.36 / 33.52 ms 
testing                           [(15, 25, 35)]   torch/tinygrad fp: 0.13 / 39.27 ms  bp: 0.49 / 38.35 ms 
testing                           [(15, 25, 35)]   torch/tinygrad fp: 0.15 / 1.54 ms  bp: 0.38 / 31.55 ms 
testing                           [(15, 25, 35)]   torch/tinygrad fp: 0.42 / 1.46 ms  bp: 0.43 / 35.39 ms 
testing                        [(1, 0, 3, 0, 5)]   torch/tinygrad fp: 0.15 / 0.95 ms  bp: 0.44 / 0.97 ms 
testing                        [(1, 0, 3, 0, 5)]   torch/tinygrad fp: 0.08 / 0.77 ms  bp: 0.16 / 0.50 ms 
testing                        [(1, 0, 3, 0, 5)]   torch/tinygrad fp: 0.04 / 0.43 ms  bp: 0.16 / 0.59 ms 
testing                                 [(100,)]   torch/tinygrad fp: 0.07 / 32.81 ms  bp: nan / nan ms 
testing                       [(8,), (1,), (1,)]   torch/tinygrad fp: 0.05 / 34.45 ms  bp: nan / nan ms 
testing                 [(10, 10), (10,), (10,)]   torch/tinygrad fp: 0.08 / 36.43 ms  bp: nan / nan ms 
testing                 [(100,), (100,), (100,)]   torch/tinygrad fp: 0.05 / 37.69 ms  bp: nan / nan ms 
testing           [(10, 10), (10, 10), (10, 10)]   torch/tinygrad fp: 0.08 / 35.34 ms  bp: nan / nan ms 
testing                                 [(5, 5)]   torch/tinygrad fp: 0.11 / 35.94 ms  bp: nan / nan ms 
testing                                       []   torch/tinygrad fp: 0.07 / 32.89 ms  bp: nan / nan ms 
testing                                       []   torch/tinygrad fp: 0.30 / 35.58 ms  bp: nan / nan ms 
testing                                       []   torch/tinygrad fp: 0.09 / 36.47 ms  bp: nan / nan ms 
testing                                       []   torch/tinygrad fp: 0.04 / 0.16 ms  bp: nan / nan ms 
testing                                       []   torch/tinygrad fp: 0.02 / 0.12 ms  bp: nan / nan ms 
testing                                       []   torch/tinygrad fp: 0.01 / 0.06 ms  bp: nan / nan ms 
testing                                       []   torch/tinygrad fp: 0.02 / 0.11 ms  bp: nan / nan ms 

test_optim.py

...........................
----------------------------------------------------------------------
Ran 27 tests in 3.959s

OK

test_randomness.py

..............
----------------------------------------------------------------------
Ran 14 tests in 6.518s

OK

test_sample.py

.
----------------------------------------------------------------------
Ran 1 test in 0.438s

OK
[8540 3050 5494 8699 5446 2895 9748 2567 7531 3761 7038 9328 7449 6356
 6707 2289]

test_schedule.py

test_basic_binop_fusion (__main__.TestSchedule) ... ok
test_basic_binop_fusion_deep (__main__.TestSchedule) ... ok
test_binop_early_reshape_reduce_fusion (__main__.TestSchedule) ... ok
test_binop_elu_fusion (__main__.TestSchedule) ... ok
test_binop_permute_fusion (__main__.TestSchedule) ... ok
test_binop_reshape_fusion (__main__.TestSchedule) ... ok
test_binop_reshape_reduce_fusion (__main__.TestSchedule) ... ok
test_cache_binaryop (__main__.TestSchedule) ... ok
test_cache_binaryop_reshaped (__main__.TestSchedule) ... skipped 'failing in old lazy'
test_cache_binaryop_transpose (__main__.TestSchedule) ... skipped 'failing in new lazy'
test_cache_two_reduceops (__main__.TestSchedule) ... ok
test_children_dont_push (__main__.TestSchedule) ... skipped 'not real world'
test_constants_are_embedded (__main__.TestSchedule) ... ok
test_contiguous_add (__main__.TestSchedule) ... ok
test_contiguous_while_contiguous (__main__.TestSchedule) ... ok
test_contiguous_while_not_contiguous (__main__.TestSchedule) ... ok
test_diamond_folded (__main__.TestSchedule) ... ok
test_dont_fuse_binops_with_children (__main__.TestSchedule) ... skipped 'failing in new lazy'
test_double_from (__main__.TestSchedule) ... ok
test_double_sum_ref (__main__.TestSchedule) ... ok
test_example_matmul (__main__.TestSchedule) ... ok
test_expand_nofuse (__main__.TestSchedule) ... ok
test_fancy_reshape_fusion (__main__.TestSchedule) ... skipped 'failing in old lazy'
test_fold_batchnorm (__main__.TestSchedule) ... ok
test_fold_conv_elu (__main__.TestSchedule) ... ok
test_fold_conv_relu (__main__.TestSchedule) ... ok
test_fold_double_unary (__main__.TestSchedule) ... ok
test_image_conv_fusion (__main__.TestSchedule) ... skipped 'failing in old lazy'
test_image_conv_fusion_minimal (__main__.TestSchedule) ... ok
test_image_conv_fusion_more_minimal (__main__.TestSchedule) ... ok
test_mulacc_fusion (__main__.TestSchedule) ... ok
test_mulacc_relu_fusion (__main__.TestSchedule) ... ok
test_multi_permute_should_collapse (__main__.TestSchedule) ... ok
test_multistage_reduce (__main__.TestSchedule) ... ok
test_multistage_reduce_fork (__main__.TestSchedule) ... ok
test_no_binop_rerun (__main__.TestSchedule) ... ok
test_permute_breaks_fusion (__main__.TestSchedule) ... ok
test_pow_const_tensor_simplified (__main__.TestSchedule) ... ok
test_pow_const_tensor_to_zero (__main__.TestSchedule) ... ok
test_push_permute_through_reshape (__main__.TestSchedule) ... ok
test_push_permute_through_reshape_alt (__main__.TestSchedule) ... ok
test_reduce_permute_binop_fusion (__main__.TestSchedule) ... skipped 'not pushing permutes through reduces'
test_reduce_permute_nofuse (__main__.TestSchedule) ... ok
test_reduce_reshape_binop_fusion (__main__.TestSchedule) ... ok
test_reduce_shrink (__main__.TestSchedule) ... ok
test_resnet_block (__main__.TestSchedule) ... ok
test_shrink_fuse (__main__.TestSchedule) ... ok
test_some_permute_fusion (__main__.TestSchedule) ... ok
test_two_elus_sum (__main__.TestSchedule) ... ok
test_two_sum (__main__.TestSchedule) ... ok
test_zero_size (__main__.TestSchedule) ... ok

----------------------------------------------------------------------
Ran 51 tests in 0.195s

OK (skipped=7)

test_search.py

.
----------------------------------------------------------------------
Ran 1 test in 0.418s

OK

test_specific_conv.py

......
----------------------------------------------------------------------
Ran 6 tests in 1.761s

OK

test_speed_v_torch.py

sssssssss......s......................
----------------------------------------------------------------------
Ran 38 tests in 20.124s

OK (skipped=10)

add                                1x    1    0.03 ms (    0.00 GFLOPS     0.00 GB/s) in torch,    0.44 ms (    0.00 GFLOPS     0.00 GB/s) in tinygrad,   16.60x slower       0.00 MOPS     0.00 MB

add                             1024x 1024    0.82 ms (    1.27 GFLOPS    15.29 GB/s) in torch,    0.46 ms (    2.28 GFLOPS    27.34 GB/s) in tinygrad,    0.56x faster       1.05 MOPS    12.58 MB

add                             4096x 4096   22.84 ms (    0.73 GFLOPS     8.82 GB/s) in torch,    1.23 ms (   13.66 GFLOPS   163.92 GB/s) in tinygrad,    0.05x faster      16.78 MOPS   201.33 MB

add_constant                    4096x 4096   20.11 ms (    0.83 GFLOPS     6.67 GB/s) in torch,    0.32 ms (   52.11 GFLOPS   416.87 GB/s) in tinygrad,    0.02x faster      16.78 MOPS   134.22 MB

add_sq                          4096x 4096   71.82 ms (    0.70 GFLOPS     2.80 GB/s) in torch,    0.47 ms (  106.81 GFLOPS   427.26 GB/s) in tinygrad,    0.01x faster      50.33 MOPS   201.33 MB

array_packing                   2048x 2048    2.73 ms (   18.41 GFLOPS    73.63 GB/s) in torch,    0.35 ms (  144.28 GFLOPS   577.10 GB/s) in tinygrad,    0.13x faster      50.33 MOPS   201.33 MB

cat_0                            256x  256    0.11 ms (    1.19 GFLOPS    11.87 GB/s) in torch,    0.44 ms (    0.30 GFLOPS     2.98 GB/s) in tinygrad,    3.98x slower       0.13 MOPS     1.31 MB

cat_1                            256x  256    0.11 ms (    1.22 GFLOPS     9.74 GB/s) in torch,    0.44 ms (    0.30 GFLOPS     2.38 GB/s) in tinygrad,    4.10x slower       0.13 MOPS     1.05 MB

conv bs: 32 chans:  4 ->  32 k:3              1.45 ms (   51.98 GFLOPS     3.30 GB/s) in torch,    0.43 ms (  175.40 GFLOPS    11.13 GB/s) in tinygrad,    0.30x faster      75.50 MOPS     4.79 MB

conv bs: 32 chans: 16 ->  32 k:3              4.01 ms (   75.36 GFLOPS     1.64 GB/s) in torch,    0.44 ms (  680.05 GFLOPS    14.82 GB/s) in tinygrad,    0.11x faster     301.99 MOPS     6.58 MB

conv bs: 32 chans: 64 ->  32 k:3             14.55 ms (   83.03 GFLOPS     0.94 GB/s) in torch,    0.51 ms ( 2382.76 GFLOPS    27.10 GB/s) in tinygrad,    0.03x faster    1207.96 MOPS    13.74 MB

double_permute (64, 64, 64, 64)              31.69 ms (   38.12 GFLOPS     0.43 GB/s) in torch,    0.63 ms ( 1912.57 GFLOPS    21.75 GB/s) in tinygrad,    0.02x faster    1207.96 MOPS    13.74 MB

exp                             2048x 2048    4.80 ms (    1.75 GFLOPS     6.98 GB/s) in torch,    0.45 ms (   18.73 GFLOPS    74.92 GB/s) in tinygrad,    0.09x faster       8.39 MOPS    33.55 MB

gemm                            1024x 1024   28.89 ms (   74.34 GFLOPS     0.44 GB/s) in torch,    0.75 ms ( 2880.83 GFLOPS    16.88 GB/s) in tinygrad,    0.03x faster    2147.48 MOPS    12.58 MB

gemm                             256x  256    0.56 ms (   60.24 GFLOPS     1.41 GB/s) in torch,    0.47 ms (   71.49 GFLOPS     1.68 GB/s) in tinygrad,    0.84x faster      33.55 MOPS     0.79 MB

gemm_unrolled                    512x  512    3.84 ms (   69.84 GFLOPS     0.82 GB/s) in torch,    0.51 ms (  526.59 GFLOPS     6.17 GB/s) in tinygrad,    0.13x faster     268.44 MOPS     3.15 MB

gemm_unrolled_permute_l          512x  512    3.91 ms (   68.64 GFLOPS     0.80 GB/s) in torch,    0.51 ms (  526.16 GFLOPS     6.17 GB/s) in tinygrad,    0.13x faster     268.44 MOPS     3.15 MB

gemm_unrolled_permute_lr         512x  512    3.88 ms (   69.16 GFLOPS     0.81 GB/s) in torch,    0.50 ms (  535.78 GFLOPS     6.28 GB/s) in tinygrad,    0.13x faster     268.44 MOPS     3.15 MB

gemm_unrolled_permute_r          512x  512    3.82 ms (   70.25 GFLOPS     0.82 GB/s) in torch,    0.51 ms (  524.03 GFLOPS     6.14 GB/s) in tinygrad,    0.13x faster     268.44 MOPS     3.15 MB

matvec_1024_1024                1024x 1024    0.35 ms (    5.91 GFLOPS    11.84 GB/s) in torch,    0.46 ms (    4.57 GFLOPS     9.15 GB/s) in tinygrad,    1.29x slower       2.10 MOPS     4.20 MB

matvec_1024_4096                1024x 4096    1.16 ms (    7.25 GFLOPS    14.52 GB/s) in torch,    0.47 ms (   17.99 GFLOPS    36.02 GB/s) in tinygrad,    0.40x faster       8.39 MOPS    16.80 MB

matvec_4096_1024                4096x 1024    1.39 ms (    6.04 GFLOPS    12.09 GB/s) in torch,    0.50 ms (   16.76 GFLOPS    33.56 GB/s) in tinygrad,    0.36x faster       8.39 MOPS    16.80 MB

matvec_4096_4096                4096x 4096    3.29 ms (   10.20 GFLOPS    20.41 GB/s) in torch,    1.19 ms (   28.28 GFLOPS    56.59 GB/s) in tinygrad,    0.36x faster      33.55 MOPS    67.14 MB

max                             4096x 4096    4.12 ms (    4.09 GFLOPS    16.41 GB/s) in torch,    0.55 ms (   30.47 GFLOPS   122.34 GB/s) in tinygrad,    0.13x faster      16.84 MOPS    67.63 MB

mul_sum                         4096x 4096   28.97 ms (    1.16 GFLOPS     4.65 GB/s) in torch,    0.68 ms (   49.27 GFLOPS   197.45 GB/s) in tinygrad,    0.02x faster      33.62 MOPS   134.74 MB

neg                             4096x 4096   19.84 ms (    0.85 GFLOPS     6.76 GB/s) in torch,    1.18 ms (   14.23 GFLOPS   113.81 GB/s) in tinygrad,    0.06x faster      16.78 MOPS   134.22 MB

conv bs:  1 chans: 12 ->  32 k:3              0.86 ms (   65.84 GFLOPS     1.70 GB/s) in torch,    0.44 ms (  127.29 GFLOPS     3.29 GB/s) in tinygrad,    0.52x faster      56.62 MOPS     1.46 MB

partial_sum                     4096x 4096    3.73 ms (    4.52 GFLOPS    18.15 GB/s) in torch,    0.34 ms (   49.88 GFLOPS   200.28 GB/s) in tinygrad,    0.09x faster      16.84 MOPS    67.63 MB

permute                         1024x 1024    1.31 ms (   12.83 GFLOPS    51.51 GB/s) in torch,    0.46 ms (   36.33 GFLOPS   145.89 GB/s) in tinygrad,    0.35x faster      16.84 MOPS    67.63 MB

permute                         4096x 4096   35.22 ms (    0.48 GFLOPS     1.92 GB/s) in torch,    0.95 ms (   17.70 GFLOPS    71.08 GB/s) in tinygrad,    0.03x faster      16.84 MOPS    67.63 MB

pow                             2048x 2048   25.25 ms (    8.97 GFLOPS     1.99 GB/s) in torch,    0.50 ms (  456.67 GFLOPS   101.48 GB/s) in tinygrad,    0.02x faster     226.49 MOPS    50.33 MB

relu                            4096x 4096   18.74 ms (    0.90 GFLOPS     7.16 GB/s) in torch,    1.60 ms (   10.45 GFLOPS    83.63 GB/s) in tinygrad,    0.09x faster      16.78 MOPS   134.22 MB

sub                             4096x 4096   21.62 ms (    0.78 GFLOPS     9.31 GB/s) in torch,    0.45 ms (   37.27 GFLOPS   447.20 GB/s) in tinygrad,    0.02x faster      16.78 MOPS   201.33 MB

sum                             2048x 2048    1.04 ms (    4.07 GFLOPS    16.32 GB/s) in torch,    0.45 ms (    9.26 GFLOPS    37.17 GB/s) in tinygrad,    0.44x faster       4.21 MOPS    16.91 MB

sum                             4096x 4096    3.54 ms (    4.76 GFLOPS    19.11 GB/s) in torch,    0.30 ms (   55.88 GFLOPS   224.40 GB/s) in tinygrad,    0.09x faster      16.84 MOPS    67.63 MB

test_symbolic_jit.py

Traceback (most recent call last):
  File "/home/jebba/devel/tinygrad/tinygrad/test/test_symbolic_jit.py", line 3, in <module>
    from test.helpers import assert_jit_cache_len
ModuleNotFoundError: No module named 'test.helpers'

test_symbolic_ops.py

.............ss
----------------------------------------------------------------------
Ran 15 tests in 4.071s

OK (skipped=2)

test_symbolic_shapetracker.py

......................
----------------------------------------------------------------------
Ran 22 tests in 0.163s

OK

test_tensor_data.py

.s...
----------------------------------------------------------------------
Ran 5 tests in 0.376s

OK (skipped=1)

test_tensor.py

.........................................
----------------------------------------------------------------------
Ran 41 tests in 3.246s

OK

test_to_numpy.py

.
----------------------------------------------------------------------
Ran 1 test in 0.426s

OK
<class 'numpy.ndarray'>

test_uops.py

Traceback (most recent call last):
  File "/home/jebba/devel/tinygrad/tinygrad/test/test_uops.py", line 10, in <module>
    from test.test_dtype import is_dtype_supported
ModuleNotFoundError: No module named 'test.test_dtype'

test_winograd.py

test_four_kernels (__main__.TestWinograd) ... ok
test_profile (__main__.TestWinograd) ... ok
test_speed (__main__.TestWinograd) ... ok

----------------------------------------------------------------------
Ran 3 tests in 1.399s

OK
n:     740  tm:  28.09ms  tot:  35.97ms lazy.py:156:_recursive_lazyop                      <- 100% lazy.py:189:<genexpr>
n:   21007  tm:   4.83ms  tot:   8.57ms ~:0:<built-in method builtins.hash>                <-  87% <string>:2:__hash__
n:    1117  tm:   2.88ms  tot:  27.89ms tensor.py:30:apply                                 <-  22% tensor.py:303:reshape
n:    1191  tm:   2.74ms  tot:   5.68ms lazy.py:28:__init__                                <- 100% lazy.py:18:create_lazybuffer
n:    1272  tm:   2.43ms  tot:  12.74ms lazy.py:18:create_lazybuffer                       <-  48% lazy.py:141:_view
n:     932  tm:   2.43ms  tot:   4.21ms lazy.py:211:_recurse_lb                            <- 100% lazy.py:211:_recurse_lb
n:      81  tm:   2.40ms  tot:  11.49ms tensor.py:349:__getitem__                          <- 100% tensor.py:666:<genexpr>
n:     367  tm:   2.25ms  tot:   7.36ms tensor.py:787:_broadcasted                         <-  55% tensor.py:814:add
n:    1103  tm:   1.92ms  tot:  35.92ms lazy.py:189:<genexpr>                              <- 100% lazy.py:156:_recursive_lazyop
n:     368  tm:   1.82ms  tot:   9.60ms lazy.py:105:e                                      <-  55% mlops.py:99:forward
n:    3210  tm:   1.54ms  tot:   3.46ms shapetracker.py:116:size                           <-  42% lazy.py:18:create_lazybuffer
n:     895  tm:   1.51ms  tot:   5.95ms tensor.py:307:expand                               <-  73% tensor.py:787:_broadcasted
n:     743  tm:   1.41ms  tot:   2.68ms ops.py:55:cached_compare                           <-  99% ops.py:59:<genexpr>
n:    8235  tm:   1.32ms  tot:   1.32ms lazy.py:52:base                                    <-  33% lazy.py:211:_recurse_lb
n:    1117  tm:   1.16ms  tot:   1.66ms tensor.py:21:__init__                              <- 100% tensor.py:30:apply
n:     747  tm:   1.06ms  tot:   8.92ms lazy.py:141:_view                                  <-  39% lazy.py:146:reshape
n:    2010  tm:   0.99ms  tot:   5.25ms ~:0:<built-in method builtins.all>                 <-  37% helpers.py:22:all_same
n:    1127  tm:   0.96ms  tot:   1.84ms shapetracker.py:171:simplify                       <-  71% shapetracker.py:98:__add__
n:    7654  tm:   0.96ms  tot:   0.96ms ~:0:<built-in method builtins.isinstance>          <-  46% enum.py:396:__contains__
n:    2404  tm:   0.86ms  tot:   0.86ms <string>:2:__init__                                <-  25% shapetracker.py:107:from_shape
n:    2494  tm:   0.83ms  tot:   2.88ms ~:0:<method 'get' of 'dict' objects>               <-  89% lazy.py:18:create_lazybuffer
n:    7097  tm:   0.81ms  tot:   0.81ms tensor.py:103:shape                                <-  28% tensor.py:787:_broadcasted
n:    2602  tm:   0.81ms  tot:   1.19ms tensor.py:806:<genexpr>                            <- 100% tensor.py:787:_broadcasted
n:     611  tm:   0.80ms  tot:   2.81ms functools.py:961:__get__                           <- 100% ops.py:65:__hash__
n:    1486  tm:   0.80ms  tot:   0.80ms <string>:2:__eq__                                  <-  50% tensor.py:948:cast
n:     895  tm:   0.78ms  tot:   0.78ms tensor.py:308:<listcomp>                           <- 100% tensor.py:307:expand
n:    2241  tm:   0.74ms  tot:   1.03ms <string>:2:__hash__                                <-  34% tensor.py:787:_broadcasted
n:    6712  tm:   0.64ms  tot:   0.64ms ~:0:<built-in method builtins.len>                 <-  22% tensor.py:787:_broadcasted
n:     254  tm:   0.62ms  tot:   6.35ms tensor.py:303:reshape                              <-  59% tensor.py:198:full
n:     156  tm:   0.59ms  tot:   2.90ms tensor.py:59:__init__                              <- 100% tensor.py:198:full
n:       1  tm:   0.57ms  tot:   8.07ms realize.py:42:run_schedule                         <- 100% tensor.py:115:realize
n:    1559  tm:   0.57ms  tot:   1.01ms enum.py:396:__contains__                           <-  37% lazy.py:211:_recurse_lb
n:    1391  tm:   0.54ms  tot:   0.54ms helpers.py:20:argfix                               <-  62% tensor.py:307:expand
n:    1190  tm:   0.53ms  tot:   1.98ms ~:0:<method 'pop' of 'dict' objects>               <- 100% lazy.py:46:__del__
n:    2206  tm:   0.53ms  tot:   0.92ms helpers.py:22:<genexpr>                            <- 100% ~:0:<built-in method builtins.all>
n:     164  tm:   0.49ms  tot:   4.13ms tensor.py:315:pad                                  <-  98% tensor.py:470:<listcomp>
n:       1  tm:   0.48ms  tot:  42.16ms lazy.py:245:create_schedule                        <- 100% lazy.py:79:schedule
n:    1913  tm:   0.48ms  tot:   0.67ms enum.py:783:__hash__                               <-  33% ~:0:<method 'get' of 'dict' objects>
n:     156  tm:   0.47ms  tot:  11.13ms tensor.py:198:full                                 <- 100% tensor.py:665:<listcomp>
n:    1190  tm:   0.46ms  tot:   2.44ms lazy.py:46:__del__                                 <-  64% realize.py:42:run_schedule
n:     247  tm:   0.41ms  tot:   0.80ms helpers.py:33:merge_dicts                          <-  98% shapetracker.py:131:unbind
n:     254  tm:   0.41ms  tot:   0.66ms shapetracker.py:184:reshape                        <- 100% lazy.py:146:reshape
n:     451  tm:   0.40ms  tot:   0.81ms tensor.py:809:_to_const_val                        <-  54% tensor.py:814:add
n:     381  tm:   0.40ms  tot:   2.17ms shapetracker.py:98:__add__                         <-  71% lazy.py:156:_recursive_lazyop
n:    1350  tm:   0.39ms  tot:   2.65ms ops.py:59:<genexpr>                                <- 100% ~:0:<built-in method builtins.all>
n:    2323  tm:   0.39ms  tot:   0.39ms ~:0:<built-in method builtins.max>                 <-  96% tensor.py:806:<genexpr>
n:      90  tm:   0.39ms  tot:   2.90ms tensor.py:312:shrink                               <-  93% tensor.py:349:__getitem__
n:     243  tm:   0.39ms  tot:   1.61ms shapetracker.py:131:unbind                         <-  99% lazy.py:156:_recursive_lazyop
n:     815  tm:   0.39ms  tot:  11.97ms ~:0:<built-in method _functools.reduce>            <-  87% helpers.py:13:prod
running conv:  23.36 ms
scheduling:   6.24 ms
linearize 1 with   90 ops:  22.67 ms
linearize 3 with  256 ops:  81.60 ms
linearize 4 with    5 ops:   1.53 ms
linearize 5 with  210 ops: 101.98 ms

test_zero_copy.py

test_zero_copy_from_default_to_cpu (__main__.TestZeroCopy) ... skipped "device isn't zero copy"

----------------------------------------------------------------------
Ran 1 test in 0.000s

OK (skipped=1)

external/external_benchmark_hip_compile.py

Traceback (most recent call last):
  File "/home/jebba/devel/tinygrad/tinygrad/test/external/external_benchmark_hip_compile.py", line 4, in <module>
    from tinygrad.runtime.ops_gpu import compile_cl, CLDevice
ImportError: cannot import name 'compile_cl' from 'tinygrad.runtime.ops_gpu' (/home/jebba/devel/tinygrad/tinygrad/tinygrad/runtime/ops_gpu.py)

external/external_benchmark_load_stable_diffusion.py

https://github.com/openai/CLIP/raw/main/clip/bpe_simple_vocab_16e6.txt.gz:   0%|          | 0.00/1.36M [00:00<?, ?B/s]
https://github.com/openai/CLIP/raw/main/clip/bpe_simple_vocab_16e6.txt.gz:  22%|██▏       | 295k/1.36M [00:00<00:00, 2.63MB/s]
https://github.com/openai/CLIP/raw/main/clip/bpe_simple_vocab_16e6.txt.gz:  48%|████▊     | 655k/1.36M [00:00<00:00, 3.15MB/s]
https://github.com/openai/CLIP/raw/main/clip/bpe_simple_vocab_16e6.txt.gz:  82%|████████▏ | 1.11M/1.36M [00:00<00:00, 3.68MB/s]
https://github.com/openai/CLIP/raw/main/clip/bpe_simple_vocab_16e6.txt.gz: 100%|██████████| 1.36M/1.36M [00:00<00:00, 3.39MB/s]

https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:   0%|          | 0.00/4.27G [00:00<?, ?B/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:   0%|          | 115k/4.27G [00:00<1:02:41, 1.13MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:   0%|          | 377k/4.27G [00:00<35:43, 1.99MB/s]  
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:   0%|          | 934k/4.27G [00:00<19:47, 3.59MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:   0%|          | 1.54M/4.27G [00:00<21:13, 3.35MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:   0%|          | 3.77M/4.27G [00:00<08:01, 8.86MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:   0%|          | 5.13M/4.27G [00:00<06:56, 10.2MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:   0%|          | 6.28M/4.27G [00:00<07:11, 9.86MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:   0%|          | 7.54M/4.27G [00:00<06:40, 10.6MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:   0%|          | 9.60M/4.27G [00:01<05:16, 13.5MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:   0%|          | 11.0M/4.27G [00:01<06:08, 11.6MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:   0%|          | 13.4M/4.27G [00:01<04:52, 14.6MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:   0%|          | 15.0M/4.27G [00:01<07:01, 10.1MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:   0%|          | 16.2M/4.27G [00:01<08:16, 8.55MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:   0%|          | 18.9M/4.27G [00:01<05:51, 12.1MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:   0%|          | 20.8M/4.27G [00:01<05:13, 13.6MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:   1%|          | 22.5M/4.27G [00:02<05:03, 14.0MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:   1%|          | 24.1M/4.27G [00:02<05:17, 13.3MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:   1%|          | 26.9M/4.27G [00:02<04:11, 16.8MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:   1%|          | 28.8M/4.27G [00:02<04:03, 17.4MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:   1%|          | 30.9M/4.27G [00:02<03:49, 18.5MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:   1%|          | 32.9M/4.27G [00:02<03:53, 18.2MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:   1%|          | 34.8M/4.27G [00:02<03:55, 18.0MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:   1%|          | 36.7M/4.27G [00:02<04:08, 17.0MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:   1%|          | 38.5M/4.27G [00:02<04:04, 17.3MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:   1%|          | 40.3M/4.27G [00:03<04:47, 14.7MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:   1%|          | 41.9M/4.27G [00:03<05:05, 13.8MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:   1%|          | 44.8M/4.27G [00:03<03:58, 17.7MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:   1%|          | 46.7M/4.27G [00:03<05:34, 12.6MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:   1%|          | 48.8M/4.27G [00:03<04:56, 14.2MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:   1%|          | 51.3M/4.27G [00:03<04:12, 16.7MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:   1%|▏         | 53.5M/4.27G [00:04<04:27, 15.8MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:   1%|▏         | 55.3M/4.27G [00:04<04:37, 15.2MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:   1%|▏         | 58.7M/4.27G [00:04<03:34, 19.6MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:   1%|▏         | 60.8M/4.27G [00:04<03:51, 18.2MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:   1%|▏         | 62.8M/4.27G [00:04<08:07, 8.61MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:   2%|▏         | 65.4M/4.27G [00:05<06:18, 11.1MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:   2%|▏         | 67.3M/4.27G [00:05<08:20, 8.39MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:   2%|▏         | 70.3M/4.27G [00:05<06:07, 11.4MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:   2%|▏         | 72.2M/4.27G [00:06<09:46, 7.15MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:   2%|▏         | 73.6M/4.27G [00:06<10:10, 6.87MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:   2%|▏         | 74.8M/4.27G [00:06<09:39, 7.23MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:   2%|▏         | 75.9M/4.27G [00:06<13:11, 5.29MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:   2%|▏         | 76.8M/4.27G [00:06<12:28, 5.59MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:   2%|▏         | 79.6M/4.27G [00:07<07:44, 9.02MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:   2%|▏         | 81.0M/4.27G [00:07<07:09, 9.75MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:   2%|▏         | 82.4M/4.27G [00:07<06:50, 10.2MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:   2%|▏         | 83.8M/4.27G [00:07<06:36, 10.6MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:   2%|▏         | 85.8M/4.27G [00:07<05:30, 12.6MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:   2%|▏         | 87.2M/4.27G [00:07<05:23, 12.9MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:   2%|▏         | 88.7M/4.27G [00:07<05:20, 13.0MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:   2%|▏         | 90.5M/4.27G [00:07<04:54, 14.2MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:   2%|▏         | 92.0M/4.27G [00:07<04:46, 14.5MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:   2%|▏         | 93.7M/4.27G [00:08<04:37, 15.0MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:   2%|▏         | 95.3M/4.27G [00:08<04:50, 14.3MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:   2%|▏         | 96.7M/4.27G [00:08<04:55, 14.1MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:   2%|▏         | 99.3M/4.27G [00:08<04:02, 17.2MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:   2%|▏         | 101M/4.27G [00:08<04:26, 15.6MB/s] 
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:   2%|▏         | 103M/4.27G [00:08<04:24, 15.8MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:   2%|▏         | 104M/4.27G [00:08<05:49, 11.9MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:   3%|▎         | 107M/4.27G [00:08<04:32, 15.3MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:   3%|▎         | 109M/4.27G [00:09<06:44, 10.3MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:   3%|▎         | 111M/4.27G [00:09<05:11, 13.3MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:   3%|▎         | 113M/4.27G [00:09<05:49, 11.9MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:   3%|▎         | 115M/4.27G [00:09<05:46, 12.0MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:   3%|▎         | 118M/4.27G [00:09<04:36, 15.0MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:   3%|▎         | 120M/4.27G [00:09<04:19, 16.0MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:   3%|▎         | 122M/4.27G [00:10<04:15, 16.2MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:   3%|▎         | 124M/4.27G [00:10<03:58, 17.4MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:   3%|▎         | 126M/4.27G [00:10<03:53, 17.8MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:   3%|▎         | 128M/4.27G [00:10<05:41, 12.1MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:   3%|▎         | 131M/4.27G [00:10<04:31, 15.2MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:   3%|▎         | 132M/4.27G [00:10<04:35, 15.0MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:   3%|▎         | 134M/4.27G [00:10<04:42, 14.6MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:   3%|▎         | 137M/4.27G [00:11<03:43, 18.5MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:   3%|▎         | 139M/4.27G [00:11<03:42, 18.5MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:   3%|▎         | 141M/4.27G [00:11<04:07, 16.6MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:   3%|▎         | 143M/4.27G [00:11<04:12, 16.3MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:   3%|▎         | 146M/4.27G [00:11<03:37, 18.9MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:   3%|▎         | 148M/4.27G [00:11<03:35, 19.1MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:   4%|▎         | 150M/4.27G [00:12<14:34, 4.71MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:   4%|▎         | 151M/4.27G [00:13<14:13, 4.82MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:   4%|▎         | 154M/4.27G [00:13<10:29, 6.54MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:   4%|▎         | 155M/4.27G [00:13<08:51, 7.73MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:   4%|▎         | 157M/4.27G [00:13<07:43, 8.86MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:   4%|▎         | 158M/4.27G [00:13<07:10, 9.53MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:   4%|▍         | 160M/4.27G [00:13<05:54, 11.6MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:   4%|▍         | 162M/4.27G [00:13<05:00, 13.7MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:   4%|▍         | 164M/4.27G [00:13<04:48, 14.2MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:   4%|▍         | 166M/4.27G [00:13<04:27, 15.3MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:   4%|▍         | 168M/4.27G [00:14<04:09, 16.4MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:   4%|▍         | 170M/4.27G [00:14<03:51, 17.7MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:   4%|▍         | 172M/4.27G [00:14<03:45, 18.1MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:   4%|▍         | 174M/4.27G [00:14<03:51, 17.7MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:   4%|▍         | 176M/4.27G [00:14<04:14, 16.1MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:   4%|▍         | 180M/4.27G [00:14<03:11, 21.3MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:   4%|▍         | 182M/4.27G [00:14<03:30, 19.4MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:   4%|▍         | 184M/4.27G [00:14<03:19, 20.4MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:   4%|▍         | 186M/4.27G [00:14<03:33, 19.1MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:   4%|▍         | 189M/4.27G [00:15<03:22, 20.1MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:   4%|▍         | 191M/4.27G [00:15<03:26, 19.7MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:   5%|▍         | 193M/4.27G [00:15<04:50, 14.0MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:   5%|▍         | 197M/4.27G [00:15<03:29, 19.4MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:   5%|▍         | 199M/4.27G [00:15<03:24, 19.9MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:   5%|▍         | 202M/4.27G [00:15<03:51, 17.6MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:   5%|▍         | 204M/4.27G [00:15<03:25, 19.8MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:   5%|▍         | 207M/4.27G [00:16<04:36, 14.7MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:   5%|▍         | 210M/4.27G [00:16<03:47, 17.8MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:   5%|▍         | 212M/4.27G [00:16<03:37, 18.6MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:   5%|▌         | 215M/4.27G [00:16<03:12, 21.0MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:   5%|▌         | 217M/4.27G [00:16<03:02, 22.2MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:   5%|▌         | 220M/4.27G [00:16<03:08, 21.5MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:   5%|▌         | 222M/4.27G [00:16<03:21, 20.1MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:   5%|▌         | 225M/4.27G [00:16<03:01, 22.3MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:   5%|▌         | 227M/4.27G [00:17<03:14, 20.8MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:   5%|▌         | 231M/4.27G [00:17<02:39, 25.3MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:   5%|▌         | 234M/4.27G [00:17<02:32, 26.4MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:   6%|▌         | 237M/4.27G [00:17<02:30, 26.7MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:   6%|▌         | 240M/4.27G [00:17<02:33, 26.2MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:   6%|▌         | 242M/4.27G [00:17<03:09, 21.3MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:   6%|▌         | 245M/4.27G [00:17<02:47, 23.9MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:   6%|▌         | 248M/4.27G [00:18<03:29, 19.2MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:   6%|▌         | 250M/4.27G [00:18<03:29, 19.1MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:   6%|▌         | 252M/4.27G [00:18<03:37, 18.5MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:   6%|▌         | 254M/4.27G [00:18<03:30, 19.0MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:   6%|▌         | 257M/4.27G [00:18<04:12, 15.9MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:   6%|▌         | 261M/4.27G [00:18<03:12, 20.8MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:   6%|▌         | 263M/4.27G [00:18<04:03, 16.4MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:   6%|▋         | 267M/4.27G [00:18<03:09, 21.1MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:   6%|▋         | 269M/4.27G [00:19<03:42, 18.0MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:   6%|▋         | 272M/4.27G [00:19<03:53, 17.1MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:   6%|▋         | 276M/4.27G [00:19<03:10, 20.9MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:   7%|▋         | 279M/4.27G [00:19<03:00, 22.0MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:   7%|▋         | 281M/4.27G [00:19<03:00, 22.1MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:   7%|▋         | 284M/4.27G [00:20<05:57, 11.1MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:   7%|▋         | 285M/4.27G [00:20<06:53, 9.62MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:   7%|▋         | 288M/4.27G [00:20<05:18, 12.5MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:   7%|▋         | 291M/4.27G [00:20<04:48, 13.8MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:   7%|▋         | 293M/4.27G [00:20<04:14, 15.6MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:   7%|▋         | 295M/4.27G [00:20<04:16, 15.5MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:   7%|▋         | 298M/4.27G [00:21<03:39, 18.1MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:   7%|▋         | 300M/4.27G [00:21<03:51, 17.1MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:   7%|▋         | 302M/4.27G [00:21<04:46, 13.8MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:   7%|▋         | 305M/4.27G [00:21<03:55, 16.8MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:   7%|▋         | 307M/4.27G [00:21<03:42, 17.8MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:   7%|▋         | 309M/4.27G [00:21<03:37, 18.2MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:   7%|▋         | 311M/4.27G [00:21<03:23, 19.5MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:   7%|▋         | 313M/4.27G [00:21<03:55, 16.8MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:   7%|▋         | 316M/4.27G [00:22<03:15, 20.2MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:   7%|▋         | 319M/4.27G [00:22<03:06, 21.2MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:   8%|▊         | 321M/4.27G [00:22<03:00, 21.9MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:   8%|▊         | 324M/4.27G [00:22<02:56, 22.3MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:   8%|▊         | 326M/4.27G [00:22<02:48, 23.4MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:   8%|▊         | 329M/4.27G [00:22<02:32, 25.9MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:   8%|▊         | 332M/4.27G [00:22<02:31, 25.9MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:   8%|▊         | 335M/4.27G [00:22<02:29, 26.4MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:   8%|▊         | 338M/4.27G [00:22<02:19, 28.2MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:   8%|▊         | 342M/4.27G [00:22<02:05, 31.3MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:   8%|▊         | 345M/4.27G [00:23<02:08, 30.5MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:   8%|▊         | 349M/4.27G [00:23<02:03, 31.8MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:   8%|▊         | 352M/4.27G [00:23<02:01, 32.3MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:   8%|▊         | 356M/4.27G [00:23<01:57, 33.2MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:   8%|▊         | 359M/4.27G [00:23<01:53, 34.4MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:   9%|▊         | 363M/4.27G [00:23<01:51, 34.9MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:   9%|▊         | 367M/4.27G [00:23<01:50, 35.2MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:   9%|▊         | 370M/4.27G [00:23<01:50, 35.2MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:   9%|▉         | 374M/4.27G [00:23<01:50, 35.1MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:   9%|▉         | 377M/4.27G [00:24<01:55, 33.8MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:   9%|▉         | 381M/4.27G [00:24<01:53, 34.1MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:   9%|▉         | 384M/4.27G [00:24<03:39, 17.7MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:   9%|▉         | 387M/4.27G [00:24<04:03, 15.9MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:   9%|▉         | 390M/4.27G [00:24<03:18, 19.5MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:   9%|▉         | 393M/4.27G [00:25<03:33, 18.1MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:   9%|▉         | 395M/4.27G [00:25<03:25, 18.8MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:   9%|▉         | 398M/4.27G [00:25<04:08, 15.5MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:   9%|▉         | 402M/4.27G [00:25<03:11, 20.2MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:   9%|▉         | 404M/4.27G [00:25<04:29, 14.3MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  10%|▉         | 407M/4.27G [00:25<03:58, 16.2MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  10%|▉         | 409M/4.27G [00:26<04:21, 14.8MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  10%|▉         | 411M/4.27G [00:26<03:49, 16.8MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  10%|▉         | 414M/4.27G [00:26<03:22, 19.0MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  10%|▉         | 417M/4.27G [00:26<02:55, 22.0MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  10%|▉         | 421M/4.27G [00:26<02:30, 25.6MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  10%|▉         | 424M/4.27G [00:26<02:25, 26.4MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  10%|█         | 427M/4.27G [00:26<02:38, 24.2MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  10%|█         | 429M/4.27G [00:26<02:37, 24.4MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  10%|█         | 432M/4.27G [00:26<03:05, 20.7MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  10%|█         | 434M/4.27G [00:27<04:53, 13.1MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  10%|█         | 437M/4.27G [00:27<04:09, 15.3MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  10%|█         | 439M/4.27G [00:27<06:08, 10.4MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  10%|█         | 442M/4.27G [00:27<04:38, 13.7MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  10%|█         | 445M/4.27G [00:28<03:50, 16.6MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  10%|█         | 448M/4.27G [00:28<03:18, 19.3MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  11%|█         | 451M/4.27G [00:28<02:56, 21.6MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  11%|█         | 453M/4.27G [00:28<03:02, 20.9MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  11%|█         | 456M/4.27G [00:28<02:58, 21.3MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  11%|█         | 458M/4.27G [00:28<02:54, 21.9MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  11%|█         | 462M/4.27G [00:28<02:32, 24.9MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  11%|█         | 464M/4.27G [00:28<02:34, 24.6MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  11%|█         | 467M/4.27G [00:29<03:25, 18.5MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  11%|█         | 469M/4.27G [00:29<03:15, 19.4MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  11%|█         | 471M/4.27G [00:29<03:59, 15.9MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  11%|█         | 473M/4.27G [00:29<03:55, 16.1MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  11%|█         | 475M/4.27G [00:29<06:03, 10.4MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  11%|█         | 478M/4.27G [00:29<04:44, 13.3MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  11%|█         | 479M/4.27G [00:29<04:31, 14.0MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  11%|█▏        | 481M/4.27G [00:30<05:07, 12.3MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  11%|█▏        | 484M/4.27G [00:30<03:52, 16.3MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  11%|█▏        | 486M/4.27G [00:30<04:00, 15.7MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  11%|█▏        | 488M/4.27G [00:30<06:07, 10.3MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  12%|█▏        | 491M/4.27G [00:30<04:40, 13.5MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  12%|█▏        | 493M/4.27G [00:31<04:33, 13.8MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  12%|█▏        | 495M/4.27G [00:31<04:55, 12.8MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  12%|█▏        | 496M/4.27G [00:31<05:03, 12.4MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  12%|█▏        | 498M/4.27G [00:31<04:41, 13.4MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  12%|█▏        | 500M/4.27G [00:31<03:59, 15.7MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  12%|█▏        | 502M/4.27G [00:31<04:48, 13.0MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  12%|█▏        | 504M/4.27G [00:31<04:19, 14.5MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  12%|█▏        | 506M/4.27G [00:31<04:26, 14.1MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  12%|█▏        | 510M/4.27G [00:32<03:11, 19.6MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  12%|█▏        | 512M/4.27G [00:32<03:07, 20.0MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  12%|█▏        | 514M/4.27G [00:32<03:27, 18.0MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  12%|█▏        | 516M/4.27G [00:32<05:24, 11.6MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  12%|█▏        | 519M/4.27G [00:32<04:16, 14.6MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  12%|█▏        | 521M/4.27G [00:32<04:12, 14.8MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  12%|█▏        | 523M/4.27G [00:33<04:09, 15.0MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  12%|█▏        | 524M/4.27G [00:33<04:14, 14.7MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  12%|█▏        | 526M/4.27G [00:33<06:20, 9.83MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  12%|█▏        | 529M/4.27G [00:33<04:51, 12.8MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  12%|█▏        | 530M/4.27G [00:33<06:09, 10.1MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  13%|█▎        | 533M/4.27G [00:33<04:32, 13.7MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  13%|█▎        | 535M/4.27G [00:34<05:12, 12.0MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  13%|█▎        | 538M/4.27G [00:34<04:01, 15.4MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  13%|█▎        | 540M/4.27G [00:34<03:47, 16.4MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  13%|█▎        | 542M/4.27G [00:34<03:52, 16.0MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  13%|█▎        | 544M/4.27G [00:34<03:53, 15.9MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  13%|█▎        | 547M/4.27G [00:34<03:27, 17.9MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  13%|█▎        | 549M/4.27G [00:34<03:36, 17.2MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  13%|█▎        | 551M/4.27G [00:34<03:10, 19.4MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  13%|█▎        | 553M/4.27G [00:35<03:10, 19.5MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  13%|█▎        | 556M/4.27G [00:35<03:05, 20.0MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  13%|█▎        | 558M/4.27G [00:35<03:08, 19.7MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  13%|█▎        | 560M/4.27G [00:35<04:27, 13.8MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  13%|█▎        | 563M/4.27G [00:35<03:32, 17.4MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  13%|█▎        | 567M/4.27G [00:35<02:53, 21.4MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  13%|█▎        | 569M/4.27G [00:35<02:57, 20.8MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  13%|█▎        | 572M/4.27G [00:35<02:41, 22.9MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  13%|█▎        | 575M/4.27G [00:36<02:35, 23.7MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  14%|█▎        | 578M/4.27G [00:36<02:28, 24.9MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  14%|█▎        | 580M/4.27G [00:36<02:27, 25.0MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  14%|█▎        | 583M/4.27G [00:36<05:04, 12.1MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  14%|█▎        | 585M/4.27G [00:36<04:20, 14.1MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  14%|█▍        | 589M/4.27G [00:36<03:33, 17.2MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  14%|█▍        | 592M/4.27G [00:37<03:01, 20.3MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  14%|█▍        | 595M/4.27G [00:37<02:36, 23.5MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  14%|█▍        | 598M/4.27G [00:37<02:55, 20.9MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  14%|█▍        | 601M/4.27G [00:37<02:43, 22.5MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  14%|█▍        | 603M/4.27G [00:37<03:31, 17.3MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  14%|█▍        | 606M/4.27G [00:37<03:07, 19.6MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  14%|█▍        | 609M/4.27G [00:37<02:53, 21.1MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  14%|█▍        | 612M/4.27G [00:37<02:32, 24.0MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  14%|█▍        | 615M/4.27G [00:38<02:27, 24.8MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  14%|█▍        | 618M/4.27G [00:38<02:25, 25.1MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  15%|█▍        | 621M/4.27G [00:38<02:17, 26.5MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  15%|█▍        | 623M/4.27G [00:38<03:01, 20.1MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  15%|█▍        | 627M/4.27G [00:38<02:40, 22.7MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  15%|█▍        | 629M/4.27G [00:38<02:38, 22.9MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  15%|█▍        | 632M/4.27G [00:38<02:27, 24.6MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  15%|█▍        | 635M/4.27G [00:38<02:18, 26.3MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  15%|█▍        | 638M/4.27G [00:39<02:22, 25.4MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  15%|█▌        | 641M/4.27G [00:39<03:20, 18.1MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  15%|█▌        | 643M/4.27G [00:39<03:00, 20.1MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  15%|█▌        | 646M/4.27G [00:39<06:01, 10.0MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  15%|█▌        | 649M/4.27G [00:40<04:46, 12.6MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  15%|█▌        | 652M/4.27G [00:40<03:55, 15.3MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  15%|█▌        | 655M/4.27G [00:40<03:33, 16.9MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  15%|█▌        | 657M/4.27G [00:40<03:18, 18.2MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  15%|█▌        | 660M/4.27G [00:40<02:59, 20.1MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  16%|█▌        | 662M/4.27G [00:40<04:54, 12.2MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  16%|█▌        | 665M/4.27G [00:41<04:00, 15.0MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  16%|█▌        | 667M/4.27G [00:41<04:56, 12.1MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  16%|█▌        | 671M/4.27G [00:41<03:38, 16.4MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  16%|█▌        | 674M/4.27G [00:41<03:19, 18.0MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  16%|█▌        | 676M/4.27G [00:41<03:00, 19.8MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  16%|█▌        | 679M/4.27G [00:41<02:39, 22.5MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  16%|█▌        | 683M/4.27G [00:41<02:23, 25.0MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  16%|█▌        | 686M/4.27G [00:41<02:10, 27.5MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  16%|█▌        | 689M/4.27G [00:42<02:08, 27.8MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  16%|█▌        | 692M/4.27G [00:42<03:28, 17.1MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  16%|█▋        | 694M/4.27G [00:42<06:12, 9.58MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  16%|█▋        | 697M/4.27G [00:43<04:59, 11.9MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  16%|█▋        | 699M/4.27G [00:43<05:26, 10.9MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  16%|█▋        | 701M/4.27G [00:43<05:01, 11.8MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  16%|█▋        | 703M/4.27G [00:43<06:49, 8.70MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  17%|█▋        | 704M/4.27G [00:43<07:06, 8.35MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  17%|█▋        | 707M/4.27G [00:44<05:10, 11.5MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  17%|█▋        | 709M/4.27G [00:44<05:23, 11.0MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  17%|█▋        | 710M/4.27G [00:44<04:59, 11.9MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  17%|█▋        | 712M/4.27G [00:44<04:55, 12.0MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  17%|█▋        | 713M/4.27G [00:44<04:57, 11.9MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  17%|█▋        | 715M/4.27G [00:44<04:30, 13.1MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  17%|█▋        | 716M/4.27G [00:44<04:32, 13.0MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  17%|█▋        | 718M/4.27G [00:44<04:50, 12.2MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  17%|█▋        | 720M/4.27G [00:44<03:45, 15.7MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  17%|█▋        | 722M/4.27G [00:45<04:13, 14.0MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  17%|█▋        | 725M/4.27G [00:45<03:22, 17.5MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  17%|█▋        | 727M/4.27G [00:45<03:06, 19.0MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  17%|█▋        | 730M/4.27G [00:45<02:59, 19.7MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  17%|█▋        | 732M/4.27G [00:45<02:55, 20.1MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  17%|█▋        | 734M/4.27G [00:45<02:49, 20.8MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  17%|█▋        | 736M/4.27G [00:45<02:45, 21.3MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  17%|█▋        | 738M/4.27G [00:45<03:22, 17.4MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  17%|█▋        | 740M/4.27G [00:46<03:39, 16.0MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  17%|█▋        | 742M/4.27G [00:46<03:24, 17.3MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  17%|█▋        | 744M/4.27G [00:46<03:28, 16.9MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  17%|█▋        | 746M/4.27G [00:46<04:11, 14.0MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  18%|█▊        | 749M/4.27G [00:46<03:15, 18.0MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  18%|█▊        | 751M/4.27G [00:46<03:13, 18.2MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  18%|█▊        | 753M/4.27G [00:46<03:09, 18.5MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  18%|█▊        | 755M/4.27G [00:46<03:14, 18.1MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  18%|█▊        | 759M/4.27G [00:47<02:28, 23.6MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  18%|█▊        | 762M/4.27G [00:47<02:26, 23.9MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  18%|█▊        | 764M/4.27G [00:47<02:22, 24.7MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  18%|█▊        | 767M/4.27G [00:47<02:21, 24.7MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  18%|█▊        | 770M/4.27G [00:47<02:31, 23.1MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  18%|█▊        | 772M/4.27G [00:47<02:34, 22.5MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  18%|█▊        | 775M/4.27G [00:47<02:43, 21.4MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  18%|█▊        | 778M/4.27G [00:47<02:19, 25.1MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  18%|█▊        | 781M/4.27G [00:47<02:31, 23.0MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  18%|█▊        | 784M/4.27G [00:48<02:39, 21.8MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  18%|█▊        | 788M/4.27G [00:48<02:20, 24.8MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  19%|█▊        | 790M/4.27G [00:48<02:30, 23.1MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  19%|█▊        | 793M/4.27G [00:48<03:36, 16.0MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  19%|█▊        | 796M/4.27G [00:48<02:56, 19.6MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  19%|█▊        | 799M/4.27G [00:48<02:54, 19.8MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  19%|█▉        | 801M/4.27G [00:48<02:50, 20.4MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  19%|█▉        | 803M/4.27G [00:49<02:57, 19.5MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  19%|█▉        | 805M/4.27G [00:49<04:05, 14.1MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  19%|█▉        | 807M/4.27G [00:49<03:50, 15.0MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  19%|█▉        | 809M/4.27G [00:49<05:44, 10.0MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  19%|█▉        | 812M/4.27G [00:49<04:49, 11.9MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  19%|█▉        | 813M/4.27G [00:50<04:54, 11.7MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  19%|█▉        | 815M/4.27G [00:50<04:56, 11.6MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  19%|█▉        | 816M/4.27G [00:50<04:32, 12.7MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  19%|█▉        | 819M/4.27G [00:50<03:27, 16.6MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  19%|█▉        | 821M/4.27G [00:50<03:17, 17.4MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  19%|█▉        | 823M/4.27G [00:50<04:21, 13.1MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  19%|█▉        | 825M/4.27G [00:50<03:43, 15.4MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  19%|█▉        | 828M/4.27G [00:50<03:26, 16.6MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  19%|█▉        | 830M/4.27G [00:51<04:15, 13.5MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  19%|█▉        | 832M/4.27G [00:51<05:15, 10.9MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  20%|█▉        | 833M/4.27G [00:51<04:48, 11.9MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  20%|█▉        | 835M/4.27G [00:51<04:05, 13.9MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  20%|█▉        | 837M/4.27G [00:51<03:57, 14.5MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  20%|█▉        | 840M/4.27G [00:51<03:15, 17.5MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  20%|█▉        | 842M/4.27G [00:52<04:38, 12.3MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  20%|█▉        | 845M/4.27G [00:52<03:24, 16.7MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  20%|█▉        | 847M/4.27G [00:52<05:11, 11.0MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  20%|█▉        | 850M/4.27G [00:52<04:04, 13.9MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  20%|█▉        | 852M/4.27G [00:52<05:00, 11.4MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  20%|██        | 856M/4.27G [00:53<03:44, 15.2MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  20%|██        | 858M/4.27G [00:53<04:26, 12.8MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  20%|██        | 861M/4.27G [00:53<03:35, 15.8MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  20%|██        | 863M/4.27G [00:53<04:50, 11.7MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  20%|██        | 866M/4.27G [00:53<03:46, 15.0MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  20%|██        | 868M/4.27G [00:53<03:37, 15.6MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  20%|██        | 870M/4.27G [00:54<03:37, 15.6MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  20%|██        | 873M/4.27G [00:54<03:01, 18.7MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  21%|██        | 876M/4.27G [00:54<02:53, 19.6MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  21%|██        | 878M/4.27G [00:54<02:58, 18.9MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  21%|██        | 880M/4.27G [00:54<03:03, 18.5MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  21%|██        | 883M/4.27G [00:54<02:33, 22.0MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  21%|██        | 885M/4.27G [00:54<03:09, 17.9MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  21%|██        | 889M/4.27G [00:54<02:37, 21.5MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  21%|██        | 891M/4.27G [00:55<02:40, 21.0MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  21%|██        | 894M/4.27G [00:55<04:00, 14.0MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  21%|██        | 896M/4.27G [00:55<03:32, 15.8MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  21%|██        | 898M/4.27G [00:55<04:45, 11.8MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  21%|██        | 900M/4.27G [00:55<04:08, 13.5MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  21%|██        | 902M/4.27G [00:56<04:15, 13.1MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  21%|██        | 903M/4.27G [00:56<05:26, 10.3MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  21%|██        | 906M/4.27G [00:56<04:31, 12.4MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  21%|██▏       | 907M/4.27G [00:56<05:17, 10.6MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  21%|██▏       | 910M/4.27G [00:56<03:57, 14.1MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  21%|██▏       | 912M/4.27G [00:57<05:27, 10.2MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  21%|██▏       | 914M/4.27G [00:57<04:55, 11.4MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  21%|██▏       | 915M/4.27G [00:57<06:22, 8.76MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  22%|██▏       | 917M/4.27G [00:57<04:58, 11.2MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  22%|██▏       | 919M/4.27G [00:57<04:51, 11.5MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  22%|██▏       | 921M/4.27G [00:57<04:22, 12.7MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  22%|██▏       | 922M/4.27G [00:57<04:58, 11.2MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  22%|██▏       | 926M/4.27G [00:58<03:10, 17.5MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  22%|██▏       | 928M/4.27G [00:58<03:22, 16.4MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  22%|██▏       | 930M/4.27G [00:58<04:39, 11.9MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  22%|██▏       | 934M/4.27G [00:58<03:18, 16.8MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  22%|██▏       | 936M/4.27G [00:58<03:14, 17.1MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  22%|██▏       | 939M/4.27G [00:58<02:47, 19.8MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  22%|██▏       | 942M/4.27G [00:58<02:52, 19.3MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  22%|██▏       | 944M/4.27G [00:58<02:44, 20.2MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  22%|██▏       | 947M/4.27G [00:59<02:21, 23.4MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  22%|██▏       | 950M/4.27G [00:59<02:11, 25.2MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  22%|██▏       | 953M/4.27G [00:59<02:43, 20.3MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  22%|██▏       | 957M/4.27G [00:59<02:12, 24.9MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  23%|██▎       | 960M/4.27G [00:59<02:19, 23.6MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  23%|██▎       | 962M/4.27G [00:59<02:40, 20.6MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  23%|██▎       | 966M/4.27G [00:59<02:22, 23.1MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  23%|██▎       | 968M/4.27G [01:00<02:35, 21.2MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  23%|██▎       | 971M/4.27G [01:00<02:18, 23.7MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  23%|██▎       | 974M/4.27G [01:00<02:12, 24.9MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  23%|██▎       | 977M/4.27G [01:00<03:53, 14.1MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  23%|██▎       | 980M/4.27G [01:00<03:14, 16.9MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  23%|██▎       | 982M/4.27G [01:01<04:16, 12.8MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  23%|██▎       | 986M/4.27G [01:01<03:18, 16.5MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  23%|██▎       | 988M/4.27G [01:01<03:06, 17.6MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  23%|██▎       | 990M/4.27G [01:01<03:22, 16.2MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  23%|██▎       | 993M/4.27G [01:01<02:51, 19.1MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  23%|██▎       | 996M/4.27G [01:01<04:52, 11.2MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  23%|██▎       | 998M/4.27G [01:02<03:55, 13.9MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  23%|██▎       | 1.00G/4.27G [01:02<03:46, 14.4MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  24%|██▎       | 1.00G/4.27G [01:02<03:08, 17.3MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  24%|██▎       | 1.01G/4.27G [01:02<03:05, 17.5MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  24%|██▎       | 1.01G/4.27G [01:02<03:07, 17.4MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  24%|██▎       | 1.01G/4.27G [01:02<02:39, 20.5MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  24%|██▍       | 1.01G/4.27G [01:02<02:35, 20.9MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  24%|██▍       | 1.02G/4.27G [01:02<02:12, 24.5MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  24%|██▍       | 1.02G/4.27G [01:03<02:18, 23.4MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  24%|██▍       | 1.02G/4.27G [01:03<02:01, 26.8MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  24%|██▍       | 1.03G/4.27G [01:03<01:54, 28.3MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  24%|██▍       | 1.03G/4.27G [01:03<02:06, 25.5MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  24%|██▍       | 1.03G/4.27G [01:03<02:10, 24.9MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  24%|██▍       | 1.04G/4.27G [01:03<02:00, 26.9MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  24%|██▍       | 1.04G/4.27G [01:03<02:06, 25.5MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  24%|██▍       | 1.04G/4.27G [01:03<03:02, 17.6MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  24%|██▍       | 1.04G/4.27G [01:04<02:33, 21.0MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  25%|██▍       | 1.05G/4.27G [01:04<02:20, 22.9MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  25%|██▍       | 1.05G/4.27G [01:04<02:10, 24.7MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  25%|██▍       | 1.05G/4.27G [01:04<04:03, 13.2MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  25%|██▍       | 1.05G/4.27G [01:04<03:46, 14.2MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  25%|██▍       | 1.06G/4.27G [01:05<04:47, 11.1MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  25%|██▍       | 1.06G/4.27G [01:05<04:12, 12.7MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  25%|██▍       | 1.06G/4.27G [01:05<04:58, 10.7MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  25%|██▍       | 1.06G/4.27G [01:05<04:16, 12.5MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  25%|██▍       | 1.06G/4.27G [01:05<04:50, 11.0MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  25%|██▌       | 1.07G/4.27G [01:05<03:46, 14.1MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  25%|██▌       | 1.07G/4.27G [01:05<03:31, 15.1MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  25%|██▌       | 1.07G/4.27G [01:06<03:07, 17.0MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  25%|██▌       | 1.07G/4.27G [01:06<02:47, 19.1MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  25%|██▌       | 1.08G/4.27G [01:06<02:33, 20.7MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  25%|██▌       | 1.08G/4.27G [01:06<02:27, 21.7MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  25%|██▌       | 1.08G/4.27G [01:06<02:26, 21.8MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  25%|██▌       | 1.08G/4.27G [01:06<02:07, 24.9MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  25%|██▌       | 1.09G/4.27G [01:06<02:01, 26.1MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  26%|██▌       | 1.09G/4.27G [01:06<02:02, 25.8MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  26%|██▌       | 1.09G/4.27G [01:07<02:58, 17.8MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  26%|██▌       | 1.10G/4.27G [01:07<02:41, 19.7MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  26%|██▌       | 1.10G/4.27G [01:07<02:35, 20.4MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  26%|██▌       | 1.10G/4.27G [01:07<03:25, 15.4MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  26%|██▌       | 1.10G/4.27G [01:07<04:23, 12.0MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  26%|██▌       | 1.11G/4.27G [01:07<03:24, 15.4MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  26%|██▌       | 1.11G/4.27G [01:08<04:36, 11.4MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  26%|██▌       | 1.11G/4.27G [01:08<06:00, 8.76MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  26%|██▌       | 1.11G/4.27G [01:08<04:05, 12.8MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  26%|██▌       | 1.11G/4.27G [01:08<03:52, 13.5MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  26%|██▌       | 1.12G/4.27G [01:08<04:10, 12.6MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  26%|██▌       | 1.12G/4.27G [01:09<04:02, 13.0MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  26%|██▋       | 1.12G/4.27G [01:09<04:15, 12.3MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  26%|██▋       | 1.12G/4.27G [01:09<04:33, 11.5MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  26%|██▋       | 1.12G/4.27G [01:09<04:44, 11.0MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  26%|██▋       | 1.13G/4.27G [01:09<03:14, 16.1MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  26%|██▋       | 1.13G/4.27G [01:09<02:57, 17.7MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  27%|██▋       | 1.13G/4.27G [01:09<02:52, 18.2MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  27%|██▋       | 1.13G/4.27G [01:09<02:53, 18.1MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  27%|██▋       | 1.13G/4.27G [01:10<03:08, 16.6MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  27%|██▋       | 1.14G/4.27G [01:10<03:10, 16.4MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  27%|██▋       | 1.14G/4.27G [01:10<02:33, 20.4MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  27%|██▋       | 1.14G/4.27G [01:10<02:29, 20.9MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  27%|██▋       | 1.14G/4.27G [01:10<02:30, 20.7MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  27%|██▋       | 1.15G/4.27G [01:10<02:30, 20.7MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  27%|██▋       | 1.15G/4.27G [01:10<02:45, 18.8MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  27%|██▋       | 1.15G/4.27G [01:10<02:29, 20.8MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  27%|██▋       | 1.15G/4.27G [01:10<02:22, 21.8MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  27%|██▋       | 1.16G/4.27G [01:11<02:20, 22.1MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  27%|██▋       | 1.16G/4.27G [01:11<02:15, 23.0MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  27%|██▋       | 1.16G/4.27G [01:11<02:10, 23.7MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  27%|██▋       | 1.16G/4.27G [01:11<02:44, 18.9MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  27%|██▋       | 1.17G/4.27G [01:11<02:28, 20.9MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  27%|██▋       | 1.17G/4.27G [01:11<02:02, 25.3MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  28%|██▊       | 1.17G/4.27G [01:11<02:04, 24.8MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  28%|██▊       | 1.18G/4.27G [01:11<02:00, 25.6MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  28%|██▊       | 1.18G/4.27G [01:12<02:06, 24.5MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  28%|██▊       | 1.18G/4.27G [01:12<04:40, 11.0MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  28%|██▊       | 1.18G/4.27G [01:12<05:58, 8.59MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  28%|██▊       | 1.19G/4.27G [01:13<05:05, 10.1MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  28%|██▊       | 1.19G/4.27G [01:13<05:55, 8.65MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  28%|██▊       | 1.19G/4.27G [01:13<05:14, 9.77MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  28%|██▊       | 1.19G/4.27G [01:13<06:45, 7.59MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  28%|██▊       | 1.19G/4.27G [01:13<05:25, 9.44MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  28%|██▊       | 1.19G/4.27G [01:14<05:40, 9.02MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  28%|██▊       | 1.19G/4.27G [01:14<05:35, 9.15MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  28%|██▊       | 1.20G/4.27G [01:14<04:43, 10.8MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  28%|██▊       | 1.20G/4.27G [01:14<06:08, 8.32MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  28%|██▊       | 1.20G/4.27G [01:14<06:51, 7.45MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  28%|██▊       | 1.20G/4.27G [01:14<07:09, 7.13MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  28%|██▊       | 1.20G/4.27G [01:15<07:10, 7.11MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  28%|██▊       | 1.20G/4.27G [01:15<04:36, 11.1MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  28%|██▊       | 1.20G/4.27G [01:15<05:13, 9.75MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  28%|██▊       | 1.21G/4.27G [01:15<04:43, 10.8MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  28%|██▊       | 1.21G/4.27G [01:15<07:33, 6.75MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  28%|██▊       | 1.21G/4.27G [01:15<07:43, 6.59MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  28%|██▊       | 1.21G/4.27G [01:16<05:27, 9.32MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  28%|██▊       | 1.21G/4.27G [01:16<04:28, 11.4MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  28%|██▊       | 1.21G/4.27G [01:16<04:13, 12.0MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  28%|██▊       | 1.22G/4.27G [01:16<05:18, 9.57MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  29%|██▊       | 1.22G/4.27G [01:16<04:58, 10.2MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  29%|██▊       | 1.22G/4.27G [01:16<03:42, 13.7MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  29%|██▊       | 1.22G/4.27G [01:16<04:29, 11.3MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  29%|██▊       | 1.22G/4.27G [01:16<03:51, 13.1MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  29%|██▊       | 1.22G/4.27G [01:17<03:36, 14.1MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  29%|██▊       | 1.23G/4.27G [01:17<06:04, 8.34MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  29%|██▉       | 1.23G/4.27G [01:17<05:33, 9.11MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  29%|██▉       | 1.23G/4.27G [01:17<04:28, 11.3MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  29%|██▉       | 1.23G/4.27G [01:17<05:18, 9.54MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  29%|██▉       | 1.23G/4.27G [01:18<04:56, 10.2MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  29%|██▉       | 1.23G/4.27G [01:18<05:49, 8.68MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  29%|██▉       | 1.24G/4.27G [01:18<04:34, 11.0MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  29%|██▉       | 1.24G/4.27G [01:18<06:08, 8.21MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  29%|██▉       | 1.24G/4.27G [01:18<04:50, 10.4MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  29%|██▉       | 1.24G/4.27G [01:19<07:10, 7.03MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  29%|██▉       | 1.24G/4.27G [01:19<07:24, 6.80MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  29%|██▉       | 1.24G/4.27G [01:19<05:20, 9.42MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  29%|██▉       | 1.25G/4.27G [01:19<04:12, 12.0MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  29%|██▉       | 1.25G/4.27G [01:19<04:10, 12.0MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  29%|██▉       | 1.25G/4.27G [01:19<03:54, 12.9MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  29%|██▉       | 1.25G/4.27G [01:19<03:51, 13.0MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  29%|██▉       | 1.25G/4.27G [01:20<04:20, 11.5MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  29%|██▉       | 1.26G/4.27G [01:20<03:35, 14.0MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  29%|██▉       | 1.26G/4.27G [01:20<04:36, 10.9MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  29%|██▉       | 1.26G/4.27G [01:20<06:18, 7.94MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  30%|██▉       | 1.26G/4.27G [01:20<04:20, 11.5MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  30%|██▉       | 1.26G/4.27G [01:21<05:29, 9.12MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  30%|██▉       | 1.26G/4.27G [01:21<08:05, 6.18MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  30%|██▉       | 1.27G/4.27G [01:21<05:48, 8.60MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  30%|██▉       | 1.27G/4.27G [01:21<05:38, 8.86MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  30%|██▉       | 1.27G/4.27G [01:21<05:49, 8.56MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  30%|██▉       | 1.27G/4.27G [01:22<05:32, 9.00MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  30%|██▉       | 1.27G/4.27G [01:22<05:31, 9.02MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  30%|██▉       | 1.27G/4.27G [01:22<04:25, 11.3MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  30%|██▉       | 1.28G/4.27G [01:22<05:34, 8.93MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  30%|██▉       | 1.28G/4.27G [01:22<04:04, 12.2MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  30%|██▉       | 1.28G/4.27G [01:22<04:11, 11.9MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  30%|███       | 1.28G/4.27G [01:22<03:38, 13.7MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  30%|███       | 1.28G/4.27G [01:23<04:34, 10.9MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  30%|███       | 1.28G/4.27G [01:23<06:22, 7.80MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  30%|███       | 1.29G/4.27G [01:23<05:39, 8.77MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  30%|███       | 1.29G/4.27G [01:23<03:53, 12.7MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  30%|███       | 1.29G/4.27G [01:23<03:48, 13.0MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  30%|███       | 1.29G/4.27G [01:23<03:56, 12.6MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  30%|███       | 1.29G/4.27G [01:24<03:50, 12.9MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  30%|███       | 1.30G/4.27G [01:24<03:17, 15.0MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  30%|███       | 1.30G/4.27G [01:24<02:53, 17.1MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  30%|███       | 1.30G/4.27G [01:24<04:55, 10.0MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  31%|███       | 1.30G/4.27G [01:24<05:50, 8.45MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  31%|███       | 1.30G/4.27G [01:25<04:05, 12.1MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  31%|███       | 1.31G/4.27G [01:25<03:46, 13.1MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  31%|███       | 1.31G/4.27G [01:25<04:05, 12.0MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  31%|███       | 1.31G/4.27G [01:25<03:30, 14.0MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  31%|███       | 1.31G/4.27G [01:25<03:07, 15.7MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  31%|███       | 1.31G/4.27G [01:25<02:53, 17.0MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  31%|███       | 1.32G/4.27G [01:25<02:39, 18.5MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  31%|███       | 1.32G/4.27G [01:25<02:33, 19.2MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  31%|███       | 1.32G/4.27G [01:25<02:25, 20.2MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  31%|███       | 1.32G/4.27G [01:26<02:27, 20.0MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  31%|███       | 1.33G/4.27G [01:26<02:24, 20.4MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  31%|███       | 1.33G/4.27G [01:26<02:23, 20.5MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  31%|███       | 1.33G/4.27G [01:26<03:01, 16.2MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  31%|███       | 1.33G/4.27G [01:26<02:56, 16.6MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  31%|███▏      | 1.33G/4.27G [01:26<04:28, 10.9MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  31%|███▏      | 1.34G/4.27G [01:26<03:22, 14.5MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  31%|███▏      | 1.34G/4.27G [01:27<03:03, 15.9MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  31%|███▏      | 1.34G/4.27G [01:27<03:41, 13.2MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  31%|███▏      | 1.34G/4.27G [01:27<03:17, 14.8MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  32%|███▏      | 1.34G/4.27G [01:27<04:45, 10.2MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  32%|███▏      | 1.35G/4.27G [01:27<03:52, 12.6MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  32%|███▏      | 1.35G/4.27G [01:27<02:55, 16.6MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  32%|███▏      | 1.35G/4.27G [01:27<02:27, 19.8MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  32%|███▏      | 1.36G/4.27G [01:28<02:29, 19.5MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  32%|███▏      | 1.36G/4.27G [01:28<02:08, 22.6MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  32%|███▏      | 1.36G/4.27G [01:28<02:11, 22.1MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  32%|███▏      | 1.36G/4.27G [01:28<02:17, 21.1MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  32%|███▏      | 1.37G/4.27G [01:28<02:56, 16.4MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  32%|███▏      | 1.37G/4.27G [01:28<02:16, 21.2MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  32%|███▏      | 1.37G/4.27G [01:28<02:32, 19.0MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  32%|███▏      | 1.38G/4.27G [01:29<02:14, 21.6MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  32%|███▏      | 1.38G/4.27G [01:29<01:55, 25.0MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  32%|███▏      | 1.38G/4.27G [01:29<01:57, 24.6MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  33%|███▎      | 1.39G/4.27G [01:29<01:32, 31.0MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  33%|███▎      | 1.39G/4.27G [01:29<01:27, 32.7MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  33%|███▎      | 1.40G/4.27G [01:29<01:32, 31.2MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  33%|███▎      | 1.40G/4.27G [01:29<01:19, 36.1MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  33%|███▎      | 1.40G/4.27G [01:29<01:13, 38.8MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  33%|███▎      | 1.41G/4.27G [01:29<01:11, 39.8MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  33%|███▎      | 1.41G/4.27G [01:30<01:16, 37.3MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  33%|███▎      | 1.42G/4.27G [01:30<01:14, 38.3MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  33%|███▎      | 1.42G/4.27G [01:30<01:11, 40.0MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  33%|███▎      | 1.43G/4.27G [01:30<01:11, 39.8MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  34%|███▎      | 1.43G/4.27G [01:30<01:21, 34.7MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  34%|███▎      | 1.43G/4.27G [01:30<01:27, 32.3MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  34%|███▍      | 1.44G/4.27G [01:30<01:16, 36.8MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  34%|███▍      | 1.44G/4.27G [01:30<01:12, 38.8MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  34%|███▍      | 1.45G/4.27G [01:30<01:08, 41.3MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  34%|███▍      | 1.45G/4.27G [01:31<01:08, 41.3MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  34%|███▍      | 1.46G/4.27G [01:31<01:11, 39.5MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  34%|███▍      | 1.46G/4.27G [01:31<01:09, 40.5MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  34%|███▍      | 1.47G/4.27G [01:31<01:16, 36.4MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  34%|███▍      | 1.47G/4.27G [01:31<01:24, 33.1MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  35%|███▍      | 1.47G/4.27G [01:31<01:20, 34.8MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  35%|███▍      | 1.48G/4.27G [01:31<01:20, 34.6MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  35%|███▍      | 1.48G/4.27G [01:31<01:21, 34.1MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  35%|███▍      | 1.48G/4.27G [01:32<01:21, 34.3MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  35%|███▍      | 1.49G/4.27G [01:32<01:21, 34.2MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  35%|███▍      | 1.49G/4.27G [01:32<01:18, 35.5MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  35%|███▌      | 1.50G/4.27G [01:32<01:18, 35.3MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  35%|███▌      | 1.50G/4.27G [01:32<01:24, 32.9MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  35%|███▌      | 1.50G/4.27G [01:32<02:03, 22.4MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  35%|███▌      | 1.51G/4.27G [01:32<01:48, 25.4MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  35%|███▌      | 1.51G/4.27G [01:32<01:53, 24.3MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  35%|███▌      | 1.51G/4.27G [01:33<01:44, 26.2MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  36%|███▌      | 1.52G/4.27G [01:33<02:12, 20.7MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  36%|███▌      | 1.52G/4.27G [01:33<02:01, 22.6MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  36%|███▌      | 1.52G/4.27G [01:33<02:15, 20.3MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  36%|███▌      | 1.52G/4.27G [01:33<02:10, 21.0MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  36%|███▌      | 1.53G/4.27G [01:33<02:17, 19.9MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  36%|███▌      | 1.53G/4.27G [01:33<02:17, 20.0MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  36%|███▌      | 1.53G/4.27G [01:34<02:45, 16.6MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  36%|███▌      | 1.53G/4.27G [01:34<02:16, 20.0MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  36%|███▌      | 1.54G/4.27G [01:34<02:07, 21.4MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  36%|███▌      | 1.54G/4.27G [01:34<02:02, 22.3MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  36%|███▌      | 1.54G/4.27G [01:34<01:39, 27.3MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  36%|███▌      | 1.55G/4.27G [01:34<01:33, 29.0MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  36%|███▋      | 1.55G/4.27G [01:34<01:29, 30.5MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  36%|███▋      | 1.55G/4.27G [01:34<01:21, 33.1MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  37%|███▋      | 1.56G/4.27G [01:34<01:18, 34.5MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  37%|███▋      | 1.56G/4.27G [01:34<01:17, 34.9MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  37%|███▋      | 1.56G/4.27G [01:35<01:23, 32.2MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  37%|███▋      | 1.57G/4.27G [01:35<01:16, 35.5MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  37%|███▋      | 1.57G/4.27G [01:35<01:32, 29.2MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  37%|███▋      | 1.58G/4.27G [01:35<01:24, 31.7MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  37%|███▋      | 1.58G/4.27G [01:35<01:21, 33.0MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  37%|███▋      | 1.58G/4.27G [01:35<01:13, 36.4MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  37%|███▋      | 1.59G/4.27G [01:35<01:15, 35.3MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  37%|███▋      | 1.59G/4.27G [01:35<01:17, 34.4MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  37%|███▋      | 1.60G/4.27G [01:36<01:15, 35.2MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  38%|███▊      | 1.60G/4.27G [01:36<01:08, 38.8MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  38%|███▊      | 1.60G/4.27G [01:36<01:14, 35.9MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  38%|███▊      | 1.61G/4.27G [01:36<01:19, 33.4MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  38%|███▊      | 1.61G/4.27G [01:36<01:27, 30.3MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  38%|███▊      | 1.61G/4.27G [01:36<01:53, 23.3MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  38%|███▊      | 1.62G/4.27G [01:36<01:31, 29.0MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  38%|███▊      | 1.62G/4.27G [01:36<01:25, 30.8MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  38%|███▊      | 1.63G/4.27G [01:37<01:17, 33.9MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  38%|███▊      | 1.63G/4.27G [01:37<01:12, 36.4MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  38%|███▊      | 1.64G/4.27G [01:37<01:07, 39.2MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  38%|███▊      | 1.64G/4.27G [01:37<01:12, 36.0MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  39%|███▊      | 1.64G/4.27G [01:37<01:20, 32.6MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  39%|███▊      | 1.65G/4.27G [01:37<01:15, 34.6MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  39%|███▊      | 1.65G/4.27G [01:38<02:14, 19.5MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  39%|███▉      | 1.66G/4.27G [01:38<01:58, 22.0MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  39%|███▉      | 1.66G/4.27G [01:38<01:39, 26.3MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  39%|███▉      | 1.66G/4.27G [01:38<01:31, 28.6MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  39%|███▉      | 1.67G/4.27G [01:38<01:26, 29.9MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  39%|███▉      | 1.67G/4.27G [01:38<01:37, 26.6MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  39%|███▉      | 1.67G/4.27G [01:38<01:37, 26.7MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  39%|███▉      | 1.68G/4.27G [01:38<01:35, 27.1MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  39%|███▉      | 1.68G/4.27G [01:38<01:51, 23.2MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  39%|███▉      | 1.68G/4.27G [01:39<01:31, 28.2MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  40%|███▉      | 1.69G/4.27G [01:39<01:32, 28.0MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  40%|███▉      | 1.69G/4.27G [01:39<01:49, 23.6MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  40%|███▉      | 1.69G/4.27G [01:39<02:14, 19.1MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  40%|███▉      | 1.70G/4.27G [01:39<01:44, 24.5MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  40%|███▉      | 1.70G/4.27G [01:39<01:40, 25.4MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  40%|███▉      | 1.70G/4.27G [01:39<01:34, 27.0MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  40%|████      | 1.71G/4.27G [01:40<01:19, 32.2MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  40%|████      | 1.71G/4.27G [01:40<01:11, 35.5MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  40%|████      | 1.72G/4.27G [01:40<01:09, 36.8MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  40%|████      | 1.72G/4.27G [01:40<01:12, 34.9MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  40%|████      | 1.73G/4.27G [01:40<01:09, 36.7MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  41%|████      | 1.73G/4.27G [01:40<01:11, 35.5MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  41%|████      | 1.73G/4.27G [01:40<01:18, 32.3MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  41%|████      | 1.74G/4.27G [01:40<01:47, 23.5MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  41%|████      | 1.74G/4.27G [01:41<01:38, 25.8MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  41%|████      | 1.74G/4.27G [01:41<01:30, 28.0MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  41%|████      | 1.75G/4.27G [01:41<01:18, 32.2MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  41%|████      | 1.75G/4.27G [01:41<01:12, 34.5MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  41%|████      | 1.76G/4.27G [01:41<01:14, 33.5MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  41%|████▏     | 1.76G/4.27G [01:41<01:09, 35.9MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  41%|████▏     | 1.76G/4.27G [01:41<01:09, 36.0MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  41%|████▏     | 1.77G/4.27G [01:41<01:06, 37.7MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  42%|████▏     | 1.77G/4.27G [01:41<01:02, 39.9MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  42%|████▏     | 1.78G/4.27G [01:41<01:03, 39.1MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  42%|████▏     | 1.78G/4.27G [01:42<02:09, 19.2MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  42%|████▏     | 1.78G/4.27G [01:42<02:04, 20.0MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  42%|████▏     | 1.79G/4.27G [01:42<01:56, 21.3MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  42%|████▏     | 1.79G/4.27G [01:42<02:24, 17.1MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  42%|████▏     | 1.79G/4.27G [01:43<02:53, 14.3MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  42%|████▏     | 1.79G/4.27G [01:43<02:23, 17.3MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  42%|████▏     | 1.80G/4.27G [01:43<02:36, 15.8MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  42%|████▏     | 1.80G/4.27G [01:43<02:25, 17.0MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  42%|████▏     | 1.80G/4.27G [01:43<03:33, 11.6MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  42%|████▏     | 1.80G/4.27G [01:44<02:52, 14.2MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  42%|████▏     | 1.81G/4.27G [01:44<02:20, 17.5MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  42%|████▏     | 1.81G/4.27G [01:44<01:57, 20.9MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  43%|████▎     | 1.81G/4.27G [01:44<02:30, 16.3MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  43%|████▎     | 1.82G/4.27G [01:44<02:01, 20.1MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  43%|████▎     | 1.82G/4.27G [01:45<03:12, 12.7MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  43%|████▎     | 1.82G/4.27G [01:45<02:41, 15.2MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  43%|████▎     | 1.82G/4.27G [01:45<02:50, 14.3MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  43%|████▎     | 1.83G/4.27G [01:45<02:29, 16.3MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  43%|████▎     | 1.83G/4.27G [01:45<02:13, 18.2MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  43%|████▎     | 1.83G/4.27G [01:45<01:49, 22.2MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  43%|████▎     | 1.84G/4.27G [01:45<01:51, 21.8MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  43%|████▎     | 1.84G/4.27G [01:45<01:39, 24.4MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  43%|████▎     | 1.84G/4.27G [01:46<02:40, 15.1MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  43%|████▎     | 1.84G/4.27G [01:46<03:02, 13.2MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  43%|████▎     | 1.85G/4.27G [01:46<02:56, 13.7MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  43%|████▎     | 1.85G/4.27G [01:46<02:57, 13.7MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  43%|████▎     | 1.85G/4.27G [01:46<02:34, 15.6MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  43%|████▎     | 1.85G/4.27G [01:46<01:58, 20.3MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  44%|████▎     | 1.86G/4.27G [01:47<01:57, 20.5MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  44%|████▎     | 1.86G/4.27G [01:47<01:55, 20.8MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  44%|████▎     | 1.86G/4.27G [01:47<01:52, 21.4MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  44%|████▎     | 1.86G/4.27G [01:47<01:41, 23.7MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  44%|████▍     | 1.87G/4.27G [01:47<01:48, 22.1MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  44%|████▍     | 1.87G/4.27G [01:47<01:37, 24.6MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  44%|████▍     | 1.87G/4.27G [01:47<01:36, 24.9MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  44%|████▍     | 1.88G/4.27G [01:47<02:25, 16.4MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  44%|████▍     | 1.88G/4.27G [01:48<02:49, 14.1MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  44%|████▍     | 1.88G/4.27G [01:48<03:12, 12.4MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  44%|████▍     | 1.88G/4.27G [01:48<02:25, 16.4MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  44%|████▍     | 1.89G/4.27G [01:48<02:53, 13.7MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  44%|████▍     | 1.89G/4.27G [01:48<02:10, 18.3MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  44%|████▍     | 1.89G/4.27G [01:49<02:03, 19.2MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  44%|████▍     | 1.90G/4.27G [01:49<02:05, 18.9MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  44%|████▍     | 1.90G/4.27G [01:49<02:31, 15.6MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  45%|████▍     | 1.90G/4.27G [01:49<02:05, 18.9MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  45%|████▍     | 1.90G/4.27G [01:49<02:01, 19.5MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  45%|████▍     | 1.91G/4.27G [01:49<01:44, 22.5MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  45%|████▍     | 1.91G/4.27G [01:50<03:14, 12.1MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  45%|████▍     | 1.91G/4.27G [01:50<03:10, 12.4MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  45%|████▍     | 1.91G/4.27G [01:50<02:29, 15.7MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  45%|████▍     | 1.92G/4.27G [01:50<02:13, 17.6MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  45%|████▍     | 1.92G/4.27G [01:50<02:14, 17.4MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  45%|████▌     | 1.92G/4.27G [01:50<02:17, 17.1MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  45%|████▌     | 1.92G/4.27G [01:51<02:58, 13.1MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  45%|████▌     | 1.93G/4.27G [01:51<02:28, 15.8MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  45%|████▌     | 1.93G/4.27G [01:51<02:25, 16.0MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  45%|████▌     | 1.93G/4.27G [01:51<02:05, 18.7MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  45%|████▌     | 1.93G/4.27G [01:51<02:06, 18.5MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  45%|████▌     | 1.93G/4.27G [01:51<01:54, 20.4MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  45%|████▌     | 1.94G/4.27G [01:51<02:27, 15.7MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  45%|████▌     | 1.94G/4.27G [01:51<02:11, 17.7MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  46%|████▌     | 1.94G/4.27G [01:52<02:54, 13.3MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  46%|████▌     | 1.94G/4.27G [01:52<02:16, 17.1MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  46%|████▌     | 1.95G/4.27G [01:52<02:17, 16.9MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  46%|████▌     | 1.95G/4.27G [01:52<02:04, 18.6MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  46%|████▌     | 1.95G/4.27G [01:52<01:48, 21.4MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  46%|████▌     | 1.95G/4.27G [01:52<02:21, 16.4MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  46%|████▌     | 1.96G/4.27G [01:52<02:11, 17.5MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  46%|████▌     | 1.96G/4.27G [01:53<03:33, 10.8MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  46%|████▌     | 1.96G/4.27G [01:53<02:51, 13.4MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  46%|████▌     | 1.96G/4.27G [01:53<02:53, 13.3MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  46%|████▌     | 1.97G/4.27G [01:53<03:10, 12.1MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  46%|████▌     | 1.97G/4.27G [01:53<02:45, 13.9MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  46%|████▌     | 1.97G/4.27G [01:54<03:41, 10.4MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  46%|████▌     | 1.97G/4.27G [01:54<02:59, 12.8MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  46%|████▋     | 1.97G/4.27G [01:54<04:42, 8.12MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  46%|████▋     | 1.97G/4.27G [01:54<05:02, 7.56MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  46%|████▋     | 1.98G/4.27G [01:54<04:00, 9.53MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  46%|████▋     | 1.98G/4.27G [01:55<04:13, 9.01MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  46%|████▋     | 1.98G/4.27G [01:55<04:06, 9.27MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  46%|████▋     | 1.98G/4.27G [01:55<03:33, 10.7MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  46%|████▋     | 1.98G/4.27G [01:55<02:57, 12.8MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  47%|████▋     | 1.98G/4.27G [01:55<02:53, 13.1MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  47%|████▋     | 1.99G/4.27G [01:55<02:48, 13.6MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  47%|████▋     | 1.99G/4.27G [01:55<02:22, 16.0MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  47%|████▋     | 1.99G/4.27G [01:55<02:19, 16.3MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  47%|████▋     | 1.99G/4.27G [01:55<02:12, 17.2MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  47%|████▋     | 1.99G/4.27G [01:56<02:25, 15.6MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  47%|████▋     | 2.00G/4.27G [01:56<02:17, 16.6MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  47%|████▋     | 2.00G/4.27G [01:56<02:08, 17.7MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  47%|████▋     | 2.00G/4.27G [01:56<02:29, 15.1MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  47%|████▋     | 2.00G/4.27G [01:56<02:12, 17.1MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  47%|████▋     | 2.00G/4.27G [01:56<02:23, 15.7MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  47%|████▋     | 2.01G/4.27G [01:56<02:05, 17.9MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  47%|████▋     | 2.01G/4.27G [01:56<01:55, 19.5MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  47%|████▋     | 2.01G/4.27G [01:57<01:50, 20.4MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  47%|████▋     | 2.01G/4.27G [01:57<03:47, 9.90MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  47%|████▋     | 2.01G/4.27G [01:57<04:29, 8.35MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  47%|████▋     | 2.02G/4.27G [01:57<03:23, 11.0MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  47%|████▋     | 2.02G/4.27G [01:58<03:00, 12.4MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  47%|████▋     | 2.02G/4.27G [01:58<03:05, 12.1MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  47%|████▋     | 2.02G/4.27G [01:58<02:23, 15.7MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  48%|████▊     | 2.03G/4.27G [01:58<02:27, 15.2MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  48%|████▊     | 2.03G/4.27G [01:58<03:09, 11.8MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  48%|████▊     | 2.03G/4.27G [01:58<02:20, 15.9MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  48%|████▊     | 2.03G/4.27G [01:58<02:08, 17.3MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  48%|████▊     | 2.04G/4.27G [01:58<02:00, 18.5MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  48%|████▊     | 2.04G/4.27G [01:59<01:52, 19.9MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  48%|████▊     | 2.04G/4.27G [01:59<01:56, 19.0MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  48%|████▊     | 2.04G/4.27G [01:59<01:44, 21.2MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  48%|████▊     | 2.05G/4.27G [01:59<01:43, 21.4MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  48%|████▊     | 2.05G/4.27G [01:59<01:37, 22.7MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  48%|████▊     | 2.05G/4.27G [01:59<03:14, 11.4MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  48%|████▊     | 2.05G/4.27G [02:00<02:48, 13.1MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  48%|████▊     | 2.05G/4.27G [02:00<03:10, 11.6MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  48%|████▊     | 2.06G/4.27G [02:00<02:42, 13.6MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  48%|████▊     | 2.06G/4.27G [02:00<02:42, 13.5MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  48%|████▊     | 2.06G/4.27G [02:00<02:25, 15.2MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  48%|████▊     | 2.06G/4.27G [02:00<02:47, 13.2MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  48%|████▊     | 2.06G/4.27G [02:00<02:30, 14.6MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  48%|████▊     | 2.07G/4.27G [02:01<03:03, 12.0MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  48%|████▊     | 2.07G/4.27G [02:01<03:22, 10.8MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  49%|████▊     | 2.07G/4.27G [02:01<05:08, 7.12MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  49%|████▊     | 2.07G/4.27G [02:01<04:32, 8.05MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  49%|████▊     | 2.07G/4.27G [02:01<04:08, 8.82MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  49%|████▊     | 2.07G/4.27G [02:01<04:00, 9.11MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  49%|████▊     | 2.07G/4.27G [02:02<03:28, 10.5MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  49%|████▊     | 2.08G/4.27G [02:02<03:20, 10.9MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  49%|████▊     | 2.08G/4.27G [02:02<03:23, 10.8MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  49%|████▊     | 2.08G/4.27G [02:02<05:18, 6.86MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  49%|████▉     | 2.08G/4.27G [02:02<03:07, 11.7MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  49%|████▉     | 2.08G/4.27G [02:02<03:05, 11.8MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  49%|████▉     | 2.08G/4.27G [02:02<03:03, 11.9MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  49%|████▉     | 2.09G/4.27G [02:03<02:38, 13.8MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  49%|████▉     | 2.09G/4.27G [02:03<02:10, 16.7MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  49%|████▉     | 2.09G/4.27G [02:03<02:01, 17.8MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  49%|████▉     | 2.09G/4.27G [02:03<02:00, 18.1MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  49%|████▉     | 2.09G/4.27G [02:03<02:03, 17.6MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  49%|████▉     | 2.10G/4.27G [02:03<01:46, 20.4MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  49%|████▉     | 2.10G/4.27G [02:03<01:44, 20.8MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  49%|████▉     | 2.10G/4.27G [02:03<01:47, 20.1MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  49%|████▉     | 2.10G/4.27G [02:03<01:41, 21.3MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  49%|████▉     | 2.11G/4.27G [02:04<01:45, 20.5MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  49%|████▉     | 2.11G/4.27G [02:04<02:53, 12.4MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  50%|████▉     | 2.11G/4.27G [02:04<02:14, 16.0MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  50%|████▉     | 2.11G/4.27G [02:04<02:18, 15.6MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  50%|████▉     | 2.12G/4.27G [02:05<03:30, 10.2MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  50%|████▉     | 2.12G/4.27G [02:05<02:34, 13.9MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  50%|████▉     | 2.12G/4.27G [02:05<02:14, 16.0MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  50%|████▉     | 2.12G/4.27G [02:05<01:59, 17.9MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  50%|████▉     | 2.13G/4.27G [02:05<01:50, 19.4MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  50%|████▉     | 2.13G/4.27G [02:05<01:37, 21.8MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  50%|████▉     | 2.13G/4.27G [02:05<01:33, 22.7MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  50%|█████     | 2.13G/4.27G [02:05<01:40, 21.3MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  50%|█████     | 2.14G/4.27G [02:06<02:22, 14.9MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  50%|█████     | 2.14G/4.27G [02:06<02:07, 16.7MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  50%|█████     | 2.14G/4.27G [02:06<02:57, 11.9MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  50%|█████     | 2.14G/4.27G [02:06<02:16, 15.6MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  50%|█████     | 2.15G/4.27G [02:06<02:15, 15.6MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  50%|█████     | 2.15G/4.27G [02:06<02:51, 12.3MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  50%|█████     | 2.15G/4.27G [02:07<02:33, 13.7MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  50%|█████     | 2.15G/4.27G [02:07<02:09, 16.3MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  51%|█████     | 2.15G/4.27G [02:07<02:23, 14.7MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  51%|█████     | 2.16G/4.27G [02:07<02:10, 16.2MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  51%|█████     | 2.16G/4.27G [02:07<02:27, 14.3MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  51%|█████     | 2.16G/4.27G [02:07<01:58, 17.7MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  51%|█████     | 2.16G/4.27G [02:07<02:08, 16.4MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  51%|█████     | 2.17G/4.27G [02:07<01:31, 23.0MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  51%|█████     | 2.17G/4.27G [02:08<01:32, 22.6MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  51%|█████     | 2.17G/4.27G [02:08<01:28, 23.7MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  51%|█████     | 2.18G/4.27G [02:08<01:28, 23.6MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  51%|█████     | 2.18G/4.27G [02:08<02:03, 16.9MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  51%|█████     | 2.18G/4.27G [02:08<01:30, 23.0MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  51%|█████▏    | 2.19G/4.27G [02:08<01:24, 24.6MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  51%|█████▏    | 2.19G/4.27G [02:08<01:24, 24.6MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  51%|█████▏    | 2.19G/4.27G [02:08<01:18, 26.4MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  51%|█████▏    | 2.20G/4.27G [02:09<01:29, 23.1MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  52%|█████▏    | 2.20G/4.27G [02:09<01:15, 27.2MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  52%|█████▏    | 2.20G/4.27G [02:09<01:13, 27.9MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  52%|█████▏    | 2.21G/4.27G [02:09<01:16, 26.8MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  52%|█████▏    | 2.21G/4.27G [02:09<01:36, 21.3MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  52%|█████▏    | 2.21G/4.27G [02:09<01:28, 23.1MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  52%|█████▏    | 2.21G/4.27G [02:10<02:09, 15.8MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  52%|█████▏    | 2.22G/4.27G [02:10<02:00, 17.0MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  52%|█████▏    | 2.22G/4.27G [02:10<01:53, 18.0MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  52%|█████▏    | 2.22G/4.27G [02:10<01:48, 18.9MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  52%|█████▏    | 2.22G/4.27G [02:10<03:01, 11.3MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  52%|█████▏    | 2.22G/4.27G [02:10<02:41, 12.6MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  52%|█████▏    | 2.23G/4.27G [02:11<03:16, 10.4MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  52%|█████▏    | 2.23G/4.27G [02:11<02:18, 14.7MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  52%|█████▏    | 2.23G/4.27G [02:11<03:00, 11.3MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  52%|█████▏    | 2.23G/4.27G [02:11<02:12, 15.4MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  52%|█████▏    | 2.24G/4.27G [02:11<02:09, 15.7MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  53%|█████▎    | 2.24G/4.27G [02:11<01:49, 18.6MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  53%|█████▎    | 2.24G/4.27G [02:11<01:44, 19.4MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  53%|█████▎    | 2.24G/4.27G [02:12<02:42, 12.4MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  53%|█████▎    | 2.25G/4.27G [02:12<02:59, 11.3MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  53%|█████▎    | 2.25G/4.27G [02:12<02:34, 13.1MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  53%|█████▎    | 2.25G/4.27G [02:12<02:10, 15.5MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  53%|█████▎    | 2.25G/4.27G [02:12<01:46, 18.8MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  53%|█████▎    | 2.26G/4.27G [02:12<01:45, 19.0MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  53%|█████▎    | 2.26G/4.27G [02:12<01:30, 22.2MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  53%|█████▎    | 2.26G/4.27G [02:13<01:30, 22.2MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  53%|█████▎    | 2.26G/4.27G [02:13<01:54, 17.5MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  53%|█████▎    | 2.27G/4.27G [02:13<01:49, 18.3MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  53%|█████▎    | 2.27G/4.27G [02:13<02:15, 14.7MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  53%|█████▎    | 2.27G/4.27G [02:13<01:52, 17.7MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  53%|█████▎    | 2.27G/4.27G [02:14<02:31, 13.2MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  53%|█████▎    | 2.28G/4.27G [02:14<01:56, 17.1MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  53%|█████▎    | 2.28G/4.27G [02:14<01:46, 18.6MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  53%|█████▎    | 2.28G/4.27G [02:14<01:45, 18.8MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  54%|█████▎    | 2.28G/4.27G [02:14<02:19, 14.2MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  54%|█████▎    | 2.29G/4.27G [02:14<02:01, 16.2MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  54%|█████▎    | 2.29G/4.27G [02:14<01:53, 17.4MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  54%|█████▎    | 2.29G/4.27G [02:14<01:56, 16.9MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  54%|█████▍    | 2.29G/4.27G [02:15<01:31, 21.6MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  54%|█████▍    | 2.30G/4.27G [02:15<01:42, 19.1MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  54%|█████▍    | 2.30G/4.27G [02:15<01:19, 24.6MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  54%|█████▍    | 2.30G/4.27G [02:15<01:18, 25.1MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  54%|█████▍    | 2.31G/4.27G [02:15<01:21, 24.0MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  54%|█████▍    | 2.31G/4.27G [02:15<01:27, 22.4MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  54%|█████▍    | 2.31G/4.27G [02:15<01:21, 24.1MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  54%|█████▍    | 2.32G/4.27G [02:15<01:11, 27.2MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  54%|█████▍    | 2.32G/4.27G [02:15<01:06, 29.3MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  54%|█████▍    | 2.32G/4.27G [02:16<01:08, 28.2MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  55%|█████▍    | 2.33G/4.27G [02:16<01:19, 24.4MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  55%|█████▍    | 2.33G/4.27G [02:16<01:16, 25.2MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  55%|█████▍    | 2.33G/4.27G [02:16<01:11, 27.1MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  55%|█████▍    | 2.33G/4.27G [02:16<01:22, 23.4MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  55%|█████▍    | 2.34G/4.27G [02:16<02:05, 15.3MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  55%|█████▍    | 2.34G/4.27G [02:17<01:44, 18.5MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  55%|█████▍    | 2.34G/4.27G [02:17<02:00, 16.0MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  55%|█████▍    | 2.34G/4.27G [02:17<01:55, 16.6MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  55%|█████▌    | 2.35G/4.27G [02:17<02:23, 13.3MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  55%|█████▌    | 2.35G/4.27G [02:17<01:54, 16.7MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  55%|█████▌    | 2.35G/4.27G [02:17<01:57, 16.3MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  55%|█████▌    | 2.36G/4.27G [02:17<01:35, 20.1MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  55%|█████▌    | 2.36G/4.27G [02:18<01:31, 20.8MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  55%|█████▌    | 2.36G/4.27G [02:18<01:33, 20.3MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  55%|█████▌    | 2.36G/4.27G [02:18<01:22, 23.0MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  55%|█████▌    | 2.37G/4.27G [02:18<01:28, 21.5MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  56%|█████▌    | 2.37G/4.27G [02:18<01:26, 22.1MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  56%|█████▌    | 2.37G/4.27G [02:18<01:16, 24.9MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  56%|█████▌    | 2.37G/4.27G [02:18<01:08, 27.4MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  56%|█████▌    | 2.38G/4.27G [02:18<01:13, 25.6MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  56%|█████▌    | 2.38G/4.27G [02:18<01:18, 23.9MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  56%|█████▌    | 2.38G/4.27G [02:19<01:20, 23.3MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  56%|█████▌    | 2.38G/4.27G [02:19<01:43, 18.3MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  56%|█████▌    | 2.39G/4.27G [02:19<01:25, 22.0MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  56%|█████▌    | 2.39G/4.27G [02:19<01:30, 20.8MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  56%|█████▌    | 2.39G/4.27G [02:19<01:20, 23.3MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  56%|█████▌    | 2.40G/4.27G [02:19<01:11, 26.3MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  56%|█████▋    | 2.40G/4.27G [02:19<01:07, 27.7MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  56%|█████▋    | 2.40G/4.27G [02:19<01:06, 28.1MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  56%|█████▋    | 2.41G/4.27G [02:20<01:05, 28.3MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  56%|█████▋    | 2.41G/4.27G [02:20<01:49, 16.9MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  57%|█████▋    | 2.41G/4.27G [02:20<01:34, 19.6MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  57%|█████▋    | 2.41G/4.27G [02:20<02:06, 14.7MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  57%|█████▋    | 2.42G/4.27G [02:21<02:39, 11.6MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  57%|█████▋    | 2.42G/4.27G [02:21<02:05, 14.7MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  57%|█████▋    | 2.42G/4.27G [02:21<01:59, 15.5MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  57%|█████▋    | 2.42G/4.27G [02:21<01:51, 16.5MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  57%|█████▋    | 2.43G/4.27G [02:21<01:39, 18.6MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  57%|█████▋    | 2.43G/4.27G [02:21<01:42, 17.9MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  57%|█████▋    | 2.43G/4.27G [02:21<01:29, 20.5MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  57%|█████▋    | 2.44G/4.27G [02:21<01:17, 23.7MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  57%|█████▋    | 2.44G/4.27G [02:21<01:23, 21.9MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  57%|█████▋    | 2.44G/4.27G [02:22<01:48, 16.8MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  57%|█████▋    | 2.44G/4.27G [02:22<01:52, 16.2MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  57%|█████▋    | 2.44G/4.27G [02:22<02:40, 11.4MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  57%|█████▋    | 2.45G/4.27G [02:22<02:36, 11.6MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  57%|█████▋    | 2.45G/4.27G [02:22<03:10, 9.57MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  57%|█████▋    | 2.45G/4.27G [02:23<02:22, 12.7MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  57%|█████▋    | 2.45G/4.27G [02:23<02:44, 11.0MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  58%|█████▊    | 2.45G/4.27G [02:23<02:07, 14.2MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  58%|█████▊    | 2.46G/4.27G [02:23<03:03, 9.86MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  58%|█████▊    | 2.46G/4.27G [02:23<02:26, 12.4MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  58%|█████▊    | 2.46G/4.27G [02:24<04:27, 6.75MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  58%|█████▊    | 2.46G/4.27G [02:24<04:55, 6.10MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  58%|█████▊    | 2.46G/4.27G [02:24<03:22, 8.89MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  58%|█████▊    | 2.47G/4.27G [02:25<03:50, 7.82MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  58%|█████▊    | 2.47G/4.27G [02:25<02:48, 10.7MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  58%|█████▊    | 2.47G/4.27G [02:25<02:44, 10.9MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  58%|█████▊    | 2.47G/4.27G [02:25<02:38, 11.3MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  58%|█████▊    | 2.47G/4.27G [02:25<02:26, 12.2MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  58%|█████▊    | 2.47G/4.27G [02:25<02:29, 12.0MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  58%|█████▊    | 2.48G/4.27G [02:25<02:24, 12.3MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  58%|█████▊    | 2.48G/4.27G [02:25<02:20, 12.7MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  58%|█████▊    | 2.48G/4.27G [02:25<02:17, 13.0MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  58%|█████▊    | 2.48G/4.27G [02:26<02:13, 13.3MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  58%|█████▊    | 2.48G/4.27G [02:26<02:34, 11.5MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  58%|█████▊    | 2.48G/4.27G [02:26<02:06, 14.1MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  58%|█████▊    | 2.49G/4.27G [02:26<02:02, 14.5MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  58%|█████▊    | 2.49G/4.27G [02:26<02:03, 14.4MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  58%|█████▊    | 2.49G/4.27G [02:26<01:46, 16.7MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  58%|█████▊    | 2.49G/4.27G [02:27<04:18, 6.88MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  58%|█████▊    | 2.49G/4.27G [02:27<03:10, 9.28MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  59%|█████▊    | 2.50G/4.27G [02:27<02:41, 10.9MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  59%|█████▊    | 2.50G/4.27G [02:27<02:23, 12.4MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  59%|█████▊    | 2.50G/4.27G [02:27<02:04, 14.1MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  59%|█████▊    | 2.50G/4.27G [02:27<01:52, 15.6MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  59%|█████▊    | 2.50G/4.27G [02:27<01:42, 17.2MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  59%|█████▊    | 2.51G/4.27G [02:28<02:03, 14.2MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  59%|█████▉    | 2.51G/4.27G [02:28<01:57, 15.0MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  59%|█████▉    | 2.51G/4.27G [02:28<01:40, 17.5MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  59%|█████▉    | 2.51G/4.27G [02:28<01:34, 18.7MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  59%|█████▉    | 2.51G/4.27G [02:28<01:28, 19.8MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  59%|█████▉    | 2.52G/4.27G [02:28<01:20, 21.7MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  59%|█████▉    | 2.52G/4.27G [02:28<01:19, 21.9MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  59%|█████▉    | 2.52G/4.27G [02:28<01:38, 17.7MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  59%|█████▉    | 2.53G/4.27G [02:28<01:15, 23.2MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  59%|█████▉    | 2.53G/4.27G [02:29<01:12, 24.0MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  59%|█████▉    | 2.53G/4.27G [02:29<01:09, 25.0MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  59%|█████▉    | 2.53G/4.27G [02:29<01:08, 25.3MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  59%|█████▉    | 2.54G/4.27G [02:29<01:06, 25.9MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  60%|█████▉    | 2.54G/4.27G [02:29<01:06, 26.1MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  60%|█████▉    | 2.54G/4.27G [02:29<01:21, 21.1MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  60%|█████▉    | 2.55G/4.27G [02:29<01:29, 19.3MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  60%|█████▉    | 2.55G/4.27G [02:29<01:13, 23.5MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  60%|█████▉    | 2.55G/4.27G [02:30<01:13, 23.4MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  60%|█████▉    | 2.56G/4.27G [02:30<01:06, 25.5MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  60%|█████▉    | 2.56G/4.27G [02:30<01:02, 27.4MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  60%|██████    | 2.56G/4.27G [02:30<00:59, 28.5MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  60%|██████    | 2.57G/4.27G [02:30<00:58, 28.9MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  60%|██████    | 2.57G/4.27G [02:30<00:55, 30.5MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  60%|██████    | 2.57G/4.27G [02:30<00:55, 30.6MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  60%|██████    | 2.58G/4.27G [02:30<00:54, 30.8MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  60%|██████    | 2.58G/4.27G [02:30<00:53, 31.8MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  61%|██████    | 2.58G/4.27G [02:31<00:51, 32.7MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  61%|██████    | 2.59G/4.27G [02:31<00:51, 32.7MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  61%|██████    | 2.59G/4.27G [02:31<00:50, 33.3MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  61%|██████    | 2.59G/4.27G [02:31<00:54, 30.8MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  61%|██████    | 2.60G/4.27G [02:31<00:52, 31.8MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  61%|██████    | 2.60G/4.27G [02:31<00:50, 32.8MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  61%|██████    | 2.60G/4.27G [02:31<00:50, 33.1MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  61%|██████    | 2.61G/4.27G [02:31<00:49, 33.3MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  61%|██████    | 2.61G/4.27G [02:31<00:49, 33.3MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  61%|██████▏   | 2.61G/4.27G [02:31<00:48, 33.7MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  61%|██████▏   | 2.62G/4.27G [02:32<00:48, 34.0MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  61%|██████▏   | 2.62G/4.27G [02:32<00:53, 30.8MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  61%|██████▏   | 2.62G/4.27G [02:32<01:03, 25.9MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  62%|██████▏   | 2.63G/4.27G [02:32<01:19, 20.6MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  62%|██████▏   | 2.63G/4.27G [02:32<01:05, 25.1MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  62%|██████▏   | 2.63G/4.27G [02:32<01:00, 27.0MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  62%|██████▏   | 2.64G/4.27G [02:32<00:57, 28.1MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  62%|██████▏   | 2.64G/4.27G [02:32<00:53, 30.2MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  62%|██████▏   | 2.64G/4.27G [02:33<01:01, 26.3MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  62%|██████▏   | 2.65G/4.27G [02:33<00:59, 27.4MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  62%|██████▏   | 2.65G/4.27G [02:33<01:09, 23.3MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  62%|██████▏   | 2.65G/4.27G [02:33<00:58, 27.4MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  62%|██████▏   | 2.66G/4.27G [02:33<00:58, 27.3MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  62%|██████▏   | 2.66G/4.27G [02:33<00:55, 29.1MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  62%|██████▏   | 2.66G/4.27G [02:33<00:53, 29.9MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  63%|██████▎   | 2.67G/4.27G [02:33<00:55, 29.0MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  63%|██████▎   | 2.67G/4.27G [02:34<00:56, 28.1MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  63%|██████▎   | 2.67G/4.27G [02:34<00:53, 29.5MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  63%|██████▎   | 2.68G/4.27G [02:34<00:52, 30.1MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  63%|██████▎   | 2.68G/4.27G [02:34<00:51, 30.5MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  63%|██████▎   | 2.68G/4.27G [02:34<00:52, 30.4MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  63%|██████▎   | 2.68G/4.27G [02:34<00:53, 29.6MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  63%|██████▎   | 2.69G/4.27G [02:34<00:52, 30.1MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  63%|██████▎   | 2.69G/4.27G [02:34<00:52, 29.9MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  63%|██████▎   | 2.69G/4.27G [02:34<01:09, 22.5MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  63%|██████▎   | 2.70G/4.27G [02:35<01:03, 24.8MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  63%|██████▎   | 2.70G/4.27G [02:35<01:10, 22.1MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  63%|██████▎   | 2.70G/4.27G [02:35<01:37, 16.0MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  63%|██████▎   | 2.71G/4.27G [02:35<01:26, 18.0MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  63%|██████▎   | 2.71G/4.27G [02:35<01:33, 16.7MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  64%|██████▎   | 2.71G/4.27G [02:35<01:37, 16.0MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  64%|██████▎   | 2.71G/4.27G [02:36<01:44, 14.9MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  64%|██████▎   | 2.71G/4.27G [02:36<01:36, 16.1MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  64%|██████▎   | 2.72G/4.27G [02:36<01:29, 17.4MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  64%|██████▎   | 2.72G/4.27G [02:36<01:26, 17.8MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  64%|██████▍   | 2.72G/4.27G [02:36<01:24, 18.4MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  64%|██████▍   | 2.72G/4.27G [02:36<01:40, 15.4MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  64%|██████▍   | 2.72G/4.27G [02:36<01:27, 17.6MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  64%|██████▍   | 2.73G/4.27G [02:36<01:34, 16.2MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  64%|██████▍   | 2.73G/4.27G [02:36<01:23, 18.4MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  64%|██████▍   | 2.73G/4.27G [02:37<03:24, 7.50MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  64%|██████▍   | 2.73G/4.27G [02:37<02:30, 10.2MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  64%|██████▍   | 2.73G/4.27G [02:37<02:30, 10.2MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  64%|██████▍   | 2.74G/4.27G [02:38<02:18, 11.0MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  64%|██████▍   | 2.74G/4.27G [02:38<02:09, 11.8MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  64%|██████▍   | 2.74G/4.27G [02:38<02:10, 11.7MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  64%|██████▍   | 2.74G/4.27G [02:38<02:14, 11.3MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  64%|██████▍   | 2.74G/4.27G [02:38<01:53, 13.4MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  64%|██████▍   | 2.74G/4.27G [02:38<02:02, 12.4MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  64%|██████▍   | 2.75G/4.27G [02:38<01:43, 14.6MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  64%|██████▍   | 2.75G/4.27G [02:38<01:44, 14.5MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  64%|██████▍   | 2.75G/4.27G [02:39<01:37, 15.5MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  65%|██████▍   | 2.75G/4.27G [02:39<01:50, 13.7MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  65%|██████▍   | 2.75G/4.27G [02:39<01:27, 17.3MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  65%|██████▍   | 2.76G/4.27G [02:39<01:28, 17.1MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  65%|██████▍   | 2.76G/4.27G [02:39<01:28, 17.0MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  65%|██████▍   | 2.76G/4.27G [02:39<01:28, 17.1MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  65%|██████▍   | 2.76G/4.27G [02:39<01:28, 17.0MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  65%|██████▍   | 2.76G/4.27G [02:39<01:23, 17.9MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  65%|██████▍   | 2.77G/4.27G [02:39<01:21, 18.4MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  65%|██████▍   | 2.77G/4.27G [02:39<01:20, 18.7MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  65%|██████▍   | 2.77G/4.27G [02:40<01:17, 19.2MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  65%|██████▍   | 2.77G/4.27G [02:40<01:20, 18.5MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  65%|██████▌   | 2.77G/4.27G [02:40<01:21, 18.4MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  65%|██████▌   | 2.78G/4.27G [02:40<01:19, 18.7MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  65%|██████▌   | 2.78G/4.27G [02:40<01:22, 18.1MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  65%|██████▌   | 2.78G/4.27G [02:40<01:11, 20.8MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  65%|██████▌   | 2.78G/4.27G [02:40<01:15, 19.6MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  65%|██████▌   | 2.78G/4.27G [02:40<01:11, 20.7MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  65%|██████▌   | 2.79G/4.27G [02:40<01:12, 20.5MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  65%|██████▌   | 2.79G/4.27G [02:41<01:02, 23.5MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  65%|██████▌   | 2.79G/4.27G [02:41<01:02, 23.7MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  66%|██████▌   | 2.80G/4.27G [02:41<01:00, 24.2MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  66%|██████▌   | 2.80G/4.27G [02:41<00:57, 25.7MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  66%|██████▌   | 2.80G/4.27G [02:41<00:57, 25.5MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  66%|██████▌   | 2.80G/4.27G [02:41<00:56, 25.7MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  66%|██████▌   | 2.81G/4.27G [02:41<00:55, 26.5MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  66%|██████▌   | 2.81G/4.27G [02:41<00:53, 27.2MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  66%|██████▌   | 2.81G/4.27G [02:41<00:51, 28.1MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  66%|██████▌   | 2.82G/4.27G [02:41<00:51, 28.0MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  66%|██████▌   | 2.82G/4.27G [02:42<01:29, 16.1MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  66%|██████▌   | 2.82G/4.27G [02:42<02:01, 11.9MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  66%|██████▌   | 2.82G/4.27G [02:42<01:35, 15.1MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  66%|██████▌   | 2.83G/4.27G [02:43<02:09, 11.1MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  66%|██████▋   | 2.83G/4.27G [02:43<01:54, 12.6MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  66%|██████▋   | 2.83G/4.27G [02:43<02:00, 11.9MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  66%|██████▋   | 2.83G/4.27G [02:43<01:33, 15.4MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  66%|██████▋   | 2.83G/4.27G [02:43<01:25, 16.8MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  67%|██████▋   | 2.84G/4.27G [02:43<01:22, 17.2MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  67%|██████▋   | 2.84G/4.27G [02:43<01:07, 21.2MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  67%|██████▋   | 2.84G/4.27G [02:44<01:28, 16.1MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  67%|██████▋   | 2.85G/4.27G [02:44<01:07, 20.9MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  67%|██████▋   | 2.85G/4.27G [02:44<01:05, 21.6MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  67%|██████▋   | 2.85G/4.27G [02:44<01:02, 22.5MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  67%|██████▋   | 2.85G/4.27G [02:44<01:23, 17.0MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  67%|██████▋   | 2.86G/4.27G [02:44<01:11, 19.7MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  67%|██████▋   | 2.86G/4.27G [02:44<01:11, 19.7MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  67%|██████▋   | 2.86G/4.27G [02:44<00:58, 24.0MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  67%|██████▋   | 2.87G/4.27G [02:45<00:56, 24.6MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  67%|██████▋   | 2.87G/4.27G [02:45<00:49, 28.4MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  67%|██████▋   | 2.87G/4.27G [02:45<00:46, 29.9MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  67%|██████▋   | 2.88G/4.27G [02:45<00:56, 24.5MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  68%|██████▊   | 2.88G/4.27G [02:45<00:51, 26.9MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  68%|██████▊   | 2.88G/4.27G [02:45<00:56, 24.6MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  68%|██████▊   | 2.89G/4.27G [02:45<00:56, 24.4MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  68%|██████▊   | 2.89G/4.27G [02:45<00:53, 25.9MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  68%|██████▊   | 2.89G/4.27G [02:46<01:00, 22.6MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  68%|██████▊   | 2.89G/4.27G [02:46<00:58, 23.5MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  68%|██████▊   | 2.90G/4.27G [02:46<00:58, 23.4MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  68%|██████▊   | 2.90G/4.27G [02:46<00:53, 25.6MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  68%|██████▊   | 2.90G/4.27G [02:46<01:01, 22.2MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  68%|██████▊   | 2.91G/4.27G [02:46<00:52, 25.8MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  68%|██████▊   | 2.91G/4.27G [02:46<01:05, 20.6MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  68%|██████▊   | 2.91G/4.27G [02:47<01:27, 15.5MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  68%|██████▊   | 2.91G/4.27G [02:47<01:07, 20.0MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  68%|██████▊   | 2.92G/4.27G [02:47<01:06, 20.3MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  68%|██████▊   | 2.92G/4.27G [02:47<00:58, 23.0MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  69%|██████▊   | 2.92G/4.27G [02:47<00:56, 23.6MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  69%|██████▊   | 2.93G/4.27G [02:47<00:48, 27.8MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  69%|██████▊   | 2.93G/4.27G [02:47<00:50, 26.5MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  69%|██████▉   | 2.93G/4.27G [02:47<00:49, 26.7MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  69%|██████▉   | 2.94G/4.27G [02:47<00:46, 28.5MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  69%|██████▉   | 2.94G/4.27G [02:48<00:52, 25.4MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  69%|██████▉   | 2.94G/4.27G [02:48<00:44, 29.6MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  69%|██████▉   | 2.95G/4.27G [02:48<00:42, 31.1MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  69%|██████▉   | 2.95G/4.27G [02:48<00:41, 31.7MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  69%|██████▉   | 2.95G/4.27G [02:48<00:40, 32.1MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  69%|██████▉   | 2.96G/4.27G [02:48<00:37, 34.7MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  69%|██████▉   | 2.96G/4.27G [02:48<00:38, 34.0MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  70%|██████▉   | 2.97G/4.27G [02:48<00:37, 34.2MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  70%|██████▉   | 2.97G/4.27G [02:48<00:36, 36.0MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  70%|██████▉   | 2.97G/4.27G [02:49<00:35, 36.5MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  70%|██████▉   | 2.98G/4.27G [02:49<00:35, 36.6MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  70%|██████▉   | 2.98G/4.27G [02:49<00:35, 36.6MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  70%|██████▉   | 2.98G/4.27G [02:49<00:36, 35.5MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  70%|███████   | 2.99G/4.27G [02:49<00:39, 32.1MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  70%|███████   | 2.99G/4.27G [02:49<00:40, 31.7MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  70%|███████   | 2.99G/4.27G [02:49<00:39, 32.4MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  70%|███████   | 3.00G/4.27G [02:49<00:41, 30.8MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  70%|███████   | 3.00G/4.27G [02:49<00:37, 33.4MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  70%|███████   | 3.01G/4.27G [02:49<00:36, 34.3MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  71%|███████   | 3.01G/4.27G [02:50<00:34, 36.5MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  71%|███████   | 3.01G/4.27G [02:50<00:37, 33.1MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  71%|███████   | 3.02G/4.27G [02:50<00:37, 33.2MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  71%|███████   | 3.02G/4.27G [02:50<00:40, 31.0MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  71%|███████   | 3.02G/4.27G [02:50<00:40, 30.7MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  71%|███████   | 3.03G/4.27G [02:50<00:39, 31.6MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  71%|███████   | 3.03G/4.27G [02:50<00:41, 29.9MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  71%|███████   | 3.03G/4.27G [02:50<00:37, 32.6MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  71%|███████   | 3.04G/4.27G [02:50<00:36, 33.6MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  71%|███████▏  | 3.04G/4.27G [02:51<00:35, 34.8MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  71%|███████▏  | 3.05G/4.27G [02:51<00:33, 36.8MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  72%|███████▏  | 3.05G/4.27G [02:51<00:31, 38.1MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  72%|███████▏  | 3.05G/4.27G [02:51<00:32, 37.6MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  72%|███████▏  | 3.06G/4.27G [02:51<00:35, 34.0MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  72%|███████▏  | 3.06G/4.27G [02:51<00:40, 29.9MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  72%|███████▏  | 3.07G/4.27G [02:51<00:36, 33.3MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  72%|███████▏  | 3.07G/4.27G [02:51<00:35, 34.0MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  72%|███████▏  | 3.07G/4.27G [02:51<00:34, 35.0MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  72%|███████▏  | 3.08G/4.27G [02:52<00:36, 32.5MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  72%|███████▏  | 3.08G/4.27G [02:52<00:33, 35.1MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  72%|███████▏  | 3.08G/4.27G [02:52<00:32, 35.9MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  72%|███████▏  | 3.09G/4.27G [02:52<00:33, 35.0MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  72%|███████▏  | 3.09G/4.27G [02:52<00:45, 26.0MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  73%|███████▎  | 3.09G/4.27G [02:52<00:44, 26.1MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  73%|███████▎  | 3.10G/4.27G [02:52<00:44, 26.5MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  73%|███████▎  | 3.10G/4.27G [02:52<00:46, 25.3MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  73%|███████▎  | 3.10G/4.27G [02:53<00:42, 27.6MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  73%|███████▎  | 3.11G/4.27G [02:53<00:40, 28.4MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  73%|███████▎  | 3.11G/4.27G [02:53<00:46, 24.9MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  73%|███████▎  | 3.11G/4.27G [02:53<00:41, 27.9MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  73%|███████▎  | 3.12G/4.27G [02:53<00:37, 30.3MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  73%|███████▎  | 3.12G/4.27G [02:53<00:35, 31.8MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  73%|███████▎  | 3.12G/4.27G [02:53<00:57, 20.0MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  73%|███████▎  | 3.13G/4.27G [02:54<00:53, 21.4MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  73%|███████▎  | 3.13G/4.27G [02:54<00:52, 21.5MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  73%|███████▎  | 3.13G/4.27G [02:54<01:04, 17.7MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  73%|███████▎  | 3.13G/4.27G [02:54<00:57, 19.7MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  74%|███████▎  | 3.14G/4.27G [02:54<00:47, 23.9MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  74%|███████▎  | 3.14G/4.27G [02:54<00:49, 22.5MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  74%|███████▎  | 3.15G/4.27G [02:54<00:43, 25.6MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  74%|███████▍  | 3.15G/4.27G [02:55<00:54, 20.6MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  74%|███████▍  | 3.15G/4.27G [02:55<00:52, 21.1MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  74%|███████▍  | 3.15G/4.27G [02:55<01:05, 17.0MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  74%|███████▍  | 3.15G/4.27G [02:55<01:19, 14.0MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  74%|███████▍  | 3.16G/4.27G [02:55<00:59, 18.6MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  74%|███████▍  | 3.16G/4.27G [02:55<01:01, 17.9MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  74%|███████▍  | 3.16G/4.27G [02:55<01:04, 17.2MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  74%|███████▍  | 3.17G/4.27G [02:56<00:55, 19.9MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  74%|███████▍  | 3.17G/4.27G [02:56<00:42, 26.0MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  74%|███████▍  | 3.17G/4.27G [02:56<00:39, 27.4MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  75%|███████▍  | 3.18G/4.27G [02:56<00:36, 29.6MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  75%|███████▍  | 3.18G/4.27G [02:56<00:35, 30.7MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  75%|███████▍  | 3.18G/4.27G [02:56<00:33, 32.0MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  75%|███████▍  | 3.19G/4.27G [02:56<00:33, 32.6MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  75%|███████▍  | 3.19G/4.27G [02:56<00:31, 33.6MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  75%|███████▍  | 3.20G/4.27G [02:56<00:31, 33.5MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  75%|███████▌  | 3.20G/4.27G [02:57<00:30, 35.5MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  75%|███████▌  | 3.20G/4.27G [02:57<00:57, 18.5MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  75%|███████▌  | 3.21G/4.27G [02:57<01:13, 14.5MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  75%|███████▌  | 3.21G/4.27G [02:57<01:01, 17.2MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  75%|███████▌  | 3.21G/4.27G [02:58<01:27, 12.1MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  75%|███████▌  | 3.21G/4.27G [02:58<01:50, 9.54MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  75%|███████▌  | 3.22G/4.27G [02:58<01:32, 11.4MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  75%|███████▌  | 3.22G/4.27G [02:59<02:08, 8.15MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  75%|███████▌  | 3.22G/4.27G [02:59<01:45, 9.93MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  76%|███████▌  | 3.22G/4.27G [02:59<01:35, 10.9MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  76%|███████▌  | 3.22G/4.27G [02:59<01:30, 11.6MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  76%|███████▌  | 3.22G/4.27G [02:59<01:26, 12.0MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  76%|███████▌  | 3.23G/4.27G [02:59<01:19, 13.1MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  76%|███████▌  | 3.23G/4.27G [02:59<01:09, 14.8MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  76%|███████▌  | 3.23G/4.27G [02:59<01:04, 15.9MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  76%|███████▌  | 3.23G/4.27G [02:59<01:02, 16.5MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  76%|███████▌  | 3.23G/4.27G [03:00<01:01, 16.8MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  76%|███████▌  | 3.24G/4.27G [03:00<01:02, 16.5MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  76%|███████▌  | 3.24G/4.27G [03:00<01:06, 15.5MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  76%|███████▌  | 3.24G/4.27G [03:00<01:58, 8.69MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  76%|███████▌  | 3.24G/4.27G [03:00<01:44, 9.75MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  76%|███████▌  | 3.24G/4.27G [03:01<01:27, 11.7MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  76%|███████▌  | 3.25G/4.27G [03:01<01:14, 13.7MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  76%|███████▌  | 3.25G/4.27G [03:01<01:05, 15.6MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  76%|███████▌  | 3.25G/4.27G [03:01<01:02, 16.2MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  76%|███████▋  | 3.25G/4.27G [03:01<00:54, 18.7MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  76%|███████▋  | 3.25G/4.27G [03:01<00:58, 17.2MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  76%|███████▋  | 3.26G/4.27G [03:01<00:56, 17.7MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  76%|███████▋  | 3.26G/4.27G [03:01<01:02, 16.1MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  76%|███████▋  | 3.26G/4.27G [03:01<00:47, 21.3MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  77%|███████▋  | 3.26G/4.27G [03:02<00:50, 20.0MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  77%|███████▋  | 3.27G/4.27G [03:02<00:49, 20.3MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  77%|███████▋  | 3.27G/4.27G [03:02<01:15, 13.2MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  77%|███████▋  | 3.27G/4.27G [03:02<00:57, 17.1MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  77%|███████▋  | 3.27G/4.27G [03:02<01:36, 10.2MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  77%|███████▋  | 3.28G/4.27G [03:03<01:33, 10.6MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  77%|███████▋  | 3.28G/4.27G [03:03<01:10, 13.9MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  77%|███████▋  | 3.28G/4.27G [03:03<01:16, 12.9MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  77%|███████▋  | 3.28G/4.27G [03:03<01:46, 9.20MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  77%|███████▋  | 3.28G/4.27G [03:03<01:30, 10.8MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  77%|███████▋  | 3.29G/4.27G [03:04<02:04, 7.85MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  77%|███████▋  | 3.29G/4.27G [03:04<02:49, 5.76MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  77%|███████▋  | 3.29G/4.27G [03:04<03:17, 4.95MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  77%|███████▋  | 3.29G/4.27G [03:05<02:12, 7.35MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  77%|███████▋  | 3.29G/4.27G [03:05<01:55, 8.39MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  77%|███████▋  | 3.29G/4.27G [03:05<04:01, 4.02MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  77%|███████▋  | 3.30G/4.27G [03:06<02:38, 6.11MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  77%|███████▋  | 3.30G/4.27G [03:06<02:22, 6.82MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  77%|███████▋  | 3.30G/4.27G [03:06<02:08, 7.53MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  77%|███████▋  | 3.30G/4.27G [03:06<01:35, 10.1MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  77%|███████▋  | 3.30G/4.27G [03:06<01:27, 11.1MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  77%|███████▋  | 3.30G/4.27G [03:06<01:20, 12.0MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  77%|███████▋  | 3.31G/4.27G [03:06<01:13, 13.1MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  78%|███████▊  | 3.31G/4.27G [03:07<02:16, 7.04MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  78%|███████▊  | 3.31G/4.27G [03:07<01:31, 10.5MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  78%|███████▊  | 3.31G/4.27G [03:07<01:33, 10.2MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  78%|███████▊  | 3.31G/4.27G [03:07<01:27, 10.9MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  78%|███████▊  | 3.31G/4.27G [03:07<01:52, 8.47MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  78%|███████▊  | 3.32G/4.27G [03:07<01:16, 12.3MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  78%|███████▊  | 3.32G/4.27G [03:08<01:24, 11.2MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  78%|███████▊  | 3.32G/4.27G [03:08<01:12, 12.9MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  78%|███████▊  | 3.32G/4.27G [03:08<01:17, 12.2MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  78%|███████▊  | 3.32G/4.27G [03:08<01:18, 12.0MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  78%|███████▊  | 3.33G/4.27G [03:08<01:20, 11.7MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  78%|███████▊  | 3.33G/4.27G [03:08<01:43, 9.02MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  78%|███████▊  | 3.33G/4.27G [03:09<01:26, 10.9MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  78%|███████▊  | 3.33G/4.27G [03:09<00:58, 15.9MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  78%|███████▊  | 3.33G/4.27G [03:09<01:01, 15.0MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  78%|███████▊  | 3.34G/4.27G [03:09<01:05, 14.1MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  78%|███████▊  | 3.34G/4.27G [03:09<00:52, 17.7MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  78%|███████▊  | 3.34G/4.27G [03:09<00:57, 16.1MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  78%|███████▊  | 3.34G/4.27G [03:10<01:34, 9.80MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  78%|███████▊  | 3.35G/4.27G [03:10<01:10, 13.1MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  78%|███████▊  | 3.35G/4.27G [03:10<01:52, 8.15MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  79%|███████▊  | 3.35G/4.27G [03:10<01:36, 9.46MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  79%|███████▊  | 3.35G/4.27G [03:11<01:59, 7.62MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  79%|███████▊  | 3.35G/4.27G [03:11<01:20, 11.4MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  79%|███████▊  | 3.36G/4.27G [03:11<01:20, 11.3MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  79%|███████▊  | 3.36G/4.27G [03:11<01:12, 12.5MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  79%|███████▉  | 3.36G/4.27G [03:11<01:09, 13.1MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  79%|███████▉  | 3.36G/4.27G [03:11<01:08, 13.2MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  79%|███████▉  | 3.36G/4.27G [03:11<01:10, 12.7MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  79%|███████▉  | 3.36G/4.27G [03:11<01:12, 12.4MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  79%|███████▉  | 3.37G/4.27G [03:12<01:47, 8.34MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  79%|███████▉  | 3.37G/4.27G [03:12<01:21, 11.0MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  79%|███████▉  | 3.37G/4.27G [03:12<01:15, 11.9MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  79%|███████▉  | 3.37G/4.27G [03:12<01:15, 11.9MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  79%|███████▉  | 3.37G/4.27G [03:12<01:13, 12.1MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  79%|███████▉  | 3.37G/4.27G [03:12<01:03, 14.0MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  79%|███████▉  | 3.38G/4.27G [03:12<00:59, 15.0MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  79%|███████▉  | 3.38G/4.27G [03:13<00:55, 15.9MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  79%|███████▉  | 3.38G/4.27G [03:13<00:54, 16.4MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  79%|███████▉  | 3.38G/4.27G [03:13<00:50, 17.5MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  79%|███████▉  | 3.38G/4.27G [03:13<00:48, 18.2MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  79%|███████▉  | 3.39G/4.27G [03:13<00:46, 19.0MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  79%|███████▉  | 3.39G/4.27G [03:13<00:44, 19.7MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  79%|███████▉  | 3.39G/4.27G [03:13<00:42, 20.8MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  80%|███████▉  | 3.39G/4.27G [03:13<00:40, 21.5MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  80%|███████▉  | 3.40G/4.27G [03:13<00:40, 21.4MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  80%|███████▉  | 3.40G/4.27G [03:13<00:38, 22.8MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  80%|███████▉  | 3.40G/4.27G [03:14<00:36, 24.0MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  80%|███████▉  | 3.40G/4.27G [03:14<00:35, 24.4MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  80%|███████▉  | 3.41G/4.27G [03:14<00:32, 26.6MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  80%|███████▉  | 3.41G/4.27G [03:14<00:42, 20.3MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  80%|████████  | 3.41G/4.27G [03:14<00:33, 25.8MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  80%|████████  | 3.42G/4.27G [03:14<00:32, 26.2MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  80%|████████  | 3.42G/4.27G [03:14<00:31, 27.0MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  80%|████████  | 3.42G/4.27G [03:14<00:29, 29.0MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  80%|████████  | 3.43G/4.27G [03:14<00:27, 30.0MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  80%|████████  | 3.43G/4.27G [03:15<00:28, 29.3MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  80%|████████  | 3.43G/4.27G [03:15<00:40, 20.3MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  81%|████████  | 3.44G/4.27G [03:15<00:34, 23.8MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  81%|████████  | 3.44G/4.27G [03:15<00:35, 23.1MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  81%|████████  | 3.44G/4.27G [03:15<00:37, 22.1MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  81%|████████  | 3.45G/4.27G [03:15<00:31, 26.3MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  81%|████████  | 3.45G/4.27G [03:15<00:30, 26.9MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  81%|████████  | 3.45G/4.27G [03:15<00:27, 29.9MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  81%|████████  | 3.46G/4.27G [03:16<00:26, 30.6MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  81%|████████  | 3.46G/4.27G [03:16<00:25, 31.3MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  81%|████████  | 3.46G/4.27G [03:16<00:26, 30.4MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  81%|████████  | 3.46G/4.27G [03:16<00:27, 28.6MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  81%|████████▏ | 3.47G/4.27G [03:16<00:28, 28.2MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  81%|████████▏ | 3.47G/4.27G [03:16<00:27, 28.9MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  81%|████████▏ | 3.47G/4.27G [03:16<00:28, 27.7MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  82%|████████▏ | 3.48G/4.27G [03:16<00:34, 22.8MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  82%|████████▏ | 3.48G/4.27G [03:17<00:34, 22.7MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  82%|████████▏ | 3.48G/4.27G [03:17<00:39, 19.9MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  82%|████████▏ | 3.48G/4.27G [03:17<00:35, 21.8MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  82%|████████▏ | 3.49G/4.27G [03:17<00:33, 23.2MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  82%|████████▏ | 3.49G/4.27G [03:17<00:30, 25.4MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  82%|████████▏ | 3.49G/4.27G [03:17<00:28, 27.5MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  82%|████████▏ | 3.50G/4.27G [03:17<00:26, 29.3MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  82%|████████▏ | 3.50G/4.27G [03:17<00:23, 32.0MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  82%|████████▏ | 3.50G/4.27G [03:17<00:24, 31.6MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  82%|████████▏ | 3.51G/4.27G [03:18<00:35, 21.1MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  82%|████████▏ | 3.51G/4.27G [03:18<00:32, 23.5MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  82%|████████▏ | 3.51G/4.27G [03:18<00:30, 24.3MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  82%|████████▏ | 3.52G/4.27G [03:18<00:34, 21.4MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  83%|████████▎ | 3.52G/4.27G [03:18<00:29, 25.2MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  83%|████████▎ | 3.52G/4.27G [03:18<00:35, 20.7MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  83%|████████▎ | 3.53G/4.27G [03:18<00:31, 23.2MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  83%|████████▎ | 3.53G/4.27G [03:19<00:41, 17.7MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  83%|████████▎ | 3.53G/4.27G [03:19<00:37, 19.6MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  83%|████████▎ | 3.53G/4.27G [03:19<00:44, 16.6MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  83%|████████▎ | 3.54G/4.27G [03:19<00:39, 18.6MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  83%|████████▎ | 3.54G/4.27G [03:19<00:40, 17.8MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  83%|████████▎ | 3.54G/4.27G [03:19<00:34, 20.7MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  83%|████████▎ | 3.54G/4.27G [03:19<00:32, 22.5MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  83%|████████▎ | 3.55G/4.27G [03:20<00:34, 20.9MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  83%|████████▎ | 3.55G/4.27G [03:20<00:29, 23.9MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  83%|████████▎ | 3.55G/4.27G [03:20<00:29, 24.0MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  83%|████████▎ | 3.56G/4.27G [03:20<00:31, 22.8MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  83%|████████▎ | 3.56G/4.27G [03:20<00:41, 17.1MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  83%|████████▎ | 3.56G/4.27G [03:20<00:32, 21.8MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  84%|████████▎ | 3.56G/4.27G [03:21<00:43, 16.2MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  84%|████████▎ | 3.57G/4.27G [03:21<00:34, 20.2MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  84%|████████▎ | 3.57G/4.27G [03:21<00:34, 20.4MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  84%|████████▍ | 3.57G/4.27G [03:21<00:33, 20.5MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  84%|████████▍ | 3.57G/4.27G [03:21<00:32, 21.2MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  84%|████████▍ | 3.58G/4.27G [03:21<00:31, 21.8MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  84%|████████▍ | 3.58G/4.27G [03:21<00:32, 20.9MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  84%|████████▍ | 3.58G/4.27G [03:21<00:27, 25.1MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  84%|████████▍ | 3.59G/4.27G [03:21<00:27, 24.7MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  84%|████████▍ | 3.59G/4.27G [03:22<00:32, 21.0MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  84%|████████▍ | 3.59G/4.27G [03:22<00:26, 25.7MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  84%|████████▍ | 3.60G/4.27G [03:22<00:30, 21.8MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  84%|████████▍ | 3.60G/4.27G [03:22<00:29, 22.3MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  84%|████████▍ | 3.60G/4.27G [03:22<00:28, 23.2MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  84%|████████▍ | 3.60G/4.27G [03:22<00:27, 23.9MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  85%|████████▍ | 3.61G/4.27G [03:22<00:26, 25.2MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  85%|████████▍ | 3.61G/4.27G [03:22<00:25, 26.2MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  85%|████████▍ | 3.61G/4.27G [03:22<00:23, 27.3MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  85%|████████▍ | 3.61G/4.27G [03:23<00:24, 26.8MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  85%|████████▍ | 3.62G/4.27G [03:23<00:22, 28.8MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  85%|████████▍ | 3.62G/4.27G [03:23<00:22, 29.2MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  85%|████████▍ | 3.62G/4.27G [03:23<00:21, 29.4MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  85%|████████▌ | 3.63G/4.27G [03:23<00:21, 30.0MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  85%|████████▌ | 3.63G/4.27G [03:23<00:20, 31.4MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  85%|████████▌ | 3.63G/4.27G [03:23<00:24, 26.1MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  85%|████████▌ | 3.64G/4.27G [03:23<00:22, 28.3MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  85%|████████▌ | 3.64G/4.27G [03:23<00:23, 26.9MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  85%|████████▌ | 3.64G/4.27G [03:24<00:19, 31.4MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  86%|████████▌ | 3.65G/4.27G [03:24<00:19, 32.3MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  86%|████████▌ | 3.65G/4.27G [03:24<00:18, 33.7MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  86%|████████▌ | 3.66G/4.27G [03:24<00:30, 19.8MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  86%|████████▌ | 3.66G/4.27G [03:24<00:37, 16.2MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  86%|████████▌ | 3.66G/4.27G [03:24<00:31, 19.0MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  86%|████████▌ | 3.66G/4.27G [03:25<00:31, 19.2MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  86%|████████▌ | 3.67G/4.27G [03:25<00:29, 20.3MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  86%|████████▌ | 3.67G/4.27G [03:25<00:25, 23.3MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  86%|████████▌ | 3.67G/4.27G [03:25<00:22, 26.3MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  86%|████████▌ | 3.68G/4.27G [03:25<00:25, 23.1MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  86%|████████▋ | 3.68G/4.27G [03:25<00:21, 27.5MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  86%|████████▋ | 3.68G/4.27G [03:25<00:20, 28.1MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  86%|████████▋ | 3.69G/4.27G [03:25<00:19, 29.2MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  87%|████████▋ | 3.69G/4.27G [03:25<00:19, 30.1MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  87%|████████▋ | 3.69G/4.27G [03:26<00:18, 31.7MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  87%|████████▋ | 3.70G/4.27G [03:26<00:17, 32.4MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  87%|████████▋ | 3.70G/4.27G [03:26<00:17, 32.2MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  87%|████████▋ | 3.70G/4.27G [03:26<00:17, 32.1MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  87%|████████▋ | 3.71G/4.27G [03:26<00:16, 33.1MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  87%|████████▋ | 3.71G/4.27G [03:26<00:17, 32.6MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  87%|████████▋ | 3.71G/4.27G [03:26<00:17, 32.0MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  87%|████████▋ | 3.72G/4.27G [03:26<00:17, 30.7MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  87%|████████▋ | 3.72G/4.27G [03:27<00:34, 15.8MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  87%|████████▋ | 3.72G/4.27G [03:27<00:32, 16.8MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  87%|████████▋ | 3.73G/4.27G [03:27<00:26, 20.2MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  87%|████████▋ | 3.73G/4.27G [03:27<00:24, 22.3MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  88%|████████▊ | 3.73G/4.27G [03:27<00:20, 25.7MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  88%|████████▊ | 3.74G/4.27G [03:27<00:19, 27.6MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  88%|████████▊ | 3.74G/4.27G [03:27<00:21, 24.8MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  88%|████████▊ | 3.74G/4.27G [03:28<00:20, 25.4MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  88%|████████▊ | 3.74G/4.27G [03:28<00:24, 21.0MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  88%|████████▊ | 3.75G/4.27G [03:28<00:24, 21.0MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  88%|████████▊ | 3.75G/4.27G [03:28<00:28, 18.0MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  88%|████████▊ | 3.75G/4.27G [03:28<00:26, 19.5MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  88%|████████▊ | 3.75G/4.27G [03:28<00:24, 21.3MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  88%|████████▊ | 3.76G/4.27G [03:28<00:21, 23.8MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  88%|████████▊ | 3.76G/4.27G [03:28<00:18, 27.4MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  88%|████████▊ | 3.76G/4.27G [03:29<00:31, 15.9MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  88%|████████▊ | 3.77G/4.27G [03:29<00:27, 17.9MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  88%|████████▊ | 3.77G/4.27G [03:29<00:22, 21.8MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  88%|████████▊ | 3.77G/4.27G [03:29<00:21, 23.4MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  89%|████████▊ | 3.78G/4.27G [03:29<00:19, 25.7MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  89%|████████▊ | 3.78G/4.27G [03:29<00:17, 27.3MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  89%|████████▊ | 3.78G/4.27G [03:29<00:17, 27.9MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  89%|████████▉ | 3.79G/4.27G [03:30<00:20, 23.2MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  89%|████████▉ | 3.79G/4.27G [03:30<00:25, 18.8MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  89%|████████▉ | 3.79G/4.27G [03:30<00:21, 21.8MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  89%|████████▉ | 3.79G/4.27G [03:30<00:30, 15.2MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  89%|████████▉ | 3.80G/4.27G [03:30<00:29, 15.9MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  89%|████████▉ | 3.80G/4.27G [03:30<00:24, 18.9MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  89%|████████▉ | 3.80G/4.27G [03:31<00:25, 18.5MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  89%|████████▉ | 3.81G/4.27G [03:31<00:21, 21.7MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  89%|████████▉ | 3.81G/4.27G [03:31<00:18, 24.3MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  89%|████████▉ | 3.81G/4.27G [03:31<00:17, 26.5MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  89%|████████▉ | 3.81G/4.27G [03:31<00:16, 27.9MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  90%|████████▉ | 3.82G/4.27G [03:31<00:18, 24.8MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  90%|████████▉ | 3.82G/4.27G [03:31<00:16, 27.7MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  90%|████████▉ | 3.82G/4.27G [03:31<00:16, 27.1MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  90%|████████▉ | 3.83G/4.27G [03:31<00:16, 26.3MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  90%|████████▉ | 3.83G/4.27G [03:32<00:15, 28.1MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  90%|████████▉ | 3.83G/4.27G [03:32<00:16, 26.3MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  90%|████████▉ | 3.84G/4.27G [03:32<00:23, 18.2MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  90%|█████████ | 3.84G/4.27G [03:32<00:19, 21.4MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  90%|█████████ | 3.84G/4.27G [03:32<00:18, 22.9MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  90%|█████████ | 3.85G/4.27G [03:32<00:18, 23.2MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  90%|█████████ | 3.85G/4.27G [03:32<00:19, 21.6MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  90%|█████████ | 3.85G/4.27G [03:32<00:17, 23.6MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  90%|█████████ | 3.85G/4.27G [03:33<00:18, 22.6MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  90%|█████████ | 3.86G/4.27G [03:33<00:15, 25.6MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  91%|█████████ | 3.86G/4.27G [03:33<00:14, 28.8MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  91%|█████████ | 3.86G/4.27G [03:33<00:12, 32.5MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  91%|█████████ | 3.87G/4.27G [03:33<00:13, 30.2MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  91%|█████████ | 3.87G/4.27G [03:33<00:12, 31.6MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  91%|█████████ | 3.87G/4.27G [03:33<00:15, 25.1MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  91%|█████████ | 3.88G/4.27G [03:34<00:16, 22.9MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  91%|█████████ | 3.88G/4.27G [03:34<00:18, 21.1MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  91%|█████████ | 3.88G/4.27G [03:34<00:17, 21.3MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  91%|█████████ | 3.88G/4.27G [03:34<00:22, 16.9MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  91%|█████████ | 3.89G/4.27G [03:34<00:18, 20.0MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  91%|█████████ | 3.89G/4.27G [03:34<00:19, 19.2MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  91%|█████████▏| 3.89G/4.27G [03:34<00:18, 20.0MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  91%|█████████▏| 3.90G/4.27G [03:34<00:16, 21.9MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  91%|█████████▏| 3.90G/4.27G [03:35<00:14, 24.6MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  91%|█████████▏| 3.90G/4.27G [03:35<00:15, 24.2MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  92%|█████████▏| 3.90G/4.27G [03:35<00:14, 24.9MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  92%|█████████▏| 3.91G/4.27G [03:35<00:13, 26.4MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  92%|█████████▏| 3.91G/4.27G [03:35<00:13, 26.0MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  92%|█████████▏| 3.91G/4.27G [03:35<00:13, 26.1MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  92%|█████████▏| 3.91G/4.27G [03:35<00:15, 22.0MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  92%|█████████▏| 3.92G/4.27G [03:35<00:13, 25.0MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  92%|█████████▏| 3.92G/4.27G [03:35<00:13, 25.0MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  92%|█████████▏| 3.92G/4.27G [03:36<00:12, 27.5MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  92%|█████████▏| 3.93G/4.27G [03:36<00:12, 27.6MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  92%|█████████▏| 3.93G/4.27G [03:36<00:14, 23.9MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  92%|█████████▏| 3.93G/4.27G [03:36<00:15, 21.5MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  92%|█████████▏| 3.94G/4.27G [03:36<00:13, 24.4MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  92%|█████████▏| 3.94G/4.27G [03:36<00:14, 22.3MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  92%|█████████▏| 3.94G/4.27G [03:36<00:13, 24.6MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  92%|█████████▏| 3.94G/4.27G [03:36<00:12, 26.3MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  93%|█████████▎| 3.95G/4.27G [03:36<00:12, 26.2MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  93%|█████████▎| 3.95G/4.27G [03:37<00:11, 27.1MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  93%|█████████▎| 3.95G/4.27G [03:37<00:12, 25.3MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  93%|█████████▎| 3.96G/4.27G [03:37<00:13, 23.0MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  93%|█████████▎| 3.96G/4.27G [03:37<00:11, 27.5MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  93%|█████████▎| 3.96G/4.27G [03:37<00:11, 26.1MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  93%|█████████▎| 3.97G/4.27G [03:37<00:11, 25.3MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  93%|█████████▎| 3.97G/4.27G [03:37<00:10, 28.2MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  93%|█████████▎| 3.97G/4.27G [03:37<00:10, 27.9MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  93%|█████████▎| 3.98G/4.27G [03:38<00:10, 28.5MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  93%|█████████▎| 3.98G/4.27G [03:38<00:10, 28.7MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  93%|█████████▎| 3.98G/4.27G [03:38<00:09, 30.1MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  93%|█████████▎| 3.98G/4.27G [03:38<00:09, 28.3MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  94%|█████████▎| 3.99G/4.27G [03:38<00:09, 29.2MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  94%|█████████▎| 3.99G/4.27G [03:38<00:09, 30.1MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  94%|█████████▎| 4.00G/4.27G [03:38<00:08, 32.1MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  94%|█████████▎| 4.00G/4.27G [03:38<00:08, 31.3MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  94%|█████████▍| 4.00G/4.27G [03:38<00:08, 30.2MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  94%|█████████▍| 4.00G/4.27G [03:38<00:09, 28.4MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  94%|█████████▍| 4.01G/4.27G [03:39<00:08, 29.0MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  94%|█████████▍| 4.01G/4.27G [03:39<00:08, 31.2MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  94%|█████████▍| 4.01G/4.27G [03:39<00:08, 30.4MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  94%|█████████▍| 4.02G/4.27G [03:39<00:08, 30.8MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  94%|█████████▍| 4.02G/4.27G [03:39<00:07, 32.1MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  94%|█████████▍| 4.02G/4.27G [03:39<00:09, 26.7MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  94%|█████████▍| 4.03G/4.27G [03:39<00:08, 28.0MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  95%|█████████▍| 4.03G/4.27G [03:39<00:10, 21.6MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  95%|█████████▍| 4.03G/4.27G [03:40<00:17, 13.4MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  95%|█████████▍| 4.04G/4.27G [03:40<00:19, 11.8MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  95%|█████████▍| 4.04G/4.27G [03:40<00:23, 9.63MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  95%|█████████▍| 4.04G/4.27G [03:41<00:18, 12.0MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  95%|█████████▍| 4.04G/4.27G [03:41<00:18, 11.9MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  95%|█████████▍| 4.04G/4.27G [03:41<00:14, 14.7MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  95%|█████████▍| 4.05G/4.27G [03:41<00:14, 15.2MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  95%|█████████▍| 4.05G/4.27G [03:41<00:13, 15.9MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  95%|█████████▍| 4.05G/4.27G [03:41<00:13, 16.5MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  95%|█████████▌| 4.05G/4.27G [03:41<00:12, 17.3MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  95%|█████████▌| 4.05G/4.27G [03:41<00:11, 17.7MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  95%|█████████▌| 4.06G/4.27G [03:41<00:10, 19.1MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  95%|█████████▌| 4.06G/4.27G [03:42<00:10, 19.7MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  95%|█████████▌| 4.06G/4.27G [03:42<00:15, 13.0MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  95%|█████████▌| 4.06G/4.27G [03:42<00:13, 15.0MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  95%|█████████▌| 4.07G/4.27G [03:42<00:12, 16.5MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  95%|█████████▌| 4.07G/4.27G [03:42<00:13, 15.2MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  95%|█████████▌| 4.07G/4.27G [03:42<00:09, 20.5MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  95%|█████████▌| 4.07G/4.27G [03:42<00:09, 20.6MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  96%|█████████▌| 4.08G/4.27G [03:43<00:09, 20.6MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  96%|█████████▌| 4.08G/4.27G [03:43<00:09, 20.2MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  96%|█████████▌| 4.08G/4.27G [03:43<00:08, 21.1MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  96%|█████████▌| 4.08G/4.27G [03:43<00:08, 21.8MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  96%|█████████▌| 4.08G/4.27G [03:43<00:08, 21.1MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  96%|█████████▌| 4.09G/4.27G [03:43<00:08, 21.7MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  96%|█████████▌| 4.09G/4.27G [03:43<00:08, 21.3MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  96%|█████████▌| 4.09G/4.27G [03:43<00:08, 20.7MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  96%|█████████▌| 4.09G/4.27G [03:44<00:11, 14.4MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  96%|█████████▌| 4.10G/4.27G [03:44<00:09, 17.5MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  96%|█████████▌| 4.10G/4.27G [03:44<00:10, 16.6MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  96%|█████████▌| 4.10G/4.27G [03:44<00:10, 16.0MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  96%|█████████▌| 4.10G/4.27G [03:44<00:14, 11.1MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  96%|█████████▌| 4.10G/4.27G [03:44<00:12, 13.3MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  96%|█████████▋| 4.11G/4.27G [03:44<00:13, 12.1MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  96%|█████████▋| 4.11G/4.27G [03:45<00:15, 10.2MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  96%|█████████▋| 4.11G/4.27G [03:45<00:11, 13.5MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  96%|█████████▋| 4.11G/4.27G [03:45<00:10, 14.0MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  96%|█████████▋| 4.11G/4.27G [03:45<00:09, 16.2MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  97%|█████████▋| 4.12G/4.27G [03:45<00:08, 17.3MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  97%|█████████▋| 4.12G/4.27G [03:45<00:08, 17.8MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  97%|█████████▋| 4.12G/4.27G [03:45<00:08, 16.8MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  97%|█████████▋| 4.12G/4.27G [03:45<00:06, 20.6MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  97%|█████████▋| 4.13G/4.27G [03:46<00:06, 21.2MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  97%|█████████▋| 4.13G/4.27G [03:46<00:06, 22.3MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  97%|█████████▋| 4.13G/4.27G [03:46<00:07, 19.3MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  97%|█████████▋| 4.13G/4.27G [03:46<00:05, 23.0MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  97%|█████████▋| 4.14G/4.27G [03:46<00:06, 21.4MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  97%|█████████▋| 4.14G/4.27G [03:46<00:05, 21.8MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  97%|█████████▋| 4.14G/4.27G [03:46<00:05, 22.3MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  97%|█████████▋| 4.14G/4.27G [03:46<00:07, 16.5MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  97%|█████████▋| 4.15G/4.27G [03:47<00:05, 22.9MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  97%|█████████▋| 4.15G/4.27G [03:47<00:04, 23.2MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  97%|█████████▋| 4.15G/4.27G [03:47<00:04, 24.2MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  97%|█████████▋| 4.16G/4.27G [03:47<00:04, 23.7MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  97%|█████████▋| 4.16G/4.27G [03:47<00:04, 23.4MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  98%|█████████▊| 4.16G/4.27G [03:47<00:04, 23.4MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  98%|█████████▊| 4.16G/4.27G [03:47<00:05, 17.6MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  98%|█████████▊| 4.17G/4.27G [03:47<00:04, 22.5MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  98%|█████████▊| 4.17G/4.27G [03:48<00:04, 23.2MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  98%|█████████▊| 4.17G/4.27G [03:48<00:03, 23.8MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  98%|█████████▊| 4.17G/4.27G [03:48<00:03, 24.1MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  98%|█████████▊| 4.18G/4.27G [03:48<00:03, 24.5MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  98%|█████████▊| 4.18G/4.27G [03:48<00:03, 23.6MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  98%|█████████▊| 4.18G/4.27G [03:48<00:04, 19.7MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  98%|█████████▊| 4.18G/4.27G [03:48<00:03, 20.4MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  98%|█████████▊| 4.19G/4.27G [03:48<00:03, 20.9MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  98%|█████████▊| 4.19G/4.27G [03:48<00:03, 19.4MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  98%|█████████▊| 4.19G/4.27G [03:49<00:03, 22.2MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  98%|█████████▊| 4.19G/4.27G [03:49<00:03, 23.1MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  98%|█████████▊| 4.20G/4.27G [03:49<00:03, 18.7MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  98%|█████████▊| 4.20G/4.27G [03:49<00:03, 21.0MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  99%|█████████▊| 4.21G/4.27G [03:49<00:02, 26.9MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  99%|█████████▊| 4.21G/4.27G [03:49<00:02, 21.3MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  99%|█████████▉| 4.21G/4.27G [03:49<00:02, 26.1MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  99%|█████████▉| 4.22G/4.27G [03:50<00:01, 25.7MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  99%|█████████▉| 4.22G/4.27G [03:50<00:02, 18.9MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  99%|█████████▉| 4.22G/4.27G [03:50<00:02, 20.5MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  99%|█████████▉| 4.22G/4.27G [03:50<00:02, 16.3MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  99%|█████████▉| 4.23G/4.27G [03:50<00:01, 19.9MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  99%|█████████▉| 4.23G/4.27G [03:50<00:02, 16.4MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  99%|█████████▉| 4.23G/4.27G [03:51<00:01, 19.3MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  99%|█████████▉| 4.23G/4.27G [03:51<00:01, 20.1MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  99%|█████████▉| 4.24G/4.27G [03:51<00:01, 21.1MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  99%|█████████▉| 4.24G/4.27G [03:51<00:01, 17.6MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt:  99%|█████████▉| 4.24G/4.27G [03:51<00:00, 23.4MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt: 100%|█████████▉| 4.25G/4.27G [03:51<00:00, 23.2MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt: 100%|█████████▉| 4.25G/4.27G [03:51<00:00, 23.0MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt: 100%|█████████▉| 4.25G/4.27G [03:51<00:00, 22.3MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt: 100%|█████████▉| 4.25G/4.27G [03:51<00:00, 22.2MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt: 100%|█████████▉| 4.26G/4.27G [03:52<00:00, 22.2MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt: 100%|█████████▉| 4.26G/4.27G [03:52<00:00, 22.5MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt: 100%|█████████▉| 4.26G/4.27G [03:52<00:00, 23.2MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt: 100%|█████████▉| 4.26G/4.27G [03:52<00:00, 23.1MB/s]
https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt: 100%|██████████| 4.27G/4.27G [03:52<00:00, 18.3MB/s]

  0%|          | 0/1131 [00:00<?, ?it/s]
ram used:  0.00 GB, alphas_cumprod                                    :   0%|          | 0/1131 [00:00<?, ?it/s]
ram used:  0.00 GB, alphas_cumprod                                    :   0%|          | 1/1131 [00:00<04:09,  4.52it/s]
ram used:  0.00 GB, model.diffusion_model.time_embed.0.weight         :   0%|          | 1/1131 [00:00<04:09,  4.52it/s]
ram used:  0.00 GB, model.diffusion_model.time_embed.0.bias           :   0%|          | 1/1131 [00:00<04:09,  4.52it/s]
ram used:  0.00 GB, model.diffusion_model.time_embed.2.weight         :   0%|          | 1/1131 [00:00<04:09,  4.52it/s]
ram used:  0.01 GB, model.diffusion_model.time_embed.2.bias           :   0%|          | 1/1131 [00:00<04:09,  4.52it/s]
ram used:  0.01 GB, model.diffusion_model.input_blocks.0.0.weight     :   0%|          | 1/1131 [00:00<04:09,  4.52it/s]
ram used:  0.01 GB, model.diffusion_model.input_blocks.0.0.bias       :   0%|          | 1/1131 [00:00<04:09,  4.52it/s]
ram used:  0.01 GB, model.diffusion_model.input_blocks.1.0.in_layers.0.weight:   0%|          | 1/1131 [00:00<04:09,  4.52it/s]
ram used:  0.01 GB, model.diffusion_model.input_blocks.1.0.in_layers.0.bias:   0%|          | 1/1131 [00:00<04:09,  4.52it/s]  
ram used:  0.01 GB, model.diffusion_model.input_blocks.1.0.in_layers.2.weight:   0%|          | 1/1131 [00:00<04:09,  4.52it/s]
ram used:  0.01 GB, model.diffusion_model.input_blocks.1.0.in_layers.2.bias:   0%|          | 1/1131 [00:00<04:09,  4.52it/s]  
ram used:  0.01 GB, model.diffusion_model.input_blocks.1.0.emb_layers.1.weight:   0%|          | 1/1131 [00:00<04:09,  4.52it/s]
ram used:  0.01 GB, model.diffusion_model.input_blocks.1.0.emb_layers.1.bias:   0%|          | 1/1131 [00:00<04:09,  4.52it/s]  
ram used:  0.01 GB, model.diffusion_model.input_blocks.1.0.out_layers.0.weight:   0%|          | 1/1131 [00:00<04:09,  4.52it/s]
ram used:  0.01 GB, model.diffusion_model.input_blocks.1.0.out_layers.0.bias:   0%|          | 1/1131 [00:00<04:09,  4.52it/s]  
ram used:  0.01 GB, model.diffusion_model.input_blocks.1.0.out_layers.3.weight:   0%|          | 1/1131 [00:00<04:09,  4.52it/s]
ram used:  0.02 GB, model.diffusion_model.input_blocks.1.0.out_layers.3.bias:   0%|          | 1/1131 [00:00<04:09,  4.52it/s]  
ram used:  0.02 GB, model.diffusion_model.input_blocks.1.1.norm.weight:   0%|          | 1/1131 [00:00<04:09,  4.52it/s]      
ram used:  0.02 GB, model.diffusion_model.input_blocks.1.1.norm.bias  :   0%|          | 1/1131 [00:00<04:09,  4.52it/s]
ram used:  0.02 GB, model.diffusion_model.input_blocks.1.1.proj_in.weight:   0%|          | 1/1131 [00:00<04:09,  4.52it/s]
ram used:  0.02 GB, model.diffusion_model.input_blocks.1.1.proj_in.bias:   0%|          | 1/1131 [00:00<04:09,  4.52it/s]  
ram used:  0.02 GB, model.diffusion_model.input_blocks.1.1.transformer_blocks.0.attn1.to_q.weight:   0%|          | 1/1131 [00:00<04:09,  4.52it/s]
ram used:  0.02 GB, model.diffusion_model.input_blocks.1.1.transformer_blocks.0.attn1.to_k.weight:   0%|          | 1/1131 [00:00<04:09,  4.52it/s]
ram used:  0.02 GB, model.diffusion_model.input_blocks.1.1.transformer_blocks.0.attn1.to_v.weight:   0%|          | 1/1131 [00:00<04:09,  4.52it/s]
ram used:  0.02 GB, model.diffusion_model.input_blocks.1.1.transformer_blocks.0.attn1.to_out.0.weight:   0%|          | 1/1131 [00:00<04:09,  4.52it/s]
ram used:  0.02 GB, model.diffusion_model.input_blocks.1.1.transformer_blocks.0.attn1.to_out.0.bias:   0%|          | 1/1131 [00:00<04:09,  4.52it/s]  
ram used:  0.02 GB, model.diffusion_model.input_blocks.1.1.transformer_blocks.0.ff.net.0.proj.weight:   0%|          | 1/1131 [00:00<04:09,  4.52it/s]
ram used:  0.02 GB, model.diffusion_model.input_blocks.1.1.transformer_blocks.0.ff.net.0.proj.bias:   0%|          | 1/1131 [00:00<04:09,  4.52it/s]  
ram used:  0.02 GB, model.diffusion_model.input_blocks.1.1.transformer_blocks.0.ff.net.2.weight:   0%|          | 1/1131 [00:00<04:09,  4.52it/s]   
ram used:  0.02 GB, model.diffusion_model.input_blocks.1.1.transformer_blocks.0.ff.net.2.weight:   3%|▎         | 29/1131 [00:00<00:09, 112.47it/s]
ram used:  0.02 GB, model.diffusion_model.input_blocks.1.1.transformer_blocks.0.ff.net.2.bias:   3%|▎         | 29/1131 [00:00<00:09, 112.47it/s]  
ram used:  0.02 GB, model.diffusion_model.input_blocks.1.1.transformer_blocks.0.attn2.to_q.weight:   3%|▎         | 29/1131 [00:00<00:09, 112.47it/s]
ram used:  0.02 GB, model.diffusion_model.input_blocks.1.1.transformer_blocks.0.attn2.to_k.weight:   3%|▎         | 29/1131 [00:00<00:09, 112.47it/s]
ram used:  0.03 GB, model.diffusion_model.input_blocks.1.1.transformer_blocks.0.attn2.to_v.weight:   3%|▎         | 29/1131 [00:00<00:09, 112.47it/s]
ram used:  0.03 GB, model.diffusion_model.input_blocks.1.1.transformer_blocks.0.attn2.to_out.0.weight:   3%|▎         | 29/1131 [00:00<00:09, 112.47it/s]
ram used:  0.03 GB, model.diffusion_model.input_blocks.1.1.transformer_blocks.0.attn2.to_out.0.bias:   3%|▎         | 29/1131 [00:00<00:09, 112.47it/s]  
ram used:  0.03 GB, model.diffusion_model.input_blocks.1.1.transformer_blocks.0.norm1.weight:   3%|▎         | 29/1131 [00:00<00:09, 112.47it/s]       
ram used:  0.03 GB, model.diffusion_model.input_blocks.1.1.transformer_blocks.0.norm1.bias:   3%|▎         | 29/1131 [00:00<00:09, 112.47it/s]  
ram used:  0.03 GB, model.diffusion_model.input_blocks.1.1.transformer_blocks.0.norm2.weight:   3%|▎         | 29/1131 [00:00<00:09, 112.47it/s]
ram used:  0.03 GB, model.diffusion_model.input_blocks.1.1.transformer_blocks.0.norm2.bias:   3%|▎         | 29/1131 [00:00<00:09, 112.47it/s]  
ram used:  0.03 GB, model.diffusion_model.input_blocks.1.1.transformer_blocks.0.norm3.weight:   3%|▎         | 29/1131 [00:00<00:09, 112.47it/s]
ram used:  0.03 GB, model.diffusion_model.input_blocks.1.1.transformer_blocks.0.norm3.bias:   3%|▎         | 29/1131 [00:00<00:09, 112.47it/s]  
ram used:  0.03 GB, model.diffusion_model.input_blocks.1.1.proj_out.weight:   3%|▎         | 29/1131 [00:00<00:09, 112.47it/s]                
ram used:  0.03 GB, model.diffusion_model.input_blocks.1.1.proj_out.bias:   3%|▎         | 29/1131 [00:00<00:09, 112.47it/s]  
ram used:  0.03 GB, model.diffusion_model.input_blocks.2.0.in_layers.0.weight:   3%|▎         | 29/1131 [00:00<00:09, 112.47it/s]
ram used:  0.03 GB, model.diffusion_model.input_blocks.2.0.in_layers.0.bias:   3%|▎         | 29/1131 [00:00<00:09, 112.47it/s]  
ram used:  0.03 GB, model.diffusion_model.input_blocks.2.0.in_layers.2.weight:   3%|▎         | 29/1131 [00:00<00:09, 112.47it/s]
ram used:  0.03 GB, model.diffusion_model.input_blocks.2.0.in_layers.2.bias:   3%|▎         | 29/1131 [00:00<00:09, 112.47it/s]  
ram used:  0.03 GB, model.diffusion_model.input_blocks.2.0.emb_layers.1.weight:   3%|▎         | 29/1131 [00:00<00:09, 112.47it/s]
ram used:  0.03 GB, model.diffusion_model.input_blocks.2.0.emb_layers.1.bias:   3%|▎         | 29/1131 [00:00<00:09, 112.47it/s]  
ram used:  0.03 GB, model.diffusion_model.input_blocks.2.0.out_layers.0.weight:   3%|▎         | 29/1131 [00:00<00:09, 112.47it/s]
ram used:  0.03 GB, model.diffusion_model.input_blocks.2.0.out_layers.0.bias:   3%|▎         | 29/1131 [00:00<00:09, 112.47it/s]  
ram used:  0.03 GB, model.diffusion_model.input_blocks.2.0.out_layers.3.weight:   3%|▎         | 29/1131 [00:00<00:09, 112.47it/s]
ram used:  0.04 GB, model.diffusion_model.input_blocks.2.0.out_layers.3.bias:   3%|▎         | 29/1131 [00:00<00:09, 112.47it/s]  
ram used:  0.04 GB, model.diffusion_model.input_blocks.2.1.norm.weight:   3%|▎         | 29/1131 [00:00<00:09, 112.47it/s]      
ram used:  0.04 GB, model.diffusion_model.input_blocks.2.1.norm.bias  :   3%|▎         | 29/1131 [00:00<00:09, 112.47it/s]
ram used:  0.04 GB, model.diffusion_model.input_blocks.2.1.proj_in.weight:   3%|▎         | 29/1131 [00:00<00:09, 112.47it/s]
ram used:  0.04 GB, model.diffusion_model.input_blocks.2.1.proj_in.bias:   3%|▎         | 29/1131 [00:00<00:09, 112.47it/s]  
ram used:  0.04 GB, model.diffusion_model.input_blocks.2.1.transformer_blocks.0.attn1.to_q.weight:   3%|▎         | 29/1131 [00:00<00:09, 112.47it/s]
ram used:  0.04 GB, model.diffusion_model.input_blocks.2.1.transformer_blocks.0.attn1.to_k.weight:   3%|▎         | 29/1131 [00:00<00:09, 112.47it/s]
ram used:  0.04 GB, model.diffusion_model.input_blocks.2.1.transformer_blocks.0.attn1.to_v.weight:   3%|▎         | 29/1131 [00:00<00:09, 112.47it/s]
ram used:  0.04 GB, model.diffusion_model.input_blocks.2.1.transformer_blocks.0.attn1.to_out.0.weight:   3%|▎         | 29/1131 [00:00<00:09, 112.47it/s]
ram used:  0.04 GB, model.diffusion_model.input_blocks.2.1.transformer_blocks.0.attn1.to_out.0.bias:   3%|▎         | 29/1131 [00:00<00:09, 112.47it/s]  
ram used:  0.04 GB, model.diffusion_model.input_blocks.2.1.transformer_blocks.0.ff.net.0.proj.weight:   3%|▎         | 29/1131 [00:00<00:09, 112.47it/s]
ram used:  0.04 GB, model.diffusion_model.input_blocks.2.1.transformer_blocks.0.ff.net.0.proj.bias:   3%|▎         | 29/1131 [00:00<00:09, 112.47it/s]  
ram used:  0.04 GB, model.diffusion_model.input_blocks.2.1.transformer_blocks.0.ff.net.2.weight:   3%|▎         | 29/1131 [00:00<00:09, 112.47it/s]   
ram used:  0.04 GB, model.diffusion_model.input_blocks.2.1.transformer_blocks.0.ff.net.2.bias:   3%|▎         | 29/1131 [00:00<00:09, 112.47it/s]  
ram used:  0.04 GB, model.diffusion_model.input_blocks.2.1.transformer_blocks.0.attn2.to_q.weight:   3%|▎         | 29/1131 [00:00<00:09, 112.47it/s]
ram used:  0.04 GB, model.diffusion_model.input_blocks.2.1.transformer_blocks.0.attn2.to_k.weight:   3%|▎         | 29/1131 [00:00<00:09, 112.47it/s]
ram used:  0.04 GB, model.diffusion_model.input_blocks.2.1.transformer_blocks.0.attn2.to_v.weight:   3%|▎         | 29/1131 [00:00<00:09, 112.47it/s]
ram used:  0.05 GB, model.diffusion_model.input_blocks.2.1.transformer_blocks.0.attn2.to_out.0.weight:   3%|▎         | 29/1131 [00:00<00:09, 112.47it/s]
ram used:  0.05 GB, model.diffusion_model.input_blocks.2.1.transformer_blocks.0.attn2.to_out.0.bias:   3%|▎         | 29/1131 [00:00<00:09, 112.47it/s]  
ram used:  0.05 GB, model.diffusion_model.input_blocks.2.1.transformer_blocks.0.norm1.weight:   3%|▎         | 29/1131 [00:00<00:09, 112.47it/s]       
ram used:  0.05 GB, model.diffusion_model.input_blocks.2.1.transformer_blocks.0.norm1.bias:   3%|▎         | 29/1131 [00:00<00:09, 112.47it/s]  
ram used:  0.05 GB, model.diffusion_model.input_blocks.2.1.transformer_blocks.0.norm2.weight:   3%|▎         | 29/1131 [00:00<00:09, 112.47it/s]
ram used:  0.05 GB, model.diffusion_model.input_blocks.2.1.transformer_blocks.0.norm2.bias:   3%|▎         | 29/1131 [00:00<00:09, 112.47it/s]  
ram used:  0.05 GB, model.diffusion_model.input_blocks.2.1.transformer_blocks.0.norm3.weight:   3%|▎         | 29/1131 [00:00<00:09, 112.47it/s]
ram used:  0.05 GB, model.diffusion_model.input_blocks.2.1.transformer_blocks.0.norm3.bias:   3%|▎         | 29/1131 [00:00<00:09, 112.47it/s]  
ram used:  0.05 GB, model.diffusion_model.input_blocks.2.1.proj_out.weight:   3%|▎         | 29/1131 [00:00<00:09, 112.47it/s]                
ram used:  0.05 GB, model.diffusion_model.input_blocks.2.1.proj_out.bias:   3%|▎         | 29/1131 [00:00<00:09, 112.47it/s]  
ram used:  0.05 GB, model.diffusion_model.input_blocks.3.0.op.weight  :   3%|▎         | 29/1131 [00:00<00:09, 112.47it/s]  
ram used:  0.05 GB, model.diffusion_model.input_blocks.3.0.op.bias    :   3%|▎         | 29/1131 [00:00<00:09, 112.47it/s]
ram used:  0.05 GB, model.diffusion_model.input_blocks.4.0.in_layers.0.weight:   3%|▎         | 29/1131 [00:00<00:09, 112.47it/s]
ram used:  0.05 GB, model.diffusion_model.input_blocks.4.0.in_layers.0.bias:   3%|▎         | 29/1131 [00:00<00:09, 112.47it/s]  
ram used:  0.05 GB, model.diffusion_model.input_blocks.4.0.in_layers.2.weight:   3%|▎         | 29/1131 [00:00<00:09, 112.47it/s]
ram used:  0.06 GB, model.diffusion_model.input_blocks.4.0.in_layers.2.bias:   3%|▎         | 29/1131 [00:00<00:09, 112.47it/s]  
ram used:  0.06 GB, model.diffusion_model.input_blocks.4.0.emb_layers.1.weight:   3%|▎         | 29/1131 [00:00<00:09, 112.47it/s]
ram used:  0.06 GB, model.diffusion_model.input_blocks.4.0.emb_layers.1.bias:   3%|▎         | 29/1131 [00:00<00:09, 112.47it/s]  
ram used:  0.06 GB, model.diffusion_model.input_blocks.4.0.out_layers.0.weight:   3%|▎         | 29/1131 [00:00<00:09, 112.47it/s]
ram used:  0.06 GB, model.diffusion_model.input_blocks.4.0.out_layers.0.bias:   3%|▎         | 29/1131 [00:00<00:09, 112.47it/s]  
ram used:  0.06 GB, model.diffusion_model.input_blocks.4.0.out_layers.3.weight:   3%|▎         | 29/1131 [00:00<00:09, 112.47it/s]
ram used:  0.08 GB, model.diffusion_model.input_blocks.4.0.out_layers.3.bias:   3%|▎         | 29/1131 [00:00<00:09, 112.47it/s]  
ram used:  0.08 GB, model.diffusion_model.input_blocks.4.0.skip_connection.weight:   3%|▎         | 29/1131 [00:00<00:09, 112.47it/s]
ram used:  0.08 GB, model.diffusion_model.input_blocks.4.0.skip_connection.bias:   3%|▎         | 29/1131 [00:00<00:09, 112.47it/s]  
ram used:  0.08 GB, model.diffusion_model.input_blocks.4.1.norm.weight:   3%|▎         | 29/1131 [00:00<00:09, 112.47it/s]         
ram used:  0.08 GB, model.diffusion_model.input_blocks.4.1.norm.bias  :   3%|▎         | 29/1131 [00:00<00:09, 112.47it/s]
ram used:  0.08 GB, model.diffusion_model.input_blocks.4.1.proj_in.weight:   3%|▎         | 29/1131 [00:00<00:09, 112.47it/s]
ram used:  0.08 GB, model.diffusion_model.input_blocks.4.1.proj_in.bias:   3%|▎         | 29/1131 [00:00<00:09, 112.47it/s]  
ram used:  0.08 GB, model.diffusion_model.input_blocks.4.1.transformer_blocks.0.attn1.to_q.weight:   3%|▎         | 29/1131 [00:00<00:09, 112.47it/s]
ram used:  0.08 GB, model.diffusion_model.input_blocks.4.1.transformer_blocks.0.attn1.to_k.weight:   3%|▎         | 29/1131 [00:00<00:09, 112.47it/s]
ram used:  0.08 GB, model.diffusion_model.input_blocks.4.1.transformer_blocks.0.attn1.to_v.weight:   3%|▎         | 29/1131 [00:00<00:09, 112.47it/s]
ram used:  0.08 GB, model.diffusion_model.input_blocks.4.1.transformer_blocks.0.attn1.to_out.0.weight:   3%|▎         | 29/1131 [00:00<00:09, 112.47it/s]
ram used:  0.08 GB, model.diffusion_model.input_blocks.4.1.transformer_blocks.0.attn1.to_out.0.bias:   3%|▎         | 29/1131 [00:00<00:09, 112.47it/s]  
ram used:  0.08 GB, model.diffusion_model.input_blocks.4.1.transformer_blocks.0.ff.net.0.proj.weight:   3%|▎         | 29/1131 [00:00<00:09, 112.47it/s]
ram used:  0.08 GB, model.diffusion_model.input_blocks.4.1.transformer_blocks.0.ff.net.0.proj.weight:   9%|▉         | 103/1131 [00:00<00:03, 337.56it/s]
ram used:  0.10 GB, model.diffusion_model.input_blocks.4.1.transformer_blocks.0.ff.net.0.proj.bias:   9%|▉         | 103/1131 [00:00<00:03, 337.56it/s]  
ram used:  0.10 GB, model.diffusion_model.input_blocks.4.1.transformer_blocks.0.ff.net.2.weight:   9%|▉         | 103/1131 [00:00<00:03, 337.56it/s]   
ram used:  0.10 GB, model.diffusion_model.input_blocks.4.1.transformer_blocks.0.ff.net.2.bias:   9%|▉         | 103/1131 [00:00<00:03, 337.56it/s]  
ram used:  0.10 GB, model.diffusion_model.input_blocks.4.1.transformer_blocks.0.attn2.to_q.weight:   9%|▉         | 103/1131 [00:00<00:03, 337.56it/s]
ram used:  0.11 GB, model.diffusion_model.input_blocks.4.1.transformer_blocks.0.attn2.to_k.weight:   9%|▉         | 103/1131 [00:00<00:03, 337.56it/s]
ram used:  0.11 GB, model.diffusion_model.input_blocks.4.1.transformer_blocks.0.attn2.to_v.weight:   9%|▉         | 103/1131 [00:00<00:03, 337.56it/s]
ram used:  0.11 GB, model.diffusion_model.input_blocks.4.1.transformer_blocks.0.attn2.to_out.0.weight:   9%|▉         | 103/1131 [00:00<00:03, 337.56it/s]
ram used:  0.11 GB, model.diffusion_model.input_blocks.4.1.transformer_blocks.0.attn2.to_out.0.bias:   9%|▉         | 103/1131 [00:00<00:03, 337.56it/s]  
ram used:  0.11 GB, model.diffusion_model.input_blocks.4.1.transformer_blocks.0.norm1.weight:   9%|▉         | 103/1131 [00:00<00:03, 337.56it/s]       
ram used:  0.11 GB, model.diffusion_model.input_blocks.4.1.transformer_blocks.0.norm1.bias:   9%|▉         | 103/1131 [00:00<00:03, 337.56it/s]  
ram used:  0.11 GB, model.diffusion_model.input_blocks.4.1.transformer_blocks.0.norm2.weight:   9%|▉         | 103/1131 [00:00<00:03, 337.56it/s]
ram used:  0.11 GB, model.diffusion_model.input_blocks.4.1.transformer_blocks.0.norm2.bias:   9%|▉         | 103/1131 [00:00<00:03, 337.56it/s]  
ram used:  0.11 GB, model.diffusion_model.input_blocks.4.1.transformer_blocks.0.norm3.weight:   9%|▉         | 103/1131 [00:00<00:03, 337.56it/s]
ram used:  0.11 GB, model.diffusion_model.input_blocks.4.1.transformer_blocks.0.norm3.bias:   9%|▉         | 103/1131 [00:00<00:03, 337.56it/s]  
ram used:  0.11 GB, model.diffusion_model.input_blocks.4.1.proj_out.weight:   9%|▉         | 103/1131 [00:00<00:03, 337.56it/s]                
ram used:  0.11 GB, model.diffusion_model.input_blocks.4.1.proj_out.bias:   9%|▉         | 103/1131 [00:00<00:03, 337.56it/s]  
ram used:  0.11 GB, model.diffusion_model.input_blocks.5.0.in_layers.0.weight:   9%|▉         | 103/1131 [00:00<00:03, 337.56it/s]
ram used:  0.11 GB, model.diffusion_model.input_blocks.5.0.in_layers.0.bias:   9%|▉         | 103/1131 [00:00<00:03, 337.56it/s]  
ram used:  0.11 GB, model.diffusion_model.input_blocks.5.0.in_layers.2.weight:   9%|▉         | 103/1131 [00:00<00:03, 337.56it/s]
ram used:  0.13 GB, model.diffusion_model.input_blocks.5.0.in_layers.2.bias:   9%|▉         | 103/1131 [00:00<00:03, 337.56it/s]  
ram used:  0.13 GB, model.diffusion_model.input_blocks.5.0.emb_layers.1.weight:   9%|▉         | 103/1131 [00:00<00:03, 337.56it/s]
ram used:  0.13 GB, model.diffusion_model.input_blocks.5.0.emb_layers.1.bias:   9%|▉         | 103/1131 [00:00<00:03, 337.56it/s]  
ram used:  0.13 GB, model.diffusion_model.input_blocks.5.0.out_layers.0.weight:   9%|▉         | 103/1131 [00:00<00:03, 337.56it/s]
ram used:  0.13 GB, model.diffusion_model.input_blocks.5.0.out_layers.0.bias:   9%|▉         | 103/1131 [00:00<00:03, 337.56it/s]  
ram used:  0.13 GB, model.diffusion_model.input_blocks.5.0.out_layers.3.weight:   9%|▉         | 103/1131 [00:00<00:03, 337.56it/s]
ram used:  0.15 GB, model.diffusion_model.input_blocks.5.0.out_layers.3.bias:   9%|▉         | 103/1131 [00:00<00:03, 337.56it/s]  
ram used:  0.15 GB, model.diffusion_model.input_blocks.5.1.norm.weight:   9%|▉         | 103/1131 [00:00<00:03, 337.56it/s]      
ram used:  0.15 GB, model.diffusion_model.input_blocks.5.1.norm.bias  :   9%|▉         | 103/1131 [00:00<00:03, 337.56it/s]
ram used:  0.15 GB, model.diffusion_model.input_blocks.5.1.proj_in.weight:   9%|▉         | 103/1131 [00:00<00:03, 337.56it/s]
ram used:  0.15 GB, model.diffusion_model.input_blocks.5.1.proj_in.bias:   9%|▉         | 103/1131 [00:00<00:03, 337.56it/s]  
ram used:  0.15 GB, model.diffusion_model.input_blocks.5.1.transformer_blocks.0.attn1.to_q.weight:   9%|▉         | 103/1131 [00:00<00:03, 337.56it/s]
ram used:  0.15 GB, model.diffusion_model.input_blocks.5.1.transformer_blocks.0.attn1.to_k.weight:   9%|▉         | 103/1131 [00:00<00:03, 337.56it/s]
ram used:  0.15 GB, model.diffusion_model.input_blocks.5.1.transformer_blocks.0.attn1.to_v.weight:   9%|▉         | 103/1131 [00:00<00:03, 337.56it/s]
ram used:  0.15 GB, model.diffusion_model.input_blocks.5.1.transformer_blocks.0.attn1.to_out.0.weight:   9%|▉         | 103/1131 [00:00<00:03, 337.56it/s]
ram used:  0.15 GB, model.diffusion_model.input_blocks.5.1.transformer_blocks.0.attn1.to_out.0.bias:   9%|▉         | 103/1131 [00:00<00:03, 337.56it/s]  
ram used:  0.15 GB, model.diffusion_model.input_blocks.5.1.transformer_blocks.0.ff.net.0.proj.weight:   9%|▉         | 103/1131 [00:00<00:03, 337.56it/s]
ram used:  0.17 GB, model.diffusion_model.input_blocks.5.1.transformer_blocks.0.ff.net.0.proj.bias:   9%|▉         | 103/1131 [00:00<00:03, 337.56it/s]  
ram used:  0.17 GB, model.diffusion_model.input_blocks.5.1.transformer_blocks.0.ff.net.2.weight:   9%|▉         | 103/1131 [00:00<00:03, 337.56it/s]   
ram used:  0.17 GB, model.diffusion_model.input_blocks.5.1.transformer_blocks.0.ff.net.2.bias:   9%|▉         | 103/1131 [00:00<00:03, 337.56it/s]  
ram used:  0.17 GB, model.diffusion_model.input_blocks.5.1.transformer_blocks.0.attn2.to_q.weight:   9%|▉         | 103/1131 [00:00<00:03, 337.56it/s]
ram used:  0.18 GB, model.diffusion_model.input_blocks.5.1.transformer_blocks.0.attn2.to_k.weight:   9%|▉         | 103/1131 [00:00<00:03, 337.56it/s]
ram used:  0.18 GB, model.diffusion_model.input_blocks.5.1.transformer_blocks.0.attn2.to_v.weight:   9%|▉         | 103/1131 [00:00<00:03, 337.56it/s]
ram used:  0.18 GB, model.diffusion_model.input_blocks.5.1.transformer_blocks.0.attn2.to_out.0.weight:   9%|▉         | 103/1131 [00:00<00:03, 337.56it/s]
ram used:  0.18 GB, model.diffusion_model.input_blocks.5.1.transformer_blocks.0.attn2.to_out.0.bias:   9%|▉         | 103/1131 [00:00<00:03, 337.56it/s]  
ram used:  0.18 GB, model.diffusion_model.input_blocks.5.1.transformer_blocks.0.norm1.weight:   9%|▉         | 103/1131 [00:00<00:03, 337.56it/s]       
ram used:  0.18 GB, model.diffusion_model.input_blocks.5.1.transformer_blocks.0.norm1.bias:   9%|▉         | 103/1131 [00:00<00:03, 337.56it/s]  
ram used:  0.18 GB, model.diffusion_model.input_blocks.5.1.transformer_blocks.0.norm2.weight:   9%|▉         | 103/1131 [00:00<00:03, 337.56it/s]
ram used:  0.18 GB, model.diffusion_model.input_blocks.5.1.transformer_blocks.0.norm2.bias:   9%|▉         | 103/1131 [00:00<00:03, 337.56it/s]  
ram used:  0.18 GB, model.diffusion_model.input_blocks.5.1.transformer_blocks.0.norm3.weight:   9%|▉         | 103/1131 [00:00<00:03, 337.56it/s]
ram used:  0.18 GB, model.diffusion_model.input_blocks.5.1.transformer_blocks.0.norm3.bias:   9%|▉         | 103/1131 [00:00<00:03, 337.56it/s]  
ram used:  0.18 GB, model.diffusion_model.input_blocks.5.1.proj_out.weight:   9%|▉         | 103/1131 [00:00<00:03, 337.56it/s]                
ram used:  0.18 GB, model.diffusion_model.input_blocks.5.1.proj_out.bias:   9%|▉         | 103/1131 [00:00<00:03, 337.56it/s]  
ram used:  0.18 GB, model.diffusion_model.input_blocks.6.0.op.weight  :   9%|▉         | 103/1131 [00:00<00:03, 337.56it/s]  
ram used:  0.20 GB, model.diffusion_model.input_blocks.6.0.op.bias    :   9%|▉         | 103/1131 [00:00<00:03, 337.56it/s]
ram used:  0.20 GB, model.diffusion_model.input_blocks.7.0.in_layers.0.weight:   9%|▉         | 103/1131 [00:00<00:03, 337.56it/s]
ram used:  0.20 GB, model.diffusion_model.input_blocks.7.0.in_layers.0.bias:   9%|▉         | 103/1131 [00:00<00:03, 337.56it/s]  
ram used:  0.20 GB, model.diffusion_model.input_blocks.7.0.in_layers.2.weight:   9%|▉         | 103/1131 [00:00<00:03, 337.56it/s]
ram used:  0.23 GB, model.diffusion_model.input_blocks.7.0.in_layers.2.bias:   9%|▉         | 103/1131 [00:00<00:03, 337.56it/s]  
ram used:  0.23 GB, model.diffusion_model.input_blocks.7.0.emb_layers.1.weight:   9%|▉         | 103/1131 [00:00<00:03, 337.56it/s]
ram used:  0.23 GB, model.diffusion_model.input_blocks.7.0.emb_layers.1.bias:   9%|▉         | 103/1131 [00:00<00:03, 337.56it/s]  
ram used:  0.23 GB, model.diffusion_model.input_blocks.7.0.out_layers.0.weight:   9%|▉         | 103/1131 [00:00<00:03, 337.56it/s]
ram used:  0.23 GB, model.diffusion_model.input_blocks.7.0.out_layers.0.weight:  15%|█▍        | 164/1131 [00:00<00:02, 428.67it/s]
ram used:  0.23 GB, model.diffusion_model.input_blocks.7.0.out_layers.0.bias:  15%|█▍        | 164/1131 [00:00<00:02, 428.67it/s]  
ram used:  0.23 GB, model.diffusion_model.input_blocks.7.0.out_layers.3.weight:  15%|█▍        | 164/1131 [00:00<00:02, 428.67it/s]
ram used:  0.29 GB, model.diffusion_model.input_blocks.7.0.out_layers.3.bias:  15%|█▍        | 164/1131 [00:00<00:02, 428.67it/s]  
ram used:  0.29 GB, model.diffusion_model.input_blocks.7.0.skip_connection.weight:  15%|█▍        | 164/1131 [00:00<00:02, 428.67it/s]
ram used:  0.30 GB, model.diffusion_model.input_blocks.7.0.skip_connection.bias:  15%|█▍        | 164/1131 [00:00<00:02, 428.67it/s]  
ram used:  0.30 GB, model.diffusion_model.input_blocks.7.1.norm.weight:  15%|█▍        | 164/1131 [00:00<00:02, 428.67it/s]         
ram used:  0.30 GB, model.diffusion_model.input_blocks.7.1.norm.bias  :  15%|█▍        | 164/1131 [00:00<00:02, 428.67it/s]
ram used:  0.30 GB, model.diffusion_model.input_blocks.7.1.proj_in.weight:  15%|█▍        | 164/1131 [00:00<00:02, 428.67it/s]
ram used:  0.30 GB, model.diffusion_model.input_blocks.7.1.proj_in.bias:  15%|█▍        | 164/1131 [00:00<00:02, 428.67it/s]  
ram used:  0.30 GB, model.diffusion_model.input_blocks.7.1.transformer_blocks.0.attn1.to_q.weight:  15%|█▍        | 164/1131 [00:00<00:02, 428.67it/s]
ram used:  0.31 GB, model.diffusion_model.input_blocks.7.1.transformer_blocks.0.attn1.to_k.weight:  15%|█▍        | 164/1131 [00:00<00:02, 428.67it/s]
ram used:  0.32 GB, model.diffusion_model.input_blocks.7.1.transformer_blocks.0.attn1.to_v.weight:  15%|█▍        | 164/1131 [00:00<00:02, 428.67it/s]
ram used:  0.32 GB, model.diffusion_model.input_blocks.7.1.transformer_blocks.0.attn1.to_out.0.weight:  15%|█▍        | 164/1131 [00:00<00:02, 428.67it/s]
ram used:  0.33 GB, model.diffusion_model.input_blocks.7.1.transformer_blocks.0.attn1.to_out.0.bias:  15%|█▍        | 164/1131 [00:00<00:02, 428.67it/s]  
ram used:  0.33 GB, model.diffusion_model.input_blocks.7.1.transformer_blocks.0.ff.net.0.proj.weight:  15%|█▍        | 164/1131 [00:00<00:02, 428.67it/s]
ram used:  0.38 GB, model.diffusion_model.input_blocks.7.1.transformer_blocks.0.ff.net.0.proj.bias:  15%|█▍        | 164/1131 [00:00<00:02, 428.67it/s]  
ram used:  0.38 GB, model.diffusion_model.input_blocks.7.1.transformer_blocks.0.ff.net.2.weight:  15%|█▍        | 164/1131 [00:00<00:02, 428.67it/s]   
ram used:  0.41 GB, model.diffusion_model.input_blocks.7.1.transformer_blocks.0.ff.net.2.bias:  15%|█▍        | 164/1131 [00:00<00:02, 428.67it/s]  
ram used:  0.41 GB, model.diffusion_model.input_blocks.7.1.transformer_blocks.0.attn2.to_q.weight:  15%|█▍        | 164/1131 [00:00<00:02, 428.67it/s]
ram used:  0.41 GB, model.diffusion_model.input_blocks.7.1.transformer_blocks.0.attn2.to_k.weight:  15%|█▍        | 164/1131 [00:00<00:02, 428.67it/s]
ram used:  0.42 GB, model.diffusion_model.input_blocks.7.1.transformer_blocks.0.attn2.to_v.weight:  15%|█▍        | 164/1131 [00:00<00:02, 428.67it/s]
ram used:  0.42 GB, model.diffusion_model.input_blocks.7.1.transformer_blocks.0.attn2.to_out.0.weight:  15%|█▍        | 164/1131 [00:00<00:02, 428.67it/s]
ram used:  0.43 GB, model.diffusion_model.input_blocks.7.1.transformer_blocks.0.attn2.to_out.0.bias:  15%|█▍        | 164/1131 [00:00<00:02, 428.67it/s]  
ram used:  0.43 GB, model.diffusion_model.input_blocks.7.1.transformer_blocks.0.norm1.weight:  15%|█▍        | 164/1131 [00:00<00:02, 428.67it/s]       
ram used:  0.43 GB, model.diffusion_model.input_blocks.7.1.transformer_blocks.0.norm1.bias:  15%|█▍        | 164/1131 [00:00<00:02, 428.67it/s]  
ram used:  0.43 GB, model.diffusion_model.input_blocks.7.1.transformer_blocks.0.norm2.weight:  15%|█▍        | 164/1131 [00:00<00:02, 428.67it/s]
ram used:  0.43 GB, model.diffusion_model.input_blocks.7.1.transformer_blocks.0.norm2.bias:  15%|█▍        | 164/1131 [00:00<00:02, 428.67it/s]  
ram used:  0.43 GB, model.diffusion_model.input_blocks.7.1.transformer_blocks.0.norm3.weight:  15%|█▍        | 164/1131 [00:00<00:02, 428.67it/s]
ram used:  0.43 GB, model.diffusion_model.input_blocks.7.1.transformer_blocks.0.norm3.bias:  15%|█▍        | 164/1131 [00:00<00:02, 428.67it/s]  
ram used:  0.43 GB, model.diffusion_model.input_blocks.7.1.proj_out.weight:  15%|█▍        | 164/1131 [00:00<00:02, 428.67it/s]                
ram used:  0.44 GB, model.diffusion_model.input_blocks.7.1.proj_out.bias:  15%|█▍        | 164/1131 [00:00<00:02, 428.67it/s]  
ram used:  0.44 GB, model.diffusion_model.input_blocks.8.0.in_layers.0.weight:  15%|█▍        | 164/1131 [00:00<00:02, 428.67it/s]
ram used:  0.44 GB, model.diffusion_model.input_blocks.8.0.in_layers.0.bias:  15%|█▍        | 164/1131 [00:00<00:02, 428.67it/s]  
ram used:  0.44 GB, model.diffusion_model.input_blocks.8.0.in_layers.2.weight:  15%|█▍        | 164/1131 [00:00<00:02, 428.67it/s]
ram used:  0.49 GB, model.diffusion_model.input_blocks.8.0.in_layers.2.bias:  15%|█▍        | 164/1131 [00:00<00:02, 428.67it/s]  
ram used:  0.49 GB, model.diffusion_model.input_blocks.8.0.emb_layers.1.weight:  15%|█▍        | 164/1131 [00:00<00:02, 428.67it/s]
ram used:  0.50 GB, model.diffusion_model.input_blocks.8.0.emb_layers.1.bias:  15%|█▍        | 164/1131 [00:00<00:02, 428.67it/s]  
ram used:  0.50 GB, model.diffusion_model.input_blocks.8.0.out_layers.0.weight:  15%|█▍        | 164/1131 [00:00<00:02, 428.67it/s]
ram used:  0.50 GB, model.diffusion_model.input_blocks.8.0.out_layers.0.bias:  15%|█▍        | 164/1131 [00:00<00:02, 428.67it/s]  
ram used:  0.50 GB, model.diffusion_model.input_blocks.8.0.out_layers.3.weight:  15%|█▍        | 164/1131 [00:00<00:02, 428.67it/s]
ram used:  0.56 GB, model.diffusion_model.input_blocks.8.0.out_layers.3.bias:  15%|█▍        | 164/1131 [00:00<00:02, 428.67it/s]  
ram used:  0.56 GB, model.diffusion_model.input_blocks.8.1.norm.weight:  15%|█▍        | 164/1131 [00:00<00:02, 428.67it/s]      
ram used:  0.56 GB, model.diffusion_model.input_blocks.8.1.norm.bias  :  15%|█▍        | 164/1131 [00:00<00:02, 428.67it/s]
ram used:  0.56 GB, model.diffusion_model.input_blocks.8.1.proj_in.weight:  15%|█▍        | 164/1131 [00:00<00:02, 428.67it/s]
ram used:  0.57 GB, model.diffusion_model.input_blocks.8.1.proj_in.bias:  15%|█▍        | 164/1131 [00:00<00:02, 428.67it/s]  
ram used:  0.57 GB, model.diffusion_model.input_blocks.8.1.transformer_blocks.0.attn1.to_q.weight:  15%|█▍        | 164/1131 [00:00<00:02, 428.67it/s]
ram used:  0.57 GB, model.diffusion_model.input_blocks.8.1.transformer_blocks.0.attn1.to_k.weight:  15%|█▍        | 164/1131 [00:00<00:02, 428.67it/s]
ram used:  0.58 GB, model.diffusion_model.input_blocks.8.1.transformer_blocks.0.attn1.to_v.weight:  15%|█▍        | 164/1131 [00:00<00:02, 428.67it/s]
ram used:  0.59 GB, model.diffusion_model.input_blocks.8.1.transformer_blocks.0.attn1.to_out.0.weight:  15%|█▍        | 164/1131 [00:00<00:02, 428.67it/s]
ram used:  0.59 GB, model.diffusion_model.input_blocks.8.1.transformer_blocks.0.attn1.to_out.0.bias:  15%|█▍        | 164/1131 [00:00<00:02, 428.67it/s]  
ram used:  0.59 GB, model.diffusion_model.input_blocks.8.1.transformer_blocks.0.attn1.to_out.0.bias:  19%|█▉        | 214/1131 [00:00<00:02, 381.73it/s]
ram used:  0.59 GB, model.diffusion_model.input_blocks.8.1.transformer_blocks.0.ff.net.0.proj.weight:  19%|█▉        | 214/1131 [00:00<00:02, 381.73it/s]
ram used:  0.64 GB, model.diffusion_model.input_blocks.8.1.transformer_blocks.0.ff.net.0.proj.bias:  19%|█▉        | 214/1131 [00:00<00:02, 381.73it/s]  
ram used:  0.64 GB, model.diffusion_model.input_blocks.8.1.transformer_blocks.0.ff.net.2.weight:  19%|█▉        | 214/1131 [00:00<00:02, 381.73it/s]   
ram used:  0.67 GB, model.diffusion_model.input_blocks.8.1.transformer_blocks.0.ff.net.2.bias:  19%|█▉        | 214/1131 [00:00<00:02, 381.73it/s]  
ram used:  0.67 GB, model.diffusion_model.input_blocks.8.1.transformer_blocks.0.attn2.to_q.weight:  19%|█▉        | 214/1131 [00:00<00:02, 381.73it/s]
ram used:  0.68 GB, model.diffusion_model.input_blocks.8.1.transformer_blocks.0.attn2.to_k.weight:  19%|█▉        | 214/1131 [00:00<00:02, 381.73it/s]
ram used:  0.68 GB, model.diffusion_model.input_blocks.8.1.transformer_blocks.0.attn2.to_v.weight:  19%|█▉        | 214/1131 [00:00<00:02, 381.73it/s]
ram used:  0.69 GB, model.diffusion_model.input_blocks.8.1.transformer_blocks.0.attn2.to_out.0.weight:  19%|█▉        | 214/1131 [00:00<00:02, 381.73it/s]
ram used:  0.69 GB, model.diffusion_model.input_blocks.8.1.transformer_blocks.0.attn2.to_out.0.bias:  19%|█▉        | 214/1131 [00:00<00:02, 381.73it/s]  
ram used:  0.69 GB, model.diffusion_model.input_blocks.8.1.transformer_blocks.0.norm1.weight:  19%|█▉        | 214/1131 [00:00<00:02, 381.73it/s]       
ram used:  0.69 GB, model.diffusion_model.input_blocks.8.1.transformer_blocks.0.norm1.bias:  19%|█▉        | 214/1131 [00:00<00:02, 381.73it/s]  
ram used:  0.69 GB, model.diffusion_model.input_blocks.8.1.transformer_blocks.0.norm2.weight:  19%|█▉        | 214/1131 [00:00<00:02, 381.73it/s]
ram used:  0.69 GB, model.diffusion_model.input_blocks.8.1.transformer_blocks.0.norm2.bias:  19%|█▉        | 214/1131 [00:00<00:02, 381.73it/s]  
ram used:  0.69 GB, model.diffusion_model.input_blocks.8.1.transformer_blocks.0.norm3.weight:  19%|█▉        | 214/1131 [00:00<00:02, 381.73it/s]
ram used:  0.69 GB, model.diffusion_model.input_blocks.8.1.transformer_blocks.0.norm3.bias:  19%|█▉        | 214/1131 [00:00<00:02, 381.73it/s]  
ram used:  0.69 GB, model.diffusion_model.input_blocks.8.1.proj_out.weight:  19%|█▉        | 214/1131 [00:00<00:02, 381.73it/s]                
ram used:  0.70 GB, model.diffusion_model.input_blocks.8.1.proj_out.bias:  19%|█▉        | 214/1131 [00:00<00:02, 381.73it/s]  
ram used:  0.70 GB, model.diffusion_model.input_blocks.9.0.op.weight  :  19%|█▉        | 214/1131 [00:00<00:02, 381.73it/s]  
ram used:  0.76 GB, model.diffusion_model.input_blocks.9.0.op.bias    :  19%|█▉        | 214/1131 [00:00<00:02, 381.73it/s]
ram used:  0.76 GB, model.diffusion_model.input_blocks.10.0.in_layers.0.weight:  19%|█▉        | 214/1131 [00:00<00:02, 381.73it/s]
ram used:  0.76 GB, model.diffusion_model.input_blocks.10.0.in_layers.0.bias:  19%|█▉        | 214/1131 [00:00<00:02, 381.73it/s]  
ram used:  0.76 GB, model.diffusion_model.input_blocks.10.0.in_layers.2.weight:  19%|█▉        | 214/1131 [00:00<00:02, 381.73it/s]
ram used:  0.82 GB, model.diffusion_model.input_blocks.10.0.in_layers.2.bias:  19%|█▉        | 214/1131 [00:00<00:02, 381.73it/s]  
ram used:  0.82 GB, model.diffusion_model.input_blocks.10.0.emb_layers.1.weight:  19%|█▉        | 214/1131 [00:00<00:02, 381.73it/s]
ram used:  0.82 GB, model.diffusion_model.input_blocks.10.0.emb_layers.1.bias:  19%|█▉        | 214/1131 [00:00<00:02, 381.73it/s]  
ram used:  0.82 GB, model.diffusion_model.input_blocks.10.0.out_layers.0.weight:  19%|█▉        | 214/1131 [00:00<00:02, 381.73it/s]
ram used:  0.82 GB, model.diffusion_model.input_blocks.10.0.out_layers.0.bias:  19%|█▉        | 214/1131 [00:00<00:02, 381.73it/s]  
ram used:  0.82 GB, model.diffusion_model.input_blocks.10.0.out_layers.3.weight:  19%|█▉        | 214/1131 [00:00<00:02, 381.73it/s]
ram used:  0.88 GB, model.diffusion_model.input_blocks.10.0.out_layers.3.bias:  19%|█▉        | 214/1131 [00:00<00:02, 381.73it/s]  
ram used:  0.88 GB, model.diffusion_model.input_blocks.11.0.in_layers.0.weight:  19%|█▉        | 214/1131 [00:00<00:02, 381.73it/s]
ram used:  0.88 GB, model.diffusion_model.input_blocks.11.0.in_layers.0.bias:  19%|█▉        | 214/1131 [00:00<00:02, 381.73it/s]  
ram used:  0.88 GB, model.diffusion_model.input_blocks.11.0.in_layers.2.weight:  19%|█▉        | 214/1131 [00:00<00:02, 381.73it/s]
ram used:  0.94 GB, model.diffusion_model.input_blocks.11.0.in_layers.2.bias:  19%|█▉        | 214/1131 [00:00<00:02, 381.73it/s]  
ram used:  0.94 GB, model.diffusion_model.input_blocks.11.0.emb_layers.1.weight:  19%|█▉        | 214/1131 [00:00<00:02, 381.73it/s]
ram used:  0.95 GB, model.diffusion_model.input_blocks.11.0.emb_layers.1.bias:  19%|█▉        | 214/1131 [00:00<00:02, 381.73it/s]  
ram used:  0.95 GB, model.diffusion_model.input_blocks.11.0.out_layers.0.weight:  19%|█▉        | 214/1131 [00:00<00:02, 381.73it/s]
ram used:  0.95 GB, model.diffusion_model.input_blocks.11.0.out_layers.0.bias:  19%|█▉        | 214/1131 [00:00<00:02, 381.73it/s]  
ram used:  0.95 GB, model.diffusion_model.input_blocks.11.0.out_layers.3.weight:  19%|█▉        | 214/1131 [00:00<00:02, 381.73it/s]
ram used:  1.01 GB, model.diffusion_model.input_blocks.11.0.out_layers.3.bias:  19%|█▉        | 214/1131 [00:00<00:02, 381.73it/s]  
ram used:  1.01 GB, model.diffusion_model.middle_block.0.in_layers.0.weight:  19%|█▉        | 214/1131 [00:00<00:02, 381.73it/s]  
ram used:  1.01 GB, model.diffusion_model.middle_block.0.in_layers.0.bias:  19%|█▉        | 214/1131 [00:00<00:02, 381.73it/s]  
ram used:  1.01 GB, model.diffusion_model.middle_block.0.in_layers.2.weight:  19%|█▉        | 214/1131 [00:00<00:02, 381.73it/s]
ram used:  1.07 GB, model.diffusion_model.middle_block.0.in_layers.2.bias:  19%|█▉        | 214/1131 [00:00<00:02, 381.73it/s]  
ram used:  1.07 GB, model.diffusion_model.middle_block.0.emb_layers.1.weight:  19%|█▉        | 214/1131 [00:00<00:02, 381.73it/s]
ram used:  1.07 GB, model.diffusion_model.middle_block.0.emb_layers.1.weight:  23%|██▎       | 258/1131 [00:00<00:02, 318.47it/s]
ram used:  1.07 GB, model.diffusion_model.middle_block.0.emb_layers.1.bias:  23%|██▎       | 258/1131 [00:00<00:02, 318.47it/s]  
ram used:  1.07 GB, model.diffusion_model.middle_block.0.out_layers.0.weight:  23%|██▎       | 258/1131 [00:00<00:02, 318.47it/s]
ram used:  1.07 GB, model.diffusion_model.middle_block.0.out_layers.0.bias:  23%|██▎       | 258/1131 [00:00<00:02, 318.47it/s]  
ram used:  1.07 GB, model.diffusion_model.middle_block.0.out_layers.3.weight:  23%|██▎       | 258/1131 [00:00<00:02, 318.47it/s]
ram used:  1.13 GB, model.diffusion_model.middle_block.0.out_layers.3.bias:  23%|██▎       | 258/1131 [00:00<00:02, 318.47it/s]  
ram used:  1.13 GB, model.diffusion_model.middle_block.1.norm.weight  :  23%|██▎       | 258/1131 [00:00<00:02, 318.47it/s]    
ram used:  1.13 GB, model.diffusion_model.middle_block.1.norm.bias    :  23%|██▎       | 258/1131 [00:00<00:02, 318.47it/s]
ram used:  1.13 GB, model.diffusion_model.middle_block.1.proj_in.weight:  23%|██▎       | 258/1131 [00:00<00:02, 318.47it/s]
ram used:  1.14 GB, model.diffusion_model.middle_block.1.proj_in.bias :  23%|██▎       | 258/1131 [00:00<00:02, 318.47it/s] 
ram used:  1.14 GB, model.diffusion_model.middle_block.1.transformer_blocks.0.attn1.to_q.weight:  23%|██▎       | 258/1131 [00:00<00:02, 318.47it/s]
ram used:  1.14 GB, model.diffusion_model.middle_block.1.transformer_blocks.0.attn1.to_k.weight:  23%|██▎       | 258/1131 [00:00<00:02, 318.47it/s]
ram used:  1.15 GB, model.diffusion_model.middle_block.1.transformer_blocks.0.attn1.to_v.weight:  23%|██▎       | 258/1131 [00:00<00:02, 318.47it/s]
ram used:  1.16 GB, model.diffusion_model.middle_block.1.transformer_blocks.0.attn1.to_out.0.weight:  23%|██▎       | 258/1131 [00:00<00:02, 318.47it/s]
ram used:  1.16 GB, model.diffusion_model.middle_block.1.transformer_blocks.0.attn1.to_out.0.bias:  23%|██▎       | 258/1131 [00:00<00:02, 318.47it/s]  
ram used:  1.16 GB, model.diffusion_model.middle_block.1.transformer_blocks.0.ff.net.0.proj.weight:  23%|██▎       | 258/1131 [00:00<00:02, 318.47it/s]
ram used:  1.22 GB, model.diffusion_model.middle_block.1.transformer_blocks.0.ff.net.0.proj.bias:  23%|██▎       | 258/1131 [00:00<00:02, 318.47it/s]  
ram used:  1.22 GB, model.diffusion_model.middle_block.1.transformer_blocks.0.ff.net.2.weight:  23%|██▎       | 258/1131 [00:00<00:02, 318.47it/s]   
ram used:  1.24 GB, model.diffusion_model.middle_block.1.transformer_blocks.0.ff.net.2.bias:  23%|██▎       | 258/1131 [00:00<00:02, 318.47it/s]  
ram used:  1.24 GB, model.diffusion_model.middle_block.1.transformer_blocks.0.attn2.to_q.weight:  23%|██▎       | 258/1131 [00:00<00:02, 318.47it/s]
ram used:  1.25 GB, model.diffusion_model.middle_block.1.transformer_blocks.0.attn2.to_k.weight:  23%|██▎       | 258/1131 [00:00<00:02, 318.47it/s]
ram used:  1.25 GB, model.diffusion_model.middle_block.1.transformer_blocks.0.attn2.to_v.weight:  23%|██▎       | 258/1131 [00:00<00:02, 318.47it/s]
ram used:  1.26 GB, model.diffusion_model.middle_block.1.transformer_blocks.0.attn2.to_out.0.weight:  23%|██▎       | 258/1131 [00:00<00:02, 318.47it/s]
ram used:  1.26 GB, model.diffusion_model.middle_block.1.transformer_blocks.0.attn2.to_out.0.bias:  23%|██▎       | 258/1131 [00:00<00:02, 318.47it/s]  
ram used:  1.26 GB, model.diffusion_model.middle_block.1.transformer_blocks.0.norm1.weight:  23%|██▎       | 258/1131 [00:00<00:02, 318.47it/s]       
ram used:  1.26 GB, model.diffusion_model.middle_block.1.transformer_blocks.0.norm1.bias:  23%|██▎       | 258/1131 [00:00<00:02, 318.47it/s]  
ram used:  1.26 GB, model.diffusion_model.middle_block.1.transformer_blocks.0.norm2.weight:  23%|██▎       | 258/1131 [00:00<00:02, 318.47it/s]
ram used:  1.26 GB, model.diffusion_model.middle_block.1.transformer_blocks.0.norm2.bias:  23%|██▎       | 258/1131 [00:00<00:02, 318.47it/s]  
ram used:  1.26 GB, model.diffusion_model.middle_block.1.transformer_blocks.0.norm3.weight:  23%|██▎       | 258/1131 [00:00<00:02, 318.47it/s]
ram used:  1.26 GB, model.diffusion_model.middle_block.1.transformer_blocks.0.norm3.bias:  23%|██▎       | 258/1131 [00:00<00:02, 318.47it/s]  
ram used:  1.26 GB, model.diffusion_model.middle_block.1.proj_out.weight:  23%|██▎       | 258/1131 [00:00<00:02, 318.47it/s]                
ram used:  1.27 GB, model.diffusion_model.middle_block.1.proj_out.bias:  23%|██▎       | 258/1131 [00:00<00:02, 318.47it/s]  
ram used:  1.27 GB, model.diffusion_model.middle_block.2.in_layers.0.weight:  23%|██▎       | 258/1131 [00:00<00:02, 318.47it/s]
ram used:  1.27 GB, model.diffusion_model.middle_block.2.in_layers.0.bias:  23%|██▎       | 258/1131 [00:00<00:02, 318.47it/s]  
ram used:  1.27 GB, model.diffusion_model.middle_block.2.in_layers.2.weight:  23%|██▎       | 258/1131 [00:00<00:02, 318.47it/s]
ram used:  1.33 GB, model.diffusion_model.middle_block.2.in_layers.2.bias:  23%|██▎       | 258/1131 [00:00<00:02, 318.47it/s]  
ram used:  1.33 GB, model.diffusion_model.middle_block.2.emb_layers.1.weight:  23%|██▎       | 258/1131 [00:00<00:02, 318.47it/s]
ram used:  1.34 GB, model.diffusion_model.middle_block.2.emb_layers.1.bias:  23%|██▎       | 258/1131 [00:00<00:02, 318.47it/s]  
ram used:  1.34 GB, model.diffusion_model.middle_block.2.emb_layers.1.bias:  26%|██▌       | 295/1131 [00:00<00:02, 317.60it/s]
ram used:  1.34 GB, model.diffusion_model.middle_block.2.out_layers.0.weight:  26%|██▌       | 295/1131 [00:00<00:02, 317.60it/s]
ram used:  1.34 GB, model.diffusion_model.middle_block.2.out_layers.0.bias:  26%|██▌       | 295/1131 [00:00<00:02, 317.60it/s]  
ram used:  1.34 GB, model.diffusion_model.middle_block.2.out_layers.3.weight:  26%|██▌       | 295/1131 [00:00<00:02, 317.60it/s]
ram used:  1.39 GB, model.diffusion_model.middle_block.2.out_layers.3.bias:  26%|██▌       | 295/1131 [00:01<00:02, 317.60it/s]  
ram used:  1.39 GB, model.diffusion_model.output_blocks.0.0.in_layers.0.weight:  26%|██▌       | 295/1131 [00:01<00:02, 317.60it/s]
ram used:  1.39 GB, model.diffusion_model.output_blocks.0.0.in_layers.0.bias:  26%|██▌       | 295/1131 [00:01<00:02, 317.60it/s]  
ram used:  1.39 GB, model.diffusion_model.output_blocks.0.0.in_layers.2.weight:  26%|██▌       | 295/1131 [00:01<00:02, 317.60it/s]
ram used:  1.51 GB, model.diffusion_model.output_blocks.0.0.in_layers.2.bias:  26%|██▌       | 295/1131 [00:01<00:02, 317.60it/s]  
ram used:  1.51 GB, model.diffusion_model.output_blocks.0.0.emb_layers.1.weight:  26%|██▌       | 295/1131 [00:01<00:02, 317.60it/s]
ram used:  1.52 GB, model.diffusion_model.output_blocks.0.0.emb_layers.1.bias:  26%|██▌       | 295/1131 [00:01<00:02, 317.60it/s]  
ram used:  1.52 GB, model.diffusion_model.output_blocks.0.0.out_layers.0.weight:  26%|██▌       | 295/1131 [00:01<00:02, 317.60it/s]
ram used:  1.52 GB, model.diffusion_model.output_blocks.0.0.out_layers.0.bias:  26%|██▌       | 295/1131 [00:01<00:02, 317.60it/s]  
ram used:  1.52 GB, model.diffusion_model.output_blocks.0.0.out_layers.3.weight:  26%|██▌       | 295/1131 [00:01<00:02, 317.60it/s]
ram used:  1.58 GB, model.diffusion_model.output_blocks.0.0.out_layers.3.bias:  26%|██▌       | 295/1131 [00:01<00:02, 317.60it/s]  
ram used:  1.58 GB, model.diffusion_model.output_blocks.0.0.skip_connection.weight:  26%|██▌       | 295/1131 [00:01<00:02, 317.60it/s]
ram used:  1.59 GB, model.diffusion_model.output_blocks.0.0.skip_connection.bias:  26%|██▌       | 295/1131 [00:01<00:02, 317.60it/s]  
ram used:  1.59 GB, model.diffusion_model.output_blocks.1.0.in_layers.0.weight:  26%|██▌       | 295/1131 [00:01<00:02, 317.60it/s]  
ram used:  1.59 GB, model.diffusion_model.output_blocks.1.0.in_layers.0.bias:  26%|██▌       | 295/1131 [00:01<00:02, 317.60it/s]  
ram used:  1.59 GB, model.diffusion_model.output_blocks.1.0.in_layers.2.weight:  26%|██▌       | 295/1131 [00:01<00:02, 317.60it/s]
ram used:  1.71 GB, model.diffusion_model.output_blocks.1.0.in_layers.2.bias:  26%|██▌       | 295/1131 [00:01<00:02, 317.60it/s]  
ram used:  1.71 GB, model.diffusion_model.output_blocks.1.0.emb_layers.1.weight:  26%|██▌       | 295/1131 [00:01<00:02, 317.60it/s]
ram used:  1.72 GB, model.diffusion_model.output_blocks.1.0.emb_layers.1.bias:  26%|██▌       | 295/1131 [00:01<00:02, 317.60it/s]  
ram used:  1.72 GB, model.diffusion_model.output_blocks.1.0.out_layers.0.weight:  26%|██▌       | 295/1131 [00:01<00:02, 317.60it/s]
ram used:  1.72 GB, model.diffusion_model.output_blocks.1.0.out_layers.0.bias:  26%|██▌       | 295/1131 [00:01<00:02, 317.60it/s]  
ram used:  1.72 GB, model.diffusion_model.output_blocks.1.0.out_layers.3.weight:  26%|██▌       | 295/1131 [00:01<00:02, 317.60it/s]
ram used:  1.78 GB, model.diffusion_model.output_blocks.1.0.out_layers.3.bias:  26%|██▌       | 295/1131 [00:01<00:02, 317.60it/s]  
ram used:  1.78 GB, model.diffusion_model.output_blocks.1.0.skip_connection.weight:  26%|██▌       | 295/1131 [00:01<00:02, 317.60it/s]
ram used:  1.79 GB, model.diffusion_model.output_blocks.1.0.skip_connection.bias:  26%|██▌       | 295/1131 [00:01<00:02, 317.60it/s]  
ram used:  1.79 GB, model.diffusion_model.output_blocks.2.0.in_layers.0.weight:  26%|██▌       | 295/1131 [00:01<00:02, 317.60it/s]  
ram used:  1.79 GB, model.diffusion_model.output_blocks.2.0.in_layers.0.bias:  26%|██▌       | 295/1131 [00:01<00:02, 317.60it/s]  
ram used:  1.79 GB, model.diffusion_model.output_blocks.2.0.in_layers.2.weight:  26%|██▌       | 295/1131 [00:01<00:02, 317.60it/s]
ram used:  1.91 GB, model.diffusion_model.output_blocks.2.0.in_layers.2.bias:  26%|██▌       | 295/1131 [00:01<00:02, 317.60it/s]  
ram used:  1.91 GB, model.diffusion_model.output_blocks.2.0.emb_layers.1.weight:  26%|██▌       | 295/1131 [00:01<00:02, 317.60it/s]
ram used:  1.91 GB, model.diffusion_model.output_blocks.2.0.emb_layers.1.bias:  26%|██▌       | 295/1131 [00:01<00:02, 317.60it/s]  
ram used:  1.91 GB, model.diffusion_model.output_blocks.2.0.out_layers.0.weight:  26%|██▌       | 295/1131 [00:01<00:02, 317.60it/s]
ram used:  1.91 GB, model.diffusion_model.output_blocks.2.0.out_layers.0.weight:  29%|██▉       | 330/1131 [00:01<00:03, 253.33it/s]
ram used:  1.91 GB, model.diffusion_model.output_blocks.2.0.out_layers.0.bias:  29%|██▉       | 330/1131 [00:01<00:03, 253.33it/s]  
ram used:  1.91 GB, model.diffusion_model.output_blocks.2.0.out_layers.3.weight:  29%|██▉       | 330/1131 [00:01<00:03, 253.33it/s]
ram used:  1.97 GB, model.diffusion_model.output_blocks.2.0.out_layers.3.bias:  29%|██▉       | 330/1131 [00:01<00:03, 253.33it/s]  
ram used:  1.97 GB, model.diffusion_model.output_blocks.2.0.skip_connection.weight:  29%|██▉       | 330/1131 [00:01<00:03, 253.33it/s]
ram used:  1.98 GB, model.diffusion_model.output_blocks.2.0.skip_connection.bias:  29%|██▉       | 330/1131 [00:01<00:03, 253.33it/s]  
ram used:  1.98 GB, model.diffusion_model.output_blocks.2.1.conv.weight:  29%|██▉       | 330/1131 [00:01<00:03, 253.33it/s]         
ram used:  2.04 GB, model.diffusion_model.output_blocks.2.1.conv.bias :  29%|██▉       | 330/1131 [00:01<00:03, 253.33it/s] 
ram used:  2.04 GB, model.diffusion_model.output_blocks.3.0.in_layers.0.weight:  29%|██▉       | 330/1131 [00:01<00:03, 253.33it/s]
ram used:  2.04 GB, model.diffusion_model.output_blocks.3.0.in_layers.0.bias:  29%|██▉       | 330/1131 [00:01<00:03, 253.33it/s]  
ram used:  2.04 GB, model.diffusion_model.output_blocks.3.0.in_layers.2.weight:  29%|██▉       | 330/1131 [00:01<00:03, 253.33it/s]
ram used:  2.16 GB, model.diffusion_model.output_blocks.3.0.in_layers.2.bias:  29%|██▉       | 330/1131 [00:01<00:03, 253.33it/s]  
ram used:  2.16 GB, model.diffusion_model.output_blocks.3.0.emb_layers.1.weight:  29%|██▉       | 330/1131 [00:01<00:03, 253.33it/s]
ram used:  2.17 GB, model.diffusion_model.output_blocks.3.0.emb_layers.1.bias:  29%|██▉       | 330/1131 [00:01<00:03, 253.33it/s]  
ram used:  2.17 GB, model.diffusion_model.output_blocks.3.0.out_layers.0.weight:  29%|██▉       | 330/1131 [00:01<00:03, 253.33it/s]
ram used:  2.17 GB, model.diffusion_model.output_blocks.3.0.out_layers.0.bias:  29%|██▉       | 330/1131 [00:01<00:03, 253.33it/s]  
ram used:  2.17 GB, model.diffusion_model.output_blocks.3.0.out_layers.3.weight:  29%|██▉       | 330/1131 [00:01<00:03, 253.33it/s]
ram used:  2.23 GB, model.diffusion_model.output_blocks.3.0.out_layers.3.bias:  29%|██▉       | 330/1131 [00:01<00:03, 253.33it/s]  
ram used:  2.23 GB, model.diffusion_model.output_blocks.3.0.skip_connection.weight:  29%|██▉       | 330/1131 [00:01<00:03, 253.33it/s]
ram used:  2.24 GB, model.diffusion_model.output_blocks.3.0.skip_connection.bias:  29%|██▉       | 330/1131 [00:01<00:03, 253.33it/s]  
ram used:  2.24 GB, model.diffusion_model.output_blocks.3.1.norm.weight:  29%|██▉       | 330/1131 [00:01<00:03, 253.33it/s]         
ram used:  2.24 GB, model.diffusion_model.output_blocks.3.1.norm.bias :  29%|██▉       | 330/1131 [00:01<00:03, 253.33it/s] 
ram used:  2.24 GB, model.diffusion_model.output_blocks.3.1.proj_in.weight:  29%|██▉       | 330/1131 [00:01<00:03, 253.33it/s]
ram used:  2.25 GB, model.diffusion_model.output_blocks.3.1.proj_in.bias:  29%|██▉       | 330/1131 [00:01<00:03, 253.33it/s]  
ram used:  2.25 GB, model.diffusion_model.output_blocks.3.1.transformer_blocks.0.attn1.to_q.weight:  29%|██▉       | 330/1131 [00:01<00:03, 253.33it/s]
ram used:  2.25 GB, model.diffusion_model.output_blocks.3.1.transformer_blocks.0.attn1.to_k.weight:  29%|██▉       | 330/1131 [00:01<00:03, 253.33it/s]
ram used:  2.26 GB, model.diffusion_model.output_blocks.3.1.transformer_blocks.0.attn1.to_v.weight:  29%|██▉       | 330/1131 [00:01<00:03, 253.33it/s]
ram used:  2.27 GB, model.diffusion_model.output_blocks.3.1.transformer_blocks.0.attn1.to_out.0.weight:  29%|██▉       | 330/1131 [00:01<00:03, 253.33it/s]
ram used:  2.27 GB, model.diffusion_model.output_blocks.3.1.transformer_blocks.0.attn1.to_out.0.bias:  29%|██▉       | 330/1131 [00:01<00:03, 253.33it/s]  
ram used:  2.27 GB, model.diffusion_model.output_blocks.3.1.transformer_blocks.0.ff.net.0.proj.weight:  29%|██▉       | 330/1131 [00:01<00:03, 253.33it/s]
ram used:  2.27 GB, model.diffusion_model.output_blocks.3.1.transformer_blocks.0.ff.net.0.proj.weight:  32%|███▏      | 359/1131 [00:01<00:03, 235.42it/s]
ram used:  2.33 GB, model.diffusion_model.output_blocks.3.1.transformer_blocks.0.ff.net.0.proj.bias:  32%|███▏      | 359/1131 [00:01<00:03, 235.42it/s]  
ram used:  2.33 GB, model.diffusion_model.output_blocks.3.1.transformer_blocks.0.ff.net.2.weight:  32%|███▏      | 359/1131 [00:01<00:03, 235.42it/s]   
ram used:  2.35 GB, model.diffusion_model.output_blocks.3.1.transformer_blocks.0.ff.net.2.bias:  32%|███▏      | 359/1131 [00:01<00:03, 235.42it/s]  
ram used:  2.35 GB, model.diffusion_model.output_blocks.3.1.transformer_blocks.0.attn2.to_q.weight:  32%|███▏      | 359/1131 [00:01<00:03, 235.42it/s]
ram used:  2.36 GB, model.diffusion_model.output_blocks.3.1.transformer_blocks.0.attn2.to_k.weight:  32%|███▏      | 359/1131 [00:01<00:03, 235.42it/s]
ram used:  2.36 GB, model.diffusion_model.output_blocks.3.1.transformer_blocks.0.attn2.to_v.weight:  32%|███▏      | 359/1131 [00:01<00:03, 235.42it/s]
ram used:  2.37 GB, model.diffusion_model.output_blocks.3.1.transformer_blocks.0.attn2.to_out.0.weight:  32%|███▏      | 359/1131 [00:01<00:03, 235.42it/s]
ram used:  2.37 GB, model.diffusion_model.output_blocks.3.1.transformer_blocks.0.attn2.to_out.0.bias:  32%|███▏      | 359/1131 [00:01<00:03, 235.42it/s]  
ram used:  2.37 GB, model.diffusion_model.output_blocks.3.1.transformer_blocks.0.norm1.weight:  32%|███▏      | 359/1131 [00:01<00:03, 235.42it/s]       
ram used:  2.37 GB, model.diffusion_model.output_blocks.3.1.transformer_blocks.0.norm1.bias:  32%|███▏      | 359/1131 [00:01<00:03, 235.42it/s]  
ram used:  2.37 GB, model.diffusion_model.output_blocks.3.1.transformer_blocks.0.norm2.weight:  32%|███▏      | 359/1131 [00:01<00:03, 235.42it/s]
ram used:  2.37 GB, model.diffusion_model.output_blocks.3.1.transformer_blocks.0.norm2.bias:  32%|███▏      | 359/1131 [00:01<00:03, 235.42it/s]  
ram used:  2.37 GB, model.diffusion_model.output_blocks.3.1.transformer_blocks.0.norm3.weight:  32%|███▏      | 359/1131 [00:01<00:03, 235.42it/s]
ram used:  2.37 GB, model.diffusion_model.output_blocks.3.1.transformer_blocks.0.norm3.bias:  32%|███▏      | 359/1131 [00:01<00:03, 235.42it/s]  
ram used:  2.37 GB, model.diffusion_model.output_blocks.3.1.proj_out.weight:  32%|███▏      | 359/1131 [00:01<00:03, 235.42it/s]                
ram used:  2.38 GB, model.diffusion_model.output_blocks.3.1.proj_out.bias:  32%|███▏      | 359/1131 [00:01<00:03, 235.42it/s]  
ram used:  2.38 GB, model.diffusion_model.output_blocks.4.0.in_layers.0.weight:  32%|███▏      | 359/1131 [00:01<00:03, 235.42it/s]
ram used:  2.38 GB, model.diffusion_model.output_blocks.4.0.in_layers.0.bias:  32%|███▏      | 359/1131 [00:01<00:03, 235.42it/s]  
ram used:  2.38 GB, model.diffusion_model.output_blocks.4.0.in_layers.2.weight:  32%|███▏      | 359/1131 [00:01<00:03, 235.42it/s]
ram used:  2.50 GB, model.diffusion_model.output_blocks.4.0.in_layers.2.bias:  32%|███▏      | 359/1131 [00:01<00:03, 235.42it/s]  
ram used:  2.50 GB, model.diffusion_model.output_blocks.4.0.emb_layers.1.weight:  32%|███▏      | 359/1131 [00:01<00:03, 235.42it/s]
ram used:  2.50 GB, model.diffusion_model.output_blocks.4.0.emb_layers.1.bias:  32%|███▏      | 359/1131 [00:01<00:03, 235.42it/s]  
ram used:  2.50 GB, model.diffusion_model.output_blocks.4.0.out_layers.0.weight:  32%|███▏      | 359/1131 [00:01<00:03, 235.42it/s]
ram used:  2.50 GB, model.diffusion_model.output_blocks.4.0.out_layers.0.bias:  32%|███▏      | 359/1131 [00:01<00:03, 235.42it/s]  
ram used:  2.50 GB, model.diffusion_model.output_blocks.4.0.out_layers.3.weight:  32%|███▏      | 359/1131 [00:01<00:03, 235.42it/s]
ram used:  2.56 GB, model.diffusion_model.output_blocks.4.0.out_layers.3.bias:  32%|███▏      | 359/1131 [00:01<00:03, 235.42it/s]  
ram used:  2.56 GB, model.diffusion_model.output_blocks.4.0.skip_connection.weight:  32%|███▏      | 359/1131 [00:01<00:03, 235.42it/s]
ram used:  2.56 GB, model.diffusion_model.output_blocks.4.0.skip_connection.weight:  34%|███▍      | 386/1131 [00:01<00:03, 242.62it/s]
ram used:  2.58 GB, model.diffusion_model.output_blocks.4.0.skip_connection.bias:  34%|███▍      | 386/1131 [00:01<00:03, 242.62it/s]  
ram used:  2.58 GB, model.diffusion_model.output_blocks.4.1.norm.weight:  34%|███▍      | 386/1131 [00:01<00:03, 242.62it/s]         
ram used:  2.58 GB, model.diffusion_model.output_blocks.4.1.norm.bias :  34%|███▍      | 386/1131 [00:01<00:03, 242.62it/s] 
ram used:  2.58 GB, model.diffusion_model.output_blocks.4.1.proj_in.weight:  34%|███▍      | 386/1131 [00:01<00:03, 242.62it/s]
ram used:  2.58 GB, model.diffusion_model.output_blocks.4.1.proj_in.bias:  34%|███▍      | 386/1131 [00:01<00:03, 242.62it/s]  
ram used:  2.58 GB, model.diffusion_model.output_blocks.4.1.transformer_blocks.0.attn1.to_q.weight:  34%|███▍      | 386/1131 [00:01<00:03, 242.62it/s]
ram used:  2.59 GB, model.diffusion_model.output_blocks.4.1.transformer_blocks.0.attn1.to_k.weight:  34%|███▍      | 386/1131 [00:01<00:03, 242.62it/s]
ram used:  2.60 GB, model.diffusion_model.output_blocks.4.1.transformer_blocks.0.attn1.to_v.weight:  34%|███▍      | 386/1131 [00:01<00:03, 242.62it/s]
ram used:  2.60 GB, model.diffusion_model.output_blocks.4.1.transformer_blocks.0.attn1.to_out.0.weight:  34%|███▍      | 386/1131 [00:01<00:03, 242.62it/s]
ram used:  2.61 GB, model.diffusion_model.output_blocks.4.1.transformer_blocks.0.attn1.to_out.0.bias:  34%|███▍      | 386/1131 [00:01<00:03, 242.62it/s]  
ram used:  2.61 GB, model.diffusion_model.output_blocks.4.1.transformer_blocks.0.ff.net.0.proj.weight:  34%|███▍      | 386/1131 [00:01<00:03, 242.62it/s]
ram used:  2.66 GB, model.diffusion_model.output_blocks.4.1.transformer_blocks.0.ff.net.0.proj.bias:  34%|███▍      | 386/1131 [00:01<00:03, 242.62it/s]  
ram used:  2.66 GB, model.diffusion_model.output_blocks.4.1.transformer_blocks.0.ff.net.2.weight:  34%|███▍      | 386/1131 [00:01<00:03, 242.62it/s]   
ram used:  2.69 GB, model.diffusion_model.output_blocks.4.1.transformer_blocks.0.ff.net.2.bias:  34%|███▍      | 386/1131 [00:01<00:03, 242.62it/s]  
ram used:  2.69 GB, model.diffusion_model.output_blocks.4.1.transformer_blocks.0.attn2.to_q.weight:  34%|███▍      | 386/1131 [00:01<00:03, 242.62it/s]
ram used:  2.69 GB, model.diffusion_model.output_blocks.4.1.transformer_blocks.0.attn2.to_k.weight:  34%|███▍      | 386/1131 [00:01<00:03, 242.62it/s]
ram used:  2.70 GB, model.diffusion_model.output_blocks.4.1.transformer_blocks.0.attn2.to_v.weight:  34%|███▍      | 386/1131 [00:01<00:03, 242.62it/s]
ram used:  2.70 GB, model.diffusion_model.output_blocks.4.1.transformer_blocks.0.attn2.to_out.0.weight:  34%|███▍      | 386/1131 [00:01<00:03, 242.62it/s]
ram used:  2.71 GB, model.diffusion_model.output_blocks.4.1.transformer_blocks.0.attn2.to_out.0.bias:  34%|███▍      | 386/1131 [00:01<00:03, 242.62it/s]  
ram used:  2.71 GB, model.diffusion_model.output_blocks.4.1.transformer_blocks.0.norm1.weight:  34%|███▍      | 386/1131 [00:01<00:03, 242.62it/s]       
ram used:  2.71 GB, model.diffusion_model.output_blocks.4.1.transformer_blocks.0.norm1.bias:  34%|███▍      | 386/1131 [00:01<00:03, 242.62it/s]  
ram used:  2.71 GB, model.diffusion_model.output_blocks.4.1.transformer_blocks.0.norm2.weight:  34%|███▍      | 386/1131 [00:01<00:03, 242.62it/s]
ram used:  2.71 GB, model.diffusion_model.output_blocks.4.1.transformer_blocks.0.norm2.bias:  34%|███▍      | 386/1131 [00:01<00:03, 242.62it/s]  
ram used:  2.71 GB, model.diffusion_model.output_blocks.4.1.transformer_blocks.0.norm3.weight:  34%|███▍      | 386/1131 [00:01<00:03, 242.62it/s]
ram used:  2.71 GB, model.diffusion_model.output_blocks.4.1.transformer_blocks.0.norm3.bias:  34%|███▍      | 386/1131 [00:01<00:03, 242.62it/s]  
ram used:  2.71 GB, model.diffusion_model.output_blocks.4.1.proj_out.weight:  34%|███▍      | 386/1131 [00:01<00:03, 242.62it/s]                
ram used:  2.72 GB, model.diffusion_model.output_blocks.4.1.proj_out.bias:  34%|███▍      | 386/1131 [00:01<00:03, 242.62it/s]  
ram used:  2.72 GB, model.diffusion_model.output_blocks.5.0.in_layers.0.weight:  34%|███▍      | 386/1131 [00:01<00:03, 242.62it/s]
ram used:  2.72 GB, model.diffusion_model.output_blocks.5.0.in_layers.0.bias:  34%|███▍      | 386/1131 [00:01<00:03, 242.62it/s]  
ram used:  2.72 GB, model.diffusion_model.output_blocks.5.0.in_layers.2.weight:  34%|███▍      | 386/1131 [00:01<00:03, 242.62it/s]
ram used:  2.80 GB, model.diffusion_model.output_blocks.5.0.in_layers.2.bias:  34%|███▍      | 386/1131 [00:01<00:03, 242.62it/s]  
ram used:  2.80 GB, model.diffusion_model.output_blocks.5.0.emb_layers.1.weight:  34%|███▍      | 386/1131 [00:01<00:03, 242.62it/s]
ram used:  2.81 GB, model.diffusion_model.output_blocks.5.0.emb_layers.1.bias:  34%|███▍      | 386/1131 [00:01<00:03, 242.62it/s]  
ram used:  2.81 GB, model.diffusion_model.output_blocks.5.0.emb_layers.1.bias:  37%|███▋      | 419/1131 [00:01<00:02, 263.28it/s]
ram used:  2.81 GB, model.diffusion_model.output_blocks.5.0.out_layers.0.weight:  37%|███▋      | 419/1131 [00:01<00:02, 263.28it/s]
ram used:  2.81 GB, model.diffusion_model.output_blocks.5.0.out_layers.0.bias:  37%|███▋      | 419/1131 [00:01<00:02, 263.28it/s]  
ram used:  2.81 GB, model.diffusion_model.output_blocks.5.0.out_layers.3.weight:  37%|███▋      | 419/1131 [00:01<00:02, 263.28it/s]
ram used:  2.87 GB, model.diffusion_model.output_blocks.5.0.out_layers.3.bias:  37%|███▋      | 419/1131 [00:01<00:02, 263.28it/s]  
ram used:  2.87 GB, model.diffusion_model.output_blocks.5.0.skip_connection.weight:  37%|███▋      | 419/1131 [00:01<00:02, 263.28it/s]
ram used:  2.88 GB, model.diffusion_model.output_blocks.5.0.skip_connection.bias:  37%|███▋      | 419/1131 [00:01<00:02, 263.28it/s]  
ram used:  2.88 GB, model.diffusion_model.output_blocks.5.1.norm.weight:  37%|███▋      | 419/1131 [00:01<00:02, 263.28it/s]         
ram used:  2.88 GB, model.diffusion_model.output_blocks.5.1.norm.bias :  37%|███▋      | 419/1131 [00:01<00:02, 263.28it/s] 
ram used:  2.88 GB, model.diffusion_model.output_blocks.5.1.proj_in.weight:  37%|███▋      | 419/1131 [00:01<00:02, 263.28it/s]
ram used:  2.89 GB, model.diffusion_model.output_blocks.5.1.proj_in.bias:  37%|███▋      | 419/1131 [00:01<00:02, 263.28it/s]  
ram used:  2.89 GB, model.diffusion_model.output_blocks.5.1.transformer_blocks.0.attn1.to_q.weight:  37%|███▋      | 419/1131 [00:01<00:02, 263.28it/s]
ram used:  2.89 GB, model.diffusion_model.output_blocks.5.1.transformer_blocks.0.attn1.to_k.weight:  37%|███▋      | 419/1131 [00:01<00:02, 263.28it/s]
ram used:  2.90 GB, model.diffusion_model.output_blocks.5.1.transformer_blocks.0.attn1.to_v.weight:  37%|███▋      | 419/1131 [00:01<00:02, 263.28it/s]
ram used:  2.91 GB, model.diffusion_model.output_blocks.5.1.transformer_blocks.0.attn1.to_out.0.weight:  37%|███▋      | 419/1131 [00:01<00:02, 263.28it/s]
ram used:  2.91 GB, model.diffusion_model.output_blocks.5.1.transformer_blocks.0.attn1.to_out.0.bias:  37%|███▋      | 419/1131 [00:01<00:02, 263.28it/s]  
ram used:  2.91 GB, model.diffusion_model.output_blocks.5.1.transformer_blocks.0.ff.net.0.proj.weight:  37%|███▋      | 419/1131 [00:01<00:02, 263.28it/s]
ram used:  2.96 GB, model.diffusion_model.output_blocks.5.1.transformer_blocks.0.ff.net.0.proj.bias:  37%|███▋      | 419/1131 [00:01<00:02, 263.28it/s]  
ram used:  2.96 GB, model.diffusion_model.output_blocks.5.1.transformer_blocks.0.ff.net.2.weight:  37%|███▋      | 419/1131 [00:01<00:02, 263.28it/s]   
ram used:  2.99 GB, model.diffusion_model.output_blocks.5.1.transformer_blocks.0.ff.net.2.bias:  37%|███▋      | 419/1131 [00:01<00:02, 263.28it/s]  
ram used:  2.99 GB, model.diffusion_model.output_blocks.5.1.transformer_blocks.0.attn2.to_q.weight:  37%|███▋      | 419/1131 [00:01<00:02, 263.28it/s]
ram used:  3.00 GB, model.diffusion_model.output_blocks.5.1.transformer_blocks.0.attn2.to_k.weight:  37%|███▋      | 419/1131 [00:01<00:02, 263.28it/s]
ram used:  3.00 GB, model.diffusion_model.output_blocks.5.1.transformer_blocks.0.attn2.to_v.weight:  37%|███▋      | 419/1131 [00:01<00:02, 263.28it/s]
ram used:  3.01 GB, model.diffusion_model.output_blocks.5.1.transformer_blocks.0.attn2.to_out.0.weight:  37%|███▋      | 419/1131 [00:01<00:02, 263.28it/s]
ram used:  3.01 GB, model.diffusion_model.output_blocks.5.1.transformer_blocks.0.attn2.to_out.0.bias:  37%|███▋      | 419/1131 [00:01<00:02, 263.28it/s]  
ram used:  3.01 GB, model.diffusion_model.output_blocks.5.1.transformer_blocks.0.norm1.weight:  37%|███▋      | 419/1131 [00:01<00:02, 263.28it/s]       
ram used:  3.01 GB, model.diffusion_model.output_blocks.5.1.transformer_blocks.0.norm1.bias:  37%|███▋      | 419/1131 [00:01<00:02, 263.28it/s]  
ram used:  3.01 GB, model.diffusion_model.output_blocks.5.1.transformer_blocks.0.norm2.weight:  37%|███▋      | 419/1131 [00:01<00:02, 263.28it/s]
ram used:  3.01 GB, model.diffusion_model.output_blocks.5.1.transformer_blocks.0.norm2.bias:  37%|███▋      | 419/1131 [00:01<00:02, 263.28it/s]  
ram used:  3.01 GB, model.diffusion_model.output_blocks.5.1.transformer_blocks.0.norm3.weight:  37%|███▋      | 419/1131 [00:01<00:02, 263.28it/s]
ram used:  3.01 GB, model.diffusion_model.output_blocks.5.1.transformer_blocks.0.norm3.bias:  37%|███▋      | 419/1131 [00:01<00:02, 263.28it/s]  
ram used:  3.01 GB, model.diffusion_model.output_blocks.5.1.proj_out.weight:  37%|███▋      | 419/1131 [00:01<00:02, 263.28it/s]                
ram used:  3.02 GB, model.diffusion_model.output_blocks.5.1.proj_out.bias:  37%|███▋      | 419/1131 [00:01<00:02, 263.28it/s]  
ram used:  3.02 GB, model.diffusion_model.output_blocks.5.2.conv.weight:  37%|███▋      | 419/1131 [00:01<00:02, 263.28it/s]  
ram used:  3.02 GB, model.diffusion_model.output_blocks.5.2.conv.weight:  40%|███▉      | 452/1131 [00:01<00:02, 274.21it/s]
ram used:  3.08 GB, model.diffusion_model.output_blocks.5.2.conv.bias :  40%|███▉      | 452/1131 [00:01<00:02, 274.21it/s] 
ram used:  3.08 GB, model.diffusion_model.output_blocks.6.0.in_layers.0.weight:  40%|███▉      | 452/1131 [00:01<00:02, 274.21it/s]
ram used:  3.08 GB, model.diffusion_model.output_blocks.6.0.in_layers.0.bias:  40%|███▉      | 452/1131 [00:01<00:02, 274.21it/s]  
ram used:  3.08 GB, model.diffusion_model.output_blocks.6.0.in_layers.2.weight:  40%|███▉      | 452/1131 [00:01<00:02, 274.21it/s]
ram used:  3.12 GB, model.diffusion_model.output_blocks.6.0.in_layers.2.bias:  40%|███▉      | 452/1131 [00:01<00:02, 274.21it/s]  
ram used:  3.12 GB, model.diffusion_model.output_blocks.6.0.emb_layers.1.weight:  40%|███▉      | 452/1131 [00:01<00:02, 274.21it/s]
ram used:  3.12 GB, model.diffusion_model.output_blocks.6.0.emb_layers.1.bias:  40%|███▉      | 452/1131 [00:01<00:02, 274.21it/s]  
ram used:  3.12 GB, model.diffusion_model.output_blocks.6.0.out_layers.0.weight:  40%|███▉      | 452/1131 [00:01<00:02, 274.21it/s]
ram used:  3.12 GB, model.diffusion_model.output_blocks.6.0.out_layers.0.bias:  40%|███▉      | 452/1131 [00:01<00:02, 274.21it/s]  
ram used:  3.12 GB, model.diffusion_model.output_blocks.6.0.out_layers.3.weight:  40%|███▉      | 452/1131 [00:01<00:02, 274.21it/s]
ram used:  3.14 GB, model.diffusion_model.output_blocks.6.0.out_layers.3.bias:  40%|███▉      | 452/1131 [00:01<00:02, 274.21it/s]  
ram used:  3.14 GB, model.diffusion_model.output_blocks.6.0.skip_connection.weight:  40%|███▉      | 452/1131 [00:01<00:02, 274.21it/s]
ram used:  3.14 GB, model.diffusion_model.output_blocks.6.0.skip_connection.bias:  40%|███▉      | 452/1131 [00:01<00:02, 274.21it/s]  
ram used:  3.14 GB, model.diffusion_model.output_blocks.6.1.norm.weight:  40%|███▉      | 452/1131 [00:01<00:02, 274.21it/s]         
ram used:  3.14 GB, model.diffusion_model.output_blocks.6.1.norm.bias :  40%|███▉      | 452/1131 [00:01<00:02, 274.21it/s] 
ram used:  3.14 GB, model.diffusion_model.output_blocks.6.1.proj_in.weight:  40%|███▉      | 452/1131 [00:01<00:02, 274.21it/s]
ram used:  3.15 GB, model.diffusion_model.output_blocks.6.1.proj_in.bias:  40%|███▉      | 452/1131 [00:01<00:02, 274.21it/s]  
ram used:  3.15 GB, model.diffusion_model.output_blocks.6.1.transformer_blocks.0.attn1.to_q.weight:  40%|███▉      | 452/1131 [00:01<00:02, 274.21it/s]
ram used:  3.15 GB, model.diffusion_model.output_blocks.6.1.transformer_blocks.0.attn1.to_k.weight:  40%|███▉      | 452/1131 [00:01<00:02, 274.21it/s]
ram used:  3.15 GB, model.diffusion_model.output_blocks.6.1.transformer_blocks.0.attn1.to_v.weight:  40%|███▉      | 452/1131 [00:01<00:02, 274.21it/s]
ram used:  3.15 GB, model.diffusion_model.output_blocks.6.1.transformer_blocks.0.attn1.to_out.0.weight:  40%|███▉      | 452/1131 [00:01<00:02, 274.21it/s]
ram used:  3.15 GB, model.diffusion_model.output_blocks.6.1.transformer_blocks.0.attn1.to_out.0.bias:  40%|███▉      | 452/1131 [00:01<00:02, 274.21it/s]  
ram used:  3.15 GB, model.diffusion_model.output_blocks.6.1.transformer_blocks.0.ff.net.0.proj.weight:  40%|███▉      | 452/1131 [00:01<00:02, 274.21it/s]
ram used:  3.17 GB, model.diffusion_model.output_blocks.6.1.transformer_blocks.0.ff.net.0.proj.bias:  40%|███▉      | 452/1131 [00:01<00:02, 274.21it/s]  
ram used:  3.17 GB, model.diffusion_model.output_blocks.6.1.transformer_blocks.0.ff.net.2.weight:  40%|███▉      | 452/1131 [00:01<00:02, 274.21it/s]   
ram used:  3.17 GB, model.diffusion_model.output_blocks.6.1.transformer_blocks.0.ff.net.2.bias:  40%|███▉      | 452/1131 [00:01<00:02, 274.21it/s]  
ram used:  3.17 GB, model.diffusion_model.output_blocks.6.1.transformer_blocks.0.attn2.to_q.weight:  40%|███▉      | 452/1131 [00:01<00:02, 274.21it/s]
ram used:  3.17 GB, model.diffusion_model.output_blocks.6.1.transformer_blocks.0.attn2.to_k.weight:  40%|███▉      | 452/1131 [00:01<00:02, 274.21it/s]
ram used:  3.18 GB, model.diffusion_model.output_blocks.6.1.transformer_blocks.0.attn2.to_v.weight:  40%|███▉      | 452/1131 [00:01<00:02, 274.21it/s]
ram used:  3.18 GB, model.diffusion_model.output_blocks.6.1.transformer_blocks.0.attn2.to_out.0.weight:  40%|███▉      | 452/1131 [00:01<00:02, 274.21it/s]
ram used:  3.18 GB, model.diffusion_model.output_blocks.6.1.transformer_blocks.0.attn2.to_out.0.bias:  40%|███▉      | 452/1131 [00:01<00:02, 274.21it/s]  
ram used:  3.18 GB, model.diffusion_model.output_blocks.6.1.transformer_blocks.0.norm1.weight:  40%|███▉      | 452/1131 [00:01<00:02, 274.21it/s]       
ram used:  3.18 GB, model.diffusion_model.output_blocks.6.1.transformer_blocks.0.norm1.bias:  40%|███▉      | 452/1131 [00:01<00:02, 274.21it/s]  
ram used:  3.18 GB, model.diffusion_model.output_blocks.6.1.transformer_blocks.0.norm2.weight:  40%|███▉      | 452/1131 [00:01<00:02, 274.21it/s]
ram used:  3.18 GB, model.diffusion_model.output_blocks.6.1.transformer_blocks.0.norm2.bias:  40%|███▉      | 452/1131 [00:01<00:02, 274.21it/s]  
ram used:  3.18 GB, model.diffusion_model.output_blocks.6.1.transformer_blocks.0.norm3.weight:  40%|███▉      | 452/1131 [00:01<00:02, 274.21it/s]
ram used:  3.18 GB, model.diffusion_model.output_blocks.6.1.transformer_blocks.0.norm3.bias:  40%|███▉      | 452/1131 [00:01<00:02, 274.21it/s]  
ram used:  3.18 GB, model.diffusion_model.output_blocks.6.1.proj_out.weight:  40%|███▉      | 452/1131 [00:01<00:02, 274.21it/s]                
ram used:  3.18 GB, model.diffusion_model.output_blocks.6.1.proj_out.bias:  40%|███▉      | 452/1131 [00:01<00:02, 274.21it/s]  
ram used:  3.18 GB, model.diffusion_model.output_blocks.7.0.in_layers.0.weight:  40%|███▉      | 452/1131 [00:01<00:02, 274.21it/s]
ram used:  3.18 GB, model.diffusion_model.output_blocks.7.0.in_layers.0.bias:  40%|███▉      | 452/1131 [00:01<00:02, 274.21it/s]  
ram used:  3.18 GB, model.diffusion_model.output_blocks.7.0.in_layers.2.weight:  40%|███▉      | 452/1131 [00:01<00:02, 274.21it/s]
ram used:  3.21 GB, model.diffusion_model.output_blocks.7.0.in_layers.2.bias:  40%|███▉      | 452/1131 [00:01<00:02, 274.21it/s]  
ram used:  3.21 GB, model.diffusion_model.output_blocks.7.0.emb_layers.1.weight:  40%|███▉      | 452/1131 [00:01<00:02, 274.21it/s]
ram used:  3.21 GB, model.diffusion_model.output_blocks.7.0.emb_layers.1.bias:  40%|███▉      | 452/1131 [00:01<00:02, 274.21it/s]  
ram used:  3.21 GB, model.diffusion_model.output_blocks.7.0.out_layers.0.weight:  40%|███▉      | 452/1131 [00:01<00:02, 274.21it/s]
ram used:  3.21 GB, model.diffusion_model.output_blocks.7.0.out_layers.0.bias:  40%|███▉      | 452/1131 [00:01<00:02, 274.21it/s]  
ram used:  3.21 GB, model.diffusion_model.output_blocks.7.0.out_layers.3.weight:  40%|███▉      | 452/1131 [00:01<00:02, 274.21it/s]
ram used:  3.23 GB, model.diffusion_model.output_blocks.7.0.out_layers.3.bias:  40%|███▉      | 452/1131 [00:01<00:02, 274.21it/s]  
ram used:  3.23 GB, model.diffusion_model.output_blocks.7.0.skip_connection.weight:  40%|███▉      | 452/1131 [00:01<00:02, 274.21it/s]
ram used:  3.23 GB, model.diffusion_model.output_blocks.7.0.skip_connection.bias:  40%|███▉      | 452/1131 [00:01<00:02, 274.21it/s]  
ram used:  3.23 GB, model.diffusion_model.output_blocks.7.1.norm.weight:  40%|███▉      | 452/1131 [00:01<00:02, 274.21it/s]         
ram used:  3.23 GB, model.diffusion_model.output_blocks.7.1.norm.bias :  40%|███▉      | 452/1131 [00:01<00:02, 274.21it/s] 
ram used:  3.23 GB, model.diffusion_model.output_blocks.7.1.proj_in.weight:  40%|███▉      | 452/1131 [00:01<00:02, 274.21it/s]
ram used:  3.23 GB, model.diffusion_model.output_blocks.7.1.proj_in.bias:  40%|███▉      | 452/1131 [00:01<00:02, 274.21it/s]  
ram used:  3.23 GB, model.diffusion_model.output_blocks.7.1.transformer_blocks.0.attn1.to_q.weight:  40%|███▉      | 452/1131 [00:01<00:02, 274.21it/s]
ram used:  3.24 GB, model.diffusion_model.output_blocks.7.1.transformer_blocks.0.attn1.to_k.weight:  40%|███▉      | 452/1131 [00:01<00:02, 274.21it/s]
ram used:  3.24 GB, model.diffusion_model.output_blocks.7.1.transformer_blocks.0.attn1.to_v.weight:  40%|███▉      | 452/1131 [00:01<00:02, 274.21it/s]
ram used:  3.24 GB, model.diffusion_model.output_blocks.7.1.transformer_blocks.0.attn1.to_out.0.weight:  40%|███▉      | 452/1131 [00:01<00:02, 274.21it/s]
ram used:  3.24 GB, model.diffusion_model.output_blocks.7.1.transformer_blocks.0.attn1.to_out.0.bias:  40%|███▉      | 452/1131 [00:01<00:02, 274.21it/s]  
ram used:  3.24 GB, model.diffusion_model.output_blocks.7.1.transformer_blocks.0.ff.net.0.proj.weight:  40%|███▉      | 452/1131 [00:01<00:02, 274.21it/s]
ram used:  3.24 GB, model.diffusion_model.output_blocks.7.1.transformer_blocks.0.ff.net.0.proj.weight:  45%|████▌     | 513/1131 [00:01<00:01, 357.60it/s]
ram used:  3.25 GB, model.diffusion_model.output_blocks.7.1.transformer_blocks.0.ff.net.0.proj.bias:  45%|████▌     | 513/1131 [00:01<00:01, 357.60it/s]  
ram used:  3.25 GB, model.diffusion_model.output_blocks.7.1.transformer_blocks.0.ff.net.2.weight:  45%|████▌     | 513/1131 [00:01<00:01, 357.60it/s]   
ram used:  3.26 GB, model.diffusion_model.output_blocks.7.1.transformer_blocks.0.ff.net.2.bias:  45%|████▌     | 513/1131 [00:01<00:01, 357.60it/s]  
ram used:  3.26 GB, model.diffusion_model.output_blocks.7.1.transformer_blocks.0.attn2.to_q.weight:  45%|████▌     | 513/1131 [00:01<00:01, 357.60it/s]
ram used:  3.26 GB, model.diffusion_model.output_blocks.7.1.transformer_blocks.0.attn2.to_k.weight:  45%|████▌     | 513/1131 [00:01<00:01, 357.60it/s]
ram used:  3.26 GB, model.diffusion_model.output_blocks.7.1.transformer_blocks.0.attn2.to_v.weight:  45%|████▌     | 513/1131 [00:01<00:01, 357.60it/s]
ram used:  3.27 GB, model.diffusion_model.output_blocks.7.1.transformer_blocks.0.attn2.to_out.0.weight:  45%|████▌     | 513/1131 [00:01<00:01, 357.60it/s]
ram used:  3.27 GB, model.diffusion_model.output_blocks.7.1.transformer_blocks.0.attn2.to_out.0.bias:  45%|████▌     | 513/1131 [00:01<00:01, 357.60it/s]  
ram used:  3.27 GB, model.diffusion_model.output_blocks.7.1.transformer_blocks.0.norm1.weight:  45%|████▌     | 513/1131 [00:01<00:01, 357.60it/s]       
ram used:  3.27 GB, model.diffusion_model.output_blocks.7.1.transformer_blocks.0.norm1.bias:  45%|████▌     | 513/1131 [00:01<00:01, 357.60it/s]  
ram used:  3.27 GB, model.diffusion_model.output_blocks.7.1.transformer_blocks.0.norm2.weight:  45%|████▌     | 513/1131 [00:01<00:01, 357.60it/s]
ram used:  3.27 GB, model.diffusion_model.output_blocks.7.1.transformer_blocks.0.norm2.bias:  45%|████▌     | 513/1131 [00:01<00:01, 357.60it/s]  
ram used:  3.27 GB, model.diffusion_model.output_blocks.7.1.transformer_blocks.0.norm3.weight:  45%|████▌     | 513/1131 [00:01<00:01, 357.60it/s]
ram used:  3.27 GB, model.diffusion_model.output_blocks.7.1.transformer_blocks.0.norm3.bias:  45%|████▌     | 513/1131 [00:01<00:01, 357.60it/s]  
ram used:  3.27 GB, model.diffusion_model.output_blocks.7.1.proj_out.weight:  45%|████▌     | 513/1131 [00:01<00:01, 357.60it/s]                
ram used:  3.27 GB, model.diffusion_model.output_blocks.7.1.proj_out.bias:  45%|████▌     | 513/1131 [00:01<00:01, 357.60it/s]  
ram used:  3.27 GB, model.diffusion_model.output_blocks.8.0.in_layers.0.weight:  45%|████▌     | 513/1131 [00:01<00:01, 357.60it/s]
ram used:  3.27 GB, model.diffusion_model.output_blocks.8.0.in_layers.0.bias:  45%|████▌     | 513/1131 [00:01<00:01, 357.60it/s]  
ram used:  3.27 GB, model.diffusion_model.output_blocks.8.0.in_layers.2.weight:  45%|████▌     | 513/1131 [00:01<00:01, 357.60it/s]
ram used:  3.29 GB, model.diffusion_model.output_blocks.8.0.in_layers.2.bias:  45%|████▌     | 513/1131 [00:01<00:01, 357.60it/s]  
ram used:  3.29 GB, model.diffusion_model.output_blocks.8.0.emb_layers.1.weight:  45%|████▌     | 513/1131 [00:01<00:01, 357.60it/s]
ram used:  3.29 GB, model.diffusion_model.output_blocks.8.0.emb_layers.1.bias:  45%|████▌     | 513/1131 [00:01<00:01, 357.60it/s]  
ram used:  3.29 GB, model.diffusion_model.output_blocks.8.0.out_layers.0.weight:  45%|████▌     | 513/1131 [00:01<00:01, 357.60it/s]
ram used:  3.29 GB, model.diffusion_model.output_blocks.8.0.out_layers.0.bias:  45%|████▌     | 513/1131 [00:01<00:01, 357.60it/s]  
ram used:  3.29 GB, model.diffusion_model.output_blocks.8.0.out_layers.3.weight:  45%|████▌     | 513/1131 [00:01<00:01, 357.60it/s]
ram used:  3.31 GB, model.diffusion_model.output_blocks.8.0.out_layers.3.bias:  45%|████▌     | 513/1131 [00:01<00:01, 357.60it/s]  
ram used:  3.31 GB, model.diffusion_model.output_blocks.8.0.skip_connection.weight:  45%|████▌     | 513/1131 [00:01<00:01, 357.60it/s]
ram used:  3.31 GB, model.diffusion_model.output_blocks.8.0.skip_connection.bias:  45%|████▌     | 513/1131 [00:01<00:01, 357.60it/s]  
ram used:  3.31 GB, model.diffusion_model.output_blocks.8.1.norm.weight:  45%|████▌     | 513/1131 [00:01<00:01, 357.60it/s]         
ram used:  3.31 GB, model.diffusion_model.output_blocks.8.1.norm.bias :  45%|████▌     | 513/1131 [00:01<00:01, 357.60it/s] 
ram used:  3.31 GB, model.diffusion_model.output_blocks.8.1.proj_in.weight:  45%|████▌     | 513/1131 [00:01<00:01, 357.60it/s]
ram used:  3.31 GB, model.diffusion_model.output_blocks.8.1.proj_in.bias:  45%|████▌     | 513/1131 [00:01<00:01, 357.60it/s]  
ram used:  3.31 GB, model.diffusion_model.output_blocks.8.1.transformer_blocks.0.attn1.to_q.weight:  45%|████▌     | 513/1131 [00:01<00:01, 357.60it/s]
ram used:  3.31 GB, model.diffusion_model.output_blocks.8.1.transformer_blocks.0.attn1.to_k.weight:  45%|████▌     | 513/1131 [00:01<00:01, 357.60it/s]
ram used:  3.32 GB, model.diffusion_model.output_blocks.8.1.transformer_blocks.0.attn1.to_v.weight:  45%|████▌     | 513/1131 [00:01<00:01, 357.60it/s]
ram used:  3.32 GB, model.diffusion_model.output_blocks.8.1.transformer_blocks.0.attn1.to_out.0.weight:  45%|████▌     | 513/1131 [00:01<00:01, 357.60it/s]
ram used:  3.32 GB, model.diffusion_model.output_blocks.8.1.transformer_blocks.0.attn1.to_out.0.bias:  45%|████▌     | 513/1131 [00:01<00:01, 357.60it/s]  
ram used:  3.32 GB, model.diffusion_model.output_blocks.8.1.transformer_blocks.0.ff.net.0.proj.weight:  45%|████▌     | 513/1131 [00:01<00:01, 357.60it/s]
ram used:  3.33 GB, model.diffusion_model.output_blocks.8.1.transformer_blocks.0.ff.net.0.proj.bias:  45%|████▌     | 513/1131 [00:01<00:01, 357.60it/s]  
ram used:  3.33 GB, model.diffusion_model.output_blocks.8.1.transformer_blocks.0.ff.net.2.weight:  45%|████▌     | 513/1131 [00:01<00:01, 357.60it/s]   
ram used:  3.34 GB, model.diffusion_model.output_blocks.8.1.transformer_blocks.0.ff.net.2.bias:  45%|████▌     | 513/1131 [00:01<00:01, 357.60it/s]  
ram used:  3.34 GB, model.diffusion_model.output_blocks.8.1.transformer_blocks.0.attn2.to_q.weight:  45%|████▌     | 513/1131 [00:01<00:01, 357.60it/s]
ram used:  3.34 GB, model.diffusion_model.output_blocks.8.1.transformer_blocks.0.attn2.to_k.weight:  45%|████▌     | 513/1131 [00:01<00:01, 357.60it/s]
ram used:  3.34 GB, model.diffusion_model.output_blocks.8.1.transformer_blocks.0.attn2.to_v.weight:  45%|████▌     | 513/1131 [00:01<00:01, 357.60it/s]
ram used:  3.34 GB, model.diffusion_model.output_blocks.8.1.transformer_blocks.0.attn2.to_out.0.weight:  45%|████▌     | 513/1131 [00:01<00:01, 357.60it/s]
ram used:  3.35 GB, model.diffusion_model.output_blocks.8.1.transformer_blocks.0.attn2.to_out.0.bias:  45%|████▌     | 513/1131 [00:01<00:01, 357.60it/s]  
ram used:  3.35 GB, model.diffusion_model.output_blocks.8.1.transformer_blocks.0.norm1.weight:  45%|████▌     | 513/1131 [00:01<00:01, 357.60it/s]       
ram used:  3.35 GB, model.diffusion_model.output_blocks.8.1.transformer_blocks.0.norm1.bias:  45%|████▌     | 513/1131 [00:01<00:01, 357.60it/s]  
ram used:  3.35 GB, model.diffusion_model.output_blocks.8.1.transformer_blocks.0.norm2.weight:  45%|████▌     | 513/1131 [00:01<00:01, 357.60it/s]
ram used:  3.35 GB, model.diffusion_model.output_blocks.8.1.transformer_blocks.0.norm2.bias:  45%|████▌     | 513/1131 [00:01<00:01, 357.60it/s]  
ram used:  3.35 GB, model.diffusion_model.output_blocks.8.1.transformer_blocks.0.norm3.weight:  45%|████▌     | 513/1131 [00:01<00:01, 357.60it/s]
ram used:  3.35 GB, model.diffusion_model.output_blocks.8.1.transformer_blocks.0.norm3.bias:  45%|████▌     | 513/1131 [00:01<00:01, 357.60it/s]  
ram used:  3.35 GB, model.diffusion_model.output_blocks.8.1.proj_out.weight:  45%|████▌     | 513/1131 [00:01<00:01, 357.60it/s]                
ram used:  3.35 GB, model.diffusion_model.output_blocks.8.1.proj_out.bias:  45%|████▌     | 513/1131 [00:01<00:01, 357.60it/s]  
ram used:  3.35 GB, model.diffusion_model.output_blocks.8.2.conv.weight:  45%|████▌     | 513/1131 [00:01<00:01, 357.60it/s]  
ram used:  3.36 GB, model.diffusion_model.output_blocks.8.2.conv.bias :  45%|████▌     | 513/1131 [00:01<00:01, 357.60it/s] 
ram used:  3.36 GB, model.diffusion_model.output_blocks.9.0.in_layers.0.weight:  45%|████▌     | 513/1131 [00:01<00:01, 357.60it/s]
ram used:  3.36 GB, model.diffusion_model.output_blocks.9.0.in_layers.0.bias:  45%|████▌     | 513/1131 [00:01<00:01, 357.60it/s]  
ram used:  3.36 GB, model.diffusion_model.output_blocks.9.0.in_layers.2.weight:  45%|████▌     | 513/1131 [00:01<00:01, 357.60it/s]
ram used:  3.37 GB, model.diffusion_model.output_blocks.9.0.in_layers.2.bias:  45%|████▌     | 513/1131 [00:01<00:01, 357.60it/s]  
ram used:  3.37 GB, model.diffusion_model.output_blocks.9.0.emb_layers.1.weight:  45%|████▌     | 513/1131 [00:01<00:01, 357.60it/s]
ram used:  3.38 GB, model.diffusion_model.output_blocks.9.0.emb_layers.1.bias:  45%|████▌     | 513/1131 [00:01<00:01, 357.60it/s]  
ram used:  3.38 GB, model.diffusion_model.output_blocks.9.0.out_layers.0.weight:  45%|████▌     | 513/1131 [00:01<00:01, 357.60it/s]
ram used:  3.38 GB, model.diffusion_model.output_blocks.9.0.out_layers.0.bias:  45%|████▌     | 513/1131 [00:01<00:01, 357.60it/s]  
ram used:  3.38 GB, model.diffusion_model.output_blocks.9.0.out_layers.3.weight:  45%|████▌     | 513/1131 [00:01<00:01, 357.60it/s]
ram used:  3.38 GB, model.diffusion_model.output_blocks.9.0.out_layers.3.bias:  45%|████▌     | 513/1131 [00:01<00:01, 357.60it/s]  
ram used:  3.38 GB, model.diffusion_model.output_blocks.9.0.skip_connection.weight:  45%|████▌     | 513/1131 [00:01<00:01, 357.60it/s]
ram used:  3.38 GB, model.diffusion_model.output_blocks.9.0.skip_connection.bias:  45%|████▌     | 513/1131 [00:01<00:01, 357.60it/s]  
ram used:  3.38 GB, model.diffusion_model.output_blocks.9.1.norm.weight:  45%|████▌     | 513/1131 [00:01<00:01, 357.60it/s]         
ram used:  3.38 GB, model.diffusion_model.output_blocks.9.1.norm.bias :  45%|████▌     | 513/1131 [00:01<00:01, 357.60it/s] 
ram used:  3.38 GB, model.diffusion_model.output_blocks.9.1.proj_in.weight:  45%|████▌     | 513/1131 [00:01<00:01, 357.60it/s]
ram used:  3.38 GB, model.diffusion_model.output_blocks.9.1.proj_in.bias:  45%|████▌     | 513/1131 [00:01<00:01, 357.60it/s]  
ram used:  3.38 GB, model.diffusion_model.output_blocks.9.1.transformer_blocks.0.attn1.to_q.weight:  45%|████▌     | 513/1131 [00:01<00:01, 357.60it/s]
ram used:  3.38 GB, model.diffusion_model.output_blocks.9.1.transformer_blocks.0.attn1.to_k.weight:  45%|████▌     | 513/1131 [00:01<00:01, 357.60it/s]
ram used:  3.38 GB, model.diffusion_model.output_blocks.9.1.transformer_blocks.0.attn1.to_v.weight:  45%|████▌     | 513/1131 [00:01<00:01, 357.60it/s]
ram used:  3.38 GB, model.diffusion_model.output_blocks.9.1.transformer_blocks.0.attn1.to_out.0.weight:  45%|████▌     | 513/1131 [00:01<00:01, 357.60it/s]
ram used:  3.38 GB, model.diffusion_model.output_blocks.9.1.transformer_blocks.0.attn1.to_out.0.bias:  45%|████▌     | 513/1131 [00:01<00:01, 357.60it/s]  
ram used:  3.38 GB, model.diffusion_model.output_blocks.9.1.transformer_blocks.0.ff.net.0.proj.weight:  45%|████▌     | 513/1131 [00:01<00:01, 357.60it/s]
ram used:  3.39 GB, model.diffusion_model.output_blocks.9.1.transformer_blocks.0.ff.net.0.proj.bias:  45%|████▌     | 513/1131 [00:01<00:01, 357.60it/s]  
ram used:  3.39 GB, model.diffusion_model.output_blocks.9.1.transformer_blocks.0.ff.net.2.weight:  45%|████▌     | 513/1131 [00:01<00:01, 357.60it/s]   
ram used:  3.39 GB, model.diffusion_model.output_blocks.9.1.transformer_blocks.0.ff.net.2.bias:  45%|████▌     | 513/1131 [00:01<00:01, 357.60it/s]  
ram used:  3.39 GB, model.diffusion_model.output_blocks.9.1.transformer_blocks.0.attn2.to_q.weight:  45%|████▌     | 513/1131 [00:01<00:01, 357.60it/s]
ram used:  3.39 GB, model.diffusion_model.output_blocks.9.1.transformer_blocks.0.attn2.to_k.weight:  45%|████▌     | 513/1131 [00:01<00:01, 357.60it/s]
ram used:  3.39 GB, model.diffusion_model.output_blocks.9.1.transformer_blocks.0.attn2.to_v.weight:  45%|████▌     | 513/1131 [00:01<00:01, 357.60it/s]
ram used:  3.39 GB, model.diffusion_model.output_blocks.9.1.transformer_blocks.0.attn2.to_v.weight:  53%|█████▎    | 597/1131 [00:01<00:01, 487.47it/s]
ram used:  3.39 GB, model.diffusion_model.output_blocks.9.1.transformer_blocks.0.attn2.to_out.0.weight:  53%|█████▎    | 597/1131 [00:01<00:01, 487.47it/s]
ram used:  3.39 GB, model.diffusion_model.output_blocks.9.1.transformer_blocks.0.attn2.to_out.0.bias:  53%|█████▎    | 597/1131 [00:01<00:01, 487.47it/s]  
ram used:  3.39 GB, model.diffusion_model.output_blocks.9.1.transformer_blocks.0.norm1.weight:  53%|█████▎    | 597/1131 [00:01<00:01, 487.47it/s]       
ram used:  3.39 GB, model.diffusion_model.output_blocks.9.1.transformer_blocks.0.norm1.bias:  53%|█████▎    | 597/1131 [00:01<00:01, 487.47it/s]  
ram used:  3.39 GB, model.diffusion_model.output_blocks.9.1.transformer_blocks.0.norm2.weight:  53%|█████▎    | 597/1131 [00:01<00:01, 487.47it/s]
ram used:  3.39 GB, model.diffusion_model.output_blocks.9.1.transformer_blocks.0.norm2.bias:  53%|█████▎    | 597/1131 [00:01<00:01, 487.47it/s]  
ram used:  3.39 GB, model.diffusion_model.output_blocks.9.1.transformer_blocks.0.norm3.weight:  53%|█████▎    | 597/1131 [00:01<00:01, 487.47it/s]
ram used:  3.39 GB, model.diffusion_model.output_blocks.9.1.transformer_blocks.0.norm3.bias:  53%|█████▎    | 597/1131 [00:01<00:01, 487.47it/s]  
ram used:  3.39 GB, model.diffusion_model.output_blocks.9.1.proj_out.weight:  53%|█████▎    | 597/1131 [00:01<00:01, 487.47it/s]                
ram used:  3.39 GB, model.diffusion_model.output_blocks.9.1.proj_out.bias:  53%|█████▎    | 597/1131 [00:01<00:01, 487.47it/s]  
ram used:  3.39 GB, model.diffusion_model.output_blocks.10.0.in_layers.0.weight:  53%|█████▎    | 597/1131 [00:01<00:01, 487.47it/s]
ram used:  3.39 GB, model.diffusion_model.output_blocks.10.0.in_layers.0.bias:  53%|█████▎    | 597/1131 [00:01<00:01, 487.47it/s]  
ram used:  3.39 GB, model.diffusion_model.output_blocks.10.0.in_layers.2.weight:  53%|█████▎    | 597/1131 [00:01<00:01, 487.47it/s]
ram used:  3.40 GB, model.diffusion_model.output_blocks.10.0.in_layers.2.bias:  53%|█████▎    | 597/1131 [00:01<00:01, 487.47it/s]  
ram used:  3.40 GB, model.diffusion_model.output_blocks.10.0.emb_layers.1.weight:  53%|█████▎    | 597/1131 [00:01<00:01, 487.47it/s]
ram used:  3.40 GB, model.diffusion_model.output_blocks.10.0.emb_layers.1.bias:  53%|█████▎    | 597/1131 [00:01<00:01, 487.47it/s]  
ram used:  3.40 GB, model.diffusion_model.output_blocks.10.0.out_layers.0.weight:  53%|█████▎    | 597/1131 [00:01<00:01, 487.47it/s]
ram used:  3.40 GB, model.diffusion_model.output_blocks.10.0.out_layers.0.bias:  53%|█████▎    | 597/1131 [00:01<00:01, 487.47it/s]  
ram used:  3.40 GB, model.diffusion_model.output_blocks.10.0.out_layers.3.weight:  53%|█████▎    | 597/1131 [00:01<00:01, 487.47it/s]
ram used:  3.40 GB, model.diffusion_model.output_blocks.10.0.out_layers.3.bias:  53%|█████▎    | 597/1131 [00:01<00:01, 487.47it/s]  
ram used:  3.40 GB, model.diffusion_model.output_blocks.10.0.skip_connection.weight:  53%|█████▎    | 597/1131 [00:01<00:01, 487.47it/s]
ram used:  3.40 GB, model.diffusion_model.output_blocks.10.0.skip_connection.bias:  53%|█████▎    | 597/1131 [00:01<00:01, 487.47it/s]  
ram used:  3.40 GB, model.diffusion_model.output_blocks.10.1.norm.weight:  53%|█████▎    | 597/1131 [00:01<00:01, 487.47it/s]         
ram used:  3.40 GB, model.diffusion_model.output_blocks.10.1.norm.bias:  53%|█████▎    | 597/1131 [00:01<00:01, 487.47it/s]  
ram used:  3.40 GB, model.diffusion_model.output_blocks.10.1.proj_in.weight:  53%|█████▎    | 597/1131 [00:01<00:01, 487.47it/s]
ram used:  3.40 GB, model.diffusion_model.output_blocks.10.1.proj_in.bias:  53%|█████▎    | 597/1131 [00:01<00:01, 487.47it/s]  
ram used:  3.40 GB, model.diffusion_model.output_blocks.10.1.transformer_blocks.0.attn1.to_q.weight:  53%|█████▎    | 597/1131 [00:01<00:01, 487.47it/s]
ram used:  3.40 GB, model.diffusion_model.output_blocks.10.1.transformer_blocks.0.attn1.to_k.weight:  53%|█████▎    | 597/1131 [00:01<00:01, 487.47it/s]
ram used:  3.41 GB, model.diffusion_model.output_blocks.10.1.transformer_blocks.0.attn1.to_v.weight:  53%|█████▎    | 597/1131 [00:01<00:01, 487.47it/s]
ram used:  3.41 GB, model.diffusion_model.output_blocks.10.1.transformer_blocks.0.attn1.to_out.0.weight:  53%|█████▎    | 597/1131 [00:01<00:01, 487.47it/s]
ram used:  3.41 GB, model.diffusion_model.output_blocks.10.1.transformer_blocks.0.attn1.to_out.0.bias:  53%|█████▎    | 597/1131 [00:01<00:01, 487.47it/s]  
ram used:  3.41 GB, model.diffusion_model.output_blocks.10.1.transformer_blocks.0.ff.net.0.proj.weight:  53%|█████▎    | 597/1131 [00:01<00:01, 487.47it/s]
ram used:  3.41 GB, model.diffusion_model.output_blocks.10.1.transformer_blocks.0.ff.net.0.proj.bias:  53%|█████▎    | 597/1131 [00:01<00:01, 487.47it/s]  
ram used:  3.41 GB, model.diffusion_model.output_blocks.10.1.transformer_blocks.0.ff.net.2.weight:  53%|█████▎    | 597/1131 [00:01<00:01, 487.47it/s]   
ram used:  3.41 GB, model.diffusion_model.output_blocks.10.1.transformer_blocks.0.ff.net.2.bias:  53%|█████▎    | 597/1131 [00:01<00:01, 487.47it/s]  
ram used:  3.41 GB, model.diffusion_model.output_blocks.10.1.transformer_blocks.0.attn2.to_q.weight:  53%|█████▎    | 597/1131 [00:01<00:01, 487.47it/s]
ram used:  3.41 GB, model.diffusion_model.output_blocks.10.1.transformer_blocks.0.attn2.to_k.weight:  53%|█████▎    | 597/1131 [00:01<00:01, 487.47it/s]
ram used:  3.41 GB, model.diffusion_model.output_blocks.10.1.transformer_blocks.0.attn2.to_v.weight:  53%|█████▎    | 597/1131 [00:01<00:01, 487.47it/s]
ram used:  3.41 GB, model.diffusion_model.output_blocks.10.1.transformer_blocks.0.attn2.to_out.0.weight:  53%|█████▎    | 597/1131 [00:01<00:01, 487.47it/s]
ram used:  3.41 GB, model.diffusion_model.output_blocks.10.1.transformer_blocks.0.attn2.to_out.0.bias:  53%|█████▎    | 597/1131 [00:01<00:01, 487.47it/s]  
ram used:  3.41 GB, model.diffusion_model.output_blocks.10.1.transformer_blocks.0.norm1.weight:  53%|█████▎    | 597/1131 [00:01<00:01, 487.47it/s]       
ram used:  3.41 GB, model.diffusion_model.output_blocks.10.1.transformer_blocks.0.norm1.bias:  53%|█████▎    | 597/1131 [00:01<00:01, 487.47it/s]  
ram used:  3.41 GB, model.diffusion_model.output_blocks.10.1.transformer_blocks.0.norm2.weight:  53%|█████▎    | 597/1131 [00:01<00:01, 487.47it/s]
ram used:  3.41 GB, model.diffusion_model.output_blocks.10.1.transformer_blocks.0.norm2.bias:  53%|█████▎    | 597/1131 [00:01<00:01, 487.47it/s]  
ram used:  3.41 GB, model.diffusion_model.output_blocks.10.1.transformer_blocks.0.norm3.weight:  53%|█████▎    | 597/1131 [00:01<00:01, 487.47it/s]
ram used:  3.41 GB, model.diffusion_model.output_blocks.10.1.transformer_blocks.0.norm3.bias:  53%|█████▎    | 597/1131 [00:01<00:01, 487.47it/s]  
ram used:  3.41 GB, model.diffusion_model.output_blocks.10.1.proj_out.weight:  53%|█████▎    | 597/1131 [00:01<00:01, 487.47it/s]                
ram used:  3.41 GB, model.diffusion_model.output_blocks.10.1.proj_out.bias:  53%|█████▎    | 597/1131 [00:01<00:01, 487.47it/s]  
ram used:  3.41 GB, model.diffusion_model.output_blocks.11.0.in_layers.0.weight:  53%|█████▎    | 597/1131 [00:01<00:01, 487.47it/s]
ram used:  3.41 GB, model.diffusion_model.output_blocks.11.0.in_layers.0.bias:  53%|█████▎    | 597/1131 [00:01<00:01, 487.47it/s]  
ram used:  3.41 GB, model.diffusion_model.output_blocks.11.0.in_layers.2.weight:  53%|█████▎    | 597/1131 [00:01<00:01, 487.47it/s]
ram used:  3.42 GB, model.diffusion_model.output_blocks.11.0.in_layers.2.bias:  53%|█████▎    | 597/1131 [00:01<00:01, 487.47it/s]  
ram used:  3.42 GB, model.diffusion_model.output_blocks.11.0.emb_layers.1.weight:  53%|█████▎    | 597/1131 [00:01<00:01, 487.47it/s]
ram used:  3.42 GB, model.diffusion_model.output_blocks.11.0.emb_layers.1.bias:  53%|█████▎    | 597/1131 [00:01<00:01, 487.47it/s]  
ram used:  3.42 GB, model.diffusion_model.output_blocks.11.0.out_layers.0.weight:  53%|█████▎    | 597/1131 [00:01<00:01, 487.47it/s]
ram used:  3.42 GB, model.diffusion_model.output_blocks.11.0.out_layers.0.bias:  53%|█████▎    | 597/1131 [00:01<00:01, 487.47it/s]  
ram used:  3.42 GB, model.diffusion_model.output_blocks.11.0.out_layers.3.weight:  53%|█████▎    | 597/1131 [00:01<00:01, 487.47it/s]
ram used:  3.43 GB, model.diffusion_model.output_blocks.11.0.out_layers.3.bias:  53%|█████▎    | 597/1131 [00:01<00:01, 487.47it/s]  
ram used:  3.43 GB, model.diffusion_model.output_blocks.11.0.skip_connection.weight:  53%|█████▎    | 597/1131 [00:01<00:01, 487.47it/s]
ram used:  3.43 GB, model.diffusion_model.output_blocks.11.0.skip_connection.bias:  53%|█████▎    | 597/1131 [00:01<00:01, 487.47it/s]  
ram used:  3.43 GB, model.diffusion_model.output_blocks.11.1.norm.weight:  53%|█████▎    | 597/1131 [00:01<00:01, 487.47it/s]         
ram used:  3.43 GB, model.diffusion_model.output_blocks.11.1.norm.bias:  53%|█████▎    | 597/1131 [00:01<00:01, 487.47it/s]  
ram used:  3.43 GB, model.diffusion_model.output_blocks.11.1.proj_in.weight:  53%|█████▎    | 597/1131 [00:01<00:01, 487.47it/s]
ram used:  3.43 GB, model.diffusion_model.output_blocks.11.1.proj_in.bias:  53%|█████▎    | 597/1131 [00:01<00:01, 487.47it/s]  
ram used:  3.43 GB, model.diffusion_model.output_blocks.11.1.transformer_blocks.0.attn1.to_q.weight:  53%|█████▎    | 597/1131 [00:01<00:01, 487.47it/s]
ram used:  3.43 GB, model.diffusion_model.output_blocks.11.1.transformer_blocks.0.attn1.to_k.weight:  53%|█████▎    | 597/1131 [00:01<00:01, 487.47it/s]
ram used:  3.43 GB, model.diffusion_model.output_blocks.11.1.transformer_blocks.0.attn1.to_v.weight:  53%|█████▎    | 597/1131 [00:01<00:01, 487.47it/s]
ram used:  3.43 GB, model.diffusion_model.output_blocks.11.1.transformer_blocks.0.attn1.to_out.0.weight:  53%|█████▎    | 597/1131 [00:01<00:01, 487.47it/s]
ram used:  3.43 GB, model.diffusion_model.output_blocks.11.1.transformer_blocks.0.attn1.to_out.0.bias:  53%|█████▎    | 597/1131 [00:01<00:01, 487.47it/s]  
ram used:  3.43 GB, model.diffusion_model.output_blocks.11.1.transformer_blocks.0.ff.net.0.proj.weight:  53%|█████▎    | 597/1131 [00:01<00:01, 487.47it/s]
ram used:  3.43 GB, model.diffusion_model.output_blocks.11.1.transformer_blocks.0.ff.net.0.proj.bias:  53%|█████▎    | 597/1131 [00:01<00:01, 487.47it/s]  
ram used:  3.43 GB, model.diffusion_model.output_blocks.11.1.transformer_blocks.0.ff.net.2.weight:  53%|█████▎    | 597/1131 [00:01<00:01, 487.47it/s]   
ram used:  3.43 GB, model.diffusion_model.output_blocks.11.1.transformer_blocks.0.ff.net.2.bias:  53%|█████▎    | 597/1131 [00:01<00:01, 487.47it/s]  
ram used:  3.43 GB, model.diffusion_model.output_blocks.11.1.transformer_blocks.0.attn2.to_q.weight:  53%|█████▎    | 597/1131 [00:01<00:01, 487.47it/s]
ram used:  3.44 GB, model.diffusion_model.output_blocks.11.1.transformer_blocks.0.attn2.to_k.weight:  53%|█████▎    | 597/1131 [00:01<00:01, 487.47it/s]
ram used:  3.44 GB, model.diffusion_model.output_blocks.11.1.transformer_blocks.0.attn2.to_v.weight:  53%|█████▎    | 597/1131 [00:01<00:01, 487.47it/s]
ram used:  3.44 GB, model.diffusion_model.output_blocks.11.1.transformer_blocks.0.attn2.to_out.0.weight:  53%|█████▎    | 597/1131 [00:01<00:01, 487.47it/s]
ram used:  3.44 GB, model.diffusion_model.output_blocks.11.1.transformer_blocks.0.attn2.to_out.0.bias:  53%|█████▎    | 597/1131 [00:01<00:01, 487.47it/s]  
ram used:  3.44 GB, model.diffusion_model.output_blocks.11.1.transformer_blocks.0.norm1.weight:  53%|█████▎    | 597/1131 [00:01<00:01, 487.47it/s]       
ram used:  3.44 GB, model.diffusion_model.output_blocks.11.1.transformer_blocks.0.norm1.bias:  53%|█████▎    | 597/1131 [00:01<00:01, 487.47it/s]  
ram used:  3.44 GB, model.diffusion_model.output_blocks.11.1.transformer_blocks.0.norm2.weight:  53%|█████▎    | 597/1131 [00:01<00:01, 487.47it/s]
ram used:  3.44 GB, model.diffusion_model.output_blocks.11.1.transformer_blocks.0.norm2.bias:  53%|█████▎    | 597/1131 [00:01<00:01, 487.47it/s]  
ram used:  3.44 GB, model.diffusion_model.output_blocks.11.1.transformer_blocks.0.norm3.weight:  53%|█████▎    | 597/1131 [00:01<00:01, 487.47it/s]
ram used:  3.44 GB, model.diffusion_model.output_blocks.11.1.transformer_blocks.0.norm3.bias:  53%|█████▎    | 597/1131 [00:01<00:01, 487.47it/s]  
ram used:  3.44 GB, model.diffusion_model.output_blocks.11.1.proj_out.weight:  53%|█████▎    | 597/1131 [00:01<00:01, 487.47it/s]                
ram used:  3.44 GB, model.diffusion_model.output_blocks.11.1.proj_out.bias:  53%|█████▎    | 597/1131 [00:01<00:01, 487.47it/s]  
ram used:  3.44 GB, model.diffusion_model.out.0.weight                :  53%|█████▎    | 597/1131 [00:01<00:01, 487.47it/s]    
ram used:  3.44 GB, model.diffusion_model.out.0.bias                  :  53%|█████▎    | 597/1131 [00:01<00:01, 487.47it/s]
ram used:  3.44 GB, model.diffusion_model.out.2.weight                :  53%|█████▎    | 597/1131 [00:01<00:01, 487.47it/s]
ram used:  3.44 GB, model.diffusion_model.out.2.bias                  :  53%|█████▎    | 597/1131 [00:01<00:01, 487.47it/s]
ram used:  3.44 GB, first_stage_model.encoder.conv_in.weight          :  53%|█████▎    | 597/1131 [00:01<00:01, 487.47it/s]
ram used:  3.44 GB, first_stage_model.encoder.conv_in.bias            :  53%|█████▎    | 597/1131 [00:01<00:01, 487.47it/s]
ram used:  3.44 GB, first_stage_model.encoder.down.0.block.0.norm1.weight:  53%|█████▎    | 597/1131 [00:01<00:01, 487.47it/s]
ram used:  3.44 GB, first_stage_model.encoder.down.0.block.0.norm1.bias:  53%|█████▎    | 597/1131 [00:01<00:01, 487.47it/s]  
ram used:  3.44 GB, first_stage_model.encoder.down.0.block.0.conv1.weight:  53%|█████▎    | 597/1131 [00:01<00:01, 487.47it/s]
ram used:  3.44 GB, first_stage_model.encoder.down.0.block.0.conv1.bias:  53%|█████▎    | 597/1131 [00:01<00:01, 487.47it/s]  
ram used:  3.44 GB, first_stage_model.encoder.down.0.block.0.norm2.weight:  53%|█████▎    | 597/1131 [00:01<00:01, 487.47it/s]
ram used:  3.44 GB, first_stage_model.encoder.down.0.block.0.norm2.bias:  53%|█████▎    | 597/1131 [00:01<00:01, 487.47it/s]  
ram used:  3.44 GB, first_stage_model.encoder.down.0.block.0.conv2.weight:  53%|█████▎    | 597/1131 [00:01<00:01, 487.47it/s]
ram used:  3.44 GB, first_stage_model.encoder.down.0.block.0.conv2.bias:  53%|█████▎    | 597/1131 [00:01<00:01, 487.47it/s]  
ram used:  3.44 GB, first_stage_model.encoder.down.0.block.1.norm1.weight:  53%|█████▎    | 597/1131 [00:01<00:01, 487.47it/s]
ram used:  3.44 GB, first_stage_model.encoder.down.0.block.1.norm1.bias:  53%|█████▎    | 597/1131 [00:01<00:01, 487.47it/s]  
ram used:  3.44 GB, first_stage_model.encoder.down.0.block.1.conv1.weight:  53%|█████▎    | 597/1131 [00:01<00:01, 487.47it/s]
ram used:  3.44 GB, first_stage_model.encoder.down.0.block.1.conv1.bias:  53%|█████▎    | 597/1131 [00:01<00:01, 487.47it/s]  
ram used:  3.44 GB, first_stage_model.encoder.down.0.block.1.norm2.weight:  53%|█████▎    | 597/1131 [00:01<00:01, 487.47it/s]
ram used:  3.44 GB, first_stage_model.encoder.down.0.block.1.norm2.bias:  53%|█████▎    | 597/1131 [00:01<00:01, 487.47it/s]  
ram used:  3.44 GB, first_stage_model.encoder.down.0.block.1.conv2.weight:  53%|█████▎    | 597/1131 [00:01<00:01, 487.47it/s]
ram used:  3.44 GB, first_stage_model.encoder.down.0.block.1.conv2.bias:  53%|█████▎    | 597/1131 [00:01<00:01, 487.47it/s]  
ram used:  3.44 GB, first_stage_model.encoder.down.0.downsample.conv.weight:  53%|█████▎    | 597/1131 [00:01<00:01, 487.47it/s]
ram used:  3.44 GB, first_stage_model.encoder.down.0.downsample.conv.bias:  53%|█████▎    | 597/1131 [00:01<00:01, 487.47it/s]  
ram used:  3.44 GB, first_stage_model.encoder.down.1.block.0.norm1.weight:  53%|█████▎    | 597/1131 [00:01<00:01, 487.47it/s]
ram used:  3.44 GB, first_stage_model.encoder.down.1.block.0.norm1.bias:  53%|█████▎    | 597/1131 [00:01<00:01, 487.47it/s]  
ram used:  3.44 GB, first_stage_model.encoder.down.1.block.0.conv1.weight:  53%|█████▎    | 597/1131 [00:01<00:01, 487.47it/s]
ram used:  3.44 GB, first_stage_model.encoder.down.1.block.0.conv1.bias:  53%|█████▎    | 597/1131 [00:01<00:01, 487.47it/s]  
ram used:  3.44 GB, first_stage_model.encoder.down.1.block.0.norm2.weight:  53%|█████▎    | 597/1131 [00:01<00:01, 487.47it/s]
ram used:  3.44 GB, first_stage_model.encoder.down.1.block.0.norm2.bias:  53%|█████▎    | 597/1131 [00:01<00:01, 487.47it/s]  
ram used:  3.44 GB, first_stage_model.encoder.down.1.block.0.conv2.weight:  53%|█████▎    | 597/1131 [00:01<00:01, 487.47it/s]
ram used:  3.44 GB, first_stage_model.encoder.down.1.block.0.conv2.bias:  53%|█████▎    | 597/1131 [00:01<00:01, 487.47it/s]  
ram used:  3.44 GB, first_stage_model.encoder.down.1.block.0.nin_shortcut.weight:  53%|█████▎    | 597/1131 [00:01<00:01, 487.47it/s]
ram used:  3.44 GB, first_stage_model.encoder.down.1.block.0.nin_shortcut.bias:  53%|█████▎    | 597/1131 [00:01<00:01, 487.47it/s]  
ram used:  3.44 GB, first_stage_model.encoder.down.1.block.1.norm1.weight:  53%|█████▎    | 597/1131 [00:01<00:01, 487.47it/s]     
ram used:  3.44 GB, first_stage_model.encoder.down.1.block.1.norm1.bias:  53%|█████▎    | 597/1131 [00:01<00:01, 487.47it/s]  
ram used:  3.44 GB, first_stage_model.encoder.down.1.block.1.conv1.weight:  53%|█████▎    | 597/1131 [00:01<00:01, 487.47it/s]
ram used:  3.45 GB, first_stage_model.encoder.down.1.block.1.conv1.bias:  53%|█████▎    | 597/1131 [00:01<00:01, 487.47it/s]  
ram used:  3.45 GB, first_stage_model.encoder.down.1.block.1.norm2.weight:  53%|█████▎    | 597/1131 [00:01<00:01, 487.47it/s]
ram used:  3.45 GB, first_stage_model.encoder.down.1.block.1.norm2.bias:  53%|█████▎    | 597/1131 [00:01<00:01, 487.47it/s]  
ram used:  3.45 GB, first_stage_model.encoder.down.1.block.1.conv2.weight:  53%|█████▎    | 597/1131 [00:01<00:01, 487.47it/s]
ram used:  3.45 GB, first_stage_model.encoder.down.1.block.1.conv2.bias:  53%|█████▎    | 597/1131 [00:01<00:01, 487.47it/s]  
ram used:  3.45 GB, first_stage_model.encoder.down.1.downsample.conv.weight:  53%|█████▎    | 597/1131 [00:01<00:01, 487.47it/s]
ram used:  3.45 GB, first_stage_model.encoder.down.1.downsample.conv.bias:  53%|█████▎    | 597/1131 [00:01<00:01, 487.47it/s]  
ram used:  3.45 GB, first_stage_model.encoder.down.2.block.0.norm1.weight:  53%|█████▎    | 597/1131 [00:01<00:01, 487.47it/s]
ram used:  3.45 GB, first_stage_model.encoder.down.2.block.0.norm1.bias:  53%|█████▎    | 597/1131 [00:01<00:01, 487.47it/s]  
ram used:  3.45 GB, first_stage_model.encoder.down.2.block.0.conv1.weight:  53%|█████▎    | 597/1131 [00:01<00:01, 487.47it/s]
ram used:  3.45 GB, first_stage_model.encoder.down.2.block.0.conv1.weight:  65%|██████▍   | 730/1131 [00:01<00:00, 720.24it/s]
ram used:  3.46 GB, first_stage_model.encoder.down.2.block.0.conv1.bias:  65%|██████▍   | 730/1131 [00:01<00:00, 720.24it/s]  
ram used:  3.46 GB, first_stage_model.encoder.down.2.block.0.norm2.weight:  65%|██████▍   | 730/1131 [00:01<00:00, 720.24it/s]
ram used:  3.46 GB, first_stage_model.encoder.down.2.block.0.norm2.bias:  65%|██████▍   | 730/1131 [00:01<00:00, 720.24it/s]  
ram used:  3.46 GB, first_stage_model.encoder.down.2.block.0.conv2.weight:  65%|██████▍   | 730/1131 [00:01<00:00, 720.24it/s]
ram used:  3.47 GB, first_stage_model.encoder.down.2.block.0.conv2.bias:  65%|██████▍   | 730/1131 [00:01<00:00, 720.24it/s]  
ram used:  3.47 GB, first_stage_model.encoder.down.2.block.0.nin_shortcut.weight:  65%|██████▍   | 730/1131 [00:01<00:00, 720.24it/s]
ram used:  3.47 GB, first_stage_model.encoder.down.2.block.0.nin_shortcut.bias:  65%|██████▍   | 730/1131 [00:01<00:00, 720.24it/s]  
ram used:  3.47 GB, first_stage_model.encoder.down.2.block.1.norm1.weight:  65%|██████▍   | 730/1131 [00:01<00:00, 720.24it/s]     
ram used:  3.47 GB, first_stage_model.encoder.down.2.block.1.norm1.bias:  65%|██████▍   | 730/1131 [00:01<00:00, 720.24it/s]  
ram used:  3.47 GB, first_stage_model.encoder.down.2.block.1.conv1.weight:  65%|██████▍   | 730/1131 [00:01<00:00, 720.24it/s]
ram used:  3.48 GB, first_stage_model.encoder.down.2.block.1.conv1.bias:  65%|██████▍   | 730/1131 [00:01<00:00, 720.24it/s]  
ram used:  3.48 GB, first_stage_model.encoder.down.2.block.1.norm2.weight:  65%|██████▍   | 730/1131 [00:01<00:00, 720.24it/s]
ram used:  3.48 GB, first_stage_model.encoder.down.2.block.1.norm2.bias:  65%|██████▍   | 730/1131 [00:01<00:00, 720.24it/s]  
ram used:  3.48 GB, first_stage_model.encoder.down.2.block.1.conv2.weight:  65%|██████▍   | 730/1131 [00:01<00:00, 720.24it/s]
ram used:  3.49 GB, first_stage_model.encoder.down.2.block.1.conv2.bias:  65%|██████▍   | 730/1131 [00:01<00:00, 720.24it/s]  
ram used:  3.49 GB, first_stage_model.encoder.down.2.downsample.conv.weight:  65%|██████▍   | 730/1131 [00:01<00:00, 720.24it/s]
ram used:  3.49 GB, first_stage_model.encoder.down.2.downsample.conv.bias:  65%|██████▍   | 730/1131 [00:01<00:00, 720.24it/s]  
ram used:  3.49 GB, first_stage_model.encoder.down.3.block.0.norm1.weight:  65%|██████▍   | 730/1131 [00:01<00:00, 720.24it/s]
ram used:  3.49 GB, first_stage_model.encoder.down.3.block.0.norm1.bias:  65%|██████▍   | 730/1131 [00:01<00:00, 720.24it/s]  
ram used:  3.49 GB, first_stage_model.encoder.down.3.block.0.conv1.weight:  65%|██████▍   | 730/1131 [00:01<00:00, 720.24it/s]
ram used:  3.50 GB, first_stage_model.encoder.down.3.block.0.conv1.bias:  65%|██████▍   | 730/1131 [00:01<00:00, 720.24it/s]  
ram used:  3.50 GB, first_stage_model.encoder.down.3.block.0.norm2.weight:  65%|██████▍   | 730/1131 [00:01<00:00, 720.24it/s]
ram used:  3.50 GB, first_stage_model.encoder.down.3.block.0.norm2.bias:  65%|██████▍   | 730/1131 [00:01<00:00, 720.24it/s]  
ram used:  3.50 GB, first_stage_model.encoder.down.3.block.0.conv2.weight:  65%|██████▍   | 730/1131 [00:01<00:00, 720.24it/s]
ram used:  3.51 GB, first_stage_model.encoder.down.3.block.0.conv2.bias:  65%|██████▍   | 730/1131 [00:01<00:00, 720.24it/s]  
ram used:  3.51 GB, first_stage_model.encoder.down.3.block.1.norm1.weight:  65%|██████▍   | 730/1131 [00:01<00:00, 720.24it/s]
ram used:  3.51 GB, first_stage_model.encoder.down.3.block.1.norm1.bias:  65%|██████▍   | 730/1131 [00:02<00:00, 720.24it/s]  
ram used:  3.51 GB, first_stage_model.encoder.down.3.block.1.conv1.weight:  65%|██████▍   | 730/1131 [00:02<00:00, 720.24it/s]
ram used:  3.52 GB, first_stage_model.encoder.down.3.block.1.conv1.bias:  65%|██████▍   | 730/1131 [00:02<00:00, 720.24it/s]  
ram used:  3.52 GB, first_stage_model.encoder.down.3.block.1.norm2.weight:  65%|██████▍   | 730/1131 [00:02<00:00, 720.24it/s]
ram used:  3.52 GB, first_stage_model.encoder.down.3.block.1.norm2.bias:  65%|██████▍   | 730/1131 [00:02<00:00, 720.24it/s]  
ram used:  3.52 GB, first_stage_model.encoder.down.3.block.1.conv2.weight:  65%|██████▍   | 730/1131 [00:02<00:00, 720.24it/s]
ram used:  3.53 GB, first_stage_model.encoder.down.3.block.1.conv2.bias:  65%|██████▍   | 730/1131 [00:02<00:00, 720.24it/s]  
ram used:  3.53 GB, first_stage_model.encoder.mid.block_1.norm1.weight:  65%|██████▍   | 730/1131 [00:02<00:00, 720.24it/s] 
ram used:  3.53 GB, first_stage_model.encoder.mid.block_1.norm1.bias  :  65%|██████▍   | 730/1131 [00:02<00:00, 720.24it/s]
ram used:  3.53 GB, first_stage_model.encoder.mid.block_1.conv1.weight:  65%|██████▍   | 730/1131 [00:02<00:00, 720.24it/s]
ram used:  3.54 GB, first_stage_model.encoder.mid.block_1.conv1.bias  :  65%|██████▍   | 730/1131 [00:02<00:00, 720.24it/s]
ram used:  3.54 GB, first_stage_model.encoder.mid.block_1.norm2.weight:  65%|██████▍   | 730/1131 [00:02<00:00, 720.24it/s]
ram used:  3.54 GB, first_stage_model.encoder.mid.block_1.norm2.bias  :  65%|██████▍   | 730/1131 [00:02<00:00, 720.24it/s]
ram used:  3.54 GB, first_stage_model.encoder.mid.block_1.conv2.weight:  65%|██████▍   | 730/1131 [00:02<00:00, 720.24it/s]
ram used:  3.55 GB, first_stage_model.encoder.mid.block_1.conv2.bias  :  65%|██████▍   | 730/1131 [00:02<00:00, 720.24it/s]
ram used:  3.55 GB, first_stage_model.encoder.mid.attn_1.norm.weight  :  65%|██████▍   | 730/1131 [00:02<00:00, 720.24it/s]
ram used:  3.55 GB, first_stage_model.encoder.mid.attn_1.norm.bias    :  65%|██████▍   | 730/1131 [00:02<00:00, 720.24it/s]
ram used:  3.55 GB, first_stage_model.encoder.mid.attn_1.q.weight     :  65%|██████▍   | 730/1131 [00:02<00:00, 720.24it/s]
ram used:  3.55 GB, first_stage_model.encoder.mid.attn_1.q.bias       :  65%|██████▍   | 730/1131 [00:02<00:00, 720.24it/s]
ram used:  3.55 GB, first_stage_model.encoder.mid.attn_1.k.weight     :  65%|██████▍   | 730/1131 [00:02<00:00, 720.24it/s]
ram used:  3.55 GB, first_stage_model.encoder.mid.attn_1.k.bias       :  65%|██████▍   | 730/1131 [00:02<00:00, 720.24it/s]
ram used:  3.55 GB, first_stage_model.encoder.mid.attn_1.v.weight     :  65%|██████▍   | 730/1131 [00:02<00:00, 720.24it/s]
ram used:  3.55 GB, first_stage_model.encoder.mid.attn_1.v.bias       :  65%|██████▍   | 730/1131 [00:02<00:00, 720.24it/s]
ram used:  3.55 GB, first_stage_model.encoder.mid.attn_1.proj_out.weight:  65%|██████▍   | 730/1131 [00:02<00:00, 720.24it/s]
ram used:  3.56 GB, first_stage_model.encoder.mid.attn_1.proj_out.bias:  65%|██████▍   | 730/1131 [00:02<00:00, 720.24it/s]  
ram used:  3.56 GB, first_stage_model.encoder.mid.block_2.norm1.weight:  65%|██████▍   | 730/1131 [00:02<00:00, 720.24it/s]
ram used:  3.56 GB, first_stage_model.encoder.mid.block_2.norm1.bias  :  65%|██████▍   | 730/1131 [00:02<00:00, 720.24it/s]
ram used:  3.56 GB, first_stage_model.encoder.mid.block_2.conv1.weight:  65%|██████▍   | 730/1131 [00:02<00:00, 720.24it/s]
ram used:  3.57 GB, first_stage_model.encoder.mid.block_2.conv1.bias  :  65%|██████▍   | 730/1131 [00:02<00:00, 720.24it/s]
ram used:  3.57 GB, first_stage_model.encoder.mid.block_2.norm2.weight:  65%|██████▍   | 730/1131 [00:02<00:00, 720.24it/s]
ram used:  3.57 GB, first_stage_model.encoder.mid.block_2.norm2.bias  :  65%|██████▍   | 730/1131 [00:02<00:00, 720.24it/s]
ram used:  3.57 GB, first_stage_model.encoder.mid.block_2.conv2.weight:  65%|██████▍   | 730/1131 [00:02<00:00, 720.24it/s]
ram used:  3.57 GB, first_stage_model.encoder.mid.block_2.conv2.bias  :  65%|██████▍   | 730/1131 [00:02<00:00, 720.24it/s]
ram used:  3.57 GB, first_stage_model.encoder.norm_out.weight         :  65%|██████▍   | 730/1131 [00:02<00:00, 720.24it/s]
ram used:  3.57 GB, first_stage_model.encoder.norm_out.bias           :  65%|██████▍   | 730/1131 [00:02<00:00, 720.24it/s]
ram used:  3.57 GB, first_stage_model.encoder.conv_out.weight         :  65%|██████▍   | 730/1131 [00:02<00:00, 720.24it/s]
ram used:  3.57 GB, first_stage_model.encoder.conv_out.bias           :  65%|██████▍   | 730/1131 [00:02<00:00, 720.24it/s]
ram used:  3.57 GB, first_stage_model.decoder.conv_in.weight          :  65%|██████▍   | 730/1131 [00:02<00:00, 720.24it/s]
ram used:  3.57 GB, first_stage_model.decoder.conv_in.bias            :  65%|██████▍   | 730/1131 [00:02<00:00, 720.24it/s]
ram used:  3.57 GB, first_stage_model.decoder.mid.block_1.norm1.weight:  65%|██████▍   | 730/1131 [00:02<00:00, 720.24it/s]
ram used:  3.57 GB, first_stage_model.decoder.mid.block_1.norm1.bias  :  65%|██████▍   | 730/1131 [00:02<00:00, 720.24it/s]
ram used:  3.57 GB, first_stage_model.decoder.mid.block_1.conv1.weight:  65%|██████▍   | 730/1131 [00:02<00:00, 720.24it/s]
ram used:  3.58 GB, first_stage_model.decoder.mid.block_1.conv1.bias  :  65%|██████▍   | 730/1131 [00:02<00:00, 720.24it/s]
ram used:  3.58 GB, first_stage_model.decoder.mid.block_1.norm2.weight:  65%|██████▍   | 730/1131 [00:02<00:00, 720.24it/s]
ram used:  3.58 GB, first_stage_model.decoder.mid.block_1.norm2.bias  :  65%|██████▍   | 730/1131 [00:02<00:00, 720.24it/s]
ram used:  3.58 GB, first_stage_model.decoder.mid.block_1.conv2.weight:  65%|██████▍   | 730/1131 [00:02<00:00, 720.24it/s]
ram used:  3.59 GB, first_stage_model.decoder.mid.block_1.conv2.bias  :  65%|██████▍   | 730/1131 [00:02<00:00, 720.24it/s]
ram used:  3.59 GB, first_stage_model.decoder.mid.attn_1.norm.weight  :  65%|██████▍   | 730/1131 [00:02<00:00, 720.24it/s]
ram used:  3.59 GB, first_stage_model.decoder.mid.attn_1.norm.bias    :  65%|██████▍   | 730/1131 [00:02<00:00, 720.24it/s]
ram used:  3.59 GB, first_stage_model.decoder.mid.attn_1.q.weight     :  65%|██████▍   | 730/1131 [00:02<00:00, 720.24it/s]
ram used:  3.59 GB, first_stage_model.decoder.mid.attn_1.q.bias       :  65%|██████▍   | 730/1131 [00:02<00:00, 720.24it/s]
ram used:  3.59 GB, first_stage_model.decoder.mid.attn_1.k.weight     :  65%|██████▍   | 730/1131 [00:02<00:00, 720.24it/s]
ram used:  3.60 GB, first_stage_model.decoder.mid.attn_1.k.bias       :  65%|██████▍   | 730/1131 [00:02<00:00, 720.24it/s]
ram used:  3.60 GB, first_stage_model.decoder.mid.attn_1.v.weight     :  65%|██████▍   | 730/1131 [00:02<00:00, 720.24it/s]
ram used:  3.60 GB, first_stage_model.decoder.mid.attn_1.v.bias       :  65%|██████▍   | 730/1131 [00:02<00:00, 720.24it/s]
ram used:  3.60 GB, first_stage_model.decoder.mid.attn_1.proj_out.weight:  65%|██████▍   | 730/1131 [00:02<00:00, 720.24it/s]
ram used:  3.60 GB, first_stage_model.decoder.mid.attn_1.proj_out.bias:  65%|██████▍   | 730/1131 [00:02<00:00, 720.24it/s]  
ram used:  3.60 GB, first_stage_model.decoder.mid.block_2.norm1.weight:  65%|██████▍   | 730/1131 [00:02<00:00, 720.24it/s]
ram used:  3.60 GB, first_stage_model.decoder.mid.block_2.norm1.weight:  72%|███████▏  | 814/1131 [00:02<00:00, 753.99it/s]
ram used:  3.60 GB, first_stage_model.decoder.mid.block_2.norm1.bias  :  72%|███████▏  | 814/1131 [00:02<00:00, 753.99it/s]
ram used:  3.60 GB, first_stage_model.decoder.mid.block_2.conv1.weight:  72%|███████▏  | 814/1131 [00:02<00:00, 753.99it/s]
ram used:  3.61 GB, first_stage_model.decoder.mid.block_2.conv1.bias  :  72%|███████▏  | 814/1131 [00:02<00:00, 753.99it/s]
ram used:  3.61 GB, first_stage_model.decoder.mid.block_2.norm2.weight:  72%|███████▏  | 814/1131 [00:02<00:00, 753.99it/s]
ram used:  3.61 GB, first_stage_model.decoder.mid.block_2.norm2.bias  :  72%|███████▏  | 814/1131 [00:02<00:00, 753.99it/s]
ram used:  3.61 GB, first_stage_model.decoder.mid.block_2.conv2.weight:  72%|███████▏  | 814/1131 [00:02<00:00, 753.99it/s]
ram used:  3.62 GB, first_stage_model.decoder.mid.block_2.conv2.bias  :  72%|███████▏  | 814/1131 [00:02<00:00, 753.99it/s]
ram used:  3.62 GB, first_stage_model.decoder.up.0.block.0.norm1.weight:  72%|███████▏  | 814/1131 [00:02<00:00, 753.99it/s]
ram used:  3.62 GB, first_stage_model.decoder.up.0.block.0.norm1.bias :  72%|███████▏  | 814/1131 [00:02<00:00, 753.99it/s] 
ram used:  3.62 GB, first_stage_model.decoder.up.0.block.0.conv1.weight:  72%|███████▏  | 814/1131 [00:02<00:00, 753.99it/s]
ram used:  3.62 GB, first_stage_model.decoder.up.0.block.0.conv1.bias :  72%|███████▏  | 814/1131 [00:02<00:00, 753.99it/s] 
ram used:  3.62 GB, first_stage_model.decoder.up.0.block.0.norm2.weight:  72%|███████▏  | 814/1131 [00:02<00:00, 753.99it/s]
ram used:  3.62 GB, first_stage_model.decoder.up.0.block.0.norm2.bias :  72%|███████▏  | 814/1131 [00:02<00:00, 753.99it/s] 
ram used:  3.62 GB, first_stage_model.decoder.up.0.block.0.conv2.weight:  72%|███████▏  | 814/1131 [00:02<00:00, 753.99it/s]
ram used:  3.62 GB, first_stage_model.decoder.up.0.block.0.conv2.bias :  72%|███████▏  | 814/1131 [00:02<00:00, 753.99it/s] 
ram used:  3.62 GB, first_stage_model.decoder.up.0.block.0.nin_shortcut.weight:  72%|███████▏  | 814/1131 [00:02<00:00, 753.99it/s]
ram used:  3.62 GB, first_stage_model.decoder.up.0.block.0.nin_shortcut.bias:  72%|███████▏  | 814/1131 [00:02<00:00, 753.99it/s]  
ram used:  3.62 GB, first_stage_model.decoder.up.0.block.1.norm1.weight:  72%|███████▏  | 814/1131 [00:02<00:00, 753.99it/s]     
ram used:  3.62 GB, first_stage_model.decoder.up.0.block.1.norm1.bias :  72%|███████▏  | 814/1131 [00:02<00:00, 753.99it/s] 
ram used:  3.62 GB, first_stage_model.decoder.up.0.block.1.conv1.weight:  72%|███████▏  | 814/1131 [00:02<00:00, 753.99it/s]
ram used:  3.62 GB, first_stage_model.decoder.up.0.block.1.conv1.bias :  72%|███████▏  | 814/1131 [00:02<00:00, 753.99it/s] 
ram used:  3.62 GB, first_stage_model.decoder.up.0.block.1.norm2.weight:  72%|███████▏  | 814/1131 [00:02<00:00, 753.99it/s]
ram used:  3.62 GB, first_stage_model.decoder.up.0.block.1.norm2.bias :  72%|███████▏  | 814/1131 [00:02<00:00, 753.99it/s] 
ram used:  3.62 GB, first_stage_model.decoder.up.0.block.1.conv2.weight:  72%|███████▏  | 814/1131 [00:02<00:00, 753.99it/s]
ram used:  3.62 GB, first_stage_model.decoder.up.0.block.1.conv2.bias :  72%|███████▏  | 814/1131 [00:02<00:00, 753.99it/s] 
ram used:  3.62 GB, first_stage_model.decoder.up.0.block.2.norm1.weight:  72%|███████▏  | 814/1131 [00:02<00:00, 753.99it/s]
ram used:  3.62 GB, first_stage_model.decoder.up.0.block.2.norm1.bias :  72%|███████▏  | 814/1131 [00:02<00:00, 753.99it/s] 
ram used:  3.62 GB, first_stage_model.decoder.up.0.block.2.conv1.weight:  72%|███████▏  | 814/1131 [00:02<00:00, 753.99it/s]
ram used:  3.62 GB, first_stage_model.decoder.up.0.block.2.conv1.bias :  72%|███████▏  | 814/1131 [00:02<00:00, 753.99it/s] 
ram used:  3.62 GB, first_stage_model.decoder.up.0.block.2.norm2.weight:  72%|███████▏  | 814/1131 [00:02<00:00, 753.99it/s]
ram used:  3.62 GB, first_stage_model.decoder.up.0.block.2.norm2.bias :  72%|███████▏  | 814/1131 [00:02<00:00, 753.99it/s] 
ram used:  3.62 GB, first_stage_model.decoder.up.0.block.2.conv2.weight:  72%|███████▏  | 814/1131 [00:02<00:00, 753.99it/s]
ram used:  3.62 GB, first_stage_model.decoder.up.0.block.2.conv2.bias :  72%|███████▏  | 814/1131 [00:02<00:00, 753.99it/s] 
ram used:  3.62 GB, first_stage_model.decoder.up.1.block.0.norm1.weight:  72%|███████▏  | 814/1131 [00:02<00:00, 753.99it/s]
ram used:  3.62 GB, first_stage_model.decoder.up.1.block.0.norm1.bias :  72%|███████▏  | 814/1131 [00:02<00:00, 753.99it/s] 
ram used:  3.62 GB, first_stage_model.decoder.up.1.block.0.conv1.weight:  72%|███████▏  | 814/1131 [00:02<00:00, 753.99it/s]
ram used:  3.63 GB, first_stage_model.decoder.up.1.block.0.conv1.bias :  72%|███████▏  | 814/1131 [00:02<00:00, 753.99it/s] 
ram used:  3.63 GB, first_stage_model.decoder.up.1.block.0.norm2.weight:  72%|███████▏  | 814/1131 [00:02<00:00, 753.99it/s]
ram used:  3.63 GB, first_stage_model.decoder.up.1.block.0.norm2.bias :  72%|███████▏  | 814/1131 [00:02<00:00, 753.99it/s] 
ram used:  3.63 GB, first_stage_model.decoder.up.1.block.0.conv2.weight:  72%|███████▏  | 814/1131 [00:02<00:00, 753.99it/s]
ram used:  3.63 GB, first_stage_model.decoder.up.1.block.0.conv2.bias :  72%|███████▏  | 814/1131 [00:02<00:00, 753.99it/s] 
ram used:  3.63 GB, first_stage_model.decoder.up.1.block.0.nin_shortcut.weight:  72%|███████▏  | 814/1131 [00:02<00:00, 753.99it/s]
ram used:  3.63 GB, first_stage_model.decoder.up.1.block.0.nin_shortcut.bias:  72%|███████▏  | 814/1131 [00:02<00:00, 753.99it/s]  
ram used:  3.63 GB, first_stage_model.decoder.up.1.block.1.norm1.weight:  72%|███████▏  | 814/1131 [00:02<00:00, 753.99it/s]     
ram used:  3.63 GB, first_stage_model.decoder.up.1.block.1.norm1.bias :  72%|███████▏  | 814/1131 [00:02<00:00, 753.99it/s] 
ram used:  3.63 GB, first_stage_model.decoder.up.1.block.1.conv1.weight:  72%|███████▏  | 814/1131 [00:02<00:00, 753.99it/s]
ram used:  3.63 GB, first_stage_model.decoder.up.1.block.1.conv1.bias :  72%|███████▏  | 814/1131 [00:02<00:00, 753.99it/s] 
ram used:  3.63 GB, first_stage_model.decoder.up.1.block.1.norm2.weight:  72%|███████▏  | 814/1131 [00:02<00:00, 753.99it/s]
ram used:  3.63 GB, first_stage_model.decoder.up.1.block.1.norm2.bias :  72%|███████▏  | 814/1131 [00:02<00:00, 753.99it/s] 
ram used:  3.63 GB, first_stage_model.decoder.up.1.block.1.conv2.weight:  72%|███████▏  | 814/1131 [00:02<00:00, 753.99it/s]
ram used:  3.63 GB, first_stage_model.decoder.up.1.block.1.conv2.bias :  72%|███████▏  | 814/1131 [00:02<00:00, 753.99it/s] 
ram used:  3.63 GB, first_stage_model.decoder.up.1.block.2.norm1.weight:  72%|███████▏  | 814/1131 [00:02<00:00, 753.99it/s]
ram used:  3.63 GB, first_stage_model.decoder.up.1.block.2.norm1.bias :  72%|███████▏  | 814/1131 [00:02<00:00, 753.99it/s] 
ram used:  3.63 GB, first_stage_model.decoder.up.1.block.2.conv1.weight:  72%|███████▏  | 814/1131 [00:02<00:00, 753.99it/s]
ram used:  3.64 GB, first_stage_model.decoder.up.1.block.2.conv1.bias :  72%|███████▏  | 814/1131 [00:02<00:00, 753.99it/s] 
ram used:  3.64 GB, first_stage_model.decoder.up.1.block.2.norm2.weight:  72%|███████▏  | 814/1131 [00:02<00:00, 753.99it/s]
ram used:  3.64 GB, first_stage_model.decoder.up.1.block.2.norm2.bias :  72%|███████▏  | 814/1131 [00:02<00:00, 753.99it/s] 
ram used:  3.64 GB, first_stage_model.decoder.up.1.block.2.conv2.weight:  72%|███████▏  | 814/1131 [00:02<00:00, 753.99it/s]
ram used:  3.64 GB, first_stage_model.decoder.up.1.block.2.conv2.bias :  72%|███████▏  | 814/1131 [00:02<00:00, 753.99it/s] 
ram used:  3.64 GB, first_stage_model.decoder.up.1.upsample.conv.weight:  72%|███████▏  | 814/1131 [00:02<00:00, 753.99it/s]
ram used:  3.64 GB, first_stage_model.decoder.up.1.upsample.conv.bias :  72%|███████▏  | 814/1131 [00:02<00:00, 753.99it/s] 
ram used:  3.64 GB, first_stage_model.decoder.up.2.block.0.norm1.weight:  72%|███████▏  | 814/1131 [00:02<00:00, 753.99it/s]
ram used:  3.64 GB, first_stage_model.decoder.up.2.block.0.norm1.bias :  72%|███████▏  | 814/1131 [00:02<00:00, 753.99it/s] 
ram used:  3.64 GB, first_stage_model.decoder.up.2.block.0.conv1.weight:  72%|███████▏  | 814/1131 [00:02<00:00, 753.99it/s]
ram used:  3.65 GB, first_stage_model.decoder.up.2.block.0.conv1.bias :  72%|███████▏  | 814/1131 [00:02<00:00, 753.99it/s] 
ram used:  3.65 GB, first_stage_model.decoder.up.2.block.0.norm2.weight:  72%|███████▏  | 814/1131 [00:02<00:00, 753.99it/s]
ram used:  3.65 GB, first_stage_model.decoder.up.2.block.0.norm2.bias :  72%|███████▏  | 814/1131 [00:02<00:00, 753.99it/s] 
ram used:  3.65 GB, first_stage_model.decoder.up.2.block.0.conv2.weight:  72%|███████▏  | 814/1131 [00:02<00:00, 753.99it/s]
ram used:  3.66 GB, first_stage_model.decoder.up.2.block.0.conv2.bias :  72%|███████▏  | 814/1131 [00:02<00:00, 753.99it/s] 
ram used:  3.66 GB, first_stage_model.decoder.up.2.block.1.norm1.weight:  72%|███████▏  | 814/1131 [00:02<00:00, 753.99it/s]
ram used:  3.66 GB, first_stage_model.decoder.up.2.block.1.norm1.bias :  72%|███████▏  | 814/1131 [00:02<00:00, 753.99it/s] 
ram used:  3.66 GB, first_stage_model.decoder.up.2.block.1.conv1.weight:  72%|███████▏  | 814/1131 [00:02<00:00, 753.99it/s]
ram used:  3.67 GB, first_stage_model.decoder.up.2.block.1.conv1.bias :  72%|███████▏  | 814/1131 [00:02<00:00, 753.99it/s] 
ram used:  3.67 GB, first_stage_model.decoder.up.2.block.1.norm2.weight:  72%|███████▏  | 814/1131 [00:02<00:00, 753.99it/s]
ram used:  3.67 GB, first_stage_model.decoder.up.2.block.1.norm2.bias :  72%|███████▏  | 814/1131 [00:02<00:00, 753.99it/s] 
ram used:  3.67 GB, first_stage_model.decoder.up.2.block.1.conv2.weight:  72%|███████▏  | 814/1131 [00:02<00:00, 753.99it/s]
ram used:  3.68 GB, first_stage_model.decoder.up.2.block.1.conv2.bias :  72%|███████▏  | 814/1131 [00:02<00:00, 753.99it/s] 
ram used:  3.68 GB, first_stage_model.decoder.up.2.block.2.norm1.weight:  72%|███████▏  | 814/1131 [00:02<00:00, 753.99it/s]
ram used:  3.68 GB, first_stage_model.decoder.up.2.block.2.norm1.bias :  72%|███████▏  | 814/1131 [00:02<00:00, 753.99it/s] 
ram used:  3.68 GB, first_stage_model.decoder.up.2.block.2.conv1.weight:  72%|███████▏  | 814/1131 [00:02<00:00, 753.99it/s]
ram used:  3.69 GB, first_stage_model.decoder.up.2.block.2.conv1.bias :  72%|███████▏  | 814/1131 [00:02<00:00, 753.99it/s] 
ram used:  3.69 GB, first_stage_model.decoder.up.2.block.2.norm2.weight:  72%|███████▏  | 814/1131 [00:02<00:00, 753.99it/s]
ram used:  3.69 GB, first_stage_model.decoder.up.2.block.2.norm2.bias :  72%|███████▏  | 814/1131 [00:02<00:00, 753.99it/s] 
ram used:  3.69 GB, first_stage_model.decoder.up.2.block.2.conv2.weight:  72%|███████▏  | 814/1131 [00:02<00:00, 753.99it/s]
ram used:  3.70 GB, first_stage_model.decoder.up.2.block.2.conv2.bias :  72%|███████▏  | 814/1131 [00:02<00:00, 753.99it/s] 
ram used:  3.70 GB, first_stage_model.decoder.up.2.upsample.conv.weight:  72%|███████▏  | 814/1131 [00:02<00:00, 753.99it/s]
ram used:  3.71 GB, first_stage_model.decoder.up.2.upsample.conv.bias :  72%|███████▏  | 814/1131 [00:02<00:00, 753.99it/s] 
ram used:  3.71 GB, first_stage_model.decoder.up.3.block.0.norm1.weight:  72%|███████▏  | 814/1131 [00:02<00:00, 753.99it/s]
ram used:  3.71 GB, first_stage_model.decoder.up.3.block.0.norm1.bias :  72%|███████▏  | 814/1131 [00:02<00:00, 753.99it/s] 
ram used:  3.71 GB, first_stage_model.decoder.up.3.block.0.conv1.weight:  72%|███████▏  | 814/1131 [00:02<00:00, 753.99it/s]
ram used:  3.72 GB, first_stage_model.decoder.up.3.block.0.conv1.bias :  72%|███████▏  | 814/1131 [00:02<00:00, 753.99it/s] 
ram used:  3.72 GB, first_stage_model.decoder.up.3.block.0.norm2.weight:  72%|███████▏  | 814/1131 [00:02<00:00, 753.99it/s]
ram used:  3.72 GB, first_stage_model.decoder.up.3.block.0.norm2.bias :  72%|███████▏  | 814/1131 [00:02<00:00, 753.99it/s] 
ram used:  3.72 GB, first_stage_model.decoder.up.3.block.0.conv2.weight:  72%|███████▏  | 814/1131 [00:02<00:00, 753.99it/s]
ram used:  3.73 GB, first_stage_model.decoder.up.3.block.0.conv2.bias :  72%|███████▏  | 814/1131 [00:02<00:00, 753.99it/s] 
ram used:  3.73 GB, first_stage_model.decoder.up.3.block.1.norm1.weight:  72%|███████▏  | 814/1131 [00:02<00:00, 753.99it/s]
ram used:  3.73 GB, first_stage_model.decoder.up.3.block.1.norm1.bias :  72%|███████▏  | 814/1131 [00:02<00:00, 753.99it/s] 
ram used:  3.73 GB, first_stage_model.decoder.up.3.block.1.norm1.bias :  81%|████████  | 911/1131 [00:02<00:00, 815.98it/s]
ram used:  3.73 GB, first_stage_model.decoder.up.3.block.1.conv1.weight:  81%|████████  | 911/1131 [00:02<00:00, 815.98it/s]
ram used:  3.73 GB, first_stage_model.decoder.up.3.block.1.conv1.bias :  81%|████████  | 911/1131 [00:02<00:00, 815.98it/s] 
ram used:  3.73 GB, first_stage_model.decoder.up.3.block.1.norm2.weight:  81%|████████  | 911/1131 [00:02<00:00, 815.98it/s]
ram used:  3.73 GB, first_stage_model.decoder.up.3.block.1.norm2.bias :  81%|████████  | 911/1131 [00:02<00:00, 815.98it/s] 
ram used:  3.73 GB, first_stage_model.decoder.up.3.block.1.conv2.weight:  81%|████████  | 911/1131 [00:02<00:00, 815.98it/s]
ram used:  3.74 GB, first_stage_model.decoder.up.3.block.1.conv2.bias :  81%|████████  | 911/1131 [00:02<00:00, 815.98it/s] 
ram used:  3.74 GB, first_stage_model.decoder.up.3.block.2.norm1.weight:  81%|████████  | 911/1131 [00:02<00:00, 815.98it/s]
ram used:  3.74 GB, first_stage_model.decoder.up.3.block.2.norm1.bias :  81%|████████  | 911/1131 [00:02<00:00, 815.98it/s] 
ram used:  3.74 GB, first_stage_model.decoder.up.3.block.2.conv1.weight:  81%|████████  | 911/1131 [00:02<00:00, 815.98it/s]
ram used:  3.75 GB, first_stage_model.decoder.up.3.block.2.conv1.bias :  81%|████████  | 911/1131 [00:02<00:00, 815.98it/s] 
ram used:  3.75 GB, first_stage_model.decoder.up.3.block.2.norm2.weight:  81%|████████  | 911/1131 [00:02<00:00, 815.98it/s]
ram used:  3.75 GB, first_stage_model.decoder.up.3.block.2.norm2.bias :  81%|████████  | 911/1131 [00:02<00:00, 815.98it/s] 
ram used:  3.75 GB, first_stage_model.decoder.up.3.block.2.conv2.weight:  81%|████████  | 911/1131 [00:02<00:00, 815.98it/s]
ram used:  3.76 GB, first_stage_model.decoder.up.3.block.2.conv2.bias :  81%|████████  | 911/1131 [00:02<00:00, 815.98it/s] 
ram used:  3.76 GB, first_stage_model.decoder.up.3.upsample.conv.weight:  81%|████████  | 911/1131 [00:02<00:00, 815.98it/s]
ram used:  3.77 GB, first_stage_model.decoder.up.3.upsample.conv.bias :  81%|████████  | 911/1131 [00:02<00:00, 815.98it/s] 
ram used:  3.77 GB, first_stage_model.decoder.norm_out.weight         :  81%|████████  | 911/1131 [00:02<00:00, 815.98it/s]
ram used:  3.77 GB, first_stage_model.decoder.norm_out.bias           :  81%|████████  | 911/1131 [00:02<00:00, 815.98it/s]
ram used:  3.77 GB, first_stage_model.decoder.conv_out.weight         :  81%|████████  | 911/1131 [00:02<00:00, 815.98it/s]
ram used:  3.77 GB, first_stage_model.decoder.conv_out.bias           :  81%|████████  | 911/1131 [00:02<00:00, 815.98it/s]
ram used:  3.77 GB, first_stage_model.quant_conv.weight               :  81%|████████  | 911/1131 [00:02<00:00, 815.98it/s]
ram used:  3.77 GB, first_stage_model.quant_conv.bias                 :  81%|████████  | 911/1131 [00:02<00:00, 815.98it/s]
ram used:  3.77 GB, first_stage_model.post_quant_conv.weight          :  81%|████████  | 911/1131 [00:02<00:00, 815.98it/s]
ram used:  3.77 GB, first_stage_model.post_quant_conv.bias            :  81%|████████  | 911/1131 [00:02<00:00, 815.98it/s]
ram used:  3.77 GB, cond_stage_model.transformer.text_model.embeddings.token_embedding.weight:  81%|████████  | 911/1131 [00:02<00:00, 815.98it/s]
ram used:  3.92 GB, cond_stage_model.transformer.text_model.embeddings.position_embedding.weight:  81%|████████  | 911/1131 [00:02<00:00, 815.98it/s]
ram used:  3.92 GB, cond_stage_model.transformer.text_model.encoder.layers.0.self_attn.k_proj.weight:  81%|████████  | 911/1131 [00:02<00:00, 815.98it/s]
ram used:  3.93 GB, cond_stage_model.transformer.text_model.encoder.layers.0.self_attn.k_proj.bias:  81%|████████  | 911/1131 [00:02<00:00, 815.98it/s]  
ram used:  3.93 GB, cond_stage_model.transformer.text_model.encoder.layers.0.self_attn.v_proj.weight:  81%|████████  | 911/1131 [00:02<00:00, 815.98it/s]
ram used:  3.93 GB, cond_stage_model.transformer.text_model.encoder.layers.0.self_attn.v_proj.bias:  81%|████████  | 911/1131 [00:02<00:00, 815.98it/s]  
ram used:  3.93 GB, cond_stage_model.transformer.text_model.encoder.layers.0.self_attn.q_proj.weight:  81%|████████  | 911/1131 [00:02<00:00, 815.98it/s]
ram used:  3.93 GB, cond_stage_model.transformer.text_model.encoder.layers.0.self_attn.q_proj.bias:  81%|████████  | 911/1131 [00:02<00:00, 815.98it/s]  
ram used:  3.93 GB, cond_stage_model.transformer.text_model.encoder.layers.0.self_attn.out_proj.weight:  81%|████████  | 911/1131 [00:02<00:00, 815.98it/s]
ram used:  3.93 GB, cond_stage_model.transformer.text_model.encoder.layers.0.self_attn.out_proj.bias:  81%|████████  | 911/1131 [00:02<00:00, 815.98it/s]  
ram used:  3.93 GB, cond_stage_model.transformer.text_model.encoder.layers.0.layer_norm1.weight:  81%|████████  | 911/1131 [00:02<00:00, 815.98it/s]     
ram used:  3.93 GB, cond_stage_model.transformer.text_model.encoder.layers.0.layer_norm1.bias:  81%|████████  | 911/1131 [00:02<00:00, 815.98it/s]  
ram used:  3.93 GB, cond_stage_model.transformer.text_model.encoder.layers.0.mlp.fc1.weight:  81%|████████  | 911/1131 [00:02<00:00, 815.98it/s]  
ram used:  3.94 GB, cond_stage_model.transformer.text_model.encoder.layers.0.mlp.fc1.bias:  81%|████████  | 911/1131 [00:02<00:00, 815.98it/s]  
ram used:  3.94 GB, cond_stage_model.transformer.text_model.encoder.layers.0.mlp.fc2.weight:  81%|████████  | 911/1131 [00:02<00:00, 815.98it/s]
ram used:  3.95 GB, cond_stage_model.transformer.text_model.encoder.layers.0.mlp.fc2.bias:  81%|████████  | 911/1131 [00:02<00:00, 815.98it/s]  
ram used:  3.95 GB, cond_stage_model.transformer.text_model.encoder.layers.0.layer_norm2.weight:  81%|████████  | 911/1131 [00:02<00:00, 815.98it/s]
ram used:  3.95 GB, cond_stage_model.transformer.text_model.encoder.layers.0.layer_norm2.bias:  81%|████████  | 911/1131 [00:02<00:00, 815.98it/s]  
ram used:  3.95 GB, cond_stage_model.transformer.text_model.encoder.layers.1.self_attn.k_proj.weight:  81%|████████  | 911/1131 [00:02<00:00, 815.98it/s]
ram used:  3.96 GB, cond_stage_model.transformer.text_model.encoder.layers.1.self_attn.k_proj.bias:  81%|████████  | 911/1131 [00:02<00:00, 815.98it/s]  
ram used:  3.96 GB, cond_stage_model.transformer.text_model.encoder.layers.1.self_attn.v_proj.weight:  81%|████████  | 911/1131 [00:02<00:00, 815.98it/s]
ram used:  3.96 GB, cond_stage_model.transformer.text_model.encoder.layers.1.self_attn.v_proj.bias:  81%|████████  | 911/1131 [00:02<00:00, 815.98it/s]  
ram used:  3.96 GB, cond_stage_model.transformer.text_model.encoder.layers.1.self_attn.q_proj.weight:  81%|████████  | 911/1131 [00:02<00:00, 815.98it/s]
ram used:  3.96 GB, cond_stage_model.transformer.text_model.encoder.layers.1.self_attn.q_proj.bias:  81%|████████  | 911/1131 [00:02<00:00, 815.98it/s]  
ram used:  3.96 GB, cond_stage_model.transformer.text_model.encoder.layers.1.self_attn.out_proj.weight:  81%|████████  | 911/1131 [00:02<00:00, 815.98it/s]
ram used:  3.96 GB, cond_stage_model.transformer.text_model.encoder.layers.1.self_attn.out_proj.bias:  81%|████████  | 911/1131 [00:02<00:00, 815.98it/s]  
ram used:  3.96 GB, cond_stage_model.transformer.text_model.encoder.layers.1.layer_norm1.weight:  81%|████████  | 911/1131 [00:02<00:00, 815.98it/s]     
ram used:  3.96 GB, cond_stage_model.transformer.text_model.encoder.layers.1.layer_norm1.bias:  81%|████████  | 911/1131 [00:02<00:00, 815.98it/s]  
ram used:  3.96 GB, cond_stage_model.transformer.text_model.encoder.layers.1.mlp.fc1.weight:  81%|████████  | 911/1131 [00:02<00:00, 815.98it/s]  
ram used:  3.97 GB, cond_stage_model.transformer.text_model.encoder.layers.1.mlp.fc1.bias:  81%|████████  | 911/1131 [00:02<00:00, 815.98it/s]  
ram used:  3.97 GB, cond_stage_model.transformer.text_model.encoder.layers.1.mlp.fc2.weight:  81%|████████  | 911/1131 [00:02<00:00, 815.98it/s]
ram used:  3.98 GB, cond_stage_model.transformer.text_model.encoder.layers.1.mlp.fc2.bias:  81%|████████  | 911/1131 [00:02<00:00, 815.98it/s]  
ram used:  3.98 GB, cond_stage_model.transformer.text_model.encoder.layers.1.layer_norm2.weight:  81%|████████  | 911/1131 [00:02<00:00, 815.98it/s]
ram used:  3.98 GB, cond_stage_model.transformer.text_model.encoder.layers.1.layer_norm2.bias:  81%|████████  | 911/1131 [00:02<00:00, 815.98it/s]  
ram used:  3.98 GB, cond_stage_model.transformer.text_model.encoder.layers.2.self_attn.k_proj.weight:  81%|████████  | 911/1131 [00:02<00:00, 815.98it/s]
ram used:  3.98 GB, cond_stage_model.transformer.text_model.encoder.layers.2.self_attn.k_proj.bias:  81%|████████  | 911/1131 [00:02<00:00, 815.98it/s]  
ram used:  3.98 GB, cond_stage_model.transformer.text_model.encoder.layers.2.self_attn.v_proj.weight:  81%|████████  | 911/1131 [00:02<00:00, 815.98it/s]
ram used:  3.99 GB, cond_stage_model.transformer.text_model.encoder.layers.2.self_attn.v_proj.bias:  81%|████████  | 911/1131 [00:02<00:00, 815.98it/s]  
ram used:  3.99 GB, cond_stage_model.transformer.text_model.encoder.layers.2.self_attn.q_proj.weight:  81%|████████  | 911/1131 [00:02<00:00, 815.98it/s]
ram used:  3.99 GB, cond_stage_model.transformer.text_model.encoder.layers.2.self_attn.q_proj.bias:  81%|████████  | 911/1131 [00:02<00:00, 815.98it/s]  
ram used:  3.99 GB, cond_stage_model.transformer.text_model.encoder.layers.2.self_attn.out_proj.weight:  81%|████████  | 911/1131 [00:02<00:00, 815.98it/s]
ram used:  3.99 GB, cond_stage_model.transformer.text_model.encoder.layers.2.self_attn.out_proj.bias:  81%|████████  | 911/1131 [00:02<00:00, 815.98it/s]  
ram used:  3.99 GB, cond_stage_model.transformer.text_model.encoder.layers.2.layer_norm1.weight:  81%|████████  | 911/1131 [00:02<00:00, 815.98it/s]     
ram used:  3.99 GB, cond_stage_model.transformer.text_model.encoder.layers.2.layer_norm1.bias:  81%|████████  | 911/1131 [00:02<00:00, 815.98it/s]  
ram used:  3.99 GB, cond_stage_model.transformer.text_model.encoder.layers.2.mlp.fc1.weight:  81%|████████  | 911/1131 [00:02<00:00, 815.98it/s]  
ram used:  4.00 GB, cond_stage_model.transformer.text_model.encoder.layers.2.mlp.fc1.bias:  81%|████████  | 911/1131 [00:02<00:00, 815.98it/s]  
ram used:  4.00 GB, cond_stage_model.transformer.text_model.encoder.layers.2.mlp.fc2.weight:  81%|████████  | 911/1131 [00:02<00:00, 815.98it/s]
ram used:  4.01 GB, cond_stage_model.transformer.text_model.encoder.layers.2.mlp.fc2.bias:  81%|████████  | 911/1131 [00:02<00:00, 815.98it/s]  
ram used:  4.01 GB, cond_stage_model.transformer.text_model.encoder.layers.2.layer_norm2.weight:  81%|████████  | 911/1131 [00:02<00:00, 815.98it/s]
ram used:  4.01 GB, cond_stage_model.transformer.text_model.encoder.layers.2.layer_norm2.bias:  81%|████████  | 911/1131 [00:02<00:00, 815.98it/s]  
ram used:  4.01 GB, cond_stage_model.transformer.text_model.encoder.layers.3.self_attn.k_proj.weight:  81%|████████  | 911/1131 [00:02<00:00, 815.98it/s]
ram used:  4.01 GB, cond_stage_model.transformer.text_model.encoder.layers.3.self_attn.k_proj.bias:  81%|████████  | 911/1131 [00:02<00:00, 815.98it/s]  
ram used:  4.01 GB, cond_stage_model.transformer.text_model.encoder.layers.3.self_attn.v_proj.weight:  81%|████████  | 911/1131 [00:02<00:00, 815.98it/s]
ram used:  4.01 GB, cond_stage_model.transformer.text_model.encoder.layers.3.self_attn.v_proj.bias:  81%|████████  | 911/1131 [00:02<00:00, 815.98it/s]  
ram used:  4.01 GB, cond_stage_model.transformer.text_model.encoder.layers.3.self_attn.q_proj.weight:  81%|████████  | 911/1131 [00:02<00:00, 815.98it/s]
ram used:  4.02 GB, cond_stage_model.transformer.text_model.encoder.layers.3.self_attn.q_proj.bias:  81%|████████  | 911/1131 [00:02<00:00, 815.98it/s]  
ram used:  4.02 GB, cond_stage_model.transformer.text_model.encoder.layers.3.self_attn.out_proj.weight:  81%|████████  | 911/1131 [00:02<00:00, 815.98it/s]
ram used:  4.02 GB, cond_stage_model.transformer.text_model.encoder.layers.3.self_attn.out_proj.bias:  81%|████████  | 911/1131 [00:02<00:00, 815.98it/s]  
ram used:  4.02 GB, cond_stage_model.transformer.text_model.encoder.layers.3.layer_norm1.weight:  81%|████████  | 911/1131 [00:02<00:00, 815.98it/s]     
ram used:  4.02 GB, cond_stage_model.transformer.text_model.encoder.layers.3.layer_norm1.bias:  81%|████████  | 911/1131 [00:02<00:00, 815.98it/s]  
ram used:  4.02 GB, cond_stage_model.transformer.text_model.encoder.layers.3.layer_norm1.bias:  88%|████████▊ | 995/1131 [00:02<00:00, 668.70it/s]
ram used:  4.02 GB, cond_stage_model.transformer.text_model.encoder.layers.3.mlp.fc1.weight:  88%|████████▊ | 995/1131 [00:02<00:00, 668.70it/s]  
ram used:  4.03 GB, cond_stage_model.transformer.text_model.encoder.layers.3.mlp.fc1.bias:  88%|████████▊ | 995/1131 [00:02<00:00, 668.70it/s]  
ram used:  4.03 GB, cond_stage_model.transformer.text_model.encoder.layers.3.mlp.fc2.weight:  88%|████████▊ | 995/1131 [00:02<00:00, 668.70it/s]
ram used:  4.04 GB, cond_stage_model.transformer.text_model.encoder.layers.3.mlp.fc2.bias:  88%|████████▊ | 995/1131 [00:02<00:00, 668.70it/s]  
ram used:  4.04 GB, cond_stage_model.transformer.text_model.encoder.layers.3.layer_norm2.weight:  88%|████████▊ | 995/1131 [00:02<00:00, 668.70it/s]
ram used:  4.04 GB, cond_stage_model.transformer.text_model.encoder.layers.3.layer_norm2.bias:  88%|████████▊ | 995/1131 [00:02<00:00, 668.70it/s]  
ram used:  4.04 GB, cond_stage_model.transformer.text_model.encoder.layers.4.self_attn.k_proj.weight:  88%|████████▊ | 995/1131 [00:02<00:00, 668.70it/s]
ram used:  4.04 GB, cond_stage_model.transformer.text_model.encoder.layers.4.self_attn.k_proj.bias:  88%|████████▊ | 995/1131 [00:02<00:00, 668.70it/s]  
ram used:  4.04 GB, cond_stage_model.transformer.text_model.encoder.layers.4.self_attn.v_proj.weight:  88%|████████▊ | 995/1131 [00:02<00:00, 668.70it/s]
ram used:  4.04 GB, cond_stage_model.transformer.text_model.encoder.layers.4.self_attn.v_proj.bias:  88%|████████▊ | 995/1131 [00:02<00:00, 668.70it/s]  
ram used:  4.04 GB, cond_stage_model.transformer.text_model.encoder.layers.4.self_attn.q_proj.weight:  88%|████████▊ | 995/1131 [00:02<00:00, 668.70it/s]
ram used:  4.05 GB, cond_stage_model.transformer.text_model.encoder.layers.4.self_attn.q_proj.bias:  88%|████████▊ | 995/1131 [00:02<00:00, 668.70it/s]  
ram used:  4.05 GB, cond_stage_model.transformer.text_model.encoder.layers.4.self_attn.out_proj.weight:  88%|████████▊ | 995/1131 [00:02<00:00, 668.70it/s]
ram used:  4.05 GB, cond_stage_model.transformer.text_model.encoder.layers.4.self_attn.out_proj.bias:  88%|████████▊ | 995/1131 [00:02<00:00, 668.70it/s]  
ram used:  4.05 GB, cond_stage_model.transformer.text_model.encoder.layers.4.layer_norm1.weight:  88%|████████▊ | 995/1131 [00:02<00:00, 668.70it/s]     
ram used:  4.05 GB, cond_stage_model.transformer.text_model.encoder.layers.4.layer_norm1.bias:  88%|████████▊ | 995/1131 [00:02<00:00, 668.70it/s]  
ram used:  4.05 GB, cond_stage_model.transformer.text_model.encoder.layers.4.mlp.fc1.weight:  88%|████████▊ | 995/1131 [00:02<00:00, 668.70it/s]  
ram used:  4.06 GB, cond_stage_model.transformer.text_model.encoder.layers.4.mlp.fc1.bias:  88%|████████▊ | 995/1131 [00:02<00:00, 668.70it/s]  
ram used:  4.06 GB, cond_stage_model.transformer.text_model.encoder.layers.4.mlp.fc2.weight:  88%|████████▊ | 995/1131 [00:02<00:00, 668.70it/s]
ram used:  4.07 GB, cond_stage_model.transformer.text_model.encoder.layers.4.mlp.fc2.bias:  88%|████████▊ | 995/1131 [00:02<00:00, 668.70it/s]  
ram used:  4.07 GB, cond_stage_model.transformer.text_model.encoder.layers.4.layer_norm2.weight:  88%|████████▊ | 995/1131 [00:02<00:00, 668.70it/s]
ram used:  4.07 GB, cond_stage_model.transformer.text_model.encoder.layers.4.layer_norm2.bias:  88%|████████▊ | 995/1131 [00:02<00:00, 668.70it/s]  
ram used:  4.07 GB, cond_stage_model.transformer.text_model.encoder.layers.5.self_attn.k_proj.weight:  88%|████████▊ | 995/1131 [00:02<00:00, 668.70it/s]
ram used:  4.07 GB, cond_stage_model.transformer.text_model.encoder.layers.5.self_attn.k_proj.bias:  88%|████████▊ | 995/1131 [00:02<00:00, 668.70it/s]  
ram used:  4.07 GB, cond_stage_model.transformer.text_model.encoder.layers.5.self_attn.v_proj.weight:  88%|████████▊ | 995/1131 [00:02<00:00, 668.70it/s]
ram used:  4.07 GB, cond_stage_model.transformer.text_model.encoder.layers.5.self_attn.v_proj.bias:  88%|████████▊ | 995/1131 [00:02<00:00, 668.70it/s]  
ram used:  4.07 GB, cond_stage_model.transformer.text_model.encoder.layers.5.self_attn.q_proj.weight:  88%|████████▊ | 995/1131 [00:02<00:00, 668.70it/s]
ram used:  4.07 GB, cond_stage_model.transformer.text_model.encoder.layers.5.self_attn.q_proj.bias:  88%|████████▊ | 995/1131 [00:02<00:00, 668.70it/s]  
ram used:  4.07 GB, cond_stage_model.transformer.text_model.encoder.layers.5.self_attn.out_proj.weight:  88%|████████▊ | 995/1131 [00:02<00:00, 668.70it/s]
ram used:  4.08 GB, cond_stage_model.transformer.text_model.encoder.layers.5.self_attn.out_proj.bias:  88%|████████▊ | 995/1131 [00:02<00:00, 668.70it/s]  
ram used:  4.08 GB, cond_stage_model.transformer.text_model.encoder.layers.5.layer_norm1.weight:  88%|████████▊ | 995/1131 [00:02<00:00, 668.70it/s]     
ram used:  4.08 GB, cond_stage_model.transformer.text_model.encoder.layers.5.layer_norm1.bias:  88%|████████▊ | 995/1131 [00:02<00:00, 668.70it/s]  
ram used:  4.08 GB, cond_stage_model.transformer.text_model.encoder.layers.5.mlp.fc1.weight:  88%|████████▊ | 995/1131 [00:02<00:00, 668.70it/s]  
ram used:  4.09 GB, cond_stage_model.transformer.text_model.encoder.layers.5.mlp.fc1.bias:  88%|████████▊ | 995/1131 [00:02<00:00, 668.70it/s]  
ram used:  4.09 GB, cond_stage_model.transformer.text_model.encoder.layers.5.mlp.fc2.weight:  88%|████████▊ | 995/1131 [00:02<00:00, 668.70it/s]
ram used:  4.09 GB, cond_stage_model.transformer.text_model.encoder.layers.5.mlp.fc2.bias:  88%|████████▊ | 995/1131 [00:02<00:00, 668.70it/s]  
ram used:  4.09 GB, cond_stage_model.transformer.text_model.encoder.layers.5.layer_norm2.weight:  88%|████████▊ | 995/1131 [00:02<00:00, 668.70it/s]
ram used:  4.09 GB, cond_stage_model.transformer.text_model.encoder.layers.5.layer_norm2.bias:  88%|████████▊ | 995/1131 [00:02<00:00, 668.70it/s]  
ram used:  4.09 GB, cond_stage_model.transformer.text_model.encoder.layers.6.self_attn.k_proj.weight:  88%|████████▊ | 995/1131 [00:02<00:00, 668.70it/s]
ram used:  4.10 GB, cond_stage_model.transformer.text_model.encoder.layers.6.self_attn.k_proj.bias:  88%|████████▊ | 995/1131 [00:02<00:00, 668.70it/s]  
ram used:  4.10 GB, cond_stage_model.transformer.text_model.encoder.layers.6.self_attn.v_proj.weight:  88%|████████▊ | 995/1131 [00:02<00:00, 668.70it/s]
ram used:  4.10 GB, cond_stage_model.transformer.text_model.encoder.layers.6.self_attn.v_proj.bias:  88%|████████▊ | 995/1131 [00:02<00:00, 668.70it/s]  
ram used:  4.10 GB, cond_stage_model.transformer.text_model.encoder.layers.6.self_attn.q_proj.weight:  88%|████████▊ | 995/1131 [00:02<00:00, 668.70it/s]
ram used:  4.10 GB, cond_stage_model.transformer.text_model.encoder.layers.6.self_attn.q_proj.bias:  88%|████████▊ | 995/1131 [00:02<00:00, 668.70it/s]  
ram used:  4.10 GB, cond_stage_model.transformer.text_model.encoder.layers.6.self_attn.out_proj.weight:  88%|████████▊ | 995/1131 [00:02<00:00, 668.70it/s]
ram used:  4.10 GB, cond_stage_model.transformer.text_model.encoder.layers.6.self_attn.out_proj.bias:  88%|████████▊ | 995/1131 [00:02<00:00, 668.70it/s]  
ram used:  4.10 GB, cond_stage_model.transformer.text_model.encoder.layers.6.layer_norm1.weight:  88%|████████▊ | 995/1131 [00:02<00:00, 668.70it/s]     
ram used:  4.10 GB, cond_stage_model.transformer.text_model.encoder.layers.6.layer_norm1.bias:  88%|████████▊ | 995/1131 [00:02<00:00, 668.70it/s]  
ram used:  4.10 GB, cond_stage_model.transformer.text_model.encoder.layers.6.mlp.fc1.weight:  88%|████████▊ | 995/1131 [00:02<00:00, 668.70it/s]  
ram used:  4.11 GB, cond_stage_model.transformer.text_model.encoder.layers.6.mlp.fc1.bias:  88%|████████▊ | 995/1131 [00:02<00:00, 668.70it/s]  
ram used:  4.11 GB, cond_stage_model.transformer.text_model.encoder.layers.6.mlp.fc2.weight:  88%|████████▊ | 995/1131 [00:02<00:00, 668.70it/s]
ram used:  4.12 GB, cond_stage_model.transformer.text_model.encoder.layers.6.mlp.fc2.bias:  88%|████████▊ | 995/1131 [00:02<00:00, 668.70it/s]  
ram used:  4.12 GB, cond_stage_model.transformer.text_model.encoder.layers.6.layer_norm2.weight:  88%|████████▊ | 995/1131 [00:02<00:00, 668.70it/s]
ram used:  4.12 GB, cond_stage_model.transformer.text_model.encoder.layers.6.layer_norm2.bias:  88%|████████▊ | 995/1131 [00:02<00:00, 668.70it/s]  
ram used:  4.12 GB, cond_stage_model.transformer.text_model.encoder.layers.7.self_attn.k_proj.weight:  88%|████████▊ | 995/1131 [00:02<00:00, 668.70it/s]
ram used:  4.13 GB, cond_stage_model.transformer.text_model.encoder.layers.7.self_attn.k_proj.bias:  88%|████████▊ | 995/1131 [00:02<00:00, 668.70it/s]  
ram used:  4.13 GB, cond_stage_model.transformer.text_model.encoder.layers.7.self_attn.v_proj.weight:  88%|████████▊ | 995/1131 [00:02<00:00, 668.70it/s]
ram used:  4.13 GB, cond_stage_model.transformer.text_model.encoder.layers.7.self_attn.v_proj.bias:  88%|████████▊ | 995/1131 [00:02<00:00, 668.70it/s]  
ram used:  4.13 GB, cond_stage_model.transformer.text_model.encoder.layers.7.self_attn.q_proj.weight:  88%|████████▊ | 995/1131 [00:02<00:00, 668.70it/s]
ram used:  4.13 GB, cond_stage_model.transformer.text_model.encoder.layers.7.self_attn.q_proj.bias:  88%|████████▊ | 995/1131 [00:02<00:00, 668.70it/s]  
ram used:  4.13 GB, cond_stage_model.transformer.text_model.encoder.layers.7.self_attn.out_proj.weight:  88%|████████▊ | 995/1131 [00:02<00:00, 668.70it/s]
ram used:  4.13 GB, cond_stage_model.transformer.text_model.encoder.layers.7.self_attn.out_proj.bias:  88%|████████▊ | 995/1131 [00:02<00:00, 668.70it/s]  
ram used:  4.13 GB, cond_stage_model.transformer.text_model.encoder.layers.7.layer_norm1.weight:  88%|████████▊ | 995/1131 [00:02<00:00, 668.70it/s]     
ram used:  4.13 GB, cond_stage_model.transformer.text_model.encoder.layers.7.layer_norm1.bias:  88%|████████▊ | 995/1131 [00:02<00:00, 668.70it/s]  
ram used:  4.13 GB, cond_stage_model.transformer.text_model.encoder.layers.7.mlp.fc1.weight:  88%|████████▊ | 995/1131 [00:02<00:00, 668.70it/s]  
ram used:  4.14 GB, cond_stage_model.transformer.text_model.encoder.layers.7.mlp.fc1.bias:  88%|████████▊ | 995/1131 [00:02<00:00, 668.70it/s]  
ram used:  4.14 GB, cond_stage_model.transformer.text_model.encoder.layers.7.mlp.fc2.weight:  88%|████████▊ | 995/1131 [00:02<00:00, 668.70it/s]
ram used:  4.15 GB, cond_stage_model.transformer.text_model.encoder.layers.7.mlp.fc2.bias:  88%|████████▊ | 995/1131 [00:02<00:00, 668.70it/s]  
ram used:  4.15 GB, cond_stage_model.transformer.text_model.encoder.layers.7.layer_norm2.weight:  88%|████████▊ | 995/1131 [00:02<00:00, 668.70it/s]
ram used:  4.15 GB, cond_stage_model.transformer.text_model.encoder.layers.7.layer_norm2.bias:  88%|████████▊ | 995/1131 [00:02<00:00, 668.70it/s]  
ram used:  4.15 GB, cond_stage_model.transformer.text_model.encoder.layers.8.self_attn.k_proj.weight:  88%|████████▊ | 995/1131 [00:02<00:00, 668.70it/s]
ram used:  4.15 GB, cond_stage_model.transformer.text_model.encoder.layers.8.self_attn.k_proj.bias:  88%|████████▊ | 995/1131 [00:02<00:00, 668.70it/s]  
ram used:  4.15 GB, cond_stage_model.transformer.text_model.encoder.layers.8.self_attn.v_proj.weight:  88%|████████▊ | 995/1131 [00:02<00:00, 668.70it/s]
ram used:  4.16 GB, cond_stage_model.transformer.text_model.encoder.layers.8.self_attn.v_proj.bias:  88%|████████▊ | 995/1131 [00:02<00:00, 668.70it/s]  
ram used:  4.16 GB, cond_stage_model.transformer.text_model.encoder.layers.8.self_attn.q_proj.weight:  88%|████████▊ | 995/1131 [00:02<00:00, 668.70it/s]
ram used:  4.16 GB, cond_stage_model.transformer.text_model.encoder.layers.8.self_attn.q_proj.bias:  88%|████████▊ | 995/1131 [00:02<00:00, 668.70it/s]  
ram used:  4.16 GB, cond_stage_model.transformer.text_model.encoder.layers.8.self_attn.q_proj.bias:  95%|█████████▍| 1071/1131 [00:02<00:00, 691.09it/s]
ram used:  4.16 GB, cond_stage_model.transformer.text_model.encoder.layers.8.self_attn.out_proj.weight:  95%|█████████▍| 1071/1131 [00:02<00:00, 691.09it/s]
ram used:  4.16 GB, cond_stage_model.transformer.text_model.encoder.layers.8.self_attn.out_proj.bias:  95%|█████████▍| 1071/1131 [00:02<00:00, 691.09it/s]  
ram used:  4.16 GB, cond_stage_model.transformer.text_model.encoder.layers.8.layer_norm1.weight:  95%|█████████▍| 1071/1131 [00:02<00:00, 691.09it/s]     
ram used:  4.16 GB, cond_stage_model.transformer.text_model.encoder.layers.8.layer_norm1.bias:  95%|█████████▍| 1071/1131 [00:02<00:00, 691.09it/s]  
ram used:  4.16 GB, cond_stage_model.transformer.text_model.encoder.layers.8.mlp.fc1.weight:  95%|█████████▍| 1071/1131 [00:02<00:00, 691.09it/s]  
ram used:  4.17 GB, cond_stage_model.transformer.text_model.encoder.layers.8.mlp.fc1.bias:  95%|█████████▍| 1071/1131 [00:02<00:00, 691.09it/s]  
ram used:  4.17 GB, cond_stage_model.transformer.text_model.encoder.layers.8.mlp.fc2.weight:  95%|█████████▍| 1071/1131 [00:02<00:00, 691.09it/s]
ram used:  4.18 GB, cond_stage_model.transformer.text_model.encoder.layers.8.mlp.fc2.bias:  95%|█████████▍| 1071/1131 [00:02<00:00, 691.09it/s]  
ram used:  4.18 GB, cond_stage_model.transformer.text_model.encoder.layers.8.layer_norm2.weight:  95%|█████████▍| 1071/1131 [00:02<00:00, 691.09it/s]
ram used:  4.18 GB, cond_stage_model.transformer.text_model.encoder.layers.8.layer_norm2.bias:  95%|█████████▍| 1071/1131 [00:02<00:00, 691.09it/s]  
ram used:  4.18 GB, cond_stage_model.transformer.text_model.encoder.layers.9.self_attn.k_proj.weight:  95%|█████████▍| 1071/1131 [00:02<00:00, 691.09it/s]
ram used:  4.18 GB, cond_stage_model.transformer.text_model.encoder.layers.9.self_attn.k_proj.bias:  95%|█████████▍| 1071/1131 [00:02<00:00, 691.09it/s]  
ram used:  4.18 GB, cond_stage_model.transformer.text_model.encoder.layers.9.self_attn.v_proj.weight:  95%|█████████▍| 1071/1131 [00:02<00:00, 691.09it/s]
ram used:  4.18 GB, cond_stage_model.transformer.text_model.encoder.layers.9.self_attn.v_proj.bias:  95%|█████████▍| 1071/1131 [00:02<00:00, 691.09it/s]  
ram used:  4.18 GB, cond_stage_model.transformer.text_model.encoder.layers.9.self_attn.q_proj.weight:  95%|█████████▍| 1071/1131 [00:02<00:00, 691.09it/s]
ram used:  4.19 GB, cond_stage_model.transformer.text_model.encoder.layers.9.self_attn.q_proj.bias:  95%|█████████▍| 1071/1131 [00:02<00:00, 691.09it/s]  
ram used:  4.19 GB, cond_stage_model.transformer.text_model.encoder.layers.9.self_attn.out_proj.weight:  95%|█████████▍| 1071/1131 [00:02<00:00, 691.09it/s]
ram used:  4.19 GB, cond_stage_model.transformer.text_model.encoder.layers.9.self_attn.out_proj.bias:  95%|█████████▍| 1071/1131 [00:02<00:00, 691.09it/s]  
ram used:  4.19 GB, cond_stage_model.transformer.text_model.encoder.layers.9.layer_norm1.weight:  95%|█████████▍| 1071/1131 [00:02<00:00, 691.09it/s]     
ram used:  4.19 GB, cond_stage_model.transformer.text_model.encoder.layers.9.layer_norm1.bias:  95%|█████████▍| 1071/1131 [00:02<00:00, 691.09it/s]  
ram used:  4.19 GB, cond_stage_model.transformer.text_model.encoder.layers.9.mlp.fc1.weight:  95%|█████████▍| 1071/1131 [00:02<00:00, 691.09it/s]  
ram used:  4.20 GB, cond_stage_model.transformer.text_model.encoder.layers.9.mlp.fc1.bias:  95%|█████████▍| 1071/1131 [00:02<00:00, 691.09it/s]  
ram used:  4.20 GB, cond_stage_model.transformer.text_model.encoder.layers.9.mlp.fc2.weight:  95%|█████████▍| 1071/1131 [00:02<00:00, 691.09it/s]
ram used:  4.21 GB, cond_stage_model.transformer.text_model.encoder.layers.9.mlp.fc2.bias:  95%|█████████▍| 1071/1131 [00:02<00:00, 691.09it/s]  
ram used:  4.21 GB, cond_stage_model.transformer.text_model.encoder.layers.9.layer_norm2.weight:  95%|█████████▍| 1071/1131 [00:02<00:00, 691.09it/s]
ram used:  4.21 GB, cond_stage_model.transformer.text_model.encoder.layers.9.layer_norm2.bias:  95%|█████████▍| 1071/1131 [00:02<00:00, 691.09it/s]  
ram used:  4.21 GB, cond_stage_model.transformer.text_model.encoder.layers.10.self_attn.k_proj.weight:  95%|█████████▍| 1071/1131 [00:02<00:00, 691.09it/s]
ram used:  4.21 GB, cond_stage_model.transformer.text_model.encoder.layers.10.self_attn.k_proj.bias:  95%|█████████▍| 1071/1131 [00:02<00:00, 691.09it/s]  
ram used:  4.21 GB, cond_stage_model.transformer.text_model.encoder.layers.10.self_attn.v_proj.weight:  95%|█████████▍| 1071/1131 [00:02<00:00, 691.09it/s]
ram used:  4.21 GB, cond_stage_model.transformer.text_model.encoder.layers.10.self_attn.v_proj.bias:  95%|█████████▍| 1071/1131 [00:02<00:00, 691.09it/s]  
ram used:  4.21 GB, cond_stage_model.transformer.text_model.encoder.layers.10.self_attn.q_proj.weight:  95%|█████████▍| 1071/1131 [00:02<00:00, 691.09it/s]
ram used:  4.22 GB, cond_stage_model.transformer.text_model.encoder.layers.10.self_attn.q_proj.bias:  95%|█████████▍| 1071/1131 [00:02<00:00, 691.09it/s]  
ram used:  4.22 GB, cond_stage_model.transformer.text_model.encoder.layers.10.self_attn.out_proj.weight:  95%|█████████▍| 1071/1131 [00:02<00:00, 691.09it/s]
ram used:  4.22 GB, cond_stage_model.transformer.text_model.encoder.layers.10.self_attn.out_proj.bias:  95%|█████████▍| 1071/1131 [00:02<00:00, 691.09it/s]  
ram used:  4.22 GB, cond_stage_model.transformer.text_model.encoder.layers.10.layer_norm1.weight:  95%|█████████▍| 1071/1131 [00:02<00:00, 691.09it/s]     
ram used:  4.22 GB, cond_stage_model.transformer.text_model.encoder.layers.10.layer_norm1.bias:  95%|█████████▍| 1071/1131 [00:02<00:00, 691.09it/s]  
ram used:  4.22 GB, cond_stage_model.transformer.text_model.encoder.layers.10.mlp.fc1.weight:  95%|█████████▍| 1071/1131 [00:02<00:00, 691.09it/s]  
ram used:  4.23 GB, cond_stage_model.transformer.text_model.encoder.layers.10.mlp.fc1.bias:  95%|█████████▍| 1071/1131 [00:02<00:00, 691.09it/s]  
ram used:  4.23 GB, cond_stage_model.transformer.text_model.encoder.layers.10.mlp.fc2.weight:  95%|█████████▍| 1071/1131 [00:02<00:00, 691.09it/s]
ram used:  4.24 GB, cond_stage_model.transformer.text_model.encoder.layers.10.mlp.fc2.bias:  95%|█████████▍| 1071/1131 [00:02<00:00, 691.09it/s]  
ram used:  4.24 GB, cond_stage_model.transformer.text_model.encoder.layers.10.layer_norm2.weight:  95%|█████████▍| 1071/1131 [00:02<00:00, 691.09it/s]
ram used:  4.24 GB, cond_stage_model.transformer.text_model.encoder.layers.10.layer_norm2.bias:  95%|█████████▍| 1071/1131 [00:02<00:00, 691.09it/s]  
ram used:  4.24 GB, cond_stage_model.transformer.text_model.encoder.layers.11.self_attn.k_proj.weight:  95%|█████████▍| 1071/1131 [00:02<00:00, 691.09it/s]
ram used:  4.24 GB, cond_stage_model.transformer.text_model.encoder.layers.11.self_attn.k_proj.bias:  95%|█████████▍| 1071/1131 [00:02<00:00, 691.09it/s]  
ram used:  4.24 GB, cond_stage_model.transformer.text_model.encoder.layers.11.self_attn.v_proj.weight:  95%|█████████▍| 1071/1131 [00:02<00:00, 691.09it/s]
ram used:  4.24 GB, cond_stage_model.transformer.text_model.encoder.layers.11.self_attn.v_proj.bias:  95%|█████████▍| 1071/1131 [00:02<00:00, 691.09it/s]  
ram used:  4.24 GB, cond_stage_model.transformer.text_model.encoder.layers.11.self_attn.q_proj.weight:  95%|█████████▍| 1071/1131 [00:02<00:00, 691.09it/s]
ram used:  4.24 GB, cond_stage_model.transformer.text_model.encoder.layers.11.self_attn.q_proj.bias:  95%|█████████▍| 1071/1131 [00:02<00:00, 691.09it/s]  
ram used:  4.24 GB, cond_stage_model.transformer.text_model.encoder.layers.11.self_attn.out_proj.weight:  95%|█████████▍| 1071/1131 [00:02<00:00, 691.09it/s]
ram used:  4.25 GB, cond_stage_model.transformer.text_model.encoder.layers.11.self_attn.out_proj.bias:  95%|█████████▍| 1071/1131 [00:02<00:00, 691.09it/s]  
ram used:  4.25 GB, cond_stage_model.transformer.text_model.encoder.layers.11.layer_norm1.weight:  95%|█████████▍| 1071/1131 [00:02<00:00, 691.09it/s]     
ram used:  4.25 GB, cond_stage_model.transformer.text_model.encoder.layers.11.layer_norm1.bias:  95%|█████████▍| 1071/1131 [00:02<00:00, 691.09it/s]  
ram used:  4.25 GB, cond_stage_model.transformer.text_model.encoder.layers.11.mlp.fc1.weight:  95%|█████████▍| 1071/1131 [00:02<00:00, 691.09it/s]  
ram used:  4.26 GB, cond_stage_model.transformer.text_model.encoder.layers.11.mlp.fc1.bias:  95%|█████████▍| 1071/1131 [00:02<00:00, 691.09it/s]  
ram used:  4.26 GB, cond_stage_model.transformer.text_model.encoder.layers.11.mlp.fc2.weight:  95%|█████████▍| 1071/1131 [00:02<00:00, 691.09it/s]
ram used:  4.26 GB, cond_stage_model.transformer.text_model.encoder.layers.11.mlp.fc2.bias:  95%|█████████▍| 1071/1131 [00:02<00:00, 691.09it/s]  
ram used:  4.26 GB, cond_stage_model.transformer.text_model.encoder.layers.11.layer_norm2.weight:  95%|█████████▍| 1071/1131 [00:02<00:00, 691.09it/s]
ram used:  4.26 GB, cond_stage_model.transformer.text_model.encoder.layers.11.layer_norm2.bias:  95%|█████████▍| 1071/1131 [00:02<00:00, 691.09it/s]  
ram used:  4.26 GB, cond_stage_model.transformer.text_model.final_layer_norm.weight:  95%|█████████▍| 1071/1131 [00:02<00:00, 691.09it/s]           
ram used:  4.26 GB, cond_stage_model.transformer.text_model.final_layer_norm.bias:  95%|█████████▍| 1071/1131 [00:02<00:00, 691.09it/s]  
ram used:  4.26 GB, cond_stage_model.transformer.text_model.final_layer_norm.bias: 100%|██████████| 1131/1131 [00:02<00:00, 448.82it/s]
loaded weights in 2523.68 ms, 4.26 GB loaded at 1.69 GB/s
3260.64 ms

external/external_cl_half_max.py

Traceback (most recent call last):
  File "/home/jebba/devel/tinygrad/tinygrad/test/external/external_cl_half_max.py", line 1, in <module>
    from tinygrad.runtime.ops_gpu import CLDevice, CLProgram, compile_cl
ImportError: cannot import name 'compile_cl' from 'tinygrad.runtime.ops_gpu' (/home/jebba/devel/tinygrad/tinygrad/tinygrad/runtime/ops_gpu.py)

external/external_jit_failure.py

0
1
2
3
4
5
6
7
8
9

external/external_llama_eval.py

Traceback (most recent call last):
  File "/home/jebba/devel/tinygrad/tinygrad/test/external/external_llama_eval.py", line 1, in <module>
    from lm_eval.base import BaseLM
ModuleNotFoundError: No module named 'lm_eval'

external/external_model_benchmark.py

Traceback (most recent call last):
  File "/home/jebba/devel/tinygrad/tinygrad/test/external/external_model_benchmark.py", line 7, in <module>
    import onnxruntime as ort
ModuleNotFoundError: No module named 'onnxruntime'

external/external_multi_gpu.py

GPU devices HIP:0 HIP:1
GPU initial sync:   0.23 ms
CPU creation:   4.17 ms, 515.45 GB/sec
Traceback (most recent call last):
  File "/home/jebba/devel/tinygrad/tinygrad/test/external/external_multi_gpu.py", line 22, in <module>
    c0 = (Tensor.ones(sz, device="clang")/2).realize()
  File "/home/jebba/devel/tinygrad/tinygrad/tinygrad/tensor.py", line 116, in realize
    run_schedule(self.lazydata.schedule())
  File "/home/jebba/devel/tinygrad/tinygrad/tinygrad/realize.py", line 48, in run_schedule
    prg = lower_schedule_item(si)
  File "/home/jebba/devel/tinygrad/tinygrad/tinygrad/realize.py", line 39, in lower_schedule_item
    return Device[si.out.device].get_runner(si.ast)
  File "/home/jebba/devel/tinygrad/tinygrad/tinygrad/device.py", line 348, in get_runner
    def get_runner(self, ast:LazyOp) -> CompiledASTRunner: return self.to_program(self.get_linearizer(ast))
  File "/home/jebba/devel/tinygrad/tinygrad/tinygrad/device.py", line 321, in to_program
    return CompiledASTRunner(k.ast, k.name, self.compiler.render(to_function_name(k.name), k.uops), self, k.global_size, k.local_size)
  File "/home/jebba/devel/tinygrad/tinygrad/tinygrad/device.py", line 284, in __init__
    lib:bytes = precompiled if precompiled is not None else self.device.compiler.compile_cached(prg)
  File "/home/jebba/devel/tinygrad/tinygrad/tinygrad/device.py", line 272, in compile_cached
    lib = self.compile(src)
  File "/home/jebba/devel/tinygrad/tinygrad/tinygrad/runtime/ops_clang.py", line 15, in compile
    subprocess.check_output(args=('clang -shared -march=native -O2 -Wall -Werror -x c -fPIC - -o '+ \
  File "/usr/lib/python3.10/subprocess.py", line 421, in check_output
    return run(*popenargs, stdout=PIPE, timeout=timeout, check=True,
  File "/usr/lib/python3.10/subprocess.py", line 503, in run
    with Popen(*popenargs, **kwargs) as process:
  File "/usr/lib/python3.10/subprocess.py", line 971, in __init__
    self._execute_child(args, executable, preexec_fn, close_fds,
  File "/usr/lib/python3.10/subprocess.py", line 1863, in _execute_child
    raise child_exception_type(errno_num, err_msg, err_filename)
FileNotFoundError: [Errno 2] No such file or directory: 'clang'

external/external_osx_profiling.py

Traceback (most recent call last):
  File "/home/jebba/devel/tinygrad/tinygrad/test/external/external_osx_profiling.py", line 1, in <module>
    from tinygrad.runtime.ops_gpu import CLProgram, CL, CLBuffer
ImportError: cannot import name 'CL' from 'tinygrad.runtime.ops_gpu' (/home/jebba/devel/tinygrad/tinygrad/tinygrad/runtime/ops_gpu.py)

external/external_test_dist_collectives.py

Traceback (most recent call last):
  File "/home/jebba/devel/tinygrad/tinygrad/test/external/external_test_dist_collectives.py", line 6, in <module>
    from extra.dist import collectives
  File "/home/jebba/devel/tinygrad/tinygrad/extra/dist/collectives.py", line 4, in <module>
    from extra.dist import world
  File "/home/jebba/devel/tinygrad/tinygrad/extra/dist/world.py", line 6, in <module>
    from tinygrad.runtime.lib import RawBuffer, RawBufferCopyInOut
ModuleNotFoundError: No module named 'tinygrad.runtime.lib'

external/external_test_dist_world.py

Traceback (most recent call last):
  File "/home/jebba/devel/tinygrad/tinygrad/test/external/external_test_dist_world.py", line 6, in <module>
    from extra.dist import world
  File "/home/jebba/devel/tinygrad/tinygrad/extra/dist/world.py", line 6, in <module>
    from tinygrad.runtime.lib import RawBuffer, RawBufferCopyInOut
ModuleNotFoundError: No module named 'tinygrad.runtime.lib'

external/external_test_embedding.py


external/external_test_example.py

.
======================================================================
ERROR: test_2_plus_3 (__main__.TestExample) (device='CLANG')
----------------------------------------------------------------------
Traceback (most recent call last):
  File "/home/jebba/devel/tinygrad/tinygrad/test/external/external_test_example.py", line 21, in ret
    fxn(self, device)
  File "/home/jebba/devel/tinygrad/tinygrad/test/external/external_test_example.py", line 37, in test_2_plus_3
    print(f"{a.numpy()} + {b.numpy()} = {result.numpy()}")
  File "/home/jebba/devel/tinygrad/tinygrad/tinygrad/tensor.py", line 155, in numpy
    return np.frombuffer(self._data(), dtype=self.dtype.np).reshape(self.shape)
  File "/home/jebba/devel/tinygrad/tinygrad/tinygrad/tensor.py", line 142, in _data
    return cast(Buffer, t.cast(t.dtype.scalar()).contiguous().realize().lazydata.base.realized).as_buffer()
  File "/home/jebba/devel/tinygrad/tinygrad/tinygrad/tensor.py", line 116, in realize
    run_schedule(self.lazydata.schedule())
  File "/home/jebba/devel/tinygrad/tinygrad/tinygrad/realize.py", line 48, in run_schedule
    prg = lower_schedule_item(si)
  File "/home/jebba/devel/tinygrad/tinygrad/tinygrad/realize.py", line 39, in lower_schedule_item
    return Device[si.out.device].get_runner(si.ast)
  File "/home/jebba/devel/tinygrad/tinygrad/tinygrad/device.py", line 348, in get_runner
    def get_runner(self, ast:LazyOp) -> CompiledASTRunner: return self.to_program(self.get_linearizer(ast))
  File "/home/jebba/devel/tinygrad/tinygrad/tinygrad/device.py", line 321, in to_program
    return CompiledASTRunner(k.ast, k.name, self.compiler.render(to_function_name(k.name), k.uops), self, k.global_size, k.local_size)
  File "/home/jebba/devel/tinygrad/tinygrad/tinygrad/device.py", line 284, in __init__
    lib:bytes = precompiled if precompiled is not None else self.device.compiler.compile_cached(prg)
  File "/home/jebba/devel/tinygrad/tinygrad/tinygrad/device.py", line 272, in compile_cached
    lib = self.compile(src)
  File "/home/jebba/devel/tinygrad/tinygrad/tinygrad/runtime/ops_clang.py", line 15, in compile
    subprocess.check_output(args=('clang -shared -march=native -O2 -Wall -Werror -x c -fPIC - -o '+ \
  File "/usr/lib/python3.10/subprocess.py", line 421, in check_output
    return run(*popenargs, stdout=PIPE, timeout=timeout, check=True,
  File "/usr/lib/python3.10/subprocess.py", line 503, in run
    with Popen(*popenargs, **kwargs) as process:
  File "/usr/lib/python3.10/subprocess.py", line 971, in __init__
    self._execute_child(args, executable, preexec_fn, close_fds,
  File "/usr/lib/python3.10/subprocess.py", line 1863, in _execute_child
    raise child_exception_type(errno_num, err_msg, err_filename)
FileNotFoundError: [Errno 2] No such file or directory: 'clang'

======================================================================
ERROR: test_example_matmul (__main__.TestExample) (device='CLANG')
----------------------------------------------------------------------
Traceback (most recent call last):
  File "/home/jebba/devel/tinygrad/tinygrad/test/external/external_test_example.py", line 21, in ret
    fxn(self, device)
  File "/home/jebba/devel/tinygrad/tinygrad/test/external/external_test_example.py", line 66, in test_example_matmul
    x.grad.numpy()  # dz/dx
  File "/home/jebba/devel/tinygrad/tinygrad/tinygrad/tensor.py", line 155, in numpy
    return np.frombuffer(self._data(), dtype=self.dtype.np).reshape(self.shape)
  File "/home/jebba/devel/tinygrad/tinygrad/tinygrad/tensor.py", line 142, in _data
    return cast(Buffer, t.cast(t.dtype.scalar()).contiguous().realize().lazydata.base.realized).as_buffer()
  File "/home/jebba/devel/tinygrad/tinygrad/tinygrad/tensor.py", line 116, in realize
    run_schedule(self.lazydata.schedule())
  File "/home/jebba/devel/tinygrad/tinygrad/tinygrad/realize.py", line 48, in run_schedule
    prg = lower_schedule_item(si)
  File "/home/jebba/devel/tinygrad/tinygrad/tinygrad/realize.py", line 39, in lower_schedule_item
    return Device[si.out.device].get_runner(si.ast)
  File "/home/jebba/devel/tinygrad/tinygrad/tinygrad/device.py", line 348, in get_runner
    def get_runner(self, ast:LazyOp) -> CompiledASTRunner: return self.to_program(self.get_linearizer(ast))
  File "/home/jebba/devel/tinygrad/tinygrad/tinygrad/device.py", line 321, in to_program
    return CompiledASTRunner(k.ast, k.name, self.compiler.render(to_function_name(k.name), k.uops), self, k.global_size, k.local_size)
  File "/home/jebba/devel/tinygrad/tinygrad/tinygrad/device.py", line 284, in __init__
    lib:bytes = precompiled if precompiled is not None else self.device.compiler.compile_cached(prg)
  File "/home/jebba/devel/tinygrad/tinygrad/tinygrad/device.py", line 272, in compile_cached
    lib = self.compile(src)
  File "/home/jebba/devel/tinygrad/tinygrad/tinygrad/runtime/ops_clang.py", line 15, in compile
    subprocess.check_output(args=('clang -shared -march=native -O2 -Wall -Werror -x c -fPIC - -o '+ \
  File "/usr/lib/python3.10/subprocess.py", line 421, in check_output
    return run(*popenargs, stdout=PIPE, timeout=timeout, check=True,
  File "/usr/lib/python3.10/subprocess.py", line 503, in run
    with Popen(*popenargs, **kwargs) as process:
  File "/usr/lib/python3.10/subprocess.py", line 971, in __init__
    self._execute_child(args, executable, preexec_fn, close_fds,
  File "/usr/lib/python3.10/subprocess.py", line 1863, in _execute_child
    raise child_exception_type(errno_num, err_msg, err_filename)
FileNotFoundError: [Errno 2] No such file or directory: 'clang'

======================================================================
ERROR: test_example_readme (__main__.TestExample) (device='CLANG')
----------------------------------------------------------------------
Traceback (most recent call last):
  File "/home/jebba/devel/tinygrad/tinygrad/test/external/external_test_example.py", line 21, in ret
    fxn(self, device)
  File "/home/jebba/devel/tinygrad/tinygrad/test/external/external_test_example.py", line 47, in test_example_readme
    x.grad.numpy()  # dz/dx
  File "/home/jebba/devel/tinygrad/tinygrad/tinygrad/tensor.py", line 155, in numpy
    return np.frombuffer(self._data(), dtype=self.dtype.np).reshape(self.shape)
  File "/home/jebba/devel/tinygrad/tinygrad/tinygrad/tensor.py", line 142, in _data
    return cast(Buffer, t.cast(t.dtype.scalar()).contiguous().realize().lazydata.base.realized).as_buffer()
  File "/home/jebba/devel/tinygrad/tinygrad/tinygrad/tensor.py", line 116, in realize
    run_schedule(self.lazydata.schedule())
  File "/home/jebba/devel/tinygrad/tinygrad/tinygrad/realize.py", line 48, in run_schedule
    prg = lower_schedule_item(si)
  File "/home/jebba/devel/tinygrad/tinygrad/tinygrad/realize.py", line 39, in lower_schedule_item
    return Device[si.out.device].get_runner(si.ast)
  File "/home/jebba/devel/tinygrad/tinygrad/tinygrad/device.py", line 348, in get_runner
    def get_runner(self, ast:LazyOp) -> CompiledASTRunner: return self.to_program(self.get_linearizer(ast))
  File "/home/jebba/devel/tinygrad/tinygrad/tinygrad/device.py", line 321, in to_program
    return CompiledASTRunner(k.ast, k.name, self.compiler.render(to_function_name(k.name), k.uops), self, k.global_size, k.local_size)
  File "/home/jebba/devel/tinygrad/tinygrad/tinygrad/device.py", line 284, in __init__
    lib:bytes = precompiled if precompiled is not None else self.device.compiler.compile_cached(prg)
  File "/home/jebba/devel/tinygrad/tinygrad/tinygrad/device.py", line 272, in compile_cached
    lib = self.compile(src)
  File "/home/jebba/devel/tinygrad/tinygrad/tinygrad/runtime/ops_clang.py", line 15, in compile
    subprocess.check_output(args=('clang -shared -march=native -O2 -Wall -Werror -x c -fPIC - -o '+ \
  File "/usr/lib/python3.10/subprocess.py", line 421, in check_output
    return run(*popenargs, stdout=PIPE, timeout=timeout, check=True,
  File "/usr/lib/python3.10/subprocess.py", line 503, in run
    with Popen(*popenargs, **kwargs) as process:
  File "/usr/lib/python3.10/subprocess.py", line 971, in __init__
    self._execute_child(args, executable, preexec_fn, close_fds,
  File "/usr/lib/python3.10/subprocess.py", line 1863, in _execute_child
    raise child_exception_type(errno_num, err_msg, err_filename)
FileNotFoundError: [Errno 2] No such file or directory: 'clang'

----------------------------------------------------------------------
Ran 4 tests in 4.673s

FAILED (errors=3)
TORCH
[2] + [3] = [5]
GPU
[2] + [3] = [5]
PYTHON
[2] + [3] = [5]
CLANG
HIP
[2] + [3] = [5]
METAL
WARNING: METAL test isn't running
LLVM
[2] + [3] = [5]
CUDA
WARNING: CUDA test isn't running
CPU
[2] + [3] = [5]
TORCH
GPU
PYTHON
CLANG
HIP
METAL
WARNING: METAL test isn't running
LLVM
CUDA
WARNING: CUDA test isn't running
CPU
TORCH
GPU
PYTHON
CLANG
HIP
METAL
WARNING: METAL test isn't running
LLVM
CUDA
WARNING: CUDA test isn't running
CPU
TORCH
GPU
PYTHON
CLANG
HIP
METAL
WARNING: METAL test isn't running
LLVM
CUDA
WARNING: CUDA test isn't running
CPU

external/external_test_image.py

.....
----------------------------------------------------------------------
Ran 5 tests in 1.683s

OK

external/external_test_jit_on_models.py

Traceback (most recent call last):
  File "/home/jebba/devel/tinygrad/tinygrad/test/external/external_test_jit_on_models.py", line 7, in <module>
    from test.helpers import derandomize_model
ModuleNotFoundError: No module named 'test.helpers'

external/external_test_onnx_backend.py

.s.s.s.s.s.s.s.sss.s.s.s.sss.sss.sss.sss.s.sssssssss.s.s.s.s.s.s.s.s.s.s.s.s.s.s.s.s.s.s.s.s.s.s.s.s.s.s.s.s.s.s.s.s.s.s.s.s.s.s.s.s.s.s.s.s.s.s.s.s.s.sprepare <class '__main__.TinygradBackend'> CPU ['x']
0: op Abs shape [(3, 4, 5)] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['x']
0: op Acos shape [(3, 4, 5)] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['x']
0: op Acos shape [(3,)] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['x']
0: op Acosh shape [(3, 4, 5)] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['x']
0: op Acosh shape [(3,)] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['R', 'T', 'X', 'G', 'H']
0: op Adagrad shape [(), (), (1,), (1,), (1,)] opt {'decay_factor': 0.10000000149011612, 'epsilon': 9.999999747378752e-06, 'norm_coefficient': 0.0010000000474974513}
prepare <class '__main__.TinygradBackend'> CPU ['R', 'T', 'X1', 'X2', 'G1', 'G2', 'H1', 'H2']
0: op Adagrad shape [(), (), (1,), (2,), (1,), (2,), (1,), (2,)] opt {'decay_factor': 0.10000000149011612, 'epsilon': 9.999999747378752e-06, 'norm_coefficient': 0.0010000000474974513}
prepare <class '__main__.TinygradBackend'> CPU ['R', 'T', 'X', 'G', 'V', 'H']
0: op Adam shape [(), (), (2,), (2,), (2,), (2,)] opt {'alpha': 0.949999988079071, 'beta': 0.10000000149011612, 'epsilon': 1.0000000116860974e-07, 'norm_coefficient': 0.0010000000474974513}
prepare <class '__main__.TinygradBackend'> CPU ['x', 'y']
0: op Add shape [(3, 4, 5), (5,)] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['x', 'y']
0: op Add shape [(3, 4, 5), (3, 4, 5)] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['x', 'y']
0: op Add shape [(3, 4, 5), (3, 4, 5)] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['theta', 'size']
0: op AffineGrid shape [(2, 2, 3), (4,)] opt {'align_corners': 1}
prepare <class '__main__.TinygradBackend'> CPU ['theta', 'size']
0: op AffineGrid shape [(2, 2, 3), (4,)] opt {'align_corners': 0}
prepare <class '__main__.TinygradBackend'> CPU ['theta', 'size']
0: op AffineGrid shape [(2, 3, 4), (5,)] opt {'align_corners': 1}
prepare <class '__main__.TinygradBackend'> CPU ['theta', 'size']
0: op AffineGrid shape [(2, 3, 4), (5,)] opt {'align_corners': 0}
prepare <class '__main__.TinygradBackend'> CPU ['x', 'y']
0: op ArrayFeatureExtractor shape [(3, 4), (2,)] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['X']
0: op Binarizer shape [(3, 4, 5)] opt {'threshold': 1.0}
prepare <class '__main__.TinygradBackend'> CPU ['x', 'y']
0: op And shape [(3, 4), (3, 4)] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['x', 'y']
0: op And shape [(3, 4, 5), (3, 4, 5)] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['x', 'y']
0: op And shape [(3, 4, 5, 6), (3, 4, 5, 6)] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['x', 'y']
0: op And shape [(3, 4, 5), (5,)] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['x', 'y']
0: op And shape [(3, 4, 5), (4, 5)] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['x', 'y']
0: op And shape [(3, 4, 5, 6), (5, 6)] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['x', 'y']
0: op And shape [(3, 4, 5, 6), (4, 5, 6)] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['x', 'y']
0: op And shape [(1, 4, 1, 6), (3, 1, 5, 6)] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['data']
0: op ArgMax shape [(2, 2)] opt {'keepdims': 1}
prepare <class '__main__.TinygradBackend'> CPU ['data']
0: op ArgMax shape [(2, 2)] opt {'keepdims': 1, 'select_last_index': 1}
prepare <class '__main__.TinygradBackend'> CPU ['data']
0: op ArgMax shape [(2, 3, 4)] opt {'keepdims': 1}
prepare <class '__main__.TinygradBackend'> CPU ['data']
0: op ArgMax shape [(2, 3, 4)] opt {'keepdims': 1, 'select_last_index': 1}
prepare <class '__main__.TinygradBackend'> CPU ['data']
0: op ArgMax shape [(2, 2)] opt {'axis': 1, 'keepdims': 1}
prepare <class '__main__.TinygradBackend'> CPU ['data']
0: op ArgMax shape [(2, 2)] opt {'axis': 1, 'keepdims': 1, 'select_last_index': 1}
prepare <class '__main__.TinygradBackend'> CPU ['data']
0: op ArgMax shape [(2, 3, 4)] opt {'axis': 1, 'keepdims': 1}
prepare <class '__main__.TinygradBackend'> CPU ['data']
0: op ArgMax shape [(2, 3, 4)] opt {'axis': 1, 'keepdims': 1, 'select_last_index': 1}
prepare <class '__main__.TinygradBackend'> CPU ['data']
0: op ArgMax shape [(2, 2)] opt {'axis': -1, 'keepdims': 1}
prepare <class '__main__.TinygradBackend'> CPU ['data']
0: op ArgMax shape [(2, 2)] opt {'axis': -1, 'keepdims': 1, 'select_last_index': 1}
prepare <class '__main__.TinygradBackend'> CPU ['data']
0: op ArgMax shape [(2, 3, 4)] opt {'axis': -1, 'keepdims': 1}
prepare <class '__main__.TinygradBackend'> CPU ['data']
0: op ArgMax shape [(2, 3, 4)] opt {'axis': -1, 'keepdims': 1, 'select_last_index': 1}
prepare <class '__main__.TinygradBackend'> CPU ['data']
0: op ArgMax shape [(2, 2)] opt {'axis': 1, 'keepdims': 0}
prepare <class '__main__.TinygradBackend'> CPU ['data']
0: op ArgMax shape [(2, 2)] opt {'axis': 1, 'keepdims': 0, 'select_last_index': 1}
prepare <class '__main__.TinygradBackend'> CPU ['data']
0: op ArgMax shape [(2, 3, 4)] opt {'axis': 1, 'keepdims': 0}
prepare <class '__main__.TinygradBackend'> CPU ['data']
0: op ArgMax shape [(2, 3, 4)] opt {'axis': 1, 'keepdims': 0, 'select_last_index': 1}
prepare <class '__main__.TinygradBackend'> CPU ['data']
0: op ArgMin shape [(2, 2)] opt {'keepdims': 1}
prepare <class '__main__.TinygradBackend'> CPU ['data']
0: op ArgMin shape [(2, 2)] opt {'keepdims': 1, 'select_last_index': 1}
prepare <class '__main__.TinygradBackend'> CPU ['data']
0: op ArgMin shape [(2, 3, 4)] opt {'keepdims': 1}
prepare <class '__main__.TinygradBackend'> CPU ['data']
0: op ArgMin shape [(2, 3, 4)] opt {'keepdims': 1, 'select_last_index': 1}
prepare <class '__main__.TinygradBackend'> CPU ['data']
0: op ArgMin shape [(2, 2)] opt {'axis': 1, 'keepdims': 1}
prepare <class '__main__.TinygradBackend'> CPU ['data']
0: op ArgMin shape [(2, 2)] opt {'axis': 1, 'keepdims': 1, 'select_last_index': 1}
prepare <class '__main__.TinygradBackend'> CPU ['data']
0: op ArgMin shape [(2, 3, 4)] opt {'axis': 1, 'keepdims': 1}
prepare <class '__main__.TinygradBackend'> CPU ['data']
0: op ArgMin shape [(2, 3, 4)] opt {'axis': 1, 'keepdims': 1, 'select_last_index': 1}
prepare <class '__main__.TinygradBackend'> CPU ['data']
0: op ArgMin shape [(2, 2)] opt {'axis': -1, 'keepdims': 1}
prepare <class '__main__.TinygradBackend'> CPU ['data']
0: op ArgMin shape [(2, 2)] opt {'axis': -1, 'keepdims': 1, 'select_last_index': 1}
prepare <class '__main__.TinygradBackend'> CPU ['data']
0: op ArgMin shape [(2, 3, 4)] opt {'axis': -1, 'keepdims': 1}
prepare <class '__main__.TinygradBackend'> CPU ['data']
0: op ArgMin shape [(2, 3, 4)] opt {'axis': -1, 'keepdims': 1, 'select_last_index': 1}
prepare <class '__main__.TinygradBackend'> CPU ['data']
0: op ArgMin shape [(2, 2)] opt {'axis': 1, 'keepdims': 0}
prepare <class '__main__.TinygradBackend'> CPU ['data']
0: op ArgMin shape [(2, 2)] opt {'axis': 1, 'keepdims': 0, 'select_last_index': 1}
prepare <class '__main__.TinygradBackend'> CPU ['data']
0: op ArgMin shape [(2, 3, 4)] opt {'axis': 1, 'keepdims': 0}
prepare <class '__main__.TinygradBackend'> CPU ['data']
0: op ArgMin shape [(2, 3, 4)] opt {'axis': 1, 'keepdims': 0, 'select_last_index': 1}
prepare <class '__main__.TinygradBackend'> CPU ['x']
0: op Asin shape [(3, 4, 5)] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['x']
0: op Asin shape [(3,)] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['x']
0: op Asinh shape [(3, 4, 5)] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['x']
0: op Asinh shape [(3,)] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['x']
0: op Atan shape [(3, 4, 5)] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['x']
0: op Atan shape [(3,)] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['x']
0: op Atanh shape [(3, 4, 5)] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['x']
0: op Atanh shape [(3,)] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['x']
0: op AveragePool shape [(1, 3, 32)] opt {'kernel_shape': (2,)}
prepare <class '__main__.TinygradBackend'> CPU ['x']
0: op AveragePool shape [(1, 1, 4, 4)] opt {'ceil_mode': 1, 'kernel_shape': (3, 3), 'strides': (2, 2)}
prepare <class '__main__.TinygradBackend'> CPU ['x']
.s.s.s.s.s.s.s.s.s.s.s.s.s.s.s.s.s.s.sssss.s.s.s.sssssssssssssssssssssssssssssssssssssssssssssssssssssssssssssssssssssss.s.sssssssss.sssssssssssssssssss.sssssssssssssssssssssssssssssssssssssss.s.s.s.s.s.sssssssssssssssssssss.s.sssssssssssssssssssssssssssss.s.s.s.s.s.s.s.s.s0: op AveragePool shape [(1, 3, 32, 32)] opt {'kernel_shape': (2, 2)}
prepare <class '__main__.TinygradBackend'> CPU ['x']
0: op AveragePool shape [(1, 1, 4, 4)] opt {'ceil_mode': 1, 'dilations': (2, 2), 'kernel_shape': (2, 2), 'strides': (1, 1)}
prepare <class '__main__.TinygradBackend'> CPU ['x']
0: op AveragePool shape [(1, 3, 28, 28)] opt {'count_include_pad': 1, 'kernel_shape': (3, 3), 'pads': (2, 2, 2, 2)}
prepare <class '__main__.TinygradBackend'> CPU ['x']
0: op AveragePool shape [(1, 3, 28, 28)] opt {'kernel_shape': (3, 3), 'pads': (2, 2, 2, 2)}
prepare <class '__main__.TinygradBackend'> CPU ['x']
0: op AveragePool shape [(1, 1, 5, 5)] opt {'count_include_pad': 1, 'kernel_shape': (5, 5), 'pads': (2, 2, 2, 2)}
prepare <class '__main__.TinygradBackend'> CPU ['x']
0: op AveragePool shape [(1, 1, 5, 5)] opt {'kernel_shape': (5, 5), 'pads': (2, 2, 2, 2)}
prepare <class '__main__.TinygradBackend'> CPU ['x']
0: op AveragePool shape [(1, 1, 5, 5)] opt {'auto_pad': 'SAME_UPPER', 'kernel_shape': (3, 3), 'strides': (2, 2)}
prepare <class '__main__.TinygradBackend'> CPU ['x']
0: op AveragePool shape [(1, 1, 5, 5)] opt {'kernel_shape': (2, 2), 'strides': (2, 2)}
prepare <class '__main__.TinygradBackend'> CPU ['x']
0: op AveragePool shape [(1, 3, 32, 32)] opt {'auto_pad': 'SAME_LOWER', 'kernel_shape': (2, 2)}
prepare <class '__main__.TinygradBackend'> CPU ['x']
0: op AveragePool shape [(1, 3, 32, 32)] opt {'auto_pad': 'SAME_UPPER', 'kernel_shape': (2, 2)}
prepare <class '__main__.TinygradBackend'> CPU ['x']
0: op AveragePool shape [(1, 3, 32, 32)] opt {'kernel_shape': (5, 5), 'strides': (3, 3)}
prepare <class '__main__.TinygradBackend'> CPU ['x']
0: op AveragePool shape [(1, 3, 32, 32, 32)] opt {'kernel_shape': (2, 2, 2)}
prepare <class '__main__.TinygradBackend'> CPU ['x']
0: op AveragePool shape [(1, 1, 32, 32, 32)] opt {'ceil_mode': 0, 'count_include_pad': 0, 'dilations': (2, 2, 2), 'kernel_shape': (5, 5, 5), 'strides': (3, 3, 3)}
prepare <class '__main__.TinygradBackend'> CPU ['x']
0: op AveragePool shape [(1, 1, 32, 32, 32)] opt {'ceil_mode': 1, 'count_include_pad': 0, 'dilations': (2, 2, 2), 'kernel_shape': (5, 5, 5), 'strides': (3, 3, 3)}
prepare <class '__main__.TinygradBackend'> CPU ['x']
0: op AveragePool shape [(1, 1, 32, 32, 32)] opt {'ceil_mode': 0, 'count_include_pad': 1, 'dilations': (2, 2, 2), 'kernel_shape': (5, 5, 5), 'strides': (3, 3, 3)}
prepare <class '__main__.TinygradBackend'> CPU ['x']
0: op AveragePool shape [(1, 1, 32, 32, 32)] opt {'ceil_mode': 1, 'count_include_pad': 1, 'dilations': (2, 2, 2), 'kernel_shape': (5, 5, 5), 'strides': (3, 3, 3)}
prepare <class '__main__.TinygradBackend'> CPU ['x']
0: op AveragePool shape [(1, 1, 4, 4, 4)] opt {'ceil_mode': 1, 'dilations': (2, 2, 2), 'kernel_shape': (2, 2, 2), 'strides': (1, 1, 1)}
prepare <class '__main__.TinygradBackend'> CPU ['x', 'W']
0: op Conv shape [(1, 1, 5, 5), (1, 1, 3, 3)] opt {'kernel_shape': (3, 3), 'pads': (1, 1, 1, 1)}
prepare <class '__main__.TinygradBackend'> CPU ['x', 'W']
0: op Conv shape [(1, 1, 5, 5), (1, 1, 3, 3)] opt {'kernel_shape': (3, 3), 'pads': (0, 0, 0, 0)}
prepare <class '__main__.TinygradBackend'> CPU ['x', 's', 'bias', 'mean', 'var']
0: op BatchNormalization shape [(2, 3, 4, 5), (3,), (3,), (3,), (3,)] opt {'epsilon': 0.009999999776482582}
prepare <class '__main__.TinygradBackend'> CPU ['x', 's', 'bias', 'mean', 'var']
0: op BatchNormalization shape [(2, 3, 4, 5), (3,), (3,), (3,), (3,)] opt {'epsilon': 0.009999999776482582, 'training_mode': 1}
prepare <class '__main__.TinygradBackend'> CPU ['x', 's', 'bias', 'mean', 'var']
0: op BatchNormalization shape [(2, 3, 4, 5), (3,), (3,), (3,), (3,)] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['x', 's', 'bias', 'mean', 'var']
0: op BatchNormalization shape [(2, 3, 4, 5), (3,), (3,), (3,), (3,)] opt {'training_mode': 1}
prepare <class '__main__.TinygradBackend'> CPU ['input']
0: op Cast shape [(3, 4)] opt {'to': 1}
prepare <class '__main__.TinygradBackend'> CPU ['input']
0: op Cast shape [(3, 4)] opt {'to': 11}
prepare <class '__main__.TinygradBackend'> CPU ['input']
0: op Cast shape [(3, 4)] opt {'to': 1}
prepare <class '__main__.TinygradBackend'> CPU ['input']
0: op Cast shape [(3, 4)] opt {'to': 11}
prepare <class '__main__.TinygradBackend'> CPU ['input', 'like']
0: op CastLike shape [(3, 4), (1,)] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['input', 'like']
0: op Cast shape [(3, 4)] opt {'to': 1, 'saturate': 1}
prepare <class '__main__.TinygradBackend'> CPU ['input', 'like']
0: op CastLike shape [(3, 4), (1,)] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['input', 'like']
0: op Cast shape [(3, 4)] opt {'to': 11, 'saturate': 1}
prepare <class '__main__.TinygradBackend'> CPU ['input', 'like']
0: op CastLike shape [(3, 4), (1,)] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['input', 'like']
0: op Cast shape [(3, 4)] opt {'to': 1, 'saturate': 1}
prepare <class '__main__.TinygradBackend'> CPU ['input', 'like']
0: op CastLike shape [(3, 4), (1,)] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['input', 'like']
0: op Cast shape [(3, 4)] opt {'to': 11, 'saturate': 1}
prepare <class '__main__.TinygradBackend'> CPU ['x']
0: op Ceil shape [(3, 4, 5)] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['x']
0: op Ceil shape [(2,)] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['X']
0: op Celu shape [(3, 3, 3, 1)] opt {'alpha': 2.0}
prepare <class '__main__.TinygradBackend'> CPU ['X']
0: op Constant shape [] opt {'value': <Tensor <LB HIP (1,) contig:True (<LoadOps.COPY: 3>, None)> on HIP with grad None>}
1: op Div shape [(3, 3, 3, 1), (1,)] opt {}
2: op Elu shape [(3, 3, 3, 1)] opt {'alpha': 1.0}
3: op Mul shape [(1,), (3, 3, 3, 1)] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['x', 'shape']
0: op CenterCropPad shape [(20, 8, 3), (3,)] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['x', 'shape']
0: op Constant shape [] opt {'value': <Tensor <LB HIP (1,) contig:True (<LoadOps.COPY: 3>, None)> on HIP with grad None>}
1: op Shape shape [(20, 8, 3)] opt {}
2: op Max shape [(3,), (3,)] opt {}
3: op Sub shape [(3,), (3,)] opt {}
4: op Div shape [(3,), (1,)] opt {}
5: op Sub shape [(3,), (3,)] opt {}
6: op Concat shape [(3,), (3,)] opt {'axis': 0}
7: op Pad shape [(20, 8, 3), (6,)] opt {}
8: op Shape shape [(20, 10, 3)] opt {}
9: op Sub shape [(3,), (3,)] opt {}
10: op Div shape [(3,), (1,)] opt {}
11: op Add shape [(3,), (3,)] opt {}
12: op Slice shape [(20, 10, 3), (3,), (3,)] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['x', 'shape']
0: op CenterCropPad shape [(3, 20, 8), (2,)] opt {'axes': (1, 2)}
prepare <class '__main__.TinygradBackend'> CPU ['x', 'shape']
0: op Constant shape [] opt {'value': <Tensor <LB HIP (1,) contig:True (<LoadOps.COPY: 3>, None)> on HIP with grad None>}
1: op Constant shape [] opt {'value_ints': (1, 2)}
2: op Shape shape [(3, 20, 8)] opt {}
3: op Gather shape [(3,), (2,)] opt {}
4: op Max shape [(2,), (2,)] opt {}
5: op Sub shape [(2,), (2,)] opt {}
6: op Div shape [(2,), (1,)] opt {}
7: op Sub shape [(2,), (2,)] opt {}
8: op Concat shape [(2,), (2,)] opt {'axis': 0}
9: op Pad shape [(3, 20, 8), (4,), None, (2,)] opt {}
10: op Shape shape [(3, 20, 9)] opt {}
11: op Gather shape [(3,), (2,)] opt {}
12: op Sub shape [(2,), (2,)] opt {}
13: op Div shape [(2,), (1,)] opt {}
14: op Add shape [(2,), (2,)] opt {}
15: op Slice shape [(3, 20, 9), (2,), (2,), (2,)] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['x', 'shape']
0: op CenterCropPad shape [(20, 8, 3), (2,)] opt {'axes': (0, 1)}
prepare <class '__main__.TinygradBackend'> CPU ['x', 'shape']
0: op Constant shape [] opt {'value': <Tensor <LB HIP (1,) contig:True (<LoadOps.COPY: 3>, None)> on HIP with grad None>}
1: op Constant shape [] opt {'value_ints': (0, 1)}
2: op Shape shape [(20, 8, 3)] opt {}
3: op Gather shape [(3,), (2,)] opt {}
4: op Max shape [(2,), (2,)] opt {}
5: op Sub shape [(2,), (2,)] opt {}
6: op Div shape [(2,), (1,)] opt {}
7: op Sub shape [(2,), (2,)] opt {}
8: op Concat shape [(2,), (2,)] opt {'axis': 0}
9: op Pad shape [(20, 8, 3), (4,), None, (2,)] opt {}
10: op Shape shape [(20, 9, 3)] opt {}
.s.s.s.s.s.s.s.s.s.s.s.s.s.s.s.s.s.s.s.s.s.s.s.s.s.s.s.s.sssssssssss.s.s.s.s.s.s.s.s.s.s.s.s.s.s.s.s.s.s.s11: op Gather shape [(3,), (2,)] opt {}
12: op Sub shape [(2,), (2,)] opt {}
13: op Div shape [(2,), (1,)] opt {}
14: op Add shape [(2,), (2,)] opt {}
15: op Slice shape [(20, 9, 3), (2,), (2,), (2,)] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['x', 'shape']
0: op CenterCropPad shape [(20, 10, 3), (3,)] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['x', 'shape']
0: op Constant shape [] opt {'value': <Tensor <LB HIP (1,) contig:True (<LoadOps.COPY: 3>, None)> on HIP with grad None>}
1: op Shape shape [(20, 10, 3)] opt {}
2: op Max shape [(3,), (3,)] opt {}
3: op Sub shape [(3,), (3,)] opt {}
4: op Div shape [(3,), (1,)] opt {}
5: op Sub shape [(3,), (3,)] opt {}
6: op Concat shape [(3,), (3,)] opt {'axis': 0}
7: op Pad shape [(20, 10, 3), (6,)] opt {}
8: op Shape shape [(20, 10, 3)] opt {}
9: op Sub shape [(3,), (3,)] opt {}
10: op Div shape [(3,), (1,)] opt {}
11: op Add shape [(3,), (3,)] opt {}
12: op Slice shape [(20, 10, 3), (3,), (3,)] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['x', 'shape']
0: op CenterCropPad shape [(20, 8, 3), (2,)] opt {'axes': (-3, -2)}
prepare <class '__main__.TinygradBackend'> CPU ['x', 'shape']
0: op Constant shape [] opt {'value': <Tensor <LB HIP (1,) contig:True (<LoadOps.COPY: 3>, None)> on HIP with grad None>}
1: op Constant shape [] opt {'value_ints': (-3, -2)}
2: op Shape shape [(20, 8, 3)] opt {}
3: op Gather shape [(3,), (2,)] opt {}
4: op Max shape [(2,), (2,)] opt {}
5: op Sub shape [(2,), (2,)] opt {}
6: op Div shape [(2,), (1,)] opt {}
7: op Sub shape [(2,), (2,)] opt {}
8: op Concat shape [(2,), (2,)] opt {'axis': 0}
9: op Pad shape [(20, 8, 3), (4,), None, (2,)] opt {}
10: op Shape shape [(20, 9, 3)] opt {}
11: op Gather shape [(3,), (2,)] opt {}
12: op Sub shape [(2,), (2,)] opt {}
13: op Div shape [(2,), (1,)] opt {}
14: op Add shape [(2,), (2,)] opt {}
15: op Slice shape [(20, 9, 3), (2,), (2,), (2,)] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['x', 'shape']
0: op CenterCropPad shape [(10, 7, 3), (3,)] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['x', 'shape']
0: op Constant shape [] opt {'value': <Tensor <LB HIP (1,) contig:True (<LoadOps.COPY: 3>, None)> on HIP with grad None>}
1: op Shape shape [(10, 7, 3)] opt {}
2: op Max shape [(3,), (3,)] opt {}
3: op Sub shape [(3,), (3,)] opt {}
4: op Div shape [(3,), (1,)] opt {}
5: op Sub shape [(3,), (3,)] opt {}
6: op Concat shape [(3,), (3,)] opt {'axis': 0}
7: op Pad shape [(10, 7, 3), (6,)] opt {}
8: op Shape shape [(20, 10, 3)] opt {}
9: op Sub shape [(3,), (3,)] opt {}
10: op Div shape [(3,), (1,)] opt {}
11: op Add shape [(3,), (3,)] opt {}
12: op Slice shape [(20, 10, 3), (3,), (3,)] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['x', 'min', 'max']
0: op Clip shape [(3, 4, 5), (), ()] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['x']
0: op Clip shape [(3,), None, None] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['x']
0: op Identity shape [(3,)] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['x']
0: op Clip shape [(3,), None, None] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['x']
0: op Identity shape [(3,)] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['x', 'max']
0: op Clip shape [(3, 4, 5), None, ()] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['x', 'max']
0: op Less shape [(), (3, 4, 5)] opt {}
1: op Where shape [(3, 4, 5), (), (3, 4, 5)] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['x', 'min']
0: op Clip shape [(3, 4, 5), ()] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['x', 'min']
0: op Less shape [(3, 4, 5), ()] opt {}
1: op Where shape [(3, 4, 5), (), (3, 4, 5)] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['x', 'max']
0: op Clip shape [(3, 4, 5), None, ()] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['x', 'max']
0: op Less shape [(), (3, 4, 5)] opt {}
1: op Where shape [(3, 4, 5), (), (3, 4, 5)] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['x', 'min']
0: op Clip shape [(3, 4, 5), ()] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['x', 'min']
0: op Less shape [(3, 4, 5), ()] opt {}
1: op Where shape [(3, 4, 5), (), (3, 4, 5)] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['x', 'min', 'max']
0: op Clip shape [(3,), (), ()] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['x', 'min', 'max']
0: op Less shape [(3,), ()] opt {}
1: op Where shape [(3,), (), (3,)] opt {}
2: op Less shape [(), (3,)] opt {}
3: op Where shape [(3,), (), (3,)] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['x', 'min', 'max']
0: op Less shape [(3, 4, 5), ()] opt {}
1: op Where shape [(3, 4, 5), (), (3, 4, 5)] opt {}
2: op Less shape [(), (3, 4, 5)] opt {}
3: op Where shape [(3, 4, 5), (), (3, 4, 5)] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['x', 'min', 'max']
0: op Clip shape [(3,), (), ()] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['x', 'min', 'max']
0: op Less shape [(3,), ()] opt {}
1: op Where shape [(3,), (), (3,)] opt {}
2: op Less shape [(), (3,)] opt {}
3: op Where shape [(3,), (), (3,)] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['x', 'min', 'max']
0: op Clip shape [(3,), (), ()] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['x', 'min', 'max']
0: op Less shape [(3,), ()] opt {}
1: op Where shape [(3,), (), (3,)] opt {}
2: op Less shape [(), (3,)] opt {}
3: op Where shape [(3,), (), (3,)] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['x', 'min', 'max']
0: op Clip shape [(3,), (), ()] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['x', 'min', 'max']
0: op Less shape [(3,), ()] opt {}
1: op Where shape [(3,), (), (3,)] opt {}
2: op Less shape [(), (3,)] opt {}
3: op Where shape [(3,), (), (3,)] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['input', 'condition']
0: op Compress shape [(3, 2), (3,)] opt {'axis': 0}
prepare <class '__main__.TinygradBackend'> CPU ['input', 'condition']
0: op Compress shape [(3, 2), (2,)] opt {'axis': 1}
prepare <class '__main__.TinygradBackend'> CPU ['input', 'condition']
0: op Compress shape [(3, 2), (5,)] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['input', 'condition']
0: op Compress shape [(3, 2), (2,)] opt {'axis': -1}
prepare <class '__main__.TinygradBackend'> CPU ['value0', 'value1']
0: op Concat shape [(2,), (2,)] opt {'axis': 0}
prepare <class '__main__.TinygradBackend'> CPU ['value0', 'value1']
0: op Concat shape [(2,), (2,)] opt {'axis': -1}
prepare <class '__main__.TinygradBackend'> CPU ['value0', 'value1']
0: op Concat shape [(2, 2), (2, 2)] opt {'axis': 0}
prepare <class '__main__.TinygradBackend'> CPU ['value0', 'value1']
0: op Concat shape [(2, 2), (2, 2)] opt {'axis': 1}
prepare <class '__main__.TinygradBackend'> CPU ['value0', 'value1']
0: op Concat shape [(2, 2), (2, 2)] opt {'axis': -1}
prepare <class '__main__.TinygradBackend'> CPU ['value0', 'value1']
0: op Concat shape [(2, 2), (2, 2)] opt {'axis': -2}
prepare <class '__main__.TinygradBackend'> CPU ['value0', 'value1']
0: op Concat shape [(2, 2, 2), (2, 2, 2)] opt {'axis': 0}
prepare <class '__main__.TinygradBackend'> CPU ['value0', 'value1']
0: op Concat shape [(2, 2, 2), (2, 2, 2)] opt {'axis': 1}
prepare <class '__main__.TinygradBackend'> CPU ['value0', 'value1']
0: op Concat shape [(2, 2, 2), (2, 2, 2)] opt {'axis': 2}
prepare <class '__main__.TinygradBackend'> CPU ['value0', 'value1']
0: op Concat shape [(2, 2, 2), (2, 2, 2)] opt {'axis': -1}
prepare <class '__main__.TinygradBackend'> CPU ['value0', 'value1']
0: op Concat shape [(2, 2, 2), (2, 2, 2)] opt {'axis': -2}
prepare <class '__main__.TinygradBackend'> CPU ['value0', 'value1']
0: op Concat shape [(2, 2, 2), (2, 2, 2)] opt {'axis': -3}
prepare <class '__main__.TinygradBackend'> CPU []
0: op Constant shape [] opt {'value': <Tensor <LB HIP (5, 5) contig:True (<LoadOps.COPY: 3>, None)> on HIP with grad None>}
prepare <class '__main__.TinygradBackend'> CPU ['x', 'pads', 'value', 'axes']
0: op Pad shape [(1, 3, 4, 5), (4,), (), (2,)] opt {'mode': 'constant'}
prepare <class '__main__.TinygradBackend'> CPU ['x', 'pads', 'value']
0: op Pad shape [(1, 3, 4, 5), (8,), ()] opt {'mode': 'constant'}
prepare .s.s.s.s.s.s.s.sssss.s.s.s.s.s.s.s.s.s.s.s.s.s.s.s.s.s.s.s.sssss.s.s.s.s.s.s.s.sssssssssssssssss.s.s.s.s.s.s.s.s.s.sssssssssssss.sss.sss.s.s.s.s.s.s.s<class '__main__.TinygradBackend'> CPU ['x', 'pads', 'value', 'axes']
0: op Pad shape [(1, 3, 4, 5), (4,), (), (2,)] opt {'mode': 'constant'}
prepare <class '__main__.TinygradBackend'> CPU ['x']
0: op ConstantOfShape shape [(3,)] opt {'value': <Tensor <LB HIP (1,) contig:True (<LoadOps.COPY: 3>, None)> on HIP with grad None>}
prepare <class '__main__.TinygradBackend'> CPU ['x']
0: op ConstantOfShape shape [(1,)] opt {'value': <Tensor <LB HIP (1,) contig:True (<LoadOps.COPY: 3>, None)> on HIP with grad None>}
prepare <class '__main__.TinygradBackend'> CPU ['x']
0: op ConstantOfShape shape [(2,)] opt {'value': <Tensor <LB HIP (1,) contig:True (<LoadOps.COPY: 3>, None)> on HIP with grad None>}
prepare <class '__main__.TinygradBackend'> CPU ['x', 'W']
0: op Conv shape [(1, 1, 5, 5), (1, 1, 3, 3)] opt {'auto_pad': 'SAME_LOWER', 'kernel_shape': (3, 3), 'strides': (2, 2)}
prepare <class '__main__.TinygradBackend'> CPU ['x', 'W']
0: op Conv shape [(1, 1, 7, 5), (1, 1, 3, 3)] opt {'kernel_shape': (3, 3), 'pads': (1, 0, 1, 0), 'strides': (2, 2)}
prepare <class '__main__.TinygradBackend'> CPU ['x', 'W']
0: op Conv shape [(1, 1, 7, 5), (1, 1, 3, 3)] opt {'kernel_shape': (3, 3), 'pads': (0, 0, 0, 0), 'strides': (2, 2)}
prepare <class '__main__.TinygradBackend'> CPU ['x', 'W']
0: op Conv shape [(1, 1, 7, 5), (1, 1, 3, 3)] opt {'kernel_shape': (3, 3), 'pads': (1, 1, 1, 1), 'strides': (2, 2)}
prepare <class '__main__.TinygradBackend'> CPU ['X', 'W']
0: op ConvTranspose shape [(1, 1, 3), (1, 2, 3)] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['X', 'W']
0: op ConvTranspose shape [(1, 1, 3, 4, 5), (1, 2, 3, 3, 3)] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['X', 'W']
0: op ConvTranspose shape [(1, 1, 3, 3), (1, 2, 3, 3)] opt {'auto_pad': 'SAME_UPPER', 'strides': (2, 2)}
prepare <class '__main__.TinygradBackend'> CPU ['X', 'W']
0: op ConvTranspose shape [(1, 1, 3, 3), (1, 2, 3, 3)] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['X', 'W']
0: op ConvTranspose shape [(1, 1, 3, 3), (1, 1, 2, 2)] opt {'dilations': (2, 2)}
prepare <class '__main__.TinygradBackend'> CPU ['X', 'W']
0: op ConvTranspose shape [(1, 1, 3, 3), (1, 2, 3, 3)] opt {'kernel_shape': (3, 3), 'output_padding': (1, 1), 'output_shape': (10, 8), 'strides': (3, 2)}
prepare <class '__main__.TinygradBackend'> CPU ['X', 'W']
0: op ConvTranspose shape [(1, 1, 3, 3), (1, 2, 3, 3)] opt {'output_shape': (10, 8), 'strides': (3, 2)}
prepare <class '__main__.TinygradBackend'> CPU ['X', 'W']
0: op ConvTranspose shape [(1, 1, 3, 3), (1, 2, 3, 3)] opt {'output_padding': (1, 1), 'strides': (3, 2)}
prepare <class '__main__.TinygradBackend'> CPU ['X', 'W']
0: op ConvTranspose shape [(1, 1, 3, 3), (1, 2, 3, 3)] opt {'pads': (1, 2, 1, 2), 'strides': (3, 2)}
prepare <class '__main__.TinygradBackend'> CPU ['x']
0: op Cos shape [(3, 4, 5)] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['x']
0: op Cos shape [(3,)] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['x']
0: op Cosh shape [(3, 4, 5)] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['x']
0: op Cosh shape [(3,)] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['x', 'axis']
0: op CumSum shape [(5,), ()] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['x', 'axis']
0: op CumSum shape [(5,), ()] opt {'exclusive': 1}
prepare <class '__main__.TinygradBackend'> CPU ['x', 'axis']
0: op CumSum shape [(5,), ()] opt {'reverse': 1}
prepare <class '__main__.TinygradBackend'> CPU ['x', 'axis']
0: op CumSum shape [(5,), ()] opt {'exclusive': 1, 'reverse': 1}
prepare <class '__main__.TinygradBackend'> CPU ['x', 'axis']
0: op CumSum shape [(2, 3), ()] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['x', 'axis']
0: op CumSum shape [(2, 3), ()] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['x', 'axis']
0: op CumSum shape [(2, 3), ()] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['x']
0: op DepthToSpace shape [(1, 8, 2, 3)] opt {'blocksize': 2, 'mode': 'CRD'}
prepare <class '__main__.TinygradBackend'> CPU ['x']
0: op DepthToSpace shape [(1, 8, 2, 3)] opt {'blocksize': 2, 'mode': 'DCR'}
prepare <class '__main__.TinygradBackend'> CPU ['x', 'x_scale', 'x_zero_point']
0: op DequantizeLinear shape [(1, 3, 3, 2), (3,), (3,)] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['x', 'x_scale', 'x_zero_point']
0: op DequantizeLinear shape [(4,), (), ()] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['x', 'x_scale']
0: op DequantizeLinear shape [(5,), ()] opt {'axis': 0}
prepare <class '__main__.TinygradBackend'> CPU ['x', 'x_scale']
0: op DequantizeLinear shape [(5,), ()] opt {'axis': 0}
prepare <class '__main__.TinygradBackend'> CPU ['x', 'x_scale', 'zero_point']
0: op DequantizeLinear shape [(5,), (), (1,)] opt {'axis': 0}
prepare <class '__main__.TinygradBackend'> CPU ['x', 'x_scale']
0: op DequantizeLinear shape [(5,), ()] opt {'axis': 0}
prepare <class '__main__.TinygradBackend'> CPU ['x', 'y']
0: op Div shape [(3, 4, 5), (5,)] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['x', 'y']
0: op Div shape [(3, 4, 5), (3, 4, 5)] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['x', 'y']
0: op Div shape [(2,), (2,)] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['x', 'y']
0: op Div shape [(3, 4, 5), (3, 4, 5)] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['x']
0: op Dropout shape [(3, 4, 5)] opt {'seed': 0}
prepare <class '__main__.TinygradBackend'> CPU ['x']
0: op Dropout shape [(3, 4, 5)] opt {'seed': 0}
prepare <class '__main__.TinygradBackend'> CPU ['x', 'r']
0: op Dropout shape [(3, 4, 5), ()] opt {'seed': 0}
prepare <class '__main__.TinygradBackend'> CPU ['x']
0: op Dropout shape [(3,)] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['x', 'r']
0: op Dropout shape [(3, 4, 5), ()] opt {'seed': 0}
prepare <class '__main__.TinygradBackend'> CPU ['x']
0: op Dropout shape [(3, 4, 5)] opt {'ratio': 0.20000000298023224}
prepare <class '__main__.TinygradBackend'> CPU ['x', 'pads']
0: op Pad shape [(1, 3, 4, 5), (8,)] opt {'mode': 'edge'}
prepare <class '__main__.TinygradBackend'> CPU ['x', 'y']
0: op Einsum shape [(5, 2, 3), (5, 3, 4)] opt {'equation': 'bij, bjk -> bik'}
prepare <class '__main__.TinygradBackend'> CPU ['x']
0: op Einsum shape [(3, 4)] opt {'equation': 'ij->i'}
prepare <class '__main__.TinygradBackend'> CPU ['x']
0: op Einsum shape [(3, 4)] opt {'equation': 'ij->ji'}
prepare <class '__main__.TinygradBackend'> CPU ['x']
0: op Elu shape [(3, 4, 5)] opt {'alpha': 2.0}
prepare <class '__main__.TinygradBackend'> CPU ['x']
0: op Elu shape [(3, 4, 5)] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['x']
0: op Constant shape [] opt {'value_float': 1.0}
1: op CastLike shape [(), (3, 4, 5)] opt {}
2: op Constant shape [] opt {'value': <Tensor <LB HIP () contig:True (<LoadOps.CONST: 2>, None)> on HIP with grad None>}
3: op CastLike shape [(), (3, 4, 5)] opt {}
4: op Constant shape [] opt {'value': <Tensor <LB HIP () contig:True (<LoadOps.CONST: 2>, None)> on HIP with grad None>}
5: op CastLike shape [(), (3, 4, 5)] opt {}
6: op Less shape [(3, 4, 5), ()] opt {}
7: op Exp shape [(3, 4, 5)] opt {}
8: op Sub shape [(3, 4, 5), ()] opt {}
9: op Mul shape [(), (3, 4, 5)] opt {}
10: op Where shape [(3, 4, 5), (3, 4, 5), (3, 4, 5)] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['x']
0: op Elu shape [(3,)] opt {'alpha': 2.0}
prepare <class '__main__.TinygradBackend'> CPU ['x']
0: op Constant shape [] opt {'value_float': 2.0}
1: op CastLike shape [(), (3,)] opt {}
2: op Constant shape [] opt {'value': <Tensor <LB HIP () contig:True (<LoadOps.CONST: 2>, None)> on HIP with grad None>}
3: op CastLike shape [(), (3,)] opt {}
4: op Constant shape [] opt {'value': <Tensor <LB HIP () contig:True (<LoadOps.CONST: 2>, None)> on HIP with grad None>}
5: op CastLike shape [(), (3,)] opt {}
6: op Less shape [(3,), ()] opt {}
7: op Exp shape [(3,)] opt {}
8: op Sub shape [(3,), ()] opt {}
9: op Mul shape [(), (3,)] opt {}
10: op Where shape [(3,), (3,), (3,)] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['x']
0: op Constant shape [] opt {'value_float': 2.0}
1: op CastLike shape [(), (3, 4, 5)] opt {}
.s.s.sssss.s.s.s.s.s.s.s.s.s.s.s.s.s.s.s.s.s.s.s.s.s.s.s.s.s.sssssss.s.s.s.s.s.s.s.s.s.s2: op Constant shape [] opt {'value': <Tensor <LB HIP () contig:True (<LoadOps.CONST: 2>, None)> on HIP with grad None>}
3: op CastLike shape [(), (3, 4, 5)] opt {}
4: op Constant shape [] opt {'value': <Tensor <LB HIP () contig:True (<LoadOps.CONST: 2>, None)> on HIP with grad None>}
5: op CastLike shape [(), (3, 4, 5)] opt {}
6: op Less shape [(3, 4, 5), ()] opt {}
7: op Exp shape [(3, 4, 5)] opt {}
8: op Sub shape [(3, 4, 5), ()] opt {}
9: op Mul shape [(), (3, 4, 5)] opt {}
10: op Where shape [(3, 4, 5), (3, 4, 5), (3, 4, 5)] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['x', 'y']
0: op Equal shape [(3, 4, 5), (5,)] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['x', 'y']
0: op Equal shape [(3, 4, 5), (3, 4, 5)] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['x']
0: op Erf shape [(1, 3, 32, 32)] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['x']
0: op Exp shape [(3, 4, 5)] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['x']
0: op Exp shape [(3,)] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['data', 'new_shape']
0: op Expand shape [(3, 1), (3,)] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['data', 'new_shape']
0: op Expand shape [(3, 1), (2,)] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['x']
0: op EyeLike shape [(4, 5)] opt {'dtype': 1, 'k': 1}
prepare <class '__main__.TinygradBackend'> CPU ['x']
0: op EyeLike shape [(3, 4)] opt {'dtype': 11}
prepare <class '__main__.TinygradBackend'> CPU ['x']
0: op EyeLike shape [(4, 4)] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['a']
0: op Flatten shape [(2, 3, 4, 5)] opt {'axis': 0}
prepare <class '__main__.TinygradBackend'> CPU ['a']
0: op Flatten shape [(2, 3, 4, 5)] opt {'axis': 1}
prepare <class '__main__.TinygradBackend'> CPU ['a']
0: op Flatten shape [(2, 3, 4, 5)] opt {'axis': 2}
prepare <class '__main__.TinygradBackend'> CPU ['a']
0: op Flatten shape [(2, 3, 4, 5)] opt {'axis': 3}
prepare <class '__main__.TinygradBackend'> CPU ['a']
0: op Flatten shape [(5, 4, 3, 2)] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['a']
0: op Flatten shape [(2, 3, 4, 5)] opt {'axis': -1}
prepare <class '__main__.TinygradBackend'> CPU ['a']
0: op Flatten shape [(2, 3, 4, 5)] opt {'axis': -2}
prepare <class '__main__.TinygradBackend'> CPU ['a']
0: op Flatten shape [(2, 3, 4, 5)] opt {'axis': -3}
prepare <class '__main__.TinygradBackend'> CPU ['a']
0: op Flatten shape [(2, 3, 4, 5)] opt {'axis': -4}
prepare <class '__main__.TinygradBackend'> CPU ['x']
0: op Floor shape [(3, 4, 5)] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['x']
0: op Floor shape [(3,)] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['data', 'indices']
0: op Gather shape [(5, 4, 3, 2), (3,)] opt {'axis': 0}
prepare <class '__main__.TinygradBackend'> CPU ['data', 'indices']
0: op Gather shape [(5, 4, 3, 2), (3,)] opt {'axis': 1}
prepare <class '__main__.TinygradBackend'> CPU ['data', 'indices']
0: op Gather shape [(3, 3), (1, 2)] opt {'axis': 1}
prepare <class '__main__.TinygradBackend'> CPU ['data', 'indices']
0: op GatherElements shape [(2, 2), (2, 2)] opt {'axis': 1}
prepare <class '__main__.TinygradBackend'> CPU ['data', 'indices']
0: op GatherElements shape [(3, 3), (2, 3)] opt {'axis': 0}
prepare <class '__main__.TinygradBackend'> CPU ['data', 'indices']
0: op GatherElements shape [(3, 3), (2, 3)] opt {'axis': 0}
prepare <class '__main__.TinygradBackend'> CPU ['data', 'indices']
0: op Gather shape [(10,), (3,)] opt {'axis': 0}
prepare <class '__main__.TinygradBackend'> CPU ['x']
0: op Gelu shape [(3,)] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['x']
0: op Constant shape [] opt {'value': <Tensor <LB HIP () contig:True (<LoadOps.CONST: 2>, None)> on HIP with grad None>}
1: op CastLike shape [(), (3,)] opt {}
2: op Constant shape [] opt {'value': <Tensor <LB HIP () contig:True (<LoadOps.CONST: 2>, None)> on HIP with grad None>}
3: op CastLike shape [(), (3,)] opt {}
4: op Constant shape [] opt {'value': <Tensor <LB HIP () contig:True (<LoadOps.CONST: 2>, None)> on HIP with grad None>}
5: op CastLike shape [(), (3,)] opt {}
6: op Sqrt shape [()] opt {}
7: op Div shape [(3,), ()] opt {}
8: op Erf shape [(3,)] opt {}
9: op Sum shape [(), (3,)] opt {}
10: op Mul shape [(), (3,)] opt {}
11: op Mul shape [(3,), (3,)] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['x']
0: op Gelu shape [(3, 4, 5)] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['x']
0: op Constant shape [] opt {'value': <Tensor <LB HIP () contig:True (<LoadOps.CONST: 2>, None)> on HIP with grad None>}
1: op CastLike shape [(), (3, 4, 5)] opt {}
2: op Constant shape [] opt {'value': <Tensor <LB HIP () contig:True (<LoadOps.CONST: 2>, None)> on HIP with grad None>}
3: op CastLike shape [(), (3, 4, 5)] opt {}
4: op Constant shape [] opt {'value': <Tensor <LB HIP () contig:True (<LoadOps.CONST: 2>, None)> on HIP with grad None>}
5: op CastLike shape [(), (3, 4, 5)] opt {}
6: op Sqrt shape [()] opt {}
7: op Div shape [(3, 4, 5), ()] opt {}
8: op Erf shape [(3, 4, 5)] opt {}
9: op Sum shape [(), (3, 4, 5)] opt {}
10: op Mul shape [(), (3, 4, 5)] opt {}
11: op Mul shape [(3, 4, 5), (3, 4, 5)] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['x']
0: op Gelu shape [(3,)] opt {'approximate': 'tanh'}
prepare <class '__main__.TinygradBackend'> CPU ['x']
0: op Constant shape [] opt {'value': <Tensor <LB HIP () contig:True (<LoadOps.CONST: 2>, None)> on HIP with grad None>}
1: op CastLike shape [(), (3,)] opt {}
2: op Constant shape [] opt {'value': <Tensor <LB HIP () contig:True (<LoadOps.CONST: 2>, None)> on HIP with grad None>}
3: op CastLike shape [(), (3,)] opt {}
4: op Constant shape [] opt {'value': <Tensor <LB HIP () contig:True (<LoadOps.CONST: 2>, None)> on HIP with grad None>}
5: op CastLike shape [(), (3,)] opt {}
6: op Constant shape [] opt {'value': <Tensor <LB HIP () contig:True (<LoadOps.CONST: 2>, None)> on HIP with grad None>}
7: op CastLike shape [(), (3,)] opt {}
8: op Sqrt shape [()] opt {}
9: op Constant shape [] opt {'value': <Tensor <LB HIP () contig:True (<LoadOps.CONST: 2>, None)> on HIP with grad None>}
10: op CastLike shape [(), (3,)] opt {}
11: op Pow shape [(3,), ()] opt {}
12: op Mul shape [(), (3,)] opt {}
13: op Sum shape [(3,), (3,)] opt {}
14: op Mul shape [(), (3,)] opt {}
15: op Tanh shape [(3,)] opt {}
16: op Sum shape [(), (3,)] opt {}
17: op Mul shape [(), (3,)] opt {}
18: op Mul shape [(3,), (3,)] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['x']
0: op Gelu shape [(3, 4, 5)] opt {'approximate': 'tanh'}
prepare <class '__main__.TinygradBackend'> CPU ['x']
0: op Constant shape [] opt {'value': <Tensor <LB HIP () contig:True (<LoadOps.CONST: 2>, None)> on HIP with grad None>}
1: op CastLike shape [(), (3, 4, 5)] opt {}
2: op Constant shape [] opt {'value': <Tensor <LB HIP () contig:True (<LoadOps.CONST: 2>, None)> on HIP with grad None>}
3: op CastLike shape [(), (3, 4, 5)] opt {}
4: op Constant shape [] opt {'value': <Tensor <LB HIP () contig:True (<LoadOps.CONST: 2>, None)> on HIP with grad None>}
5: op CastLike shape [(), (3, 4, 5)] opt {}
6: op Constant shape [] opt {'value': <Tensor <LB HIP () contig:True (<LoadOps.CONST: 2>, None)> on HIP with grad None>}
7: op CastLike shape [(), (3, 4, 5)] opt {}
8: op Sqrt shape [()] opt {}
9: op Constant shape [] opt {'value': <Tensor <LB HIP () contig:True (<LoadOps.CONST: 2>, None)> on HIP with grad None>}
10: op CastLike shape [(), (3, 4, 5)] opt {}
11: op Pow shape [(3, 4, 5), ()] opt {}
12: op Mul shape [(), (3, 4, 5)] opt {}
13: op Sum shape [(3, 4, 5), (3, 4, 5)] opt {}
14: op Mul shape [(), (3, 4, 5)] opt {}
15: op Tanh shape [(3, 4, 5)] opt {}
16: op Sum shape [(), (3, 4, 5)] opt {}
17: op Mul shape [(), (3, 4, 5)] opt {}
18: op Mul shape [(3, 4, 5), (3, 4, 5)] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['a', 'b', 'c']
0: op Gemm shape [(4, 3), (5, 4), (1, 5)] opt {'alpha': 0.25, 'beta': 0.3499999940395355, 'transA': 1, 'transB': 1}
prepare <class '__main__.TinygradBackend'> CPU ['a', 'b', 'c']
0: op Gemm shape [(3, 5), (5, 4), (1, 4)] opt {'alpha': 0.5}
prepare <class '__main__.TinygradBackend'> CPU ['a', 'b', 'c']
.s.s.s.s.s.s.s.s.s.s.s.s.s.s.s.s.s.s.sssssssssssssssssssssssssssssssssssss.s.s.s.sssssssssssssssssssssssssssssssssssssss.s.s.s.s.s0: op Gemm shape [(2, 7), (7, 4), (1, 4)] opt {'beta': 0.5}
prepare <class '__main__.TinygradBackend'> CPU ['a', 'b', 'c']
0: op Gemm shape [(3, 6), (6, 4), (3, 4)] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['a', 'b']
0: op Gemm shape [(2, 10), (10, 3)] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['a', 'b', 'c']
0: op Gemm shape [(2, 3), (3, 4), ()] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['a', 'b', 'c']
0: op Gemm shape [(3, 7), (7, 3), (1,)] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['a', 'b', 'c']
0: op Gemm shape [(2, 7), (7, 4), (1, 4)] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['a', 'b', 'c']
0: op Gemm shape [(3, 5), (5, 4), (1, 4)] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['a', 'b', 'c']
0: op Gemm shape [(6, 3), (6, 4), (1, 4)] opt {'transA': 1}
prepare <class '__main__.TinygradBackend'> CPU ['a', 'b', 'c']
0: op Gemm shape [(3, 6), (4, 6), (1, 4)] opt {'transB': 1}
prepare <class '__main__.TinygradBackend'> CPU ['x']
0: op GlobalAveragePool shape [(1, 3, 5, 5)] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['x']
0: op GlobalAveragePool shape [(1, 1, 3, 3)] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['x']
0: op GlobalMaxPool shape [(1, 3, 5, 5)] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['x']
0: op GlobalMaxPool shape [(1, 1, 3, 3)] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['x', 'y']
0: op Greater shape [(3, 4, 5), (5,)] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['x', 'y']
0: op Greater shape [(3, 4, 5), (3, 4, 5)] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['x', 'y']
0: op GreaterOrEqual shape [(3, 4, 5), (5,)] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['x', 'y']
0: op Greater shape [(3, 4, 5), (5,)] opt {}
1: op Equal shape [(3, 4, 5), (5,)] opt {}
2: op Or shape [(3, 4, 5), (3, 4, 5)] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['x', 'y']
0: op GreaterOrEqual shape [(3, 4, 5), (3, 4, 5)] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['x', 'y']
0: op Greater shape [(3, 4, 5), (3, 4, 5)] opt {}
1: op Equal shape [(3, 4, 5), (3, 4, 5)] opt {}
2: op Or shape [(3, 4, 5), (3, 4, 5)] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['x', 'scale', 'bias']
0: op GroupNormalization shape [(3, 4, 2, 2), (2,), (2,)] opt {'epsilon': 0.009999999776482582, 'num_groups': 2}
prepare <class '__main__.TinygradBackend'> CPU ['x', 'scale', 'bias']
0: op Constant shape [] opt {'value': <Tensor <LB HIP (1,) contig:True (<LoadOps.COPY: 3>, None)> on HIP with grad None>}
1: op Cast shape [(1,)] opt {'to': 1}
2: op Shape shape [(3, 4, 2, 2)] opt {}
3: op Shape shape [(3, 4, 2, 2)] opt {'start': 1, 'end': 2}
4: op Constant shape [] opt {'value': <Tensor <LB HIP (1,) contig:True (<LoadOps.COPY: 3>, None)> on HIP with grad None>}
5: op Div shape [(1,), (1,)] opt {}
6: op Shape shape [(3, 4, 2, 2)] opt {'start': 0, 'end': 1}
7: op Shape shape [(3, 4, 2, 2)] opt {'start': 2}
8: op Concat shape [(1,), (1,), (1,), (2,)] opt {'axis': 0}
9: op Reshape shape [(3, 4, 2, 2), (5,)] opt {}
10: op Constant shape [] opt {'value_ints': (0, 0, -1)}
11: op Reshape shape [(3, 2, 2, 2, 2), (3,)] opt {}
12: op Constant shape [] opt {'value': <Tensor <LB HIP (1,) contig:True (<LoadOps.COPY: 3>, None)> on HIP with grad None>}
13: op ReduceMean shape [(3, 2, 8), (1,)] opt {}
14: op Mul shape [(3, 2, 8), (3, 2, 8)] opt {}
15: op ReduceMean shape [(3, 2, 8), (1,)] opt {}
16: op Mul shape [(3, 2, 1), (3, 2, 1)] opt {}
17: op Sub shape [(3, 2, 1), (3, 2, 1)] opt {}
18: op Add shape [(3, 2, 1), (1,)] opt {}
19: op Sqrt shape [(3, 2, 1)] opt {}
20: op Sub shape [(3, 2, 8), (3, 2, 1)] opt {}
21: op Div shape [(3, 2, 8), (3, 2, 1)] opt {}
22: op Constant shape [] opt {'value_ints': (1, -1, 1)}
23: op Cast shape [(2,)] opt {'to': 1}
24: op Cast shape [(2,)] opt {'to': 1}
25: op Reshape shape [(2,), (3,)] opt {}
26: op Reshape shape [(2,), (3,)] opt {}
27: op Mul shape [(1, 2, 1), (3, 2, 8)] opt {}
28: op Add shape [(3, 2, 8), (1, 2, 1)] opt {}
29: op Reshape shape [(3, 2, 8), (4,)] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['x', 'scale', 'bias']
0: op GroupNormalization shape [(3, 4, 2, 2), (2,), (2,)] opt {'num_groups': 2}
prepare <class '__main__.TinygradBackend'> CPU ['x', 'scale', 'bias']
0: op Constant shape [] opt {'value': <Tensor <LB HIP (1,) contig:True (<LoadOps.COPY: 3>, None)> on HIP with grad None>}
1: op Cast shape [(1,)] opt {'to': 1}
2: op Shape shape [(3, 4, 2, 2)] opt {}
3: op Shape shape [(3, 4, 2, 2)] opt {'start': 1, 'end': 2}
4: op Constant shape [] opt {'value': <Tensor <LB HIP (1,) contig:True (<LoadOps.COPY: 3>, None)> on HIP with grad None>}
5: op Div shape [(1,), (1,)] opt {}
6: op Shape shape [(3, 4, 2, 2)] opt {'start': 0, 'end': 1}
7: op Shape shape [(3, 4, 2, 2)] opt {'start': 2}
8: op Concat shape [(1,), (1,), (1,), (2,)] opt {'axis': 0}
9: op Reshape shape [(3, 4, 2, 2), (5,)] opt {}
10: op Constant shape [] opt {'value_ints': (0, 0, -1)}
11: op Reshape shape [(3, 2, 2, 2, 2), (3,)] opt {}
12: op Constant shape [] opt {'value': <Tensor <LB HIP (1,) contig:True (<LoadOps.COPY: 3>, None)> on HIP with grad None>}
13: op ReduceMean shape [(3, 2, 8), (1,)] opt {}
14: op Mul shape [(3, 2, 8), (3, 2, 8)] opt {}
15: op ReduceMean shape [(3, 2, 8), (1,)] opt {}
16: op Mul shape [(3, 2, 1), (3, 2, 1)] opt {}
17: op Sub shape [(3, 2, 1), (3, 2, 1)] opt {}
18: op Add shape [(3, 2, 1), (1,)] opt {}
19: op Sqrt shape [(3, 2, 1)] opt {}
20: op Sub shape [(3, 2, 8), (3, 2, 1)] opt {}
21: op Div shape [(3, 2, 8), (3, 2, 1)] opt {}
22: op Constant shape [] opt {'value_ints': (1, -1, 1)}
23: op Cast shape [(2,)] opt {'to': 1}
24: op Cast shape [(2,)] opt {'to': 1}
25: op Reshape shape [(2,), (3,)] opt {}
26: op Reshape shape [(2,), (3,)] opt {}
27: op Mul shape [(1, 2, 1), (3, 2, 8)] opt {}
28: op Add shape [(3, 2, 8), (1, 2, 1)] opt {}
29: op Reshape shape [(3, 2, 8), (4,)] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['x']
0: op HardSigmoid shape [(3, 4, 5)] opt {'alpha': 0.5, 'beta': 0.6000000238418579}
prepare <class '__main__.TinygradBackend'> CPU ['x']
0: op HardSigmoid shape [(3, 4, 5)] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['x']
0: op Constant shape [] opt {'value_float': 0.20000000298023224}
1: op CastLike shape [(), (3, 4, 5)] opt {}
2: op Constant shape [] opt {'value_float': 0.5}
3: op CastLike shape [(), (3, 4, 5)] opt {}
4: op Constant shape [] opt {'value': <Tensor <LB HIP () contig:True (<LoadOps.CONST: 2>, None)> on HIP with grad None>}
5: op CastLike shape [(), (3, 4, 5)] opt {}
6: op Constant shape [] opt {'value': <Tensor <LB HIP () contig:True (<LoadOps.CONST: 2>, None)> on HIP with grad None>}
7: op CastLike shape [(), (3, 4, 5)] opt {}
8: op Mul shape [(3, 4, 5), ()] opt {}
9: op Add shape [(3, 4, 5), ()] opt {}
10: op Min shape [(3, 4, 5), ()] opt {}
11: op Max shape [(3, 4, 5), ()] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['x']
0: op HardSigmoid shape [(3,)] opt {'alpha': 0.5, 'beta': 0.6000000238418579}
prepare <class '__main__.TinygradBackend'> CPU ['x']
0: op Constant shape [] opt {'value_float': 0.5}
1: op CastLike shape [(), (3,)] opt {}
2: op Constant shape [] opt {'value_float': 0.6000000238418579}
3: op CastLike shape [(), (3,)] opt {}
4: op Constant shape [] opt {'value': <Tensor <LB HIP () contig:True (<LoadOps.CONST: 2>, None)> on HIP with grad None>}
5: op CastLike shape [(), (3,)] opt {}
6: op Constant shape [] opt {'value': <Tensor <LB HIP () contig:True (<LoadOps.CONST: 2>, None)> on HIP with grad None>}
7: op CastLike shape [(), (3,)] opt {}
8: op Mul shape [(3,), ()] opt {}
9: op Add shape [(3,), ()] opt {}
10: op Min shape [(3,), ()] opt {}
11: op Max shape [(3,), ()] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['x']
0: op Constant shape [] opt {'value_float': 0.5}
1: op CastLike shape [(), (3, 4, 5)] opt {}
2: op Constant shape [] opt {'value_float': 0.6000000238418579}
3: op CastLike shape [(), (3, 4, 5)] opt {}
4: op Constant shape [] opt {'value': <Tensor <LB HIP () contig:True (<LoadOps.CONST: 2>, None)> on HIP with grad None>}
5: op CastLike shape [(), (3, 4, 5)] opt {}
.s.s.s.s.s.sssssss.s.s.s.s.s.s.s.s.s.s.s.s.s.s.s.s.s.s.s.s.s6: op Constant shape [] opt {'value': <Tensor <LB HIP () contig:True (<LoadOps.CONST: 2>, None)> on HIP with grad None>}
7: op CastLike shape [(), (3, 4, 5)] opt {}
8: op Mul shape [(3, 4, 5), ()] opt {}
9: op Add shape [(3, 4, 5), ()] opt {}
10: op Min shape [(3, 4, 5), ()] opt {}
11: op Max shape [(3, 4, 5), ()] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['x']
0: op HardSwish shape [(3, 4, 5)] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['x']
0: op HardSigmoid shape [(3, 4, 5)] opt {'alpha': 0.1666666716337204, 'beta': 0.5}
1: op Mul shape [(3, 4, 5), (3, 4, 5)] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['x']
0: op Identity shape [(1, 1, 2, 2)] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['opt_in']
0: op Identity shape [[<Tensor <LB HIP (5,) contig:True (<LoadOps.COPY: 3>, None)> on HIP with grad None>]] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['x']
0: op Identity shape [[<Tensor <LB HIP (1, 1, 2, 2) contig:True (<LoadOps.COPY: 3>, None)> on HIP with grad None>, <Tensor <LB HIP (1, 1, 2, 2) contig:True (<LoadOps.COPY: 3>, None)> on HIP with grad None>]] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['data']
0: op ImageDecoder shape [(3126,)] opt {'pixel_format': 'RGB'}
prepare <class '__main__.TinygradBackend'> CPU ['data']
0: op ImageDecoder shape [(1887,)] opt {'pixel_format': 'RGB'}
prepare <class '__main__.TinygradBackend'> CPU ['data']
0: op ImageDecoder shape [(1058,)] opt {'pixel_format': 'BGR'}
prepare <class '__main__.TinygradBackend'> CPU ['data']
0: op ImageDecoder shape [(1058,)] opt {'pixel_format': 'Grayscale'}
prepare <class '__main__.TinygradBackend'> CPU ['data']
0: op ImageDecoder shape [(1058,)] opt {'pixel_format': 'RGB'}
prepare <class '__main__.TinygradBackend'> CPU ['data']
0: op ImageDecoder shape [(312,)] opt {'pixel_format': 'RGB'}
prepare <class '__main__.TinygradBackend'> CPU ['data']
0: op ImageDecoder shape [(3085,)] opt {'pixel_format': 'RGB'}
prepare <class '__main__.TinygradBackend'> CPU ['data']
0: op ImageDecoder shape [(3212,)] opt {'pixel_format': 'RGB'}
prepare <class '__main__.TinygradBackend'> CPU ['data']
0: op ImageDecoder shape [(552,)] opt {'pixel_format': 'RGB'}
prepare <class '__main__.TinygradBackend'> CPU ['x', 's', 'bias']
0: op InstanceNormalization shape [(2, 3, 4, 5), (3,), (3,)] opt {'epsilon': 0.009999999776482582}
prepare <class '__main__.TinygradBackend'> CPU ['x', 's', 'bias']
0: op InstanceNormalization shape [(1, 2, 1, 3), (2,), (2,)] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['x']
0: op IsInf shape [(6,)] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['x']
0: op IsInf shape [(6,)] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['x']
0: op IsInf shape [(6,)] opt {'detect_positive': 0}
prepare <class '__main__.TinygradBackend'> CPU ['x']
0: op IsInf shape [(6,)] opt {'detect_negative': 0}
prepare <class '__main__.TinygradBackend'> CPU ['x']
0: op IsNaN shape [(6,)] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['x']
0: op IsNaN shape [(6,)] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['X', 'W', 'B']
0: op LayerNormalization shape [(3, 4), (3, 4), (3, 4)] opt {'axis': 0}
prepare <class '__main__.TinygradBackend'> CPU ['X', 'W', 'B']
0: op Constant shape [] opt {'value': <Tensor <LB HIP () contig:True (<LoadOps.CONST: 2>, None)> on HIP with grad None>}
1: op Cast shape [()] opt {'to': 1}
2: op Shape shape [(3, 4)] opt {}
3: op Size shape [(2,)] opt {}
4: op Constant shape [] opt {'value': <Tensor <LB HIP (1,) contig:True (<LoadOps.COPY: 3>, None)> on HIP with grad None>}
5: op Constant shape [] opt {'value': <Tensor <LB HIP (1,) contig:True (<LoadOps.COPY: 3>, None)> on HIP with grad None>}
6: op Slice shape [(2,), (1,), (1,)] opt {}
7: op Sub shape [2, (1,)] opt {}
8: op ConstantOfShape shape [(1,)] opt {'value': <Tensor <LB HIP (1,) contig:True (<LoadOps.COPY: 3>, None)> on HIP with grad None>}
9: op Concat shape [(0,), (2,)] opt {'axis': 0}
10: op Flatten shape [(3, 4)] opt {'axis': 0}
11: op Cast shape [(1, 12)] opt {'to': 1}
12: op ReduceMean shape [(1, 12)] opt {'axes': (1,)}
13: op Mul shape [(1, 12), (1, 12)] opt {}
14: op ReduceMean shape [(1, 12)] opt {'axes': (1,)}
15: op Mul shape [(1, 1), (1, 1)] opt {}
16: op Sub shape [(1, 1), (1, 1)] opt {}
17: op Add shape [(1, 1), ()] opt {}
18: op Sqrt shape [(1, 1)] opt {}
19: op Sub shape [(1, 12), (1, 1)] opt {}
20: op Div shape [(1, 12), (1, 1)] opt {}
21: op Cast shape [(1, 12)] opt {'to': 1}
22: op Flatten shape [(3, 4)] opt {'axis': 0}
23: op Mul shape [(1, 12), (1, 12)] opt {}
24: op Flatten shape [(3, 4)] opt {'axis': 0}
25: op Add shape [(1, 12), (1, 12)] opt {}
26: op Reshape shape [(1, 12), (2,)] opt {}
27: op Reciprocal shape [(1, 1)] opt {}
28: op Reshape shape [(1, 1), (2,)] opt {}
29: op Reshape shape [(1, 1), (2,)] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['X', 'W', 'B']
0: op Constant shape [] opt {'value': <Tensor <LB HIP () contig:True (<LoadOps.CONST: 2>, None)> on HIP with grad None>}
1: op Cast shape [()] opt {'to': 1}
2: op Shape shape [(3, 4)] opt {}
3: op Size shape [(2,)] opt {}
4: op Constant shape [] opt {'value': <Tensor <LB HIP (1,) contig:True (<LoadOps.COPY: 3>, None)> on HIP with grad None>}
5: op Constant shape [] opt {'value': <Tensor <LB HIP (1,) contig:True (<LoadOps.COPY: 3>, None)> on HIP with grad None>}
6: op Slice shape [(2,), (1,), (1,)] opt {}
7: op Sub shape [2, (1,)] opt {}
8: op ConstantOfShape shape [(1,)] opt {'value': <Tensor <LB HIP (1,) contig:True (<LoadOps.COPY: 3>, None)> on HIP with grad None>}
9: op Concat shape [(0,), (2,)] opt {'axis': 0}
10: op Flatten shape [(3, 4)] opt {'axis': 0}
11: op Cast shape [(1, 12)] opt {'to': 1}
12: op Constant shape [] opt {'value': <Tensor <LB HIP (1,) contig:True (<LoadOps.COPY: 3>, None)> on HIP with grad None>}
13: op ReduceMean shape [(1, 12), (1,)] opt {}
14: op Mul shape [(1, 12), (1, 12)] opt {}
15: op ReduceMean shape [(1, 12), (1,)] opt {}
16: op Mul shape [(1, 1), (1, 1)] opt {}
17: op Sub shape [(1, 1), (1, 1)] opt {}
18: op Add shape [(1, 1), ()] opt {}
19: op Sqrt shape [(1, 1)] opt {}
20: op Sub shape [(1, 12), (1, 1)] opt {}
21: op Div shape [(1, 12), (1, 1)] opt {}
22: op Cast shape [(1, 12)] opt {'to': 1}
23: op Flatten shape [(3, 4)] opt {'axis': 0}
24: op Mul shape [(1, 12), (1, 12)] opt {}
25: op Flatten shape [(3, 4)] opt {'axis': 0}
26: op Add shape [(1, 12), (1, 12)] opt {}
27: op Reshape shape [(1, 12), (2,)] opt {}
28: op Reciprocal shape [(1, 1)] opt {}
29: op Reshape shape [(1, 1), (2,)] opt {}
30: op Reshape shape [(1, 1), (2,)] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['X', 'W', 'B']
0: op LayerNormalization shape [(3, 4), (4,), (4,)] opt {'axis': 1}
prepare <class '__main__.TinygradBackend'> CPU ['X', 'W', 'B']
0: op Constant shape [] opt {'value': <Tensor <LB HIP () contig:True (<LoadOps.CONST: 2>, None)> on HIP with grad None>}
1: op Cast shape [()] opt {'to': 1}
2: op Shape shape [(3, 4)] opt {}
3: op Size shape [(2,)] opt {}
4: op Constant shape [] opt {'value': <Tensor <LB HIP (1,) contig:True (<LoadOps.COPY: 3>, None)> on HIP with grad None>}
5: op Constant shape [] opt {'value': <Tensor <LB HIP (1,) contig:True (<LoadOps.COPY: 3>, None)> on HIP with grad None>}
6: op Slice shape [(2,), (1,), (1,)] opt {}
7: op Sub shape [2, (1,)] opt {}
8: op ConstantOfShape shape [(1,)] opt {'value': <Tensor <LB HIP (1,) contig:True (<LoadOps.COPY: 3>, None)> on HIP with grad None>}
9: op Concat shape [(1,), (1,)] opt {'axis': 0}
10: op Flatten shape [(3, 4)] opt {'axis': 1}
11: op Cast shape [(3, 4)] opt {'to': 1}
12: op ReduceMean shape [(3, 4)] opt {'axes': (1,)}
13: op Mul shape [(3, 4), (3, 4)] opt {}
14: op ReduceMean shape [(3, 4)] opt {'axes': (1,)}
15: op Mul shape [(3, 1), (3, 1)] opt {}
16: op Sub shape [(3, 1), (3, 1)] opt {}
17: op Add shape [(3, 1), ()] opt {}
18: op Sqrt shape [(3, 1)] opt {}
19: op Sub shape [(3, 4), (3, 1)] opt {}
20: op Div shape [(3, 4), (3, 1)] opt {}
21: op Cast shape [(3, 4)] opt {'to': 1}
22: op Flatten shape [(4,)] opt {'axis': 0}
23: op Mul shape [(3, 4), (1, 4)] opt {}
24: op Flatten shape [(4,)] opt {'axis': 0}
.s.s.s.s.s.s.s25: op Add shape [(3, 4), (1, 4)] opt {}
26: op Reshape shape [(3, 4), (2,)] opt {}
27: op Reciprocal shape [(3, 1)] opt {}
28: op Reshape shape [(3, 1), (2,)] opt {}
29: op Reshape shape [(3, 1), (2,)] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['X', 'W', 'B']
0: op Constant shape [] opt {'value': <Tensor <LB HIP () contig:True (<LoadOps.CONST: 2>, None)> on HIP with grad None>}
1: op Cast shape [()] opt {'to': 1}
2: op Shape shape [(3, 4)] opt {}
3: op Size shape [(2,)] opt {}
4: op Constant shape [] opt {'value': <Tensor <LB HIP (1,) contig:True (<LoadOps.COPY: 3>, None)> on HIP with grad None>}
5: op Constant shape [] opt {'value': <Tensor <LB HIP (1,) contig:True (<LoadOps.COPY: 3>, None)> on HIP with grad None>}
6: op Slice shape [(2,), (1,), (1,)] opt {}
7: op Sub shape [2, (1,)] opt {}
8: op ConstantOfShape shape [(1,)] opt {'value': <Tensor <LB HIP (1,) contig:True (<LoadOps.COPY: 3>, None)> on HIP with grad None>}
9: op Concat shape [(1,), (1,)] opt {'axis': 0}
10: op Flatten shape [(3, 4)] opt {'axis': 1}
11: op Cast shape [(3, 4)] opt {'to': 1}
12: op Constant shape [] opt {'value': <Tensor <LB HIP (1,) contig:True (<LoadOps.COPY: 3>, None)> on HIP with grad None>}
13: op ReduceMean shape [(3, 4), (1,)] opt {}
14: op Mul shape [(3, 4), (3, 4)] opt {}
15: op ReduceMean shape [(3, 4), (1,)] opt {}
16: op Mul shape [(3, 1), (3, 1)] opt {}
17: op Sub shape [(3, 1), (3, 1)] opt {}
18: op Add shape [(3, 1), ()] opt {}
19: op Sqrt shape [(3, 1)] opt {}
20: op Sub shape [(3, 4), (3, 1)] opt {}
21: op Div shape [(3, 4), (3, 1)] opt {}
22: op Cast shape [(3, 4)] opt {'to': 1}
23: op Flatten shape [(4,)] opt {'axis': 0}
24: op Mul shape [(3, 4), (1, 4)] opt {}
25: op Flatten shape [(4,)] opt {'axis': 0}
26: op Add shape [(3, 4), (1, 4)] opt {}
27: op Reshape shape [(3, 4), (2,)] opt {}
28: op Reciprocal shape [(3, 1)] opt {}
29: op Reshape shape [(3, 1), (2,)] opt {}
30: op Reshape shape [(3, 1), (2,)] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['X', 'W', 'B']
0: op LayerNormalization shape [(3, 4), (4,), (4,)] opt {'axis': -1}
prepare <class '__main__.TinygradBackend'> CPU ['X', 'W', 'B']
0: op Constant shape [] opt {'value': <Tensor <LB HIP () contig:True (<LoadOps.CONST: 2>, None)> on HIP with grad None>}
1: op Cast shape [()] opt {'to': 1}
2: op Shape shape [(3, 4)] opt {}
3: op Size shape [(2,)] opt {}
4: op Constant shape [] opt {'value': <Tensor <LB HIP (1,) contig:True (<LoadOps.COPY: 3>, None)> on HIP with grad None>}
5: op Constant shape [] opt {'value': <Tensor <LB HIP (1,) contig:True (<LoadOps.COPY: 3>, None)> on HIP with grad None>}
6: op Slice shape [(2,), (1,), (1,)] opt {}
7: op Neg shape [(1,)] opt {}
8: op ConstantOfShape shape [(1,)] opt {'value': <Tensor <LB HIP (1,) contig:True (<LoadOps.COPY: 3>, None)> on HIP with grad None>}
9: op Concat shape [(1,), (1,)] opt {'axis': 0}
10: op Flatten shape [(3, 4)] opt {'axis': -1}
11: op Cast shape [(3, 4)] opt {'to': 1}
12: op ReduceMean shape [(3, 4)] opt {'axes': (1,)}
13: op Mul shape [(3, 4), (3, 4)] opt {}
14: op ReduceMean shape [(3, 4)] opt {'axes': (1,)}
15: op Mul shape [(3, 1), (3, 1)] opt {}
16: op Sub shape [(3, 1), (3, 1)] opt {}
17: op Add shape [(3, 1), ()] opt {}
18: op Sqrt shape [(3, 1)] opt {}
19: op Sub shape [(3, 4), (3, 1)] opt {}
20: op Div shape [(3, 4), (3, 1)] opt {}
21: op Cast shape [(3, 4)] opt {'to': 1}
22: op Flatten shape [(4,)] opt {'axis': 0}
23: op Mul shape [(3, 4), (1, 4)] opt {}
24: op Flatten shape [(4,)] opt {'axis': 0}
25: op Add shape [(3, 4), (1, 4)] opt {}
26: op Reshape shape [(3, 4), (2,)] opt {}
27: op Reciprocal shape [(3, 1)] opt {}
28: op Reshape shape [(3, 1), (2,)] opt {}
29: op Reshape shape [(3, 1), (2,)] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['X', 'W', 'B']
0: op Constant shape [] opt {'value': <Tensor <LB HIP () contig:True (<LoadOps.CONST: 2>, None)> on HIP with grad None>}
1: op Cast shape [()] opt {'to': 1}
2: op Shape shape [(3, 4)] opt {}
3: op Size shape [(2,)] opt {}
4: op Constant shape [] opt {'value': <Tensor <LB HIP (1,) contig:True (<LoadOps.COPY: 3>, None)> on HIP with grad None>}
5: op Constant shape [] opt {'value': <Tensor <LB HIP (1,) contig:True (<LoadOps.COPY: 3>, None)> on HIP with grad None>}
6: op Slice shape [(2,), (1,), (1,)] opt {}
7: op Neg shape [(1,)] opt {}
8: op ConstantOfShape shape [(1,)] opt {'value': <Tensor <LB HIP (1,) contig:True (<LoadOps.COPY: 3>, None)> on HIP with grad None>}
9: op Concat shape [(1,), (1,)] opt {'axis': 0}
10: op Flatten shape [(3, 4)] opt {'axis': -1}
11: op Cast shape [(3, 4)] opt {'to': 1}
12: op Constant shape [] opt {'value': <Tensor <LB HIP (1,) contig:True (<LoadOps.COPY: 3>, None)> on HIP with grad None>}
13: op ReduceMean shape [(3, 4), (1,)] opt {}
14: op Mul shape [(3, 4), (3, 4)] opt {}
15: op ReduceMean shape [(3, 4), (1,)] opt {}
16: op Mul shape [(3, 1), (3, 1)] opt {}
17: op Sub shape [(3, 1), (3, 1)] opt {}
18: op Add shape [(3, 1), ()] opt {}
19: op Sqrt shape [(3, 1)] opt {}
20: op Sub shape [(3, 4), (3, 1)] opt {}
21: op Div shape [(3, 4), (3, 1)] opt {}
22: op Cast shape [(3, 4)] opt {'to': 1}
23: op Flatten shape [(4,)] opt {'axis': 0}
24: op Mul shape [(3, 4), (1, 4)] opt {}
25: op Flatten shape [(4,)] opt {'axis': 0}
26: op Add shape [(3, 4), (1, 4)] opt {}
27: op Reshape shape [(3, 4), (2,)] opt {}
28: op Reciprocal shape [(3, 1)] opt {}
29: op Reshape shape [(3, 1), (2,)] opt {}
30: op Reshape shape [(3, 1), (2,)] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['X', 'W', 'B']
0: op LayerNormalization shape [(3, 4), (3, 4), (3, 4)] opt {'axis': -2}
prepare <class '__main__.TinygradBackend'> CPU ['X', 'W', 'B']
0: op Constant shape [] opt {'value': <Tensor <LB HIP () contig:True (<LoadOps.CONST: 2>, None)> on HIP with grad None>}
1: op Cast shape [()] opt {'to': 1}
2: op Shape shape [(3, 4)] opt {}
3: op Size shape [(2,)] opt {}
4: op Constant shape [] opt {'value': <Tensor <LB HIP (1,) contig:True (<LoadOps.COPY: 3>, None)> on HIP with grad None>}
5: op Constant shape [] opt {'value': <Tensor <LB HIP (1,) contig:True (<LoadOps.COPY: 3>, None)> on HIP with grad None>}
6: op Slice shape [(2,), (1,), (1,)] opt {}
7: op Neg shape [(1,)] opt {}
8: op ConstantOfShape shape [(1,)] opt {'value': <Tensor <LB HIP (1,) contig:True (<LoadOps.COPY: 3>, None)> on HIP with grad None>}
9: op Concat shape [(0,), (2,)] opt {'axis': 0}
10: op Flatten shape [(3, 4)] opt {'axis': -2}
11: op Cast shape [(1, 12)] opt {'to': 1}
12: op ReduceMean shape [(1, 12)] opt {'axes': (1,)}
13: op Mul shape [(1, 12), (1, 12)] opt {}
14: op ReduceMean shape [(1, 12)] opt {'axes': (1,)}
15: op Mul shape [(1, 1), (1, 1)] opt {}
16: op Sub shape [(1, 1), (1, 1)] opt {}
17: op Add shape [(1, 1), ()] opt {}
18: op Sqrt shape [(1, 1)] opt {}
19: op Sub shape [(1, 12), (1, 1)] opt {}
20: op Div shape [(1, 12), (1, 1)] opt {}
21: op Cast shape [(1, 12)] opt {'to': 1}
22: op Flatten shape [(3, 4)] opt {'axis': 0}
23: op Mul shape [(1, 12), (1, 12)] opt {}
24: op Flatten shape [(3, 4)] opt {'axis': 0}
25: op Add shape [(1, 12), (1, 12)] opt {}
26: op Reshape shape [(1, 12), (2,)] opt {}
27: op Reciprocal shape [(1, 1)] opt {}
28: op Reshape shape [(1, 1), (2,)] opt {}
29: op Reshape shape [(1, 1), (2,)] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['X', 'W', 'B']
0: op Constant shape [] opt {'value': <Tensor <LB HIP () contig:True (<LoadOps.CONST: 2>, None)> on HIP with grad None>}
1: op Cast shape [()] opt {'to': 1}
2: op Shape shape [(3, 4)] opt {}
3: op Size shape [(2,)] opt {}
4: op Constant shape [] opt {'value': <Tensor <LB HIP (1,) contig:True (<LoadOps.COPY: 3>, None)> on HIP with grad None>}
5: op Constant shape [] opt {'value': <Tensor <LB HIP (1,) contig:True (<LoadOps.COPY: 3>, None)> on HIP with grad None>}
6: op Slice shape [(2,), (1,), (1,)] opt {}
7: op Neg shape [(1,)] opt {}
8: op ConstantOfShape shape [(1,)] opt {'value': <Tensor <LB HIP (1,) contig:True (<LoadOps.COPY: 3>, None)> on HIP with grad None>}
9: op Concat shape [(0,), (2,)] opt {'axis': 0}
10: op Flatten shape [(3, 4)] opt {'axis': -2}
11: op Cast shape [(1, 12)] opt {'to': 1}
.s.s.s.s.s.s.s12: op Constant shape [] opt {'value': <Tensor <LB HIP (1,) contig:True (<LoadOps.COPY: 3>, None)> on HIP with grad None>}
13: op ReduceMean shape [(1, 12), (1,)] opt {}
14: op Mul shape [(1, 12), (1, 12)] opt {}
15: op ReduceMean shape [(1, 12), (1,)] opt {}
16: op Mul shape [(1, 1), (1, 1)] opt {}
17: op Sub shape [(1, 1), (1, 1)] opt {}
18: op Add shape [(1, 1), ()] opt {}
19: op Sqrt shape [(1, 1)] opt {}
20: op Sub shape [(1, 12), (1, 1)] opt {}
21: op Div shape [(1, 12), (1, 1)] opt {}
22: op Cast shape [(1, 12)] opt {'to': 1}
23: op Flatten shape [(3, 4)] opt {'axis': 0}
24: op Mul shape [(1, 12), (1, 12)] opt {}
25: op Flatten shape [(3, 4)] opt {'axis': 0}
26: op Add shape [(1, 12), (1, 12)] opt {}
27: op Reshape shape [(1, 12), (2,)] opt {}
28: op Reciprocal shape [(1, 1)] opt {}
29: op Reshape shape [(1, 1), (2,)] opt {}
30: op Reshape shape [(1, 1), (2,)] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['X', 'W', 'B']
0: op LayerNormalization shape [(2, 3, 5), (2, 3, 5), (2, 3, 5)] opt {'axis': 0, 'epsilon': 0.10000000149011612}
prepare <class '__main__.TinygradBackend'> CPU ['X', 'W', 'B']
0: op Constant shape [] opt {'value': <Tensor <LB HIP () contig:True (<LoadOps.CONST: 2>, None)> on HIP with grad None>}
1: op Cast shape [()] opt {'to': 1}
2: op Shape shape [(2, 3, 5)] opt {}
3: op Size shape [(3,)] opt {}
4: op Constant shape [] opt {'value': <Tensor <LB HIP (1,) contig:True (<LoadOps.COPY: 3>, None)> on HIP with grad None>}
5: op Constant shape [] opt {'value': <Tensor <LB HIP (1,) contig:True (<LoadOps.COPY: 3>, None)> on HIP with grad None>}
6: op Slice shape [(3,), (1,), (1,)] opt {}
7: op Sub shape [3, (1,)] opt {}
8: op ConstantOfShape shape [(1,)] opt {'value': <Tensor <LB HIP (1,) contig:True (<LoadOps.COPY: 3>, None)> on HIP with grad None>}
9: op Concat shape [(0,), (3,)] opt {'axis': 0}
10: op Flatten shape [(2, 3, 5)] opt {'axis': 0}
11: op Cast shape [(1, 30)] opt {'to': 1}
12: op ReduceMean shape [(1, 30)] opt {'axes': (1,)}
13: op Mul shape [(1, 30), (1, 30)] opt {}
14: op ReduceMean shape [(1, 30)] opt {'axes': (1,)}
15: op Mul shape [(1, 1), (1, 1)] opt {}
16: op Sub shape [(1, 1), (1, 1)] opt {}
17: op Add shape [(1, 1), ()] opt {}
18: op Sqrt shape [(1, 1)] opt {}
19: op Sub shape [(1, 30), (1, 1)] opt {}
20: op Div shape [(1, 30), (1, 1)] opt {}
21: op Cast shape [(1, 30)] opt {'to': 1}
22: op Flatten shape [(2, 3, 5)] opt {'axis': 0}
23: op Mul shape [(1, 30), (1, 30)] opt {}
24: op Flatten shape [(2, 3, 5)] opt {'axis': 0}
25: op Add shape [(1, 30), (1, 30)] opt {}
26: op Reshape shape [(1, 30), (3,)] opt {}
27: op Reciprocal shape [(1, 1)] opt {}
28: op Reshape shape [(1, 1), (3,)] opt {}
29: op Reshape shape [(1, 1), (3,)] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['X', 'W', 'B']
0: op Constant shape [] opt {'value': <Tensor <LB HIP () contig:True (<LoadOps.CONST: 2>, None)> on HIP with grad None>}
1: op Cast shape [()] opt {'to': 1}
2: op Shape shape [(2, 3, 5)] opt {}
3: op Size shape [(3,)] opt {}
4: op Constant shape [] opt {'value': <Tensor <LB HIP (1,) contig:True (<LoadOps.COPY: 3>, None)> on HIP with grad None>}
5: op Constant shape [] opt {'value': <Tensor <LB HIP (1,) contig:True (<LoadOps.COPY: 3>, None)> on HIP with grad None>}
6: op Slice shape [(3,), (1,), (1,)] opt {}
7: op Sub shape [3, (1,)] opt {}
8: op ConstantOfShape shape [(1,)] opt {'value': <Tensor <LB HIP (1,) contig:True (<LoadOps.COPY: 3>, None)> on HIP with grad None>}
9: op Concat shape [(0,), (3,)] opt {'axis': 0}
10: op Flatten shape [(2, 3, 5)] opt {'axis': 0}
11: op Cast shape [(1, 30)] opt {'to': 1}
12: op Constant shape [] opt {'value': <Tensor <LB HIP (1,) contig:True (<LoadOps.COPY: 3>, None)> on HIP with grad None>}
13: op ReduceMean shape [(1, 30), (1,)] opt {}
14: op Mul shape [(1, 30), (1, 30)] opt {}
15: op ReduceMean shape [(1, 30), (1,)] opt {}
16: op Mul shape [(1, 1), (1, 1)] opt {}
17: op Sub shape [(1, 1), (1, 1)] opt {}
18: op Add shape [(1, 1), ()] opt {}
19: op Sqrt shape [(1, 1)] opt {}
20: op Sub shape [(1, 30), (1, 1)] opt {}
21: op Div shape [(1, 30), (1, 1)] opt {}
22: op Cast shape [(1, 30)] opt {'to': 1}
23: op Flatten shape [(2, 3, 5)] opt {'axis': 0}
24: op Mul shape [(1, 30), (1, 30)] opt {}
25: op Flatten shape [(2, 3, 5)] opt {'axis': 0}
26: op Add shape [(1, 30), (1, 30)] opt {}
27: op Reshape shape [(1, 30), (3,)] opt {}
28: op Reciprocal shape [(1, 1)] opt {}
29: op Reshape shape [(1, 1), (3,)] opt {}
30: op Reshape shape [(1, 1), (3,)] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['X', 'W', 'B']
0: op LayerNormalization shape [(2, 3, 5), (3, 5), (3, 5)] opt {'axis': 1, 'epsilon': 0.10000000149011612}
prepare <class '__main__.TinygradBackend'> CPU ['X', 'W', 'B']
0: op Constant shape [] opt {'value': <Tensor <LB HIP () contig:True (<LoadOps.CONST: 2>, None)> on HIP with grad None>}
1: op Cast shape [()] opt {'to': 1}
2: op Shape shape [(2, 3, 5)] opt {}
3: op Size shape [(3,)] opt {}
4: op Constant shape [] opt {'value': <Tensor <LB HIP (1,) contig:True (<LoadOps.COPY: 3>, None)> on HIP with grad None>}
5: op Constant shape [] opt {'value': <Tensor <LB HIP (1,) contig:True (<LoadOps.COPY: 3>, None)> on HIP with grad None>}
6: op Slice shape [(3,), (1,), (1,)] opt {}
7: op Sub shape [3, (1,)] opt {}
8: op ConstantOfShape shape [(1,)] opt {'value': <Tensor <LB HIP (1,) contig:True (<LoadOps.COPY: 3>, None)> on HIP with grad None>}
9: op Concat shape [(1,), (2,)] opt {'axis': 0}
10: op Flatten shape [(2, 3, 5)] opt {'axis': 1}
11: op Cast shape [(2, 15)] opt {'to': 1}
12: op ReduceMean shape [(2, 15)] opt {'axes': (1,)}
13: op Mul shape [(2, 15), (2, 15)] opt {}
14: op ReduceMean shape [(2, 15)] opt {'axes': (1,)}
15: op Mul shape [(2, 1), (2, 1)] opt {}
16: op Sub shape [(2, 1), (2, 1)] opt {}
17: op Add shape [(2, 1), ()] opt {}
18: op Sqrt shape [(2, 1)] opt {}
19: op Sub shape [(2, 15), (2, 1)] opt {}
20: op Div shape [(2, 15), (2, 1)] opt {}
21: op Cast shape [(2, 15)] opt {'to': 1}
22: op Flatten shape [(3, 5)] opt {'axis': 0}
23: op Mul shape [(2, 15), (1, 15)] opt {}
24: op Flatten shape [(3, 5)] opt {'axis': 0}
25: op Add shape [(2, 15), (1, 15)] opt {}
26: op Reshape shape [(2, 15), (3,)] opt {}
27: op Reciprocal shape [(2, 1)] opt {}
28: op Reshape shape [(2, 1), (3,)] opt {}
29: op Reshape shape [(2, 1), (3,)] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['X', 'W', 'B']
0: op Constant shape [] opt {'value': <Tensor <LB HIP () contig:True (<LoadOps.CONST: 2>, None)> on HIP with grad None>}
1: op Cast shape [()] opt {'to': 1}
2: op Shape shape [(2, 3, 5)] opt {}
3: op Size shape [(3,)] opt {}
4: op Constant shape [] opt {'value': <Tensor <LB HIP (1,) contig:True (<LoadOps.COPY: 3>, None)> on HIP with grad None>}
5: op Constant shape [] opt {'value': <Tensor <LB HIP (1,) contig:True (<LoadOps.COPY: 3>, None)> on HIP with grad None>}
6: op Slice shape [(3,), (1,), (1,)] opt {}
7: op Sub shape [3, (1,)] opt {}
8: op ConstantOfShape shape [(1,)] opt {'value': <Tensor <LB HIP (1,) contig:True (<LoadOps.COPY: 3>, None)> on HIP with grad None>}
9: op Concat shape [(1,), (2,)] opt {'axis': 0}
10: op Flatten shape [(2, 3, 5)] opt {'axis': 1}
11: op Cast shape [(2, 15)] opt {'to': 1}
12: op Constant shape [] opt {'value': <Tensor <LB HIP (1,) contig:True (<LoadOps.COPY: 3>, None)> on HIP with grad None>}
13: op ReduceMean shape [(2, 15), (1,)] opt {}
14: op Mul shape [(2, 15), (2, 15)] opt {}
15: op ReduceMean shape [(2, 15), (1,)] opt {}
16: op Mul shape [(2, 1), (2, 1)] opt {}
17: op Sub shape [(2, 1), (2, 1)] opt {}
18: op Add shape [(2, 1), ()] opt {}
19: op Sqrt shape [(2, 1)] opt {}
20: op Sub shape [(2, 15), (2, 1)] opt {}
21: op Div shape [(2, 15), (2, 1)] opt {}
22: op Cast shape [(2, 15)] opt {'to': 1}
23: op Flatten shape [(3, 5)] opt {'axis': 0}
24: op Mul shape [(2, 15), (1, 15)] opt {}
25: op Flatten shape [(3, 5)] opt {'axis': 0}
26: op Add shape [(2, 15), (1, 15)] opt {}
27: op Reshape shape [(2, 15), (3,)] opt {}
28: op Reciprocal shape [(2, 1)] opt {}
29: op Reshape shape [(2, 1), (3,)] opt {}
30: op Reshape shape [(2, 1), (3,)] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['X', 'W', 'B']
.s.s.s.s.s.s.s0: op LayerNormalization shape [(2, 3, 5), (5,), (5,)] opt {'axis': 2, 'epsilon': 0.10000000149011612}
prepare <class '__main__.TinygradBackend'> CPU ['X', 'W', 'B']
0: op Constant shape [] opt {'value': <Tensor <LB HIP () contig:True (<LoadOps.CONST: 2>, None)> on HIP with grad None>}
1: op Cast shape [()] opt {'to': 1}
2: op Shape shape [(2, 3, 5)] opt {}
3: op Size shape [(3,)] opt {}
4: op Constant shape [] opt {'value': <Tensor <LB HIP (1,) contig:True (<LoadOps.COPY: 3>, None)> on HIP with grad None>}
5: op Constant shape [] opt {'value': <Tensor <LB HIP (1,) contig:True (<LoadOps.COPY: 3>, None)> on HIP with grad None>}
6: op Slice shape [(3,), (1,), (1,)] opt {}
7: op Sub shape [3, (1,)] opt {}
8: op ConstantOfShape shape [(1,)] opt {'value': <Tensor <LB HIP (1,) contig:True (<LoadOps.COPY: 3>, None)> on HIP with grad None>}
9: op Concat shape [(2,), (1,)] opt {'axis': 0}
10: op Flatten shape [(2, 3, 5)] opt {'axis': 2}
11: op Cast shape [(6, 5)] opt {'to': 1}
12: op ReduceMean shape [(6, 5)] opt {'axes': (1,)}
13: op Mul shape [(6, 5), (6, 5)] opt {}
14: op ReduceMean shape [(6, 5)] opt {'axes': (1,)}
15: op Mul shape [(6, 1), (6, 1)] opt {}
16: op Sub shape [(6, 1), (6, 1)] opt {}
17: op Add shape [(6, 1), ()] opt {}
18: op Sqrt shape [(6, 1)] opt {}
19: op Sub shape [(6, 5), (6, 1)] opt {}
20: op Div shape [(6, 5), (6, 1)] opt {}
21: op Cast shape [(6, 5)] opt {'to': 1}
22: op Flatten shape [(5,)] opt {'axis': 0}
23: op Mul shape [(6, 5), (1, 5)] opt {}
24: op Flatten shape [(5,)] opt {'axis': 0}
25: op Add shape [(6, 5), (1, 5)] opt {}
26: op Reshape shape [(6, 5), (3,)] opt {}
27: op Reciprocal shape [(6, 1)] opt {}
28: op Reshape shape [(6, 1), (3,)] opt {}
29: op Reshape shape [(6, 1), (3,)] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['X', 'W', 'B']
0: op Constant shape [] opt {'value': <Tensor <LB HIP () contig:True (<LoadOps.CONST: 2>, None)> on HIP with grad None>}
1: op Cast shape [()] opt {'to': 1}
2: op Shape shape [(2, 3, 5)] opt {}
3: op Size shape [(3,)] opt {}
4: op Constant shape [] opt {'value': <Tensor <LB HIP (1,) contig:True (<LoadOps.COPY: 3>, None)> on HIP with grad None>}
5: op Constant shape [] opt {'value': <Tensor <LB HIP (1,) contig:True (<LoadOps.COPY: 3>, None)> on HIP with grad None>}
6: op Slice shape [(3,), (1,), (1,)] opt {}
7: op Sub shape [3, (1,)] opt {}
8: op ConstantOfShape shape [(1,)] opt {'value': <Tensor <LB HIP (1,) contig:True (<LoadOps.COPY: 3>, None)> on HIP with grad None>}
9: op Concat shape [(2,), (1,)] opt {'axis': 0}
10: op Flatten shape [(2, 3, 5)] opt {'axis': 2}
11: op Cast shape [(6, 5)] opt {'to': 1}
12: op Constant shape [] opt {'value': <Tensor <LB HIP (1,) contig:True (<LoadOps.COPY: 3>, None)> on HIP with grad None>}
13: op ReduceMean shape [(6, 5), (1,)] opt {}
14: op Mul shape [(6, 5), (6, 5)] opt {}
15: op ReduceMean shape [(6, 5), (1,)] opt {}
16: op Mul shape [(6, 1), (6, 1)] opt {}
17: op Sub shape [(6, 1), (6, 1)] opt {}
18: op Add shape [(6, 1), ()] opt {}
19: op Sqrt shape [(6, 1)] opt {}
20: op Sub shape [(6, 5), (6, 1)] opt {}
21: op Div shape [(6, 5), (6, 1)] opt {}
22: op Cast shape [(6, 5)] opt {'to': 1}
23: op Flatten shape [(5,)] opt {'axis': 0}
24: op Mul shape [(6, 5), (1, 5)] opt {}
25: op Flatten shape [(5,)] opt {'axis': 0}
26: op Add shape [(6, 5), (1, 5)] opt {}
27: op Reshape shape [(6, 5), (3,)] opt {}
28: op Reciprocal shape [(6, 1)] opt {}
29: op Reshape shape [(6, 1), (3,)] opt {}
30: op Reshape shape [(6, 1), (3,)] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['X', 'W', 'B']
0: op LayerNormalization shape [(2, 3, 5), (5,), (5,)] opt {'axis': -1, 'epsilon': 0.10000000149011612}
prepare <class '__main__.TinygradBackend'> CPU ['X', 'W', 'B']
0: op Constant shape [] opt {'value': <Tensor <LB HIP () contig:True (<LoadOps.CONST: 2>, None)> on HIP with grad None>}
1: op Cast shape [()] opt {'to': 1}
2: op Shape shape [(2, 3, 5)] opt {}
3: op Size shape [(3,)] opt {}
4: op Constant shape [] opt {'value': <Tensor <LB HIP (1,) contig:True (<LoadOps.COPY: 3>, None)> on HIP with grad None>}
5: op Constant shape [] opt {'value': <Tensor <LB HIP (1,) contig:True (<LoadOps.COPY: 3>, None)> on HIP with grad None>}
6: op Slice shape [(3,), (1,), (1,)] opt {}
7: op Neg shape [(1,)] opt {}
8: op ConstantOfShape shape [(1,)] opt {'value': <Tensor <LB HIP (1,) contig:True (<LoadOps.COPY: 3>, None)> on HIP with grad None>}
9: op Concat shape [(2,), (1,)] opt {'axis': 0}
10: op Flatten shape [(2, 3, 5)] opt {'axis': -1}
11: op Cast shape [(6, 5)] opt {'to': 1}
12: op ReduceMean shape [(6, 5)] opt {'axes': (1,)}
13: op Mul shape [(6, 5), (6, 5)] opt {}
14: op ReduceMean shape [(6, 5)] opt {'axes': (1,)}
15: op Mul shape [(6, 1), (6, 1)] opt {}
16: op Sub shape [(6, 1), (6, 1)] opt {}
17: op Add shape [(6, 1), ()] opt {}
18: op Sqrt shape [(6, 1)] opt {}
19: op Sub shape [(6, 5), (6, 1)] opt {}
20: op Div shape [(6, 5), (6, 1)] opt {}
21: op Cast shape [(6, 5)] opt {'to': 1}
22: op Flatten shape [(5,)] opt {'axis': 0}
23: op Mul shape [(6, 5), (1, 5)] opt {}
24: op Flatten shape [(5,)] opt {'axis': 0}
25: op Add shape [(6, 5), (1, 5)] opt {}
26: op Reshape shape [(6, 5), (3,)] opt {}
27: op Reciprocal shape [(6, 1)] opt {}
28: op Reshape shape [(6, 1), (3,)] opt {}
29: op Reshape shape [(6, 1), (3,)] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['X', 'W', 'B']
0: op Constant shape [] opt {'value': <Tensor <LB HIP () contig:True (<LoadOps.CONST: 2>, None)> on HIP with grad None>}
1: op Cast shape [()] opt {'to': 1}
2: op Shape shape [(2, 3, 5)] opt {}
3: op Size shape [(3,)] opt {}
4: op Constant shape [] opt {'value': <Tensor <LB HIP (1,) contig:True (<LoadOps.COPY: 3>, None)> on HIP with grad None>}
5: op Constant shape [] opt {'value': <Tensor <LB HIP (1,) contig:True (<LoadOps.COPY: 3>, None)> on HIP with grad None>}
6: op Slice shape [(3,), (1,), (1,)] opt {}
7: op Neg shape [(1,)] opt {}
8: op ConstantOfShape shape [(1,)] opt {'value': <Tensor <LB HIP (1,) contig:True (<LoadOps.COPY: 3>, None)> on HIP with grad None>}
9: op Concat shape [(2,), (1,)] opt {'axis': 0}
10: op Flatten shape [(2, 3, 5)] opt {'axis': -1}
11: op Cast shape [(6, 5)] opt {'to': 1}
12: op Constant shape [] opt {'value': <Tensor <LB HIP (1,) contig:True (<LoadOps.COPY: 3>, None)> on HIP with grad None>}
13: op ReduceMean shape [(6, 5), (1,)] opt {}
14: op Mul shape [(6, 5), (6, 5)] opt {}
15: op ReduceMean shape [(6, 5), (1,)] opt {}
16: op Mul shape [(6, 1), (6, 1)] opt {}
17: op Sub shape [(6, 1), (6, 1)] opt {}
18: op Add shape [(6, 1), ()] opt {}
19: op Sqrt shape [(6, 1)] opt {}
20: op Sub shape [(6, 5), (6, 1)] opt {}
21: op Div shape [(6, 5), (6, 1)] opt {}
22: op Cast shape [(6, 5)] opt {'to': 1}
23: op Flatten shape [(5,)] opt {'axis': 0}
24: op Mul shape [(6, 5), (1, 5)] opt {}
25: op Flatten shape [(5,)] opt {'axis': 0}
26: op Add shape [(6, 5), (1, 5)] opt {}
27: op Reshape shape [(6, 5), (3,)] opt {}
28: op Reciprocal shape [(6, 1)] opt {}
29: op Reshape shape [(6, 1), (3,)] opt {}
30: op Reshape shape [(6, 1), (3,)] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['X', 'W', 'B']
0: op LayerNormalization shape [(2, 3, 5), (3, 5), (3, 5)] opt {'axis': -2, 'epsilon': 0.10000000149011612}
prepare <class '__main__.TinygradBackend'> CPU ['X', 'W', 'B']
0: op Constant shape [] opt {'value': <Tensor <LB HIP () contig:True (<LoadOps.CONST: 2>, None)> on HIP with grad None>}
1: op Cast shape [()] opt {'to': 1}
2: op Shape shape [(2, 3, 5)] opt {}
3: op Size shape [(3,)] opt {}
4: op Constant shape [] opt {'value': <Tensor <LB HIP (1,) contig:True (<LoadOps.COPY: 3>, None)> on HIP with grad None>}
5: op Constant shape [] opt {'value': <Tensor <LB HIP (1,) contig:True (<LoadOps.COPY: 3>, None)> on HIP with grad None>}
6: op Slice shape [(3,), (1,), (1,)] opt {}
7: op Neg shape [(1,)] opt {}
8: op ConstantOfShape shape [(1,)] opt {'value': <Tensor <LB HIP (1,) contig:True (<LoadOps.COPY: 3>, None)> on HIP with grad None>}
9: op Concat shape [(1,), (2,)] opt {'axis': 0}
10: op Flatten shape [(2, 3, 5)] opt {'axis': -2}
11: op Cast shape [(2, 15)] opt {'to': 1}
12: op ReduceMean shape [(2, 15)] opt {'axes': (1,)}
.s.s.s.s.s.s.s13: op Mul shape [(2, 15), (2, 15)] opt {}
14: op ReduceMean shape [(2, 15)] opt {'axes': (1,)}
15: op Mul shape [(2, 1), (2, 1)] opt {}
16: op Sub shape [(2, 1), (2, 1)] opt {}
17: op Add shape [(2, 1), ()] opt {}
18: op Sqrt shape [(2, 1)] opt {}
19: op Sub shape [(2, 15), (2, 1)] opt {}
20: op Div shape [(2, 15), (2, 1)] opt {}
21: op Cast shape [(2, 15)] opt {'to': 1}
22: op Flatten shape [(3, 5)] opt {'axis': 0}
23: op Mul shape [(2, 15), (1, 15)] opt {}
24: op Flatten shape [(3, 5)] opt {'axis': 0}
25: op Add shape [(2, 15), (1, 15)] opt {}
26: op Reshape shape [(2, 15), (3,)] opt {}
27: op Reciprocal shape [(2, 1)] opt {}
28: op Reshape shape [(2, 1), (3,)] opt {}
29: op Reshape shape [(2, 1), (3,)] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['X', 'W', 'B']
0: op Constant shape [] opt {'value': <Tensor <LB HIP () contig:True (<LoadOps.CONST: 2>, None)> on HIP with grad None>}
1: op Cast shape [()] opt {'to': 1}
2: op Shape shape [(2, 3, 5)] opt {}
3: op Size shape [(3,)] opt {}
4: op Constant shape [] opt {'value': <Tensor <LB HIP (1,) contig:True (<LoadOps.COPY: 3>, None)> on HIP with grad None>}
5: op Constant shape [] opt {'value': <Tensor <LB HIP (1,) contig:True (<LoadOps.COPY: 3>, None)> on HIP with grad None>}
6: op Slice shape [(3,), (1,), (1,)] opt {}
7: op Neg shape [(1,)] opt {}
8: op ConstantOfShape shape [(1,)] opt {'value': <Tensor <LB HIP (1,) contig:True (<LoadOps.COPY: 3>, None)> on HIP with grad None>}
9: op Concat shape [(1,), (2,)] opt {'axis': 0}
10: op Flatten shape [(2, 3, 5)] opt {'axis': -2}
11: op Cast shape [(2, 15)] opt {'to': 1}
12: op Constant shape [] opt {'value': <Tensor <LB HIP (1,) contig:True (<LoadOps.COPY: 3>, None)> on HIP with grad None>}
13: op ReduceMean shape [(2, 15), (1,)] opt {}
14: op Mul shape [(2, 15), (2, 15)] opt {}
15: op ReduceMean shape [(2, 15), (1,)] opt {}
16: op Mul shape [(2, 1), (2, 1)] opt {}
17: op Sub shape [(2, 1), (2, 1)] opt {}
18: op Add shape [(2, 1), ()] opt {}
19: op Sqrt shape [(2, 1)] opt {}
20: op Sub shape [(2, 15), (2, 1)] opt {}
21: op Div shape [(2, 15), (2, 1)] opt {}
22: op Cast shape [(2, 15)] opt {'to': 1}
23: op Flatten shape [(3, 5)] opt {'axis': 0}
24: op Mul shape [(2, 15), (1, 15)] opt {}
25: op Flatten shape [(3, 5)] opt {'axis': 0}
26: op Add shape [(2, 15), (1, 15)] opt {}
27: op Reshape shape [(2, 15), (3,)] opt {}
28: op Reciprocal shape [(2, 1)] opt {}
29: op Reshape shape [(2, 1), (3,)] opt {}
30: op Reshape shape [(2, 1), (3,)] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['X', 'W', 'B']
0: op LayerNormalization shape [(2, 3, 5), (2, 3, 5), (2, 3, 5)] opt {'axis': -3, 'epsilon': 0.10000000149011612}
prepare <class '__main__.TinygradBackend'> CPU ['X', 'W', 'B']
0: op Constant shape [] opt {'value': <Tensor <LB HIP () contig:True (<LoadOps.CONST: 2>, None)> on HIP with grad None>}
1: op Cast shape [()] opt {'to': 1}
2: op Shape shape [(2, 3, 5)] opt {}
3: op Size shape [(3,)] opt {}
4: op Constant shape [] opt {'value': <Tensor <LB HIP (1,) contig:True (<LoadOps.COPY: 3>, None)> on HIP with grad None>}
5: op Constant shape [] opt {'value': <Tensor <LB HIP (1,) contig:True (<LoadOps.COPY: 3>, None)> on HIP with grad None>}
6: op Slice shape [(3,), (1,), (1,)] opt {}
7: op Neg shape [(1,)] opt {}
8: op ConstantOfShape shape [(1,)] opt {'value': <Tensor <LB HIP (1,) contig:True (<LoadOps.COPY: 3>, None)> on HIP with grad None>}
9: op Concat shape [(0,), (3,)] opt {'axis': 0}
10: op Flatten shape [(2, 3, 5)] opt {'axis': -3}
11: op Cast shape [(1, 30)] opt {'to': 1}
12: op ReduceMean shape [(1, 30)] opt {'axes': (1,)}
13: op Mul shape [(1, 30), (1, 30)] opt {}
14: op ReduceMean shape [(1, 30)] opt {'axes': (1,)}
15: op Mul shape [(1, 1), (1, 1)] opt {}
16: op Sub shape [(1, 1), (1, 1)] opt {}
17: op Add shape [(1, 1), ()] opt {}
18: op Sqrt shape [(1, 1)] opt {}
19: op Sub shape [(1, 30), (1, 1)] opt {}
20: op Div shape [(1, 30), (1, 1)] opt {}
21: op Cast shape [(1, 30)] opt {'to': 1}
22: op Flatten shape [(2, 3, 5)] opt {'axis': 0}
23: op Mul shape [(1, 30), (1, 30)] opt {}
24: op Flatten shape [(2, 3, 5)] opt {'axis': 0}
25: op Add shape [(1, 30), (1, 30)] opt {}
26: op Reshape shape [(1, 30), (3,)] opt {}
27: op Reciprocal shape [(1, 1)] opt {}
28: op Reshape shape [(1, 1), (3,)] opt {}
29: op Reshape shape [(1, 1), (3,)] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['X', 'W', 'B']
0: op Constant shape [] opt {'value': <Tensor <LB HIP () contig:True (<LoadOps.CONST: 2>, None)> on HIP with grad None>}
1: op Cast shape [()] opt {'to': 1}
2: op Shape shape [(2, 3, 5)] opt {}
3: op Size shape [(3,)] opt {}
4: op Constant shape [] opt {'value': <Tensor <LB HIP (1,) contig:True (<LoadOps.COPY: 3>, None)> on HIP with grad None>}
5: op Constant shape [] opt {'value': <Tensor <LB HIP (1,) contig:True (<LoadOps.COPY: 3>, None)> on HIP with grad None>}
6: op Slice shape [(3,), (1,), (1,)] opt {}
7: op Neg shape [(1,)] opt {}
8: op ConstantOfShape shape [(1,)] opt {'value': <Tensor <LB HIP (1,) contig:True (<LoadOps.COPY: 3>, None)> on HIP with grad None>}
9: op Concat shape [(0,), (3,)] opt {'axis': 0}
10: op Flatten shape [(2, 3, 5)] opt {'axis': -3}
11: op Cast shape [(1, 30)] opt {'to': 1}
12: op Constant shape [] opt {'value': <Tensor <LB HIP (1,) contig:True (<LoadOps.COPY: 3>, None)> on HIP with grad None>}
13: op ReduceMean shape [(1, 30), (1,)] opt {}
14: op Mul shape [(1, 30), (1, 30)] opt {}
15: op ReduceMean shape [(1, 30), (1,)] opt {}
16: op Mul shape [(1, 1), (1, 1)] opt {}
17: op Sub shape [(1, 1), (1, 1)] opt {}
18: op Add shape [(1, 1), ()] opt {}
19: op Sqrt shape [(1, 1)] opt {}
20: op Sub shape [(1, 30), (1, 1)] opt {}
21: op Div shape [(1, 30), (1, 1)] opt {}
22: op Cast shape [(1, 30)] opt {'to': 1}
23: op Flatten shape [(2, 3, 5)] opt {'axis': 0}
24: op Mul shape [(1, 30), (1, 30)] opt {}
25: op Flatten shape [(2, 3, 5)] opt {'axis': 0}
26: op Add shape [(1, 30), (1, 30)] opt {}
27: op Reshape shape [(1, 30), (3,)] opt {}
28: op Reciprocal shape [(1, 1)] opt {}
29: op Reshape shape [(1, 1), (3,)] opt {}
30: op Reshape shape [(1, 1), (3,)] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['X', 'W', 'B']
0: op LayerNormalization shape [(2, 3, 4, 5), (2, 3, 4, 5), (2, 3, 4, 5)] opt {'axis': 0}
prepare <class '__main__.TinygradBackend'> CPU ['X', 'W', 'B']
0: op Constant shape [] opt {'value': <Tensor <LB HIP () contig:True (<LoadOps.CONST: 2>, None)> on HIP with grad None>}
1: op Cast shape [()] opt {'to': 1}
2: op Shape shape [(2, 3, 4, 5)] opt {}
3: op Size shape [(4,)] opt {}
4: op Constant shape [] opt {'value': <Tensor <LB HIP (1,) contig:True (<LoadOps.COPY: 3>, None)> on HIP with grad None>}
5: op Constant shape [] opt {'value': <Tensor <LB HIP (1,) contig:True (<LoadOps.COPY: 3>, None)> on HIP with grad None>}
6: op Slice shape [(4,), (1,), (1,)] opt {}
7: op Sub shape [4, (1,)] opt {}
8: op ConstantOfShape shape [(1,)] opt {'value': <Tensor <LB HIP (1,) contig:True (<LoadOps.COPY: 3>, None)> on HIP with grad None>}
9: op Concat shape [(0,), (4,)] opt {'axis': 0}
10: op Flatten shape [(2, 3, 4, 5)] opt {'axis': 0}
11: op Cast shape [(1, 120)] opt {'to': 1}
12: op ReduceMean shape [(1, 120)] opt {'axes': (1,)}
13: op Mul shape [(1, 120), (1, 120)] opt {}
14: op ReduceMean shape [(1, 120)] opt {'axes': (1,)}
15: op Mul shape [(1, 1), (1, 1)] opt {}
16: op Sub shape [(1, 1), (1, 1)] opt {}
17: op Add shape [(1, 1), ()] opt {}
18: op Sqrt shape [(1, 1)] opt {}
19: op Sub shape [(1, 120), (1, 1)] opt {}
20: op Div shape [(1, 120), (1, 1)] opt {}
21: op Cast shape [(1, 120)] opt {'to': 1}
22: op Flatten shape [(2, 3, 4, 5)] opt {'axis': 0}
23: op Mul shape [(1, 120), (1, 120)] opt {}
24: op Flatten shape [(2, 3, 4, 5)] opt {'axis': 0}
25: op Add shape [(1, 120), (1, 120)] opt {}
26: op Reshape shape [(1, 120), (4,)] opt {}
27: op Reciprocal shape [(1, 1)] opt {}
28: op Reshape shape [(1, 1), (4,)] opt {}
29: op Reshape shape [(1, 1), (4,)] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['X', 'W', 'B']
0: op Constant shape [] opt {'value': <Tensor <LB HIP () contig:True (<LoadOps.CONST: 2>, None)> on HIP with grad None>}
1: op Cast shape [()] opt {'to': 1}
.s.s.s.s.s.s2: op Shape shape [(2, 3, 4, 5)] opt {}
3: op Size shape [(4,)] opt {}
4: op Constant shape [] opt {'value': <Tensor <LB HIP (1,) contig:True (<LoadOps.COPY: 3>, None)> on HIP with grad None>}
5: op Constant shape [] opt {'value': <Tensor <LB HIP (1,) contig:True (<LoadOps.COPY: 3>, None)> on HIP with grad None>}
6: op Slice shape [(4,), (1,), (1,)] opt {}
7: op Sub shape [4, (1,)] opt {}
8: op ConstantOfShape shape [(1,)] opt {'value': <Tensor <LB HIP (1,) contig:True (<LoadOps.COPY: 3>, None)> on HIP with grad None>}
9: op Concat shape [(0,), (4,)] opt {'axis': 0}
10: op Flatten shape [(2, 3, 4, 5)] opt {'axis': 0}
11: op Cast shape [(1, 120)] opt {'to': 1}
12: op Constant shape [] opt {'value': <Tensor <LB HIP (1,) contig:True (<LoadOps.COPY: 3>, None)> on HIP with grad None>}
13: op ReduceMean shape [(1, 120), (1,)] opt {}
14: op Mul shape [(1, 120), (1, 120)] opt {}
15: op ReduceMean shape [(1, 120), (1,)] opt {}
16: op Mul shape [(1, 1), (1, 1)] opt {}
17: op Sub shape [(1, 1), (1, 1)] opt {}
18: op Add shape [(1, 1), ()] opt {}
19: op Sqrt shape [(1, 1)] opt {}
20: op Sub shape [(1, 120), (1, 1)] opt {}
21: op Div shape [(1, 120), (1, 1)] opt {}
22: op Cast shape [(1, 120)] opt {'to': 1}
23: op Flatten shape [(2, 3, 4, 5)] opt {'axis': 0}
24: op Mul shape [(1, 120), (1, 120)] opt {}
25: op Flatten shape [(2, 3, 4, 5)] opt {'axis': 0}
26: op Add shape [(1, 120), (1, 120)] opt {}
27: op Reshape shape [(1, 120), (4,)] opt {}
28: op Reciprocal shape [(1, 1)] opt {}
29: op Reshape shape [(1, 1), (4,)] opt {}
30: op Reshape shape [(1, 1), (4,)] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['X', 'W', 'B']
0: op LayerNormalization shape [(2, 3, 4, 5), (3, 4, 5), (3, 4, 5)] opt {'axis': 1}
prepare <class '__main__.TinygradBackend'> CPU ['X', 'W', 'B']
0: op Constant shape [] opt {'value': <Tensor <LB HIP () contig:True (<LoadOps.CONST: 2>, None)> on HIP with grad None>}
1: op Cast shape [()] opt {'to': 1}
2: op Shape shape [(2, 3, 4, 5)] opt {}
3: op Size shape [(4,)] opt {}
4: op Constant shape [] opt {'value': <Tensor <LB HIP (1,) contig:True (<LoadOps.COPY: 3>, None)> on HIP with grad None>}
5: op Constant shape [] opt {'value': <Tensor <LB HIP (1,) contig:True (<LoadOps.COPY: 3>, None)> on HIP with grad None>}
6: op Slice shape [(4,), (1,), (1,)] opt {}
7: op Sub shape [4, (1,)] opt {}
8: op ConstantOfShape shape [(1,)] opt {'value': <Tensor <LB HIP (1,) contig:True (<LoadOps.COPY: 3>, None)> on HIP with grad None>}
9: op Concat shape [(1,), (3,)] opt {'axis': 0}
10: op Flatten shape [(2, 3, 4, 5)] opt {'axis': 1}
11: op Cast shape [(2, 60)] opt {'to': 1}
12: op ReduceMean shape [(2, 60)] opt {'axes': (1,)}
13: op Mul shape [(2, 60), (2, 60)] opt {}
14: op ReduceMean shape [(2, 60)] opt {'axes': (1,)}
15: op Mul shape [(2, 1), (2, 1)] opt {}
16: op Sub shape [(2, 1), (2, 1)] opt {}
17: op Add shape [(2, 1), ()] opt {}
18: op Sqrt shape [(2, 1)] opt {}
19: op Sub shape [(2, 60), (2, 1)] opt {}
20: op Div shape [(2, 60), (2, 1)] opt {}
21: op Cast shape [(2, 60)] opt {'to': 1}
22: op Flatten shape [(3, 4, 5)] opt {'axis': 0}
23: op Mul shape [(2, 60), (1, 60)] opt {}
24: op Flatten shape [(3, 4, 5)] opt {'axis': 0}
25: op Add shape [(2, 60), (1, 60)] opt {}
26: op Reshape shape [(2, 60), (4,)] opt {}
27: op Reciprocal shape [(2, 1)] opt {}
28: op Reshape shape [(2, 1), (4,)] opt {}
29: op Reshape shape [(2, 1), (4,)] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['X', 'W', 'B']
0: op Constant shape [] opt {'value': <Tensor <LB HIP () contig:True (<LoadOps.CONST: 2>, None)> on HIP with grad None>}
1: op Cast shape [()] opt {'to': 1}
2: op Shape shape [(2, 3, 4, 5)] opt {}
3: op Size shape [(4,)] opt {}
4: op Constant shape [] opt {'value': <Tensor <LB HIP (1,) contig:True (<LoadOps.COPY: 3>, None)> on HIP with grad None>}
5: op Constant shape [] opt {'value': <Tensor <LB HIP (1,) contig:True (<LoadOps.COPY: 3>, None)> on HIP with grad None>}
6: op Slice shape [(4,), (1,), (1,)] opt {}
7: op Sub shape [4, (1,)] opt {}
8: op ConstantOfShape shape [(1,)] opt {'value': <Tensor <LB HIP (1,) contig:True (<LoadOps.COPY: 3>, None)> on HIP with grad None>}
9: op Concat shape [(1,), (3,)] opt {'axis': 0}
10: op Flatten shape [(2, 3, 4, 5)] opt {'axis': 1}
11: op Cast shape [(2, 60)] opt {'to': 1}
12: op Constant shape [] opt {'value': <Tensor <LB HIP (1,) contig:True (<LoadOps.COPY: 3>, None)> on HIP with grad None>}
13: op ReduceMean shape [(2, 60), (1,)] opt {}
14: op Mul shape [(2, 60), (2, 60)] opt {}
15: op ReduceMean shape [(2, 60), (1,)] opt {}
16: op Mul shape [(2, 1), (2, 1)] opt {}
17: op Sub shape [(2, 1), (2, 1)] opt {}
18: op Add shape [(2, 1), ()] opt {}
19: op Sqrt shape [(2, 1)] opt {}
20: op Sub shape [(2, 60), (2, 1)] opt {}
21: op Div shape [(2, 60), (2, 1)] opt {}
22: op Cast shape [(2, 60)] opt {'to': 1}
23: op Flatten shape [(3, 4, 5)] opt {'axis': 0}
24: op Mul shape [(2, 60), (1, 60)] opt {}
25: op Flatten shape [(3, 4, 5)] opt {'axis': 0}
26: op Add shape [(2, 60), (1, 60)] opt {}
27: op Reshape shape [(2, 60), (4,)] opt {}
28: op Reciprocal shape [(2, 1)] opt {}
29: op Reshape shape [(2, 1), (4,)] opt {}
30: op Reshape shape [(2, 1), (4,)] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['X', 'W', 'B']
0: op LayerNormalization shape [(2, 3, 4, 5), (4, 5), (4, 5)] opt {'axis': 2}
prepare <class '__main__.TinygradBackend'> CPU ['X', 'W', 'B']
0: op Constant shape [] opt {'value': <Tensor <LB HIP () contig:True (<LoadOps.CONST: 2>, None)> on HIP with grad None>}
1: op Cast shape [()] opt {'to': 1}
2: op Shape shape [(2, 3, 4, 5)] opt {}
3: op Size shape [(4,)] opt {}
4: op Constant shape [] opt {'value': <Tensor <LB HIP (1,) contig:True (<LoadOps.COPY: 3>, None)> on HIP with grad None>}
5: op Constant shape [] opt {'value': <Tensor <LB HIP (1,) contig:True (<LoadOps.COPY: 3>, None)> on HIP with grad None>}
6: op Slice shape [(4,), (1,), (1,)] opt {}
7: op Sub shape [4, (1,)] opt {}
8: op ConstantOfShape shape [(1,)] opt {'value': <Tensor <LB HIP (1,) contig:True (<LoadOps.COPY: 3>, None)> on HIP with grad None>}
9: op Concat shape [(2,), (2,)] opt {'axis': 0}
10: op Flatten shape [(2, 3, 4, 5)] opt {'axis': 2}
11: op Cast shape [(6, 20)] opt {'to': 1}
12: op ReduceMean shape [(6, 20)] opt {'axes': (1,)}
13: op Mul shape [(6, 20), (6, 20)] opt {}
14: op ReduceMean shape [(6, 20)] opt {'axes': (1,)}
15: op Mul shape [(6, 1), (6, 1)] opt {}
16: op Sub shape [(6, 1), (6, 1)] opt {}
17: op Add shape [(6, 1), ()] opt {}
18: op Sqrt shape [(6, 1)] opt {}
19: op Sub shape [(6, 20), (6, 1)] opt {}
20: op Div shape [(6, 20), (6, 1)] opt {}
21: op Cast shape [(6, 20)] opt {'to': 1}
22: op Flatten shape [(4, 5)] opt {'axis': 0}
23: op Mul shape [(6, 20), (1, 20)] opt {}
24: op Flatten shape [(4, 5)] opt {'axis': 0}
25: op Add shape [(6, 20), (1, 20)] opt {}
26: op Reshape shape [(6, 20), (4,)] opt {}
27: op Reciprocal shape [(6, 1)] opt {}
28: op Reshape shape [(6, 1), (4,)] opt {}
29: op Reshape shape [(6, 1), (4,)] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['X', 'W', 'B']
0: op Constant shape [] opt {'value': <Tensor <LB HIP () contig:True (<LoadOps.CONST: 2>, None)> on HIP with grad None>}
1: op Cast shape [()] opt {'to': 1}
2: op Shape shape [(2, 3, 4, 5)] opt {}
3: op Size shape [(4,)] opt {}
4: op Constant shape [] opt {'value': <Tensor <LB HIP (1,) contig:True (<LoadOps.COPY: 3>, None)> on HIP with grad None>}
5: op Constant shape [] opt {'value': <Tensor <LB HIP (1,) contig:True (<LoadOps.COPY: 3>, None)> on HIP with grad None>}
6: op Slice shape [(4,), (1,), (1,)] opt {}
7: op Sub shape [4, (1,)] opt {}
8: op ConstantOfShape shape [(1,)] opt {'value': <Tensor <LB HIP (1,) contig:True (<LoadOps.COPY: 3>, None)> on HIP with grad None>}
9: op Concat shape [(2,), (2,)] opt {'axis': 0}
10: op Flatten shape [(2, 3, 4, 5)] opt {'axis': 2}
11: op Cast shape [(6, 20)] opt {'to': 1}
12: op Constant shape [] opt {'value': <Tensor <LB HIP (1,) contig:True (<LoadOps.COPY: 3>, None)> on HIP with grad None>}
13: op ReduceMean shape [(6, 20), (1,)] opt {}
14: op Mul shape [(6, 20), (6, 20)] opt {}
15: op ReduceMean shape [(6, 20), (1,)] opt {}
16: op Mul shape [(6, 1), (6, 1)] opt {}
.s.s.s.s.s.s.s.s17: op Sub shape [(6, 1), (6, 1)] opt {}
18: op Add shape [(6, 1), ()] opt {}
19: op Sqrt shape [(6, 1)] opt {}
20: op Sub shape [(6, 20), (6, 1)] opt {}
21: op Div shape [(6, 20), (6, 1)] opt {}
22: op Cast shape [(6, 20)] opt {'to': 1}
23: op Flatten shape [(4, 5)] opt {'axis': 0}
24: op Mul shape [(6, 20), (1, 20)] opt {}
25: op Flatten shape [(4, 5)] opt {'axis': 0}
26: op Add shape [(6, 20), (1, 20)] opt {}
27: op Reshape shape [(6, 20), (4,)] opt {}
28: op Reciprocal shape [(6, 1)] opt {}
29: op Reshape shape [(6, 1), (4,)] opt {}
30: op Reshape shape [(6, 1), (4,)] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['X', 'W', 'B']
0: op LayerNormalization shape [(2, 3, 4, 5), (5,), (5,)] opt {'axis': 3}
prepare <class '__main__.TinygradBackend'> CPU ['X', 'W', 'B']
0: op Constant shape [] opt {'value': <Tensor <LB HIP () contig:True (<LoadOps.CONST: 2>, None)> on HIP with grad None>}
1: op Cast shape [()] opt {'to': 1}
2: op Shape shape [(2, 3, 4, 5)] opt {}
3: op Size shape [(4,)] opt {}
4: op Constant shape [] opt {'value': <Tensor <LB HIP (1,) contig:True (<LoadOps.COPY: 3>, None)> on HIP with grad None>}
5: op Constant shape [] opt {'value': <Tensor <LB HIP (1,) contig:True (<LoadOps.COPY: 3>, None)> on HIP with grad None>}
6: op Slice shape [(4,), (1,), (1,)] opt {}
7: op Sub shape [4, (1,)] opt {}
8: op ConstantOfShape shape [(1,)] opt {'value': <Tensor <LB HIP (1,) contig:True (<LoadOps.COPY: 3>, None)> on HIP with grad None>}
9: op Concat shape [(3,), (1,)] opt {'axis': 0}
10: op Flatten shape [(2, 3, 4, 5)] opt {'axis': 3}
11: op Cast shape [(24, 5)] opt {'to': 1}
12: op ReduceMean shape [(24, 5)] opt {'axes': (1,)}
13: op Mul shape [(24, 5), (24, 5)] opt {}
14: op ReduceMean shape [(24, 5)] opt {'axes': (1,)}
15: op Mul shape [(24, 1), (24, 1)] opt {}
16: op Sub shape [(24, 1), (24, 1)] opt {}
17: op Add shape [(24, 1), ()] opt {}
18: op Sqrt shape [(24, 1)] opt {}
19: op Sub shape [(24, 5), (24, 1)] opt {}
20: op Div shape [(24, 5), (24, 1)] opt {}
21: op Cast shape [(24, 5)] opt {'to': 1}
22: op Flatten shape [(5,)] opt {'axis': 0}
23: op Mul shape [(24, 5), (1, 5)] opt {}
24: op Flatten shape [(5,)] opt {'axis': 0}
25: op Add shape [(24, 5), (1, 5)] opt {}
26: op Reshape shape [(24, 5), (4,)] opt {}
27: op Reciprocal shape [(24, 1)] opt {}
28: op Reshape shape [(24, 1), (4,)] opt {}
29: op Reshape shape [(24, 1), (4,)] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['X', 'W', 'B']
0: op Constant shape [] opt {'value': <Tensor <LB HIP () contig:True (<LoadOps.CONST: 2>, None)> on HIP with grad None>}
1: op Cast shape [()] opt {'to': 1}
2: op Shape shape [(2, 3, 4, 5)] opt {}
3: op Size shape [(4,)] opt {}
4: op Constant shape [] opt {'value': <Tensor <LB HIP (1,) contig:True (<LoadOps.COPY: 3>, None)> on HIP with grad None>}
5: op Constant shape [] opt {'value': <Tensor <LB HIP (1,) contig:True (<LoadOps.COPY: 3>, None)> on HIP with grad None>}
6: op Slice shape [(4,), (1,), (1,)] opt {}
7: op Sub shape [4, (1,)] opt {}
8: op ConstantOfShape shape [(1,)] opt {'value': <Tensor <LB HIP (1,) contig:True (<LoadOps.COPY: 3>, None)> on HIP with grad None>}
9: op Concat shape [(3,), (1,)] opt {'axis': 0}
10: op Flatten shape [(2, 3, 4, 5)] opt {'axis': 3}
11: op Cast shape [(24, 5)] opt {'to': 1}
12: op Constant shape [] opt {'value': <Tensor <LB HIP (1,) contig:True (<LoadOps.COPY: 3>, None)> on HIP with grad None>}
13: op ReduceMean shape [(24, 5), (1,)] opt {}
14: op Mul shape [(24, 5), (24, 5)] opt {}
15: op ReduceMean shape [(24, 5), (1,)] opt {}
16: op Mul shape [(24, 1), (24, 1)] opt {}
17: op Sub shape [(24, 1), (24, 1)] opt {}
18: op Add shape [(24, 1), ()] opt {}
19: op Sqrt shape [(24, 1)] opt {}
20: op Sub shape [(24, 5), (24, 1)] opt {}
21: op Div shape [(24, 5), (24, 1)] opt {}
22: op Cast shape [(24, 5)] opt {'to': 1}
23: op Flatten shape [(5,)] opt {'axis': 0}
24: op Mul shape [(24, 5), (1, 5)] opt {}
25: op Flatten shape [(5,)] opt {'axis': 0}
26: op Add shape [(24, 5), (1, 5)] opt {}
27: op Reshape shape [(24, 5), (4,)] opt {}
28: op Reciprocal shape [(24, 1)] opt {}
29: op Reshape shape [(24, 1), (4,)] opt {}
30: op Reshape shape [(24, 1), (4,)] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['X', 'W', 'B']
0: op LayerNormalization shape [(2, 3, 4, 5), (5,), (5,)] opt {'axis': -1}
prepare <class '__main__.TinygradBackend'> CPU ['X', 'W', 'B']
0: op Constant shape [] opt {'value': <Tensor <LB HIP () contig:True (<LoadOps.CONST: 2>, None)> on HIP with grad None>}
1: op Cast shape [()] opt {'to': 1}
2: op Shape shape [(2, 3, 4, 5)] opt {}
3: op Size shape [(4,)] opt {}
4: op Constant shape [] opt {'value': <Tensor <LB HIP (1,) contig:True (<LoadOps.COPY: 3>, None)> on HIP with grad None>}
5: op Constant shape [] opt {'value': <Tensor <LB HIP (1,) contig:True (<LoadOps.COPY: 3>, None)> on HIP with grad None>}
6: op Slice shape [(4,), (1,), (1,)] opt {}
7: op Neg shape [(1,)] opt {}
8: op ConstantOfShape shape [(1,)] opt {'value': <Tensor <LB HIP (1,) contig:True (<LoadOps.COPY: 3>, None)> on HIP with grad None>}
9: op Concat shape [(3,), (1,)] opt {'axis': 0}
10: op Flatten shape [(2, 3, 4, 5)] opt {'axis': -1}
11: op Cast shape [(24, 5)] opt {'to': 1}
12: op ReduceMean shape [(24, 5)] opt {'axes': (1,)}
13: op Mul shape [(24, 5), (24, 5)] opt {}
14: op ReduceMean shape [(24, 5)] opt {'axes': (1,)}
15: op Mul shape [(24, 1), (24, 1)] opt {}
16: op Sub shape [(24, 1), (24, 1)] opt {}
17: op Add shape [(24, 1), ()] opt {}
18: op Sqrt shape [(24, 1)] opt {}
19: op Sub shape [(24, 5), (24, 1)] opt {}
20: op Div shape [(24, 5), (24, 1)] opt {}
21: op Cast shape [(24, 5)] opt {'to': 1}
22: op Flatten shape [(5,)] opt {'axis': 0}
23: op Mul shape [(24, 5), (1, 5)] opt {}
24: op Flatten shape [(5,)] opt {'axis': 0}
25: op Add shape [(24, 5), (1, 5)] opt {}
26: op Reshape shape [(24, 5), (4,)] opt {}
27: op Reciprocal shape [(24, 1)] opt {}
28: op Reshape shape [(24, 1), (4,)] opt {}
29: op Reshape shape [(24, 1), (4,)] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['X', 'W', 'B']
0: op Constant shape [] opt {'value': <Tensor <LB HIP () contig:True (<LoadOps.CONST: 2>, None)> on HIP with grad None>}
1: op Cast shape [()] opt {'to': 1}
2: op Shape shape [(2, 3, 4, 5)] opt {}
3: op Size shape [(4,)] opt {}
4: op Constant shape [] opt {'value': <Tensor <LB HIP (1,) contig:True (<LoadOps.COPY: 3>, None)> on HIP with grad None>}
5: op Constant shape [] opt {'value': <Tensor <LB HIP (1,) contig:True (<LoadOps.COPY: 3>, None)> on HIP with grad None>}
6: op Slice shape [(4,), (1,), (1,)] opt {}
7: op Neg shape [(1,)] opt {}
8: op ConstantOfShape shape [(1,)] opt {'value': <Tensor <LB HIP (1,) contig:True (<LoadOps.COPY: 3>, None)> on HIP with grad None>}
9: op Concat shape [(3,), (1,)] opt {'axis': 0}
10: op Flatten shape [(2, 3, 4, 5)] opt {'axis': -1}
11: op Cast shape [(24, 5)] opt {'to': 1}
12: op Constant shape [] opt {'value': <Tensor <LB HIP (1,) contig:True (<LoadOps.COPY: 3>, None)> on HIP with grad None>}
13: op ReduceMean shape [(24, 5), (1,)] opt {}
14: op Mul shape [(24, 5), (24, 5)] opt {}
15: op ReduceMean shape [(24, 5), (1,)] opt {}
16: op Mul shape [(24, 1), (24, 1)] opt {}
17: op Sub shape [(24, 1), (24, 1)] opt {}
18: op Add shape [(24, 1), ()] opt {}
19: op Sqrt shape [(24, 1)] opt {}
20: op Sub shape [(24, 5), (24, 1)] opt {}
21: op Div shape [(24, 5), (24, 1)] opt {}
22: op Cast shape [(24, 5)] opt {'to': 1}
23: op Flatten shape [(5,)] opt {'axis': 0}
24: op Mul shape [(24, 5), (1, 5)] opt {}
25: op Flatten shape [(5,)] opt {'axis': 0}
26: op Add shape [(24, 5), (1, 5)] opt {}
27: op Reshape shape [(24, 5), (4,)] opt {}
28: op Reciprocal shape [(24, 1)] opt {}
29: op Reshape shape [(24, 1), (4,)] opt {}
30: op Reshape shape [(24, 1), (4,)] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['X', 'W', 'B']
0: op LayerNormalization shape [(2, 3, 4, 5), (4, 5), (4, 5)] opt {'axis': -2}
prepare <class '__main__.TinygradBackend'> CPU ['X', 'W', 'B']
0: op Constant shape [] opt {'value': <Tensor <LB HIP () contig:True (<LoadOps.CONST: 2>, None)> on HIP with grad None>}
1: op Cast shape [()] opt {'to': 1}
2: op Shape shape [(2, 3, 4, 5)] opt {}
3: op Size shape [(4,)] opt {}
.s.s.s.s.s.s4: op Constant shape [] opt {'value': <Tensor <LB HIP (1,) contig:True (<LoadOps.COPY: 3>, None)> on HIP with grad None>}
5: op Constant shape [] opt {'value': <Tensor <LB HIP (1,) contig:True (<LoadOps.COPY: 3>, None)> on HIP with grad None>}
6: op Slice shape [(4,), (1,), (1,)] opt {}
7: op Neg shape [(1,)] opt {}
8: op ConstantOfShape shape [(1,)] opt {'value': <Tensor <LB HIP (1,) contig:True (<LoadOps.COPY: 3>, None)> on HIP with grad None>}
9: op Concat shape [(2,), (2,)] opt {'axis': 0}
10: op Flatten shape [(2, 3, 4, 5)] opt {'axis': -2}
11: op Cast shape [(6, 20)] opt {'to': 1}
12: op ReduceMean shape [(6, 20)] opt {'axes': (1,)}
13: op Mul shape [(6, 20), (6, 20)] opt {}
14: op ReduceMean shape [(6, 20)] opt {'axes': (1,)}
15: op Mul shape [(6, 1), (6, 1)] opt {}
16: op Sub shape [(6, 1), (6, 1)] opt {}
17: op Add shape [(6, 1), ()] opt {}
18: op Sqrt shape [(6, 1)] opt {}
19: op Sub shape [(6, 20), (6, 1)] opt {}
20: op Div shape [(6, 20), (6, 1)] opt {}
21: op Cast shape [(6, 20)] opt {'to': 1}
22: op Flatten shape [(4, 5)] opt {'axis': 0}
23: op Mul shape [(6, 20), (1, 20)] opt {}
24: op Flatten shape [(4, 5)] opt {'axis': 0}
25: op Add shape [(6, 20), (1, 20)] opt {}
26: op Reshape shape [(6, 20), (4,)] opt {}
27: op Reciprocal shape [(6, 1)] opt {}
28: op Reshape shape [(6, 1), (4,)] opt {}
29: op Reshape shape [(6, 1), (4,)] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['X', 'W', 'B']
0: op Constant shape [] opt {'value': <Tensor <LB HIP () contig:True (<LoadOps.CONST: 2>, None)> on HIP with grad None>}
1: op Cast shape [()] opt {'to': 1}
2: op Shape shape [(2, 3, 4, 5)] opt {}
3: op Size shape [(4,)] opt {}
4: op Constant shape [] opt {'value': <Tensor <LB HIP (1,) contig:True (<LoadOps.COPY: 3>, None)> on HIP with grad None>}
5: op Constant shape [] opt {'value': <Tensor <LB HIP (1,) contig:True (<LoadOps.COPY: 3>, None)> on HIP with grad None>}
6: op Slice shape [(4,), (1,), (1,)] opt {}
7: op Neg shape [(1,)] opt {}
8: op ConstantOfShape shape [(1,)] opt {'value': <Tensor <LB HIP (1,) contig:True (<LoadOps.COPY: 3>, None)> on HIP with grad None>}
9: op Concat shape [(2,), (2,)] opt {'axis': 0}
10: op Flatten shape [(2, 3, 4, 5)] opt {'axis': -2}
11: op Cast shape [(6, 20)] opt {'to': 1}
12: op Constant shape [] opt {'value': <Tensor <LB HIP (1,) contig:True (<LoadOps.COPY: 3>, None)> on HIP with grad None>}
13: op ReduceMean shape [(6, 20), (1,)] opt {}
14: op Mul shape [(6, 20), (6, 20)] opt {}
15: op ReduceMean shape [(6, 20), (1,)] opt {}
16: op Mul shape [(6, 1), (6, 1)] opt {}
17: op Sub shape [(6, 1), (6, 1)] opt {}
18: op Add shape [(6, 1), ()] opt {}
19: op Sqrt shape [(6, 1)] opt {}
20: op Sub shape [(6, 20), (6, 1)] opt {}
21: op Div shape [(6, 20), (6, 1)] opt {}
22: op Cast shape [(6, 20)] opt {'to': 1}
23: op Flatten shape [(4, 5)] opt {'axis': 0}
24: op Mul shape [(6, 20), (1, 20)] opt {}
25: op Flatten shape [(4, 5)] opt {'axis': 0}
26: op Add shape [(6, 20), (1, 20)] opt {}
27: op Reshape shape [(6, 20), (4,)] opt {}
28: op Reciprocal shape [(6, 1)] opt {}
29: op Reshape shape [(6, 1), (4,)] opt {}
30: op Reshape shape [(6, 1), (4,)] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['X', 'W', 'B']
0: op LayerNormalization shape [(2, 3, 4, 5), (3, 4, 5), (3, 4, 5)] opt {'axis': -3}
prepare <class '__main__.TinygradBackend'> CPU ['X', 'W', 'B']
0: op Constant shape [] opt {'value': <Tensor <LB HIP () contig:True (<LoadOps.CONST: 2>, None)> on HIP with grad None>}
1: op Cast shape [()] opt {'to': 1}
2: op Shape shape [(2, 3, 4, 5)] opt {}
3: op Size shape [(4,)] opt {}
4: op Constant shape [] opt {'value': <Tensor <LB HIP (1,) contig:True (<LoadOps.COPY: 3>, None)> on HIP with grad None>}
5: op Constant shape [] opt {'value': <Tensor <LB HIP (1,) contig:True (<LoadOps.COPY: 3>, None)> on HIP with grad None>}
6: op Slice shape [(4,), (1,), (1,)] opt {}
7: op Neg shape [(1,)] opt {}
8: op ConstantOfShape shape [(1,)] opt {'value': <Tensor <LB HIP (1,) contig:True (<LoadOps.COPY: 3>, None)> on HIP with grad None>}
9: op Concat shape [(1,), (3,)] opt {'axis': 0}
10: op Flatten shape [(2, 3, 4, 5)] opt {'axis': -3}
11: op Cast shape [(2, 60)] opt {'to': 1}
12: op ReduceMean shape [(2, 60)] opt {'axes': (1,)}
13: op Mul shape [(2, 60), (2, 60)] opt {}
14: op ReduceMean shape [(2, 60)] opt {'axes': (1,)}
15: op Mul shape [(2, 1), (2, 1)] opt {}
16: op Sub shape [(2, 1), (2, 1)] opt {}
17: op Add shape [(2, 1), ()] opt {}
18: op Sqrt shape [(2, 1)] opt {}
19: op Sub shape [(2, 60), (2, 1)] opt {}
20: op Div shape [(2, 60), (2, 1)] opt {}
21: op Cast shape [(2, 60)] opt {'to': 1}
22: op Flatten shape [(3, 4, 5)] opt {'axis': 0}
23: op Mul shape [(2, 60), (1, 60)] opt {}
24: op Flatten shape [(3, 4, 5)] opt {'axis': 0}
25: op Add shape [(2, 60), (1, 60)] opt {}
26: op Reshape shape [(2, 60), (4,)] opt {}
27: op Reciprocal shape [(2, 1)] opt {}
28: op Reshape shape [(2, 1), (4,)] opt {}
29: op Reshape shape [(2, 1), (4,)] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['X', 'W', 'B']
0: op Constant shape [] opt {'value': <Tensor <LB HIP () contig:True (<LoadOps.CONST: 2>, None)> on HIP with grad None>}
1: op Cast shape [()] opt {'to': 1}
2: op Shape shape [(2, 3, 4, 5)] opt {}
3: op Size shape [(4,)] opt {}
4: op Constant shape [] opt {'value': <Tensor <LB HIP (1,) contig:True (<LoadOps.COPY: 3>, None)> on HIP with grad None>}
5: op Constant shape [] opt {'value': <Tensor <LB HIP (1,) contig:True (<LoadOps.COPY: 3>, None)> on HIP with grad None>}
6: op Slice shape [(4,), (1,), (1,)] opt {}
7: op Neg shape [(1,)] opt {}
8: op ConstantOfShape shape [(1,)] opt {'value': <Tensor <LB HIP (1,) contig:True (<LoadOps.COPY: 3>, None)> on HIP with grad None>}
9: op Concat shape [(1,), (3,)] opt {'axis': 0}
10: op Flatten shape [(2, 3, 4, 5)] opt {'axis': -3}
11: op Cast shape [(2, 60)] opt {'to': 1}
12: op Constant shape [] opt {'value': <Tensor <LB HIP (1,) contig:True (<LoadOps.COPY: 3>, None)> on HIP with grad None>}
13: op ReduceMean shape [(2, 60), (1,)] opt {}
14: op Mul shape [(2, 60), (2, 60)] opt {}
15: op ReduceMean shape [(2, 60), (1,)] opt {}
16: op Mul shape [(2, 1), (2, 1)] opt {}
17: op Sub shape [(2, 1), (2, 1)] opt {}
18: op Add shape [(2, 1), ()] opt {}
19: op Sqrt shape [(2, 1)] opt {}
20: op Sub shape [(2, 60), (2, 1)] opt {}
21: op Div shape [(2, 60), (2, 1)] opt {}
22: op Cast shape [(2, 60)] opt {'to': 1}
23: op Flatten shape [(3, 4, 5)] opt {'axis': 0}
24: op Mul shape [(2, 60), (1, 60)] opt {}
25: op Flatten shape [(3, 4, 5)] opt {'axis': 0}
26: op Add shape [(2, 60), (1, 60)] opt {}
27: op Reshape shape [(2, 60), (4,)] opt {}
28: op Reciprocal shape [(2, 1)] opt {}
29: op Reshape shape [(2, 1), (4,)] opt {}
30: op Reshape shape [(2, 1), (4,)] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['X', 'W', 'B']
0: op LayerNormalization shape [(2, 3, 4, 5), (2, 3, 4, 5), (2, 3, 4, 5)] opt {'axis': -4}
prepare <class '__main__.TinygradBackend'> CPU ['X', 'W', 'B']
0: op Constant shape [] opt {'value': <Tensor <LB HIP () contig:True (<LoadOps.CONST: 2>, None)> on HIP with grad None>}
1: op Cast shape [()] opt {'to': 1}
2: op Shape shape [(2, 3, 4, 5)] opt {}
3: op Size shape [(4,)] opt {}
4: op Constant shape [] opt {'value': <Tensor <LB HIP (1,) contig:True (<LoadOps.COPY: 3>, None)> on HIP with grad None>}
5: op Constant shape [] opt {'value': <Tensor <LB HIP (1,) contig:True (<LoadOps.COPY: 3>, None)> on HIP with grad None>}
6: op Slice shape [(4,), (1,), (1,)] opt {}
7: op Neg shape [(1,)] opt {}
8: op ConstantOfShape shape [(1,)] opt {'value': <Tensor <LB HIP (1,) contig:True (<LoadOps.COPY: 3>, None)> on HIP with grad None>}
9: op Concat shape [(0,), (4,)] opt {'axis': 0}
10: op Flatten shape [(2, 3, 4, 5)] opt {'axis': -4}
11: op Cast shape [(1, 120)] opt {'to': 1}
12: op ReduceMean shape [(1, 120)] opt {'axes': (1,)}
13: op Mul shape [(1, 120), (1, 120)] opt {}
14: op ReduceMean shape [(1, 120)] opt {'axes': (1,)}
15: op Mul shape [(1, 1), (1, 1)] opt {}
16: op Sub shape [(1, 1), (1, 1)] opt {}
17: op Add shape [(1, 1), ()] opt {}
18: op Sqrt shape [(1, 1)] opt {}
19: op Sub shape [(1, 120), (1, 1)] opt {}
20: op Div shape [(1, 120), (1, 1)] opt {}
.s.s.s.s.s.s.s.s.s.s.s.s.s.s.s.s21: op Cast shape [(1, 120)] opt {'to': 1}
22: op Flatten shape [(2, 3, 4, 5)] opt {'axis': 0}
23: op Mul shape [(1, 120), (1, 120)] opt {}
24: op Flatten shape [(2, 3, 4, 5)] opt {'axis': 0}
25: op Add shape [(1, 120), (1, 120)] opt {}
26: op Reshape shape [(1, 120), (4,)] opt {}
27: op Reciprocal shape [(1, 1)] opt {}
28: op Reshape shape [(1, 1), (4,)] opt {}
29: op Reshape shape [(1, 1), (4,)] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['X', 'W', 'B']
0: op Constant shape [] opt {'value': <Tensor <LB HIP () contig:True (<LoadOps.CONST: 2>, None)> on HIP with grad None>}
1: op Cast shape [()] opt {'to': 1}
2: op Shape shape [(2, 3, 4, 5)] opt {}
3: op Size shape [(4,)] opt {}
4: op Constant shape [] opt {'value': <Tensor <LB HIP (1,) contig:True (<LoadOps.COPY: 3>, None)> on HIP with grad None>}
5: op Constant shape [] opt {'value': <Tensor <LB HIP (1,) contig:True (<LoadOps.COPY: 3>, None)> on HIP with grad None>}
6: op Slice shape [(4,), (1,), (1,)] opt {}
7: op Neg shape [(1,)] opt {}
8: op ConstantOfShape shape [(1,)] opt {'value': <Tensor <LB HIP (1,) contig:True (<LoadOps.COPY: 3>, None)> on HIP with grad None>}
9: op Concat shape [(0,), (4,)] opt {'axis': 0}
10: op Flatten shape [(2, 3, 4, 5)] opt {'axis': -4}
11: op Cast shape [(1, 120)] opt {'to': 1}
12: op Constant shape [] opt {'value': <Tensor <LB HIP (1,) contig:True (<LoadOps.COPY: 3>, None)> on HIP with grad None>}
13: op ReduceMean shape [(1, 120), (1,)] opt {}
14: op Mul shape [(1, 120), (1, 120)] opt {}
15: op ReduceMean shape [(1, 120), (1,)] opt {}
16: op Mul shape [(1, 1), (1, 1)] opt {}
17: op Sub shape [(1, 1), (1, 1)] opt {}
18: op Add shape [(1, 1), ()] opt {}
19: op Sqrt shape [(1, 1)] opt {}
20: op Sub shape [(1, 120), (1, 1)] opt {}
21: op Div shape [(1, 120), (1, 1)] opt {}
22: op Cast shape [(1, 120)] opt {'to': 1}
23: op Flatten shape [(2, 3, 4, 5)] opt {'axis': 0}
24: op Mul shape [(1, 120), (1, 120)] opt {}
25: op Flatten shape [(2, 3, 4, 5)] opt {'axis': 0}
26: op Add shape [(1, 120), (1, 120)] opt {}
27: op Reshape shape [(1, 120), (4,)] opt {}
28: op Reciprocal shape [(1, 1)] opt {}
29: op Reshape shape [(1, 1), (4,)] opt {}
30: op Reshape shape [(1, 1), (4,)] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['X', 'W', 'B']
0: op LayerNormalization shape [(2, 3, 4, 5), (5,), (5,)] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['X', 'W', 'B']
0: op Constant shape [] opt {'value': <Tensor <LB HIP () contig:True (<LoadOps.CONST: 2>, None)> on HIP with grad None>}
1: op Cast shape [()] opt {'to': 1}
2: op Shape shape [(2, 3, 4, 5)] opt {}
3: op Size shape [(4,)] opt {}
4: op Constant shape [] opt {'value': <Tensor <LB HIP (1,) contig:True (<LoadOps.COPY: 3>, None)> on HIP with grad None>}
5: op Constant shape [] opt {'value': <Tensor <LB HIP (1,) contig:True (<LoadOps.COPY: 3>, None)> on HIP with grad None>}
6: op Slice shape [(4,), (1,), (1,)] opt {}
7: op Neg shape [(1,)] opt {}
8: op ConstantOfShape shape [(1,)] opt {'value': <Tensor <LB HIP (1,) contig:True (<LoadOps.COPY: 3>, None)> on HIP with grad None>}
9: op Concat shape [(3,), (1,)] opt {'axis': 0}
10: op Flatten shape [(2, 3, 4, 5)] opt {'axis': -1}
11: op Cast shape [(24, 5)] opt {'to': 1}
12: op ReduceMean shape [(24, 5)] opt {'axes': (1,)}
13: op Mul shape [(24, 5), (24, 5)] opt {}
14: op ReduceMean shape [(24, 5)] opt {'axes': (1,)}
15: op Mul shape [(24, 1), (24, 1)] opt {}
16: op Sub shape [(24, 1), (24, 1)] opt {}
17: op Add shape [(24, 1), ()] opt {}
18: op Sqrt shape [(24, 1)] opt {}
19: op Sub shape [(24, 5), (24, 1)] opt {}
20: op Div shape [(24, 5), (24, 1)] opt {}
21: op Cast shape [(24, 5)] opt {'to': 1}
22: op Flatten shape [(5,)] opt {'axis': 0}
23: op Mul shape [(24, 5), (1, 5)] opt {}
24: op Flatten shape [(5,)] opt {'axis': 0}
25: op Add shape [(24, 5), (1, 5)] opt {}
26: op Reshape shape [(24, 5), (4,)] opt {}
27: op Reciprocal shape [(24, 1)] opt {}
28: op Reshape shape [(24, 1), (4,)] opt {}
29: op Reshape shape [(24, 1), (4,)] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['X', 'W', 'B']
0: op Constant shape [] opt {'value': <Tensor <LB HIP () contig:True (<LoadOps.CONST: 2>, None)> on HIP with grad None>}
1: op Cast shape [()] opt {'to': 1}
2: op Shape shape [(2, 3, 4, 5)] opt {}
3: op Size shape [(4,)] opt {}
4: op Constant shape [] opt {'value': <Tensor <LB HIP (1,) contig:True (<LoadOps.COPY: 3>, None)> on HIP with grad None>}
5: op Constant shape [] opt {'value': <Tensor <LB HIP (1,) contig:True (<LoadOps.COPY: 3>, None)> on HIP with grad None>}
6: op Slice shape [(4,), (1,), (1,)] opt {}
7: op Neg shape [(1,)] opt {}
8: op ConstantOfShape shape [(1,)] opt {'value': <Tensor <LB HIP (1,) contig:True (<LoadOps.COPY: 3>, None)> on HIP with grad None>}
9: op Concat shape [(3,), (1,)] opt {'axis': 0}
10: op Flatten shape [(2, 3, 4, 5)] opt {'axis': -1}
11: op Cast shape [(24, 5)] opt {'to': 1}
12: op Constant shape [] opt {'value': <Tensor <LB HIP (1,) contig:True (<LoadOps.COPY: 3>, None)> on HIP with grad None>}
13: op ReduceMean shape [(24, 5), (1,)] opt {}
14: op Mul shape [(24, 5), (24, 5)] opt {}
15: op ReduceMean shape [(24, 5), (1,)] opt {}
16: op Mul shape [(24, 1), (24, 1)] opt {}
17: op Sub shape [(24, 1), (24, 1)] opt {}
18: op Add shape [(24, 1), ()] opt {}
19: op Sqrt shape [(24, 1)] opt {}
20: op Sub shape [(24, 5), (24, 1)] opt {}
21: op Div shape [(24, 5), (24, 1)] opt {}
22: op Cast shape [(24, 5)] opt {'to': 1}
23: op Flatten shape [(5,)] opt {'axis': 0}
24: op Mul shape [(24, 5), (1, 5)] opt {}
25: op Flatten shape [(5,)] opt {'axis': 0}
26: op Add shape [(24, 5), (1, 5)] opt {}
27: op Reshape shape [(24, 5), (4,)] opt {}
28: op Reciprocal shape [(24, 1)] opt {}
29: op Reshape shape [(24, 1), (4,)] opt {}
30: op Reshape shape [(24, 1), (4,)] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['x']
0: op LeakyRelu shape [(3, 4, 5)] opt {'alpha': 0.10000000149011612}
prepare <class '__main__.TinygradBackend'> CPU ['x']
0: op LeakyRelu shape [(3, 4, 5)] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['x']
0: op Constant shape [] opt {'value_float': 0.009999999776482582}
1: op CastLike shape [(), (3, 4, 5)] opt {}
2: op Constant shape [] opt {'value': <Tensor <LB HIP () contig:True (<LoadOps.CONST: 2>, None)> on HIP with grad None>}
3: op CastLike shape [(), (3, 4, 5)] opt {}
4: op Less shape [(3, 4, 5), ()] opt {}
5: op Mul shape [(), (3, 4, 5)] opt {}
6: op Where shape [(3, 4, 5), (3, 4, 5), (3, 4, 5)] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['x']
0: op LeakyRelu shape [(3,)] opt {'alpha': 0.10000000149011612}
prepare <class '__main__.TinygradBackend'> CPU ['x']
0: op Constant shape [] opt {'value_float': 0.10000000149011612}
1: op CastLike shape [(), (3,)] opt {}
2: op Constant shape [] opt {'value': <Tensor <LB HIP () contig:True (<LoadOps.CONST: 2>, None)> on HIP with grad None>}
3: op CastLike shape [(), (3,)] opt {}
4: op Less shape [(3,), ()] opt {}
5: op Mul shape [(), (3,)] opt {}
6: op Where shape [(3,), (3,), (3,)] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['x']
0: op Constant shape [] opt {'value_float': 0.10000000149011612}
1: op CastLike shape [(), (3, 4, 5)] opt {}
2: op Constant shape [] opt {'value': <Tensor <LB HIP () contig:True (<LoadOps.CONST: 2>, None)> on HIP with grad None>}
3: op CastLike shape [(), (3, 4, 5)] opt {}
4: op Less shape [(3, 4, 5), ()] opt {}
5: op Mul shape [(), (3, 4, 5)] opt {}
6: op Where shape [(3, 4, 5), (3, 4, 5), (3, 4, 5)] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['x', 'y']
0: op Less shape [(3, 4, 5), (5,)] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['x', 'y']
0: op Less shape [(3, 4, 5), (3, 4, 5)] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['x', 'y']
0: op LessOrEqual shape [(3, 4, 5), (5,)] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['x', 'y']
0: op Less shape [(3, 4, 5), (5,)] opt {}
1: op Equal shape [(3, 4, 5), (5,)] opt {}
2: op Or shape [(3, 4, 5), (3, 4, 5)] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['x', 'y']
0: op LessOrEqual shape [(3, 4, 5), (3, 4, 5)] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['x', 'y']
0: op Less shape [(3, 4, 5), (3, 4, 5)] opt {}
.s.s.s.s.s.s.s.s.s.s.s.s.s.s.s.s.s.s.s.s.s.s.s.sssssssssssssssssssssss.s.sssssssss.s.s.sss.s.s1: op Equal shape [(3, 4, 5), (3, 4, 5)] opt {}
2: op Or shape [(3, 4, 5), (3, 4, 5)] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['x']
0: op Log shape [(3, 4, 5)] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['x']
0: op Log shape [(2,)] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['x']
0: op LogSoftmax shape [(3, 4, 5)] opt {'axis': 0}
prepare <class '__main__.TinygradBackend'> CPU ['x']
0: op Constant shape [] opt {'value': <Tensor <LB HIP (1,) contig:True (<LoadOps.COPY: 3>, None)> on HIP with grad None>}
1: op ReduceMax shape [(3, 4, 5)] opt {'keepdims': 1, 'axes': (0,)}
2: op Sub shape [(3, 4, 5), (1, 4, 5)] opt {}
3: op Exp shape [(3, 4, 5)] opt {}
4: op ReduceSum shape [(3, 4, 5), (1,)] opt {'keepdims': 1}
5: op Log shape [(1, 4, 5)] opt {}
6: op Sub shape [(3, 4, 5), (1, 4, 5)] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['x']
0: op Constant shape [] opt {'value': <Tensor <LB HIP (1,) contig:True (<LoadOps.COPY: 3>, None)> on HIP with grad None>}
1: op ReduceMax shape [(3, 4, 5), (1,)] opt {'keepdims': 1}
2: op Sub shape [(3, 4, 5), (1, 4, 5)] opt {}
3: op Exp shape [(3, 4, 5)] opt {}
4: op ReduceSum shape [(3, 4, 5), (1,)] opt {'keepdims': 1}
5: op Log shape [(1, 4, 5)] opt {}
6: op Sub shape [(3, 4, 5), (1, 4, 5)] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['x']
0: op LogSoftmax shape [(3, 4, 5)] opt {'axis': 1}
prepare <class '__main__.TinygradBackend'> CPU ['x']
0: op Constant shape [] opt {'value': <Tensor <LB HIP (1,) contig:True (<LoadOps.COPY: 3>, None)> on HIP with grad None>}
1: op ReduceMax shape [(3, 4, 5)] opt {'keepdims': 1, 'axes': (1,)}
2: op Sub shape [(3, 4, 5), (3, 1, 5)] opt {}
3: op Exp shape [(3, 4, 5)] opt {}
4: op ReduceSum shape [(3, 4, 5), (1,)] opt {'keepdims': 1}
5: op Log shape [(3, 1, 5)] opt {}
6: op Sub shape [(3, 4, 5), (3, 1, 5)] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['x']
0: op Constant shape [] opt {'value': <Tensor <LB HIP (1,) contig:True (<LoadOps.COPY: 3>, None)> on HIP with grad None>}
1: op ReduceMax shape [(3, 4, 5), (1,)] opt {'keepdims': 1}
2: op Sub shape [(3, 4, 5), (3, 1, 5)] opt {}
3: op Exp shape [(3, 4, 5)] opt {}
4: op ReduceSum shape [(3, 4, 5), (1,)] opt {'keepdims': 1}
5: op Log shape [(3, 1, 5)] opt {}
6: op Sub shape [(3, 4, 5), (3, 1, 5)] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['x']
0: op LogSoftmax shape [(3, 4, 5)] opt {'axis': 2}
prepare <class '__main__.TinygradBackend'> CPU ['x']
0: op Constant shape [] opt {'value': <Tensor <LB HIP (1,) contig:True (<LoadOps.COPY: 3>, None)> on HIP with grad None>}
1: op ReduceMax shape [(3, 4, 5)] opt {'keepdims': 1, 'axes': (2,)}
2: op Sub shape [(3, 4, 5), (3, 4, 1)] opt {}
3: op Exp shape [(3, 4, 5)] opt {}
4: op ReduceSum shape [(3, 4, 5), (1,)] opt {'keepdims': 1}
5: op Log shape [(3, 4, 1)] opt {}
6: op Sub shape [(3, 4, 5), (3, 4, 1)] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['x']
0: op Constant shape [] opt {'value': <Tensor <LB HIP (1,) contig:True (<LoadOps.COPY: 3>, None)> on HIP with grad None>}
1: op ReduceMax shape [(3, 4, 5), (1,)] opt {'keepdims': 1}
2: op Sub shape [(3, 4, 5), (3, 4, 1)] opt {}
3: op Exp shape [(3, 4, 5)] opt {}
4: op ReduceSum shape [(3, 4, 5), (1,)] opt {'keepdims': 1}
5: op Log shape [(3, 4, 1)] opt {}
6: op Sub shape [(3, 4, 5), (3, 4, 1)] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['x']
0: op LogSoftmax shape [(3, 4, 5)] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['x']
0: op Constant shape [] opt {'value': <Tensor <LB HIP (1,) contig:True (<LoadOps.COPY: 3>, None)> on HIP with grad None>}
1: op ReduceMax shape [(3, 4, 5)] opt {'keepdims': 1, 'axes': (-1,)}
2: op Sub shape [(3, 4, 5), (3, 4, 1)] opt {}
3: op Exp shape [(3, 4, 5)] opt {}
4: op ReduceSum shape [(3, 4, 5), (1,)] opt {'keepdims': 1}
5: op Log shape [(3, 4, 1)] opt {}
6: op Sub shape [(3, 4, 5), (3, 4, 1)] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['x']
0: op Constant shape [] opt {'value': <Tensor <LB HIP (1,) contig:True (<LoadOps.COPY: 3>, None)> on HIP with grad None>}
1: op ReduceMax shape [(3, 4, 5), (1,)] opt {'keepdims': 1}
2: op Sub shape [(3, 4, 5), (3, 4, 1)] opt {}
3: op Exp shape [(3, 4, 5)] opt {}
4: op ReduceSum shape [(3, 4, 5), (1,)] opt {'keepdims': 1}
5: op Log shape [(3, 4, 1)] opt {}
6: op Sub shape [(3, 4, 5), (3, 4, 1)] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['x']
0: op LogSoftmax shape [(1, 3)] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['x']
0: op Constant shape [] opt {'value': <Tensor <LB HIP (1,) contig:True (<LoadOps.COPY: 3>, None)> on HIP with grad None>}
1: op ReduceMax shape [(1, 3)] opt {'keepdims': 1, 'axes': (-1,)}
2: op Sub shape [(1, 3), (1, 1)] opt {}
3: op Exp shape [(1, 3)] opt {}
4: op ReduceSum shape [(1, 3), (1,)] opt {'keepdims': 1}
5: op Log shape [(1, 1)] opt {}
6: op Sub shape [(1, 3), (1, 1)] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['x']
0: op Constant shape [] opt {'value': <Tensor <LB HIP (1,) contig:True (<LoadOps.COPY: 3>, None)> on HIP with grad None>}
1: op ReduceMax shape [(1, 3), (1,)] opt {'keepdims': 1}
2: op Sub shape [(1, 3), (1, 1)] opt {}
3: op Exp shape [(1, 3)] opt {}
4: op ReduceSum shape [(1, 3), (1,)] opt {'keepdims': 1}
5: op Log shape [(1, 1)] opt {}
6: op Sub shape [(1, 3), (1, 1)] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['x']
0: op LogSoftmax shape [(2, 4)] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['x']
0: op Constant shape [] opt {'value': <Tensor <LB HIP (1,) contig:True (<LoadOps.COPY: 3>, None)> on HIP with grad None>}
1: op ReduceMax shape [(2, 4)] opt {'keepdims': 1, 'axes': (-1,)}
2: op Sub shape [(2, 4), (2, 1)] opt {}
3: op Exp shape [(2, 4)] opt {}
4: op ReduceSum shape [(2, 4), (1,)] opt {'keepdims': 1}
5: op Log shape [(2, 1)] opt {}
6: op Sub shape [(2, 4), (2, 1)] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['x']
0: op Constant shape [] opt {'value': <Tensor <LB HIP (1,) contig:True (<LoadOps.COPY: 3>, None)> on HIP with grad None>}
1: op ReduceMax shape [(2, 4), (1,)] opt {'keepdims': 1}
2: op Sub shape [(2, 4), (2, 1)] opt {}
3: op Exp shape [(2, 4)] opt {}
4: op ReduceSum shape [(2, 4), (1,)] opt {'keepdims': 1}
5: op Log shape [(2, 1)] opt {}
6: op Sub shape [(2, 4), (2, 1)] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['x']
0: op LogSoftmax shape [(3, 4, 5)] opt {'axis': -1}
prepare <class '__main__.TinygradBackend'> CPU ['x']
0: op Constant shape [] opt {'value': <Tensor <LB HIP (1,) contig:True (<LoadOps.COPY: 3>, None)> on HIP with grad None>}
1: op ReduceMax shape [(3, 4, 5)] opt {'keepdims': 1, 'axes': (-1,)}
2: op Sub shape [(3, 4, 5), (3, 4, 1)] opt {}
3: op Exp shape [(3, 4, 5)] opt {}
4: op ReduceSum shape [(3, 4, 5), (1,)] opt {'keepdims': 1}
5: op Log shape [(3, 4, 1)] opt {}
6: op Sub shape [(3, 4, 5), (3, 4, 1)] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['x']
0: op Constant shape [] opt {'value': <Tensor <LB HIP (1,) contig:True (<LoadOps.COPY: 3>, None)> on HIP with grad None>}
1: op ReduceMax shape [(3, 4, 5), (1,)] opt {'keepdims': 1}
2: op Sub shape [(3, 4, 5), (3, 4, 1)] opt {}
3: op Exp shape [(3, 4, 5)] opt {}
4: op ReduceSum shape [(3, 4, 5), (1,)] opt {'keepdims': 1}
5: op Log shape [(3, 4, 1)] opt {}
6: op Sub shape [(3, 4, 5), (3, 4, 1)] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['x']
0: op LRN shape [(5, 5, 5, 5)] opt {'alpha': 0.00019999999494757503, 'beta': 0.5, 'bias': 2.0, 'size': 3}
prepare <class '__main__.TinygradBackend'> CPU ['x']
0: op LRN shape [(5, 5, 5, 5)] opt {'size': 3}
prepare <class '__main__.TinygradBackend'> CPU ['a', 'b']
0: op MatMul shape [(3, 4), (4, 3)] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['a', 'b']
0: op MatMul shape [(2, 3, 4), (2, 4, 3)] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['a', 'b']
0: op MatMul shape [(1, 2, 3, 4), (1, 2, 4, 3)] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['data_0', 'data_1', 'data_2']
0: op Max shape [(3,), (3,), (3,)] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['data_0', 'data_1']
0: op Max shape [(3,), (3,)] opt {}
prepare <class '__main__.TinygradBackend'> CPU .s.s.s.s.s.s.s.s.s.s.s.s.s.s.s.s.s.s.s.s.s.s.s.s.s.s.s.s.s.s.s.s.s.s.sss.s.s.s.s.s.s.s.s.s.s.s.s.s.s.s.sssssssssssssssssssssssssss.s.s.s.s.s.s.s.s['data_0', 'data_1']
0: op Max shape [(3,), (3,)] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['data_0', 'data_1']
0: op Max shape [(3,), (3,)] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['data_0', 'data_1']
0: op Max shape [(3,), (3,)] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['data_0', 'data_1']
0: op Max shape [(3,), (3,)] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['data_0', 'data_1']
0: op Max shape [(3,), (3,)] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['data_0', 'data_1']
0: op Max shape [(3,), (3,)] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['data_0']
0: op Max shape [(3,)] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['data_0', 'data_1']
0: op Max shape [(3,), (3,)] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['data_0', 'data_1']
0: op Max shape [(3,), (3,)] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['data_0', 'data_1']
0: op Max shape [(3,), (3,)] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['data_0', 'data_1']
0: op Max shape [(3,), (3,)] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['data_0', 'data_1']
0: op Max shape [(3,), (3,)] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['x']
0: op MaxPool shape [(1, 3, 32)] opt {'kernel_shape': (2,)}
prepare <class '__main__.TinygradBackend'> CPU ['x']
0: op MaxPool shape [(1, 1, 4, 4)] opt {'ceil_mode': 1, 'kernel_shape': (3, 3), 'strides': (2, 2)}
prepare <class '__main__.TinygradBackend'> CPU ['x']
0: op MaxPool shape [(1, 3, 32, 32)] opt {'kernel_shape': (2, 2)}
prepare <class '__main__.TinygradBackend'> CPU ['x']
0: op MaxPool shape [(1, 1, 4, 4)] opt {'dilations': (2, 2), 'kernel_shape': (2, 2), 'strides': (1, 1)}
prepare <class '__main__.TinygradBackend'> CPU ['x']
0: op MaxPool shape [(1, 3, 28, 28)] opt {'kernel_shape': (3, 3), 'pads': (2, 2, 2, 2)}
prepare <class '__main__.TinygradBackend'> CPU ['x']
0: op MaxPool shape [(1, 1, 5, 5)] opt {'kernel_shape': (5, 5), 'pads': (2, 2, 2, 2)}
prepare <class '__main__.TinygradBackend'> CPU ['x']
0: op MaxPool shape [(1, 1, 5, 5)] opt {'auto_pad': 'SAME_UPPER', 'kernel_shape': (3, 3), 'strides': (2, 2)}
prepare <class '__main__.TinygradBackend'> CPU ['x']
0: op MaxPool shape [(1, 1, 5, 5)] opt {'kernel_shape': (2, 2), 'strides': (2, 2)}
prepare <class '__main__.TinygradBackend'> CPU ['x']
0: op MaxPool shape [(1, 3, 32, 32)] opt {'auto_pad': 'SAME_LOWER', 'kernel_shape': (2, 2)}
prepare <class '__main__.TinygradBackend'> CPU ['x']
0: op MaxPool shape [(1, 3, 32, 32)] opt {'auto_pad': 'SAME_UPPER', 'kernel_shape': (2, 2)}
prepare <class '__main__.TinygradBackend'> CPU ['x']
0: op MaxPool shape [(1, 3, 32, 32)] opt {'kernel_shape': (5, 5), 'strides': (3, 3)}
prepare <class '__main__.TinygradBackend'> CPU ['x']
0: op MaxPool shape [(1, 1, 5, 5)] opt {'kernel_shape': (5, 5), 'pads': (2, 2, 2, 2)}
prepare <class '__main__.TinygradBackend'> CPU ['x']
0: op MaxPool shape [(1, 3, 32, 32, 32)] opt {'kernel_shape': (2, 2, 2)}
prepare <class '__main__.TinygradBackend'> CPU ['x']
0: op MaxPool shape [(1, 1, 4, 4, 4)] opt {'dilations': (2, 2, 2), 'kernel_shape': (2, 2, 2), 'strides': (1, 1, 1)}
prepare <class '__main__.TinygradBackend'> CPU ['x']
0: op MaxPool shape [(1, 1, 4, 4, 4)] opt {'dilations': (2, 2, 2), 'kernel_shape': (2, 2, 2), 'strides': (1, 1, 1)}
prepare <class '__main__.TinygradBackend'> CPU ['x']
0: op MaxPool shape [(1, 1, 32, 32, 32)] opt {'ceil_mode': 1, 'dilations': (2, 2, 2), 'kernel_shape': (5, 5, 5), 'strides': (3, 3, 3)}
prepare <class '__main__.TinygradBackend'> CPU ['x']
0: op MaxPool shape [(1, 1, 5, 5)] opt {'kernel_shape': (5, 5), 'pads': (2, 2, 2, 2)}
prepare <class '__main__.TinygradBackend'> CPU ['x']
0: op MaxPool shape [(1, 1, 5, 5)] opt {'kernel_shape': (2, 2), 'storage_order': 1, 'strides': (2, 2)}
prepare <class '__main__.TinygradBackend'> CPU ['xT', 'xI', 'output_shape']
0: op MaxUnpool shape [(1, 1, 2, 2), (1, 1, 2, 2), (4,)] opt {'kernel_shape': (2, 2), 'strides': (2, 2)}
prepare <class '__main__.TinygradBackend'> CPU ['xT', 'xI']
0: op MaxUnpool shape [(1, 1, 2, 2), (1, 1, 2, 2)] opt {'kernel_shape': (2, 2), 'strides': (2, 2)}
prepare <class '__main__.TinygradBackend'> CPU ['data_0', 'data_1', 'data_2']
0: op Mean shape [(3,), (3,), (3,)] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['data_0']
0: op Mean shape [(3,)] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['data_0', 'data_1']
0: op Mean shape [(3,), (3,)] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['data_0', 'data_1', 'data_2']
0: op Min shape [(3,), (3,), (3,)] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['data_0', 'data_1']
0: op Min shape [(3,), (3,)] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['data_0', 'data_1']
0: op Min shape [(3,), (3,)] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['data_0', 'data_1']
0: op Min shape [(3,), (3,)] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['data_0', 'data_1']
0: op Min shape [(3,), (3,)] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['data_0', 'data_1']
0: op Min shape [(3,), (3,)] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['data_0', 'data_1']
0: op Min shape [(3,), (3,)] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['data_0', 'data_1']
0: op Min shape [(3,), (3,)] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['data_0']
0: op Min shape [(3,)] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['data_0', 'data_1']
0: op Min shape [(3,), (3,)] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['data_0', 'data_1']
0: op Min shape [(3,), (3,)] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['data_0', 'data_1']
0: op Min shape [(3,), (3,)] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['data_0', 'data_1']
0: op Min shape [(3,), (3,)] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['data_0', 'data_1']
0: op Min shape [(3,), (3,)] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['X']
0: op Mish shape [(10000,)] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['X']
0: op Softplus shape [(10000,)] opt {}
1: op Tanh shape [(10000,)] opt {}
2: op Mul shape [(10000,), (10000,)] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['R', 'T', 'X', 'G', 'V']
0: op Momentum shape [(), (), (2,), (2,), (2,)] opt {'alpha': 0.949999988079071, 'beta': 0.10000000149011612, 'mode': 'standard', 'norm_coefficient': 0.0010000000474974513}
prepare <class '__main__.TinygradBackend'> CPU ['R', 'T', 'X1', 'X2', 'G1', 'G2', 'H1', 'H2']
0: op Momentum shape [(), (), (1,), (2,), (1,), (2,), (1,), (2,)] opt {'alpha': 0.949999988079071, 'beta': 0.8500000238418579, 'mode': 'standard', 'norm_coefficient': 0.0010000000474974513}
prepare <class '__main__.TinygradBackend'> CPU ['x', 'y']
0: op Mul shape [(3, 4, 5), (5,)] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['x', 'y']
0: op Mul shape [(3, 4, 5), (3, 4, 5)] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['x', 'y']
0: op Mul shape [(3,), (3,)] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['x', 'y']
0: op Mul shape [(3, 4, 5), (3, 4, 5)] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['X']
0: op MeanVarianceNormalization shape [(3, 3, 3, 1)] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['X']
0: op Constant shape [] opt {'value': <Tensor <LB HIP () contig:True (<LoadOps.CONST: 2>, None)> on HIP with grad None>}
1: op Constant shape [] opt {'value': <Tensor <LB HIP () contig:True (<LoadOps.CONST: 2>, None)> on HIP with grad None>}
2: op ReduceMean shape [(3, 3, 3, 1)] opt {'axes': (0, 2, 3)}
3: op Pow shape [(1, 3, 1, 1), ()] opt {}
4: op Pow shape [(3, 3, 3, 1), ()] opt {}
5: op ReduceMean shape [(3, 3, 3, 1)] opt {'axes': (0, 2, 3)}
6: op Sub shape [(1, 3, 1, 1), (1, 3, 1, 1)] opt {}
7: op Sqrt shape [(1, 3, 1, 1)] opt {}
8: op Sub shape [(3, 3, 3, 1), (1, 3, 1, 1)] opt {}
9: op Add shape [(1, 3, 1, 1), ()] opt {}
10: op Div shape [(3, 3, 3, 1), (1, 3, 1, 1)] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['X']
0: op Constant shape [] opt {'value': <Tensor <LB HIP () contig:True (<LoadOps.CONST: 2>, None)> on HIP with grad None>}
.s.s.sss.s.s.s.s.s.s.s.s.s.s.s1: op Constant shape [] opt {'value': <Tensor <LB HIP () contig:True (<LoadOps.CONST: 2>, None)> on HIP with grad None>}
2: op Constant shape [] opt {'value_ints': (0, 2, 3)}
3: op ReduceMean shape [(3, 3, 3, 1), (3,)] opt {}
4: op Pow shape [(1, 3, 1, 1), ()] opt {}
5: op Pow shape [(3, 3, 3, 1), ()] opt {}
6: op ReduceMean shape [(3, 3, 3, 1), (3,)] opt {}
7: op Sub shape [(1, 3, 1, 1), (1, 3, 1, 1)] opt {}
8: op Sqrt shape [(1, 3, 1, 1)] opt {}
9: op Sub shape [(3, 3, 3, 1), (1, 3, 1, 1)] opt {}
10: op Add shape [(1, 3, 1, 1), ()] opt {}
11: op Div shape [(3, 3, 3, 1), (1, 3, 1, 1)] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['x']
0: op Neg shape [(3, 4, 5)] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['x']
0: op Neg shape [(2,)] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['input', 'target']
0: op NegativeLogLikelihoodLoss shape [(3, 5), (3,)] opt {'reduction': 'none'}
prepare <class '__main__.TinygradBackend'> CPU ['input', 'target']
0: op Constant shape [] opt {'value': <Tensor <LB HIP (1,) contig:True (<LoadOps.COPY: 3>, None)> on HIP with grad None>}
1: op Constant shape [] opt {'value': <Tensor <LB HIP (1,) contig:True (<LoadOps.COPY: 3>, None)> on HIP with grad None>}
2: op Constant shape [] opt {'value': <Tensor <LB HIP (1,) contig:True (<LoadOps.COPY: 3>, None)> on HIP with grad None>}
3: op Unsqueeze shape [(3,), (1,)] opt {}
4: op GatherElements shape [(3, 5), (3, 1)] opt {'axis': 1}
5: op Neg shape [(3, 1)] opt {}
6: op Slice shape [(3, 1), (1,), (1,), (1,)] opt {}
7: op Squeeze shape [(3, 1), (1,)] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['input', 'target']
0: op NegativeLogLikelihoodLoss shape [(3, 5, 2), (3, 2)] opt {'reduction': 'mean'}
prepare <class '__main__.TinygradBackend'> CPU ['input', 'target']
0: op Constant shape [] opt {'value': <Tensor <LB HIP (1,) contig:True (<LoadOps.COPY: 3>, None)> on HIP with grad None>}
1: op Constant shape [] opt {'value': <Tensor <LB HIP (1,) contig:True (<LoadOps.COPY: 3>, None)> on HIP with grad None>}
2: op Constant shape [] opt {'value': <Tensor <LB HIP (1,) contig:True (<LoadOps.COPY: 3>, None)> on HIP with grad None>}
3: op Unsqueeze shape [(3, 2), (1,)] opt {}
4: op GatherElements shape [(3, 5, 2), (3, 1, 2)] opt {'axis': 1}
5: op Neg shape [(3, 1, 2)] opt {}
6: op Slice shape [(3, 1, 2), (1,), (1,), (1,)] opt {}
7: op Squeeze shape [(3, 1, 2), (1,)] opt {}
8: op ReduceMean shape [(3, 2)] opt {'keepdims': 0}
prepare <class '__main__.TinygradBackend'> CPU ['input', 'target']
0: op NegativeLogLikelihoodLoss shape [(3, 5, 2), (3, 2)] opt {'ignore_index': 1, 'reduction': 'mean'}
prepare <class '__main__.TinygradBackend'> CPU ['input', 'target']
0: op Constant shape [] opt {'value': <Tensor <LB HIP (1,) contig:True (<LoadOps.COPY: 3>, None)> on HIP with grad None>}
1: op Constant shape [] opt {'value': <Tensor <LB HIP (1,) contig:True (<LoadOps.COPY: 3>, None)> on HIP with grad None>}
2: op Constant shape [] opt {'value': <Tensor <LB HIP (1,) contig:True (<LoadOps.COPY: 3>, None)> on HIP with grad None>}
3: op Unsqueeze shape [(3, 2), (1,)] opt {}
4: op Constant shape [] opt {'value': <Tensor <LB HIP (1,) contig:True (<LoadOps.COPY: 3>, None)> on HIP with grad None>}
5: op Sub shape [(3, 1, 2), (3, 1, 2)] opt {}
6: op Cast shape [(3, 1, 2)] opt {'to': 7}
7: op Equal shape [(3, 1, 2), (1,)] opt {}
8: op Where shape [(3, 1, 2), (3, 1, 2), (3, 1, 2)] opt {}
9: op GatherElements shape [(3, 5, 2), (3, 1, 2)] opt {'axis': 1}
10: op Constant shape [] opt {'value': <Tensor <LB HIP (1,) contig:True (<LoadOps.COPY: 3>, None)> on HIP with grad None>}
11: op Where shape [(3, 1, 2), (1,), (3, 1, 2)] opt {}
12: op Neg shape [(3, 1, 2)] opt {}
13: op Slice shape [(3, 1, 2), (1,), (1,), (1,)] opt {}
14: op Squeeze shape [(3, 1, 2), (1,)] opt {}
15: op Constant shape [] opt {'value': <Tensor <LB HIP (1,) contig:True (<LoadOps.COPY: 3>, None)> on HIP with grad None>}
16: op Where shape [(3, 2), (1,), (1,)] opt {}
17: op Squeeze shape [(3, 1, 2), (1,)] opt {}
18: op Mul shape [(3, 2), (3, 2)] opt {}
19: op ReduceSum shape [(3, 2)] opt {'keepdims': 0}
20: op ReduceSum shape [(3, 2)] opt {'keepdims': 0}
21: op Div shape [(), ()] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['input', 'target', 'weight']
0: op NegativeLogLikelihoodLoss shape [(3, 5, 6), (3, 6), (5,)] opt {'ignore_index': -1, 'reduction': 'mean'}
prepare <class '__main__.TinygradBackend'> CPU ['input', 'target', 'weight']
0: op Constant shape [] opt {'value': <Tensor <LB HIP (1,) contig:True (<LoadOps.COPY: 3>, None)> on HIP with grad None>}
1: op Constant shape [] opt {'value': <Tensor <LB HIP (1,) contig:True (<LoadOps.COPY: 3>, None)> on HIP with grad None>}
2: op Constant shape [] opt {'value': <Tensor <LB HIP (1,) contig:True (<LoadOps.COPY: 3>, None)> on HIP with grad None>}
3: op Unsqueeze shape [(3, 6), (1,)] opt {}
4: op Constant shape [] opt {'value': <Tensor <LB HIP (1,) contig:True (<LoadOps.COPY: 3>, None)> on HIP with grad None>}
5: op Sub shape [(3, 1, 6), (3, 1, 6)] opt {}
6: op Cast shape [(3, 1, 6)] opt {'to': 7}
7: op Equal shape [(3, 1, 6), (1,)] opt {}
8: op Where shape [(3, 1, 6), (3, 1, 6), (3, 1, 6)] opt {}
9: op GatherElements shape [(3, 5, 6), (3, 1, 6)] opt {'axis': 1}
10: op Constant shape [] opt {'value': <Tensor <LB HIP (1,) contig:True (<LoadOps.COPY: 3>, None)> on HIP with grad None>}
11: op Where shape [(3, 1, 6), (1,), (3, 1, 6)] opt {}
12: op Neg shape [(3, 1, 6)] opt {}
13: op Slice shape [(3, 1, 6), (1,), (1,), (1,)] opt {}
14: op Gather shape [(5,), (3, 1, 6)] opt {}
15: op Where shape [(3, 1, 6), (1,), (3, 1, 6)] opt {}
16: op Squeeze shape [(3, 1, 6), (1,)] opt {}
17: op Squeeze shape [(3, 1, 6), (1,)] opt {}
18: op Mul shape [(3, 6), (3, 6)] opt {}
19: op ReduceSum shape [(3, 6)] opt {'keepdims': 0}
20: op ReduceSum shape [(3, 6)] opt {'keepdims': 0}
21: op Div shape [(), ()] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['input', 'target', 'weight']
0: op NegativeLogLikelihoodLoss shape [(3, 5, 2), (3, 2), (5,)] opt {'reduction': 'mean'}
prepare <class '__main__.TinygradBackend'> CPU ['input', 'target', 'weight']
0: op Constant shape [] opt {'value': <Tensor <LB HIP (1,) contig:True (<LoadOps.COPY: 3>, None)> on HIP with grad None>}
1: op Constant shape [] opt {'value': <Tensor <LB HIP (1,) contig:True (<LoadOps.COPY: 3>, None)> on HIP with grad None>}
2: op Constant shape [] opt {'value': <Tensor <LB HIP (1,) contig:True (<LoadOps.COPY: 3>, None)> on HIP with grad None>}
3: op Unsqueeze shape [(3, 2), (1,)] opt {}
4: op GatherElements shape [(3, 5, 2), (3, 1, 2)] opt {'axis': 1}
5: op Neg shape [(3, 1, 2)] opt {}
6: op Slice shape [(3, 1, 2), (1,), (1,), (1,)] opt {}
7: op Gather shape [(5,), (3, 2)] opt {}
8: op Squeeze shape [(3, 1, 2), (1,)] opt {}
9: op Mul shape [(3, 2), (3, 2)] opt {}
10: op ReduceSum shape [(3, 2)] opt {'keepdims': 0}
11: op ReduceSum shape [(3, 2)] opt {'keepdims': 0}
12: op Div shape [(), ()] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['input', 'target', 'weight']
0: op NegativeLogLikelihoodLoss shape [(3, 5, 2), (3, 2), (5,)] opt {'ignore_index': 1, 'reduction': 'mean'}
prepare <class '__main__.TinygradBackend'> CPU ['input', 'target', 'weight']
0: op Constant shape [] opt {'value': <Tensor <LB HIP (1,) contig:True (<LoadOps.COPY: 3>, None)> on HIP with grad None>}
1: op Constant shape [] opt {'value': <Tensor <LB HIP (1,) contig:True (<LoadOps.COPY: 3>, None)> on HIP with grad None>}
2: op Constant shape [] opt {'value': <Tensor <LB HIP (1,) contig:True (<LoadOps.COPY: 3>, None)> on HIP with grad None>}
3: op Unsqueeze shape [(3, 2), (1,)] opt {}
4: op Constant shape [] opt {'value': <Tensor <LB HIP (1,) contig:True (<LoadOps.COPY: 3>, None)> on HIP with grad None>}
5: op Sub shape [(3, 1, 2), (3, 1, 2)] opt {}
6: op Cast shape [(3, 1, 2)] opt {'to': 7}
7: op Equal shape [(3, 1, 2), (1,)] opt {}
8: op Where shape [(3, 1, 2), (3, 1, 2), (3, 1, 2)] opt {}
9: op GatherElements shape [(3, 5, 2), (3, 1, 2)] opt {'axis': 1}
10: op Constant shape [] opt {'value': <Tensor <LB HIP (1,) contig:True (<LoadOps.COPY: 3>, None)> on HIP with grad None>}
11: op Where shape [(3, 1, 2), (1,), (3, 1, 2)] opt {}
.s.s.s.s.s.s.s.s.s.s.s.s.s.s.s12: op Neg shape [(3, 1, 2)] opt {}
13: op Slice shape [(3, 1, 2), (1,), (1,), (1,)] opt {}
14: op Gather shape [(5,), (3, 1, 2)] opt {}
15: op Where shape [(3, 1, 2), (1,), (3, 1, 2)] opt {}
16: op Squeeze shape [(3, 1, 2), (1,)] opt {}
17: op Squeeze shape [(3, 1, 2), (1,)] opt {}
18: op Mul shape [(3, 2), (3, 2)] opt {}
19: op ReduceSum shape [(3, 2)] opt {'keepdims': 0}
20: op ReduceSum shape [(3, 2)] opt {'keepdims': 0}
21: op Div shape [(), ()] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['input', 'target']
0: op NegativeLogLikelihoodLoss shape [(3, 5, 6, 6), (3, 6, 6)] opt {'reduction': 'none'}
prepare <class '__main__.TinygradBackend'> CPU ['input', 'target']
0: op Constant shape [] opt {'value': <Tensor <LB HIP (1,) contig:True (<LoadOps.COPY: 3>, None)> on HIP with grad None>}
1: op Constant shape [] opt {'value': <Tensor <LB HIP (1,) contig:True (<LoadOps.COPY: 3>, None)> on HIP with grad None>}
2: op Constant shape [] opt {'value': <Tensor <LB HIP (1,) contig:True (<LoadOps.COPY: 3>, None)> on HIP with grad None>}
3: op Unsqueeze shape [(3, 6, 6), (1,)] opt {}
4: op GatherElements shape [(3, 5, 6, 6), (3, 1, 6, 6)] opt {'axis': 1}
5: op Neg shape [(3, 1, 6, 6)] opt {}
6: op Slice shape [(3, 1, 6, 6), (1,), (1,), (1,)] opt {}
7: op Squeeze shape [(3, 1, 6, 6), (1,)] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['input', 'target']
0: op NegativeLogLikelihoodLoss shape [(3, 5, 6, 6), (3, 6, 6)] opt {'ignore_index': 1, 'reduction': 'mean'}
prepare <class '__main__.TinygradBackend'> CPU ['input', 'target']
0: op Constant shape [] opt {'value': <Tensor <LB HIP (1,) contig:True (<LoadOps.COPY: 3>, None)> on HIP with grad None>}
1: op Constant shape [] opt {'value': <Tensor <LB HIP (1,) contig:True (<LoadOps.COPY: 3>, None)> on HIP with grad None>}
2: op Constant shape [] opt {'value': <Tensor <LB HIP (1,) contig:True (<LoadOps.COPY: 3>, None)> on HIP with grad None>}
3: op Unsqueeze shape [(3, 6, 6), (1,)] opt {}
4: op Constant shape [] opt {'value': <Tensor <LB HIP (1,) contig:True (<LoadOps.COPY: 3>, None)> on HIP with grad None>}
5: op Sub shape [(3, 1, 6, 6), (3, 1, 6, 6)] opt {}
6: op Cast shape [(3, 1, 6, 6)] opt {'to': 7}
7: op Equal shape [(3, 1, 6, 6), (1,)] opt {}
8: op Where shape [(3, 1, 6, 6), (3, 1, 6, 6), (3, 1, 6, 6)] opt {}
9: op GatherElements shape [(3, 5, 6, 6), (3, 1, 6, 6)] opt {'axis': 1}
10: op Constant shape [] opt {'value': <Tensor <LB HIP (1,) contig:True (<LoadOps.COPY: 3>, None)> on HIP with grad None>}
11: op Where shape [(3, 1, 6, 6), (1,), (3, 1, 6, 6)] opt {}
12: op Neg shape [(3, 1, 6, 6)] opt {}
13: op Slice shape [(3, 1, 6, 6), (1,), (1,), (1,)] opt {}
14: op Squeeze shape [(3, 1, 6, 6), (1,)] opt {}
15: op Constant shape [] opt {'value': <Tensor <LB HIP (1,) contig:True (<LoadOps.COPY: 3>, None)> on HIP with grad None>}
16: op Where shape [(3, 6, 6), (1,), (1,)] opt {}
17: op Squeeze shape [(3, 1, 6, 6), (1,)] opt {}
18: op Mul shape [(3, 6, 6), (3, 6, 6)] opt {}
19: op ReduceSum shape [(3, 6, 6)] opt {'keepdims': 0}
20: op ReduceSum shape [(3, 6, 6)] opt {'keepdims': 0}
21: op Div shape [(), ()] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['input', 'target']
0: op NegativeLogLikelihoodLoss shape [(3, 5, 6, 6), (3, 6, 6)] opt {'reduction': 'mean'}
prepare <class '__main__.TinygradBackend'> CPU ['input', 'target']
0: op Constant shape [] opt {'value': <Tensor <LB HIP (1,) contig:True (<LoadOps.COPY: 3>, None)> on HIP with grad None>}
1: op Constant shape [] opt {'value': <Tensor <LB HIP (1,) contig:True (<LoadOps.COPY: 3>, None)> on HIP with grad None>}
2: op Constant shape [] opt {'value': <Tensor <LB HIP (1,) contig:True (<LoadOps.COPY: 3>, None)> on HIP with grad None>}
3: op Unsqueeze shape [(3, 6, 6), (1,)] opt {}
4: op GatherElements shape [(3, 5, 6, 6), (3, 1, 6, 6)] opt {'axis': 1}
5: op Neg shape [(3, 1, 6, 6)] opt {}
6: op Slice shape [(3, 1, 6, 6), (1,), (1,), (1,)] opt {}
7: op Squeeze shape [(3, 1, 6, 6), (1,)] opt {}
8: op ReduceMean shape [(3, 6, 6)] opt {'keepdims': 0}
prepare <class '__main__.TinygradBackend'> CPU ['input', 'target']
0: op NegativeLogLikelihoodLoss shape [(3, 5, 6, 6), (3, 6, 6)] opt {'reduction': 'sum'}
prepare <class '__main__.TinygradBackend'> CPU ['input', 'target']
0: op Constant shape [] opt {'value': <Tensor <LB HIP (1,) contig:True (<LoadOps.COPY: 3>, None)> on HIP with grad None>}
1: op Constant shape [] opt {'value': <Tensor <LB HIP (1,) contig:True (<LoadOps.COPY: 3>, None)> on HIP with grad None>}
2: op Constant shape [] opt {'value': <Tensor <LB HIP (1,) contig:True (<LoadOps.COPY: 3>, None)> on HIP with grad None>}
3: op Unsqueeze shape [(3, 6, 6), (1,)] opt {}
4: op GatherElements shape [(3, 5, 6, 6), (3, 1, 6, 6)] opt {'axis': 1}
5: op Neg shape [(3, 1, 6, 6)] opt {}
6: op Slice shape [(3, 1, 6, 6), (1,), (1,), (1,)] opt {}
7: op Squeeze shape [(3, 1, 6, 6), (1,)] opt {}
8: op ReduceSum shape [(3, 6, 6)] opt {'keepdims': 0}
prepare <class '__main__.TinygradBackend'> CPU ['input', 'target', 'weight']
0: op NegativeLogLikelihoodLoss shape [(3, 5, 6, 6), (3, 6, 6), (5,)] opt {'reduction': 'none'}
prepare <class '__main__.TinygradBackend'> CPU ['input', 'target', 'weight']
0: op Constant shape [] opt {'value': <Tensor <LB HIP (1,) contig:True (<LoadOps.COPY: 3>, None)> on HIP with grad None>}
1: op Constant shape [] opt {'value': <Tensor <LB HIP (1,) contig:True (<LoadOps.COPY: 3>, None)> on HIP with grad None>}
2: op Constant shape [] opt {'value': <Tensor <LB HIP (1,) contig:True (<LoadOps.COPY: 3>, None)> on HIP with grad None>}
3: op Unsqueeze shape [(3, 6, 6), (1,)] opt {}
4: op GatherElements shape [(3, 5, 6, 6), (3, 1, 6, 6)] opt {'axis': 1}
5: op Neg shape [(3, 1, 6, 6)] opt {}
6: op Slice shape [(3, 1, 6, 6), (1,), (1,), (1,)] opt {}
7: op Gather shape [(5,), (3, 6, 6)] opt {}
8: op Squeeze shape [(3, 1, 6, 6), (1,)] opt {}
9: op Mul shape [(3, 6, 6), (3, 6, 6)] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['input', 'target', 'weight']
0: op NegativeLogLikelihoodLoss shape [(3, 5, 6, 6), (3, 6, 6), (5,)] opt {'reduction': 'mean'}
prepare <class '__main__.TinygradBackend'> CPU ['input', 'target', 'weight']
0: op Constant shape [] opt {'value': <Tensor <LB HIP (1,) contig:True (<LoadOps.COPY: 3>, None)> on HIP with grad None>}
1: op Constant shape [] opt {'value': <Tensor <LB HIP (1,) contig:True (<LoadOps.COPY: 3>, None)> on HIP with grad None>}
2: op Constant shape [] opt {'value': <Tensor <LB HIP (1,) contig:True (<LoadOps.COPY: 3>, None)> on HIP with grad None>}
3: op Unsqueeze shape [(3, 6, 6), (1,)] opt {}
4: op GatherElements shape [(3, 5, 6, 6), (3, 1, 6, 6)] opt {'axis': 1}
5: op Neg shape [(3, 1, 6, 6)] opt {}
6: op Slice shape [(3, 1, 6, 6), (1,), (1,), (1,)] opt {}
7: op Gather shape [(5,), (3, 6, 6)] opt {}
8: op Squeeze shape [(3, 1, 6, 6), (1,)] opt {}
9: op Mul shape [(3, 6, 6), (3, 6, 6)] opt {}
10: op ReduceSum shape [(3, 6, 6)] opt {'keepdims': 0}
11: op ReduceSum shape [(3, 6, 6)] opt {'keepdims': 0}
12: op Div shape [(), ()] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['input', 'target', 'weight']
0: op NegativeLogLikelihoodLoss shape [(3, 5, 6, 6), (3, 6, 6), (5,)] opt {'reduction': 'sum'}
prepare <class '__main__.TinygradBackend'> CPU ['input', 'target', 'weight']
0: op Constant shape [] opt {'value': <Tensor <LB HIP (1,) contig:True (<LoadOps.COPY: 3>, None)> on HIP with grad None>}
1: op Constant shape [] opt {'value': <Tensor <LB HIP (1,) contig:True (<LoadOps.COPY: 3>, None)> on HIP with grad None>}
2: op Constant shape [] opt {'value': <Tensor <LB HIP (1,) contig:True (<LoadOps.COPY: 3>, None)> on HIP with grad None>}
3: op Unsqueeze shape [(3, 6, 6), (1,)] opt {}
4: op GatherElements shape [(3, 5, 6, 6), (3, 1, 6, 6)] opt {'axis': 1}
5: op Neg shape [(3, 1, 6, 6)] opt {}
6: op Slice shape [(3, 1, 6, 6), (1,), (1,), (1,)] opt {}
7: op Gather shape [(5,), (3, 6, 6)] opt {}
8: op Squeeze shape [(3, 1, 6, 6), (1,)] opt {}
9: op Mul shape [(3, 6, 6), (3, 6, 6)] opt {}
10: op ReduceSum shape [(3, 6, 6)] opt {'keepdims': 0}
prepare <class '__main__.TinygradBackend'> CPU ['input', 'target', 'weight']
.s.s.s.s.s.s.s.s.s.sssssssssssssssssssss.s.s.s.s.s.s.s.s.s0: op NegativeLogLikelihoodLoss shape [(3, 5, 6, 6), (3, 6, 6), (5,)] opt {'ignore_index': 0, 'reduction': 'sum'}
prepare <class '__main__.TinygradBackend'> CPU ['input', 'target', 'weight']
0: op Constant shape [] opt {'value': <Tensor <LB HIP (1,) contig:True (<LoadOps.COPY: 3>, None)> on HIP with grad None>}
1: op Constant shape [] opt {'value': <Tensor <LB HIP (1,) contig:True (<LoadOps.COPY: 3>, None)> on HIP with grad None>}
2: op Constant shape [] opt {'value': <Tensor <LB HIP (1,) contig:True (<LoadOps.COPY: 3>, None)> on HIP with grad None>}
3: op Unsqueeze shape [(3, 6, 6), (1,)] opt {}
4: op Constant shape [] opt {'value': <Tensor <LB HIP (1,) contig:True (<LoadOps.COPY: 3>, None)> on HIP with grad None>}
5: op Sub shape [(3, 1, 6, 6), (3, 1, 6, 6)] opt {}
6: op Cast shape [(3, 1, 6, 6)] opt {'to': 7}
7: op Equal shape [(3, 1, 6, 6), (1,)] opt {}
8: op Where shape [(3, 1, 6, 6), (3, 1, 6, 6), (3, 1, 6, 6)] opt {}
9: op GatherElements shape [(3, 5, 6, 6), (3, 1, 6, 6)] opt {'axis': 1}
10: op Constant shape [] opt {'value': <Tensor <LB HIP (1,) contig:True (<LoadOps.COPY: 3>, None)> on HIP with grad None>}
11: op Where shape [(3, 1, 6, 6), (1,), (3, 1, 6, 6)] opt {}
12: op Neg shape [(3, 1, 6, 6)] opt {}
13: op Slice shape [(3, 1, 6, 6), (1,), (1,), (1,)] opt {}
14: op Gather shape [(5,), (3, 1, 6, 6)] opt {}
15: op Where shape [(3, 1, 6, 6), (1,), (3, 1, 6, 6)] opt {}
16: op Squeeze shape [(3, 1, 6, 6), (1,)] opt {}
17: op Squeeze shape [(3, 1, 6, 6), (1,)] opt {}
18: op Mul shape [(3, 6, 6), (3, 6, 6)] opt {}
19: op ReduceSum shape [(3, 6, 6)] opt {'keepdims': 0}
prepare <class '__main__.TinygradBackend'> CPU ['input', 'target']
0: op NegativeLogLikelihoodLoss shape [(3, 5, 6, 6, 5), (3, 6, 6, 5)] opt {'ignore_index': -5, 'reduction': 'none'}
prepare <class '__main__.TinygradBackend'> CPU ['input', 'target']
0: op Constant shape [] opt {'value': <Tensor <LB HIP (1,) contig:True (<LoadOps.COPY: 3>, None)> on HIP with grad None>}
1: op Constant shape [] opt {'value': <Tensor <LB HIP (1,) contig:True (<LoadOps.COPY: 3>, None)> on HIP with grad None>}
2: op Constant shape [] opt {'value': <Tensor <LB HIP (1,) contig:True (<LoadOps.COPY: 3>, None)> on HIP with grad None>}
3: op Unsqueeze shape [(3, 6, 6, 5), (1,)] opt {}
4: op Constant shape [] opt {'value': <Tensor <LB HIP (1,) contig:True (<LoadOps.COPY: 3>, None)> on HIP with grad None>}
5: op Sub shape [(3, 1, 6, 6, 5), (3, 1, 6, 6, 5)] opt {}
6: op Cast shape [(3, 1, 6, 6, 5)] opt {'to': 7}
7: op Equal shape [(3, 1, 6, 6, 5), (1,)] opt {}
8: op Where shape [(3, 1, 6, 6, 5), (3, 1, 6, 6, 5), (3, 1, 6, 6, 5)] opt {}
9: op GatherElements shape [(3, 5, 6, 6, 5), (3, 1, 6, 6, 5)] opt {'axis': 1}
10: op Constant shape [] opt {'value': <Tensor <LB HIP (1,) contig:True (<LoadOps.COPY: 3>, None)> on HIP with grad None>}
11: op Where shape [(3, 1, 6, 6, 5), (1,), (3, 1, 6, 6, 5)] opt {}
12: op Neg shape [(3, 1, 6, 6, 5)] opt {}
13: op Slice shape [(3, 1, 6, 6, 5), (1,), (1,), (1,)] opt {}
14: op Squeeze shape [(3, 1, 6, 6, 5), (1,)] opt {}
15: op Constant shape [] opt {'value': <Tensor <LB HIP (1,) contig:True (<LoadOps.COPY: 3>, None)> on HIP with grad None>}
16: op Where shape [(3, 6, 6, 5), (1,), (1,)] opt {}
17: op Squeeze shape [(3, 1, 6, 6, 5), (1,)] opt {}
18: op Mul shape [(3, 6, 6, 5), (3, 6, 6, 5)] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['input', 'target', 'weight']
0: op NegativeLogLikelihoodLoss shape [(3, 5), (3,), (5,)] opt {'ignore_index': 10, 'reduction': 'sum'}
prepare <class '__main__.TinygradBackend'> CPU ['input', 'target', 'weight']
0: op Constant shape [] opt {'value': <Tensor <LB HIP (1,) contig:True (<LoadOps.COPY: 3>, None)> on HIP with grad None>}
1: op Constant shape [] opt {'value': <Tensor <LB HIP (1,) contig:True (<LoadOps.COPY: 3>, None)> on HIP with grad None>}
2: op Constant shape [] opt {'value': <Tensor <LB HIP (1,) contig:True (<LoadOps.COPY: 3>, None)> on HIP with grad None>}
3: op Unsqueeze shape [(3,), (1,)] opt {}
4: op Constant shape [] opt {'value': <Tensor <LB HIP (1,) contig:True (<LoadOps.COPY: 3>, None)> on HIP with grad None>}
5: op Sub shape [(3, 1), (3, 1)] opt {}
6: op Cast shape [(3, 1)] opt {'to': 7}
7: op Equal shape [(3, 1), (1,)] opt {}
8: op Where shape [(3, 1), (3, 1), (3, 1)] opt {}
9: op GatherElements shape [(3, 5), (3, 1)] opt {'axis': 1}
10: op Constant shape [] opt {'value': <Tensor <LB HIP (1,) contig:True (<LoadOps.COPY: 3>, None)> on HIP with grad None>}
11: op Where shape [(3, 1), (1,), (3, 1)] opt {}
12: op Neg shape [(3, 1)] opt {}
13: op Slice shape [(3, 1), (1,), (1,), (1,)] opt {}
14: op Gather shape [(5,), (3, 1)] opt {}
15: op Where shape [(3, 1), (1,), (3, 1)] opt {}
16: op Squeeze shape [(3, 1), (1,)] opt {}
17: op Squeeze shape [(3, 1), (1,)] opt {}
18: op Mul shape [(3,), (3,)] opt {}
19: op ReduceSum shape [(3,)] opt {'keepdims': 0}
prepare <class '__main__.TinygradBackend'> CPU ['input', 'target', 'weight']
0: op NegativeLogLikelihoodLoss shape [(3, 5, 6, 6, 5, 3, 4), (3, 6, 6, 5, 3, 4), (5,)] opt {'reduction': 'mean'}
prepare <class '__main__.TinygradBackend'> CPU ['input', 'target', 'weight']
0: op Constant shape [] opt {'value': <Tensor <LB HIP (1,) contig:True (<LoadOps.COPY: 3>, None)> on HIP with grad None>}
1: op Constant shape [] opt {'value': <Tensor <LB HIP (1,) contig:True (<LoadOps.COPY: 3>, None)> on HIP with grad None>}
2: op Constant shape [] opt {'value': <Tensor <LB HIP (1,) contig:True (<LoadOps.COPY: 3>, None)> on HIP with grad None>}
3: op Unsqueeze shape [(3, 6, 6, 5, 3, 4), (1,)] opt {}
4: op GatherElements shape [(3, 5, 6, 6, 5, 3, 4), (3, 1, 6, 6, 5, 3, 4)] opt {'axis': 1}
5: op Neg shape [(3, 1, 6, 6, 5, 3, 4)] opt {}
6: op Slice shape [(3, 1, 6, 6, 5, 3, 4), (1,), (1,), (1,)] opt {}
7: op Gather shape [(5,), (3, 6, 6, 5, 3, 4)] opt {}
8: op Squeeze shape [(3, 1, 6, 6, 5, 3, 4), (1,)] opt {}
9: op Mul shape [(3, 6, 6, 5, 3, 4), (3, 6, 6, 5, 3, 4)] opt {}
10: op ReduceSum shape [(3, 6, 6, 5, 3, 4)] opt {'keepdims': 0}
11: op ReduceSum shape [(3, 6, 6, 5, 3, 4)] opt {'keepdims': 0}
12: op Div shape [(), ()] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['input', 'target']
0: op NegativeLogLikelihoodLoss shape [(3, 5, 6, 6, 5, 3, 4), (3, 6, 6, 5, 3, 4)] opt {'reduction': 'none'}
prepare <class '__main__.TinygradBackend'> CPU ['input', 'target']
0: op Constant shape [] opt {'value': <Tensor <LB HIP (1,) contig:True (<LoadOps.COPY: 3>, None)> on HIP with grad None>}
1: op Constant shape [] opt {'value': <Tensor <LB HIP (1,) contig:True (<LoadOps.COPY: 3>, None)> on HIP with grad None>}
2: op Constant shape [] opt {'value': <Tensor <LB HIP (1,) contig:True (<LoadOps.COPY: 3>, None)> on HIP with grad None>}
3: op Unsqueeze shape [(3, 6, 6, 5, 3, 4), (1,)] opt {}
4: op GatherElements shape [(3, 5, 6, 6, 5, 3, 4), (3, 1, 6, 6, 5, 3, 4)] opt {'axis': 1}
5: op Neg shape [(3, 1, 6, 6, 5, 3, 4)] opt {}
6: op Slice shape [(3, 1, 6, 6, 5, 3, 4), (1,), (1,), (1,)] opt {}
7: op Squeeze shape [(3, 1, 6, 6, 5, 3, 4), (1,)] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['x']
0: op Not shape [(3, 4)] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['x']
0: op Not shape [(3, 4, 5)] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['x']
0: op Not shape [(3, 4, 5, 6)] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['indices', 'depth', 'values']
0: op OneHot shape [(3,), (), (2,)] opt {'axis': 1}
prepare <class '__main__.TinygradBackend'> CPU ['indices', 'depth', 'values']
0: op OneHot shape [(2, 2), (), (2,)] opt {'axis': 1}
prepare <class '__main__.TinygradBackend'> CPU ['indices', 'depth', 'values']
0: op OneHot shape [(2, 2), (), (2,)] opt {'axis': -2}
prepare <class '__main__.TinygradBackend'> CPU ['indices', 'depth', 'values']
0: op OneHot shape [(3,), (), (2,)] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['optional_input']
0: op OptionalGetElement shape [[<Tensor <LB HIP (4,) contig:True (<LoadOps.COPY: 3>, None)> on HIP with grad None>]] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['optional_input']
0: op OptionalGetElement shape [(4,)] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['optional_input']
.s.s.s.s.s.s.s.s.s.s.s.s.s.s.s.s.s.s.s.s.s.s.s.s.sssssssss.s.s.s.sssssssssssssss.sss.sss.s.s.s.s.s.s.s.s.s.s.s.s.s.s.s.s.s.s.s.s.s.s.s.s.s.s.s.s0: op OptionalGetElement shape [[<Tensor <LB HIP (4,) contig:True (<LoadOps.COPY: 3>, None)> on HIP with grad None>]] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['optional_input']
0: op OptionalGetElement shape [(4,)] opt {}
prepare <class '__main__.TinygradBackend'> CPU []
0: op OptionalHasElement shape [None] opt {}
prepare <class '__main__.TinygradBackend'> CPU []
0: op OptionalHasElement shape [None] opt {}
prepare <class '__main__.TinygradBackend'> CPU []
0: op OptionalHasElement shape [] opt {}
prepare <class '__main__.TinygradBackend'> CPU []
0: op OptionalHasElement shape [] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['optional_input']
0: op OptionalHasElement shape [(0,)] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['optional_input']
0: op OptionalHasElement shape [(4,)] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['optional_input']
0: op OptionalHasElement shape [(4,)] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['x', 'y']
0: op Or shape [(3, 4), (3, 4)] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['x', 'y']
0: op Or shape [(3, 4, 5), (3, 4, 5)] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['x', 'y']
0: op Or shape [(3, 4, 5, 6), (3, 4, 5, 6)] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['x', 'y']
0: op Or shape [(3, 4, 5), (5,)] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['x', 'y']
0: op Or shape [(3, 4, 5), (4, 5)] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['x', 'y']
0: op Or shape [(3, 4, 5, 6), (5, 6)] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['x', 'y']
0: op Or shape [(3, 4, 5, 6), (4, 5, 6)] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['x', 'y']
0: op Or shape [(1, 4, 1, 6), (3, 1, 5, 6)] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['x', 'y']
0: op Pow shape [(2, 3), (3,)] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['x', 'y']
0: op Pow shape [(3,), ()] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['x', 'y']
0: op Pow shape [(3, 4, 5), (3, 4, 5)] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['x', 'y']
0: op Pow shape [(3,), (3,)] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['x', 'y']
0: op Pow shape [(3,), (3,)] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['x', 'y']
0: op Pow shape [(3,), (3,)] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['x', 'y']
0: op Pow shape [(3,), (3,)] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['x', 'y']
0: op Pow shape [(3,), (3,)] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['x', 'slope']
0: op PRelu shape [(3, 4, 5), (5,)] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['x', 'slope']
0: op Constant shape [] opt {'value': <Tensor <LB HIP () contig:True (<LoadOps.CONST: 2>, None)> on HIP with grad None>}
1: op CastLike shape [(), (3, 4, 5)] opt {}
2: op Less shape [(3, 4, 5), ()] opt {}
3: op Mul shape [(5,), (3, 4, 5)] opt {}
4: op Where shape [(3, 4, 5), (3, 4, 5), (3, 4, 5)] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['x', 'slope']
0: op PRelu shape [(3, 4, 5), (3, 4, 5)] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['x', 'slope']
0: op Constant shape [] opt {'value': <Tensor <LB HIP () contig:True (<LoadOps.CONST: 2>, None)> on HIP with grad None>}
1: op CastLike shape [(), (3, 4, 5)] opt {}
2: op Less shape [(3, 4, 5), ()] opt {}
3: op Mul shape [(3, 4, 5), (3, 4, 5)] opt {}
4: op Where shape [(3, 4, 5), (3, 4, 5), (3, 4, 5)] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['start', 'limit', 'delta']
0: op Range shape [(), (), ()] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['start', 'limit', 'delta']
0: op Range shape [(), (), ()] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['x']
0: op Reciprocal shape [(3, 4, 5)] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['x']
0: op Reciprocal shape [(2,)] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['data', 'axes']
0: op ReduceL1 shape [(3, 2, 2), (0,)] opt {'keepdims': 1}
prepare <class '__main__.TinygradBackend'> CPU ['data', 'axes']
0: op Abs shape [(3, 2, 2)] opt {}
1: op ReduceSum shape [(3, 2, 2), (0,)] opt {'keepdims': 1}
prepare <class '__main__.TinygradBackend'> CPU ['data', 'axes']
0: op ReduceL1 shape [(3, 2, 2), (0,)] opt {'keepdims': 1}
prepare <class '__main__.TinygradBackend'> CPU ['data', 'axes']
0: op Abs shape [(3, 2, 2)] opt {}
1: op ReduceSum shape [(3, 2, 2), (0,)] opt {'keepdims': 1}
prepare <class '__main__.TinygradBackend'> CPU ['data', 'axes']
0: op ReduceL1 shape [(3, 2, 2), (1,)] opt {'keepdims': 0}
prepare <class '__main__.TinygradBackend'> CPU ['data', 'axes']
0: op Abs shape [(3, 2, 2)] opt {}
1: op ReduceSum shape [(3, 2, 2), (1,)] opt {'keepdims': 0}
prepare <class '__main__.TinygradBackend'> CPU ['data', 'axes']
0: op ReduceL1 shape [(3, 2, 2), (1,)] opt {'keepdims': 0}
prepare <class '__main__.TinygradBackend'> CPU ['data', 'axes']
0: op Abs shape [(3, 2, 2)] opt {}
1: op ReduceSum shape [(3, 2, 2), (1,)] opt {'keepdims': 0}
prepare <class '__main__.TinygradBackend'> CPU ['data', 'axes']
0: op ReduceL1 shape [(2, 0, 4), (1,)] opt {'keepdims': 1}
prepare <class '__main__.TinygradBackend'> CPU ['data', 'axes']
0: op Abs shape [(2, 0, 4)] opt {}
1: op ReduceSum shape [(2, 0, 4), (1,)] opt {'keepdims': 1}
prepare <class '__main__.TinygradBackend'> CPU ['data', 'axes']
0: op ReduceL1 shape [(3, 2, 2), (1,)] opt {'keepdims': 1}
prepare <class '__main__.TinygradBackend'> CPU ['data', 'axes']
0: op Abs shape [(3, 2, 2)] opt {}
1: op ReduceSum shape [(3, 2, 2), (1,)] opt {'keepdims': 1}
prepare <class '__main__.TinygradBackend'> CPU ['data', 'axes']
0: op ReduceL1 shape [(3, 2, 2), (1,)] opt {'keepdims': 1}
prepare <class '__main__.TinygradBackend'> CPU ['data', 'axes']
0: op Abs shape [(3, 2, 2)] opt {}
1: op ReduceSum shape [(3, 2, 2), (1,)] opt {'keepdims': 1}
prepare <class '__main__.TinygradBackend'> CPU ['data', 'axes']
0: op ReduceL1 shape [(3, 2, 2), (1,)] opt {'keepdims': 1}
prepare <class '__main__.TinygradBackend'> CPU ['data', 'axes']
0: op Abs shape [(3, 2, 2)] opt {}
1: op ReduceSum shape [(3, 2, 2), (1,)] opt {'keepdims': 1}
prepare <class '__main__.TinygradBackend'> CPU ['data', 'axes']
0: op ReduceL1 shape [(3, 2, 2), (1,)] opt {'keepdims': 1}
prepare <class '__main__.TinygradBackend'> CPU ['data', 'axes']
0: op Abs shape [(3, 2, 2)] opt {}
1: op ReduceSum shape [(3, 2, 2), (1,)] opt {'keepdims': 1}
prepare <class '__main__.TinygradBackend'> CPU ['data', 'axes']
0: op ReduceL2 shape [(3, 2, 2), (0,)] opt {'keepdims': 1}
prepare <class '__main__.TinygradBackend'> CPU ['data', 'axes']
0: op Mul shape [(3, 2, 2), (3, 2, 2)] opt {}
1: op ReduceSum shape [(3, 2, 2), (0,)] opt {'keepdims': 1}
2: op Cast shape [(1, 1, 1)] opt {'to': 1}
3: op Sqrt shape [(1, 1, 1)] opt {}
4: op CastLike shape [(1, 1, 1), (3, 2, 2)] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['data', 'axes']
0: op ReduceL2 shape [(3, 2, 2), (0,)] opt {'keepdims': 1}
prepare <class '__main__.TinygradBackend'> CPU ['data', 'axes']
0: op Mul shape [(3, 2, 2), (3, 2, 2)] opt {}
1: op ReduceSum shape [(3, 2, 2), (0,)] opt {'keepdims': 1}
2: op Cast shape [(1, 1, 1)] opt {'to': 1}
3: op Sqrt shape [(1, 1, 1)] opt {}
4: op CastLike shape [(1, 1, 1), (3, 2, 2)] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['data', 'axes']
0: op ReduceL2 shape [(3, 2, 2), (1,)] opt {'keepdims': 0}
prepare <class '__main__.TinygradBackend'> CPU ['data', 'axes']
0: op Mul shape [(3, 2, 2), (3, 2, 2)] opt {}
1: op ReduceSum shape [(3, 2, 2), (1,)] opt {'keepdims': 0}
2: op Cast shape [(3, 2)] opt {'to': 1}
3: op Sqrt shape [(3, 2)] opt {}
4: op CastLike shape [(3, 2), (3, 2, 2)] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['data', 'axes']
0: op ReduceL2 shape [(3, 2, 2), (1,)] opt {'keepdims': 0}
prepare <class '__main__.TinygradBackend'> CPU ['data', 'axes']
0: op Mul shape [(3, 2, 2), (3, 2, 2)] opt {}
1: op ReduceSum shape [(3, 2, 2), (1,)] opt {'keepdims': 0}
2: op Cast shape [(3, 2)] opt {'to': 1}
3: op Sqrt shape [(3, 2)] opt {}
4: op CastLike shape [(3, 2), (3, 2, 2)] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['data', 'axes']
.s.s.s.s.s.s.s.s.s.s.s.s.s.s.s.s.s.s.s.s.s.s.s.s.s.s.s.s.s.s.s.s.s.s.s.s.s.s.s.s.s.s.s.s.s.s0: op ReduceL2 shape [(2, 0, 4), (1,)] opt {'keepdims': 1}
prepare <class '__main__.TinygradBackend'> CPU ['data', 'axes']
0: op Mul shape [(2, 0, 4), (2, 0, 4)] opt {}
1: op ReduceSum shape [(2, 0, 4), (1,)] opt {'keepdims': 1}
2: op Cast shape [(2, 1, 4)] opt {'to': 1}
3: op Sqrt shape [(2, 1, 4)] opt {}
4: op CastLike shape [(2, 1, 4), (2, 0, 4)] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['data', 'axes']
0: op ReduceL2 shape [(3, 2, 2), (1,)] opt {'keepdims': 1}
prepare <class '__main__.TinygradBackend'> CPU ['data', 'axes']
0: op Mul shape [(3, 2, 2), (3, 2, 2)] opt {}
1: op ReduceSum shape [(3, 2, 2), (1,)] opt {'keepdims': 1}
2: op Cast shape [(3, 2, 1)] opt {'to': 1}
3: op Sqrt shape [(3, 2, 1)] opt {}
4: op CastLike shape [(3, 2, 1), (3, 2, 2)] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['data', 'axes']
0: op ReduceL2 shape [(3, 2, 2), (1,)] opt {'keepdims': 1}
prepare <class '__main__.TinygradBackend'> CPU ['data', 'axes']
0: op Mul shape [(3, 2, 2), (3, 2, 2)] opt {}
1: op ReduceSum shape [(3, 2, 2), (1,)] opt {'keepdims': 1}
2: op Cast shape [(3, 2, 1)] opt {'to': 1}
3: op Sqrt shape [(3, 2, 1)] opt {}
4: op CastLike shape [(3, 2, 1), (3, 2, 2)] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['data', 'axes']
0: op ReduceL2 shape [(3, 2, 2), (1,)] opt {'keepdims': 1}
prepare <class '__main__.TinygradBackend'> CPU ['data', 'axes']
0: op Mul shape [(3, 2, 2), (3, 2, 2)] opt {}
1: op ReduceSum shape [(3, 2, 2), (1,)] opt {'keepdims': 1}
2: op Cast shape [(3, 2, 1)] opt {'to': 1}
3: op Sqrt shape [(3, 2, 1)] opt {}
4: op CastLike shape [(3, 2, 1), (3, 2, 2)] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['data', 'axes']
0: op ReduceL2 shape [(3, 2, 2), (1,)] opt {'keepdims': 1}
prepare <class '__main__.TinygradBackend'> CPU ['data', 'axes']
0: op Mul shape [(3, 2, 2), (3, 2, 2)] opt {}
1: op ReduceSum shape [(3, 2, 2), (1,)] opt {'keepdims': 1}
2: op Cast shape [(3, 2, 1)] opt {'to': 1}
3: op Sqrt shape [(3, 2, 1)] opt {}
4: op CastLike shape [(3, 2, 1), (3, 2, 2)] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['data', 'axes']
0: op ReduceLogSum shape [(3, 4, 5), (2,)] opt {'keepdims': 0}
prepare <class '__main__.TinygradBackend'> CPU ['data', 'axes']
0: op ReduceSum shape [(3, 4, 5), (2,)] opt {'keepdims': 0}
1: op Log shape [(5,)] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['data', 'axes']
0: op ReduceLogSum shape [(3, 4, 5), (0,)] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['data', 'axes']
0: op ReduceSum shape [(3, 4, 5), (0,)] opt {'keepdims': 1}
1: op Log shape [(1, 1, 1)] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['data', 'axes']
0: op ReduceLogSum shape [(3, 4, 5), (2,)] opt {'keepdims': 0}
prepare <class '__main__.TinygradBackend'> CPU ['data', 'axes']
0: op ReduceSum shape [(3, 4, 5), (2,)] opt {'keepdims': 0}
1: op Log shape [(3,)] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['data', 'axes']
0: op ReduceLogSum shape [(2, 0, 4), (1,)] opt {'keepdims': 1}
prepare <class '__main__.TinygradBackend'> CPU ['data', 'axes']
0: op ReduceSum shape [(2, 0, 4), (1,)] opt {'keepdims': 1}
1: op Log shape [(2, 1, 4)] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['data', 'axes']
0: op ReduceLogSumExp shape [(3, 2, 2), (0,)] opt {'keepdims': 1}
prepare <class '__main__.TinygradBackend'> CPU ['data', 'axes']
0: op Cast shape [(3, 2, 2)] opt {'to': 11}
1: op Exp shape [(3, 2, 2)] opt {}
2: op ReduceSum shape [(3, 2, 2), (0,)] opt {'keepdims': 1}
3: op Log shape [(1, 1, 1)] opt {}
4: op CastLike shape [(1, 1, 1), (3, 2, 2)] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['data', 'axes']
0: op ReduceLogSumExp shape [(3, 2, 2), (0,)] opt {'keepdims': 1}
prepare <class '__main__.TinygradBackend'> CPU ['data', 'axes']
0: op Cast shape [(3, 2, 2)] opt {'to': 11}
1: op Exp shape [(3, 2, 2)] opt {}
2: op ReduceSum shape [(3, 2, 2), (0,)] opt {'keepdims': 1}
3: op Log shape [(1, 1, 1)] opt {}
4: op CastLike shape [(1, 1, 1), (3, 2, 2)] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['data', 'axes']
0: op ReduceLogSumExp shape [(3, 2, 2), (1,)] opt {'keepdims': 0}
prepare <class '__main__.TinygradBackend'> CPU ['data', 'axes']
0: op Cast shape [(3, 2, 2)] opt {'to': 11}
1: op Exp shape [(3, 2, 2)] opt {}
2: op ReduceSum shape [(3, 2, 2), (1,)] opt {'keepdims': 0}
3: op Log shape [(3, 2)] opt {}
4: op CastLike shape [(3, 2), (3, 2, 2)] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['data', 'axes']
0: op ReduceLogSumExp shape [(3, 2, 2), (1,)] opt {'keepdims': 0}
prepare <class '__main__.TinygradBackend'> CPU ['data', 'axes']
0: op Cast shape [(3, 2, 2)] opt {'to': 11}
1: op Exp shape [(3, 2, 2)] opt {}
2: op ReduceSum shape [(3, 2, 2), (1,)] opt {'keepdims': 0}
3: op Log shape [(3, 2)] opt {}
4: op CastLike shape [(3, 2), (3, 2, 2)] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['data', 'axes']
0: op ReduceLogSumExp shape [(2, 0, 4), (1,)] opt {'keepdims': 1}
prepare <class '__main__.TinygradBackend'> CPU ['data', 'axes']
0: op Cast shape [(2, 0, 4)] opt {'to': 11}
1: op Exp shape [(2, 0, 4)] opt {}
2: op ReduceSum shape [(2, 0, 4), (1,)] opt {'keepdims': 1}
3: op Log shape [(2, 1, 4)] opt {}
4: op CastLike shape [(2, 1, 4), (2, 0, 4)] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['data', 'axes']
0: op ReduceLogSumExp shape [(3, 2, 2), (1,)] opt {'keepdims': 1}
prepare <class '__main__.TinygradBackend'> CPU ['data', 'axes']
0: op Cast shape [(3, 2, 2)] opt {'to': 11}
1: op Exp shape [(3, 2, 2)] opt {}
2: op ReduceSum shape [(3, 2, 2), (1,)] opt {'keepdims': 1}
3: op Log shape [(3, 1, 2)] opt {}
4: op CastLike shape [(3, 1, 2), (3, 2, 2)] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['data', 'axes']
0: op ReduceLogSumExp shape [(3, 2, 2), (1,)] opt {'keepdims': 1}
prepare <class '__main__.TinygradBackend'> CPU ['data', 'axes']
0: op Cast shape [(3, 2, 2)] opt {'to': 11}
1: op Exp shape [(3, 2, 2)] opt {}
2: op ReduceSum shape [(3, 2, 2), (1,)] opt {'keepdims': 1}
3: op Log shape [(3, 1, 2)] opt {}
4: op CastLike shape [(3, 1, 2), (3, 2, 2)] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['data', 'axes']
0: op ReduceLogSumExp shape [(3, 2, 2), (1,)] opt {'keepdims': 1}
prepare <class '__main__.TinygradBackend'> CPU ['data', 'axes']
0: op Cast shape [(3, 2, 2)] opt {'to': 11}
1: op Exp shape [(3, 2, 2)] opt {}
2: op ReduceSum shape [(3, 2, 2), (1,)] opt {'keepdims': 1}
3: op Log shape [(3, 1, 2)] opt {}
4: op CastLike shape [(3, 1, 2), (3, 2, 2)] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['data', 'axes']
0: op ReduceLogSumExp shape [(3, 2, 2), (1,)] opt {'keepdims': 1}
prepare <class '__main__.TinygradBackend'> CPU ['data', 'axes']
0: op Cast shape [(3, 2, 2)] opt {'to': 11}
1: op Exp shape [(3, 2, 2)] opt {}
2: op ReduceSum shape [(3, 2, 2), (1,)] opt {'keepdims': 1}
3: op Log shape [(3, 1, 2)] opt {}
4: op CastLike shape [(3, 1, 2), (3, 2, 2)] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['data', 'axes']
0: op ReduceLogSum shape [(3, 4, 5), (1,)] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['data', 'axes']
0: op ReduceSum shape [(3, 4, 5), (1,)] opt {'keepdims': 1}
1: op Log shape [(3, 1, 5)] opt {}
prepare <class '__main__.TinygradBackend'> CPU ['data', 'axes']
0: op ReduceMax shape [(4, 2), (1,)] opt {'keepdims': 1}
prepare <class '__main__.TinygradBackend'> CPU ['data']
0: op ReduceMax shape [(3, 2, 2)] opt {'keepdims': 1}
prepare <class '__main__.TinygradBackend'> CPU ['data']
0: op ReduceMax shape [(3, 2, 2)] opt {'keepdims': 1}
prepare <class '__main__.TinygradBackend'> CPU ['data', 'axes']
0: op ReduceMax shape [(3, 2, 2), (1,)] opt {'keepdims': 0}
prepare <class '__main__.TinygradBackend'> CPU ['data', 'axes']
0: op ReduceMax shape [(3, 2, 2), (1,)] opt {'keepdims': 0}
prepare <class '__main__.TinygradBackend'> CPU ['data', 'axes']
0: op ReduceMax shape [(3, 2, 2), (1,)] opt {'keepdims': 1}
prepare <class '__main__.TinygradBackend'> CPU ['data', 'axes']
0: op ReduceMax shape [(3, 2, 2), (1,)] opt {'keepdims': 1}
prepare <class '__main__.TinygradBackend'> CPU ['data', 'axes']
0: op ReduceMax shape [(3, 2, 2), (1,)] opt {'keepdims': 1}
prepare .s.s.s.s.s.s.s.s.s.s.s.s.s.s.s.s.s.s.sssssssssssssssssss.s.s.s.s.s.s.s.s.s.s.s.s.s.s.s.s.s.s.s.s.s.s.s.s.s.s.s.s.s.sssssss.s.s.s.s.s.s.s.s.s.s.s.sssssssss<class '__main__.TinygradBackend'> CPU ['data', 'axes']
0: op ReduceMax shape [(3, 2, 2), (1,)] opt {'keepdims': 1}
prepare <class '__main__.TinygradBackend'> CPU ['data', 'axes']
0: op ReduceMean shape [(3, 2, 2), (0,)] opt {'keepdims': 1}
prepare <class '__main__.TinygradBackend'> CPU ['data', 'axes']
0: op ReduceMean shape [(3, 2, 2), (0,)] opt {'keepdims': 1}
prepare <class '__main__.TinygradBackend'> CPU ['data', 'axes']
0: op ReduceMean shape [(3, 2, 2), (1,)] opt {'keepdims': 0}
prepare <class '__main__.TinygradBackend'> CPU ['data', 'axes']
0: op ReduceMean shape [(3, 2, 2), (1,)] opt {'keepdims': 0}
prepare <class '__main__.TinygradBackend'> CPU ['data', 'axes']
0: op ReduceMean shape [(3, 2, 2), (1,)] opt {'keepdims': 1}
prepare <class '__main__.TinygradBackend'> CPU ['data', 'axes']
0: op ReduceMean shape [(3, 2, 2), (1,)] opt {'keepdims': 1}
prepare <class '__main__.TinygradBackend'> CPU ['data', 'axes']
0: op ReduceMean shape [(3, 2, 2), (1,)] opt {'keepdims': 1}
prepare <class '__main__.TinygradBackend'> CPU ['data', 'axes']
0: op ReduceMean shape [(3, 2, 2), (1,)] opt {'keepdims': 1}
prepare <class '__main__.TinygradBackend'> CPU ['data', 'axes']
0: op ReduceMin shape [(4, 2), (1,)] opt {'keepdims': 1}
prepare <class '__main__.TinygradBackend'> CPU ['data']
0: op ReduceMin shape [(3, 2, 2)] opt {'keepdims': 1}
prepare <class '__main__.TinygradBackend'> CPU ['data']
0: op ReduceMin shape [(3, 2, 2)] opt {'keepdims': 1}
prepare <class '__main__.TinygradBackend&