Github action: auto-update.

dev/_sources/auto_examples/plot_FNO_darcy.rst.txt

@@ -223,13 +223,13 @@ Creating the losses
     )
 
     ### SCHEDULER ###
-     <torch.optim.lr_scheduler.CosineAnnealingLR object at 0x7fe1371973d0>
+     <torch.optim.lr_scheduler.CosineAnnealingLR object at 0x7fb9a05f07c0>
 
     ### LOSSES ###
 
-     * Train: <neuralop.losses.data_losses.H1Loss object at 0x7fe137197b50>
+     * Train: <neuralop.losses.data_losses.H1Loss object at 0x7fb9a05f0f70>
 
-     * Test: {'h1': <neuralop.losses.data_losses.H1Loss object at 0x7fe137197b50>, 'l2': <neuralop.losses.data_losses.LpLoss object at 0x7fe13719fd30>}
+     * Test: {'h1': <neuralop.losses.data_losses.H1Loss object at 0x7fb9a05f0f70>, 'l2': <neuralop.losses.data_losses.LpLoss object at 0x7fb9a05f8b50>}
 
 
 
@@ -287,22 +287,22 @@ Actually train the model on our small Darcy-Flow dataset
     Training on 1000 samples
     Testing on [50, 50] samples         on resolutions [16, 32].
     Raw outputs of shape torch.Size([32, 1, 16, 16])
-    [0] time=2.59, avg_loss=0.6029, train_err=18.8421
-    Eval: 16_h1=0.3249, 16_l2=0.2475, 32_h1=0.4084, 32_l2=0.2616
-    [3] time=2.63, avg_loss=0.2414, train_err=7.5426
-    Eval: 16_h1=0.2092, 16_l2=0.1670, 32_h1=0.3164, 32_l2=0.1965
-    [6] time=2.59, avg_loss=0.2151, train_err=6.7212
-    Eval: 16_h1=0.1527, 16_l2=0.1086, 32_h1=0.2998, 32_l2=0.1481
-    [9] time=2.58, avg_loss=0.1882, train_err=5.8805
-    Eval: 16_h1=0.1568, 16_l2=0.1165, 32_h1=0.3090, 32_l2=0.1546
-    [12] time=2.58, avg_loss=0.1524, train_err=4.7630
-    Eval: 16_h1=0.1324, 16_l2=0.0921, 32_h1=0.3010, 32_l2=0.1353
-    [15] time=2.58, avg_loss=0.1472, train_err=4.5996
-    Eval: 16_h1=0.2177, 16_l2=0.1881, 32_h1=0.3272, 32_l2=0.2122
-    [18] time=2.57, avg_loss=0.1346, train_err=4.2072
-    Eval: 16_h1=0.1387, 16_l2=0.0998, 32_h1=0.3084, 32_l2=0.1386
+    [0] time=2.69, avg_loss=0.7268, train_err=22.7111
+    Eval: 16_h1=0.4083, 16_l2=0.3227, 32_h1=0.4680, 32_l2=0.3310
+    [3] time=2.74, avg_loss=0.2853, train_err=8.9167
+    Eval: 16_h1=0.2253, 16_l2=0.1743, 32_h1=0.3443, 32_l2=0.2092
+    [6] time=2.69, avg_loss=0.2521, train_err=7.8778
+    Eval: 16_h1=0.1865, 16_l2=0.1396, 32_h1=0.3035, 32_l2=0.1736
+    [9] time=2.69, avg_loss=0.1972, train_err=6.1629
+    Eval: 16_h1=0.1649, 16_l2=0.1180, 32_h1=0.2790, 32_l2=0.1320
+    [12] time=2.66, avg_loss=0.1757, train_err=5.4904
+    Eval: 16_h1=0.1613, 16_l2=0.1163, 32_h1=0.2669, 32_l2=0.1385
+    [15] time=2.65, avg_loss=0.1840, train_err=5.7502
+    Eval: 16_h1=0.1862, 16_l2=0.1522, 32_h1=0.2923, 32_l2=0.1889
+    [18] time=2.66, avg_loss=0.1646, train_err=5.1435
+    Eval: 16_h1=0.1507, 16_l2=0.1085, 32_h1=0.2738, 32_l2=0.1403
 
-    {'train_err': 4.1801688596606255, 'avg_loss': 0.13376540350914, 'avg_lasso_loss': None, 'epoch_train_time': 2.5705975879999983}
+    {'train_err': 4.775076363235712, 'avg_loss': 0.15280244362354278, 'avg_lasso_loss': None, 'epoch_train_time': 2.7486929789999976}
 
 
 
@@ -376,7 +376,7 @@ In practice we would train a Neural Operator on one or multiple GPUs
 
 .. rst-class:: sphx-glr-timing
 
-   **Total running time of the script:** (0 minutes 52.902 seconds)
+   **Total running time of the script:** (0 minutes 54.855 seconds)
 
 
 .. _sphx_glr_download_auto_examples_plot_FNO_darcy.py:

dev/_sources/auto_examples/plot_SFNO_swe.rst.txt

@@ -219,13 +219,13 @@ Creating the losses
     )
 
     ### SCHEDULER ###
-     <torch.optim.lr_scheduler.CosineAnnealingLR object at 0x7fe125b628e0>
+     <torch.optim.lr_scheduler.CosineAnnealingLR object at 0x7fb98ffe14c0>
 
     ### LOSSES ###
 
-     * Train: <neuralop.losses.data_losses.LpLoss object at 0x7fe13726c8e0>
+     * Train: <neuralop.losses.data_losses.LpLoss object at 0x7fb9a16f1a90>
 
-     * Test: {'l2': <neuralop.losses.data_losses.LpLoss object at 0x7fe13726c8e0>}
+     * Test: {'l2': <neuralop.losses.data_losses.LpLoss object at 0x7fb9a16f1a90>}
 
 
 
@@ -282,22 +282,22 @@ Actually train the model on our small Darcy-Flow dataset
     Training on 200 samples
     Testing on [50, 50] samples         on resolutions [(32, 64), (64, 128)].
     Raw outputs of shape torch.Size([4, 3, 32, 64])
-    [0] time=3.45, avg_loss=2.2364, train_err=8.9456
-    Eval: (32, 64)_l2=1.5414, (64, 128)_l2=2.6027
-    [3] time=3.43, avg_loss=0.4398, train_err=1.7591
-    Eval: (32, 64)_l2=0.4122, (64, 128)_l2=2.3448
-    [6] time=3.42, avg_loss=0.2936, train_err=1.1745
-    Eval: (32, 64)_l2=0.3607, (64, 128)_l2=2.3185
-    [9] time=3.41, avg_loss=0.2525, train_err=1.0099
-    Eval: (32, 64)_l2=0.3318, (64, 128)_l2=2.2875
-    [12] time=3.39, avg_loss=0.2005, train_err=0.8018
-    Eval: (32, 64)_l2=0.2855, (64, 128)_l2=2.2774
-    [15] time=3.41, avg_loss=0.1665, train_err=0.6661
-    Eval: (32, 64)_l2=0.2413, (64, 128)_l2=2.2890
-    [18] time=3.39, avg_loss=0.1431, train_err=0.5724
-    Eval: (32, 64)_l2=0.2218, (64, 128)_l2=2.2927
+    [0] time=3.56, avg_loss=2.1941, train_err=8.7763
+    Eval: (32, 64)_l2=1.2997, (64, 128)_l2=2.4382
+    [3] time=3.58, avg_loss=0.4245, train_err=1.6982
+    Eval: (32, 64)_l2=0.3959, (64, 128)_l2=2.3520
+    [6] time=3.55, avg_loss=0.3063, train_err=1.2254
+    Eval: (32, 64)_l2=0.3061, (64, 128)_l2=2.3443
+    [9] time=3.53, avg_loss=0.2690, train_err=1.0762
+    Eval: (32, 64)_l2=0.2966, (64, 128)_l2=2.3318
+    [12] time=3.58, avg_loss=0.2315, train_err=0.9261
+    Eval: (32, 64)_l2=0.2737, (64, 128)_l2=2.3063
+    [15] time=3.55, avg_loss=0.1845, train_err=0.7379
+    Eval: (32, 64)_l2=0.2309, (64, 128)_l2=2.3138
+    [18] time=3.54, avg_loss=0.1538, train_err=0.6152
+    Eval: (32, 64)_l2=0.2018, (64, 128)_l2=2.3443
 
-    {'train_err': 0.5530825763940811, 'avg_loss': 0.13827064409852027, 'avg_lasso_loss': None, 'epoch_train_time': 3.380090987000017}
+    {'train_err': 0.6165244770050049, 'avg_loss': 0.15413111925125123, 'avg_lasso_loss': None, 'epoch_train_time': 3.56806422599999}
 
 
 
@@ -368,7 +368,7 @@ In practice we would train a Neural Operator on one or multiple GPUs
 
 .. rst-class:: sphx-glr-timing
 
-   **Total running time of the script:** (1 minutes 24.407 seconds)
+   **Total running time of the script:** (1 minutes 27.738 seconds)
 
 
 .. _sphx_glr_download_auto_examples_plot_SFNO_swe.py:

dev/_sources/auto_examples/plot_UNO_darcy.rst.txt

@@ -263,13 +263,13 @@ Creating the losses
     )
 
     ### SCHEDULER ###
-     <torch.optim.lr_scheduler.CosineAnnealingLR object at 0x7fe14a27bf40>
+     <torch.optim.lr_scheduler.CosineAnnealingLR object at 0x7fb9b465ec40>
 
     ### LOSSES ###
 
-     * Train: <neuralop.losses.data_losses.H1Loss object at 0x7fe14a27b970>
+     * Train: <neuralop.losses.data_losses.H1Loss object at 0x7fb9b465e370>
 
-     * Test: {'h1': <neuralop.losses.data_losses.H1Loss object at 0x7fe14a27b970>, 'l2': <neuralop.losses.data_losses.LpLoss object at 0x7fe14a27b940>}
+     * Test: {'h1': <neuralop.losses.data_losses.H1Loss object at 0x7fb9b465e370>, 'l2': <neuralop.losses.data_losses.LpLoss object at 0x7fb9b465ec10>}
 
 
 
@@ -328,22 +328,22 @@ Actually train the model on our small Darcy-Flow dataset
     Training on 1000 samples
     Testing on [50, 50] samples         on resolutions [16, 32].
     Raw outputs of shape torch.Size([32, 1, 16, 16])
-    [0] time=6.55, avg_loss=0.5899, train_err=18.4342
-    Eval: 16_h1=0.3262, 16_l2=0.2621, 32_h1=0.8145, 32_l2=0.6577
-    [3] time=6.57, avg_loss=0.2657, train_err=8.3027
-    Eval: 16_h1=0.2603, 16_l2=0.2103, 32_h1=0.7715, 32_l2=0.6125
-    [6] time=6.66, avg_loss=0.2369, train_err=7.4020
-    Eval: 16_h1=0.2259, 16_l2=0.1721, 32_h1=0.7553, 32_l2=0.6095
-    [9] time=6.56, avg_loss=0.2127, train_err=6.6471
-    Eval: 16_h1=0.1982, 16_l2=0.1445, 32_h1=0.7570, 32_l2=0.6110
-    [12] time=6.58, avg_loss=0.2285, train_err=7.1407
-    Eval: 16_h1=0.2033, 16_l2=0.1444, 32_h1=0.7633, 32_l2=0.6271
-    [15] time=6.60, avg_loss=0.1873, train_err=5.8541
-    Eval: 16_h1=0.1990, 16_l2=0.1370, 32_h1=0.7599, 32_l2=0.6143
-    [18] time=6.60, avg_loss=0.1679, train_err=5.2471
-    Eval: 16_h1=0.1828, 16_l2=0.1259, 32_h1=0.7599, 32_l2=0.6190
+    [0] time=6.59, avg_loss=0.5322, train_err=16.6327
+    Eval: 16_h1=0.2821, 16_l2=0.2152, 32_h1=0.7833, 32_l2=0.6138
+    [3] time=6.59, avg_loss=0.2638, train_err=8.2445
+    Eval: 16_h1=0.2229, 16_l2=0.1711, 32_h1=0.7605, 32_l2=0.5979
+    [6] time=6.69, avg_loss=0.2435, train_err=7.6093
+    Eval: 16_h1=0.2201, 16_l2=0.1656, 32_h1=0.7540, 32_l2=0.6042
+    [9] time=6.66, avg_loss=0.2218, train_err=6.9315
+    Eval: 16_h1=0.1917, 16_l2=0.1368, 32_h1=0.7273, 32_l2=0.5864
+    [12] time=6.59, avg_loss=0.2040, train_err=6.3740
+    Eval: 16_h1=0.2075, 16_l2=0.1511, 32_h1=0.7168, 32_l2=0.5722
+    [15] time=6.64, avg_loss=0.1850, train_err=5.7799
+    Eval: 16_h1=0.1890, 16_l2=0.1308, 32_h1=0.7177, 32_l2=0.5650
+    [18] time=6.66, avg_loss=0.1755, train_err=5.4850
+    Eval: 16_h1=0.1832, 16_l2=0.1244, 32_h1=0.7110, 32_l2=0.5602
 
-    {'train_err': 5.3287844732403755, 'avg_loss': 0.170521103143692, 'avg_lasso_loss': None, 'epoch_train_time': 6.628478556999994}
+    {'train_err': 5.016685966402292, 'avg_loss': 0.16053395092487335, 'avg_lasso_loss': None, 'epoch_train_time': 6.617671456999915}
 
 
 
@@ -417,7 +417,7 @@ In practice we would train a Neural Operator on one or multiple GPUs
 
 .. rst-class:: sphx-glr-timing
 
-   **Total running time of the script:** (2 minutes 14.659 seconds)
+   **Total running time of the script:** (2 minutes 15.589 seconds)
 
 
 .. _sphx_glr_download_auto_examples_plot_UNO_darcy.py:

dev/_sources/auto_examples/plot_count_flops.rst.txt

@@ -80,7 +80,7 @@ This output is organized as a defaultdict object that counts the FLOPS used in e
 
  .. code-block:: none
 
-    defaultdict(<function FlopTensorDispatchMode.__init__.<locals>.<lambda> at 0x7fe14a263ca0>, {'': defaultdict(<class 'int'>, {'convolution.default': 2503999488, 'bmm.default': 138412032}), 'lifting': defaultdict(<class 'int'>, {'convolution.default': 1157627904}), 'lifting.fcs.0': defaultdict(<class 'int'>, {'convolution.default': 83886080}), 'lifting.fcs.1': defaultdict(<class 'int'>, {'convolution.default': 1073741824}), 'fno_blocks': defaultdict(<class 'int'>, {'convolution.default': 1073741824, 'bmm.default': 138412032}), 'fno_blocks.fno_skips.0': defaultdict(<class 'int'>, {'convolution.default': 268435456}), 'fno_blocks.fno_skips.0.conv': defaultdict(<class 'int'>, {'convolution.default': 268435456}), 'fno_blocks.convs': defaultdict(<class 'int'>, {'bmm.default': 138412032}), 'fno_blocks.fno_skips.1': defaultdict(<class 'int'>, {'convolution.default': 268435456}), 'fno_blocks.fno_skips.1.conv': defaultdict(<class 'int'>, {'convolution.default': 268435456}), 'fno_blocks.fno_skips.2': defaultdict(<class 'int'>, {'convolution.default': 268435456}), 'fno_blocks.fno_skips.2.conv': defaultdict(<class 'int'>, {'convolution.default': 268435456}), 'fno_blocks.fno_skips.3': defaultdict(<class 'int'>, {'convolution.default': 268435456}), 'fno_blocks.fno_skips.3.conv': defaultdict(<class 'int'>, {'convolution.default': 268435456}), 'projection': defaultdict(<class 'int'>, {'convolution.default': 272629760}), 'projection.fcs.0': defaultdict(<class 'int'>, {'convolution.default': 268435456}), 'projection.fcs.1': defaultdict(<class 'int'>, {'convolution.default': 4194304})})
+    defaultdict(<function FlopTensorDispatchMode.__init__.<locals>.<lambda> at 0x7fb9b465cca0>, {'': defaultdict(<class 'int'>, {'convolution.default': 2503999488, 'bmm.default': 138412032}), 'lifting': defaultdict(<class 'int'>, {'convolution.default': 1157627904}), 'lifting.fcs.0': defaultdict(<class 'int'>, {'convolution.default': 83886080}), 'lifting.fcs.1': defaultdict(<class 'int'>, {'convolution.default': 1073741824}), 'fno_blocks': defaultdict(<class 'int'>, {'convolution.default': 1073741824, 'bmm.default': 138412032}), 'fno_blocks.fno_skips.0': defaultdict(<class 'int'>, {'convolution.default': 268435456}), 'fno_blocks.fno_skips.0.conv': defaultdict(<class 'int'>, {'convolution.default': 268435456}), 'fno_blocks.convs': defaultdict(<class 'int'>, {'bmm.default': 138412032}), 'fno_blocks.fno_skips.1': defaultdict(<class 'int'>, {'convolution.default': 268435456}), 'fno_blocks.fno_skips.1.conv': defaultdict(<class 'int'>, {'convolution.default': 268435456}), 'fno_blocks.fno_skips.2': defaultdict(<class 'int'>, {'convolution.default': 268435456}), 'fno_blocks.fno_skips.2.conv': defaultdict(<class 'int'>, {'convolution.default': 268435456}), 'fno_blocks.fno_skips.3': defaultdict(<class 'int'>, {'convolution.default': 268435456}), 'fno_blocks.fno_skips.3.conv': defaultdict(<class 'int'>, {'convolution.default': 268435456}), 'projection': defaultdict(<class 'int'>, {'convolution.default': 272629760}), 'projection.fcs.0': defaultdict(<class 'int'>, {'convolution.default': 268435456}), 'projection.fcs.1': defaultdict(<class 'int'>, {'convolution.default': 4194304})})
 
 
 
@@ -125,7 +125,7 @@ To check the maximum FLOPS used during the forward pass, let's create a recursiv
 
 .. rst-class:: sphx-glr-timing
 
-   **Total running time of the script:** (0 minutes 4.883 seconds)
+   **Total running time of the script:** (0 minutes 3.651 seconds)
 
 
 .. _sphx_glr_download_auto_examples_plot_count_flops.py:

dev/_sources/auto_examples/plot_darcy_flow.rst.txt

@@ -163,7 +163,7 @@ Visualizing the data
 
 .. rst-class:: sphx-glr-timing
 
-   **Total running time of the script:** (0 minutes 0.424 seconds)
+   **Total running time of the script:** (0 minutes 0.429 seconds)
 
 
 .. _sphx_glr_download_auto_examples_plot_darcy_flow.py:

dev/_sources/auto_examples/plot_darcy_flow_spectrum.rst.txt

@@ -219,7 +219,7 @@ Loading the Navier-Stokes dataset in 128x128 resolution
 
 .. rst-class:: sphx-glr-timing
 
-   **Total running time of the script:** (0 minutes 0.277 seconds)
+   **Total running time of the script:** (0 minutes 0.279 seconds)
 
 
 .. _sphx_glr_download_auto_examples_plot_darcy_flow_spectrum.py:

dev/_sources/auto_examples/plot_incremental_FNO_darcy.rst.txt

@@ -238,15 +238,15 @@ Set up the losses
     )
 
     ### SCHEDULER ###
-     <torch.optim.lr_scheduler.CosineAnnealingLR object at 0x7fe14a2b4ee0>
+     <torch.optim.lr_scheduler.CosineAnnealingLR object at 0x7fb9a175d940>
 
     ### LOSSES ###
 
     ### INCREMENTAL RESOLUTION + GRADIENT EXPLAINED ###
 
-     * Train: <neuralop.losses.data_losses.H1Loss object at 0x7fe137118430>
+     * Train: <neuralop.losses.data_losses.H1Loss object at 0x7fb9a175d250>
 
-     * Test: {'h1': <neuralop.losses.data_losses.H1Loss object at 0x7fe137118430>, 'l2': <neuralop.losses.data_losses.LpLoss object at 0x7fe125b86b20>}
+     * Test: {'h1': <neuralop.losses.data_losses.H1Loss object at 0x7fb9a175d250>, 'l2': <neuralop.losses.data_losses.LpLoss object at 0x7fb9a175d7f0>}
 
 
 
@@ -329,49 +329,49 @@ Train the model
     Raw outputs of shape torch.Size([16, 1, 8, 8])
     [0] time=0.22, avg_loss=0.7750, train_err=11.0714
     Eval: 16_h1=0.7031, 16_l2=0.5348, 32_h1=0.7319, 32_l2=0.5357
-    [1] time=0.20, avg_loss=0.5908, train_err=8.4395
+    [1] time=0.21, avg_loss=0.5908, train_err=8.4395
     Eval: 16_h1=0.6114, 16_l2=0.4391, 32_h1=0.6716, 32_l2=0.4473
-    [2] time=0.20, avg_loss=0.5093, train_err=7.2754
+    [2] time=0.21, avg_loss=0.5093, train_err=7.2754
     Eval: 16_h1=0.5647, 16_l2=0.3843, 32_h1=0.6667, 32_l2=0.3946
-    [3] time=0.21, avg_loss=0.4408, train_err=6.2975
+    [3] time=0.22, avg_loss=0.4408, train_err=6.2975
     Eval: 16_h1=0.5216, 16_l2=0.3600, 32_h1=0.6661, 32_l2=0.3915
     [4] time=0.21, avg_loss=0.4055, train_err=5.7927
     Eval: 16_h1=0.5165, 16_l2=0.3631, 32_h1=0.6852, 32_l2=0.4008
-    [5] time=0.21, avg_loss=0.3794, train_err=5.4201
+    [5] time=0.22, avg_loss=0.3794, train_err=5.4201
     Eval: 16_h1=0.5407, 16_l2=0.4053, 32_h1=0.6456, 32_l2=0.4213
-    [6] time=0.22, avg_loss=0.3662, train_err=5.2311
+    [6] time=0.23, avg_loss=0.3662, train_err=5.2311
     Eval: 16_h1=0.4848, 16_l2=0.3434, 32_h1=0.6641, 32_l2=0.3786
-    [7] time=0.22, avg_loss=0.3320, train_err=4.7433
+    [7] time=0.23, avg_loss=0.3320, train_err=4.7433
     Eval: 16_h1=0.4515, 16_l2=0.3280, 32_h1=0.5890, 32_l2=0.3661
-    [8] time=0.22, avg_loss=0.3013, train_err=4.3041
+    [8] time=0.23, avg_loss=0.3013, train_err=4.3041
     Eval: 16_h1=0.4443, 16_l2=0.3024, 32_h1=0.6300, 32_l2=0.3467
-    [9] time=0.23, avg_loss=0.2621, train_err=3.7436
+    [9] time=0.24, avg_loss=0.2621, train_err=3.7436
     Eval: 16_h1=0.4252, 16_l2=0.2978, 32_h1=0.6085, 32_l2=0.3395
     Incre Res Update: change index to 1
     Incre Res Update: change sub to 1
     Incre Res Update: change res to 16
-    [10] time=0.30, avg_loss=0.3530, train_err=5.0422
+    [10] time=0.31, avg_loss=0.3530, train_err=5.0422
     Eval: 16_h1=0.3418, 16_l2=0.2496, 32_h1=0.4258, 32_l2=0.2477
-    [11] time=0.29, avg_loss=0.2891, train_err=4.1300
+    [11] time=0.30, avg_loss=0.2891, train_err=4.1300
     Eval: 16_h1=0.3833, 16_l2=0.2783, 32_h1=0.4696, 32_l2=0.2820
-    [12] time=0.31, avg_loss=0.2975, train_err=4.2504
+    [12] time=0.32, avg_loss=0.2975, train_err=4.2504
     Eval: 16_h1=0.3179, 16_l2=0.2267, 32_h1=0.4156, 32_l2=0.2404
-    [13] time=0.31, avg_loss=0.2420, train_err=3.4567
+    [13] time=0.32, avg_loss=0.2420, train_err=3.4567
     Eval: 16_h1=0.2829, 16_l2=0.2034, 32_h1=0.3807, 32_l2=0.2174
-    [14] time=0.31, avg_loss=0.2147, train_err=3.0676
+    [14] time=0.33, avg_loss=0.2147, train_err=3.0676
     Eval: 16_h1=0.3394, 16_l2=0.2630, 32_h1=0.4255, 32_l2=0.2714
-    [15] time=0.32, avg_loss=0.2232, train_err=3.1885
+    [15] time=0.35, avg_loss=0.2232, train_err=3.1885
     Eval: 16_h1=0.3785, 16_l2=0.2985, 32_h1=0.4668, 32_l2=0.3102
-    [16] time=0.32, avg_loss=0.2555, train_err=3.6494
+    [16] time=0.33, avg_loss=0.2555, train_err=3.6494
     Eval: 16_h1=0.3279, 16_l2=0.2593, 32_h1=0.4078, 32_l2=0.2623
-    [17] time=0.32, avg_loss=0.2769, train_err=3.9559
+    [17] time=0.34, avg_loss=0.2769, train_err=3.9559
     Eval: 16_h1=0.4073, 16_l2=0.3371, 32_h1=0.4499, 32_l2=0.3422
-    [18] time=0.32, avg_loss=0.2840, train_err=4.0576
+    [18] time=0.34, avg_loss=0.2840, train_err=4.0576
     Eval: 16_h1=0.2826, 16_l2=0.2202, 32_h1=0.3649, 32_l2=0.2272
-    [19] time=0.32, avg_loss=0.1984, train_err=2.8340
+    [19] time=0.34, avg_loss=0.1984, train_err=2.8340
     Eval: 16_h1=0.2795, 16_l2=0.2186, 32_h1=0.3582, 32_l2=0.2296
 
-    {'train_err': 2.8339713641575406, 'avg_loss': 0.19837799549102783, 'avg_lasso_loss': None, 'epoch_train_time': 0.32204329900002904, '16_h1': tensor(0.2795), '16_l2': tensor(0.2186), '32_h1': tensor(0.3582), '32_l2': tensor(0.2296)}
+    {'train_err': 2.8339713641575406, 'avg_loss': 0.19837799549102783, 'avg_lasso_loss': None, 'epoch_train_time': 0.33832480899991424, '16_h1': tensor(0.2795), '16_l2': tensor(0.2186), '32_h1': tensor(0.3582), '32_l2': tensor(0.2296)}
 
 
 
@@ -445,7 +445,7 @@ In practice we would train a Neural Operator on one or multiple GPUs
 
 .. rst-class:: sphx-glr-timing
 
-   **Total running time of the script:** (0 minutes 7.816 seconds)
+   **Total running time of the script:** (0 minutes 8.163 seconds)
 
 
 .. _sphx_glr_download_auto_examples_plot_incremental_FNO_darcy.py:

dev/_sources/auto_examples/sg_execution_times.rst.txt

@@ -6,7 +6,7 @@
 
 Computation times
 =================
-**04:45.368** total execution time for 8 files **from auto_examples**:
+**04:50.704** total execution time for 8 files **from auto_examples**:
 
 .. container::
 
@@ -33,25 +33,25 @@ Computation times
      - Time
      - Mem (MB)
    * - :ref:`sphx_glr_auto_examples_plot_UNO_darcy.py` (``plot_UNO_darcy.py``)
-     - 02:14.659
+     - 02:15.589
      - 0.0
    * - :ref:`sphx_glr_auto_examples_plot_SFNO_swe.py` (``plot_SFNO_swe.py``)
-     - 01:24.407
+     - 01:27.738
      - 0.0
    * - :ref:`sphx_glr_auto_examples_plot_FNO_darcy.py` (``plot_FNO_darcy.py``)
-     - 00:52.902
+     - 00:54.855
      - 0.0
    * - :ref:`sphx_glr_auto_examples_plot_incremental_FNO_darcy.py` (``plot_incremental_FNO_darcy.py``)
-     - 00:07.816
+     - 00:08.163
      - 0.0
    * - :ref:`sphx_glr_auto_examples_plot_count_flops.py` (``plot_count_flops.py``)
-     - 00:04.883
+     - 00:03.651
      - 0.0
    * - :ref:`sphx_glr_auto_examples_plot_darcy_flow.py` (``plot_darcy_flow.py``)
-     - 00:00.424
+     - 00:00.429
      - 0.0
    * - :ref:`sphx_glr_auto_examples_plot_darcy_flow_spectrum.py` (``plot_darcy_flow_spectrum.py``)
-     - 00:00.277
+     - 00:00.279
      - 0.0
    * - :ref:`sphx_glr_auto_examples_checkpoint_FNO_darcy.py` (``checkpoint_FNO_darcy.py``)
      - 00:00.000