diff --git a/.gitattributes b/.gitattributes index 346400c8545c485f3f785c6f987ff67b3006755c..d9eae9056c0f53e0f60910c32e3de54570e8b23b 100644 --- a/.gitattributes +++ b/.gitattributes @@ -35,3 +35,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text *tfevents* filter=lfs diff=lfs merge=lfs -text nnUNetTrainer__nnUNetResEncUNetLPlans__2d/fold_all/progress.png filter=lfs diff=lfs merge=lfs -text nnUNetTrainer__nnUNetResEncUNetLPlans__3d_fullres/fold_all/progress.png filter=lfs diff=lfs merge=lfs -text +Dataset809_AbdomenAtlasF17/nnUNetTrainer__nnUNetResEncUNetLPlans__2d/fold_all/progress.png filter=lfs diff=lfs merge=lfs -text +Dataset809_AbdomenAtlasF17/nnUNetTrainer__nnUNetResEncUNetLPlans__3d_fullres/fold_all/progress.png filter=lfs diff=lfs merge=lfs -text diff --git a/Dataset809_AbdomenAtlasF17/nnUNetTrainer__nnUNetResEncUNetLPlans__2d/dataset.json b/Dataset809_AbdomenAtlasF17/nnUNetTrainer__nnUNetResEncUNetLPlans__2d/dataset.json new file mode 100644 index 0000000000000000000000000000000000000000..9f2938d4f2036ea8e2f707c46f59d7221f42eb16 --- /dev/null +++ b/Dataset809_AbdomenAtlasF17/nnUNetTrainer__nnUNetResEncUNetLPlans__2d/dataset.json @@ -0,0 +1,34 @@ +{ + "name": "JHH-Train-test", + "description": "3151 cases for training; 1958 cases for testing", + "reference": "ScaleMAI", + "licence": "CC-BY-SA 4.0", + "relase": "1.0 10/28/2024", + "tensorImageSize": "3D", + "labels": { + "background": 0, + "aorta": 1, + "adrenal_gland_left": 2, + "adrenal_gland_right": 3, + "celiac_aa": 4, + "colon": 5, + "duodenum": 6, + "gall_bladder": 7, + "postcava": 8, + "kidney_left": 9, + "kidney_right": 10, + "liver": 11, + "pancreas": 12, + "superior_mesenteric_artery": 13, + "intestine": 14, + "spleen": 15, + "renal_vein_left": 16, + "renal_vein_right": 17 + }, + "numTraining": 3151, + "numTest": 1958, + "file_ending": ".nii.gz", + "channel_names": { + "0": "CT" + } +} \ No newline at end of file diff --git a/Dataset809_AbdomenAtlasF17/nnUNetTrainer__nnUNetResEncUNetLPlans__2d/dataset_fingerprint.json b/Dataset809_AbdomenAtlasF17/nnUNetTrainer__nnUNetResEncUNetLPlans__2d/dataset_fingerprint.json new file mode 100644 index 0000000000000000000000000000000000000000..3d1c25963dacc9058ac9738afdb0da4304b43a4f --- /dev/null +++ b/Dataset809_AbdomenAtlasF17/nnUNetTrainer__nnUNetResEncUNetLPlans__2d/dataset_fingerprint.json @@ -0,0 +1,31528 @@ +{ + "foreground_intensity_properties_per_channel": { + "0": { + "max": 1000.0, + "mean": 39.68027877807617, + "median": 71.0, + "min": -1000.0, + "percentile_00_5": -1000.0, + "percentile_99_5": 379.0, + "std": 192.4669952392578 + } + }, + "median_relative_size_after_cropping": 1.0, + "shapes_after_crop": [ + [ + 541, + 512, + 512 + ], + [ + 523, + 512, + 512 + ], + [ + 547, + 512, + 512 + ], + [ + 437, + 512, + 512 + ], + [ + 582, + 512, + 512 + ], + [ + 595, + 512, + 512 + ], + [ + 472, + 512, + 512 + ], + [ + 879, + 512, + 512 + ], + [ + 522, + 512, + 512 + ], + [ + 606, + 512, + 512 + ], + [ + 620, + 512, + 512 + ], + [ + 549, + 512, + 512 + ], + [ + 817, + 512, + 512 + ], + [ + 504, + 512, + 512 + ], + [ + 470, + 512, + 512 + ], + [ + 565, + 512, + 512 + ], + [ + 490, + 512, + 512 + ], + [ + 772, + 512, + 512 + ], + [ + 579, + 512, + 512 + ], + [ + 561, + 512, + 512 + ], + [ + 485, + 512, + 512 + ], + [ + 371, + 512, + 512 + ], + [ + 697, + 512, + 512 + ], + [ + 409, + 512, + 512 + ], + [ + 553, + 512, + 512 + ], + [ + 557, + 512, + 512 + ], + [ + 589, + 512, + 512 + ], + [ + 416, + 512, + 512 + ], + [ + 481, + 512, + 512 + ], + [ + 498, + 512, + 512 + ], + [ + 453, + 512, + 512 + ], + [ + 436, + 512, + 512 + ], + [ + 581, + 512, + 512 + ], + [ + 485, + 512, + 512 + ], + [ + 545, + 512, + 512 + ], + [ + 553, + 512, + 512 + ], + [ + 621, + 512, + 512 + ], + [ + 470, + 512, + 512 + ], + [ + 855, + 512, + 512 + ], + [ + 423, + 512, + 512 + ], + [ + 443, + 512, + 512 + ], + [ + 542, + 512, + 512 + ], + [ + 602, + 512, + 512 + ], + [ + 453, + 512, + 512 + ], + [ + 453, + 512, + 512 + ], + [ + 491, + 512, + 512 + ], + [ + 581, + 512, + 512 + ], + [ + 553, + 512, + 512 + ], + [ + 535, + 512, + 512 + ], + [ + 885, + 512, + 512 + ], + [ + 581, + 512, + 512 + ], + [ + 581, + 512, + 512 + ], + [ + 521, + 512, + 512 + ], + [ + 853, + 512, + 512 + ], + [ + 536, + 512, + 512 + ], + [ + 557, + 512, + 512 + ], + [ + 882, + 512, + 512 + ], + [ + 462, + 512, + 512 + ], + [ + 601, + 512, + 512 + ], + [ + 431, + 512, + 512 + ], + [ + 585, + 512, + 512 + ], + [ + 525, + 512, + 512 + ], + [ + 542, + 512, + 512 + ], + [ + 549, + 512, + 512 + ], + [ + 493, + 512, + 512 + ], + [ + 598, + 512, + 512 + ], + [ + 505, + 512, + 512 + ], + [ + 437, + 512, + 512 + ], + [ + 630, + 512, + 512 + ], + [ + 450, + 512, + 512 + ], + [ + 524, + 512, + 512 + ], + [ + 497, + 512, + 512 + ], + [ + 464, + 512, + 512 + ], + [ + 577, + 512, + 512 + ], + [ + 505, + 512, + 512 + ], + [ + 462, + 512, + 512 + ], + [ + 570, + 512, + 512 + ], + [ + 586, + 512, + 512 + ], + [ + 557, + 512, + 512 + ], + [ + 525, + 512, + 512 + ], + [ + 485, + 512, + 512 + ], + [ + 565, + 512, + 512 + ], + [ + 429, + 512, + 512 + ], + [ + 553, + 512, + 512 + ], + [ + 450, + 512, + 512 + ], + [ + 561, + 512, + 512 + ], + [ + 472, + 512, + 512 + ], + [ + 805, + 512, + 512 + ], + [ + 525, + 512, + 512 + ], + [ + 572, + 512, + 512 + ], + [ + 959, + 512, + 512 + ], + [ + 559, + 512, + 512 + ], + [ + 481, + 512, + 512 + ], + [ + 552, + 512, + 512 + ], + [ + 510, + 512, + 512 + ], + [ + 449, + 512, + 512 + ], + [ + 663, + 512, + 512 + ], + [ + 609, + 512, + 512 + ], + [ + 432, + 512, + 512 + ], + [ + 534, + 512, + 512 + ], + [ + 523, + 512, + 512 + ], + [ + 521, + 512, + 512 + ], + [ + 461, + 512, + 512 + ], + [ + 453, + 512, + 512 + ], + [ + 431, + 512, + 512 + ], + [ + 521, + 512, + 512 + ], + [ + 521, + 512, + 512 + ], + [ + 498, + 512, + 512 + ], + [ + 490, + 512, + 512 + ], + [ + 461, + 512, + 512 + ], + [ + 639, + 512, + 512 + ], + [ + 514, + 512, + 512 + ], + [ + 547, + 512, + 512 + ], + [ + 883, + 512, + 512 + ], + [ + 471, + 512, + 512 + ], + [ + 491, + 512, + 512 + ], + [ + 429, + 512, + 512 + ], + [ + 1026, + 512, + 512 + ], + [ + 449, + 512, + 512 + ], + [ + 553, + 512, + 512 + ], + [ + 542, + 512, + 512 + ], + [ + 481, + 512, + 512 + ], + [ + 705, + 512, + 512 + ], + [ + 585, + 512, + 512 + ], + [ + 605, + 512, + 512 + ], + [ + 523, + 512, + 512 + ], + [ + 425, + 512, + 512 + ], + [ + 410, + 512, + 512 + ], + [ + 901, + 512, + 512 + ], + [ + 472, + 512, + 512 + ], + [ + 441, + 512, + 512 + ], + [ + 561, + 512, + 512 + ], + [ + 592, + 512, + 512 + ], + [ + 584, + 512, + 512 + ], + [ + 589, + 512, + 512 + ], + [ + 565, + 512, + 512 + ], + [ + 502, + 512, + 512 + ], + [ + 554, + 512, + 512 + ], + [ + 765, + 512, + 512 + ], + [ + 481, + 512, + 512 + ], + [ + 649, + 512, + 512 + ], + [ + 476, + 512, + 512 + ], + [ + 518, + 512, + 512 + ], + [ + 942, + 512, + 512 + ], + [ + 500, + 512, + 512 + ], + [ + 411, + 512, + 512 + ], + [ + 569, + 512, + 512 + ], + [ + 608, + 512, + 512 + ], + [ + 490, + 512, + 512 + ], + [ + 406, + 512, + 512 + ], + [ + 465, + 512, + 512 + ], + [ + 546, + 512, + 512 + ], + [ + 492, + 512, + 512 + ], + [ + 485, + 512, + 512 + ], + [ + 559, + 512, + 512 + ], + [ + 577, + 512, + 512 + ], + [ + 533, + 512, + 512 + ], + [ + 528, + 512, + 512 + ], + [ + 874, + 512, + 512 + ], + [ + 946, + 512, + 512 + ], + [ + 461, + 512, + 512 + ], + [ + 903, + 512, + 512 + ], + [ + 879, + 512, + 512 + ], + [ + 493, + 512, + 512 + ], + [ + 437, + 512, + 512 + ], + [ + 601, + 512, + 512 + ], + [ + 554, + 512, + 512 + ], + [ + 486, + 512, + 512 + ], + [ + 569, + 512, + 512 + ], + [ + 873, + 512, + 512 + ], + [ + 499, + 512, + 512 + ], + [ + 565, + 512, + 512 + ], + [ + 533, + 512, + 512 + ], + [ + 473, + 512, + 512 + ], + [ + 562, + 512, + 512 + ], + [ + 493, + 512, + 512 + ], + [ + 474, + 512, + 512 + ], + [ + 644, + 512, + 512 + ], + [ + 470, + 512, + 512 + ], + [ + 540, + 512, + 512 + ], + [ + 501, + 512, + 512 + ], + [ + 389, + 512, + 512 + ], + [ + 423, + 512, + 512 + ], + [ + 493, + 512, + 512 + ], + [ + 529, + 512, + 512 + ], + [ + 529, + 512, + 512 + ], + [ + 361, + 512, + 512 + ], + [ + 596, + 512, + 512 + ], + [ + 582, + 512, + 512 + ], + [ + 471, + 512, + 512 + ], + [ + 533, + 512, + 512 + ], + [ + 506, + 512, + 512 + ], + [ + 509, + 512, + 512 + ], + [ + 586, + 512, + 512 + ], + [ + 438, + 512, + 512 + ], + [ + 504, + 512, + 512 + ], + [ + 497, + 512, + 512 + ], + [ + 793, + 512, + 512 + ], + [ + 520, + 512, + 512 + ], + [ + 417, + 512, + 512 + ], + [ + 393, + 512, + 512 + ], + [ + 512, + 512, + 512 + ], + [ + 596, + 512, + 512 + ], + [ + 569, + 512, + 512 + ], + [ + 587, + 512, + 512 + ], + [ + 569, + 512, + 512 + ], + [ + 617, + 512, + 512 + ], + [ + 587, + 512, + 512 + ], + [ + 591, + 512, + 512 + ], + [ + 547, + 512, + 512 + ], + [ + 636, + 512, + 512 + ], + [ + 481, + 512, + 512 + ], + [ + 676, + 512, + 512 + ], + [ + 587, + 512, + 512 + ], + [ + 655, + 512, + 512 + ], + [ + 502, + 512, + 512 + ], + [ + 632, + 512, + 512 + ], + [ + 445, + 512, + 512 + ], + [ + 605, + 512, + 512 + ], + [ + 563, + 512, + 512 + ], + [ + 579, + 512, + 512 + ], + [ + 667, + 512, + 512 + ], + [ + 601, + 512, + 512 + ], + [ + 632, + 512, + 512 + ], + [ + 653, + 512, + 512 + ], + [ + 585, + 512, + 512 + ], + [ + 521, + 512, + 512 + ], + [ + 667, + 512, + 512 + ], + [ + 609, + 512, + 512 + ], + [ + 606, + 512, + 512 + ], + [ + 483, + 512, + 512 + ], + [ + 641, + 512, + 512 + ], + [ + 590, + 512, + 512 + ], + [ + 708, + 512, + 512 + ], + [ + 617, + 512, + 512 + ], + [ + 672, + 512, + 512 + ], + [ + 461, + 512, + 512 + ], + [ + 655, + 512, + 512 + ], + [ + 633, + 512, + 512 + ], + [ + 493, + 512, + 512 + ], + [ + 477, + 512, + 512 + ], + [ + 606, + 512, + 512 + ], + [ + 590, + 512, + 512 + ], + [ + 629, + 512, + 512 + ], + [ + 489, + 512, + 512 + ], + [ + 469, + 512, + 512 + ], + [ + 543, + 512, + 512 + ], + [ + 713, + 512, + 512 + ], + [ + 643, + 512, + 512 + ], + [ + 553, + 512, + 512 + ], + [ + 557, + 512, + 512 + ], + [ + 655, + 512, + 512 + ], + [ + 512, + 512, + 512 + ], + [ + 490, + 512, + 512 + ], + [ + 521, + 512, + 512 + ], + [ + 627, + 512, + 512 + ], + [ + 675, + 512, + 512 + ], + [ + 553, + 512, + 512 + ], + [ + 642, + 512, + 512 + ], + [ + 726, + 512, + 512 + ], + [ + 539, + 512, + 512 + ], + [ + 421, + 512, + 512 + ], + [ + 697, + 512, + 512 + ], + [ + 631, + 512, + 512 + ], + [ + 611, + 512, + 512 + ], + [ + 557, + 512, + 512 + ], + [ + 479, + 512, + 512 + ], + [ + 605, + 512, + 512 + ], + [ + 585, + 512, + 512 + ], + [ + 637, + 512, + 512 + ], + [ + 627, + 512, + 512 + ], + [ + 531, + 512, + 512 + ], + [ + 631, + 512, + 512 + ], + [ + 431, + 512, + 512 + ], + [ + 641, + 512, + 512 + ], + [ + 401, + 512, + 512 + ], + [ + 711, + 512, + 512 + ], + [ + 659, + 512, + 512 + ], + [ + 525, + 512, + 512 + ], + [ + 593, + 512, + 512 + ], + [ + 613, + 512, + 512 + ], + [ + 709, + 512, + 512 + ], + [ + 631, + 512, + 512 + ], + [ + 499, + 512, + 512 + ], + [ + 643, + 512, + 512 + ], + [ + 657, + 512, + 512 + ], + [ + 625, + 512, + 512 + ], + [ + 513, + 512, + 512 + ], + [ + 545, + 512, + 512 + ], + [ + 603, + 512, + 512 + ], + [ + 575, + 512, + 512 + ], + [ + 611, + 512, + 512 + ], + [ + 618, + 512, + 512 + ], + [ + 643, + 512, + 512 + ], + [ + 675, + 512, + 512 + ], + [ + 553, + 512, + 512 + ], + [ + 635, + 512, + 512 + ], + [ + 585, + 512, + 512 + ], + [ + 677, + 512, + 512 + ], + [ + 655, + 512, + 512 + ], + [ + 667, + 512, + 512 + ], + [ + 655, + 512, + 512 + ], + [ + 568, + 512, + 512 + ], + [ + 445, + 512, + 512 + ], + [ + 659, + 512, + 512 + ], + [ + 497, + 512, + 512 + ], + [ + 581, + 512, + 512 + ], + [ + 721, + 512, + 512 + ], + [ + 651, + 512, + 512 + ], + [ + 639, + 512, + 512 + ], + [ + 748, + 512, + 512 + ], + [ + 554, + 512, + 512 + ], + [ + 502, + 512, + 512 + ], + [ + 587, + 512, + 512 + ], + [ + 761, + 512, + 512 + ], + [ + 537, + 512, + 512 + ], + [ + 621, + 512, + 512 + ], + [ + 563, + 512, + 512 + ], + [ + 671, + 512, + 512 + ], + [ + 663, + 512, + 512 + ], + [ + 581, + 512, + 512 + ], + [ + 632, + 512, + 512 + ], + [ + 600, + 512, + 512 + ], + [ + 657, + 512, + 512 + ], + [ + 775, + 512, + 512 + ], + [ + 684, + 512, + 512 + ], + [ + 707, + 512, + 512 + ], + [ + 624, + 512, + 512 + ], + [ + 625, + 512, + 512 + ], + [ + 469, + 512, + 512 + ], + [ + 697, + 512, + 512 + ], + [ + 585, + 512, + 512 + ], + [ + 445, + 512, + 512 + ], + [ + 634, + 512, + 512 + ], + [ + 557, + 512, + 512 + ], + [ + 623, + 512, + 512 + ], + [ + 613, + 512, + 512 + ], + [ + 735, + 512, + 512 + ], + [ + 639, + 512, + 512 + ], + [ + 808, + 512, + 512 + ], + [ + 605, + 512, + 512 + ], + [ + 679, + 512, + 512 + ], + [ + 659, + 512, + 512 + ], + [ + 660, + 512, + 512 + ], + [ + 496, + 512, + 512 + ], + [ + 624, + 512, + 512 + ], + [ + 619, + 512, + 512 + ], + [ + 635, + 512, + 512 + ], + [ + 697, + 512, + 512 + ], + [ + 859, + 512, + 512 + ], + [ + 563, + 512, + 512 + ], + [ + 653, + 512, + 512 + ], + [ + 614, + 512, + 512 + ], + [ + 611, + 512, + 512 + ], + [ + 685, + 512, + 512 + ], + [ + 591, + 512, + 512 + ], + [ + 616, + 512, + 512 + ], + [ + 723, + 512, + 512 + ], + [ + 683, + 512, + 512 + ], + [ + 579, + 512, + 512 + ], + [ + 647, + 512, + 512 + ], + [ + 709, + 512, + 512 + ], + [ + 667, + 512, + 512 + ], + [ + 649, + 512, + 512 + ], + [ + 568, + 512, + 512 + ], + [ + 580, + 512, + 512 + ], + [ + 441, + 512, + 512 + ], + [ + 363, + 512, + 512 + ], + [ + 479, + 512, + 512 + ], + [ + 557, + 512, + 512 + ], + [ + 603, + 512, + 512 + ], + [ + 767, + 512, + 512 + ], + [ + 657, + 512, + 512 + ], + [ + 601, + 512, + 512 + ], + [ + 575, + 512, + 512 + ], + [ + 668, + 512, + 512 + ], + [ + 528, + 512, + 512 + ], + [ + 585, + 512, + 512 + ], + [ + 586, + 512, + 512 + ], + [ + 625, + 512, + 512 + ], + [ + 695, + 512, + 512 + ], + [ + 757, + 512, + 512 + ], + [ + 689, + 512, + 512 + ], + [ + 632, + 512, + 512 + ], + [ + 536, + 512, + 512 + ], + [ + 641, + 512, + 512 + ], + [ + 653, + 512, + 512 + ], + [ + 598, + 512, + 512 + ], + [ + 564, + 512, + 512 + ], + [ + 472, + 512, + 512 + ], + [ + 602, + 512, + 512 + ], + [ + 331, + 512, + 512 + ], + [ + 441, + 512, + 512 + ], + [ + 635, + 512, + 512 + ], + [ + 368, + 512, + 512 + ], + [ + 583, + 512, + 512 + ], + [ + 771, + 512, + 512 + ], + [ + 421, + 512, + 512 + ], + [ + 399, + 512, + 512 + ], + [ + 576, + 512, + 512 + ], + [ + 707, + 512, + 512 + ], + [ + 507, + 512, + 512 + ], + [ + 586, + 512, + 512 + ], + [ + 585, + 512, + 512 + ], + [ + 512, + 512, + 512 + ], + [ + 588, + 512, + 512 + ], + [ + 563, + 512, + 512 + ], + [ + 586, + 512, + 512 + ], + [ + 598, + 512, + 512 + ], + [ + 546, + 512, + 512 + ], + [ + 527, + 512, + 512 + ], + [ + 650, + 512, + 512 + ], + [ + 505, + 512, + 512 + ], + [ + 645, + 512, + 512 + ], + [ + 521, + 512, + 512 + ], + [ + 606, + 512, + 512 + ], + [ + 600, + 512, + 512 + ], + [ + 556, + 512, + 512 + ], + [ + 642, + 512, + 512 + ], + [ + 647, + 512, + 512 + ], + [ + 582, + 512, + 512 + ], + [ + 537, + 512, + 512 + ], + [ + 621, + 512, + 512 + ], + [ + 611, + 512, + 512 + ], + [ + 599, + 512, + 512 + ], + [ + 667, + 512, + 512 + ], + [ + 538, + 512, + 512 + ], + [ + 553, + 512, + 512 + ], + [ + 594, + 512, + 512 + ], + [ + 361, + 512, + 512 + ], + [ + 679, + 512, + 512 + ], + [ + 670, + 512, + 512 + ], + [ + 673, + 512, + 512 + ], + [ + 618, + 512, + 512 + ], + [ + 689, + 512, + 512 + ], + [ + 616, + 512, + 512 + ], + [ + 619, + 512, + 512 + ], + [ + 548, + 512, + 512 + ], + [ + 618, + 512, + 512 + ], + [ + 503, + 512, + 512 + ], + [ + 531, + 512, + 512 + ], + [ + 609, + 512, + 512 + ], + [ + 610, + 512, + 512 + ], + [ + 579, + 512, + 512 + ], + [ + 603, + 512, + 512 + ], + [ + 640, + 512, + 512 + ], + [ + 511, + 512, + 512 + ], + [ + 585, + 512, + 512 + ], + [ + 707, + 512, + 512 + ], + [ + 606, + 512, + 512 + ], + [ + 629, + 512, + 512 + ], + [ + 627, + 512, + 512 + ], + [ + 656, + 512, + 512 + ], + [ + 606, + 512, + 512 + ], + [ + 477, + 512, + 512 + ], + [ + 537, + 512, + 512 + ], + [ + 505, + 512, + 512 + ], + [ + 448, + 512, + 512 + ], + [ + 483, + 512, + 512 + ], + [ + 444, + 512, + 512 + ], + [ + 549, + 512, + 512 + ], + [ + 664, + 512, + 512 + ], + [ + 556, + 512, + 512 + ], + [ + 734, + 512, + 512 + ], + [ + 620, + 512, + 512 + ], + [ + 555, + 512, + 512 + ], + [ + 602, + 512, + 512 + ], + [ + 505, + 512, + 512 + ], + [ + 587, + 512, + 512 + ], + [ + 641, + 512, + 512 + ], + [ + 533, + 512, + 512 + ], + [ + 631, + 512, + 512 + ], + [ + 594, + 512, + 512 + ], + [ + 579, + 512, + 512 + ], + [ + 465, + 512, + 512 + ], + [ + 544, + 512, + 512 + ], + [ + 707, + 512, + 512 + ], + [ + 687, + 512, + 512 + ], + [ + 578, + 512, + 512 + ], + [ + 646, + 512, + 512 + ], + [ + 590, + 512, + 512 + ], + [ + 510, + 512, + 512 + ], + [ + 649, + 512, + 512 + ], + [ + 761, + 512, + 512 + ], + [ + 565, + 512, + 512 + ], + [ + 679, + 512, + 512 + ], + [ + 576, + 512, + 512 + ], + [ + 485, + 512, + 512 + ], + [ + 594, + 512, + 512 + ], + [ + 717, + 512, + 512 + ], + [ + 577, + 512, + 512 + ], + [ + 605, + 512, + 512 + ], + [ + 557, + 512, + 512 + ], + [ + 527, + 512, + 512 + ], + [ + 687, + 512, + 512 + ], + [ + 645, + 512, + 512 + ], + [ + 558, + 512, + 512 + ], + [ + 545, + 512, + 512 + ], + [ + 510, + 512, + 512 + ], + [ + 691, + 512, + 512 + ], + [ + 708, + 512, + 512 + ], + [ + 649, + 512, + 512 + ], + [ + 625, + 512, + 512 + ], + [ + 593, + 512, + 512 + ], + [ + 582, + 512, + 512 + ], + [ + 548, + 512, + 512 + ], + [ + 721, + 512, + 512 + ], + [ + 647, + 512, + 512 + ], + [ + 661, + 512, + 512 + ], + [ + 689, + 512, + 512 + ], + [ + 617, + 512, + 512 + ], + [ + 688, + 512, + 512 + ], + [ + 501, + 512, + 512 + ], + [ + 677, + 512, + 512 + ], + [ + 602, + 512, + 512 + ], + [ + 577, + 512, + 512 + ], + [ + 578, + 512, + 512 + ], + [ + 569, + 512, + 512 + ], + [ + 573, + 512, + 512 + ], + [ + 579, + 512, + 512 + ], + [ + 672, + 512, + 512 + ], + [ + 545, + 512, + 512 + ], + [ + 691, + 512, + 512 + ], + [ + 591, + 512, + 512 + ], + [ + 509, + 512, + 512 + ], + [ + 441, + 512, + 512 + ], + [ + 589, + 512, + 512 + ], + [ + 621, + 512, + 512 + ], + [ + 553, + 512, + 512 + ], + [ + 528, + 512, + 512 + ], + [ + 461, + 512, + 512 + ], + [ + 513, + 512, + 512 + ], + [ + 589, + 512, + 512 + ], + [ + 469, + 512, + 512 + ], + [ + 561, + 512, + 512 + ], + [ + 527, + 512, + 512 + ], + [ + 577, + 512, + 512 + ], + [ + 629, + 512, + 512 + ], + [ + 623, + 512, + 512 + ], + [ + 549, + 512, + 512 + ], + [ + 563, + 512, + 512 + ], + [ + 573, + 512, + 512 + ], + [ + 621, + 512, + 512 + ], + [ + 671, + 512, + 512 + ], + [ + 625, + 512, + 512 + ], + [ + 577, + 512, + 512 + ], + [ + 617, + 512, + 512 + ], + [ + 597, + 512, + 512 + ], + [ + 637, + 512, + 512 + ], + [ + 605, + 512, + 512 + ], + [ + 625, + 512, + 512 + ], + [ + 655, + 512, + 512 + ], + [ + 577, + 512, + 512 + ], + [ + 857, + 512, + 512 + ], + [ + 609, + 512, + 512 + ], + [ + 505, + 512, + 512 + ], + [ + 509, + 512, + 512 + ], + [ + 641, + 512, + 512 + ], + [ + 641, + 512, + 512 + ], + [ + 697, + 512, + 512 + ], + [ + 553, + 512, + 512 + ], + [ + 525, + 512, + 512 + ], + [ + 737, + 512, + 512 + ], + [ + 537, + 512, + 512 + ], + [ + 630, + 512, + 512 + ], + [ + 693, + 512, + 512 + ], + [ + 417, + 512, + 512 + ], + [ + 651, + 512, + 512 + ], + [ + 678, + 512, + 512 + ], + [ + 585, + 512, + 512 + ], + [ + 609, + 512, + 512 + ], + [ + 597, + 512, + 512 + ], + [ + 449, + 512, + 512 + ], + [ + 381, + 512, + 512 + ], + [ + 697, + 512, + 512 + ], + [ + 612, + 512, + 512 + ], + [ + 541, + 512, + 512 + ], + [ + 533, + 512, + 512 + ], + [ + 659, + 512, + 512 + ], + [ + 541, + 512, + 512 + ], + [ + 601, + 512, + 512 + ], + [ + 617, + 512, + 512 + ], + [ + 515, + 512, + 512 + ], + [ + 621, + 512, + 512 + ], + [ + 751, + 512, + 512 + ], + [ + 705, + 512, + 512 + ], + [ + 573, + 512, + 512 + ], + [ + 693, + 512, + 512 + ], + [ + 483, + 512, + 512 + ], + [ + 583, + 512, + 512 + ], + [ + 621, + 512, + 512 + ], + [ + 613, + 512, + 512 + ], + [ + 589, + 512, + 512 + ], + [ + 513, + 512, + 512 + ], + [ + 609, + 512, + 512 + ], + [ + 954, + 512, + 512 + ], + [ + 986, + 512, + 512 + ], + [ + 513, + 512, + 512 + ], + [ + 629, + 512, + 512 + ], + [ + 621, + 512, + 512 + ], + [ + 513, + 512, + 512 + ], + [ + 553, + 512, + 512 + ], + [ + 609, + 512, + 512 + ], + [ + 442, + 512, + 512 + ], + [ + 460, + 512, + 512 + ], + [ + 673, + 512, + 512 + ], + [ + 512, + 512, + 512 + ], + [ + 562, + 512, + 512 + ], + [ + 496, + 512, + 512 + ], + [ + 629, + 512, + 512 + ], + [ + 836, + 512, + 512 + ], + [ + 913, + 512, + 512 + ], + [ + 465, + 512, + 512 + ], + [ + 469, + 512, + 512 + ], + [ + 635, + 512, + 512 + ], + [ + 506, + 512, + 512 + ], + [ + 549, + 512, + 512 + ], + [ + 507, + 512, + 512 + ], + [ + 881, + 512, + 512 + ], + [ + 521, + 512, + 512 + ], + [ + 548, + 512, + 512 + ], + [ + 893, + 512, + 512 + ], + [ + 939, + 512, + 512 + ], + [ + 927, + 512, + 512 + ], + [ + 905, + 512, + 512 + ], + [ + 589, + 512, + 512 + ], + [ + 493, + 512, + 512 + ], + [ + 533, + 512, + 512 + ], + [ + 769, + 512, + 512 + ], + [ + 606, + 512, + 512 + ], + [ + 541, + 512, + 512 + ], + [ + 893, + 512, + 512 + ], + [ + 881, + 512, + 512 + ], + [ + 1201, + 512, + 512 + ], + [ + 1266, + 512, + 512 + ], + [ + 533, + 512, + 512 + ], + [ + 877, + 512, + 512 + ], + [ + 945, + 512, + 512 + ], + [ + 891, + 512, + 512 + ], + [ + 850, + 512, + 512 + ], + [ + 697, + 512, + 512 + ], + [ + 602, + 512, + 512 + ], + [ + 829, + 512, + 512 + ], + [ + 893, + 512, + 512 + ], + [ + 829, + 512, + 512 + ], + [ + 832, + 512, + 512 + ], + [ + 877, + 512, + 512 + ], + [ + 933, + 512, + 512 + ], + [ + 710, + 512, + 512 + ], + [ + 1012, + 512, + 512 + ], + [ + 1049, + 512, + 512 + ], + [ + 877, + 512, + 512 + ], + [ + 600, + 512, + 512 + ], + [ + 853, + 512, + 512 + ], + [ + 541, + 512, + 512 + ], + [ + 557, + 512, + 512 + ], + [ + 506, + 512, + 512 + ], + [ + 552, + 512, + 512 + ], + [ + 1360, + 512, + 512 + ], + [ + 865, + 512, + 512 + ], + [ + 717, + 512, + 512 + ], + [ + 851, + 512, + 512 + ], + [ + 1297, + 512, + 512 + ], + [ + 858, + 512, + 512 + ], + [ + 930, + 512, + 512 + ], + [ + 847, + 512, + 512 + ], + [ + 745, + 512, + 512 + ], + [ + 825, + 512, + 512 + ], + [ + 634, + 512, + 512 + ], + [ + 853, + 512, + 512 + ], + [ + 917, + 512, + 512 + ], + [ + 863, + 512, + 512 + ], + [ + 765, + 512, + 512 + ], + [ + 913, + 512, + 512 + ], + [ + 977, + 512, + 512 + ], + [ + 793, + 512, + 512 + ], + [ + 858, + 512, + 512 + ], + [ + 809, + 512, + 512 + ], + [ + 721, + 512, + 512 + ], + [ + 915, + 512, + 512 + ], + [ + 674, + 512, + 512 + ], + [ + 936, + 512, + 512 + ], + [ + 849, + 512, + 512 + ], + [ + 881, + 512, + 512 + ], + [ + 857, + 512, + 512 + ], + [ + 834, + 512, + 512 + ], + [ + 815, + 512, + 512 + ], + [ + 953, + 512, + 512 + ], + [ + 985, + 512, + 512 + ], + [ + 831, + 512, + 512 + ], + [ + 700, + 512, + 512 + ], + [ + 784, + 512, + 512 + ], + [ + 881, + 512, + 512 + ], + [ + 854, + 512, + 512 + ], + [ + 829, + 512, + 512 + ], + [ + 994, + 512, + 512 + ], + [ + 846, + 512, + 512 + ], + [ + 853, + 512, + 512 + ], + [ + 663, + 512, + 512 + ], + [ + 785, + 512, + 512 + ], + [ + 990, + 512, + 512 + ], + [ + 901, + 512, + 512 + ], + [ + 593, + 512, + 512 + ], + [ + 563, + 512, + 512 + ], + [ + 513, + 512, + 512 + ], + [ + 617, + 512, + 512 + ], + [ + 993, + 512, + 512 + ], + [ + 962, + 512, + 512 + ], + [ + 738, + 512, + 512 + ], + [ + 721, + 512, + 512 + ], + [ + 897, + 512, + 512 + ], + [ + 819, + 512, + 512 + ], + [ + 745, + 512, + 512 + ], + [ + 857, + 512, + 512 + ], + [ + 989, + 512, + 512 + ], + [ + 881, + 512, + 512 + ], + [ + 901, + 512, + 512 + ], + [ + 479, + 512, + 512 + ], + [ + 508, + 512, + 512 + ], + [ + 650, + 512, + 512 + ], + [ + 689, + 512, + 512 + ], + [ + 549, + 512, + 512 + ], + [ + 528, + 512, + 512 + ], + [ + 509, + 512, + 512 + ], + [ + 974, + 512, + 512 + ], + [ + 621, + 512, + 512 + ], + [ + 887, + 512, + 512 + ], + [ + 607, + 512, + 512 + ], + [ + 473, + 512, + 512 + ], + [ + 873, + 512, + 512 + ], + [ + 528, + 512, + 512 + ], + [ + 931, + 512, + 512 + ], + [ + 876, + 512, + 512 + ], + [ + 881, + 512, + 512 + ], + [ + 685, + 512, + 512 + ], + [ + 552, + 512, + 512 + ], + [ + 896, + 512, + 512 + ], + [ + 883, + 512, + 512 + ], + [ + 900, + 512, + 512 + ], + [ + 837, + 512, + 512 + ], + [ + 873, + 512, + 512 + ], + [ + 865, + 512, + 512 + ], + [ + 565, + 512, + 512 + ], + [ + 1009, + 512, + 512 + ], + [ + 951, + 512, + 512 + ], + [ + 842, + 512, + 512 + ], + [ + 557, + 512, + 512 + ], + [ + 905, + 512, + 512 + ], + [ + 898, + 512, + 512 + ], + [ + 481, + 512, + 512 + ], + [ + 937, + 512, + 512 + ], + [ + 804, + 512, + 512 + ], + [ + 463, + 512, + 512 + ], + [ + 936, + 512, + 512 + ], + [ + 889, + 512, + 512 + ], + [ + 918, + 512, + 512 + ], + [ + 913, + 512, + 512 + ], + [ + 392, + 512, + 512 + ], + [ + 857, + 512, + 512 + ], + [ + 888, + 512, + 512 + ], + [ + 849, + 512, + 512 + ], + [ + 898, + 512, + 512 + ], + [ + 543, + 512, + 512 + ], + [ + 819, + 512, + 512 + ], + [ + 916, + 512, + 512 + ], + [ + 826, + 512, + 512 + ], + [ + 859, + 512, + 512 + ], + [ + 834, + 512, + 512 + ], + [ + 537, + 512, + 512 + ], + [ + 790, + 512, + 512 + ], + [ + 857, + 512, + 512 + ], + [ + 913, + 512, + 512 + ], + [ + 904, + 512, + 512 + ], + [ + 843, + 512, + 512 + ], + [ + 819, + 512, + 512 + ], + [ + 882, + 512, + 512 + ], + [ + 546, + 512, + 512 + ], + [ + 737, + 512, + 512 + ], + [ + 855, + 512, + 512 + ], + [ + 997, + 512, + 512 + ], + [ + 488, + 512, + 512 + ], + [ + 818, + 512, + 512 + ], + [ + 805, + 512, + 512 + ], + [ + 937, + 512, + 512 + ], + [ + 749, + 512, + 512 + ], + [ + 946, + 512, + 512 + ], + [ + 849, + 512, + 512 + ], + [ + 983, + 512, + 512 + ], + [ + 977, + 512, + 512 + ], + [ + 925, + 512, + 512 + ], + [ + 768, + 512, + 512 + ], + [ + 851, + 512, + 512 + ], + [ + 982, + 512, + 512 + ], + [ + 898, + 512, + 512 + ], + [ + 946, + 512, + 512 + ], + [ + 773, + 512, + 512 + ], + [ + 857, + 512, + 512 + ], + [ + 1008, + 512, + 512 + ], + [ + 931, + 512, + 512 + ], + [ + 877, + 512, + 512 + ], + [ + 882, + 512, + 512 + ], + [ + 889, + 512, + 512 + ], + [ + 951, + 512, + 512 + ], + [ + 521, + 512, + 512 + ], + [ + 881, + 512, + 512 + ], + [ + 602, + 512, + 512 + ], + [ + 889, + 512, + 512 + ], + [ + 888, + 512, + 512 + ], + [ + 1004, + 512, + 512 + ], + [ + 989, + 512, + 512 + ], + [ + 903, + 512, + 512 + ], + [ + 777, + 512, + 512 + ], + [ + 886, + 512, + 512 + ], + [ + 936, + 512, + 512 + ], + [ + 525, + 512, + 512 + ], + [ + 881, + 512, + 512 + ], + [ + 985, + 512, + 512 + ], + [ + 894, + 512, + 512 + ], + [ + 1016, + 512, + 512 + ], + [ + 979, + 512, + 512 + ], + [ + 626, + 512, + 512 + ], + [ + 876, + 512, + 512 + ], + [ + 917, + 512, + 512 + ], + [ + 897, + 512, + 512 + ], + [ + 791, + 512, + 512 + ], + [ + 903, + 512, + 512 + ], + [ + 865, + 512, + 512 + ], + [ + 877, + 512, + 512 + ], + [ + 485, + 512, + 512 + ], + [ + 481, + 512, + 512 + ], + [ + 453, + 512, + 512 + ], + [ + 889, + 512, + 512 + ], + [ + 553, + 512, + 512 + ], + [ + 910, + 512, + 512 + ], + [ + 1004, + 512, + 512 + ], + [ + 856, + 512, + 512 + ], + [ + 891, + 512, + 512 + ], + [ + 532, + 512, + 512 + ], + [ + 597, + 512, + 512 + ], + [ + 793, + 512, + 512 + ], + [ + 913, + 512, + 512 + ], + [ + 491, + 512, + 512 + ], + [ + 463, + 512, + 512 + ], + [ + 868, + 512, + 512 + ], + [ + 675, + 512, + 512 + ], + [ + 827, + 512, + 512 + ], + [ + 825, + 512, + 512 + ], + [ + 979, + 512, + 512 + ], + [ + 856, + 512, + 512 + ], + [ + 820, + 512, + 512 + ], + [ + 902, + 512, + 512 + ], + [ + 921, + 512, + 512 + ], + [ + 910, + 512, + 512 + ], + [ + 833, + 512, + 512 + ], + [ + 489, + 512, + 512 + ], + [ + 588, + 512, + 512 + ], + [ + 888, + 512, + 512 + ], + [ + 504, + 512, + 512 + ], + [ + 529, + 512, + 512 + ], + [ + 1013, + 512, + 512 + ], + [ + 849, + 512, + 512 + ], + [ + 450, + 512, + 512 + ], + [ + 889, + 512, + 512 + ], + [ + 575, + 512, + 512 + ], + [ + 941, + 512, + 512 + ], + [ + 855, + 512, + 512 + ], + [ + 863, + 512, + 512 + ], + [ + 882, + 512, + 512 + ], + [ + 931, + 512, + 512 + ], + [ + 496, + 512, + 512 + ], + [ + 484, + 512, + 512 + ], + [ + 929, + 512, + 512 + ], + [ + 830, + 512, + 512 + ], + [ + 898, + 512, + 512 + ], + [ + 596, + 512, + 512 + ], + [ + 1063, + 512, + 512 + ], + [ + 909, + 512, + 512 + ], + [ + 897, + 512, + 512 + ], + [ + 898, + 512, + 512 + ], + [ + 868, + 512, + 512 + ], + [ + 789, + 512, + 512 + ], + [ + 551, + 512, + 512 + ], + [ + 914, + 512, + 512 + ], + [ + 901, + 512, + 512 + ], + [ + 907, + 512, + 512 + ], + [ + 965, + 512, + 512 + ], + [ + 791, + 512, + 512 + ], + [ + 852, + 512, + 512 + ], + [ + 1007, + 512, + 512 + ], + [ + 778, + 512, + 512 + ], + [ + 914, + 512, + 512 + ], + [ + 916, + 512, + 512 + ], + [ + 934, + 512, + 512 + ], + [ + 848, + 512, + 512 + ], + [ + 461, + 512, + 512 + ], + [ + 553, + 512, + 512 + ], + [ + 557, + 512, + 512 + ], + [ + 521, + 512, + 512 + ], + [ + 982, + 512, + 512 + ], + [ + 839, + 512, + 512 + ], + [ + 819, + 512, + 512 + ], + [ + 865, + 512, + 512 + ], + [ + 792, + 512, + 512 + ], + [ + 455, + 512, + 512 + ], + [ + 830, + 512, + 512 + ], + [ + 575, + 512, + 512 + ], + [ + 904, + 512, + 512 + ], + [ + 975, + 512, + 512 + ], + [ + 849, + 512, + 512 + ], + [ + 541, + 512, + 512 + ], + [ + 807, + 512, + 512 + ], + [ + 881, + 512, + 512 + ], + [ + 551, + 512, + 512 + ], + [ + 865, + 512, + 512 + ], + [ + 845, + 512, + 512 + ], + [ + 559, + 512, + 512 + ], + [ + 881, + 512, + 512 + ], + [ + 916, + 512, + 512 + ], + [ + 917, + 512, + 512 + ], + [ + 891, + 512, + 512 + ], + [ + 897, + 512, + 512 + ], + [ + 947, + 512, + 512 + ], + [ + 461, + 512, + 512 + ], + [ + 850, + 512, + 512 + ], + [ + 896, + 512, + 512 + ], + [ + 478, + 512, + 512 + ], + [ + 899, + 512, + 512 + ], + [ + 586, + 512, + 512 + ], + [ + 489, + 512, + 512 + ], + [ + 528, + 512, + 512 + ], + [ + 842, + 512, + 512 + ], + [ + 575, + 512, + 512 + ], + [ + 884, + 512, + 512 + ], + [ + 881, + 512, + 512 + ], + [ + 447, + 512, + 512 + ], + [ + 957, + 512, + 512 + ], + [ + 562, + 512, + 512 + ], + [ + 764, + 512, + 512 + ], + [ + 509, + 512, + 512 + ], + [ + 884, + 512, + 512 + ], + [ + 562, + 512, + 512 + ], + [ + 880, + 512, + 512 + ], + [ + 533, + 512, + 512 + ], + [ + 517, + 512, + 512 + ], + [ + 541, + 512, + 512 + ], + [ + 517, + 512, + 512 + ], + [ + 934, + 512, + 512 + ], + [ + 585, + 512, + 512 + ], + [ + 437, + 512, + 512 + ], + [ + 793, + 512, + 512 + ], + [ + 629, + 512, + 512 + ], + [ + 1010, + 512, + 512 + ], + [ + 798, + 512, + 512 + ], + [ + 791, + 512, + 512 + ], + [ + 468, + 512, + 512 + ], + [ + 808, + 512, + 512 + ], + [ + 922, + 512, + 512 + ], + [ + 879, + 512, + 512 + ], + [ + 900, + 512, + 512 + ], + [ + 562, + 512, + 512 + ], + [ + 886, + 512, + 512 + ], + [ + 764, + 512, + 512 + ], + [ + 947, + 512, + 512 + ], + [ + 891, + 512, + 512 + ], + [ + 468, + 512, + 512 + ], + [ + 897, + 512, + 512 + ], + [ + 962, + 512, + 512 + ], + [ + 901, + 512, + 512 + ], + [ + 801, + 512, + 512 + ], + [ + 929, + 512, + 512 + ], + [ + 929, + 512, + 512 + ], + [ + 942, + 512, + 512 + ], + [ + 461, + 512, + 512 + ], + [ + 506, + 512, + 512 + ], + [ + 1049, + 512, + 512 + ], + [ + 829, + 512, + 512 + ], + [ + 471, + 512, + 512 + ], + [ + 874, + 512, + 512 + ], + [ + 957, + 512, + 512 + ], + [ + 893, + 512, + 512 + ], + [ + 826, + 512, + 512 + ], + [ + 678, + 512, + 512 + ], + [ + 940, + 512, + 512 + ], + [ + 514, + 512, + 512 + ], + [ + 530, + 512, + 512 + ], + [ + 517, + 512, + 512 + ], + [ + 1005, + 512, + 512 + ], + [ + 869, + 512, + 512 + ], + [ + 1034, + 512, + 512 + ], + [ + 537, + 512, + 512 + ], + [ + 1281, + 512, + 512 + ], + [ + 405, + 512, + 512 + ], + [ + 365, + 512, + 512 + ], + [ + 614, + 512, + 512 + ], + [ + 432, + 512, + 512 + ], + [ + 529, + 512, + 512 + ], + [ + 573, + 512, + 512 + ], + [ + 496, + 512, + 512 + ], + [ + 500, + 512, + 512 + ], + [ + 969, + 512, + 512 + ], + [ + 965, + 512, + 512 + ], + [ + 864, + 512, + 512 + ], + [ + 496, + 512, + 512 + ], + [ + 585, + 512, + 512 + ], + [ + 906, + 512, + 512 + ], + [ + 956, + 512, + 512 + ], + [ + 573, + 512, + 512 + ], + [ + 549, + 512, + 512 + ], + [ + 789, + 512, + 512 + ], + [ + 791, + 512, + 512 + ], + [ + 481, + 512, + 512 + ], + [ + 965, + 512, + 512 + ], + [ + 967, + 512, + 512 + ], + [ + 425, + 512, + 512 + ], + [ + 629, + 512, + 512 + ], + [ + 945, + 512, + 512 + ], + [ + 420, + 512, + 512 + ], + [ + 437, + 512, + 512 + ], + [ + 657, + 512, + 512 + ], + [ + 477, + 512, + 512 + ], + [ + 1001, + 512, + 512 + ], + [ + 506, + 512, + 512 + ], + [ + 515, + 512, + 512 + ], + [ + 437, + 512, + 512 + ], + [ + 411, + 512, + 512 + ], + [ + 587, + 512, + 512 + ], + [ + 849, + 512, + 512 + ], + [ + 950, + 512, + 512 + ], + [ + 611, + 512, + 512 + ], + [ + 933, + 512, + 512 + ], + [ + 853, + 512, + 512 + ], + [ + 447, + 512, + 512 + ], + [ + 561, + 512, + 512 + ], + [ + 512, + 512, + 512 + ], + [ + 876, + 512, + 512 + ], + [ + 550, + 512, + 512 + ], + [ + 482, + 512, + 512 + ], + [ + 484, + 512, + 512 + ], + [ + 552, + 512, + 512 + ], + [ + 518, + 512, + 512 + ], + [ + 562, + 512, + 512 + ], + [ + 869, + 512, + 512 + ], + [ + 491, + 512, + 512 + ], + [ + 791, + 512, + 512 + ], + [ + 961, + 512, + 512 + ], + [ + 560, + 512, + 512 + ], + [ + 925, + 512, + 512 + ], + [ + 468, + 512, + 512 + ], + [ + 1296, + 512, + 512 + ], + [ + 799, + 512, + 512 + ], + [ + 930, + 512, + 512 + ], + [ + 850, + 512, + 512 + ], + [ + 916, + 512, + 512 + ], + [ + 891, + 512, + 512 + ], + [ + 914, + 512, + 512 + ], + [ + 928, + 512, + 512 + ], + [ + 988, + 512, + 512 + ], + [ + 836, + 512, + 512 + ], + [ + 587, + 512, + 512 + ], + [ + 550, + 512, + 512 + ], + [ + 477, + 512, + 512 + ], + [ + 495, + 512, + 512 + ], + [ + 512, + 512, + 512 + ], + [ + 533, + 512, + 512 + ], + [ + 586, + 512, + 512 + ], + [ + 549, + 512, + 512 + ], + [ + 512, + 512, + 512 + ], + [ + 932, + 512, + 512 + ], + [ + 497, + 512, + 512 + ], + [ + 907, + 512, + 512 + ], + [ + 841, + 512, + 512 + ], + [ + 469, + 512, + 512 + ], + [ + 793, + 512, + 512 + ], + [ + 460, + 512, + 512 + ], + [ + 899, + 512, + 512 + ], + [ + 534, + 512, + 512 + ], + [ + 933, + 512, + 512 + ], + [ + 519, + 512, + 512 + ], + [ + 895, + 512, + 512 + ], + [ + 495, + 512, + 512 + ], + [ + 950, + 512, + 512 + ], + [ + 401, + 512, + 512 + ], + [ + 517, + 512, + 512 + ], + [ + 934, + 512, + 512 + ], + [ + 553, + 512, + 512 + ], + [ + 519, + 512, + 512 + ], + [ + 889, + 512, + 512 + ], + [ + 487, + 512, + 512 + ], + [ + 557, + 512, + 512 + ], + [ + 843, + 512, + 512 + ], + [ + 457, + 512, + 512 + ], + [ + 478, + 512, + 512 + ], + [ + 509, + 512, + 512 + ], + [ + 813, + 512, + 512 + ], + [ + 509, + 512, + 512 + ], + [ + 930, + 512, + 512 + ], + [ + 483, + 512, + 512 + ], + [ + 917, + 512, + 512 + ], + [ + 593, + 512, + 512 + ], + [ + 516, + 512, + 512 + ], + [ + 685, + 512, + 512 + ], + [ + 547, + 512, + 512 + ], + [ + 1066, + 512, + 512 + ], + [ + 741, + 512, + 512 + ], + [ + 486, + 512, + 512 + ], + [ + 481, + 512, + 512 + ], + [ + 502, + 512, + 512 + ], + [ + 613, + 512, + 512 + ], + [ + 925, + 512, + 512 + ], + [ + 994, + 512, + 512 + ], + [ + 985, + 512, + 512 + ], + [ + 860, + 512, + 512 + ], + [ + 949, + 512, + 512 + ], + [ + 855, + 512, + 512 + ], + [ + 542, + 512, + 512 + ], + [ + 956, + 512, + 512 + ], + [ + 477, + 512, + 512 + ], + [ + 917, + 512, + 512 + ], + [ + 504, + 512, + 512 + ], + [ + 945, + 512, + 512 + ], + [ + 529, + 512, + 512 + ], + [ + 865, + 512, + 512 + ], + [ + 466, + 512, + 512 + ], + [ + 523, + 512, + 512 + ], + [ + 789, + 512, + 512 + ], + [ + 885, + 512, + 512 + ], + [ + 902, + 512, + 512 + ], + [ + 848, + 512, + 512 + ], + [ + 931, + 512, + 512 + ], + [ + 518, + 512, + 512 + ], + [ + 897, + 512, + 512 + ], + [ + 665, + 512, + 512 + ], + [ + 517, + 512, + 512 + ], + [ + 469, + 512, + 512 + ], + [ + 430, + 512, + 512 + ], + [ + 469, + 512, + 512 + ], + [ + 901, + 512, + 512 + ], + [ + 431, + 512, + 512 + ], + [ + 377, + 512, + 512 + ], + [ + 813, + 512, + 512 + ], + [ + 890, + 512, + 512 + ], + [ + 886, + 512, + 512 + ], + [ + 953, + 512, + 512 + ], + [ + 589, + 512, + 512 + ], + [ + 869, + 512, + 512 + ], + [ + 953, + 512, + 512 + ], + [ + 782, + 512, + 512 + ], + [ + 803, + 512, + 512 + ], + [ + 568, + 512, + 512 + ], + [ + 525, + 512, + 512 + ], + [ + 926, + 512, + 512 + ], + [ + 869, + 512, + 512 + ], + [ + 881, + 512, + 512 + ], + [ + 615, + 512, + 512 + ], + [ + 957, + 512, + 512 + ], + [ + 397, + 512, + 512 + ], + [ + 537, + 512, + 512 + ], + [ + 857, + 512, + 512 + ], + [ + 857, + 512, + 512 + ], + [ + 465, + 512, + 512 + ], + [ + 548, + 512, + 512 + ], + [ + 661, + 512, + 512 + ], + [ + 597, + 512, + 512 + ], + [ + 949, + 512, + 512 + ], + [ + 969, + 512, + 512 + ], + [ + 415, + 512, + 512 + ], + [ + 559, + 512, + 512 + ], + [ + 528, + 512, + 512 + ], + [ + 753, + 512, + 512 + ], + [ + 598, + 512, + 512 + ], + [ + 461, + 512, + 512 + ], + [ + 889, + 512, + 512 + ], + [ + 645, + 512, + 512 + ], + [ + 981, + 512, + 512 + ], + [ + 889, + 512, + 512 + ], + [ + 514, + 512, + 512 + ], + [ + 929, + 512, + 512 + ], + [ + 597, + 512, + 512 + ], + [ + 952, + 512, + 512 + ], + [ + 1001, + 512, + 512 + ], + [ + 965, + 512, + 512 + ], + [ + 601, + 512, + 512 + ], + [ + 990, + 512, + 512 + ], + [ + 880, + 512, + 512 + ], + [ + 563, + 512, + 512 + ], + [ + 926, + 512, + 512 + ], + [ + 933, + 512, + 512 + ], + [ + 861, + 512, + 512 + ], + [ + 849, + 512, + 512 + ], + [ + 955, + 512, + 512 + ], + [ + 921, + 512, + 512 + ], + [ + 1021, + 512, + 512 + ], + [ + 930, + 512, + 512 + ], + [ + 585, + 512, + 512 + ], + [ + 876, + 512, + 512 + ], + [ + 534, + 512, + 512 + ], + [ + 859, + 512, + 512 + ], + [ + 673, + 512, + 512 + ], + [ + 912, + 512, + 512 + ], + [ + 533, + 512, + 512 + ], + [ + 893, + 512, + 512 + ], + [ + 930, + 512, + 512 + ], + [ + 460, + 512, + 512 + ], + [ + 886, + 512, + 512 + ], + [ + 439, + 512, + 512 + ], + [ + 856, + 512, + 512 + ], + [ + 982, + 512, + 512 + ], + [ + 526, + 512, + 512 + ], + [ + 844, + 512, + 512 + ], + [ + 484, + 512, + 512 + ], + [ + 593, + 512, + 512 + ], + [ + 441, + 512, + 512 + ], + [ + 530, + 512, + 512 + ], + [ + 981, + 512, + 512 + ], + [ + 446, + 512, + 512 + ], + [ + 545, + 512, + 512 + ], + [ + 861, + 512, + 512 + ], + [ + 953, + 512, + 512 + ], + [ + 501, + 512, + 512 + ], + [ + 564, + 512, + 512 + ], + [ + 981, + 512, + 512 + ], + [ + 459, + 512, + 512 + ], + [ + 681, + 512, + 512 + ], + [ + 897, + 512, + 512 + ], + [ + 669, + 512, + 512 + ], + [ + 789, + 512, + 512 + ], + [ + 505, + 512, + 512 + ], + [ + 561, + 512, + 512 + ], + [ + 890, + 512, + 512 + ], + [ + 861, + 512, + 512 + ], + [ + 649, + 512, + 512 + ], + [ + 485, + 512, + 512 + ], + [ + 923, + 512, + 512 + ], + [ + 448, + 512, + 512 + ], + [ + 1181, + 512, + 512 + ], + [ + 965, + 512, + 512 + ], + [ + 905, + 512, + 512 + ], + [ + 560, + 512, + 512 + ], + [ + 517, + 512, + 512 + ], + [ + 905, + 512, + 512 + ], + [ + 833, + 512, + 512 + ], + [ + 849, + 512, + 512 + ], + [ + 838, + 512, + 512 + ], + [ + 468, + 512, + 512 + ], + [ + 929, + 512, + 512 + ], + [ + 554, + 512, + 512 + ], + [ + 559, + 512, + 512 + ], + [ + 513, + 512, + 512 + ], + [ + 921, + 512, + 512 + ], + [ + 533, + 512, + 512 + ], + [ + 467, + 512, + 512 + ], + [ + 843, + 512, + 512 + ], + [ + 780, + 512, + 512 + ], + [ + 1044, + 512, + 512 + ], + [ + 965, + 512, + 512 + ], + [ + 858, + 512, + 512 + ], + [ + 997, + 512, + 512 + ], + [ + 984, + 512, + 512 + ], + [ + 663, + 512, + 512 + ], + [ + 562, + 512, + 512 + ], + [ + 924, + 512, + 512 + ], + [ + 883, + 512, + 512 + ], + [ + 982, + 512, + 512 + ], + [ + 902, + 512, + 512 + ], + [ + 507, + 512, + 512 + ], + [ + 909, + 512, + 512 + ], + [ + 905, + 512, + 512 + ], + [ + 747, + 512, + 512 + ], + [ + 621, + 512, + 512 + ], + [ + 409, + 512, + 512 + ], + [ + 513, + 512, + 512 + ], + [ + 505, + 512, + 512 + ], + [ + 813, + 512, + 512 + ], + [ + 838, + 512, + 512 + ], + [ + 554, + 512, + 512 + ], + [ + 852, + 512, + 512 + ], + [ + 418, + 512, + 512 + ], + [ + 562, + 512, + 512 + ], + [ + 761, + 512, + 512 + ], + [ + 430, + 512, + 512 + ], + [ + 829, + 512, + 512 + ], + [ + 493, + 512, + 512 + ], + [ + 526, + 512, + 512 + ], + [ + 533, + 512, + 512 + ], + [ + 799, + 512, + 512 + ], + [ + 510, + 512, + 512 + ], + [ + 941, + 512, + 512 + ], + [ + 525, + 512, + 512 + ], + [ + 903, + 512, + 512 + ], + [ + 1177, + 512, + 512 + ], + [ + 677, + 512, + 512 + ], + [ + 981, + 512, + 512 + ], + [ + 866, + 512, + 512 + ], + [ + 721, + 512, + 512 + ], + [ + 901, + 512, + 512 + ], + [ + 873, + 512, + 512 + ], + [ + 603, + 512, + 512 + ], + [ + 456, + 512, + 512 + ], + [ + 507, + 512, + 512 + ], + [ + 418, + 512, + 512 + ], + [ + 461, + 512, + 512 + ], + [ + 475, + 512, + 512 + ], + [ + 852, + 512, + 512 + ], + [ + 709, + 512, + 512 + ], + [ + 849, + 512, + 512 + ], + [ + 926, + 512, + 512 + ], + [ + 540, + 512, + 512 + ], + [ + 896, + 512, + 512 + ], + [ + 861, + 512, + 512 + ], + [ + 954, + 512, + 512 + ], + [ + 849, + 512, + 512 + ], + [ + 493, + 512, + 512 + ], + [ + 949, + 512, + 512 + ], + [ + 921, + 512, + 512 + ], + [ + 652, + 512, + 512 + ], + [ + 915, + 512, + 512 + ], + [ + 638, + 512, + 512 + ], + [ + 821, + 512, + 512 + ], + [ + 593, + 512, + 512 + ], + [ + 948, + 512, + 512 + ], + [ + 886, + 512, + 512 + ], + [ + 649, + 512, + 512 + ], + [ + 513, + 512, + 512 + ], + [ + 845, + 512, + 512 + ], + [ + 721, + 512, + 512 + ], + [ + 564, + 512, + 512 + ], + [ + 424, + 512, + 512 + ], + [ + 557, + 512, + 512 + ], + [ + 419, + 512, + 512 + ], + [ + 864, + 512, + 512 + ], + [ + 484, + 512, + 512 + ], + [ + 529, + 512, + 512 + ], + [ + 509, + 512, + 512 + ], + [ + 501, + 512, + 512 + ], + [ + 485, + 512, + 512 + ], + [ + 512, + 512, + 512 + ], + [ + 475, + 512, + 512 + ], + [ + 1001, + 512, + 512 + ], + [ + 896, + 512, + 512 + ], + [ + 470, + 512, + 512 + ], + [ + 877, + 512, + 512 + ], + [ + 942, + 512, + 512 + ], + [ + 953, + 512, + 512 + ], + [ + 570, + 512, + 512 + ], + [ + 893, + 512, + 512 + ], + [ + 988, + 512, + 512 + ], + [ + 785, + 512, + 512 + ], + [ + 596, + 512, + 512 + ], + [ + 538, + 512, + 512 + ], + [ + 1050, + 512, + 512 + ], + [ + 559, + 512, + 512 + ], + [ + 512, + 512, + 512 + ], + [ + 1074, + 512, + 512 + ], + [ + 505, + 512, + 512 + ], + [ + 825, + 512, + 512 + ], + [ + 426, + 512, + 512 + ], + [ + 573, + 512, + 512 + ], + [ + 914, + 512, + 512 + ], + [ + 564, + 512, + 512 + ], + [ + 578, + 512, + 512 + ], + [ + 442, + 512, + 512 + ], + [ + 870, + 512, + 512 + ], + [ + 488, + 512, + 512 + ], + [ + 1100, + 512, + 512 + ], + [ + 620, + 512, + 512 + ], + [ + 482, + 512, + 512 + ], + [ + 590, + 512, + 512 + ], + [ + 463, + 512, + 512 + ], + [ + 836, + 512, + 512 + ], + [ + 914, + 512, + 512 + ], + [ + 580, + 512, + 512 + ], + [ + 935, + 512, + 512 + ], + [ + 493, + 512, + 512 + ], + [ + 516, + 512, + 512 + ], + [ + 494, + 512, + 512 + ], + [ + 605, + 512, + 512 + ], + [ + 446, + 512, + 512 + ], + [ + 945, + 512, + 512 + ], + [ + 473, + 512, + 512 + ], + [ + 836, + 512, + 512 + ], + [ + 471, + 512, + 512 + ], + [ + 563, + 512, + 512 + ], + [ + 877, + 512, + 512 + ], + [ + 647, + 512, + 512 + ], + [ + 970, + 512, + 512 + ], + [ + 515, + 512, + 512 + ], + [ + 582, + 512, + 512 + ], + [ + 849, + 512, + 512 + ], + [ + 489, + 512, + 512 + ], + [ + 529, + 512, + 512 + ], + [ + 865, + 512, + 512 + ], + [ + 937, + 512, + 512 + ], + [ + 505, + 512, + 512 + ], + [ + 526, + 512, + 512 + ], + [ + 379, + 512, + 512 + ], + [ + 362, + 512, + 512 + ], + [ + 573, + 512, + 512 + ], + [ + 473, + 512, + 512 + ], + [ + 552, + 512, + 512 + ], + [ + 394, + 512, + 512 + ], + [ + 657, + 512, + 512 + ], + [ + 596, + 512, + 512 + ], + [ + 530, + 512, + 512 + ], + [ + 542, + 512, + 512 + ], + [ + 814, + 512, + 512 + ], + [ + 633, + 512, + 512 + ], + [ + 539, + 512, + 512 + ], + [ + 634, + 512, + 512 + ], + [ + 570, + 512, + 512 + ], + [ + 893, + 512, + 512 + ], + [ + 801, + 512, + 512 + ], + [ + 893, + 512, + 512 + ], + [ + 564, + 512, + 512 + ], + [ + 859, + 512, + 512 + ], + [ + 617, + 512, + 512 + ], + [ + 890, + 512, + 512 + ], + [ + 653, + 512, + 512 + ], + [ + 477, + 512, + 512 + ], + [ + 507, + 512, + 512 + ], + [ + 529, + 512, + 512 + ], + [ + 577, + 512, + 512 + ], + [ + 632, + 512, + 512 + ], + [ + 426, + 512, + 512 + ], + [ + 641, + 512, + 512 + ], + [ + 509, + 512, + 512 + ], + [ + 481, + 512, + 512 + ], + [ + 913, + 512, + 512 + ], + [ + 560, + 512, + 512 + ], + [ + 936, + 512, + 512 + ], + [ + 997, + 512, + 512 + ], + [ + 637, + 512, + 512 + ], + [ + 545, + 512, + 512 + ], + [ + 525, + 512, + 512 + ], + [ + 385, + 512, + 512 + ], + [ + 620, + 512, + 512 + ], + [ + 482, + 512, + 512 + ], + [ + 553, + 512, + 512 + ], + [ + 902, + 512, + 512 + ], + [ + 709, + 512, + 512 + ], + [ + 528, + 512, + 512 + ], + [ + 901, + 512, + 512 + ], + [ + 685, + 512, + 512 + ], + [ + 1007, + 512, + 512 + ], + [ + 415, + 512, + 512 + ], + [ + 601, + 512, + 512 + ], + [ + 618, + 512, + 512 + ], + [ + 885, + 512, + 512 + ], + [ + 561, + 512, + 512 + ], + [ + 833, + 512, + 512 + ], + [ + 497, + 512, + 512 + ], + [ + 581, + 512, + 512 + ], + [ + 559, + 512, + 512 + ], + [ + 505, + 512, + 512 + ], + [ + 871, + 512, + 512 + ], + [ + 628, + 512, + 512 + ], + [ + 594, + 512, + 512 + ], + [ + 609, + 512, + 512 + ], + [ + 493, + 512, + 512 + ], + [ + 601, + 512, + 512 + ], + [ + 541, + 512, + 512 + ], + [ + 493, + 512, + 512 + ], + [ + 545, + 512, + 512 + ], + [ + 553, + 512, + 512 + ], + [ + 511, + 512, + 512 + ], + [ + 613, + 512, + 512 + ], + [ + 509, + 512, + 512 + ], + [ + 582, + 512, + 512 + ], + [ + 596, + 512, + 512 + ], + [ + 341, + 512, + 512 + ], + [ + 425, + 512, + 512 + ], + [ + 990, + 512, + 512 + ], + [ + 630, + 512, + 512 + ], + [ + 496, + 512, + 512 + ], + [ + 497, + 512, + 512 + ], + [ + 501, + 512, + 512 + ], + [ + 573, + 512, + 512 + ], + [ + 473, + 512, + 512 + ], + [ + 449, + 512, + 512 + ], + [ + 506, + 512, + 512 + ], + [ + 533, + 512, + 512 + ], + [ + 521, + 512, + 512 + ], + [ + 438, + 512, + 512 + ], + [ + 689, + 512, + 512 + ], + [ + 537, + 512, + 512 + ], + [ + 633, + 512, + 512 + ], + [ + 449, + 512, + 512 + ], + [ + 608, + 512, + 512 + ], + [ + 934, + 512, + 512 + ], + [ + 542, + 512, + 512 + ], + [ + 453, + 512, + 512 + ], + [ + 565, + 512, + 512 + ], + [ + 601, + 512, + 512 + ], + [ + 883, + 512, + 512 + ], + [ + 513, + 512, + 512 + ], + [ + 505, + 512, + 512 + ], + [ + 585, + 512, + 512 + ], + [ + 533, + 512, + 512 + ], + [ + 509, + 512, + 512 + ], + [ + 457, + 512, + 512 + ], + [ + 555, + 512, + 512 + ], + [ + 452, + 512, + 512 + ], + [ + 425, + 512, + 512 + ], + [ + 560, + 512, + 512 + ], + [ + 831, + 512, + 512 + ], + [ + 497, + 512, + 512 + ], + [ + 593, + 512, + 512 + ], + [ + 625, + 512, + 512 + ], + [ + 537, + 512, + 512 + ], + [ + 487, + 512, + 512 + ], + [ + 508, + 512, + 512 + ], + [ + 993, + 512, + 512 + ], + [ + 601, + 512, + 512 + ], + [ + 506, + 512, + 512 + ], + [ + 596, + 512, + 512 + ], + [ + 617, + 512, + 512 + ], + [ + 431, + 512, + 512 + ], + [ + 485, + 512, + 512 + ], + [ + 555, + 512, + 512 + ], + [ + 511, + 512, + 512 + ], + [ + 516, + 512, + 512 + ], + [ + 492, + 512, + 512 + ], + [ + 525, + 512, + 512 + ], + [ + 511, + 512, + 512 + ], + [ + 575, + 512, + 512 + ], + [ + 815, + 512, + 512 + ], + [ + 429, + 512, + 512 + ], + [ + 589, + 512, + 512 + ], + [ + 521, + 512, + 512 + ], + [ + 461, + 512, + 512 + ], + [ + 449, + 512, + 512 + ], + [ + 559, + 512, + 512 + ], + [ + 676, + 512, + 512 + ], + [ + 461, + 512, + 512 + ], + [ + 493, + 512, + 512 + ], + [ + 435, + 512, + 512 + ], + [ + 573, + 512, + 512 + ], + [ + 820, + 512, + 512 + ], + [ + 921, + 512, + 512 + ], + [ + 897, + 512, + 512 + ], + [ + 833, + 512, + 512 + ], + [ + 865, + 512, + 512 + ], + [ + 988, + 512, + 512 + ], + [ + 467, + 512, + 512 + ], + [ + 605, + 512, + 512 + ], + [ + 877, + 512, + 512 + ], + [ + 460, + 512, + 512 + ], + [ + 796, + 512, + 512 + ], + [ + 965, + 512, + 512 + ], + [ + 535, + 512, + 512 + ], + [ + 527, + 512, + 512 + ], + [ + 453, + 512, + 512 + ], + [ + 463, + 512, + 512 + ], + [ + 645, + 512, + 512 + ], + [ + 723, + 512, + 512 + ], + [ + 1023, + 512, + 512 + ], + [ + 567, + 512, + 707 + ], + [ + 820, + 512, + 512 + ], + [ + 641, + 512, + 512 + ], + [ + 921, + 512, + 512 + ], + [ + 897, + 512, + 512 + ], + [ + 1177, + 512, + 512 + ], + [ + 509, + 512, + 512 + ], + [ + 864, + 512, + 512 + ], + [ + 718, + 512, + 512 + ], + [ + 965, + 512, + 512 + ], + [ + 942, + 512, + 512 + ], + [ + 466, + 512, + 512 + ], + [ + 537, + 512, + 512 + ], + [ + 546, + 512, + 512 + ], + [ + 999, + 512, + 512 + ], + [ + 421, + 512, + 512 + ], + [ + 651, + 512, + 512 + ], + [ + 403, + 512, + 512 + ], + [ + 575, + 512, + 512 + ], + [ + 581, + 512, + 512 + ], + [ + 842, + 512, + 512 + ], + [ + 546, + 512, + 512 + ], + [ + 912, + 512, + 512 + ], + [ + 550, + 512, + 512 + ], + [ + 499, + 512, + 512 + ], + [ + 918, + 512, + 512 + ], + [ + 793, + 512, + 512 + ], + [ + 1034, + 512, + 512 + ], + [ + 595, + 512, + 512 + ], + [ + 420, + 512, + 512 + ], + [ + 890, + 512, + 512 + ], + [ + 522, + 512, + 512 + ], + [ + 594, + 512, + 512 + ], + [ + 628, + 512, + 512 + ], + [ + 400, + 512, + 512 + ], + [ + 949, + 512, + 512 + ], + [ + 504, + 512, + 512 + ], + [ + 471, + 512, + 512 + ], + [ + 913, + 512, + 512 + ], + [ + 434, + 512, + 512 + ], + [ + 868, + 512, + 512 + ], + [ + 580, + 512, + 512 + ], + [ + 505, + 512, + 512 + ], + [ + 490, + 512, + 512 + ], + [ + 380, + 512, + 512 + ], + [ + 698, + 512, + 512 + ], + [ + 409, + 512, + 512 + ], + [ + 553, + 512, + 512 + ], + [ + 557, + 512, + 512 + ], + [ + 885, + 512, + 512 + ], + [ + 411, + 512, + 512 + ], + [ + 481, + 512, + 512 + ], + [ + 462, + 512, + 512 + ], + [ + 453, + 512, + 512 + ], + [ + 438, + 512, + 512 + ], + [ + 859, + 512, + 512 + ], + [ + 938, + 512, + 512 + ], + [ + 554, + 512, + 512 + ], + [ + 981, + 512, + 512 + ], + [ + 470, + 512, + 512 + ], + [ + 500, + 512, + 512 + ], + [ + 446, + 512, + 512 + ], + [ + 443, + 512, + 512 + ], + [ + 1050, + 512, + 512 + ], + [ + 929, + 512, + 512 + ], + [ + 465, + 512, + 512 + ], + [ + 795, + 512, + 512 + ], + [ + 581, + 512, + 512 + ], + [ + 889, + 512, + 512 + ], + [ + 511, + 512, + 512 + ], + [ + 505, + 512, + 512 + ], + [ + 581, + 512, + 512 + ], + [ + 580, + 512, + 512 + ], + [ + 521, + 512, + 512 + ], + [ + 808, + 512, + 512 + ], + [ + 776, + 512, + 512 + ], + [ + 929, + 512, + 512 + ], + [ + 961, + 512, + 512 + ], + [ + 800, + 512, + 512 + ], + [ + 955, + 512, + 512 + ], + [ + 431, + 512, + 512 + ], + [ + 585, + 512, + 512 + ], + [ + 525, + 512, + 512 + ], + [ + 547, + 512, + 512 + ], + [ + 457, + 512, + 512 + ], + [ + 893, + 512, + 512 + ], + [ + 505, + 512, + 512 + ], + [ + 441, + 512, + 512 + ], + [ + 630, + 512, + 512 + ], + [ + 463, + 512, + 512 + ], + [ + 544, + 512, + 512 + ], + [ + 504, + 512, + 512 + ], + [ + 468, + 512, + 512 + ], + [ + 1010, + 512, + 512 + ], + [ + 505, + 512, + 512 + ], + [ + 451, + 512, + 512 + ], + [ + 525, + 512, + 512 + ], + [ + 586, + 512, + 512 + ], + [ + 557, + 512, + 512 + ], + [ + 457, + 512, + 512 + ], + [ + 486, + 512, + 512 + ], + [ + 957, + 512, + 512 + ], + [ + 432, + 512, + 512 + ], + [ + 553, + 512, + 512 + ], + [ + 810, + 512, + 512 + ], + [ + 873, + 512, + 512 + ], + [ + 480, + 512, + 512 + ], + [ + 821, + 512, + 512 + ], + [ + 537, + 512, + 512 + ], + [ + 905, + 512, + 512 + ], + [ + 953, + 512, + 512 + ], + [ + 559, + 512, + 512 + ], + [ + 857, + 512, + 512 + ], + [ + 552, + 512, + 512 + ], + [ + 510, + 512, + 512 + ], + [ + 427, + 512, + 512 + ], + [ + 1099, + 512, + 512 + ], + [ + 607, + 512, + 512 + ], + [ + 419, + 512, + 512 + ], + [ + 534, + 512, + 512 + ], + [ + 523, + 512, + 512 + ], + [ + 521, + 512, + 512 + ], + [ + 769, + 512, + 512 + ], + [ + 453, + 512, + 512 + ], + [ + 431, + 512, + 512 + ], + [ + 521, + 512, + 512 + ], + [ + 521, + 512, + 512 + ], + [ + 462, + 512, + 512 + ], + [ + 490, + 512, + 512 + ], + [ + 461, + 512, + 512 + ], + [ + 639, + 512, + 512 + ], + [ + 904, + 512, + 512 + ], + [ + 921, + 512, + 512 + ], + [ + 477, + 512, + 512 + ], + [ + 471, + 512, + 512 + ], + [ + 499, + 512, + 512 + ], + [ + 419, + 512, + 512 + ], + [ + 678, + 512, + 512 + ], + [ + 449, + 512, + 512 + ], + [ + 553, + 512, + 512 + ], + [ + 542, + 512, + 512 + ], + [ + 481, + 512, + 512 + ], + [ + 705, + 512, + 512 + ], + [ + 585, + 512, + 512 + ], + [ + 605, + 512, + 512 + ], + [ + 523, + 512, + 512 + ], + [ + 425, + 512, + 512 + ], + [ + 417, + 512, + 512 + ], + [ + 847, + 512, + 512 + ], + [ + 420, + 512, + 512 + ], + [ + 441, + 512, + 512 + ], + [ + 893, + 512, + 512 + ], + [ + 989, + 512, + 512 + ], + [ + 918, + 512, + 512 + ], + [ + 937, + 512, + 512 + ], + [ + 519, + 512, + 512 + ], + [ + 502, + 512, + 512 + ], + [ + 925, + 512, + 512 + ], + [ + 516, + 512, + 512 + ], + [ + 942, + 512, + 512 + ], + [ + 574, + 512, + 512 + ], + [ + 476, + 512, + 512 + ], + [ + 518, + 512, + 512 + ], + [ + 991, + 512, + 512 + ], + [ + 500, + 512, + 512 + ], + [ + 411, + 512, + 512 + ], + [ + 597, + 512, + 512 + ], + [ + 608, + 512, + 512 + ], + [ + 490, + 512, + 512 + ], + [ + 394, + 512, + 512 + ], + [ + 841, + 512, + 512 + ], + [ + 962, + 512, + 512 + ], + [ + 806, + 512, + 512 + ], + [ + 485, + 512, + 512 + ], + [ + 559, + 512, + 512 + ], + [ + 577, + 512, + 512 + ], + [ + 912, + 512, + 512 + ], + [ + 917, + 512, + 512 + ], + [ + 528, + 512, + 512 + ], + [ + 999, + 512, + 512 + ], + [ + 589, + 512, + 512 + ], + [ + 469, + 512, + 512 + ], + [ + 1002, + 512, + 512 + ], + [ + 1013, + 512, + 512 + ], + [ + 905, + 512, + 512 + ], + [ + 465, + 512, + 512 + ], + [ + 953, + 512, + 512 + ], + [ + 525, + 512, + 512 + ], + [ + 504, + 512, + 512 + ], + [ + 597, + 512, + 512 + ], + [ + 827, + 512, + 512 + ], + [ + 569, + 512, + 512 + ], + [ + 497, + 512, + 512 + ], + [ + 471, + 512, + 512 + ], + [ + 493, + 512, + 512 + ], + [ + 465, + 512, + 512 + ], + [ + 636, + 512, + 512 + ], + [ + 468, + 512, + 512 + ], + [ + 479, + 512, + 512 + ], + [ + 501, + 512, + 512 + ], + [ + 456, + 512, + 512 + ], + [ + 443, + 512, + 512 + ], + [ + 504, + 512, + 512 + ], + [ + 529, + 512, + 512 + ], + [ + 538, + 512, + 512 + ], + [ + 389, + 512, + 512 + ], + [ + 515, + 512, + 512 + ], + [ + 575, + 512, + 512 + ], + [ + 457, + 512, + 512 + ], + [ + 497, + 512, + 512 + ], + [ + 524, + 512, + 512 + ], + [ + 509, + 512, + 512 + ], + [ + 588, + 512, + 512 + ], + [ + 831, + 512, + 512 + ], + [ + 504, + 512, + 512 + ], + [ + 500, + 512, + 512 + ], + [ + 785, + 512, + 512 + ], + [ + 535, + 512, + 512 + ], + [ + 417, + 512, + 512 + ], + [ + 393, + 512, + 512 + ], + [ + 520, + 512, + 512 + ], + [ + 425, + 512, + 512 + ], + [ + 401, + 512, + 512 + ], + [ + 425, + 512, + 512 + ], + [ + 427, + 512, + 512 + ], + [ + 437, + 512, + 512 + ], + [ + 395, + 512, + 512 + ], + [ + 469, + 512, + 512 + ], + [ + 469, + 512, + 512 + ], + [ + 449, + 512, + 512 + ], + [ + 345, + 512, + 512 + ], + [ + 506, + 512, + 512 + ], + [ + 391, + 512, + 512 + ], + [ + 458, + 512, + 512 + ], + [ + 333, + 512, + 512 + ], + [ + 632, + 512, + 512 + ], + [ + 635, + 512, + 512 + ], + [ + 605, + 512, + 512 + ], + [ + 417, + 512, + 512 + ], + [ + 579, + 512, + 512 + ], + [ + 493, + 512, + 512 + ], + [ + 467, + 512, + 512 + ], + [ + 502, + 512, + 512 + ], + [ + 798, + 512, + 512 + ], + [ + 447, + 512, + 512 + ], + [ + 346, + 512, + 512 + ], + [ + 531, + 512, + 512 + ], + [ + 435, + 512, + 512 + ], + [ + 606, + 512, + 512 + ], + [ + 327, + 512, + 512 + ], + [ + 397, + 512, + 512 + ], + [ + 465, + 512, + 512 + ], + [ + 469, + 512, + 512 + ], + [ + 447, + 512, + 512 + ], + [ + 858, + 512, + 512 + ], + [ + 569, + 512, + 512 + ], + [ + 473, + 512, + 512 + ], + [ + 841, + 512, + 512 + ], + [ + 921, + 512, + 512 + ], + [ + 805, + 512, + 512 + ], + [ + 773, + 512, + 512 + ], + [ + 332, + 512, + 512 + ], + [ + 873, + 512, + 512 + ], + [ + 823, + 512, + 512 + ], + [ + 842, + 512, + 512 + ], + [ + 415, + 512, + 512 + ], + [ + 555, + 512, + 512 + ], + [ + 441, + 512, + 512 + ], + [ + 438, + 512, + 512 + ], + [ + 430, + 512, + 512 + ], + [ + 391, + 512, + 512 + ], + [ + 501, + 512, + 512 + ], + [ + 590, + 512, + 512 + ], + [ + 851, + 512, + 512 + ], + [ + 501, + 512, + 512 + ], + [ + 373, + 512, + 512 + ], + [ + 476, + 512, + 512 + ], + [ + 473, + 512, + 512 + ], + [ + 379, + 512, + 512 + ], + [ + 821, + 512, + 512 + ], + [ + 551, + 512, + 512 + ], + [ + 405, + 512, + 512 + ], + [ + 456, + 512, + 512 + ], + [ + 561, + 512, + 512 + ], + [ + 493, + 512, + 512 + ], + [ + 435, + 512, + 512 + ], + [ + 391, + 512, + 512 + ], + [ + 361, + 512, + 512 + ], + [ + 443, + 512, + 512 + ], + [ + 495, + 512, + 512 + ], + [ + 447, + 512, + 512 + ], + [ + 441, + 512, + 512 + ], + [ + 393, + 512, + 512 + ], + [ + 423, + 512, + 512 + ], + [ + 573, + 512, + 512 + ], + [ + 471, + 512, + 512 + ], + [ + 412, + 512, + 512 + ], + [ + 481, + 512, + 512 + ], + [ + 447, + 512, + 512 + ], + [ + 441, + 512, + 512 + ], + [ + 423, + 512, + 512 + ], + [ + 511, + 512, + 512 + ], + [ + 765, + 512, + 512 + ], + [ + 551, + 512, + 512 + ], + [ + 457, + 512, + 512 + ], + [ + 379, + 512, + 512 + ], + [ + 481, + 512, + 512 + ], + [ + 369, + 512, + 512 + ], + [ + 389, + 512, + 512 + ], + [ + 407, + 512, + 512 + ], + [ + 447, + 512, + 512 + ], + [ + 452, + 512, + 512 + ], + [ + 441, + 512, + 512 + ], + [ + 425, + 512, + 512 + ], + [ + 466, + 512, + 512 + ], + [ + 433, + 512, + 512 + ], + [ + 500, + 512, + 512 + ], + [ + 441, + 512, + 512 + ], + [ + 470, + 512, + 512 + ], + [ + 423, + 512, + 512 + ], + [ + 515, + 512, + 512 + ], + [ + 525, + 512, + 512 + ], + [ + 491, + 512, + 512 + ], + [ + 458, + 512, + 512 + ], + [ + 407, + 512, + 512 + ], + [ + 719, + 512, + 512 + ], + [ + 485, + 512, + 512 + ], + [ + 417, + 512, + 512 + ], + [ + 359, + 512, + 512 + ], + [ + 559, + 512, + 512 + ], + [ + 495, + 512, + 512 + ], + [ + 453, + 512, + 512 + ], + [ + 510, + 512, + 512 + ], + [ + 392, + 512, + 512 + ], + [ + 333, + 512, + 512 + ], + [ + 736, + 512, + 512 + ], + [ + 539, + 512, + 512 + ], + [ + 543, + 512, + 512 + ], + [ + 443, + 512, + 512 + ], + [ + 417, + 512, + 512 + ], + [ + 467, + 512, + 512 + ], + [ + 497, + 512, + 512 + ], + [ + 407, + 512, + 512 + ], + [ + 459, + 512, + 512 + ], + [ + 632, + 512, + 512 + ], + [ + 437, + 512, + 512 + ], + [ + 485, + 512, + 512 + ], + [ + 539, + 512, + 512 + ], + [ + 482, + 512, + 512 + ], + [ + 541, + 512, + 512 + ], + [ + 458, + 512, + 512 + ], + [ + 423, + 512, + 512 + ], + [ + 371, + 512, + 512 + ], + [ + 621, + 512, + 512 + ], + [ + 801, + 512, + 512 + ], + [ + 635, + 512, + 512 + ], + [ + 466, + 512, + 512 + ], + [ + 435, + 512, + 512 + ], + [ + 477, + 512, + 512 + ], + [ + 499, + 512, + 512 + ], + [ + 565, + 512, + 512 + ], + [ + 784, + 512, + 512 + ], + [ + 966, + 512, + 512 + ], + [ + 605, + 512, + 512 + ], + [ + 506, + 512, + 512 + ], + [ + 505, + 512, + 512 + ], + [ + 351, + 512, + 512 + ], + [ + 512, + 512, + 512 + ], + [ + 521, + 512, + 512 + ], + [ + 441, + 512, + 512 + ], + [ + 857, + 512, + 512 + ], + [ + 417, + 512, + 512 + ], + [ + 431, + 512, + 512 + ], + [ + 425, + 512, + 512 + ], + [ + 491, + 512, + 512 + ], + [ + 433, + 512, + 512 + ], + [ + 815, + 512, + 512 + ], + [ + 412, + 512, + 512 + ], + [ + 546, + 512, + 512 + ], + [ + 521, + 512, + 512 + ], + [ + 579, + 512, + 512 + ], + [ + 481, + 512, + 512 + ], + [ + 564, + 512, + 512 + ], + [ + 493, + 512, + 512 + ], + [ + 430, + 512, + 512 + ], + [ + 568, + 512, + 512 + ], + [ + 455, + 512, + 512 + ], + [ + 844, + 512, + 512 + ], + [ + 654, + 512, + 512 + ], + [ + 645, + 512, + 512 + ], + [ + 471, + 512, + 512 + ], + [ + 481, + 512, + 512 + ], + [ + 767, + 512, + 512 + ], + [ + 519, + 512, + 512 + ], + [ + 467, + 512, + 512 + ], + [ + 458, + 512, + 512 + ], + [ + 571, + 512, + 512 + ], + [ + 898, + 512, + 512 + ], + [ + 415, + 512, + 512 + ], + [ + 463, + 512, + 512 + ], + [ + 485, + 512, + 512 + ], + [ + 565, + 512, + 512 + ], + [ + 587, + 512, + 512 + ], + [ + 597, + 512, + 512 + ], + [ + 502, + 512, + 512 + ], + [ + 423, + 512, + 512 + ], + [ + 518, + 512, + 512 + ], + [ + 798, + 512, + 512 + ], + [ + 441, + 512, + 512 + ], + [ + 399, + 512, + 512 + ], + [ + 463, + 512, + 512 + ], + [ + 574, + 512, + 512 + ], + [ + 389, + 512, + 512 + ], + [ + 554, + 512, + 512 + ], + [ + 631, + 512, + 512 + ], + [ + 461, + 512, + 512 + ], + [ + 584, + 512, + 512 + ], + [ + 438, + 512, + 512 + ], + [ + 609, + 512, + 512 + ], + [ + 607, + 512, + 512 + ], + [ + 712, + 512, + 512 + ], + [ + 355, + 512, + 512 + ], + [ + 549, + 512, + 512 + ], + [ + 443, + 512, + 512 + ], + [ + 461, + 512, + 512 + ], + [ + 447, + 512, + 512 + ], + [ + 327, + 512, + 512 + ], + [ + 418, + 512, + 512 + ], + [ + 367, + 512, + 512 + ], + [ + 345, + 512, + 512 + ], + [ + 341, + 512, + 512 + ], + [ + 378, + 512, + 512 + ], + [ + 538, + 512, + 512 + ], + [ + 485, + 512, + 512 + ], + [ + 360, + 512, + 512 + ], + [ + 474, + 512, + 512 + ], + [ + 403, + 512, + 512 + ], + [ + 449, + 512, + 512 + ], + [ + 513, + 512, + 512 + ], + [ + 404, + 512, + 512 + ], + [ + 396, + 512, + 512 + ], + [ + 401, + 512, + 512 + ], + [ + 423, + 512, + 512 + ], + [ + 433, + 512, + 512 + ], + [ + 424, + 512, + 512 + ], + [ + 452, + 512, + 512 + ], + [ + 531, + 512, + 512 + ], + [ + 435, + 512, + 512 + ], + [ + 815, + 512, + 512 + ], + [ + 785, + 512, + 512 + ], + [ + 746, + 512, + 512 + ], + [ + 569, + 512, + 512 + ], + [ + 442, + 512, + 512 + ], + [ + 450, + 512, + 512 + ], + [ + 475, + 512, + 512 + ], + [ + 484, + 512, + 512 + ], + [ + 539, + 512, + 512 + ], + [ + 493, + 512, + 512 + ], + [ + 358, + 512, + 512 + ], + [ + 844, + 512, + 512 + ], + [ + 843, + 512, + 512 + ], + [ + 581, + 512, + 512 + ], + [ + 734, + 512, + 512 + ], + [ + 435, + 512, + 512 + ], + [ + 422, + 512, + 512 + ], + [ + 417, + 512, + 512 + ], + [ + 431, + 512, + 512 + ], + [ + 336, + 512, + 512 + ], + [ + 768, + 512, + 512 + ], + [ + 463, + 512, + 512 + ], + [ + 565, + 512, + 512 + ], + [ + 606, + 512, + 512 + ], + [ + 756, + 512, + 512 + ], + [ + 812, + 512, + 512 + ], + [ + 475, + 512, + 512 + ], + [ + 606, + 512, + 512 + ], + [ + 363, + 512, + 512 + ], + [ + 929, + 512, + 512 + ], + [ + 1105, + 512, + 512 + ], + [ + 507, + 512, + 512 + ], + [ + 327, + 512, + 512 + ], + [ + 533, + 512, + 512 + ], + [ + 429, + 512, + 512 + ], + [ + 527, + 512, + 512 + ], + [ + 411, + 512, + 512 + ], + [ + 499, + 512, + 512 + ], + [ + 800, + 512, + 512 + ], + [ + 419, + 512, + 512 + ], + [ + 490, + 512, + 512 + ], + [ + 407, + 512, + 512 + ], + [ + 401, + 512, + 512 + ], + [ + 397, + 512, + 512 + ], + [ + 396, + 512, + 512 + ], + [ + 497, + 512, + 512 + ], + [ + 837, + 512, + 512 + ], + [ + 363, + 512, + 512 + ], + [ + 367, + 512, + 512 + ], + [ + 497, + 512, + 512 + ], + [ + 545, + 512, + 512 + ], + [ + 390, + 512, + 512 + ], + [ + 378, + 512, + 512 + ], + [ + 465, + 512, + 512 + ], + [ + 863, + 512, + 512 + ], + [ + 940, + 512, + 512 + ], + [ + 407, + 512, + 512 + ], + [ + 485, + 512, + 512 + ], + [ + 422, + 512, + 512 + ], + [ + 789, + 512, + 512 + ], + [ + 807, + 512, + 512 + ], + [ + 909, + 512, + 512 + ], + [ + 961, + 512, + 512 + ], + [ + 921, + 512, + 512 + ], + [ + 441, + 512, + 512 + ], + [ + 433, + 512, + 512 + ], + [ + 553, + 512, + 512 + ], + [ + 853, + 512, + 512 + ], + [ + 712, + 512, + 512 + ], + [ + 363, + 512, + 512 + ], + [ + 407, + 512, + 512 + ], + [ + 553, + 512, + 512 + ], + [ + 469, + 512, + 512 + ], + [ + 911, + 512, + 512 + ], + [ + 541, + 512, + 512 + ], + [ + 415, + 512, + 512 + ], + [ + 494, + 512, + 512 + ], + [ + 332, + 512, + 512 + ], + [ + 581, + 512, + 512 + ], + [ + 685, + 512, + 512 + ], + [ + 472, + 512, + 512 + ], + [ + 474, + 512, + 512 + ], + [ + 447, + 512, + 512 + ], + [ + 554, + 512, + 512 + ], + [ + 505, + 512, + 512 + ], + [ + 319, + 512, + 512 + ], + [ + 551, + 512, + 512 + ], + [ + 432, + 512, + 512 + ], + [ + 454, + 512, + 512 + ], + [ + 834, + 512, + 512 + ], + [ + 395, + 512, + 512 + ], + [ + 421, + 512, + 512 + ], + [ + 579, + 512, + 512 + ], + [ + 858, + 512, + 512 + ], + [ + 401, + 512, + 512 + ], + [ + 537, + 512, + 512 + ], + [ + 469, + 512, + 512 + ], + [ + 965, + 512, + 512 + ], + [ + 727, + 512, + 512 + ], + [ + 411, + 512, + 512 + ], + [ + 407, + 512, + 512 + ], + [ + 634, + 512, + 512 + ], + [ + 386, + 512, + 512 + ], + [ + 569, + 512, + 512 + ], + [ + 362, + 512, + 512 + ], + [ + 461, + 512, + 512 + ], + [ + 773, + 512, + 512 + ], + [ + 358, + 512, + 512 + ], + [ + 388, + 512, + 512 + ], + [ + 369, + 512, + 512 + ], + [ + 509, + 512, + 512 + ], + [ + 376, + 512, + 512 + ], + [ + 437, + 512, + 512 + ], + [ + 485, + 512, + 512 + ], + [ + 669, + 512, + 512 + ], + [ + 470, + 512, + 512 + ], + [ + 457, + 512, + 512 + ], + [ + 531, + 512, + 512 + ], + [ + 489, + 512, + 512 + ], + [ + 402, + 512, + 512 + ], + [ + 448, + 512, + 512 + ], + [ + 473, + 512, + 512 + ], + [ + 454, + 512, + 512 + ], + [ + 445, + 512, + 512 + ], + [ + 460, + 512, + 512 + ], + [ + 473, + 512, + 512 + ], + [ + 381, + 512, + 512 + ], + [ + 389, + 512, + 512 + ], + [ + 545, + 512, + 512 + ], + [ + 485, + 512, + 512 + ], + [ + 561, + 512, + 512 + ], + [ + 673, + 512, + 512 + ], + [ + 865, + 512, + 512 + ], + [ + 437, + 512, + 512 + ], + [ + 405, + 512, + 512 + ], + [ + 557, + 512, + 512 + ], + [ + 893, + 512, + 512 + ], + [ + 510, + 512, + 512 + ], + [ + 972, + 512, + 512 + ], + [ + 501, + 512, + 512 + ], + [ + 905, + 512, + 512 + ], + [ + 565, + 512, + 512 + ], + [ + 944, + 512, + 512 + ], + [ + 513, + 512, + 512 + ], + [ + 501, + 512, + 512 + ], + [ + 556, + 512, + 512 + ], + [ + 505, + 512, + 512 + ], + [ + 417, + 512, + 512 + ], + [ + 393, + 512, + 512 + ], + [ + 646, + 512, + 512 + ], + [ + 566, + 512, + 512 + ], + [ + 489, + 512, + 512 + ], + [ + 465, + 512, + 512 + ], + [ + 804, + 512, + 512 + ], + [ + 469, + 512, + 512 + ], + [ + 1022, + 512, + 512 + ], + [ + 473, + 512, + 512 + ], + [ + 409, + 512, + 512 + ], + [ + 537, + 512, + 512 + ], + [ + 928, + 512, + 512 + ], + [ + 816, + 512, + 512 + ], + [ + 453, + 512, + 512 + ], + [ + 441, + 512, + 512 + ], + [ + 453, + 512, + 512 + ], + [ + 517, + 512, + 512 + ], + [ + 473, + 512, + 512 + ], + [ + 547, + 512, + 512 + ], + [ + 537, + 512, + 512 + ], + [ + 513, + 512, + 512 + ], + [ + 629, + 512, + 512 + ], + [ + 565, + 512, + 512 + ], + [ + 513, + 512, + 512 + ], + [ + 476, + 512, + 512 + ], + [ + 553, + 512, + 512 + ], + [ + 442, + 512, + 512 + ], + [ + 448, + 512, + 512 + ], + [ + 498, + 512, + 512 + ], + [ + 512, + 512, + 512 + ], + [ + 819, + 512, + 512 + ], + [ + 726, + 512, + 512 + ], + [ + 505, + 512, + 512 + ], + [ + 487, + 512, + 512 + ], + [ + 519, + 512, + 512 + ], + [ + 465, + 512, + 512 + ], + [ + 469, + 512, + 512 + ], + [ + 635, + 512, + 512 + ], + [ + 500, + 512, + 512 + ], + [ + 549, + 512, + 512 + ], + [ + 397, + 512, + 512 + ], + [ + 765, + 512, + 512 + ], + [ + 786, + 512, + 512 + ], + [ + 919, + 512, + 512 + ], + [ + 529, + 512, + 512 + ], + [ + 504, + 512, + 512 + ], + [ + 559, + 512, + 512 + ], + [ + 537, + 512, + 512 + ], + [ + 589, + 512, + 512 + ], + [ + 454, + 512, + 512 + ], + [ + 454, + 512, + 512 + ], + [ + 777, + 512, + 512 + ], + [ + 606, + 512, + 512 + ], + [ + 731, + 512, + 512 + ], + [ + 553, + 512, + 512 + ], + [ + 557, + 512, + 512 + ], + [ + 628, + 512, + 512 + ], + [ + 511, + 512, + 512 + ], + [ + 533, + 512, + 512 + ], + [ + 481, + 512, + 512 + ], + [ + 640, + 512, + 512 + ], + [ + 500, + 512, + 512 + ], + [ + 494, + 512, + 512 + ], + [ + 587, + 512, + 512 + ], + [ + 446, + 512, + 512 + ], + [ + 506, + 512, + 512 + ], + [ + 505, + 512, + 512 + ], + [ + 536, + 512, + 512 + ], + [ + 476, + 512, + 512 + ], + [ + 573, + 512, + 512 + ], + [ + 539, + 512, + 512 + ], + [ + 466, + 512, + 512 + ], + [ + 657, + 512, + 512 + ], + [ + 653, + 512, + 512 + ], + [ + 573, + 512, + 512 + ], + [ + 435, + 512, + 512 + ], + [ + 423, + 512, + 512 + ], + [ + 541, + 512, + 512 + ], + [ + 557, + 512, + 512 + ], + [ + 506, + 512, + 512 + ], + [ + 552, + 512, + 512 + ], + [ + 512, + 512, + 512 + ], + [ + 539, + 512, + 512 + ], + [ + 561, + 512, + 512 + ], + [ + 480, + 512, + 512 + ], + [ + 496, + 512, + 512 + ], + [ + 501, + 512, + 512 + ], + [ + 596, + 512, + 512 + ], + [ + 454, + 512, + 512 + ], + [ + 429, + 512, + 512 + ], + [ + 458, + 512, + 512 + ], + [ + 432, + 512, + 512 + ], + [ + 493, + 512, + 512 + ], + [ + 564, + 512, + 512 + ], + [ + 518, + 512, + 512 + ], + [ + 555, + 512, + 512 + ], + [ + 493, + 512, + 512 + ], + [ + 585, + 512, + 512 + ], + [ + 456, + 512, + 512 + ], + [ + 486, + 512, + 512 + ], + [ + 445, + 512, + 512 + ], + [ + 618, + 512, + 512 + ], + [ + 585, + 512, + 512 + ], + [ + 522, + 512, + 512 + ], + [ + 548, + 512, + 512 + ], + [ + 529, + 512, + 512 + ], + [ + 517, + 512, + 512 + ], + [ + 533, + 512, + 512 + ], + [ + 457, + 512, + 512 + ], + [ + 582, + 512, + 512 + ], + [ + 557, + 512, + 512 + ], + [ + 607, + 512, + 512 + ], + [ + 427, + 512, + 512 + ], + [ + 481, + 512, + 512 + ], + [ + 474, + 512, + 512 + ], + [ + 517, + 512, + 512 + ], + [ + 446, + 512, + 512 + ], + [ + 535, + 512, + 512 + ], + [ + 557, + 512, + 512 + ], + [ + 475, + 512, + 512 + ], + [ + 525, + 512, + 512 + ], + [ + 618, + 512, + 512 + ], + [ + 529, + 512, + 512 + ], + [ + 536, + 512, + 512 + ], + [ + 529, + 512, + 512 + ], + [ + 593, + 512, + 512 + ], + [ + 555, + 512, + 512 + ], + [ + 513, + 512, + 512 + ], + [ + 617, + 512, + 512 + ], + [ + 650, + 512, + 512 + ], + [ + 518, + 512, + 512 + ], + [ + 550, + 512, + 512 + ], + [ + 503, + 512, + 512 + ], + [ + 505, + 512, + 512 + ], + [ + 420, + 512, + 512 + ], + [ + 482, + 512, + 512 + ], + [ + 509, + 512, + 512 + ], + [ + 540, + 512, + 512 + ], + [ + 531, + 512, + 512 + ], + [ + 491, + 512, + 512 + ], + [ + 740, + 512, + 512 + ], + [ + 508, + 512, + 512 + ], + [ + 422, + 512, + 512 + ], + [ + 525, + 512, + 512 + ], + [ + 549, + 512, + 512 + ], + [ + 532, + 512, + 512 + ], + [ + 403, + 512, + 512 + ], + [ + 592, + 512, + 512 + ], + [ + 1057, + 512, + 512 + ], + [ + 807, + 512, + 512 + ], + [ + 997, + 512, + 512 + ], + [ + 889, + 512, + 512 + ], + [ + 873, + 512, + 512 + ], + [ + 939, + 512, + 512 + ], + [ + 908, + 512, + 512 + ], + [ + 966, + 512, + 512 + ], + [ + 915, + 512, + 512 + ], + [ + 933, + 512, + 512 + ], + [ + 950, + 512, + 512 + ], + [ + 880, + 512, + 512 + ], + [ + 874, + 512, + 512 + ], + [ + 834, + 512, + 512 + ], + [ + 1085, + 512, + 512 + ], + [ + 896, + 512, + 512 + ], + [ + 943, + 512, + 512 + ], + [ + 1065, + 512, + 512 + ], + [ + 905, + 512, + 512 + ], + [ + 803, + 512, + 512 + ], + [ + 928, + 512, + 512 + ], + [ + 868, + 512, + 512 + ], + [ + 811, + 512, + 512 + ], + [ + 876, + 512, + 512 + ], + [ + 578, + 512, + 512 + ], + [ + 916, + 512, + 512 + ], + [ + 463, + 512, + 512 + ], + [ + 568, + 512, + 512 + ], + [ + 1225, + 512, + 512 + ], + [ + 892, + 512, + 512 + ], + [ + 1013, + 512, + 512 + ], + [ + 392, + 512, + 512 + ], + [ + 889, + 512, + 512 + ], + [ + 575, + 512, + 512 + ], + [ + 896, + 512, + 512 + ], + [ + 913, + 512, + 512 + ], + [ + 889, + 512, + 512 + ], + [ + 884, + 512, + 512 + ], + [ + 956, + 512, + 512 + ], + [ + 853, + 512, + 512 + ], + [ + 755, + 512, + 512 + ], + [ + 883, + 512, + 512 + ], + [ + 889, + 512, + 512 + ], + [ + 758, + 512, + 512 + ], + [ + 845, + 512, + 512 + ], + [ + 934, + 512, + 512 + ], + [ + 934, + 512, + 512 + ], + [ + 875, + 512, + 512 + ], + [ + 866, + 512, + 512 + ], + [ + 995, + 512, + 512 + ], + [ + 998, + 512, + 512 + ], + [ + 746, + 512, + 512 + ], + [ + 906, + 512, + 512 + ], + [ + 997, + 512, + 512 + ], + [ + 872, + 512, + 512 + ], + [ + 579, + 512, + 512 + ], + [ + 906, + 512, + 512 + ], + [ + 1022, + 512, + 512 + ], + [ + 705, + 512, + 512 + ], + [ + 877, + 512, + 512 + ], + [ + 917, + 512, + 512 + ], + [ + 986, + 512, + 512 + ], + [ + 972, + 512, + 512 + ], + [ + 684, + 512, + 512 + ], + [ + 824, + 512, + 512 + ], + [ + 1017, + 512, + 512 + ], + [ + 1899, + 512, + 512 + ], + [ + 575, + 512, + 512 + ], + [ + 1083, + 512, + 512 + ], + [ + 488, + 512, + 512 + ], + [ + 881, + 512, + 512 + ], + [ + 1092, + 512, + 512 + ], + [ + 961, + 512, + 512 + ], + [ + 867, + 512, + 512 + ], + [ + 860, + 512, + 512 + ], + [ + 972, + 512, + 512 + ], + [ + 905, + 512, + 512 + ], + [ + 869, + 512, + 512 + ], + [ + 910, + 512, + 512 + ], + [ + 1067, + 512, + 512 + ], + [ + 945, + 512, + 512 + ], + [ + 545, + 512, + 512 + ], + [ + 1037, + 512, + 512 + ], + [ + 986, + 512, + 512 + ], + [ + 950, + 512, + 512 + ], + [ + 937, + 512, + 512 + ], + [ + 829, + 512, + 512 + ], + [ + 568, + 512, + 512 + ], + [ + 973, + 512, + 512 + ], + [ + 881, + 512, + 512 + ], + [ + 937, + 512, + 512 + ], + [ + 558, + 512, + 512 + ], + [ + 999, + 512, + 512 + ], + [ + 1031, + 512, + 512 + ], + [ + 1030, + 512, + 512 + ], + [ + 583, + 512, + 512 + ], + [ + 940, + 512, + 512 + ], + [ + 950, + 512, + 512 + ], + [ + 792, + 512, + 512 + ], + [ + 857, + 512, + 512 + ], + [ + 967, + 512, + 512 + ], + [ + 867, + 512, + 512 + ], + [ + 793, + 512, + 512 + ], + [ + 869, + 512, + 512 + ], + [ + 430, + 512, + 512 + ], + [ + 909, + 512, + 512 + ], + [ + 987, + 512, + 512 + ], + [ + 942, + 512, + 512 + ], + [ + 954, + 512, + 512 + ], + [ + 862, + 512, + 512 + ], + [ + 1063, + 512, + 512 + ], + [ + 863, + 512, + 512 + ], + [ + 1037, + 512, + 512 + ], + [ + 827, + 512, + 512 + ], + [ + 901, + 512, + 512 + ], + [ + 494, + 512, + 512 + ], + [ + 463, + 512, + 512 + ], + [ + 926, + 512, + 512 + ], + [ + 1094, + 512, + 512 + ], + [ + 972, + 512, + 512 + ], + [ + 565, + 512, + 512 + ], + [ + 1031, + 512, + 512 + ], + [ + 917, + 512, + 512 + ], + [ + 817, + 512, + 512 + ], + [ + 857, + 512, + 512 + ], + [ + 923, + 512, + 512 + ], + [ + 861, + 512, + 512 + ], + [ + 793, + 512, + 512 + ], + [ + 834, + 512, + 512 + ], + [ + 980, + 512, + 512 + ], + [ + 575, + 512, + 512 + ], + [ + 921, + 512, + 512 + ], + [ + 933, + 512, + 512 + ], + [ + 1085, + 512, + 512 + ], + [ + 926, + 512, + 512 + ], + [ + 802, + 512, + 512 + ], + [ + 1225, + 512, + 512 + ], + [ + 1026, + 512, + 512 + ], + [ + 865, + 512, + 512 + ], + [ + 933, + 512, + 512 + ], + [ + 950, + 512, + 512 + ], + [ + 893, + 512, + 512 + ], + [ + 974, + 512, + 512 + ], + [ + 820, + 512, + 512 + ], + [ + 843, + 512, + 512 + ], + [ + 975, + 512, + 512 + ], + [ + 826, + 512, + 512 + ], + [ + 898, + 512, + 512 + ], + [ + 995, + 512, + 512 + ], + [ + 1005, + 512, + 512 + ], + [ + 956, + 512, + 512 + ], + [ + 949, + 512, + 512 + ], + [ + 634, + 512, + 512 + ], + [ + 981, + 512, + 512 + ], + [ + 905, + 512, + 512 + ], + [ + 908, + 512, + 512 + ], + [ + 948, + 512, + 512 + ], + [ + 913, + 512, + 512 + ], + [ + 1040, + 512, + 512 + ], + [ + 989, + 512, + 512 + ], + [ + 779, + 512, + 512 + ], + [ + 916, + 512, + 512 + ], + [ + 1001, + 512, + 512 + ], + [ + 782, + 512, + 512 + ], + [ + 1011, + 512, + 512 + ], + [ + 1132, + 512, + 512 + ], + [ + 594, + 512, + 512 + ], + [ + 921, + 512, + 512 + ], + [ + 461, + 512, + 512 + ], + [ + 559, + 512, + 512 + ], + [ + 983, + 512, + 512 + ], + [ + 989, + 512, + 512 + ], + [ + 866, + 512, + 512 + ], + [ + 937, + 512, + 512 + ], + [ + 839, + 512, + 512 + ], + [ + 889, + 512, + 512 + ], + [ + 853, + 512, + 512 + ], + [ + 790, + 512, + 512 + ], + [ + 826, + 512, + 512 + ], + [ + 1012, + 512, + 512 + ], + [ + 561, + 512, + 512 + ], + [ + 902, + 512, + 512 + ], + [ + 896, + 512, + 512 + ], + [ + 952, + 512, + 512 + ], + [ + 839, + 512, + 512 + ], + [ + 866, + 512, + 512 + ], + [ + 965, + 512, + 512 + ], + [ + 865, + 512, + 512 + ], + [ + 1099, + 512, + 512 + ], + [ + 581, + 512, + 512 + ], + [ + 868, + 512, + 512 + ], + [ + 900, + 512, + 512 + ], + [ + 960, + 512, + 512 + ], + [ + 912, + 512, + 512 + ], + [ + 909, + 512, + 512 + ], + [ + 601, + 512, + 512 + ], + [ + 780, + 512, + 512 + ], + [ + 906, + 512, + 512 + ], + [ + 912, + 512, + 512 + ], + [ + 822, + 512, + 512 + ], + [ + 881, + 512, + 512 + ], + [ + 587, + 512, + 512 + ], + [ + 497, + 512, + 512 + ], + [ + 982, + 512, + 512 + ], + [ + 897, + 512, + 512 + ], + [ + 898, + 512, + 512 + ], + [ + 793, + 512, + 512 + ], + [ + 866, + 512, + 512 + ], + [ + 807, + 512, + 512 + ], + [ + 909, + 512, + 512 + ], + [ + 686, + 512, + 512 + ], + [ + 759, + 512, + 512 + ], + [ + 524, + 512, + 512 + ], + [ + 841, + 512, + 512 + ], + [ + 868, + 512, + 512 + ], + [ + 992, + 512, + 512 + ], + [ + 904, + 512, + 512 + ], + [ + 557, + 512, + 512 + ], + [ + 929, + 512, + 512 + ], + [ + 1006, + 512, + 512 + ], + [ + 607, + 512, + 512 + ], + [ + 989, + 512, + 512 + ], + [ + 812, + 512, + 512 + ], + [ + 827, + 512, + 512 + ], + [ + 1021, + 512, + 512 + ], + [ + 904, + 512, + 512 + ], + [ + 778, + 512, + 512 + ], + [ + 482, + 512, + 512 + ], + [ + 455, + 512, + 512 + ], + [ + 866, + 512, + 512 + ], + [ + 950, + 512, + 512 + ], + [ + 951, + 512, + 512 + ], + [ + 857, + 512, + 512 + ], + [ + 686, + 512, + 512 + ], + [ + 836, + 512, + 512 + ], + [ + 759, + 512, + 512 + ], + [ + 976, + 512, + 512 + ], + [ + 1017, + 512, + 512 + ], + [ + 817, + 512, + 512 + ], + [ + 795, + 512, + 512 + ], + [ + 988, + 512, + 512 + ], + [ + 930, + 512, + 512 + ], + [ + 825, + 512, + 512 + ], + [ + 853, + 512, + 512 + ], + [ + 933, + 512, + 512 + ], + [ + 931, + 512, + 512 + ], + [ + 828, + 512, + 512 + ], + [ + 506, + 512, + 512 + ], + [ + 996, + 512, + 512 + ], + [ + 853, + 512, + 512 + ], + [ + 480, + 512, + 512 + ], + [ + 884, + 512, + 512 + ], + [ + 541, + 512, + 512 + ], + [ + 945, + 512, + 512 + ], + [ + 930, + 512, + 512 + ], + [ + 1027, + 512, + 512 + ], + [ + 978, + 512, + 512 + ], + [ + 887, + 512, + 512 + ], + [ + 829, + 512, + 512 + ], + [ + 814, + 512, + 512 + ], + [ + 457, + 512, + 512 + ], + [ + 890, + 512, + 512 + ], + [ + 1034, + 512, + 512 + ], + [ + 882, + 512, + 512 + ], + [ + 1053, + 512, + 512 + ], + [ + 400, + 512, + 512 + ], + [ + 773, + 512, + 512 + ], + [ + 999, + 512, + 512 + ], + [ + 784, + 512, + 512 + ], + [ + 913, + 512, + 512 + ], + [ + 945, + 512, + 512 + ], + [ + 824, + 512, + 512 + ], + [ + 507, + 512, + 512 + ], + [ + 949, + 512, + 512 + ], + [ + 965, + 512, + 512 + ], + [ + 987, + 512, + 512 + ], + [ + 503, + 512, + 512 + ], + [ + 1008, + 512, + 512 + ], + [ + 860, + 512, + 512 + ], + [ + 815, + 512, + 512 + ], + [ + 901, + 512, + 512 + ], + [ + 957, + 512, + 512 + ], + [ + 777, + 512, + 512 + ], + [ + 482, + 512, + 512 + ], + [ + 853, + 512, + 512 + ], + [ + 929, + 512, + 512 + ], + [ + 718, + 512, + 512 + ], + [ + 900, + 512, + 512 + ], + [ + 805, + 512, + 512 + ], + [ + 1021, + 512, + 512 + ], + [ + 973, + 512, + 512 + ], + [ + 415, + 512, + 512 + ], + [ + 437, + 512, + 512 + ], + [ + 1012, + 512, + 512 + ], + [ + 481, + 512, + 512 + ], + [ + 1085, + 512, + 512 + ], + [ + 851, + 512, + 512 + ], + [ + 856, + 512, + 512 + ], + [ + 812, + 512, + 512 + ], + [ + 423, + 512, + 512 + ], + [ + 1005, + 512, + 512 + ], + [ + 837, + 512, + 512 + ], + [ + 964, + 512, + 512 + ], + [ + 625, + 512, + 512 + ], + [ + 857, + 512, + 512 + ], + [ + 841, + 512, + 512 + ], + [ + 807, + 512, + 512 + ], + [ + 567, + 512, + 512 + ], + [ + 512, + 512, + 512 + ], + [ + 907, + 512, + 512 + ], + [ + 481, + 512, + 512 + ], + [ + 489, + 512, + 512 + ], + [ + 488, + 512, + 512 + ], + [ + 581, + 512, + 512 + ], + [ + 481, + 512, + 512 + ], + [ + 897, + 512, + 512 + ], + [ + 874, + 512, + 512 + ], + [ + 803, + 512, + 512 + ], + [ + 814, + 512, + 512 + ], + [ + 861, + 512, + 512 + ], + [ + 564, + 512, + 512 + ], + [ + 910, + 512, + 512 + ], + [ + 890, + 512, + 512 + ], + [ + 884, + 512, + 512 + ], + [ + 880, + 512, + 512 + ], + [ + 569, + 512, + 512 + ], + [ + 927, + 512, + 512 + ], + [ + 922, + 512, + 512 + ], + [ + 615, + 512, + 512 + ], + [ + 938, + 512, + 512 + ], + [ + 605, + 512, + 512 + ], + [ + 619, + 512, + 512 + ], + [ + 889, + 512, + 512 + ], + [ + 1005, + 512, + 512 + ], + [ + 481, + 512, + 512 + ], + [ + 797, + 512, + 512 + ], + [ + 954, + 512, + 512 + ], + [ + 768, + 512, + 512 + ], + [ + 957, + 512, + 512 + ], + [ + 873, + 512, + 512 + ], + [ + 925, + 512, + 512 + ], + [ + 806, + 512, + 512 + ], + [ + 834, + 512, + 512 + ], + [ + 510, + 512, + 512 + ], + [ + 779, + 512, + 512 + ], + [ + 469, + 512, + 512 + ], + [ + 837, + 512, + 512 + ], + [ + 365, + 512, + 512 + ], + [ + 939, + 512, + 512 + ], + [ + 468, + 512, + 512 + ], + [ + 491, + 512, + 512 + ], + [ + 531, + 512, + 512 + ], + [ + 474, + 512, + 512 + ], + [ + 965, + 512, + 512 + ], + [ + 845, + 512, + 512 + ], + [ + 828, + 512, + 512 + ], + [ + 1003, + 512, + 512 + ], + [ + 401, + 512, + 512 + ], + [ + 865, + 512, + 512 + ], + [ + 585, + 512, + 512 + ], + [ + 569, + 512, + 512 + ], + [ + 869, + 512, + 512 + ], + [ + 988, + 512, + 512 + ], + [ + 824, + 512, + 512 + ], + [ + 569, + 512, + 512 + ], + [ + 801, + 512, + 512 + ], + [ + 451, + 512, + 512 + ], + [ + 487, + 512, + 512 + ], + [ + 848, + 512, + 512 + ], + [ + 849, + 512, + 512 + ], + [ + 524, + 512, + 512 + ], + [ + 576, + 512, + 512 + ], + [ + 502, + 512, + 512 + ], + [ + 521, + 512, + 512 + ], + [ + 929, + 512, + 512 + ], + [ + 884, + 512, + 512 + ], + [ + 1013, + 512, + 512 + ], + [ + 921, + 512, + 512 + ], + [ + 630, + 512, + 512 + ], + [ + 1154, + 512, + 512 + ], + [ + 490, + 512, + 512 + ], + [ + 493, + 512, + 512 + ], + [ + 503, + 512, + 512 + ], + [ + 989, + 512, + 512 + ], + [ + 550, + 512, + 512 + ], + [ + 1030, + 512, + 512 + ], + [ + 994, + 512, + 512 + ], + [ + 848, + 512, + 512 + ], + [ + 900, + 512, + 512 + ], + [ + 919, + 512, + 512 + ], + [ + 935, + 512, + 512 + ], + [ + 1013, + 512, + 512 + ], + [ + 809, + 512, + 512 + ], + [ + 504, + 512, + 512 + ], + [ + 945, + 512, + 512 + ], + [ + 915, + 512, + 512 + ], + [ + 469, + 512, + 512 + ], + [ + 858, + 512, + 512 + ], + [ + 373, + 512, + 512 + ], + [ + 970, + 512, + 512 + ], + [ + 864, + 512, + 512 + ], + [ + 921, + 512, + 512 + ], + [ + 650, + 512, + 512 + ], + [ + 959, + 512, + 512 + ], + [ + 858, + 512, + 512 + ], + [ + 1114, + 512, + 512 + ], + [ + 525, + 512, + 512 + ], + [ + 825, + 512, + 512 + ], + [ + 761, + 512, + 512 + ], + [ + 465, + 512, + 512 + ], + [ + 447, + 512, + 512 + ], + [ + 377, + 512, + 512 + ], + [ + 869, + 512, + 512 + ], + [ + 633, + 512, + 512 + ], + [ + 1002, + 512, + 512 + ], + [ + 1013, + 512, + 512 + ], + [ + 997, + 512, + 512 + ], + [ + 837, + 512, + 512 + ], + [ + 930, + 512, + 512 + ], + [ + 864, + 512, + 512 + ], + [ + 875, + 512, + 512 + ], + [ + 880, + 512, + 512 + ], + [ + 805, + 512, + 512 + ], + [ + 833, + 512, + 512 + ], + [ + 910, + 512, + 512 + ], + [ + 885, + 512, + 512 + ], + [ + 988, + 512, + 512 + ], + [ + 821, + 512, + 512 + ], + [ + 388, + 512, + 512 + ], + [ + 877, + 512, + 512 + ], + [ + 785, + 512, + 512 + ], + [ + 914, + 512, + 512 + ], + [ + 469, + 512, + 512 + ], + [ + 542, + 512, + 512 + ], + [ + 856, + 512, + 512 + ], + [ + 1049, + 512, + 512 + ], + [ + 969, + 512, + 512 + ], + [ + 969, + 512, + 512 + ], + [ + 941, + 512, + 512 + ], + [ + 871, + 512, + 512 + ], + [ + 888, + 512, + 512 + ], + [ + 888, + 512, + 512 + ], + [ + 817, + 512, + 512 + ], + [ + 984, + 512, + 512 + ], + [ + 877, + 512, + 512 + ], + [ + 841, + 512, + 512 + ], + [ + 1029, + 512, + 512 + ], + [ + 929, + 512, + 512 + ], + [ + 517, + 512, + 512 + ], + [ + 861, + 512, + 512 + ], + [ + 614, + 512, + 512 + ], + [ + 901, + 512, + 512 + ], + [ + 900, + 512, + 512 + ], + [ + 997, + 512, + 512 + ], + [ + 957, + 512, + 512 + ], + [ + 997, + 512, + 512 + ], + [ + 624, + 512, + 512 + ], + [ + 659, + 512, + 512 + ], + [ + 955, + 512, + 512 + ], + [ + 1029, + 512, + 512 + ], + [ + 946, + 512, + 512 + ], + [ + 1020, + 512, + 512 + ], + [ + 990, + 512, + 512 + ], + [ + 945, + 512, + 512 + ], + [ + 584, + 512, + 512 + ], + [ + 966, + 512, + 512 + ], + [ + 930, + 512, + 512 + ], + [ + 582, + 512, + 512 + ], + [ + 970, + 512, + 512 + ], + [ + 562, + 512, + 512 + ], + [ + 910, + 512, + 512 + ], + [ + 1053, + 512, + 512 + ], + [ + 853, + 512, + 512 + ], + [ + 896, + 512, + 512 + ], + [ + 921, + 512, + 512 + ], + [ + 611, + 512, + 512 + ], + [ + 868, + 512, + 512 + ], + [ + 909, + 512, + 512 + ], + [ + 803, + 512, + 512 + ], + [ + 950, + 512, + 512 + ], + [ + 963, + 512, + 512 + ], + [ + 884, + 512, + 512 + ], + [ + 928, + 512, + 512 + ], + [ + 888, + 512, + 512 + ], + [ + 957, + 512, + 512 + ], + [ + 441, + 512, + 512 + ], + [ + 1267, + 512, + 512 + ], + [ + 1001, + 512, + 512 + ], + [ + 818, + 512, + 512 + ], + [ + 921, + 512, + 512 + ], + [ + 893, + 512, + 512 + ], + [ + 942, + 512, + 512 + ], + [ + 881, + 512, + 512 + ], + [ + 567, + 512, + 512 + ], + [ + 873, + 512, + 512 + ], + [ + 467, + 512, + 512 + ], + [ + 1029, + 512, + 512 + ], + [ + 869, + 512, + 512 + ], + [ + 967, + 512, + 512 + ], + [ + 821, + 512, + 512 + ], + [ + 865, + 512, + 512 + ], + [ + 933, + 512, + 512 + ], + [ + 895, + 512, + 512 + ], + [ + 865, + 512, + 512 + ], + [ + 997, + 512, + 512 + ], + [ + 863, + 512, + 512 + ], + [ + 912, + 512, + 512 + ], + [ + 894, + 512, + 512 + ], + [ + 997, + 512, + 512 + ], + [ + 897, + 512, + 512 + ], + [ + 613, + 512, + 512 + ], + [ + 982, + 512, + 512 + ], + [ + 853, + 512, + 512 + ], + [ + 904, + 512, + 512 + ], + [ + 795, + 512, + 512 + ], + [ + 837, + 512, + 512 + ], + [ + 529, + 512, + 512 + ], + [ + 890, + 512, + 512 + ], + [ + 994, + 512, + 512 + ], + [ + 969, + 512, + 512 + ], + [ + 912, + 512, + 512 + ], + [ + 889, + 512, + 512 + ], + [ + 866, + 512, + 512 + ], + [ + 893, + 512, + 512 + ], + [ + 901, + 512, + 512 + ], + [ + 856, + 512, + 512 + ], + [ + 815, + 512, + 512 + ], + [ + 680, + 512, + 512 + ], + [ + 945, + 512, + 512 + ], + [ + 853, + 512, + 512 + ], + [ + 1071, + 512, + 512 + ], + [ + 652, + 512, + 512 + ], + [ + 1038, + 512, + 512 + ], + [ + 956, + 512, + 512 + ], + [ + 994, + 512, + 512 + ], + [ + 926, + 512, + 512 + ], + [ + 1123, + 512, + 512 + ], + [ + 885, + 512, + 512 + ], + [ + 845, + 512, + 512 + ], + [ + 830, + 512, + 512 + ], + [ + 909, + 512, + 512 + ], + [ + 1148, + 512, + 512 + ], + [ + 1009, + 512, + 512 + ], + [ + 741, + 512, + 512 + ], + [ + 869, + 512, + 512 + ], + [ + 857, + 512, + 512 + ], + [ + 829, + 512, + 512 + ], + [ + 791, + 512, + 512 + ], + [ + 935, + 512, + 512 + ], + [ + 507, + 512, + 512 + ], + [ + 399, + 512, + 512 + ], + [ + 567, + 512, + 512 + ], + [ + 455, + 512, + 512 + ], + [ + 495, + 512, + 512 + ], + [ + 845, + 512, + 512 + ], + [ + 501, + 512, + 512 + ], + [ + 917, + 512, + 512 + ], + [ + 899, + 512, + 512 + ], + [ + 833, + 512, + 512 + ], + [ + 947, + 512, + 512 + ], + [ + 881, + 512, + 512 + ], + [ + 941, + 512, + 512 + ], + [ + 873, + 512, + 512 + ], + [ + 425, + 512, + 512 + ], + [ + 1061, + 512, + 512 + ], + [ + 876, + 512, + 512 + ], + [ + 720, + 512, + 512 + ], + [ + 867, + 512, + 512 + ], + [ + 741, + 512, + 512 + ], + [ + 941, + 512, + 512 + ], + [ + 461, + 512, + 512 + ], + [ + 831, + 512, + 512 + ], + [ + 418, + 512, + 512 + ], + [ + 825, + 512, + 512 + ], + [ + 477, + 512, + 512 + ], + [ + 842, + 512, + 512 + ], + [ + 707, + 512, + 512 + ], + [ + 573, + 512, + 512 + ], + [ + 856, + 512, + 512 + ], + [ + 954, + 512, + 512 + ], + [ + 971, + 512, + 512 + ], + [ + 873, + 512, + 512 + ], + [ + 1027, + 512, + 512 + ], + [ + 958, + 512, + 512 + ], + [ + 789, + 512, + 512 + ], + [ + 1010, + 512, + 512 + ], + [ + 797, + 512, + 512 + ], + [ + 995, + 512, + 512 + ], + [ + 930, + 512, + 512 + ], + [ + 1052, + 512, + 512 + ], + [ + 459, + 512, + 512 + ], + [ + 954, + 512, + 512 + ], + [ + 967, + 512, + 512 + ], + [ + 999, + 512, + 512 + ], + [ + 1041, + 512, + 512 + ], + [ + 881, + 512, + 512 + ], + [ + 830, + 512, + 512 + ], + [ + 1121, + 512, + 512 + ], + [ + 935, + 512, + 512 + ], + [ + 767, + 512, + 512 + ], + [ + 889, + 512, + 512 + ], + [ + 791, + 512, + 512 + ], + [ + 851, + 512, + 512 + ], + [ + 494, + 512, + 512 + ], + [ + 521, + 512, + 512 + ], + [ + 885, + 512, + 512 + ], + [ + 485, + 512, + 512 + ], + [ + 966, + 512, + 512 + ], + [ + 881, + 512, + 512 + ], + [ + 816, + 512, + 512 + ], + [ + 581, + 512, + 512 + ], + [ + 984, + 512, + 512 + ], + [ + 753, + 512, + 512 + ], + [ + 997, + 512, + 512 + ], + [ + 615, + 512, + 512 + ], + [ + 945, + 512, + 512 + ], + [ + 975, + 512, + 512 + ], + [ + 519, + 512, + 512 + ], + [ + 995, + 512, + 512 + ], + [ + 925, + 512, + 512 + ], + [ + 600, + 512, + 512 + ], + [ + 527, + 512, + 512 + ], + [ + 1047, + 512, + 512 + ], + [ + 937, + 512, + 512 + ], + [ + 522, + 512, + 512 + ], + [ + 1074, + 512, + 512 + ], + [ + 487, + 512, + 512 + ], + [ + 862, + 512, + 512 + ], + [ + 439, + 512, + 512 + ], + [ + 945, + 512, + 512 + ], + [ + 484, + 512, + 512 + ], + [ + 584, + 512, + 512 + ], + [ + 952, + 512, + 512 + ], + [ + 871, + 512, + 512 + ], + [ + 811, + 512, + 512 + ], + [ + 527, + 512, + 512 + ], + [ + 1085, + 512, + 512 + ], + [ + 628, + 512, + 512 + ], + [ + 457, + 512, + 512 + ], + [ + 649, + 512, + 512 + ], + [ + 466, + 512, + 512 + ], + [ + 507, + 512, + 512 + ], + [ + 484, + 512, + 512 + ], + [ + 999, + 512, + 512 + ], + [ + 510, + 512, + 512 + ], + [ + 873, + 512, + 512 + ], + [ + 800, + 512, + 512 + ], + [ + 545, + 512, + 512 + ], + [ + 985, + 512, + 512 + ], + [ + 471, + 512, + 512 + ], + [ + 435, + 512, + 512 + ], + [ + 470, + 512, + 512 + ], + [ + 507, + 512, + 512 + ], + [ + 479, + 512, + 512 + ], + [ + 567, + 512, + 512 + ], + [ + 525, + 512, + 512 + ], + [ + 1070, + 512, + 512 + ], + [ + 971, + 512, + 512 + ], + [ + 522, + 512, + 512 + ], + [ + 581, + 512, + 512 + ], + [ + 573, + 512, + 512 + ], + [ + 490, + 512, + 512 + ], + [ + 905, + 512, + 512 + ], + [ + 857, + 512, + 512 + ], + [ + 918, + 512, + 512 + ], + [ + 537, + 512, + 512 + ], + [ + 875, + 512, + 512 + ], + [ + 397, + 512, + 512 + ], + [ + 371, + 512, + 512 + ], + [ + 593, + 512, + 512 + ], + [ + 470, + 512, + 512 + ], + [ + 582, + 512, + 512 + ], + [ + 440, + 512, + 512 + ], + [ + 930, + 512, + 512 + ], + [ + 601, + 512, + 512 + ], + [ + 531, + 512, + 512 + ], + [ + 923, + 512, + 512 + ], + [ + 853, + 512, + 512 + ], + [ + 1005, + 512, + 512 + ], + [ + 948, + 512, + 512 + ], + [ + 637, + 512, + 512 + ], + [ + 975, + 512, + 512 + ], + [ + 477, + 512, + 512 + ], + [ + 411, + 512, + 512 + ], + [ + 519, + 512, + 512 + ], + [ + 584, + 512, + 512 + ], + [ + 814, + 512, + 512 + ], + [ + 977, + 512, + 512 + ], + [ + 533, + 512, + 512 + ], + [ + 939, + 512, + 512 + ], + [ + 457, + 512, + 512 + ], + [ + 507, + 512, + 512 + ], + [ + 529, + 512, + 512 + ], + [ + 945, + 512, + 512 + ], + [ + 950, + 512, + 512 + ], + [ + 421, + 512, + 512 + ], + [ + 642, + 512, + 512 + ], + [ + 885, + 512, + 512 + ], + [ + 477, + 512, + 512 + ], + [ + 506, + 512, + 512 + ], + [ + 919, + 512, + 512 + ], + [ + 993, + 512, + 512 + ], + [ + 865, + 512, + 512 + ], + [ + 1009, + 512, + 512 + ], + [ + 554, + 512, + 512 + ], + [ + 889, + 512, + 512 + ], + [ + 377, + 512, + 512 + ], + [ + 934, + 512, + 512 + ], + [ + 869, + 512, + 512 + ], + [ + 945, + 512, + 512 + ], + [ + 502, + 512, + 512 + ], + [ + 1063, + 512, + 512 + ], + [ + 892, + 512, + 512 + ], + [ + 867, + 512, + 512 + ], + [ + 1061, + 512, + 512 + ], + [ + 947, + 512, + 512 + ], + [ + 745, + 512, + 512 + ], + [ + 959, + 512, + 512 + ], + [ + 618, + 512, + 512 + ], + [ + 841, + 512, + 512 + ], + [ + 565, + 512, + 512 + ], + [ + 833, + 512, + 512 + ], + [ + 510, + 512, + 512 + ], + [ + 577, + 512, + 512 + ], + [ + 505, + 512, + 512 + ], + [ + 504, + 512, + 512 + ], + [ + 551, + 512, + 512 + ], + [ + 982, + 512, + 512 + ], + [ + 853, + 512, + 512 + ], + [ + 845, + 512, + 512 + ], + [ + 556, + 512, + 512 + ], + [ + 897, + 512, + 512 + ], + [ + 467, + 512, + 512 + ], + [ + 498, + 512, + 512 + ], + [ + 537, + 512, + 512 + ], + [ + 875, + 512, + 512 + ], + [ + 511, + 512, + 512 + ], + [ + 622, + 512, + 512 + ], + [ + 948, + 512, + 512 + ], + [ + 586, + 512, + 512 + ], + [ + 596, + 512, + 512 + ], + [ + 629, + 512, + 512 + ], + [ + 425, + 512, + 512 + ], + [ + 887, + 512, + 512 + ], + [ + 1053, + 512, + 512 + ], + [ + 832, + 512, + 512 + ], + [ + 497, + 512, + 512 + ], + [ + 865, + 512, + 512 + ], + [ + 971, + 512, + 512 + ], + [ + 800, + 512, + 512 + ], + [ + 805, + 512, + 512 + ], + [ + 900, + 512, + 512 + ], + [ + 937, + 512, + 512 + ], + [ + 524, + 512, + 512 + ], + [ + 452, + 512, + 512 + ], + [ + 690, + 512, + 512 + ], + [ + 546, + 512, + 512 + ], + [ + 719, + 512, + 512 + ], + [ + 850, + 512, + 512 + ], + [ + 590, + 512, + 512 + ], + [ + 979, + 512, + 512 + ], + [ + 547, + 512, + 512 + ], + [ + 458, + 512, + 512 + ], + [ + 570, + 512, + 512 + ], + [ + 586, + 512, + 512 + ], + [ + 965, + 512, + 512 + ], + [ + 518, + 512, + 512 + ], + [ + 506, + 512, + 512 + ], + [ + 910, + 512, + 512 + ], + [ + 530, + 512, + 512 + ], + [ + 870, + 512, + 512 + ], + [ + 454, + 512, + 512 + ], + [ + 555, + 512, + 512 + ], + [ + 455, + 512, + 512 + ], + [ + 425, + 512, + 512 + ], + [ + 568, + 512, + 512 + ], + [ + 549, + 512, + 512 + ], + [ + 512, + 512, + 512 + ], + [ + 1034, + 512, + 512 + ], + [ + 975, + 512, + 512 + ], + [ + 528, + 512, + 512 + ], + [ + 490, + 512, + 512 + ], + [ + 506, + 512, + 512 + ], + [ + 940, + 512, + 512 + ], + [ + 602, + 512, + 512 + ], + [ + 500, + 512, + 512 + ], + [ + 610, + 512, + 512 + ], + [ + 1002, + 512, + 512 + ], + [ + 431, + 512, + 512 + ], + [ + 485, + 512, + 512 + ], + [ + 547, + 512, + 512 + ], + [ + 921, + 512, + 512 + ], + [ + 915, + 512, + 512 + ], + [ + 970, + 512, + 512 + ], + [ + 492, + 512, + 512 + ], + [ + 511, + 512, + 512 + ], + [ + 503, + 512, + 512 + ], + [ + 976, + 512, + 512 + ], + [ + 846, + 512, + 512 + ], + [ + 429, + 512, + 512 + ], + [ + 589, + 512, + 512 + ], + [ + 521, + 512, + 512 + ], + [ + 461, + 512, + 512 + ], + [ + 451, + 512, + 512 + ], + [ + 559, + 512, + 512 + ], + [ + 1020, + 512, + 512 + ], + [ + 464, + 512, + 512 + ], + [ + 634, + 512, + 512 + ], + [ + 435, + 512, + 512 + ], + [ + 562, + 512, + 512 + ], + [ + 794, + 512, + 512 + ], + [ + 557, + 512, + 512 + ], + [ + 897, + 512, + 512 + ], + [ + 847, + 512, + 512 + ], + [ + 881, + 512, + 512 + ], + [ + 995, + 512, + 512 + ], + [ + 850, + 512, + 512 + ], + [ + 298, + 512, + 512 + ], + [ + 786, + 512, + 512 + ], + [ + 855, + 512, + 512 + ], + [ + 803, + 512, + 512 + ], + [ + 1059, + 512, + 512 + ], + [ + 535, + 512, + 512 + ], + [ + 527, + 512, + 512 + ], + [ + 453, + 512, + 512 + ], + [ + 463, + 512, + 512 + ], + [ + 1037, + 512, + 512 + ], + [ + 1084, + 512, + 512 + ], + [ + 656, + 512, + 512 + ], + [ + 924, + 512, + 662 + ], + [ + 794, + 512, + 512 + ], + [ + 937, + 512, + 512 + ], + [ + 557, + 512, + 512 + ], + [ + 897, + 512, + 512 + ], + [ + 425, + 512, + 512 + ], + [ + 828, + 512, + 512 + ], + [ + 914, + 512, + 512 + ], + [ + 723, + 512, + 512 + ], + [ + 1059, + 512, + 512 + ], + [ + 1000, + 512, + 512 + ], + [ + 826, + 512, + 512 + ], + [ + 911, + 512, + 512 + ], + [ + 544, + 512, + 512 + ], + [ + 621, + 512, + 512 + ], + [ + 818, + 512, + 512 + ], + [ + 1026, + 512, + 512 + ], + [ + 788, + 512, + 512 + ], + [ + 976, + 512, + 512 + ], + [ + 1015, + 512, + 512 + ], + [ + 884, + 512, + 512 + ], + [ + 544, + 512, + 512 + ], + [ + 913, + 512, + 512 + ] + ], + "spacings": [ + [ + 0.5, + 0.76953125, + 0.76953125 + ], + [ + 0.5, + 0.7265625, + 0.7265625 + ], + [ + 0.5, + 0.787109375, + 0.787109375 + ], + [ + 0.5, + 0.62890625, + 0.62890625 + ], + [ + 0.5, + 0.953125, + 0.953125 + ], + [ + 0.5, + 0.875, + 0.875 + ], + [ + 0.5, + 0.693359375, + 0.693359375 + ], + [ + 0.5, + 0.685546875, + 0.685546875 + ], + [ + 0.5, + 0.6953125, + 0.6953125 + ], + [ + 0.5, + 0.75, + 0.75 + ], + [ + 0.5, + 0.74609375, + 0.74609375 + ], + [ + 0.5, + 0.6015625, + 0.6015625 + ], + [ + 0.5, + 0.6875, + 0.6875 + ], + [ + 0.5, + 0.7265625, + 0.7265625 + ], + [ + 0.5, + 0.59375, + 0.59375 + ], + [ + 0.5, + 0.7265625, + 0.7265625 + ], + [ + 0.5, + 0.66015625, + 0.66015625 + ], + [ + 0.5, + 0.79296875, + 0.79296875 + ], + [ + 0.5, + 0.650390625, + 0.650390625 + ], + [ + 0.5, + 0.7421875, + 0.7421875 + ], + [ + 0.5, + 0.791015625, + 0.791015625 + ], + [ + 0.5, + 0.82421875, + 0.82421875 + ], + [ + 0.5, + 0.875, + 0.875 + ], + [ + 0.5, + 0.6328125, + 0.6328125 + ], + [ + 0.5, + 0.759765625, + 0.759765625 + ], + [ + 0.5, + 0.9765625, + 0.9765625 + ], + [ + 0.5, + 0.693359375, + 0.693359375 + ], + [ + 0.5, + 0.751953125, + 0.751953125 + ], + [ + 0.5, + 0.625, + 0.625 + ], + [ + 0.5, + 0.8203125, + 0.8203125 + ], + [ + 0.5, + 0.69921875, + 0.69921875 + ], + [ + 0.5, + 0.70703125, + 0.70703125 + ], + [ + 0.5, + 0.79296875, + 0.79296875 + ], + [ + 0.5, + 0.611328125, + 0.611328125 + ], + [ + 0.5, + 0.8125, + 0.8125 + ], + [ + 0.5, + 0.78125, + 0.78125 + ], + [ + 0.5, + 0.92578125, + 0.92578125 + ], + [ + 0.5, + 0.67578125, + 0.67578125 + ], + [ + 0.5, + 0.662109375, + 0.662109375 + ], + [ + 0.5, + 0.56640625, + 0.56640625 + ], + [ + 0.5, + 0.6484375, + 0.6484375 + ], + [ + 0.5, + 0.861328125, + 0.861328125 + ], + [ + 0.5, + 0.63671875, + 0.63671875 + ], + [ + 0.5, + 0.673828125, + 0.673828125 + ], + [ + 0.5, + 0.65625, + 0.65625 + ], + [ + 0.5, + 0.712890625, + 0.712890625 + ], + [ + 0.5, + 0.71875, + 0.71875 + ], + [ + 0.5, + 0.771484375, + 0.771484375 + ], + [ + 0.5, + 0.5859375, + 0.5859375 + ], + [ + 0.5, + 0.841796875, + 0.841796875 + ], + [ + 0.5, + 0.771484375, + 0.771484375 + ], + [ + 0.5, + 0.73046875, + 0.73046875 + ], + [ + 0.5, + 0.611328125, + 0.611328125 + ], + [ + 0.5, + 0.849609375, + 0.849609375 + ], + [ + 0.5, + 0.7109375, + 0.7109375 + ], + [ + 0.5, + 0.771484375, + 0.771484375 + ], + [ + 0.5, + 0.81640625, + 0.81640625 + ], + [ + 0.5, + 0.662109375, + 0.662109375 + ], + [ + 0.5, + 0.671875, + 0.671875 + ], + [ + 0.5, + 0.625, + 0.625 + ], + [ + 0.5, + 0.966796875, + 0.966796875 + ], + [ + 0.5, + 0.6328125, + 0.6328125 + ], + [ + 0.5, + 0.865234375, + 0.865234375 + ], + [ + 0.5, + 0.7265625, + 0.7265625 + ], + [ + 0.5, + 0.62890625, + 0.62890625 + ], + [ + 0.5, + 0.80859375, + 0.80859375 + ], + [ + 0.5, + 0.5859375, + 0.5859375 + ], + [ + 0.5, + 0.69140625, + 0.69140625 + ], + [ + 0.5, + 0.8046875, + 0.8046875 + ], + [ + 0.5, + 0.583984375, + 0.583984375 + ], + [ + 0.5, + 0.78125, + 0.78125 + ], + [ + 0.5, + 0.796875, + 0.796875 + ], + [ + 0.5, + 0.638671875, + 0.638671875 + ], + [ + 0.5, + 0.69921875, + 0.69921875 + ], + [ + 0.5, + 0.68359375, + 0.68359375 + ], + [ + 0.5, + 0.81640625, + 0.81640625 + ], + [ + 0.5, + 0.89453125, + 0.89453125 + ], + [ + 0.5, + 0.681640625, + 0.681640625 + ], + [ + 0.5, + 0.73046875, + 0.73046875 + ], + [ + 0.5, + 0.857421875, + 0.857421875 + ], + [ + 0.5, + 0.658203125, + 0.658203125 + ], + [ + 0.5, + 0.734375, + 0.734375 + ], + [ + 0.5, + 0.625, + 0.625 + ], + [ + 0.5, + 0.6875, + 0.6875 + ], + [ + 0.5, + 0.68359375, + 0.68359375 + ], + [ + 0.5, + 0.91796875, + 0.91796875 + ], + [ + 0.5, + 0.75390625, + 0.75390625 + ], + [ + 0.5, + 0.765625, + 0.765625 + ], + [ + 0.5, + 0.611328125, + 0.611328125 + ], + [ + 0.5, + 0.798828125, + 0.798828125 + ], + [ + 0.5, + 0.81640625, + 0.81640625 + ], + [ + 0.5, + 0.75, + 0.75 + ], + [ + 0.5, + 0.75390625, + 0.75390625 + ], + [ + 0.5, + 0.9140625, + 0.9140625 + ], + [ + 0.5, + 0.685546875, + 0.685546875 + ], + [ + 0.5, + 0.71875, + 0.71875 + ], + [ + 0.5, + 0.72265625, + 0.72265625 + ], + [ + 0.5, + 0.830078125, + 0.830078125 + ], + [ + 0.5, + 0.751953125, + 0.751953125 + ], + [ + 0.5, + 0.794921875, + 0.794921875 + ], + [ + 0.5, + 0.669921875, + 0.669921875 + ], + [ + 0.5, + 0.65625, + 0.65625 + ], + [ + 0.5, + 0.595703125, + 0.595703125 + ], + [ + 0.5, + 0.6484375, + 0.6484375 + ], + [ + 0.5, + 0.61328125, + 0.61328125 + ], + [ + 0.5, + 0.6171875, + 0.6171875 + ], + [ + 0.5, + 0.669921875, + 0.669921875 + ], + [ + 0.5, + 0.822265625, + 0.822265625 + ], + [ + 0.5, + 0.6640625, + 0.6640625 + ], + [ + 0.5, + 0.515625, + 0.515625 + ], + [ + 0.5, + 0.787109375, + 0.787109375 + ], + [ + 0.5, + 0.8046875, + 0.8046875 + ], + [ + 0.5, + 0.66796875, + 0.66796875 + ], + [ + 0.5, + 0.69140625, + 0.69140625 + ], + [ + 0.5, + 0.734375, + 0.734375 + ], + [ + 0.5, + 0.75, + 0.75 + ], + [ + 0.5, + 0.625, + 0.625 + ], + [ + 0.5, + 0.9765625, + 0.9765625 + ], + [ + 0.5, + 0.6796875, + 0.6796875 + ], + [ + 0.5, + 0.67578125, + 0.67578125 + ], + [ + 0.5, + 0.62109375, + 0.62109375 + ], + [ + 0.5, + 0.546875, + 0.546875 + ], + [ + 0.5, + 0.67578125, + 0.67578125 + ], + [ + 0.5, + 0.77734375, + 0.77734375 + ], + [ + 0.5, + 0.966796875, + 0.966796875 + ], + [ + 0.5, + 0.68359375, + 0.68359375 + ], + [ + 0.5, + 0.701171875, + 0.701171875 + ], + [ + 0.5, + 0.6875, + 0.6875 + ], + [ + 0.5, + 0.70703125, + 0.70703125 + ], + [ + 0.5, + 0.693359375, + 0.693359375 + ], + [ + 0.5, + 0.62890625, + 0.62890625 + ], + [ + 0.5, + 0.5859375, + 0.5859375 + ], + [ + 0.5, + 0.79296875, + 0.79296875 + ], + [ + 0.5, + 0.712890625, + 0.712890625 + ], + [ + 0.5, + 0.650390625, + 0.650390625 + ], + [ + 0.5, + 0.720703125, + 0.720703125 + ], + [ + 0.5, + 0.73046875, + 0.73046875 + ], + [ + 0.5, + 0.666015625, + 0.666015625 + ], + [ + 0.5, + 0.53515625, + 0.53515625 + ], + [ + 0.5, + 0.78125, + 0.78125 + ], + [ + 0.5, + 0.76171875, + 0.76171875 + ], + [ + 0.5, + 0.6953125, + 0.6953125 + ], + [ + 0.5, + 0.677734375, + 0.677734375 + ], + [ + 0.5, + 0.88671875, + 0.88671875 + ], + [ + 0.5, + 0.65234375, + 0.65234375 + ], + [ + 0.5, + 0.630859375, + 0.630859375 + ], + [ + 0.5, + 0.75390625, + 0.75390625 + ], + [ + 0.5, + 0.78125, + 0.78125 + ], + [ + 0.5, + 0.72265625, + 0.72265625 + ], + [ + 0.5, + 0.654296875, + 0.654296875 + ], + [ + 0.5, + 0.84765625, + 0.84765625 + ], + [ + 0.5, + 0.91796875, + 0.91796875 + ], + [ + 0.5, + 0.6796875, + 0.6796875 + ], + [ + 0.5, + 0.666015625, + 0.666015625 + ], + [ + 0.5, + 0.55078125, + 0.55078125 + ], + [ + 0.5, + 0.63671875, + 0.63671875 + ], + [ + 0.5, + 0.8125, + 0.8125 + ], + [ + 0.5, + 0.796875, + 0.796875 + ], + [ + 0.5, + 0.70703125, + 0.70703125 + ], + [ + 0.5, + 0.78125, + 0.78125 + ], + [ + 0.5, + 0.7265625, + 0.7265625 + ], + [ + 0.5, + 0.818359375, + 0.818359375 + ], + [ + 0.5, + 0.791015625, + 0.791015625 + ], + [ + 0.5, + 0.85546875, + 0.85546875 + ], + [ + 0.5, + 0.703125, + 0.703125 + ], + [ + 0.5, + 0.78515625, + 0.78515625 + ], + [ + 0.5, + 0.86328125, + 0.86328125 + ], + [ + 0.5, + 0.6796875, + 0.6796875 + ], + [ + 0.5, + 0.75390625, + 0.75390625 + ], + [ + 0.5, + 0.671875, + 0.671875 + ], + [ + 0.5, + 0.537109375, + 0.537109375 + ], + [ + 0.5, + 0.71484375, + 0.71484375 + ], + [ + 0.5, + 0.67578125, + 0.67578125 + ], + [ + 0.5, + 0.671875, + 0.671875 + ], + [ + 0.5, + 0.841796875, + 0.841796875 + ], + [ + 0.5, + 0.703125, + 0.703125 + ], + [ + 0.5, + 0.75390625, + 0.75390625 + ], + [ + 0.5, + 0.77734375, + 0.77734375 + ], + [ + 0.5, + 0.78515625, + 0.78515625 + ], + [ + 0.5, + 0.73828125, + 0.73828125 + ], + [ + 0.5, + 0.71484375, + 0.71484375 + ], + [ + 0.5, + 0.6484375, + 0.6484375 + ], + [ + 0.5, + 0.763671875, + 0.763671875 + ], + [ + 0.5, + 0.79296875, + 0.79296875 + ], + [ + 0.5, + 0.81640625, + 0.81640625 + ], + [ + 0.5, + 0.80859375, + 0.80859375 + ], + [ + 0.5, + 0.66796875, + 0.66796875 + ], + [ + 0.5, + 0.94921875, + 0.94921875 + ], + [ + 0.5, + 0.966796875, + 0.966796875 + ], + [ + 0.5, + 0.65625, + 0.65625 + ], + [ + 0.5, + 0.67578125, + 0.67578125 + ], + [ + 0.5, + 0.6953125, + 0.6953125 + ], + [ + 0.5, + 0.66796875, + 0.66796875 + ], + [ + 0.5, + 0.7890625, + 0.7890625 + ], + [ + 0.5, + 0.76171875, + 0.76171875 + ], + [ + 0.5, + 0.705078125, + 0.705078125 + ], + [ + 0.5, + 0.7734375, + 0.7734375 + ], + [ + 0.5, + 0.5859375, + 0.5859375 + ], + [ + 0.5, + 0.583984375, + 0.583984375 + ], + [ + 0.5, + 0.70703125, + 0.70703125 + ], + [ + 0.5, + 0.69921875, + 0.69921875 + ], + [ + 0.5, + 0.671875, + 0.671875 + ], + [ + 0.5, + 0.568359375, + 0.568359375 + ], + [ + 0.5, + 0.55859375, + 0.55859375 + ], + [ + 0.5, + 0.5859375, + 0.5859375 + ], + [ + 0.5, + 0.546875, + 0.546875 + ], + [ + 0.5, + 0.6171875, + 0.6171875 + ], + [ + 0.5, + 0.63671875, + 0.63671875 + ], + [ + 0.5, + 0.5859375, + 0.5859375 + ], + [ + 0.5, + 0.5859375, + 0.5859375 + ], + [ + 0.5, + 0.697265625, + 0.697265625 + ], + [ + 0.5, + 0.63671875, + 0.63671875 + ], + [ + 0.5, + 0.625, + 0.625 + ], + [ + 0.5, + 0.5859375, + 0.5859375 + ], + [ + 0.5, + 0.5859375, + 0.5859375 + ], + [ + 0.5, + 0.5859375, + 0.5859375 + ], + [ + 0.5, + 0.59375, + 0.59375 + ], + [ + 0.5, + 0.703125, + 0.703125 + ], + [ + 0.5, + 0.6328125, + 0.6328125 + ], + [ + 0.5, + 0.5859375, + 0.5859375 + ], + [ + 0.5, + 0.6328125, + 0.6328125 + ], + [ + 0.5, + 0.66015625, + 0.66015625 + ], + [ + 0.5, + 0.79296875, + 0.79296875 + ], + [ + 0.5, + 0.642578125, + 0.642578125 + ], + [ + 0.5, + 0.6875, + 0.6875 + ], + [ + 0.5, + 0.5859375, + 0.5859375 + ], + [ + 0.5, + 0.638671875, + 0.638671875 + ], + [ + 0.5, + 0.634765625, + 0.634765625 + ], + [ + 0.5, + 0.658203125, + 0.658203125 + ], + [ + 0.5, + 0.580078125, + 0.580078125 + ], + [ + 0.5, + 0.6875, + 0.6875 + ], + [ + 0.5, + 0.712890625, + 0.712890625 + ], + [ + 0.5, + 0.720703125, + 0.720703125 + ], + [ + 0.5, + 0.572265625, + 0.572265625 + ], + [ + 0.5, + 0.6328125, + 0.6328125 + ], + [ + 0.5, + 0.65625, + 0.65625 + ], + [ + 0.5, + 0.5859375, + 0.5859375 + ], + [ + 0.5, + 0.5859375, + 0.5859375 + ], + [ + 0.5, + 0.708984375, + 0.708984375 + ], + [ + 0.5, + 0.68359375, + 0.68359375 + ], + [ + 0.5, + 0.5625, + 0.5625 + ], + [ + 0.5, + 0.7421875, + 0.7421875 + ], + [ + 0.5, + 0.7421875, + 0.7421875 + ], + [ + 0.5, + 0.71484375, + 0.71484375 + ], + [ + 0.5, + 0.6328125, + 0.6328125 + ], + [ + 0.5, + 0.68359375, + 0.68359375 + ], + [ + 0.5, + 0.59375, + 0.59375 + ], + [ + 0.5, + 0.53515625, + 0.53515625 + ], + [ + 0.5, + 0.6875, + 0.6875 + ], + [ + 0.5, + 0.78125, + 0.78125 + ], + [ + 0.5, + 0.74609375, + 0.74609375 + ], + [ + 0.5, + 0.611328125, + 0.611328125 + ], + [ + 0.5, + 0.68359375, + 0.68359375 + ], + [ + 0.5, + 0.84375, + 0.84375 + ], + [ + 0.5, + 0.68359375, + 0.68359375 + ], + [ + 0.5, + 0.59375, + 0.59375 + ], + [ + 0.5, + 0.7265625, + 0.7265625 + ], + [ + 0.5, + 0.619140625, + 0.619140625 + ], + [ + 0.5, + 0.640625, + 0.640625 + ], + [ + 0.5, + 0.65625, + 0.65625 + ], + [ + 0.5, + 0.591796875, + 0.591796875 + ], + [ + 0.5, + 0.765625, + 0.765625 + ], + [ + 0.5, + 0.828125, + 0.828125 + ], + [ + 0.5, + 0.5390625, + 0.5390625 + ], + [ + 0.5, + 0.6328125, + 0.6328125 + ], + [ + 0.5, + 0.671875, + 0.671875 + ], + [ + 0.5, + 0.6015625, + 0.6015625 + ], + [ + 0.5, + 0.65625, + 0.65625 + ], + [ + 0.5, + 0.75390625, + 0.75390625 + ], + [ + 0.5, + 0.5859375, + 0.5859375 + ], + [ + 0.5, + 0.59375, + 0.59375 + ], + [ + 0.5, + 0.5390625, + 0.5390625 + ], + [ + 0.5, + 0.64453125, + 0.64453125 + ], + [ + 0.5, + 0.63671875, + 0.63671875 + ], + [ + 0.5, + 0.66015625, + 0.66015625 + ], + [ + 0.699999988079071, + 0.724609375, + 0.724609375 + ], + [ + 0.5, + 0.71875, + 0.71875 + ], + [ + 0.5, + 0.5859375, + 0.5859375 + ], + [ + 0.5, + 0.58984375, + 0.58984375 + ], + [ + 0.5, + 0.615234375, + 0.615234375 + ], + [ + 0.5, + 0.59765625, + 0.59765625 + ], + [ + 0.5, + 0.728515625, + 0.728515625 + ], + [ + 0.5, + 0.5859375, + 0.5859375 + ], + [ + 0.5, + 0.6015625, + 0.6015625 + ], + [ + 0.5, + 0.5859375, + 0.5859375 + ], + [ + 0.5, + 0.70703125, + 0.70703125 + ], + [ + 0.5, + 0.626953125, + 0.626953125 + ], + [ + 0.5, + 0.58203125, + 0.58203125 + ], + [ + 0.5, + 0.703125, + 0.703125 + ], + [ + 0.5, + 0.7109375, + 0.7109375 + ], + [ + 0.5, + 0.625, + 0.625 + ], + [ + 0.5, + 0.7421875, + 0.7421875 + ], + [ + 0.5, + 0.66015625, + 0.66015625 + ], + [ + 0.5, + 0.5859375, + 0.5859375 + ], + [ + 0.5, + 0.638671875, + 0.638671875 + ], + [ + 0.5, + 0.6484375, + 0.6484375 + ], + [ + 0.5, + 0.7421875, + 0.7421875 + ], + [ + 0.5, + 0.7265625, + 0.7265625 + ], + [ + 0.5, + 0.67578125, + 0.67578125 + ], + [ + 0.5, + 0.5859375, + 0.5859375 + ], + [ + 0.5, + 0.640625, + 0.640625 + ], + [ + 0.5, + 0.5859375, + 0.5859375 + ], + [ + 0.5, + 0.650390625, + 0.650390625 + ], + [ + 0.5, + 0.6171875, + 0.6171875 + ], + [ + 0.5, + 0.5859375, + 0.5859375 + ], + [ + 0.5, + 0.615234375, + 0.615234375 + ], + [ + 0.5, + 0.7421875, + 0.7421875 + ], + [ + 0.5, + 0.7890625, + 0.7890625 + ], + [ + 0.5, + 0.6640625, + 0.6640625 + ], + [ + 0.5, + 0.5859375, + 0.5859375 + ], + [ + 0.5, + 0.791015625, + 0.791015625 + ], + [ + 0.5, + 0.6484375, + 0.6484375 + ], + [ + 0.5, + 0.5859375, + 0.5859375 + ], + [ + 0.5, + 0.630859375, + 0.630859375 + ], + [ + 0.5, + 0.74609375, + 0.74609375 + ], + [ + 0.5, + 0.65234375, + 0.65234375 + ], + [ + 0.5, + 0.5859375, + 0.5859375 + ], + [ + 0.5, + 0.5859375, + 0.5859375 + ], + [ + 0.5, + 0.5859375, + 0.5859375 + ], + [ + 0.5, + 0.65625, + 0.65625 + ], + [ + 0.5, + 0.71484375, + 0.71484375 + ], + [ + 0.5, + 0.59375, + 0.59375 + ], + [ + 0.5, + 0.552734375, + 0.552734375 + ], + [ + 0.5, + 0.671875, + 0.671875 + ], + [ + 0.5, + 0.640625, + 0.640625 + ], + [ + 0.5, + 0.68359375, + 0.68359375 + ], + [ + 0.5, + 0.630859375, + 0.630859375 + ], + [ + 0.5, + 0.59765625, + 0.59765625 + ], + [ + 0.5, + 0.5859375, + 0.5859375 + ], + [ + 0.5, + 0.5859375, + 0.5859375 + ], + [ + 0.5, + 0.57421875, + 0.57421875 + ], + [ + 0.5, + 0.666015625, + 0.666015625 + ], + [ + 0.5, + 0.703125, + 0.703125 + ], + [ + 0.5, + 0.5546875, + 0.5546875 + ], + [ + 0.5, + 0.7421875, + 0.7421875 + ], + [ + 0.5, + 0.5859375, + 0.5859375 + ], + [ + 0.5, + 0.5859375, + 0.5859375 + ], + [ + 0.5, + 0.69921875, + 0.69921875 + ], + [ + 0.5, + 0.740234375, + 0.740234375 + ], + [ + 0.5, + 0.875, + 0.875 + ], + [ + 0.5, + 0.6328125, + 0.6328125 + ], + [ + 0.5, + 0.65234375, + 0.65234375 + ], + [ + 0.5, + 0.615234375, + 0.615234375 + ], + [ + 0.5, + 0.626953125, + 0.626953125 + ], + [ + 0.5, + 0.5859375, + 0.5859375 + ], + [ + 0.5, + 0.666015625, + 0.666015625 + ], + [ + 0.5, + 0.693359375, + 0.693359375 + ], + [ + 0.5, + 0.66796875, + 0.66796875 + ], + [ + 0.5, + 0.6328125, + 0.6328125 + ], + [ + 0.5, + 0.70703125, + 0.70703125 + ], + [ + 0.5, + 0.5859375, + 0.5859375 + ], + [ + 0.5, + 0.67578125, + 0.67578125 + ], + [ + 0.5, + 0.65625, + 0.65625 + ], + [ + 0.5, + 0.5859375, + 0.5859375 + ], + [ + 0.5, + 0.666015625, + 0.666015625 + ], + [ + 0.5, + 0.658203125, + 0.658203125 + ], + [ + 0.5, + 0.611328125, + 0.611328125 + ], + [ + 0.5, + 0.69140625, + 0.69140625 + ], + [ + 0.5, + 0.5859375, + 0.5859375 + ], + [ + 0.5, + 0.6328125, + 0.6328125 + ], + [ + 0.5, + 0.623046875, + 0.623046875 + ], + [ + 0.5, + 0.59765625, + 0.59765625 + ], + [ + 0.5, + 0.66015625, + 0.66015625 + ], + [ + 0.5, + 0.6328125, + 0.6328125 + ], + [ + 0.5, + 0.583984375, + 0.583984375 + ], + [ + 0.5, + 0.603515625, + 0.603515625 + ], + [ + 0.5, + 0.662109375, + 0.662109375 + ], + [ + 0.5, + 0.634765625, + 0.634765625 + ], + [ + 0.5, + 0.708984375, + 0.708984375 + ], + [ + 0.5, + 0.65625, + 0.65625 + ], + [ + 0.5, + 0.46484375, + 0.46484375 + ], + [ + 0.5, + 0.59765625, + 0.59765625 + ], + [ + 0.5, + 0.724609375, + 0.724609375 + ], + [ + 0.5, + 0.79296875, + 0.79296875 + ], + [ + 0.5, + 0.5859375, + 0.5859375 + ], + [ + 0.5, + 0.7421875, + 0.7421875 + ], + [ + 0.5, + 0.69140625, + 0.69140625 + ], + [ + 0.5, + 0.62890625, + 0.62890625 + ], + [ + 0.5, + 0.5859375, + 0.5859375 + ], + [ + 0.5, + 0.65625, + 0.65625 + ], + [ + 0.5, + 0.7109375, + 0.7109375 + ], + [ + 0.5, + 0.84375, + 0.84375 + ], + [ + 0.5, + 0.650390625, + 0.650390625 + ], + [ + 0.5, + 0.642578125, + 0.642578125 + ], + [ + 0.5, + 0.703125, + 0.703125 + ], + [ + 0.5, + 0.7421875, + 0.7421875 + ], + [ + 0.5, + 0.6875, + 0.6875 + ], + [ + 0.5, + 0.583984375, + 0.583984375 + ], + [ + 0.5, + 0.7421875, + 0.7421875 + ], + [ + 0.5, + 0.5859375, + 0.5859375 + ], + [ + 0.5, + 0.771484375, + 0.771484375 + ], + [ + 1.0, + 0.654296875, + 0.654296875 + ], + [ + 0.5, + 0.720703125, + 0.720703125 + ], + [ + 0.5, + 0.5859375, + 0.5859375 + ], + [ + 0.5, + 0.638671875, + 0.638671875 + ], + [ + 0.5, + 0.734375, + 0.734375 + ], + [ + 0.5, + 0.69921875, + 0.69921875 + ], + [ + 0.5, + 0.619140625, + 0.619140625 + ], + [ + 0.5, + 0.611328125, + 0.611328125 + ], + [ + 0.5, + 0.591796875, + 0.591796875 + ], + [ + 0.5, + 0.669921875, + 0.669921875 + ], + [ + 0.5, + 0.60546875, + 0.60546875 + ], + [ + 0.5, + 0.595703125, + 0.595703125 + ], + [ + 0.5, + 0.5859375, + 0.5859375 + ], + [ + 0.5, + 0.53515625, + 0.53515625 + ], + [ + 0.5, + 0.587890625, + 0.587890625 + ], + [ + 0.5, + 0.6171875, + 0.6171875 + ], + [ + 0.5, + 0.576171875, + 0.576171875 + ], + [ + 0.5, + 0.583984375, + 0.583984375 + ], + [ + 0.5, + 0.7421875, + 0.7421875 + ], + [ + 0.5, + 0.7421875, + 0.7421875 + ], + [ + 0.5, + 0.755859375, + 0.755859375 + ], + [ + 0.5, + 0.59765625, + 0.59765625 + ], + [ + 0.5, + 0.712890625, + 0.712890625 + ], + [ + 0.5, + 0.638671875, + 0.638671875 + ], + [ + 0.5, + 0.677734375, + 0.677734375 + ], + [ + 0.5, + 0.623046875, + 0.623046875 + ], + [ + 0.5, + 0.658203125, + 0.658203125 + ], + [ + 0.5, + 0.693359375, + 0.693359375 + ], + [ + 0.5, + 0.73046875, + 0.73046875 + ], + [ + 0.5, + 0.62109375, + 0.62109375 + ], + [ + 0.5, + 0.638671875, + 0.638671875 + ], + [ + 0.5, + 0.748046875, + 0.748046875 + ], + [ + 0.5, + 0.669921875, + 0.669921875 + ], + [ + 0.5, + 0.763671875, + 0.763671875 + ], + [ + 0.5, + 0.634765625, + 0.634765625 + ], + [ + 0.5, + 0.65234375, + 0.65234375 + ], + [ + 0.5, + 0.642578125, + 0.642578125 + ], + [ + 0.5, + 0.60546875, + 0.60546875 + ], + [ + 0.5, + 0.6953125, + 0.6953125 + ], + [ + 0.5, + 0.5859375, + 0.5859375 + ], + [ + 0.5, + 0.626953125, + 0.626953125 + ], + [ + 0.5, + 0.7421875, + 0.7421875 + ], + [ + 0.5, + 0.76953125, + 0.76953125 + ], + [ + 0.5, + 0.5859375, + 0.5859375 + ], + [ + 0.5, + 0.693359375, + 0.693359375 + ], + [ + 0.5, + 0.6953125, + 0.6953125 + ], + [ + 0.5, + 0.73046875, + 0.73046875 + ], + [ + 0.5, + 0.681640625, + 0.681640625 + ], + [ + 0.5, + 0.6171875, + 0.6171875 + ], + [ + 0.5, + 0.62109375, + 0.62109375 + ], + [ + 0.5, + 0.658203125, + 0.658203125 + ], + [ + 0.5, + 0.6328125, + 0.6328125 + ], + [ + 0.5, + 0.57421875, + 0.57421875 + ], + [ + 0.5, + 0.6953125, + 0.6953125 + ], + [ + 0.5, + 0.654296875, + 0.654296875 + ], + [ + 0.5, + 0.609375, + 0.609375 + ], + [ + 0.5, + 0.681640625, + 0.681640625 + ], + [ + 0.5, + 0.66015625, + 0.66015625 + ], + [ + 0.5, + 0.580078125, + 0.580078125 + ], + [ + 0.5, + 0.689453125, + 0.689453125 + ], + [ + 0.5, + 0.6015625, + 0.6015625 + ], + [ + 0.5, + 0.7421875, + 0.7421875 + ], + [ + 0.5, + 0.611328125, + 0.611328125 + ], + [ + 0.5, + 0.650390625, + 0.650390625 + ], + [ + 0.5, + 0.91015625, + 0.91015625 + ], + [ + 0.5, + 0.732421875, + 0.732421875 + ], + [ + 0.5, + 0.7109375, + 0.7109375 + ], + [ + 0.5, + 0.6875, + 0.6875 + ], + [ + 0.5, + 0.7421875, + 0.7421875 + ], + [ + 0.5, + 0.68359375, + 0.68359375 + ], + [ + 0.5, + 0.7421875, + 0.7421875 + ], + [ + 0.5, + 0.6484375, + 0.6484375 + ], + [ + 0.5, + 0.7421875, + 0.7421875 + ], + [ + 0.5, + 0.55078125, + 0.55078125 + ], + [ + 0.5, + 0.7265625, + 0.7265625 + ], + [ + 0.5, + 0.748046875, + 0.748046875 + ], + [ + 0.5, + 0.5859375, + 0.5859375 + ], + [ + 0.5, + 0.6484375, + 0.6484375 + ], + [ + 0.5, + 0.712890625, + 0.712890625 + ], + [ + 0.5, + 0.6015625, + 0.6015625 + ], + [ + 0.5, + 0.65234375, + 0.65234375 + ], + [ + 0.5, + 0.583984375, + 0.583984375 + ], + [ + 0.5, + 0.5859375, + 0.5859375 + ], + [ + 0.5, + 0.603515625, + 0.603515625 + ], + [ + 0.5, + 0.587890625, + 0.587890625 + ], + [ + 0.5, + 0.701171875, + 0.701171875 + ], + [ + 0.5, + 0.642578125, + 0.642578125 + ], + [ + 0.5, + 0.7578125, + 0.7578125 + ], + [ + 0.5, + 0.6171875, + 0.6171875 + ], + [ + 0.5, + 0.720703125, + 0.720703125 + ], + [ + 0.5, + 0.720703125, + 0.720703125 + ], + [ + 0.5, + 0.720703125, + 0.720703125 + ], + [ + 0.5, + 0.69921875, + 0.69921875 + ], + [ + 0.5, + 0.650390625, + 0.650390625 + ], + [ + 0.5, + 0.5859375, + 0.5859375 + ], + [ + 0.5, + 0.615234375, + 0.615234375 + ], + [ + 0.5, + 0.68359375, + 0.68359375 + ], + [ + 0.5, + 0.6796875, + 0.6796875 + ], + [ + 0.5, + 0.7421875, + 0.7421875 + ], + [ + 0.5, + 0.8203125, + 0.8203125 + ], + [ + 0.5, + 0.73046875, + 0.73046875 + ], + [ + 0.5, + 0.68359375, + 0.68359375 + ], + [ + 0.5, + 0.748046875, + 0.748046875 + ], + [ + 0.5, + 0.791015625, + 0.791015625 + ], + [ + 0.5, + 0.68359375, + 0.68359375 + ], + [ + 0.5, + 0.58203125, + 0.58203125 + ], + [ + 0.5, + 0.6640625, + 0.6640625 + ], + [ + 0.5, + 0.62890625, + 0.62890625 + ], + [ + 0.5, + 0.822265625, + 0.822265625 + ], + [ + 0.5, + 0.572265625, + 0.572265625 + ], + [ + 0.5, + 0.599609375, + 0.599609375 + ], + [ + 0.5, + 0.6796875, + 0.6796875 + ], + [ + 0.5, + 0.560546875, + 0.560546875 + ], + [ + 0.5, + 0.71875, + 0.71875 + ], + [ + 0.5, + 0.60546875, + 0.60546875 + ], + [ + 0.5, + 0.68359375, + 0.68359375 + ], + [ + 0.5, + 0.76953125, + 0.76953125 + ], + [ + 0.5, + 0.68359375, + 0.68359375 + ], + [ + 0.5, + 0.75390625, + 0.75390625 + ], + [ + 0.5, + 0.6328125, + 0.6328125 + ], + [ + 0.5, + 0.83203125, + 0.83203125 + ], + [ + 0.5, + 0.64453125, + 0.64453125 + ], + [ + 0.5, + 0.73828125, + 0.73828125 + ], + [ + 0.5, + 0.671875, + 0.671875 + ], + [ + 0.5, + 0.5546875, + 0.5546875 + ], + [ + 0.5, + 0.6484375, + 0.6484375 + ], + [ + 0.5, + 0.66015625, + 0.66015625 + ], + [ + 0.5, + 0.63671875, + 0.63671875 + ], + [ + 0.5, + 0.662109375, + 0.662109375 + ], + [ + 0.5, + 0.65625, + 0.65625 + ], + [ + 0.5, + 0.640625, + 0.640625 + ], + [ + 0.5, + 0.66015625, + 0.66015625 + ], + [ + 0.5, + 0.6171875, + 0.6171875 + ], + [ + 0.5, + 0.75, + 0.75 + ], + [ + 0.5, + 0.68359375, + 0.68359375 + ], + [ + 0.5, + 0.828125, + 0.828125 + ], + [ + 0.5, + 0.7109375, + 0.7109375 + ], + [ + 0.5, + 0.68359375, + 0.68359375 + ], + [ + 0.5, + 0.728515625, + 0.728515625 + ], + [ + 0.5, + 0.5859375, + 0.5859375 + ], + [ + 0.5, + 0.607421875, + 0.607421875 + ], + [ + 0.5, + 0.68359375, + 0.68359375 + ], + [ + 0.5, + 0.64453125, + 0.64453125 + ], + [ + 0.5, + 0.69921875, + 0.69921875 + ], + [ + 0.5, + 0.5546875, + 0.5546875 + ], + [ + 0.5, + 0.68359375, + 0.68359375 + ], + [ + 0.5, + 0.68359375, + 0.68359375 + ], + [ + 0.5, + 0.732421875, + 0.732421875 + ], + [ + 0.5, + 0.68359375, + 0.68359375 + ], + [ + 0.5, + 0.5859375, + 0.5859375 + ], + [ + 0.5, + 0.90234375, + 0.90234375 + ], + [ + 0.5, + 0.78125, + 0.78125 + ], + [ + 0.5, + 0.7890625, + 0.7890625 + ], + [ + 0.5, + 0.68359375, + 0.68359375 + ], + [ + 0.5, + 0.66015625, + 0.66015625 + ], + [ + 0.5, + 0.734375, + 0.734375 + ], + [ + 0.5, + 0.810546875, + 0.810546875 + ], + [ + 0.5, + 0.7734375, + 0.7734375 + ], + [ + 0.5, + 0.5859375, + 0.5859375 + ], + [ + 0.5, + 0.5859375, + 0.5859375 + ], + [ + 0.5, + 0.5859375, + 0.5859375 + ], + [ + 0.5, + 0.68359375, + 0.68359375 + ], + [ + 0.5, + 0.73046875, + 0.73046875 + ], + [ + 0.5, + 0.68359375, + 0.68359375 + ], + [ + 0.5, + 0.77734375, + 0.77734375 + ], + [ + 0.5, + 0.5859375, + 0.5859375 + ], + [ + 0.5, + 0.7109375, + 0.7109375 + ], + [ + 0.5, + 0.68359375, + 0.68359375 + ], + [ + 0.5, + 0.7890625, + 0.7890625 + ], + [ + 0.5, + 0.90625, + 0.90625 + ], + [ + 0.5, + 0.68359375, + 0.68359375 + ], + [ + 0.5, + 0.79296875, + 0.79296875 + ], + [ + 0.5, + 0.68359375, + 0.68359375 + ], + [ + 0.5, + 0.5546875, + 0.5546875 + ], + [ + 0.5, + 0.68359375, + 0.68359375 + ], + [ + 0.5, + 0.810546875, + 0.810546875 + ], + [ + 0.5, + 0.703125, + 0.703125 + ], + [ + 0.5, + 0.767578125, + 0.767578125 + ], + [ + 0.5, + 0.701171875, + 0.701171875 + ], + [ + 0.5, + 0.68359375, + 0.68359375 + ], + [ + 0.5, + 0.70703125, + 0.70703125 + ], + [ + 0.5, + 0.9453125, + 0.9453125 + ], + [ + 0.5, + 0.65625, + 0.65625 + ], + [ + 0.5, + 0.90625, + 0.90625 + ], + [ + 0.5, + 0.71484375, + 0.71484375 + ], + [ + 0.5, + 0.78125, + 0.78125 + ], + [ + 0.5, + 0.68359375, + 0.68359375 + ], + [ + 0.5, + 0.87109375, + 0.87109375 + ], + [ + 0.5, + 0.765625, + 0.765625 + ], + [ + 0.5, + 0.68359375, + 0.68359375 + ], + [ + 0.5, + 0.79296875, + 0.79296875 + ], + [ + 0.5, + 0.765625, + 0.765625 + ], + [ + 0.5, + 0.68359375, + 0.68359375 + ], + [ + 0.5, + 0.765625, + 0.765625 + ], + [ + 0.5, + 0.79296875, + 0.79296875 + ], + [ + 0.5, + 0.55078125, + 0.55078125 + ], + [ + 0.5, + 0.607421875, + 0.607421875 + ], + [ + 0.5, + 0.666015625, + 0.666015625 + ], + [ + 0.5, + 0.623046875, + 0.623046875 + ], + [ + 0.5, + 0.68359375, + 0.68359375 + ], + [ + 0.5, + 0.73046875, + 0.73046875 + ], + [ + 0.5, + 0.78515625, + 0.78515625 + ], + [ + 0.5, + 0.68359375, + 0.68359375 + ], + [ + 0.5, + 0.68359375, + 0.68359375 + ], + [ + 0.5, + 0.70703125, + 0.70703125 + ], + [ + 0.5, + 0.65625, + 0.65625 + ], + [ + 0.5, + 0.693359375, + 0.693359375 + ], + [ + 0.5, + 0.73046875, + 0.73046875 + ], + [ + 0.5, + 0.80078125, + 0.80078125 + ], + [ + 0.5, + 0.669921875, + 0.669921875 + ], + [ + 0.5, + 0.736328125, + 0.736328125 + ], + [ + 0.5, + 0.732421875, + 0.732421875 + ], + [ + 0.5, + 0.640625, + 0.640625 + ], + [ + 0.5, + 0.68359375, + 0.68359375 + ], + [ + 0.5, + 0.65625, + 0.65625 + ], + [ + 0.5, + 0.6875, + 0.6875 + ], + [ + 0.5, + 0.78515625, + 0.78515625 + ], + [ + 0.5, + 0.58203125, + 0.58203125 + ], + [ + 0.5, + 0.580078125, + 0.580078125 + ], + [ + 0.5, + 0.69921875, + 0.69921875 + ], + [ + 0.5, + 0.8515625, + 0.8515625 + ], + [ + 0.5, + 0.78125, + 0.78125 + ], + [ + 0.5, + 0.59765625, + 0.59765625 + ], + [ + 0.5, + 0.84375, + 0.84375 + ], + [ + 0.5, + 0.62109375, + 0.62109375 + ], + [ + 0.5, + 0.734375, + 0.734375 + ], + [ + 0.5, + 0.728515625, + 0.728515625 + ], + [ + 0.5, + 0.88671875, + 0.88671875 + ], + [ + 0.5, + 0.734375, + 0.734375 + ], + [ + 0.5, + 0.8359375, + 0.8359375 + ], + [ + 0.5, + 0.64453125, + 0.64453125 + ], + [ + 0.5, + 0.7578125, + 0.7578125 + ], + [ + 0.5, + 0.748046875, + 0.748046875 + ], + [ + 0.5, + 0.7890625, + 0.7890625 + ], + [ + 0.4000000059604645, + 0.666015625, + 0.666015625 + ], + [ + 0.5, + 0.572265625, + 0.572265625 + ], + [ + 0.5, + 0.64453125, + 0.64453125 + ], + [ + 0.5, + 0.537109375, + 0.537109375 + ], + [ + 0.5, + 0.73828125, + 0.73828125 + ], + [ + 0.5, + 0.78515625, + 0.78515625 + ], + [ + 0.5, + 0.76171875, + 0.76171875 + ], + [ + 0.5, + 0.828125, + 0.828125 + ], + [ + 0.5, + 0.662109375, + 0.662109375 + ], + [ + 0.5, + 0.6640625, + 0.6640625 + ], + [ + 0.5, + 0.619140625, + 0.619140625 + ], + [ + 0.5, + 0.78125, + 0.78125 + ], + [ + 0.5, + 0.896484375, + 0.896484375 + ], + [ + 0.5, + 0.71484375, + 0.71484375 + ], + [ + 0.5, + 0.712890625, + 0.712890625 + ], + [ + 0.5, + 0.7109375, + 0.7109375 + ], + [ + 0.5, + 0.68359375, + 0.68359375 + ], + [ + 0.5, + 0.65234375, + 0.65234375 + ], + [ + 0.5, + 0.76171875, + 0.76171875 + ], + [ + 0.5, + 0.708984375, + 0.708984375 + ], + [ + 0.5, + 0.75390625, + 0.75390625 + ], + [ + 0.5, + 0.681640625, + 0.681640625 + ], + [ + 0.5, + 0.796875, + 0.796875 + ], + [ + 0.5, + 0.68359375, + 0.68359375 + ], + [ + 0.5, + 0.814453125, + 0.814453125 + ], + [ + 0.5, + 0.78515625, + 0.78515625 + ], + [ + 0.5, + 0.681640625, + 0.681640625 + ], + [ + 0.5, + 0.7421875, + 0.7421875 + ], + [ + 0.5, + 0.828125, + 0.828125 + ], + [ + 0.5, + 0.80078125, + 0.80078125 + ], + [ + 0.5, + 0.73046875, + 0.73046875 + ], + [ + 0.5, + 0.6640625, + 0.6640625 + ], + [ + 0.5, + 0.77734375, + 0.77734375 + ], + [ + 0.5, + 0.84765625, + 0.84765625 + ], + [ + 0.5, + 0.732421875, + 0.732421875 + ], + [ + 0.5, + 0.76171875, + 0.76171875 + ], + [ + 0.5, + 0.7265625, + 0.7265625 + ], + [ + 0.5, + 0.724609375, + 0.724609375 + ], + [ + 0.5, + 0.859375, + 0.859375 + ], + [ + 0.5, + 0.69921875, + 0.69921875 + ], + [ + 0.5, + 0.68359375, + 0.68359375 + ], + [ + 0.5, + 0.630859375, + 0.630859375 + ], + [ + 0.5, + 0.69921875, + 0.69921875 + ], + [ + 0.5, + 0.626953125, + 0.626953125 + ], + [ + 0.5, + 0.69140625, + 0.69140625 + ], + [ + 0.5, + 0.67578125, + 0.67578125 + ], + [ + 0.5, + 0.755859375, + 0.755859375 + ], + [ + 0.5, + 0.650390625, + 0.650390625 + ], + [ + 0.5, + 0.70703125, + 0.70703125 + ], + [ + 0.5, + 0.75390625, + 0.75390625 + ], + [ + 0.5, + 0.6796875, + 0.6796875 + ], + [ + 0.5, + 0.7578125, + 0.7578125 + ], + [ + 0.5, + 0.82421875, + 0.82421875 + ], + [ + 0.5, + 0.76171875, + 0.76171875 + ], + [ + 0.5, + 0.6875, + 0.6875 + ], + [ + 0.5, + 0.712890625, + 0.712890625 + ], + [ + 0.5, + 0.703125, + 0.703125 + ], + [ + 0.5, + 0.6796875, + 0.6796875 + ], + [ + 0.5, + 0.765625, + 0.765625 + ], + [ + 0.5, + 0.6484375, + 0.6484375 + ], + [ + 0.5, + 0.677734375, + 0.677734375 + ], + [ + 0.5, + 0.765625, + 0.765625 + ], + [ + 0.5, + 0.84375, + 0.84375 + ], + [ + 0.5, + 0.76953125, + 0.76953125 + ], + [ + 0.5, + 0.71875, + 0.71875 + ], + [ + 0.5, + 0.740234375, + 0.740234375 + ], + [ + 0.5, + 0.517578125, + 0.517578125 + ], + [ + 0.5, + 0.6953125, + 0.6953125 + ], + [ + 0.5, + 0.61328125, + 0.61328125 + ], + [ + 0.5, + 0.583984375, + 0.583984375 + ], + [ + 0.5, + 0.7109375, + 0.7109375 + ], + [ + 0.5, + 0.646484375, + 0.646484375 + ], + [ + 0.5, + 0.8359375, + 0.8359375 + ], + [ + 0.5, + 0.69921875, + 0.69921875 + ], + [ + 0.5, + 0.607421875, + 0.607421875 + ], + [ + 0.5, + 0.701171875, + 0.701171875 + ], + [ + 0.5, + 0.7109375, + 0.7109375 + ], + [ + 0.5, + 0.77734375, + 0.77734375 + ], + [ + 0.5, + 0.72265625, + 0.72265625 + ], + [ + 0.5, + 0.64453125, + 0.64453125 + ], + [ + 0.4000000059604645, + 0.6875, + 0.6875 + ], + [ + 0.5, + 0.76953125, + 0.76953125 + ], + [ + 0.5, + 0.68359375, + 0.68359375 + ], + [ + 0.5, + 0.69140625, + 0.69140625 + ], + [ + 0.5, + 0.671875, + 0.671875 + ], + [ + 0.5, + 0.828125, + 0.828125 + ], + [ + 0.5, + 0.6015625, + 0.6015625 + ], + [ + 0.5, + 0.646484375, + 0.646484375 + ], + [ + 0.5, + 0.708984375, + 0.708984375 + ], + [ + 0.5, + 0.828125, + 0.828125 + ], + [ + 0.5, + 0.744140625, + 0.744140625 + ], + [ + 0.5, + 0.796875, + 0.796875 + ], + [ + 0.5, + 0.6875, + 0.6875 + ], + [ + 0.5, + 0.7265625, + 0.7265625 + ], + [ + 0.5, + 0.68359375, + 0.68359375 + ], + [ + 0.5, + 0.8046875, + 0.8046875 + ], + [ + 0.5, + 0.693359375, + 0.693359375 + ], + [ + 0.5, + 0.744140625, + 0.744140625 + ], + [ + 0.5, + 0.578125, + 0.578125 + ], + [ + 0.5, + 0.744140625, + 0.744140625 + ], + [ + 0.5, + 0.74609375, + 0.74609375 + ], + [ + 0.5, + 0.68359375, + 0.68359375 + ], + [ + 0.5, + 0.6875, + 0.6875 + ], + [ + 0.5, + 0.73046875, + 0.73046875 + ], + [ + 0.5, + 0.69921875, + 0.69921875 + ], + [ + 0.5, + 0.87890625, + 0.87890625 + ], + [ + 0.5, + 0.77734375, + 0.77734375 + ], + [ + 0.5, + 0.6875, + 0.6875 + ], + [ + 0.5, + 0.77734375, + 0.77734375 + ], + [ + 0.5, + 0.716796875, + 0.716796875 + ], + [ + 0.5, + 0.666015625, + 0.666015625 + ], + [ + 0.5, + 0.697265625, + 0.697265625 + ], + [ + 0.5, + 0.6875, + 0.6875 + ], + [ + 0.5, + 0.73046875, + 0.73046875 + ], + [ + 0.5, + 0.62109375, + 0.62109375 + ], + [ + 0.5, + 0.8046875, + 0.8046875 + ], + [ + 0.5, + 0.806640625, + 0.806640625 + ], + [ + 0.5, + 0.65234375, + 0.65234375 + ], + [ + 0.5, + 0.943359375, + 0.943359375 + ], + [ + 0.5, + 0.703125, + 0.703125 + ], + [ + 0.5, + 0.595703125, + 0.595703125 + ], + [ + 0.5, + 0.734375, + 0.734375 + ], + [ + 0.5, + 0.70703125, + 0.70703125 + ], + [ + 0.5, + 0.716796875, + 0.716796875 + ], + [ + 0.5, + 0.71484375, + 0.71484375 + ], + [ + 0.5, + 0.77734375, + 0.77734375 + ], + [ + 0.5, + 0.6796875, + 0.6796875 + ], + [ + 0.5, + 0.83203125, + 0.83203125 + ], + [ + 0.5, + 0.7421875, + 0.7421875 + ], + [ + 0.5, + 0.70703125, + 0.70703125 + ], + [ + 0.5, + 0.73828125, + 0.73828125 + ], + [ + 0.5, + 0.66796875, + 0.66796875 + ], + [ + 0.5, + 0.642578125, + 0.642578125 + ], + [ + 0.5, + 0.73046875, + 0.73046875 + ], + [ + 0.5, + 0.740234375, + 0.740234375 + ], + [ + 0.5, + 0.765625, + 0.765625 + ], + [ + 0.5, + 0.783203125, + 0.783203125 + ], + [ + 0.5, + 0.67578125, + 0.67578125 + ], + [ + 0.5, + 0.7265625, + 0.7265625 + ], + [ + 0.5, + 0.84375, + 0.84375 + ], + [ + 0.5, + 0.72265625, + 0.72265625 + ], + [ + 0.5, + 0.615234375, + 0.615234375 + ], + [ + 0.5, + 0.66015625, + 0.66015625 + ], + [ + 0.5, + 0.71484375, + 0.71484375 + ], + [ + 0.5, + 0.66015625, + 0.66015625 + ], + [ + 0.5, + 0.73828125, + 0.73828125 + ], + [ + 0.5, + 0.681640625, + 0.681640625 + ], + [ + 0.5, + 0.80859375, + 0.80859375 + ], + [ + 0.5, + 0.6640625, + 0.6640625 + ], + [ + 0.5, + 0.693359375, + 0.693359375 + ], + [ + 0.5, + 0.74609375, + 0.74609375 + ], + [ + 0.5, + 0.802734375, + 0.802734375 + ], + [ + 0.5, + 0.595703125, + 0.595703125 + ], + [ + 0.5, + 0.7265625, + 0.7265625 + ], + [ + 0.5, + 0.947265625, + 0.947265625 + ], + [ + 0.5, + 0.63671875, + 0.63671875 + ], + [ + 0.5, + 0.609375, + 0.609375 + ], + [ + 0.5, + 0.7109375, + 0.7109375 + ], + [ + 0.5, + 0.7578125, + 0.7578125 + ], + [ + 0.5, + 0.60546875, + 0.60546875 + ], + [ + 0.5, + 0.771484375, + 0.771484375 + ], + [ + 0.5, + 0.8359375, + 0.8359375 + ], + [ + 0.5, + 0.748046875, + 0.748046875 + ], + [ + 0.5, + 0.9765625, + 0.9765625 + ], + [ + 0.5, + 0.798828125, + 0.798828125 + ], + [ + 0.5, + 0.734375, + 0.734375 + ], + [ + 0.5, + 0.6640625, + 0.6640625 + ], + [ + 0.5, + 0.732421875, + 0.732421875 + ], + [ + 0.5, + 0.73046875, + 0.73046875 + ], + [ + 0.5, + 0.78125, + 0.78125 + ], + [ + 0.5, + 0.654296875, + 0.654296875 + ], + [ + 0.5, + 0.8515625, + 0.8515625 + ], + [ + 0.5, + 0.79296875, + 0.79296875 + ], + [ + 0.5, + 0.7890625, + 0.7890625 + ], + [ + 0.5, + 0.66796875, + 0.66796875 + ], + [ + 0.5, + 0.7109375, + 0.7109375 + ], + [ + 0.5, + 0.71875, + 0.71875 + ], + [ + 0.5, + 0.703125, + 0.703125 + ], + [ + 0.5, + 0.74609375, + 0.74609375 + ], + [ + 0.5, + 0.7109375, + 0.7109375 + ], + [ + 0.5, + 0.84765625, + 0.84765625 + ], + [ + 0.5, + 0.76171875, + 0.76171875 + ], + [ + 0.5, + 0.69140625, + 0.69140625 + ], + [ + 0.5, + 0.859375, + 0.859375 + ], + [ + 0.5, + 0.78515625, + 0.78515625 + ], + [ + 0.5, + 0.619140625, + 0.619140625 + ], + [ + 0.5, + 0.73828125, + 0.73828125 + ], + [ + 0.5, + 0.732421875, + 0.732421875 + ], + [ + 0.5, + 0.7421875, + 0.7421875 + ], + [ + 0.5, + 0.875, + 0.875 + ], + [ + 0.5, + 0.84375, + 0.84375 + ], + [ + 0.5, + 0.775390625, + 0.775390625 + ], + [ + 0.5, + 0.6171875, + 0.6171875 + ], + [ + 0.5, + 0.830078125, + 0.830078125 + ], + [ + 0.5, + 0.84765625, + 0.84765625 + ], + [ + 0.5, + 0.751953125, + 0.751953125 + ], + [ + 0.5, + 0.7265625, + 0.7265625 + ], + [ + 0.5, + 0.833984375, + 0.833984375 + ], + [ + 0.5, + 0.76171875, + 0.76171875 + ], + [ + 0.5, + 0.640625, + 0.640625 + ], + [ + 0.5, + 0.65234375, + 0.65234375 + ], + [ + 0.5, + 0.6875, + 0.6875 + ], + [ + 0.5, + 0.66796875, + 0.66796875 + ], + [ + 0.5, + 0.70703125, + 0.70703125 + ], + [ + 0.5, + 0.71484375, + 0.71484375 + ], + [ + 0.5, + 0.75390625, + 0.75390625 + ], + [ + 0.5, + 0.77734375, + 0.77734375 + ], + [ + 0.5, + 0.76953125, + 0.76953125 + ], + [ + 0.5, + 0.80859375, + 0.80859375 + ], + [ + 0.5, + 0.76171875, + 0.76171875 + ], + [ + 0.5, + 0.712890625, + 0.712890625 + ], + [ + 0.5, + 0.796875, + 0.796875 + ], + [ + 0.5, + 0.859375, + 0.859375 + ], + [ + 0.5, + 0.79296875, + 0.79296875 + ], + [ + 0.5, + 0.62890625, + 0.62890625 + ], + [ + 0.5, + 0.7734375, + 0.7734375 + ], + [ + 0.5, + 0.69921875, + 0.69921875 + ], + [ + 0.5, + 0.83203125, + 0.83203125 + ], + [ + 0.5, + 0.953125, + 0.953125 + ], + [ + 0.5, + 0.88671875, + 0.88671875 + ], + [ + 0.5, + 0.841796875, + 0.841796875 + ], + [ + 0.5, + 0.732421875, + 0.732421875 + ], + [ + 0.5, + 0.84765625, + 0.84765625 + ], + [ + 0.5, + 0.7109375, + 0.7109375 + ], + [ + 0.5, + 0.6953125, + 0.6953125 + ], + [ + 0.5, + 0.638671875, + 0.638671875 + ], + [ + 0.5, + 0.6875, + 0.6875 + ], + [ + 0.5, + 0.64453125, + 0.64453125 + ], + [ + 0.5, + 0.6484375, + 0.6484375 + ], + [ + 0.5, + 0.6796875, + 0.6796875 + ], + [ + 0.5, + 0.91015625, + 0.91015625 + ], + [ + 0.5, + 0.740234375, + 0.740234375 + ], + [ + 0.5, + 0.6328125, + 0.6328125 + ], + [ + 0.5, + 0.68359375, + 0.68359375 + ], + [ + 0.5, + 0.91015625, + 0.91015625 + ], + [ + 0.5, + 0.796875, + 0.796875 + ], + [ + 0.5, + 0.720703125, + 0.720703125 + ], + [ + 0.5, + 0.70703125, + 0.70703125 + ], + [ + 0.5, + 0.830078125, + 0.830078125 + ], + [ + 0.5, + 0.75, + 0.75 + ], + [ + 0.5, + 0.69921875, + 0.69921875 + ], + [ + 0.5, + 0.85546875, + 0.85546875 + ], + [ + 0.5, + 0.60546875, + 0.60546875 + ], + [ + 0.5, + 0.77734375, + 0.77734375 + ], + [ + 0.5, + 0.65234375, + 0.65234375 + ], + [ + 0.5, + 0.685546875, + 0.685546875 + ], + [ + 0.5, + 0.69140625, + 0.69140625 + ], + [ + 0.5, + 0.69140625, + 0.69140625 + ], + [ + 0.5, + 0.75390625, + 0.75390625 + ], + [ + 0.5, + 0.75, + 0.75 + ], + [ + 0.5, + 0.724609375, + 0.724609375 + ], + [ + 0.5, + 0.71484375, + 0.71484375 + ], + [ + 0.5, + 0.734375, + 0.734375 + ], + [ + 0.5, + 0.75, + 0.75 + ], + [ + 0.5, + 0.73828125, + 0.73828125 + ], + [ + 0.5, + 0.69140625, + 0.69140625 + ], + [ + 0.5, + 0.72265625, + 0.72265625 + ], + [ + 0.5, + 0.6953125, + 0.6953125 + ], + [ + 0.5, + 0.939453125, + 0.939453125 + ], + [ + 0.5, + 0.8203125, + 0.8203125 + ], + [ + 0.5, + 0.7734375, + 0.7734375 + ], + [ + 0.5, + 0.607421875, + 0.607421875 + ], + [ + 0.5, + 0.626953125, + 0.626953125 + ], + [ + 0.5, + 0.8046875, + 0.8046875 + ], + [ + 0.5, + 0.69921875, + 0.69921875 + ], + [ + 0.5, + 0.703125, + 0.703125 + ], + [ + 0.5, + 0.8046875, + 0.8046875 + ], + [ + 0.5, + 0.7421875, + 0.7421875 + ], + [ + 0.5, + 0.9765625, + 0.9765625 + ], + [ + 0.5, + 0.642578125, + 0.642578125 + ], + [ + 0.5, + 0.720703125, + 0.720703125 + ], + [ + 0.5, + 0.78125, + 0.78125 + ], + [ + 0.5, + 0.712890625, + 0.712890625 + ], + [ + 0.5, + 0.78125, + 0.78125 + ], + [ + 0.5, + 0.728515625, + 0.728515625 + ], + [ + 0.5, + 0.734375, + 0.734375 + ], + [ + 0.5, + 0.677734375, + 0.677734375 + ], + [ + 0.5, + 0.71875, + 0.71875 + ], + [ + 0.5, + 0.69921875, + 0.69921875 + ], + [ + 0.5, + 0.69140625, + 0.69140625 + ], + [ + 0.5, + 0.802734375, + 0.802734375 + ], + [ + 0.5, + 0.734375, + 0.734375 + ], + [ + 0.5, + 0.76953125, + 0.76953125 + ], + [ + 0.5, + 0.765625, + 0.765625 + ], + [ + 0.5, + 0.8125, + 0.8125 + ], + [ + 0.5, + 0.65625, + 0.65625 + ], + [ + 0.5, + 0.8515625, + 0.8515625 + ], + [ + 0.5, + 0.69140625, + 0.69140625 + ], + [ + 0.5, + 0.70703125, + 0.70703125 + ], + [ + 0.5, + 0.875, + 0.875 + ], + [ + 0.5, + 0.689453125, + 0.689453125 + ], + [ + 0.5, + 0.68359375, + 0.68359375 + ], + [ + 0.5, + 0.71484375, + 0.71484375 + ], + [ + 0.5, + 0.76953125, + 0.76953125 + ], + [ + 0.5, + 0.822265625, + 0.822265625 + ], + [ + 0.5, + 0.71875, + 0.71875 + ], + [ + 0.5, + 0.787109375, + 0.787109375 + ], + [ + 0.5, + 0.609375, + 0.609375 + ], + [ + 0.5, + 0.744140625, + 0.744140625 + ], + [ + 0.5, + 0.75, + 0.75 + ], + [ + 0.5, + 0.66796875, + 0.66796875 + ], + [ + 0.5, + 0.74609375, + 0.74609375 + ], + [ + 0.5, + 0.7734375, + 0.7734375 + ], + [ + 0.5, + 0.69921875, + 0.69921875 + ], + [ + 0.5, + 0.6796875, + 0.6796875 + ], + [ + 0.5, + 0.7109375, + 0.7109375 + ], + [ + 0.5, + 0.69140625, + 0.69140625 + ], + [ + 0.5, + 0.521484375, + 0.521484375 + ], + [ + 0.5, + 0.8515625, + 0.8515625 + ], + [ + 0.5, + 0.69140625, + 0.69140625 + ], + [ + 0.5, + 0.73828125, + 0.73828125 + ], + [ + 0.5, + 0.734375, + 0.734375 + ], + [ + 0.5, + 0.84765625, + 0.84765625 + ], + [ + 0.5, + 0.8046875, + 0.8046875 + ], + [ + 0.5, + 0.771484375, + 0.771484375 + ], + [ + 0.5, + 0.666015625, + 0.666015625 + ], + [ + 0.5, + 0.72265625, + 0.72265625 + ], + [ + 0.5, + 0.759765625, + 0.759765625 + ], + [ + 0.5, + 0.78125, + 0.78125 + ], + [ + 0.5, + 0.681640625, + 0.681640625 + ], + [ + 0.5, + 0.6953125, + 0.6953125 + ], + [ + 0.5, + 0.78125, + 0.78125 + ], + [ + 0.5, + 0.740234375, + 0.740234375 + ], + [ + 0.5, + 0.64453125, + 0.64453125 + ], + [ + 0.5, + 0.673828125, + 0.673828125 + ], + [ + 0.5, + 0.87890625, + 0.87890625 + ], + [ + 0.5, + 0.673828125, + 0.673828125 + ], + [ + 0.5, + 0.57421875, + 0.57421875 + ], + [ + 0.5, + 0.703125, + 0.703125 + ], + [ + 0.5, + 0.673828125, + 0.673828125 + ], + [ + 0.5, + 0.580078125, + 0.580078125 + ], + [ + 0.5, + 0.85546875, + 0.85546875 + ], + [ + 0.5, + 0.734375, + 0.734375 + ], + [ + 0.5, + 0.75390625, + 0.75390625 + ], + [ + 0.5, + 0.734375, + 0.734375 + ], + [ + 0.5, + 0.7890625, + 0.7890625 + ], + [ + 0.5, + 0.84765625, + 0.84765625 + ], + [ + 0.5, + 0.86328125, + 0.86328125 + ], + [ + 0.5, + 0.8671875, + 0.8671875 + ], + [ + 0.5, + 0.70703125, + 0.70703125 + ], + [ + 0.5, + 0.734375, + 0.734375 + ], + [ + 0.5, + 0.76953125, + 0.76953125 + ], + [ + 0.5, + 0.7265625, + 0.7265625 + ], + [ + 0.5, + 0.626953125, + 0.626953125 + ], + [ + 0.5, + 0.7578125, + 0.7578125 + ], + [ + 0.5, + 0.76953125, + 0.76953125 + ], + [ + 0.5, + 0.7890625, + 0.7890625 + ], + [ + 0.5, + 0.63671875, + 0.63671875 + ], + [ + 0.5, + 0.630859375, + 0.630859375 + ], + [ + 0.5, + 0.826171875, + 0.826171875 + ], + [ + 0.5, + 0.69140625, + 0.69140625 + ], + [ + 0.5, + 0.8203125, + 0.8203125 + ], + [ + 0.5, + 0.857421875, + 0.857421875 + ], + [ + 0.5, + 0.744140625, + 0.744140625 + ], + [ + 0.5, + 0.716796875, + 0.716796875 + ], + [ + 0.5, + 0.75, + 0.75 + ], + [ + 0.5, + 0.7734375, + 0.7734375 + ], + [ + 0.5, + 0.79296875, + 0.79296875 + ], + [ + 0.5, + 0.685546875, + 0.685546875 + ], + [ + 0.5, + 0.6171875, + 0.6171875 + ], + [ + 0.5, + 0.70703125, + 0.70703125 + ], + [ + 0.5, + 0.76953125, + 0.76953125 + ], + [ + 0.5, + 0.76953125, + 0.76953125 + ], + [ + 0.5, + 0.728515625, + 0.728515625 + ], + [ + 0.5, + 0.6171875, + 0.6171875 + ], + [ + 0.5, + 0.787109375, + 0.787109375 + ], + [ + 0.5, + 0.619140625, + 0.619140625 + ], + [ + 0.5, + 0.671875, + 0.671875 + ], + [ + 0.5, + 0.84375, + 0.84375 + ], + [ + 0.5, + 0.67578125, + 0.67578125 + ], + [ + 0.5, + 0.67578125, + 0.67578125 + ], + [ + 0.5, + 0.798828125, + 0.798828125 + ], + [ + 0.5, + 0.720703125, + 0.720703125 + ], + [ + 0.5, + 0.59375, + 0.59375 + ], + [ + 0.5, + 0.7109375, + 0.7109375 + ], + [ + 0.5, + 0.65625, + 0.65625 + ], + [ + 0.5, + 0.78125, + 0.78125 + ], + [ + 0.5, + 0.58203125, + 0.58203125 + ], + [ + 0.5, + 0.740234375, + 0.740234375 + ], + [ + 0.5, + 0.775390625, + 0.775390625 + ], + [ + 0.5, + 0.548828125, + 0.548828125 + ], + [ + 0.5, + 0.66796875, + 0.66796875 + ], + [ + 0.5, + 0.796875, + 0.796875 + ], + [ + 0.5, + 0.67578125, + 0.67578125 + ], + [ + 0.5, + 0.703125, + 0.703125 + ], + [ + 0.5, + 0.658203125, + 0.658203125 + ], + [ + 0.5, + 0.67578125, + 0.67578125 + ], + [ + 0.5, + 0.953125, + 0.953125 + ], + [ + 0.5, + 0.66796875, + 0.66796875 + ], + [ + 0.5, + 0.87890625, + 0.87890625 + ], + [ + 0.5, + 0.7109375, + 0.7109375 + ], + [ + 0.5, + 0.5859375, + 0.5859375 + ], + [ + 0.5, + 0.744140625, + 0.744140625 + ], + [ + 0.5, + 0.70703125, + 0.70703125 + ], + [ + 0.5, + 0.6796875, + 0.6796875 + ], + [ + 0.5, + 0.7421875, + 0.7421875 + ], + [ + 0.5, + 0.6953125, + 0.6953125 + ], + [ + 0.5, + 0.580078125, + 0.580078125 + ], + [ + 0.5, + 0.64453125, + 0.64453125 + ], + [ + 0.5, + 0.658203125, + 0.658203125 + ], + [ + 0.5, + 0.740234375, + 0.740234375 + ], + [ + 0.5, + 0.875, + 0.875 + ], + [ + 0.5, + 0.734375, + 0.734375 + ], + [ + 0.5, + 0.720703125, + 0.720703125 + ], + [ + 0.5, + 0.6171875, + 0.6171875 + ], + [ + 0.5, + 0.611328125, + 0.611328125 + ], + [ + 0.5, + 0.69140625, + 0.69140625 + ], + [ + 0.5, + 0.7109375, + 0.7109375 + ], + [ + 0.5, + 0.787109375, + 0.787109375 + ], + [ + 0.5, + 0.734375, + 0.734375 + ], + [ + 0.5, + 0.720703125, + 0.720703125 + ], + [ + 0.5, + 0.783203125, + 0.783203125 + ], + [ + 0.5, + 0.732421875, + 0.732421875 + ], + [ + 0.5, + 0.9765625, + 0.9765625 + ], + [ + 0.5, + 0.689453125, + 0.689453125 + ], + [ + 0.5, + 0.791015625, + 0.791015625 + ], + [ + 0.5, + 0.8359375, + 0.8359375 + ], + [ + 0.5, + 0.701171875, + 0.701171875 + ], + [ + 0.5, + 0.59375, + 0.59375 + ], + [ + 0.5, + 0.62109375, + 0.62109375 + ], + [ + 0.5, + 0.830078125, + 0.830078125 + ], + [ + 0.5, + 0.759765625, + 0.759765625 + ], + [ + 0.5, + 0.62890625, + 0.62890625 + ], + [ + 0.5, + 0.6953125, + 0.6953125 + ], + [ + 0.5, + 0.640625, + 0.640625 + ], + [ + 0.5, + 0.6171875, + 0.6171875 + ], + [ + 0.5, + 0.68359375, + 0.68359375 + ], + [ + 0.5, + 0.94921875, + 0.94921875 + ], + [ + 0.5, + 0.76953125, + 0.76953125 + ], + [ + 0.5, + 0.76953125, + 0.76953125 + ], + [ + 0.5, + 0.76171875, + 0.76171875 + ], + [ + 0.5, + 0.7265625, + 0.7265625 + ], + [ + 0.5, + 0.71484375, + 0.71484375 + ], + [ + 0.5, + 0.740234375, + 0.740234375 + ], + [ + 0.5, + 0.720703125, + 0.720703125 + ], + [ + 0.5, + 0.63671875, + 0.63671875 + ], + [ + 0.5, + 0.8359375, + 0.8359375 + ], + [ + 0.5, + 0.625, + 0.625 + ], + [ + 0.5, + 0.76953125, + 0.76953125 + ], + [ + 0.5, + 0.84765625, + 0.84765625 + ], + [ + 0.5, + 0.73046875, + 0.73046875 + ], + [ + 0.5, + 0.59765625, + 0.59765625 + ], + [ + 0.5, + 0.61328125, + 0.61328125 + ], + [ + 0.5, + 0.84375, + 0.84375 + ], + [ + 0.5, + 0.65234375, + 0.65234375 + ], + [ + 0.5, + 0.73046875, + 0.73046875 + ], + [ + 0.5, + 0.6875, + 0.6875 + ], + [ + 0.5, + 0.56640625, + 0.56640625 + ], + [ + 0.5, + 0.92578125, + 0.92578125 + ], + [ + 0.5, + 0.65234375, + 0.65234375 + ], + [ + 0.5, + 0.96484375, + 0.96484375 + ], + [ + 0.5, + 0.865234375, + 0.865234375 + ], + [ + 0.5, + 0.720703125, + 0.720703125 + ], + [ + 0.5, + 0.66796875, + 0.66796875 + ], + [ + 0.5, + 0.685546875, + 0.685546875 + ], + [ + 0.5, + 0.763671875, + 0.763671875 + ], + [ + 0.5, + 0.62109375, + 0.62109375 + ], + [ + 0.5, + 0.67578125, + 0.67578125 + ], + [ + 0.5, + 0.78125, + 0.78125 + ], + [ + 0.5, + 0.689453125, + 0.689453125 + ], + [ + 0.5, + 0.611328125, + 0.611328125 + ], + [ + 0.5, + 0.75390625, + 0.75390625 + ], + [ + 0.5, + 0.66015625, + 0.66015625 + ], + [ + 0.5, + 0.59375, + 0.59375 + ], + [ + 0.5, + 0.62890625, + 0.62890625 + ], + [ + 0.5, + 0.720703125, + 0.720703125 + ], + [ + 0.5, + 0.6875, + 0.6875 + ], + [ + 0.5, + 0.671875, + 0.671875 + ], + [ + 0.5, + 0.83984375, + 0.83984375 + ], + [ + 0.5, + 0.8046875, + 0.8046875 + ], + [ + 0.5, + 0.83984375, + 0.83984375 + ], + [ + 0.5, + 0.84375, + 0.84375 + ], + [ + 0.5, + 0.7890625, + 0.7890625 + ], + [ + 0.5, + 0.82421875, + 0.82421875 + ], + [ + 0.5, + 0.705078125, + 0.705078125 + ], + [ + 0.5, + 0.580078125, + 0.580078125 + ], + [ + 0.5, + 0.734375, + 0.734375 + ], + [ + 0.5, + 0.6796875, + 0.6796875 + ], + [ + 0.4000000059604645, + 0.65625, + 0.65625 + ], + [ + 0.5, + 0.6875, + 0.6875 + ], + [ + 0.5, + 0.794921875, + 0.794921875 + ], + [ + 0.5, + 0.58203125, + 0.58203125 + ], + [ + 0.5, + 0.74609375, + 0.74609375 + ], + [ + 0.5, + 0.66796875, + 0.66796875 + ], + [ + 0.5, + 0.935546875, + 0.935546875 + ], + [ + 0.5, + 0.7890625, + 0.7890625 + ], + [ + 0.5, + 0.74609375, + 0.74609375 + ], + [ + 0.5, + 0.80078125, + 0.80078125 + ], + [ + 0.5, + 0.6015625, + 0.6015625 + ], + [ + 0.5, + 0.9765625, + 0.9765625 + ], + [ + 0.5, + 0.79296875, + 0.79296875 + ], + [ + 0.5, + 0.87890625, + 0.87890625 + ], + [ + 0.5, + 0.875, + 0.875 + ], + [ + 0.5, + 0.779296875, + 0.779296875 + ], + [ + 0.5, + 0.611328125, + 0.611328125 + ], + [ + 0.5, + 0.666015625, + 0.666015625 + ], + [ + 0.5, + 0.62890625, + 0.62890625 + ], + [ + 0.5, + 0.693359375, + 0.693359375 + ], + [ + 0.5, + 0.6640625, + 0.6640625 + ], + [ + 0.5, + 0.609375, + 0.609375 + ], + [ + 0.5, + 0.740234375, + 0.740234375 + ], + [ + 0.5, + 0.7421875, + 0.7421875 + ], + [ + 0.5, + 0.845703125, + 0.845703125 + ], + [ + 0.5, + 0.7890625, + 0.7890625 + ], + [ + 0.5, + 0.64453125, + 0.64453125 + ], + [ + 0.5, + 0.634765625, + 0.634765625 + ], + [ + 0.5, + 0.8515625, + 0.8515625 + ], + [ + 0.5, + 0.79296875, + 0.79296875 + ], + [ + 0.5, + 0.625, + 0.625 + ], + [ + 0.5, + 0.658203125, + 0.658203125 + ], + [ + 0.5, + 0.9765625, + 0.9765625 + ], + [ + 0.5, + 0.92578125, + 0.92578125 + ], + [ + 0.5, + 0.640625, + 0.640625 + ], + [ + 0.5, + 0.720703125, + 0.720703125 + ], + [ + 0.5, + 0.80078125, + 0.80078125 + ], + [ + 0.5, + 0.705078125, + 0.705078125 + ], + [ + 0.5, + 0.671875, + 0.671875 + ], + [ + 0.5, + 0.935546875, + 0.935546875 + ], + [ + 0.5, + 0.7109375, + 0.7109375 + ], + [ + 0.5, + 0.703125, + 0.703125 + ], + [ + 0.5, + 0.76953125, + 0.76953125 + ], + [ + 0.5, + 0.763671875, + 0.763671875 + ], + [ + 0.5, + 0.72265625, + 0.72265625 + ], + [ + 0.5, + 0.849609375, + 0.849609375 + ], + [ + 0.5, + 0.6015625, + 0.6015625 + ], + [ + 0.5, + 0.73046875, + 0.73046875 + ], + [ + 0.5, + 0.74609375, + 0.74609375 + ], + [ + 0.5, + 0.60546875, + 0.60546875 + ], + [ + 0.5, + 0.890625, + 0.890625 + ], + [ + 0.5, + 0.611328125, + 0.611328125 + ], + [ + 0.5, + 0.685546875, + 0.685546875 + ], + [ + 0.5, + 0.69921875, + 0.69921875 + ], + [ + 0.5, + 0.576171875, + 0.576171875 + ], + [ + 0.5, + 0.716796875, + 0.716796875 + ], + [ + 0.5, + 0.751953125, + 0.751953125 + ], + [ + 0.5, + 0.494140625, + 0.494140625 + ], + [ + 0.5, + 0.7421875, + 0.7421875 + ], + [ + 0.5, + 0.6640625, + 0.6640625 + ], + [ + 0.5, + 0.916015625, + 0.916015625 + ], + [ + 0.5, + 0.8984375, + 0.8984375 + ], + [ + 0.5, + 0.65625, + 0.65625 + ], + [ + 0.5, + 0.625, + 0.625 + ], + [ + 0.5, + 0.625, + 0.625 + ], + [ + 0.5, + 0.7890625, + 0.7890625 + ], + [ + 0.5, + 0.765625, + 0.765625 + ], + [ + 0.5, + 0.69140625, + 0.69140625 + ], + [ + 0.5, + 0.681640625, + 0.681640625 + ], + [ + 0.5, + 0.7890625, + 0.7890625 + ], + [ + 0.5, + 0.705078125, + 0.705078125 + ], + [ + 0.5, + 0.69921875, + 0.69921875 + ], + [ + 0.5, + 0.703125, + 0.703125 + ], + [ + 0.5, + 0.748046875, + 0.748046875 + ], + [ + 0.5, + 0.85546875, + 0.85546875 + ], + [ + 0.5, + 0.63671875, + 0.63671875 + ], + [ + 0.5, + 0.875, + 0.875 + ], + [ + 0.5, + 0.771484375, + 0.771484375 + ], + [ + 0.5, + 0.88671875, + 0.88671875 + ], + [ + 0.5, + 0.7734375, + 0.7734375 + ], + [ + 0.5, + 0.80859375, + 0.80859375 + ], + [ + 0.5, + 0.71875, + 0.71875 + ], + [ + 0.5, + 0.71484375, + 0.71484375 + ], + [ + 0.5, + 0.84765625, + 0.84765625 + ], + [ + 0.5, + 0.927734375, + 0.927734375 + ], + [ + 0.5, + 0.935546875, + 0.935546875 + ], + [ + 0.5, + 0.6640625, + 0.6640625 + ], + [ + 0.5, + 0.759765625, + 0.759765625 + ], + [ + 0.5, + 0.662109375, + 0.662109375 + ], + [ + 0.5, + 0.81640625, + 0.81640625 + ], + [ + 0.5, + 0.74609375, + 0.74609375 + ], + [ + 0.5, + 0.68359375, + 0.68359375 + ], + [ + 0.5, + 0.802734375, + 0.802734375 + ], + [ + 0.5, + 0.763671875, + 0.763671875 + ], + [ + 0.5, + 0.8125, + 0.8125 + ], + [ + 0.5, + 0.77734375, + 0.77734375 + ], + [ + 0.5, + 0.650390625, + 0.650390625 + ], + [ + 0.5, + 0.85546875, + 0.85546875 + ], + [ + 0.5, + 0.734375, + 0.734375 + ], + [ + 0.5, + 0.638671875, + 0.638671875 + ], + [ + 0.5, + 0.7265625, + 0.7265625 + ], + [ + 0.5, + 0.6640625, + 0.6640625 + ], + [ + 0.5, + 0.74609375, + 0.74609375 + ], + [ + 0.5, + 0.703125, + 0.703125 + ], + [ + 0.5, + 0.73046875, + 0.73046875 + ], + [ + 0.5, + 0.7421875, + 0.7421875 + ], + [ + 0.5, + 0.6171875, + 0.6171875 + ], + [ + 0.5, + 0.69921875, + 0.69921875 + ], + [ + 0.5, + 0.640625, + 0.640625 + ], + [ + 0.5, + 0.73828125, + 0.73828125 + ], + [ + 0.5, + 0.84375, + 0.84375 + ], + [ + 0.5, + 0.78125, + 0.78125 + ], + [ + 0.5, + 0.720703125, + 0.720703125 + ], + [ + 0.5, + 0.76171875, + 0.76171875 + ], + [ + 0.5, + 0.8046875, + 0.8046875 + ], + [ + 0.5, + 0.712890625, + 0.712890625 + ], + [ + 0.5, + 0.703125, + 0.703125 + ], + [ + 0.5, + 0.64453125, + 0.64453125 + ], + [ + 0.5, + 0.765625, + 0.765625 + ], + [ + 0.5, + 0.8359375, + 0.8359375 + ], + [ + 0.5, + 0.765625, + 0.765625 + ], + [ + 0.5, + 0.728515625, + 0.728515625 + ], + [ + 0.5, + 0.7265625, + 0.7265625 + ], + [ + 0.5, + 0.771484375, + 0.771484375 + ], + [ + 0.5, + 0.72265625, + 0.72265625 + ], + [ + 0.5, + 0.73046875, + 0.73046875 + ], + [ + 0.5, + 0.78125, + 0.78125 + ], + [ + 0.5, + 0.76953125, + 0.76953125 + ], + [ + 0.5, + 0.625, + 0.625 + ], + [ + 0.5, + 0.77734375, + 0.77734375 + ], + [ + 0.5, + 0.7109375, + 0.7109375 + ], + [ + 0.5, + 0.97265625, + 0.97265625 + ], + [ + 0.5, + 0.71484375, + 0.71484375 + ], + [ + 0.5, + 0.69140625, + 0.69140625 + ], + [ + 0.5, + 0.76953125, + 0.76953125 + ], + [ + 0.5, + 0.890625, + 0.890625 + ], + [ + 0.5, + 0.884765625, + 0.884765625 + ], + [ + 0.5, + 0.712890625, + 0.712890625 + ], + [ + 0.5, + 0.875, + 0.875 + ], + [ + 0.5, + 0.6328125, + 0.6328125 + ], + [ + 0.5, + 0.62890625, + 0.62890625 + ], + [ + 0.5, + 0.861328125, + 0.861328125 + ], + [ + 0.5, + 0.75390625, + 0.75390625 + ], + [ + 0.5, + 0.80078125, + 0.80078125 + ], + [ + 0.5, + 0.681640625, + 0.681640625 + ], + [ + 0.5, + 0.68359375, + 0.68359375 + ], + [ + 0.5, + 0.80078125, + 0.80078125 + ], + [ + 0.5, + 0.640625, + 0.640625 + ], + [ + 0.5, + 0.74609375, + 0.74609375 + ], + [ + 0.5, + 0.68359375, + 0.68359375 + ], + [ + 0.5, + 0.8125, + 0.8125 + ], + [ + 0.5, + 0.931640625, + 0.931640625 + ], + [ + 0.5, + 0.701171875, + 0.701171875 + ], + [ + 0.5, + 0.796875, + 0.796875 + ], + [ + 0.5, + 0.81640625, + 0.81640625 + ], + [ + 0.5, + 0.861328125, + 0.861328125 + ], + [ + 0.5, + 0.81640625, + 0.81640625 + ], + [ + 0.5, + 0.8046875, + 0.8046875 + ], + [ + 0.5, + 0.6484375, + 0.6484375 + ], + [ + 0.5, + 0.88671875, + 0.88671875 + ], + [ + 0.5, + 0.771484375, + 0.771484375 + ], + [ + 0.5, + 0.69921875, + 0.69921875 + ], + [ + 0.5, + 0.68359375, + 0.68359375 + ], + [ + 0.5, + 0.734375, + 0.734375 + ], + [ + 0.5, + 0.748046875, + 0.748046875 + ], + [ + 0.5, + 0.7265625, + 0.7265625 + ], + [ + 0.5, + 0.58984375, + 0.58984375 + ], + [ + 0.5, + 0.7265625, + 0.7265625 + ], + [ + 0.5, + 0.68359375, + 0.68359375 + ], + [ + 0.5, + 0.708984375, + 0.708984375 + ], + [ + 0.5, + 0.68359375, + 0.68359375 + ], + [ + 0.5, + 0.71875, + 0.71875 + ], + [ + 0.5, + 0.68359375, + 0.68359375 + ], + [ + 0.5, + 0.599609375, + 0.599609375 + ], + [ + 0.5, + 0.953125, + 0.953125 + ], + [ + 0.5, + 0.876953125, + 0.876953125 + ], + [ + 0.5, + 0.619140625, + 0.619140625 + ], + [ + 0.5, + 0.73046875, + 0.73046875 + ], + [ + 0.5, + 0.72265625, + 0.72265625 + ], + [ + 0.5, + 0.76953125, + 0.76953125 + ], + [ + 0.5, + 0.5703125, + 0.5703125 + ], + [ + 0.5, + 0.693359375, + 0.693359375 + ], + [ + 0.5, + 0.845703125, + 0.845703125 + ], + [ + 0.5, + 0.76171875, + 0.76171875 + ], + [ + 0.5, + 0.71875, + 0.71875 + ], + [ + 0.5, + 0.84375, + 0.84375 + ], + [ + 0.5, + 0.68359375, + 0.68359375 + ], + [ + 0.5, + 0.9765625, + 0.9765625 + ], + [ + 0.5, + 0.6953125, + 0.6953125 + ], + [ + 0.5, + 0.666015625, + 0.666015625 + ], + [ + 0.5, + 0.90625, + 0.90625 + ], + [ + 0.5, + 0.681640625, + 0.681640625 + ], + [ + 0.5, + 0.578125, + 0.578125 + ], + [ + 0.5, + 0.822265625, + 0.822265625 + ], + [ + 0.5, + 0.6875, + 0.6875 + ], + [ + 0.5, + 0.58984375, + 0.58984375 + ], + [ + 0.5, + 0.671875, + 0.671875 + ], + [ + 0.5, + 0.611328125, + 0.611328125 + ], + [ + 0.5, + 0.806640625, + 0.806640625 + ], + [ + 0.5, + 0.66796875, + 0.66796875 + ], + [ + 0.5, + 0.9140625, + 0.9140625 + ], + [ + 0.5, + 0.890625, + 0.890625 + ], + [ + 0.5, + 0.84375, + 0.84375 + ], + [ + 0.5, + 0.88671875, + 0.88671875 + ], + [ + 0.5, + 0.84765625, + 0.84765625 + ], + [ + 0.5, + 0.69140625, + 0.69140625 + ], + [ + 0.5, + 0.7578125, + 0.7578125 + ], + [ + 0.5, + 0.7734375, + 0.7734375 + ], + [ + 0.5, + 0.5703125, + 0.5703125 + ], + [ + 0.5, + 0.67578125, + 0.67578125 + ], + [ + 0.5, + 0.6015625, + 0.6015625 + ], + [ + 0.5, + 0.796875, + 0.796875 + ], + [ + 0.5, + 0.72265625, + 0.72265625 + ], + [ + 0.5, + 0.75390625, + 0.75390625 + ], + [ + 0.5, + 0.7265625, + 0.7265625 + ], + [ + 0.5, + 0.75, + 0.75 + ], + [ + 0.5, + 0.72265625, + 0.72265625 + ], + [ + 0.5, + 0.890625, + 0.890625 + ], + [ + 0.5, + 0.8984375, + 0.8984375 + ], + [ + 0.5, + 0.78125, + 0.78125 + ], + [ + 0.5, + 0.599609375, + 0.599609375 + ], + [ + 0.5, + 0.80859375, + 0.80859375 + ], + [ + 0.5, + 0.712890625, + 0.712890625 + ], + [ + 0.5, + 0.60546875, + 0.60546875 + ], + [ + 0.5, + 0.59765625, + 0.59765625 + ], + [ + 0.5, + 0.69140625, + 0.69140625 + ], + [ + 0.5, + 0.765625, + 0.765625 + ], + [ + 0.5, + 0.70703125, + 0.70703125 + ], + [ + 0.5, + 0.89453125, + 0.89453125 + ], + [ + 0.5, + 0.73046875, + 0.73046875 + ], + [ + 0.5, + 0.74609375, + 0.74609375 + ], + [ + 0.5, + 0.8359375, + 0.8359375 + ], + [ + 0.5, + 0.927734375, + 0.927734375 + ], + [ + 0.5, + 0.626953125, + 0.626953125 + ], + [ + 0.5, + 0.84375, + 0.84375 + ], + [ + 0.5, + 0.943359375, + 0.943359375 + ], + [ + 0.5, + 0.748046875, + 0.748046875 + ], + [ + 0.5, + 0.962890625, + 0.962890625 + ], + [ + 0.5, + 0.90625, + 0.90625 + ], + [ + 0.5, + 0.693359375, + 0.693359375 + ], + [ + 0.5, + 0.8203125, + 0.8203125 + ], + [ + 0.5, + 0.72265625, + 0.72265625 + ], + [ + 0.5, + 0.79296875, + 0.79296875 + ], + [ + 0.5, + 0.79296875, + 0.79296875 + ], + [ + 0.5, + 0.791015625, + 0.791015625 + ], + [ + 0.5, + 0.73828125, + 0.73828125 + ], + [ + 0.5, + 0.798828125, + 0.798828125 + ], + [ + 0.5, + 0.71875, + 0.71875 + ], + [ + 0.5, + 0.6484375, + 0.6484375 + ], + [ + 0.5, + 0.79296875, + 0.79296875 + ], + [ + 0.5, + 0.681640625, + 0.681640625 + ], + [ + 0.5, + 0.58203125, + 0.58203125 + ], + [ + 0.5, + 0.564453125, + 0.564453125 + ], + [ + 0.5, + 0.765625, + 0.765625 + ], + [ + 0.5, + 0.71875, + 0.71875 + ], + [ + 0.5, + 0.791015625, + 0.791015625 + ], + [ + 0.5, + 0.638671875, + 0.638671875 + ], + [ + 0.5, + 0.833984375, + 0.833984375 + ], + [ + 0.5, + 0.669921875, + 0.669921875 + ], + [ + 0.5, + 0.759765625, + 0.759765625 + ], + [ + 0.5, + 0.96875, + 0.96875 + ], + [ + 0.5, + 0.74609375, + 0.74609375 + ], + [ + 0.5, + 0.60546875, + 0.60546875 + ], + [ + 0.5, + 0.953125, + 0.953125 + ], + [ + 0.5, + 0.767578125, + 0.767578125 + ], + [ + 0.5, + 0.658203125, + 0.658203125 + ], + [ + 0.5, + 0.71875, + 0.71875 + ], + [ + 0.5, + 0.75390625, + 0.75390625 + ], + [ + 0.5, + 0.78125, + 0.78125 + ], + [ + 0.5, + 0.75, + 0.75 + ], + [ + 0.5, + 0.6015625, + 0.6015625 + ], + [ + 0.5, + 0.650390625, + 0.650390625 + ], + [ + 0.5, + 0.8671875, + 0.8671875 + ], + [ + 0.5, + 0.62890625, + 0.62890625 + ], + [ + 0.5, + 0.640625, + 0.640625 + ], + [ + 0.5, + 0.669921875, + 0.669921875 + ], + [ + 0.5, + 0.658203125, + 0.658203125 + ], + [ + 0.5, + 0.734375, + 0.734375 + ], + [ + 0.5, + 0.83203125, + 0.83203125 + ], + [ + 0.5, + 0.83984375, + 0.83984375 + ], + [ + 0.5, + 0.8046875, + 0.8046875 + ], + [ + 0.5, + 0.9765625, + 0.9765625 + ], + [ + 0.5, + 0.70703125, + 0.70703125 + ], + [ + 0.5, + 0.86328125, + 0.86328125 + ], + [ + 0.5, + 0.890625, + 0.890625 + ], + [ + 0.5, + 0.8671875, + 0.8671875 + ], + [ + 0.5, + 0.865234375, + 0.865234375 + ], + [ + 0.5, + 0.76171875, + 0.76171875 + ], + [ + 0.5, + 0.720703125, + 0.720703125 + ], + [ + 0.5, + 0.76171875, + 0.76171875 + ], + [ + 0.5, + 0.66796875, + 0.66796875 + ], + [ + 0.5, + 0.84375, + 0.84375 + ], + [ + 0.5, + 0.541015625, + 0.541015625 + ], + [ + 0.5, + 0.76953125, + 0.76953125 + ], + [ + 0.5, + 0.669921875, + 0.669921875 + ], + [ + 0.5, + 0.86328125, + 0.86328125 + ], + [ + 0.5, + 0.74609375, + 0.74609375 + ], + [ + 0.5, + 0.921875, + 0.921875 + ], + [ + 0.5, + 0.783203125, + 0.783203125 + ], + [ + 0.5, + 0.90625, + 0.90625 + ], + [ + 0.5, + 0.81640625, + 0.81640625 + ], + [ + 0.5, + 0.77734375, + 0.77734375 + ], + [ + 0.5, + 0.7890625, + 0.7890625 + ], + [ + 0.5, + 0.7109375, + 0.7109375 + ], + [ + 0.5, + 0.857421875, + 0.857421875 + ], + [ + 0.5, + 0.8203125, + 0.8203125 + ], + [ + 0.5, + 0.7890625, + 0.7890625 + ], + [ + 0.5, + 0.734375, + 0.734375 + ], + [ + 0.5, + 0.72265625, + 0.72265625 + ], + [ + 0.5, + 0.791015625, + 0.791015625 + ], + [ + 0.5, + 0.61328125, + 0.61328125 + ], + [ + 0.5, + 0.9765625, + 0.9765625 + ], + [ + 0.5, + 0.69140625, + 0.69140625 + ], + [ + 0.5, + 0.88671875, + 0.88671875 + ], + [ + 0.5, + 0.650390625, + 0.650390625 + ], + [ + 0.5, + 0.78515625, + 0.78515625 + ], + [ + 0.5, + 0.72265625, + 0.72265625 + ], + [ + 0.5, + 0.701171875, + 0.701171875 + ], + [ + 0.5, + 0.796875, + 0.796875 + ], + [ + 0.5, + 0.77734375, + 0.77734375 + ], + [ + 0.5, + 0.78125, + 0.78125 + ], + [ + 0.5, + 0.73046875, + 0.73046875 + ], + [ + 0.5, + 0.82421875, + 0.82421875 + ], + [ + 0.5, + 0.60546875, + 0.60546875 + ], + [ + 0.5, + 0.7578125, + 0.7578125 + ], + [ + 0.5, + 0.673828125, + 0.673828125 + ], + [ + 0.5, + 0.7109375, + 0.7109375 + ], + [ + 0.5, + 0.76171875, + 0.76171875 + ], + [ + 0.5, + 0.6953125, + 0.6953125 + ], + [ + 0.5, + 0.828125, + 0.828125 + ], + [ + 0.5, + 0.6875, + 0.6875 + ], + [ + 0.5, + 0.61328125, + 0.61328125 + ], + [ + 0.5, + 0.751953125, + 0.751953125 + ], + [ + 0.5, + 0.890625, + 0.890625 + ], + [ + 0.5, + 0.66796875, + 0.66796875 + ], + [ + 0.5, + 0.67578125, + 0.67578125 + ], + [ + 0.5, + 0.685546875, + 0.685546875 + ], + [ + 0.5, + 0.681640625, + 0.681640625 + ], + [ + 0.5, + 0.828125, + 0.828125 + ], + [ + 0.5, + 0.958984375, + 0.958984375 + ], + [ + 0.5, + 0.66015625, + 0.66015625 + ], + [ + 0.5, + 0.775390625, + 0.775390625 + ], + [ + 0.5, + 0.75, + 0.75 + ], + [ + 0.5, + 0.62890625, + 0.62890625 + ], + [ + 0.5, + 0.79296875, + 0.79296875 + ], + [ + 0.5, + 0.64453125, + 0.64453125 + ], + [ + 0.5, + 0.640625, + 0.640625 + ], + [ + 0.5, + 0.68359375, + 0.68359375 + ], + [ + 0.5, + 0.703125, + 0.703125 + ], + [ + 0.5, + 0.63671875, + 0.63671875 + ], + [ + 0.5, + 0.673828125, + 0.673828125 + ], + [ + 0.5, + 0.94921875, + 0.94921875 + ], + [ + 0.5, + 0.83984375, + 0.83984375 + ], + [ + 0.5, + 0.72265625, + 0.72265625 + ], + [ + 0.5, + 0.73046875, + 0.73046875 + ], + [ + 0.5, + 0.80859375, + 0.80859375 + ], + [ + 0.5, + 0.828125, + 0.828125 + ], + [ + 0.5, + 0.74609375, + 0.74609375 + ], + [ + 0.5, + 0.828125, + 0.828125 + ], + [ + 0.5, + 0.66015625, + 0.66015625 + ], + [ + 0.5, + 0.75, + 0.75 + ], + [ + 0.5, + 0.724609375, + 0.724609375 + ], + [ + 0.5, + 0.828125, + 0.828125 + ], + [ + 0.5, + 0.681640625, + 0.681640625 + ], + [ + 0.5, + 0.673828125, + 0.673828125 + ], + [ + 0.800000011920929, + 0.9765625, + 0.9765625 + ], + [ + 0.5, + 0.65625, + 0.65625 + ], + [ + 0.5, + 0.732421875, + 0.732421875 + ], + [ + 0.5, + 0.73828125, + 0.73828125 + ], + [ + 0.625, + 0.8144530057907104, + 0.8144530057907104 + ], + [ + 0.5, + 0.640625, + 0.640625 + ], + [ + 0.5, + 0.66015625, + 0.66015625 + ], + [ + 0.5, + 0.734375, + 0.734375 + ], + [ + 0.5, + 0.55859375, + 0.55859375 + ], + [ + 0.5, + 0.70703125, + 0.70703125 + ], + [ + 0.5, + 0.759765625, + 0.759765625 + ], + [ + 0.5, + 0.8515625, + 0.8515625 + ], + [ + 0.5, + 0.662109375, + 0.662109375 + ], + [ + 0.5, + 0.720703125, + 0.720703125 + ], + [ + 0.5, + 0.828125, + 0.828125 + ], + [ + 0.5, + 0.7265625, + 0.7265625 + ], + [ + 0.5, + 0.90234375, + 0.90234375 + ], + [ + 0.5, + 0.64453125, + 0.64453125 + ], + [ + 0.5, + 0.5, + 0.5 + ], + [ + 0.5, + 0.6875, + 0.6875 + ], + [ + 0.5, + 0.78125, + 0.78125 + ], + [ + 0.5, + 0.64453125, + 0.64453125 + ], + [ + 0.5, + 0.79296875, + 0.79296875 + ], + [ + 0.5, + 0.78125, + 0.78125 + ], + [ + 0.5, + 0.7421875, + 0.7421875 + ], + [ + 0.5, + 0.60546875, + 0.60546875 + ], + [ + 0.5, + 0.5859375, + 0.5859375 + ], + [ + 0.5, + 0.7265625, + 0.7265625 + ], + [ + 0.5, + 0.72265625, + 0.72265625 + ], + [ + 0.5, + 0.7109375, + 0.7109375 + ], + [ + 0.5, + 0.5859375, + 0.5859375 + ], + [ + 0.5, + 0.7421875, + 0.7421875 + ], + [ + 0.5, + 0.6953125, + 0.6953125 + ], + [ + 0.5, + 0.7421875, + 0.7421875 + ], + [ + 0.5, + 0.662109375, + 0.662109375 + ], + [ + 0.5, + 0.75390625, + 0.75390625 + ], + [ + 0.5, + 0.70703125, + 0.70703125 + ], + [ + 0.5, + 0.92578125, + 0.92578125 + ], + [ + 0.5, + 0.765625, + 0.765625 + ], + [ + 0.5, + 0.6796875, + 0.6796875 + ], + [ + 0.5, + 0.73828125, + 0.73828125 + ], + [ + 0.5, + 0.71484375, + 0.71484375 + ], + [ + 0.5, + 0.7578125, + 0.7578125 + ], + [ + 0.5, + 0.859375, + 0.859375 + ], + [ + 0.5, + 0.578125, + 0.578125 + ], + [ + 0.5, + 0.796875, + 0.796875 + ], + [ + 0.5, + 0.75, + 0.75 + ], + [ + 0.5, + 0.64453125, + 0.64453125 + ], + [ + 0.5, + 0.64453125, + 0.64453125 + ], + [ + 0.5, + 0.75, + 0.75 + ], + [ + 0.5, + 0.75, + 0.75 + ], + [ + 0.5, + 0.712890625, + 0.712890625 + ], + [ + 0.5, + 0.64453125, + 0.64453125 + ], + [ + 0.5, + 0.7421875, + 0.7421875 + ], + [ + 0.5, + 0.5859375, + 0.5859375 + ], + [ + 0.5, + 0.70703125, + 0.70703125 + ], + [ + 0.5, + 0.810546875, + 0.810546875 + ], + [ + 0.5, + 0.6328125, + 0.6328125 + ], + [ + 0.5, + 0.6640625, + 0.6640625 + ], + [ + 0.5, + 0.65234375, + 0.65234375 + ], + [ + 0.5, + 0.62890625, + 0.62890625 + ], + [ + 0.5, + 0.5859375, + 0.5859375 + ], + [ + 0.5, + 0.5703125, + 0.5703125 + ], + [ + 0.5, + 0.876953125, + 0.876953125 + ], + [ + 0.5, + 0.6953125, + 0.6953125 + ], + [ + 0.5, + 0.859375, + 0.859375 + ], + [ + 0.5, + 0.71484375, + 0.71484375 + ], + [ + 0.5, + 0.552734375, + 0.552734375 + ], + [ + 0.5, + 0.626953125, + 0.626953125 + ], + [ + 0.5, + 0.734375, + 0.734375 + ], + [ + 0.5, + 0.796875, + 0.796875 + ], + [ + 0.5, + 0.80859375, + 0.80859375 + ], + [ + 0.5, + 0.63671875, + 0.63671875 + ], + [ + 0.5, + 0.79296875, + 0.79296875 + ], + [ + 0.5, + 0.6171875, + 0.6171875 + ], + [ + 0.5, + 0.8203125, + 0.8203125 + ], + [ + 0.5, + 0.6640625, + 0.6640625 + ], + [ + 0.5, + 0.759765625, + 0.759765625 + ], + [ + 0.5, + 0.8203125, + 0.8203125 + ], + [ + 0.5, + 0.8984375, + 0.8984375 + ], + [ + 0.5, + 0.7421875, + 0.7421875 + ], + [ + 0.5, + 0.5976561903953552, + 0.5976561903953552 + ], + [ + 0.5, + 0.6328125, + 0.6328125 + ], + [ + 0.5, + 0.6523438096046448, + 0.6523438096046448 + ], + [ + 0.5, + 0.8671875, + 0.8671875 + ], + [ + 0.5, + 0.875, + 0.875 + ], + [ + 0.5, + 0.734375, + 0.734375 + ], + [ + 0.5, + 0.552734375, + 0.552734375 + ], + [ + 0.5, + 0.626953125, + 0.626953125 + ], + [ + 0.5, + 0.841796875, + 0.841796875 + ], + [ + 0.5, + 0.734375, + 0.734375 + ], + [ + 0.5, + 0.796875, + 0.796875 + ], + [ + 0.5, + 0.68359375, + 0.68359375 + ], + [ + 0.5, + 0.634765625, + 0.634765625 + ], + [ + 0.5, + 0.75390625, + 0.75390625 + ], + [ + 0.5, + 0.7890625, + 0.7890625 + ], + [ + 0.5, + 0.8984375, + 0.8984375 + ], + [ + 0.5, + 0.73046875, + 0.73046875 + ], + [ + 0.5, + 0.619140625, + 0.619140625 + ], + [ + 0.5, + 0.7109375, + 0.7109375 + ], + [ + 0.5, + 0.669921875, + 0.669921875 + ], + [ + 0.5, + 0.744140625, + 0.744140625 + ], + [ + 0.5, + 0.587890625, + 0.587890625 + ], + [ + 0.5, + 0.84765625, + 0.84765625 + ], + [ + 0.5, + 0.62890625, + 0.62890625 + ], + [ + 0.5, + 0.70703125, + 0.70703125 + ], + [ + 0.5, + 0.7734375, + 0.7734375 + ], + [ + 0.5, + 0.83984375, + 0.83984375 + ], + [ + 0.5, + 0.669921875, + 0.669921875 + ], + [ + 0.5, + 0.630859375, + 0.630859375 + ], + [ + 0.5, + 0.779296875, + 0.779296875 + ], + [ + 0.5, + 0.7265625, + 0.7265625 + ], + [ + 0.5, + 0.787109375, + 0.787109375 + ], + [ + 0.5, + 0.642578125, + 0.642578125 + ], + [ + 0.5, + 0.94921875, + 0.94921875 + ], + [ + 0.5, + 0.875, + 0.875 + ], + [ + 0.5, + 0.693359375, + 0.693359375 + ], + [ + 0.5, + 0.689453125, + 0.689453125 + ], + [ + 0.5, + 0.6953125, + 0.6953125 + ], + [ + 0.5, + 0.71484375, + 0.71484375 + ], + [ + 0.5, + 0.7421875, + 0.7421875 + ], + [ + 0.5, + 0.5625, + 0.5625 + ], + [ + 0.5, + 0.6953125, + 0.6953125 + ], + [ + 0.5, + 0.7265625, + 0.7265625 + ], + [ + 0.5, + 0.59375, + 0.59375 + ], + [ + 0.5, + 0.697265625, + 0.697265625 + ], + [ + 0.5, + 0.66015625, + 0.66015625 + ], + [ + 0.5, + 0.7421875, + 0.7421875 + ], + [ + 0.5, + 0.654296875, + 0.654296875 + ], + [ + 0.5, + 0.7421875, + 0.7421875 + ], + [ + 0.5, + 0.78515625, + 0.78515625 + ], + [ + 0.5, + 0.828125, + 0.828125 + ], + [ + 0.5, + 0.875, + 0.875 + ], + [ + 0.5, + 0.6328125, + 0.6328125 + ], + [ + 0.5, + 0.76953125, + 0.76953125 + ], + [ + 0.5, + 0.9765625, + 0.9765625 + ], + [ + 0.5, + 0.65625, + 0.65625 + ], + [ + 0.5, + 0.751953125, + 0.751953125 + ], + [ + 0.5, + 0.63671875, + 0.63671875 + ], + [ + 0.5, + 0.8203125, + 0.8203125 + ], + [ + 0.5, + 0.69921875, + 0.69921875 + ], + [ + 0.5, + 0.70703125, + 0.70703125 + ], + [ + 0.5, + 0.6484375, + 0.6484375 + ], + [ + 0.5, + 0.87109375, + 0.87109375 + ], + [ + 0.5, + 0.78125, + 0.78125 + ], + [ + 0.5, + 0.91796875, + 0.91796875 + ], + [ + 0.5, + 0.69140625, + 0.69140625 + ], + [ + 0.5, + 0.626953125, + 0.626953125 + ], + [ + 0.5, + 0.556640625, + 0.556640625 + ], + [ + 0.5, + 0.6484375, + 0.6484375 + ], + [ + 0.5, + 0.9453125, + 0.9453125 + ], + [ + 0.5, + 0.734375, + 0.734375 + ], + [ + 0.5, + 0.69921875, + 0.69921875 + ], + [ + 0.5, + 0.697265625, + 0.697265625 + ], + [ + 0.5, + 0.7578125, + 0.7578125 + ], + [ + 0.5, + 0.8046875, + 0.8046875 + ], + [ + 0.5, + 0.578125, + 0.578125 + ], + [ + 0.5, + 0.83984375, + 0.83984375 + ], + [ + 0.5, + 0.7578125, + 0.7578125 + ], + [ + 0.5, + 0.744140625, + 0.744140625 + ], + [ + 0.5, + 0.6015625, + 0.6015625 + ], + [ + 0.5, + 0.904296875, + 0.904296875 + ], + [ + 0.5, + 0.66015625, + 0.66015625 + ], + [ + 0.5, + 0.79296875, + 0.79296875 + ], + [ + 0.5, + 0.787109375, + 0.787109375 + ], + [ + 0.5, + 0.64453125, + 0.64453125 + ], + [ + 0.5, + 0.625, + 0.625 + ], + [ + 0.5, + 0.625, + 0.625 + ], + [ + 0.5, + 0.966796875, + 0.966796875 + ], + [ + 0.5, + 0.66015625, + 0.66015625 + ], + [ + 0.5, + 0.86328125, + 0.86328125 + ], + [ + 0.5, + 0.7265625, + 0.7265625 + ], + [ + 0.5, + 0.6484375, + 0.6484375 + ], + [ + 0.5, + 0.5625, + 0.5625 + ], + [ + 0.5, + 0.693359375, + 0.693359375 + ], + [ + 0.5, + 0.84765625, + 0.84765625 + ], + [ + 0.5, + 0.57421875, + 0.57421875 + ], + [ + 0.5, + 0.78125, + 0.78125 + ], + [ + 0.5, + 0.783203125, + 0.783203125 + ], + [ + 0.5, + 0.640625, + 0.640625 + ], + [ + 0.5, + 0.734375, + 0.734375 + ], + [ + 0.5, + 0.68359375, + 0.68359375 + ], + [ + 0.5, + 0.81640625, + 0.81640625 + ], + [ + 0.5, + 0.9453125, + 0.9453125 + ], + [ + 0.5, + 0.626953125, + 0.626953125 + ], + [ + 0.5, + 0.73046875, + 0.73046875 + ], + [ + 0.5, + 0.880859375, + 0.880859375 + ], + [ + 0.5, + 0.662109375, + 0.662109375 + ], + [ + 0.5, + 0.76171875, + 0.76171875 + ], + [ + 0.5, + 0.625, + 0.625 + ], + [ + 0.5, + 0.6875, + 0.6875 + ], + [ + 0.5, + 0.68359375, + 0.68359375 + ], + [ + 0.5, + 0.900390625, + 0.900390625 + ], + [ + 0.5, + 0.74609375, + 0.74609375 + ], + [ + 0.5, + 0.845703125, + 0.845703125 + ], + [ + 0.5, + 0.611328125, + 0.611328125 + ], + [ + 0.5, + 0.8515625, + 0.8515625 + ], + [ + 0.5, + 0.8125, + 0.8125 + ], + [ + 0.5, + 0.75, + 0.75 + ], + [ + 0.5, + 0.7578125, + 0.7578125 + ], + [ + 0.5, + 0.9140625, + 0.9140625 + ], + [ + 0.5, + 0.7265625, + 0.7265625 + ], + [ + 0.5, + 0.71875, + 0.71875 + ], + [ + 0.5, + 0.80078125, + 0.80078125 + ], + [ + 0.5, + 0.82421875, + 0.82421875 + ], + [ + 0.5, + 0.7578125, + 0.7578125 + ], + [ + 0.5, + 0.80078125, + 0.80078125 + ], + [ + 0.5, + 0.669921875, + 0.669921875 + ], + [ + 0.5, + 0.65625, + 0.65625 + ], + [ + 0.5, + 0.708984375, + 0.708984375 + ], + [ + 0.5, + 0.6484375, + 0.6484375 + ], + [ + 0.5, + 0.646484375, + 0.646484375 + ], + [ + 0.5, + 0.61328125, + 0.61328125 + ], + [ + 0.5, + 0.65625, + 0.65625 + ], + [ + 0.5, + 0.9140625, + 0.9140625 + ], + [ + 0.5, + 0.6640625, + 0.6640625 + ], + [ + 0.5, + 0.5234375, + 0.5234375 + ], + [ + 0.5, + 0.787109375, + 0.787109375 + ], + [ + 0.5, + 0.828125, + 0.828125 + ], + [ + 0.5, + 0.744140625, + 0.744140625 + ], + [ + 0.5, + 0.701171875, + 0.701171875 + ], + [ + 0.5, + 0.734375, + 0.734375 + ], + [ + 0.5, + 0.75, + 0.75 + ], + [ + 0.5, + 0.623046875, + 0.623046875 + ], + [ + 0.5, + 0.9765625, + 0.9765625 + ], + [ + 0.5, + 0.6796875, + 0.6796875 + ], + [ + 0.5, + 0.701171875, + 0.701171875 + ], + [ + 0.5, + 0.646484375, + 0.646484375 + ], + [ + 0.5, + 0.5546875, + 0.5546875 + ], + [ + 0.5, + 0.67578125, + 0.67578125 + ], + [ + 0.5, + 0.77734375, + 0.77734375 + ], + [ + 0.5, + 0.966796875, + 0.966796875 + ], + [ + 0.5, + 0.68359375, + 0.68359375 + ], + [ + 0.5, + 0.71484375, + 0.71484375 + ], + [ + 0.5, + 0.6875, + 0.6875 + ], + [ + 0.5, + 0.6484375, + 0.6484375 + ], + [ + 0.5, + 0.693359375, + 0.693359375 + ], + [ + 0.5, + 0.609375, + 0.609375 + ], + [ + 0.5, + 0.576171875, + 0.576171875 + ], + [ + 0.5, + 0.79296875, + 0.79296875 + ], + [ + 0.5, + 0.703125, + 0.703125 + ], + [ + 0.5, + 0.671875, + 0.671875 + ], + [ + 0.5, + 0.736328125, + 0.736328125 + ], + [ + 0.5, + 0.73046875, + 0.73046875 + ], + [ + 0.5, + 0.791015625, + 0.791015625 + ], + [ + 0.5, + 0.52734375, + 0.52734375 + ], + [ + 0.5, + 0.810546875, + 0.810546875 + ], + [ + 0.5, + 0.76171875, + 0.76171875 + ], + [ + 0.5, + 0.6953125, + 0.6953125 + ], + [ + 0.5, + 0.677734375, + 0.677734375 + ], + [ + 0.5, + 0.8359375, + 0.8359375 + ], + [ + 0.5, + 0.69921875, + 0.69921875 + ], + [ + 0.5, + 0.630859375, + 0.630859375 + ], + [ + 0.5, + 0.75390625, + 0.75390625 + ], + [ + 0.5, + 0.78125, + 0.78125 + ], + [ + 0.5, + 0.70703125, + 0.70703125 + ], + [ + 0.5, + 0.654296875, + 0.654296875 + ], + [ + 0.5, + 0.90234375, + 0.90234375 + ], + [ + 0.5, + 0.9140625, + 0.9140625 + ], + [ + 0.5, + 0.685546875, + 0.685546875 + ], + [ + 0.5, + 0.58203125, + 0.58203125 + ], + [ + 0.5, + 0.576171875, + 0.576171875 + ], + [ + 0.5, + 0.72265625, + 0.72265625 + ], + [ + 0.5, + 0.65625, + 0.65625 + ], + [ + 0.5, + 0.84765625, + 0.84765625 + ], + [ + 0.5, + 0.796875, + 0.796875 + ], + [ + 0.5, + 0.71484375, + 0.71484375 + ], + [ + 0.5, + 0.78125, + 0.78125 + ], + [ + 0.5, + 0.724609375, + 0.724609375 + ], + [ + 0.5, + 0.853515625, + 0.853515625 + ], + [ + 0.5, + 0.765625, + 0.765625 + ], + [ + 0.5, + 0.859375, + 0.859375 + ], + [ + 0.5, + 0.70703125, + 0.70703125 + ], + [ + 0.5, + 0.78515625, + 0.78515625 + ], + [ + 0.5, + 0.83984375, + 0.83984375 + ], + [ + 0.5, + 0.68359375, + 0.68359375 + ], + [ + 0.5, + 0.75390625, + 0.75390625 + ], + [ + 0.5, + 0.685546875, + 0.685546875 + ], + [ + 0.5, + 0.71875, + 0.71875 + ], + [ + 0.5, + 0.67578125, + 0.67578125 + ], + [ + 0.5, + 0.673828125, + 0.673828125 + ], + [ + 0.5, + 0.703125, + 0.703125 + ], + [ + 0.5, + 0.73046875, + 0.73046875 + ], + [ + 0.5, + 0.8046875, + 0.8046875 + ], + [ + 0.5, + 0.78515625, + 0.78515625 + ], + [ + 0.5, + 0.697265625, + 0.697265625 + ], + [ + 0.5, + 0.71484375, + 0.71484375 + ], + [ + 0.5, + 0.65625, + 0.65625 + ], + [ + 0.5, + 0.7265625, + 0.7265625 + ], + [ + 0.5, + 0.8046875, + 0.8046875 + ], + [ + 0.5, + 0.81640625, + 0.81640625 + ], + [ + 0.5, + 0.80859375, + 0.80859375 + ], + [ + 0.5, + 0.66796875, + 0.66796875 + ], + [ + 0.5, + 0.9765625, + 0.9765625 + ], + [ + 0.5, + 0.96484375, + 0.96484375 + ], + [ + 0.5, + 0.65625, + 0.65625 + ], + [ + 0.5, + 0.67578125, + 0.67578125 + ], + [ + 0.5, + 0.6953125, + 0.6953125 + ], + [ + 0.5, + 0.66796875, + 0.66796875 + ], + [ + 0.5, + 0.791015625, + 0.791015625 + ], + [ + 0.5, + 0.765625, + 0.765625 + ], + [ + 0.5, + 0.83984375, + 0.83984375 + ], + [ + 0.5, + 0.7734375, + 0.7734375 + ], + [ + 0.5, + 0.58984375, + 0.58984375 + ], + [ + 0.5, + 0.5859375, + 0.5859375 + ], + [ + 0.5, + 0.70703125, + 0.70703125 + ], + [ + 0.5, + 0.69921875, + 0.69921875 + ], + [ + 0.5, + 0.673828125, + 0.673828125 + ], + [ + 0.5, + 0.568359375, + 0.568359375 + ], + [ + 0.5, + 0.55859375, + 0.55859375 + ], + [ + 0.5, + 0.5859375, + 0.5859375 + ], + [ + 0.5, + 0.5859375, + 0.5859375 + ], + [ + 0.5, + 0.6171875, + 0.6171875 + ], + [ + 0.5, + 0.625, + 0.625 + ], + [ + 0.5, + 0.5859375, + 0.5859375 + ], + [ + 0.5, + 0.5859375, + 0.5859375 + ], + [ + 0.5, + 0.673828125, + 0.673828125 + ], + [ + 0.5, + 0.63671875, + 0.63671875 + ], + [ + 0.5, + 0.625, + 0.625 + ], + [ + 0.5, + 0.5859375, + 0.5859375 + ], + [ + 0.5, + 0.5859375, + 0.5859375 + ], + [ + 0.5, + 0.5859375, + 0.5859375 + ], + [ + 0.5, + 0.59375, + 0.59375 + ], + [ + 0.5, + 0.703125, + 0.703125 + ], + [ + 0.5, + 0.6328125, + 0.6328125 + ], + [ + 0.5, + 0.5859375, + 0.5859375 + ], + [ + 0.5, + 0.6328125, + 0.6328125 + ], + [ + 0.5, + 0.66015625, + 0.66015625 + ], + [ + 0.5, + 0.79296875, + 0.79296875 + ], + [ + 0.5, + 0.642578125, + 0.642578125 + ], + [ + 0.5, + 0.6875, + 0.6875 + ], + [ + 0.5, + 0.5859375, + 0.5859375 + ], + [ + 0.5, + 0.638671875, + 0.638671875 + ], + [ + 0.5, + 0.640625, + 0.640625 + ], + [ + 0.5, + 0.658203125, + 0.658203125 + ], + [ + 0.5, + 0.58203125, + 0.58203125 + ], + [ + 0.5, + 0.6875, + 0.6875 + ], + [ + 0.5, + 0.712890625, + 0.712890625 + ], + [ + 0.5, + 0.720703125, + 0.720703125 + ], + [ + 0.5, + 0.572265625, + 0.572265625 + ], + [ + 0.5, + 0.6328125, + 0.6328125 + ], + [ + 0.5, + 0.65625, + 0.65625 + ], + [ + 0.5, + 0.5859375, + 0.5859375 + ], + [ + 0.5, + 0.5859375, + 0.5859375 + ], + [ + 0.5, + 0.708984375, + 0.708984375 + ], + [ + 0.5, + 0.68359375, + 0.68359375 + ], + [ + 0.5, + 0.5625, + 0.5625 + ], + [ + 0.5, + 0.7421875, + 0.7421875 + ], + [ + 0.5, + 0.7421875, + 0.7421875 + ], + [ + 0.5, + 0.71875, + 0.71875 + ], + [ + 0.5, + 0.6328125, + 0.6328125 + ], + [ + 0.5, + 0.68359375, + 0.68359375 + ], + [ + 0.5, + 0.595703125, + 0.595703125 + ], + [ + 0.5, + 0.53515625, + 0.53515625 + ], + [ + 0.5, + 0.6875, + 0.6875 + ], + [ + 0.5, + 0.685546875, + 0.685546875 + ], + [ + 0.5, + 0.78125, + 0.78125 + ], + [ + 0.5, + 0.74609375, + 0.74609375 + ], + [ + 0.5, + 0.625, + 0.625 + ], + [ + 0.5, + 0.68359375, + 0.68359375 + ], + [ + 0.5, + 0.84375, + 0.84375 + ], + [ + 0.5, + 0.68359375, + 0.68359375 + ], + [ + 0.5, + 0.59375, + 0.59375 + ], + [ + 0.5, + 0.58984375, + 0.58984375 + ], + [ + 0.5, + 0.7265625, + 0.7265625 + ], + [ + 0.5, + 0.677734375, + 0.677734375 + ], + [ + 0.5, + 0.640625, + 0.640625 + ], + [ + 0.5, + 0.65625, + 0.65625 + ], + [ + 0.5, + 0.591796875, + 0.591796875 + ], + [ + 0.5, + 0.765625, + 0.765625 + ], + [ + 0.5, + 0.828125, + 0.828125 + ], + [ + 0.5, + 0.5859375, + 0.5859375 + ], + [ + 0.5, + 0.6328125, + 0.6328125 + ], + [ + 0.5, + 0.66796875, + 0.66796875 + ], + [ + 0.5, + 0.6015625, + 0.6015625 + ], + [ + 0.5, + 0.65625, + 0.65625 + ], + [ + 0.5, + 0.75390625, + 0.75390625 + ], + [ + 0.5, + 0.5859375, + 0.5859375 + ], + [ + 0.5, + 0.58984375, + 0.58984375 + ], + [ + 0.5, + 0.5390625, + 0.5390625 + ], + [ + 0.5, + 0.64453125, + 0.64453125 + ], + [ + 0.5, + 0.626953125, + 0.626953125 + ], + [ + 0.5, + 0.66015625, + 0.66015625 + ], + [ + 0.5, + 0.724609375, + 0.724609375 + ], + [ + 0.5, + 0.71875, + 0.71875 + ], + [ + 0.5, + 0.65234375, + 0.65234375 + ], + [ + 0.5, + 0.5859375, + 0.5859375 + ], + [ + 0.5, + 0.59765625, + 0.59765625 + ], + [ + 0.5, + 0.603515625, + 0.603515625 + ], + [ + 0.5, + 0.60546875, + 0.60546875 + ], + [ + 0.5, + 0.728515625, + 0.728515625 + ], + [ + 0.5, + 0.5859375, + 0.5859375 + ], + [ + 0.5, + 0.6015625, + 0.6015625 + ], + [ + 0.5, + 0.5859375, + 0.5859375 + ], + [ + 0.5, + 0.7109375, + 0.7109375 + ], + [ + 0.5, + 0.626953125, + 0.626953125 + ], + [ + 0.5, + 0.58203125, + 0.58203125 + ], + [ + 0.5, + 0.703125, + 0.703125 + ], + [ + 0.5, + 0.7109375, + 0.7109375 + ], + [ + 0.5, + 0.625, + 0.625 + ], + [ + 0.5, + 0.7421875, + 0.7421875 + ], + [ + 0.5, + 0.66015625, + 0.66015625 + ], + [ + 0.5, + 0.5859375, + 0.5859375 + ], + [ + 0.5, + 0.638671875, + 0.638671875 + ], + [ + 0.5, + 0.693359375, + 0.693359375 + ], + [ + 0.5, + 0.7421875, + 0.7421875 + ], + [ + 0.5, + 0.7265625, + 0.7265625 + ], + [ + 0.5, + 0.67578125, + 0.67578125 + ], + [ + 0.5, + 0.5859375, + 0.5859375 + ], + [ + 0.5, + 0.640625, + 0.640625 + ], + [ + 0.5, + 0.5859375, + 0.5859375 + ], + [ + 0.5, + 0.650390625, + 0.650390625 + ], + [ + 0.5, + 0.6171875, + 0.6171875 + ], + [ + 0.5, + 0.5859375, + 0.5859375 + ], + [ + 0.5, + 0.615234375, + 0.615234375 + ], + [ + 0.5, + 0.7421875, + 0.7421875 + ], + [ + 0.5, + 0.7890625, + 0.7890625 + ], + [ + 0.5, + 0.6640625, + 0.6640625 + ], + [ + 0.5, + 0.5859375, + 0.5859375 + ], + [ + 0.5, + 0.791015625, + 0.791015625 + ], + [ + 0.5, + 0.6484375, + 0.6484375 + ], + [ + 0.5, + 0.5859375, + 0.5859375 + ], + [ + 0.5, + 0.630859375, + 0.630859375 + ], + [ + 0.5, + 0.74609375, + 0.74609375 + ], + [ + 0.5, + 0.74609375, + 0.74609375 + ], + [ + 0.5, + 0.65234375, + 0.65234375 + ], + [ + 0.5, + 0.5859375, + 0.5859375 + ], + [ + 0.5, + 0.5859375, + 0.5859375 + ], + [ + 0.5, + 0.5859375, + 0.5859375 + ], + [ + 0.5, + 0.65625, + 0.65625 + ], + [ + 0.5, + 0.71484375, + 0.71484375 + ], + [ + 0.5, + 0.59375, + 0.59375 + ], + [ + 0.5, + 0.552734375, + 0.552734375 + ], + [ + 0.5, + 0.671875, + 0.671875 + ], + [ + 0.5, + 0.640625, + 0.640625 + ], + [ + 0.5, + 0.68359375, + 0.68359375 + ], + [ + 0.5, + 0.630859375, + 0.630859375 + ], + [ + 0.5, + 0.59765625, + 0.59765625 + ], + [ + 0.5, + 0.5859375, + 0.5859375 + ], + [ + 0.5, + 0.5859375, + 0.5859375 + ], + [ + 0.5, + 0.57421875, + 0.57421875 + ], + [ + 0.5, + 0.666015625, + 0.666015625 + ], + [ + 0.5, + 0.703125, + 0.703125 + ], + [ + 0.5, + 0.5546875, + 0.5546875 + ], + [ + 0.5, + 0.7421875, + 0.7421875 + ], + [ + 0.5, + 0.619140625, + 0.619140625 + ], + [ + 0.5, + 0.5859375, + 0.5859375 + ], + [ + 0.5, + 0.740234375, + 0.740234375 + ], + [ + 0.5, + 0.744140625, + 0.744140625 + ], + [ + 0.5, + 0.875, + 0.875 + ], + [ + 0.5, + 0.6328125, + 0.6328125 + ], + [ + 0.5, + 0.615234375, + 0.615234375 + ], + [ + 0.5, + 0.626953125, + 0.626953125 + ], + [ + 0.5, + 0.5859375, + 0.5859375 + ], + [ + 0.5, + 0.62109375, + 0.62109375 + ], + [ + 0.5, + 0.693359375, + 0.693359375 + ], + [ + 0.5, + 0.66796875, + 0.66796875 + ], + [ + 0.5, + 0.70703125, + 0.70703125 + ], + [ + 0.5, + 0.5859375, + 0.5859375 + ], + [ + 0.5, + 0.65625, + 0.65625 + ], + [ + 0.5, + 0.5859375, + 0.5859375 + ], + [ + 0.5, + 0.666015625, + 0.666015625 + ], + [ + 0.5, + 0.658203125, + 0.658203125 + ], + [ + 0.5, + 0.595703125, + 0.595703125 + ], + [ + 0.5, + 0.611328125, + 0.611328125 + ], + [ + 0.5, + 0.724609375, + 0.724609375 + ], + [ + 0.5, + 0.5859375, + 0.5859375 + ], + [ + 0.5, + 0.6328125, + 0.6328125 + ], + [ + 0.5, + 0.67578125, + 0.67578125 + ], + [ + 0.5, + 0.595703125, + 0.595703125 + ], + [ + 0.5, + 0.66015625, + 0.66015625 + ], + [ + 0.5, + 0.6328125, + 0.6328125 + ], + [ + 0.5, + 0.583984375, + 0.583984375 + ], + [ + 0.5, + 0.603515625, + 0.603515625 + ], + [ + 0.5, + 0.662109375, + 0.662109375 + ], + [ + 0.5, + 0.65234375, + 0.65234375 + ], + [ + 0.5, + 0.708984375, + 0.708984375 + ], + [ + 0.5, + 0.65625, + 0.65625 + ], + [ + 0.5, + 0.4765625, + 0.4765625 + ], + [ + 0.5, + 0.59765625, + 0.59765625 + ], + [ + 0.5, + 0.724609375, + 0.724609375 + ], + [ + 0.5, + 0.79296875, + 0.79296875 + ], + [ + 0.5, + 0.583984375, + 0.583984375 + ], + [ + 0.5, + 0.7421875, + 0.7421875 + ], + [ + 0.5, + 0.69140625, + 0.69140625 + ], + [ + 0.5, + 0.62890625, + 0.62890625 + ], + [ + 0.5, + 0.5859375, + 0.5859375 + ], + [ + 0.5, + 0.65625, + 0.65625 + ], + [ + 0.5, + 0.7109375, + 0.7109375 + ], + [ + 0.5, + 0.84375, + 0.84375 + ], + [ + 0.5, + 0.67578125, + 0.67578125 + ], + [ + 0.5, + 0.642578125, + 0.642578125 + ], + [ + 0.5, + 0.703125, + 0.703125 + ], + [ + 0.5, + 0.7421875, + 0.7421875 + ], + [ + 0.5, + 0.6875, + 0.6875 + ], + [ + 0.5, + 0.7109375, + 0.7109375 + ], + [ + 0.5, + 0.583984375, + 0.583984375 + ], + [ + 0.5, + 0.7421875, + 0.7421875 + ], + [ + 0.5, + 0.5859375, + 0.5859375 + ], + [ + 0.5, + 0.771484375, + 0.771484375 + ], + [ + 0.5, + 0.654296875, + 0.654296875 + ], + [ + 0.5, + 0.720703125, + 0.720703125 + ], + [ + 0.5, + 0.5859375, + 0.5859375 + ], + [ + 0.5, + 0.638671875, + 0.638671875 + ], + [ + 0.5, + 0.734375, + 0.734375 + ], + [ + 0.5, + 0.69921875, + 0.69921875 + ], + [ + 0.5, + 0.619140625, + 0.619140625 + ], + [ + 0.5, + 0.626953125, + 0.626953125 + ], + [ + 0.5, + 0.591796875, + 0.591796875 + ], + [ + 0.5, + 0.666015625, + 0.666015625 + ], + [ + 0.5, + 0.60546875, + 0.60546875 + ], + [ + 0.5, + 0.595703125, + 0.595703125 + ], + [ + 0.5, + 0.5859375, + 0.5859375 + ], + [ + 0.5, + 0.53515625, + 0.53515625 + ], + [ + 0.5, + 0.587890625, + 0.587890625 + ], + [ + 0.5, + 0.6171875, + 0.6171875 + ], + [ + 0.5, + 0.576171875, + 0.576171875 + ], + [ + 0.5, + 0.802734375, + 0.802734375 + ], + [ + 0.5, + 0.7421875, + 0.7421875 + ], + [ + 0.5, + 0.7421875, + 0.7421875 + ], + [ + 0.5, + 0.755859375, + 0.755859375 + ], + [ + 0.5, + 0.5859375, + 0.5859375 + ], + [ + 0.5, + 0.70703125, + 0.70703125 + ], + [ + 0.5, + 0.67578125, + 0.67578125 + ], + [ + 0.5, + 0.623046875, + 0.623046875 + ], + [ + 0.5, + 0.658203125, + 0.658203125 + ], + [ + 0.5, + 0.693359375, + 0.693359375 + ], + [ + 0.5, + 0.73046875, + 0.73046875 + ], + [ + 0.5, + 0.62109375, + 0.62109375 + ], + [ + 0.5, + 0.638671875, + 0.638671875 + ], + [ + 0.5, + 0.748046875, + 0.748046875 + ], + [ + 0.5, + 0.669921875, + 0.669921875 + ], + [ + 0.5, + 0.7578125, + 0.7578125 + ], + [ + 0.5, + 0.640625, + 0.640625 + ], + [ + 0.5, + 0.65234375, + 0.65234375 + ], + [ + 0.5, + 0.642578125, + 0.642578125 + ], + [ + 0.5, + 0.60546875, + 0.60546875 + ], + [ + 0.5, + 0.6953125, + 0.6953125 + ], + [ + 0.5, + 0.5859375, + 0.5859375 + ], + [ + 0.5, + 0.626953125, + 0.626953125 + ], + [ + 0.5, + 0.7421875, + 0.7421875 + ], + [ + 0.5, + 0.76953125, + 0.76953125 + ], + [ + 0.5, + 0.619140625, + 0.619140625 + ], + [ + 0.5, + 0.5859375, + 0.5859375 + ], + [ + 0.5, + 0.693359375, + 0.693359375 + ], + [ + 0.5, + 0.6953125, + 0.6953125 + ], + [ + 0.5, + 0.73046875, + 0.73046875 + ], + [ + 0.5, + 0.681640625, + 0.681640625 + ], + [ + 0.5, + 0.6171875, + 0.6171875 + ], + [ + 0.5, + 0.62109375, + 0.62109375 + ], + [ + 0.5, + 0.658203125, + 0.658203125 + ], + [ + 0.5, + 0.6328125, + 0.6328125 + ], + [ + 0.5, + 0.57421875, + 0.57421875 + ], + [ + 0.5, + 0.6953125, + 0.6953125 + ], + [ + 0.5, + 0.654296875, + 0.654296875 + ], + [ + 0.5, + 0.609375, + 0.609375 + ], + [ + 0.5, + 0.751953125, + 0.751953125 + ], + [ + 0.5, + 0.615234375, + 0.615234375 + ], + [ + 0.5, + 0.58203125, + 0.58203125 + ], + [ + 0.5, + 0.689453125, + 0.689453125 + ], + [ + 0.5, + 0.625, + 0.625 + ], + [ + 0.5, + 0.7421875, + 0.7421875 + ], + [ + 0.5, + 0.611328125, + 0.611328125 + ], + [ + 0.5, + 0.650390625, + 0.650390625 + ], + [ + 0.5, + 0.91015625, + 0.91015625 + ], + [ + 0.5, + 0.732421875, + 0.732421875 + ], + [ + 0.5, + 0.7109375, + 0.7109375 + ], + [ + 0.5, + 0.6875, + 0.6875 + ], + [ + 0.5, + 0.7421875, + 0.7421875 + ], + [ + 0.5, + 0.68359375, + 0.68359375 + ], + [ + 0.5, + 0.7421875, + 0.7421875 + ], + [ + 0.5, + 0.6484375, + 0.6484375 + ], + [ + 0.5, + 0.7421875, + 0.7421875 + ], + [ + 0.5, + 0.625, + 0.625 + ], + [ + 0.5, + 0.7265625, + 0.7265625 + ], + [ + 0.5, + 0.751953125, + 0.751953125 + ], + [ + 0.5, + 0.5859375, + 0.5859375 + ], + [ + 0.5, + 0.6484375, + 0.6484375 + ], + [ + 0.5, + 0.712890625, + 0.712890625 + ], + [ + 0.5, + 0.6015625, + 0.6015625 + ], + [ + 0.5, + 0.669921875, + 0.669921875 + ], + [ + 0.5, + 0.583984375, + 0.583984375 + ], + [ + 0.5, + 0.5625, + 0.5625 + ], + [ + 0.5, + 0.587890625, + 0.587890625 + ], + [ + 0.5, + 0.701171875, + 0.701171875 + ], + [ + 0.5, + 0.642578125, + 0.642578125 + ], + [ + 0.5, + 0.7578125, + 0.7578125 + ], + [ + 0.5, + 0.6171875, + 0.6171875 + ], + [ + 0.5, + 0.720703125, + 0.720703125 + ], + [ + 0.5, + 0.720703125, + 0.720703125 + ], + [ + 0.5, + 0.69921875, + 0.69921875 + ], + [ + 0.5, + 0.701171875, + 0.701171875 + ], + [ + 0.5, + 0.5859375, + 0.5859375 + ], + [ + 0.5, + 0.615234375, + 0.615234375 + ], + [ + 0.5, + 0.68359375, + 0.68359375 + ], + [ + 0.5, + 0.6796875, + 0.6796875 + ], + [ + 0.5, + 0.7421875, + 0.7421875 + ], + [ + 0.5, + 0.802734375, + 0.802734375 + ], + [ + 0.5, + 0.73046875, + 0.73046875 + ], + [ + 0.5, + 0.68359375, + 0.68359375 + ], + [ + 0.5, + 0.748046875, + 0.748046875 + ], + [ + 0.5, + 0.7890625, + 0.7890625 + ], + [ + 0.5, + 0.68359375, + 0.68359375 + ], + [ + 0.5, + 0.58203125, + 0.58203125 + ], + [ + 0.5, + 0.6640625, + 0.6640625 + ], + [ + 0.5, + 0.62890625, + 0.62890625 + ], + [ + 0.5, + 0.87109375, + 0.87109375 + ], + [ + 0.5, + 0.572265625, + 0.572265625 + ], + [ + 0.5, + 0.599609375, + 0.599609375 + ], + [ + 0.5, + 0.689453125, + 0.689453125 + ], + [ + 0.5, + 0.55078125, + 0.55078125 + ], + [ + 0.5, + 0.751953125, + 0.751953125 + ], + [ + 0.5, + 0.60546875, + 0.60546875 + ], + [ + 0.5, + 0.68359375, + 0.68359375 + ], + [ + 0.5, + 0.76953125, + 0.76953125 + ], + [ + 0.5, + 0.68359375, + 0.68359375 + ], + [ + 0.5, + 0.75390625, + 0.75390625 + ], + [ + 0.5, + 0.6328125, + 0.6328125 + ], + [ + 0.5, + 0.68359375, + 0.68359375 + ], + [ + 0.5, + 0.740234375, + 0.740234375 + ], + [ + 0.5, + 0.64453125, + 0.64453125 + ], + [ + 0.5, + 0.73828125, + 0.73828125 + ], + [ + 0.5, + 0.671875, + 0.671875 + ], + [ + 0.5, + 0.595703125, + 0.595703125 + ], + [ + 0.5, + 0.6484375, + 0.6484375 + ], + [ + 0.5, + 0.66015625, + 0.66015625 + ], + [ + 0.5, + 0.63671875, + 0.63671875 + ], + [ + 0.5, + 0.662109375, + 0.662109375 + ], + [ + 0.5, + 0.65625, + 0.65625 + ], + [ + 0.5, + 0.640625, + 0.640625 + ], + [ + 0.5, + 0.681640625, + 0.681640625 + ], + [ + 0.5, + 0.626953125, + 0.626953125 + ], + [ + 0.5, + 0.75, + 0.75 + ], + [ + 0.5, + 0.68359375, + 0.68359375 + ], + [ + 0.5, + 0.828125, + 0.828125 + ], + [ + 0.5, + 0.7109375, + 0.7109375 + ], + [ + 0.5, + 0.68359375, + 0.68359375 + ], + [ + 0.5, + 0.728515625, + 0.728515625 + ], + [ + 0.5, + 0.5859375, + 0.5859375 + ], + [ + 0.5, + 0.5859375, + 0.5859375 + ], + [ + 0.5, + 0.68359375, + 0.68359375 + ], + [ + 0.5, + 0.64453125, + 0.64453125 + ], + [ + 0.5, + 0.69921875, + 0.69921875 + ], + [ + 0.5, + 0.5546875, + 0.5546875 + ], + [ + 0.5, + 0.68359375, + 0.68359375 + ], + [ + 0.5, + 0.68359375, + 0.68359375 + ], + [ + 0.5, + 0.68359375, + 0.68359375 + ], + [ + 0.5, + 0.5859375, + 0.5859375 + ], + [ + 0.5, + 0.90234375, + 0.90234375 + ], + [ + 0.5, + 0.7890625, + 0.7890625 + ], + [ + 0.5, + 0.68359375, + 0.68359375 + ], + [ + 0.5, + 0.734375, + 0.734375 + ], + [ + 0.5, + 0.826171875, + 0.826171875 + ], + [ + 0.5, + 0.7734375, + 0.7734375 + ], + [ + 0.5, + 0.5859375, + 0.5859375 + ], + [ + 0.5, + 0.5859375, + 0.5859375 + ], + [ + 0.5, + 0.5859375, + 0.5859375 + ], + [ + 0.5, + 0.68359375, + 0.68359375 + ], + [ + 0.5, + 0.73046875, + 0.73046875 + ], + [ + 0.5, + 0.75390625, + 0.75390625 + ], + [ + 0.5, + 0.68359375, + 0.68359375 + ], + [ + 0.5, + 0.77734375, + 0.77734375 + ], + [ + 0.5, + 0.587890625, + 0.587890625 + ], + [ + 0.5, + 0.7109375, + 0.7109375 + ], + [ + 0.5, + 0.68359375, + 0.68359375 + ], + [ + 0.5, + 0.7890625, + 0.7890625 + ], + [ + 0.5, + 0.90625, + 0.90625 + ], + [ + 0.5, + 0.68359375, + 0.68359375 + ], + [ + 0.5, + 0.68359375, + 0.68359375 + ], + [ + 0.5, + 0.5546875, + 0.5546875 + ], + [ + 0.5, + 0.68359375, + 0.68359375 + ], + [ + 0.5, + 0.810546875, + 0.810546875 + ], + [ + 0.5, + 0.70703125, + 0.70703125 + ], + [ + 0.5, + 0.767578125, + 0.767578125 + ], + [ + 0.5, + 0.71875, + 0.71875 + ], + [ + 0.5, + 0.68359375, + 0.68359375 + ], + [ + 0.5, + 0.70703125, + 0.70703125 + ], + [ + 0.5, + 0.9453125, + 0.9453125 + ], + [ + 0.5, + 0.74609375, + 0.74609375 + ], + [ + 0.5, + 0.65625, + 0.65625 + ], + [ + 0.5, + 0.90625, + 0.90625 + ], + [ + 0.5, + 0.71484375, + 0.71484375 + ], + [ + 0.5, + 0.78125, + 0.78125 + ], + [ + 0.5, + 0.68359375, + 0.68359375 + ], + [ + 0.5, + 0.87109375, + 0.87109375 + ], + [ + 0.5, + 0.765625, + 0.765625 + ], + [ + 0.5, + 0.68359375, + 0.68359375 + ], + [ + 0.5, + 0.79296875, + 0.79296875 + ], + [ + 0.5, + 0.76171875, + 0.76171875 + ], + [ + 0.5, + 0.68359375, + 0.68359375 + ], + [ + 0.5, + 0.765625, + 0.765625 + ], + [ + 0.5, + 0.79296875, + 0.79296875 + ], + [ + 0.5, + 0.55078125, + 0.55078125 + ], + [ + 0.5, + 0.6171875, + 0.6171875 + ], + [ + 0.5, + 0.70703125, + 0.70703125 + ], + [ + 0.5, + 0.662109375, + 0.662109375 + ], + [ + 0.5, + 0.68359375, + 0.68359375 + ], + [ + 0.5, + 0.73046875, + 0.73046875 + ], + [ + 0.5, + 0.78515625, + 0.78515625 + ], + [ + 0.5, + 0.6796875, + 0.6796875 + ], + [ + 0.5, + 0.68359375, + 0.68359375 + ], + [ + 0.5, + 0.69140625, + 0.69140625 + ], + [ + 0.5, + 0.689453125, + 0.689453125 + ], + [ + 0.5, + 0.677734375, + 0.677734375 + ], + [ + 0.5, + 0.74609375, + 0.74609375 + ], + [ + 0.5, + 0.80078125, + 0.80078125 + ], + [ + 0.5, + 0.669921875, + 0.669921875 + ], + [ + 0.5, + 0.7265625, + 0.7265625 + ], + [ + 0.5, + 0.724609375, + 0.724609375 + ], + [ + 0.5, + 0.640625, + 0.640625 + ], + [ + 0.5, + 0.64453125, + 0.64453125 + ], + [ + 0.5, + 0.65625, + 0.65625 + ], + [ + 0.5, + 0.716796875, + 0.716796875 + ], + [ + 0.5, + 0.76953125, + 0.76953125 + ], + [ + 0.5, + 0.576171875, + 0.576171875 + ], + [ + 0.5, + 0.564453125, + 0.564453125 + ], + [ + 0.5, + 0.70703125, + 0.70703125 + ], + [ + 0.5, + 0.82421875, + 0.82421875 + ], + [ + 0.5, + 0.78125, + 0.78125 + ], + [ + 0.5, + 0.607421875, + 0.607421875 + ], + [ + 0.5, + 0.84375, + 0.84375 + ], + [ + 0.5, + 0.6484375, + 0.6484375 + ], + [ + 0.5, + 0.734375, + 0.734375 + ], + [ + 0.5, + 0.78125, + 0.78125 + ], + [ + 0.5, + 0.88671875, + 0.88671875 + ], + [ + 0.5, + 0.81640625, + 0.81640625 + ], + [ + 0.5, + 0.8359375, + 0.8359375 + ], + [ + 0.5, + 0.64453125, + 0.64453125 + ], + [ + 0.5, + 0.701171875, + 0.701171875 + ], + [ + 0.5, + 0.6640625, + 0.6640625 + ], + [ + 0.5, + 0.78515625, + 0.78515625 + ], + [ + 0.4000000059604645, + 0.685546875, + 0.685546875 + ], + [ + 0.5, + 0.55859375, + 0.55859375 + ], + [ + 0.5, + 0.63671875, + 0.63671875 + ], + [ + 0.5, + 0.521484375, + 0.521484375 + ], + [ + 0.5, + 0.73828125, + 0.73828125 + ], + [ + 0.5, + 0.78515625, + 0.78515625 + ], + [ + 0.5, + 0.75390625, + 0.75390625 + ], + [ + 0.5, + 0.845703125, + 0.845703125 + ], + [ + 0.5, + 0.66796875, + 0.66796875 + ], + [ + 0.5, + 0.70703125, + 0.70703125 + ], + [ + 0.5, + 0.630859375, + 0.630859375 + ], + [ + 0.5, + 0.765625, + 0.765625 + ], + [ + 0.5, + 0.888671875, + 0.888671875 + ], + [ + 0.5, + 0.681640625, + 0.681640625 + ], + [ + 0.5, + 0.712890625, + 0.712890625 + ], + [ + 0.5, + 0.70703125, + 0.70703125 + ], + [ + 0.5, + 0.68359375, + 0.68359375 + ], + [ + 0.5, + 0.59765625, + 0.59765625 + ], + [ + 0.5, + 0.7578125, + 0.7578125 + ], + [ + 0.5, + 0.703125, + 0.703125 + ], + [ + 0.5, + 0.71484375, + 0.71484375 + ], + [ + 0.5, + 0.728515625, + 0.728515625 + ], + [ + 0.5, + 0.734375, + 0.734375 + ], + [ + 0.5, + 0.703125, + 0.703125 + ], + [ + 0.5, + 0.888671875, + 0.888671875 + ], + [ + 0.5, + 0.79296875, + 0.79296875 + ], + [ + 0.5, + 0.728515625, + 0.728515625 + ], + [ + 0.5, + 0.619140625, + 0.619140625 + ], + [ + 0.5, + 0.703125, + 0.703125 + ], + [ + 0.5, + 0.80078125, + 0.80078125 + ], + [ + 0.5, + 0.73046875, + 0.73046875 + ], + [ + 0.5, + 0.6640625, + 0.6640625 + ], + [ + 0.5, + 0.771484375, + 0.771484375 + ], + [ + 0.5, + 0.8515625, + 0.8515625 + ], + [ + 0.5, + 0.7890625, + 0.7890625 + ], + [ + 0.5, + 0.76171875, + 0.76171875 + ], + [ + 0.5, + 0.6796875, + 0.6796875 + ], + [ + 0.5, + 0.662109375, + 0.662109375 + ], + [ + 0.5, + 0.76171875, + 0.76171875 + ], + [ + 0.5, + 0.71875, + 0.71875 + ], + [ + 0.5, + 0.734375, + 0.734375 + ], + [ + 0.5, + 0.58984375, + 0.58984375 + ], + [ + 0.5, + 0.6015625, + 0.6015625 + ], + [ + 0.5, + 0.580078125, + 0.580078125 + ], + [ + 0.5, + 0.6875, + 0.6875 + ], + [ + 0.5, + 0.72265625, + 0.72265625 + ], + [ + 0.5, + 0.625, + 0.625 + ], + [ + 0.5, + 0.72265625, + 0.72265625 + ], + [ + 0.5, + 0.6875, + 0.6875 + ], + [ + 0.5, + 0.703125, + 0.703125 + ], + [ + 0.5, + 0.662109375, + 0.662109375 + ], + [ + 0.5, + 0.744140625, + 0.744140625 + ], + [ + 0.5, + 0.7265625, + 0.7265625 + ], + [ + 0.5, + 0.765625, + 0.765625 + ], + [ + 0.5, + 0.6796875, + 0.6796875 + ], + [ + 0.5, + 0.83203125, + 0.83203125 + ], + [ + 0.5, + 0.69140625, + 0.69140625 + ], + [ + 0.5, + 0.67578125, + 0.67578125 + ], + [ + 0.5, + 0.6640625, + 0.6640625 + ], + [ + 0.5, + 0.6171875, + 0.6171875 + ], + [ + 0.5, + 0.666015625, + 0.666015625 + ], + [ + 0.5, + 0.765625, + 0.765625 + ], + [ + 0.5, + 0.705078125, + 0.705078125 + ], + [ + 0.5, + 0.7578125, + 0.7578125 + ], + [ + 0.5, + 0.6796875, + 0.6796875 + ], + [ + 0.5, + 0.736328125, + 0.736328125 + ], + [ + 0.5, + 0.53515625, + 0.53515625 + ], + [ + 0.5, + 0.703125, + 0.703125 + ], + [ + 0.5, + 0.650390625, + 0.650390625 + ], + [ + 0.5, + 0.607421875, + 0.607421875 + ], + [ + 0.5, + 0.78125, + 0.78125 + ], + [ + 0.5, + 0.607421875, + 0.607421875 + ], + [ + 0.5, + 0.716796875, + 0.716796875 + ], + [ + 0.5, + 0.69140625, + 0.69140625 + ], + [ + 0.5, + 0.650390625, + 0.650390625 + ], + [ + 0.5, + 0.740234375, + 0.740234375 + ], + [ + 0.5, + 0.66015625, + 0.66015625 + ], + [ + 0.5, + 0.77734375, + 0.77734375 + ], + [ + 0.5, + 0.72265625, + 0.72265625 + ], + [ + 0.5, + 0.64453125, + 0.64453125 + ], + [ + 0.4000000059604645, + 0.6953125, + 0.6953125 + ], + [ + 0.5, + 0.7734375, + 0.7734375 + ], + [ + 0.5, + 0.68359375, + 0.68359375 + ], + [ + 0.5, + 0.69140625, + 0.69140625 + ], + [ + 0.5, + 0.66796875, + 0.66796875 + ], + [ + 0.5, + 0.71875, + 0.71875 + ], + [ + 0.5, + 0.6015625, + 0.6015625 + ], + [ + 0.5, + 0.669921875, + 0.669921875 + ], + [ + 0.5, + 0.673828125, + 0.673828125 + ], + [ + 0.5, + 0.828125, + 0.828125 + ], + [ + 0.5, + 0.728515625, + 0.728515625 + ], + [ + 0.5, + 0.80078125, + 0.80078125 + ], + [ + 0.5, + 0.724609375, + 0.724609375 + ], + [ + 0.5, + 0.70703125, + 0.70703125 + ], + [ + 0.5, + 0.59375, + 0.59375 + ], + [ + 0.5, + 0.78515625, + 0.78515625 + ], + [ + 0.5, + 0.681640625, + 0.681640625 + ], + [ + 0.5, + 0.685546875, + 0.685546875 + ], + [ + 0.5, + 0.572265625, + 0.572265625 + ], + [ + 0.5, + 0.697265625, + 0.697265625 + ], + [ + 0.5, + 0.84375, + 0.84375 + ], + [ + 0.5, + 0.6796875, + 0.6796875 + ], + [ + 0.5, + 0.6875, + 0.6875 + ], + [ + 0.5, + 0.78515625, + 0.78515625 + ], + [ + 0.5, + 0.7109375, + 0.7109375 + ], + [ + 0.5, + 0.912109375, + 0.912109375 + ], + [ + 0.5, + 0.78515625, + 0.78515625 + ], + [ + 0.5, + 0.685546875, + 0.685546875 + ], + [ + 0.5, + 0.775390625, + 0.775390625 + ], + [ + 0.5, + 0.623046875, + 0.623046875 + ], + [ + 0.5, + 0.765625, + 0.765625 + ], + [ + 0.5, + 0.6328125, + 0.6328125 + ], + [ + 0.5, + 0.8203125, + 0.8203125 + ], + [ + 0.5, + 0.61328125, + 0.61328125 + ], + [ + 0.5, + 0.87890625, + 0.87890625 + ], + [ + 0.5, + 0.7578125, + 0.7578125 + ], + [ + 0.5, + 0.71484375, + 0.71484375 + ], + [ + 0.5, + 0.9453125, + 0.9453125 + ], + [ + 0.5, + 0.755859375, + 0.755859375 + ], + [ + 0.5, + 0.6015625, + 0.6015625 + ], + [ + 0.5, + 0.72265625, + 0.72265625 + ], + [ + 0.5, + 0.701171875, + 0.701171875 + ], + [ + 0.5, + 0.73046875, + 0.73046875 + ], + [ + 0.5, + 0.751953125, + 0.751953125 + ], + [ + 0.75, + 0.66015625, + 0.66015625 + ], + [ + 0.5, + 0.67578125, + 0.67578125 + ], + [ + 0.5, + 0.83203125, + 0.83203125 + ], + [ + 0.75, + 0.732421875, + 0.732421875 + ], + [ + 0.5, + 0.71875, + 0.71875 + ], + [ + 0.5, + 0.7265625, + 0.7265625 + ], + [ + 0.5, + 0.6015625, + 0.6015625 + ], + [ + 0.5, + 0.642578125, + 0.642578125 + ], + [ + 0.5, + 0.73046875, + 0.73046875 + ], + [ + 0.75, + 0.7421875, + 0.7421875 + ], + [ + 0.5, + 0.76953125, + 0.76953125 + ], + [ + 0.5, + 0.744140625, + 0.744140625 + ], + [ + 0.5, + 0.703125, + 0.703125 + ], + [ + 0.5, + 0.7265625, + 0.7265625 + ], + [ + 0.5, + 0.8359375, + 0.8359375 + ], + [ + 0.5, + 0.7109375, + 0.7109375 + ], + [ + 0.5, + 0.59765625, + 0.59765625 + ], + [ + 0.5, + 0.685546875, + 0.685546875 + ], + [ + 0.5, + 0.759765625, + 0.759765625 + ], + [ + 0.5, + 0.66015625, + 0.66015625 + ], + [ + 0.5, + 0.59375, + 0.59375 + ], + [ + 0.5, + 0.716796875, + 0.716796875 + ], + [ + 0.5, + 0.73828125, + 0.73828125 + ], + [ + 0.5, + 0.697265625, + 0.697265625 + ], + [ + 0.5, + 0.71875, + 0.71875 + ], + [ + 0.5, + 0.736328125, + 0.736328125 + ], + [ + 0.5, + 0.828125, + 0.828125 + ], + [ + 0.5, + 0.626953125, + 0.626953125 + ], + [ + 0.5, + 0.71484375, + 0.71484375 + ], + [ + 0.5, + 0.837890625, + 0.837890625 + ], + [ + 0.5, + 0.646484375, + 0.646484375 + ], + [ + 0.75, + 0.595703125, + 0.595703125 + ], + [ + 0.5, + 0.66796875, + 0.66796875 + ], + [ + 0.5, + 0.75, + 0.75 + ], + [ + 0.5, + 0.578125, + 0.578125 + ], + [ + 0.5, + 0.7734375, + 0.7734375 + ], + [ + 0.5, + 0.82421875, + 0.82421875 + ], + [ + 0.5, + 0.75, + 0.75 + ], + [ + 0.5, + 0.841796875, + 0.841796875 + ], + [ + 0.75, + 0.75390625, + 0.75390625 + ], + [ + 0.5, + 0.734375, + 0.734375 + ], + [ + 0.5, + 0.6875, + 0.6875 + ], + [ + 0.5, + 0.833984375, + 0.833984375 + ], + [ + 0.75, + 0.712890625, + 0.712890625 + ], + [ + 0.5, + 0.84375, + 0.84375 + ], + [ + 0.5, + 0.68359375, + 0.68359375 + ], + [ + 0.5, + 0.8125, + 0.8125 + ], + [ + 0.5, + 0.87109375, + 0.87109375 + ], + [ + 0.5, + 0.783203125, + 0.783203125 + ], + [ + 0.5, + 0.6640625, + 0.6640625 + ], + [ + 0.5, + 0.7109375, + 0.7109375 + ], + [ + 0.5, + 0.71484375, + 0.71484375 + ], + [ + 0.5, + 0.755859375, + 0.755859375 + ], + [ + 0.5, + 0.74609375, + 0.74609375 + ], + [ + 0.5, + 0.703125, + 0.703125 + ], + [ + 0.5, + 0.7578125, + 0.7578125 + ], + [ + 0.5, + 0.76171875, + 0.76171875 + ], + [ + 0.75, + 0.705078125, + 0.705078125 + ], + [ + 0.5, + 0.82421875, + 0.82421875 + ], + [ + 0.5, + 0.8125, + 0.8125 + ], + [ + 0.5, + 0.64453125, + 0.64453125 + ], + [ + 0.5, + 0.7265625, + 0.7265625 + ], + [ + 0.5, + 0.73828125, + 0.73828125 + ], + [ + 0.75, + 0.732421875, + 0.732421875 + ], + [ + 0.5, + 0.875, + 0.875 + ], + [ + 0.5, + 0.7421875, + 0.7421875 + ], + [ + 0.5, + 0.79296875, + 0.79296875 + ], + [ + 0.75, + 0.611328125, + 0.611328125 + ], + [ + 0.5, + 0.84765625, + 0.84765625 + ], + [ + 0.5, + 0.8671875, + 0.8671875 + ], + [ + 0.5, + 0.74609375, + 0.74609375 + ], + [ + 0.75, + 0.73046875, + 0.73046875 + ], + [ + 0.5, + 0.861328125, + 0.861328125 + ], + [ + 0.5, + 0.767578125, + 0.767578125 + ], + [ + 0.5, + 0.640625, + 0.640625 + ], + [ + 0.5, + 0.65234375, + 0.65234375 + ], + [ + 0.5, + 0.75390625, + 0.75390625 + ], + [ + 0.5, + 0.6640625, + 0.6640625 + ], + [ + 0.5, + 0.662109375, + 0.662109375 + ], + [ + 0.5, + 0.734375, + 0.734375 + ], + [ + 0.5, + 0.75390625, + 0.75390625 + ], + [ + 0.5, + 0.818359375, + 0.818359375 + ], + [ + 0.5, + 0.7578125, + 0.7578125 + ], + [ + 0.5, + 0.7890625, + 0.7890625 + ], + [ + 0.5, + 0.76953125, + 0.76953125 + ], + [ + 0.5, + 0.68359375, + 0.68359375 + ], + [ + 0.5, + 0.78515625, + 0.78515625 + ], + [ + 0.5, + 0.88671875, + 0.88671875 + ], + [ + 0.5, + 0.83984375, + 0.83984375 + ], + [ + 0.5, + 0.611328125, + 0.611328125 + ], + [ + 0.5, + 0.7734375, + 0.7734375 + ], + [ + 0.5, + 0.69921875, + 0.69921875 + ], + [ + 0.5, + 0.83203125, + 0.83203125 + ], + [ + 0.5, + 0.9765625, + 0.9765625 + ], + [ + 0.5, + 0.89453125, + 0.89453125 + ], + [ + 0.5, + 0.83203125, + 0.83203125 + ], + [ + 0.75, + 0.71484375, + 0.71484375 + ], + [ + 0.5, + 0.8671875, + 0.8671875 + ], + [ + 0.5, + 0.703125, + 0.703125 + ], + [ + 0.5, + 0.69140625, + 0.69140625 + ], + [ + 0.5, + 0.63671875, + 0.63671875 + ], + [ + 0.5, + 0.66015625, + 0.66015625 + ], + [ + 0.5, + 0.625, + 0.625 + ], + [ + 0.5, + 0.67578125, + 0.67578125 + ], + [ + 0.5, + 0.69140625, + 0.69140625 + ], + [ + 0.5, + 0.94921875, + 0.94921875 + ], + [ + 0.75, + 0.7421875, + 0.7421875 + ], + [ + 0.5, + 0.685546875, + 0.685546875 + ], + [ + 0.5, + 0.69140625, + 0.69140625 + ], + [ + 0.5, + 0.9140625, + 0.9140625 + ], + [ + 0.5, + 0.828125, + 0.828125 + ], + [ + 0.5, + 0.716796875, + 0.716796875 + ], + [ + 0.5, + 0.71875, + 0.71875 + ], + [ + 0.5, + 0.7890625, + 0.7890625 + ], + [ + 0.5, + 0.79296875, + 0.79296875 + ], + [ + 0.5, + 0.69140625, + 0.69140625 + ], + [ + 0.5, + 0.892578125, + 0.892578125 + ], + [ + 0.5, + 0.5703125, + 0.5703125 + ], + [ + 0.5, + 0.837890625, + 0.837890625 + ], + [ + 0.5, + 0.6640625, + 0.6640625 + ], + [ + 0.5, + 0.736328125, + 0.736328125 + ], + [ + 0.5, + 0.68359375, + 0.68359375 + ], + [ + 0.5, + 0.6953125, + 0.6953125 + ], + [ + 0.5, + 0.71484375, + 0.71484375 + ], + [ + 0.5, + 0.80859375, + 0.80859375 + ], + [ + 0.5, + 0.783203125, + 0.783203125 + ], + [ + 0.5, + 0.73828125, + 0.73828125 + ], + [ + 0.5, + 0.80078125, + 0.80078125 + ], + [ + 0.75, + 0.70703125, + 0.70703125 + ], + [ + 0.5, + 0.75, + 0.75 + ], + [ + 0.5, + 0.72265625, + 0.72265625 + ], + [ + 0.5, + 0.72265625, + 0.72265625 + ], + [ + 0.5, + 0.734375, + 0.734375 + ], + [ + 0.5, + 0.775390625, + 0.775390625 + ], + [ + 0.5, + 0.759765625, + 0.759765625 + ], + [ + 0.5, + 0.765625, + 0.765625 + ], + [ + 0.5, + 0.5859375, + 0.5859375 + ], + [ + 0.5, + 0.62109375, + 0.62109375 + ], + [ + 0.5, + 0.796875, + 0.796875 + ], + [ + 0.5, + 0.69921875, + 0.69921875 + ], + [ + 0.5, + 0.6875, + 0.6875 + ], + [ + 0.5, + 0.82421875, + 0.82421875 + ], + [ + 0.75, + 0.7421875, + 0.7421875 + ], + [ + 0.5, + 0.9453125, + 0.9453125 + ], + [ + 0.5, + 0.642578125, + 0.642578125 + ], + [ + 0.5, + 0.71484375, + 0.71484375 + ], + [ + 0.5, + 0.78125, + 0.78125 + ], + [ + 0.5, + 0.7890625, + 0.7890625 + ], + [ + 0.5, + 0.78125, + 0.78125 + ], + [ + 0.5, + 0.814453125, + 0.814453125 + ], + [ + 0.5, + 0.77734375, + 0.77734375 + ], + [ + 0.5, + 0.75390625, + 0.75390625 + ], + [ + 0.5, + 0.68359375, + 0.68359375 + ], + [ + 0.5, + 0.73828125, + 0.73828125 + ], + [ + 0.5, + 0.6953125, + 0.6953125 + ], + [ + 0.5, + 0.798828125, + 0.798828125 + ], + [ + 0.75, + 0.73046875, + 0.73046875 + ], + [ + 0.5, + 0.73046875, + 0.73046875 + ], + [ + 0.5, + 0.76953125, + 0.76953125 + ], + [ + 0.5, + 0.87890625, + 0.87890625 + ], + [ + 0.5, + 0.6640625, + 0.6640625 + ], + [ + 0.5, + 0.8359375, + 0.8359375 + ], + [ + 0.5, + 0.71484375, + 0.71484375 + ], + [ + 0.5, + 0.70703125, + 0.70703125 + ], + [ + 0.5, + 0.8671875, + 0.8671875 + ], + [ + 0.5, + 0.71484375, + 0.71484375 + ], + [ + 0.5, + 0.68359375, + 0.68359375 + ], + [ + 0.5, + 0.6640625, + 0.6640625 + ], + [ + 0.5, + 0.76953125, + 0.76953125 + ], + [ + 0.5, + 0.818359375, + 0.818359375 + ], + [ + 0.5, + 0.73046875, + 0.73046875 + ], + [ + 0.75, + 0.791015625, + 0.791015625 + ], + [ + 0.5, + 0.6328125, + 0.6328125 + ], + [ + 0.5, + 0.806640625, + 0.806640625 + ], + [ + 0.5, + 0.7421875, + 0.7421875 + ], + [ + 0.5, + 0.68359375, + 0.68359375 + ], + [ + 0.5, + 0.751953125, + 0.751953125 + ], + [ + 0.5, + 0.7734375, + 0.7734375 + ], + [ + 0.5, + 0.75, + 0.75 + ], + [ + 0.5, + 0.681640625, + 0.681640625 + ], + [ + 0.5, + 0.7109375, + 0.7109375 + ], + [ + 0.5, + 0.67578125, + 0.67578125 + ], + [ + 0.5, + 0.541015625, + 0.541015625 + ], + [ + 0.5, + 0.8359375, + 0.8359375 + ], + [ + 0.5, + 0.68359375, + 0.68359375 + ], + [ + 0.5, + 0.703125, + 0.703125 + ], + [ + 0.5, + 0.75, + 0.75 + ], + [ + 0.5, + 0.84765625, + 0.84765625 + ], + [ + 0.5, + 0.80078125, + 0.80078125 + ], + [ + 0.5, + 0.77734375, + 0.77734375 + ], + [ + 0.5, + 0.83203125, + 0.83203125 + ], + [ + 0.5, + 0.69921875, + 0.69921875 + ], + [ + 0.5, + 0.8046875, + 0.8046875 + ], + [ + 0.5, + 0.76953125, + 0.76953125 + ], + [ + 0.5, + 0.7109375, + 0.7109375 + ], + [ + 0.5, + 0.75, + 0.75 + ], + [ + 0.5, + 0.78125, + 0.78125 + ], + [ + 0.5, + 0.77734375, + 0.77734375 + ], + [ + 0.5, + 0.6875, + 0.6875 + ], + [ + 0.5, + 0.724609375, + 0.724609375 + ], + [ + 0.5, + 0.87109375, + 0.87109375 + ], + [ + 0.5, + 0.646484375, + 0.646484375 + ], + [ + 0.5, + 0.64453125, + 0.64453125 + ], + [ + 0.5, + 0.708984375, + 0.708984375 + ], + [ + 0.5, + 0.71484375, + 0.71484375 + ], + [ + 0.5, + 0.58203125, + 0.58203125 + ], + [ + 0.5, + 0.87109375, + 0.87109375 + ], + [ + 0.5, + 0.78125, + 0.78125 + ], + [ + 0.5, + 0.72265625, + 0.72265625 + ], + [ + 0.5, + 0.75, + 0.75 + ], + [ + 0.5, + 0.7578125, + 0.7578125 + ], + [ + 0.5, + 0.84765625, + 0.84765625 + ], + [ + 0.5, + 0.796875, + 0.796875 + ], + [ + 0.5, + 0.87109375, + 0.87109375 + ], + [ + 0.5, + 0.75, + 0.75 + ], + [ + 0.5, + 0.734375, + 0.734375 + ], + [ + 0.5, + 0.7578125, + 0.7578125 + ], + [ + 0.5, + 0.6875, + 0.6875 + ], + [ + 0.5, + 0.6640625, + 0.6640625 + ], + [ + 0.5, + 0.70703125, + 0.70703125 + ], + [ + 0.5, + 0.8359375, + 0.8359375 + ], + [ + 0.5, + 0.828125, + 0.828125 + ], + [ + 0.5, + 0.6484375, + 0.6484375 + ], + [ + 0.5, + 0.654296875, + 0.654296875 + ], + [ + 0.5, + 0.8046875, + 0.8046875 + ], + [ + 0.5, + 0.75, + 0.75 + ], + [ + 0.5, + 0.814453125, + 0.814453125 + ], + [ + 0.5, + 0.84375, + 0.84375 + ], + [ + 0.5, + 0.74609375, + 0.74609375 + ], + [ + 0.5, + 0.71484375, + 0.71484375 + ], + [ + 0.5, + 0.712890625, + 0.712890625 + ], + [ + 0.5, + 0.755859375, + 0.755859375 + ], + [ + 0.5, + 0.78125, + 0.78125 + ], + [ + 0.5, + 0.708984375, + 0.708984375 + ], + [ + 0.5, + 0.73828125, + 0.73828125 + ], + [ + 0.5, + 0.69140625, + 0.69140625 + ], + [ + 0.5, + 0.7578125, + 0.7578125 + ], + [ + 0.5, + 0.787109375, + 0.787109375 + ], + [ + 0.5, + 0.728515625, + 0.728515625 + ], + [ + 0.5, + 0.65234375, + 0.65234375 + ], + [ + 0.5, + 0.791015625, + 0.791015625 + ], + [ + 0.5, + 0.6171875, + 0.6171875 + ], + [ + 0.5, + 0.640625, + 0.640625 + ], + [ + 0.5, + 0.83984375, + 0.83984375 + ], + [ + 0.5, + 0.59765625, + 0.59765625 + ], + [ + 0.5, + 0.75, + 0.75 + ], + [ + 0.5, + 0.83203125, + 0.83203125 + ], + [ + 0.5, + 0.71875, + 0.71875 + ], + [ + 0.5, + 0.6015625, + 0.6015625 + ], + [ + 0.5, + 0.71484375, + 0.71484375 + ], + [ + 0.5, + 0.65625, + 0.65625 + ], + [ + 0.5, + 0.78125, + 0.78125 + ], + [ + 0.5, + 0.58203125, + 0.58203125 + ], + [ + 0.5, + 0.73828125, + 0.73828125 + ], + [ + 0.5, + 0.76171875, + 0.76171875 + ], + [ + 0.5, + 0.53515625, + 0.53515625 + ], + [ + 0.5, + 0.689453125, + 0.689453125 + ], + [ + 0.5, + 0.798828125, + 0.798828125 + ], + [ + 0.5, + 0.72265625, + 0.72265625 + ], + [ + 0.5, + 0.708984375, + 0.708984375 + ], + [ + 0.5, + 0.650390625, + 0.650390625 + ], + [ + 0.5, + 0.693359375, + 0.693359375 + ], + [ + 0.699999988079071, + 0.9765625, + 0.9765625 + ], + [ + 0.5, + 0.71875, + 0.71875 + ], + [ + 0.5, + 0.66796875, + 0.66796875 + ], + [ + 0.5, + 0.87109375, + 0.87109375 + ], + [ + 0.5, + 0.75, + 0.75 + ], + [ + 0.5, + 0.5859375, + 0.5859375 + ], + [ + 0.5, + 0.748046875, + 0.748046875 + ], + [ + 0.5, + 0.74609375, + 0.74609375 + ], + [ + 0.5, + 0.69140625, + 0.69140625 + ], + [ + 0.5, + 0.7421875, + 0.7421875 + ], + [ + 0.5, + 0.7109375, + 0.7109375 + ], + [ + 0.5, + 0.68359375, + 0.68359375 + ], + [ + 0.5, + 0.6875, + 0.6875 + ], + [ + 0.5, + 0.669921875, + 0.669921875 + ], + [ + 0.5, + 0.740234375, + 0.740234375 + ], + [ + 0.5, + 0.890625, + 0.890625 + ], + [ + 0.5, + 0.73046875, + 0.73046875 + ], + [ + 0.5, + 0.71484375, + 0.71484375 + ], + [ + 0.5, + 0.609375, + 0.609375 + ], + [ + 0.5, + 0.638671875, + 0.638671875 + ], + [ + 0.5, + 0.68359375, + 0.68359375 + ], + [ + 0.5, + 0.775390625, + 0.775390625 + ], + [ + 0.5, + 0.78515625, + 0.78515625 + ], + [ + 0.5, + 0.6875, + 0.6875 + ], + [ + 0.5, + 0.71484375, + 0.71484375 + ], + [ + 0.5, + 0.83203125, + 0.83203125 + ], + [ + 0.5, + 0.7265625, + 0.7265625 + ], + [ + 0.5, + 0.9765625, + 0.9765625 + ], + [ + 0.5, + 0.693359375, + 0.693359375 + ], + [ + 0.5, + 0.890625, + 0.890625 + ], + [ + 0.5, + 0.8515625, + 0.8515625 + ], + [ + 0.5, + 0.740234375, + 0.740234375 + ], + [ + 0.5, + 0.5859375, + 0.5859375 + ], + [ + 0.5, + 0.61328125, + 0.61328125 + ], + [ + 0.5, + 0.76171875, + 0.76171875 + ], + [ + 0.5, + 0.70703125, + 0.70703125 + ], + [ + 0.5, + 0.64453125, + 0.64453125 + ], + [ + 0.5, + 0.640625, + 0.640625 + ], + [ + 0.5, + 0.64453125, + 0.64453125 + ], + [ + 0.75, + 0.63671875, + 0.63671875 + ], + [ + 0.5, + 0.68359375, + 0.68359375 + ], + [ + 0.5, + 0.9453125, + 0.9453125 + ], + [ + 0.75, + 0.76953125, + 0.76953125 + ], + [ + 0.5, + 0.7734375, + 0.7734375 + ], + [ + 0.75, + 0.76171875, + 0.76171875 + ], + [ + 0.75, + 0.73828125, + 0.73828125 + ], + [ + 0.5, + 0.6796875, + 0.6796875 + ], + [ + 0.5, + 0.740234375, + 0.740234375 + ], + [ + 0.5, + 0.71484375, + 0.71484375 + ], + [ + 0.5, + 0.63671875, + 0.63671875 + ], + [ + 0.5, + 0.78125, + 0.78125 + ], + [ + 0.5, + 0.67578125, + 0.67578125 + ], + [ + 0.5, + 0.80078125, + 0.80078125 + ], + [ + 0.5, + 0.8515625, + 0.8515625 + ], + [ + 0.5, + 0.720703125, + 0.720703125 + ], + [ + 0.5, + 0.625, + 0.625 + ], + [ + 0.5, + 0.63671875, + 0.63671875 + ], + [ + 0.5, + 0.8671875, + 0.8671875 + ], + [ + 0.5, + 0.705078125, + 0.705078125 + ], + [ + 0.5, + 0.716796875, + 0.716796875 + ], + [ + 0.5, + 0.669921875, + 0.669921875 + ], + [ + 0.5, + 0.59765625, + 0.59765625 + ], + [ + 0.5, + 0.7578125, + 0.7578125 + ], + [ + 0.5, + 0.876953125, + 0.876953125 + ], + [ + 0.5, + 0.78125, + 0.78125 + ], + [ + 0.5, + 0.9453125, + 0.9453125 + ], + [ + 0.5, + 0.83984375, + 0.83984375 + ], + [ + 0.5, + 0.71484375, + 0.71484375 + ], + [ + 0.5, + 0.62109375, + 0.62109375 + ], + [ + 0.5, + 0.66796875, + 0.66796875 + ], + [ + 0.5, + 0.701171875, + 0.701171875 + ], + [ + 0.5, + 0.625, + 0.625 + ], + [ + 0.5, + 0.689453125, + 0.689453125 + ], + [ + 0.5, + 0.78125, + 0.78125 + ], + [ + 0.5, + 0.6875, + 0.6875 + ], + [ + 0.5, + 0.642578125, + 0.642578125 + ], + [ + 0.5, + 0.78125, + 0.78125 + ], + [ + 0.5, + 0.658203125, + 0.658203125 + ], + [ + 0.5, + 0.5859375, + 0.5859375 + ], + [ + 0.5, + 0.634765625, + 0.634765625 + ], + [ + 0.5, + 0.71484375, + 0.71484375 + ], + [ + 0.5, + 0.689453125, + 0.689453125 + ], + [ + 0.5, + 0.658203125, + 0.658203125 + ], + [ + 0.5, + 0.75390625, + 0.75390625 + ], + [ + 0.5, + 0.80078125, + 0.80078125 + ], + [ + 0.5, + 0.83984375, + 0.83984375 + ], + [ + 0.5, + 0.8203125, + 0.8203125 + ], + [ + 0.5, + 0.78515625, + 0.78515625 + ], + [ + 0.5, + 0.8203125, + 0.8203125 + ], + [ + 0.5, + 0.728515625, + 0.728515625 + ], + [ + 0.5, + 0.6015625, + 0.6015625 + ], + [ + 0.5, + 0.77734375, + 0.77734375 + ], + [ + 0.5, + 0.67578125, + 0.67578125 + ], + [ + 0.4000000059604645, + 0.66015625, + 0.66015625 + ], + [ + 0.5, + 0.693359375, + 0.693359375 + ], + [ + 0.5, + 0.763671875, + 0.763671875 + ], + [ + 0.5, + 0.6015625, + 0.6015625 + ], + [ + 0.5, + 0.74609375, + 0.74609375 + ], + [ + 0.75, + 0.68359375, + 0.68359375 + ], + [ + 0.5, + 0.904296875, + 0.904296875 + ], + [ + 0.5, + 0.80859375, + 0.80859375 + ], + [ + 0.5, + 0.693359375, + 0.693359375 + ], + [ + 0.5, + 0.794921875, + 0.794921875 + ], + [ + 0.5, + 0.642578125, + 0.642578125 + ], + [ + 0.5, + 0.9765625, + 0.9765625 + ], + [ + 0.5, + 0.78515625, + 0.78515625 + ], + [ + 0.5, + 0.87890625, + 0.87890625 + ], + [ + 0.5, + 0.77734375, + 0.77734375 + ], + [ + 0.5, + 0.607421875, + 0.607421875 + ], + [ + 0.5, + 0.677734375, + 0.677734375 + ], + [ + 0.5, + 0.716796875, + 0.716796875 + ], + [ + 0.5, + 0.6640625, + 0.6640625 + ], + [ + 0.5, + 0.60546875, + 0.60546875 + ], + [ + 0.5, + 0.73828125, + 0.73828125 + ], + [ + 0.5, + 0.75390625, + 0.75390625 + ], + [ + 0.5, + 0.818359375, + 0.818359375 + ], + [ + 0.75, + 0.78125, + 0.78125 + ], + [ + 0.5, + 0.671875, + 0.671875 + ], + [ + 0.5, + 0.697265625, + 0.697265625 + ], + [ + 0.5, + 0.85546875, + 0.85546875 + ], + [ + 0.5, + 0.7890625, + 0.7890625 + ], + [ + 0.5, + 0.62109375, + 0.62109375 + ], + [ + 0.5, + 0.658203125, + 0.658203125 + ], + [ + 0.5, + 0.9765625, + 0.9765625 + ], + [ + 0.5, + 0.75, + 0.75 + ], + [ + 0.5, + 0.7109375, + 0.7109375 + ], + [ + 0.5, + 0.81640625, + 0.81640625 + ], + [ + 0.5, + 0.71875, + 0.71875 + ], + [ + 0.5, + 0.73046875, + 0.73046875 + ], + [ + 0.5, + 0.9375, + 0.9375 + ], + [ + 0.5, + 0.748046875, + 0.748046875 + ], + [ + 0.5, + 0.7109375, + 0.7109375 + ], + [ + 0.5, + 0.76953125, + 0.76953125 + ], + [ + 0.5, + 0.7890625, + 0.7890625 + ], + [ + 0.5, + 0.75390625, + 0.75390625 + ], + [ + 0.5, + 0.892578125, + 0.892578125 + ], + [ + 0.5, + 0.58984375, + 0.58984375 + ], + [ + 0.5, + 0.72265625, + 0.72265625 + ], + [ + 0.5, + 0.78125, + 0.78125 + ], + [ + 0.5, + 0.6640625, + 0.6640625 + ], + [ + 0.5, + 0.890625, + 0.890625 + ], + [ + 0.5, + 0.58984375, + 0.58984375 + ], + [ + 0.5, + 0.689453125, + 0.689453125 + ], + [ + 0.5, + 0.658203125, + 0.658203125 + ], + [ + 0.5, + 0.580078125, + 0.580078125 + ], + [ + 0.5, + 0.77734375, + 0.77734375 + ], + [ + 0.5, + 0.755859375, + 0.755859375 + ], + [ + 0.5, + 0.50390625, + 0.50390625 + ], + [ + 0.5, + 0.54296875, + 0.54296875 + ], + [ + 0.5, + 0.76953125, + 0.76953125 + ], + [ + 0.5, + 0.61328125, + 0.61328125 + ], + [ + 0.5, + 0.90234375, + 0.90234375 + ], + [ + 0.5, + 0.89453125, + 0.89453125 + ], + [ + 0.5, + 0.65625, + 0.65625 + ], + [ + 0.5, + 0.7265625, + 0.7265625 + ], + [ + 0.5, + 0.703125, + 0.703125 + ], + [ + 0.5, + 0.720703125, + 0.720703125 + ], + [ + 0.5, + 0.765625, + 0.765625 + ], + [ + 0.5, + 0.71484375, + 0.71484375 + ], + [ + 0.5, + 0.697265625, + 0.697265625 + ], + [ + 0.5, + 0.833984375, + 0.833984375 + ], + [ + 0.5, + 0.705078125, + 0.705078125 + ], + [ + 0.5, + 0.72265625, + 0.72265625 + ], + [ + 0.5, + 0.7421875, + 0.7421875 + ], + [ + 0.5, + 0.705078125, + 0.705078125 + ], + [ + 0.5, + 0.87890625, + 0.87890625 + ], + [ + 0.5, + 0.65625, + 0.65625 + ], + [ + 0.5, + 0.80859375, + 0.80859375 + ], + [ + 0.5, + 0.75390625, + 0.75390625 + ], + [ + 0.5, + 0.89453125, + 0.89453125 + ], + [ + 0.75, + 0.765625, + 0.765625 + ], + [ + 0.75, + 0.77734375, + 0.77734375 + ], + [ + 0.5, + 0.7109375, + 0.7109375 + ], + [ + 0.5, + 0.68359375, + 0.68359375 + ], + [ + 0.5, + 0.818359375, + 0.818359375 + ], + [ + 0.5, + 0.916015625, + 0.916015625 + ], + [ + 0.5, + 0.91015625, + 0.91015625 + ], + [ + 0.5, + 0.765625, + 0.765625 + ], + [ + 0.75, + 0.755859375, + 0.755859375 + ], + [ + 0.5, + 0.6796875, + 0.6796875 + ], + [ + 0.5, + 0.81640625, + 0.81640625 + ], + [ + 0.5, + 0.74609375, + 0.74609375 + ], + [ + 0.5, + 0.671875, + 0.671875 + ], + [ + 0.5, + 0.72265625, + 0.72265625 + ], + [ + 0.5, + 0.720703125, + 0.720703125 + ], + [ + 0.5, + 0.900390625, + 0.900390625 + ], + [ + 0.5, + 0.76953125, + 0.76953125 + ], + [ + 0.5, + 0.716796875, + 0.716796875 + ], + [ + 0.5, + 0.859375, + 0.859375 + ], + [ + 0.75, + 0.73046875, + 0.73046875 + ], + [ + 0.5, + 0.7421875, + 0.7421875 + ], + [ + 0.5, + 0.73046875, + 0.73046875 + ], + [ + 0.5, + 0.6796875, + 0.6796875 + ], + [ + 0.5, + 0.748046875, + 0.748046875 + ], + [ + 0.5, + 0.65234375, + 0.65234375 + ], + [ + 0.5, + 0.7890625, + 0.7890625 + ], + [ + 0.5, + 0.720703125, + 0.720703125 + ], + [ + 0.5, + 0.62109375, + 0.62109375 + ], + [ + 0.5, + 0.69921875, + 0.69921875 + ], + [ + 0.5, + 0.625, + 0.625 + ], + [ + 0.5, + 0.818359375, + 0.818359375 + ], + [ + 0.5, + 0.8515625, + 0.8515625 + ], + [ + 0.5, + 0.802734375, + 0.802734375 + ], + [ + 0.5, + 0.71484375, + 0.71484375 + ], + [ + 0.5, + 0.76953125, + 0.76953125 + ], + [ + 0.5, + 0.83203125, + 0.83203125 + ], + [ + 0.5, + 0.720703125, + 0.720703125 + ], + [ + 0.5, + 0.703125, + 0.703125 + ], + [ + 0.5, + 0.8203125, + 0.8203125 + ], + [ + 0.5, + 0.6953125, + 0.6953125 + ], + [ + 0.5, + 0.84375, + 0.84375 + ], + [ + 0.5, + 0.75390625, + 0.75390625 + ], + [ + 0.5, + 0.654296875, + 0.654296875 + ], + [ + 0.5, + 0.765625, + 0.765625 + ], + [ + 0.5, + 0.830078125, + 0.830078125 + ], + [ + 0.5, + 0.75390625, + 0.75390625 + ], + [ + 0.5, + 0.736328125, + 0.736328125 + ], + [ + 0.5, + 0.8828125, + 0.8828125 + ], + [ + 0.5, + 0.77734375, + 0.77734375 + ], + [ + 0.5, + 0.576171875, + 0.576171875 + ], + [ + 0.5, + 0.755859375, + 0.755859375 + ], + [ + 0.5, + 0.71875, + 0.71875 + ], + [ + 0.5, + 0.9765625, + 0.9765625 + ], + [ + 0.5, + 0.71484375, + 0.71484375 + ], + [ + 0.75, + 0.68359375, + 0.68359375 + ], + [ + 0.5, + 0.76953125, + 0.76953125 + ], + [ + 0.5, + 0.8984375, + 0.8984375 + ], + [ + 0.5, + 0.890625, + 0.890625 + ], + [ + 0.5, + 0.740234375, + 0.740234375 + ], + [ + 0.5, + 0.890625, + 0.890625 + ], + [ + 0.75, + 0.6328125, + 0.6328125 + ], + [ + 0.5, + 0.64453125, + 0.64453125 + ], + [ + 0.5, + 0.859375, + 0.859375 + ], + [ + 0.5, + 0.765625, + 0.765625 + ], + [ + 0.5, + 0.7890625, + 0.7890625 + ], + [ + 0.5, + 0.75, + 0.75 + ], + [ + 0.5, + 0.703125, + 0.703125 + ], + [ + 0.5, + 0.80078125, + 0.80078125 + ], + [ + 0.5, + 0.69921875, + 0.69921875 + ], + [ + 0.5, + 0.7109375, + 0.7109375 + ], + [ + 0.5, + 0.68359375, + 0.68359375 + ], + [ + 0.5, + 0.8203125, + 0.8203125 + ], + [ + 0.5, + 0.93359375, + 0.93359375 + ], + [ + 0.5, + 0.68359375, + 0.68359375 + ], + [ + 0.5, + 0.76171875, + 0.76171875 + ], + [ + 0.75, + 0.8203125, + 0.8203125 + ], + [ + 0.5, + 0.82421875, + 0.82421875 + ], + [ + 0.5, + 0.8125, + 0.8125 + ], + [ + 0.5, + 0.76953125, + 0.76953125 + ], + [ + 0.5, + 0.7265625, + 0.7265625 + ], + [ + 0.5, + 0.85546875, + 0.85546875 + ], + [ + 0.5, + 0.791015625, + 0.791015625 + ], + [ + 0.5, + 0.74609375, + 0.74609375 + ], + [ + 0.5, + 0.673828125, + 0.673828125 + ], + [ + 0.5, + 0.734375, + 0.734375 + ], + [ + 0.5, + 0.83984375, + 0.83984375 + ], + [ + 0.5, + 0.669921875, + 0.669921875 + ], + [ + 0.5, + 0.62890625, + 0.62890625 + ], + [ + 0.75, + 0.71875, + 0.71875 + ], + [ + 0.5, + 0.6875, + 0.6875 + ], + [ + 0.5, + 0.77734375, + 0.77734375 + ], + [ + 0.5, + 0.68359375, + 0.68359375 + ], + [ + 0.5, + 0.71875, + 0.71875 + ], + [ + 0.5, + 0.68359375, + 0.68359375 + ], + [ + 0.5, + 0.580078125, + 0.580078125 + ], + [ + 0.5, + 0.828125, + 0.828125 + ], + [ + 0.5, + 0.876953125, + 0.876953125 + ], + [ + 0.5, + 0.626953125, + 0.626953125 + ], + [ + 0.5, + 0.73046875, + 0.73046875 + ], + [ + 0.5, + 0.7109375, + 0.7109375 + ], + [ + 0.5, + 0.890625, + 0.890625 + ], + [ + 0.5, + 0.564453125, + 0.564453125 + ], + [ + 0.5, + 0.7109375, + 0.7109375 + ], + [ + 0.5, + 0.857421875, + 0.857421875 + ], + [ + 0.5, + 0.76953125, + 0.76953125 + ], + [ + 0.5, + 0.72265625, + 0.72265625 + ], + [ + 0.5, + 0.85546875, + 0.85546875 + ], + [ + 0.5, + 0.69140625, + 0.69140625 + ], + [ + 0.5, + 0.9765625, + 0.9765625 + ], + [ + 0.5, + 0.66796875, + 0.66796875 + ], + [ + 0.5, + 0.90625, + 0.90625 + ], + [ + 0.5, + 0.69140625, + 0.69140625 + ], + [ + 0.5, + 0.49609375, + 0.49609375 + ], + [ + 0.5, + 0.845703125, + 0.845703125 + ], + [ + 0.5, + 0.736328125, + 0.736328125 + ], + [ + 0.5, + 0.6015625, + 0.6015625 + ], + [ + 0.5, + 0.681640625, + 0.681640625 + ], + [ + 0.5, + 0.75, + 0.75 + ], + [ + 0.5, + 0.77734375, + 0.77734375 + ], + [ + 0.5, + 0.75390625, + 0.75390625 + ], + [ + 0.5, + 0.9140625, + 0.9140625 + ], + [ + 0.5, + 0.83984375, + 0.83984375 + ], + [ + 0.5, + 0.830078125, + 0.830078125 + ], + [ + 0.5, + 0.92578125, + 0.92578125 + ], + [ + 0.5, + 0.8125, + 0.8125 + ], + [ + 0.5, + 0.671875, + 0.671875 + ], + [ + 0.5, + 0.75390625, + 0.75390625 + ], + [ + 0.5, + 0.767578125, + 0.767578125 + ], + [ + 0.5, + 0.56640625, + 0.56640625 + ], + [ + 0.5, + 0.658203125, + 0.658203125 + ], + [ + 0.5, + 0.6015625, + 0.6015625 + ], + [ + 0.5, + 0.841796875, + 0.841796875 + ], + [ + 0.5, + 0.71484375, + 0.71484375 + ], + [ + 0.5, + 0.76171875, + 0.76171875 + ], + [ + 0.5, + 0.6953125, + 0.6953125 + ], + [ + 0.5, + 0.76171875, + 0.76171875 + ], + [ + 0.5, + 0.73828125, + 0.73828125 + ], + [ + 0.5, + 0.8984375, + 0.8984375 + ], + [ + 0.5, + 0.90234375, + 0.90234375 + ], + [ + 0.5, + 0.79296875, + 0.79296875 + ], + [ + 0.5, + 0.6640625, + 0.6640625 + ], + [ + 0.5, + 0.80859375, + 0.80859375 + ], + [ + 0.5, + 0.7265625, + 0.7265625 + ], + [ + 0.5, + 0.6796875, + 0.6796875 + ], + [ + 0.5, + 0.681640625, + 0.681640625 + ], + [ + 0.5, + 0.703125, + 0.703125 + ], + [ + 0.5, + 0.796875, + 0.796875 + ], + [ + 0.5, + 0.70703125, + 0.70703125 + ], + [ + 0.5, + 0.88671875, + 0.88671875 + ], + [ + 0.5, + 0.7734375, + 0.7734375 + ], + [ + 0.5, + 0.755859375, + 0.755859375 + ], + [ + 0.5, + 0.8359375, + 0.8359375 + ], + [ + 0.5, + 0.9765625, + 0.9765625 + ], + [ + 0.5, + 0.60546875, + 0.60546875 + ], + [ + 0.5, + 0.88671875, + 0.88671875 + ], + [ + 0.5, + 0.962890625, + 0.962890625 + ], + [ + 0.5, + 0.80078125, + 0.80078125 + ], + [ + 0.5, + 0.9609375, + 0.9609375 + ], + [ + 0.5, + 0.892578125, + 0.892578125 + ], + [ + 0.5, + 0.703125, + 0.703125 + ], + [ + 0.5, + 0.83984375, + 0.83984375 + ], + [ + 0.5, + 0.837890625, + 0.837890625 + ], + [ + 0.5, + 0.759765625, + 0.759765625 + ], + [ + 0.5, + 0.875, + 0.875 + ], + [ + 0.5, + 0.765625, + 0.765625 + ], + [ + 0.5, + 0.74609375, + 0.74609375 + ], + [ + 0.5, + 0.77734375, + 0.77734375 + ], + [ + 0.5, + 0.748046875, + 0.748046875 + ], + [ + 0.5, + 0.65234375, + 0.65234375 + ], + [ + 0.5, + 0.7734375, + 0.7734375 + ], + [ + 0.5, + 0.73828125, + 0.73828125 + ], + [ + 0.5, + 0.62890625, + 0.62890625 + ], + [ + 0.5, + 0.560546875, + 0.560546875 + ], + [ + 0.5, + 0.80078125, + 0.80078125 + ], + [ + 0.5, + 0.685546875, + 0.685546875 + ], + [ + 0.5, + 0.779296875, + 0.779296875 + ], + [ + 0.5, + 0.6484375, + 0.6484375 + ], + [ + 0.5, + 0.869140625, + 0.869140625 + ], + [ + 0.5, + 0.669921875, + 0.669921875 + ], + [ + 0.5, + 0.78515625, + 0.78515625 + ], + [ + 0.5, + 0.966796875, + 0.966796875 + ], + [ + 0.5, + 0.7421875, + 0.7421875 + ], + [ + 0.5, + 0.63671875, + 0.63671875 + ], + [ + 0.5, + 0.9453125, + 0.9453125 + ], + [ + 0.5, + 0.765625, + 0.765625 + ], + [ + 0.5, + 0.662109375, + 0.662109375 + ], + [ + 0.5, + 0.685546875, + 0.685546875 + ], + [ + 0.5, + 0.75390625, + 0.75390625 + ], + [ + 0.5, + 0.78125, + 0.78125 + ], + [ + 0.5, + 0.6640625, + 0.6640625 + ], + [ + 0.5, + 0.59375, + 0.59375 + ], + [ + 0.5, + 0.69140625, + 0.69140625 + ], + [ + 0.5, + 0.841796875, + 0.841796875 + ], + [ + 0.5, + 0.642578125, + 0.642578125 + ], + [ + 0.5, + 0.609375, + 0.609375 + ], + [ + 0.5, + 0.76171875, + 0.76171875 + ], + [ + 0.5, + 0.662109375, + 0.662109375 + ], + [ + 0.5, + 0.74609375, + 0.74609375 + ], + [ + 0.5, + 0.828125, + 0.828125 + ], + [ + 0.5, + 0.83984375, + 0.83984375 + ], + [ + 0.5, + 0.8125, + 0.8125 + ], + [ + 0.5, + 0.9765625, + 0.9765625 + ], + [ + 0.5, + 0.7265625, + 0.7265625 + ], + [ + 0.5, + 0.86328125, + 0.86328125 + ], + [ + 0.5, + 0.83984375, + 0.83984375 + ], + [ + 0.5, + 0.87109375, + 0.87109375 + ], + [ + 0.5, + 0.97265625, + 0.97265625 + ], + [ + 0.5, + 0.7265625, + 0.7265625 + ], + [ + 0.5, + 0.69921875, + 0.69921875 + ], + [ + 0.5, + 0.76171875, + 0.76171875 + ], + [ + 0.5, + 0.677734375, + 0.677734375 + ], + [ + 0.5, + 0.865234375, + 0.865234375 + ], + [ + 0.5, + 0.54296875, + 0.54296875 + ], + [ + 0.5, + 0.8125, + 0.8125 + ], + [ + 0.5, + 0.76171875, + 0.76171875 + ], + [ + 0.5, + 0.814453125, + 0.814453125 + ], + [ + 0.5, + 0.697265625, + 0.697265625 + ], + [ + 0.5, + 0.921875, + 0.921875 + ], + [ + 0.5, + 0.783203125, + 0.783203125 + ], + [ + 0.5, + 0.90234375, + 0.90234375 + ], + [ + 0.5, + 0.8203125, + 0.8203125 + ], + [ + 0.5, + 0.77734375, + 0.77734375 + ], + [ + 0.5, + 0.7890625, + 0.7890625 + ], + [ + 0.5, + 0.724609375, + 0.724609375 + ], + [ + 0.5, + 0.853515625, + 0.853515625 + ], + [ + 0.5, + 0.83984375, + 0.83984375 + ], + [ + 0.5, + 0.77734375, + 0.77734375 + ], + [ + 0.5, + 0.67578125, + 0.67578125 + ], + [ + 0.5, + 0.837890625, + 0.837890625 + ], + [ + 0.5, + 0.779296875, + 0.779296875 + ], + [ + 0.5, + 0.595703125, + 0.595703125 + ], + [ + 0.5, + 0.9765625, + 0.9765625 + ], + [ + 0.5, + 0.6640625, + 0.6640625 + ], + [ + 0.5, + 0.82421875, + 0.82421875 + ], + [ + 0.5, + 0.650390625, + 0.650390625 + ], + [ + 0.5, + 0.78515625, + 0.78515625 + ], + [ + 0.5, + 0.701171875, + 0.701171875 + ], + [ + 0.5, + 0.70703125, + 0.70703125 + ], + [ + 0.5, + 0.755859375, + 0.755859375 + ], + [ + 0.5, + 0.77734375, + 0.77734375 + ], + [ + 0.5, + 0.78125, + 0.78125 + ], + [ + 0.5, + 0.7734375, + 0.7734375 + ], + [ + 0.5, + 0.82421875, + 0.82421875 + ], + [ + 0.5, + 0.619140625, + 0.619140625 + ], + [ + 0.5, + 0.74609375, + 0.74609375 + ], + [ + 0.5, + 0.73046875, + 0.73046875 + ], + [ + 0.5, + 0.6953125, + 0.6953125 + ], + [ + 0.5, + 0.77734375, + 0.77734375 + ], + [ + 0.5, + 0.73828125, + 0.73828125 + ], + [ + 0.5, + 0.822265625, + 0.822265625 + ], + [ + 0.5, + 0.693359375, + 0.693359375 + ], + [ + 0.5, + 0.6953125, + 0.6953125 + ], + [ + 0.5, + 0.78515625, + 0.78515625 + ], + [ + 0.5, + 0.890625, + 0.890625 + ], + [ + 0.5, + 0.6875, + 0.6875 + ], + [ + 0.5, + 0.75390625, + 0.75390625 + ], + [ + 0.5, + 0.701171875, + 0.701171875 + ], + [ + 0.5, + 0.69140625, + 0.69140625 + ], + [ + 0.5, + 0.810546875, + 0.810546875 + ], + [ + 0.5, + 0.95703125, + 0.95703125 + ], + [ + 0.5, + 0.66796875, + 0.66796875 + ], + [ + 0.5, + 0.767578125, + 0.767578125 + ], + [ + 0.5, + 0.75, + 0.75 + ], + [ + 0.5, + 0.62890625, + 0.62890625 + ], + [ + 0.5, + 0.77734375, + 0.77734375 + ], + [ + 0.5, + 0.65234375, + 0.65234375 + ], + [ + 0.5, + 0.6328125, + 0.6328125 + ], + [ + 0.5, + 0.68359375, + 0.68359375 + ], + [ + 0.5, + 0.6328125, + 0.6328125 + ], + [ + 0.5, + 0.69921875, + 0.69921875 + ], + [ + 0.5, + 0.9765625, + 0.9765625 + ], + [ + 0.5, + 0.85546875, + 0.85546875 + ], + [ + 0.5, + 0.7421875, + 0.7421875 + ], + [ + 0.5, + 0.73828125, + 0.73828125 + ], + [ + 0.5, + 0.80859375, + 0.80859375 + ], + [ + 0.5, + 0.86328125, + 0.86328125 + ], + [ + 1.0, + 0.849609375, + 0.849609375 + ], + [ + 0.5, + 0.7890625, + 0.7890625 + ], + [ + 0.5, + 0.828125, + 0.828125 + ], + [ + 0.5, + 0.66015625, + 0.66015625 + ], + [ + 0.5, + 0.75, + 0.75 + ], + [ + 0.5, + 0.7578125, + 0.7578125 + ], + [ + 0.5, + 0.828125, + 0.828125 + ], + [ + 0.5, + 0.681640625, + 0.681640625 + ], + [ + 0.5, + 0.673828125, + 0.673828125 + ], + [ + 0.800048828125, + 0.9765625, + 0.9765625 + ], + [ + 0.5, + 0.65625, + 0.65625 + ], + [ + 0.5, + 0.736328125, + 0.736328125 + ], + [ + 0.5, + 0.75390625, + 0.75390625 + ], + [ + 0.625, + 0.8261719942092896, + 0.8261719942092896 + ], + [ + 0.5, + 0.640625, + 0.640625 + ], + [ + 0.5, + 0.681640625, + 0.681640625 + ], + [ + 0.5, + 0.74609375, + 0.74609375 + ], + [ + 0.5, + 0.6484375, + 0.6484375 + ], + [ + 0.5, + 0.7109375, + 0.7109375 + ], + [ + 0.5, + 0.759765625, + 0.759765625 + ], + [ + 0.5, + 0.8515625, + 0.8515625 + ], + [ + 0.5, + 0.662109375, + 0.662109375 + ], + [ + 0.5, + 0.720703125, + 0.720703125 + ], + [ + 0.5, + 0.822265625, + 0.822265625 + ], + [ + 0.5, + 0.73828125, + 0.73828125 + ], + [ + 0.5, + 0.93359375, + 0.93359375 + ], + [ + 0.5, + 0.64453125, + 0.64453125 + ], + [ + 0.5, + 0.486328125, + 0.486328125 + ], + [ + 0.5, + 0.70703125, + 0.70703125 + ], + [ + 0.5, + 0.78125, + 0.78125 + ], + [ + 0.5, + 0.64453125, + 0.64453125 + ], + [ + 0.5, + 0.79296875, + 0.79296875 + ], + [ + 0.5, + 0.78125, + 0.78125 + ], + [ + 0.5, + 0.7421875, + 0.7421875 + ], + [ + 0.5, + 0.60546875, + 0.60546875 + ], + [ + 0.5, + 0.5859375, + 0.5859375 + ], + [ + 0.5, + 0.7265625, + 0.7265625 + ], + [ + 0.5, + 0.72265625, + 0.72265625 + ], + [ + 0.5, + 0.7109375, + 0.7109375 + ], + [ + 0.5, + 0.5859375, + 0.5859375 + ], + [ + 0.5, + 0.7421875, + 0.7421875 + ], + [ + 0.5, + 0.6953125, + 0.6953125 + ], + [ + 0.5, + 0.7421875, + 0.7421875 + ], + [ + 0.5, + 0.68359375, + 0.68359375 + ], + [ + 0.5, + 0.85546875, + 0.85546875 + ], + [ + 0.5, + 0.71484375, + 0.71484375 + ], + [ + 0.5, + 0.92578125, + 0.92578125 + ], + [ + 0.5, + 0.765625, + 0.765625 + ], + [ + 0.5, + 0.67578125, + 0.67578125 + ], + [ + 0.5, + 0.740234375, + 0.740234375 + ], + [ + 0.5, + 0.724609375, + 0.724609375 + ], + [ + 0.5, + 0.78125, + 0.78125 + ], + [ + 0.5, + 0.859375, + 0.859375 + ], + [ + 0.5, + 0.5859375, + 0.5859375 + ], + [ + 0.5, + 0.796875, + 0.796875 + ], + [ + 0.5, + 0.75, + 0.75 + ], + [ + 0.5, + 0.64453125, + 0.64453125 + ], + [ + 0.5, + 0.64453125, + 0.64453125 + ], + [ + 0.5, + 0.75, + 0.75 + ], + [ + 0.5, + 0.75, + 0.75 + ], + [ + 0.5, + 0.7109375, + 0.7109375 + ], + [ + 0.5, + 0.712890625, + 0.712890625 + ], + [ + 0.5, + 0.64453125, + 0.64453125 + ], + [ + 0.5, + 0.736328125, + 0.736328125 + ], + [ + 0.5, + 0.5859375, + 0.5859375 + ], + [ + 0.5, + 0.71484375, + 0.71484375 + ], + [ + 0.5, + 0.83203125, + 0.83203125 + ], + [ + 0.5, + 0.6328125, + 0.6328125 + ], + [ + 0.5, + 0.6640625, + 0.6640625 + ], + [ + 0.5, + 0.65234375, + 0.65234375 + ], + [ + 0.5, + 0.62890625, + 0.62890625 + ], + [ + 0.5, + 0.5859375, + 0.5859375 + ], + [ + 0.5, + 0.55078125, + 0.55078125 + ], + [ + 0.5, + 0.88671875, + 0.88671875 + ], + [ + 0.5, + 0.6953125, + 0.6953125 + ], + [ + 0.5, + 0.859375, + 0.859375 + ], + [ + 0.5, + 0.71484375, + 0.71484375 + ], + [ + 0.5, + 0.560546875, + 0.560546875 + ], + [ + 0.5, + 0.5625, + 0.5625 + ], + [ + 0.75, + 0.73046875, + 0.73046875 + ], + [ + 0.5, + 0.802734375, + 0.802734375 + ], + [ + 0.5, + 0.84375, + 0.84375 + ], + [ + 0.5, + 0.69921875, + 0.69921875 + ], + [ + 0.5, + 0.759765625, + 0.759765625 + ], + [ + 0.5, + 0.62109375, + 0.62109375 + ], + [ + 0.5, + 0.8125, + 0.8125 + ], + [ + 0.5, + 0.6484375, + 0.6484375 + ], + [ + 0.5, + 0.75, + 0.75 + ], + [ + 0.5, + 0.7890625, + 0.7890625 + ], + [ + 0.5, + 0.80859375, + 0.80859375 + ], + [ + 0.5, + 0.775390625, + 0.775390625 + ], + [ + 0.5, + 0.591796875, + 0.591796875 + ], + [ + 0.5, + 0.6328125, + 0.6328125 + ], + [ + 0.5, + 0.6523438096046448, + 0.6523438096046448 + ], + [ + 0.5, + 0.93359375, + 0.93359375 + ], + [ + 0.5, + 0.74609375, + 0.74609375 + ], + [ + 0.75, + 0.6640625, + 0.6640625 + ], + [ + 0.5, + 0.625, + 0.625 + ], + [ + 0.5, + 0.5625, + 0.5625 + ], + [ + 0.5, + 0.953125, + 0.953125 + ], + [ + 0.75, + 0.73046875, + 0.73046875 + ], + [ + 0.5, + 0.802734375, + 0.802734375 + ], + [ + 0.5, + 0.69140625, + 0.69140625 + ], + [ + 0.5, + 0.666015625, + 0.666015625 + ], + [ + 0.5, + 0.765625, + 0.765625 + ], + [ + 0.5, + 0.830078125, + 0.830078125 + ], + [ + 0.5, + 0.80859375, + 0.80859375 + ], + [ + 0.5, + 0.72265625, + 0.72265625 + ], + [ + 0.5, + 0.6953125, + 0.6953125 + ], + [ + 0.5, + 0.70703125, + 0.70703125 + ], + [ + 0.5, + 0.689453125, + 0.689453125 + ], + [ + 0.75, + 0.771484375, + 0.771484375 + ], + [ + 0.5, + 0.6171875, + 0.6171875 + ], + [ + 0.5, + 0.79296875, + 0.79296875 + ], + [ + 0.5, + 0.71484375, + 0.71484375 + ], + [ + 0.5, + 0.71484375, + 0.71484375 + ], + [ + 0.5, + 0.80859375, + 0.80859375 + ], + [ + 0.5, + 0.8515625, + 0.8515625 + ], + [ + 0.5, + 0.689453125, + 0.689453125 + ], + [ + 0.5, + 0.693359375, + 0.693359375 + ] + ] +} \ No newline at end of file diff --git a/Dataset809_AbdomenAtlasF17/nnUNetTrainer__nnUNetResEncUNetLPlans__2d/fold_all/.DS_Store b/Dataset809_AbdomenAtlasF17/nnUNetTrainer__nnUNetResEncUNetLPlans__2d/fold_all/.DS_Store new file mode 100644 index 0000000000000000000000000000000000000000..5008ddfcf53c02e82d7eee2e57c38e5672ef89f6 Binary files /dev/null and b/Dataset809_AbdomenAtlasF17/nnUNetTrainer__nnUNetResEncUNetLPlans__2d/fold_all/.DS_Store differ diff --git a/Dataset809_AbdomenAtlasF17/nnUNetTrainer__nnUNetResEncUNetLPlans__2d/fold_all/checkpoint_best.pth b/Dataset809_AbdomenAtlasF17/nnUNetTrainer__nnUNetResEncUNetLPlans__2d/fold_all/checkpoint_best.pth new file mode 100644 index 0000000000000000000000000000000000000000..3c2260a41b523e70a72abbeeca98b2662d6630b9 --- /dev/null +++ b/Dataset809_AbdomenAtlasF17/nnUNetTrainer__nnUNetResEncUNetLPlans__2d/fold_all/checkpoint_best.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:54a721b665bc283aefb9aad70ecc34f773fb703b149e3cbe67280fbbe68ad1f9 +size 1122159090 diff --git a/Dataset809_AbdomenAtlasF17/nnUNetTrainer__nnUNetResEncUNetLPlans__2d/fold_all/checkpoint_final.pth b/Dataset809_AbdomenAtlasF17/nnUNetTrainer__nnUNetResEncUNetLPlans__2d/fold_all/checkpoint_final.pth new file mode 100644 index 0000000000000000000000000000000000000000..bcc4c37d03b0c9cf7327ddd9a1f537ad8886c67b --- /dev/null +++ b/Dataset809_AbdomenAtlasF17/nnUNetTrainer__nnUNetResEncUNetLPlans__2d/fold_all/checkpoint_final.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:84df811db038623efb6cb3993e5271f688d2b57ab44a9ec45a545acf7f418a38 +size 1122162406 diff --git a/Dataset809_AbdomenAtlasF17/nnUNetTrainer__nnUNetResEncUNetLPlans__2d/fold_all/debug.json b/Dataset809_AbdomenAtlasF17/nnUNetTrainer__nnUNetResEncUNetLPlans__2d/fold_all/debug.json new file mode 100644 index 0000000000000000000000000000000000000000..060b42c2c0e191c9cb97d5791013575d2b6bb3b3 --- /dev/null +++ b/Dataset809_AbdomenAtlasF17/nnUNetTrainer__nnUNetResEncUNetLPlans__2d/fold_all/debug.json @@ -0,0 +1,53 @@ +{ + "_best_ema": "None", + "batch_size": "22", + "configuration_manager": "{'data_identifier': 'nnUNetPlans_2d', 'preprocessor_name': 'DefaultPreprocessor', 'batch_size': 22, 'patch_size': [640, 640], 'median_image_size_in_voxels': [613.0, 513.0], 'spacing': [0.5, 0.7109375], 'normalization_schemes': ['CTNormalization'], 'use_mask_for_norm': [False], 'resampling_fn_data': 'resample_data_or_seg_to_shape', 'resampling_fn_seg': 'resample_data_or_seg_to_shape', 'resampling_fn_data_kwargs': {'is_seg': False, 'order': 3, 'order_z': 0, 'force_separate_z': None}, 'resampling_fn_seg_kwargs': {'is_seg': True, 'order': 1, 'order_z': 0, 'force_separate_z': None}, 'resampling_fn_probabilities': 'resample_data_or_seg_to_shape', 'resampling_fn_probabilities_kwargs': {'is_seg': False, 'order': 1, 'order_z': 0, 'force_separate_z': None}, 'architecture': {'network_class_name': 'dynamic_network_architectures.architectures.unet.ResidualEncoderUNet', 'arch_kwargs': {'n_stages': 8, 'features_per_stage': [32, 64, 128, 256, 512, 512, 512, 512], 'conv_op': 'torch.nn.modules.conv.Conv2d', 'kernel_sizes': [[3, 3], [3, 3], [3, 3], [3, 3], [3, 3], [3, 3], [3, 3], [3, 3]], 'strides': [[1, 1], [2, 2], [2, 2], [2, 2], [2, 2], [2, 2], [2, 2], [2, 2]], 'n_blocks_per_stage': [1, 3, 4, 6, 6, 6, 6, 6], 'n_conv_per_stage_decoder': [1, 1, 1, 1, 1, 1, 1], 'conv_bias': True, 'norm_op': 'torch.nn.modules.instancenorm.InstanceNorm2d', 'norm_op_kwargs': {'eps': 1e-05, 'affine': True}, 'dropout_op': None, 'dropout_op_kwargs': None, 'nonlin': 'torch.nn.LeakyReLU', 'nonlin_kwargs': {'inplace': True}}, '_kw_requires_import': ['conv_op', 'norm_op', 'dropout_op', 'nonlin']}, 'batch_dice': True}", + "configuration_name": "2d", + "cudnn_version": 90100, + "current_epoch": "0", + "dataloader_train": "", + "dataloader_train.generator": "", + "dataloader_train.num_processes": "12", + "dataloader_train.transform": "None", + "dataloader_val": "", + "dataloader_val.generator": "", + "dataloader_val.num_processes": "6", + "dataloader_val.transform": "None", + "dataset_json": "{'name': 'JHH-Train-test', 'description': '3151 cases for training; 1958 cases for testing', 'reference': 'ScaleMAI', 'licence': 'CC-BY-SA 4.0', 'relase': '1.0 10/28/2024', 'tensorImageSize': '3D', 'labels': {'background': 0, 'aorta': 1, 'adrenal_gland_left': 2, 'adrenal_gland_right': 3, 'celiac_aa': 4, 'colon': 5, 'duodenum': 6, 'gall_bladder': 7, 'postcava': 8, 'kidney_left': 9, 'kidney_right': 10, 'liver': 11, 'pancreas': 12, 'superior_mesenteric_artery': 13, 'intestine': 14, 'spleen': 15, 'renal_vein_left': 16, 'renal_vein_right': 17}, 'numTraining': 3151, 'numTest': 1958, 'file_ending': '.nii.gz', 'channel_names': {'0': 'CT'}}", + "device": "cuda:0", + "disable_checkpointing": "False", + "enable_deep_supervision": "True", + "fold": "all", + "folder_with_segs_from_previous_stage": "None", + "gpu_name": "NVIDIA TITAN RTX", + "grad_scaler": "", + "hostname": "ccvl18", + "inference_allowed_mirroring_axes": "(0, 1)", + "initial_lr": "0.01", + "is_cascaded": "False", + "is_ddp": "False", + "label_manager": "", + "local_rank": "0", + "log_file": "/mnt/T9/tlin67/nnUNet_results/Dataset809_AbdomenAtlasF17/nnUNetTrainer__nnUNetResEncUNetLPlans__2d/fold_all/training_log_2025_11_10_22_36_21.txt", + "logger": "", + "loss": "DeepSupervisionWrapper(\n (loss): DC_and_CE_loss(\n (ce): RobustCrossEntropyLoss()\n (dc): OptimizedModule(\n (_orig_mod): MemoryEfficientSoftDiceLoss()\n )\n )\n)", + "lr_scheduler": "", + "my_init_kwargs": "{'plans': {'dataset_name': 'Dataset809_AbdomenAtlasF17', 'plans_name': 'nnUNetResEncUNetLPlans', 'original_median_spacing_after_transp': [0.7109375, 0.5, 0.7109375], 'original_median_shape_after_transp': [512, 608, 512], 'image_reader_writer': 'SimpleITKIO', 'transpose_forward': [1, 0, 2], 'transpose_backward': [1, 0, 2], 'configurations': {'2d': {'data_identifier': 'nnUNetPlans_2d', 'preprocessor_name': 'DefaultPreprocessor', 'batch_size': 22, 'patch_size': [640, 640], 'median_image_size_in_voxels': [613.0, 513.0], 'spacing': [0.5, 0.7109375], 'normalization_schemes': ['CTNormalization'], 'use_mask_for_norm': [False], 'resampling_fn_data': 'resample_data_or_seg_to_shape', 'resampling_fn_seg': 'resample_data_or_seg_to_shape', 'resampling_fn_data_kwargs': {'is_seg': False, 'order': 3, 'order_z': 0, 'force_separate_z': None}, 'resampling_fn_seg_kwargs': {'is_seg': True, 'order': 1, 'order_z': 0, 'force_separate_z': None}, 'resampling_fn_probabilities': 'resample_data_or_seg_to_shape', 'resampling_fn_probabilities_kwargs': {'is_seg': False, 'order': 1, 'order_z': 0, 'force_separate_z': None}, 'architecture': {'network_class_name': 'dynamic_network_architectures.architectures.unet.ResidualEncoderUNet', 'arch_kwargs': {'n_stages': 8, 'features_per_stage': [32, 64, 128, 256, 512, 512, 512, 512], 'conv_op': 'torch.nn.modules.conv.Conv2d', 'kernel_sizes': [[3, 3], [3, 3], [3, 3], [3, 3], [3, 3], [3, 3], [3, 3], [3, 3]], 'strides': [[1, 1], [2, 2], [2, 2], [2, 2], [2, 2], [2, 2], [2, 2], [2, 2]], 'n_blocks_per_stage': [1, 3, 4, 6, 6, 6, 6, 6], 'n_conv_per_stage_decoder': [1, 1, 1, 1, 1, 1, 1], 'conv_bias': True, 'norm_op': 'torch.nn.modules.instancenorm.InstanceNorm2d', 'norm_op_kwargs': {'eps': 1e-05, 'affine': True}, 'dropout_op': None, 'dropout_op_kwargs': None, 'nonlin': 'torch.nn.LeakyReLU', 'nonlin_kwargs': {'inplace': True}}, '_kw_requires_import': ['conv_op', 'norm_op', 'dropout_op', 'nonlin']}, 'batch_dice': True}, '3d_lowres': {'data_identifier': 'nnUNetResEncUNetLPlans_3d_lowres', 'preprocessor_name': 'DefaultPreprocessor', 'batch_size': 2, 'patch_size': [160, 224, 192], 'median_image_size_in_voxels': [283, 339, 284], 'spacing': [1.284032205897787, 0.9030556173347075, 1.284032205897787], 'normalization_schemes': ['CTNormalization'], 'use_mask_for_norm': [False], 'resampling_fn_data': 'resample_data_or_seg_to_shape', 'resampling_fn_seg': 'resample_data_or_seg_to_shape', 'resampling_fn_data_kwargs': {'is_seg': False, 'order': 3, 'order_z': 0, 'force_separate_z': None}, 'resampling_fn_seg_kwargs': {'is_seg': True, 'order': 1, 'order_z': 0, 'force_separate_z': None}, 'resampling_fn_probabilities': 'resample_data_or_seg_to_shape', 'resampling_fn_probabilities_kwargs': {'is_seg': False, 'order': 1, 'order_z': 0, 'force_separate_z': None}, 'architecture': {'network_class_name': 'dynamic_network_architectures.architectures.unet.ResidualEncoderUNet', 'arch_kwargs': {'n_stages': 6, 'features_per_stage': [32, 64, 128, 256, 320, 320], 'conv_op': 'torch.nn.modules.conv.Conv3d', 'kernel_sizes': [[3, 3, 3], [3, 3, 3], [3, 3, 3], [3, 3, 3], [3, 3, 3], [3, 3, 3]], 'strides': [[1, 1, 1], [2, 2, 2], [2, 2, 2], [2, 2, 2], [2, 2, 2], [2, 2, 2]], 'n_blocks_per_stage': [1, 3, 4, 6, 6, 6], 'n_conv_per_stage_decoder': [1, 1, 1, 1, 1], 'conv_bias': True, 'norm_op': 'torch.nn.modules.instancenorm.InstanceNorm3d', 'norm_op_kwargs': {'eps': 1e-05, 'affine': True}, 'dropout_op': None, 'dropout_op_kwargs': None, 'nonlin': 'torch.nn.LeakyReLU', 'nonlin_kwargs': {'inplace': True}}, '_kw_requires_import': ['conv_op', 'norm_op', 'dropout_op', 'nonlin']}, 'batch_dice': False, 'next_stage': '3d_cascade_fullres'}, '3d_fullres': {'data_identifier': 'nnUNetPlans_3d_fullres', 'preprocessor_name': 'DefaultPreprocessor', 'batch_size': 2, 'patch_size': [160, 224, 192], 'median_image_size_in_voxels': [512.0, 613.0, 513.0], 'spacing': [0.7109375, 0.5, 0.7109375], 'normalization_schemes': ['CTNormalization'], 'use_mask_for_norm': [False], 'resampling_fn_data': 'resample_data_or_seg_to_shape', 'resampling_fn_seg': 'resample_data_or_seg_to_shape', 'resampling_fn_data_kwargs': {'is_seg': False, 'order': 3, 'order_z': 0, 'force_separate_z': None}, 'resampling_fn_seg_kwargs': {'is_seg': True, 'order': 1, 'order_z': 0, 'force_separate_z': None}, 'resampling_fn_probabilities': 'resample_data_or_seg_to_shape', 'resampling_fn_probabilities_kwargs': {'is_seg': False, 'order': 1, 'order_z': 0, 'force_separate_z': None}, 'architecture': {'network_class_name': 'dynamic_network_architectures.architectures.unet.ResidualEncoderUNet', 'arch_kwargs': {'n_stages': 6, 'features_per_stage': [32, 64, 128, 256, 320, 320], 'conv_op': 'torch.nn.modules.conv.Conv3d', 'kernel_sizes': [[3, 3, 3], [3, 3, 3], [3, 3, 3], [3, 3, 3], [3, 3, 3], [3, 3, 3]], 'strides': [[1, 1, 1], [2, 2, 2], [2, 2, 2], [2, 2, 2], [2, 2, 2], [2, 2, 2]], 'n_blocks_per_stage': [1, 3, 4, 6, 6, 6], 'n_conv_per_stage_decoder': [1, 1, 1, 1, 1], 'conv_bias': True, 'norm_op': 'torch.nn.modules.instancenorm.InstanceNorm3d', 'norm_op_kwargs': {'eps': 1e-05, 'affine': True}, 'dropout_op': None, 'dropout_op_kwargs': None, 'nonlin': 'torch.nn.LeakyReLU', 'nonlin_kwargs': {'inplace': True}}, '_kw_requires_import': ['conv_op', 'norm_op', 'dropout_op', 'nonlin']}, 'batch_dice': True}, '3d_cascade_fullres': {'inherits_from': '3d_fullres', 'previous_stage': '3d_lowres'}}, 'experiment_planner_used': 'nnUNetPlannerResEncL', 'label_manager': 'LabelManager', 'foreground_intensity_properties_per_channel': {'0': {'max': 1000.0, 'mean': 39.68027877807617, 'median': 71.0, 'min': -1000.0, 'percentile_00_5': -1000.0, 'percentile_99_5': 379.0, 'std': 192.4669952392578}}}, 'configuration': '2d', 'fold': 'all', 'dataset_json': {'name': 'JHH-Train-test', 'description': '3151 cases for training; 1958 cases for testing', 'reference': 'ScaleMAI', 'licence': 'CC-BY-SA 4.0', 'relase': '1.0 10/28/2024', 'tensorImageSize': '3D', 'labels': {'background': 0, 'aorta': 1, 'adrenal_gland_left': 2, 'adrenal_gland_right': 3, 'celiac_aa': 4, 'colon': 5, 'duodenum': 6, 'gall_bladder': 7, 'postcava': 8, 'kidney_left': 9, 'kidney_right': 10, 'liver': 11, 'pancreas': 12, 'superior_mesenteric_artery': 13, 'intestine': 14, 'spleen': 15, 'renal_vein_left': 16, 'renal_vein_right': 17}, 'numTraining': 3151, 'numTest': 1958, 'file_ending': '.nii.gz', 'channel_names': {'0': 'CT'}}, 'unpack_dataset': True, 'device': device(type='cuda')}", + "network": "OptimizedModule", + "num_epochs": "1000", + "num_input_channels": "1", + "num_iterations_per_epoch": "250", + "num_val_iterations_per_epoch": "50", + "optimizer": "SGD (\nParameter Group 0\n dampening: 0\n differentiable: False\n foreach: None\n fused: None\n initial_lr: 0.01\n lr: 0.01\n maximize: False\n momentum: 0.99\n nesterov: True\n weight_decay: 3e-05\n)", + "output_folder": "/mnt/T9/tlin67/nnUNet_results/Dataset809_AbdomenAtlasF17/nnUNetTrainer__nnUNetResEncUNetLPlans__2d/fold_all", + "output_folder_base": "/mnt/T9/tlin67/nnUNet_results/Dataset809_AbdomenAtlasF17/nnUNetTrainer__nnUNetResEncUNetLPlans__2d", + "oversample_foreground_percent": "0.33", + "plans_manager": "{'dataset_name': 'Dataset809_AbdomenAtlasF17', 'plans_name': 'nnUNetResEncUNetLPlans', 'original_median_spacing_after_transp': [0.7109375, 0.5, 0.7109375], 'original_median_shape_after_transp': [512, 608, 512], 'image_reader_writer': 'SimpleITKIO', 'transpose_forward': [1, 0, 2], 'transpose_backward': [1, 0, 2], 'configurations': {'2d': {'data_identifier': 'nnUNetPlans_2d', 'preprocessor_name': 'DefaultPreprocessor', 'batch_size': 22, 'patch_size': [640, 640], 'median_image_size_in_voxels': [613.0, 513.0], 'spacing': [0.5, 0.7109375], 'normalization_schemes': ['CTNormalization'], 'use_mask_for_norm': [False], 'resampling_fn_data': 'resample_data_or_seg_to_shape', 'resampling_fn_seg': 'resample_data_or_seg_to_shape', 'resampling_fn_data_kwargs': {'is_seg': False, 'order': 3, 'order_z': 0, 'force_separate_z': None}, 'resampling_fn_seg_kwargs': {'is_seg': True, 'order': 1, 'order_z': 0, 'force_separate_z': None}, 'resampling_fn_probabilities': 'resample_data_or_seg_to_shape', 'resampling_fn_probabilities_kwargs': {'is_seg': False, 'order': 1, 'order_z': 0, 'force_separate_z': None}, 'architecture': {'network_class_name': 'dynamic_network_architectures.architectures.unet.ResidualEncoderUNet', 'arch_kwargs': {'n_stages': 8, 'features_per_stage': [32, 64, 128, 256, 512, 512, 512, 512], 'conv_op': 'torch.nn.modules.conv.Conv2d', 'kernel_sizes': [[3, 3], [3, 3], [3, 3], [3, 3], [3, 3], [3, 3], [3, 3], [3, 3]], 'strides': [[1, 1], [2, 2], [2, 2], [2, 2], [2, 2], [2, 2], [2, 2], [2, 2]], 'n_blocks_per_stage': [1, 3, 4, 6, 6, 6, 6, 6], 'n_conv_per_stage_decoder': [1, 1, 1, 1, 1, 1, 1], 'conv_bias': True, 'norm_op': 'torch.nn.modules.instancenorm.InstanceNorm2d', 'norm_op_kwargs': {'eps': 1e-05, 'affine': True}, 'dropout_op': None, 'dropout_op_kwargs': None, 'nonlin': 'torch.nn.LeakyReLU', 'nonlin_kwargs': {'inplace': True}}, '_kw_requires_import': ['conv_op', 'norm_op', 'dropout_op', 'nonlin']}, 'batch_dice': True}, '3d_lowres': {'data_identifier': 'nnUNetResEncUNetLPlans_3d_lowres', 'preprocessor_name': 'DefaultPreprocessor', 'batch_size': 2, 'patch_size': [160, 224, 192], 'median_image_size_in_voxels': [283, 339, 284], 'spacing': [1.284032205897787, 0.9030556173347075, 1.284032205897787], 'normalization_schemes': ['CTNormalization'], 'use_mask_for_norm': [False], 'resampling_fn_data': 'resample_data_or_seg_to_shape', 'resampling_fn_seg': 'resample_data_or_seg_to_shape', 'resampling_fn_data_kwargs': {'is_seg': False, 'order': 3, 'order_z': 0, 'force_separate_z': None}, 'resampling_fn_seg_kwargs': {'is_seg': True, 'order': 1, 'order_z': 0, 'force_separate_z': None}, 'resampling_fn_probabilities': 'resample_data_or_seg_to_shape', 'resampling_fn_probabilities_kwargs': {'is_seg': False, 'order': 1, 'order_z': 0, 'force_separate_z': None}, 'architecture': {'network_class_name': 'dynamic_network_architectures.architectures.unet.ResidualEncoderUNet', 'arch_kwargs': {'n_stages': 6, 'features_per_stage': [32, 64, 128, 256, 320, 320], 'conv_op': 'torch.nn.modules.conv.Conv3d', 'kernel_sizes': [[3, 3, 3], [3, 3, 3], [3, 3, 3], [3, 3, 3], [3, 3, 3], [3, 3, 3]], 'strides': [[1, 1, 1], [2, 2, 2], [2, 2, 2], [2, 2, 2], [2, 2, 2], [2, 2, 2]], 'n_blocks_per_stage': [1, 3, 4, 6, 6, 6], 'n_conv_per_stage_decoder': [1, 1, 1, 1, 1], 'conv_bias': True, 'norm_op': 'torch.nn.modules.instancenorm.InstanceNorm3d', 'norm_op_kwargs': {'eps': 1e-05, 'affine': True}, 'dropout_op': None, 'dropout_op_kwargs': None, 'nonlin': 'torch.nn.LeakyReLU', 'nonlin_kwargs': {'inplace': True}}, '_kw_requires_import': ['conv_op', 'norm_op', 'dropout_op', 'nonlin']}, 'batch_dice': False, 'next_stage': '3d_cascade_fullres'}, '3d_fullres': {'data_identifier': 'nnUNetPlans_3d_fullres', 'preprocessor_name': 'DefaultPreprocessor', 'batch_size': 2, 'patch_size': [160, 224, 192], 'median_image_size_in_voxels': [512.0, 613.0, 513.0], 'spacing': [0.7109375, 0.5, 0.7109375], 'normalization_schemes': ['CTNormalization'], 'use_mask_for_norm': [False], 'resampling_fn_data': 'resample_data_or_seg_to_shape', 'resampling_fn_seg': 'resample_data_or_seg_to_shape', 'resampling_fn_data_kwargs': {'is_seg': False, 'order': 3, 'order_z': 0, 'force_separate_z': None}, 'resampling_fn_seg_kwargs': {'is_seg': True, 'order': 1, 'order_z': 0, 'force_separate_z': None}, 'resampling_fn_probabilities': 'resample_data_or_seg_to_shape', 'resampling_fn_probabilities_kwargs': {'is_seg': False, 'order': 1, 'order_z': 0, 'force_separate_z': None}, 'architecture': {'network_class_name': 'dynamic_network_architectures.architectures.unet.ResidualEncoderUNet', 'arch_kwargs': {'n_stages': 6, 'features_per_stage': [32, 64, 128, 256, 320, 320], 'conv_op': 'torch.nn.modules.conv.Conv3d', 'kernel_sizes': [[3, 3, 3], [3, 3, 3], [3, 3, 3], [3, 3, 3], [3, 3, 3], [3, 3, 3]], 'strides': [[1, 1, 1], [2, 2, 2], [2, 2, 2], [2, 2, 2], [2, 2, 2], [2, 2, 2]], 'n_blocks_per_stage': [1, 3, 4, 6, 6, 6], 'n_conv_per_stage_decoder': [1, 1, 1, 1, 1], 'conv_bias': True, 'norm_op': 'torch.nn.modules.instancenorm.InstanceNorm3d', 'norm_op_kwargs': {'eps': 1e-05, 'affine': True}, 'dropout_op': None, 'dropout_op_kwargs': None, 'nonlin': 'torch.nn.LeakyReLU', 'nonlin_kwargs': {'inplace': True}}, '_kw_requires_import': ['conv_op', 'norm_op', 'dropout_op', 'nonlin']}, 'batch_dice': True}, '3d_cascade_fullres': {'inherits_from': '3d_fullres', 'previous_stage': '3d_lowres'}}, 'experiment_planner_used': 'nnUNetPlannerResEncL', 'label_manager': 'LabelManager', 'foreground_intensity_properties_per_channel': {'0': {'max': 1000.0, 'mean': 39.68027877807617, 'median': 71.0, 'min': -1000.0, 'percentile_00_5': -1000.0, 'percentile_99_5': 379.0, 'std': 192.4669952392578}}}", + "preprocessed_dataset_folder": "/mnt/T9/tlin67/Dataset_preprocessed/Dataset809_AbdomenAtlasF17/nnUNetPlans_2d", + "preprocessed_dataset_folder_base": "/mnt/T9/tlin67/Dataset_preprocessed/Dataset809_AbdomenAtlasF17", + "save_every": "50", + "torch_version": "2.4.0+cu121", + "unpack_dataset": "True", + "was_initialized": "True", + "weight_decay": "3e-05" +} \ No newline at end of file diff --git a/Dataset809_AbdomenAtlasF17/nnUNetTrainer__nnUNetResEncUNetLPlans__2d/fold_all/progress.png b/Dataset809_AbdomenAtlasF17/nnUNetTrainer__nnUNetResEncUNetLPlans__2d/fold_all/progress.png new file mode 100644 index 0000000000000000000000000000000000000000..b0076bdec422666800bf3106398952bf5ce7d39a --- /dev/null +++ b/Dataset809_AbdomenAtlasF17/nnUNetTrainer__nnUNetResEncUNetLPlans__2d/fold_all/progress.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d94326f8a0604a9a2f429e5306ed13d979f37fe12fefe992b35fa6cfa7cbb0c0 +size 547108 diff --git a/Dataset809_AbdomenAtlasF17/nnUNetTrainer__nnUNetResEncUNetLPlans__2d/fold_all/training_log_2025_11_10_22_36_21.txt b/Dataset809_AbdomenAtlasF17/nnUNetTrainer__nnUNetResEncUNetLPlans__2d/fold_all/training_log_2025_11_10_22_36_21.txt new file mode 100644 index 0000000000000000000000000000000000000000..a216430a275a0b0aba2dc06db06a037b4b24675b --- /dev/null +++ b/Dataset809_AbdomenAtlasF17/nnUNetTrainer__nnUNetResEncUNetLPlans__2d/fold_all/training_log_2025_11_10_22_36_21.txt @@ -0,0 +1,8098 @@ + +####################################################################### +Please cite the following paper when using nnU-Net: +Isensee, F., Jaeger, P. F., Kohl, S. A., Petersen, J., & Maier-Hein, K. H. (2021). nnU-Net: a self-configuring method for deep learning-based biomedical image segmentation. Nature methods, 18(2), 203-211. +####################################################################### + +2025-11-10 22:36:21.071446: do_dummy_2d_data_aug: False +2025-11-10 22:49:53.345873: Using torch.compile... + +This is the configuration used by this training: +Configuration name: 2d + {'data_identifier': 'nnUNetPlans_2d', 'preprocessor_name': 'DefaultPreprocessor', 'batch_size': 22, 'patch_size': [640, 640], 'median_image_size_in_voxels': [613.0, 513.0], 'spacing': [0.5, 0.7109375], 'normalization_schemes': ['CTNormalization'], 'use_mask_for_norm': [False], 'resampling_fn_data': 'resample_data_or_seg_to_shape', 'resampling_fn_seg': 'resample_data_or_seg_to_shape', 'resampling_fn_data_kwargs': {'is_seg': False, 'order': 3, 'order_z': 0, 'force_separate_z': None}, 'resampling_fn_seg_kwargs': {'is_seg': True, 'order': 1, 'order_z': 0, 'force_separate_z': None}, 'resampling_fn_probabilities': 'resample_data_or_seg_to_shape', 'resampling_fn_probabilities_kwargs': {'is_seg': False, 'order': 1, 'order_z': 0, 'force_separate_z': None}, 'architecture': {'network_class_name': 'dynamic_network_architectures.architectures.unet.ResidualEncoderUNet', 'arch_kwargs': {'n_stages': 8, 'features_per_stage': [32, 64, 128, 256, 512, 512, 512, 512], 'conv_op': 'torch.nn.modules.conv.Conv2d', 'kernel_sizes': [[3, 3], [3, 3], [3, 3], [3, 3], [3, 3], [3, 3], [3, 3], [3, 3]], 'strides': [[1, 1], [2, 2], [2, 2], [2, 2], [2, 2], [2, 2], [2, 2], [2, 2]], 'n_blocks_per_stage': [1, 3, 4, 6, 6, 6, 6, 6], 'n_conv_per_stage_decoder': [1, 1, 1, 1, 1, 1, 1], 'conv_bias': True, 'norm_op': 'torch.nn.modules.instancenorm.InstanceNorm2d', 'norm_op_kwargs': {'eps': 1e-05, 'affine': True}, 'dropout_op': None, 'dropout_op_kwargs': None, 'nonlin': 'torch.nn.LeakyReLU', 'nonlin_kwargs': {'inplace': True}}, '_kw_requires_import': ['conv_op', 'norm_op', 'dropout_op', 'nonlin']}, 'batch_dice': True} + +These are the global plan.json settings: + {'dataset_name': 'Dataset809_AbdomenAtlasF17', 'plans_name': 'nnUNetResEncUNetLPlans', 'original_median_spacing_after_transp': [0.7109375, 0.5, 0.7109375], 'original_median_shape_after_transp': [512, 608, 512], 'image_reader_writer': 'SimpleITKIO', 'transpose_forward': [1, 0, 2], 'transpose_backward': [1, 0, 2], 'experiment_planner_used': 'nnUNetPlannerResEncL', 'label_manager': 'LabelManager', 'foreground_intensity_properties_per_channel': {'0': {'max': 1000.0, 'mean': 39.68027877807617, 'median': 71.0, 'min': -1000.0, 'percentile_00_5': -1000.0, 'percentile_99_5': 379.0, 'std': 192.4669952392578}}} + +2025-11-10 22:50:57.328513: unpacking dataset... +2025-11-11 01:59:03.436516: unpacking done... +2025-11-11 01:59:03.462193: Unable to plot network architecture: nnUNet_compile is enabled! +2025-11-11 01:59:04.831842: +2025-11-11 01:59:04.833712: Epoch 0 +2025-11-11 01:59:04.835889: Current learning rate: 0.01 +2025-11-11 02:10:22.089738: train_loss 0.6043 +2025-11-11 02:10:22.109177: val_loss 0.3326 +2025-11-11 02:10:22.112800: Pseudo dice [np.float32(0.0), np.float32(0.0), np.float32(0.0), np.float32(0.0), np.float32(0.0), np.float32(0.0), np.float32(0.0), np.float32(0.0), np.float32(0.0), np.float32(0.0), np.float32(0.0), np.float32(0.0), np.float32(0.0), np.float32(0.0), np.float32(0.0), np.float32(0.0), np.float32(0.0)] +2025-11-11 02:10:22.113923: Epoch time: 677.27 s +2025-11-11 02:10:22.114983: Yayy! New best EMA pseudo Dice: 0.0 +2025-11-11 02:10:31.755489: +2025-11-11 02:10:31.757420: Epoch 1 +2025-11-11 02:10:31.759239: Current learning rate: 0.00999 +2025-11-11 02:14:50.594106: train_loss 0.2818 +2025-11-11 02:14:50.598103: val_loss 0.2135 +2025-11-11 02:14:50.599260: Pseudo dice [np.float32(0.0), np.float32(0.0), np.float32(0.0), np.float32(0.0), np.float32(0.0), np.float32(0.0), np.float32(0.0), np.float32(0.0), np.float32(0.0), np.float32(0.0), np.float32(0.7051), np.float32(0.0), np.float32(0.0), np.float32(0.0), np.float32(0.0), np.float32(0.0), np.float32(0.0)] +2025-11-11 02:14:50.600352: Epoch time: 258.84 s +2025-11-11 02:14:50.601354: Yayy! New best EMA pseudo Dice: 0.004100000020116568 +2025-11-11 02:14:55.858829: +2025-11-11 02:14:55.860234: Epoch 2 +2025-11-11 02:14:55.861637: Current learning rate: 0.00998 +2025-11-11 02:19:13.984946: train_loss 0.168 +2025-11-11 02:19:13.989994: val_loss 0.1051 +2025-11-11 02:19:13.991193: Pseudo dice [np.float32(0.0), np.float32(0.0), np.float32(0.0), np.float32(0.0), np.float32(0.0801), np.float32(0.0), np.float32(0.0), np.float32(0.0), np.float32(0.0), np.float32(0.0), np.float32(0.8083), np.float32(0.0), np.float32(0.0), np.float32(0.2355), np.float32(0.0), np.float32(0.0), np.float32(0.0)] +2025-11-11 02:19:13.992429: Epoch time: 258.13 s +2025-11-11 02:19:13.993509: Yayy! New best EMA pseudo Dice: 0.010300000198185444 +2025-11-11 02:19:19.194769: +2025-11-11 02:19:19.196463: Epoch 3 +2025-11-11 02:19:19.198052: Current learning rate: 0.00997 +2025-11-11 02:23:37.546254: train_loss 0.0662 +2025-11-11 02:23:37.551659: val_loss 0.0015 +2025-11-11 02:23:37.553453: Pseudo dice [np.float32(0.4507), np.float32(0.0), np.float32(0.0), np.float32(0.0), np.float32(0.6441), np.float32(0.0), np.float32(0.0), np.float32(0.0), np.float32(0.2898), np.float32(0.0), np.float32(0.8756), np.float32(0.0), np.float32(0.0), np.float32(0.5069), np.float32(0.3746), np.float32(0.0), np.float32(0.0)] +2025-11-11 02:23:37.555100: Epoch time: 258.36 s +2025-11-11 02:23:37.556497: Yayy! New best EMA pseudo Dice: 0.027799999341368675 +2025-11-11 02:23:42.861665: +2025-11-11 02:23:42.862991: Epoch 4 +2025-11-11 02:23:42.864403: Current learning rate: 0.00996 +2025-11-11 02:28:01.100373: train_loss -0.0434 +2025-11-11 02:28:01.106385: val_loss -0.13 +2025-11-11 02:28:01.108033: Pseudo dice [np.float32(0.7152), np.float32(0.0), np.float32(0.0), np.float32(0.0), np.float32(0.7126), np.float32(0.0), np.float32(0.0), np.float32(0.0), np.float32(0.6337), np.float32(0.6418), np.float32(0.9133), np.float32(0.0), np.float32(0.0), np.float32(0.6614), np.float32(0.766), np.float32(0.0), np.float32(0.0)] +2025-11-11 02:28:01.113585: Epoch time: 258.24 s +2025-11-11 02:28:01.115263: Yayy! New best EMA pseudo Dice: 0.05469999834895134 +2025-11-11 02:28:06.395044: +2025-11-11 02:28:06.396575: Epoch 5 +2025-11-11 02:28:06.397972: Current learning rate: 0.00995 +2025-11-11 02:32:24.687855: train_loss -0.15 +2025-11-11 02:32:24.692533: val_loss -0.2075 +2025-11-11 02:32:24.693777: Pseudo dice [np.float32(0.8091), np.float32(0.0), np.float32(0.0), np.float32(0.0), np.float32(0.728), np.float32(0.0102), np.float32(0.0), np.float32(0.0659), np.float32(0.811), np.float32(0.7846), np.float32(0.9143), np.float32(0.0876), np.float32(0.0), np.float32(0.7131), np.float32(0.8218), np.float32(0.0), np.float32(0.0)] +2025-11-11 02:32:24.695160: Epoch time: 258.3 s +2025-11-11 02:32:24.696634: Yayy! New best EMA pseudo Dice: 0.08299999684095383 +2025-11-11 02:32:29.964368: +2025-11-11 02:32:29.965863: Epoch 6 +2025-11-11 02:32:29.967240: Current learning rate: 0.00995 +2025-11-11 02:36:48.610176: train_loss -0.2158 +2025-11-11 02:36:48.615491: val_loss -0.2803 +2025-11-11 02:36:48.616785: Pseudo dice [np.float32(0.8387), np.float32(0.0), np.float32(0.0), np.float32(0.0), np.float32(0.7594), np.float32(0.2348), np.float32(0.0), np.float32(0.4861), np.float32(0.9), np.float32(0.9045), np.float32(0.9357), np.float32(0.3265), np.float32(0.0), np.float32(0.739), np.float32(0.8896), np.float32(0.0), np.float32(0.0)] +2025-11-11 02:36:48.618114: Epoch time: 258.65 s +2025-11-11 02:36:48.619411: Yayy! New best EMA pseudo Dice: 0.11599999666213989 +2025-11-11 02:36:53.715032: +2025-11-11 02:36:53.716864: Epoch 7 +2025-11-11 02:36:53.718444: Current learning rate: 0.00994 +2025-11-11 02:41:11.885706: train_loss -0.26 +2025-11-11 02:41:11.902484: val_loss -0.3048 +2025-11-11 02:41:11.903673: Pseudo dice [np.float32(0.8349), np.float32(0.0), np.float32(0.0), np.float32(0.0), np.float32(0.75), np.float32(0.388), np.float32(0.0), np.float32(0.6772), np.float32(0.9033), np.float32(0.8869), np.float32(0.9343), np.float32(0.3779), np.float32(0.0), np.float32(0.7476), np.float32(0.8877), np.float32(0.0), np.float32(0.0)] +2025-11-11 02:41:11.906842: Epoch time: 258.18 s +2025-11-11 02:41:11.909719: Yayy! New best EMA pseudo Dice: 0.1477999985218048 +2025-11-11 02:41:16.861890: +2025-11-11 02:41:16.863553: Epoch 8 +2025-11-11 02:41:16.865131: Current learning rate: 0.00993 +2025-11-11 02:45:35.489289: train_loss -0.2986 +2025-11-11 02:45:35.494329: val_loss -0.3421 +2025-11-11 02:45:35.496035: Pseudo dice [np.float32(0.8233), np.float32(0.0), np.float32(0.0), np.float32(0.0), np.float32(0.7505), np.float32(0.4697), np.float32(0.0), np.float32(0.7222), np.float32(0.9297), np.float32(0.9278), np.float32(0.9369), np.float32(0.5766), np.float32(0.0), np.float32(0.754), np.float32(0.8889), np.float32(0.0), np.float32(0.0)] +2025-11-11 02:45:35.497893: Epoch time: 258.63 s +2025-11-11 02:45:35.499489: Yayy! New best EMA pseudo Dice: 0.17880000174045563 +2025-11-11 02:45:40.717635: +2025-11-11 02:45:40.719391: Epoch 9 +2025-11-11 02:45:40.721069: Current learning rate: 0.00992 +2025-11-11 02:49:59.918945: train_loss -0.3272 +2025-11-11 02:49:59.923744: val_loss -0.3702 +2025-11-11 02:49:59.924977: Pseudo dice [np.float32(0.8531), np.float32(0.0), np.float32(0.0), np.float32(0.0), np.float32(0.7674), np.float32(0.5638), np.float32(0.5392), np.float32(0.715), np.float32(0.9139), np.float32(0.917), np.float32(0.9408), np.float32(0.6196), np.float32(0.0), np.float32(0.7822), np.float32(0.9005), np.float32(0.0), np.float32(0.0)] +2025-11-11 02:49:59.926204: Epoch time: 259.21 s +2025-11-11 02:49:59.927648: Yayy! New best EMA pseudo Dice: 0.210999995470047 +2025-11-11 02:50:05.145817: +2025-11-11 02:50:05.147126: Epoch 10 +2025-11-11 02:50:05.148528: Current learning rate: 0.00991 +2025-11-11 02:54:23.624119: train_loss -0.3571 +2025-11-11 02:54:23.630337: val_loss -0.3838 +2025-11-11 02:54:23.631925: Pseudo dice [np.float32(0.8599), np.float32(0.0), np.float32(0.0), np.float32(0.0), np.float32(0.7683), np.float32(0.5469), np.float32(0.6476), np.float32(0.7266), np.float32(0.9089), np.float32(0.901), np.float32(0.9418), np.float32(0.6406), np.float32(0.0), np.float32(0.7639), np.float32(0.8777), np.float32(0.0), np.float32(0.0)] +2025-11-11 02:54:23.633116: Epoch time: 258.48 s +2025-11-11 02:54:23.634315: Yayy! New best EMA pseudo Dice: 0.24040000140666962 +2025-11-11 02:54:28.575119: +2025-11-11 02:54:28.576672: Epoch 11 +2025-11-11 02:54:28.577792: Current learning rate: 0.0099 +2025-11-11 02:58:46.995399: train_loss -0.3767 +2025-11-11 02:58:47.000584: val_loss -0.4024 +2025-11-11 02:58:47.002065: Pseudo dice [np.float32(0.853), np.float32(0.0), np.float32(0.0), np.float32(0.0), np.float32(0.7744), np.float32(0.6065), np.float32(0.7036), np.float32(0.7517), np.float32(0.9182), np.float32(0.9239), np.float32(0.9453), np.float32(0.6383), np.float32(0.0), np.float32(0.7709), np.float32(0.8995), np.float32(0.0), np.float32(0.0)] +2025-11-11 02:58:47.003658: Epoch time: 258.43 s +2025-11-11 02:58:47.004959: Yayy! New best EMA pseudo Dice: 0.2680000066757202 +2025-11-11 02:58:52.253329: +2025-11-11 02:58:52.254771: Epoch 12 +2025-11-11 02:58:52.256095: Current learning rate: 0.00989 +2025-11-11 03:03:10.750983: train_loss -0.3831 +2025-11-11 03:03:10.758825: val_loss -0.4105 +2025-11-11 03:03:10.761209: Pseudo dice [np.float32(0.8692), np.float32(0.0), np.float32(0.0), np.float32(0.0), np.float32(0.7836), np.float32(0.5869), np.float32(0.6894), np.float32(0.7262), np.float32(0.925), np.float32(0.9119), np.float32(0.9438), np.float32(0.6823), np.float32(0.0), np.float32(0.782), np.float32(0.9065), np.float32(0.0), np.float32(0.0)] +2025-11-11 03:03:10.763421: Epoch time: 258.5 s +2025-11-11 03:03:10.764746: Yayy! New best EMA pseudo Dice: 0.2930000126361847 +2025-11-11 03:03:15.839660: +2025-11-11 03:03:15.841170: Epoch 13 +2025-11-11 03:03:15.842581: Current learning rate: 0.00988 +2025-11-11 03:07:34.367100: train_loss -0.4 +2025-11-11 03:07:34.370915: val_loss -0.4203 +2025-11-11 03:07:34.372175: Pseudo dice [np.float32(0.8751), np.float32(0.0), np.float32(0.0), np.float32(0.0), np.float32(0.7794), np.float32(0.6225), np.float32(0.7619), np.float32(0.7434), np.float32(0.9344), np.float32(0.9287), np.float32(0.9431), np.float32(0.6702), np.float32(0.0), np.float32(0.7907), np.float32(0.9019), np.float32(0.0), np.float32(0.0)] +2025-11-11 03:07:34.373304: Epoch time: 258.53 s +2025-11-11 03:07:34.374805: Yayy! New best EMA pseudo Dice: 0.3163999915122986 +2025-11-11 03:07:39.390779: +2025-11-11 03:07:39.393524: Epoch 14 +2025-11-11 03:07:39.395678: Current learning rate: 0.00987 +2025-11-11 03:11:57.913580: train_loss -0.4137 +2025-11-11 03:11:57.917254: val_loss -0.4356 +2025-11-11 03:11:57.918512: Pseudo dice [np.float32(0.8527), np.float32(0.0), np.float32(0.0), np.float32(0.0), np.float32(0.793), np.float32(0.6478), np.float32(0.7727), np.float32(0.7817), np.float32(0.9206), np.float32(0.9303), np.float32(0.9446), np.float32(0.7015), np.float32(0.0), np.float32(0.7998), np.float32(0.9105), np.float32(0.0), np.float32(0.0)] +2025-11-11 03:11:57.919736: Epoch time: 258.53 s +2025-11-11 03:11:57.920848: Yayy! New best EMA pseudo Dice: 0.33799999952316284 +2025-11-11 03:12:03.040392: +2025-11-11 03:12:03.041762: Epoch 15 +2025-11-11 03:12:03.043012: Current learning rate: 0.00986 +2025-11-11 03:16:21.592355: train_loss -0.4205 +2025-11-11 03:16:21.596682: val_loss -0.4404 +2025-11-11 03:16:21.598156: Pseudo dice [np.float32(0.8486), np.float32(0.0), np.float32(0.0), np.float32(0.0), np.float32(0.8033), np.float32(0.6465), np.float32(0.7922), np.float32(0.7626), np.float32(0.9129), np.float32(0.9097), np.float32(0.9507), np.float32(0.7221), np.float32(0.0), np.float32(0.8102), np.float32(0.9168), np.float32(0.0), np.float32(0.0)] +2025-11-11 03:16:21.599381: Epoch time: 258.56 s +2025-11-11 03:16:21.600680: Yayy! New best EMA pseudo Dice: 0.35760000348091125 +2025-11-11 03:16:26.618436: +2025-11-11 03:16:26.619865: Epoch 16 +2025-11-11 03:16:26.621200: Current learning rate: 0.00986 +2025-11-11 03:20:45.210918: train_loss -0.4268 +2025-11-11 03:20:45.214619: val_loss -0.4448 +2025-11-11 03:20:45.215733: Pseudo dice [np.float32(0.8665), np.float32(0.0), np.float32(0.0), np.float32(0.0), np.float32(0.7939), np.float32(0.6802), np.float32(0.7823), np.float32(0.7831), np.float32(0.9056), np.float32(0.9045), np.float32(0.9494), np.float32(0.7042), np.float32(0.0), np.float32(0.8023), np.float32(0.9057), np.float32(0.0), np.float32(0.0)] +2025-11-11 03:20:45.216846: Epoch time: 258.6 s +2025-11-11 03:20:45.217929: Yayy! New best EMA pseudo Dice: 0.3752000033855438 +2025-11-11 03:20:50.357314: +2025-11-11 03:20:50.358834: Epoch 17 +2025-11-11 03:20:50.360095: Current learning rate: 0.00985 +2025-11-11 03:25:09.034028: train_loss -0.4337 +2025-11-11 03:25:09.038027: val_loss -0.44 +2025-11-11 03:25:09.039251: Pseudo dice [np.float32(0.8741), np.float32(0.0), np.float32(0.0), np.float32(0.0), np.float32(0.8016), np.float32(0.6292), np.float32(0.7653), np.float32(0.7917), np.float32(0.9133), np.float32(0.914), np.float32(0.9436), np.float32(0.7004), np.float32(0.0), np.float32(0.8028), np.float32(0.8762), np.float32(0.0), np.float32(0.0)] +2025-11-11 03:25:09.040485: Epoch time: 258.68 s +2025-11-11 03:25:09.041680: Yayy! New best EMA pseudo Dice: 0.39070001244544983 +2025-11-11 03:25:15.218098: +2025-11-11 03:25:15.219483: Epoch 18 +2025-11-11 03:25:15.220885: Current learning rate: 0.00984 +2025-11-11 03:29:33.873866: train_loss -0.4379 +2025-11-11 03:29:33.880513: val_loss -0.4694 +2025-11-11 03:29:33.882266: Pseudo dice [np.float32(0.8578), np.float32(0.0), np.float32(0.0), np.float32(0.0), np.float32(0.8118), np.float32(0.6992), np.float32(0.7993), np.float32(0.7808), np.float32(0.9417), np.float32(0.9506), np.float32(0.9533), np.float32(0.7247), np.float32(0.0009), np.float32(0.8214), np.float32(0.931), np.float32(0.0), np.float32(0.0)] +2025-11-11 03:29:33.883945: Epoch time: 258.66 s +2025-11-11 03:29:33.885594: Yayy! New best EMA pseudo Dice: 0.40619999170303345 +2025-11-11 03:29:38.855703: +2025-11-11 03:29:38.857412: Epoch 19 +2025-11-11 03:29:38.859300: Current learning rate: 0.00983 +2025-11-11 03:33:57.470385: train_loss -0.4554 +2025-11-11 03:33:57.474607: val_loss -0.4831 +2025-11-11 03:33:57.475894: Pseudo dice [np.float32(0.8655), np.float32(0.0), np.float32(0.0), np.float32(0.0), np.float32(0.8113), np.float32(0.6595), np.float32(0.8304), np.float32(0.776), np.float32(0.9587), np.float32(0.9585), np.float32(0.9512), np.float32(0.7174), np.float32(0.4303), np.float32(0.8207), np.float32(0.9352), np.float32(0.0), np.float32(0.0)] +2025-11-11 03:33:57.477283: Epoch time: 258.62 s +2025-11-11 03:33:57.478854: Yayy! New best EMA pseudo Dice: 0.4226999878883362 +2025-11-11 03:34:02.527408: +2025-11-11 03:34:02.529079: Epoch 20 +2025-11-11 03:34:02.530613: Current learning rate: 0.00982 +2025-11-11 03:38:21.108052: train_loss -0.4641 +2025-11-11 03:38:21.112503: val_loss -0.4927 +2025-11-11 03:38:21.113964: Pseudo dice [np.float32(0.8648), np.float32(0.0), np.float32(0.0), np.float32(0.0), np.float32(0.8091), np.float32(0.6602), np.float32(0.8057), np.float32(0.7821), np.float32(0.9484), np.float32(0.9456), np.float32(0.9499), np.float32(0.7184), np.float32(0.5356), np.float32(0.8066), np.float32(0.9049), np.float32(0.0), np.float32(0.0)] +2025-11-11 03:38:21.115228: Epoch time: 258.59 s +2025-11-11 03:38:21.116548: Yayy! New best EMA pseudo Dice: 0.4377000033855438 +2025-11-11 03:38:26.301299: +2025-11-11 03:38:26.303534: Epoch 21 +2025-11-11 03:38:26.305811: Current learning rate: 0.00981 +2025-11-11 03:42:45.009681: train_loss -0.4811 +2025-11-11 03:42:45.016719: val_loss -0.5008 +2025-11-11 03:42:45.018598: Pseudo dice [np.float32(0.8816), np.float32(0.0), np.float32(0.0), np.float32(0.4429), np.float32(0.8097), np.float32(0.6657), np.float32(0.7671), np.float32(0.755), np.float32(0.9312), np.float32(0.9355), np.float32(0.952), np.float32(0.6887), np.float32(0.6004), np.float32(0.8179), np.float32(0.9161), np.float32(0.0), np.float32(0.0)] +2025-11-11 03:42:45.020966: Epoch time: 258.71 s +2025-11-11 03:42:45.022991: Yayy! New best EMA pseudo Dice: 0.4537000060081482 +2025-11-11 03:42:50.027803: +2025-11-11 03:42:50.029721: Epoch 22 +2025-11-11 03:42:50.031221: Current learning rate: 0.0098 +2025-11-11 03:47:08.690375: train_loss -0.4949 +2025-11-11 03:47:08.695651: val_loss -0.5069 +2025-11-11 03:47:08.697400: Pseudo dice [np.float32(0.8699), np.float32(0.0), np.float32(0.0), np.float32(0.4756), np.float32(0.8049), np.float32(0.6496), np.float32(0.7464), np.float32(0.799), np.float32(0.9676), np.float32(0.9534), np.float32(0.954), np.float32(0.7102), np.float32(0.5567), np.float32(0.8134), np.float32(0.94), np.float32(0.0), np.float32(0.0)] +2025-11-11 03:47:08.698500: Epoch time: 258.67 s +2025-11-11 03:47:08.699570: Yayy! New best EMA pseudo Dice: 0.46860000491142273 +2025-11-11 03:47:13.648280: +2025-11-11 03:47:13.650005: Epoch 23 +2025-11-11 03:47:13.651835: Current learning rate: 0.00979 +2025-11-11 03:51:32.447010: train_loss -0.4953 +2025-11-11 03:51:32.451383: val_loss -0.5139 +2025-11-11 03:51:32.452758: Pseudo dice [np.float32(0.8762), np.float32(0.0157), np.float32(0.0128), np.float32(0.4999), np.float32(0.8096), np.float32(0.6704), np.float32(0.7538), np.float32(0.7715), np.float32(0.9372), np.float32(0.9366), np.float32(0.9519), np.float32(0.7238), np.float32(0.6121), np.float32(0.818), np.float32(0.9207), np.float32(0.0), np.float32(0.0)] +2025-11-11 03:51:32.453911: Epoch time: 258.8 s +2025-11-11 03:51:32.454984: Yayy! New best EMA pseudo Dice: 0.48240000009536743 +2025-11-11 03:51:37.486339: +2025-11-11 03:51:37.488190: Epoch 24 +2025-11-11 03:51:37.489896: Current learning rate: 0.00978 +2025-11-11 03:55:56.173158: train_loss -0.5097 +2025-11-11 03:55:56.179919: val_loss -0.5618 +2025-11-11 03:55:56.181458: Pseudo dice [np.float32(0.8649), np.float32(0.5881), np.float32(0.5331), np.float32(0.509), np.float32(0.8168), np.float32(0.6825), np.float32(0.8139), np.float32(0.7877), np.float32(0.9554), np.float32(0.9545), np.float32(0.9552), np.float32(0.7189), np.float32(0.6171), np.float32(0.8256), np.float32(0.9348), np.float32(0.0), np.float32(0.0)] +2025-11-11 03:55:56.182856: Epoch time: 258.69 s +2025-11-11 03:55:56.183997: Yayy! New best EMA pseudo Dice: 0.5020999908447266 +2025-11-11 03:56:01.213567: +2025-11-11 03:56:01.215059: Epoch 25 +2025-11-11 03:56:01.216442: Current learning rate: 0.00977 +2025-11-11 04:00:20.072616: train_loss -0.543 +2025-11-11 04:00:20.076857: val_loss -0.5662 +2025-11-11 04:00:20.078583: Pseudo dice [np.float32(0.8778), np.float32(0.5385), np.float32(0.5291), np.float32(0.4894), np.float32(0.8102), np.float32(0.6907), np.float32(0.8007), np.float32(0.79), np.float32(0.9465), np.float32(0.9439), np.float32(0.9539), np.float32(0.7248), np.float32(0.6095), np.float32(0.8235), np.float32(0.9245), np.float32(0.0016), np.float32(0.0)] +2025-11-11 04:00:20.081000: Epoch time: 258.86 s +2025-11-11 04:00:20.082561: Yayy! New best EMA pseudo Dice: 0.5192999839782715 +2025-11-11 04:00:25.120479: +2025-11-11 04:00:25.122039: Epoch 26 +2025-11-11 04:00:25.123245: Current learning rate: 0.00977 +2025-11-11 04:04:44.985969: train_loss -0.5535 +2025-11-11 04:04:44.989472: val_loss -0.5706 +2025-11-11 04:04:44.990669: Pseudo dice [np.float32(0.8712), np.float32(0.58), np.float32(0.595), np.float32(0.4656), np.float32(0.8154), np.float32(0.6958), np.float32(0.7776), np.float32(0.7864), np.float32(0.9386), np.float32(0.9289), np.float32(0.9497), np.float32(0.7563), np.float32(0.5577), np.float32(0.8159), np.float32(0.9119), np.float32(0.0317), np.float32(0.0)] +2025-11-11 04:04:44.991751: Epoch time: 259.87 s +2025-11-11 04:04:44.992710: Yayy! New best EMA pseudo Dice: 0.5349000096321106 +2025-11-11 04:04:49.960299: +2025-11-11 04:04:49.962046: Epoch 27 +2025-11-11 04:04:49.963892: Current learning rate: 0.00976 +2025-11-11 04:09:08.696124: train_loss -0.5673 +2025-11-11 04:09:08.701908: val_loss -0.5954 +2025-11-11 04:09:08.704298: Pseudo dice [np.float32(0.8925), np.float32(0.608), np.float32(0.6335), np.float32(0.501), np.float32(0.8125), np.float32(0.6713), np.float32(0.8365), np.float32(0.8063), np.float32(0.9523), np.float32(0.9571), np.float32(0.9576), np.float32(0.7188), np.float32(0.5913), np.float32(0.8262), np.float32(0.9413), np.float32(0.231), np.float32(0.0)] +2025-11-11 04:09:08.706729: Epoch time: 258.74 s +2025-11-11 04:09:08.708793: Yayy! New best EMA pseudo Dice: 0.5515999794006348 +2025-11-11 04:09:13.690005: +2025-11-11 04:09:13.691960: Epoch 28 +2025-11-11 04:09:13.693644: Current learning rate: 0.00975 +2025-11-11 04:13:32.417439: train_loss -0.5723 +2025-11-11 04:13:32.424925: val_loss -0.5941 +2025-11-11 04:13:32.426429: Pseudo dice [np.float32(0.8906), np.float32(0.6169), np.float32(0.5939), np.float32(0.5168), np.float32(0.824), np.float32(0.7039), np.float32(0.8008), np.float32(0.7901), np.float32(0.9433), np.float32(0.9515), np.float32(0.9532), np.float32(0.7501), np.float32(0.6246), np.float32(0.8122), np.float32(0.9212), np.float32(0.296), np.float32(0.0)] +2025-11-11 04:13:32.428119: Epoch time: 258.73 s +2025-11-11 04:13:32.429708: Yayy! New best EMA pseudo Dice: 0.5669999718666077 +2025-11-11 04:13:37.564957: +2025-11-11 04:13:37.567144: Epoch 29 +2025-11-11 04:13:37.568758: Current learning rate: 0.00974 +2025-11-11 04:17:56.397086: train_loss -0.5698 +2025-11-11 04:17:56.402824: val_loss -0.5753 +2025-11-11 04:17:56.405162: Pseudo dice [np.float32(0.8768), np.float32(0.4878), np.float32(0.5288), np.float32(0.5174), np.float32(0.8211), np.float32(0.6742), np.float32(0.7886), np.float32(0.7962), np.float32(0.913), np.float32(0.9151), np.float32(0.9506), np.float32(0.7252), np.float32(0.63), np.float32(0.8251), np.float32(0.8957), np.float32(0.3132), np.float32(0.0)] +2025-11-11 04:17:56.407657: Epoch time: 258.84 s +2025-11-11 04:17:56.409971: Yayy! New best EMA pseudo Dice: 0.5788999795913696 +2025-11-11 04:18:01.534715: +2025-11-11 04:18:01.536270: Epoch 30 +2025-11-11 04:18:01.537614: Current learning rate: 0.00973 +2025-11-11 04:22:20.421314: train_loss -0.5807 +2025-11-11 04:22:20.426062: val_loss -0.593 +2025-11-11 04:22:20.427780: Pseudo dice [np.float32(0.8806), np.float32(0.652), np.float32(0.5305), np.float32(0.5111), np.float32(0.8159), np.float32(0.7004), np.float32(0.7425), np.float32(0.7985), np.float32(0.9435), np.float32(0.9337), np.float32(0.9575), np.float32(0.7252), np.float32(0.6282), np.float32(0.8279), np.float32(0.9342), np.float32(0.3012), np.float32(0.0)] +2025-11-11 04:22:20.429099: Epoch time: 258.89 s +2025-11-11 04:22:20.430440: Yayy! New best EMA pseudo Dice: 0.5909000039100647 +2025-11-11 04:22:25.496396: +2025-11-11 04:22:25.497832: Epoch 31 +2025-11-11 04:22:25.499251: Current learning rate: 0.00972 +2025-11-11 04:26:44.297907: train_loss -0.5801 +2025-11-11 04:26:44.303325: val_loss -0.5929 +2025-11-11 04:26:44.304704: Pseudo dice [np.float32(0.8965), np.float32(0.674), np.float32(0.6038), np.float32(0.5489), np.float32(0.8113), np.float32(0.6936), np.float32(0.8183), np.float32(0.8064), np.float32(0.8952), np.float32(0.8992), np.float32(0.949), np.float32(0.7526), np.float32(0.6809), np.float32(0.8169), np.float32(0.8876), np.float32(0.2793), np.float32(0.0)] +2025-11-11 04:26:44.306157: Epoch time: 258.81 s +2025-11-11 04:26:44.307628: Yayy! New best EMA pseudo Dice: 0.602400004863739 +2025-11-11 04:26:49.413344: +2025-11-11 04:26:49.415643: Epoch 32 +2025-11-11 04:26:49.417728: Current learning rate: 0.00971 +2025-11-11 04:31:08.345242: train_loss -0.588 +2025-11-11 04:31:08.349442: val_loss -0.6206 +2025-11-11 04:31:08.350828: Pseudo dice [np.float32(0.8891), np.float32(0.6841), np.float32(0.6285), np.float32(0.541), np.float32(0.8207), np.float32(0.74), np.float32(0.8294), np.float32(0.8076), np.float32(0.948), np.float32(0.9437), np.float32(0.9555), np.float32(0.7391), np.float32(0.6718), np.float32(0.8285), np.float32(0.9343), np.float32(0.271), np.float32(0.0)] +2025-11-11 04:31:08.352222: Epoch time: 258.94 s +2025-11-11 04:31:08.353661: Yayy! New best EMA pseudo Dice: 0.6141999959945679 +2025-11-11 04:31:13.423910: +2025-11-11 04:31:13.425593: Epoch 33 +2025-11-11 04:31:13.427100: Current learning rate: 0.0097 +2025-11-11 04:35:32.250905: train_loss -0.5982 +2025-11-11 04:35:32.256970: val_loss -0.6084 +2025-11-11 04:35:32.258264: Pseudo dice [np.float32(0.8914), np.float32(0.587), np.float32(0.6139), np.float32(0.5239), np.float32(0.821), np.float32(0.7129), np.float32(0.7813), np.float32(0.7939), np.float32(0.946), np.float32(0.9502), np.float32(0.9541), np.float32(0.7559), np.float32(0.6559), np.float32(0.8322), np.float32(0.9319), np.float32(0.3018), np.float32(0.0)] +2025-11-11 04:35:32.260343: Epoch time: 258.83 s +2025-11-11 04:35:32.262374: Yayy! New best EMA pseudo Dice: 0.6236000061035156 +2025-11-11 04:35:37.304903: +2025-11-11 04:35:37.306987: Epoch 34 +2025-11-11 04:35:37.308995: Current learning rate: 0.00969 +2025-11-11 04:39:56.881190: train_loss -0.5937 +2025-11-11 04:39:56.887768: val_loss -0.6133 +2025-11-11 04:39:56.890540: Pseudo dice [np.float32(0.8864), np.float32(0.6749), np.float32(0.6099), np.float32(0.5208), np.float32(0.8217), np.float32(0.7024), np.float32(0.7912), np.float32(0.8104), np.float32(0.9642), np.float32(0.9599), np.float32(0.9574), np.float32(0.7574), np.float32(0.6288), np.float32(0.8294), np.float32(0.9443), np.float32(0.3332), np.float32(0.0)] +2025-11-11 04:39:56.893126: Epoch time: 259.58 s +2025-11-11 04:39:56.894882: Yayy! New best EMA pseudo Dice: 0.6330000162124634 +2025-11-11 04:40:01.978770: +2025-11-11 04:40:01.980804: Epoch 35 +2025-11-11 04:40:01.982197: Current learning rate: 0.00968 +2025-11-11 04:44:20.466162: train_loss -0.5949 +2025-11-11 04:44:20.474160: val_loss -0.6231 +2025-11-11 04:44:20.476009: Pseudo dice [np.float32(0.8896), np.float32(0.6715), np.float32(0.6153), np.float32(0.5618), np.float32(0.8267), np.float32(0.7078), np.float32(0.8349), np.float32(0.8039), np.float32(0.9596), np.float32(0.9554), np.float32(0.9576), np.float32(0.7516), np.float32(0.6779), np.float32(0.8269), np.float32(0.9457), np.float32(0.3614), np.float32(0.1033)] +2025-11-11 04:44:20.477668: Epoch time: 258.49 s +2025-11-11 04:44:20.480072: Yayy! New best EMA pseudo Dice: 0.6428999900817871 +2025-11-11 04:44:25.536218: +2025-11-11 04:44:25.537690: Epoch 36 +2025-11-11 04:44:25.538943: Current learning rate: 0.00968 +2025-11-11 04:48:44.249933: train_loss -0.5971 +2025-11-11 04:48:44.256965: val_loss -0.6116 +2025-11-11 04:48:44.259175: Pseudo dice [np.float32(0.8892), np.float32(0.57), np.float32(0.5038), np.float32(0.5393), np.float32(0.8203), np.float32(0.7187), np.float32(0.8111), np.float32(0.8091), np.float32(0.938), np.float32(0.9407), np.float32(0.9557), np.float32(0.7618), np.float32(0.6633), np.float32(0.8348), np.float32(0.9241), np.float32(0.2855), np.float32(0.2325)] +2025-11-11 04:48:44.261074: Epoch time: 258.72 s +2025-11-11 04:48:44.263035: Yayy! New best EMA pseudo Dice: 0.6503999829292297 +2025-11-11 04:48:49.435618: +2025-11-11 04:48:49.437140: Epoch 37 +2025-11-11 04:48:49.438503: Current learning rate: 0.00967 +2025-11-11 04:53:08.379061: train_loss -0.6045 +2025-11-11 04:53:08.384098: val_loss -0.6343 +2025-11-11 04:53:08.385819: Pseudo dice [np.float32(0.8977), np.float32(0.6631), np.float32(0.6586), np.float32(0.5467), np.float32(0.8253), np.float32(0.7287), np.float32(0.8574), np.float32(0.8056), np.float32(0.955), np.float32(0.9518), np.float32(0.959), np.float32(0.7759), np.float32(0.6688), np.float32(0.8351), np.float32(0.9323), np.float32(0.2998), np.float32(0.2374)] +2025-11-11 04:53:08.387255: Epoch time: 258.95 s +2025-11-11 04:53:08.388555: Yayy! New best EMA pseudo Dice: 0.659500002861023 +2025-11-11 04:53:13.469512: +2025-11-11 04:53:13.471015: Epoch 38 +2025-11-11 04:53:13.472378: Current learning rate: 0.00966 +2025-11-11 04:57:32.135716: train_loss -0.6104 +2025-11-11 04:57:32.139541: val_loss -0.6312 +2025-11-11 04:57:32.140843: Pseudo dice [np.float32(0.8954), np.float32(0.6963), np.float32(0.6585), np.float32(0.5449), np.float32(0.8322), np.float32(0.7276), np.float32(0.8163), np.float32(0.8201), np.float32(0.9571), np.float32(0.9559), np.float32(0.9594), np.float32(0.7564), np.float32(0.678), np.float32(0.8353), np.float32(0.9381), np.float32(0.3001), np.float32(0.1663)] +2025-11-11 04:57:32.141975: Epoch time: 258.67 s +2025-11-11 04:57:32.143050: Yayy! New best EMA pseudo Dice: 0.6672999858856201 +2025-11-11 04:57:37.167074: +2025-11-11 04:57:37.168602: Epoch 39 +2025-11-11 04:57:37.170237: Current learning rate: 0.00965 +2025-11-11 05:01:55.742689: train_loss -0.6142 +2025-11-11 05:01:55.747581: val_loss -0.645 +2025-11-11 05:01:55.749392: Pseudo dice [np.float32(0.8949), np.float32(0.6915), np.float32(0.6353), np.float32(0.5523), np.float32(0.8296), np.float32(0.7287), np.float32(0.8573), np.float32(0.8361), np.float32(0.9612), np.float32(0.9536), np.float32(0.9585), np.float32(0.7725), np.float32(0.6918), np.float32(0.8381), np.float32(0.9481), np.float32(0.3635), np.float32(0.3126)] +2025-11-11 05:01:55.751073: Epoch time: 258.58 s +2025-11-11 05:01:55.752300: Yayy! New best EMA pseudo Dice: 0.6759999990463257 +2025-11-11 05:02:00.851067: +2025-11-11 05:02:00.852544: Epoch 40 +2025-11-11 05:02:00.854255: Current learning rate: 0.00964 +2025-11-11 05:06:19.575550: train_loss -0.6067 +2025-11-11 05:06:19.580929: val_loss -0.6333 +2025-11-11 05:06:19.583060: Pseudo dice [np.float32(0.8766), np.float32(0.6868), np.float32(0.6581), np.float32(0.5479), np.float32(0.8204), np.float32(0.714), np.float32(0.8162), np.float32(0.8112), np.float32(0.9473), np.float32(0.9517), np.float32(0.9597), np.float32(0.7452), np.float32(0.6679), np.float32(0.8329), np.float32(0.928), np.float32(0.3068), np.float32(0.3081)] +2025-11-11 05:06:19.585256: Epoch time: 258.73 s +2025-11-11 05:06:19.587424: Yayy! New best EMA pseudo Dice: 0.6823999881744385 +2025-11-11 05:06:24.772927: +2025-11-11 05:06:24.774587: Epoch 41 +2025-11-11 05:06:24.776199: Current learning rate: 0.00963 +2025-11-11 05:10:43.494553: train_loss -0.6161 +2025-11-11 05:10:43.499926: val_loss -0.6345 +2025-11-11 05:10:43.501121: Pseudo dice [np.float32(0.8771), np.float32(0.6933), np.float32(0.6042), np.float32(0.5509), np.float32(0.8252), np.float32(0.7299), np.float32(0.7996), np.float32(0.806), np.float32(0.9472), np.float32(0.9493), np.float32(0.9592), np.float32(0.7635), np.float32(0.7104), np.float32(0.8377), np.float32(0.9319), np.float32(0.327), np.float32(0.2496)] +2025-11-11 05:10:43.503079: Epoch time: 258.73 s +2025-11-11 05:10:43.504211: Yayy! New best EMA pseudo Dice: 0.6880000233650208 +2025-11-11 05:10:48.614005: +2025-11-11 05:10:48.615615: Epoch 42 +2025-11-11 05:10:48.616873: Current learning rate: 0.00962 +2025-11-11 05:15:09.273551: train_loss -0.6247 +2025-11-11 05:15:09.278300: val_loss -0.6432 +2025-11-11 05:15:09.280563: Pseudo dice [np.float32(0.884), np.float32(0.7293), np.float32(0.6496), np.float32(0.5205), np.float32(0.8339), np.float32(0.7271), np.float32(0.8216), np.float32(0.8403), np.float32(0.9451), np.float32(0.9466), np.float32(0.9594), np.float32(0.7604), np.float32(0.6812), np.float32(0.8455), np.float32(0.9402), np.float32(0.3309), np.float32(0.2854)] +2025-11-11 05:15:09.283164: Epoch time: 260.66 s +2025-11-11 05:15:09.285117: Yayy! New best EMA pseudo Dice: 0.6938999891281128 +2025-11-11 05:15:14.276866: +2025-11-11 05:15:14.278474: Epoch 43 +2025-11-11 05:15:14.279757: Current learning rate: 0.00961 +2025-11-11 05:19:32.917983: train_loss -0.6258 +2025-11-11 05:19:32.924500: val_loss -0.643 +2025-11-11 05:19:32.926452: Pseudo dice [np.float32(0.8992), np.float32(0.7159), np.float32(0.6567), np.float32(0.5336), np.float32(0.8287), np.float32(0.7153), np.float32(0.834), np.float32(0.8307), np.float32(0.9599), np.float32(0.9547), np.float32(0.9561), np.float32(0.7641), np.float32(0.6899), np.float32(0.8428), np.float32(0.9384), np.float32(0.3065), np.float32(0.2802)] +2025-11-11 05:19:32.928210: Epoch time: 258.65 s +2025-11-11 05:19:32.929539: Yayy! New best EMA pseudo Dice: 0.6992999911308289 +2025-11-11 05:19:37.941598: +2025-11-11 05:19:37.943706: Epoch 44 +2025-11-11 05:19:37.945127: Current learning rate: 0.0096 +2025-11-11 05:23:56.794382: train_loss -0.6261 +2025-11-11 05:23:56.799953: val_loss -0.6471 +2025-11-11 05:23:56.801471: Pseudo dice [np.float32(0.9026), np.float32(0.6688), np.float32(0.658), np.float32(0.568), np.float32(0.8232), np.float32(0.7143), np.float32(0.8513), np.float32(0.8278), np.float32(0.9617), np.float32(0.9601), np.float32(0.9602), np.float32(0.7761), np.float32(0.658), np.float32(0.8378), np.float32(0.9449), np.float32(0.3519), np.float32(0.323)] +2025-11-11 05:23:56.802781: Epoch time: 258.86 s +2025-11-11 05:23:56.804256: Yayy! New best EMA pseudo Dice: 0.7045999765396118 +2025-11-11 05:24:01.709565: +2025-11-11 05:24:01.711617: Epoch 45 +2025-11-11 05:24:01.713461: Current learning rate: 0.00959 +2025-11-11 05:28:20.487941: train_loss -0.6204 +2025-11-11 05:28:20.492386: val_loss -0.6296 +2025-11-11 05:28:20.493900: Pseudo dice [np.float32(0.8931), np.float32(0.6645), np.float32(0.673), np.float32(0.5345), np.float32(0.8251), np.float32(0.729), np.float32(0.8119), np.float32(0.8125), np.float32(0.9413), np.float32(0.9366), np.float32(0.9555), np.float32(0.7546), np.float32(0.6447), np.float32(0.8368), np.float32(0.9339), np.float32(0.3139), np.float32(0.2803)] +2025-11-11 05:28:20.495325: Epoch time: 258.79 s +2025-11-11 05:28:20.496964: Yayy! New best EMA pseudo Dice: 0.7078999876976013 +2025-11-11 05:28:25.498223: +2025-11-11 05:28:25.500066: Epoch 46 +2025-11-11 05:28:25.502098: Current learning rate: 0.00959 +2025-11-11 05:32:44.299196: train_loss -0.628 +2025-11-11 05:32:44.308530: val_loss -0.6366 +2025-11-11 05:32:44.312222: Pseudo dice [np.float32(0.8778), np.float32(0.7174), np.float32(0.6406), np.float32(0.5684), np.float32(0.8227), np.float32(0.7125), np.float32(0.8078), np.float32(0.8127), np.float32(0.9579), np.float32(0.9525), np.float32(0.9582), np.float32(0.7727), np.float32(0.7065), np.float32(0.839), np.float32(0.9404), np.float32(0.3375), np.float32(0.3014)] +2025-11-11 05:32:44.314686: Epoch time: 258.81 s +2025-11-11 05:32:44.316985: Yayy! New best EMA pseudo Dice: 0.7120000123977661 +2025-11-11 05:32:49.244017: +2025-11-11 05:32:49.245729: Epoch 47 +2025-11-11 05:32:49.247059: Current learning rate: 0.00958 +2025-11-11 05:37:08.330292: train_loss -0.6182 +2025-11-11 05:37:08.334413: val_loss -0.6389 +2025-11-11 05:37:08.336564: Pseudo dice [np.float32(0.8927), np.float32(0.6951), np.float32(0.6444), np.float32(0.5702), np.float32(0.8262), np.float32(0.711), np.float32(0.8428), np.float32(0.8214), np.float32(0.9431), np.float32(0.9562), np.float32(0.9609), np.float32(0.768), np.float32(0.6865), np.float32(0.8314), np.float32(0.9326), np.float32(0.3141), np.float32(0.2976)] +2025-11-11 05:37:08.339441: Epoch time: 259.09 s +2025-11-11 05:37:08.341074: Yayy! New best EMA pseudo Dice: 0.715399980545044 +2025-11-11 05:37:14.002666: +2025-11-11 05:37:14.004709: Epoch 48 +2025-11-11 05:37:14.008282: Current learning rate: 0.00957 +2025-11-11 05:41:32.701213: train_loss -0.6295 +2025-11-11 05:41:32.706174: val_loss -0.6493 +2025-11-11 05:41:32.707885: Pseudo dice [np.float32(0.8885), np.float32(0.6844), np.float32(0.6411), np.float32(0.6101), np.float32(0.838), np.float32(0.7452), np.float32(0.8453), np.float32(0.8134), np.float32(0.9576), np.float32(0.9547), np.float32(0.956), np.float32(0.7507), np.float32(0.7107), np.float32(0.8438), np.float32(0.9484), np.float32(0.2966), np.float32(0.3127)] +2025-11-11 05:41:32.709484: Epoch time: 258.7 s +2025-11-11 05:41:32.711194: Yayy! New best EMA pseudo Dice: 0.7192000150680542 +2025-11-11 05:41:37.717137: +2025-11-11 05:41:37.719033: Epoch 49 +2025-11-11 05:41:37.720701: Current learning rate: 0.00956 +2025-11-11 05:45:56.479009: train_loss -0.6224 +2025-11-11 05:45:56.485651: val_loss -0.6581 +2025-11-11 05:45:56.487985: Pseudo dice [np.float32(0.8963), np.float32(0.7237), np.float32(0.6588), np.float32(0.5651), np.float32(0.8338), np.float32(0.7301), np.float32(0.8313), np.float32(0.8267), np.float32(0.9564), np.float32(0.9579), np.float32(0.9609), np.float32(0.7681), np.float32(0.71), np.float32(0.8437), np.float32(0.9485), np.float32(0.3206), np.float32(0.3564)] +2025-11-11 05:45:56.490408: Epoch time: 258.77 s +2025-11-11 05:45:59.315838: Yayy! New best EMA pseudo Dice: 0.7231000065803528 +2025-11-11 05:46:04.397987: +2025-11-11 05:46:04.399518: Epoch 50 +2025-11-11 05:46:04.400983: Current learning rate: 0.00955 +2025-11-11 05:50:23.861881: train_loss -0.632 +2025-11-11 05:50:23.868373: val_loss -0.657 +2025-11-11 05:50:23.869979: Pseudo dice [np.float32(0.8934), np.float32(0.6817), np.float32(0.682), np.float32(0.6046), np.float32(0.8286), np.float32(0.7009), np.float32(0.8277), np.float32(0.8242), np.float32(0.9532), np.float32(0.955), np.float32(0.9622), np.float32(0.7725), np.float32(0.7), np.float32(0.8444), np.float32(0.9473), np.float32(0.3247), np.float32(0.3101)] +2025-11-11 05:50:23.871542: Epoch time: 259.47 s +2025-11-11 05:50:23.873073: Yayy! New best EMA pseudo Dice: 0.7261000275611877 +2025-11-11 05:50:29.954049: +2025-11-11 05:50:29.959173: Epoch 51 +2025-11-11 05:50:29.964144: Current learning rate: 0.00954 +2025-11-11 05:54:51.231057: train_loss -0.6353 +2025-11-11 05:54:51.361629: val_loss -0.6606 +2025-11-11 05:54:51.369772: Pseudo dice [np.float32(0.8971), np.float32(0.709), np.float32(0.669), np.float32(0.5986), np.float32(0.8244), np.float32(0.7454), np.float32(0.8481), np.float32(0.8172), np.float32(0.9575), np.float32(0.9655), np.float32(0.9604), np.float32(0.7723), np.float32(0.7094), np.float32(0.8343), np.float32(0.9389), np.float32(0.3739), np.float32(0.3717)] +2025-11-11 05:54:51.421730: Epoch time: 261.28 s +2025-11-11 05:54:51.427519: Yayy! New best EMA pseudo Dice: 0.7299000024795532 +2025-11-11 05:54:58.216161: +2025-11-11 05:54:58.223686: Epoch 52 +2025-11-11 05:54:58.231240: Current learning rate: 0.00953 +2025-11-11 05:59:17.303694: train_loss -0.6204 +2025-11-11 05:59:17.312777: val_loss -0.6404 +2025-11-11 05:59:17.314517: Pseudo dice [np.float32(0.8912), np.float32(0.6755), np.float32(0.6115), np.float32(0.5712), np.float32(0.8227), np.float32(0.7179), np.float32(0.8317), np.float32(0.8217), np.float32(0.9534), np.float32(0.9503), np.float32(0.9597), np.float32(0.7645), np.float32(0.6735), np.float32(0.8245), np.float32(0.9362), np.float32(0.4119), np.float32(0.3456)] +2025-11-11 05:59:17.317461: Epoch time: 259.09 s +2025-11-11 05:59:17.320899: Yayy! New best EMA pseudo Dice: 0.7319999933242798 +2025-11-11 05:59:23.381430: +2025-11-11 05:59:23.383734: Epoch 53 +2025-11-11 05:59:23.385953: Current learning rate: 0.00952 +2025-11-11 06:03:42.408204: train_loss -0.6237 +2025-11-11 06:03:42.549014: val_loss -0.657 +2025-11-11 06:03:42.550964: Pseudo dice [np.float32(0.8984), np.float32(0.6445), np.float32(0.6829), np.float32(0.5666), np.float32(0.8196), np.float32(0.7465), np.float32(0.8396), np.float32(0.8392), np.float32(0.9576), np.float32(0.9611), np.float32(0.9595), np.float32(0.7751), np.float32(0.7176), np.float32(0.8239), np.float32(0.945), np.float32(0.3581), np.float32(0.2393)] +2025-11-11 06:03:42.592298: Epoch time: 259.03 s +2025-11-11 06:03:42.594251: Yayy! New best EMA pseudo Dice: 0.734000027179718 +2025-11-11 06:03:48.544616: +2025-11-11 06:03:48.547382: Epoch 54 +2025-11-11 06:03:48.550418: Current learning rate: 0.00951 +2025-11-11 06:08:09.015130: train_loss -0.6344 +2025-11-11 06:08:09.739105: val_loss -0.663 +2025-11-11 06:08:09.742646: Pseudo dice [np.float32(0.8964), np.float32(0.7171), np.float32(0.6735), np.float32(0.6), np.float32(0.8397), np.float32(0.7455), np.float32(0.8758), np.float32(0.8171), np.float32(0.9568), np.float32(0.9563), np.float32(0.9608), np.float32(0.776), np.float32(0.6945), np.float32(0.8487), np.float32(0.9338), np.float32(0.3703), np.float32(0.3489)] +2025-11-11 06:08:09.821522: Epoch time: 260.09 s +2025-11-11 06:08:09.911578: Yayy! New best EMA pseudo Dice: 0.7371000051498413 +2025-11-11 06:08:20.165693: +2025-11-11 06:08:20.171074: Epoch 55 +2025-11-11 06:08:20.176160: Current learning rate: 0.0095 +2025-11-11 06:12:39.310330: train_loss -0.6342 +2025-11-11 06:12:39.431185: val_loss -0.6569 +2025-11-11 06:12:39.438245: Pseudo dice [np.float32(0.9008), np.float32(0.6505), np.float32(0.6599), np.float32(0.5734), np.float32(0.8279), np.float32(0.7102), np.float32(0.7836), np.float32(0.8203), np.float32(0.9581), np.float32(0.9517), np.float32(0.9577), np.float32(0.7478), np.float32(0.7043), np.float32(0.835), np.float32(0.9406), np.float32(0.4237), np.float32(0.3075)] +2025-11-11 06:12:39.488462: Epoch time: 259.15 s +2025-11-11 06:12:39.491784: Yayy! New best EMA pseudo Dice: 0.7383999824523926 +2025-11-11 06:12:46.535549: +2025-11-11 06:12:46.538291: Epoch 56 +2025-11-11 06:12:46.540191: Current learning rate: 0.00949 +2025-11-11 06:17:05.712260: train_loss -0.6338 +2025-11-11 06:17:05.864098: val_loss -0.6479 +2025-11-11 06:17:05.869141: Pseudo dice [np.float32(0.895), np.float32(0.6349), np.float32(0.6506), np.float32(0.5998), np.float32(0.8308), np.float32(0.7384), np.float32(0.8269), np.float32(0.7898), np.float32(0.9563), np.float32(0.9697), np.float32(0.9606), np.float32(0.764), np.float32(0.7083), np.float32(0.8339), np.float32(0.9474), np.float32(0.3098), np.float32(0.2687)] +2025-11-11 06:17:05.915390: Epoch time: 259.18 s +2025-11-11 06:17:05.926224: Yayy! New best EMA pseudo Dice: 0.7391999959945679 +2025-11-11 06:17:11.893557: +2025-11-11 06:17:11.896939: Epoch 57 +2025-11-11 06:17:11.898475: Current learning rate: 0.00949 +2025-11-11 06:21:30.930646: train_loss -0.6351 +2025-11-11 06:21:31.065487: val_loss -0.6449 +2025-11-11 06:21:31.070643: Pseudo dice [np.float32(0.8968), np.float32(0.7183), np.float32(0.658), np.float32(0.5439), np.float32(0.8378), np.float32(0.7427), np.float32(0.8185), np.float32(0.816), np.float32(0.9336), np.float32(0.9259), np.float32(0.9587), np.float32(0.7755), np.float32(0.7134), np.float32(0.8383), np.float32(0.9178), np.float32(0.3892), np.float32(0.2579)] +2025-11-11 06:21:31.241132: Epoch time: 259.04 s +2025-11-11 06:21:31.244628: Yayy! New best EMA pseudo Dice: 0.7401999831199646 +2025-11-11 06:21:37.510694: +2025-11-11 06:21:37.513044: Epoch 58 +2025-11-11 06:21:37.516097: Current learning rate: 0.00948 +2025-11-11 06:25:56.459143: train_loss -0.6255 +2025-11-11 06:25:56.614316: val_loss -0.6532 +2025-11-11 06:25:56.619848: Pseudo dice [np.float32(0.8986), np.float32(0.683), np.float32(0.6632), np.float32(0.5826), np.float32(0.8278), np.float32(0.7334), np.float32(0.8262), np.float32(0.8312), np.float32(0.9495), np.float32(0.954), np.float32(0.9595), np.float32(0.7705), np.float32(0.6817), np.float32(0.8334), np.float32(0.9446), np.float32(0.3724), np.float32(0.3743)] +2025-11-11 06:25:56.714806: Epoch time: 258.95 s +2025-11-11 06:25:56.719428: Yayy! New best EMA pseudo Dice: 0.7419999837875366 +2025-11-11 06:26:03.493620: +2025-11-11 06:26:03.496960: Epoch 59 +2025-11-11 06:26:03.499644: Current learning rate: 0.00947 +2025-11-11 06:30:38.072734: train_loss -0.6348 +2025-11-11 06:30:38.101113: val_loss -0.6584 +2025-11-11 06:30:38.109593: Pseudo dice [np.float32(0.8868), np.float32(0.7365), np.float32(0.6827), np.float32(0.5862), np.float32(0.8351), np.float32(0.7226), np.float32(0.8492), np.float32(0.8359), np.float32(0.9578), np.float32(0.9631), np.float32(0.9614), np.float32(0.7721), np.float32(0.7167), np.float32(0.8419), np.float32(0.9399), np.float32(0.3093), np.float32(0.2628)] +2025-11-11 06:30:38.116121: Epoch time: 274.58 s +2025-11-11 06:30:38.122017: Yayy! New best EMA pseudo Dice: 0.743399977684021 +2025-11-11 06:30:43.905119: +2025-11-11 06:30:43.910094: Epoch 60 +2025-11-11 06:30:43.916210: Current learning rate: 0.00946 +2025-11-11 06:35:03.576709: train_loss -0.6395 +2025-11-11 06:35:03.672471: val_loss -0.6618 +2025-11-11 06:35:03.681581: Pseudo dice [np.float32(0.8883), np.float32(0.6991), np.float32(0.6791), np.float32(0.5752), np.float32(0.8311), np.float32(0.7524), np.float32(0.8522), np.float32(0.8236), np.float32(0.967), np.float32(0.9632), np.float32(0.9632), np.float32(0.7976), np.float32(0.6804), np.float32(0.8347), np.float32(0.9501), np.float32(0.3709), np.float32(0.3486)] +2025-11-11 06:35:03.892945: Epoch time: 259.68 s +2025-11-11 06:35:03.899833: Yayy! New best EMA pseudo Dice: 0.7454000115394592 +2025-11-11 06:35:10.262227: +2025-11-11 06:35:10.265920: Epoch 61 +2025-11-11 06:35:10.269488: Current learning rate: 0.00945 +2025-11-11 06:39:29.021975: train_loss -0.6455 +2025-11-11 06:39:29.042141: val_loss -0.6755 +2025-11-11 06:39:29.044879: Pseudo dice [np.float32(0.8971), np.float32(0.7124), np.float32(0.6574), np.float32(0.6197), np.float32(0.8387), np.float32(0.7411), np.float32(0.8363), np.float32(0.8366), np.float32(0.9663), np.float32(0.9631), np.float32(0.9623), np.float32(0.7812), np.float32(0.686), np.float32(0.8384), np.float32(0.9455), np.float32(0.4462), np.float32(0.3643)] +2025-11-11 06:39:29.047878: Epoch time: 258.77 s +2025-11-11 06:39:29.053040: Yayy! New best EMA pseudo Dice: 0.7479000091552734 +2025-11-11 06:39:35.100650: +2025-11-11 06:39:35.102901: Epoch 62 +2025-11-11 06:39:35.104368: Current learning rate: 0.00944 +2025-11-11 06:43:54.641887: train_loss -0.646 +2025-11-11 06:43:54.738665: val_loss -0.6493 +2025-11-11 06:43:54.741835: Pseudo dice [np.float32(0.8884), np.float32(0.7304), np.float32(0.6057), np.float32(0.5839), np.float32(0.8294), np.float32(0.73), np.float32(0.87), np.float32(0.8229), np.float32(0.9224), np.float32(0.9195), np.float32(0.9544), np.float32(0.774), np.float32(0.7145), np.float32(0.8432), np.float32(0.9034), np.float32(0.3808), np.float32(0.3307)] +2025-11-11 06:43:54.956675: Epoch time: 259.55 s +2025-11-11 06:43:54.959009: Yayy! New best EMA pseudo Dice: 0.7483999729156494 +2025-11-11 06:44:01.931531: +2025-11-11 06:44:01.933171: Epoch 63 +2025-11-11 06:44:01.934501: Current learning rate: 0.00943 +2025-11-11 06:48:20.885232: train_loss -0.6403 +2025-11-11 06:48:20.951378: val_loss -0.6674 +2025-11-11 06:48:20.954103: Pseudo dice [np.float32(0.8939), np.float32(0.7296), np.float32(0.6905), np.float32(0.5641), np.float32(0.838), np.float32(0.7544), np.float32(0.858), np.float32(0.8287), np.float32(0.9586), np.float32(0.9574), np.float32(0.9593), np.float32(0.7791), np.float32(0.7166), np.float32(0.8462), np.float32(0.9537), np.float32(0.3669), np.float32(0.3154)] +2025-11-11 06:48:21.087885: Epoch time: 258.96 s +2025-11-11 06:48:21.090340: Yayy! New best EMA pseudo Dice: 0.7501000165939331 +2025-11-11 06:48:28.159765: +2025-11-11 06:48:28.161537: Epoch 64 +2025-11-11 06:48:28.163221: Current learning rate: 0.00942 +2025-11-11 06:52:47.409562: train_loss -0.6497 +2025-11-11 06:52:47.534267: val_loss -0.671 +2025-11-11 06:52:47.543404: Pseudo dice [np.float32(0.9054), np.float32(0.7248), np.float32(0.6712), np.float32(0.5941), np.float32(0.8382), np.float32(0.7385), np.float32(0.866), np.float32(0.8348), np.float32(0.9667), np.float32(0.9643), np.float32(0.9647), np.float32(0.7974), np.float32(0.7043), np.float32(0.8427), np.float32(0.9558), np.float32(0.3942), np.float32(0.3393)] +2025-11-11 06:52:47.546150: Epoch time: 259.26 s +2025-11-11 06:52:47.548695: Yayy! New best EMA pseudo Dice: 0.7522000074386597 +2025-11-11 06:52:53.538600: +2025-11-11 06:52:53.540252: Epoch 65 +2025-11-11 06:52:53.541966: Current learning rate: 0.00941 +2025-11-11 06:57:12.591614: train_loss -0.6404 +2025-11-11 06:57:12.671640: val_loss -0.6597 +2025-11-11 06:57:12.675246: Pseudo dice [np.float32(0.9008), np.float32(0.6641), np.float32(0.6787), np.float32(0.5769), np.float32(0.8292), np.float32(0.7366), np.float32(0.834), np.float32(0.8364), np.float32(0.9628), np.float32(0.9621), np.float32(0.9599), np.float32(0.7531), np.float32(0.7149), np.float32(0.8411), np.float32(0.9418), np.float32(0.3219), np.float32(0.3313)] +2025-11-11 06:57:12.799622: Epoch time: 259.06 s +2025-11-11 06:57:12.803669: Yayy! New best EMA pseudo Dice: 0.7524999976158142 +2025-11-11 06:57:19.785919: +2025-11-11 06:57:19.794817: Epoch 66 +2025-11-11 06:57:19.799655: Current learning rate: 0.0094 +2025-11-11 07:01:38.793668: train_loss -0.6323 +2025-11-11 07:01:39.009248: val_loss -0.6438 +2025-11-11 07:01:39.011122: Pseudo dice [np.float32(0.8976), np.float32(0.6744), np.float32(0.697), np.float32(0.5766), np.float32(0.8295), np.float32(0.7264), np.float32(0.7878), np.float32(0.8181), np.float32(0.9589), np.float32(0.9622), np.float32(0.9608), np.float32(0.7812), np.float32(0.6877), np.float32(0.8401), np.float32(0.9471), np.float32(0.2816), np.float32(0.2987)] +2025-11-11 07:01:39.013725: Epoch time: 259.01 s +2025-11-11 07:01:41.461962: +2025-11-11 07:01:41.466344: Epoch 67 +2025-11-11 07:01:41.469906: Current learning rate: 0.00939 +2025-11-11 07:06:01.416444: train_loss -0.6419 +2025-11-11 07:06:01.503280: val_loss -0.6591 +2025-11-11 07:06:01.504583: Pseudo dice [np.float32(0.9008), np.float32(0.7293), np.float32(0.6501), np.float32(0.5508), np.float32(0.8446), np.float32(0.7859), np.float32(0.8672), np.float32(0.8348), np.float32(0.9626), np.float32(0.957), np.float32(0.9648), np.float32(0.7836), np.float32(0.6828), np.float32(0.8512), np.float32(0.9439), np.float32(0.2586), np.float32(0.2481)] +2025-11-11 07:06:01.777588: Epoch time: 259.97 s +2025-11-11 07:06:26.093397: +2025-11-11 07:06:26.098310: Epoch 68 +2025-11-11 07:06:26.102454: Current learning rate: 0.00939 +2025-11-11 07:10:46.148271: train_loss -0.6421 +2025-11-11 07:10:46.174370: val_loss -0.6636 +2025-11-11 07:10:46.178344: Pseudo dice [np.float32(0.8944), np.float32(0.6321), np.float32(0.644), np.float32(0.5968), np.float32(0.8301), np.float32(0.7329), np.float32(0.8351), np.float32(0.8319), np.float32(0.9696), np.float32(0.9654), np.float32(0.9613), np.float32(0.7723), np.float32(0.7057), np.float32(0.839), np.float32(0.9429), np.float32(0.3897), np.float32(0.3324)] +2025-11-11 07:10:46.182509: Epoch time: 260.06 s +2025-11-11 07:10:46.188159: Yayy! New best EMA pseudo Dice: 0.7527999877929688 +2025-11-11 07:10:54.125760: +2025-11-11 07:10:54.128524: Epoch 69 +2025-11-11 07:10:54.131401: Current learning rate: 0.00938 +2025-11-11 07:15:14.388878: train_loss -0.6546 +2025-11-11 07:15:14.496981: val_loss -0.6679 +2025-11-11 07:15:14.500678: Pseudo dice [np.float32(0.9003), np.float32(0.6709), np.float32(0.6729), np.float32(0.5855), np.float32(0.8424), np.float32(0.7544), np.float32(0.8632), np.float32(0.8384), np.float32(0.9546), np.float32(0.9475), np.float32(0.9617), np.float32(0.7866), np.float32(0.716), np.float32(0.8471), np.float32(0.9366), np.float32(0.3893), np.float32(0.3488)] +2025-11-11 07:15:14.603669: Epoch time: 260.27 s +2025-11-11 07:15:14.607775: Yayy! New best EMA pseudo Dice: 0.7541000247001648 +2025-11-11 07:15:20.867469: +2025-11-11 07:15:20.873132: Epoch 70 +2025-11-11 07:15:20.878827: Current learning rate: 0.00937 +2025-11-11 07:19:40.437513: train_loss -0.6482 +2025-11-11 07:19:40.467575: val_loss -0.658 +2025-11-11 07:19:40.471378: Pseudo dice [np.float32(0.9048), np.float32(0.7184), np.float32(0.6595), np.float32(0.576), np.float32(0.8396), np.float32(0.7142), np.float32(0.8387), np.float32(0.8286), np.float32(0.9605), np.float32(0.9523), np.float32(0.9585), np.float32(0.7928), np.float32(0.7197), np.float32(0.8485), np.float32(0.9446), np.float32(0.3503), np.float32(0.3095)] +2025-11-11 07:19:40.477881: Epoch time: 259.58 s +2025-11-11 07:19:40.485804: Yayy! New best EMA pseudo Dice: 0.7547000050544739 +2025-11-11 07:19:46.750719: +2025-11-11 07:19:46.753792: Epoch 71 +2025-11-11 07:19:46.757423: Current learning rate: 0.00936 +2025-11-11 07:24:07.099508: train_loss -0.6501 +2025-11-11 07:24:07.795421: val_loss -0.6664 +2025-11-11 07:24:07.796881: Pseudo dice [np.float32(0.9007), np.float32(0.7314), np.float32(0.6452), np.float32(0.5694), np.float32(0.8445), np.float32(0.7469), np.float32(0.846), np.float32(0.8331), np.float32(0.9457), np.float32(0.9478), np.float32(0.9627), np.float32(0.7726), np.float32(0.715), np.float32(0.8439), np.float32(0.9454), np.float32(0.3476), np.float32(0.3379)] +2025-11-11 07:24:07.859518: Epoch time: 260.35 s +2025-11-11 07:24:07.860873: Yayy! New best EMA pseudo Dice: 0.755299985408783 +2025-11-11 07:24:14.320929: +2025-11-11 07:24:14.325318: Epoch 72 +2025-11-11 07:24:14.328302: Current learning rate: 0.00935 +2025-11-11 07:28:33.609088: train_loss -0.655 +2025-11-11 07:28:33.635625: val_loss -0.6657 +2025-11-11 07:28:33.642214: Pseudo dice [np.float32(0.8988), np.float32(0.7312), np.float32(0.67), np.float32(0.5698), np.float32(0.8302), np.float32(0.7577), np.float32(0.8339), np.float32(0.8204), np.float32(0.9594), np.float32(0.956), np.float32(0.9636), np.float32(0.7771), np.float32(0.714), np.float32(0.8417), np.float32(0.9487), np.float32(0.3442), np.float32(0.3198)] +2025-11-11 07:28:33.645945: Epoch time: 259.29 s +2025-11-11 07:28:33.650132: Yayy! New best EMA pseudo Dice: 0.7559000253677368 +2025-11-11 07:28:40.871320: +2025-11-11 07:28:40.874154: Epoch 73 +2025-11-11 07:28:40.876606: Current learning rate: 0.00934 +2025-11-11 07:33:01.605067: train_loss -0.6511 +2025-11-11 07:33:01.943866: val_loss -0.6801 +2025-11-11 07:33:01.946395: Pseudo dice [np.float32(0.9052), np.float32(0.7319), np.float32(0.6848), np.float32(0.5945), np.float32(0.8455), np.float32(0.768), np.float32(0.8575), np.float32(0.8112), np.float32(0.9574), np.float32(0.965), np.float32(0.96), np.float32(0.7845), np.float32(0.7491), np.float32(0.8523), np.float32(0.9536), np.float32(0.3448), np.float32(0.3476)] +2025-11-11 07:33:01.989456: Epoch time: 260.74 s +2025-11-11 07:33:01.994692: Yayy! New best EMA pseudo Dice: 0.7573999762535095 +2025-11-11 07:33:08.867614: +2025-11-11 07:33:08.869174: Epoch 74 +2025-11-11 07:33:08.871886: Current learning rate: 0.00933 +2025-11-11 07:37:28.620688: train_loss -0.6538 +2025-11-11 07:37:28.635833: val_loss -0.6714 +2025-11-11 07:37:28.641221: Pseudo dice [np.float32(0.8945), np.float32(0.7263), np.float32(0.696), np.float32(0.611), np.float32(0.8348), np.float32(0.7385), np.float32(0.8559), np.float32(0.841), np.float32(0.9692), np.float32(0.9695), np.float32(0.9642), np.float32(0.7805), np.float32(0.71), np.float32(0.8454), np.float32(0.9416), np.float32(0.3105), np.float32(0.3583)] +2025-11-11 07:37:28.646104: Epoch time: 259.76 s +2025-11-11 07:37:28.650687: Yayy! New best EMA pseudo Dice: 0.758400022983551 +2025-11-11 07:37:36.529152: +2025-11-11 07:37:36.530570: Epoch 75 +2025-11-11 07:37:36.531889: Current learning rate: 0.00932 +2025-11-11 07:41:55.781948: train_loss -0.6563 +2025-11-11 07:41:56.028631: val_loss -0.6657 +2025-11-11 07:41:56.030571: Pseudo dice [np.float32(0.891), np.float32(0.6911), np.float32(0.6154), np.float32(0.5949), np.float32(0.8429), np.float32(0.7457), np.float32(0.845), np.float32(0.8322), np.float32(0.9671), np.float32(0.9673), np.float32(0.9625), np.float32(0.7954), np.float32(0.7409), np.float32(0.8532), np.float32(0.9474), np.float32(0.3409), np.float32(0.4285)] +2025-11-11 07:41:56.139584: Epoch time: 259.26 s +2025-11-11 07:41:56.141669: Yayy! New best EMA pseudo Dice: 0.7594000101089478 +2025-11-11 07:42:01.924809: +2025-11-11 07:42:01.926342: Epoch 76 +2025-11-11 07:42:01.927903: Current learning rate: 0.00931 +2025-11-11 07:46:42.137635: train_loss -0.66 +2025-11-11 07:46:42.143331: val_loss -0.6679 +2025-11-11 07:46:42.144934: Pseudo dice [np.float32(0.8956), np.float32(0.6995), np.float32(0.6898), np.float32(0.5763), np.float32(0.8437), np.float32(0.7401), np.float32(0.8625), np.float32(0.8345), np.float32(0.9721), np.float32(0.9754), np.float32(0.9624), np.float32(0.7982), np.float32(0.6628), np.float32(0.8529), np.float32(0.9492), np.float32(0.4046), np.float32(0.3142)] +2025-11-11 07:46:42.146166: Epoch time: 280.22 s +2025-11-11 07:46:42.147548: Yayy! New best EMA pseudo Dice: 0.7601000070571899 +2025-11-11 07:46:47.240773: +2025-11-11 07:46:47.242682: Epoch 77 +2025-11-11 07:46:47.244293: Current learning rate: 0.0093 +2025-11-11 07:51:06.020520: train_loss -0.6544 +2025-11-11 07:51:06.026230: val_loss -0.6627 +2025-11-11 07:51:06.028396: Pseudo dice [np.float32(0.8957), np.float32(0.7103), np.float32(0.6996), np.float32(0.6262), np.float32(0.8347), np.float32(0.7445), np.float32(0.8496), np.float32(0.8333), np.float32(0.9544), np.float32(0.9417), np.float32(0.962), np.float32(0.7818), np.float32(0.7215), np.float32(0.84), np.float32(0.9451), np.float32(0.3061), np.float32(0.3115)] +2025-11-11 07:51:06.030261: Epoch time: 258.79 s +2025-11-11 07:51:06.032537: Yayy! New best EMA pseudo Dice: 0.7602999806404114 +2025-11-11 07:51:11.356701: +2025-11-11 07:51:11.358578: Epoch 78 +2025-11-11 07:51:11.360255: Current learning rate: 0.0093 +2025-11-11 07:55:30.346413: train_loss -0.6588 +2025-11-11 07:55:30.353091: val_loss -0.6639 +2025-11-11 07:55:30.354842: Pseudo dice [np.float32(0.8839), np.float32(0.7191), np.float32(0.6398), np.float32(0.5929), np.float32(0.8326), np.float32(0.7525), np.float32(0.8374), np.float32(0.8324), np.float32(0.9649), np.float32(0.9614), np.float32(0.9628), np.float32(0.7864), np.float32(0.7185), np.float32(0.8492), np.float32(0.9477), np.float32(0.3469), np.float32(0.2944)] +2025-11-11 07:55:30.357126: Epoch time: 259.0 s +2025-11-11 07:55:32.311084: +2025-11-11 07:55:32.312985: Epoch 79 +2025-11-11 07:55:32.314785: Current learning rate: 0.00929 +2025-11-11 07:59:51.498257: train_loss -0.6599 +2025-11-11 07:59:51.503968: val_loss -0.6799 +2025-11-11 07:59:51.505696: Pseudo dice [np.float32(0.9103), np.float32(0.7238), np.float32(0.6799), np.float32(0.5893), np.float32(0.8415), np.float32(0.7383), np.float32(0.8689), np.float32(0.8339), np.float32(0.9578), np.float32(0.9611), np.float32(0.9608), np.float32(0.795), np.float32(0.6948), np.float32(0.8489), np.float32(0.9386), np.float32(0.434), np.float32(0.343)] +2025-11-11 07:59:51.507445: Epoch time: 259.19 s +2025-11-11 07:59:51.509473: Yayy! New best EMA pseudo Dice: 0.7615000009536743 +2025-11-11 07:59:56.478368: +2025-11-11 07:59:56.479807: Epoch 80 +2025-11-11 07:59:56.481087: Current learning rate: 0.00928 +2025-11-11 08:04:15.308307: train_loss -0.6605 +2025-11-11 08:04:15.315859: val_loss -0.6721 +2025-11-11 08:04:15.318179: Pseudo dice [np.float32(0.9011), np.float32(0.7156), np.float32(0.6745), np.float32(0.5778), np.float32(0.8398), np.float32(0.753), np.float32(0.8753), np.float32(0.8387), np.float32(0.9695), np.float32(0.9617), np.float32(0.9624), np.float32(0.7907), np.float32(0.688), np.float32(0.8477), np.float32(0.9509), np.float32(0.4084), np.float32(0.3281)] +2025-11-11 08:04:15.320349: Epoch time: 258.84 s +2025-11-11 08:04:15.322844: Yayy! New best EMA pseudo Dice: 0.7623000144958496 +2025-11-11 08:04:20.512975: +2025-11-11 08:04:20.514755: Epoch 81 +2025-11-11 08:04:20.516202: Current learning rate: 0.00927 +2025-11-11 08:08:39.311249: train_loss -0.6423 +2025-11-11 08:08:39.315968: val_loss -0.6497 +2025-11-11 08:08:39.317183: Pseudo dice [np.float32(0.9019), np.float32(0.6368), np.float32(0.67), np.float32(0.6123), np.float32(0.8283), np.float32(0.7324), np.float32(0.8678), np.float32(0.8233), np.float32(0.9387), np.float32(0.9341), np.float32(0.9514), np.float32(0.7615), np.float32(0.6891), np.float32(0.8386), np.float32(0.8839), np.float32(0.351), np.float32(0.3025)] +2025-11-11 08:08:39.318280: Epoch time: 258.8 s +2025-11-11 08:08:41.241629: +2025-11-11 08:08:41.243978: Epoch 82 +2025-11-11 08:08:41.246089: Current learning rate: 0.00926 +2025-11-11 08:13:00.081768: train_loss -0.6469 +2025-11-11 08:13:00.093528: val_loss -0.6462 +2025-11-11 08:13:00.095611: Pseudo dice [np.float32(0.9041), np.float32(0.7074), np.float32(0.6791), np.float32(0.586), np.float32(0.8326), np.float32(0.7364), np.float32(0.8266), np.float32(0.8373), np.float32(0.9207), np.float32(0.9196), np.float32(0.9516), np.float32(0.777), np.float32(0.6674), np.float32(0.8426), np.float32(0.8825), np.float32(0.4053), np.float32(0.355)] +2025-11-11 08:13:00.097764: Epoch time: 258.85 s +2025-11-11 08:13:01.978366: +2025-11-11 08:13:01.980157: Epoch 83 +2025-11-11 08:13:01.981655: Current learning rate: 0.00925 +2025-11-11 08:17:21.087782: train_loss -0.6404 +2025-11-11 08:17:21.091902: val_loss -0.6715 +2025-11-11 08:17:21.093399: Pseudo dice [np.float32(0.9006), np.float32(0.7146), np.float32(0.6817), np.float32(0.6072), np.float32(0.8368), np.float32(0.7675), np.float32(0.8626), np.float32(0.834), np.float32(0.9531), np.float32(0.9501), np.float32(0.961), np.float32(0.789), np.float32(0.7066), np.float32(0.8501), np.float32(0.938), np.float32(0.3863), np.float32(0.2999)] +2025-11-11 08:17:21.094578: Epoch time: 259.12 s +2025-11-11 08:17:22.960201: +2025-11-11 08:17:22.961979: Epoch 84 +2025-11-11 08:17:22.963278: Current learning rate: 0.00924 +2025-11-11 08:21:47.215623: train_loss -0.6454 +2025-11-11 08:21:47.222229: val_loss -0.6502 +2025-11-11 08:21:47.224313: Pseudo dice [np.float32(0.8961), np.float32(0.6737), np.float32(0.6214), np.float32(0.5685), np.float32(0.8382), np.float32(0.7237), np.float32(0.8592), np.float32(0.8262), np.float32(0.9428), np.float32(0.9416), np.float32(0.9519), np.float32(0.7706), np.float32(0.7306), np.float32(0.8411), np.float32(0.8871), np.float32(0.411), np.float32(0.3644)] +2025-11-11 08:21:47.226573: Epoch time: 264.26 s +2025-11-11 08:21:49.008594: +2025-11-11 08:21:49.011773: Epoch 85 +2025-11-11 08:21:49.014306: Current learning rate: 0.00923 +2025-11-11 08:26:07.935537: train_loss -0.6448 +2025-11-11 08:26:07.941234: val_loss -0.6804 +2025-11-11 08:26:07.942762: Pseudo dice [np.float32(0.8967), np.float32(0.7337), np.float32(0.6904), np.float32(0.5953), np.float32(0.8379), np.float32(0.7478), np.float32(0.8368), np.float32(0.8424), np.float32(0.9679), np.float32(0.9681), np.float32(0.9614), np.float32(0.7834), np.float32(0.6916), np.float32(0.849), np.float32(0.95), np.float32(0.4841), np.float32(0.4064)] +2025-11-11 08:26:07.944518: Epoch time: 258.93 s +2025-11-11 08:26:07.946307: Yayy! New best EMA pseudo Dice: 0.7623000144958496 +2025-11-11 08:26:12.576244: +2025-11-11 08:26:12.578537: Epoch 86 +2025-11-11 08:26:12.580413: Current learning rate: 0.00922 +2025-11-11 08:30:31.502175: train_loss -0.6575 +2025-11-11 08:30:31.507669: val_loss -0.6798 +2025-11-11 08:30:31.509068: Pseudo dice [np.float32(0.9055), np.float32(0.6846), np.float32(0.685), np.float32(0.6096), np.float32(0.8288), np.float32(0.756), np.float32(0.8779), np.float32(0.8512), np.float32(0.9629), np.float32(0.9605), np.float32(0.9639), np.float32(0.7881), np.float32(0.7228), np.float32(0.8365), np.float32(0.9537), np.float32(0.3683), np.float32(0.4155)] +2025-11-11 08:30:31.510547: Epoch time: 258.93 s +2025-11-11 08:30:31.511986: Yayy! New best EMA pseudo Dice: 0.7634999752044678 +2025-11-11 08:30:36.510038: +2025-11-11 08:30:36.511807: Epoch 87 +2025-11-11 08:30:36.513401: Current learning rate: 0.00921 +2025-11-11 08:34:55.442045: train_loss -0.6617 +2025-11-11 08:34:55.446438: val_loss -0.679 +2025-11-11 08:34:55.447599: Pseudo dice [np.float32(0.9029), np.float32(0.7289), np.float32(0.6649), np.float32(0.6083), np.float32(0.8423), np.float32(0.7652), np.float32(0.8451), np.float32(0.8438), np.float32(0.9659), np.float32(0.9709), np.float32(0.9635), np.float32(0.7889), np.float32(0.7014), np.float32(0.8438), np.float32(0.9563), np.float32(0.4204), np.float32(0.3776)] +2025-11-11 08:34:55.448822: Epoch time: 258.94 s +2025-11-11 08:34:55.449952: Yayy! New best EMA pseudo Dice: 0.7648000121116638 +2025-11-11 08:35:00.467987: +2025-11-11 08:35:00.469667: Epoch 88 +2025-11-11 08:35:00.471267: Current learning rate: 0.0092 +2025-11-11 08:39:19.686198: train_loss -0.6672 +2025-11-11 08:39:19.690172: val_loss -0.6864 +2025-11-11 08:39:19.692523: Pseudo dice [np.float32(0.9137), np.float32(0.7472), np.float32(0.6885), np.float32(0.6058), np.float32(0.8457), np.float32(0.7901), np.float32(0.8768), np.float32(0.8446), np.float32(0.9634), np.float32(0.9615), np.float32(0.9648), np.float32(0.8009), np.float32(0.7151), np.float32(0.857), np.float32(0.9496), np.float32(0.4298), np.float32(0.3781)] +2025-11-11 08:39:19.694493: Epoch time: 259.22 s +2025-11-11 08:39:19.696166: Yayy! New best EMA pseudo Dice: 0.766700029373169 +2025-11-11 08:39:24.818305: +2025-11-11 08:39:24.819944: Epoch 89 +2025-11-11 08:39:24.821575: Current learning rate: 0.0092 +2025-11-11 08:43:43.718364: train_loss -0.6657 +2025-11-11 08:43:43.723180: val_loss -0.6843 +2025-11-11 08:43:43.724552: Pseudo dice [np.float32(0.9), np.float32(0.6858), np.float32(0.6784), np.float32(0.6193), np.float32(0.8465), np.float32(0.7511), np.float32(0.8701), np.float32(0.8515), np.float32(0.9723), np.float32(0.9692), np.float32(0.9654), np.float32(0.787), np.float32(0.6893), np.float32(0.8609), np.float32(0.9544), np.float32(0.3553), np.float32(0.2992)] +2025-11-11 08:43:43.725791: Epoch time: 258.91 s +2025-11-11 08:43:43.727067: Yayy! New best EMA pseudo Dice: 0.7669000029563904 +2025-11-11 08:43:48.638382: +2025-11-11 08:43:48.640039: Epoch 90 +2025-11-11 08:43:48.641408: Current learning rate: 0.00919 +2025-11-11 08:48:07.540019: train_loss -0.6638 +2025-11-11 08:48:07.544226: val_loss -0.6741 +2025-11-11 08:48:07.545709: Pseudo dice [np.float32(0.8978), np.float32(0.7215), np.float32(0.663), np.float32(0.6111), np.float32(0.84), np.float32(0.7681), np.float32(0.8508), np.float32(0.832), np.float32(0.9738), np.float32(0.9672), np.float32(0.964), np.float32(0.7942), np.float32(0.742), np.float32(0.8491), np.float32(0.954), np.float32(0.3493), np.float32(0.2973)] +2025-11-11 08:48:07.547078: Epoch time: 258.91 s +2025-11-11 08:48:07.548498: Yayy! New best EMA pseudo Dice: 0.7670999765396118 +2025-11-11 08:48:12.447711: +2025-11-11 08:48:12.449028: Epoch 91 +2025-11-11 08:48:12.450219: Current learning rate: 0.00918 +2025-11-11 08:52:31.466806: train_loss -0.6642 +2025-11-11 08:52:31.472376: val_loss -0.6736 +2025-11-11 08:52:31.473863: Pseudo dice [np.float32(0.8866), np.float32(0.7417), np.float32(0.696), np.float32(0.6025), np.float32(0.8349), np.float32(0.7342), np.float32(0.8801), np.float32(0.8083), np.float32(0.966), np.float32(0.9657), np.float32(0.9623), np.float32(0.7812), np.float32(0.7235), np.float32(0.8461), np.float32(0.9453), np.float32(0.3722), np.float32(0.2765)] +2025-11-11 08:52:31.475195: Epoch time: 259.02 s +2025-11-11 08:52:33.320427: +2025-11-11 08:52:33.322608: Epoch 92 +2025-11-11 08:52:33.324473: Current learning rate: 0.00917 +2025-11-11 08:56:52.558176: train_loss -0.6537 +2025-11-11 08:56:52.563943: val_loss -0.6791 +2025-11-11 08:56:52.565803: Pseudo dice [np.float32(0.8963), np.float32(0.7408), np.float32(0.7004), np.float32(0.5798), np.float32(0.8434), np.float32(0.7691), np.float32(0.8583), np.float32(0.8397), np.float32(0.9635), np.float32(0.9579), np.float32(0.963), np.float32(0.7853), np.float32(0.7326), np.float32(0.8469), np.float32(0.9393), np.float32(0.3777), np.float32(0.37)] +2025-11-11 08:56:52.567898: Epoch time: 259.25 s +2025-11-11 08:56:52.569696: Yayy! New best EMA pseudo Dice: 0.7677000164985657 +2025-11-11 08:56:57.647913: +2025-11-11 08:56:57.649386: Epoch 93 +2025-11-11 08:56:57.650585: Current learning rate: 0.00916 +2025-11-11 09:01:17.695427: train_loss -0.6514 +2025-11-11 09:01:17.699689: val_loss -0.6753 +2025-11-11 09:01:17.701034: Pseudo dice [np.float32(0.8999), np.float32(0.7371), np.float32(0.6539), np.float32(0.6116), np.float32(0.8325), np.float32(0.7722), np.float32(0.8654), np.float32(0.8453), np.float32(0.9558), np.float32(0.9543), np.float32(0.9612), np.float32(0.7779), np.float32(0.7111), np.float32(0.8457), np.float32(0.9475), np.float32(0.3473), np.float32(0.3324)] +2025-11-11 09:01:17.702136: Epoch time: 260.05 s +2025-11-11 09:01:19.745618: +2025-11-11 09:01:19.747328: Epoch 94 +2025-11-11 09:01:19.749141: Current learning rate: 0.00915 +2025-11-11 09:05:38.696784: train_loss -0.6565 +2025-11-11 09:05:38.701047: val_loss -0.6769 +2025-11-11 09:05:38.702373: Pseudo dice [np.float32(0.9071), np.float32(0.7333), np.float32(0.682), np.float32(0.6063), np.float32(0.8358), np.float32(0.7464), np.float32(0.875), np.float32(0.846), np.float32(0.956), np.float32(0.9581), np.float32(0.9639), np.float32(0.8151), np.float32(0.7023), np.float32(0.8565), np.float32(0.9429), np.float32(0.3533), np.float32(0.2648)] +2025-11-11 09:05:38.703709: Epoch time: 258.96 s +2025-11-11 09:05:40.469571: +2025-11-11 09:05:40.471518: Epoch 95 +2025-11-11 09:05:40.473060: Current learning rate: 0.00914 +2025-11-11 09:09:59.555654: train_loss -0.6594 +2025-11-11 09:09:59.561170: val_loss -0.6773 +2025-11-11 09:09:59.562790: Pseudo dice [np.float32(0.9038), np.float32(0.7025), np.float32(0.69), np.float32(0.5998), np.float32(0.8386), np.float32(0.7454), np.float32(0.8575), np.float32(0.8266), np.float32(0.9679), np.float32(0.9607), np.float32(0.9623), np.float32(0.7764), np.float32(0.7398), np.float32(0.8554), np.float32(0.9534), np.float32(0.3168), np.float32(0.3943)] +2025-11-11 09:09:59.564219: Epoch time: 259.09 s +2025-11-11 09:09:59.565656: Yayy! New best EMA pseudo Dice: 0.7678999900817871 +2025-11-11 09:10:04.285178: +2025-11-11 09:10:04.286417: Epoch 96 +2025-11-11 09:10:04.287828: Current learning rate: 0.00913 +2025-11-11 09:14:23.303362: train_loss -0.6625 +2025-11-11 09:14:23.308259: val_loss -0.665 +2025-11-11 09:14:23.309730: Pseudo dice [np.float32(0.9038), np.float32(0.6997), np.float32(0.6415), np.float32(0.612), np.float32(0.8333), np.float32(0.7477), np.float32(0.843), np.float32(0.8293), np.float32(0.9618), np.float32(0.9611), np.float32(0.961), np.float32(0.8052), np.float32(0.7491), np.float32(0.848), np.float32(0.9445), np.float32(0.4025), np.float32(0.365)] +2025-11-11 09:14:23.310998: Epoch time: 259.02 s +2025-11-11 09:14:23.312541: Yayy! New best EMA pseudo Dice: 0.7681999802589417 +2025-11-11 09:14:28.240513: +2025-11-11 09:14:28.242313: Epoch 97 +2025-11-11 09:14:28.243688: Current learning rate: 0.00912 +2025-11-11 09:18:47.234901: train_loss -0.6553 +2025-11-11 09:18:47.240590: val_loss -0.6735 +2025-11-11 09:18:47.242300: Pseudo dice [np.float32(0.8947), np.float32(0.7285), np.float32(0.6715), np.float32(0.6336), np.float32(0.8375), np.float32(0.7582), np.float32(0.8325), np.float32(0.8349), np.float32(0.976), np.float32(0.9777), np.float32(0.9648), np.float32(0.7913), np.float32(0.727), np.float32(0.8396), np.float32(0.9577), np.float32(0.2967), np.float32(0.3069)] +2025-11-11 09:18:47.243802: Epoch time: 259.0 s +2025-11-11 09:18:49.050011: +2025-11-11 09:18:49.051633: Epoch 98 +2025-11-11 09:18:49.053333: Current learning rate: 0.00911 +2025-11-11 09:23:08.165406: train_loss -0.668 +2025-11-11 09:23:08.170558: val_loss -0.671 +2025-11-11 09:23:08.171770: Pseudo dice [np.float32(0.8988), np.float32(0.7246), np.float32(0.657), np.float32(0.5809), np.float32(0.8479), np.float32(0.7672), np.float32(0.8724), np.float32(0.8415), np.float32(0.9661), np.float32(0.9569), np.float32(0.9622), np.float32(0.8048), np.float32(0.7153), np.float32(0.8535), np.float32(0.955), np.float32(0.3814), np.float32(0.3215)] +2025-11-11 09:23:08.173244: Epoch time: 259.12 s +2025-11-11 09:23:08.174679: Yayy! New best EMA pseudo Dice: 0.7682999968528748 +2025-11-11 09:23:13.068043: +2025-11-11 09:23:13.070144: Epoch 99 +2025-11-11 09:23:13.072025: Current learning rate: 0.0091 +2025-11-11 09:27:31.865608: train_loss -0.6635 +2025-11-11 09:27:31.872974: val_loss -0.6783 +2025-11-11 09:27:31.875158: Pseudo dice [np.float32(0.9053), np.float32(0.727), np.float32(0.6943), np.float32(0.6249), np.float32(0.8365), np.float32(0.7534), np.float32(0.8437), np.float32(0.8421), np.float32(0.9655), np.float32(0.9471), np.float32(0.9621), np.float32(0.794), np.float32(0.7396), np.float32(0.8549), np.float32(0.9476), np.float32(0.3973), np.float32(0.2686)] +2025-11-11 09:27:31.877398: Epoch time: 258.8 s +2025-11-11 09:27:34.719662: Yayy! New best EMA pseudo Dice: 0.7685999870300293 +2025-11-11 09:27:39.843455: +2025-11-11 09:27:39.844960: Epoch 100 +2025-11-11 09:27:39.846434: Current learning rate: 0.0091 +2025-11-11 09:31:58.857388: train_loss -0.6675 +2025-11-11 09:31:58.861336: val_loss -0.6692 +2025-11-11 09:31:58.862751: Pseudo dice [np.float32(0.9057), np.float32(0.6203), np.float32(0.6538), np.float32(0.5821), np.float32(0.8382), np.float32(0.759), np.float32(0.8591), np.float32(0.8388), np.float32(0.9629), np.float32(0.9657), np.float32(0.9632), np.float32(0.7865), np.float32(0.7283), np.float32(0.8442), np.float32(0.9511), np.float32(0.4246), np.float32(0.3649)] +2025-11-11 09:31:58.864637: Epoch time: 259.02 s +2025-11-11 09:32:00.712185: +2025-11-11 09:32:00.713908: Epoch 101 +2025-11-11 09:32:00.715627: Current learning rate: 0.00909 +2025-11-11 09:36:19.874283: train_loss -0.6637 +2025-11-11 09:36:19.878686: val_loss -0.6736 +2025-11-11 09:36:19.879913: Pseudo dice [np.float32(0.9037), np.float32(0.7214), np.float32(0.7063), np.float32(0.6114), np.float32(0.8399), np.float32(0.7695), np.float32(0.8555), np.float32(0.8277), np.float32(0.9669), np.float32(0.9674), np.float32(0.963), np.float32(0.7889), np.float32(0.7362), np.float32(0.8498), np.float32(0.9567), np.float32(0.3841), np.float32(0.2316)] +2025-11-11 09:36:19.881301: Epoch time: 259.17 s +2025-11-11 09:36:22.971670: +2025-11-11 09:36:22.974044: Epoch 102 +2025-11-11 09:36:22.976330: Current learning rate: 0.00908 +2025-11-11 09:40:42.125607: train_loss -0.6607 +2025-11-11 09:40:42.132466: val_loss -0.677 +2025-11-11 09:40:42.134094: Pseudo dice [np.float32(0.9018), np.float32(0.7128), np.float32(0.6554), np.float32(0.6365), np.float32(0.8498), np.float32(0.7747), np.float32(0.8616), np.float32(0.8441), np.float32(0.9487), np.float32(0.955), np.float32(0.9602), np.float32(0.7946), np.float32(0.7659), np.float32(0.8509), np.float32(0.9364), np.float32(0.3802), np.float32(0.2935)] +2025-11-11 09:40:42.135631: Epoch time: 259.16 s +2025-11-11 09:40:42.137591: Yayy! New best EMA pseudo Dice: 0.7688999772071838 +2025-11-11 09:40:46.887251: +2025-11-11 09:40:46.888868: Epoch 103 +2025-11-11 09:40:46.890384: Current learning rate: 0.00907 +2025-11-11 09:45:06.184550: train_loss -0.667 +2025-11-11 09:45:06.190637: val_loss -0.6749 +2025-11-11 09:45:06.193212: Pseudo dice [np.float32(0.8978), np.float32(0.7355), np.float32(0.6952), np.float32(0.6013), np.float32(0.8443), np.float32(0.7798), np.float32(0.8551), np.float32(0.8438), np.float32(0.9449), np.float32(0.9464), np.float32(0.9618), np.float32(0.7933), np.float32(0.7563), np.float32(0.8509), np.float32(0.9323), np.float32(0.4012), np.float32(0.2847)] +2025-11-11 09:45:06.195154: Epoch time: 259.3 s +2025-11-11 09:45:06.197064: Yayy! New best EMA pseudo Dice: 0.7692000269889832 +2025-11-11 09:45:11.214207: +2025-11-11 09:45:11.216897: Epoch 104 +2025-11-11 09:45:11.219822: Current learning rate: 0.00906 +2025-11-11 09:49:30.343125: train_loss -0.6666 +2025-11-11 09:49:30.347636: val_loss -0.679 +2025-11-11 09:49:30.349132: Pseudo dice [np.float32(0.9061), np.float32(0.7331), np.float32(0.7126), np.float32(0.6305), np.float32(0.8455), np.float32(0.7576), np.float32(0.8814), np.float32(0.8402), np.float32(0.9421), np.float32(0.9431), np.float32(0.9645), np.float32(0.7948), np.float32(0.7161), np.float32(0.8613), np.float32(0.9522), np.float32(0.3327), np.float32(0.2998)] +2025-11-11 09:49:30.351023: Epoch time: 259.13 s +2025-11-11 09:49:30.352331: Yayy! New best EMA pseudo Dice: 0.7694000005722046 +2025-11-11 09:49:35.307063: +2025-11-11 09:49:35.308861: Epoch 105 +2025-11-11 09:49:35.310580: Current learning rate: 0.00905 +2025-11-11 09:53:54.661455: train_loss -0.6666 +2025-11-11 09:53:54.670488: val_loss -0.6815 +2025-11-11 09:53:54.673100: Pseudo dice [np.float32(0.8989), np.float32(0.7421), np.float32(0.7079), np.float32(0.5847), np.float32(0.8501), np.float32(0.7773), np.float32(0.8708), np.float32(0.8299), np.float32(0.9542), np.float32(0.9466), np.float32(0.9649), np.float32(0.8008), np.float32(0.7536), np.float32(0.8593), np.float32(0.9417), np.float32(0.2813), np.float32(0.3466)] +2025-11-11 09:53:54.675238: Epoch time: 259.36 s +2025-11-11 09:53:54.677623: Yayy! New best EMA pseudo Dice: 0.769599974155426 +2025-11-11 09:53:59.755435: +2025-11-11 09:53:59.757382: Epoch 106 +2025-11-11 09:53:59.759100: Current learning rate: 0.00904 +2025-11-11 09:58:18.724794: train_loss -0.6699 +2025-11-11 09:58:18.731103: val_loss -0.6823 +2025-11-11 09:58:18.733102: Pseudo dice [np.float32(0.8938), np.float32(0.6031), np.float32(0.6835), np.float32(0.6084), np.float32(0.8441), np.float32(0.7382), np.float32(0.8835), np.float32(0.8313), np.float32(0.9568), np.float32(0.9588), np.float32(0.9642), np.float32(0.796), np.float32(0.6844), np.float32(0.8515), np.float32(0.9569), np.float32(0.4286), np.float32(0.3733)] +2025-11-11 09:58:18.734949: Epoch time: 258.97 s +2025-11-11 09:58:20.578094: +2025-11-11 09:58:20.579658: Epoch 107 +2025-11-11 09:58:20.580948: Current learning rate: 0.00903 +2025-11-11 10:02:39.400573: train_loss -0.6617 +2025-11-11 10:02:39.405310: val_loss -0.6649 +2025-11-11 10:02:39.406862: Pseudo dice [np.float32(0.9064), np.float32(0.6862), np.float32(0.6622), np.float32(0.6212), np.float32(0.8392), np.float32(0.7377), np.float32(0.861), np.float32(0.8253), np.float32(0.954), np.float32(0.9584), np.float32(0.9609), np.float32(0.787), np.float32(0.7235), np.float32(0.8401), np.float32(0.926), np.float32(0.3287), np.float32(0.2416)] +2025-11-11 10:02:39.408712: Epoch time: 258.83 s +2025-11-11 10:02:41.227264: +2025-11-11 10:02:41.229503: Epoch 108 +2025-11-11 10:02:41.231432: Current learning rate: 0.00902 +2025-11-11 10:07:00.259392: train_loss -0.6535 +2025-11-11 10:07:00.268947: val_loss -0.6818 +2025-11-11 10:07:00.271874: Pseudo dice [np.float32(0.9035), np.float32(0.7204), np.float32(0.6684), np.float32(0.636), np.float32(0.849), np.float32(0.7668), np.float32(0.8544), np.float32(0.8266), np.float32(0.9544), np.float32(0.9503), np.float32(0.9627), np.float32(0.81), np.float32(0.7464), np.float32(0.8562), np.float32(0.9359), np.float32(0.283), np.float32(0.3191)] +2025-11-11 10:07:00.274212: Epoch time: 259.04 s +2025-11-11 10:07:02.128391: +2025-11-11 10:07:02.130292: Epoch 109 +2025-11-11 10:07:02.131738: Current learning rate: 0.00901 +2025-11-11 10:11:21.087981: train_loss -0.6646 +2025-11-11 10:11:21.093173: val_loss -0.6858 +2025-11-11 10:11:21.094544: Pseudo dice [np.float32(0.9089), np.float32(0.7263), np.float32(0.6825), np.float32(0.596), np.float32(0.8471), np.float32(0.7622), np.float32(0.8796), np.float32(0.8365), np.float32(0.9621), np.float32(0.9557), np.float32(0.9636), np.float32(0.7947), np.float32(0.7439), np.float32(0.8579), np.float32(0.9457), np.float32(0.4738), np.float32(0.3842)] +2025-11-11 10:11:21.095780: Epoch time: 258.96 s +2025-11-11 10:11:22.936217: +2025-11-11 10:11:22.937974: Epoch 110 +2025-11-11 10:11:22.939514: Current learning rate: 0.009 +2025-11-11 10:15:42.716666: train_loss -0.6638 +2025-11-11 10:15:42.720668: val_loss -0.6756 +2025-11-11 10:15:42.721870: Pseudo dice [np.float32(0.9069), np.float32(0.741), np.float32(0.6825), np.float32(0.6381), np.float32(0.8365), np.float32(0.7544), np.float32(0.8615), np.float32(0.8421), np.float32(0.9686), np.float32(0.969), np.float32(0.9596), np.float32(0.7903), np.float32(0.719), np.float32(0.8483), np.float32(0.9299), np.float32(0.3589), np.float32(0.2796)] +2025-11-11 10:15:42.723088: Epoch time: 259.79 s +2025-11-11 10:15:42.724435: Yayy! New best EMA pseudo Dice: 0.769599974155426 +2025-11-11 10:15:47.484674: +2025-11-11 10:15:47.486205: Epoch 111 +2025-11-11 10:15:47.487730: Current learning rate: 0.009 +2025-11-11 10:20:06.258975: train_loss -0.6611 +2025-11-11 10:20:06.266413: val_loss -0.6799 +2025-11-11 10:20:06.268699: Pseudo dice [np.float32(0.9109), np.float32(0.6303), np.float32(0.6706), np.float32(0.6291), np.float32(0.8469), np.float32(0.766), np.float32(0.8693), np.float32(0.8312), np.float32(0.9493), np.float32(0.9551), np.float32(0.9628), np.float32(0.7935), np.float32(0.7521), np.float32(0.8533), np.float32(0.9449), np.float32(0.3171), np.float32(0.2785)] +2025-11-11 10:20:06.270283: Epoch time: 258.78 s +2025-11-11 10:20:08.052197: +2025-11-11 10:20:08.053594: Epoch 112 +2025-11-11 10:20:08.054801: Current learning rate: 0.00899 +2025-11-11 10:24:26.997459: train_loss -0.6689 +2025-11-11 10:24:27.002166: val_loss -0.666 +2025-11-11 10:24:27.003520: Pseudo dice [np.float32(0.9001), np.float32(0.6463), np.float32(0.6801), np.float32(0.6109), np.float32(0.8504), np.float32(0.7176), np.float32(0.8417), np.float32(0.8345), np.float32(0.9518), np.float32(0.9465), np.float32(0.9639), np.float32(0.7851), np.float32(0.7211), np.float32(0.8471), np.float32(0.9518), np.float32(0.3553), np.float32(0.2386)] +2025-11-11 10:24:27.004880: Epoch time: 258.95 s +2025-11-11 10:24:28.863462: +2025-11-11 10:24:28.865395: Epoch 113 +2025-11-11 10:24:28.867459: Current learning rate: 0.00898 +2025-11-11 10:28:47.716979: train_loss -0.666 +2025-11-11 10:28:47.721015: val_loss -0.6752 +2025-11-11 10:28:47.722497: Pseudo dice [np.float32(0.8982), np.float32(0.7287), np.float32(0.6723), np.float32(0.62), np.float32(0.8465), np.float32(0.7632), np.float32(0.8534), np.float32(0.8378), np.float32(0.9624), np.float32(0.959), np.float32(0.964), np.float32(0.7841), np.float32(0.7809), np.float32(0.8538), np.float32(0.9451), np.float32(0.2365), np.float32(0.3169)] +2025-11-11 10:28:47.723703: Epoch time: 258.86 s +2025-11-11 10:28:49.509916: +2025-11-11 10:28:49.511509: Epoch 114 +2025-11-11 10:28:49.512841: Current learning rate: 0.00897 +2025-11-11 10:33:08.568686: train_loss -0.6748 +2025-11-11 10:33:08.573680: val_loss -0.6747 +2025-11-11 10:33:08.575173: Pseudo dice [np.float32(0.898), np.float32(0.7187), np.float32(0.7085), np.float32(0.6206), np.float32(0.8382), np.float32(0.7661), np.float32(0.8442), np.float32(0.8367), np.float32(0.9469), np.float32(0.9483), np.float32(0.9621), np.float32(0.7969), np.float32(0.7275), np.float32(0.848), np.float32(0.9365), np.float32(0.3525), np.float32(0.358)] +2025-11-11 10:33:08.576668: Epoch time: 259.06 s +2025-11-11 10:33:10.354525: +2025-11-11 10:33:10.357208: Epoch 115 +2025-11-11 10:33:10.359109: Current learning rate: 0.00896 +2025-11-11 10:37:29.013072: train_loss -0.6647 +2025-11-11 10:37:29.017135: val_loss -0.6853 +2025-11-11 10:37:29.018619: Pseudo dice [np.float32(0.8968), np.float32(0.679), np.float32(0.7176), np.float32(0.6055), np.float32(0.8439), np.float32(0.7694), np.float32(0.8676), np.float32(0.8368), np.float32(0.973), np.float32(0.9732), np.float32(0.9649), np.float32(0.791), np.float32(0.7299), np.float32(0.8571), np.float32(0.9538), np.float32(0.3903), np.float32(0.3074)] +2025-11-11 10:37:29.019944: Epoch time: 258.66 s +2025-11-11 10:37:30.897521: +2025-11-11 10:37:30.898826: Epoch 116 +2025-11-11 10:37:30.900101: Current learning rate: 0.00895 +2025-11-11 10:41:49.678987: train_loss -0.662 +2025-11-11 10:41:49.683149: val_loss -0.6716 +2025-11-11 10:41:49.685040: Pseudo dice [np.float32(0.903), np.float32(0.7134), np.float32(0.6981), np.float32(0.5912), np.float32(0.8395), np.float32(0.7511), np.float32(0.8102), np.float32(0.8422), np.float32(0.9627), np.float32(0.96), np.float32(0.962), np.float32(0.7997), np.float32(0.7481), np.float32(0.8453), np.float32(0.9449), np.float32(0.354), np.float32(0.2555)] +2025-11-11 10:41:49.686643: Epoch time: 258.79 s +2025-11-11 10:41:51.501931: +2025-11-11 10:41:51.503993: Epoch 117 +2025-11-11 10:41:51.506187: Current learning rate: 0.00894 +2025-11-11 10:46:10.268023: train_loss -0.6589 +2025-11-11 10:46:10.273293: val_loss -0.6805 +2025-11-11 10:46:10.274632: Pseudo dice [np.float32(0.9068), np.float32(0.7122), np.float32(0.6866), np.float32(0.6086), np.float32(0.8514), np.float32(0.7742), np.float32(0.8463), np.float32(0.8442), np.float32(0.9564), np.float32(0.9589), np.float32(0.9645), np.float32(0.7908), np.float32(0.7294), np.float32(0.8564), np.float32(0.9477), np.float32(0.3624), np.float32(0.3414)] +2025-11-11 10:46:10.276002: Epoch time: 258.77 s +2025-11-11 10:46:12.084322: +2025-11-11 10:46:12.085748: Epoch 118 +2025-11-11 10:46:12.087122: Current learning rate: 0.00893 +2025-11-11 10:50:30.861876: train_loss -0.6658 +2025-11-11 10:50:30.867018: val_loss -0.6831 +2025-11-11 10:50:30.869088: Pseudo dice [np.float32(0.9039), np.float32(0.7499), np.float32(0.6933), np.float32(0.6333), np.float32(0.8464), np.float32(0.7504), np.float32(0.8919), np.float32(0.8251), np.float32(0.9664), np.float32(0.9664), np.float32(0.9608), np.float32(0.7992), np.float32(0.7357), np.float32(0.8547), np.float32(0.9476), np.float32(0.3113), np.float32(0.2846)] +2025-11-11 10:50:30.870445: Epoch time: 258.78 s +2025-11-11 10:50:32.700605: +2025-11-11 10:50:32.702039: Epoch 119 +2025-11-11 10:50:32.703421: Current learning rate: 0.00892 +2025-11-11 10:54:51.092202: train_loss -0.6719 +2025-11-11 10:54:51.096370: val_loss -0.6782 +2025-11-11 10:54:51.097538: Pseudo dice [np.float32(0.8907), np.float32(0.7014), np.float32(0.6859), np.float32(0.5877), np.float32(0.8497), np.float32(0.771), np.float32(0.8602), np.float32(0.8258), np.float32(0.9467), np.float32(0.951), np.float32(0.9612), np.float32(0.7919), np.float32(0.7513), np.float32(0.8612), np.float32(0.9384), np.float32(0.3001), np.float32(0.3465)] +2025-11-11 10:54:51.098799: Epoch time: 258.4 s +2025-11-11 10:54:54.239119: +2025-11-11 10:54:54.240574: Epoch 120 +2025-11-11 10:54:54.241798: Current learning rate: 0.00891 +2025-11-11 10:59:12.787905: train_loss -0.6677 +2025-11-11 10:59:12.792737: val_loss -0.6765 +2025-11-11 10:59:12.794331: Pseudo dice [np.float32(0.9097), np.float32(0.7347), np.float32(0.6975), np.float32(0.5986), np.float32(0.8414), np.float32(0.7594), np.float32(0.8605), np.float32(0.8481), np.float32(0.9561), np.float32(0.9539), np.float32(0.9645), np.float32(0.8048), np.float32(0.7448), np.float32(0.854), np.float32(0.9516), np.float32(0.3402), np.float32(0.3271)] +2025-11-11 10:59:12.795813: Epoch time: 258.55 s +2025-11-11 10:59:14.563587: +2025-11-11 10:59:14.565338: Epoch 121 +2025-11-11 10:59:14.566720: Current learning rate: 0.0089 +2025-11-11 11:03:33.475016: train_loss -0.6743 +2025-11-11 11:03:33.482545: val_loss -0.6891 +2025-11-11 11:03:33.484960: Pseudo dice [np.float32(0.9017), np.float32(0.7244), np.float32(0.6599), np.float32(0.6018), np.float32(0.8517), np.float32(0.7876), np.float32(0.8447), np.float32(0.8421), np.float32(0.9766), np.float32(0.9764), np.float32(0.9662), np.float32(0.814), np.float32(0.7376), np.float32(0.8589), np.float32(0.9567), np.float32(0.3522), np.float32(0.3705)] +2025-11-11 11:03:33.487231: Epoch time: 258.92 s +2025-11-11 11:03:33.489548: Yayy! New best EMA pseudo Dice: 0.7698000073432922 +2025-11-11 11:03:38.427601: +2025-11-11 11:03:38.429088: Epoch 122 +2025-11-11 11:03:38.430477: Current learning rate: 0.00889 +2025-11-11 11:07:56.838547: train_loss -0.6722 +2025-11-11 11:07:56.843127: val_loss -0.673 +2025-11-11 11:07:56.844394: Pseudo dice [np.float32(0.9002), np.float32(0.7357), np.float32(0.6628), np.float32(0.6229), np.float32(0.8413), np.float32(0.7683), np.float32(0.8763), np.float32(0.8428), np.float32(0.9512), np.float32(0.9489), np.float32(0.9644), np.float32(0.8098), np.float32(0.6876), np.float32(0.8453), np.float32(0.9349), np.float32(0.3862), np.float32(0.3212)] +2025-11-11 11:07:56.846081: Epoch time: 258.42 s +2025-11-11 11:07:56.847374: Yayy! New best EMA pseudo Dice: 0.7699000239372253 +2025-11-11 11:08:01.867797: +2025-11-11 11:08:01.869450: Epoch 123 +2025-11-11 11:08:01.870734: Current learning rate: 0.00889 +2025-11-11 11:12:20.378388: train_loss -0.6717 +2025-11-11 11:12:20.382879: val_loss -0.6786 +2025-11-11 11:12:20.384840: Pseudo dice [np.float32(0.9018), np.float32(0.7305), np.float32(0.6718), np.float32(0.613), np.float32(0.8375), np.float32(0.7671), np.float32(0.8349), np.float32(0.8499), np.float32(0.9561), np.float32(0.9578), np.float32(0.9651), np.float32(0.8029), np.float32(0.7182), np.float32(0.8575), np.float32(0.956), np.float32(0.393), np.float32(0.3301)] +2025-11-11 11:12:20.387415: Epoch time: 258.52 s +2025-11-11 11:12:20.389007: Yayy! New best EMA pseudo Dice: 0.7702000141143799 +2025-11-11 11:12:25.581606: +2025-11-11 11:12:25.583343: Epoch 124 +2025-11-11 11:12:25.584718: Current learning rate: 0.00888 +2025-11-11 11:16:44.101351: train_loss -0.6744 +2025-11-11 11:16:44.106233: val_loss -0.6833 +2025-11-11 11:16:44.107941: Pseudo dice [np.float32(0.9184), np.float32(0.6308), np.float32(0.7112), np.float32(0.5853), np.float32(0.84), np.float32(0.7661), np.float32(0.8525), np.float32(0.8347), np.float32(0.9696), np.float32(0.969), np.float32(0.9661), np.float32(0.7959), np.float32(0.7421), np.float32(0.8558), np.float32(0.9617), np.float32(0.3841), np.float32(0.329)] +2025-11-11 11:16:44.110153: Epoch time: 258.53 s +2025-11-11 11:16:44.111844: Yayy! New best EMA pseudo Dice: 0.7702999711036682 +2025-11-11 11:16:49.203485: +2025-11-11 11:16:49.205012: Epoch 125 +2025-11-11 11:16:49.206354: Current learning rate: 0.00887 +2025-11-11 11:21:07.938773: train_loss -0.669 +2025-11-11 11:21:07.943118: val_loss -0.6924 +2025-11-11 11:21:07.944474: Pseudo dice [np.float32(0.9084), np.float32(0.7608), np.float32(0.6972), np.float32(0.6236), np.float32(0.8605), np.float32(0.7745), np.float32(0.8686), np.float32(0.8475), np.float32(0.9674), np.float32(0.9726), np.float32(0.9678), np.float32(0.8005), np.float32(0.7225), np.float32(0.8623), np.float32(0.959), np.float32(0.2858), np.float32(0.2053)] +2025-11-11 11:21:07.945795: Epoch time: 258.74 s +2025-11-11 11:21:09.846182: +2025-11-11 11:21:09.848430: Epoch 126 +2025-11-11 11:21:09.849931: Current learning rate: 0.00886 +2025-11-11 11:25:28.656910: train_loss -0.6731 +2025-11-11 11:25:28.661977: val_loss -0.678 +2025-11-11 11:25:28.663591: Pseudo dice [np.float32(0.8891), np.float32(0.711), np.float32(0.6919), np.float32(0.5842), np.float32(0.8519), np.float32(0.7666), np.float32(0.8763), np.float32(0.8456), np.float32(0.9694), np.float32(0.9615), np.float32(0.965), np.float32(0.7963), np.float32(0.7277), np.float32(0.8583), np.float32(0.9533), np.float32(0.3657), np.float32(0.349)] +2025-11-11 11:25:28.665246: Epoch time: 258.82 s +2025-11-11 11:25:28.666381: Yayy! New best EMA pseudo Dice: 0.7706999778747559 +2025-11-11 11:25:33.689599: +2025-11-11 11:25:33.691136: Epoch 127 +2025-11-11 11:25:33.692685: Current learning rate: 0.00885 +2025-11-11 11:29:52.497384: train_loss -0.67 +2025-11-11 11:29:52.502261: val_loss -0.6868 +2025-11-11 11:29:52.503893: Pseudo dice [np.float32(0.9075), np.float32(0.7433), np.float32(0.7153), np.float32(0.6073), np.float32(0.8426), np.float32(0.7687), np.float32(0.8349), np.float32(0.8407), np.float32(0.957), np.float32(0.9607), np.float32(0.9646), np.float32(0.8178), np.float32(0.7389), np.float32(0.8534), np.float32(0.9567), np.float32(0.4457), np.float32(0.35)] +2025-11-11 11:29:52.505474: Epoch time: 258.81 s +2025-11-11 11:29:52.506831: Yayy! New best EMA pseudo Dice: 0.7718999981880188 +2025-11-11 11:29:57.460738: +2025-11-11 11:29:57.462808: Epoch 128 +2025-11-11 11:29:57.464571: Current learning rate: 0.00884 +2025-11-11 11:34:17.413588: train_loss -0.6737 +2025-11-11 11:34:17.418693: val_loss -0.6924 +2025-11-11 11:34:17.420437: Pseudo dice [np.float32(0.8941), np.float32(0.7207), np.float32(0.692), np.float32(0.6289), np.float32(0.8516), np.float32(0.7796), np.float32(0.8481), np.float32(0.8406), np.float32(0.9765), np.float32(0.9711), np.float32(0.9665), np.float32(0.8034), np.float32(0.7536), np.float32(0.8643), np.float32(0.9602), np.float32(0.4357), np.float32(0.3328)] +2025-11-11 11:34:17.422533: Epoch time: 259.96 s +2025-11-11 11:34:17.424007: Yayy! New best EMA pseudo Dice: 0.7730000019073486 +2025-11-11 11:34:22.489340: +2025-11-11 11:34:22.491509: Epoch 129 +2025-11-11 11:34:22.493601: Current learning rate: 0.00883 +2025-11-11 11:38:41.362512: train_loss -0.6704 +2025-11-11 11:38:41.366541: val_loss -0.6921 +2025-11-11 11:38:41.367727: Pseudo dice [np.float32(0.9102), np.float32(0.7533), np.float32(0.6799), np.float32(0.5884), np.float32(0.8412), np.float32(0.7454), np.float32(0.8575), np.float32(0.8388), np.float32(0.9642), np.float32(0.9689), np.float32(0.9646), np.float32(0.8023), np.float32(0.751), np.float32(0.8498), np.float32(0.9518), np.float32(0.3936), np.float32(0.4485)] +2025-11-11 11:38:41.368833: Epoch time: 258.88 s +2025-11-11 11:38:41.370018: Yayy! New best EMA pseudo Dice: 0.7739999890327454 +2025-11-11 11:38:46.381747: +2025-11-11 11:38:46.383816: Epoch 130 +2025-11-11 11:38:46.385275: Current learning rate: 0.00882 +2025-11-11 11:43:05.038210: train_loss -0.6739 +2025-11-11 11:43:05.044360: val_loss -0.6817 +2025-11-11 11:43:05.046593: Pseudo dice [np.float32(0.8965), np.float32(0.7609), np.float32(0.6911), np.float32(0.5846), np.float32(0.844), np.float32(0.7661), np.float32(0.853), np.float32(0.8447), np.float32(0.9638), np.float32(0.9647), np.float32(0.9646), np.float32(0.7967), np.float32(0.7305), np.float32(0.8536), np.float32(0.9517), np.float32(0.4378), np.float32(0.2766)] +2025-11-11 11:43:05.048476: Epoch time: 258.66 s +2025-11-11 11:43:05.050100: Yayy! New best EMA pseudo Dice: 0.7742000222206116 +2025-11-11 11:43:10.140339: +2025-11-11 11:43:10.141885: Epoch 131 +2025-11-11 11:43:10.143698: Current learning rate: 0.00881 +2025-11-11 11:47:29.416348: train_loss -0.6746 +2025-11-11 11:47:29.420606: val_loss -0.6774 +2025-11-11 11:47:29.422258: Pseudo dice [np.float32(0.8911), np.float32(0.659), np.float32(0.6882), np.float32(0.6015), np.float32(0.8525), np.float32(0.7642), np.float32(0.8323), np.float32(0.839), np.float32(0.9616), np.float32(0.9621), np.float32(0.9645), np.float32(0.8126), np.float32(0.7586), np.float32(0.8526), np.float32(0.9467), np.float32(0.3623), np.float32(0.2865)] +2025-11-11 11:47:29.423738: Epoch time: 259.28 s +2025-11-11 11:47:31.296330: +2025-11-11 11:47:31.297954: Epoch 132 +2025-11-11 11:47:31.299191: Current learning rate: 0.0088 +2025-11-11 11:51:49.745367: train_loss -0.6757 +2025-11-11 11:51:49.750199: val_loss -0.6835 +2025-11-11 11:51:49.751914: Pseudo dice [np.float32(0.9027), np.float32(0.7363), np.float32(0.6931), np.float32(0.6109), np.float32(0.8462), np.float32(0.7681), np.float32(0.8508), np.float32(0.8415), np.float32(0.9514), np.float32(0.9528), np.float32(0.9626), np.float32(0.8176), np.float32(0.7484), np.float32(0.8507), np.float32(0.9417), np.float32(0.43), np.float32(0.3339)] +2025-11-11 11:51:49.753433: Epoch time: 258.45 s +2025-11-11 11:51:51.667347: +2025-11-11 11:51:51.669523: Epoch 133 +2025-11-11 11:51:51.671747: Current learning rate: 0.00879 +2025-11-11 11:56:10.272203: train_loss -0.6754 +2025-11-11 11:56:10.276992: val_loss -0.6835 +2025-11-11 11:56:10.278183: Pseudo dice [np.float32(0.9052), np.float32(0.7388), np.float32(0.6349), np.float32(0.6143), np.float32(0.8501), np.float32(0.7736), np.float32(0.857), np.float32(0.8425), np.float32(0.9619), np.float32(0.9639), np.float32(0.9657), np.float32(0.795), np.float32(0.7504), np.float32(0.8575), np.float32(0.9503), np.float32(0.4413), np.float32(0.4353)] +2025-11-11 11:56:10.279434: Epoch time: 258.62 s +2025-11-11 11:56:10.280608: Yayy! New best EMA pseudo Dice: 0.7749999761581421 +2025-11-11 11:56:14.909212: +2025-11-11 11:56:14.910855: Epoch 134 +2025-11-11 11:56:14.912431: Current learning rate: 0.00879 +2025-11-11 12:00:33.776531: train_loss -0.6739 +2025-11-11 12:00:33.782826: val_loss -0.6839 +2025-11-11 12:00:33.785470: Pseudo dice [np.float32(0.9075), np.float32(0.7357), np.float32(0.7016), np.float32(0.5979), np.float32(0.8525), np.float32(0.7699), np.float32(0.8812), np.float32(0.8462), np.float32(0.9586), np.float32(0.9553), np.float32(0.9658), np.float32(0.8094), np.float32(0.7086), np.float32(0.8551), np.float32(0.9592), np.float32(0.3181), np.float32(0.3328)] +2025-11-11 12:00:33.786834: Epoch time: 258.87 s +2025-11-11 12:00:35.671006: +2025-11-11 12:00:35.672316: Epoch 135 +2025-11-11 12:00:35.673622: Current learning rate: 0.00878 +2025-11-11 12:04:54.464349: train_loss -0.6772 +2025-11-11 12:04:54.469835: val_loss -0.7025 +2025-11-11 12:04:54.472003: Pseudo dice [np.float32(0.9101), np.float32(0.7488), np.float32(0.6982), np.float32(0.6158), np.float32(0.8435), np.float32(0.7794), np.float32(0.8748), np.float32(0.8438), np.float32(0.9716), np.float32(0.9711), np.float32(0.9643), np.float32(0.8027), np.float32(0.7403), np.float32(0.8523), np.float32(0.9551), np.float32(0.3428), np.float32(0.4155)] +2025-11-11 12:04:54.473918: Epoch time: 258.8 s +2025-11-11 12:04:54.475893: Yayy! New best EMA pseudo Dice: 0.7757999897003174 +2025-11-11 12:04:59.546134: +2025-11-11 12:04:59.547702: Epoch 136 +2025-11-11 12:04:59.549027: Current learning rate: 0.00877 +2025-11-11 12:09:18.204029: train_loss -0.6785 +2025-11-11 12:09:18.208387: val_loss -0.689 +2025-11-11 12:09:18.209656: Pseudo dice [np.float32(0.9077), np.float32(0.7134), np.float32(0.6811), np.float32(0.6338), np.float32(0.8362), np.float32(0.7862), np.float32(0.8481), np.float32(0.8612), np.float32(0.9674), np.float32(0.9656), np.float32(0.9658), np.float32(0.7919), np.float32(0.7641), np.float32(0.8579), np.float32(0.9538), np.float32(0.3223), np.float32(0.4328)] +2025-11-11 12:09:18.211071: Epoch time: 258.66 s +2025-11-11 12:09:18.212263: Yayy! New best EMA pseudo Dice: 0.7764000296592712 +2025-11-11 12:09:25.102449: +2025-11-11 12:09:25.104162: Epoch 137 +2025-11-11 12:09:25.105579: Current learning rate: 0.00876 +2025-11-11 12:13:43.805231: train_loss -0.6786 +2025-11-11 12:13:43.811769: val_loss -0.6779 +2025-11-11 12:13:43.814117: Pseudo dice [np.float32(0.9018), np.float32(0.7239), np.float32(0.6978), np.float32(0.6115), np.float32(0.8563), np.float32(0.7646), np.float32(0.8669), np.float32(0.8409), np.float32(0.9569), np.float32(0.9574), np.float32(0.9638), np.float32(0.8027), np.float32(0.7359), np.float32(0.861), np.float32(0.9383), np.float32(0.3457), np.float32(0.2381)] +2025-11-11 12:13:43.816064: Epoch time: 258.71 s +2025-11-11 12:13:45.645447: +2025-11-11 12:13:45.646895: Epoch 138 +2025-11-11 12:13:45.648835: Current learning rate: 0.00875 +2025-11-11 12:18:04.371200: train_loss -0.6837 +2025-11-11 12:18:04.375939: val_loss -0.682 +2025-11-11 12:18:04.377937: Pseudo dice [np.float32(0.9149), np.float32(0.7634), np.float32(0.7127), np.float32(0.6373), np.float32(0.8464), np.float32(0.773), np.float32(0.8872), np.float32(0.8502), np.float32(0.9564), np.float32(0.9592), np.float32(0.963), np.float32(0.8073), np.float32(0.745), np.float32(0.8564), np.float32(0.9302), np.float32(0.2877), np.float32(0.2923)] +2025-11-11 12:18:04.379184: Epoch time: 258.73 s +2025-11-11 12:18:06.204237: +2025-11-11 12:18:06.208830: Epoch 139 +2025-11-11 12:18:06.210585: Current learning rate: 0.00874 +2025-11-11 12:22:24.539183: train_loss -0.6719 +2025-11-11 12:22:24.546543: val_loss -0.6813 +2025-11-11 12:22:24.548784: Pseudo dice [np.float32(0.9056), np.float32(0.7521), np.float32(0.6912), np.float32(0.6342), np.float32(0.844), np.float32(0.7645), np.float32(0.8428), np.float32(0.8382), np.float32(0.9302), np.float32(0.928), np.float32(0.9586), np.float32(0.7985), np.float32(0.7317), np.float32(0.8593), np.float32(0.9315), np.float32(0.36), np.float32(0.2946)] +2025-11-11 12:22:24.550576: Epoch time: 258.34 s +2025-11-11 12:22:26.400164: +2025-11-11 12:22:26.402234: Epoch 140 +2025-11-11 12:22:26.403759: Current learning rate: 0.00873 +2025-11-11 12:26:44.838425: train_loss -0.6707 +2025-11-11 12:26:44.842438: val_loss -0.6838 +2025-11-11 12:26:44.843865: Pseudo dice [np.float32(0.9069), np.float32(0.7194), np.float32(0.689), np.float32(0.5691), np.float32(0.8433), np.float32(0.7786), np.float32(0.8432), np.float32(0.8431), np.float32(0.9668), np.float32(0.9732), np.float32(0.9656), np.float32(0.8011), np.float32(0.7392), np.float32(0.8496), np.float32(0.9594), np.float32(0.4381), np.float32(0.293)] +2025-11-11 12:26:44.845559: Epoch time: 258.44 s +2025-11-11 12:26:46.743380: +2025-11-11 12:26:46.744805: Epoch 141 +2025-11-11 12:26:46.746047: Current learning rate: 0.00872 +2025-11-11 12:31:05.289641: train_loss -0.6769 +2025-11-11 12:31:05.295492: val_loss -0.6831 +2025-11-11 12:31:05.297723: Pseudo dice [np.float32(0.9153), np.float32(0.6745), np.float32(0.6906), np.float32(0.6089), np.float32(0.8474), np.float32(0.771), np.float32(0.8618), np.float32(0.8416), np.float32(0.9536), np.float32(0.9535), np.float32(0.9624), np.float32(0.8119), np.float32(0.7534), np.float32(0.8546), np.float32(0.9342), np.float32(0.3726), np.float32(0.3517)] +2025-11-11 12:31:05.298910: Epoch time: 258.55 s +2025-11-11 12:31:07.156776: +2025-11-11 12:31:07.158269: Epoch 142 +2025-11-11 12:31:07.159462: Current learning rate: 0.00871 +2025-11-11 12:35:25.751328: train_loss -0.6781 +2025-11-11 12:35:25.755575: val_loss -0.672 +2025-11-11 12:35:25.757022: Pseudo dice [np.float32(0.9), np.float32(0.6584), np.float32(0.6557), np.float32(0.6361), np.float32(0.8483), np.float32(0.7695), np.float32(0.8578), np.float32(0.8359), np.float32(0.9372), np.float32(0.9277), np.float32(0.962), np.float32(0.8006), np.float32(0.7416), np.float32(0.8611), np.float32(0.9334), np.float32(0.2844), np.float32(0.3051)] +2025-11-11 12:35:25.758281: Epoch time: 258.6 s +2025-11-11 12:35:27.672285: +2025-11-11 12:35:27.673743: Epoch 143 +2025-11-11 12:35:27.675019: Current learning rate: 0.0087 +2025-11-11 12:39:46.326582: train_loss -0.6738 +2025-11-11 12:39:46.331348: val_loss -0.675 +2025-11-11 12:39:46.332702: Pseudo dice [np.float32(0.9017), np.float32(0.6938), np.float32(0.6975), np.float32(0.621), np.float32(0.839), np.float32(0.7728), np.float32(0.8613), np.float32(0.8379), np.float32(0.9599), np.float32(0.9555), np.float32(0.9619), np.float32(0.8072), np.float32(0.709), np.float32(0.8428), np.float32(0.9418), np.float32(0.4057), np.float32(0.2837)] +2025-11-11 12:39:46.334409: Epoch time: 258.66 s +2025-11-11 12:39:48.222551: +2025-11-11 12:39:48.224279: Epoch 144 +2025-11-11 12:39:48.225921: Current learning rate: 0.00869 +2025-11-11 12:44:07.295223: train_loss -0.672 +2025-11-11 12:44:07.299537: val_loss -0.6733 +2025-11-11 12:44:07.301200: Pseudo dice [np.float32(0.8852), np.float32(0.7593), np.float32(0.7064), np.float32(0.5637), np.float32(0.8524), np.float32(0.7471), np.float32(0.8824), np.float32(0.8396), np.float32(0.9574), np.float32(0.9558), np.float32(0.9639), np.float32(0.7885), np.float32(0.731), np.float32(0.8571), np.float32(0.9439), np.float32(0.2603), np.float32(0.3362)] +2025-11-11 12:44:07.303235: Epoch time: 259.08 s +2025-11-11 12:44:09.188766: +2025-11-11 12:44:09.190731: Epoch 145 +2025-11-11 12:44:09.192268: Current learning rate: 0.00868 +2025-11-11 12:48:27.528258: train_loss -0.6785 +2025-11-11 12:48:27.534484: val_loss -0.7035 +2025-11-11 12:48:27.536131: Pseudo dice [np.float32(0.9065), np.float32(0.7563), np.float32(0.7063), np.float32(0.6404), np.float32(0.8515), np.float32(0.7783), np.float32(0.8841), np.float32(0.8439), np.float32(0.9712), np.float32(0.9731), np.float32(0.9659), np.float32(0.8128), np.float32(0.7502), np.float32(0.8592), np.float32(0.9543), np.float32(0.4643), np.float32(0.359)] +2025-11-11 12:48:27.537652: Epoch time: 258.34 s +2025-11-11 12:48:30.784487: +2025-11-11 12:48:30.787352: Epoch 146 +2025-11-11 12:48:30.789267: Current learning rate: 0.00868 +2025-11-11 12:52:49.571412: train_loss -0.6674 +2025-11-11 12:52:49.576594: val_loss -0.6932 +2025-11-11 12:52:49.578552: Pseudo dice [np.float32(0.9104), np.float32(0.7275), np.float32(0.6959), np.float32(0.6154), np.float32(0.8443), np.float32(0.7763), np.float32(0.8764), np.float32(0.8476), np.float32(0.9604), np.float32(0.9523), np.float32(0.9653), np.float32(0.8069), np.float32(0.7184), np.float32(0.8538), np.float32(0.9502), np.float32(0.4146), np.float32(0.235)] +2025-11-11 12:52:49.579862: Epoch time: 258.79 s +2025-11-11 12:52:51.470504: +2025-11-11 12:52:51.471884: Epoch 147 +2025-11-11 12:52:51.474143: Current learning rate: 0.00867 +2025-11-11 12:57:10.052799: train_loss -0.6768 +2025-11-11 12:57:10.060567: val_loss -0.6869 +2025-11-11 12:57:10.062911: Pseudo dice [np.float32(0.8996), np.float32(0.7363), np.float32(0.6872), np.float32(0.623), np.float32(0.8553), np.float32(0.7681), np.float32(0.886), np.float32(0.8373), np.float32(0.9532), np.float32(0.9552), np.float32(0.9666), np.float32(0.7919), np.float32(0.7265), np.float32(0.8559), np.float32(0.9505), np.float32(0.4554), np.float32(0.3138)] +2025-11-11 12:57:10.064508: Epoch time: 258.59 s +2025-11-11 12:57:11.965969: +2025-11-11 12:57:11.967427: Epoch 148 +2025-11-11 12:57:11.968725: Current learning rate: 0.00866 +2025-11-11 13:01:30.505553: train_loss -0.6788 +2025-11-11 13:01:30.509475: val_loss -0.6916 +2025-11-11 13:01:30.510891: Pseudo dice [np.float32(0.8969), np.float32(0.7212), np.float32(0.7077), np.float32(0.6276), np.float32(0.8545), np.float32(0.7631), np.float32(0.8852), np.float32(0.8466), np.float32(0.9695), np.float32(0.9691), np.float32(0.9665), np.float32(0.8088), np.float32(0.7329), np.float32(0.8649), np.float32(0.9561), np.float32(0.35), np.float32(0.3671)] +2025-11-11 13:01:30.512030: Epoch time: 258.55 s +2025-11-11 13:01:32.441905: +2025-11-11 13:01:32.443630: Epoch 149 +2025-11-11 13:01:32.445589: Current learning rate: 0.00865 +2025-11-11 13:05:50.913724: train_loss -0.6685 +2025-11-11 13:05:50.919677: val_loss -0.6936 +2025-11-11 13:05:50.921303: Pseudo dice [np.float32(0.8965), np.float32(0.7477), np.float32(0.7267), np.float32(0.6461), np.float32(0.8411), np.float32(0.7819), np.float32(0.8568), np.float32(0.8369), np.float32(0.9636), np.float32(0.967), np.float32(0.9654), np.float32(0.7838), np.float32(0.7197), np.float32(0.8583), np.float32(0.953), np.float32(0.4167), np.float32(0.2891)] +2025-11-11 13:05:50.922894: Epoch time: 258.48 s +2025-11-11 13:05:55.716580: +2025-11-11 13:05:55.718480: Epoch 150 +2025-11-11 13:05:55.720285: Current learning rate: 0.00864 +2025-11-11 13:10:14.215514: train_loss -0.6748 +2025-11-11 13:10:14.221449: val_loss -0.6811 +2025-11-11 13:10:14.223316: Pseudo dice [np.float32(0.8968), np.float32(0.7517), np.float32(0.6965), np.float32(0.6301), np.float32(0.8392), np.float32(0.773), np.float32(0.8591), np.float32(0.8416), np.float32(0.951), np.float32(0.9467), np.float32(0.964), np.float32(0.8216), np.float32(0.7217), np.float32(0.8528), np.float32(0.9406), np.float32(0.3314), np.float32(0.2407)] +2025-11-11 13:10:14.225005: Epoch time: 258.5 s +2025-11-11 13:10:16.049285: +2025-11-11 13:10:16.050795: Epoch 151 +2025-11-11 13:10:16.052333: Current learning rate: 0.00863 +2025-11-11 13:14:34.397709: train_loss -0.6717 +2025-11-11 13:14:34.401944: val_loss -0.6794 +2025-11-11 13:14:34.403264: Pseudo dice [np.float32(0.8979), np.float32(0.7421), np.float32(0.7049), np.float32(0.6133), np.float32(0.844), np.float32(0.7639), np.float32(0.8585), np.float32(0.851), np.float32(0.9691), np.float32(0.9643), np.float32(0.9606), np.float32(0.7988), np.float32(0.746), np.float32(0.8504), np.float32(0.9502), np.float32(0.4155), np.float32(0.3399)] +2025-11-11 13:14:34.404592: Epoch time: 258.35 s +2025-11-11 13:14:36.252291: +2025-11-11 13:14:36.253934: Epoch 152 +2025-11-11 13:14:36.255643: Current learning rate: 0.00862 +2025-11-11 13:18:54.791011: train_loss -0.6699 +2025-11-11 13:18:54.794665: val_loss -0.6831 +2025-11-11 13:18:54.795814: Pseudo dice [np.float32(0.903), np.float32(0.6656), np.float32(0.6831), np.float32(0.6322), np.float32(0.839), np.float32(0.7848), np.float32(0.8772), np.float32(0.8224), np.float32(0.961), np.float32(0.9627), np.float32(0.966), np.float32(0.7935), np.float32(0.7409), np.float32(0.8501), np.float32(0.9565), np.float32(0.3516), np.float32(0.3827)] +2025-11-11 13:18:54.797006: Epoch time: 258.54 s +2025-11-11 13:18:56.659717: +2025-11-11 13:18:56.661752: Epoch 153 +2025-11-11 13:18:56.663237: Current learning rate: 0.00861 +2025-11-11 13:23:15.179536: train_loss -0.6753 +2025-11-11 13:23:15.184065: val_loss -0.6812 +2025-11-11 13:23:15.185660: Pseudo dice [np.float32(0.9115), np.float32(0.6465), np.float32(0.6857), np.float32(0.6062), np.float32(0.8402), np.float32(0.7881), np.float32(0.84), np.float32(0.8336), np.float32(0.9626), np.float32(0.9576), np.float32(0.9628), np.float32(0.801), np.float32(0.7463), np.float32(0.8592), np.float32(0.9346), np.float32(0.3768), np.float32(0.3582)] +2025-11-11 13:23:15.187393: Epoch time: 258.53 s +2025-11-11 13:23:17.075707: +2025-11-11 13:23:17.077258: Epoch 154 +2025-11-11 13:23:17.078506: Current learning rate: 0.0086 +2025-11-11 13:27:35.407717: train_loss -0.6759 +2025-11-11 13:27:35.413065: val_loss -0.6877 +2025-11-11 13:27:35.414839: Pseudo dice [np.float32(0.9055), np.float32(0.7314), np.float32(0.6752), np.float32(0.6238), np.float32(0.847), np.float32(0.7735), np.float32(0.8645), np.float32(0.842), np.float32(0.9614), np.float32(0.9605), np.float32(0.9635), np.float32(0.799), np.float32(0.7126), np.float32(0.8503), np.float32(0.9288), np.float32(0.3806), np.float32(0.3649)] +2025-11-11 13:27:35.416091: Epoch time: 258.34 s +2025-11-11 13:27:37.265109: +2025-11-11 13:27:37.266617: Epoch 155 +2025-11-11 13:27:37.268135: Current learning rate: 0.00859 +2025-11-11 13:31:56.757480: train_loss -0.6809 +2025-11-11 13:31:56.762494: val_loss -0.6757 +2025-11-11 13:31:56.764173: Pseudo dice [np.float32(0.8882), np.float32(0.7424), np.float32(0.6924), np.float32(0.6017), np.float32(0.843), np.float32(0.7667), np.float32(0.8853), np.float32(0.8292), np.float32(0.9629), np.float32(0.962), np.float32(0.9656), np.float32(0.8112), np.float32(0.7143), np.float32(0.8573), np.float32(0.9572), np.float32(0.3347), np.float32(0.3156)] +2025-11-11 13:31:56.765884: Epoch time: 259.5 s +2025-11-11 13:31:58.696234: +2025-11-11 13:31:58.697683: Epoch 156 +2025-11-11 13:31:58.699677: Current learning rate: 0.00858 +2025-11-11 13:36:17.320968: train_loss -0.6694 +2025-11-11 13:36:17.326992: val_loss -0.6903 +2025-11-11 13:36:17.329576: Pseudo dice [np.float32(0.9022), np.float32(0.7334), np.float32(0.6787), np.float32(0.6035), np.float32(0.8517), np.float32(0.7617), np.float32(0.8748), np.float32(0.8393), np.float32(0.9633), np.float32(0.9613), np.float32(0.9666), np.float32(0.8024), np.float32(0.7389), np.float32(0.8624), np.float32(0.9584), np.float32(0.3513), np.float32(0.4029)] +2025-11-11 13:36:17.331643: Epoch time: 258.63 s +2025-11-11 13:36:19.261088: +2025-11-11 13:36:19.263795: Epoch 157 +2025-11-11 13:36:19.266249: Current learning rate: 0.00858 +2025-11-11 13:40:37.690060: train_loss -0.6778 +2025-11-11 13:40:37.695165: val_loss -0.6856 +2025-11-11 13:40:37.696835: Pseudo dice [np.float32(0.8948), np.float32(0.7313), np.float32(0.7074), np.float32(0.6286), np.float32(0.8497), np.float32(0.774), np.float32(0.854), np.float32(0.8376), np.float32(0.956), np.float32(0.9637), np.float32(0.9618), np.float32(0.7927), np.float32(0.7284), np.float32(0.8574), np.float32(0.9421), np.float32(0.3574), np.float32(0.3524)] +2025-11-11 13:40:37.699304: Epoch time: 258.43 s +2025-11-11 13:40:39.578823: +2025-11-11 13:40:39.580613: Epoch 158 +2025-11-11 13:40:39.582346: Current learning rate: 0.00857 +2025-11-11 13:44:58.373286: train_loss -0.6668 +2025-11-11 13:44:58.378591: val_loss -0.6808 +2025-11-11 13:44:58.380496: Pseudo dice [np.float32(0.8992), np.float32(0.7151), np.float32(0.6877), np.float32(0.6108), np.float32(0.8391), np.float32(0.7914), np.float32(0.8044), np.float32(0.8477), np.float32(0.9465), np.float32(0.9423), np.float32(0.9643), np.float32(0.8084), np.float32(0.7304), np.float32(0.8582), np.float32(0.944), np.float32(0.3698), np.float32(0.4138)] +2025-11-11 13:44:58.382510: Epoch time: 258.8 s +2025-11-11 13:45:00.292284: +2025-11-11 13:45:00.294182: Epoch 159 +2025-11-11 13:45:00.295823: Current learning rate: 0.00856 +2025-11-11 13:49:18.737819: train_loss -0.6791 +2025-11-11 13:49:18.745493: val_loss -0.6918 +2025-11-11 13:49:18.748067: Pseudo dice [np.float32(0.9044), np.float32(0.7584), np.float32(0.7328), np.float32(0.6028), np.float32(0.8443), np.float32(0.7659), np.float32(0.8716), np.float32(0.8474), np.float32(0.9668), np.float32(0.9667), np.float32(0.9651), np.float32(0.805), np.float32(0.754), np.float32(0.859), np.float32(0.9515), np.float32(0.3575), np.float32(0.3705)] +2025-11-11 13:49:18.749969: Epoch time: 258.45 s +2025-11-11 13:49:20.672368: +2025-11-11 13:49:20.674109: Epoch 160 +2025-11-11 13:49:20.675611: Current learning rate: 0.00855 +2025-11-11 13:53:39.380991: train_loss -0.6777 +2025-11-11 13:53:39.386061: val_loss -0.683 +2025-11-11 13:53:39.387928: Pseudo dice [np.float32(0.9008), np.float32(0.7358), np.float32(0.6997), np.float32(0.5855), np.float32(0.8546), np.float32(0.7723), np.float32(0.8778), np.float32(0.8387), np.float32(0.9663), np.float32(0.9704), np.float32(0.9658), np.float32(0.8056), np.float32(0.7242), np.float32(0.8621), np.float32(0.9504), np.float32(0.2861), np.float32(0.3276)] +2025-11-11 13:53:39.389474: Epoch time: 258.71 s +2025-11-11 13:53:41.407339: +2025-11-11 13:53:41.409007: Epoch 161 +2025-11-11 13:53:41.410574: Current learning rate: 0.00854 +2025-11-11 13:58:00.240347: train_loss -0.6738 +2025-11-11 13:58:00.244909: val_loss -0.686 +2025-11-11 13:58:00.246659: Pseudo dice [np.float32(0.9098), np.float32(0.6533), np.float32(0.6724), np.float32(0.6164), np.float32(0.841), np.float32(0.7657), np.float32(0.887), np.float32(0.8297), np.float32(0.9678), np.float32(0.9747), np.float32(0.9647), np.float32(0.8145), np.float32(0.7146), np.float32(0.851), np.float32(0.9578), np.float32(0.3951), np.float32(0.3015)] +2025-11-11 13:58:00.247978: Epoch time: 258.84 s +2025-11-11 13:58:02.128916: +2025-11-11 13:58:02.130486: Epoch 162 +2025-11-11 13:58:02.132454: Current learning rate: 0.00853 +2025-11-11 14:02:20.842017: train_loss -0.6821 +2025-11-11 14:02:20.847408: val_loss -0.6982 +2025-11-11 14:02:20.849095: Pseudo dice [np.float32(0.912), np.float32(0.6961), np.float32(0.6936), np.float32(0.6312), np.float32(0.8547), np.float32(0.7609), np.float32(0.882), np.float32(0.8538), np.float32(0.9737), np.float32(0.9703), np.float32(0.9687), np.float32(0.8115), np.float32(0.7399), np.float32(0.8612), np.float32(0.957), np.float32(0.352), np.float32(0.336)] +2025-11-11 14:02:20.850802: Epoch time: 258.72 s +2025-11-11 14:02:22.752789: +2025-11-11 14:02:22.754477: Epoch 163 +2025-11-11 14:02:22.755835: Current learning rate: 0.00852 +2025-11-11 14:06:41.328405: train_loss -0.6809 +2025-11-11 14:06:41.334862: val_loss -0.6883 +2025-11-11 14:06:41.337182: Pseudo dice [np.float32(0.9185), np.float32(0.7423), np.float32(0.7084), np.float32(0.6135), np.float32(0.8343), np.float32(0.7481), np.float32(0.8709), np.float32(0.8318), np.float32(0.9743), np.float32(0.972), np.float32(0.9659), np.float32(0.7871), np.float32(0.7439), np.float32(0.8518), np.float32(0.9585), np.float32(0.4096), np.float32(0.3416)] +2025-11-11 14:06:41.339470: Epoch time: 258.58 s +2025-11-11 14:06:43.145378: +2025-11-11 14:06:43.147161: Epoch 164 +2025-11-11 14:06:43.149050: Current learning rate: 0.00851 +2025-11-11 14:11:02.781370: train_loss -0.6777 +2025-11-11 14:11:02.786633: val_loss -0.6815 +2025-11-11 14:11:02.788143: Pseudo dice [np.float32(0.8981), np.float32(0.7309), np.float32(0.7145), np.float32(0.6385), np.float32(0.8443), np.float32(0.7588), np.float32(0.8681), np.float32(0.8367), np.float32(0.9513), np.float32(0.9516), np.float32(0.9639), np.float32(0.8033), np.float32(0.7469), np.float32(0.8476), np.float32(0.9441), np.float32(0.382), np.float32(0.3037)] +2025-11-11 14:11:02.789377: Epoch time: 259.64 s +2025-11-11 14:11:04.709636: +2025-11-11 14:11:04.711056: Epoch 165 +2025-11-11 14:11:04.712418: Current learning rate: 0.0085 +2025-11-11 14:15:23.253890: train_loss -0.672 +2025-11-11 14:15:23.258720: val_loss -0.6753 +2025-11-11 14:15:23.260159: Pseudo dice [np.float32(0.8879), np.float32(0.6392), np.float32(0.6554), np.float32(0.6068), np.float32(0.8321), np.float32(0.7659), np.float32(0.8856), np.float32(0.8348), np.float32(0.9393), np.float32(0.9379), np.float32(0.9603), np.float32(0.7914), np.float32(0.7213), np.float32(0.8508), np.float32(0.9322), np.float32(0.3953), np.float32(0.3825)] +2025-11-11 14:15:23.261806: Epoch time: 258.55 s +2025-11-11 14:15:25.116014: +2025-11-11 14:15:25.117404: Epoch 166 +2025-11-11 14:15:25.118645: Current learning rate: 0.00849 +2025-11-11 14:19:43.787920: train_loss -0.6718 +2025-11-11 14:19:43.793573: val_loss -0.676 +2025-11-11 14:19:43.795531: Pseudo dice [np.float32(0.8932), np.float32(0.6477), np.float32(0.6458), np.float32(0.627), np.float32(0.8452), np.float32(0.7659), np.float32(0.8637), np.float32(0.8264), np.float32(0.9592), np.float32(0.9518), np.float32(0.9582), np.float32(0.8045), np.float32(0.7426), np.float32(0.8473), np.float32(0.936), np.float32(0.3662), np.float32(0.2933)] +2025-11-11 14:19:43.797466: Epoch time: 258.68 s +2025-11-11 14:19:45.663273: +2025-11-11 14:19:45.664690: Epoch 167 +2025-11-11 14:19:45.665964: Current learning rate: 0.00848 +2025-11-11 14:24:04.470159: train_loss -0.6742 +2025-11-11 14:24:04.475462: val_loss -0.6843 +2025-11-11 14:24:04.477287: Pseudo dice [np.float32(0.8959), np.float32(0.7336), np.float32(0.6856), np.float32(0.6187), np.float32(0.8405), np.float32(0.7633), np.float32(0.8725), np.float32(0.8337), np.float32(0.964), np.float32(0.9599), np.float32(0.965), np.float32(0.7919), np.float32(0.7305), np.float32(0.856), np.float32(0.9524), np.float32(0.3566), np.float32(0.3617)] +2025-11-11 14:24:04.478806: Epoch time: 258.81 s +2025-11-11 14:24:06.397951: +2025-11-11 14:24:06.399590: Epoch 168 +2025-11-11 14:24:06.401705: Current learning rate: 0.00847 +2025-11-11 14:28:25.067744: train_loss -0.6738 +2025-11-11 14:28:25.072819: val_loss -0.6945 +2025-11-11 14:28:25.074446: Pseudo dice [np.float32(0.8956), np.float32(0.7646), np.float32(0.7014), np.float32(0.6108), np.float32(0.8475), np.float32(0.7778), np.float32(0.888), np.float32(0.8351), np.float32(0.9736), np.float32(0.9668), np.float32(0.9639), np.float32(0.8117), np.float32(0.7271), np.float32(0.8647), np.float32(0.9587), np.float32(0.3667), np.float32(0.365)] +2025-11-11 14:28:25.075639: Epoch time: 258.68 s +2025-11-11 14:28:26.997923: +2025-11-11 14:28:26.999388: Epoch 169 +2025-11-11 14:28:27.000810: Current learning rate: 0.00847 +2025-11-11 14:32:45.450726: train_loss -0.6803 +2025-11-11 14:32:45.454701: val_loss -0.6923 +2025-11-11 14:32:45.456367: Pseudo dice [np.float32(0.9085), np.float32(0.7619), np.float32(0.678), np.float32(0.5973), np.float32(0.8422), np.float32(0.752), np.float32(0.8703), np.float32(0.8385), np.float32(0.9648), np.float32(0.9674), np.float32(0.9669), np.float32(0.799), np.float32(0.7067), np.float32(0.8468), np.float32(0.9522), np.float32(0.4451), np.float32(0.3787)] +2025-11-11 14:32:45.458206: Epoch time: 258.46 s +2025-11-11 14:32:47.345409: +2025-11-11 14:32:47.347988: Epoch 170 +2025-11-11 14:32:47.349257: Current learning rate: 0.00846 +2025-11-11 14:37:05.666666: train_loss -0.6827 +2025-11-11 14:37:05.671546: val_loss -0.6986 +2025-11-11 14:37:05.673095: Pseudo dice [np.float32(0.9066), np.float32(0.7566), np.float32(0.7149), np.float32(0.6157), np.float32(0.8471), np.float32(0.7784), np.float32(0.8684), np.float32(0.8431), np.float32(0.9674), np.float32(0.966), np.float32(0.9666), np.float32(0.8118), np.float32(0.7644), np.float32(0.8607), np.float32(0.9566), np.float32(0.4394), np.float32(0.3668)] +2025-11-11 14:37:05.674487: Epoch time: 258.33 s +2025-11-11 14:37:05.676143: Yayy! New best EMA pseudo Dice: 0.7771000266075134 +2025-11-11 14:37:11.402320: +2025-11-11 14:37:11.405020: Epoch 171 +2025-11-11 14:37:11.407078: Current learning rate: 0.00845 +2025-11-11 14:41:29.704604: train_loss -0.681 +2025-11-11 14:41:29.708968: val_loss -0.6872 +2025-11-11 14:41:29.710565: Pseudo dice [np.float32(0.9122), np.float32(0.7485), np.float32(0.6938), np.float32(0.6208), np.float32(0.836), np.float32(0.7641), np.float32(0.8895), np.float32(0.8425), np.float32(0.9682), np.float32(0.9658), np.float32(0.9649), np.float32(0.8021), np.float32(0.7135), np.float32(0.853), np.float32(0.953), np.float32(0.3366), np.float32(0.2636)] +2025-11-11 14:41:29.711753: Epoch time: 258.31 s +2025-11-11 14:41:31.620584: +2025-11-11 14:41:31.622074: Epoch 172 +2025-11-11 14:41:31.623566: Current learning rate: 0.00844 +2025-11-11 14:45:50.140631: train_loss -0.6845 +2025-11-11 14:45:50.146167: val_loss -0.6916 +2025-11-11 14:45:50.147649: Pseudo dice [np.float32(0.9153), np.float32(0.6189), np.float32(0.6716), np.float32(0.6519), np.float32(0.8504), np.float32(0.7935), np.float32(0.8767), np.float32(0.8459), np.float32(0.9622), np.float32(0.9544), np.float32(0.9665), np.float32(0.8091), np.float32(0.7257), np.float32(0.859), np.float32(0.9512), np.float32(0.3457), np.float32(0.2829)] +2025-11-11 14:45:50.149322: Epoch time: 258.53 s +2025-11-11 14:45:52.106840: +2025-11-11 14:45:52.108292: Epoch 173 +2025-11-11 14:45:52.109651: Current learning rate: 0.00843 +2025-11-11 14:50:13.655682: train_loss -0.6864 +2025-11-11 14:50:13.659798: val_loss -0.6934 +2025-11-11 14:50:13.661219: Pseudo dice [np.float32(0.8987), np.float32(0.7544), np.float32(0.6794), np.float32(0.6452), np.float32(0.854), np.float32(0.7668), np.float32(0.882), np.float32(0.8539), np.float32(0.9627), np.float32(0.9647), np.float32(0.9655), np.float32(0.8084), np.float32(0.7477), np.float32(0.8638), np.float32(0.9549), np.float32(0.3615), np.float32(0.3181)] +2025-11-11 14:50:13.662309: Epoch time: 261.55 s +2025-11-11 14:50:15.519520: +2025-11-11 14:50:15.521211: Epoch 174 +2025-11-11 14:50:15.522784: Current learning rate: 0.00842 +2025-11-11 14:54:33.869796: train_loss -0.6854 +2025-11-11 14:54:33.875342: val_loss -0.6896 +2025-11-11 14:54:33.877652: Pseudo dice [np.float32(0.9101), np.float32(0.7739), np.float32(0.7003), np.float32(0.6015), np.float32(0.8517), np.float32(0.77), np.float32(0.8747), np.float32(0.848), np.float32(0.9386), np.float32(0.9368), np.float32(0.9645), np.float32(0.7902), np.float32(0.7151), np.float32(0.864), np.float32(0.9448), np.float32(0.4104), np.float32(0.3563)] +2025-11-11 14:54:33.880103: Epoch time: 258.36 s +2025-11-11 14:54:35.738485: +2025-11-11 14:54:35.740499: Epoch 175 +2025-11-11 14:54:35.742527: Current learning rate: 0.00841 +2025-11-11 14:58:54.326514: train_loss -0.6793 +2025-11-11 14:58:54.334691: val_loss -0.6943 +2025-11-11 14:58:54.335881: Pseudo dice [np.float32(0.8995), np.float32(0.7645), np.float32(0.7128), np.float32(0.6046), np.float32(0.8522), np.float32(0.7684), np.float32(0.8796), np.float32(0.8398), np.float32(0.9734), np.float32(0.9734), np.float32(0.9664), np.float32(0.8024), np.float32(0.7459), np.float32(0.8613), np.float32(0.9549), np.float32(0.3862), np.float32(0.3388)] +2025-11-11 14:58:54.337545: Epoch time: 258.59 s +2025-11-11 14:58:54.339249: Yayy! New best EMA pseudo Dice: 0.777400016784668 +2025-11-11 14:58:59.248928: +2025-11-11 14:58:59.251378: Epoch 176 +2025-11-11 14:58:59.253438: Current learning rate: 0.0084 +2025-11-11 15:03:17.843853: train_loss -0.6776 +2025-11-11 15:03:17.849823: val_loss -0.6933 +2025-11-11 15:03:17.851886: Pseudo dice [np.float32(0.9093), np.float32(0.7389), np.float32(0.6744), np.float32(0.5894), np.float32(0.8516), np.float32(0.786), np.float32(0.8843), np.float32(0.8507), np.float32(0.9735), np.float32(0.9698), np.float32(0.9674), np.float32(0.807), np.float32(0.7553), np.float32(0.8618), np.float32(0.9544), np.float32(0.3879), np.float32(0.3092)] +2025-11-11 15:03:17.854454: Epoch time: 258.6 s +2025-11-11 15:03:17.856183: Yayy! New best EMA pseudo Dice: 0.7778000235557556 +2025-11-11 15:03:22.937222: +2025-11-11 15:03:22.939275: Epoch 177 +2025-11-11 15:03:22.941260: Current learning rate: 0.00839 +2025-11-11 15:07:41.532009: train_loss -0.6766 +2025-11-11 15:07:41.539054: val_loss -0.6864 +2025-11-11 15:07:41.541177: Pseudo dice [np.float32(0.9072), np.float32(0.749), np.float32(0.7102), np.float32(0.6429), np.float32(0.8443), np.float32(0.7756), np.float32(0.8348), np.float32(0.8352), np.float32(0.9721), np.float32(0.9742), np.float32(0.9654), np.float32(0.8075), np.float32(0.7191), np.float32(0.8548), np.float32(0.9542), np.float32(0.3887), np.float32(0.3711)] +2025-11-11 15:07:41.542951: Epoch time: 258.61 s +2025-11-11 15:07:41.544353: Yayy! New best EMA pseudo Dice: 0.7782999873161316 +2025-11-11 15:07:46.546842: +2025-11-11 15:07:46.548348: Epoch 178 +2025-11-11 15:07:46.549825: Current learning rate: 0.00838 +2025-11-11 15:12:05.122603: train_loss -0.6865 +2025-11-11 15:12:05.127109: val_loss -0.6867 +2025-11-11 15:12:05.128477: Pseudo dice [np.float32(0.9043), np.float32(0.7371), np.float32(0.6886), np.float32(0.6136), np.float32(0.8492), np.float32(0.7676), np.float32(0.8788), np.float32(0.8389), np.float32(0.9671), np.float32(0.9644), np.float32(0.9676), np.float32(0.8004), np.float32(0.7329), np.float32(0.856), np.float32(0.9558), np.float32(0.2688), np.float32(0.272)] +2025-11-11 15:12:05.130692: Epoch time: 258.58 s +2025-11-11 15:12:07.062060: +2025-11-11 15:12:07.063535: Epoch 179 +2025-11-11 15:12:07.065080: Current learning rate: 0.00837 +2025-11-11 15:16:25.709887: train_loss -0.6849 +2025-11-11 15:16:25.715019: val_loss -0.706 +2025-11-11 15:16:25.716910: Pseudo dice [np.float32(0.9124), np.float32(0.7566), np.float32(0.7036), np.float32(0.5949), np.float32(0.8525), np.float32(0.7614), np.float32(0.8684), np.float32(0.8471), np.float32(0.9706), np.float32(0.9717), np.float32(0.9673), np.float32(0.8221), np.float32(0.7585), np.float32(0.8576), np.float32(0.9571), np.float32(0.4045), np.float32(0.4245)] +2025-11-11 15:16:25.718432: Epoch time: 258.65 s +2025-11-11 15:16:25.727263: Yayy! New best EMA pseudo Dice: 0.7785000205039978 +2025-11-11 15:16:30.708046: +2025-11-11 15:16:30.710055: Epoch 180 +2025-11-11 15:16:30.711858: Current learning rate: 0.00836 +2025-11-11 15:20:49.240165: train_loss -0.6855 +2025-11-11 15:20:49.248210: val_loss -0.6807 +2025-11-11 15:20:49.250872: Pseudo dice [np.float32(0.9129), np.float32(0.7421), np.float32(0.7005), np.float32(0.6368), np.float32(0.8511), np.float32(0.7627), np.float32(0.8432), np.float32(0.846), np.float32(0.9264), np.float32(0.9259), np.float32(0.9604), np.float32(0.8002), np.float32(0.7392), np.float32(0.8561), np.float32(0.9251), np.float32(0.4119), np.float32(0.3595)] +2025-11-11 15:20:49.253295: Epoch time: 258.54 s +2025-11-11 15:20:51.134492: +2025-11-11 15:20:51.136543: Epoch 181 +2025-11-11 15:20:51.138346: Current learning rate: 0.00836 +2025-11-11 15:25:09.720734: train_loss -0.6814 +2025-11-11 15:25:09.728252: val_loss -0.6915 +2025-11-11 15:25:09.729878: Pseudo dice [np.float32(0.9076), np.float32(0.7339), np.float32(0.6987), np.float32(0.6262), np.float32(0.8544), np.float32(0.7685), np.float32(0.9023), np.float32(0.8472), np.float32(0.9712), np.float32(0.9677), np.float32(0.9663), np.float32(0.8079), np.float32(0.7437), np.float32(0.8571), np.float32(0.9564), np.float32(0.3889), np.float32(0.3747)] +2025-11-11 15:25:09.731421: Epoch time: 258.59 s +2025-11-11 15:25:09.732563: Yayy! New best EMA pseudo Dice: 0.77920001745224 +2025-11-11 15:25:15.918117: +2025-11-11 15:25:15.919939: Epoch 182 +2025-11-11 15:25:15.921785: Current learning rate: 0.00835 +2025-11-11 15:29:34.428294: train_loss -0.6724 +2025-11-11 15:29:34.436262: val_loss -0.679 +2025-11-11 15:29:34.438347: Pseudo dice [np.float32(0.9039), np.float32(0.6934), np.float32(0.6993), np.float32(0.5774), np.float32(0.8399), np.float32(0.7635), np.float32(0.8764), np.float32(0.848), np.float32(0.9532), np.float32(0.9445), np.float32(0.961), np.float32(0.7992), np.float32(0.7334), np.float32(0.8467), np.float32(0.933), np.float32(0.3723), np.float32(0.2982)] +2025-11-11 15:29:34.440505: Epoch time: 258.52 s +2025-11-11 15:29:36.292107: +2025-11-11 15:29:36.294107: Epoch 183 +2025-11-11 15:29:36.296024: Current learning rate: 0.00834 +2025-11-11 15:33:54.882730: train_loss -0.672 +2025-11-11 15:33:54.887765: val_loss -0.6968 +2025-11-11 15:33:54.889017: Pseudo dice [np.float32(0.9031), np.float32(0.761), np.float32(0.7005), np.float32(0.6035), np.float32(0.8575), np.float32(0.7869), np.float32(0.884), np.float32(0.8522), np.float32(0.9592), np.float32(0.9653), np.float32(0.9647), np.float32(0.8032), np.float32(0.7379), np.float32(0.8665), np.float32(0.9473), np.float32(0.3634), np.float32(0.3215)] +2025-11-11 15:33:54.890333: Epoch time: 258.6 s +2025-11-11 15:33:56.813301: +2025-11-11 15:33:56.814955: Epoch 184 +2025-11-11 15:33:56.816481: Current learning rate: 0.00833 +2025-11-11 15:38:15.343727: train_loss -0.6844 +2025-11-11 15:38:15.348195: val_loss -0.6909 +2025-11-11 15:38:15.349579: Pseudo dice [np.float32(0.9002), np.float32(0.7279), np.float32(0.6813), np.float32(0.6012), np.float32(0.8568), np.float32(0.7666), np.float32(0.8588), np.float32(0.8351), np.float32(0.9712), np.float32(0.9674), np.float32(0.9661), np.float32(0.8066), np.float32(0.6927), np.float32(0.8649), np.float32(0.9608), np.float32(0.4324), np.float32(0.4412)] +2025-11-11 15:38:15.351259: Epoch time: 258.54 s +2025-11-11 15:38:17.226527: +2025-11-11 15:38:17.227949: Epoch 185 +2025-11-11 15:38:17.229233: Current learning rate: 0.00832 +2025-11-11 15:42:35.369294: train_loss -0.6828 +2025-11-11 15:42:35.375184: val_loss -0.6934 +2025-11-11 15:42:35.377297: Pseudo dice [np.float32(0.9022), np.float32(0.748), np.float32(0.6854), np.float32(0.5749), np.float32(0.8532), np.float32(0.7851), np.float32(0.8865), np.float32(0.8407), np.float32(0.9711), np.float32(0.9705), np.float32(0.9666), np.float32(0.8053), np.float32(0.7324), np.float32(0.8646), np.float32(0.9571), np.float32(0.3214), np.float32(0.3412)] +2025-11-11 15:42:35.378778: Epoch time: 258.15 s +2025-11-11 15:42:37.285458: +2025-11-11 15:42:37.286983: Epoch 186 +2025-11-11 15:42:37.288356: Current learning rate: 0.00831 +2025-11-11 15:46:55.501739: train_loss -0.6827 +2025-11-11 15:46:55.508739: val_loss -0.6843 +2025-11-11 15:46:55.511289: Pseudo dice [np.float32(0.911), np.float32(0.7432), np.float32(0.6857), np.float32(0.6179), np.float32(0.8534), np.float32(0.7732), np.float32(0.8738), np.float32(0.8536), np.float32(0.9665), np.float32(0.9651), np.float32(0.9657), np.float32(0.8183), np.float32(0.7073), np.float32(0.857), np.float32(0.9553), np.float32(0.3604), np.float32(0.2989)] +2025-11-11 15:46:55.513527: Epoch time: 258.22 s +2025-11-11 15:46:57.388770: +2025-11-11 15:46:57.390380: Epoch 187 +2025-11-11 15:46:57.392027: Current learning rate: 0.0083 +2025-11-11 15:51:15.777338: train_loss -0.6793 +2025-11-11 15:51:15.782315: val_loss -0.6922 +2025-11-11 15:51:15.783764: Pseudo dice [np.float32(0.905), np.float32(0.7058), np.float32(0.6989), np.float32(0.5964), np.float32(0.8518), np.float32(0.7885), np.float32(0.8705), np.float32(0.8477), np.float32(0.9745), np.float32(0.9673), np.float32(0.9669), np.float32(0.8146), np.float32(0.7336), np.float32(0.8651), np.float32(0.9541), np.float32(0.3495), np.float32(0.2985)] +2025-11-11 15:51:15.785004: Epoch time: 258.39 s +2025-11-11 15:51:17.669164: +2025-11-11 15:51:17.671394: Epoch 188 +2025-11-11 15:51:17.673214: Current learning rate: 0.00829 +2025-11-11 15:55:36.023906: train_loss -0.6816 +2025-11-11 15:55:36.028286: val_loss -0.6905 +2025-11-11 15:55:36.029705: Pseudo dice [np.float32(0.8969), np.float32(0.7392), np.float32(0.6537), np.float32(0.6197), np.float32(0.8499), np.float32(0.765), np.float32(0.8892), np.float32(0.8487), np.float32(0.9718), np.float32(0.9672), np.float32(0.9658), np.float32(0.8034), np.float32(0.7385), np.float32(0.8576), np.float32(0.9554), np.float32(0.3671), np.float32(0.3409)] +2025-11-11 15:55:36.030846: Epoch time: 258.36 s +2025-11-11 15:55:37.891513: +2025-11-11 15:55:37.893022: Epoch 189 +2025-11-11 15:55:37.894469: Current learning rate: 0.00828 +2025-11-11 15:59:56.283355: train_loss -0.6761 +2025-11-11 15:59:56.292318: val_loss -0.7032 +2025-11-11 15:59:56.294134: Pseudo dice [np.float32(0.9085), np.float32(0.7672), np.float32(0.7137), np.float32(0.6031), np.float32(0.8482), np.float32(0.7838), np.float32(0.8861), np.float32(0.8412), np.float32(0.9676), np.float32(0.964), np.float32(0.9655), np.float32(0.8114), np.float32(0.7352), np.float32(0.8593), np.float32(0.95), np.float32(0.4282), np.float32(0.3855)] +2025-11-11 15:59:56.296086: Epoch time: 258.4 s +2025-11-11 15:59:56.298006: Yayy! New best EMA pseudo Dice: 0.7792999744415283 +2025-11-11 16:00:01.217396: +2025-11-11 16:00:01.219097: Epoch 190 +2025-11-11 16:00:01.220934: Current learning rate: 0.00827 +2025-11-11 16:04:19.837169: train_loss -0.6755 +2025-11-11 16:04:19.843602: val_loss -0.685 +2025-11-11 16:04:19.845256: Pseudo dice [np.float32(0.9063), np.float32(0.7063), np.float32(0.6612), np.float32(0.587), np.float32(0.8501), np.float32(0.7612), np.float32(0.8652), np.float32(0.8433), np.float32(0.9691), np.float32(0.968), np.float32(0.9658), np.float32(0.8007), np.float32(0.7021), np.float32(0.8655), np.float32(0.9545), np.float32(0.3097), np.float32(0.3334)] +2025-11-11 16:04:19.846610: Epoch time: 258.62 s +2025-11-11 16:04:23.055908: +2025-11-11 16:04:23.057535: Epoch 191 +2025-11-11 16:04:23.059695: Current learning rate: 0.00826 +2025-11-11 16:08:41.740942: train_loss -0.6789 +2025-11-11 16:08:41.747576: val_loss -0.6919 +2025-11-11 16:08:41.749991: Pseudo dice [np.float32(0.9077), np.float32(0.7103), np.float32(0.6887), np.float32(0.6424), np.float32(0.8494), np.float32(0.7698), np.float32(0.8777), np.float32(0.8517), np.float32(0.9646), np.float32(0.9729), np.float32(0.9656), np.float32(0.8075), np.float32(0.7628), np.float32(0.866), np.float32(0.95), np.float32(0.3367), np.float32(0.3165)] +2025-11-11 16:08:41.752813: Epoch time: 258.69 s +2025-11-11 16:08:43.644864: +2025-11-11 16:08:43.646830: Epoch 192 +2025-11-11 16:08:43.649193: Current learning rate: 0.00825 +2025-11-11 16:13:02.416036: train_loss -0.6746 +2025-11-11 16:13:02.420164: val_loss -0.6806 +2025-11-11 16:13:02.421516: Pseudo dice [np.float32(0.8989), np.float32(0.6503), np.float32(0.6553), np.float32(0.6353), np.float32(0.8548), np.float32(0.7769), np.float32(0.8587), np.float32(0.8308), np.float32(0.9548), np.float32(0.9569), np.float32(0.9624), np.float32(0.8104), np.float32(0.7251), np.float32(0.8642), np.float32(0.9358), np.float32(0.321), np.float32(0.3303)] +2025-11-11 16:13:02.422811: Epoch time: 258.78 s +2025-11-11 16:13:04.343436: +2025-11-11 16:13:04.344824: Epoch 193 +2025-11-11 16:13:04.346466: Current learning rate: 0.00824 +2025-11-11 16:17:23.447154: train_loss -0.6787 +2025-11-11 16:17:23.451194: val_loss -0.6898 +2025-11-11 16:17:23.452843: Pseudo dice [np.float32(0.9185), np.float32(0.7502), np.float32(0.69), np.float32(0.6566), np.float32(0.8491), np.float32(0.7678), np.float32(0.8925), np.float32(0.8528), np.float32(0.9628), np.float32(0.9593), np.float32(0.9668), np.float32(0.8083), np.float32(0.7498), np.float32(0.8554), np.float32(0.9602), np.float32(0.3039), np.float32(0.2754)] +2025-11-11 16:17:23.454010: Epoch time: 259.11 s +2025-11-11 16:17:25.370759: +2025-11-11 16:17:25.372942: Epoch 194 +2025-11-11 16:17:25.374978: Current learning rate: 0.00824 +2025-11-11 16:21:44.610760: train_loss -0.6801 +2025-11-11 16:21:44.617495: val_loss -0.6951 +2025-11-11 16:21:44.619670: Pseudo dice [np.float32(0.9026), np.float32(0.7491), np.float32(0.6917), np.float32(0.6121), np.float32(0.8467), np.float32(0.7655), np.float32(0.8669), np.float32(0.8441), np.float32(0.9742), np.float32(0.9742), np.float32(0.965), np.float32(0.7948), np.float32(0.7551), np.float32(0.8593), np.float32(0.9557), np.float32(0.4312), np.float32(0.3657)] +2025-11-11 16:21:44.621808: Epoch time: 259.25 s +2025-11-11 16:21:46.517957: +2025-11-11 16:21:46.520609: Epoch 195 +2025-11-11 16:21:46.523036: Current learning rate: 0.00823 +2025-11-11 16:26:05.389474: train_loss -0.6704 +2025-11-11 16:26:05.394967: val_loss -0.6807 +2025-11-11 16:26:05.397010: Pseudo dice [np.float32(0.9115), np.float32(0.7391), np.float32(0.6894), np.float32(0.638), np.float32(0.8495), np.float32(0.7705), np.float32(0.8733), np.float32(0.842), np.float32(0.971), np.float32(0.9716), np.float32(0.9638), np.float32(0.799), np.float32(0.7223), np.float32(0.8557), np.float32(0.9463), np.float32(0.3331), np.float32(0.2397)] +2025-11-11 16:26:05.398984: Epoch time: 258.88 s +2025-11-11 16:26:07.322224: +2025-11-11 16:26:07.323800: Epoch 196 +2025-11-11 16:26:07.325253: Current learning rate: 0.00822 +2025-11-11 16:30:26.011976: train_loss -0.6784 +2025-11-11 16:30:26.018758: val_loss -0.7016 +2025-11-11 16:30:26.020683: Pseudo dice [np.float32(0.8931), np.float32(0.7448), np.float32(0.707), np.float32(0.6245), np.float32(0.852), np.float32(0.7672), np.float32(0.8947), np.float32(0.8539), np.float32(0.9708), np.float32(0.9677), np.float32(0.968), np.float32(0.807), np.float32(0.7249), np.float32(0.8603), np.float32(0.9604), np.float32(0.3746), np.float32(0.4377)] +2025-11-11 16:30:26.022392: Epoch time: 258.7 s +2025-11-11 16:30:27.877863: +2025-11-11 16:30:27.879678: Epoch 197 +2025-11-11 16:30:27.880883: Current learning rate: 0.00821 +2025-11-11 16:34:46.620683: train_loss -0.6865 +2025-11-11 16:34:46.627086: val_loss -0.6935 +2025-11-11 16:34:46.628958: Pseudo dice [np.float32(0.9067), np.float32(0.7681), np.float32(0.6892), np.float32(0.6161), np.float32(0.8457), np.float32(0.777), np.float32(0.8888), np.float32(0.845), np.float32(0.967), np.float32(0.9629), np.float32(0.9676), np.float32(0.8066), np.float32(0.739), np.float32(0.8538), np.float32(0.9537), np.float32(0.3756), np.float32(0.3708)] +2025-11-11 16:34:46.630842: Epoch time: 258.75 s +2025-11-11 16:34:48.514140: +2025-11-11 16:34:48.515596: Epoch 198 +2025-11-11 16:34:48.517097: Current learning rate: 0.0082 +2025-11-11 16:39:07.413870: train_loss -0.6803 +2025-11-11 16:39:07.419951: val_loss -0.7055 +2025-11-11 16:39:07.422122: Pseudo dice [np.float32(0.909), np.float32(0.7809), np.float32(0.6961), np.float32(0.6322), np.float32(0.8598), np.float32(0.7713), np.float32(0.8723), np.float32(0.8571), np.float32(0.9635), np.float32(0.9693), np.float32(0.9655), np.float32(0.8073), np.float32(0.7086), np.float32(0.8661), np.float32(0.9437), np.float32(0.4616), np.float32(0.3318)] +2025-11-11 16:39:07.423952: Epoch time: 258.9 s +2025-11-11 16:39:07.425829: Yayy! New best EMA pseudo Dice: 0.7799000144004822 +2025-11-11 16:39:12.416512: +2025-11-11 16:39:12.418461: Epoch 199 +2025-11-11 16:39:12.420099: Current learning rate: 0.00819 +2025-11-11 16:43:31.169178: train_loss -0.6763 +2025-11-11 16:43:31.176181: val_loss -0.6913 +2025-11-11 16:43:31.178402: Pseudo dice [np.float32(0.9057), np.float32(0.7218), np.float32(0.7156), np.float32(0.6126), np.float32(0.8434), np.float32(0.7776), np.float32(0.8863), np.float32(0.8348), np.float32(0.9715), np.float32(0.9699), np.float32(0.9661), np.float32(0.8017), np.float32(0.7373), np.float32(0.8502), np.float32(0.9517), np.float32(0.3947), np.float32(0.313)] +2025-11-11 16:43:31.180078: Epoch time: 258.76 s +2025-11-11 16:43:37.158391: +2025-11-11 16:43:37.160527: Epoch 200 +2025-11-11 16:43:37.162617: Current learning rate: 0.00818 +2025-11-11 16:47:55.774894: train_loss -0.6893 +2025-11-11 16:47:55.779626: val_loss -0.6885 +2025-11-11 16:47:55.781028: Pseudo dice [np.float32(0.91), np.float32(0.7612), np.float32(0.7031), np.float32(0.6226), np.float32(0.8508), np.float32(0.784), np.float32(0.8552), np.float32(0.8459), np.float32(0.9645), np.float32(0.9645), np.float32(0.9667), np.float32(0.8234), np.float32(0.7033), np.float32(0.8612), np.float32(0.9611), np.float32(0.3058), np.float32(0.3509)] +2025-11-11 16:47:55.782375: Epoch time: 258.62 s +2025-11-11 16:47:57.644567: +2025-11-11 16:47:57.646460: Epoch 201 +2025-11-11 16:47:57.647999: Current learning rate: 0.00817 +2025-11-11 16:52:16.703916: train_loss -0.6763 +2025-11-11 16:52:16.709951: val_loss -0.6889 +2025-11-11 16:52:16.712227: Pseudo dice [np.float32(0.9006), np.float32(0.7197), np.float32(0.7081), np.float32(0.6509), np.float32(0.851), np.float32(0.7835), np.float32(0.8684), np.float32(0.8441), np.float32(0.9472), np.float32(0.9507), np.float32(0.9617), np.float32(0.791), np.float32(0.7363), np.float32(0.8569), np.float32(0.9496), np.float32(0.4125), np.float32(0.3094)] +2025-11-11 16:52:16.714109: Epoch time: 259.06 s +2025-11-11 16:52:18.568726: +2025-11-11 16:52:18.570591: Epoch 202 +2025-11-11 16:52:18.572095: Current learning rate: 0.00816 +2025-11-11 16:56:37.595263: train_loss -0.6771 +2025-11-11 16:56:37.604598: val_loss -0.6764 +2025-11-11 16:56:37.607764: Pseudo dice [np.float32(0.9056), np.float32(0.756), np.float32(0.6901), np.float32(0.612), np.float32(0.8475), np.float32(0.7738), np.float32(0.8806), np.float32(0.8349), np.float32(0.9574), np.float32(0.9407), np.float32(0.9645), np.float32(0.8115), np.float32(0.7293), np.float32(0.8622), np.float32(0.9428), np.float32(0.2957), np.float32(0.2242)] +2025-11-11 16:56:37.610450: Epoch time: 259.03 s +2025-11-11 16:56:39.475869: +2025-11-11 16:56:39.477611: Epoch 203 +2025-11-11 16:56:39.478850: Current learning rate: 0.00815 +2025-11-11 17:00:58.281312: train_loss -0.6794 +2025-11-11 17:00:58.287865: val_loss -0.685 +2025-11-11 17:00:58.289660: Pseudo dice [np.float32(0.903), np.float32(0.7441), np.float32(0.6963), np.float32(0.603), np.float32(0.8458), np.float32(0.7806), np.float32(0.8434), np.float32(0.8485), np.float32(0.9669), np.float32(0.9648), np.float32(0.9671), np.float32(0.8071), np.float32(0.6901), np.float32(0.856), np.float32(0.9589), np.float32(0.3647), np.float32(0.2945)] +2025-11-11 17:00:58.291505: Epoch time: 258.81 s +2025-11-11 17:01:00.181783: +2025-11-11 17:01:00.183553: Epoch 204 +2025-11-11 17:01:00.185249: Current learning rate: 0.00814 +2025-11-11 17:05:19.033839: train_loss -0.6859 +2025-11-11 17:05:19.037050: val_loss -0.6992 +2025-11-11 17:05:19.038479: Pseudo dice [np.float32(0.9196), np.float32(0.7614), np.float32(0.696), np.float32(0.6242), np.float32(0.8556), np.float32(0.7944), np.float32(0.8901), np.float32(0.8446), np.float32(0.9749), np.float32(0.9748), np.float32(0.9661), np.float32(0.8295), np.float32(0.7326), np.float32(0.8603), np.float32(0.9574), np.float32(0.3084), np.float32(0.3431)] +2025-11-11 17:05:19.039667: Epoch time: 258.86 s +2025-11-11 17:05:20.933040: +2025-11-11 17:05:20.934548: Epoch 205 +2025-11-11 17:05:20.935799: Current learning rate: 0.00813 +2025-11-11 17:09:39.854961: train_loss -0.6866 +2025-11-11 17:09:39.860034: val_loss -0.695 +2025-11-11 17:09:39.861939: Pseudo dice [np.float32(0.911), np.float32(0.7145), np.float32(0.6688), np.float32(0.6299), np.float32(0.8472), np.float32(0.7699), np.float32(0.8782), np.float32(0.8534), np.float32(0.9762), np.float32(0.9758), np.float32(0.9667), np.float32(0.8088), np.float32(0.7604), np.float32(0.8569), np.float32(0.9602), np.float32(0.3871), np.float32(0.2234)] +2025-11-11 17:09:39.863949: Epoch time: 258.93 s +2025-11-11 17:09:41.641778: +2025-11-11 17:09:41.643132: Epoch 206 +2025-11-11 17:09:41.644474: Current learning rate: 0.00813 +2025-11-11 17:14:00.403364: train_loss -0.6871 +2025-11-11 17:14:00.407990: val_loss -0.6927 +2025-11-11 17:14:00.409451: Pseudo dice [np.float32(0.9132), np.float32(0.7597), np.float32(0.7141), np.float32(0.6446), np.float32(0.8499), np.float32(0.7771), np.float32(0.9003), np.float32(0.847), np.float32(0.9714), np.float32(0.9708), np.float32(0.9637), np.float32(0.8034), np.float32(0.736), np.float32(0.864), np.float32(0.9455), np.float32(0.2971), np.float32(0.242)] +2025-11-11 17:14:00.410975: Epoch time: 258.77 s +2025-11-11 17:14:02.257268: +2025-11-11 17:14:02.258800: Epoch 207 +2025-11-11 17:14:02.259865: Current learning rate: 0.00812 +2025-11-11 17:18:21.088420: train_loss -0.6772 +2025-11-11 17:18:21.092257: val_loss -0.6901 +2025-11-11 17:18:21.094561: Pseudo dice [np.float32(0.9051), np.float32(0.7429), np.float32(0.7008), np.float32(0.6294), np.float32(0.8472), np.float32(0.7862), np.float32(0.8716), np.float32(0.8507), np.float32(0.9617), np.float32(0.9648), np.float32(0.9651), np.float32(0.8131), np.float32(0.7215), np.float32(0.8499), np.float32(0.9535), np.float32(0.3822), np.float32(0.3025)] +2025-11-11 17:18:21.096626: Epoch time: 258.84 s +2025-11-11 17:18:22.910350: +2025-11-11 17:18:22.911852: Epoch 208 +2025-11-11 17:18:22.913225: Current learning rate: 0.00811 +2025-11-11 17:22:41.617875: train_loss -0.6801 +2025-11-11 17:22:41.622537: val_loss -0.6968 +2025-11-11 17:22:41.624115: Pseudo dice [np.float32(0.9116), np.float32(0.7578), np.float32(0.6913), np.float32(0.631), np.float32(0.8474), np.float32(0.7865), np.float32(0.8722), np.float32(0.8509), np.float32(0.9652), np.float32(0.9652), np.float32(0.9647), np.float32(0.8173), np.float32(0.7348), np.float32(0.8529), np.float32(0.955), np.float32(0.3421), np.float32(0.369)] +2025-11-11 17:22:41.625254: Epoch time: 258.71 s +2025-11-11 17:22:43.436548: +2025-11-11 17:22:43.438247: Epoch 209 +2025-11-11 17:22:43.439932: Current learning rate: 0.0081 +2025-11-11 17:27:03.561116: train_loss -0.6857 +2025-11-11 17:27:03.567995: val_loss -0.7028 +2025-11-11 17:27:03.569795: Pseudo dice [np.float32(0.9057), np.float32(0.768), np.float32(0.688), np.float32(0.6483), np.float32(0.8605), np.float32(0.7697), np.float32(0.8686), np.float32(0.8605), np.float32(0.9731), np.float32(0.973), np.float32(0.9673), np.float32(0.8114), np.float32(0.7363), np.float32(0.87), np.float32(0.9508), np.float32(0.3839), np.float32(0.3561)] +2025-11-11 17:27:03.571547: Epoch time: 260.13 s +2025-11-11 17:27:05.348699: +2025-11-11 17:27:05.350425: Epoch 210 +2025-11-11 17:27:05.351765: Current learning rate: 0.00809 +2025-11-11 17:31:23.989189: train_loss -0.6828 +2025-11-11 17:31:23.993046: val_loss -0.6998 +2025-11-11 17:31:23.994528: Pseudo dice [np.float32(0.8922), np.float32(0.745), np.float32(0.7054), np.float32(0.6579), np.float32(0.8431), np.float32(0.7888), np.float32(0.89), np.float32(0.8555), np.float32(0.9708), np.float32(0.9735), np.float32(0.967), np.float32(0.8006), np.float32(0.7226), np.float32(0.8551), np.float32(0.9559), np.float32(0.4182), np.float32(0.3715)] +2025-11-11 17:31:23.995744: Epoch time: 258.65 s +2025-11-11 17:31:23.996835: Yayy! New best EMA pseudo Dice: 0.7804999947547913 +2025-11-11 17:31:28.656887: +2025-11-11 17:31:28.658776: Epoch 211 +2025-11-11 17:31:28.660239: Current learning rate: 0.00808 +2025-11-11 17:35:47.043669: train_loss -0.6824 +2025-11-11 17:35:47.048589: val_loss -0.6885 +2025-11-11 17:35:47.050042: Pseudo dice [np.float32(0.9155), np.float32(0.7377), np.float32(0.6606), np.float32(0.6176), np.float32(0.8437), np.float32(0.7758), np.float32(0.879), np.float32(0.831), np.float32(0.9749), np.float32(0.9762), np.float32(0.9643), np.float32(0.8039), np.float32(0.7344), np.float32(0.8528), np.float32(0.9538), np.float32(0.3969), np.float32(0.363)] +2025-11-11 17:35:47.051483: Epoch time: 258.39 s +2025-11-11 17:35:47.053072: Yayy! New best EMA pseudo Dice: 0.7806000113487244 +2025-11-11 17:35:52.078487: +2025-11-11 17:35:52.080385: Epoch 212 +2025-11-11 17:35:52.082212: Current learning rate: 0.00807 +2025-11-11 17:40:10.559201: train_loss -0.6789 +2025-11-11 17:40:10.565610: val_loss -0.6915 +2025-11-11 17:40:10.567306: Pseudo dice [np.float32(0.904), np.float32(0.7597), np.float32(0.6803), np.float32(0.6175), np.float32(0.8581), np.float32(0.7729), np.float32(0.8646), np.float32(0.851), np.float32(0.9618), np.float32(0.9649), np.float32(0.9628), np.float32(0.8057), np.float32(0.7252), np.float32(0.8644), np.float32(0.9329), np.float32(0.4404), np.float32(0.3436)] +2025-11-11 17:40:10.568786: Epoch time: 258.49 s +2025-11-11 17:40:10.569995: Yayy! New best EMA pseudo Dice: 0.7807999849319458 +2025-11-11 17:40:15.464569: +2025-11-11 17:40:15.466589: Epoch 213 +2025-11-11 17:40:15.468235: Current learning rate: 0.00806 +2025-11-11 17:44:33.940267: train_loss -0.6776 +2025-11-11 17:44:33.945856: val_loss -0.6775 +2025-11-11 17:44:33.947677: Pseudo dice [np.float32(0.9145), np.float32(0.6818), np.float32(0.6954), np.float32(0.6095), np.float32(0.8441), np.float32(0.7676), np.float32(0.856), np.float32(0.8036), np.float32(0.9575), np.float32(0.9603), np.float32(0.9607), np.float32(0.8042), np.float32(0.7127), np.float32(0.8553), np.float32(0.9324), np.float32(0.329), np.float32(0.3228)] +2025-11-11 17:44:33.949572: Epoch time: 258.48 s +2025-11-11 17:44:35.710292: +2025-11-11 17:44:35.712960: Epoch 214 +2025-11-11 17:44:35.714746: Current learning rate: 0.00805 +2025-11-11 17:48:54.077621: train_loss -0.6759 +2025-11-11 17:48:54.083432: val_loss -0.7004 +2025-11-11 17:48:54.085605: Pseudo dice [np.float32(0.9097), np.float32(0.7489), np.float32(0.7034), np.float32(0.6229), np.float32(0.8468), np.float32(0.7765), np.float32(0.8985), np.float32(0.8474), np.float32(0.9625), np.float32(0.9695), np.float32(0.9664), np.float32(0.8023), np.float32(0.7581), np.float32(0.8558), np.float32(0.9525), np.float32(0.4058), np.float32(0.3313)] +2025-11-11 17:48:54.087110: Epoch time: 258.37 s +2025-11-11 17:48:55.823649: +2025-11-11 17:48:55.825298: Epoch 215 +2025-11-11 17:48:55.827202: Current learning rate: 0.00804 +2025-11-11 17:53:14.343697: train_loss -0.6784 +2025-11-11 17:53:14.348236: val_loss -0.6958 +2025-11-11 17:53:14.350214: Pseudo dice [np.float32(0.9132), np.float32(0.7294), np.float32(0.6815), np.float32(0.605), np.float32(0.8509), np.float32(0.7791), np.float32(0.8849), np.float32(0.843), np.float32(0.9689), np.float32(0.9677), np.float32(0.9655), np.float32(0.8209), np.float32(0.7432), np.float32(0.8634), np.float32(0.9587), np.float32(0.3433), np.float32(0.4182)] +2025-11-11 17:53:14.351807: Epoch time: 258.53 s +2025-11-11 17:53:16.179110: +2025-11-11 17:53:16.181762: Epoch 216 +2025-11-11 17:53:16.182997: Current learning rate: 0.00803 +2025-11-11 17:57:34.517923: train_loss -0.6825 +2025-11-11 17:57:34.522129: val_loss -0.6948 +2025-11-11 17:57:34.523535: Pseudo dice [np.float32(0.9173), np.float32(0.7353), np.float32(0.6858), np.float32(0.5847), np.float32(0.8531), np.float32(0.7727), np.float32(0.8782), np.float32(0.8417), np.float32(0.9685), np.float32(0.9643), np.float32(0.9663), np.float32(0.8147), np.float32(0.7393), np.float32(0.8653), np.float32(0.9575), np.float32(0.3996), np.float32(0.3827)] +2025-11-11 17:57:34.525061: Epoch time: 258.34 s +2025-11-11 17:57:36.318298: +2025-11-11 17:57:36.319835: Epoch 217 +2025-11-11 17:57:36.321484: Current learning rate: 0.00802 +2025-11-11 18:01:54.549745: train_loss -0.6791 +2025-11-11 18:01:54.553443: val_loss -0.6981 +2025-11-11 18:01:54.554631: Pseudo dice [np.float32(0.9093), np.float32(0.737), np.float32(0.6871), np.float32(0.6261), np.float32(0.8516), np.float32(0.7834), np.float32(0.8715), np.float32(0.8475), np.float32(0.9645), np.float32(0.9661), np.float32(0.9635), np.float32(0.8232), np.float32(0.7688), np.float32(0.8648), np.float32(0.9422), np.float32(0.3177), np.float32(0.3213)] +2025-11-11 18:01:54.556282: Epoch time: 258.24 s +2025-11-11 18:01:58.085044: +2025-11-11 18:01:58.086753: Epoch 218 +2025-11-11 18:01:58.088375: Current learning rate: 0.00801 +2025-11-11 18:06:16.568853: train_loss -0.6856 +2025-11-11 18:06:16.574530: val_loss -0.6978 +2025-11-11 18:06:16.576382: Pseudo dice [np.float32(0.9056), np.float32(0.756), np.float32(0.7013), np.float32(0.6424), np.float32(0.8548), np.float32(0.79), np.float32(0.8847), np.float32(0.8504), np.float32(0.9739), np.float32(0.9652), np.float32(0.9686), np.float32(0.8201), np.float32(0.7698), np.float32(0.8579), np.float32(0.9503), np.float32(0.3555), np.float32(0.2706)] +2025-11-11 18:06:16.578294: Epoch time: 258.49 s +2025-11-11 18:06:16.579738: Yayy! New best EMA pseudo Dice: 0.7807999849319458 +2025-11-11 18:06:21.310416: +2025-11-11 18:06:21.312815: Epoch 219 +2025-11-11 18:06:21.314866: Current learning rate: 0.00801 +2025-11-11 18:10:39.936530: train_loss -0.6827 +2025-11-11 18:10:39.941561: val_loss -0.6941 +2025-11-11 18:10:39.943173: Pseudo dice [np.float32(0.9057), np.float32(0.7282), np.float32(0.671), np.float32(0.6276), np.float32(0.8577), np.float32(0.7869), np.float32(0.8896), np.float32(0.8415), np.float32(0.9658), np.float32(0.9674), np.float32(0.9662), np.float32(0.8064), np.float32(0.7552), np.float32(0.8639), np.float32(0.9536), np.float32(0.3432), np.float32(0.3126)] +2025-11-11 18:10:39.944595: Epoch time: 258.63 s +2025-11-11 18:10:41.747405: +2025-11-11 18:10:41.749998: Epoch 220 +2025-11-11 18:10:41.751302: Current learning rate: 0.008 +2025-11-11 18:15:00.349278: train_loss -0.6843 +2025-11-11 18:15:00.353138: val_loss -0.7008 +2025-11-11 18:15:00.354727: Pseudo dice [np.float32(0.8876), np.float32(0.7613), np.float32(0.6653), np.float32(0.6377), np.float32(0.8584), np.float32(0.7711), np.float32(0.8865), np.float32(0.8507), np.float32(0.9675), np.float32(0.9712), np.float32(0.966), np.float32(0.8211), np.float32(0.7206), np.float32(0.8667), np.float32(0.9557), np.float32(0.4029), np.float32(0.4207)] +2025-11-11 18:15:00.356139: Epoch time: 258.61 s +2025-11-11 18:15:00.357357: Yayy! New best EMA pseudo Dice: 0.781499981880188 +2025-11-11 18:15:05.334283: +2025-11-11 18:15:05.335989: Epoch 221 +2025-11-11 18:15:05.337480: Current learning rate: 0.00799 +2025-11-11 18:19:24.051796: train_loss -0.689 +2025-11-11 18:19:24.060400: val_loss -0.7023 +2025-11-11 18:19:24.062999: Pseudo dice [np.float32(0.9051), np.float32(0.7586), np.float32(0.7015), np.float32(0.619), np.float32(0.8596), np.float32(0.7977), np.float32(0.9085), np.float32(0.8489), np.float32(0.968), np.float32(0.9673), np.float32(0.9671), np.float32(0.8117), np.float32(0.7526), np.float32(0.8696), np.float32(0.9478), np.float32(0.4003), np.float32(0.3549)] +2025-11-11 18:19:24.065480: Epoch time: 258.72 s +2025-11-11 18:19:24.067646: Yayy! New best EMA pseudo Dice: 0.7824000120162964 +2025-11-11 18:19:29.011865: +2025-11-11 18:19:29.013205: Epoch 222 +2025-11-11 18:19:29.014500: Current learning rate: 0.00798 +2025-11-11 18:23:47.301193: train_loss -0.6922 +2025-11-11 18:23:47.306568: val_loss -0.6931 +2025-11-11 18:23:47.308317: Pseudo dice [np.float32(0.8987), np.float32(0.7514), np.float32(0.691), np.float32(0.6092), np.float32(0.8493), np.float32(0.772), np.float32(0.8864), np.float32(0.85), np.float32(0.9736), np.float32(0.9717), np.float32(0.9668), np.float32(0.8192), np.float32(0.7424), np.float32(0.8567), np.float32(0.9535), np.float32(0.4192), np.float32(0.2693)] +2025-11-11 18:23:47.309506: Epoch time: 258.29 s +2025-11-11 18:23:49.097504: +2025-11-11 18:23:49.098915: Epoch 223 +2025-11-11 18:23:49.100313: Current learning rate: 0.00797 +2025-11-11 18:28:07.377775: train_loss -0.6816 +2025-11-11 18:28:07.382849: val_loss -0.7035 +2025-11-11 18:28:07.384329: Pseudo dice [np.float32(0.9138), np.float32(0.7412), np.float32(0.689), np.float32(0.6623), np.float32(0.8555), np.float32(0.7825), np.float32(0.8932), np.float32(0.8443), np.float32(0.9742), np.float32(0.9745), np.float32(0.9677), np.float32(0.808), np.float32(0.7423), np.float32(0.8697), np.float32(0.9599), np.float32(0.3984), np.float32(0.3794)] +2025-11-11 18:28:07.386169: Epoch time: 258.29 s +2025-11-11 18:28:07.387753: Yayy! New best EMA pseudo Dice: 0.7832000255584717 +2025-11-11 18:28:12.416504: +2025-11-11 18:28:12.417798: Epoch 224 +2025-11-11 18:28:12.418898: Current learning rate: 0.00796 +2025-11-11 18:32:30.844815: train_loss -0.6795 +2025-11-11 18:32:30.848454: val_loss -0.698 +2025-11-11 18:32:30.850117: Pseudo dice [np.float32(0.911), np.float32(0.7552), np.float32(0.6423), np.float32(0.6662), np.float32(0.8628), np.float32(0.7841), np.float32(0.8773), np.float32(0.8483), np.float32(0.9738), np.float32(0.9705), np.float32(0.9664), np.float32(0.8238), np.float32(0.7238), np.float32(0.867), np.float32(0.9632), np.float32(0.4117), np.float32(0.2904)] +2025-11-11 18:32:30.851217: Epoch time: 258.43 s +2025-11-11 18:32:30.852443: Yayy! New best EMA pseudo Dice: 0.78329998254776 +2025-11-11 18:32:35.682000: +2025-11-11 18:32:35.684210: Epoch 225 +2025-11-11 18:32:35.685625: Current learning rate: 0.00795 +2025-11-11 18:36:54.616969: train_loss -0.6836 +2025-11-11 18:36:54.623046: val_loss -0.6925 +2025-11-11 18:36:54.624920: Pseudo dice [np.float32(0.9079), np.float32(0.7323), np.float32(0.6821), np.float32(0.6119), np.float32(0.8545), np.float32(0.7789), np.float32(0.854), np.float32(0.8375), np.float32(0.9777), np.float32(0.9691), np.float32(0.9664), np.float32(0.8138), np.float32(0.7414), np.float32(0.8661), np.float32(0.9553), np.float32(0.3876), np.float32(0.3)] +2025-11-11 18:36:54.627136: Epoch time: 258.94 s +2025-11-11 18:36:56.421753: +2025-11-11 18:36:56.423526: Epoch 226 +2025-11-11 18:36:56.425069: Current learning rate: 0.00794 +2025-11-11 18:41:16.128282: train_loss -0.6954 +2025-11-11 18:41:16.132323: val_loss -0.6867 +2025-11-11 18:41:16.133662: Pseudo dice [np.float32(0.9049), np.float32(0.7291), np.float32(0.7092), np.float32(0.6185), np.float32(0.8481), np.float32(0.7837), np.float32(0.8783), np.float32(0.8508), np.float32(0.9555), np.float32(0.9547), np.float32(0.964), np.float32(0.8014), np.float32(0.7633), np.float32(0.8535), np.float32(0.9435), np.float32(0.3646), np.float32(0.2626)] +2025-11-11 18:41:16.134979: Epoch time: 259.71 s +2025-11-11 18:41:17.914238: +2025-11-11 18:41:17.915887: Epoch 227 +2025-11-11 18:41:17.917363: Current learning rate: 0.00793 +2025-11-11 18:45:36.757914: train_loss -0.6905 +2025-11-11 18:45:36.762934: val_loss -0.709 +2025-11-11 18:45:36.764255: Pseudo dice [np.float32(0.9067), np.float32(0.7718), np.float32(0.698), np.float32(0.6447), np.float32(0.8459), np.float32(0.7783), np.float32(0.8815), np.float32(0.8659), np.float32(0.9754), np.float32(0.9733), np.float32(0.969), np.float32(0.8058), np.float32(0.7513), np.float32(0.8651), np.float32(0.9633), np.float32(0.4099), np.float32(0.3587)] +2025-11-11 18:45:36.765829: Epoch time: 258.85 s +2025-11-11 18:45:38.519495: +2025-11-11 18:45:38.521463: Epoch 228 +2025-11-11 18:45:38.523012: Current learning rate: 0.00792 +2025-11-11 18:49:56.963944: train_loss -0.6858 +2025-11-11 18:49:56.970024: val_loss -0.6857 +2025-11-11 18:49:56.972078: Pseudo dice [np.float32(0.9156), np.float32(0.757), np.float32(0.6683), np.float32(0.6275), np.float32(0.851), np.float32(0.7814), np.float32(0.8523), np.float32(0.8441), np.float32(0.9605), np.float32(0.9558), np.float32(0.9631), np.float32(0.8211), np.float32(0.7683), np.float32(0.863), np.float32(0.9528), np.float32(0.2884), np.float32(0.2602)] +2025-11-11 18:49:56.974225: Epoch time: 258.45 s +2025-11-11 18:49:58.730198: +2025-11-11 18:49:58.731655: Epoch 229 +2025-11-11 18:49:58.732908: Current learning rate: 0.00791 +2025-11-11 18:54:16.960432: train_loss -0.694 +2025-11-11 18:54:16.965466: val_loss -0.7064 +2025-11-11 18:54:16.966736: Pseudo dice [np.float32(0.9143), np.float32(0.7413), np.float32(0.7072), np.float32(0.629), np.float32(0.8622), np.float32(0.7861), np.float32(0.8866), np.float32(0.8582), np.float32(0.9708), np.float32(0.9728), np.float32(0.967), np.float32(0.8248), np.float32(0.7749), np.float32(0.8698), np.float32(0.9606), np.float32(0.4287), np.float32(0.2704)] +2025-11-11 18:54:16.968586: Epoch time: 258.24 s +2025-11-11 18:54:18.713408: +2025-11-11 18:54:18.715523: Epoch 230 +2025-11-11 18:54:18.717108: Current learning rate: 0.0079 +2025-11-11 18:58:37.084430: train_loss -0.6949 +2025-11-11 18:58:37.090723: val_loss -0.699 +2025-11-11 18:58:37.092231: Pseudo dice [np.float32(0.9108), np.float32(0.7513), np.float32(0.6625), np.float32(0.6397), np.float32(0.8482), np.float32(0.7849), np.float32(0.8845), np.float32(0.8453), np.float32(0.9706), np.float32(0.975), np.float32(0.9668), np.float32(0.8193), np.float32(0.7061), np.float32(0.8644), np.float32(0.9558), np.float32(0.3242), np.float32(0.3009)] +2025-11-11 18:58:37.093812: Epoch time: 258.38 s +2025-11-11 18:58:39.004836: +2025-11-11 18:58:39.006795: Epoch 231 +2025-11-11 18:58:39.008618: Current learning rate: 0.00789 +2025-11-11 19:02:57.560488: train_loss -0.6908 +2025-11-11 19:02:57.564473: val_loss -0.6938 +2025-11-11 19:02:57.565686: Pseudo dice [np.float32(0.9092), np.float32(0.7347), np.float32(0.6809), np.float32(0.6184), np.float32(0.8475), np.float32(0.7669), np.float32(0.8785), np.float32(0.844), np.float32(0.958), np.float32(0.9599), np.float32(0.9661), np.float32(0.8053), np.float32(0.7384), np.float32(0.8641), np.float32(0.9465), np.float32(0.4211), np.float32(0.3775)] +2025-11-11 19:02:57.566854: Epoch time: 258.56 s +2025-11-11 19:02:59.295332: +2025-11-11 19:02:59.296757: Epoch 232 +2025-11-11 19:02:59.297988: Current learning rate: 0.00789 +2025-11-11 19:07:17.733659: train_loss -0.6869 +2025-11-11 19:07:17.737662: val_loss -0.7149 +2025-11-11 19:07:17.738912: Pseudo dice [np.float32(0.9052), np.float32(0.7465), np.float32(0.6951), np.float32(0.6536), np.float32(0.8528), np.float32(0.7856), np.float32(0.8934), np.float32(0.8437), np.float32(0.9709), np.float32(0.9716), np.float32(0.9667), np.float32(0.8265), np.float32(0.7416), np.float32(0.871), np.float32(0.9603), np.float32(0.4751), np.float32(0.3988)] +2025-11-11 19:07:17.740147: Epoch time: 258.44 s +2025-11-11 19:07:17.741401: Yayy! New best EMA pseudo Dice: 0.7839000225067139 +2025-11-11 19:07:22.454757: +2025-11-11 19:07:22.457069: Epoch 233 +2025-11-11 19:07:22.459261: Current learning rate: 0.00788 +2025-11-11 19:11:40.842009: train_loss -0.6878 +2025-11-11 19:11:40.846439: val_loss -0.7071 +2025-11-11 19:11:40.847581: Pseudo dice [np.float32(0.9109), np.float32(0.692), np.float32(0.7012), np.float32(0.6112), np.float32(0.8606), np.float32(0.7806), np.float32(0.8872), np.float32(0.8507), np.float32(0.9718), np.float32(0.9671), np.float32(0.9696), np.float32(0.8234), np.float32(0.7116), np.float32(0.866), np.float32(0.954), np.float32(0.4764), np.float32(0.3219)] +2025-11-11 19:11:40.848917: Epoch time: 258.39 s +2025-11-11 19:11:40.850325: Yayy! New best EMA pseudo Dice: 0.7839999794960022 +2025-11-11 19:11:45.816093: +2025-11-11 19:11:45.818020: Epoch 234 +2025-11-11 19:11:45.819656: Current learning rate: 0.00787 +2025-11-11 19:16:04.170681: train_loss -0.6976 +2025-11-11 19:16:04.175131: val_loss -0.7112 +2025-11-11 19:16:04.176716: Pseudo dice [np.float32(0.8907), np.float32(0.6872), np.float32(0.6938), np.float32(0.6129), np.float32(0.8586), np.float32(0.7718), np.float32(0.8815), np.float32(0.8432), np.float32(0.9732), np.float32(0.9732), np.float32(0.9691), np.float32(0.8194), np.float32(0.7401), np.float32(0.8656), np.float32(0.9661), np.float32(0.3816), np.float32(0.4413)] +2025-11-11 19:16:04.178157: Epoch time: 258.36 s +2025-11-11 19:16:04.179507: Yayy! New best EMA pseudo Dice: 0.7843000292778015 +2025-11-11 19:16:08.945880: +2025-11-11 19:16:08.947402: Epoch 235 +2025-11-11 19:16:08.948889: Current learning rate: 0.00786 +2025-11-11 19:20:28.810823: train_loss -0.6845 +2025-11-11 19:20:28.814580: val_loss -0.6789 +2025-11-11 19:20:28.815724: Pseudo dice [np.float32(0.9096), np.float32(0.7379), np.float32(0.6896), np.float32(0.6188), np.float32(0.8425), np.float32(0.7589), np.float32(0.8457), np.float32(0.8393), np.float32(0.9596), np.float32(0.9544), np.float32(0.9599), np.float32(0.8095), np.float32(0.7269), np.float32(0.8534), np.float32(0.9266), np.float32(0.3831), np.float32(0.3067)] +2025-11-11 19:20:28.817071: Epoch time: 259.87 s +2025-11-11 19:20:30.574526: +2025-11-11 19:20:30.576160: Epoch 236 +2025-11-11 19:20:30.577833: Current learning rate: 0.00785 +2025-11-11 19:24:49.136784: train_loss -0.6818 +2025-11-11 19:24:49.142911: val_loss -0.6941 +2025-11-11 19:24:49.144257: Pseudo dice [np.float32(0.918), np.float32(0.7431), np.float32(0.7023), np.float32(0.6088), np.float32(0.8435), np.float32(0.7716), np.float32(0.8472), np.float32(0.8516), np.float32(0.9458), np.float32(0.9473), np.float32(0.9641), np.float32(0.8162), np.float32(0.7469), np.float32(0.8606), np.float32(0.9414), np.float32(0.4488), np.float32(0.4016)] +2025-11-11 19:24:49.145542: Epoch time: 258.57 s +2025-11-11 19:24:50.898199: +2025-11-11 19:24:50.900160: Epoch 237 +2025-11-11 19:24:50.901763: Current learning rate: 0.00784 +2025-11-11 19:29:09.770355: train_loss -0.6627 +2025-11-11 19:29:09.777064: val_loss -0.6816 +2025-11-11 19:29:09.778959: Pseudo dice [np.float32(0.9003), np.float32(0.7305), np.float32(0.6852), np.float32(0.6196), np.float32(0.8451), np.float32(0.7813), np.float32(0.8621), np.float32(0.8423), np.float32(0.9422), np.float32(0.9516), np.float32(0.9602), np.float32(0.7912), np.float32(0.7384), np.float32(0.8436), np.float32(0.9216), np.float32(0.3896), np.float32(0.4212)] +2025-11-11 19:29:09.780953: Epoch time: 258.88 s +2025-11-11 19:29:11.566946: +2025-11-11 19:29:11.568683: Epoch 238 +2025-11-11 19:29:11.570634: Current learning rate: 0.00783 +2025-11-11 19:33:30.204223: train_loss -0.6739 +2025-11-11 19:33:30.208314: val_loss -0.6919 +2025-11-11 19:33:30.209698: Pseudo dice [np.float32(0.8997), np.float32(0.7204), np.float32(0.6759), np.float32(0.6422), np.float32(0.8492), np.float32(0.7672), np.float32(0.8855), np.float32(0.8495), np.float32(0.9672), np.float32(0.9662), np.float32(0.9666), np.float32(0.7926), np.float32(0.746), np.float32(0.8642), np.float32(0.954), np.float32(0.3891), np.float32(0.3637)] +2025-11-11 19:33:30.210948: Epoch time: 258.64 s +2025-11-11 19:33:31.970340: +2025-11-11 19:33:31.972405: Epoch 239 +2025-11-11 19:33:31.974813: Current learning rate: 0.00782 +2025-11-11 19:37:50.099213: train_loss -0.6751 +2025-11-11 19:37:50.102973: val_loss -0.6884 +2025-11-11 19:37:50.104415: Pseudo dice [np.float32(0.9119), np.float32(0.7372), np.float32(0.6863), np.float32(0.6232), np.float32(0.8531), np.float32(0.7508), np.float32(0.8381), np.float32(0.8461), np.float32(0.9716), np.float32(0.9684), np.float32(0.9655), np.float32(0.8041), np.float32(0.7279), np.float32(0.8657), np.float32(0.9552), np.float32(0.3587), np.float32(0.3459)] +2025-11-11 19:37:50.105632: Epoch time: 258.14 s +2025-11-11 19:37:52.020329: +2025-11-11 19:37:52.022292: Epoch 240 +2025-11-11 19:37:52.023772: Current learning rate: 0.00781 +2025-11-11 19:42:10.437338: train_loss -0.6806 +2025-11-11 19:42:10.442388: val_loss -0.7 +2025-11-11 19:42:10.444155: Pseudo dice [np.float32(0.8979), np.float32(0.7542), np.float32(0.6756), np.float32(0.6448), np.float32(0.8444), np.float32(0.7944), np.float32(0.8419), np.float32(0.8446), np.float32(0.9753), np.float32(0.9735), np.float32(0.9655), np.float32(0.8207), np.float32(0.7487), np.float32(0.8581), np.float32(0.9595), np.float32(0.4368), np.float32(0.3766)] +2025-11-11 19:42:10.445540: Epoch time: 258.42 s +2025-11-11 19:42:12.214583: +2025-11-11 19:42:12.216266: Epoch 241 +2025-11-11 19:42:12.217535: Current learning rate: 0.0078 +2025-11-11 19:46:30.564284: train_loss -0.6826 +2025-11-11 19:46:30.568729: val_loss -0.7044 +2025-11-11 19:46:30.570302: Pseudo dice [np.float32(0.915), np.float32(0.732), np.float32(0.7001), np.float32(0.6623), np.float32(0.849), np.float32(0.7805), np.float32(0.8782), np.float32(0.8483), np.float32(0.9721), np.float32(0.978), np.float32(0.9677), np.float32(0.8124), np.float32(0.7103), np.float32(0.8533), np.float32(0.9573), np.float32(0.3503), np.float32(0.396)] +2025-11-11 19:46:30.571722: Epoch time: 258.36 s +2025-11-11 19:46:32.337280: +2025-11-11 19:46:32.338993: Epoch 242 +2025-11-11 19:46:32.340696: Current learning rate: 0.00779 +2025-11-11 19:50:50.630680: train_loss -0.6837 +2025-11-11 19:50:50.637172: val_loss -0.6772 +2025-11-11 19:50:50.639599: Pseudo dice [np.float32(0.9106), np.float32(0.6839), np.float32(0.686), np.float32(0.6357), np.float32(0.8552), np.float32(0.7826), np.float32(0.8778), np.float32(0.8484), np.float32(0.9336), np.float32(0.9355), np.float32(0.9589), np.float32(0.8114), np.float32(0.7208), np.float32(0.8582), np.float32(0.8999), np.float32(0.3544), np.float32(0.2942)] +2025-11-11 19:50:50.641588: Epoch time: 258.3 s +2025-11-11 19:50:52.377449: +2025-11-11 19:50:52.378928: Epoch 243 +2025-11-11 19:50:52.380158: Current learning rate: 0.00778 +2025-11-11 19:55:10.773715: train_loss -0.6914 +2025-11-11 19:55:10.778276: val_loss -0.709 +2025-11-11 19:55:10.779772: Pseudo dice [np.float32(0.9066), np.float32(0.7584), np.float32(0.7129), np.float32(0.6332), np.float32(0.8604), np.float32(0.7575), np.float32(0.8663), np.float32(0.8544), np.float32(0.9768), np.float32(0.9762), np.float32(0.9666), np.float32(0.8114), np.float32(0.7398), np.float32(0.8594), np.float32(0.9571), np.float32(0.499), np.float32(0.3615)] +2025-11-11 19:55:10.781011: Epoch time: 258.4 s +2025-11-11 19:55:12.518456: +2025-11-11 19:55:12.520480: Epoch 244 +2025-11-11 19:55:12.522334: Current learning rate: 0.00777 +2025-11-11 19:59:31.182809: train_loss -0.6897 +2025-11-11 19:59:31.186837: val_loss -0.7066 +2025-11-11 19:59:31.188298: Pseudo dice [np.float32(0.9022), np.float32(0.7697), np.float32(0.7398), np.float32(0.6392), np.float32(0.8513), np.float32(0.7808), np.float32(0.8842), np.float32(0.8571), np.float32(0.9596), np.float32(0.9607), np.float32(0.9654), np.float32(0.816), np.float32(0.7421), np.float32(0.869), np.float32(0.9466), np.float32(0.3933), np.float32(0.392)] +2025-11-11 19:59:31.189586: Epoch time: 258.67 s +2025-11-11 19:59:34.268261: +2025-11-11 19:59:34.269732: Epoch 245 +2025-11-11 19:59:34.271106: Current learning rate: 0.00777 +2025-11-11 20:03:52.788186: train_loss -0.688 +2025-11-11 20:03:52.791922: val_loss -0.6866 +2025-11-11 20:03:52.792986: Pseudo dice [np.float32(0.9148), np.float32(0.656), np.float32(0.6998), np.float32(0.6324), np.float32(0.8487), np.float32(0.7836), np.float32(0.8797), np.float32(0.83), np.float32(0.9464), np.float32(0.9516), np.float32(0.959), np.float32(0.8076), np.float32(0.7127), np.float32(0.8574), np.float32(0.9322), np.float32(0.3724), np.float32(0.4379)] +2025-11-11 20:03:52.794245: Epoch time: 258.53 s +2025-11-11 20:03:54.557585: +2025-11-11 20:03:54.558999: Epoch 246 +2025-11-11 20:03:54.560403: Current learning rate: 0.00776 +2025-11-11 20:08:13.102864: train_loss -0.6843 +2025-11-11 20:08:13.108253: val_loss -0.6996 +2025-11-11 20:08:13.109515: Pseudo dice [np.float32(0.9127), np.float32(0.6783), np.float32(0.7257), np.float32(0.6226), np.float32(0.8512), np.float32(0.7861), np.float32(0.8979), np.float32(0.8532), np.float32(0.9654), np.float32(0.969), np.float32(0.9673), np.float32(0.8119), np.float32(0.7337), np.float32(0.8672), np.float32(0.952), np.float32(0.4276), np.float32(0.4132)] +2025-11-11 20:08:13.111348: Epoch time: 258.55 s +2025-11-11 20:08:14.885326: +2025-11-11 20:08:14.887063: Epoch 247 +2025-11-11 20:08:14.888830: Current learning rate: 0.00775 +2025-11-11 20:12:33.250669: train_loss -0.6785 +2025-11-11 20:12:33.256046: val_loss -0.697 +2025-11-11 20:12:33.257494: Pseudo dice [np.float32(0.9076), np.float32(0.7623), np.float32(0.6946), np.float32(0.6241), np.float32(0.8489), np.float32(0.7643), np.float32(0.8905), np.float32(0.851), np.float32(0.9716), np.float32(0.9774), np.float32(0.9676), np.float32(0.8001), np.float32(0.7191), np.float32(0.8541), np.float32(0.9546), np.float32(0.439), np.float32(0.2962)] +2025-11-11 20:12:33.259274: Epoch time: 258.37 s +2025-11-11 20:12:35.019790: +2025-11-11 20:12:35.021859: Epoch 248 +2025-11-11 20:12:35.023643: Current learning rate: 0.00774 +2025-11-11 20:16:53.485710: train_loss -0.6877 +2025-11-11 20:16:53.489922: val_loss -0.6948 +2025-11-11 20:16:53.491093: Pseudo dice [np.float32(0.8877), np.float32(0.6763), np.float32(0.7159), np.float32(0.6464), np.float32(0.8534), np.float32(0.7767), np.float32(0.8852), np.float32(0.8469), np.float32(0.9703), np.float32(0.9739), np.float32(0.9665), np.float32(0.7945), np.float32(0.7269), np.float32(0.8641), np.float32(0.9585), np.float32(0.4233), np.float32(0.395)] +2025-11-11 20:16:53.493294: Epoch time: 258.47 s +2025-11-11 20:16:55.301575: +2025-11-11 20:16:55.303027: Epoch 249 +2025-11-11 20:16:55.304318: Current learning rate: 0.00773 +2025-11-11 20:21:14.002715: train_loss -0.6777 +2025-11-11 20:21:14.008218: val_loss -0.7016 +2025-11-11 20:21:14.009542: Pseudo dice [np.float32(0.9075), np.float32(0.7827), np.float32(0.7015), np.float32(0.615), np.float32(0.8564), np.float32(0.7749), np.float32(0.8748), np.float32(0.8535), np.float32(0.9604), np.float32(0.9529), np.float32(0.9658), np.float32(0.8142), np.float32(0.718), np.float32(0.8641), np.float32(0.9524), np.float32(0.465), np.float32(0.3789)] +2025-11-11 20:21:14.010964: Epoch time: 258.71 s +2025-11-11 20:21:17.623736: Yayy! New best EMA pseudo Dice: 0.7846999764442444 +2025-11-11 20:21:22.312809: +2025-11-11 20:21:22.314188: Epoch 250 +2025-11-11 20:21:22.315593: Current learning rate: 0.00772 +2025-11-11 20:25:40.724466: train_loss -0.6888 +2025-11-11 20:25:40.728703: val_loss -0.6966 +2025-11-11 20:25:40.730340: Pseudo dice [np.float32(0.9054), np.float32(0.7793), np.float32(0.7062), np.float32(0.6349), np.float32(0.8599), np.float32(0.7975), np.float32(0.8768), np.float32(0.8562), np.float32(0.9597), np.float32(0.9579), np.float32(0.9652), np.float32(0.8135), np.float32(0.7302), np.float32(0.8678), np.float32(0.9429), np.float32(0.3787), np.float32(0.3303)] +2025-11-11 20:25:40.731696: Epoch time: 258.42 s +2025-11-11 20:25:40.733052: Yayy! New best EMA pseudo Dice: 0.7849000096321106 +2025-11-11 20:25:45.668337: +2025-11-11 20:25:45.670160: Epoch 251 +2025-11-11 20:25:45.671814: Current learning rate: 0.00771 +2025-11-11 20:30:03.967293: train_loss -0.6865 +2025-11-11 20:30:03.972084: val_loss -0.6922 +2025-11-11 20:30:03.973540: Pseudo dice [np.float32(0.9156), np.float32(0.6567), np.float32(0.7075), np.float32(0.6432), np.float32(0.8505), np.float32(0.777), np.float32(0.8673), np.float32(0.8529), np.float32(0.9595), np.float32(0.9583), np.float32(0.9645), np.float32(0.8172), np.float32(0.7462), np.float32(0.8565), np.float32(0.9483), np.float32(0.3473), np.float32(0.3498)] +2025-11-11 20:30:03.975104: Epoch time: 258.3 s +2025-11-11 20:30:05.733518: +2025-11-11 20:30:05.735226: Epoch 252 +2025-11-11 20:30:05.736801: Current learning rate: 0.0077 +2025-11-11 20:34:24.071548: train_loss -0.6897 +2025-11-11 20:34:24.075484: val_loss -0.7038 +2025-11-11 20:34:24.077050: Pseudo dice [np.float32(0.916), np.float32(0.7501), np.float32(0.7005), np.float32(0.629), np.float32(0.8628), np.float32(0.7854), np.float32(0.8852), np.float32(0.8519), np.float32(0.9545), np.float32(0.9514), np.float32(0.966), np.float32(0.8235), np.float32(0.7491), np.float32(0.8701), np.float32(0.9506), np.float32(0.3668), np.float32(0.3742)] +2025-11-11 20:34:24.078558: Epoch time: 258.34 s +2025-11-11 20:34:25.916266: +2025-11-11 20:34:25.917914: Epoch 253 +2025-11-11 20:34:25.919252: Current learning rate: 0.00769 +2025-11-11 20:38:44.341478: train_loss -0.6887 +2025-11-11 20:38:44.346332: val_loss -0.6859 +2025-11-11 20:38:44.347517: Pseudo dice [np.float32(0.903), np.float32(0.7658), np.float32(0.7009), np.float32(0.6461), np.float32(0.8506), np.float32(0.7937), np.float32(0.869), np.float32(0.8439), np.float32(0.9572), np.float32(0.96), np.float32(0.9646), np.float32(0.8282), np.float32(0.7403), np.float32(0.856), np.float32(0.9402), np.float32(0.2984), np.float32(0.3012)] +2025-11-11 20:38:44.348648: Epoch time: 258.43 s +2025-11-11 20:38:48.244718: +2025-11-11 20:38:48.246154: Epoch 254 +2025-11-11 20:38:48.247319: Current learning rate: 0.00768 +2025-11-11 20:43:06.781022: train_loss -0.6853 +2025-11-11 20:43:06.784931: val_loss -0.7051 +2025-11-11 20:43:06.786514: Pseudo dice [np.float32(0.9134), np.float32(0.7615), np.float32(0.7179), np.float32(0.6532), np.float32(0.8508), np.float32(0.7658), np.float32(0.8808), np.float32(0.8446), np.float32(0.9706), np.float32(0.9699), np.float32(0.9663), np.float32(0.8234), np.float32(0.7314), np.float32(0.864), np.float32(0.9564), np.float32(0.404), np.float32(0.4698)] +2025-11-11 20:43:06.787735: Epoch time: 258.54 s +2025-11-11 20:43:06.789069: Yayy! New best EMA pseudo Dice: 0.785099983215332 +2025-11-11 20:43:11.813148: +2025-11-11 20:43:11.814630: Epoch 255 +2025-11-11 20:43:11.816497: Current learning rate: 0.00767 +2025-11-11 20:47:30.703075: train_loss -0.6905 +2025-11-11 20:47:30.710386: val_loss -0.7035 +2025-11-11 20:47:30.712310: Pseudo dice [np.float32(0.9142), np.float32(0.6594), np.float32(0.6855), np.float32(0.6028), np.float32(0.8558), np.float32(0.7978), np.float32(0.8939), np.float32(0.8495), np.float32(0.9724), np.float32(0.971), np.float32(0.9682), np.float32(0.8219), np.float32(0.7461), np.float32(0.8577), np.float32(0.9546), np.float32(0.3736), np.float32(0.3956)] +2025-11-11 20:47:30.714341: Epoch time: 258.9 s +2025-11-11 20:47:32.498795: +2025-11-11 20:47:32.500471: Epoch 256 +2025-11-11 20:47:32.502241: Current learning rate: 0.00766 +2025-11-11 20:51:51.400259: train_loss -0.6862 +2025-11-11 20:51:51.405071: val_loss -0.6926 +2025-11-11 20:51:51.407127: Pseudo dice [np.float32(0.9099), np.float32(0.7533), np.float32(0.7066), np.float32(0.61), np.float32(0.8463), np.float32(0.7682), np.float32(0.8464), np.float32(0.8479), np.float32(0.9721), np.float32(0.9681), np.float32(0.9634), np.float32(0.8152), np.float32(0.73), np.float32(0.8635), np.float32(0.9513), np.float32(0.4544), np.float32(0.3591)] +2025-11-11 20:51:51.409338: Epoch time: 258.91 s +2025-11-11 20:51:53.209304: +2025-11-11 20:51:53.210843: Epoch 257 +2025-11-11 20:51:53.212263: Current learning rate: 0.00765 +2025-11-11 20:56:11.813939: train_loss -0.6882 +2025-11-11 20:56:11.819624: val_loss -0.6863 +2025-11-11 20:56:11.820824: Pseudo dice [np.float32(0.9085), np.float32(0.7488), np.float32(0.6942), np.float32(0.6427), np.float32(0.8473), np.float32(0.7895), np.float32(0.8634), np.float32(0.8333), np.float32(0.9357), np.float32(0.9385), np.float32(0.9621), np.float32(0.8184), np.float32(0.7252), np.float32(0.863), np.float32(0.9276), np.float32(0.3656), np.float32(0.3756)] +2025-11-11 20:56:11.822392: Epoch time: 258.61 s +2025-11-11 20:56:13.645379: +2025-11-11 20:56:13.646906: Epoch 258 +2025-11-11 20:56:13.648907: Current learning rate: 0.00764 +2025-11-11 21:00:32.446896: train_loss -0.6916 +2025-11-11 21:00:32.461362: val_loss -0.694 +2025-11-11 21:00:32.464604: Pseudo dice [np.float32(0.9028), np.float32(0.6135), np.float32(0.6988), np.float32(0.6524), np.float32(0.8582), np.float32(0.7899), np.float32(0.8676), np.float32(0.8429), np.float32(0.966), np.float32(0.9731), np.float32(0.9678), np.float32(0.8251), np.float32(0.7351), np.float32(0.8624), np.float32(0.9579), np.float32(0.3396), np.float32(0.3937)] +2025-11-11 21:00:32.467984: Epoch time: 258.81 s +2025-11-11 21:00:34.220866: +2025-11-11 21:00:34.223510: Epoch 259 +2025-11-11 21:00:34.225884: Current learning rate: 0.00764 +2025-11-11 21:04:52.936043: train_loss -0.6923 +2025-11-11 21:04:52.947665: val_loss -0.7035 +2025-11-11 21:04:52.951204: Pseudo dice [np.float32(0.9083), np.float32(0.7285), np.float32(0.6977), np.float32(0.6199), np.float32(0.8532), np.float32(0.7776), np.float32(0.8899), np.float32(0.8395), np.float32(0.9688), np.float32(0.9726), np.float32(0.9671), np.float32(0.8058), np.float32(0.7395), np.float32(0.8645), np.float32(0.9556), np.float32(0.3316), np.float32(0.3371)] +2025-11-11 21:04:52.954424: Epoch time: 258.72 s +2025-11-11 21:04:54.886173: +2025-11-11 21:04:54.887806: Epoch 260 +2025-11-11 21:04:54.889331: Current learning rate: 0.00763 +2025-11-11 21:09:13.569097: train_loss -0.6868 +2025-11-11 21:09:13.576926: val_loss -0.69 +2025-11-11 21:09:13.579699: Pseudo dice [np.float32(0.9042), np.float32(0.7494), np.float32(0.7029), np.float32(0.6402), np.float32(0.8464), np.float32(0.8013), np.float32(0.8705), np.float32(0.8502), np.float32(0.9762), np.float32(0.9713), np.float32(0.9644), np.float32(0.8196), np.float32(0.7248), np.float32(0.8564), np.float32(0.9565), np.float32(0.2714), np.float32(0.2499)] +2025-11-11 21:09:13.581954: Epoch time: 258.69 s +2025-11-11 21:09:15.361627: +2025-11-11 21:09:15.363023: Epoch 261 +2025-11-11 21:09:15.364662: Current learning rate: 0.00762 +2025-11-11 21:13:33.914772: train_loss -0.6824 +2025-11-11 21:13:33.920740: val_loss -0.6911 +2025-11-11 21:13:33.923012: Pseudo dice [np.float32(0.9055), np.float32(0.7523), np.float32(0.6901), np.float32(0.6153), np.float32(0.8547), np.float32(0.7524), np.float32(0.8417), np.float32(0.8387), np.float32(0.9712), np.float32(0.9641), np.float32(0.9656), np.float32(0.8061), np.float32(0.7445), np.float32(0.8641), np.float32(0.955), np.float32(0.3927), np.float32(0.2719)] +2025-11-11 21:13:33.925471: Epoch time: 258.56 s +2025-11-11 21:13:35.703656: +2025-11-11 21:13:35.705501: Epoch 262 +2025-11-11 21:13:35.708169: Current learning rate: 0.00761 +2025-11-11 21:17:54.414024: train_loss -0.6877 +2025-11-11 21:17:54.421664: val_loss -0.6991 +2025-11-11 21:17:54.423646: Pseudo dice [np.float32(0.9075), np.float32(0.758), np.float32(0.7002), np.float32(0.6283), np.float32(0.8516), np.float32(0.78), np.float32(0.8863), np.float32(0.8564), np.float32(0.9594), np.float32(0.9599), np.float32(0.9652), np.float32(0.8143), np.float32(0.7678), np.float32(0.8616), np.float32(0.9479), np.float32(0.3363), np.float32(0.3136)] +2025-11-11 21:17:54.425797: Epoch time: 258.72 s +2025-11-11 21:17:56.200913: +2025-11-11 21:17:56.202515: Epoch 263 +2025-11-11 21:17:56.203782: Current learning rate: 0.0076 +2025-11-11 21:22:16.265202: train_loss -0.6952 +2025-11-11 21:22:16.274712: val_loss -0.7056 +2025-11-11 21:22:16.277205: Pseudo dice [np.float32(0.914), np.float32(0.6813), np.float32(0.7119), np.float32(0.6213), np.float32(0.8606), np.float32(0.7872), np.float32(0.8711), np.float32(0.8395), np.float32(0.9737), np.float32(0.9716), np.float32(0.9678), np.float32(0.8124), np.float32(0.7363), np.float32(0.87), np.float32(0.9634), np.float32(0.3928), np.float32(0.3026)] +2025-11-11 21:22:16.279932: Epoch time: 260.07 s +2025-11-11 21:22:18.111056: +2025-11-11 21:22:18.112896: Epoch 264 +2025-11-11 21:22:18.114976: Current learning rate: 0.00759 +2025-11-11 21:26:36.796958: train_loss -0.6955 +2025-11-11 21:26:36.802083: val_loss -0.7018 +2025-11-11 21:26:36.804278: Pseudo dice [np.float32(0.9023), np.float32(0.7725), np.float32(0.7329), np.float32(0.6396), np.float32(0.8556), np.float32(0.777), np.float32(0.8654), np.float32(0.8487), np.float32(0.9701), np.float32(0.9551), np.float32(0.9661), np.float32(0.794), np.float32(0.7434), np.float32(0.8613), np.float32(0.9494), np.float32(0.4019), np.float32(0.3496)] +2025-11-11 21:26:36.806197: Epoch time: 258.69 s +2025-11-11 21:26:38.609964: +2025-11-11 21:26:38.612711: Epoch 265 +2025-11-11 21:26:38.615020: Current learning rate: 0.00758 +2025-11-11 21:30:57.291407: train_loss -0.6894 +2025-11-11 21:30:57.300849: val_loss -0.6973 +2025-11-11 21:30:57.303711: Pseudo dice [np.float32(0.9002), np.float32(0.673), np.float32(0.6888), np.float32(0.6279), np.float32(0.8494), np.float32(0.7843), np.float32(0.8801), np.float32(0.8544), np.float32(0.9596), np.float32(0.9605), np.float32(0.9672), np.float32(0.8136), np.float32(0.7426), np.float32(0.8634), np.float32(0.9522), np.float32(0.3673), np.float32(0.4443)] +2025-11-11 21:30:57.306516: Epoch time: 258.69 s +2025-11-11 21:30:59.120351: +2025-11-11 21:30:59.122056: Epoch 266 +2025-11-11 21:30:59.123831: Current learning rate: 0.00757 +2025-11-11 21:35:17.941932: train_loss -0.6908 +2025-11-11 21:35:17.946171: val_loss -0.6932 +2025-11-11 21:35:17.947470: Pseudo dice [np.float32(0.9074), np.float32(0.7614), np.float32(0.7283), np.float32(0.6012), np.float32(0.8402), np.float32(0.7719), np.float32(0.8685), np.float32(0.8502), np.float32(0.9572), np.float32(0.9501), np.float32(0.9651), np.float32(0.8249), np.float32(0.7238), np.float32(0.8581), np.float32(0.9397), np.float32(0.3415), np.float32(0.2819)] +2025-11-11 21:35:17.948534: Epoch time: 258.83 s +2025-11-11 21:35:19.793350: +2025-11-11 21:35:19.794969: Epoch 267 +2025-11-11 21:35:19.797136: Current learning rate: 0.00756 +2025-11-11 21:39:38.390681: train_loss -0.6892 +2025-11-11 21:39:38.395585: val_loss -0.69 +2025-11-11 21:39:38.397239: Pseudo dice [np.float32(0.9063), np.float32(0.7557), np.float32(0.6849), np.float32(0.61), np.float32(0.8485), np.float32(0.7923), np.float32(0.9018), np.float32(0.8301), np.float32(0.9668), np.float32(0.9639), np.float32(0.9655), np.float32(0.8017), np.float32(0.7358), np.float32(0.8634), np.float32(0.9571), np.float32(0.3433), np.float32(0.3264)] +2025-11-11 21:39:38.398795: Epoch time: 258.6 s +2025-11-11 21:39:40.201080: +2025-11-11 21:39:40.202616: Epoch 268 +2025-11-11 21:39:40.204155: Current learning rate: 0.00755 +2025-11-11 21:43:58.705370: train_loss -0.6896 +2025-11-11 21:43:58.710771: val_loss -0.7019 +2025-11-11 21:43:58.712457: Pseudo dice [np.float32(0.9011), np.float32(0.744), np.float32(0.6797), np.float32(0.6533), np.float32(0.8523), np.float32(0.7785), np.float32(0.8642), np.float32(0.8488), np.float32(0.9714), np.float32(0.9734), np.float32(0.9671), np.float32(0.8074), np.float32(0.7274), np.float32(0.8615), np.float32(0.9603), np.float32(0.4534), np.float32(0.4567)] +2025-11-11 21:43:58.713887: Epoch time: 258.51 s +2025-11-11 21:44:00.520929: +2025-11-11 21:44:00.522197: Epoch 269 +2025-11-11 21:44:00.523813: Current learning rate: 0.00754 +2025-11-11 21:48:19.163476: train_loss -0.6882 +2025-11-11 21:48:19.168467: val_loss -0.6836 +2025-11-11 21:48:19.169795: Pseudo dice [np.float32(0.9012), np.float32(0.7595), np.float32(0.6823), np.float32(0.6441), np.float32(0.8595), np.float32(0.7821), np.float32(0.8528), np.float32(0.842), np.float32(0.9464), np.float32(0.948), np.float32(0.9614), np.float32(0.8165), np.float32(0.7348), np.float32(0.8619), np.float32(0.926), np.float32(0.3209), np.float32(0.2861)] +2025-11-11 21:48:19.171872: Epoch time: 258.65 s +2025-11-11 21:48:20.978216: +2025-11-11 21:48:20.979635: Epoch 270 +2025-11-11 21:48:20.980927: Current learning rate: 0.00753 +2025-11-11 21:52:39.685689: train_loss -0.6874 +2025-11-11 21:52:39.690176: val_loss -0.6915 +2025-11-11 21:52:39.691673: Pseudo dice [np.float32(0.9182), np.float32(0.7725), np.float32(0.6829), np.float32(0.6385), np.float32(0.8431), np.float32(0.7777), np.float32(0.8567), np.float32(0.8473), np.float32(0.967), np.float32(0.9645), np.float32(0.9651), np.float32(0.7941), np.float32(0.7606), np.float32(0.8525), np.float32(0.9455), np.float32(0.3529), np.float32(0.2829)] +2025-11-11 21:52:39.693131: Epoch time: 258.71 s +2025-11-11 21:52:41.449399: +2025-11-11 21:52:41.450783: Epoch 271 +2025-11-11 21:52:41.452096: Current learning rate: 0.00752 +2025-11-11 21:56:59.906560: train_loss -0.6881 +2025-11-11 21:56:59.916355: val_loss -0.6901 +2025-11-11 21:56:59.919256: Pseudo dice [np.float32(0.9125), np.float32(0.7334), np.float32(0.6762), np.float32(0.6326), np.float32(0.8536), np.float32(0.7723), np.float32(0.8874), np.float32(0.8456), np.float32(0.9667), np.float32(0.9666), np.float32(0.9653), np.float32(0.8204), np.float32(0.7207), np.float32(0.8676), np.float32(0.9485), np.float32(0.3462), np.float32(0.3579)] +2025-11-11 21:56:59.922152: Epoch time: 258.46 s +2025-11-11 21:57:01.711803: +2025-11-11 21:57:01.714962: Epoch 272 +2025-11-11 21:57:01.717980: Current learning rate: 0.00751 +2025-11-11 22:01:21.281204: train_loss -0.6874 +2025-11-11 22:01:21.286129: val_loss -0.699 +2025-11-11 22:01:21.287722: Pseudo dice [np.float32(0.9158), np.float32(0.7726), np.float32(0.7189), np.float32(0.607), np.float32(0.8449), np.float32(0.7874), np.float32(0.8732), np.float32(0.8543), np.float32(0.9761), np.float32(0.9712), np.float32(0.9666), np.float32(0.826), np.float32(0.7298), np.float32(0.8582), np.float32(0.9597), np.float32(0.4605), np.float32(0.4731)] +2025-11-11 22:01:21.289150: Epoch time: 259.57 s +2025-11-11 22:01:23.081526: +2025-11-11 22:01:23.083915: Epoch 273 +2025-11-11 22:01:23.086319: Current learning rate: 0.00751 +2025-11-11 22:05:41.496972: train_loss -0.6901 +2025-11-11 22:05:41.503233: val_loss -0.7005 +2025-11-11 22:05:41.504877: Pseudo dice [np.float32(0.9085), np.float32(0.6813), np.float32(0.6995), np.float32(0.633), np.float32(0.8622), np.float32(0.7902), np.float32(0.8796), np.float32(0.8591), np.float32(0.968), np.float32(0.9661), np.float32(0.9675), np.float32(0.8162), np.float32(0.7287), np.float32(0.8663), np.float32(0.9547), np.float32(0.4351), np.float32(0.3165)] +2025-11-11 22:05:41.507488: Epoch time: 258.42 s +2025-11-11 22:05:43.350147: +2025-11-11 22:05:43.353102: Epoch 274 +2025-11-11 22:05:43.355676: Current learning rate: 0.0075 +2025-11-11 22:10:02.102713: train_loss -0.6901 +2025-11-11 22:10:02.112787: val_loss -0.6997 +2025-11-11 22:10:02.115852: Pseudo dice [np.float32(0.914), np.float32(0.7487), np.float32(0.6865), np.float32(0.6413), np.float32(0.8516), np.float32(0.7768), np.float32(0.8943), np.float32(0.8439), np.float32(0.9719), np.float32(0.9675), np.float32(0.9681), np.float32(0.8236), np.float32(0.7197), np.float32(0.8559), np.float32(0.9559), np.float32(0.4472), np.float32(0.3914)] +2025-11-11 22:10:02.118595: Epoch time: 258.76 s +2025-11-11 22:10:03.927346: +2025-11-11 22:10:03.930110: Epoch 275 +2025-11-11 22:10:03.932809: Current learning rate: 0.00749 +2025-11-11 22:14:22.865272: train_loss -0.6902 +2025-11-11 22:14:22.874026: val_loss -0.6974 +2025-11-11 22:14:22.876458: Pseudo dice [np.float32(0.91), np.float32(0.7204), np.float32(0.6825), np.float32(0.6054), np.float32(0.8555), np.float32(0.7709), np.float32(0.8805), np.float32(0.8432), np.float32(0.972), np.float32(0.9708), np.float32(0.9681), np.float32(0.8124), np.float32(0.7009), np.float32(0.8619), np.float32(0.9619), np.float32(0.3854), np.float32(0.3834)] +2025-11-11 22:14:22.878404: Epoch time: 258.94 s +2025-11-11 22:14:24.693484: +2025-11-11 22:14:24.695887: Epoch 276 +2025-11-11 22:14:24.697634: Current learning rate: 0.00748 +2025-11-11 22:18:43.483864: train_loss -0.6985 +2025-11-11 22:18:43.491421: val_loss -0.7053 +2025-11-11 22:18:43.494509: Pseudo dice [np.float32(0.9115), np.float32(0.7788), np.float32(0.7064), np.float32(0.6326), np.float32(0.8621), np.float32(0.7972), np.float32(0.9009), np.float32(0.854), np.float32(0.9756), np.float32(0.9774), np.float32(0.9691), np.float32(0.8155), np.float32(0.7146), np.float32(0.8681), np.float32(0.9649), np.float32(0.3661), np.float32(0.2953)] +2025-11-11 22:18:43.496757: Epoch time: 258.8 s +2025-11-11 22:18:45.287027: +2025-11-11 22:18:45.288806: Epoch 277 +2025-11-11 22:18:45.291066: Current learning rate: 0.00747 +2025-11-11 22:23:04.023507: train_loss -0.6925 +2025-11-11 22:23:04.028218: val_loss -0.7029 +2025-11-11 22:23:04.030654: Pseudo dice [np.float32(0.8995), np.float32(0.7333), np.float32(0.6826), np.float32(0.648), np.float32(0.8504), np.float32(0.7977), np.float32(0.8874), np.float32(0.8448), np.float32(0.973), np.float32(0.9722), np.float32(0.9675), np.float32(0.839), np.float32(0.7336), np.float32(0.8581), np.float32(0.9593), np.float32(0.373), np.float32(0.2785)] +2025-11-11 22:23:04.032498: Epoch time: 258.74 s +2025-11-11 22:23:05.844989: +2025-11-11 22:23:05.846574: Epoch 278 +2025-11-11 22:23:05.848299: Current learning rate: 0.00746 +2025-11-11 22:27:24.622734: train_loss -0.6956 +2025-11-11 22:27:24.626680: val_loss -0.7011 +2025-11-11 22:27:24.627816: Pseudo dice [np.float32(0.9117), np.float32(0.7549), np.float32(0.6665), np.float32(0.618), np.float32(0.8574), np.float32(0.7746), np.float32(0.8959), np.float32(0.8516), np.float32(0.9631), np.float32(0.9655), np.float32(0.9673), np.float32(0.8273), np.float32(0.7631), np.float32(0.8638), np.float32(0.9552), np.float32(0.447), np.float32(0.3136)] +2025-11-11 22:27:24.628895: Epoch time: 258.78 s +2025-11-11 22:27:26.414893: +2025-11-11 22:27:26.416384: Epoch 279 +2025-11-11 22:27:26.417696: Current learning rate: 0.00745 +2025-11-11 22:31:45.309220: train_loss -0.6937 +2025-11-11 22:31:45.313252: val_loss -0.6974 +2025-11-11 22:31:45.314557: Pseudo dice [np.float32(0.9018), np.float32(0.741), np.float32(0.6943), np.float32(0.6261), np.float32(0.8588), np.float32(0.7754), np.float32(0.8645), np.float32(0.8504), np.float32(0.9724), np.float32(0.9648), np.float32(0.9685), np.float32(0.8227), np.float32(0.7141), np.float32(0.8695), np.float32(0.9602), np.float32(0.3753), np.float32(0.2604)] +2025-11-11 22:31:45.315887: Epoch time: 258.9 s +2025-11-11 22:31:47.161542: +2025-11-11 22:31:47.162993: Epoch 280 +2025-11-11 22:31:47.164510: Current learning rate: 0.00744 +2025-11-11 22:36:05.770226: train_loss -0.6882 +2025-11-11 22:36:05.775592: val_loss -0.6948 +2025-11-11 22:36:05.777032: Pseudo dice [np.float32(0.8885), np.float32(0.7532), np.float32(0.6972), np.float32(0.5947), np.float32(0.8559), np.float32(0.7917), np.float32(0.8518), np.float32(0.8386), np.float32(0.973), np.float32(0.9718), np.float32(0.9655), np.float32(0.8104), np.float32(0.7025), np.float32(0.8672), np.float32(0.9581), np.float32(0.4598), np.float32(0.3299)] +2025-11-11 22:36:05.778764: Epoch time: 258.61 s +2025-11-11 22:36:07.545643: +2025-11-11 22:36:07.547017: Epoch 281 +2025-11-11 22:36:07.548497: Current learning rate: 0.00743 +2025-11-11 22:40:26.250086: train_loss -0.6816 +2025-11-11 22:40:26.255116: val_loss -0.7046 +2025-11-11 22:40:26.256578: Pseudo dice [np.float32(0.9108), np.float32(0.7486), np.float32(0.7026), np.float32(0.5815), np.float32(0.8566), np.float32(0.7936), np.float32(0.8936), np.float32(0.8401), np.float32(0.9718), np.float32(0.9729), np.float32(0.9672), np.float32(0.8088), np.float32(0.7212), np.float32(0.8701), np.float32(0.9599), np.float32(0.4349), np.float32(0.3389)] +2025-11-11 22:40:26.258085: Epoch time: 258.71 s +2025-11-11 22:40:28.077790: +2025-11-11 22:40:28.079350: Epoch 282 +2025-11-11 22:40:28.080548: Current learning rate: 0.00742 +2025-11-11 22:44:48.127614: train_loss -0.6888 +2025-11-11 22:44:48.131719: val_loss -0.7046 +2025-11-11 22:44:48.132967: Pseudo dice [np.float32(0.9064), np.float32(0.7548), np.float32(0.7071), np.float32(0.6128), np.float32(0.8581), np.float32(0.7838), np.float32(0.8769), np.float32(0.8519), np.float32(0.972), np.float32(0.9684), np.float32(0.9659), np.float32(0.8155), np.float32(0.7529), np.float32(0.8615), np.float32(0.9498), np.float32(0.412), np.float32(0.4294)] +2025-11-11 22:44:48.134235: Epoch time: 260.06 s +2025-11-11 22:44:50.009375: +2025-11-11 22:44:50.011175: Epoch 283 +2025-11-11 22:44:50.012798: Current learning rate: 0.00741 +2025-11-11 22:49:08.831833: train_loss -0.6922 +2025-11-11 22:49:08.835946: val_loss -0.711 +2025-11-11 22:49:08.837281: Pseudo dice [np.float32(0.915), np.float32(0.7779), np.float32(0.6994), np.float32(0.639), np.float32(0.8473), np.float32(0.7926), np.float32(0.9013), np.float32(0.846), np.float32(0.9697), np.float32(0.9723), np.float32(0.9676), np.float32(0.8209), np.float32(0.7673), np.float32(0.8631), np.float32(0.9587), np.float32(0.3839), np.float32(0.3184)] +2025-11-11 22:49:08.838625: Epoch time: 258.83 s +2025-11-11 22:49:08.839856: Yayy! New best EMA pseudo Dice: 0.7853999733924866 +2025-11-11 22:49:17.325248: +2025-11-11 22:49:17.327586: Epoch 284 +2025-11-11 22:49:17.329646: Current learning rate: 0.0074 +2025-11-11 22:53:35.906434: train_loss -0.6886 +2025-11-11 22:53:35.910923: val_loss -0.7029 +2025-11-11 22:53:35.912474: Pseudo dice [np.float32(0.9144), np.float32(0.7487), np.float32(0.707), np.float32(0.6323), np.float32(0.854), np.float32(0.7829), np.float32(0.8804), np.float32(0.8462), np.float32(0.9549), np.float32(0.9513), np.float32(0.9643), np.float32(0.8112), np.float32(0.765), np.float32(0.8635), np.float32(0.9418), np.float32(0.4365), np.float32(0.3968)] +2025-11-11 22:53:35.913668: Epoch time: 258.59 s +2025-11-11 22:53:35.914690: Yayy! New best EMA pseudo Dice: 0.7860000133514404 +2025-11-11 22:53:40.852754: +2025-11-11 22:53:40.854324: Epoch 285 +2025-11-11 22:53:40.855835: Current learning rate: 0.00739 +2025-11-11 22:57:59.691296: train_loss -0.6909 +2025-11-11 22:57:59.696859: val_loss -0.7097 +2025-11-11 22:57:59.699012: Pseudo dice [np.float32(0.9087), np.float32(0.7669), np.float32(0.7353), np.float32(0.623), np.float32(0.8605), np.float32(0.7928), np.float32(0.8759), np.float32(0.8522), np.float32(0.9637), np.float32(0.9638), np.float32(0.9675), np.float32(0.8259), np.float32(0.735), np.float32(0.8642), np.float32(0.9575), np.float32(0.3937), np.float32(0.3696)] +2025-11-11 22:57:59.700825: Epoch time: 258.84 s +2025-11-11 22:57:59.702234: Yayy! New best EMA pseudo Dice: 0.7865999937057495 +2025-11-11 22:58:04.690556: +2025-11-11 22:58:04.692007: Epoch 286 +2025-11-11 22:58:04.693296: Current learning rate: 0.00738 +2025-11-11 23:02:23.312009: train_loss -0.6907 +2025-11-11 23:02:23.317149: val_loss -0.7068 +2025-11-11 23:02:23.318748: Pseudo dice [np.float32(0.9137), np.float32(0.7626), np.float32(0.6769), np.float32(0.6131), np.float32(0.8642), np.float32(0.7918), np.float32(0.8825), np.float32(0.8396), np.float32(0.9703), np.float32(0.9691), np.float32(0.968), np.float32(0.8223), np.float32(0.7548), np.float32(0.8762), np.float32(0.9573), np.float32(0.4542), np.float32(0.3903)] +2025-11-11 23:02:23.320274: Epoch time: 258.63 s +2025-11-11 23:02:23.321709: Yayy! New best EMA pseudo Dice: 0.7874000072479248 +2025-11-11 23:02:28.189921: +2025-11-11 23:02:28.192029: Epoch 287 +2025-11-11 23:02:28.193443: Current learning rate: 0.00738 +2025-11-11 23:06:46.733808: train_loss -0.693 +2025-11-11 23:06:46.739748: val_loss -0.7055 +2025-11-11 23:06:46.741123: Pseudo dice [np.float32(0.9037), np.float32(0.7692), np.float32(0.7135), np.float32(0.6444), np.float32(0.8586), np.float32(0.7764), np.float32(0.8887), np.float32(0.8528), np.float32(0.9743), np.float32(0.9757), np.float32(0.9665), np.float32(0.8301), np.float32(0.7436), np.float32(0.8688), np.float32(0.9624), np.float32(0.3787), np.float32(0.4012)] +2025-11-11 23:06:46.742288: Epoch time: 258.55 s +2025-11-11 23:06:46.743679: Yayy! New best EMA pseudo Dice: 0.788100004196167 +2025-11-11 23:06:51.705200: +2025-11-11 23:06:51.706729: Epoch 288 +2025-11-11 23:06:51.708146: Current learning rate: 0.00737 +2025-11-11 23:11:10.566748: train_loss -0.6911 +2025-11-11 23:11:10.570864: val_loss -0.7064 +2025-11-11 23:11:10.572448: Pseudo dice [np.float32(0.9168), np.float32(0.7584), np.float32(0.7282), np.float32(0.6373), np.float32(0.8592), np.float32(0.7991), np.float32(0.8755), np.float32(0.8442), np.float32(0.9787), np.float32(0.9765), np.float32(0.967), np.float32(0.8269), np.float32(0.7622), np.float32(0.8622), np.float32(0.96), np.float32(0.2908), np.float32(0.3496)] +2025-11-11 23:11:10.573938: Epoch time: 258.87 s +2025-11-11 23:11:12.371500: +2025-11-11 23:11:12.373101: Epoch 289 +2025-11-11 23:11:12.374506: Current learning rate: 0.00736 +2025-11-11 23:15:31.050489: train_loss -0.6941 +2025-11-11 23:15:31.055641: val_loss -0.6942 +2025-11-11 23:15:31.057537: Pseudo dice [np.float32(0.909), np.float32(0.6381), np.float32(0.6875), np.float32(0.6099), np.float32(0.8639), np.float32(0.7831), np.float32(0.8883), np.float32(0.8615), np.float32(0.9635), np.float32(0.9654), np.float32(0.9671), np.float32(0.8266), np.float32(0.7355), np.float32(0.8656), np.float32(0.9542), np.float32(0.2876), np.float32(0.2521)] +2025-11-11 23:15:31.058800: Epoch time: 258.68 s +2025-11-11 23:15:32.839389: +2025-11-11 23:15:32.841515: Epoch 290 +2025-11-11 23:15:32.843153: Current learning rate: 0.00735 +2025-11-11 23:19:52.508359: train_loss -0.6912 +2025-11-11 23:19:52.513292: val_loss -0.6952 +2025-11-11 23:19:52.514873: Pseudo dice [np.float32(0.913), np.float32(0.7626), np.float32(0.7139), np.float32(0.6263), np.float32(0.857), np.float32(0.786), np.float32(0.8673), np.float32(0.8373), np.float32(0.9755), np.float32(0.9774), np.float32(0.9669), np.float32(0.8099), np.float32(0.7581), np.float32(0.8628), np.float32(0.9609), np.float32(0.3613), np.float32(0.3061)] +2025-11-11 23:19:52.516379: Epoch time: 259.67 s +2025-11-11 23:19:54.310950: +2025-11-11 23:19:54.312437: Epoch 291 +2025-11-11 23:19:54.314743: Current learning rate: 0.00734 +2025-11-11 23:24:13.005722: train_loss -0.6843 +2025-11-11 23:24:13.009933: val_loss -0.7018 +2025-11-11 23:24:13.011104: Pseudo dice [np.float32(0.9192), np.float32(0.7383), np.float32(0.7145), np.float32(0.6453), np.float32(0.8525), np.float32(0.7806), np.float32(0.8834), np.float32(0.8541), np.float32(0.9696), np.float32(0.9735), np.float32(0.9659), np.float32(0.8083), np.float32(0.7484), np.float32(0.8526), np.float32(0.9564), np.float32(0.4437), np.float32(0.3542)] +2025-11-11 23:24:13.012606: Epoch time: 258.7 s +2025-11-11 23:24:14.754365: +2025-11-11 23:24:14.756041: Epoch 292 +2025-11-11 23:24:14.758013: Current learning rate: 0.00733 +2025-11-11 23:28:33.287346: train_loss -0.6868 +2025-11-11 23:28:33.293166: val_loss -0.701 +2025-11-11 23:28:33.295002: Pseudo dice [np.float32(0.916), np.float32(0.7315), np.float32(0.7183), np.float32(0.6425), np.float32(0.8518), np.float32(0.7793), np.float32(0.8778), np.float32(0.835), np.float32(0.9714), np.float32(0.9749), np.float32(0.9656), np.float32(0.7895), np.float32(0.7405), np.float32(0.8616), np.float32(0.9597), np.float32(0.3789), np.float32(0.3967)] +2025-11-11 23:28:33.296948: Epoch time: 258.54 s +2025-11-11 23:28:35.306933: +2025-11-11 23:28:35.309529: Epoch 293 +2025-11-11 23:28:35.312182: Current learning rate: 0.00732 +2025-11-11 23:32:54.006943: train_loss -0.6883 +2025-11-11 23:32:54.011152: val_loss -0.6944 +2025-11-11 23:32:54.012985: Pseudo dice [np.float32(0.9094), np.float32(0.7491), np.float32(0.7181), np.float32(0.5952), np.float32(0.8533), np.float32(0.791), np.float32(0.8878), np.float32(0.8422), np.float32(0.9465), np.float32(0.9507), np.float32(0.9629), np.float32(0.8122), np.float32(0.7583), np.float32(0.863), np.float32(0.9424), np.float32(0.4537), np.float32(0.3023)] +2025-11-11 23:32:54.014428: Epoch time: 258.71 s +2025-11-11 23:32:55.840269: +2025-11-11 23:32:55.842007: Epoch 294 +2025-11-11 23:32:55.843634: Current learning rate: 0.00731 +2025-11-11 23:37:14.463406: train_loss -0.6888 +2025-11-11 23:37:14.469489: val_loss -0.7036 +2025-11-11 23:37:14.471401: Pseudo dice [np.float32(0.9116), np.float32(0.6934), np.float32(0.7173), np.float32(0.6162), np.float32(0.8555), np.float32(0.7968), np.float32(0.8889), np.float32(0.8524), np.float32(0.9755), np.float32(0.9732), np.float32(0.967), np.float32(0.8279), np.float32(0.7498), np.float32(0.8626), np.float32(0.9632), np.float32(0.3436), np.float32(0.398)] +2025-11-11 23:37:14.473185: Epoch time: 258.63 s +2025-11-11 23:37:16.319782: +2025-11-11 23:37:16.321241: Epoch 295 +2025-11-11 23:37:16.322470: Current learning rate: 0.0073 +2025-11-11 23:41:34.616460: train_loss -0.6922 +2025-11-11 23:41:34.620649: val_loss -0.6999 +2025-11-11 23:41:34.621933: Pseudo dice [np.float32(0.9173), np.float32(0.753), np.float32(0.7296), np.float32(0.6495), np.float32(0.8488), np.float32(0.7824), np.float32(0.9004), np.float32(0.837), np.float32(0.9745), np.float32(0.9733), np.float32(0.968), np.float32(0.8177), np.float32(0.7568), np.float32(0.8639), np.float32(0.9544), np.float32(0.2999), np.float32(0.2906)] +2025-11-11 23:41:34.623089: Epoch time: 258.3 s +2025-11-11 23:41:36.363196: +2025-11-11 23:41:36.364960: Epoch 296 +2025-11-11 23:41:36.366559: Current learning rate: 0.00729 +2025-11-11 23:45:55.158026: train_loss -0.6929 +2025-11-11 23:45:55.164404: val_loss -0.694 +2025-11-11 23:45:55.166138: Pseudo dice [np.float32(0.901), np.float32(0.7396), np.float32(0.7069), np.float32(0.6293), np.float32(0.8572), np.float32(0.7849), np.float32(0.8687), np.float32(0.8437), np.float32(0.9769), np.float32(0.9734), np.float32(0.9672), np.float32(0.813), np.float32(0.7368), np.float32(0.8612), np.float32(0.963), np.float32(0.3539), np.float32(0.308)] +2025-11-11 23:45:55.167972: Epoch time: 258.8 s +2025-11-11 23:45:56.991587: +2025-11-11 23:45:56.993318: Epoch 297 +2025-11-11 23:45:56.994861: Current learning rate: 0.00728 +2025-11-11 23:50:15.614184: train_loss -0.6873 +2025-11-11 23:50:15.620651: val_loss -0.6958 +2025-11-11 23:50:15.622393: Pseudo dice [np.float32(0.9131), np.float32(0.742), np.float32(0.6925), np.float32(0.6466), np.float32(0.8507), np.float32(0.7817), np.float32(0.8716), np.float32(0.8363), np.float32(0.9662), np.float32(0.9638), np.float32(0.9642), np.float32(0.8184), np.float32(0.723), np.float32(0.8629), np.float32(0.9471), np.float32(0.3503), np.float32(0.2994)] +2025-11-11 23:50:15.624179: Epoch time: 258.63 s +2025-11-11 23:50:17.384478: +2025-11-11 23:50:17.387546: Epoch 298 +2025-11-11 23:50:17.389872: Current learning rate: 0.00727 +2025-11-11 23:54:36.049299: train_loss -0.6796 +2025-11-11 23:54:36.054230: val_loss -0.6872 +2025-11-11 23:54:36.056218: Pseudo dice [np.float32(0.9088), np.float32(0.7482), np.float32(0.6871), np.float32(0.6201), np.float32(0.8495), np.float32(0.7416), np.float32(0.8836), np.float32(0.845), np.float32(0.9614), np.float32(0.9615), np.float32(0.9648), np.float32(0.8004), np.float32(0.7191), np.float32(0.8544), np.float32(0.946), np.float32(0.346), np.float32(0.3421)] +2025-11-11 23:54:36.058281: Epoch time: 258.67 s +2025-11-11 23:54:37.861150: +2025-11-11 23:54:37.862842: Epoch 299 +2025-11-11 23:54:37.864425: Current learning rate: 0.00726 +2025-11-11 23:58:56.260534: train_loss -0.6798 +2025-11-11 23:58:56.265692: val_loss -0.6913 +2025-11-11 23:58:56.267273: Pseudo dice [np.float32(0.9127), np.float32(0.759), np.float32(0.7116), np.float32(0.6182), np.float32(0.8529), np.float32(0.7867), np.float32(0.8485), np.float32(0.8433), np.float32(0.9628), np.float32(0.9631), np.float32(0.9644), np.float32(0.813), np.float32(0.7289), np.float32(0.8538), np.float32(0.952), np.float32(0.3199), np.float32(0.2649)] +2025-11-11 23:58:56.269019: Epoch time: 258.4 s +2025-11-11 23:59:02.453702: +2025-11-11 23:59:02.455197: Epoch 300 +2025-11-11 23:59:02.456363: Current learning rate: 0.00725 +2025-11-12 00:03:21.006237: train_loss -0.6841 +2025-11-12 00:03:21.010174: val_loss -0.7076 +2025-11-12 00:03:21.011374: Pseudo dice [np.float32(0.9105), np.float32(0.7734), np.float32(0.7147), np.float32(0.62), np.float32(0.8508), np.float32(0.784), np.float32(0.8977), np.float32(0.8369), np.float32(0.9704), np.float32(0.9696), np.float32(0.9664), np.float32(0.8215), np.float32(0.7554), np.float32(0.8633), np.float32(0.9545), np.float32(0.4279), np.float32(0.3807)] +2025-11-12 00:03:21.012810: Epoch time: 258.56 s +2025-11-12 00:03:22.791061: +2025-11-12 00:03:22.792482: Epoch 301 +2025-11-12 00:03:22.794040: Current learning rate: 0.00724 +2025-11-12 00:07:41.029986: train_loss -0.6919 +2025-11-12 00:07:41.034710: val_loss -0.6954 +2025-11-12 00:07:41.036149: Pseudo dice [np.float32(0.9072), np.float32(0.7763), np.float32(0.6873), np.float32(0.6384), np.float32(0.8548), np.float32(0.7798), np.float32(0.8703), np.float32(0.8327), np.float32(0.9653), np.float32(0.9708), np.float32(0.9681), np.float32(0.8233), np.float32(0.7011), np.float32(0.864), np.float32(0.9585), np.float32(0.3893), np.float32(0.2928)] +2025-11-12 00:07:41.037902: Epoch time: 258.24 s +2025-11-12 00:07:42.883540: +2025-11-12 00:07:42.885293: Epoch 302 +2025-11-12 00:07:42.886985: Current learning rate: 0.00724 +2025-11-12 00:12:01.198912: train_loss -0.6914 +2025-11-12 00:12:01.203336: val_loss -0.7024 +2025-11-12 00:12:01.204713: Pseudo dice [np.float32(0.91), np.float32(0.7231), np.float32(0.7416), np.float32(0.6153), np.float32(0.8513), np.float32(0.7928), np.float32(0.8626), np.float32(0.8448), np.float32(0.9641), np.float32(0.9678), np.float32(0.9665), np.float32(0.8202), np.float32(0.7488), np.float32(0.8678), np.float32(0.9526), np.float32(0.3552), np.float32(0.3828)] +2025-11-12 00:12:01.206360: Epoch time: 258.32 s +2025-11-12 00:12:03.008328: +2025-11-12 00:12:03.010621: Epoch 303 +2025-11-12 00:12:03.012270: Current learning rate: 0.00723 +2025-11-12 00:16:21.214635: train_loss -0.6948 +2025-11-12 00:16:21.219701: val_loss -0.7101 +2025-11-12 00:16:21.221701: Pseudo dice [np.float32(0.911), np.float32(0.7755), np.float32(0.7208), np.float32(0.6171), np.float32(0.8545), np.float32(0.8162), np.float32(0.9017), np.float32(0.8595), np.float32(0.9752), np.float32(0.976), np.float32(0.9677), np.float32(0.8282), np.float32(0.7709), np.float32(0.8739), np.float32(0.9524), np.float32(0.342), np.float32(0.3669)] +2025-11-12 00:16:21.223568: Epoch time: 258.21 s +2025-11-12 00:16:23.032716: +2025-11-12 00:16:23.034688: Epoch 304 +2025-11-12 00:16:23.036276: Current learning rate: 0.00722 +2025-11-12 00:20:41.354296: train_loss -0.6875 +2025-11-12 00:20:41.358841: val_loss -0.6997 +2025-11-12 00:20:41.360360: Pseudo dice [np.float32(0.9081), np.float32(0.7435), np.float32(0.7011), np.float32(0.613), np.float32(0.853), np.float32(0.7717), np.float32(0.8911), np.float32(0.8404), np.float32(0.9602), np.float32(0.959), np.float32(0.9669), np.float32(0.8098), np.float32(0.741), np.float32(0.8626), np.float32(0.9586), np.float32(0.3927), np.float32(0.2776)] +2025-11-12 00:20:41.361634: Epoch time: 258.33 s +2025-11-12 00:20:43.183964: +2025-11-12 00:20:43.185640: Epoch 305 +2025-11-12 00:20:43.186959: Current learning rate: 0.00721 +2025-11-12 00:25:01.461492: train_loss -0.6844 +2025-11-12 00:25:01.470106: val_loss -0.6908 +2025-11-12 00:25:01.471693: Pseudo dice [np.float32(0.8973), np.float32(0.7457), np.float32(0.6648), np.float32(0.6224), np.float32(0.858), np.float32(0.7737), np.float32(0.8784), np.float32(0.8398), np.float32(0.9658), np.float32(0.968), np.float32(0.9671), np.float32(0.8164), np.float32(0.7658), np.float32(0.8661), np.float32(0.9626), np.float32(0.4082), np.float32(0.2515)] +2025-11-12 00:25:01.473011: Epoch time: 258.28 s +2025-11-12 00:25:03.304950: +2025-11-12 00:25:03.307243: Epoch 306 +2025-11-12 00:25:03.310080: Current learning rate: 0.0072 +2025-11-12 00:29:22.039413: train_loss -0.6866 +2025-11-12 00:29:22.050123: val_loss -0.6944 +2025-11-12 00:29:22.052914: Pseudo dice [np.float32(0.9095), np.float32(0.7485), np.float32(0.6724), np.float32(0.6258), np.float32(0.8546), np.float32(0.7816), np.float32(0.8864), np.float32(0.8398), np.float32(0.9509), np.float32(0.9437), np.float32(0.9673), np.float32(0.8249), np.float32(0.7537), np.float32(0.8659), np.float32(0.9534), np.float32(0.3425), np.float32(0.324)] +2025-11-12 00:29:22.056039: Epoch time: 258.74 s +2025-11-12 00:29:23.872571: +2025-11-12 00:29:23.874414: Epoch 307 +2025-11-12 00:29:23.875997: Current learning rate: 0.00719 +2025-11-12 00:33:42.463469: train_loss -0.693 +2025-11-12 00:33:42.469866: val_loss -0.6919 +2025-11-12 00:33:42.472289: Pseudo dice [np.float32(0.9171), np.float32(0.6913), np.float32(0.69), np.float32(0.6415), np.float32(0.8498), np.float32(0.7803), np.float32(0.8767), np.float32(0.8413), np.float32(0.9732), np.float32(0.9743), np.float32(0.9664), np.float32(0.8185), np.float32(0.7409), np.float32(0.8664), np.float32(0.9492), np.float32(0.446), np.float32(0.319)] +2025-11-12 00:33:42.474566: Epoch time: 258.6 s +2025-11-12 00:33:44.290328: +2025-11-12 00:33:44.292763: Epoch 308 +2025-11-12 00:33:44.294130: Current learning rate: 0.00718 +2025-11-12 00:38:02.889206: train_loss -0.6844 +2025-11-12 00:38:02.893183: val_loss -0.7005 +2025-11-12 00:38:02.895093: Pseudo dice [np.float32(0.9142), np.float32(0.7518), np.float32(0.7171), np.float32(0.6585), np.float32(0.8504), np.float32(0.7852), np.float32(0.8877), np.float32(0.8524), np.float32(0.9642), np.float32(0.9631), np.float32(0.9625), np.float32(0.8159), np.float32(0.7407), np.float32(0.8613), np.float32(0.9353), np.float32(0.3695), np.float32(0.3269)] +2025-11-12 00:38:02.896295: Epoch time: 258.6 s +2025-11-12 00:38:04.762600: +2025-11-12 00:38:04.764801: Epoch 309 +2025-11-12 00:38:04.766741: Current learning rate: 0.00717 +2025-11-12 00:42:24.384731: train_loss -0.6778 +2025-11-12 00:42:24.392018: val_loss -0.6941 +2025-11-12 00:42:24.394480: Pseudo dice [np.float32(0.9052), np.float32(0.7864), np.float32(0.717), np.float32(0.6462), np.float32(0.8509), np.float32(0.7704), np.float32(0.8757), np.float32(0.8367), np.float32(0.9737), np.float32(0.9664), np.float32(0.9644), np.float32(0.8062), np.float32(0.7308), np.float32(0.8522), np.float32(0.9544), np.float32(0.3712), np.float32(0.3281)] +2025-11-12 00:42:24.396908: Epoch time: 259.63 s +2025-11-12 00:42:26.264556: +2025-11-12 00:42:26.266302: Epoch 310 +2025-11-12 00:42:26.268250: Current learning rate: 0.00716 +2025-11-12 00:46:44.856503: train_loss -0.6816 +2025-11-12 00:46:44.865659: val_loss -0.7094 +2025-11-12 00:46:44.868464: Pseudo dice [np.float32(0.9167), np.float32(0.7656), np.float32(0.7237), np.float32(0.6349), np.float32(0.8538), np.float32(0.7907), np.float32(0.8795), np.float32(0.8534), np.float32(0.9744), np.float32(0.9657), np.float32(0.9655), np.float32(0.8117), np.float32(0.7522), np.float32(0.8689), np.float32(0.9512), np.float32(0.4177), np.float32(0.3347)] +2025-11-12 00:46:44.870825: Epoch time: 258.6 s +2025-11-12 00:46:46.771087: +2025-11-12 00:46:46.773432: Epoch 311 +2025-11-12 00:46:46.775069: Current learning rate: 0.00715 +2025-11-12 00:51:05.449058: train_loss -0.6902 +2025-11-12 00:51:05.458214: val_loss -0.7048 +2025-11-12 00:51:05.460204: Pseudo dice [np.float32(0.9168), np.float32(0.7428), np.float32(0.6807), np.float32(0.6335), np.float32(0.8551), np.float32(0.7832), np.float32(0.8832), np.float32(0.8578), np.float32(0.9713), np.float32(0.9657), np.float32(0.9675), np.float32(0.8287), np.float32(0.7395), np.float32(0.8644), np.float32(0.9538), np.float32(0.3327), np.float32(0.3136)] +2025-11-12 00:51:05.462588: Epoch time: 258.68 s +2025-11-12 00:51:07.277346: +2025-11-12 00:51:07.279048: Epoch 312 +2025-11-12 00:51:07.280863: Current learning rate: 0.00714 +2025-11-12 00:55:25.822812: train_loss -0.6856 +2025-11-12 00:55:25.827861: val_loss -0.7137 +2025-11-12 00:55:25.829439: Pseudo dice [np.float32(0.9111), np.float32(0.759), np.float32(0.7017), np.float32(0.6614), np.float32(0.859), np.float32(0.7827), np.float32(0.8895), np.float32(0.8614), np.float32(0.9707), np.float32(0.9762), np.float32(0.9663), np.float32(0.8273), np.float32(0.7466), np.float32(0.8712), np.float32(0.9537), np.float32(0.4478), np.float32(0.3396)] +2025-11-12 00:55:25.831580: Epoch time: 258.55 s +2025-11-12 00:55:27.690528: +2025-11-12 00:55:27.692161: Epoch 313 +2025-11-12 00:55:27.693608: Current learning rate: 0.00713 +2025-11-12 00:59:46.402009: train_loss -0.6906 +2025-11-12 00:59:46.406635: val_loss -0.7012 +2025-11-12 00:59:46.407825: Pseudo dice [np.float32(0.9038), np.float32(0.7745), np.float32(0.6854), np.float32(0.6561), np.float32(0.8544), np.float32(0.7897), np.float32(0.8712), np.float32(0.8469), np.float32(0.9638), np.float32(0.9631), np.float32(0.9666), np.float32(0.8268), np.float32(0.7341), np.float32(0.8688), np.float32(0.9556), np.float32(0.3892), np.float32(0.3695)] +2025-11-12 00:59:46.408981: Epoch time: 258.72 s +2025-11-12 00:59:48.250082: +2025-11-12 00:59:48.251985: Epoch 314 +2025-11-12 00:59:48.253840: Current learning rate: 0.00712 +2025-11-12 01:04:06.620936: train_loss -0.6918 +2025-11-12 01:04:06.627107: val_loss -0.7113 +2025-11-12 01:04:06.628564: Pseudo dice [np.float32(0.9121), np.float32(0.7713), np.float32(0.7003), np.float32(0.6705), np.float32(0.8517), np.float32(0.7952), np.float32(0.8765), np.float32(0.8424), np.float32(0.9756), np.float32(0.9741), np.float32(0.9666), np.float32(0.8071), np.float32(0.7503), np.float32(0.8695), np.float32(0.9625), np.float32(0.4064), np.float32(0.3106)] +2025-11-12 01:04:06.630099: Epoch time: 258.38 s +2025-11-12 01:04:08.456954: +2025-11-12 01:04:08.458816: Epoch 315 +2025-11-12 01:04:08.461327: Current learning rate: 0.00711 +2025-11-12 01:08:27.119040: train_loss -0.6946 +2025-11-12 01:08:27.127584: val_loss -0.7006 +2025-11-12 01:08:27.130174: Pseudo dice [np.float32(0.9089), np.float32(0.7645), np.float32(0.7135), np.float32(0.6116), np.float32(0.859), np.float32(0.7811), np.float32(0.8914), np.float32(0.8522), np.float32(0.9692), np.float32(0.9672), np.float32(0.9665), np.float32(0.8164), np.float32(0.7678), np.float32(0.869), np.float32(0.9508), np.float32(0.3314), np.float32(0.3064)] +2025-11-12 01:08:27.132972: Epoch time: 258.67 s +2025-11-12 01:08:28.927600: +2025-11-12 01:08:28.929326: Epoch 316 +2025-11-12 01:08:28.931566: Current learning rate: 0.0071 +2025-11-12 01:12:47.538648: train_loss -0.6896 +2025-11-12 01:12:47.545542: val_loss -0.7057 +2025-11-12 01:12:47.547122: Pseudo dice [np.float32(0.9163), np.float32(0.7582), np.float32(0.6756), np.float32(0.6194), np.float32(0.8541), np.float32(0.7861), np.float32(0.8629), np.float32(0.8472), np.float32(0.9631), np.float32(0.9604), np.float32(0.9659), np.float32(0.8102), np.float32(0.7626), np.float32(0.8648), np.float32(0.9543), np.float32(0.4325), np.float32(0.4171)] +2025-11-12 01:12:47.548865: Epoch time: 258.62 s +2025-11-12 01:12:49.387996: +2025-11-12 01:12:49.390637: Epoch 317 +2025-11-12 01:12:49.393208: Current learning rate: 0.0071 +2025-11-12 01:17:07.870810: train_loss -0.6835 +2025-11-12 01:17:07.879859: val_loss -0.7021 +2025-11-12 01:17:07.882511: Pseudo dice [np.float32(0.9093), np.float32(0.7577), np.float32(0.6811), np.float32(0.6123), np.float32(0.8558), np.float32(0.7855), np.float32(0.8911), np.float32(0.8423), np.float32(0.9692), np.float32(0.9697), np.float32(0.9651), np.float32(0.8089), np.float32(0.7471), np.float32(0.8698), np.float32(0.953), np.float32(0.4586), np.float32(0.4633)] +2025-11-12 01:17:07.884492: Epoch time: 258.49 s +2025-11-12 01:17:09.769180: +2025-11-12 01:17:09.772006: Epoch 318 +2025-11-12 01:17:09.774456: Current learning rate: 0.00709 +2025-11-12 01:21:29.845283: train_loss -0.6857 +2025-11-12 01:21:29.850629: val_loss -0.699 +2025-11-12 01:21:29.852291: Pseudo dice [np.float32(0.9099), np.float32(0.7312), np.float32(0.7233), np.float32(0.6144), np.float32(0.8518), np.float32(0.7846), np.float32(0.883), np.float32(0.8471), np.float32(0.963), np.float32(0.9636), np.float32(0.9675), np.float32(0.8096), np.float32(0.7458), np.float32(0.8628), np.float32(0.957), np.float32(0.3878), np.float32(0.3175)] +2025-11-12 01:21:29.853557: Epoch time: 260.08 s +2025-11-12 01:21:31.648261: +2025-11-12 01:21:31.649888: Epoch 319 +2025-11-12 01:21:31.651139: Current learning rate: 0.00708 +2025-11-12 01:25:50.043880: train_loss -0.696 +2025-11-12 01:25:50.049169: val_loss -0.7117 +2025-11-12 01:25:50.051565: Pseudo dice [np.float32(0.9123), np.float32(0.7473), np.float32(0.7171), np.float32(0.6212), np.float32(0.8546), np.float32(0.8048), np.float32(0.8688), np.float32(0.8538), np.float32(0.9734), np.float32(0.9686), np.float32(0.9682), np.float32(0.8232), np.float32(0.7175), np.float32(0.8691), np.float32(0.9559), np.float32(0.5118), np.float32(0.3971)] +2025-11-12 01:25:50.053091: Epoch time: 258.4 s +2025-11-12 01:25:50.054541: Yayy! New best EMA pseudo Dice: 0.7882999777793884 +2025-11-12 01:25:54.915260: +2025-11-12 01:25:54.918000: Epoch 320 +2025-11-12 01:25:54.920434: Current learning rate: 0.00707 +2025-11-12 01:30:13.535810: train_loss -0.6992 +2025-11-12 01:30:13.542574: val_loss -0.7049 +2025-11-12 01:30:13.545554: Pseudo dice [np.float32(0.9149), np.float32(0.7458), np.float32(0.7148), np.float32(0.6271), np.float32(0.8529), np.float32(0.8083), np.float32(0.9008), np.float32(0.8567), np.float32(0.9673), np.float32(0.9709), np.float32(0.9682), np.float32(0.8195), np.float32(0.7628), np.float32(0.856), np.float32(0.9527), np.float32(0.4351), np.float32(0.3242)] +2025-11-12 01:30:13.547677: Epoch time: 258.63 s +2025-11-12 01:30:13.549368: Yayy! New best EMA pseudo Dice: 0.7888000011444092 +2025-11-12 01:30:18.469054: +2025-11-12 01:30:18.470578: Epoch 321 +2025-11-12 01:30:18.471813: Current learning rate: 0.00706 +2025-11-12 01:34:36.881481: train_loss -0.691 +2025-11-12 01:34:36.885725: val_loss -0.7034 +2025-11-12 01:34:36.887380: Pseudo dice [np.float32(0.9125), np.float32(0.7658), np.float32(0.7097), np.float32(0.6242), np.float32(0.8556), np.float32(0.7919), np.float32(0.8782), np.float32(0.8454), np.float32(0.963), np.float32(0.9635), np.float32(0.968), np.float32(0.819), np.float32(0.7578), np.float32(0.8622), np.float32(0.9503), np.float32(0.3711), np.float32(0.2696)] +2025-11-12 01:34:36.889140: Epoch time: 258.42 s +2025-11-12 01:34:38.738727: +2025-11-12 01:34:38.740690: Epoch 322 +2025-11-12 01:34:38.743270: Current learning rate: 0.00705 +2025-11-12 01:38:57.286244: train_loss -0.6861 +2025-11-12 01:38:57.294023: val_loss -0.6865 +2025-11-12 01:38:57.295868: Pseudo dice [np.float32(0.9016), np.float32(0.7482), np.float32(0.7086), np.float32(0.6338), np.float32(0.8505), np.float32(0.7884), np.float32(0.8703), np.float32(0.8339), np.float32(0.9238), np.float32(0.9173), np.float32(0.9653), np.float32(0.8174), np.float32(0.7449), np.float32(0.8612), np.float32(0.9485), np.float32(0.3701), np.float32(0.306)] +2025-11-12 01:38:57.297686: Epoch time: 258.55 s +2025-11-12 01:38:59.150345: +2025-11-12 01:38:59.153038: Epoch 323 +2025-11-12 01:38:59.156029: Current learning rate: 0.00704 +2025-11-12 01:43:17.768450: train_loss -0.685 +2025-11-12 01:43:17.774078: val_loss -0.695 +2025-11-12 01:43:17.775647: Pseudo dice [np.float32(0.9078), np.float32(0.767), np.float32(0.7123), np.float32(0.6071), np.float32(0.8485), np.float32(0.7994), np.float32(0.8899), np.float32(0.8543), np.float32(0.9656), np.float32(0.9667), np.float32(0.9678), np.float32(0.8153), np.float32(0.7401), np.float32(0.8609), np.float32(0.9496), np.float32(0.388), np.float32(0.3663)] +2025-11-12 01:43:17.777226: Epoch time: 258.62 s +2025-11-12 01:43:19.601439: +2025-11-12 01:43:19.602986: Epoch 324 +2025-11-12 01:43:19.604827: Current learning rate: 0.00703 +2025-11-12 01:47:38.229371: train_loss -0.6948 +2025-11-12 01:47:38.235887: val_loss -0.6964 +2025-11-12 01:47:38.238125: Pseudo dice [np.float32(0.9124), np.float32(0.7754), np.float32(0.6997), np.float32(0.6356), np.float32(0.8492), np.float32(0.7584), np.float32(0.8961), np.float32(0.852), np.float32(0.9464), np.float32(0.9457), np.float32(0.9652), np.float32(0.8053), np.float32(0.7229), np.float32(0.8628), np.float32(0.9369), np.float32(0.3708), np.float32(0.3811)] +2025-11-12 01:47:38.240321: Epoch time: 258.63 s +2025-11-12 01:47:40.111879: +2025-11-12 01:47:40.114733: Epoch 325 +2025-11-12 01:47:40.117475: Current learning rate: 0.00702 +2025-11-12 01:51:58.869908: train_loss -0.6899 +2025-11-12 01:51:58.874881: val_loss -0.7011 +2025-11-12 01:51:58.876984: Pseudo dice [np.float32(0.9149), np.float32(0.7735), np.float32(0.7272), np.float32(0.6295), np.float32(0.8628), np.float32(0.7875), np.float32(0.8767), np.float32(0.8449), np.float32(0.9668), np.float32(0.9715), np.float32(0.9665), np.float32(0.8193), np.float32(0.7514), np.float32(0.8642), np.float32(0.9564), np.float32(0.3641), np.float32(0.298)] +2025-11-12 01:51:58.878602: Epoch time: 258.76 s +2025-11-12 01:52:00.706602: +2025-11-12 01:52:00.708677: Epoch 326 +2025-11-12 01:52:00.710145: Current learning rate: 0.00701 +2025-11-12 01:56:19.476986: train_loss -0.6902 +2025-11-12 01:56:19.483277: val_loss -0.7123 +2025-11-12 01:56:19.484613: Pseudo dice [np.float32(0.9104), np.float32(0.7499), np.float32(0.7181), np.float32(0.6382), np.float32(0.8646), np.float32(0.7905), np.float32(0.8803), np.float32(0.8553), np.float32(0.974), np.float32(0.9744), np.float32(0.9689), np.float32(0.8148), np.float32(0.7518), np.float32(0.867), np.float32(0.9561), np.float32(0.3441), np.float32(0.4014)] +2025-11-12 01:56:19.485984: Epoch time: 258.77 s +2025-11-12 01:56:21.300344: +2025-11-12 01:56:21.303429: Epoch 327 +2025-11-12 01:56:21.306070: Current learning rate: 0.007 +2025-11-12 02:00:41.022849: train_loss -0.6932 +2025-11-12 02:00:41.031156: val_loss -0.7027 +2025-11-12 02:00:41.033856: Pseudo dice [np.float32(0.918), np.float32(0.7526), np.float32(0.6895), np.float32(0.624), np.float32(0.8642), np.float32(0.8078), np.float32(0.8866), np.float32(0.8395), np.float32(0.957), np.float32(0.9546), np.float32(0.9662), np.float32(0.8282), np.float32(0.7478), np.float32(0.8795), np.float32(0.9511), np.float32(0.3461), np.float32(0.3324)] +2025-11-12 02:00:41.036724: Epoch time: 259.73 s +2025-11-12 02:00:43.050355: +2025-11-12 02:00:43.051828: Epoch 328 +2025-11-12 02:00:43.053410: Current learning rate: 0.00699 +2025-11-12 02:05:01.936153: train_loss -0.694 +2025-11-12 02:05:01.941932: val_loss -0.7105 +2025-11-12 02:05:01.943494: Pseudo dice [np.float32(0.9228), np.float32(0.7775), np.float32(0.7389), np.float32(0.6195), np.float32(0.8578), np.float32(0.7945), np.float32(0.895), np.float32(0.8482), np.float32(0.9613), np.float32(0.9646), np.float32(0.9655), np.float32(0.8158), np.float32(0.7557), np.float32(0.8678), np.float32(0.943), np.float32(0.4146), np.float32(0.4121)] +2025-11-12 02:05:01.945230: Epoch time: 258.89 s +2025-11-12 02:05:03.821530: +2025-11-12 02:05:03.822760: Epoch 329 +2025-11-12 02:05:03.824034: Current learning rate: 0.00698 +2025-11-12 02:09:22.590665: train_loss -0.6876 +2025-11-12 02:09:22.596391: val_loss -0.6994 +2025-11-12 02:09:22.598051: Pseudo dice [np.float32(0.9004), np.float32(0.7403), np.float32(0.6936), np.float32(0.6544), np.float32(0.8475), np.float32(0.8046), np.float32(0.863), np.float32(0.8364), np.float32(0.9719), np.float32(0.9663), np.float32(0.9649), np.float32(0.8163), np.float32(0.7537), np.float32(0.866), np.float32(0.9593), np.float32(0.3689), np.float32(0.2859)] +2025-11-12 02:09:22.600165: Epoch time: 258.77 s +2025-11-12 02:09:24.420567: +2025-11-12 02:09:24.424309: Epoch 330 +2025-11-12 02:09:24.427808: Current learning rate: 0.00697 +2025-11-12 02:13:43.082384: train_loss -0.6854 +2025-11-12 02:13:43.087163: val_loss -0.7004 +2025-11-12 02:13:43.089559: Pseudo dice [np.float32(0.9126), np.float32(0.7445), np.float32(0.702), np.float32(0.645), np.float32(0.8492), np.float32(0.7878), np.float32(0.8839), np.float32(0.8515), np.float32(0.9617), np.float32(0.9549), np.float32(0.9659), np.float32(0.822), np.float32(0.7244), np.float32(0.8554), np.float32(0.953), np.float32(0.4015), np.float32(0.3657)] +2025-11-12 02:13:43.091550: Epoch time: 258.67 s +2025-11-12 02:13:44.891443: +2025-11-12 02:13:44.894157: Epoch 331 +2025-11-12 02:13:44.896309: Current learning rate: 0.00696 +2025-11-12 02:18:03.857908: train_loss -0.6872 +2025-11-12 02:18:03.863125: val_loss -0.6967 +2025-11-12 02:18:03.864541: Pseudo dice [np.float32(0.9084), np.float32(0.7419), np.float32(0.6805), np.float32(0.6092), np.float32(0.8552), np.float32(0.764), np.float32(0.8551), np.float32(0.8462), np.float32(0.9667), np.float32(0.9644), np.float32(0.9677), np.float32(0.8099), np.float32(0.7435), np.float32(0.8668), np.float32(0.9568), np.float32(0.3714), np.float32(0.3174)] +2025-11-12 02:18:03.865893: Epoch time: 258.97 s +2025-11-12 02:18:05.734101: +2025-11-12 02:18:05.735963: Epoch 332 +2025-11-12 02:18:05.737623: Current learning rate: 0.00696 +2025-11-12 02:22:24.565408: train_loss -0.6966 +2025-11-12 02:22:24.570744: val_loss -0.7026 +2025-11-12 02:22:24.572688: Pseudo dice [np.float32(0.9056), np.float32(0.7669), np.float32(0.7286), np.float32(0.6473), np.float32(0.8583), np.float32(0.7743), np.float32(0.8877), np.float32(0.8465), np.float32(0.9767), np.float32(0.9734), np.float32(0.9686), np.float32(0.8136), np.float32(0.7709), np.float32(0.8678), np.float32(0.9578), np.float32(0.4046), np.float32(0.3064)] +2025-11-12 02:22:24.574500: Epoch time: 258.84 s +2025-11-12 02:22:26.444972: +2025-11-12 02:22:26.446950: Epoch 333 +2025-11-12 02:22:26.448488: Current learning rate: 0.00695 +2025-11-12 02:26:45.108050: train_loss -0.697 +2025-11-12 02:26:45.113348: val_loss -0.7127 +2025-11-12 02:26:45.116717: Pseudo dice [np.float32(0.9261), np.float32(0.755), np.float32(0.7141), np.float32(0.6277), np.float32(0.8513), np.float32(0.7824), np.float32(0.8537), np.float32(0.8498), np.float32(0.9712), np.float32(0.9712), np.float32(0.9677), np.float32(0.8266), np.float32(0.7349), np.float32(0.8661), np.float32(0.9612), np.float32(0.414), np.float32(0.4626)] +2025-11-12 02:26:45.119879: Epoch time: 258.67 s +2025-11-12 02:26:46.953473: +2025-11-12 02:26:46.956105: Epoch 334 +2025-11-12 02:26:46.958907: Current learning rate: 0.00694 +2025-11-12 02:31:05.403086: train_loss -0.6979 +2025-11-12 02:31:05.407796: val_loss -0.7185 +2025-11-12 02:31:05.409280: Pseudo dice [np.float32(0.9101), np.float32(0.7864), np.float32(0.7103), np.float32(0.6603), np.float32(0.8562), np.float32(0.7934), np.float32(0.8707), np.float32(0.8473), np.float32(0.9747), np.float32(0.9749), np.float32(0.9693), np.float32(0.829), np.float32(0.7564), np.float32(0.8706), np.float32(0.9637), np.float32(0.4244), np.float32(0.4163)] +2025-11-12 02:31:05.410595: Epoch time: 258.46 s +2025-11-12 02:31:05.411780: Yayy! New best EMA pseudo Dice: 0.7892000079154968 +2025-11-12 02:31:10.248163: +2025-11-12 02:31:10.250698: Epoch 335 +2025-11-12 02:31:10.253239: Current learning rate: 0.00693 +2025-11-12 02:35:28.695873: train_loss -0.7013 +2025-11-12 02:35:28.701458: val_loss -0.699 +2025-11-12 02:35:28.703412: Pseudo dice [np.float32(0.9111), np.float32(0.7626), np.float32(0.7106), np.float32(0.67), np.float32(0.8595), np.float32(0.7704), np.float32(0.9132), np.float32(0.8344), np.float32(0.9724), np.float32(0.9721), np.float32(0.9678), np.float32(0.8204), np.float32(0.7557), np.float32(0.867), np.float32(0.9587), np.float32(0.3326), np.float32(0.2947)] +2025-11-12 02:35:28.705621: Epoch time: 258.45 s +2025-11-12 02:35:30.553500: +2025-11-12 02:35:30.555479: Epoch 336 +2025-11-12 02:35:30.557839: Current learning rate: 0.00692 +2025-11-12 02:39:50.182013: train_loss -0.6971 +2025-11-12 02:39:50.190680: val_loss -0.7017 +2025-11-12 02:39:50.193279: Pseudo dice [np.float32(0.9082), np.float32(0.7747), np.float32(0.7154), np.float32(0.6341), np.float32(0.8572), np.float32(0.7791), np.float32(0.8709), np.float32(0.8527), np.float32(0.961), np.float32(0.9667), np.float32(0.9652), np.float32(0.8297), np.float32(0.7388), np.float32(0.8615), np.float32(0.9499), np.float32(0.3571), np.float32(0.4175)] +2025-11-12 02:39:50.195384: Epoch time: 259.63 s +2025-11-12 02:39:52.059664: +2025-11-12 02:39:52.061764: Epoch 337 +2025-11-12 02:39:52.063890: Current learning rate: 0.00691 +2025-11-12 02:44:10.552127: train_loss -0.699 +2025-11-12 02:44:10.561115: val_loss -0.7001 +2025-11-12 02:44:10.562349: Pseudo dice [np.float32(0.901), np.float32(0.749), np.float32(0.729), np.float32(0.6134), np.float32(0.8633), np.float32(0.7677), np.float32(0.9), np.float32(0.8412), np.float32(0.9548), np.float32(0.9583), np.float32(0.9677), np.float32(0.8259), np.float32(0.7319), np.float32(0.8673), np.float32(0.9536), np.float32(0.3255), np.float32(0.3808)] +2025-11-12 02:44:10.563943: Epoch time: 258.5 s +2025-11-12 02:44:12.478931: +2025-11-12 02:44:12.481602: Epoch 338 +2025-11-12 02:44:12.483282: Current learning rate: 0.0069 +2025-11-12 02:48:30.953547: train_loss -0.7011 +2025-11-12 02:48:30.959687: val_loss -0.7035 +2025-11-12 02:48:30.960968: Pseudo dice [np.float32(0.8976), np.float32(0.7593), np.float32(0.6998), np.float32(0.6497), np.float32(0.8602), np.float32(0.7947), np.float32(0.8899), np.float32(0.8528), np.float32(0.9692), np.float32(0.9659), np.float32(0.9674), np.float32(0.8199), np.float32(0.7473), np.float32(0.8727), np.float32(0.9556), np.float32(0.4043), np.float32(0.3638)] +2025-11-12 02:48:30.962544: Epoch time: 258.48 s +2025-11-12 02:48:32.785286: +2025-11-12 02:48:32.786843: Epoch 339 +2025-11-12 02:48:32.788714: Current learning rate: 0.00689 +2025-11-12 02:52:51.233080: train_loss -0.7006 +2025-11-12 02:52:51.241506: val_loss -0.7051 +2025-11-12 02:52:51.244869: Pseudo dice [np.float32(0.9047), np.float32(0.7457), np.float32(0.7121), np.float32(0.6579), np.float32(0.8571), np.float32(0.8024), np.float32(0.8947), np.float32(0.8431), np.float32(0.9756), np.float32(0.9743), np.float32(0.9677), np.float32(0.8159), np.float32(0.7338), np.float32(0.8651), np.float32(0.9572), np.float32(0.3435), np.float32(0.3202)] +2025-11-12 02:52:51.247896: Epoch time: 258.45 s +2025-11-12 02:52:53.172890: +2025-11-12 02:52:53.175733: Epoch 340 +2025-11-12 02:52:53.178391: Current learning rate: 0.00688 +2025-11-12 02:57:11.420244: train_loss -0.6896 +2025-11-12 02:57:11.430221: val_loss -0.7062 +2025-11-12 02:57:11.433323: Pseudo dice [np.float32(0.9072), np.float32(0.7315), np.float32(0.7319), np.float32(0.6351), np.float32(0.8525), np.float32(0.7899), np.float32(0.9078), np.float32(0.8482), np.float32(0.9664), np.float32(0.9663), np.float32(0.9655), np.float32(0.8296), np.float32(0.7481), np.float32(0.8662), np.float32(0.9522), np.float32(0.3911), np.float32(0.3198)] +2025-11-12 02:57:11.436285: Epoch time: 258.25 s +2025-11-12 02:57:13.255813: +2025-11-12 02:57:13.257666: Epoch 341 +2025-11-12 02:57:13.259572: Current learning rate: 0.00687 +2025-11-12 03:01:31.770943: train_loss -0.6863 +2025-11-12 03:01:31.779669: val_loss -0.691 +2025-11-12 03:01:31.782099: Pseudo dice [np.float32(0.9082), np.float32(0.7222), np.float32(0.6861), np.float32(0.6341), np.float32(0.8604), np.float32(0.7752), np.float32(0.8859), np.float32(0.857), np.float32(0.9618), np.float32(0.9643), np.float32(0.9663), np.float32(0.814), np.float32(0.7479), np.float32(0.8697), np.float32(0.9557), np.float32(0.3132), np.float32(0.3016)] +2025-11-12 03:01:31.785301: Epoch time: 258.52 s +2025-11-12 03:01:33.652424: +2025-11-12 03:01:33.654320: Epoch 342 +2025-11-12 03:01:33.657400: Current learning rate: 0.00686 +2025-11-12 03:05:51.973683: train_loss -0.6922 +2025-11-12 03:05:51.983569: val_loss -0.6994 +2025-11-12 03:05:51.986307: Pseudo dice [np.float32(0.9152), np.float32(0.7643), np.float32(0.7154), np.float32(0.6334), np.float32(0.8573), np.float32(0.7889), np.float32(0.8848), np.float32(0.8445), np.float32(0.9669), np.float32(0.9644), np.float32(0.9662), np.float32(0.8175), np.float32(0.7376), np.float32(0.8668), np.float32(0.954), np.float32(0.3668), np.float32(0.2988)] +2025-11-12 03:05:51.988553: Epoch time: 258.33 s +2025-11-12 03:05:53.953348: +2025-11-12 03:05:53.955113: Epoch 343 +2025-11-12 03:05:53.956988: Current learning rate: 0.00685 +2025-11-12 03:10:12.171238: train_loss -0.6939 +2025-11-12 03:10:12.178209: val_loss -0.708 +2025-11-12 03:10:12.180669: Pseudo dice [np.float32(0.9101), np.float32(0.7725), np.float32(0.7149), np.float32(0.6094), np.float32(0.8615), np.float32(0.7998), np.float32(0.8609), np.float32(0.8601), np.float32(0.9632), np.float32(0.9567), np.float32(0.9667), np.float32(0.8088), np.float32(0.7512), np.float32(0.8682), np.float32(0.9547), np.float32(0.4731), np.float32(0.3642)] +2025-11-12 03:10:12.182667: Epoch time: 258.22 s +2025-11-12 03:10:14.025082: +2025-11-12 03:10:14.026995: Epoch 344 +2025-11-12 03:10:14.028890: Current learning rate: 0.00684 +2025-11-12 03:14:32.155608: train_loss -0.6932 +2025-11-12 03:14:32.165371: val_loss -0.7078 +2025-11-12 03:14:32.168200: Pseudo dice [np.float32(0.9064), np.float32(0.7585), np.float32(0.6886), np.float32(0.6149), np.float32(0.8618), np.float32(0.7907), np.float32(0.8763), np.float32(0.8543), np.float32(0.9647), np.float32(0.9601), np.float32(0.9683), np.float32(0.8217), np.float32(0.7536), np.float32(0.8718), np.float32(0.9562), np.float32(0.4059), np.float32(0.4413)] +2025-11-12 03:14:32.171125: Epoch time: 258.14 s +2025-11-12 03:14:34.048699: +2025-11-12 03:14:34.050858: Epoch 345 +2025-11-12 03:14:34.052916: Current learning rate: 0.00683 +2025-11-12 03:18:52.375150: train_loss -0.696 +2025-11-12 03:18:52.381247: val_loss -0.7091 +2025-11-12 03:18:52.383240: Pseudo dice [np.float32(0.92), np.float32(0.7789), np.float32(0.6882), np.float32(0.6487), np.float32(0.8517), np.float32(0.7777), np.float32(0.8806), np.float32(0.8542), np.float32(0.9764), np.float32(0.9781), np.float32(0.9682), np.float32(0.8324), np.float32(0.7566), np.float32(0.8608), np.float32(0.9626), np.float32(0.375), np.float32(0.3616)] +2025-11-12 03:18:52.384504: Epoch time: 258.33 s +2025-11-12 03:18:55.490745: +2025-11-12 03:18:55.492763: Epoch 346 +2025-11-12 03:18:55.494192: Current learning rate: 0.00682 +2025-11-12 03:23:13.845123: train_loss -0.695 +2025-11-12 03:23:13.851628: val_loss -0.7171 +2025-11-12 03:23:13.854471: Pseudo dice [np.float32(0.9099), np.float32(0.7734), np.float32(0.7305), np.float32(0.6648), np.float32(0.8598), np.float32(0.7969), np.float32(0.8916), np.float32(0.8546), np.float32(0.9686), np.float32(0.9676), np.float32(0.9683), np.float32(0.827), np.float32(0.7762), np.float32(0.8636), np.float32(0.9545), np.float32(0.4665), np.float32(0.3867)] +2025-11-12 03:23:13.857620: Epoch time: 258.36 s +2025-11-12 03:23:13.860897: Yayy! New best EMA pseudo Dice: 0.7904000282287598 +2025-11-12 03:23:18.457859: +2025-11-12 03:23:18.459653: Epoch 347 +2025-11-12 03:23:18.461251: Current learning rate: 0.00681 +2025-11-12 03:27:36.898657: train_loss -0.6923 +2025-11-12 03:27:36.904383: val_loss -0.6945 +2025-11-12 03:27:36.906348: Pseudo dice [np.float32(0.9075), np.float32(0.7269), np.float32(0.6916), np.float32(0.6175), np.float32(0.8598), np.float32(0.7876), np.float32(0.8657), np.float32(0.8487), np.float32(0.962), np.float32(0.9676), np.float32(0.9654), np.float32(0.821), np.float32(0.7239), np.float32(0.8635), np.float32(0.9446), np.float32(0.3309), np.float32(0.2819)] +2025-11-12 03:27:36.908410: Epoch time: 258.45 s +2025-11-12 03:27:38.876209: +2025-11-12 03:27:38.878112: Epoch 348 +2025-11-12 03:27:38.880263: Current learning rate: 0.0068 +2025-11-12 03:31:57.406955: train_loss -0.6919 +2025-11-12 03:31:57.416430: val_loss -0.6987 +2025-11-12 03:31:57.419152: Pseudo dice [np.float32(0.9007), np.float32(0.7232), np.float32(0.6592), np.float32(0.6318), np.float32(0.8633), np.float32(0.7728), np.float32(0.8839), np.float32(0.8573), np.float32(0.9683), np.float32(0.9641), np.float32(0.9693), np.float32(0.8329), np.float32(0.7522), np.float32(0.876), np.float32(0.9636), np.float32(0.3606), np.float32(0.3339)] +2025-11-12 03:31:57.421564: Epoch time: 258.54 s +2025-11-12 03:31:59.321237: +2025-11-12 03:31:59.323794: Epoch 349 +2025-11-12 03:31:59.325764: Current learning rate: 0.0068 +2025-11-12 03:36:17.745774: train_loss -0.6867 +2025-11-12 03:36:17.755817: val_loss -0.7018 +2025-11-12 03:36:17.758962: Pseudo dice [np.float32(0.9061), np.float32(0.6775), np.float32(0.6646), np.float32(0.6686), np.float32(0.8633), np.float32(0.7906), np.float32(0.8862), np.float32(0.8628), np.float32(0.9675), np.float32(0.9674), np.float32(0.9657), np.float32(0.8308), np.float32(0.7683), np.float32(0.8657), np.float32(0.9542), np.float32(0.4219), np.float32(0.4024)] +2025-11-12 03:36:17.761646: Epoch time: 258.43 s +2025-11-12 03:36:22.600970: +2025-11-12 03:36:22.602318: Epoch 350 +2025-11-12 03:36:22.603682: Current learning rate: 0.00679 +2025-11-12 03:40:41.142925: train_loss -0.6904 +2025-11-12 03:40:41.148362: val_loss -0.7033 +2025-11-12 03:40:41.149593: Pseudo dice [np.float32(0.9099), np.float32(0.7603), np.float32(0.7161), np.float32(0.6224), np.float32(0.8595), np.float32(0.7958), np.float32(0.8972), np.float32(0.8503), np.float32(0.9581), np.float32(0.9575), np.float32(0.9662), np.float32(0.818), np.float32(0.6861), np.float32(0.8605), np.float32(0.9526), np.float32(0.3597), np.float32(0.3948)] +2025-11-12 03:40:41.151289: Epoch time: 258.55 s +2025-11-12 03:40:43.009075: +2025-11-12 03:40:43.010529: Epoch 351 +2025-11-12 03:40:43.011961: Current learning rate: 0.00678 +2025-11-12 03:45:01.598638: train_loss -0.6885 +2025-11-12 03:45:01.610962: val_loss -0.7129 +2025-11-12 03:45:01.614198: Pseudo dice [np.float32(0.9073), np.float32(0.767), np.float32(0.7392), np.float32(0.6431), np.float32(0.8572), np.float32(0.8065), np.float32(0.8853), np.float32(0.8508), np.float32(0.9638), np.float32(0.9664), np.float32(0.9656), np.float32(0.8228), np.float32(0.7675), np.float32(0.8649), np.float32(0.9574), np.float32(0.4196), np.float32(0.3809)] +2025-11-12 03:45:01.617370: Epoch time: 258.59 s +2025-11-12 03:45:03.431595: +2025-11-12 03:45:03.434876: Epoch 352 +2025-11-12 03:45:03.438036: Current learning rate: 0.00677 +2025-11-12 03:49:21.898897: train_loss -0.6979 +2025-11-12 03:49:21.904078: val_loss -0.7129 +2025-11-12 03:49:21.905536: Pseudo dice [np.float32(0.91), np.float32(0.7692), np.float32(0.6967), np.float32(0.6584), np.float32(0.8621), np.float32(0.7796), np.float32(0.897), np.float32(0.8523), np.float32(0.964), np.float32(0.9662), np.float32(0.9675), np.float32(0.8133), np.float32(0.7555), np.float32(0.8708), np.float32(0.9542), np.float32(0.4412), np.float32(0.3871)] +2025-11-12 03:49:21.907062: Epoch time: 258.47 s +2025-11-12 03:49:23.784141: +2025-11-12 03:49:23.785521: Epoch 353 +2025-11-12 03:49:23.786743: Current learning rate: 0.00676 +2025-11-12 03:53:42.448723: train_loss -0.6904 +2025-11-12 03:53:42.456186: val_loss -0.7043 +2025-11-12 03:53:42.458397: Pseudo dice [np.float32(0.9177), np.float32(0.7864), np.float32(0.6995), np.float32(0.6187), np.float32(0.8578), np.float32(0.7924), np.float32(0.8823), np.float32(0.8487), np.float32(0.9533), np.float32(0.9538), np.float32(0.9662), np.float32(0.8363), np.float32(0.7722), np.float32(0.8711), np.float32(0.9536), np.float32(0.3491), np.float32(0.2644)] +2025-11-12 03:53:42.460393: Epoch time: 258.67 s +2025-11-12 03:53:44.331583: +2025-11-12 03:53:44.334952: Epoch 354 +2025-11-12 03:53:44.338101: Current learning rate: 0.00675 +2025-11-12 03:58:02.938913: train_loss -0.6954 +2025-11-12 03:58:02.947904: val_loss -0.7025 +2025-11-12 03:58:02.950213: Pseudo dice [np.float32(0.8939), np.float32(0.726), np.float32(0.6811), np.float32(0.6532), np.float32(0.8581), np.float32(0.7834), np.float32(0.8863), np.float32(0.8409), np.float32(0.9625), np.float32(0.9645), np.float32(0.9676), np.float32(0.8247), np.float32(0.7334), np.float32(0.8637), np.float32(0.959), np.float32(0.3819), np.float32(0.3869)] +2025-11-12 03:58:02.951944: Epoch time: 258.61 s +2025-11-12 03:58:05.983102: +2025-11-12 03:58:05.985834: Epoch 355 +2025-11-12 03:58:05.987235: Current learning rate: 0.00674 +2025-11-12 04:02:24.298020: train_loss -0.6964 +2025-11-12 04:02:24.310992: val_loss -0.7039 +2025-11-12 04:02:24.313833: Pseudo dice [np.float32(0.9108), np.float32(0.7553), np.float32(0.7261), np.float32(0.6212), np.float32(0.8642), np.float32(0.7999), np.float32(0.8676), np.float32(0.8456), np.float32(0.9711), np.float32(0.9711), np.float32(0.9679), np.float32(0.8175), np.float32(0.7541), np.float32(0.8649), np.float32(0.9557), np.float32(0.4843), np.float32(0.3293)] +2025-11-12 04:02:24.317112: Epoch time: 258.32 s +2025-11-12 04:02:26.168641: +2025-11-12 04:02:26.170813: Epoch 356 +2025-11-12 04:02:26.173387: Current learning rate: 0.00673 +2025-11-12 04:06:44.474020: train_loss -0.6942 +2025-11-12 04:06:44.481259: val_loss -0.7054 +2025-11-12 04:06:44.483450: Pseudo dice [np.float32(0.9151), np.float32(0.7647), np.float32(0.7151), np.float32(0.6638), np.float32(0.8543), np.float32(0.7812), np.float32(0.8856), np.float32(0.8573), np.float32(0.9713), np.float32(0.9704), np.float32(0.9681), np.float32(0.8248), np.float32(0.7455), np.float32(0.863), np.float32(0.9555), np.float32(0.3034), np.float32(0.3262)] +2025-11-12 04:06:44.485127: Epoch time: 258.31 s +2025-11-12 04:06:46.341197: +2025-11-12 04:06:46.342744: Epoch 357 +2025-11-12 04:06:46.344781: Current learning rate: 0.00672 +2025-11-12 04:11:04.645740: train_loss -0.6982 +2025-11-12 04:11:04.652180: val_loss -0.7077 +2025-11-12 04:11:04.654336: Pseudo dice [np.float32(0.9001), np.float32(0.7492), np.float32(0.7318), np.float32(0.661), np.float32(0.8545), np.float32(0.793), np.float32(0.8928), np.float32(0.8614), np.float32(0.9672), np.float32(0.967), np.float32(0.9667), np.float32(0.8182), np.float32(0.7522), np.float32(0.8757), np.float32(0.9496), np.float32(0.4069), np.float32(0.2998)] +2025-11-12 04:11:04.657362: Epoch time: 258.31 s +2025-11-12 04:11:06.555443: +2025-11-12 04:11:06.557214: Epoch 358 +2025-11-12 04:11:06.558565: Current learning rate: 0.00671 +2025-11-12 04:15:25.007998: train_loss -0.6937 +2025-11-12 04:15:25.015691: val_loss -0.693 +2025-11-12 04:15:25.018426: Pseudo dice [np.float32(0.9161), np.float32(0.7426), np.float32(0.6509), np.float32(0.6327), np.float32(0.848), np.float32(0.7862), np.float32(0.8674), np.float32(0.8234), np.float32(0.9739), np.float32(0.9687), np.float32(0.9636), np.float32(0.8109), np.float32(0.7362), np.float32(0.8599), np.float32(0.9524), np.float32(0.399), np.float32(0.3488)] +2025-11-12 04:15:25.020882: Epoch time: 258.46 s +2025-11-12 04:15:26.860783: +2025-11-12 04:15:26.863291: Epoch 359 +2025-11-12 04:15:26.866074: Current learning rate: 0.0067 +2025-11-12 04:19:45.290671: train_loss -0.6939 +2025-11-12 04:19:45.298200: val_loss -0.7111 +2025-11-12 04:19:45.300456: Pseudo dice [np.float32(0.9011), np.float32(0.7156), np.float32(0.7082), np.float32(0.6141), np.float32(0.8579), np.float32(0.7732), np.float32(0.8956), np.float32(0.8457), np.float32(0.972), np.float32(0.9738), np.float32(0.967), np.float32(0.7991), np.float32(0.7558), np.float32(0.8624), np.float32(0.9528), np.float32(0.3664), np.float32(0.4301)] +2025-11-12 04:19:45.303169: Epoch time: 258.43 s +2025-11-12 04:19:47.151492: +2025-11-12 04:19:47.153960: Epoch 360 +2025-11-12 04:19:47.155904: Current learning rate: 0.00669 +2025-11-12 04:24:05.410625: train_loss -0.7002 +2025-11-12 04:24:05.415605: val_loss -0.7069 +2025-11-12 04:24:05.416748: Pseudo dice [np.float32(0.9158), np.float32(0.7952), np.float32(0.7189), np.float32(0.6389), np.float32(0.8635), np.float32(0.7918), np.float32(0.863), np.float32(0.8517), np.float32(0.9634), np.float32(0.9638), np.float32(0.9658), np.float32(0.8222), np.float32(0.7717), np.float32(0.8728), np.float32(0.947), np.float32(0.3927), np.float32(0.3607)] +2025-11-12 04:24:05.417976: Epoch time: 258.26 s +2025-11-12 04:24:07.414124: +2025-11-12 04:24:07.417401: Epoch 361 +2025-11-12 04:24:07.419735: Current learning rate: 0.00668 +2025-11-12 04:28:25.813377: train_loss -0.6977 +2025-11-12 04:28:25.822984: val_loss -0.698 +2025-11-12 04:28:25.826989: Pseudo dice [np.float32(0.8982), np.float32(0.7575), np.float32(0.6809), np.float32(0.6518), np.float32(0.8503), np.float32(0.7832), np.float32(0.8746), np.float32(0.8474), np.float32(0.9684), np.float32(0.9679), np.float32(0.9676), np.float32(0.8252), np.float32(0.7415), np.float32(0.8606), np.float32(0.9558), np.float32(0.3403), np.float32(0.3426)] +2025-11-12 04:28:25.830693: Epoch time: 258.4 s +2025-11-12 04:28:27.748295: +2025-11-12 04:28:27.749859: Epoch 362 +2025-11-12 04:28:27.751110: Current learning rate: 0.00667 +2025-11-12 04:32:46.013363: train_loss -0.6934 +2025-11-12 04:32:46.018113: val_loss -0.706 +2025-11-12 04:32:46.020022: Pseudo dice [np.float32(0.9062), np.float32(0.7779), np.float32(0.6887), np.float32(0.6167), np.float32(0.8566), np.float32(0.7852), np.float32(0.8909), np.float32(0.8385), np.float32(0.9779), np.float32(0.9787), np.float32(0.967), np.float32(0.8247), np.float32(0.765), np.float32(0.8651), np.float32(0.956), np.float32(0.4073), np.float32(0.3577)] +2025-11-12 04:32:46.021534: Epoch time: 258.27 s +2025-11-12 04:32:47.901520: +2025-11-12 04:32:47.903100: Epoch 363 +2025-11-12 04:32:47.905191: Current learning rate: 0.00666 +2025-11-12 04:37:06.621327: train_loss -0.6999 +2025-11-12 04:37:06.626578: val_loss -0.6985 +2025-11-12 04:37:06.627782: Pseudo dice [np.float32(0.9082), np.float32(0.7623), np.float32(0.7073), np.float32(0.6467), np.float32(0.8616), np.float32(0.7782), np.float32(0.8981), np.float32(0.8615), np.float32(0.9652), np.float32(0.9642), np.float32(0.9652), np.float32(0.8179), np.float32(0.7691), np.float32(0.8649), np.float32(0.9417), np.float32(0.3992), np.float32(0.2385)] +2025-11-12 04:37:06.629274: Epoch time: 258.73 s +2025-11-12 04:37:08.515248: +2025-11-12 04:37:08.517938: Epoch 364 +2025-11-12 04:37:08.520210: Current learning rate: 0.00665 +2025-11-12 04:41:28.077941: train_loss -0.6974 +2025-11-12 04:41:28.083965: val_loss -0.7087 +2025-11-12 04:41:28.086273: Pseudo dice [np.float32(0.9088), np.float32(0.7573), np.float32(0.7184), np.float32(0.6663), np.float32(0.8568), np.float32(0.8056), np.float32(0.8743), np.float32(0.8628), np.float32(0.9764), np.float32(0.9678), np.float32(0.9694), np.float32(0.8295), np.float32(0.7424), np.float32(0.8703), np.float32(0.9624), np.float32(0.3362), np.float32(0.2887)] +2025-11-12 04:41:28.088413: Epoch time: 259.57 s +2025-11-12 04:41:29.922326: +2025-11-12 04:41:29.923970: Epoch 365 +2025-11-12 04:41:29.925732: Current learning rate: 0.00665 +2025-11-12 04:45:48.333179: train_loss -0.6967 +2025-11-12 04:45:48.338940: val_loss -0.702 +2025-11-12 04:45:48.341262: Pseudo dice [np.float32(0.9062), np.float32(0.7447), np.float32(0.7236), np.float32(0.6495), np.float32(0.8615), np.float32(0.8003), np.float32(0.8696), np.float32(0.847), np.float32(0.9665), np.float32(0.9637), np.float32(0.9641), np.float32(0.8308), np.float32(0.7331), np.float32(0.861), np.float32(0.9458), np.float32(0.3628), np.float32(0.2953)] +2025-11-12 04:45:48.343925: Epoch time: 258.42 s +2025-11-12 04:45:50.212075: +2025-11-12 04:45:50.214825: Epoch 366 +2025-11-12 04:45:50.217366: Current learning rate: 0.00664 +2025-11-12 04:50:08.587967: train_loss -0.6958 +2025-11-12 04:50:08.592825: val_loss -0.7018 +2025-11-12 04:50:08.594241: Pseudo dice [np.float32(0.9085), np.float32(0.7322), np.float32(0.7088), np.float32(0.6457), np.float32(0.8595), np.float32(0.8003), np.float32(0.8807), np.float32(0.8377), np.float32(0.976), np.float32(0.9754), np.float32(0.9686), np.float32(0.8205), np.float32(0.7402), np.float32(0.8629), np.float32(0.9563), np.float32(0.4339), np.float32(0.2957)] +2025-11-12 04:50:08.595541: Epoch time: 258.38 s +2025-11-12 04:50:10.455364: +2025-11-12 04:50:10.457478: Epoch 367 +2025-11-12 04:50:10.458953: Current learning rate: 0.00663 +2025-11-12 04:54:28.706282: train_loss -0.6948 +2025-11-12 04:54:28.710745: val_loss -0.7141 +2025-11-12 04:54:28.712341: Pseudo dice [np.float32(0.9171), np.float32(0.7122), np.float32(0.7128), np.float32(0.6403), np.float32(0.8617), np.float32(0.8052), np.float32(0.8852), np.float32(0.8525), np.float32(0.9555), np.float32(0.9612), np.float32(0.9661), np.float32(0.8221), np.float32(0.7351), np.float32(0.8694), np.float32(0.9586), np.float32(0.5129), np.float32(0.3979)] +2025-11-12 04:54:28.713763: Epoch time: 258.26 s +2025-11-12 04:54:30.582702: +2025-11-12 04:54:30.585505: Epoch 368 +2025-11-12 04:54:30.588038: Current learning rate: 0.00662 +2025-11-12 04:58:49.048230: train_loss -0.6936 +2025-11-12 04:58:49.056505: val_loss -0.7152 +2025-11-12 04:58:49.059259: Pseudo dice [np.float32(0.9118), np.float32(0.7654), np.float32(0.707), np.float32(0.6548), np.float32(0.8573), np.float32(0.7893), np.float32(0.8854), np.float32(0.846), np.float32(0.972), np.float32(0.9725), np.float32(0.9683), np.float32(0.8303), np.float32(0.7718), np.float32(0.8637), np.float32(0.9602), np.float32(0.4751), np.float32(0.3655)] +2025-11-12 04:58:49.062003: Epoch time: 258.47 s +2025-11-12 04:58:50.922991: +2025-11-12 04:58:50.924322: Epoch 369 +2025-11-12 04:58:50.925621: Current learning rate: 0.00661 +2025-11-12 05:03:09.228884: train_loss -0.6903 +2025-11-12 05:03:09.233617: val_loss -0.696 +2025-11-12 05:03:09.234863: Pseudo dice [np.float32(0.9047), np.float32(0.7519), np.float32(0.7119), np.float32(0.6109), np.float32(0.8493), np.float32(0.7767), np.float32(0.892), np.float32(0.851), np.float32(0.9673), np.float32(0.9697), np.float32(0.9663), np.float32(0.8175), np.float32(0.7519), np.float32(0.8678), np.float32(0.9591), np.float32(0.4181), np.float32(0.3426)] +2025-11-12 05:03:09.236472: Epoch time: 258.31 s +2025-11-12 05:03:11.096323: +2025-11-12 05:03:11.098425: Epoch 370 +2025-11-12 05:03:11.099860: Current learning rate: 0.0066 +2025-11-12 05:07:29.529204: train_loss -0.687 +2025-11-12 05:07:29.533369: val_loss -0.7109 +2025-11-12 05:07:29.534822: Pseudo dice [np.float32(0.9089), np.float32(0.7648), np.float32(0.7329), np.float32(0.6239), np.float32(0.8553), np.float32(0.7966), np.float32(0.888), np.float32(0.8526), np.float32(0.9724), np.float32(0.9672), np.float32(0.9673), np.float32(0.799), np.float32(0.7388), np.float32(0.8665), np.float32(0.961), np.float32(0.4674), np.float32(0.3412)] +2025-11-12 05:07:29.536176: Epoch time: 258.44 s +2025-11-12 05:07:31.411474: +2025-11-12 05:07:31.413138: Epoch 371 +2025-11-12 05:07:31.414590: Current learning rate: 0.00659 +2025-11-12 05:11:49.830872: train_loss -0.7006 +2025-11-12 05:11:49.835563: val_loss -0.7019 +2025-11-12 05:11:49.837073: Pseudo dice [np.float32(0.913), np.float32(0.7678), np.float32(0.7142), np.float32(0.6463), np.float32(0.8535), np.float32(0.7761), np.float32(0.8908), np.float32(0.8441), np.float32(0.9527), np.float32(0.9488), np.float32(0.9668), np.float32(0.8413), np.float32(0.7374), np.float32(0.866), np.float32(0.9491), np.float32(0.3296), np.float32(0.3491)] +2025-11-12 05:11:49.838235: Epoch time: 258.43 s +2025-11-12 05:11:51.610141: +2025-11-12 05:11:51.614097: Epoch 372 +2025-11-12 05:11:51.617370: Current learning rate: 0.00658 +2025-11-12 05:16:09.902840: train_loss -0.7006 +2025-11-12 05:16:09.910527: val_loss -0.7122 +2025-11-12 05:16:09.912096: Pseudo dice [np.float32(0.9114), np.float32(0.754), np.float32(0.7073), np.float32(0.6263), np.float32(0.8532), np.float32(0.7851), np.float32(0.9025), np.float32(0.8554), np.float32(0.9729), np.float32(0.9715), np.float32(0.9681), np.float32(0.8336), np.float32(0.7481), np.float32(0.8603), np.float32(0.9586), np.float32(0.4286), np.float32(0.3954)] +2025-11-12 05:16:09.914742: Epoch time: 258.3 s +2025-11-12 05:16:09.916625: Yayy! New best EMA pseudo Dice: 0.7904999852180481 +2025-11-12 05:16:17.181988: +2025-11-12 05:16:17.184024: Epoch 373 +2025-11-12 05:16:17.185747: Current learning rate: 0.00657 +2025-11-12 05:20:36.962946: train_loss -0.7007 +2025-11-12 05:20:36.968956: val_loss -0.7146 +2025-11-12 05:20:36.970567: Pseudo dice [np.float32(0.9096), np.float32(0.7653), np.float32(0.7155), np.float32(0.6201), np.float32(0.8556), np.float32(0.7794), np.float32(0.9002), np.float32(0.8555), np.float32(0.9753), np.float32(0.969), np.float32(0.9676), np.float32(0.8267), np.float32(0.7739), np.float32(0.8641), np.float32(0.9628), np.float32(0.4267), np.float32(0.3105)] +2025-11-12 05:20:36.972255: Epoch time: 259.79 s +2025-11-12 05:20:36.974026: Yayy! New best EMA pseudo Dice: 0.7907000184059143 +2025-11-12 05:20:42.129457: +2025-11-12 05:20:42.131100: Epoch 374 +2025-11-12 05:20:42.132747: Current learning rate: 0.00656 +2025-11-12 05:25:00.824168: train_loss -0.697 +2025-11-12 05:25:00.829365: val_loss -0.7102 +2025-11-12 05:25:00.831759: Pseudo dice [np.float32(0.9004), np.float32(0.7359), np.float32(0.7103), np.float32(0.645), np.float32(0.8506), np.float32(0.8027), np.float32(0.877), np.float32(0.8449), np.float32(0.9768), np.float32(0.9768), np.float32(0.9677), np.float32(0.8113), np.float32(0.7406), np.float32(0.8643), np.float32(0.9602), np.float32(0.4226), np.float32(0.3597)] +2025-11-12 05:25:00.833675: Epoch time: 258.7 s +2025-11-12 05:25:00.835026: Yayy! New best EMA pseudo Dice: 0.7907000184059143 +2025-11-12 05:25:05.828297: +2025-11-12 05:25:05.830873: Epoch 375 +2025-11-12 05:25:05.832757: Current learning rate: 0.00655 +2025-11-12 05:29:24.431573: train_loss -0.6914 +2025-11-12 05:29:24.438433: val_loss -0.7015 +2025-11-12 05:29:24.440559: Pseudo dice [np.float32(0.9104), np.float32(0.7456), np.float32(0.6908), np.float32(0.6594), np.float32(0.8589), np.float32(0.7767), np.float32(0.8411), np.float32(0.8484), np.float32(0.9674), np.float32(0.9682), np.float32(0.9665), np.float32(0.8121), np.float32(0.7597), np.float32(0.8703), np.float32(0.9547), np.float32(0.3701), np.float32(0.3807)] +2025-11-12 05:29:24.442488: Epoch time: 258.61 s +2025-11-12 05:29:26.288763: +2025-11-12 05:29:26.291105: Epoch 376 +2025-11-12 05:29:26.293032: Current learning rate: 0.00654 +2025-11-12 05:33:44.869139: train_loss -0.7013 +2025-11-12 05:33:44.878977: val_loss -0.7137 +2025-11-12 05:33:44.882004: Pseudo dice [np.float32(0.9075), np.float32(0.7579), np.float32(0.7007), np.float32(0.6586), np.float32(0.863), np.float32(0.7943), np.float32(0.891), np.float32(0.8573), np.float32(0.9731), np.float32(0.9694), np.float32(0.967), np.float32(0.8414), np.float32(0.7682), np.float32(0.8644), np.float32(0.9638), np.float32(0.3927), np.float32(0.3658)] +2025-11-12 05:33:44.884579: Epoch time: 258.59 s +2025-11-12 05:33:44.887170: Yayy! New best EMA pseudo Dice: 0.7910000085830688 +2025-11-12 05:33:49.899838: +2025-11-12 05:33:49.901869: Epoch 377 +2025-11-12 05:33:49.903280: Current learning rate: 0.00653 +2025-11-12 05:38:08.216717: train_loss -0.6999 +2025-11-12 05:38:08.220886: val_loss -0.6993 +2025-11-12 05:38:08.222143: Pseudo dice [np.float32(0.9105), np.float32(0.7622), np.float32(0.7265), np.float32(0.6478), np.float32(0.8545), np.float32(0.7819), np.float32(0.8933), np.float32(0.8422), np.float32(0.9502), np.float32(0.9531), np.float32(0.9666), np.float32(0.8106), np.float32(0.7594), np.float32(0.8662), np.float32(0.9533), np.float32(0.3986), np.float32(0.3411)] +2025-11-12 05:38:08.223766: Epoch time: 258.32 s +2025-11-12 05:38:10.077065: +2025-11-12 05:38:10.079894: Epoch 378 +2025-11-12 05:38:10.082721: Current learning rate: 0.00652 +2025-11-12 05:42:28.669806: train_loss -0.6952 +2025-11-12 05:42:28.676259: val_loss -0.7075 +2025-11-12 05:42:28.678405: Pseudo dice [np.float32(0.9195), np.float32(0.7968), np.float32(0.6902), np.float32(0.6372), np.float32(0.8586), np.float32(0.8042), np.float32(0.8898), np.float32(0.8495), np.float32(0.9694), np.float32(0.9697), np.float32(0.9686), np.float32(0.8189), np.float32(0.7303), np.float32(0.864), np.float32(0.9628), np.float32(0.3781), np.float32(0.3724)] +2025-11-12 05:42:28.679882: Epoch time: 258.6 s +2025-11-12 05:42:28.681414: Yayy! New best EMA pseudo Dice: 0.7910000085830688 +2025-11-12 05:42:33.729772: +2025-11-12 05:42:33.732413: Epoch 379 +2025-11-12 05:42:33.734104: Current learning rate: 0.00651 +2025-11-12 05:46:52.246243: train_loss -0.6996 +2025-11-12 05:46:52.251109: val_loss -0.714 +2025-11-12 05:46:52.253676: Pseudo dice [np.float32(0.9085), np.float32(0.7745), np.float32(0.7452), np.float32(0.659), np.float32(0.8591), np.float32(0.7934), np.float32(0.8983), np.float32(0.8597), np.float32(0.9717), np.float32(0.9714), np.float32(0.9677), np.float32(0.824), np.float32(0.75), np.float32(0.873), np.float32(0.9583), np.float32(0.4246), np.float32(0.3187)] +2025-11-12 05:46:52.255521: Epoch time: 258.52 s +2025-11-12 05:46:52.257181: Yayy! New best EMA pseudo Dice: 0.791700005531311 +2025-11-12 05:46:57.318322: +2025-11-12 05:46:57.320324: Epoch 380 +2025-11-12 05:46:57.322497: Current learning rate: 0.0065 +2025-11-12 05:51:16.148222: train_loss -0.6974 +2025-11-12 05:51:16.152269: val_loss -0.6951 +2025-11-12 05:51:16.153627: Pseudo dice [np.float32(0.9017), np.float32(0.7188), np.float32(0.712), np.float32(0.6354), np.float32(0.8431), np.float32(0.7917), np.float32(0.8942), np.float32(0.8584), np.float32(0.975), np.float32(0.9712), np.float32(0.9683), np.float32(0.8292), np.float32(0.7685), np.float32(0.8491), np.float32(0.9553), np.float32(0.3523), np.float32(0.2423)] +2025-11-12 05:51:16.154876: Epoch time: 258.84 s +2025-11-12 05:51:18.205295: +2025-11-12 05:51:18.207385: Epoch 381 +2025-11-12 05:51:18.208860: Current learning rate: 0.00649 +2025-11-12 05:55:38.212156: train_loss -0.7011 +2025-11-12 05:55:38.219568: val_loss -0.713 +2025-11-12 05:55:38.221795: Pseudo dice [np.float32(0.9076), np.float32(0.7603), np.float32(0.7284), np.float32(0.6295), np.float32(0.8572), np.float32(0.7986), np.float32(0.9013), np.float32(0.8486), np.float32(0.9673), np.float32(0.9695), np.float32(0.9652), np.float32(0.8246), np.float32(0.7341), np.float32(0.8741), np.float32(0.9469), np.float32(0.4412), np.float32(0.4007)] +2025-11-12 05:55:38.224160: Epoch time: 260.01 s +2025-11-12 05:55:40.128757: +2025-11-12 05:55:40.131136: Epoch 382 +2025-11-12 05:55:40.133423: Current learning rate: 0.00648 +2025-11-12 05:59:58.999772: train_loss -0.702 +2025-11-12 05:59:59.005065: val_loss -0.7117 +2025-11-12 05:59:59.006680: Pseudo dice [np.float32(0.9036), np.float32(0.7377), np.float32(0.7241), np.float32(0.6719), np.float32(0.8588), np.float32(0.794), np.float32(0.891), np.float32(0.8514), np.float32(0.9699), np.float32(0.9664), np.float32(0.9681), np.float32(0.8176), np.float32(0.7796), np.float32(0.8683), np.float32(0.9526), np.float32(0.3792), np.float32(0.3133)] +2025-11-12 05:59:59.008187: Epoch time: 258.88 s +2025-11-12 06:00:00.900903: +2025-11-12 06:00:00.903716: Epoch 383 +2025-11-12 06:00:00.906424: Current learning rate: 0.00648 +2025-11-12 06:04:19.567007: train_loss -0.701 +2025-11-12 06:04:19.572860: val_loss -0.7091 +2025-11-12 06:04:19.575098: Pseudo dice [np.float32(0.9039), np.float32(0.7681), np.float32(0.725), np.float32(0.6297), np.float32(0.8592), np.float32(0.8039), np.float32(0.8894), np.float32(0.849), np.float32(0.9778), np.float32(0.9736), np.float32(0.9686), np.float32(0.8276), np.float32(0.7515), np.float32(0.8727), np.float32(0.9649), np.float32(0.4206), np.float32(0.2992)] +2025-11-12 06:04:19.577357: Epoch time: 258.67 s +2025-11-12 06:04:21.452308: +2025-11-12 06:04:21.454900: Epoch 384 +2025-11-12 06:04:21.457203: Current learning rate: 0.00647 +2025-11-12 06:08:39.950879: train_loss -0.6977 +2025-11-12 06:08:39.956577: val_loss -0.7203 +2025-11-12 06:08:39.958585: Pseudo dice [np.float32(0.9152), np.float32(0.7545), np.float32(0.7236), np.float32(0.6719), np.float32(0.8602), np.float32(0.8066), np.float32(0.8706), np.float32(0.8579), np.float32(0.9624), np.float32(0.9635), np.float32(0.968), np.float32(0.8248), np.float32(0.7407), np.float32(0.8633), np.float32(0.9573), np.float32(0.4154), np.float32(0.4336)] +2025-11-12 06:08:39.960411: Epoch time: 258.5 s +2025-11-12 06:08:39.962197: Yayy! New best EMA pseudo Dice: 0.7922000288963318 +2025-11-12 06:08:44.949679: +2025-11-12 06:08:44.952376: Epoch 385 +2025-11-12 06:08:44.954311: Current learning rate: 0.00646 +2025-11-12 06:13:03.474500: train_loss -0.7056 +2025-11-12 06:13:03.482303: val_loss -0.7108 +2025-11-12 06:13:03.484896: Pseudo dice [np.float32(0.9149), np.float32(0.7469), np.float32(0.735), np.float32(0.6411), np.float32(0.8544), np.float32(0.7905), np.float32(0.851), np.float32(0.8459), np.float32(0.9718), np.float32(0.9724), np.float32(0.9678), np.float32(0.8094), np.float32(0.7484), np.float32(0.8734), np.float32(0.956), np.float32(0.3564), np.float32(0.3841)] +2025-11-12 06:13:03.487156: Epoch time: 258.53 s +2025-11-12 06:13:05.362948: +2025-11-12 06:13:05.366060: Epoch 386 +2025-11-12 06:13:05.369529: Current learning rate: 0.00645 +2025-11-12 06:17:23.889006: train_loss -0.6956 +2025-11-12 06:17:23.898457: val_loss -0.7064 +2025-11-12 06:17:23.901211: Pseudo dice [np.float32(0.9168), np.float32(0.7635), np.float32(0.704), np.float32(0.6263), np.float32(0.8539), np.float32(0.7842), np.float32(0.8773), np.float32(0.8609), np.float32(0.9539), np.float32(0.9522), np.float32(0.9651), np.float32(0.8197), np.float32(0.7462), np.float32(0.87), np.float32(0.9513), np.float32(0.3864), np.float32(0.3221)] +2025-11-12 06:17:23.904065: Epoch time: 258.53 s +2025-11-12 06:17:25.796887: +2025-11-12 06:17:25.799360: Epoch 387 +2025-11-12 06:17:25.801030: Current learning rate: 0.00644 +2025-11-12 06:21:44.313716: train_loss -0.701 +2025-11-12 06:21:44.323801: val_loss -0.7048 +2025-11-12 06:21:44.326679: Pseudo dice [np.float32(0.9088), np.float32(0.7671), np.float32(0.6562), np.float32(0.617), np.float32(0.8596), np.float32(0.786), np.float32(0.9045), np.float32(0.8501), np.float32(0.9726), np.float32(0.9715), np.float32(0.9682), np.float32(0.8223), np.float32(0.7309), np.float32(0.8687), np.float32(0.9538), np.float32(0.4209), np.float32(0.3792)] +2025-11-12 06:21:44.329364: Epoch time: 258.52 s +2025-11-12 06:21:46.249309: +2025-11-12 06:21:46.250815: Epoch 388 +2025-11-12 06:21:46.252374: Current learning rate: 0.00643 +2025-11-12 06:26:04.788827: train_loss -0.6996 +2025-11-12 06:26:04.796971: val_loss -0.7032 +2025-11-12 06:26:04.799659: Pseudo dice [np.float32(0.9135), np.float32(0.6704), np.float32(0.7), np.float32(0.6437), np.float32(0.8615), np.float32(0.8081), np.float32(0.8867), np.float32(0.8569), np.float32(0.9735), np.float32(0.9734), np.float32(0.9687), np.float32(0.821), np.float32(0.7439), np.float32(0.8729), np.float32(0.9616), np.float32(0.4335), np.float32(0.2525)] +2025-11-12 06:26:04.803597: Epoch time: 258.55 s +2025-11-12 06:26:06.717275: +2025-11-12 06:26:06.720260: Epoch 389 +2025-11-12 06:26:06.723451: Current learning rate: 0.00642 +2025-11-12 06:30:25.257187: train_loss -0.7007 +2025-11-12 06:30:25.262173: val_loss -0.6975 +2025-11-12 06:30:25.263947: Pseudo dice [np.float32(0.9173), np.float32(0.7589), np.float32(0.6693), np.float32(0.6452), np.float32(0.8631), np.float32(0.7815), np.float32(0.8804), np.float32(0.8424), np.float32(0.9592), np.float32(0.9597), np.float32(0.9671), np.float32(0.8151), np.float32(0.7471), np.float32(0.8654), np.float32(0.9553), np.float32(0.364), np.float32(0.2918)] +2025-11-12 06:30:25.266151: Epoch time: 258.55 s +2025-11-12 06:30:27.215752: +2025-11-12 06:30:27.217321: Epoch 390 +2025-11-12 06:30:27.218644: Current learning rate: 0.00641 +2025-11-12 06:34:46.918025: train_loss -0.6962 +2025-11-12 06:34:46.924573: val_loss -0.6881 +2025-11-12 06:34:46.926624: Pseudo dice [np.float32(0.9037), np.float32(0.6687), np.float32(0.7024), np.float32(0.6438), np.float32(0.8568), np.float32(0.7886), np.float32(0.866), np.float32(0.8518), np.float32(0.9561), np.float32(0.9555), np.float32(0.9652), np.float32(0.8168), np.float32(0.7356), np.float32(0.8648), np.float32(0.9496), np.float32(0.3707), np.float32(0.3066)] +2025-11-12 06:34:46.928157: Epoch time: 259.71 s +2025-11-12 06:34:48.801006: +2025-11-12 06:34:48.802965: Epoch 391 +2025-11-12 06:34:48.804899: Current learning rate: 0.0064 +2025-11-12 06:39:07.314725: train_loss -0.6969 +2025-11-12 06:39:07.324126: val_loss -0.7183 +2025-11-12 06:39:07.326260: Pseudo dice [np.float32(0.9136), np.float32(0.7634), np.float32(0.7201), np.float32(0.6423), np.float32(0.8545), np.float32(0.8036), np.float32(0.8804), np.float32(0.8599), np.float32(0.9772), np.float32(0.9766), np.float32(0.97), np.float32(0.8143), np.float32(0.7494), np.float32(0.8681), np.float32(0.9645), np.float32(0.4274), np.float32(0.401)] +2025-11-12 06:39:07.328688: Epoch time: 258.52 s +2025-11-12 06:39:09.205471: +2025-11-12 06:39:09.208230: Epoch 392 +2025-11-12 06:39:09.210528: Current learning rate: 0.00639 +2025-11-12 06:43:27.752377: train_loss -0.6948 +2025-11-12 06:43:27.760332: val_loss -0.7034 +2025-11-12 06:43:27.762771: Pseudo dice [np.float32(0.9096), np.float32(0.6667), np.float32(0.7119), np.float32(0.6267), np.float32(0.8446), np.float32(0.7873), np.float32(0.8871), np.float32(0.8391), np.float32(0.9656), np.float32(0.9673), np.float32(0.9666), np.float32(0.8209), np.float32(0.7641), np.float32(0.8617), np.float32(0.9502), np.float32(0.4411), np.float32(0.3825)] +2025-11-12 06:43:27.765411: Epoch time: 258.55 s +2025-11-12 06:43:29.697355: +2025-11-12 06:43:29.699082: Epoch 393 +2025-11-12 06:43:29.700764: Current learning rate: 0.00638 +2025-11-12 06:47:48.161886: train_loss -0.6945 +2025-11-12 06:47:48.166534: val_loss -0.7114 +2025-11-12 06:47:48.168216: Pseudo dice [np.float32(0.907), np.float32(0.7474), np.float32(0.6955), np.float32(0.6421), np.float32(0.8607), np.float32(0.7779), np.float32(0.8923), np.float32(0.8553), np.float32(0.9783), np.float32(0.9762), np.float32(0.9662), np.float32(0.8205), np.float32(0.7481), np.float32(0.864), np.float32(0.9602), np.float32(0.428), np.float32(0.3867)] +2025-11-12 06:47:48.169603: Epoch time: 258.47 s +2025-11-12 06:47:50.053769: +2025-11-12 06:47:50.056276: Epoch 394 +2025-11-12 06:47:50.058016: Current learning rate: 0.00637 +2025-11-12 06:52:08.755498: train_loss -0.6977 +2025-11-12 06:52:08.764509: val_loss -0.707 +2025-11-12 06:52:08.767040: Pseudo dice [np.float32(0.8984), np.float32(0.7765), np.float32(0.6973), np.float32(0.6674), np.float32(0.848), np.float32(0.7814), np.float32(0.8938), np.float32(0.8515), np.float32(0.9726), np.float32(0.9728), np.float32(0.9649), np.float32(0.803), np.float32(0.7418), np.float32(0.8676), np.float32(0.9558), np.float32(0.383), np.float32(0.4167)] +2025-11-12 06:52:08.769488: Epoch time: 258.71 s +2025-11-12 06:52:10.757555: +2025-11-12 06:52:10.758889: Epoch 395 +2025-11-12 06:52:10.760737: Current learning rate: 0.00636 +2025-11-12 06:56:29.577404: train_loss -0.695 +2025-11-12 06:56:29.586699: val_loss -0.696 +2025-11-12 06:56:29.589515: Pseudo dice [np.float32(0.9056), np.float32(0.7339), np.float32(0.6874), np.float32(0.6427), np.float32(0.848), np.float32(0.769), np.float32(0.8895), np.float32(0.8474), np.float32(0.97), np.float32(0.9707), np.float32(0.9668), np.float32(0.8128), np.float32(0.7571), np.float32(0.866), np.float32(0.957), np.float32(0.4259), np.float32(0.3248)] +2025-11-12 06:56:29.592873: Epoch time: 258.83 s +2025-11-12 06:56:31.514102: +2025-11-12 06:56:31.515580: Epoch 396 +2025-11-12 06:56:31.516883: Current learning rate: 0.00635 +2025-11-12 07:00:50.076337: train_loss -0.7005 +2025-11-12 07:00:50.084062: val_loss -0.7073 +2025-11-12 07:00:50.085726: Pseudo dice [np.float32(0.9146), np.float32(0.7414), np.float32(0.7063), np.float32(0.645), np.float32(0.855), np.float32(0.7921), np.float32(0.8706), np.float32(0.8508), np.float32(0.9718), np.float32(0.9663), np.float32(0.9666), np.float32(0.8158), np.float32(0.7403), np.float32(0.8718), np.float32(0.9539), np.float32(0.4011), np.float32(0.3595)] +2025-11-12 07:00:50.087571: Epoch time: 258.57 s +2025-11-12 07:00:51.954521: +2025-11-12 07:00:51.957293: Epoch 397 +2025-11-12 07:00:51.959282: Current learning rate: 0.00634 +2025-11-12 07:05:10.598926: train_loss -0.6999 +2025-11-12 07:05:10.605700: val_loss -0.7119 +2025-11-12 07:05:10.608005: Pseudo dice [np.float32(0.9194), np.float32(0.7687), np.float32(0.7053), np.float32(0.6401), np.float32(0.8604), np.float32(0.801), np.float32(0.8911), np.float32(0.8544), np.float32(0.9685), np.float32(0.9724), np.float32(0.9672), np.float32(0.8165), np.float32(0.7491), np.float32(0.8706), np.float32(0.9591), np.float32(0.4006), np.float32(0.36)] +2025-11-12 07:05:10.610250: Epoch time: 258.65 s +2025-11-12 07:05:12.531676: +2025-11-12 07:05:12.533413: Epoch 398 +2025-11-12 07:05:12.535193: Current learning rate: 0.00633 +2025-11-12 07:09:30.958810: train_loss -0.7005 +2025-11-12 07:09:30.966079: val_loss -0.7075 +2025-11-12 07:09:30.968258: Pseudo dice [np.float32(0.9144), np.float32(0.7289), np.float32(0.681), np.float32(0.6264), np.float32(0.8638), np.float32(0.8118), np.float32(0.8955), np.float32(0.8631), np.float32(0.9805), np.float32(0.9789), np.float32(0.9702), np.float32(0.8222), np.float32(0.7625), np.float32(0.8688), np.float32(0.9625), np.float32(0.3533), np.float32(0.3216)] +2025-11-12 07:09:30.969901: Epoch time: 258.43 s +2025-11-12 07:09:32.891991: +2025-11-12 07:09:32.893572: Epoch 399 +2025-11-12 07:09:32.894866: Current learning rate: 0.00632 +2025-11-12 07:13:51.298860: train_loss -0.7044 +2025-11-12 07:13:51.305953: val_loss -0.6998 +2025-11-12 07:13:51.308773: Pseudo dice [np.float32(0.9135), np.float32(0.7191), np.float32(0.706), np.float32(0.5728), np.float32(0.8547), np.float32(0.8061), np.float32(0.9025), np.float32(0.8573), np.float32(0.9761), np.float32(0.978), np.float32(0.9697), np.float32(0.8236), np.float32(0.7458), np.float32(0.8614), np.float32(0.9651), np.float32(0.3134), np.float32(0.2415)] +2025-11-12 07:13:51.311463: Epoch time: 258.41 s +2025-11-12 07:13:57.517402: +2025-11-12 07:13:57.518716: Epoch 400 +2025-11-12 07:13:57.520093: Current learning rate: 0.00631 +2025-11-12 07:18:16.109406: train_loss -0.7085 +2025-11-12 07:18:16.115364: val_loss -0.7098 +2025-11-12 07:18:16.117961: Pseudo dice [np.float32(0.8905), np.float32(0.7582), np.float32(0.7432), np.float32(0.6419), np.float32(0.861), np.float32(0.7874), np.float32(0.888), np.float32(0.856), np.float32(0.9727), np.float32(0.9742), np.float32(0.9696), np.float32(0.8232), np.float32(0.76), np.float32(0.8661), np.float32(0.966), np.float32(0.4067), np.float32(0.4718)] +2025-11-12 07:18:16.120987: Epoch time: 258.6 s +2025-11-12 07:18:18.047300: +2025-11-12 07:18:18.049802: Epoch 401 +2025-11-12 07:18:18.052114: Current learning rate: 0.0063 +2025-11-12 07:22:36.817103: train_loss -0.6974 +2025-11-12 07:22:36.825841: val_loss -0.6917 +2025-11-12 07:22:36.828678: Pseudo dice [np.float32(0.8953), np.float32(0.7731), np.float32(0.7017), np.float32(0.6124), np.float32(0.8585), np.float32(0.7806), np.float32(0.899), np.float32(0.8613), np.float32(0.9461), np.float32(0.9417), np.float32(0.9644), np.float32(0.8141), np.float32(0.7219), np.float32(0.8695), np.float32(0.9257), np.float32(0.422), np.float32(0.3844)] +2025-11-12 07:22:36.831182: Epoch time: 258.78 s +2025-11-12 07:22:38.689688: +2025-11-12 07:22:38.691685: Epoch 402 +2025-11-12 07:22:38.693942: Current learning rate: 0.0063 +2025-11-12 07:26:57.213200: train_loss -0.6965 +2025-11-12 07:26:57.218065: val_loss -0.7163 +2025-11-12 07:26:57.219752: Pseudo dice [np.float32(0.9199), np.float32(0.7593), np.float32(0.7166), np.float32(0.6388), np.float32(0.8521), np.float32(0.7802), np.float32(0.8822), np.float32(0.8474), np.float32(0.9732), np.float32(0.9768), np.float32(0.9684), np.float32(0.8277), np.float32(0.759), np.float32(0.8696), np.float32(0.9576), np.float32(0.4614), np.float32(0.4401)] +2025-11-12 07:26:57.221018: Epoch time: 258.53 s +2025-11-12 07:26:59.106305: +2025-11-12 07:26:59.108324: Epoch 403 +2025-11-12 07:26:59.109944: Current learning rate: 0.00629 +2025-11-12 07:31:17.995057: train_loss -0.6861 +2025-11-12 07:31:18.002670: val_loss -0.6988 +2025-11-12 07:31:18.004995: Pseudo dice [np.float32(0.9163), np.float32(0.7592), np.float32(0.7223), np.float32(0.6283), np.float32(0.8464), np.float32(0.7783), np.float32(0.8649), np.float32(0.8524), np.float32(0.963), np.float32(0.9613), np.float32(0.9665), np.float32(0.8078), np.float32(0.7533), np.float32(0.8615), np.float32(0.9561), np.float32(0.3556), np.float32(0.2961)] +2025-11-12 07:31:18.007360: Epoch time: 258.89 s +2025-11-12 07:31:19.897424: +2025-11-12 07:31:19.898855: Epoch 404 +2025-11-12 07:31:19.900306: Current learning rate: 0.00628 +2025-11-12 07:35:38.519905: train_loss -0.6964 +2025-11-12 07:35:38.525956: val_loss -0.7055 +2025-11-12 07:35:38.528127: Pseudo dice [np.float32(0.9147), np.float32(0.769), np.float32(0.6669), np.float32(0.6394), np.float32(0.8569), np.float32(0.8007), np.float32(0.8749), np.float32(0.8444), np.float32(0.9765), np.float32(0.9769), np.float32(0.9695), np.float32(0.8065), np.float32(0.7551), np.float32(0.8727), np.float32(0.9622), np.float32(0.3438), np.float32(0.3467)] +2025-11-12 07:35:38.530039: Epoch time: 258.63 s +2025-11-12 07:35:40.435884: +2025-11-12 07:35:40.437348: Epoch 405 +2025-11-12 07:35:40.438871: Current learning rate: 0.00627 +2025-11-12 07:39:58.954537: train_loss -0.7067 +2025-11-12 07:39:58.959410: val_loss -0.7175 +2025-11-12 07:39:58.960703: Pseudo dice [np.float32(0.9183), np.float32(0.7764), np.float32(0.7579), np.float32(0.6106), np.float32(0.861), np.float32(0.7839), np.float32(0.8341), np.float32(0.8745), np.float32(0.9753), np.float32(0.9754), np.float32(0.9686), np.float32(0.8187), np.float32(0.7047), np.float32(0.8732), np.float32(0.9639), np.float32(0.4265), np.float32(0.4545)] +2025-11-12 07:39:58.962831: Epoch time: 258.52 s +2025-11-12 07:40:00.804315: +2025-11-12 07:40:00.806075: Epoch 406 +2025-11-12 07:40:00.807534: Current learning rate: 0.00626 +2025-11-12 07:44:19.343569: train_loss -0.7014 +2025-11-12 07:44:19.353578: val_loss -0.6958 +2025-11-12 07:44:19.357069: Pseudo dice [np.float32(0.914), np.float32(0.7554), np.float32(0.7037), np.float32(0.6348), np.float32(0.8574), np.float32(0.7987), np.float32(0.9019), np.float32(0.8411), np.float32(0.9207), np.float32(0.9192), np.float32(0.9646), np.float32(0.819), np.float32(0.7576), np.float32(0.8735), np.float32(0.9308), np.float32(0.3321), np.float32(0.36)] +2025-11-12 07:44:19.359693: Epoch time: 258.54 s +2025-11-12 07:44:21.263457: +2025-11-12 07:44:21.265627: Epoch 407 +2025-11-12 07:44:21.267147: Current learning rate: 0.00625 +2025-11-12 07:48:39.881044: train_loss -0.6987 +2025-11-12 07:48:39.888121: val_loss -0.7026 +2025-11-12 07:48:39.890247: Pseudo dice [np.float32(0.9118), np.float32(0.7583), np.float32(0.6887), np.float32(0.6406), np.float32(0.8566), np.float32(0.7884), np.float32(0.8955), np.float32(0.8465), np.float32(0.9766), np.float32(0.9734), np.float32(0.9678), np.float32(0.8286), np.float32(0.7716), np.float32(0.8707), np.float32(0.9599), np.float32(0.3427), np.float32(0.3214)] +2025-11-12 07:48:39.892490: Epoch time: 258.62 s +2025-11-12 07:48:41.797004: +2025-11-12 07:48:41.800681: Epoch 408 +2025-11-12 07:48:41.802733: Current learning rate: 0.00624 +2025-11-12 07:53:00.590484: train_loss -0.702 +2025-11-12 07:53:00.599531: val_loss -0.7123 +2025-11-12 07:53:00.601426: Pseudo dice [np.float32(0.9064), np.float32(0.7788), np.float32(0.7208), np.float32(0.6411), np.float32(0.8628), np.float32(0.8059), np.float32(0.8809), np.float32(0.8534), np.float32(0.975), np.float32(0.9712), np.float32(0.9689), np.float32(0.8359), np.float32(0.7658), np.float32(0.8685), np.float32(0.9581), np.float32(0.3638), np.float32(0.3524)] +2025-11-12 07:53:00.602797: Epoch time: 258.8 s +2025-11-12 07:53:04.353334: +2025-11-12 07:53:04.354691: Epoch 409 +2025-11-12 07:53:04.356846: Current learning rate: 0.00623 +2025-11-12 07:57:22.722665: train_loss -0.6939 +2025-11-12 07:57:22.734445: val_loss -0.7064 +2025-11-12 07:57:22.737524: Pseudo dice [np.float32(0.9155), np.float32(0.7765), np.float32(0.6875), np.float32(0.6503), np.float32(0.8589), np.float32(0.7942), np.float32(0.8784), np.float32(0.8568), np.float32(0.9721), np.float32(0.9667), np.float32(0.9656), np.float32(0.8257), np.float32(0.724), np.float32(0.8689), np.float32(0.9561), np.float32(0.4345), np.float32(0.3341)] +2025-11-12 07:57:22.739935: Epoch time: 258.37 s +2025-11-12 07:57:24.593368: +2025-11-12 07:57:24.594759: Epoch 410 +2025-11-12 07:57:24.596442: Current learning rate: 0.00622 +2025-11-12 08:01:42.881466: train_loss -0.6953 +2025-11-12 08:01:42.888958: val_loss -0.7125 +2025-11-12 08:01:42.890864: Pseudo dice [np.float32(0.9109), np.float32(0.7617), np.float32(0.7202), np.float32(0.6507), np.float32(0.8619), np.float32(0.7901), np.float32(0.8874), np.float32(0.8431), np.float32(0.9616), np.float32(0.9568), np.float32(0.9656), np.float32(0.8197), np.float32(0.7547), np.float32(0.8629), np.float32(0.9525), np.float32(0.4139), np.float32(0.4609)] +2025-11-12 08:01:42.892941: Epoch time: 258.29 s +2025-11-12 08:01:44.662448: +2025-11-12 08:01:44.664993: Epoch 411 +2025-11-12 08:01:44.667496: Current learning rate: 0.00621 +2025-11-12 08:06:02.931731: train_loss -0.6896 +2025-11-12 08:06:02.938264: val_loss -0.6961 +2025-11-12 08:06:02.939448: Pseudo dice [np.float32(0.91), np.float32(0.7521), np.float32(0.7153), np.float32(0.6359), np.float32(0.8481), np.float32(0.7871), np.float32(0.8829), np.float32(0.8335), np.float32(0.9681), np.float32(0.9657), np.float32(0.9635), np.float32(0.8185), np.float32(0.7581), np.float32(0.853), np.float32(0.9542), np.float32(0.4015), np.float32(0.2787)] +2025-11-12 08:06:02.941007: Epoch time: 258.27 s +2025-11-12 08:06:04.750264: +2025-11-12 08:06:04.752386: Epoch 412 +2025-11-12 08:06:04.754128: Current learning rate: 0.0062 +2025-11-12 08:10:23.108784: train_loss -0.6681 +2025-11-12 08:10:23.114616: val_loss -0.6881 +2025-11-12 08:10:23.116011: Pseudo dice [np.float32(0.9047), np.float32(0.7682), np.float32(0.7005), np.float32(0.6359), np.float32(0.8536), np.float32(0.7595), np.float32(0.8682), np.float32(0.8592), np.float32(0.9214), np.float32(0.9161), np.float32(0.9604), np.float32(0.8062), np.float32(0.7472), np.float32(0.8568), np.float32(0.9151), np.float32(0.3978), np.float32(0.499)] +2025-11-12 08:10:23.117144: Epoch time: 258.36 s +2025-11-12 08:10:24.906311: +2025-11-12 08:10:24.909046: Epoch 413 +2025-11-12 08:10:24.911537: Current learning rate: 0.00619 +2025-11-12 08:14:43.245565: train_loss -0.681 +2025-11-12 08:14:43.251820: val_loss -0.7112 +2025-11-12 08:14:43.252968: Pseudo dice [np.float32(0.9033), np.float32(0.7587), np.float32(0.6982), np.float32(0.6488), np.float32(0.8599), np.float32(0.8131), np.float32(0.893), np.float32(0.8286), np.float32(0.9659), np.float32(0.9642), np.float32(0.9659), np.float32(0.8189), np.float32(0.7522), np.float32(0.8651), np.float32(0.9495), np.float32(0.4597), np.float32(0.4291)] +2025-11-12 08:14:43.254537: Epoch time: 258.35 s +2025-11-12 08:14:44.995628: +2025-11-12 08:14:44.997658: Epoch 414 +2025-11-12 08:14:44.999133: Current learning rate: 0.00618 +2025-11-12 08:19:03.297523: train_loss -0.6985 +2025-11-12 08:19:03.305213: val_loss -0.7157 +2025-11-12 08:19:03.308147: Pseudo dice [np.float32(0.8944), np.float32(0.781), np.float32(0.7219), np.float32(0.6541), np.float32(0.8564), np.float32(0.7995), np.float32(0.8978), np.float32(0.8535), np.float32(0.9676), np.float32(0.9656), np.float32(0.9674), np.float32(0.8179), np.float32(0.7413), np.float32(0.868), np.float32(0.9571), np.float32(0.4517), np.float32(0.4124)] +2025-11-12 08:19:03.310556: Epoch time: 258.31 s +2025-11-12 08:19:05.084841: +2025-11-12 08:19:05.087550: Epoch 415 +2025-11-12 08:19:05.089792: Current learning rate: 0.00617 +2025-11-12 08:23:23.265235: train_loss -0.7014 +2025-11-12 08:23:23.272899: val_loss -0.7192 +2025-11-12 08:23:23.275095: Pseudo dice [np.float32(0.9154), np.float32(0.7872), np.float32(0.7329), np.float32(0.6428), np.float32(0.853), np.float32(0.8186), np.float32(0.8916), np.float32(0.8472), np.float32(0.9683), np.float32(0.9688), np.float32(0.9676), np.float32(0.8169), np.float32(0.7777), np.float32(0.8649), np.float32(0.9556), np.float32(0.425), np.float32(0.3209)] +2025-11-12 08:23:23.276587: Epoch time: 258.19 s +2025-11-12 08:23:23.278135: Yayy! New best EMA pseudo Dice: 0.7922999858856201 +2025-11-12 08:23:28.894320: +2025-11-12 08:23:28.896509: Epoch 416 +2025-11-12 08:23:28.899263: Current learning rate: 0.00616 +2025-11-12 08:27:47.204381: train_loss -0.6939 +2025-11-12 08:27:47.214031: val_loss -0.697 +2025-11-12 08:27:47.217147: Pseudo dice [np.float32(0.9166), np.float32(0.7971), np.float32(0.7354), np.float32(0.6084), np.float32(0.8498), np.float32(0.7668), np.float32(0.8787), np.float32(0.8561), np.float32(0.9709), np.float32(0.9732), np.float32(0.9665), np.float32(0.8072), np.float32(0.7259), np.float32(0.8622), np.float32(0.9599), np.float32(0.354), np.float32(0.3967)] +2025-11-12 08:27:47.219938: Epoch time: 258.32 s +2025-11-12 08:27:49.033092: +2025-11-12 08:27:49.035517: Epoch 417 +2025-11-12 08:27:49.037218: Current learning rate: 0.00615 +2025-11-12 08:32:07.440109: train_loss -0.6917 +2025-11-12 08:32:07.445230: val_loss -0.7159 +2025-11-12 08:32:07.446455: Pseudo dice [np.float32(0.909), np.float32(0.7583), np.float32(0.7233), np.float32(0.6518), np.float32(0.8563), np.float32(0.7781), np.float32(0.864), np.float32(0.8599), np.float32(0.9727), np.float32(0.9765), np.float32(0.9682), np.float32(0.8253), np.float32(0.7744), np.float32(0.8748), np.float32(0.956), np.float32(0.366), np.float32(0.3487)] +2025-11-12 08:32:07.447607: Epoch time: 258.41 s +2025-11-12 08:32:09.227634: +2025-11-12 08:32:09.229632: Epoch 418 +2025-11-12 08:32:09.231517: Current learning rate: 0.00614 +2025-11-12 08:36:28.577156: train_loss -0.7025 +2025-11-12 08:36:28.583516: val_loss -0.7104 +2025-11-12 08:36:28.586252: Pseudo dice [np.float32(0.9148), np.float32(0.763), np.float32(0.7078), np.float32(0.6535), np.float32(0.8569), np.float32(0.7748), np.float32(0.8763), np.float32(0.8502), np.float32(0.9782), np.float32(0.9754), np.float32(0.9681), np.float32(0.8107), np.float32(0.743), np.float32(0.8621), np.float32(0.9632), np.float32(0.4016), np.float32(0.306)] +2025-11-12 08:36:28.589722: Epoch time: 259.36 s +2025-11-12 08:36:30.387442: +2025-11-12 08:36:30.390908: Epoch 419 +2025-11-12 08:36:30.393997: Current learning rate: 0.00613 +2025-11-12 08:40:48.472784: train_loss -0.694 +2025-11-12 08:40:48.482880: val_loss -0.7085 +2025-11-12 08:40:48.485243: Pseudo dice [np.float32(0.9237), np.float32(0.7796), np.float32(0.6896), np.float32(0.6335), np.float32(0.8576), np.float32(0.7883), np.float32(0.8621), np.float32(0.8651), np.float32(0.968), np.float32(0.9669), np.float32(0.9662), np.float32(0.8161), np.float32(0.7473), np.float32(0.866), np.float32(0.9539), np.float32(0.413), np.float32(0.3913)] +2025-11-12 08:40:48.487511: Epoch time: 258.09 s +2025-11-12 08:40:50.275042: +2025-11-12 08:40:50.276499: Epoch 420 +2025-11-12 08:40:50.278300: Current learning rate: 0.00612 +2025-11-12 08:45:08.375365: train_loss -0.6987 +2025-11-12 08:45:08.385046: val_loss -0.7116 +2025-11-12 08:45:08.387914: Pseudo dice [np.float32(0.9151), np.float32(0.7532), np.float32(0.7117), np.float32(0.6433), np.float32(0.8636), np.float32(0.7966), np.float32(0.8858), np.float32(0.8413), np.float32(0.9708), np.float32(0.9695), np.float32(0.9669), np.float32(0.8309), np.float32(0.7765), np.float32(0.8724), np.float32(0.9528), np.float32(0.3472), np.float32(0.4079)] +2025-11-12 08:45:08.389758: Epoch time: 258.11 s +2025-11-12 08:45:10.142623: +2025-11-12 08:45:10.144568: Epoch 421 +2025-11-12 08:45:10.146437: Current learning rate: 0.00612 +2025-11-12 08:49:28.383637: train_loss -0.6881 +2025-11-12 08:49:28.390514: val_loss -0.7066 +2025-11-12 08:49:28.392485: Pseudo dice [np.float32(0.919), np.float32(0.7487), np.float32(0.6972), np.float32(0.6158), np.float32(0.8494), np.float32(0.7669), np.float32(0.8873), np.float32(0.8444), np.float32(0.9779), np.float32(0.9717), np.float32(0.9674), np.float32(0.8207), np.float32(0.7442), np.float32(0.8608), np.float32(0.9574), np.float32(0.3554), np.float32(0.3685)] +2025-11-12 08:49:28.393988: Epoch time: 258.25 s +2025-11-12 08:49:30.192185: +2025-11-12 08:49:30.194427: Epoch 422 +2025-11-12 08:49:30.196985: Current learning rate: 0.00611 +2025-11-12 08:53:48.284294: train_loss -0.695 +2025-11-12 08:53:48.290004: val_loss -0.7044 +2025-11-12 08:53:48.291417: Pseudo dice [np.float32(0.919), np.float32(0.7948), np.float32(0.7326), np.float32(0.5929), np.float32(0.8619), np.float32(0.7923), np.float32(0.895), np.float32(0.8585), np.float32(0.9579), np.float32(0.955), np.float32(0.9623), np.float32(0.8272), np.float32(0.7496), np.float32(0.8746), np.float32(0.9196), np.float32(0.2617), np.float32(0.3193)] +2025-11-12 08:53:48.293309: Epoch time: 258.1 s +2025-11-12 08:53:50.116470: +2025-11-12 08:53:50.119433: Epoch 423 +2025-11-12 08:53:50.121538: Current learning rate: 0.0061 +2025-11-12 08:58:08.100889: train_loss -0.7046 +2025-11-12 08:58:08.107493: val_loss -0.7107 +2025-11-12 08:58:08.109923: Pseudo dice [np.float32(0.9084), np.float32(0.7699), np.float32(0.686), np.float32(0.6478), np.float32(0.8618), np.float32(0.794), np.float32(0.8874), np.float32(0.8517), np.float32(0.9754), np.float32(0.974), np.float32(0.9675), np.float32(0.8237), np.float32(0.7273), np.float32(0.8725), np.float32(0.9467), np.float32(0.4268), np.float32(0.4511)] +2025-11-12 08:58:08.112230: Epoch time: 257.99 s +2025-11-12 08:58:09.882068: +2025-11-12 08:58:09.883995: Epoch 424 +2025-11-12 08:58:09.886104: Current learning rate: 0.00609 +2025-11-12 09:02:28.443234: train_loss -0.7052 +2025-11-12 09:02:28.449367: val_loss -0.7149 +2025-11-12 09:02:28.451930: Pseudo dice [np.float32(0.911), np.float32(0.7549), np.float32(0.7116), np.float32(0.6533), np.float32(0.8663), np.float32(0.7994), np.float32(0.8977), np.float32(0.8548), np.float32(0.9663), np.float32(0.9673), np.float32(0.9686), np.float32(0.834), np.float32(0.7525), np.float32(0.8677), np.float32(0.9543), np.float32(0.4176), np.float32(0.3031)] +2025-11-12 09:02:28.454114: Epoch time: 258.57 s +2025-11-12 09:02:30.411383: +2025-11-12 09:02:30.412902: Epoch 425 +2025-11-12 09:02:30.414675: Current learning rate: 0.00608 +2025-11-12 09:06:48.712497: train_loss -0.6982 +2025-11-12 09:06:48.717678: val_loss -0.7097 +2025-11-12 09:06:48.719661: Pseudo dice [np.float32(0.9065), np.float32(0.787), np.float32(0.7111), np.float32(0.6552), np.float32(0.8531), np.float32(0.801), np.float32(0.8856), np.float32(0.8508), np.float32(0.9678), np.float32(0.9682), np.float32(0.967), np.float32(0.8235), np.float32(0.7854), np.float32(0.865), np.float32(0.9568), np.float32(0.3696), np.float32(0.3666)] +2025-11-12 09:06:48.721635: Epoch time: 258.31 s +2025-11-12 09:06:50.552885: +2025-11-12 09:06:50.554585: Epoch 426 +2025-11-12 09:06:50.556200: Current learning rate: 0.00607 +2025-11-12 09:11:09.052050: train_loss -0.6974 +2025-11-12 09:11:09.059606: val_loss -0.7045 +2025-11-12 09:11:09.061430: Pseudo dice [np.float32(0.9106), np.float32(0.7528), np.float32(0.6967), np.float32(0.6343), np.float32(0.8587), np.float32(0.7822), np.float32(0.9105), np.float32(0.8563), np.float32(0.9684), np.float32(0.9665), np.float32(0.9661), np.float32(0.8128), np.float32(0.7258), np.float32(0.875), np.float32(0.9461), np.float32(0.4825), np.float32(0.3544)] +2025-11-12 09:11:09.063876: Epoch time: 258.5 s +2025-11-12 09:11:10.818067: +2025-11-12 09:11:10.819583: Epoch 427 +2025-11-12 09:11:10.821105: Current learning rate: 0.00606 +2025-11-12 09:15:29.252090: train_loss -0.7049 +2025-11-12 09:15:29.263750: val_loss -0.7008 +2025-11-12 09:15:29.267412: Pseudo dice [np.float32(0.9021), np.float32(0.767), np.float32(0.6772), np.float32(0.6613), np.float32(0.8571), np.float32(0.7935), np.float32(0.8914), np.float32(0.8386), np.float32(0.9499), np.float32(0.9563), np.float32(0.9663), np.float32(0.837), np.float32(0.7483), np.float32(0.8594), np.float32(0.9504), np.float32(0.435), np.float32(0.3345)] +2025-11-12 09:15:29.270650: Epoch time: 258.44 s +2025-11-12 09:15:34.048282: +2025-11-12 09:15:34.051164: Epoch 428 +2025-11-12 09:15:34.053991: Current learning rate: 0.00605 +2025-11-12 09:19:52.498569: train_loss -0.6967 +2025-11-12 09:19:52.505313: val_loss -0.7098 +2025-11-12 09:19:52.507864: Pseudo dice [np.float32(0.9028), np.float32(0.7424), np.float32(0.7248), np.float32(0.6443), np.float32(0.848), np.float32(0.7948), np.float32(0.8811), np.float32(0.8484), np.float32(0.9742), np.float32(0.9727), np.float32(0.967), np.float32(0.8055), np.float32(0.7806), np.float32(0.8641), np.float32(0.9653), np.float32(0.399), np.float32(0.3683)] +2025-11-12 09:19:52.510228: Epoch time: 258.46 s +2025-11-12 09:19:54.311044: +2025-11-12 09:19:54.313784: Epoch 429 +2025-11-12 09:19:54.316401: Current learning rate: 0.00604 +2025-11-12 09:24:12.796721: train_loss -0.7005 +2025-11-12 09:24:12.803509: val_loss -0.7053 +2025-11-12 09:24:12.805216: Pseudo dice [np.float32(0.9136), np.float32(0.765), np.float32(0.7168), np.float32(0.6135), np.float32(0.8531), np.float32(0.7759), np.float32(0.9022), np.float32(0.8583), np.float32(0.9629), np.float32(0.9651), np.float32(0.968), np.float32(0.8257), np.float32(0.7541), np.float32(0.8648), np.float32(0.9472), np.float32(0.37), np.float32(0.3781)] +2025-11-12 09:24:12.808218: Epoch time: 258.49 s +2025-11-12 09:24:14.587518: +2025-11-12 09:24:14.589417: Epoch 430 +2025-11-12 09:24:14.591069: Current learning rate: 0.00603 +2025-11-12 09:28:33.131762: train_loss -0.6949 +2025-11-12 09:28:33.139248: val_loss -0.7192 +2025-11-12 09:28:33.140646: Pseudo dice [np.float32(0.9181), np.float32(0.7534), np.float32(0.7465), np.float32(0.6237), np.float32(0.8597), np.float32(0.7995), np.float32(0.8836), np.float32(0.8511), np.float32(0.9751), np.float32(0.9771), np.float32(0.9691), np.float32(0.8319), np.float32(0.7328), np.float32(0.8625), np.float32(0.9629), np.float32(0.4419), np.float32(0.3265)] +2025-11-12 09:28:33.142743: Epoch time: 258.55 s +2025-11-12 09:28:34.921836: +2025-11-12 09:28:34.924056: Epoch 431 +2025-11-12 09:28:34.925931: Current learning rate: 0.00602 +2025-11-12 09:32:53.307469: train_loss -0.6998 +2025-11-12 09:32:53.313565: val_loss -0.7042 +2025-11-12 09:32:53.315815: Pseudo dice [np.float32(0.9085), np.float32(0.7543), np.float32(0.6912), np.float32(0.6513), np.float32(0.8606), np.float32(0.7788), np.float32(0.8683), np.float32(0.8532), np.float32(0.9742), np.float32(0.9732), np.float32(0.9664), np.float32(0.8236), np.float32(0.7549), np.float32(0.8629), np.float32(0.953), np.float32(0.2867), np.float32(0.3368)] +2025-11-12 09:32:53.317638: Epoch time: 258.39 s +2025-11-12 09:32:55.133527: +2025-11-12 09:32:55.135607: Epoch 432 +2025-11-12 09:32:55.136976: Current learning rate: 0.00601 +2025-11-12 09:37:13.654174: train_loss -0.6986 +2025-11-12 09:37:13.658237: val_loss -0.7109 +2025-11-12 09:37:13.660054: Pseudo dice [np.float32(0.9052), np.float32(0.7616), np.float32(0.7148), np.float32(0.653), np.float32(0.8512), np.float32(0.8033), np.float32(0.9019), np.float32(0.844), np.float32(0.9742), np.float32(0.9746), np.float32(0.9665), np.float32(0.8215), np.float32(0.726), np.float32(0.8639), np.float32(0.9524), np.float32(0.3662), np.float32(0.437)] +2025-11-12 09:37:13.661778: Epoch time: 258.53 s +2025-11-12 09:37:15.557930: +2025-11-12 09:37:15.560883: Epoch 433 +2025-11-12 09:37:15.563340: Current learning rate: 0.006 +2025-11-12 09:41:33.989836: train_loss -0.7003 +2025-11-12 09:41:34.000971: val_loss -0.7202 +2025-11-12 09:41:34.003356: Pseudo dice [np.float32(0.9134), np.float32(0.7575), np.float32(0.694), np.float32(0.6372), np.float32(0.8644), np.float32(0.796), np.float32(0.8933), np.float32(0.8591), np.float32(0.9751), np.float32(0.9757), np.float32(0.9691), np.float32(0.8144), np.float32(0.7656), np.float32(0.8698), np.float32(0.9616), np.float32(0.4121), np.float32(0.4284)] +2025-11-12 09:41:34.004767: Epoch time: 258.45 s +2025-11-12 09:41:35.792271: +2025-11-12 09:41:35.793821: Epoch 434 +2025-11-12 09:41:35.795383: Current learning rate: 0.00599 +2025-11-12 09:45:54.184166: train_loss -0.7028 +2025-11-12 09:45:54.189531: val_loss -0.7199 +2025-11-12 09:45:54.191371: Pseudo dice [np.float32(0.9161), np.float32(0.7703), np.float32(0.7258), np.float32(0.6409), np.float32(0.8573), np.float32(0.7735), np.float32(0.8924), np.float32(0.8523), np.float32(0.9742), np.float32(0.9729), np.float32(0.9669), np.float32(0.8439), np.float32(0.7677), np.float32(0.8705), np.float32(0.9512), np.float32(0.4579), np.float32(0.4165)] +2025-11-12 09:45:54.192788: Epoch time: 258.4 s +2025-11-12 09:45:54.194269: Yayy! New best EMA pseudo Dice: 0.7932999730110168 +2025-11-12 09:45:59.189154: +2025-11-12 09:45:59.192137: Epoch 435 +2025-11-12 09:45:59.194794: Current learning rate: 0.00598 +2025-11-12 09:50:17.623725: train_loss -0.7015 +2025-11-12 09:50:17.633241: val_loss -0.707 +2025-11-12 09:50:17.635896: Pseudo dice [np.float32(0.9101), np.float32(0.7787), np.float32(0.7261), np.float32(0.621), np.float32(0.8645), np.float32(0.7947), np.float32(0.8918), np.float32(0.8637), np.float32(0.9766), np.float32(0.9723), np.float32(0.9693), np.float32(0.8402), np.float32(0.7343), np.float32(0.867), np.float32(0.9626), np.float32(0.3423), np.float32(0.2064)] +2025-11-12 09:50:17.638299: Epoch time: 258.44 s +2025-11-12 09:50:19.401654: +2025-11-12 09:50:19.403468: Epoch 436 +2025-11-12 09:50:19.405514: Current learning rate: 0.00597 +2025-11-12 09:54:37.785248: train_loss -0.7038 +2025-11-12 09:54:37.790926: val_loss -0.707 +2025-11-12 09:54:37.792792: Pseudo dice [np.float32(0.9202), np.float32(0.7325), np.float32(0.6978), np.float32(0.636), np.float32(0.8628), np.float32(0.7957), np.float32(0.8897), np.float32(0.8365), np.float32(0.969), np.float32(0.9722), np.float32(0.9679), np.float32(0.8279), np.float32(0.7582), np.float32(0.8686), np.float32(0.9479), np.float32(0.4928), np.float32(0.4003)] +2025-11-12 09:54:37.795158: Epoch time: 258.39 s +2025-11-12 09:54:39.557983: +2025-11-12 09:54:39.559510: Epoch 437 +2025-11-12 09:54:39.561218: Current learning rate: 0.00596 +2025-11-12 09:58:58.690128: train_loss -0.6975 +2025-11-12 09:58:58.697349: val_loss -0.7156 +2025-11-12 09:58:58.699411: Pseudo dice [np.float32(0.9132), np.float32(0.7692), np.float32(0.7368), np.float32(0.6482), np.float32(0.8637), np.float32(0.8028), np.float32(0.8938), np.float32(0.861), np.float32(0.9644), np.float32(0.9637), np.float32(0.9678), np.float32(0.8079), np.float32(0.7359), np.float32(0.8683), np.float32(0.9564), np.float32(0.4197), np.float32(0.4754)] +2025-11-12 09:58:58.701321: Epoch time: 259.14 s +2025-11-12 09:58:58.702746: Yayy! New best EMA pseudo Dice: 0.7940000295639038 +2025-11-12 09:59:03.425411: +2025-11-12 09:59:03.428005: Epoch 438 +2025-11-12 09:59:03.430544: Current learning rate: 0.00595 +2025-11-12 10:03:21.913963: train_loss -0.7004 +2025-11-12 10:03:21.920523: val_loss -0.7139 +2025-11-12 10:03:21.922467: Pseudo dice [np.float32(0.9055), np.float32(0.7579), np.float32(0.6968), np.float32(0.6427), np.float32(0.8653), np.float32(0.796), np.float32(0.881), np.float32(0.8614), np.float32(0.9647), np.float32(0.9658), np.float32(0.9677), np.float32(0.8152), np.float32(0.7458), np.float32(0.873), np.float32(0.9549), np.float32(0.4143), np.float32(0.3556)] +2025-11-12 10:03:21.924363: Epoch time: 258.49 s +2025-11-12 10:03:23.715422: +2025-11-12 10:03:23.716944: Epoch 439 +2025-11-12 10:03:23.718264: Current learning rate: 0.00594 +2025-11-12 10:07:42.115257: train_loss -0.6985 +2025-11-12 10:07:42.121992: val_loss -0.7027 +2025-11-12 10:07:42.124059: Pseudo dice [np.float32(0.913), np.float32(0.763), np.float32(0.7199), np.float32(0.637), np.float32(0.8596), np.float32(0.79), np.float32(0.8994), np.float32(0.8615), np.float32(0.9724), np.float32(0.9724), np.float32(0.9681), np.float32(0.8272), np.float32(0.7378), np.float32(0.8648), np.float32(0.9568), np.float32(0.3358), np.float32(0.3111)] +2025-11-12 10:07:42.125818: Epoch time: 258.4 s +2025-11-12 10:07:43.952471: +2025-11-12 10:07:43.954149: Epoch 440 +2025-11-12 10:07:43.955653: Current learning rate: 0.00593 +2025-11-12 10:12:02.309137: train_loss -0.7072 +2025-11-12 10:12:02.316832: val_loss -0.7116 +2025-11-12 10:12:02.318548: Pseudo dice [np.float32(0.9209), np.float32(0.7465), np.float32(0.7065), np.float32(0.6214), np.float32(0.8555), np.float32(0.7897), np.float32(0.8856), np.float32(0.8575), np.float32(0.9672), np.float32(0.9673), np.float32(0.9667), np.float32(0.8279), np.float32(0.7737), np.float32(0.8638), np.float32(0.9531), np.float32(0.4088), np.float32(0.4186)] +2025-11-12 10:12:02.320018: Epoch time: 258.36 s +2025-11-12 10:12:04.087153: +2025-11-12 10:12:04.089902: Epoch 441 +2025-11-12 10:12:04.092216: Current learning rate: 0.00592 +2025-11-12 10:16:22.767516: train_loss -0.6984 +2025-11-12 10:16:22.776000: val_loss -0.7015 +2025-11-12 10:16:22.779591: Pseudo dice [np.float32(0.9176), np.float32(0.7574), np.float32(0.7155), np.float32(0.6512), np.float32(0.8531), np.float32(0.78), np.float32(0.8936), np.float32(0.8489), np.float32(0.9728), np.float32(0.975), np.float32(0.9666), np.float32(0.8257), np.float32(0.7602), np.float32(0.8582), np.float32(0.9539), np.float32(0.3299), np.float32(0.33)] +2025-11-12 10:16:22.782690: Epoch time: 258.69 s +2025-11-12 10:16:24.615562: +2025-11-12 10:16:24.617569: Epoch 442 +2025-11-12 10:16:24.619838: Current learning rate: 0.00592 +2025-11-12 10:20:43.308198: train_loss -0.7038 +2025-11-12 10:20:43.314741: val_loss -0.7157 +2025-11-12 10:20:43.316900: Pseudo dice [np.float32(0.912), np.float32(0.7601), np.float32(0.7063), np.float32(0.6589), np.float32(0.8534), np.float32(0.79), np.float32(0.8966), np.float32(0.849), np.float32(0.9718), np.float32(0.9778), np.float32(0.9678), np.float32(0.8332), np.float32(0.7773), np.float32(0.8674), np.float32(0.9609), np.float32(0.388), np.float32(0.3746)] +2025-11-12 10:20:43.319038: Epoch time: 258.7 s +2025-11-12 10:20:45.057079: +2025-11-12 10:20:45.060177: Epoch 443 +2025-11-12 10:20:45.063348: Current learning rate: 0.00591 +2025-11-12 10:25:03.327527: train_loss -0.7046 +2025-11-12 10:25:03.336651: val_loss -0.7083 +2025-11-12 10:25:03.339113: Pseudo dice [np.float32(0.9122), np.float32(0.7671), np.float32(0.7352), np.float32(0.6452), np.float32(0.8566), np.float32(0.7917), np.float32(0.8864), np.float32(0.8553), np.float32(0.9648), np.float32(0.9656), np.float32(0.9675), np.float32(0.8238), np.float32(0.7277), np.float32(0.8676), np.float32(0.9536), np.float32(0.4134), np.float32(0.3481)] +2025-11-12 10:25:03.341461: Epoch time: 258.28 s +2025-11-12 10:25:05.105006: +2025-11-12 10:25:05.107786: Epoch 444 +2025-11-12 10:25:05.110287: Current learning rate: 0.0059 +2025-11-12 10:29:23.657661: train_loss -0.7028 +2025-11-12 10:29:23.663046: val_loss -0.7067 +2025-11-12 10:29:23.664778: Pseudo dice [np.float32(0.9085), np.float32(0.7649), np.float32(0.684), np.float32(0.667), np.float32(0.8628), np.float32(0.7895), np.float32(0.8951), np.float32(0.8545), np.float32(0.9694), np.float32(0.9702), np.float32(0.9659), np.float32(0.816), np.float32(0.7494), np.float32(0.8724), np.float32(0.9563), np.float32(0.2976), np.float32(0.2783)] +2025-11-12 10:29:23.666499: Epoch time: 258.56 s +2025-11-12 10:29:25.402394: +2025-11-12 10:29:25.403880: Epoch 445 +2025-11-12 10:29:25.405152: Current learning rate: 0.00589 +2025-11-12 10:33:44.082144: train_loss -0.7029 +2025-11-12 10:33:44.087002: val_loss -0.7097 +2025-11-12 10:33:44.088732: Pseudo dice [np.float32(0.9147), np.float32(0.79), np.float32(0.7336), np.float32(0.6001), np.float32(0.8516), np.float32(0.7676), np.float32(0.8788), np.float32(0.8539), np.float32(0.9747), np.float32(0.9732), np.float32(0.9687), np.float32(0.8284), np.float32(0.7226), np.float32(0.8608), np.float32(0.9638), np.float32(0.3644), np.float32(0.436)] +2025-11-12 10:33:44.090036: Epoch time: 258.69 s +2025-11-12 10:33:45.829441: +2025-11-12 10:33:45.830847: Epoch 446 +2025-11-12 10:33:45.832148: Current learning rate: 0.00588 +2025-11-12 10:38:05.295823: train_loss -0.7055 +2025-11-12 10:38:05.299966: val_loss -0.7107 +2025-11-12 10:38:05.301295: Pseudo dice [np.float32(0.9161), np.float32(0.7611), np.float32(0.7327), np.float32(0.6261), np.float32(0.8645), np.float32(0.7888), np.float32(0.8921), np.float32(0.8468), np.float32(0.9714), np.float32(0.9771), np.float32(0.97), np.float32(0.8323), np.float32(0.7379), np.float32(0.8632), np.float32(0.9638), np.float32(0.3666), np.float32(0.3812)] +2025-11-12 10:38:05.302553: Epoch time: 259.47 s +2025-11-12 10:38:07.038533: +2025-11-12 10:38:07.040134: Epoch 447 +2025-11-12 10:38:07.041861: Current learning rate: 0.00587 +2025-11-12 10:42:25.518859: train_loss -0.6965 +2025-11-12 10:42:25.524668: val_loss -0.7002 +2025-11-12 10:42:25.527308: Pseudo dice [np.float32(0.9037), np.float32(0.7555), np.float32(0.7195), np.float32(0.6432), np.float32(0.8511), np.float32(0.7925), np.float32(0.8796), np.float32(0.8524), np.float32(0.9704), np.float32(0.9719), np.float32(0.9677), np.float32(0.8155), np.float32(0.7678), np.float32(0.8646), np.float32(0.9578), np.float32(0.3726), np.float32(0.3289)] +2025-11-12 10:42:25.529422: Epoch time: 258.49 s +2025-11-12 10:42:27.226951: +2025-11-12 10:42:27.229470: Epoch 448 +2025-11-12 10:42:27.230953: Current learning rate: 0.00586 +2025-11-12 10:46:45.632807: train_loss -0.6974 +2025-11-12 10:46:45.639700: val_loss -0.7118 +2025-11-12 10:46:45.641366: Pseudo dice [np.float32(0.9117), np.float32(0.7602), np.float32(0.6979), np.float32(0.6097), np.float32(0.8523), np.float32(0.7839), np.float32(0.8912), np.float32(0.8454), np.float32(0.969), np.float32(0.9684), np.float32(0.9649), np.float32(0.8125), np.float32(0.7092), np.float32(0.8706), np.float32(0.9513), np.float32(0.4816), np.float32(0.3663)] +2025-11-12 10:46:45.643847: Epoch time: 258.41 s +2025-11-12 10:46:47.407379: +2025-11-12 10:46:47.409669: Epoch 449 +2025-11-12 10:46:47.412193: Current learning rate: 0.00585 +2025-11-12 10:51:06.014165: train_loss -0.6938 +2025-11-12 10:51:06.021401: val_loss -0.7012 +2025-11-12 10:51:06.023571: Pseudo dice [np.float32(0.9037), np.float32(0.7632), np.float32(0.7162), np.float32(0.6494), np.float32(0.8603), np.float32(0.7893), np.float32(0.888), np.float32(0.8507), np.float32(0.975), np.float32(0.9715), np.float32(0.969), np.float32(0.8084), np.float32(0.7538), np.float32(0.8582), np.float32(0.9622), np.float32(0.3789), np.float32(0.3261)] +2025-11-12 10:51:06.025481: Epoch time: 258.61 s +2025-11-12 10:51:10.777518: +2025-11-12 10:51:10.778850: Epoch 450 +2025-11-12 10:51:10.780138: Current learning rate: 0.00584 +2025-11-12 10:55:29.386993: train_loss -0.6902 +2025-11-12 10:55:29.390911: val_loss -0.7201 +2025-11-12 10:55:29.392201: Pseudo dice [np.float32(0.9147), np.float32(0.7666), np.float32(0.7144), np.float32(0.6399), np.float32(0.8604), np.float32(0.7864), np.float32(0.8822), np.float32(0.8432), np.float32(0.9771), np.float32(0.9756), np.float32(0.9684), np.float32(0.805), np.float32(0.7831), np.float32(0.874), np.float32(0.9577), np.float32(0.4166), np.float32(0.4172)] +2025-11-12 10:55:29.393544: Epoch time: 258.62 s +2025-11-12 10:55:31.165753: +2025-11-12 10:55:31.167169: Epoch 451 +2025-11-12 10:55:31.168685: Current learning rate: 0.00583 +2025-11-12 10:59:49.726705: train_loss -0.7009 +2025-11-12 10:59:49.735195: val_loss -0.7053 +2025-11-12 10:59:49.737769: Pseudo dice [np.float32(0.9207), np.float32(0.7523), np.float32(0.7442), np.float32(0.6648), np.float32(0.8592), np.float32(0.7934), np.float32(0.8809), np.float32(0.8527), np.float32(0.9778), np.float32(0.9776), np.float32(0.9682), np.float32(0.8284), np.float32(0.7187), np.float32(0.8727), np.float32(0.9614), np.float32(0.3869), np.float32(0.2746)] +2025-11-12 10:59:49.740081: Epoch time: 258.57 s +2025-11-12 10:59:51.538433: +2025-11-12 10:59:51.539996: Epoch 452 +2025-11-12 10:59:51.541466: Current learning rate: 0.00582 +2025-11-12 11:04:10.224399: train_loss -0.6995 +2025-11-12 11:04:10.230238: val_loss -0.7042 +2025-11-12 11:04:10.232141: Pseudo dice [np.float32(0.9162), np.float32(0.7606), np.float32(0.7112), np.float32(0.6283), np.float32(0.8537), np.float32(0.8012), np.float32(0.8988), np.float32(0.85), np.float32(0.9724), np.float32(0.9762), np.float32(0.9674), np.float32(0.8265), np.float32(0.7737), np.float32(0.8644), np.float32(0.9602), np.float32(0.326), np.float32(0.4246)] +2025-11-12 11:04:10.234149: Epoch time: 258.69 s +2025-11-12 11:04:12.001433: +2025-11-12 11:04:12.004614: Epoch 453 +2025-11-12 11:04:12.007771: Current learning rate: 0.00581 +2025-11-12 11:08:30.530841: train_loss -0.7013 +2025-11-12 11:08:30.536593: val_loss -0.7101 +2025-11-12 11:08:30.539191: Pseudo dice [np.float32(0.9128), np.float32(0.7516), np.float32(0.7192), np.float32(0.6459), np.float32(0.8568), np.float32(0.8028), np.float32(0.8805), np.float32(0.8535), np.float32(0.9732), np.float32(0.9726), np.float32(0.9688), np.float32(0.8185), np.float32(0.7476), np.float32(0.867), np.float32(0.9594), np.float32(0.3432), np.float32(0.3326)] +2025-11-12 11:08:30.540641: Epoch time: 258.54 s +2025-11-12 11:08:32.442586: +2025-11-12 11:08:32.445572: Epoch 454 +2025-11-12 11:08:32.448582: Current learning rate: 0.0058 +2025-11-12 11:12:50.845911: train_loss -0.6988 +2025-11-12 11:12:50.854143: val_loss -0.7005 +2025-11-12 11:12:50.856356: Pseudo dice [np.float32(0.9171), np.float32(0.7229), np.float32(0.7015), np.float32(0.6126), np.float32(0.8485), np.float32(0.7851), np.float32(0.8258), np.float32(0.8478), np.float32(0.9708), np.float32(0.9777), np.float32(0.9669), np.float32(0.821), np.float32(0.7384), np.float32(0.8545), np.float32(0.955), np.float32(0.4259), np.float32(0.331)] +2025-11-12 11:12:50.857893: Epoch time: 258.41 s +2025-11-12 11:12:52.627868: +2025-11-12 11:12:52.629511: Epoch 455 +2025-11-12 11:12:52.630635: Current learning rate: 0.00579 +2025-11-12 11:17:10.956797: train_loss -0.7032 +2025-11-12 11:17:10.966282: val_loss -0.72 +2025-11-12 11:17:10.969138: Pseudo dice [np.float32(0.9156), np.float32(0.796), np.float32(0.7433), np.float32(0.6114), np.float32(0.8669), np.float32(0.8056), np.float32(0.9049), np.float32(0.8454), np.float32(0.9781), np.float32(0.9736), np.float32(0.9684), np.float32(0.8213), np.float32(0.7444), np.float32(0.867), np.float32(0.9611), np.float32(0.399), np.float32(0.4322)] +2025-11-12 11:17:10.972081: Epoch time: 258.33 s +2025-11-12 11:17:14.319412: +2025-11-12 11:17:14.321936: Epoch 456 +2025-11-12 11:17:14.324278: Current learning rate: 0.00578 +2025-11-12 11:21:32.782565: train_loss -0.7058 +2025-11-12 11:21:32.791429: val_loss -0.6924 +2025-11-12 11:21:32.793213: Pseudo dice [np.float32(0.9032), np.float32(0.7767), np.float32(0.7056), np.float32(0.6378), np.float32(0.8613), np.float32(0.8046), np.float32(0.8792), np.float32(0.8458), np.float32(0.9729), np.float32(0.9694), np.float32(0.9693), np.float32(0.8373), np.float32(0.7109), np.float32(0.8719), np.float32(0.9618), np.float32(0.3414), np.float32(0.2725)] +2025-11-12 11:21:32.795489: Epoch time: 258.47 s +2025-11-12 11:21:34.588202: +2025-11-12 11:21:34.591810: Epoch 457 +2025-11-12 11:21:34.593936: Current learning rate: 0.00577 +2025-11-12 11:25:53.277246: train_loss -0.7028 +2025-11-12 11:25:53.284520: val_loss -0.7172 +2025-11-12 11:25:53.286010: Pseudo dice [np.float32(0.9126), np.float32(0.7643), np.float32(0.708), np.float32(0.6588), np.float32(0.8691), np.float32(0.8024), np.float32(0.8847), np.float32(0.8564), np.float32(0.97), np.float32(0.9704), np.float32(0.9682), np.float32(0.8348), np.float32(0.7654), np.float32(0.8801), np.float32(0.9615), np.float32(0.4499), np.float32(0.4139)] +2025-11-12 11:25:53.289290: Epoch time: 258.69 s +2025-11-12 11:25:55.054584: +2025-11-12 11:25:55.056316: Epoch 458 +2025-11-12 11:25:55.057926: Current learning rate: 0.00576 +2025-11-12 11:30:13.910111: train_loss -0.7032 +2025-11-12 11:30:13.918474: val_loss -0.7145 +2025-11-12 11:30:13.921140: Pseudo dice [np.float32(0.9154), np.float32(0.7582), np.float32(0.7396), np.float32(0.6449), np.float32(0.869), np.float32(0.794), np.float32(0.8887), np.float32(0.8523), np.float32(0.9788), np.float32(0.9807), np.float32(0.9695), np.float32(0.8302), np.float32(0.7454), np.float32(0.8743), np.float32(0.9625), np.float32(0.375), np.float32(0.402)] +2025-11-12 11:30:13.923544: Epoch time: 258.86 s +2025-11-12 11:30:15.710505: +2025-11-12 11:30:15.712725: Epoch 459 +2025-11-12 11:30:15.714353: Current learning rate: 0.00575 +2025-11-12 11:34:34.075987: train_loss -0.6987 +2025-11-12 11:34:34.080457: val_loss -0.7024 +2025-11-12 11:34:34.081921: Pseudo dice [np.float32(0.9129), np.float32(0.7538), np.float32(0.7337), np.float32(0.6365), np.float32(0.86), np.float32(0.7814), np.float32(0.8757), np.float32(0.8551), np.float32(0.9639), np.float32(0.9636), np.float32(0.9642), np.float32(0.8288), np.float32(0.7323), np.float32(0.8605), np.float32(0.948), np.float32(0.3745), np.float32(0.355)] +2025-11-12 11:34:34.083145: Epoch time: 258.37 s +2025-11-12 11:34:35.819074: +2025-11-12 11:34:35.821186: Epoch 460 +2025-11-12 11:34:35.823158: Current learning rate: 0.00574 +2025-11-12 11:38:54.230109: train_loss -0.6948 +2025-11-12 11:38:54.236585: val_loss -0.715 +2025-11-12 11:38:54.239441: Pseudo dice [np.float32(0.9035), np.float32(0.7421), np.float32(0.6619), np.float32(0.6605), np.float32(0.861), np.float32(0.8004), np.float32(0.878), np.float32(0.8568), np.float32(0.9777), np.float32(0.9748), np.float32(0.9666), np.float32(0.8281), np.float32(0.7586), np.float32(0.8701), np.float32(0.9616), np.float32(0.4074), np.float32(0.3864)] +2025-11-12 11:38:54.242103: Epoch time: 258.42 s +2025-11-12 11:38:55.982605: +2025-11-12 11:38:55.985654: Epoch 461 +2025-11-12 11:38:55.988457: Current learning rate: 0.00573 +2025-11-12 11:43:14.336244: train_loss -0.7029 +2025-11-12 11:43:14.341367: val_loss -0.7107 +2025-11-12 11:43:14.343477: Pseudo dice [np.float32(0.9111), np.float32(0.776), np.float32(0.6909), np.float32(0.6372), np.float32(0.8597), np.float32(0.7944), np.float32(0.8865), np.float32(0.8579), np.float32(0.977), np.float32(0.9774), np.float32(0.9681), np.float32(0.8294), np.float32(0.7686), np.float32(0.8691), np.float32(0.9616), np.float32(0.3873), np.float32(0.3159)] +2025-11-12 11:43:14.345379: Epoch time: 258.36 s +2025-11-12 11:43:16.129516: +2025-11-12 11:43:16.131662: Epoch 462 +2025-11-12 11:43:16.133573: Current learning rate: 0.00572 +2025-11-12 11:47:34.977789: train_loss -0.6977 +2025-11-12 11:47:34.985216: val_loss -0.7073 +2025-11-12 11:47:34.987793: Pseudo dice [np.float32(0.9206), np.float32(0.7651), np.float32(0.7207), np.float32(0.6154), np.float32(0.8502), np.float32(0.7937), np.float32(0.8722), np.float32(0.8574), np.float32(0.9713), np.float32(0.9745), np.float32(0.9689), np.float32(0.8136), np.float32(0.7481), np.float32(0.8641), np.float32(0.9514), np.float32(0.3656), np.float32(0.3561)] +2025-11-12 11:47:34.990134: Epoch time: 258.85 s +2025-11-12 11:47:36.745839: +2025-11-12 11:47:36.747244: Epoch 463 +2025-11-12 11:47:36.749258: Current learning rate: 0.00571 +2025-11-12 11:51:55.286221: train_loss -0.6857 +2025-11-12 11:51:55.295533: val_loss -0.7035 +2025-11-12 11:51:55.298385: Pseudo dice [np.float32(0.9111), np.float32(0.7647), np.float32(0.7004), np.float32(0.6327), np.float32(0.8589), np.float32(0.7976), np.float32(0.8998), np.float32(0.8496), np.float32(0.976), np.float32(0.9652), np.float32(0.9665), np.float32(0.8095), np.float32(0.728), np.float32(0.867), np.float32(0.9585), np.float32(0.3909), np.float32(0.3667)] +2025-11-12 11:51:55.301238: Epoch time: 258.55 s +2025-11-12 11:51:57.056892: +2025-11-12 11:51:57.058300: Epoch 464 +2025-11-12 11:51:57.059737: Current learning rate: 0.0057 +2025-11-12 11:56:15.401810: train_loss -0.6999 +2025-11-12 11:56:15.405865: val_loss -0.7019 +2025-11-12 11:56:15.407259: Pseudo dice [np.float32(0.9065), np.float32(0.7432), np.float32(0.6825), np.float32(0.61), np.float32(0.8532), np.float32(0.8001), np.float32(0.8938), np.float32(0.8619), np.float32(0.9691), np.float32(0.9677), np.float32(0.9681), np.float32(0.8252), np.float32(0.7478), np.float32(0.8642), np.float32(0.9591), np.float32(0.4094), np.float32(0.3562)] +2025-11-12 11:56:15.408408: Epoch time: 258.35 s +2025-11-12 11:56:17.240818: +2025-11-12 11:56:17.243088: Epoch 465 +2025-11-12 11:56:17.244958: Current learning rate: 0.0057 +2025-11-12 12:00:36.533540: train_loss -0.6976 +2025-11-12 12:00:36.537548: val_loss -0.7112 +2025-11-12 12:00:36.538750: Pseudo dice [np.float32(0.9104), np.float32(0.7699), np.float32(0.7069), np.float32(0.6397), np.float32(0.8702), np.float32(0.8155), np.float32(0.8586), np.float32(0.8647), np.float32(0.9663), np.float32(0.9739), np.float32(0.9696), np.float32(0.8445), np.float32(0.7863), np.float32(0.8779), np.float32(0.9589), np.float32(0.3672), np.float32(0.3188)] +2025-11-12 12:00:36.540295: Epoch time: 259.3 s +2025-11-12 12:00:38.309334: +2025-11-12 12:00:38.312239: Epoch 466 +2025-11-12 12:00:38.315002: Current learning rate: 0.00569 +2025-11-12 12:04:56.759692: train_loss -0.6999 +2025-11-12 12:04:56.768593: val_loss -0.7076 +2025-11-12 12:04:56.771094: Pseudo dice [np.float32(0.9268), np.float32(0.7866), np.float32(0.6991), np.float32(0.6191), np.float32(0.8532), np.float32(0.7886), np.float32(0.8514), np.float32(0.8454), np.float32(0.9726), np.float32(0.9744), np.float32(0.9689), np.float32(0.8343), np.float32(0.7564), np.float32(0.8683), np.float32(0.9588), np.float32(0.4498), np.float32(0.3391)] +2025-11-12 12:04:56.773705: Epoch time: 258.46 s +2025-11-12 12:04:58.546591: +2025-11-12 12:04:58.548285: Epoch 467 +2025-11-12 12:04:58.550125: Current learning rate: 0.00568 +2025-11-12 12:09:17.152336: train_loss -0.7019 +2025-11-12 12:09:17.159570: val_loss -0.7113 +2025-11-12 12:09:17.161171: Pseudo dice [np.float32(0.9145), np.float32(0.6335), np.float32(0.6877), np.float32(0.652), np.float32(0.8546), np.float32(0.7909), np.float32(0.9065), np.float32(0.8518), np.float32(0.9782), np.float32(0.9758), np.float32(0.9686), np.float32(0.8423), np.float32(0.7163), np.float32(0.8667), np.float32(0.964), np.float32(0.4345), np.float32(0.346)] +2025-11-12 12:09:17.163486: Epoch time: 258.61 s +2025-11-12 12:09:18.965039: +2025-11-12 12:09:18.967572: Epoch 468 +2025-11-12 12:09:18.969637: Current learning rate: 0.00567 +2025-11-12 12:13:37.619214: train_loss -0.7094 +2025-11-12 12:13:37.627826: val_loss -0.7171 +2025-11-12 12:13:37.630063: Pseudo dice [np.float32(0.9111), np.float32(0.745), np.float32(0.7052), np.float32(0.6612), np.float32(0.8691), np.float32(0.7933), np.float32(0.9066), np.float32(0.8596), np.float32(0.9743), np.float32(0.9685), np.float32(0.9693), np.float32(0.8293), np.float32(0.753), np.float32(0.874), np.float32(0.9624), np.float32(0.3472), np.float32(0.3067)] +2025-11-12 12:13:37.631791: Epoch time: 258.66 s +2025-11-12 12:13:39.397481: +2025-11-12 12:13:39.399956: Epoch 469 +2025-11-12 12:13:39.402436: Current learning rate: 0.00566 +2025-11-12 12:17:57.835554: train_loss -0.7038 +2025-11-12 12:17:57.845349: val_loss -0.696 +2025-11-12 12:17:57.848218: Pseudo dice [np.float32(0.9175), np.float32(0.7736), np.float32(0.6929), np.float32(0.6349), np.float32(0.8574), np.float32(0.8014), np.float32(0.895), np.float32(0.8661), np.float32(0.9291), np.float32(0.9329), np.float32(0.9629), np.float32(0.8321), np.float32(0.7604), np.float32(0.8607), np.float32(0.9273), np.float32(0.4423), np.float32(0.3226)] +2025-11-12 12:17:57.850538: Epoch time: 258.44 s +2025-11-12 12:17:59.850470: +2025-11-12 12:17:59.852965: Epoch 470 +2025-11-12 12:17:59.855332: Current learning rate: 0.00565 +2025-11-12 12:22:18.312459: train_loss -0.6988 +2025-11-12 12:22:18.321727: val_loss -0.7128 +2025-11-12 12:22:18.324482: Pseudo dice [np.float32(0.9167), np.float32(0.7708), np.float32(0.7343), np.float32(0.6599), np.float32(0.855), np.float32(0.7937), np.float32(0.8964), np.float32(0.8566), np.float32(0.9709), np.float32(0.9719), np.float32(0.9683), np.float32(0.8355), np.float32(0.755), np.float32(0.8593), np.float32(0.9575), np.float32(0.462), np.float32(0.3251)] +2025-11-12 12:22:18.326996: Epoch time: 258.47 s +2025-11-12 12:22:20.116775: +2025-11-12 12:22:20.118137: Epoch 471 +2025-11-12 12:22:20.119786: Current learning rate: 0.00564 +2025-11-12 12:26:38.823011: train_loss -0.6987 +2025-11-12 12:26:38.826921: val_loss -0.7097 +2025-11-12 12:26:38.828312: Pseudo dice [np.float32(0.9118), np.float32(0.7526), np.float32(0.7085), np.float32(0.6553), np.float32(0.8652), np.float32(0.7899), np.float32(0.9035), np.float32(0.8627), np.float32(0.9686), np.float32(0.9651), np.float32(0.9681), np.float32(0.8333), np.float32(0.7442), np.float32(0.8701), np.float32(0.955), np.float32(0.3615), np.float32(0.2599)] +2025-11-12 12:26:38.829570: Epoch time: 258.71 s +2025-11-12 12:26:40.690114: +2025-11-12 12:26:40.692073: Epoch 472 +2025-11-12 12:26:40.693553: Current learning rate: 0.00563 +2025-11-12 12:30:59.500512: train_loss -0.7011 +2025-11-12 12:30:59.507622: val_loss -0.7142 +2025-11-12 12:30:59.509983: Pseudo dice [np.float32(0.8968), np.float32(0.7567), np.float32(0.7385), np.float32(0.6604), np.float32(0.8597), np.float32(0.7916), np.float32(0.9032), np.float32(0.8445), np.float32(0.9679), np.float32(0.9695), np.float32(0.9664), np.float32(0.819), np.float32(0.7597), np.float32(0.8725), np.float32(0.9544), np.float32(0.4113), np.float32(0.3148)] +2025-11-12 12:30:59.511345: Epoch time: 258.82 s +2025-11-12 12:31:01.293432: +2025-11-12 12:31:01.295382: Epoch 473 +2025-11-12 12:31:01.296753: Current learning rate: 0.00562 +2025-11-12 12:35:19.849196: train_loss -0.6994 +2025-11-12 12:35:19.856281: val_loss -0.7073 +2025-11-12 12:35:19.859862: Pseudo dice [np.float32(0.9001), np.float32(0.7645), np.float32(0.7317), np.float32(0.6279), np.float32(0.8606), np.float32(0.7932), np.float32(0.8936), np.float32(0.857), np.float32(0.9558), np.float32(0.9536), np.float32(0.9671), np.float32(0.8318), np.float32(0.7477), np.float32(0.8644), np.float32(0.9552), np.float32(0.3533), np.float32(0.3075)] +2025-11-12 12:35:19.863178: Epoch time: 258.56 s +2025-11-12 12:35:21.700657: +2025-11-12 12:35:21.703148: Epoch 474 +2025-11-12 12:35:21.705178: Current learning rate: 0.00561 +2025-11-12 12:39:40.237654: train_loss -0.7014 +2025-11-12 12:39:40.241788: val_loss -0.7001 +2025-11-12 12:39:40.243508: Pseudo dice [np.float32(0.903), np.float32(0.7581), np.float32(0.7199), np.float32(0.6362), np.float32(0.8573), np.float32(0.7969), np.float32(0.8442), np.float32(0.8471), np.float32(0.9627), np.float32(0.9594), np.float32(0.9662), np.float32(0.8126), np.float32(0.7508), np.float32(0.8799), np.float32(0.9501), np.float32(0.4442), np.float32(0.3756)] +2025-11-12 12:39:40.245239: Epoch time: 258.54 s +2025-11-12 12:39:43.645275: +2025-11-12 12:39:43.647816: Epoch 475 +2025-11-12 12:39:43.649956: Current learning rate: 0.0056 +2025-11-12 12:44:02.217630: train_loss -0.697 +2025-11-12 12:44:02.223457: val_loss -0.6977 +2025-11-12 12:44:02.225144: Pseudo dice [np.float32(0.9157), np.float32(0.7507), np.float32(0.7279), np.float32(0.6233), np.float32(0.8558), np.float32(0.7887), np.float32(0.8893), np.float32(0.8535), np.float32(0.9718), np.float32(0.9706), np.float32(0.9684), np.float32(0.8215), np.float32(0.7379), np.float32(0.8703), np.float32(0.9558), np.float32(0.3383), np.float32(0.3219)] +2025-11-12 12:44:02.227629: Epoch time: 258.58 s +2025-11-12 12:44:04.086979: +2025-11-12 12:44:04.089551: Epoch 476 +2025-11-12 12:44:04.092220: Current learning rate: 0.00559 +2025-11-12 12:48:22.700588: train_loss -0.6962 +2025-11-12 12:48:22.708729: val_loss -0.7162 +2025-11-12 12:48:22.711022: Pseudo dice [np.float32(0.9158), np.float32(0.7758), np.float32(0.6926), np.float32(0.6606), np.float32(0.8617), np.float32(0.7849), np.float32(0.8814), np.float32(0.8707), np.float32(0.9562), np.float32(0.9547), np.float32(0.9692), np.float32(0.8325), np.float32(0.7402), np.float32(0.8774), np.float32(0.9574), np.float32(0.3378), np.float32(0.431)] +2025-11-12 12:48:22.713675: Epoch time: 258.62 s +2025-11-12 12:48:24.620476: +2025-11-12 12:48:24.622498: Epoch 477 +2025-11-12 12:48:24.624351: Current learning rate: 0.00558 +2025-11-12 12:52:43.542423: train_loss -0.7037 +2025-11-12 12:52:43.550875: val_loss -0.7036 +2025-11-12 12:52:43.553679: Pseudo dice [np.float32(0.907), np.float32(0.7597), np.float32(0.7094), np.float32(0.6477), np.float32(0.8619), np.float32(0.8115), np.float32(0.8824), np.float32(0.8368), np.float32(0.9765), np.float32(0.9768), np.float32(0.9677), np.float32(0.8257), np.float32(0.7372), np.float32(0.8721), np.float32(0.9626), np.float32(0.3039), np.float32(0.3289)] +2025-11-12 12:52:43.556147: Epoch time: 258.93 s +2025-11-12 12:52:45.388958: +2025-11-12 12:52:45.390468: Epoch 478 +2025-11-12 12:52:45.391892: Current learning rate: 0.00557 +2025-11-12 12:57:04.078117: train_loss -0.7009 +2025-11-12 12:57:04.084801: val_loss -0.7145 +2025-11-12 12:57:04.086921: Pseudo dice [np.float32(0.909), np.float32(0.7568), np.float32(0.7169), np.float32(0.6325), np.float32(0.8643), np.float32(0.8019), np.float32(0.9052), np.float32(0.8506), np.float32(0.9743), np.float32(0.9737), np.float32(0.9685), np.float32(0.8249), np.float32(0.7706), np.float32(0.8769), np.float32(0.9603), np.float32(0.3885), np.float32(0.293)] +2025-11-12 12:57:04.088835: Epoch time: 258.69 s +2025-11-12 12:57:05.915399: +2025-11-12 12:57:05.917712: Epoch 479 +2025-11-12 12:57:05.919653: Current learning rate: 0.00556 +2025-11-12 13:01:24.577332: train_loss -0.7014 +2025-11-12 13:01:24.583992: val_loss -0.7181 +2025-11-12 13:01:24.585958: Pseudo dice [np.float32(0.9085), np.float32(0.7776), np.float32(0.7157), np.float32(0.6276), np.float32(0.8631), np.float32(0.8106), np.float32(0.9086), np.float32(0.8552), np.float32(0.9689), np.float32(0.9732), np.float32(0.9698), np.float32(0.8256), np.float32(0.7445), np.float32(0.8746), np.float32(0.9596), np.float32(0.417), np.float32(0.3177)] +2025-11-12 13:01:24.588360: Epoch time: 258.67 s +2025-11-12 13:01:26.410608: +2025-11-12 13:01:26.412384: Epoch 480 +2025-11-12 13:01:26.413993: Current learning rate: 0.00555 +2025-11-12 13:05:44.992951: train_loss -0.7062 +2025-11-12 13:05:45.002244: val_loss -0.719 +2025-11-12 13:05:45.004932: Pseudo dice [np.float32(0.9096), np.float32(0.7972), np.float32(0.7275), np.float32(0.6493), np.float32(0.8574), np.float32(0.7899), np.float32(0.8923), np.float32(0.8555), np.float32(0.9781), np.float32(0.9716), np.float32(0.9689), np.float32(0.8248), np.float32(0.7655), np.float32(0.8701), np.float32(0.9602), np.float32(0.407), np.float32(0.3985)] +2025-11-12 13:05:45.007499: Epoch time: 258.59 s +2025-11-12 13:05:47.039099: +2025-11-12 13:05:47.041497: Epoch 481 +2025-11-12 13:05:47.043880: Current learning rate: 0.00554 +2025-11-12 13:10:05.516660: train_loss -0.7006 +2025-11-12 13:10:05.524068: val_loss -0.7182 +2025-11-12 13:10:05.527074: Pseudo dice [np.float32(0.9219), np.float32(0.7861), np.float32(0.6929), np.float32(0.6735), np.float32(0.8615), np.float32(0.8069), np.float32(0.8892), np.float32(0.8488), np.float32(0.9692), np.float32(0.9709), np.float32(0.9688), np.float32(0.8255), np.float32(0.7505), np.float32(0.8719), np.float32(0.9559), np.float32(0.5334), np.float32(0.4036)] +2025-11-12 13:10:05.530317: Epoch time: 258.48 s +2025-11-12 13:10:07.341986: +2025-11-12 13:10:07.344461: Epoch 482 +2025-11-12 13:10:07.346897: Current learning rate: 0.00553 +2025-11-12 13:14:25.960307: train_loss -0.7021 +2025-11-12 13:14:25.967109: val_loss -0.7132 +2025-11-12 13:14:25.968300: Pseudo dice [np.float32(0.912), np.float32(0.7723), np.float32(0.7254), np.float32(0.6763), np.float32(0.8512), np.float32(0.8043), np.float32(0.8961), np.float32(0.8488), np.float32(0.9727), np.float32(0.9727), np.float32(0.969), np.float32(0.8383), np.float32(0.7734), np.float32(0.8621), np.float32(0.9639), np.float32(0.3974), np.float32(0.4082)] +2025-11-12 13:14:25.969975: Epoch time: 258.62 s +2025-11-12 13:14:25.972016: Yayy! New best EMA pseudo Dice: 0.794700026512146 +2025-11-12 13:14:35.224713: +2025-11-12 13:14:35.227337: Epoch 483 +2025-11-12 13:14:35.230261: Current learning rate: 0.00552 +2025-11-12 13:18:53.719378: train_loss -0.6964 +2025-11-12 13:18:53.730515: val_loss -0.7092 +2025-11-12 13:18:53.733909: Pseudo dice [np.float32(0.8901), np.float32(0.7674), np.float32(0.7161), np.float32(0.6452), np.float32(0.8642), np.float32(0.7898), np.float32(0.8963), np.float32(0.8342), np.float32(0.9692), np.float32(0.9689), np.float32(0.9671), np.float32(0.8181), np.float32(0.7619), np.float32(0.8777), np.float32(0.9571), np.float32(0.4432), np.float32(0.3446)] +2025-11-12 13:18:53.737089: Epoch time: 258.5 s +2025-11-12 13:18:53.740115: Yayy! New best EMA pseudo Dice: 0.794700026512146 +2025-11-12 13:18:58.819681: +2025-11-12 13:18:58.821852: Epoch 484 +2025-11-12 13:18:58.823588: Current learning rate: 0.00551 +2025-11-12 13:23:18.506351: train_loss -0.6947 +2025-11-12 13:23:18.511824: val_loss -0.7043 +2025-11-12 13:23:18.514115: Pseudo dice [np.float32(0.9134), np.float32(0.7511), np.float32(0.7183), np.float32(0.6657), np.float32(0.8536), np.float32(0.7923), np.float32(0.9066), np.float32(0.8561), np.float32(0.9736), np.float32(0.9717), np.float32(0.9702), np.float32(0.8226), np.float32(0.7248), np.float32(0.8621), np.float32(0.9594), np.float32(0.3321), np.float32(0.2757)] +2025-11-12 13:23:18.515578: Epoch time: 259.69 s +2025-11-12 13:23:20.352557: +2025-11-12 13:23:20.354110: Epoch 485 +2025-11-12 13:23:20.355639: Current learning rate: 0.0055 +2025-11-12 13:27:39.036398: train_loss -0.7016 +2025-11-12 13:27:39.041067: val_loss -0.7035 +2025-11-12 13:27:39.042763: Pseudo dice [np.float32(0.9244), np.float32(0.7575), np.float32(0.6925), np.float32(0.6395), np.float32(0.865), np.float32(0.7806), np.float32(0.8661), np.float32(0.8585), np.float32(0.973), np.float32(0.9713), np.float32(0.9681), np.float32(0.8237), np.float32(0.7493), np.float32(0.8641), np.float32(0.9523), np.float32(0.392), np.float32(0.2981)] +2025-11-12 13:27:39.044168: Epoch time: 258.69 s +2025-11-12 13:27:40.849622: +2025-11-12 13:27:40.852511: Epoch 486 +2025-11-12 13:27:40.854929: Current learning rate: 0.00549 +2025-11-12 13:31:59.770500: train_loss -0.6966 +2025-11-12 13:31:59.774611: val_loss -0.7118 +2025-11-12 13:31:59.776345: Pseudo dice [np.float32(0.9149), np.float32(0.7557), np.float32(0.7157), np.float32(0.6532), np.float32(0.8531), np.float32(0.7986), np.float32(0.875), np.float32(0.8562), np.float32(0.9717), np.float32(0.9702), np.float32(0.9653), np.float32(0.832), np.float32(0.7528), np.float32(0.8613), np.float32(0.9573), np.float32(0.463), np.float32(0.3673)] +2025-11-12 13:31:59.777808: Epoch time: 258.93 s +2025-11-12 13:32:01.584863: +2025-11-12 13:32:01.586707: Epoch 487 +2025-11-12 13:32:01.588309: Current learning rate: 0.00548 +2025-11-12 13:36:20.291325: train_loss -0.6933 +2025-11-12 13:36:20.295498: val_loss -0.7127 +2025-11-12 13:36:20.297344: Pseudo dice [np.float32(0.9116), np.float32(0.755), np.float32(0.7177), np.float32(0.6598), np.float32(0.8578), np.float32(0.8021), np.float32(0.894), np.float32(0.848), np.float32(0.9767), np.float32(0.974), np.float32(0.9659), np.float32(0.8241), np.float32(0.7861), np.float32(0.8719), np.float32(0.9559), np.float32(0.4111), np.float32(0.3862)] +2025-11-12 13:36:20.299625: Epoch time: 258.71 s +2025-11-12 13:36:22.183855: +2025-11-12 13:36:22.185574: Epoch 488 +2025-11-12 13:36:22.187360: Current learning rate: 0.00547 +2025-11-12 13:40:41.087433: train_loss -0.6989 +2025-11-12 13:40:41.097546: val_loss -0.7155 +2025-11-12 13:40:41.100239: Pseudo dice [np.float32(0.92), np.float32(0.7596), np.float32(0.6806), np.float32(0.6386), np.float32(0.8632), np.float32(0.7869), np.float32(0.887), np.float32(0.8625), np.float32(0.9658), np.float32(0.9644), np.float32(0.9679), np.float32(0.8143), np.float32(0.7578), np.float32(0.8776), np.float32(0.9548), np.float32(0.4441), np.float32(0.395)] +2025-11-12 13:40:41.102344: Epoch time: 258.91 s +2025-11-12 13:40:42.929285: +2025-11-12 13:40:42.930836: Epoch 489 +2025-11-12 13:40:42.932022: Current learning rate: 0.00546 +2025-11-12 13:45:01.935305: train_loss -0.7005 +2025-11-12 13:45:01.940646: val_loss -0.7061 +2025-11-12 13:45:01.942280: Pseudo dice [np.float32(0.919), np.float32(0.7933), np.float32(0.6875), np.float32(0.6216), np.float32(0.8528), np.float32(0.8068), np.float32(0.9032), np.float32(0.8425), np.float32(0.9811), np.float32(0.9789), np.float32(0.9679), np.float32(0.8388), np.float32(0.7363), np.float32(0.8708), np.float32(0.9591), np.float32(0.4384), np.float32(0.2884)] +2025-11-12 13:45:01.944638: Epoch time: 259.01 s +2025-11-12 13:45:03.863291: +2025-11-12 13:45:03.866329: Epoch 490 +2025-11-12 13:45:03.869314: Current learning rate: 0.00546 +2025-11-12 13:49:22.785880: train_loss -0.7094 +2025-11-12 13:49:22.793597: val_loss -0.7162 +2025-11-12 13:49:22.795998: Pseudo dice [np.float32(0.9176), np.float32(0.7789), np.float32(0.7244), np.float32(0.6442), np.float32(0.8581), np.float32(0.8005), np.float32(0.8937), np.float32(0.85), np.float32(0.9686), np.float32(0.9652), np.float32(0.9689), np.float32(0.8344), np.float32(0.7539), np.float32(0.8708), np.float32(0.9594), np.float32(0.3933), np.float32(0.4332)] +2025-11-12 13:49:22.798260: Epoch time: 258.93 s +2025-11-12 13:49:22.800446: Yayy! New best EMA pseudo Dice: 0.7949000000953674 +2025-11-12 13:49:27.778579: +2025-11-12 13:49:27.780412: Epoch 491 +2025-11-12 13:49:27.781966: Current learning rate: 0.00545 +2025-11-12 13:53:46.196937: train_loss -0.7029 +2025-11-12 13:53:46.201521: val_loss -0.7275 +2025-11-12 13:53:46.202688: Pseudo dice [np.float32(0.9156), np.float32(0.774), np.float32(0.7288), np.float32(0.6665), np.float32(0.8601), np.float32(0.8076), np.float32(0.8901), np.float32(0.8535), np.float32(0.9723), np.float32(0.9751), np.float32(0.9681), np.float32(0.8183), np.float32(0.7684), np.float32(0.8737), np.float32(0.9632), np.float32(0.4577), np.float32(0.5014)] +2025-11-12 13:53:46.204143: Epoch time: 258.42 s +2025-11-12 13:53:46.205416: Yayy! New best EMA pseudo Dice: 0.7965999841690063 +2025-11-12 13:53:51.274668: +2025-11-12 13:53:51.277233: Epoch 492 +2025-11-12 13:53:51.278948: Current learning rate: 0.00544 +2025-11-12 13:58:09.797657: train_loss -0.6978 +2025-11-12 13:58:09.811924: val_loss -0.7001 +2025-11-12 13:58:09.817093: Pseudo dice [np.float32(0.9025), np.float32(0.7456), np.float32(0.7092), np.float32(0.6364), np.float32(0.8595), np.float32(0.797), np.float32(0.8836), np.float32(0.8486), np.float32(0.9804), np.float32(0.9744), np.float32(0.9687), np.float32(0.8201), np.float32(0.7468), np.float32(0.8694), np.float32(0.9629), np.float32(0.344), np.float32(0.1895)] +2025-11-12 13:58:09.821088: Epoch time: 258.53 s +2025-11-12 13:58:11.612185: +2025-11-12 13:58:11.613997: Epoch 493 +2025-11-12 13:58:11.615720: Current learning rate: 0.00543 +2025-11-12 14:02:32.158774: train_loss -0.7008 +2025-11-12 14:02:32.167473: val_loss -0.7126 +2025-11-12 14:02:32.170528: Pseudo dice [np.float32(0.9106), np.float32(0.7494), np.float32(0.7135), np.float32(0.6489), np.float32(0.8544), np.float32(0.7917), np.float32(0.8956), np.float32(0.8516), np.float32(0.9583), np.float32(0.9627), np.float32(0.9681), np.float32(0.8267), np.float32(0.7567), np.float32(0.8701), np.float32(0.9555), np.float32(0.4542), np.float32(0.4409)] +2025-11-12 14:02:32.173042: Epoch time: 260.55 s +2025-11-12 14:02:34.001606: +2025-11-12 14:02:34.003113: Epoch 494 +2025-11-12 14:02:34.004370: Current learning rate: 0.00542 +2025-11-12 14:06:52.606427: train_loss -0.7021 +2025-11-12 14:06:52.610949: val_loss -0.7214 +2025-11-12 14:06:52.612676: Pseudo dice [np.float32(0.9139), np.float32(0.7522), np.float32(0.7122), np.float32(0.6624), np.float32(0.8576), np.float32(0.8093), np.float32(0.9008), np.float32(0.8647), np.float32(0.9718), np.float32(0.9728), np.float32(0.9692), np.float32(0.8174), np.float32(0.7513), np.float32(0.8677), np.float32(0.9564), np.float32(0.4968), np.float32(0.4112)] +2025-11-12 14:06:52.614021: Epoch time: 258.61 s +2025-11-12 14:06:54.442518: +2025-11-12 14:06:54.444420: Epoch 495 +2025-11-12 14:06:54.446843: Current learning rate: 0.00541 +2025-11-12 14:11:13.102688: train_loss -0.7095 +2025-11-12 14:11:13.113500: val_loss -0.7204 +2025-11-12 14:11:13.116978: Pseudo dice [np.float32(0.913), np.float32(0.7773), np.float32(0.7385), np.float32(0.6578), np.float32(0.8748), np.float32(0.8014), np.float32(0.889), np.float32(0.8505), np.float32(0.9786), np.float32(0.9764), np.float32(0.9681), np.float32(0.8372), np.float32(0.7838), np.float32(0.8707), np.float32(0.9624), np.float32(0.4436), np.float32(0.4155)] +2025-11-12 14:11:13.120876: Epoch time: 258.66 s +2025-11-12 14:11:13.124033: Yayy! New best EMA pseudo Dice: 0.7975000143051147 +2025-11-12 14:11:17.923686: +2025-11-12 14:11:17.927071: Epoch 496 +2025-11-12 14:11:17.930062: Current learning rate: 0.0054 +2025-11-12 14:15:36.570567: train_loss -0.7025 +2025-11-12 14:15:36.576098: val_loss -0.7179 +2025-11-12 14:15:36.578243: Pseudo dice [np.float32(0.9174), np.float32(0.7284), np.float32(0.7037), np.float32(0.6423), np.float32(0.8582), np.float32(0.8039), np.float32(0.9078), np.float32(0.8512), np.float32(0.9755), np.float32(0.9755), np.float32(0.9682), np.float32(0.8313), np.float32(0.7485), np.float32(0.8759), np.float32(0.9612), np.float32(0.4197), np.float32(0.3637)] +2025-11-12 14:15:36.579331: Epoch time: 258.65 s +2025-11-12 14:15:38.343672: +2025-11-12 14:15:38.346128: Epoch 497 +2025-11-12 14:15:38.347927: Current learning rate: 0.00539 +2025-11-12 14:19:56.974601: train_loss -0.7058 +2025-11-12 14:19:56.986507: val_loss -0.7176 +2025-11-12 14:19:56.989631: Pseudo dice [np.float32(0.9182), np.float32(0.7684), np.float32(0.718), np.float32(0.6353), np.float32(0.8663), np.float32(0.8083), np.float32(0.8879), np.float32(0.8569), np.float32(0.9631), np.float32(0.9626), np.float32(0.9675), np.float32(0.8372), np.float32(0.7633), np.float32(0.8755), np.float32(0.9512), np.float32(0.3934), np.float32(0.3388)] +2025-11-12 14:19:56.993406: Epoch time: 258.64 s +2025-11-12 14:19:58.783319: +2025-11-12 14:19:58.785823: Epoch 498 +2025-11-12 14:19:58.788443: Current learning rate: 0.00538 +2025-11-12 14:24:17.385524: train_loss -0.6951 +2025-11-12 14:24:17.390010: val_loss -0.7026 +2025-11-12 14:24:17.391243: Pseudo dice [np.float32(0.9209), np.float32(0.7581), np.float32(0.7054), np.float32(0.6241), np.float32(0.855), np.float32(0.7743), np.float32(0.8675), np.float32(0.8522), np.float32(0.9658), np.float32(0.9655), np.float32(0.9673), np.float32(0.8186), np.float32(0.7722), np.float32(0.8633), np.float32(0.9563), np.float32(0.4063), np.float32(0.2706)] +2025-11-12 14:24:17.392698: Epoch time: 258.61 s +2025-11-12 14:24:19.168846: +2025-11-12 14:24:19.170835: Epoch 499 +2025-11-12 14:24:19.172932: Current learning rate: 0.00537 +2025-11-12 14:28:37.825122: train_loss -0.6998 +2025-11-12 14:28:37.834575: val_loss -0.7106 +2025-11-12 14:28:37.837568: Pseudo dice [np.float32(0.9177), np.float32(0.7651), np.float32(0.7084), np.float32(0.6521), np.float32(0.8423), np.float32(0.7937), np.float32(0.8964), np.float32(0.861), np.float32(0.9731), np.float32(0.9709), np.float32(0.9692), np.float32(0.8263), np.float32(0.7731), np.float32(0.859), np.float32(0.9617), np.float32(0.3618), np.float32(0.3829)] +2025-11-12 14:28:37.840474: Epoch time: 258.66 s +2025-11-12 14:28:42.479538: +2025-11-12 14:28:42.481173: Epoch 500 +2025-11-12 14:28:42.483009: Current learning rate: 0.00536 +2025-11-12 14:33:00.928997: train_loss -0.7017 +2025-11-12 14:33:00.937264: val_loss -0.7127 +2025-11-12 14:33:00.940256: Pseudo dice [np.float32(0.9138), np.float32(0.753), np.float32(0.7299), np.float32(0.6567), np.float32(0.8557), np.float32(0.8077), np.float32(0.8886), np.float32(0.8599), np.float32(0.9424), np.float32(0.9467), np.float32(0.9647), np.float32(0.8336), np.float32(0.7744), np.float32(0.8649), np.float32(0.9284), np.float32(0.4395), np.float32(0.4366)] +2025-11-12 14:33:00.942996: Epoch time: 258.45 s +2025-11-12 14:33:02.701579: +2025-11-12 14:33:02.703343: Epoch 501 +2025-11-12 14:33:02.705090: Current learning rate: 0.00535 +2025-11-12 14:37:21.420927: train_loss -0.7022 +2025-11-12 14:37:21.429061: val_loss -0.7191 +2025-11-12 14:37:21.432117: Pseudo dice [np.float32(0.9093), np.float32(0.7768), np.float32(0.743), np.float32(0.6474), np.float32(0.8626), np.float32(0.8079), np.float32(0.8949), np.float32(0.8482), np.float32(0.9685), np.float32(0.9679), np.float32(0.9695), np.float32(0.8211), np.float32(0.761), np.float32(0.8727), np.float32(0.9605), np.float32(0.3579), np.float32(0.3365)] +2025-11-12 14:37:21.434766: Epoch time: 258.73 s +2025-11-12 14:37:23.299659: +2025-11-12 14:37:23.302030: Epoch 502 +2025-11-12 14:37:23.304044: Current learning rate: 0.00534 +2025-11-12 14:41:42.952629: train_loss -0.708 +2025-11-12 14:41:42.959115: val_loss -0.7099 +2025-11-12 14:41:42.960532: Pseudo dice [np.float32(0.9135), np.float32(0.7369), np.float32(0.7208), np.float32(0.6569), np.float32(0.8631), np.float32(0.8129), np.float32(0.8972), np.float32(0.8533), np.float32(0.9606), np.float32(0.9578), np.float32(0.9671), np.float32(0.8421), np.float32(0.7533), np.float32(0.8703), np.float32(0.9424), np.float32(0.3319), np.float32(0.3768)] +2025-11-12 14:41:42.961959: Epoch time: 259.66 s +2025-11-12 14:41:44.822028: +2025-11-12 14:41:44.823424: Epoch 503 +2025-11-12 14:41:44.824969: Current learning rate: 0.00533 +2025-11-12 14:46:03.681600: train_loss -0.7024 +2025-11-12 14:46:03.687474: val_loss -0.7021 +2025-11-12 14:46:03.689489: Pseudo dice [np.float32(0.9122), np.float32(0.7058), np.float32(0.7306), np.float32(0.6422), np.float32(0.8643), np.float32(0.7957), np.float32(0.8771), np.float32(0.8591), np.float32(0.9765), np.float32(0.9759), np.float32(0.9698), np.float32(0.841), np.float32(0.7164), np.float32(0.875), np.float32(0.9582), np.float32(0.3696), np.float32(0.3406)] +2025-11-12 14:46:03.691533: Epoch time: 258.87 s +2025-11-12 14:46:05.579306: +2025-11-12 14:46:05.580918: Epoch 504 +2025-11-12 14:46:05.582483: Current learning rate: 0.00532 +2025-11-12 14:50:24.121453: train_loss -0.7064 +2025-11-12 14:50:24.129679: val_loss -0.712 +2025-11-12 14:50:24.132241: Pseudo dice [np.float32(0.8998), np.float32(0.7803), np.float32(0.7118), np.float32(0.6271), np.float32(0.8576), np.float32(0.7982), np.float32(0.8984), np.float32(0.8634), np.float32(0.9785), np.float32(0.9794), np.float32(0.9689), np.float32(0.8272), np.float32(0.7364), np.float32(0.8742), np.float32(0.9594), np.float32(0.3308), np.float32(0.366)] +2025-11-12 14:50:24.134534: Epoch time: 258.55 s +2025-11-12 14:50:25.931864: +2025-11-12 14:50:25.933943: Epoch 505 +2025-11-12 14:50:25.935210: Current learning rate: 0.00531 +2025-11-12 14:54:44.520723: train_loss -0.7036 +2025-11-12 14:54:44.525165: val_loss -0.7168 +2025-11-12 14:54:44.527987: Pseudo dice [np.float32(0.9191), np.float32(0.7819), np.float32(0.7186), np.float32(0.6369), np.float32(0.8659), np.float32(0.8057), np.float32(0.906), np.float32(0.8511), np.float32(0.9757), np.float32(0.9735), np.float32(0.969), np.float32(0.8343), np.float32(0.781), np.float32(0.8703), np.float32(0.9664), np.float32(0.3758), np.float32(0.4104)] +2025-11-12 14:54:44.530399: Epoch time: 258.59 s +2025-11-12 14:54:46.415524: +2025-11-12 14:54:46.417792: Epoch 506 +2025-11-12 14:54:46.419615: Current learning rate: 0.0053 +2025-11-12 14:59:05.230162: train_loss -0.7022 +2025-11-12 14:59:05.238229: val_loss -0.7097 +2025-11-12 14:59:05.242003: Pseudo dice [np.float32(0.9111), np.float32(0.7839), np.float32(0.7067), np.float32(0.6633), np.float32(0.8509), np.float32(0.7788), np.float32(0.8863), np.float32(0.8601), np.float32(0.9686), np.float32(0.9704), np.float32(0.9687), np.float32(0.8173), np.float32(0.7357), np.float32(0.8667), np.float32(0.9608), np.float32(0.4342), np.float32(0.359)] +2025-11-12 14:59:05.245302: Epoch time: 258.82 s +2025-11-12 14:59:07.148900: +2025-11-12 14:59:07.150606: Epoch 507 +2025-11-12 14:59:07.152066: Current learning rate: 0.00529 +2025-11-12 15:03:25.837446: train_loss -0.7083 +2025-11-12 15:03:25.847458: val_loss -0.7033 +2025-11-12 15:03:25.849443: Pseudo dice [np.float32(0.9206), np.float32(0.7217), np.float32(0.6977), np.float32(0.6219), np.float32(0.8589), np.float32(0.798), np.float32(0.8936), np.float32(0.8593), np.float32(0.9587), np.float32(0.9621), np.float32(0.9676), np.float32(0.8348), np.float32(0.7734), np.float32(0.8735), np.float32(0.9495), np.float32(0.3378), np.float32(0.2656)] +2025-11-12 15:03:25.851039: Epoch time: 258.7 s +2025-11-12 15:03:27.668052: +2025-11-12 15:03:27.671211: Epoch 508 +2025-11-12 15:03:27.674273: Current learning rate: 0.00528 +2025-11-12 15:07:46.111621: train_loss -0.7066 +2025-11-12 15:07:46.116047: val_loss -0.7213 +2025-11-12 15:07:46.117683: Pseudo dice [np.float32(0.9127), np.float32(0.7755), np.float32(0.7024), np.float32(0.6488), np.float32(0.8567), np.float32(0.8106), np.float32(0.8974), np.float32(0.857), np.float32(0.9629), np.float32(0.9627), np.float32(0.9664), np.float32(0.8427), np.float32(0.7763), np.float32(0.8714), np.float32(0.9503), np.float32(0.4611), np.float32(0.3633)] +2025-11-12 15:07:46.119014: Epoch time: 258.45 s +2025-11-12 15:07:47.880541: +2025-11-12 15:07:47.882246: Epoch 509 +2025-11-12 15:07:47.884098: Current learning rate: 0.00527 +2025-11-12 15:12:06.307693: train_loss -0.7059 +2025-11-12 15:12:06.315063: val_loss -0.7045 +2025-11-12 15:12:06.316550: Pseudo dice [np.float32(0.9195), np.float32(0.7683), np.float32(0.7089), np.float32(0.6495), np.float32(0.8555), np.float32(0.7996), np.float32(0.8846), np.float32(0.8523), np.float32(0.9752), np.float32(0.9766), np.float32(0.9655), np.float32(0.824), np.float32(0.7575), np.float32(0.8558), np.float32(0.9532), np.float32(0.4312), np.float32(0.3269)] +2025-11-12 15:12:06.317895: Epoch time: 258.43 s +2025-11-12 15:12:08.194527: +2025-11-12 15:12:08.196040: Epoch 510 +2025-11-12 15:12:08.198026: Current learning rate: 0.00526 +2025-11-12 15:16:26.700472: train_loss -0.7029 +2025-11-12 15:16:26.706219: val_loss -0.6953 +2025-11-12 15:16:26.708558: Pseudo dice [np.float32(0.9096), np.float32(0.7405), np.float32(0.6806), np.float32(0.663), np.float32(0.8607), np.float32(0.7922), np.float32(0.9013), np.float32(0.8579), np.float32(0.9628), np.float32(0.9645), np.float32(0.9674), np.float32(0.8218), np.float32(0.7324), np.float32(0.8661), np.float32(0.96), np.float32(0.313), np.float32(0.3318)] +2025-11-12 15:16:26.711069: Epoch time: 258.51 s +2025-11-12 15:16:28.577192: +2025-11-12 15:16:28.578770: Epoch 511 +2025-11-12 15:16:28.580512: Current learning rate: 0.00525 +2025-11-12 15:20:48.704892: train_loss -0.697 +2025-11-12 15:20:48.710867: val_loss -0.6955 +2025-11-12 15:20:48.713046: Pseudo dice [np.float32(0.902), np.float32(0.7619), np.float32(0.7016), np.float32(0.6422), np.float32(0.8553), np.float32(0.7887), np.float32(0.8939), np.float32(0.8469), np.float32(0.955), np.float32(0.9543), np.float32(0.9636), np.float32(0.8143), np.float32(0.7543), np.float32(0.8665), np.float32(0.936), np.float32(0.4407), np.float32(0.3728)] +2025-11-12 15:20:48.715228: Epoch time: 260.13 s +2025-11-12 15:20:50.877422: +2025-11-12 15:20:50.879158: Epoch 512 +2025-11-12 15:20:50.880897: Current learning rate: 0.00524 +2025-11-12 15:25:09.374234: train_loss -0.7012 +2025-11-12 15:25:09.382646: val_loss -0.71 +2025-11-12 15:25:09.385611: Pseudo dice [np.float32(0.91), np.float32(0.7843), np.float32(0.7259), np.float32(0.6733), np.float32(0.8567), np.float32(0.7776), np.float32(0.8899), np.float32(0.8564), np.float32(0.9655), np.float32(0.9696), np.float32(0.9686), np.float32(0.8187), np.float32(0.759), np.float32(0.862), np.float32(0.9451), np.float32(0.4293), np.float32(0.2897)] +2025-11-12 15:25:09.389104: Epoch time: 258.5 s +2025-11-12 15:25:11.274159: +2025-11-12 15:25:11.276448: Epoch 513 +2025-11-12 15:25:11.278787: Current learning rate: 0.00523 +2025-11-12 15:29:29.819197: train_loss -0.7023 +2025-11-12 15:29:29.826190: val_loss -0.7188 +2025-11-12 15:29:29.828322: Pseudo dice [np.float32(0.9166), np.float32(0.7745), np.float32(0.7305), np.float32(0.6416), np.float32(0.8645), np.float32(0.7857), np.float32(0.8903), np.float32(0.8593), np.float32(0.9718), np.float32(0.9749), np.float32(0.9684), np.float32(0.8214), np.float32(0.7446), np.float32(0.8748), np.float32(0.96), np.float32(0.4364), np.float32(0.4329)] +2025-11-12 15:29:29.829770: Epoch time: 258.55 s +2025-11-12 15:29:31.668591: +2025-11-12 15:29:31.671520: Epoch 514 +2025-11-12 15:29:31.674495: Current learning rate: 0.00522 +2025-11-12 15:33:50.222109: train_loss -0.7105 +2025-11-12 15:33:50.229955: val_loss -0.7207 +2025-11-12 15:33:50.231606: Pseudo dice [np.float32(0.9058), np.float32(0.7642), np.float32(0.7393), np.float32(0.6633), np.float32(0.8678), np.float32(0.8054), np.float32(0.8985), np.float32(0.8613), np.float32(0.9743), np.float32(0.9795), np.float32(0.9696), np.float32(0.8413), np.float32(0.7173), np.float32(0.8698), np.float32(0.9645), np.float32(0.3929), np.float32(0.4405)] +2025-11-12 15:33:50.233836: Epoch time: 258.56 s +2025-11-12 15:33:52.058892: +2025-11-12 15:33:52.061360: Epoch 515 +2025-11-12 15:33:52.064044: Current learning rate: 0.00521 +2025-11-12 15:38:10.800866: train_loss -0.7063 +2025-11-12 15:38:10.808942: val_loss -0.7077 +2025-11-12 15:38:10.811695: Pseudo dice [np.float32(0.9131), np.float32(0.7651), np.float32(0.6902), np.float32(0.6317), np.float32(0.8664), np.float32(0.8123), np.float32(0.9107), np.float32(0.8592), np.float32(0.9717), np.float32(0.9682), np.float32(0.9686), np.float32(0.832), np.float32(0.7439), np.float32(0.8721), np.float32(0.9495), np.float32(0.3565), np.float32(0.299)] +2025-11-12 15:38:10.814483: Epoch time: 258.75 s +2025-11-12 15:38:12.634281: +2025-11-12 15:38:12.636418: Epoch 516 +2025-11-12 15:38:12.638541: Current learning rate: 0.0052 +2025-11-12 15:42:31.292481: train_loss -0.7053 +2025-11-12 15:42:31.301676: val_loss -0.7212 +2025-11-12 15:42:31.304532: Pseudo dice [np.float32(0.9091), np.float32(0.7525), np.float32(0.7323), np.float32(0.6484), np.float32(0.8518), np.float32(0.812), np.float32(0.92), np.float32(0.8508), np.float32(0.9753), np.float32(0.9776), np.float32(0.9692), np.float32(0.8362), np.float32(0.7664), np.float32(0.8743), np.float32(0.9606), np.float32(0.3891), np.float32(0.3669)] +2025-11-12 15:42:31.308190: Epoch time: 258.66 s +2025-11-12 15:42:33.186248: +2025-11-12 15:42:33.188010: Epoch 517 +2025-11-12 15:42:33.189675: Current learning rate: 0.00519 +2025-11-12 15:46:51.796192: train_loss -0.7069 +2025-11-12 15:46:51.804569: val_loss -0.7107 +2025-11-12 15:46:51.807134: Pseudo dice [np.float32(0.9091), np.float32(0.7901), np.float32(0.7024), np.float32(0.6638), np.float32(0.8637), np.float32(0.8123), np.float32(0.8884), np.float32(0.8637), np.float32(0.971), np.float32(0.9723), np.float32(0.9677), np.float32(0.8287), np.float32(0.7307), np.float32(0.8761), np.float32(0.96), np.float32(0.3658), np.float32(0.3284)] +2025-11-12 15:46:51.810532: Epoch time: 258.62 s +2025-11-12 15:46:53.602541: +2025-11-12 15:46:53.604287: Epoch 518 +2025-11-12 15:46:53.606272: Current learning rate: 0.00518 +2025-11-12 15:51:12.096256: train_loss -0.7105 +2025-11-12 15:51:12.104553: val_loss -0.719 +2025-11-12 15:51:12.107540: Pseudo dice [np.float32(0.897), np.float32(0.7756), np.float32(0.7026), np.float32(0.644), np.float32(0.873), np.float32(0.801), np.float32(0.8994), np.float32(0.8598), np.float32(0.9642), np.float32(0.9661), np.float32(0.9689), np.float32(0.8304), np.float32(0.776), np.float32(0.8761), np.float32(0.9584), np.float32(0.4527), np.float32(0.346)] +2025-11-12 15:51:12.110738: Epoch time: 258.5 s +2025-11-12 15:51:13.916211: +2025-11-12 15:51:13.917634: Epoch 519 +2025-11-12 15:51:13.919946: Current learning rate: 0.00518 +2025-11-12 15:55:32.109804: train_loss -0.7081 +2025-11-12 15:55:32.118140: val_loss -0.71 +2025-11-12 15:55:32.120163: Pseudo dice [np.float32(0.9076), np.float32(0.7705), np.float32(0.7257), np.float32(0.6443), np.float32(0.8607), np.float32(0.8019), np.float32(0.8757), np.float32(0.8549), np.float32(0.973), np.float32(0.9745), np.float32(0.9674), np.float32(0.8241), np.float32(0.7697), np.float32(0.8648), np.float32(0.9587), np.float32(0.3427), np.float32(0.2853)] +2025-11-12 15:55:32.122203: Epoch time: 258.2 s +2025-11-12 15:55:33.920864: +2025-11-12 15:55:33.923619: Epoch 520 +2025-11-12 15:55:33.926520: Current learning rate: 0.00517 +2025-11-12 15:59:52.413628: train_loss -0.7045 +2025-11-12 15:59:52.417834: val_loss -0.7156 +2025-11-12 15:59:52.419095: Pseudo dice [np.float32(0.9161), np.float32(0.7772), np.float32(0.7317), np.float32(0.6037), np.float32(0.8671), np.float32(0.7883), np.float32(0.8926), np.float32(0.8594), np.float32(0.9775), np.float32(0.9783), np.float32(0.9699), np.float32(0.8262), np.float32(0.7532), np.float32(0.8731), np.float32(0.9644), np.float32(0.4043), np.float32(0.4089)] +2025-11-12 15:59:52.420142: Epoch time: 258.5 s +2025-11-12 15:59:54.262835: +2025-11-12 15:59:54.265244: Epoch 521 +2025-11-12 15:59:54.266919: Current learning rate: 0.00516 +2025-11-12 16:04:13.656812: train_loss -0.6916 +2025-11-12 16:04:13.662434: val_loss -0.6749 +2025-11-12 16:04:13.664343: Pseudo dice [np.float32(0.9193), np.float32(0.7493), np.float32(0.685), np.float32(0.6245), np.float32(0.8509), np.float32(0.7694), np.float32(0.8971), np.float32(0.8305), np.float32(0.9154), np.float32(0.9128), np.float32(0.9566), np.float32(0.818), np.float32(0.7359), np.float32(0.8631), np.float32(0.8926), np.float32(0.3423), np.float32(0.3028)] +2025-11-12 16:04:13.665683: Epoch time: 259.4 s +2025-11-12 16:04:15.461603: +2025-11-12 16:04:15.462996: Epoch 522 +2025-11-12 16:04:15.464572: Current learning rate: 0.00515 +2025-11-12 16:08:33.958620: train_loss -0.6993 +2025-11-12 16:08:33.964327: val_loss -0.7057 +2025-11-12 16:08:33.966022: Pseudo dice [np.float32(0.9117), np.float32(0.7623), np.float32(0.6869), np.float32(0.6431), np.float32(0.8667), np.float32(0.7931), np.float32(0.9033), np.float32(0.8469), np.float32(0.9672), np.float32(0.9675), np.float32(0.9676), np.float32(0.8247), np.float32(0.7601), np.float32(0.8771), np.float32(0.9564), np.float32(0.3526), np.float32(0.3538)] +2025-11-12 16:08:33.967641: Epoch time: 258.5 s +2025-11-12 16:08:35.953089: +2025-11-12 16:08:35.956019: Epoch 523 +2025-11-12 16:08:35.958986: Current learning rate: 0.00514 +2025-11-12 16:12:54.297312: train_loss -0.7037 +2025-11-12 16:12:54.306283: val_loss -0.7107 +2025-11-12 16:12:54.309014: Pseudo dice [np.float32(0.8973), np.float32(0.7679), np.float32(0.688), np.float32(0.663), np.float32(0.8609), np.float32(0.7919), np.float32(0.9075), np.float32(0.8521), np.float32(0.9566), np.float32(0.9516), np.float32(0.9666), np.float32(0.8209), np.float32(0.7613), np.float32(0.8668), np.float32(0.9529), np.float32(0.426), np.float32(0.4142)] +2025-11-12 16:12:54.311932: Epoch time: 258.35 s +2025-11-12 16:12:56.114493: +2025-11-12 16:12:56.116041: Epoch 524 +2025-11-12 16:12:56.117390: Current learning rate: 0.00513 +2025-11-12 16:17:14.508024: train_loss -0.7082 +2025-11-12 16:17:14.514110: val_loss -0.7245 +2025-11-12 16:17:14.516100: Pseudo dice [np.float32(0.921), np.float32(0.7492), np.float32(0.7395), np.float32(0.6718), np.float32(0.8651), np.float32(0.7951), np.float32(0.8992), np.float32(0.8524), np.float32(0.9759), np.float32(0.9759), np.float32(0.9694), np.float32(0.8281), np.float32(0.714), np.float32(0.8726), np.float32(0.9649), np.float32(0.4271), np.float32(0.4232)] +2025-11-12 16:17:14.517825: Epoch time: 258.4 s +2025-11-12 16:17:16.373986: +2025-11-12 16:17:16.376635: Epoch 525 +2025-11-12 16:17:16.379097: Current learning rate: 0.00512 +2025-11-12 16:21:34.587250: train_loss -0.7045 +2025-11-12 16:21:34.594882: val_loss -0.7145 +2025-11-12 16:21:34.597145: Pseudo dice [np.float32(0.9152), np.float32(0.77), np.float32(0.7248), np.float32(0.6696), np.float32(0.8548), np.float32(0.8161), np.float32(0.9089), np.float32(0.8567), np.float32(0.9733), np.float32(0.9664), np.float32(0.9678), np.float32(0.8267), np.float32(0.7765), np.float32(0.865), np.float32(0.9633), np.float32(0.4453), np.float32(0.3907)] +2025-11-12 16:21:34.599480: Epoch time: 258.22 s +2025-11-12 16:21:36.454677: +2025-11-12 16:21:36.456675: Epoch 526 +2025-11-12 16:21:36.459061: Current learning rate: 0.00511 +2025-11-12 16:25:54.760337: train_loss -0.7025 +2025-11-12 16:25:54.767814: val_loss -0.7232 +2025-11-12 16:25:54.770497: Pseudo dice [np.float32(0.911), np.float32(0.7865), np.float32(0.7147), np.float32(0.6654), np.float32(0.8582), np.float32(0.7965), np.float32(0.9088), np.float32(0.8594), np.float32(0.9729), np.float32(0.9755), np.float32(0.9701), np.float32(0.8186), np.float32(0.7583), np.float32(0.8718), np.float32(0.9583), np.float32(0.4556), np.float32(0.429)] +2025-11-12 16:25:54.772853: Epoch time: 258.31 s +2025-11-12 16:25:56.582397: +2025-11-12 16:25:56.585149: Epoch 527 +2025-11-12 16:25:56.587498: Current learning rate: 0.0051 +2025-11-12 16:30:14.899609: train_loss -0.6994 +2025-11-12 16:30:14.904614: val_loss -0.7212 +2025-11-12 16:30:14.906051: Pseudo dice [np.float32(0.9149), np.float32(0.7811), np.float32(0.7268), np.float32(0.6346), np.float32(0.864), np.float32(0.7886), np.float32(0.8765), np.float32(0.858), np.float32(0.98), np.float32(0.9783), np.float32(0.9693), np.float32(0.8238), np.float32(0.7521), np.float32(0.8679), np.float32(0.9613), np.float32(0.4495), np.float32(0.4124)] +2025-11-12 16:30:14.907479: Epoch time: 258.32 s +2025-11-12 16:30:16.728685: +2025-11-12 16:30:16.732216: Epoch 528 +2025-11-12 16:30:16.735612: Current learning rate: 0.00509 +2025-11-12 16:34:35.220560: train_loss -0.7055 +2025-11-12 16:34:35.231484: val_loss -0.7137 +2025-11-12 16:34:35.233752: Pseudo dice [np.float32(0.9248), np.float32(0.748), np.float32(0.7166), np.float32(0.6448), np.float32(0.8598), np.float32(0.7936), np.float32(0.8729), np.float32(0.8556), np.float32(0.9771), np.float32(0.9699), np.float32(0.9685), np.float32(0.829), np.float32(0.7113), np.float32(0.8733), np.float32(0.9631), np.float32(0.4037), np.float32(0.3137)] +2025-11-12 16:34:35.236279: Epoch time: 258.5 s +2025-11-12 16:34:37.056218: +2025-11-12 16:34:37.059108: Epoch 529 +2025-11-12 16:34:37.061807: Current learning rate: 0.00508 +2025-11-12 16:38:55.419896: train_loss -0.6936 +2025-11-12 16:38:55.425866: val_loss -0.6974 +2025-11-12 16:38:55.428540: Pseudo dice [np.float32(0.913), np.float32(0.7594), np.float32(0.7017), np.float32(0.6296), np.float32(0.855), np.float32(0.7921), np.float32(0.8873), np.float32(0.8508), np.float32(0.9724), np.float32(0.9741), np.float32(0.966), np.float32(0.8325), np.float32(0.7524), np.float32(0.8682), np.float32(0.9495), np.float32(0.2813), np.float32(0.299)] +2025-11-12 16:38:55.431283: Epoch time: 258.37 s +2025-11-12 16:38:57.262522: +2025-11-12 16:38:57.264151: Epoch 530 +2025-11-12 16:38:57.266144: Current learning rate: 0.00507 +2025-11-12 16:43:16.746051: train_loss -0.6969 +2025-11-12 16:43:16.751398: val_loss -0.7138 +2025-11-12 16:43:16.753383: Pseudo dice [np.float32(0.9087), np.float32(0.7482), np.float32(0.7077), np.float32(0.679), np.float32(0.8514), np.float32(0.8001), np.float32(0.8958), np.float32(0.8574), np.float32(0.9731), np.float32(0.9717), np.float32(0.9678), np.float32(0.8361), np.float32(0.7261), np.float32(0.8661), np.float32(0.9602), np.float32(0.3923), np.float32(0.354)] +2025-11-12 16:43:16.755087: Epoch time: 259.49 s +2025-11-12 16:43:18.838193: +2025-11-12 16:43:18.840136: Epoch 531 +2025-11-12 16:43:18.842505: Current learning rate: 0.00506 +2025-11-12 16:47:37.392378: train_loss -0.6969 +2025-11-12 16:47:37.399904: val_loss -0.7045 +2025-11-12 16:47:37.402990: Pseudo dice [np.float32(0.9102), np.float32(0.771), np.float32(0.705), np.float32(0.6478), np.float32(0.8571), np.float32(0.8027), np.float32(0.9047), np.float32(0.8496), np.float32(0.9542), np.float32(0.9541), np.float32(0.9661), np.float32(0.8196), np.float32(0.7385), np.float32(0.8698), np.float32(0.944), np.float32(0.4197), np.float32(0.3819)] +2025-11-12 16:47:37.405632: Epoch time: 258.56 s +2025-11-12 16:47:39.308043: +2025-11-12 16:47:39.310193: Epoch 532 +2025-11-12 16:47:39.311950: Current learning rate: 0.00505 +2025-11-12 16:51:57.734148: train_loss -0.7051 +2025-11-12 16:51:57.739269: val_loss -0.7106 +2025-11-12 16:51:57.740914: Pseudo dice [np.float32(0.9157), np.float32(0.7689), np.float32(0.7152), np.float32(0.6285), np.float32(0.8583), np.float32(0.8021), np.float32(0.904), np.float32(0.847), np.float32(0.9568), np.float32(0.9578), np.float32(0.9661), np.float32(0.825), np.float32(0.7521), np.float32(0.868), np.float32(0.9439), np.float32(0.4516), np.float32(0.3603)] +2025-11-12 16:51:57.742546: Epoch time: 258.43 s +2025-11-12 16:51:59.545832: +2025-11-12 16:51:59.548037: Epoch 533 +2025-11-12 16:51:59.550578: Current learning rate: 0.00504 +2025-11-12 16:56:18.120501: train_loss -0.7068 +2025-11-12 16:56:18.125852: val_loss -0.7095 +2025-11-12 16:56:18.128087: Pseudo dice [np.float32(0.9063), np.float32(0.7559), np.float32(0.6872), np.float32(0.6368), np.float32(0.8607), np.float32(0.8025), np.float32(0.8748), np.float32(0.856), np.float32(0.9775), np.float32(0.9748), np.float32(0.9683), np.float32(0.8247), np.float32(0.7656), np.float32(0.8677), np.float32(0.9609), np.float32(0.3609), np.float32(0.3325)] +2025-11-12 16:56:18.129738: Epoch time: 258.58 s +2025-11-12 16:56:19.998924: +2025-11-12 16:56:20.001271: Epoch 534 +2025-11-12 16:56:20.003119: Current learning rate: 0.00503 +2025-11-12 17:00:38.354916: train_loss -0.7017 +2025-11-12 17:00:38.362188: val_loss -0.7165 +2025-11-12 17:00:38.364424: Pseudo dice [np.float32(0.9021), np.float32(0.7664), np.float32(0.7287), np.float32(0.6389), np.float32(0.8614), np.float32(0.7951), np.float32(0.8975), np.float32(0.848), np.float32(0.9744), np.float32(0.9754), np.float32(0.9677), np.float32(0.8242), np.float32(0.7606), np.float32(0.8728), np.float32(0.9628), np.float32(0.3364), np.float32(0.3331)] +2025-11-12 17:00:38.366376: Epoch time: 258.36 s +2025-11-12 17:00:40.182714: +2025-11-12 17:00:40.184129: Epoch 535 +2025-11-12 17:00:40.185330: Current learning rate: 0.00502 +2025-11-12 17:04:58.645107: train_loss -0.704 +2025-11-12 17:04:58.653944: val_loss -0.7113 +2025-11-12 17:04:58.656280: Pseudo dice [np.float32(0.8983), np.float32(0.7371), np.float32(0.7282), np.float32(0.6466), np.float32(0.8633), np.float32(0.8247), np.float32(0.9077), np.float32(0.8495), np.float32(0.9721), np.float32(0.9681), np.float32(0.9689), np.float32(0.8245), np.float32(0.7616), np.float32(0.8722), np.float32(0.9568), np.float32(0.3117), np.float32(0.2524)] +2025-11-12 17:04:58.658199: Epoch time: 258.47 s +2025-11-12 17:05:00.412003: +2025-11-12 17:05:00.414501: Epoch 536 +2025-11-12 17:05:00.416219: Current learning rate: 0.00501 +2025-11-12 17:09:18.655904: train_loss -0.7057 +2025-11-12 17:09:18.662900: val_loss -0.7172 +2025-11-12 17:09:18.664625: Pseudo dice [np.float32(0.9086), np.float32(0.7396), np.float32(0.7299), np.float32(0.6555), np.float32(0.8611), np.float32(0.8049), np.float32(0.9011), np.float32(0.8519), np.float32(0.9745), np.float32(0.9677), np.float32(0.9684), np.float32(0.8318), np.float32(0.7717), np.float32(0.8754), np.float32(0.9544), np.float32(0.4031), np.float32(0.302)] +2025-11-12 17:09:18.666099: Epoch time: 258.25 s +2025-11-12 17:09:20.567826: +2025-11-12 17:09:20.570502: Epoch 537 +2025-11-12 17:09:20.572538: Current learning rate: 0.005 +2025-11-12 17:13:38.899978: train_loss -0.7044 +2025-11-12 17:13:38.909101: val_loss -0.7144 +2025-11-12 17:13:38.912477: Pseudo dice [np.float32(0.9033), np.float32(0.7941), np.float32(0.7343), np.float32(0.6488), np.float32(0.8597), np.float32(0.8106), np.float32(0.9047), np.float32(0.8483), np.float32(0.9662), np.float32(0.9629), np.float32(0.9688), np.float32(0.8326), np.float32(0.7625), np.float32(0.8663), np.float32(0.9562), np.float32(0.3796), np.float32(0.3435)] +2025-11-12 17:13:38.915732: Epoch time: 258.34 s +2025-11-12 17:13:40.764535: +2025-11-12 17:13:40.766112: Epoch 538 +2025-11-12 17:13:40.767771: Current learning rate: 0.00499 +2025-11-12 17:17:59.233400: train_loss -0.7058 +2025-11-12 17:17:59.240611: val_loss -0.6966 +2025-11-12 17:17:59.244158: Pseudo dice [np.float32(0.9082), np.float32(0.7641), np.float32(0.7155), np.float32(0.6475), np.float32(0.8577), np.float32(0.8023), np.float32(0.8931), np.float32(0.8596), np.float32(0.9615), np.float32(0.9652), np.float32(0.9682), np.float32(0.8276), np.float32(0.7401), np.float32(0.8658), np.float32(0.9597), np.float32(0.3334), np.float32(0.2321)] +2025-11-12 17:17:59.246684: Epoch time: 258.47 s +2025-11-12 17:18:01.072753: +2025-11-12 17:18:01.075840: Epoch 539 +2025-11-12 17:18:01.078712: Current learning rate: 0.00498 +2025-11-12 17:22:19.378728: train_loss -0.7137 +2025-11-12 17:22:19.387787: val_loss -0.7042 +2025-11-12 17:22:19.390778: Pseudo dice [np.float32(0.9103), np.float32(0.7674), np.float32(0.7009), np.float32(0.6617), np.float32(0.8616), np.float32(0.8028), np.float32(0.8962), np.float32(0.8516), np.float32(0.9708), np.float32(0.9669), np.float32(0.9668), np.float32(0.8353), np.float32(0.7424), np.float32(0.874), np.float32(0.9598), np.float32(0.4166), np.float32(0.4043)] +2025-11-12 17:22:19.394058: Epoch time: 258.31 s +2025-11-12 17:22:22.631518: +2025-11-12 17:22:22.633183: Epoch 540 +2025-11-12 17:22:22.634899: Current learning rate: 0.00497 +2025-11-12 17:26:40.996229: train_loss -0.7093 +2025-11-12 17:26:41.005252: val_loss -0.7148 +2025-11-12 17:26:41.008173: Pseudo dice [np.float32(0.9129), np.float32(0.7764), np.float32(0.7229), np.float32(0.6588), np.float32(0.8658), np.float32(0.7963), np.float32(0.902), np.float32(0.8419), np.float32(0.9796), np.float32(0.9754), np.float32(0.968), np.float32(0.8229), np.float32(0.742), np.float32(0.881), np.float32(0.9585), np.float32(0.4247), np.float32(0.3167)] +2025-11-12 17:26:41.010739: Epoch time: 258.37 s +2025-11-12 17:26:43.005175: +2025-11-12 17:26:43.006580: Epoch 541 +2025-11-12 17:26:43.008525: Current learning rate: 0.00496 +2025-11-12 17:31:01.460340: train_loss -0.7113 +2025-11-12 17:31:01.466543: val_loss -0.7035 +2025-11-12 17:31:01.468767: Pseudo dice [np.float32(0.9118), np.float32(0.7804), np.float32(0.7156), np.float32(0.6633), np.float32(0.8574), np.float32(0.7986), np.float32(0.9094), np.float32(0.8595), np.float32(0.9669), np.float32(0.9619), np.float32(0.9664), np.float32(0.8222), np.float32(0.7073), np.float32(0.8684), np.float32(0.942), np.float32(0.3521), np.float32(0.3216)] +2025-11-12 17:31:01.470605: Epoch time: 258.46 s +2025-11-12 17:31:03.283975: +2025-11-12 17:31:03.286992: Epoch 542 +2025-11-12 17:31:03.288359: Current learning rate: 0.00495 +2025-11-12 17:35:21.672799: train_loss -0.6995 +2025-11-12 17:35:21.680350: val_loss -0.712 +2025-11-12 17:35:21.682609: Pseudo dice [np.float32(0.8971), np.float32(0.7768), np.float32(0.7017), np.float32(0.6481), np.float32(0.8587), np.float32(0.8007), np.float32(0.8808), np.float32(0.8549), np.float32(0.971), np.float32(0.9725), np.float32(0.9666), np.float32(0.8183), np.float32(0.7488), np.float32(0.8684), np.float32(0.9554), np.float32(0.3944), np.float32(0.3844)] +2025-11-12 17:35:21.684590: Epoch time: 258.39 s +2025-11-12 17:35:23.532574: +2025-11-12 17:35:23.535346: Epoch 543 +2025-11-12 17:35:23.537719: Current learning rate: 0.00494 +2025-11-12 17:39:42.166123: train_loss -0.7 +2025-11-12 17:39:42.174402: val_loss -0.7146 +2025-11-12 17:39:42.177581: Pseudo dice [np.float32(0.9196), np.float32(0.7712), np.float32(0.7), np.float32(0.6624), np.float32(0.8641), np.float32(0.7964), np.float32(0.8761), np.float32(0.8548), np.float32(0.975), np.float32(0.9669), np.float32(0.9671), np.float32(0.8346), np.float32(0.7734), np.float32(0.8714), np.float32(0.9599), np.float32(0.3901), np.float32(0.3583)] +2025-11-12 17:39:42.179645: Epoch time: 258.64 s +2025-11-12 17:39:44.093929: +2025-11-12 17:39:44.096235: Epoch 544 +2025-11-12 17:39:44.098124: Current learning rate: 0.00493 +2025-11-12 17:44:02.490025: train_loss -0.7078 +2025-11-12 17:44:02.503373: val_loss -0.7208 +2025-11-12 17:44:02.507204: Pseudo dice [np.float32(0.9082), np.float32(0.7817), np.float32(0.7153), np.float32(0.6632), np.float32(0.8689), np.float32(0.7933), np.float32(0.9022), np.float32(0.8555), np.float32(0.9744), np.float32(0.9746), np.float32(0.9697), np.float32(0.824), np.float32(0.7511), np.float32(0.8734), np.float32(0.9618), np.float32(0.4341), np.float32(0.4051)] +2025-11-12 17:44:02.510193: Epoch time: 258.4 s +2025-11-12 17:44:04.351272: +2025-11-12 17:44:04.356013: Epoch 545 +2025-11-12 17:44:04.359177: Current learning rate: 0.00492 +2025-11-12 17:48:22.920339: train_loss -0.6993 +2025-11-12 17:48:22.927639: val_loss -0.7083 +2025-11-12 17:48:22.930031: Pseudo dice [np.float32(0.9155), np.float32(0.7774), np.float32(0.7182), np.float32(0.6486), np.float32(0.8609), np.float32(0.8099), np.float32(0.9125), np.float32(0.8527), np.float32(0.977), np.float32(0.9719), np.float32(0.9677), np.float32(0.8364), np.float32(0.7623), np.float32(0.8725), np.float32(0.9548), np.float32(0.4117), np.float32(0.3274)] +2025-11-12 17:48:22.933144: Epoch time: 258.58 s +2025-11-12 17:48:24.799452: +2025-11-12 17:48:24.802362: Epoch 546 +2025-11-12 17:48:24.805027: Current learning rate: 0.00491 +2025-11-12 17:52:43.097758: train_loss -0.7038 +2025-11-12 17:52:43.104330: val_loss -0.7221 +2025-11-12 17:52:43.106157: Pseudo dice [np.float32(0.9152), np.float32(0.7742), np.float32(0.7196), np.float32(0.6349), np.float32(0.8644), np.float32(0.7986), np.float32(0.8872), np.float32(0.8496), np.float32(0.9794), np.float32(0.9758), np.float32(0.9711), np.float32(0.8283), np.float32(0.7575), np.float32(0.8721), np.float32(0.9632), np.float32(0.4353), np.float32(0.3812)] +2025-11-12 17:52:43.109016: Epoch time: 258.3 s +2025-11-12 17:52:44.918190: +2025-11-12 17:52:44.919497: Epoch 547 +2025-11-12 17:52:44.920801: Current learning rate: 0.0049 +2025-11-12 17:57:03.299823: train_loss -0.6965 +2025-11-12 17:57:03.304601: val_loss -0.7033 +2025-11-12 17:57:03.306243: Pseudo dice [np.float32(0.897), np.float32(0.7515), np.float32(0.734), np.float32(0.6416), np.float32(0.8457), np.float32(0.7734), np.float32(0.8891), np.float32(0.8491), np.float32(0.9723), np.float32(0.9683), np.float32(0.9652), np.float32(0.8232), np.float32(0.7547), np.float32(0.8576), np.float32(0.9545), np.float32(0.4232), np.float32(0.3474)] +2025-11-12 17:57:03.307759: Epoch time: 258.39 s +2025-11-12 17:57:05.085593: +2025-11-12 17:57:05.087553: Epoch 548 +2025-11-12 17:57:05.088850: Current learning rate: 0.00489 +2025-11-12 18:01:23.467291: train_loss -0.6919 +2025-11-12 18:01:23.475278: val_loss -0.7063 +2025-11-12 18:01:23.476796: Pseudo dice [np.float32(0.9115), np.float32(0.7673), np.float32(0.7102), np.float32(0.6172), np.float32(0.8593), np.float32(0.7958), np.float32(0.8867), np.float32(0.8652), np.float32(0.9735), np.float32(0.9703), np.float32(0.9681), np.float32(0.8271), np.float32(0.7428), np.float32(0.8604), np.float32(0.9596), np.float32(0.3545), np.float32(0.294)] +2025-11-12 18:01:23.478788: Epoch time: 258.39 s +2025-11-12 18:01:25.306278: +2025-11-12 18:01:25.308132: Epoch 549 +2025-11-12 18:01:25.309784: Current learning rate: 0.00488 +2025-11-12 18:05:45.133226: train_loss -0.6982 +2025-11-12 18:05:45.140084: val_loss -0.7115 +2025-11-12 18:05:45.142220: Pseudo dice [np.float32(0.9193), np.float32(0.7805), np.float32(0.7221), np.float32(0.6551), np.float32(0.862), np.float32(0.7889), np.float32(0.9065), np.float32(0.8465), np.float32(0.9659), np.float32(0.9598), np.float32(0.9675), np.float32(0.8191), np.float32(0.7564), np.float32(0.8691), np.float32(0.9549), np.float32(0.298), np.float32(0.3366)] +2025-11-12 18:05:45.143856: Epoch time: 259.83 s +2025-11-12 18:05:52.442072: +2025-11-12 18:05:52.446184: Epoch 550 +2025-11-12 18:05:52.449314: Current learning rate: 0.00487 +2025-11-12 18:10:10.658247: train_loss -0.7081 +2025-11-12 18:10:10.663026: val_loss -0.7103 +2025-11-12 18:10:10.664732: Pseudo dice [np.float32(0.9029), np.float32(0.766), np.float32(0.6827), np.float32(0.6774), np.float32(0.857), np.float32(0.7953), np.float32(0.879), np.float32(0.8609), np.float32(0.9754), np.float32(0.9768), np.float32(0.9685), np.float32(0.824), np.float32(0.7662), np.float32(0.8668), np.float32(0.9567), np.float32(0.326), np.float32(0.3451)] +2025-11-12 18:10:10.666131: Epoch time: 258.22 s +2025-11-12 18:10:12.477019: +2025-11-12 18:10:12.480221: Epoch 551 +2025-11-12 18:10:12.482930: Current learning rate: 0.00486 +2025-11-12 18:14:31.168037: train_loss -0.7089 +2025-11-12 18:14:31.172707: val_loss -0.7197 +2025-11-12 18:14:31.174703: Pseudo dice [np.float32(0.9077), np.float32(0.7635), np.float32(0.709), np.float32(0.6537), np.float32(0.8668), np.float32(0.796), np.float32(0.8879), np.float32(0.8565), np.float32(0.9804), np.float32(0.9791), np.float32(0.9707), np.float32(0.8285), np.float32(0.7706), np.float32(0.8738), np.float32(0.9656), np.float32(0.4513), np.float32(0.3967)] +2025-11-12 18:14:31.176694: Epoch time: 258.7 s +2025-11-12 18:14:33.033216: +2025-11-12 18:14:33.034846: Epoch 552 +2025-11-12 18:14:33.036571: Current learning rate: 0.00485 +2025-11-12 18:18:51.659584: train_loss -0.7096 +2025-11-12 18:18:51.663615: val_loss -0.7148 +2025-11-12 18:18:51.665081: Pseudo dice [np.float32(0.9182), np.float32(0.7591), np.float32(0.6915), np.float32(0.6326), np.float32(0.8656), np.float32(0.7909), np.float32(0.8795), np.float32(0.8487), np.float32(0.9695), np.float32(0.9655), np.float32(0.9677), np.float32(0.8341), np.float32(0.7547), np.float32(0.8772), np.float32(0.958), np.float32(0.4301), np.float32(0.3582)] +2025-11-12 18:18:51.666411: Epoch time: 258.63 s +2025-11-12 18:18:53.437627: +2025-11-12 18:18:53.440278: Epoch 553 +2025-11-12 18:18:53.441976: Current learning rate: 0.00484 +2025-11-12 18:23:11.959879: train_loss -0.7074 +2025-11-12 18:23:11.964841: val_loss -0.7163 +2025-11-12 18:23:11.966638: Pseudo dice [np.float32(0.9124), np.float32(0.7736), np.float32(0.7181), np.float32(0.6469), np.float32(0.8621), np.float32(0.8022), np.float32(0.8972), np.float32(0.8657), np.float32(0.9793), np.float32(0.9757), np.float32(0.9699), np.float32(0.8362), np.float32(0.7741), np.float32(0.8649), np.float32(0.9653), np.float32(0.4042), np.float32(0.3684)] +2025-11-12 18:23:11.968563: Epoch time: 258.53 s +2025-11-12 18:23:13.845411: +2025-11-12 18:23:13.847275: Epoch 554 +2025-11-12 18:23:13.849905: Current learning rate: 0.00484 +2025-11-12 18:27:32.553334: train_loss -0.7077 +2025-11-12 18:27:32.558662: val_loss -0.7118 +2025-11-12 18:27:32.560810: Pseudo dice [np.float32(0.9044), np.float32(0.7412), np.float32(0.6975), np.float32(0.654), np.float32(0.862), np.float32(0.78), np.float32(0.8753), np.float32(0.8628), np.float32(0.9758), np.float32(0.9775), np.float32(0.9704), np.float32(0.8192), np.float32(0.7726), np.float32(0.8644), np.float32(0.9621), np.float32(0.3454), np.float32(0.4022)] +2025-11-12 18:27:32.562664: Epoch time: 258.71 s +2025-11-12 18:27:34.379363: +2025-11-12 18:27:34.381196: Epoch 555 +2025-11-12 18:27:34.383993: Current learning rate: 0.00483 +2025-11-12 18:31:52.936831: train_loss -0.7018 +2025-11-12 18:31:52.944107: val_loss -0.7027 +2025-11-12 18:31:52.946521: Pseudo dice [np.float32(0.9011), np.float32(0.7764), np.float32(0.7195), np.float32(0.6695), np.float32(0.8574), np.float32(0.7806), np.float32(0.8884), np.float32(0.8538), np.float32(0.9776), np.float32(0.9773), np.float32(0.9676), np.float32(0.8356), np.float32(0.7459), np.float32(0.8721), np.float32(0.9631), np.float32(0.3028), np.float32(0.2732)] +2025-11-12 18:31:52.947885: Epoch time: 258.56 s +2025-11-12 18:31:54.798212: +2025-11-12 18:31:54.801710: Epoch 556 +2025-11-12 18:31:54.804868: Current learning rate: 0.00482 +2025-11-12 18:36:13.350991: train_loss -0.7079 +2025-11-12 18:36:13.357738: val_loss -0.7007 +2025-11-12 18:36:13.360025: Pseudo dice [np.float32(0.9022), np.float32(0.7625), np.float32(0.7079), np.float32(0.6339), np.float32(0.8594), np.float32(0.7847), np.float32(0.897), np.float32(0.8629), np.float32(0.9556), np.float32(0.9555), np.float32(0.9655), np.float32(0.8215), np.float32(0.771), np.float32(0.8694), np.float32(0.9406), np.float32(0.4241), np.float32(0.3236)] +2025-11-12 18:36:13.362480: Epoch time: 258.56 s +2025-11-12 18:36:15.168617: +2025-11-12 18:36:15.171357: Epoch 557 +2025-11-12 18:36:15.173642: Current learning rate: 0.00481 +2025-11-12 18:40:33.951897: train_loss -0.7049 +2025-11-12 18:40:33.960021: val_loss -0.7146 +2025-11-12 18:40:33.963106: Pseudo dice [np.float32(0.9144), np.float32(0.7928), np.float32(0.7359), np.float32(0.6492), np.float32(0.8609), np.float32(0.7933), np.float32(0.8956), np.float32(0.8639), np.float32(0.9802), np.float32(0.9793), np.float32(0.9665), np.float32(0.8282), np.float32(0.7696), np.float32(0.8699), np.float32(0.9523), np.float32(0.4091), np.float32(0.3817)] +2025-11-12 18:40:33.966061: Epoch time: 258.79 s +2025-11-12 18:40:35.734782: +2025-11-12 18:40:35.737282: Epoch 558 +2025-11-12 18:40:35.739547: Current learning rate: 0.0048 +2025-11-12 18:44:55.572406: train_loss -0.7033 +2025-11-12 18:44:55.576674: val_loss -0.7094 +2025-11-12 18:44:55.578150: Pseudo dice [np.float32(0.9051), np.float32(0.7823), np.float32(0.7202), np.float32(0.6416), np.float32(0.8654), np.float32(0.8077), np.float32(0.8763), np.float32(0.8503), np.float32(0.963), np.float32(0.9554), np.float32(0.9677), np.float32(0.8325), np.float32(0.7346), np.float32(0.8684), np.float32(0.9559), np.float32(0.474), np.float32(0.3355)] +2025-11-12 18:44:55.579798: Epoch time: 259.84 s +2025-11-12 18:44:57.437526: +2025-11-12 18:44:57.440009: Epoch 559 +2025-11-12 18:44:57.442243: Current learning rate: 0.00479 +2025-11-12 18:49:16.148502: train_loss -0.7026 +2025-11-12 18:49:16.153116: val_loss -0.703 +2025-11-12 18:49:16.154606: Pseudo dice [np.float32(0.912), np.float32(0.7602), np.float32(0.7246), np.float32(0.6276), np.float32(0.8584), np.float32(0.7883), np.float32(0.8836), np.float32(0.83), np.float32(0.9708), np.float32(0.9705), np.float32(0.9667), np.float32(0.8326), np.float32(0.7702), np.float32(0.8644), np.float32(0.9487), np.float32(0.3759), np.float32(0.3041)] +2025-11-12 18:49:16.155688: Epoch time: 258.72 s +2025-11-12 18:49:17.988203: +2025-11-12 18:49:17.989855: Epoch 560 +2025-11-12 18:49:17.991388: Current learning rate: 0.00478 +2025-11-12 18:53:36.385865: train_loss -0.7066 +2025-11-12 18:53:36.394716: val_loss -0.7168 +2025-11-12 18:53:36.397621: Pseudo dice [np.float32(0.9177), np.float32(0.7703), np.float32(0.6742), np.float32(0.6373), np.float32(0.8596), np.float32(0.8082), np.float32(0.9059), np.float32(0.8577), np.float32(0.9741), np.float32(0.9715), np.float32(0.969), np.float32(0.8288), np.float32(0.7511), np.float32(0.8695), np.float32(0.9638), np.float32(0.3849), np.float32(0.366)] +2025-11-12 18:53:36.400493: Epoch time: 258.4 s +2025-11-12 18:53:38.282538: +2025-11-12 18:53:38.284530: Epoch 561 +2025-11-12 18:53:38.286230: Current learning rate: 0.00477 +2025-11-12 18:57:56.805355: train_loss -0.712 +2025-11-12 18:57:56.811056: val_loss -0.7131 +2025-11-12 18:57:56.813879: Pseudo dice [np.float32(0.9093), np.float32(0.7789), np.float32(0.7228), np.float32(0.6387), np.float32(0.8609), np.float32(0.8128), np.float32(0.8761), np.float32(0.8517), np.float32(0.9796), np.float32(0.9759), np.float32(0.9694), np.float32(0.8246), np.float32(0.7542), np.float32(0.8692), np.float32(0.9625), np.float32(0.4237), np.float32(0.3194)] +2025-11-12 18:57:56.816336: Epoch time: 258.53 s +2025-11-12 18:57:58.635138: +2025-11-12 18:57:58.636842: Epoch 562 +2025-11-12 18:57:58.638340: Current learning rate: 0.00476 +2025-11-12 19:02:17.109328: train_loss -0.7092 +2025-11-12 19:02:17.118194: val_loss -0.7171 +2025-11-12 19:02:17.119931: Pseudo dice [np.float32(0.9174), np.float32(0.757), np.float32(0.7258), np.float32(0.6702), np.float32(0.865), np.float32(0.7847), np.float32(0.9039), np.float32(0.8527), np.float32(0.9708), np.float32(0.9661), np.float32(0.9679), np.float32(0.8145), np.float32(0.758), np.float32(0.8786), np.float32(0.9519), np.float32(0.4301), np.float32(0.3569)] +2025-11-12 19:02:17.121567: Epoch time: 258.48 s +2025-11-12 19:02:19.018950: +2025-11-12 19:02:19.021531: Epoch 563 +2025-11-12 19:02:19.023780: Current learning rate: 0.00475 +2025-11-12 19:06:37.645187: train_loss -0.708 +2025-11-12 19:06:37.654346: val_loss -0.7219 +2025-11-12 19:06:37.656632: Pseudo dice [np.float32(0.9173), np.float32(0.7559), np.float32(0.7223), np.float32(0.6506), np.float32(0.8619), np.float32(0.808), np.float32(0.8724), np.float32(0.8598), np.float32(0.9746), np.float32(0.9743), np.float32(0.9687), np.float32(0.8305), np.float32(0.7438), np.float32(0.8723), np.float32(0.9618), np.float32(0.4402), np.float32(0.3769)] +2025-11-12 19:06:37.658288: Epoch time: 258.63 s +2025-11-12 19:06:39.473463: +2025-11-12 19:06:39.475011: Epoch 564 +2025-11-12 19:06:39.476368: Current learning rate: 0.00474 +2025-11-12 19:12:18.357304: train_loss -0.7062 +2025-11-12 19:12:18.362314: val_loss -0.7136 +2025-11-12 19:12:18.367784: Pseudo dice [np.float32(0.9211), np.float32(0.7624), np.float32(0.7229), np.float32(0.6331), np.float32(0.8583), np.float32(0.8012), np.float32(0.8914), np.float32(0.8663), np.float32(0.9712), np.float32(0.9684), np.float32(0.9697), np.float32(0.8329), np.float32(0.7781), np.float32(0.8725), np.float32(0.9587), np.float32(0.3847), np.float32(0.2956)] +2025-11-12 19:12:18.369573: Epoch time: 338.89 s +2025-11-12 19:12:20.256303: +2025-11-12 19:12:20.258171: Epoch 565 +2025-11-12 19:12:20.259959: Current learning rate: 0.00473 +2025-11-12 19:16:38.636024: train_loss -0.7121 +2025-11-12 19:16:38.643664: val_loss -0.7142 +2025-11-12 19:16:38.645812: Pseudo dice [np.float32(0.9009), np.float32(0.7482), np.float32(0.7117), np.float32(0.6689), np.float32(0.8713), np.float32(0.8042), np.float32(0.8973), np.float32(0.8537), np.float32(0.9802), np.float32(0.9763), np.float32(0.9688), np.float32(0.8417), np.float32(0.7802), np.float32(0.8804), np.float32(0.9558), np.float32(0.3784), np.float32(0.2998)] +2025-11-12 19:16:38.647707: Epoch time: 258.39 s +2025-11-12 19:16:40.529713: +2025-11-12 19:16:40.531177: Epoch 566 +2025-11-12 19:16:40.532694: Current learning rate: 0.00472 +2025-11-12 19:20:59.227106: train_loss -0.7068 +2025-11-12 19:20:59.232966: val_loss -0.7096 +2025-11-12 19:20:59.234844: Pseudo dice [np.float32(0.9124), np.float32(0.7676), np.float32(0.7312), np.float32(0.6437), np.float32(0.8682), np.float32(0.8095), np.float32(0.8865), np.float32(0.8637), np.float32(0.9729), np.float32(0.9688), np.float32(0.9684), np.float32(0.8285), np.float32(0.755), np.float32(0.869), np.float32(0.9544), np.float32(0.2847), np.float32(0.3278)] +2025-11-12 19:20:59.236896: Epoch time: 258.7 s +2025-11-12 19:21:01.106497: +2025-11-12 19:21:01.109948: Epoch 567 +2025-11-12 19:21:01.113181: Current learning rate: 0.00471 +2025-11-12 19:25:19.755574: train_loss -0.7134 +2025-11-12 19:25:19.762549: val_loss -0.7241 +2025-11-12 19:25:19.765197: Pseudo dice [np.float32(0.9089), np.float32(0.7632), np.float32(0.7369), np.float32(0.6403), np.float32(0.8611), np.float32(0.8115), np.float32(0.8975), np.float32(0.8551), np.float32(0.978), np.float32(0.9808), np.float32(0.9694), np.float32(0.8297), np.float32(0.7321), np.float32(0.8705), np.float32(0.958), np.float32(0.4376), np.float32(0.4351)] +2025-11-12 19:25:19.767967: Epoch time: 258.65 s +2025-11-12 19:25:21.627888: +2025-11-12 19:25:21.629737: Epoch 568 +2025-11-12 19:25:21.631943: Current learning rate: 0.0047 +2025-11-12 19:29:42.508891: train_loss -0.7075 +2025-11-12 19:29:42.515320: val_loss -0.7165 +2025-11-12 19:29:42.517017: Pseudo dice [np.float32(0.9034), np.float32(0.7861), np.float32(0.7011), np.float32(0.6797), np.float32(0.8703), np.float32(0.8041), np.float32(0.9019), np.float32(0.8563), np.float32(0.9792), np.float32(0.9782), np.float32(0.9691), np.float32(0.8262), np.float32(0.7281), np.float32(0.8794), np.float32(0.9619), np.float32(0.4514), np.float32(0.2942)] +2025-11-12 19:29:42.519066: Epoch time: 260.89 s +2025-11-12 19:29:44.407728: +2025-11-12 19:29:44.410776: Epoch 569 +2025-11-12 19:29:44.413447: Current learning rate: 0.00469 +2025-11-12 19:34:02.899831: train_loss -0.7103 +2025-11-12 19:34:02.907216: val_loss -0.7123 +2025-11-12 19:34:02.909633: Pseudo dice [np.float32(0.9085), np.float32(0.7819), np.float32(0.7082), np.float32(0.6319), np.float32(0.8646), np.float32(0.8067), np.float32(0.8857), np.float32(0.8561), np.float32(0.9767), np.float32(0.9723), np.float32(0.9688), np.float32(0.8338), np.float32(0.7631), np.float32(0.8697), np.float32(0.9611), np.float32(0.3975), np.float32(0.2971)] +2025-11-12 19:34:02.911637: Epoch time: 258.5 s +2025-11-12 19:34:04.808943: +2025-11-12 19:34:04.811831: Epoch 570 +2025-11-12 19:34:04.814346: Current learning rate: 0.00468 +2025-11-12 19:38:23.433371: train_loss -0.7047 +2025-11-12 19:38:23.438852: val_loss -0.7144 +2025-11-12 19:38:23.441516: Pseudo dice [np.float32(0.9111), np.float32(0.7438), np.float32(0.699), np.float32(0.6611), np.float32(0.8595), np.float32(0.7754), np.float32(0.9104), np.float32(0.8616), np.float32(0.9734), np.float32(0.9763), np.float32(0.9685), np.float32(0.8303), np.float32(0.7524), np.float32(0.8705), np.float32(0.9651), np.float32(0.4754), np.float32(0.4224)] +2025-11-12 19:38:23.444102: Epoch time: 258.63 s +2025-11-12 19:38:25.307835: +2025-11-12 19:38:25.310633: Epoch 571 +2025-11-12 19:38:25.312834: Current learning rate: 0.00467 +2025-11-12 19:42:43.785203: train_loss -0.7095 +2025-11-12 19:42:43.793140: val_loss -0.712 +2025-11-12 19:42:43.796075: Pseudo dice [np.float32(0.9082), np.float32(0.7838), np.float32(0.7359), np.float32(0.6532), np.float32(0.8613), np.float32(0.7992), np.float32(0.8834), np.float32(0.8678), np.float32(0.9795), np.float32(0.976), np.float32(0.9696), np.float32(0.845), np.float32(0.7682), np.float32(0.8801), np.float32(0.9635), np.float32(0.2883), np.float32(0.3148)] +2025-11-12 19:42:43.799115: Epoch time: 258.48 s +2025-11-12 19:42:45.756390: +2025-11-12 19:42:45.758026: Epoch 572 +2025-11-12 19:42:45.759862: Current learning rate: 0.00466 +2025-11-12 19:47:04.166576: train_loss -0.711 +2025-11-12 19:47:04.171343: val_loss -0.7245 +2025-11-12 19:47:04.172562: Pseudo dice [np.float32(0.9103), np.float32(0.7651), np.float32(0.7383), np.float32(0.6904), np.float32(0.8708), np.float32(0.8101), np.float32(0.8925), np.float32(0.8599), np.float32(0.9806), np.float32(0.9804), np.float32(0.9695), np.float32(0.8211), np.float32(0.7604), np.float32(0.874), np.float32(0.9621), np.float32(0.4118), np.float32(0.3474)] +2025-11-12 19:47:04.174210: Epoch time: 258.42 s +2025-11-12 19:47:06.040173: +2025-11-12 19:47:06.041733: Epoch 573 +2025-11-12 19:47:06.043007: Current learning rate: 0.00465 +2025-11-12 19:51:24.766224: train_loss -0.7109 +2025-11-12 19:51:24.770436: val_loss -0.7136 +2025-11-12 19:51:24.771644: Pseudo dice [np.float32(0.9117), np.float32(0.7775), np.float32(0.6902), np.float32(0.6603), np.float32(0.8694), np.float32(0.7915), np.float32(0.9025), np.float32(0.8606), np.float32(0.9757), np.float32(0.9727), np.float32(0.9694), np.float32(0.8364), np.float32(0.7717), np.float32(0.8751), np.float32(0.9627), np.float32(0.3763), np.float32(0.3021)] +2025-11-12 19:51:24.772705: Epoch time: 258.73 s +2025-11-12 19:51:26.679526: +2025-11-12 19:51:26.681844: Epoch 574 +2025-11-12 19:51:26.682995: Current learning rate: 0.00464 +2025-11-12 19:55:45.121895: train_loss -0.7147 +2025-11-12 19:55:45.128014: val_loss -0.7125 +2025-11-12 19:55:45.131013: Pseudo dice [np.float32(0.9043), np.float32(0.7742), np.float32(0.7345), np.float32(0.6673), np.float32(0.8637), np.float32(0.8136), np.float32(0.9094), np.float32(0.8605), np.float32(0.9733), np.float32(0.9753), np.float32(0.9694), np.float32(0.8322), np.float32(0.7599), np.float32(0.8728), np.float32(0.9628), np.float32(0.4128), np.float32(0.3136)] +2025-11-12 19:55:45.132725: Epoch time: 258.45 s +2025-11-12 19:55:47.036255: +2025-11-12 19:55:47.039024: Epoch 575 +2025-11-12 19:55:47.041671: Current learning rate: 0.00463 +2025-11-12 20:00:05.629964: train_loss -0.7088 +2025-11-12 20:00:05.635392: val_loss -0.719 +2025-11-12 20:00:05.637145: Pseudo dice [np.float32(0.9195), np.float32(0.7504), np.float32(0.73), np.float32(0.6458), np.float32(0.8639), np.float32(0.8062), np.float32(0.898), np.float32(0.8556), np.float32(0.9748), np.float32(0.9716), np.float32(0.9706), np.float32(0.8276), np.float32(0.7441), np.float32(0.8771), np.float32(0.9627), np.float32(0.4836), np.float32(0.3107)] +2025-11-12 20:00:05.639310: Epoch time: 258.6 s +2025-11-12 20:00:07.514957: +2025-11-12 20:00:07.516788: Epoch 576 +2025-11-12 20:00:07.518786: Current learning rate: 0.00462 +2025-11-12 20:04:26.102144: train_loss -0.7098 +2025-11-12 20:04:26.106012: val_loss -0.7204 +2025-11-12 20:04:26.107345: Pseudo dice [np.float32(0.9112), np.float32(0.7823), np.float32(0.6888), np.float32(0.6594), np.float32(0.8628), np.float32(0.7918), np.float32(0.9031), np.float32(0.8512), np.float32(0.9766), np.float32(0.9771), np.float32(0.9691), np.float32(0.8314), np.float32(0.7675), np.float32(0.8757), np.float32(0.9642), np.float32(0.4759), np.float32(0.3892)] +2025-11-12 20:04:26.108405: Epoch time: 258.59 s +2025-11-12 20:04:26.109496: Yayy! New best EMA pseudo Dice: 0.7976999878883362 +2025-11-12 20:04:32.228337: +2025-11-12 20:04:32.230112: Epoch 577 +2025-11-12 20:04:32.231450: Current learning rate: 0.00461 +2025-11-12 20:08:52.154741: train_loss -0.715 +2025-11-12 20:08:52.159585: val_loss -0.7207 +2025-11-12 20:08:52.160877: Pseudo dice [np.float32(0.9163), np.float32(0.775), np.float32(0.699), np.float32(0.6412), np.float32(0.8614), np.float32(0.812), np.float32(0.8756), np.float32(0.8567), np.float32(0.9769), np.float32(0.9753), np.float32(0.9699), np.float32(0.8434), np.float32(0.7877), np.float32(0.8716), np.float32(0.9633), np.float32(0.4565), np.float32(0.3153)] +2025-11-12 20:08:52.162237: Epoch time: 259.93 s +2025-11-12 20:08:52.163894: Yayy! New best EMA pseudo Dice: 0.7979000210762024 +2025-11-12 20:08:57.231877: +2025-11-12 20:08:57.233324: Epoch 578 +2025-11-12 20:08:57.234557: Current learning rate: 0.0046 +2025-11-12 20:13:15.582001: train_loss -0.7179 +2025-11-12 20:13:15.586817: val_loss -0.7108 +2025-11-12 20:13:15.588123: Pseudo dice [np.float32(0.9074), np.float32(0.7584), np.float32(0.696), np.float32(0.6737), np.float32(0.8622), np.float32(0.8062), np.float32(0.8956), np.float32(0.8491), np.float32(0.9809), np.float32(0.9801), np.float32(0.9684), np.float32(0.8475), np.float32(0.7712), np.float32(0.8758), np.float32(0.963), np.float32(0.2777), np.float32(0.3791)] +2025-11-12 20:13:15.589331: Epoch time: 258.36 s +2025-11-12 20:13:17.450199: +2025-11-12 20:13:17.451608: Epoch 579 +2025-11-12 20:13:17.452756: Current learning rate: 0.00459 +2025-11-12 20:17:36.245816: train_loss -0.7089 +2025-11-12 20:17:36.253793: val_loss -0.7217 +2025-11-12 20:17:36.257765: Pseudo dice [np.float32(0.9136), np.float32(0.7741), np.float32(0.7355), np.float32(0.6662), np.float32(0.8679), np.float32(0.7995), np.float32(0.9053), np.float32(0.8498), np.float32(0.9724), np.float32(0.9756), np.float32(0.9693), np.float32(0.8256), np.float32(0.7512), np.float32(0.8809), np.float32(0.958), np.float32(0.3936), np.float32(0.3969)] +2025-11-12 20:17:36.261064: Epoch time: 258.8 s +2025-11-12 20:17:36.263685: Yayy! New best EMA pseudo Dice: 0.7979000210762024 +2025-11-12 20:17:41.444242: +2025-11-12 20:17:41.447731: Epoch 580 +2025-11-12 20:17:41.449943: Current learning rate: 0.00458 +2025-11-12 20:22:00.035218: train_loss -0.7101 +2025-11-12 20:22:00.046130: val_loss -0.7144 +2025-11-12 20:22:00.049280: Pseudo dice [np.float32(0.9138), np.float32(0.7329), np.float32(0.7289), np.float32(0.6262), np.float32(0.8588), np.float32(0.7945), np.float32(0.9061), np.float32(0.8582), np.float32(0.9713), np.float32(0.9733), np.float32(0.9695), np.float32(0.8259), np.float32(0.7311), np.float32(0.864), np.float32(0.9666), np.float32(0.4266), np.float32(0.3431)] +2025-11-12 20:22:00.052548: Epoch time: 258.6 s +2025-11-12 20:22:01.872416: +2025-11-12 20:22:01.875478: Epoch 581 +2025-11-12 20:22:01.877085: Current learning rate: 0.00457 +2025-11-12 20:26:20.577523: train_loss -0.7082 +2025-11-12 20:26:20.583716: val_loss -0.7138 +2025-11-12 20:26:20.586303: Pseudo dice [np.float32(0.9136), np.float32(0.7661), np.float32(0.73), np.float32(0.6325), np.float32(0.8642), np.float32(0.8025), np.float32(0.9049), np.float32(0.8577), np.float32(0.9598), np.float32(0.9624), np.float32(0.969), np.float32(0.8342), np.float32(0.7382), np.float32(0.8741), np.float32(0.9567), np.float32(0.3841), np.float32(0.3098)] +2025-11-12 20:26:20.589526: Epoch time: 258.71 s +2025-11-12 20:26:22.400380: +2025-11-12 20:26:22.402393: Epoch 582 +2025-11-12 20:26:22.404986: Current learning rate: 0.00456 +2025-11-12 20:30:40.969736: train_loss -0.7102 +2025-11-12 20:30:40.975904: val_loss -0.7155 +2025-11-12 20:30:40.977347: Pseudo dice [np.float32(0.9101), np.float32(0.7798), np.float32(0.7188), np.float32(0.6623), np.float32(0.8738), np.float32(0.8046), np.float32(0.895), np.float32(0.8416), np.float32(0.9794), np.float32(0.9769), np.float32(0.9687), np.float32(0.8358), np.float32(0.7597), np.float32(0.8715), np.float32(0.9638), np.float32(0.3783), np.float32(0.3229)] +2025-11-12 20:30:40.979223: Epoch time: 258.58 s +2025-11-12 20:30:42.816609: +2025-11-12 20:30:42.818128: Epoch 583 +2025-11-12 20:30:42.819672: Current learning rate: 0.00455 +2025-11-12 20:35:01.378687: train_loss -0.7047 +2025-11-12 20:35:01.385113: val_loss -0.7143 +2025-11-12 20:35:01.386848: Pseudo dice [np.float32(0.8957), np.float32(0.7629), np.float32(0.7227), np.float32(0.6579), np.float32(0.8657), np.float32(0.8051), np.float32(0.8927), np.float32(0.8667), np.float32(0.9661), np.float32(0.9661), np.float32(0.968), np.float32(0.8229), np.float32(0.748), np.float32(0.8766), np.float32(0.9586), np.float32(0.4802), np.float32(0.3932)] +2025-11-12 20:35:01.388917: Epoch time: 258.57 s +2025-11-12 20:35:03.245171: +2025-11-12 20:35:03.247058: Epoch 584 +2025-11-12 20:35:03.248830: Current learning rate: 0.00454 +2025-11-12 20:39:21.673138: train_loss -0.7072 +2025-11-12 20:39:21.679935: val_loss -0.7254 +2025-11-12 20:39:21.682242: Pseudo dice [np.float32(0.9134), np.float32(0.8), np.float32(0.7224), np.float32(0.6762), np.float32(0.8568), np.float32(0.8144), np.float32(0.9021), np.float32(0.8664), np.float32(0.968), np.float32(0.9747), np.float32(0.9682), np.float32(0.8387), np.float32(0.781), np.float32(0.873), np.float32(0.9616), np.float32(0.4529), np.float32(0.3635)] +2025-11-12 20:39:21.684989: Epoch time: 258.43 s +2025-11-12 20:39:21.688023: Yayy! New best EMA pseudo Dice: 0.7985000014305115 +2025-11-12 20:39:26.579120: +2025-11-12 20:39:26.582567: Epoch 585 +2025-11-12 20:39:26.586232: Current learning rate: 0.00453 +2025-11-12 20:43:45.061358: train_loss -0.704 +2025-11-12 20:43:45.065668: val_loss -0.73 +2025-11-12 20:43:45.066913: Pseudo dice [np.float32(0.9226), np.float32(0.7866), np.float32(0.722), np.float32(0.658), np.float32(0.867), np.float32(0.8042), np.float32(0.9128), np.float32(0.8632), np.float32(0.9744), np.float32(0.9699), np.float32(0.968), np.float32(0.8311), np.float32(0.7773), np.float32(0.8728), np.float32(0.9578), np.float32(0.4778), np.float32(0.4837)] +2025-11-12 20:43:45.068194: Epoch time: 258.49 s +2025-11-12 20:43:45.069683: Yayy! New best EMA pseudo Dice: 0.8001000285148621 +2025-11-12 20:43:51.663260: +2025-11-12 20:43:51.664981: Epoch 586 +2025-11-12 20:43:51.666289: Current learning rate: 0.00452 +2025-11-12 20:48:09.830203: train_loss -0.7033 +2025-11-12 20:48:09.836999: val_loss -0.7221 +2025-11-12 20:48:09.838971: Pseudo dice [np.float32(0.9234), np.float32(0.782), np.float32(0.7221), np.float32(0.6317), np.float32(0.8539), np.float32(0.7948), np.float32(0.8918), np.float32(0.8579), np.float32(0.9717), np.float32(0.971), np.float32(0.9682), np.float32(0.836), np.float32(0.7461), np.float32(0.8686), np.float32(0.9618), np.float32(0.4747), np.float32(0.4622)] +2025-11-12 20:48:09.842960: Epoch time: 258.17 s +2025-11-12 20:48:09.845397: Yayy! New best EMA pseudo Dice: 0.8008000254631042 +2025-11-12 20:48:15.210742: +2025-11-12 20:48:15.212689: Epoch 587 +2025-11-12 20:48:15.214549: Current learning rate: 0.00451 +2025-11-12 20:52:33.856725: train_loss -0.7095 +2025-11-12 20:52:33.868304: val_loss -0.7167 +2025-11-12 20:52:33.871797: Pseudo dice [np.float32(0.9072), np.float32(0.7783), np.float32(0.7011), np.float32(0.6561), np.float32(0.8555), np.float32(0.7968), np.float32(0.8941), np.float32(0.8515), np.float32(0.9743), np.float32(0.9724), np.float32(0.969), np.float32(0.8315), np.float32(0.7572), np.float32(0.8643), np.float32(0.96), np.float32(0.3689), np.float32(0.4796)] +2025-11-12 20:52:33.875076: Epoch time: 258.65 s +2025-11-12 20:52:33.878038: Yayy! New best EMA pseudo Dice: 0.8008000254631042 +2025-11-12 20:52:39.218795: +2025-11-12 20:52:39.220801: Epoch 588 +2025-11-12 20:52:39.222407: Current learning rate: 0.0045 +2025-11-12 20:56:57.744464: train_loss -0.7059 +2025-11-12 20:56:57.749664: val_loss -0.7116 +2025-11-12 20:56:57.751140: Pseudo dice [np.float32(0.913), np.float32(0.8143), np.float32(0.7274), np.float32(0.6347), np.float32(0.8636), np.float32(0.7973), np.float32(0.869), np.float32(0.8557), np.float32(0.9743), np.float32(0.9752), np.float32(0.9698), np.float32(0.825), np.float32(0.7405), np.float32(0.8683), np.float32(0.9617), np.float32(0.4277), np.float32(0.3152)] +2025-11-12 20:56:57.753006: Epoch time: 258.54 s +2025-11-12 20:56:59.655637: +2025-11-12 20:56:59.657671: Epoch 589 +2025-11-12 20:56:59.659786: Current learning rate: 0.00449 +2025-11-12 21:01:18.266241: train_loss -0.7042 +2025-11-12 21:01:18.273613: val_loss -0.7174 +2025-11-12 21:01:18.276067: Pseudo dice [np.float32(0.9033), np.float32(0.7582), np.float32(0.709), np.float32(0.6516), np.float32(0.8665), np.float32(0.8017), np.float32(0.9014), np.float32(0.8555), np.float32(0.9707), np.float32(0.9674), np.float32(0.9691), np.float32(0.8329), np.float32(0.7635), np.float32(0.8772), np.float32(0.9654), np.float32(0.4072), np.float32(0.3728)] +2025-11-12 21:01:18.278568: Epoch time: 258.62 s +2025-11-12 21:01:20.190410: +2025-11-12 21:01:20.192701: Epoch 590 +2025-11-12 21:01:20.194488: Current learning rate: 0.00448 +2025-11-12 21:05:38.659702: train_loss -0.7096 +2025-11-12 21:05:38.668571: val_loss -0.7215 +2025-11-12 21:05:38.671933: Pseudo dice [np.float32(0.9144), np.float32(0.7861), np.float32(0.7068), np.float32(0.6727), np.float32(0.8681), np.float32(0.8039), np.float32(0.898), np.float32(0.8661), np.float32(0.968), np.float32(0.9698), np.float32(0.9697), np.float32(0.8216), np.float32(0.7313), np.float32(0.8833), np.float32(0.9628), np.float32(0.3364), np.float32(0.3477)] +2025-11-12 21:05:38.674919: Epoch time: 258.48 s +2025-11-12 21:05:40.564586: +2025-11-12 21:05:40.567196: Epoch 591 +2025-11-12 21:05:40.568295: Current learning rate: 0.00447 +2025-11-12 21:09:58.907813: train_loss -0.712 +2025-11-12 21:09:58.913954: val_loss -0.7192 +2025-11-12 21:09:58.915651: Pseudo dice [np.float32(0.9204), np.float32(0.7718), np.float32(0.7349), np.float32(0.6361), np.float32(0.8605), np.float32(0.8015), np.float32(0.9058), np.float32(0.8496), np.float32(0.9747), np.float32(0.9726), np.float32(0.9705), np.float32(0.8418), np.float32(0.742), np.float32(0.8701), np.float32(0.965), np.float32(0.3662), np.float32(0.381)] +2025-11-12 21:09:58.917759: Epoch time: 258.35 s +2025-11-12 21:10:00.865074: +2025-11-12 21:10:00.866302: Epoch 592 +2025-11-12 21:10:00.868103: Current learning rate: 0.00446 +2025-11-12 21:14:19.486848: train_loss -0.7091 +2025-11-12 21:14:19.494588: val_loss -0.7146 +2025-11-12 21:14:19.497519: Pseudo dice [np.float32(0.9108), np.float32(0.7718), np.float32(0.7324), np.float32(0.6668), np.float32(0.8636), np.float32(0.8025), np.float32(0.8976), np.float32(0.8418), np.float32(0.96), np.float32(0.9622), np.float32(0.967), np.float32(0.8226), np.float32(0.7929), np.float32(0.8709), np.float32(0.9474), np.float32(0.3778), np.float32(0.2812)] +2025-11-12 21:14:19.499853: Epoch time: 258.63 s +2025-11-12 21:14:21.370224: +2025-11-12 21:14:21.371793: Epoch 593 +2025-11-12 21:14:21.373160: Current learning rate: 0.00445 +2025-11-12 21:18:40.024958: train_loss -0.7157 +2025-11-12 21:18:40.030519: val_loss -0.7163 +2025-11-12 21:18:40.032311: Pseudo dice [np.float32(0.9178), np.float32(0.772), np.float32(0.7159), np.float32(0.6479), np.float32(0.8559), np.float32(0.8079), np.float32(0.9092), np.float32(0.8646), np.float32(0.9796), np.float32(0.979), np.float32(0.9696), np.float32(0.8356), np.float32(0.7766), np.float32(0.872), np.float32(0.9649), np.float32(0.4146), np.float32(0.3474)] +2025-11-12 21:18:40.034245: Epoch time: 258.66 s +2025-11-12 21:18:41.921911: +2025-11-12 21:18:41.925006: Epoch 594 +2025-11-12 21:18:41.927794: Current learning rate: 0.00444 +2025-11-12 21:23:00.280680: train_loss -0.7086 +2025-11-12 21:23:00.287805: val_loss -0.7278 +2025-11-12 21:23:00.290134: Pseudo dice [np.float32(0.9179), np.float32(0.7696), np.float32(0.7238), np.float32(0.6437), np.float32(0.8607), np.float32(0.8071), np.float32(0.9079), np.float32(0.8519), np.float32(0.9808), np.float32(0.9762), np.float32(0.9686), np.float32(0.8268), np.float32(0.7858), np.float32(0.869), np.float32(0.9647), np.float32(0.4482), np.float32(0.4279)] +2025-11-12 21:23:00.292331: Epoch time: 258.36 s +2025-11-12 21:23:02.186606: +2025-11-12 21:23:02.189115: Epoch 595 +2025-11-12 21:23:02.191105: Current learning rate: 0.00443 +2025-11-12 21:27:22.095611: train_loss -0.7116 +2025-11-12 21:27:22.101592: val_loss -0.7217 +2025-11-12 21:27:22.103429: Pseudo dice [np.float32(0.9083), np.float32(0.7766), np.float32(0.7092), np.float32(0.6792), np.float32(0.8649), np.float32(0.8178), np.float32(0.9013), np.float32(0.854), np.float32(0.9735), np.float32(0.9761), np.float32(0.9684), np.float32(0.8347), np.float32(0.774), np.float32(0.8701), np.float32(0.9615), np.float32(0.446), np.float32(0.4175)] +2025-11-12 21:27:22.104767: Epoch time: 259.92 s +2025-11-12 21:27:23.932712: +2025-11-12 21:27:23.936014: Epoch 596 +2025-11-12 21:27:23.939075: Current learning rate: 0.00442 +2025-11-12 21:31:42.313162: train_loss -0.7083 +2025-11-12 21:31:42.325518: val_loss -0.7221 +2025-11-12 21:31:42.328064: Pseudo dice [np.float32(0.9143), np.float32(0.7831), np.float32(0.7536), np.float32(0.6453), np.float32(0.8586), np.float32(0.7961), np.float32(0.9065), np.float32(0.86), np.float32(0.9704), np.float32(0.9672), np.float32(0.9683), np.float32(0.8279), np.float32(0.777), np.float32(0.8789), np.float32(0.9577), np.float32(0.4086), np.float32(0.4)] +2025-11-12 21:31:42.329823: Epoch time: 258.39 s +2025-11-12 21:31:42.333008: Yayy! New best EMA pseudo Dice: 0.8011000156402588 +2025-11-12 21:31:47.202491: +2025-11-12 21:31:47.204216: Epoch 597 +2025-11-12 21:31:47.206315: Current learning rate: 0.00441 +2025-11-12 21:36:05.662767: train_loss -0.7087 +2025-11-12 21:36:05.668213: val_loss -0.7185 +2025-11-12 21:36:05.669848: Pseudo dice [np.float32(0.9121), np.float32(0.7619), np.float32(0.7358), np.float32(0.6777), np.float32(0.8616), np.float32(0.7915), np.float32(0.8941), np.float32(0.8586), np.float32(0.9789), np.float32(0.9771), np.float32(0.9694), np.float32(0.8267), np.float32(0.7671), np.float32(0.876), np.float32(0.963), np.float32(0.3631), np.float32(0.3232)] +2025-11-12 21:36:05.671078: Epoch time: 258.47 s +2025-11-12 21:36:07.548653: +2025-11-12 21:36:07.551230: Epoch 598 +2025-11-12 21:36:07.554006: Current learning rate: 0.0044 +2025-11-12 21:40:26.199823: train_loss -0.7052 +2025-11-12 21:40:26.205326: val_loss -0.7208 +2025-11-12 21:40:26.206568: Pseudo dice [np.float32(0.9219), np.float32(0.7496), np.float32(0.7147), np.float32(0.6428), np.float32(0.8597), np.float32(0.8073), np.float32(0.914), np.float32(0.8614), np.float32(0.9779), np.float32(0.9764), np.float32(0.9687), np.float32(0.8406), np.float32(0.7467), np.float32(0.8736), np.float32(0.9654), np.float32(0.4171), np.float32(0.4047)] +2025-11-12 21:40:26.208024: Epoch time: 258.66 s +2025-11-12 21:40:28.041981: +2025-11-12 21:40:28.043468: Epoch 599 +2025-11-12 21:40:28.045133: Current learning rate: 0.00439 +2025-11-12 21:45:43.531137: train_loss -0.7086 +2025-11-12 21:45:43.538163: val_loss -0.7177 +2025-11-12 21:45:43.540050: Pseudo dice [np.float32(0.9065), np.float32(0.7609), np.float32(0.7258), np.float32(0.6464), np.float32(0.8614), np.float32(0.7989), np.float32(0.88), np.float32(0.855), np.float32(0.9765), np.float32(0.9775), np.float32(0.9692), np.float32(0.8407), np.float32(0.7533), np.float32(0.8727), np.float32(0.9607), np.float32(0.4164), np.float32(0.3506)] +2025-11-12 21:45:43.542608: Epoch time: 315.49 s +2025-11-12 21:45:48.214396: +2025-11-12 21:45:48.216662: Epoch 600 +2025-11-12 21:45:48.218696: Current learning rate: 0.00438 +2025-11-12 21:50:06.666721: train_loss -0.7136 +2025-11-12 21:50:06.674647: val_loss -0.7335 +2025-11-12 21:50:06.676656: Pseudo dice [np.float32(0.923), np.float32(0.7985), np.float32(0.7052), np.float32(0.6743), np.float32(0.8681), np.float32(0.8125), np.float32(0.8592), np.float32(0.8692), np.float32(0.9753), np.float32(0.9743), np.float32(0.9694), np.float32(0.8383), np.float32(0.7791), np.float32(0.8819), np.float32(0.9651), np.float32(0.4556), np.float32(0.3761)] +2025-11-12 21:50:06.678277: Epoch time: 258.46 s +2025-11-12 21:50:06.680302: Yayy! New best EMA pseudo Dice: 0.8011000156402588 +2025-11-12 21:50:11.672111: +2025-11-12 21:50:11.675771: Epoch 601 +2025-11-12 21:50:11.679297: Current learning rate: 0.00437 +2025-11-12 21:54:30.157673: train_loss -0.7138 +2025-11-12 21:54:30.165686: val_loss -0.7255 +2025-11-12 21:54:30.168502: Pseudo dice [np.float32(0.8979), np.float32(0.7893), np.float32(0.7137), np.float32(0.6784), np.float32(0.8684), np.float32(0.7967), np.float32(0.8801), np.float32(0.8521), np.float32(0.9719), np.float32(0.9753), np.float32(0.9696), np.float32(0.8324), np.float32(0.7716), np.float32(0.876), np.float32(0.9651), np.float32(0.4506), np.float32(0.4006)] +2025-11-12 21:54:30.170844: Epoch time: 258.49 s +2025-11-12 21:54:30.173079: Yayy! New best EMA pseudo Dice: 0.8015000224113464 +2025-11-12 21:54:35.201782: +2025-11-12 21:54:35.204695: Epoch 602 +2025-11-12 21:54:35.207599: Current learning rate: 0.00436 +2025-11-12 21:58:53.766639: train_loss -0.7094 +2025-11-12 21:58:53.779724: val_loss -0.7271 +2025-11-12 21:58:53.783190: Pseudo dice [np.float32(0.9136), np.float32(0.7938), np.float32(0.7132), np.float32(0.6551), np.float32(0.8748), np.float32(0.8182), np.float32(0.8965), np.float32(0.8603), np.float32(0.9746), np.float32(0.9779), np.float32(0.9681), np.float32(0.8361), np.float32(0.779), np.float32(0.8809), np.float32(0.9575), np.float32(0.4168), np.float32(0.3669)] +2025-11-12 21:58:53.787030: Epoch time: 258.57 s +2025-11-12 21:58:53.791402: Yayy! New best EMA pseudo Dice: 0.8019000291824341 +2025-11-12 21:58:58.972658: +2025-11-12 21:58:58.974782: Epoch 603 +2025-11-12 21:58:58.977252: Current learning rate: 0.00435 +2025-11-12 22:03:18.881184: train_loss -0.7114 +2025-11-12 22:03:18.889380: val_loss -0.7241 +2025-11-12 22:03:18.891849: Pseudo dice [np.float32(0.9167), np.float32(0.7893), np.float32(0.7148), np.float32(0.6572), np.float32(0.8719), np.float32(0.812), np.float32(0.9043), np.float32(0.8534), np.float32(0.9788), np.float32(0.9733), np.float32(0.9703), np.float32(0.8379), np.float32(0.7761), np.float32(0.8824), np.float32(0.9587), np.float32(0.3905), np.float32(0.3751)] +2025-11-12 22:03:18.893820: Epoch time: 259.91 s +2025-11-12 22:03:18.896053: Yayy! New best EMA pseudo Dice: 0.8019999861717224 +2025-11-12 22:03:23.961855: +2025-11-12 22:03:23.964483: Epoch 604 +2025-11-12 22:03:23.967051: Current learning rate: 0.00434 +2025-11-12 22:07:42.483307: train_loss -0.7153 +2025-11-12 22:07:42.490982: val_loss -0.724 +2025-11-12 22:07:42.494092: Pseudo dice [np.float32(0.9207), np.float32(0.7712), np.float32(0.696), np.float32(0.6825), np.float32(0.8736), np.float32(0.8083), np.float32(0.9066), np.float32(0.8719), np.float32(0.978), np.float32(0.9746), np.float32(0.9708), np.float32(0.8472), np.float32(0.7665), np.float32(0.8848), np.float32(0.9653), np.float32(0.3663), np.float32(0.3255)] +2025-11-12 22:07:42.495576: Epoch time: 258.53 s +2025-11-12 22:07:44.408092: +2025-11-12 22:07:44.409602: Epoch 605 +2025-11-12 22:07:44.411711: Current learning rate: 0.00433 +2025-11-12 22:12:03.102456: train_loss -0.7182 +2025-11-12 22:12:03.110219: val_loss -0.7142 +2025-11-12 22:12:03.112582: Pseudo dice [np.float32(0.9196), np.float32(0.7967), np.float32(0.7231), np.float32(0.652), np.float32(0.8639), np.float32(0.7969), np.float32(0.9006), np.float32(0.8498), np.float32(0.9785), np.float32(0.975), np.float32(0.9683), np.float32(0.8397), np.float32(0.7607), np.float32(0.8774), np.float32(0.9559), np.float32(0.2988), np.float32(0.3975)] +2025-11-12 22:12:03.115558: Epoch time: 258.7 s +2025-11-12 22:12:04.998757: +2025-11-12 22:12:05.001249: Epoch 606 +2025-11-12 22:12:05.003646: Current learning rate: 0.00432 +2025-11-12 22:16:23.492058: train_loss -0.7132 +2025-11-12 22:16:23.502145: val_loss -0.7249 +2025-11-12 22:16:23.505583: Pseudo dice [np.float32(0.9214), np.float32(0.7763), np.float32(0.7408), np.float32(0.6402), np.float32(0.8677), np.float32(0.8104), np.float32(0.8827), np.float32(0.8555), np.float32(0.9684), np.float32(0.968), np.float32(0.9704), np.float32(0.8305), np.float32(0.7469), np.float32(0.8742), np.float32(0.9635), np.float32(0.4662), np.float32(0.411)] +2025-11-12 22:16:23.509008: Epoch time: 258.5 s +2025-11-12 22:16:25.414750: +2025-11-12 22:16:25.418034: Epoch 607 +2025-11-12 22:16:25.421242: Current learning rate: 0.00431 +2025-11-12 22:20:43.946962: train_loss -0.712 +2025-11-12 22:20:43.953784: val_loss -0.7241 +2025-11-12 22:20:43.956234: Pseudo dice [np.float32(0.9299), np.float32(0.7834), np.float32(0.7217), np.float32(0.6568), np.float32(0.8696), np.float32(0.8081), np.float32(0.9077), np.float32(0.8602), np.float32(0.9766), np.float32(0.9763), np.float32(0.9702), np.float32(0.8305), np.float32(0.7479), np.float32(0.8831), np.float32(0.9647), np.float32(0.3881), np.float32(0.3765)] +2025-11-12 22:20:43.958749: Epoch time: 258.54 s +2025-11-12 22:20:45.809037: +2025-11-12 22:20:45.812340: Epoch 608 +2025-11-12 22:20:45.815765: Current learning rate: 0.0043 +2025-11-12 22:25:04.256470: train_loss -0.7142 +2025-11-12 22:25:04.261883: val_loss -0.7212 +2025-11-12 22:25:04.263657: Pseudo dice [np.float32(0.9164), np.float32(0.7684), np.float32(0.7183), np.float32(0.6171), np.float32(0.8691), np.float32(0.8071), np.float32(0.8965), np.float32(0.8634), np.float32(0.972), np.float32(0.9742), np.float32(0.969), np.float32(0.8128), np.float32(0.7612), np.float32(0.8857), np.float32(0.9661), np.float32(0.4238), np.float32(0.4438)] +2025-11-12 22:25:04.265667: Epoch time: 258.45 s +2025-11-12 22:25:04.267793: Yayy! New best EMA pseudo Dice: 0.8022000193595886 +2025-11-12 22:25:09.230515: +2025-11-12 22:25:09.232144: Epoch 609 +2025-11-12 22:25:09.233540: Current learning rate: 0.00429 +2025-11-12 22:29:27.668994: train_loss -0.7133 +2025-11-12 22:29:27.681432: val_loss -0.7173 +2025-11-12 22:29:27.685181: Pseudo dice [np.float32(0.9121), np.float32(0.7845), np.float32(0.7338), np.float32(0.6484), np.float32(0.8613), np.float32(0.7792), np.float32(0.8957), np.float32(0.8616), np.float32(0.9754), np.float32(0.9721), np.float32(0.97), np.float32(0.8188), np.float32(0.7221), np.float32(0.8699), np.float32(0.9666), np.float32(0.469), np.float32(0.3834)] +2025-11-12 22:29:27.688412: Epoch time: 258.44 s +2025-11-12 22:29:29.550972: +2025-11-12 22:29:29.553467: Epoch 610 +2025-11-12 22:29:29.555636: Current learning rate: 0.00429 +2025-11-12 22:33:48.105417: train_loss -0.7137 +2025-11-12 22:33:48.111080: val_loss -0.717 +2025-11-12 22:33:48.113029: Pseudo dice [np.float32(0.9188), np.float32(0.7495), np.float32(0.7175), np.float32(0.6519), np.float32(0.8646), np.float32(0.8163), np.float32(0.8902), np.float32(0.8583), np.float32(0.9762), np.float32(0.976), np.float32(0.9697), np.float32(0.8407), np.float32(0.7643), np.float32(0.8797), np.float32(0.9622), np.float32(0.3698), np.float32(0.2671)] +2025-11-12 22:33:48.114335: Epoch time: 258.56 s +2025-11-12 22:33:50.000779: +2025-11-12 22:33:50.003587: Epoch 611 +2025-11-12 22:33:50.006273: Current learning rate: 0.00428 +2025-11-12 22:38:08.230249: train_loss -0.7121 +2025-11-12 22:38:08.240487: val_loss -0.7226 +2025-11-12 22:38:08.243694: Pseudo dice [np.float32(0.9239), np.float32(0.7883), np.float32(0.7489), np.float32(0.6473), np.float32(0.87), np.float32(0.809), np.float32(0.9074), np.float32(0.8559), np.float32(0.9726), np.float32(0.9733), np.float32(0.9696), np.float32(0.8333), np.float32(0.7539), np.float32(0.8822), np.float32(0.9582), np.float32(0.4118), np.float32(0.3711)] +2025-11-12 22:38:08.245544: Epoch time: 258.23 s +2025-11-12 22:38:10.092468: +2025-11-12 22:38:10.094604: Epoch 612 +2025-11-12 22:38:10.096788: Current learning rate: 0.00427 +2025-11-12 22:42:29.326549: train_loss -0.7132 +2025-11-12 22:42:29.330373: val_loss -0.7156 +2025-11-12 22:42:29.331512: Pseudo dice [np.float32(0.9046), np.float32(0.7879), np.float32(0.744), np.float32(0.6429), np.float32(0.8627), np.float32(0.8042), np.float32(0.905), np.float32(0.854), np.float32(0.9811), np.float32(0.9753), np.float32(0.9697), np.float32(0.8377), np.float32(0.7609), np.float32(0.8787), np.float32(0.9653), np.float32(0.3576), np.float32(0.2679)] +2025-11-12 22:42:29.332853: Epoch time: 259.24 s +2025-11-12 22:42:31.262695: +2025-11-12 22:42:31.264420: Epoch 613 +2025-11-12 22:42:31.266267: Current learning rate: 0.00426 +2025-11-12 22:46:49.853027: train_loss -0.7048 +2025-11-12 22:46:49.860594: val_loss -0.7222 +2025-11-12 22:46:49.862901: Pseudo dice [np.float32(0.9057), np.float32(0.7897), np.float32(0.7191), np.float32(0.6353), np.float32(0.8607), np.float32(0.7949), np.float32(0.8832), np.float32(0.8629), np.float32(0.976), np.float32(0.9765), np.float32(0.968), np.float32(0.8286), np.float32(0.7726), np.float32(0.866), np.float32(0.9618), np.float32(0.4462), np.float32(0.3563)] +2025-11-12 22:46:49.864714: Epoch time: 258.6 s +2025-11-12 22:46:51.839511: +2025-11-12 22:46:51.841553: Epoch 614 +2025-11-12 22:46:51.843426: Current learning rate: 0.00425 +2025-11-12 22:51:10.197234: train_loss -0.704 +2025-11-12 22:51:10.204341: val_loss -0.7133 +2025-11-12 22:51:10.206396: Pseudo dice [np.float32(0.913), np.float32(0.7693), np.float32(0.7054), np.float32(0.6518), np.float32(0.852), np.float32(0.8096), np.float32(0.9045), np.float32(0.8503), np.float32(0.9727), np.float32(0.9676), np.float32(0.9668), np.float32(0.8285), np.float32(0.7619), np.float32(0.8585), np.float32(0.9576), np.float32(0.4202), np.float32(0.3585)] +2025-11-12 22:51:10.209058: Epoch time: 258.36 s +2025-11-12 22:51:12.083383: +2025-11-12 22:51:12.085921: Epoch 615 +2025-11-12 22:51:12.088190: Current learning rate: 0.00424 +2025-11-12 22:55:30.553675: train_loss -0.6994 +2025-11-12 22:55:30.557428: val_loss -0.7122 +2025-11-12 22:55:30.558863: Pseudo dice [np.float32(0.9087), np.float32(0.7997), np.float32(0.7129), np.float32(0.6458), np.float32(0.866), np.float32(0.7875), np.float32(0.9004), np.float32(0.8599), np.float32(0.9632), np.float32(0.9632), np.float32(0.9689), np.float32(0.8203), np.float32(0.763), np.float32(0.8735), np.float32(0.959), np.float32(0.3614), np.float32(0.3224)] +2025-11-12 22:55:30.560210: Epoch time: 258.48 s +2025-11-12 22:55:32.599046: +2025-11-12 22:55:32.601502: Epoch 616 +2025-11-12 22:55:32.602967: Current learning rate: 0.00423 +2025-11-12 22:59:51.023795: train_loss -0.7075 +2025-11-12 22:59:51.031652: val_loss -0.7141 +2025-11-12 22:59:51.034013: Pseudo dice [np.float32(0.9162), np.float32(0.7809), np.float32(0.735), np.float32(0.6575), np.float32(0.8591), np.float32(0.7932), np.float32(0.8932), np.float32(0.8618), np.float32(0.9799), np.float32(0.9786), np.float32(0.9692), np.float32(0.8381), np.float32(0.7625), np.float32(0.8697), np.float32(0.9612), np.float32(0.3775), np.float32(0.3556)] +2025-11-12 22:59:51.036342: Epoch time: 258.43 s +2025-11-12 22:59:52.946630: +2025-11-12 22:59:52.949264: Epoch 617 +2025-11-12 22:59:52.951772: Current learning rate: 0.00422 +2025-11-12 23:04:11.362969: train_loss -0.7056 +2025-11-12 23:04:11.372781: val_loss -0.7147 +2025-11-12 23:04:11.375748: Pseudo dice [np.float32(0.9062), np.float32(0.7728), np.float32(0.695), np.float32(0.656), np.float32(0.8567), np.float32(0.7946), np.float32(0.894), np.float32(0.8633), np.float32(0.9752), np.float32(0.9688), np.float32(0.9686), np.float32(0.8304), np.float32(0.7676), np.float32(0.8701), np.float32(0.9579), np.float32(0.4937), np.float32(0.4437)] +2025-11-12 23:04:11.378801: Epoch time: 258.42 s +2025-11-12 23:04:13.257138: +2025-11-12 23:04:13.258975: Epoch 618 +2025-11-12 23:04:13.260516: Current learning rate: 0.00421 +2025-11-12 23:08:31.724137: train_loss -0.7043 +2025-11-12 23:08:31.735953: val_loss -0.7106 +2025-11-12 23:08:31.739154: Pseudo dice [np.float32(0.9087), np.float32(0.7223), np.float32(0.7003), np.float32(0.632), np.float32(0.8664), np.float32(0.7985), np.float32(0.9125), np.float32(0.8488), np.float32(0.9677), np.float32(0.9674), np.float32(0.9683), np.float32(0.8236), np.float32(0.7751), np.float32(0.8776), np.float32(0.9626), np.float32(0.3175), np.float32(0.2532)] +2025-11-12 23:08:31.742720: Epoch time: 258.47 s +2025-11-12 23:08:33.876076: +2025-11-12 23:08:33.877696: Epoch 619 +2025-11-12 23:08:33.879273: Current learning rate: 0.0042 +2025-11-12 23:12:52.662460: train_loss -0.7123 +2025-11-12 23:12:52.672159: val_loss -0.7174 +2025-11-12 23:12:52.675533: Pseudo dice [np.float32(0.9124), np.float32(0.7778), np.float32(0.7295), np.float32(0.6696), np.float32(0.871), np.float32(0.8241), np.float32(0.9067), np.float32(0.852), np.float32(0.9626), np.float32(0.9665), np.float32(0.9698), np.float32(0.8358), np.float32(0.7786), np.float32(0.881), np.float32(0.9596), np.float32(0.2986), np.float32(0.3303)] +2025-11-12 23:12:52.678164: Epoch time: 258.79 s +2025-11-12 23:12:54.555618: +2025-11-12 23:12:54.558242: Epoch 620 +2025-11-12 23:12:54.560862: Current learning rate: 0.00419 +2025-11-12 23:17:12.982783: train_loss -0.7132 +2025-11-12 23:17:12.987126: val_loss -0.7117 +2025-11-12 23:17:12.988384: Pseudo dice [np.float32(0.9173), np.float32(0.7589), np.float32(0.683), np.float32(0.6635), np.float32(0.8545), np.float32(0.809), np.float32(0.9073), np.float32(0.8591), np.float32(0.9788), np.float32(0.9782), np.float32(0.9696), np.float32(0.8337), np.float32(0.7725), np.float32(0.8669), np.float32(0.9651), np.float32(0.4177), np.float32(0.3122)] +2025-11-12 23:17:12.990269: Epoch time: 258.43 s +2025-11-12 23:17:14.851377: +2025-11-12 23:17:14.856087: Epoch 621 +2025-11-12 23:17:14.859034: Current learning rate: 0.00418 +2025-11-12 23:21:33.221380: train_loss -0.7089 +2025-11-12 23:21:33.228364: val_loss -0.7106 +2025-11-12 23:21:33.230561: Pseudo dice [np.float32(0.9102), np.float32(0.7808), np.float32(0.727), np.float32(0.6568), np.float32(0.8598), np.float32(0.8103), np.float32(0.8935), np.float32(0.8655), np.float32(0.9686), np.float32(0.9679), np.float32(0.9688), np.float32(0.8293), np.float32(0.7572), np.float32(0.8697), np.float32(0.9551), np.float32(0.3261), np.float32(0.2977)] +2025-11-12 23:21:33.232525: Epoch time: 258.38 s +2025-11-12 23:21:36.342568: +2025-11-12 23:21:36.344557: Epoch 622 +2025-11-12 23:21:36.346502: Current learning rate: 0.00417 +2025-11-12 23:25:54.881109: train_loss -0.7082 +2025-11-12 23:25:54.888797: val_loss -0.7239 +2025-11-12 23:25:54.890785: Pseudo dice [np.float32(0.9103), np.float32(0.7832), np.float32(0.7408), np.float32(0.6718), np.float32(0.8537), np.float32(0.7795), np.float32(0.8888), np.float32(0.859), np.float32(0.9742), np.float32(0.9774), np.float32(0.9682), np.float32(0.8321), np.float32(0.736), np.float32(0.8712), np.float32(0.9621), np.float32(0.5055), np.float32(0.4378)] +2025-11-12 23:25:54.892555: Epoch time: 258.54 s +2025-11-12 23:25:56.761153: +2025-11-12 23:25:56.763698: Epoch 623 +2025-11-12 23:25:56.765906: Current learning rate: 0.00416 +2025-11-12 23:30:15.326400: train_loss -0.7137 +2025-11-12 23:30:15.334011: val_loss -0.7113 +2025-11-12 23:30:15.336466: Pseudo dice [np.float32(0.9176), np.float32(0.7682), np.float32(0.7044), np.float32(0.6465), np.float32(0.8661), np.float32(0.8065), np.float32(0.9146), np.float32(0.8527), np.float32(0.9754), np.float32(0.9727), np.float32(0.9688), np.float32(0.835), np.float32(0.7729), np.float32(0.8721), np.float32(0.9565), np.float32(0.3757), np.float32(0.3332)] +2025-11-12 23:30:15.338458: Epoch time: 258.57 s +2025-11-12 23:30:17.234364: +2025-11-12 23:30:17.236131: Epoch 624 +2025-11-12 23:30:17.237841: Current learning rate: 0.00415 +2025-11-12 23:34:35.536610: train_loss -0.7111 +2025-11-12 23:34:35.543896: val_loss -0.718 +2025-11-12 23:34:35.546337: Pseudo dice [np.float32(0.9319), np.float32(0.7642), np.float32(0.6934), np.float32(0.6749), np.float32(0.8616), np.float32(0.8105), np.float32(0.909), np.float32(0.8518), np.float32(0.9796), np.float32(0.9765), np.float32(0.9695), np.float32(0.8442), np.float32(0.7709), np.float32(0.8712), np.float32(0.9606), np.float32(0.3309), np.float32(0.3167)] +2025-11-12 23:34:35.548795: Epoch time: 258.31 s +2025-11-12 23:34:37.449180: +2025-11-12 23:34:37.451823: Epoch 625 +2025-11-12 23:34:37.454365: Current learning rate: 0.00414 +2025-11-12 23:38:55.882566: train_loss -0.7075 +2025-11-12 23:38:55.892025: val_loss -0.7141 +2025-11-12 23:38:55.893829: Pseudo dice [np.float32(0.9087), np.float32(0.7888), np.float32(0.7126), np.float32(0.6662), np.float32(0.8644), np.float32(0.8122), np.float32(0.8966), np.float32(0.8702), np.float32(0.9795), np.float32(0.9758), np.float32(0.9713), np.float32(0.8343), np.float32(0.7597), np.float32(0.8791), np.float32(0.9618), np.float32(0.3491), np.float32(0.295)] +2025-11-12 23:38:55.896021: Epoch time: 258.44 s +2025-11-12 23:38:57.801930: +2025-11-12 23:38:57.804633: Epoch 626 +2025-11-12 23:38:57.806933: Current learning rate: 0.00413 +2025-11-12 23:43:16.458361: train_loss -0.7089 +2025-11-12 23:43:16.464257: val_loss -0.7225 +2025-11-12 23:43:16.466282: Pseudo dice [np.float32(0.9172), np.float32(0.7794), np.float32(0.7137), np.float32(0.6817), np.float32(0.8652), np.float32(0.7924), np.float32(0.8948), np.float32(0.8515), np.float32(0.9758), np.float32(0.9793), np.float32(0.9702), np.float32(0.8393), np.float32(0.7683), np.float32(0.8699), np.float32(0.9638), np.float32(0.3196), np.float32(0.4166)] +2025-11-12 23:43:16.467763: Epoch time: 258.66 s +2025-11-12 23:43:18.337428: +2025-11-12 23:43:18.339972: Epoch 627 +2025-11-12 23:43:18.342012: Current learning rate: 0.00412 +2025-11-12 23:47:36.920615: train_loss -0.7134 +2025-11-12 23:47:36.928499: val_loss -0.7254 +2025-11-12 23:47:36.930352: Pseudo dice [np.float32(0.9168), np.float32(0.7768), np.float32(0.7103), np.float32(0.6428), np.float32(0.8629), np.float32(0.8198), np.float32(0.9077), np.float32(0.8579), np.float32(0.9765), np.float32(0.9781), np.float32(0.9705), np.float32(0.8444), np.float32(0.773), np.float32(0.876), np.float32(0.9616), np.float32(0.3632), np.float32(0.3672)] +2025-11-12 23:47:36.931590: Epoch time: 258.59 s +2025-11-12 23:47:38.816698: +2025-11-12 23:47:38.818936: Epoch 628 +2025-11-12 23:47:38.821445: Current learning rate: 0.00411 +2025-11-12 23:51:57.575584: train_loss -0.7151 +2025-11-12 23:51:57.584152: val_loss -0.7223 +2025-11-12 23:51:57.587037: Pseudo dice [np.float32(0.9198), np.float32(0.7631), np.float32(0.7409), np.float32(0.6557), np.float32(0.8652), np.float32(0.8014), np.float32(0.9014), np.float32(0.8552), np.float32(0.9815), np.float32(0.9806), np.float32(0.9688), np.float32(0.8392), np.float32(0.7619), np.float32(0.8786), np.float32(0.9604), np.float32(0.423), np.float32(0.4057)] +2025-11-12 23:51:57.590008: Epoch time: 258.76 s +2025-11-12 23:51:59.437431: +2025-11-12 23:51:59.439011: Epoch 629 +2025-11-12 23:51:59.440314: Current learning rate: 0.0041 +2025-11-12 23:56:18.024796: train_loss -0.7108 +2025-11-12 23:56:18.034791: val_loss -0.7212 +2025-11-12 23:56:18.037615: Pseudo dice [np.float32(0.9075), np.float32(0.7729), np.float32(0.6968), np.float32(0.6497), np.float32(0.8645), np.float32(0.8089), np.float32(0.8902), np.float32(0.8555), np.float32(0.9681), np.float32(0.9679), np.float32(0.97), np.float32(0.8357), np.float32(0.7506), np.float32(0.8795), np.float32(0.959), np.float32(0.465), np.float32(0.3613)] +2025-11-12 23:56:18.039510: Epoch time: 258.59 s +2025-11-12 23:56:19.896510: +2025-11-12 23:56:19.899166: Epoch 630 +2025-11-12 23:56:19.900472: Current learning rate: 0.00409 +2025-11-13 00:00:38.673130: train_loss -0.7174 +2025-11-13 00:00:38.680050: val_loss -0.7233 +2025-11-13 00:00:38.681820: Pseudo dice [np.float32(0.9228), np.float32(0.7978), np.float32(0.6933), np.float32(0.6697), np.float32(0.8718), np.float32(0.8217), np.float32(0.8811), np.float32(0.857), np.float32(0.9748), np.float32(0.9747), np.float32(0.969), np.float32(0.844), np.float32(0.7724), np.float32(0.88), np.float32(0.9601), np.float32(0.3986), np.float32(0.3329)] +2025-11-13 00:00:38.683804: Epoch time: 258.78 s +2025-11-13 00:00:40.581280: +2025-11-13 00:00:40.582695: Epoch 631 +2025-11-13 00:00:40.584167: Current learning rate: 0.00408 +2025-11-13 00:05:00.345359: train_loss -0.7156 +2025-11-13 00:05:00.353096: val_loss -0.7211 +2025-11-13 00:05:00.355218: Pseudo dice [np.float32(0.9142), np.float32(0.7777), np.float32(0.6952), np.float32(0.6385), np.float32(0.869), np.float32(0.8053), np.float32(0.9108), np.float32(0.8597), np.float32(0.9798), np.float32(0.9768), np.float32(0.9702), np.float32(0.8325), np.float32(0.761), np.float32(0.8748), np.float32(0.9662), np.float32(0.4157), np.float32(0.3833)] +2025-11-13 00:05:00.357354: Epoch time: 259.77 s +2025-11-13 00:05:02.246580: +2025-11-13 00:05:02.248154: Epoch 632 +2025-11-13 00:05:02.250576: Current learning rate: 0.00407 +2025-11-13 00:09:21.086229: train_loss -0.7128 +2025-11-13 00:09:21.093615: val_loss -0.7232 +2025-11-13 00:09:21.096177: Pseudo dice [np.float32(0.9194), np.float32(0.7937), np.float32(0.7203), np.float32(0.6628), np.float32(0.8702), np.float32(0.8114), np.float32(0.8994), np.float32(0.8534), np.float32(0.9788), np.float32(0.9794), np.float32(0.9699), np.float32(0.8207), np.float32(0.7513), np.float32(0.869), np.float32(0.9657), np.float32(0.5335), np.float32(0.3218)] +2025-11-13 00:09:21.098389: Epoch time: 258.84 s +2025-11-13 00:09:22.974933: +2025-11-13 00:09:22.977490: Epoch 633 +2025-11-13 00:09:22.980242: Current learning rate: 0.00406 +2025-11-13 00:13:41.955258: train_loss -0.7136 +2025-11-13 00:13:41.960077: val_loss -0.7273 +2025-11-13 00:13:41.961671: Pseudo dice [np.float32(0.9166), np.float32(0.7697), np.float32(0.7206), np.float32(0.6423), np.float32(0.8603), np.float32(0.8244), np.float32(0.9056), np.float32(0.8473), np.float32(0.9806), np.float32(0.9803), np.float32(0.97), np.float32(0.8272), np.float32(0.779), np.float32(0.8768), np.float32(0.9628), np.float32(0.516), np.float32(0.3911)] +2025-11-13 00:13:41.963035: Epoch time: 258.99 s +2025-11-13 00:13:43.868953: +2025-11-13 00:13:43.871762: Epoch 634 +2025-11-13 00:13:43.874064: Current learning rate: 0.00405 +2025-11-13 00:18:02.469149: train_loss -0.7097 +2025-11-13 00:18:02.476165: val_loss -0.7134 +2025-11-13 00:18:02.478640: Pseudo dice [np.float32(0.9145), np.float32(0.7504), np.float32(0.7063), np.float32(0.6576), np.float32(0.8613), np.float32(0.7865), np.float32(0.8895), np.float32(0.8682), np.float32(0.9714), np.float32(0.9665), np.float32(0.97), np.float32(0.8357), np.float32(0.7645), np.float32(0.8663), np.float32(0.9619), np.float32(0.3909), np.float32(0.3394)] +2025-11-13 00:18:02.480886: Epoch time: 258.61 s +2025-11-13 00:18:04.348795: +2025-11-13 00:18:04.350347: Epoch 635 +2025-11-13 00:18:04.351895: Current learning rate: 0.00404 +2025-11-13 00:22:22.763569: train_loss -0.7089 +2025-11-13 00:22:22.769365: val_loss -0.7125 +2025-11-13 00:22:22.771710: Pseudo dice [np.float32(0.9175), np.float32(0.8004), np.float32(0.7471), np.float32(0.6366), np.float32(0.8616), np.float32(0.8006), np.float32(0.9077), np.float32(0.8597), np.float32(0.9688), np.float32(0.9701), np.float32(0.9686), np.float32(0.8302), np.float32(0.785), np.float32(0.8704), np.float32(0.9541), np.float32(0.3006), np.float32(0.32)] +2025-11-13 00:22:22.773924: Epoch time: 258.42 s +2025-11-13 00:22:24.660552: +2025-11-13 00:22:24.662679: Epoch 636 +2025-11-13 00:22:24.664691: Current learning rate: 0.00403 +2025-11-13 00:26:43.063273: train_loss -0.7183 +2025-11-13 00:26:43.067391: val_loss -0.7103 +2025-11-13 00:26:43.069536: Pseudo dice [np.float32(0.9144), np.float32(0.7679), np.float32(0.7239), np.float32(0.6414), np.float32(0.8571), np.float32(0.796), np.float32(0.9133), np.float32(0.8421), np.float32(0.9759), np.float32(0.9764), np.float32(0.9694), np.float32(0.8233), np.float32(0.7729), np.float32(0.8725), np.float32(0.9637), np.float32(0.427), np.float32(0.2264)] +2025-11-13 00:26:43.071451: Epoch time: 258.41 s +2025-11-13 00:26:45.036299: +2025-11-13 00:26:45.038984: Epoch 637 +2025-11-13 00:26:45.040474: Current learning rate: 0.00402 +2025-11-13 00:31:03.674670: train_loss -0.7137 +2025-11-13 00:31:03.683080: val_loss -0.708 +2025-11-13 00:31:03.685650: Pseudo dice [np.float32(0.9077), np.float32(0.7877), np.float32(0.7159), np.float32(0.6405), np.float32(0.8645), np.float32(0.8122), np.float32(0.8955), np.float32(0.8568), np.float32(0.9708), np.float32(0.9723), np.float32(0.968), np.float32(0.8314), np.float32(0.7532), np.float32(0.8804), np.float32(0.9626), np.float32(0.2783), np.float32(0.3242)] +2025-11-13 00:31:03.687867: Epoch time: 258.64 s +2025-11-13 00:31:05.747443: +2025-11-13 00:31:05.748940: Epoch 638 +2025-11-13 00:31:05.750051: Current learning rate: 0.00401 +2025-11-13 00:35:24.020494: train_loss -0.7115 +2025-11-13 00:35:24.024190: val_loss -0.7166 +2025-11-13 00:35:24.025337: Pseudo dice [np.float32(0.9219), np.float32(0.7782), np.float32(0.7294), np.float32(0.6922), np.float32(0.8567), np.float32(0.7958), np.float32(0.8962), np.float32(0.8546), np.float32(0.9705), np.float32(0.9708), np.float32(0.9685), np.float32(0.8339), np.float32(0.7772), np.float32(0.8652), np.float32(0.9607), np.float32(0.4466), np.float32(0.3644)] +2025-11-13 00:35:24.026465: Epoch time: 258.28 s +2025-11-13 00:35:25.941540: +2025-11-13 00:35:25.944225: Epoch 639 +2025-11-13 00:35:25.946586: Current learning rate: 0.004 +2025-11-13 00:39:44.617429: train_loss -0.7094 +2025-11-13 00:39:44.622842: val_loss -0.6276 +2025-11-13 00:39:44.624692: Pseudo dice [np.float32(0.904), np.float32(0.737), np.float32(0.6501), np.float32(0.6539), np.float32(0.8533), np.float32(0.8063), np.float32(0.8478), np.float32(0.8566), np.float32(0.7657), np.float32(0.7713), np.float32(0.9379), np.float32(0.8139), np.float32(0.7518), np.float32(0.8583), np.float32(0.7811), np.float32(0.3787), np.float32(0.3395)] +2025-11-13 00:39:44.626503: Epoch time: 258.68 s +2025-11-13 00:39:46.515707: +2025-11-13 00:39:46.517035: Epoch 640 +2025-11-13 00:39:46.518286: Current learning rate: 0.00399 +2025-11-13 00:44:06.391218: train_loss -0.6969 +2025-11-13 00:44:06.395380: val_loss -0.7071 +2025-11-13 00:44:06.396722: Pseudo dice [np.float32(0.9191), np.float32(0.7757), np.float32(0.7006), np.float32(0.6189), np.float32(0.8654), np.float32(0.7847), np.float32(0.886), np.float32(0.8578), np.float32(0.9673), np.float32(0.9668), np.float32(0.9661), np.float32(0.8148), np.float32(0.7802), np.float32(0.8658), np.float32(0.9475), np.float32(0.4018), np.float32(0.3628)] +2025-11-13 00:44:06.397841: Epoch time: 259.88 s +2025-11-13 00:44:08.328949: +2025-11-13 00:44:08.331155: Epoch 641 +2025-11-13 00:44:08.333167: Current learning rate: 0.00398 +2025-11-13 00:48:26.980211: train_loss -0.7041 +2025-11-13 00:48:26.987784: val_loss -0.7307 +2025-11-13 00:48:26.989893: Pseudo dice [np.float32(0.9084), np.float32(0.7629), np.float32(0.6999), np.float32(0.6605), np.float32(0.8659), np.float32(0.8127), np.float32(0.9117), np.float32(0.8508), np.float32(0.9739), np.float32(0.9719), np.float32(0.9693), np.float32(0.8346), np.float32(0.764), np.float32(0.8751), np.float32(0.9586), np.float32(0.4501), np.float32(0.4537)] +2025-11-13 00:48:26.992099: Epoch time: 258.66 s +2025-11-13 00:48:28.913074: +2025-11-13 00:48:28.916246: Epoch 642 +2025-11-13 00:48:28.919073: Current learning rate: 0.00397 +2025-11-13 00:52:47.341100: train_loss -0.7074 +2025-11-13 00:52:47.346807: val_loss -0.727 +2025-11-13 00:52:47.348713: Pseudo dice [np.float32(0.9155), np.float32(0.7674), np.float32(0.7002), np.float32(0.653), np.float32(0.8559), np.float32(0.8052), np.float32(0.8971), np.float32(0.8671), np.float32(0.9763), np.float32(0.9773), np.float32(0.9694), np.float32(0.8406), np.float32(0.7536), np.float32(0.8662), np.float32(0.9627), np.float32(0.4414), np.float32(0.4611)] +2025-11-13 00:52:47.350288: Epoch time: 258.43 s +2025-11-13 00:52:49.235394: +2025-11-13 00:52:49.238086: Epoch 643 +2025-11-13 00:52:49.240622: Current learning rate: 0.00396 +2025-11-13 00:57:07.560073: train_loss -0.7042 +2025-11-13 00:57:07.567064: val_loss -0.7127 +2025-11-13 00:57:07.569506: Pseudo dice [np.float32(0.9199), np.float32(0.7797), np.float32(0.7295), np.float32(0.6621), np.float32(0.8642), np.float32(0.7992), np.float32(0.8882), np.float32(0.8617), np.float32(0.9698), np.float32(0.97), np.float32(0.9691), np.float32(0.8242), np.float32(0.7538), np.float32(0.8722), np.float32(0.9648), np.float32(0.3824), np.float32(0.2991)] +2025-11-13 00:57:07.571988: Epoch time: 258.33 s +2025-11-13 00:57:09.450268: +2025-11-13 00:57:09.452031: Epoch 644 +2025-11-13 00:57:09.453859: Current learning rate: 0.00395 +2025-11-13 01:01:27.719477: train_loss -0.7071 +2025-11-13 01:01:27.724787: val_loss -0.715 +2025-11-13 01:01:27.726584: Pseudo dice [np.float32(0.919), np.float32(0.7767), np.float32(0.6875), np.float32(0.6572), np.float32(0.8704), np.float32(0.8125), np.float32(0.9127), np.float32(0.857), np.float32(0.9606), np.float32(0.9611), np.float32(0.968), np.float32(0.822), np.float32(0.7532), np.float32(0.8766), np.float32(0.9551), np.float32(0.359), np.float32(0.3865)] +2025-11-13 01:01:27.728237: Epoch time: 258.28 s +2025-11-13 01:01:29.645643: +2025-11-13 01:01:29.648212: Epoch 645 +2025-11-13 01:01:29.650535: Current learning rate: 0.00394 +2025-11-13 01:05:47.879743: train_loss -0.7029 +2025-11-13 01:05:47.886538: val_loss -0.7288 +2025-11-13 01:05:47.888958: Pseudo dice [np.float32(0.915), np.float32(0.7764), np.float32(0.7129), np.float32(0.652), np.float32(0.8646), np.float32(0.799), np.float32(0.9066), np.float32(0.8606), np.float32(0.9766), np.float32(0.9755), np.float32(0.969), np.float32(0.8324), np.float32(0.7526), np.float32(0.8773), np.float32(0.96), np.float32(0.4241), np.float32(0.466)] +2025-11-13 01:05:47.891246: Epoch time: 258.24 s +2025-11-13 01:05:49.806631: +2025-11-13 01:05:49.809632: Epoch 646 +2025-11-13 01:05:49.812012: Current learning rate: 0.00393 +2025-11-13 01:10:08.158362: train_loss -0.712 +2025-11-13 01:10:08.166938: val_loss -0.7299 +2025-11-13 01:10:08.170377: Pseudo dice [np.float32(0.9103), np.float32(0.7963), np.float32(0.7237), np.float32(0.6574), np.float32(0.8703), np.float32(0.8143), np.float32(0.8613), np.float32(0.8614), np.float32(0.9771), np.float32(0.9775), np.float32(0.9694), np.float32(0.8272), np.float32(0.7658), np.float32(0.8814), np.float32(0.9662), np.float32(0.5362), np.float32(0.4647)] +2025-11-13 01:10:08.173277: Epoch time: 258.36 s +2025-11-13 01:10:10.053757: +2025-11-13 01:10:10.055977: Epoch 647 +2025-11-13 01:10:10.058133: Current learning rate: 0.00392 +2025-11-13 01:14:28.378144: train_loss -0.7097 +2025-11-13 01:14:28.382457: val_loss -0.7223 +2025-11-13 01:14:28.383895: Pseudo dice [np.float32(0.9162), np.float32(0.7564), np.float32(0.7187), np.float32(0.6641), np.float32(0.8619), np.float32(0.8072), np.float32(0.8975), np.float32(0.8566), np.float32(0.9741), np.float32(0.973), np.float32(0.9702), np.float32(0.8373), np.float32(0.7592), np.float32(0.8716), np.float32(0.9656), np.float32(0.3744), np.float32(0.4307)] +2025-11-13 01:14:28.385140: Epoch time: 258.33 s +2025-11-13 01:14:30.242749: +2025-11-13 01:14:30.245921: Epoch 648 +2025-11-13 01:14:30.248831: Current learning rate: 0.00391 +2025-11-13 01:18:48.444419: train_loss -0.7152 +2025-11-13 01:18:48.450335: val_loss -0.7204 +2025-11-13 01:18:48.452218: Pseudo dice [np.float32(0.9151), np.float32(0.7781), np.float32(0.7301), np.float32(0.6512), np.float32(0.8645), np.float32(0.7909), np.float32(0.9132), np.float32(0.8642), np.float32(0.9784), np.float32(0.9776), np.float32(0.9707), np.float32(0.844), np.float32(0.7698), np.float32(0.8683), np.float32(0.9647), np.float32(0.3583), np.float32(0.3777)] +2025-11-13 01:18:48.454195: Epoch time: 258.21 s +2025-11-13 01:18:50.340134: +2025-11-13 01:18:50.342268: Epoch 649 +2025-11-13 01:18:50.343605: Current learning rate: 0.0039 +2025-11-13 01:23:08.827450: train_loss -0.7126 +2025-11-13 01:23:08.833986: val_loss -0.7303 +2025-11-13 01:23:08.835630: Pseudo dice [np.float32(0.9139), np.float32(0.817), np.float32(0.7195), np.float32(0.6445), np.float32(0.8638), np.float32(0.8166), np.float32(0.9022), np.float32(0.8577), np.float32(0.9783), np.float32(0.9805), np.float32(0.971), np.float32(0.8386), np.float32(0.797), np.float32(0.8701), np.float32(0.9609), np.float32(0.435), np.float32(0.4489)] +2025-11-13 01:23:08.837184: Epoch time: 258.49 s +2025-11-13 01:23:18.059705: +2025-11-13 01:23:18.063754: Epoch 650 +2025-11-13 01:23:18.066624: Current learning rate: 0.00389 +2025-11-13 01:27:36.500919: train_loss -0.7134 +2025-11-13 01:27:36.505120: val_loss -0.7263 +2025-11-13 01:27:36.506636: Pseudo dice [np.float32(0.9143), np.float32(0.788), np.float32(0.7136), np.float32(0.6668), np.float32(0.8658), np.float32(0.7929), np.float32(0.8984), np.float32(0.8575), np.float32(0.9779), np.float32(0.9767), np.float32(0.9691), np.float32(0.8327), np.float32(0.7719), np.float32(0.8702), np.float32(0.9605), np.float32(0.426), np.float32(0.4514)] +2025-11-13 01:27:36.507771: Epoch time: 258.45 s +2025-11-13 01:27:38.359249: +2025-11-13 01:27:38.361418: Epoch 651 +2025-11-13 01:27:38.363030: Current learning rate: 0.00388 +2025-11-13 01:31:56.703133: train_loss -0.7112 +2025-11-13 01:31:56.707944: val_loss -0.7149 +2025-11-13 01:31:56.709194: Pseudo dice [np.float32(0.9209), np.float32(0.7751), np.float32(0.7249), np.float32(0.6339), np.float32(0.867), np.float32(0.8038), np.float32(0.9099), np.float32(0.8488), np.float32(0.9775), np.float32(0.9739), np.float32(0.9689), np.float32(0.8354), np.float32(0.7768), np.float32(0.879), np.float32(0.9608), np.float32(0.3917), np.float32(0.347)] +2025-11-13 01:31:56.710438: Epoch time: 258.35 s +2025-11-13 01:31:58.671686: +2025-11-13 01:31:58.674346: Epoch 652 +2025-11-13 01:31:58.676485: Current learning rate: 0.00387 +2025-11-13 01:36:17.406082: train_loss -0.713 +2025-11-13 01:36:17.411646: val_loss -0.7097 +2025-11-13 01:36:17.414154: Pseudo dice [np.float32(0.9069), np.float32(0.7796), np.float32(0.7241), np.float32(0.6362), np.float32(0.8643), np.float32(0.7967), np.float32(0.9068), np.float32(0.8559), np.float32(0.9588), np.float32(0.9573), np.float32(0.9673), np.float32(0.835), np.float32(0.7532), np.float32(0.8693), np.float32(0.9536), np.float32(0.2976), np.float32(0.3637)] +2025-11-13 01:36:17.416532: Epoch time: 258.74 s +2025-11-13 01:36:19.286141: +2025-11-13 01:36:19.287707: Epoch 653 +2025-11-13 01:36:19.289041: Current learning rate: 0.00386 +2025-11-13 01:40:38.169709: train_loss -0.7062 +2025-11-13 01:40:38.174388: val_loss -0.715 +2025-11-13 01:40:38.175618: Pseudo dice [np.float32(0.8964), np.float32(0.7665), np.float32(0.7434), np.float32(0.6484), np.float32(0.8651), np.float32(0.7978), np.float32(0.91), np.float32(0.8612), np.float32(0.9614), np.float32(0.9619), np.float32(0.9684), np.float32(0.8254), np.float32(0.7433), np.float32(0.8794), np.float32(0.9573), np.float32(0.4562), np.float32(0.3569)] +2025-11-13 01:40:38.177924: Epoch time: 258.89 s +2025-11-13 01:40:40.126033: +2025-11-13 01:40:40.129016: Epoch 654 +2025-11-13 01:40:40.131715: Current learning rate: 0.00385 +2025-11-13 01:44:59.119421: train_loss -0.711 +2025-11-13 01:44:59.129016: val_loss -0.7088 +2025-11-13 01:44:59.132396: Pseudo dice [np.float32(0.9048), np.float32(0.7915), np.float32(0.6646), np.float32(0.6373), np.float32(0.8669), np.float32(0.8008), np.float32(0.8917), np.float32(0.8439), np.float32(0.976), np.float32(0.9709), np.float32(0.9692), np.float32(0.8241), np.float32(0.7571), np.float32(0.8757), np.float32(0.9627), np.float32(0.4206), np.float32(0.3392)] +2025-11-13 01:44:59.134597: Epoch time: 259.0 s +2025-11-13 01:45:00.982679: +2025-11-13 01:45:00.984410: Epoch 655 +2025-11-13 01:45:00.986153: Current learning rate: 0.00384 +2025-11-13 01:49:19.787361: train_loss -0.7134 +2025-11-13 01:49:19.794384: val_loss -0.7241 +2025-11-13 01:49:19.796465: Pseudo dice [np.float32(0.9187), np.float32(0.7634), np.float32(0.7311), np.float32(0.6544), np.float32(0.8671), np.float32(0.8166), np.float32(0.904), np.float32(0.8568), np.float32(0.9773), np.float32(0.9793), np.float32(0.9696), np.float32(0.8369), np.float32(0.7483), np.float32(0.8764), np.float32(0.9625), np.float32(0.4514), np.float32(0.3898)] +2025-11-13 01:49:19.798166: Epoch time: 258.81 s +2025-11-13 01:49:21.760650: +2025-11-13 01:49:21.762920: Epoch 656 +2025-11-13 01:49:21.764631: Current learning rate: 0.00383 +2025-11-13 01:53:40.499934: train_loss -0.712 +2025-11-13 01:53:40.506321: val_loss -0.7199 +2025-11-13 01:53:40.508774: Pseudo dice [np.float32(0.9143), np.float32(0.7862), np.float32(0.7201), np.float32(0.6474), np.float32(0.8608), np.float32(0.8029), np.float32(0.8954), np.float32(0.8584), np.float32(0.9705), np.float32(0.9706), np.float32(0.9693), np.float32(0.8389), np.float32(0.7805), np.float32(0.8722), np.float32(0.9613), np.float32(0.4011), np.float32(0.3643)] +2025-11-13 01:53:40.511157: Epoch time: 258.75 s +2025-11-13 01:53:42.581384: +2025-11-13 01:53:42.583762: Epoch 657 +2025-11-13 01:53:42.586065: Current learning rate: 0.00382 +2025-11-13 01:58:01.253278: train_loss -0.7046 +2025-11-13 01:58:01.262262: val_loss -0.7281 +2025-11-13 01:58:01.265214: Pseudo dice [np.float32(0.9141), np.float32(0.787), np.float32(0.7334), np.float32(0.6386), np.float32(0.8656), np.float32(0.8083), np.float32(0.8869), np.float32(0.8541), np.float32(0.9775), np.float32(0.9801), np.float32(0.9697), np.float32(0.8223), np.float32(0.7869), np.float32(0.8698), np.float32(0.9655), np.float32(0.4463), np.float32(0.4462)] +2025-11-13 01:58:01.267929: Epoch time: 258.68 s +2025-11-13 01:58:03.156204: +2025-11-13 01:58:03.158066: Epoch 658 +2025-11-13 01:58:03.160177: Current learning rate: 0.00381 +2025-11-13 02:02:21.782332: train_loss -0.7162 +2025-11-13 02:02:21.790625: val_loss -0.7129 +2025-11-13 02:02:21.792682: Pseudo dice [np.float32(0.924), np.float32(0.7854), np.float32(0.7316), np.float32(0.646), np.float32(0.8588), np.float32(0.8144), np.float32(0.9015), np.float32(0.8512), np.float32(0.9675), np.float32(0.9648), np.float32(0.9687), np.float32(0.8382), np.float32(0.7806), np.float32(0.8807), np.float32(0.9532), np.float32(0.3556), np.float32(0.2692)] +2025-11-13 02:02:21.794348: Epoch time: 258.63 s +2025-11-13 02:02:23.767581: +2025-11-13 02:02:23.769634: Epoch 659 +2025-11-13 02:02:23.771080: Current learning rate: 0.0038 +2025-11-13 02:06:43.612143: train_loss -0.7161 +2025-11-13 02:06:43.617620: val_loss -0.7305 +2025-11-13 02:06:43.619247: Pseudo dice [np.float32(0.9118), np.float32(0.7966), np.float32(0.7361), np.float32(0.6588), np.float32(0.8655), np.float32(0.8214), np.float32(0.9004), np.float32(0.862), np.float32(0.9757), np.float32(0.9736), np.float32(0.9709), np.float32(0.8392), np.float32(0.7688), np.float32(0.882), np.float32(0.9635), np.float32(0.4965), np.float32(0.3553)] +2025-11-13 02:06:43.620825: Epoch time: 259.85 s +2025-11-13 02:06:45.541464: +2025-11-13 02:06:45.542927: Epoch 660 +2025-11-13 02:06:45.544659: Current learning rate: 0.00379 +2025-11-13 02:11:04.295273: train_loss -0.7159 +2025-11-13 02:11:04.302938: val_loss -0.7194 +2025-11-13 02:11:04.305126: Pseudo dice [np.float32(0.9107), np.float32(0.8191), np.float32(0.7154), np.float32(0.6645), np.float32(0.8623), np.float32(0.8149), np.float32(0.8983), np.float32(0.8476), np.float32(0.9725), np.float32(0.9708), np.float32(0.9696), np.float32(0.8286), np.float32(0.7599), np.float32(0.8775), np.float32(0.9611), np.float32(0.4098), np.float32(0.4038)] +2025-11-13 02:11:04.306947: Epoch time: 258.76 s +2025-11-13 02:11:06.188574: +2025-11-13 02:11:06.190705: Epoch 661 +2025-11-13 02:11:06.192876: Current learning rate: 0.00378 +2025-11-13 02:15:24.826094: train_loss -0.7092 +2025-11-13 02:15:24.830707: val_loss -0.7227 +2025-11-13 02:15:24.831983: Pseudo dice [np.float32(0.9132), np.float32(0.7612), np.float32(0.7252), np.float32(0.661), np.float32(0.8689), np.float32(0.7959), np.float32(0.8894), np.float32(0.8553), np.float32(0.975), np.float32(0.9797), np.float32(0.9695), np.float32(0.8311), np.float32(0.7563), np.float32(0.877), np.float32(0.963), np.float32(0.4337), np.float32(0.3529)] +2025-11-13 02:15:24.833323: Epoch time: 258.64 s +2025-11-13 02:15:26.695985: +2025-11-13 02:15:26.698234: Epoch 662 +2025-11-13 02:15:26.699737: Current learning rate: 0.00377 +2025-11-13 02:19:45.407055: train_loss -0.7097 +2025-11-13 02:19:45.415050: val_loss -0.7202 +2025-11-13 02:19:45.417678: Pseudo dice [np.float32(0.9153), np.float32(0.7738), np.float32(0.6902), np.float32(0.6491), np.float32(0.8741), np.float32(0.8133), np.float32(0.9001), np.float32(0.8623), np.float32(0.9772), np.float32(0.9749), np.float32(0.9703), np.float32(0.8387), np.float32(0.7747), np.float32(0.8769), np.float32(0.965), np.float32(0.4181), np.float32(0.4322)] +2025-11-13 02:19:45.420413: Epoch time: 258.72 s +2025-11-13 02:19:47.342546: +2025-11-13 02:19:47.344313: Epoch 663 +2025-11-13 02:19:47.346430: Current learning rate: 0.00376 +2025-11-13 02:24:05.930108: train_loss -0.715 +2025-11-13 02:24:05.936752: val_loss -0.7248 +2025-11-13 02:24:05.938752: Pseudo dice [np.float32(0.9124), np.float32(0.7996), np.float32(0.6952), np.float32(0.6545), np.float32(0.8727), np.float32(0.8001), np.float32(0.8991), np.float32(0.8677), np.float32(0.9717), np.float32(0.9778), np.float32(0.9698), np.float32(0.8308), np.float32(0.7757), np.float32(0.882), np.float32(0.9549), np.float32(0.3901), np.float32(0.4171)] +2025-11-13 02:24:05.941482: Epoch time: 258.6 s +2025-11-13 02:24:05.944170: Yayy! New best EMA pseudo Dice: 0.802299976348877 +2025-11-13 02:24:10.720108: +2025-11-13 02:24:10.722084: Epoch 664 +2025-11-13 02:24:10.723783: Current learning rate: 0.00375 +2025-11-13 02:28:29.119834: train_loss -0.7142 +2025-11-13 02:28:29.124476: val_loss -0.725 +2025-11-13 02:28:29.126073: Pseudo dice [np.float32(0.9248), np.float32(0.7726), np.float32(0.7215), np.float32(0.6523), np.float32(0.8675), np.float32(0.821), np.float32(0.9135), np.float32(0.8587), np.float32(0.9809), np.float32(0.9793), np.float32(0.9706), np.float32(0.833), np.float32(0.7517), np.float32(0.8791), np.float32(0.9675), np.float32(0.3905), np.float32(0.338)] +2025-11-13 02:28:29.127441: Epoch time: 258.41 s +2025-11-13 02:28:31.003560: +2025-11-13 02:28:31.005172: Epoch 665 +2025-11-13 02:28:31.006935: Current learning rate: 0.00374 +2025-11-13 02:32:49.665698: train_loss -0.714 +2025-11-13 02:32:49.674925: val_loss -0.7204 +2025-11-13 02:32:49.677563: Pseudo dice [np.float32(0.9056), np.float32(0.7816), np.float32(0.7232), np.float32(0.6632), np.float32(0.8599), np.float32(0.7786), np.float32(0.8729), np.float32(0.8582), np.float32(0.9787), np.float32(0.9801), np.float32(0.9692), np.float32(0.8317), np.float32(0.7814), np.float32(0.8755), np.float32(0.9668), np.float32(0.4311), np.float32(0.4419)] +2025-11-13 02:32:49.680271: Epoch time: 258.67 s +2025-11-13 02:32:49.683572: Yayy! New best EMA pseudo Dice: 0.8026000261306763 +2025-11-13 02:32:54.786179: +2025-11-13 02:32:54.788400: Epoch 666 +2025-11-13 02:32:54.789942: Current learning rate: 0.00373 +2025-11-13 02:37:13.206073: train_loss -0.7068 +2025-11-13 02:37:13.215245: val_loss -0.7254 +2025-11-13 02:37:13.217559: Pseudo dice [np.float32(0.9136), np.float32(0.7933), np.float32(0.7187), np.float32(0.6426), np.float32(0.8719), np.float32(0.7971), np.float32(0.8969), np.float32(0.8677), np.float32(0.9633), np.float32(0.9671), np.float32(0.9683), np.float32(0.8391), np.float32(0.7534), np.float32(0.8844), np.float32(0.9561), np.float32(0.408), np.float32(0.4022)] +2025-11-13 02:37:13.219733: Epoch time: 258.43 s +2025-11-13 02:37:13.221260: Yayy! New best EMA pseudo Dice: 0.8026000261306763 +2025-11-13 02:37:18.448700: +2025-11-13 02:37:18.450722: Epoch 667 +2025-11-13 02:37:18.453437: Current learning rate: 0.00372 +2025-11-13 02:41:36.925024: train_loss -0.7147 +2025-11-13 02:41:36.929495: val_loss -0.7161 +2025-11-13 02:41:36.930848: Pseudo dice [np.float32(0.9273), np.float32(0.8038), np.float32(0.7116), np.float32(0.6597), np.float32(0.8665), np.float32(0.8008), np.float32(0.9048), np.float32(0.8647), np.float32(0.9678), np.float32(0.9675), np.float32(0.9702), np.float32(0.8403), np.float32(0.7457), np.float32(0.8773), np.float32(0.9556), np.float32(0.4082), np.float32(0.3393)] +2025-11-13 02:41:36.932506: Epoch time: 258.48 s +2025-11-13 02:41:38.865561: +2025-11-13 02:41:38.868276: Epoch 668 +2025-11-13 02:41:38.870548: Current learning rate: 0.00371 +2025-11-13 02:45:58.523837: train_loss -0.7079 +2025-11-13 02:45:58.531028: val_loss -0.7174 +2025-11-13 02:45:58.532407: Pseudo dice [np.float32(0.9229), np.float32(0.772), np.float32(0.6968), np.float32(0.644), np.float32(0.8573), np.float32(0.8052), np.float32(0.9057), np.float32(0.8581), np.float32(0.9736), np.float32(0.9718), np.float32(0.9658), np.float32(0.8306), np.float32(0.7537), np.float32(0.8697), np.float32(0.9526), np.float32(0.3527), np.float32(0.4123)] +2025-11-13 02:45:58.533733: Epoch time: 259.66 s +2025-11-13 02:46:00.743648: +2025-11-13 02:46:00.746111: Epoch 669 +2025-11-13 02:46:00.748098: Current learning rate: 0.0037 +2025-11-13 02:50:19.468617: train_loss -0.7051 +2025-11-13 02:50:19.478511: val_loss -0.7116 +2025-11-13 02:50:19.481369: Pseudo dice [np.float32(0.924), np.float32(0.7627), np.float32(0.7136), np.float32(0.646), np.float32(0.8576), np.float32(0.7995), np.float32(0.9067), np.float32(0.854), np.float32(0.9727), np.float32(0.9762), np.float32(0.9679), np.float32(0.823), np.float32(0.7489), np.float32(0.8733), np.float32(0.9547), np.float32(0.3151), np.float32(0.3855)] +2025-11-13 02:50:19.483853: Epoch time: 258.73 s +2025-11-13 02:50:21.371056: +2025-11-13 02:50:21.373215: Epoch 670 +2025-11-13 02:50:21.374442: Current learning rate: 0.00369 +2025-11-13 02:54:39.920483: train_loss -0.7088 +2025-11-13 02:54:39.926470: val_loss -0.7149 +2025-11-13 02:54:39.928175: Pseudo dice [np.float32(0.919), np.float32(0.7706), np.float32(0.7109), np.float32(0.6409), np.float32(0.8665), np.float32(0.8055), np.float32(0.9133), np.float32(0.859), np.float32(0.9468), np.float32(0.9449), np.float32(0.9675), np.float32(0.8257), np.float32(0.7524), np.float32(0.8808), np.float32(0.9422), np.float32(0.4146), np.float32(0.3831)] +2025-11-13 02:54:39.929534: Epoch time: 258.55 s +2025-11-13 02:54:41.907887: +2025-11-13 02:54:41.910412: Epoch 671 +2025-11-13 02:54:41.913008: Current learning rate: 0.00368 +2025-11-13 02:59:00.362186: train_loss -0.7188 +2025-11-13 02:59:00.366769: val_loss -0.7182 +2025-11-13 02:59:00.368998: Pseudo dice [np.float32(0.9086), np.float32(0.7919), np.float32(0.7193), np.float32(0.645), np.float32(0.8704), np.float32(0.8152), np.float32(0.9073), np.float32(0.8625), np.float32(0.9728), np.float32(0.9702), np.float32(0.9697), np.float32(0.81), np.float32(0.7863), np.float32(0.88), np.float32(0.9619), np.float32(0.3386), np.float32(0.3773)] +2025-11-13 02:59:00.370633: Epoch time: 258.46 s +2025-11-13 02:59:02.380650: +2025-11-13 02:59:02.382853: Epoch 672 +2025-11-13 02:59:02.384705: Current learning rate: 0.00367 +2025-11-13 03:03:20.802231: train_loss -0.7177 +2025-11-13 03:03:20.807514: val_loss -0.7295 +2025-11-13 03:03:20.810513: Pseudo dice [np.float32(0.9116), np.float32(0.7812), np.float32(0.7146), np.float32(0.6482), np.float32(0.8704), np.float32(0.8262), np.float32(0.902), np.float32(0.8558), np.float32(0.9699), np.float32(0.9667), np.float32(0.9702), np.float32(0.8298), np.float32(0.7901), np.float32(0.8775), np.float32(0.9566), np.float32(0.3903), np.float32(0.3664)] +2025-11-13 03:03:20.813223: Epoch time: 258.43 s +2025-11-13 03:03:22.690872: +2025-11-13 03:03:22.692609: Epoch 673 +2025-11-13 03:03:22.694293: Current learning rate: 0.00366 +2025-11-13 03:07:41.152384: train_loss -0.7151 +2025-11-13 03:07:41.159008: val_loss -0.726 +2025-11-13 03:07:41.161709: Pseudo dice [np.float32(0.9137), np.float32(0.8058), np.float32(0.7325), np.float32(0.6472), np.float32(0.8601), np.float32(0.8214), np.float32(0.8977), np.float32(0.8418), np.float32(0.9765), np.float32(0.976), np.float32(0.9683), np.float32(0.8273), np.float32(0.7704), np.float32(0.8765), np.float32(0.9647), np.float32(0.423), np.float32(0.4378)] +2025-11-13 03:07:41.164218: Epoch time: 258.47 s +2025-11-13 03:07:43.052313: +2025-11-13 03:07:43.053870: Epoch 674 +2025-11-13 03:07:43.055106: Current learning rate: 0.00365 +2025-11-13 03:12:01.628453: train_loss -0.7176 +2025-11-13 03:12:01.635856: val_loss -0.7308 +2025-11-13 03:12:01.638708: Pseudo dice [np.float32(0.911), np.float32(0.7729), np.float32(0.7072), np.float32(0.6349), np.float32(0.8686), np.float32(0.8126), np.float32(0.9074), np.float32(0.8658), np.float32(0.978), np.float32(0.978), np.float32(0.9707), np.float32(0.841), np.float32(0.7849), np.float32(0.8787), np.float32(0.9595), np.float32(0.4326), np.float32(0.4127)] +2025-11-13 03:12:01.641178: Epoch time: 258.58 s +2025-11-13 03:12:03.523557: +2025-11-13 03:12:03.525593: Epoch 675 +2025-11-13 03:12:03.526978: Current learning rate: 0.00364 +2025-11-13 03:16:21.838488: train_loss -0.7112 +2025-11-13 03:16:21.843688: val_loss -0.7154 +2025-11-13 03:16:21.845061: Pseudo dice [np.float32(0.9231), np.float32(0.7784), np.float32(0.7403), np.float32(0.6408), np.float32(0.8667), np.float32(0.8216), np.float32(0.8919), np.float32(0.8792), np.float32(0.9672), np.float32(0.9667), np.float32(0.9709), np.float32(0.8389), np.float32(0.7625), np.float32(0.8727), np.float32(0.9572), np.float32(0.4042), np.float32(0.2708)] +2025-11-13 03:16:21.846975: Epoch time: 258.32 s +2025-11-13 03:16:23.781950: +2025-11-13 03:16:23.783914: Epoch 676 +2025-11-13 03:16:23.785485: Current learning rate: 0.00363 +2025-11-13 03:20:42.406516: train_loss -0.7145 +2025-11-13 03:20:42.414279: val_loss -0.7138 +2025-11-13 03:20:42.416617: Pseudo dice [np.float32(0.9136), np.float32(0.7756), np.float32(0.6884), np.float32(0.6507), np.float32(0.868), np.float32(0.8049), np.float32(0.9064), np.float32(0.8548), np.float32(0.9778), np.float32(0.9778), np.float32(0.9712), np.float32(0.8364), np.float32(0.7554), np.float32(0.8756), np.float32(0.9623), np.float32(0.4235), np.float32(0.3489)] +2025-11-13 03:20:42.418811: Epoch time: 258.63 s +2025-11-13 03:20:44.381759: +2025-11-13 03:20:44.383207: Epoch 677 +2025-11-13 03:20:44.384650: Current learning rate: 0.00362 +2025-11-13 03:25:04.256116: train_loss -0.7155 +2025-11-13 03:25:04.260929: val_loss -0.7173 +2025-11-13 03:25:04.262499: Pseudo dice [np.float32(0.899), np.float32(0.7736), np.float32(0.7189), np.float32(0.6441), np.float32(0.8559), np.float32(0.799), np.float32(0.9041), np.float32(0.8627), np.float32(0.9711), np.float32(0.9718), np.float32(0.9696), np.float32(0.8377), np.float32(0.7618), np.float32(0.8697), np.float32(0.9627), np.float32(0.3329), np.float32(0.4517)] +2025-11-13 03:25:04.264102: Epoch time: 259.89 s +2025-11-13 03:25:06.194665: +2025-11-13 03:25:06.198008: Epoch 678 +2025-11-13 03:25:06.199937: Current learning rate: 0.00361 +2025-11-13 03:29:24.666879: train_loss -0.7103 +2025-11-13 03:29:24.671095: val_loss -0.7269 +2025-11-13 03:29:24.672225: Pseudo dice [np.float32(0.9168), np.float32(0.8015), np.float32(0.7376), np.float32(0.6495), np.float32(0.8635), np.float32(0.781), np.float32(0.9104), np.float32(0.8598), np.float32(0.9712), np.float32(0.971), np.float32(0.9705), np.float32(0.8379), np.float32(0.7617), np.float32(0.8747), np.float32(0.9628), np.float32(0.3986), np.float32(0.3715)] +2025-11-13 03:29:24.673494: Epoch time: 258.48 s +2025-11-13 03:29:26.647935: +2025-11-13 03:29:26.650020: Epoch 679 +2025-11-13 03:29:26.651150: Current learning rate: 0.0036 +2025-11-13 03:33:45.038948: train_loss -0.7154 +2025-11-13 03:33:45.042564: val_loss -0.7242 +2025-11-13 03:33:45.043692: Pseudo dice [np.float32(0.9101), np.float32(0.7873), np.float32(0.7341), np.float32(0.655), np.float32(0.8661), np.float32(0.8269), np.float32(0.9091), np.float32(0.8607), np.float32(0.9763), np.float32(0.9762), np.float32(0.9702), np.float32(0.828), np.float32(0.7325), np.float32(0.8741), np.float32(0.9627), np.float32(0.3928), np.float32(0.374)] +2025-11-13 03:33:45.045012: Epoch time: 258.4 s +2025-11-13 03:33:46.968684: +2025-11-13 03:33:46.970063: Epoch 680 +2025-11-13 03:33:46.971228: Current learning rate: 0.00359 +2025-11-13 03:38:05.632684: train_loss -0.721 +2025-11-13 03:38:05.637118: val_loss -0.7202 +2025-11-13 03:38:05.638225: Pseudo dice [np.float32(0.9162), np.float32(0.7339), np.float32(0.7095), np.float32(0.6438), np.float32(0.8657), np.float32(0.8075), np.float32(0.8997), np.float32(0.8495), np.float32(0.9758), np.float32(0.9734), np.float32(0.9678), np.float32(0.823), np.float32(0.7643), np.float32(0.8776), np.float32(0.9637), np.float32(0.5212), np.float32(0.3381)] +2025-11-13 03:38:05.639554: Epoch time: 258.67 s +2025-11-13 03:38:07.655948: +2025-11-13 03:38:07.657632: Epoch 681 +2025-11-13 03:38:07.659164: Current learning rate: 0.00358 +2025-11-13 03:42:26.043776: train_loss -0.7197 +2025-11-13 03:42:26.047934: val_loss -0.7309 +2025-11-13 03:42:26.049257: Pseudo dice [np.float32(0.9159), np.float32(0.7966), np.float32(0.7221), np.float32(0.683), np.float32(0.8719), np.float32(0.8127), np.float32(0.8975), np.float32(0.8583), np.float32(0.9751), np.float32(0.978), np.float32(0.9711), np.float32(0.8432), np.float32(0.7889), np.float32(0.8787), np.float32(0.9605), np.float32(0.4594), np.float32(0.3313)] +2025-11-13 03:42:26.050495: Epoch time: 258.39 s +2025-11-13 03:42:27.887437: +2025-11-13 03:42:27.889005: Epoch 682 +2025-11-13 03:42:27.890443: Current learning rate: 0.00357 +2025-11-13 03:46:46.358727: train_loss -0.7174 +2025-11-13 03:46:46.363345: val_loss -0.7274 +2025-11-13 03:46:46.364797: Pseudo dice [np.float32(0.9087), np.float32(0.7761), np.float32(0.7189), np.float32(0.6695), np.float32(0.8688), np.float32(0.8066), np.float32(0.9053), np.float32(0.8629), np.float32(0.9787), np.float32(0.9778), np.float32(0.9703), np.float32(0.8433), np.float32(0.7853), np.float32(0.8751), np.float32(0.9627), np.float32(0.4356), np.float32(0.4083)] +2025-11-13 03:46:46.366229: Epoch time: 258.48 s +2025-11-13 03:46:46.367416: Yayy! New best EMA pseudo Dice: 0.8026999831199646 +2025-11-13 03:46:51.167457: +2025-11-13 03:46:51.168960: Epoch 683 +2025-11-13 03:46:51.170063: Current learning rate: 0.00356 +2025-11-13 03:51:09.668577: train_loss -0.7163 +2025-11-13 03:51:09.673290: val_loss -0.7218 +2025-11-13 03:51:09.674661: Pseudo dice [np.float32(0.9235), np.float32(0.7726), np.float32(0.7101), np.float32(0.6459), np.float32(0.8658), np.float32(0.8106), np.float32(0.9021), np.float32(0.8633), np.float32(0.9756), np.float32(0.9769), np.float32(0.9692), np.float32(0.8256), np.float32(0.7445), np.float32(0.8833), np.float32(0.9639), np.float32(0.3786), np.float32(0.4268)] +2025-11-13 03:51:09.675879: Epoch time: 258.51 s +2025-11-13 03:51:11.557389: +2025-11-13 03:51:11.558861: Epoch 684 +2025-11-13 03:51:11.560557: Current learning rate: 0.00355 +2025-11-13 03:55:29.921665: train_loss -0.7212 +2025-11-13 03:55:29.925771: val_loss -0.7189 +2025-11-13 03:55:29.927275: Pseudo dice [np.float32(0.916), np.float32(0.7772), np.float32(0.7437), np.float32(0.6443), np.float32(0.87), np.float32(0.8081), np.float32(0.8747), np.float32(0.8649), np.float32(0.9766), np.float32(0.9808), np.float32(0.9703), np.float32(0.8345), np.float32(0.7705), np.float32(0.883), np.float32(0.9624), np.float32(0.4586), np.float32(0.3539)] +2025-11-13 03:55:29.928506: Epoch time: 258.37 s +2025-11-13 03:55:29.929873: Yayy! New best EMA pseudo Dice: 0.8029000163078308 +2025-11-13 03:55:35.008566: +2025-11-13 03:55:35.010016: Epoch 685 +2025-11-13 03:55:35.011093: Current learning rate: 0.00354 +2025-11-13 03:59:53.669308: train_loss -0.7128 +2025-11-13 03:59:53.673592: val_loss -0.7356 +2025-11-13 03:59:53.674976: Pseudo dice [np.float32(0.9238), np.float32(0.7797), np.float32(0.7216), np.float32(0.6646), np.float32(0.8601), np.float32(0.7942), np.float32(0.9137), np.float32(0.8593), np.float32(0.9774), np.float32(0.9763), np.float32(0.9698), np.float32(0.8472), np.float32(0.7625), np.float32(0.8769), np.float32(0.9645), np.float32(0.4653), np.float32(0.4183)] +2025-11-13 03:59:53.676771: Epoch time: 258.67 s +2025-11-13 03:59:53.677813: Yayy! New best EMA pseudo Dice: 0.8036999702453613 +2025-11-13 03:59:58.852897: +2025-11-13 03:59:58.854480: Epoch 686 +2025-11-13 03:59:58.855736: Current learning rate: 0.00353 +2025-11-13 04:04:18.960258: train_loss -0.715 +2025-11-13 04:04:18.964767: val_loss -0.7136 +2025-11-13 04:04:18.966384: Pseudo dice [np.float32(0.9079), np.float32(0.7605), np.float32(0.6787), np.float32(0.6513), np.float32(0.862), np.float32(0.7964), np.float32(0.8979), np.float32(0.8544), np.float32(0.9779), np.float32(0.9819), np.float32(0.9698), np.float32(0.828), np.float32(0.7731), np.float32(0.8706), np.float32(0.966), np.float32(0.3823), np.float32(0.4069)] +2025-11-13 04:04:18.967833: Epoch time: 260.11 s +2025-11-13 04:04:21.113752: +2025-11-13 04:04:21.115444: Epoch 687 +2025-11-13 04:04:21.117018: Current learning rate: 0.00352 +2025-11-13 04:08:39.637906: train_loss -0.7176 +2025-11-13 04:08:39.642240: val_loss -0.7238 +2025-11-13 04:08:39.643775: Pseudo dice [np.float32(0.9218), np.float32(0.7849), np.float32(0.7243), np.float32(0.6639), np.float32(0.864), np.float32(0.7948), np.float32(0.892), np.float32(0.8661), np.float32(0.9744), np.float32(0.9734), np.float32(0.9687), np.float32(0.8276), np.float32(0.771), np.float32(0.8813), np.float32(0.9605), np.float32(0.4228), np.float32(0.341)] +2025-11-13 04:08:39.645075: Epoch time: 258.53 s +2025-11-13 04:08:41.587783: +2025-11-13 04:08:41.589283: Epoch 688 +2025-11-13 04:08:41.590756: Current learning rate: 0.00351 +2025-11-13 04:13:00.434123: train_loss -0.7121 +2025-11-13 04:13:00.439647: val_loss -0.7212 +2025-11-13 04:13:00.441084: Pseudo dice [np.float32(0.9118), np.float32(0.7941), np.float32(0.7247), np.float32(0.6643), np.float32(0.867), np.float32(0.7973), np.float32(0.8996), np.float32(0.8531), np.float32(0.9709), np.float32(0.9695), np.float32(0.9688), np.float32(0.828), np.float32(0.7517), np.float32(0.878), np.float32(0.9548), np.float32(0.4403), np.float32(0.3493)] +2025-11-13 04:13:00.442430: Epoch time: 258.85 s +2025-11-13 04:13:02.395437: +2025-11-13 04:13:02.397081: Epoch 689 +2025-11-13 04:13:02.398902: Current learning rate: 0.0035 +2025-11-13 04:17:21.278183: train_loss -0.7167 +2025-11-13 04:17:21.286589: val_loss -0.7272 +2025-11-13 04:17:21.288976: Pseudo dice [np.float32(0.9157), np.float32(0.7935), np.float32(0.712), np.float32(0.6706), np.float32(0.8689), np.float32(0.8028), np.float32(0.9104), np.float32(0.8635), np.float32(0.9676), np.float32(0.9639), np.float32(0.9686), np.float32(0.8385), np.float32(0.7557), np.float32(0.8821), np.float32(0.9598), np.float32(0.3577), np.float32(0.4421)] +2025-11-13 04:17:21.291766: Epoch time: 258.89 s +2025-11-13 04:17:23.339183: +2025-11-13 04:17:23.340652: Epoch 690 +2025-11-13 04:17:23.342009: Current learning rate: 0.00349 +2025-11-13 04:21:41.950591: train_loss -0.7166 +2025-11-13 04:21:41.954579: val_loss -0.7225 +2025-11-13 04:21:41.955860: Pseudo dice [np.float32(0.9006), np.float32(0.795), np.float32(0.7282), np.float32(0.6821), np.float32(0.8704), np.float32(0.8078), np.float32(0.8975), np.float32(0.8474), np.float32(0.9737), np.float32(0.9722), np.float32(0.9701), np.float32(0.833), np.float32(0.7595), np.float32(0.8754), np.float32(0.9677), np.float32(0.4976), np.float32(0.3699)] +2025-11-13 04:21:41.957226: Epoch time: 258.62 s +2025-11-13 04:21:43.852212: +2025-11-13 04:21:43.853881: Epoch 691 +2025-11-13 04:21:43.855695: Current learning rate: 0.00348 +2025-11-13 04:26:02.748597: train_loss -0.7159 +2025-11-13 04:26:02.752495: val_loss -0.7355 +2025-11-13 04:26:02.753718: Pseudo dice [np.float32(0.9159), np.float32(0.8041), np.float32(0.7237), np.float32(0.6751), np.float32(0.8736), np.float32(0.8171), np.float32(0.9091), np.float32(0.8641), np.float32(0.9783), np.float32(0.9788), np.float32(0.9707), np.float32(0.8566), np.float32(0.7645), np.float32(0.8846), np.float32(0.9648), np.float32(0.3917), np.float32(0.4384)] +2025-11-13 04:26:02.754798: Epoch time: 258.9 s +2025-11-13 04:26:02.755846: Yayy! New best EMA pseudo Dice: 0.8044000267982483 +2025-11-13 04:26:07.591423: +2025-11-13 04:26:07.593140: Epoch 692 +2025-11-13 04:26:07.594564: Current learning rate: 0.00346 +2025-11-13 04:30:26.232640: train_loss -0.7158 +2025-11-13 04:30:26.237716: val_loss -0.7174 +2025-11-13 04:30:26.238894: Pseudo dice [np.float32(0.9214), np.float32(0.8008), np.float32(0.7475), np.float32(0.6209), np.float32(0.874), np.float32(0.8095), np.float32(0.8861), np.float32(0.8609), np.float32(0.9728), np.float32(0.9749), np.float32(0.9691), np.float32(0.8325), np.float32(0.7694), np.float32(0.8826), np.float32(0.9599), np.float32(0.3872), np.float32(0.3373)] +2025-11-13 04:30:26.240587: Epoch time: 258.65 s +2025-11-13 04:30:28.170792: +2025-11-13 04:30:28.172156: Epoch 693 +2025-11-13 04:30:28.173612: Current learning rate: 0.00345 +2025-11-13 04:34:46.773513: train_loss -0.7182 +2025-11-13 04:34:46.777965: val_loss -0.7272 +2025-11-13 04:34:46.779534: Pseudo dice [np.float32(0.9125), np.float32(0.779), np.float32(0.7286), np.float32(0.6439), np.float32(0.8573), np.float32(0.801), np.float32(0.9023), np.float32(0.8691), np.float32(0.9764), np.float32(0.9773), np.float32(0.9683), np.float32(0.8286), np.float32(0.7713), np.float32(0.8771), np.float32(0.9621), np.float32(0.5265), np.float32(0.4438)] +2025-11-13 04:34:46.780782: Epoch time: 258.61 s +2025-11-13 04:34:46.781848: Yayy! New best EMA pseudo Dice: 0.8048999905586243 +2025-11-13 04:34:51.994841: +2025-11-13 04:34:51.996186: Epoch 694 +2025-11-13 04:34:51.997933: Current learning rate: 0.00344 +2025-11-13 04:39:10.359270: train_loss -0.7185 +2025-11-13 04:39:10.363158: val_loss -0.7189 +2025-11-13 04:39:10.364311: Pseudo dice [np.float32(0.9037), np.float32(0.7704), np.float32(0.7348), np.float32(0.6782), np.float32(0.8623), np.float32(0.8026), np.float32(0.9009), np.float32(0.8529), np.float32(0.9789), np.float32(0.979), np.float32(0.9688), np.float32(0.8392), np.float32(0.7369), np.float32(0.8816), np.float32(0.9593), np.float32(0.4082), np.float32(0.4284)] +2025-11-13 04:39:10.365479: Epoch time: 258.37 s +2025-11-13 04:39:10.366503: Yayy! New best EMA pseudo Dice: 0.8050000071525574 +2025-11-13 04:39:17.125222: +2025-11-13 04:39:17.126821: Epoch 695 +2025-11-13 04:39:17.128134: Current learning rate: 0.00343 +2025-11-13 04:43:35.788548: train_loss -0.7164 +2025-11-13 04:43:35.792459: val_loss -0.7258 +2025-11-13 04:43:35.793727: Pseudo dice [np.float32(0.9125), np.float32(0.7918), np.float32(0.7417), np.float32(0.6688), np.float32(0.8703), np.float32(0.7825), np.float32(0.8983), np.float32(0.8672), np.float32(0.9778), np.float32(0.9749), np.float32(0.9707), np.float32(0.8341), np.float32(0.7346), np.float32(0.8798), np.float32(0.9651), np.float32(0.3863), np.float32(0.3281)] +2025-11-13 04:43:35.795164: Epoch time: 258.67 s +2025-11-13 04:43:37.692544: +2025-11-13 04:43:37.694181: Epoch 696 +2025-11-13 04:43:37.695527: Current learning rate: 0.00342 +2025-11-13 04:47:56.262536: train_loss -0.7114 +2025-11-13 04:47:56.266991: val_loss -0.7343 +2025-11-13 04:47:56.268203: Pseudo dice [np.float32(0.9142), np.float32(0.7114), np.float32(0.7455), np.float32(0.6205), np.float32(0.8715), np.float32(0.7923), np.float32(0.9004), np.float32(0.8525), np.float32(0.9764), np.float32(0.9766), np.float32(0.9685), np.float32(0.8398), np.float32(0.7801), np.float32(0.8807), np.float32(0.9613), np.float32(0.505), np.float32(0.4688)] +2025-11-13 04:47:56.269674: Epoch time: 258.58 s +2025-11-13 04:47:58.141719: +2025-11-13 04:47:58.143205: Epoch 697 +2025-11-13 04:47:58.144692: Current learning rate: 0.00341 +2025-11-13 04:52:16.881785: train_loss -0.7067 +2025-11-13 04:52:16.885721: val_loss -0.7158 +2025-11-13 04:52:16.887256: Pseudo dice [np.float32(0.9049), np.float32(0.7757), np.float32(0.7063), np.float32(0.623), np.float32(0.8639), np.float32(0.8222), np.float32(0.9104), np.float32(0.8617), np.float32(0.9687), np.float32(0.9665), np.float32(0.968), np.float32(0.8457), np.float32(0.7629), np.float32(0.878), np.float32(0.9584), np.float32(0.2917), np.float32(0.3528)] +2025-11-13 04:52:16.888640: Epoch time: 258.75 s +2025-11-13 04:52:18.751864: +2025-11-13 04:52:18.753315: Epoch 698 +2025-11-13 04:52:18.754556: Current learning rate: 0.0034 +2025-11-13 04:56:37.407371: train_loss -0.7121 +2025-11-13 04:56:37.411649: val_loss -0.7169 +2025-11-13 04:56:37.412893: Pseudo dice [np.float32(0.9136), np.float32(0.7822), np.float32(0.7417), np.float32(0.6696), np.float32(0.8679), np.float32(0.8002), np.float32(0.8884), np.float32(0.8586), np.float32(0.9715), np.float32(0.9678), np.float32(0.9696), np.float32(0.8384), np.float32(0.7858), np.float32(0.8778), np.float32(0.9595), np.float32(0.3601), np.float32(0.3343)] +2025-11-13 04:56:37.414106: Epoch time: 258.66 s +2025-11-13 04:56:39.350461: +2025-11-13 04:56:39.352181: Epoch 699 +2025-11-13 04:56:39.353431: Current learning rate: 0.00339 +2025-11-13 05:00:58.193993: train_loss -0.7126 +2025-11-13 05:00:58.198453: val_loss -0.733 +2025-11-13 05:00:58.199654: Pseudo dice [np.float32(0.9179), np.float32(0.7695), np.float32(0.7312), np.float32(0.6585), np.float32(0.8677), np.float32(0.7929), np.float32(0.9054), np.float32(0.8694), np.float32(0.9801), np.float32(0.9779), np.float32(0.9699), np.float32(0.8249), np.float32(0.7772), np.float32(0.8749), np.float32(0.9654), np.float32(0.4591), np.float32(0.4338)] +2025-11-13 05:00:58.200883: Epoch time: 258.85 s +2025-11-13 05:01:03.076584: +2025-11-13 05:01:03.078099: Epoch 700 +2025-11-13 05:01:03.079226: Current learning rate: 0.00338 +2025-11-13 05:05:21.641977: train_loss -0.7218 +2025-11-13 05:05:21.646559: val_loss -0.7343 +2025-11-13 05:05:21.647856: Pseudo dice [np.float32(0.9113), np.float32(0.7989), np.float32(0.7247), np.float32(0.6624), np.float32(0.8682), np.float32(0.7986), np.float32(0.9119), np.float32(0.8739), np.float32(0.9646), np.float32(0.9688), np.float32(0.9701), np.float32(0.8406), np.float32(0.7845), np.float32(0.8825), np.float32(0.956), np.float32(0.509), np.float32(0.4587)] +2025-11-13 05:05:21.649204: Epoch time: 258.57 s +2025-11-13 05:05:21.650398: Yayy! New best EMA pseudo Dice: 0.8051999807357788 +2025-11-13 05:05:26.622844: +2025-11-13 05:05:26.624313: Epoch 701 +2025-11-13 05:05:26.625741: Current learning rate: 0.00337 +2025-11-13 05:09:45.340693: train_loss -0.7074 +2025-11-13 05:09:45.345400: val_loss -0.7192 +2025-11-13 05:09:45.346879: Pseudo dice [np.float32(0.9245), np.float32(0.7814), np.float32(0.714), np.float32(0.6307), np.float32(0.8639), np.float32(0.8071), np.float32(0.8893), np.float32(0.8615), np.float32(0.978), np.float32(0.978), np.float32(0.9698), np.float32(0.8325), np.float32(0.7555), np.float32(0.8746), np.float32(0.964), np.float32(0.4553), np.float32(0.2701)] +2025-11-13 05:09:45.348425: Epoch time: 258.72 s +2025-11-13 05:09:47.208516: +2025-11-13 05:09:47.210118: Epoch 702 +2025-11-13 05:09:47.211464: Current learning rate: 0.00336 +2025-11-13 05:14:05.745862: train_loss -0.713 +2025-11-13 05:14:05.749776: val_loss -0.7272 +2025-11-13 05:14:05.750945: Pseudo dice [np.float32(0.9048), np.float32(0.7653), np.float32(0.6984), np.float32(0.6694), np.float32(0.8623), np.float32(0.8092), np.float32(0.9091), np.float32(0.8684), np.float32(0.9789), np.float32(0.9798), np.float32(0.9687), np.float32(0.8391), np.float32(0.7638), np.float32(0.8775), np.float32(0.9662), np.float32(0.4382), np.float32(0.3609)] +2025-11-13 05:14:05.752435: Epoch time: 258.54 s +2025-11-13 05:14:07.703740: +2025-11-13 05:14:07.705151: Epoch 703 +2025-11-13 05:14:07.706443: Current learning rate: 0.00335 +2025-11-13 05:18:26.387039: train_loss -0.7159 +2025-11-13 05:18:26.390657: val_loss -0.7165 +2025-11-13 05:18:26.391963: Pseudo dice [np.float32(0.9017), np.float32(0.7907), np.float32(0.7319), np.float32(0.6599), np.float32(0.8626), np.float32(0.8198), np.float32(0.89), np.float32(0.8546), np.float32(0.9767), np.float32(0.9768), np.float32(0.9675), np.float32(0.833), np.float32(0.7551), np.float32(0.8722), np.float32(0.9605), np.float32(0.3724), np.float32(0.3456)] +2025-11-13 05:18:26.393135: Epoch time: 258.69 s +2025-11-13 05:18:29.926185: +2025-11-13 05:18:29.927633: Epoch 704 +2025-11-13 05:18:29.928963: Current learning rate: 0.00334 +2025-11-13 05:22:48.545300: train_loss -0.7103 +2025-11-13 05:22:48.549266: val_loss -0.7128 +2025-11-13 05:22:48.550673: Pseudo dice [np.float32(0.9076), np.float32(0.784), np.float32(0.6955), np.float32(0.6464), np.float32(0.858), np.float32(0.8081), np.float32(0.8587), np.float32(0.8616), np.float32(0.973), np.float32(0.9659), np.float32(0.9696), np.float32(0.8347), np.float32(0.7634), np.float32(0.8717), np.float32(0.9613), np.float32(0.4156), np.float32(0.2899)] +2025-11-13 05:22:48.552116: Epoch time: 258.62 s +2025-11-13 05:22:50.402767: +2025-11-13 05:22:50.404306: Epoch 705 +2025-11-13 05:22:50.405545: Current learning rate: 0.00333 +2025-11-13 05:27:09.007099: train_loss -0.7145 +2025-11-13 05:27:09.011016: val_loss -0.7112 +2025-11-13 05:27:09.012591: Pseudo dice [np.float32(0.9096), np.float32(0.7715), np.float32(0.6783), np.float32(0.6913), np.float32(0.8701), np.float32(0.8099), np.float32(0.8974), np.float32(0.8609), np.float32(0.9741), np.float32(0.9732), np.float32(0.9698), np.float32(0.842), np.float32(0.7644), np.float32(0.8792), np.float32(0.9587), np.float32(0.2981), np.float32(0.2776)] +2025-11-13 05:27:09.013881: Epoch time: 258.61 s +2025-11-13 05:27:10.948595: +2025-11-13 05:27:10.949778: Epoch 706 +2025-11-13 05:27:10.951027: Current learning rate: 0.00332 +2025-11-13 05:31:29.581485: train_loss -0.7137 +2025-11-13 05:31:29.585367: val_loss -0.7252 +2025-11-13 05:31:29.587030: Pseudo dice [np.float32(0.9173), np.float32(0.7923), np.float32(0.7443), np.float32(0.6515), np.float32(0.8708), np.float32(0.7981), np.float32(0.9137), np.float32(0.8632), np.float32(0.9751), np.float32(0.9749), np.float32(0.9697), np.float32(0.8387), np.float32(0.7528), np.float32(0.8794), np.float32(0.9629), np.float32(0.4443), np.float32(0.398)] +2025-11-13 05:31:29.588528: Epoch time: 258.64 s +2025-11-13 05:31:31.478095: +2025-11-13 05:31:31.480295: Epoch 707 +2025-11-13 05:31:31.481775: Current learning rate: 0.00331 +2025-11-13 05:35:49.997895: train_loss -0.713 +2025-11-13 05:35:50.002105: val_loss -0.7142 +2025-11-13 05:35:50.003304: Pseudo dice [np.float32(0.9138), np.float32(0.7812), np.float32(0.7324), np.float32(0.6686), np.float32(0.8646), np.float32(0.8096), np.float32(0.9128), np.float32(0.8463), np.float32(0.9791), np.float32(0.9776), np.float32(0.9689), np.float32(0.8358), np.float32(0.7689), np.float32(0.8767), np.float32(0.9643), np.float32(0.3085), np.float32(0.3163)] +2025-11-13 05:35:50.004748: Epoch time: 258.52 s +2025-11-13 05:35:51.917696: +2025-11-13 05:35:51.919047: Epoch 708 +2025-11-13 05:35:51.920277: Current learning rate: 0.0033 +2025-11-13 05:40:10.567464: train_loss -0.7193 +2025-11-13 05:40:10.571120: val_loss -0.7158 +2025-11-13 05:40:10.573128: Pseudo dice [np.float32(0.9076), np.float32(0.7716), np.float32(0.7165), np.float32(0.6819), np.float32(0.8688), np.float32(0.8109), np.float32(0.8774), np.float32(0.8558), np.float32(0.9747), np.float32(0.9727), np.float32(0.9696), np.float32(0.8416), np.float32(0.7583), np.float32(0.8777), np.float32(0.9622), np.float32(0.3227), np.float32(0.3164)] +2025-11-13 05:40:10.574250: Epoch time: 258.66 s +2025-11-13 05:40:12.520480: +2025-11-13 05:40:12.522100: Epoch 709 +2025-11-13 05:40:12.523757: Current learning rate: 0.00329 +2025-11-13 05:44:31.297834: train_loss -0.7165 +2025-11-13 05:44:31.302017: val_loss -0.7186 +2025-11-13 05:44:31.303537: Pseudo dice [np.float32(0.907), np.float32(0.7748), np.float32(0.7111), np.float32(0.64), np.float32(0.8594), np.float32(0.8005), np.float32(0.8949), np.float32(0.8499), np.float32(0.9693), np.float32(0.9689), np.float32(0.9693), np.float32(0.829), np.float32(0.7497), np.float32(0.8751), np.float32(0.9616), np.float32(0.3743), np.float32(0.3746)] +2025-11-13 05:44:31.304623: Epoch time: 258.78 s +2025-11-13 05:44:33.161252: +2025-11-13 05:44:33.162619: Epoch 710 +2025-11-13 05:44:33.164071: Current learning rate: 0.00328 +2025-11-13 05:48:51.637612: train_loss -0.714 +2025-11-13 05:48:51.643382: val_loss -0.7188 +2025-11-13 05:48:51.645031: Pseudo dice [np.float32(0.923), np.float32(0.7845), np.float32(0.7281), np.float32(0.6611), np.float32(0.8679), np.float32(0.8081), np.float32(0.9013), np.float32(0.8566), np.float32(0.9667), np.float32(0.9668), np.float32(0.9704), np.float32(0.8375), np.float32(0.734), np.float32(0.8826), np.float32(0.9603), np.float32(0.3925), np.float32(0.3529)] +2025-11-13 05:48:51.646207: Epoch time: 258.48 s +2025-11-13 05:48:53.554641: +2025-11-13 05:48:53.556201: Epoch 711 +2025-11-13 05:48:53.557550: Current learning rate: 0.00327 +2025-11-13 05:53:12.078805: train_loss -0.7035 +2025-11-13 05:53:12.082905: val_loss -0.7121 +2025-11-13 05:53:12.084194: Pseudo dice [np.float32(0.9017), np.float32(0.775), np.float32(0.7427), np.float32(0.66), np.float32(0.8638), np.float32(0.8157), np.float32(0.8887), np.float32(0.8594), np.float32(0.9566), np.float32(0.9592), np.float32(0.9689), np.float32(0.8392), np.float32(0.7621), np.float32(0.8728), np.float32(0.9554), np.float32(0.5361), np.float32(0.3671)] +2025-11-13 05:53:12.085756: Epoch time: 258.53 s +2025-11-13 05:53:13.983523: +2025-11-13 05:53:13.984953: Epoch 712 +2025-11-13 05:53:13.986275: Current learning rate: 0.00326 +2025-11-13 05:57:32.465031: train_loss -0.7101 +2025-11-13 05:57:32.469521: val_loss -0.7189 +2025-11-13 05:57:32.471161: Pseudo dice [np.float32(0.9082), np.float32(0.7879), np.float32(0.7448), np.float32(0.6452), np.float32(0.8625), np.float32(0.8108), np.float32(0.8742), np.float32(0.8577), np.float32(0.9739), np.float32(0.973), np.float32(0.968), np.float32(0.8379), np.float32(0.774), np.float32(0.8684), np.float32(0.9611), np.float32(0.4436), np.float32(0.2796)] +2025-11-13 05:57:32.472883: Epoch time: 258.49 s +2025-11-13 05:57:34.393256: +2025-11-13 05:57:34.395036: Epoch 713 +2025-11-13 05:57:34.396248: Current learning rate: 0.00325 +2025-11-13 06:01:54.281705: train_loss -0.7081 +2025-11-13 06:01:54.285734: val_loss -0.7133 +2025-11-13 06:01:54.286947: Pseudo dice [np.float32(0.9074), np.float32(0.7759), np.float32(0.7082), np.float32(0.6608), np.float32(0.8604), np.float32(0.7986), np.float32(0.9135), np.float32(0.8502), np.float32(0.9678), np.float32(0.9699), np.float32(0.968), np.float32(0.832), np.float32(0.779), np.float32(0.8654), np.float32(0.9549), np.float32(0.2677), np.float32(0.3713)] +2025-11-13 06:01:54.288165: Epoch time: 259.89 s +2025-11-13 06:01:56.156680: +2025-11-13 06:01:56.158321: Epoch 714 +2025-11-13 06:01:56.159821: Current learning rate: 0.00324 +2025-11-13 06:06:14.751859: train_loss -0.7081 +2025-11-13 06:06:14.755915: val_loss -0.7225 +2025-11-13 06:06:14.757287: Pseudo dice [np.float32(0.9173), np.float32(0.7799), np.float32(0.7399), np.float32(0.6485), np.float32(0.8659), np.float32(0.7936), np.float32(0.9084), np.float32(0.8608), np.float32(0.9515), np.float32(0.9558), np.float32(0.9684), np.float32(0.8336), np.float32(0.7837), np.float32(0.878), np.float32(0.9553), np.float32(0.4414), np.float32(0.3492)] +2025-11-13 06:06:14.758445: Epoch time: 258.6 s +2025-11-13 06:06:16.705829: +2025-11-13 06:06:16.707179: Epoch 715 +2025-11-13 06:06:16.708534: Current learning rate: 0.00323 +2025-11-13 06:10:35.070032: train_loss -0.715 +2025-11-13 06:10:35.073841: val_loss -0.7269 +2025-11-13 06:10:35.074927: Pseudo dice [np.float32(0.9092), np.float32(0.7759), np.float32(0.7458), np.float32(0.6394), np.float32(0.8667), np.float32(0.818), np.float32(0.9119), np.float32(0.857), np.float32(0.9736), np.float32(0.9705), np.float32(0.9692), np.float32(0.8349), np.float32(0.7273), np.float32(0.8731), np.float32(0.9624), np.float32(0.4741), np.float32(0.4466)] +2025-11-13 06:10:35.076136: Epoch time: 258.37 s +2025-11-13 06:10:37.017685: +2025-11-13 06:10:37.019177: Epoch 716 +2025-11-13 06:10:37.020602: Current learning rate: 0.00322 +2025-11-13 06:14:55.296254: train_loss -0.7171 +2025-11-13 06:14:55.300451: val_loss -0.7251 +2025-11-13 06:14:55.301852: Pseudo dice [np.float32(0.9165), np.float32(0.7811), np.float32(0.7223), np.float32(0.6577), np.float32(0.8688), np.float32(0.8041), np.float32(0.9132), np.float32(0.8602), np.float32(0.9741), np.float32(0.9736), np.float32(0.9699), np.float32(0.8267), np.float32(0.7646), np.float32(0.8795), np.float32(0.9604), np.float32(0.4313), np.float32(0.364)] +2025-11-13 06:14:55.303125: Epoch time: 258.29 s +2025-11-13 06:14:57.228132: +2025-11-13 06:14:57.229749: Epoch 717 +2025-11-13 06:14:57.231430: Current learning rate: 0.00321 +2025-11-13 06:19:15.648018: train_loss -0.7155 +2025-11-13 06:19:15.653059: val_loss -0.7245 +2025-11-13 06:19:15.654354: Pseudo dice [np.float32(0.916), np.float32(0.759), np.float32(0.6904), np.float32(0.6528), np.float32(0.8669), np.float32(0.8049), np.float32(0.8873), np.float32(0.8563), np.float32(0.964), np.float32(0.9644), np.float32(0.9686), np.float32(0.8385), np.float32(0.7936), np.float32(0.8831), np.float32(0.9593), np.float32(0.5096), np.float32(0.3685)] +2025-11-13 06:19:15.655726: Epoch time: 258.43 s +2025-11-13 06:19:17.600525: +2025-11-13 06:19:17.602249: Epoch 718 +2025-11-13 06:19:17.603522: Current learning rate: 0.0032 +2025-11-13 06:23:35.897825: train_loss -0.71 +2025-11-13 06:23:35.903305: val_loss -0.7256 +2025-11-13 06:23:35.905001: Pseudo dice [np.float32(0.9067), np.float32(0.8062), np.float32(0.7208), np.float32(0.6835), np.float32(0.8687), np.float32(0.7958), np.float32(0.8997), np.float32(0.8769), np.float32(0.9731), np.float32(0.9771), np.float32(0.9696), np.float32(0.8316), np.float32(0.7612), np.float32(0.8714), np.float32(0.9627), np.float32(0.4109), np.float32(0.4127)] +2025-11-13 06:23:35.906481: Epoch time: 258.3 s +2025-11-13 06:23:37.841585: +2025-11-13 06:23:37.843198: Epoch 719 +2025-11-13 06:23:37.844688: Current learning rate: 0.00319 +2025-11-13 06:27:56.297986: train_loss -0.7156 +2025-11-13 06:27:56.303106: val_loss -0.724 +2025-11-13 06:27:56.304255: Pseudo dice [np.float32(0.9091), np.float32(0.7963), np.float32(0.6919), np.float32(0.6602), np.float32(0.8691), np.float32(0.8029), np.float32(0.8892), np.float32(0.8599), np.float32(0.9732), np.float32(0.9735), np.float32(0.9693), np.float32(0.8395), np.float32(0.7566), np.float32(0.8789), np.float32(0.9576), np.float32(0.4711), np.float32(0.4122)] +2025-11-13 06:27:56.305999: Epoch time: 258.46 s +2025-11-13 06:27:58.202350: +2025-11-13 06:27:58.203699: Epoch 720 +2025-11-13 06:27:58.205145: Current learning rate: 0.00318 +2025-11-13 06:32:16.755414: train_loss -0.71 +2025-11-13 06:32:16.760120: val_loss -0.7095 +2025-11-13 06:32:16.761481: Pseudo dice [np.float32(0.9185), np.float32(0.741), np.float32(0.695), np.float32(0.6478), np.float32(0.868), np.float32(0.8077), np.float32(0.8959), np.float32(0.8632), np.float32(0.9754), np.float32(0.9732), np.float32(0.9699), np.float32(0.8264), np.float32(0.7787), np.float32(0.8753), np.float32(0.9635), np.float32(0.3249), np.float32(0.2647)] +2025-11-13 06:32:16.762806: Epoch time: 258.56 s +2025-11-13 06:32:18.678453: +2025-11-13 06:32:18.680071: Epoch 721 +2025-11-13 06:32:18.681335: Current learning rate: 0.00317 +2025-11-13 06:36:37.144651: train_loss -0.708 +2025-11-13 06:36:37.149094: val_loss -0.7202 +2025-11-13 06:36:37.150333: Pseudo dice [np.float32(0.9256), np.float32(0.7699), np.float32(0.7344), np.float32(0.6448), np.float32(0.8636), np.float32(0.8042), np.float32(0.895), np.float32(0.8628), np.float32(0.9757), np.float32(0.9714), np.float32(0.968), np.float32(0.8311), np.float32(0.7664), np.float32(0.8813), np.float32(0.9602), np.float32(0.456), np.float32(0.3661)] +2025-11-13 06:36:37.151845: Epoch time: 258.47 s +2025-11-13 06:36:39.026649: +2025-11-13 06:36:39.028042: Epoch 722 +2025-11-13 06:36:39.029698: Current learning rate: 0.00316 +2025-11-13 06:40:58.780044: train_loss -0.7165 +2025-11-13 06:40:58.783969: val_loss -0.7224 +2025-11-13 06:40:58.785503: Pseudo dice [np.float32(0.9097), np.float32(0.7768), np.float32(0.7257), np.float32(0.6546), np.float32(0.8687), np.float32(0.8119), np.float32(0.9074), np.float32(0.8497), np.float32(0.9675), np.float32(0.9699), np.float32(0.9693), np.float32(0.8317), np.float32(0.7934), np.float32(0.878), np.float32(0.961), np.float32(0.3743), np.float32(0.4049)] +2025-11-13 06:40:58.786743: Epoch time: 259.76 s +2025-11-13 06:41:00.678004: +2025-11-13 06:41:00.679755: Epoch 723 +2025-11-13 06:41:00.681106: Current learning rate: 0.00315 +2025-11-13 06:45:19.128746: train_loss -0.7173 +2025-11-13 06:45:19.133593: val_loss -0.7277 +2025-11-13 06:45:19.135148: Pseudo dice [np.float32(0.9146), np.float32(0.7561), np.float32(0.7162), np.float32(0.6433), np.float32(0.8734), np.float32(0.8133), np.float32(0.9105), np.float32(0.868), np.float32(0.9677), np.float32(0.9677), np.float32(0.9703), np.float32(0.8379), np.float32(0.8009), np.float32(0.8809), np.float32(0.9585), np.float32(0.4378), np.float32(0.3968)] +2025-11-13 06:45:19.136280: Epoch time: 258.46 s +2025-11-13 06:45:21.030153: +2025-11-13 06:45:21.031765: Epoch 724 +2025-11-13 06:45:21.033018: Current learning rate: 0.00314 +2025-11-13 06:49:39.338063: train_loss -0.717 +2025-11-13 06:49:39.341874: val_loss -0.7292 +2025-11-13 06:49:39.343065: Pseudo dice [np.float32(0.9076), np.float32(0.8055), np.float32(0.7168), np.float32(0.6655), np.float32(0.8705), np.float32(0.8082), np.float32(0.9024), np.float32(0.857), np.float32(0.9752), np.float32(0.9767), np.float32(0.9696), np.float32(0.8355), np.float32(0.7762), np.float32(0.8737), np.float32(0.9658), np.float32(0.4216), np.float32(0.445)] +2025-11-13 06:49:39.344222: Epoch time: 258.31 s +2025-11-13 06:49:41.260628: +2025-11-13 06:49:41.262085: Epoch 725 +2025-11-13 06:49:41.263301: Current learning rate: 0.00313 +2025-11-13 06:53:59.876700: train_loss -0.714 +2025-11-13 06:53:59.880903: val_loss -0.7269 +2025-11-13 06:53:59.882127: Pseudo dice [np.float32(0.916), np.float32(0.7735), np.float32(0.7433), np.float32(0.6459), np.float32(0.8657), np.float32(0.8199), np.float32(0.8911), np.float32(0.8654), np.float32(0.9794), np.float32(0.9798), np.float32(0.9701), np.float32(0.839), np.float32(0.7677), np.float32(0.8785), np.float32(0.9643), np.float32(0.414), np.float32(0.4012)] +2025-11-13 06:53:59.883410: Epoch time: 258.62 s +2025-11-13 06:54:01.751376: +2025-11-13 06:54:01.752838: Epoch 726 +2025-11-13 06:54:01.754205: Current learning rate: 0.00312 +2025-11-13 06:58:20.417252: train_loss -0.7183 +2025-11-13 06:58:20.421207: val_loss -0.7221 +2025-11-13 06:58:20.422962: Pseudo dice [np.float32(0.9186), np.float32(0.7797), np.float32(0.7071), np.float32(0.6617), np.float32(0.8674), np.float32(0.8094), np.float32(0.9117), np.float32(0.8488), np.float32(0.9812), np.float32(0.9801), np.float32(0.969), np.float32(0.8237), np.float32(0.7553), np.float32(0.878), np.float32(0.9691), np.float32(0.3839), np.float32(0.3495)] +2025-11-13 06:58:20.424307: Epoch time: 258.67 s +2025-11-13 06:58:22.282892: +2025-11-13 06:58:22.284310: Epoch 727 +2025-11-13 06:58:22.285722: Current learning rate: 0.00311 +2025-11-13 07:02:41.062832: train_loss -0.7133 +2025-11-13 07:02:41.067743: val_loss -0.7246 +2025-11-13 07:02:41.069090: Pseudo dice [np.float32(0.8942), np.float32(0.7747), np.float32(0.6901), np.float32(0.6497), np.float32(0.8614), np.float32(0.8171), np.float32(0.9054), np.float32(0.8722), np.float32(0.9771), np.float32(0.9766), np.float32(0.9694), np.float32(0.8376), np.float32(0.7753), np.float32(0.871), np.float32(0.965), np.float32(0.4602), np.float32(0.4088)] +2025-11-13 07:02:41.070255: Epoch time: 258.79 s +2025-11-13 07:02:42.952905: +2025-11-13 07:02:42.954453: Epoch 728 +2025-11-13 07:02:42.955639: Current learning rate: 0.0031 +2025-11-13 07:07:01.889768: train_loss -0.7139 +2025-11-13 07:07:01.894167: val_loss -0.7258 +2025-11-13 07:07:01.895867: Pseudo dice [np.float32(0.9197), np.float32(0.7562), np.float32(0.7135), np.float32(0.6713), np.float32(0.8687), np.float32(0.8296), np.float32(0.9165), np.float32(0.8628), np.float32(0.9796), np.float32(0.9807), np.float32(0.9704), np.float32(0.8359), np.float32(0.7354), np.float32(0.884), np.float32(0.9657), np.float32(0.3986), np.float32(0.4014)] +2025-11-13 07:07:01.896929: Epoch time: 258.94 s +2025-11-13 07:07:03.898810: +2025-11-13 07:07:03.900565: Epoch 729 +2025-11-13 07:07:03.902182: Current learning rate: 0.00309 +2025-11-13 07:11:22.532694: train_loss -0.7182 +2025-11-13 07:11:22.536634: val_loss -0.7277 +2025-11-13 07:11:22.538137: Pseudo dice [np.float32(0.9229), np.float32(0.8138), np.float32(0.7307), np.float32(0.6472), np.float32(0.8701), np.float32(0.8058), np.float32(0.8918), np.float32(0.8686), np.float32(0.9802), np.float32(0.9805), np.float32(0.969), np.float32(0.8357), np.float32(0.759), np.float32(0.8789), np.float32(0.9568), np.float32(0.3932), np.float32(0.43)] +2025-11-13 07:11:22.539850: Epoch time: 258.64 s +2025-11-13 07:11:24.634224: +2025-11-13 07:11:24.635840: Epoch 730 +2025-11-13 07:11:24.636972: Current learning rate: 0.00308 +2025-11-13 07:15:43.353803: train_loss -0.7218 +2025-11-13 07:15:43.357669: val_loss -0.7198 +2025-11-13 07:15:43.358951: Pseudo dice [np.float32(0.9168), np.float32(0.7448), np.float32(0.7096), np.float32(0.6577), np.float32(0.8679), np.float32(0.7831), np.float32(0.898), np.float32(0.8639), np.float32(0.9725), np.float32(0.9732), np.float32(0.9694), np.float32(0.829), np.float32(0.7512), np.float32(0.875), np.float32(0.9626), np.float32(0.3981), np.float32(0.2916)] +2025-11-13 07:15:43.360094: Epoch time: 258.73 s +2025-11-13 07:15:45.330028: +2025-11-13 07:15:45.331601: Epoch 731 +2025-11-13 07:15:45.332966: Current learning rate: 0.00307 +2025-11-13 07:20:03.908570: train_loss -0.7223 +2025-11-13 07:20:03.912436: val_loss -0.7302 +2025-11-13 07:20:03.913749: Pseudo dice [np.float32(0.9154), np.float32(0.7897), np.float32(0.7473), np.float32(0.6799), np.float32(0.8718), np.float32(0.8263), np.float32(0.9001), np.float32(0.8531), np.float32(0.9815), np.float32(0.9819), np.float32(0.9698), np.float32(0.8349), np.float32(0.7456), np.float32(0.8852), np.float32(0.9662), np.float32(0.4574), np.float32(0.4484)] +2025-11-13 07:20:03.914828: Epoch time: 258.58 s +2025-11-13 07:20:07.625535: +2025-11-13 07:20:07.626967: Epoch 732 +2025-11-13 07:20:07.628222: Current learning rate: 0.00306 +2025-11-13 07:24:26.427505: train_loss -0.7179 +2025-11-13 07:24:26.432145: val_loss -0.7385 +2025-11-13 07:24:26.433905: Pseudo dice [np.float32(0.9151), np.float32(0.785), np.float32(0.7291), np.float32(0.6914), np.float32(0.8746), np.float32(0.8084), np.float32(0.9136), np.float32(0.8623), np.float32(0.979), np.float32(0.9776), np.float32(0.9693), np.float32(0.8416), np.float32(0.752), np.float32(0.883), np.float32(0.9639), np.float32(0.4743), np.float32(0.4402)] +2025-11-13 07:24:26.435411: Epoch time: 258.81 s +2025-11-13 07:24:28.331719: +2025-11-13 07:24:28.333419: Epoch 733 +2025-11-13 07:24:28.334792: Current learning rate: 0.00305 +2025-11-13 07:28:46.931713: train_loss -0.7208 +2025-11-13 07:28:46.936048: val_loss -0.7209 +2025-11-13 07:28:46.937765: Pseudo dice [np.float32(0.9245), np.float32(0.8022), np.float32(0.7156), np.float32(0.6549), np.float32(0.8714), np.float32(0.8274), np.float32(0.8922), np.float32(0.8534), np.float32(0.9806), np.float32(0.9795), np.float32(0.97), np.float32(0.8448), np.float32(0.7518), np.float32(0.8766), np.float32(0.9628), np.float32(0.4224), np.float32(0.2957)] +2025-11-13 07:28:46.939147: Epoch time: 258.6 s +2025-11-13 07:28:48.847813: +2025-11-13 07:28:48.849837: Epoch 734 +2025-11-13 07:28:48.851881: Current learning rate: 0.00304 +2025-11-13 07:33:07.311494: train_loss -0.7137 +2025-11-13 07:33:07.316571: val_loss -0.712 +2025-11-13 07:33:07.318249: Pseudo dice [np.float32(0.9179), np.float32(0.7592), np.float32(0.7293), np.float32(0.6682), np.float32(0.8675), np.float32(0.8168), np.float32(0.9022), np.float32(0.8573), np.float32(0.9666), np.float32(0.9629), np.float32(0.9655), np.float32(0.8228), np.float32(0.7594), np.float32(0.872), np.float32(0.9448), np.float32(0.4252), np.float32(0.2877)] +2025-11-13 07:33:07.319284: Epoch time: 258.47 s +2025-11-13 07:33:09.281712: +2025-11-13 07:33:09.283499: Epoch 735 +2025-11-13 07:33:09.285307: Current learning rate: 0.00303 +2025-11-13 07:37:27.963607: train_loss -0.7098 +2025-11-13 07:37:27.968132: val_loss -0.724 +2025-11-13 07:37:27.969643: Pseudo dice [np.float32(0.9095), np.float32(0.7445), np.float32(0.7161), np.float32(0.671), np.float32(0.8653), np.float32(0.7964), np.float32(0.9033), np.float32(0.8627), np.float32(0.9765), np.float32(0.9748), np.float32(0.9697), np.float32(0.8266), np.float32(0.771), np.float32(0.8757), np.float32(0.9633), np.float32(0.3832), np.float32(0.3628)] +2025-11-13 07:37:27.971463: Epoch time: 258.69 s +2025-11-13 07:37:29.893141: +2025-11-13 07:37:29.894745: Epoch 736 +2025-11-13 07:37:29.896211: Current learning rate: 0.00302 +2025-11-13 07:41:48.398674: train_loss -0.7168 +2025-11-13 07:41:48.402422: val_loss -0.7355 +2025-11-13 07:41:48.403831: Pseudo dice [np.float32(0.9174), np.float32(0.7811), np.float32(0.7226), np.float32(0.6619), np.float32(0.8746), np.float32(0.8316), np.float32(0.9035), np.float32(0.8647), np.float32(0.9761), np.float32(0.9788), np.float32(0.9709), np.float32(0.8445), np.float32(0.777), np.float32(0.8811), np.float32(0.9653), np.float32(0.4501), np.float32(0.4349)] +2025-11-13 07:41:48.404984: Epoch time: 258.51 s +2025-11-13 07:41:50.334812: +2025-11-13 07:41:50.336450: Epoch 737 +2025-11-13 07:41:50.337788: Current learning rate: 0.00301 +2025-11-13 07:46:08.759968: train_loss -0.7158 +2025-11-13 07:46:08.764363: val_loss -0.7082 +2025-11-13 07:46:08.765801: Pseudo dice [np.float32(0.9148), np.float32(0.8088), np.float32(0.7153), np.float32(0.646), np.float32(0.8706), np.float32(0.808), np.float32(0.8949), np.float32(0.8626), np.float32(0.9207), np.float32(0.9169), np.float32(0.9593), np.float32(0.8229), np.float32(0.7629), np.float32(0.8807), np.float32(0.8919), np.float32(0.427), np.float32(0.3855)] +2025-11-13 07:46:08.767177: Epoch time: 258.43 s +2025-11-13 07:46:10.643211: +2025-11-13 07:46:10.644557: Epoch 738 +2025-11-13 07:46:10.645904: Current learning rate: 0.003 +2025-11-13 07:50:29.118985: train_loss -0.7108 +2025-11-13 07:50:29.123919: val_loss -0.7349 +2025-11-13 07:50:29.125358: Pseudo dice [np.float32(0.9146), np.float32(0.7791), np.float32(0.7249), np.float32(0.6761), np.float32(0.8631), np.float32(0.8199), np.float32(0.9081), np.float32(0.8606), np.float32(0.9733), np.float32(0.972), np.float32(0.9708), np.float32(0.8402), np.float32(0.7764), np.float32(0.88), np.float32(0.9622), np.float32(0.5452), np.float32(0.4486)] +2025-11-13 07:50:29.126479: Epoch time: 258.48 s +2025-11-13 07:50:30.981833: +2025-11-13 07:50:30.983153: Epoch 739 +2025-11-13 07:50:30.984441: Current learning rate: 0.00299 +2025-11-13 07:54:49.450390: train_loss -0.7137 +2025-11-13 07:54:49.454560: val_loss -0.7228 +2025-11-13 07:54:49.456087: Pseudo dice [np.float32(0.9177), np.float32(0.7859), np.float32(0.702), np.float32(0.6668), np.float32(0.8661), np.float32(0.803), np.float32(0.8962), np.float32(0.8526), np.float32(0.9739), np.float32(0.9713), np.float32(0.9689), np.float32(0.8234), np.float32(0.7766), np.float32(0.8774), np.float32(0.964), np.float32(0.4394), np.float32(0.3599)] +2025-11-13 07:54:49.457599: Epoch time: 258.47 s +2025-11-13 07:54:51.305194: +2025-11-13 07:54:51.306631: Epoch 740 +2025-11-13 07:54:51.308282: Current learning rate: 0.00297 +2025-11-13 07:59:10.029852: train_loss -0.7113 +2025-11-13 07:59:10.034088: val_loss -0.7236 +2025-11-13 07:59:10.035303: Pseudo dice [np.float32(0.9154), np.float32(0.7713), np.float32(0.7186), np.float32(0.6626), np.float32(0.8703), np.float32(0.8071), np.float32(0.8989), np.float32(0.8636), np.float32(0.9804), np.float32(0.9771), np.float32(0.9715), np.float32(0.8468), np.float32(0.7595), np.float32(0.8701), np.float32(0.9673), np.float32(0.4148), np.float32(0.3463)] +2025-11-13 07:59:10.037659: Epoch time: 258.73 s +2025-11-13 07:59:11.945305: +2025-11-13 07:59:11.947091: Epoch 741 +2025-11-13 07:59:11.948974: Current learning rate: 0.00296 +2025-11-13 08:03:31.943796: train_loss -0.7136 +2025-11-13 08:03:31.948035: val_loss -0.7241 +2025-11-13 08:03:31.949246: Pseudo dice [np.float32(0.9252), np.float32(0.806), np.float32(0.7414), np.float32(0.6452), np.float32(0.8707), np.float32(0.8064), np.float32(0.9178), np.float32(0.8558), np.float32(0.9715), np.float32(0.9723), np.float32(0.9691), np.float32(0.8334), np.float32(0.7773), np.float32(0.8826), np.float32(0.9585), np.float32(0.3674), np.float32(0.4297)] +2025-11-13 08:03:31.950456: Epoch time: 260.0 s +2025-11-13 08:03:33.809005: +2025-11-13 08:03:33.810634: Epoch 742 +2025-11-13 08:03:33.811976: Current learning rate: 0.00295 +2025-11-13 08:07:52.182717: train_loss -0.7149 +2025-11-13 08:07:52.187779: val_loss -0.7197 +2025-11-13 08:07:52.189391: Pseudo dice [np.float32(0.9168), np.float32(0.7802), np.float32(0.7015), np.float32(0.6625), np.float32(0.8623), np.float32(0.8159), np.float32(0.8944), np.float32(0.8599), np.float32(0.9782), np.float32(0.9777), np.float32(0.9694), np.float32(0.8323), np.float32(0.7659), np.float32(0.8811), np.float32(0.9663), np.float32(0.4114), np.float32(0.3157)] +2025-11-13 08:07:52.190820: Epoch time: 258.38 s +2025-11-13 08:07:54.002465: +2025-11-13 08:07:54.003842: Epoch 743 +2025-11-13 08:07:54.005130: Current learning rate: 0.00294 +2025-11-13 08:12:12.383910: train_loss -0.7128 +2025-11-13 08:12:12.387730: val_loss -0.7287 +2025-11-13 08:12:12.389235: Pseudo dice [np.float32(0.9153), np.float32(0.7782), np.float32(0.7316), np.float32(0.6917), np.float32(0.8669), np.float32(0.8194), np.float32(0.9092), np.float32(0.8622), np.float32(0.9776), np.float32(0.9768), np.float32(0.9706), np.float32(0.8418), np.float32(0.753), np.float32(0.8695), np.float32(0.9647), np.float32(0.3879), np.float32(0.4067)] +2025-11-13 08:12:12.390410: Epoch time: 258.39 s +2025-11-13 08:12:14.282158: +2025-11-13 08:12:14.283877: Epoch 744 +2025-11-13 08:12:14.285323: Current learning rate: 0.00293 +2025-11-13 08:16:32.841691: train_loss -0.7141 +2025-11-13 08:16:32.846436: val_loss -0.719 +2025-11-13 08:16:32.847717: Pseudo dice [np.float32(0.9169), np.float32(0.7821), np.float32(0.7398), np.float32(0.6717), np.float32(0.8705), np.float32(0.8285), np.float32(0.9069), np.float32(0.8679), np.float32(0.9798), np.float32(0.9805), np.float32(0.9686), np.float32(0.8358), np.float32(0.7552), np.float32(0.8811), np.float32(0.9606), np.float32(0.3349), np.float32(0.2417)] +2025-11-13 08:16:32.849138: Epoch time: 258.56 s +2025-11-13 08:19:03.581331: +2025-11-13 08:19:03.583738: Epoch 745 +2025-11-13 08:19:03.585374: Current learning rate: 0.00292 +2025-11-13 08:23:21.130382: train_loss -0.7205 +2025-11-13 08:23:21.135192: val_loss -0.7323 +2025-11-13 08:23:21.136813: Pseudo dice [np.float32(0.9135), np.float32(0.7874), np.float32(0.7155), np.float32(0.6946), np.float32(0.8688), np.float32(0.8113), np.float32(0.9213), np.float32(0.8547), np.float32(0.9801), np.float32(0.9789), np.float32(0.9698), np.float32(0.8279), np.float32(0.7807), np.float32(0.8802), np.float32(0.9649), np.float32(0.4849), np.float32(0.4103)] +2025-11-13 08:23:21.138269: Epoch time: 257.56 s +2025-11-13 08:23:23.063985: +2025-11-13 08:23:23.065822: Epoch 746 +2025-11-13 08:23:23.067514: Current learning rate: 0.00291 +2025-11-13 08:27:41.487859: train_loss -0.7204 +2025-11-13 08:27:41.491702: val_loss -0.7186 +2025-11-13 08:27:41.493203: Pseudo dice [np.float32(0.9069), np.float32(0.7601), np.float32(0.6975), np.float32(0.6792), np.float32(0.8659), np.float32(0.8361), np.float32(0.9087), np.float32(0.8567), np.float32(0.9709), np.float32(0.9722), np.float32(0.9691), np.float32(0.8332), np.float32(0.7792), np.float32(0.8731), np.float32(0.9556), np.float32(0.3908), np.float32(0.317)] +2025-11-13 08:27:41.494507: Epoch time: 258.43 s +2025-11-13 08:27:43.306377: +2025-11-13 08:27:43.307851: Epoch 747 +2025-11-13 08:27:43.309139: Current learning rate: 0.0029 +2025-11-13 08:32:01.902211: train_loss -0.7225 +2025-11-13 08:32:01.907202: val_loss -0.7206 +2025-11-13 08:32:01.908626: Pseudo dice [np.float32(0.9231), np.float32(0.7797), np.float32(0.7223), np.float32(0.6658), np.float32(0.8695), np.float32(0.8016), np.float32(0.8863), np.float32(0.8632), np.float32(0.9567), np.float32(0.958), np.float32(0.9643), np.float32(0.8435), np.float32(0.7691), np.float32(0.8755), np.float32(0.9205), np.float32(0.4562), np.float32(0.523)] +2025-11-13 08:32:01.910043: Epoch time: 258.6 s +2025-11-13 08:32:04.004068: +2025-11-13 08:32:04.006842: Epoch 748 +2025-11-13 08:32:04.008586: Current learning rate: 0.00289 +2025-11-13 08:36:22.422207: train_loss -0.7168 +2025-11-13 08:36:22.426243: val_loss -0.7223 +2025-11-13 08:36:22.427726: Pseudo dice [np.float32(0.9116), np.float32(0.7765), np.float32(0.7281), np.float32(0.6517), np.float32(0.8725), np.float32(0.8096), np.float32(0.9058), np.float32(0.8597), np.float32(0.9788), np.float32(0.9811), np.float32(0.971), np.float32(0.8424), np.float32(0.7644), np.float32(0.8795), np.float32(0.9673), np.float32(0.3753), np.float32(0.3735)] +2025-11-13 08:36:22.428890: Epoch time: 258.42 s +2025-11-13 08:36:24.347962: +2025-11-13 08:36:24.349341: Epoch 749 +2025-11-13 08:36:24.350646: Current learning rate: 0.00288 +2025-11-13 08:40:42.812418: train_loss -0.7151 +2025-11-13 08:40:42.816932: val_loss -0.7204 +2025-11-13 08:40:42.818412: Pseudo dice [np.float32(0.9208), np.float32(0.7643), np.float32(0.7059), np.float32(0.6468), np.float32(0.863), np.float32(0.814), np.float32(0.9023), np.float32(0.8686), np.float32(0.9646), np.float32(0.9669), np.float32(0.9695), np.float32(0.8379), np.float32(0.7567), np.float32(0.8759), np.float32(0.9507), np.float32(0.4306), np.float32(0.4367)] +2025-11-13 08:40:42.819689: Epoch time: 258.47 s +2025-11-13 08:40:48.577908: +2025-11-13 08:40:48.579343: Epoch 750 +2025-11-13 08:40:48.580632: Current learning rate: 0.00287 +2025-11-13 08:45:08.389982: train_loss -0.7131 +2025-11-13 08:45:08.394068: val_loss -0.7208 +2025-11-13 08:45:08.395800: Pseudo dice [np.float32(0.9098), np.float32(0.7865), np.float32(0.7174), np.float32(0.6763), np.float32(0.8656), np.float32(0.8057), np.float32(0.9119), np.float32(0.8604), np.float32(0.9544), np.float32(0.957), np.float32(0.9685), np.float32(0.8236), np.float32(0.7544), np.float32(0.8775), np.float32(0.9454), np.float32(0.4266), np.float32(0.3658)] +2025-11-13 08:45:08.397022: Epoch time: 259.82 s +2025-11-13 08:45:10.279712: +2025-11-13 08:45:10.281191: Epoch 751 +2025-11-13 08:45:10.282491: Current learning rate: 0.00286 +2025-11-13 08:49:28.676162: train_loss -0.7135 +2025-11-13 08:49:28.681097: val_loss -0.7212 +2025-11-13 08:49:28.682604: Pseudo dice [np.float32(0.9056), np.float32(0.7856), np.float32(0.723), np.float32(0.6882), np.float32(0.8686), np.float32(0.796), np.float32(0.8916), np.float32(0.871), np.float32(0.9815), np.float32(0.9784), np.float32(0.9704), np.float32(0.8418), np.float32(0.7827), np.float32(0.8777), np.float32(0.9634), np.float32(0.3687), np.float32(0.2957)] +2025-11-13 08:49:28.684487: Epoch time: 258.4 s +2025-11-13 08:49:30.713198: +2025-11-13 08:49:30.714465: Epoch 752 +2025-11-13 08:49:30.715772: Current learning rate: 0.00285 +2025-11-13 08:53:49.153859: train_loss -0.7163 +2025-11-13 08:53:49.158066: val_loss -0.7351 +2025-11-13 08:53:49.159960: Pseudo dice [np.float32(0.9148), np.float32(0.8129), np.float32(0.7369), np.float32(0.6914), np.float32(0.8741), np.float32(0.8097), np.float32(0.9014), np.float32(0.853), np.float32(0.9807), np.float32(0.9789), np.float32(0.9711), np.float32(0.8235), np.float32(0.7822), np.float32(0.8774), np.float32(0.9643), np.float32(0.4524), np.float32(0.385)] +2025-11-13 08:53:49.161217: Epoch time: 258.45 s +2025-11-13 08:53:51.057225: +2025-11-13 08:53:51.058742: Epoch 753 +2025-11-13 08:53:51.060116: Current learning rate: 0.00284 +2025-11-13 08:58:09.448548: train_loss -0.7211 +2025-11-13 08:58:09.452829: val_loss -0.7263 +2025-11-13 08:58:09.454447: Pseudo dice [np.float32(0.9182), np.float32(0.7813), np.float32(0.7204), np.float32(0.6735), np.float32(0.8647), np.float32(0.8177), np.float32(0.9045), np.float32(0.8658), np.float32(0.9786), np.float32(0.9761), np.float32(0.971), np.float32(0.841), np.float32(0.7751), np.float32(0.8766), np.float32(0.9653), np.float32(0.3849), np.float32(0.3279)] +2025-11-13 08:58:09.455688: Epoch time: 258.4 s +2025-11-13 08:58:11.273784: +2025-11-13 08:58:11.275156: Epoch 754 +2025-11-13 08:58:11.276536: Current learning rate: 0.00283 +2025-11-13 09:02:29.517184: train_loss -0.7151 +2025-11-13 09:02:29.521684: val_loss -0.737 +2025-11-13 09:02:29.523614: Pseudo dice [np.float32(0.9206), np.float32(0.7966), np.float32(0.7405), np.float32(0.6693), np.float32(0.8666), np.float32(0.8159), np.float32(0.9062), np.float32(0.8646), np.float32(0.9795), np.float32(0.9784), np.float32(0.9713), np.float32(0.844), np.float32(0.7945), np.float32(0.8754), np.float32(0.9673), np.float32(0.4896), np.float32(0.3681)] +2025-11-13 09:02:29.525005: Epoch time: 258.25 s +2025-11-13 09:02:29.526348: Yayy! New best EMA pseudo Dice: 0.8052999973297119 +2025-11-13 09:02:34.203828: +2025-11-13 09:02:34.205503: Epoch 755 +2025-11-13 09:02:34.206668: Current learning rate: 0.00282 +2025-11-13 09:06:52.548371: train_loss -0.7248 +2025-11-13 09:06:52.553690: val_loss -0.7208 +2025-11-13 09:06:52.555592: Pseudo dice [np.float32(0.9093), np.float32(0.7617), np.float32(0.7007), np.float32(0.6455), np.float32(0.8618), np.float32(0.7975), np.float32(0.8931), np.float32(0.8644), np.float32(0.9719), np.float32(0.9711), np.float32(0.9703), np.float32(0.8254), np.float32(0.768), np.float32(0.8754), np.float32(0.9656), np.float32(0.431), np.float32(0.4353)] +2025-11-13 09:06:52.557074: Epoch time: 258.35 s +2025-11-13 09:06:54.394783: +2025-11-13 09:06:54.396255: Epoch 756 +2025-11-13 09:06:54.397898: Current learning rate: 0.00281 +2025-11-13 09:11:12.939584: train_loss -0.7178 +2025-11-13 09:11:12.944680: val_loss -0.7225 +2025-11-13 09:11:12.946351: Pseudo dice [np.float32(0.9181), np.float32(0.7845), np.float32(0.735), np.float32(0.689), np.float32(0.8721), np.float32(0.8061), np.float32(0.8948), np.float32(0.8649), np.float32(0.9767), np.float32(0.9774), np.float32(0.9707), np.float32(0.8449), np.float32(0.7648), np.float32(0.8761), np.float32(0.9651), np.float32(0.3465), np.float32(0.3035)] +2025-11-13 09:11:12.947971: Epoch time: 258.55 s +2025-11-13 09:11:14.858581: +2025-11-13 09:11:14.860116: Epoch 757 +2025-11-13 09:11:14.861587: Current learning rate: 0.0028 +2025-11-13 09:15:33.539209: train_loss -0.7196 +2025-11-13 09:15:33.543324: val_loss -0.7245 +2025-11-13 09:15:33.545006: Pseudo dice [np.float32(0.92), np.float32(0.7932), np.float32(0.7108), np.float32(0.6527), np.float32(0.8634), np.float32(0.8022), np.float32(0.9011), np.float32(0.8565), np.float32(0.965), np.float32(0.9661), np.float32(0.9703), np.float32(0.8373), np.float32(0.7707), np.float32(0.8734), np.float32(0.9627), np.float32(0.3823), np.float32(0.401)] +2025-11-13 09:15:33.546315: Epoch time: 258.69 s +2025-11-13 09:15:35.365380: +2025-11-13 09:15:35.366907: Epoch 758 +2025-11-13 09:15:35.368563: Current learning rate: 0.00279 +2025-11-13 09:19:53.752649: train_loss -0.712 +2025-11-13 09:19:53.756783: val_loss -0.7293 +2025-11-13 09:19:53.758018: Pseudo dice [np.float32(0.9253), np.float32(0.7808), np.float32(0.7096), np.float32(0.6788), np.float32(0.8718), np.float32(0.8201), np.float32(0.9126), np.float32(0.8458), np.float32(0.98), np.float32(0.9781), np.float32(0.9706), np.float32(0.8384), np.float32(0.7436), np.float32(0.8829), np.float32(0.9666), np.float32(0.4688), np.float32(0.3855)] +2025-11-13 09:19:53.759403: Epoch time: 258.39 s +2025-11-13 09:19:55.627389: +2025-11-13 09:19:55.628746: Epoch 759 +2025-11-13 09:19:55.630000: Current learning rate: 0.00278 +2025-11-13 09:24:14.871728: train_loss -0.7149 +2025-11-13 09:24:14.875652: val_loss -0.7327 +2025-11-13 09:24:14.877203: Pseudo dice [np.float32(0.9138), np.float32(0.7845), np.float32(0.7455), np.float32(0.6597), np.float32(0.8762), np.float32(0.8219), np.float32(0.9245), np.float32(0.8661), np.float32(0.9588), np.float32(0.958), np.float32(0.9688), np.float32(0.8375), np.float32(0.7787), np.float32(0.8845), np.float32(0.9498), np.float32(0.4428), np.float32(0.4053)] +2025-11-13 09:24:14.879043: Epoch time: 259.25 s +2025-11-13 09:24:16.711442: +2025-11-13 09:24:16.712931: Epoch 760 +2025-11-13 09:24:16.714435: Current learning rate: 0.00277 +2025-11-13 09:28:35.125129: train_loss -0.7227 +2025-11-13 09:28:35.129972: val_loss -0.7296 +2025-11-13 09:28:35.131542: Pseudo dice [np.float32(0.9123), np.float32(0.7778), np.float32(0.7216), np.float32(0.6423), np.float32(0.8726), np.float32(0.8098), np.float32(0.8935), np.float32(0.8478), np.float32(0.9723), np.float32(0.9718), np.float32(0.9711), np.float32(0.8484), np.float32(0.7676), np.float32(0.8808), np.float32(0.9643), np.float32(0.4273), np.float32(0.4263)] +2025-11-13 09:28:35.133418: Epoch time: 258.42 s +2025-11-13 09:28:35.134523: Yayy! New best EMA pseudo Dice: 0.805400013923645 +2025-11-13 09:28:40.171085: +2025-11-13 09:28:40.172514: Epoch 761 +2025-11-13 09:28:40.173718: Current learning rate: 0.00276 +2025-11-13 09:32:58.468537: train_loss -0.7229 +2025-11-13 09:32:58.473054: val_loss -0.7244 +2025-11-13 09:32:58.474190: Pseudo dice [np.float32(0.9203), np.float32(0.8043), np.float32(0.7294), np.float32(0.6581), np.float32(0.8767), np.float32(0.8137), np.float32(0.9105), np.float32(0.8641), np.float32(0.9752), np.float32(0.9795), np.float32(0.9706), np.float32(0.8373), np.float32(0.773), np.float32(0.8834), np.float32(0.9668), np.float32(0.3346), np.float32(0.3744)] +2025-11-13 09:32:58.475456: Epoch time: 258.3 s +2025-11-13 09:33:00.294580: +2025-11-13 09:33:00.295916: Epoch 762 +2025-11-13 09:33:00.297332: Current learning rate: 0.00275 +2025-11-13 09:37:18.832410: train_loss -0.7179 +2025-11-13 09:37:18.836676: val_loss -0.7261 +2025-11-13 09:37:18.837899: Pseudo dice [np.float32(0.9127), np.float32(0.7836), np.float32(0.7089), np.float32(0.6654), np.float32(0.8735), np.float32(0.8215), np.float32(0.9083), np.float32(0.8613), np.float32(0.9803), np.float32(0.9778), np.float32(0.9703), np.float32(0.8351), np.float32(0.7782), np.float32(0.882), np.float32(0.9644), np.float32(0.464), np.float32(0.3275)] +2025-11-13 09:37:18.839198: Epoch time: 258.54 s +2025-11-13 09:37:18.840577: Yayy! New best EMA pseudo Dice: 0.805400013923645 +2025-11-13 09:37:23.834979: +2025-11-13 09:37:23.836366: Epoch 763 +2025-11-13 09:37:23.837671: Current learning rate: 0.00274 +2025-11-13 09:41:42.189301: train_loss -0.7205 +2025-11-13 09:41:42.193648: val_loss -0.7305 +2025-11-13 09:41:42.195106: Pseudo dice [np.float32(0.9091), np.float32(0.7927), np.float32(0.735), np.float32(0.6458), np.float32(0.8707), np.float32(0.8128), np.float32(0.9006), np.float32(0.8625), np.float32(0.9754), np.float32(0.9714), np.float32(0.97), np.float32(0.831), np.float32(0.7807), np.float32(0.8868), np.float32(0.963), np.float32(0.4377), np.float32(0.3685)] +2025-11-13 09:41:42.196390: Epoch time: 258.36 s +2025-11-13 09:41:42.197668: Yayy! New best EMA pseudo Dice: 0.8055999875068665 +2025-11-13 09:41:47.470946: +2025-11-13 09:41:47.472413: Epoch 764 +2025-11-13 09:41:47.473736: Current learning rate: 0.00273 +2025-11-13 09:46:05.613423: train_loss -0.7176 +2025-11-13 09:46:05.618237: val_loss -0.7267 +2025-11-13 09:46:05.620029: Pseudo dice [np.float32(0.9194), np.float32(0.8002), np.float32(0.706), np.float32(0.6788), np.float32(0.8746), np.float32(0.8071), np.float32(0.9085), np.float32(0.855), np.float32(0.9771), np.float32(0.978), np.float32(0.97), np.float32(0.8465), np.float32(0.7656), np.float32(0.8779), np.float32(0.9531), np.float32(0.4136), np.float32(0.4226)] +2025-11-13 09:46:05.621755: Epoch time: 258.15 s +2025-11-13 09:46:05.622904: Yayy! New best EMA pseudo Dice: 0.805899977684021 +2025-11-13 09:46:10.952664: +2025-11-13 09:46:10.954246: Epoch 765 +2025-11-13 09:46:10.955633: Current learning rate: 0.00272 +2025-11-13 09:50:29.102944: train_loss -0.7198 +2025-11-13 09:50:29.107776: val_loss -0.7452 +2025-11-13 09:50:29.109089: Pseudo dice [np.float32(0.9251), np.float32(0.7978), np.float32(0.7407), np.float32(0.6258), np.float32(0.866), np.float32(0.827), np.float32(0.914), np.float32(0.8645), np.float32(0.976), np.float32(0.9764), np.float32(0.9707), np.float32(0.836), np.float32(0.7776), np.float32(0.8727), np.float32(0.9642), np.float32(0.4728), np.float32(0.4825)] +2025-11-13 09:50:29.110532: Epoch time: 258.16 s +2025-11-13 09:50:29.111874: Yayy! New best EMA pseudo Dice: 0.8069999814033508 +2025-11-13 09:50:34.430465: +2025-11-13 09:50:34.431799: Epoch 766 +2025-11-13 09:50:34.432963: Current learning rate: 0.00271 +2025-11-13 09:54:52.748210: train_loss -0.7247 +2025-11-13 09:54:52.752700: val_loss -0.7205 +2025-11-13 09:54:52.754303: Pseudo dice [np.float32(0.9081), np.float32(0.7856), np.float32(0.7366), np.float32(0.6593), np.float32(0.872), np.float32(0.8145), np.float32(0.8922), np.float32(0.8552), np.float32(0.9712), np.float32(0.9699), np.float32(0.9702), np.float32(0.839), np.float32(0.7614), np.float32(0.8801), np.float32(0.961), np.float32(0.3642), np.float32(0.3222)] +2025-11-13 09:54:52.755729: Epoch time: 258.32 s +2025-11-13 09:54:54.630438: +2025-11-13 09:54:54.631972: Epoch 767 +2025-11-13 09:54:54.633637: Current learning rate: 0.0027 +2025-11-13 09:59:12.960245: train_loss -0.7211 +2025-11-13 09:59:12.965570: val_loss -0.7331 +2025-11-13 09:59:12.967229: Pseudo dice [np.float32(0.918), np.float32(0.7652), np.float32(0.7294), np.float32(0.6809), np.float32(0.8685), np.float32(0.814), np.float32(0.9135), np.float32(0.87), np.float32(0.9803), np.float32(0.9806), np.float32(0.9719), np.float32(0.8322), np.float32(0.7529), np.float32(0.8757), np.float32(0.965), np.float32(0.4238), np.float32(0.4286)] +2025-11-13 09:59:12.968387: Epoch time: 258.33 s +2025-11-13 09:59:16.662721: +2025-11-13 09:59:16.664405: Epoch 768 +2025-11-13 09:59:16.665534: Current learning rate: 0.00268 +2025-11-13 10:03:35.124013: train_loss -0.7229 +2025-11-13 10:03:35.128305: val_loss -0.723 +2025-11-13 10:03:35.129543: Pseudo dice [np.float32(0.8986), np.float32(0.7784), np.float32(0.6994), np.float32(0.6615), np.float32(0.8689), np.float32(0.8066), np.float32(0.8989), np.float32(0.8622), np.float32(0.9816), np.float32(0.9806), np.float32(0.971), np.float32(0.8366), np.float32(0.7761), np.float32(0.8837), np.float32(0.9647), np.float32(0.4585), np.float32(0.389)] +2025-11-13 10:03:35.130706: Epoch time: 258.47 s +2025-11-13 10:03:37.015248: +2025-11-13 10:03:37.016694: Epoch 769 +2025-11-13 10:03:37.018070: Current learning rate: 0.00267 +2025-11-13 10:07:55.496150: train_loss -0.7232 +2025-11-13 10:07:55.502211: val_loss -0.7193 +2025-11-13 10:07:55.504234: Pseudo dice [np.float32(0.9214), np.float32(0.7618), np.float32(0.711), np.float32(0.6285), np.float32(0.872), np.float32(0.8118), np.float32(0.901), np.float32(0.8558), np.float32(0.9783), np.float32(0.9757), np.float32(0.9688), np.float32(0.839), np.float32(0.7652), np.float32(0.8737), np.float32(0.9648), np.float32(0.3666), np.float32(0.3785)] +2025-11-13 10:07:55.505536: Epoch time: 258.49 s +2025-11-13 10:07:57.583354: +2025-11-13 10:07:57.584847: Epoch 770 +2025-11-13 10:07:57.586344: Current learning rate: 0.00266 +2025-11-13 10:12:16.014785: train_loss -0.7202 +2025-11-13 10:12:16.019064: val_loss -0.7222 +2025-11-13 10:12:16.020653: Pseudo dice [np.float32(0.9184), np.float32(0.7834), np.float32(0.7126), np.float32(0.6657), np.float32(0.8703), np.float32(0.8058), np.float32(0.9046), np.float32(0.8519), np.float32(0.9769), np.float32(0.9816), np.float32(0.9712), np.float32(0.8419), np.float32(0.7617), np.float32(0.877), np.float32(0.9639), np.float32(0.4171), np.float32(0.393)] +2025-11-13 10:12:16.022532: Epoch time: 258.44 s +2025-11-13 10:12:17.869717: +2025-11-13 10:12:17.871179: Epoch 771 +2025-11-13 10:12:17.872563: Current learning rate: 0.00265 +2025-11-13 10:16:36.684808: train_loss -0.7245 +2025-11-13 10:16:36.689177: val_loss -0.7411 +2025-11-13 10:16:36.690403: Pseudo dice [np.float32(0.9158), np.float32(0.7931), np.float32(0.7113), np.float32(0.6664), np.float32(0.8706), np.float32(0.8161), np.float32(0.8954), np.float32(0.8616), np.float32(0.9789), np.float32(0.9809), np.float32(0.971), np.float32(0.8438), np.float32(0.7924), np.float32(0.8765), np.float32(0.9673), np.float32(0.4602), np.float32(0.4379)] +2025-11-13 10:16:36.691492: Epoch time: 258.82 s +2025-11-13 10:16:38.606916: +2025-11-13 10:16:38.608574: Epoch 772 +2025-11-13 10:16:38.610589: Current learning rate: 0.00264 +2025-11-13 10:20:57.293536: train_loss -0.7213 +2025-11-13 10:20:57.298068: val_loss -0.7288 +2025-11-13 10:20:57.299432: Pseudo dice [np.float32(0.9169), np.float32(0.7849), np.float32(0.7298), np.float32(0.6363), np.float32(0.8687), np.float32(0.8106), np.float32(0.9096), np.float32(0.8709), np.float32(0.98), np.float32(0.9798), np.float32(0.9717), np.float32(0.8501), np.float32(0.7186), np.float32(0.8741), np.float32(0.9648), np.float32(0.4287), np.float32(0.376)] +2025-11-13 10:20:57.300533: Epoch time: 258.69 s +2025-11-13 10:20:59.214853: +2025-11-13 10:20:59.216509: Epoch 773 +2025-11-13 10:20:59.217724: Current learning rate: 0.00263 +2025-11-13 10:25:17.725687: train_loss -0.7183 +2025-11-13 10:25:17.729837: val_loss -0.7305 +2025-11-13 10:25:17.731810: Pseudo dice [np.float32(0.9177), np.float32(0.7725), np.float32(0.7014), np.float32(0.6687), np.float32(0.8765), np.float32(0.8166), np.float32(0.8994), np.float32(0.8572), np.float32(0.9796), np.float32(0.9793), np.float32(0.9692), np.float32(0.8454), np.float32(0.7608), np.float32(0.8815), np.float32(0.9606), np.float32(0.5186), np.float32(0.3486)] +2025-11-13 10:25:17.733572: Epoch time: 258.52 s +2025-11-13 10:25:20.254057: +2025-11-13 10:25:20.255567: Epoch 774 +2025-11-13 10:25:20.256925: Current learning rate: 0.00262 +2025-11-13 10:29:38.720427: train_loss -0.7232 +2025-11-13 10:29:38.725019: val_loss -0.7236 +2025-11-13 10:29:38.726290: Pseudo dice [np.float32(0.9177), np.float32(0.7743), np.float32(0.7206), np.float32(0.6686), np.float32(0.871), np.float32(0.8151), np.float32(0.8975), np.float32(0.863), np.float32(0.9701), np.float32(0.9642), np.float32(0.9697), np.float32(0.845), np.float32(0.7579), np.float32(0.8814), np.float32(0.959), np.float32(0.407), np.float32(0.2445)] +2025-11-13 10:29:38.728033: Epoch time: 258.47 s +2025-11-13 10:29:42.883984: +2025-11-13 10:29:42.885522: Epoch 775 +2025-11-13 10:29:42.886851: Current learning rate: 0.00261 +2025-11-13 10:34:01.345970: train_loss -0.7206 +2025-11-13 10:34:01.350707: val_loss -0.7335 +2025-11-13 10:34:01.352100: Pseudo dice [np.float32(0.9111), np.float32(0.7577), np.float32(0.7345), np.float32(0.66), np.float32(0.8752), np.float32(0.8192), np.float32(0.9113), np.float32(0.8611), np.float32(0.9735), np.float32(0.9732), np.float32(0.9711), np.float32(0.827), np.float32(0.8109), np.float32(0.8851), np.float32(0.9686), np.float32(0.458), np.float32(0.4158)] +2025-11-13 10:34:01.353279: Epoch time: 258.47 s +2025-11-13 10:34:07.872615: +2025-11-13 10:34:07.874276: Epoch 776 +2025-11-13 10:34:07.875676: Current learning rate: 0.0026 +2025-11-13 10:38:26.213790: train_loss -0.7275 +2025-11-13 10:38:26.218209: val_loss -0.7248 +2025-11-13 10:38:26.219494: Pseudo dice [np.float32(0.9158), np.float32(0.7923), np.float32(0.7169), np.float32(0.6731), np.float32(0.8732), np.float32(0.8074), np.float32(0.8891), np.float32(0.8663), np.float32(0.9789), np.float32(0.9759), np.float32(0.9705), np.float32(0.8419), np.float32(0.766), np.float32(0.8815), np.float32(0.9647), np.float32(0.4725), np.float32(0.3059)] +2025-11-13 10:38:26.221146: Epoch time: 258.35 s +2025-11-13 10:38:29.456138: +2025-11-13 10:38:29.457594: Epoch 777 +2025-11-13 10:38:29.458763: Current learning rate: 0.00259 +2025-11-13 10:42:49.378045: train_loss -0.7214 +2025-11-13 10:42:49.381908: val_loss -0.7215 +2025-11-13 10:42:49.383042: Pseudo dice [np.float32(0.9188), np.float32(0.8053), np.float32(0.7147), np.float32(0.6586), np.float32(0.8695), np.float32(0.8035), np.float32(0.8959), np.float32(0.8557), np.float32(0.9798), np.float32(0.9798), np.float32(0.9711), np.float32(0.8367), np.float32(0.7771), np.float32(0.8778), np.float32(0.9632), np.float32(0.3857), np.float32(0.3513)] +2025-11-13 10:42:49.384179: Epoch time: 259.93 s +2025-11-13 10:42:51.587908: +2025-11-13 10:42:51.589517: Epoch 778 +2025-11-13 10:42:51.590719: Current learning rate: 0.00258 +2025-11-13 10:47:10.015105: train_loss -0.7199 +2025-11-13 10:47:10.019513: val_loss -0.7344 +2025-11-13 10:47:10.020854: Pseudo dice [np.float32(0.9179), np.float32(0.7751), np.float32(0.7428), np.float32(0.6963), np.float32(0.8668), np.float32(0.827), np.float32(0.9066), np.float32(0.8638), np.float32(0.9796), np.float32(0.9759), np.float32(0.9706), np.float32(0.8383), np.float32(0.7676), np.float32(0.8795), np.float32(0.9645), np.float32(0.5032), np.float32(0.3947)] +2025-11-13 10:47:10.022344: Epoch time: 258.43 s +2025-11-13 10:47:12.273220: +2025-11-13 10:47:12.275370: Epoch 779 +2025-11-13 10:47:12.276715: Current learning rate: 0.00257 +2025-11-13 10:51:30.904522: train_loss -0.7176 +2025-11-13 10:51:30.908655: val_loss -0.7188 +2025-11-13 10:51:30.910268: Pseudo dice [np.float32(0.9174), np.float32(0.777), np.float32(0.7331), np.float32(0.6641), np.float32(0.8675), np.float32(0.8076), np.float32(0.9086), np.float32(0.8654), np.float32(0.9672), np.float32(0.9639), np.float32(0.9701), np.float32(0.8435), np.float32(0.7446), np.float32(0.8777), np.float32(0.9602), np.float32(0.3092), np.float32(0.3306)] +2025-11-13 10:51:30.911729: Epoch time: 258.64 s +2025-11-13 10:51:33.257569: +2025-11-13 10:51:33.259038: Epoch 780 +2025-11-13 10:51:33.260303: Current learning rate: 0.00256 +2025-11-13 10:55:51.849272: train_loss -0.7214 +2025-11-13 10:55:51.854360: val_loss -0.7335 +2025-11-13 10:55:51.855950: Pseudo dice [np.float32(0.9161), np.float32(0.7854), np.float32(0.7338), np.float32(0.6671), np.float32(0.8697), np.float32(0.8158), np.float32(0.904), np.float32(0.8531), np.float32(0.9761), np.float32(0.9755), np.float32(0.9694), np.float32(0.8496), np.float32(0.8003), np.float32(0.8824), np.float32(0.9529), np.float32(0.4736), np.float32(0.394)] +2025-11-13 10:55:51.857389: Epoch time: 258.6 s +2025-11-13 10:55:53.851067: +2025-11-13 10:55:53.852483: Epoch 781 +2025-11-13 10:55:53.853690: Current learning rate: 0.00255 +2025-11-13 11:00:12.178151: train_loss -0.721 +2025-11-13 11:00:12.182541: val_loss -0.7324 +2025-11-13 11:00:12.183968: Pseudo dice [np.float32(0.9155), np.float32(0.7752), np.float32(0.7071), np.float32(0.6416), np.float32(0.8739), np.float32(0.8206), np.float32(0.9167), np.float32(0.8632), np.float32(0.9799), np.float32(0.9799), np.float32(0.971), np.float32(0.8397), np.float32(0.7698), np.float32(0.8846), np.float32(0.9665), np.float32(0.4481), np.float32(0.4004)] +2025-11-13 11:00:12.185444: Epoch time: 258.33 s +2025-11-13 11:00:14.065372: +2025-11-13 11:00:14.066933: Epoch 782 +2025-11-13 11:00:14.068082: Current learning rate: 0.00254 +2025-11-13 11:04:32.706479: train_loss -0.7238 +2025-11-13 11:04:32.710389: val_loss -0.7266 +2025-11-13 11:04:32.711643: Pseudo dice [np.float32(0.919), np.float32(0.7694), np.float32(0.7201), np.float32(0.6348), np.float32(0.8711), np.float32(0.8165), np.float32(0.9104), np.float32(0.8682), np.float32(0.9801), np.float32(0.9784), np.float32(0.9714), np.float32(0.843), np.float32(0.7709), np.float32(0.8847), np.float32(0.9659), np.float32(0.4295), np.float32(0.3608)] +2025-11-13 11:04:32.713099: Epoch time: 258.65 s +2025-11-13 11:04:34.568245: +2025-11-13 11:04:34.569909: Epoch 783 +2025-11-13 11:04:34.571336: Current learning rate: 0.00253 +2025-11-13 11:08:53.085052: train_loss -0.7225 +2025-11-13 11:08:53.090161: val_loss -0.7365 +2025-11-13 11:08:53.091421: Pseudo dice [np.float32(0.9157), np.float32(0.7848), np.float32(0.7175), np.float32(0.6803), np.float32(0.8721), np.float32(0.8159), np.float32(0.9102), np.float32(0.8544), np.float32(0.9813), np.float32(0.9796), np.float32(0.9714), np.float32(0.8357), np.float32(0.765), np.float32(0.8832), np.float32(0.9687), np.float32(0.4636), np.float32(0.3699)] +2025-11-13 11:08:53.092563: Epoch time: 258.52 s +2025-11-13 11:08:54.957539: +2025-11-13 11:08:54.958968: Epoch 784 +2025-11-13 11:08:54.960459: Current learning rate: 0.00252 +2025-11-13 11:13:13.558289: train_loss -0.7244 +2025-11-13 11:13:13.561771: val_loss -0.726 +2025-11-13 11:13:13.562854: Pseudo dice [np.float32(0.9147), np.float32(0.791), np.float32(0.7421), np.float32(0.6639), np.float32(0.8745), np.float32(0.8183), np.float32(0.9107), np.float32(0.8596), np.float32(0.976), np.float32(0.9781), np.float32(0.9706), np.float32(0.8469), np.float32(0.7638), np.float32(0.8835), np.float32(0.9642), np.float32(0.4057), np.float32(0.3459)] +2025-11-13 11:13:13.564086: Epoch time: 258.61 s +2025-11-13 11:13:15.432453: +2025-11-13 11:13:15.433877: Epoch 785 +2025-11-13 11:13:15.435118: Current learning rate: 0.00251 +2025-11-13 11:17:33.757494: train_loss -0.7229 +2025-11-13 11:17:33.761517: val_loss -0.7233 +2025-11-13 11:17:33.763238: Pseudo dice [np.float32(0.9206), np.float32(0.7878), np.float32(0.7319), np.float32(0.6805), np.float32(0.8641), np.float32(0.8218), np.float32(0.898), np.float32(0.8553), np.float32(0.9692), np.float32(0.9675), np.float32(0.9689), np.float32(0.8349), np.float32(0.7653), np.float32(0.8701), np.float32(0.9569), np.float32(0.3319), np.float32(0.3565)] +2025-11-13 11:17:33.764623: Epoch time: 258.33 s +2025-11-13 11:17:35.573221: +2025-11-13 11:17:35.574828: Epoch 786 +2025-11-13 11:17:35.576154: Current learning rate: 0.0025 +2025-11-13 11:21:54.957010: train_loss -0.7232 +2025-11-13 11:21:54.961675: val_loss -0.7221 +2025-11-13 11:21:54.962958: Pseudo dice [np.float32(0.9135), np.float32(0.7981), np.float32(0.7659), np.float32(0.6826), np.float32(0.8689), np.float32(0.8024), np.float32(0.8947), np.float32(0.8517), np.float32(0.9822), np.float32(0.9772), np.float32(0.9721), np.float32(0.8483), np.float32(0.777), np.float32(0.8792), np.float32(0.9661), np.float32(0.3215), np.float32(0.4283)] +2025-11-13 11:21:54.964156: Epoch time: 259.39 s +2025-11-13 11:21:57.338776: +2025-11-13 11:21:57.340160: Epoch 787 +2025-11-13 11:21:57.341436: Current learning rate: 0.00249 +2025-11-13 11:26:15.869591: train_loss -0.7235 +2025-11-13 11:26:15.874254: val_loss -0.7256 +2025-11-13 11:26:15.875918: Pseudo dice [np.float32(0.912), np.float32(0.775), np.float32(0.7358), np.float32(0.6625), np.float32(0.8784), np.float32(0.8133), np.float32(0.9089), np.float32(0.8656), np.float32(0.9787), np.float32(0.9767), np.float32(0.9701), np.float32(0.8414), np.float32(0.7646), np.float32(0.887), np.float32(0.9626), np.float32(0.4341), np.float32(0.4291)] +2025-11-13 11:26:15.877244: Epoch time: 258.54 s +2025-11-13 11:26:17.915838: +2025-11-13 11:26:17.917714: Epoch 788 +2025-11-13 11:26:17.919509: Current learning rate: 0.00248 +2025-11-13 11:30:36.303875: train_loss -0.7217 +2025-11-13 11:30:36.308192: val_loss -0.7332 +2025-11-13 11:30:36.309606: Pseudo dice [np.float32(0.9188), np.float32(0.7763), np.float32(0.7527), np.float32(0.6466), np.float32(0.8729), np.float32(0.8264), np.float32(0.9068), np.float32(0.8699), np.float32(0.9743), np.float32(0.9745), np.float32(0.969), np.float32(0.8419), np.float32(0.7629), np.float32(0.8863), np.float32(0.9582), np.float32(0.3846), np.float32(0.4367)] +2025-11-13 11:30:36.311022: Epoch time: 258.4 s +2025-11-13 11:30:38.170081: +2025-11-13 11:30:38.171507: Epoch 789 +2025-11-13 11:30:38.172864: Current learning rate: 0.00247 +2025-11-13 11:34:56.568667: train_loss -0.7253 +2025-11-13 11:34:56.573379: val_loss -0.7308 +2025-11-13 11:34:56.575182: Pseudo dice [np.float32(0.9184), np.float32(0.7717), np.float32(0.7084), np.float32(0.6858), np.float32(0.8791), np.float32(0.804), np.float32(0.91), np.float32(0.8618), np.float32(0.9805), np.float32(0.979), np.float32(0.9713), np.float32(0.8373), np.float32(0.7553), np.float32(0.8854), np.float32(0.9668), np.float32(0.4276), np.float32(0.3798)] +2025-11-13 11:34:56.576835: Epoch time: 258.4 s +2025-11-13 11:34:58.416816: +2025-11-13 11:34:58.420732: Epoch 790 +2025-11-13 11:34:58.422706: Current learning rate: 0.00245 +2025-11-13 11:39:16.973148: train_loss -0.7199 +2025-11-13 11:39:16.976993: val_loss -0.7383 +2025-11-13 11:39:16.978651: Pseudo dice [np.float32(0.9161), np.float32(0.7934), np.float32(0.7537), np.float32(0.6828), np.float32(0.8655), np.float32(0.8265), np.float32(0.9067), np.float32(0.8542), np.float32(0.9747), np.float32(0.9745), np.float32(0.9714), np.float32(0.8256), np.float32(0.7979), np.float32(0.8764), np.float32(0.9654), np.float32(0.4917), np.float32(0.3748)] +2025-11-13 11:39:16.979845: Epoch time: 258.56 s +2025-11-13 11:39:16.981163: Yayy! New best EMA pseudo Dice: 0.8077999949455261 +2025-11-13 11:40:46.827853: +2025-11-13 11:40:46.830358: Epoch 791 +2025-11-13 11:40:46.831802: Current learning rate: 0.00244 +2025-11-13 11:45:04.379573: train_loss -0.7229 +2025-11-13 11:45:04.384465: val_loss -0.7378 +2025-11-13 11:45:04.386068: Pseudo dice [np.float32(0.9208), np.float32(0.8075), np.float32(0.7334), np.float32(0.6521), np.float32(0.8736), np.float32(0.8179), np.float32(0.9053), np.float32(0.8585), np.float32(0.9805), np.float32(0.9759), np.float32(0.9703), np.float32(0.8334), np.float32(0.7648), np.float32(0.884), np.float32(0.9657), np.float32(0.4881), np.float32(0.3949)] +2025-11-13 11:45:04.387497: Epoch time: 257.56 s +2025-11-13 11:45:04.388767: Yayy! New best EMA pseudo Dice: 0.8083000183105469 +2025-11-13 11:45:09.548561: +2025-11-13 11:45:09.550259: Epoch 792 +2025-11-13 11:45:09.551527: Current learning rate: 0.00243 +2025-11-13 11:49:27.873136: train_loss -0.7223 +2025-11-13 11:49:27.876765: val_loss -0.7238 +2025-11-13 11:49:27.877980: Pseudo dice [np.float32(0.917), np.float32(0.7785), np.float32(0.7383), np.float32(0.6486), np.float32(0.8761), np.float32(0.8132), np.float32(0.9006), np.float32(0.8664), np.float32(0.9748), np.float32(0.9747), np.float32(0.9707), np.float32(0.8408), np.float32(0.7638), np.float32(0.8722), np.float32(0.9658), np.float32(0.3549), np.float32(0.346)] +2025-11-13 11:49:27.879123: Epoch time: 258.33 s +2025-11-13 11:49:29.732886: +2025-11-13 11:49:29.734304: Epoch 793 +2025-11-13 11:49:29.735541: Current learning rate: 0.00242 +2025-11-13 11:53:48.221539: train_loss -0.7184 +2025-11-13 11:53:48.225944: val_loss -0.7349 +2025-11-13 11:53:48.227174: Pseudo dice [np.float32(0.9144), np.float32(0.8005), np.float32(0.7485), np.float32(0.6555), np.float32(0.8745), np.float32(0.8255), np.float32(0.8997), np.float32(0.8621), np.float32(0.9773), np.float32(0.9723), np.float32(0.9708), np.float32(0.8439), np.float32(0.764), np.float32(0.8801), np.float32(0.9637), np.float32(0.4483), np.float32(0.3587)] +2025-11-13 11:53:48.228594: Epoch time: 258.49 s +2025-11-13 11:53:50.091422: +2025-11-13 11:53:50.093085: Epoch 794 +2025-11-13 11:53:50.094484: Current learning rate: 0.00241 +2025-11-13 11:58:08.465215: train_loss -0.7209 +2025-11-13 11:58:08.469451: val_loss -0.7298 +2025-11-13 11:58:08.470852: Pseudo dice [np.float32(0.9074), np.float32(0.7882), np.float32(0.7234), np.float32(0.654), np.float32(0.8697), np.float32(0.8283), np.float32(0.8985), np.float32(0.8555), np.float32(0.9786), np.float32(0.979), np.float32(0.9712), np.float32(0.8361), np.float32(0.7782), np.float32(0.881), np.float32(0.969), np.float32(0.3986), np.float32(0.4281)] +2025-11-13 11:58:08.472071: Epoch time: 258.38 s +2025-11-13 11:58:10.229742: +2025-11-13 11:58:10.231167: Epoch 795 +2025-11-13 11:58:10.232417: Current learning rate: 0.0024 +2025-11-13 12:02:29.053384: train_loss -0.7255 +2025-11-13 12:02:29.058270: val_loss -0.7254 +2025-11-13 12:02:29.059785: Pseudo dice [np.float32(0.9153), np.float32(0.8009), np.float32(0.7333), np.float32(0.6546), np.float32(0.8683), np.float32(0.8201), np.float32(0.9023), np.float32(0.8657), np.float32(0.9778), np.float32(0.9778), np.float32(0.9708), np.float32(0.8462), np.float32(0.7766), np.float32(0.8824), np.float32(0.9676), np.float32(0.3544), np.float32(0.3811)] +2025-11-13 12:02:29.061181: Epoch time: 258.83 s +2025-11-13 12:02:30.903468: +2025-11-13 12:02:30.905073: Epoch 796 +2025-11-13 12:02:30.906423: Current learning rate: 0.00239 +2025-11-13 12:06:49.021874: train_loss -0.7261 +2025-11-13 12:06:49.025803: val_loss -0.7341 +2025-11-13 12:06:49.027331: Pseudo dice [np.float32(0.9228), np.float32(0.7949), np.float32(0.7127), np.float32(0.6622), np.float32(0.8669), np.float32(0.8149), np.float32(0.9071), np.float32(0.8614), np.float32(0.9788), np.float32(0.9795), np.float32(0.9713), np.float32(0.8482), np.float32(0.8011), np.float32(0.8786), np.float32(0.9668), np.float32(0.4148), np.float32(0.3906)] +2025-11-13 12:06:49.028481: Epoch time: 258.12 s +2025-11-13 12:06:50.877872: +2025-11-13 12:06:50.879207: Epoch 797 +2025-11-13 12:06:50.880384: Current learning rate: 0.00238 +2025-11-13 12:11:08.991084: train_loss -0.7204 +2025-11-13 12:11:08.995921: val_loss -0.7298 +2025-11-13 12:11:08.997570: Pseudo dice [np.float32(0.9242), np.float32(0.7693), np.float32(0.7437), np.float32(0.6589), np.float32(0.8732), np.float32(0.8021), np.float32(0.9074), np.float32(0.8711), np.float32(0.9786), np.float32(0.978), np.float32(0.9714), np.float32(0.8391), np.float32(0.771), np.float32(0.8814), np.float32(0.9659), np.float32(0.4188), np.float32(0.3907)] +2025-11-13 12:11:08.998827: Epoch time: 258.12 s +2025-11-13 12:11:10.774256: +2025-11-13 12:11:10.775689: Epoch 798 +2025-11-13 12:11:10.777172: Current learning rate: 0.00237 +2025-11-13 12:15:28.903713: train_loss -0.7226 +2025-11-13 12:15:28.908521: val_loss -0.732 +2025-11-13 12:15:28.909680: Pseudo dice [np.float32(0.9135), np.float32(0.7915), np.float32(0.7452), np.float32(0.6796), np.float32(0.8679), np.float32(0.7961), np.float32(0.91), np.float32(0.8483), np.float32(0.9783), np.float32(0.9772), np.float32(0.9717), np.float32(0.8334), np.float32(0.7467), np.float32(0.8802), np.float32(0.9637), np.float32(0.4673), np.float32(0.4619)] +2025-11-13 12:15:28.910875: Epoch time: 258.13 s +2025-11-13 12:15:28.912062: Yayy! New best EMA pseudo Dice: 0.8084999918937683 +2025-11-13 12:15:33.627573: +2025-11-13 12:15:33.629058: Epoch 799 +2025-11-13 12:15:33.630584: Current learning rate: 0.00236 +2025-11-13 12:19:51.658289: train_loss -0.7263 +2025-11-13 12:19:51.663409: val_loss -0.7327 +2025-11-13 12:19:51.664852: Pseudo dice [np.float32(0.9198), np.float32(0.7804), np.float32(0.7237), np.float32(0.6609), np.float32(0.8661), np.float32(0.8264), np.float32(0.9059), np.float32(0.8612), np.float32(0.9791), np.float32(0.9777), np.float32(0.9702), np.float32(0.8462), np.float32(0.7665), np.float32(0.8798), np.float32(0.9641), np.float32(0.4051), np.float32(0.3513)] +2025-11-13 12:19:51.666406: Epoch time: 258.04 s +2025-11-13 12:19:56.394666: +2025-11-13 12:19:56.396123: Epoch 800 +2025-11-13 12:19:56.397463: Current learning rate: 0.00235 +2025-11-13 12:24:14.354066: train_loss -0.7207 +2025-11-13 12:24:14.358186: val_loss -0.7306 +2025-11-13 12:24:14.359829: Pseudo dice [np.float32(0.9229), np.float32(0.82), np.float32(0.7252), np.float32(0.6424), np.float32(0.8748), np.float32(0.813), np.float32(0.9047), np.float32(0.8629), np.float32(0.9785), np.float32(0.9798), np.float32(0.9711), np.float32(0.8406), np.float32(0.7924), np.float32(0.8837), np.float32(0.9647), np.float32(0.4849), np.float32(0.4014)] +2025-11-13 12:24:14.361125: Epoch time: 257.96 s +2025-11-13 12:24:14.362826: Yayy! New best EMA pseudo Dice: 0.8087999820709229 +2025-11-13 12:24:19.415842: +2025-11-13 12:24:19.417266: Epoch 801 +2025-11-13 12:24:19.418498: Current learning rate: 0.00234 +2025-11-13 12:28:37.324874: train_loss -0.7248 +2025-11-13 12:28:37.329545: val_loss -0.7311 +2025-11-13 12:28:37.331770: Pseudo dice [np.float32(0.9145), np.float32(0.7634), np.float32(0.7263), np.float32(0.7), np.float32(0.8729), np.float32(0.8235), np.float32(0.9101), np.float32(0.8627), np.float32(0.9807), np.float32(0.9802), np.float32(0.9715), np.float32(0.8409), np.float32(0.7762), np.float32(0.8799), np.float32(0.9663), np.float32(0.4366), np.float32(0.3825)] +2025-11-13 12:28:37.334332: Epoch time: 257.91 s +2025-11-13 12:28:37.335704: Yayy! New best EMA pseudo Dice: 0.8090999722480774 +2025-11-13 12:28:42.451222: +2025-11-13 12:28:42.452648: Epoch 802 +2025-11-13 12:28:42.453807: Current learning rate: 0.00233 +2025-11-13 12:33:00.387174: train_loss -0.7267 +2025-11-13 12:33:00.392043: val_loss -0.7265 +2025-11-13 12:33:00.393399: Pseudo dice [np.float32(0.9158), np.float32(0.7992), np.float32(0.7133), np.float32(0.6842), np.float32(0.87), np.float32(0.817), np.float32(0.9066), np.float32(0.8717), np.float32(0.9794), np.float32(0.9795), np.float32(0.9703), np.float32(0.8521), np.float32(0.7592), np.float32(0.8822), np.float32(0.9697), np.float32(0.39), np.float32(0.3222)] +2025-11-13 12:33:00.397379: Epoch time: 257.94 s +2025-11-13 12:33:03.024384: +2025-11-13 12:33:03.025782: Epoch 803 +2025-11-13 12:33:03.027113: Current learning rate: 0.00232 +2025-11-13 12:37:21.285809: train_loss -0.7281 +2025-11-13 12:37:21.292753: val_loss -0.7236 +2025-11-13 12:37:21.294214: Pseudo dice [np.float32(0.9163), np.float32(0.7956), np.float32(0.7167), np.float32(0.6822), np.float32(0.8666), np.float32(0.8108), np.float32(0.9031), np.float32(0.8608), np.float32(0.9755), np.float32(0.9771), np.float32(0.9705), np.float32(0.8451), np.float32(0.7737), np.float32(0.8681), np.float32(0.9676), np.float32(0.373), np.float32(0.3665)] +2025-11-13 12:37:21.295907: Epoch time: 258.27 s +2025-11-13 12:37:23.120141: +2025-11-13 12:37:23.121574: Epoch 804 +2025-11-13 12:37:23.123077: Current learning rate: 0.00231 +2025-11-13 12:41:43.083643: train_loss -0.7226 +2025-11-13 12:41:43.088283: val_loss -0.7231 +2025-11-13 12:41:43.089698: Pseudo dice [np.float32(0.896), np.float32(0.7535), np.float32(0.736), np.float32(0.6681), np.float32(0.8689), np.float32(0.8047), np.float32(0.9097), np.float32(0.8467), np.float32(0.9804), np.float32(0.9801), np.float32(0.9696), np.float32(0.8413), np.float32(0.7435), np.float32(0.8747), np.float32(0.9653), np.float32(0.4021), np.float32(0.3748)] +2025-11-13 12:41:43.090879: Epoch time: 259.97 s +2025-11-13 12:41:44.868945: +2025-11-13 12:41:44.870254: Epoch 805 +2025-11-13 12:41:44.871478: Current learning rate: 0.0023 +2025-11-13 12:46:03.152983: train_loss -0.7241 +2025-11-13 12:46:03.156753: val_loss -0.7327 +2025-11-13 12:46:03.157942: Pseudo dice [np.float32(0.911), np.float32(0.7793), np.float32(0.7398), np.float32(0.6751), np.float32(0.8709), np.float32(0.821), np.float32(0.9166), np.float32(0.8622), np.float32(0.9745), np.float32(0.9748), np.float32(0.9703), np.float32(0.8383), np.float32(0.7694), np.float32(0.886), np.float32(0.9636), np.float32(0.4738), np.float32(0.4204)] +2025-11-13 12:46:03.159687: Epoch time: 258.29 s +2025-11-13 12:46:05.128803: +2025-11-13 12:46:05.130167: Epoch 806 +2025-11-13 12:46:05.131695: Current learning rate: 0.00229 +2025-11-13 12:50:23.226121: train_loss -0.7237 +2025-11-13 12:50:23.230080: val_loss -0.7333 +2025-11-13 12:50:23.231686: Pseudo dice [np.float32(0.9263), np.float32(0.8123), np.float32(0.751), np.float32(0.6672), np.float32(0.8742), np.float32(0.8288), np.float32(0.9026), np.float32(0.8645), np.float32(0.9799), np.float32(0.9775), np.float32(0.9705), np.float32(0.8363), np.float32(0.7334), np.float32(0.8828), np.float32(0.9649), np.float32(0.5234), np.float32(0.4318)] +2025-11-13 12:50:23.232938: Epoch time: 258.1 s +2025-11-13 12:50:23.233895: Yayy! New best EMA pseudo Dice: 0.8093000054359436 +2025-11-13 12:50:27.939348: +2025-11-13 12:50:27.940733: Epoch 807 +2025-11-13 12:50:27.942171: Current learning rate: 0.00228 +2025-11-13 12:54:46.297207: train_loss -0.7209 +2025-11-13 12:54:46.301078: val_loss -0.7347 +2025-11-13 12:54:46.302361: Pseudo dice [np.float32(0.9173), np.float32(0.7792), np.float32(0.7159), np.float32(0.672), np.float32(0.869), np.float32(0.8153), np.float32(0.9112), np.float32(0.8708), np.float32(0.9732), np.float32(0.9713), np.float32(0.9711), np.float32(0.8419), np.float32(0.7629), np.float32(0.8834), np.float32(0.9647), np.float32(0.502), np.float32(0.3948)] +2025-11-13 12:54:46.303506: Epoch time: 258.36 s +2025-11-13 12:54:46.304659: Yayy! New best EMA pseudo Dice: 0.8095999956130981 +2025-11-13 12:54:51.288922: +2025-11-13 12:54:51.290701: Epoch 808 +2025-11-13 12:54:51.292462: Current learning rate: 0.00226 +2025-11-13 12:59:09.550325: train_loss -0.7237 +2025-11-13 12:59:09.553847: val_loss -0.723 +2025-11-13 12:59:09.554872: Pseudo dice [np.float32(0.9139), np.float32(0.7759), np.float32(0.7431), np.float32(0.6573), np.float32(0.8741), np.float32(0.8227), np.float32(0.9098), np.float32(0.8657), np.float32(0.9682), np.float32(0.9654), np.float32(0.971), np.float32(0.8392), np.float32(0.7394), np.float32(0.8863), np.float32(0.9667), np.float32(0.3454), np.float32(0.3304)] +2025-11-13 12:59:09.556184: Epoch time: 258.27 s +2025-11-13 12:59:11.417935: +2025-11-13 12:59:11.419862: Epoch 809 +2025-11-13 12:59:11.421753: Current learning rate: 0.00225 +2025-11-13 13:03:29.963505: train_loss -0.7244 +2025-11-13 13:03:29.968177: val_loss -0.7154 +2025-11-13 13:03:29.969285: Pseudo dice [np.float32(0.911), np.float32(0.7663), np.float32(0.7318), np.float32(0.6294), np.float32(0.8703), np.float32(0.8131), np.float32(0.9117), np.float32(0.8694), np.float32(0.9801), np.float32(0.9792), np.float32(0.9704), np.float32(0.8421), np.float32(0.7584), np.float32(0.8805), np.float32(0.9661), np.float32(0.3224), np.float32(0.3384)] +2025-11-13 13:03:29.970389: Epoch time: 258.55 s +2025-11-13 13:03:31.761835: +2025-11-13 13:03:31.763293: Epoch 810 +2025-11-13 13:03:31.764551: Current learning rate: 0.00224 +2025-11-13 13:07:50.250506: train_loss -0.7268 +2025-11-13 13:07:50.255156: val_loss -0.7273 +2025-11-13 13:07:50.257056: Pseudo dice [np.float32(0.9203), np.float32(0.7912), np.float32(0.7202), np.float32(0.6531), np.float32(0.8691), np.float32(0.8329), np.float32(0.9141), np.float32(0.8634), np.float32(0.9778), np.float32(0.9784), np.float32(0.9727), np.float32(0.8405), np.float32(0.7602), np.float32(0.8794), np.float32(0.9674), np.float32(0.3643), np.float32(0.3762)] +2025-11-13 13:07:50.258326: Epoch time: 258.49 s +2025-11-13 13:07:52.075214: +2025-11-13 13:07:52.076656: Epoch 811 +2025-11-13 13:07:52.078029: Current learning rate: 0.00223 +2025-11-13 13:12:10.487600: train_loss -0.7245 +2025-11-13 13:12:10.491721: val_loss -0.7288 +2025-11-13 13:12:10.493175: Pseudo dice [np.float32(0.9108), np.float32(0.795), np.float32(0.7236), np.float32(0.6514), np.float32(0.8736), np.float32(0.8068), np.float32(0.9097), np.float32(0.8637), np.float32(0.978), np.float32(0.9784), np.float32(0.9698), np.float32(0.8389), np.float32(0.7681), np.float32(0.8812), np.float32(0.965), np.float32(0.4465), np.float32(0.391)] +2025-11-13 13:12:10.494381: Epoch time: 258.42 s +2025-11-13 13:12:12.228582: +2025-11-13 13:12:12.230032: Epoch 812 +2025-11-13 13:12:12.231287: Current learning rate: 0.00222 +2025-11-13 13:16:30.724816: train_loss -0.7239 +2025-11-13 13:16:30.729087: val_loss -0.7309 +2025-11-13 13:16:30.730404: Pseudo dice [np.float32(0.9109), np.float32(0.7864), np.float32(0.7488), np.float32(0.6646), np.float32(0.8792), np.float32(0.833), np.float32(0.918), np.float32(0.8494), np.float32(0.9801), np.float32(0.979), np.float32(0.972), np.float32(0.8422), np.float32(0.7668), np.float32(0.8868), np.float32(0.9661), np.float32(0.4615), np.float32(0.4033)] +2025-11-13 13:16:30.731967: Epoch time: 258.5 s +2025-11-13 13:16:32.534463: +2025-11-13 13:16:32.536162: Epoch 813 +2025-11-13 13:16:32.538033: Current learning rate: 0.00221 +2025-11-13 13:20:51.864771: train_loss -0.7221 +2025-11-13 13:20:51.869054: val_loss -0.7412 +2025-11-13 13:20:51.870362: Pseudo dice [np.float32(0.9259), np.float32(0.8037), np.float32(0.7597), np.float32(0.6599), np.float32(0.8723), np.float32(0.8076), np.float32(0.9119), np.float32(0.8702), np.float32(0.9788), np.float32(0.9801), np.float32(0.9714), np.float32(0.8414), np.float32(0.7644), np.float32(0.8859), np.float32(0.9673), np.float32(0.4316), np.float32(0.4734)] +2025-11-13 13:20:51.871587: Epoch time: 259.34 s +2025-11-13 13:20:53.703030: +2025-11-13 13:20:53.704558: Epoch 814 +2025-11-13 13:20:53.705996: Current learning rate: 0.0022 +2025-11-13 13:25:12.287954: train_loss -0.7294 +2025-11-13 13:25:12.292266: val_loss -0.7371 +2025-11-13 13:25:12.293510: Pseudo dice [np.float32(0.9093), np.float32(0.8045), np.float32(0.7347), np.float32(0.7041), np.float32(0.8714), np.float32(0.8049), np.float32(0.9063), np.float32(0.8596), np.float32(0.9762), np.float32(0.977), np.float32(0.9699), np.float32(0.8475), np.float32(0.7788), np.float32(0.8829), np.float32(0.9649), np.float32(0.5182), np.float32(0.3579)] +2025-11-13 13:25:12.294781: Epoch time: 258.59 s +2025-11-13 13:25:12.295977: Yayy! New best EMA pseudo Dice: 0.8097000122070312 +2025-11-13 13:25:16.984169: +2025-11-13 13:25:16.985732: Epoch 815 +2025-11-13 13:25:16.987069: Current learning rate: 0.00219 +2025-11-13 13:29:35.416815: train_loss -0.7233 +2025-11-13 13:29:35.420804: val_loss -0.7312 +2025-11-13 13:29:35.422235: Pseudo dice [np.float32(0.9185), np.float32(0.7782), np.float32(0.7231), np.float32(0.6613), np.float32(0.8752), np.float32(0.806), np.float32(0.899), np.float32(0.8527), np.float32(0.9806), np.float32(0.9802), np.float32(0.9705), np.float32(0.8265), np.float32(0.7739), np.float32(0.8781), np.float32(0.9643), np.float32(0.4524), np.float32(0.3068)] +2025-11-13 13:29:35.423570: Epoch time: 258.44 s +2025-11-13 13:29:37.266068: +2025-11-13 13:29:37.267501: Epoch 816 +2025-11-13 13:29:37.269228: Current learning rate: 0.00218 +2025-11-13 13:33:55.691947: train_loss -0.7266 +2025-11-13 13:33:55.697187: val_loss -0.7287 +2025-11-13 13:33:55.698466: Pseudo dice [np.float32(0.923), np.float32(0.8186), np.float32(0.7315), np.float32(0.6684), np.float32(0.8743), np.float32(0.8235), np.float32(0.8951), np.float32(0.8627), np.float32(0.9808), np.float32(0.9814), np.float32(0.9712), np.float32(0.8388), np.float32(0.7534), np.float32(0.8848), np.float32(0.966), np.float32(0.467), np.float32(0.3659)] +2025-11-13 13:33:55.700371: Epoch time: 258.43 s +2025-11-13 13:33:57.665010: +2025-11-13 13:33:57.666679: Epoch 817 +2025-11-13 13:33:57.668278: Current learning rate: 0.00217 +2025-11-13 13:38:15.958110: train_loss -0.727 +2025-11-13 13:38:15.962656: val_loss -0.734 +2025-11-13 13:38:15.963850: Pseudo dice [np.float32(0.9147), np.float32(0.8356), np.float32(0.7208), np.float32(0.687), np.float32(0.8726), np.float32(0.8092), np.float32(0.9124), np.float32(0.8695), np.float32(0.9752), np.float32(0.9769), np.float32(0.9703), np.float32(0.8527), np.float32(0.7809), np.float32(0.879), np.float32(0.9638), np.float32(0.4594), np.float32(0.4182)] +2025-11-13 13:38:15.967938: Epoch time: 258.3 s +2025-11-13 13:38:15.969492: Yayy! New best EMA pseudo Dice: 0.8101000189781189 +2025-11-13 13:38:20.730422: +2025-11-13 13:38:20.732394: Epoch 818 +2025-11-13 13:38:20.733865: Current learning rate: 0.00216 +2025-11-13 13:42:39.082916: train_loss -0.7192 +2025-11-13 13:42:39.086674: val_loss -0.7306 +2025-11-13 13:42:39.087806: Pseudo dice [np.float32(0.9169), np.float32(0.7859), np.float32(0.7285), np.float32(0.6918), np.float32(0.8787), np.float32(0.8343), np.float32(0.9042), np.float32(0.8694), np.float32(0.9792), np.float32(0.9813), np.float32(0.9711), np.float32(0.8394), np.float32(0.7941), np.float32(0.8883), np.float32(0.9651), np.float32(0.396), np.float32(0.4197)] +2025-11-13 13:42:39.088988: Epoch time: 258.36 s +2025-11-13 13:42:39.090174: Yayy! New best EMA pseudo Dice: 0.8105000257492065 +2025-11-13 13:42:44.256244: +2025-11-13 13:42:44.257760: Epoch 819 +2025-11-13 13:42:44.259010: Current learning rate: 0.00215 +2025-11-13 13:47:02.828643: train_loss -0.721 +2025-11-13 13:47:02.833087: val_loss -0.7316 +2025-11-13 13:47:02.834437: Pseudo dice [np.float32(0.9111), np.float32(0.7823), np.float32(0.7122), np.float32(0.6691), np.float32(0.8663), np.float32(0.82), np.float32(0.9093), np.float32(0.8658), np.float32(0.9791), np.float32(0.9809), np.float32(0.9716), np.float32(0.8308), np.float32(0.7773), np.float32(0.8792), np.float32(0.9663), np.float32(0.3931), np.float32(0.3505)] +2025-11-13 13:47:02.835680: Epoch time: 258.58 s +2025-11-13 13:47:04.567524: +2025-11-13 13:47:04.569023: Epoch 820 +2025-11-13 13:47:04.570419: Current learning rate: 0.00214 +2025-11-13 13:51:23.185679: train_loss -0.7259 +2025-11-13 13:51:23.190120: val_loss -0.7296 +2025-11-13 13:51:23.191643: Pseudo dice [np.float32(0.9174), np.float32(0.7785), np.float32(0.7192), np.float32(0.6828), np.float32(0.8751), np.float32(0.7992), np.float32(0.9006), np.float32(0.8636), np.float32(0.9791), np.float32(0.9797), np.float32(0.9707), np.float32(0.8429), np.float32(0.7614), np.float32(0.8834), np.float32(0.965), np.float32(0.4296), np.float32(0.3677)] +2025-11-13 13:51:23.192789: Epoch time: 258.62 s +2025-11-13 13:51:24.904906: +2025-11-13 13:51:24.906414: Epoch 821 +2025-11-13 13:51:24.907925: Current learning rate: 0.00213 +2025-11-13 13:55:43.090104: train_loss -0.7236 +2025-11-13 13:55:43.093724: val_loss -0.7351 +2025-11-13 13:55:43.094827: Pseudo dice [np.float32(0.9205), np.float32(0.8003), np.float32(0.7307), np.float32(0.689), np.float32(0.863), np.float32(0.8103), np.float32(0.9148), np.float32(0.8709), np.float32(0.9763), np.float32(0.9746), np.float32(0.9719), np.float32(0.8414), np.float32(0.7642), np.float32(0.8733), np.float32(0.9616), np.float32(0.4027), np.float32(0.4225)] +2025-11-13 13:55:43.096013: Epoch time: 258.19 s +2025-11-13 13:55:46.698254: +2025-11-13 13:55:46.699753: Epoch 822 +2025-11-13 13:55:46.701264: Current learning rate: 0.00212 +2025-11-13 14:00:04.748667: train_loss -0.7226 +2025-11-13 14:00:04.752140: val_loss -0.7468 +2025-11-13 14:00:04.753160: Pseudo dice [np.float32(0.9263), np.float32(0.8075), np.float32(0.7339), np.float32(0.6564), np.float32(0.8778), np.float32(0.8317), np.float32(0.9093), np.float32(0.8694), np.float32(0.9813), np.float32(0.982), np.float32(0.9712), np.float32(0.8465), np.float32(0.7912), np.float32(0.8849), np.float32(0.9666), np.float32(0.4649), np.float32(0.3698)] +2025-11-13 14:00:04.754156: Epoch time: 258.06 s +2025-11-13 14:00:06.538825: +2025-11-13 14:00:06.540187: Epoch 823 +2025-11-13 14:00:06.541587: Current learning rate: 0.0021 +2025-11-13 14:04:24.571356: train_loss -0.7262 +2025-11-13 14:04:24.575837: val_loss -0.7309 +2025-11-13 14:04:24.577399: Pseudo dice [np.float32(0.9172), np.float32(0.7821), np.float32(0.7277), np.float32(0.6849), np.float32(0.8687), np.float32(0.8221), np.float32(0.9063), np.float32(0.8597), np.float32(0.9814), np.float32(0.982), np.float32(0.9709), np.float32(0.8283), np.float32(0.7721), np.float32(0.8798), np.float32(0.9674), np.float32(0.3963), np.float32(0.4417)] +2025-11-13 14:04:24.578789: Epoch time: 258.04 s +2025-11-13 14:04:26.348048: +2025-11-13 14:04:26.349483: Epoch 824 +2025-11-13 14:04:26.350762: Current learning rate: 0.00209 +2025-11-13 14:08:44.382583: train_loss -0.7265 +2025-11-13 14:08:44.386374: val_loss -0.7266 +2025-11-13 14:08:44.388124: Pseudo dice [np.float32(0.9196), np.float32(0.7962), np.float32(0.7209), np.float32(0.6746), np.float32(0.8714), np.float32(0.816), np.float32(0.9143), np.float32(0.8602), np.float32(0.98), np.float32(0.9817), np.float32(0.971), np.float32(0.8382), np.float32(0.7501), np.float32(0.88), np.float32(0.9625), np.float32(0.415), np.float32(0.397)] +2025-11-13 14:08:44.389279: Epoch time: 258.04 s +2025-11-13 14:08:46.171427: +2025-11-13 14:08:46.172835: Epoch 825 +2025-11-13 14:08:46.174697: Current learning rate: 0.00208 +2025-11-13 14:13:04.179846: train_loss -0.7258 +2025-11-13 14:13:04.183853: val_loss -0.7235 +2025-11-13 14:13:04.185154: Pseudo dice [np.float32(0.919), np.float32(0.793), np.float32(0.7265), np.float32(0.6526), np.float32(0.868), np.float32(0.8114), np.float32(0.9137), np.float32(0.8598), np.float32(0.9792), np.float32(0.9813), np.float32(0.971), np.float32(0.8428), np.float32(0.7531), np.float32(0.8786), np.float32(0.9651), np.float32(0.4027), np.float32(0.414)] +2025-11-13 14:13:04.186505: Epoch time: 258.01 s +2025-11-13 14:13:05.898642: +2025-11-13 14:13:05.900388: Epoch 826 +2025-11-13 14:13:05.901879: Current learning rate: 0.00207 +2025-11-13 14:17:24.118106: train_loss -0.7246 +2025-11-13 14:17:24.122316: val_loss -0.7274 +2025-11-13 14:17:24.123701: Pseudo dice [np.float32(0.9185), np.float32(0.7849), np.float32(0.7432), np.float32(0.6607), np.float32(0.8641), np.float32(0.8158), np.float32(0.9027), np.float32(0.8476), np.float32(0.9783), np.float32(0.9796), np.float32(0.9699), np.float32(0.8383), np.float32(0.7676), np.float32(0.8765), np.float32(0.9657), np.float32(0.4203), np.float32(0.4086)] +2025-11-13 14:17:24.125520: Epoch time: 258.23 s +2025-11-13 14:17:25.880327: +2025-11-13 14:17:25.881821: Epoch 827 +2025-11-13 14:17:25.883189: Current learning rate: 0.00206 +2025-11-13 14:21:43.906732: train_loss -0.7218 +2025-11-13 14:21:43.910829: val_loss -0.7272 +2025-11-13 14:21:43.912058: Pseudo dice [np.float32(0.9057), np.float32(0.8026), np.float32(0.7366), np.float32(0.678), np.float32(0.8711), np.float32(0.8278), np.float32(0.9111), np.float32(0.8557), np.float32(0.9763), np.float32(0.9748), np.float32(0.9705), np.float32(0.8449), np.float32(0.7643), np.float32(0.8869), np.float32(0.9654), np.float32(0.4247), np.float32(0.3496)] +2025-11-13 14:21:43.913526: Epoch time: 258.03 s +2025-11-13 14:21:45.628245: +2025-11-13 14:21:45.629754: Epoch 828 +2025-11-13 14:21:45.631334: Current learning rate: 0.00205 +2025-11-13 14:26:03.644931: train_loss -0.7215 +2025-11-13 14:26:03.649164: val_loss -0.7284 +2025-11-13 14:26:03.650961: Pseudo dice [np.float32(0.9108), np.float32(0.7921), np.float32(0.7489), np.float32(0.6808), np.float32(0.8658), np.float32(0.8295), np.float32(0.8925), np.float32(0.8662), np.float32(0.9792), np.float32(0.979), np.float32(0.9718), np.float32(0.8428), np.float32(0.7424), np.float32(0.8806), np.float32(0.9659), np.float32(0.3866), np.float32(0.3208)] +2025-11-13 14:26:03.652045: Epoch time: 258.02 s +2025-11-13 14:26:05.330859: +2025-11-13 14:26:05.332688: Epoch 829 +2025-11-13 14:26:05.334160: Current learning rate: 0.00204 +2025-11-13 14:30:23.351716: train_loss -0.7242 +2025-11-13 14:30:23.355876: val_loss -0.7354 +2025-11-13 14:30:23.357669: Pseudo dice [np.float32(0.9121), np.float32(0.8167), np.float32(0.6822), np.float32(0.6801), np.float32(0.8672), np.float32(0.8289), np.float32(0.9051), np.float32(0.864), np.float32(0.9711), np.float32(0.9727), np.float32(0.9693), np.float32(0.8459), np.float32(0.8027), np.float32(0.8804), np.float32(0.9609), np.float32(0.4619), np.float32(0.3792)] +2025-11-13 14:30:23.358958: Epoch time: 258.03 s +2025-11-13 14:30:25.094517: +2025-11-13 14:30:25.096041: Epoch 830 +2025-11-13 14:30:25.097328: Current learning rate: 0.00203 +2025-11-13 14:34:43.158508: train_loss -0.723 +2025-11-13 14:34:43.162851: val_loss -0.7276 +2025-11-13 14:34:43.164482: Pseudo dice [np.float32(0.9285), np.float32(0.788), np.float32(0.7271), np.float32(0.6702), np.float32(0.8735), np.float32(0.8107), np.float32(0.9032), np.float32(0.8597), np.float32(0.9751), np.float32(0.9762), np.float32(0.97), np.float32(0.8397), np.float32(0.7685), np.float32(0.8835), np.float32(0.9639), np.float32(0.4586), np.float32(0.4033)] +2025-11-13 14:34:43.165996: Epoch time: 258.07 s +2025-11-13 14:34:44.903299: +2025-11-13 14:34:44.904876: Epoch 831 +2025-11-13 14:34:44.906238: Current learning rate: 0.00202 +2025-11-13 14:39:04.014588: train_loss -0.7235 +2025-11-13 14:39:04.019571: val_loss -0.729 +2025-11-13 14:39:04.020986: Pseudo dice [np.float32(0.9168), np.float32(0.7886), np.float32(0.7017), np.float32(0.6866), np.float32(0.8682), np.float32(0.8237), np.float32(0.9087), np.float32(0.8565), np.float32(0.9669), np.float32(0.9657), np.float32(0.9688), np.float32(0.8445), np.float32(0.7729), np.float32(0.8817), np.float32(0.9601), np.float32(0.5004), np.float32(0.4353)] +2025-11-13 14:39:04.022219: Epoch time: 259.12 s +2025-11-13 14:39:05.714944: +2025-11-13 14:39:05.716411: Epoch 832 +2025-11-13 14:39:05.717782: Current learning rate: 0.00201 +2025-11-13 14:43:23.959552: train_loss -0.7272 +2025-11-13 14:43:23.963461: val_loss -0.725 +2025-11-13 14:43:23.964835: Pseudo dice [np.float32(0.9156), np.float32(0.7776), np.float32(0.7294), np.float32(0.6491), np.float32(0.8632), np.float32(0.8269), np.float32(0.9129), np.float32(0.8593), np.float32(0.9799), np.float32(0.9778), np.float32(0.971), np.float32(0.8478), np.float32(0.7755), np.float32(0.8799), np.float32(0.966), np.float32(0.3981), np.float32(0.3516)] +2025-11-13 14:43:23.966572: Epoch time: 258.25 s +2025-11-13 14:43:26.563173: +2025-11-13 14:43:26.565170: Epoch 833 +2025-11-13 14:43:26.566472: Current learning rate: 0.002 +2025-11-13 14:47:44.652222: train_loss -0.7261 +2025-11-13 14:47:44.656841: val_loss -0.7246 +2025-11-13 14:47:44.658220: Pseudo dice [np.float32(0.9155), np.float32(0.773), np.float32(0.735), np.float32(0.6816), np.float32(0.874), np.float32(0.8163), np.float32(0.9084), np.float32(0.8589), np.float32(0.9726), np.float32(0.9716), np.float32(0.9695), np.float32(0.8445), np.float32(0.7751), np.float32(0.8836), np.float32(0.9638), np.float32(0.4099), np.float32(0.3358)] +2025-11-13 14:47:44.659600: Epoch time: 258.09 s +2025-11-13 14:47:46.449421: +2025-11-13 14:47:46.451193: Epoch 834 +2025-11-13 14:47:46.452837: Current learning rate: 0.00199 +2025-11-13 14:52:04.658124: train_loss -0.7311 +2025-11-13 14:52:04.662990: val_loss -0.7427 +2025-11-13 14:52:04.664471: Pseudo dice [np.float32(0.9287), np.float32(0.8047), np.float32(0.7382), np.float32(0.6231), np.float32(0.869), np.float32(0.8314), np.float32(0.9269), np.float32(0.8639), np.float32(0.9815), np.float32(0.9807), np.float32(0.9728), np.float32(0.8378), np.float32(0.7826), np.float32(0.8842), np.float32(0.9634), np.float32(0.4711), np.float32(0.4044)] +2025-11-13 14:52:04.665912: Epoch time: 258.21 s +2025-11-13 14:52:07.270829: +2025-11-13 14:52:07.272323: Epoch 835 +2025-11-13 14:52:07.273713: Current learning rate: 0.00198 +2025-11-13 14:56:25.145955: train_loss -0.721 +2025-11-13 14:56:25.149943: val_loss -0.7373 +2025-11-13 14:56:25.151151: Pseudo dice [np.float32(0.925), np.float32(0.7897), np.float32(0.724), np.float32(0.6727), np.float32(0.8684), np.float32(0.8031), np.float32(0.8932), np.float32(0.8645), np.float32(0.9805), np.float32(0.9823), np.float32(0.9703), np.float32(0.8347), np.float32(0.7626), np.float32(0.8838), np.float32(0.9641), np.float32(0.5195), np.float32(0.5009)] +2025-11-13 14:56:25.152441: Epoch time: 257.88 s +2025-11-13 14:56:25.153475: Yayy! New best EMA pseudo Dice: 0.8108000159263611 +2025-11-13 14:56:44.070985: +2025-11-13 14:56:44.072482: Epoch 836 +2025-11-13 14:56:44.073767: Current learning rate: 0.00196 +2025-11-13 15:01:02.043731: train_loss -0.7287 +2025-11-13 15:01:02.048560: val_loss -0.7322 +2025-11-13 15:01:02.050099: Pseudo dice [np.float32(0.9275), np.float32(0.7949), np.float32(0.7129), np.float32(0.6404), np.float32(0.8776), np.float32(0.8109), np.float32(0.9079), np.float32(0.8673), np.float32(0.9765), np.float32(0.9773), np.float32(0.9714), np.float32(0.8421), np.float32(0.7632), np.float32(0.8792), np.float32(0.9664), np.float32(0.4475), np.float32(0.3806)] +2025-11-13 15:01:02.051643: Epoch time: 257.98 s +2025-11-13 15:01:04.144448: +2025-11-13 15:01:04.145918: Epoch 837 +2025-11-13 15:01:04.147284: Current learning rate: 0.00195 +2025-11-13 15:05:22.407233: train_loss -0.7271 +2025-11-13 15:05:22.410974: val_loss -0.7277 +2025-11-13 15:05:22.412223: Pseudo dice [np.float32(0.9198), np.float32(0.7917), np.float32(0.7057), np.float32(0.6822), np.float32(0.8773), np.float32(0.8234), np.float32(0.9067), np.float32(0.8606), np.float32(0.9761), np.float32(0.9767), np.float32(0.9714), np.float32(0.8462), np.float32(0.7714), np.float32(0.8846), np.float32(0.9652), np.float32(0.3238), np.float32(0.4193)] +2025-11-13 15:05:22.413334: Epoch time: 258.27 s +2025-11-13 15:05:24.421920: +2025-11-13 15:05:24.423404: Epoch 838 +2025-11-13 15:05:24.424681: Current learning rate: 0.00194 +2025-11-13 15:09:42.526869: train_loss -0.7278 +2025-11-13 15:09:42.531466: val_loss -0.7375 +2025-11-13 15:09:42.532663: Pseudo dice [np.float32(0.9227), np.float32(0.7768), np.float32(0.7332), np.float32(0.6668), np.float32(0.8767), np.float32(0.8045), np.float32(0.9071), np.float32(0.8502), np.float32(0.9788), np.float32(0.9809), np.float32(0.971), np.float32(0.8419), np.float32(0.7593), np.float32(0.8848), np.float32(0.9667), np.float32(0.4932), np.float32(0.4114)] +2025-11-13 15:09:42.533900: Epoch time: 258.11 s +2025-11-13 15:09:44.401645: +2025-11-13 15:09:44.403119: Epoch 839 +2025-11-13 15:09:44.404708: Current learning rate: 0.00193 +2025-11-13 15:14:02.621164: train_loss -0.7277 +2025-11-13 15:14:02.626733: val_loss -0.7253 +2025-11-13 15:14:02.628690: Pseudo dice [np.float32(0.9204), np.float32(0.7873), np.float32(0.6979), np.float32(0.6383), np.float32(0.8744), np.float32(0.8249), np.float32(0.9038), np.float32(0.8709), np.float32(0.9818), np.float32(0.9781), np.float32(0.9714), np.float32(0.8371), np.float32(0.7663), np.float32(0.8802), np.float32(0.9672), np.float32(0.4962), np.float32(0.3109)] +2025-11-13 15:14:02.630278: Epoch time: 258.22 s +2025-11-13 15:14:06.085677: +2025-11-13 15:14:06.087302: Epoch 840 +2025-11-13 15:14:06.088568: Current learning rate: 0.00192 +2025-11-13 15:18:25.884061: train_loss -0.7281 +2025-11-13 15:18:25.888335: val_loss -0.7277 +2025-11-13 15:18:25.889462: Pseudo dice [np.float32(0.9185), np.float32(0.7991), np.float32(0.7035), np.float32(0.6854), np.float32(0.871), np.float32(0.8195), np.float32(0.9039), np.float32(0.8557), np.float32(0.9776), np.float32(0.9762), np.float32(0.9716), np.float32(0.8527), np.float32(0.7627), np.float32(0.8798), np.float32(0.9654), np.float32(0.3566), np.float32(0.3687)] +2025-11-13 15:18:25.890499: Epoch time: 259.8 s +2025-11-13 15:18:28.293888: +2025-11-13 15:18:28.295801: Epoch 841 +2025-11-13 15:18:28.297518: Current learning rate: 0.00191 +2025-11-13 15:22:46.902130: train_loss -0.7257 +2025-11-13 15:22:46.906086: val_loss -0.7244 +2025-11-13 15:22:46.907349: Pseudo dice [np.float32(0.9212), np.float32(0.7819), np.float32(0.7056), np.float32(0.6564), np.float32(0.8728), np.float32(0.8017), np.float32(0.906), np.float32(0.8611), np.float32(0.9815), np.float32(0.98), np.float32(0.9717), np.float32(0.8431), np.float32(0.7435), np.float32(0.8812), np.float32(0.9656), np.float32(0.375), np.float32(0.4039)] +2025-11-13 15:22:46.908514: Epoch time: 258.61 s +2025-11-13 15:22:48.877737: +2025-11-13 15:22:48.879173: Epoch 842 +2025-11-13 15:22:48.881422: Current learning rate: 0.0019 +2025-11-13 15:27:07.125451: train_loss -0.7228 +2025-11-13 15:27:07.129128: val_loss -0.7437 +2025-11-13 15:27:07.130474: Pseudo dice [np.float32(0.9246), np.float32(0.793), np.float32(0.7419), np.float32(0.6797), np.float32(0.8833), np.float32(0.8315), np.float32(0.9174), np.float32(0.8629), np.float32(0.9799), np.float32(0.9798), np.float32(0.9714), np.float32(0.8503), np.float32(0.7963), np.float32(0.8903), np.float32(0.9668), np.float32(0.3942), np.float32(0.3996)] +2025-11-13 15:27:07.131755: Epoch time: 258.25 s +2025-11-13 15:27:09.045735: +2025-11-13 15:27:09.047167: Epoch 843 +2025-11-13 15:27:09.048719: Current learning rate: 0.00189 +2025-11-13 15:31:27.536588: train_loss -0.7287 +2025-11-13 15:31:27.540920: val_loss -0.7297 +2025-11-13 15:31:27.542445: Pseudo dice [np.float32(0.9229), np.float32(0.7816), np.float32(0.7459), np.float32(0.6632), np.float32(0.8724), np.float32(0.8228), np.float32(0.8996), np.float32(0.8663), np.float32(0.9751), np.float32(0.9758), np.float32(0.9721), np.float32(0.8432), np.float32(0.7677), np.float32(0.8805), np.float32(0.9701), np.float32(0.4486), np.float32(0.3434)] +2025-11-13 15:31:27.543659: Epoch time: 258.5 s +2025-11-13 15:31:29.474316: +2025-11-13 15:31:29.475661: Epoch 844 +2025-11-13 15:31:29.477217: Current learning rate: 0.00188 +2025-11-13 15:35:47.774113: train_loss -0.7255 +2025-11-13 15:35:47.778418: val_loss -0.7343 +2025-11-13 15:35:47.779869: Pseudo dice [np.float32(0.9157), np.float32(0.7634), np.float32(0.739), np.float32(0.7039), np.float32(0.8712), np.float32(0.823), np.float32(0.8951), np.float32(0.8717), np.float32(0.9791), np.float32(0.9799), np.float32(0.9715), np.float32(0.845), np.float32(0.7832), np.float32(0.8816), np.float32(0.9689), np.float32(0.4423), np.float32(0.3501)] +2025-11-13 15:35:47.781296: Epoch time: 258.31 s +2025-11-13 15:35:49.676405: +2025-11-13 15:35:49.678113: Epoch 845 +2025-11-13 15:35:49.679570: Current learning rate: 0.00187 +2025-11-13 15:40:08.198095: train_loss -0.7235 +2025-11-13 15:40:08.202780: val_loss -0.7377 +2025-11-13 15:40:08.204287: Pseudo dice [np.float32(0.9095), np.float32(0.762), np.float32(0.7183), np.float32(0.678), np.float32(0.8754), np.float32(0.8186), np.float32(0.9289), np.float32(0.8612), np.float32(0.9779), np.float32(0.9792), np.float32(0.9701), np.float32(0.8409), np.float32(0.7777), np.float32(0.8848), np.float32(0.9667), np.float32(0.5349), np.float32(0.4453)] +2025-11-13 15:40:08.206234: Epoch time: 258.53 s +2025-11-13 15:40:10.253877: +2025-11-13 15:40:10.260669: Epoch 846 +2025-11-13 15:40:10.261948: Current learning rate: 0.00186 +2025-11-13 15:44:28.829235: train_loss -0.7259 +2025-11-13 15:44:28.833354: val_loss -0.7298 +2025-11-13 15:44:28.834718: Pseudo dice [np.float32(0.922), np.float32(0.7761), np.float32(0.7148), np.float32(0.6853), np.float32(0.8735), np.float32(0.8203), np.float32(0.9055), np.float32(0.8618), np.float32(0.9805), np.float32(0.9773), np.float32(0.9715), np.float32(0.8462), np.float32(0.7729), np.float32(0.8807), np.float32(0.9631), np.float32(0.3988), np.float32(0.3389)] +2025-11-13 15:44:28.836313: Epoch time: 258.58 s +2025-11-13 15:44:30.651273: +2025-11-13 15:44:30.652776: Epoch 847 +2025-11-13 15:44:30.654180: Current learning rate: 0.00185 +2025-11-13 15:48:49.218910: train_loss -0.729 +2025-11-13 15:48:49.222936: val_loss -0.7316 +2025-11-13 15:48:49.224599: Pseudo dice [np.float32(0.9183), np.float32(0.8328), np.float32(0.7342), np.float32(0.6605), np.float32(0.868), np.float32(0.8216), np.float32(0.914), np.float32(0.8617), np.float32(0.9787), np.float32(0.9761), np.float32(0.9711), np.float32(0.8422), np.float32(0.7829), np.float32(0.8756), np.float32(0.9661), np.float32(0.4415), np.float32(0.3913)] +2025-11-13 15:48:49.225787: Epoch time: 258.57 s +2025-11-13 15:48:51.292255: +2025-11-13 15:48:51.293776: Epoch 848 +2025-11-13 15:48:51.295626: Current learning rate: 0.00184 +2025-11-13 15:53:09.946280: train_loss -0.7282 +2025-11-13 15:53:09.950310: val_loss -0.7324 +2025-11-13 15:53:09.951754: Pseudo dice [np.float32(0.9164), np.float32(0.7984), np.float32(0.7415), np.float32(0.6695), np.float32(0.8743), np.float32(0.8266), np.float32(0.9186), np.float32(0.8632), np.float32(0.9683), np.float32(0.9712), np.float32(0.9702), np.float32(0.8495), np.float32(0.7531), np.float32(0.8889), np.float32(0.962), np.float32(0.4571), np.float32(0.4194)] +2025-11-13 15:53:09.952991: Epoch time: 258.66 s +2025-11-13 15:53:09.954145: Yayy! New best EMA pseudo Dice: 0.8108000159263611 +2025-11-13 15:53:14.905025: +2025-11-13 15:53:14.906606: Epoch 849 +2025-11-13 15:53:14.908027: Current learning rate: 0.00182 +2025-11-13 15:57:33.249263: train_loss -0.7259 +2025-11-13 15:57:33.253272: val_loss -0.7258 +2025-11-13 15:57:33.254791: Pseudo dice [np.float32(0.9268), np.float32(0.7956), np.float32(0.7347), np.float32(0.6809), np.float32(0.8705), np.float32(0.8205), np.float32(0.9126), np.float32(0.8572), np.float32(0.9756), np.float32(0.9744), np.float32(0.9717), np.float32(0.8512), np.float32(0.78), np.float32(0.884), np.float32(0.9682), np.float32(0.3735), np.float32(0.2381)] +2025-11-13 15:57:33.256555: Epoch time: 258.35 s +2025-11-13 15:57:40.319537: +2025-11-13 15:57:40.321063: Epoch 850 +2025-11-13 15:57:40.322808: Current learning rate: 0.00181 +2025-11-13 16:01:58.829959: train_loss -0.7302 +2025-11-13 16:01:58.834176: val_loss -0.7312 +2025-11-13 16:01:58.835596: Pseudo dice [np.float32(0.9135), np.float32(0.799), np.float32(0.7534), np.float32(0.663), np.float32(0.8768), np.float32(0.8155), np.float32(0.9139), np.float32(0.8601), np.float32(0.9766), np.float32(0.9777), np.float32(0.9721), np.float32(0.8408), np.float32(0.7292), np.float32(0.8789), np.float32(0.9654), np.float32(0.518), np.float32(0.3958)] +2025-11-13 16:01:58.836963: Epoch time: 258.52 s +2025-11-13 16:02:00.989426: +2025-11-13 16:02:00.990932: Epoch 851 +2025-11-13 16:02:00.992225: Current learning rate: 0.0018 +2025-11-13 16:06:19.429755: train_loss -0.73 +2025-11-13 16:06:19.434173: val_loss -0.7523 +2025-11-13 16:06:19.435612: Pseudo dice [np.float32(0.9257), np.float32(0.791), np.float32(0.7679), np.float32(0.6746), np.float32(0.8803), np.float32(0.816), np.float32(0.9081), np.float32(0.8718), np.float32(0.9813), np.float32(0.9818), np.float32(0.9732), np.float32(0.8388), np.float32(0.7884), np.float32(0.8916), np.float32(0.969), np.float32(0.5131), np.float32(0.4902)] +2025-11-13 16:06:19.437412: Epoch time: 258.45 s +2025-11-13 16:06:19.438643: Yayy! New best EMA pseudo Dice: 0.8119999766349792 +2025-11-13 16:06:24.356253: +2025-11-13 16:06:24.358008: Epoch 852 +2025-11-13 16:06:24.359379: Current learning rate: 0.00179 +2025-11-13 16:10:42.766463: train_loss -0.7249 +2025-11-13 16:10:42.770318: val_loss -0.732 +2025-11-13 16:10:42.771815: Pseudo dice [np.float32(0.9083), np.float32(0.7746), np.float32(0.7373), np.float32(0.6519), np.float32(0.8717), np.float32(0.8237), np.float32(0.9012), np.float32(0.8716), np.float32(0.9804), np.float32(0.9792), np.float32(0.9704), np.float32(0.8462), np.float32(0.794), np.float32(0.8815), np.float32(0.9655), np.float32(0.4363), np.float32(0.362)] +2025-11-13 16:10:42.773084: Epoch time: 258.42 s +2025-11-13 16:10:44.515442: +2025-11-13 16:10:44.516841: Epoch 853 +2025-11-13 16:10:44.518131: Current learning rate: 0.00178 +2025-11-13 16:15:03.006807: train_loss -0.7288 +2025-11-13 16:15:03.010844: val_loss -0.7281 +2025-11-13 16:15:03.012275: Pseudo dice [np.float32(0.9221), np.float32(0.7742), np.float32(0.7388), np.float32(0.6634), np.float32(0.8667), np.float32(0.8211), np.float32(0.921), np.float32(0.8715), np.float32(0.9792), np.float32(0.9802), np.float32(0.9709), np.float32(0.8501), np.float32(0.772), np.float32(0.8748), np.float32(0.9653), np.float32(0.4096), np.float32(0.3483)] +2025-11-13 16:15:03.013803: Epoch time: 258.5 s +2025-11-13 16:15:04.678325: +2025-11-13 16:15:04.680069: Epoch 854 +2025-11-13 16:15:04.681546: Current learning rate: 0.00177 +2025-11-13 16:19:22.910004: train_loss -0.7302 +2025-11-13 16:19:22.913890: val_loss -0.7382 +2025-11-13 16:19:22.915185: Pseudo dice [np.float32(0.9155), np.float32(0.8015), np.float32(0.7315), np.float32(0.6615), np.float32(0.8785), np.float32(0.8137), np.float32(0.9171), np.float32(0.8679), np.float32(0.9766), np.float32(0.9769), np.float32(0.9712), np.float32(0.8448), np.float32(0.797), np.float32(0.8902), np.float32(0.9682), np.float32(0.4169), np.float32(0.2954)] +2025-11-13 16:19:22.916456: Epoch time: 258.24 s +2025-11-13 16:19:24.649518: +2025-11-13 16:19:24.651028: Epoch 855 +2025-11-13 16:19:24.652458: Current learning rate: 0.00176 +2025-11-13 16:23:42.997026: train_loss -0.7284 +2025-11-13 16:23:43.001244: val_loss -0.7435 +2025-11-13 16:23:43.002653: Pseudo dice [np.float32(0.9173), np.float32(0.7762), np.float32(0.7342), np.float32(0.674), np.float32(0.8775), np.float32(0.8227), np.float32(0.9121), np.float32(0.8783), np.float32(0.9808), np.float32(0.9774), np.float32(0.9721), np.float32(0.8466), np.float32(0.7758), np.float32(0.8876), np.float32(0.9689), np.float32(0.4502), np.float32(0.4136)] +2025-11-13 16:23:43.004109: Epoch time: 258.35 s +2025-11-13 16:23:44.737505: +2025-11-13 16:23:44.739033: Epoch 856 +2025-11-13 16:23:44.740540: Current learning rate: 0.00175 +2025-11-13 16:28:03.125993: train_loss -0.7303 +2025-11-13 16:28:03.129935: val_loss -0.7238 +2025-11-13 16:28:03.131274: Pseudo dice [np.float32(0.9182), np.float32(0.7783), np.float32(0.6953), np.float32(0.6614), np.float32(0.8765), np.float32(0.8181), np.float32(0.8884), np.float32(0.8648), np.float32(0.9796), np.float32(0.981), np.float32(0.9715), np.float32(0.8493), np.float32(0.7744), np.float32(0.8859), np.float32(0.9655), np.float32(0.3867), np.float32(0.3359)] +2025-11-13 16:28:03.132582: Epoch time: 258.39 s +2025-11-13 16:28:04.825624: +2025-11-13 16:28:04.827162: Epoch 857 +2025-11-13 16:28:04.828530: Current learning rate: 0.00174 +2025-11-13 16:32:23.323113: train_loss -0.7294 +2025-11-13 16:32:23.327730: val_loss -0.738 +2025-11-13 16:32:23.329142: Pseudo dice [np.float32(0.921), np.float32(0.7873), np.float32(0.7684), np.float32(0.666), np.float32(0.8771), np.float32(0.8281), np.float32(0.9073), np.float32(0.8623), np.float32(0.9763), np.float32(0.9746), np.float32(0.9711), np.float32(0.8455), np.float32(0.7629), np.float32(0.881), np.float32(0.9663), np.float32(0.4388), np.float32(0.3505)] +2025-11-13 16:32:23.330691: Epoch time: 258.5 s +2025-11-13 16:32:25.028285: +2025-11-13 16:32:25.029791: Epoch 858 +2025-11-13 16:32:25.031168: Current learning rate: 0.00173 +2025-11-13 16:36:43.412237: train_loss -0.7275 +2025-11-13 16:36:43.417059: val_loss -0.7404 +2025-11-13 16:36:43.418806: Pseudo dice [np.float32(0.9299), np.float32(0.8172), np.float32(0.76), np.float32(0.7013), np.float32(0.8746), np.float32(0.8216), np.float32(0.9024), np.float32(0.8754), np.float32(0.9773), np.float32(0.9785), np.float32(0.9715), np.float32(0.8428), np.float32(0.7601), np.float32(0.8847), np.float32(0.9601), np.float32(0.4089), np.float32(0.5265)] +2025-11-13 16:36:43.420332: Epoch time: 258.39 s +2025-11-13 16:36:45.131480: +2025-11-13 16:36:45.132931: Epoch 859 +2025-11-13 16:36:45.134309: Current learning rate: 0.00172 +2025-11-13 16:41:04.466085: train_loss -0.727 +2025-11-13 16:41:04.470145: val_loss -0.7247 +2025-11-13 16:41:04.471682: Pseudo dice [np.float32(0.9222), np.float32(0.7818), np.float32(0.7311), np.float32(0.6816), np.float32(0.8714), np.float32(0.82), np.float32(0.898), np.float32(0.8549), np.float32(0.9727), np.float32(0.9723), np.float32(0.9695), np.float32(0.8449), np.float32(0.7598), np.float32(0.8795), np.float32(0.9613), np.float32(0.3161), np.float32(0.3653)] +2025-11-13 16:41:04.473162: Epoch time: 259.34 s +2025-11-13 16:41:06.184484: +2025-11-13 16:41:06.185923: Epoch 860 +2025-11-13 16:41:06.187103: Current learning rate: 0.0017 +2025-11-13 16:45:24.433914: train_loss -0.7281 +2025-11-13 16:45:24.438110: val_loss -0.7276 +2025-11-13 16:45:24.439843: Pseudo dice [np.float32(0.9112), np.float32(0.7954), np.float32(0.726), np.float32(0.6774), np.float32(0.8741), np.float32(0.8097), np.float32(0.9077), np.float32(0.8639), np.float32(0.9805), np.float32(0.9791), np.float32(0.9714), np.float32(0.8478), np.float32(0.7775), np.float32(0.8797), np.float32(0.97), np.float32(0.4922), np.float32(0.3649)] +2025-11-13 16:45:24.441899: Epoch time: 258.26 s +2025-11-13 16:45:26.159078: +2025-11-13 16:45:26.161281: Epoch 861 +2025-11-13 16:45:26.162535: Current learning rate: 0.00169 +2025-11-13 16:49:44.668121: train_loss -0.7243 +2025-11-13 16:49:44.671768: val_loss -0.7445 +2025-11-13 16:49:44.672899: Pseudo dice [np.float32(0.9165), np.float32(0.796), np.float32(0.742), np.float32(0.6562), np.float32(0.8746), np.float32(0.823), np.float32(0.9177), np.float32(0.8662), np.float32(0.9816), np.float32(0.9814), np.float32(0.973), np.float32(0.8313), np.float32(0.7818), np.float32(0.8892), np.float32(0.9652), np.float32(0.5015), np.float32(0.4499)] +2025-11-13 16:49:44.674097: Epoch time: 258.51 s +2025-11-13 16:49:46.346099: +2025-11-13 16:49:46.347607: Epoch 862 +2025-11-13 16:49:46.348928: Current learning rate: 0.00168 +2025-11-13 16:54:04.634625: train_loss -0.731 +2025-11-13 16:54:04.638446: val_loss -0.7467 +2025-11-13 16:54:04.639803: Pseudo dice [np.float32(0.9105), np.float32(0.7828), np.float32(0.7514), np.float32(0.6624), np.float32(0.8724), np.float32(0.8203), np.float32(0.9118), np.float32(0.8752), np.float32(0.9794), np.float32(0.9797), np.float32(0.9713), np.float32(0.8433), np.float32(0.771), np.float32(0.8804), np.float32(0.9653), np.float32(0.4869), np.float32(0.5141)] +2025-11-13 16:54:04.641336: Epoch time: 258.29 s +2025-11-13 16:54:04.642337: Yayy! New best EMA pseudo Dice: 0.8129000067710876 +2025-11-13 16:54:09.294785: +2025-11-13 16:54:09.296380: Epoch 863 +2025-11-13 16:54:09.297861: Current learning rate: 0.00167 +2025-11-13 16:58:27.581294: train_loss -0.7301 +2025-11-13 16:58:27.585274: val_loss -0.7398 +2025-11-13 16:58:27.586461: Pseudo dice [np.float32(0.9311), np.float32(0.8141), np.float32(0.7573), np.float32(0.6616), np.float32(0.8729), np.float32(0.8105), np.float32(0.9209), np.float32(0.8699), np.float32(0.9814), np.float32(0.9815), np.float32(0.9715), np.float32(0.8452), np.float32(0.7581), np.float32(0.8821), np.float32(0.9661), np.float32(0.4025), np.float32(0.3884)] +2025-11-13 16:58:27.587608: Epoch time: 258.29 s +2025-11-13 16:58:29.294653: +2025-11-13 16:58:29.295986: Epoch 864 +2025-11-13 16:58:29.297372: Current learning rate: 0.00166 +2025-11-13 17:02:47.980614: train_loss -0.7286 +2025-11-13 17:02:47.985628: val_loss -0.74 +2025-11-13 17:02:47.987313: Pseudo dice [np.float32(0.9088), np.float32(0.7853), np.float32(0.6942), np.float32(0.6708), np.float32(0.8764), np.float32(0.8128), np.float32(0.9125), np.float32(0.8708), np.float32(0.9817), np.float32(0.9826), np.float32(0.9717), np.float32(0.8426), np.float32(0.7798), np.float32(0.8825), np.float32(0.9625), np.float32(0.445), np.float32(0.5012)] +2025-11-13 17:02:47.989284: Epoch time: 258.69 s +2025-11-13 17:02:47.990852: Yayy! New best EMA pseudo Dice: 0.8131999969482422 +2025-11-13 17:02:52.893690: +2025-11-13 17:02:52.895124: Epoch 865 +2025-11-13 17:02:52.896537: Current learning rate: 0.00165 +2025-11-13 17:07:11.400063: train_loss -0.7318 +2025-11-13 17:07:11.403949: val_loss -0.7398 +2025-11-13 17:07:11.405276: Pseudo dice [np.float32(0.9139), np.float32(0.8093), np.float32(0.7136), np.float32(0.691), np.float32(0.8787), np.float32(0.8158), np.float32(0.9081), np.float32(0.8726), np.float32(0.9787), np.float32(0.9798), np.float32(0.972), np.float32(0.8403), np.float32(0.7408), np.float32(0.8884), np.float32(0.965), np.float32(0.4049), np.float32(0.4463)] +2025-11-13 17:07:11.406564: Epoch time: 258.51 s +2025-11-13 17:07:13.083959: +2025-11-13 17:07:13.085462: Epoch 866 +2025-11-13 17:07:13.086808: Current learning rate: 0.00164 +2025-11-13 17:11:31.601961: train_loss -0.7275 +2025-11-13 17:11:31.606109: val_loss -0.7372 +2025-11-13 17:11:31.607671: Pseudo dice [np.float32(0.9105), np.float32(0.7931), np.float32(0.7424), np.float32(0.6932), np.float32(0.8749), np.float32(0.8206), np.float32(0.9179), np.float32(0.8693), np.float32(0.9787), np.float32(0.9772), np.float32(0.9709), np.float32(0.8462), np.float32(0.8034), np.float32(0.8773), np.float32(0.9651), np.float32(0.4868), np.float32(0.4704)] +2025-11-13 17:11:31.608933: Epoch time: 258.52 s +2025-11-13 17:11:31.610110: Yayy! New best EMA pseudo Dice: 0.8141999840736389 +2025-11-13 17:11:36.521458: +2025-11-13 17:11:36.523031: Epoch 867 +2025-11-13 17:11:36.524605: Current learning rate: 0.00163 +2025-11-13 17:15:54.978716: train_loss -0.7273 +2025-11-13 17:15:54.983494: val_loss -0.7342 +2025-11-13 17:15:54.984680: Pseudo dice [np.float32(0.9146), np.float32(0.7713), np.float32(0.729), np.float32(0.6789), np.float32(0.8805), np.float32(0.7984), np.float32(0.9146), np.float32(0.8653), np.float32(0.975), np.float32(0.9784), np.float32(0.972), np.float32(0.8448), np.float32(0.7749), np.float32(0.8846), np.float32(0.9661), np.float32(0.4101), np.float32(0.3624)] +2025-11-13 17:15:54.986010: Epoch time: 258.46 s +2025-11-13 17:15:56.678996: +2025-11-13 17:15:56.680712: Epoch 868 +2025-11-13 17:15:56.682232: Current learning rate: 0.00162 +2025-11-13 17:20:15.834794: train_loss -0.7337 +2025-11-13 17:20:15.839663: val_loss -0.7448 +2025-11-13 17:20:15.841912: Pseudo dice [np.float32(0.9129), np.float32(0.783), np.float32(0.7404), np.float32(0.6614), np.float32(0.8774), np.float32(0.8198), np.float32(0.9079), np.float32(0.8628), np.float32(0.9813), np.float32(0.98), np.float32(0.97), np.float32(0.8351), np.float32(0.7829), np.float32(0.8848), np.float32(0.964), np.float32(0.4864), np.float32(0.4807)] +2025-11-13 17:20:15.843403: Epoch time: 259.16 s +2025-11-13 17:20:17.559527: +2025-11-13 17:20:17.561018: Epoch 869 +2025-11-13 17:20:17.562366: Current learning rate: 0.00161 +2025-11-13 17:24:36.169843: train_loss -0.7331 +2025-11-13 17:24:36.173918: val_loss -0.7345 +2025-11-13 17:24:36.175654: Pseudo dice [np.float32(0.9147), np.float32(0.7573), np.float32(0.7317), np.float32(0.6708), np.float32(0.874), np.float32(0.8113), np.float32(0.9212), np.float32(0.8642), np.float32(0.9764), np.float32(0.9782), np.float32(0.9719), np.float32(0.8525), np.float32(0.7665), np.float32(0.8811), np.float32(0.9669), np.float32(0.4049), np.float32(0.358)] +2025-11-13 17:24:36.176911: Epoch time: 258.62 s +2025-11-13 17:24:37.899693: +2025-11-13 17:24:37.901042: Epoch 870 +2025-11-13 17:24:37.902331: Current learning rate: 0.00159 +2025-11-13 17:28:56.439709: train_loss -0.7261 +2025-11-13 17:28:56.444650: val_loss -0.7412 +2025-11-13 17:28:56.445953: Pseudo dice [np.float32(0.9134), np.float32(0.7879), np.float32(0.7267), np.float32(0.6389), np.float32(0.8712), np.float32(0.8519), np.float32(0.9093), np.float32(0.8748), np.float32(0.9798), np.float32(0.9806), np.float32(0.9708), np.float32(0.8414), np.float32(0.759), np.float32(0.8821), np.float32(0.9628), np.float32(0.4294), np.float32(0.4567)] +2025-11-13 17:28:56.447578: Epoch time: 258.55 s +2025-11-13 17:28:58.292007: +2025-11-13 17:28:58.293660: Epoch 871 +2025-11-13 17:28:58.295446: Current learning rate: 0.00158 +2025-11-13 17:33:16.739893: train_loss -0.7264 +2025-11-13 17:33:16.744372: val_loss -0.7243 +2025-11-13 17:33:16.745919: Pseudo dice [np.float32(0.9166), np.float32(0.7917), np.float32(0.7413), np.float32(0.6475), np.float32(0.8684), np.float32(0.8231), np.float32(0.9098), np.float32(0.8674), np.float32(0.9801), np.float32(0.9811), np.float32(0.9706), np.float32(0.8419), np.float32(0.7743), np.float32(0.8818), np.float32(0.9661), np.float32(0.3534), np.float32(0.2812)] +2025-11-13 17:33:16.747258: Epoch time: 258.45 s +2025-11-13 17:33:18.450946: +2025-11-13 17:33:18.452491: Epoch 872 +2025-11-13 17:33:18.453958: Current learning rate: 0.00157 +2025-11-13 17:37:36.780835: train_loss -0.731 +2025-11-13 17:37:36.785051: val_loss -0.7433 +2025-11-13 17:37:36.786709: Pseudo dice [np.float32(0.9231), np.float32(0.796), np.float32(0.745), np.float32(0.6829), np.float32(0.8835), np.float32(0.8154), np.float32(0.9198), np.float32(0.8579), np.float32(0.9806), np.float32(0.9783), np.float32(0.9709), np.float32(0.8421), np.float32(0.8087), np.float32(0.8896), np.float32(0.9642), np.float32(0.5276), np.float32(0.3626)] +2025-11-13 17:37:36.788073: Epoch time: 258.33 s +2025-11-13 17:38:03.561083: +2025-11-13 17:38:03.562602: Epoch 873 +2025-11-13 17:38:03.563871: Current learning rate: 0.00156 +2025-11-13 17:42:21.603284: train_loss -0.7296 +2025-11-13 17:42:21.607674: val_loss -0.7335 +2025-11-13 17:42:21.608934: Pseudo dice [np.float32(0.9191), np.float32(0.7904), np.float32(0.7443), np.float32(0.6562), np.float32(0.8779), np.float32(0.8303), np.float32(0.9064), np.float32(0.8542), np.float32(0.9766), np.float32(0.9797), np.float32(0.9715), np.float32(0.8548), np.float32(0.7861), np.float32(0.8911), np.float32(0.9686), np.float32(0.4336), np.float32(0.4234)] +2025-11-13 17:42:21.610246: Epoch time: 258.05 s +2025-11-13 17:43:34.853140: +2025-11-13 17:43:34.855118: Epoch 874 +2025-11-13 17:43:34.856442: Current learning rate: 0.00155 +2025-11-13 17:47:52.290505: train_loss -0.7312 +2025-11-13 17:47:52.294061: val_loss -0.7302 +2025-11-13 17:47:52.295171: Pseudo dice [np.float32(0.9103), np.float32(0.7735), np.float32(0.7054), np.float32(0.6906), np.float32(0.8725), np.float32(0.8036), np.float32(0.9045), np.float32(0.8638), np.float32(0.9826), np.float32(0.9811), np.float32(0.9719), np.float32(0.846), np.float32(0.7881), np.float32(0.8843), np.float32(0.9688), np.float32(0.3917), np.float32(0.3442)] +2025-11-13 17:47:52.296226: Epoch time: 257.44 s +2025-11-13 17:50:20.023202: +2025-11-13 17:50:20.025891: Epoch 875 +2025-11-13 17:50:20.027241: Current learning rate: 0.00154 +2025-11-13 17:54:37.251095: train_loss -0.7318 +2025-11-13 17:54:37.255136: val_loss -0.7303 +2025-11-13 17:54:37.256818: Pseudo dice [np.float32(0.909), np.float32(0.7822), np.float32(0.7296), np.float32(0.681), np.float32(0.8771), np.float32(0.8186), np.float32(0.9114), np.float32(0.8653), np.float32(0.9791), np.float32(0.9774), np.float32(0.9702), np.float32(0.8472), np.float32(0.7801), np.float32(0.8819), np.float32(0.9677), np.float32(0.4987), np.float32(0.3695)] +2025-11-13 17:54:37.258522: Epoch time: 257.23 s +2025-11-13 17:54:38.940156: +2025-11-13 17:54:38.941614: Epoch 876 +2025-11-13 17:54:38.943254: Current learning rate: 0.00153 +2025-11-13 17:58:57.134473: train_loss -0.7302 +2025-11-13 17:58:57.138165: val_loss -0.7378 +2025-11-13 17:58:57.139325: Pseudo dice [np.float32(0.9212), np.float32(0.8163), np.float32(0.7173), np.float32(0.6771), np.float32(0.8797), np.float32(0.8229), np.float32(0.9078), np.float32(0.8637), np.float32(0.9816), np.float32(0.9817), np.float32(0.9712), np.float32(0.85), np.float32(0.7888), np.float32(0.8849), np.float32(0.9651), np.float32(0.4749), np.float32(0.3751)] +2025-11-13 17:58:57.140377: Epoch time: 258.2 s +2025-11-13 17:59:16.114573: +2025-11-13 17:59:16.116132: Epoch 877 +2025-11-13 17:59:16.118101: Current learning rate: 0.00152 +2025-11-13 18:03:34.396302: train_loss -0.7277 +2025-11-13 18:03:34.400664: val_loss -0.7391 +2025-11-13 18:03:34.402223: Pseudo dice [np.float32(0.9029), np.float32(0.75), np.float32(0.7426), np.float32(0.6588), np.float32(0.8774), np.float32(0.8086), np.float32(0.9225), np.float32(0.8643), np.float32(0.9787), np.float32(0.9807), np.float32(0.9725), np.float32(0.8423), np.float32(0.7522), np.float32(0.8859), np.float32(0.9673), np.float32(0.463), np.float32(0.4438)] +2025-11-13 18:03:34.403758: Epoch time: 258.29 s +2025-11-13 18:40:32.243908: +2025-11-13 18:40:32.245801: Epoch 878 +2025-11-13 18:40:32.247059: Current learning rate: 0.00151 +2025-11-13 18:44:49.683808: train_loss -0.7291 +2025-11-13 18:44:49.688446: val_loss -0.7344 +2025-11-13 18:44:49.690029: Pseudo dice [np.float32(0.9096), np.float32(0.7814), np.float32(0.7473), np.float32(0.6449), np.float32(0.8813), np.float32(0.8162), np.float32(0.9111), np.float32(0.8664), np.float32(0.9812), np.float32(0.9816), np.float32(0.971), np.float32(0.8496), np.float32(0.7581), np.float32(0.8886), np.float32(0.9685), np.float32(0.4563), np.float32(0.3506)] +2025-11-13 18:44:49.691638: Epoch time: 257.45 s +2025-11-13 18:44:51.383986: +2025-11-13 18:44:51.385466: Epoch 879 +2025-11-13 18:44:51.387063: Current learning rate: 0.00149 +2025-11-13 18:49:09.794196: train_loss -0.7277 +2025-11-13 18:49:09.798815: val_loss -0.7273 +2025-11-13 18:49:09.800102: Pseudo dice [np.float32(0.9186), np.float32(0.8107), np.float32(0.7584), np.float32(0.6692), np.float32(0.8722), np.float32(0.8259), np.float32(0.9107), np.float32(0.8672), np.float32(0.9643), np.float32(0.9618), np.float32(0.9687), np.float32(0.8449), np.float32(0.7711), np.float32(0.879), np.float32(0.9562), np.float32(0.3485), np.float32(0.4225)] +2025-11-13 18:49:09.801307: Epoch time: 258.42 s +2025-11-13 18:49:11.466280: +2025-11-13 18:49:11.467745: Epoch 880 +2025-11-13 18:49:11.469163: Current learning rate: 0.00148 +2025-11-13 18:53:30.042580: train_loss -0.7314 +2025-11-13 18:53:30.047194: val_loss -0.739 +2025-11-13 18:53:30.048674: Pseudo dice [np.float32(0.9233), np.float32(0.726), np.float32(0.726), np.float32(0.6847), np.float32(0.8826), np.float32(0.8254), np.float32(0.9078), np.float32(0.8605), np.float32(0.9786), np.float32(0.9777), np.float32(0.9721), np.float32(0.8444), np.float32(0.7968), np.float32(0.892), np.float32(0.9648), np.float32(0.4946), np.float32(0.3959)] +2025-11-13 18:53:30.050087: Epoch time: 258.58 s +2025-11-13 18:53:31.784403: +2025-11-13 18:53:31.786890: Epoch 881 +2025-11-13 18:53:31.788303: Current learning rate: 0.00147 +2025-11-13 18:57:50.056484: train_loss -0.7357 +2025-11-13 18:57:50.061082: val_loss -0.7384 +2025-11-13 18:57:50.062682: Pseudo dice [np.float32(0.9126), np.float32(0.7997), np.float32(0.7414), np.float32(0.6525), np.float32(0.8757), np.float32(0.8213), np.float32(0.9169), np.float32(0.8698), np.float32(0.9768), np.float32(0.9786), np.float32(0.9723), np.float32(0.848), np.float32(0.7599), np.float32(0.8865), np.float32(0.9665), np.float32(0.438), np.float32(0.3812)] +2025-11-13 18:57:50.064115: Epoch time: 258.28 s +2025-11-13 18:57:51.762260: +2025-11-13 18:57:51.763973: Epoch 882 +2025-11-13 18:57:51.765996: Current learning rate: 0.00146 +2025-11-13 19:02:10.248965: train_loss -0.7292 +2025-11-13 19:02:10.253624: val_loss -0.7341 +2025-11-13 19:02:10.255007: Pseudo dice [np.float32(0.9125), np.float32(0.7855), np.float32(0.7646), np.float32(0.6739), np.float32(0.8698), np.float32(0.8276), np.float32(0.9008), np.float32(0.8701), np.float32(0.9798), np.float32(0.9819), np.float32(0.9702), np.float32(0.8568), np.float32(0.7908), np.float32(0.8839), np.float32(0.9614), np.float32(0.4456), np.float32(0.3847)] +2025-11-13 19:02:10.256401: Epoch time: 258.49 s +2025-11-13 19:02:12.094687: +2025-11-13 19:02:12.096159: Epoch 883 +2025-11-13 19:02:12.097476: Current learning rate: 0.00145 +2025-11-13 19:06:30.463063: train_loss -0.7317 +2025-11-13 19:06:30.467633: val_loss -0.7334 +2025-11-13 19:06:30.469338: Pseudo dice [np.float32(0.9181), np.float32(0.8143), np.float32(0.7205), np.float32(0.6659), np.float32(0.8826), np.float32(0.8246), np.float32(0.9129), np.float32(0.8681), np.float32(0.9774), np.float32(0.9789), np.float32(0.9713), np.float32(0.8415), np.float32(0.7909), np.float32(0.887), np.float32(0.9659), np.float32(0.3925), np.float32(0.4458)] +2025-11-13 19:06:30.470580: Epoch time: 258.37 s +2025-11-13 19:06:32.345554: +2025-11-13 19:06:32.348460: Epoch 884 +2025-11-13 19:06:32.350036: Current learning rate: 0.00144 +2025-11-13 19:10:50.817201: train_loss -0.7286 +2025-11-13 19:10:50.822225: val_loss -0.7329 +2025-11-13 19:10:50.823700: Pseudo dice [np.float32(0.9225), np.float32(0.7872), np.float32(0.7418), np.float32(0.6794), np.float32(0.8778), np.float32(0.8242), np.float32(0.9128), np.float32(0.868), np.float32(0.9781), np.float32(0.9747), np.float32(0.9709), np.float32(0.8517), np.float32(0.7827), np.float32(0.8837), np.float32(0.9607), np.float32(0.3959), np.float32(0.3044)] +2025-11-13 19:10:50.825239: Epoch time: 258.48 s +2025-11-13 19:10:52.701703: +2025-11-13 19:10:52.703203: Epoch 885 +2025-11-13 19:10:52.704551: Current learning rate: 0.00143 +2025-11-13 19:15:11.147144: train_loss -0.7267 +2025-11-13 19:15:11.151639: val_loss -0.7317 +2025-11-13 19:15:11.152999: Pseudo dice [np.float32(0.9229), np.float32(0.8216), np.float32(0.7389), np.float32(0.6959), np.float32(0.8774), np.float32(0.8031), np.float32(0.9031), np.float32(0.8599), np.float32(0.9757), np.float32(0.9752), np.float32(0.9707), np.float32(0.8456), np.float32(0.7679), np.float32(0.8836), np.float32(0.9668), np.float32(0.4468), np.float32(0.3446)] +2025-11-13 19:15:11.154370: Epoch time: 258.45 s +2025-11-13 19:15:12.862449: +2025-11-13 19:15:12.863905: Epoch 886 +2025-11-13 19:15:12.865441: Current learning rate: 0.00142 +2025-11-13 19:19:31.315231: train_loss -0.7271 +2025-11-13 19:19:31.320369: val_loss -0.7358 +2025-11-13 19:19:31.321782: Pseudo dice [np.float32(0.912), np.float32(0.7752), np.float32(0.7558), np.float32(0.6727), np.float32(0.8755), np.float32(0.828), np.float32(0.9025), np.float32(0.8637), np.float32(0.9809), np.float32(0.98), np.float32(0.972), np.float32(0.8469), np.float32(0.7667), np.float32(0.8861), np.float32(0.9691), np.float32(0.461), np.float32(0.3575)] +2025-11-13 19:19:31.323069: Epoch time: 258.46 s +2025-11-13 19:19:33.068042: +2025-11-13 19:19:33.069535: Epoch 887 +2025-11-13 19:19:33.070848: Current learning rate: 0.00141 +2025-11-13 19:23:52.467124: train_loss -0.7261 +2025-11-13 19:23:52.471089: val_loss -0.7432 +2025-11-13 19:23:52.472564: Pseudo dice [np.float32(0.9275), np.float32(0.7778), np.float32(0.7066), np.float32(0.6771), np.float32(0.8775), np.float32(0.8136), np.float32(0.9089), np.float32(0.8707), np.float32(0.98), np.float32(0.9808), np.float32(0.9717), np.float32(0.8545), np.float32(0.7675), np.float32(0.8837), np.float32(0.9623), np.float32(0.4367), np.float32(0.451)] +2025-11-13 19:23:52.473995: Epoch time: 259.4 s +2025-11-13 19:23:54.653256: +2025-11-13 19:23:54.654819: Epoch 888 +2025-11-13 19:23:54.656614: Current learning rate: 0.00139 +2025-11-13 19:28:13.294999: train_loss -0.7311 +2025-11-13 19:28:13.298666: val_loss -0.7281 +2025-11-13 19:28:13.299777: Pseudo dice [np.float32(0.9168), np.float32(0.8343), np.float32(0.7354), np.float32(0.6798), np.float32(0.875), np.float32(0.8327), np.float32(0.899), np.float32(0.8655), np.float32(0.9736), np.float32(0.9772), np.float32(0.9712), np.float32(0.8506), np.float32(0.7783), np.float32(0.8756), np.float32(0.9649), np.float32(0.4078), np.float32(0.437)] +2025-11-13 19:28:13.300933: Epoch time: 258.65 s +2025-11-13 19:28:15.014261: +2025-11-13 19:28:15.015554: Epoch 889 +2025-11-13 19:28:15.016713: Current learning rate: 0.00138 +2025-11-13 19:32:33.563487: train_loss -0.7314 +2025-11-13 19:32:33.567779: val_loss -0.7401 +2025-11-13 19:32:33.569339: Pseudo dice [np.float32(0.922), np.float32(0.7875), np.float32(0.7411), np.float32(0.6703), np.float32(0.8771), np.float32(0.8255), np.float32(0.9093), np.float32(0.8597), np.float32(0.9793), np.float32(0.978), np.float32(0.9713), np.float32(0.8411), np.float32(0.7719), np.float32(0.8861), np.float32(0.9656), np.float32(0.4423), np.float32(0.3656)] +2025-11-13 19:32:33.570986: Epoch time: 258.55 s +2025-11-13 19:32:35.353657: +2025-11-13 19:32:35.355572: Epoch 890 +2025-11-13 19:32:35.357385: Current learning rate: 0.00137 +2025-11-13 19:36:53.821525: train_loss -0.7275 +2025-11-13 19:36:53.825956: val_loss -0.7422 +2025-11-13 19:36:53.827313: Pseudo dice [np.float32(0.916), np.float32(0.8344), np.float32(0.7483), np.float32(0.6937), np.float32(0.8804), np.float32(0.8321), np.float32(0.9178), np.float32(0.8668), np.float32(0.979), np.float32(0.9805), np.float32(0.9719), np.float32(0.8483), np.float32(0.805), np.float32(0.8877), np.float32(0.9667), np.float32(0.4819), np.float32(0.4298)] +2025-11-13 19:36:53.828884: Epoch time: 258.47 s +2025-11-13 19:36:55.542455: +2025-11-13 19:36:55.543843: Epoch 891 +2025-11-13 19:36:55.545152: Current learning rate: 0.00136 +2025-11-13 19:41:13.923635: train_loss -0.7312 +2025-11-13 19:41:13.928312: val_loss -0.7442 +2025-11-13 19:41:13.929459: Pseudo dice [np.float32(0.91), np.float32(0.8251), np.float32(0.7628), np.float32(0.6651), np.float32(0.8697), np.float32(0.8252), np.float32(0.899), np.float32(0.8642), np.float32(0.9776), np.float32(0.9759), np.float32(0.9716), np.float32(0.8504), np.float32(0.7902), np.float32(0.8855), np.float32(0.9686), np.float32(0.495), np.float32(0.4213)] +2025-11-13 19:41:13.930902: Epoch time: 258.39 s +2025-11-13 19:41:13.932657: Yayy! New best EMA pseudo Dice: 0.8147000074386597 +2025-11-13 19:41:20.933762: +2025-11-13 19:41:20.935195: Epoch 892 +2025-11-13 19:41:20.936542: Current learning rate: 0.00135 +2025-11-13 19:45:39.119053: train_loss -0.7338 +2025-11-13 19:45:39.123169: val_loss -0.7437 +2025-11-13 19:45:39.124475: Pseudo dice [np.float32(0.922), np.float32(0.7833), np.float32(0.7192), np.float32(0.6968), np.float32(0.8698), np.float32(0.8232), np.float32(0.915), np.float32(0.8649), np.float32(0.9769), np.float32(0.9749), np.float32(0.9709), np.float32(0.852), np.float32(0.7562), np.float32(0.8856), np.float32(0.9676), np.float32(0.476), np.float32(0.4796)] +2025-11-13 19:45:39.126012: Epoch time: 258.19 s +2025-11-13 19:45:39.127133: Yayy! New best EMA pseudo Dice: 0.8151999711990356 +2025-11-13 19:45:44.352616: +2025-11-13 19:45:44.354313: Epoch 893 +2025-11-13 19:45:44.355903: Current learning rate: 0.00134 +2025-11-13 19:50:02.572821: train_loss -0.7343 +2025-11-13 19:50:02.577205: val_loss -0.7415 +2025-11-13 19:50:02.578734: Pseudo dice [np.float32(0.9116), np.float32(0.7937), np.float32(0.7573), np.float32(0.6643), np.float32(0.8764), np.float32(0.8239), np.float32(0.9008), np.float32(0.8677), np.float32(0.9768), np.float32(0.9775), np.float32(0.9719), np.float32(0.8451), np.float32(0.8102), np.float32(0.8924), np.float32(0.9679), np.float32(0.4792), np.float32(0.4741)] +2025-11-13 19:50:02.579913: Epoch time: 258.23 s +2025-11-13 19:50:02.581133: Yayy! New best EMA pseudo Dice: 0.8159999847412109 +2025-11-13 19:50:07.475540: +2025-11-13 19:50:07.477136: Epoch 894 +2025-11-13 19:50:07.478501: Current learning rate: 0.00133 +2025-11-13 19:54:25.996676: train_loss -0.734 +2025-11-13 19:54:26.001708: val_loss -0.7275 +2025-11-13 19:54:26.003169: Pseudo dice [np.float32(0.9094), np.float32(0.7955), np.float32(0.7239), np.float32(0.6742), np.float32(0.8801), np.float32(0.8232), np.float32(0.8927), np.float32(0.8576), np.float32(0.977), np.float32(0.9789), np.float32(0.971), np.float32(0.8531), np.float32(0.7887), np.float32(0.8907), np.float32(0.9695), np.float32(0.4346), np.float32(0.2949)] +2025-11-13 19:54:26.004842: Epoch time: 258.53 s +2025-11-13 19:54:27.723973: +2025-11-13 19:54:27.725447: Epoch 895 +2025-11-13 19:54:27.726762: Current learning rate: 0.00132 +2025-11-13 19:58:46.224828: train_loss -0.7332 +2025-11-13 19:58:46.229110: val_loss -0.7388 +2025-11-13 19:58:46.230355: Pseudo dice [np.float32(0.9197), np.float32(0.7944), np.float32(0.7558), np.float32(0.6842), np.float32(0.8815), np.float32(0.8286), np.float32(0.902), np.float32(0.8606), np.float32(0.9801), np.float32(0.9785), np.float32(0.9718), np.float32(0.8441), np.float32(0.7426), np.float32(0.8867), np.float32(0.9646), np.float32(0.4792), np.float32(0.3446)] +2025-11-13 19:58:46.231688: Epoch time: 258.51 s +2025-11-13 19:58:47.981930: +2025-11-13 19:58:47.983463: Epoch 896 +2025-11-13 19:58:47.985185: Current learning rate: 0.0013 +2025-11-13 20:03:07.507673: train_loss -0.7301 +2025-11-13 20:03:07.512558: val_loss -0.7459 +2025-11-13 20:03:07.513829: Pseudo dice [np.float32(0.9256), np.float32(0.7864), np.float32(0.7329), np.float32(0.6786), np.float32(0.8736), np.float32(0.8246), np.float32(0.9232), np.float32(0.8722), np.float32(0.9792), np.float32(0.9776), np.float32(0.9728), np.float32(0.8488), np.float32(0.7834), np.float32(0.8871), np.float32(0.9675), np.float32(0.4443), np.float32(0.4535)] +2025-11-13 20:03:07.515627: Epoch time: 259.53 s +2025-11-13 20:03:09.250949: +2025-11-13 20:03:09.252402: Epoch 897 +2025-11-13 20:03:09.253903: Current learning rate: 0.00129 +2025-11-13 20:07:27.587859: train_loss -0.7362 +2025-11-13 20:07:27.592143: val_loss -0.742 +2025-11-13 20:07:27.593689: Pseudo dice [np.float32(0.924), np.float32(0.7729), np.float32(0.7278), np.float32(0.6719), np.float32(0.8775), np.float32(0.8321), np.float32(0.9226), np.float32(0.8747), np.float32(0.9827), np.float32(0.9817), np.float32(0.9722), np.float32(0.8447), np.float32(0.764), np.float32(0.8846), np.float32(0.9698), np.float32(0.463), np.float32(0.436)] +2025-11-13 20:07:27.594986: Epoch time: 258.34 s +2025-11-13 20:07:29.305838: +2025-11-13 20:07:29.307366: Epoch 898 +2025-11-13 20:07:29.308756: Current learning rate: 0.00128 +2025-11-13 20:11:47.730376: train_loss -0.7323 +2025-11-13 20:11:47.734440: val_loss -0.7464 +2025-11-13 20:11:47.736035: Pseudo dice [np.float32(0.9101), np.float32(0.7875), np.float32(0.748), np.float32(0.6794), np.float32(0.8724), np.float32(0.8107), np.float32(0.9097), np.float32(0.8616), np.float32(0.9695), np.float32(0.971), np.float32(0.9704), np.float32(0.8373), np.float32(0.7834), np.float32(0.8822), np.float32(0.9604), np.float32(0.5826), np.float32(0.4913)] +2025-11-13 20:11:47.737314: Epoch time: 258.43 s +2025-11-13 20:11:47.738408: Yayy! New best EMA pseudo Dice: 0.8165000081062317 +2025-11-13 20:11:52.546575: +2025-11-13 20:11:52.547800: Epoch 899 +2025-11-13 20:11:52.548922: Current learning rate: 0.00127 +2025-11-13 20:16:10.826223: train_loss -0.7287 +2025-11-13 20:16:10.830390: val_loss -0.7356 +2025-11-13 20:16:10.831709: Pseudo dice [np.float32(0.9209), np.float32(0.7898), np.float32(0.7198), np.float32(0.7016), np.float32(0.8761), np.float32(0.8313), np.float32(0.9107), np.float32(0.8644), np.float32(0.9789), np.float32(0.9795), np.float32(0.9725), np.float32(0.8574), np.float32(0.7805), np.float32(0.8813), np.float32(0.9672), np.float32(0.4532), np.float32(0.4016)] +2025-11-13 20:16:10.833375: Epoch time: 258.29 s +2025-11-13 20:16:13.752189: Yayy! New best EMA pseudo Dice: 0.8166000247001648 +2025-11-13 20:16:18.572053: +2025-11-13 20:16:18.573534: Epoch 900 +2025-11-13 20:16:18.574903: Current learning rate: 0.00126 +2025-11-13 20:20:36.640646: train_loss -0.7414 +2025-11-13 20:20:36.644179: val_loss -0.7392 +2025-11-13 20:20:36.645342: Pseudo dice [np.float32(0.9158), np.float32(0.7671), np.float32(0.7207), np.float32(0.7043), np.float32(0.8791), np.float32(0.8343), np.float32(0.9071), np.float32(0.8685), np.float32(0.9812), np.float32(0.9799), np.float32(0.9715), np.float32(0.8451), np.float32(0.7774), np.float32(0.8871), np.float32(0.968), np.float32(0.4458), np.float32(0.4137)] +2025-11-13 20:20:36.646441: Epoch time: 258.07 s +2025-11-13 20:20:38.395151: +2025-11-13 20:20:38.396638: Epoch 901 +2025-11-13 20:20:38.397921: Current learning rate: 0.00125 +2025-11-13 20:24:57.050737: train_loss -0.734 +2025-11-13 20:24:57.055211: val_loss -0.7457 +2025-11-13 20:24:57.056727: Pseudo dice [np.float32(0.9137), np.float32(0.7744), np.float32(0.7477), np.float32(0.6748), np.float32(0.8768), np.float32(0.8047), np.float32(0.9016), np.float32(0.8802), np.float32(0.9764), np.float32(0.9786), np.float32(0.9716), np.float32(0.8597), np.float32(0.7973), np.float32(0.8839), np.float32(0.9658), np.float32(0.4918), np.float32(0.4855)] +2025-11-13 20:24:57.058199: Epoch time: 258.66 s +2025-11-13 20:24:57.059187: Yayy! New best EMA pseudo Dice: 0.8170999884605408 +2025-11-13 20:25:01.999837: +2025-11-13 20:25:02.001399: Epoch 902 +2025-11-13 20:25:02.002795: Current learning rate: 0.00124 +2025-11-13 20:29:20.509145: train_loss -0.7307 +2025-11-13 20:29:20.514019: val_loss -0.7344 +2025-11-13 20:29:20.515596: Pseudo dice [np.float32(0.9251), np.float32(0.7916), np.float32(0.7233), np.float32(0.7045), np.float32(0.8835), np.float32(0.8187), np.float32(0.9197), np.float32(0.8667), np.float32(0.9826), np.float32(0.982), np.float32(0.9723), np.float32(0.8484), np.float32(0.7496), np.float32(0.8916), np.float32(0.9688), np.float32(0.4127), np.float32(0.3634)] +2025-11-13 20:29:20.517256: Epoch time: 258.52 s +2025-11-13 20:29:22.337871: +2025-11-13 20:29:22.339440: Epoch 903 +2025-11-13 20:29:22.340749: Current learning rate: 0.00122 +2025-11-13 20:33:41.030111: train_loss -0.7293 +2025-11-13 20:33:41.034334: val_loss -0.7438 +2025-11-13 20:33:41.036064: Pseudo dice [np.float32(0.9094), np.float32(0.8097), np.float32(0.755), np.float32(0.6496), np.float32(0.8759), np.float32(0.8286), np.float32(0.9141), np.float32(0.8642), np.float32(0.9782), np.float32(0.9815), np.float32(0.9718), np.float32(0.8512), np.float32(0.7857), np.float32(0.8893), np.float32(0.9648), np.float32(0.4634), np.float32(0.4382)] +2025-11-13 20:33:41.037582: Epoch time: 258.7 s +2025-11-13 20:33:42.762452: +2025-11-13 20:33:42.763674: Epoch 904 +2025-11-13 20:33:42.765111: Current learning rate: 0.00121 +2025-11-13 20:38:01.408408: train_loss -0.7324 +2025-11-13 20:38:01.413390: val_loss -0.7293 +2025-11-13 20:38:01.414969: Pseudo dice [np.float32(0.9161), np.float32(0.8025), np.float32(0.7484), np.float32(0.6638), np.float32(0.8767), np.float32(0.8137), np.float32(0.9122), np.float32(0.8654), np.float32(0.9778), np.float32(0.9782), np.float32(0.9728), np.float32(0.853), np.float32(0.773), np.float32(0.8858), np.float32(0.9689), np.float32(0.3892), np.float32(0.2653)] +2025-11-13 20:38:01.416408: Epoch time: 258.65 s +2025-11-13 20:38:03.161066: +2025-11-13 20:38:03.162547: Epoch 905 +2025-11-13 20:38:03.163715: Current learning rate: 0.0012 +2025-11-13 20:42:22.599742: train_loss -0.7358 +2025-11-13 20:42:22.604550: val_loss -0.7457 +2025-11-13 20:42:22.605879: Pseudo dice [np.float32(0.9204), np.float32(0.7732), np.float32(0.7374), np.float32(0.6678), np.float32(0.8849), np.float32(0.8229), np.float32(0.9102), np.float32(0.8742), np.float32(0.9711), np.float32(0.9699), np.float32(0.9718), np.float32(0.8567), np.float32(0.8049), np.float32(0.8937), np.float32(0.9629), np.float32(0.5614), np.float32(0.4894)] +2025-11-13 20:42:22.607490: Epoch time: 259.44 s +2025-11-13 20:42:24.475720: +2025-11-13 20:42:24.477279: Epoch 906 +2025-11-13 20:42:24.478650: Current learning rate: 0.00119 +2025-11-13 20:46:42.823874: train_loss -0.7339 +2025-11-13 20:46:42.828193: val_loss -0.7361 +2025-11-13 20:46:42.829653: Pseudo dice [np.float32(0.9159), np.float32(0.815), np.float32(0.715), np.float32(0.7148), np.float32(0.8759), np.float32(0.8178), np.float32(0.9061), np.float32(0.87), np.float32(0.9819), np.float32(0.9827), np.float32(0.9725), np.float32(0.853), np.float32(0.7762), np.float32(0.8867), np.float32(0.9697), np.float32(0.4944), np.float32(0.336)] +2025-11-13 20:46:42.830930: Epoch time: 258.35 s +2025-11-13 20:46:44.549916: +2025-11-13 20:46:44.551595: Epoch 907 +2025-11-13 20:46:44.553453: Current learning rate: 0.00118 +2025-11-13 20:51:02.881654: train_loss -0.7364 +2025-11-13 20:51:02.886344: val_loss -0.7392 +2025-11-13 20:51:02.887736: Pseudo dice [np.float32(0.9108), np.float32(0.8278), np.float32(0.7079), np.float32(0.6999), np.float32(0.8762), np.float32(0.8379), np.float32(0.9116), np.float32(0.8689), np.float32(0.98), np.float32(0.9804), np.float32(0.9715), np.float32(0.8522), np.float32(0.7927), np.float32(0.8854), np.float32(0.9666), np.float32(0.4307), np.float32(0.3862)] +2025-11-13 20:51:02.888935: Epoch time: 258.34 s +2025-11-13 20:51:04.579158: +2025-11-13 20:51:04.580607: Epoch 908 +2025-11-13 20:51:04.581938: Current learning rate: 0.00117 +2025-11-13 20:55:22.964386: train_loss -0.7304 +2025-11-13 20:55:22.968340: val_loss -0.7476 +2025-11-13 20:55:22.969492: Pseudo dice [np.float32(0.9258), np.float32(0.8096), np.float32(0.7741), np.float32(0.6717), np.float32(0.8818), np.float32(0.8218), np.float32(0.9197), np.float32(0.8676), np.float32(0.9821), np.float32(0.9815), np.float32(0.9713), np.float32(0.8447), np.float32(0.7979), np.float32(0.895), np.float32(0.9667), np.float32(0.4271), np.float32(0.4952)] +2025-11-13 20:55:22.970868: Epoch time: 258.39 s +2025-11-13 20:55:22.972233: Yayy! New best EMA pseudo Dice: 0.8176000118255615 +2025-11-13 20:55:27.626279: +2025-11-13 20:55:27.627671: Epoch 909 +2025-11-13 20:55:27.628935: Current learning rate: 0.00116 +2025-11-13 20:59:45.849648: train_loss -0.7326 +2025-11-13 20:59:45.853758: val_loss -0.7374 +2025-11-13 20:59:45.854963: Pseudo dice [np.float32(0.9193), np.float32(0.7857), np.float32(0.7311), np.float32(0.6801), np.float32(0.8697), np.float32(0.8185), np.float32(0.9286), np.float32(0.8605), np.float32(0.9802), np.float32(0.9791), np.float32(0.9717), np.float32(0.8474), np.float32(0.7825), np.float32(0.884), np.float32(0.9654), np.float32(0.5234), np.float32(0.4235)] +2025-11-13 20:59:45.856134: Epoch time: 258.23 s +2025-11-13 20:59:45.857133: Yayy! New best EMA pseudo Dice: 0.8179000020027161 +2025-11-13 20:59:50.857555: +2025-11-13 20:59:50.859164: Epoch 910 +2025-11-13 20:59:50.860547: Current learning rate: 0.00115 +2025-11-13 21:04:09.214916: train_loss -0.7295 +2025-11-13 21:04:09.219723: val_loss -0.7405 +2025-11-13 21:04:09.221251: Pseudo dice [np.float32(0.9117), np.float32(0.8258), np.float32(0.7319), np.float32(0.6653), np.float32(0.8863), np.float32(0.8286), np.float32(0.922), np.float32(0.8692), np.float32(0.9816), np.float32(0.9823), np.float32(0.9722), np.float32(0.8476), np.float32(0.7729), np.float32(0.8906), np.float32(0.9682), np.float32(0.4429), np.float32(0.3655)] +2025-11-13 21:04:09.222737: Epoch time: 258.36 s +2025-11-13 21:04:11.230748: +2025-11-13 21:04:11.232605: Epoch 911 +2025-11-13 21:04:11.234046: Current learning rate: 0.00113 +2025-11-13 21:08:29.604295: train_loss -0.7382 +2025-11-13 21:08:29.608837: val_loss -0.7349 +2025-11-13 21:08:29.610628: Pseudo dice [np.float32(0.925), np.float32(0.795), np.float32(0.7654), np.float32(0.667), np.float32(0.8779), np.float32(0.8239), np.float32(0.9205), np.float32(0.8621), np.float32(0.9787), np.float32(0.9782), np.float32(0.972), np.float32(0.8424), np.float32(0.7364), np.float32(0.8865), np.float32(0.9635), np.float32(0.5368), np.float32(0.3827)] +2025-11-13 21:08:29.612111: Epoch time: 258.38 s +2025-11-13 21:08:31.292138: +2025-11-13 21:08:31.293685: Epoch 912 +2025-11-13 21:08:31.295057: Current learning rate: 0.00112 +2025-11-13 21:12:49.789082: train_loss -0.7312 +2025-11-13 21:12:49.793912: val_loss -0.7378 +2025-11-13 21:12:49.795117: Pseudo dice [np.float32(0.9254), np.float32(0.772), np.float32(0.7383), np.float32(0.6736), np.float32(0.8779), np.float32(0.8163), np.float32(0.9002), np.float32(0.8651), np.float32(0.9809), np.float32(0.9805), np.float32(0.9703), np.float32(0.8505), np.float32(0.7706), np.float32(0.8865), np.float32(0.966), np.float32(0.4338), np.float32(0.4537)] +2025-11-13 21:12:49.796689: Epoch time: 258.5 s +2025-11-13 21:12:51.489014: +2025-11-13 21:12:51.490374: Epoch 913 +2025-11-13 21:12:51.491648: Current learning rate: 0.00111 +2025-11-13 21:17:10.066811: train_loss -0.7391 +2025-11-13 21:17:10.070717: val_loss -0.7511 +2025-11-13 21:17:10.072012: Pseudo dice [np.float32(0.92), np.float32(0.8053), np.float32(0.7502), np.float32(0.6478), np.float32(0.8799), np.float32(0.8367), np.float32(0.9117), np.float32(0.8779), np.float32(0.9725), np.float32(0.9737), np.float32(0.972), np.float32(0.8491), np.float32(0.7698), np.float32(0.8862), np.float32(0.9663), np.float32(0.5736), np.float32(0.4585)] +2025-11-13 21:17:10.073154: Epoch time: 258.58 s +2025-11-13 21:17:10.074548: Yayy! New best EMA pseudo Dice: 0.8184000253677368 +2025-11-13 21:17:14.893658: +2025-11-13 21:17:14.895317: Epoch 914 +2025-11-13 21:17:14.896737: Current learning rate: 0.0011 +2025-11-13 21:21:34.251468: train_loss -0.732 +2025-11-13 21:21:34.255485: val_loss -0.7336 +2025-11-13 21:21:34.256688: Pseudo dice [np.float32(0.9165), np.float32(0.7784), np.float32(0.7452), np.float32(0.6843), np.float32(0.8697), np.float32(0.8307), np.float32(0.9157), np.float32(0.8704), np.float32(0.9827), np.float32(0.9812), np.float32(0.9722), np.float32(0.8541), np.float32(0.7787), np.float32(0.8859), np.float32(0.967), np.float32(0.5063), np.float32(0.4382)] +2025-11-13 21:21:34.257961: Epoch time: 259.36 s +2025-11-13 21:21:34.259228: Yayy! New best EMA pseudo Dice: 0.8187999725341797 +2025-11-13 21:21:39.524195: +2025-11-13 21:21:39.526491: Epoch 915 +2025-11-13 21:21:39.528124: Current learning rate: 0.00109 +2025-11-13 21:25:58.005800: train_loss -0.7314 +2025-11-13 21:25:58.010455: val_loss -0.7403 +2025-11-13 21:25:58.012041: Pseudo dice [np.float32(0.9117), np.float32(0.7941), np.float32(0.7536), np.float32(0.683), np.float32(0.8857), np.float32(0.8074), np.float32(0.9112), np.float32(0.8754), np.float32(0.9779), np.float32(0.9768), np.float32(0.9717), np.float32(0.8341), np.float32(0.7726), np.float32(0.891), np.float32(0.967), np.float32(0.5269), np.float32(0.4687)] +2025-11-13 21:25:58.013560: Epoch time: 258.49 s +2025-11-13 21:25:58.015119: Yayy! New best EMA pseudo Dice: 0.8192999958992004 +2025-11-13 21:26:02.852261: +2025-11-13 21:26:02.853648: Epoch 916 +2025-11-13 21:26:02.854731: Current learning rate: 0.00108 +2025-11-13 21:30:21.134597: train_loss -0.732 +2025-11-13 21:30:21.138704: val_loss -0.7409 +2025-11-13 21:30:21.139863: Pseudo dice [np.float32(0.9124), np.float32(0.7806), np.float32(0.7314), np.float32(0.6737), np.float32(0.8787), np.float32(0.8137), np.float32(0.9123), np.float32(0.8651), np.float32(0.9813), np.float32(0.9782), np.float32(0.9717), np.float32(0.8433), np.float32(0.7725), np.float32(0.8859), np.float32(0.9678), np.float32(0.5243), np.float32(0.4462)] +2025-11-13 21:30:21.141156: Epoch time: 258.29 s +2025-11-13 21:30:21.142673: Yayy! New best EMA pseudo Dice: 0.8194000124931335 +2025-11-13 21:30:25.911306: +2025-11-13 21:30:25.913308: Epoch 917 +2025-11-13 21:30:25.915094: Current learning rate: 0.00106 +2025-11-13 21:34:44.038302: train_loss -0.7376 +2025-11-13 21:34:44.042383: val_loss -0.7294 +2025-11-13 21:34:44.043727: Pseudo dice [np.float32(0.92), np.float32(0.766), np.float32(0.7246), np.float32(0.6679), np.float32(0.8776), np.float32(0.8125), np.float32(0.9076), np.float32(0.8641), np.float32(0.9782), np.float32(0.9763), np.float32(0.9725), np.float32(0.8434), np.float32(0.7754), np.float32(0.8834), np.float32(0.9658), np.float32(0.397), np.float32(0.3953)] +2025-11-13 21:34:44.044866: Epoch time: 258.13 s +2025-11-13 21:34:45.766656: +2025-11-13 21:34:45.768286: Epoch 918 +2025-11-13 21:34:45.769644: Current learning rate: 0.00105 +2025-11-13 21:39:04.149718: train_loss -0.7343 +2025-11-13 21:39:04.154111: val_loss -0.7349 +2025-11-13 21:39:04.155345: Pseudo dice [np.float32(0.9196), np.float32(0.8091), np.float32(0.7494), np.float32(0.6848), np.float32(0.8783), np.float32(0.8224), np.float32(0.9043), np.float32(0.8623), np.float32(0.9759), np.float32(0.9715), np.float32(0.9714), np.float32(0.8465), np.float32(0.7677), np.float32(0.8913), np.float32(0.9687), np.float32(0.4007), np.float32(0.2796)] +2025-11-13 21:39:04.156558: Epoch time: 258.39 s +2025-11-13 21:39:05.852107: +2025-11-13 21:39:05.853622: Epoch 919 +2025-11-13 21:39:05.854919: Current learning rate: 0.00104 +2025-11-13 21:43:24.513005: train_loss -0.735 +2025-11-13 21:43:24.517545: val_loss -0.7474 +2025-11-13 21:43:24.519010: Pseudo dice [np.float32(0.9217), np.float32(0.796), np.float32(0.7459), np.float32(0.6574), np.float32(0.8764), np.float32(0.8319), np.float32(0.9087), np.float32(0.8757), np.float32(0.9815), np.float32(0.9811), np.float32(0.973), np.float32(0.8433), np.float32(0.778), np.float32(0.8879), np.float32(0.9669), np.float32(0.4447), np.float32(0.4556)] +2025-11-13 21:43:24.520368: Epoch time: 258.67 s +2025-11-13 21:43:26.192878: +2025-11-13 21:43:26.194348: Epoch 920 +2025-11-13 21:43:26.195680: Current learning rate: 0.00103 +2025-11-13 21:47:44.692850: train_loss -0.7367 +2025-11-13 21:47:44.697568: val_loss -0.7501 +2025-11-13 21:47:44.699139: Pseudo dice [np.float32(0.9271), np.float32(0.7824), np.float32(0.7577), np.float32(0.6565), np.float32(0.8799), np.float32(0.8221), np.float32(0.9121), np.float32(0.8592), np.float32(0.9727), np.float32(0.9734), np.float32(0.9713), np.float32(0.8466), np.float32(0.7847), np.float32(0.8873), np.float32(0.9649), np.float32(0.6027), np.float32(0.4625)] +2025-11-13 21:47:44.700831: Epoch time: 258.51 s +2025-11-13 21:47:46.427179: +2025-11-13 21:47:46.428900: Epoch 921 +2025-11-13 21:47:46.430503: Current learning rate: 0.00102 +2025-11-13 21:52:04.754956: train_loss -0.7374 +2025-11-13 21:52:04.759014: val_loss -0.7523 +2025-11-13 21:52:04.760422: Pseudo dice [np.float32(0.9198), np.float32(0.8192), np.float32(0.7618), np.float32(0.7008), np.float32(0.8814), np.float32(0.8254), np.float32(0.9178), np.float32(0.8663), np.float32(0.9788), np.float32(0.978), np.float32(0.9723), np.float32(0.8507), np.float32(0.7787), np.float32(0.8893), np.float32(0.9692), np.float32(0.5443), np.float32(0.3716)] +2025-11-13 21:52:04.761585: Epoch time: 258.33 s +2025-11-13 21:52:06.466308: +2025-11-13 21:52:06.467620: Epoch 922 +2025-11-13 21:52:06.468961: Current learning rate: 0.00101 +2025-11-13 21:56:24.836899: train_loss -0.7362 +2025-11-13 21:56:24.840946: val_loss -0.738 +2025-11-13 21:56:24.842158: Pseudo dice [np.float32(0.9237), np.float32(0.7793), np.float32(0.7495), np.float32(0.6624), np.float32(0.8798), np.float32(0.8202), np.float32(0.926), np.float32(0.8688), np.float32(0.9824), np.float32(0.9828), np.float32(0.9725), np.float32(0.8629), np.float32(0.7762), np.float32(0.8895), np.float32(0.9676), np.float32(0.4042), np.float32(0.4324)] +2025-11-13 21:56:24.843269: Epoch time: 258.38 s +2025-11-13 21:56:26.496918: +2025-11-13 21:56:26.498616: Epoch 923 +2025-11-13 21:56:26.500025: Current learning rate: 0.001 +2025-11-13 22:00:45.675726: train_loss -0.7336 +2025-11-13 22:00:45.679695: val_loss -0.7409 +2025-11-13 22:00:45.680848: Pseudo dice [np.float32(0.9111), np.float32(0.7908), np.float32(0.7099), np.float32(0.6572), np.float32(0.8771), np.float32(0.8112), np.float32(0.9209), np.float32(0.8575), np.float32(0.9684), np.float32(0.9705), np.float32(0.9713), np.float32(0.8585), np.float32(0.7711), np.float32(0.882), np.float32(0.9654), np.float32(0.5127), np.float32(0.5354)] +2025-11-13 22:00:45.681985: Epoch time: 259.18 s +2025-11-13 22:00:47.619666: +2025-11-13 22:00:47.621594: Epoch 924 +2025-11-13 22:00:47.623070: Current learning rate: 0.00098 +2025-11-13 22:05:06.130305: train_loss -0.735 +2025-11-13 22:05:06.135087: val_loss -0.7354 +2025-11-13 22:05:06.136549: Pseudo dice [np.float32(0.921), np.float32(0.7927), np.float32(0.7365), np.float32(0.6847), np.float32(0.8842), np.float32(0.8289), np.float32(0.9039), np.float32(0.8797), np.float32(0.9787), np.float32(0.9793), np.float32(0.9721), np.float32(0.8464), np.float32(0.7779), np.float32(0.8895), np.float32(0.9666), np.float32(0.3878), np.float32(0.4305)] +2025-11-13 22:05:06.138063: Epoch time: 258.52 s +2025-11-13 22:05:07.846873: +2025-11-13 22:05:07.848333: Epoch 925 +2025-11-13 22:05:07.849734: Current learning rate: 0.00097 +2025-11-13 22:09:26.340202: train_loss -0.7376 +2025-11-13 22:09:26.344442: val_loss -0.7482 +2025-11-13 22:09:26.345796: Pseudo dice [np.float32(0.9248), np.float32(0.8202), np.float32(0.745), np.float32(0.6898), np.float32(0.8862), np.float32(0.8211), np.float32(0.9136), np.float32(0.8758), np.float32(0.9809), np.float32(0.9809), np.float32(0.9719), np.float32(0.8394), np.float32(0.7819), np.float32(0.8872), np.float32(0.9677), np.float32(0.4478), np.float32(0.4569)] +2025-11-13 22:09:26.347037: Epoch time: 258.5 s +2025-11-13 22:09:28.059539: +2025-11-13 22:09:28.061213: Epoch 926 +2025-11-13 22:09:28.062504: Current learning rate: 0.00096 +2025-11-13 22:13:46.245019: train_loss -0.7308 +2025-11-13 22:13:46.248936: val_loss -0.7443 +2025-11-13 22:13:46.250179: Pseudo dice [np.float32(0.9287), np.float32(0.8095), np.float32(0.7439), np.float32(0.6883), np.float32(0.8793), np.float32(0.8245), np.float32(0.919), np.float32(0.8723), np.float32(0.9818), np.float32(0.9793), np.float32(0.9717), np.float32(0.8475), np.float32(0.7751), np.float32(0.8863), np.float32(0.9681), np.float32(0.4683), np.float32(0.3856)] +2025-11-13 22:13:46.251414: Epoch time: 258.19 s +2025-11-13 22:13:47.924512: +2025-11-13 22:13:47.925781: Epoch 927 +2025-11-13 22:13:47.926924: Current learning rate: 0.00095 +2025-11-13 22:18:06.763158: train_loss -0.7347 +2025-11-13 22:18:06.768105: val_loss -0.7447 +2025-11-13 22:18:06.769641: Pseudo dice [np.float32(0.922), np.float32(0.8024), np.float32(0.7507), np.float32(0.6777), np.float32(0.8794), np.float32(0.8183), np.float32(0.9222), np.float32(0.8745), np.float32(0.9783), np.float32(0.9774), np.float32(0.9726), np.float32(0.8473), np.float32(0.7464), np.float32(0.8866), np.float32(0.9691), np.float32(0.4311), np.float32(0.4639)] +2025-11-13 22:18:06.771376: Epoch time: 258.84 s +2025-11-13 22:18:08.523795: +2025-11-13 22:18:08.525470: Epoch 928 +2025-11-13 22:18:08.526899: Current learning rate: 0.00094 +2025-11-13 22:22:27.286274: train_loss -0.7374 +2025-11-13 22:22:27.291293: val_loss -0.745 +2025-11-13 22:22:27.292585: Pseudo dice [np.float32(0.915), np.float32(0.7949), np.float32(0.7409), np.float32(0.6886), np.float32(0.8835), np.float32(0.8302), np.float32(0.9114), np.float32(0.8688), np.float32(0.981), np.float32(0.9813), np.float32(0.9713), np.float32(0.8525), np.float32(0.7857), np.float32(0.8926), np.float32(0.9662), np.float32(0.4347), np.float32(0.4455)] +2025-11-13 22:22:27.294228: Epoch time: 258.77 s +2025-11-13 22:22:29.000897: +2025-11-13 22:22:29.002433: Epoch 929 +2025-11-13 22:22:29.003736: Current learning rate: 0.00092 +2025-11-13 22:26:47.358416: train_loss -0.7317 +2025-11-13 22:26:47.362562: val_loss -0.7395 +2025-11-13 22:26:47.363798: Pseudo dice [np.float32(0.9159), np.float32(0.7992), np.float32(0.7469), np.float32(0.7083), np.float32(0.8796), np.float32(0.8236), np.float32(0.9135), np.float32(0.8746), np.float32(0.9794), np.float32(0.9805), np.float32(0.9723), np.float32(0.844), np.float32(0.7651), np.float32(0.8821), np.float32(0.9667), np.float32(0.4999), np.float32(0.4015)] +2025-11-13 22:26:47.365234: Epoch time: 258.36 s +2025-11-13 22:26:49.058595: +2025-11-13 22:26:49.060006: Epoch 930 +2025-11-13 22:26:49.061301: Current learning rate: 0.00091 +2025-11-13 22:31:07.422068: train_loss -0.7357 +2025-11-13 22:31:07.426270: val_loss -0.739 +2025-11-13 22:31:07.427607: Pseudo dice [np.float32(0.9225), np.float32(0.764), np.float32(0.7449), np.float32(0.6641), np.float32(0.8819), np.float32(0.8178), np.float32(0.9106), np.float32(0.8692), np.float32(0.9761), np.float32(0.9774), np.float32(0.9722), np.float32(0.8485), np.float32(0.7903), np.float32(0.8896), np.float32(0.9651), np.float32(0.4589), np.float32(0.4049)] +2025-11-13 22:31:07.429477: Epoch time: 258.37 s +2025-11-13 22:31:09.158439: +2025-11-13 22:31:09.159994: Epoch 931 +2025-11-13 22:31:09.161389: Current learning rate: 0.0009 +2025-11-13 22:35:27.510221: train_loss -0.7362 +2025-11-13 22:35:27.514491: val_loss -0.7406 +2025-11-13 22:35:27.515680: Pseudo dice [np.float32(0.922), np.float32(0.8128), np.float32(0.7256), np.float32(0.6901), np.float32(0.8798), np.float32(0.843), np.float32(0.9204), np.float32(0.8735), np.float32(0.9765), np.float32(0.9753), np.float32(0.9705), np.float32(0.858), np.float32(0.7982), np.float32(0.8873), np.float32(0.9629), np.float32(0.4601), np.float32(0.3932)] +2025-11-13 22:35:27.516944: Epoch time: 258.36 s +2025-11-13 22:35:29.213580: +2025-11-13 22:35:29.215486: Epoch 932 +2025-11-13 22:35:29.216970: Current learning rate: 0.00089 +2025-11-13 22:39:47.732013: train_loss -0.7342 +2025-11-13 22:39:47.736114: val_loss -0.7401 +2025-11-13 22:39:47.737543: Pseudo dice [np.float32(0.9247), np.float32(0.7934), np.float32(0.7184), np.float32(0.6789), np.float32(0.8783), np.float32(0.8303), np.float32(0.9257), np.float32(0.8702), np.float32(0.9815), np.float32(0.9818), np.float32(0.9722), np.float32(0.8547), np.float32(0.7862), np.float32(0.8935), np.float32(0.9693), np.float32(0.5291), np.float32(0.4156)] +2025-11-13 22:39:47.738658: Epoch time: 258.52 s +2025-11-13 22:39:47.739783: Yayy! New best EMA pseudo Dice: 0.8195000290870667 +2025-11-13 22:39:54.486828: +2025-11-13 22:39:54.488239: Epoch 933 +2025-11-13 22:39:54.489536: Current learning rate: 0.00088 +2025-11-13 22:44:12.864034: train_loss -0.742 +2025-11-13 22:44:12.868145: val_loss -0.7365 +2025-11-13 22:44:12.869371: Pseudo dice [np.float32(0.9287), np.float32(0.8166), np.float32(0.7237), np.float32(0.6768), np.float32(0.8768), np.float32(0.8264), np.float32(0.9206), np.float32(0.8566), np.float32(0.9826), np.float32(0.9814), np.float32(0.9723), np.float32(0.854), np.float32(0.7729), np.float32(0.8891), np.float32(0.9688), np.float32(0.5016), np.float32(0.4284)] +2025-11-13 22:44:12.870673: Epoch time: 258.38 s +2025-11-13 22:44:12.871691: Yayy! New best EMA pseudo Dice: 0.8198000192642212 +2025-11-13 22:44:17.776886: +2025-11-13 22:44:17.778413: Epoch 934 +2025-11-13 22:44:17.780406: Current learning rate: 0.00087 +2025-11-13 22:48:36.082713: train_loss -0.7311 +2025-11-13 22:48:36.087344: val_loss -0.7356 +2025-11-13 22:48:36.088665: Pseudo dice [np.float32(0.9238), np.float32(0.7914), np.float32(0.7486), np.float32(0.6688), np.float32(0.8827), np.float32(0.8269), np.float32(0.9127), np.float32(0.8581), np.float32(0.982), np.float32(0.9811), np.float32(0.9729), np.float32(0.8522), np.float32(0.773), np.float32(0.8911), np.float32(0.9668), np.float32(0.4987), np.float32(0.2801)] +2025-11-13 22:48:36.090057: Epoch time: 258.31 s +2025-11-13 22:51:01.417994: +2025-11-13 22:51:01.420064: Epoch 935 +2025-11-13 22:51:01.421609: Current learning rate: 0.00085 +2025-11-13 22:55:18.485889: train_loss -0.7365 +2025-11-13 22:55:18.489872: val_loss -0.7347 +2025-11-13 22:55:18.491165: Pseudo dice [np.float32(0.9121), np.float32(0.8086), np.float32(0.7368), np.float32(0.6783), np.float32(0.8761), np.float32(0.8372), np.float32(0.9247), np.float32(0.8679), np.float32(0.9795), np.float32(0.9811), np.float32(0.9724), np.float32(0.8591), np.float32(0.7704), np.float32(0.8853), np.float32(0.9673), np.float32(0.3789), np.float32(0.3425)] +2025-11-13 22:55:18.492389: Epoch time: 257.07 s +2025-11-13 22:56:42.449507: +2025-11-13 22:56:42.451452: Epoch 936 +2025-11-13 22:56:42.453415: Current learning rate: 0.00084 +2025-11-13 23:00:59.903658: train_loss -0.7398 +2025-11-13 23:00:59.908323: val_loss -0.7347 +2025-11-13 23:00:59.909795: Pseudo dice [np.float32(0.9248), np.float32(0.8246), np.float32(0.7337), np.float32(0.6912), np.float32(0.8812), np.float32(0.8195), np.float32(0.9206), np.float32(0.8773), np.float32(0.9754), np.float32(0.9756), np.float32(0.9717), np.float32(0.846), np.float32(0.8023), np.float32(0.8917), np.float32(0.969), np.float32(0.3989), np.float32(0.3806)] +2025-11-13 23:00:59.911151: Epoch time: 257.46 s +2025-11-13 23:02:29.492338: +2025-11-13 23:02:29.494446: Epoch 937 +2025-11-13 23:02:29.495667: Current learning rate: 0.00083 +2025-11-13 23:06:47.073124: train_loss -0.7323 +2025-11-13 23:06:47.077828: val_loss -0.7353 +2025-11-13 23:06:47.079304: Pseudo dice [np.float32(0.9216), np.float32(0.8146), np.float32(0.7296), np.float32(0.6651), np.float32(0.8807), np.float32(0.8336), np.float32(0.9167), np.float32(0.8602), np.float32(0.9801), np.float32(0.9752), np.float32(0.9718), np.float32(0.8469), np.float32(0.7837), np.float32(0.8859), np.float32(0.9672), np.float32(0.3393), np.float32(0.4391)] +2025-11-13 23:06:47.081365: Epoch time: 257.59 s +2025-11-13 23:07:11.505412: +2025-11-13 23:07:11.506825: Epoch 938 +2025-11-13 23:07:11.508251: Current learning rate: 0.00082 +2025-11-13 23:11:29.643743: train_loss -0.7403 +2025-11-13 23:11:29.647532: val_loss -0.7345 +2025-11-13 23:11:29.649490: Pseudo dice [np.float32(0.9101), np.float32(0.7875), np.float32(0.7), np.float32(0.6873), np.float32(0.8792), np.float32(0.821), np.float32(0.9109), np.float32(0.8644), np.float32(0.9809), np.float32(0.9806), np.float32(0.971), np.float32(0.858), np.float32(0.7809), np.float32(0.8918), np.float32(0.9668), np.float32(0.4277), np.float32(0.4046)] +2025-11-13 23:11:29.650626: Epoch time: 258.14 s +2025-11-13 23:11:31.322856: +2025-11-13 23:11:31.324682: Epoch 939 +2025-11-13 23:11:31.326148: Current learning rate: 0.00081 +2025-11-13 23:15:49.690302: train_loss -0.7376 +2025-11-13 23:15:49.694251: val_loss -0.7472 +2025-11-13 23:15:49.695480: Pseudo dice [np.float32(0.9306), np.float32(0.7921), np.float32(0.7413), np.float32(0.6729), np.float32(0.8723), np.float32(0.8299), np.float32(0.9128), np.float32(0.8716), np.float32(0.9811), np.float32(0.9822), np.float32(0.9723), np.float32(0.853), np.float32(0.7943), np.float32(0.8886), np.float32(0.9705), np.float32(0.5108), np.float32(0.5222)] +2025-11-13 23:15:49.696933: Epoch time: 258.37 s +2025-11-13 23:15:51.636417: +2025-11-13 23:15:51.638098: Epoch 940 +2025-11-13 23:15:51.639467: Current learning rate: 0.00079 +2025-11-13 23:20:09.915725: train_loss -0.7389 +2025-11-13 23:20:09.919878: val_loss -0.7454 +2025-11-13 23:20:09.921594: Pseudo dice [np.float32(0.9186), np.float32(0.8082), np.float32(0.7363), np.float32(0.6821), np.float32(0.878), np.float32(0.8361), np.float32(0.917), np.float32(0.8733), np.float32(0.9815), np.float32(0.9796), np.float32(0.9728), np.float32(0.8466), np.float32(0.7688), np.float32(0.8894), np.float32(0.9672), np.float32(0.3989), np.float32(0.3524)] +2025-11-13 23:20:09.923126: Epoch time: 258.28 s +2025-11-13 23:20:11.611759: +2025-11-13 23:20:11.613551: Epoch 941 +2025-11-13 23:20:11.615072: Current learning rate: 0.00078 +2025-11-13 23:24:30.180179: train_loss -0.7387 +2025-11-13 23:24:30.184470: val_loss -0.7448 +2025-11-13 23:24:30.185990: Pseudo dice [np.float32(0.9287), np.float32(0.8068), np.float32(0.7441), np.float32(0.6707), np.float32(0.8826), np.float32(0.8268), np.float32(0.9185), np.float32(0.868), np.float32(0.9835), np.float32(0.9815), np.float32(0.9722), np.float32(0.8584), np.float32(0.7897), np.float32(0.8884), np.float32(0.9671), np.float32(0.5565), np.float32(0.4562)] +2025-11-13 23:24:30.187368: Epoch time: 258.57 s +2025-11-13 23:24:31.963335: +2025-11-13 23:24:31.965017: Epoch 942 +2025-11-13 23:24:31.966591: Current learning rate: 0.00077 +2025-11-13 23:28:51.947256: train_loss -0.7369 +2025-11-13 23:28:51.951194: val_loss -0.7283 +2025-11-13 23:28:51.952413: Pseudo dice [np.float32(0.9217), np.float32(0.7987), np.float32(0.7121), np.float32(0.6821), np.float32(0.8814), np.float32(0.8222), np.float32(0.9171), np.float32(0.8696), np.float32(0.9813), np.float32(0.9801), np.float32(0.9713), np.float32(0.8556), np.float32(0.7889), np.float32(0.8908), np.float32(0.9662), np.float32(0.5617), np.float32(0.4825)] +2025-11-13 23:28:51.953749: Epoch time: 259.99 s +2025-11-13 23:28:53.662426: +2025-11-13 23:28:53.663909: Epoch 943 +2025-11-13 23:28:53.665317: Current learning rate: 0.00076 +2025-11-13 23:33:12.219593: train_loss -0.7383 +2025-11-13 23:33:12.224385: val_loss -0.7379 +2025-11-13 23:33:12.226031: Pseudo dice [np.float32(0.9139), np.float32(0.781), np.float32(0.7147), np.float32(0.6796), np.float32(0.8771), np.float32(0.832), np.float32(0.921), np.float32(0.8774), np.float32(0.9818), np.float32(0.9825), np.float32(0.972), np.float32(0.8449), np.float32(0.774), np.float32(0.8878), np.float32(0.9674), np.float32(0.4522), np.float32(0.4129)] +2025-11-13 23:33:12.227264: Epoch time: 258.56 s +2025-11-13 23:33:14.021617: +2025-11-13 23:33:14.023085: Epoch 944 +2025-11-13 23:33:14.024994: Current learning rate: 0.00075 +2025-11-13 23:37:32.427723: train_loss -0.732 +2025-11-13 23:37:32.432578: val_loss -0.7474 +2025-11-13 23:37:32.434042: Pseudo dice [np.float32(0.9163), np.float32(0.7887), np.float32(0.7504), np.float32(0.6773), np.float32(0.8817), np.float32(0.8277), np.float32(0.92), np.float32(0.8762), np.float32(0.9777), np.float32(0.9778), np.float32(0.9718), np.float32(0.8462), np.float32(0.782), np.float32(0.8867), np.float32(0.9636), np.float32(0.521), np.float32(0.4458)] +2025-11-13 23:37:32.435162: Epoch time: 258.42 s +2025-11-13 23:37:32.436840: Yayy! New best EMA pseudo Dice: 0.8198999762535095 +2025-11-13 23:37:36.983302: +2025-11-13 23:37:36.984948: Epoch 945 +2025-11-13 23:37:36.986320: Current learning rate: 0.00074 +2025-11-13 23:41:55.581979: train_loss -0.7375 +2025-11-13 23:41:55.586519: val_loss -0.7391 +2025-11-13 23:41:55.588081: Pseudo dice [np.float32(0.9153), np.float32(0.8291), np.float32(0.7345), np.float32(0.6923), np.float32(0.8802), np.float32(0.8236), np.float32(0.914), np.float32(0.8673), np.float32(0.9796), np.float32(0.9792), np.float32(0.9729), np.float32(0.8432), np.float32(0.7658), np.float32(0.8892), np.float32(0.9686), np.float32(0.3695), np.float32(0.3852)] +2025-11-13 23:41:55.589642: Epoch time: 258.6 s +2025-11-13 23:41:57.296696: +2025-11-13 23:41:57.298510: Epoch 946 +2025-11-13 23:41:57.300229: Current learning rate: 0.00072 +2025-11-13 23:46:15.709673: train_loss -0.7365 +2025-11-13 23:46:15.714537: val_loss -0.7457 +2025-11-13 23:46:15.716314: Pseudo dice [np.float32(0.926), np.float32(0.7851), np.float32(0.7498), np.float32(0.6775), np.float32(0.8779), np.float32(0.8338), np.float32(0.9094), np.float32(0.8658), np.float32(0.9794), np.float32(0.9777), np.float32(0.9738), np.float32(0.852), np.float32(0.7608), np.float32(0.8868), np.float32(0.9695), np.float32(0.4765), np.float32(0.4426)] +2025-11-13 23:46:15.717741: Epoch time: 258.42 s +2025-11-13 23:46:17.550756: +2025-11-13 23:46:17.552256: Epoch 947 +2025-11-13 23:46:17.553684: Current learning rate: 0.00071 +2025-11-13 23:50:36.084220: train_loss -0.7353 +2025-11-13 23:50:36.088571: val_loss -0.7522 +2025-11-13 23:50:36.089963: Pseudo dice [np.float32(0.9215), np.float32(0.8059), np.float32(0.7331), np.float32(0.67), np.float32(0.8814), np.float32(0.8338), np.float32(0.9008), np.float32(0.8628), np.float32(0.9795), np.float32(0.9818), np.float32(0.9721), np.float32(0.8461), np.float32(0.7829), np.float32(0.8889), np.float32(0.9665), np.float32(0.5226), np.float32(0.5297)] +2025-11-13 23:50:36.091618: Epoch time: 258.54 s +2025-11-13 23:50:36.093047: Yayy! New best EMA pseudo Dice: 0.8201000094413757 +2025-11-13 23:50:40.849296: +2025-11-13 23:50:40.850835: Epoch 948 +2025-11-13 23:50:40.852092: Current learning rate: 0.0007 +2025-11-13 23:54:59.387487: train_loss -0.7374 +2025-11-13 23:54:59.391175: val_loss -0.741 +2025-11-13 23:54:59.392503: Pseudo dice [np.float32(0.9261), np.float32(0.8009), np.float32(0.7453), np.float32(0.6752), np.float32(0.8729), np.float32(0.8326), np.float32(0.9146), np.float32(0.8754), np.float32(0.9786), np.float32(0.9766), np.float32(0.9714), np.float32(0.8552), np.float32(0.7657), np.float32(0.8824), np.float32(0.963), np.float32(0.5554), np.float32(0.5082)] +2025-11-13 23:54:59.393567: Epoch time: 258.54 s +2025-11-13 23:54:59.394944: Yayy! New best EMA pseudo Dice: 0.8210999965667725 +2025-11-13 23:55:28.076467: +2025-11-13 23:55:28.078163: Epoch 949 +2025-11-13 23:55:28.079790: Current learning rate: 0.00069 +2025-11-13 23:59:46.215160: train_loss -0.7446 +2025-11-13 23:59:46.219383: val_loss -0.7497 +2025-11-13 23:59:46.220971: Pseudo dice [np.float32(0.9227), np.float32(0.8001), np.float32(0.7402), np.float32(0.6922), np.float32(0.8824), np.float32(0.8176), np.float32(0.9223), np.float32(0.8723), np.float32(0.9745), np.float32(0.9749), np.float32(0.9715), np.float32(0.8519), np.float32(0.7705), np.float32(0.8919), np.float32(0.9675), np.float32(0.4875), np.float32(0.4031)] +2025-11-13 23:59:46.222068: Epoch time: 258.15 s +2025-11-14 00:00:12.076556: +2025-11-14 00:00:12.077900: Epoch 950 +2025-11-14 00:00:12.079418: Current learning rate: 0.00067 +2025-11-14 00:04:30.389611: train_loss -0.7341 +2025-11-14 00:04:30.393705: val_loss -0.7518 +2025-11-14 00:04:30.395006: Pseudo dice [np.float32(0.9035), np.float32(0.7937), np.float32(0.7537), np.float32(0.7124), np.float32(0.8766), np.float32(0.8361), np.float32(0.9094), np.float32(0.8649), np.float32(0.9779), np.float32(0.98), np.float32(0.9718), np.float32(0.8563), np.float32(0.8055), np.float32(0.8883), np.float32(0.9684), np.float32(0.5263), np.float32(0.4845)] +2025-11-14 00:04:30.396534: Epoch time: 258.32 s +2025-11-14 00:04:30.397819: Yayy! New best EMA pseudo Dice: 0.8219000101089478 +2025-11-14 00:04:38.232231: +2025-11-14 00:04:38.233731: Epoch 951 +2025-11-14 00:04:38.235043: Current learning rate: 0.00066 +2025-11-14 00:08:56.869761: train_loss -0.7358 +2025-11-14 00:08:56.873971: val_loss -0.7428 +2025-11-14 00:08:56.875327: Pseudo dice [np.float32(0.9259), np.float32(0.7583), np.float32(0.7255), np.float32(0.684), np.float32(0.8822), np.float32(0.8294), np.float32(0.9047), np.float32(0.8763), np.float32(0.9813), np.float32(0.9818), np.float32(0.971), np.float32(0.8582), np.float32(0.7668), np.float32(0.8908), np.float32(0.9685), np.float32(0.4875), np.float32(0.4401)] +2025-11-14 00:08:56.876500: Epoch time: 258.64 s +2025-11-14 00:09:06.075703: +2025-11-14 00:09:06.077182: Epoch 952 +2025-11-14 00:09:06.078469: Current learning rate: 0.00065 +2025-11-14 00:13:24.562494: train_loss -0.74 +2025-11-14 00:13:24.566599: val_loss -0.7462 +2025-11-14 00:13:24.567799: Pseudo dice [np.float32(0.9311), np.float32(0.8), np.float32(0.7475), np.float32(0.6925), np.float32(0.8801), np.float32(0.8358), np.float32(0.9137), np.float32(0.8788), np.float32(0.9816), np.float32(0.9817), np.float32(0.9728), np.float32(0.8549), np.float32(0.7763), np.float32(0.8954), np.float32(0.9674), np.float32(0.4426), np.float32(0.3789)] +2025-11-14 00:13:24.569177: Epoch time: 258.49 s +2025-11-14 00:13:33.482005: +2025-11-14 00:13:33.483520: Epoch 953 +2025-11-14 00:13:33.484815: Current learning rate: 0.00064 +2025-11-14 00:17:51.821688: train_loss -0.7366 +2025-11-14 00:17:51.825732: val_loss -0.7349 +2025-11-14 00:17:51.826980: Pseudo dice [np.float32(0.9327), np.float32(0.7837), np.float32(0.7087), np.float32(0.7104), np.float32(0.8756), np.float32(0.8095), np.float32(0.9071), np.float32(0.8608), np.float32(0.9749), np.float32(0.9713), np.float32(0.9711), np.float32(0.8423), np.float32(0.7536), np.float32(0.8804), np.float32(0.9656), np.float32(0.4449), np.float32(0.42)] +2025-11-14 00:17:51.828455: Epoch time: 258.35 s +2025-11-14 00:17:53.728297: +2025-11-14 00:17:53.729687: Epoch 954 +2025-11-14 00:17:53.730944: Current learning rate: 0.00063 +2025-11-14 00:22:12.318197: train_loss -0.7393 +2025-11-14 00:22:12.322293: val_loss -0.7508 +2025-11-14 00:22:12.323748: Pseudo dice [np.float32(0.9297), np.float32(0.8028), np.float32(0.7411), np.float32(0.684), np.float32(0.8796), np.float32(0.8327), np.float32(0.9161), np.float32(0.8727), np.float32(0.9825), np.float32(0.981), np.float32(0.9709), np.float32(0.8513), np.float32(0.8047), np.float32(0.8907), np.float32(0.9684), np.float32(0.5039), np.float32(0.4098)] +2025-11-14 00:22:12.324946: Epoch time: 258.6 s +2025-11-14 00:27:46.841089: +2025-11-14 00:27:46.843095: Epoch 955 +2025-11-14 00:27:46.844291: Current learning rate: 0.00061 +2025-11-14 00:32:04.329796: train_loss -0.7405 +2025-11-14 00:32:04.333951: val_loss -0.7541 +2025-11-14 00:32:04.335125: Pseudo dice [np.float32(0.9228), np.float32(0.8155), np.float32(0.7556), np.float32(0.6934), np.float32(0.8835), np.float32(0.8384), np.float32(0.9122), np.float32(0.8722), np.float32(0.98), np.float32(0.9812), np.float32(0.9735), np.float32(0.8471), np.float32(0.764), np.float32(0.8952), np.float32(0.9705), np.float32(0.5405), np.float32(0.4878)] +2025-11-14 00:32:04.336309: Epoch time: 257.5 s +2025-11-14 00:32:04.337334: Yayy! New best EMA pseudo Dice: 0.8220000267028809 +2025-11-14 00:32:10.713895: +2025-11-14 00:32:10.715223: Epoch 956 +2025-11-14 00:32:10.716549: Current learning rate: 0.0006 +2025-11-14 00:36:29.236871: train_loss -0.7412 +2025-11-14 00:36:29.241197: val_loss -0.748 +2025-11-14 00:36:29.242611: Pseudo dice [np.float32(0.9137), np.float32(0.8082), np.float32(0.7006), np.float32(0.7035), np.float32(0.8802), np.float32(0.8272), np.float32(0.9153), np.float32(0.8733), np.float32(0.9838), np.float32(0.9832), np.float32(0.9724), np.float32(0.8613), np.float32(0.7637), np.float32(0.8891), np.float32(0.9691), np.float32(0.4701), np.float32(0.3992)] +2025-11-14 00:36:29.243792: Epoch time: 258.53 s +2025-11-14 00:36:30.983422: +2025-11-14 00:36:30.984861: Epoch 957 +2025-11-14 00:36:30.986256: Current learning rate: 0.00059 +2025-11-14 00:40:49.561577: train_loss -0.7437 +2025-11-14 00:40:49.565289: val_loss -0.7469 +2025-11-14 00:40:49.566481: Pseudo dice [np.float32(0.91), np.float32(0.7655), np.float32(0.7339), np.float32(0.7089), np.float32(0.8832), np.float32(0.8304), np.float32(0.9157), np.float32(0.8649), np.float32(0.9832), np.float32(0.983), np.float32(0.9724), np.float32(0.8516), np.float32(0.7864), np.float32(0.8927), np.float32(0.9686), np.float32(0.5405), np.float32(0.4675)] +2025-11-14 00:40:49.567676: Epoch time: 258.58 s +2025-11-14 00:40:49.568757: Yayy! New best EMA pseudo Dice: 0.8222000002861023 +2025-11-14 00:40:54.552406: +2025-11-14 00:40:54.553871: Epoch 958 +2025-11-14 00:40:54.555092: Current learning rate: 0.00058 +2025-11-14 00:45:12.922300: train_loss -0.7417 +2025-11-14 00:45:12.926333: val_loss -0.747 +2025-11-14 00:45:12.927528: Pseudo dice [np.float32(0.9195), np.float32(0.7999), np.float32(0.7388), np.float32(0.693), np.float32(0.8794), np.float32(0.8361), np.float32(0.913), np.float32(0.866), np.float32(0.981), np.float32(0.9808), np.float32(0.9714), np.float32(0.8503), np.float32(0.7831), np.float32(0.892), np.float32(0.9668), np.float32(0.4533), np.float32(0.4562)] +2025-11-14 00:45:12.928832: Epoch time: 258.37 s +2025-11-14 00:45:12.929961: Yayy! New best EMA pseudo Dice: 0.8222000002861023 +2025-11-14 00:45:17.868970: +2025-11-14 00:45:17.870445: Epoch 959 +2025-11-14 00:45:17.871656: Current learning rate: 0.00056 +2025-11-14 00:49:37.603418: train_loss -0.7366 +2025-11-14 00:49:37.607661: val_loss -0.7377 +2025-11-14 00:49:37.608974: Pseudo dice [np.float32(0.9191), np.float32(0.823), np.float32(0.7534), np.float32(0.6941), np.float32(0.8804), np.float32(0.8159), np.float32(0.9109), np.float32(0.8696), np.float32(0.981), np.float32(0.9808), np.float32(0.9723), np.float32(0.8502), np.float32(0.7554), np.float32(0.8909), np.float32(0.9668), np.float32(0.3813), np.float32(0.3654)] +2025-11-14 00:49:37.610244: Epoch time: 259.74 s +2025-11-14 00:49:41.342412: +2025-11-14 00:49:41.343837: Epoch 960 +2025-11-14 00:49:41.345318: Current learning rate: 0.00055 +2025-11-14 00:53:59.899521: train_loss -0.7366 +2025-11-14 00:53:59.903604: val_loss -0.7408 +2025-11-14 00:53:59.905144: Pseudo dice [np.float32(0.9282), np.float32(0.7992), np.float32(0.7426), np.float32(0.6834), np.float32(0.8856), np.float32(0.8137), np.float32(0.9232), np.float32(0.8732), np.float32(0.9821), np.float32(0.9809), np.float32(0.9719), np.float32(0.8463), np.float32(0.7639), np.float32(0.8863), np.float32(0.9674), np.float32(0.4527), np.float32(0.3684)] +2025-11-14 00:53:59.906324: Epoch time: 258.56 s +2025-11-14 00:54:01.644142: +2025-11-14 00:54:01.645515: Epoch 961 +2025-11-14 00:54:01.646775: Current learning rate: 0.00054 +2025-11-14 00:58:20.295292: train_loss -0.7422 +2025-11-14 00:58:20.299613: val_loss -0.7502 +2025-11-14 00:58:20.300913: Pseudo dice [np.float32(0.9245), np.float32(0.7997), np.float32(0.7571), np.float32(0.6587), np.float32(0.882), np.float32(0.8089), np.float32(0.9178), np.float32(0.8697), np.float32(0.9799), np.float32(0.9821), np.float32(0.9729), np.float32(0.8531), np.float32(0.7822), np.float32(0.8927), np.float32(0.97), np.float32(0.5192), np.float32(0.523)] +2025-11-14 00:58:20.302293: Epoch time: 258.66 s +2025-11-14 00:58:22.503277: +2025-11-14 00:58:22.504651: Epoch 962 +2025-11-14 00:58:22.506183: Current learning rate: 0.00053 +2025-11-14 01:02:41.332289: train_loss -0.7382 +2025-11-14 01:02:41.335929: val_loss -0.728 +2025-11-14 01:02:41.337188: Pseudo dice [np.float32(0.9177), np.float32(0.8118), np.float32(0.7298), np.float32(0.668), np.float32(0.8802), np.float32(0.809), np.float32(0.9185), np.float32(0.8688), np.float32(0.9778), np.float32(0.9795), np.float32(0.9719), np.float32(0.846), np.float32(0.7723), np.float32(0.8892), np.float32(0.963), np.float32(0.4549), np.float32(0.4091)] +2025-11-14 01:02:41.338299: Epoch time: 258.83 s +2025-11-14 01:02:44.833683: +2025-11-14 01:02:44.835078: Epoch 963 +2025-11-14 01:02:44.836348: Current learning rate: 0.00051 +2025-11-14 01:07:03.132249: train_loss -0.7357 +2025-11-14 01:07:03.136802: val_loss -0.7533 +2025-11-14 01:07:03.138384: Pseudo dice [np.float32(0.9138), np.float32(0.8105), np.float32(0.7561), np.float32(0.7131), np.float32(0.8786), np.float32(0.8346), np.float32(0.9064), np.float32(0.8734), np.float32(0.9809), np.float32(0.9808), np.float32(0.9719), np.float32(0.8552), np.float32(0.7893), np.float32(0.8849), np.float32(0.9667), np.float32(0.5082), np.float32(0.4331)] +2025-11-14 01:07:03.139686: Epoch time: 258.3 s +2025-11-14 01:07:05.694962: +2025-11-14 01:07:05.696571: Epoch 964 +2025-11-14 01:07:05.697911: Current learning rate: 0.0005 +2025-11-14 01:11:24.411089: train_loss -0.7364 +2025-11-14 01:11:24.415130: val_loss -0.741 +2025-11-14 01:11:24.416553: Pseudo dice [np.float32(0.9222), np.float32(0.8167), np.float32(0.749), np.float32(0.7161), np.float32(0.8796), np.float32(0.8266), np.float32(0.9123), np.float32(0.8739), np.float32(0.979), np.float32(0.9797), np.float32(0.9721), np.float32(0.8603), np.float32(0.784), np.float32(0.8915), np.float32(0.9659), np.float32(0.378), np.float32(0.2877)] +2025-11-14 01:11:24.417672: Epoch time: 258.72 s +2025-11-14 01:11:32.601691: +2025-11-14 01:11:32.603114: Epoch 965 +2025-11-14 01:11:32.604428: Current learning rate: 0.00049 +2025-11-14 01:15:50.745686: train_loss -0.7397 +2025-11-14 01:15:50.749980: val_loss -0.7468 +2025-11-14 01:15:50.751178: Pseudo dice [np.float32(0.929), np.float32(0.7949), np.float32(0.702), np.float32(0.6981), np.float32(0.8816), np.float32(0.8157), np.float32(0.9206), np.float32(0.875), np.float32(0.9726), np.float32(0.9754), np.float32(0.9729), np.float32(0.8614), np.float32(0.8006), np.float32(0.8861), np.float32(0.9646), np.float32(0.5103), np.float32(0.4345)] +2025-11-14 01:15:50.752428: Epoch time: 258.15 s +2025-11-14 01:15:52.461080: +2025-11-14 01:15:52.462469: Epoch 966 +2025-11-14 01:15:52.463695: Current learning rate: 0.00048 +2025-11-14 01:20:10.915651: train_loss -0.7388 +2025-11-14 01:20:10.919569: val_loss -0.7471 +2025-11-14 01:20:10.920769: Pseudo dice [np.float32(0.9219), np.float32(0.7825), np.float32(0.7382), np.float32(0.6701), np.float32(0.884), np.float32(0.841), np.float32(0.9159), np.float32(0.8633), np.float32(0.983), np.float32(0.9833), np.float32(0.9729), np.float32(0.851), np.float32(0.7799), np.float32(0.8943), np.float32(0.9696), np.float32(0.477), np.float32(0.4614)] +2025-11-14 01:20:10.921989: Epoch time: 258.46 s +2025-11-14 01:20:15.222800: +2025-11-14 01:20:15.224274: Epoch 967 +2025-11-14 01:20:15.225608: Current learning rate: 0.00046 +2025-11-14 01:24:33.593782: train_loss -0.7437 +2025-11-14 01:24:33.597520: val_loss -0.7386 +2025-11-14 01:24:33.598619: Pseudo dice [np.float32(0.9314), np.float32(0.7934), np.float32(0.7407), np.float32(0.6763), np.float32(0.8849), np.float32(0.8334), np.float32(0.9189), np.float32(0.8613), np.float32(0.9827), np.float32(0.9816), np.float32(0.972), np.float32(0.8483), np.float32(0.7823), np.float32(0.8968), np.float32(0.9684), np.float32(0.4861), np.float32(0.375)] +2025-11-14 01:24:33.599798: Epoch time: 258.38 s +2025-11-14 01:24:35.455169: +2025-11-14 01:24:35.456678: Epoch 968 +2025-11-14 01:24:35.458001: Current learning rate: 0.00045 +2025-11-14 01:28:54.057202: train_loss -0.7398 +2025-11-14 01:28:54.061281: val_loss -0.744 +2025-11-14 01:28:54.062604: Pseudo dice [np.float32(0.9202), np.float32(0.7943), np.float32(0.7126), np.float32(0.6976), np.float32(0.8795), np.float32(0.8311), np.float32(0.9093), np.float32(0.878), np.float32(0.9819), np.float32(0.9821), np.float32(0.9727), np.float32(0.8441), np.float32(0.7869), np.float32(0.8865), np.float32(0.9709), np.float32(0.4813), np.float32(0.407)] +2025-11-14 01:28:54.063862: Epoch time: 258.61 s +2025-11-14 01:28:56.111696: +2025-11-14 01:28:56.113132: Epoch 969 +2025-11-14 01:28:56.114424: Current learning rate: 0.00044 +2025-11-14 01:33:15.514480: train_loss -0.7427 +2025-11-14 01:33:15.518312: val_loss -0.7512 +2025-11-14 01:33:15.519557: Pseudo dice [np.float32(0.9169), np.float32(0.8043), np.float32(0.7521), np.float32(0.6901), np.float32(0.8886), np.float32(0.8299), np.float32(0.9197), np.float32(0.8739), np.float32(0.9828), np.float32(0.983), np.float32(0.9727), np.float32(0.8541), np.float32(0.7823), np.float32(0.8921), np.float32(0.9671), np.float32(0.4463), np.float32(0.4235)] +2025-11-14 01:33:15.520789: Epoch time: 259.41 s +2025-11-14 01:33:17.556732: +2025-11-14 01:33:17.558168: Epoch 970 +2025-11-14 01:33:17.559311: Current learning rate: 0.00043 +2025-11-14 01:37:36.121350: train_loss -0.7383 +2025-11-14 01:37:36.125551: val_loss -0.7494 +2025-11-14 01:37:36.126748: Pseudo dice [np.float32(0.9227), np.float32(0.776), np.float32(0.7425), np.float32(0.712), np.float32(0.8838), np.float32(0.8336), np.float32(0.9102), np.float32(0.8741), np.float32(0.9795), np.float32(0.9811), np.float32(0.9726), np.float32(0.8593), np.float32(0.7726), np.float32(0.8899), np.float32(0.9644), np.float32(0.5084), np.float32(0.4652)] +2025-11-14 01:37:36.127900: Epoch time: 258.57 s +2025-11-14 01:37:38.638075: +2025-11-14 01:37:38.639622: Epoch 971 +2025-11-14 01:37:38.640961: Current learning rate: 0.00041 +2025-11-14 01:41:57.322686: train_loss -0.7419 +2025-11-14 01:41:57.326425: val_loss -0.7411 +2025-11-14 01:41:57.327622: Pseudo dice [np.float32(0.9182), np.float32(0.7914), np.float32(0.7388), np.float32(0.6917), np.float32(0.8773), np.float32(0.8232), np.float32(0.9159), np.float32(0.871), np.float32(0.9803), np.float32(0.9829), np.float32(0.972), np.float32(0.8501), np.float32(0.7752), np.float32(0.8883), np.float32(0.9645), np.float32(0.4932), np.float32(0.4288)] +2025-11-14 01:41:57.329067: Epoch time: 258.69 s +2025-11-14 01:42:00.956583: +2025-11-14 01:42:00.957960: Epoch 972 +2025-11-14 01:42:00.959204: Current learning rate: 0.0004 +2025-11-14 01:46:19.396801: train_loss -0.7444 +2025-11-14 01:46:19.400365: val_loss -0.7393 +2025-11-14 01:46:19.401561: Pseudo dice [np.float32(0.9124), np.float32(0.8052), np.float32(0.7421), np.float32(0.6807), np.float32(0.8796), np.float32(0.8353), np.float32(0.9162), np.float32(0.8692), np.float32(0.9809), np.float32(0.9818), np.float32(0.9732), np.float32(0.8507), np.float32(0.783), np.float32(0.8965), np.float32(0.9671), np.float32(0.4243), np.float32(0.3195)] +2025-11-14 01:46:19.402827: Epoch time: 258.45 s +2025-11-14 01:46:21.392378: +2025-11-14 01:46:21.393820: Epoch 973 +2025-11-14 01:46:21.395185: Current learning rate: 0.00039 +2025-11-14 01:50:39.704972: train_loss -0.7401 +2025-11-14 01:50:39.709067: val_loss -0.7499 +2025-11-14 01:50:39.710514: Pseudo dice [np.float32(0.9277), np.float32(0.7985), np.float32(0.7427), np.float32(0.6953), np.float32(0.8845), np.float32(0.8299), np.float32(0.9176), np.float32(0.8679), np.float32(0.9821), np.float32(0.9779), np.float32(0.9709), np.float32(0.8514), np.float32(0.7918), np.float32(0.89), np.float32(0.9648), np.float32(0.4588), np.float32(0.3974)] +2025-11-14 01:50:39.711678: Epoch time: 258.32 s +2025-11-14 01:50:45.737742: +2025-11-14 01:50:45.739048: Epoch 974 +2025-11-14 01:50:45.740346: Current learning rate: 0.00037 +2025-11-14 01:55:04.057540: train_loss -0.7431 +2025-11-14 01:55:04.061659: val_loss -0.751 +2025-11-14 01:55:04.062982: Pseudo dice [np.float32(0.9212), np.float32(0.8083), np.float32(0.7499), np.float32(0.7103), np.float32(0.8815), np.float32(0.8476), np.float32(0.9149), np.float32(0.876), np.float32(0.9822), np.float32(0.9829), np.float32(0.9723), np.float32(0.8563), np.float32(0.801), np.float32(0.8811), np.float32(0.9693), np.float32(0.466), np.float32(0.508)] +2025-11-14 01:55:04.064405: Epoch time: 258.33 s +2025-11-14 01:55:05.822498: +2025-11-14 01:55:05.824016: Epoch 975 +2025-11-14 01:55:05.825309: Current learning rate: 0.00036 +2025-11-14 01:59:24.216811: train_loss -0.74 +2025-11-14 01:59:24.220639: val_loss -0.7561 +2025-11-14 01:59:24.221961: Pseudo dice [np.float32(0.9274), np.float32(0.8082), np.float32(0.7361), np.float32(0.7095), np.float32(0.8796), np.float32(0.85), np.float32(0.9143), np.float32(0.8679), np.float32(0.9815), np.float32(0.9822), np.float32(0.9726), np.float32(0.856), np.float32(0.7993), np.float32(0.8919), np.float32(0.9686), np.float32(0.4674), np.float32(0.4959)] +2025-11-14 01:59:24.223090: Epoch time: 258.4 s +2025-11-14 01:59:24.224210: Yayy! New best EMA pseudo Dice: 0.8224999904632568 +2025-11-14 01:59:29.124396: +2025-11-14 01:59:29.125805: Epoch 976 +2025-11-14 01:59:29.127116: Current learning rate: 0.00035 +2025-11-14 02:03:47.221887: train_loss -0.7416 +2025-11-14 02:03:47.225635: val_loss -0.7542 +2025-11-14 02:03:47.226923: Pseudo dice [np.float32(0.9262), np.float32(0.813), np.float32(0.768), np.float32(0.6792), np.float32(0.8853), np.float32(0.8372), np.float32(0.9173), np.float32(0.8721), np.float32(0.9785), np.float32(0.9784), np.float32(0.9717), np.float32(0.8435), np.float32(0.7869), np.float32(0.8945), np.float32(0.97), np.float32(0.5662), np.float32(0.5093)] +2025-11-14 02:03:47.228115: Epoch time: 258.1 s +2025-11-14 02:03:47.229202: Yayy! New best EMA pseudo Dice: 0.8237000107765198 +2025-11-14 02:03:52.223085: +2025-11-14 02:03:52.224396: Epoch 977 +2025-11-14 02:03:52.225658: Current learning rate: 0.00034 +2025-11-14 02:08:10.450451: train_loss -0.7395 +2025-11-14 02:08:10.454446: val_loss -0.7511 +2025-11-14 02:08:10.456092: Pseudo dice [np.float32(0.9132), np.float32(0.786), np.float32(0.7098), np.float32(0.698), np.float32(0.8794), np.float32(0.8349), np.float32(0.9027), np.float32(0.8662), np.float32(0.9823), np.float32(0.9832), np.float32(0.9724), np.float32(0.8551), np.float32(0.7726), np.float32(0.8931), np.float32(0.9697), np.float32(0.5281), np.float32(0.4993)] +2025-11-14 02:08:10.457547: Epoch time: 258.23 s +2025-11-14 02:08:10.458944: Yayy! New best EMA pseudo Dice: 0.8240000009536743 +2025-11-14 02:08:15.615783: +2025-11-14 02:08:15.617131: Epoch 978 +2025-11-14 02:08:15.618459: Current learning rate: 0.00032 +2025-11-14 02:12:35.007588: train_loss -0.7445 +2025-11-14 02:12:35.011183: val_loss -0.7585 +2025-11-14 02:12:35.012435: Pseudo dice [np.float32(0.9246), np.float32(0.8236), np.float32(0.758), np.float32(0.7055), np.float32(0.8841), np.float32(0.8294), np.float32(0.9132), np.float32(0.8689), np.float32(0.9821), np.float32(0.9834), np.float32(0.9723), np.float32(0.8505), np.float32(0.7902), np.float32(0.8886), np.float32(0.9678), np.float32(0.5775), np.float32(0.5182)] +2025-11-14 02:12:35.013729: Epoch time: 259.4 s +2025-11-14 02:12:35.015358: Yayy! New best EMA pseudo Dice: 0.8252999782562256 +2025-11-14 02:12:40.585562: +2025-11-14 02:12:40.586950: Epoch 979 +2025-11-14 02:12:40.588236: Current learning rate: 0.00031 +2025-11-14 02:16:58.689191: train_loss -0.7383 +2025-11-14 02:16:58.693120: val_loss -0.7375 +2025-11-14 02:16:58.694306: Pseudo dice [np.float32(0.9246), np.float32(0.7625), np.float32(0.7205), np.float32(0.6887), np.float32(0.887), np.float32(0.8151), np.float32(0.928), np.float32(0.8812), np.float32(0.9817), np.float32(0.9848), np.float32(0.973), np.float32(0.856), np.float32(0.7895), np.float32(0.8935), np.float32(0.9716), np.float32(0.4436), np.float32(0.4416)] +2025-11-14 02:16:58.695576: Epoch time: 258.11 s +2025-11-14 02:17:00.446131: +2025-11-14 02:17:00.447530: Epoch 980 +2025-11-14 02:17:00.448918: Current learning rate: 0.0003 +2025-11-14 02:21:18.686818: train_loss -0.7424 +2025-11-14 02:21:18.690903: val_loss -0.7531 +2025-11-14 02:21:18.692308: Pseudo dice [np.float32(0.923), np.float32(0.8097), np.float32(0.7149), np.float32(0.6802), np.float32(0.8772), np.float32(0.8182), np.float32(0.9222), np.float32(0.8679), np.float32(0.9822), np.float32(0.9829), np.float32(0.9722), np.float32(0.8523), np.float32(0.7674), np.float32(0.8889), np.float32(0.9689), np.float32(0.6387), np.float32(0.5596)] +2025-11-14 02:21:18.693639: Epoch time: 258.25 s +2025-11-14 02:21:18.694735: Yayy! New best EMA pseudo Dice: 0.8259999752044678 +2025-11-14 02:21:23.560454: +2025-11-14 02:21:23.562054: Epoch 981 +2025-11-14 02:21:23.563302: Current learning rate: 0.00028 +2025-11-14 02:25:41.719161: train_loss -0.7434 +2025-11-14 02:25:41.723042: val_loss -0.7412 +2025-11-14 02:25:41.724277: Pseudo dice [np.float32(0.9296), np.float32(0.7783), np.float32(0.7328), np.float32(0.6694), np.float32(0.8822), np.float32(0.8404), np.float32(0.9066), np.float32(0.869), np.float32(0.9824), np.float32(0.9841), np.float32(0.973), np.float32(0.8551), np.float32(0.783), np.float32(0.8914), np.float32(0.9696), np.float32(0.447), np.float32(0.4284)] +2025-11-14 02:25:41.725504: Epoch time: 258.16 s +2025-11-14 02:25:44.021222: +2025-11-14 02:25:44.022750: Epoch 982 +2025-11-14 02:25:44.024128: Current learning rate: 0.00027 +2025-11-14 02:30:02.126970: train_loss -0.7424 +2025-11-14 02:30:02.130754: val_loss -0.7567 +2025-11-14 02:30:02.132006: Pseudo dice [np.float32(0.9324), np.float32(0.8077), np.float32(0.7664), np.float32(0.6742), np.float32(0.8896), np.float32(0.8399), np.float32(0.9201), np.float32(0.8742), np.float32(0.9822), np.float32(0.9818), np.float32(0.9733), np.float32(0.8555), np.float32(0.7712), np.float32(0.9032), np.float32(0.9692), np.float32(0.5076), np.float32(0.485)] +2025-11-14 02:30:02.133633: Epoch time: 258.11 s +2025-11-14 02:30:03.819269: +2025-11-14 02:30:03.820776: Epoch 983 +2025-11-14 02:30:03.822067: Current learning rate: 0.00026 +2025-11-14 02:34:22.123008: train_loss -0.7425 +2025-11-14 02:34:22.126957: val_loss -0.751 +2025-11-14 02:34:22.128272: Pseudo dice [np.float32(0.9242), np.float32(0.7869), np.float32(0.7577), np.float32(0.6906), np.float32(0.8799), np.float32(0.8319), np.float32(0.9268), np.float32(0.8756), np.float32(0.9832), np.float32(0.9828), np.float32(0.9735), np.float32(0.8575), np.float32(0.7613), np.float32(0.8906), np.float32(0.9658), np.float32(0.5502), np.float32(0.4627)] +2025-11-14 02:34:22.129445: Epoch time: 258.31 s +2025-11-14 02:34:22.130810: Yayy! New best EMA pseudo Dice: 0.8263000249862671 +2025-11-14 02:34:27.009721: +2025-11-14 02:34:27.011302: Epoch 984 +2025-11-14 02:34:27.012656: Current learning rate: 0.00024 +2025-11-14 02:38:45.330394: train_loss -0.7396 +2025-11-14 02:38:45.334125: val_loss -0.7509 +2025-11-14 02:38:45.335489: Pseudo dice [np.float32(0.9121), np.float32(0.7775), np.float32(0.74), np.float32(0.6892), np.float32(0.8841), np.float32(0.8223), np.float32(0.9196), np.float32(0.8758), np.float32(0.9827), np.float32(0.9817), np.float32(0.9718), np.float32(0.857), np.float32(0.7663), np.float32(0.8896), np.float32(0.963), np.float32(0.5377), np.float32(0.5033)] +2025-11-14 02:38:45.336606: Epoch time: 258.33 s +2025-11-14 02:38:45.337645: Yayy! New best EMA pseudo Dice: 0.8263999819755554 +2025-11-14 02:39:02.414333: +2025-11-14 02:39:02.415787: Epoch 985 +2025-11-14 02:39:02.417099: Current learning rate: 0.00023 +2025-11-14 02:43:20.683693: train_loss -0.7404 +2025-11-14 02:43:20.687753: val_loss -0.7547 +2025-11-14 02:43:20.689200: Pseudo dice [np.float32(0.9305), np.float32(0.8075), np.float32(0.766), np.float32(0.6899), np.float32(0.8797), np.float32(0.8411), np.float32(0.9069), np.float32(0.8763), np.float32(0.9816), np.float32(0.9828), np.float32(0.972), np.float32(0.8568), np.float32(0.8098), np.float32(0.8842), np.float32(0.9683), np.float32(0.5045), np.float32(0.4854)] +2025-11-14 02:43:20.690461: Epoch time: 258.28 s +2025-11-14 02:43:20.691467: Yayy! New best EMA pseudo Dice: 0.8270000219345093 +2025-11-14 02:43:25.743249: +2025-11-14 02:43:25.744560: Epoch 986 +2025-11-14 02:43:25.745741: Current learning rate: 0.00021 +2025-11-14 02:47:45.426722: train_loss -0.7394 +2025-11-14 02:47:45.430629: val_loss -0.7492 +2025-11-14 02:47:45.431846: Pseudo dice [np.float32(0.9162), np.float32(0.8366), np.float32(0.7707), np.float32(0.701), np.float32(0.8859), np.float32(0.8312), np.float32(0.9198), np.float32(0.8699), np.float32(0.9828), np.float32(0.9838), np.float32(0.9724), np.float32(0.8535), np.float32(0.7707), np.float32(0.8938), np.float32(0.9691), np.float32(0.5102), np.float32(0.4842)] +2025-11-14 02:47:45.433030: Epoch time: 259.69 s +2025-11-14 02:47:45.434311: Yayy! New best EMA pseudo Dice: 0.8274999856948853 +2025-11-14 02:47:50.442876: +2025-11-14 02:47:50.444395: Epoch 987 +2025-11-14 02:47:50.445683: Current learning rate: 0.0002 +2025-11-14 02:52:08.840949: train_loss -0.7443 +2025-11-14 02:52:08.844911: val_loss -0.7505 +2025-11-14 02:52:08.846345: Pseudo dice [np.float32(0.926), np.float32(0.7696), np.float32(0.7257), np.float32(0.6944), np.float32(0.8861), np.float32(0.828), np.float32(0.9192), np.float32(0.859), np.float32(0.9808), np.float32(0.9812), np.float32(0.9729), np.float32(0.8527), np.float32(0.7657), np.float32(0.8898), np.float32(0.9689), np.float32(0.5559), np.float32(0.4774)] +2025-11-14 02:52:08.847598: Epoch time: 258.4 s +2025-11-14 02:52:14.308507: +2025-11-14 02:52:14.309864: Epoch 988 +2025-11-14 02:52:14.311095: Current learning rate: 0.00019 +2025-11-14 02:56:32.608872: train_loss -0.7443 +2025-11-14 02:56:32.612938: val_loss -0.7419 +2025-11-14 02:56:32.614470: Pseudo dice [np.float32(0.9187), np.float32(0.8205), np.float32(0.7465), np.float32(0.6969), np.float32(0.885), np.float32(0.8397), np.float32(0.9228), np.float32(0.8777), np.float32(0.9822), np.float32(0.983), np.float32(0.9722), np.float32(0.8476), np.float32(0.801), np.float32(0.8928), np.float32(0.9683), np.float32(0.4504), np.float32(0.4034)] +2025-11-14 02:56:32.615563: Epoch time: 258.31 s +2025-11-14 02:56:35.061589: +2025-11-14 02:56:35.063005: Epoch 989 +2025-11-14 02:56:35.064379: Current learning rate: 0.00017 +2025-11-14 03:00:53.217931: train_loss -0.7457 +2025-11-14 03:00:53.221956: val_loss -0.7472 +2025-11-14 03:00:53.223531: Pseudo dice [np.float32(0.9253), np.float32(0.7923), np.float32(0.7418), np.float32(0.6955), np.float32(0.885), np.float32(0.831), np.float32(0.9265), np.float32(0.8766), np.float32(0.9799), np.float32(0.9806), np.float32(0.9722), np.float32(0.8494), np.float32(0.7879), np.float32(0.8936), np.float32(0.9698), np.float32(0.4924), np.float32(0.4496)] +2025-11-14 03:00:53.224890: Epoch time: 258.16 s +2025-11-14 03:00:54.976743: +2025-11-14 03:00:54.978266: Epoch 990 +2025-11-14 03:00:54.979414: Current learning rate: 0.00016 +2025-11-14 03:05:13.464341: train_loss -0.7443 +2025-11-14 03:05:13.468730: val_loss -0.752 +2025-11-14 03:05:13.469955: Pseudo dice [np.float32(0.9173), np.float32(0.8215), np.float32(0.7546), np.float32(0.6557), np.float32(0.8847), np.float32(0.8331), np.float32(0.9286), np.float32(0.854), np.float32(0.9808), np.float32(0.9803), np.float32(0.9719), np.float32(0.859), np.float32(0.7794), np.float32(0.8905), np.float32(0.97), np.float32(0.496), np.float32(0.5347)] +2025-11-14 03:05:13.471295: Epoch time: 258.49 s +2025-11-14 03:05:15.235420: +2025-11-14 03:05:15.236911: Epoch 991 +2025-11-14 03:05:15.238209: Current learning rate: 0.00014 +2025-11-14 03:09:33.462650: train_loss -0.7433 +2025-11-14 03:09:33.466244: val_loss -0.7481 +2025-11-14 03:09:33.467582: Pseudo dice [np.float32(0.9286), np.float32(0.7937), np.float32(0.7397), np.float32(0.6875), np.float32(0.8849), np.float32(0.8209), np.float32(0.9285), np.float32(0.856), np.float32(0.9826), np.float32(0.9835), np.float32(0.9721), np.float32(0.8445), np.float32(0.7839), np.float32(0.8968), np.float32(0.9689), np.float32(0.4542), np.float32(0.4762)] +2025-11-14 03:09:33.469071: Epoch time: 258.23 s +2025-11-14 03:09:35.215868: +2025-11-14 03:09:35.217172: Epoch 992 +2025-11-14 03:09:35.218529: Current learning rate: 0.00013 +2025-11-14 03:13:53.829193: train_loss -0.7439 +2025-11-14 03:13:53.833249: val_loss -0.764 +2025-11-14 03:13:53.834489: Pseudo dice [np.float32(0.9307), np.float32(0.8036), np.float32(0.7482), np.float32(0.7049), np.float32(0.8878), np.float32(0.8445), np.float32(0.9107), np.float32(0.8682), np.float32(0.9812), np.float32(0.9826), np.float32(0.9722), np.float32(0.8591), np.float32(0.8129), np.float32(0.8973), np.float32(0.9664), np.float32(0.5162), np.float32(0.5058)] +2025-11-14 03:13:53.835536: Epoch time: 258.62 s +2025-11-14 03:13:53.836886: Yayy! New best EMA pseudo Dice: 0.8277999758720398 +2025-11-14 03:13:58.942616: +2025-11-14 03:13:58.944127: Epoch 993 +2025-11-14 03:13:58.945487: Current learning rate: 0.00011 +2025-11-14 03:18:17.315087: train_loss -0.7375 +2025-11-14 03:18:17.319186: val_loss -0.7443 +2025-11-14 03:18:17.320413: Pseudo dice [np.float32(0.922), np.float32(0.7917), np.float32(0.7191), np.float32(0.6931), np.float32(0.8886), np.float32(0.8302), np.float32(0.909), np.float32(0.88), np.float32(0.9822), np.float32(0.9816), np.float32(0.9727), np.float32(0.855), np.float32(0.7952), np.float32(0.8926), np.float32(0.9692), np.float32(0.4544), np.float32(0.4442)] +2025-11-14 03:18:17.321642: Epoch time: 258.38 s +2025-11-14 03:18:19.071095: +2025-11-14 03:18:19.072577: Epoch 994 +2025-11-14 03:18:19.073950: Current learning rate: 0.0001 +2025-11-14 03:22:37.504770: train_loss -0.7457 +2025-11-14 03:22:37.508780: val_loss -0.7529 +2025-11-14 03:22:37.510034: Pseudo dice [np.float32(0.9254), np.float32(0.7958), np.float32(0.7573), np.float32(0.6985), np.float32(0.8775), np.float32(0.8399), np.float32(0.9094), np.float32(0.8681), np.float32(0.9835), np.float32(0.9838), np.float32(0.9717), np.float32(0.8499), np.float32(0.7873), np.float32(0.8876), np.float32(0.9698), np.float32(0.5582), np.float32(0.5434)] +2025-11-14 03:22:37.511510: Epoch time: 258.44 s +2025-11-14 03:22:37.512663: Yayy! New best EMA pseudo Dice: 0.8281000256538391 +2025-11-14 03:22:43.150645: +2025-11-14 03:22:43.152112: Epoch 995 +2025-11-14 03:22:43.153482: Current learning rate: 8e-05 +2025-11-14 03:27:02.827545: train_loss -0.7454 +2025-11-14 03:27:02.831277: val_loss -0.7529 +2025-11-14 03:27:02.832433: Pseudo dice [np.float32(0.9286), np.float32(0.8392), np.float32(0.7484), np.float32(0.6979), np.float32(0.8816), np.float32(0.8379), np.float32(0.9166), np.float32(0.8718), np.float32(0.9825), np.float32(0.9836), np.float32(0.9722), np.float32(0.8615), np.float32(0.7576), np.float32(0.8937), np.float32(0.9678), np.float32(0.5451), np.float32(0.4568)] +2025-11-14 03:27:02.833659: Epoch time: 259.68 s +2025-11-14 03:27:02.834953: Yayy! New best EMA pseudo Dice: 0.828499972820282 +2025-11-14 03:27:08.314959: +2025-11-14 03:27:08.316364: Epoch 996 +2025-11-14 03:27:08.317626: Current learning rate: 7e-05 +2025-11-14 03:31:26.941918: train_loss -0.745 +2025-11-14 03:31:26.946131: val_loss -0.749 +2025-11-14 03:31:26.947283: Pseudo dice [np.float32(0.932), np.float32(0.8545), np.float32(0.764), np.float32(0.7207), np.float32(0.8862), np.float32(0.8356), np.float32(0.9251), np.float32(0.8669), np.float32(0.9822), np.float32(0.9819), np.float32(0.9724), np.float32(0.8577), np.float32(0.7816), np.float32(0.8968), np.float32(0.9676), np.float32(0.4993), np.float32(0.4583)] +2025-11-14 03:31:26.948495: Epoch time: 258.63 s +2025-11-14 03:31:26.949453: Yayy! New best EMA pseudo Dice: 0.8289999961853027 +2025-11-14 03:31:31.857066: +2025-11-14 03:31:31.858409: Epoch 997 +2025-11-14 03:31:31.859685: Current learning rate: 5e-05 +2025-11-14 03:35:50.107862: train_loss -0.7497 +2025-11-14 03:35:50.112075: val_loss -0.7543 +2025-11-14 03:35:50.113837: Pseudo dice [np.float32(0.9262), np.float32(0.8238), np.float32(0.7427), np.float32(0.6819), np.float32(0.8805), np.float32(0.8268), np.float32(0.9136), np.float32(0.8656), np.float32(0.9837), np.float32(0.9813), np.float32(0.9733), np.float32(0.8478), np.float32(0.8021), np.float32(0.8897), np.float32(0.9701), np.float32(0.5725), np.float32(0.5101)] +2025-11-14 03:35:50.115216: Epoch time: 258.26 s +2025-11-14 03:35:50.116375: Yayy! New best EMA pseudo Dice: 0.8295999765396118 +2025-11-14 03:35:55.144578: +2025-11-14 03:35:55.146049: Epoch 998 +2025-11-14 03:35:55.147279: Current learning rate: 4e-05 +2025-11-14 03:40:13.330839: train_loss -0.7476 +2025-11-14 03:40:13.334999: val_loss -0.7412 +2025-11-14 03:40:13.336460: Pseudo dice [np.float32(0.928), np.float32(0.8102), np.float32(0.7355), np.float32(0.6756), np.float32(0.8871), np.float32(0.8276), np.float32(0.9132), np.float32(0.8738), np.float32(0.9813), np.float32(0.9824), np.float32(0.9725), np.float32(0.852), np.float32(0.7714), np.float32(0.8923), np.float32(0.9692), np.float32(0.5078), np.float32(0.43)] +2025-11-14 03:40:13.337638: Epoch time: 258.19 s +2025-11-14 03:40:15.107128: +2025-11-14 03:40:15.108484: Epoch 999 +2025-11-14 03:40:15.109746: Current learning rate: 2e-05 +2025-11-14 03:44:33.460983: train_loss -0.7447 +2025-11-14 03:44:33.464973: val_loss -0.7462 +2025-11-14 03:44:33.466115: Pseudo dice [np.float32(0.933), np.float32(0.7933), np.float32(0.7561), np.float32(0.6874), np.float32(0.8814), np.float32(0.8391), np.float32(0.9134), np.float32(0.8753), np.float32(0.9806), np.float32(0.9831), np.float32(0.9727), np.float32(0.8481), np.float32(0.7664), np.float32(0.8942), np.float32(0.969), np.float32(0.5137), np.float32(0.4514)] +2025-11-14 03:44:33.467213: Epoch time: 258.36 s +2025-11-14 03:44:44.217931: Training done. +2025-11-14 03:44:46.269599: predicting BDMAP_A0000001 +2025-11-14 03:44:48.215034: BDMAP_A0000001, shape torch.Size([1, 512, 541, 554]), rank 0 +2025-11-14 03:49:24.073254: predicting BDMAP_A0000002 +2025-11-14 03:49:24.128318: BDMAP_A0000002, shape torch.Size([1, 512, 523, 523]), rank 0 +2025-11-14 03:52:11.765887: predicting BDMAP_A0000004 +2025-11-14 03:52:11.819120: BDMAP_A0000004, shape torch.Size([1, 512, 547, 567]), rank 0 +2025-11-14 03:54:38.476642: predicting BDMAP_A0000005 +2025-11-14 03:54:38.527834: BDMAP_A0000005, shape torch.Size([1, 512, 437, 453]), rank 0 +2025-11-14 03:56:35.027301: predicting BDMAP_A0000006 +2025-11-14 03:56:35.070811: BDMAP_A0000006, shape torch.Size([1, 512, 582, 686]), rank 0 +2025-11-14 04:02:13.194616: predicting BDMAP_A0000007 +2025-11-14 04:02:13.261340: BDMAP_A0000007, shape torch.Size([1, 512, 595, 630]), rank 0 +2025-11-14 04:03:56.491638: predicting BDMAP_A0000008 +2025-11-14 04:03:56.547266: BDMAP_A0000008, shape torch.Size([1, 512, 472, 499]), rank 0 +2025-11-14 04:06:26.103923: predicting BDMAP_A0000010 +2025-11-14 04:06:26.155771: BDMAP_A0000010, shape torch.Size([1, 512, 879, 494]), rank 0 +2025-11-14 04:09:33.925412: predicting BDMAP_A0000011 +2025-11-14 04:09:33.997846: BDMAP_A0000011, shape torch.Size([1, 512, 522, 501]), rank 0 +2025-11-14 04:11:17.008284: predicting BDMAP_A0000012 +2025-11-14 04:11:17.056406: BDMAP_A0000012, shape torch.Size([1, 512, 606, 540]), rank 0 +2025-11-14 04:13:01.568040: predicting BDMAP_A0000013 +2025-11-14 04:13:01.625204: BDMAP_A0000013, shape torch.Size([1, 512, 620, 537]), rank 0 +2025-11-14 04:15:16.681623: predicting BDMAP_A0000019 +2025-11-14 04:15:16.726626: BDMAP_A0000019, shape torch.Size([1, 512, 549, 433]), rank 0 +2025-11-14 04:17:02.335754: predicting BDMAP_A0000021 +2025-11-14 04:17:02.395010: BDMAP_A0000021, shape torch.Size([1, 512, 817, 495]), rank 0 +2025-11-14 04:20:46.743107: predicting BDMAP_A0000022 +2025-11-14 04:20:46.806018: BDMAP_A0000022, shape torch.Size([1, 512, 504, 523]), rank 0 +2025-11-14 04:22:33.835139: predicting BDMAP_A0000023 +2025-11-14 04:22:33.892816: BDMAP_A0000023, shape torch.Size([1, 512, 470, 428]), rank 0 +2025-11-14 04:24:17.819688: predicting BDMAP_A0000024 +2025-11-14 04:24:17.862019: BDMAP_A0000024, shape torch.Size([1, 512, 565, 523]), rank 0 +2025-11-14 04:26:26.792436: predicting BDMAP_A0000026 +2025-11-14 04:26:26.840983: BDMAP_A0000026, shape torch.Size([1, 512, 490, 475]), rank 0 +2025-11-14 04:28:09.800944: predicting BDMAP_A0000027 +2025-11-14 04:28:09.845557: BDMAP_A0000027, shape torch.Size([1, 512, 772, 571]), rank 0 +2025-11-14 04:31:16.645390: predicting BDMAP_A0000030 +2025-11-14 04:31:16.715608: BDMAP_A0000030, shape torch.Size([1, 512, 579, 468]), rank 0 +2025-11-14 04:32:59.957658: predicting BDMAP_A0000031 +2025-11-14 04:33:00.024091: BDMAP_A0000031, shape torch.Size([1, 512, 561, 535]), rank 0 +2025-11-14 04:34:43.504968: predicting BDMAP_A0000033 +2025-11-14 04:34:43.577441: BDMAP_A0000033, shape torch.Size([1, 512, 485, 570]), rank 0 +2025-11-14 04:36:50.345402: predicting BDMAP_A0000034 +2025-11-14 04:36:50.382306: BDMAP_A0000034, shape torch.Size([1, 512, 371, 594]), rank 0 +2025-11-14 04:38:34.648218: predicting BDMAP_A0000035 +2025-11-14 04:38:34.698630: BDMAP_A0000035, shape torch.Size([1, 512, 697, 630]), rank 0 +2025-11-14 04:41:40.013390: predicting BDMAP_A0000036 +2025-11-14 04:41:40.065975: BDMAP_A0000036, shape torch.Size([1, 512, 409, 456]), rank 0 +2025-11-14 04:43:27.897221: predicting BDMAP_A0000037 +2025-11-14 04:43:27.959161: BDMAP_A0000037, shape torch.Size([1, 512, 553, 547]), rank 0 +2025-11-14 04:45:14.919137: predicting BDMAP_A0000038 +2025-11-14 04:45:14.979809: BDMAP_A0000038, shape torch.Size([1, 512, 557, 703]), rank 0 +2025-11-14 04:48:18.047287: predicting BDMAP_A0000040 +2025-11-14 04:48:18.119069: BDMAP_A0000040, shape torch.Size([1, 512, 589, 499]), rank 0 +2025-11-14 04:50:01.951387: predicting BDMAP_A0000042 +2025-11-14 04:50:02.008940: BDMAP_A0000042, shape torch.Size([1, 512, 416, 542]), rank 0 +2025-11-14 04:51:45.360137: predicting BDMAP_A0000043 +2025-11-14 04:51:45.433127: BDMAP_A0000043, shape torch.Size([1, 512, 481, 450]), rank 0 +2025-11-14 04:53:29.347140: predicting BDMAP_A0000044 +2025-11-14 04:53:29.406444: BDMAP_A0000044, shape torch.Size([1, 512, 498, 591]), rank 0 +2025-11-14 04:55:15.359571: predicting BDMAP_A0000045 +2025-11-14 04:55:15.421654: BDMAP_A0000045, shape torch.Size([1, 512, 453, 504]), rank 0 +2025-11-14 04:56:58.506001: predicting BDMAP_A0000046 +2025-11-14 04:56:58.564143: BDMAP_A0000046, shape torch.Size([1, 512, 436, 509]), rank 0 +2025-11-14 04:58:41.682468: predicting BDMAP_A0000047 +2025-11-14 04:58:41.757051: BDMAP_A0000047, shape torch.Size([1, 512, 581, 571]), rank 0 +2025-11-14 05:00:28.509207: predicting BDMAP_A0000048 +2025-11-14 05:00:28.560926: BDMAP_A0000048, shape torch.Size([1, 512, 485, 440]), rank 0 +2025-11-14 05:02:12.174956: predicting BDMAP_A0000049 +2025-11-14 05:02:12.241209: BDMAP_A0000049, shape torch.Size([1, 512, 545, 585]), rank 0 +2025-11-14 05:03:55.203275: predicting BDMAP_A0000050 +2025-11-14 05:03:55.258442: BDMAP_A0000050, shape torch.Size([1, 512, 553, 563]), rank 0 +2025-11-14 05:05:39.943806: predicting BDMAP_A0000051 +2025-11-14 05:05:39.991320: BDMAP_A0000051, shape torch.Size([1, 512, 621, 667]), rank 0 +2025-11-14 05:08:44.301304: predicting BDMAP_A0000053 +2025-11-14 05:08:44.350377: BDMAP_A0000053, shape torch.Size([1, 512, 470, 487]), rank 0 +2025-11-14 05:10:29.738953: predicting BDMAP_A0000054 +2025-11-14 05:10:29.786147: BDMAP_A0000054, shape torch.Size([1, 512, 855, 477]), rank 0 +2025-11-14 05:13:41.074782: predicting BDMAP_A0000058 +2025-11-14 05:13:41.138412: BDMAP_A0000058, shape torch.Size([1, 512, 423, 408]), rank 0 +2025-11-14 05:15:23.300967: predicting BDMAP_A0000060 +2025-11-14 05:15:23.341394: BDMAP_A0000060, shape torch.Size([1, 512, 443, 467]), rank 0 +2025-11-14 05:17:10.393347: predicting BDMAP_A0000061 +2025-11-14 05:17:10.450704: BDMAP_A0000061, shape torch.Size([1, 512, 542, 620]), rank 0 +2025-11-14 05:18:56.357009: predicting BDMAP_A0000064 +2025-11-14 05:18:56.434143: BDMAP_A0000064, shape torch.Size([1, 512, 602, 459]), rank 0 +2025-11-14 05:20:42.573069: predicting BDMAP_A0000065 +2025-11-14 05:20:42.648056: BDMAP_A0000065, shape torch.Size([1, 512, 453, 485]), rank 0 +2025-11-14 05:22:28.580891: predicting BDMAP_A0000067 +2025-11-14 05:22:28.652601: BDMAP_A0000067, shape torch.Size([1, 512, 453, 473]), rank 0 +2025-11-14 05:24:15.595687: predicting BDMAP_A0000068 +2025-11-14 05:24:15.637871: BDMAP_A0000068, shape torch.Size([1, 512, 491, 513]), rank 0 +2025-11-14 05:26:04.158639: predicting BDMAP_A0000069 +2025-11-14 05:26:04.206440: BDMAP_A0000069, shape torch.Size([1, 512, 581, 518]), rank 0 +2025-11-14 05:27:48.397259: predicting BDMAP_A0000070 +2025-11-14 05:27:48.452689: BDMAP_A0000070, shape torch.Size([1, 512, 553, 556]), rank 0 +2025-11-14 05:29:34.706501: predicting BDMAP_A0000071 +2025-11-14 05:29:34.778676: BDMAP_A0000071, shape torch.Size([1, 512, 535, 422]), rank 0 +2025-11-14 05:31:18.322602: predicting BDMAP_A0000072 +2025-11-14 05:31:18.387600: BDMAP_A0000072, shape torch.Size([1, 512, 885, 606]), rank 0 +2025-11-14 05:34:32.831589: predicting BDMAP_A0000077 +2025-11-14 05:34:32.907027: BDMAP_A0000077, shape torch.Size([1, 512, 581, 556]), rank 0 +2025-11-14 05:36:20.851397: predicting BDMAP_A0000079 +2025-11-14 05:36:20.919943: BDMAP_A0000079, shape torch.Size([1, 512, 581, 526]), rank 0 +2025-11-14 05:38:06.347872: predicting BDMAP_A0000080 +2025-11-14 05:38:06.412766: BDMAP_A0000080, shape torch.Size([1, 512, 521, 440]), rank 0 +2025-11-14 05:40:19.870049: predicting BDMAP_A0000082 +2025-11-14 05:40:19.989622: BDMAP_A0000082, shape torch.Size([1, 512, 853, 612]), rank 0 +2025-11-14 05:43:38.409067: predicting BDMAP_A0000083 +2025-11-14 05:43:38.487944: BDMAP_A0000083, shape torch.Size([1, 512, 536, 512]), rank 0 +2025-11-14 05:45:21.896114: predicting BDMAP_A0000084 +2025-11-14 05:45:21.961328: BDMAP_A0000084, shape torch.Size([1, 512, 557, 556]), rank 0 +2025-11-14 05:47:05.302206: predicting BDMAP_A0000085 +2025-11-14 05:47:05.381814: BDMAP_A0000085, shape torch.Size([1, 512, 882, 588]), rank 0 +2025-11-14 05:50:18.469864: predicting BDMAP_A0000090 +2025-11-14 05:50:18.547911: BDMAP_A0000090, shape torch.Size([1, 512, 462, 477]), rank 0 +2025-11-14 05:52:03.317157: predicting BDMAP_A0000091 +2025-11-14 05:52:03.385840: BDMAP_A0000091, shape torch.Size([1, 512, 601, 484]), rank 0 +2025-11-14 05:53:46.268920: predicting BDMAP_A0000094 +2025-11-14 05:53:46.322646: BDMAP_A0000094, shape torch.Size([1, 512, 431, 450]), rank 0 +2025-11-14 05:55:46.723754: predicting BDMAP_A0000095 +2025-11-14 05:55:46.796775: BDMAP_A0000095, shape torch.Size([1, 512, 585, 696]), rank 0 +2025-11-14 05:58:54.532681: predicting BDMAP_A0000096 +2025-11-14 05:58:54.622221: BDMAP_A0000096, shape torch.Size([1, 512, 525, 456]), rank 0 +2025-11-14 06:00:38.744904: predicting BDMAP_A0000097 +2025-11-14 06:00:38.802998: BDMAP_A0000097, shape torch.Size([1, 512, 542, 623]), rank 0 +2025-11-14 06:02:25.580200: predicting BDMAP_A0000098 +2025-11-14 06:02:25.637442: BDMAP_A0000098, shape torch.Size([1, 512, 549, 523]), rank 0 +2025-11-14 06:04:12.127056: predicting BDMAP_A0000101 +2025-11-14 06:04:12.180755: BDMAP_A0000101, shape torch.Size([1, 512, 493, 453]), rank 0 +2025-11-14 06:05:55.975566: predicting BDMAP_A0000102 +2025-11-14 06:05:56.035569: BDMAP_A0000102, shape torch.Size([1, 512, 598, 582]), rank 0 +2025-11-14 06:07:39.807039: predicting BDMAP_A0000107 +2025-11-14 06:07:39.878098: BDMAP_A0000107, shape torch.Size([1, 512, 505, 422]), rank 0 +2025-11-14 06:09:24.032654: predicting BDMAP_A0000108 +2025-11-14 06:09:24.093136: BDMAP_A0000108, shape torch.Size([1, 512, 437, 498]), rank 0 +2025-11-14 06:11:06.097584: predicting BDMAP_A0000109 +2025-11-14 06:11:06.162687: BDMAP_A0000109, shape torch.Size([1, 512, 630, 580]), rank 0 +2025-11-14 06:12:54.040949: predicting BDMAP_A0000110 +2025-11-14 06:12:54.116930: BDMAP_A0000110, shape torch.Size([1, 512, 450, 421]), rank 0 +2025-11-14 06:14:36.927250: predicting BDMAP_A0000112 +2025-11-14 06:14:36.985614: BDMAP_A0000112, shape torch.Size([1, 512, 524, 563]), rank 0 +2025-11-14 06:16:22.008117: predicting BDMAP_A0000113 +2025-11-14 06:16:22.077814: BDMAP_A0000113, shape torch.Size([1, 512, 497, 574]), rank 0 +2025-11-14 06:18:08.821560: predicting BDMAP_A0000114 +2025-11-14 06:18:08.880791: BDMAP_A0000114, shape torch.Size([1, 512, 464, 460]), rank 0 +2025-11-14 06:19:52.761954: predicting BDMAP_A0000116 +2025-11-14 06:19:52.821477: BDMAP_A0000116, shape torch.Size([1, 512, 577, 504]), rank 0 +2025-11-14 06:21:39.612874: predicting BDMAP_A0000117 +2025-11-14 06:21:39.679373: BDMAP_A0000117, shape torch.Size([1, 512, 505, 492]), rank 0 +2025-11-14 06:23:23.611718: predicting BDMAP_A0000118 +2025-11-14 06:23:23.686430: BDMAP_A0000118, shape torch.Size([1, 512, 462, 588]), rank 0 +2025-11-14 06:25:06.306243: predicting BDMAP_A0000119 +2025-11-14 06:25:06.377665: BDMAP_A0000119, shape torch.Size([1, 512, 570, 644]), rank 0 +2025-11-14 06:28:09.425520: predicting BDMAP_A0000120 +2025-11-14 06:28:09.489055: BDMAP_A0000120, shape torch.Size([1, 512, 586, 491]), rank 0 +2025-11-14 06:29:52.064706: predicting BDMAP_A0000122 +2025-11-14 06:29:52.142483: BDMAP_A0000122, shape torch.Size([1, 512, 557, 526]), rank 0 +2025-11-14 06:31:37.870501: predicting BDMAP_A0000123 +2025-11-14 06:31:37.928729: BDMAP_A0000123, shape torch.Size([1, 512, 525, 617]), rank 0 +2025-11-14 06:33:25.100455: predicting BDMAP_A0000125 +2025-11-14 06:33:25.166636: BDMAP_A0000125, shape torch.Size([1, 512, 485, 474]), rank 0 +2025-11-14 06:35:09.512743: predicting BDMAP_A0000126 +2025-11-14 06:35:09.567556: BDMAP_A0000126, shape torch.Size([1, 512, 565, 529]), rank 0 +2025-11-14 06:36:53.638099: predicting BDMAP_A0000127 +2025-11-14 06:36:53.702230: BDMAP_A0000127, shape torch.Size([1, 512, 429, 450]), rank 0 +2025-11-14 06:38:38.679862: predicting BDMAP_A0000128 +2025-11-14 06:38:38.735342: BDMAP_A0000128, shape torch.Size([1, 512, 553, 495]), rank 0 +2025-11-14 06:40:21.614185: predicting BDMAP_A0000129 +2025-11-14 06:40:21.668789: BDMAP_A0000129, shape torch.Size([1, 512, 450, 492]), rank 0 +2025-11-14 06:42:06.959006: predicting BDMAP_A0000130 +2025-11-14 06:42:07.010227: BDMAP_A0000130, shape torch.Size([1, 512, 561, 661]), rank 0 +2025-11-14 06:45:07.766452: predicting BDMAP_A0000132 +2025-11-14 06:45:07.853924: BDMAP_A0000132, shape torch.Size([1, 512, 472, 543]), rank 0 +2025-11-14 06:46:49.890370: predicting BDMAP_A0000133 +2025-11-14 06:46:49.967988: BDMAP_A0000133, shape torch.Size([1, 512, 805, 551]), rank 0 +2025-11-14 06:49:59.372405: predicting BDMAP_A0000134 +2025-11-14 06:49:59.446263: BDMAP_A0000134, shape torch.Size([1, 512, 525, 440]), rank 0 +2025-11-14 06:51:42.656289: predicting BDMAP_A0000135 +2025-11-14 06:51:42.713471: BDMAP_A0000135, shape torch.Size([1, 512, 572, 575]), rank 0 +2025-11-14 06:53:25.944167: predicting BDMAP_A0000136 +2025-11-14 06:53:26.004362: BDMAP_A0000136, shape torch.Size([1, 512, 959, 588]), rank 0 +2025-11-14 06:57:00.377385: predicting BDMAP_A0000137 +2025-11-14 06:57:00.453878: BDMAP_A0000137, shape torch.Size([1, 512, 559, 540]), rank 0 +2025-11-14 06:58:45.895030: predicting BDMAP_A0000138 +2025-11-14 06:58:45.965126: BDMAP_A0000138, shape torch.Size([1, 512, 481, 543]), rank 0 +2025-11-14 07:00:32.104173: predicting BDMAP_A0000139 +2025-11-14 07:00:32.176850: BDMAP_A0000139, shape torch.Size([1, 512, 552, 658]), rank 0 +2025-11-14 07:04:03.945436: predicting BDMAP_A0000143 +2025-11-14 07:04:04.002186: BDMAP_A0000143, shape torch.Size([1, 512, 510, 494]), rank 0 +2025-11-14 07:05:46.961662: predicting BDMAP_A0000147 +2025-11-14 07:05:47.029876: BDMAP_A0000147, shape torch.Size([1, 512, 449, 518]), rank 0 +2025-11-14 07:07:29.466358: predicting BDMAP_A0000148 +2025-11-14 07:07:29.533267: BDMAP_A0000148, shape torch.Size([1, 512, 663, 520]), rank 0 +2025-11-14 07:10:30.733748: predicting BDMAP_A0000149 +2025-11-14 07:10:30.787905: BDMAP_A0000149, shape torch.Size([1, 512, 609, 598]), rank 0 +2025-11-14 07:12:14.535062: predicting BDMAP_A0000152 +2025-11-14 07:12:14.625946: BDMAP_A0000152, shape torch.Size([1, 512, 432, 542]), rank 0 +2025-11-14 07:13:57.354490: predicting BDMAP_A0000153 +2025-11-14 07:13:57.409047: BDMAP_A0000153, shape torch.Size([1, 512, 534, 572]), rank 0 +2025-11-14 07:15:40.783317: predicting BDMAP_A0000154 +2025-11-14 07:15:40.865461: BDMAP_A0000154, shape torch.Size([1, 512, 523, 482]), rank 0 +2025-11-14 07:17:23.137148: predicting BDMAP_A0000155 +2025-11-14 07:17:23.200296: BDMAP_A0000155, shape torch.Size([1, 512, 521, 473]), rank 0 +2025-11-14 07:19:05.623260: predicting BDMAP_A0000157 +2025-11-14 07:19:05.686215: BDMAP_A0000157, shape torch.Size([1, 512, 461, 429]), rank 0 +2025-11-14 07:20:49.310134: predicting BDMAP_A0000158 +2025-11-14 07:20:49.362914: BDMAP_A0000158, shape torch.Size([1, 512, 453, 467]), rank 0 +2025-11-14 07:22:34.328133: predicting BDMAP_A0000160 +2025-11-14 07:22:34.399787: BDMAP_A0000160, shape torch.Size([1, 512, 431, 442]), rank 0 +2025-11-14 07:24:16.760723: predicting BDMAP_A0000162 +2025-11-14 07:24:16.823155: BDMAP_A0000162, shape torch.Size([1, 512, 521, 444]), rank 0 +2025-11-14 07:25:59.393885: predicting BDMAP_A0000163 +2025-11-14 07:25:59.464262: BDMAP_A0000163, shape torch.Size([1, 512, 521, 482]), rank 0 +2025-11-14 07:27:42.183235: predicting BDMAP_A0000164 +2025-11-14 07:27:42.237510: BDMAP_A0000164, shape torch.Size([1, 512, 498, 592]), rank 0 +2025-11-14 07:29:28.018055: predicting BDMAP_A0000167 +2025-11-14 07:29:28.105602: BDMAP_A0000167, shape torch.Size([1, 512, 490, 478]), rank 0 +2025-11-14 07:31:12.863716: predicting BDMAP_A0000168 +2025-11-14 07:31:12.935719: BDMAP_A0000168, shape torch.Size([1, 512, 461, 371]), rank 0 +2025-11-14 07:32:55.364497: predicting BDMAP_A0000169 +2025-11-14 07:32:55.429151: BDMAP_A0000169, shape torch.Size([1, 512, 639, 567]), rank 0 +2025-11-14 07:34:39.978973: predicting BDMAP_A0000170 +2025-11-14 07:34:40.040717: BDMAP_A0000170, shape torch.Size([1, 512, 514, 580]), rank 0 +2025-11-14 07:36:23.166945: predicting BDMAP_A0000171 +2025-11-14 07:36:23.239227: BDMAP_A0000171, shape torch.Size([1, 512, 547, 481]), rank 0 +2025-11-14 07:38:06.480883: predicting BDMAP_A0000173 +2025-11-14 07:38:06.558348: BDMAP_A0000173, shape torch.Size([1, 512, 883, 498]), rank 0 +2025-11-14 07:41:17.793762: predicting BDMAP_A0000174 +2025-11-14 07:41:17.867209: BDMAP_A0000174, shape torch.Size([1, 512, 471, 529]), rank 0 +2025-11-14 07:43:01.151719: predicting BDMAP_A0000175 +2025-11-14 07:43:01.223721: BDMAP_A0000175, shape torch.Size([1, 512, 491, 540]), rank 0 +2025-11-14 07:44:45.512976: predicting BDMAP_A0000176 +2025-11-14 07:44:45.581527: BDMAP_A0000176, shape torch.Size([1, 512, 429, 450]), rank 0 +2025-11-14 07:46:29.982466: predicting BDMAP_A0000178 +2025-11-14 07:46:30.039146: BDMAP_A0000178, shape torch.Size([1, 512, 1026, 703]), rank 0 +2025-11-14 07:51:23.664976: predicting BDMAP_A0000180 +2025-11-14 07:51:23.781208: BDMAP_A0000180, shape torch.Size([1, 512, 449, 489]), rank 0 +2025-11-14 07:53:07.904312: predicting BDMAP_A0000184 +2025-11-14 07:53:07.967500: BDMAP_A0000184, shape torch.Size([1, 512, 553, 487]), rank 0 +2025-11-14 07:54:53.483609: predicting BDMAP_A0000185 +2025-11-14 07:54:53.567652: BDMAP_A0000185, shape torch.Size([1, 512, 542, 447]), rank 0 +2025-11-14 07:56:53.988256: predicting BDMAP_A0000186 +2025-11-14 07:56:54.050487: BDMAP_A0000186, shape torch.Size([1, 512, 481, 394]), rank 0 +2025-11-14 07:58:50.792586: predicting BDMAP_A0000188 +2025-11-14 07:58:50.860635: BDMAP_A0000188, shape torch.Size([1, 512, 705, 487]), rank 0 +2025-11-14 08:01:55.714646: predicting BDMAP_A0000189 +2025-11-14 08:01:55.791994: BDMAP_A0000189, shape torch.Size([1, 512, 585, 560]), rank 0 +2025-11-14 08:03:39.964491: predicting BDMAP_A0000191 +2025-11-14 08:03:40.031297: BDMAP_A0000191, shape torch.Size([1, 512, 605, 696]), rank 0 +2025-11-14 08:06:41.666323: predicting BDMAP_A0000192 +2025-11-14 08:06:41.755852: BDMAP_A0000192, shape torch.Size([1, 512, 523, 492]), rank 0 +2025-11-14 08:08:24.639335: predicting BDMAP_A0000193 +2025-11-14 08:08:24.704841: BDMAP_A0000193, shape torch.Size([1, 512, 425, 505]), rank 0 +2025-11-14 08:10:06.680368: predicting BDMAP_A0000195 +2025-11-14 08:10:06.740251: BDMAP_A0000195, shape torch.Size([1, 512, 410, 495]), rank 0 +2025-11-14 08:11:52.360443: predicting BDMAP_A0000196 +2025-11-14 08:11:52.418149: BDMAP_A0000196, shape torch.Size([1, 512, 901, 509]), rank 0 +2025-11-14 08:15:03.415648: predicting BDMAP_A0000197 +2025-11-14 08:15:03.499908: BDMAP_A0000197, shape torch.Size([1, 512, 472, 499]), rank 0 +2025-11-14 08:16:46.307697: predicting BDMAP_A0000198 +2025-11-14 08:16:46.376983: BDMAP_A0000198, shape torch.Size([1, 512, 441, 453]), rank 0 +2025-11-14 08:18:33.525436: predicting BDMAP_A0000199 +2025-11-14 08:18:33.590465: BDMAP_A0000199, shape torch.Size([1, 512, 561, 422]), rank 0 +2025-11-14 08:20:21.301309: predicting BDMAP_A0000201 +2025-11-14 08:20:21.379061: BDMAP_A0000201, shape torch.Size([1, 512, 592, 571]), rank 0 +2025-11-14 08:22:16.644337: predicting BDMAP_A0000202 +2025-11-14 08:22:16.713497: BDMAP_A0000202, shape torch.Size([1, 512, 584, 513]), rank 0 +2025-11-14 08:24:07.501423: predicting BDMAP_A0000203 +2025-11-14 08:24:07.566225: BDMAP_A0000203, shape torch.Size([1, 512, 589, 468]), rank 0 +2025-11-14 08:25:51.496071: predicting BDMAP_A0000206 +2025-11-14 08:25:51.570295: BDMAP_A0000206, shape torch.Size([1, 512, 565, 519]), rank 0 +2025-11-14 08:27:40.772780: predicting BDMAP_A0000208 +2025-11-14 08:27:40.834763: BDMAP_A0000208, shape torch.Size([1, 512, 502, 526]), rank 0 +2025-11-14 08:29:25.092998: predicting BDMAP_A0000209 +2025-11-14 08:29:25.155797: BDMAP_A0000209, shape torch.Size([1, 512, 554, 480]), rank 0 +2025-11-14 08:31:14.087132: predicting BDMAP_A0000210 +2025-11-14 08:31:14.156250: BDMAP_A0000210, shape torch.Size([1, 512, 765, 385]), rank 0 +2025-11-14 08:34:20.054939: predicting BDMAP_A0000211 +2025-11-14 08:34:20.118253: BDMAP_A0000211, shape torch.Size([1, 512, 481, 563]), rank 0 +2025-11-14 08:36:04.299657: predicting BDMAP_A0000212 +2025-11-14 08:36:04.370709: BDMAP_A0000212, shape torch.Size([1, 512, 649, 549]), rank 0 +2025-11-14 08:39:06.518234: predicting BDMAP_A0000213 +2025-11-14 08:39:06.595777: BDMAP_A0000213, shape torch.Size([1, 512, 476, 501]), rank 0 +2025-11-14 08:40:50.280416: predicting BDMAP_A0000215 +2025-11-14 08:40:50.347246: BDMAP_A0000215, shape torch.Size([1, 512, 518, 488]), rank 0 +2025-11-14 08:42:33.055559: predicting BDMAP_A0000216 +2025-11-14 08:42:33.128750: BDMAP_A0000216, shape torch.Size([1, 512, 942, 639]), rank 0 +2025-11-14 08:45:49.402874: predicting BDMAP_A0000218 +2025-11-14 08:45:49.493166: BDMAP_A0000218, shape torch.Size([1, 512, 500, 470]), rank 0 +2025-11-14 08:47:34.698677: predicting BDMAP_A0000219 +2025-11-14 08:47:34.773170: BDMAP_A0000219, shape torch.Size([1, 512, 411, 454]), rank 0 +2025-11-14 08:49:19.771840: predicting BDMAP_A0000316 +2025-11-14 08:49:19.832391: BDMAP_A0000316, shape torch.Size([1, 512, 569, 543]), rank 0 +2025-11-14 08:51:25.509143: predicting BDMAP_A0000317 +2025-11-14 08:51:25.583160: BDMAP_A0000317, shape torch.Size([1, 512, 608, 563]), rank 0 +2025-11-14 08:53:09.831155: predicting BDMAP_A0000319 +2025-11-14 08:53:09.913892: BDMAP_A0000319, shape torch.Size([1, 512, 490, 520]), rank 0 +2025-11-14 08:54:55.474850: predicting BDMAP_A0000320 +2025-11-14 08:54:55.548383: BDMAP_A0000320, shape torch.Size([1, 512, 406, 471]), rank 0 +2025-11-14 08:56:38.502322: predicting BDMAP_A0000321 +2025-11-14 08:56:38.574577: BDMAP_A0000321, shape torch.Size([1, 512, 465, 610]), rank 0 +2025-11-14 08:58:23.528732: predicting BDMAP_A0000323 +2025-11-14 08:58:23.585904: BDMAP_A0000323, shape torch.Size([1, 512, 546, 661]), rank 0 +2025-11-14 09:01:21.970095: predicting BDMAP_A0000324 +2025-11-14 09:01:22.049054: BDMAP_A0000324, shape torch.Size([1, 512, 492, 489]), rank 0 +2025-11-14 09:03:05.969822: predicting BDMAP_A0000325 +2025-11-14 09:03:06.034006: BDMAP_A0000325, shape torch.Size([1, 512, 485, 480]), rank 0 +2025-11-14 09:04:51.363635: predicting BDMAP_A0000326 +2025-11-14 09:04:51.426512: BDMAP_A0000326, shape torch.Size([1, 512, 559, 397]), rank 0 +2025-11-14 09:06:37.231822: predicting BDMAP_A0000329 +2025-11-14 09:06:37.296174: BDMAP_A0000329, shape torch.Size([1, 512, 577, 459]), rank 0 +2025-11-14 09:08:22.173688: predicting BDMAP_A0000330 +2025-11-14 09:08:22.239782: BDMAP_A0000330, shape torch.Size([1, 512, 533, 585]), rank 0 +2025-11-14 09:10:05.779738: predicting BDMAP_A0000331 +2025-11-14 09:10:05.857102: BDMAP_A0000331, shape torch.Size([1, 512, 528, 574]), rank 0 +2025-11-14 09:11:52.823764: predicting BDMAP_A0000332 +2025-11-14 09:11:52.889522: BDMAP_A0000332, shape torch.Size([1, 512, 874, 509]), rank 0 +2025-11-14 09:15:06.850953: predicting BDMAP_A0000336 +2025-11-14 09:15:06.941982: BDMAP_A0000336, shape torch.Size([1, 512, 946, 563]), rank 0 +2025-11-14 09:18:23.589290: predicting BDMAP_A0000337 +2025-11-14 09:18:23.679038: BDMAP_A0000337, shape torch.Size([1, 512, 461, 523]), rank 0 +2025-11-14 09:20:09.512296: predicting BDMAP_A0000340 +2025-11-14 09:20:09.568456: BDMAP_A0000340, shape torch.Size([1, 512, 903, 589]), rank 0 +2025-11-14 09:23:24.444761: predicting BDMAP_A0000341 +2025-11-14 09:23:24.547050: BDMAP_A0000341, shape torch.Size([1, 512, 879, 570]), rank 0 +2025-11-14 09:26:39.371407: predicting BDMAP_A0000343 +2025-11-14 09:26:39.453921: BDMAP_A0000343, shape torch.Size([1, 512, 493, 616]), rank 0 +2025-11-14 09:28:35.770051: predicting BDMAP_A0000344 +2025-11-14 09:28:35.848065: BDMAP_A0000344, shape torch.Size([1, 512, 437, 506]), rank 0 +2025-11-14 09:30:23.959857: predicting BDMAP_A0000345 +2025-11-14 09:30:24.023759: BDMAP_A0000345, shape torch.Size([1, 512, 601, 565]), rank 0 +2025-11-14 09:32:12.930110: predicting BDMAP_A0000346 +2025-11-14 09:32:13.001843: BDMAP_A0000346, shape torch.Size([1, 512, 554, 622]), rank 0 +2025-11-14 09:33:57.262045: predicting BDMAP_A0000349 +2025-11-14 09:33:57.341476: BDMAP_A0000349, shape torch.Size([1, 512, 486, 489]), rank 0 +2025-11-14 09:35:39.991195: predicting BDMAP_A0000350 +2025-11-14 09:35:40.067752: BDMAP_A0000350, shape torch.Size([1, 512, 569, 543]), rank 0 +2025-11-14 09:37:26.401865: predicting BDMAP_A0000351 +2025-11-14 09:37:26.471330: BDMAP_A0000351, shape torch.Size([1, 512, 873, 484]), rank 0 +2025-11-14 09:40:39.130611: predicting BDMAP_A0000353 +2025-11-14 09:40:39.208611: BDMAP_A0000353, shape torch.Size([1, 512, 499, 387]), rank 0 +2025-11-14 09:42:25.636577: predicting BDMAP_A0000354 +2025-11-14 09:42:25.700677: BDMAP_A0000354, shape torch.Size([1, 512, 565, 515]), rank 0 +2025-11-14 09:44:08.463718: predicting BDMAP_A0000356 +2025-11-14 09:44:08.533491: BDMAP_A0000356, shape torch.Size([1, 512, 533, 487]), rank 0 +2025-11-14 09:45:53.735977: predicting BDMAP_A0000357 +2025-11-14 09:45:53.800321: BDMAP_A0000357, shape torch.Size([1, 512, 473, 484]), rank 0 +2025-11-14 09:47:37.376745: predicting BDMAP_A0000360 +2025-11-14 09:47:37.442317: BDMAP_A0000360, shape torch.Size([1, 512, 562, 606]), rank 0 +2025-11-14 09:49:21.189795: predicting BDMAP_A0000361 +2025-11-14 09:49:21.264368: BDMAP_A0000361, shape torch.Size([1, 512, 493, 506]), rank 0 +2025-11-14 09:51:03.866295: predicting BDMAP_A0000362 +2025-11-14 09:51:03.925595: BDMAP_A0000362, shape torch.Size([1, 512, 474, 543]), rank 0 +2025-11-14 09:52:48.569531: predicting BDMAP_A0000366 +2025-11-14 09:52:48.645484: BDMAP_A0000366, shape torch.Size([1, 512, 644, 560]), rank 0 +2025-11-14 09:55:53.188821: predicting BDMAP_A0000368 +2025-11-14 09:55:53.282013: BDMAP_A0000368, shape torch.Size([1, 512, 470, 565]), rank 0 +2025-11-14 09:57:41.491705: predicting BDMAP_A0000370 +2025-11-14 09:57:41.561606: BDMAP_A0000370, shape torch.Size([1, 512, 540, 532]), rank 0 +2025-11-14 09:59:29.127907: predicting BDMAP_A0000371 +2025-11-14 09:59:29.194731: BDMAP_A0000371, shape torch.Size([1, 512, 501, 515]), rank 0 +2025-11-14 10:01:12.541408: predicting BDMAP_A0000374 +2025-11-14 10:01:12.618218: BDMAP_A0000374, shape torch.Size([1, 512, 389, 467]), rank 0 +2025-11-14 10:02:55.328546: predicting BDMAP_A0000375 +2025-11-14 10:02:55.391228: BDMAP_A0000375, shape torch.Size([1, 512, 423, 550]), rank 0 +2025-11-14 10:04:38.509520: predicting BDMAP_A0000377 +2025-11-14 10:04:38.578752: BDMAP_A0000377, shape torch.Size([1, 512, 493, 571]), rank 0 +2025-11-14 10:06:22.107519: predicting BDMAP_A0000378 +2025-11-14 10:06:22.175265: BDMAP_A0000378, shape torch.Size([1, 512, 529, 588]), rank 0 +2025-11-14 10:08:05.775828: predicting BDMAP_A0000379 +2025-11-14 10:08:05.851657: BDMAP_A0000379, shape torch.Size([1, 512, 529, 582]), rank 0 +2025-11-14 10:09:49.731481: predicting BDMAP_A0000380 +2025-11-14 10:09:49.805525: BDMAP_A0000380, shape torch.Size([1, 512, 361, 481]), rank 0 +2025-11-14 10:11:34.943403: predicting BDMAP_A0000382 +2025-11-14 10:11:35.004816: BDMAP_A0000382, shape torch.Size([1, 512, 596, 684]), rank 0 +2025-11-14 10:14:38.510482: predicting BDMAP_A0000384 +2025-11-14 10:14:38.597172: BDMAP_A0000384, shape torch.Size([1, 512, 582, 696]), rank 0 +2025-11-14 10:17:38.521679: predicting BDMAP_A0000386 +2025-11-14 10:17:38.598349: BDMAP_A0000386, shape torch.Size([1, 512, 471, 473]), rank 0 +2025-11-14 10:19:25.980736: predicting BDMAP_A0000387 +2025-11-14 10:19:26.029533: BDMAP_A0000387, shape torch.Size([1, 512, 533, 487]), rank 0 +2025-11-14 10:21:10.960677: predicting BDMAP_A0000389 +2025-11-14 10:21:11.028698: BDMAP_A0000389, shape torch.Size([1, 512, 506, 501]), rank 0 +2025-11-14 10:22:54.459605: predicting BDMAP_A0000390 +2025-11-14 10:22:54.519665: BDMAP_A0000390, shape torch.Size([1, 512, 509, 481]), rank 0 +2025-11-14 10:24:38.023049: predicting BDMAP_A0000391 +2025-11-14 10:24:38.097884: BDMAP_A0000391, shape torch.Size([1, 512, 586, 568]), rank 0 +2025-11-14 10:26:22.568728: predicting BDMAP_A0000392 +2025-11-14 10:26:22.646485: BDMAP_A0000392, shape torch.Size([1, 512, 438, 549]), rank 0 +2025-11-14 10:28:06.536615: predicting BDMAP_A0000393 +2025-11-14 10:28:06.610489: BDMAP_A0000393, shape torch.Size([1, 512, 504, 508]), rank 0 +2025-11-14 10:29:49.324419: predicting BDMAP_A0000394 +2025-11-14 10:29:49.396743: BDMAP_A0000394, shape torch.Size([1, 512, 497, 557]), rank 0 +2025-11-14 10:31:32.677831: predicting BDMAP_A0000396 +2025-11-14 10:31:32.738868: BDMAP_A0000396, shape torch.Size([1, 512, 793, 422]), rank 0 +2025-11-14 10:34:39.605699: predicting BDMAP_A0000398 +2025-11-14 10:34:39.693349: BDMAP_A0000398, shape torch.Size([1, 512, 520, 421]), rank 0 +2025-11-14 10:36:23.087723: predicting BDMAP_A0000399 +2025-11-14 10:36:23.177702: BDMAP_A0000399, shape torch.Size([1, 512, 417, 509]), rank 0 +2025-11-14 10:38:05.609611: predicting BDMAP_A0000401 +2025-11-14 10:38:05.678467: BDMAP_A0000401, shape torch.Size([1, 512, 393, 504]), rank 0 +2025-11-14 10:39:50.317232: predicting BDMAP_A0000402 +2025-11-14 10:39:50.373052: BDMAP_A0000402, shape torch.Size([1, 512, 512, 484]), rank 0 +2025-11-14 10:41:33.640591: predicting BDMAP_A0000576 +2025-11-14 10:41:33.723531: BDMAP_A0000576, shape torch.Size([1, 512, 596, 409]), rank 0 +2025-11-14 10:43:16.752000: predicting BDMAP_A0000577 +2025-11-14 10:43:16.809976: BDMAP_A0000577, shape torch.Size([1, 512, 569, 402]), rank 0 +2025-11-14 10:44:59.895300: predicting BDMAP_A0000578 +2025-11-14 10:44:59.972839: BDMAP_A0000578, shape torch.Size([1, 512, 587, 422]), rank 0 +2025-11-14 10:46:42.072060: predicting BDMAP_A0000579 +2025-11-14 10:46:42.146596: BDMAP_A0000579, shape torch.Size([1, 512, 569, 394]), rank 0 +2025-11-14 10:48:26.029049: predicting BDMAP_A0000580 +2025-11-14 10:48:26.083799: BDMAP_A0000580, shape torch.Size([1, 512, 617, 444]), rank 0 +2025-11-14 10:50:10.514303: predicting BDMAP_A0000581 +2025-11-14 10:50:10.586407: BDMAP_A0000581, shape torch.Size([1, 512, 587, 459]), rank 0 +2025-11-14 10:51:58.548224: predicting BDMAP_A0000582 +2025-11-14 10:51:58.615350: BDMAP_A0000582, shape torch.Size([1, 512, 591, 422]), rank 0 +2025-11-14 10:53:45.965844: predicting BDMAP_A0000583 +2025-11-14 10:53:46.034229: BDMAP_A0000583, shape torch.Size([1, 512, 547, 422]), rank 0 +2025-11-14 10:55:28.087450: predicting BDMAP_A0000584 +2025-11-14 10:55:28.156188: BDMAP_A0000584, shape torch.Size([1, 512, 636, 502]), rank 0 +2025-11-14 10:57:12.510391: predicting BDMAP_A0000585 +2025-11-14 10:57:12.586412: BDMAP_A0000585, shape torch.Size([1, 512, 481, 459]), rank 0 +2025-11-14 10:58:58.661804: predicting BDMAP_A0000586 +2025-11-14 10:58:58.740630: BDMAP_A0000586, shape torch.Size([1, 512, 676, 450]), rank 0 +2025-11-14 11:02:00.504865: predicting BDMAP_A0000587 +2025-11-14 11:02:00.572589: BDMAP_A0000587, shape torch.Size([1, 512, 587, 422]), rank 0 +2025-11-14 11:03:43.783200: predicting BDMAP_A0000588 +2025-11-14 11:03:43.855885: BDMAP_A0000588, shape torch.Size([1, 512, 655, 422]), rank 0 +2025-11-14 11:06:44.696580: predicting BDMAP_A0000589 +2025-11-14 11:06:44.770172: BDMAP_A0000589, shape torch.Size([1, 512, 502, 422]), rank 0 +2025-11-14 11:08:27.528915: predicting BDMAP_A0000590 +2025-11-14 11:08:27.608391: BDMAP_A0000590, shape torch.Size([1, 512, 632, 428]), rank 0 +2025-11-14 11:10:10.667436: predicting BDMAP_A0000591 +2025-11-14 11:10:10.744539: BDMAP_A0000591, shape torch.Size([1, 512, 445, 506]), rank 0 +2025-11-14 11:11:53.542091: predicting BDMAP_A0000592 +2025-11-14 11:11:53.614622: BDMAP_A0000592, shape torch.Size([1, 512, 605, 456]), rank 0 +2025-11-14 11:13:38.264663: predicting BDMAP_A0000593 +2025-11-14 11:13:38.341672: BDMAP_A0000593, shape torch.Size([1, 512, 563, 422]), rank 0 +2025-11-14 11:15:23.021443: predicting BDMAP_A0000594 +2025-11-14 11:15:23.087639: BDMAP_A0000594, shape torch.Size([1, 512, 579, 456]), rank 0 +2025-11-14 11:17:05.953480: predicting BDMAP_A0000595 +2025-11-14 11:17:06.026622: BDMAP_A0000595, shape torch.Size([1, 512, 667, 475]), rank 0 +2025-11-14 11:20:08.065025: predicting BDMAP_A0000596 +2025-11-14 11:20:08.130825: BDMAP_A0000596, shape torch.Size([1, 512, 601, 571]), rank 0 +2025-11-14 11:21:51.630034: predicting BDMAP_A0000597 +2025-11-14 11:21:51.717831: BDMAP_A0000597, shape torch.Size([1, 512, 632, 463]), rank 0 +2025-11-14 11:23:33.879317: predicting BDMAP_A0000598 +2025-11-14 11:23:33.954375: BDMAP_A0000598, shape torch.Size([1, 512, 653, 495]), rank 0 +2025-11-14 11:26:35.015953: predicting BDMAP_A0000600 +2025-11-14 11:26:35.087317: BDMAP_A0000600, shape torch.Size([1, 512, 585, 422]), rank 0 +2025-11-14 11:28:19.011112: predicting BDMAP_A0000601 +2025-11-14 11:28:19.079144: BDMAP_A0000601, shape torch.Size([1, 512, 521, 460]), rank 0 +2025-11-14 11:30:01.162626: predicting BDMAP_A0000602 +2025-11-14 11:30:01.230544: BDMAP_A0000602, shape torch.Size([1, 512, 667, 457]), rank 0 +2025-11-14 11:33:01.863814: predicting BDMAP_A0000604 +2025-11-14 11:33:01.918114: BDMAP_A0000604, shape torch.Size([1, 512, 609, 474]), rank 0 +2025-11-14 11:34:45.918459: predicting BDMAP_A0000605 +2025-11-14 11:34:45.982912: BDMAP_A0000605, shape torch.Size([1, 512, 606, 418]), rank 0 +2025-11-14 11:36:29.174593: predicting BDMAP_A0000606 +2025-11-14 11:36:29.242349: BDMAP_A0000606, shape torch.Size([1, 512, 483, 495]), rank 0 +2025-11-14 11:38:13.676986: predicting BDMAP_A0000607 +2025-11-14 11:38:13.746972: BDMAP_A0000607, shape torch.Size([1, 512, 641, 513]), rank 0 +2025-11-14 11:41:14.186683: predicting BDMAP_A0000608 +2025-11-14 11:41:14.251811: BDMAP_A0000608, shape torch.Size([1, 512, 590, 519]), rank 0 +2025-11-14 11:42:57.883262: predicting BDMAP_A0000609 +2025-11-14 11:42:57.961227: BDMAP_A0000609, shape torch.Size([1, 512, 708, 412]), rank 0 +2025-11-14 11:46:00.810008: predicting BDMAP_A0000610 +2025-11-14 11:46:00.879463: BDMAP_A0000610, shape torch.Size([1, 512, 617, 456]), rank 0 +2025-11-14 11:47:44.071112: predicting BDMAP_A0000611 +2025-11-14 11:47:44.143941: BDMAP_A0000611, shape torch.Size([1, 512, 672, 473]), rank 0 +2025-11-14 11:50:46.449012: predicting BDMAP_A0000612 +2025-11-14 11:50:46.521940: BDMAP_A0000612, shape torch.Size([1, 512, 461, 422]), rank 0 +2025-11-14 11:52:29.181241: predicting BDMAP_A0000614 +2025-11-14 11:52:29.250237: BDMAP_A0000614, shape torch.Size([1, 512, 655, 422]), rank 0 +2025-11-14 11:55:33.393509: predicting BDMAP_A0000615 +2025-11-14 11:55:33.471398: BDMAP_A0000615, shape torch.Size([1, 512, 633, 511]), rank 0 +2025-11-14 11:57:17.080392: predicting BDMAP_A0000616 +2025-11-14 11:57:17.166030: BDMAP_A0000616, shape torch.Size([1, 512, 493, 492]), rank 0 +2025-11-14 11:58:58.919605: predicting BDMAP_A0000617 +2025-11-14 11:58:58.974669: BDMAP_A0000617, shape torch.Size([1, 512, 477, 405]), rank 0 +2025-11-14 12:00:43.446687: predicting BDMAP_A0000618 +2025-11-14 12:00:43.513268: BDMAP_A0000618, shape torch.Size([1, 512, 606, 535]), rank 0 +2025-11-14 12:02:31.198396: predicting BDMAP_A0000620 +2025-11-14 12:02:31.278205: BDMAP_A0000620, shape torch.Size([1, 512, 590, 535]), rank 0 +2025-11-14 12:04:15.856906: predicting BDMAP_A0000621 +2025-11-14 12:04:15.932320: BDMAP_A0000621, shape torch.Size([1, 512, 629, 515]), rank 0 +2025-11-14 12:06:00.682600: predicting BDMAP_A0000623 +2025-11-14 12:06:00.765976: BDMAP_A0000623, shape torch.Size([1, 512, 489, 456]), rank 0 +2025-11-14 12:07:44.686647: predicting BDMAP_A0000624 +2025-11-14 12:07:44.748998: BDMAP_A0000624, shape torch.Size([1, 512, 469, 492]), rank 0 +2025-11-14 12:09:31.071598: predicting BDMAP_A0000625 +2025-11-14 12:09:31.135076: BDMAP_A0000625, shape torch.Size([1, 512, 543, 428]), rank 0 +2025-11-14 12:11:18.028755: predicting BDMAP_A0000626 +2025-11-14 12:11:18.106770: BDMAP_A0000626, shape torch.Size([1, 512, 713, 385]), rank 0 +2025-11-14 12:14:21.399030: predicting BDMAP_A0000627 +2025-11-14 12:14:21.482058: BDMAP_A0000627, shape torch.Size([1, 512, 643, 495]), rank 0 +2025-11-14 12:17:22.594966: predicting BDMAP_A0000631 +2025-11-14 12:17:22.678200: BDMAP_A0000631, shape torch.Size([1, 512, 553, 563]), rank 0 +2025-11-14 12:19:08.734377: predicting BDMAP_A0000632 +2025-11-14 12:19:08.797822: BDMAP_A0000632, shape torch.Size([1, 512, 557, 537]), rank 0 +2025-11-14 12:20:53.589182: predicting BDMAP_A0000633 +2025-11-14 12:20:53.664855: BDMAP_A0000633, shape torch.Size([1, 512, 655, 440]), rank 0 +2025-11-14 12:23:56.999114: predicting BDMAP_A0000634 +2025-11-14 12:23:57.061808: BDMAP_A0000634, shape torch.Size([1, 512, 512, 492]), rank 0 +2025-11-14 12:25:39.820943: predicting BDMAP_A0000635 +2025-11-14 12:25:39.882264: BDMAP_A0000635, shape torch.Size([1, 512, 490, 608]), rank 0 +2025-11-14 12:27:23.241287: predicting BDMAP_A0000636 +2025-11-14 12:27:23.317640: BDMAP_A0000636, shape torch.Size([1, 512, 521, 492]), rank 0 +2025-11-14 12:29:10.352644: predicting BDMAP_A0000638 +2025-11-14 12:29:10.415657: BDMAP_A0000638, shape torch.Size([1, 512, 627, 428]), rank 0 +2025-11-14 12:30:55.217332: predicting BDMAP_A0000639 +2025-11-14 12:30:55.298012: BDMAP_A0000639, shape torch.Size([1, 512, 675, 523]), rank 0 +2025-11-14 12:33:57.143812: predicting BDMAP_A0000640 +2025-11-14 12:33:57.235079: BDMAP_A0000640, shape torch.Size([1, 512, 553, 446]), rank 0 +2025-11-14 12:35:40.550381: predicting BDMAP_A0000641 +2025-11-14 12:35:40.630770: BDMAP_A0000641, shape torch.Size([1, 512, 642, 461]), rank 0 +2025-11-14 12:38:40.628160: predicting BDMAP_A0000642 +2025-11-14 12:38:40.699321: BDMAP_A0000642, shape torch.Size([1, 512, 726, 473]), rank 0 +2025-11-14 12:41:43.480303: predicting BDMAP_A0000643 +2025-11-14 12:41:43.560772: BDMAP_A0000643, shape torch.Size([1, 512, 539, 426]), rank 0 +2025-11-14 12:43:26.832620: predicting BDMAP_A0000644 +2025-11-14 12:43:26.889014: BDMAP_A0000644, shape torch.Size([1, 512, 421, 551]), rank 0 +2025-11-14 12:45:10.043965: predicting BDMAP_A0000645 +2025-11-14 12:45:10.113929: BDMAP_A0000645, shape torch.Size([1, 512, 697, 596]), rank 0 +2025-11-14 12:48:16.619104: predicting BDMAP_A0000646 +2025-11-14 12:48:16.703542: BDMAP_A0000646, shape torch.Size([1, 512, 631, 388]), rank 0 +2025-11-14 12:49:59.476038: predicting BDMAP_A0000647 +2025-11-14 12:49:59.555828: BDMAP_A0000647, shape torch.Size([1, 512, 611, 456]), rank 0 +2025-11-14 12:51:43.150481: predicting BDMAP_A0000648 +2025-11-14 12:51:43.219171: BDMAP_A0000648, shape torch.Size([1, 512, 557, 484]), rank 0 +2025-11-14 12:53:28.882658: predicting BDMAP_A0000649 +2025-11-14 12:53:28.949555: BDMAP_A0000649, shape torch.Size([1, 512, 479, 433]), rank 0 +2025-11-14 12:55:15.023395: predicting BDMAP_A0000650 +2025-11-14 12:55:15.095580: BDMAP_A0000650, shape torch.Size([1, 512, 605, 473]), rank 0 +2025-11-14 12:56:58.032375: predicting BDMAP_A0000651 +2025-11-14 12:56:58.108341: BDMAP_A0000651, shape torch.Size([1, 512, 585, 543]), rank 0 +2025-11-14 12:58:42.036465: predicting BDMAP_A0000652 +2025-11-14 12:58:42.125292: BDMAP_A0000652, shape torch.Size([1, 512, 637, 422]), rank 0 +2025-11-14 13:00:24.693315: predicting BDMAP_A0000653 +2025-11-14 13:00:24.770424: BDMAP_A0000653, shape torch.Size([1, 512, 627, 428]), rank 0 +2025-11-14 13:02:11.282919: predicting BDMAP_A0000654 +2025-11-14 13:02:11.348800: BDMAP_A0000654, shape torch.Size([1, 512, 531, 388]), rank 0 +2025-11-14 13:03:56.445896: predicting BDMAP_A0000655 +2025-11-14 13:03:56.526013: BDMAP_A0000655, shape torch.Size([1, 512, 631, 464]), rank 0 +2025-11-14 13:05:39.711592: predicting BDMAP_A0000656 +2025-11-14 13:05:39.765522: BDMAP_A0000656, shape torch.Size([1, 512, 431, 459]), rank 0 +2025-11-14 13:07:23.957810: predicting BDMAP_A0000657 +2025-11-14 13:07:24.034015: BDMAP_A0000657, shape torch.Size([1, 512, 641, 475]), rank 0 +2025-11-14 13:10:26.296180: predicting BDMAP_A0000658 +2025-11-14 13:10:26.375831: BDMAP_A0000658, shape torch.Size([1, 512, 561, 522]), rank 0 +2025-11-14 13:12:09.024072: predicting BDMAP_A0000659 +2025-11-14 13:12:09.104271: BDMAP_A0000659, shape torch.Size([1, 512, 711, 518]), rank 0 +2025-11-14 13:15:14.076287: predicting BDMAP_A0000661 +2025-11-14 13:15:14.160083: BDMAP_A0000661, shape torch.Size([1, 512, 659, 422]), rank 0 +2025-11-14 13:18:14.797294: predicting BDMAP_A0000662 +2025-11-14 13:18:14.873683: BDMAP_A0000662, shape torch.Size([1, 512, 525, 425]), rank 0 +2025-11-14 13:19:58.006068: predicting BDMAP_A0000663 +2025-11-14 13:19:58.063341: BDMAP_A0000663, shape torch.Size([1, 512, 593, 443]), rank 0 +2025-11-14 13:21:40.860038: predicting BDMAP_A0000664 +2025-11-14 13:21:41.123202: BDMAP_A0000664, shape torch.Size([1, 512, 613, 430]), rank 0 +2025-11-14 13:23:29.510109: predicting BDMAP_A0000665 +2025-11-14 13:23:30.126578: BDMAP_A0000665, shape torch.Size([1, 512, 709, 525]), rank 0 +2025-11-14 13:27:08.064249: predicting BDMAP_A0000666 +2025-11-14 13:27:08.154718: BDMAP_A0000666, shape torch.Size([1, 512, 631, 422]), rank 0 +2025-11-14 13:28:51.948271: predicting BDMAP_A0000667 +2025-11-14 13:28:52.030305: BDMAP_A0000667, shape torch.Size([1, 512, 499, 433]), rank 0 +2025-11-14 13:30:36.278375: predicting BDMAP_A0000668 +2025-11-14 13:30:36.348713: BDMAP_A0000668, shape torch.Size([1, 512, 643, 422]), rank 0 +2025-11-14 13:33:39.029123: predicting BDMAP_A0000669 +2025-11-14 13:33:39.104382: BDMAP_A0000669, shape torch.Size([1, 512, 657, 509]), rank 0 +2025-11-14 13:36:42.520510: predicting BDMAP_A0000670 +2025-11-14 13:36:42.608638: BDMAP_A0000670, shape torch.Size([1, 512, 625, 452]), rank 0 +2025-11-14 13:38:26.594390: predicting BDMAP_A0000671 +2025-11-14 13:38:26.656104: BDMAP_A0000671, shape torch.Size([1, 512, 513, 419]), rank 0 +2025-11-14 13:40:08.657916: predicting BDMAP_A0000672 +2025-11-14 13:40:08.735853: BDMAP_A0000672, shape torch.Size([1, 512, 545, 506]), rank 0 +2025-11-14 13:41:51.135070: predicting BDMAP_A0000673 +2025-11-14 13:41:51.208190: BDMAP_A0000673, shape torch.Size([1, 512, 603, 512]), rank 0 +2025-11-14 13:43:36.100883: predicting BDMAP_A0000674 +2025-11-14 13:43:36.167866: BDMAP_A0000674, shape torch.Size([1, 512, 575, 450]), rank 0 +2025-11-14 13:45:19.352537: predicting BDMAP_A0000675 +2025-11-14 13:45:19.425269: BDMAP_A0000675, shape torch.Size([1, 512, 611, 535]), rank 0 +2025-11-14 13:47:02.172394: predicting BDMAP_A0000676 +2025-11-14 13:47:02.248873: BDMAP_A0000676, shape torch.Size([1, 512, 618, 475]), rank 0 +2025-11-14 13:48:45.570038: predicting BDMAP_A0000677 +2025-11-14 13:48:45.662547: BDMAP_A0000677, shape torch.Size([1, 512, 643, 422]), rank 0 +2025-11-14 13:51:45.976331: predicting BDMAP_A0000678 +2025-11-14 13:51:46.038297: BDMAP_A0000678, shape torch.Size([1, 512, 675, 460]), rank 0 +2025-11-14 13:54:47.180134: predicting BDMAP_A0000679 +2025-11-14 13:54:47.266074: BDMAP_A0000679, shape torch.Size([1, 512, 553, 467]), rank 0 +2025-11-14 13:56:30.730369: predicting BDMAP_A0000680 +2025-11-14 13:56:30.795969: BDMAP_A0000680, shape torch.Size([1, 512, 635, 535]), rank 0 +2025-11-14 13:58:13.340796: predicting BDMAP_A0000681 +2025-11-14 13:58:13.413142: BDMAP_A0000681, shape torch.Size([1, 512, 585, 523]), rank 0 +2025-11-14 13:59:58.445708: predicting BDMAP_A0000682 +2025-11-14 13:59:58.522038: BDMAP_A0000682, shape torch.Size([1, 512, 677, 487]), rank 0 +2025-11-14 14:03:02.556408: predicting BDMAP_A0000683 +2025-11-14 14:03:02.628792: BDMAP_A0000683, shape torch.Size([1, 512, 655, 422]), rank 0 +2025-11-14 14:06:02.868684: predicting BDMAP_A0000684 +2025-11-14 14:06:02.949368: BDMAP_A0000684, shape torch.Size([1, 512, 667, 461]), rank 0 +2025-11-14 14:09:04.499935: predicting BDMAP_A0000685 +2025-11-14 14:09:04.811949: BDMAP_A0000685, shape torch.Size([1, 512, 655, 422]), rank 0 +2025-11-14 14:12:05.165641: predicting BDMAP_A0000686 +2025-11-14 14:12:05.248958: BDMAP_A0000686, shape torch.Size([1, 512, 568, 468]), rank 0 +2025-11-14 14:13:48.441252: predicting BDMAP_A0000687 +2025-11-14 14:13:48.521784: BDMAP_A0000687, shape torch.Size([1, 512, 445, 444]), rank 0 +2025-11-14 14:15:31.596596: predicting BDMAP_A0000688 +2025-11-14 14:15:31.663874: BDMAP_A0000688, shape torch.Size([1, 512, 659, 422]), rank 0 +2025-11-14 14:18:32.474079: predicting BDMAP_A0000689 +2025-11-14 14:18:32.545952: BDMAP_A0000689, shape torch.Size([1, 512, 497, 443]), rank 0 +2025-11-14 14:20:14.754143: predicting BDMAP_A0000690 +2025-11-14 14:20:14.820539: BDMAP_A0000690, shape torch.Size([1, 512, 581, 535]), rank 0 +2025-11-14 14:21:58.414139: predicting BDMAP_A0000691 +2025-11-14 14:21:58.485507: BDMAP_A0000691, shape torch.Size([1, 512, 721, 568]), rank 0 +2025-11-14 14:25:03.993675: predicting BDMAP_A0000692 +2025-11-14 14:25:04.073770: BDMAP_A0000692, shape torch.Size([1, 512, 651, 478]), rank 0 +2025-11-14 14:28:04.082520: predicting BDMAP_A0000693 +2025-11-14 14:28:04.173644: BDMAP_A0000693, shape torch.Size([1, 512, 639, 422]), rank 0 +2025-11-14 14:29:48.874270: predicting BDMAP_A0000694 +2025-11-14 14:29:48.947840: BDMAP_A0000694, shape torch.Size([1, 512, 748, 570]), rank 0 +2025-11-14 14:32:54.699100: predicting BDMAP_A0000695 +2025-11-14 14:32:54.778539: BDMAP_A0000695, shape torch.Size([1, 512, 554, 467]), rank 0 +2025-11-14 14:34:38.614937: predicting BDMAP_A0000696 +2025-11-14 14:34:38.683593: BDMAP_A0000696, shape torch.Size([1, 512, 502, 422]), rank 0 +2025-11-14 14:36:21.273724: predicting BDMAP_A0000697 +2025-11-14 14:36:21.344319: BDMAP_A0000697, shape torch.Size([1, 512, 587, 454]), rank 0 +2025-11-14 14:38:07.171744: predicting BDMAP_A0000699 +2025-11-14 14:38:07.237115: BDMAP_A0000699, shape torch.Size([1, 512, 761, 537]), rank 0 +2025-11-14 14:41:13.163951: predicting BDMAP_A0000700 +2025-11-14 14:41:13.235602: BDMAP_A0000700, shape torch.Size([1, 512, 537, 470]), rank 0 +2025-11-14 14:42:58.614716: predicting BDMAP_A0000701 +2025-11-14 14:42:58.685717: BDMAP_A0000701, shape torch.Size([1, 512, 621, 422]), rank 0 +2025-11-14 14:44:42.312815: predicting BDMAP_A0000702 +2025-11-14 14:44:42.383719: BDMAP_A0000702, shape torch.Size([1, 512, 563, 422]), rank 0 +2025-11-14 14:46:28.074608: predicting BDMAP_A0000703 +2025-11-14 14:46:28.136770: BDMAP_A0000703, shape torch.Size([1, 512, 671, 422]), rank 0 +2025-11-14 14:49:28.361359: predicting BDMAP_A0000704 +2025-11-14 14:49:28.429778: BDMAP_A0000704, shape torch.Size([1, 512, 663, 473]), rank 0 +2025-11-14 14:52:28.877359: predicting BDMAP_A0000705 +2025-11-14 14:52:28.966904: BDMAP_A0000705, shape torch.Size([1, 512, 581, 515]), rank 0 +2025-11-14 14:54:12.254996: predicting BDMAP_A0000706 +2025-11-14 14:54:12.334527: BDMAP_A0000706, shape torch.Size([1, 512, 632, 428]), rank 0 +2025-11-14 14:55:54.902997: predicting BDMAP_A0000707 +2025-11-14 14:55:54.992433: BDMAP_A0000707, shape torch.Size([1, 512, 600, 398]), rank 0 +2025-11-14 14:57:41.040609: predicting BDMAP_A0000708 +2025-11-14 14:57:41.100730: BDMAP_A0000708, shape torch.Size([1, 512, 657, 484]), rank 0 +2025-11-14 15:00:42.688070: predicting BDMAP_A0000709 +2025-11-14 15:00:42.769298: BDMAP_A0000709, shape torch.Size([1, 512, 775, 461]), rank 0 +2025-11-14 15:03:49.813460: predicting BDMAP_A0000710 +2025-11-14 15:03:49.877468: BDMAP_A0000710, shape torch.Size([1, 512, 684, 492]), rank 0 +2025-11-14 15:06:54.144123: predicting BDMAP_A0000711 +2025-11-14 15:06:54.216089: BDMAP_A0000711, shape torch.Size([1, 512, 707, 454]), rank 0 +2025-11-14 15:09:57.986808: predicting BDMAP_A0000712 +2025-11-14 15:09:58.057443: BDMAP_A0000712, shape torch.Size([1, 512, 624, 430]), rank 0 +2025-11-14 15:11:41.497085: predicting BDMAP_A0000713 +2025-11-14 15:11:41.583883: BDMAP_A0000713, shape torch.Size([1, 512, 625, 422]), rank 0 +2025-11-14 15:13:23.739840: predicting BDMAP_A0000714 +2025-11-14 15:13:23.813638: BDMAP_A0000714, shape torch.Size([1, 512, 469, 422]), rank 0 +2025-11-14 15:15:06.353396: predicting BDMAP_A0000715 +2025-11-14 15:15:06.411609: BDMAP_A0000715, shape torch.Size([1, 512, 697, 414]), rank 0 +2025-11-14 15:18:07.900473: predicting BDMAP_A0000716 +2025-11-14 15:18:07.975734: BDMAP_A0000716, shape torch.Size([1, 512, 585, 480]), rank 0 +2025-11-14 15:19:50.529488: predicting BDMAP_A0000717 +2025-11-14 15:19:50.599853: BDMAP_A0000717, shape torch.Size([1, 512, 445, 506]), rank 0 +2025-11-14 15:21:32.393002: predicting BDMAP_A0000718 +2025-11-14 15:21:32.470393: BDMAP_A0000718, shape torch.Size([1, 512, 634, 399]), rank 0 +2025-11-14 15:23:16.090663: predicting BDMAP_A0000719 +2025-11-14 15:23:16.163400: BDMAP_A0000719, shape torch.Size([1, 512, 557, 535]), rank 0 +2025-11-14 15:25:02.027947: predicting BDMAP_A0000720 +2025-11-14 15:25:02.097722: BDMAP_A0000720, shape torch.Size([1, 512, 623, 422]), rank 0 +2025-11-14 15:26:45.242832: predicting BDMAP_A0000721 +2025-11-14 15:26:45.322587: BDMAP_A0000721, shape torch.Size([1, 512, 613, 422]), rank 0 +2025-11-14 15:28:28.585127: predicting BDMAP_A0000722 +2025-11-14 15:28:28.648161: BDMAP_A0000722, shape torch.Size([1, 512, 735, 504]), rank 0 +2025-11-14 15:31:32.655380: predicting BDMAP_A0000723 +2025-11-14 15:31:32.741182: BDMAP_A0000723, shape torch.Size([1, 512, 639, 533]), rank 0 +2025-11-14 15:33:18.153984: predicting BDMAP_A0000724 +2025-11-14 15:33:18.237181: BDMAP_A0000724, shape torch.Size([1, 512, 808, 630]), rank 0 +2025-11-14 15:36:27.497312: predicting BDMAP_A0000725 +2025-11-14 15:36:27.585811: BDMAP_A0000725, shape torch.Size([1, 512, 605, 456]), rank 0 +2025-11-14 15:38:14.668568: predicting BDMAP_A0000726 +2025-11-14 15:38:14.753842: BDMAP_A0000726, shape torch.Size([1, 512, 679, 470]), rank 0 +2025-11-14 15:41:17.173835: predicting BDMAP_A0000727 +2025-11-14 15:41:17.251990: BDMAP_A0000727, shape torch.Size([1, 512, 659, 443]), rank 0 +2025-11-14 15:44:21.658231: predicting BDMAP_A0000728 +2025-11-14 15:44:21.714842: BDMAP_A0000728, shape torch.Size([1, 512, 660, 452]), rank 0 +2025-11-14 15:47:23.204141: predicting BDMAP_A0000729 +2025-11-14 15:47:23.264858: BDMAP_A0000729, shape torch.Size([1, 512, 496, 422]), rank 0 +2025-11-14 15:49:05.261364: predicting BDMAP_A0000730 +2025-11-14 15:49:05.332541: BDMAP_A0000730, shape torch.Size([1, 512, 624, 480]), rank 0 +2025-11-14 15:50:47.548509: predicting BDMAP_A0000731 +2025-11-14 15:50:47.646288: BDMAP_A0000731, shape torch.Size([1, 512, 619, 499]), rank 0 +2025-11-14 15:52:33.816406: predicting BDMAP_A0000732 +2025-11-14 15:52:33.876642: BDMAP_A0000732, shape torch.Size([1, 512, 635, 481]), rank 0 +2025-11-14 15:54:17.560731: predicting BDMAP_A0000733 +2025-11-14 15:54:17.634152: BDMAP_A0000733, shape torch.Size([1, 512, 697, 456]), rank 0 +2025-11-14 15:57:20.799778: predicting BDMAP_A0000734 +2025-11-14 15:57:20.862512: BDMAP_A0000734, shape torch.Size([1, 512, 859, 509]), rank 0 +2025-11-14 16:00:31.919937: predicting BDMAP_A0000735 +2025-11-14 16:00:32.007903: BDMAP_A0000735, shape torch.Size([1, 512, 563, 422]), rank 0 +2025-11-14 16:02:18.164072: predicting BDMAP_A0000736 +2025-11-14 16:02:18.236295: BDMAP_A0000736, shape torch.Size([1, 512, 653, 487]), rank 0 +2025-11-14 16:05:17.650663: predicting BDMAP_A0000737 +2025-11-14 16:05:17.748720: BDMAP_A0000737, shape torch.Size([1, 512, 614, 473]), rank 0 +2025-11-14 16:07:04.241411: predicting BDMAP_A0000738 +2025-11-14 16:07:04.307100: BDMAP_A0000738, shape torch.Size([1, 512, 611, 422]), rank 0 +2025-11-14 16:08:46.230935: predicting BDMAP_A0000739 +2025-11-14 16:08:46.307931: BDMAP_A0000739, shape torch.Size([1, 512, 685, 480]), rank 0 +2025-11-14 16:11:52.033628: predicting BDMAP_A0000740 +2025-11-14 16:11:52.095077: BDMAP_A0000740, shape torch.Size([1, 512, 591, 474]), rank 0 +2025-11-14 16:13:37.420296: predicting BDMAP_A0000742 +2025-11-14 16:13:37.492249: BDMAP_A0000742, shape torch.Size([1, 512, 616, 440]), rank 0 +2025-11-14 16:15:20.800897: predicting BDMAP_A0000743 +2025-11-14 16:15:20.879956: BDMAP_A0000743, shape torch.Size([1, 512, 723, 498]), rank 0 +2025-11-14 16:18:28.782580: predicting BDMAP_A0000744 +2025-11-14 16:18:28.846317: BDMAP_A0000744, shape torch.Size([1, 512, 683, 422]), rank 0 +2025-11-14 16:21:33.172535: predicting BDMAP_A0000745 +2025-11-14 16:21:33.248878: BDMAP_A0000745, shape torch.Size([1, 512, 579, 456]), rank 0 +2025-11-14 16:23:18.212689: predicting BDMAP_A0000746 +2025-11-14 16:23:18.280577: BDMAP_A0000746, shape torch.Size([1, 512, 647, 449]), rank 0 +2025-11-14 16:26:19.943894: predicting BDMAP_A0000747 +2025-11-14 16:26:20.035180: BDMAP_A0000747, shape torch.Size([1, 512, 709, 430]), rank 0 +2025-11-14 16:29:24.330579: predicting BDMAP_A0000748 +2025-11-14 16:29:24.403197: BDMAP_A0000748, shape torch.Size([1, 512, 667, 475]), rank 0 +2025-11-14 16:32:26.574158: predicting BDMAP_A0000749 +2025-11-14 16:32:26.649843: BDMAP_A0000749, shape torch.Size([1, 512, 649, 456]), rank 0 +2025-11-14 16:35:27.146504: predicting BDMAP_A0000750 +2025-11-14 16:35:27.219350: BDMAP_A0000750, shape torch.Size([1, 512, 568, 421]), rank 0 +2025-11-14 16:37:11.825603: predicting BDMAP_A0000751 +2025-11-14 16:37:11.889916: BDMAP_A0000751, shape torch.Size([1, 512, 580, 435]), rank 0 +2025-11-14 16:38:53.849863: predicting BDMAP_A0000752 +2025-11-14 16:38:53.925074: BDMAP_A0000752, shape torch.Size([1, 512, 441, 477]), rank 0 +2025-11-14 16:40:38.326676: predicting BDMAP_A0000753 +2025-11-14 16:40:38.386028: BDMAP_A0000753, shape torch.Size([1, 512, 363, 457]), rank 0 +2025-11-14 16:42:21.537250: predicting BDMAP_A0000754 +2025-11-14 16:42:21.600009: BDMAP_A0000754, shape torch.Size([1, 512, 479, 511]), rank 0 +2025-11-14 16:44:07.202129: predicting BDMAP_A0000755 +2025-11-14 16:44:07.266186: BDMAP_A0000755, shape torch.Size([1, 512, 557, 473]), rank 0 +2025-11-14 16:45:50.096658: predicting BDMAP_A0000756 +2025-11-14 16:45:50.159604: BDMAP_A0000756, shape torch.Size([1, 512, 603, 335]), rank 0 +2025-11-14 16:47:32.547699: predicting BDMAP_A0000757 +2025-11-14 16:47:32.615946: BDMAP_A0000757, shape torch.Size([1, 512, 767, 430]), rank 0 +2025-11-14 16:50:37.597472: predicting BDMAP_A0000758 +2025-11-14 16:50:37.690829: BDMAP_A0000758, shape torch.Size([1, 512, 657, 522]), rank 0 +2025-11-14 16:53:38.599108: predicting BDMAP_A0000759 +2025-11-14 16:53:38.671814: BDMAP_A0000759, shape torch.Size([1, 512, 601, 571]), rank 0 +2025-11-14 16:55:25.347332: predicting BDMAP_A0000760 +2025-11-14 16:55:25.428329: BDMAP_A0000760, shape torch.Size([1, 512, 575, 422]), rank 0 +2025-11-14 16:57:09.436081: predicting BDMAP_A0000761 +2025-11-14 16:57:09.514404: BDMAP_A0000761, shape torch.Size([1, 512, 668, 535]), rank 0 +2025-11-14 17:00:12.899226: predicting BDMAP_A0000762 +2025-11-14 17:00:12.961381: BDMAP_A0000762, shape torch.Size([1, 512, 528, 498]), rank 0 +2025-11-14 17:01:56.593210: predicting BDMAP_A0000763 +2025-11-14 17:01:56.678752: BDMAP_A0000763, shape torch.Size([1, 512, 585, 453]), rank 0 +2025-11-14 17:03:38.437300: predicting BDMAP_A0000764 +2025-11-14 17:03:38.528908: BDMAP_A0000764, shape torch.Size([1, 512, 586, 422]), rank 0 +2025-11-14 17:05:24.064702: predicting BDMAP_A0000765 +2025-11-14 17:05:24.135231: BDMAP_A0000765, shape torch.Size([1, 512, 625, 473]), rank 0 +2025-11-14 17:07:09.816401: predicting BDMAP_A0000766 +2025-11-14 17:07:09.885432: BDMAP_A0000766, shape torch.Size([1, 512, 695, 512]), rank 0 +2025-11-14 17:10:15.709102: predicting BDMAP_A0000767 +2025-11-14 17:10:15.781440: BDMAP_A0000767, shape torch.Size([1, 512, 757, 608]), rank 0 +2025-11-14 17:13:22.169212: predicting BDMAP_A0000768 +2025-11-14 17:13:22.280062: BDMAP_A0000768, shape torch.Size([1, 512, 689, 468]), rank 0 +2025-11-14 17:16:26.477002: predicting BDMAP_A0000769 +2025-11-14 17:16:26.562006: BDMAP_A0000769, shape torch.Size([1, 512, 632, 463]), rank 0 +2025-11-14 17:18:13.543773: predicting BDMAP_A0000770 +2025-11-14 17:18:13.608219: BDMAP_A0000770, shape torch.Size([1, 512, 536, 506]), rank 0 +2025-11-14 17:19:56.277168: predicting BDMAP_A0000771 +2025-11-14 17:19:56.355161: BDMAP_A0000771, shape torch.Size([1, 512, 641, 535]), rank 0 +2025-11-14 17:22:58.469476: predicting BDMAP_A0000772 +2025-11-14 17:22:58.537867: BDMAP_A0000772, shape torch.Size([1, 512, 653, 495]), rank 0 +2025-11-14 17:25:59.093857: predicting BDMAP_A0000774 +2025-11-14 17:25:59.186622: BDMAP_A0000774, shape torch.Size([1, 512, 598, 421]), rank 0 +2025-11-14 17:27:45.535868: predicting BDMAP_A0000775 +2025-11-14 17:27:45.622741: BDMAP_A0000775, shape torch.Size([1, 512, 564, 535]), rank 0 +2025-11-14 17:29:29.913353: predicting BDMAP_A0000776 +2025-11-14 17:29:30.025800: BDMAP_A0000776, shape torch.Size([1, 512, 472, 422]), rank 0 +2025-11-14 17:31:13.852629: predicting BDMAP_A0000777 +2025-11-14 17:31:13.932831: BDMAP_A0000777, shape torch.Size([1, 512, 602, 556]), rank 0 +2025-11-14 17:32:58.893440: predicting BDMAP_A0000778 +2025-11-14 17:32:58.975089: BDMAP_A0000778, shape torch.Size([1, 512, 662, 471]), rank 0 +2025-11-14 17:36:01.437467: predicting BDMAP_A0000779 +2025-11-14 17:36:01.517465: BDMAP_A0000779, shape torch.Size([1, 512, 441, 519]), rank 0 +2025-11-14 17:37:44.779181: predicting BDMAP_A0000780 +2025-11-14 17:37:44.841874: BDMAP_A0000780, shape torch.Size([1, 512, 635, 422]), rank 0 +2025-11-14 17:39:27.576627: predicting BDMAP_A0000781 +2025-11-14 17:39:27.650706: BDMAP_A0000781, shape torch.Size([1, 512, 368, 460]), rank 0 +2025-11-14 17:41:09.544500: predicting BDMAP_A0000782 +2025-11-14 17:41:09.619718: BDMAP_A0000782, shape torch.Size([1, 512, 583, 529]), rank 0 +2025-11-14 17:42:54.115858: predicting BDMAP_A0000783 +2025-11-14 17:42:54.197852: BDMAP_A0000783, shape torch.Size([1, 512, 771, 504]), rank 0 +2025-11-14 17:46:00.236679: predicting BDMAP_A0000784 +2025-11-14 17:46:00.326857: BDMAP_A0000784, shape torch.Size([1, 512, 421, 446]), rank 0 +2025-11-14 17:47:43.327582: predicting BDMAP_A0000785 +2025-11-14 17:47:43.392909: BDMAP_A0000785, shape torch.Size([1, 512, 399, 440]), rank 0 +2025-11-14 17:49:25.975208: predicting BDMAP_A0000786 +2025-11-14 17:49:26.046943: BDMAP_A0000786, shape torch.Size([1, 512, 576, 426]), rank 0 +2025-11-14 17:51:10.440311: predicting BDMAP_A0000787 +2025-11-14 17:51:10.506772: BDMAP_A0000787, shape torch.Size([1, 512, 707, 482]), rank 0 +2025-11-14 17:54:14.217346: predicting BDMAP_A0000788 +2025-11-14 17:54:14.290836: BDMAP_A0000788, shape torch.Size([1, 512, 507, 436]), rank 0 +2025-11-14 17:55:57.101414: predicting BDMAP_A0000789 +2025-11-14 17:55:57.168059: BDMAP_A0000789, shape torch.Size([1, 512, 586, 429]), rank 0 +2025-11-14 17:57:39.484759: predicting BDMAP_A0000790 +2025-11-14 17:57:39.550849: BDMAP_A0000790, shape torch.Size([1, 512, 585, 422]), rank 0 +2025-11-14 17:59:26.099065: predicting BDMAP_A0000791 +2025-11-14 17:59:26.175071: BDMAP_A0000791, shape torch.Size([1, 512, 512, 385]), rank 0 +2025-11-14 18:01:09.717502: predicting BDMAP_A0000792 +2025-11-14 18:01:09.796989: BDMAP_A0000792, shape torch.Size([1, 512, 588, 423]), rank 0 +2025-11-14 18:02:53.568188: predicting BDMAP_A0000793 +2025-11-14 18:02:53.640319: BDMAP_A0000793, shape torch.Size([1, 512, 563, 444]), rank 0 +2025-11-14 18:04:38.102526: predicting BDMAP_A0000794 +2025-11-14 18:04:38.178859: BDMAP_A0000794, shape torch.Size([1, 512, 586, 415]), rank 0 +2025-11-14 18:06:20.488789: predicting BDMAP_A0000795 +2025-11-14 18:06:20.566944: BDMAP_A0000795, shape torch.Size([1, 512, 598, 421]), rank 0 +2025-11-14 18:08:06.431316: predicting BDMAP_A0000796 +2025-11-14 18:08:06.498564: BDMAP_A0000796, shape torch.Size([1, 512, 546, 535]), rank 0 +2025-11-14 18:09:50.201828: predicting BDMAP_A0000797 +2025-11-14 18:09:50.285722: BDMAP_A0000797, shape torch.Size([1, 512, 527, 535]), rank 0 +2025-11-14 18:11:33.351014: predicting BDMAP_A0000798 +2025-11-14 18:11:33.427069: BDMAP_A0000798, shape torch.Size([1, 512, 650, 544]), rank 0 +2025-11-14 18:14:35.427021: predicting BDMAP_A0000799 +2025-11-14 18:14:35.506423: BDMAP_A0000799, shape torch.Size([1, 512, 505, 430]), rank 0 +2025-11-14 18:16:18.079156: predicting BDMAP_A0000800 +2025-11-14 18:16:18.142266: BDMAP_A0000800, shape torch.Size([1, 512, 645, 513]), rank 0 +2025-11-14 18:19:19.489369: predicting BDMAP_A0000801 +2025-11-14 18:19:19.562026: BDMAP_A0000801, shape torch.Size([1, 512, 521, 460]), rank 0 +2025-11-14 18:21:03.399328: predicting BDMAP_A0000802 +2025-11-14 18:21:03.466957: BDMAP_A0000802, shape torch.Size([1, 512, 606, 488]), rank 0 +2025-11-14 18:22:48.391660: predicting BDMAP_A0000803 +2025-11-14 18:22:48.470003: BDMAP_A0000803, shape torch.Size([1, 512, 600, 449]), rank 0 +2025-11-14 18:24:33.662939: predicting BDMAP_A0000804 +2025-11-14 18:24:33.723543: BDMAP_A0000804, shape torch.Size([1, 512, 556, 474]), rank 0 +2025-11-14 18:26:17.708066: predicting BDMAP_A0000805 +2025-11-14 18:26:17.788775: BDMAP_A0000805, shape torch.Size([1, 512, 642, 499]), rank 0 +2025-11-14 18:29:19.819881: predicting BDMAP_A0000806 +2025-11-14 18:29:19.891047: BDMAP_A0000806, shape torch.Size([1, 512, 647, 526]), rank 0 +2025-11-14 18:32:19.695242: predicting BDMAP_A0000807 +2025-11-14 18:32:19.772128: BDMAP_A0000807, shape torch.Size([1, 512, 582, 447]), rank 0 +2025-11-14 18:34:07.531389: predicting BDMAP_A0000808 +2025-11-14 18:34:07.592729: BDMAP_A0000808, shape torch.Size([1, 512, 537, 460]), rank 0 +2025-11-14 18:35:51.721221: predicting BDMAP_A0000809 +2025-11-14 18:35:52.308893: BDMAP_A0000809, shape torch.Size([1, 512, 621, 539]), rank 0 diff --git a/Dataset809_AbdomenAtlasF17/nnUNetTrainer__nnUNetResEncUNetLPlans__2d/plans.json b/Dataset809_AbdomenAtlasF17/nnUNetTrainer__nnUNetResEncUNetLPlans__2d/plans.json new file mode 100644 index 0000000000000000000000000000000000000000..6a454377902d2dc1d2629a9bf5d73e8c3d812623 --- /dev/null +++ b/Dataset809_AbdomenAtlasF17/nnUNetTrainer__nnUNetResEncUNetLPlans__2d/plans.json @@ -0,0 +1,532 @@ +{ + "dataset_name": "Dataset809_AbdomenAtlasF17", + "plans_name": "nnUNetResEncUNetLPlans", + "original_median_spacing_after_transp": [ + 0.7109375, + 0.5, + 0.7109375 + ], + "original_median_shape_after_transp": [ + 512, + 608, + 512 + ], + "image_reader_writer": "SimpleITKIO", + "transpose_forward": [ + 1, + 0, + 2 + ], + "transpose_backward": [ + 1, + 0, + 2 + ], + "configurations": { + "2d": { + "data_identifier": "nnUNetPlans_2d", + "preprocessor_name": "DefaultPreprocessor", + "batch_size": 22, + "patch_size": [ + 640, + 640 + ], + "median_image_size_in_voxels": [ + 613.0, + 513.0 + ], + "spacing": [ + 0.5, + 0.7109375 + ], + "normalization_schemes": [ + "CTNormalization" + ], + "use_mask_for_norm": [ + false + ], + "resampling_fn_data": "resample_data_or_seg_to_shape", + "resampling_fn_seg": "resample_data_or_seg_to_shape", + "resampling_fn_data_kwargs": { + "is_seg": false, + "order": 3, + "order_z": 0, + "force_separate_z": null + }, + "resampling_fn_seg_kwargs": { + "is_seg": true, + "order": 1, + "order_z": 0, + "force_separate_z": null + }, + "resampling_fn_probabilities": "resample_data_or_seg_to_shape", + "resampling_fn_probabilities_kwargs": { + "is_seg": false, + "order": 1, + "order_z": 0, + "force_separate_z": null + }, + "architecture": { + "network_class_name": "dynamic_network_architectures.architectures.unet.ResidualEncoderUNet", + "arch_kwargs": { + "n_stages": 8, + "features_per_stage": [ + 32, + 64, + 128, + 256, + 512, + 512, + 512, + 512 + ], + "conv_op": "torch.nn.modules.conv.Conv2d", + "kernel_sizes": [ + [ + 3, + 3 + ], + [ + 3, + 3 + ], + [ + 3, + 3 + ], + [ + 3, + 3 + ], + [ + 3, + 3 + ], + [ + 3, + 3 + ], + [ + 3, + 3 + ], + [ + 3, + 3 + ] + ], + "strides": [ + [ + 1, + 1 + ], + [ + 2, + 2 + ], + [ + 2, + 2 + ], + [ + 2, + 2 + ], + [ + 2, + 2 + ], + [ + 2, + 2 + ], + [ + 2, + 2 + ], + [ + 2, + 2 + ] + ], + "n_blocks_per_stage": [ + 1, + 3, + 4, + 6, + 6, + 6, + 6, + 6 + ], + "n_conv_per_stage_decoder": [ + 1, + 1, + 1, + 1, + 1, + 1, + 1 + ], + "conv_bias": true, + "norm_op": "torch.nn.modules.instancenorm.InstanceNorm2d", + "norm_op_kwargs": { + "eps": 1e-05, + "affine": true + }, + "dropout_op": null, + "dropout_op_kwargs": null, + "nonlin": "torch.nn.LeakyReLU", + "nonlin_kwargs": { + "inplace": true + } + }, + "_kw_requires_import": [ + "conv_op", + "norm_op", + "dropout_op", + "nonlin" + ] + }, + "batch_dice": true + }, + "3d_lowres": { + "data_identifier": "nnUNetResEncUNetLPlans_3d_lowres", + "preprocessor_name": "DefaultPreprocessor", + "batch_size": 2, + "patch_size": [ + 160, + 224, + 192 + ], + "median_image_size_in_voxels": [ + 283, + 339, + 284 + ], + "spacing": [ + 1.284032205897787, + 0.9030556173347075, + 1.284032205897787 + ], + "normalization_schemes": [ + "CTNormalization" + ], + "use_mask_for_norm": [ + false + ], + "resampling_fn_data": "resample_data_or_seg_to_shape", + "resampling_fn_seg": "resample_data_or_seg_to_shape", + "resampling_fn_data_kwargs": { + "is_seg": false, + "order": 3, + "order_z": 0, + "force_separate_z": null + }, + "resampling_fn_seg_kwargs": { + "is_seg": true, + "order": 1, + "order_z": 0, + "force_separate_z": null + }, + "resampling_fn_probabilities": "resample_data_or_seg_to_shape", + "resampling_fn_probabilities_kwargs": { + "is_seg": false, + "order": 1, + "order_z": 0, + "force_separate_z": null + }, + "architecture": { + "network_class_name": "dynamic_network_architectures.architectures.unet.ResidualEncoderUNet", + "arch_kwargs": { + "n_stages": 6, + "features_per_stage": [ + 32, + 64, + 128, + 256, + 320, + 320 + ], + "conv_op": "torch.nn.modules.conv.Conv3d", + "kernel_sizes": [ + [ + 3, + 3, + 3 + ], + [ + 3, + 3, + 3 + ], + [ + 3, + 3, + 3 + ], + [ + 3, + 3, + 3 + ], + [ + 3, + 3, + 3 + ], + [ + 3, + 3, + 3 + ] + ], + "strides": [ + [ + 1, + 1, + 1 + ], + [ + 2, + 2, + 2 + ], + [ + 2, + 2, + 2 + ], + [ + 2, + 2, + 2 + ], + [ + 2, + 2, + 2 + ], + [ + 2, + 2, + 2 + ] + ], + "n_blocks_per_stage": [ + 1, + 3, + 4, + 6, + 6, + 6 + ], + "n_conv_per_stage_decoder": [ + 1, + 1, + 1, + 1, + 1 + ], + "conv_bias": true, + "norm_op": "torch.nn.modules.instancenorm.InstanceNorm3d", + "norm_op_kwargs": { + "eps": 1e-05, + "affine": true + }, + "dropout_op": null, + "dropout_op_kwargs": null, + "nonlin": "torch.nn.LeakyReLU", + "nonlin_kwargs": { + "inplace": true + } + }, + "_kw_requires_import": [ + "conv_op", + "norm_op", + "dropout_op", + "nonlin" + ] + }, + "batch_dice": false, + "next_stage": "3d_cascade_fullres" + }, + "3d_fullres": { + "data_identifier": "nnUNetPlans_3d_fullres", + "preprocessor_name": "DefaultPreprocessor", + "batch_size": 2, + "patch_size": [ + 160, + 224, + 192 + ], + "median_image_size_in_voxels": [ + 512.0, + 613.0, + 513.0 + ], + "spacing": [ + 0.7109375, + 0.5, + 0.7109375 + ], + "normalization_schemes": [ + "CTNormalization" + ], + "use_mask_for_norm": [ + false + ], + "resampling_fn_data": "resample_data_or_seg_to_shape", + "resampling_fn_seg": "resample_data_or_seg_to_shape", + "resampling_fn_data_kwargs": { + "is_seg": false, + "order": 3, + "order_z": 0, + "force_separate_z": null + }, + "resampling_fn_seg_kwargs": { + "is_seg": true, + "order": 1, + "order_z": 0, + "force_separate_z": null + }, + "resampling_fn_probabilities": "resample_data_or_seg_to_shape", + "resampling_fn_probabilities_kwargs": { + "is_seg": false, + "order": 1, + "order_z": 0, + "force_separate_z": null + }, + "architecture": { + "network_class_name": "dynamic_network_architectures.architectures.unet.ResidualEncoderUNet", + "arch_kwargs": { + "n_stages": 6, + "features_per_stage": [ + 32, + 64, + 128, + 256, + 320, + 320 + ], + "conv_op": "torch.nn.modules.conv.Conv3d", + "kernel_sizes": [ + [ + 3, + 3, + 3 + ], + [ + 3, + 3, + 3 + ], + [ + 3, + 3, + 3 + ], + [ + 3, + 3, + 3 + ], + [ + 3, + 3, + 3 + ], + [ + 3, + 3, + 3 + ] + ], + "strides": [ + [ + 1, + 1, + 1 + ], + [ + 2, + 2, + 2 + ], + [ + 2, + 2, + 2 + ], + [ + 2, + 2, + 2 + ], + [ + 2, + 2, + 2 + ], + [ + 2, + 2, + 2 + ] + ], + "n_blocks_per_stage": [ + 1, + 3, + 4, + 6, + 6, + 6 + ], + "n_conv_per_stage_decoder": [ + 1, + 1, + 1, + 1, + 1 + ], + "conv_bias": true, + "norm_op": "torch.nn.modules.instancenorm.InstanceNorm3d", + "norm_op_kwargs": { + "eps": 1e-05, + "affine": true + }, + "dropout_op": null, + "dropout_op_kwargs": null, + "nonlin": "torch.nn.LeakyReLU", + "nonlin_kwargs": { + "inplace": true + } + }, + "_kw_requires_import": [ + "conv_op", + "norm_op", + "dropout_op", + "nonlin" + ] + }, + "batch_dice": true + }, + "3d_cascade_fullres": { + "inherits_from": "3d_fullres", + "previous_stage": "3d_lowres" + } + }, + "experiment_planner_used": "nnUNetPlannerResEncL", + "label_manager": "LabelManager", + "foreground_intensity_properties_per_channel": { + "0": { + "max": 1000.0, + "mean": 39.68027877807617, + "median": 71.0, + "min": -1000.0, + "percentile_00_5": -1000.0, + "percentile_99_5": 379.0, + "std": 192.4669952392578 + } + } +} \ No newline at end of file diff --git a/Dataset809_AbdomenAtlasF17/nnUNetTrainer__nnUNetResEncUNetLPlans__3d_fullres/dataset.json b/Dataset809_AbdomenAtlasF17/nnUNetTrainer__nnUNetResEncUNetLPlans__3d_fullres/dataset.json new file mode 100644 index 0000000000000000000000000000000000000000..9f2938d4f2036ea8e2f707c46f59d7221f42eb16 --- /dev/null +++ b/Dataset809_AbdomenAtlasF17/nnUNetTrainer__nnUNetResEncUNetLPlans__3d_fullres/dataset.json @@ -0,0 +1,34 @@ +{ + "name": "JHH-Train-test", + "description": "3151 cases for training; 1958 cases for testing", + "reference": "ScaleMAI", + "licence": "CC-BY-SA 4.0", + "relase": "1.0 10/28/2024", + "tensorImageSize": "3D", + "labels": { + "background": 0, + "aorta": 1, + "adrenal_gland_left": 2, + "adrenal_gland_right": 3, + "celiac_aa": 4, + "colon": 5, + "duodenum": 6, + "gall_bladder": 7, + "postcava": 8, + "kidney_left": 9, + "kidney_right": 10, + "liver": 11, + "pancreas": 12, + "superior_mesenteric_artery": 13, + "intestine": 14, + "spleen": 15, + "renal_vein_left": 16, + "renal_vein_right": 17 + }, + "numTraining": 3151, + "numTest": 1958, + "file_ending": ".nii.gz", + "channel_names": { + "0": "CT" + } +} \ No newline at end of file diff --git a/Dataset809_AbdomenAtlasF17/nnUNetTrainer__nnUNetResEncUNetLPlans__3d_fullres/dataset_fingerprint.json b/Dataset809_AbdomenAtlasF17/nnUNetTrainer__nnUNetResEncUNetLPlans__3d_fullres/dataset_fingerprint.json new file mode 100644 index 0000000000000000000000000000000000000000..3d1c25963dacc9058ac9738afdb0da4304b43a4f --- /dev/null +++ b/Dataset809_AbdomenAtlasF17/nnUNetTrainer__nnUNetResEncUNetLPlans__3d_fullres/dataset_fingerprint.json @@ -0,0 +1,31528 @@ +{ + "foreground_intensity_properties_per_channel": { + "0": { + "max": 1000.0, + "mean": 39.68027877807617, + "median": 71.0, + "min": -1000.0, + "percentile_00_5": -1000.0, + "percentile_99_5": 379.0, + "std": 192.4669952392578 + } + }, + "median_relative_size_after_cropping": 1.0, + "shapes_after_crop": [ + [ + 541, + 512, + 512 + ], + [ + 523, + 512, + 512 + ], + [ + 547, + 512, + 512 + ], + [ + 437, + 512, + 512 + ], + [ + 582, + 512, + 512 + ], + [ + 595, + 512, + 512 + ], + [ + 472, + 512, + 512 + ], + [ + 879, + 512, + 512 + ], + [ + 522, + 512, + 512 + ], + [ + 606, + 512, + 512 + ], + [ + 620, + 512, + 512 + ], + [ + 549, + 512, + 512 + ], + [ + 817, + 512, + 512 + ], + [ + 504, + 512, + 512 + ], + [ + 470, + 512, + 512 + ], + [ + 565, + 512, + 512 + ], + [ + 490, + 512, + 512 + ], + [ + 772, + 512, + 512 + ], + [ + 579, + 512, + 512 + ], + [ + 561, + 512, + 512 + ], + [ + 485, + 512, + 512 + ], + [ + 371, + 512, + 512 + ], + [ + 697, + 512, + 512 + ], + [ + 409, + 512, + 512 + ], + [ + 553, + 512, + 512 + ], + [ + 557, + 512, + 512 + ], + [ + 589, + 512, + 512 + ], + [ + 416, + 512, + 512 + ], + [ + 481, + 512, + 512 + ], + [ + 498, + 512, + 512 + ], + [ + 453, + 512, + 512 + ], + [ + 436, + 512, + 512 + ], + [ + 581, + 512, + 512 + ], + [ + 485, + 512, + 512 + ], + [ + 545, + 512, + 512 + ], + [ + 553, + 512, + 512 + ], + [ + 621, + 512, + 512 + ], + [ + 470, + 512, + 512 + ], + [ + 855, + 512, + 512 + ], + [ + 423, + 512, + 512 + ], + [ + 443, + 512, + 512 + ], + [ + 542, + 512, + 512 + ], + [ + 602, + 512, + 512 + ], + [ + 453, + 512, + 512 + ], + [ + 453, + 512, + 512 + ], + [ + 491, + 512, + 512 + ], + [ + 581, + 512, + 512 + ], + [ + 553, + 512, + 512 + ], + [ + 535, + 512, + 512 + ], + [ + 885, + 512, + 512 + ], + [ + 581, + 512, + 512 + ], + [ + 581, + 512, + 512 + ], + [ + 521, + 512, + 512 + ], + [ + 853, + 512, + 512 + ], + [ + 536, + 512, + 512 + ], + [ + 557, + 512, + 512 + ], + [ + 882, + 512, + 512 + ], + [ + 462, + 512, + 512 + ], + [ + 601, + 512, + 512 + ], + [ + 431, + 512, + 512 + ], + [ + 585, + 512, + 512 + ], + [ + 525, + 512, + 512 + ], + [ + 542, + 512, + 512 + ], + [ + 549, + 512, + 512 + ], + [ + 493, + 512, + 512 + ], + [ + 598, + 512, + 512 + ], + [ + 505, + 512, + 512 + ], + [ + 437, + 512, + 512 + ], + [ + 630, + 512, + 512 + ], + [ + 450, + 512, + 512 + ], + [ + 524, + 512, + 512 + ], + [ + 497, + 512, + 512 + ], + [ + 464, + 512, + 512 + ], + [ + 577, + 512, + 512 + ], + [ + 505, + 512, + 512 + ], + [ + 462, + 512, + 512 + ], + [ + 570, + 512, + 512 + ], + [ + 586, + 512, + 512 + ], + [ + 557, + 512, + 512 + ], + [ + 525, + 512, + 512 + ], + [ + 485, + 512, + 512 + ], + [ + 565, + 512, + 512 + ], + [ + 429, + 512, + 512 + ], + [ + 553, + 512, + 512 + ], + [ + 450, + 512, + 512 + ], + [ + 561, + 512, + 512 + ], + [ + 472, + 512, + 512 + ], + [ + 805, + 512, + 512 + ], + [ + 525, + 512, + 512 + ], + [ + 572, + 512, + 512 + ], + [ + 959, + 512, + 512 + ], + [ + 559, + 512, + 512 + ], + [ + 481, + 512, + 512 + ], + [ + 552, + 512, + 512 + ], + [ + 510, + 512, + 512 + ], + [ + 449, + 512, + 512 + ], + [ + 663, + 512, + 512 + ], + [ + 609, + 512, + 512 + ], + [ + 432, + 512, + 512 + ], + [ + 534, + 512, + 512 + ], + [ + 523, + 512, + 512 + ], + [ + 521, + 512, + 512 + ], + [ + 461, + 512, + 512 + ], + [ + 453, + 512, + 512 + ], + [ + 431, + 512, + 512 + ], + [ + 521, + 512, + 512 + ], + [ + 521, + 512, + 512 + ], + [ + 498, + 512, + 512 + ], + [ + 490, + 512, + 512 + ], + [ + 461, + 512, + 512 + ], + [ + 639, + 512, + 512 + ], + [ + 514, + 512, + 512 + ], + [ + 547, + 512, + 512 + ], + [ + 883, + 512, + 512 + ], + [ + 471, + 512, + 512 + ], + [ + 491, + 512, + 512 + ], + [ + 429, + 512, + 512 + ], + [ + 1026, + 512, + 512 + ], + [ + 449, + 512, + 512 + ], + [ + 553, + 512, + 512 + ], + [ + 542, + 512, + 512 + ], + [ + 481, + 512, + 512 + ], + [ + 705, + 512, + 512 + ], + [ + 585, + 512, + 512 + ], + [ + 605, + 512, + 512 + ], + [ + 523, + 512, + 512 + ], + [ + 425, + 512, + 512 + ], + [ + 410, + 512, + 512 + ], + [ + 901, + 512, + 512 + ], + [ + 472, + 512, + 512 + ], + [ + 441, + 512, + 512 + ], + [ + 561, + 512, + 512 + ], + [ + 592, + 512, + 512 + ], + [ + 584, + 512, + 512 + ], + [ + 589, + 512, + 512 + ], + [ + 565, + 512, + 512 + ], + [ + 502, + 512, + 512 + ], + [ + 554, + 512, + 512 + ], + [ + 765, + 512, + 512 + ], + [ + 481, + 512, + 512 + ], + [ + 649, + 512, + 512 + ], + [ + 476, + 512, + 512 + ], + [ + 518, + 512, + 512 + ], + [ + 942, + 512, + 512 + ], + [ + 500, + 512, + 512 + ], + [ + 411, + 512, + 512 + ], + [ + 569, + 512, + 512 + ], + [ + 608, + 512, + 512 + ], + [ + 490, + 512, + 512 + ], + [ + 406, + 512, + 512 + ], + [ + 465, + 512, + 512 + ], + [ + 546, + 512, + 512 + ], + [ + 492, + 512, + 512 + ], + [ + 485, + 512, + 512 + ], + [ + 559, + 512, + 512 + ], + [ + 577, + 512, + 512 + ], + [ + 533, + 512, + 512 + ], + [ + 528, + 512, + 512 + ], + [ + 874, + 512, + 512 + ], + [ + 946, + 512, + 512 + ], + [ + 461, + 512, + 512 + ], + [ + 903, + 512, + 512 + ], + [ + 879, + 512, + 512 + ], + [ + 493, + 512, + 512 + ], + [ + 437, + 512, + 512 + ], + [ + 601, + 512, + 512 + ], + [ + 554, + 512, + 512 + ], + [ + 486, + 512, + 512 + ], + [ + 569, + 512, + 512 + ], + [ + 873, + 512, + 512 + ], + [ + 499, + 512, + 512 + ], + [ + 565, + 512, + 512 + ], + [ + 533, + 512, + 512 + ], + [ + 473, + 512, + 512 + ], + [ + 562, + 512, + 512 + ], + [ + 493, + 512, + 512 + ], + [ + 474, + 512, + 512 + ], + [ + 644, + 512, + 512 + ], + [ + 470, + 512, + 512 + ], + [ + 540, + 512, + 512 + ], + [ + 501, + 512, + 512 + ], + [ + 389, + 512, + 512 + ], + [ + 423, + 512, + 512 + ], + [ + 493, + 512, + 512 + ], + [ + 529, + 512, + 512 + ], + [ + 529, + 512, + 512 + ], + [ + 361, + 512, + 512 + ], + [ + 596, + 512, + 512 + ], + [ + 582, + 512, + 512 + ], + [ + 471, + 512, + 512 + ], + [ + 533, + 512, + 512 + ], + [ + 506, + 512, + 512 + ], + [ + 509, + 512, + 512 + ], + [ + 586, + 512, + 512 + ], + [ + 438, + 512, + 512 + ], + [ + 504, + 512, + 512 + ], + [ + 497, + 512, + 512 + ], + [ + 793, + 512, + 512 + ], + [ + 520, + 512, + 512 + ], + [ + 417, + 512, + 512 + ], + [ + 393, + 512, + 512 + ], + [ + 512, + 512, + 512 + ], + [ + 596, + 512, + 512 + ], + [ + 569, + 512, + 512 + ], + [ + 587, + 512, + 512 + ], + [ + 569, + 512, + 512 + ], + [ + 617, + 512, + 512 + ], + [ + 587, + 512, + 512 + ], + [ + 591, + 512, + 512 + ], + [ + 547, + 512, + 512 + ], + [ + 636, + 512, + 512 + ], + [ + 481, + 512, + 512 + ], + [ + 676, + 512, + 512 + ], + [ + 587, + 512, + 512 + ], + [ + 655, + 512, + 512 + ], + [ + 502, + 512, + 512 + ], + [ + 632, + 512, + 512 + ], + [ + 445, + 512, + 512 + ], + [ + 605, + 512, + 512 + ], + [ + 563, + 512, + 512 + ], + [ + 579, + 512, + 512 + ], + [ + 667, + 512, + 512 + ], + [ + 601, + 512, + 512 + ], + [ + 632, + 512, + 512 + ], + [ + 653, + 512, + 512 + ], + [ + 585, + 512, + 512 + ], + [ + 521, + 512, + 512 + ], + [ + 667, + 512, + 512 + ], + [ + 609, + 512, + 512 + ], + [ + 606, + 512, + 512 + ], + [ + 483, + 512, + 512 + ], + [ + 641, + 512, + 512 + ], + [ + 590, + 512, + 512 + ], + [ + 708, + 512, + 512 + ], + [ + 617, + 512, + 512 + ], + [ + 672, + 512, + 512 + ], + [ + 461, + 512, + 512 + ], + [ + 655, + 512, + 512 + ], + [ + 633, + 512, + 512 + ], + [ + 493, + 512, + 512 + ], + [ + 477, + 512, + 512 + ], + [ + 606, + 512, + 512 + ], + [ + 590, + 512, + 512 + ], + [ + 629, + 512, + 512 + ], + [ + 489, + 512, + 512 + ], + [ + 469, + 512, + 512 + ], + [ + 543, + 512, + 512 + ], + [ + 713, + 512, + 512 + ], + [ + 643, + 512, + 512 + ], + [ + 553, + 512, + 512 + ], + [ + 557, + 512, + 512 + ], + [ + 655, + 512, + 512 + ], + [ + 512, + 512, + 512 + ], + [ + 490, + 512, + 512 + ], + [ + 521, + 512, + 512 + ], + [ + 627, + 512, + 512 + ], + [ + 675, + 512, + 512 + ], + [ + 553, + 512, + 512 + ], + [ + 642, + 512, + 512 + ], + [ + 726, + 512, + 512 + ], + [ + 539, + 512, + 512 + ], + [ + 421, + 512, + 512 + ], + [ + 697, + 512, + 512 + ], + [ + 631, + 512, + 512 + ], + [ + 611, + 512, + 512 + ], + [ + 557, + 512, + 512 + ], + [ + 479, + 512, + 512 + ], + [ + 605, + 512, + 512 + ], + [ + 585, + 512, + 512 + ], + [ + 637, + 512, + 512 + ], + [ + 627, + 512, + 512 + ], + [ + 531, + 512, + 512 + ], + [ + 631, + 512, + 512 + ], + [ + 431, + 512, + 512 + ], + [ + 641, + 512, + 512 + ], + [ + 401, + 512, + 512 + ], + [ + 711, + 512, + 512 + ], + [ + 659, + 512, + 512 + ], + [ + 525, + 512, + 512 + ], + [ + 593, + 512, + 512 + ], + [ + 613, + 512, + 512 + ], + [ + 709, + 512, + 512 + ], + [ + 631, + 512, + 512 + ], + [ + 499, + 512, + 512 + ], + [ + 643, + 512, + 512 + ], + [ + 657, + 512, + 512 + ], + [ + 625, + 512, + 512 + ], + [ + 513, + 512, + 512 + ], + [ + 545, + 512, + 512 + ], + [ + 603, + 512, + 512 + ], + [ + 575, + 512, + 512 + ], + [ + 611, + 512, + 512 + ], + [ + 618, + 512, + 512 + ], + [ + 643, + 512, + 512 + ], + [ + 675, + 512, + 512 + ], + [ + 553, + 512, + 512 + ], + [ + 635, + 512, + 512 + ], + [ + 585, + 512, + 512 + ], + [ + 677, + 512, + 512 + ], + [ + 655, + 512, + 512 + ], + [ + 667, + 512, + 512 + ], + [ + 655, + 512, + 512 + ], + [ + 568, + 512, + 512 + ], + [ + 445, + 512, + 512 + ], + [ + 659, + 512, + 512 + ], + [ + 497, + 512, + 512 + ], + [ + 581, + 512, + 512 + ], + [ + 721, + 512, + 512 + ], + [ + 651, + 512, + 512 + ], + [ + 639, + 512, + 512 + ], + [ + 748, + 512, + 512 + ], + [ + 554, + 512, + 512 + ], + [ + 502, + 512, + 512 + ], + [ + 587, + 512, + 512 + ], + [ + 761, + 512, + 512 + ], + [ + 537, + 512, + 512 + ], + [ + 621, + 512, + 512 + ], + [ + 563, + 512, + 512 + ], + [ + 671, + 512, + 512 + ], + [ + 663, + 512, + 512 + ], + [ + 581, + 512, + 512 + ], + [ + 632, + 512, + 512 + ], + [ + 600, + 512, + 512 + ], + [ + 657, + 512, + 512 + ], + [ + 775, + 512, + 512 + ], + [ + 684, + 512, + 512 + ], + [ + 707, + 512, + 512 + ], + [ + 624, + 512, + 512 + ], + [ + 625, + 512, + 512 + ], + [ + 469, + 512, + 512 + ], + [ + 697, + 512, + 512 + ], + [ + 585, + 512, + 512 + ], + [ + 445, + 512, + 512 + ], + [ + 634, + 512, + 512 + ], + [ + 557, + 512, + 512 + ], + [ + 623, + 512, + 512 + ], + [ + 613, + 512, + 512 + ], + [ + 735, + 512, + 512 + ], + [ + 639, + 512, + 512 + ], + [ + 808, + 512, + 512 + ], + [ + 605, + 512, + 512 + ], + [ + 679, + 512, + 512 + ], + [ + 659, + 512, + 512 + ], + [ + 660, + 512, + 512 + ], + [ + 496, + 512, + 512 + ], + [ + 624, + 512, + 512 + ], + [ + 619, + 512, + 512 + ], + [ + 635, + 512, + 512 + ], + [ + 697, + 512, + 512 + ], + [ + 859, + 512, + 512 + ], + [ + 563, + 512, + 512 + ], + [ + 653, + 512, + 512 + ], + [ + 614, + 512, + 512 + ], + [ + 611, + 512, + 512 + ], + [ + 685, + 512, + 512 + ], + [ + 591, + 512, + 512 + ], + [ + 616, + 512, + 512 + ], + [ + 723, + 512, + 512 + ], + [ + 683, + 512, + 512 + ], + [ + 579, + 512, + 512 + ], + [ + 647, + 512, + 512 + ], + [ + 709, + 512, + 512 + ], + [ + 667, + 512, + 512 + ], + [ + 649, + 512, + 512 + ], + [ + 568, + 512, + 512 + ], + [ + 580, + 512, + 512 + ], + [ + 441, + 512, + 512 + ], + [ + 363, + 512, + 512 + ], + [ + 479, + 512, + 512 + ], + [ + 557, + 512, + 512 + ], + [ + 603, + 512, + 512 + ], + [ + 767, + 512, + 512 + ], + [ + 657, + 512, + 512 + ], + [ + 601, + 512, + 512 + ], + [ + 575, + 512, + 512 + ], + [ + 668, + 512, + 512 + ], + [ + 528, + 512, + 512 + ], + [ + 585, + 512, + 512 + ], + [ + 586, + 512, + 512 + ], + [ + 625, + 512, + 512 + ], + [ + 695, + 512, + 512 + ], + [ + 757, + 512, + 512 + ], + [ + 689, + 512, + 512 + ], + [ + 632, + 512, + 512 + ], + [ + 536, + 512, + 512 + ], + [ + 641, + 512, + 512 + ], + [ + 653, + 512, + 512 + ], + [ + 598, + 512, + 512 + ], + [ + 564, + 512, + 512 + ], + [ + 472, + 512, + 512 + ], + [ + 602, + 512, + 512 + ], + [ + 331, + 512, + 512 + ], + [ + 441, + 512, + 512 + ], + [ + 635, + 512, + 512 + ], + [ + 368, + 512, + 512 + ], + [ + 583, + 512, + 512 + ], + [ + 771, + 512, + 512 + ], + [ + 421, + 512, + 512 + ], + [ + 399, + 512, + 512 + ], + [ + 576, + 512, + 512 + ], + [ + 707, + 512, + 512 + ], + [ + 507, + 512, + 512 + ], + [ + 586, + 512, + 512 + ], + [ + 585, + 512, + 512 + ], + [ + 512, + 512, + 512 + ], + [ + 588, + 512, + 512 + ], + [ + 563, + 512, + 512 + ], + [ + 586, + 512, + 512 + ], + [ + 598, + 512, + 512 + ], + [ + 546, + 512, + 512 + ], + [ + 527, + 512, + 512 + ], + [ + 650, + 512, + 512 + ], + [ + 505, + 512, + 512 + ], + [ + 645, + 512, + 512 + ], + [ + 521, + 512, + 512 + ], + [ + 606, + 512, + 512 + ], + [ + 600, + 512, + 512 + ], + [ + 556, + 512, + 512 + ], + [ + 642, + 512, + 512 + ], + [ + 647, + 512, + 512 + ], + [ + 582, + 512, + 512 + ], + [ + 537, + 512, + 512 + ], + [ + 621, + 512, + 512 + ], + [ + 611, + 512, + 512 + ], + [ + 599, + 512, + 512 + ], + [ + 667, + 512, + 512 + ], + [ + 538, + 512, + 512 + ], + [ + 553, + 512, + 512 + ], + [ + 594, + 512, + 512 + ], + [ + 361, + 512, + 512 + ], + [ + 679, + 512, + 512 + ], + [ + 670, + 512, + 512 + ], + [ + 673, + 512, + 512 + ], + [ + 618, + 512, + 512 + ], + [ + 689, + 512, + 512 + ], + [ + 616, + 512, + 512 + ], + [ + 619, + 512, + 512 + ], + [ + 548, + 512, + 512 + ], + [ + 618, + 512, + 512 + ], + [ + 503, + 512, + 512 + ], + [ + 531, + 512, + 512 + ], + [ + 609, + 512, + 512 + ], + [ + 610, + 512, + 512 + ], + [ + 579, + 512, + 512 + ], + [ + 603, + 512, + 512 + ], + [ + 640, + 512, + 512 + ], + [ + 511, + 512, + 512 + ], + [ + 585, + 512, + 512 + ], + [ + 707, + 512, + 512 + ], + [ + 606, + 512, + 512 + ], + [ + 629, + 512, + 512 + ], + [ + 627, + 512, + 512 + ], + [ + 656, + 512, + 512 + ], + [ + 606, + 512, + 512 + ], + [ + 477, + 512, + 512 + ], + [ + 537, + 512, + 512 + ], + [ + 505, + 512, + 512 + ], + [ + 448, + 512, + 512 + ], + [ + 483, + 512, + 512 + ], + [ + 444, + 512, + 512 + ], + [ + 549, + 512, + 512 + ], + [ + 664, + 512, + 512 + ], + [ + 556, + 512, + 512 + ], + [ + 734, + 512, + 512 + ], + [ + 620, + 512, + 512 + ], + [ + 555, + 512, + 512 + ], + [ + 602, + 512, + 512 + ], + [ + 505, + 512, + 512 + ], + [ + 587, + 512, + 512 + ], + [ + 641, + 512, + 512 + ], + [ + 533, + 512, + 512 + ], + [ + 631, + 512, + 512 + ], + [ + 594, + 512, + 512 + ], + [ + 579, + 512, + 512 + ], + [ + 465, + 512, + 512 + ], + [ + 544, + 512, + 512 + ], + [ + 707, + 512, + 512 + ], + [ + 687, + 512, + 512 + ], + [ + 578, + 512, + 512 + ], + [ + 646, + 512, + 512 + ], + [ + 590, + 512, + 512 + ], + [ + 510, + 512, + 512 + ], + [ + 649, + 512, + 512 + ], + [ + 761, + 512, + 512 + ], + [ + 565, + 512, + 512 + ], + [ + 679, + 512, + 512 + ], + [ + 576, + 512, + 512 + ], + [ + 485, + 512, + 512 + ], + [ + 594, + 512, + 512 + ], + [ + 717, + 512, + 512 + ], + [ + 577, + 512, + 512 + ], + [ + 605, + 512, + 512 + ], + [ + 557, + 512, + 512 + ], + [ + 527, + 512, + 512 + ], + [ + 687, + 512, + 512 + ], + [ + 645, + 512, + 512 + ], + [ + 558, + 512, + 512 + ], + [ + 545, + 512, + 512 + ], + [ + 510, + 512, + 512 + ], + [ + 691, + 512, + 512 + ], + [ + 708, + 512, + 512 + ], + [ + 649, + 512, + 512 + ], + [ + 625, + 512, + 512 + ], + [ + 593, + 512, + 512 + ], + [ + 582, + 512, + 512 + ], + [ + 548, + 512, + 512 + ], + [ + 721, + 512, + 512 + ], + [ + 647, + 512, + 512 + ], + [ + 661, + 512, + 512 + ], + [ + 689, + 512, + 512 + ], + [ + 617, + 512, + 512 + ], + [ + 688, + 512, + 512 + ], + [ + 501, + 512, + 512 + ], + [ + 677, + 512, + 512 + ], + [ + 602, + 512, + 512 + ], + [ + 577, + 512, + 512 + ], + [ + 578, + 512, + 512 + ], + [ + 569, + 512, + 512 + ], + [ + 573, + 512, + 512 + ], + [ + 579, + 512, + 512 + ], + [ + 672, + 512, + 512 + ], + [ + 545, + 512, + 512 + ], + [ + 691, + 512, + 512 + ], + [ + 591, + 512, + 512 + ], + [ + 509, + 512, + 512 + ], + [ + 441, + 512, + 512 + ], + [ + 589, + 512, + 512 + ], + [ + 621, + 512, + 512 + ], + [ + 553, + 512, + 512 + ], + [ + 528, + 512, + 512 + ], + [ + 461, + 512, + 512 + ], + [ + 513, + 512, + 512 + ], + [ + 589, + 512, + 512 + ], + [ + 469, + 512, + 512 + ], + [ + 561, + 512, + 512 + ], + [ + 527, + 512, + 512 + ], + [ + 577, + 512, + 512 + ], + [ + 629, + 512, + 512 + ], + [ + 623, + 512, + 512 + ], + [ + 549, + 512, + 512 + ], + [ + 563, + 512, + 512 + ], + [ + 573, + 512, + 512 + ], + [ + 621, + 512, + 512 + ], + [ + 671, + 512, + 512 + ], + [ + 625, + 512, + 512 + ], + [ + 577, + 512, + 512 + ], + [ + 617, + 512, + 512 + ], + [ + 597, + 512, + 512 + ], + [ + 637, + 512, + 512 + ], + [ + 605, + 512, + 512 + ], + [ + 625, + 512, + 512 + ], + [ + 655, + 512, + 512 + ], + [ + 577, + 512, + 512 + ], + [ + 857, + 512, + 512 + ], + [ + 609, + 512, + 512 + ], + [ + 505, + 512, + 512 + ], + [ + 509, + 512, + 512 + ], + [ + 641, + 512, + 512 + ], + [ + 641, + 512, + 512 + ], + [ + 697, + 512, + 512 + ], + [ + 553, + 512, + 512 + ], + [ + 525, + 512, + 512 + ], + [ + 737, + 512, + 512 + ], + [ + 537, + 512, + 512 + ], + [ + 630, + 512, + 512 + ], + [ + 693, + 512, + 512 + ], + [ + 417, + 512, + 512 + ], + [ + 651, + 512, + 512 + ], + [ + 678, + 512, + 512 + ], + [ + 585, + 512, + 512 + ], + [ + 609, + 512, + 512 + ], + [ + 597, + 512, + 512 + ], + [ + 449, + 512, + 512 + ], + [ + 381, + 512, + 512 + ], + [ + 697, + 512, + 512 + ], + [ + 612, + 512, + 512 + ], + [ + 541, + 512, + 512 + ], + [ + 533, + 512, + 512 + ], + [ + 659, + 512, + 512 + ], + [ + 541, + 512, + 512 + ], + [ + 601, + 512, + 512 + ], + [ + 617, + 512, + 512 + ], + [ + 515, + 512, + 512 + ], + [ + 621, + 512, + 512 + ], + [ + 751, + 512, + 512 + ], + [ + 705, + 512, + 512 + ], + [ + 573, + 512, + 512 + ], + [ + 693, + 512, + 512 + ], + [ + 483, + 512, + 512 + ], + [ + 583, + 512, + 512 + ], + [ + 621, + 512, + 512 + ], + [ + 613, + 512, + 512 + ], + [ + 589, + 512, + 512 + ], + [ + 513, + 512, + 512 + ], + [ + 609, + 512, + 512 + ], + [ + 954, + 512, + 512 + ], + [ + 986, + 512, + 512 + ], + [ + 513, + 512, + 512 + ], + [ + 629, + 512, + 512 + ], + [ + 621, + 512, + 512 + ], + [ + 513, + 512, + 512 + ], + [ + 553, + 512, + 512 + ], + [ + 609, + 512, + 512 + ], + [ + 442, + 512, + 512 + ], + [ + 460, + 512, + 512 + ], + [ + 673, + 512, + 512 + ], + [ + 512, + 512, + 512 + ], + [ + 562, + 512, + 512 + ], + [ + 496, + 512, + 512 + ], + [ + 629, + 512, + 512 + ], + [ + 836, + 512, + 512 + ], + [ + 913, + 512, + 512 + ], + [ + 465, + 512, + 512 + ], + [ + 469, + 512, + 512 + ], + [ + 635, + 512, + 512 + ], + [ + 506, + 512, + 512 + ], + [ + 549, + 512, + 512 + ], + [ + 507, + 512, + 512 + ], + [ + 881, + 512, + 512 + ], + [ + 521, + 512, + 512 + ], + [ + 548, + 512, + 512 + ], + [ + 893, + 512, + 512 + ], + [ + 939, + 512, + 512 + ], + [ + 927, + 512, + 512 + ], + [ + 905, + 512, + 512 + ], + [ + 589, + 512, + 512 + ], + [ + 493, + 512, + 512 + ], + [ + 533, + 512, + 512 + ], + [ + 769, + 512, + 512 + ], + [ + 606, + 512, + 512 + ], + [ + 541, + 512, + 512 + ], + [ + 893, + 512, + 512 + ], + [ + 881, + 512, + 512 + ], + [ + 1201, + 512, + 512 + ], + [ + 1266, + 512, + 512 + ], + [ + 533, + 512, + 512 + ], + [ + 877, + 512, + 512 + ], + [ + 945, + 512, + 512 + ], + [ + 891, + 512, + 512 + ], + [ + 850, + 512, + 512 + ], + [ + 697, + 512, + 512 + ], + [ + 602, + 512, + 512 + ], + [ + 829, + 512, + 512 + ], + [ + 893, + 512, + 512 + ], + [ + 829, + 512, + 512 + ], + [ + 832, + 512, + 512 + ], + [ + 877, + 512, + 512 + ], + [ + 933, + 512, + 512 + ], + [ + 710, + 512, + 512 + ], + [ + 1012, + 512, + 512 + ], + [ + 1049, + 512, + 512 + ], + [ + 877, + 512, + 512 + ], + [ + 600, + 512, + 512 + ], + [ + 853, + 512, + 512 + ], + [ + 541, + 512, + 512 + ], + [ + 557, + 512, + 512 + ], + [ + 506, + 512, + 512 + ], + [ + 552, + 512, + 512 + ], + [ + 1360, + 512, + 512 + ], + [ + 865, + 512, + 512 + ], + [ + 717, + 512, + 512 + ], + [ + 851, + 512, + 512 + ], + [ + 1297, + 512, + 512 + ], + [ + 858, + 512, + 512 + ], + [ + 930, + 512, + 512 + ], + [ + 847, + 512, + 512 + ], + [ + 745, + 512, + 512 + ], + [ + 825, + 512, + 512 + ], + [ + 634, + 512, + 512 + ], + [ + 853, + 512, + 512 + ], + [ + 917, + 512, + 512 + ], + [ + 863, + 512, + 512 + ], + [ + 765, + 512, + 512 + ], + [ + 913, + 512, + 512 + ], + [ + 977, + 512, + 512 + ], + [ + 793, + 512, + 512 + ], + [ + 858, + 512, + 512 + ], + [ + 809, + 512, + 512 + ], + [ + 721, + 512, + 512 + ], + [ + 915, + 512, + 512 + ], + [ + 674, + 512, + 512 + ], + [ + 936, + 512, + 512 + ], + [ + 849, + 512, + 512 + ], + [ + 881, + 512, + 512 + ], + [ + 857, + 512, + 512 + ], + [ + 834, + 512, + 512 + ], + [ + 815, + 512, + 512 + ], + [ + 953, + 512, + 512 + ], + [ + 985, + 512, + 512 + ], + [ + 831, + 512, + 512 + ], + [ + 700, + 512, + 512 + ], + [ + 784, + 512, + 512 + ], + [ + 881, + 512, + 512 + ], + [ + 854, + 512, + 512 + ], + [ + 829, + 512, + 512 + ], + [ + 994, + 512, + 512 + ], + [ + 846, + 512, + 512 + ], + [ + 853, + 512, + 512 + ], + [ + 663, + 512, + 512 + ], + [ + 785, + 512, + 512 + ], + [ + 990, + 512, + 512 + ], + [ + 901, + 512, + 512 + ], + [ + 593, + 512, + 512 + ], + [ + 563, + 512, + 512 + ], + [ + 513, + 512, + 512 + ], + [ + 617, + 512, + 512 + ], + [ + 993, + 512, + 512 + ], + [ + 962, + 512, + 512 + ], + [ + 738, + 512, + 512 + ], + [ + 721, + 512, + 512 + ], + [ + 897, + 512, + 512 + ], + [ + 819, + 512, + 512 + ], + [ + 745, + 512, + 512 + ], + [ + 857, + 512, + 512 + ], + [ + 989, + 512, + 512 + ], + [ + 881, + 512, + 512 + ], + [ + 901, + 512, + 512 + ], + [ + 479, + 512, + 512 + ], + [ + 508, + 512, + 512 + ], + [ + 650, + 512, + 512 + ], + [ + 689, + 512, + 512 + ], + [ + 549, + 512, + 512 + ], + [ + 528, + 512, + 512 + ], + [ + 509, + 512, + 512 + ], + [ + 974, + 512, + 512 + ], + [ + 621, + 512, + 512 + ], + [ + 887, + 512, + 512 + ], + [ + 607, + 512, + 512 + ], + [ + 473, + 512, + 512 + ], + [ + 873, + 512, + 512 + ], + [ + 528, + 512, + 512 + ], + [ + 931, + 512, + 512 + ], + [ + 876, + 512, + 512 + ], + [ + 881, + 512, + 512 + ], + [ + 685, + 512, + 512 + ], + [ + 552, + 512, + 512 + ], + [ + 896, + 512, + 512 + ], + [ + 883, + 512, + 512 + ], + [ + 900, + 512, + 512 + ], + [ + 837, + 512, + 512 + ], + [ + 873, + 512, + 512 + ], + [ + 865, + 512, + 512 + ], + [ + 565, + 512, + 512 + ], + [ + 1009, + 512, + 512 + ], + [ + 951, + 512, + 512 + ], + [ + 842, + 512, + 512 + ], + [ + 557, + 512, + 512 + ], + [ + 905, + 512, + 512 + ], + [ + 898, + 512, + 512 + ], + [ + 481, + 512, + 512 + ], + [ + 937, + 512, + 512 + ], + [ + 804, + 512, + 512 + ], + [ + 463, + 512, + 512 + ], + [ + 936, + 512, + 512 + ], + [ + 889, + 512, + 512 + ], + [ + 918, + 512, + 512 + ], + [ + 913, + 512, + 512 + ], + [ + 392, + 512, + 512 + ], + [ + 857, + 512, + 512 + ], + [ + 888, + 512, + 512 + ], + [ + 849, + 512, + 512 + ], + [ + 898, + 512, + 512 + ], + [ + 543, + 512, + 512 + ], + [ + 819, + 512, + 512 + ], + [ + 916, + 512, + 512 + ], + [ + 826, + 512, + 512 + ], + [ + 859, + 512, + 512 + ], + [ + 834, + 512, + 512 + ], + [ + 537, + 512, + 512 + ], + [ + 790, + 512, + 512 + ], + [ + 857, + 512, + 512 + ], + [ + 913, + 512, + 512 + ], + [ + 904, + 512, + 512 + ], + [ + 843, + 512, + 512 + ], + [ + 819, + 512, + 512 + ], + [ + 882, + 512, + 512 + ], + [ + 546, + 512, + 512 + ], + [ + 737, + 512, + 512 + ], + [ + 855, + 512, + 512 + ], + [ + 997, + 512, + 512 + ], + [ + 488, + 512, + 512 + ], + [ + 818, + 512, + 512 + ], + [ + 805, + 512, + 512 + ], + [ + 937, + 512, + 512 + ], + [ + 749, + 512, + 512 + ], + [ + 946, + 512, + 512 + ], + [ + 849, + 512, + 512 + ], + [ + 983, + 512, + 512 + ], + [ + 977, + 512, + 512 + ], + [ + 925, + 512, + 512 + ], + [ + 768, + 512, + 512 + ], + [ + 851, + 512, + 512 + ], + [ + 982, + 512, + 512 + ], + [ + 898, + 512, + 512 + ], + [ + 946, + 512, + 512 + ], + [ + 773, + 512, + 512 + ], + [ + 857, + 512, + 512 + ], + [ + 1008, + 512, + 512 + ], + [ + 931, + 512, + 512 + ], + [ + 877, + 512, + 512 + ], + [ + 882, + 512, + 512 + ], + [ + 889, + 512, + 512 + ], + [ + 951, + 512, + 512 + ], + [ + 521, + 512, + 512 + ], + [ + 881, + 512, + 512 + ], + [ + 602, + 512, + 512 + ], + [ + 889, + 512, + 512 + ], + [ + 888, + 512, + 512 + ], + [ + 1004, + 512, + 512 + ], + [ + 989, + 512, + 512 + ], + [ + 903, + 512, + 512 + ], + [ + 777, + 512, + 512 + ], + [ + 886, + 512, + 512 + ], + [ + 936, + 512, + 512 + ], + [ + 525, + 512, + 512 + ], + [ + 881, + 512, + 512 + ], + [ + 985, + 512, + 512 + ], + [ + 894, + 512, + 512 + ], + [ + 1016, + 512, + 512 + ], + [ + 979, + 512, + 512 + ], + [ + 626, + 512, + 512 + ], + [ + 876, + 512, + 512 + ], + [ + 917, + 512, + 512 + ], + [ + 897, + 512, + 512 + ], + [ + 791, + 512, + 512 + ], + [ + 903, + 512, + 512 + ], + [ + 865, + 512, + 512 + ], + [ + 877, + 512, + 512 + ], + [ + 485, + 512, + 512 + ], + [ + 481, + 512, + 512 + ], + [ + 453, + 512, + 512 + ], + [ + 889, + 512, + 512 + ], + [ + 553, + 512, + 512 + ], + [ + 910, + 512, + 512 + ], + [ + 1004, + 512, + 512 + ], + [ + 856, + 512, + 512 + ], + [ + 891, + 512, + 512 + ], + [ + 532, + 512, + 512 + ], + [ + 597, + 512, + 512 + ], + [ + 793, + 512, + 512 + ], + [ + 913, + 512, + 512 + ], + [ + 491, + 512, + 512 + ], + [ + 463, + 512, + 512 + ], + [ + 868, + 512, + 512 + ], + [ + 675, + 512, + 512 + ], + [ + 827, + 512, + 512 + ], + [ + 825, + 512, + 512 + ], + [ + 979, + 512, + 512 + ], + [ + 856, + 512, + 512 + ], + [ + 820, + 512, + 512 + ], + [ + 902, + 512, + 512 + ], + [ + 921, + 512, + 512 + ], + [ + 910, + 512, + 512 + ], + [ + 833, + 512, + 512 + ], + [ + 489, + 512, + 512 + ], + [ + 588, + 512, + 512 + ], + [ + 888, + 512, + 512 + ], + [ + 504, + 512, + 512 + ], + [ + 529, + 512, + 512 + ], + [ + 1013, + 512, + 512 + ], + [ + 849, + 512, + 512 + ], + [ + 450, + 512, + 512 + ], + [ + 889, + 512, + 512 + ], + [ + 575, + 512, + 512 + ], + [ + 941, + 512, + 512 + ], + [ + 855, + 512, + 512 + ], + [ + 863, + 512, + 512 + ], + [ + 882, + 512, + 512 + ], + [ + 931, + 512, + 512 + ], + [ + 496, + 512, + 512 + ], + [ + 484, + 512, + 512 + ], + [ + 929, + 512, + 512 + ], + [ + 830, + 512, + 512 + ], + [ + 898, + 512, + 512 + ], + [ + 596, + 512, + 512 + ], + [ + 1063, + 512, + 512 + ], + [ + 909, + 512, + 512 + ], + [ + 897, + 512, + 512 + ], + [ + 898, + 512, + 512 + ], + [ + 868, + 512, + 512 + ], + [ + 789, + 512, + 512 + ], + [ + 551, + 512, + 512 + ], + [ + 914, + 512, + 512 + ], + [ + 901, + 512, + 512 + ], + [ + 907, + 512, + 512 + ], + [ + 965, + 512, + 512 + ], + [ + 791, + 512, + 512 + ], + [ + 852, + 512, + 512 + ], + [ + 1007, + 512, + 512 + ], + [ + 778, + 512, + 512 + ], + [ + 914, + 512, + 512 + ], + [ + 916, + 512, + 512 + ], + [ + 934, + 512, + 512 + ], + [ + 848, + 512, + 512 + ], + [ + 461, + 512, + 512 + ], + [ + 553, + 512, + 512 + ], + [ + 557, + 512, + 512 + ], + [ + 521, + 512, + 512 + ], + [ + 982, + 512, + 512 + ], + [ + 839, + 512, + 512 + ], + [ + 819, + 512, + 512 + ], + [ + 865, + 512, + 512 + ], + [ + 792, + 512, + 512 + ], + [ + 455, + 512, + 512 + ], + [ + 830, + 512, + 512 + ], + [ + 575, + 512, + 512 + ], + [ + 904, + 512, + 512 + ], + [ + 975, + 512, + 512 + ], + [ + 849, + 512, + 512 + ], + [ + 541, + 512, + 512 + ], + [ + 807, + 512, + 512 + ], + [ + 881, + 512, + 512 + ], + [ + 551, + 512, + 512 + ], + [ + 865, + 512, + 512 + ], + [ + 845, + 512, + 512 + ], + [ + 559, + 512, + 512 + ], + [ + 881, + 512, + 512 + ], + [ + 916, + 512, + 512 + ], + [ + 917, + 512, + 512 + ], + [ + 891, + 512, + 512 + ], + [ + 897, + 512, + 512 + ], + [ + 947, + 512, + 512 + ], + [ + 461, + 512, + 512 + ], + [ + 850, + 512, + 512 + ], + [ + 896, + 512, + 512 + ], + [ + 478, + 512, + 512 + ], + [ + 899, + 512, + 512 + ], + [ + 586, + 512, + 512 + ], + [ + 489, + 512, + 512 + ], + [ + 528, + 512, + 512 + ], + [ + 842, + 512, + 512 + ], + [ + 575, + 512, + 512 + ], + [ + 884, + 512, + 512 + ], + [ + 881, + 512, + 512 + ], + [ + 447, + 512, + 512 + ], + [ + 957, + 512, + 512 + ], + [ + 562, + 512, + 512 + ], + [ + 764, + 512, + 512 + ], + [ + 509, + 512, + 512 + ], + [ + 884, + 512, + 512 + ], + [ + 562, + 512, + 512 + ], + [ + 880, + 512, + 512 + ], + [ + 533, + 512, + 512 + ], + [ + 517, + 512, + 512 + ], + [ + 541, + 512, + 512 + ], + [ + 517, + 512, + 512 + ], + [ + 934, + 512, + 512 + ], + [ + 585, + 512, + 512 + ], + [ + 437, + 512, + 512 + ], + [ + 793, + 512, + 512 + ], + [ + 629, + 512, + 512 + ], + [ + 1010, + 512, + 512 + ], + [ + 798, + 512, + 512 + ], + [ + 791, + 512, + 512 + ], + [ + 468, + 512, + 512 + ], + [ + 808, + 512, + 512 + ], + [ + 922, + 512, + 512 + ], + [ + 879, + 512, + 512 + ], + [ + 900, + 512, + 512 + ], + [ + 562, + 512, + 512 + ], + [ + 886, + 512, + 512 + ], + [ + 764, + 512, + 512 + ], + [ + 947, + 512, + 512 + ], + [ + 891, + 512, + 512 + ], + [ + 468, + 512, + 512 + ], + [ + 897, + 512, + 512 + ], + [ + 962, + 512, + 512 + ], + [ + 901, + 512, + 512 + ], + [ + 801, + 512, + 512 + ], + [ + 929, + 512, + 512 + ], + [ + 929, + 512, + 512 + ], + [ + 942, + 512, + 512 + ], + [ + 461, + 512, + 512 + ], + [ + 506, + 512, + 512 + ], + [ + 1049, + 512, + 512 + ], + [ + 829, + 512, + 512 + ], + [ + 471, + 512, + 512 + ], + [ + 874, + 512, + 512 + ], + [ + 957, + 512, + 512 + ], + [ + 893, + 512, + 512 + ], + [ + 826, + 512, + 512 + ], + [ + 678, + 512, + 512 + ], + [ + 940, + 512, + 512 + ], + [ + 514, + 512, + 512 + ], + [ + 530, + 512, + 512 + ], + [ + 517, + 512, + 512 + ], + [ + 1005, + 512, + 512 + ], + [ + 869, + 512, + 512 + ], + [ + 1034, + 512, + 512 + ], + [ + 537, + 512, + 512 + ], + [ + 1281, + 512, + 512 + ], + [ + 405, + 512, + 512 + ], + [ + 365, + 512, + 512 + ], + [ + 614, + 512, + 512 + ], + [ + 432, + 512, + 512 + ], + [ + 529, + 512, + 512 + ], + [ + 573, + 512, + 512 + ], + [ + 496, + 512, + 512 + ], + [ + 500, + 512, + 512 + ], + [ + 969, + 512, + 512 + ], + [ + 965, + 512, + 512 + ], + [ + 864, + 512, + 512 + ], + [ + 496, + 512, + 512 + ], + [ + 585, + 512, + 512 + ], + [ + 906, + 512, + 512 + ], + [ + 956, + 512, + 512 + ], + [ + 573, + 512, + 512 + ], + [ + 549, + 512, + 512 + ], + [ + 789, + 512, + 512 + ], + [ + 791, + 512, + 512 + ], + [ + 481, + 512, + 512 + ], + [ + 965, + 512, + 512 + ], + [ + 967, + 512, + 512 + ], + [ + 425, + 512, + 512 + ], + [ + 629, + 512, + 512 + ], + [ + 945, + 512, + 512 + ], + [ + 420, + 512, + 512 + ], + [ + 437, + 512, + 512 + ], + [ + 657, + 512, + 512 + ], + [ + 477, + 512, + 512 + ], + [ + 1001, + 512, + 512 + ], + [ + 506, + 512, + 512 + ], + [ + 515, + 512, + 512 + ], + [ + 437, + 512, + 512 + ], + [ + 411, + 512, + 512 + ], + [ + 587, + 512, + 512 + ], + [ + 849, + 512, + 512 + ], + [ + 950, + 512, + 512 + ], + [ + 611, + 512, + 512 + ], + [ + 933, + 512, + 512 + ], + [ + 853, + 512, + 512 + ], + [ + 447, + 512, + 512 + ], + [ + 561, + 512, + 512 + ], + [ + 512, + 512, + 512 + ], + [ + 876, + 512, + 512 + ], + [ + 550, + 512, + 512 + ], + [ + 482, + 512, + 512 + ], + [ + 484, + 512, + 512 + ], + [ + 552, + 512, + 512 + ], + [ + 518, + 512, + 512 + ], + [ + 562, + 512, + 512 + ], + [ + 869, + 512, + 512 + ], + [ + 491, + 512, + 512 + ], + [ + 791, + 512, + 512 + ], + [ + 961, + 512, + 512 + ], + [ + 560, + 512, + 512 + ], + [ + 925, + 512, + 512 + ], + [ + 468, + 512, + 512 + ], + [ + 1296, + 512, + 512 + ], + [ + 799, + 512, + 512 + ], + [ + 930, + 512, + 512 + ], + [ + 850, + 512, + 512 + ], + [ + 916, + 512, + 512 + ], + [ + 891, + 512, + 512 + ], + [ + 914, + 512, + 512 + ], + [ + 928, + 512, + 512 + ], + [ + 988, + 512, + 512 + ], + [ + 836, + 512, + 512 + ], + [ + 587, + 512, + 512 + ], + [ + 550, + 512, + 512 + ], + [ + 477, + 512, + 512 + ], + [ + 495, + 512, + 512 + ], + [ + 512, + 512, + 512 + ], + [ + 533, + 512, + 512 + ], + [ + 586, + 512, + 512 + ], + [ + 549, + 512, + 512 + ], + [ + 512, + 512, + 512 + ], + [ + 932, + 512, + 512 + ], + [ + 497, + 512, + 512 + ], + [ + 907, + 512, + 512 + ], + [ + 841, + 512, + 512 + ], + [ + 469, + 512, + 512 + ], + [ + 793, + 512, + 512 + ], + [ + 460, + 512, + 512 + ], + [ + 899, + 512, + 512 + ], + [ + 534, + 512, + 512 + ], + [ + 933, + 512, + 512 + ], + [ + 519, + 512, + 512 + ], + [ + 895, + 512, + 512 + ], + [ + 495, + 512, + 512 + ], + [ + 950, + 512, + 512 + ], + [ + 401, + 512, + 512 + ], + [ + 517, + 512, + 512 + ], + [ + 934, + 512, + 512 + ], + [ + 553, + 512, + 512 + ], + [ + 519, + 512, + 512 + ], + [ + 889, + 512, + 512 + ], + [ + 487, + 512, + 512 + ], + [ + 557, + 512, + 512 + ], + [ + 843, + 512, + 512 + ], + [ + 457, + 512, + 512 + ], + [ + 478, + 512, + 512 + ], + [ + 509, + 512, + 512 + ], + [ + 813, + 512, + 512 + ], + [ + 509, + 512, + 512 + ], + [ + 930, + 512, + 512 + ], + [ + 483, + 512, + 512 + ], + [ + 917, + 512, + 512 + ], + [ + 593, + 512, + 512 + ], + [ + 516, + 512, + 512 + ], + [ + 685, + 512, + 512 + ], + [ + 547, + 512, + 512 + ], + [ + 1066, + 512, + 512 + ], + [ + 741, + 512, + 512 + ], + [ + 486, + 512, + 512 + ], + [ + 481, + 512, + 512 + ], + [ + 502, + 512, + 512 + ], + [ + 613, + 512, + 512 + ], + [ + 925, + 512, + 512 + ], + [ + 994, + 512, + 512 + ], + [ + 985, + 512, + 512 + ], + [ + 860, + 512, + 512 + ], + [ + 949, + 512, + 512 + ], + [ + 855, + 512, + 512 + ], + [ + 542, + 512, + 512 + ], + [ + 956, + 512, + 512 + ], + [ + 477, + 512, + 512 + ], + [ + 917, + 512, + 512 + ], + [ + 504, + 512, + 512 + ], + [ + 945, + 512, + 512 + ], + [ + 529, + 512, + 512 + ], + [ + 865, + 512, + 512 + ], + [ + 466, + 512, + 512 + ], + [ + 523, + 512, + 512 + ], + [ + 789, + 512, + 512 + ], + [ + 885, + 512, + 512 + ], + [ + 902, + 512, + 512 + ], + [ + 848, + 512, + 512 + ], + [ + 931, + 512, + 512 + ], + [ + 518, + 512, + 512 + ], + [ + 897, + 512, + 512 + ], + [ + 665, + 512, + 512 + ], + [ + 517, + 512, + 512 + ], + [ + 469, + 512, + 512 + ], + [ + 430, + 512, + 512 + ], + [ + 469, + 512, + 512 + ], + [ + 901, + 512, + 512 + ], + [ + 431, + 512, + 512 + ], + [ + 377, + 512, + 512 + ], + [ + 813, + 512, + 512 + ], + [ + 890, + 512, + 512 + ], + [ + 886, + 512, + 512 + ], + [ + 953, + 512, + 512 + ], + [ + 589, + 512, + 512 + ], + [ + 869, + 512, + 512 + ], + [ + 953, + 512, + 512 + ], + [ + 782, + 512, + 512 + ], + [ + 803, + 512, + 512 + ], + [ + 568, + 512, + 512 + ], + [ + 525, + 512, + 512 + ], + [ + 926, + 512, + 512 + ], + [ + 869, + 512, + 512 + ], + [ + 881, + 512, + 512 + ], + [ + 615, + 512, + 512 + ], + [ + 957, + 512, + 512 + ], + [ + 397, + 512, + 512 + ], + [ + 537, + 512, + 512 + ], + [ + 857, + 512, + 512 + ], + [ + 857, + 512, + 512 + ], + [ + 465, + 512, + 512 + ], + [ + 548, + 512, + 512 + ], + [ + 661, + 512, + 512 + ], + [ + 597, + 512, + 512 + ], + [ + 949, + 512, + 512 + ], + [ + 969, + 512, + 512 + ], + [ + 415, + 512, + 512 + ], + [ + 559, + 512, + 512 + ], + [ + 528, + 512, + 512 + ], + [ + 753, + 512, + 512 + ], + [ + 598, + 512, + 512 + ], + [ + 461, + 512, + 512 + ], + [ + 889, + 512, + 512 + ], + [ + 645, + 512, + 512 + ], + [ + 981, + 512, + 512 + ], + [ + 889, + 512, + 512 + ], + [ + 514, + 512, + 512 + ], + [ + 929, + 512, + 512 + ], + [ + 597, + 512, + 512 + ], + [ + 952, + 512, + 512 + ], + [ + 1001, + 512, + 512 + ], + [ + 965, + 512, + 512 + ], + [ + 601, + 512, + 512 + ], + [ + 990, + 512, + 512 + ], + [ + 880, + 512, + 512 + ], + [ + 563, + 512, + 512 + ], + [ + 926, + 512, + 512 + ], + [ + 933, + 512, + 512 + ], + [ + 861, + 512, + 512 + ], + [ + 849, + 512, + 512 + ], + [ + 955, + 512, + 512 + ], + [ + 921, + 512, + 512 + ], + [ + 1021, + 512, + 512 + ], + [ + 930, + 512, + 512 + ], + [ + 585, + 512, + 512 + ], + [ + 876, + 512, + 512 + ], + [ + 534, + 512, + 512 + ], + [ + 859, + 512, + 512 + ], + [ + 673, + 512, + 512 + ], + [ + 912, + 512, + 512 + ], + [ + 533, + 512, + 512 + ], + [ + 893, + 512, + 512 + ], + [ + 930, + 512, + 512 + ], + [ + 460, + 512, + 512 + ], + [ + 886, + 512, + 512 + ], + [ + 439, + 512, + 512 + ], + [ + 856, + 512, + 512 + ], + [ + 982, + 512, + 512 + ], + [ + 526, + 512, + 512 + ], + [ + 844, + 512, + 512 + ], + [ + 484, + 512, + 512 + ], + [ + 593, + 512, + 512 + ], + [ + 441, + 512, + 512 + ], + [ + 530, + 512, + 512 + ], + [ + 981, + 512, + 512 + ], + [ + 446, + 512, + 512 + ], + [ + 545, + 512, + 512 + ], + [ + 861, + 512, + 512 + ], + [ + 953, + 512, + 512 + ], + [ + 501, + 512, + 512 + ], + [ + 564, + 512, + 512 + ], + [ + 981, + 512, + 512 + ], + [ + 459, + 512, + 512 + ], + [ + 681, + 512, + 512 + ], + [ + 897, + 512, + 512 + ], + [ + 669, + 512, + 512 + ], + [ + 789, + 512, + 512 + ], + [ + 505, + 512, + 512 + ], + [ + 561, + 512, + 512 + ], + [ + 890, + 512, + 512 + ], + [ + 861, + 512, + 512 + ], + [ + 649, + 512, + 512 + ], + [ + 485, + 512, + 512 + ], + [ + 923, + 512, + 512 + ], + [ + 448, + 512, + 512 + ], + [ + 1181, + 512, + 512 + ], + [ + 965, + 512, + 512 + ], + [ + 905, + 512, + 512 + ], + [ + 560, + 512, + 512 + ], + [ + 517, + 512, + 512 + ], + [ + 905, + 512, + 512 + ], + [ + 833, + 512, + 512 + ], + [ + 849, + 512, + 512 + ], + [ + 838, + 512, + 512 + ], + [ + 468, + 512, + 512 + ], + [ + 929, + 512, + 512 + ], + [ + 554, + 512, + 512 + ], + [ + 559, + 512, + 512 + ], + [ + 513, + 512, + 512 + ], + [ + 921, + 512, + 512 + ], + [ + 533, + 512, + 512 + ], + [ + 467, + 512, + 512 + ], + [ + 843, + 512, + 512 + ], + [ + 780, + 512, + 512 + ], + [ + 1044, + 512, + 512 + ], + [ + 965, + 512, + 512 + ], + [ + 858, + 512, + 512 + ], + [ + 997, + 512, + 512 + ], + [ + 984, + 512, + 512 + ], + [ + 663, + 512, + 512 + ], + [ + 562, + 512, + 512 + ], + [ + 924, + 512, + 512 + ], + [ + 883, + 512, + 512 + ], + [ + 982, + 512, + 512 + ], + [ + 902, + 512, + 512 + ], + [ + 507, + 512, + 512 + ], + [ + 909, + 512, + 512 + ], + [ + 905, + 512, + 512 + ], + [ + 747, + 512, + 512 + ], + [ + 621, + 512, + 512 + ], + [ + 409, + 512, + 512 + ], + [ + 513, + 512, + 512 + ], + [ + 505, + 512, + 512 + ], + [ + 813, + 512, + 512 + ], + [ + 838, + 512, + 512 + ], + [ + 554, + 512, + 512 + ], + [ + 852, + 512, + 512 + ], + [ + 418, + 512, + 512 + ], + [ + 562, + 512, + 512 + ], + [ + 761, + 512, + 512 + ], + [ + 430, + 512, + 512 + ], + [ + 829, + 512, + 512 + ], + [ + 493, + 512, + 512 + ], + [ + 526, + 512, + 512 + ], + [ + 533, + 512, + 512 + ], + [ + 799, + 512, + 512 + ], + [ + 510, + 512, + 512 + ], + [ + 941, + 512, + 512 + ], + [ + 525, + 512, + 512 + ], + [ + 903, + 512, + 512 + ], + [ + 1177, + 512, + 512 + ], + [ + 677, + 512, + 512 + ], + [ + 981, + 512, + 512 + ], + [ + 866, + 512, + 512 + ], + [ + 721, + 512, + 512 + ], + [ + 901, + 512, + 512 + ], + [ + 873, + 512, + 512 + ], + [ + 603, + 512, + 512 + ], + [ + 456, + 512, + 512 + ], + [ + 507, + 512, + 512 + ], + [ + 418, + 512, + 512 + ], + [ + 461, + 512, + 512 + ], + [ + 475, + 512, + 512 + ], + [ + 852, + 512, + 512 + ], + [ + 709, + 512, + 512 + ], + [ + 849, + 512, + 512 + ], + [ + 926, + 512, + 512 + ], + [ + 540, + 512, + 512 + ], + [ + 896, + 512, + 512 + ], + [ + 861, + 512, + 512 + ], + [ + 954, + 512, + 512 + ], + [ + 849, + 512, + 512 + ], + [ + 493, + 512, + 512 + ], + [ + 949, + 512, + 512 + ], + [ + 921, + 512, + 512 + ], + [ + 652, + 512, + 512 + ], + [ + 915, + 512, + 512 + ], + [ + 638, + 512, + 512 + ], + [ + 821, + 512, + 512 + ], + [ + 593, + 512, + 512 + ], + [ + 948, + 512, + 512 + ], + [ + 886, + 512, + 512 + ], + [ + 649, + 512, + 512 + ], + [ + 513, + 512, + 512 + ], + [ + 845, + 512, + 512 + ], + [ + 721, + 512, + 512 + ], + [ + 564, + 512, + 512 + ], + [ + 424, + 512, + 512 + ], + [ + 557, + 512, + 512 + ], + [ + 419, + 512, + 512 + ], + [ + 864, + 512, + 512 + ], + [ + 484, + 512, + 512 + ], + [ + 529, + 512, + 512 + ], + [ + 509, + 512, + 512 + ], + [ + 501, + 512, + 512 + ], + [ + 485, + 512, + 512 + ], + [ + 512, + 512, + 512 + ], + [ + 475, + 512, + 512 + ], + [ + 1001, + 512, + 512 + ], + [ + 896, + 512, + 512 + ], + [ + 470, + 512, + 512 + ], + [ + 877, + 512, + 512 + ], + [ + 942, + 512, + 512 + ], + [ + 953, + 512, + 512 + ], + [ + 570, + 512, + 512 + ], + [ + 893, + 512, + 512 + ], + [ + 988, + 512, + 512 + ], + [ + 785, + 512, + 512 + ], + [ + 596, + 512, + 512 + ], + [ + 538, + 512, + 512 + ], + [ + 1050, + 512, + 512 + ], + [ + 559, + 512, + 512 + ], + [ + 512, + 512, + 512 + ], + [ + 1074, + 512, + 512 + ], + [ + 505, + 512, + 512 + ], + [ + 825, + 512, + 512 + ], + [ + 426, + 512, + 512 + ], + [ + 573, + 512, + 512 + ], + [ + 914, + 512, + 512 + ], + [ + 564, + 512, + 512 + ], + [ + 578, + 512, + 512 + ], + [ + 442, + 512, + 512 + ], + [ + 870, + 512, + 512 + ], + [ + 488, + 512, + 512 + ], + [ + 1100, + 512, + 512 + ], + [ + 620, + 512, + 512 + ], + [ + 482, + 512, + 512 + ], + [ + 590, + 512, + 512 + ], + [ + 463, + 512, + 512 + ], + [ + 836, + 512, + 512 + ], + [ + 914, + 512, + 512 + ], + [ + 580, + 512, + 512 + ], + [ + 935, + 512, + 512 + ], + [ + 493, + 512, + 512 + ], + [ + 516, + 512, + 512 + ], + [ + 494, + 512, + 512 + ], + [ + 605, + 512, + 512 + ], + [ + 446, + 512, + 512 + ], + [ + 945, + 512, + 512 + ], + [ + 473, + 512, + 512 + ], + [ + 836, + 512, + 512 + ], + [ + 471, + 512, + 512 + ], + [ + 563, + 512, + 512 + ], + [ + 877, + 512, + 512 + ], + [ + 647, + 512, + 512 + ], + [ + 970, + 512, + 512 + ], + [ + 515, + 512, + 512 + ], + [ + 582, + 512, + 512 + ], + [ + 849, + 512, + 512 + ], + [ + 489, + 512, + 512 + ], + [ + 529, + 512, + 512 + ], + [ + 865, + 512, + 512 + ], + [ + 937, + 512, + 512 + ], + [ + 505, + 512, + 512 + ], + [ + 526, + 512, + 512 + ], + [ + 379, + 512, + 512 + ], + [ + 362, + 512, + 512 + ], + [ + 573, + 512, + 512 + ], + [ + 473, + 512, + 512 + ], + [ + 552, + 512, + 512 + ], + [ + 394, + 512, + 512 + ], + [ + 657, + 512, + 512 + ], + [ + 596, + 512, + 512 + ], + [ + 530, + 512, + 512 + ], + [ + 542, + 512, + 512 + ], + [ + 814, + 512, + 512 + ], + [ + 633, + 512, + 512 + ], + [ + 539, + 512, + 512 + ], + [ + 634, + 512, + 512 + ], + [ + 570, + 512, + 512 + ], + [ + 893, + 512, + 512 + ], + [ + 801, + 512, + 512 + ], + [ + 893, + 512, + 512 + ], + [ + 564, + 512, + 512 + ], + [ + 859, + 512, + 512 + ], + [ + 617, + 512, + 512 + ], + [ + 890, + 512, + 512 + ], + [ + 653, + 512, + 512 + ], + [ + 477, + 512, + 512 + ], + [ + 507, + 512, + 512 + ], + [ + 529, + 512, + 512 + ], + [ + 577, + 512, + 512 + ], + [ + 632, + 512, + 512 + ], + [ + 426, + 512, + 512 + ], + [ + 641, + 512, + 512 + ], + [ + 509, + 512, + 512 + ], + [ + 481, + 512, + 512 + ], + [ + 913, + 512, + 512 + ], + [ + 560, + 512, + 512 + ], + [ + 936, + 512, + 512 + ], + [ + 997, + 512, + 512 + ], + [ + 637, + 512, + 512 + ], + [ + 545, + 512, + 512 + ], + [ + 525, + 512, + 512 + ], + [ + 385, + 512, + 512 + ], + [ + 620, + 512, + 512 + ], + [ + 482, + 512, + 512 + ], + [ + 553, + 512, + 512 + ], + [ + 902, + 512, + 512 + ], + [ + 709, + 512, + 512 + ], + [ + 528, + 512, + 512 + ], + [ + 901, + 512, + 512 + ], + [ + 685, + 512, + 512 + ], + [ + 1007, + 512, + 512 + ], + [ + 415, + 512, + 512 + ], + [ + 601, + 512, + 512 + ], + [ + 618, + 512, + 512 + ], + [ + 885, + 512, + 512 + ], + [ + 561, + 512, + 512 + ], + [ + 833, + 512, + 512 + ], + [ + 497, + 512, + 512 + ], + [ + 581, + 512, + 512 + ], + [ + 559, + 512, + 512 + ], + [ + 505, + 512, + 512 + ], + [ + 871, + 512, + 512 + ], + [ + 628, + 512, + 512 + ], + [ + 594, + 512, + 512 + ], + [ + 609, + 512, + 512 + ], + [ + 493, + 512, + 512 + ], + [ + 601, + 512, + 512 + ], + [ + 541, + 512, + 512 + ], + [ + 493, + 512, + 512 + ], + [ + 545, + 512, + 512 + ], + [ + 553, + 512, + 512 + ], + [ + 511, + 512, + 512 + ], + [ + 613, + 512, + 512 + ], + [ + 509, + 512, + 512 + ], + [ + 582, + 512, + 512 + ], + [ + 596, + 512, + 512 + ], + [ + 341, + 512, + 512 + ], + [ + 425, + 512, + 512 + ], + [ + 990, + 512, + 512 + ], + [ + 630, + 512, + 512 + ], + [ + 496, + 512, + 512 + ], + [ + 497, + 512, + 512 + ], + [ + 501, + 512, + 512 + ], + [ + 573, + 512, + 512 + ], + [ + 473, + 512, + 512 + ], + [ + 449, + 512, + 512 + ], + [ + 506, + 512, + 512 + ], + [ + 533, + 512, + 512 + ], + [ + 521, + 512, + 512 + ], + [ + 438, + 512, + 512 + ], + [ + 689, + 512, + 512 + ], + [ + 537, + 512, + 512 + ], + [ + 633, + 512, + 512 + ], + [ + 449, + 512, + 512 + ], + [ + 608, + 512, + 512 + ], + [ + 934, + 512, + 512 + ], + [ + 542, + 512, + 512 + ], + [ + 453, + 512, + 512 + ], + [ + 565, + 512, + 512 + ], + [ + 601, + 512, + 512 + ], + [ + 883, + 512, + 512 + ], + [ + 513, + 512, + 512 + ], + [ + 505, + 512, + 512 + ], + [ + 585, + 512, + 512 + ], + [ + 533, + 512, + 512 + ], + [ + 509, + 512, + 512 + ], + [ + 457, + 512, + 512 + ], + [ + 555, + 512, + 512 + ], + [ + 452, + 512, + 512 + ], + [ + 425, + 512, + 512 + ], + [ + 560, + 512, + 512 + ], + [ + 831, + 512, + 512 + ], + [ + 497, + 512, + 512 + ], + [ + 593, + 512, + 512 + ], + [ + 625, + 512, + 512 + ], + [ + 537, + 512, + 512 + ], + [ + 487, + 512, + 512 + ], + [ + 508, + 512, + 512 + ], + [ + 993, + 512, + 512 + ], + [ + 601, + 512, + 512 + ], + [ + 506, + 512, + 512 + ], + [ + 596, + 512, + 512 + ], + [ + 617, + 512, + 512 + ], + [ + 431, + 512, + 512 + ], + [ + 485, + 512, + 512 + ], + [ + 555, + 512, + 512 + ], + [ + 511, + 512, + 512 + ], + [ + 516, + 512, + 512 + ], + [ + 492, + 512, + 512 + ], + [ + 525, + 512, + 512 + ], + [ + 511, + 512, + 512 + ], + [ + 575, + 512, + 512 + ], + [ + 815, + 512, + 512 + ], + [ + 429, + 512, + 512 + ], + [ + 589, + 512, + 512 + ], + [ + 521, + 512, + 512 + ], + [ + 461, + 512, + 512 + ], + [ + 449, + 512, + 512 + ], + [ + 559, + 512, + 512 + ], + [ + 676, + 512, + 512 + ], + [ + 461, + 512, + 512 + ], + [ + 493, + 512, + 512 + ], + [ + 435, + 512, + 512 + ], + [ + 573, + 512, + 512 + ], + [ + 820, + 512, + 512 + ], + [ + 921, + 512, + 512 + ], + [ + 897, + 512, + 512 + ], + [ + 833, + 512, + 512 + ], + [ + 865, + 512, + 512 + ], + [ + 988, + 512, + 512 + ], + [ + 467, + 512, + 512 + ], + [ + 605, + 512, + 512 + ], + [ + 877, + 512, + 512 + ], + [ + 460, + 512, + 512 + ], + [ + 796, + 512, + 512 + ], + [ + 965, + 512, + 512 + ], + [ + 535, + 512, + 512 + ], + [ + 527, + 512, + 512 + ], + [ + 453, + 512, + 512 + ], + [ + 463, + 512, + 512 + ], + [ + 645, + 512, + 512 + ], + [ + 723, + 512, + 512 + ], + [ + 1023, + 512, + 512 + ], + [ + 567, + 512, + 707 + ], + [ + 820, + 512, + 512 + ], + [ + 641, + 512, + 512 + ], + [ + 921, + 512, + 512 + ], + [ + 897, + 512, + 512 + ], + [ + 1177, + 512, + 512 + ], + [ + 509, + 512, + 512 + ], + [ + 864, + 512, + 512 + ], + [ + 718, + 512, + 512 + ], + [ + 965, + 512, + 512 + ], + [ + 942, + 512, + 512 + ], + [ + 466, + 512, + 512 + ], + [ + 537, + 512, + 512 + ], + [ + 546, + 512, + 512 + ], + [ + 999, + 512, + 512 + ], + [ + 421, + 512, + 512 + ], + [ + 651, + 512, + 512 + ], + [ + 403, + 512, + 512 + ], + [ + 575, + 512, + 512 + ], + [ + 581, + 512, + 512 + ], + [ + 842, + 512, + 512 + ], + [ + 546, + 512, + 512 + ], + [ + 912, + 512, + 512 + ], + [ + 550, + 512, + 512 + ], + [ + 499, + 512, + 512 + ], + [ + 918, + 512, + 512 + ], + [ + 793, + 512, + 512 + ], + [ + 1034, + 512, + 512 + ], + [ + 595, + 512, + 512 + ], + [ + 420, + 512, + 512 + ], + [ + 890, + 512, + 512 + ], + [ + 522, + 512, + 512 + ], + [ + 594, + 512, + 512 + ], + [ + 628, + 512, + 512 + ], + [ + 400, + 512, + 512 + ], + [ + 949, + 512, + 512 + ], + [ + 504, + 512, + 512 + ], + [ + 471, + 512, + 512 + ], + [ + 913, + 512, + 512 + ], + [ + 434, + 512, + 512 + ], + [ + 868, + 512, + 512 + ], + [ + 580, + 512, + 512 + ], + [ + 505, + 512, + 512 + ], + [ + 490, + 512, + 512 + ], + [ + 380, + 512, + 512 + ], + [ + 698, + 512, + 512 + ], + [ + 409, + 512, + 512 + ], + [ + 553, + 512, + 512 + ], + [ + 557, + 512, + 512 + ], + [ + 885, + 512, + 512 + ], + [ + 411, + 512, + 512 + ], + [ + 481, + 512, + 512 + ], + [ + 462, + 512, + 512 + ], + [ + 453, + 512, + 512 + ], + [ + 438, + 512, + 512 + ], + [ + 859, + 512, + 512 + ], + [ + 938, + 512, + 512 + ], + [ + 554, + 512, + 512 + ], + [ + 981, + 512, + 512 + ], + [ + 470, + 512, + 512 + ], + [ + 500, + 512, + 512 + ], + [ + 446, + 512, + 512 + ], + [ + 443, + 512, + 512 + ], + [ + 1050, + 512, + 512 + ], + [ + 929, + 512, + 512 + ], + [ + 465, + 512, + 512 + ], + [ + 795, + 512, + 512 + ], + [ + 581, + 512, + 512 + ], + [ + 889, + 512, + 512 + ], + [ + 511, + 512, + 512 + ], + [ + 505, + 512, + 512 + ], + [ + 581, + 512, + 512 + ], + [ + 580, + 512, + 512 + ], + [ + 521, + 512, + 512 + ], + [ + 808, + 512, + 512 + ], + [ + 776, + 512, + 512 + ], + [ + 929, + 512, + 512 + ], + [ + 961, + 512, + 512 + ], + [ + 800, + 512, + 512 + ], + [ + 955, + 512, + 512 + ], + [ + 431, + 512, + 512 + ], + [ + 585, + 512, + 512 + ], + [ + 525, + 512, + 512 + ], + [ + 547, + 512, + 512 + ], + [ + 457, + 512, + 512 + ], + [ + 893, + 512, + 512 + ], + [ + 505, + 512, + 512 + ], + [ + 441, + 512, + 512 + ], + [ + 630, + 512, + 512 + ], + [ + 463, + 512, + 512 + ], + [ + 544, + 512, + 512 + ], + [ + 504, + 512, + 512 + ], + [ + 468, + 512, + 512 + ], + [ + 1010, + 512, + 512 + ], + [ + 505, + 512, + 512 + ], + [ + 451, + 512, + 512 + ], + [ + 525, + 512, + 512 + ], + [ + 586, + 512, + 512 + ], + [ + 557, + 512, + 512 + ], + [ + 457, + 512, + 512 + ], + [ + 486, + 512, + 512 + ], + [ + 957, + 512, + 512 + ], + [ + 432, + 512, + 512 + ], + [ + 553, + 512, + 512 + ], + [ + 810, + 512, + 512 + ], + [ + 873, + 512, + 512 + ], + [ + 480, + 512, + 512 + ], + [ + 821, + 512, + 512 + ], + [ + 537, + 512, + 512 + ], + [ + 905, + 512, + 512 + ], + [ + 953, + 512, + 512 + ], + [ + 559, + 512, + 512 + ], + [ + 857, + 512, + 512 + ], + [ + 552, + 512, + 512 + ], + [ + 510, + 512, + 512 + ], + [ + 427, + 512, + 512 + ], + [ + 1099, + 512, + 512 + ], + [ + 607, + 512, + 512 + ], + [ + 419, + 512, + 512 + ], + [ + 534, + 512, + 512 + ], + [ + 523, + 512, + 512 + ], + [ + 521, + 512, + 512 + ], + [ + 769, + 512, + 512 + ], + [ + 453, + 512, + 512 + ], + [ + 431, + 512, + 512 + ], + [ + 521, + 512, + 512 + ], + [ + 521, + 512, + 512 + ], + [ + 462, + 512, + 512 + ], + [ + 490, + 512, + 512 + ], + [ + 461, + 512, + 512 + ], + [ + 639, + 512, + 512 + ], + [ + 904, + 512, + 512 + ], + [ + 921, + 512, + 512 + ], + [ + 477, + 512, + 512 + ], + [ + 471, + 512, + 512 + ], + [ + 499, + 512, + 512 + ], + [ + 419, + 512, + 512 + ], + [ + 678, + 512, + 512 + ], + [ + 449, + 512, + 512 + ], + [ + 553, + 512, + 512 + ], + [ + 542, + 512, + 512 + ], + [ + 481, + 512, + 512 + ], + [ + 705, + 512, + 512 + ], + [ + 585, + 512, + 512 + ], + [ + 605, + 512, + 512 + ], + [ + 523, + 512, + 512 + ], + [ + 425, + 512, + 512 + ], + [ + 417, + 512, + 512 + ], + [ + 847, + 512, + 512 + ], + [ + 420, + 512, + 512 + ], + [ + 441, + 512, + 512 + ], + [ + 893, + 512, + 512 + ], + [ + 989, + 512, + 512 + ], + [ + 918, + 512, + 512 + ], + [ + 937, + 512, + 512 + ], + [ + 519, + 512, + 512 + ], + [ + 502, + 512, + 512 + ], + [ + 925, + 512, + 512 + ], + [ + 516, + 512, + 512 + ], + [ + 942, + 512, + 512 + ], + [ + 574, + 512, + 512 + ], + [ + 476, + 512, + 512 + ], + [ + 518, + 512, + 512 + ], + [ + 991, + 512, + 512 + ], + [ + 500, + 512, + 512 + ], + [ + 411, + 512, + 512 + ], + [ + 597, + 512, + 512 + ], + [ + 608, + 512, + 512 + ], + [ + 490, + 512, + 512 + ], + [ + 394, + 512, + 512 + ], + [ + 841, + 512, + 512 + ], + [ + 962, + 512, + 512 + ], + [ + 806, + 512, + 512 + ], + [ + 485, + 512, + 512 + ], + [ + 559, + 512, + 512 + ], + [ + 577, + 512, + 512 + ], + [ + 912, + 512, + 512 + ], + [ + 917, + 512, + 512 + ], + [ + 528, + 512, + 512 + ], + [ + 999, + 512, + 512 + ], + [ + 589, + 512, + 512 + ], + [ + 469, + 512, + 512 + ], + [ + 1002, + 512, + 512 + ], + [ + 1013, + 512, + 512 + ], + [ + 905, + 512, + 512 + ], + [ + 465, + 512, + 512 + ], + [ + 953, + 512, + 512 + ], + [ + 525, + 512, + 512 + ], + [ + 504, + 512, + 512 + ], + [ + 597, + 512, + 512 + ], + [ + 827, + 512, + 512 + ], + [ + 569, + 512, + 512 + ], + [ + 497, + 512, + 512 + ], + [ + 471, + 512, + 512 + ], + [ + 493, + 512, + 512 + ], + [ + 465, + 512, + 512 + ], + [ + 636, + 512, + 512 + ], + [ + 468, + 512, + 512 + ], + [ + 479, + 512, + 512 + ], + [ + 501, + 512, + 512 + ], + [ + 456, + 512, + 512 + ], + [ + 443, + 512, + 512 + ], + [ + 504, + 512, + 512 + ], + [ + 529, + 512, + 512 + ], + [ + 538, + 512, + 512 + ], + [ + 389, + 512, + 512 + ], + [ + 515, + 512, + 512 + ], + [ + 575, + 512, + 512 + ], + [ + 457, + 512, + 512 + ], + [ + 497, + 512, + 512 + ], + [ + 524, + 512, + 512 + ], + [ + 509, + 512, + 512 + ], + [ + 588, + 512, + 512 + ], + [ + 831, + 512, + 512 + ], + [ + 504, + 512, + 512 + ], + [ + 500, + 512, + 512 + ], + [ + 785, + 512, + 512 + ], + [ + 535, + 512, + 512 + ], + [ + 417, + 512, + 512 + ], + [ + 393, + 512, + 512 + ], + [ + 520, + 512, + 512 + ], + [ + 425, + 512, + 512 + ], + [ + 401, + 512, + 512 + ], + [ + 425, + 512, + 512 + ], + [ + 427, + 512, + 512 + ], + [ + 437, + 512, + 512 + ], + [ + 395, + 512, + 512 + ], + [ + 469, + 512, + 512 + ], + [ + 469, + 512, + 512 + ], + [ + 449, + 512, + 512 + ], + [ + 345, + 512, + 512 + ], + [ + 506, + 512, + 512 + ], + [ + 391, + 512, + 512 + ], + [ + 458, + 512, + 512 + ], + [ + 333, + 512, + 512 + ], + [ + 632, + 512, + 512 + ], + [ + 635, + 512, + 512 + ], + [ + 605, + 512, + 512 + ], + [ + 417, + 512, + 512 + ], + [ + 579, + 512, + 512 + ], + [ + 493, + 512, + 512 + ], + [ + 467, + 512, + 512 + ], + [ + 502, + 512, + 512 + ], + [ + 798, + 512, + 512 + ], + [ + 447, + 512, + 512 + ], + [ + 346, + 512, + 512 + ], + [ + 531, + 512, + 512 + ], + [ + 435, + 512, + 512 + ], + [ + 606, + 512, + 512 + ], + [ + 327, + 512, + 512 + ], + [ + 397, + 512, + 512 + ], + [ + 465, + 512, + 512 + ], + [ + 469, + 512, + 512 + ], + [ + 447, + 512, + 512 + ], + [ + 858, + 512, + 512 + ], + [ + 569, + 512, + 512 + ], + [ + 473, + 512, + 512 + ], + [ + 841, + 512, + 512 + ], + [ + 921, + 512, + 512 + ], + [ + 805, + 512, + 512 + ], + [ + 773, + 512, + 512 + ], + [ + 332, + 512, + 512 + ], + [ + 873, + 512, + 512 + ], + [ + 823, + 512, + 512 + ], + [ + 842, + 512, + 512 + ], + [ + 415, + 512, + 512 + ], + [ + 555, + 512, + 512 + ], + [ + 441, + 512, + 512 + ], + [ + 438, + 512, + 512 + ], + [ + 430, + 512, + 512 + ], + [ + 391, + 512, + 512 + ], + [ + 501, + 512, + 512 + ], + [ + 590, + 512, + 512 + ], + [ + 851, + 512, + 512 + ], + [ + 501, + 512, + 512 + ], + [ + 373, + 512, + 512 + ], + [ + 476, + 512, + 512 + ], + [ + 473, + 512, + 512 + ], + [ + 379, + 512, + 512 + ], + [ + 821, + 512, + 512 + ], + [ + 551, + 512, + 512 + ], + [ + 405, + 512, + 512 + ], + [ + 456, + 512, + 512 + ], + [ + 561, + 512, + 512 + ], + [ + 493, + 512, + 512 + ], + [ + 435, + 512, + 512 + ], + [ + 391, + 512, + 512 + ], + [ + 361, + 512, + 512 + ], + [ + 443, + 512, + 512 + ], + [ + 495, + 512, + 512 + ], + [ + 447, + 512, + 512 + ], + [ + 441, + 512, + 512 + ], + [ + 393, + 512, + 512 + ], + [ + 423, + 512, + 512 + ], + [ + 573, + 512, + 512 + ], + [ + 471, + 512, + 512 + ], + [ + 412, + 512, + 512 + ], + [ + 481, + 512, + 512 + ], + [ + 447, + 512, + 512 + ], + [ + 441, + 512, + 512 + ], + [ + 423, + 512, + 512 + ], + [ + 511, + 512, + 512 + ], + [ + 765, + 512, + 512 + ], + [ + 551, + 512, + 512 + ], + [ + 457, + 512, + 512 + ], + [ + 379, + 512, + 512 + ], + [ + 481, + 512, + 512 + ], + [ + 369, + 512, + 512 + ], + [ + 389, + 512, + 512 + ], + [ + 407, + 512, + 512 + ], + [ + 447, + 512, + 512 + ], + [ + 452, + 512, + 512 + ], + [ + 441, + 512, + 512 + ], + [ + 425, + 512, + 512 + ], + [ + 466, + 512, + 512 + ], + [ + 433, + 512, + 512 + ], + [ + 500, + 512, + 512 + ], + [ + 441, + 512, + 512 + ], + [ + 470, + 512, + 512 + ], + [ + 423, + 512, + 512 + ], + [ + 515, + 512, + 512 + ], + [ + 525, + 512, + 512 + ], + [ + 491, + 512, + 512 + ], + [ + 458, + 512, + 512 + ], + [ + 407, + 512, + 512 + ], + [ + 719, + 512, + 512 + ], + [ + 485, + 512, + 512 + ], + [ + 417, + 512, + 512 + ], + [ + 359, + 512, + 512 + ], + [ + 559, + 512, + 512 + ], + [ + 495, + 512, + 512 + ], + [ + 453, + 512, + 512 + ], + [ + 510, + 512, + 512 + ], + [ + 392, + 512, + 512 + ], + [ + 333, + 512, + 512 + ], + [ + 736, + 512, + 512 + ], + [ + 539, + 512, + 512 + ], + [ + 543, + 512, + 512 + ], + [ + 443, + 512, + 512 + ], + [ + 417, + 512, + 512 + ], + [ + 467, + 512, + 512 + ], + [ + 497, + 512, + 512 + ], + [ + 407, + 512, + 512 + ], + [ + 459, + 512, + 512 + ], + [ + 632, + 512, + 512 + ], + [ + 437, + 512, + 512 + ], + [ + 485, + 512, + 512 + ], + [ + 539, + 512, + 512 + ], + [ + 482, + 512, + 512 + ], + [ + 541, + 512, + 512 + ], + [ + 458, + 512, + 512 + ], + [ + 423, + 512, + 512 + ], + [ + 371, + 512, + 512 + ], + [ + 621, + 512, + 512 + ], + [ + 801, + 512, + 512 + ], + [ + 635, + 512, + 512 + ], + [ + 466, + 512, + 512 + ], + [ + 435, + 512, + 512 + ], + [ + 477, + 512, + 512 + ], + [ + 499, + 512, + 512 + ], + [ + 565, + 512, + 512 + ], + [ + 784, + 512, + 512 + ], + [ + 966, + 512, + 512 + ], + [ + 605, + 512, + 512 + ], + [ + 506, + 512, + 512 + ], + [ + 505, + 512, + 512 + ], + [ + 351, + 512, + 512 + ], + [ + 512, + 512, + 512 + ], + [ + 521, + 512, + 512 + ], + [ + 441, + 512, + 512 + ], + [ + 857, + 512, + 512 + ], + [ + 417, + 512, + 512 + ], + [ + 431, + 512, + 512 + ], + [ + 425, + 512, + 512 + ], + [ + 491, + 512, + 512 + ], + [ + 433, + 512, + 512 + ], + [ + 815, + 512, + 512 + ], + [ + 412, + 512, + 512 + ], + [ + 546, + 512, + 512 + ], + [ + 521, + 512, + 512 + ], + [ + 579, + 512, + 512 + ], + [ + 481, + 512, + 512 + ], + [ + 564, + 512, + 512 + ], + [ + 493, + 512, + 512 + ], + [ + 430, + 512, + 512 + ], + [ + 568, + 512, + 512 + ], + [ + 455, + 512, + 512 + ], + [ + 844, + 512, + 512 + ], + [ + 654, + 512, + 512 + ], + [ + 645, + 512, + 512 + ], + [ + 471, + 512, + 512 + ], + [ + 481, + 512, + 512 + ], + [ + 767, + 512, + 512 + ], + [ + 519, + 512, + 512 + ], + [ + 467, + 512, + 512 + ], + [ + 458, + 512, + 512 + ], + [ + 571, + 512, + 512 + ], + [ + 898, + 512, + 512 + ], + [ + 415, + 512, + 512 + ], + [ + 463, + 512, + 512 + ], + [ + 485, + 512, + 512 + ], + [ + 565, + 512, + 512 + ], + [ + 587, + 512, + 512 + ], + [ + 597, + 512, + 512 + ], + [ + 502, + 512, + 512 + ], + [ + 423, + 512, + 512 + ], + [ + 518, + 512, + 512 + ], + [ + 798, + 512, + 512 + ], + [ + 441, + 512, + 512 + ], + [ + 399, + 512, + 512 + ], + [ + 463, + 512, + 512 + ], + [ + 574, + 512, + 512 + ], + [ + 389, + 512, + 512 + ], + [ + 554, + 512, + 512 + ], + [ + 631, + 512, + 512 + ], + [ + 461, + 512, + 512 + ], + [ + 584, + 512, + 512 + ], + [ + 438, + 512, + 512 + ], + [ + 609, + 512, + 512 + ], + [ + 607, + 512, + 512 + ], + [ + 712, + 512, + 512 + ], + [ + 355, + 512, + 512 + ], + [ + 549, + 512, + 512 + ], + [ + 443, + 512, + 512 + ], + [ + 461, + 512, + 512 + ], + [ + 447, + 512, + 512 + ], + [ + 327, + 512, + 512 + ], + [ + 418, + 512, + 512 + ], + [ + 367, + 512, + 512 + ], + [ + 345, + 512, + 512 + ], + [ + 341, + 512, + 512 + ], + [ + 378, + 512, + 512 + ], + [ + 538, + 512, + 512 + ], + [ + 485, + 512, + 512 + ], + [ + 360, + 512, + 512 + ], + [ + 474, + 512, + 512 + ], + [ + 403, + 512, + 512 + ], + [ + 449, + 512, + 512 + ], + [ + 513, + 512, + 512 + ], + [ + 404, + 512, + 512 + ], + [ + 396, + 512, + 512 + ], + [ + 401, + 512, + 512 + ], + [ + 423, + 512, + 512 + ], + [ + 433, + 512, + 512 + ], + [ + 424, + 512, + 512 + ], + [ + 452, + 512, + 512 + ], + [ + 531, + 512, + 512 + ], + [ + 435, + 512, + 512 + ], + [ + 815, + 512, + 512 + ], + [ + 785, + 512, + 512 + ], + [ + 746, + 512, + 512 + ], + [ + 569, + 512, + 512 + ], + [ + 442, + 512, + 512 + ], + [ + 450, + 512, + 512 + ], + [ + 475, + 512, + 512 + ], + [ + 484, + 512, + 512 + ], + [ + 539, + 512, + 512 + ], + [ + 493, + 512, + 512 + ], + [ + 358, + 512, + 512 + ], + [ + 844, + 512, + 512 + ], + [ + 843, + 512, + 512 + ], + [ + 581, + 512, + 512 + ], + [ + 734, + 512, + 512 + ], + [ + 435, + 512, + 512 + ], + [ + 422, + 512, + 512 + ], + [ + 417, + 512, + 512 + ], + [ + 431, + 512, + 512 + ], + [ + 336, + 512, + 512 + ], + [ + 768, + 512, + 512 + ], + [ + 463, + 512, + 512 + ], + [ + 565, + 512, + 512 + ], + [ + 606, + 512, + 512 + ], + [ + 756, + 512, + 512 + ], + [ + 812, + 512, + 512 + ], + [ + 475, + 512, + 512 + ], + [ + 606, + 512, + 512 + ], + [ + 363, + 512, + 512 + ], + [ + 929, + 512, + 512 + ], + [ + 1105, + 512, + 512 + ], + [ + 507, + 512, + 512 + ], + [ + 327, + 512, + 512 + ], + [ + 533, + 512, + 512 + ], + [ + 429, + 512, + 512 + ], + [ + 527, + 512, + 512 + ], + [ + 411, + 512, + 512 + ], + [ + 499, + 512, + 512 + ], + [ + 800, + 512, + 512 + ], + [ + 419, + 512, + 512 + ], + [ + 490, + 512, + 512 + ], + [ + 407, + 512, + 512 + ], + [ + 401, + 512, + 512 + ], + [ + 397, + 512, + 512 + ], + [ + 396, + 512, + 512 + ], + [ + 497, + 512, + 512 + ], + [ + 837, + 512, + 512 + ], + [ + 363, + 512, + 512 + ], + [ + 367, + 512, + 512 + ], + [ + 497, + 512, + 512 + ], + [ + 545, + 512, + 512 + ], + [ + 390, + 512, + 512 + ], + [ + 378, + 512, + 512 + ], + [ + 465, + 512, + 512 + ], + [ + 863, + 512, + 512 + ], + [ + 940, + 512, + 512 + ], + [ + 407, + 512, + 512 + ], + [ + 485, + 512, + 512 + ], + [ + 422, + 512, + 512 + ], + [ + 789, + 512, + 512 + ], + [ + 807, + 512, + 512 + ], + [ + 909, + 512, + 512 + ], + [ + 961, + 512, + 512 + ], + [ + 921, + 512, + 512 + ], + [ + 441, + 512, + 512 + ], + [ + 433, + 512, + 512 + ], + [ + 553, + 512, + 512 + ], + [ + 853, + 512, + 512 + ], + [ + 712, + 512, + 512 + ], + [ + 363, + 512, + 512 + ], + [ + 407, + 512, + 512 + ], + [ + 553, + 512, + 512 + ], + [ + 469, + 512, + 512 + ], + [ + 911, + 512, + 512 + ], + [ + 541, + 512, + 512 + ], + [ + 415, + 512, + 512 + ], + [ + 494, + 512, + 512 + ], + [ + 332, + 512, + 512 + ], + [ + 581, + 512, + 512 + ], + [ + 685, + 512, + 512 + ], + [ + 472, + 512, + 512 + ], + [ + 474, + 512, + 512 + ], + [ + 447, + 512, + 512 + ], + [ + 554, + 512, + 512 + ], + [ + 505, + 512, + 512 + ], + [ + 319, + 512, + 512 + ], + [ + 551, + 512, + 512 + ], + [ + 432, + 512, + 512 + ], + [ + 454, + 512, + 512 + ], + [ + 834, + 512, + 512 + ], + [ + 395, + 512, + 512 + ], + [ + 421, + 512, + 512 + ], + [ + 579, + 512, + 512 + ], + [ + 858, + 512, + 512 + ], + [ + 401, + 512, + 512 + ], + [ + 537, + 512, + 512 + ], + [ + 469, + 512, + 512 + ], + [ + 965, + 512, + 512 + ], + [ + 727, + 512, + 512 + ], + [ + 411, + 512, + 512 + ], + [ + 407, + 512, + 512 + ], + [ + 634, + 512, + 512 + ], + [ + 386, + 512, + 512 + ], + [ + 569, + 512, + 512 + ], + [ + 362, + 512, + 512 + ], + [ + 461, + 512, + 512 + ], + [ + 773, + 512, + 512 + ], + [ + 358, + 512, + 512 + ], + [ + 388, + 512, + 512 + ], + [ + 369, + 512, + 512 + ], + [ + 509, + 512, + 512 + ], + [ + 376, + 512, + 512 + ], + [ + 437, + 512, + 512 + ], + [ + 485, + 512, + 512 + ], + [ + 669, + 512, + 512 + ], + [ + 470, + 512, + 512 + ], + [ + 457, + 512, + 512 + ], + [ + 531, + 512, + 512 + ], + [ + 489, + 512, + 512 + ], + [ + 402, + 512, + 512 + ], + [ + 448, + 512, + 512 + ], + [ + 473, + 512, + 512 + ], + [ + 454, + 512, + 512 + ], + [ + 445, + 512, + 512 + ], + [ + 460, + 512, + 512 + ], + [ + 473, + 512, + 512 + ], + [ + 381, + 512, + 512 + ], + [ + 389, + 512, + 512 + ], + [ + 545, + 512, + 512 + ], + [ + 485, + 512, + 512 + ], + [ + 561, + 512, + 512 + ], + [ + 673, + 512, + 512 + ], + [ + 865, + 512, + 512 + ], + [ + 437, + 512, + 512 + ], + [ + 405, + 512, + 512 + ], + [ + 557, + 512, + 512 + ], + [ + 893, + 512, + 512 + ], + [ + 510, + 512, + 512 + ], + [ + 972, + 512, + 512 + ], + [ + 501, + 512, + 512 + ], + [ + 905, + 512, + 512 + ], + [ + 565, + 512, + 512 + ], + [ + 944, + 512, + 512 + ], + [ + 513, + 512, + 512 + ], + [ + 501, + 512, + 512 + ], + [ + 556, + 512, + 512 + ], + [ + 505, + 512, + 512 + ], + [ + 417, + 512, + 512 + ], + [ + 393, + 512, + 512 + ], + [ + 646, + 512, + 512 + ], + [ + 566, + 512, + 512 + ], + [ + 489, + 512, + 512 + ], + [ + 465, + 512, + 512 + ], + [ + 804, + 512, + 512 + ], + [ + 469, + 512, + 512 + ], + [ + 1022, + 512, + 512 + ], + [ + 473, + 512, + 512 + ], + [ + 409, + 512, + 512 + ], + [ + 537, + 512, + 512 + ], + [ + 928, + 512, + 512 + ], + [ + 816, + 512, + 512 + ], + [ + 453, + 512, + 512 + ], + [ + 441, + 512, + 512 + ], + [ + 453, + 512, + 512 + ], + [ + 517, + 512, + 512 + ], + [ + 473, + 512, + 512 + ], + [ + 547, + 512, + 512 + ], + [ + 537, + 512, + 512 + ], + [ + 513, + 512, + 512 + ], + [ + 629, + 512, + 512 + ], + [ + 565, + 512, + 512 + ], + [ + 513, + 512, + 512 + ], + [ + 476, + 512, + 512 + ], + [ + 553, + 512, + 512 + ], + [ + 442, + 512, + 512 + ], + [ + 448, + 512, + 512 + ], + [ + 498, + 512, + 512 + ], + [ + 512, + 512, + 512 + ], + [ + 819, + 512, + 512 + ], + [ + 726, + 512, + 512 + ], + [ + 505, + 512, + 512 + ], + [ + 487, + 512, + 512 + ], + [ + 519, + 512, + 512 + ], + [ + 465, + 512, + 512 + ], + [ + 469, + 512, + 512 + ], + [ + 635, + 512, + 512 + ], + [ + 500, + 512, + 512 + ], + [ + 549, + 512, + 512 + ], + [ + 397, + 512, + 512 + ], + [ + 765, + 512, + 512 + ], + [ + 786, + 512, + 512 + ], + [ + 919, + 512, + 512 + ], + [ + 529, + 512, + 512 + ], + [ + 504, + 512, + 512 + ], + [ + 559, + 512, + 512 + ], + [ + 537, + 512, + 512 + ], + [ + 589, + 512, + 512 + ], + [ + 454, + 512, + 512 + ], + [ + 454, + 512, + 512 + ], + [ + 777, + 512, + 512 + ], + [ + 606, + 512, + 512 + ], + [ + 731, + 512, + 512 + ], + [ + 553, + 512, + 512 + ], + [ + 557, + 512, + 512 + ], + [ + 628, + 512, + 512 + ], + [ + 511, + 512, + 512 + ], + [ + 533, + 512, + 512 + ], + [ + 481, + 512, + 512 + ], + [ + 640, + 512, + 512 + ], + [ + 500, + 512, + 512 + ], + [ + 494, + 512, + 512 + ], + [ + 587, + 512, + 512 + ], + [ + 446, + 512, + 512 + ], + [ + 506, + 512, + 512 + ], + [ + 505, + 512, + 512 + ], + [ + 536, + 512, + 512 + ], + [ + 476, + 512, + 512 + ], + [ + 573, + 512, + 512 + ], + [ + 539, + 512, + 512 + ], + [ + 466, + 512, + 512 + ], + [ + 657, + 512, + 512 + ], + [ + 653, + 512, + 512 + ], + [ + 573, + 512, + 512 + ], + [ + 435, + 512, + 512 + ], + [ + 423, + 512, + 512 + ], + [ + 541, + 512, + 512 + ], + [ + 557, + 512, + 512 + ], + [ + 506, + 512, + 512 + ], + [ + 552, + 512, + 512 + ], + [ + 512, + 512, + 512 + ], + [ + 539, + 512, + 512 + ], + [ + 561, + 512, + 512 + ], + [ + 480, + 512, + 512 + ], + [ + 496, + 512, + 512 + ], + [ + 501, + 512, + 512 + ], + [ + 596, + 512, + 512 + ], + [ + 454, + 512, + 512 + ], + [ + 429, + 512, + 512 + ], + [ + 458, + 512, + 512 + ], + [ + 432, + 512, + 512 + ], + [ + 493, + 512, + 512 + ], + [ + 564, + 512, + 512 + ], + [ + 518, + 512, + 512 + ], + [ + 555, + 512, + 512 + ], + [ + 493, + 512, + 512 + ], + [ + 585, + 512, + 512 + ], + [ + 456, + 512, + 512 + ], + [ + 486, + 512, + 512 + ], + [ + 445, + 512, + 512 + ], + [ + 618, + 512, + 512 + ], + [ + 585, + 512, + 512 + ], + [ + 522, + 512, + 512 + ], + [ + 548, + 512, + 512 + ], + [ + 529, + 512, + 512 + ], + [ + 517, + 512, + 512 + ], + [ + 533, + 512, + 512 + ], + [ + 457, + 512, + 512 + ], + [ + 582, + 512, + 512 + ], + [ + 557, + 512, + 512 + ], + [ + 607, + 512, + 512 + ], + [ + 427, + 512, + 512 + ], + [ + 481, + 512, + 512 + ], + [ + 474, + 512, + 512 + ], + [ + 517, + 512, + 512 + ], + [ + 446, + 512, + 512 + ], + [ + 535, + 512, + 512 + ], + [ + 557, + 512, + 512 + ], + [ + 475, + 512, + 512 + ], + [ + 525, + 512, + 512 + ], + [ + 618, + 512, + 512 + ], + [ + 529, + 512, + 512 + ], + [ + 536, + 512, + 512 + ], + [ + 529, + 512, + 512 + ], + [ + 593, + 512, + 512 + ], + [ + 555, + 512, + 512 + ], + [ + 513, + 512, + 512 + ], + [ + 617, + 512, + 512 + ], + [ + 650, + 512, + 512 + ], + [ + 518, + 512, + 512 + ], + [ + 550, + 512, + 512 + ], + [ + 503, + 512, + 512 + ], + [ + 505, + 512, + 512 + ], + [ + 420, + 512, + 512 + ], + [ + 482, + 512, + 512 + ], + [ + 509, + 512, + 512 + ], + [ + 540, + 512, + 512 + ], + [ + 531, + 512, + 512 + ], + [ + 491, + 512, + 512 + ], + [ + 740, + 512, + 512 + ], + [ + 508, + 512, + 512 + ], + [ + 422, + 512, + 512 + ], + [ + 525, + 512, + 512 + ], + [ + 549, + 512, + 512 + ], + [ + 532, + 512, + 512 + ], + [ + 403, + 512, + 512 + ], + [ + 592, + 512, + 512 + ], + [ + 1057, + 512, + 512 + ], + [ + 807, + 512, + 512 + ], + [ + 997, + 512, + 512 + ], + [ + 889, + 512, + 512 + ], + [ + 873, + 512, + 512 + ], + [ + 939, + 512, + 512 + ], + [ + 908, + 512, + 512 + ], + [ + 966, + 512, + 512 + ], + [ + 915, + 512, + 512 + ], + [ + 933, + 512, + 512 + ], + [ + 950, + 512, + 512 + ], + [ + 880, + 512, + 512 + ], + [ + 874, + 512, + 512 + ], + [ + 834, + 512, + 512 + ], + [ + 1085, + 512, + 512 + ], + [ + 896, + 512, + 512 + ], + [ + 943, + 512, + 512 + ], + [ + 1065, + 512, + 512 + ], + [ + 905, + 512, + 512 + ], + [ + 803, + 512, + 512 + ], + [ + 928, + 512, + 512 + ], + [ + 868, + 512, + 512 + ], + [ + 811, + 512, + 512 + ], + [ + 876, + 512, + 512 + ], + [ + 578, + 512, + 512 + ], + [ + 916, + 512, + 512 + ], + [ + 463, + 512, + 512 + ], + [ + 568, + 512, + 512 + ], + [ + 1225, + 512, + 512 + ], + [ + 892, + 512, + 512 + ], + [ + 1013, + 512, + 512 + ], + [ + 392, + 512, + 512 + ], + [ + 889, + 512, + 512 + ], + [ + 575, + 512, + 512 + ], + [ + 896, + 512, + 512 + ], + [ + 913, + 512, + 512 + ], + [ + 889, + 512, + 512 + ], + [ + 884, + 512, + 512 + ], + [ + 956, + 512, + 512 + ], + [ + 853, + 512, + 512 + ], + [ + 755, + 512, + 512 + ], + [ + 883, + 512, + 512 + ], + [ + 889, + 512, + 512 + ], + [ + 758, + 512, + 512 + ], + [ + 845, + 512, + 512 + ], + [ + 934, + 512, + 512 + ], + [ + 934, + 512, + 512 + ], + [ + 875, + 512, + 512 + ], + [ + 866, + 512, + 512 + ], + [ + 995, + 512, + 512 + ], + [ + 998, + 512, + 512 + ], + [ + 746, + 512, + 512 + ], + [ + 906, + 512, + 512 + ], + [ + 997, + 512, + 512 + ], + [ + 872, + 512, + 512 + ], + [ + 579, + 512, + 512 + ], + [ + 906, + 512, + 512 + ], + [ + 1022, + 512, + 512 + ], + [ + 705, + 512, + 512 + ], + [ + 877, + 512, + 512 + ], + [ + 917, + 512, + 512 + ], + [ + 986, + 512, + 512 + ], + [ + 972, + 512, + 512 + ], + [ + 684, + 512, + 512 + ], + [ + 824, + 512, + 512 + ], + [ + 1017, + 512, + 512 + ], + [ + 1899, + 512, + 512 + ], + [ + 575, + 512, + 512 + ], + [ + 1083, + 512, + 512 + ], + [ + 488, + 512, + 512 + ], + [ + 881, + 512, + 512 + ], + [ + 1092, + 512, + 512 + ], + [ + 961, + 512, + 512 + ], + [ + 867, + 512, + 512 + ], + [ + 860, + 512, + 512 + ], + [ + 972, + 512, + 512 + ], + [ + 905, + 512, + 512 + ], + [ + 869, + 512, + 512 + ], + [ + 910, + 512, + 512 + ], + [ + 1067, + 512, + 512 + ], + [ + 945, + 512, + 512 + ], + [ + 545, + 512, + 512 + ], + [ + 1037, + 512, + 512 + ], + [ + 986, + 512, + 512 + ], + [ + 950, + 512, + 512 + ], + [ + 937, + 512, + 512 + ], + [ + 829, + 512, + 512 + ], + [ + 568, + 512, + 512 + ], + [ + 973, + 512, + 512 + ], + [ + 881, + 512, + 512 + ], + [ + 937, + 512, + 512 + ], + [ + 558, + 512, + 512 + ], + [ + 999, + 512, + 512 + ], + [ + 1031, + 512, + 512 + ], + [ + 1030, + 512, + 512 + ], + [ + 583, + 512, + 512 + ], + [ + 940, + 512, + 512 + ], + [ + 950, + 512, + 512 + ], + [ + 792, + 512, + 512 + ], + [ + 857, + 512, + 512 + ], + [ + 967, + 512, + 512 + ], + [ + 867, + 512, + 512 + ], + [ + 793, + 512, + 512 + ], + [ + 869, + 512, + 512 + ], + [ + 430, + 512, + 512 + ], + [ + 909, + 512, + 512 + ], + [ + 987, + 512, + 512 + ], + [ + 942, + 512, + 512 + ], + [ + 954, + 512, + 512 + ], + [ + 862, + 512, + 512 + ], + [ + 1063, + 512, + 512 + ], + [ + 863, + 512, + 512 + ], + [ + 1037, + 512, + 512 + ], + [ + 827, + 512, + 512 + ], + [ + 901, + 512, + 512 + ], + [ + 494, + 512, + 512 + ], + [ + 463, + 512, + 512 + ], + [ + 926, + 512, + 512 + ], + [ + 1094, + 512, + 512 + ], + [ + 972, + 512, + 512 + ], + [ + 565, + 512, + 512 + ], + [ + 1031, + 512, + 512 + ], + [ + 917, + 512, + 512 + ], + [ + 817, + 512, + 512 + ], + [ + 857, + 512, + 512 + ], + [ + 923, + 512, + 512 + ], + [ + 861, + 512, + 512 + ], + [ + 793, + 512, + 512 + ], + [ + 834, + 512, + 512 + ], + [ + 980, + 512, + 512 + ], + [ + 575, + 512, + 512 + ], + [ + 921, + 512, + 512 + ], + [ + 933, + 512, + 512 + ], + [ + 1085, + 512, + 512 + ], + [ + 926, + 512, + 512 + ], + [ + 802, + 512, + 512 + ], + [ + 1225, + 512, + 512 + ], + [ + 1026, + 512, + 512 + ], + [ + 865, + 512, + 512 + ], + [ + 933, + 512, + 512 + ], + [ + 950, + 512, + 512 + ], + [ + 893, + 512, + 512 + ], + [ + 974, + 512, + 512 + ], + [ + 820, + 512, + 512 + ], + [ + 843, + 512, + 512 + ], + [ + 975, + 512, + 512 + ], + [ + 826, + 512, + 512 + ], + [ + 898, + 512, + 512 + ], + [ + 995, + 512, + 512 + ], + [ + 1005, + 512, + 512 + ], + [ + 956, + 512, + 512 + ], + [ + 949, + 512, + 512 + ], + [ + 634, + 512, + 512 + ], + [ + 981, + 512, + 512 + ], + [ + 905, + 512, + 512 + ], + [ + 908, + 512, + 512 + ], + [ + 948, + 512, + 512 + ], + [ + 913, + 512, + 512 + ], + [ + 1040, + 512, + 512 + ], + [ + 989, + 512, + 512 + ], + [ + 779, + 512, + 512 + ], + [ + 916, + 512, + 512 + ], + [ + 1001, + 512, + 512 + ], + [ + 782, + 512, + 512 + ], + [ + 1011, + 512, + 512 + ], + [ + 1132, + 512, + 512 + ], + [ + 594, + 512, + 512 + ], + [ + 921, + 512, + 512 + ], + [ + 461, + 512, + 512 + ], + [ + 559, + 512, + 512 + ], + [ + 983, + 512, + 512 + ], + [ + 989, + 512, + 512 + ], + [ + 866, + 512, + 512 + ], + [ + 937, + 512, + 512 + ], + [ + 839, + 512, + 512 + ], + [ + 889, + 512, + 512 + ], + [ + 853, + 512, + 512 + ], + [ + 790, + 512, + 512 + ], + [ + 826, + 512, + 512 + ], + [ + 1012, + 512, + 512 + ], + [ + 561, + 512, + 512 + ], + [ + 902, + 512, + 512 + ], + [ + 896, + 512, + 512 + ], + [ + 952, + 512, + 512 + ], + [ + 839, + 512, + 512 + ], + [ + 866, + 512, + 512 + ], + [ + 965, + 512, + 512 + ], + [ + 865, + 512, + 512 + ], + [ + 1099, + 512, + 512 + ], + [ + 581, + 512, + 512 + ], + [ + 868, + 512, + 512 + ], + [ + 900, + 512, + 512 + ], + [ + 960, + 512, + 512 + ], + [ + 912, + 512, + 512 + ], + [ + 909, + 512, + 512 + ], + [ + 601, + 512, + 512 + ], + [ + 780, + 512, + 512 + ], + [ + 906, + 512, + 512 + ], + [ + 912, + 512, + 512 + ], + [ + 822, + 512, + 512 + ], + [ + 881, + 512, + 512 + ], + [ + 587, + 512, + 512 + ], + [ + 497, + 512, + 512 + ], + [ + 982, + 512, + 512 + ], + [ + 897, + 512, + 512 + ], + [ + 898, + 512, + 512 + ], + [ + 793, + 512, + 512 + ], + [ + 866, + 512, + 512 + ], + [ + 807, + 512, + 512 + ], + [ + 909, + 512, + 512 + ], + [ + 686, + 512, + 512 + ], + [ + 759, + 512, + 512 + ], + [ + 524, + 512, + 512 + ], + [ + 841, + 512, + 512 + ], + [ + 868, + 512, + 512 + ], + [ + 992, + 512, + 512 + ], + [ + 904, + 512, + 512 + ], + [ + 557, + 512, + 512 + ], + [ + 929, + 512, + 512 + ], + [ + 1006, + 512, + 512 + ], + [ + 607, + 512, + 512 + ], + [ + 989, + 512, + 512 + ], + [ + 812, + 512, + 512 + ], + [ + 827, + 512, + 512 + ], + [ + 1021, + 512, + 512 + ], + [ + 904, + 512, + 512 + ], + [ + 778, + 512, + 512 + ], + [ + 482, + 512, + 512 + ], + [ + 455, + 512, + 512 + ], + [ + 866, + 512, + 512 + ], + [ + 950, + 512, + 512 + ], + [ + 951, + 512, + 512 + ], + [ + 857, + 512, + 512 + ], + [ + 686, + 512, + 512 + ], + [ + 836, + 512, + 512 + ], + [ + 759, + 512, + 512 + ], + [ + 976, + 512, + 512 + ], + [ + 1017, + 512, + 512 + ], + [ + 817, + 512, + 512 + ], + [ + 795, + 512, + 512 + ], + [ + 988, + 512, + 512 + ], + [ + 930, + 512, + 512 + ], + [ + 825, + 512, + 512 + ], + [ + 853, + 512, + 512 + ], + [ + 933, + 512, + 512 + ], + [ + 931, + 512, + 512 + ], + [ + 828, + 512, + 512 + ], + [ + 506, + 512, + 512 + ], + [ + 996, + 512, + 512 + ], + [ + 853, + 512, + 512 + ], + [ + 480, + 512, + 512 + ], + [ + 884, + 512, + 512 + ], + [ + 541, + 512, + 512 + ], + [ + 945, + 512, + 512 + ], + [ + 930, + 512, + 512 + ], + [ + 1027, + 512, + 512 + ], + [ + 978, + 512, + 512 + ], + [ + 887, + 512, + 512 + ], + [ + 829, + 512, + 512 + ], + [ + 814, + 512, + 512 + ], + [ + 457, + 512, + 512 + ], + [ + 890, + 512, + 512 + ], + [ + 1034, + 512, + 512 + ], + [ + 882, + 512, + 512 + ], + [ + 1053, + 512, + 512 + ], + [ + 400, + 512, + 512 + ], + [ + 773, + 512, + 512 + ], + [ + 999, + 512, + 512 + ], + [ + 784, + 512, + 512 + ], + [ + 913, + 512, + 512 + ], + [ + 945, + 512, + 512 + ], + [ + 824, + 512, + 512 + ], + [ + 507, + 512, + 512 + ], + [ + 949, + 512, + 512 + ], + [ + 965, + 512, + 512 + ], + [ + 987, + 512, + 512 + ], + [ + 503, + 512, + 512 + ], + [ + 1008, + 512, + 512 + ], + [ + 860, + 512, + 512 + ], + [ + 815, + 512, + 512 + ], + [ + 901, + 512, + 512 + ], + [ + 957, + 512, + 512 + ], + [ + 777, + 512, + 512 + ], + [ + 482, + 512, + 512 + ], + [ + 853, + 512, + 512 + ], + [ + 929, + 512, + 512 + ], + [ + 718, + 512, + 512 + ], + [ + 900, + 512, + 512 + ], + [ + 805, + 512, + 512 + ], + [ + 1021, + 512, + 512 + ], + [ + 973, + 512, + 512 + ], + [ + 415, + 512, + 512 + ], + [ + 437, + 512, + 512 + ], + [ + 1012, + 512, + 512 + ], + [ + 481, + 512, + 512 + ], + [ + 1085, + 512, + 512 + ], + [ + 851, + 512, + 512 + ], + [ + 856, + 512, + 512 + ], + [ + 812, + 512, + 512 + ], + [ + 423, + 512, + 512 + ], + [ + 1005, + 512, + 512 + ], + [ + 837, + 512, + 512 + ], + [ + 964, + 512, + 512 + ], + [ + 625, + 512, + 512 + ], + [ + 857, + 512, + 512 + ], + [ + 841, + 512, + 512 + ], + [ + 807, + 512, + 512 + ], + [ + 567, + 512, + 512 + ], + [ + 512, + 512, + 512 + ], + [ + 907, + 512, + 512 + ], + [ + 481, + 512, + 512 + ], + [ + 489, + 512, + 512 + ], + [ + 488, + 512, + 512 + ], + [ + 581, + 512, + 512 + ], + [ + 481, + 512, + 512 + ], + [ + 897, + 512, + 512 + ], + [ + 874, + 512, + 512 + ], + [ + 803, + 512, + 512 + ], + [ + 814, + 512, + 512 + ], + [ + 861, + 512, + 512 + ], + [ + 564, + 512, + 512 + ], + [ + 910, + 512, + 512 + ], + [ + 890, + 512, + 512 + ], + [ + 884, + 512, + 512 + ], + [ + 880, + 512, + 512 + ], + [ + 569, + 512, + 512 + ], + [ + 927, + 512, + 512 + ], + [ + 922, + 512, + 512 + ], + [ + 615, + 512, + 512 + ], + [ + 938, + 512, + 512 + ], + [ + 605, + 512, + 512 + ], + [ + 619, + 512, + 512 + ], + [ + 889, + 512, + 512 + ], + [ + 1005, + 512, + 512 + ], + [ + 481, + 512, + 512 + ], + [ + 797, + 512, + 512 + ], + [ + 954, + 512, + 512 + ], + [ + 768, + 512, + 512 + ], + [ + 957, + 512, + 512 + ], + [ + 873, + 512, + 512 + ], + [ + 925, + 512, + 512 + ], + [ + 806, + 512, + 512 + ], + [ + 834, + 512, + 512 + ], + [ + 510, + 512, + 512 + ], + [ + 779, + 512, + 512 + ], + [ + 469, + 512, + 512 + ], + [ + 837, + 512, + 512 + ], + [ + 365, + 512, + 512 + ], + [ + 939, + 512, + 512 + ], + [ + 468, + 512, + 512 + ], + [ + 491, + 512, + 512 + ], + [ + 531, + 512, + 512 + ], + [ + 474, + 512, + 512 + ], + [ + 965, + 512, + 512 + ], + [ + 845, + 512, + 512 + ], + [ + 828, + 512, + 512 + ], + [ + 1003, + 512, + 512 + ], + [ + 401, + 512, + 512 + ], + [ + 865, + 512, + 512 + ], + [ + 585, + 512, + 512 + ], + [ + 569, + 512, + 512 + ], + [ + 869, + 512, + 512 + ], + [ + 988, + 512, + 512 + ], + [ + 824, + 512, + 512 + ], + [ + 569, + 512, + 512 + ], + [ + 801, + 512, + 512 + ], + [ + 451, + 512, + 512 + ], + [ + 487, + 512, + 512 + ], + [ + 848, + 512, + 512 + ], + [ + 849, + 512, + 512 + ], + [ + 524, + 512, + 512 + ], + [ + 576, + 512, + 512 + ], + [ + 502, + 512, + 512 + ], + [ + 521, + 512, + 512 + ], + [ + 929, + 512, + 512 + ], + [ + 884, + 512, + 512 + ], + [ + 1013, + 512, + 512 + ], + [ + 921, + 512, + 512 + ], + [ + 630, + 512, + 512 + ], + [ + 1154, + 512, + 512 + ], + [ + 490, + 512, + 512 + ], + [ + 493, + 512, + 512 + ], + [ + 503, + 512, + 512 + ], + [ + 989, + 512, + 512 + ], + [ + 550, + 512, + 512 + ], + [ + 1030, + 512, + 512 + ], + [ + 994, + 512, + 512 + ], + [ + 848, + 512, + 512 + ], + [ + 900, + 512, + 512 + ], + [ + 919, + 512, + 512 + ], + [ + 935, + 512, + 512 + ], + [ + 1013, + 512, + 512 + ], + [ + 809, + 512, + 512 + ], + [ + 504, + 512, + 512 + ], + [ + 945, + 512, + 512 + ], + [ + 915, + 512, + 512 + ], + [ + 469, + 512, + 512 + ], + [ + 858, + 512, + 512 + ], + [ + 373, + 512, + 512 + ], + [ + 970, + 512, + 512 + ], + [ + 864, + 512, + 512 + ], + [ + 921, + 512, + 512 + ], + [ + 650, + 512, + 512 + ], + [ + 959, + 512, + 512 + ], + [ + 858, + 512, + 512 + ], + [ + 1114, + 512, + 512 + ], + [ + 525, + 512, + 512 + ], + [ + 825, + 512, + 512 + ], + [ + 761, + 512, + 512 + ], + [ + 465, + 512, + 512 + ], + [ + 447, + 512, + 512 + ], + [ + 377, + 512, + 512 + ], + [ + 869, + 512, + 512 + ], + [ + 633, + 512, + 512 + ], + [ + 1002, + 512, + 512 + ], + [ + 1013, + 512, + 512 + ], + [ + 997, + 512, + 512 + ], + [ + 837, + 512, + 512 + ], + [ + 930, + 512, + 512 + ], + [ + 864, + 512, + 512 + ], + [ + 875, + 512, + 512 + ], + [ + 880, + 512, + 512 + ], + [ + 805, + 512, + 512 + ], + [ + 833, + 512, + 512 + ], + [ + 910, + 512, + 512 + ], + [ + 885, + 512, + 512 + ], + [ + 988, + 512, + 512 + ], + [ + 821, + 512, + 512 + ], + [ + 388, + 512, + 512 + ], + [ + 877, + 512, + 512 + ], + [ + 785, + 512, + 512 + ], + [ + 914, + 512, + 512 + ], + [ + 469, + 512, + 512 + ], + [ + 542, + 512, + 512 + ], + [ + 856, + 512, + 512 + ], + [ + 1049, + 512, + 512 + ], + [ + 969, + 512, + 512 + ], + [ + 969, + 512, + 512 + ], + [ + 941, + 512, + 512 + ], + [ + 871, + 512, + 512 + ], + [ + 888, + 512, + 512 + ], + [ + 888, + 512, + 512 + ], + [ + 817, + 512, + 512 + ], + [ + 984, + 512, + 512 + ], + [ + 877, + 512, + 512 + ], + [ + 841, + 512, + 512 + ], + [ + 1029, + 512, + 512 + ], + [ + 929, + 512, + 512 + ], + [ + 517, + 512, + 512 + ], + [ + 861, + 512, + 512 + ], + [ + 614, + 512, + 512 + ], + [ + 901, + 512, + 512 + ], + [ + 900, + 512, + 512 + ], + [ + 997, + 512, + 512 + ], + [ + 957, + 512, + 512 + ], + [ + 997, + 512, + 512 + ], + [ + 624, + 512, + 512 + ], + [ + 659, + 512, + 512 + ], + [ + 955, + 512, + 512 + ], + [ + 1029, + 512, + 512 + ], + [ + 946, + 512, + 512 + ], + [ + 1020, + 512, + 512 + ], + [ + 990, + 512, + 512 + ], + [ + 945, + 512, + 512 + ], + [ + 584, + 512, + 512 + ], + [ + 966, + 512, + 512 + ], + [ + 930, + 512, + 512 + ], + [ + 582, + 512, + 512 + ], + [ + 970, + 512, + 512 + ], + [ + 562, + 512, + 512 + ], + [ + 910, + 512, + 512 + ], + [ + 1053, + 512, + 512 + ], + [ + 853, + 512, + 512 + ], + [ + 896, + 512, + 512 + ], + [ + 921, + 512, + 512 + ], + [ + 611, + 512, + 512 + ], + [ + 868, + 512, + 512 + ], + [ + 909, + 512, + 512 + ], + [ + 803, + 512, + 512 + ], + [ + 950, + 512, + 512 + ], + [ + 963, + 512, + 512 + ], + [ + 884, + 512, + 512 + ], + [ + 928, + 512, + 512 + ], + [ + 888, + 512, + 512 + ], + [ + 957, + 512, + 512 + ], + [ + 441, + 512, + 512 + ], + [ + 1267, + 512, + 512 + ], + [ + 1001, + 512, + 512 + ], + [ + 818, + 512, + 512 + ], + [ + 921, + 512, + 512 + ], + [ + 893, + 512, + 512 + ], + [ + 942, + 512, + 512 + ], + [ + 881, + 512, + 512 + ], + [ + 567, + 512, + 512 + ], + [ + 873, + 512, + 512 + ], + [ + 467, + 512, + 512 + ], + [ + 1029, + 512, + 512 + ], + [ + 869, + 512, + 512 + ], + [ + 967, + 512, + 512 + ], + [ + 821, + 512, + 512 + ], + [ + 865, + 512, + 512 + ], + [ + 933, + 512, + 512 + ], + [ + 895, + 512, + 512 + ], + [ + 865, + 512, + 512 + ], + [ + 997, + 512, + 512 + ], + [ + 863, + 512, + 512 + ], + [ + 912, + 512, + 512 + ], + [ + 894, + 512, + 512 + ], + [ + 997, + 512, + 512 + ], + [ + 897, + 512, + 512 + ], + [ + 613, + 512, + 512 + ], + [ + 982, + 512, + 512 + ], + [ + 853, + 512, + 512 + ], + [ + 904, + 512, + 512 + ], + [ + 795, + 512, + 512 + ], + [ + 837, + 512, + 512 + ], + [ + 529, + 512, + 512 + ], + [ + 890, + 512, + 512 + ], + [ + 994, + 512, + 512 + ], + [ + 969, + 512, + 512 + ], + [ + 912, + 512, + 512 + ], + [ + 889, + 512, + 512 + ], + [ + 866, + 512, + 512 + ], + [ + 893, + 512, + 512 + ], + [ + 901, + 512, + 512 + ], + [ + 856, + 512, + 512 + ], + [ + 815, + 512, + 512 + ], + [ + 680, + 512, + 512 + ], + [ + 945, + 512, + 512 + ], + [ + 853, + 512, + 512 + ], + [ + 1071, + 512, + 512 + ], + [ + 652, + 512, + 512 + ], + [ + 1038, + 512, + 512 + ], + [ + 956, + 512, + 512 + ], + [ + 994, + 512, + 512 + ], + [ + 926, + 512, + 512 + ], + [ + 1123, + 512, + 512 + ], + [ + 885, + 512, + 512 + ], + [ + 845, + 512, + 512 + ], + [ + 830, + 512, + 512 + ], + [ + 909, + 512, + 512 + ], + [ + 1148, + 512, + 512 + ], + [ + 1009, + 512, + 512 + ], + [ + 741, + 512, + 512 + ], + [ + 869, + 512, + 512 + ], + [ + 857, + 512, + 512 + ], + [ + 829, + 512, + 512 + ], + [ + 791, + 512, + 512 + ], + [ + 935, + 512, + 512 + ], + [ + 507, + 512, + 512 + ], + [ + 399, + 512, + 512 + ], + [ + 567, + 512, + 512 + ], + [ + 455, + 512, + 512 + ], + [ + 495, + 512, + 512 + ], + [ + 845, + 512, + 512 + ], + [ + 501, + 512, + 512 + ], + [ + 917, + 512, + 512 + ], + [ + 899, + 512, + 512 + ], + [ + 833, + 512, + 512 + ], + [ + 947, + 512, + 512 + ], + [ + 881, + 512, + 512 + ], + [ + 941, + 512, + 512 + ], + [ + 873, + 512, + 512 + ], + [ + 425, + 512, + 512 + ], + [ + 1061, + 512, + 512 + ], + [ + 876, + 512, + 512 + ], + [ + 720, + 512, + 512 + ], + [ + 867, + 512, + 512 + ], + [ + 741, + 512, + 512 + ], + [ + 941, + 512, + 512 + ], + [ + 461, + 512, + 512 + ], + [ + 831, + 512, + 512 + ], + [ + 418, + 512, + 512 + ], + [ + 825, + 512, + 512 + ], + [ + 477, + 512, + 512 + ], + [ + 842, + 512, + 512 + ], + [ + 707, + 512, + 512 + ], + [ + 573, + 512, + 512 + ], + [ + 856, + 512, + 512 + ], + [ + 954, + 512, + 512 + ], + [ + 971, + 512, + 512 + ], + [ + 873, + 512, + 512 + ], + [ + 1027, + 512, + 512 + ], + [ + 958, + 512, + 512 + ], + [ + 789, + 512, + 512 + ], + [ + 1010, + 512, + 512 + ], + [ + 797, + 512, + 512 + ], + [ + 995, + 512, + 512 + ], + [ + 930, + 512, + 512 + ], + [ + 1052, + 512, + 512 + ], + [ + 459, + 512, + 512 + ], + [ + 954, + 512, + 512 + ], + [ + 967, + 512, + 512 + ], + [ + 999, + 512, + 512 + ], + [ + 1041, + 512, + 512 + ], + [ + 881, + 512, + 512 + ], + [ + 830, + 512, + 512 + ], + [ + 1121, + 512, + 512 + ], + [ + 935, + 512, + 512 + ], + [ + 767, + 512, + 512 + ], + [ + 889, + 512, + 512 + ], + [ + 791, + 512, + 512 + ], + [ + 851, + 512, + 512 + ], + [ + 494, + 512, + 512 + ], + [ + 521, + 512, + 512 + ], + [ + 885, + 512, + 512 + ], + [ + 485, + 512, + 512 + ], + [ + 966, + 512, + 512 + ], + [ + 881, + 512, + 512 + ], + [ + 816, + 512, + 512 + ], + [ + 581, + 512, + 512 + ], + [ + 984, + 512, + 512 + ], + [ + 753, + 512, + 512 + ], + [ + 997, + 512, + 512 + ], + [ + 615, + 512, + 512 + ], + [ + 945, + 512, + 512 + ], + [ + 975, + 512, + 512 + ], + [ + 519, + 512, + 512 + ], + [ + 995, + 512, + 512 + ], + [ + 925, + 512, + 512 + ], + [ + 600, + 512, + 512 + ], + [ + 527, + 512, + 512 + ], + [ + 1047, + 512, + 512 + ], + [ + 937, + 512, + 512 + ], + [ + 522, + 512, + 512 + ], + [ + 1074, + 512, + 512 + ], + [ + 487, + 512, + 512 + ], + [ + 862, + 512, + 512 + ], + [ + 439, + 512, + 512 + ], + [ + 945, + 512, + 512 + ], + [ + 484, + 512, + 512 + ], + [ + 584, + 512, + 512 + ], + [ + 952, + 512, + 512 + ], + [ + 871, + 512, + 512 + ], + [ + 811, + 512, + 512 + ], + [ + 527, + 512, + 512 + ], + [ + 1085, + 512, + 512 + ], + [ + 628, + 512, + 512 + ], + [ + 457, + 512, + 512 + ], + [ + 649, + 512, + 512 + ], + [ + 466, + 512, + 512 + ], + [ + 507, + 512, + 512 + ], + [ + 484, + 512, + 512 + ], + [ + 999, + 512, + 512 + ], + [ + 510, + 512, + 512 + ], + [ + 873, + 512, + 512 + ], + [ + 800, + 512, + 512 + ], + [ + 545, + 512, + 512 + ], + [ + 985, + 512, + 512 + ], + [ + 471, + 512, + 512 + ], + [ + 435, + 512, + 512 + ], + [ + 470, + 512, + 512 + ], + [ + 507, + 512, + 512 + ], + [ + 479, + 512, + 512 + ], + [ + 567, + 512, + 512 + ], + [ + 525, + 512, + 512 + ], + [ + 1070, + 512, + 512 + ], + [ + 971, + 512, + 512 + ], + [ + 522, + 512, + 512 + ], + [ + 581, + 512, + 512 + ], + [ + 573, + 512, + 512 + ], + [ + 490, + 512, + 512 + ], + [ + 905, + 512, + 512 + ], + [ + 857, + 512, + 512 + ], + [ + 918, + 512, + 512 + ], + [ + 537, + 512, + 512 + ], + [ + 875, + 512, + 512 + ], + [ + 397, + 512, + 512 + ], + [ + 371, + 512, + 512 + ], + [ + 593, + 512, + 512 + ], + [ + 470, + 512, + 512 + ], + [ + 582, + 512, + 512 + ], + [ + 440, + 512, + 512 + ], + [ + 930, + 512, + 512 + ], + [ + 601, + 512, + 512 + ], + [ + 531, + 512, + 512 + ], + [ + 923, + 512, + 512 + ], + [ + 853, + 512, + 512 + ], + [ + 1005, + 512, + 512 + ], + [ + 948, + 512, + 512 + ], + [ + 637, + 512, + 512 + ], + [ + 975, + 512, + 512 + ], + [ + 477, + 512, + 512 + ], + [ + 411, + 512, + 512 + ], + [ + 519, + 512, + 512 + ], + [ + 584, + 512, + 512 + ], + [ + 814, + 512, + 512 + ], + [ + 977, + 512, + 512 + ], + [ + 533, + 512, + 512 + ], + [ + 939, + 512, + 512 + ], + [ + 457, + 512, + 512 + ], + [ + 507, + 512, + 512 + ], + [ + 529, + 512, + 512 + ], + [ + 945, + 512, + 512 + ], + [ + 950, + 512, + 512 + ], + [ + 421, + 512, + 512 + ], + [ + 642, + 512, + 512 + ], + [ + 885, + 512, + 512 + ], + [ + 477, + 512, + 512 + ], + [ + 506, + 512, + 512 + ], + [ + 919, + 512, + 512 + ], + [ + 993, + 512, + 512 + ], + [ + 865, + 512, + 512 + ], + [ + 1009, + 512, + 512 + ], + [ + 554, + 512, + 512 + ], + [ + 889, + 512, + 512 + ], + [ + 377, + 512, + 512 + ], + [ + 934, + 512, + 512 + ], + [ + 869, + 512, + 512 + ], + [ + 945, + 512, + 512 + ], + [ + 502, + 512, + 512 + ], + [ + 1063, + 512, + 512 + ], + [ + 892, + 512, + 512 + ], + [ + 867, + 512, + 512 + ], + [ + 1061, + 512, + 512 + ], + [ + 947, + 512, + 512 + ], + [ + 745, + 512, + 512 + ], + [ + 959, + 512, + 512 + ], + [ + 618, + 512, + 512 + ], + [ + 841, + 512, + 512 + ], + [ + 565, + 512, + 512 + ], + [ + 833, + 512, + 512 + ], + [ + 510, + 512, + 512 + ], + [ + 577, + 512, + 512 + ], + [ + 505, + 512, + 512 + ], + [ + 504, + 512, + 512 + ], + [ + 551, + 512, + 512 + ], + [ + 982, + 512, + 512 + ], + [ + 853, + 512, + 512 + ], + [ + 845, + 512, + 512 + ], + [ + 556, + 512, + 512 + ], + [ + 897, + 512, + 512 + ], + [ + 467, + 512, + 512 + ], + [ + 498, + 512, + 512 + ], + [ + 537, + 512, + 512 + ], + [ + 875, + 512, + 512 + ], + [ + 511, + 512, + 512 + ], + [ + 622, + 512, + 512 + ], + [ + 948, + 512, + 512 + ], + [ + 586, + 512, + 512 + ], + [ + 596, + 512, + 512 + ], + [ + 629, + 512, + 512 + ], + [ + 425, + 512, + 512 + ], + [ + 887, + 512, + 512 + ], + [ + 1053, + 512, + 512 + ], + [ + 832, + 512, + 512 + ], + [ + 497, + 512, + 512 + ], + [ + 865, + 512, + 512 + ], + [ + 971, + 512, + 512 + ], + [ + 800, + 512, + 512 + ], + [ + 805, + 512, + 512 + ], + [ + 900, + 512, + 512 + ], + [ + 937, + 512, + 512 + ], + [ + 524, + 512, + 512 + ], + [ + 452, + 512, + 512 + ], + [ + 690, + 512, + 512 + ], + [ + 546, + 512, + 512 + ], + [ + 719, + 512, + 512 + ], + [ + 850, + 512, + 512 + ], + [ + 590, + 512, + 512 + ], + [ + 979, + 512, + 512 + ], + [ + 547, + 512, + 512 + ], + [ + 458, + 512, + 512 + ], + [ + 570, + 512, + 512 + ], + [ + 586, + 512, + 512 + ], + [ + 965, + 512, + 512 + ], + [ + 518, + 512, + 512 + ], + [ + 506, + 512, + 512 + ], + [ + 910, + 512, + 512 + ], + [ + 530, + 512, + 512 + ], + [ + 870, + 512, + 512 + ], + [ + 454, + 512, + 512 + ], + [ + 555, + 512, + 512 + ], + [ + 455, + 512, + 512 + ], + [ + 425, + 512, + 512 + ], + [ + 568, + 512, + 512 + ], + [ + 549, + 512, + 512 + ], + [ + 512, + 512, + 512 + ], + [ + 1034, + 512, + 512 + ], + [ + 975, + 512, + 512 + ], + [ + 528, + 512, + 512 + ], + [ + 490, + 512, + 512 + ], + [ + 506, + 512, + 512 + ], + [ + 940, + 512, + 512 + ], + [ + 602, + 512, + 512 + ], + [ + 500, + 512, + 512 + ], + [ + 610, + 512, + 512 + ], + [ + 1002, + 512, + 512 + ], + [ + 431, + 512, + 512 + ], + [ + 485, + 512, + 512 + ], + [ + 547, + 512, + 512 + ], + [ + 921, + 512, + 512 + ], + [ + 915, + 512, + 512 + ], + [ + 970, + 512, + 512 + ], + [ + 492, + 512, + 512 + ], + [ + 511, + 512, + 512 + ], + [ + 503, + 512, + 512 + ], + [ + 976, + 512, + 512 + ], + [ + 846, + 512, + 512 + ], + [ + 429, + 512, + 512 + ], + [ + 589, + 512, + 512 + ], + [ + 521, + 512, + 512 + ], + [ + 461, + 512, + 512 + ], + [ + 451, + 512, + 512 + ], + [ + 559, + 512, + 512 + ], + [ + 1020, + 512, + 512 + ], + [ + 464, + 512, + 512 + ], + [ + 634, + 512, + 512 + ], + [ + 435, + 512, + 512 + ], + [ + 562, + 512, + 512 + ], + [ + 794, + 512, + 512 + ], + [ + 557, + 512, + 512 + ], + [ + 897, + 512, + 512 + ], + [ + 847, + 512, + 512 + ], + [ + 881, + 512, + 512 + ], + [ + 995, + 512, + 512 + ], + [ + 850, + 512, + 512 + ], + [ + 298, + 512, + 512 + ], + [ + 786, + 512, + 512 + ], + [ + 855, + 512, + 512 + ], + [ + 803, + 512, + 512 + ], + [ + 1059, + 512, + 512 + ], + [ + 535, + 512, + 512 + ], + [ + 527, + 512, + 512 + ], + [ + 453, + 512, + 512 + ], + [ + 463, + 512, + 512 + ], + [ + 1037, + 512, + 512 + ], + [ + 1084, + 512, + 512 + ], + [ + 656, + 512, + 512 + ], + [ + 924, + 512, + 662 + ], + [ + 794, + 512, + 512 + ], + [ + 937, + 512, + 512 + ], + [ + 557, + 512, + 512 + ], + [ + 897, + 512, + 512 + ], + [ + 425, + 512, + 512 + ], + [ + 828, + 512, + 512 + ], + [ + 914, + 512, + 512 + ], + [ + 723, + 512, + 512 + ], + [ + 1059, + 512, + 512 + ], + [ + 1000, + 512, + 512 + ], + [ + 826, + 512, + 512 + ], + [ + 911, + 512, + 512 + ], + [ + 544, + 512, + 512 + ], + [ + 621, + 512, + 512 + ], + [ + 818, + 512, + 512 + ], + [ + 1026, + 512, + 512 + ], + [ + 788, + 512, + 512 + ], + [ + 976, + 512, + 512 + ], + [ + 1015, + 512, + 512 + ], + [ + 884, + 512, + 512 + ], + [ + 544, + 512, + 512 + ], + [ + 913, + 512, + 512 + ] + ], + "spacings": [ + [ + 0.5, + 0.76953125, + 0.76953125 + ], + [ + 0.5, + 0.7265625, + 0.7265625 + ], + [ + 0.5, + 0.787109375, + 0.787109375 + ], + [ + 0.5, + 0.62890625, + 0.62890625 + ], + [ + 0.5, + 0.953125, + 0.953125 + ], + [ + 0.5, + 0.875, + 0.875 + ], + [ + 0.5, + 0.693359375, + 0.693359375 + ], + [ + 0.5, + 0.685546875, + 0.685546875 + ], + [ + 0.5, + 0.6953125, + 0.6953125 + ], + [ + 0.5, + 0.75, + 0.75 + ], + [ + 0.5, + 0.74609375, + 0.74609375 + ], + [ + 0.5, + 0.6015625, + 0.6015625 + ], + [ + 0.5, + 0.6875, + 0.6875 + ], + [ + 0.5, + 0.7265625, + 0.7265625 + ], + [ + 0.5, + 0.59375, + 0.59375 + ], + [ + 0.5, + 0.7265625, + 0.7265625 + ], + [ + 0.5, + 0.66015625, + 0.66015625 + ], + [ + 0.5, + 0.79296875, + 0.79296875 + ], + [ + 0.5, + 0.650390625, + 0.650390625 + ], + [ + 0.5, + 0.7421875, + 0.7421875 + ], + [ + 0.5, + 0.791015625, + 0.791015625 + ], + [ + 0.5, + 0.82421875, + 0.82421875 + ], + [ + 0.5, + 0.875, + 0.875 + ], + [ + 0.5, + 0.6328125, + 0.6328125 + ], + [ + 0.5, + 0.759765625, + 0.759765625 + ], + [ + 0.5, + 0.9765625, + 0.9765625 + ], + [ + 0.5, + 0.693359375, + 0.693359375 + ], + [ + 0.5, + 0.751953125, + 0.751953125 + ], + [ + 0.5, + 0.625, + 0.625 + ], + [ + 0.5, + 0.8203125, + 0.8203125 + ], + [ + 0.5, + 0.69921875, + 0.69921875 + ], + [ + 0.5, + 0.70703125, + 0.70703125 + ], + [ + 0.5, + 0.79296875, + 0.79296875 + ], + [ + 0.5, + 0.611328125, + 0.611328125 + ], + [ + 0.5, + 0.8125, + 0.8125 + ], + [ + 0.5, + 0.78125, + 0.78125 + ], + [ + 0.5, + 0.92578125, + 0.92578125 + ], + [ + 0.5, + 0.67578125, + 0.67578125 + ], + [ + 0.5, + 0.662109375, + 0.662109375 + ], + [ + 0.5, + 0.56640625, + 0.56640625 + ], + [ + 0.5, + 0.6484375, + 0.6484375 + ], + [ + 0.5, + 0.861328125, + 0.861328125 + ], + [ + 0.5, + 0.63671875, + 0.63671875 + ], + [ + 0.5, + 0.673828125, + 0.673828125 + ], + [ + 0.5, + 0.65625, + 0.65625 + ], + [ + 0.5, + 0.712890625, + 0.712890625 + ], + [ + 0.5, + 0.71875, + 0.71875 + ], + [ + 0.5, + 0.771484375, + 0.771484375 + ], + [ + 0.5, + 0.5859375, + 0.5859375 + ], + [ + 0.5, + 0.841796875, + 0.841796875 + ], + [ + 0.5, + 0.771484375, + 0.771484375 + ], + [ + 0.5, + 0.73046875, + 0.73046875 + ], + [ + 0.5, + 0.611328125, + 0.611328125 + ], + [ + 0.5, + 0.849609375, + 0.849609375 + ], + [ + 0.5, + 0.7109375, + 0.7109375 + ], + [ + 0.5, + 0.771484375, + 0.771484375 + ], + [ + 0.5, + 0.81640625, + 0.81640625 + ], + [ + 0.5, + 0.662109375, + 0.662109375 + ], + [ + 0.5, + 0.671875, + 0.671875 + ], + [ + 0.5, + 0.625, + 0.625 + ], + [ + 0.5, + 0.966796875, + 0.966796875 + ], + [ + 0.5, + 0.6328125, + 0.6328125 + ], + [ + 0.5, + 0.865234375, + 0.865234375 + ], + [ + 0.5, + 0.7265625, + 0.7265625 + ], + [ + 0.5, + 0.62890625, + 0.62890625 + ], + [ + 0.5, + 0.80859375, + 0.80859375 + ], + [ + 0.5, + 0.5859375, + 0.5859375 + ], + [ + 0.5, + 0.69140625, + 0.69140625 + ], + [ + 0.5, + 0.8046875, + 0.8046875 + ], + [ + 0.5, + 0.583984375, + 0.583984375 + ], + [ + 0.5, + 0.78125, + 0.78125 + ], + [ + 0.5, + 0.796875, + 0.796875 + ], + [ + 0.5, + 0.638671875, + 0.638671875 + ], + [ + 0.5, + 0.69921875, + 0.69921875 + ], + [ + 0.5, + 0.68359375, + 0.68359375 + ], + [ + 0.5, + 0.81640625, + 0.81640625 + ], + [ + 0.5, + 0.89453125, + 0.89453125 + ], + [ + 0.5, + 0.681640625, + 0.681640625 + ], + [ + 0.5, + 0.73046875, + 0.73046875 + ], + [ + 0.5, + 0.857421875, + 0.857421875 + ], + [ + 0.5, + 0.658203125, + 0.658203125 + ], + [ + 0.5, + 0.734375, + 0.734375 + ], + [ + 0.5, + 0.625, + 0.625 + ], + [ + 0.5, + 0.6875, + 0.6875 + ], + [ + 0.5, + 0.68359375, + 0.68359375 + ], + [ + 0.5, + 0.91796875, + 0.91796875 + ], + [ + 0.5, + 0.75390625, + 0.75390625 + ], + [ + 0.5, + 0.765625, + 0.765625 + ], + [ + 0.5, + 0.611328125, + 0.611328125 + ], + [ + 0.5, + 0.798828125, + 0.798828125 + ], + [ + 0.5, + 0.81640625, + 0.81640625 + ], + [ + 0.5, + 0.75, + 0.75 + ], + [ + 0.5, + 0.75390625, + 0.75390625 + ], + [ + 0.5, + 0.9140625, + 0.9140625 + ], + [ + 0.5, + 0.685546875, + 0.685546875 + ], + [ + 0.5, + 0.71875, + 0.71875 + ], + [ + 0.5, + 0.72265625, + 0.72265625 + ], + [ + 0.5, + 0.830078125, + 0.830078125 + ], + [ + 0.5, + 0.751953125, + 0.751953125 + ], + [ + 0.5, + 0.794921875, + 0.794921875 + ], + [ + 0.5, + 0.669921875, + 0.669921875 + ], + [ + 0.5, + 0.65625, + 0.65625 + ], + [ + 0.5, + 0.595703125, + 0.595703125 + ], + [ + 0.5, + 0.6484375, + 0.6484375 + ], + [ + 0.5, + 0.61328125, + 0.61328125 + ], + [ + 0.5, + 0.6171875, + 0.6171875 + ], + [ + 0.5, + 0.669921875, + 0.669921875 + ], + [ + 0.5, + 0.822265625, + 0.822265625 + ], + [ + 0.5, + 0.6640625, + 0.6640625 + ], + [ + 0.5, + 0.515625, + 0.515625 + ], + [ + 0.5, + 0.787109375, + 0.787109375 + ], + [ + 0.5, + 0.8046875, + 0.8046875 + ], + [ + 0.5, + 0.66796875, + 0.66796875 + ], + [ + 0.5, + 0.69140625, + 0.69140625 + ], + [ + 0.5, + 0.734375, + 0.734375 + ], + [ + 0.5, + 0.75, + 0.75 + ], + [ + 0.5, + 0.625, + 0.625 + ], + [ + 0.5, + 0.9765625, + 0.9765625 + ], + [ + 0.5, + 0.6796875, + 0.6796875 + ], + [ + 0.5, + 0.67578125, + 0.67578125 + ], + [ + 0.5, + 0.62109375, + 0.62109375 + ], + [ + 0.5, + 0.546875, + 0.546875 + ], + [ + 0.5, + 0.67578125, + 0.67578125 + ], + [ + 0.5, + 0.77734375, + 0.77734375 + ], + [ + 0.5, + 0.966796875, + 0.966796875 + ], + [ + 0.5, + 0.68359375, + 0.68359375 + ], + [ + 0.5, + 0.701171875, + 0.701171875 + ], + [ + 0.5, + 0.6875, + 0.6875 + ], + [ + 0.5, + 0.70703125, + 0.70703125 + ], + [ + 0.5, + 0.693359375, + 0.693359375 + ], + [ + 0.5, + 0.62890625, + 0.62890625 + ], + [ + 0.5, + 0.5859375, + 0.5859375 + ], + [ + 0.5, + 0.79296875, + 0.79296875 + ], + [ + 0.5, + 0.712890625, + 0.712890625 + ], + [ + 0.5, + 0.650390625, + 0.650390625 + ], + [ + 0.5, + 0.720703125, + 0.720703125 + ], + [ + 0.5, + 0.73046875, + 0.73046875 + ], + [ + 0.5, + 0.666015625, + 0.666015625 + ], + [ + 0.5, + 0.53515625, + 0.53515625 + ], + [ + 0.5, + 0.78125, + 0.78125 + ], + [ + 0.5, + 0.76171875, + 0.76171875 + ], + [ + 0.5, + 0.6953125, + 0.6953125 + ], + [ + 0.5, + 0.677734375, + 0.677734375 + ], + [ + 0.5, + 0.88671875, + 0.88671875 + ], + [ + 0.5, + 0.65234375, + 0.65234375 + ], + [ + 0.5, + 0.630859375, + 0.630859375 + ], + [ + 0.5, + 0.75390625, + 0.75390625 + ], + [ + 0.5, + 0.78125, + 0.78125 + ], + [ + 0.5, + 0.72265625, + 0.72265625 + ], + [ + 0.5, + 0.654296875, + 0.654296875 + ], + [ + 0.5, + 0.84765625, + 0.84765625 + ], + [ + 0.5, + 0.91796875, + 0.91796875 + ], + [ + 0.5, + 0.6796875, + 0.6796875 + ], + [ + 0.5, + 0.666015625, + 0.666015625 + ], + [ + 0.5, + 0.55078125, + 0.55078125 + ], + [ + 0.5, + 0.63671875, + 0.63671875 + ], + [ + 0.5, + 0.8125, + 0.8125 + ], + [ + 0.5, + 0.796875, + 0.796875 + ], + [ + 0.5, + 0.70703125, + 0.70703125 + ], + [ + 0.5, + 0.78125, + 0.78125 + ], + [ + 0.5, + 0.7265625, + 0.7265625 + ], + [ + 0.5, + 0.818359375, + 0.818359375 + ], + [ + 0.5, + 0.791015625, + 0.791015625 + ], + [ + 0.5, + 0.85546875, + 0.85546875 + ], + [ + 0.5, + 0.703125, + 0.703125 + ], + [ + 0.5, + 0.78515625, + 0.78515625 + ], + [ + 0.5, + 0.86328125, + 0.86328125 + ], + [ + 0.5, + 0.6796875, + 0.6796875 + ], + [ + 0.5, + 0.75390625, + 0.75390625 + ], + [ + 0.5, + 0.671875, + 0.671875 + ], + [ + 0.5, + 0.537109375, + 0.537109375 + ], + [ + 0.5, + 0.71484375, + 0.71484375 + ], + [ + 0.5, + 0.67578125, + 0.67578125 + ], + [ + 0.5, + 0.671875, + 0.671875 + ], + [ + 0.5, + 0.841796875, + 0.841796875 + ], + [ + 0.5, + 0.703125, + 0.703125 + ], + [ + 0.5, + 0.75390625, + 0.75390625 + ], + [ + 0.5, + 0.77734375, + 0.77734375 + ], + [ + 0.5, + 0.78515625, + 0.78515625 + ], + [ + 0.5, + 0.73828125, + 0.73828125 + ], + [ + 0.5, + 0.71484375, + 0.71484375 + ], + [ + 0.5, + 0.6484375, + 0.6484375 + ], + [ + 0.5, + 0.763671875, + 0.763671875 + ], + [ + 0.5, + 0.79296875, + 0.79296875 + ], + [ + 0.5, + 0.81640625, + 0.81640625 + ], + [ + 0.5, + 0.80859375, + 0.80859375 + ], + [ + 0.5, + 0.66796875, + 0.66796875 + ], + [ + 0.5, + 0.94921875, + 0.94921875 + ], + [ + 0.5, + 0.966796875, + 0.966796875 + ], + [ + 0.5, + 0.65625, + 0.65625 + ], + [ + 0.5, + 0.67578125, + 0.67578125 + ], + [ + 0.5, + 0.6953125, + 0.6953125 + ], + [ + 0.5, + 0.66796875, + 0.66796875 + ], + [ + 0.5, + 0.7890625, + 0.7890625 + ], + [ + 0.5, + 0.76171875, + 0.76171875 + ], + [ + 0.5, + 0.705078125, + 0.705078125 + ], + [ + 0.5, + 0.7734375, + 0.7734375 + ], + [ + 0.5, + 0.5859375, + 0.5859375 + ], + [ + 0.5, + 0.583984375, + 0.583984375 + ], + [ + 0.5, + 0.70703125, + 0.70703125 + ], + [ + 0.5, + 0.69921875, + 0.69921875 + ], + [ + 0.5, + 0.671875, + 0.671875 + ], + [ + 0.5, + 0.568359375, + 0.568359375 + ], + [ + 0.5, + 0.55859375, + 0.55859375 + ], + [ + 0.5, + 0.5859375, + 0.5859375 + ], + [ + 0.5, + 0.546875, + 0.546875 + ], + [ + 0.5, + 0.6171875, + 0.6171875 + ], + [ + 0.5, + 0.63671875, + 0.63671875 + ], + [ + 0.5, + 0.5859375, + 0.5859375 + ], + [ + 0.5, + 0.5859375, + 0.5859375 + ], + [ + 0.5, + 0.697265625, + 0.697265625 + ], + [ + 0.5, + 0.63671875, + 0.63671875 + ], + [ + 0.5, + 0.625, + 0.625 + ], + [ + 0.5, + 0.5859375, + 0.5859375 + ], + [ + 0.5, + 0.5859375, + 0.5859375 + ], + [ + 0.5, + 0.5859375, + 0.5859375 + ], + [ + 0.5, + 0.59375, + 0.59375 + ], + [ + 0.5, + 0.703125, + 0.703125 + ], + [ + 0.5, + 0.6328125, + 0.6328125 + ], + [ + 0.5, + 0.5859375, + 0.5859375 + ], + [ + 0.5, + 0.6328125, + 0.6328125 + ], + [ + 0.5, + 0.66015625, + 0.66015625 + ], + [ + 0.5, + 0.79296875, + 0.79296875 + ], + [ + 0.5, + 0.642578125, + 0.642578125 + ], + [ + 0.5, + 0.6875, + 0.6875 + ], + [ + 0.5, + 0.5859375, + 0.5859375 + ], + [ + 0.5, + 0.638671875, + 0.638671875 + ], + [ + 0.5, + 0.634765625, + 0.634765625 + ], + [ + 0.5, + 0.658203125, + 0.658203125 + ], + [ + 0.5, + 0.580078125, + 0.580078125 + ], + [ + 0.5, + 0.6875, + 0.6875 + ], + [ + 0.5, + 0.712890625, + 0.712890625 + ], + [ + 0.5, + 0.720703125, + 0.720703125 + ], + [ + 0.5, + 0.572265625, + 0.572265625 + ], + [ + 0.5, + 0.6328125, + 0.6328125 + ], + [ + 0.5, + 0.65625, + 0.65625 + ], + [ + 0.5, + 0.5859375, + 0.5859375 + ], + [ + 0.5, + 0.5859375, + 0.5859375 + ], + [ + 0.5, + 0.708984375, + 0.708984375 + ], + [ + 0.5, + 0.68359375, + 0.68359375 + ], + [ + 0.5, + 0.5625, + 0.5625 + ], + [ + 0.5, + 0.7421875, + 0.7421875 + ], + [ + 0.5, + 0.7421875, + 0.7421875 + ], + [ + 0.5, + 0.71484375, + 0.71484375 + ], + [ + 0.5, + 0.6328125, + 0.6328125 + ], + [ + 0.5, + 0.68359375, + 0.68359375 + ], + [ + 0.5, + 0.59375, + 0.59375 + ], + [ + 0.5, + 0.53515625, + 0.53515625 + ], + [ + 0.5, + 0.6875, + 0.6875 + ], + [ + 0.5, + 0.78125, + 0.78125 + ], + [ + 0.5, + 0.74609375, + 0.74609375 + ], + [ + 0.5, + 0.611328125, + 0.611328125 + ], + [ + 0.5, + 0.68359375, + 0.68359375 + ], + [ + 0.5, + 0.84375, + 0.84375 + ], + [ + 0.5, + 0.68359375, + 0.68359375 + ], + [ + 0.5, + 0.59375, + 0.59375 + ], + [ + 0.5, + 0.7265625, + 0.7265625 + ], + [ + 0.5, + 0.619140625, + 0.619140625 + ], + [ + 0.5, + 0.640625, + 0.640625 + ], + [ + 0.5, + 0.65625, + 0.65625 + ], + [ + 0.5, + 0.591796875, + 0.591796875 + ], + [ + 0.5, + 0.765625, + 0.765625 + ], + [ + 0.5, + 0.828125, + 0.828125 + ], + [ + 0.5, + 0.5390625, + 0.5390625 + ], + [ + 0.5, + 0.6328125, + 0.6328125 + ], + [ + 0.5, + 0.671875, + 0.671875 + ], + [ + 0.5, + 0.6015625, + 0.6015625 + ], + [ + 0.5, + 0.65625, + 0.65625 + ], + [ + 0.5, + 0.75390625, + 0.75390625 + ], + [ + 0.5, + 0.5859375, + 0.5859375 + ], + [ + 0.5, + 0.59375, + 0.59375 + ], + [ + 0.5, + 0.5390625, + 0.5390625 + ], + [ + 0.5, + 0.64453125, + 0.64453125 + ], + [ + 0.5, + 0.63671875, + 0.63671875 + ], + [ + 0.5, + 0.66015625, + 0.66015625 + ], + [ + 0.699999988079071, + 0.724609375, + 0.724609375 + ], + [ + 0.5, + 0.71875, + 0.71875 + ], + [ + 0.5, + 0.5859375, + 0.5859375 + ], + [ + 0.5, + 0.58984375, + 0.58984375 + ], + [ + 0.5, + 0.615234375, + 0.615234375 + ], + [ + 0.5, + 0.59765625, + 0.59765625 + ], + [ + 0.5, + 0.728515625, + 0.728515625 + ], + [ + 0.5, + 0.5859375, + 0.5859375 + ], + [ + 0.5, + 0.6015625, + 0.6015625 + ], + [ + 0.5, + 0.5859375, + 0.5859375 + ], + [ + 0.5, + 0.70703125, + 0.70703125 + ], + [ + 0.5, + 0.626953125, + 0.626953125 + ], + [ + 0.5, + 0.58203125, + 0.58203125 + ], + [ + 0.5, + 0.703125, + 0.703125 + ], + [ + 0.5, + 0.7109375, + 0.7109375 + ], + [ + 0.5, + 0.625, + 0.625 + ], + [ + 0.5, + 0.7421875, + 0.7421875 + ], + [ + 0.5, + 0.66015625, + 0.66015625 + ], + [ + 0.5, + 0.5859375, + 0.5859375 + ], + [ + 0.5, + 0.638671875, + 0.638671875 + ], + [ + 0.5, + 0.6484375, + 0.6484375 + ], + [ + 0.5, + 0.7421875, + 0.7421875 + ], + [ + 0.5, + 0.7265625, + 0.7265625 + ], + [ + 0.5, + 0.67578125, + 0.67578125 + ], + [ + 0.5, + 0.5859375, + 0.5859375 + ], + [ + 0.5, + 0.640625, + 0.640625 + ], + [ + 0.5, + 0.5859375, + 0.5859375 + ], + [ + 0.5, + 0.650390625, + 0.650390625 + ], + [ + 0.5, + 0.6171875, + 0.6171875 + ], + [ + 0.5, + 0.5859375, + 0.5859375 + ], + [ + 0.5, + 0.615234375, + 0.615234375 + ], + [ + 0.5, + 0.7421875, + 0.7421875 + ], + [ + 0.5, + 0.7890625, + 0.7890625 + ], + [ + 0.5, + 0.6640625, + 0.6640625 + ], + [ + 0.5, + 0.5859375, + 0.5859375 + ], + [ + 0.5, + 0.791015625, + 0.791015625 + ], + [ + 0.5, + 0.6484375, + 0.6484375 + ], + [ + 0.5, + 0.5859375, + 0.5859375 + ], + [ + 0.5, + 0.630859375, + 0.630859375 + ], + [ + 0.5, + 0.74609375, + 0.74609375 + ], + [ + 0.5, + 0.65234375, + 0.65234375 + ], + [ + 0.5, + 0.5859375, + 0.5859375 + ], + [ + 0.5, + 0.5859375, + 0.5859375 + ], + [ + 0.5, + 0.5859375, + 0.5859375 + ], + [ + 0.5, + 0.65625, + 0.65625 + ], + [ + 0.5, + 0.71484375, + 0.71484375 + ], + [ + 0.5, + 0.59375, + 0.59375 + ], + [ + 0.5, + 0.552734375, + 0.552734375 + ], + [ + 0.5, + 0.671875, + 0.671875 + ], + [ + 0.5, + 0.640625, + 0.640625 + ], + [ + 0.5, + 0.68359375, + 0.68359375 + ], + [ + 0.5, + 0.630859375, + 0.630859375 + ], + [ + 0.5, + 0.59765625, + 0.59765625 + ], + [ + 0.5, + 0.5859375, + 0.5859375 + ], + [ + 0.5, + 0.5859375, + 0.5859375 + ], + [ + 0.5, + 0.57421875, + 0.57421875 + ], + [ + 0.5, + 0.666015625, + 0.666015625 + ], + [ + 0.5, + 0.703125, + 0.703125 + ], + [ + 0.5, + 0.5546875, + 0.5546875 + ], + [ + 0.5, + 0.7421875, + 0.7421875 + ], + [ + 0.5, + 0.5859375, + 0.5859375 + ], + [ + 0.5, + 0.5859375, + 0.5859375 + ], + [ + 0.5, + 0.69921875, + 0.69921875 + ], + [ + 0.5, + 0.740234375, + 0.740234375 + ], + [ + 0.5, + 0.875, + 0.875 + ], + [ + 0.5, + 0.6328125, + 0.6328125 + ], + [ + 0.5, + 0.65234375, + 0.65234375 + ], + [ + 0.5, + 0.615234375, + 0.615234375 + ], + [ + 0.5, + 0.626953125, + 0.626953125 + ], + [ + 0.5, + 0.5859375, + 0.5859375 + ], + [ + 0.5, + 0.666015625, + 0.666015625 + ], + [ + 0.5, + 0.693359375, + 0.693359375 + ], + [ + 0.5, + 0.66796875, + 0.66796875 + ], + [ + 0.5, + 0.6328125, + 0.6328125 + ], + [ + 0.5, + 0.70703125, + 0.70703125 + ], + [ + 0.5, + 0.5859375, + 0.5859375 + ], + [ + 0.5, + 0.67578125, + 0.67578125 + ], + [ + 0.5, + 0.65625, + 0.65625 + ], + [ + 0.5, + 0.5859375, + 0.5859375 + ], + [ + 0.5, + 0.666015625, + 0.666015625 + ], + [ + 0.5, + 0.658203125, + 0.658203125 + ], + [ + 0.5, + 0.611328125, + 0.611328125 + ], + [ + 0.5, + 0.69140625, + 0.69140625 + ], + [ + 0.5, + 0.5859375, + 0.5859375 + ], + [ + 0.5, + 0.6328125, + 0.6328125 + ], + [ + 0.5, + 0.623046875, + 0.623046875 + ], + [ + 0.5, + 0.59765625, + 0.59765625 + ], + [ + 0.5, + 0.66015625, + 0.66015625 + ], + [ + 0.5, + 0.6328125, + 0.6328125 + ], + [ + 0.5, + 0.583984375, + 0.583984375 + ], + [ + 0.5, + 0.603515625, + 0.603515625 + ], + [ + 0.5, + 0.662109375, + 0.662109375 + ], + [ + 0.5, + 0.634765625, + 0.634765625 + ], + [ + 0.5, + 0.708984375, + 0.708984375 + ], + [ + 0.5, + 0.65625, + 0.65625 + ], + [ + 0.5, + 0.46484375, + 0.46484375 + ], + [ + 0.5, + 0.59765625, + 0.59765625 + ], + [ + 0.5, + 0.724609375, + 0.724609375 + ], + [ + 0.5, + 0.79296875, + 0.79296875 + ], + [ + 0.5, + 0.5859375, + 0.5859375 + ], + [ + 0.5, + 0.7421875, + 0.7421875 + ], + [ + 0.5, + 0.69140625, + 0.69140625 + ], + [ + 0.5, + 0.62890625, + 0.62890625 + ], + [ + 0.5, + 0.5859375, + 0.5859375 + ], + [ + 0.5, + 0.65625, + 0.65625 + ], + [ + 0.5, + 0.7109375, + 0.7109375 + ], + [ + 0.5, + 0.84375, + 0.84375 + ], + [ + 0.5, + 0.650390625, + 0.650390625 + ], + [ + 0.5, + 0.642578125, + 0.642578125 + ], + [ + 0.5, + 0.703125, + 0.703125 + ], + [ + 0.5, + 0.7421875, + 0.7421875 + ], + [ + 0.5, + 0.6875, + 0.6875 + ], + [ + 0.5, + 0.583984375, + 0.583984375 + ], + [ + 0.5, + 0.7421875, + 0.7421875 + ], + [ + 0.5, + 0.5859375, + 0.5859375 + ], + [ + 0.5, + 0.771484375, + 0.771484375 + ], + [ + 1.0, + 0.654296875, + 0.654296875 + ], + [ + 0.5, + 0.720703125, + 0.720703125 + ], + [ + 0.5, + 0.5859375, + 0.5859375 + ], + [ + 0.5, + 0.638671875, + 0.638671875 + ], + [ + 0.5, + 0.734375, + 0.734375 + ], + [ + 0.5, + 0.69921875, + 0.69921875 + ], + [ + 0.5, + 0.619140625, + 0.619140625 + ], + [ + 0.5, + 0.611328125, + 0.611328125 + ], + [ + 0.5, + 0.591796875, + 0.591796875 + ], + [ + 0.5, + 0.669921875, + 0.669921875 + ], + [ + 0.5, + 0.60546875, + 0.60546875 + ], + [ + 0.5, + 0.595703125, + 0.595703125 + ], + [ + 0.5, + 0.5859375, + 0.5859375 + ], + [ + 0.5, + 0.53515625, + 0.53515625 + ], + [ + 0.5, + 0.587890625, + 0.587890625 + ], + [ + 0.5, + 0.6171875, + 0.6171875 + ], + [ + 0.5, + 0.576171875, + 0.576171875 + ], + [ + 0.5, + 0.583984375, + 0.583984375 + ], + [ + 0.5, + 0.7421875, + 0.7421875 + ], + [ + 0.5, + 0.7421875, + 0.7421875 + ], + [ + 0.5, + 0.755859375, + 0.755859375 + ], + [ + 0.5, + 0.59765625, + 0.59765625 + ], + [ + 0.5, + 0.712890625, + 0.712890625 + ], + [ + 0.5, + 0.638671875, + 0.638671875 + ], + [ + 0.5, + 0.677734375, + 0.677734375 + ], + [ + 0.5, + 0.623046875, + 0.623046875 + ], + [ + 0.5, + 0.658203125, + 0.658203125 + ], + [ + 0.5, + 0.693359375, + 0.693359375 + ], + [ + 0.5, + 0.73046875, + 0.73046875 + ], + [ + 0.5, + 0.62109375, + 0.62109375 + ], + [ + 0.5, + 0.638671875, + 0.638671875 + ], + [ + 0.5, + 0.748046875, + 0.748046875 + ], + [ + 0.5, + 0.669921875, + 0.669921875 + ], + [ + 0.5, + 0.763671875, + 0.763671875 + ], + [ + 0.5, + 0.634765625, + 0.634765625 + ], + [ + 0.5, + 0.65234375, + 0.65234375 + ], + [ + 0.5, + 0.642578125, + 0.642578125 + ], + [ + 0.5, + 0.60546875, + 0.60546875 + ], + [ + 0.5, + 0.6953125, + 0.6953125 + ], + [ + 0.5, + 0.5859375, + 0.5859375 + ], + [ + 0.5, + 0.626953125, + 0.626953125 + ], + [ + 0.5, + 0.7421875, + 0.7421875 + ], + [ + 0.5, + 0.76953125, + 0.76953125 + ], + [ + 0.5, + 0.5859375, + 0.5859375 + ], + [ + 0.5, + 0.693359375, + 0.693359375 + ], + [ + 0.5, + 0.6953125, + 0.6953125 + ], + [ + 0.5, + 0.73046875, + 0.73046875 + ], + [ + 0.5, + 0.681640625, + 0.681640625 + ], + [ + 0.5, + 0.6171875, + 0.6171875 + ], + [ + 0.5, + 0.62109375, + 0.62109375 + ], + [ + 0.5, + 0.658203125, + 0.658203125 + ], + [ + 0.5, + 0.6328125, + 0.6328125 + ], + [ + 0.5, + 0.57421875, + 0.57421875 + ], + [ + 0.5, + 0.6953125, + 0.6953125 + ], + [ + 0.5, + 0.654296875, + 0.654296875 + ], + [ + 0.5, + 0.609375, + 0.609375 + ], + [ + 0.5, + 0.681640625, + 0.681640625 + ], + [ + 0.5, + 0.66015625, + 0.66015625 + ], + [ + 0.5, + 0.580078125, + 0.580078125 + ], + [ + 0.5, + 0.689453125, + 0.689453125 + ], + [ + 0.5, + 0.6015625, + 0.6015625 + ], + [ + 0.5, + 0.7421875, + 0.7421875 + ], + [ + 0.5, + 0.611328125, + 0.611328125 + ], + [ + 0.5, + 0.650390625, + 0.650390625 + ], + [ + 0.5, + 0.91015625, + 0.91015625 + ], + [ + 0.5, + 0.732421875, + 0.732421875 + ], + [ + 0.5, + 0.7109375, + 0.7109375 + ], + [ + 0.5, + 0.6875, + 0.6875 + ], + [ + 0.5, + 0.7421875, + 0.7421875 + ], + [ + 0.5, + 0.68359375, + 0.68359375 + ], + [ + 0.5, + 0.7421875, + 0.7421875 + ], + [ + 0.5, + 0.6484375, + 0.6484375 + ], + [ + 0.5, + 0.7421875, + 0.7421875 + ], + [ + 0.5, + 0.55078125, + 0.55078125 + ], + [ + 0.5, + 0.7265625, + 0.7265625 + ], + [ + 0.5, + 0.748046875, + 0.748046875 + ], + [ + 0.5, + 0.5859375, + 0.5859375 + ], + [ + 0.5, + 0.6484375, + 0.6484375 + ], + [ + 0.5, + 0.712890625, + 0.712890625 + ], + [ + 0.5, + 0.6015625, + 0.6015625 + ], + [ + 0.5, + 0.65234375, + 0.65234375 + ], + [ + 0.5, + 0.583984375, + 0.583984375 + ], + [ + 0.5, + 0.5859375, + 0.5859375 + ], + [ + 0.5, + 0.603515625, + 0.603515625 + ], + [ + 0.5, + 0.587890625, + 0.587890625 + ], + [ + 0.5, + 0.701171875, + 0.701171875 + ], + [ + 0.5, + 0.642578125, + 0.642578125 + ], + [ + 0.5, + 0.7578125, + 0.7578125 + ], + [ + 0.5, + 0.6171875, + 0.6171875 + ], + [ + 0.5, + 0.720703125, + 0.720703125 + ], + [ + 0.5, + 0.720703125, + 0.720703125 + ], + [ + 0.5, + 0.720703125, + 0.720703125 + ], + [ + 0.5, + 0.69921875, + 0.69921875 + ], + [ + 0.5, + 0.650390625, + 0.650390625 + ], + [ + 0.5, + 0.5859375, + 0.5859375 + ], + [ + 0.5, + 0.615234375, + 0.615234375 + ], + [ + 0.5, + 0.68359375, + 0.68359375 + ], + [ + 0.5, + 0.6796875, + 0.6796875 + ], + [ + 0.5, + 0.7421875, + 0.7421875 + ], + [ + 0.5, + 0.8203125, + 0.8203125 + ], + [ + 0.5, + 0.73046875, + 0.73046875 + ], + [ + 0.5, + 0.68359375, + 0.68359375 + ], + [ + 0.5, + 0.748046875, + 0.748046875 + ], + [ + 0.5, + 0.791015625, + 0.791015625 + ], + [ + 0.5, + 0.68359375, + 0.68359375 + ], + [ + 0.5, + 0.58203125, + 0.58203125 + ], + [ + 0.5, + 0.6640625, + 0.6640625 + ], + [ + 0.5, + 0.62890625, + 0.62890625 + ], + [ + 0.5, + 0.822265625, + 0.822265625 + ], + [ + 0.5, + 0.572265625, + 0.572265625 + ], + [ + 0.5, + 0.599609375, + 0.599609375 + ], + [ + 0.5, + 0.6796875, + 0.6796875 + ], + [ + 0.5, + 0.560546875, + 0.560546875 + ], + [ + 0.5, + 0.71875, + 0.71875 + ], + [ + 0.5, + 0.60546875, + 0.60546875 + ], + [ + 0.5, + 0.68359375, + 0.68359375 + ], + [ + 0.5, + 0.76953125, + 0.76953125 + ], + [ + 0.5, + 0.68359375, + 0.68359375 + ], + [ + 0.5, + 0.75390625, + 0.75390625 + ], + [ + 0.5, + 0.6328125, + 0.6328125 + ], + [ + 0.5, + 0.83203125, + 0.83203125 + ], + [ + 0.5, + 0.64453125, + 0.64453125 + ], + [ + 0.5, + 0.73828125, + 0.73828125 + ], + [ + 0.5, + 0.671875, + 0.671875 + ], + [ + 0.5, + 0.5546875, + 0.5546875 + ], + [ + 0.5, + 0.6484375, + 0.6484375 + ], + [ + 0.5, + 0.66015625, + 0.66015625 + ], + [ + 0.5, + 0.63671875, + 0.63671875 + ], + [ + 0.5, + 0.662109375, + 0.662109375 + ], + [ + 0.5, + 0.65625, + 0.65625 + ], + [ + 0.5, + 0.640625, + 0.640625 + ], + [ + 0.5, + 0.66015625, + 0.66015625 + ], + [ + 0.5, + 0.6171875, + 0.6171875 + ], + [ + 0.5, + 0.75, + 0.75 + ], + [ + 0.5, + 0.68359375, + 0.68359375 + ], + [ + 0.5, + 0.828125, + 0.828125 + ], + [ + 0.5, + 0.7109375, + 0.7109375 + ], + [ + 0.5, + 0.68359375, + 0.68359375 + ], + [ + 0.5, + 0.728515625, + 0.728515625 + ], + [ + 0.5, + 0.5859375, + 0.5859375 + ], + [ + 0.5, + 0.607421875, + 0.607421875 + ], + [ + 0.5, + 0.68359375, + 0.68359375 + ], + [ + 0.5, + 0.64453125, + 0.64453125 + ], + [ + 0.5, + 0.69921875, + 0.69921875 + ], + [ + 0.5, + 0.5546875, + 0.5546875 + ], + [ + 0.5, + 0.68359375, + 0.68359375 + ], + [ + 0.5, + 0.68359375, + 0.68359375 + ], + [ + 0.5, + 0.732421875, + 0.732421875 + ], + [ + 0.5, + 0.68359375, + 0.68359375 + ], + [ + 0.5, + 0.5859375, + 0.5859375 + ], + [ + 0.5, + 0.90234375, + 0.90234375 + ], + [ + 0.5, + 0.78125, + 0.78125 + ], + [ + 0.5, + 0.7890625, + 0.7890625 + ], + [ + 0.5, + 0.68359375, + 0.68359375 + ], + [ + 0.5, + 0.66015625, + 0.66015625 + ], + [ + 0.5, + 0.734375, + 0.734375 + ], + [ + 0.5, + 0.810546875, + 0.810546875 + ], + [ + 0.5, + 0.7734375, + 0.7734375 + ], + [ + 0.5, + 0.5859375, + 0.5859375 + ], + [ + 0.5, + 0.5859375, + 0.5859375 + ], + [ + 0.5, + 0.5859375, + 0.5859375 + ], + [ + 0.5, + 0.68359375, + 0.68359375 + ], + [ + 0.5, + 0.73046875, + 0.73046875 + ], + [ + 0.5, + 0.68359375, + 0.68359375 + ], + [ + 0.5, + 0.77734375, + 0.77734375 + ], + [ + 0.5, + 0.5859375, + 0.5859375 + ], + [ + 0.5, + 0.7109375, + 0.7109375 + ], + [ + 0.5, + 0.68359375, + 0.68359375 + ], + [ + 0.5, + 0.7890625, + 0.7890625 + ], + [ + 0.5, + 0.90625, + 0.90625 + ], + [ + 0.5, + 0.68359375, + 0.68359375 + ], + [ + 0.5, + 0.79296875, + 0.79296875 + ], + [ + 0.5, + 0.68359375, + 0.68359375 + ], + [ + 0.5, + 0.5546875, + 0.5546875 + ], + [ + 0.5, + 0.68359375, + 0.68359375 + ], + [ + 0.5, + 0.810546875, + 0.810546875 + ], + [ + 0.5, + 0.703125, + 0.703125 + ], + [ + 0.5, + 0.767578125, + 0.767578125 + ], + [ + 0.5, + 0.701171875, + 0.701171875 + ], + [ + 0.5, + 0.68359375, + 0.68359375 + ], + [ + 0.5, + 0.70703125, + 0.70703125 + ], + [ + 0.5, + 0.9453125, + 0.9453125 + ], + [ + 0.5, + 0.65625, + 0.65625 + ], + [ + 0.5, + 0.90625, + 0.90625 + ], + [ + 0.5, + 0.71484375, + 0.71484375 + ], + [ + 0.5, + 0.78125, + 0.78125 + ], + [ + 0.5, + 0.68359375, + 0.68359375 + ], + [ + 0.5, + 0.87109375, + 0.87109375 + ], + [ + 0.5, + 0.765625, + 0.765625 + ], + [ + 0.5, + 0.68359375, + 0.68359375 + ], + [ + 0.5, + 0.79296875, + 0.79296875 + ], + [ + 0.5, + 0.765625, + 0.765625 + ], + [ + 0.5, + 0.68359375, + 0.68359375 + ], + [ + 0.5, + 0.765625, + 0.765625 + ], + [ + 0.5, + 0.79296875, + 0.79296875 + ], + [ + 0.5, + 0.55078125, + 0.55078125 + ], + [ + 0.5, + 0.607421875, + 0.607421875 + ], + [ + 0.5, + 0.666015625, + 0.666015625 + ], + [ + 0.5, + 0.623046875, + 0.623046875 + ], + [ + 0.5, + 0.68359375, + 0.68359375 + ], + [ + 0.5, + 0.73046875, + 0.73046875 + ], + [ + 0.5, + 0.78515625, + 0.78515625 + ], + [ + 0.5, + 0.68359375, + 0.68359375 + ], + [ + 0.5, + 0.68359375, + 0.68359375 + ], + [ + 0.5, + 0.70703125, + 0.70703125 + ], + [ + 0.5, + 0.65625, + 0.65625 + ], + [ + 0.5, + 0.693359375, + 0.693359375 + ], + [ + 0.5, + 0.73046875, + 0.73046875 + ], + [ + 0.5, + 0.80078125, + 0.80078125 + ], + [ + 0.5, + 0.669921875, + 0.669921875 + ], + [ + 0.5, + 0.736328125, + 0.736328125 + ], + [ + 0.5, + 0.732421875, + 0.732421875 + ], + [ + 0.5, + 0.640625, + 0.640625 + ], + [ + 0.5, + 0.68359375, + 0.68359375 + ], + [ + 0.5, + 0.65625, + 0.65625 + ], + [ + 0.5, + 0.6875, + 0.6875 + ], + [ + 0.5, + 0.78515625, + 0.78515625 + ], + [ + 0.5, + 0.58203125, + 0.58203125 + ], + [ + 0.5, + 0.580078125, + 0.580078125 + ], + [ + 0.5, + 0.69921875, + 0.69921875 + ], + [ + 0.5, + 0.8515625, + 0.8515625 + ], + [ + 0.5, + 0.78125, + 0.78125 + ], + [ + 0.5, + 0.59765625, + 0.59765625 + ], + [ + 0.5, + 0.84375, + 0.84375 + ], + [ + 0.5, + 0.62109375, + 0.62109375 + ], + [ + 0.5, + 0.734375, + 0.734375 + ], + [ + 0.5, + 0.728515625, + 0.728515625 + ], + [ + 0.5, + 0.88671875, + 0.88671875 + ], + [ + 0.5, + 0.734375, + 0.734375 + ], + [ + 0.5, + 0.8359375, + 0.8359375 + ], + [ + 0.5, + 0.64453125, + 0.64453125 + ], + [ + 0.5, + 0.7578125, + 0.7578125 + ], + [ + 0.5, + 0.748046875, + 0.748046875 + ], + [ + 0.5, + 0.7890625, + 0.7890625 + ], + [ + 0.4000000059604645, + 0.666015625, + 0.666015625 + ], + [ + 0.5, + 0.572265625, + 0.572265625 + ], + [ + 0.5, + 0.64453125, + 0.64453125 + ], + [ + 0.5, + 0.537109375, + 0.537109375 + ], + [ + 0.5, + 0.73828125, + 0.73828125 + ], + [ + 0.5, + 0.78515625, + 0.78515625 + ], + [ + 0.5, + 0.76171875, + 0.76171875 + ], + [ + 0.5, + 0.828125, + 0.828125 + ], + [ + 0.5, + 0.662109375, + 0.662109375 + ], + [ + 0.5, + 0.6640625, + 0.6640625 + ], + [ + 0.5, + 0.619140625, + 0.619140625 + ], + [ + 0.5, + 0.78125, + 0.78125 + ], + [ + 0.5, + 0.896484375, + 0.896484375 + ], + [ + 0.5, + 0.71484375, + 0.71484375 + ], + [ + 0.5, + 0.712890625, + 0.712890625 + ], + [ + 0.5, + 0.7109375, + 0.7109375 + ], + [ + 0.5, + 0.68359375, + 0.68359375 + ], + [ + 0.5, + 0.65234375, + 0.65234375 + ], + [ + 0.5, + 0.76171875, + 0.76171875 + ], + [ + 0.5, + 0.708984375, + 0.708984375 + ], + [ + 0.5, + 0.75390625, + 0.75390625 + ], + [ + 0.5, + 0.681640625, + 0.681640625 + ], + [ + 0.5, + 0.796875, + 0.796875 + ], + [ + 0.5, + 0.68359375, + 0.68359375 + ], + [ + 0.5, + 0.814453125, + 0.814453125 + ], + [ + 0.5, + 0.78515625, + 0.78515625 + ], + [ + 0.5, + 0.681640625, + 0.681640625 + ], + [ + 0.5, + 0.7421875, + 0.7421875 + ], + [ + 0.5, + 0.828125, + 0.828125 + ], + [ + 0.5, + 0.80078125, + 0.80078125 + ], + [ + 0.5, + 0.73046875, + 0.73046875 + ], + [ + 0.5, + 0.6640625, + 0.6640625 + ], + [ + 0.5, + 0.77734375, + 0.77734375 + ], + [ + 0.5, + 0.84765625, + 0.84765625 + ], + [ + 0.5, + 0.732421875, + 0.732421875 + ], + [ + 0.5, + 0.76171875, + 0.76171875 + ], + [ + 0.5, + 0.7265625, + 0.7265625 + ], + [ + 0.5, + 0.724609375, + 0.724609375 + ], + [ + 0.5, + 0.859375, + 0.859375 + ], + [ + 0.5, + 0.69921875, + 0.69921875 + ], + [ + 0.5, + 0.68359375, + 0.68359375 + ], + [ + 0.5, + 0.630859375, + 0.630859375 + ], + [ + 0.5, + 0.69921875, + 0.69921875 + ], + [ + 0.5, + 0.626953125, + 0.626953125 + ], + [ + 0.5, + 0.69140625, + 0.69140625 + ], + [ + 0.5, + 0.67578125, + 0.67578125 + ], + [ + 0.5, + 0.755859375, + 0.755859375 + ], + [ + 0.5, + 0.650390625, + 0.650390625 + ], + [ + 0.5, + 0.70703125, + 0.70703125 + ], + [ + 0.5, + 0.75390625, + 0.75390625 + ], + [ + 0.5, + 0.6796875, + 0.6796875 + ], + [ + 0.5, + 0.7578125, + 0.7578125 + ], + [ + 0.5, + 0.82421875, + 0.82421875 + ], + [ + 0.5, + 0.76171875, + 0.76171875 + ], + [ + 0.5, + 0.6875, + 0.6875 + ], + [ + 0.5, + 0.712890625, + 0.712890625 + ], + [ + 0.5, + 0.703125, + 0.703125 + ], + [ + 0.5, + 0.6796875, + 0.6796875 + ], + [ + 0.5, + 0.765625, + 0.765625 + ], + [ + 0.5, + 0.6484375, + 0.6484375 + ], + [ + 0.5, + 0.677734375, + 0.677734375 + ], + [ + 0.5, + 0.765625, + 0.765625 + ], + [ + 0.5, + 0.84375, + 0.84375 + ], + [ + 0.5, + 0.76953125, + 0.76953125 + ], + [ + 0.5, + 0.71875, + 0.71875 + ], + [ + 0.5, + 0.740234375, + 0.740234375 + ], + [ + 0.5, + 0.517578125, + 0.517578125 + ], + [ + 0.5, + 0.6953125, + 0.6953125 + ], + [ + 0.5, + 0.61328125, + 0.61328125 + ], + [ + 0.5, + 0.583984375, + 0.583984375 + ], + [ + 0.5, + 0.7109375, + 0.7109375 + ], + [ + 0.5, + 0.646484375, + 0.646484375 + ], + [ + 0.5, + 0.8359375, + 0.8359375 + ], + [ + 0.5, + 0.69921875, + 0.69921875 + ], + [ + 0.5, + 0.607421875, + 0.607421875 + ], + [ + 0.5, + 0.701171875, + 0.701171875 + ], + [ + 0.5, + 0.7109375, + 0.7109375 + ], + [ + 0.5, + 0.77734375, + 0.77734375 + ], + [ + 0.5, + 0.72265625, + 0.72265625 + ], + [ + 0.5, + 0.64453125, + 0.64453125 + ], + [ + 0.4000000059604645, + 0.6875, + 0.6875 + ], + [ + 0.5, + 0.76953125, + 0.76953125 + ], + [ + 0.5, + 0.68359375, + 0.68359375 + ], + [ + 0.5, + 0.69140625, + 0.69140625 + ], + [ + 0.5, + 0.671875, + 0.671875 + ], + [ + 0.5, + 0.828125, + 0.828125 + ], + [ + 0.5, + 0.6015625, + 0.6015625 + ], + [ + 0.5, + 0.646484375, + 0.646484375 + ], + [ + 0.5, + 0.708984375, + 0.708984375 + ], + [ + 0.5, + 0.828125, + 0.828125 + ], + [ + 0.5, + 0.744140625, + 0.744140625 + ], + [ + 0.5, + 0.796875, + 0.796875 + ], + [ + 0.5, + 0.6875, + 0.6875 + ], + [ + 0.5, + 0.7265625, + 0.7265625 + ], + [ + 0.5, + 0.68359375, + 0.68359375 + ], + [ + 0.5, + 0.8046875, + 0.8046875 + ], + [ + 0.5, + 0.693359375, + 0.693359375 + ], + [ + 0.5, + 0.744140625, + 0.744140625 + ], + [ + 0.5, + 0.578125, + 0.578125 + ], + [ + 0.5, + 0.744140625, + 0.744140625 + ], + [ + 0.5, + 0.74609375, + 0.74609375 + ], + [ + 0.5, + 0.68359375, + 0.68359375 + ], + [ + 0.5, + 0.6875, + 0.6875 + ], + [ + 0.5, + 0.73046875, + 0.73046875 + ], + [ + 0.5, + 0.69921875, + 0.69921875 + ], + [ + 0.5, + 0.87890625, + 0.87890625 + ], + [ + 0.5, + 0.77734375, + 0.77734375 + ], + [ + 0.5, + 0.6875, + 0.6875 + ], + [ + 0.5, + 0.77734375, + 0.77734375 + ], + [ + 0.5, + 0.716796875, + 0.716796875 + ], + [ + 0.5, + 0.666015625, + 0.666015625 + ], + [ + 0.5, + 0.697265625, + 0.697265625 + ], + [ + 0.5, + 0.6875, + 0.6875 + ], + [ + 0.5, + 0.73046875, + 0.73046875 + ], + [ + 0.5, + 0.62109375, + 0.62109375 + ], + [ + 0.5, + 0.8046875, + 0.8046875 + ], + [ + 0.5, + 0.806640625, + 0.806640625 + ], + [ + 0.5, + 0.65234375, + 0.65234375 + ], + [ + 0.5, + 0.943359375, + 0.943359375 + ], + [ + 0.5, + 0.703125, + 0.703125 + ], + [ + 0.5, + 0.595703125, + 0.595703125 + ], + [ + 0.5, + 0.734375, + 0.734375 + ], + [ + 0.5, + 0.70703125, + 0.70703125 + ], + [ + 0.5, + 0.716796875, + 0.716796875 + ], + [ + 0.5, + 0.71484375, + 0.71484375 + ], + [ + 0.5, + 0.77734375, + 0.77734375 + ], + [ + 0.5, + 0.6796875, + 0.6796875 + ], + [ + 0.5, + 0.83203125, + 0.83203125 + ], + [ + 0.5, + 0.7421875, + 0.7421875 + ], + [ + 0.5, + 0.70703125, + 0.70703125 + ], + [ + 0.5, + 0.73828125, + 0.73828125 + ], + [ + 0.5, + 0.66796875, + 0.66796875 + ], + [ + 0.5, + 0.642578125, + 0.642578125 + ], + [ + 0.5, + 0.73046875, + 0.73046875 + ], + [ + 0.5, + 0.740234375, + 0.740234375 + ], + [ + 0.5, + 0.765625, + 0.765625 + ], + [ + 0.5, + 0.783203125, + 0.783203125 + ], + [ + 0.5, + 0.67578125, + 0.67578125 + ], + [ + 0.5, + 0.7265625, + 0.7265625 + ], + [ + 0.5, + 0.84375, + 0.84375 + ], + [ + 0.5, + 0.72265625, + 0.72265625 + ], + [ + 0.5, + 0.615234375, + 0.615234375 + ], + [ + 0.5, + 0.66015625, + 0.66015625 + ], + [ + 0.5, + 0.71484375, + 0.71484375 + ], + [ + 0.5, + 0.66015625, + 0.66015625 + ], + [ + 0.5, + 0.73828125, + 0.73828125 + ], + [ + 0.5, + 0.681640625, + 0.681640625 + ], + [ + 0.5, + 0.80859375, + 0.80859375 + ], + [ + 0.5, + 0.6640625, + 0.6640625 + ], + [ + 0.5, + 0.693359375, + 0.693359375 + ], + [ + 0.5, + 0.74609375, + 0.74609375 + ], + [ + 0.5, + 0.802734375, + 0.802734375 + ], + [ + 0.5, + 0.595703125, + 0.595703125 + ], + [ + 0.5, + 0.7265625, + 0.7265625 + ], + [ + 0.5, + 0.947265625, + 0.947265625 + ], + [ + 0.5, + 0.63671875, + 0.63671875 + ], + [ + 0.5, + 0.609375, + 0.609375 + ], + [ + 0.5, + 0.7109375, + 0.7109375 + ], + [ + 0.5, + 0.7578125, + 0.7578125 + ], + [ + 0.5, + 0.60546875, + 0.60546875 + ], + [ + 0.5, + 0.771484375, + 0.771484375 + ], + [ + 0.5, + 0.8359375, + 0.8359375 + ], + [ + 0.5, + 0.748046875, + 0.748046875 + ], + [ + 0.5, + 0.9765625, + 0.9765625 + ], + [ + 0.5, + 0.798828125, + 0.798828125 + ], + [ + 0.5, + 0.734375, + 0.734375 + ], + [ + 0.5, + 0.6640625, + 0.6640625 + ], + [ + 0.5, + 0.732421875, + 0.732421875 + ], + [ + 0.5, + 0.73046875, + 0.73046875 + ], + [ + 0.5, + 0.78125, + 0.78125 + ], + [ + 0.5, + 0.654296875, + 0.654296875 + ], + [ + 0.5, + 0.8515625, + 0.8515625 + ], + [ + 0.5, + 0.79296875, + 0.79296875 + ], + [ + 0.5, + 0.7890625, + 0.7890625 + ], + [ + 0.5, + 0.66796875, + 0.66796875 + ], + [ + 0.5, + 0.7109375, + 0.7109375 + ], + [ + 0.5, + 0.71875, + 0.71875 + ], + [ + 0.5, + 0.703125, + 0.703125 + ], + [ + 0.5, + 0.74609375, + 0.74609375 + ], + [ + 0.5, + 0.7109375, + 0.7109375 + ], + [ + 0.5, + 0.84765625, + 0.84765625 + ], + [ + 0.5, + 0.76171875, + 0.76171875 + ], + [ + 0.5, + 0.69140625, + 0.69140625 + ], + [ + 0.5, + 0.859375, + 0.859375 + ], + [ + 0.5, + 0.78515625, + 0.78515625 + ], + [ + 0.5, + 0.619140625, + 0.619140625 + ], + [ + 0.5, + 0.73828125, + 0.73828125 + ], + [ + 0.5, + 0.732421875, + 0.732421875 + ], + [ + 0.5, + 0.7421875, + 0.7421875 + ], + [ + 0.5, + 0.875, + 0.875 + ], + [ + 0.5, + 0.84375, + 0.84375 + ], + [ + 0.5, + 0.775390625, + 0.775390625 + ], + [ + 0.5, + 0.6171875, + 0.6171875 + ], + [ + 0.5, + 0.830078125, + 0.830078125 + ], + [ + 0.5, + 0.84765625, + 0.84765625 + ], + [ + 0.5, + 0.751953125, + 0.751953125 + ], + [ + 0.5, + 0.7265625, + 0.7265625 + ], + [ + 0.5, + 0.833984375, + 0.833984375 + ], + [ + 0.5, + 0.76171875, + 0.76171875 + ], + [ + 0.5, + 0.640625, + 0.640625 + ], + [ + 0.5, + 0.65234375, + 0.65234375 + ], + [ + 0.5, + 0.6875, + 0.6875 + ], + [ + 0.5, + 0.66796875, + 0.66796875 + ], + [ + 0.5, + 0.70703125, + 0.70703125 + ], + [ + 0.5, + 0.71484375, + 0.71484375 + ], + [ + 0.5, + 0.75390625, + 0.75390625 + ], + [ + 0.5, + 0.77734375, + 0.77734375 + ], + [ + 0.5, + 0.76953125, + 0.76953125 + ], + [ + 0.5, + 0.80859375, + 0.80859375 + ], + [ + 0.5, + 0.76171875, + 0.76171875 + ], + [ + 0.5, + 0.712890625, + 0.712890625 + ], + [ + 0.5, + 0.796875, + 0.796875 + ], + [ + 0.5, + 0.859375, + 0.859375 + ], + [ + 0.5, + 0.79296875, + 0.79296875 + ], + [ + 0.5, + 0.62890625, + 0.62890625 + ], + [ + 0.5, + 0.7734375, + 0.7734375 + ], + [ + 0.5, + 0.69921875, + 0.69921875 + ], + [ + 0.5, + 0.83203125, + 0.83203125 + ], + [ + 0.5, + 0.953125, + 0.953125 + ], + [ + 0.5, + 0.88671875, + 0.88671875 + ], + [ + 0.5, + 0.841796875, + 0.841796875 + ], + [ + 0.5, + 0.732421875, + 0.732421875 + ], + [ + 0.5, + 0.84765625, + 0.84765625 + ], + [ + 0.5, + 0.7109375, + 0.7109375 + ], + [ + 0.5, + 0.6953125, + 0.6953125 + ], + [ + 0.5, + 0.638671875, + 0.638671875 + ], + [ + 0.5, + 0.6875, + 0.6875 + ], + [ + 0.5, + 0.64453125, + 0.64453125 + ], + [ + 0.5, + 0.6484375, + 0.6484375 + ], + [ + 0.5, + 0.6796875, + 0.6796875 + ], + [ + 0.5, + 0.91015625, + 0.91015625 + ], + [ + 0.5, + 0.740234375, + 0.740234375 + ], + [ + 0.5, + 0.6328125, + 0.6328125 + ], + [ + 0.5, + 0.68359375, + 0.68359375 + ], + [ + 0.5, + 0.91015625, + 0.91015625 + ], + [ + 0.5, + 0.796875, + 0.796875 + ], + [ + 0.5, + 0.720703125, + 0.720703125 + ], + [ + 0.5, + 0.70703125, + 0.70703125 + ], + [ + 0.5, + 0.830078125, + 0.830078125 + ], + [ + 0.5, + 0.75, + 0.75 + ], + [ + 0.5, + 0.69921875, + 0.69921875 + ], + [ + 0.5, + 0.85546875, + 0.85546875 + ], + [ + 0.5, + 0.60546875, + 0.60546875 + ], + [ + 0.5, + 0.77734375, + 0.77734375 + ], + [ + 0.5, + 0.65234375, + 0.65234375 + ], + [ + 0.5, + 0.685546875, + 0.685546875 + ], + [ + 0.5, + 0.69140625, + 0.69140625 + ], + [ + 0.5, + 0.69140625, + 0.69140625 + ], + [ + 0.5, + 0.75390625, + 0.75390625 + ], + [ + 0.5, + 0.75, + 0.75 + ], + [ + 0.5, + 0.724609375, + 0.724609375 + ], + [ + 0.5, + 0.71484375, + 0.71484375 + ], + [ + 0.5, + 0.734375, + 0.734375 + ], + [ + 0.5, + 0.75, + 0.75 + ], + [ + 0.5, + 0.73828125, + 0.73828125 + ], + [ + 0.5, + 0.69140625, + 0.69140625 + ], + [ + 0.5, + 0.72265625, + 0.72265625 + ], + [ + 0.5, + 0.6953125, + 0.6953125 + ], + [ + 0.5, + 0.939453125, + 0.939453125 + ], + [ + 0.5, + 0.8203125, + 0.8203125 + ], + [ + 0.5, + 0.7734375, + 0.7734375 + ], + [ + 0.5, + 0.607421875, + 0.607421875 + ], + [ + 0.5, + 0.626953125, + 0.626953125 + ], + [ + 0.5, + 0.8046875, + 0.8046875 + ], + [ + 0.5, + 0.69921875, + 0.69921875 + ], + [ + 0.5, + 0.703125, + 0.703125 + ], + [ + 0.5, + 0.8046875, + 0.8046875 + ], + [ + 0.5, + 0.7421875, + 0.7421875 + ], + [ + 0.5, + 0.9765625, + 0.9765625 + ], + [ + 0.5, + 0.642578125, + 0.642578125 + ], + [ + 0.5, + 0.720703125, + 0.720703125 + ], + [ + 0.5, + 0.78125, + 0.78125 + ], + [ + 0.5, + 0.712890625, + 0.712890625 + ], + [ + 0.5, + 0.78125, + 0.78125 + ], + [ + 0.5, + 0.728515625, + 0.728515625 + ], + [ + 0.5, + 0.734375, + 0.734375 + ], + [ + 0.5, + 0.677734375, + 0.677734375 + ], + [ + 0.5, + 0.71875, + 0.71875 + ], + [ + 0.5, + 0.69921875, + 0.69921875 + ], + [ + 0.5, + 0.69140625, + 0.69140625 + ], + [ + 0.5, + 0.802734375, + 0.802734375 + ], + [ + 0.5, + 0.734375, + 0.734375 + ], + [ + 0.5, + 0.76953125, + 0.76953125 + ], + [ + 0.5, + 0.765625, + 0.765625 + ], + [ + 0.5, + 0.8125, + 0.8125 + ], + [ + 0.5, + 0.65625, + 0.65625 + ], + [ + 0.5, + 0.8515625, + 0.8515625 + ], + [ + 0.5, + 0.69140625, + 0.69140625 + ], + [ + 0.5, + 0.70703125, + 0.70703125 + ], + [ + 0.5, + 0.875, + 0.875 + ], + [ + 0.5, + 0.689453125, + 0.689453125 + ], + [ + 0.5, + 0.68359375, + 0.68359375 + ], + [ + 0.5, + 0.71484375, + 0.71484375 + ], + [ + 0.5, + 0.76953125, + 0.76953125 + ], + [ + 0.5, + 0.822265625, + 0.822265625 + ], + [ + 0.5, + 0.71875, + 0.71875 + ], + [ + 0.5, + 0.787109375, + 0.787109375 + ], + [ + 0.5, + 0.609375, + 0.609375 + ], + [ + 0.5, + 0.744140625, + 0.744140625 + ], + [ + 0.5, + 0.75, + 0.75 + ], + [ + 0.5, + 0.66796875, + 0.66796875 + ], + [ + 0.5, + 0.74609375, + 0.74609375 + ], + [ + 0.5, + 0.7734375, + 0.7734375 + ], + [ + 0.5, + 0.69921875, + 0.69921875 + ], + [ + 0.5, + 0.6796875, + 0.6796875 + ], + [ + 0.5, + 0.7109375, + 0.7109375 + ], + [ + 0.5, + 0.69140625, + 0.69140625 + ], + [ + 0.5, + 0.521484375, + 0.521484375 + ], + [ + 0.5, + 0.8515625, + 0.8515625 + ], + [ + 0.5, + 0.69140625, + 0.69140625 + ], + [ + 0.5, + 0.73828125, + 0.73828125 + ], + [ + 0.5, + 0.734375, + 0.734375 + ], + [ + 0.5, + 0.84765625, + 0.84765625 + ], + [ + 0.5, + 0.8046875, + 0.8046875 + ], + [ + 0.5, + 0.771484375, + 0.771484375 + ], + [ + 0.5, + 0.666015625, + 0.666015625 + ], + [ + 0.5, + 0.72265625, + 0.72265625 + ], + [ + 0.5, + 0.759765625, + 0.759765625 + ], + [ + 0.5, + 0.78125, + 0.78125 + ], + [ + 0.5, + 0.681640625, + 0.681640625 + ], + [ + 0.5, + 0.6953125, + 0.6953125 + ], + [ + 0.5, + 0.78125, + 0.78125 + ], + [ + 0.5, + 0.740234375, + 0.740234375 + ], + [ + 0.5, + 0.64453125, + 0.64453125 + ], + [ + 0.5, + 0.673828125, + 0.673828125 + ], + [ + 0.5, + 0.87890625, + 0.87890625 + ], + [ + 0.5, + 0.673828125, + 0.673828125 + ], + [ + 0.5, + 0.57421875, + 0.57421875 + ], + [ + 0.5, + 0.703125, + 0.703125 + ], + [ + 0.5, + 0.673828125, + 0.673828125 + ], + [ + 0.5, + 0.580078125, + 0.580078125 + ], + [ + 0.5, + 0.85546875, + 0.85546875 + ], + [ + 0.5, + 0.734375, + 0.734375 + ], + [ + 0.5, + 0.75390625, + 0.75390625 + ], + [ + 0.5, + 0.734375, + 0.734375 + ], + [ + 0.5, + 0.7890625, + 0.7890625 + ], + [ + 0.5, + 0.84765625, + 0.84765625 + ], + [ + 0.5, + 0.86328125, + 0.86328125 + ], + [ + 0.5, + 0.8671875, + 0.8671875 + ], + [ + 0.5, + 0.70703125, + 0.70703125 + ], + [ + 0.5, + 0.734375, + 0.734375 + ], + [ + 0.5, + 0.76953125, + 0.76953125 + ], + [ + 0.5, + 0.7265625, + 0.7265625 + ], + [ + 0.5, + 0.626953125, + 0.626953125 + ], + [ + 0.5, + 0.7578125, + 0.7578125 + ], + [ + 0.5, + 0.76953125, + 0.76953125 + ], + [ + 0.5, + 0.7890625, + 0.7890625 + ], + [ + 0.5, + 0.63671875, + 0.63671875 + ], + [ + 0.5, + 0.630859375, + 0.630859375 + ], + [ + 0.5, + 0.826171875, + 0.826171875 + ], + [ + 0.5, + 0.69140625, + 0.69140625 + ], + [ + 0.5, + 0.8203125, + 0.8203125 + ], + [ + 0.5, + 0.857421875, + 0.857421875 + ], + [ + 0.5, + 0.744140625, + 0.744140625 + ], + [ + 0.5, + 0.716796875, + 0.716796875 + ], + [ + 0.5, + 0.75, + 0.75 + ], + [ + 0.5, + 0.7734375, + 0.7734375 + ], + [ + 0.5, + 0.79296875, + 0.79296875 + ], + [ + 0.5, + 0.685546875, + 0.685546875 + ], + [ + 0.5, + 0.6171875, + 0.6171875 + ], + [ + 0.5, + 0.70703125, + 0.70703125 + ], + [ + 0.5, + 0.76953125, + 0.76953125 + ], + [ + 0.5, + 0.76953125, + 0.76953125 + ], + [ + 0.5, + 0.728515625, + 0.728515625 + ], + [ + 0.5, + 0.6171875, + 0.6171875 + ], + [ + 0.5, + 0.787109375, + 0.787109375 + ], + [ + 0.5, + 0.619140625, + 0.619140625 + ], + [ + 0.5, + 0.671875, + 0.671875 + ], + [ + 0.5, + 0.84375, + 0.84375 + ], + [ + 0.5, + 0.67578125, + 0.67578125 + ], + [ + 0.5, + 0.67578125, + 0.67578125 + ], + [ + 0.5, + 0.798828125, + 0.798828125 + ], + [ + 0.5, + 0.720703125, + 0.720703125 + ], + [ + 0.5, + 0.59375, + 0.59375 + ], + [ + 0.5, + 0.7109375, + 0.7109375 + ], + [ + 0.5, + 0.65625, + 0.65625 + ], + [ + 0.5, + 0.78125, + 0.78125 + ], + [ + 0.5, + 0.58203125, + 0.58203125 + ], + [ + 0.5, + 0.740234375, + 0.740234375 + ], + [ + 0.5, + 0.775390625, + 0.775390625 + ], + [ + 0.5, + 0.548828125, + 0.548828125 + ], + [ + 0.5, + 0.66796875, + 0.66796875 + ], + [ + 0.5, + 0.796875, + 0.796875 + ], + [ + 0.5, + 0.67578125, + 0.67578125 + ], + [ + 0.5, + 0.703125, + 0.703125 + ], + [ + 0.5, + 0.658203125, + 0.658203125 + ], + [ + 0.5, + 0.67578125, + 0.67578125 + ], + [ + 0.5, + 0.953125, + 0.953125 + ], + [ + 0.5, + 0.66796875, + 0.66796875 + ], + [ + 0.5, + 0.87890625, + 0.87890625 + ], + [ + 0.5, + 0.7109375, + 0.7109375 + ], + [ + 0.5, + 0.5859375, + 0.5859375 + ], + [ + 0.5, + 0.744140625, + 0.744140625 + ], + [ + 0.5, + 0.70703125, + 0.70703125 + ], + [ + 0.5, + 0.6796875, + 0.6796875 + ], + [ + 0.5, + 0.7421875, + 0.7421875 + ], + [ + 0.5, + 0.6953125, + 0.6953125 + ], + [ + 0.5, + 0.580078125, + 0.580078125 + ], + [ + 0.5, + 0.64453125, + 0.64453125 + ], + [ + 0.5, + 0.658203125, + 0.658203125 + ], + [ + 0.5, + 0.740234375, + 0.740234375 + ], + [ + 0.5, + 0.875, + 0.875 + ], + [ + 0.5, + 0.734375, + 0.734375 + ], + [ + 0.5, + 0.720703125, + 0.720703125 + ], + [ + 0.5, + 0.6171875, + 0.6171875 + ], + [ + 0.5, + 0.611328125, + 0.611328125 + ], + [ + 0.5, + 0.69140625, + 0.69140625 + ], + [ + 0.5, + 0.7109375, + 0.7109375 + ], + [ + 0.5, + 0.787109375, + 0.787109375 + ], + [ + 0.5, + 0.734375, + 0.734375 + ], + [ + 0.5, + 0.720703125, + 0.720703125 + ], + [ + 0.5, + 0.783203125, + 0.783203125 + ], + [ + 0.5, + 0.732421875, + 0.732421875 + ], + [ + 0.5, + 0.9765625, + 0.9765625 + ], + [ + 0.5, + 0.689453125, + 0.689453125 + ], + [ + 0.5, + 0.791015625, + 0.791015625 + ], + [ + 0.5, + 0.8359375, + 0.8359375 + ], + [ + 0.5, + 0.701171875, + 0.701171875 + ], + [ + 0.5, + 0.59375, + 0.59375 + ], + [ + 0.5, + 0.62109375, + 0.62109375 + ], + [ + 0.5, + 0.830078125, + 0.830078125 + ], + [ + 0.5, + 0.759765625, + 0.759765625 + ], + [ + 0.5, + 0.62890625, + 0.62890625 + ], + [ + 0.5, + 0.6953125, + 0.6953125 + ], + [ + 0.5, + 0.640625, + 0.640625 + ], + [ + 0.5, + 0.6171875, + 0.6171875 + ], + [ + 0.5, + 0.68359375, + 0.68359375 + ], + [ + 0.5, + 0.94921875, + 0.94921875 + ], + [ + 0.5, + 0.76953125, + 0.76953125 + ], + [ + 0.5, + 0.76953125, + 0.76953125 + ], + [ + 0.5, + 0.76171875, + 0.76171875 + ], + [ + 0.5, + 0.7265625, + 0.7265625 + ], + [ + 0.5, + 0.71484375, + 0.71484375 + ], + [ + 0.5, + 0.740234375, + 0.740234375 + ], + [ + 0.5, + 0.720703125, + 0.720703125 + ], + [ + 0.5, + 0.63671875, + 0.63671875 + ], + [ + 0.5, + 0.8359375, + 0.8359375 + ], + [ + 0.5, + 0.625, + 0.625 + ], + [ + 0.5, + 0.76953125, + 0.76953125 + ], + [ + 0.5, + 0.84765625, + 0.84765625 + ], + [ + 0.5, + 0.73046875, + 0.73046875 + ], + [ + 0.5, + 0.59765625, + 0.59765625 + ], + [ + 0.5, + 0.61328125, + 0.61328125 + ], + [ + 0.5, + 0.84375, + 0.84375 + ], + [ + 0.5, + 0.65234375, + 0.65234375 + ], + [ + 0.5, + 0.73046875, + 0.73046875 + ], + [ + 0.5, + 0.6875, + 0.6875 + ], + [ + 0.5, + 0.56640625, + 0.56640625 + ], + [ + 0.5, + 0.92578125, + 0.92578125 + ], + [ + 0.5, + 0.65234375, + 0.65234375 + ], + [ + 0.5, + 0.96484375, + 0.96484375 + ], + [ + 0.5, + 0.865234375, + 0.865234375 + ], + [ + 0.5, + 0.720703125, + 0.720703125 + ], + [ + 0.5, + 0.66796875, + 0.66796875 + ], + [ + 0.5, + 0.685546875, + 0.685546875 + ], + [ + 0.5, + 0.763671875, + 0.763671875 + ], + [ + 0.5, + 0.62109375, + 0.62109375 + ], + [ + 0.5, + 0.67578125, + 0.67578125 + ], + [ + 0.5, + 0.78125, + 0.78125 + ], + [ + 0.5, + 0.689453125, + 0.689453125 + ], + [ + 0.5, + 0.611328125, + 0.611328125 + ], + [ + 0.5, + 0.75390625, + 0.75390625 + ], + [ + 0.5, + 0.66015625, + 0.66015625 + ], + [ + 0.5, + 0.59375, + 0.59375 + ], + [ + 0.5, + 0.62890625, + 0.62890625 + ], + [ + 0.5, + 0.720703125, + 0.720703125 + ], + [ + 0.5, + 0.6875, + 0.6875 + ], + [ + 0.5, + 0.671875, + 0.671875 + ], + [ + 0.5, + 0.83984375, + 0.83984375 + ], + [ + 0.5, + 0.8046875, + 0.8046875 + ], + [ + 0.5, + 0.83984375, + 0.83984375 + ], + [ + 0.5, + 0.84375, + 0.84375 + ], + [ + 0.5, + 0.7890625, + 0.7890625 + ], + [ + 0.5, + 0.82421875, + 0.82421875 + ], + [ + 0.5, + 0.705078125, + 0.705078125 + ], + [ + 0.5, + 0.580078125, + 0.580078125 + ], + [ + 0.5, + 0.734375, + 0.734375 + ], + [ + 0.5, + 0.6796875, + 0.6796875 + ], + [ + 0.4000000059604645, + 0.65625, + 0.65625 + ], + [ + 0.5, + 0.6875, + 0.6875 + ], + [ + 0.5, + 0.794921875, + 0.794921875 + ], + [ + 0.5, + 0.58203125, + 0.58203125 + ], + [ + 0.5, + 0.74609375, + 0.74609375 + ], + [ + 0.5, + 0.66796875, + 0.66796875 + ], + [ + 0.5, + 0.935546875, + 0.935546875 + ], + [ + 0.5, + 0.7890625, + 0.7890625 + ], + [ + 0.5, + 0.74609375, + 0.74609375 + ], + [ + 0.5, + 0.80078125, + 0.80078125 + ], + [ + 0.5, + 0.6015625, + 0.6015625 + ], + [ + 0.5, + 0.9765625, + 0.9765625 + ], + [ + 0.5, + 0.79296875, + 0.79296875 + ], + [ + 0.5, + 0.87890625, + 0.87890625 + ], + [ + 0.5, + 0.875, + 0.875 + ], + [ + 0.5, + 0.779296875, + 0.779296875 + ], + [ + 0.5, + 0.611328125, + 0.611328125 + ], + [ + 0.5, + 0.666015625, + 0.666015625 + ], + [ + 0.5, + 0.62890625, + 0.62890625 + ], + [ + 0.5, + 0.693359375, + 0.693359375 + ], + [ + 0.5, + 0.6640625, + 0.6640625 + ], + [ + 0.5, + 0.609375, + 0.609375 + ], + [ + 0.5, + 0.740234375, + 0.740234375 + ], + [ + 0.5, + 0.7421875, + 0.7421875 + ], + [ + 0.5, + 0.845703125, + 0.845703125 + ], + [ + 0.5, + 0.7890625, + 0.7890625 + ], + [ + 0.5, + 0.64453125, + 0.64453125 + ], + [ + 0.5, + 0.634765625, + 0.634765625 + ], + [ + 0.5, + 0.8515625, + 0.8515625 + ], + [ + 0.5, + 0.79296875, + 0.79296875 + ], + [ + 0.5, + 0.625, + 0.625 + ], + [ + 0.5, + 0.658203125, + 0.658203125 + ], + [ + 0.5, + 0.9765625, + 0.9765625 + ], + [ + 0.5, + 0.92578125, + 0.92578125 + ], + [ + 0.5, + 0.640625, + 0.640625 + ], + [ + 0.5, + 0.720703125, + 0.720703125 + ], + [ + 0.5, + 0.80078125, + 0.80078125 + ], + [ + 0.5, + 0.705078125, + 0.705078125 + ], + [ + 0.5, + 0.671875, + 0.671875 + ], + [ + 0.5, + 0.935546875, + 0.935546875 + ], + [ + 0.5, + 0.7109375, + 0.7109375 + ], + [ + 0.5, + 0.703125, + 0.703125 + ], + [ + 0.5, + 0.76953125, + 0.76953125 + ], + [ + 0.5, + 0.763671875, + 0.763671875 + ], + [ + 0.5, + 0.72265625, + 0.72265625 + ], + [ + 0.5, + 0.849609375, + 0.849609375 + ], + [ + 0.5, + 0.6015625, + 0.6015625 + ], + [ + 0.5, + 0.73046875, + 0.73046875 + ], + [ + 0.5, + 0.74609375, + 0.74609375 + ], + [ + 0.5, + 0.60546875, + 0.60546875 + ], + [ + 0.5, + 0.890625, + 0.890625 + ], + [ + 0.5, + 0.611328125, + 0.611328125 + ], + [ + 0.5, + 0.685546875, + 0.685546875 + ], + [ + 0.5, + 0.69921875, + 0.69921875 + ], + [ + 0.5, + 0.576171875, + 0.576171875 + ], + [ + 0.5, + 0.716796875, + 0.716796875 + ], + [ + 0.5, + 0.751953125, + 0.751953125 + ], + [ + 0.5, + 0.494140625, + 0.494140625 + ], + [ + 0.5, + 0.7421875, + 0.7421875 + ], + [ + 0.5, + 0.6640625, + 0.6640625 + ], + [ + 0.5, + 0.916015625, + 0.916015625 + ], + [ + 0.5, + 0.8984375, + 0.8984375 + ], + [ + 0.5, + 0.65625, + 0.65625 + ], + [ + 0.5, + 0.625, + 0.625 + ], + [ + 0.5, + 0.625, + 0.625 + ], + [ + 0.5, + 0.7890625, + 0.7890625 + ], + [ + 0.5, + 0.765625, + 0.765625 + ], + [ + 0.5, + 0.69140625, + 0.69140625 + ], + [ + 0.5, + 0.681640625, + 0.681640625 + ], + [ + 0.5, + 0.7890625, + 0.7890625 + ], + [ + 0.5, + 0.705078125, + 0.705078125 + ], + [ + 0.5, + 0.69921875, + 0.69921875 + ], + [ + 0.5, + 0.703125, + 0.703125 + ], + [ + 0.5, + 0.748046875, + 0.748046875 + ], + [ + 0.5, + 0.85546875, + 0.85546875 + ], + [ + 0.5, + 0.63671875, + 0.63671875 + ], + [ + 0.5, + 0.875, + 0.875 + ], + [ + 0.5, + 0.771484375, + 0.771484375 + ], + [ + 0.5, + 0.88671875, + 0.88671875 + ], + [ + 0.5, + 0.7734375, + 0.7734375 + ], + [ + 0.5, + 0.80859375, + 0.80859375 + ], + [ + 0.5, + 0.71875, + 0.71875 + ], + [ + 0.5, + 0.71484375, + 0.71484375 + ], + [ + 0.5, + 0.84765625, + 0.84765625 + ], + [ + 0.5, + 0.927734375, + 0.927734375 + ], + [ + 0.5, + 0.935546875, + 0.935546875 + ], + [ + 0.5, + 0.6640625, + 0.6640625 + ], + [ + 0.5, + 0.759765625, + 0.759765625 + ], + [ + 0.5, + 0.662109375, + 0.662109375 + ], + [ + 0.5, + 0.81640625, + 0.81640625 + ], + [ + 0.5, + 0.74609375, + 0.74609375 + ], + [ + 0.5, + 0.68359375, + 0.68359375 + ], + [ + 0.5, + 0.802734375, + 0.802734375 + ], + [ + 0.5, + 0.763671875, + 0.763671875 + ], + [ + 0.5, + 0.8125, + 0.8125 + ], + [ + 0.5, + 0.77734375, + 0.77734375 + ], + [ + 0.5, + 0.650390625, + 0.650390625 + ], + [ + 0.5, + 0.85546875, + 0.85546875 + ], + [ + 0.5, + 0.734375, + 0.734375 + ], + [ + 0.5, + 0.638671875, + 0.638671875 + ], + [ + 0.5, + 0.7265625, + 0.7265625 + ], + [ + 0.5, + 0.6640625, + 0.6640625 + ], + [ + 0.5, + 0.74609375, + 0.74609375 + ], + [ + 0.5, + 0.703125, + 0.703125 + ], + [ + 0.5, + 0.73046875, + 0.73046875 + ], + [ + 0.5, + 0.7421875, + 0.7421875 + ], + [ + 0.5, + 0.6171875, + 0.6171875 + ], + [ + 0.5, + 0.69921875, + 0.69921875 + ], + [ + 0.5, + 0.640625, + 0.640625 + ], + [ + 0.5, + 0.73828125, + 0.73828125 + ], + [ + 0.5, + 0.84375, + 0.84375 + ], + [ + 0.5, + 0.78125, + 0.78125 + ], + [ + 0.5, + 0.720703125, + 0.720703125 + ], + [ + 0.5, + 0.76171875, + 0.76171875 + ], + [ + 0.5, + 0.8046875, + 0.8046875 + ], + [ + 0.5, + 0.712890625, + 0.712890625 + ], + [ + 0.5, + 0.703125, + 0.703125 + ], + [ + 0.5, + 0.64453125, + 0.64453125 + ], + [ + 0.5, + 0.765625, + 0.765625 + ], + [ + 0.5, + 0.8359375, + 0.8359375 + ], + [ + 0.5, + 0.765625, + 0.765625 + ], + [ + 0.5, + 0.728515625, + 0.728515625 + ], + [ + 0.5, + 0.7265625, + 0.7265625 + ], + [ + 0.5, + 0.771484375, + 0.771484375 + ], + [ + 0.5, + 0.72265625, + 0.72265625 + ], + [ + 0.5, + 0.73046875, + 0.73046875 + ], + [ + 0.5, + 0.78125, + 0.78125 + ], + [ + 0.5, + 0.76953125, + 0.76953125 + ], + [ + 0.5, + 0.625, + 0.625 + ], + [ + 0.5, + 0.77734375, + 0.77734375 + ], + [ + 0.5, + 0.7109375, + 0.7109375 + ], + [ + 0.5, + 0.97265625, + 0.97265625 + ], + [ + 0.5, + 0.71484375, + 0.71484375 + ], + [ + 0.5, + 0.69140625, + 0.69140625 + ], + [ + 0.5, + 0.76953125, + 0.76953125 + ], + [ + 0.5, + 0.890625, + 0.890625 + ], + [ + 0.5, + 0.884765625, + 0.884765625 + ], + [ + 0.5, + 0.712890625, + 0.712890625 + ], + [ + 0.5, + 0.875, + 0.875 + ], + [ + 0.5, + 0.6328125, + 0.6328125 + ], + [ + 0.5, + 0.62890625, + 0.62890625 + ], + [ + 0.5, + 0.861328125, + 0.861328125 + ], + [ + 0.5, + 0.75390625, + 0.75390625 + ], + [ + 0.5, + 0.80078125, + 0.80078125 + ], + [ + 0.5, + 0.681640625, + 0.681640625 + ], + [ + 0.5, + 0.68359375, + 0.68359375 + ], + [ + 0.5, + 0.80078125, + 0.80078125 + ], + [ + 0.5, + 0.640625, + 0.640625 + ], + [ + 0.5, + 0.74609375, + 0.74609375 + ], + [ + 0.5, + 0.68359375, + 0.68359375 + ], + [ + 0.5, + 0.8125, + 0.8125 + ], + [ + 0.5, + 0.931640625, + 0.931640625 + ], + [ + 0.5, + 0.701171875, + 0.701171875 + ], + [ + 0.5, + 0.796875, + 0.796875 + ], + [ + 0.5, + 0.81640625, + 0.81640625 + ], + [ + 0.5, + 0.861328125, + 0.861328125 + ], + [ + 0.5, + 0.81640625, + 0.81640625 + ], + [ + 0.5, + 0.8046875, + 0.8046875 + ], + [ + 0.5, + 0.6484375, + 0.6484375 + ], + [ + 0.5, + 0.88671875, + 0.88671875 + ], + [ + 0.5, + 0.771484375, + 0.771484375 + ], + [ + 0.5, + 0.69921875, + 0.69921875 + ], + [ + 0.5, + 0.68359375, + 0.68359375 + ], + [ + 0.5, + 0.734375, + 0.734375 + ], + [ + 0.5, + 0.748046875, + 0.748046875 + ], + [ + 0.5, + 0.7265625, + 0.7265625 + ], + [ + 0.5, + 0.58984375, + 0.58984375 + ], + [ + 0.5, + 0.7265625, + 0.7265625 + ], + [ + 0.5, + 0.68359375, + 0.68359375 + ], + [ + 0.5, + 0.708984375, + 0.708984375 + ], + [ + 0.5, + 0.68359375, + 0.68359375 + ], + [ + 0.5, + 0.71875, + 0.71875 + ], + [ + 0.5, + 0.68359375, + 0.68359375 + ], + [ + 0.5, + 0.599609375, + 0.599609375 + ], + [ + 0.5, + 0.953125, + 0.953125 + ], + [ + 0.5, + 0.876953125, + 0.876953125 + ], + [ + 0.5, + 0.619140625, + 0.619140625 + ], + [ + 0.5, + 0.73046875, + 0.73046875 + ], + [ + 0.5, + 0.72265625, + 0.72265625 + ], + [ + 0.5, + 0.76953125, + 0.76953125 + ], + [ + 0.5, + 0.5703125, + 0.5703125 + ], + [ + 0.5, + 0.693359375, + 0.693359375 + ], + [ + 0.5, + 0.845703125, + 0.845703125 + ], + [ + 0.5, + 0.76171875, + 0.76171875 + ], + [ + 0.5, + 0.71875, + 0.71875 + ], + [ + 0.5, + 0.84375, + 0.84375 + ], + [ + 0.5, + 0.68359375, + 0.68359375 + ], + [ + 0.5, + 0.9765625, + 0.9765625 + ], + [ + 0.5, + 0.6953125, + 0.6953125 + ], + [ + 0.5, + 0.666015625, + 0.666015625 + ], + [ + 0.5, + 0.90625, + 0.90625 + ], + [ + 0.5, + 0.681640625, + 0.681640625 + ], + [ + 0.5, + 0.578125, + 0.578125 + ], + [ + 0.5, + 0.822265625, + 0.822265625 + ], + [ + 0.5, + 0.6875, + 0.6875 + ], + [ + 0.5, + 0.58984375, + 0.58984375 + ], + [ + 0.5, + 0.671875, + 0.671875 + ], + [ + 0.5, + 0.611328125, + 0.611328125 + ], + [ + 0.5, + 0.806640625, + 0.806640625 + ], + [ + 0.5, + 0.66796875, + 0.66796875 + ], + [ + 0.5, + 0.9140625, + 0.9140625 + ], + [ + 0.5, + 0.890625, + 0.890625 + ], + [ + 0.5, + 0.84375, + 0.84375 + ], + [ + 0.5, + 0.88671875, + 0.88671875 + ], + [ + 0.5, + 0.84765625, + 0.84765625 + ], + [ + 0.5, + 0.69140625, + 0.69140625 + ], + [ + 0.5, + 0.7578125, + 0.7578125 + ], + [ + 0.5, + 0.7734375, + 0.7734375 + ], + [ + 0.5, + 0.5703125, + 0.5703125 + ], + [ + 0.5, + 0.67578125, + 0.67578125 + ], + [ + 0.5, + 0.6015625, + 0.6015625 + ], + [ + 0.5, + 0.796875, + 0.796875 + ], + [ + 0.5, + 0.72265625, + 0.72265625 + ], + [ + 0.5, + 0.75390625, + 0.75390625 + ], + [ + 0.5, + 0.7265625, + 0.7265625 + ], + [ + 0.5, + 0.75, + 0.75 + ], + [ + 0.5, + 0.72265625, + 0.72265625 + ], + [ + 0.5, + 0.890625, + 0.890625 + ], + [ + 0.5, + 0.8984375, + 0.8984375 + ], + [ + 0.5, + 0.78125, + 0.78125 + ], + [ + 0.5, + 0.599609375, + 0.599609375 + ], + [ + 0.5, + 0.80859375, + 0.80859375 + ], + [ + 0.5, + 0.712890625, + 0.712890625 + ], + [ + 0.5, + 0.60546875, + 0.60546875 + ], + [ + 0.5, + 0.59765625, + 0.59765625 + ], + [ + 0.5, + 0.69140625, + 0.69140625 + ], + [ + 0.5, + 0.765625, + 0.765625 + ], + [ + 0.5, + 0.70703125, + 0.70703125 + ], + [ + 0.5, + 0.89453125, + 0.89453125 + ], + [ + 0.5, + 0.73046875, + 0.73046875 + ], + [ + 0.5, + 0.74609375, + 0.74609375 + ], + [ + 0.5, + 0.8359375, + 0.8359375 + ], + [ + 0.5, + 0.927734375, + 0.927734375 + ], + [ + 0.5, + 0.626953125, + 0.626953125 + ], + [ + 0.5, + 0.84375, + 0.84375 + ], + [ + 0.5, + 0.943359375, + 0.943359375 + ], + [ + 0.5, + 0.748046875, + 0.748046875 + ], + [ + 0.5, + 0.962890625, + 0.962890625 + ], + [ + 0.5, + 0.90625, + 0.90625 + ], + [ + 0.5, + 0.693359375, + 0.693359375 + ], + [ + 0.5, + 0.8203125, + 0.8203125 + ], + [ + 0.5, + 0.72265625, + 0.72265625 + ], + [ + 0.5, + 0.79296875, + 0.79296875 + ], + [ + 0.5, + 0.79296875, + 0.79296875 + ], + [ + 0.5, + 0.791015625, + 0.791015625 + ], + [ + 0.5, + 0.73828125, + 0.73828125 + ], + [ + 0.5, + 0.798828125, + 0.798828125 + ], + [ + 0.5, + 0.71875, + 0.71875 + ], + [ + 0.5, + 0.6484375, + 0.6484375 + ], + [ + 0.5, + 0.79296875, + 0.79296875 + ], + [ + 0.5, + 0.681640625, + 0.681640625 + ], + [ + 0.5, + 0.58203125, + 0.58203125 + ], + [ + 0.5, + 0.564453125, + 0.564453125 + ], + [ + 0.5, + 0.765625, + 0.765625 + ], + [ + 0.5, + 0.71875, + 0.71875 + ], + [ + 0.5, + 0.791015625, + 0.791015625 + ], + [ + 0.5, + 0.638671875, + 0.638671875 + ], + [ + 0.5, + 0.833984375, + 0.833984375 + ], + [ + 0.5, + 0.669921875, + 0.669921875 + ], + [ + 0.5, + 0.759765625, + 0.759765625 + ], + [ + 0.5, + 0.96875, + 0.96875 + ], + [ + 0.5, + 0.74609375, + 0.74609375 + ], + [ + 0.5, + 0.60546875, + 0.60546875 + ], + [ + 0.5, + 0.953125, + 0.953125 + ], + [ + 0.5, + 0.767578125, + 0.767578125 + ], + [ + 0.5, + 0.658203125, + 0.658203125 + ], + [ + 0.5, + 0.71875, + 0.71875 + ], + [ + 0.5, + 0.75390625, + 0.75390625 + ], + [ + 0.5, + 0.78125, + 0.78125 + ], + [ + 0.5, + 0.75, + 0.75 + ], + [ + 0.5, + 0.6015625, + 0.6015625 + ], + [ + 0.5, + 0.650390625, + 0.650390625 + ], + [ + 0.5, + 0.8671875, + 0.8671875 + ], + [ + 0.5, + 0.62890625, + 0.62890625 + ], + [ + 0.5, + 0.640625, + 0.640625 + ], + [ + 0.5, + 0.669921875, + 0.669921875 + ], + [ + 0.5, + 0.658203125, + 0.658203125 + ], + [ + 0.5, + 0.734375, + 0.734375 + ], + [ + 0.5, + 0.83203125, + 0.83203125 + ], + [ + 0.5, + 0.83984375, + 0.83984375 + ], + [ + 0.5, + 0.8046875, + 0.8046875 + ], + [ + 0.5, + 0.9765625, + 0.9765625 + ], + [ + 0.5, + 0.70703125, + 0.70703125 + ], + [ + 0.5, + 0.86328125, + 0.86328125 + ], + [ + 0.5, + 0.890625, + 0.890625 + ], + [ + 0.5, + 0.8671875, + 0.8671875 + ], + [ + 0.5, + 0.865234375, + 0.865234375 + ], + [ + 0.5, + 0.76171875, + 0.76171875 + ], + [ + 0.5, + 0.720703125, + 0.720703125 + ], + [ + 0.5, + 0.76171875, + 0.76171875 + ], + [ + 0.5, + 0.66796875, + 0.66796875 + ], + [ + 0.5, + 0.84375, + 0.84375 + ], + [ + 0.5, + 0.541015625, + 0.541015625 + ], + [ + 0.5, + 0.76953125, + 0.76953125 + ], + [ + 0.5, + 0.669921875, + 0.669921875 + ], + [ + 0.5, + 0.86328125, + 0.86328125 + ], + [ + 0.5, + 0.74609375, + 0.74609375 + ], + [ + 0.5, + 0.921875, + 0.921875 + ], + [ + 0.5, + 0.783203125, + 0.783203125 + ], + [ + 0.5, + 0.90625, + 0.90625 + ], + [ + 0.5, + 0.81640625, + 0.81640625 + ], + [ + 0.5, + 0.77734375, + 0.77734375 + ], + [ + 0.5, + 0.7890625, + 0.7890625 + ], + [ + 0.5, + 0.7109375, + 0.7109375 + ], + [ + 0.5, + 0.857421875, + 0.857421875 + ], + [ + 0.5, + 0.8203125, + 0.8203125 + ], + [ + 0.5, + 0.7890625, + 0.7890625 + ], + [ + 0.5, + 0.734375, + 0.734375 + ], + [ + 0.5, + 0.72265625, + 0.72265625 + ], + [ + 0.5, + 0.791015625, + 0.791015625 + ], + [ + 0.5, + 0.61328125, + 0.61328125 + ], + [ + 0.5, + 0.9765625, + 0.9765625 + ], + [ + 0.5, + 0.69140625, + 0.69140625 + ], + [ + 0.5, + 0.88671875, + 0.88671875 + ], + [ + 0.5, + 0.650390625, + 0.650390625 + ], + [ + 0.5, + 0.78515625, + 0.78515625 + ], + [ + 0.5, + 0.72265625, + 0.72265625 + ], + [ + 0.5, + 0.701171875, + 0.701171875 + ], + [ + 0.5, + 0.796875, + 0.796875 + ], + [ + 0.5, + 0.77734375, + 0.77734375 + ], + [ + 0.5, + 0.78125, + 0.78125 + ], + [ + 0.5, + 0.73046875, + 0.73046875 + ], + [ + 0.5, + 0.82421875, + 0.82421875 + ], + [ + 0.5, + 0.60546875, + 0.60546875 + ], + [ + 0.5, + 0.7578125, + 0.7578125 + ], + [ + 0.5, + 0.673828125, + 0.673828125 + ], + [ + 0.5, + 0.7109375, + 0.7109375 + ], + [ + 0.5, + 0.76171875, + 0.76171875 + ], + [ + 0.5, + 0.6953125, + 0.6953125 + ], + [ + 0.5, + 0.828125, + 0.828125 + ], + [ + 0.5, + 0.6875, + 0.6875 + ], + [ + 0.5, + 0.61328125, + 0.61328125 + ], + [ + 0.5, + 0.751953125, + 0.751953125 + ], + [ + 0.5, + 0.890625, + 0.890625 + ], + [ + 0.5, + 0.66796875, + 0.66796875 + ], + [ + 0.5, + 0.67578125, + 0.67578125 + ], + [ + 0.5, + 0.685546875, + 0.685546875 + ], + [ + 0.5, + 0.681640625, + 0.681640625 + ], + [ + 0.5, + 0.828125, + 0.828125 + ], + [ + 0.5, + 0.958984375, + 0.958984375 + ], + [ + 0.5, + 0.66015625, + 0.66015625 + ], + [ + 0.5, + 0.775390625, + 0.775390625 + ], + [ + 0.5, + 0.75, + 0.75 + ], + [ + 0.5, + 0.62890625, + 0.62890625 + ], + [ + 0.5, + 0.79296875, + 0.79296875 + ], + [ + 0.5, + 0.64453125, + 0.64453125 + ], + [ + 0.5, + 0.640625, + 0.640625 + ], + [ + 0.5, + 0.68359375, + 0.68359375 + ], + [ + 0.5, + 0.703125, + 0.703125 + ], + [ + 0.5, + 0.63671875, + 0.63671875 + ], + [ + 0.5, + 0.673828125, + 0.673828125 + ], + [ + 0.5, + 0.94921875, + 0.94921875 + ], + [ + 0.5, + 0.83984375, + 0.83984375 + ], + [ + 0.5, + 0.72265625, + 0.72265625 + ], + [ + 0.5, + 0.73046875, + 0.73046875 + ], + [ + 0.5, + 0.80859375, + 0.80859375 + ], + [ + 0.5, + 0.828125, + 0.828125 + ], + [ + 0.5, + 0.74609375, + 0.74609375 + ], + [ + 0.5, + 0.828125, + 0.828125 + ], + [ + 0.5, + 0.66015625, + 0.66015625 + ], + [ + 0.5, + 0.75, + 0.75 + ], + [ + 0.5, + 0.724609375, + 0.724609375 + ], + [ + 0.5, + 0.828125, + 0.828125 + ], + [ + 0.5, + 0.681640625, + 0.681640625 + ], + [ + 0.5, + 0.673828125, + 0.673828125 + ], + [ + 0.800000011920929, + 0.9765625, + 0.9765625 + ], + [ + 0.5, + 0.65625, + 0.65625 + ], + [ + 0.5, + 0.732421875, + 0.732421875 + ], + [ + 0.5, + 0.73828125, + 0.73828125 + ], + [ + 0.625, + 0.8144530057907104, + 0.8144530057907104 + ], + [ + 0.5, + 0.640625, + 0.640625 + ], + [ + 0.5, + 0.66015625, + 0.66015625 + ], + [ + 0.5, + 0.734375, + 0.734375 + ], + [ + 0.5, + 0.55859375, + 0.55859375 + ], + [ + 0.5, + 0.70703125, + 0.70703125 + ], + [ + 0.5, + 0.759765625, + 0.759765625 + ], + [ + 0.5, + 0.8515625, + 0.8515625 + ], + [ + 0.5, + 0.662109375, + 0.662109375 + ], + [ + 0.5, + 0.720703125, + 0.720703125 + ], + [ + 0.5, + 0.828125, + 0.828125 + ], + [ + 0.5, + 0.7265625, + 0.7265625 + ], + [ + 0.5, + 0.90234375, + 0.90234375 + ], + [ + 0.5, + 0.64453125, + 0.64453125 + ], + [ + 0.5, + 0.5, + 0.5 + ], + [ + 0.5, + 0.6875, + 0.6875 + ], + [ + 0.5, + 0.78125, + 0.78125 + ], + [ + 0.5, + 0.64453125, + 0.64453125 + ], + [ + 0.5, + 0.79296875, + 0.79296875 + ], + [ + 0.5, + 0.78125, + 0.78125 + ], + [ + 0.5, + 0.7421875, + 0.7421875 + ], + [ + 0.5, + 0.60546875, + 0.60546875 + ], + [ + 0.5, + 0.5859375, + 0.5859375 + ], + [ + 0.5, + 0.7265625, + 0.7265625 + ], + [ + 0.5, + 0.72265625, + 0.72265625 + ], + [ + 0.5, + 0.7109375, + 0.7109375 + ], + [ + 0.5, + 0.5859375, + 0.5859375 + ], + [ + 0.5, + 0.7421875, + 0.7421875 + ], + [ + 0.5, + 0.6953125, + 0.6953125 + ], + [ + 0.5, + 0.7421875, + 0.7421875 + ], + [ + 0.5, + 0.662109375, + 0.662109375 + ], + [ + 0.5, + 0.75390625, + 0.75390625 + ], + [ + 0.5, + 0.70703125, + 0.70703125 + ], + [ + 0.5, + 0.92578125, + 0.92578125 + ], + [ + 0.5, + 0.765625, + 0.765625 + ], + [ + 0.5, + 0.6796875, + 0.6796875 + ], + [ + 0.5, + 0.73828125, + 0.73828125 + ], + [ + 0.5, + 0.71484375, + 0.71484375 + ], + [ + 0.5, + 0.7578125, + 0.7578125 + ], + [ + 0.5, + 0.859375, + 0.859375 + ], + [ + 0.5, + 0.578125, + 0.578125 + ], + [ + 0.5, + 0.796875, + 0.796875 + ], + [ + 0.5, + 0.75, + 0.75 + ], + [ + 0.5, + 0.64453125, + 0.64453125 + ], + [ + 0.5, + 0.64453125, + 0.64453125 + ], + [ + 0.5, + 0.75, + 0.75 + ], + [ + 0.5, + 0.75, + 0.75 + ], + [ + 0.5, + 0.712890625, + 0.712890625 + ], + [ + 0.5, + 0.64453125, + 0.64453125 + ], + [ + 0.5, + 0.7421875, + 0.7421875 + ], + [ + 0.5, + 0.5859375, + 0.5859375 + ], + [ + 0.5, + 0.70703125, + 0.70703125 + ], + [ + 0.5, + 0.810546875, + 0.810546875 + ], + [ + 0.5, + 0.6328125, + 0.6328125 + ], + [ + 0.5, + 0.6640625, + 0.6640625 + ], + [ + 0.5, + 0.65234375, + 0.65234375 + ], + [ + 0.5, + 0.62890625, + 0.62890625 + ], + [ + 0.5, + 0.5859375, + 0.5859375 + ], + [ + 0.5, + 0.5703125, + 0.5703125 + ], + [ + 0.5, + 0.876953125, + 0.876953125 + ], + [ + 0.5, + 0.6953125, + 0.6953125 + ], + [ + 0.5, + 0.859375, + 0.859375 + ], + [ + 0.5, + 0.71484375, + 0.71484375 + ], + [ + 0.5, + 0.552734375, + 0.552734375 + ], + [ + 0.5, + 0.626953125, + 0.626953125 + ], + [ + 0.5, + 0.734375, + 0.734375 + ], + [ + 0.5, + 0.796875, + 0.796875 + ], + [ + 0.5, + 0.80859375, + 0.80859375 + ], + [ + 0.5, + 0.63671875, + 0.63671875 + ], + [ + 0.5, + 0.79296875, + 0.79296875 + ], + [ + 0.5, + 0.6171875, + 0.6171875 + ], + [ + 0.5, + 0.8203125, + 0.8203125 + ], + [ + 0.5, + 0.6640625, + 0.6640625 + ], + [ + 0.5, + 0.759765625, + 0.759765625 + ], + [ + 0.5, + 0.8203125, + 0.8203125 + ], + [ + 0.5, + 0.8984375, + 0.8984375 + ], + [ + 0.5, + 0.7421875, + 0.7421875 + ], + [ + 0.5, + 0.5976561903953552, + 0.5976561903953552 + ], + [ + 0.5, + 0.6328125, + 0.6328125 + ], + [ + 0.5, + 0.6523438096046448, + 0.6523438096046448 + ], + [ + 0.5, + 0.8671875, + 0.8671875 + ], + [ + 0.5, + 0.875, + 0.875 + ], + [ + 0.5, + 0.734375, + 0.734375 + ], + [ + 0.5, + 0.552734375, + 0.552734375 + ], + [ + 0.5, + 0.626953125, + 0.626953125 + ], + [ + 0.5, + 0.841796875, + 0.841796875 + ], + [ + 0.5, + 0.734375, + 0.734375 + ], + [ + 0.5, + 0.796875, + 0.796875 + ], + [ + 0.5, + 0.68359375, + 0.68359375 + ], + [ + 0.5, + 0.634765625, + 0.634765625 + ], + [ + 0.5, + 0.75390625, + 0.75390625 + ], + [ + 0.5, + 0.7890625, + 0.7890625 + ], + [ + 0.5, + 0.8984375, + 0.8984375 + ], + [ + 0.5, + 0.73046875, + 0.73046875 + ], + [ + 0.5, + 0.619140625, + 0.619140625 + ], + [ + 0.5, + 0.7109375, + 0.7109375 + ], + [ + 0.5, + 0.669921875, + 0.669921875 + ], + [ + 0.5, + 0.744140625, + 0.744140625 + ], + [ + 0.5, + 0.587890625, + 0.587890625 + ], + [ + 0.5, + 0.84765625, + 0.84765625 + ], + [ + 0.5, + 0.62890625, + 0.62890625 + ], + [ + 0.5, + 0.70703125, + 0.70703125 + ], + [ + 0.5, + 0.7734375, + 0.7734375 + ], + [ + 0.5, + 0.83984375, + 0.83984375 + ], + [ + 0.5, + 0.669921875, + 0.669921875 + ], + [ + 0.5, + 0.630859375, + 0.630859375 + ], + [ + 0.5, + 0.779296875, + 0.779296875 + ], + [ + 0.5, + 0.7265625, + 0.7265625 + ], + [ + 0.5, + 0.787109375, + 0.787109375 + ], + [ + 0.5, + 0.642578125, + 0.642578125 + ], + [ + 0.5, + 0.94921875, + 0.94921875 + ], + [ + 0.5, + 0.875, + 0.875 + ], + [ + 0.5, + 0.693359375, + 0.693359375 + ], + [ + 0.5, + 0.689453125, + 0.689453125 + ], + [ + 0.5, + 0.6953125, + 0.6953125 + ], + [ + 0.5, + 0.71484375, + 0.71484375 + ], + [ + 0.5, + 0.7421875, + 0.7421875 + ], + [ + 0.5, + 0.5625, + 0.5625 + ], + [ + 0.5, + 0.6953125, + 0.6953125 + ], + [ + 0.5, + 0.7265625, + 0.7265625 + ], + [ + 0.5, + 0.59375, + 0.59375 + ], + [ + 0.5, + 0.697265625, + 0.697265625 + ], + [ + 0.5, + 0.66015625, + 0.66015625 + ], + [ + 0.5, + 0.7421875, + 0.7421875 + ], + [ + 0.5, + 0.654296875, + 0.654296875 + ], + [ + 0.5, + 0.7421875, + 0.7421875 + ], + [ + 0.5, + 0.78515625, + 0.78515625 + ], + [ + 0.5, + 0.828125, + 0.828125 + ], + [ + 0.5, + 0.875, + 0.875 + ], + [ + 0.5, + 0.6328125, + 0.6328125 + ], + [ + 0.5, + 0.76953125, + 0.76953125 + ], + [ + 0.5, + 0.9765625, + 0.9765625 + ], + [ + 0.5, + 0.65625, + 0.65625 + ], + [ + 0.5, + 0.751953125, + 0.751953125 + ], + [ + 0.5, + 0.63671875, + 0.63671875 + ], + [ + 0.5, + 0.8203125, + 0.8203125 + ], + [ + 0.5, + 0.69921875, + 0.69921875 + ], + [ + 0.5, + 0.70703125, + 0.70703125 + ], + [ + 0.5, + 0.6484375, + 0.6484375 + ], + [ + 0.5, + 0.87109375, + 0.87109375 + ], + [ + 0.5, + 0.78125, + 0.78125 + ], + [ + 0.5, + 0.91796875, + 0.91796875 + ], + [ + 0.5, + 0.69140625, + 0.69140625 + ], + [ + 0.5, + 0.626953125, + 0.626953125 + ], + [ + 0.5, + 0.556640625, + 0.556640625 + ], + [ + 0.5, + 0.6484375, + 0.6484375 + ], + [ + 0.5, + 0.9453125, + 0.9453125 + ], + [ + 0.5, + 0.734375, + 0.734375 + ], + [ + 0.5, + 0.69921875, + 0.69921875 + ], + [ + 0.5, + 0.697265625, + 0.697265625 + ], + [ + 0.5, + 0.7578125, + 0.7578125 + ], + [ + 0.5, + 0.8046875, + 0.8046875 + ], + [ + 0.5, + 0.578125, + 0.578125 + ], + [ + 0.5, + 0.83984375, + 0.83984375 + ], + [ + 0.5, + 0.7578125, + 0.7578125 + ], + [ + 0.5, + 0.744140625, + 0.744140625 + ], + [ + 0.5, + 0.6015625, + 0.6015625 + ], + [ + 0.5, + 0.904296875, + 0.904296875 + ], + [ + 0.5, + 0.66015625, + 0.66015625 + ], + [ + 0.5, + 0.79296875, + 0.79296875 + ], + [ + 0.5, + 0.787109375, + 0.787109375 + ], + [ + 0.5, + 0.64453125, + 0.64453125 + ], + [ + 0.5, + 0.625, + 0.625 + ], + [ + 0.5, + 0.625, + 0.625 + ], + [ + 0.5, + 0.966796875, + 0.966796875 + ], + [ + 0.5, + 0.66015625, + 0.66015625 + ], + [ + 0.5, + 0.86328125, + 0.86328125 + ], + [ + 0.5, + 0.7265625, + 0.7265625 + ], + [ + 0.5, + 0.6484375, + 0.6484375 + ], + [ + 0.5, + 0.5625, + 0.5625 + ], + [ + 0.5, + 0.693359375, + 0.693359375 + ], + [ + 0.5, + 0.84765625, + 0.84765625 + ], + [ + 0.5, + 0.57421875, + 0.57421875 + ], + [ + 0.5, + 0.78125, + 0.78125 + ], + [ + 0.5, + 0.783203125, + 0.783203125 + ], + [ + 0.5, + 0.640625, + 0.640625 + ], + [ + 0.5, + 0.734375, + 0.734375 + ], + [ + 0.5, + 0.68359375, + 0.68359375 + ], + [ + 0.5, + 0.81640625, + 0.81640625 + ], + [ + 0.5, + 0.9453125, + 0.9453125 + ], + [ + 0.5, + 0.626953125, + 0.626953125 + ], + [ + 0.5, + 0.73046875, + 0.73046875 + ], + [ + 0.5, + 0.880859375, + 0.880859375 + ], + [ + 0.5, + 0.662109375, + 0.662109375 + ], + [ + 0.5, + 0.76171875, + 0.76171875 + ], + [ + 0.5, + 0.625, + 0.625 + ], + [ + 0.5, + 0.6875, + 0.6875 + ], + [ + 0.5, + 0.68359375, + 0.68359375 + ], + [ + 0.5, + 0.900390625, + 0.900390625 + ], + [ + 0.5, + 0.74609375, + 0.74609375 + ], + [ + 0.5, + 0.845703125, + 0.845703125 + ], + [ + 0.5, + 0.611328125, + 0.611328125 + ], + [ + 0.5, + 0.8515625, + 0.8515625 + ], + [ + 0.5, + 0.8125, + 0.8125 + ], + [ + 0.5, + 0.75, + 0.75 + ], + [ + 0.5, + 0.7578125, + 0.7578125 + ], + [ + 0.5, + 0.9140625, + 0.9140625 + ], + [ + 0.5, + 0.7265625, + 0.7265625 + ], + [ + 0.5, + 0.71875, + 0.71875 + ], + [ + 0.5, + 0.80078125, + 0.80078125 + ], + [ + 0.5, + 0.82421875, + 0.82421875 + ], + [ + 0.5, + 0.7578125, + 0.7578125 + ], + [ + 0.5, + 0.80078125, + 0.80078125 + ], + [ + 0.5, + 0.669921875, + 0.669921875 + ], + [ + 0.5, + 0.65625, + 0.65625 + ], + [ + 0.5, + 0.708984375, + 0.708984375 + ], + [ + 0.5, + 0.6484375, + 0.6484375 + ], + [ + 0.5, + 0.646484375, + 0.646484375 + ], + [ + 0.5, + 0.61328125, + 0.61328125 + ], + [ + 0.5, + 0.65625, + 0.65625 + ], + [ + 0.5, + 0.9140625, + 0.9140625 + ], + [ + 0.5, + 0.6640625, + 0.6640625 + ], + [ + 0.5, + 0.5234375, + 0.5234375 + ], + [ + 0.5, + 0.787109375, + 0.787109375 + ], + [ + 0.5, + 0.828125, + 0.828125 + ], + [ + 0.5, + 0.744140625, + 0.744140625 + ], + [ + 0.5, + 0.701171875, + 0.701171875 + ], + [ + 0.5, + 0.734375, + 0.734375 + ], + [ + 0.5, + 0.75, + 0.75 + ], + [ + 0.5, + 0.623046875, + 0.623046875 + ], + [ + 0.5, + 0.9765625, + 0.9765625 + ], + [ + 0.5, + 0.6796875, + 0.6796875 + ], + [ + 0.5, + 0.701171875, + 0.701171875 + ], + [ + 0.5, + 0.646484375, + 0.646484375 + ], + [ + 0.5, + 0.5546875, + 0.5546875 + ], + [ + 0.5, + 0.67578125, + 0.67578125 + ], + [ + 0.5, + 0.77734375, + 0.77734375 + ], + [ + 0.5, + 0.966796875, + 0.966796875 + ], + [ + 0.5, + 0.68359375, + 0.68359375 + ], + [ + 0.5, + 0.71484375, + 0.71484375 + ], + [ + 0.5, + 0.6875, + 0.6875 + ], + [ + 0.5, + 0.6484375, + 0.6484375 + ], + [ + 0.5, + 0.693359375, + 0.693359375 + ], + [ + 0.5, + 0.609375, + 0.609375 + ], + [ + 0.5, + 0.576171875, + 0.576171875 + ], + [ + 0.5, + 0.79296875, + 0.79296875 + ], + [ + 0.5, + 0.703125, + 0.703125 + ], + [ + 0.5, + 0.671875, + 0.671875 + ], + [ + 0.5, + 0.736328125, + 0.736328125 + ], + [ + 0.5, + 0.73046875, + 0.73046875 + ], + [ + 0.5, + 0.791015625, + 0.791015625 + ], + [ + 0.5, + 0.52734375, + 0.52734375 + ], + [ + 0.5, + 0.810546875, + 0.810546875 + ], + [ + 0.5, + 0.76171875, + 0.76171875 + ], + [ + 0.5, + 0.6953125, + 0.6953125 + ], + [ + 0.5, + 0.677734375, + 0.677734375 + ], + [ + 0.5, + 0.8359375, + 0.8359375 + ], + [ + 0.5, + 0.69921875, + 0.69921875 + ], + [ + 0.5, + 0.630859375, + 0.630859375 + ], + [ + 0.5, + 0.75390625, + 0.75390625 + ], + [ + 0.5, + 0.78125, + 0.78125 + ], + [ + 0.5, + 0.70703125, + 0.70703125 + ], + [ + 0.5, + 0.654296875, + 0.654296875 + ], + [ + 0.5, + 0.90234375, + 0.90234375 + ], + [ + 0.5, + 0.9140625, + 0.9140625 + ], + [ + 0.5, + 0.685546875, + 0.685546875 + ], + [ + 0.5, + 0.58203125, + 0.58203125 + ], + [ + 0.5, + 0.576171875, + 0.576171875 + ], + [ + 0.5, + 0.72265625, + 0.72265625 + ], + [ + 0.5, + 0.65625, + 0.65625 + ], + [ + 0.5, + 0.84765625, + 0.84765625 + ], + [ + 0.5, + 0.796875, + 0.796875 + ], + [ + 0.5, + 0.71484375, + 0.71484375 + ], + [ + 0.5, + 0.78125, + 0.78125 + ], + [ + 0.5, + 0.724609375, + 0.724609375 + ], + [ + 0.5, + 0.853515625, + 0.853515625 + ], + [ + 0.5, + 0.765625, + 0.765625 + ], + [ + 0.5, + 0.859375, + 0.859375 + ], + [ + 0.5, + 0.70703125, + 0.70703125 + ], + [ + 0.5, + 0.78515625, + 0.78515625 + ], + [ + 0.5, + 0.83984375, + 0.83984375 + ], + [ + 0.5, + 0.68359375, + 0.68359375 + ], + [ + 0.5, + 0.75390625, + 0.75390625 + ], + [ + 0.5, + 0.685546875, + 0.685546875 + ], + [ + 0.5, + 0.71875, + 0.71875 + ], + [ + 0.5, + 0.67578125, + 0.67578125 + ], + [ + 0.5, + 0.673828125, + 0.673828125 + ], + [ + 0.5, + 0.703125, + 0.703125 + ], + [ + 0.5, + 0.73046875, + 0.73046875 + ], + [ + 0.5, + 0.8046875, + 0.8046875 + ], + [ + 0.5, + 0.78515625, + 0.78515625 + ], + [ + 0.5, + 0.697265625, + 0.697265625 + ], + [ + 0.5, + 0.71484375, + 0.71484375 + ], + [ + 0.5, + 0.65625, + 0.65625 + ], + [ + 0.5, + 0.7265625, + 0.7265625 + ], + [ + 0.5, + 0.8046875, + 0.8046875 + ], + [ + 0.5, + 0.81640625, + 0.81640625 + ], + [ + 0.5, + 0.80859375, + 0.80859375 + ], + [ + 0.5, + 0.66796875, + 0.66796875 + ], + [ + 0.5, + 0.9765625, + 0.9765625 + ], + [ + 0.5, + 0.96484375, + 0.96484375 + ], + [ + 0.5, + 0.65625, + 0.65625 + ], + [ + 0.5, + 0.67578125, + 0.67578125 + ], + [ + 0.5, + 0.6953125, + 0.6953125 + ], + [ + 0.5, + 0.66796875, + 0.66796875 + ], + [ + 0.5, + 0.791015625, + 0.791015625 + ], + [ + 0.5, + 0.765625, + 0.765625 + ], + [ + 0.5, + 0.83984375, + 0.83984375 + ], + [ + 0.5, + 0.7734375, + 0.7734375 + ], + [ + 0.5, + 0.58984375, + 0.58984375 + ], + [ + 0.5, + 0.5859375, + 0.5859375 + ], + [ + 0.5, + 0.70703125, + 0.70703125 + ], + [ + 0.5, + 0.69921875, + 0.69921875 + ], + [ + 0.5, + 0.673828125, + 0.673828125 + ], + [ + 0.5, + 0.568359375, + 0.568359375 + ], + [ + 0.5, + 0.55859375, + 0.55859375 + ], + [ + 0.5, + 0.5859375, + 0.5859375 + ], + [ + 0.5, + 0.5859375, + 0.5859375 + ], + [ + 0.5, + 0.6171875, + 0.6171875 + ], + [ + 0.5, + 0.625, + 0.625 + ], + [ + 0.5, + 0.5859375, + 0.5859375 + ], + [ + 0.5, + 0.5859375, + 0.5859375 + ], + [ + 0.5, + 0.673828125, + 0.673828125 + ], + [ + 0.5, + 0.63671875, + 0.63671875 + ], + [ + 0.5, + 0.625, + 0.625 + ], + [ + 0.5, + 0.5859375, + 0.5859375 + ], + [ + 0.5, + 0.5859375, + 0.5859375 + ], + [ + 0.5, + 0.5859375, + 0.5859375 + ], + [ + 0.5, + 0.59375, + 0.59375 + ], + [ + 0.5, + 0.703125, + 0.703125 + ], + [ + 0.5, + 0.6328125, + 0.6328125 + ], + [ + 0.5, + 0.5859375, + 0.5859375 + ], + [ + 0.5, + 0.6328125, + 0.6328125 + ], + [ + 0.5, + 0.66015625, + 0.66015625 + ], + [ + 0.5, + 0.79296875, + 0.79296875 + ], + [ + 0.5, + 0.642578125, + 0.642578125 + ], + [ + 0.5, + 0.6875, + 0.6875 + ], + [ + 0.5, + 0.5859375, + 0.5859375 + ], + [ + 0.5, + 0.638671875, + 0.638671875 + ], + [ + 0.5, + 0.640625, + 0.640625 + ], + [ + 0.5, + 0.658203125, + 0.658203125 + ], + [ + 0.5, + 0.58203125, + 0.58203125 + ], + [ + 0.5, + 0.6875, + 0.6875 + ], + [ + 0.5, + 0.712890625, + 0.712890625 + ], + [ + 0.5, + 0.720703125, + 0.720703125 + ], + [ + 0.5, + 0.572265625, + 0.572265625 + ], + [ + 0.5, + 0.6328125, + 0.6328125 + ], + [ + 0.5, + 0.65625, + 0.65625 + ], + [ + 0.5, + 0.5859375, + 0.5859375 + ], + [ + 0.5, + 0.5859375, + 0.5859375 + ], + [ + 0.5, + 0.708984375, + 0.708984375 + ], + [ + 0.5, + 0.68359375, + 0.68359375 + ], + [ + 0.5, + 0.5625, + 0.5625 + ], + [ + 0.5, + 0.7421875, + 0.7421875 + ], + [ + 0.5, + 0.7421875, + 0.7421875 + ], + [ + 0.5, + 0.71875, + 0.71875 + ], + [ + 0.5, + 0.6328125, + 0.6328125 + ], + [ + 0.5, + 0.68359375, + 0.68359375 + ], + [ + 0.5, + 0.595703125, + 0.595703125 + ], + [ + 0.5, + 0.53515625, + 0.53515625 + ], + [ + 0.5, + 0.6875, + 0.6875 + ], + [ + 0.5, + 0.685546875, + 0.685546875 + ], + [ + 0.5, + 0.78125, + 0.78125 + ], + [ + 0.5, + 0.74609375, + 0.74609375 + ], + [ + 0.5, + 0.625, + 0.625 + ], + [ + 0.5, + 0.68359375, + 0.68359375 + ], + [ + 0.5, + 0.84375, + 0.84375 + ], + [ + 0.5, + 0.68359375, + 0.68359375 + ], + [ + 0.5, + 0.59375, + 0.59375 + ], + [ + 0.5, + 0.58984375, + 0.58984375 + ], + [ + 0.5, + 0.7265625, + 0.7265625 + ], + [ + 0.5, + 0.677734375, + 0.677734375 + ], + [ + 0.5, + 0.640625, + 0.640625 + ], + [ + 0.5, + 0.65625, + 0.65625 + ], + [ + 0.5, + 0.591796875, + 0.591796875 + ], + [ + 0.5, + 0.765625, + 0.765625 + ], + [ + 0.5, + 0.828125, + 0.828125 + ], + [ + 0.5, + 0.5859375, + 0.5859375 + ], + [ + 0.5, + 0.6328125, + 0.6328125 + ], + [ + 0.5, + 0.66796875, + 0.66796875 + ], + [ + 0.5, + 0.6015625, + 0.6015625 + ], + [ + 0.5, + 0.65625, + 0.65625 + ], + [ + 0.5, + 0.75390625, + 0.75390625 + ], + [ + 0.5, + 0.5859375, + 0.5859375 + ], + [ + 0.5, + 0.58984375, + 0.58984375 + ], + [ + 0.5, + 0.5390625, + 0.5390625 + ], + [ + 0.5, + 0.64453125, + 0.64453125 + ], + [ + 0.5, + 0.626953125, + 0.626953125 + ], + [ + 0.5, + 0.66015625, + 0.66015625 + ], + [ + 0.5, + 0.724609375, + 0.724609375 + ], + [ + 0.5, + 0.71875, + 0.71875 + ], + [ + 0.5, + 0.65234375, + 0.65234375 + ], + [ + 0.5, + 0.5859375, + 0.5859375 + ], + [ + 0.5, + 0.59765625, + 0.59765625 + ], + [ + 0.5, + 0.603515625, + 0.603515625 + ], + [ + 0.5, + 0.60546875, + 0.60546875 + ], + [ + 0.5, + 0.728515625, + 0.728515625 + ], + [ + 0.5, + 0.5859375, + 0.5859375 + ], + [ + 0.5, + 0.6015625, + 0.6015625 + ], + [ + 0.5, + 0.5859375, + 0.5859375 + ], + [ + 0.5, + 0.7109375, + 0.7109375 + ], + [ + 0.5, + 0.626953125, + 0.626953125 + ], + [ + 0.5, + 0.58203125, + 0.58203125 + ], + [ + 0.5, + 0.703125, + 0.703125 + ], + [ + 0.5, + 0.7109375, + 0.7109375 + ], + [ + 0.5, + 0.625, + 0.625 + ], + [ + 0.5, + 0.7421875, + 0.7421875 + ], + [ + 0.5, + 0.66015625, + 0.66015625 + ], + [ + 0.5, + 0.5859375, + 0.5859375 + ], + [ + 0.5, + 0.638671875, + 0.638671875 + ], + [ + 0.5, + 0.693359375, + 0.693359375 + ], + [ + 0.5, + 0.7421875, + 0.7421875 + ], + [ + 0.5, + 0.7265625, + 0.7265625 + ], + [ + 0.5, + 0.67578125, + 0.67578125 + ], + [ + 0.5, + 0.5859375, + 0.5859375 + ], + [ + 0.5, + 0.640625, + 0.640625 + ], + [ + 0.5, + 0.5859375, + 0.5859375 + ], + [ + 0.5, + 0.650390625, + 0.650390625 + ], + [ + 0.5, + 0.6171875, + 0.6171875 + ], + [ + 0.5, + 0.5859375, + 0.5859375 + ], + [ + 0.5, + 0.615234375, + 0.615234375 + ], + [ + 0.5, + 0.7421875, + 0.7421875 + ], + [ + 0.5, + 0.7890625, + 0.7890625 + ], + [ + 0.5, + 0.6640625, + 0.6640625 + ], + [ + 0.5, + 0.5859375, + 0.5859375 + ], + [ + 0.5, + 0.791015625, + 0.791015625 + ], + [ + 0.5, + 0.6484375, + 0.6484375 + ], + [ + 0.5, + 0.5859375, + 0.5859375 + ], + [ + 0.5, + 0.630859375, + 0.630859375 + ], + [ + 0.5, + 0.74609375, + 0.74609375 + ], + [ + 0.5, + 0.74609375, + 0.74609375 + ], + [ + 0.5, + 0.65234375, + 0.65234375 + ], + [ + 0.5, + 0.5859375, + 0.5859375 + ], + [ + 0.5, + 0.5859375, + 0.5859375 + ], + [ + 0.5, + 0.5859375, + 0.5859375 + ], + [ + 0.5, + 0.65625, + 0.65625 + ], + [ + 0.5, + 0.71484375, + 0.71484375 + ], + [ + 0.5, + 0.59375, + 0.59375 + ], + [ + 0.5, + 0.552734375, + 0.552734375 + ], + [ + 0.5, + 0.671875, + 0.671875 + ], + [ + 0.5, + 0.640625, + 0.640625 + ], + [ + 0.5, + 0.68359375, + 0.68359375 + ], + [ + 0.5, + 0.630859375, + 0.630859375 + ], + [ + 0.5, + 0.59765625, + 0.59765625 + ], + [ + 0.5, + 0.5859375, + 0.5859375 + ], + [ + 0.5, + 0.5859375, + 0.5859375 + ], + [ + 0.5, + 0.57421875, + 0.57421875 + ], + [ + 0.5, + 0.666015625, + 0.666015625 + ], + [ + 0.5, + 0.703125, + 0.703125 + ], + [ + 0.5, + 0.5546875, + 0.5546875 + ], + [ + 0.5, + 0.7421875, + 0.7421875 + ], + [ + 0.5, + 0.619140625, + 0.619140625 + ], + [ + 0.5, + 0.5859375, + 0.5859375 + ], + [ + 0.5, + 0.740234375, + 0.740234375 + ], + [ + 0.5, + 0.744140625, + 0.744140625 + ], + [ + 0.5, + 0.875, + 0.875 + ], + [ + 0.5, + 0.6328125, + 0.6328125 + ], + [ + 0.5, + 0.615234375, + 0.615234375 + ], + [ + 0.5, + 0.626953125, + 0.626953125 + ], + [ + 0.5, + 0.5859375, + 0.5859375 + ], + [ + 0.5, + 0.62109375, + 0.62109375 + ], + [ + 0.5, + 0.693359375, + 0.693359375 + ], + [ + 0.5, + 0.66796875, + 0.66796875 + ], + [ + 0.5, + 0.70703125, + 0.70703125 + ], + [ + 0.5, + 0.5859375, + 0.5859375 + ], + [ + 0.5, + 0.65625, + 0.65625 + ], + [ + 0.5, + 0.5859375, + 0.5859375 + ], + [ + 0.5, + 0.666015625, + 0.666015625 + ], + [ + 0.5, + 0.658203125, + 0.658203125 + ], + [ + 0.5, + 0.595703125, + 0.595703125 + ], + [ + 0.5, + 0.611328125, + 0.611328125 + ], + [ + 0.5, + 0.724609375, + 0.724609375 + ], + [ + 0.5, + 0.5859375, + 0.5859375 + ], + [ + 0.5, + 0.6328125, + 0.6328125 + ], + [ + 0.5, + 0.67578125, + 0.67578125 + ], + [ + 0.5, + 0.595703125, + 0.595703125 + ], + [ + 0.5, + 0.66015625, + 0.66015625 + ], + [ + 0.5, + 0.6328125, + 0.6328125 + ], + [ + 0.5, + 0.583984375, + 0.583984375 + ], + [ + 0.5, + 0.603515625, + 0.603515625 + ], + [ + 0.5, + 0.662109375, + 0.662109375 + ], + [ + 0.5, + 0.65234375, + 0.65234375 + ], + [ + 0.5, + 0.708984375, + 0.708984375 + ], + [ + 0.5, + 0.65625, + 0.65625 + ], + [ + 0.5, + 0.4765625, + 0.4765625 + ], + [ + 0.5, + 0.59765625, + 0.59765625 + ], + [ + 0.5, + 0.724609375, + 0.724609375 + ], + [ + 0.5, + 0.79296875, + 0.79296875 + ], + [ + 0.5, + 0.583984375, + 0.583984375 + ], + [ + 0.5, + 0.7421875, + 0.7421875 + ], + [ + 0.5, + 0.69140625, + 0.69140625 + ], + [ + 0.5, + 0.62890625, + 0.62890625 + ], + [ + 0.5, + 0.5859375, + 0.5859375 + ], + [ + 0.5, + 0.65625, + 0.65625 + ], + [ + 0.5, + 0.7109375, + 0.7109375 + ], + [ + 0.5, + 0.84375, + 0.84375 + ], + [ + 0.5, + 0.67578125, + 0.67578125 + ], + [ + 0.5, + 0.642578125, + 0.642578125 + ], + [ + 0.5, + 0.703125, + 0.703125 + ], + [ + 0.5, + 0.7421875, + 0.7421875 + ], + [ + 0.5, + 0.6875, + 0.6875 + ], + [ + 0.5, + 0.7109375, + 0.7109375 + ], + [ + 0.5, + 0.583984375, + 0.583984375 + ], + [ + 0.5, + 0.7421875, + 0.7421875 + ], + [ + 0.5, + 0.5859375, + 0.5859375 + ], + [ + 0.5, + 0.771484375, + 0.771484375 + ], + [ + 0.5, + 0.654296875, + 0.654296875 + ], + [ + 0.5, + 0.720703125, + 0.720703125 + ], + [ + 0.5, + 0.5859375, + 0.5859375 + ], + [ + 0.5, + 0.638671875, + 0.638671875 + ], + [ + 0.5, + 0.734375, + 0.734375 + ], + [ + 0.5, + 0.69921875, + 0.69921875 + ], + [ + 0.5, + 0.619140625, + 0.619140625 + ], + [ + 0.5, + 0.626953125, + 0.626953125 + ], + [ + 0.5, + 0.591796875, + 0.591796875 + ], + [ + 0.5, + 0.666015625, + 0.666015625 + ], + [ + 0.5, + 0.60546875, + 0.60546875 + ], + [ + 0.5, + 0.595703125, + 0.595703125 + ], + [ + 0.5, + 0.5859375, + 0.5859375 + ], + [ + 0.5, + 0.53515625, + 0.53515625 + ], + [ + 0.5, + 0.587890625, + 0.587890625 + ], + [ + 0.5, + 0.6171875, + 0.6171875 + ], + [ + 0.5, + 0.576171875, + 0.576171875 + ], + [ + 0.5, + 0.802734375, + 0.802734375 + ], + [ + 0.5, + 0.7421875, + 0.7421875 + ], + [ + 0.5, + 0.7421875, + 0.7421875 + ], + [ + 0.5, + 0.755859375, + 0.755859375 + ], + [ + 0.5, + 0.5859375, + 0.5859375 + ], + [ + 0.5, + 0.70703125, + 0.70703125 + ], + [ + 0.5, + 0.67578125, + 0.67578125 + ], + [ + 0.5, + 0.623046875, + 0.623046875 + ], + [ + 0.5, + 0.658203125, + 0.658203125 + ], + [ + 0.5, + 0.693359375, + 0.693359375 + ], + [ + 0.5, + 0.73046875, + 0.73046875 + ], + [ + 0.5, + 0.62109375, + 0.62109375 + ], + [ + 0.5, + 0.638671875, + 0.638671875 + ], + [ + 0.5, + 0.748046875, + 0.748046875 + ], + [ + 0.5, + 0.669921875, + 0.669921875 + ], + [ + 0.5, + 0.7578125, + 0.7578125 + ], + [ + 0.5, + 0.640625, + 0.640625 + ], + [ + 0.5, + 0.65234375, + 0.65234375 + ], + [ + 0.5, + 0.642578125, + 0.642578125 + ], + [ + 0.5, + 0.60546875, + 0.60546875 + ], + [ + 0.5, + 0.6953125, + 0.6953125 + ], + [ + 0.5, + 0.5859375, + 0.5859375 + ], + [ + 0.5, + 0.626953125, + 0.626953125 + ], + [ + 0.5, + 0.7421875, + 0.7421875 + ], + [ + 0.5, + 0.76953125, + 0.76953125 + ], + [ + 0.5, + 0.619140625, + 0.619140625 + ], + [ + 0.5, + 0.5859375, + 0.5859375 + ], + [ + 0.5, + 0.693359375, + 0.693359375 + ], + [ + 0.5, + 0.6953125, + 0.6953125 + ], + [ + 0.5, + 0.73046875, + 0.73046875 + ], + [ + 0.5, + 0.681640625, + 0.681640625 + ], + [ + 0.5, + 0.6171875, + 0.6171875 + ], + [ + 0.5, + 0.62109375, + 0.62109375 + ], + [ + 0.5, + 0.658203125, + 0.658203125 + ], + [ + 0.5, + 0.6328125, + 0.6328125 + ], + [ + 0.5, + 0.57421875, + 0.57421875 + ], + [ + 0.5, + 0.6953125, + 0.6953125 + ], + [ + 0.5, + 0.654296875, + 0.654296875 + ], + [ + 0.5, + 0.609375, + 0.609375 + ], + [ + 0.5, + 0.751953125, + 0.751953125 + ], + [ + 0.5, + 0.615234375, + 0.615234375 + ], + [ + 0.5, + 0.58203125, + 0.58203125 + ], + [ + 0.5, + 0.689453125, + 0.689453125 + ], + [ + 0.5, + 0.625, + 0.625 + ], + [ + 0.5, + 0.7421875, + 0.7421875 + ], + [ + 0.5, + 0.611328125, + 0.611328125 + ], + [ + 0.5, + 0.650390625, + 0.650390625 + ], + [ + 0.5, + 0.91015625, + 0.91015625 + ], + [ + 0.5, + 0.732421875, + 0.732421875 + ], + [ + 0.5, + 0.7109375, + 0.7109375 + ], + [ + 0.5, + 0.6875, + 0.6875 + ], + [ + 0.5, + 0.7421875, + 0.7421875 + ], + [ + 0.5, + 0.68359375, + 0.68359375 + ], + [ + 0.5, + 0.7421875, + 0.7421875 + ], + [ + 0.5, + 0.6484375, + 0.6484375 + ], + [ + 0.5, + 0.7421875, + 0.7421875 + ], + [ + 0.5, + 0.625, + 0.625 + ], + [ + 0.5, + 0.7265625, + 0.7265625 + ], + [ + 0.5, + 0.751953125, + 0.751953125 + ], + [ + 0.5, + 0.5859375, + 0.5859375 + ], + [ + 0.5, + 0.6484375, + 0.6484375 + ], + [ + 0.5, + 0.712890625, + 0.712890625 + ], + [ + 0.5, + 0.6015625, + 0.6015625 + ], + [ + 0.5, + 0.669921875, + 0.669921875 + ], + [ + 0.5, + 0.583984375, + 0.583984375 + ], + [ + 0.5, + 0.5625, + 0.5625 + ], + [ + 0.5, + 0.587890625, + 0.587890625 + ], + [ + 0.5, + 0.701171875, + 0.701171875 + ], + [ + 0.5, + 0.642578125, + 0.642578125 + ], + [ + 0.5, + 0.7578125, + 0.7578125 + ], + [ + 0.5, + 0.6171875, + 0.6171875 + ], + [ + 0.5, + 0.720703125, + 0.720703125 + ], + [ + 0.5, + 0.720703125, + 0.720703125 + ], + [ + 0.5, + 0.69921875, + 0.69921875 + ], + [ + 0.5, + 0.701171875, + 0.701171875 + ], + [ + 0.5, + 0.5859375, + 0.5859375 + ], + [ + 0.5, + 0.615234375, + 0.615234375 + ], + [ + 0.5, + 0.68359375, + 0.68359375 + ], + [ + 0.5, + 0.6796875, + 0.6796875 + ], + [ + 0.5, + 0.7421875, + 0.7421875 + ], + [ + 0.5, + 0.802734375, + 0.802734375 + ], + [ + 0.5, + 0.73046875, + 0.73046875 + ], + [ + 0.5, + 0.68359375, + 0.68359375 + ], + [ + 0.5, + 0.748046875, + 0.748046875 + ], + [ + 0.5, + 0.7890625, + 0.7890625 + ], + [ + 0.5, + 0.68359375, + 0.68359375 + ], + [ + 0.5, + 0.58203125, + 0.58203125 + ], + [ + 0.5, + 0.6640625, + 0.6640625 + ], + [ + 0.5, + 0.62890625, + 0.62890625 + ], + [ + 0.5, + 0.87109375, + 0.87109375 + ], + [ + 0.5, + 0.572265625, + 0.572265625 + ], + [ + 0.5, + 0.599609375, + 0.599609375 + ], + [ + 0.5, + 0.689453125, + 0.689453125 + ], + [ + 0.5, + 0.55078125, + 0.55078125 + ], + [ + 0.5, + 0.751953125, + 0.751953125 + ], + [ + 0.5, + 0.60546875, + 0.60546875 + ], + [ + 0.5, + 0.68359375, + 0.68359375 + ], + [ + 0.5, + 0.76953125, + 0.76953125 + ], + [ + 0.5, + 0.68359375, + 0.68359375 + ], + [ + 0.5, + 0.75390625, + 0.75390625 + ], + [ + 0.5, + 0.6328125, + 0.6328125 + ], + [ + 0.5, + 0.68359375, + 0.68359375 + ], + [ + 0.5, + 0.740234375, + 0.740234375 + ], + [ + 0.5, + 0.64453125, + 0.64453125 + ], + [ + 0.5, + 0.73828125, + 0.73828125 + ], + [ + 0.5, + 0.671875, + 0.671875 + ], + [ + 0.5, + 0.595703125, + 0.595703125 + ], + [ + 0.5, + 0.6484375, + 0.6484375 + ], + [ + 0.5, + 0.66015625, + 0.66015625 + ], + [ + 0.5, + 0.63671875, + 0.63671875 + ], + [ + 0.5, + 0.662109375, + 0.662109375 + ], + [ + 0.5, + 0.65625, + 0.65625 + ], + [ + 0.5, + 0.640625, + 0.640625 + ], + [ + 0.5, + 0.681640625, + 0.681640625 + ], + [ + 0.5, + 0.626953125, + 0.626953125 + ], + [ + 0.5, + 0.75, + 0.75 + ], + [ + 0.5, + 0.68359375, + 0.68359375 + ], + [ + 0.5, + 0.828125, + 0.828125 + ], + [ + 0.5, + 0.7109375, + 0.7109375 + ], + [ + 0.5, + 0.68359375, + 0.68359375 + ], + [ + 0.5, + 0.728515625, + 0.728515625 + ], + [ + 0.5, + 0.5859375, + 0.5859375 + ], + [ + 0.5, + 0.5859375, + 0.5859375 + ], + [ + 0.5, + 0.68359375, + 0.68359375 + ], + [ + 0.5, + 0.64453125, + 0.64453125 + ], + [ + 0.5, + 0.69921875, + 0.69921875 + ], + [ + 0.5, + 0.5546875, + 0.5546875 + ], + [ + 0.5, + 0.68359375, + 0.68359375 + ], + [ + 0.5, + 0.68359375, + 0.68359375 + ], + [ + 0.5, + 0.68359375, + 0.68359375 + ], + [ + 0.5, + 0.5859375, + 0.5859375 + ], + [ + 0.5, + 0.90234375, + 0.90234375 + ], + [ + 0.5, + 0.7890625, + 0.7890625 + ], + [ + 0.5, + 0.68359375, + 0.68359375 + ], + [ + 0.5, + 0.734375, + 0.734375 + ], + [ + 0.5, + 0.826171875, + 0.826171875 + ], + [ + 0.5, + 0.7734375, + 0.7734375 + ], + [ + 0.5, + 0.5859375, + 0.5859375 + ], + [ + 0.5, + 0.5859375, + 0.5859375 + ], + [ + 0.5, + 0.5859375, + 0.5859375 + ], + [ + 0.5, + 0.68359375, + 0.68359375 + ], + [ + 0.5, + 0.73046875, + 0.73046875 + ], + [ + 0.5, + 0.75390625, + 0.75390625 + ], + [ + 0.5, + 0.68359375, + 0.68359375 + ], + [ + 0.5, + 0.77734375, + 0.77734375 + ], + [ + 0.5, + 0.587890625, + 0.587890625 + ], + [ + 0.5, + 0.7109375, + 0.7109375 + ], + [ + 0.5, + 0.68359375, + 0.68359375 + ], + [ + 0.5, + 0.7890625, + 0.7890625 + ], + [ + 0.5, + 0.90625, + 0.90625 + ], + [ + 0.5, + 0.68359375, + 0.68359375 + ], + [ + 0.5, + 0.68359375, + 0.68359375 + ], + [ + 0.5, + 0.5546875, + 0.5546875 + ], + [ + 0.5, + 0.68359375, + 0.68359375 + ], + [ + 0.5, + 0.810546875, + 0.810546875 + ], + [ + 0.5, + 0.70703125, + 0.70703125 + ], + [ + 0.5, + 0.767578125, + 0.767578125 + ], + [ + 0.5, + 0.71875, + 0.71875 + ], + [ + 0.5, + 0.68359375, + 0.68359375 + ], + [ + 0.5, + 0.70703125, + 0.70703125 + ], + [ + 0.5, + 0.9453125, + 0.9453125 + ], + [ + 0.5, + 0.74609375, + 0.74609375 + ], + [ + 0.5, + 0.65625, + 0.65625 + ], + [ + 0.5, + 0.90625, + 0.90625 + ], + [ + 0.5, + 0.71484375, + 0.71484375 + ], + [ + 0.5, + 0.78125, + 0.78125 + ], + [ + 0.5, + 0.68359375, + 0.68359375 + ], + [ + 0.5, + 0.87109375, + 0.87109375 + ], + [ + 0.5, + 0.765625, + 0.765625 + ], + [ + 0.5, + 0.68359375, + 0.68359375 + ], + [ + 0.5, + 0.79296875, + 0.79296875 + ], + [ + 0.5, + 0.76171875, + 0.76171875 + ], + [ + 0.5, + 0.68359375, + 0.68359375 + ], + [ + 0.5, + 0.765625, + 0.765625 + ], + [ + 0.5, + 0.79296875, + 0.79296875 + ], + [ + 0.5, + 0.55078125, + 0.55078125 + ], + [ + 0.5, + 0.6171875, + 0.6171875 + ], + [ + 0.5, + 0.70703125, + 0.70703125 + ], + [ + 0.5, + 0.662109375, + 0.662109375 + ], + [ + 0.5, + 0.68359375, + 0.68359375 + ], + [ + 0.5, + 0.73046875, + 0.73046875 + ], + [ + 0.5, + 0.78515625, + 0.78515625 + ], + [ + 0.5, + 0.6796875, + 0.6796875 + ], + [ + 0.5, + 0.68359375, + 0.68359375 + ], + [ + 0.5, + 0.69140625, + 0.69140625 + ], + [ + 0.5, + 0.689453125, + 0.689453125 + ], + [ + 0.5, + 0.677734375, + 0.677734375 + ], + [ + 0.5, + 0.74609375, + 0.74609375 + ], + [ + 0.5, + 0.80078125, + 0.80078125 + ], + [ + 0.5, + 0.669921875, + 0.669921875 + ], + [ + 0.5, + 0.7265625, + 0.7265625 + ], + [ + 0.5, + 0.724609375, + 0.724609375 + ], + [ + 0.5, + 0.640625, + 0.640625 + ], + [ + 0.5, + 0.64453125, + 0.64453125 + ], + [ + 0.5, + 0.65625, + 0.65625 + ], + [ + 0.5, + 0.716796875, + 0.716796875 + ], + [ + 0.5, + 0.76953125, + 0.76953125 + ], + [ + 0.5, + 0.576171875, + 0.576171875 + ], + [ + 0.5, + 0.564453125, + 0.564453125 + ], + [ + 0.5, + 0.70703125, + 0.70703125 + ], + [ + 0.5, + 0.82421875, + 0.82421875 + ], + [ + 0.5, + 0.78125, + 0.78125 + ], + [ + 0.5, + 0.607421875, + 0.607421875 + ], + [ + 0.5, + 0.84375, + 0.84375 + ], + [ + 0.5, + 0.6484375, + 0.6484375 + ], + [ + 0.5, + 0.734375, + 0.734375 + ], + [ + 0.5, + 0.78125, + 0.78125 + ], + [ + 0.5, + 0.88671875, + 0.88671875 + ], + [ + 0.5, + 0.81640625, + 0.81640625 + ], + [ + 0.5, + 0.8359375, + 0.8359375 + ], + [ + 0.5, + 0.64453125, + 0.64453125 + ], + [ + 0.5, + 0.701171875, + 0.701171875 + ], + [ + 0.5, + 0.6640625, + 0.6640625 + ], + [ + 0.5, + 0.78515625, + 0.78515625 + ], + [ + 0.4000000059604645, + 0.685546875, + 0.685546875 + ], + [ + 0.5, + 0.55859375, + 0.55859375 + ], + [ + 0.5, + 0.63671875, + 0.63671875 + ], + [ + 0.5, + 0.521484375, + 0.521484375 + ], + [ + 0.5, + 0.73828125, + 0.73828125 + ], + [ + 0.5, + 0.78515625, + 0.78515625 + ], + [ + 0.5, + 0.75390625, + 0.75390625 + ], + [ + 0.5, + 0.845703125, + 0.845703125 + ], + [ + 0.5, + 0.66796875, + 0.66796875 + ], + [ + 0.5, + 0.70703125, + 0.70703125 + ], + [ + 0.5, + 0.630859375, + 0.630859375 + ], + [ + 0.5, + 0.765625, + 0.765625 + ], + [ + 0.5, + 0.888671875, + 0.888671875 + ], + [ + 0.5, + 0.681640625, + 0.681640625 + ], + [ + 0.5, + 0.712890625, + 0.712890625 + ], + [ + 0.5, + 0.70703125, + 0.70703125 + ], + [ + 0.5, + 0.68359375, + 0.68359375 + ], + [ + 0.5, + 0.59765625, + 0.59765625 + ], + [ + 0.5, + 0.7578125, + 0.7578125 + ], + [ + 0.5, + 0.703125, + 0.703125 + ], + [ + 0.5, + 0.71484375, + 0.71484375 + ], + [ + 0.5, + 0.728515625, + 0.728515625 + ], + [ + 0.5, + 0.734375, + 0.734375 + ], + [ + 0.5, + 0.703125, + 0.703125 + ], + [ + 0.5, + 0.888671875, + 0.888671875 + ], + [ + 0.5, + 0.79296875, + 0.79296875 + ], + [ + 0.5, + 0.728515625, + 0.728515625 + ], + [ + 0.5, + 0.619140625, + 0.619140625 + ], + [ + 0.5, + 0.703125, + 0.703125 + ], + [ + 0.5, + 0.80078125, + 0.80078125 + ], + [ + 0.5, + 0.73046875, + 0.73046875 + ], + [ + 0.5, + 0.6640625, + 0.6640625 + ], + [ + 0.5, + 0.771484375, + 0.771484375 + ], + [ + 0.5, + 0.8515625, + 0.8515625 + ], + [ + 0.5, + 0.7890625, + 0.7890625 + ], + [ + 0.5, + 0.76171875, + 0.76171875 + ], + [ + 0.5, + 0.6796875, + 0.6796875 + ], + [ + 0.5, + 0.662109375, + 0.662109375 + ], + [ + 0.5, + 0.76171875, + 0.76171875 + ], + [ + 0.5, + 0.71875, + 0.71875 + ], + [ + 0.5, + 0.734375, + 0.734375 + ], + [ + 0.5, + 0.58984375, + 0.58984375 + ], + [ + 0.5, + 0.6015625, + 0.6015625 + ], + [ + 0.5, + 0.580078125, + 0.580078125 + ], + [ + 0.5, + 0.6875, + 0.6875 + ], + [ + 0.5, + 0.72265625, + 0.72265625 + ], + [ + 0.5, + 0.625, + 0.625 + ], + [ + 0.5, + 0.72265625, + 0.72265625 + ], + [ + 0.5, + 0.6875, + 0.6875 + ], + [ + 0.5, + 0.703125, + 0.703125 + ], + [ + 0.5, + 0.662109375, + 0.662109375 + ], + [ + 0.5, + 0.744140625, + 0.744140625 + ], + [ + 0.5, + 0.7265625, + 0.7265625 + ], + [ + 0.5, + 0.765625, + 0.765625 + ], + [ + 0.5, + 0.6796875, + 0.6796875 + ], + [ + 0.5, + 0.83203125, + 0.83203125 + ], + [ + 0.5, + 0.69140625, + 0.69140625 + ], + [ + 0.5, + 0.67578125, + 0.67578125 + ], + [ + 0.5, + 0.6640625, + 0.6640625 + ], + [ + 0.5, + 0.6171875, + 0.6171875 + ], + [ + 0.5, + 0.666015625, + 0.666015625 + ], + [ + 0.5, + 0.765625, + 0.765625 + ], + [ + 0.5, + 0.705078125, + 0.705078125 + ], + [ + 0.5, + 0.7578125, + 0.7578125 + ], + [ + 0.5, + 0.6796875, + 0.6796875 + ], + [ + 0.5, + 0.736328125, + 0.736328125 + ], + [ + 0.5, + 0.53515625, + 0.53515625 + ], + [ + 0.5, + 0.703125, + 0.703125 + ], + [ + 0.5, + 0.650390625, + 0.650390625 + ], + [ + 0.5, + 0.607421875, + 0.607421875 + ], + [ + 0.5, + 0.78125, + 0.78125 + ], + [ + 0.5, + 0.607421875, + 0.607421875 + ], + [ + 0.5, + 0.716796875, + 0.716796875 + ], + [ + 0.5, + 0.69140625, + 0.69140625 + ], + [ + 0.5, + 0.650390625, + 0.650390625 + ], + [ + 0.5, + 0.740234375, + 0.740234375 + ], + [ + 0.5, + 0.66015625, + 0.66015625 + ], + [ + 0.5, + 0.77734375, + 0.77734375 + ], + [ + 0.5, + 0.72265625, + 0.72265625 + ], + [ + 0.5, + 0.64453125, + 0.64453125 + ], + [ + 0.4000000059604645, + 0.6953125, + 0.6953125 + ], + [ + 0.5, + 0.7734375, + 0.7734375 + ], + [ + 0.5, + 0.68359375, + 0.68359375 + ], + [ + 0.5, + 0.69140625, + 0.69140625 + ], + [ + 0.5, + 0.66796875, + 0.66796875 + ], + [ + 0.5, + 0.71875, + 0.71875 + ], + [ + 0.5, + 0.6015625, + 0.6015625 + ], + [ + 0.5, + 0.669921875, + 0.669921875 + ], + [ + 0.5, + 0.673828125, + 0.673828125 + ], + [ + 0.5, + 0.828125, + 0.828125 + ], + [ + 0.5, + 0.728515625, + 0.728515625 + ], + [ + 0.5, + 0.80078125, + 0.80078125 + ], + [ + 0.5, + 0.724609375, + 0.724609375 + ], + [ + 0.5, + 0.70703125, + 0.70703125 + ], + [ + 0.5, + 0.59375, + 0.59375 + ], + [ + 0.5, + 0.78515625, + 0.78515625 + ], + [ + 0.5, + 0.681640625, + 0.681640625 + ], + [ + 0.5, + 0.685546875, + 0.685546875 + ], + [ + 0.5, + 0.572265625, + 0.572265625 + ], + [ + 0.5, + 0.697265625, + 0.697265625 + ], + [ + 0.5, + 0.84375, + 0.84375 + ], + [ + 0.5, + 0.6796875, + 0.6796875 + ], + [ + 0.5, + 0.6875, + 0.6875 + ], + [ + 0.5, + 0.78515625, + 0.78515625 + ], + [ + 0.5, + 0.7109375, + 0.7109375 + ], + [ + 0.5, + 0.912109375, + 0.912109375 + ], + [ + 0.5, + 0.78515625, + 0.78515625 + ], + [ + 0.5, + 0.685546875, + 0.685546875 + ], + [ + 0.5, + 0.775390625, + 0.775390625 + ], + [ + 0.5, + 0.623046875, + 0.623046875 + ], + [ + 0.5, + 0.765625, + 0.765625 + ], + [ + 0.5, + 0.6328125, + 0.6328125 + ], + [ + 0.5, + 0.8203125, + 0.8203125 + ], + [ + 0.5, + 0.61328125, + 0.61328125 + ], + [ + 0.5, + 0.87890625, + 0.87890625 + ], + [ + 0.5, + 0.7578125, + 0.7578125 + ], + [ + 0.5, + 0.71484375, + 0.71484375 + ], + [ + 0.5, + 0.9453125, + 0.9453125 + ], + [ + 0.5, + 0.755859375, + 0.755859375 + ], + [ + 0.5, + 0.6015625, + 0.6015625 + ], + [ + 0.5, + 0.72265625, + 0.72265625 + ], + [ + 0.5, + 0.701171875, + 0.701171875 + ], + [ + 0.5, + 0.73046875, + 0.73046875 + ], + [ + 0.5, + 0.751953125, + 0.751953125 + ], + [ + 0.75, + 0.66015625, + 0.66015625 + ], + [ + 0.5, + 0.67578125, + 0.67578125 + ], + [ + 0.5, + 0.83203125, + 0.83203125 + ], + [ + 0.75, + 0.732421875, + 0.732421875 + ], + [ + 0.5, + 0.71875, + 0.71875 + ], + [ + 0.5, + 0.7265625, + 0.7265625 + ], + [ + 0.5, + 0.6015625, + 0.6015625 + ], + [ + 0.5, + 0.642578125, + 0.642578125 + ], + [ + 0.5, + 0.73046875, + 0.73046875 + ], + [ + 0.75, + 0.7421875, + 0.7421875 + ], + [ + 0.5, + 0.76953125, + 0.76953125 + ], + [ + 0.5, + 0.744140625, + 0.744140625 + ], + [ + 0.5, + 0.703125, + 0.703125 + ], + [ + 0.5, + 0.7265625, + 0.7265625 + ], + [ + 0.5, + 0.8359375, + 0.8359375 + ], + [ + 0.5, + 0.7109375, + 0.7109375 + ], + [ + 0.5, + 0.59765625, + 0.59765625 + ], + [ + 0.5, + 0.685546875, + 0.685546875 + ], + [ + 0.5, + 0.759765625, + 0.759765625 + ], + [ + 0.5, + 0.66015625, + 0.66015625 + ], + [ + 0.5, + 0.59375, + 0.59375 + ], + [ + 0.5, + 0.716796875, + 0.716796875 + ], + [ + 0.5, + 0.73828125, + 0.73828125 + ], + [ + 0.5, + 0.697265625, + 0.697265625 + ], + [ + 0.5, + 0.71875, + 0.71875 + ], + [ + 0.5, + 0.736328125, + 0.736328125 + ], + [ + 0.5, + 0.828125, + 0.828125 + ], + [ + 0.5, + 0.626953125, + 0.626953125 + ], + [ + 0.5, + 0.71484375, + 0.71484375 + ], + [ + 0.5, + 0.837890625, + 0.837890625 + ], + [ + 0.5, + 0.646484375, + 0.646484375 + ], + [ + 0.75, + 0.595703125, + 0.595703125 + ], + [ + 0.5, + 0.66796875, + 0.66796875 + ], + [ + 0.5, + 0.75, + 0.75 + ], + [ + 0.5, + 0.578125, + 0.578125 + ], + [ + 0.5, + 0.7734375, + 0.7734375 + ], + [ + 0.5, + 0.82421875, + 0.82421875 + ], + [ + 0.5, + 0.75, + 0.75 + ], + [ + 0.5, + 0.841796875, + 0.841796875 + ], + [ + 0.75, + 0.75390625, + 0.75390625 + ], + [ + 0.5, + 0.734375, + 0.734375 + ], + [ + 0.5, + 0.6875, + 0.6875 + ], + [ + 0.5, + 0.833984375, + 0.833984375 + ], + [ + 0.75, + 0.712890625, + 0.712890625 + ], + [ + 0.5, + 0.84375, + 0.84375 + ], + [ + 0.5, + 0.68359375, + 0.68359375 + ], + [ + 0.5, + 0.8125, + 0.8125 + ], + [ + 0.5, + 0.87109375, + 0.87109375 + ], + [ + 0.5, + 0.783203125, + 0.783203125 + ], + [ + 0.5, + 0.6640625, + 0.6640625 + ], + [ + 0.5, + 0.7109375, + 0.7109375 + ], + [ + 0.5, + 0.71484375, + 0.71484375 + ], + [ + 0.5, + 0.755859375, + 0.755859375 + ], + [ + 0.5, + 0.74609375, + 0.74609375 + ], + [ + 0.5, + 0.703125, + 0.703125 + ], + [ + 0.5, + 0.7578125, + 0.7578125 + ], + [ + 0.5, + 0.76171875, + 0.76171875 + ], + [ + 0.75, + 0.705078125, + 0.705078125 + ], + [ + 0.5, + 0.82421875, + 0.82421875 + ], + [ + 0.5, + 0.8125, + 0.8125 + ], + [ + 0.5, + 0.64453125, + 0.64453125 + ], + [ + 0.5, + 0.7265625, + 0.7265625 + ], + [ + 0.5, + 0.73828125, + 0.73828125 + ], + [ + 0.75, + 0.732421875, + 0.732421875 + ], + [ + 0.5, + 0.875, + 0.875 + ], + [ + 0.5, + 0.7421875, + 0.7421875 + ], + [ + 0.5, + 0.79296875, + 0.79296875 + ], + [ + 0.75, + 0.611328125, + 0.611328125 + ], + [ + 0.5, + 0.84765625, + 0.84765625 + ], + [ + 0.5, + 0.8671875, + 0.8671875 + ], + [ + 0.5, + 0.74609375, + 0.74609375 + ], + [ + 0.75, + 0.73046875, + 0.73046875 + ], + [ + 0.5, + 0.861328125, + 0.861328125 + ], + [ + 0.5, + 0.767578125, + 0.767578125 + ], + [ + 0.5, + 0.640625, + 0.640625 + ], + [ + 0.5, + 0.65234375, + 0.65234375 + ], + [ + 0.5, + 0.75390625, + 0.75390625 + ], + [ + 0.5, + 0.6640625, + 0.6640625 + ], + [ + 0.5, + 0.662109375, + 0.662109375 + ], + [ + 0.5, + 0.734375, + 0.734375 + ], + [ + 0.5, + 0.75390625, + 0.75390625 + ], + [ + 0.5, + 0.818359375, + 0.818359375 + ], + [ + 0.5, + 0.7578125, + 0.7578125 + ], + [ + 0.5, + 0.7890625, + 0.7890625 + ], + [ + 0.5, + 0.76953125, + 0.76953125 + ], + [ + 0.5, + 0.68359375, + 0.68359375 + ], + [ + 0.5, + 0.78515625, + 0.78515625 + ], + [ + 0.5, + 0.88671875, + 0.88671875 + ], + [ + 0.5, + 0.83984375, + 0.83984375 + ], + [ + 0.5, + 0.611328125, + 0.611328125 + ], + [ + 0.5, + 0.7734375, + 0.7734375 + ], + [ + 0.5, + 0.69921875, + 0.69921875 + ], + [ + 0.5, + 0.83203125, + 0.83203125 + ], + [ + 0.5, + 0.9765625, + 0.9765625 + ], + [ + 0.5, + 0.89453125, + 0.89453125 + ], + [ + 0.5, + 0.83203125, + 0.83203125 + ], + [ + 0.75, + 0.71484375, + 0.71484375 + ], + [ + 0.5, + 0.8671875, + 0.8671875 + ], + [ + 0.5, + 0.703125, + 0.703125 + ], + [ + 0.5, + 0.69140625, + 0.69140625 + ], + [ + 0.5, + 0.63671875, + 0.63671875 + ], + [ + 0.5, + 0.66015625, + 0.66015625 + ], + [ + 0.5, + 0.625, + 0.625 + ], + [ + 0.5, + 0.67578125, + 0.67578125 + ], + [ + 0.5, + 0.69140625, + 0.69140625 + ], + [ + 0.5, + 0.94921875, + 0.94921875 + ], + [ + 0.75, + 0.7421875, + 0.7421875 + ], + [ + 0.5, + 0.685546875, + 0.685546875 + ], + [ + 0.5, + 0.69140625, + 0.69140625 + ], + [ + 0.5, + 0.9140625, + 0.9140625 + ], + [ + 0.5, + 0.828125, + 0.828125 + ], + [ + 0.5, + 0.716796875, + 0.716796875 + ], + [ + 0.5, + 0.71875, + 0.71875 + ], + [ + 0.5, + 0.7890625, + 0.7890625 + ], + [ + 0.5, + 0.79296875, + 0.79296875 + ], + [ + 0.5, + 0.69140625, + 0.69140625 + ], + [ + 0.5, + 0.892578125, + 0.892578125 + ], + [ + 0.5, + 0.5703125, + 0.5703125 + ], + [ + 0.5, + 0.837890625, + 0.837890625 + ], + [ + 0.5, + 0.6640625, + 0.6640625 + ], + [ + 0.5, + 0.736328125, + 0.736328125 + ], + [ + 0.5, + 0.68359375, + 0.68359375 + ], + [ + 0.5, + 0.6953125, + 0.6953125 + ], + [ + 0.5, + 0.71484375, + 0.71484375 + ], + [ + 0.5, + 0.80859375, + 0.80859375 + ], + [ + 0.5, + 0.783203125, + 0.783203125 + ], + [ + 0.5, + 0.73828125, + 0.73828125 + ], + [ + 0.5, + 0.80078125, + 0.80078125 + ], + [ + 0.75, + 0.70703125, + 0.70703125 + ], + [ + 0.5, + 0.75, + 0.75 + ], + [ + 0.5, + 0.72265625, + 0.72265625 + ], + [ + 0.5, + 0.72265625, + 0.72265625 + ], + [ + 0.5, + 0.734375, + 0.734375 + ], + [ + 0.5, + 0.775390625, + 0.775390625 + ], + [ + 0.5, + 0.759765625, + 0.759765625 + ], + [ + 0.5, + 0.765625, + 0.765625 + ], + [ + 0.5, + 0.5859375, + 0.5859375 + ], + [ + 0.5, + 0.62109375, + 0.62109375 + ], + [ + 0.5, + 0.796875, + 0.796875 + ], + [ + 0.5, + 0.69921875, + 0.69921875 + ], + [ + 0.5, + 0.6875, + 0.6875 + ], + [ + 0.5, + 0.82421875, + 0.82421875 + ], + [ + 0.75, + 0.7421875, + 0.7421875 + ], + [ + 0.5, + 0.9453125, + 0.9453125 + ], + [ + 0.5, + 0.642578125, + 0.642578125 + ], + [ + 0.5, + 0.71484375, + 0.71484375 + ], + [ + 0.5, + 0.78125, + 0.78125 + ], + [ + 0.5, + 0.7890625, + 0.7890625 + ], + [ + 0.5, + 0.78125, + 0.78125 + ], + [ + 0.5, + 0.814453125, + 0.814453125 + ], + [ + 0.5, + 0.77734375, + 0.77734375 + ], + [ + 0.5, + 0.75390625, + 0.75390625 + ], + [ + 0.5, + 0.68359375, + 0.68359375 + ], + [ + 0.5, + 0.73828125, + 0.73828125 + ], + [ + 0.5, + 0.6953125, + 0.6953125 + ], + [ + 0.5, + 0.798828125, + 0.798828125 + ], + [ + 0.75, + 0.73046875, + 0.73046875 + ], + [ + 0.5, + 0.73046875, + 0.73046875 + ], + [ + 0.5, + 0.76953125, + 0.76953125 + ], + [ + 0.5, + 0.87890625, + 0.87890625 + ], + [ + 0.5, + 0.6640625, + 0.6640625 + ], + [ + 0.5, + 0.8359375, + 0.8359375 + ], + [ + 0.5, + 0.71484375, + 0.71484375 + ], + [ + 0.5, + 0.70703125, + 0.70703125 + ], + [ + 0.5, + 0.8671875, + 0.8671875 + ], + [ + 0.5, + 0.71484375, + 0.71484375 + ], + [ + 0.5, + 0.68359375, + 0.68359375 + ], + [ + 0.5, + 0.6640625, + 0.6640625 + ], + [ + 0.5, + 0.76953125, + 0.76953125 + ], + [ + 0.5, + 0.818359375, + 0.818359375 + ], + [ + 0.5, + 0.73046875, + 0.73046875 + ], + [ + 0.75, + 0.791015625, + 0.791015625 + ], + [ + 0.5, + 0.6328125, + 0.6328125 + ], + [ + 0.5, + 0.806640625, + 0.806640625 + ], + [ + 0.5, + 0.7421875, + 0.7421875 + ], + [ + 0.5, + 0.68359375, + 0.68359375 + ], + [ + 0.5, + 0.751953125, + 0.751953125 + ], + [ + 0.5, + 0.7734375, + 0.7734375 + ], + [ + 0.5, + 0.75, + 0.75 + ], + [ + 0.5, + 0.681640625, + 0.681640625 + ], + [ + 0.5, + 0.7109375, + 0.7109375 + ], + [ + 0.5, + 0.67578125, + 0.67578125 + ], + [ + 0.5, + 0.541015625, + 0.541015625 + ], + [ + 0.5, + 0.8359375, + 0.8359375 + ], + [ + 0.5, + 0.68359375, + 0.68359375 + ], + [ + 0.5, + 0.703125, + 0.703125 + ], + [ + 0.5, + 0.75, + 0.75 + ], + [ + 0.5, + 0.84765625, + 0.84765625 + ], + [ + 0.5, + 0.80078125, + 0.80078125 + ], + [ + 0.5, + 0.77734375, + 0.77734375 + ], + [ + 0.5, + 0.83203125, + 0.83203125 + ], + [ + 0.5, + 0.69921875, + 0.69921875 + ], + [ + 0.5, + 0.8046875, + 0.8046875 + ], + [ + 0.5, + 0.76953125, + 0.76953125 + ], + [ + 0.5, + 0.7109375, + 0.7109375 + ], + [ + 0.5, + 0.75, + 0.75 + ], + [ + 0.5, + 0.78125, + 0.78125 + ], + [ + 0.5, + 0.77734375, + 0.77734375 + ], + [ + 0.5, + 0.6875, + 0.6875 + ], + [ + 0.5, + 0.724609375, + 0.724609375 + ], + [ + 0.5, + 0.87109375, + 0.87109375 + ], + [ + 0.5, + 0.646484375, + 0.646484375 + ], + [ + 0.5, + 0.64453125, + 0.64453125 + ], + [ + 0.5, + 0.708984375, + 0.708984375 + ], + [ + 0.5, + 0.71484375, + 0.71484375 + ], + [ + 0.5, + 0.58203125, + 0.58203125 + ], + [ + 0.5, + 0.87109375, + 0.87109375 + ], + [ + 0.5, + 0.78125, + 0.78125 + ], + [ + 0.5, + 0.72265625, + 0.72265625 + ], + [ + 0.5, + 0.75, + 0.75 + ], + [ + 0.5, + 0.7578125, + 0.7578125 + ], + [ + 0.5, + 0.84765625, + 0.84765625 + ], + [ + 0.5, + 0.796875, + 0.796875 + ], + [ + 0.5, + 0.87109375, + 0.87109375 + ], + [ + 0.5, + 0.75, + 0.75 + ], + [ + 0.5, + 0.734375, + 0.734375 + ], + [ + 0.5, + 0.7578125, + 0.7578125 + ], + [ + 0.5, + 0.6875, + 0.6875 + ], + [ + 0.5, + 0.6640625, + 0.6640625 + ], + [ + 0.5, + 0.70703125, + 0.70703125 + ], + [ + 0.5, + 0.8359375, + 0.8359375 + ], + [ + 0.5, + 0.828125, + 0.828125 + ], + [ + 0.5, + 0.6484375, + 0.6484375 + ], + [ + 0.5, + 0.654296875, + 0.654296875 + ], + [ + 0.5, + 0.8046875, + 0.8046875 + ], + [ + 0.5, + 0.75, + 0.75 + ], + [ + 0.5, + 0.814453125, + 0.814453125 + ], + [ + 0.5, + 0.84375, + 0.84375 + ], + [ + 0.5, + 0.74609375, + 0.74609375 + ], + [ + 0.5, + 0.71484375, + 0.71484375 + ], + [ + 0.5, + 0.712890625, + 0.712890625 + ], + [ + 0.5, + 0.755859375, + 0.755859375 + ], + [ + 0.5, + 0.78125, + 0.78125 + ], + [ + 0.5, + 0.708984375, + 0.708984375 + ], + [ + 0.5, + 0.73828125, + 0.73828125 + ], + [ + 0.5, + 0.69140625, + 0.69140625 + ], + [ + 0.5, + 0.7578125, + 0.7578125 + ], + [ + 0.5, + 0.787109375, + 0.787109375 + ], + [ + 0.5, + 0.728515625, + 0.728515625 + ], + [ + 0.5, + 0.65234375, + 0.65234375 + ], + [ + 0.5, + 0.791015625, + 0.791015625 + ], + [ + 0.5, + 0.6171875, + 0.6171875 + ], + [ + 0.5, + 0.640625, + 0.640625 + ], + [ + 0.5, + 0.83984375, + 0.83984375 + ], + [ + 0.5, + 0.59765625, + 0.59765625 + ], + [ + 0.5, + 0.75, + 0.75 + ], + [ + 0.5, + 0.83203125, + 0.83203125 + ], + [ + 0.5, + 0.71875, + 0.71875 + ], + [ + 0.5, + 0.6015625, + 0.6015625 + ], + [ + 0.5, + 0.71484375, + 0.71484375 + ], + [ + 0.5, + 0.65625, + 0.65625 + ], + [ + 0.5, + 0.78125, + 0.78125 + ], + [ + 0.5, + 0.58203125, + 0.58203125 + ], + [ + 0.5, + 0.73828125, + 0.73828125 + ], + [ + 0.5, + 0.76171875, + 0.76171875 + ], + [ + 0.5, + 0.53515625, + 0.53515625 + ], + [ + 0.5, + 0.689453125, + 0.689453125 + ], + [ + 0.5, + 0.798828125, + 0.798828125 + ], + [ + 0.5, + 0.72265625, + 0.72265625 + ], + [ + 0.5, + 0.708984375, + 0.708984375 + ], + [ + 0.5, + 0.650390625, + 0.650390625 + ], + [ + 0.5, + 0.693359375, + 0.693359375 + ], + [ + 0.699999988079071, + 0.9765625, + 0.9765625 + ], + [ + 0.5, + 0.71875, + 0.71875 + ], + [ + 0.5, + 0.66796875, + 0.66796875 + ], + [ + 0.5, + 0.87109375, + 0.87109375 + ], + [ + 0.5, + 0.75, + 0.75 + ], + [ + 0.5, + 0.5859375, + 0.5859375 + ], + [ + 0.5, + 0.748046875, + 0.748046875 + ], + [ + 0.5, + 0.74609375, + 0.74609375 + ], + [ + 0.5, + 0.69140625, + 0.69140625 + ], + [ + 0.5, + 0.7421875, + 0.7421875 + ], + [ + 0.5, + 0.7109375, + 0.7109375 + ], + [ + 0.5, + 0.68359375, + 0.68359375 + ], + [ + 0.5, + 0.6875, + 0.6875 + ], + [ + 0.5, + 0.669921875, + 0.669921875 + ], + [ + 0.5, + 0.740234375, + 0.740234375 + ], + [ + 0.5, + 0.890625, + 0.890625 + ], + [ + 0.5, + 0.73046875, + 0.73046875 + ], + [ + 0.5, + 0.71484375, + 0.71484375 + ], + [ + 0.5, + 0.609375, + 0.609375 + ], + [ + 0.5, + 0.638671875, + 0.638671875 + ], + [ + 0.5, + 0.68359375, + 0.68359375 + ], + [ + 0.5, + 0.775390625, + 0.775390625 + ], + [ + 0.5, + 0.78515625, + 0.78515625 + ], + [ + 0.5, + 0.6875, + 0.6875 + ], + [ + 0.5, + 0.71484375, + 0.71484375 + ], + [ + 0.5, + 0.83203125, + 0.83203125 + ], + [ + 0.5, + 0.7265625, + 0.7265625 + ], + [ + 0.5, + 0.9765625, + 0.9765625 + ], + [ + 0.5, + 0.693359375, + 0.693359375 + ], + [ + 0.5, + 0.890625, + 0.890625 + ], + [ + 0.5, + 0.8515625, + 0.8515625 + ], + [ + 0.5, + 0.740234375, + 0.740234375 + ], + [ + 0.5, + 0.5859375, + 0.5859375 + ], + [ + 0.5, + 0.61328125, + 0.61328125 + ], + [ + 0.5, + 0.76171875, + 0.76171875 + ], + [ + 0.5, + 0.70703125, + 0.70703125 + ], + [ + 0.5, + 0.64453125, + 0.64453125 + ], + [ + 0.5, + 0.640625, + 0.640625 + ], + [ + 0.5, + 0.64453125, + 0.64453125 + ], + [ + 0.75, + 0.63671875, + 0.63671875 + ], + [ + 0.5, + 0.68359375, + 0.68359375 + ], + [ + 0.5, + 0.9453125, + 0.9453125 + ], + [ + 0.75, + 0.76953125, + 0.76953125 + ], + [ + 0.5, + 0.7734375, + 0.7734375 + ], + [ + 0.75, + 0.76171875, + 0.76171875 + ], + [ + 0.75, + 0.73828125, + 0.73828125 + ], + [ + 0.5, + 0.6796875, + 0.6796875 + ], + [ + 0.5, + 0.740234375, + 0.740234375 + ], + [ + 0.5, + 0.71484375, + 0.71484375 + ], + [ + 0.5, + 0.63671875, + 0.63671875 + ], + [ + 0.5, + 0.78125, + 0.78125 + ], + [ + 0.5, + 0.67578125, + 0.67578125 + ], + [ + 0.5, + 0.80078125, + 0.80078125 + ], + [ + 0.5, + 0.8515625, + 0.8515625 + ], + [ + 0.5, + 0.720703125, + 0.720703125 + ], + [ + 0.5, + 0.625, + 0.625 + ], + [ + 0.5, + 0.63671875, + 0.63671875 + ], + [ + 0.5, + 0.8671875, + 0.8671875 + ], + [ + 0.5, + 0.705078125, + 0.705078125 + ], + [ + 0.5, + 0.716796875, + 0.716796875 + ], + [ + 0.5, + 0.669921875, + 0.669921875 + ], + [ + 0.5, + 0.59765625, + 0.59765625 + ], + [ + 0.5, + 0.7578125, + 0.7578125 + ], + [ + 0.5, + 0.876953125, + 0.876953125 + ], + [ + 0.5, + 0.78125, + 0.78125 + ], + [ + 0.5, + 0.9453125, + 0.9453125 + ], + [ + 0.5, + 0.83984375, + 0.83984375 + ], + [ + 0.5, + 0.71484375, + 0.71484375 + ], + [ + 0.5, + 0.62109375, + 0.62109375 + ], + [ + 0.5, + 0.66796875, + 0.66796875 + ], + [ + 0.5, + 0.701171875, + 0.701171875 + ], + [ + 0.5, + 0.625, + 0.625 + ], + [ + 0.5, + 0.689453125, + 0.689453125 + ], + [ + 0.5, + 0.78125, + 0.78125 + ], + [ + 0.5, + 0.6875, + 0.6875 + ], + [ + 0.5, + 0.642578125, + 0.642578125 + ], + [ + 0.5, + 0.78125, + 0.78125 + ], + [ + 0.5, + 0.658203125, + 0.658203125 + ], + [ + 0.5, + 0.5859375, + 0.5859375 + ], + [ + 0.5, + 0.634765625, + 0.634765625 + ], + [ + 0.5, + 0.71484375, + 0.71484375 + ], + [ + 0.5, + 0.689453125, + 0.689453125 + ], + [ + 0.5, + 0.658203125, + 0.658203125 + ], + [ + 0.5, + 0.75390625, + 0.75390625 + ], + [ + 0.5, + 0.80078125, + 0.80078125 + ], + [ + 0.5, + 0.83984375, + 0.83984375 + ], + [ + 0.5, + 0.8203125, + 0.8203125 + ], + [ + 0.5, + 0.78515625, + 0.78515625 + ], + [ + 0.5, + 0.8203125, + 0.8203125 + ], + [ + 0.5, + 0.728515625, + 0.728515625 + ], + [ + 0.5, + 0.6015625, + 0.6015625 + ], + [ + 0.5, + 0.77734375, + 0.77734375 + ], + [ + 0.5, + 0.67578125, + 0.67578125 + ], + [ + 0.4000000059604645, + 0.66015625, + 0.66015625 + ], + [ + 0.5, + 0.693359375, + 0.693359375 + ], + [ + 0.5, + 0.763671875, + 0.763671875 + ], + [ + 0.5, + 0.6015625, + 0.6015625 + ], + [ + 0.5, + 0.74609375, + 0.74609375 + ], + [ + 0.75, + 0.68359375, + 0.68359375 + ], + [ + 0.5, + 0.904296875, + 0.904296875 + ], + [ + 0.5, + 0.80859375, + 0.80859375 + ], + [ + 0.5, + 0.693359375, + 0.693359375 + ], + [ + 0.5, + 0.794921875, + 0.794921875 + ], + [ + 0.5, + 0.642578125, + 0.642578125 + ], + [ + 0.5, + 0.9765625, + 0.9765625 + ], + [ + 0.5, + 0.78515625, + 0.78515625 + ], + [ + 0.5, + 0.87890625, + 0.87890625 + ], + [ + 0.5, + 0.77734375, + 0.77734375 + ], + [ + 0.5, + 0.607421875, + 0.607421875 + ], + [ + 0.5, + 0.677734375, + 0.677734375 + ], + [ + 0.5, + 0.716796875, + 0.716796875 + ], + [ + 0.5, + 0.6640625, + 0.6640625 + ], + [ + 0.5, + 0.60546875, + 0.60546875 + ], + [ + 0.5, + 0.73828125, + 0.73828125 + ], + [ + 0.5, + 0.75390625, + 0.75390625 + ], + [ + 0.5, + 0.818359375, + 0.818359375 + ], + [ + 0.75, + 0.78125, + 0.78125 + ], + [ + 0.5, + 0.671875, + 0.671875 + ], + [ + 0.5, + 0.697265625, + 0.697265625 + ], + [ + 0.5, + 0.85546875, + 0.85546875 + ], + [ + 0.5, + 0.7890625, + 0.7890625 + ], + [ + 0.5, + 0.62109375, + 0.62109375 + ], + [ + 0.5, + 0.658203125, + 0.658203125 + ], + [ + 0.5, + 0.9765625, + 0.9765625 + ], + [ + 0.5, + 0.75, + 0.75 + ], + [ + 0.5, + 0.7109375, + 0.7109375 + ], + [ + 0.5, + 0.81640625, + 0.81640625 + ], + [ + 0.5, + 0.71875, + 0.71875 + ], + [ + 0.5, + 0.73046875, + 0.73046875 + ], + [ + 0.5, + 0.9375, + 0.9375 + ], + [ + 0.5, + 0.748046875, + 0.748046875 + ], + [ + 0.5, + 0.7109375, + 0.7109375 + ], + [ + 0.5, + 0.76953125, + 0.76953125 + ], + [ + 0.5, + 0.7890625, + 0.7890625 + ], + [ + 0.5, + 0.75390625, + 0.75390625 + ], + [ + 0.5, + 0.892578125, + 0.892578125 + ], + [ + 0.5, + 0.58984375, + 0.58984375 + ], + [ + 0.5, + 0.72265625, + 0.72265625 + ], + [ + 0.5, + 0.78125, + 0.78125 + ], + [ + 0.5, + 0.6640625, + 0.6640625 + ], + [ + 0.5, + 0.890625, + 0.890625 + ], + [ + 0.5, + 0.58984375, + 0.58984375 + ], + [ + 0.5, + 0.689453125, + 0.689453125 + ], + [ + 0.5, + 0.658203125, + 0.658203125 + ], + [ + 0.5, + 0.580078125, + 0.580078125 + ], + [ + 0.5, + 0.77734375, + 0.77734375 + ], + [ + 0.5, + 0.755859375, + 0.755859375 + ], + [ + 0.5, + 0.50390625, + 0.50390625 + ], + [ + 0.5, + 0.54296875, + 0.54296875 + ], + [ + 0.5, + 0.76953125, + 0.76953125 + ], + [ + 0.5, + 0.61328125, + 0.61328125 + ], + [ + 0.5, + 0.90234375, + 0.90234375 + ], + [ + 0.5, + 0.89453125, + 0.89453125 + ], + [ + 0.5, + 0.65625, + 0.65625 + ], + [ + 0.5, + 0.7265625, + 0.7265625 + ], + [ + 0.5, + 0.703125, + 0.703125 + ], + [ + 0.5, + 0.720703125, + 0.720703125 + ], + [ + 0.5, + 0.765625, + 0.765625 + ], + [ + 0.5, + 0.71484375, + 0.71484375 + ], + [ + 0.5, + 0.697265625, + 0.697265625 + ], + [ + 0.5, + 0.833984375, + 0.833984375 + ], + [ + 0.5, + 0.705078125, + 0.705078125 + ], + [ + 0.5, + 0.72265625, + 0.72265625 + ], + [ + 0.5, + 0.7421875, + 0.7421875 + ], + [ + 0.5, + 0.705078125, + 0.705078125 + ], + [ + 0.5, + 0.87890625, + 0.87890625 + ], + [ + 0.5, + 0.65625, + 0.65625 + ], + [ + 0.5, + 0.80859375, + 0.80859375 + ], + [ + 0.5, + 0.75390625, + 0.75390625 + ], + [ + 0.5, + 0.89453125, + 0.89453125 + ], + [ + 0.75, + 0.765625, + 0.765625 + ], + [ + 0.75, + 0.77734375, + 0.77734375 + ], + [ + 0.5, + 0.7109375, + 0.7109375 + ], + [ + 0.5, + 0.68359375, + 0.68359375 + ], + [ + 0.5, + 0.818359375, + 0.818359375 + ], + [ + 0.5, + 0.916015625, + 0.916015625 + ], + [ + 0.5, + 0.91015625, + 0.91015625 + ], + [ + 0.5, + 0.765625, + 0.765625 + ], + [ + 0.75, + 0.755859375, + 0.755859375 + ], + [ + 0.5, + 0.6796875, + 0.6796875 + ], + [ + 0.5, + 0.81640625, + 0.81640625 + ], + [ + 0.5, + 0.74609375, + 0.74609375 + ], + [ + 0.5, + 0.671875, + 0.671875 + ], + [ + 0.5, + 0.72265625, + 0.72265625 + ], + [ + 0.5, + 0.720703125, + 0.720703125 + ], + [ + 0.5, + 0.900390625, + 0.900390625 + ], + [ + 0.5, + 0.76953125, + 0.76953125 + ], + [ + 0.5, + 0.716796875, + 0.716796875 + ], + [ + 0.5, + 0.859375, + 0.859375 + ], + [ + 0.75, + 0.73046875, + 0.73046875 + ], + [ + 0.5, + 0.7421875, + 0.7421875 + ], + [ + 0.5, + 0.73046875, + 0.73046875 + ], + [ + 0.5, + 0.6796875, + 0.6796875 + ], + [ + 0.5, + 0.748046875, + 0.748046875 + ], + [ + 0.5, + 0.65234375, + 0.65234375 + ], + [ + 0.5, + 0.7890625, + 0.7890625 + ], + [ + 0.5, + 0.720703125, + 0.720703125 + ], + [ + 0.5, + 0.62109375, + 0.62109375 + ], + [ + 0.5, + 0.69921875, + 0.69921875 + ], + [ + 0.5, + 0.625, + 0.625 + ], + [ + 0.5, + 0.818359375, + 0.818359375 + ], + [ + 0.5, + 0.8515625, + 0.8515625 + ], + [ + 0.5, + 0.802734375, + 0.802734375 + ], + [ + 0.5, + 0.71484375, + 0.71484375 + ], + [ + 0.5, + 0.76953125, + 0.76953125 + ], + [ + 0.5, + 0.83203125, + 0.83203125 + ], + [ + 0.5, + 0.720703125, + 0.720703125 + ], + [ + 0.5, + 0.703125, + 0.703125 + ], + [ + 0.5, + 0.8203125, + 0.8203125 + ], + [ + 0.5, + 0.6953125, + 0.6953125 + ], + [ + 0.5, + 0.84375, + 0.84375 + ], + [ + 0.5, + 0.75390625, + 0.75390625 + ], + [ + 0.5, + 0.654296875, + 0.654296875 + ], + [ + 0.5, + 0.765625, + 0.765625 + ], + [ + 0.5, + 0.830078125, + 0.830078125 + ], + [ + 0.5, + 0.75390625, + 0.75390625 + ], + [ + 0.5, + 0.736328125, + 0.736328125 + ], + [ + 0.5, + 0.8828125, + 0.8828125 + ], + [ + 0.5, + 0.77734375, + 0.77734375 + ], + [ + 0.5, + 0.576171875, + 0.576171875 + ], + [ + 0.5, + 0.755859375, + 0.755859375 + ], + [ + 0.5, + 0.71875, + 0.71875 + ], + [ + 0.5, + 0.9765625, + 0.9765625 + ], + [ + 0.5, + 0.71484375, + 0.71484375 + ], + [ + 0.75, + 0.68359375, + 0.68359375 + ], + [ + 0.5, + 0.76953125, + 0.76953125 + ], + [ + 0.5, + 0.8984375, + 0.8984375 + ], + [ + 0.5, + 0.890625, + 0.890625 + ], + [ + 0.5, + 0.740234375, + 0.740234375 + ], + [ + 0.5, + 0.890625, + 0.890625 + ], + [ + 0.75, + 0.6328125, + 0.6328125 + ], + [ + 0.5, + 0.64453125, + 0.64453125 + ], + [ + 0.5, + 0.859375, + 0.859375 + ], + [ + 0.5, + 0.765625, + 0.765625 + ], + [ + 0.5, + 0.7890625, + 0.7890625 + ], + [ + 0.5, + 0.75, + 0.75 + ], + [ + 0.5, + 0.703125, + 0.703125 + ], + [ + 0.5, + 0.80078125, + 0.80078125 + ], + [ + 0.5, + 0.69921875, + 0.69921875 + ], + [ + 0.5, + 0.7109375, + 0.7109375 + ], + [ + 0.5, + 0.68359375, + 0.68359375 + ], + [ + 0.5, + 0.8203125, + 0.8203125 + ], + [ + 0.5, + 0.93359375, + 0.93359375 + ], + [ + 0.5, + 0.68359375, + 0.68359375 + ], + [ + 0.5, + 0.76171875, + 0.76171875 + ], + [ + 0.75, + 0.8203125, + 0.8203125 + ], + [ + 0.5, + 0.82421875, + 0.82421875 + ], + [ + 0.5, + 0.8125, + 0.8125 + ], + [ + 0.5, + 0.76953125, + 0.76953125 + ], + [ + 0.5, + 0.7265625, + 0.7265625 + ], + [ + 0.5, + 0.85546875, + 0.85546875 + ], + [ + 0.5, + 0.791015625, + 0.791015625 + ], + [ + 0.5, + 0.74609375, + 0.74609375 + ], + [ + 0.5, + 0.673828125, + 0.673828125 + ], + [ + 0.5, + 0.734375, + 0.734375 + ], + [ + 0.5, + 0.83984375, + 0.83984375 + ], + [ + 0.5, + 0.669921875, + 0.669921875 + ], + [ + 0.5, + 0.62890625, + 0.62890625 + ], + [ + 0.75, + 0.71875, + 0.71875 + ], + [ + 0.5, + 0.6875, + 0.6875 + ], + [ + 0.5, + 0.77734375, + 0.77734375 + ], + [ + 0.5, + 0.68359375, + 0.68359375 + ], + [ + 0.5, + 0.71875, + 0.71875 + ], + [ + 0.5, + 0.68359375, + 0.68359375 + ], + [ + 0.5, + 0.580078125, + 0.580078125 + ], + [ + 0.5, + 0.828125, + 0.828125 + ], + [ + 0.5, + 0.876953125, + 0.876953125 + ], + [ + 0.5, + 0.626953125, + 0.626953125 + ], + [ + 0.5, + 0.73046875, + 0.73046875 + ], + [ + 0.5, + 0.7109375, + 0.7109375 + ], + [ + 0.5, + 0.890625, + 0.890625 + ], + [ + 0.5, + 0.564453125, + 0.564453125 + ], + [ + 0.5, + 0.7109375, + 0.7109375 + ], + [ + 0.5, + 0.857421875, + 0.857421875 + ], + [ + 0.5, + 0.76953125, + 0.76953125 + ], + [ + 0.5, + 0.72265625, + 0.72265625 + ], + [ + 0.5, + 0.85546875, + 0.85546875 + ], + [ + 0.5, + 0.69140625, + 0.69140625 + ], + [ + 0.5, + 0.9765625, + 0.9765625 + ], + [ + 0.5, + 0.66796875, + 0.66796875 + ], + [ + 0.5, + 0.90625, + 0.90625 + ], + [ + 0.5, + 0.69140625, + 0.69140625 + ], + [ + 0.5, + 0.49609375, + 0.49609375 + ], + [ + 0.5, + 0.845703125, + 0.845703125 + ], + [ + 0.5, + 0.736328125, + 0.736328125 + ], + [ + 0.5, + 0.6015625, + 0.6015625 + ], + [ + 0.5, + 0.681640625, + 0.681640625 + ], + [ + 0.5, + 0.75, + 0.75 + ], + [ + 0.5, + 0.77734375, + 0.77734375 + ], + [ + 0.5, + 0.75390625, + 0.75390625 + ], + [ + 0.5, + 0.9140625, + 0.9140625 + ], + [ + 0.5, + 0.83984375, + 0.83984375 + ], + [ + 0.5, + 0.830078125, + 0.830078125 + ], + [ + 0.5, + 0.92578125, + 0.92578125 + ], + [ + 0.5, + 0.8125, + 0.8125 + ], + [ + 0.5, + 0.671875, + 0.671875 + ], + [ + 0.5, + 0.75390625, + 0.75390625 + ], + [ + 0.5, + 0.767578125, + 0.767578125 + ], + [ + 0.5, + 0.56640625, + 0.56640625 + ], + [ + 0.5, + 0.658203125, + 0.658203125 + ], + [ + 0.5, + 0.6015625, + 0.6015625 + ], + [ + 0.5, + 0.841796875, + 0.841796875 + ], + [ + 0.5, + 0.71484375, + 0.71484375 + ], + [ + 0.5, + 0.76171875, + 0.76171875 + ], + [ + 0.5, + 0.6953125, + 0.6953125 + ], + [ + 0.5, + 0.76171875, + 0.76171875 + ], + [ + 0.5, + 0.73828125, + 0.73828125 + ], + [ + 0.5, + 0.8984375, + 0.8984375 + ], + [ + 0.5, + 0.90234375, + 0.90234375 + ], + [ + 0.5, + 0.79296875, + 0.79296875 + ], + [ + 0.5, + 0.6640625, + 0.6640625 + ], + [ + 0.5, + 0.80859375, + 0.80859375 + ], + [ + 0.5, + 0.7265625, + 0.7265625 + ], + [ + 0.5, + 0.6796875, + 0.6796875 + ], + [ + 0.5, + 0.681640625, + 0.681640625 + ], + [ + 0.5, + 0.703125, + 0.703125 + ], + [ + 0.5, + 0.796875, + 0.796875 + ], + [ + 0.5, + 0.70703125, + 0.70703125 + ], + [ + 0.5, + 0.88671875, + 0.88671875 + ], + [ + 0.5, + 0.7734375, + 0.7734375 + ], + [ + 0.5, + 0.755859375, + 0.755859375 + ], + [ + 0.5, + 0.8359375, + 0.8359375 + ], + [ + 0.5, + 0.9765625, + 0.9765625 + ], + [ + 0.5, + 0.60546875, + 0.60546875 + ], + [ + 0.5, + 0.88671875, + 0.88671875 + ], + [ + 0.5, + 0.962890625, + 0.962890625 + ], + [ + 0.5, + 0.80078125, + 0.80078125 + ], + [ + 0.5, + 0.9609375, + 0.9609375 + ], + [ + 0.5, + 0.892578125, + 0.892578125 + ], + [ + 0.5, + 0.703125, + 0.703125 + ], + [ + 0.5, + 0.83984375, + 0.83984375 + ], + [ + 0.5, + 0.837890625, + 0.837890625 + ], + [ + 0.5, + 0.759765625, + 0.759765625 + ], + [ + 0.5, + 0.875, + 0.875 + ], + [ + 0.5, + 0.765625, + 0.765625 + ], + [ + 0.5, + 0.74609375, + 0.74609375 + ], + [ + 0.5, + 0.77734375, + 0.77734375 + ], + [ + 0.5, + 0.748046875, + 0.748046875 + ], + [ + 0.5, + 0.65234375, + 0.65234375 + ], + [ + 0.5, + 0.7734375, + 0.7734375 + ], + [ + 0.5, + 0.73828125, + 0.73828125 + ], + [ + 0.5, + 0.62890625, + 0.62890625 + ], + [ + 0.5, + 0.560546875, + 0.560546875 + ], + [ + 0.5, + 0.80078125, + 0.80078125 + ], + [ + 0.5, + 0.685546875, + 0.685546875 + ], + [ + 0.5, + 0.779296875, + 0.779296875 + ], + [ + 0.5, + 0.6484375, + 0.6484375 + ], + [ + 0.5, + 0.869140625, + 0.869140625 + ], + [ + 0.5, + 0.669921875, + 0.669921875 + ], + [ + 0.5, + 0.78515625, + 0.78515625 + ], + [ + 0.5, + 0.966796875, + 0.966796875 + ], + [ + 0.5, + 0.7421875, + 0.7421875 + ], + [ + 0.5, + 0.63671875, + 0.63671875 + ], + [ + 0.5, + 0.9453125, + 0.9453125 + ], + [ + 0.5, + 0.765625, + 0.765625 + ], + [ + 0.5, + 0.662109375, + 0.662109375 + ], + [ + 0.5, + 0.685546875, + 0.685546875 + ], + [ + 0.5, + 0.75390625, + 0.75390625 + ], + [ + 0.5, + 0.78125, + 0.78125 + ], + [ + 0.5, + 0.6640625, + 0.6640625 + ], + [ + 0.5, + 0.59375, + 0.59375 + ], + [ + 0.5, + 0.69140625, + 0.69140625 + ], + [ + 0.5, + 0.841796875, + 0.841796875 + ], + [ + 0.5, + 0.642578125, + 0.642578125 + ], + [ + 0.5, + 0.609375, + 0.609375 + ], + [ + 0.5, + 0.76171875, + 0.76171875 + ], + [ + 0.5, + 0.662109375, + 0.662109375 + ], + [ + 0.5, + 0.74609375, + 0.74609375 + ], + [ + 0.5, + 0.828125, + 0.828125 + ], + [ + 0.5, + 0.83984375, + 0.83984375 + ], + [ + 0.5, + 0.8125, + 0.8125 + ], + [ + 0.5, + 0.9765625, + 0.9765625 + ], + [ + 0.5, + 0.7265625, + 0.7265625 + ], + [ + 0.5, + 0.86328125, + 0.86328125 + ], + [ + 0.5, + 0.83984375, + 0.83984375 + ], + [ + 0.5, + 0.87109375, + 0.87109375 + ], + [ + 0.5, + 0.97265625, + 0.97265625 + ], + [ + 0.5, + 0.7265625, + 0.7265625 + ], + [ + 0.5, + 0.69921875, + 0.69921875 + ], + [ + 0.5, + 0.76171875, + 0.76171875 + ], + [ + 0.5, + 0.677734375, + 0.677734375 + ], + [ + 0.5, + 0.865234375, + 0.865234375 + ], + [ + 0.5, + 0.54296875, + 0.54296875 + ], + [ + 0.5, + 0.8125, + 0.8125 + ], + [ + 0.5, + 0.76171875, + 0.76171875 + ], + [ + 0.5, + 0.814453125, + 0.814453125 + ], + [ + 0.5, + 0.697265625, + 0.697265625 + ], + [ + 0.5, + 0.921875, + 0.921875 + ], + [ + 0.5, + 0.783203125, + 0.783203125 + ], + [ + 0.5, + 0.90234375, + 0.90234375 + ], + [ + 0.5, + 0.8203125, + 0.8203125 + ], + [ + 0.5, + 0.77734375, + 0.77734375 + ], + [ + 0.5, + 0.7890625, + 0.7890625 + ], + [ + 0.5, + 0.724609375, + 0.724609375 + ], + [ + 0.5, + 0.853515625, + 0.853515625 + ], + [ + 0.5, + 0.83984375, + 0.83984375 + ], + [ + 0.5, + 0.77734375, + 0.77734375 + ], + [ + 0.5, + 0.67578125, + 0.67578125 + ], + [ + 0.5, + 0.837890625, + 0.837890625 + ], + [ + 0.5, + 0.779296875, + 0.779296875 + ], + [ + 0.5, + 0.595703125, + 0.595703125 + ], + [ + 0.5, + 0.9765625, + 0.9765625 + ], + [ + 0.5, + 0.6640625, + 0.6640625 + ], + [ + 0.5, + 0.82421875, + 0.82421875 + ], + [ + 0.5, + 0.650390625, + 0.650390625 + ], + [ + 0.5, + 0.78515625, + 0.78515625 + ], + [ + 0.5, + 0.701171875, + 0.701171875 + ], + [ + 0.5, + 0.70703125, + 0.70703125 + ], + [ + 0.5, + 0.755859375, + 0.755859375 + ], + [ + 0.5, + 0.77734375, + 0.77734375 + ], + [ + 0.5, + 0.78125, + 0.78125 + ], + [ + 0.5, + 0.7734375, + 0.7734375 + ], + [ + 0.5, + 0.82421875, + 0.82421875 + ], + [ + 0.5, + 0.619140625, + 0.619140625 + ], + [ + 0.5, + 0.74609375, + 0.74609375 + ], + [ + 0.5, + 0.73046875, + 0.73046875 + ], + [ + 0.5, + 0.6953125, + 0.6953125 + ], + [ + 0.5, + 0.77734375, + 0.77734375 + ], + [ + 0.5, + 0.73828125, + 0.73828125 + ], + [ + 0.5, + 0.822265625, + 0.822265625 + ], + [ + 0.5, + 0.693359375, + 0.693359375 + ], + [ + 0.5, + 0.6953125, + 0.6953125 + ], + [ + 0.5, + 0.78515625, + 0.78515625 + ], + [ + 0.5, + 0.890625, + 0.890625 + ], + [ + 0.5, + 0.6875, + 0.6875 + ], + [ + 0.5, + 0.75390625, + 0.75390625 + ], + [ + 0.5, + 0.701171875, + 0.701171875 + ], + [ + 0.5, + 0.69140625, + 0.69140625 + ], + [ + 0.5, + 0.810546875, + 0.810546875 + ], + [ + 0.5, + 0.95703125, + 0.95703125 + ], + [ + 0.5, + 0.66796875, + 0.66796875 + ], + [ + 0.5, + 0.767578125, + 0.767578125 + ], + [ + 0.5, + 0.75, + 0.75 + ], + [ + 0.5, + 0.62890625, + 0.62890625 + ], + [ + 0.5, + 0.77734375, + 0.77734375 + ], + [ + 0.5, + 0.65234375, + 0.65234375 + ], + [ + 0.5, + 0.6328125, + 0.6328125 + ], + [ + 0.5, + 0.68359375, + 0.68359375 + ], + [ + 0.5, + 0.6328125, + 0.6328125 + ], + [ + 0.5, + 0.69921875, + 0.69921875 + ], + [ + 0.5, + 0.9765625, + 0.9765625 + ], + [ + 0.5, + 0.85546875, + 0.85546875 + ], + [ + 0.5, + 0.7421875, + 0.7421875 + ], + [ + 0.5, + 0.73828125, + 0.73828125 + ], + [ + 0.5, + 0.80859375, + 0.80859375 + ], + [ + 0.5, + 0.86328125, + 0.86328125 + ], + [ + 1.0, + 0.849609375, + 0.849609375 + ], + [ + 0.5, + 0.7890625, + 0.7890625 + ], + [ + 0.5, + 0.828125, + 0.828125 + ], + [ + 0.5, + 0.66015625, + 0.66015625 + ], + [ + 0.5, + 0.75, + 0.75 + ], + [ + 0.5, + 0.7578125, + 0.7578125 + ], + [ + 0.5, + 0.828125, + 0.828125 + ], + [ + 0.5, + 0.681640625, + 0.681640625 + ], + [ + 0.5, + 0.673828125, + 0.673828125 + ], + [ + 0.800048828125, + 0.9765625, + 0.9765625 + ], + [ + 0.5, + 0.65625, + 0.65625 + ], + [ + 0.5, + 0.736328125, + 0.736328125 + ], + [ + 0.5, + 0.75390625, + 0.75390625 + ], + [ + 0.625, + 0.8261719942092896, + 0.8261719942092896 + ], + [ + 0.5, + 0.640625, + 0.640625 + ], + [ + 0.5, + 0.681640625, + 0.681640625 + ], + [ + 0.5, + 0.74609375, + 0.74609375 + ], + [ + 0.5, + 0.6484375, + 0.6484375 + ], + [ + 0.5, + 0.7109375, + 0.7109375 + ], + [ + 0.5, + 0.759765625, + 0.759765625 + ], + [ + 0.5, + 0.8515625, + 0.8515625 + ], + [ + 0.5, + 0.662109375, + 0.662109375 + ], + [ + 0.5, + 0.720703125, + 0.720703125 + ], + [ + 0.5, + 0.822265625, + 0.822265625 + ], + [ + 0.5, + 0.73828125, + 0.73828125 + ], + [ + 0.5, + 0.93359375, + 0.93359375 + ], + [ + 0.5, + 0.64453125, + 0.64453125 + ], + [ + 0.5, + 0.486328125, + 0.486328125 + ], + [ + 0.5, + 0.70703125, + 0.70703125 + ], + [ + 0.5, + 0.78125, + 0.78125 + ], + [ + 0.5, + 0.64453125, + 0.64453125 + ], + [ + 0.5, + 0.79296875, + 0.79296875 + ], + [ + 0.5, + 0.78125, + 0.78125 + ], + [ + 0.5, + 0.7421875, + 0.7421875 + ], + [ + 0.5, + 0.60546875, + 0.60546875 + ], + [ + 0.5, + 0.5859375, + 0.5859375 + ], + [ + 0.5, + 0.7265625, + 0.7265625 + ], + [ + 0.5, + 0.72265625, + 0.72265625 + ], + [ + 0.5, + 0.7109375, + 0.7109375 + ], + [ + 0.5, + 0.5859375, + 0.5859375 + ], + [ + 0.5, + 0.7421875, + 0.7421875 + ], + [ + 0.5, + 0.6953125, + 0.6953125 + ], + [ + 0.5, + 0.7421875, + 0.7421875 + ], + [ + 0.5, + 0.68359375, + 0.68359375 + ], + [ + 0.5, + 0.85546875, + 0.85546875 + ], + [ + 0.5, + 0.71484375, + 0.71484375 + ], + [ + 0.5, + 0.92578125, + 0.92578125 + ], + [ + 0.5, + 0.765625, + 0.765625 + ], + [ + 0.5, + 0.67578125, + 0.67578125 + ], + [ + 0.5, + 0.740234375, + 0.740234375 + ], + [ + 0.5, + 0.724609375, + 0.724609375 + ], + [ + 0.5, + 0.78125, + 0.78125 + ], + [ + 0.5, + 0.859375, + 0.859375 + ], + [ + 0.5, + 0.5859375, + 0.5859375 + ], + [ + 0.5, + 0.796875, + 0.796875 + ], + [ + 0.5, + 0.75, + 0.75 + ], + [ + 0.5, + 0.64453125, + 0.64453125 + ], + [ + 0.5, + 0.64453125, + 0.64453125 + ], + [ + 0.5, + 0.75, + 0.75 + ], + [ + 0.5, + 0.75, + 0.75 + ], + [ + 0.5, + 0.7109375, + 0.7109375 + ], + [ + 0.5, + 0.712890625, + 0.712890625 + ], + [ + 0.5, + 0.64453125, + 0.64453125 + ], + [ + 0.5, + 0.736328125, + 0.736328125 + ], + [ + 0.5, + 0.5859375, + 0.5859375 + ], + [ + 0.5, + 0.71484375, + 0.71484375 + ], + [ + 0.5, + 0.83203125, + 0.83203125 + ], + [ + 0.5, + 0.6328125, + 0.6328125 + ], + [ + 0.5, + 0.6640625, + 0.6640625 + ], + [ + 0.5, + 0.65234375, + 0.65234375 + ], + [ + 0.5, + 0.62890625, + 0.62890625 + ], + [ + 0.5, + 0.5859375, + 0.5859375 + ], + [ + 0.5, + 0.55078125, + 0.55078125 + ], + [ + 0.5, + 0.88671875, + 0.88671875 + ], + [ + 0.5, + 0.6953125, + 0.6953125 + ], + [ + 0.5, + 0.859375, + 0.859375 + ], + [ + 0.5, + 0.71484375, + 0.71484375 + ], + [ + 0.5, + 0.560546875, + 0.560546875 + ], + [ + 0.5, + 0.5625, + 0.5625 + ], + [ + 0.75, + 0.73046875, + 0.73046875 + ], + [ + 0.5, + 0.802734375, + 0.802734375 + ], + [ + 0.5, + 0.84375, + 0.84375 + ], + [ + 0.5, + 0.69921875, + 0.69921875 + ], + [ + 0.5, + 0.759765625, + 0.759765625 + ], + [ + 0.5, + 0.62109375, + 0.62109375 + ], + [ + 0.5, + 0.8125, + 0.8125 + ], + [ + 0.5, + 0.6484375, + 0.6484375 + ], + [ + 0.5, + 0.75, + 0.75 + ], + [ + 0.5, + 0.7890625, + 0.7890625 + ], + [ + 0.5, + 0.80859375, + 0.80859375 + ], + [ + 0.5, + 0.775390625, + 0.775390625 + ], + [ + 0.5, + 0.591796875, + 0.591796875 + ], + [ + 0.5, + 0.6328125, + 0.6328125 + ], + [ + 0.5, + 0.6523438096046448, + 0.6523438096046448 + ], + [ + 0.5, + 0.93359375, + 0.93359375 + ], + [ + 0.5, + 0.74609375, + 0.74609375 + ], + [ + 0.75, + 0.6640625, + 0.6640625 + ], + [ + 0.5, + 0.625, + 0.625 + ], + [ + 0.5, + 0.5625, + 0.5625 + ], + [ + 0.5, + 0.953125, + 0.953125 + ], + [ + 0.75, + 0.73046875, + 0.73046875 + ], + [ + 0.5, + 0.802734375, + 0.802734375 + ], + [ + 0.5, + 0.69140625, + 0.69140625 + ], + [ + 0.5, + 0.666015625, + 0.666015625 + ], + [ + 0.5, + 0.765625, + 0.765625 + ], + [ + 0.5, + 0.830078125, + 0.830078125 + ], + [ + 0.5, + 0.80859375, + 0.80859375 + ], + [ + 0.5, + 0.72265625, + 0.72265625 + ], + [ + 0.5, + 0.6953125, + 0.6953125 + ], + [ + 0.5, + 0.70703125, + 0.70703125 + ], + [ + 0.5, + 0.689453125, + 0.689453125 + ], + [ + 0.75, + 0.771484375, + 0.771484375 + ], + [ + 0.5, + 0.6171875, + 0.6171875 + ], + [ + 0.5, + 0.79296875, + 0.79296875 + ], + [ + 0.5, + 0.71484375, + 0.71484375 + ], + [ + 0.5, + 0.71484375, + 0.71484375 + ], + [ + 0.5, + 0.80859375, + 0.80859375 + ], + [ + 0.5, + 0.8515625, + 0.8515625 + ], + [ + 0.5, + 0.689453125, + 0.689453125 + ], + [ + 0.5, + 0.693359375, + 0.693359375 + ] + ] +} \ No newline at end of file diff --git a/Dataset809_AbdomenAtlasF17/nnUNetTrainer__nnUNetResEncUNetLPlans__3d_fullres/fold_all/.DS_Store b/Dataset809_AbdomenAtlasF17/nnUNetTrainer__nnUNetResEncUNetLPlans__3d_fullres/fold_all/.DS_Store new file mode 100644 index 0000000000000000000000000000000000000000..5008ddfcf53c02e82d7eee2e57c38e5672ef89f6 Binary files /dev/null and b/Dataset809_AbdomenAtlasF17/nnUNetTrainer__nnUNetResEncUNetLPlans__3d_fullres/fold_all/.DS_Store differ diff --git a/Dataset809_AbdomenAtlasF17/nnUNetTrainer__nnUNetResEncUNetLPlans__3d_fullres/fold_all/checkpoint_best.pth b/Dataset809_AbdomenAtlasF17/nnUNetTrainer__nnUNetResEncUNetLPlans__3d_fullres/fold_all/checkpoint_best.pth new file mode 100644 index 0000000000000000000000000000000000000000..7f379d95c53a808e960361bc1323e35dbfffc753 --- /dev/null +++ b/Dataset809_AbdomenAtlasF17/nnUNetTrainer__nnUNetResEncUNetLPlans__3d_fullres/fold_all/checkpoint_best.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b2c5c78b5a40289b05ad8051f385d4b01ea61ead3b48dfadc302d2387a06d50a +size 820518770 diff --git a/Dataset809_AbdomenAtlasF17/nnUNetTrainer__nnUNetResEncUNetLPlans__3d_fullres/fold_all/checkpoint_final.pth b/Dataset809_AbdomenAtlasF17/nnUNetTrainer__nnUNetResEncUNetLPlans__3d_fullres/fold_all/checkpoint_final.pth new file mode 100644 index 0000000000000000000000000000000000000000..012c2f135cdfe6b64dd49ae630c2442231f3cbd4 --- /dev/null +++ b/Dataset809_AbdomenAtlasF17/nnUNetTrainer__nnUNetResEncUNetLPlans__3d_fullres/fold_all/checkpoint_final.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e59f75679e8f119a3ff67bd3c86f34ac005bc687d4875bc59b7e878259e36582 +size 820526982 diff --git a/Dataset809_AbdomenAtlasF17/nnUNetTrainer__nnUNetResEncUNetLPlans__3d_fullres/fold_all/debug.json b/Dataset809_AbdomenAtlasF17/nnUNetTrainer__nnUNetResEncUNetLPlans__3d_fullres/fold_all/debug.json new file mode 100644 index 0000000000000000000000000000000000000000..9984c7fa3ecfee740d50fe4c02b25d9fab3d3cc4 --- /dev/null +++ b/Dataset809_AbdomenAtlasF17/nnUNetTrainer__nnUNetResEncUNetLPlans__3d_fullres/fold_all/debug.json @@ -0,0 +1,53 @@ +{ + "_best_ema": "0.80715364", + "batch_size": "2", + "configuration_manager": "{'data_identifier': 'nnUNetPlans_3d_fullres', 'preprocessor_name': 'DefaultPreprocessor', 'batch_size': 2, 'patch_size': [160, 224, 192], 'median_image_size_in_voxels': [512.0, 613.0, 513.0], 'spacing': [0.7109375, 0.5, 0.7109375], 'normalization_schemes': ['CTNormalization'], 'use_mask_for_norm': [False], 'resampling_fn_data': 'resample_data_or_seg_to_shape', 'resampling_fn_seg': 'resample_data_or_seg_to_shape', 'resampling_fn_data_kwargs': {'is_seg': False, 'order': 3, 'order_z': 0, 'force_separate_z': None}, 'resampling_fn_seg_kwargs': {'is_seg': True, 'order': 1, 'order_z': 0, 'force_separate_z': None}, 'resampling_fn_probabilities': 'resample_data_or_seg_to_shape', 'resampling_fn_probabilities_kwargs': {'is_seg': False, 'order': 1, 'order_z': 0, 'force_separate_z': None}, 'architecture': {'network_class_name': 'dynamic_network_architectures.architectures.unet.ResidualEncoderUNet', 'arch_kwargs': {'n_stages': 6, 'features_per_stage': [32, 64, 128, 256, 320, 320], 'conv_op': 'torch.nn.modules.conv.Conv3d', 'kernel_sizes': [[3, 3, 3], [3, 3, 3], [3, 3, 3], [3, 3, 3], [3, 3, 3], [3, 3, 3]], 'strides': [[1, 1, 1], [2, 2, 2], [2, 2, 2], [2, 2, 2], [2, 2, 2], [2, 2, 2]], 'n_blocks_per_stage': [1, 3, 4, 6, 6, 6], 'n_conv_per_stage_decoder': [1, 1, 1, 1, 1], 'conv_bias': True, 'norm_op': 'torch.nn.modules.instancenorm.InstanceNorm3d', 'norm_op_kwargs': {'eps': 1e-05, 'affine': True}, 'dropout_op': None, 'dropout_op_kwargs': None, 'nonlin': 'torch.nn.LeakyReLU', 'nonlin_kwargs': {'inplace': True}}, '_kw_requires_import': ['conv_op', 'norm_op', 'dropout_op', 'nonlin']}, 'batch_dice': True}", + "configuration_name": "3d_fullres", + "cudnn_version": 90100, + "current_epoch": "900", + "dataloader_train": "", + "dataloader_train.generator": "", + "dataloader_train.num_processes": "12", + "dataloader_train.transform": "None", + "dataloader_val": "", + "dataloader_val.generator": "", + "dataloader_val.num_processes": "6", + "dataloader_val.transform": "None", + "dataset_json": "{'name': 'JHH-Train-test', 'description': '3151 cases for training; 1958 cases for testing', 'reference': 'ScaleMAI', 'licence': 'CC-BY-SA 4.0', 'relase': '1.0 10/28/2024', 'tensorImageSize': '3D', 'labels': {'background': 0, 'aorta': 1, 'adrenal_gland_left': 2, 'adrenal_gland_right': 3, 'celiac_aa': 4, 'colon': 5, 'duodenum': 6, 'gall_bladder': 7, 'postcava': 8, 'kidney_left': 9, 'kidney_right': 10, 'liver': 11, 'pancreas': 12, 'superior_mesenteric_artery': 13, 'intestine': 14, 'spleen': 15, 'renal_vein_left': 16, 'renal_vein_right': 17}, 'numTraining': 3151, 'numTest': 1958, 'file_ending': '.nii.gz', 'channel_names': {'0': 'CT'}}", + "device": "cuda:0", + "disable_checkpointing": "False", + "enable_deep_supervision": "True", + "fold": "all", + "folder_with_segs_from_previous_stage": "None", + "gpu_name": "NVIDIA TITAN RTX", + "grad_scaler": "", + "hostname": "ccvl18", + "inference_allowed_mirroring_axes": "(0, 1, 2)", + "initial_lr": "0.01", + "is_cascaded": "False", + "is_ddp": "False", + "label_manager": "", + "local_rank": "0", + "log_file": "/mnt/T9/tlin67/nnUNet_results/Dataset809_AbdomenAtlasF17/nnUNetTrainer__nnUNetResEncUNetLPlans__3d_fullres/fold_all/training_log_2025_11_7_21_08_06.txt", + "logger": "", + "loss": "DeepSupervisionWrapper(\n (loss): DC_and_CE_loss(\n (ce): RobustCrossEntropyLoss()\n (dc): OptimizedModule(\n (_orig_mod): MemoryEfficientSoftDiceLoss()\n )\n )\n)", + "lr_scheduler": "", + "my_init_kwargs": "{'plans': {'dataset_name': 'Dataset809_AbdomenAtlasF17', 'plans_name': 'nnUNetResEncUNetLPlans', 'original_median_spacing_after_transp': [0.7109375, 0.5, 0.7109375], 'original_median_shape_after_transp': [512, 608, 512], 'image_reader_writer': 'SimpleITKIO', 'transpose_forward': [1, 0, 2], 'transpose_backward': [1, 0, 2], 'configurations': {'2d': {'data_identifier': 'nnUNetPlans_2d', 'preprocessor_name': 'DefaultPreprocessor', 'batch_size': 22, 'patch_size': [640, 640], 'median_image_size_in_voxels': [613.0, 513.0], 'spacing': [0.5, 0.7109375], 'normalization_schemes': ['CTNormalization'], 'use_mask_for_norm': [False], 'resampling_fn_data': 'resample_data_or_seg_to_shape', 'resampling_fn_seg': 'resample_data_or_seg_to_shape', 'resampling_fn_data_kwargs': {'is_seg': False, 'order': 3, 'order_z': 0, 'force_separate_z': None}, 'resampling_fn_seg_kwargs': {'is_seg': True, 'order': 1, 'order_z': 0, 'force_separate_z': None}, 'resampling_fn_probabilities': 'resample_data_or_seg_to_shape', 'resampling_fn_probabilities_kwargs': {'is_seg': False, 'order': 1, 'order_z': 0, 'force_separate_z': None}, 'architecture': {'network_class_name': 'dynamic_network_architectures.architectures.unet.ResidualEncoderUNet', 'arch_kwargs': {'n_stages': 8, 'features_per_stage': [32, 64, 128, 256, 512, 512, 512, 512], 'conv_op': 'torch.nn.modules.conv.Conv2d', 'kernel_sizes': [[3, 3], [3, 3], [3, 3], [3, 3], [3, 3], [3, 3], [3, 3], [3, 3]], 'strides': [[1, 1], [2, 2], [2, 2], [2, 2], [2, 2], [2, 2], [2, 2], [2, 2]], 'n_blocks_per_stage': [1, 3, 4, 6, 6, 6, 6, 6], 'n_conv_per_stage_decoder': [1, 1, 1, 1, 1, 1, 1], 'conv_bias': True, 'norm_op': 'torch.nn.modules.instancenorm.InstanceNorm2d', 'norm_op_kwargs': {'eps': 1e-05, 'affine': True}, 'dropout_op': None, 'dropout_op_kwargs': None, 'nonlin': 'torch.nn.LeakyReLU', 'nonlin_kwargs': {'inplace': True}}, '_kw_requires_import': ['conv_op', 'norm_op', 'dropout_op', 'nonlin']}, 'batch_dice': True}, '3d_lowres': {'data_identifier': 'nnUNetResEncUNetLPlans_3d_lowres', 'preprocessor_name': 'DefaultPreprocessor', 'batch_size': 2, 'patch_size': [160, 224, 192], 'median_image_size_in_voxels': [283, 339, 284], 'spacing': [1.284032205897787, 0.9030556173347075, 1.284032205897787], 'normalization_schemes': ['CTNormalization'], 'use_mask_for_norm': [False], 'resampling_fn_data': 'resample_data_or_seg_to_shape', 'resampling_fn_seg': 'resample_data_or_seg_to_shape', 'resampling_fn_data_kwargs': {'is_seg': False, 'order': 3, 'order_z': 0, 'force_separate_z': None}, 'resampling_fn_seg_kwargs': {'is_seg': True, 'order': 1, 'order_z': 0, 'force_separate_z': None}, 'resampling_fn_probabilities': 'resample_data_or_seg_to_shape', 'resampling_fn_probabilities_kwargs': {'is_seg': False, 'order': 1, 'order_z': 0, 'force_separate_z': None}, 'architecture': {'network_class_name': 'dynamic_network_architectures.architectures.unet.ResidualEncoderUNet', 'arch_kwargs': {'n_stages': 6, 'features_per_stage': [32, 64, 128, 256, 320, 320], 'conv_op': 'torch.nn.modules.conv.Conv3d', 'kernel_sizes': [[3, 3, 3], [3, 3, 3], [3, 3, 3], [3, 3, 3], [3, 3, 3], [3, 3, 3]], 'strides': [[1, 1, 1], [2, 2, 2], [2, 2, 2], [2, 2, 2], [2, 2, 2], [2, 2, 2]], 'n_blocks_per_stage': [1, 3, 4, 6, 6, 6], 'n_conv_per_stage_decoder': [1, 1, 1, 1, 1], 'conv_bias': True, 'norm_op': 'torch.nn.modules.instancenorm.InstanceNorm3d', 'norm_op_kwargs': {'eps': 1e-05, 'affine': True}, 'dropout_op': None, 'dropout_op_kwargs': None, 'nonlin': 'torch.nn.LeakyReLU', 'nonlin_kwargs': {'inplace': True}}, '_kw_requires_import': ['conv_op', 'norm_op', 'dropout_op', 'nonlin']}, 'batch_dice': False, 'next_stage': '3d_cascade_fullres'}, '3d_fullres': {'data_identifier': 'nnUNetPlans_3d_fullres', 'preprocessor_name': 'DefaultPreprocessor', 'batch_size': 2, 'patch_size': [160, 224, 192], 'median_image_size_in_voxels': [512.0, 613.0, 513.0], 'spacing': [0.7109375, 0.5, 0.7109375], 'normalization_schemes': ['CTNormalization'], 'use_mask_for_norm': [False], 'resampling_fn_data': 'resample_data_or_seg_to_shape', 'resampling_fn_seg': 'resample_data_or_seg_to_shape', 'resampling_fn_data_kwargs': {'is_seg': False, 'order': 3, 'order_z': 0, 'force_separate_z': None}, 'resampling_fn_seg_kwargs': {'is_seg': True, 'order': 1, 'order_z': 0, 'force_separate_z': None}, 'resampling_fn_probabilities': 'resample_data_or_seg_to_shape', 'resampling_fn_probabilities_kwargs': {'is_seg': False, 'order': 1, 'order_z': 0, 'force_separate_z': None}, 'architecture': {'network_class_name': 'dynamic_network_architectures.architectures.unet.ResidualEncoderUNet', 'arch_kwargs': {'n_stages': 6, 'features_per_stage': [32, 64, 128, 256, 320, 320], 'conv_op': 'torch.nn.modules.conv.Conv3d', 'kernel_sizes': [[3, 3, 3], [3, 3, 3], [3, 3, 3], [3, 3, 3], [3, 3, 3], [3, 3, 3]], 'strides': [[1, 1, 1], [2, 2, 2], [2, 2, 2], [2, 2, 2], [2, 2, 2], [2, 2, 2]], 'n_blocks_per_stage': [1, 3, 4, 6, 6, 6], 'n_conv_per_stage_decoder': [1, 1, 1, 1, 1], 'conv_bias': True, 'norm_op': 'torch.nn.modules.instancenorm.InstanceNorm3d', 'norm_op_kwargs': {'eps': 1e-05, 'affine': True}, 'dropout_op': None, 'dropout_op_kwargs': None, 'nonlin': 'torch.nn.LeakyReLU', 'nonlin_kwargs': {'inplace': True}}, '_kw_requires_import': ['conv_op', 'norm_op', 'dropout_op', 'nonlin']}, 'batch_dice': True}, '3d_cascade_fullres': {'inherits_from': '3d_fullres', 'previous_stage': '3d_lowres'}}, 'experiment_planner_used': 'nnUNetPlannerResEncL', 'label_manager': 'LabelManager', 'foreground_intensity_properties_per_channel': {'0': {'max': 1000.0, 'mean': 39.68027877807617, 'median': 71.0, 'min': -1000.0, 'percentile_00_5': -1000.0, 'percentile_99_5': 379.0, 'std': 192.4669952392578}}}, 'configuration': '3d_fullres', 'fold': 'all', 'dataset_json': {'name': 'JHH-Train-test', 'description': '3151 cases for training; 1958 cases for testing', 'reference': 'ScaleMAI', 'licence': 'CC-BY-SA 4.0', 'relase': '1.0 10/28/2024', 'tensorImageSize': '3D', 'labels': {'background': 0, 'aorta': 1, 'adrenal_gland_left': 2, 'adrenal_gland_right': 3, 'celiac_aa': 4, 'colon': 5, 'duodenum': 6, 'gall_bladder': 7, 'postcava': 8, 'kidney_left': 9, 'kidney_right': 10, 'liver': 11, 'pancreas': 12, 'superior_mesenteric_artery': 13, 'intestine': 14, 'spleen': 15, 'renal_vein_left': 16, 'renal_vein_right': 17}, 'numTraining': 3151, 'numTest': 1958, 'file_ending': '.nii.gz', 'channel_names': {'0': 'CT'}}, 'unpack_dataset': True, 'device': device(type='cuda')}", + "network": "OptimizedModule", + "num_epochs": "1000", + "num_input_channels": "1", + "num_iterations_per_epoch": "250", + "num_val_iterations_per_epoch": "50", + "optimizer": "SGD (\nParameter Group 0\n dampening: 0\n differentiable: False\n foreach: None\n fused: None\n initial_lr: 0.01\n lr: 0.0012702500959998477\n maximize: False\n momentum: 0.99\n nesterov: True\n weight_decay: 3e-05\n)", + "output_folder": "/mnt/T9/tlin67/nnUNet_results/Dataset809_AbdomenAtlasF17/nnUNetTrainer__nnUNetResEncUNetLPlans__3d_fullres/fold_all", + "output_folder_base": "/mnt/T9/tlin67/nnUNet_results/Dataset809_AbdomenAtlasF17/nnUNetTrainer__nnUNetResEncUNetLPlans__3d_fullres", + "oversample_foreground_percent": "0.33", + "plans_manager": "{'dataset_name': 'Dataset809_AbdomenAtlasF17', 'plans_name': 'nnUNetResEncUNetLPlans', 'original_median_spacing_after_transp': [0.7109375, 0.5, 0.7109375], 'original_median_shape_after_transp': [512, 608, 512], 'image_reader_writer': 'SimpleITKIO', 'transpose_forward': [1, 0, 2], 'transpose_backward': [1, 0, 2], 'configurations': {'2d': {'data_identifier': 'nnUNetPlans_2d', 'preprocessor_name': 'DefaultPreprocessor', 'batch_size': 22, 'patch_size': [640, 640], 'median_image_size_in_voxels': [613.0, 513.0], 'spacing': [0.5, 0.7109375], 'normalization_schemes': ['CTNormalization'], 'use_mask_for_norm': [False], 'resampling_fn_data': 'resample_data_or_seg_to_shape', 'resampling_fn_seg': 'resample_data_or_seg_to_shape', 'resampling_fn_data_kwargs': {'is_seg': False, 'order': 3, 'order_z': 0, 'force_separate_z': None}, 'resampling_fn_seg_kwargs': {'is_seg': True, 'order': 1, 'order_z': 0, 'force_separate_z': None}, 'resampling_fn_probabilities': 'resample_data_or_seg_to_shape', 'resampling_fn_probabilities_kwargs': {'is_seg': False, 'order': 1, 'order_z': 0, 'force_separate_z': None}, 'architecture': {'network_class_name': 'dynamic_network_architectures.architectures.unet.ResidualEncoderUNet', 'arch_kwargs': {'n_stages': 8, 'features_per_stage': [32, 64, 128, 256, 512, 512, 512, 512], 'conv_op': 'torch.nn.modules.conv.Conv2d', 'kernel_sizes': [[3, 3], [3, 3], [3, 3], [3, 3], [3, 3], [3, 3], [3, 3], [3, 3]], 'strides': [[1, 1], [2, 2], [2, 2], [2, 2], [2, 2], [2, 2], [2, 2], [2, 2]], 'n_blocks_per_stage': [1, 3, 4, 6, 6, 6, 6, 6], 'n_conv_per_stage_decoder': [1, 1, 1, 1, 1, 1, 1], 'conv_bias': True, 'norm_op': 'torch.nn.modules.instancenorm.InstanceNorm2d', 'norm_op_kwargs': {'eps': 1e-05, 'affine': True}, 'dropout_op': None, 'dropout_op_kwargs': None, 'nonlin': 'torch.nn.LeakyReLU', 'nonlin_kwargs': {'inplace': True}}, '_kw_requires_import': ['conv_op', 'norm_op', 'dropout_op', 'nonlin']}, 'batch_dice': True}, '3d_lowres': {'data_identifier': 'nnUNetResEncUNetLPlans_3d_lowres', 'preprocessor_name': 'DefaultPreprocessor', 'batch_size': 2, 'patch_size': [160, 224, 192], 'median_image_size_in_voxels': [283, 339, 284], 'spacing': [1.284032205897787, 0.9030556173347075, 1.284032205897787], 'normalization_schemes': ['CTNormalization'], 'use_mask_for_norm': [False], 'resampling_fn_data': 'resample_data_or_seg_to_shape', 'resampling_fn_seg': 'resample_data_or_seg_to_shape', 'resampling_fn_data_kwargs': {'is_seg': False, 'order': 3, 'order_z': 0, 'force_separate_z': None}, 'resampling_fn_seg_kwargs': {'is_seg': True, 'order': 1, 'order_z': 0, 'force_separate_z': None}, 'resampling_fn_probabilities': 'resample_data_or_seg_to_shape', 'resampling_fn_probabilities_kwargs': {'is_seg': False, 'order': 1, 'order_z': 0, 'force_separate_z': None}, 'architecture': {'network_class_name': 'dynamic_network_architectures.architectures.unet.ResidualEncoderUNet', 'arch_kwargs': {'n_stages': 6, 'features_per_stage': [32, 64, 128, 256, 320, 320], 'conv_op': 'torch.nn.modules.conv.Conv3d', 'kernel_sizes': [[3, 3, 3], [3, 3, 3], [3, 3, 3], [3, 3, 3], [3, 3, 3], [3, 3, 3]], 'strides': [[1, 1, 1], [2, 2, 2], [2, 2, 2], [2, 2, 2], [2, 2, 2], [2, 2, 2]], 'n_blocks_per_stage': [1, 3, 4, 6, 6, 6], 'n_conv_per_stage_decoder': [1, 1, 1, 1, 1], 'conv_bias': True, 'norm_op': 'torch.nn.modules.instancenorm.InstanceNorm3d', 'norm_op_kwargs': {'eps': 1e-05, 'affine': True}, 'dropout_op': None, 'dropout_op_kwargs': None, 'nonlin': 'torch.nn.LeakyReLU', 'nonlin_kwargs': {'inplace': True}}, '_kw_requires_import': ['conv_op', 'norm_op', 'dropout_op', 'nonlin']}, 'batch_dice': False, 'next_stage': '3d_cascade_fullres'}, '3d_fullres': {'data_identifier': 'nnUNetPlans_3d_fullres', 'preprocessor_name': 'DefaultPreprocessor', 'batch_size': 2, 'patch_size': [160, 224, 192], 'median_image_size_in_voxels': [512.0, 613.0, 513.0], 'spacing': [0.7109375, 0.5, 0.7109375], 'normalization_schemes': ['CTNormalization'], 'use_mask_for_norm': [False], 'resampling_fn_data': 'resample_data_or_seg_to_shape', 'resampling_fn_seg': 'resample_data_or_seg_to_shape', 'resampling_fn_data_kwargs': {'is_seg': False, 'order': 3, 'order_z': 0, 'force_separate_z': None}, 'resampling_fn_seg_kwargs': {'is_seg': True, 'order': 1, 'order_z': 0, 'force_separate_z': None}, 'resampling_fn_probabilities': 'resample_data_or_seg_to_shape', 'resampling_fn_probabilities_kwargs': {'is_seg': False, 'order': 1, 'order_z': 0, 'force_separate_z': None}, 'architecture': {'network_class_name': 'dynamic_network_architectures.architectures.unet.ResidualEncoderUNet', 'arch_kwargs': {'n_stages': 6, 'features_per_stage': [32, 64, 128, 256, 320, 320], 'conv_op': 'torch.nn.modules.conv.Conv3d', 'kernel_sizes': [[3, 3, 3], [3, 3, 3], [3, 3, 3], [3, 3, 3], [3, 3, 3], [3, 3, 3]], 'strides': [[1, 1, 1], [2, 2, 2], [2, 2, 2], [2, 2, 2], [2, 2, 2], [2, 2, 2]], 'n_blocks_per_stage': [1, 3, 4, 6, 6, 6], 'n_conv_per_stage_decoder': [1, 1, 1, 1, 1], 'conv_bias': True, 'norm_op': 'torch.nn.modules.instancenorm.InstanceNorm3d', 'norm_op_kwargs': {'eps': 1e-05, 'affine': True}, 'dropout_op': None, 'dropout_op_kwargs': None, 'nonlin': 'torch.nn.LeakyReLU', 'nonlin_kwargs': {'inplace': True}}, '_kw_requires_import': ['conv_op', 'norm_op', 'dropout_op', 'nonlin']}, 'batch_dice': True}, '3d_cascade_fullres': {'inherits_from': '3d_fullres', 'previous_stage': '3d_lowres'}}, 'experiment_planner_used': 'nnUNetPlannerResEncL', 'label_manager': 'LabelManager', 'foreground_intensity_properties_per_channel': {'0': {'max': 1000.0, 'mean': 39.68027877807617, 'median': 71.0, 'min': -1000.0, 'percentile_00_5': -1000.0, 'percentile_99_5': 379.0, 'std': 192.4669952392578}}}", + "preprocessed_dataset_folder": "/mnt/T9/tlin67/Dataset_preprocessed/Dataset809_AbdomenAtlasF17/nnUNetPlans_3d_fullres", + "preprocessed_dataset_folder_base": "/mnt/T9/tlin67/Dataset_preprocessed/Dataset809_AbdomenAtlasF17", + "save_every": "50", + "torch_version": "2.4.0+cu121", + "unpack_dataset": "True", + "was_initialized": "True", + "weight_decay": "3e-05" +} \ No newline at end of file diff --git a/Dataset809_AbdomenAtlasF17/nnUNetTrainer__nnUNetResEncUNetLPlans__3d_fullres/fold_all/progress.png b/Dataset809_AbdomenAtlasF17/nnUNetTrainer__nnUNetResEncUNetLPlans__3d_fullres/fold_all/progress.png new file mode 100644 index 0000000000000000000000000000000000000000..32346752f604e38502c354bc3c2b6265c7a30bfe --- /dev/null +++ b/Dataset809_AbdomenAtlasF17/nnUNetTrainer__nnUNetResEncUNetLPlans__3d_fullres/fold_all/progress.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3761cc90cb8d651acb34978204dae754a776901b234cc376ee73bdc1b1c0c068 +size 679314 diff --git a/Dataset809_AbdomenAtlasF17/nnUNetTrainer__nnUNetResEncUNetLPlans__3d_fullres/fold_all/training_log_2025_10_28_22_51_12.txt b/Dataset809_AbdomenAtlasF17/nnUNetTrainer__nnUNetResEncUNetLPlans__3d_fullres/fold_all/training_log_2025_10_28_22_51_12.txt new file mode 100644 index 0000000000000000000000000000000000000000..4467cc067fff63201d4415165ad51fbae40f4c82 --- /dev/null +++ b/Dataset809_AbdomenAtlasF17/nnUNetTrainer__nnUNetResEncUNetLPlans__3d_fullres/fold_all/training_log_2025_10_28_22_51_12.txt @@ -0,0 +1,3369 @@ + +####################################################################### +Please cite the following paper when using nnU-Net: +Isensee, F., Jaeger, P. F., Kohl, S. A., Petersen, J., & Maier-Hein, K. H. (2021). nnU-Net: a self-configuring method for deep learning-based biomedical image segmentation. Nature methods, 18(2), 203-211. +####################################################################### + +2025-10-28 22:51:12.903960: do_dummy_2d_data_aug: False +2025-10-28 22:52:35.706528: Using torch.compile... + +This is the configuration used by this training: +Configuration name: 3d_fullres + {'data_identifier': 'nnUNetPlans_3d_fullres', 'preprocessor_name': 'DefaultPreprocessor', 'batch_size': 2, 'patch_size': [160, 224, 192], 'median_image_size_in_voxels': [512.0, 613.0, 513.0], 'spacing': [0.7109375, 0.5, 0.7109375], 'normalization_schemes': ['CTNormalization'], 'use_mask_for_norm': [False], 'resampling_fn_data': 'resample_data_or_seg_to_shape', 'resampling_fn_seg': 'resample_data_or_seg_to_shape', 'resampling_fn_data_kwargs': {'is_seg': False, 'order': 3, 'order_z': 0, 'force_separate_z': None}, 'resampling_fn_seg_kwargs': {'is_seg': True, 'order': 1, 'order_z': 0, 'force_separate_z': None}, 'resampling_fn_probabilities': 'resample_data_or_seg_to_shape', 'resampling_fn_probabilities_kwargs': {'is_seg': False, 'order': 1, 'order_z': 0, 'force_separate_z': None}, 'architecture': {'network_class_name': 'dynamic_network_architectures.architectures.unet.ResidualEncoderUNet', 'arch_kwargs': {'n_stages': 6, 'features_per_stage': [32, 64, 128, 256, 320, 320], 'conv_op': 'torch.nn.modules.conv.Conv3d', 'kernel_sizes': [[3, 3, 3], [3, 3, 3], [3, 3, 3], [3, 3, 3], [3, 3, 3], [3, 3, 3]], 'strides': [[1, 1, 1], [2, 2, 2], [2, 2, 2], [2, 2, 2], [2, 2, 2], [2, 2, 2]], 'n_blocks_per_stage': [1, 3, 4, 6, 6, 6], 'n_conv_per_stage_decoder': [1, 1, 1, 1, 1], 'conv_bias': True, 'norm_op': 'torch.nn.modules.instancenorm.InstanceNorm3d', 'norm_op_kwargs': {'eps': 1e-05, 'affine': True}, 'dropout_op': None, 'dropout_op_kwargs': None, 'nonlin': 'torch.nn.LeakyReLU', 'nonlin_kwargs': {'inplace': True}}, '_kw_requires_import': ['conv_op', 'norm_op', 'dropout_op', 'nonlin']}, 'batch_dice': True} + +These are the global plan.json settings: + {'dataset_name': 'Dataset809_AbdomenAtlasF17', 'plans_name': 'nnUNetResEncUNetLPlans', 'original_median_spacing_after_transp': [0.7109375, 0.5, 0.7109375], 'original_median_shape_after_transp': [512, 608, 512], 'image_reader_writer': 'SimpleITKIO', 'transpose_forward': [1, 0, 2], 'transpose_backward': [1, 0, 2], 'experiment_planner_used': 'nnUNetPlannerResEncL', 'label_manager': 'LabelManager', 'foreground_intensity_properties_per_channel': {'0': {'max': 1000.0, 'mean': 39.68027877807617, 'median': 71.0, 'min': -1000.0, 'percentile_00_5': -1000.0, 'percentile_99_5': 379.0, 'std': 192.4669952392578}}} + +2025-10-28 22:52:45.251093: unpacking dataset... +2025-10-29 03:04:14.185816: unpacking done... +2025-10-29 03:04:14.210528: Unable to plot network architecture: nnUNet_compile is enabled! +2025-10-29 03:04:14.633008: +2025-10-29 03:04:14.634617: Epoch 0 +2025-10-29 03:04:14.641395: Current learning rate: 0.01 +2025-10-29 03:16:07.709939: train_loss 1.1435 +2025-10-29 03:16:07.739164: val_loss 0.9795 +2025-10-29 03:16:07.741052: Pseudo dice [np.float32(0.0), np.float32(0.0), np.float32(0.0), np.float32(0.0), np.float32(0.0114), np.float32(0.0), np.float32(0.0), np.float32(0.0), np.float32(0.0), np.float32(0.0), np.float32(0.0), np.float32(0.0), np.float32(0.0), np.float32(0.0), np.float32(0.0), np.float32(0.0), np.float32(0.0)] +2025-10-29 03:16:07.742556: Epoch time: 713.09 s +2025-10-29 03:16:07.743856: Yayy! New best EMA pseudo Dice: 0.000699999975040555 +2025-10-29 03:16:14.901604: +2025-10-29 03:16:14.908938: Epoch 1 +2025-10-29 03:16:14.912533: Current learning rate: 0.00999 +2025-10-29 03:25:20.356294: train_loss 0.879 +2025-10-29 03:25:20.364063: val_loss 0.7949 +2025-10-29 03:25:20.365272: Pseudo dice [np.float32(0.0), np.float32(0.0), np.float32(0.0), np.float32(0.0), np.float32(0.0066), np.float32(0.0), np.float32(0.0), np.float32(0.0), np.float32(0.0), np.float32(0.0), np.float32(0.1963), np.float32(0.0), np.float32(0.0), np.float32(0.0), np.float32(0.0), np.float32(0.0), np.float32(0.0)] +2025-10-29 03:25:20.366601: Epoch time: 545.46 s +2025-10-29 03:25:20.367934: Yayy! New best EMA pseudo Dice: 0.0017999999690800905 +2025-10-29 03:25:24.534014: +2025-10-29 03:25:24.535212: Epoch 2 +2025-10-29 03:25:24.536794: Current learning rate: 0.00998 +2025-10-29 04:18:29.117362: train_loss 0.7741 +2025-10-29 04:18:29.123326: val_loss 0.7514 +2025-10-29 04:18:29.124523: Pseudo dice [np.float32(0.0222), np.float32(0.0), np.float32(0.0), np.float32(0.0), np.float32(0.1129), np.float32(0.0), np.float32(0.0), np.float32(0.0), np.float32(0.0), np.float32(0.0006), np.float32(0.5269), np.float32(0.0), np.float32(0.0), np.float32(0.0), np.float32(0.0), np.float32(0.0), np.float32(0.0)] +2025-10-29 04:18:29.125996: Epoch time: 3184.59 s +2025-10-29 04:18:29.127331: Yayy! New best EMA pseudo Dice: 0.005499999970197678 +2025-10-29 04:18:33.195214: +2025-10-29 04:18:33.198257: Epoch 3 +2025-10-29 04:18:33.199532: Current learning rate: 0.00997 +2025-10-29 04:29:03.078311: train_loss 0.7188 +2025-10-29 04:29:03.087715: val_loss 0.7238 +2025-10-29 04:29:03.089129: Pseudo dice [np.float32(0.1533), np.float32(0.0), np.float32(0.0), np.float32(0.0), np.float32(0.2752), np.float32(0.0), np.float32(0.0), np.float32(0.0), np.float32(0.2737), np.float32(0.0), np.float32(0.5941), np.float32(0.0), np.float32(0.0), np.float32(0.0), np.float32(0.0), np.float32(0.0), np.float32(0.0)] +2025-10-29 04:29:03.090657: Epoch time: 629.89 s +2025-10-29 04:29:03.092201: Yayy! New best EMA pseudo Dice: 0.012600000016391277 +2025-10-29 04:29:07.305075: +2025-10-29 04:29:07.310085: Epoch 4 +2025-10-29 04:29:07.311722: Current learning rate: 0.00996 +2025-10-29 04:39:31.251895: train_loss 0.6562 +2025-10-29 04:39:31.275317: val_loss 0.6172 +2025-10-29 04:39:31.276803: Pseudo dice [np.float32(0.0009), np.float32(0.0), np.float32(0.0), np.float32(0.0), np.float32(0.4916), np.float32(0.0), np.float32(0.0), np.float32(0.0), np.float32(0.5417), np.float32(0.0), np.float32(0.6623), np.float32(0.0), np.float32(0.0), np.float32(0.0), np.float32(0.0), np.float32(0.0), np.float32(0.0)] +2025-10-29 04:39:31.283282: Epoch time: 623.95 s +2025-10-29 04:39:31.288370: Yayy! New best EMA pseudo Dice: 0.021299999207258224 +2025-10-29 04:39:35.539147: +2025-10-29 04:39:35.548715: Epoch 5 +2025-10-29 04:39:35.550482: Current learning rate: 0.00995 +2025-10-29 04:50:15.720959: train_loss 0.5691 +2025-10-29 04:50:15.728331: val_loss 0.529 +2025-10-29 04:50:15.729835: Pseudo dice [np.float32(0.3567), np.float32(0.0), np.float32(0.0), np.float32(0.0), np.float32(0.5288), np.float32(0.0), np.float32(0.0), np.float32(0.0), np.float32(0.3577), np.float32(0.3122), np.float32(0.7059), np.float32(0.0), np.float32(0.0), np.float32(0.0862), np.float32(0.0589), np.float32(0.0), np.float32(0.0)] +2025-10-29 04:50:15.731174: Epoch time: 640.19 s +2025-10-29 04:50:15.732277: Yayy! New best EMA pseudo Dice: 0.0333000011742115 +2025-10-29 04:50:20.042686: +2025-10-29 04:50:20.044040: Epoch 6 +2025-10-29 04:50:20.045417: Current learning rate: 0.00995 +2025-10-29 05:00:42.531369: train_loss 0.5184 +2025-10-29 05:00:42.537497: val_loss 0.4745 +2025-10-29 05:00:42.539270: Pseudo dice [np.float32(0.4346), np.float32(0.0), np.float32(0.0), np.float32(0.0), np.float32(0.4416), np.float32(0.0), np.float32(0.0), np.float32(0.0), np.float32(0.5408), np.float32(0.1765), np.float32(0.7352), np.float32(0.0), np.float32(0.0), np.float32(0.1316), np.float32(0.2263), np.float32(0.0), np.float32(0.0)] +2025-10-29 05:00:42.541211: Epoch time: 622.49 s +2025-10-29 05:00:42.542246: Yayy! New best EMA pseudo Dice: 0.04580000042915344 +2025-10-29 05:00:46.786365: +2025-10-29 05:00:46.810617: Epoch 7 +2025-10-29 05:00:46.814260: Current learning rate: 0.00994 +2025-10-29 05:11:11.656176: train_loss 0.4649 +2025-10-29 05:11:11.661906: val_loss 0.4036 +2025-10-29 05:11:11.663132: Pseudo dice [np.float32(0.6124), np.float32(0.0), np.float32(0.0), np.float32(0.0), np.float32(0.5456), np.float32(0.0), np.float32(0.0), np.float32(0.0092), np.float32(0.5153), np.float32(0.0568), np.float32(0.7972), np.float32(0.0), np.float32(0.0), np.float32(0.239), np.float32(0.1089), np.float32(0.0), np.float32(0.0)] +2025-10-29 05:11:11.664488: Epoch time: 624.87 s +2025-10-29 05:11:11.665718: Yayy! New best EMA pseudo Dice: 0.05820000171661377 +2025-10-29 05:11:16.168741: +2025-10-29 05:11:16.176692: Epoch 8 +2025-10-29 05:11:16.179006: Current learning rate: 0.00993 +2025-10-29 05:21:38.416054: train_loss 0.4304 +2025-10-29 05:21:38.424648: val_loss 0.3901 +2025-10-29 05:21:38.427627: Pseudo dice [np.float32(0.6806), np.float32(0.0), np.float32(0.0), np.float32(0.0), np.float32(0.5911), np.float32(0.0), np.float32(0.0), np.float32(0.1977), np.float32(1e-04), np.float32(0.5171), np.float32(0.735), np.float32(0.0409), np.float32(0.0), np.float32(0.3179), np.float32(0.0052), np.float32(0.0), np.float32(0.0)] +2025-10-29 05:21:38.457591: Epoch time: 622.25 s +2025-10-29 05:21:38.464983: Yayy! New best EMA pseudo Dice: 0.07050000131130219 +2025-10-29 05:21:42.883873: +2025-10-29 05:21:42.900773: Epoch 9 +2025-10-29 05:21:42.901934: Current learning rate: 0.00992 +2025-10-29 05:32:19.147123: train_loss 0.4177 +2025-10-29 05:32:19.176367: val_loss 0.3688 +2025-10-29 05:32:19.177717: Pseudo dice [np.float32(0.7222), np.float32(0.0), np.float32(0.0), np.float32(0.0), np.float32(0.6147), np.float32(0.0), np.float32(0.0), np.float32(0.3041), np.float32(0.5091), np.float32(0.1321), np.float32(0.7544), np.float32(0.1305), np.float32(0.0), np.float32(0.4813), np.float32(0.3715), np.float32(0.0), np.float32(0.0)] +2025-10-29 05:32:19.179417: Epoch time: 636.27 s +2025-10-29 05:32:19.181290: Yayy! New best EMA pseudo Dice: 0.08709999918937683 +2025-10-29 05:32:23.347480: +2025-10-29 05:32:23.349147: Epoch 10 +2025-10-29 05:32:23.350360: Current learning rate: 0.00991 +2025-10-29 05:42:54.996432: train_loss 0.3778 +2025-10-29 05:42:55.001212: val_loss 0.374 +2025-10-29 05:42:55.003212: Pseudo dice [np.float32(0.6992), np.float32(0.0), np.float32(0.0), np.float32(0.0), np.float32(0.6371), np.float32(0.0358), np.float32(0.0), np.float32(0.3369), np.float32(0.0171), np.float32(0.5132), np.float32(0.7963), np.float32(0.1304), np.float32(0.0), np.float32(0.412), np.float32(0.2734), np.float32(0.0), np.float32(0.0)] +2025-10-29 05:42:55.004646: Epoch time: 631.65 s +2025-10-29 05:42:55.006182: Yayy! New best EMA pseudo Dice: 0.10109999775886536 +2025-10-29 05:42:58.947271: +2025-10-29 05:42:58.948927: Epoch 11 +2025-10-29 05:42:58.950669: Current learning rate: 0.0099 +2025-10-29 05:53:20.747276: train_loss 0.2949 +2025-10-29 05:53:20.753076: val_loss 0.3008 +2025-10-29 05:53:20.754729: Pseudo dice [np.float32(0.6812), np.float32(0.0), np.float32(0.0), np.float32(0.0), np.float32(0.6879), np.float32(0.1041), np.float32(0.0), np.float32(0.3997), np.float32(0.437), np.float32(0.068), np.float32(0.8244), np.float32(0.0507), np.float32(0.0), np.float32(0.5228), np.float32(0.3263), np.float32(0.0), np.float32(0.0)] +2025-10-29 05:53:20.755975: Epoch time: 621.8 s +2025-10-29 05:53:20.757423: Yayy! New best EMA pseudo Dice: 0.11509999632835388 +2025-10-29 05:53:24.905769: +2025-10-29 05:53:24.907273: Epoch 12 +2025-10-29 05:53:24.908584: Current learning rate: 0.00989 +2025-10-29 06:04:02.618077: train_loss 0.2765 +2025-10-29 06:04:02.643013: val_loss 0.2204 +2025-10-29 06:04:02.645132: Pseudo dice [np.float32(0.7783), np.float32(0.0), np.float32(0.0), np.float32(0.0), np.float32(0.6584), np.float32(0.0239), np.float32(0.0), np.float32(0.5872), np.float32(0.5706), np.float32(0.1422), np.float32(0.7438), np.float32(0.4243), np.float32(0.0), np.float32(0.4866), np.float32(0.4454), np.float32(0.0), np.float32(0.0)] +2025-10-29 06:04:02.646477: Epoch time: 637.72 s +2025-10-29 06:04:02.647536: Yayy! New best EMA pseudo Dice: 0.13220000267028809 +2025-10-29 06:04:07.101446: +2025-10-29 06:04:07.108492: Epoch 13 +2025-10-29 06:04:07.112646: Current learning rate: 0.00988 +2025-10-29 06:14:33.507998: train_loss 0.2364 +2025-10-29 06:14:33.512925: val_loss 0.2146 +2025-10-29 06:14:33.514356: Pseudo dice [np.float32(0.785), np.float32(0.0), np.float32(0.0), np.float32(0.0), np.float32(0.6378), np.float32(0.0356), np.float32(0.0), np.float32(0.5564), np.float32(0.4033), np.float32(0.7016), np.float32(0.8521), np.float32(0.342), np.float32(0.0), np.float32(0.5536), np.float32(0.456), np.float32(0.0), np.float32(0.0)] +2025-10-29 06:14:33.515540: Epoch time: 626.41 s +2025-10-29 06:14:33.516501: Yayy! New best EMA pseudo Dice: 0.15029999613761902 +2025-10-29 06:14:37.946906: +2025-10-29 06:14:37.948421: Epoch 14 +2025-10-29 06:14:37.949894: Current learning rate: 0.00987 +2025-10-29 06:25:09.197132: train_loss 0.1959 +2025-10-29 06:25:09.209028: val_loss 0.1955 +2025-10-29 06:25:09.210340: Pseudo dice [np.float32(0.7776), np.float32(0.0), np.float32(0.0), np.float32(0.0), np.float32(0.7099), np.float32(0.1421), np.float32(0.0), np.float32(0.6246), np.float32(0.5692), np.float32(0.3856), np.float32(0.819), np.float32(0.4399), np.float32(0.0061), np.float32(0.6328), np.float32(0.5268), np.float32(0.0), np.float32(0.0)] +2025-10-29 06:25:09.211817: Epoch time: 631.25 s +2025-10-29 06:25:09.213560: Yayy! New best EMA pseudo Dice: 0.16840000450611115 +2025-10-29 06:25:13.553192: +2025-10-29 06:25:13.554496: Epoch 15 +2025-10-29 06:25:13.555605: Current learning rate: 0.00986 +2025-10-29 06:35:44.631234: train_loss 0.1825 +2025-10-29 06:35:44.639610: val_loss 0.1647 +2025-10-29 06:35:44.641381: Pseudo dice [np.float32(0.8168), np.float32(0.0), np.float32(0.0), np.float32(0.0), np.float32(0.6766), np.float32(0.2349), np.float32(0.0), np.float32(0.6629), np.float32(0.6342), np.float32(0.1203), np.float32(0.86), np.float32(0.441), np.float32(0.1867), np.float32(0.5887), np.float32(0.6633), np.float32(0.0), np.float32(0.0)] +2025-10-29 06:35:44.643662: Epoch time: 631.08 s +2025-10-29 06:35:44.645000: Yayy! New best EMA pseudo Dice: 0.18619999289512634 +2025-10-29 06:35:49.016070: +2025-10-29 06:35:49.020521: Epoch 16 +2025-10-29 06:35:49.021671: Current learning rate: 0.00986 +2025-10-29 06:46:05.714644: train_loss 0.1483 +2025-10-29 06:46:05.721828: val_loss 0.1572 +2025-10-29 06:46:05.723162: Pseudo dice [np.float32(0.8662), np.float32(0.0), np.float32(0.0), np.float32(0.0), np.float32(0.7011), np.float32(0.2985), np.float32(0.0), np.float32(0.6482), np.float32(0.5757), np.float32(0.5531), np.float32(0.7564), np.float32(0.4463), np.float32(0.0983), np.float32(0.6082), np.float32(0.6022), np.float32(0.0), np.float32(0.0)] +2025-10-29 06:46:05.725144: Epoch time: 616.7 s +2025-10-29 06:46:05.738007: Yayy! New best EMA pseudo Dice: 0.2037000060081482 +2025-10-29 06:46:10.220311: +2025-10-29 06:46:10.222229: Epoch 17 +2025-10-29 06:46:10.224055: Current learning rate: 0.00985 +2025-10-29 06:56:31.991221: train_loss 0.1388 +2025-10-29 06:56:32.007721: val_loss 0.0724 +2025-10-29 06:56:32.010756: Pseudo dice [np.float32(0.8641), np.float32(0.0), np.float32(0.0), np.float32(0.0055), np.float32(0.7157), np.float32(0.299), np.float32(0.0), np.float32(0.6697), np.float32(0.7335), np.float32(0.5784), np.float32(0.8437), np.float32(0.5023), np.float32(0.2987), np.float32(0.6487), np.float32(0.6003), np.float32(0.0), np.float32(0.0)] +2025-10-29 06:56:32.015202: Epoch time: 621.77 s +2025-10-29 06:56:32.016266: Yayy! New best EMA pseudo Dice: 0.22310000658035278 +2025-10-29 06:56:36.215720: +2025-10-29 06:56:36.217035: Epoch 18 +2025-10-29 06:56:36.218142: Current learning rate: 0.00984 +2025-10-29 07:07:01.998962: train_loss 0.1129 +2025-10-29 07:07:02.011686: val_loss 0.0564 +2025-10-29 07:07:02.013133: Pseudo dice [np.float32(0.864), np.float32(0.0), np.float32(0.0), np.float32(0.0151), np.float32(0.695), np.float32(0.3178), np.float32(0.0), np.float32(0.725), np.float32(0.8184), np.float32(0.7057), np.float32(0.8606), np.float32(0.4037), np.float32(0.3129), np.float32(0.6332), np.float32(0.5891), np.float32(0.0), np.float32(0.0)] +2025-10-29 07:07:02.015571: Epoch time: 625.79 s +2025-10-29 07:07:02.022038: Yayy! New best EMA pseudo Dice: 0.24160000681877136 +2025-10-29 07:07:06.268312: +2025-10-29 07:07:06.274542: Epoch 19 +2025-10-29 07:07:06.276650: Current learning rate: 0.00983 +2025-10-29 07:17:24.145820: train_loss 0.1079 +2025-10-29 07:17:24.172613: val_loss 0.0855 +2025-10-29 07:17:24.174818: Pseudo dice [np.float32(0.8482), np.float32(0.0), np.float32(0.0), np.float32(0.086), np.float32(0.6882), np.float32(0.4335), np.float32(0.0), np.float32(0.7005), np.float32(0.6343), np.float32(0.7164), np.float32(0.9025), np.float32(0.4664), np.float32(0.4499), np.float32(0.5894), np.float32(0.693), np.float32(0.0), np.float32(0.0)] +2025-10-29 07:17:24.176699: Epoch time: 617.88 s +2025-10-29 07:17:24.178283: Yayy! New best EMA pseudo Dice: 0.2599000036716461 +2025-10-29 07:17:28.296508: +2025-10-29 07:17:28.297965: Epoch 20 +2025-10-29 07:17:28.304938: Current learning rate: 0.00982 +2025-10-29 07:26:31.609133: train_loss 0.059 +2025-10-29 07:26:31.613834: val_loss 0.0206 +2025-10-29 07:26:31.615276: Pseudo dice [np.float32(0.8851), np.float32(0.0), np.float32(0.0), np.float32(0.1148), np.float32(0.639), np.float32(0.4662), np.float32(0.0075), np.float32(0.7459), np.float32(0.7493), np.float32(0.7193), np.float32(0.8516), np.float32(0.5107), np.float32(0.4713), np.float32(0.6713), np.float32(0.6622), np.float32(0.0), np.float32(0.0)] +2025-10-29 07:26:31.616543: Epoch time: 543.32 s +2025-10-29 07:26:31.617838: Yayy! New best EMA pseudo Dice: 0.27799999713897705 +2025-10-29 07:26:35.720472: +2025-10-29 07:26:35.721918: Epoch 21 +2025-10-29 07:26:35.723158: Current learning rate: 0.00981 +2025-10-29 07:35:22.561846: train_loss 0.0394 +2025-10-29 07:35:22.568664: val_loss -0.0311 +2025-10-29 07:35:22.570142: Pseudo dice [np.float32(0.8625), np.float32(0.0), np.float32(0.0), np.float32(0.1944), np.float32(0.7475), np.float32(0.457), np.float32(0.4323), np.float32(0.7574), np.float32(0.7938), np.float32(0.7631), np.float32(0.8907), np.float32(0.5226), np.float32(0.4951), np.float32(0.6474), np.float32(0.5742), np.float32(0.0), np.float32(0.0)] +2025-10-29 07:35:22.572341: Epoch time: 526.85 s +2025-10-29 07:35:22.573389: Yayy! New best EMA pseudo Dice: 0.2980000078678131 +2025-10-29 07:35:26.838992: +2025-10-29 07:35:26.841002: Epoch 22 +2025-10-29 07:35:26.842953: Current learning rate: 0.0098 +2025-10-29 07:44:00.808764: train_loss 0.0122 +2025-10-29 07:44:00.817967: val_loss -0.0413 +2025-10-29 07:44:00.824272: Pseudo dice [np.float32(0.8524), np.float32(0.0), np.float32(0.0), np.float32(0.1951), np.float32(0.7435), np.float32(0.4861), np.float32(0.4979), np.float32(0.7753), np.float32(0.8381), np.float32(0.6899), np.float32(0.89), np.float32(0.5934), np.float32(0.4902), np.float32(0.6901), np.float32(0.7895), np.float32(0.0), np.float32(0.0)] +2025-10-29 07:44:00.825840: Epoch time: 513.97 s +2025-10-29 07:44:00.826992: Yayy! New best EMA pseudo Dice: 0.31839999556541443 +2025-10-29 07:44:05.002734: +2025-10-29 07:44:05.003928: Epoch 23 +2025-10-29 07:44:05.005026: Current learning rate: 0.00979 +2025-10-29 07:52:54.235689: train_loss 0.0086 +2025-10-29 07:52:54.244927: val_loss -0.077 +2025-10-29 07:52:54.248411: Pseudo dice [np.float32(0.8344), np.float32(0.0), np.float32(0.0), np.float32(0.2491), np.float32(0.7408), np.float32(0.4458), np.float32(0.4725), np.float32(0.7543), np.float32(0.8341), np.float32(0.8379), np.float32(0.8723), np.float32(0.6023), np.float32(0.4733), np.float32(0.7264), np.float32(0.8), np.float32(0.0), np.float32(0.0)] +2025-10-29 07:52:54.251014: Epoch time: 529.24 s +2025-10-29 07:52:54.253470: Yayy! New best EMA pseudo Dice: 0.33739998936653137 +2025-10-29 07:52:58.461985: +2025-10-29 07:52:58.464158: Epoch 24 +2025-10-29 07:52:58.465866: Current learning rate: 0.00978 +2025-10-29 08:01:45.854191: train_loss -0.0136 +2025-10-29 08:01:45.863508: val_loss -0.0462 +2025-10-29 08:01:45.865513: Pseudo dice [np.float32(0.7647), np.float32(0.0), np.float32(0.0), np.float32(0.3067), np.float32(0.7704), np.float32(0.5288), np.float32(0.4818), np.float32(0.7056), np.float32(0.7744), np.float32(0.7523), np.float32(0.9062), np.float32(0.581), np.float32(0.4467), np.float32(0.7392), np.float32(0.795), np.float32(0.0), np.float32(0.0)] +2025-10-29 08:01:45.867867: Epoch time: 527.4 s +2025-10-29 08:01:45.869495: Yayy! New best EMA pseudo Dice: 0.3540000021457672 +2025-10-29 08:01:50.040379: +2025-10-29 08:01:50.041954: Epoch 25 +2025-10-29 08:01:50.043296: Current learning rate: 0.00977 +2025-10-29 08:10:31.759777: train_loss -0.0294 +2025-10-29 08:10:31.764232: val_loss -0.1051 +2025-10-29 08:10:31.765652: Pseudo dice [np.float32(0.8698), np.float32(0.0), np.float32(0.0), np.float32(0.307), np.float32(0.741), np.float32(0.6015), np.float32(0.5024), np.float32(0.7858), np.float32(0.7565), np.float32(0.7795), np.float32(0.9295), np.float32(0.6402), np.float32(0.6073), np.float32(0.7438), np.float32(0.89), np.float32(0.0), np.float32(0.0)] +2025-10-29 08:10:31.766992: Epoch time: 521.72 s +2025-10-29 08:10:31.769237: Yayy! New best EMA pseudo Dice: 0.3723999857902527 +2025-10-29 08:10:36.096926: +2025-10-29 08:10:36.100909: Epoch 26 +2025-10-29 08:10:36.102471: Current learning rate: 0.00977 +2025-10-29 08:19:24.810320: train_loss -0.059 +2025-10-29 08:19:24.837362: val_loss -0.0966 +2025-10-29 08:19:24.840102: Pseudo dice [np.float32(0.894), np.float32(0.0), np.float32(0.0), np.float32(0.3638), np.float32(0.7819), np.float32(0.5112), np.float32(0.4455), np.float32(0.7367), np.float32(0.8628), np.float32(0.8359), np.float32(0.8863), np.float32(0.6278), np.float32(0.5251), np.float32(0.7131), np.float32(0.7702), np.float32(0.0), np.float32(0.0)] +2025-10-29 08:19:24.845593: Epoch time: 528.72 s +2025-10-29 08:19:24.852507: Yayy! New best EMA pseudo Dice: 0.3878999948501587 +2025-10-29 08:19:29.099430: +2025-10-29 08:19:29.100766: Epoch 27 +2025-10-29 08:19:29.102090: Current learning rate: 0.00976 +2025-10-29 08:28:32.637524: train_loss -0.0696 +2025-10-29 08:28:32.643763: val_loss -0.0572 +2025-10-29 08:28:32.645930: Pseudo dice [np.float32(0.846), np.float32(0.0), np.float32(0.0), np.float32(0.3789), np.float32(0.6204), np.float32(0.5041), np.float32(0.6992), np.float32(0.7331), np.float32(0.8629), np.float32(0.8313), np.float32(0.8737), np.float32(0.6231), np.float32(0.4745), np.float32(0.6911), np.float32(0.6731), np.float32(0.0), np.float32(0.0)] +2025-10-29 08:28:32.651010: Epoch time: 543.54 s +2025-10-29 08:28:32.652426: Yayy! New best EMA pseudo Dice: 0.4009000062942505 +2025-10-29 08:28:36.947737: +2025-10-29 08:28:36.952311: Epoch 28 +2025-10-29 08:28:36.953869: Current learning rate: 0.00975 +2025-10-29 08:37:29.655616: train_loss -0.0649 +2025-10-29 08:37:29.666552: val_loss -0.0855 +2025-10-29 08:37:29.667875: Pseudo dice [np.float32(0.8193), np.float32(0.0), np.float32(0.0), np.float32(0.2999), np.float32(0.766), np.float32(0.4913), np.float32(0.5395), np.float32(0.7434), np.float32(0.8524), np.float32(0.8125), np.float32(0.9056), np.float32(0.5606), np.float32(0.5478), np.float32(0.7356), np.float32(0.802), np.float32(0.0), np.float32(0.0)] +2025-10-29 08:37:29.669172: Epoch time: 532.72 s +2025-10-29 08:37:29.671374: Yayy! New best EMA pseudo Dice: 0.4129999876022339 +2025-10-29 08:37:33.801533: +2025-10-29 08:37:33.807163: Epoch 29 +2025-10-29 08:37:33.813146: Current learning rate: 0.00974 +2025-10-29 08:46:19.017793: train_loss -0.1027 +2025-10-29 08:46:19.024773: val_loss -0.1492 +2025-10-29 08:46:19.032246: Pseudo dice [np.float32(0.8805), np.float32(0.0), np.float32(0.0), np.float32(0.4012), np.float32(0.775), np.float32(0.5675), np.float32(0.6446), np.float32(0.799), np.float32(0.9014), np.float32(0.9133), np.float32(0.9092), np.float32(0.6902), np.float32(0.5754), np.float32(0.7052), np.float32(0.8594), np.float32(0.0), np.float32(0.0)] +2025-10-29 08:46:19.034434: Epoch time: 525.22 s +2025-10-29 08:46:19.036060: Yayy! New best EMA pseudo Dice: 0.42829999327659607 +2025-10-29 08:46:23.194476: +2025-10-29 08:46:23.195959: Epoch 30 +2025-10-29 08:46:23.197069: Current learning rate: 0.00973 +2025-10-29 08:55:14.171739: train_loss -0.0819 +2025-10-29 08:55:14.184366: val_loss -0.1334 +2025-10-29 08:55:14.185637: Pseudo dice [np.float32(0.8581), np.float32(0.0), np.float32(0.0), np.float32(0.4405), np.float32(0.7768), np.float32(0.5914), np.float32(0.5922), np.float32(0.7613), np.float32(0.8771), np.float32(0.8843), np.float32(0.9203), np.float32(0.665), np.float32(0.5703), np.float32(0.7574), np.float32(0.8002), np.float32(0.0), np.float32(0.0)] +2025-10-29 08:55:14.187058: Epoch time: 530.99 s +2025-10-29 08:55:14.188100: Yayy! New best EMA pseudo Dice: 0.4413999915122986 +2025-10-29 08:55:18.225024: +2025-10-29 08:55:18.226667: Epoch 31 +2025-10-29 08:55:18.228855: Current learning rate: 0.00972 +2025-10-29 09:04:01.448131: train_loss -0.1391 +2025-10-29 09:04:01.500785: val_loss -0.136 +2025-10-29 09:04:01.502339: Pseudo dice [np.float32(0.8679), np.float32(0.0), np.float32(0.114), np.float32(0.4443), np.float32(0.749), np.float32(0.5482), np.float32(0.6109), np.float32(0.7409), np.float32(0.8991), np.float32(0.9), np.float32(0.8893), np.float32(0.7069), np.float32(0.6118), np.float32(0.7387), np.float32(0.8415), np.float32(0.0002), np.float32(0.0)] +2025-10-29 09:04:01.503888: Epoch time: 523.23 s +2025-10-29 09:04:01.505243: Yayy! New best EMA pseudo Dice: 0.45410001277923584 +2025-10-29 09:04:05.682816: +2025-10-29 09:04:05.685268: Epoch 32 +2025-10-29 09:04:05.686702: Current learning rate: 0.00971 +2025-10-29 09:13:08.003975: train_loss -0.1507 +2025-10-29 09:13:08.008773: val_loss -0.091 +2025-10-29 09:13:08.010458: Pseudo dice [np.float32(0.8774), np.float32(0.0), np.float32(0.3724), np.float32(0.346), np.float32(0.7672), np.float32(0.6309), np.float32(0.6933), np.float32(0.7566), np.float32(0.8306), np.float32(0.6932), np.float32(0.9233), np.float32(0.5899), np.float32(0.557), np.float32(0.7356), np.float32(0.8276), np.float32(0.0), np.float32(0.0)] +2025-10-29 09:13:08.011981: Epoch time: 542.32 s +2025-10-29 09:13:08.013081: Yayy! New best EMA pseudo Dice: 0.4650999903678894 +2025-10-29 09:13:12.126510: +2025-10-29 09:13:12.130656: Epoch 33 +2025-10-29 09:13:12.132406: Current learning rate: 0.0097 +2025-10-29 09:22:00.079663: train_loss -0.1404 +2025-10-29 09:22:00.115003: val_loss -0.1739 +2025-10-29 09:22:00.116395: Pseudo dice [np.float32(0.8595), np.float32(0.0133), np.float32(0.5282), np.float32(0.4575), np.float32(0.7723), np.float32(0.6102), np.float32(0.5968), np.float32(0.8191), np.float32(0.8765), np.float32(0.8286), np.float32(0.892), np.float32(0.6827), np.float32(0.6136), np.float32(0.7293), np.float32(0.8634), np.float32(0.0), np.float32(0.0)] +2025-10-29 09:22:00.119317: Epoch time: 527.96 s +2025-10-29 09:22:00.122125: Yayy! New best EMA pseudo Dice: 0.478300005197525 +2025-10-29 09:22:04.417890: +2025-10-29 09:22:04.419430: Epoch 34 +2025-10-29 09:22:04.420676: Current learning rate: 0.00969 +2025-10-29 09:30:49.815622: train_loss -0.1253 +2025-10-29 09:30:49.832469: val_loss -0.1982 +2025-10-29 09:30:49.834542: Pseudo dice [np.float32(0.8813), np.float32(0.434), np.float32(0.541), np.float32(0.4507), np.float32(0.7881), np.float32(0.6517), np.float32(0.592), np.float32(0.845), np.float32(0.8721), np.float32(0.8703), np.float32(0.9023), np.float32(0.7104), np.float32(0.6023), np.float32(0.7456), np.float32(0.8527), np.float32(0.0014), np.float32(0.0)] +2025-10-29 09:30:49.836520: Epoch time: 525.4 s +2025-10-29 09:30:49.838358: Yayy! New best EMA pseudo Dice: 0.4936000108718872 +2025-10-29 09:30:54.273261: +2025-10-29 09:30:54.274934: Epoch 35 +2025-10-29 09:30:54.277098: Current learning rate: 0.00968 +2025-10-29 09:39:48.317779: train_loss -0.1645 +2025-10-29 09:39:48.338661: val_loss -0.2272 +2025-10-29 09:39:48.341201: Pseudo dice [np.float32(0.9044), np.float32(0.4085), np.float32(0.5627), np.float32(0.4977), np.float32(0.7911), np.float32(0.5879), np.float32(0.7285), np.float32(0.8189), np.float32(0.9061), np.float32(0.9303), np.float32(0.9256), np.float32(0.7208), np.float32(0.6251), np.float32(0.7003), np.float32(0.8656), np.float32(0.0), np.float32(0.0)] +2025-10-29 09:39:48.351712: Epoch time: 534.05 s +2025-10-29 09:39:48.353358: Yayy! New best EMA pseudo Dice: 0.5088000297546387 +2025-10-29 09:39:52.742464: +2025-10-29 09:39:52.744024: Epoch 36 +2025-10-29 09:39:52.745249: Current learning rate: 0.00968 +2025-10-29 09:48:40.730385: train_loss -0.1638 +2025-10-29 09:48:40.743319: val_loss -0.1951 +2025-10-29 09:48:40.744692: Pseudo dice [np.float32(0.8652), np.float32(0.5393), np.float32(0.5534), np.float32(0.4807), np.float32(0.7985), np.float32(0.6318), np.float32(0.7573), np.float32(0.779), np.float32(0.917), np.float32(0.9333), np.float32(0.9286), np.float32(0.6876), np.float32(0.5527), np.float32(0.7245), np.float32(0.8272), np.float32(0.0), np.float32(0.0)] +2025-10-29 09:48:40.746520: Epoch time: 527.99 s +2025-10-29 09:48:40.748481: Yayy! New best EMA pseudo Dice: 0.5224999785423279 +2025-10-29 09:48:44.963738: +2025-10-29 09:48:44.965790: Epoch 37 +2025-10-29 09:48:44.967625: Current learning rate: 0.00967 +2025-10-29 09:57:23.424215: train_loss -0.165 +2025-10-29 09:57:23.428993: val_loss -0.1717 +2025-10-29 09:57:23.430157: Pseudo dice [np.float32(0.862), np.float32(0.5459), np.float32(0.5464), np.float32(0.403), np.float32(0.7478), np.float32(0.6115), np.float32(0.6353), np.float32(0.769), np.float32(0.8994), np.float32(0.8573), np.float32(0.9105), np.float32(0.6986), np.float32(0.5505), np.float32(0.7854), np.float32(0.8501), np.float32(0.0), np.float32(0.0)] +2025-10-29 09:57:23.431531: Epoch time: 518.46 s +2025-10-29 09:57:23.432794: Yayy! New best EMA pseudo Dice: 0.5329999923706055 +2025-10-29 09:57:27.615157: +2025-10-29 09:57:27.620175: Epoch 38 +2025-10-29 09:57:27.622599: Current learning rate: 0.00966 +2025-10-29 10:06:07.555806: train_loss -0.1917 +2025-10-29 10:06:07.562101: val_loss -0.1869 +2025-10-29 10:06:07.566441: Pseudo dice [np.float32(0.8866), np.float32(0.4507), np.float32(0.5443), np.float32(0.431), np.float32(0.7881), np.float32(0.6273), np.float32(0.679), np.float32(0.8253), np.float32(0.8887), np.float32(0.8686), np.float32(0.9071), np.float32(0.6631), np.float32(0.5709), np.float32(0.7675), np.float32(0.6696), np.float32(0.0), np.float32(0.0)] +2025-10-29 10:06:07.568517: Epoch time: 519.94 s +2025-10-29 10:06:07.571340: Yayy! New best EMA pseudo Dice: 0.5418999791145325 +2025-10-29 10:06:12.516424: +2025-10-29 10:06:12.518322: Epoch 39 +2025-10-29 10:06:12.520138: Current learning rate: 0.00965 +2025-10-29 10:15:03.877784: train_loss -0.2201 +2025-10-29 10:15:03.893015: val_loss -0.2007 +2025-10-29 10:15:03.895715: Pseudo dice [np.float32(0.8684), np.float32(0.5451), np.float32(0.5423), np.float32(0.4026), np.float32(0.7643), np.float32(0.5909), np.float32(0.7251), np.float32(0.7912), np.float32(0.9063), np.float32(0.903), np.float32(0.8791), np.float32(0.6992), np.float32(0.5964), np.float32(0.7758), np.float32(0.8626), np.float32(0.0089), np.float32(0.0)] +2025-10-29 10:15:03.897240: Epoch time: 531.37 s +2025-10-29 10:15:03.899149: Yayy! New best EMA pseudo Dice: 0.5515999794006348 +2025-10-29 10:15:08.198357: +2025-10-29 10:15:08.199684: Epoch 40 +2025-10-29 10:15:08.202160: Current learning rate: 0.00964 +2025-10-29 10:23:56.285005: train_loss -0.1865 +2025-10-29 10:23:56.290270: val_loss -0.2548 +2025-10-29 10:23:56.291510: Pseudo dice [np.float32(0.8521), np.float32(0.6408), np.float32(0.5168), np.float32(0.4504), np.float32(0.8124), np.float32(0.6148), np.float32(0.7576), np.float32(0.8208), np.float32(0.88), np.float32(0.8713), np.float32(0.9397), np.float32(0.6747), np.float32(0.5749), np.float32(0.7657), np.float32(0.9007), np.float32(0.0), np.float32(0.0)] +2025-10-29 10:23:56.292673: Epoch time: 528.09 s +2025-10-29 10:23:56.293747: Yayy! New best EMA pseudo Dice: 0.5616000294685364 +2025-10-29 10:24:00.598752: +2025-10-29 10:24:00.600494: Epoch 41 +2025-10-29 10:24:00.602978: Current learning rate: 0.00963 +2025-10-29 10:32:45.474102: train_loss -0.1727 +2025-10-29 10:32:45.483559: val_loss -0.2157 +2025-10-29 10:32:45.486233: Pseudo dice [np.float32(0.8922), np.float32(0.5806), np.float32(0.4855), np.float32(0.428), np.float32(0.7984), np.float32(0.5965), np.float32(0.6652), np.float32(0.8145), np.float32(0.9211), np.float32(0.8401), np.float32(0.92), np.float32(0.7129), np.float32(0.6091), np.float32(0.7569), np.float32(0.8546), np.float32(1e-04), np.float32(0.0)] +2025-10-29 10:32:45.488921: Epoch time: 524.88 s +2025-10-29 10:32:45.491608: Yayy! New best EMA pseudo Dice: 0.5694000124931335 +2025-10-29 10:32:49.697821: +2025-10-29 10:32:49.699153: Epoch 42 +2025-10-29 10:32:49.700761: Current learning rate: 0.00962 +2025-10-29 10:41:34.510113: train_loss -0.197 +2025-10-29 10:41:34.528741: val_loss -0.2245 +2025-10-29 10:41:34.541130: Pseudo dice [np.float32(0.8643), np.float32(0.5761), np.float32(0.4965), np.float32(0.4608), np.float32(0.8032), np.float32(0.591), np.float32(0.5917), np.float32(0.7526), np.float32(0.8833), np.float32(0.9008), np.float32(0.9336), np.float32(0.6729), np.float32(0.5988), np.float32(0.7837), np.float32(0.8942), np.float32(0.0033), np.float32(0.0)] +2025-10-29 10:41:34.542965: Epoch time: 524.82 s +2025-10-29 10:41:34.544722: Yayy! New best EMA pseudo Dice: 0.5759999752044678 +2025-10-29 10:41:38.937792: +2025-10-29 10:41:38.939291: Epoch 43 +2025-10-29 10:41:38.940692: Current learning rate: 0.00961 +2025-10-29 10:50:18.027768: train_loss -0.1953 +2025-10-29 10:50:18.046096: val_loss -0.241 +2025-10-29 10:50:18.047696: Pseudo dice [np.float32(0.8999), np.float32(0.5015), np.float32(0.5772), np.float32(0.5098), np.float32(0.8039), np.float32(0.6232), np.float32(0.6493), np.float32(0.805), np.float32(0.8938), np.float32(0.9), np.float32(0.8949), np.float32(0.7007), np.float32(0.6534), np.float32(0.773), np.float32(0.8964), np.float32(0.0271), np.float32(0.0)] +2025-10-29 10:50:18.048889: Epoch time: 519.09 s +2025-10-29 10:50:18.050130: Yayy! New best EMA pseudo Dice: 0.5838000178337097 +2025-10-29 10:50:22.301247: +2025-10-29 10:50:22.303463: Epoch 44 +2025-10-29 10:50:22.304819: Current learning rate: 0.0096 +2025-10-29 10:59:09.891651: train_loss -0.2161 +2025-10-29 10:59:09.913043: val_loss -0.1892 +2025-10-29 10:59:09.917042: Pseudo dice [np.float32(0.8825), np.float32(0.6071), np.float32(0.5569), np.float32(0.4173), np.float32(0.7139), np.float32(0.6333), np.float32(0.7472), np.float32(0.823), np.float32(0.823), np.float32(0.7606), np.float32(0.9181), np.float32(0.7145), np.float32(0.5956), np.float32(0.7707), np.float32(0.7598), np.float32(0.066), np.float32(0.0)] +2025-10-29 10:59:09.920224: Epoch time: 527.59 s +2025-10-29 10:59:09.924033: Yayy! New best EMA pseudo Dice: 0.5888000130653381 +2025-10-29 10:59:14.215178: +2025-10-29 10:59:14.226440: Epoch 45 +2025-10-29 10:59:14.237606: Current learning rate: 0.00959 +2025-10-29 11:08:06.815926: train_loss -0.2358 +2025-10-29 11:08:06.832159: val_loss -0.2395 +2025-10-29 11:08:06.835497: Pseudo dice [np.float32(0.8826), np.float32(0.5074), np.float32(0.4947), np.float32(0.4653), np.float32(0.7714), np.float32(0.6644), np.float32(0.7105), np.float32(0.8463), np.float32(0.8572), np.float32(0.8585), np.float32(0.9319), np.float32(0.6813), np.float32(0.6048), np.float32(0.7955), np.float32(0.8102), np.float32(0.0774), np.float32(0.0)] +2025-10-29 11:08:06.839272: Epoch time: 532.6 s +2025-10-29 11:08:06.844523: Yayy! New best EMA pseudo Dice: 0.5943999886512756 +2025-10-29 11:08:11.114437: +2025-10-29 11:08:11.115724: Epoch 46 +2025-10-29 11:08:11.117261: Current learning rate: 0.00959 +2025-10-29 11:16:44.904257: train_loss -0.2333 +2025-10-29 11:16:44.922770: val_loss -0.2806 +2025-10-29 11:16:44.924329: Pseudo dice [np.float32(0.8983), np.float32(0.6138), np.float32(0.6192), np.float32(0.4473), np.float32(0.7667), np.float32(0.657), np.float32(0.6876), np.float32(0.8381), np.float32(0.9558), np.float32(0.9464), np.float32(0.9336), np.float32(0.7245), np.float32(0.6152), np.float32(0.7947), np.float32(0.9211), np.float32(0.1721), np.float32(0.0)] +2025-10-29 11:16:44.925778: Epoch time: 513.79 s +2025-10-29 11:16:44.927020: Yayy! New best EMA pseudo Dice: 0.6032000184059143 +2025-10-29 11:16:49.212636: +2025-10-29 11:16:49.214002: Epoch 47 +2025-10-29 11:16:49.215281: Current learning rate: 0.00958 +2025-10-29 11:25:24.510674: train_loss -0.2258 +2025-10-29 11:25:24.527845: val_loss -0.2382 +2025-10-29 11:25:24.529231: Pseudo dice [np.float32(0.8968), np.float32(0.5723), np.float32(0.6095), np.float32(0.4582), np.float32(0.7887), np.float32(0.6722), np.float32(0.6917), np.float32(0.8031), np.float32(0.874), np.float32(0.8487), np.float32(0.9091), np.float32(0.7466), np.float32(0.6289), np.float32(0.7846), np.float32(0.7062), np.float32(0.1711), np.float32(0.0)] +2025-10-29 11:25:24.530438: Epoch time: 515.3 s +2025-10-29 11:25:24.531636: Yayy! New best EMA pseudo Dice: 0.6085000038146973 +2025-10-29 11:25:28.779349: +2025-10-29 11:25:28.780914: Epoch 48 +2025-10-29 11:25:28.782508: Current learning rate: 0.00957 +2025-10-29 11:34:13.087426: train_loss -0.2174 +2025-10-29 11:34:13.100395: val_loss -0.2853 +2025-10-29 11:34:13.102972: Pseudo dice [np.float32(0.8787), np.float32(0.6258), np.float32(0.579), np.float32(0.4879), np.float32(0.8409), np.float32(0.6602), np.float32(0.7142), np.float32(0.8083), np.float32(0.9194), np.float32(0.9168), np.float32(0.9106), np.float32(0.739), np.float32(0.6453), np.float32(0.8041), np.float32(0.8899), np.float32(0.2693), np.float32(0.0)] +2025-10-29 11:34:13.108066: Epoch time: 524.32 s +2025-10-29 11:34:13.110029: Yayy! New best EMA pseudo Dice: 0.6164000034332275 +2025-10-29 11:34:17.338576: +2025-10-29 11:34:17.339780: Epoch 49 +2025-10-29 11:34:17.340976: Current learning rate: 0.00956 +2025-10-29 11:43:18.500700: train_loss -0.256 +2025-10-29 11:43:18.534252: val_loss -0.257 +2025-10-29 11:43:18.535544: Pseudo dice [np.float32(0.8527), np.float32(0.5807), np.float32(0.6219), np.float32(0.4709), np.float32(0.8197), np.float32(0.66), np.float32(0.7889), np.float32(0.8025), np.float32(0.9398), np.float32(0.9253), np.float32(0.9377), np.float32(0.7022), np.float32(0.6037), np.float32(0.8041), np.float32(0.9019), np.float32(0.2044), np.float32(0.0)] +2025-10-29 11:43:18.536692: Epoch time: 541.17 s +2025-10-29 11:43:20.657034: Yayy! New best EMA pseudo Dice: 0.6230999827384949 +2025-10-29 11:43:24.834729: +2025-10-29 11:43:24.838241: Epoch 50 +2025-10-29 11:43:24.839552: Current learning rate: 0.00955 +2025-10-29 11:52:29.318990: train_loss -0.2713 +2025-10-29 11:52:29.338447: val_loss -0.2352 +2025-10-29 11:52:29.340390: Pseudo dice [np.float32(0.9068), np.float32(0.6056), np.float32(0.6192), np.float32(0.3682), np.float32(0.7841), np.float32(0.6391), np.float32(0.6449), np.float32(0.8312), np.float32(0.9293), np.float32(0.9024), np.float32(0.8988), np.float32(0.7303), np.float32(0.5399), np.float32(0.7982), np.float32(0.8476), np.float32(0.233), np.float32(0.0)] +2025-10-29 11:52:29.346588: Epoch time: 544.49 s +2025-10-29 11:52:29.352541: Yayy! New best EMA pseudo Dice: 0.6270999908447266 +2025-10-29 11:52:33.497542: +2025-10-29 11:52:33.499015: Epoch 51 +2025-10-29 11:52:33.508000: Current learning rate: 0.00954 +2025-10-29 12:01:18.084981: train_loss -0.2621 +2025-10-29 12:01:18.100200: val_loss -0.2571 +2025-10-29 12:01:18.101353: Pseudo dice [np.float32(0.8872), np.float32(0.5653), np.float32(0.4846), np.float32(0.4744), np.float32(0.8025), np.float32(0.6853), np.float32(0.7676), np.float32(0.8203), np.float32(0.8959), np.float32(0.9061), np.float32(0.9357), np.float32(0.7449), np.float32(0.5977), np.float32(0.8048), np.float32(0.8767), np.float32(0.254), np.float32(0.0)] +2025-10-29 12:01:18.102412: Epoch time: 524.59 s +2025-10-29 12:01:18.103467: Yayy! New best EMA pseudo Dice: 0.632099986076355 +2025-10-29 12:01:22.310417: +2025-10-29 12:01:22.313677: Epoch 52 +2025-10-29 12:01:22.318379: Current learning rate: 0.00953 +2025-10-29 12:10:08.576267: train_loss -0.26 +2025-10-29 12:10:08.581534: val_loss -0.3214 +2025-10-29 12:10:08.582856: Pseudo dice [np.float32(0.8959), np.float32(0.6258), np.float32(0.604), np.float32(0.4723), np.float32(0.821), np.float32(0.6871), np.float32(0.806), np.float32(0.8039), np.float32(0.9238), np.float32(0.937), np.float32(0.9492), np.float32(0.7385), np.float32(0.6369), np.float32(0.8118), np.float32(0.9332), np.float32(0.2649), np.float32(0.0)] +2025-10-29 12:10:08.584305: Epoch time: 526.27 s +2025-10-29 12:10:08.585468: Yayy! New best EMA pseudo Dice: 0.6389999985694885 +2025-10-29 12:10:12.825648: +2025-10-29 12:10:12.831434: Epoch 53 +2025-10-29 12:10:12.834461: Current learning rate: 0.00952 +2025-10-29 12:19:02.352728: train_loss -0.2734 +2025-10-29 12:19:02.360040: val_loss -0.2634 +2025-10-29 12:19:02.362068: Pseudo dice [np.float32(0.8945), np.float32(0.5126), np.float32(0.6336), np.float32(0.4906), np.float32(0.7953), np.float32(0.6684), np.float32(0.674), np.float32(0.8213), np.float32(0.922), np.float32(0.9254), np.float32(0.9428), np.float32(0.7713), np.float32(0.6653), np.float32(0.7987), np.float32(0.9104), np.float32(0.2368), np.float32(0.0)] +2025-10-29 12:19:02.363494: Epoch time: 529.53 s +2025-10-29 12:19:02.366823: Yayy! New best EMA pseudo Dice: 0.6437000036239624 +2025-10-29 12:19:06.888357: +2025-10-29 12:19:06.890995: Epoch 54 +2025-10-29 12:19:06.892560: Current learning rate: 0.00951 +2025-10-29 12:28:01.378299: train_loss -0.2705 +2025-10-29 12:28:01.386794: val_loss -0.2435 +2025-10-29 12:28:01.388927: Pseudo dice [np.float32(0.8977), np.float32(0.6101), np.float32(0.574), np.float32(0.4392), np.float32(0.7833), np.float32(0.6334), np.float32(0.6497), np.float32(0.8141), np.float32(0.9053), np.float32(0.8928), np.float32(0.9458), np.float32(0.6906), np.float32(0.6812), np.float32(0.734), np.float32(0.8977), np.float32(0.1859), np.float32(0.0)] +2025-10-29 12:28:01.390381: Epoch time: 534.49 s +2025-10-29 12:28:01.391684: Yayy! New best EMA pseudo Dice: 0.6460000276565552 +2025-10-29 12:28:06.818235: +2025-10-29 12:28:06.820678: Epoch 55 +2025-10-29 12:28:06.823077: Current learning rate: 0.0095 +2025-10-29 12:36:45.076768: train_loss -0.2649 +2025-10-29 12:36:45.081703: val_loss -0.3237 +2025-10-29 12:36:45.082959: Pseudo dice [np.float32(0.9132), np.float32(0.654), np.float32(0.6325), np.float32(0.5038), np.float32(0.7826), np.float32(0.7194), np.float32(0.8093), np.float32(0.8368), np.float32(0.917), np.float32(0.9163), np.float32(0.9436), np.float32(0.7389), np.float32(0.646), np.float32(0.7958), np.float32(0.9421), np.float32(0.2295), np.float32(0.0)] +2025-10-29 12:36:45.084532: Epoch time: 518.26 s +2025-10-29 12:36:45.085798: Yayy! New best EMA pseudo Dice: 0.6518999934196472 +2025-10-29 12:36:49.321380: +2025-10-29 12:36:49.322727: Epoch 56 +2025-10-29 12:36:49.323890: Current learning rate: 0.00949 +2025-10-29 12:45:43.624058: train_loss -0.2814 +2025-10-29 12:45:43.629333: val_loss -0.3312 +2025-10-29 12:45:43.630547: Pseudo dice [np.float32(0.9081), np.float32(0.6747), np.float32(0.6497), np.float32(0.5327), np.float32(0.8322), np.float32(0.6675), np.float32(0.7903), np.float32(0.8403), np.float32(0.9705), np.float32(0.9725), np.float32(0.9486), np.float32(0.7586), np.float32(0.6525), np.float32(0.8324), np.float32(0.8428), np.float32(0.2723), np.float32(0.0)] +2025-10-29 12:45:43.633223: Epoch time: 534.31 s +2025-10-29 12:45:43.634321: Yayy! New best EMA pseudo Dice: 0.6581000089645386 +2025-10-29 12:45:47.723068: +2025-10-29 12:45:47.724275: Epoch 57 +2025-10-29 12:45:47.725427: Current learning rate: 0.00949 +2025-10-29 12:54:46.907606: train_loss -0.2924 +2025-10-29 12:54:46.912872: val_loss -0.3351 +2025-10-29 12:54:46.914575: Pseudo dice [np.float32(0.9026), np.float32(0.6469), np.float32(0.6236), np.float32(0.4947), np.float32(0.8085), np.float32(0.7168), np.float32(0.7296), np.float32(0.8423), np.float32(0.9594), np.float32(0.9544), np.float32(0.9437), np.float32(0.7675), np.float32(0.6704), np.float32(0.8195), np.float32(0.9351), np.float32(0.3119), np.float32(0.0)] +2025-10-29 12:54:46.916414: Epoch time: 539.19 s +2025-10-29 12:54:46.917473: Yayy! New best EMA pseudo Dice: 0.6636000275611877 +2025-10-29 12:54:51.056889: +2025-10-29 12:54:51.057998: Epoch 58 +2025-10-29 12:54:51.060214: Current learning rate: 0.00948 +2025-10-29 13:03:39.656558: train_loss -0.2576 +2025-10-29 13:03:39.662963: val_loss -0.3314 +2025-10-29 13:03:39.665535: Pseudo dice [np.float32(0.9055), np.float32(0.6265), np.float32(0.6509), np.float32(0.4616), np.float32(0.8081), np.float32(0.6792), np.float32(0.7958), np.float32(0.8287), np.float32(0.9651), np.float32(0.9489), np.float32(0.941), np.float32(0.7565), np.float32(0.6679), np.float32(0.7925), np.float32(0.9453), np.float32(0.3187), np.float32(0.0)] +2025-10-29 13:03:39.667672: Epoch time: 528.6 s +2025-10-29 13:03:39.669122: Yayy! New best EMA pseudo Dice: 0.66839998960495 +2025-10-29 13:03:54.324859: +2025-10-29 13:03:54.326273: Epoch 59 +2025-10-29 13:03:54.327330: Current learning rate: 0.00947 +2025-10-29 13:12:36.362129: train_loss -0.2882 +2025-10-29 13:12:36.367159: val_loss -0.3193 +2025-10-29 13:12:36.368268: Pseudo dice [np.float32(0.8847), np.float32(0.6633), np.float32(0.6457), np.float32(0.4976), np.float32(0.8326), np.float32(0.7297), np.float32(0.7249), np.float32(0.8285), np.float32(0.9332), np.float32(0.9499), np.float32(0.9504), np.float32(0.777), np.float32(0.6179), np.float32(0.8165), np.float32(0.8999), np.float32(0.2941), np.float32(0.0)] +2025-10-29 13:12:36.369278: Epoch time: 522.04 s +2025-10-29 13:12:36.370243: Yayy! New best EMA pseudo Dice: 0.6723999977111816 +2025-10-29 13:12:40.431355: +2025-10-29 13:12:40.432670: Epoch 60 +2025-10-29 13:12:40.433871: Current learning rate: 0.00946 +2025-10-29 13:21:19.698130: train_loss -0.2899 +2025-10-29 13:21:19.704296: val_loss -0.3135 +2025-10-29 13:21:19.705611: Pseudo dice [np.float32(0.9043), np.float32(0.6457), np.float32(0.6359), np.float32(0.5347), np.float32(0.8098), np.float32(0.7019), np.float32(0.7606), np.float32(0.8542), np.float32(0.9444), np.float32(0.9323), np.float32(0.9475), np.float32(0.7488), np.float32(0.6642), np.float32(0.7892), np.float32(0.9307), np.float32(0.3426), np.float32(0.0)] +2025-10-29 13:21:19.706744: Epoch time: 519.27 s +2025-10-29 13:21:19.711530: Yayy! New best EMA pseudo Dice: 0.6765999794006348 +2025-10-29 13:21:23.916598: +2025-10-29 13:21:23.917954: Epoch 61 +2025-10-29 13:21:23.919029: Current learning rate: 0.00945 +2025-10-29 13:30:35.524777: train_loss -0.2458 +2025-10-29 13:30:35.535830: val_loss -0.2597 +2025-10-29 13:30:35.538177: Pseudo dice [np.float32(0.8695), np.float32(0.6181), np.float32(0.5991), np.float32(0.5129), np.float32(0.8034), np.float32(0.6783), np.float32(0.7201), np.float32(0.8051), np.float32(0.9566), np.float32(0.9527), np.float32(0.9497), np.float32(0.7355), np.float32(0.5589), np.float32(0.7899), np.float32(0.9076), np.float32(0.2132), np.float32(0.0)] +2025-10-29 13:30:35.540195: Epoch time: 551.61 s +2025-10-29 13:30:35.541893: Yayy! New best EMA pseudo Dice: 0.6776000261306763 +2025-10-29 13:30:39.591045: +2025-10-29 13:30:39.593200: Epoch 62 +2025-10-29 13:30:39.594436: Current learning rate: 0.00944 +2025-10-29 13:39:32.585530: train_loss -0.2386 +2025-10-29 13:39:32.591819: val_loss -0.2815 +2025-10-29 13:39:32.593349: Pseudo dice [np.float32(0.8706), np.float32(0.6719), np.float32(0.6382), np.float32(0.4753), np.float32(0.8063), np.float32(0.7319), np.float32(0.7587), np.float32(0.8417), np.float32(0.9129), np.float32(0.9305), np.float32(0.9426), np.float32(0.7616), np.float32(0.5864), np.float32(0.8047), np.float32(0.8625), np.float32(0.2358), np.float32(0.0)] +2025-10-29 13:39:32.595313: Epoch time: 533.0 s +2025-10-29 13:39:32.596444: Yayy! New best EMA pseudo Dice: 0.6794999837875366 +2025-10-29 13:39:36.790459: +2025-10-29 13:39:36.792067: Epoch 63 +2025-10-29 13:39:36.793509: Current learning rate: 0.00943 +2025-10-29 13:48:32.341422: train_loss -0.2696 +2025-10-29 13:48:32.346320: val_loss -0.2799 +2025-10-29 13:48:32.347832: Pseudo dice [np.float32(0.8997), np.float32(0.5659), np.float32(0.6089), np.float32(0.4879), np.float32(0.7932), np.float32(0.7125), np.float32(0.7693), np.float32(0.8581), np.float32(0.8419), np.float32(0.8885), np.float32(0.9456), np.float32(0.751), np.float32(0.6702), np.float32(0.7983), np.float32(0.8508), np.float32(0.2297), np.float32(0.0225)] +2025-10-29 13:48:32.349177: Epoch time: 535.55 s +2025-10-29 13:48:32.350091: Yayy! New best EMA pseudo Dice: 0.6802999973297119 +2025-10-29 13:48:36.475362: +2025-10-29 13:48:36.477042: Epoch 64 +2025-10-29 13:48:36.482427: Current learning rate: 0.00942 +2025-10-29 13:57:36.813189: train_loss -0.2641 +2025-10-29 13:57:36.826064: val_loss -0.2576 +2025-10-29 13:57:36.827432: Pseudo dice [np.float32(0.8995), np.float32(0.5817), np.float32(0.596), np.float32(0.551), np.float32(0.8184), np.float32(0.6616), np.float32(0.6951), np.float32(0.8107), np.float32(0.8487), np.float32(0.8391), np.float32(0.921), np.float32(0.7522), np.float32(0.6231), np.float32(0.7863), np.float32(0.8008), np.float32(0.1604), np.float32(0.0267)] +2025-10-29 13:57:36.829976: Epoch time: 540.35 s +2025-10-29 13:57:38.791804: +2025-10-29 13:57:38.794044: Epoch 65 +2025-10-29 13:57:38.795654: Current learning rate: 0.00941 +2025-10-29 14:06:38.819979: train_loss -0.2678 +2025-10-29 14:06:38.830275: val_loss -0.2849 +2025-10-29 14:06:38.832191: Pseudo dice [np.float32(0.9043), np.float32(0.6342), np.float32(0.6442), np.float32(0.4622), np.float32(0.8003), np.float32(0.6691), np.float32(0.7353), np.float32(0.8313), np.float32(0.9141), np.float32(0.9185), np.float32(0.9495), np.float32(0.7927), np.float32(0.6419), np.float32(0.8042), np.float32(0.919), np.float32(0.0707), np.float32(0.0045)] +2025-10-29 14:06:38.844917: Epoch time: 540.03 s +2025-10-29 14:06:41.022284: +2025-10-29 14:06:41.023610: Epoch 66 +2025-10-29 14:06:41.025289: Current learning rate: 0.0094 +2025-10-29 14:15:25.725610: train_loss -0.2881 +2025-10-29 14:15:25.730553: val_loss -0.334 +2025-10-29 14:15:25.732003: Pseudo dice [np.float32(0.903), np.float32(0.641), np.float32(0.6311), np.float32(0.5282), np.float32(0.8377), np.float32(0.6654), np.float32(0.7707), np.float32(0.8316), np.float32(0.937), np.float32(0.929), np.float32(0.9381), np.float32(0.7744), np.float32(0.6876), np.float32(0.8152), np.float32(0.8994), np.float32(0.2945), np.float32(0.1842)] +2025-10-29 14:15:25.734028: Epoch time: 524.71 s +2025-10-29 14:15:25.735576: Yayy! New best EMA pseudo Dice: 0.6841999888420105 +2025-10-29 14:15:30.009237: +2025-10-29 14:15:30.011084: Epoch 67 +2025-10-29 14:15:30.012592: Current learning rate: 0.00939 +2025-10-29 14:24:21.772004: train_loss -0.3036 +2025-10-29 14:24:21.777762: val_loss -0.3575 +2025-10-29 14:24:21.779390: Pseudo dice [np.float32(0.8874), np.float32(0.6509), np.float32(0.6588), np.float32(0.5345), np.float32(0.8297), np.float32(0.6897), np.float32(0.7571), np.float32(0.8482), np.float32(0.9537), np.float32(0.9574), np.float32(0.9469), np.float32(0.7646), np.float32(0.6482), np.float32(0.8338), np.float32(0.9424), np.float32(0.2207), np.float32(0.0778)] +2025-10-29 14:24:21.781274: Epoch time: 531.77 s +2025-10-29 14:24:21.787093: Yayy! New best EMA pseudo Dice: 0.6876000165939331 +2025-10-29 14:24:26.114188: +2025-10-29 14:24:26.115815: Epoch 68 +2025-10-29 14:24:26.117226: Current learning rate: 0.00939 +2025-10-29 14:33:15.290647: train_loss -0.3105 +2025-10-29 14:33:15.295525: val_loss -0.3447 +2025-10-29 14:33:15.296830: Pseudo dice [np.float32(0.9211), np.float32(0.6416), np.float32(0.5791), np.float32(0.5501), np.float32(0.7935), np.float32(0.708), np.float32(0.8232), np.float32(0.8631), np.float32(0.9477), np.float32(0.9444), np.float32(0.9448), np.float32(0.7804), np.float32(0.6786), np.float32(0.7864), np.float32(0.9383), np.float32(0.3439), np.float32(0.2827)] +2025-10-29 14:33:15.297879: Epoch time: 529.18 s +2025-10-29 14:33:15.299048: Yayy! New best EMA pseudo Dice: 0.6924999952316284 +2025-10-29 14:33:19.937294: +2025-10-29 14:33:19.943502: Epoch 69 +2025-10-29 14:33:19.954950: Current learning rate: 0.00938 +2025-10-29 14:41:52.720079: train_loss -0.3024 +2025-10-29 14:41:52.726993: val_loss -0.3325 +2025-10-29 14:41:52.728407: Pseudo dice [np.float32(0.8824), np.float32(0.7042), np.float32(0.6314), np.float32(0.5551), np.float32(0.8007), np.float32(0.6812), np.float32(0.7713), np.float32(0.8294), np.float32(0.9686), np.float32(0.9656), np.float32(0.9458), np.float32(0.7734), np.float32(0.6951), np.float32(0.8033), np.float32(0.9132), np.float32(0.1587), np.float32(0.1992)] +2025-10-29 14:41:52.729847: Epoch time: 512.79 s +2025-10-29 14:41:52.730866: Yayy! New best EMA pseudo Dice: 0.6955000162124634 +2025-10-29 14:41:57.159971: +2025-10-29 14:41:57.164397: Epoch 70 +2025-10-29 14:41:57.173387: Current learning rate: 0.00937 +2025-10-29 14:50:58.515748: train_loss -0.2771 +2025-10-29 14:50:58.525461: val_loss -0.3259 +2025-10-29 14:50:58.526984: Pseudo dice [np.float32(0.8887), np.float32(0.6669), np.float32(0.6226), np.float32(0.5212), np.float32(0.8406), np.float32(0.7263), np.float32(0.7569), np.float32(0.8307), np.float32(0.8889), np.float32(0.8961), np.float32(0.9377), np.float32(0.757), np.float32(0.7128), np.float32(0.7955), np.float32(0.8527), np.float32(0.3892), np.float32(0.2708)] +2025-10-29 14:50:58.529058: Epoch time: 541.36 s +2025-10-29 14:50:58.530710: Yayy! New best EMA pseudo Dice: 0.6985999941825867 +2025-10-29 14:51:02.968031: +2025-10-29 14:51:02.970027: Epoch 71 +2025-10-29 14:51:02.976822: Current learning rate: 0.00936 +2025-10-29 15:00:02.600662: train_loss -0.2764 +2025-10-29 15:00:02.609427: val_loss -0.2972 +2025-10-29 15:00:02.610604: Pseudo dice [np.float32(0.8895), np.float32(0.6673), np.float32(0.6476), np.float32(0.4648), np.float32(0.7822), np.float32(0.7046), np.float32(0.7862), np.float32(0.8185), np.float32(0.9443), np.float32(0.9363), np.float32(0.9365), np.float32(0.7823), np.float32(0.6826), np.float32(0.8027), np.float32(0.8947), np.float32(0.133), np.float32(0.1314)] +2025-10-29 15:00:02.611675: Epoch time: 539.64 s +2025-10-29 15:00:02.613007: Yayy! New best EMA pseudo Dice: 0.699400007724762 +2025-10-29 15:00:07.067807: +2025-10-29 15:00:07.070876: Epoch 72 +2025-10-29 15:00:07.073099: Current learning rate: 0.00935 +2025-10-29 15:09:00.903921: train_loss -0.3029 +2025-10-29 15:09:00.911841: val_loss -0.3311 +2025-10-29 15:09:00.915186: Pseudo dice [np.float32(0.8831), np.float32(0.7388), np.float32(0.649), np.float32(0.5206), np.float32(0.8391), np.float32(0.7051), np.float32(0.7604), np.float32(0.8502), np.float32(0.9382), np.float32(0.9144), np.float32(0.9522), np.float32(0.7923), np.float32(0.653), np.float32(0.8128), np.float32(0.945), np.float32(0.2801), np.float32(0.2864)] +2025-10-29 15:09:00.917733: Epoch time: 533.85 s +2025-10-29 15:09:00.920647: Yayy! New best EMA pseudo Dice: 0.7031000256538391 +2025-10-29 15:09:05.197154: +2025-10-29 15:09:05.208746: Epoch 73 +2025-10-29 15:09:05.209862: Current learning rate: 0.00934 +2025-10-29 15:17:58.202483: train_loss -0.3004 +2025-10-29 15:17:58.210987: val_loss -0.3003 +2025-10-29 15:17:58.212532: Pseudo dice [np.float32(0.8777), np.float32(0.5867), np.float32(0.5859), np.float32(0.5108), np.float32(0.7684), np.float32(0.7025), np.float32(0.7523), np.float32(0.8297), np.float32(0.9477), np.float32(0.9291), np.float32(0.9445), np.float32(0.7999), np.float32(0.6671), np.float32(0.8051), np.float32(0.9239), np.float32(0.3243), np.float32(0.2175)] +2025-10-29 15:17:58.213643: Epoch time: 533.01 s +2025-10-29 15:17:58.214624: Yayy! New best EMA pseudo Dice: 0.7044000029563904 +2025-10-29 15:18:02.631426: +2025-10-29 15:18:02.632653: Epoch 74 +2025-10-29 15:18:02.633694: Current learning rate: 0.00933 +2025-10-29 15:26:38.854813: train_loss -0.3067 +2025-10-29 15:26:38.864346: val_loss -0.2893 +2025-10-29 15:26:38.868748: Pseudo dice [np.float32(0.8953), np.float32(0.6983), np.float32(0.677), np.float32(0.4214), np.float32(0.7482), np.float32(0.6876), np.float32(0.7856), np.float32(0.8359), np.float32(0.8739), np.float32(0.859), np.float32(0.9364), np.float32(0.7638), np.float32(0.7036), np.float32(0.7958), np.float32(0.8096), np.float32(0.2381), np.float32(0.2414)] +2025-10-29 15:26:38.871433: Epoch time: 516.23 s +2025-10-29 15:26:40.873645: +2025-10-29 15:26:40.876179: Epoch 75 +2025-10-29 15:26:40.878304: Current learning rate: 0.00932 +2025-10-29 15:35:17.563683: train_loss -0.3257 +2025-10-29 15:35:17.573723: val_loss -0.3562 +2025-10-29 15:35:17.575581: Pseudo dice [np.float32(0.8857), np.float32(0.6629), np.float32(0.6391), np.float32(0.5914), np.float32(0.8493), np.float32(0.7306), np.float32(0.8125), np.float32(0.8472), np.float32(0.954), np.float32(0.9611), np.float32(0.9426), np.float32(0.8068), np.float32(0.6875), np.float32(0.8546), np.float32(0.9067), np.float32(0.1797), np.float32(0.0827)] +2025-10-29 15:35:17.582357: Epoch time: 516.69 s +2025-10-29 15:35:17.587614: Yayy! New best EMA pseudo Dice: 0.7067999839782715 +2025-10-29 15:35:21.980514: +2025-10-29 15:35:21.985739: Epoch 76 +2025-10-29 15:35:21.987668: Current learning rate: 0.00931 +2025-10-29 15:44:17.289106: train_loss -0.3256 +2025-10-29 15:44:17.319617: val_loss -0.3555 +2025-10-29 15:44:17.321447: Pseudo dice [np.float32(0.8919), np.float32(0.6764), np.float32(0.6772), np.float32(0.5205), np.float32(0.8041), np.float32(0.7199), np.float32(0.8428), np.float32(0.8563), np.float32(0.9559), np.float32(0.9486), np.float32(0.9511), np.float32(0.7983), np.float32(0.6633), np.float32(0.8371), np.float32(0.9446), np.float32(0.3148), np.float32(0.2416)] +2025-10-29 15:44:17.323007: Epoch time: 535.31 s +2025-10-29 15:44:17.324508: Yayy! New best EMA pseudo Dice: 0.7105000019073486 +2025-10-29 15:44:21.600189: +2025-10-29 15:44:21.601542: Epoch 77 +2025-10-29 15:44:21.602915: Current learning rate: 0.0093 +2025-10-29 15:52:58.877858: train_loss -0.3122 +2025-10-29 15:52:58.883604: val_loss -0.3441 +2025-10-29 15:52:58.884822: Pseudo dice [np.float32(0.9125), np.float32(0.6839), np.float32(0.6878), np.float32(0.5353), np.float32(0.8376), np.float32(0.699), np.float32(0.7794), np.float32(0.845), np.float32(0.9449), np.float32(0.9351), np.float32(0.9484), np.float32(0.7751), np.float32(0.6954), np.float32(0.8438), np.float32(0.9338), np.float32(0.2332), np.float32(0.2034)] +2025-10-29 15:52:58.886149: Epoch time: 517.28 s +2025-10-29 15:52:58.887374: Yayy! New best EMA pseudo Dice: 0.7129999995231628 +2025-10-29 15:53:03.527863: +2025-10-29 15:53:03.529472: Epoch 78 +2025-10-29 15:53:03.531237: Current learning rate: 0.0093 +2025-10-29 16:02:23.375336: train_loss -0.3462 +2025-10-29 16:02:23.385568: val_loss -0.357 +2025-10-29 16:02:23.394920: Pseudo dice [np.float32(0.9135), np.float32(0.6361), np.float32(0.6243), np.float32(0.4918), np.float32(0.8009), np.float32(0.6988), np.float32(0.7591), np.float32(0.8488), np.float32(0.9429), np.float32(0.9279), np.float32(0.9492), np.float32(0.7836), np.float32(0.6643), np.float32(0.8263), np.float32(0.9352), np.float32(0.3762), np.float32(0.3051)] +2025-10-29 16:02:23.402450: Epoch time: 559.85 s +2025-10-29 16:02:23.406327: Yayy! New best EMA pseudo Dice: 0.7150999903678894 +2025-10-29 16:02:28.489254: +2025-10-29 16:02:28.491810: Epoch 79 +2025-10-29 16:02:28.494250: Current learning rate: 0.00929 +2025-10-29 16:11:21.577368: train_loss -0.3418 +2025-10-29 16:11:21.586116: val_loss -0.3252 +2025-10-29 16:11:21.587403: Pseudo dice [np.float32(0.9026), np.float32(0.6438), np.float32(0.571), np.float32(0.535), np.float32(0.8267), np.float32(0.6479), np.float32(0.8), np.float32(0.8404), np.float32(0.9387), np.float32(0.9148), np.float32(0.9389), np.float32(0.7588), np.float32(0.6407), np.float32(0.8065), np.float32(0.8844), np.float32(0.3168), np.float32(0.2532)] +2025-10-29 16:11:21.589911: Epoch time: 533.09 s +2025-10-29 16:11:21.591846: Yayy! New best EMA pseudo Dice: 0.715499997138977 +2025-10-29 16:11:25.717596: +2025-10-29 16:11:25.719174: Epoch 80 +2025-10-29 16:11:25.721741: Current learning rate: 0.00928 +2025-10-29 16:20:32.397382: train_loss -0.3173 +2025-10-29 16:20:32.404883: val_loss -0.3238 +2025-10-29 16:20:32.406353: Pseudo dice [np.float32(0.8986), np.float32(0.6682), np.float32(0.5942), np.float32(0.4943), np.float32(0.8003), np.float32(0.681), np.float32(0.7946), np.float32(0.8199), np.float32(0.9025), np.float32(0.9162), np.float32(0.9531), np.float32(0.7851), np.float32(0.6992), np.float32(0.8309), np.float32(0.8946), np.float32(0.2474), np.float32(0.2809)] +2025-10-29 16:20:32.407683: Epoch time: 546.68 s +2025-10-29 16:20:32.409750: Yayy! New best EMA pseudo Dice: 0.7160000205039978 +2025-10-29 16:20:36.678322: +2025-10-29 16:20:36.680138: Epoch 81 +2025-10-29 16:20:36.681200: Current learning rate: 0.00927 +2025-10-29 16:29:19.988324: train_loss -0.324 +2025-10-29 16:29:20.005239: val_loss -0.3404 +2025-10-29 16:29:20.006669: Pseudo dice [np.float32(0.9219), np.float32(0.3606), np.float32(0.6873), np.float32(0.521), np.float32(0.8479), np.float32(0.7244), np.float32(0.7648), np.float32(0.8674), np.float32(0.9303), np.float32(0.9293), np.float32(0.9417), np.float32(0.7612), np.float32(0.7165), np.float32(0.8415), np.float32(0.8834), np.float32(0.2316), np.float32(0.188)] +2025-10-29 16:29:20.008128: Epoch time: 523.31 s +2025-10-29 16:29:22.037365: +2025-10-29 16:29:22.039224: Epoch 82 +2025-10-29 16:29:22.040632: Current learning rate: 0.00926 +2025-10-29 16:38:03.241198: train_loss -0.3229 +2025-10-29 16:38:03.247145: val_loss -0.3204 +2025-10-29 16:38:03.248415: Pseudo dice [np.float32(0.8958), np.float32(0.6227), np.float32(0.625), np.float32(0.4917), np.float32(0.8574), np.float32(0.6635), np.float32(0.824), np.float32(0.817), np.float32(0.911), np.float32(0.9243), np.float32(0.9468), np.float32(0.7484), np.float32(0.6463), np.float32(0.782), np.float32(0.914), np.float32(0.3651), np.float32(0.4016)] +2025-10-29 16:38:03.249478: Epoch time: 521.21 s +2025-10-29 16:38:03.250595: Yayy! New best EMA pseudo Dice: 0.7172999978065491 +2025-10-29 16:38:07.378634: +2025-10-29 16:38:07.379977: Epoch 83 +2025-10-29 16:38:07.381229: Current learning rate: 0.00925 +2025-10-29 16:46:51.920161: train_loss -0.3164 +2025-10-29 16:46:51.927327: val_loss -0.3378 +2025-10-29 16:46:51.929747: Pseudo dice [np.float32(0.9098), np.float32(0.653), np.float32(0.6235), np.float32(0.5256), np.float32(0.8285), np.float32(0.6692), np.float32(0.8283), np.float32(0.8401), np.float32(0.9234), np.float32(0.9396), np.float32(0.9494), np.float32(0.7976), np.float32(0.6862), np.float32(0.8209), np.float32(0.9181), np.float32(0.3743), np.float32(0.2797)] +2025-10-29 16:46:51.931098: Epoch time: 524.55 s +2025-10-29 16:46:51.932370: Yayy! New best EMA pseudo Dice: 0.7195000052452087 +2025-10-29 16:46:57.217655: +2025-10-29 16:46:57.233397: Epoch 84 +2025-10-29 16:46:57.238325: Current learning rate: 0.00924 +2025-10-29 16:55:52.895601: train_loss -0.3523 +2025-10-29 16:55:52.904475: val_loss -0.3053 +2025-10-29 16:55:52.906390: Pseudo dice [np.float32(0.8868), np.float32(0.689), np.float32(0.6577), np.float32(0.5091), np.float32(0.7941), np.float32(0.6607), np.float32(0.7072), np.float32(0.8634), np.float32(0.8847), np.float32(0.9135), np.float32(0.9607), np.float32(0.7597), np.float32(0.691), np.float32(0.7742), np.float32(0.9128), np.float32(0.2529), np.float32(0.2398)] +2025-10-29 16:55:52.907633: Epoch time: 535.68 s +2025-10-29 16:55:54.990036: +2025-10-29 16:55:54.992837: Epoch 85 +2025-10-29 16:55:54.995233: Current learning rate: 0.00923 +2025-10-29 17:04:54.123177: train_loss -0.3024 +2025-10-29 17:04:54.137224: val_loss -0.3152 +2025-10-29 17:04:54.139003: Pseudo dice [np.float32(0.8798), np.float32(0.7088), np.float32(0.6332), np.float32(0.4994), np.float32(0.795), np.float32(0.7106), np.float32(0.6851), np.float32(0.8246), np.float32(0.9152), np.float32(0.9247), np.float32(0.924), np.float32(0.751), np.float32(0.6817), np.float32(0.7777), np.float32(0.9353), np.float32(0.331), np.float32(0.2635)] +2025-10-29 17:04:54.143148: Epoch time: 539.14 s +2025-10-29 17:04:56.350264: +2025-10-29 17:04:56.351817: Epoch 86 +2025-10-29 17:04:56.353329: Current learning rate: 0.00922 +2025-10-29 17:13:38.332692: train_loss -0.3051 +2025-10-29 17:13:38.337607: val_loss -0.2824 +2025-10-29 17:13:38.340651: Pseudo dice [np.float32(0.8749), np.float32(0.68), np.float32(0.6367), np.float32(0.4934), np.float32(0.7375), np.float32(0.6774), np.float32(0.723), np.float32(0.849), np.float32(0.9169), np.float32(0.9156), np.float32(0.9369), np.float32(0.7966), np.float32(0.6886), np.float32(0.7385), np.float32(0.9066), np.float32(0.3216), np.float32(0.2385)] +2025-10-29 17:13:38.342151: Epoch time: 521.99 s +2025-10-29 17:13:40.877263: +2025-10-29 17:13:40.878505: Epoch 87 +2025-10-29 17:13:40.879790: Current learning rate: 0.00921 +2025-10-29 17:22:35.138817: train_loss -0.3078 +2025-10-29 17:22:35.145194: val_loss -0.3501 +2025-10-29 17:22:35.147257: Pseudo dice [np.float32(0.9206), np.float32(0.6662), np.float32(0.695), np.float32(0.5603), np.float32(0.7844), np.float32(0.7239), np.float32(0.6567), np.float32(0.8505), np.float32(0.9398), np.float32(0.9258), np.float32(0.9499), np.float32(0.7917), np.float32(0.6938), np.float32(0.7994), np.float32(0.9305), np.float32(0.3259), np.float32(0.165)] +2025-10-29 17:22:35.148910: Epoch time: 534.27 s +2025-10-29 17:22:35.151467: Yayy! New best EMA pseudo Dice: 0.7196000218391418 +2025-10-29 17:22:39.567643: +2025-10-29 17:22:39.569628: Epoch 88 +2025-10-29 17:22:39.574490: Current learning rate: 0.0092 +2025-10-29 17:31:25.047832: train_loss -0.3237 +2025-10-29 17:31:25.054133: val_loss -0.379 +2025-10-29 17:31:25.055336: Pseudo dice [np.float32(0.8987), np.float32(0.7033), np.float32(0.6635), np.float32(0.5663), np.float32(0.8257), np.float32(0.7409), np.float32(0.817), np.float32(0.8546), np.float32(0.9518), np.float32(0.9461), np.float32(0.9609), np.float32(0.8141), np.float32(0.7249), np.float32(0.8272), np.float32(0.9148), np.float32(0.3425), np.float32(0.2404)] +2025-10-29 17:31:25.057176: Epoch time: 525.48 s +2025-10-29 17:31:25.058594: Yayy! New best EMA pseudo Dice: 0.7228999733924866 +2025-10-29 17:31:29.473799: +2025-10-29 17:31:29.479280: Epoch 89 +2025-10-29 17:31:29.480758: Current learning rate: 0.0092 +2025-10-29 17:40:09.764306: train_loss -0.3264 +2025-10-29 17:40:09.771491: val_loss -0.3843 +2025-10-29 17:40:09.772811: Pseudo dice [np.float32(0.9145), np.float32(0.6727), np.float32(0.6151), np.float32(0.6006), np.float32(0.8573), np.float32(0.7136), np.float32(0.8234), np.float32(0.856), np.float32(0.9169), np.float32(0.9399), np.float32(0.956), np.float32(0.7922), np.float32(0.7178), np.float32(0.8302), np.float32(0.9403), np.float32(0.2936), np.float32(0.2226)] +2025-10-29 17:40:09.774872: Epoch time: 520.3 s +2025-10-29 17:40:09.776604: Yayy! New best EMA pseudo Dice: 0.7250999808311462 +2025-10-29 17:40:13.932710: +2025-10-29 17:40:13.938800: Epoch 90 +2025-10-29 17:40:13.941289: Current learning rate: 0.00919 +2025-10-29 17:49:08.004256: train_loss -0.3443 +2025-10-29 17:49:08.012884: val_loss -0.3762 +2025-10-29 17:49:08.015004: Pseudo dice [np.float32(0.9275), np.float32(0.6879), np.float32(0.6733), np.float32(0.5843), np.float32(0.8316), np.float32(0.7313), np.float32(0.806), np.float32(0.8513), np.float32(0.9427), np.float32(0.9588), np.float32(0.9575), np.float32(0.8051), np.float32(0.6764), np.float32(0.8328), np.float32(0.9381), np.float32(0.2617), np.float32(0.2132)] +2025-10-29 17:49:08.017263: Epoch time: 534.08 s +2025-10-29 17:49:08.018534: Yayy! New best EMA pseudo Dice: 0.7271000146865845 +2025-10-29 17:49:12.261428: +2025-10-29 17:49:12.262684: Epoch 91 +2025-10-29 17:49:12.264373: Current learning rate: 0.00918 +2025-10-29 17:58:05.725329: train_loss -0.3527 +2025-10-29 17:58:05.753930: val_loss -0.3767 +2025-10-29 17:58:05.755952: Pseudo dice [np.float32(0.9105), np.float32(0.6866), np.float32(0.6545), np.float32(0.5581), np.float32(0.8288), np.float32(0.7354), np.float32(0.8195), np.float32(0.8526), np.float32(0.9616), np.float32(0.965), np.float32(0.963), np.float32(0.7967), np.float32(0.6824), np.float32(0.8201), np.float32(0.9514), np.float32(0.336), np.float32(0.2095)] +2025-10-29 17:58:05.757305: Epoch time: 533.47 s +2025-10-29 17:58:05.762940: Yayy! New best EMA pseudo Dice: 0.7293000221252441 +2025-10-29 17:58:10.350404: +2025-10-29 17:58:10.352226: Epoch 92 +2025-10-29 17:58:10.353617: Current learning rate: 0.00917 +2025-10-29 18:06:54.199144: train_loss -0.3418 +2025-10-29 18:06:54.210039: val_loss -0.3495 +2025-10-29 18:06:54.211226: Pseudo dice [np.float32(0.9283), np.float32(0.7164), np.float32(0.6854), np.float32(0.5246), np.float32(0.8561), np.float32(0.7546), np.float32(0.8145), np.float32(0.8396), np.float32(0.9525), np.float32(0.9077), np.float32(0.957), np.float32(0.8026), np.float32(0.7361), np.float32(0.8315), np.float32(0.9368), np.float32(0.2612), np.float32(0.1667)] +2025-10-29 18:06:54.212308: Epoch time: 523.85 s +2025-10-29 18:06:54.213532: Yayy! New best EMA pseudo Dice: 0.73089998960495 +2025-10-29 18:06:58.528273: +2025-10-29 18:06:58.529921: Epoch 93 +2025-10-29 18:06:58.531083: Current learning rate: 0.00916 +2025-10-29 18:15:48.000980: train_loss -0.3658 +2025-10-29 18:15:48.006550: val_loss -0.3593 +2025-10-29 18:15:48.008354: Pseudo dice [np.float32(0.8911), np.float32(0.6654), np.float32(0.6769), np.float32(0.6025), np.float32(0.8401), np.float32(0.6842), np.float32(0.8301), np.float32(0.875), np.float32(0.9686), np.float32(0.9731), np.float32(0.9544), np.float32(0.8168), np.float32(0.7221), np.float32(0.8284), np.float32(0.9218), np.float32(0.4), np.float32(0.3981)] +2025-10-29 18:15:48.011221: Epoch time: 529.48 s +2025-10-29 18:15:48.012621: Yayy! New best EMA pseudo Dice: 0.7346000075340271 +2025-10-29 18:15:52.273640: +2025-10-29 18:15:52.275102: Epoch 94 +2025-10-29 18:15:52.276424: Current learning rate: 0.00915 +2025-10-29 18:24:48.453248: train_loss -0.3441 +2025-10-29 18:24:48.457792: val_loss -0.3344 +2025-10-29 18:24:48.459318: Pseudo dice [np.float32(0.9128), np.float32(0.6206), np.float32(0.6017), np.float32(0.5889), np.float32(0.8208), np.float32(0.6978), np.float32(0.7563), np.float32(0.8349), np.float32(0.963), np.float32(0.955), np.float32(0.933), np.float32(0.7257), np.float32(0.6972), np.float32(0.8355), np.float32(0.9008), np.float32(0.3819), np.float32(0.409)] +2025-10-29 18:24:48.460421: Epoch time: 536.18 s +2025-10-29 18:24:48.461437: Yayy! New best EMA pseudo Dice: 0.7354999780654907 +2025-10-29 18:24:52.646598: +2025-10-29 18:24:52.648087: Epoch 95 +2025-10-29 18:24:52.649740: Current learning rate: 0.00914 +2025-10-29 18:33:54.840225: train_loss -0.3297 +2025-10-29 18:33:54.847155: val_loss -0.3272 +2025-10-29 18:33:54.848447: Pseudo dice [np.float32(0.8895), np.float32(0.6205), np.float32(0.5715), np.float32(0.4534), np.float32(0.8283), np.float32(0.6657), np.float32(0.7935), np.float32(0.854), np.float32(0.9315), np.float32(0.9356), np.float32(0.9457), np.float32(0.773), np.float32(0.6918), np.float32(0.8342), np.float32(0.9102), np.float32(0.2492), np.float32(0.2354)] +2025-10-29 18:33:54.849904: Epoch time: 542.2 s +2025-10-29 18:33:56.780603: +2025-10-29 18:33:56.782042: Epoch 96 +2025-10-29 18:33:56.783377: Current learning rate: 0.00913 +2025-10-29 18:42:44.997936: train_loss -0.3079 +2025-10-29 18:42:45.003042: val_loss -0.3283 +2025-10-29 18:42:45.004431: Pseudo dice [np.float32(0.8916), np.float32(0.6539), np.float32(0.6739), np.float32(0.5687), np.float32(0.8284), np.float32(0.7115), np.float32(0.6767), np.float32(0.8188), np.float32(0.9534), np.float32(0.9564), np.float32(0.9451), np.float32(0.7289), np.float32(0.6953), np.float32(0.8402), np.float32(0.9442), np.float32(0.3224), np.float32(0.2254)] +2025-10-29 18:42:45.005584: Epoch time: 528.22 s +2025-10-29 18:42:47.022794: +2025-10-29 18:42:47.024204: Epoch 97 +2025-10-29 18:42:47.026288: Current learning rate: 0.00912 +2025-10-29 18:51:31.577836: train_loss -0.3585 +2025-10-29 18:51:31.583494: val_loss -0.3744 +2025-10-29 18:51:31.585737: Pseudo dice [np.float32(0.8844), np.float32(0.6086), np.float32(0.6525), np.float32(0.6033), np.float32(0.851), np.float32(0.7142), np.float32(0.8009), np.float32(0.8604), np.float32(0.9392), np.float32(0.9555), np.float32(0.9473), np.float32(0.807), np.float32(0.7127), np.float32(0.8282), np.float32(0.9349), np.float32(0.2552), np.float32(0.1989)] +2025-10-29 18:51:31.587752: Epoch time: 524.56 s +2025-10-29 18:51:33.524200: +2025-10-29 18:51:33.525853: Epoch 98 +2025-10-29 18:51:33.527671: Current learning rate: 0.00911 +2025-10-29 19:00:22.573594: train_loss -0.3092 +2025-10-29 19:00:22.598794: val_loss -0.3618 +2025-10-29 19:00:22.600997: Pseudo dice [np.float32(0.9133), np.float32(0.6659), np.float32(0.665), np.float32(0.4996), np.float32(0.8357), np.float32(0.7567), np.float32(0.6892), np.float32(0.8286), np.float32(0.9409), np.float32(0.9418), np.float32(0.9492), np.float32(0.7848), np.float32(0.7136), np.float32(0.8229), np.float32(0.9192), np.float32(0.1574), np.float32(0.1733)] +2025-10-29 19:00:22.610184: Epoch time: 529.05 s +2025-10-29 19:00:24.557312: +2025-10-29 19:00:24.565008: Epoch 99 +2025-10-29 19:00:24.587782: Current learning rate: 0.0091 +2025-10-29 19:09:19.927700: train_loss -0.3254 +2025-10-29 19:09:19.935414: val_loss -0.3179 +2025-10-29 19:09:19.936942: Pseudo dice [np.float32(0.902), np.float32(0.669), np.float32(0.6711), np.float32(0.5543), np.float32(0.8384), np.float32(0.6899), np.float32(0.7825), np.float32(0.8133), np.float32(0.9088), np.float32(0.8985), np.float32(0.9405), np.float32(0.774), np.float32(0.6523), np.float32(0.8246), np.float32(0.9344), np.float32(0.3254), np.float32(0.2394)] +2025-10-29 19:09:19.939297: Epoch time: 535.38 s +2025-10-29 19:09:24.340123: +2025-10-29 19:09:24.341912: Epoch 100 +2025-10-29 19:09:24.343720: Current learning rate: 0.0091 +2025-10-29 19:18:19.905767: train_loss -0.3244 +2025-10-29 19:18:19.917702: val_loss -0.376 +2025-10-29 19:18:19.918926: Pseudo dice [np.float32(0.9204), np.float32(0.6992), np.float32(0.6046), np.float32(0.5515), np.float32(0.8458), np.float32(0.7045), np.float32(0.8331), np.float32(0.8242), np.float32(0.9549), np.float32(0.9604), np.float32(0.9503), np.float32(0.7517), np.float32(0.7281), np.float32(0.8423), np.float32(0.9286), np.float32(0.2807), np.float32(0.326)] +2025-10-29 19:18:19.919990: Epoch time: 535.57 s +2025-10-29 19:18:33.110488: +2025-10-29 19:18:33.112033: Epoch 101 +2025-10-29 19:18:33.113405: Current learning rate: 0.00909 +2025-10-29 19:27:25.134403: train_loss -0.3767 +2025-10-29 19:27:25.144150: val_loss -0.3603 +2025-10-29 19:27:25.145627: Pseudo dice [np.float32(0.9081), np.float32(0.7053), np.float32(0.6116), np.float32(0.4938), np.float32(0.8523), np.float32(0.7006), np.float32(0.8516), np.float32(0.8515), np.float32(0.9044), np.float32(0.9016), np.float32(0.9555), np.float32(0.8053), np.float32(0.6965), np.float32(0.8319), np.float32(0.9198), np.float32(0.4123), np.float32(0.2882)] +2025-10-29 19:27:25.151520: Epoch time: 532.03 s +2025-10-29 19:27:27.097809: +2025-10-29 19:27:27.099990: Epoch 102 +2025-10-29 19:27:27.101321: Current learning rate: 0.00908 +2025-10-29 19:36:07.416556: train_loss -0.3043 +2025-10-29 19:36:07.422857: val_loss -0.3397 +2025-10-29 19:36:07.424437: Pseudo dice [np.float32(0.8757), np.float32(0.6582), np.float32(0.6132), np.float32(0.4933), np.float32(0.7932), np.float32(0.7301), np.float32(0.7925), np.float32(0.8597), np.float32(0.8929), np.float32(0.9071), np.float32(0.951), np.float32(0.7859), np.float32(0.6749), np.float32(0.8283), np.float32(0.9275), np.float32(0.218), np.float32(0.1679)] +2025-10-29 19:36:07.425755: Epoch time: 520.32 s +2025-10-29 19:36:09.378687: +2025-10-29 19:36:09.381337: Epoch 103 +2025-10-29 19:36:09.382989: Current learning rate: 0.00907 +2025-10-29 19:44:59.192579: train_loss -0.3146 +2025-10-29 19:44:59.200042: val_loss -0.3651 +2025-10-29 19:44:59.201163: Pseudo dice [np.float32(0.8998), np.float32(0.7202), np.float32(0.6801), np.float32(0.4945), np.float32(0.8129), np.float32(0.7427), np.float32(0.7935), np.float32(0.8629), np.float32(0.9547), np.float32(0.9587), np.float32(0.9433), np.float32(0.7969), np.float32(0.6989), np.float32(0.7804), np.float32(0.8527), np.float32(0.3604), np.float32(0.3087)] +2025-10-29 19:44:59.202317: Epoch time: 529.82 s +2025-10-29 19:45:01.157411: +2025-10-29 19:45:01.159084: Epoch 104 +2025-10-29 19:45:01.160462: Current learning rate: 0.00906 +2025-10-29 19:55:19.423656: train_loss -0.3359 +2025-10-29 19:55:19.446482: val_loss -0.3706 +2025-10-29 19:55:19.449150: Pseudo dice [np.float32(0.9142), np.float32(0.7274), np.float32(0.6851), np.float32(0.5567), np.float32(0.8233), np.float32(0.7271), np.float32(0.8408), np.float32(0.8712), np.float32(0.9638), np.float32(0.9596), np.float32(0.9574), np.float32(0.8078), np.float32(0.7008), np.float32(0.8363), np.float32(0.9243), np.float32(0.3276), np.float32(0.2618)] +2025-10-29 19:55:19.458652: Epoch time: 618.27 s +2025-10-29 19:55:19.461317: Yayy! New best EMA pseudo Dice: 0.7366999983787537 +2025-10-29 19:55:23.753682: +2025-10-29 19:55:23.760731: Epoch 105 +2025-10-29 19:55:23.770328: Current learning rate: 0.00905 +2025-10-29 20:04:05.809353: train_loss -0.3484 +2025-10-29 20:04:05.820374: val_loss -0.3423 +2025-10-29 20:04:05.822072: Pseudo dice [np.float32(0.9056), np.float32(0.7098), np.float32(0.6812), np.float32(0.5592), np.float32(0.8056), np.float32(0.6866), np.float32(0.8187), np.float32(0.8426), np.float32(0.9278), np.float32(0.9275), np.float32(0.9555), np.float32(0.7922), np.float32(0.7392), np.float32(0.8281), np.float32(0.944), np.float32(0.4132), np.float32(0.3109)] +2025-10-29 20:04:05.824596: Epoch time: 522.06 s +2025-10-29 20:04:05.826568: Yayy! New best EMA pseudo Dice: 0.7386000156402588 +2025-10-29 20:04:10.015478: +2025-10-29 20:04:10.016771: Epoch 106 +2025-10-29 20:04:10.018849: Current learning rate: 0.00904 +2025-10-29 20:12:55.388076: train_loss -0.3388 +2025-10-29 20:12:55.394985: val_loss -0.3665 +2025-10-29 20:12:55.396581: Pseudo dice [np.float32(0.8941), np.float32(0.7139), np.float32(0.6701), np.float32(0.5719), np.float32(0.8494), np.float32(0.7148), np.float32(0.7914), np.float32(0.8541), np.float32(0.9467), np.float32(0.9591), np.float32(0.9581), np.float32(0.805), np.float32(0.6154), np.float32(0.8164), np.float32(0.9529), np.float32(0.3126), np.float32(0.3926)] +2025-10-29 20:12:55.398575: Epoch time: 525.38 s +2025-10-29 20:12:55.400464: Yayy! New best EMA pseudo Dice: 0.7401999831199646 +2025-10-29 20:12:59.890632: +2025-10-29 20:12:59.892053: Epoch 107 +2025-10-29 20:12:59.893158: Current learning rate: 0.00903 +2025-10-29 20:21:41.047398: train_loss -0.3641 +2025-10-29 20:21:41.052357: val_loss -0.357 +2025-10-29 20:21:41.054444: Pseudo dice [np.float32(0.913), np.float32(0.6441), np.float32(0.6767), np.float32(0.5537), np.float32(0.8289), np.float32(0.7364), np.float32(0.8138), np.float32(0.8727), np.float32(0.9236), np.float32(0.9044), np.float32(0.9408), np.float32(0.8279), np.float32(0.6386), np.float32(0.8273), np.float32(0.8272), np.float32(0.2624), np.float32(0.2622)] +2025-10-29 20:21:41.056222: Epoch time: 521.16 s +2025-10-29 20:21:43.391420: +2025-10-29 20:21:43.397814: Epoch 108 +2025-10-29 20:21:43.400925: Current learning rate: 0.00902 +2025-10-29 20:30:37.372639: train_loss -0.348 +2025-10-29 20:30:37.387544: val_loss -0.3807 +2025-10-29 20:30:37.389228: Pseudo dice [np.float32(0.9031), np.float32(0.6812), np.float32(0.6628), np.float32(0.604), np.float32(0.8232), np.float32(0.7506), np.float32(0.8208), np.float32(0.8665), np.float32(0.9417), np.float32(0.9582), np.float32(0.9547), np.float32(0.8116), np.float32(0.7083), np.float32(0.8), np.float32(0.9085), np.float32(0.1767), np.float32(0.2563)] +2025-10-29 20:30:37.391266: Epoch time: 534.01 s +2025-10-29 20:30:39.463478: +2025-10-29 20:30:39.464865: Epoch 109 +2025-10-29 20:30:39.466153: Current learning rate: 0.00901 +2025-10-29 20:39:47.527223: train_loss -0.3311 +2025-10-29 20:39:47.538593: val_loss -0.3691 +2025-10-29 20:39:47.541717: Pseudo dice [np.float32(0.9164), np.float32(0.7313), np.float32(0.6797), np.float32(0.6005), np.float32(0.8553), np.float32(0.7565), np.float32(0.6874), np.float32(0.8571), np.float32(0.9633), np.float32(0.9131), np.float32(0.9427), np.float32(0.8364), np.float32(0.7074), np.float32(0.8428), np.float32(0.9391), np.float32(0.3215), np.float32(0.3036)] +2025-10-29 20:39:47.544194: Epoch time: 548.07 s +2025-10-29 20:39:47.546448: Yayy! New best EMA pseudo Dice: 0.7414000034332275 +2025-10-29 20:39:52.378371: +2025-10-29 20:39:52.379760: Epoch 110 +2025-10-29 20:39:52.381035: Current learning rate: 0.009 +2025-10-29 20:48:48.712887: train_loss -0.3513 +2025-10-29 20:48:48.724824: val_loss -0.3269 +2025-10-29 20:48:48.727716: Pseudo dice [np.float32(0.905), np.float32(0.6449), np.float32(0.6662), np.float32(0.5911), np.float32(0.7986), np.float32(0.7332), np.float32(0.7681), np.float32(0.8423), np.float32(0.9633), np.float32(0.9557), np.float32(0.9415), np.float32(0.7844), np.float32(0.7035), np.float32(0.8173), np.float32(0.9486), np.float32(0.2955), np.float32(0.2682)] +2025-10-29 20:48:48.733977: Epoch time: 536.34 s +2025-10-29 20:48:48.741525: Yayy! New best EMA pseudo Dice: 0.7415000200271606 +2025-10-29 20:48:53.087942: +2025-10-29 20:48:53.095578: Epoch 111 +2025-10-29 20:48:53.110202: Current learning rate: 0.009 +2025-10-29 20:57:52.906708: train_loss -0.3117 +2025-10-29 20:57:52.917451: val_loss -0.3772 +2025-10-29 20:57:52.920514: Pseudo dice [np.float32(0.93), np.float32(0.6906), np.float32(0.5838), np.float32(0.5505), np.float32(0.8293), np.float32(0.7047), np.float32(0.8623), np.float32(0.8642), np.float32(0.9334), np.float32(0.9489), np.float32(0.9414), np.float32(0.7928), np.float32(0.7265), np.float32(0.8189), np.float32(0.855), np.float32(0.295), np.float32(0.2801)] +2025-10-29 20:57:52.923602: Epoch time: 539.82 s +2025-10-29 20:57:52.925351: Yayy! New best EMA pseudo Dice: 0.7415000200271606 +2025-10-29 20:57:58.317962: +2025-10-29 20:57:58.320699: Epoch 112 +2025-10-29 20:57:58.322650: Current learning rate: 0.00899 +2025-10-29 21:07:12.035407: train_loss -0.3439 +2025-10-29 21:07:12.055563: val_loss -0.3358 +2025-10-29 21:07:12.057745: Pseudo dice [np.float32(0.9063), np.float32(0.3758), np.float32(0.7079), np.float32(0.5343), np.float32(0.8008), np.float32(0.7395), np.float32(0.8167), np.float32(0.8404), np.float32(0.9383), np.float32(0.94), np.float32(0.9435), np.float32(0.7651), np.float32(0.7267), np.float32(0.8574), np.float32(0.8881), np.float32(0.3698), np.float32(0.2894)] +2025-10-29 21:07:12.059472: Epoch time: 553.72 s +2025-10-29 21:07:15.584155: +2025-10-29 21:07:15.586503: Epoch 113 +2025-10-29 21:07:15.589505: Current learning rate: 0.00898 +2025-10-29 21:16:15.609181: train_loss -0.3584 +2025-10-29 21:16:15.618250: val_loss -0.3592 +2025-10-29 21:16:15.620452: Pseudo dice [np.float32(0.9013), np.float32(0.7323), np.float32(0.6774), np.float32(0.5447), np.float32(0.8294), np.float32(0.7429), np.float32(0.838), np.float32(0.8686), np.float32(0.9719), np.float32(0.9688), np.float32(0.9543), np.float32(0.7967), np.float32(0.73), np.float32(0.8187), np.float32(0.9419), np.float32(0.3159), np.float32(0.2729)] +2025-10-29 21:16:15.622656: Epoch time: 540.03 s +2025-10-29 21:16:15.624783: Yayy! New best EMA pseudo Dice: 0.7423999905586243 +2025-10-29 21:16:20.063341: +2025-10-29 21:16:20.064867: Epoch 114 +2025-10-29 21:16:20.066107: Current learning rate: 0.00897 +2025-10-29 21:25:22.724662: train_loss -0.3678 +2025-10-29 21:25:22.731427: val_loss -0.3872 +2025-10-29 21:25:22.733812: Pseudo dice [np.float32(0.9109), np.float32(0.7354), np.float32(0.6496), np.float32(0.5431), np.float32(0.8427), np.float32(0.7089), np.float32(0.8273), np.float32(0.867), np.float32(0.9404), np.float32(0.9507), np.float32(0.96), np.float32(0.8012), np.float32(0.7326), np.float32(0.8418), np.float32(0.919), np.float32(0.4083), np.float32(0.4283)] +2025-10-29 21:25:22.736128: Epoch time: 542.67 s +2025-10-29 21:25:22.737646: Yayy! New best EMA pseudo Dice: 0.7450000047683716 +2025-10-29 21:25:27.355022: +2025-10-29 21:25:27.357687: Epoch 115 +2025-10-29 21:25:27.359473: Current learning rate: 0.00896 +2025-10-29 21:34:21.231879: train_loss -0.366 +2025-10-29 21:34:21.267974: val_loss -0.4064 +2025-10-29 21:34:21.269889: Pseudo dice [np.float32(0.9149), np.float32(0.7263), np.float32(0.6765), np.float32(0.623), np.float32(0.8469), np.float32(0.7473), np.float32(0.8498), np.float32(0.8683), np.float32(0.9233), np.float32(0.9437), np.float32(0.9537), np.float32(0.8212), np.float32(0.75), np.float32(0.8473), np.float32(0.9337), np.float32(0.2679), np.float32(0.3025)] +2025-10-29 21:34:21.271802: Epoch time: 533.88 s +2025-10-29 21:34:21.274119: Yayy! New best EMA pseudo Dice: 0.746999979019165 +2025-10-29 21:34:25.649413: +2025-10-29 21:34:25.650681: Epoch 116 +2025-10-29 21:34:25.652820: Current learning rate: 0.00895 +2025-10-29 21:43:35.864525: train_loss -0.3663 +2025-10-29 21:43:35.870474: val_loss -0.4154 +2025-10-29 21:43:35.871972: Pseudo dice [np.float32(0.9128), np.float32(0.6454), np.float32(0.6911), np.float32(0.5721), np.float32(0.8599), np.float32(0.7455), np.float32(0.8863), np.float32(0.8737), np.float32(0.9734), np.float32(0.9764), np.float32(0.9635), np.float32(0.8174), np.float32(0.721), np.float32(0.815), np.float32(0.948), np.float32(0.2323), np.float32(0.2663)] +2025-10-29 21:43:35.873181: Epoch time: 550.22 s +2025-10-29 21:43:35.875648: Yayy! New best EMA pseudo Dice: 0.748199999332428 +2025-10-29 21:43:40.110814: +2025-10-29 21:43:40.112371: Epoch 117 +2025-10-29 21:43:40.114469: Current learning rate: 0.00894 +2025-10-29 21:52:51.166672: train_loss -0.3258 +2025-10-29 21:52:51.175520: val_loss -0.3882 +2025-10-29 21:52:51.176706: Pseudo dice [np.float32(0.9132), np.float32(0.705), np.float32(0.5828), np.float32(0.6124), np.float32(0.8378), np.float32(0.7315), np.float32(0.8825), np.float32(0.8627), np.float32(0.9536), np.float32(0.9509), np.float32(0.9625), np.float32(0.8233), np.float32(0.6792), np.float32(0.8127), np.float32(0.9245), np.float32(0.3522), np.float32(0.3297)] +2025-10-29 21:52:51.178725: Epoch time: 551.06 s +2025-10-29 21:52:51.179761: Yayy! New best EMA pseudo Dice: 0.7493000030517578 +2025-10-29 21:52:55.523490: +2025-10-29 21:52:55.525143: Epoch 118 +2025-10-29 21:52:55.527378: Current learning rate: 0.00893 +2025-10-29 22:02:01.805476: train_loss -0.3529 +2025-10-29 22:02:01.810211: val_loss -0.3606 +2025-10-29 22:02:01.811408: Pseudo dice [np.float32(0.904), np.float32(0.7265), np.float32(0.6862), np.float32(0.6109), np.float32(0.8193), np.float32(0.7202), np.float32(0.7378), np.float32(0.8575), np.float32(0.9284), np.float32(0.9137), np.float32(0.9354), np.float32(0.787), np.float32(0.7411), np.float32(0.8264), np.float32(0.9204), np.float32(0.3169), np.float32(0.2197)] +2025-10-29 22:02:01.820075: Epoch time: 546.29 s +2025-10-29 22:02:03.778911: +2025-10-29 22:02:03.780227: Epoch 119 +2025-10-29 22:02:03.781537: Current learning rate: 0.00892 +2025-10-29 22:11:01.657546: train_loss -0.3576 +2025-10-29 22:11:01.672695: val_loss -0.338 +2025-10-29 22:11:01.673972: Pseudo dice [np.float32(0.8953), np.float32(0.699), np.float32(0.6291), np.float32(0.4938), np.float32(0.847), np.float32(0.7094), np.float32(0.7701), np.float32(0.8217), np.float32(0.9106), np.float32(0.9225), np.float32(0.9484), np.float32(0.7615), np.float32(0.7015), np.float32(0.8156), np.float32(0.8884), np.float32(0.3117), np.float32(0.2338)] +2025-10-29 22:11:01.675956: Epoch time: 537.89 s +2025-10-29 22:11:03.790071: +2025-10-29 22:11:03.791747: Epoch 120 +2025-10-29 22:11:03.793489: Current learning rate: 0.00891 +2025-10-29 22:19:59.703858: train_loss -0.3296 +2025-10-29 22:19:59.718570: val_loss -0.2884 +2025-10-29 22:19:59.721217: Pseudo dice [np.float32(0.8456), np.float32(0.6899), np.float32(0.531), np.float32(0.5133), np.float32(0.8315), np.float32(0.6923), np.float32(0.8325), np.float32(0.8305), np.float32(0.9417), np.float32(0.951), np.float32(0.9297), np.float32(0.819), np.float32(0.6992), np.float32(0.816), np.float32(0.6606), np.float32(0.4547), np.float32(0.2995)] +2025-10-29 22:19:59.722746: Epoch time: 535.92 s +2025-10-29 22:20:01.865960: +2025-10-29 22:20:01.867500: Epoch 121 +2025-10-29 22:20:01.869049: Current learning rate: 0.0089 +2025-10-29 22:28:48.717069: train_loss -0.3487 +2025-10-29 22:28:48.723283: val_loss -0.375 +2025-10-29 22:28:48.724984: Pseudo dice [np.float32(0.9128), np.float32(0.7178), np.float32(0.6457), np.float32(0.5881), np.float32(0.8251), np.float32(0.7253), np.float32(0.8167), np.float32(0.8571), np.float32(0.9402), np.float32(0.9485), np.float32(0.9543), np.float32(0.8127), np.float32(0.7294), np.float32(0.832), np.float32(0.932), np.float32(0.28), np.float32(0.248)] +2025-10-29 22:28:48.727485: Epoch time: 526.85 s +2025-10-29 22:28:50.757499: +2025-10-29 22:28:50.760757: Epoch 122 +2025-10-29 22:28:50.762976: Current learning rate: 0.00889 +2025-10-29 22:37:36.765061: train_loss -0.3497 +2025-10-29 22:37:36.785639: val_loss -0.4171 +2025-10-29 22:37:36.787124: Pseudo dice [np.float32(0.9133), np.float32(0.7241), np.float32(0.669), np.float32(0.5563), np.float32(0.845), np.float32(0.7069), np.float32(0.821), np.float32(0.8487), np.float32(0.9606), np.float32(0.9736), np.float32(0.957), np.float32(0.7924), np.float32(0.6833), np.float32(0.8303), np.float32(0.9411), np.float32(0.4396), np.float32(0.3853)] +2025-10-29 22:37:36.788492: Epoch time: 526.01 s +2025-10-29 22:37:38.777579: +2025-10-29 22:37:38.779707: Epoch 123 +2025-10-29 22:37:38.781147: Current learning rate: 0.00889 +2025-10-29 22:46:38.605281: train_loss -0.3481 +2025-10-29 22:46:38.614757: val_loss -0.3736 +2025-10-29 22:46:38.620643: Pseudo dice [np.float32(0.9212), np.float32(0.6675), np.float32(0.6817), np.float32(0.5211), np.float32(0.8146), np.float32(0.7491), np.float32(0.7793), np.float32(0.8411), np.float32(0.9117), np.float32(0.9186), np.float32(0.9425), np.float32(0.7893), np.float32(0.6905), np.float32(0.8194), np.float32(0.9165), np.float32(0.4356), np.float32(0.3601)] +2025-10-29 22:46:38.622854: Epoch time: 539.83 s +2025-10-29 22:46:40.576187: +2025-10-29 22:46:40.583493: Epoch 124 +2025-10-29 22:46:40.585169: Current learning rate: 0.00888 +2025-10-29 22:55:33.597435: train_loss -0.3701 +2025-10-29 22:55:33.630985: val_loss -0.3911 +2025-10-29 22:55:33.633159: Pseudo dice [np.float32(0.9061), np.float32(0.684), np.float32(0.6837), np.float32(0.5931), np.float32(0.8247), np.float32(0.7503), np.float32(0.8308), np.float32(0.8353), np.float32(0.9718), np.float32(0.9762), np.float32(0.9563), np.float32(0.8016), np.float32(0.7456), np.float32(0.7899), np.float32(0.9246), np.float32(0.2491), np.float32(0.1897)] +2025-10-29 22:55:33.636156: Epoch time: 533.03 s +2025-10-29 22:55:35.644156: +2025-10-29 22:55:35.649839: Epoch 125 +2025-10-29 22:55:35.651391: Current learning rate: 0.00887 +2025-10-29 23:04:27.315092: train_loss -0.3631 +2025-10-29 23:04:27.330325: val_loss -0.3794 +2025-10-29 23:04:27.331703: Pseudo dice [np.float32(0.8789), np.float32(0.7237), np.float32(0.6129), np.float32(0.6142), np.float32(0.8463), np.float32(0.7695), np.float32(0.7991), np.float32(0.8559), np.float32(0.9588), np.float32(0.9628), np.float32(0.9504), np.float32(0.8021), np.float32(0.7406), np.float32(0.8591), np.float32(0.8693), np.float32(0.4372), np.float32(0.3516)] +2025-10-29 23:04:27.345979: Epoch time: 531.68 s +2025-10-29 23:04:27.347190: Yayy! New best EMA pseudo Dice: 0.7495999932289124 +2025-10-29 23:04:31.671643: +2025-10-29 23:04:31.673535: Epoch 126 +2025-10-29 23:04:31.674834: Current learning rate: 0.00886 +2025-10-29 23:13:44.577052: train_loss -0.3627 +2025-10-29 23:13:44.627140: val_loss -0.3701 +2025-10-29 23:13:44.629080: Pseudo dice [np.float32(0.9104), np.float32(0.7236), np.float32(0.6488), np.float32(0.6132), np.float32(0.8359), np.float32(0.7281), np.float32(0.8308), np.float32(0.857), np.float32(0.963), np.float32(0.9155), np.float32(0.9503), np.float32(0.8082), np.float32(0.7473), np.float32(0.8251), np.float32(0.924), np.float32(0.1858), np.float32(0.224)] +2025-10-29 23:13:44.630704: Epoch time: 552.91 s +2025-10-29 23:13:46.775785: +2025-10-29 23:13:46.777879: Epoch 127 +2025-10-29 23:13:46.779403: Current learning rate: 0.00885 +2025-10-29 23:22:28.950033: train_loss -0.3889 +2025-10-29 23:22:28.956117: val_loss -0.3749 +2025-10-29 23:22:28.957589: Pseudo dice [np.float32(0.9259), np.float32(0.7242), np.float32(0.6891), np.float32(0.4812), np.float32(0.8386), np.float32(0.754), np.float32(0.8492), np.float32(0.8622), np.float32(0.9486), np.float32(0.9586), np.float32(0.9552), np.float32(0.7928), np.float32(0.7121), np.float32(0.8592), np.float32(0.8858), np.float32(0.2877), np.float32(0.231)] +2025-10-29 23:22:28.964002: Epoch time: 522.18 s +2025-10-29 23:22:31.150267: +2025-10-29 23:22:31.151887: Epoch 128 +2025-10-29 23:22:31.153100: Current learning rate: 0.00884 +2025-10-29 23:31:27.165239: train_loss -0.3689 +2025-10-29 23:31:27.177214: val_loss -0.3912 +2025-10-29 23:31:27.179229: Pseudo dice [np.float32(0.9094), np.float32(0.7003), np.float32(0.6459), np.float32(0.5774), np.float32(0.8772), np.float32(0.7456), np.float32(0.8114), np.float32(0.8763), np.float32(0.95), np.float32(0.9599), np.float32(0.9428), np.float32(0.7886), np.float32(0.6594), np.float32(0.8157), np.float32(0.9374), np.float32(0.3136), np.float32(0.2959)] +2025-10-29 23:31:27.180917: Epoch time: 536.02 s +2025-10-29 23:31:27.182920: Yayy! New best EMA pseudo Dice: 0.7498000264167786 +2025-10-29 23:31:31.706094: +2025-10-29 23:31:31.708028: Epoch 129 +2025-10-29 23:31:31.710393: Current learning rate: 0.00883 +2025-10-29 23:40:37.977917: train_loss -0.347 +2025-10-29 23:40:37.988303: val_loss -0.3459 +2025-10-29 23:40:37.995709: Pseudo dice [np.float32(0.9124), np.float32(0.7171), np.float32(0.672), np.float32(0.5722), np.float32(0.8184), np.float32(0.7069), np.float32(0.7885), np.float32(0.8558), np.float32(0.9424), np.float32(0.93), np.float32(0.913), np.float32(0.8072), np.float32(0.7015), np.float32(0.7919), np.float32(0.8314), np.float32(0.3511), np.float32(0.3339)] +2025-10-29 23:40:37.997007: Epoch time: 546.28 s +2025-10-29 23:40:40.164716: +2025-10-29 23:40:40.166499: Epoch 130 +2025-10-29 23:40:40.167867: Current learning rate: 0.00882 +2025-10-29 23:49:52.486080: train_loss -0.3583 +2025-10-29 23:49:52.499967: val_loss -0.3653 +2025-10-29 23:49:52.522318: Pseudo dice [np.float32(0.8977), np.float32(0.7513), np.float32(0.7172), np.float32(0.6043), np.float32(0.7719), np.float32(0.7857), np.float32(0.8278), np.float32(0.8545), np.float32(0.9435), np.float32(0.909), np.float32(0.9494), np.float32(0.8011), np.float32(0.7377), np.float32(0.8515), np.float32(0.9025), np.float32(0.293), np.float32(0.1669)] +2025-10-29 23:49:52.524555: Epoch time: 552.33 s +2025-10-29 23:49:54.564945: +2025-10-29 23:49:54.566274: Epoch 131 +2025-10-29 23:49:54.567682: Current learning rate: 0.00881 +2025-10-29 23:58:42.599271: train_loss -0.3804 +2025-10-29 23:58:42.606373: val_loss -0.4366 +2025-10-29 23:58:42.608358: Pseudo dice [np.float32(0.901), np.float32(0.7151), np.float32(0.7126), np.float32(0.633), np.float32(0.8694), np.float32(0.7588), np.float32(0.8819), np.float32(0.8475), np.float32(0.9443), np.float32(0.9324), np.float32(0.9537), np.float32(0.839), np.float32(0.743), np.float32(0.867), np.float32(0.9155), np.float32(0.3639), np.float32(0.3548)] +2025-10-29 23:58:42.609737: Epoch time: 528.04 s +2025-10-29 23:58:42.611130: Yayy! New best EMA pseudo Dice: 0.7523000240325928 +2025-10-29 23:58:47.035336: +2025-10-29 23:58:47.037112: Epoch 132 +2025-10-29 23:58:47.039109: Current learning rate: 0.0088 +2025-10-30 00:07:31.225675: train_loss -0.3525 +2025-10-30 00:07:31.262120: val_loss -0.3516 +2025-10-30 00:07:31.263326: Pseudo dice [np.float32(0.8951), np.float32(0.7013), np.float32(0.6877), np.float32(0.5455), np.float32(0.8252), np.float32(0.7413), np.float32(0.6723), np.float32(0.8425), np.float32(0.9395), np.float32(0.941), np.float32(0.9483), np.float32(0.7871), np.float32(0.6948), np.float32(0.8417), np.float32(0.8835), np.float32(0.3696), np.float32(0.2971)] +2025-10-30 00:07:31.264479: Epoch time: 524.19 s +2025-10-30 00:07:33.312382: +2025-10-30 00:07:33.313683: Epoch 133 +2025-10-30 00:07:33.315305: Current learning rate: 0.00879 +2025-10-30 00:16:20.012200: train_loss -0.3514 +2025-10-30 00:16:20.026717: val_loss -0.3584 +2025-10-30 00:16:20.028627: Pseudo dice [np.float32(0.8865), np.float32(0.7233), np.float32(0.642), np.float32(0.5216), np.float32(0.8221), np.float32(0.7389), np.float32(0.8717), np.float32(0.8409), np.float32(0.9645), np.float32(0.9526), np.float32(0.9431), np.float32(0.7872), np.float32(0.7257), np.float32(0.8402), np.float32(0.9055), np.float32(0.2021), np.float32(0.2455)] +2025-10-30 00:16:20.030408: Epoch time: 526.7 s +2025-10-30 00:16:22.151048: +2025-10-30 00:16:22.152610: Epoch 134 +2025-10-30 00:16:22.154104: Current learning rate: 0.00879 +2025-10-30 00:24:54.049285: train_loss -0.374 +2025-10-30 00:24:54.084813: val_loss -0.3817 +2025-10-30 00:24:54.086513: Pseudo dice [np.float32(0.8985), np.float32(0.7133), np.float32(0.6086), np.float32(0.519), np.float32(0.8654), np.float32(0.7472), np.float32(0.7818), np.float32(0.8542), np.float32(0.9176), np.float32(0.9009), np.float32(0.9574), np.float32(0.7262), np.float32(0.668), np.float32(0.8455), np.float32(0.9564), np.float32(0.2075), np.float32(0.2447)] +2025-10-30 00:24:54.088907: Epoch time: 511.9 s +2025-10-30 00:24:57.043467: +2025-10-30 00:24:57.045727: Epoch 135 +2025-10-30 00:24:57.047062: Current learning rate: 0.00878 +2025-10-30 00:33:50.564028: train_loss -0.3634 +2025-10-30 00:33:50.586221: val_loss -0.3278 +2025-10-30 00:33:50.587814: Pseudo dice [np.float32(0.9261), np.float32(0.6687), np.float32(0.6801), np.float32(0.6301), np.float32(0.82), np.float32(0.7231), np.float32(0.7895), np.float32(0.867), np.float32(0.8661), np.float32(0.9009), np.float32(0.9373), np.float32(0.7926), np.float32(0.7176), np.float32(0.7851), np.float32(0.9062), np.float32(0.1569), np.float32(0.2224)] +2025-10-30 00:33:50.590410: Epoch time: 533.52 s +2025-10-30 00:33:52.673509: +2025-10-30 00:33:52.674860: Epoch 136 +2025-10-30 00:33:52.676211: Current learning rate: 0.00877 +2025-10-30 00:43:01.664726: train_loss -0.3566 +2025-10-30 00:43:01.681780: val_loss -0.3648 +2025-10-30 00:43:01.683298: Pseudo dice [np.float32(0.9263), np.float32(0.7038), np.float32(0.6435), np.float32(0.5931), np.float32(0.8668), np.float32(0.6959), np.float32(0.8245), np.float32(0.8619), np.float32(0.9207), np.float32(0.9324), np.float32(0.9566), np.float32(0.8006), np.float32(0.7253), np.float32(0.8404), np.float32(0.9231), np.float32(0.2262), np.float32(0.2964)] +2025-10-30 00:43:01.685020: Epoch time: 549.0 s +2025-10-30 00:43:03.850709: +2025-10-30 00:43:03.852591: Epoch 137 +2025-10-30 00:43:03.854415: Current learning rate: 0.00876 +2025-10-30 00:52:00.089753: train_loss -0.3884 +2025-10-30 00:52:00.094568: val_loss -0.4355 +2025-10-30 00:52:00.095694: Pseudo dice [np.float32(0.9189), np.float32(0.7394), np.float32(0.7042), np.float32(0.5859), np.float32(0.8318), np.float32(0.735), np.float32(0.873), np.float32(0.8769), np.float32(0.9777), np.float32(0.9769), np.float32(0.9684), np.float32(0.8114), np.float32(0.7634), np.float32(0.8476), np.float32(0.9471), np.float32(0.3438), np.float32(0.3239)] +2025-10-30 00:52:00.096805: Epoch time: 536.24 s +2025-10-30 00:52:02.210016: +2025-10-30 00:52:02.211735: Epoch 138 +2025-10-30 00:52:02.213631: Current learning rate: 0.00875 +2025-10-30 01:01:00.584391: train_loss -0.3815 +2025-10-30 01:01:00.616344: val_loss -0.3199 +2025-10-30 01:01:00.618124: Pseudo dice [np.float32(0.9153), np.float32(0.6972), np.float32(0.665), np.float32(0.5322), np.float32(0.7653), np.float32(0.7514), np.float32(0.8211), np.float32(0.8584), np.float32(0.9179), np.float32(0.9275), np.float32(0.9232), np.float32(0.7903), np.float32(0.7058), np.float32(0.7976), np.float32(0.7214), np.float32(0.3454), np.float32(0.2906)] +2025-10-30 01:01:00.619622: Epoch time: 538.38 s +2025-10-30 01:01:02.892587: +2025-10-30 01:01:02.896201: Epoch 139 +2025-10-30 01:01:02.897829: Current learning rate: 0.00874 +2025-10-30 01:10:11.608320: train_loss -0.3418 +2025-10-30 01:10:11.616677: val_loss -0.3934 +2025-10-30 01:10:11.618515: Pseudo dice [np.float32(0.9219), np.float32(0.6686), np.float32(0.7189), np.float32(0.5946), np.float32(0.8556), np.float32(0.7473), np.float32(0.8199), np.float32(0.8815), np.float32(0.8917), np.float32(0.87), np.float32(0.9443), np.float32(0.8253), np.float32(0.7165), np.float32(0.8456), np.float32(0.9158), np.float32(0.2252), np.float32(0.1771)] +2025-10-30 01:10:11.619712: Epoch time: 548.72 s +2025-10-30 01:10:13.639790: +2025-10-30 01:10:13.641481: Epoch 140 +2025-10-30 01:10:13.644434: Current learning rate: 0.00873 +2025-10-30 01:19:16.538262: train_loss -0.3691 +2025-10-30 01:19:16.543546: val_loss -0.429 +2025-10-30 01:19:16.546301: Pseudo dice [np.float32(0.9154), np.float32(0.7568), np.float32(0.681), np.float32(0.6302), np.float32(0.8511), np.float32(0.7591), np.float32(0.7654), np.float32(0.8547), np.float32(0.9594), np.float32(0.9632), np.float32(0.9536), np.float32(0.8215), np.float32(0.7197), np.float32(0.8338), np.float32(0.9486), np.float32(0.3434), np.float32(0.3222)] +2025-10-30 01:19:16.547621: Epoch time: 542.9 s +2025-10-30 01:19:18.623416: +2025-10-30 01:19:18.625017: Epoch 141 +2025-10-30 01:19:18.626463: Current learning rate: 0.00872 +2025-10-30 01:28:18.517833: train_loss -0.3848 +2025-10-30 01:28:18.530340: val_loss -0.3615 +2025-10-30 01:28:18.532954: Pseudo dice [np.float32(0.9071), np.float32(0.7479), np.float32(0.6398), np.float32(0.5466), np.float32(0.8292), np.float32(0.7679), np.float32(0.8277), np.float32(0.8591), np.float32(0.9661), np.float32(0.9655), np.float32(0.9547), np.float32(0.8453), np.float32(0.726), np.float32(0.8313), np.float32(0.9345), np.float32(0.2419), np.float32(0.2644)] +2025-10-30 01:28:18.534765: Epoch time: 539.9 s +2025-10-30 01:28:20.631324: +2025-10-30 01:28:20.632704: Epoch 142 +2025-10-30 01:28:20.634055: Current learning rate: 0.00871 +2025-10-30 01:37:09.161577: train_loss -0.3759 +2025-10-30 01:37:09.173092: val_loss -0.3912 +2025-10-30 01:37:09.175080: Pseudo dice [np.float32(0.9166), np.float32(0.6814), np.float32(0.6605), np.float32(0.5602), np.float32(0.8354), np.float32(0.7439), np.float32(0.848), np.float32(0.861), np.float32(0.9719), np.float32(0.9584), np.float32(0.9626), np.float32(0.8287), np.float32(0.7388), np.float32(0.8511), np.float32(0.9486), np.float32(0.3687), np.float32(0.3209)] +2025-10-30 01:37:09.176769: Epoch time: 528.53 s +2025-10-30 01:37:11.208838: +2025-10-30 01:37:11.212561: Epoch 143 +2025-10-30 01:37:11.214018: Current learning rate: 0.0087 +2025-10-30 01:46:01.965211: train_loss -0.3426 +2025-10-30 01:46:01.985202: val_loss -0.3326 +2025-10-30 01:46:01.991768: Pseudo dice [np.float32(0.9019), np.float32(0.6953), np.float32(0.6493), np.float32(0.5692), np.float32(0.8131), np.float32(0.7318), np.float32(0.8108), np.float32(0.8466), np.float32(0.9558), np.float32(0.9529), np.float32(0.9609), np.float32(0.782), np.float32(0.7013), np.float32(0.8342), np.float32(0.9389), np.float32(0.262), np.float32(0.2771)] +2025-10-30 01:46:01.993816: Epoch time: 530.76 s +2025-10-30 01:46:04.071002: +2025-10-30 01:46:04.073520: Epoch 144 +2025-10-30 01:46:04.075224: Current learning rate: 0.00869 +2025-10-30 01:55:01.962065: train_loss -0.3592 +2025-10-30 01:55:01.985847: val_loss -0.3868 +2025-10-30 01:55:01.987087: Pseudo dice [np.float32(0.9242), np.float32(0.7229), np.float32(0.5904), np.float32(0.5906), np.float32(0.8563), np.float32(0.7472), np.float32(0.8112), np.float32(0.8484), np.float32(0.9513), np.float32(0.9315), np.float32(0.9564), np.float32(0.8093), np.float32(0.6809), np.float32(0.8626), np.float32(0.9467), np.float32(0.3031), np.float32(0.2731)] +2025-10-30 01:55:01.989240: Epoch time: 537.9 s +2025-10-30 01:55:04.002574: +2025-10-30 01:55:04.005803: Epoch 145 +2025-10-30 01:55:04.011034: Current learning rate: 0.00868 +2025-10-30 02:03:57.557631: train_loss -0.3537 +2025-10-30 02:03:57.579823: val_loss -0.3383 +2025-10-30 02:03:57.582054: Pseudo dice [np.float32(0.9068), np.float32(0.673), np.float32(0.65), np.float32(0.5149), np.float32(0.8401), np.float32(0.7231), np.float32(0.8251), np.float32(0.8626), np.float32(0.9374), np.float32(0.9504), np.float32(0.9408), np.float32(0.8042), np.float32(0.7035), np.float32(0.8142), np.float32(0.8847), np.float32(0.2836), np.float32(0.2692)] +2025-10-30 02:03:57.583401: Epoch time: 533.56 s +2025-10-30 02:03:59.590973: +2025-10-30 02:03:59.593420: Epoch 146 +2025-10-30 02:03:59.599185: Current learning rate: 0.00868 +2025-10-30 02:12:47.391127: train_loss -0.3605 +2025-10-30 02:12:47.410908: val_loss -0.3778 +2025-10-30 02:12:47.412161: Pseudo dice [np.float32(0.9179), np.float32(0.6955), np.float32(0.6478), np.float32(0.622), np.float32(0.8482), np.float32(0.7333), np.float32(0.7646), np.float32(0.8589), np.float32(0.9534), np.float32(0.9643), np.float32(0.9466), np.float32(0.7802), np.float32(0.7078), np.float32(0.8426), np.float32(0.9335), np.float32(0.2906), np.float32(0.4258)] +2025-10-30 02:12:47.413498: Epoch time: 527.8 s +2025-10-30 02:12:49.545917: +2025-10-30 02:12:49.550948: Epoch 147 +2025-10-30 02:12:49.552644: Current learning rate: 0.00867 +2025-10-30 02:21:45.791649: train_loss -0.3479 +2025-10-30 02:21:45.807543: val_loss -0.3676 +2025-10-30 02:21:45.809594: Pseudo dice [np.float32(0.9003), np.float32(0.7377), np.float32(0.6458), np.float32(0.5764), np.float32(0.8313), np.float32(0.7604), np.float32(0.8442), np.float32(0.8563), np.float32(0.9531), np.float32(0.9482), np.float32(0.9518), np.float32(0.8177), np.float32(0.7528), np.float32(0.8545), np.float32(0.934), np.float32(0.2172), np.float32(0.1758)] +2025-10-30 02:21:45.811924: Epoch time: 536.25 s +2025-10-30 02:21:47.886325: +2025-10-30 02:21:47.890369: Epoch 148 +2025-10-30 02:21:47.891578: Current learning rate: 0.00866 +2025-10-30 02:30:36.951673: train_loss -0.3728 +2025-10-30 02:30:36.972349: val_loss -0.3659 +2025-10-30 02:30:36.973971: Pseudo dice [np.float32(0.9142), np.float32(0.7317), np.float32(0.673), np.float32(0.5462), np.float32(0.7836), np.float32(0.7303), np.float32(0.8193), np.float32(0.8545), np.float32(0.9396), np.float32(0.9236), np.float32(0.9441), np.float32(0.8084), np.float32(0.765), np.float32(0.8263), np.float32(0.9507), np.float32(0.3697), np.float32(0.2185)] +2025-10-30 02:30:36.979332: Epoch time: 529.07 s +2025-10-30 02:30:39.086916: +2025-10-30 02:30:39.088111: Epoch 149 +2025-10-30 02:30:39.089287: Current learning rate: 0.00865 +2025-10-30 02:39:45.515391: train_loss -0.4008 +2025-10-30 02:39:45.526043: val_loss -0.3723 +2025-10-30 02:39:45.532622: Pseudo dice [np.float32(0.9129), np.float32(0.7453), np.float32(0.6979), np.float32(0.6405), np.float32(0.8562), np.float32(0.7526), np.float32(0.8127), np.float32(0.8599), np.float32(0.9282), np.float32(0.9207), np.float32(0.9635), np.float32(0.797), np.float32(0.7254), np.float32(0.8325), np.float32(0.9607), np.float32(0.1621), np.float32(0.1926)] +2025-10-30 02:39:45.535887: Epoch time: 546.43 s +2025-10-30 02:39:49.970541: +2025-10-30 02:39:49.972359: Epoch 150 +2025-10-30 02:39:49.973765: Current learning rate: 0.00864 +2025-10-30 02:49:01.273713: train_loss -0.3715 +2025-10-30 02:49:01.278341: val_loss -0.386 +2025-10-30 02:49:01.280794: Pseudo dice [np.float32(0.9083), np.float32(0.751), np.float32(0.7132), np.float32(0.5542), np.float32(0.806), np.float32(0.72), np.float32(0.8517), np.float32(0.8636), np.float32(0.9719), np.float32(0.9731), np.float32(0.9618), np.float32(0.8172), np.float32(0.7308), np.float32(0.8191), np.float32(0.9468), np.float32(0.3042), np.float32(0.2904)] +2025-10-30 02:49:01.282127: Epoch time: 551.31 s +2025-10-30 02:49:01.283541: Yayy! New best EMA pseudo Dice: 0.7526999711990356 +2025-10-30 02:49:06.435610: +2025-10-30 02:49:06.438588: Epoch 151 +2025-10-30 02:49:06.440129: Current learning rate: 0.00863 +2025-10-30 02:58:11.915890: train_loss -0.3812 +2025-10-30 02:58:11.920279: val_loss -0.3217 +2025-10-30 02:58:11.921451: Pseudo dice [np.float32(0.9009), np.float32(0.6879), np.float32(0.6547), np.float32(0.6213), np.float32(0.8295), np.float32(0.7447), np.float32(0.774), np.float32(0.8684), np.float32(0.8812), np.float32(0.9124), np.float32(0.9533), np.float32(0.7933), np.float32(0.7447), np.float32(0.8099), np.float32(0.9266), np.float32(0.3257), np.float32(0.0971)] +2025-10-30 02:58:11.922977: Epoch time: 545.48 s +2025-10-30 02:58:14.154708: +2025-10-30 02:58:14.156397: Epoch 152 +2025-10-30 02:58:14.157427: Current learning rate: 0.00862 +2025-10-30 03:07:20.835337: train_loss -0.385 +2025-10-30 03:07:20.843943: val_loss -0.3928 +2025-10-30 03:07:20.845324: Pseudo dice [np.float32(0.9337), np.float32(0.7267), np.float32(0.6506), np.float32(0.6345), np.float32(0.8536), np.float32(0.7659), np.float32(0.842), np.float32(0.8404), np.float32(0.9482), np.float32(0.9448), np.float32(0.9608), np.float32(0.8321), np.float32(0.709), np.float32(0.8568), np.float32(0.9253), np.float32(0.4012), np.float32(0.327)] +2025-10-30 03:07:20.846561: Epoch time: 546.69 s +2025-10-30 03:07:20.847584: Yayy! New best EMA pseudo Dice: 0.7533000111579895 +2025-10-30 03:07:25.232861: +2025-10-30 03:07:25.234940: Epoch 153 +2025-10-30 03:07:25.236388: Current learning rate: 0.00861 +2025-10-30 03:16:27.795428: train_loss -0.3799 +2025-10-30 03:16:27.811529: val_loss -0.4244 +2025-10-30 03:16:27.813018: Pseudo dice [np.float32(0.9174), np.float32(0.6953), np.float32(0.635), np.float32(0.5971), np.float32(0.8478), np.float32(0.7435), np.float32(0.8759), np.float32(0.8601), np.float32(0.9348), np.float32(0.93), np.float32(0.9589), np.float32(0.8031), np.float32(0.7571), np.float32(0.8413), np.float32(0.9504), np.float32(0.3345), np.float32(0.2808)] +2025-10-30 03:16:27.821198: Epoch time: 542.57 s +2025-10-30 03:16:27.822346: Yayy! New best EMA pseudo Dice: 0.7542999982833862 +2025-10-30 03:16:32.564055: +2025-10-30 03:16:32.573897: Epoch 154 +2025-10-30 03:16:32.575829: Current learning rate: 0.0086 +2025-10-30 03:25:31.934641: train_loss -0.3881 +2025-10-30 03:25:31.947593: val_loss -0.4172 +2025-10-30 03:25:31.949234: Pseudo dice [np.float32(0.9032), np.float32(0.5953), np.float32(0.6686), np.float32(0.59), np.float32(0.8382), np.float32(0.7588), np.float32(0.8582), np.float32(0.8665), np.float32(0.9719), np.float32(0.9724), np.float32(0.9588), np.float32(0.8222), np.float32(0.7392), np.float32(0.8133), np.float32(0.8931), np.float32(0.391), np.float32(0.3186)] +2025-10-30 03:25:31.950665: Epoch time: 539.38 s +2025-10-30 03:25:31.952563: Yayy! New best EMA pseudo Dice: 0.7551000118255615 +2025-10-30 03:25:37.235916: +2025-10-30 03:25:37.238107: Epoch 155 +2025-10-30 03:25:37.240123: Current learning rate: 0.00859 +2025-10-30 03:34:37.457779: train_loss -0.3776 +2025-10-30 03:34:37.469785: val_loss -0.4005 +2025-10-30 03:34:37.474612: Pseudo dice [np.float32(0.9218), np.float32(0.7163), np.float32(0.6197), np.float32(0.6112), np.float32(0.8342), np.float32(0.7504), np.float32(0.8484), np.float32(0.8471), np.float32(0.9517), np.float32(0.9574), np.float32(0.9572), np.float32(0.8115), np.float32(0.7465), np.float32(0.8288), np.float32(0.9416), np.float32(0.1316), np.float32(0.2532)] +2025-10-30 03:34:37.476538: Epoch time: 540.23 s +2025-10-30 03:34:39.753263: +2025-10-30 03:34:39.756707: Epoch 156 +2025-10-30 03:34:39.758823: Current learning rate: 0.00858 +2025-10-30 03:43:30.120796: train_loss -0.3301 +2025-10-30 03:43:30.159826: val_loss -0.3323 +2025-10-30 03:43:30.161412: Pseudo dice [np.float32(0.897), np.float32(0.6476), np.float32(0.6507), np.float32(0.6072), np.float32(0.7944), np.float32(0.7241), np.float32(0.8623), np.float32(0.8462), np.float32(0.9423), np.float32(0.9457), np.float32(0.9397), np.float32(0.8138), np.float32(0.6994), np.float32(0.8292), np.float32(0.9388), np.float32(0.3872), np.float32(0.2803)] +2025-10-30 03:43:30.162826: Epoch time: 530.38 s +2025-10-30 03:43:32.578794: +2025-10-30 03:43:32.583365: Epoch 157 +2025-10-30 03:43:32.584699: Current learning rate: 0.00858 +2025-10-30 03:52:24.502358: train_loss -0.3644 +2025-10-30 03:52:24.507653: val_loss -0.3539 +2025-10-30 03:52:24.508942: Pseudo dice [np.float32(0.9129), np.float32(0.729), np.float32(0.7493), np.float32(0.5649), np.float32(0.829), np.float32(0.738), np.float32(0.7593), np.float32(0.8613), np.float32(0.9207), np.float32(0.936), np.float32(0.9579), np.float32(0.7976), np.float32(0.704), np.float32(0.8462), np.float32(0.9373), np.float32(0.4515), np.float32(0.2255)] +2025-10-30 03:52:24.510085: Epoch time: 531.93 s +2025-10-30 03:52:26.774814: +2025-10-30 03:52:26.784613: Epoch 158 +2025-10-30 03:52:26.785882: Current learning rate: 0.00857 +2025-10-30 04:01:22.164149: train_loss -0.4059 +2025-10-30 04:01:22.188190: val_loss -0.4018 +2025-10-30 04:01:22.189594: Pseudo dice [np.float32(0.9289), np.float32(0.7295), np.float32(0.644), np.float32(0.5392), np.float32(0.8562), np.float32(0.7283), np.float32(0.8183), np.float32(0.8484), np.float32(0.9623), np.float32(0.9685), np.float32(0.959), np.float32(0.8193), np.float32(0.7416), np.float32(0.8258), np.float32(0.9446), np.float32(0.297), np.float32(0.2159)] +2025-10-30 04:01:22.192583: Epoch time: 535.39 s +2025-10-30 04:01:24.484253: +2025-10-30 04:01:24.485759: Epoch 159 +2025-10-30 04:01:24.487817: Current learning rate: 0.00856 +2025-10-30 04:10:30.524817: train_loss -0.4005 +2025-10-30 04:10:30.559922: val_loss -0.3795 +2025-10-30 04:10:30.562253: Pseudo dice [np.float32(0.9146), np.float32(0.7527), np.float32(0.6965), np.float32(0.5986), np.float32(0.8311), np.float32(0.7261), np.float32(0.8246), np.float32(0.8627), np.float32(0.9617), np.float32(0.9662), np.float32(0.9512), np.float32(0.8076), np.float32(0.7332), np.float32(0.8607), np.float32(0.934), np.float32(0.3545), np.float32(0.3578)] +2025-10-30 04:10:30.563763: Epoch time: 546.05 s +2025-10-30 04:10:30.565747: Yayy! New best EMA pseudo Dice: 0.756600022315979 +2025-10-30 04:10:35.958571: +2025-10-30 04:10:35.960001: Epoch 160 +2025-10-30 04:10:35.961302: Current learning rate: 0.00855 +2025-10-30 04:19:28.595146: train_loss -0.3953 +2025-10-30 04:19:28.609372: val_loss -0.3887 +2025-10-30 04:19:28.611401: Pseudo dice [np.float32(0.9323), np.float32(0.7279), np.float32(0.6893), np.float32(0.569), np.float32(0.8622), np.float32(0.7622), np.float32(0.8307), np.float32(0.8811), np.float32(0.9491), np.float32(0.9485), np.float32(0.9577), np.float32(0.818), np.float32(0.762), np.float32(0.8426), np.float32(0.9342), np.float32(0.399), np.float32(0.3151)] +2025-10-30 04:19:28.613261: Epoch time: 532.64 s +2025-10-30 04:19:28.614213: Yayy! New best EMA pseudo Dice: 0.7584999799728394 +2025-10-30 04:19:33.070145: +2025-10-30 04:19:33.073945: Epoch 161 +2025-10-30 04:19:33.075539: Current learning rate: 0.00854 +2025-10-30 04:28:24.767996: train_loss -0.3742 +2025-10-30 04:28:24.784198: val_loss -0.433 +2025-10-30 04:28:24.786052: Pseudo dice [np.float32(0.9349), np.float32(0.7627), np.float32(0.6868), np.float32(0.6106), np.float32(0.8509), np.float32(0.7668), np.float32(0.8124), np.float32(0.8635), np.float32(0.96), np.float32(0.937), np.float32(0.9509), np.float32(0.8181), np.float32(0.7693), np.float32(0.8546), np.float32(0.952), np.float32(0.2696), np.float32(0.1846)] +2025-10-30 04:28:24.787508: Epoch time: 531.7 s +2025-10-30 04:28:24.788796: Yayy! New best EMA pseudo Dice: 0.7590000033378601 +2025-10-30 04:28:29.250265: +2025-10-30 04:28:29.267835: Epoch 162 +2025-10-30 04:28:29.291566: Current learning rate: 0.00853 +2025-10-30 04:37:30.258862: train_loss -0.3702 +2025-10-30 04:37:30.312231: val_loss -0.3516 +2025-10-30 04:37:30.314427: Pseudo dice [np.float32(0.9052), np.float32(0.7523), np.float32(0.6823), np.float32(0.561), np.float32(0.8418), np.float32(0.7235), np.float32(0.6883), np.float32(0.8608), np.float32(0.9303), np.float32(0.9384), np.float32(0.9301), np.float32(0.7618), np.float32(0.7346), np.float32(0.8088), np.float32(0.8818), np.float32(0.3671), np.float32(0.3839)] +2025-10-30 04:37:30.342109: Epoch time: 541.01 s +2025-10-30 04:37:32.546171: +2025-10-30 04:37:32.567161: Epoch 163 +2025-10-30 04:37:32.572734: Current learning rate: 0.00852 +2025-10-30 04:46:31.284555: train_loss -0.3323 +2025-10-30 04:46:31.359200: val_loss -0.3901 +2025-10-30 04:46:31.360881: Pseudo dice [np.float32(0.8979), np.float32(0.7238), np.float32(0.6747), np.float32(0.5709), np.float32(0.8075), np.float32(0.7443), np.float32(0.8753), np.float32(0.8739), np.float32(0.9642), np.float32(0.9702), np.float32(0.9542), np.float32(0.7869), np.float32(0.7471), np.float32(0.7931), np.float32(0.9348), np.float32(0.3998), np.float32(0.3438)] +2025-10-30 04:46:31.362214: Epoch time: 538.74 s +2025-10-30 04:46:31.369372: Yayy! New best EMA pseudo Dice: 0.7591999769210815 +2025-10-30 04:46:35.861553: +2025-10-30 04:46:35.863581: Epoch 164 +2025-10-30 04:46:35.864978: Current learning rate: 0.00851 +2025-10-30 04:55:21.839222: train_loss -0.3465 +2025-10-30 04:55:21.865015: val_loss -0.369 +2025-10-30 04:55:21.867330: Pseudo dice [np.float32(0.9083), np.float32(0.7393), np.float32(0.7091), np.float32(0.6), np.float32(0.8695), np.float32(0.7174), np.float32(0.7957), np.float32(0.8649), np.float32(0.9316), np.float32(0.9251), np.float32(0.9509), np.float32(0.7916), np.float32(0.7505), np.float32(0.8218), np.float32(0.9552), np.float32(0.2898), np.float32(0.2446)] +2025-10-30 04:55:21.868831: Epoch time: 525.98 s +2025-10-30 04:55:40.031789: +2025-10-30 04:55:40.033431: Epoch 165 +2025-10-30 04:55:40.034668: Current learning rate: 0.0085 +2025-10-30 05:04:39.674389: train_loss -0.3855 +2025-10-30 05:04:39.685838: val_loss -0.4262 +2025-10-30 05:04:39.689160: Pseudo dice [np.float32(0.9243), np.float32(0.743), np.float32(0.6235), np.float32(0.637), np.float32(0.8481), np.float32(0.7577), np.float32(0.7887), np.float32(0.8693), np.float32(0.9628), np.float32(0.9668), np.float32(0.9604), np.float32(0.8315), np.float32(0.7414), np.float32(0.8557), np.float32(0.943), np.float32(0.3955), np.float32(0.3736)] +2025-10-30 05:04:39.690865: Epoch time: 539.65 s +2025-10-30 05:04:39.692308: Yayy! New best EMA pseudo Dice: 0.7608000040054321 +2025-10-30 05:04:44.297872: +2025-10-30 05:04:44.299611: Epoch 166 +2025-10-30 05:04:44.301363: Current learning rate: 0.00849 +2025-10-30 05:13:41.765299: train_loss -0.3857 +2025-10-30 05:13:41.794117: val_loss -0.3557 +2025-10-30 05:13:41.795303: Pseudo dice [np.float32(0.8861), np.float32(0.6719), np.float32(0.6581), np.float32(0.5325), np.float32(0.839), np.float32(0.7423), np.float32(0.7855), np.float32(0.8486), np.float32(0.9142), np.float32(0.894), np.float32(0.942), np.float32(0.8277), np.float32(0.7241), np.float32(0.8491), np.float32(0.9076), np.float32(0.2072), np.float32(0.1342)] +2025-10-30 05:13:41.796579: Epoch time: 537.47 s +2025-10-30 05:13:43.794982: +2025-10-30 05:13:43.797109: Epoch 167 +2025-10-30 05:13:43.801015: Current learning rate: 0.00848 +2025-10-30 05:22:48.038514: train_loss -0.3729 +2025-10-30 05:22:48.053316: val_loss -0.364 +2025-10-30 05:22:48.054364: Pseudo dice [np.float32(0.9058), np.float32(0.7489), np.float32(0.6828), np.float32(0.5363), np.float32(0.822), np.float32(0.7946), np.float32(0.822), np.float32(0.8641), np.float32(0.917), np.float32(0.9499), np.float32(0.9543), np.float32(0.8339), np.float32(0.718), np.float32(0.7897), np.float32(0.955), np.float32(0.3189), np.float32(0.2122)] +2025-10-30 05:22:48.056027: Epoch time: 544.25 s +2025-10-30 05:22:50.102215: +2025-10-30 05:22:50.103426: Epoch 168 +2025-10-30 05:22:50.104769: Current learning rate: 0.00847 +2025-10-30 05:31:49.687324: train_loss -0.3602 +2025-10-30 05:31:49.718354: val_loss -0.4139 +2025-10-30 05:31:49.719717: Pseudo dice [np.float32(0.9161), np.float32(0.7392), np.float32(0.7064), np.float32(0.6375), np.float32(0.8301), np.float32(0.7399), np.float32(0.8163), np.float32(0.8809), np.float32(0.9373), np.float32(0.9406), np.float32(0.9603), np.float32(0.7991), np.float32(0.7694), np.float32(0.8382), np.float32(0.877), np.float32(0.4171), np.float32(0.3992)] +2025-10-30 05:31:49.756691: Epoch time: 539.59 s +2025-10-30 05:31:52.092918: +2025-10-30 05:31:52.094834: Epoch 169 +2025-10-30 05:31:52.096053: Current learning rate: 0.00847 +2025-10-30 05:40:57.428942: train_loss -0.3498 +2025-10-30 05:40:57.464032: val_loss -0.3698 +2025-10-30 05:40:57.465334: Pseudo dice [np.float32(0.8764), np.float32(0.7041), np.float32(0.6724), np.float32(0.569), np.float32(0.857), np.float32(0.7286), np.float32(0.7256), np.float32(0.8632), np.float32(0.9569), np.float32(0.9586), np.float32(0.9515), np.float32(0.8329), np.float32(0.6772), np.float32(0.8449), np.float32(0.8706), np.float32(0.2862), np.float32(0.2883)] +2025-10-30 05:40:57.466526: Epoch time: 545.35 s +2025-10-30 05:40:59.739127: +2025-10-30 05:40:59.740630: Epoch 170 +2025-10-30 05:40:59.742165: Current learning rate: 0.00846 +2025-10-30 05:49:49.778836: train_loss -0.4038 +2025-10-30 05:49:49.814742: val_loss -0.4408 +2025-10-30 05:49:49.816610: Pseudo dice [np.float32(0.9308), np.float32(0.7388), np.float32(0.653), np.float32(0.6002), np.float32(0.8275), np.float32(0.7583), np.float32(0.8002), np.float32(0.8658), np.float32(0.9695), np.float32(0.963), np.float32(0.9519), np.float32(0.8306), np.float32(0.744), np.float32(0.8364), np.float32(0.9356), np.float32(0.3933), np.float32(0.3274)] +2025-10-30 05:49:49.818492: Epoch time: 530.04 s +2025-10-30 05:49:52.450898: +2025-10-30 05:49:52.452387: Epoch 171 +2025-10-30 05:49:52.454013: Current learning rate: 0.00845 +2025-10-30 05:59:05.142444: train_loss -0.3984 +2025-10-30 05:59:05.184005: val_loss -0.3776 +2025-10-30 05:59:05.185412: Pseudo dice [np.float32(0.9106), np.float32(0.7164), np.float32(0.7008), np.float32(0.5259), np.float32(0.8561), np.float32(0.7382), np.float32(0.8525), np.float32(0.8871), np.float32(0.9618), np.float32(0.9668), np.float32(0.9622), np.float32(0.8152), np.float32(0.7055), np.float32(0.8452), np.float32(0.9423), np.float32(0.3229), np.float32(0.3037)] +2025-10-30 05:59:05.186919: Epoch time: 552.7 s +2025-10-30 05:59:07.386153: +2025-10-30 05:59:07.387884: Epoch 172 +2025-10-30 05:59:07.389118: Current learning rate: 0.00844 +2025-10-30 06:08:05.391641: train_loss -0.402 +2025-10-30 06:08:05.423008: val_loss -0.38 +2025-10-30 06:08:05.424557: Pseudo dice [np.float32(0.917), np.float32(0.7252), np.float32(0.647), np.float32(0.5875), np.float32(0.8475), np.float32(0.7917), np.float32(0.7776), np.float32(0.8641), np.float32(0.9389), np.float32(0.9475), np.float32(0.9498), np.float32(0.8041), np.float32(0.7533), np.float32(0.8446), np.float32(0.9285), np.float32(0.3388), np.float32(0.3289)] +2025-10-30 06:08:05.426303: Epoch time: 538.01 s +2025-10-30 06:08:07.802934: +2025-10-30 06:08:07.804235: Epoch 173 +2025-10-30 06:08:07.805640: Current learning rate: 0.00843 +2025-10-30 06:17:03.434910: train_loss -0.398 +2025-10-30 06:17:03.478105: val_loss -0.4001 +2025-10-30 06:17:03.479854: Pseudo dice [np.float32(0.9036), np.float32(0.7231), np.float32(0.669), np.float32(0.548), np.float32(0.8546), np.float32(0.7889), np.float32(0.8074), np.float32(0.8612), np.float32(0.9297), np.float32(0.9558), np.float32(0.9651), np.float32(0.8039), np.float32(0.709), np.float32(0.853), np.float32(0.9589), np.float32(0.2802), np.float32(0.2262)] +2025-10-30 06:17:03.481583: Epoch time: 535.64 s +2025-10-30 06:17:05.737871: +2025-10-30 06:17:05.739176: Epoch 174 +2025-10-30 06:17:05.740857: Current learning rate: 0.00842 +2025-10-30 06:26:06.319244: train_loss -0.3953 +2025-10-30 06:26:06.330607: val_loss -0.3623 +2025-10-30 06:26:06.332233: Pseudo dice [np.float32(0.9312), np.float32(0.3164), np.float32(0.6394), np.float32(0.5502), np.float32(0.8356), np.float32(0.7463), np.float32(0.8389), np.float32(0.8514), np.float32(0.949), np.float32(0.9724), np.float32(0.963), np.float32(0.8347), np.float32(0.7901), np.float32(0.8209), np.float32(0.944), np.float32(0.2943), np.float32(0.3136)] +2025-10-30 06:26:06.333442: Epoch time: 540.59 s +2025-10-30 06:26:08.909537: +2025-10-30 06:26:08.914303: Epoch 175 +2025-10-30 06:26:08.915522: Current learning rate: 0.00841 +2025-10-30 06:35:21.996654: train_loss -0.3978 +2025-10-30 06:35:22.048067: val_loss -0.4058 +2025-10-30 06:35:22.050147: Pseudo dice [np.float32(0.9112), np.float32(0.7462), np.float32(0.6818), np.float32(0.5814), np.float32(0.8425), np.float32(0.7113), np.float32(0.7445), np.float32(0.8768), np.float32(0.9744), np.float32(0.9649), np.float32(0.9539), np.float32(0.8067), np.float32(0.7175), np.float32(0.8328), np.float32(0.9589), np.float32(0.2802), np.float32(0.1577)] +2025-10-30 06:35:22.051819: Epoch time: 553.1 s +2025-10-30 06:35:24.235404: +2025-10-30 06:35:24.236708: Epoch 176 +2025-10-30 06:35:24.238077: Current learning rate: 0.0084 +2025-10-30 06:44:19.775816: train_loss -0.4055 +2025-10-30 06:44:19.815899: val_loss -0.3789 +2025-10-30 06:44:19.818583: Pseudo dice [np.float32(0.8988), np.float32(0.7437), np.float32(0.6483), np.float32(0.5974), np.float32(0.8383), np.float32(0.7264), np.float32(0.7903), np.float32(0.8532), np.float32(0.9158), np.float32(0.9012), np.float32(0.9388), np.float32(0.833), np.float32(0.7301), np.float32(0.8702), np.float32(0.8729), np.float32(0.3381), np.float32(0.2419)] +2025-10-30 06:44:19.819649: Epoch time: 535.54 s +2025-10-30 06:44:21.950713: +2025-10-30 06:44:21.954625: Epoch 177 +2025-10-30 06:44:21.956394: Current learning rate: 0.00839 +2025-10-30 06:53:12.485862: train_loss -0.4055 +2025-10-30 06:53:12.519498: val_loss -0.4119 +2025-10-30 06:53:12.522458: Pseudo dice [np.float32(0.8904), np.float32(0.5245), np.float32(0.6987), np.float32(0.6009), np.float32(0.8337), np.float32(0.7621), np.float32(0.8693), np.float32(0.8752), np.float32(0.9569), np.float32(0.9786), np.float32(0.9666), np.float32(0.8115), np.float32(0.7425), np.float32(0.8373), np.float32(0.9599), np.float32(0.2166), np.float32(0.2452)] +2025-10-30 06:53:12.523909: Epoch time: 530.54 s +2025-10-30 06:53:14.774647: +2025-10-30 06:53:14.776146: Epoch 178 +2025-10-30 06:53:14.777429: Current learning rate: 0.00838 +2025-10-30 07:02:13.333344: train_loss -0.3828 +2025-10-30 07:02:13.354538: val_loss -0.3154 +2025-10-30 07:02:13.356322: Pseudo dice [np.float32(0.9009), np.float32(0.7298), np.float32(0.726), np.float32(0.532), np.float32(0.8293), np.float32(0.6657), np.float32(0.8443), np.float32(0.8262), np.float32(0.9069), np.float32(0.916), np.float32(0.9345), np.float32(0.7613), np.float32(0.7303), np.float32(0.8342), np.float32(0.859), np.float32(0.1425), np.float32(0.219)] +2025-10-30 07:02:13.362791: Epoch time: 538.56 s +2025-10-30 07:02:15.392995: +2025-10-30 07:02:15.394570: Epoch 179 +2025-10-30 07:02:15.396262: Current learning rate: 0.00837 +2025-10-30 07:11:12.765778: train_loss -0.3094 +2025-10-30 07:11:12.790032: val_loss -0.3585 +2025-10-30 07:11:12.791492: Pseudo dice [np.float32(0.9108), np.float32(0.7188), np.float32(0.6066), np.float32(0.5768), np.float32(0.8495), np.float32(0.7366), np.float32(0.7814), np.float32(0.8351), np.float32(0.9497), np.float32(0.9285), np.float32(0.9437), np.float32(0.7786), np.float32(0.7542), np.float32(0.8323), np.float32(0.9093), np.float32(0.2254), np.float32(0.3069)] +2025-10-30 07:11:12.792901: Epoch time: 537.38 s +2025-10-30 07:11:15.076207: +2025-10-30 07:11:15.077598: Epoch 180 +2025-10-30 07:11:15.079067: Current learning rate: 0.00836 +2025-10-30 07:20:08.561731: train_loss -0.3323 +2025-10-30 07:20:08.591965: val_loss -0.3515 +2025-10-30 07:20:08.594226: Pseudo dice [np.float32(0.8991), np.float32(0.7442), np.float32(0.6824), np.float32(0.5721), np.float32(0.8204), np.float32(0.7235), np.float32(0.7716), np.float32(0.8568), np.float32(0.9451), np.float32(0.9328), np.float32(0.9292), np.float32(0.7907), np.float32(0.7433), np.float32(0.7591), np.float32(0.8926), np.float32(0.3322), np.float32(0.2469)] +2025-10-30 07:20:08.596193: Epoch time: 533.49 s +2025-10-30 07:20:10.811154: +2025-10-30 07:20:10.812819: Epoch 181 +2025-10-30 07:20:10.814188: Current learning rate: 0.00836 +2025-10-30 07:29:16.404070: train_loss -0.3492 +2025-10-30 07:29:16.410362: val_loss -0.3689 +2025-10-30 07:29:16.411977: Pseudo dice [np.float32(0.9137), np.float32(0.722), np.float32(0.6778), np.float32(0.5904), np.float32(0.8267), np.float32(0.7439), np.float32(0.7887), np.float32(0.8488), np.float32(0.9345), np.float32(0.9319), np.float32(0.9491), np.float32(0.7912), np.float32(0.7741), np.float32(0.821), np.float32(0.8924), np.float32(0.2839), np.float32(0.2658)] +2025-10-30 07:29:16.413208: Epoch time: 545.6 s +2025-10-30 07:29:18.497092: +2025-10-30 07:29:18.503920: Epoch 182 +2025-10-30 07:29:18.505807: Current learning rate: 0.00835 +2025-10-30 07:38:13.020854: train_loss -0.3534 +2025-10-30 07:38:13.060359: val_loss -0.3577 +2025-10-30 07:38:13.062410: Pseudo dice [np.float32(0.915), np.float32(0.7455), np.float32(0.6593), np.float32(0.6278), np.float32(0.8219), np.float32(0.7336), np.float32(0.7635), np.float32(0.8564), np.float32(0.9309), np.float32(0.9145), np.float32(0.9453), np.float32(0.8021), np.float32(0.7097), np.float32(0.8168), np.float32(0.8891), np.float32(0.4124), np.float32(0.3436)] +2025-10-30 07:38:13.063687: Epoch time: 534.53 s +2025-10-30 07:38:15.313060: +2025-10-30 07:38:15.314283: Epoch 183 +2025-10-30 07:38:15.315763: Current learning rate: 0.00834 +2025-10-30 07:46:57.803777: train_loss -0.3235 +2025-10-30 07:46:57.828886: val_loss -0.3593 +2025-10-30 07:46:57.830369: Pseudo dice [np.float32(0.9191), np.float32(0.7468), np.float32(0.6842), np.float32(0.5353), np.float32(0.8176), np.float32(0.7477), np.float32(0.7972), np.float32(0.8736), np.float32(0.9601), np.float32(0.9625), np.float32(0.9527), np.float32(0.7504), np.float32(0.7388), np.float32(0.8063), np.float32(0.9385), np.float32(0.141), np.float32(0.2482)] +2025-10-30 07:46:57.832012: Epoch time: 522.5 s +2025-10-30 07:46:59.994067: +2025-10-30 07:46:59.995882: Epoch 184 +2025-10-30 07:46:59.997229: Current learning rate: 0.00833 +2025-10-30 07:55:57.215646: train_loss -0.3526 +2025-10-30 07:55:57.248761: val_loss -0.3877 +2025-10-30 07:55:57.262300: Pseudo dice [np.float32(0.8993), np.float32(0.7275), np.float32(0.6694), np.float32(0.6305), np.float32(0.8533), np.float32(0.75), np.float32(0.8669), np.float32(0.8672), np.float32(0.9702), np.float32(0.9253), np.float32(0.9519), np.float32(0.8065), np.float32(0.7468), np.float32(0.86), np.float32(0.952), np.float32(0.4955), np.float32(0.3464)] +2025-10-30 07:55:57.264161: Epoch time: 537.23 s +2025-10-30 07:55:59.475969: +2025-10-30 07:55:59.479251: Epoch 185 +2025-10-30 07:55:59.481785: Current learning rate: 0.00832 +2025-10-30 08:04:55.649059: train_loss -0.3796 +2025-10-30 08:04:55.659028: val_loss -0.3772 +2025-10-30 08:04:55.660855: Pseudo dice [np.float32(0.8855), np.float32(0.701), np.float32(0.6687), np.float32(0.6121), np.float32(0.8159), np.float32(0.7379), np.float32(0.8266), np.float32(0.8651), np.float32(0.9427), np.float32(0.9355), np.float32(0.9582), np.float32(0.8082), np.float32(0.7412), np.float32(0.8335), np.float32(0.9275), np.float32(0.2239), np.float32(0.2009)] +2025-10-30 08:04:55.662775: Epoch time: 536.18 s +2025-10-30 08:04:57.761655: +2025-10-30 08:04:57.765324: Epoch 186 +2025-10-30 08:04:57.772586: Current learning rate: 0.00831 +2025-10-30 08:14:07.370117: train_loss -0.3529 +2025-10-30 08:14:07.386953: val_loss -0.3525 +2025-10-30 08:14:07.389067: Pseudo dice [np.float32(0.894), np.float32(0.6289), np.float32(0.6294), np.float32(0.6231), np.float32(0.8471), np.float32(0.7362), np.float32(0.7513), np.float32(0.8583), np.float32(0.9235), np.float32(0.9282), np.float32(0.9311), np.float32(0.7822), np.float32(0.7142), np.float32(0.8439), np.float32(0.7969), np.float32(0.2961), np.float32(0.3083)] +2025-10-30 08:14:07.393748: Epoch time: 549.61 s +2025-10-30 08:14:09.396314: +2025-10-30 08:14:09.397726: Epoch 187 +2025-10-30 08:14:09.398962: Current learning rate: 0.0083 +2025-10-30 08:23:04.604087: train_loss -0.3576 +2025-10-30 08:23:04.615387: val_loss -0.3881 +2025-10-30 08:23:04.616996: Pseudo dice [np.float32(0.901), np.float32(0.7213), np.float32(0.6124), np.float32(0.5656), np.float32(0.8229), np.float32(0.7263), np.float32(0.8656), np.float32(0.8326), np.float32(0.9639), np.float32(0.9756), np.float32(0.9512), np.float32(0.8052), np.float32(0.7031), np.float32(0.8266), np.float32(0.9469), np.float32(0.428), np.float32(0.2865)] +2025-10-30 08:23:04.618316: Epoch time: 535.21 s +2025-10-30 08:23:22.565795: +2025-10-30 08:23:22.567493: Epoch 188 +2025-10-30 08:23:22.569327: Current learning rate: 0.00829 +2025-10-30 08:32:13.645048: train_loss -0.3687 +2025-10-30 08:32:13.671390: val_loss -0.3739 +2025-10-30 08:32:13.679151: Pseudo dice [np.float32(0.935), np.float32(0.6869), np.float32(0.6926), np.float32(0.5723), np.float32(0.8229), np.float32(0.7969), np.float32(0.8694), np.float32(0.8633), np.float32(0.976), np.float32(0.9741), np.float32(0.9551), np.float32(0.8149), np.float32(0.7366), np.float32(0.8126), np.float32(0.9388), np.float32(0.3409), np.float32(0.2701)] +2025-10-30 08:32:13.681169: Epoch time: 531.08 s +2025-10-30 08:32:15.729513: +2025-10-30 08:32:15.736709: Epoch 189 +2025-10-30 08:32:15.737851: Current learning rate: 0.00828 +2025-10-30 08:41:11.770571: train_loss -0.3823 +2025-10-30 08:41:11.815875: val_loss -0.3925 +2025-10-30 08:41:11.820150: Pseudo dice [np.float32(0.9157), np.float32(0.6989), np.float32(0.6717), np.float32(0.5947), np.float32(0.8318), np.float32(0.7418), np.float32(0.7425), np.float32(0.8598), np.float32(0.9656), np.float32(0.9661), np.float32(0.9426), np.float32(0.8118), np.float32(0.7476), np.float32(0.8585), np.float32(0.962), np.float32(0.3577), np.float32(0.3028)] +2025-10-30 08:41:11.822167: Epoch time: 536.05 s +2025-10-30 08:41:13.958148: +2025-10-30 08:41:13.959527: Epoch 190 +2025-10-30 08:41:13.960684: Current learning rate: 0.00827 +2025-10-30 08:50:15.355632: train_loss -0.3735 +2025-10-30 08:50:15.405195: val_loss -0.3752 +2025-10-30 08:50:15.412591: Pseudo dice [np.float32(0.8785), np.float32(0.7239), np.float32(0.6615), np.float32(0.5653), np.float32(0.8624), np.float32(0.7588), np.float32(0.8228), np.float32(0.868), np.float32(0.9389), np.float32(0.9365), np.float32(0.9515), np.float32(0.8091), np.float32(0.7089), np.float32(0.8575), np.float32(0.872), np.float32(0.3382), np.float32(0.2723)] +2025-10-30 08:50:15.439274: Epoch time: 541.41 s +2025-10-30 08:50:17.623448: +2025-10-30 08:50:17.624938: Epoch 191 +2025-10-30 08:50:17.626343: Current learning rate: 0.00826 +2025-10-30 08:59:12.635772: train_loss -0.3906 +2025-10-30 08:59:12.685293: val_loss -0.4112 +2025-10-30 08:59:12.687105: Pseudo dice [np.float32(0.9276), np.float32(0.7637), np.float32(0.6898), np.float32(0.6128), np.float32(0.8433), np.float32(0.7384), np.float32(0.8261), np.float32(0.8469), np.float32(0.9366), np.float32(0.9444), np.float32(0.9646), np.float32(0.8063), np.float32(0.6929), np.float32(0.8438), np.float32(0.9591), np.float32(0.1058), np.float32(0.0898)] +2025-10-30 08:59:12.689025: Epoch time: 535.02 s +2025-10-30 08:59:14.875052: +2025-10-30 08:59:14.876350: Epoch 192 +2025-10-30 08:59:14.877758: Current learning rate: 0.00825 +2025-10-30 09:08:15.230777: train_loss -0.4093 +2025-10-30 09:08:15.255373: val_loss -0.3937 +2025-10-30 09:08:15.257770: Pseudo dice [np.float32(0.9236), np.float32(0.7257), np.float32(0.685), np.float32(0.6131), np.float32(0.8536), np.float32(0.7065), np.float32(0.7949), np.float32(0.8572), np.float32(0.9405), np.float32(0.9477), np.float32(0.9616), np.float32(0.8312), np.float32(0.7722), np.float32(0.8541), np.float32(0.9461), np.float32(0.302), np.float32(0.3574)] +2025-10-30 09:08:15.262421: Epoch time: 540.36 s +2025-10-30 09:08:17.937034: +2025-10-30 09:08:17.940662: Epoch 193 +2025-10-30 09:08:17.942676: Current learning rate: 0.00824 +2025-10-30 09:17:24.892540: train_loss -0.3963 +2025-10-30 09:17:24.926998: val_loss -0.3808 +2025-10-30 09:17:24.928160: Pseudo dice [np.float32(0.92), np.float32(0.7561), np.float32(0.718), np.float32(0.6137), np.float32(0.8335), np.float32(0.7698), np.float32(0.8064), np.float32(0.8732), np.float32(0.9085), np.float32(0.9347), np.float32(0.9522), np.float32(0.8164), np.float32(0.764), np.float32(0.8528), np.float32(0.8926), np.float32(0.4156), np.float32(0.2785)] +2025-10-30 09:17:24.932327: Epoch time: 546.96 s +2025-10-30 09:17:27.108237: +2025-10-30 09:17:27.114673: Epoch 194 +2025-10-30 09:17:27.120695: Current learning rate: 0.00824 +2025-10-30 09:26:35.935179: train_loss -0.4014 +2025-10-30 09:26:35.983188: val_loss -0.4092 +2025-10-30 09:26:35.984589: Pseudo dice [np.float32(0.911), np.float32(0.7227), np.float32(0.6688), np.float32(0.5428), np.float32(0.839), np.float32(0.7557), np.float32(0.8499), np.float32(0.8541), np.float32(0.9682), np.float32(0.9602), np.float32(0.9553), np.float32(0.8328), np.float32(0.7401), np.float32(0.8467), np.float32(0.9474), np.float32(0.3265), np.float32(0.137)] +2025-10-30 09:26:35.987273: Epoch time: 548.83 s +2025-10-30 09:26:38.136961: +2025-10-30 09:26:38.139784: Epoch 195 +2025-10-30 09:26:38.141233: Current learning rate: 0.00823 +2025-10-30 09:35:27.396162: train_loss -0.3956 +2025-10-30 09:35:27.470087: val_loss -0.4489 +2025-10-30 09:35:27.472176: Pseudo dice [np.float32(0.9249), np.float32(0.7596), np.float32(0.6628), np.float32(0.6092), np.float32(0.8596), np.float32(0.7671), np.float32(0.8438), np.float32(0.8648), np.float32(0.9699), np.float32(0.9581), np.float32(0.9592), np.float32(0.8118), np.float32(0.779), np.float32(0.8379), np.float32(0.9577), np.float32(0.3142), np.float32(0.2986)] +2025-10-30 09:35:27.473825: Epoch time: 529.26 s +2025-10-30 09:35:29.779372: +2025-10-30 09:35:29.780816: Epoch 196 +2025-10-30 09:35:29.782177: Current learning rate: 0.00822 +2025-10-30 09:44:36.318940: train_loss -0.3833 +2025-10-30 09:44:36.364379: val_loss -0.4363 +2025-10-30 09:44:36.365903: Pseudo dice [np.float32(0.9051), np.float32(0.7525), np.float32(0.7169), np.float32(0.5738), np.float32(0.8552), np.float32(0.7385), np.float32(0.8382), np.float32(0.8582), np.float32(0.9674), np.float32(0.9566), np.float32(0.9567), np.float32(0.8101), np.float32(0.7557), np.float32(0.8679), np.float32(0.9307), np.float32(0.3459), np.float32(0.4367)] +2025-10-30 09:44:36.367303: Epoch time: 546.55 s +2025-10-30 09:44:38.798483: +2025-10-30 09:44:38.800325: Epoch 197 +2025-10-30 09:44:38.801861: Current learning rate: 0.00821 +2025-10-30 09:53:43.084790: train_loss -0.4024 +2025-10-30 09:53:43.103528: val_loss -0.3664 +2025-10-30 09:53:43.105447: Pseudo dice [np.float32(0.8999), np.float32(0.7366), np.float32(0.6919), np.float32(0.6695), np.float32(0.8353), np.float32(0.7826), np.float32(0.7494), np.float32(0.8577), np.float32(0.9489), np.float32(0.954), np.float32(0.9447), np.float32(0.842), np.float32(0.7667), np.float32(0.8618), np.float32(0.8567), np.float32(0.374), np.float32(0.3812)] +2025-10-30 09:53:43.107222: Epoch time: 544.29 s +2025-10-30 09:53:43.109874: Yayy! New best EMA pseudo Dice: 0.761900007724762 +2025-10-30 09:53:48.705242: +2025-10-30 09:53:48.712508: Epoch 198 +2025-10-30 09:53:48.714277: Current learning rate: 0.0082 +2025-10-30 10:02:32.005369: train_loss -0.3957 +2025-10-30 10:02:32.046278: val_loss -0.3724 +2025-10-30 10:02:32.047556: Pseudo dice [np.float32(0.9041), np.float32(0.6856), np.float32(0.6918), np.float32(0.536), np.float32(0.8371), np.float32(0.7345), np.float32(0.867), np.float32(0.8555), np.float32(0.9326), np.float32(0.9214), np.float32(0.9634), np.float32(0.7946), np.float32(0.7329), np.float32(0.8596), np.float32(0.9451), np.float32(0.2102), np.float32(0.2212)] +2025-10-30 10:02:32.049033: Epoch time: 523.3 s +2025-10-30 10:02:34.204360: +2025-10-30 10:02:34.207219: Epoch 199 +2025-10-30 10:02:34.209546: Current learning rate: 0.00819 +2025-10-30 10:11:29.753206: train_loss -0.3869 +2025-10-30 10:11:29.767154: val_loss -0.3565 +2025-10-30 10:11:29.768794: Pseudo dice [np.float32(0.9241), np.float32(0.7308), np.float32(0.7121), np.float32(0.5875), np.float32(0.8033), np.float32(0.7019), np.float32(0.839), np.float32(0.8627), np.float32(0.9184), np.float32(0.9168), np.float32(0.9548), np.float32(0.8097), np.float32(0.7835), np.float32(0.7831), np.float32(0.9254), np.float32(0.3033), np.float32(0.2105)] +2025-10-30 10:11:29.770205: Epoch time: 535.55 s +2025-10-30 10:11:34.888840: +2025-10-30 10:11:34.890726: Epoch 200 +2025-10-30 10:11:34.899092: Current learning rate: 0.00818 +2025-10-30 10:20:41.698739: train_loss -0.3715 +2025-10-30 10:20:41.705928: val_loss -0.3951 +2025-10-30 10:20:41.707728: Pseudo dice [np.float32(0.9128), np.float32(0.7658), np.float32(0.7127), np.float32(0.5884), np.float32(0.8308), np.float32(0.7416), np.float32(0.8372), np.float32(0.8706), np.float32(0.9646), np.float32(0.9688), np.float32(0.9555), np.float32(0.8371), np.float32(0.7725), np.float32(0.8314), np.float32(0.9329), np.float32(0.3021), np.float32(0.2333)] +2025-10-30 10:20:41.709544: Epoch time: 546.81 s +2025-10-30 10:20:44.009076: +2025-10-30 10:20:44.016793: Epoch 201 +2025-10-30 10:20:44.018783: Current learning rate: 0.00817 +2025-10-30 10:29:42.894892: train_loss -0.3682 +2025-10-30 10:29:42.947094: val_loss -0.3674 +2025-10-30 10:29:42.949563: Pseudo dice [np.float32(0.8682), np.float32(0.7318), np.float32(0.6818), np.float32(0.569), np.float32(0.8361), np.float32(0.7346), np.float32(0.8517), np.float32(0.8181), np.float32(0.966), np.float32(0.9507), np.float32(0.9531), np.float32(0.8253), np.float32(0.7429), np.float32(0.85), np.float32(0.9483), np.float32(0.2742), np.float32(0.1295)] +2025-10-30 10:29:42.950647: Epoch time: 538.89 s +2025-10-30 10:29:45.438993: +2025-10-30 10:29:45.443491: Epoch 202 +2025-10-30 10:29:45.449992: Current learning rate: 0.00816 +2025-10-30 10:38:43.530681: train_loss -0.3534 +2025-10-30 10:38:43.545249: val_loss -0.3891 +2025-10-30 10:38:43.547401: Pseudo dice [np.float32(0.919), np.float32(0.7409), np.float32(0.7304), np.float32(0.5643), np.float32(0.8584), np.float32(0.7337), np.float32(0.8607), np.float32(0.8257), np.float32(0.9615), np.float32(0.9523), np.float32(0.9547), np.float32(0.788), np.float32(0.7394), np.float32(0.8131), np.float32(0.9298), np.float32(0.3097), np.float32(0.2371)] +2025-10-30 10:38:43.552935: Epoch time: 538.1 s +2025-10-30 10:38:46.054406: +2025-10-30 10:38:46.056026: Epoch 203 +2025-10-30 10:38:46.057260: Current learning rate: 0.00815 +2025-10-30 10:47:44.761429: train_loss -0.3745 +2025-10-30 10:47:44.818147: val_loss -0.381 +2025-10-30 10:47:44.825956: Pseudo dice [np.float32(0.9095), np.float32(0.7486), np.float32(0.6639), np.float32(0.5735), np.float32(0.8256), np.float32(0.74), np.float32(0.8385), np.float32(0.86), np.float32(0.9118), np.float32(0.9132), np.float32(0.9663), np.float32(0.806), np.float32(0.7609), np.float32(0.8108), np.float32(0.9414), np.float32(0.3001), np.float32(0.2099)] +2025-10-30 10:47:44.827047: Epoch time: 538.71 s +2025-10-30 10:47:47.017877: +2025-10-30 10:47:47.019101: Epoch 204 +2025-10-30 10:47:47.020197: Current learning rate: 0.00814 +2025-10-30 10:56:48.242408: train_loss -0.3803 +2025-10-30 10:56:48.277496: val_loss -0.367 +2025-10-30 10:56:48.278911: Pseudo dice [np.float32(0.88), np.float32(0.7123), np.float32(0.6832), np.float32(0.5344), np.float32(0.8109), np.float32(0.7092), np.float32(0.8639), np.float32(0.8379), np.float32(0.9797), np.float32(0.9795), np.float32(0.9551), np.float32(0.8153), np.float32(0.7633), np.float32(0.8388), np.float32(0.9401), np.float32(0.4417), np.float32(0.3927)] +2025-10-30 10:56:48.280582: Epoch time: 541.23 s +2025-10-30 10:56:50.570726: +2025-10-30 10:56:50.573417: Epoch 205 +2025-10-30 10:56:50.574786: Current learning rate: 0.00813 +2025-10-30 11:05:47.020362: train_loss -0.3566 +2025-10-30 11:05:47.085162: val_loss -0.3938 +2025-10-30 11:05:47.086967: Pseudo dice [np.float32(0.8976), np.float32(0.6605), np.float32(0.6234), np.float32(0.5213), np.float32(0.8397), np.float32(0.7801), np.float32(0.7757), np.float32(0.8557), np.float32(0.9446), np.float32(0.9446), np.float32(0.954), np.float32(0.7785), np.float32(0.721), np.float32(0.8324), np.float32(0.9012), np.float32(0.218), np.float32(0.2221)] +2025-10-30 11:05:47.088476: Epoch time: 536.45 s +2025-10-30 11:05:49.185755: +2025-10-30 11:05:49.188371: Epoch 206 +2025-10-30 11:05:49.190727: Current learning rate: 0.00813 +2025-10-30 11:14:55.622915: train_loss -0.3713 +2025-10-30 11:14:55.635539: val_loss -0.3908 +2025-10-30 11:14:55.637928: Pseudo dice [np.float32(0.9287), np.float32(0.7309), np.float32(0.7032), np.float32(0.6295), np.float32(0.8051), np.float32(0.7757), np.float32(0.7837), np.float32(0.858), np.float32(0.9397), np.float32(0.9586), np.float32(0.9587), np.float32(0.8061), np.float32(0.7775), np.float32(0.8319), np.float32(0.942), np.float32(0.3224), np.float32(0.3741)] +2025-10-30 11:14:55.639253: Epoch time: 546.44 s +2025-10-30 11:14:58.154526: +2025-10-30 11:14:58.158780: Epoch 207 +2025-10-30 11:14:58.160023: Current learning rate: 0.00812 +2025-10-30 11:23:56.251785: train_loss -0.3749 +2025-10-30 11:23:56.325462: val_loss -0.3755 +2025-10-30 11:23:56.326818: Pseudo dice [np.float32(0.9124), np.float32(0.6928), np.float32(0.6345), np.float32(0.6), np.float32(0.8273), np.float32(0.7667), np.float32(0.7932), np.float32(0.8499), np.float32(0.9563), np.float32(0.9543), np.float32(0.9504), np.float32(0.8093), np.float32(0.7389), np.float32(0.84), np.float32(0.9267), np.float32(0.359), np.float32(0.2843)] +2025-10-30 11:23:56.328551: Epoch time: 538.1 s +2025-10-30 11:23:58.401458: +2025-10-30 11:23:58.403179: Epoch 208 +2025-10-30 11:23:58.404456: Current learning rate: 0.00811 +2025-10-30 11:32:54.988302: train_loss -0.3744 +2025-10-30 11:32:55.021443: val_loss -0.4184 +2025-10-30 11:32:55.022854: Pseudo dice [np.float32(0.9188), np.float32(0.6908), np.float32(0.6974), np.float32(0.6011), np.float32(0.8789), np.float32(0.7743), np.float32(0.8171), np.float32(0.87), np.float32(0.9648), np.float32(0.9646), np.float32(0.9608), np.float32(0.8394), np.float32(0.7673), np.float32(0.8646), np.float32(0.9469), np.float32(0.1867), np.float32(0.1495)] +2025-10-30 11:32:55.024030: Epoch time: 536.59 s +2025-10-30 11:32:57.141767: +2025-10-30 11:32:57.156763: Epoch 209 +2025-10-30 11:32:57.158260: Current learning rate: 0.0081 +2025-10-30 11:41:38.901696: train_loss -0.3986 +2025-10-30 11:41:38.908118: val_loss -0.3937 +2025-10-30 11:41:38.910579: Pseudo dice [np.float32(0.8997), np.float32(0.7386), np.float32(0.7123), np.float32(0.6682), np.float32(0.8215), np.float32(0.7223), np.float32(0.8876), np.float32(0.8816), np.float32(0.8931), np.float32(0.9613), np.float32(0.9637), np.float32(0.8063), np.float32(0.7233), np.float32(0.8291), np.float32(0.947), np.float32(0.2929), np.float32(0.2727)] +2025-10-30 11:41:38.912302: Epoch time: 521.77 s +2025-10-30 11:41:40.935779: +2025-10-30 11:41:40.938053: Epoch 210 +2025-10-30 11:41:40.940085: Current learning rate: 0.00809 +2025-10-30 11:50:43.122071: train_loss -0.4009 +2025-10-30 11:50:43.142828: val_loss -0.3936 +2025-10-30 11:50:43.150989: Pseudo dice [np.float32(0.9108), np.float32(0.7322), np.float32(0.7244), np.float32(0.5517), np.float32(0.8283), np.float32(0.7166), np.float32(0.8198), np.float32(0.8385), np.float32(0.8791), np.float32(0.8383), np.float32(0.9434), np.float32(0.8273), np.float32(0.7185), np.float32(0.8408), np.float32(0.9057), np.float32(0.3302), np.float32(0.2638)] +2025-10-30 11:50:43.153782: Epoch time: 542.19 s +2025-10-30 11:51:01.450861: +2025-10-30 11:51:01.452358: Epoch 211 +2025-10-30 11:51:01.454076: Current learning rate: 0.00808 +2025-10-30 11:59:47.601816: train_loss -0.3469 +2025-10-30 11:59:47.629958: val_loss -0.4009 +2025-10-30 11:59:47.631292: Pseudo dice [np.float32(0.9381), np.float32(0.7094), np.float32(0.6539), np.float32(0.5665), np.float32(0.854), np.float32(0.739), np.float32(0.8366), np.float32(0.88), np.float32(0.9614), np.float32(0.9522), np.float32(0.9335), np.float32(0.8256), np.float32(0.7573), np.float32(0.8172), np.float32(0.886), np.float32(0.2492), np.float32(0.2176)] +2025-10-30 11:59:47.633212: Epoch time: 526.16 s +2025-10-30 11:59:49.624520: +2025-10-30 11:59:49.626313: Epoch 212 +2025-10-30 11:59:49.627645: Current learning rate: 0.00807 +2025-10-30 12:08:56.679488: train_loss -0.3699 +2025-10-30 12:08:56.693552: val_loss -0.3958 +2025-10-30 12:08:56.694893: Pseudo dice [np.float32(0.9061), np.float32(0.744), np.float32(0.7356), np.float32(0.5174), np.float32(0.8527), np.float32(0.7714), np.float32(0.8234), np.float32(0.8789), np.float32(0.9592), np.float32(0.9627), np.float32(0.9608), np.float32(0.8137), np.float32(0.7299), np.float32(0.8553), np.float32(0.9474), np.float32(0.4359), np.float32(0.4599)] +2025-10-30 12:08:56.701013: Epoch time: 547.06 s +2025-10-30 12:08:58.680077: +2025-10-30 12:08:58.681610: Epoch 213 +2025-10-30 12:08:58.682734: Current learning rate: 0.00806 +2025-10-30 12:17:51.706704: train_loss -0.3831 +2025-10-30 12:17:51.769739: val_loss -0.3892 +2025-10-30 12:17:51.771075: Pseudo dice [np.float32(0.9138), np.float32(0.6979), np.float32(0.6502), np.float32(0.5717), np.float32(0.8295), np.float32(0.7437), np.float32(0.8693), np.float32(0.8816), np.float32(0.958), np.float32(0.959), np.float32(0.9521), np.float32(0.7931), np.float32(0.7689), np.float32(0.8379), np.float32(0.9149), np.float32(0.3653), np.float32(0.2676)] +2025-10-30 12:17:51.772301: Epoch time: 533.03 s +2025-10-30 12:17:53.763360: +2025-10-30 12:17:53.768376: Epoch 214 +2025-10-30 12:17:53.769924: Current learning rate: 0.00805 +2025-10-30 12:26:56.714484: train_loss -0.3697 +2025-10-30 12:26:56.766895: val_loss -0.4106 +2025-10-30 12:26:56.768343: Pseudo dice [np.float32(0.9104), np.float32(0.7543), np.float32(0.6851), np.float32(0.5937), np.float32(0.8267), np.float32(0.75), np.float32(0.8635), np.float32(0.8582), np.float32(0.9644), np.float32(0.9687), np.float32(0.9643), np.float32(0.828), np.float32(0.7119), np.float32(0.8391), np.float32(0.9583), np.float32(0.2899), np.float32(0.2241)] +2025-10-30 12:26:56.798118: Epoch time: 542.96 s +2025-10-30 12:26:58.916303: +2025-10-30 12:26:58.918570: Epoch 215 +2025-10-30 12:26:58.921628: Current learning rate: 0.00804 +2025-10-30 12:35:56.815631: train_loss -0.407 +2025-10-30 12:35:56.876116: val_loss -0.3994 +2025-10-30 12:35:56.877505: Pseudo dice [np.float32(0.9242), np.float32(0.7145), np.float32(0.6802), np.float32(0.6106), np.float32(0.815), np.float32(0.7245), np.float32(0.7974), np.float32(0.8601), np.float32(0.9636), np.float32(0.9682), np.float32(0.9542), np.float32(0.8291), np.float32(0.7583), np.float32(0.8174), np.float32(0.8695), np.float32(0.2726), np.float32(0.2931)] +2025-10-30 12:35:56.878577: Epoch time: 537.9 s +2025-10-30 12:35:58.905150: +2025-10-30 12:35:58.921898: Epoch 216 +2025-10-30 12:35:58.923243: Current learning rate: 0.00803 +2025-10-30 12:44:40.077459: train_loss -0.3726 +2025-10-30 12:44:40.115558: val_loss -0.4423 +2025-10-30 12:44:40.123038: Pseudo dice [np.float32(0.9316), np.float32(0.7666), np.float32(0.7245), np.float32(0.6097), np.float32(0.8269), np.float32(0.7814), np.float32(0.8825), np.float32(0.875), np.float32(0.9325), np.float32(0.9251), np.float32(0.9576), np.float32(0.8154), np.float32(0.7357), np.float32(0.8534), np.float32(0.9491), np.float32(0.4164), np.float32(0.3513)] +2025-10-30 12:44:40.124327: Epoch time: 521.18 s +2025-10-30 12:44:40.125412: Yayy! New best EMA pseudo Dice: 0.7627999782562256 +2025-10-30 12:44:45.579334: +2025-10-30 12:44:45.585661: Epoch 217 +2025-10-30 12:44:45.587412: Current learning rate: 0.00802 +2025-10-30 12:53:31.429347: train_loss -0.4005 +2025-10-30 12:53:31.499039: val_loss -0.3953 +2025-10-30 12:53:31.500805: Pseudo dice [np.float32(0.9251), np.float32(0.7648), np.float32(0.6197), np.float32(0.6434), np.float32(0.843), np.float32(0.767), np.float32(0.8284), np.float32(0.8581), np.float32(0.9454), np.float32(0.9475), np.float32(0.9571), np.float32(0.8085), np.float32(0.7665), np.float32(0.8476), np.float32(0.9089), np.float32(0.239), np.float32(0.2428)] +2025-10-30 12:53:31.504165: Epoch time: 525.85 s +2025-10-30 12:53:33.525389: +2025-10-30 12:53:33.529581: Epoch 218 +2025-10-30 12:53:33.531280: Current learning rate: 0.00801 +2025-10-30 13:02:33.295209: train_loss -0.3819 +2025-10-30 13:02:33.314126: val_loss -0.3901 +2025-10-30 13:02:33.317527: Pseudo dice [np.float32(0.9291), np.float32(0.7095), np.float32(0.6723), np.float32(0.586), np.float32(0.8764), np.float32(0.7393), np.float32(0.7885), np.float32(0.8648), np.float32(0.9507), np.float32(0.9398), np.float32(0.9333), np.float32(0.8086), np.float32(0.7489), np.float32(0.8483), np.float32(0.8812), np.float32(0.298), np.float32(0.1388)] +2025-10-30 13:02:33.319265: Epoch time: 539.77 s +2025-10-30 13:02:35.418112: +2025-10-30 13:02:35.419325: Epoch 219 +2025-10-30 13:02:35.420626: Current learning rate: 0.00801 +2025-10-30 13:11:28.424479: train_loss -0.3888 +2025-10-30 13:11:28.553209: val_loss -0.3564 +2025-10-30 13:11:28.554602: Pseudo dice [np.float32(0.9112), np.float32(0.7342), np.float32(0.5949), np.float32(0.6044), np.float32(0.865), np.float32(0.7206), np.float32(0.7596), np.float32(0.8691), np.float32(0.9561), np.float32(0.9463), np.float32(0.9517), np.float32(0.7956), np.float32(0.7332), np.float32(0.8308), np.float32(0.8599), np.float32(0.1661), np.float32(0.1776)] +2025-10-30 13:11:28.582977: Epoch time: 533.01 s +2025-10-30 13:11:31.444854: +2025-10-30 13:11:31.446008: Epoch 220 +2025-10-30 13:11:31.447285: Current learning rate: 0.008 +2025-10-30 13:20:18.630363: train_loss -0.3894 +2025-10-30 13:20:18.643618: val_loss -0.3953 +2025-10-30 13:20:18.645243: Pseudo dice [np.float32(0.9133), np.float32(0.62), np.float32(0.7068), np.float32(0.6445), np.float32(0.8279), np.float32(0.757), np.float32(0.8287), np.float32(0.8653), np.float32(0.9617), np.float32(0.9643), np.float32(0.9458), np.float32(0.8287), np.float32(0.7587), np.float32(0.8323), np.float32(0.9214), np.float32(0.3444), np.float32(0.3094)] +2025-10-30 13:20:18.646560: Epoch time: 527.19 s +2025-10-30 13:20:20.753414: +2025-10-30 13:20:20.755341: Epoch 221 +2025-10-30 13:20:20.756987: Current learning rate: 0.00799 +2025-10-30 13:29:20.010356: train_loss -0.3889 +2025-10-30 13:29:20.019652: val_loss -0.3931 +2025-10-30 13:29:20.022684: Pseudo dice [np.float32(0.9231), np.float32(0.7485), np.float32(0.5978), np.float32(0.5928), np.float32(0.8473), np.float32(0.7723), np.float32(0.8598), np.float32(0.8799), np.float32(0.9371), np.float32(0.9432), np.float32(0.9499), np.float32(0.8058), np.float32(0.7543), np.float32(0.8414), np.float32(0.9123), np.float32(0.3302), np.float32(0.281)] +2025-10-30 13:29:20.024388: Epoch time: 539.26 s +2025-10-30 13:29:22.098501: +2025-10-30 13:29:22.099988: Epoch 222 +2025-10-30 13:29:22.101244: Current learning rate: 0.00798 +2025-10-30 13:38:22.890974: train_loss -0.4138 +2025-10-30 13:38:22.933454: val_loss -0.3731 +2025-10-30 13:38:22.935610: Pseudo dice [np.float32(0.9112), np.float32(0.7193), np.float32(0.6707), np.float32(0.5973), np.float32(0.8428), np.float32(0.7681), np.float32(0.8485), np.float32(0.8803), np.float32(0.9446), np.float32(0.9425), np.float32(0.954), np.float32(0.8136), np.float32(0.7411), np.float32(0.8728), np.float32(0.8771), np.float32(0.3916), np.float32(0.4)] +2025-10-30 13:38:22.936907: Epoch time: 540.8 s +2025-10-30 13:38:25.749244: +2025-10-30 13:38:25.757479: Epoch 223 +2025-10-30 13:38:25.759600: Current learning rate: 0.00797 +2025-10-30 13:47:38.835092: train_loss -0.395 +2025-10-30 13:47:38.870237: val_loss -0.4359 +2025-10-30 13:47:38.871371: Pseudo dice [np.float32(0.9321), np.float32(0.7391), np.float32(0.6854), np.float32(0.544), np.float32(0.8775), np.float32(0.7618), np.float32(0.8662), np.float32(0.8614), np.float32(0.9544), np.float32(0.9602), np.float32(0.9638), np.float32(0.8125), np.float32(0.7729), np.float32(0.8765), np.float32(0.95), np.float32(0.345), np.float32(0.3366)] +2025-10-30 13:47:38.872706: Epoch time: 553.09 s +2025-10-30 13:47:38.876107: Yayy! New best EMA pseudo Dice: 0.7628999948501587 +2025-10-30 13:47:44.693086: +2025-10-30 13:47:44.694738: Epoch 224 +2025-10-30 13:47:44.696622: Current learning rate: 0.00796 +2025-10-30 13:56:50.010368: train_loss -0.4075 +2025-10-30 13:56:50.047522: val_loss -0.4118 +2025-10-30 13:56:50.049404: Pseudo dice [np.float32(0.9132), np.float32(0.7246), np.float32(0.6267), np.float32(0.6322), np.float32(0.8426), np.float32(0.77), np.float32(0.8222), np.float32(0.8585), np.float32(0.9622), np.float32(0.9529), np.float32(0.9596), np.float32(0.8217), np.float32(0.7627), np.float32(0.8432), np.float32(0.9388), np.float32(0.3665), np.float32(0.324)] +2025-10-30 13:56:50.091233: Epoch time: 545.32 s +2025-10-30 13:56:50.096025: Yayy! New best EMA pseudo Dice: 0.7638000249862671 +2025-10-30 13:56:55.192701: +2025-10-30 13:56:55.197766: Epoch 225 +2025-10-30 13:56:55.201747: Current learning rate: 0.00795 +2025-10-30 14:05:50.829008: train_loss -0.4157 +2025-10-30 14:05:50.861293: val_loss -0.3748 +2025-10-30 14:05:50.867277: Pseudo dice [np.float32(0.931), np.float32(0.7325), np.float32(0.6366), np.float32(0.6064), np.float32(0.8345), np.float32(0.7808), np.float32(0.7311), np.float32(0.8736), np.float32(0.9357), np.float32(0.9266), np.float32(0.9578), np.float32(0.8104), np.float32(0.7534), np.float32(0.848), np.float32(0.9176), np.float32(0.2075), np.float32(0.385)] +2025-10-30 14:05:50.873210: Epoch time: 535.64 s +2025-10-30 14:05:52.850873: +2025-10-30 14:05:52.853190: Epoch 226 +2025-10-30 14:05:52.855161: Current learning rate: 0.00794 +2025-10-30 14:14:53.802552: train_loss -0.3808 +2025-10-30 14:14:53.872885: val_loss -0.383 +2025-10-30 14:14:53.874343: Pseudo dice [np.float32(0.8991), np.float32(0.7419), np.float32(0.6638), np.float32(0.5897), np.float32(0.8167), np.float32(0.7517), np.float32(0.7997), np.float32(0.8675), np.float32(0.9478), np.float32(0.9502), np.float32(0.9586), np.float32(0.803), np.float32(0.7577), np.float32(0.8297), np.float32(0.94), np.float32(0.4173), np.float32(0.39)] +2025-10-30 14:14:53.875618: Epoch time: 540.96 s +2025-10-30 14:14:53.877618: Yayy! New best EMA pseudo Dice: 0.7639999985694885 +2025-10-30 14:14:58.447288: +2025-10-30 14:14:58.451413: Epoch 227 +2025-10-30 14:14:58.460645: Current learning rate: 0.00793 +2025-10-30 14:23:56.903236: train_loss -0.4078 +2025-10-30 14:23:56.934559: val_loss -0.3637 +2025-10-30 14:23:56.939118: Pseudo dice [np.float32(0.9128), np.float32(0.7484), np.float32(0.7005), np.float32(0.5641), np.float32(0.8789), np.float32(0.7891), np.float32(0.829), np.float32(0.8622), np.float32(0.8872), np.float32(0.867), np.float32(0.9575), np.float32(0.8208), np.float32(0.7581), np.float32(0.8594), np.float32(0.9419), np.float32(0.2984), np.float32(0.2608)] +2025-10-30 14:23:56.940592: Epoch time: 538.46 s +2025-10-30 14:23:59.050526: +2025-10-30 14:23:59.053868: Epoch 228 +2025-10-30 14:23:59.055646: Current learning rate: 0.00792 +2025-10-30 14:32:42.668150: train_loss -0.3722 +2025-10-30 14:32:42.747029: val_loss -0.3523 +2025-10-30 14:32:42.750448: Pseudo dice [np.float32(0.9037), np.float32(0.6561), np.float32(0.6867), np.float32(0.5265), np.float32(0.8533), np.float32(0.7548), np.float32(0.8687), np.float32(0.8414), np.float32(0.9289), np.float32(0.9351), np.float32(0.9526), np.float32(0.8161), np.float32(0.7383), np.float32(0.854), np.float32(0.9411), np.float32(0.241), np.float32(0.1657)] +2025-10-30 14:32:42.752334: Epoch time: 523.62 s +2025-10-30 14:32:44.859984: +2025-10-30 14:32:44.861373: Epoch 229 +2025-10-30 14:32:44.863220: Current learning rate: 0.00791 +2025-10-30 14:41:37.671142: train_loss -0.4012 +2025-10-30 14:41:37.752345: val_loss -0.3782 +2025-10-30 14:41:37.754307: Pseudo dice [np.float32(0.8906), np.float32(0.7675), np.float32(0.722), np.float32(0.5228), np.float32(0.8607), np.float32(0.7445), np.float32(0.7651), np.float32(0.8736), np.float32(0.9635), np.float32(0.9651), np.float32(0.9528), np.float32(0.8281), np.float32(0.7388), np.float32(0.8315), np.float32(0.9501), np.float32(0.363), np.float32(0.3346)] +2025-10-30 14:41:37.755910: Epoch time: 532.82 s +2025-10-30 14:41:39.703073: +2025-10-30 14:41:39.704650: Epoch 230 +2025-10-30 14:41:39.705961: Current learning rate: 0.0079 +2025-10-30 14:50:30.670995: train_loss -0.4014 +2025-10-30 14:50:30.724837: val_loss -0.4152 +2025-10-30 14:50:30.726727: Pseudo dice [np.float32(0.9088), np.float32(0.7109), np.float32(0.6668), np.float32(0.5801), np.float32(0.8407), np.float32(0.7447), np.float32(0.8655), np.float32(0.8719), np.float32(0.9685), np.float32(0.968), np.float32(0.961), np.float32(0.8356), np.float32(0.7447), np.float32(0.8551), np.float32(0.9462), np.float32(0.2899), np.float32(0.2533)] +2025-10-30 14:50:30.728757: Epoch time: 530.97 s +2025-10-30 14:50:32.737269: +2025-10-30 14:50:32.744735: Epoch 231 +2025-10-30 14:50:32.749997: Current learning rate: 0.00789 +2025-10-30 14:59:45.203493: train_loss -0.4085 +2025-10-30 14:59:45.218336: val_loss -0.3582 +2025-10-30 14:59:45.219523: Pseudo dice [np.float32(0.9026), np.float32(0.7237), np.float32(0.7298), np.float32(0.6123), np.float32(0.8114), np.float32(0.7714), np.float32(0.8092), np.float32(0.8778), np.float32(0.955), np.float32(0.9514), np.float32(0.9431), np.float32(0.8197), np.float32(0.7337), np.float32(0.8222), np.float32(0.9456), np.float32(0.4042), np.float32(0.2311)] +2025-10-30 14:59:45.223457: Epoch time: 552.47 s +2025-10-30 14:59:47.324428: +2025-10-30 14:59:47.325785: Epoch 232 +2025-10-30 14:59:47.328416: Current learning rate: 0.00789 +2025-10-30 15:08:39.729034: train_loss -0.3667 +2025-10-30 15:08:39.771656: val_loss -0.3836 +2025-10-30 15:08:39.774310: Pseudo dice [np.float32(0.9196), np.float32(0.7531), np.float32(0.6819), np.float32(0.6203), np.float32(0.8644), np.float32(0.7861), np.float32(0.7887), np.float32(0.8448), np.float32(0.9183), np.float32(0.9308), np.float32(0.9525), np.float32(0.7999), np.float32(0.7286), np.float32(0.8599), np.float32(0.9326), np.float32(0.1329), np.float32(0.2493)] +2025-10-30 15:08:39.776964: Epoch time: 532.41 s +2025-10-30 15:08:42.179272: +2025-10-30 15:08:42.181370: Epoch 233 +2025-10-30 15:08:42.183760: Current learning rate: 0.00788 +2025-10-30 15:17:33.244613: train_loss -0.3845 +2025-10-30 15:17:33.292040: val_loss -0.4179 +2025-10-30 15:17:33.293615: Pseudo dice [np.float32(0.8701), np.float32(0.7546), np.float32(0.7047), np.float32(0.6494), np.float32(0.8398), np.float32(0.7684), np.float32(0.8727), np.float32(0.8798), np.float32(0.9734), np.float32(0.9748), np.float32(0.9669), np.float32(0.8506), np.float32(0.7676), np.float32(0.8235), np.float32(0.9528), np.float32(0.2959), np.float32(0.2584)] +2025-10-30 15:17:33.294782: Epoch time: 531.07 s +2025-10-30 15:17:51.053820: +2025-10-30 15:17:51.055386: Epoch 234 +2025-10-30 15:17:51.056656: Current learning rate: 0.00787 +2025-10-30 15:26:53.722322: train_loss -0.3872 +2025-10-30 15:26:53.800055: val_loss -0.4262 +2025-10-30 15:26:53.803361: Pseudo dice [np.float32(0.9014), np.float32(0.7034), np.float32(0.6978), np.float32(0.5943), np.float32(0.8429), np.float32(0.7871), np.float32(0.8629), np.float32(0.8799), np.float32(0.9648), np.float32(0.9729), np.float32(0.9538), np.float32(0.7934), np.float32(0.724), np.float32(0.8853), np.float32(0.8745), np.float32(0.4209), np.float32(0.3101)] +2025-10-30 15:26:53.808724: Epoch time: 542.67 s +2025-10-30 15:26:53.811459: Yayy! New best EMA pseudo Dice: 0.7645999789237976 +2025-10-30 15:26:58.954838: +2025-10-30 15:26:58.956842: Epoch 235 +2025-10-30 15:26:58.958330: Current learning rate: 0.00786 +2025-10-30 15:36:05.129364: train_loss -0.4026 +2025-10-30 15:36:05.166726: val_loss -0.3914 +2025-10-30 15:36:05.168394: Pseudo dice [np.float32(0.9004), np.float32(0.7373), np.float32(0.7247), np.float32(0.5208), np.float32(0.8542), np.float32(0.7744), np.float32(0.833), np.float32(0.8647), np.float32(0.9491), np.float32(0.8941), np.float32(0.9511), np.float32(0.8037), np.float32(0.7225), np.float32(0.8588), np.float32(0.9549), np.float32(0.1737), np.float32(0.1816)] +2025-10-30 15:36:05.169862: Epoch time: 546.18 s +2025-10-30 15:36:07.027799: +2025-10-30 15:36:07.034243: Epoch 236 +2025-10-30 15:36:07.035751: Current learning rate: 0.00785 +2025-10-30 15:44:53.303635: train_loss -0.3889 +2025-10-30 15:44:53.368277: val_loss -0.3815 +2025-10-30 15:44:53.373615: Pseudo dice [np.float32(0.9177), np.float32(0.7213), np.float32(0.6507), np.float32(0.5788), np.float32(0.82), np.float32(0.7555), np.float32(0.8728), np.float32(0.8601), np.float32(0.9765), np.float32(0.976), np.float32(0.9539), np.float32(0.8374), np.float32(0.7505), np.float32(0.8409), np.float32(0.9239), np.float32(0.2685), np.float32(0.2563)] +2025-10-30 15:44:53.375144: Epoch time: 526.28 s +2025-10-30 15:44:55.343871: +2025-10-30 15:44:55.349411: Epoch 237 +2025-10-30 15:44:55.368472: Current learning rate: 0.00784 +2025-10-30 15:54:02.159206: train_loss -0.3982 +2025-10-30 15:54:02.186189: val_loss -0.3722 +2025-10-30 15:54:02.189005: Pseudo dice [np.float32(0.9284), np.float32(0.7487), np.float32(0.6853), np.float32(0.5674), np.float32(0.8373), np.float32(0.7842), np.float32(0.8638), np.float32(0.8682), np.float32(0.9698), np.float32(0.9764), np.float32(0.9368), np.float32(0.8199), np.float32(0.7522), np.float32(0.853), np.float32(0.9345), np.float32(0.2234), np.float32(0.2456)] +2025-10-30 15:54:02.193407: Epoch time: 546.82 s +2025-10-30 15:54:04.173355: +2025-10-30 15:54:04.174558: Epoch 238 +2025-10-30 15:54:04.175929: Current learning rate: 0.00783 +2025-10-30 16:03:15.541000: train_loss -0.4089 +2025-10-30 16:03:15.604383: val_loss -0.4031 +2025-10-30 16:03:15.605797: Pseudo dice [np.float32(0.9344), np.float32(0.7535), np.float32(0.6867), np.float32(0.6282), np.float32(0.8561), np.float32(0.7702), np.float32(0.8635), np.float32(0.882), np.float32(0.9558), np.float32(0.9548), np.float32(0.9561), np.float32(0.801), np.float32(0.7233), np.float32(0.8513), np.float32(0.9096), np.float32(0.3549), np.float32(0.2824)] +2025-10-30 16:03:15.607724: Epoch time: 551.38 s +2025-10-30 16:03:17.703434: +2025-10-30 16:03:17.704971: Epoch 239 +2025-10-30 16:03:17.706395: Current learning rate: 0.00782 +2025-10-30 16:12:22.999244: train_loss -0.3939 +2025-10-30 16:12:23.022051: val_loss -0.3849 +2025-10-30 16:12:23.023537: Pseudo dice [np.float32(0.8919), np.float32(0.7387), np.float32(0.6731), np.float32(0.6434), np.float32(0.8619), np.float32(0.7636), np.float32(0.8477), np.float32(0.8388), np.float32(0.9218), np.float32(0.91), np.float32(0.9504), np.float32(0.8242), np.float32(0.7642), np.float32(0.8818), np.float32(0.9363), np.float32(0.1967), np.float32(0.2186)] +2025-10-30 16:12:23.024869: Epoch time: 545.31 s +2025-10-30 16:12:25.041793: +2025-10-30 16:12:25.043483: Epoch 240 +2025-10-30 16:12:25.056621: Current learning rate: 0.00781 +2025-10-30 16:21:15.164803: train_loss -0.4199 +2025-10-30 16:21:15.189920: val_loss -0.4275 +2025-10-30 16:21:15.191429: Pseudo dice [np.float32(0.9296), np.float32(0.7464), np.float32(0.7243), np.float32(0.6091), np.float32(0.8323), np.float32(0.7423), np.float32(0.837), np.float32(0.8599), np.float32(0.9753), np.float32(0.9719), np.float32(0.9633), np.float32(0.827), np.float32(0.721), np.float32(0.8666), np.float32(0.9616), np.float32(0.3299), np.float32(0.3589)] +2025-10-30 16:21:15.192810: Epoch time: 530.13 s +2025-10-30 16:21:15.194216: Yayy! New best EMA pseudo Dice: 0.7649999856948853 +2025-10-30 16:21:20.321747: +2025-10-30 16:21:20.324662: Epoch 241 +2025-10-30 16:21:20.326120: Current learning rate: 0.0078 +2025-10-30 16:30:21.565048: train_loss -0.3903 +2025-10-30 16:30:21.582991: val_loss -0.3888 +2025-10-30 16:30:21.584851: Pseudo dice [np.float32(0.9082), np.float32(0.779), np.float32(0.7345), np.float32(0.6345), np.float32(0.8465), np.float32(0.7703), np.float32(0.8481), np.float32(0.83), np.float32(0.9548), np.float32(0.9565), np.float32(0.9618), np.float32(0.8117), np.float32(0.6964), np.float32(0.8096), np.float32(0.9497), np.float32(0.2988), np.float32(0.2882)] +2025-10-30 16:30:21.586425: Epoch time: 541.25 s +2025-10-30 16:30:21.587582: Yayy! New best EMA pseudo Dice: 0.7653999924659729 +2025-10-30 16:30:26.066398: +2025-10-30 16:30:26.074603: Epoch 242 +2025-10-30 16:30:26.079361: Current learning rate: 0.00779 +2025-10-30 16:39:05.135392: train_loss -0.3811 +2025-10-30 16:39:05.165283: val_loss -0.4227 +2025-10-30 16:39:05.167284: Pseudo dice [np.float32(0.9333), np.float32(0.7577), np.float32(0.7114), np.float32(0.5355), np.float32(0.8397), np.float32(0.7612), np.float32(0.8571), np.float32(0.8556), np.float32(0.9279), np.float32(0.8839), np.float32(0.9559), np.float32(0.8025), np.float32(0.7877), np.float32(0.8633), np.float32(0.9019), np.float32(0.3815), np.float32(0.3788)] +2025-10-30 16:39:05.168865: Epoch time: 519.08 s +2025-10-30 16:39:05.181144: Yayy! New best EMA pseudo Dice: 0.7662000060081482 +2025-10-30 16:39:09.810584: +2025-10-30 16:39:09.821113: Epoch 243 +2025-10-30 16:39:09.822862: Current learning rate: 0.00778 +2025-10-30 16:48:08.447636: train_loss -0.4005 +2025-10-30 16:48:08.473128: val_loss -0.3865 +2025-10-30 16:48:08.474767: Pseudo dice [np.float32(0.9052), np.float32(0.7761), np.float32(0.7418), np.float32(0.4978), np.float32(0.8268), np.float32(0.7768), np.float32(0.8575), np.float32(0.8652), np.float32(0.9754), np.float32(0.9751), np.float32(0.955), np.float32(0.8277), np.float32(0.7266), np.float32(0.8448), np.float32(0.9629), np.float32(0.2575), np.float32(0.1979)] +2025-10-30 16:48:08.478278: Epoch time: 538.64 s +2025-10-30 16:48:10.615512: +2025-10-30 16:48:10.622291: Epoch 244 +2025-10-30 16:48:10.625571: Current learning rate: 0.00777 +2025-10-30 16:57:25.251285: train_loss -0.4178 +2025-10-30 16:57:25.279161: val_loss -0.4273 +2025-10-30 16:57:25.280572: Pseudo dice [np.float32(0.9367), np.float32(0.7129), np.float32(0.6212), np.float32(0.6303), np.float32(0.8389), np.float32(0.7699), np.float32(0.8562), np.float32(0.8628), np.float32(0.9675), np.float32(0.9686), np.float32(0.9633), np.float32(0.8051), np.float32(0.773), np.float32(0.8096), np.float32(0.9341), np.float32(0.3264), np.float32(0.2224)] +2025-10-30 16:57:25.282499: Epoch time: 554.65 s +2025-10-30 16:57:27.526550: +2025-10-30 16:57:27.531661: Epoch 245 +2025-10-30 16:57:27.535049: Current learning rate: 0.00777 +2025-10-30 17:06:29.935468: train_loss -0.406 +2025-10-30 17:06:29.978339: val_loss -0.3522 +2025-10-30 17:06:29.980068: Pseudo dice [np.float32(0.9209), np.float32(0.7159), np.float32(0.6695), np.float32(0.6053), np.float32(0.8219), np.float32(0.7616), np.float32(0.7118), np.float32(0.8465), np.float32(0.9299), np.float32(0.9389), np.float32(0.9405), np.float32(0.8377), np.float32(0.7434), np.float32(0.8116), np.float32(0.9015), np.float32(0.3916), np.float32(0.324)] +2025-10-30 17:06:30.015240: Epoch time: 542.41 s +2025-10-30 17:06:32.293677: +2025-10-30 17:06:32.298654: Epoch 246 +2025-10-30 17:06:32.300302: Current learning rate: 0.00776 +2025-10-30 17:15:28.218442: train_loss -0.3895 +2025-10-30 17:15:28.282533: val_loss -0.3709 +2025-10-30 17:15:28.284153: Pseudo dice [np.float32(0.9135), np.float32(0.6758), np.float32(0.6829), np.float32(0.5641), np.float32(0.8521), np.float32(0.7329), np.float32(0.8897), np.float32(0.8617), np.float32(0.9313), np.float32(0.951), np.float32(0.9578), np.float32(0.7783), np.float32(0.7474), np.float32(0.8349), np.float32(0.8831), np.float32(0.3421), np.float32(0.3771)] +2025-10-30 17:15:28.285319: Epoch time: 535.93 s +2025-10-30 17:15:30.362145: +2025-10-30 17:15:30.366339: Epoch 247 +2025-10-30 17:15:30.367461: Current learning rate: 0.00775 +2025-10-30 17:24:32.369933: train_loss -0.364 +2025-10-30 17:24:32.415737: val_loss -0.3739 +2025-10-30 17:24:32.416926: Pseudo dice [np.float32(0.9035), np.float32(0.7206), np.float32(0.7113), np.float32(0.6201), np.float32(0.8503), np.float32(0.7571), np.float32(0.8164), np.float32(0.8741), np.float32(0.949), np.float32(0.9558), np.float32(0.9527), np.float32(0.8024), np.float32(0.7081), np.float32(0.833), np.float32(0.9321), np.float32(0.5128), np.float32(0.3688)] +2025-10-30 17:24:32.418251: Epoch time: 542.01 s +2025-10-30 17:24:32.419417: Yayy! New best EMA pseudo Dice: 0.7663000226020813 +2025-10-30 17:24:37.528252: +2025-10-30 17:24:37.529520: Epoch 248 +2025-10-30 17:24:37.531374: Current learning rate: 0.00774 +2025-10-30 17:33:40.503262: train_loss -0.3855 +2025-10-30 17:33:40.548476: val_loss -0.3594 +2025-10-30 17:33:40.550186: Pseudo dice [np.float32(0.9162), np.float32(0.6996), np.float32(0.6738), np.float32(0.5791), np.float32(0.8285), np.float32(0.7345), np.float32(0.8062), np.float32(0.866), np.float32(0.978), np.float32(0.9673), np.float32(0.9444), np.float32(0.8171), np.float32(0.7445), np.float32(0.8384), np.float32(0.9382), np.float32(0.3017), np.float32(0.2747)] +2025-10-30 17:33:40.551442: Epoch time: 542.98 s +2025-10-30 17:33:42.599323: +2025-10-30 17:33:42.601925: Epoch 249 +2025-10-30 17:33:42.603290: Current learning rate: 0.00773 +2025-10-30 17:42:28.262791: train_loss -0.3755 +2025-10-30 17:42:28.272798: val_loss -0.39 +2025-10-30 17:42:28.274325: Pseudo dice [np.float32(0.9299), np.float32(0.7263), np.float32(0.6667), np.float32(0.5765), np.float32(0.8209), np.float32(0.7304), np.float32(0.8291), np.float32(0.8655), np.float32(0.9603), np.float32(0.9544), np.float32(0.9549), np.float32(0.7989), np.float32(0.7666), np.float32(0.8235), np.float32(0.9342), np.float32(0.2691), np.float32(0.2999)] +2025-10-30 17:42:28.275690: Epoch time: 525.67 s +2025-10-30 17:42:33.270549: +2025-10-30 17:42:33.276752: Epoch 250 +2025-10-30 17:42:33.278502: Current learning rate: 0.00772 +2025-10-30 17:51:28.297076: train_loss -0.3736 +2025-10-30 17:51:28.327758: val_loss -0.3552 +2025-10-30 17:51:28.329866: Pseudo dice [np.float32(0.8645), np.float32(0.7702), np.float32(0.6756), np.float32(0.5525), np.float32(0.8626), np.float32(0.7539), np.float32(0.7901), np.float32(0.8732), np.float32(0.9265), np.float32(0.9159), np.float32(0.9377), np.float32(0.8003), np.float32(0.7464), np.float32(0.8527), np.float32(0.8182), np.float32(0.5071), np.float32(0.2977)] +2025-10-30 17:51:28.331441: Epoch time: 535.03 s +2025-10-30 17:51:30.364025: +2025-10-30 17:51:30.372284: Epoch 251 +2025-10-30 17:51:30.386155: Current learning rate: 0.00771 +2025-10-30 18:00:39.546315: train_loss -0.3865 +2025-10-30 18:00:39.645425: val_loss -0.4043 +2025-10-30 18:00:39.647639: Pseudo dice [np.float32(0.9167), np.float32(0.7397), np.float32(0.6498), np.float32(0.61), np.float32(0.8422), np.float32(0.7045), np.float32(0.8105), np.float32(0.8519), np.float32(0.9615), np.float32(0.9528), np.float32(0.9544), np.float32(0.8061), np.float32(0.7059), np.float32(0.8287), np.float32(0.9404), np.float32(0.2832), np.float32(0.2589)] +2025-10-30 18:00:39.649986: Epoch time: 549.19 s +2025-10-30 18:00:41.734204: +2025-10-30 18:00:41.735519: Epoch 252 +2025-10-30 18:00:41.736712: Current learning rate: 0.0077 +2025-10-30 18:09:34.326581: train_loss -0.3475 +2025-10-30 18:09:34.393869: val_loss -0.3881 +2025-10-30 18:09:34.395527: Pseudo dice [np.float32(0.9198), np.float32(0.6352), np.float32(0.6471), np.float32(0.5955), np.float32(0.8584), np.float32(0.7512), np.float32(0.7154), np.float32(0.8652), np.float32(0.944), np.float32(0.9404), np.float32(0.9389), np.float32(0.7702), np.float32(0.7308), np.float32(0.8455), np.float32(0.8311), np.float32(0.413), np.float32(0.2973)] +2025-10-30 18:09:34.397342: Epoch time: 532.6 s +2025-10-30 18:09:36.458262: +2025-10-30 18:09:36.461712: Epoch 253 +2025-10-30 18:09:36.468801: Current learning rate: 0.00769 +2025-10-30 18:18:14.925916: train_loss -0.3975 +2025-10-30 18:18:15.016420: val_loss -0.392 +2025-10-30 18:18:15.022085: Pseudo dice [np.float32(0.9226), np.float32(0.6803), np.float32(0.6777), np.float32(0.5812), np.float32(0.8299), np.float32(0.7354), np.float32(0.8738), np.float32(0.8519), np.float32(0.9395), np.float32(0.9493), np.float32(0.9618), np.float32(0.8026), np.float32(0.7194), np.float32(0.8507), np.float32(0.9387), np.float32(0.2849), np.float32(0.3272)] +2025-10-30 18:18:15.023887: Epoch time: 518.47 s +2025-10-30 18:18:16.989834: +2025-10-30 18:18:16.992085: Epoch 254 +2025-10-30 18:18:16.995120: Current learning rate: 0.00768 +2025-10-30 18:27:36.998666: train_loss -0.3704 +2025-10-30 18:27:37.070778: val_loss -0.4023 +2025-10-30 18:27:37.073446: Pseudo dice [np.float32(0.9181), np.float32(0.7312), np.float32(0.6893), np.float32(0.597), np.float32(0.8216), np.float32(0.7325), np.float32(0.8044), np.float32(0.8589), np.float32(0.964), np.float32(0.9545), np.float32(0.9484), np.float32(0.7568), np.float32(0.7463), np.float32(0.8304), np.float32(0.9329), np.float32(0.2626), np.float32(0.2781)] +2025-10-30 18:27:37.075913: Epoch time: 560.01 s +2025-10-30 18:27:39.119245: +2025-10-30 18:27:39.120949: Epoch 255 +2025-10-30 18:27:39.122055: Current learning rate: 0.00767 +2025-10-30 18:36:39.720660: train_loss -0.4034 +2025-10-30 18:36:39.744796: val_loss -0.406 +2025-10-30 18:36:39.747680: Pseudo dice [np.float32(0.9305), np.float32(0.7611), np.float32(0.7128), np.float32(0.5955), np.float32(0.7945), np.float32(0.7482), np.float32(0.8175), np.float32(0.8765), np.float32(0.9366), np.float32(0.9594), np.float32(0.9637), np.float32(0.7894), np.float32(0.7723), np.float32(0.8157), np.float32(0.9477), np.float32(0.3094), np.float32(0.3272)] +2025-10-30 18:36:39.749320: Epoch time: 540.61 s +2025-10-30 18:36:41.781279: +2025-10-30 18:36:41.785185: Epoch 256 +2025-10-30 18:36:41.788074: Current learning rate: 0.00766 +2025-10-30 18:45:35.053393: train_loss -0.3666 +2025-10-30 18:45:35.059743: val_loss -0.3688 +2025-10-30 18:45:35.061030: Pseudo dice [np.float32(0.9288), np.float32(0.7322), np.float32(0.7028), np.float32(0.6338), np.float32(0.8133), np.float32(0.7692), np.float32(0.8274), np.float32(0.8739), np.float32(0.9618), np.float32(0.9505), np.float32(0.9576), np.float32(0.8281), np.float32(0.7417), np.float32(0.818), np.float32(0.9418), np.float32(0.095), np.float32(0.2358)] +2025-10-30 18:45:35.062426: Epoch time: 533.28 s +2025-10-30 18:45:52.025825: +2025-10-30 18:45:52.027287: Epoch 257 +2025-10-30 18:45:52.028630: Current learning rate: 0.00765 +2025-10-30 18:54:44.456759: train_loss -0.406 +2025-10-30 18:54:44.488911: val_loss -0.4103 +2025-10-30 18:54:44.490501: Pseudo dice [np.float32(0.9163), np.float32(0.7511), np.float32(0.7034), np.float32(0.5812), np.float32(0.8465), np.float32(0.7281), np.float32(0.7513), np.float32(0.8594), np.float32(0.9601), np.float32(0.9597), np.float32(0.9568), np.float32(0.8155), np.float32(0.7789), np.float32(0.8461), np.float32(0.9292), np.float32(0.4208), np.float32(0.3303)] +2025-10-30 18:54:44.491888: Epoch time: 532.44 s +2025-10-30 18:54:46.497577: +2025-10-30 18:54:46.499248: Epoch 258 +2025-10-30 18:54:46.501327: Current learning rate: 0.00764 +2025-10-30 19:03:28.777967: train_loss -0.3502 +2025-10-30 19:03:28.791322: val_loss -0.4523 +2025-10-30 19:03:28.795821: Pseudo dice [np.float32(0.9143), np.float32(0.7264), np.float32(0.7157), np.float32(0.5801), np.float32(0.839), np.float32(0.7503), np.float32(0.8184), np.float32(0.873), np.float32(0.9528), np.float32(0.9458), np.float32(0.9606), np.float32(0.8088), np.float32(0.7516), np.float32(0.862), np.float32(0.9508), np.float32(0.3903), np.float32(0.3742)] +2025-10-30 19:03:28.797399: Epoch time: 522.28 s +2025-10-30 19:03:30.983743: +2025-10-30 19:03:30.986403: Epoch 259 +2025-10-30 19:03:30.988274: Current learning rate: 0.00764 +2025-10-30 19:12:23.384949: train_loss -0.3945 +2025-10-30 19:12:23.444327: val_loss -0.4169 +2025-10-30 19:12:23.445473: Pseudo dice [np.float32(0.9069), np.float32(0.7195), np.float32(0.7133), np.float32(0.5344), np.float32(0.8536), np.float32(0.7947), np.float32(0.8203), np.float32(0.8638), np.float32(0.9602), np.float32(0.9596), np.float32(0.9629), np.float32(0.798), np.float32(0.7624), np.float32(0.8501), np.float32(0.9492), np.float32(0.4398), np.float32(0.2964)] +2025-10-30 19:12:23.447860: Epoch time: 532.41 s +2025-10-30 19:12:25.391431: +2025-10-30 19:12:25.399990: Epoch 260 +2025-10-30 19:12:25.402314: Current learning rate: 0.00763 +2025-10-30 19:21:31.523146: train_loss -0.3968 +2025-10-30 19:21:31.547459: val_loss -0.4405 +2025-10-30 19:21:31.548831: Pseudo dice [np.float32(0.9278), np.float32(0.7619), np.float32(0.7154), np.float32(0.5721), np.float32(0.8446), np.float32(0.7687), np.float32(0.8863), np.float32(0.8715), np.float32(0.9501), np.float32(0.9491), np.float32(0.9609), np.float32(0.8198), np.float32(0.7601), np.float32(0.8622), np.float32(0.9486), np.float32(0.2944), np.float32(0.3469)] +2025-10-30 19:21:31.550678: Epoch time: 546.14 s +2025-10-30 19:21:33.586238: +2025-10-30 19:21:33.588362: Epoch 261 +2025-10-30 19:21:33.589602: Current learning rate: 0.00762 +2025-10-30 19:30:28.841749: train_loss -0.4027 +2025-10-30 19:30:28.873669: val_loss -0.4252 +2025-10-30 19:30:28.875533: Pseudo dice [np.float32(0.9234), np.float32(0.6787), np.float32(0.6794), np.float32(0.5807), np.float32(0.8389), np.float32(0.7718), np.float32(0.8743), np.float32(0.8743), np.float32(0.9643), np.float32(0.9724), np.float32(0.9509), np.float32(0.8337), np.float32(0.7305), np.float32(0.8281), np.float32(0.8553), np.float32(0.4614), np.float32(0.3699)] +2025-10-30 19:30:28.876915: Epoch time: 535.26 s +2025-10-30 19:30:28.878228: Yayy! New best EMA pseudo Dice: 0.7671999931335449 +2025-10-30 19:30:34.104931: +2025-10-30 19:30:34.106361: Epoch 262 +2025-10-30 19:30:34.108220: Current learning rate: 0.00761 +2025-10-30 19:39:47.929798: train_loss -0.4073 +2025-10-30 19:39:47.955522: val_loss -0.3644 +2025-10-30 19:39:47.957634: Pseudo dice [np.float32(0.9079), np.float32(0.6494), np.float32(0.6571), np.float32(0.5895), np.float32(0.8133), np.float32(0.7421), np.float32(0.7569), np.float32(0.8542), np.float32(0.871), np.float32(0.9007), np.float32(0.9606), np.float32(0.8273), np.float32(0.7642), np.float32(0.851), np.float32(0.9064), np.float32(0.3295), np.float32(0.3374)] +2025-10-30 19:39:47.959942: Epoch time: 553.83 s +2025-10-30 19:39:50.066097: +2025-10-30 19:39:50.068087: Epoch 263 +2025-10-30 19:39:50.073147: Current learning rate: 0.0076 +2025-10-30 19:48:57.034173: train_loss -0.386 +2025-10-30 19:48:57.088222: val_loss -0.4398 +2025-10-30 19:48:57.095504: Pseudo dice [np.float32(0.9391), np.float32(0.7719), np.float32(0.7161), np.float32(0.6445), np.float32(0.8462), np.float32(0.7987), np.float32(0.873), np.float32(0.872), np.float32(0.969), np.float32(0.9716), np.float32(0.9621), np.float32(0.8302), np.float32(0.7738), np.float32(0.8655), np.float32(0.9512), np.float32(0.2933), np.float32(0.2737)] +2025-10-30 19:48:57.097423: Epoch time: 546.97 s +2025-10-30 19:48:57.098654: Yayy! New best EMA pseudo Dice: 0.767300009727478 +2025-10-30 19:49:02.393927: +2025-10-30 19:49:02.395720: Epoch 264 +2025-10-30 19:49:02.397225: Current learning rate: 0.00759 +2025-10-30 19:57:50.935172: train_loss -0.4044 +2025-10-30 19:57:50.952367: val_loss -0.4204 +2025-10-30 19:57:50.953957: Pseudo dice [np.float32(0.9156), np.float32(0.7455), np.float32(0.6739), np.float32(0.6217), np.float32(0.8413), np.float32(0.7569), np.float32(0.8644), np.float32(0.8679), np.float32(0.9633), np.float32(0.972), np.float32(0.9592), np.float32(0.835), np.float32(0.6881), np.float32(0.839), np.float32(0.9152), np.float32(0.2746), np.float32(0.2076)] +2025-10-30 19:57:50.956089: Epoch time: 528.55 s +2025-10-30 19:57:53.079032: +2025-10-30 19:57:53.081842: Epoch 265 +2025-10-30 19:57:53.083834: Current learning rate: 0.00758 +2025-10-30 20:06:41.412147: train_loss -0.3988 +2025-10-30 20:06:41.438017: val_loss -0.3757 +2025-10-30 20:06:41.439356: Pseudo dice [np.float32(0.9105), np.float32(0.7184), np.float32(0.6851), np.float32(0.6205), np.float32(0.8209), np.float32(0.773), np.float32(0.8596), np.float32(0.863), np.float32(0.913), np.float32(0.8798), np.float32(0.9595), np.float32(0.8214), np.float32(0.7579), np.float32(0.8551), np.float32(0.9532), np.float32(0.4125), np.float32(0.2929)] +2025-10-30 20:06:41.440724: Epoch time: 528.34 s +2025-10-30 20:06:43.745457: +2025-10-30 20:06:43.747647: Epoch 266 +2025-10-30 20:06:43.750200: Current learning rate: 0.00757 +2025-10-30 20:15:33.891545: train_loss -0.4073 +2025-10-30 20:15:33.978060: val_loss -0.3576 +2025-10-30 20:15:33.980067: Pseudo dice [np.float32(0.9075), np.float32(0.7509), np.float32(0.7116), np.float32(0.634), np.float32(0.8296), np.float32(0.7275), np.float32(0.7667), np.float32(0.8498), np.float32(0.9231), np.float32(0.9026), np.float32(0.9411), np.float32(0.8057), np.float32(0.7906), np.float32(0.8502), np.float32(0.8658), np.float32(0.3404), np.float32(0.2368)] +2025-10-30 20:15:33.982368: Epoch time: 530.15 s +2025-10-30 20:15:36.299460: +2025-10-30 20:15:36.306207: Epoch 267 +2025-10-30 20:15:36.307517: Current learning rate: 0.00756 +2025-10-30 20:24:14.799664: train_loss -0.3829 +2025-10-30 20:24:14.819885: val_loss -0.4565 +2025-10-30 20:24:14.822075: Pseudo dice [np.float32(0.9238), np.float32(0.7648), np.float32(0.7573), np.float32(0.6591), np.float32(0.8733), np.float32(0.775), np.float32(0.8693), np.float32(0.8845), np.float32(0.949), np.float32(0.9309), np.float32(0.962), np.float32(0.8373), np.float32(0.752), np.float32(0.8628), np.float32(0.9591), np.float32(0.3827), np.float32(0.3518)] +2025-10-30 20:24:14.823648: Epoch time: 518.5 s +2025-10-30 20:24:14.824943: Yayy! New best EMA pseudo Dice: 0.7685999870300293 +2025-10-30 20:24:19.953791: +2025-10-30 20:24:19.954961: Epoch 268 +2025-10-30 20:24:19.956137: Current learning rate: 0.00755 +2025-10-30 20:33:01.474827: train_loss -0.4065 +2025-10-30 20:33:01.519521: val_loss -0.3894 +2025-10-30 20:33:01.522309: Pseudo dice [np.float32(0.94), np.float32(0.7737), np.float32(0.7047), np.float32(0.6528), np.float32(0.8424), np.float32(0.7215), np.float32(0.8745), np.float32(0.8709), np.float32(0.9477), np.float32(0.9622), np.float32(0.9644), np.float32(0.845), np.float32(0.7599), np.float32(0.8527), np.float32(0.9528), np.float32(0.2357), np.float32(0.2944)] +2025-10-30 20:33:01.523902: Epoch time: 521.53 s +2025-10-30 20:33:01.525132: Yayy! New best EMA pseudo Dice: 0.7694000005722046 +2025-10-30 20:33:06.097453: +2025-10-30 20:33:06.098970: Epoch 269 +2025-10-30 20:33:06.100126: Current learning rate: 0.00754 +2025-10-30 20:41:55.336108: train_loss -0.393 +2025-10-30 20:41:55.379461: val_loss -0.4345 +2025-10-30 20:41:55.386606: Pseudo dice [np.float32(0.9251), np.float32(0.7695), np.float32(0.7174), np.float32(0.6235), np.float32(0.8518), np.float32(0.785), np.float32(0.8706), np.float32(0.8763), np.float32(0.9661), np.float32(0.9663), np.float32(0.9606), np.float32(0.8434), np.float32(0.7823), np.float32(0.8404), np.float32(0.9511), np.float32(0.303), np.float32(0.3662)] +2025-10-30 20:41:55.393669: Epoch time: 529.24 s +2025-10-30 20:41:55.396285: Yayy! New best EMA pseudo Dice: 0.7713000178337097 +2025-10-30 20:42:00.223492: +2025-10-30 20:42:00.225737: Epoch 270 +2025-10-30 20:42:00.227234: Current learning rate: 0.00753 +2025-10-30 20:50:47.063072: train_loss -0.42 +2025-10-30 20:50:47.084919: val_loss -0.4323 +2025-10-30 20:50:47.086751: Pseudo dice [np.float32(0.9301), np.float32(0.7611), np.float32(0.737), np.float32(0.6138), np.float32(0.8448), np.float32(0.7457), np.float32(0.8826), np.float32(0.8936), np.float32(0.9751), np.float32(0.9777), np.float32(0.9613), np.float32(0.8401), np.float32(0.7447), np.float32(0.8204), np.float32(0.9531), np.float32(0.3675), np.float32(0.3086)] +2025-10-30 20:50:47.088329: Epoch time: 526.85 s +2025-10-30 20:50:47.089621: Yayy! New best EMA pseudo Dice: 0.7727000117301941 +2025-10-30 20:50:51.688667: +2025-10-30 20:50:51.691274: Epoch 271 +2025-10-30 20:50:51.693857: Current learning rate: 0.00752 +2025-10-30 20:59:42.403983: train_loss -0.3957 +2025-10-30 20:59:42.479486: val_loss -0.428 +2025-10-30 20:59:42.481265: Pseudo dice [np.float32(0.9246), np.float32(0.7634), np.float32(0.6831), np.float32(0.6005), np.float32(0.8607), np.float32(0.7355), np.float32(0.8405), np.float32(0.8674), np.float32(0.9489), np.float32(0.9543), np.float32(0.9482), np.float32(0.8334), np.float32(0.7696), np.float32(0.8598), np.float32(0.8784), np.float32(0.2524), np.float32(0.3355)] +2025-10-30 20:59:42.501933: Epoch time: 530.72 s +2025-10-30 20:59:44.536712: +2025-10-30 20:59:44.537983: Epoch 272 +2025-10-30 20:59:44.541451: Current learning rate: 0.00751 +2025-10-30 21:08:31.549660: train_loss -0.3973 +2025-10-30 21:08:31.561576: val_loss -0.4067 +2025-10-30 21:08:31.563222: Pseudo dice [np.float32(0.9251), np.float32(0.7891), np.float32(0.7102), np.float32(0.5994), np.float32(0.8219), np.float32(0.7388), np.float32(0.8218), np.float32(0.8528), np.float32(0.9711), np.float32(0.9566), np.float32(0.9541), np.float32(0.7984), np.float32(0.7676), np.float32(0.8195), np.float32(0.9564), np.float32(0.3704), np.float32(0.324)] +2025-10-30 21:08:31.565966: Epoch time: 527.02 s +2025-10-30 21:08:33.530366: +2025-10-30 21:08:33.533172: Epoch 273 +2025-10-30 21:08:33.536007: Current learning rate: 0.00751 +2025-10-30 21:17:24.093829: train_loss -0.3952 +2025-10-30 21:17:24.115537: val_loss -0.3881 +2025-10-30 21:17:24.117829: Pseudo dice [np.float32(0.917), np.float32(0.7092), np.float32(0.6935), np.float32(0.6156), np.float32(0.8088), np.float32(0.7349), np.float32(0.8716), np.float32(0.8773), np.float32(0.9454), np.float32(0.9462), np.float32(0.9555), np.float32(0.7991), np.float32(0.7727), np.float32(0.8363), np.float32(0.8986), np.float32(0.3826), np.float32(0.3389)] +2025-10-30 21:17:24.120112: Epoch time: 530.57 s +2025-10-30 21:17:26.217289: +2025-10-30 21:17:26.219851: Epoch 274 +2025-10-30 21:17:26.222650: Current learning rate: 0.0075 +2025-10-30 21:26:06.111057: train_loss -0.3815 +2025-10-30 21:26:06.158605: val_loss -0.3098 +2025-10-30 21:26:06.161700: Pseudo dice [np.float32(0.9248), np.float32(0.7265), np.float32(0.6779), np.float32(0.6081), np.float32(0.8194), np.float32(0.6872), np.float32(0.8362), np.float32(0.795), np.float32(0.9044), np.float32(0.8977), np.float32(0.9406), np.float32(0.8206), np.float32(0.7236), np.float32(0.7945), np.float32(0.8789), np.float32(0.3647), np.float32(0.1944)] +2025-10-30 21:26:06.163724: Epoch time: 519.9 s +2025-10-30 21:26:08.311706: +2025-10-30 21:26:08.313346: Epoch 275 +2025-10-30 21:26:08.315108: Current learning rate: 0.00749 +2025-10-30 21:34:43.994353: train_loss -0.3867 +2025-10-30 21:34:44.043008: val_loss -0.4448 +2025-10-30 21:34:44.044734: Pseudo dice [np.float32(0.9347), np.float32(0.7159), np.float32(0.6735), np.float32(0.6525), np.float32(0.8555), np.float32(0.7732), np.float32(0.8818), np.float32(0.8873), np.float32(0.9319), np.float32(0.9484), np.float32(0.9615), np.float32(0.846), np.float32(0.7453), np.float32(0.8513), np.float32(0.9522), np.float32(0.3024), np.float32(0.2073)] +2025-10-30 21:34:44.046255: Epoch time: 515.69 s +2025-10-30 21:34:46.242211: +2025-10-30 21:34:46.252656: Epoch 276 +2025-10-30 21:34:46.254585: Current learning rate: 0.00748 +2025-10-30 21:43:24.254810: train_loss -0.4167 +2025-10-30 21:43:24.284736: val_loss -0.3867 +2025-10-30 21:43:24.302041: Pseudo dice [np.float32(0.9234), np.float32(0.7734), np.float32(0.7186), np.float32(0.6321), np.float32(0.8179), np.float32(0.7776), np.float32(0.7619), np.float32(0.8639), np.float32(0.9155), np.float32(0.9137), np.float32(0.9537), np.float32(0.8389), np.float32(0.7395), np.float32(0.8511), np.float32(0.8986), np.float32(0.3765), np.float32(0.2685)] +2025-10-30 21:43:24.337488: Epoch time: 518.02 s +2025-10-30 21:43:26.416567: +2025-10-30 21:43:26.417831: Epoch 277 +2025-10-30 21:43:26.419149: Current learning rate: 0.00747 +2025-10-30 21:52:26.978858: train_loss -0.3398 +2025-10-30 21:52:27.011698: val_loss -0.378 +2025-10-30 21:52:27.013039: Pseudo dice [np.float32(0.9334), np.float32(0.6098), np.float32(0.7212), np.float32(0.6134), np.float32(0.819), np.float32(0.6982), np.float32(0.841), np.float32(0.869), np.float32(0.9412), np.float32(0.9354), np.float32(0.9518), np.float32(0.7835), np.float32(0.7476), np.float32(0.8418), np.float32(0.944), np.float32(0.2811), np.float32(0.2094)] +2025-10-30 21:52:27.014955: Epoch time: 540.57 s +2025-10-30 21:52:29.145035: +2025-10-30 21:52:29.150055: Epoch 278 +2025-10-30 21:52:29.151610: Current learning rate: 0.00746 +2025-10-30 22:01:31.127964: train_loss -0.39 +2025-10-30 22:01:31.202030: val_loss -0.4074 +2025-10-30 22:01:31.228472: Pseudo dice [np.float32(0.9155), np.float32(0.6735), np.float32(0.661), np.float32(0.6243), np.float32(0.8602), np.float32(0.7386), np.float32(0.7927), np.float32(0.8473), np.float32(0.9423), np.float32(0.9421), np.float32(0.9609), np.float32(0.8361), np.float32(0.7606), np.float32(0.8755), np.float32(0.9079), np.float32(0.2376), np.float32(0.2866)] +2025-10-30 22:01:31.229946: Epoch time: 541.99 s +2025-10-30 22:01:33.284216: +2025-10-30 22:01:33.286559: Epoch 279 +2025-10-30 22:01:33.287706: Current learning rate: 0.00745 +2025-10-30 22:10:30.587077: train_loss -0.3973 +2025-10-30 22:10:30.621346: val_loss -0.3623 +2025-10-30 22:10:30.622937: Pseudo dice [np.float32(0.8951), np.float32(0.7292), np.float32(0.7072), np.float32(0.5838), np.float32(0.8186), np.float32(0.7021), np.float32(0.8581), np.float32(0.8697), np.float32(0.9615), np.float32(0.9623), np.float32(0.9614), np.float32(0.8132), np.float32(0.7589), np.float32(0.8565), np.float32(0.9585), np.float32(0.3386), np.float32(0.2809)] +2025-10-30 22:10:30.625178: Epoch time: 537.31 s +2025-10-30 22:10:32.581523: +2025-10-30 22:10:32.582947: Epoch 280 +2025-10-30 22:10:32.584067: Current learning rate: 0.00744 +2025-10-30 22:19:31.522797: train_loss -0.3779 +2025-10-30 22:19:31.542485: val_loss -0.3874 +2025-10-30 22:19:31.543714: Pseudo dice [np.float32(0.909), np.float32(0.7587), np.float32(0.7002), np.float32(0.6396), np.float32(0.8465), np.float32(0.7796), np.float32(0.8725), np.float32(0.8721), np.float32(0.9302), np.float32(0.9394), np.float32(0.928), np.float32(0.827), np.float32(0.7239), np.float32(0.8534), np.float32(0.9014), np.float32(0.2763), np.float32(0.2648)] +2025-10-30 22:19:31.545201: Epoch time: 538.95 s +2025-10-30 22:19:33.431318: +2025-10-30 22:19:33.432687: Epoch 281 +2025-10-30 22:19:33.443694: Current learning rate: 0.00743 +2025-10-30 22:28:24.637934: train_loss -0.3638 +2025-10-30 22:28:24.704297: val_loss -0.3774 +2025-10-30 22:28:24.708905: Pseudo dice [np.float32(0.9212), np.float32(0.7443), np.float32(0.671), np.float32(0.6136), np.float32(0.8279), np.float32(0.7826), np.float32(0.861), np.float32(0.8598), np.float32(0.9027), np.float32(0.8992), np.float32(0.9536), np.float32(0.8333), np.float32(0.7569), np.float32(0.8149), np.float32(0.9022), np.float32(0.2545), np.float32(0.3067)] +2025-10-30 22:28:24.710789: Epoch time: 531.21 s +2025-10-30 22:28:26.771868: +2025-10-30 22:28:26.773375: Epoch 282 +2025-10-30 22:28:26.774499: Current learning rate: 0.00742 +2025-10-30 22:37:17.479014: train_loss -0.3897 +2025-10-30 22:37:17.491992: val_loss -0.4272 +2025-10-30 22:37:17.493289: Pseudo dice [np.float32(0.9032), np.float32(0.6814), np.float32(0.6937), np.float32(0.581), np.float32(0.8395), np.float32(0.744), np.float32(0.8857), np.float32(0.8712), np.float32(0.9358), np.float32(0.9516), np.float32(0.9545), np.float32(0.8065), np.float32(0.7534), np.float32(0.8089), np.float32(0.8776), np.float32(0.4213), np.float32(0.3715)] +2025-10-30 22:37:17.494412: Epoch time: 530.71 s +2025-10-30 22:37:21.148652: +2025-10-30 22:37:21.150002: Epoch 283 +2025-10-30 22:37:21.151329: Current learning rate: 0.00741 +2025-10-30 22:46:06.197267: train_loss -0.387 +2025-10-30 22:46:06.229568: val_loss -0.3647 +2025-10-30 22:46:06.231701: Pseudo dice [np.float32(0.9049), np.float32(0.6705), np.float32(0.646), np.float32(0.5908), np.float32(0.866), np.float32(0.7685), np.float32(0.8453), np.float32(0.8579), np.float32(0.9121), np.float32(0.9138), np.float32(0.9355), np.float32(0.818), np.float32(0.7364), np.float32(0.847), np.float32(0.8486), np.float32(0.3238), np.float32(0.3014)] +2025-10-30 22:46:06.233146: Epoch time: 525.05 s +2025-10-30 22:46:09.151292: +2025-10-30 22:46:09.152988: Epoch 284 +2025-10-30 22:46:09.154415: Current learning rate: 0.0074 +2025-10-30 22:54:54.383153: train_loss -0.3462 +2025-10-30 22:54:54.393443: val_loss -0.381 +2025-10-30 22:54:54.395262: Pseudo dice [np.float32(0.9205), np.float32(0.6817), np.float32(0.6866), np.float32(0.5448), np.float32(0.8698), np.float32(0.7575), np.float32(0.836), np.float32(0.8602), np.float32(0.9555), np.float32(0.9583), np.float32(0.936), np.float32(0.8124), np.float32(0.7392), np.float32(0.8541), np.float32(0.8505), np.float32(0.3451), np.float32(0.4219)] +2025-10-30 22:54:54.396641: Epoch time: 525.24 s +2025-10-30 22:54:56.604992: +2025-10-30 22:54:56.607654: Epoch 285 +2025-10-30 22:54:56.610993: Current learning rate: 0.00739 +2025-10-30 23:03:40.724455: train_loss -0.3835 +2025-10-30 23:03:40.739990: val_loss -0.4086 +2025-10-30 23:03:40.746394: Pseudo dice [np.float32(0.9383), np.float32(0.7471), np.float32(0.7317), np.float32(0.6398), np.float32(0.8253), np.float32(0.7579), np.float32(0.8096), np.float32(0.8611), np.float32(0.9707), np.float32(0.9671), np.float32(0.9598), np.float32(0.8101), np.float32(0.7691), np.float32(0.8173), np.float32(0.9503), np.float32(0.2823), np.float32(0.2285)] +2025-10-30 23:03:40.748077: Epoch time: 524.13 s +2025-10-30 23:03:42.818962: +2025-10-30 23:03:42.829216: Epoch 286 +2025-10-30 23:03:42.831275: Current learning rate: 0.00738 +2025-10-30 23:12:52.709111: train_loss -0.3595 +2025-10-30 23:12:52.727533: val_loss -0.3756 +2025-10-30 23:12:52.728782: Pseudo dice [np.float32(0.9242), np.float32(0.6569), np.float32(0.6744), np.float32(0.6151), np.float32(0.8605), np.float32(0.726), np.float32(0.802), np.float32(0.8562), np.float32(0.9473), np.float32(0.9379), np.float32(0.9534), np.float32(0.8195), np.float32(0.7516), np.float32(0.8752), np.float32(0.9188), np.float32(0.3402), np.float32(0.3798)] +2025-10-30 23:12:52.731752: Epoch time: 549.89 s +2025-10-30 23:12:54.983746: +2025-10-30 23:12:54.985244: Epoch 287 +2025-10-30 23:12:54.991636: Current learning rate: 0.00738 +2025-10-30 23:21:41.287078: train_loss -0.4053 +2025-10-30 23:21:41.351093: val_loss -0.4266 +2025-10-30 23:21:41.352777: Pseudo dice [np.float32(0.9247), np.float32(0.7135), np.float32(0.7014), np.float32(0.6034), np.float32(0.8376), np.float32(0.7705), np.float32(0.7512), np.float32(0.8782), np.float32(0.9651), np.float32(0.9608), np.float32(0.9621), np.float32(0.8269), np.float32(0.7454), np.float32(0.8386), np.float32(0.9631), np.float32(0.1413), np.float32(0.2032)] +2025-10-30 23:21:41.357646: Epoch time: 526.31 s +2025-10-30 23:21:43.644773: +2025-10-30 23:21:43.646265: Epoch 288 +2025-10-30 23:21:43.647707: Current learning rate: 0.00737 +2025-10-30 23:30:39.148377: train_loss -0.3958 +2025-10-30 23:30:39.162246: val_loss -0.3802 +2025-10-30 23:30:39.164038: Pseudo dice [np.float32(0.9263), np.float32(0.7349), np.float32(0.6981), np.float32(0.6813), np.float32(0.8379), np.float32(0.7834), np.float32(0.8541), np.float32(0.858), np.float32(0.943), np.float32(0.9497), np.float32(0.9586), np.float32(0.8315), np.float32(0.7572), np.float32(0.8136), np.float32(0.9407), np.float32(0.1869), np.float32(0.2091)] +2025-10-30 23:30:39.165440: Epoch time: 535.51 s +2025-10-30 23:30:41.393275: +2025-10-30 23:30:41.395143: Epoch 289 +2025-10-30 23:30:41.396807: Current learning rate: 0.00736 +2025-10-30 23:39:40.437863: train_loss -0.3819 +2025-10-30 23:39:40.477165: val_loss -0.4126 +2025-10-30 23:39:40.479091: Pseudo dice [np.float32(0.9212), np.float32(0.7411), np.float32(0.7043), np.float32(0.6408), np.float32(0.824), np.float32(0.742), np.float32(0.8323), np.float32(0.8805), np.float32(0.9775), np.float32(0.9799), np.float32(0.964), np.float32(0.8396), np.float32(0.773), np.float32(0.8208), np.float32(0.9658), np.float32(0.3368), np.float32(0.1302)] +2025-10-30 23:39:40.481852: Epoch time: 539.05 s +2025-10-30 23:39:42.672888: +2025-10-30 23:39:42.674619: Epoch 290 +2025-10-30 23:39:42.676356: Current learning rate: 0.00735 +2025-10-30 23:48:53.026779: train_loss -0.388 +2025-10-30 23:48:53.041817: val_loss -0.4477 +2025-10-30 23:48:53.043468: Pseudo dice [np.float32(0.932), np.float32(0.7511), np.float32(0.7209), np.float32(0.6482), np.float32(0.8651), np.float32(0.784), np.float32(0.8251), np.float32(0.8902), np.float32(0.9619), np.float32(0.9604), np.float32(0.9596), np.float32(0.8253), np.float32(0.7709), np.float32(0.8483), np.float32(0.9301), np.float32(0.3385), np.float32(0.3068)] +2025-10-30 23:48:53.046338: Epoch time: 550.36 s +2025-10-30 23:48:55.181946: +2025-10-30 23:48:55.183175: Epoch 291 +2025-10-30 23:48:55.185538: Current learning rate: 0.00734 +2025-10-30 23:57:57.381359: train_loss -0.4069 +2025-10-30 23:57:57.420301: val_loss -0.4157 +2025-10-30 23:57:57.424661: Pseudo dice [np.float32(0.9137), np.float32(0.7314), np.float32(0.7173), np.float32(0.5967), np.float32(0.8445), np.float32(0.7504), np.float32(0.8364), np.float32(0.8423), np.float32(0.9747), np.float32(0.9671), np.float32(0.9572), np.float32(0.821), np.float32(0.7618), np.float32(0.8339), np.float32(0.9538), np.float32(0.346), np.float32(0.2717)] +2025-10-30 23:57:57.426588: Epoch time: 542.2 s +2025-10-30 23:57:59.711550: +2025-10-30 23:57:59.714592: Epoch 292 +2025-10-30 23:57:59.716137: Current learning rate: 0.00733 +2025-10-31 00:06:59.188708: train_loss -0.3839 +2025-10-31 00:06:59.211173: val_loss -0.4282 +2025-10-31 00:06:59.240057: Pseudo dice [np.float32(0.933), np.float32(0.7493), np.float32(0.6852), np.float32(0.6608), np.float32(0.8392), np.float32(0.7695), np.float32(0.8323), np.float32(0.8658), np.float32(0.9777), np.float32(0.9758), np.float32(0.9619), np.float32(0.8342), np.float32(0.766), np.float32(0.8477), np.float32(0.9578), np.float32(0.3802), np.float32(0.3817)] +2025-10-31 00:06:59.243505: Epoch time: 539.48 s +2025-10-31 00:07:01.362314: +2025-10-31 00:07:01.364298: Epoch 293 +2025-10-31 00:07:01.365723: Current learning rate: 0.00732 +2025-10-31 00:15:58.651680: train_loss -0.4024 +2025-10-31 00:15:58.661659: val_loss -0.4358 +2025-10-31 00:15:58.668332: Pseudo dice [np.float32(0.9323), np.float32(0.7061), np.float32(0.668), np.float32(0.6459), np.float32(0.8614), np.float32(0.7847), np.float32(0.8619), np.float32(0.856), np.float32(0.9605), np.float32(0.9676), np.float32(0.964), np.float32(0.8257), np.float32(0.7622), np.float32(0.8582), np.float32(0.9565), np.float32(0.4415), np.float32(0.3089)] +2025-10-31 00:15:58.669924: Epoch time: 537.3 s +2025-10-31 00:16:00.817378: +2025-10-31 00:16:00.819406: Epoch 294 +2025-10-31 00:16:00.820766: Current learning rate: 0.00731 +2025-10-31 00:24:55.340917: train_loss -0.4035 +2025-10-31 00:24:55.384475: val_loss -0.4611 +2025-10-31 00:24:55.386591: Pseudo dice [np.float32(0.9308), np.float32(0.7617), np.float32(0.7042), np.float32(0.6068), np.float32(0.8296), np.float32(0.7925), np.float32(0.7605), np.float32(0.8692), np.float32(0.966), np.float32(0.9723), np.float32(0.9606), np.float32(0.8406), np.float32(0.7567), np.float32(0.8681), np.float32(0.9601), np.float32(0.3174), np.float32(0.3488)] +2025-10-31 00:24:55.388605: Epoch time: 534.53 s +2025-10-31 00:24:57.508886: +2025-10-31 00:24:57.510349: Epoch 295 +2025-10-31 00:24:57.511457: Current learning rate: 0.0073 +2025-10-31 00:34:03.494512: train_loss -0.4071 +2025-10-31 00:34:03.507119: val_loss -0.3938 +2025-10-31 00:34:03.511088: Pseudo dice [np.float32(0.9186), np.float32(0.6917), np.float32(0.6653), np.float32(0.5697), np.float32(0.8275), np.float32(0.7645), np.float32(0.8905), np.float32(0.8588), np.float32(0.9648), np.float32(0.9603), np.float32(0.9524), np.float32(0.8116), np.float32(0.7211), np.float32(0.8451), np.float32(0.9407), np.float32(0.3313), np.float32(0.3076)] +2025-10-31 00:34:03.515129: Epoch time: 545.99 s +2025-10-31 00:34:05.645895: +2025-10-31 00:34:05.647431: Epoch 296 +2025-10-31 00:34:05.648978: Current learning rate: 0.00729 +2025-10-31 00:43:02.923449: train_loss -0.3994 +2025-10-31 00:43:02.960704: val_loss -0.4163 +2025-10-31 00:43:02.962683: Pseudo dice [np.float32(0.9205), np.float32(0.7686), np.float32(0.7263), np.float32(0.6169), np.float32(0.8681), np.float32(0.7696), np.float32(0.8512), np.float32(0.8531), np.float32(0.9367), np.float32(0.9392), np.float32(0.9546), np.float32(0.8356), np.float32(0.7696), np.float32(0.8402), np.float32(0.944), np.float32(0.3227), np.float32(0.2542)] +2025-10-31 00:43:02.965002: Epoch time: 537.29 s +2025-10-31 00:43:04.978731: +2025-10-31 00:43:04.981306: Epoch 297 +2025-10-31 00:43:04.983687: Current learning rate: 0.00728 +2025-10-31 00:51:55.193094: train_loss -0.4173 +2025-10-31 00:51:55.229233: val_loss -0.3782 +2025-10-31 00:51:55.233781: Pseudo dice [np.float32(0.8881), np.float32(0.7279), np.float32(0.6958), np.float32(0.6247), np.float32(0.8548), np.float32(0.7467), np.float32(0.8339), np.float32(0.865), np.float32(0.9713), np.float32(0.9685), np.float32(0.9607), np.float32(0.8164), np.float32(0.7387), np.float32(0.8425), np.float32(0.9591), np.float32(0.1339), np.float32(0.2131)] +2025-10-31 00:51:55.237088: Epoch time: 530.22 s +2025-10-31 00:51:57.394065: +2025-10-31 00:51:57.395866: Epoch 298 +2025-10-31 00:51:57.397489: Current learning rate: 0.00727 +2025-10-31 01:00:58.005210: train_loss -0.4169 +2025-10-31 01:00:58.046596: val_loss -0.454 +2025-10-31 01:00:58.050027: Pseudo dice [np.float32(0.9319), np.float32(0.7062), np.float32(0.6953), np.float32(0.6009), np.float32(0.8639), np.float32(0.7823), np.float32(0.8401), np.float32(0.8708), np.float32(0.9505), np.float32(0.9406), np.float32(0.9563), np.float32(0.8276), np.float32(0.7814), np.float32(0.8598), np.float32(0.9083), np.float32(0.3878), np.float32(0.422)] +2025-10-31 01:00:58.052417: Epoch time: 540.62 s +2025-10-31 01:01:00.131592: +2025-10-31 01:01:00.133364: Epoch 299 +2025-10-31 01:01:00.134400: Current learning rate: 0.00726 +2025-10-31 01:09:55.883778: train_loss -0.4077 +2025-10-31 01:09:55.931432: val_loss -0.4263 +2025-10-31 01:09:55.932894: Pseudo dice [np.float32(0.9192), np.float32(0.7725), np.float32(0.7024), np.float32(0.6276), np.float32(0.8713), np.float32(0.7927), np.float32(0.856), np.float32(0.8751), np.float32(0.9653), np.float32(0.9716), np.float32(0.9335), np.float32(0.8045), np.float32(0.7414), np.float32(0.863), np.float32(0.9481), np.float32(0.3272), np.float32(0.3477)] +2025-10-31 01:09:55.940587: Epoch time: 535.76 s +2025-10-31 01:10:01.301332: +2025-10-31 01:10:01.302974: Epoch 300 +2025-10-31 01:10:01.305516: Current learning rate: 0.00725 +2025-10-31 01:19:11.699813: train_loss -0.398 +2025-10-31 01:19:11.706555: val_loss -0.4083 +2025-10-31 01:19:11.708528: Pseudo dice [np.float32(0.9211), np.float32(0.7274), np.float32(0.6985), np.float32(0.6628), np.float32(0.8346), np.float32(0.7569), np.float32(0.8821), np.float32(0.8613), np.float32(0.9537), np.float32(0.9533), np.float32(0.9598), np.float32(0.8249), np.float32(0.7841), np.float32(0.8403), np.float32(0.962), np.float32(0.3956), np.float32(0.2269)] +2025-10-31 01:19:11.710933: Epoch time: 550.4 s +2025-10-31 01:19:11.712279: Yayy! New best EMA pseudo Dice: 0.7731000185012817 +2025-10-31 01:19:16.172308: +2025-10-31 01:19:16.177773: Epoch 301 +2025-10-31 01:19:16.185090: Current learning rate: 0.00724 +2025-10-31 01:28:08.646334: train_loss -0.4009 +2025-10-31 01:28:08.663951: val_loss -0.3884 +2025-10-31 01:28:08.665957: Pseudo dice [np.float32(0.9208), np.float32(0.7454), np.float32(0.7198), np.float32(0.6453), np.float32(0.8469), np.float32(0.7757), np.float32(0.8811), np.float32(0.888), np.float32(0.952), np.float32(0.934), np.float32(0.9579), np.float32(0.8476), np.float32(0.7788), np.float32(0.8408), np.float32(0.9253), np.float32(0.3934), np.float32(0.382)] +2025-10-31 01:28:08.667581: Epoch time: 532.48 s +2025-10-31 01:28:08.669090: Yayy! New best EMA pseudo Dice: 0.7748000025749207 +2025-10-31 01:28:13.162244: +2025-10-31 01:28:13.182940: Epoch 302 +2025-10-31 01:28:13.184662: Current learning rate: 0.00724 +2025-10-31 01:37:09.983896: train_loss -0.4066 +2025-10-31 01:37:09.990130: val_loss -0.4216 +2025-10-31 01:37:09.991716: Pseudo dice [np.float32(0.9268), np.float32(0.7906), np.float32(0.6921), np.float32(0.5936), np.float32(0.8255), np.float32(0.7588), np.float32(0.7993), np.float32(0.8815), np.float32(0.9725), np.float32(0.9674), np.float32(0.9582), np.float32(0.7483), np.float32(0.7052), np.float32(0.8361), np.float32(0.9402), np.float32(0.388), np.float32(0.3685)] +2025-10-31 01:37:09.993181: Epoch time: 536.83 s +2025-10-31 01:37:27.511175: +2025-10-31 01:37:27.512360: Epoch 303 +2025-10-31 01:37:27.513829: Current learning rate: 0.00723 +2025-10-31 01:46:38.073944: train_loss -0.4038 +2025-10-31 01:46:38.135540: val_loss -0.4026 +2025-10-31 01:46:38.137226: Pseudo dice [np.float32(0.9166), np.float32(0.7343), np.float32(0.6461), np.float32(0.6012), np.float32(0.8341), np.float32(0.7867), np.float32(0.8663), np.float32(0.8802), np.float32(0.9108), np.float32(0.9217), np.float32(0.9639), np.float32(0.8423), np.float32(0.7524), np.float32(0.8468), np.float32(0.9351), np.float32(0.2953), np.float32(0.1399)] +2025-10-31 01:46:38.139722: Epoch time: 550.57 s +2025-10-31 01:46:40.108503: +2025-10-31 01:46:40.110030: Epoch 304 +2025-10-31 01:46:40.113395: Current learning rate: 0.00722 +2025-10-31 01:55:32.423496: train_loss -0.4086 +2025-10-31 01:55:32.438900: val_loss -0.4405 +2025-10-31 01:55:32.440315: Pseudo dice [np.float32(0.9265), np.float32(0.4465), np.float32(0.7063), np.float32(0.6531), np.float32(0.8687), np.float32(0.7697), np.float32(0.8857), np.float32(0.8723), np.float32(0.9611), np.float32(0.9739), np.float32(0.9461), np.float32(0.8267), np.float32(0.7608), np.float32(0.8501), np.float32(0.9423), np.float32(0.3942), np.float32(0.4224)] +2025-10-31 01:55:32.441518: Epoch time: 532.32 s +2025-10-31 01:55:34.474596: +2025-10-31 01:55:34.476506: Epoch 305 +2025-10-31 01:55:34.480871: Current learning rate: 0.00721 +2025-10-31 02:04:36.897287: train_loss -0.4383 +2025-10-31 02:04:36.941121: val_loss -0.3967 +2025-10-31 02:04:36.942852: Pseudo dice [np.float32(0.9115), np.float32(0.7516), np.float32(0.6749), np.float32(0.6452), np.float32(0.8495), np.float32(0.7707), np.float32(0.8162), np.float32(0.8655), np.float32(0.9068), np.float32(0.9188), np.float32(0.9578), np.float32(0.7789), np.float32(0.7542), np.float32(0.8265), np.float32(0.8692), np.float32(0.358), np.float32(0.2113)] +2025-10-31 02:04:37.005144: Epoch time: 542.43 s +2025-10-31 02:04:39.151873: +2025-10-31 02:04:39.154426: Epoch 306 +2025-10-31 02:04:39.155669: Current learning rate: 0.0072 +2025-10-31 02:13:32.770961: train_loss -0.4288 +2025-10-31 02:13:32.786734: val_loss -0.4192 +2025-10-31 02:13:32.788274: Pseudo dice [np.float32(0.8846), np.float32(0.7203), np.float32(0.6915), np.float32(0.5909), np.float32(0.7996), np.float32(0.7477), np.float32(0.8583), np.float32(0.8956), np.float32(0.9532), np.float32(0.9583), np.float32(0.9658), np.float32(0.8484), np.float32(0.7574), np.float32(0.8084), np.float32(0.9576), np.float32(0.3995), np.float32(0.3949)] +2025-10-31 02:13:32.789643: Epoch time: 533.62 s +2025-10-31 02:13:34.933420: +2025-10-31 02:13:34.941552: Epoch 307 +2025-10-31 02:13:34.956137: Current learning rate: 0.00719 +2025-10-31 02:22:24.440589: train_loss -0.4079 +2025-10-31 02:22:24.483254: val_loss -0.3921 +2025-10-31 02:22:24.485915: Pseudo dice [np.float32(0.9383), np.float32(0.7549), np.float32(0.7284), np.float32(0.6017), np.float32(0.8164), np.float32(0.7895), np.float32(0.8219), np.float32(0.85), np.float32(0.961), np.float32(0.9596), np.float32(0.9559), np.float32(0.8201), np.float32(0.764), np.float32(0.8211), np.float32(0.9423), np.float32(0.3806), np.float32(0.5093)] +2025-10-31 02:22:24.487256: Epoch time: 529.51 s +2025-10-31 02:22:26.720806: +2025-10-31 02:22:26.722262: Epoch 308 +2025-10-31 02:22:26.723955: Current learning rate: 0.00718 +2025-10-31 02:31:29.332468: train_loss -0.4186 +2025-10-31 02:31:29.338480: val_loss -0.4229 +2025-10-31 02:31:29.339819: Pseudo dice [np.float32(0.913), np.float32(0.7289), np.float32(0.6793), np.float32(0.6098), np.float32(0.849), np.float32(0.7495), np.float32(0.8616), np.float32(0.8797), np.float32(0.9382), np.float32(0.9302), np.float32(0.9611), np.float32(0.8444), np.float32(0.7329), np.float32(0.8472), np.float32(0.9528), np.float32(0.3327), np.float32(0.4093)] +2025-10-31 02:31:29.341024: Epoch time: 542.62 s +2025-10-31 02:31:31.483463: +2025-10-31 02:31:31.485397: Epoch 309 +2025-10-31 02:31:31.487054: Current learning rate: 0.00717 +2025-10-31 02:40:24.601063: train_loss -0.4514 +2025-10-31 02:40:24.636176: val_loss -0.4393 +2025-10-31 02:40:24.637925: Pseudo dice [np.float32(0.9054), np.float32(0.7545), np.float32(0.6909), np.float32(0.6893), np.float32(0.8669), np.float32(0.7701), np.float32(0.8892), np.float32(0.8748), np.float32(0.9301), np.float32(0.9343), np.float32(0.9638), np.float32(0.8334), np.float32(0.7562), np.float32(0.8672), np.float32(0.9445), np.float32(0.264), np.float32(0.3863)] +2025-10-31 02:40:24.640921: Epoch time: 533.12 s +2025-10-31 02:40:24.642420: Yayy! New best EMA pseudo Dice: 0.7753000259399414 +2025-10-31 02:40:30.166346: +2025-10-31 02:40:30.170369: Epoch 310 +2025-10-31 02:40:30.181104: Current learning rate: 0.00716 +2025-10-31 02:49:14.468399: train_loss -0.4138 +2025-10-31 02:49:14.601646: val_loss -0.4311 +2025-10-31 02:49:14.603552: Pseudo dice [np.float32(0.9201), np.float32(0.7237), np.float32(0.7007), np.float32(0.6557), np.float32(0.8268), np.float32(0.7706), np.float32(0.8192), np.float32(0.8491), np.float32(0.9659), np.float32(0.9643), np.float32(0.9591), np.float32(0.8347), np.float32(0.7727), np.float32(0.8368), np.float32(0.9273), np.float32(0.2595), np.float32(0.1851)] +2025-10-31 02:49:14.605255: Epoch time: 524.31 s +2025-10-31 02:49:16.689080: +2025-10-31 02:49:16.704948: Epoch 311 +2025-10-31 02:49:16.706201: Current learning rate: 0.00715 +2025-10-31 02:58:14.890726: train_loss -0.3948 +2025-10-31 02:58:14.915204: val_loss -0.4176 +2025-10-31 02:58:14.919366: Pseudo dice [np.float32(0.9139), np.float32(0.7256), np.float32(0.6688), np.float32(0.6158), np.float32(0.817), np.float32(0.7436), np.float32(0.8556), np.float32(0.8623), np.float32(0.9455), np.float32(0.9342), np.float32(0.9614), np.float32(0.8376), np.float32(0.7849), np.float32(0.8079), np.float32(0.9494), np.float32(0.2742), np.float32(0.3064)] +2025-10-31 02:58:14.921591: Epoch time: 538.21 s +2025-10-31 02:58:17.473155: +2025-10-31 02:58:17.481725: Epoch 312 +2025-10-31 02:58:17.482979: Current learning rate: 0.00714 +2025-10-31 03:07:21.351681: train_loss -0.4202 +2025-10-31 03:07:21.433689: val_loss -0.4487 +2025-10-31 03:07:21.434909: Pseudo dice [np.float32(0.9356), np.float32(0.7634), np.float32(0.7412), np.float32(0.6508), np.float32(0.8668), np.float32(0.7814), np.float32(0.8848), np.float32(0.8694), np.float32(0.9531), np.float32(0.9478), np.float32(0.9563), np.float32(0.8055), np.float32(0.7545), np.float32(0.8549), np.float32(0.9573), np.float32(0.423), np.float32(0.426)] +2025-10-31 03:07:21.436144: Epoch time: 543.88 s +2025-10-31 03:07:21.438056: Yayy! New best EMA pseudo Dice: 0.7756999731063843 +2025-10-31 03:07:26.223281: +2025-10-31 03:07:26.224805: Epoch 313 +2025-10-31 03:07:26.225916: Current learning rate: 0.00713 +2025-10-31 03:16:06.855246: train_loss -0.4203 +2025-10-31 03:16:06.890168: val_loss -0.4192 +2025-10-31 03:16:06.892233: Pseudo dice [np.float32(0.9046), np.float32(0.7549), np.float32(0.6785), np.float32(0.6206), np.float32(0.8576), np.float32(0.7447), np.float32(0.871), np.float32(0.8669), np.float32(0.9623), np.float32(0.9652), np.float32(0.9607), np.float32(0.8247), np.float32(0.7479), np.float32(0.8404), np.float32(0.9376), np.float32(0.2489), np.float32(0.1552)] +2025-10-31 03:16:06.894103: Epoch time: 520.64 s +2025-10-31 03:16:08.856044: +2025-10-31 03:16:08.857832: Epoch 314 +2025-10-31 03:16:08.859152: Current learning rate: 0.00712 +2025-10-31 03:25:09.291755: train_loss -0.4151 +2025-10-31 03:25:09.370255: val_loss -0.4403 +2025-10-31 03:25:09.371618: Pseudo dice [np.float32(0.927), np.float32(0.7567), np.float32(0.7242), np.float32(0.6757), np.float32(0.8737), np.float32(0.7854), np.float32(0.8648), np.float32(0.8833), np.float32(0.9658), np.float32(0.8921), np.float32(0.9662), np.float32(0.845), np.float32(0.7927), np.float32(0.8613), np.float32(0.9526), np.float32(0.3577), np.float32(0.2733)] +2025-10-31 03:25:09.378347: Epoch time: 540.44 s +2025-10-31 03:25:11.533906: +2025-10-31 03:25:11.535735: Epoch 315 +2025-10-31 03:25:11.540192: Current learning rate: 0.00711 +2025-10-31 03:34:02.754149: train_loss -0.4164 +2025-10-31 03:34:02.805772: val_loss -0.4314 +2025-10-31 03:34:02.807151: Pseudo dice [np.float32(0.9255), np.float32(0.7396), np.float32(0.6752), np.float32(0.6383), np.float32(0.8628), np.float32(0.7524), np.float32(0.729), np.float32(0.8658), np.float32(0.9773), np.float32(0.9808), np.float32(0.9629), np.float32(0.8245), np.float32(0.7584), np.float32(0.8596), np.float32(0.9522), np.float32(0.3034), np.float32(0.3168)] +2025-10-31 03:34:02.809001: Epoch time: 531.22 s +2025-10-31 03:34:04.968697: +2025-10-31 03:34:04.971682: Epoch 316 +2025-10-31 03:34:04.972869: Current learning rate: 0.0071 +2025-10-31 03:42:45.905311: train_loss -0.4089 +2025-10-31 03:42:45.927097: val_loss -0.3977 +2025-10-31 03:42:45.931985: Pseudo dice [np.float32(0.9168), np.float32(0.7025), np.float32(0.6944), np.float32(0.5677), np.float32(0.8443), np.float32(0.7778), np.float32(0.7164), np.float32(0.8547), np.float32(0.9559), np.float32(0.9505), np.float32(0.9628), np.float32(0.823), np.float32(0.7634), np.float32(0.8504), np.float32(0.9538), np.float32(0.2968), np.float32(0.2495)] +2025-10-31 03:42:45.933737: Epoch time: 520.94 s +2025-10-31 03:42:47.962426: +2025-10-31 03:42:47.965726: Epoch 317 +2025-10-31 03:42:47.967381: Current learning rate: 0.0071 +2025-10-31 03:51:36.497310: train_loss -0.4337 +2025-10-31 03:51:36.520329: val_loss -0.4101 +2025-10-31 03:51:36.528823: Pseudo dice [np.float32(0.9034), np.float32(0.7785), np.float32(0.6912), np.float32(0.6158), np.float32(0.8582), np.float32(0.7574), np.float32(0.8448), np.float32(0.8683), np.float32(0.9779), np.float32(0.9798), np.float32(0.9648), np.float32(0.8211), np.float32(0.7731), np.float32(0.864), np.float32(0.9495), np.float32(0.3588), np.float32(0.2079)] +2025-10-31 03:51:36.530255: Epoch time: 528.54 s +2025-10-31 03:51:38.625344: +2025-10-31 03:51:38.626784: Epoch 318 +2025-10-31 03:51:38.628129: Current learning rate: 0.00709 +2025-10-31 04:00:19.549164: train_loss -0.4073 +2025-10-31 04:00:19.595270: val_loss -0.4332 +2025-10-31 04:00:19.597182: Pseudo dice [np.float32(0.9172), np.float32(0.7564), np.float32(0.7005), np.float32(0.6025), np.float32(0.8327), np.float32(0.7897), np.float32(0.8457), np.float32(0.88), np.float32(0.9596), np.float32(0.9586), np.float32(0.9555), np.float32(0.839), np.float32(0.7709), np.float32(0.836), np.float32(0.9194), np.float32(0.3419), np.float32(0.3591)] +2025-10-31 04:00:19.601998: Epoch time: 520.93 s +2025-10-31 04:00:21.755153: +2025-10-31 04:00:21.757005: Epoch 319 +2025-10-31 04:00:21.758940: Current learning rate: 0.00708 +2025-10-31 04:09:30.234220: train_loss -0.4205 +2025-10-31 04:09:30.288367: val_loss -0.4135 +2025-10-31 04:09:30.289914: Pseudo dice [np.float32(0.9382), np.float32(0.7136), np.float32(0.6775), np.float32(0.6204), np.float32(0.852), np.float32(0.7775), np.float32(0.774), np.float32(0.8748), np.float32(0.9477), np.float32(0.9266), np.float32(0.9574), np.float32(0.8333), np.float32(0.7748), np.float32(0.8417), np.float32(0.9486), np.float32(0.396), np.float32(0.3168)] +2025-10-31 04:09:30.291078: Epoch time: 548.48 s +2025-10-31 04:09:32.343660: +2025-10-31 04:09:32.344978: Epoch 320 +2025-10-31 04:09:32.346231: Current learning rate: 0.00707 +2025-10-31 04:18:32.046736: train_loss -0.4269 +2025-10-31 04:18:32.097617: val_loss -0.4323 +2025-10-31 04:18:32.099101: Pseudo dice [np.float32(0.9235), np.float32(0.7587), np.float32(0.7408), np.float32(0.6414), np.float32(0.8477), np.float32(0.7822), np.float32(0.8648), np.float32(0.8783), np.float32(0.9487), np.float32(0.9548), np.float32(0.9673), np.float32(0.8353), np.float32(0.7861), np.float32(0.8475), np.float32(0.9484), np.float32(0.4449), np.float32(0.3814)] +2025-10-31 04:18:32.100499: Epoch time: 539.71 s +2025-10-31 04:18:32.101740: Yayy! New best EMA pseudo Dice: 0.7767999768257141 +2025-10-31 04:18:37.216302: +2025-10-31 04:18:37.217786: Epoch 321 +2025-10-31 04:18:37.219283: Current learning rate: 0.00706 +2025-10-31 04:27:29.589498: train_loss -0.4347 +2025-10-31 04:27:29.601693: val_loss -0.4228 +2025-10-31 04:27:29.602972: Pseudo dice [np.float32(0.8994), np.float32(0.664), np.float32(0.7372), np.float32(0.5932), np.float32(0.8382), np.float32(0.7779), np.float32(0.882), np.float32(0.8701), np.float32(0.9615), np.float32(0.9491), np.float32(0.9607), np.float32(0.806), np.float32(0.7826), np.float32(0.8472), np.float32(0.9501), np.float32(0.3499), np.float32(0.2913)] +2025-10-31 04:27:29.606009: Epoch time: 532.38 s +2025-10-31 04:27:31.626979: +2025-10-31 04:27:31.631326: Epoch 322 +2025-10-31 04:27:31.635706: Current learning rate: 0.00705 +2025-10-31 04:36:37.691262: train_loss -0.4056 +2025-10-31 04:36:37.709432: val_loss -0.399 +2025-10-31 04:36:37.720747: Pseudo dice [np.float32(0.9187), np.float32(0.734), np.float32(0.6944), np.float32(0.6258), np.float32(0.8394), np.float32(0.7897), np.float32(0.8666), np.float32(0.8537), np.float32(0.9614), np.float32(0.9626), np.float32(0.9412), np.float32(0.819), np.float32(0.7917), np.float32(0.8642), np.float32(0.9068), np.float32(0.3705), np.float32(0.3091)] +2025-10-31 04:36:37.722096: Epoch time: 546.07 s +2025-10-31 04:36:37.723714: Yayy! New best EMA pseudo Dice: 0.7767999768257141 +2025-10-31 04:36:42.347591: +2025-10-31 04:36:42.349314: Epoch 323 +2025-10-31 04:36:42.351471: Current learning rate: 0.00704 +2025-10-31 04:45:43.836278: train_loss -0.4102 +2025-10-31 04:45:43.889681: val_loss -0.4369 +2025-10-31 04:45:43.891464: Pseudo dice [np.float32(0.9021), np.float32(0.7837), np.float32(0.689), np.float32(0.593), np.float32(0.8602), np.float32(0.7836), np.float32(0.8865), np.float32(0.8615), np.float32(0.9767), np.float32(0.975), np.float32(0.9369), np.float32(0.8379), np.float32(0.7547), np.float32(0.867), np.float32(0.922), np.float32(0.4299), np.float32(0.3315)] +2025-10-31 04:45:43.892940: Epoch time: 541.49 s +2025-10-31 04:45:43.894447: Yayy! New best EMA pseudo Dice: 0.777899980545044 +2025-10-31 04:45:48.318047: +2025-10-31 04:45:48.319998: Epoch 324 +2025-10-31 04:45:48.321219: Current learning rate: 0.00703 +2025-10-31 04:54:48.086561: train_loss -0.3659 +2025-10-31 04:54:48.100737: val_loss -0.3334 +2025-10-31 04:54:48.102636: Pseudo dice [np.float32(0.9091), np.float32(0.7048), np.float32(0.684), np.float32(0.5562), np.float32(0.8327), np.float32(0.7149), np.float32(0.8215), np.float32(0.8403), np.float32(0.9032), np.float32(0.8867), np.float32(0.9458), np.float32(0.7975), np.float32(0.7425), np.float32(0.8233), np.float32(0.8407), np.float32(0.3913), np.float32(0.273)] +2025-10-31 04:54:48.104020: Epoch time: 539.77 s +2025-10-31 04:55:04.961689: +2025-10-31 04:55:04.963347: Epoch 325 +2025-10-31 04:55:04.965283: Current learning rate: 0.00702 +2025-10-31 05:03:48.958000: train_loss -0.379 +2025-10-31 05:03:48.978151: val_loss -0.4294 +2025-10-31 05:03:48.991985: Pseudo dice [np.float32(0.9085), np.float32(0.7635), np.float32(0.71), np.float32(0.6263), np.float32(0.8464), np.float32(0.7422), np.float32(0.8667), np.float32(0.8617), np.float32(0.9159), np.float32(0.9437), np.float32(0.9569), np.float32(0.8338), np.float32(0.726), np.float32(0.8138), np.float32(0.9124), np.float32(0.2778), np.float32(0.2288)] +2025-10-31 05:03:48.993984: Epoch time: 524.0 s +2025-10-31 05:03:51.030529: +2025-10-31 05:03:51.032039: Epoch 326 +2025-10-31 05:03:51.033834: Current learning rate: 0.00701 +2025-10-31 05:12:35.074217: train_loss -0.4069 +2025-10-31 05:12:35.144458: val_loss -0.3955 +2025-10-31 05:12:35.150281: Pseudo dice [np.float32(0.9319), np.float32(0.7177), np.float32(0.673), np.float32(0.5874), np.float32(0.8488), np.float32(0.7724), np.float32(0.8711), np.float32(0.893), np.float32(0.9262), np.float32(0.9105), np.float32(0.9535), np.float32(0.8409), np.float32(0.7541), np.float32(0.8635), np.float32(0.893), np.float32(0.4193), np.float32(0.2735)] +2025-10-31 05:12:35.152051: Epoch time: 524.05 s +2025-10-31 05:12:37.138835: +2025-10-31 05:12:37.141294: Epoch 327 +2025-10-31 05:12:37.146120: Current learning rate: 0.007 +2025-10-31 05:21:32.847783: train_loss -0.4134 +2025-10-31 05:21:32.865074: val_loss -0.4162 +2025-10-31 05:21:32.871604: Pseudo dice [np.float32(0.9057), np.float32(0.7375), np.float32(0.6881), np.float32(0.6403), np.float32(0.8208), np.float32(0.7679), np.float32(0.8473), np.float32(0.8494), np.float32(0.9574), np.float32(0.9656), np.float32(0.9606), np.float32(0.8206), np.float32(0.758), np.float32(0.8402), np.float32(0.9422), np.float32(0.2957), np.float32(0.2183)] +2025-10-31 05:21:32.874840: Epoch time: 535.71 s +2025-10-31 05:21:34.867760: +2025-10-31 05:21:34.869163: Epoch 328 +2025-10-31 05:21:34.870420: Current learning rate: 0.00699 +2025-10-31 05:30:36.117091: train_loss -0.386 +2025-10-31 05:30:36.128796: val_loss -0.3356 +2025-10-31 05:30:36.130150: Pseudo dice [np.float32(0.9014), np.float32(0.708), np.float32(0.6717), np.float32(0.5771), np.float32(0.7892), np.float32(0.7466), np.float32(0.7499), np.float32(0.8598), np.float32(0.9216), np.float32(0.9135), np.float32(0.9325), np.float32(0.7523), np.float32(0.7977), np.float32(0.8462), np.float32(0.6874), np.float32(0.2473), np.float32(0.3634)] +2025-10-31 05:30:36.132829: Epoch time: 541.25 s +2025-10-31 05:30:38.714029: +2025-10-31 05:30:38.719823: Epoch 329 +2025-10-31 05:30:38.722581: Current learning rate: 0.00698 +2025-10-31 05:39:35.504850: train_loss -0.352 +2025-10-31 05:39:35.545517: val_loss -0.4007 +2025-10-31 05:39:35.548231: Pseudo dice [np.float32(0.9237), np.float32(0.7402), np.float32(0.6891), np.float32(0.6192), np.float32(0.8318), np.float32(0.7632), np.float32(0.8615), np.float32(0.8698), np.float32(0.9052), np.float32(0.964), np.float32(0.9591), np.float32(0.7943), np.float32(0.7669), np.float32(0.8513), np.float32(0.92), np.float32(0.352), np.float32(0.3291)] +2025-10-31 05:39:35.550787: Epoch time: 536.8 s +2025-10-31 05:39:39.247247: +2025-10-31 05:39:39.249075: Epoch 330 +2025-10-31 05:39:39.250555: Current learning rate: 0.00697 +2025-10-31 05:48:42.316827: train_loss -0.4065 +2025-10-31 05:48:42.324389: val_loss -0.3991 +2025-10-31 05:48:42.327304: Pseudo dice [np.float32(0.9009), np.float32(0.7564), np.float32(0.6963), np.float32(0.654), np.float32(0.8386), np.float32(0.7396), np.float32(0.859), np.float32(0.8755), np.float32(0.9682), np.float32(0.9694), np.float32(0.9655), np.float32(0.8244), np.float32(0.7433), np.float32(0.8425), np.float32(0.9483), np.float32(0.325), np.float32(0.3512)] +2025-10-31 05:48:42.328715: Epoch time: 543.07 s +2025-10-31 05:48:44.371766: +2025-10-31 05:48:44.373614: Epoch 331 +2025-10-31 05:48:44.375479: Current learning rate: 0.00696 +2025-10-31 05:57:47.811765: train_loss -0.4358 +2025-10-31 05:57:47.834304: val_loss -0.4068 +2025-10-31 05:57:47.836492: Pseudo dice [np.float32(0.9185), np.float32(0.7695), np.float32(0.7213), np.float32(0.552), np.float32(0.8366), np.float32(0.7718), np.float32(0.8667), np.float32(0.8727), np.float32(0.9569), np.float32(0.96), np.float32(0.9673), np.float32(0.8417), np.float32(0.7536), np.float32(0.836), np.float32(0.9684), np.float32(0.3552), np.float32(0.3691)] +2025-10-31 05:57:47.837814: Epoch time: 543.45 s +2025-10-31 05:57:49.892691: +2025-10-31 05:57:49.894258: Epoch 332 +2025-10-31 05:57:49.898197: Current learning rate: 0.00696 +2025-10-31 06:06:39.742780: train_loss -0.3955 +2025-10-31 06:06:39.770106: val_loss -0.4217 +2025-10-31 06:06:39.772128: Pseudo dice [np.float32(0.927), np.float32(0.747), np.float32(0.7102), np.float32(0.6299), np.float32(0.8473), np.float32(0.7702), np.float32(0.8811), np.float32(0.866), np.float32(0.953), np.float32(0.9582), np.float32(0.96), np.float32(0.8258), np.float32(0.7843), np.float32(0.8371), np.float32(0.95), np.float32(0.4279), np.float32(0.4251)] +2025-10-31 06:06:39.776976: Epoch time: 529.86 s +2025-10-31 06:06:41.909909: +2025-10-31 06:06:41.911463: Epoch 333 +2025-10-31 06:06:41.912871: Current learning rate: 0.00695 +2025-10-31 06:15:43.037385: train_loss -0.3964 +2025-10-31 06:15:43.074662: val_loss -0.4393 +2025-10-31 06:15:43.076000: Pseudo dice [np.float32(0.9327), np.float32(0.6356), np.float32(0.7049), np.float32(0.6013), np.float32(0.8608), np.float32(0.7656), np.float32(0.7598), np.float32(0.8765), np.float32(0.931), np.float32(0.9417), np.float32(0.9647), np.float32(0.8336), np.float32(0.785), np.float32(0.8521), np.float32(0.9525), np.float32(0.3753), np.float32(0.3101)] +2025-10-31 06:15:43.077292: Epoch time: 541.14 s +2025-10-31 06:15:45.210704: +2025-10-31 06:15:45.213409: Epoch 334 +2025-10-31 06:15:45.217916: Current learning rate: 0.00694 +2025-10-31 06:24:51.405787: train_loss -0.4099 +2025-10-31 06:24:51.439722: val_loss -0.4221 +2025-10-31 06:24:51.443414: Pseudo dice [np.float32(0.9376), np.float32(0.7428), np.float32(0.6882), np.float32(0.6129), np.float32(0.8379), np.float32(0.785), np.float32(0.7788), np.float32(0.8818), np.float32(0.9645), np.float32(0.969), np.float32(0.9485), np.float32(0.8518), np.float32(0.7604), np.float32(0.8298), np.float32(0.9494), np.float32(0.3115), np.float32(0.4338)] +2025-10-31 06:24:51.446634: Epoch time: 546.2 s +2025-10-31 06:24:53.567219: +2025-10-31 06:24:53.568909: Epoch 335 +2025-10-31 06:24:53.571533: Current learning rate: 0.00693 +2025-10-31 06:33:46.293982: train_loss -0.4044 +2025-10-31 06:33:46.307000: val_loss -0.4135 +2025-10-31 06:33:46.308584: Pseudo dice [np.float32(0.9262), np.float32(0.7284), np.float32(0.7114), np.float32(0.6257), np.float32(0.8384), np.float32(0.7858), np.float32(0.8627), np.float32(0.8843), np.float32(0.9438), np.float32(0.9535), np.float32(0.9638), np.float32(0.8168), np.float32(0.7853), np.float32(0.8475), np.float32(0.9545), np.float32(0.4168), np.float32(0.3186)] +2025-10-31 06:33:46.309848: Epoch time: 532.73 s +2025-10-31 06:33:48.524653: +2025-10-31 06:33:48.528478: Epoch 336 +2025-10-31 06:33:48.529753: Current learning rate: 0.00692 +2025-10-31 06:42:52.219526: train_loss -0.4244 +2025-10-31 06:42:52.313972: val_loss -0.4449 +2025-10-31 06:42:52.315865: Pseudo dice [np.float32(0.94), np.float32(0.7272), np.float32(0.7052), np.float32(0.603), np.float32(0.8088), np.float32(0.7604), np.float32(0.8348), np.float32(0.8789), np.float32(0.9748), np.float32(0.9702), np.float32(0.9649), np.float32(0.8362), np.float32(0.7708), np.float32(0.8436), np.float32(0.9618), np.float32(0.2674), np.float32(0.3566)] +2025-10-31 06:42:52.317800: Epoch time: 543.7 s +2025-10-31 06:42:54.413361: +2025-10-31 06:42:54.414723: Epoch 337 +2025-10-31 06:42:54.416353: Current learning rate: 0.00691 +2025-10-31 06:51:53.648958: train_loss -0.409 +2025-10-31 06:51:53.730666: val_loss -0.4253 +2025-10-31 06:51:53.736049: Pseudo dice [np.float32(0.928), np.float32(0.7414), np.float32(0.6926), np.float32(0.6822), np.float32(0.8681), np.float32(0.7659), np.float32(0.8163), np.float32(0.8725), np.float32(0.9774), np.float32(0.9801), np.float32(0.9594), np.float32(0.8192), np.float32(0.7656), np.float32(0.8767), np.float32(0.9532), np.float32(0.2583), np.float32(0.2226)] +2025-10-31 06:51:53.737365: Epoch time: 539.24 s +2025-10-31 06:51:55.873441: +2025-10-31 06:51:55.877251: Epoch 338 +2025-10-31 06:51:55.880397: Current learning rate: 0.0069 +2025-10-31 07:01:55.874913: train_loss -0.416 +2025-10-31 07:01:55.885610: val_loss -0.425 +2025-10-31 07:01:55.890932: Pseudo dice [np.float32(0.9334), np.float32(0.7639), np.float32(0.7401), np.float32(0.5927), np.float32(0.8638), np.float32(0.7712), np.float32(0.8494), np.float32(0.8459), np.float32(0.957), np.float32(0.9544), np.float32(0.9617), np.float32(0.8426), np.float32(0.7747), np.float32(0.8457), np.float32(0.933), np.float32(0.2958), np.float32(0.2659)] +2025-10-31 07:01:55.892867: Epoch time: 600.01 s +2025-10-31 07:01:57.974872: +2025-10-31 07:01:57.977362: Epoch 339 +2025-10-31 07:01:57.978536: Current learning rate: 0.00689 +2025-10-31 07:11:05.277425: train_loss -0.4286 +2025-10-31 07:11:05.291348: val_loss -0.4404 +2025-10-31 07:11:05.292964: Pseudo dice [np.float32(0.937), np.float32(0.793), np.float32(0.7216), np.float32(0.6253), np.float32(0.8372), np.float32(0.7887), np.float32(0.8245), np.float32(0.8918), np.float32(0.8979), np.float32(0.9398), np.float32(0.9674), np.float32(0.8024), np.float32(0.7501), np.float32(0.8419), np.float32(0.9589), np.float32(0.3744), np.float32(0.3222)] +2025-10-31 07:11:05.294161: Epoch time: 547.31 s +2025-10-31 07:11:07.339748: +2025-10-31 07:11:07.341232: Epoch 340 +2025-10-31 07:11:07.342761: Current learning rate: 0.00688 +2025-10-31 07:19:58.997245: train_loss -0.396 +2025-10-31 07:19:59.002196: val_loss -0.3345 +2025-10-31 07:19:59.003405: Pseudo dice [np.float32(0.9026), np.float32(0.7565), np.float32(0.6416), np.float32(0.5407), np.float32(0.8083), np.float32(0.7752), np.float32(0.8852), np.float32(0.8313), np.float32(0.8974), np.float32(0.8465), np.float32(0.9443), np.float32(0.8034), np.float32(0.7626), np.float32(0.8369), np.float32(0.9046), np.float32(0.3836), np.float32(0.2643)] +2025-10-31 07:19:59.004616: Epoch time: 531.66 s +2025-10-31 07:20:01.136380: +2025-10-31 07:20:01.140188: Epoch 341 +2025-10-31 07:20:01.141400: Current learning rate: 0.00687 +2025-10-31 07:28:56.869010: train_loss -0.3724 +2025-10-31 07:28:56.890029: val_loss -0.3839 +2025-10-31 07:28:56.891474: Pseudo dice [np.float32(0.9023), np.float32(0.7508), np.float32(0.6524), np.float32(0.6191), np.float32(0.85), np.float32(0.7512), np.float32(0.8477), np.float32(0.8473), np.float32(0.9575), np.float32(0.9555), np.float32(0.9599), np.float32(0.8138), np.float32(0.7549), np.float32(0.847), np.float32(0.9592), np.float32(0.3651), np.float32(0.4004)] +2025-10-31 07:28:56.892534: Epoch time: 535.74 s +2025-10-31 07:28:58.933622: +2025-10-31 07:28:58.935127: Epoch 342 +2025-10-31 07:28:58.937484: Current learning rate: 0.00686 +2025-10-31 07:38:00.446623: train_loss -0.4031 +2025-10-31 07:38:00.463006: val_loss -0.4252 +2025-10-31 07:38:00.464320: Pseudo dice [np.float32(0.9047), np.float32(0.7632), np.float32(0.7012), np.float32(0.6394), np.float32(0.8443), np.float32(0.734), np.float32(0.8915), np.float32(0.8609), np.float32(0.9661), np.float32(0.9681), np.float32(0.9628), np.float32(0.794), np.float32(0.7597), np.float32(0.87), np.float32(0.9524), np.float32(0.3325), np.float32(0.3051)] +2025-10-31 07:38:00.466529: Epoch time: 541.52 s +2025-10-31 07:38:02.529744: +2025-10-31 07:38:02.531341: Epoch 343 +2025-10-31 07:38:02.533019: Current learning rate: 0.00685 +2025-10-31 07:47:00.521498: train_loss -0.405 +2025-10-31 07:47:00.560751: val_loss -0.4087 +2025-10-31 07:47:00.568650: Pseudo dice [np.float32(0.9325), np.float32(0.7392), np.float32(0.7035), np.float32(0.6625), np.float32(0.8611), np.float32(0.7867), np.float32(0.8701), np.float32(0.8718), np.float32(0.9673), np.float32(0.9687), np.float32(0.9524), np.float32(0.8198), np.float32(0.7877), np.float32(0.827), np.float32(0.8941), np.float32(0.3055), np.float32(0.2716)] +2025-10-31 07:47:00.581011: Epoch time: 538.0 s +2025-10-31 07:47:02.624586: +2025-10-31 07:47:02.626958: Epoch 344 +2025-10-31 07:47:02.629435: Current learning rate: 0.00684 +2025-10-31 07:56:09.576730: train_loss -0.4101 +2025-10-31 07:56:09.601907: val_loss -0.4506 +2025-10-31 07:56:09.616089: Pseudo dice [np.float32(0.8888), np.float32(0.765), np.float32(0.6194), np.float32(0.6215), np.float32(0.8632), np.float32(0.7764), np.float32(0.8339), np.float32(0.8519), np.float32(0.9521), np.float32(0.9615), np.float32(0.9669), np.float32(0.838), np.float32(0.7859), np.float32(0.8631), np.float32(0.9339), np.float32(0.3385), np.float32(0.3992)] +2025-10-31 07:56:09.618991: Epoch time: 546.96 s +2025-10-31 07:56:11.809597: +2025-10-31 07:56:11.811690: Epoch 345 +2025-10-31 07:56:11.813595: Current learning rate: 0.00683 +2025-10-31 08:05:02.315523: train_loss -0.4152 +2025-10-31 08:05:02.336255: val_loss -0.4248 +2025-10-31 08:05:02.340074: Pseudo dice [np.float32(0.9031), np.float32(0.7479), np.float32(0.6864), np.float32(0.6225), np.float32(0.852), np.float32(0.7689), np.float32(0.8568), np.float32(0.8676), np.float32(0.9653), np.float32(0.9585), np.float32(0.9637), np.float32(0.8541), np.float32(0.7741), np.float32(0.8553), np.float32(0.9586), np.float32(0.3505), np.float32(0.2659)] +2025-10-31 08:05:02.343150: Epoch time: 530.51 s +2025-10-31 08:05:04.617533: +2025-10-31 08:05:04.620199: Epoch 346 +2025-10-31 08:05:04.623423: Current learning rate: 0.00682 +2025-10-31 08:14:02.879316: train_loss -0.4412 +2025-10-31 08:14:02.916577: val_loss -0.4194 +2025-10-31 08:14:02.921722: Pseudo dice [np.float32(0.9232), np.float32(0.7314), np.float32(0.7312), np.float32(0.6497), np.float32(0.8339), np.float32(0.7694), np.float32(0.8491), np.float32(0.8788), np.float32(0.9565), np.float32(0.9312), np.float32(0.9581), np.float32(0.8227), np.float32(0.7738), np.float32(0.809), np.float32(0.9624), np.float32(0.3004), np.float32(0.2449)] +2025-10-31 08:14:02.933663: Epoch time: 538.27 s +2025-10-31 08:14:05.043997: +2025-10-31 08:14:05.045921: Epoch 347 +2025-10-31 08:14:05.048926: Current learning rate: 0.00681 +2025-10-31 08:23:34.023745: train_loss -0.4422 +2025-10-31 08:23:34.051782: val_loss -0.4365 +2025-10-31 08:23:34.055566: Pseudo dice [np.float32(0.9346), np.float32(0.8003), np.float32(0.7197), np.float32(0.6461), np.float32(0.8548), np.float32(0.8133), np.float32(0.8747), np.float32(0.8791), np.float32(0.9817), np.float32(0.979), np.float32(0.9589), np.float32(0.8353), np.float32(0.7826), np.float32(0.8556), np.float32(0.9512), np.float32(0.3509), np.float32(0.2613)] +2025-10-31 08:23:34.071734: Epoch time: 568.98 s +2025-10-31 08:23:36.090257: +2025-10-31 08:23:36.096797: Epoch 348 +2025-10-31 08:23:36.107240: Current learning rate: 0.0068 +2025-10-31 08:32:39.676036: train_loss -0.403 +2025-10-31 08:32:39.704071: val_loss -0.4427 +2025-10-31 08:32:39.708878: Pseudo dice [np.float32(0.9257), np.float32(0.7302), np.float32(0.7066), np.float32(0.5674), np.float32(0.8531), np.float32(0.7845), np.float32(0.8693), np.float32(0.8858), np.float32(0.9591), np.float32(0.9537), np.float32(0.9653), np.float32(0.823), np.float32(0.7664), np.float32(0.8674), np.float32(0.9444), np.float32(0.4609), np.float32(0.4533)] +2025-10-31 08:32:39.711162: Epoch time: 543.59 s +2025-10-31 08:32:39.725938: Yayy! New best EMA pseudo Dice: 0.7789999842643738 +2025-10-31 08:32:55.862558: +2025-10-31 08:32:55.864416: Epoch 349 +2025-10-31 08:32:55.865693: Current learning rate: 0.0068 +2025-10-31 08:41:48.982865: train_loss -0.4338 +2025-10-31 08:41:48.993488: val_loss -0.4334 +2025-10-31 08:41:48.995826: Pseudo dice [np.float32(0.9427), np.float32(0.7699), np.float32(0.7021), np.float32(0.6556), np.float32(0.8754), np.float32(0.7827), np.float32(0.8865), np.float32(0.859), np.float32(0.9257), np.float32(0.9244), np.float32(0.9554), np.float32(0.8232), np.float32(0.8044), np.float32(0.8611), np.float32(0.9644), np.float32(0.3664), np.float32(0.271)] +2025-10-31 08:41:48.999395: Epoch time: 533.12 s +2025-10-31 08:41:51.403407: Yayy! New best EMA pseudo Dice: 0.779699981212616 +2025-10-31 08:41:56.871743: +2025-10-31 08:41:56.879617: Epoch 350 +2025-10-31 08:41:56.888952: Current learning rate: 0.00679 +2025-10-31 08:51:00.963740: train_loss -0.3967 +2025-10-31 08:51:00.976016: val_loss -0.4045 +2025-10-31 08:51:00.978747: Pseudo dice [np.float32(0.9101), np.float32(0.7632), np.float32(0.6653), np.float32(0.6114), np.float32(0.8603), np.float32(0.7661), np.float32(0.8403), np.float32(0.8541), np.float32(0.9402), np.float32(0.9435), np.float32(0.9589), np.float32(0.8359), np.float32(0.7351), np.float32(0.8591), np.float32(0.8906), np.float32(0.4672), np.float32(0.2677)] +2025-10-31 08:51:00.980569: Epoch time: 544.1 s +2025-10-31 08:51:03.091705: +2025-10-31 08:51:03.106389: Epoch 351 +2025-10-31 08:51:03.109771: Current learning rate: 0.00678 +2025-10-31 08:59:55.652549: train_loss -0.4135 +2025-10-31 08:59:55.684554: val_loss -0.4059 +2025-10-31 08:59:55.687347: Pseudo dice [np.float32(0.9121), np.float32(0.7499), np.float32(0.6661), np.float32(0.5908), np.float32(0.871), np.float32(0.7663), np.float32(0.786), np.float32(0.8741), np.float32(0.9687), np.float32(0.9691), np.float32(0.9616), np.float32(0.8156), np.float32(0.7448), np.float32(0.871), np.float32(0.944), np.float32(0.3894), np.float32(0.2114)] +2025-10-31 08:59:55.699699: Epoch time: 532.57 s +2025-10-31 08:59:57.782133: +2025-10-31 08:59:57.785681: Epoch 352 +2025-10-31 08:59:57.787109: Current learning rate: 0.00677 +2025-10-31 09:08:55.315846: train_loss -0.3644 +2025-10-31 09:08:55.323950: val_loss -0.3952 +2025-10-31 09:08:55.325104: Pseudo dice [np.float32(0.8989), np.float32(0.749), np.float32(0.6684), np.float32(0.5703), np.float32(0.8247), np.float32(0.795), np.float32(0.8318), np.float32(0.8818), np.float32(0.9748), np.float32(0.9757), np.float32(0.957), np.float32(0.8016), np.float32(0.7443), np.float32(0.8454), np.float32(0.9498), np.float32(0.3481), np.float32(0.3699)] +2025-10-31 09:08:55.326317: Epoch time: 537.54 s +2025-10-31 09:08:57.460345: +2025-10-31 09:08:57.470612: Epoch 353 +2025-10-31 09:08:57.473463: Current learning rate: 0.00676 +2025-10-31 09:17:52.902676: train_loss -0.4107 +2025-10-31 09:17:52.925164: val_loss -0.4375 +2025-10-31 09:17:52.927104: Pseudo dice [np.float32(0.9339), np.float32(0.732), np.float32(0.6887), np.float32(0.6318), np.float32(0.8569), np.float32(0.7452), np.float32(0.8263), np.float32(0.8827), np.float32(0.9792), np.float32(0.9712), np.float32(0.9646), np.float32(0.8425), np.float32(0.7627), np.float32(0.8521), np.float32(0.9595), np.float32(0.2276), np.float32(0.1814)] +2025-10-31 09:17:52.928529: Epoch time: 535.45 s +2025-10-31 09:17:55.142918: +2025-10-31 09:17:55.151750: Epoch 354 +2025-10-31 09:17:55.153190: Current learning rate: 0.00675 +2025-10-31 09:27:17.749743: train_loss -0.4262 +2025-10-31 09:27:17.777334: val_loss -0.4242 +2025-10-31 09:27:17.781105: Pseudo dice [np.float32(0.9288), np.float32(0.7455), np.float32(0.697), np.float32(0.6482), np.float32(0.8742), np.float32(0.7752), np.float32(0.8678), np.float32(0.8818), np.float32(0.9802), np.float32(0.9725), np.float32(0.958), np.float32(0.8134), np.float32(0.7744), np.float32(0.8681), np.float32(0.9298), np.float32(0.4124), np.float32(0.3871)] +2025-10-31 09:27:17.786997: Epoch time: 562.62 s +2025-10-31 09:27:19.875561: +2025-10-31 09:27:19.887070: Epoch 355 +2025-10-31 09:27:19.896432: Current learning rate: 0.00674 +2025-10-31 09:42:56.059837: train_loss -0.4275 +2025-10-31 09:42:56.100640: val_loss -0.4038 +2025-10-31 09:42:56.104865: Pseudo dice [np.float32(0.9177), np.float32(0.7733), np.float32(0.7134), np.float32(0.67), np.float32(0.815), np.float32(0.7834), np.float32(0.8659), np.float32(0.8711), np.float32(0.9601), np.float32(0.96), np.float32(0.9629), np.float32(0.8431), np.float32(0.7897), np.float32(0.7835), np.float32(0.9536), np.float32(0.3036), np.float32(0.2412)] +2025-10-31 09:42:56.108170: Epoch time: 936.19 s +2025-10-31 09:42:58.700698: +2025-10-31 09:42:58.713871: Epoch 356 +2025-10-31 09:42:58.716022: Current learning rate: 0.00673 +2025-10-31 09:52:32.333314: train_loss -0.4389 +2025-10-31 09:52:32.346717: val_loss -0.4237 +2025-10-31 09:52:32.349536: Pseudo dice [np.float32(0.9327), np.float32(0.7703), np.float32(0.7538), np.float32(0.6395), np.float32(0.8367), np.float32(0.7705), np.float32(0.8813), np.float32(0.8861), np.float32(0.9298), np.float32(0.9231), np.float32(0.9639), np.float32(0.8361), np.float32(0.8008), np.float32(0.8674), np.float32(0.955), np.float32(0.3176), np.float32(0.21)] +2025-10-31 09:52:32.351942: Epoch time: 573.64 s +2025-10-31 09:52:34.594209: +2025-10-31 09:52:34.601228: Epoch 357 +2025-10-31 09:52:34.603464: Current learning rate: 0.00672 +2025-10-31 10:01:55.317481: train_loss -0.4223 +2025-10-31 10:01:55.352644: val_loss -0.4316 +2025-10-31 10:01:55.374471: Pseudo dice [np.float32(0.9355), np.float32(0.7372), np.float32(0.7029), np.float32(0.5836), np.float32(0.8797), np.float32(0.7925), np.float32(0.8765), np.float32(0.8719), np.float32(0.9632), np.float32(0.9447), np.float32(0.9604), np.float32(0.8323), np.float32(0.7865), np.float32(0.878), np.float32(0.9142), np.float32(0.4256), np.float32(0.434)] +2025-10-31 10:01:55.380663: Epoch time: 560.73 s +2025-10-31 10:01:55.383752: Yayy! New best EMA pseudo Dice: 0.7803999781608582 +2025-10-31 10:02:00.121689: +2025-10-31 10:02:00.126049: Epoch 358 +2025-10-31 10:02:00.135513: Current learning rate: 0.00671 +2025-10-31 10:11:16.263942: train_loss -0.4089 +2025-10-31 10:11:16.303020: val_loss -0.4374 +2025-10-31 10:11:16.313553: Pseudo dice [np.float32(0.921), np.float32(0.6782), np.float32(0.6695), np.float32(0.664), np.float32(0.8666), np.float32(0.7861), np.float32(0.8386), np.float32(0.8773), np.float32(0.9704), np.float32(0.9542), np.float32(0.9585), np.float32(0.8296), np.float32(0.7564), np.float32(0.8588), np.float32(0.9589), np.float32(0.1531), np.float32(0.2695)] +2025-10-31 10:11:16.323226: Epoch time: 556.15 s +2025-10-31 10:11:18.605883: +2025-10-31 10:11:18.611693: Epoch 359 +2025-10-31 10:11:18.616736: Current learning rate: 0.0067 +2025-10-31 10:20:33.189996: train_loss -0.4237 +2025-10-31 10:20:33.243241: val_loss -0.4315 +2025-10-31 10:20:33.246836: Pseudo dice [np.float32(0.9151), np.float32(0.7569), np.float32(0.7379), np.float32(0.6444), np.float32(0.8738), np.float32(0.8032), np.float32(0.8802), np.float32(0.8819), np.float32(0.9486), np.float32(0.9106), np.float32(0.9574), np.float32(0.8432), np.float32(0.7634), np.float32(0.8742), np.float32(0.9552), np.float32(0.4007), np.float32(0.3902)] +2025-10-31 10:20:33.314656: Epoch time: 554.59 s +2025-10-31 10:20:33.318115: Yayy! New best EMA pseudo Dice: 0.7807000279426575 +2025-10-31 10:20:38.808014: +2025-10-31 10:20:38.813645: Epoch 360 +2025-10-31 10:20:38.821026: Current learning rate: 0.00669 +2025-10-31 10:29:38.514496: train_loss -0.4265 +2025-10-31 10:29:38.574619: val_loss -0.4202 +2025-10-31 10:29:38.578137: Pseudo dice [np.float32(0.9233), np.float32(0.7489), np.float32(0.7059), np.float32(0.6352), np.float32(0.8623), np.float32(0.7456), np.float32(0.8582), np.float32(0.8728), np.float32(0.9686), np.float32(0.9709), np.float32(0.9631), np.float32(0.8353), np.float32(0.7399), np.float32(0.863), np.float32(0.9462), np.float32(0.296), np.float32(0.2523)] +2025-10-31 10:29:38.587450: Epoch time: 539.71 s +2025-10-31 10:29:40.800708: +2025-10-31 10:29:40.806554: Epoch 361 +2025-10-31 10:29:40.813697: Current learning rate: 0.00668 +2025-10-31 10:38:51.924138: train_loss -0.4135 +2025-10-31 10:38:51.967415: val_loss -0.4638 +2025-10-31 10:38:51.969790: Pseudo dice [np.float32(0.9437), np.float32(0.7648), np.float32(0.7112), np.float32(0.6528), np.float32(0.8689), np.float32(0.7782), np.float32(0.8701), np.float32(0.8691), np.float32(0.9521), np.float32(0.9478), np.float32(0.9579), np.float32(0.8433), np.float32(0.7592), np.float32(0.8585), np.float32(0.9202), np.float32(0.3421), np.float32(0.1741)] +2025-10-31 10:38:51.971581: Epoch time: 551.13 s +2025-10-31 10:38:54.220479: +2025-10-31 10:38:54.223801: Epoch 362 +2025-10-31 10:38:54.226328: Current learning rate: 0.00667 +2025-10-31 10:47:57.773932: train_loss -0.4114 +2025-10-31 10:47:57.794148: val_loss -0.3942 +2025-10-31 10:47:57.796000: Pseudo dice [np.float32(0.942), np.float32(0.7457), np.float32(0.7202), np.float32(0.6233), np.float32(0.8809), np.float32(0.7661), np.float32(0.8909), np.float32(0.8836), np.float32(0.9407), np.float32(0.936), np.float32(0.9538), np.float32(0.8318), np.float32(0.7614), np.float32(0.8574), np.float32(0.9555), np.float32(0.3086), np.float32(0.3419)] +2025-10-31 10:47:57.797933: Epoch time: 543.57 s +2025-10-31 10:48:00.014732: +2025-10-31 10:48:00.016467: Epoch 363 +2025-10-31 10:48:00.018140: Current learning rate: 0.00666 +2025-10-31 10:57:11.549296: train_loss -0.3998 +2025-10-31 10:57:11.611172: val_loss -0.374 +2025-10-31 10:57:11.612669: Pseudo dice [np.float32(0.9037), np.float32(0.7914), np.float32(0.6648), np.float32(0.6537), np.float32(0.8482), np.float32(0.7662), np.float32(0.8792), np.float32(0.8704), np.float32(0.955), np.float32(0.9704), np.float32(0.9641), np.float32(0.8289), np.float32(0.73), np.float32(0.8468), np.float32(0.9337), np.float32(0.3596), np.float32(0.3063)] +2025-10-31 10:57:11.614200: Epoch time: 551.54 s +2025-10-31 10:57:13.731017: +2025-10-31 10:57:13.737267: Epoch 364 +2025-10-31 10:57:13.739681: Current learning rate: 0.00665 +2025-10-31 11:06:07.074123: train_loss -0.4168 +2025-10-31 11:06:07.097145: val_loss -0.4555 +2025-10-31 11:06:07.099522: Pseudo dice [np.float32(0.9517), np.float32(0.7737), np.float32(0.7368), np.float32(0.6259), np.float32(0.8709), np.float32(0.7879), np.float32(0.812), np.float32(0.8787), np.float32(0.9696), np.float32(0.9722), np.float32(0.9634), np.float32(0.8399), np.float32(0.8049), np.float32(0.8331), np.float32(0.9538), np.float32(0.4678), np.float32(0.4169)] +2025-10-31 11:06:07.101795: Epoch time: 533.35 s +2025-10-31 11:06:07.103359: Yayy! New best EMA pseudo Dice: 0.7827000021934509 +2025-10-31 11:06:13.273236: +2025-10-31 11:06:13.290563: Epoch 365 +2025-10-31 11:06:13.292536: Current learning rate: 0.00665 +2025-10-31 11:15:09.400213: train_loss -0.4135 +2025-10-31 11:15:09.452310: val_loss -0.4452 +2025-10-31 11:15:09.454021: Pseudo dice [np.float32(0.9196), np.float32(0.757), np.float32(0.7196), np.float32(0.6302), np.float32(0.8655), np.float32(0.7949), np.float32(0.8831), np.float32(0.8714), np.float32(0.9778), np.float32(0.9674), np.float32(0.9602), np.float32(0.8245), np.float32(0.7944), np.float32(0.8779), np.float32(0.9491), np.float32(0.1934), np.float32(0.2348)] +2025-10-31 11:15:09.456361: Epoch time: 536.13 s +2025-10-31 11:15:11.453078: +2025-10-31 11:15:11.455906: Epoch 366 +2025-10-31 11:15:11.461759: Current learning rate: 0.00664 +2025-10-31 11:24:12.885327: train_loss -0.4444 +2025-10-31 11:24:12.897529: val_loss -0.4263 +2025-10-31 11:24:12.905255: Pseudo dice [np.float32(0.9334), np.float32(0.7421), np.float32(0.6458), np.float32(0.6789), np.float32(0.8456), np.float32(0.7798), np.float32(0.8976), np.float32(0.8792), np.float32(0.9548), np.float32(0.9602), np.float32(0.9612), np.float32(0.8373), np.float32(0.768), np.float32(0.8576), np.float32(0.9544), np.float32(0.3134), np.float32(0.221)] +2025-10-31 11:24:12.909917: Epoch time: 541.44 s +2025-10-31 11:24:15.026380: +2025-10-31 11:24:15.031797: Epoch 367 +2025-10-31 11:24:15.033276: Current learning rate: 0.00663 +2025-10-31 11:33:39.072257: train_loss -0.4265 +2025-10-31 11:33:39.090459: val_loss -0.464 +2025-10-31 11:33:39.098200: Pseudo dice [np.float32(0.9262), np.float32(0.7727), np.float32(0.7265), np.float32(0.6628), np.float32(0.8629), np.float32(0.7909), np.float32(0.8908), np.float32(0.8676), np.float32(0.9592), np.float32(0.9634), np.float32(0.9689), np.float32(0.8214), np.float32(0.7679), np.float32(0.8627), np.float32(0.9369), np.float32(0.3164), np.float32(0.2694)] +2025-10-31 11:33:39.100680: Epoch time: 564.05 s +2025-10-31 11:33:41.183427: +2025-10-31 11:33:41.188265: Epoch 368 +2025-10-31 11:33:41.193610: Current learning rate: 0.00662 +2025-10-31 11:42:40.099981: train_loss -0.4338 +2025-10-31 11:42:40.113019: val_loss -0.4578 +2025-10-31 11:42:40.114731: Pseudo dice [np.float32(0.9257), np.float32(0.7448), np.float32(0.7084), np.float32(0.6267), np.float32(0.8752), np.float32(0.7729), np.float32(0.899), np.float32(0.8858), np.float32(0.9669), np.float32(0.9663), np.float32(0.9643), np.float32(0.8386), np.float32(0.7812), np.float32(0.8708), np.float32(0.9653), np.float32(0.3565), np.float32(0.4076)] +2025-10-31 11:42:40.130791: Epoch time: 538.92 s +2025-10-31 11:42:40.133440: Yayy! New best EMA pseudo Dice: 0.7838000059127808 +2025-10-31 11:42:44.980488: +2025-10-31 11:42:44.990791: Epoch 369 +2025-10-31 11:42:44.992816: Current learning rate: 0.00661 +2025-10-31 11:51:47.709118: train_loss -0.4241 +2025-10-31 11:51:47.723153: val_loss -0.4495 +2025-10-31 11:51:47.726316: Pseudo dice [np.float32(0.9246), np.float32(0.7573), np.float32(0.7219), np.float32(0.6301), np.float32(0.8827), np.float32(0.776), np.float32(0.8406), np.float32(0.8752), np.float32(0.9536), np.float32(0.947), np.float32(0.9674), np.float32(0.8382), np.float32(0.7593), np.float32(0.8716), np.float32(0.9617), np.float32(0.2489), np.float32(0.3515)] +2025-10-31 11:51:47.728610: Epoch time: 542.73 s +2025-10-31 11:52:04.341650: +2025-10-31 11:52:04.343074: Epoch 370 +2025-10-31 11:52:04.344487: Current learning rate: 0.0066 +2025-10-31 12:00:55.812783: train_loss -0.4378 +2025-10-31 12:00:55.843019: val_loss -0.4431 +2025-10-31 12:00:55.845583: Pseudo dice [np.float32(0.9197), np.float32(0.7496), np.float32(0.6881), np.float32(0.6384), np.float32(0.8569), np.float32(0.8157), np.float32(0.8607), np.float32(0.8784), np.float32(0.9478), np.float32(0.9501), np.float32(0.9629), np.float32(0.8335), np.float32(0.7576), np.float32(0.864), np.float32(0.9574), np.float32(0.446), np.float32(0.4109)] +2025-10-31 12:00:55.847646: Epoch time: 531.48 s +2025-10-31 12:00:55.849434: Yayy! New best EMA pseudo Dice: 0.7849000096321106 +2025-10-31 12:01:00.229658: +2025-10-31 12:01:00.232212: Epoch 371 +2025-10-31 12:01:00.234755: Current learning rate: 0.00659 +2025-10-31 12:09:58.697123: train_loss -0.4351 +2025-10-31 12:09:58.729288: val_loss -0.4327 +2025-10-31 12:09:58.731587: Pseudo dice [np.float32(0.9224), np.float32(0.8045), np.float32(0.7271), np.float32(0.6244), np.float32(0.8544), np.float32(0.7418), np.float32(0.8773), np.float32(0.8797), np.float32(0.9626), np.float32(0.956), np.float32(0.9536), np.float32(0.8357), np.float32(0.7732), np.float32(0.8273), np.float32(0.9289), np.float32(0.2941), np.float32(0.1598)] +2025-10-31 12:09:58.733695: Epoch time: 538.47 s +2025-10-31 12:10:00.774906: +2025-10-31 12:10:00.777481: Epoch 372 +2025-10-31 12:10:00.779544: Current learning rate: 0.00658 +2025-10-31 12:19:07.828162: train_loss -0.4155 +2025-10-31 12:19:07.875106: val_loss -0.4292 +2025-10-31 12:19:07.877195: Pseudo dice [np.float32(0.9187), np.float32(0.7546), np.float32(0.6883), np.float32(0.6199), np.float32(0.8551), np.float32(0.7424), np.float32(0.6367), np.float32(0.8898), np.float32(0.9686), np.float32(0.9615), np.float32(0.9544), np.float32(0.7999), np.float32(0.7927), np.float32(0.8455), np.float32(0.9156), np.float32(0.3041), np.float32(0.2899)] +2025-10-31 12:19:07.879012: Epoch time: 547.06 s +2025-10-31 12:19:09.933797: +2025-10-31 12:19:09.936329: Epoch 373 +2025-10-31 12:19:09.940733: Current learning rate: 0.00657 +2025-10-31 12:27:59.291334: train_loss -0.4199 +2025-10-31 12:27:59.298142: val_loss -0.4766 +2025-10-31 12:27:59.305067: Pseudo dice [np.float32(0.9307), np.float32(0.7726), np.float32(0.7442), np.float32(0.5754), np.float32(0.8721), np.float32(0.7959), np.float32(0.8961), np.float32(0.894), np.float32(0.9614), np.float32(0.9652), np.float32(0.9635), np.float32(0.8574), np.float32(0.7891), np.float32(0.8632), np.float32(0.9538), np.float32(0.5458), np.float32(0.4552)] +2025-10-31 12:27:59.306597: Epoch time: 529.36 s +2025-10-31 12:28:01.414798: +2025-10-31 12:28:01.427020: Epoch 374 +2025-10-31 12:28:01.441493: Current learning rate: 0.00656 +2025-10-31 12:37:14.045221: train_loss -0.4302 +2025-10-31 12:37:14.072165: val_loss -0.411 +2025-10-31 12:37:14.077598: Pseudo dice [np.float32(0.9151), np.float32(0.7553), np.float32(0.7096), np.float32(0.6187), np.float32(0.8438), np.float32(0.7749), np.float32(0.9005), np.float32(0.87), np.float32(0.9164), np.float32(0.9377), np.float32(0.9637), np.float32(0.8513), np.float32(0.7687), np.float32(0.8656), np.float32(0.9333), np.float32(0.2375), np.float32(0.2014)] +2025-10-31 12:37:14.080268: Epoch time: 552.64 s +2025-10-31 12:37:16.232917: +2025-10-31 12:37:16.235757: Epoch 375 +2025-10-31 12:37:16.240792: Current learning rate: 0.00655 +2025-10-31 12:46:17.619686: train_loss -0.4208 +2025-10-31 12:46:17.652013: val_loss -0.4281 +2025-10-31 12:46:17.656078: Pseudo dice [np.float32(0.9225), np.float32(0.7606), np.float32(0.6725), np.float32(0.6337), np.float32(0.8047), np.float32(0.7732), np.float32(0.8962), np.float32(0.8623), np.float32(0.9371), np.float32(0.9451), np.float32(0.9617), np.float32(0.8255), np.float32(0.745), np.float32(0.8337), np.float32(0.9484), np.float32(0.2134), np.float32(0.2343)] +2025-10-31 12:46:17.661002: Epoch time: 541.39 s +2025-10-31 12:46:19.850612: +2025-10-31 12:46:19.854129: Epoch 376 +2025-10-31 12:46:19.856066: Current learning rate: 0.00654 +2025-10-31 12:55:05.555981: train_loss -0.4352 +2025-10-31 12:55:05.584728: val_loss -0.4415 +2025-10-31 12:55:05.586529: Pseudo dice [np.float32(0.9236), np.float32(0.7633), np.float32(0.6981), np.float32(0.6513), np.float32(0.839), np.float32(0.7909), np.float32(0.8805), np.float32(0.8889), np.float32(0.9769), np.float32(0.9751), np.float32(0.962), np.float32(0.8356), np.float32(0.7682), np.float32(0.8879), np.float32(0.9631), np.float32(0.28), np.float32(0.1863)] +2025-10-31 12:55:05.588034: Epoch time: 525.71 s +2025-10-31 12:55:07.746967: +2025-10-31 12:55:07.767061: Epoch 377 +2025-10-31 12:55:07.768646: Current learning rate: 0.00653 +2025-10-31 13:04:06.622757: train_loss -0.3772 +2025-10-31 13:04:06.666495: val_loss -0.422 +2025-10-31 13:04:06.670158: Pseudo dice [np.float32(0.9305), np.float32(0.7713), np.float32(0.7554), np.float32(0.6118), np.float32(0.8433), np.float32(0.7507), np.float32(0.8161), np.float32(0.8602), np.float32(0.959), np.float32(0.9482), np.float32(0.9532), np.float32(0.7897), np.float32(0.7697), np.float32(0.829), np.float32(0.9311), np.float32(0.315), np.float32(0.3554)] +2025-10-31 13:04:06.672450: Epoch time: 538.88 s +2025-10-31 13:04:08.893551: +2025-10-31 13:04:08.894969: Epoch 378 +2025-10-31 13:04:08.900267: Current learning rate: 0.00652 +2025-10-31 13:13:07.647267: train_loss -0.4085 +2025-10-31 13:13:07.693161: val_loss -0.3421 +2025-10-31 13:13:07.702688: Pseudo dice [np.float32(0.9138), np.float32(0.7241), np.float32(0.6864), np.float32(0.6292), np.float32(0.8466), np.float32(0.778), np.float32(0.8782), np.float32(0.8798), np.float32(0.9435), np.float32(0.9332), np.float32(0.9274), np.float32(0.8139), np.float32(0.7402), np.float32(0.8145), np.float32(0.8124), np.float32(0.1757), np.float32(0.1803)] +2025-10-31 13:13:07.706336: Epoch time: 538.76 s +2025-10-31 13:13:10.239051: +2025-10-31 13:13:10.240442: Epoch 379 +2025-10-31 13:13:10.241557: Current learning rate: 0.00651 +2025-10-31 13:22:15.902492: train_loss -0.395 +2025-10-31 13:22:15.943420: val_loss -0.4366 +2025-10-31 13:22:15.948241: Pseudo dice [np.float32(0.9095), np.float32(0.7288), np.float32(0.5675), np.float32(0.5833), np.float32(0.8625), np.float32(0.7839), np.float32(0.8215), np.float32(0.8744), np.float32(0.929), np.float32(0.9282), np.float32(0.9504), np.float32(0.8339), np.float32(0.737), np.float32(0.8671), np.float32(0.9237), np.float32(0.3555), np.float32(0.3551)] +2025-10-31 13:22:15.950439: Epoch time: 545.67 s +2025-10-31 13:22:18.145867: +2025-10-31 13:22:18.158958: Epoch 380 +2025-10-31 13:22:18.160793: Current learning rate: 0.0065 +2025-10-31 13:31:20.931628: train_loss -0.4169 +2025-10-31 13:31:20.961683: val_loss -0.4026 +2025-10-31 13:31:20.963196: Pseudo dice [np.float32(0.9261), np.float32(0.769), np.float32(0.6914), np.float32(0.6338), np.float32(0.8425), np.float32(0.7806), np.float32(0.8841), np.float32(0.8617), np.float32(0.956), np.float32(0.9689), np.float32(0.9659), np.float32(0.8487), np.float32(0.7945), np.float32(0.8405), np.float32(0.9544), np.float32(0.355), np.float32(0.3121)] +2025-10-31 13:31:20.964849: Epoch time: 542.8 s +2025-10-31 13:31:23.302561: +2025-10-31 13:31:23.314244: Epoch 381 +2025-10-31 13:31:23.318170: Current learning rate: 0.00649 +2025-10-31 13:40:04.539815: train_loss -0.3865 +2025-10-31 13:40:04.576503: val_loss -0.3448 +2025-10-31 13:40:04.578290: Pseudo dice [np.float32(0.9331), np.float32(0.7815), np.float32(0.731), np.float32(0.6078), np.float32(0.7571), np.float32(0.7365), np.float32(0.8419), np.float32(0.8401), np.float32(0.9519), np.float32(0.9472), np.float32(0.9583), np.float32(0.7992), np.float32(0.7575), np.float32(0.8297), np.float32(0.9302), np.float32(0.2634), np.float32(0.2582)] +2025-10-31 13:40:04.579776: Epoch time: 521.24 s +2025-10-31 13:40:06.756862: +2025-10-31 13:40:06.758371: Epoch 382 +2025-10-31 13:40:06.761283: Current learning rate: 0.00648 +2025-10-31 13:48:58.134465: train_loss -0.4293 +2025-10-31 13:48:58.167188: val_loss -0.4224 +2025-10-31 13:48:58.170662: Pseudo dice [np.float32(0.9132), np.float32(0.743), np.float32(0.6857), np.float32(0.6103), np.float32(0.8731), np.float32(0.7705), np.float32(0.8728), np.float32(0.8839), np.float32(0.9788), np.float32(0.978), np.float32(0.9616), np.float32(0.8149), np.float32(0.8004), np.float32(0.87), np.float32(0.9025), np.float32(0.2671), np.float32(0.2858)] +2025-10-31 13:48:58.173413: Epoch time: 531.38 s +2025-10-31 13:49:00.362532: +2025-10-31 13:49:00.364975: Epoch 383 +2025-10-31 13:49:00.366982: Current learning rate: 0.00648 +2025-10-31 13:58:00.473301: train_loss -0.4009 +2025-10-31 13:58:00.512281: val_loss -0.4159 +2025-10-31 13:58:00.513689: Pseudo dice [np.float32(0.9313), np.float32(0.7446), np.float32(0.702), np.float32(0.6823), np.float32(0.8105), np.float32(0.7871), np.float32(0.8317), np.float32(0.8772), np.float32(0.9635), np.float32(0.973), np.float32(0.9642), np.float32(0.8314), np.float32(0.7834), np.float32(0.82), np.float32(0.9424), np.float32(0.345), np.float32(0.2438)] +2025-10-31 13:58:00.516510: Epoch time: 540.12 s +2025-10-31 13:58:02.612736: +2025-10-31 13:58:02.628784: Epoch 384 +2025-10-31 13:58:02.633733: Current learning rate: 0.00647 +2025-10-31 14:06:44.429120: train_loss -0.4069 +2025-10-31 14:06:44.458361: val_loss -0.4288 +2025-10-31 14:06:44.467083: Pseudo dice [np.float32(0.9283), np.float32(0.7841), np.float32(0.6843), np.float32(0.5632), np.float32(0.8578), np.float32(0.7742), np.float32(0.8674), np.float32(0.8862), np.float32(0.9603), np.float32(0.9583), np.float32(0.958), np.float32(0.8439), np.float32(0.7819), np.float32(0.8457), np.float32(0.9127), np.float32(0.3364), np.float32(0.2816)] +2025-10-31 14:06:44.469345: Epoch time: 521.82 s +2025-10-31 14:06:46.653415: +2025-10-31 14:06:46.655109: Epoch 385 +2025-10-31 14:06:46.656567: Current learning rate: 0.00646 +2025-10-31 14:15:28.843144: train_loss -0.4115 +2025-10-31 14:15:28.858009: val_loss -0.4253 +2025-10-31 14:15:28.859900: Pseudo dice [np.float32(0.9349), np.float32(0.7714), np.float32(0.7174), np.float32(0.6015), np.float32(0.8462), np.float32(0.7813), np.float32(0.8616), np.float32(0.8916), np.float32(0.9635), np.float32(0.9434), np.float32(0.9626), np.float32(0.7994), np.float32(0.7571), np.float32(0.8556), np.float32(0.9631), np.float32(0.3978), np.float32(0.254)] +2025-10-31 14:15:28.861319: Epoch time: 522.19 s +2025-10-31 14:15:30.986631: +2025-10-31 14:15:31.004942: Epoch 386 +2025-10-31 14:15:31.011556: Current learning rate: 0.00645 +2025-10-31 14:24:44.143569: train_loss -0.4118 +2025-10-31 14:24:44.157158: val_loss -0.4055 +2025-10-31 14:24:44.158679: Pseudo dice [np.float32(0.932), np.float32(0.7321), np.float32(0.7431), np.float32(0.6056), np.float32(0.8524), np.float32(0.79), np.float32(0.8648), np.float32(0.8755), np.float32(0.9694), np.float32(0.9712), np.float32(0.9628), np.float32(0.8144), np.float32(0.7659), np.float32(0.8528), np.float32(0.9438), np.float32(0.3363), np.float32(0.2735)] +2025-10-31 14:24:44.160311: Epoch time: 553.16 s +2025-10-31 14:24:46.507015: +2025-10-31 14:24:46.508952: Epoch 387 +2025-10-31 14:24:46.510791: Current learning rate: 0.00644 +2025-10-31 14:33:40.468053: train_loss -0.4014 +2025-10-31 14:33:40.512377: val_loss -0.406 +2025-10-31 14:33:40.518266: Pseudo dice [np.float32(0.9247), np.float32(0.7563), np.float32(0.6837), np.float32(0.5917), np.float32(0.8443), np.float32(0.7565), np.float32(0.8638), np.float32(0.87), np.float32(0.9304), np.float32(0.9485), np.float32(0.9603), np.float32(0.8416), np.float32(0.7692), np.float32(0.876), np.float32(0.9363), np.float32(0.4405), np.float32(0.2658)] +2025-10-31 14:33:40.519671: Epoch time: 533.97 s +2025-10-31 14:33:42.660734: +2025-10-31 14:33:42.667347: Epoch 388 +2025-10-31 14:33:42.669264: Current learning rate: 0.00643 +2025-10-31 14:42:49.072987: train_loss -0.4176 +2025-10-31 14:42:49.087097: val_loss -0.4285 +2025-10-31 14:42:49.088660: Pseudo dice [np.float32(0.896), np.float32(0.7468), np.float32(0.6681), np.float32(0.7042), np.float32(0.8612), np.float32(0.7967), np.float32(0.8377), np.float32(0.8662), np.float32(0.9248), np.float32(0.9102), np.float32(0.953), np.float32(0.8481), np.float32(0.7937), np.float32(0.8692), np.float32(0.9516), np.float32(0.2952), np.float32(0.2325)] +2025-10-31 14:42:49.090760: Epoch time: 546.42 s +2025-10-31 14:42:51.225648: +2025-10-31 14:42:51.229352: Epoch 389 +2025-10-31 14:42:51.240010: Current learning rate: 0.00642 +2025-10-31 14:51:57.841269: train_loss -0.3892 +2025-10-31 14:51:57.855655: val_loss -0.39 +2025-10-31 14:51:57.861843: Pseudo dice [np.float32(0.9341), np.float32(0.7845), np.float32(0.7434), np.float32(0.5586), np.float32(0.861), np.float32(0.7988), np.float32(0.8127), np.float32(0.8659), np.float32(0.9725), np.float32(0.9649), np.float32(0.9559), np.float32(0.8348), np.float32(0.769), np.float32(0.8662), np.float32(0.9359), np.float32(0.2969), np.float32(0.2776)] +2025-10-31 14:51:57.863670: Epoch time: 546.62 s +2025-10-31 14:51:59.978007: +2025-10-31 14:51:59.980581: Epoch 390 +2025-10-31 14:51:59.986401: Current learning rate: 0.00641 +2025-10-31 15:00:48.031404: train_loss -0.4125 +2025-10-31 15:00:48.044313: val_loss -0.4303 +2025-10-31 15:00:48.050743: Pseudo dice [np.float32(0.9388), np.float32(0.7579), np.float32(0.7329), np.float32(0.6652), np.float32(0.862), np.float32(0.7893), np.float32(0.7296), np.float32(0.8809), np.float32(0.9504), np.float32(0.9617), np.float32(0.9633), np.float32(0.804), np.float32(0.7645), np.float32(0.7996), np.float32(0.9195), np.float32(0.1632), np.float32(0.1015)] +2025-10-31 15:00:48.053861: Epoch time: 528.06 s +2025-10-31 15:00:50.853792: +2025-10-31 15:00:50.855748: Epoch 391 +2025-10-31 15:00:50.857654: Current learning rate: 0.0064 +2025-10-31 15:09:52.497927: train_loss -0.3702 +2025-10-31 15:09:52.519013: val_loss -0.3988 +2025-10-31 15:09:52.520775: Pseudo dice [np.float32(0.9102), np.float32(0.7884), np.float32(0.751), np.float32(0.5976), np.float32(0.8725), np.float32(0.786), np.float32(0.7941), np.float32(0.8551), np.float32(0.9365), np.float32(0.9445), np.float32(0.9607), np.float32(0.7914), np.float32(0.7568), np.float32(0.8627), np.float32(0.9253), np.float32(0.4418), np.float32(0.2851)] +2025-10-31 15:09:52.522125: Epoch time: 541.65 s +2025-10-31 15:09:54.755841: +2025-10-31 15:09:54.759666: Epoch 392 +2025-10-31 15:09:54.761110: Current learning rate: 0.00639 +2025-10-31 15:18:48.438854: train_loss -0.4129 +2025-10-31 15:18:48.446786: val_loss -0.3959 +2025-10-31 15:18:48.448481: Pseudo dice [np.float32(0.9269), np.float32(0.711), np.float32(0.6629), np.float32(0.652), np.float32(0.8381), np.float32(0.7876), np.float32(0.8517), np.float32(0.8602), np.float32(0.929), np.float32(0.9505), np.float32(0.9328), np.float32(0.8341), np.float32(0.7792), np.float32(0.8469), np.float32(0.9215), np.float32(0.2329), np.float32(0.1964)] +2025-10-31 15:18:48.450648: Epoch time: 533.69 s +2025-10-31 15:19:01.765817: +2025-10-31 15:19:01.767165: Epoch 393 +2025-10-31 15:19:01.768358: Current learning rate: 0.00638 +2025-10-31 15:27:46.670370: train_loss -0.4165 +2025-10-31 15:27:46.706588: val_loss -0.416 +2025-10-31 15:27:46.710244: Pseudo dice [np.float32(0.9263), np.float32(0.7829), np.float32(0.731), np.float32(0.6397), np.float32(0.826), np.float32(0.736), np.float32(0.8127), np.float32(0.8623), np.float32(0.9441), np.float32(0.9403), np.float32(0.959), np.float32(0.8274), np.float32(0.7573), np.float32(0.8316), np.float32(0.9467), np.float32(0.3917), np.float32(0.2462)] +2025-10-31 15:27:46.711942: Epoch time: 524.91 s +2025-10-31 15:27:50.715342: +2025-10-31 15:27:50.717019: Epoch 394 +2025-10-31 15:27:50.718389: Current learning rate: 0.00637 +2025-10-31 15:36:43.640788: train_loss -0.4273 +2025-10-31 15:36:43.657704: val_loss -0.434 +2025-10-31 15:36:43.659841: Pseudo dice [np.float32(0.91), np.float32(0.6855), np.float32(0.6706), np.float32(0.6486), np.float32(0.8419), np.float32(0.7722), np.float32(0.8679), np.float32(0.8904), np.float32(0.9704), np.float32(0.973), np.float32(0.964), np.float32(0.8363), np.float32(0.7621), np.float32(0.8439), np.float32(0.9613), np.float32(0.3373), np.float32(0.4268)] +2025-10-31 15:36:43.661143: Epoch time: 532.93 s +2025-10-31 15:36:45.715657: +2025-10-31 15:36:45.716988: Epoch 395 +2025-10-31 15:36:45.718289: Current learning rate: 0.00636 +2025-10-31 15:45:57.256378: train_loss -0.339 +2025-10-31 15:45:57.298476: val_loss -0.3735 +2025-10-31 15:45:57.307651: Pseudo dice [np.float32(0.8969), np.float32(0.7398), np.float32(0.6747), np.float32(0.619), np.float32(0.8288), np.float32(0.7336), np.float32(0.7283), np.float32(0.8672), np.float32(0.9162), np.float32(0.8786), np.float32(0.9539), np.float32(0.8192), np.float32(0.782), np.float32(0.852), np.float32(0.899), np.float32(0.2729), np.float32(0.1976)] +2025-10-31 15:45:57.309672: Epoch time: 551.55 s +2025-10-31 15:45:59.328989: +2025-10-31 15:45:59.330685: Epoch 396 +2025-10-31 15:45:59.333945: Current learning rate: 0.00635 +2025-10-31 15:55:08.564792: train_loss -0.3852 +2025-10-31 15:55:08.588565: val_loss -0.4155 +2025-10-31 15:55:08.595095: Pseudo dice [np.float32(0.932), np.float32(0.4352), np.float32(0.7245), np.float32(0.6877), np.float32(0.8693), np.float32(0.7629), np.float32(0.7471), np.float32(0.8456), np.float32(0.9677), np.float32(0.9615), np.float32(0.934), np.float32(0.7823), np.float32(0.7628), np.float32(0.8683), np.float32(0.9609), np.float32(0.2524), np.float32(0.2771)] +2025-10-31 15:55:08.597683: Epoch time: 549.24 s +2025-10-31 15:55:10.713945: +2025-10-31 15:55:10.719370: Epoch 397 +2025-10-31 15:55:10.720948: Current learning rate: 0.00634 +2025-10-31 16:04:07.756603: train_loss -0.4061 +2025-10-31 16:04:07.763205: val_loss -0.4389 +2025-10-31 16:04:07.764718: Pseudo dice [np.float32(0.9296), np.float32(0.7596), np.float32(0.7127), np.float32(0.6895), np.float32(0.8512), np.float32(0.7845), np.float32(0.7592), np.float32(0.8857), np.float32(0.9703), np.float32(0.9709), np.float32(0.962), np.float32(0.831), np.float32(0.7873), np.float32(0.8258), np.float32(0.9509), np.float32(0.4462), np.float32(0.3484)] +2025-10-31 16:04:07.766753: Epoch time: 537.05 s +2025-10-31 16:04:09.959297: +2025-10-31 16:04:09.961409: Epoch 398 +2025-10-31 16:04:09.963494: Current learning rate: 0.00633 +2025-10-31 16:13:13.980300: train_loss -0.4332 +2025-10-31 16:13:13.992611: val_loss -0.4443 +2025-10-31 16:13:13.999041: Pseudo dice [np.float32(0.925), np.float32(0.7527), np.float32(0.7221), np.float32(0.6418), np.float32(0.818), np.float32(0.7826), np.float32(0.8647), np.float32(0.8931), np.float32(0.9674), np.float32(0.965), np.float32(0.9634), np.float32(0.8472), np.float32(0.771), np.float32(0.8225), np.float32(0.9606), np.float32(0.3578), np.float32(0.3776)] +2025-10-31 16:13:14.001431: Epoch time: 544.03 s +2025-10-31 16:13:16.232583: +2025-10-31 16:13:16.235204: Epoch 399 +2025-10-31 16:13:16.236678: Current learning rate: 0.00632 +2025-10-31 16:22:13.999110: train_loss -0.4215 +2025-10-31 16:22:14.021300: val_loss -0.4007 +2025-10-31 16:22:14.022704: Pseudo dice [np.float32(0.9361), np.float32(0.7679), np.float32(0.6967), np.float32(0.6163), np.float32(0.8366), np.float32(0.7711), np.float32(0.8231), np.float32(0.8626), np.float32(0.9727), np.float32(0.9712), np.float32(0.9601), np.float32(0.834), np.float32(0.7863), np.float32(0.8633), np.float32(0.9559), np.float32(0.1332), np.float32(0.101)] +2025-10-31 16:22:14.024947: Epoch time: 537.77 s +2025-10-31 16:22:19.608653: +2025-10-31 16:22:19.610405: Epoch 400 +2025-10-31 16:22:19.613062: Current learning rate: 0.00631 +2025-10-31 16:31:35.029483: train_loss -0.4207 +2025-10-31 16:31:35.036862: val_loss -0.4094 +2025-10-31 16:31:35.038474: Pseudo dice [np.float32(0.9279), np.float32(0.7821), np.float32(0.6965), np.float32(0.691), np.float32(0.8518), np.float32(0.8018), np.float32(0.8379), np.float32(0.8496), np.float32(0.9655), np.float32(0.9647), np.float32(0.959), np.float32(0.8362), np.float32(0.7455), np.float32(0.8617), np.float32(0.9285), np.float32(0.3805), np.float32(0.308)] +2025-10-31 16:31:35.039968: Epoch time: 555.42 s +2025-10-31 16:31:37.126391: +2025-10-31 16:31:37.128289: Epoch 401 +2025-10-31 16:31:37.130029: Current learning rate: 0.0063 +2025-10-31 16:40:44.105573: train_loss -0.3979 +2025-10-31 16:40:44.121724: val_loss -0.4023 +2025-10-31 16:40:44.129095: Pseudo dice [np.float32(0.9257), np.float32(0.7709), np.float32(0.6755), np.float32(0.6182), np.float32(0.8746), np.float32(0.8037), np.float32(0.8815), np.float32(0.852), np.float32(0.956), np.float32(0.952), np.float32(0.9618), np.float32(0.8429), np.float32(0.7563), np.float32(0.8646), np.float32(0.9506), np.float32(0.2584), np.float32(0.1594)] +2025-10-31 16:40:44.131126: Epoch time: 546.98 s +2025-10-31 16:40:46.289124: +2025-10-31 16:40:46.294341: Epoch 402 +2025-10-31 16:40:46.308787: Current learning rate: 0.0063 +2025-10-31 16:49:47.346000: train_loss -0.4176 +2025-10-31 16:49:47.371077: val_loss -0.4197 +2025-10-31 16:49:47.372346: Pseudo dice [np.float32(0.9086), np.float32(0.783), np.float32(0.7068), np.float32(0.6977), np.float32(0.859), np.float32(0.7744), np.float32(0.8536), np.float32(0.8823), np.float32(0.979), np.float32(0.978), np.float32(0.9597), np.float32(0.8467), np.float32(0.8179), np.float32(0.8596), np.float32(0.9602), np.float32(0.3916), np.float32(0.4552)] +2025-10-31 16:49:47.373423: Epoch time: 541.06 s +2025-10-31 16:49:49.676324: +2025-10-31 16:49:49.678141: Epoch 403 +2025-10-31 16:49:49.681293: Current learning rate: 0.00629 +2025-10-31 16:58:59.677023: train_loss -0.3855 +2025-10-31 16:58:59.685705: val_loss -0.4245 +2025-10-31 16:58:59.687879: Pseudo dice [np.float32(0.9421), np.float32(0.7439), np.float32(0.6876), np.float32(0.6735), np.float32(0.8478), np.float32(0.7386), np.float32(0.8576), np.float32(0.8765), np.float32(0.96), np.float32(0.9553), np.float32(0.9548), np.float32(0.7931), np.float32(0.7598), np.float32(0.8636), np.float32(0.9285), np.float32(0.3419), np.float32(0.4456)] +2025-10-31 16:58:59.690646: Epoch time: 550.01 s +2025-10-31 16:59:01.902991: +2025-10-31 16:59:01.905664: Epoch 404 +2025-10-31 16:59:01.907056: Current learning rate: 0.00628 +2025-10-31 17:07:56.635706: train_loss -0.4158 +2025-10-31 17:07:56.682817: val_loss -0.3732 +2025-10-31 17:07:56.697407: Pseudo dice [np.float32(0.9106), np.float32(0.7816), np.float32(0.7218), np.float32(0.6118), np.float32(0.8304), np.float32(0.7637), np.float32(0.8304), np.float32(0.8741), np.float32(0.9644), np.float32(0.9669), np.float32(0.9634), np.float32(0.8524), np.float32(0.7551), np.float32(0.8639), np.float32(0.9634), np.float32(0.4074), np.float32(0.3953)] +2025-10-31 17:07:56.721254: Epoch time: 534.74 s +2025-10-31 17:07:59.650229: +2025-10-31 17:07:59.657016: Epoch 405 +2025-10-31 17:07:59.658930: Current learning rate: 0.00627 +2025-10-31 17:16:45.832712: train_loss -0.4269 +2025-10-31 17:16:45.843383: val_loss -0.4584 +2025-10-31 17:16:45.844750: Pseudo dice [np.float32(0.9377), np.float32(0.6921), np.float32(0.6825), np.float32(0.6619), np.float32(0.8646), np.float32(0.7776), np.float32(0.8831), np.float32(0.8747), np.float32(0.9771), np.float32(0.9771), np.float32(0.962), np.float32(0.8561), np.float32(0.802), np.float32(0.8691), np.float32(0.9632), np.float32(0.2999), np.float32(0.2733)] +2025-10-31 17:16:45.850154: Epoch time: 526.2 s +2025-10-31 17:16:48.056413: +2025-10-31 17:16:48.058121: Epoch 406 +2025-10-31 17:16:48.060002: Current learning rate: 0.00626 +2025-10-31 17:25:39.498446: train_loss -0.4295 +2025-10-31 17:25:39.534711: val_loss -0.4118 +2025-10-31 17:25:39.540883: Pseudo dice [np.float32(0.9219), np.float32(0.7686), np.float32(0.6695), np.float32(0.5931), np.float32(0.8341), np.float32(0.7599), np.float32(0.8765), np.float32(0.8581), np.float32(0.9642), np.float32(0.9447), np.float32(0.9596), np.float32(0.7783), np.float32(0.7559), np.float32(0.8633), np.float32(0.9508), np.float32(0.3539), np.float32(0.3687)] +2025-10-31 17:25:39.547761: Epoch time: 531.45 s +2025-10-31 17:25:41.762317: +2025-10-31 17:25:41.764383: Epoch 407 +2025-10-31 17:25:41.766004: Current learning rate: 0.00625 +2025-10-31 17:34:24.350685: train_loss -0.4113 +2025-10-31 17:34:24.357425: val_loss -0.4282 +2025-10-31 17:34:24.358543: Pseudo dice [np.float32(0.931), np.float32(0.6999), np.float32(0.6555), np.float32(0.5817), np.float32(0.8742), np.float32(0.7809), np.float32(0.8564), np.float32(0.8745), np.float32(0.9758), np.float32(0.9761), np.float32(0.9597), np.float32(0.8572), np.float32(0.7795), np.float32(0.8656), np.float32(0.9448), np.float32(0.3103), np.float32(0.3064)] +2025-10-31 17:34:24.359880: Epoch time: 522.59 s +2025-10-31 17:34:26.491806: +2025-10-31 17:34:26.493845: Epoch 408 +2025-10-31 17:34:26.499048: Current learning rate: 0.00624 +2025-10-31 17:43:25.792806: train_loss -0.4171 +2025-10-31 17:43:25.806247: val_loss -0.4591 +2025-10-31 17:43:25.810234: Pseudo dice [np.float32(0.9302), np.float32(0.763), np.float32(0.7062), np.float32(0.6737), np.float32(0.8449), np.float32(0.7995), np.float32(0.9052), np.float32(0.8905), np.float32(0.9648), np.float32(0.9647), np.float32(0.957), np.float32(0.8592), np.float32(0.7856), np.float32(0.8601), np.float32(0.9372), np.float32(0.2606), np.float32(0.3592)] +2025-10-31 17:43:25.822522: Epoch time: 539.31 s +2025-10-31 17:43:27.993863: +2025-10-31 17:43:27.999430: Epoch 409 +2025-10-31 17:43:28.006751: Current learning rate: 0.00623 +2025-10-31 17:52:36.496477: train_loss -0.4327 +2025-10-31 17:52:36.544647: val_loss -0.4374 +2025-10-31 17:52:36.546858: Pseudo dice [np.float32(0.9362), np.float32(0.7655), np.float32(0.7001), np.float32(0.6449), np.float32(0.8552), np.float32(0.8013), np.float32(0.8237), np.float32(0.8773), np.float32(0.9518), np.float32(0.9317), np.float32(0.9587), np.float32(0.8434), np.float32(0.7472), np.float32(0.8653), np.float32(0.9612), np.float32(0.2801), np.float32(0.1756)] +2025-10-31 17:52:36.548834: Epoch time: 548.51 s +2025-10-31 17:52:38.775688: +2025-10-31 17:52:38.778063: Epoch 410 +2025-10-31 17:52:38.779482: Current learning rate: 0.00622 +2025-10-31 18:01:42.283648: train_loss -0.443 +2025-10-31 18:01:42.298476: val_loss -0.4303 +2025-10-31 18:01:42.300283: Pseudo dice [np.float32(0.9161), np.float32(0.754), np.float32(0.6557), np.float32(0.6898), np.float32(0.8665), np.float32(0.7977), np.float32(0.8066), np.float32(0.8795), np.float32(0.9658), np.float32(0.9568), np.float32(0.9656), np.float32(0.8484), np.float32(0.7629), np.float32(0.8845), np.float32(0.9659), np.float32(0.304), np.float32(0.2727)] +2025-10-31 18:01:42.301811: Epoch time: 543.52 s +2025-10-31 18:01:44.426046: +2025-10-31 18:01:44.432298: Epoch 411 +2025-10-31 18:01:44.434645: Current learning rate: 0.00621 +2025-10-31 18:10:32.434831: train_loss -0.424 +2025-10-31 18:10:32.460453: val_loss -0.4678 +2025-10-31 18:10:32.462653: Pseudo dice [np.float32(0.9367), np.float32(0.7503), np.float32(0.7348), np.float32(0.654), np.float32(0.8555), np.float32(0.7425), np.float32(0.9072), np.float32(0.8689), np.float32(0.9544), np.float32(0.9611), np.float32(0.9667), np.float32(0.8478), np.float32(0.7627), np.float32(0.8592), np.float32(0.9563), np.float32(0.3471), np.float32(0.3562)] +2025-10-31 18:10:32.463987: Epoch time: 528.02 s +2025-10-31 18:10:34.536989: +2025-10-31 18:10:34.538960: Epoch 412 +2025-10-31 18:10:34.540429: Current learning rate: 0.0062 +2025-10-31 18:19:34.066848: train_loss -0.4005 +2025-10-31 18:19:34.098188: val_loss -0.4036 +2025-10-31 18:19:34.099751: Pseudo dice [np.float32(0.9051), np.float32(0.7397), np.float32(0.7185), np.float32(0.6504), np.float32(0.8176), np.float32(0.7331), np.float32(0.8962), np.float32(0.8627), np.float32(0.9623), np.float32(0.97), np.float32(0.9607), np.float32(0.7901), np.float32(0.7375), np.float32(0.8352), np.float32(0.9467), np.float32(0.1915), np.float32(0.1644)] +2025-10-31 18:19:34.101715: Epoch time: 539.53 s +2025-10-31 18:19:36.161577: +2025-10-31 18:19:36.168695: Epoch 413 +2025-10-31 18:19:36.170118: Current learning rate: 0.00619 +2025-10-31 18:28:30.072206: train_loss -0.4077 +2025-10-31 18:28:30.078568: val_loss -0.4133 +2025-10-31 18:28:30.083271: Pseudo dice [np.float32(0.9338), np.float32(0.7586), np.float32(0.7072), np.float32(0.5923), np.float32(0.86), np.float32(0.7498), np.float32(0.8677), np.float32(0.8551), np.float32(0.9468), np.float32(0.9567), np.float32(0.9586), np.float32(0.7985), np.float32(0.7362), np.float32(0.8425), np.float32(0.9191), np.float32(0.2567), np.float32(0.1745)] +2025-10-31 18:28:30.088420: Epoch time: 533.92 s +2025-10-31 18:28:32.101141: +2025-10-31 18:28:32.102850: Epoch 414 +2025-10-31 18:28:32.104245: Current learning rate: 0.00618 +2025-10-31 18:37:07.543224: train_loss -0.4285 +2025-10-31 18:37:07.554568: val_loss -0.3926 +2025-10-31 18:37:07.556375: Pseudo dice [np.float32(0.9133), np.float32(0.7631), np.float32(0.7104), np.float32(0.6635), np.float32(0.8454), np.float32(0.7479), np.float32(0.8924), np.float32(0.8661), np.float32(0.9591), np.float32(0.9573), np.float32(0.9639), np.float32(0.7904), np.float32(0.7342), np.float32(0.8579), np.float32(0.9467), np.float32(0.1492), np.float32(0.0247)] +2025-10-31 18:37:07.558225: Epoch time: 515.45 s +2025-10-31 18:37:09.572059: +2025-10-31 18:37:09.573898: Epoch 415 +2025-10-31 18:37:09.574986: Current learning rate: 0.00617 +2025-10-31 18:45:47.871749: train_loss -0.4123 +2025-10-31 18:45:47.908978: val_loss -0.431 +2025-10-31 18:45:47.911884: Pseudo dice [np.float32(0.9284), np.float32(0.7946), np.float32(0.7118), np.float32(0.628), np.float32(0.8598), np.float32(0.7764), np.float32(0.8888), np.float32(0.8822), np.float32(0.966), np.float32(0.9717), np.float32(0.9644), np.float32(0.8529), np.float32(0.7662), np.float32(0.8371), np.float32(0.9355), np.float32(0.2904), np.float32(0.3462)] +2025-10-31 18:45:47.913193: Epoch time: 518.3 s +2025-10-31 18:45:49.959825: +2025-10-31 18:45:49.963654: Epoch 416 +2025-10-31 18:45:49.965007: Current learning rate: 0.00616 +2025-10-31 18:54:50.565964: train_loss -0.4134 +2025-10-31 18:54:50.572181: val_loss -0.4461 +2025-10-31 18:54:50.573341: Pseudo dice [np.float32(0.9347), np.float32(0.7489), np.float32(0.6951), np.float32(0.6712), np.float32(0.8524), np.float32(0.7771), np.float32(0.8929), np.float32(0.8836), np.float32(0.9675), np.float32(0.9623), np.float32(0.9671), np.float32(0.8531), np.float32(0.789), np.float32(0.8629), np.float32(0.9599), np.float32(0.351), np.float32(0.3168)] +2025-10-31 18:54:50.574871: Epoch time: 540.61 s +2025-10-31 18:54:52.535968: +2025-10-31 18:54:52.537702: Epoch 417 +2025-10-31 18:54:52.538920: Current learning rate: 0.00615 +2025-10-31 19:03:54.024398: train_loss -0.4097 +2025-10-31 19:03:54.033525: val_loss -0.3629 +2025-10-31 19:03:54.035382: Pseudo dice [np.float32(0.9152), np.float32(0.7683), np.float32(0.6978), np.float32(0.645), np.float32(0.8373), np.float32(0.7671), np.float32(0.8419), np.float32(0.8619), np.float32(0.9503), np.float32(0.9595), np.float32(0.9572), np.float32(0.8139), np.float32(0.7447), np.float32(0.8519), np.float32(0.9162), np.float32(0.4258), np.float32(0.3431)] +2025-10-31 19:03:54.036645: Epoch time: 541.49 s +2025-10-31 19:03:56.064924: +2025-10-31 19:03:56.070924: Epoch 418 +2025-10-31 19:03:56.072646: Current learning rate: 0.00614 +2025-10-31 19:12:40.307138: train_loss -0.3951 +2025-10-31 19:12:40.320940: val_loss -0.412 +2025-10-31 19:12:40.322219: Pseudo dice [np.float32(0.9171), np.float32(0.7685), np.float32(0.7338), np.float32(0.647), np.float32(0.8312), np.float32(0.8043), np.float32(0.862), np.float32(0.8733), np.float32(0.9271), np.float32(0.9317), np.float32(0.9623), np.float32(0.8051), np.float32(0.7651), np.float32(0.8579), np.float32(0.9454), np.float32(0.3944), np.float32(0.4081)] +2025-10-31 19:12:40.354976: Epoch time: 524.25 s +2025-10-31 19:12:42.346764: +2025-10-31 19:12:42.348348: Epoch 419 +2025-10-31 19:12:42.350486: Current learning rate: 0.00613 +2025-10-31 19:21:44.400485: train_loss -0.4145 +2025-10-31 19:21:44.429735: val_loss -0.4388 +2025-10-31 19:21:44.432597: Pseudo dice [np.float32(0.9331), np.float32(0.7327), np.float32(0.6512), np.float32(0.6777), np.float32(0.8501), np.float32(0.7813), np.float32(0.9018), np.float32(0.8638), np.float32(0.9287), np.float32(0.9132), np.float32(0.9626), np.float32(0.838), np.float32(0.7697), np.float32(0.8667), np.float32(0.938), np.float32(0.4303), np.float32(0.3175)] +2025-10-31 19:21:44.434777: Epoch time: 542.06 s +2025-10-31 19:21:47.114959: +2025-10-31 19:21:47.116529: Epoch 420 +2025-10-31 19:21:47.118358: Current learning rate: 0.00612 +2025-10-31 19:30:57.688531: train_loss -0.4442 +2025-10-31 19:30:57.701691: val_loss -0.4277 +2025-10-31 19:30:57.703198: Pseudo dice [np.float32(0.928), np.float32(0.7387), np.float32(0.7114), np.float32(0.6356), np.float32(0.8535), np.float32(0.8144), np.float32(0.8838), np.float32(0.8837), np.float32(0.8846), np.float32(0.9204), np.float32(0.9647), np.float32(0.8191), np.float32(0.7821), np.float32(0.8295), np.float32(0.9491), np.float32(0.3461), np.float32(0.3366)] +2025-10-31 19:30:57.705657: Epoch time: 550.58 s +2025-10-31 19:30:59.825419: +2025-10-31 19:30:59.826863: Epoch 421 +2025-10-31 19:30:59.828271: Current learning rate: 0.00612 +2025-10-31 19:40:02.524948: train_loss -0.424 +2025-10-31 19:40:02.551637: val_loss -0.4347 +2025-10-31 19:40:02.553290: Pseudo dice [np.float32(0.9404), np.float32(0.8004), np.float32(0.7494), np.float32(0.6393), np.float32(0.8619), np.float32(0.7751), np.float32(0.8803), np.float32(0.8774), np.float32(0.9604), np.float32(0.9555), np.float32(0.9625), np.float32(0.8382), np.float32(0.7799), np.float32(0.8438), np.float32(0.9012), np.float32(0.2267), np.float32(0.1553)] +2025-10-31 19:40:02.555735: Epoch time: 542.71 s +2025-10-31 19:40:04.675893: +2025-10-31 19:40:04.679034: Epoch 422 +2025-10-31 19:40:04.700431: Current learning rate: 0.00611 +2025-10-31 19:48:52.219703: train_loss -0.4308 +2025-10-31 19:48:52.271530: val_loss -0.4019 +2025-10-31 19:48:52.273135: Pseudo dice [np.float32(0.9317), np.float32(0.7376), np.float32(0.6619), np.float32(0.5552), np.float32(0.861), np.float32(0.7932), np.float32(0.8933), np.float32(0.8606), np.float32(0.9666), np.float32(0.9558), np.float32(0.959), np.float32(0.8321), np.float32(0.7907), np.float32(0.8736), np.float32(0.9481), np.float32(0.2902), np.float32(0.2045)] +2025-10-31 19:48:52.274616: Epoch time: 527.55 s +2025-10-31 19:48:54.538494: +2025-10-31 19:48:54.541963: Epoch 423 +2025-10-31 19:48:54.543617: Current learning rate: 0.0061 +2025-10-31 19:58:00.222852: train_loss -0.4204 +2025-10-31 19:58:00.233963: val_loss -0.4688 +2025-10-31 19:58:00.235234: Pseudo dice [np.float32(0.9327), np.float32(0.7518), np.float32(0.6918), np.float32(0.6155), np.float32(0.8775), np.float32(0.8139), np.float32(0.8481), np.float32(0.8649), np.float32(0.9416), np.float32(0.9396), np.float32(0.9624), np.float32(0.8376), np.float32(0.7787), np.float32(0.8703), np.float32(0.929), np.float32(0.3376), np.float32(0.265)] +2025-10-31 19:58:00.236931: Epoch time: 545.69 s +2025-10-31 19:58:02.450331: +2025-10-31 19:58:02.458530: Epoch 424 +2025-10-31 19:58:02.460670: Current learning rate: 0.00609 +2025-10-31 20:07:02.416709: train_loss -0.4447 +2025-10-31 20:07:02.421099: val_loss -0.4472 +2025-10-31 20:07:02.422842: Pseudo dice [np.float32(0.9249), np.float32(0.7439), np.float32(0.7135), np.float32(0.6852), np.float32(0.8591), np.float32(0.7851), np.float32(0.8759), np.float32(0.871), np.float32(0.9349), np.float32(0.9577), np.float32(0.9625), np.float32(0.8349), np.float32(0.762), np.float32(0.8478), np.float32(0.9366), np.float32(0.2387), np.float32(0.1429)] +2025-10-31 20:07:02.424758: Epoch time: 539.98 s +2025-10-31 20:07:04.463456: +2025-10-31 20:07:04.465122: Epoch 425 +2025-10-31 20:07:04.466486: Current learning rate: 0.00608 +2025-10-31 20:16:03.177142: train_loss -0.4448 +2025-10-31 20:16:03.216508: val_loss -0.4291 +2025-10-31 20:16:03.226188: Pseudo dice [np.float32(0.9315), np.float32(0.7465), np.float32(0.6567), np.float32(0.6892), np.float32(0.856), np.float32(0.8057), np.float32(0.8828), np.float32(0.8751), np.float32(0.9664), np.float32(0.9648), np.float32(0.9679), np.float32(0.8526), np.float32(0.753), np.float32(0.8675), np.float32(0.9554), np.float32(0.2003), np.float32(0.2526)] +2025-10-31 20:16:03.228153: Epoch time: 538.72 s +2025-10-31 20:16:05.331979: +2025-10-31 20:16:05.352052: Epoch 426 +2025-10-31 20:16:05.354574: Current learning rate: 0.00607 +2025-10-31 20:25:07.372167: train_loss -0.4456 +2025-10-31 20:25:07.379062: val_loss -0.423 +2025-10-31 20:25:07.380837: Pseudo dice [np.float32(0.9272), np.float32(0.6192), np.float32(0.6657), np.float32(0.6993), np.float32(0.8425), np.float32(0.7662), np.float32(0.8724), np.float32(0.8794), np.float32(0.96), np.float32(0.961), np.float32(0.9606), np.float32(0.8515), np.float32(0.8027), np.float32(0.855), np.float32(0.9535), np.float32(0.2574), np.float32(0.1677)] +2025-10-31 20:25:07.403117: Epoch time: 542.04 s +2025-10-31 20:25:09.530761: +2025-10-31 20:25:09.532087: Epoch 427 +2025-10-31 20:25:09.533575: Current learning rate: 0.00606 +2025-10-31 20:34:05.505780: train_loss -0.4539 +2025-10-31 20:34:05.530985: val_loss -0.432 +2025-10-31 20:34:05.532268: Pseudo dice [np.float32(0.9227), np.float32(0.7906), np.float32(0.672), np.float32(0.6177), np.float32(0.8782), np.float32(0.7795), np.float32(0.8735), np.float32(0.8758), np.float32(0.969), np.float32(0.9693), np.float32(0.9655), np.float32(0.8499), np.float32(0.7847), np.float32(0.8695), np.float32(0.9525), np.float32(0.3337), np.float32(0.2213)] +2025-10-31 20:34:05.533640: Epoch time: 535.98 s +2025-10-31 20:34:07.705716: +2025-10-31 20:34:07.706919: Epoch 428 +2025-10-31 20:34:07.709413: Current learning rate: 0.00605 +2025-10-31 20:43:06.804619: train_loss -0.4059 +2025-10-31 20:43:06.845289: val_loss -0.4205 +2025-10-31 20:43:06.846669: Pseudo dice [np.float32(0.9253), np.float32(0.7555), np.float32(0.6852), np.float32(0.5972), np.float32(0.8446), np.float32(0.7777), np.float32(0.8368), np.float32(0.8677), np.float32(0.9493), np.float32(0.9398), np.float32(0.9573), np.float32(0.845), np.float32(0.7792), np.float32(0.8666), np.float32(0.9577), np.float32(0.4406), np.float32(0.3608)] +2025-10-31 20:43:06.847825: Epoch time: 539.11 s +2025-10-31 20:43:08.896759: +2025-10-31 20:43:08.898061: Epoch 429 +2025-10-31 20:43:08.899578: Current learning rate: 0.00604 +2025-10-31 20:52:03.682706: train_loss -0.4067 +2025-10-31 20:52:03.696738: val_loss -0.4184 +2025-10-31 20:52:03.698166: Pseudo dice [np.float32(0.8693), np.float32(0.7418), np.float32(0.7174), np.float32(0.6437), np.float32(0.8646), np.float32(0.7495), np.float32(0.8778), np.float32(0.8713), np.float32(0.9781), np.float32(0.9713), np.float32(0.9608), np.float32(0.8413), np.float32(0.789), np.float32(0.8758), np.float32(0.9488), np.float32(0.3322), np.float32(0.3003)] +2025-10-31 20:52:03.701262: Epoch time: 534.8 s +2025-10-31 20:52:05.741742: +2025-10-31 20:52:05.742878: Epoch 430 +2025-10-31 20:52:05.743986: Current learning rate: 0.00603 +2025-10-31 21:00:56.781423: train_loss -0.3969 +2025-10-31 21:00:56.805286: val_loss -0.3988 +2025-10-31 21:00:56.808341: Pseudo dice [np.float32(0.9328), np.float32(0.7236), np.float32(0.6558), np.float32(0.6551), np.float32(0.878), np.float32(0.767), np.float32(0.8297), np.float32(0.8643), np.float32(0.857), np.float32(0.8476), np.float32(0.9538), np.float32(0.8051), np.float32(0.75), np.float32(0.848), np.float32(0.9201), np.float32(0.3101), np.float32(0.3295)] +2025-10-31 21:00:56.816597: Epoch time: 531.04 s +2025-10-31 21:00:58.913757: +2025-10-31 21:00:58.914973: Epoch 431 +2025-10-31 21:00:58.916078: Current learning rate: 0.00602 +2025-10-31 21:09:55.584105: train_loss -0.3814 +2025-10-31 21:09:55.595918: val_loss -0.4264 +2025-10-31 21:09:55.599745: Pseudo dice [np.float32(0.9135), np.float32(0.7408), np.float32(0.7135), np.float32(0.6313), np.float32(0.8622), np.float32(0.7547), np.float32(0.8342), np.float32(0.8589), np.float32(0.977), np.float32(0.9702), np.float32(0.9517), np.float32(0.8325), np.float32(0.7764), np.float32(0.8557), np.float32(0.9433), np.float32(0.3212), np.float32(0.2706)] +2025-10-31 21:09:55.601097: Epoch time: 536.67 s +2025-10-31 21:09:57.677690: +2025-10-31 21:09:57.678904: Epoch 432 +2025-10-31 21:09:57.680102: Current learning rate: 0.00601 +2025-10-31 21:18:45.574684: train_loss -0.3819 +2025-10-31 21:18:45.588872: val_loss -0.4102 +2025-10-31 21:18:45.596426: Pseudo dice [np.float32(0.9191), np.float32(0.6808), np.float32(0.6592), np.float32(0.6801), np.float32(0.8628), np.float32(0.7513), np.float32(0.8615), np.float32(0.8618), np.float32(0.971), np.float32(0.9727), np.float32(0.963), np.float32(0.8178), np.float32(0.7791), np.float32(0.8225), np.float32(0.9565), np.float32(0.1397), np.float32(0.1531)] +2025-10-31 21:18:45.599768: Epoch time: 527.9 s +2025-10-31 21:18:47.938637: +2025-10-31 21:18:47.941727: Epoch 433 +2025-10-31 21:18:47.942986: Current learning rate: 0.006 +2025-10-31 21:27:45.789773: train_loss -0.419 +2025-10-31 21:27:45.819980: val_loss -0.4361 +2025-10-31 21:27:45.821381: Pseudo dice [np.float32(0.9341), np.float32(0.758), np.float32(0.736), np.float32(0.6233), np.float32(0.8584), np.float32(0.7722), np.float32(0.8578), np.float32(0.882), np.float32(0.9743), np.float32(0.9755), np.float32(0.9624), np.float32(0.8263), np.float32(0.7964), np.float32(0.867), np.float32(0.9643), np.float32(0.299), np.float32(0.2298)] +2025-10-31 21:27:45.822540: Epoch time: 537.86 s +2025-10-31 21:27:47.846317: +2025-10-31 21:27:47.848161: Epoch 434 +2025-10-31 21:27:47.849591: Current learning rate: 0.00599 +2025-10-31 21:36:49.595610: train_loss -0.4326 +2025-10-31 21:36:49.642326: val_loss -0.4015 +2025-10-31 21:36:49.645402: Pseudo dice [np.float32(0.9059), np.float32(0.7751), np.float32(0.7252), np.float32(0.6172), np.float32(0.8512), np.float32(0.7531), np.float32(0.8702), np.float32(0.8751), np.float32(0.9642), np.float32(0.9628), np.float32(0.9545), np.float32(0.7957), np.float32(0.7831), np.float32(0.8343), np.float32(0.9369), np.float32(0.1147), np.float32(0.2296)] +2025-10-31 21:36:49.666119: Epoch time: 541.75 s +2025-10-31 21:36:51.830909: +2025-10-31 21:36:51.834590: Epoch 435 +2025-10-31 21:36:51.836124: Current learning rate: 0.00598 +2025-10-31 21:45:56.391540: train_loss -0.412 +2025-10-31 21:45:56.412117: val_loss -0.3874 +2025-10-31 21:45:56.413816: Pseudo dice [np.float32(0.9039), np.float32(0.7034), np.float32(0.6086), np.float32(0.6714), np.float32(0.8225), np.float32(0.759), np.float32(0.8667), np.float32(0.8461), np.float32(0.922), np.float32(0.9325), np.float32(0.9547), np.float32(0.8196), np.float32(0.7862), np.float32(0.8673), np.float32(0.8068), np.float32(0.2373), np.float32(0.198)] +2025-10-31 21:45:56.415083: Epoch time: 544.57 s +2025-10-31 21:45:58.499562: +2025-10-31 21:45:58.501513: Epoch 436 +2025-10-31 21:45:58.503336: Current learning rate: 0.00597 +2025-10-31 21:54:47.457573: train_loss -0.4066 +2025-10-31 21:54:47.466768: val_loss -0.4214 +2025-10-31 21:54:47.468127: Pseudo dice [np.float32(0.9371), np.float32(0.7495), np.float32(0.7185), np.float32(0.5431), np.float32(0.8667), np.float32(0.7985), np.float32(0.8978), np.float32(0.8953), np.float32(0.9379), np.float32(0.9532), np.float32(0.9644), np.float32(0.8445), np.float32(0.7266), np.float32(0.8903), np.float32(0.9387), np.float32(0.342), np.float32(0.3362)] +2025-10-31 21:54:47.469401: Epoch time: 528.96 s +2025-10-31 21:54:49.419815: +2025-10-31 21:54:49.421122: Epoch 437 +2025-10-31 21:54:49.422345: Current learning rate: 0.00596 +2025-10-31 22:03:52.003417: train_loss -0.425 +2025-10-31 22:03:52.012151: val_loss -0.4143 +2025-10-31 22:03:52.013775: Pseudo dice [np.float32(0.9092), np.float32(0.7164), np.float32(0.7127), np.float32(0.5561), np.float32(0.8475), np.float32(0.7879), np.float32(0.866), np.float32(0.8878), np.float32(0.9651), np.float32(0.966), np.float32(0.9648), np.float32(0.8276), np.float32(0.7617), np.float32(0.8515), np.float32(0.9175), np.float32(0.3996), np.float32(0.2496)] +2025-10-31 22:03:52.015011: Epoch time: 542.59 s +2025-10-31 22:03:54.024110: +2025-10-31 22:03:54.025687: Epoch 438 +2025-10-31 22:03:54.030269: Current learning rate: 0.00595 +2025-10-31 22:12:45.302008: train_loss -0.4386 +2025-10-31 22:12:45.311021: val_loss -0.4254 +2025-10-31 22:12:45.312383: Pseudo dice [np.float32(0.9374), np.float32(0.7284), np.float32(0.6894), np.float32(0.6444), np.float32(0.888), np.float32(0.7811), np.float32(0.8972), np.float32(0.8751), np.float32(0.9765), np.float32(0.9587), np.float32(0.9629), np.float32(0.8317), np.float32(0.7885), np.float32(0.8653), np.float32(0.9651), np.float32(0.1764), np.float32(0.2585)] +2025-10-31 22:12:45.314128: Epoch time: 531.29 s +2025-10-31 22:12:47.376917: +2025-10-31 22:12:47.378093: Epoch 439 +2025-10-31 22:12:47.379350: Current learning rate: 0.00594 +2025-10-31 22:21:51.415230: train_loss -0.4184 +2025-10-31 22:21:51.465642: val_loss -0.4337 +2025-10-31 22:21:51.467265: Pseudo dice [np.float32(0.9148), np.float32(0.7164), np.float32(0.6367), np.float32(0.6258), np.float32(0.8652), np.float32(0.8), np.float32(0.8204), np.float32(0.8757), np.float32(0.9752), np.float32(0.978), np.float32(0.962), np.float32(0.8368), np.float32(0.7786), np.float32(0.8706), np.float32(0.965), np.float32(0.2091), np.float32(0.1128)] +2025-10-31 22:21:51.468879: Epoch time: 544.04 s +2025-10-31 22:21:53.502353: +2025-10-31 22:21:53.503596: Epoch 440 +2025-10-31 22:21:53.505164: Current learning rate: 0.00593 +2025-10-31 22:30:45.393263: train_loss -0.4229 +2025-10-31 22:30:45.419165: val_loss -0.4093 +2025-10-31 22:30:45.420470: Pseudo dice [np.float32(0.9052), np.float32(0.7588), np.float32(0.7189), np.float32(0.6017), np.float32(0.8393), np.float32(0.7894), np.float32(0.824), np.float32(0.8552), np.float32(0.9823), np.float32(0.9812), np.float32(0.9641), np.float32(0.825), np.float32(0.763), np.float32(0.8424), np.float32(0.958), np.float32(0.2221), np.float32(0.1795)] +2025-10-31 22:30:45.422291: Epoch time: 531.9 s +2025-10-31 22:31:03.977697: +2025-10-31 22:31:03.979338: Epoch 441 +2025-10-31 22:31:03.980700: Current learning rate: 0.00592 +2025-10-31 22:39:56.459020: train_loss -0.4277 +2025-10-31 22:39:56.491734: val_loss -0.382 +2025-10-31 22:39:56.493015: Pseudo dice [np.float32(0.9303), np.float32(0.7258), np.float32(0.6931), np.float32(0.6153), np.float32(0.8236), np.float32(0.769), np.float32(0.8284), np.float32(0.871), np.float32(0.9727), np.float32(0.9647), np.float32(0.962), np.float32(0.8403), np.float32(0.7812), np.float32(0.8187), np.float32(0.9363), np.float32(0.3352), np.float32(0.2157)] +2025-10-31 22:39:56.494278: Epoch time: 532.49 s +2025-10-31 22:39:58.378422: +2025-10-31 22:39:58.379892: Epoch 442 +2025-10-31 22:39:58.391966: Current learning rate: 0.00592 +2025-10-31 22:48:59.510215: train_loss -0.4105 +2025-10-31 22:48:59.520850: val_loss -0.4188 +2025-10-31 22:48:59.529209: Pseudo dice [np.float32(0.9118), np.float32(0.7267), np.float32(0.6939), np.float32(0.646), np.float32(0.8539), np.float32(0.7731), np.float32(0.7979), np.float32(0.8756), np.float32(0.9641), np.float32(0.9683), np.float32(0.9636), np.float32(0.8523), np.float32(0.792), np.float32(0.845), np.float32(0.9476), np.float32(0.3798), np.float32(0.204)] +2025-10-31 22:48:59.530984: Epoch time: 541.14 s +2025-10-31 22:49:01.452529: +2025-10-31 22:49:01.453785: Epoch 443 +2025-10-31 22:49:01.455216: Current learning rate: 0.00591 +2025-10-31 22:57:54.885687: train_loss -0.4027 +2025-10-31 22:57:54.892834: val_loss -0.4161 +2025-10-31 22:57:54.899174: Pseudo dice [np.float32(0.9353), np.float32(0.7862), np.float32(0.7709), np.float32(0.6191), np.float32(0.8579), np.float32(0.7787), np.float32(0.872), np.float32(0.8877), np.float32(0.9477), np.float32(0.9554), np.float32(0.9631), np.float32(0.8208), np.float32(0.7677), np.float32(0.8529), np.float32(0.92), np.float32(0.2947), np.float32(0.3293)] +2025-10-31 22:57:54.900789: Epoch time: 533.44 s +2025-10-31 22:57:56.808293: +2025-10-31 22:57:56.811159: Epoch 444 +2025-10-31 22:57:56.812844: Current learning rate: 0.0059 +2025-10-31 23:07:12.546602: train_loss -0.4241 +2025-10-31 23:07:12.558337: val_loss -0.4258 +2025-10-31 23:07:12.559929: Pseudo dice [np.float32(0.928), np.float32(0.7153), np.float32(0.6932), np.float32(0.6259), np.float32(0.8625), np.float32(0.75), np.float32(0.8789), np.float32(0.863), np.float32(0.9465), np.float32(0.9656), np.float32(0.9542), np.float32(0.8183), np.float32(0.7819), np.float32(0.8655), np.float32(0.8572), np.float32(0.4303), np.float32(0.3016)] +2025-10-31 23:07:12.561062: Epoch time: 555.74 s +2025-10-31 23:07:14.716647: +2025-10-31 23:07:14.719057: Epoch 445 +2025-10-31 23:07:14.720380: Current learning rate: 0.00589 +2025-10-31 23:16:10.163577: train_loss -0.3894 +2025-10-31 23:16:10.192648: val_loss -0.4126 +2025-10-31 23:16:10.194937: Pseudo dice [np.float32(0.933), np.float32(0.7399), np.float32(0.6911), np.float32(0.6725), np.float32(0.8497), np.float32(0.7757), np.float32(0.8191), np.float32(0.8642), np.float32(0.9565), np.float32(0.955), np.float32(0.9624), np.float32(0.8176), np.float32(0.7532), np.float32(0.8592), np.float32(0.956), np.float32(0.4986), np.float32(0.4163)] +2025-10-31 23:16:10.196666: Epoch time: 535.45 s +2025-10-31 23:16:12.585544: +2025-10-31 23:16:12.587019: Epoch 446 +2025-10-31 23:16:12.588299: Current learning rate: 0.00588 +2025-10-31 23:25:12.756807: train_loss -0.4071 +2025-10-31 23:25:12.814776: val_loss -0.3732 +2025-10-31 23:25:12.817575: Pseudo dice [np.float32(0.9123), np.float32(0.72), np.float32(0.6976), np.float32(0.6159), np.float32(0.843), np.float32(0.775), np.float32(0.8396), np.float32(0.8363), np.float32(0.9378), np.float32(0.9318), np.float32(0.9507), np.float32(0.83), np.float32(0.7695), np.float32(0.8452), np.float32(0.9108), np.float32(0.345), np.float32(0.3122)] +2025-10-31 23:25:12.820054: Epoch time: 540.18 s +2025-10-31 23:25:15.060831: +2025-10-31 23:25:15.062152: Epoch 447 +2025-10-31 23:25:15.063240: Current learning rate: 0.00587 +2025-10-31 23:34:00.627894: train_loss -0.4068 +2025-10-31 23:34:00.634908: val_loss -0.4167 +2025-10-31 23:34:00.636734: Pseudo dice [np.float32(0.9348), np.float32(0.7858), np.float32(0.6504), np.float32(0.6522), np.float32(0.8527), np.float32(0.7618), np.float32(0.8603), np.float32(0.8778), np.float32(0.9745), np.float32(0.9792), np.float32(0.9612), np.float32(0.826), np.float32(0.7834), np.float32(0.8526), np.float32(0.9515), np.float32(0.2482), np.float32(0.2366)] +2025-10-31 23:34:00.637911: Epoch time: 525.57 s +2025-10-31 23:34:02.650419: +2025-10-31 23:34:02.653841: Epoch 448 +2025-10-31 23:34:02.655247: Current learning rate: 0.00586 +2025-10-31 23:42:57.655957: train_loss -0.4266 +2025-10-31 23:42:57.684651: val_loss -0.4641 +2025-10-31 23:42:57.685897: Pseudo dice [np.float32(0.9408), np.float32(0.7544), np.float32(0.7201), np.float32(0.6642), np.float32(0.8889), np.float32(0.8038), np.float32(0.8657), np.float32(0.8851), np.float32(0.9701), np.float32(0.9676), np.float32(0.9548), np.float32(0.84), np.float32(0.7685), np.float32(0.8901), np.float32(0.9113), np.float32(0.359), np.float32(0.3218)] +2025-10-31 23:42:57.687072: Epoch time: 535.01 s +2025-10-31 23:42:59.785595: +2025-10-31 23:42:59.787294: Epoch 449 +2025-10-31 23:42:59.788660: Current learning rate: 0.00585 +2025-10-31 23:51:52.556161: train_loss -0.4498 +2025-10-31 23:51:52.582203: val_loss -0.4549 +2025-10-31 23:51:52.588157: Pseudo dice [np.float32(0.9246), np.float32(0.7538), np.float32(0.7172), np.float32(0.6754), np.float32(0.8603), np.float32(0.8047), np.float32(0.909), np.float32(0.8939), np.float32(0.9763), np.float32(0.9774), np.float32(0.9646), np.float32(0.8312), np.float32(0.763), np.float32(0.8433), np.float32(0.9595), np.float32(0.3589), np.float32(0.3743)] +2025-10-31 23:51:52.596784: Epoch time: 532.78 s +2025-10-31 23:51:57.849376: +2025-10-31 23:51:57.851096: Epoch 450 +2025-10-31 23:51:57.852697: Current learning rate: 0.00584 +2025-11-01 00:00:50.107553: train_loss -0.434 +2025-11-01 00:00:50.150060: val_loss -0.4452 +2025-11-01 00:00:50.151341: Pseudo dice [np.float32(0.9351), np.float32(0.7817), np.float32(0.723), np.float32(0.7026), np.float32(0.8733), np.float32(0.7788), np.float32(0.8483), np.float32(0.8804), np.float32(0.9561), np.float32(0.9496), np.float32(0.9644), np.float32(0.8127), np.float32(0.7669), np.float32(0.8745), np.float32(0.9612), np.float32(0.3078), np.float32(0.3201)] +2025-11-01 00:00:50.152395: Epoch time: 532.27 s +2025-11-01 00:00:52.493688: +2025-11-01 00:00:52.495062: Epoch 451 +2025-11-01 00:00:52.500013: Current learning rate: 0.00583 +2025-11-01 00:10:25.402498: train_loss -0.4278 +2025-11-01 00:10:25.448640: val_loss -0.4399 +2025-11-01 00:10:25.450346: Pseudo dice [np.float32(0.9299), np.float32(0.7452), np.float32(0.5597), np.float32(0.6845), np.float32(0.8314), np.float32(0.6982), np.float32(0.8634), np.float32(0.8857), np.float32(0.9698), np.float32(0.969), np.float32(0.9609), np.float32(0.8138), np.float32(0.7777), np.float32(0.8303), np.float32(0.959), np.float32(0.4057), np.float32(0.3154)] +2025-11-01 00:10:25.477906: Epoch time: 572.91 s +2025-11-01 00:10:27.759700: +2025-11-01 00:10:27.761273: Epoch 452 +2025-11-01 00:10:27.762870: Current learning rate: 0.00582 +2025-11-01 00:20:48.542404: train_loss -0.4089 +2025-11-01 00:20:48.587615: val_loss -0.4487 +2025-11-01 00:20:48.589113: Pseudo dice [np.float32(0.9206), np.float32(0.7906), np.float32(0.7337), np.float32(0.6347), np.float32(0.8673), np.float32(0.7825), np.float32(0.8972), np.float32(0.8771), np.float32(0.9538), np.float32(0.9496), np.float32(0.9677), np.float32(0.8219), np.float32(0.774), np.float32(0.8712), np.float32(0.9579), np.float32(0.3816), np.float32(0.3339)] +2025-11-01 00:20:48.635107: Epoch time: 620.79 s +2025-11-01 00:20:50.965239: +2025-11-01 00:20:50.969850: Epoch 453 +2025-11-01 00:20:50.972132: Current learning rate: 0.00581 +2025-11-01 00:31:08.827361: train_loss -0.4271 +2025-11-01 00:31:08.880387: val_loss -0.4522 +2025-11-01 00:31:08.882041: Pseudo dice [np.float32(0.9421), np.float32(0.758), np.float32(0.7217), np.float32(0.6638), np.float32(0.8599), np.float32(0.7827), np.float32(0.8416), np.float32(0.8872), np.float32(0.973), np.float32(0.9734), np.float32(0.9624), np.float32(0.8416), np.float32(0.778), np.float32(0.8512), np.float32(0.949), np.float32(0.3184), np.float32(0.2498)] +2025-11-01 00:31:08.884481: Epoch time: 617.87 s +2025-11-01 00:31:11.607421: +2025-11-01 00:31:11.608987: Epoch 454 +2025-11-01 00:31:11.612856: Current learning rate: 0.0058 +2025-11-01 00:41:19.924125: train_loss -0.4124 +2025-11-01 00:41:19.940522: val_loss -0.4295 +2025-11-01 00:41:19.943597: Pseudo dice [np.float32(0.9239), np.float32(0.74), np.float32(0.7294), np.float32(0.6308), np.float32(0.857), np.float32(0.791), np.float32(0.8109), np.float32(0.8831), np.float32(0.9599), np.float32(0.9025), np.float32(0.9553), np.float32(0.8351), np.float32(0.7214), np.float32(0.8698), np.float32(0.9237), np.float32(0.3207), np.float32(0.4422)] +2025-11-01 00:41:19.945928: Epoch time: 608.32 s +2025-11-01 00:41:22.645824: +2025-11-01 00:41:22.647795: Epoch 455 +2025-11-01 00:41:22.649782: Current learning rate: 0.00579 +2025-11-01 00:51:25.255985: train_loss -0.4251 +2025-11-01 00:51:25.331132: val_loss -0.4155 +2025-11-01 00:51:25.332603: Pseudo dice [np.float32(0.918), np.float32(0.7653), np.float32(0.6839), np.float32(0.6564), np.float32(0.8539), np.float32(0.7861), np.float32(0.8325), np.float32(0.8703), np.float32(0.9669), np.float32(0.9665), np.float32(0.9521), np.float32(0.8344), np.float32(0.7502), np.float32(0.8574), np.float32(0.9025), np.float32(0.3082), np.float32(0.208)] +2025-11-01 00:51:25.344786: Epoch time: 602.62 s +2025-11-01 00:51:27.587073: +2025-11-01 00:51:27.588865: Epoch 456 +2025-11-01 00:51:27.590569: Current learning rate: 0.00578 +2025-11-01 01:02:18.771798: train_loss -0.4267 +2025-11-01 01:02:18.826982: val_loss -0.428 +2025-11-01 01:02:18.829295: Pseudo dice [np.float32(0.9277), np.float32(0.7476), np.float32(0.7149), np.float32(0.5791), np.float32(0.8696), np.float32(0.7746), np.float32(0.8156), np.float32(0.8885), np.float32(0.9747), np.float32(0.9776), np.float32(0.9628), np.float32(0.8475), np.float32(0.7773), np.float32(0.874), np.float32(0.9186), np.float32(0.3863), np.float32(0.3561)] +2025-11-01 01:02:18.831382: Epoch time: 651.19 s +2025-11-01 01:02:21.058337: +2025-11-01 01:02:21.061887: Epoch 457 +2025-11-01 01:02:21.063243: Current learning rate: 0.00577 +2025-11-01 01:14:47.352034: train_loss -0.431 +2025-11-01 01:14:47.405950: val_loss -0.4687 +2025-11-01 01:14:47.407277: Pseudo dice [np.float32(0.9328), np.float32(0.7851), np.float32(0.7686), np.float32(0.6349), np.float32(0.879), np.float32(0.7978), np.float32(0.8567), np.float32(0.8917), np.float32(0.9637), np.float32(0.9683), np.float32(0.964), np.float32(0.8414), np.float32(0.7954), np.float32(0.8806), np.float32(0.9146), np.float32(0.2676), np.float32(0.1632)] +2025-11-01 01:14:47.409079: Epoch time: 746.3 s +2025-11-01 01:14:57.576603: +2025-11-01 01:14:57.591877: Epoch 458 +2025-11-01 01:14:57.605262: Current learning rate: 0.00576 diff --git a/Dataset809_AbdomenAtlasF17/nnUNetTrainer__nnUNetResEncUNetLPlans__3d_fullres/fold_all/training_log_2025_11_1_08_36_18.txt b/Dataset809_AbdomenAtlasF17/nnUNetTrainer__nnUNetResEncUNetLPlans__3d_fullres/fold_all/training_log_2025_11_1_08_36_18.txt new file mode 100644 index 0000000000000000000000000000000000000000..810472e0883138068c13a40e9cb09fac94314a5b --- /dev/null +++ b/Dataset809_AbdomenAtlasF17/nnUNetTrainer__nnUNetResEncUNetLPlans__3d_fullres/fold_all/training_log_2025_11_1_08_36_18.txt @@ -0,0 +1,26 @@ + +####################################################################### +Please cite the following paper when using nnU-Net: +Isensee, F., Jaeger, P. F., Kohl, S. A., Petersen, J., & Maier-Hein, K. H. (2021). nnU-Net: a self-configuring method for deep learning-based biomedical image segmentation. Nature methods, 18(2), 203-211. +####################################################################### + +2025-11-01 08:36:24.398811: Using torch.compile... +2025-11-01 08:36:45.052451: do_dummy_2d_data_aug: False + +This is the configuration used by this training: +Configuration name: 3d_fullres + {'data_identifier': 'nnUNetPlans_3d_fullres', 'preprocessor_name': 'DefaultPreprocessor', 'batch_size': 2, 'patch_size': [160, 224, 192], 'median_image_size_in_voxels': [512.0, 613.0, 513.0], 'spacing': [0.7109375, 0.5, 0.7109375], 'normalization_schemes': ['CTNormalization'], 'use_mask_for_norm': [False], 'resampling_fn_data': 'resample_data_or_seg_to_shape', 'resampling_fn_seg': 'resample_data_or_seg_to_shape', 'resampling_fn_data_kwargs': {'is_seg': False, 'order': 3, 'order_z': 0, 'force_separate_z': None}, 'resampling_fn_seg_kwargs': {'is_seg': True, 'order': 1, 'order_z': 0, 'force_separate_z': None}, 'resampling_fn_probabilities': 'resample_data_or_seg_to_shape', 'resampling_fn_probabilities_kwargs': {'is_seg': False, 'order': 1, 'order_z': 0, 'force_separate_z': None}, 'architecture': {'network_class_name': 'dynamic_network_architectures.architectures.unet.ResidualEncoderUNet', 'arch_kwargs': {'n_stages': 6, 'features_per_stage': [32, 64, 128, 256, 320, 320], 'conv_op': 'torch.nn.modules.conv.Conv3d', 'kernel_sizes': [[3, 3, 3], [3, 3, 3], [3, 3, 3], [3, 3, 3], [3, 3, 3], [3, 3, 3]], 'strides': [[1, 1, 1], [2, 2, 2], [2, 2, 2], [2, 2, 2], [2, 2, 2], [2, 2, 2]], 'n_blocks_per_stage': [1, 3, 4, 6, 6, 6], 'n_conv_per_stage_decoder': [1, 1, 1, 1, 1], 'conv_bias': True, 'norm_op': 'torch.nn.modules.instancenorm.InstanceNorm3d', 'norm_op_kwargs': {'eps': 1e-05, 'affine': True}, 'dropout_op': None, 'dropout_op_kwargs': None, 'nonlin': 'torch.nn.LeakyReLU', 'nonlin_kwargs': {'inplace': True}}, '_kw_requires_import': ['conv_op', 'norm_op', 'dropout_op', 'nonlin']}, 'batch_dice': True} + +These are the global plan.json settings: + {'dataset_name': 'Dataset809_AbdomenAtlasF17', 'plans_name': 'nnUNetResEncUNetLPlans', 'original_median_spacing_after_transp': [0.7109375, 0.5, 0.7109375], 'original_median_shape_after_transp': [512, 608, 512], 'image_reader_writer': 'SimpleITKIO', 'transpose_forward': [1, 0, 2], 'transpose_backward': [1, 0, 2], 'experiment_planner_used': 'nnUNetPlannerResEncL', 'label_manager': 'LabelManager', 'foreground_intensity_properties_per_channel': {'0': {'max': 1000.0, 'mean': 39.68027877807617, 'median': 71.0, 'min': -1000.0, 'percentile_00_5': -1000.0, 'percentile_99_5': 379.0, 'std': 192.4669952392578}}} + +2025-11-01 08:37:17.108070: unpacking dataset... +2025-11-01 08:38:09.972894: unpacking done... +2025-11-01 08:38:09.995002: Unable to plot network architecture: nnUNet_compile is enabled! +2025-11-01 08:38:10.515083: +2025-11-01 08:38:10.517237: Epoch 450 +2025-11-01 08:38:10.518909: Current learning rate: 0.00584 +2025-11-01 08:55:58.583854: train_loss -0.4371 +2025-11-01 08:55:58.605177: val_loss -0.4559 +2025-11-01 08:55:58.606929: Pseudo dice [np.float32(0.9505), np.float32(0.7827), np.float32(0.7344), np.float32(0.675), np.float32(0.846), np.float32(0.7937), np.float32(0.8776), np.float32(0.8831), np.float32(0.9412), np.float32(0.9393), np.float32(0.9665), np.float32(0.85), np.float32(0.7965), np.float32(0.846), np.float32(0.9684), np.float32(0.2859), np.float32(0.2493)] +2025-11-01 08:55:58.608141: Epoch time: 1068.08 s diff --git a/Dataset809_AbdomenAtlasF17/nnUNetTrainer__nnUNetResEncUNetLPlans__3d_fullres/fold_all/training_log_2025_11_1_10_13_43.txt b/Dataset809_AbdomenAtlasF17/nnUNetTrainer__nnUNetResEncUNetLPlans__3d_fullres/fold_all/training_log_2025_11_1_10_13_43.txt new file mode 100644 index 0000000000000000000000000000000000000000..ff81256a86c4ebbcfcd5ee9e591eeab7c16c72bc --- /dev/null +++ b/Dataset809_AbdomenAtlasF17/nnUNetTrainer__nnUNetResEncUNetLPlans__3d_fullres/fold_all/training_log_2025_11_1_10_13_43.txt @@ -0,0 +1,3452 @@ + +####################################################################### +Please cite the following paper when using nnU-Net: +Isensee, F., Jaeger, P. F., Kohl, S. A., Petersen, J., & Maier-Hein, K. H. (2021). nnU-Net: a self-configuring method for deep learning-based biomedical image segmentation. Nature methods, 18(2), 203-211. +####################################################################### + +2025-11-01 10:13:47.647567: Using torch.compile... +2025-11-01 10:13:57.191924: do_dummy_2d_data_aug: False + +This is the configuration used by this training: +Configuration name: 3d_fullres + {'data_identifier': 'nnUNetPlans_3d_fullres', 'preprocessor_name': 'DefaultPreprocessor', 'batch_size': 2, 'patch_size': [160, 224, 192], 'median_image_size_in_voxels': [512.0, 613.0, 513.0], 'spacing': [0.7109375, 0.5, 0.7109375], 'normalization_schemes': ['CTNormalization'], 'use_mask_for_norm': [False], 'resampling_fn_data': 'resample_data_or_seg_to_shape', 'resampling_fn_seg': 'resample_data_or_seg_to_shape', 'resampling_fn_data_kwargs': {'is_seg': False, 'order': 3, 'order_z': 0, 'force_separate_z': None}, 'resampling_fn_seg_kwargs': {'is_seg': True, 'order': 1, 'order_z': 0, 'force_separate_z': None}, 'resampling_fn_probabilities': 'resample_data_or_seg_to_shape', 'resampling_fn_probabilities_kwargs': {'is_seg': False, 'order': 1, 'order_z': 0, 'force_separate_z': None}, 'architecture': {'network_class_name': 'dynamic_network_architectures.architectures.unet.ResidualEncoderUNet', 'arch_kwargs': {'n_stages': 6, 'features_per_stage': [32, 64, 128, 256, 320, 320], 'conv_op': 'torch.nn.modules.conv.Conv3d', 'kernel_sizes': [[3, 3, 3], [3, 3, 3], [3, 3, 3], [3, 3, 3], [3, 3, 3], [3, 3, 3]], 'strides': [[1, 1, 1], [2, 2, 2], [2, 2, 2], [2, 2, 2], [2, 2, 2], [2, 2, 2]], 'n_blocks_per_stage': [1, 3, 4, 6, 6, 6], 'n_conv_per_stage_decoder': [1, 1, 1, 1, 1], 'conv_bias': True, 'norm_op': 'torch.nn.modules.instancenorm.InstanceNorm3d', 'norm_op_kwargs': {'eps': 1e-05, 'affine': True}, 'dropout_op': None, 'dropout_op_kwargs': None, 'nonlin': 'torch.nn.LeakyReLU', 'nonlin_kwargs': {'inplace': True}}, '_kw_requires_import': ['conv_op', 'norm_op', 'dropout_op', 'nonlin']}, 'batch_dice': True} + +These are the global plan.json settings: + {'dataset_name': 'Dataset809_AbdomenAtlasF17', 'plans_name': 'nnUNetResEncUNetLPlans', 'original_median_spacing_after_transp': [0.7109375, 0.5, 0.7109375], 'original_median_shape_after_transp': [512, 608, 512], 'image_reader_writer': 'SimpleITKIO', 'transpose_forward': [1, 0, 2], 'transpose_backward': [1, 0, 2], 'experiment_planner_used': 'nnUNetPlannerResEncL', 'label_manager': 'LabelManager', 'foreground_intensity_properties_per_channel': {'0': {'max': 1000.0, 'mean': 39.68027877807617, 'median': 71.0, 'min': -1000.0, 'percentile_00_5': -1000.0, 'percentile_99_5': 379.0, 'std': 192.4669952392578}}} + +2025-11-01 10:14:30.926474: unpacking dataset... +2025-11-01 10:15:19.042328: unpacking done... +2025-11-01 10:15:19.063479: Unable to plot network architecture: nnUNet_compile is enabled! +2025-11-01 10:15:19.135991: +2025-11-01 10:15:19.137342: Epoch 450 +2025-11-01 10:15:19.139066: Current learning rate: 0.00584 +2025-11-01 10:26:49.156073: train_loss -0.4438 +2025-11-01 10:26:49.177761: val_loss -0.4153 +2025-11-01 10:26:49.180488: Pseudo dice [np.float32(0.9335), np.float32(0.7675), np.float32(0.7089), np.float32(0.6511), np.float32(0.7979), np.float32(0.7703), np.float32(0.7819), np.float32(0.8782), np.float32(0.9346), np.float32(0.9637), np.float32(0.9534), np.float32(0.8401), np.float32(0.799), np.float32(0.809), np.float32(0.9386), np.float32(0.3564), np.float32(0.3423)] +2025-11-01 10:26:49.181932: Epoch time: 690.03 s +2025-11-01 10:26:55.269691: +2025-11-01 10:26:55.273703: Epoch 451 +2025-11-01 10:26:55.275024: Current learning rate: 0.00583 +2025-11-01 10:35:55.498753: train_loss -0.4152 +2025-11-01 10:35:55.544734: val_loss -0.4168 +2025-11-01 10:35:55.546165: Pseudo dice [np.float32(0.9421), np.float32(0.7373), np.float32(0.6832), np.float32(0.6806), np.float32(0.8319), np.float32(0.767), np.float32(0.823), np.float32(0.8572), np.float32(0.9645), np.float32(0.9355), np.float32(0.967), np.float32(0.8407), np.float32(0.7979), np.float32(0.8409), np.float32(0.958), np.float32(0.4114), np.float32(0.3062)] +2025-11-01 10:35:55.548986: Epoch time: 540.23 s +2025-11-01 10:35:57.564637: +2025-11-01 10:35:57.568272: Epoch 452 +2025-11-01 10:35:57.570216: Current learning rate: 0.00582 +2025-11-01 10:44:49.153139: train_loss -0.449 +2025-11-01 10:44:49.161616: val_loss -0.429 +2025-11-01 10:44:49.162743: Pseudo dice [np.float32(0.9318), np.float32(0.7562), np.float32(0.6714), np.float32(0.5958), np.float32(0.8666), np.float32(0.7785), np.float32(0.8808), np.float32(0.8557), np.float32(0.967), np.float32(0.9709), np.float32(0.9678), np.float32(0.8338), np.float32(0.7551), np.float32(0.8824), np.float32(0.9653), np.float32(0.1977), np.float32(0.1661)] +2025-11-01 10:44:49.199109: Epoch time: 531.6 s +2025-11-01 10:44:51.185269: +2025-11-01 10:44:51.186914: Epoch 453 +2025-11-01 10:44:51.188335: Current learning rate: 0.00581 +2025-11-01 10:53:56.296225: train_loss -0.4144 +2025-11-01 10:53:56.307675: val_loss -0.4453 +2025-11-01 10:53:56.309739: Pseudo dice [np.float32(0.8955), np.float32(0.7443), np.float32(0.6655), np.float32(0.6979), np.float32(0.8592), np.float32(0.7752), np.float32(0.8925), np.float32(0.8688), np.float32(0.9585), np.float32(0.9649), np.float32(0.9614), np.float32(0.8353), np.float32(0.7888), np.float32(0.855), np.float32(0.955), np.float32(0.3405), np.float32(0.2902)] +2025-11-01 10:53:56.311394: Epoch time: 545.12 s +2025-11-01 10:53:58.363756: +2025-11-01 10:53:58.365852: Epoch 454 +2025-11-01 10:53:58.370609: Current learning rate: 0.0058 +2025-11-01 11:02:47.024143: train_loss -0.4181 +2025-11-01 11:02:47.079034: val_loss -0.4575 +2025-11-01 11:02:47.080439: Pseudo dice [np.float32(0.9249), np.float32(0.7185), np.float32(0.6632), np.float32(0.653), np.float32(0.8474), np.float32(0.7642), np.float32(0.8906), np.float32(0.8766), np.float32(0.97), np.float32(0.9672), np.float32(0.9499), np.float32(0.824), np.float32(0.7901), np.float32(0.8519), np.float32(0.9617), np.float32(0.4387), np.float32(0.3608)] +2025-11-01 11:02:47.082393: Epoch time: 528.66 s +2025-11-01 11:02:49.051844: +2025-11-01 11:02:49.062562: Epoch 455 +2025-11-01 11:02:49.070172: Current learning rate: 0.00579 +2025-11-01 11:11:36.501174: train_loss -0.4012 +2025-11-01 11:11:36.505563: val_loss -0.424 +2025-11-01 11:11:36.506944: Pseudo dice [np.float32(0.9022), np.float32(0.7741), np.float32(0.6815), np.float32(0.6591), np.float32(0.8472), np.float32(0.7901), np.float32(0.8957), np.float32(0.8749), np.float32(0.9565), np.float32(0.9591), np.float32(0.939), np.float32(0.8379), np.float32(0.7863), np.float32(0.8635), np.float32(0.8847), np.float32(0.3593), np.float32(0.3552)] +2025-11-01 11:11:36.508251: Epoch time: 527.45 s +2025-11-01 11:11:38.268121: +2025-11-01 11:11:38.272816: Epoch 456 +2025-11-01 11:11:38.274262: Current learning rate: 0.00578 +2025-11-01 11:20:05.627680: train_loss -0.4372 +2025-11-01 11:20:05.632667: val_loss -0.4209 +2025-11-01 11:20:05.633907: Pseudo dice [np.float32(0.9392), np.float32(0.7715), np.float32(0.714), np.float32(0.667), np.float32(0.8425), np.float32(0.7451), np.float32(0.8141), np.float32(0.8825), np.float32(0.9141), np.float32(0.9556), np.float32(0.9505), np.float32(0.8398), np.float32(0.7794), np.float32(0.8563), np.float32(0.9061), np.float32(0.2387), np.float32(0.2197)] +2025-11-01 11:20:05.635134: Epoch time: 507.36 s +2025-11-01 11:20:07.637561: +2025-11-01 11:20:07.642212: Epoch 457 +2025-11-01 11:20:07.644212: Current learning rate: 0.00577 +2025-11-01 11:29:01.664156: train_loss -0.4472 +2025-11-01 11:29:01.673231: val_loss -0.4049 +2025-11-01 11:29:01.675797: Pseudo dice [np.float32(0.9238), np.float32(0.7708), np.float32(0.7286), np.float32(0.605), np.float32(0.8209), np.float32(0.7859), np.float32(0.8855), np.float32(0.8888), np.float32(0.9341), np.float32(0.9419), np.float32(0.9654), np.float32(0.852), np.float32(0.7674), np.float32(0.8283), np.float32(0.9521), np.float32(0.4243), np.float32(0.4461)] +2025-11-01 11:29:01.815814: Epoch time: 534.03 s +2025-11-01 11:29:04.484459: +2025-11-01 11:29:04.488949: Epoch 458 +2025-11-01 11:29:04.490847: Current learning rate: 0.00576 +2025-11-01 11:37:54.082186: train_loss -0.4529 +2025-11-01 11:37:54.088335: val_loss -0.4642 +2025-11-01 11:37:54.089768: Pseudo dice [np.float32(0.9231), np.float32(0.7739), np.float32(0.6677), np.float32(0.6436), np.float32(0.889), np.float32(0.7778), np.float32(0.8851), np.float32(0.8784), np.float32(0.98), np.float32(0.9826), np.float32(0.9655), np.float32(0.8369), np.float32(0.8142), np.float32(0.8757), np.float32(0.9628), np.float32(0.4345), np.float32(0.4178)] +2025-11-01 11:37:54.091143: Epoch time: 529.61 s +2025-11-01 11:37:55.989151: +2025-11-01 11:37:55.990791: Epoch 459 +2025-11-01 11:37:55.992099: Current learning rate: 0.00575 +2025-11-01 11:46:54.885500: train_loss -0.4385 +2025-11-01 11:46:54.890272: val_loss -0.4771 +2025-11-01 11:46:54.891989: Pseudo dice [np.float32(0.9395), np.float32(0.7777), np.float32(0.781), np.float32(0.6858), np.float32(0.8658), np.float32(0.8015), np.float32(0.9134), np.float32(0.8815), np.float32(0.9763), np.float32(0.975), np.float32(0.968), np.float32(0.8409), np.float32(0.7904), np.float32(0.8855), np.float32(0.965), np.float32(0.2781), np.float32(0.306)] +2025-11-01 11:46:54.893562: Epoch time: 538.91 s +2025-11-01 11:46:54.894768: Yayy! New best EMA pseudo Dice: 0.7856000065803528 +2025-11-01 11:47:00.599449: +2025-11-01 11:47:00.602124: Epoch 460 +2025-11-01 11:47:00.603212: Current learning rate: 0.00574 +2025-11-01 11:55:56.155874: train_loss -0.4439 +2025-11-01 11:55:56.160627: val_loss -0.4412 +2025-11-01 11:55:56.162012: Pseudo dice [np.float32(0.9034), np.float32(0.7215), np.float32(0.6874), np.float32(0.6408), np.float32(0.8074), np.float32(0.7781), np.float32(0.8963), np.float32(0.8842), np.float32(0.981), np.float32(0.9795), np.float32(0.9561), np.float32(0.8258), np.float32(0.7708), np.float32(0.8619), np.float32(0.9252), np.float32(0.2965), np.float32(0.3768)] +2025-11-01 11:55:56.163556: Epoch time: 535.57 s +2025-11-01 11:55:57.960803: +2025-11-01 11:55:57.962937: Epoch 461 +2025-11-01 11:55:57.964232: Current learning rate: 0.00573 +2025-11-01 12:04:38.659126: train_loss -0.4312 +2025-11-01 12:04:38.676835: val_loss -0.4642 +2025-11-01 12:04:38.678632: Pseudo dice [np.float32(0.9368), np.float32(0.7947), np.float32(0.6682), np.float32(0.5727), np.float32(0.8841), np.float32(0.7963), np.float32(0.885), np.float32(0.8669), np.float32(0.9672), np.float32(0.9657), np.float32(0.9607), np.float32(0.8498), np.float32(0.7889), np.float32(0.888), np.float32(0.9358), np.float32(0.1647), np.float32(0.1621)] +2025-11-01 12:04:38.679990: Epoch time: 520.7 s +2025-11-01 12:04:40.591633: +2025-11-01 12:04:40.595882: Epoch 462 +2025-11-01 12:04:40.597944: Current learning rate: 0.00572 +2025-11-01 12:13:41.228184: train_loss -0.4166 +2025-11-01 12:13:41.274361: val_loss -0.4377 +2025-11-01 12:13:41.276017: Pseudo dice [np.float32(0.9397), np.float32(0.7933), np.float32(0.7024), np.float32(0.6538), np.float32(0.8808), np.float32(0.8002), np.float32(0.8903), np.float32(0.8863), np.float32(0.9328), np.float32(0.927), np.float32(0.9537), np.float32(0.8578), np.float32(0.7654), np.float32(0.8827), np.float32(0.9144), np.float32(0.4836), np.float32(0.3274)] +2025-11-01 12:13:41.277284: Epoch time: 540.64 s +2025-11-01 12:13:43.046881: +2025-11-01 12:13:43.052714: Epoch 463 +2025-11-01 12:13:43.054465: Current learning rate: 0.00571 +2025-11-01 12:22:34.531021: train_loss -0.4206 +2025-11-01 12:22:34.541430: val_loss -0.4106 +2025-11-01 12:22:34.546847: Pseudo dice [np.float32(0.9315), np.float32(0.7379), np.float32(0.5541), np.float32(0.6343), np.float32(0.8386), np.float32(0.7751), np.float32(0.865), np.float32(0.8558), np.float32(0.9419), np.float32(0.9516), np.float32(0.9552), np.float32(0.826), np.float32(0.7205), np.float32(0.8396), np.float32(0.9238), np.float32(0.2805), np.float32(0.3056)] +2025-11-01 12:22:34.549223: Epoch time: 531.49 s +2025-11-01 12:22:36.415609: +2025-11-01 12:22:36.423182: Epoch 464 +2025-11-01 12:22:36.424968: Current learning rate: 0.0057 +2025-11-01 12:31:20.942596: train_loss -0.4226 +2025-11-01 12:31:20.951902: val_loss -0.4291 +2025-11-01 12:31:20.953360: Pseudo dice [np.float32(0.9286), np.float32(0.7335), np.float32(0.7144), np.float32(0.6584), np.float32(0.8472), np.float32(0.7816), np.float32(0.8479), np.float32(0.8791), np.float32(0.9413), np.float32(0.9507), np.float32(0.9623), np.float32(0.8232), np.float32(0.7853), np.float32(0.8607), np.float32(0.9561), np.float32(0.2485), np.float32(0.3033)] +2025-11-01 12:31:20.954673: Epoch time: 524.53 s +2025-11-01 12:31:22.837552: +2025-11-01 12:31:22.839167: Epoch 465 +2025-11-01 12:31:22.840485: Current learning rate: 0.0057 +2025-11-01 12:40:23.358704: train_loss -0.441 +2025-11-01 12:40:23.429685: val_loss -0.3586 +2025-11-01 12:40:23.434528: Pseudo dice [np.float32(0.9342), np.float32(0.7183), np.float32(0.7063), np.float32(0.6428), np.float32(0.834), np.float32(0.8028), np.float32(0.8581), np.float32(0.8604), np.float32(0.9598), np.float32(0.949), np.float32(0.9415), np.float32(0.8113), np.float32(0.7752), np.float32(0.854), np.float32(0.9589), np.float32(0.2799), np.float32(0.1747)] +2025-11-01 12:40:23.441010: Epoch time: 540.53 s +2025-11-01 12:40:25.293179: +2025-11-01 12:40:25.303354: Epoch 466 +2025-11-01 12:40:25.304730: Current learning rate: 0.00569 +2025-11-01 12:49:29.249110: train_loss -0.4447 +2025-11-01 12:49:29.261805: val_loss -0.4663 +2025-11-01 12:49:29.265234: Pseudo dice [np.float32(0.9166), np.float32(0.7416), np.float32(0.6805), np.float32(0.7102), np.float32(0.8876), np.float32(0.7615), np.float32(0.8786), np.float32(0.8612), np.float32(0.9497), np.float32(0.96), np.float32(0.9638), np.float32(0.8209), np.float32(0.747), np.float32(0.8568), np.float32(0.95), np.float32(0.2849), np.float32(0.2592)] +2025-11-01 12:49:29.267061: Epoch time: 543.96 s +2025-11-01 12:49:31.091898: +2025-11-01 12:49:31.093414: Epoch 467 +2025-11-01 12:49:31.095079: Current learning rate: 0.00568 +2025-11-01 12:58:20.201551: train_loss -0.416 +2025-11-01 12:58:20.208139: val_loss -0.4232 +2025-11-01 12:58:20.209844: Pseudo dice [np.float32(0.9266), np.float32(0.6737), np.float32(0.6492), np.float32(0.5779), np.float32(0.8531), np.float32(0.7927), np.float32(0.8663), np.float32(0.8762), np.float32(0.9533), np.float32(0.9556), np.float32(0.9627), np.float32(0.8408), np.float32(0.7855), np.float32(0.832), np.float32(0.952), np.float32(0.4285), np.float32(0.3055)] +2025-11-01 12:58:20.211199: Epoch time: 529.11 s +2025-11-01 12:58:22.130486: +2025-11-01 12:58:22.132049: Epoch 468 +2025-11-01 12:58:22.133217: Current learning rate: 0.00567 +2025-11-01 13:07:12.520622: train_loss -0.4285 +2025-11-01 13:07:12.532111: val_loss -0.4674 +2025-11-01 13:07:12.533740: Pseudo dice [np.float32(0.9397), np.float32(0.6921), np.float32(0.6771), np.float32(0.6982), np.float32(0.8728), np.float32(0.7626), np.float32(0.8124), np.float32(0.86), np.float32(0.9627), np.float32(0.9695), np.float32(0.962), np.float32(0.8377), np.float32(0.7913), np.float32(0.8432), np.float32(0.961), np.float32(0.3797), np.float32(0.3402)] +2025-11-01 13:07:12.534923: Epoch time: 530.39 s +2025-11-01 13:07:15.008475: +2025-11-01 13:07:15.016809: Epoch 469 +2025-11-01 13:07:15.023487: Current learning rate: 0.00566 +2025-11-01 13:15:55.710609: train_loss -0.4027 +2025-11-01 13:15:55.715486: val_loss -0.4297 +2025-11-01 13:15:55.717006: Pseudo dice [np.float32(0.9299), np.float32(0.7488), np.float32(0.6827), np.float32(0.6583), np.float32(0.8401), np.float32(0.7512), np.float32(0.8456), np.float32(0.8547), np.float32(0.9536), np.float32(0.9409), np.float32(0.957), np.float32(0.8245), np.float32(0.7914), np.float32(0.8581), np.float32(0.9595), np.float32(0.2326), np.float32(0.1838)] +2025-11-01 13:15:55.718404: Epoch time: 520.71 s +2025-11-01 13:15:57.527684: +2025-11-01 13:15:57.531192: Epoch 470 +2025-11-01 13:15:57.534511: Current learning rate: 0.00565 +2025-11-01 13:24:38.083108: train_loss -0.435 +2025-11-01 13:24:38.093373: val_loss -0.4381 +2025-11-01 13:24:38.100100: Pseudo dice [np.float32(0.9139), np.float32(0.6934), np.float32(0.7013), np.float32(0.6699), np.float32(0.8646), np.float32(0.7846), np.float32(0.7831), np.float32(0.8806), np.float32(0.9808), np.float32(0.9725), np.float32(0.9601), np.float32(0.8126), np.float32(0.7832), np.float32(0.8632), np.float32(0.9589), np.float32(0.3775), np.float32(0.3966)] +2025-11-01 13:24:38.101554: Epoch time: 520.56 s +2025-11-01 13:24:39.908026: +2025-11-01 13:24:39.935549: Epoch 471 +2025-11-01 13:24:39.938533: Current learning rate: 0.00564 +2025-11-01 13:33:29.308801: train_loss -0.4348 +2025-11-01 13:33:29.321022: val_loss -0.4594 +2025-11-01 13:33:29.323077: Pseudo dice [np.float32(0.9423), np.float32(0.7713), np.float32(0.7274), np.float32(0.6461), np.float32(0.826), np.float32(0.7884), np.float32(0.8671), np.float32(0.8822), np.float32(0.9726), np.float32(0.9665), np.float32(0.9559), np.float32(0.8582), np.float32(0.7905), np.float32(0.8522), np.float32(0.9212), np.float32(0.4405), np.float32(0.3783)] +2025-11-01 13:33:29.327220: Epoch time: 529.41 s +2025-11-01 13:33:31.308480: +2025-11-01 13:33:31.310043: Epoch 472 +2025-11-01 13:33:31.312274: Current learning rate: 0.00563 +2025-11-01 13:42:35.530180: train_loss -0.4389 +2025-11-01 13:42:35.631934: val_loss -0.4536 +2025-11-01 13:42:35.633362: Pseudo dice [np.float32(0.8973), np.float32(0.7719), np.float32(0.6998), np.float32(0.6492), np.float32(0.8696), np.float32(0.7882), np.float32(0.9009), np.float32(0.8684), np.float32(0.9789), np.float32(0.9745), np.float32(0.9653), np.float32(0.8439), np.float32(0.8005), np.float32(0.8678), np.float32(0.9604), np.float32(0.252), np.float32(0.2583)] +2025-11-01 13:42:35.635217: Epoch time: 544.22 s +2025-11-01 13:42:37.700107: +2025-11-01 13:42:37.710701: Epoch 473 +2025-11-01 13:42:37.711867: Current learning rate: 0.00562 +2025-11-01 13:51:38.959510: train_loss -0.4062 +2025-11-01 13:51:38.972630: val_loss -0.4299 +2025-11-01 13:51:38.977554: Pseudo dice [np.float32(0.9358), np.float32(0.7441), np.float32(0.7152), np.float32(0.6509), np.float32(0.8458), np.float32(0.7634), np.float32(0.8448), np.float32(0.866), np.float32(0.9584), np.float32(0.8312), np.float32(0.9524), np.float32(0.8073), np.float32(0.7896), np.float32(0.8707), np.float32(0.9602), np.float32(0.2845), np.float32(0.2981)] +2025-11-01 13:51:38.979398: Epoch time: 541.26 s +2025-11-01 13:51:40.826813: +2025-11-01 13:51:40.828203: Epoch 474 +2025-11-01 13:51:40.829440: Current learning rate: 0.00561 +2025-11-01 14:00:48.071923: train_loss -0.4314 +2025-11-01 14:00:48.088386: val_loss -0.4144 +2025-11-01 14:00:48.091458: Pseudo dice [np.float32(0.9368), np.float32(0.738), np.float32(0.7514), np.float32(0.564), np.float32(0.8497), np.float32(0.7722), np.float32(0.8776), np.float32(0.8665), np.float32(0.9489), np.float32(0.9533), np.float32(0.9624), np.float32(0.8399), np.float32(0.7832), np.float32(0.8508), np.float32(0.9225), np.float32(0.3033), np.float32(0.2825)] +2025-11-01 14:00:48.093006: Epoch time: 547.25 s +2025-11-01 14:00:50.149428: +2025-11-01 14:00:50.150668: Epoch 475 +2025-11-01 14:00:50.152001: Current learning rate: 0.0056 +2025-11-01 14:09:37.843381: train_loss -0.4189 +2025-11-01 14:09:37.848578: val_loss -0.4113 +2025-11-01 14:09:37.849917: Pseudo dice [np.float32(0.911), np.float32(0.7639), np.float32(0.7246), np.float32(0.6224), np.float32(0.8468), np.float32(0.7883), np.float32(0.8109), np.float32(0.8757), np.float32(0.9746), np.float32(0.9724), np.float32(0.9631), np.float32(0.8415), np.float32(0.7897), np.float32(0.8414), np.float32(0.9454), np.float32(0.1699), np.float32(0.17)] +2025-11-01 14:09:37.851200: Epoch time: 527.7 s +2025-11-01 14:09:58.209315: +2025-11-01 14:09:58.210931: Epoch 476 +2025-11-01 14:09:58.212458: Current learning rate: 0.00559 +2025-11-01 14:18:52.740487: train_loss -0.4214 +2025-11-01 14:18:52.756497: val_loss -0.4145 +2025-11-01 14:18:52.758042: Pseudo dice [np.float32(0.9106), np.float32(0.7721), np.float32(0.7045), np.float32(0.6217), np.float32(0.8617), np.float32(0.7992), np.float32(0.866), np.float32(0.8664), np.float32(0.9619), np.float32(0.9607), np.float32(0.9607), np.float32(0.8376), np.float32(0.7877), np.float32(0.8522), np.float32(0.9544), np.float32(0.248), np.float32(0.2524)] +2025-11-01 14:18:52.777889: Epoch time: 534.53 s +2025-11-01 14:18:54.664706: +2025-11-01 14:18:54.666081: Epoch 477 +2025-11-01 14:18:54.667512: Current learning rate: 0.00558 +2025-11-01 14:27:54.938593: train_loss -0.3824 +2025-11-01 14:27:54.947564: val_loss -0.4636 +2025-11-01 14:27:54.951222: Pseudo dice [np.float32(0.9116), np.float32(0.798), np.float32(0.6926), np.float32(0.6629), np.float32(0.8725), np.float32(0.7766), np.float32(0.8633), np.float32(0.8782), np.float32(0.9703), np.float32(0.9675), np.float32(0.9573), np.float32(0.8496), np.float32(0.7773), np.float32(0.848), np.float32(0.9345), np.float32(0.4231), np.float32(0.4123)] +2025-11-01 14:27:54.952843: Epoch time: 540.28 s +2025-11-01 14:27:56.925875: +2025-11-01 14:27:56.927761: Epoch 478 +2025-11-01 14:27:56.929181: Current learning rate: 0.00557 +2025-11-01 14:36:47.159212: train_loss -0.4029 +2025-11-01 14:36:47.165424: val_loss -0.3956 +2025-11-01 14:36:47.167342: Pseudo dice [np.float32(0.9184), np.float32(0.7854), np.float32(0.7487), np.float32(0.6916), np.float32(0.8503), np.float32(0.7786), np.float32(0.8558), np.float32(0.866), np.float32(0.9102), np.float32(0.9172), np.float32(0.9577), np.float32(0.8441), np.float32(0.7647), np.float32(0.862), np.float32(0.9509), np.float32(0.2914), np.float32(0.1874)] +2025-11-01 14:36:47.168614: Epoch time: 530.24 s +2025-11-01 14:36:49.055205: +2025-11-01 14:36:49.064960: Epoch 479 +2025-11-01 14:36:49.067112: Current learning rate: 0.00556 +2025-11-01 14:45:32.601107: train_loss -0.4166 +2025-11-01 14:45:32.606575: val_loss -0.4439 +2025-11-01 14:45:32.610651: Pseudo dice [np.float32(0.9299), np.float32(0.7652), np.float32(0.6808), np.float32(0.6139), np.float32(0.8553), np.float32(0.7413), np.float32(0.8308), np.float32(0.8702), np.float32(0.9583), np.float32(0.9484), np.float32(0.9624), np.float32(0.8197), np.float32(0.791), np.float32(0.8582), np.float32(0.9578), np.float32(0.3335), np.float32(0.264)] +2025-11-01 14:45:32.612520: Epoch time: 523.55 s +2025-11-01 14:45:34.755258: +2025-11-01 14:45:34.759155: Epoch 480 +2025-11-01 14:45:34.761337: Current learning rate: 0.00555 +2025-11-01 14:54:32.666204: train_loss -0.4052 +2025-11-01 14:54:32.671681: val_loss -0.3951 +2025-11-01 14:54:32.673325: Pseudo dice [np.float32(0.9216), np.float32(0.7157), np.float32(0.6771), np.float32(0.6638), np.float32(0.8593), np.float32(0.7609), np.float32(0.8661), np.float32(0.8669), np.float32(0.9371), np.float32(0.9356), np.float32(0.9602), np.float32(0.8055), np.float32(0.776), np.float32(0.8633), np.float32(0.9319), np.float32(0.3249), np.float32(0.22)] +2025-11-01 14:54:32.675204: Epoch time: 537.92 s +2025-11-01 14:54:34.904279: +2025-11-01 14:54:34.906111: Epoch 481 +2025-11-01 14:54:34.908200: Current learning rate: 0.00554 +2025-11-01 15:03:32.519491: train_loss -0.4335 +2025-11-01 15:03:32.543076: val_loss -0.4649 +2025-11-01 15:03:32.546639: Pseudo dice [np.float32(0.9436), np.float32(0.7477), np.float32(0.7146), np.float32(0.6553), np.float32(0.8408), np.float32(0.7577), np.float32(0.8733), np.float32(0.8739), np.float32(0.9644), np.float32(0.9624), np.float32(0.9669), np.float32(0.8549), np.float32(0.8127), np.float32(0.8564), np.float32(0.9582), np.float32(0.3054), np.float32(0.324)] +2025-11-01 15:03:32.548814: Epoch time: 537.63 s +2025-11-01 15:03:34.766973: +2025-11-01 15:03:34.769016: Epoch 482 +2025-11-01 15:03:34.771835: Current learning rate: 0.00553 +2025-11-01 15:12:24.333149: train_loss -0.4161 +2025-11-01 15:12:24.337917: val_loss -0.4104 +2025-11-01 15:12:24.339236: Pseudo dice [np.float32(0.9097), np.float32(0.7415), np.float32(0.7364), np.float32(0.5938), np.float32(0.865), np.float32(0.8261), np.float32(0.867), np.float32(0.8883), np.float32(0.9686), np.float32(0.9705), np.float32(0.9662), np.float32(0.8334), np.float32(0.7408), np.float32(0.8772), np.float32(0.9513), np.float32(0.3705), np.float32(0.275)] +2025-11-01 15:12:24.385585: Epoch time: 529.58 s +2025-11-01 15:12:26.495506: +2025-11-01 15:12:26.502712: Epoch 483 +2025-11-01 15:12:26.507452: Current learning rate: 0.00552 +2025-11-01 15:20:59.940650: train_loss -0.4191 +2025-11-01 15:21:00.036215: val_loss -0.438 +2025-11-01 15:21:00.038857: Pseudo dice [np.float32(0.9301), np.float32(0.7633), np.float32(0.7018), np.float32(0.6123), np.float32(0.8776), np.float32(0.7977), np.float32(0.814), np.float32(0.877), np.float32(0.9624), np.float32(0.9694), np.float32(0.9531), np.float32(0.8371), np.float32(0.7737), np.float32(0.8597), np.float32(0.9542), np.float32(0.2745), np.float32(0.3648)] +2025-11-01 15:21:00.040931: Epoch time: 513.45 s +2025-11-01 15:21:02.295809: +2025-11-01 15:21:02.301487: Epoch 484 +2025-11-01 15:21:02.303648: Current learning rate: 0.00551 +2025-11-01 15:30:40.172907: train_loss -0.4312 +2025-11-01 15:30:40.185323: val_loss -0.4581 +2025-11-01 15:30:40.187490: Pseudo dice [np.float32(0.9103), np.float32(0.7495), np.float32(0.7398), np.float32(0.6513), np.float32(0.8864), np.float32(0.7794), np.float32(0.8253), np.float32(0.8653), np.float32(0.9448), np.float32(0.9091), np.float32(0.9533), np.float32(0.8552), np.float32(0.7949), np.float32(0.8793), np.float32(0.9279), np.float32(0.4157), np.float32(0.2944)] +2025-11-01 15:30:40.189053: Epoch time: 577.89 s +2025-11-01 15:30:42.487721: +2025-11-01 15:30:42.488947: Epoch 485 +2025-11-01 15:30:42.490306: Current learning rate: 0.0055 +2025-11-01 15:40:09.026519: train_loss -0.4318 +2025-11-01 15:40:09.035902: val_loss -0.4172 +2025-11-01 15:40:09.037795: Pseudo dice [np.float32(0.9203), np.float32(0.745), np.float32(0.7277), np.float32(0.6373), np.float32(0.8665), np.float32(0.7966), np.float32(0.8615), np.float32(0.8844), np.float32(0.9516), np.float32(0.956), np.float32(0.9503), np.float32(0.7984), np.float32(0.7629), np.float32(0.8844), np.float32(0.8982), np.float32(0.2091), np.float32(0.2396)] +2025-11-01 15:40:09.039445: Epoch time: 566.54 s +2025-11-01 15:40:11.390402: +2025-11-01 15:40:11.393076: Epoch 486 +2025-11-01 15:40:11.394753: Current learning rate: 0.00549 +2025-11-01 15:50:16.128203: train_loss -0.4528 +2025-11-01 15:50:16.141234: val_loss -0.459 +2025-11-01 15:50:16.143165: Pseudo dice [np.float32(0.9364), np.float32(0.7894), np.float32(0.6718), np.float32(0.634), np.float32(0.8529), np.float32(0.7708), np.float32(0.8199), np.float32(0.8634), np.float32(0.9784), np.float32(0.97), np.float32(0.9676), np.float32(0.8479), np.float32(0.7868), np.float32(0.8448), np.float32(0.9667), np.float32(0.3167), np.float32(0.3786)] +2025-11-01 15:50:16.145060: Epoch time: 604.74 s +2025-11-01 15:50:18.773934: +2025-11-01 15:50:18.777550: Epoch 487 +2025-11-01 15:50:18.780611: Current learning rate: 0.00548 +2025-11-01 16:00:35.450947: train_loss -0.4482 +2025-11-01 16:00:35.476776: val_loss -0.4376 +2025-11-01 16:00:35.478741: Pseudo dice [np.float32(0.9267), np.float32(0.7816), np.float32(0.7291), np.float32(0.6854), np.float32(0.8262), np.float32(0.7633), np.float32(0.8378), np.float32(0.8838), np.float32(0.9697), np.float32(0.9633), np.float32(0.9624), np.float32(0.8347), np.float32(0.7795), np.float32(0.8267), np.float32(0.9245), np.float32(0.3649), np.float32(0.3942)] +2025-11-01 16:00:35.481991: Epoch time: 616.68 s +2025-11-01 16:00:37.660124: +2025-11-01 16:00:37.663185: Epoch 488 +2025-11-01 16:00:37.667731: Current learning rate: 0.00547 +2025-11-01 16:10:54.396025: train_loss -0.4203 +2025-11-01 16:10:54.823913: val_loss -0.4303 +2025-11-01 16:10:54.838973: Pseudo dice [np.float32(0.8994), np.float32(0.7658), np.float32(0.7051), np.float32(0.6902), np.float32(0.845), np.float32(0.753), np.float32(0.8865), np.float32(0.8898), np.float32(0.967), np.float32(0.9615), np.float32(0.95), np.float32(0.8069), np.float32(0.7826), np.float32(0.8515), np.float32(0.9196), np.float32(0.3373), np.float32(0.3096)] +2025-11-01 16:10:54.904422: Epoch time: 616.74 s +2025-11-01 16:10:57.911278: +2025-11-01 16:10:57.914371: Epoch 489 +2025-11-01 16:10:57.920446: Current learning rate: 0.00546 +2025-11-01 16:21:02.639503: train_loss -0.3823 +2025-11-01 16:21:02.778240: val_loss -0.4756 +2025-11-01 16:21:02.784954: Pseudo dice [np.float32(0.9235), np.float32(0.7674), np.float32(0.6847), np.float32(0.6262), np.float32(0.8575), np.float32(0.7501), np.float32(0.8603), np.float32(0.8748), np.float32(0.9651), np.float32(0.9686), np.float32(0.9629), np.float32(0.8384), np.float32(0.7908), np.float32(0.8728), np.float32(0.9396), np.float32(0.3022), np.float32(0.262)] +2025-11-01 16:21:02.793592: Epoch time: 604.73 s +2025-11-01 16:21:04.876023: +2025-11-01 16:21:04.883940: Epoch 490 +2025-11-01 16:21:04.886467: Current learning rate: 0.00546 +2025-11-01 16:31:20.229097: train_loss -0.4102 +2025-11-01 16:31:20.264438: val_loss -0.3901 +2025-11-01 16:31:20.270597: Pseudo dice [np.float32(0.8836), np.float32(0.7666), np.float32(0.6909), np.float32(0.5662), np.float32(0.8494), np.float32(0.7211), np.float32(0.864), np.float32(0.8639), np.float32(0.8741), np.float32(0.8629), np.float32(0.9602), np.float32(0.8238), np.float32(0.7757), np.float32(0.8668), np.float32(0.9278), np.float32(0.3534), np.float32(0.3254)] +2025-11-01 16:31:20.272906: Epoch time: 615.36 s +2025-11-01 16:31:22.392665: +2025-11-01 16:31:22.398549: Epoch 491 +2025-11-01 16:31:22.405523: Current learning rate: 0.00545 +2025-11-01 16:41:24.033595: train_loss -0.4256 +2025-11-01 16:41:24.091128: val_loss -0.4016 +2025-11-01 16:41:24.095432: Pseudo dice [np.float32(0.9224), np.float32(0.7425), np.float32(0.7333), np.float32(0.5991), np.float32(0.7657), np.float32(0.7461), np.float32(0.8923), np.float32(0.8731), np.float32(0.9754), np.float32(0.9814), np.float32(0.9603), np.float32(0.8286), np.float32(0.7547), np.float32(0.8129), np.float32(0.9352), np.float32(0.4863), np.float32(0.2943)] +2025-11-01 16:41:24.098336: Epoch time: 601.65 s +2025-11-01 16:41:26.178751: +2025-11-01 16:41:26.191450: Epoch 492 +2025-11-01 16:41:26.193573: Current learning rate: 0.00544 +2025-11-01 16:51:27.914637: train_loss -0.4047 +2025-11-01 16:51:28.019348: val_loss -0.4041 +2025-11-01 16:51:28.022094: Pseudo dice [np.float32(0.9247), np.float32(0.769), np.float32(0.6512), np.float32(0.5885), np.float32(0.8476), np.float32(0.7221), np.float32(0.7991), np.float32(0.8596), np.float32(0.9081), np.float32(0.901), np.float32(0.9487), np.float32(0.8279), np.float32(0.7558), np.float32(0.8223), np.float32(0.9396), np.float32(0.3457), np.float32(0.3)] +2025-11-01 16:51:28.073440: Epoch time: 601.74 s +2025-11-01 16:51:30.829756: +2025-11-01 16:51:30.833247: Epoch 493 +2025-11-01 16:51:30.835596: Current learning rate: 0.00543 +2025-11-01 17:01:31.362477: train_loss -0.3901 +2025-11-01 17:01:31.384003: val_loss -0.4505 +2025-11-01 17:01:31.386605: Pseudo dice [np.float32(0.9361), np.float32(0.7731), np.float32(0.7197), np.float32(0.678), np.float32(0.8755), np.float32(0.7561), np.float32(0.8463), np.float32(0.8825), np.float32(0.9433), np.float32(0.9602), np.float32(0.9633), np.float32(0.8451), np.float32(0.7206), np.float32(0.8645), np.float32(0.8946), np.float32(0.3101), np.float32(0.295)] +2025-11-01 17:01:31.403681: Epoch time: 600.55 s +2025-11-01 17:01:33.407316: +2025-11-01 17:01:33.411552: Epoch 494 +2025-11-01 17:01:33.419003: Current learning rate: 0.00542 +2025-11-01 17:11:56.265953: train_loss -0.4127 +2025-11-01 17:11:56.275882: val_loss -0.397 +2025-11-01 17:11:56.278459: Pseudo dice [np.float32(0.9118), np.float32(0.7497), np.float32(0.6544), np.float32(0.6461), np.float32(0.8469), np.float32(0.7387), np.float32(0.8537), np.float32(0.8657), np.float32(0.975), np.float32(0.9661), np.float32(0.9487), np.float32(0.8266), np.float32(0.7589), np.float32(0.8581), np.float32(0.9413), np.float32(0.2885), np.float32(0.2864)] +2025-11-01 17:11:56.281777: Epoch time: 622.86 s +2025-11-01 17:11:58.369414: +2025-11-01 17:11:58.399377: Epoch 495 +2025-11-01 17:11:58.413120: Current learning rate: 0.00541 +2025-11-01 17:22:15.895301: train_loss -0.4368 +2025-11-01 17:22:15.946617: val_loss -0.4466 +2025-11-01 17:22:15.949194: Pseudo dice [np.float32(0.9349), np.float32(0.7413), np.float32(0.7267), np.float32(0.6791), np.float32(0.8698), np.float32(0.7876), np.float32(0.8758), np.float32(0.8926), np.float32(0.9405), np.float32(0.9373), np.float32(0.9622), np.float32(0.8507), np.float32(0.7972), np.float32(0.8671), np.float32(0.9559), np.float32(0.2681), np.float32(0.2873)] +2025-11-01 17:22:15.965751: Epoch time: 617.53 s +2025-11-01 17:22:18.095228: +2025-11-01 17:22:18.099949: Epoch 496 +2025-11-01 17:22:18.107673: Current learning rate: 0.0054 +2025-11-01 17:32:23.494115: train_loss -0.432 +2025-11-01 17:32:23.507321: val_loss -0.4362 +2025-11-01 17:32:23.520019: Pseudo dice [np.float32(0.9127), np.float32(0.7407), np.float32(0.6538), np.float32(0.6673), np.float32(0.8481), np.float32(0.7532), np.float32(0.8876), np.float32(0.8828), np.float32(0.9637), np.float32(0.9818), np.float32(0.965), np.float32(0.8295), np.float32(0.7926), np.float32(0.8518), np.float32(0.9578), np.float32(0.4333), np.float32(0.3986)] +2025-11-01 17:32:23.523491: Epoch time: 605.4 s +2025-11-01 17:32:25.505576: +2025-11-01 17:32:25.509448: Epoch 497 +2025-11-01 17:32:25.511779: Current learning rate: 0.00539 +2025-11-01 17:42:39.404964: train_loss -0.4272 +2025-11-01 17:42:39.457242: val_loss -0.4698 +2025-11-01 17:42:39.460083: Pseudo dice [np.float32(0.9264), np.float32(0.7351), np.float32(0.7051), np.float32(0.6296), np.float32(0.8841), np.float32(0.8086), np.float32(0.9094), np.float32(0.8909), np.float32(0.9738), np.float32(0.9758), np.float32(0.9673), np.float32(0.8647), np.float32(0.8116), np.float32(0.8802), np.float32(0.9617), np.float32(0.2321), np.float32(0.2055)] +2025-11-01 17:42:39.465726: Epoch time: 613.9 s +2025-11-01 17:42:41.505341: +2025-11-01 17:42:41.511038: Epoch 498 +2025-11-01 17:42:41.526619: Current learning rate: 0.00538 +2025-11-01 17:52:55.137769: train_loss -0.3684 +2025-11-01 17:52:55.175608: val_loss -0.415 +2025-11-01 17:52:55.181271: Pseudo dice [np.float32(0.9274), np.float32(0.7417), np.float32(0.7005), np.float32(0.6534), np.float32(0.8086), np.float32(0.7544), np.float32(0.877), np.float32(0.8607), np.float32(0.9584), np.float32(0.9401), np.float32(0.9564), np.float32(0.8441), np.float32(0.7852), np.float32(0.8352), np.float32(0.9439), np.float32(0.3424), np.float32(0.3086)] +2025-11-01 17:52:55.187643: Epoch time: 613.64 s +2025-11-01 17:52:57.244092: +2025-11-01 17:52:57.246054: Epoch 499 +2025-11-01 17:52:57.248815: Current learning rate: 0.00537 +2025-11-01 18:03:03.009847: train_loss -0.3877 +2025-11-01 18:03:03.038356: val_loss -0.4588 +2025-11-01 18:03:03.042527: Pseudo dice [np.float32(0.9279), np.float32(0.7268), np.float32(0.7452), np.float32(0.5722), np.float32(0.8811), np.float32(0.7643), np.float32(0.8003), np.float32(0.8687), np.float32(0.9515), np.float32(0.9188), np.float32(0.9566), np.float32(0.8612), np.float32(0.7443), np.float32(0.8807), np.float32(0.935), np.float32(0.2707), np.float32(0.3227)] +2025-11-01 18:03:03.047683: Epoch time: 605.77 s +2025-11-01 18:03:24.524111: +2025-11-01 18:03:24.526002: Epoch 500 +2025-11-01 18:03:24.527479: Current learning rate: 0.00536 +2025-11-01 18:13:44.609572: train_loss -0.4201 +2025-11-01 18:13:44.641304: val_loss -0.431 +2025-11-01 18:13:44.646179: Pseudo dice [np.float32(0.9299), np.float32(0.7456), np.float32(0.6848), np.float32(0.6702), np.float32(0.8542), np.float32(0.7867), np.float32(0.8495), np.float32(0.8686), np.float32(0.9587), np.float32(0.9483), np.float32(0.9575), np.float32(0.8213), np.float32(0.7905), np.float32(0.8545), np.float32(0.9567), np.float32(0.2684), np.float32(0.2493)] +2025-11-01 18:13:44.650649: Epoch time: 620.09 s +2025-11-01 18:13:46.532518: +2025-11-01 18:13:46.535249: Epoch 501 +2025-11-01 18:13:46.538976: Current learning rate: 0.00535 +2025-11-01 18:24:16.749735: train_loss -0.4154 +2025-11-01 18:24:16.772722: val_loss -0.4261 +2025-11-01 18:24:16.785619: Pseudo dice [np.float32(0.9345), np.float32(0.7788), np.float32(0.6937), np.float32(0.6414), np.float32(0.8782), np.float32(0.7284), np.float32(0.8856), np.float32(0.8688), np.float32(0.9615), np.float32(0.9343), np.float32(0.9564), np.float32(0.8447), np.float32(0.7546), np.float32(0.8618), np.float32(0.9534), np.float32(0.3202), np.float32(0.3024)] +2025-11-01 18:24:16.791203: Epoch time: 630.22 s +2025-11-01 18:24:18.639414: +2025-11-01 18:24:18.656384: Epoch 502 +2025-11-01 18:24:18.660952: Current learning rate: 0.00534 +2025-11-01 18:34:21.486183: train_loss -0.4249 +2025-11-01 18:34:21.492173: val_loss -0.41 +2025-11-01 18:34:21.493982: Pseudo dice [np.float32(0.9267), np.float32(0.7834), np.float32(0.6893), np.float32(0.6878), np.float32(0.8585), np.float32(0.754), np.float32(0.8894), np.float32(0.8543), np.float32(0.9812), np.float32(0.9814), np.float32(0.9665), np.float32(0.8174), np.float32(0.762), np.float32(0.8524), np.float32(0.9651), np.float32(0.3087), np.float32(0.3111)] +2025-11-01 18:34:21.495850: Epoch time: 602.85 s +2025-11-01 18:34:23.445011: +2025-11-01 18:34:23.462997: Epoch 503 +2025-11-01 18:34:23.470091: Current learning rate: 0.00533 +2025-11-01 18:44:22.818831: train_loss -0.4217 +2025-11-01 18:44:22.850983: val_loss -0.4253 +2025-11-01 18:44:22.852946: Pseudo dice [np.float32(0.9361), np.float32(0.8076), np.float32(0.7549), np.float32(0.6821), np.float32(0.8498), np.float32(0.8052), np.float32(0.8946), np.float32(0.8846), np.float32(0.9644), np.float32(0.9658), np.float32(0.9637), np.float32(0.86), np.float32(0.7342), np.float32(0.8606), np.float32(0.9598), np.float32(0.2443), np.float32(0.2212)] +2025-11-01 18:44:22.854762: Epoch time: 599.38 s +2025-11-01 18:44:24.794471: +2025-11-01 18:44:24.832307: Epoch 504 +2025-11-01 18:44:24.836739: Current learning rate: 0.00532 +2025-11-01 18:54:39.828084: train_loss -0.4293 +2025-11-01 18:54:39.840636: val_loss -0.4415 +2025-11-01 18:54:39.842635: Pseudo dice [np.float32(0.9327), np.float32(0.7754), np.float32(0.7202), np.float32(0.6549), np.float32(0.8748), np.float32(0.7829), np.float32(0.8602), np.float32(0.8726), np.float32(0.9234), np.float32(0.9358), np.float32(0.9474), np.float32(0.8352), np.float32(0.7562), np.float32(0.8628), np.float32(0.9212), np.float32(0.3137), np.float32(0.3129)] +2025-11-01 18:54:39.845147: Epoch time: 615.04 s +2025-11-01 18:54:41.984076: +2025-11-01 18:54:41.998001: Epoch 505 +2025-11-01 18:54:42.000773: Current learning rate: 0.00531 +2025-11-01 19:04:54.448812: train_loss -0.4356 +2025-11-01 19:04:54.483243: val_loss -0.4455 +2025-11-01 19:04:54.486805: Pseudo dice [np.float32(0.9196), np.float32(0.7399), np.float32(0.699), np.float32(0.6688), np.float32(0.8557), np.float32(0.7708), np.float32(0.8305), np.float32(0.8678), np.float32(0.9662), np.float32(0.9602), np.float32(0.9623), np.float32(0.8651), np.float32(0.7673), np.float32(0.8524), np.float32(0.9541), np.float32(0.3275), np.float32(0.2986)] +2025-11-01 19:04:54.492906: Epoch time: 612.47 s +2025-11-01 19:04:56.871101: +2025-11-01 19:04:56.875406: Epoch 506 +2025-11-01 19:04:56.888240: Current learning rate: 0.0053 +2025-11-01 19:14:57.174123: train_loss -0.4384 +2025-11-01 19:14:57.184933: val_loss -0.4474 +2025-11-01 19:14:57.190328: Pseudo dice [np.float32(0.9322), np.float32(0.7715), np.float32(0.6895), np.float32(0.6741), np.float32(0.8766), np.float32(0.7924), np.float32(0.8442), np.float32(0.8782), np.float32(0.9834), np.float32(0.9068), np.float32(0.9653), np.float32(0.8324), np.float32(0.7783), np.float32(0.8695), np.float32(0.9473), np.float32(0.237), np.float32(0.2096)] +2025-11-01 19:14:57.201409: Epoch time: 600.31 s +2025-11-01 19:14:59.433521: +2025-11-01 19:14:59.441191: Epoch 507 +2025-11-01 19:14:59.443717: Current learning rate: 0.00529 +2025-11-01 19:25:11.444787: train_loss -0.4665 +2025-11-01 19:25:11.461043: val_loss -0.4241 +2025-11-01 19:25:11.466864: Pseudo dice [np.float32(0.9353), np.float32(0.7464), np.float32(0.7004), np.float32(0.6481), np.float32(0.877), np.float32(0.7859), np.float32(0.8392), np.float32(0.8832), np.float32(0.9741), np.float32(0.9766), np.float32(0.9688), np.float32(0.8467), np.float32(0.7698), np.float32(0.8813), np.float32(0.9632), np.float32(0.3724), np.float32(0.2868)] +2025-11-01 19:25:11.470022: Epoch time: 612.02 s +2025-11-01 19:25:13.694136: +2025-11-01 19:25:13.699240: Epoch 508 +2025-11-01 19:25:13.701948: Current learning rate: 0.00528 +2025-11-01 19:35:22.721388: train_loss -0.4211 +2025-11-01 19:35:22.746069: val_loss -0.4448 +2025-11-01 19:35:22.752664: Pseudo dice [np.float32(0.9298), np.float32(0.7564), np.float32(0.704), np.float32(0.6892), np.float32(0.8598), np.float32(0.7939), np.float32(0.8796), np.float32(0.8844), np.float32(0.9808), np.float32(0.9775), np.float32(0.9654), np.float32(0.8368), np.float32(0.7564), np.float32(0.8678), np.float32(0.9334), np.float32(0.2317), np.float32(0.2583)] +2025-11-01 19:35:22.755012: Epoch time: 609.03 s +2025-11-01 19:35:24.713980: +2025-11-01 19:35:24.716573: Epoch 509 +2025-11-01 19:35:24.718785: Current learning rate: 0.00527 +2025-11-01 19:45:01.544731: train_loss -0.4218 +2025-11-01 19:45:01.570774: val_loss -0.4273 +2025-11-01 19:45:01.572644: Pseudo dice [np.float32(0.9277), np.float32(0.7569), np.float32(0.6423), np.float32(0.6632), np.float32(0.7571), np.float32(0.7488), np.float32(0.8467), np.float32(0.8777), np.float32(0.9675), np.float32(0.9653), np.float32(0.9586), np.float32(0.8394), np.float32(0.8021), np.float32(0.8728), np.float32(0.9517), np.float32(0.3417), np.float32(0.3342)] +2025-11-01 19:45:01.574741: Epoch time: 576.84 s +2025-11-01 19:45:03.493891: +2025-11-01 19:45:03.501646: Epoch 510 +2025-11-01 19:45:03.503470: Current learning rate: 0.00526 +2025-11-01 19:54:22.859623: train_loss -0.3979 +2025-11-01 19:54:22.868221: val_loss -0.4449 +2025-11-01 19:54:22.870044: Pseudo dice [np.float32(0.9318), np.float32(0.7492), np.float32(0.7139), np.float32(0.6332), np.float32(0.8594), np.float32(0.7709), np.float32(0.8709), np.float32(0.8665), np.float32(0.9659), np.float32(0.978), np.float32(0.9423), np.float32(0.8308), np.float32(0.7654), np.float32(0.8388), np.float32(0.957), np.float32(0.2965), np.float32(0.204)] +2025-11-01 19:54:22.872548: Epoch time: 559.37 s +2025-11-01 19:54:24.841251: +2025-11-01 19:54:24.844874: Epoch 511 +2025-11-01 19:54:24.846691: Current learning rate: 0.00525 +2025-11-01 20:03:57.886273: train_loss -0.4049 +2025-11-01 20:03:57.894515: val_loss -0.4256 +2025-11-01 20:03:57.897512: Pseudo dice [np.float32(0.9193), np.float32(0.7685), np.float32(0.7248), np.float32(0.6077), np.float32(0.8069), np.float32(0.8065), np.float32(0.8693), np.float32(0.8681), np.float32(0.9722), np.float32(0.977), np.float32(0.9624), np.float32(0.8291), np.float32(0.7402), np.float32(0.8215), np.float32(0.9596), np.float32(0.3053), np.float32(0.2888)] +2025-11-01 20:03:57.903739: Epoch time: 573.05 s +2025-11-01 20:03:59.859998: +2025-11-01 20:03:59.865581: Epoch 512 +2025-11-01 20:03:59.874837: Current learning rate: 0.00524 +2025-11-01 20:13:33.255243: train_loss -0.4406 +2025-11-01 20:13:33.266624: val_loss -0.4472 +2025-11-01 20:13:33.270056: Pseudo dice [np.float32(0.9262), np.float32(0.7564), np.float32(0.6653), np.float32(0.5689), np.float32(0.8777), np.float32(0.7573), np.float32(0.8952), np.float32(0.8869), np.float32(0.9738), np.float32(0.9828), np.float32(0.9653), np.float32(0.8533), np.float32(0.7986), np.float32(0.8921), np.float32(0.9552), np.float32(0.3376), np.float32(0.2413)] +2025-11-01 20:13:33.272677: Epoch time: 573.4 s +2025-11-01 20:13:35.333464: +2025-11-01 20:13:35.335759: Epoch 513 +2025-11-01 20:13:35.339410: Current learning rate: 0.00523 +2025-11-01 20:23:00.782022: train_loss -0.4448 +2025-11-01 20:23:00.794192: val_loss -0.4 +2025-11-01 20:23:00.797694: Pseudo dice [np.float32(0.9319), np.float32(0.3311), np.float32(0.7682), np.float32(0.6752), np.float32(0.8405), np.float32(0.7839), np.float32(0.8539), np.float32(0.8871), np.float32(0.958), np.float32(0.972), np.float32(0.9665), np.float32(0.8248), np.float32(0.7751), np.float32(0.8468), np.float32(0.9524), np.float32(0.3595), np.float32(0.3505)] +2025-11-01 20:23:00.802819: Epoch time: 565.45 s +2025-11-01 20:23:02.926739: +2025-11-01 20:23:02.941357: Epoch 514 +2025-11-01 20:23:02.944256: Current learning rate: 0.00522 +2025-11-01 20:32:06.639488: train_loss -0.433 +2025-11-01 20:32:06.669963: val_loss -0.406 +2025-11-01 20:32:06.672638: Pseudo dice [np.float32(0.9176), np.float32(0.7329), np.float32(0.7354), np.float32(0.6358), np.float32(0.8148), np.float32(0.7689), np.float32(0.8784), np.float32(0.8713), np.float32(0.9448), np.float32(0.9138), np.float32(0.9594), np.float32(0.8542), np.float32(0.7938), np.float32(0.8656), np.float32(0.9548), np.float32(0.3492), np.float32(0.4602)] +2025-11-01 20:32:06.678643: Epoch time: 543.72 s +2025-11-01 20:32:08.844030: +2025-11-01 20:32:08.846882: Epoch 515 +2025-11-01 20:32:08.850411: Current learning rate: 0.00521 +2025-11-01 20:41:36.270647: train_loss -0.4112 +2025-11-01 20:41:36.292334: val_loss -0.4569 +2025-11-01 20:41:36.297021: Pseudo dice [np.float32(0.9084), np.float32(0.7779), np.float32(0.73), np.float32(0.5676), np.float32(0.8642), np.float32(0.783), np.float32(0.8452), np.float32(0.8621), np.float32(0.9571), np.float32(0.9676), np.float32(0.9644), np.float32(0.8182), np.float32(0.808), np.float32(0.8855), np.float32(0.9541), np.float32(0.3193), np.float32(0.397)] +2025-11-01 20:41:36.299138: Epoch time: 567.44 s +2025-11-01 20:41:38.286685: +2025-11-01 20:41:38.291930: Epoch 516 +2025-11-01 20:41:38.295027: Current learning rate: 0.0052 +2025-11-01 20:51:00.278263: train_loss -0.4251 +2025-11-01 20:51:00.307607: val_loss -0.4279 +2025-11-01 20:51:00.309648: Pseudo dice [np.float32(0.8663), np.float32(0.7626), np.float32(0.7043), np.float32(0.6133), np.float32(0.8415), np.float32(0.7941), np.float32(0.7973), np.float32(0.8736), np.float32(0.9745), np.float32(0.9741), np.float32(0.9651), np.float32(0.8482), np.float32(0.7607), np.float32(0.8237), np.float32(0.9667), np.float32(0.2943), np.float32(0.3047)] +2025-11-01 20:51:00.311818: Epoch time: 562.0 s +2025-11-01 20:51:02.262259: +2025-11-01 20:51:02.264607: Epoch 517 +2025-11-01 20:51:02.266506: Current learning rate: 0.00519 +2025-11-01 21:00:40.423797: train_loss -0.4222 +2025-11-01 21:00:40.434939: val_loss -0.4049 +2025-11-01 21:00:40.444738: Pseudo dice [np.float32(0.8949), np.float32(0.7437), np.float32(0.7098), np.float32(0.6165), np.float32(0.8391), np.float32(0.7785), np.float32(0.8287), np.float32(0.8652), np.float32(0.9675), np.float32(0.959), np.float32(0.9594), np.float32(0.8239), np.float32(0.7463), np.float32(0.8711), np.float32(0.9645), np.float32(0.3435), np.float32(0.3439)] +2025-11-01 21:00:40.453364: Epoch time: 578.17 s +2025-11-01 21:00:42.331605: +2025-11-01 21:00:42.335155: Epoch 518 +2025-11-01 21:00:42.336600: Current learning rate: 0.00518 +2025-11-01 21:09:52.512421: train_loss -0.4525 +2025-11-01 21:09:52.525783: val_loss -0.4712 +2025-11-01 21:09:52.527347: Pseudo dice [np.float32(0.9314), np.float32(0.7905), np.float32(0.7611), np.float32(0.6997), np.float32(0.8664), np.float32(0.7862), np.float32(0.9068), np.float32(0.8851), np.float32(0.9831), np.float32(0.9804), np.float32(0.971), np.float32(0.8444), np.float32(0.8017), np.float32(0.8771), np.float32(0.9664), np.float32(0.3693), np.float32(0.3346)] +2025-11-01 21:09:52.529761: Epoch time: 550.19 s +2025-11-01 21:09:54.509193: +2025-11-01 21:09:54.511186: Epoch 519 +2025-11-01 21:09:54.516180: Current learning rate: 0.00518 +2025-11-01 21:19:19.742516: train_loss -0.4273 +2025-11-01 21:19:19.787830: val_loss -0.4912 +2025-11-01 21:19:19.791167: Pseudo dice [np.float32(0.9292), np.float32(0.7788), np.float32(0.7307), np.float32(0.6884), np.float32(0.8776), np.float32(0.773), np.float32(0.9065), np.float32(0.8888), np.float32(0.9763), np.float32(0.9734), np.float32(0.9645), np.float32(0.8439), np.float32(0.8038), np.float32(0.8686), np.float32(0.9487), np.float32(0.4023), np.float32(0.2683)] +2025-11-01 21:19:19.802399: Epoch time: 565.24 s +2025-11-01 21:19:21.710515: +2025-11-01 21:19:21.729196: Epoch 520 +2025-11-01 21:19:21.731668: Current learning rate: 0.00517 +2025-11-01 21:28:50.579284: train_loss -0.4301 +2025-11-01 21:28:50.604225: val_loss -0.4004 +2025-11-01 21:28:50.611013: Pseudo dice [np.float32(0.895), np.float32(0.8159), np.float32(0.7385), np.float32(0.636), np.float32(0.8732), np.float32(0.7791), np.float32(0.8758), np.float32(0.8756), np.float32(0.9752), np.float32(0.9771), np.float32(0.9634), np.float32(0.8335), np.float32(0.7596), np.float32(0.8529), np.float32(0.9425), np.float32(0.161), np.float32(0.3105)] +2025-11-01 21:28:50.614034: Epoch time: 568.87 s +2025-11-01 21:28:52.869302: +2025-11-01 21:28:52.888188: Epoch 521 +2025-11-01 21:28:52.895059: Current learning rate: 0.00516 +2025-11-01 21:38:10.392496: train_loss -0.4089 +2025-11-01 21:38:10.411104: val_loss -0.4288 +2025-11-01 21:38:10.413706: Pseudo dice [np.float32(0.9172), np.float32(0.6959), np.float32(0.61), np.float32(0.6945), np.float32(0.853), np.float32(0.7818), np.float32(0.8921), np.float32(0.8663), np.float32(0.973), np.float32(0.977), np.float32(0.9659), np.float32(0.8279), np.float32(0.7916), np.float32(0.8086), np.float32(0.9666), np.float32(0.4396), np.float32(0.4112)] +2025-11-01 21:38:10.416164: Epoch time: 557.53 s +2025-11-01 21:38:10.418323: Yayy! New best EMA pseudo Dice: 0.7857999801635742 +2025-11-01 21:38:17.388520: +2025-11-01 21:38:17.399289: Epoch 522 +2025-11-01 21:38:17.415059: Current learning rate: 0.00515 +2025-11-01 21:47:39.092792: train_loss -0.4416 +2025-11-01 21:47:39.170818: val_loss -0.4412 +2025-11-01 21:47:39.190618: Pseudo dice [np.float32(0.9293), np.float32(0.731), np.float32(0.7267), np.float32(0.6085), np.float32(0.8698), np.float32(0.7536), np.float32(0.8752), np.float32(0.8888), np.float32(0.9672), np.float32(0.9669), np.float32(0.9637), np.float32(0.8297), np.float32(0.7744), np.float32(0.864), np.float32(0.9332), np.float32(0.3712), np.float32(0.3167)] +2025-11-01 21:47:39.193880: Epoch time: 561.71 s +2025-11-01 21:47:39.198172: Yayy! New best EMA pseudo Dice: 0.7857999801635742 +2025-11-01 21:47:44.673421: +2025-11-01 21:47:44.676323: Epoch 523 +2025-11-01 21:47:44.678712: Current learning rate: 0.00514 +2025-11-01 21:57:05.499015: train_loss -0.4253 +2025-11-01 21:57:05.535239: val_loss -0.4576 +2025-11-01 21:57:05.537878: Pseudo dice [np.float32(0.9134), np.float32(0.7468), np.float32(0.7047), np.float32(0.6059), np.float32(0.8769), np.float32(0.7726), np.float32(0.8599), np.float32(0.8803), np.float32(0.9792), np.float32(0.9802), np.float32(0.9631), np.float32(0.853), np.float32(0.7798), np.float32(0.8658), np.float32(0.9388), np.float32(0.3834), np.float32(0.2322)] +2025-11-01 21:57:05.539785: Epoch time: 560.83 s +2025-11-01 21:57:26.038950: +2025-11-01 21:57:26.040321: Epoch 524 +2025-11-01 21:57:26.041866: Current learning rate: 0.00513 +2025-11-01 22:06:34.267383: train_loss -0.4641 +2025-11-01 22:06:34.290842: val_loss -0.4362 +2025-11-01 22:06:34.294513: Pseudo dice [np.float32(0.9339), np.float32(0.8092), np.float32(0.7518), np.float32(0.549), np.float32(0.8527), np.float32(0.8028), np.float32(0.892), np.float32(0.8981), np.float32(0.9439), np.float32(0.9602), np.float32(0.9674), np.float32(0.8552), np.float32(0.8205), np.float32(0.8415), np.float32(0.9577), np.float32(0.4601), np.float32(0.3541)] +2025-11-01 22:06:34.298683: Epoch time: 548.23 s +2025-11-01 22:06:34.301112: Yayy! New best EMA pseudo Dice: 0.7874000072479248 +2025-11-01 22:06:38.949158: +2025-11-01 22:06:38.952065: Epoch 525 +2025-11-01 22:06:38.969999: Current learning rate: 0.00512 +2025-11-01 22:16:15.602573: train_loss -0.4427 +2025-11-01 22:16:15.622117: val_loss -0.4515 +2025-11-01 22:16:15.625603: Pseudo dice [np.float32(0.9234), np.float32(0.7776), np.float32(0.7688), np.float32(0.6316), np.float32(0.8638), np.float32(0.7811), np.float32(0.8489), np.float32(0.869), np.float32(0.9752), np.float32(0.9699), np.float32(0.9691), np.float32(0.8485), np.float32(0.7911), np.float32(0.8754), np.float32(0.9714), np.float32(0.3819), np.float32(0.3795)] +2025-11-01 22:16:15.627234: Epoch time: 576.66 s +2025-11-01 22:16:15.629767: Yayy! New best EMA pseudo Dice: 0.7888000011444092 +2025-11-01 22:16:20.158285: +2025-11-01 22:16:20.162432: Epoch 526 +2025-11-01 22:16:20.164512: Current learning rate: 0.00511 +2025-11-01 22:25:35.862791: train_loss -0.4532 +2025-11-01 22:25:35.883275: val_loss -0.4502 +2025-11-01 22:25:35.891191: Pseudo dice [np.float32(0.9382), np.float32(0.7387), np.float32(0.7335), np.float32(0.6671), np.float32(0.8485), np.float32(0.8096), np.float32(0.8957), np.float32(0.8821), np.float32(0.9834), np.float32(0.9803), np.float32(0.9692), np.float32(0.8303), np.float32(0.8032), np.float32(0.8612), np.float32(0.9604), np.float32(0.2341), np.float32(0.1732)] +2025-11-01 22:25:35.893486: Epoch time: 555.71 s +2025-11-01 22:25:37.903715: +2025-11-01 22:25:37.909062: Epoch 527 +2025-11-01 22:25:37.911943: Current learning rate: 0.0051 +2025-11-01 22:35:22.182377: train_loss -0.4177 +2025-11-01 22:35:22.332158: val_loss -0.3925 +2025-11-01 22:35:22.341763: Pseudo dice [np.float32(0.9223), np.float32(0.7644), np.float32(0.7196), np.float32(0.6853), np.float32(0.8564), np.float32(0.8179), np.float32(0.8702), np.float32(0.8574), np.float32(0.968), np.float32(0.9697), np.float32(0.9661), np.float32(0.8536), np.float32(0.7538), np.float32(0.8583), np.float32(0.9546), np.float32(0.268), np.float32(0.287)] +2025-11-01 22:35:22.349298: Epoch time: 584.29 s +2025-11-01 22:35:24.730425: +2025-11-01 22:35:24.732864: Epoch 528 +2025-11-01 22:35:24.734382: Current learning rate: 0.00509 +2025-11-01 22:44:47.424085: train_loss -0.4428 +2025-11-01 22:44:47.450089: val_loss -0.4876 +2025-11-01 22:44:47.459464: Pseudo dice [np.float32(0.9441), np.float32(0.8211), np.float32(0.724), np.float32(0.6017), np.float32(0.8282), np.float32(0.7978), np.float32(0.89), np.float32(0.8834), np.float32(0.9829), np.float32(0.9815), np.float32(0.9702), np.float32(0.8543), np.float32(0.8171), np.float32(0.8554), np.float32(0.9645), np.float32(0.2846), np.float32(0.2834)] +2025-11-01 22:44:47.463194: Epoch time: 562.7 s +2025-11-01 22:44:49.636598: +2025-11-01 22:44:49.638595: Epoch 529 +2025-11-01 22:44:49.641952: Current learning rate: 0.00508 +2025-11-01 22:54:14.322388: train_loss -0.4591 +2025-11-01 22:54:14.415807: val_loss -0.4478 +2025-11-01 22:54:14.418351: Pseudo dice [np.float32(0.9278), np.float32(0.7731), np.float32(0.7052), np.float32(0.6938), np.float32(0.8464), np.float32(0.8088), np.float32(0.8353), np.float32(0.8835), np.float32(0.9721), np.float32(0.9698), np.float32(0.9669), np.float32(0.8295), np.float32(0.7878), np.float32(0.8802), np.float32(0.9414), np.float32(0.201), np.float32(0.3366)] +2025-11-01 22:54:14.421212: Epoch time: 564.69 s +2025-11-01 22:54:16.633087: +2025-11-01 22:54:16.637664: Epoch 530 +2025-11-01 22:54:16.642869: Current learning rate: 0.00507 +2025-11-01 23:03:37.063714: train_loss -0.4543 +2025-11-01 23:03:37.108286: val_loss -0.4682 +2025-11-01 23:03:37.110287: Pseudo dice [np.float32(0.9368), np.float32(0.7623), np.float32(0.7289), np.float32(0.6263), np.float32(0.8837), np.float32(0.8082), np.float32(0.8875), np.float32(0.891), np.float32(0.9798), np.float32(0.9763), np.float32(0.9666), np.float32(0.8573), np.float32(0.7769), np.float32(0.8695), np.float32(0.9589), np.float32(0.3095), np.float32(0.248)] +2025-11-01 23:03:37.112355: Epoch time: 560.43 s +2025-11-01 23:03:39.772147: +2025-11-01 23:03:39.778847: Epoch 531 +2025-11-01 23:03:39.786468: Current learning rate: 0.00506 +2025-11-01 23:12:57.238712: train_loss -0.4327 +2025-11-01 23:12:57.343272: val_loss -0.441 +2025-11-01 23:12:57.346377: Pseudo dice [np.float32(0.9201), np.float32(0.7647), np.float32(0.714), np.float32(0.6622), np.float32(0.8614), np.float32(0.8208), np.float32(0.905), np.float32(0.8918), np.float32(0.9765), np.float32(0.9776), np.float32(0.959), np.float32(0.8407), np.float32(0.7708), np.float32(0.8472), np.float32(0.9473), np.float32(0.3521), np.float32(0.2934)] +2025-11-01 23:12:57.394819: Epoch time: 557.47 s +2025-11-01 23:12:57.409239: Yayy! New best EMA pseudo Dice: 0.7893000245094299 +2025-11-01 23:13:04.710617: +2025-11-01 23:13:04.713993: Epoch 532 +2025-11-01 23:13:04.725499: Current learning rate: 0.00505 +2025-11-01 23:22:23.393120: train_loss -0.437 +2025-11-01 23:22:23.409894: val_loss -0.431 +2025-11-01 23:22:23.417573: Pseudo dice [np.float32(0.9339), np.float32(0.7433), np.float32(0.6236), np.float32(0.6081), np.float32(0.8729), np.float32(0.794), np.float32(0.8487), np.float32(0.8864), np.float32(0.9819), np.float32(0.9796), np.float32(0.9639), np.float32(0.8396), np.float32(0.7621), np.float32(0.8619), np.float32(0.9589), np.float32(0.4122), np.float32(0.312)] +2025-11-01 23:22:23.421543: Epoch time: 558.69 s +2025-11-01 23:22:25.553932: +2025-11-01 23:22:25.561370: Epoch 533 +2025-11-01 23:22:25.566213: Current learning rate: 0.00504 +2025-11-01 23:31:37.280859: train_loss -0.4467 +2025-11-01 23:31:37.302729: val_loss -0.4581 +2025-11-01 23:31:37.305397: Pseudo dice [np.float32(0.928), np.float32(0.778), np.float32(0.7478), np.float32(0.6464), np.float32(0.8789), np.float32(0.8156), np.float32(0.8949), np.float32(0.8839), np.float32(0.978), np.float32(0.9806), np.float32(0.9659), np.float32(0.868), np.float32(0.7946), np.float32(0.8736), np.float32(0.9653), np.float32(0.421), np.float32(0.3821)] +2025-11-01 23:31:37.317415: Epoch time: 551.74 s +2025-11-01 23:31:37.321305: Yayy! New best EMA pseudo Dice: 0.7914000153541565 +2025-11-01 23:31:43.667024: +2025-11-01 23:31:43.674224: Epoch 534 +2025-11-01 23:31:43.690555: Current learning rate: 0.00503 +2025-11-01 23:41:06.175214: train_loss -0.4554 +2025-11-01 23:41:06.205465: val_loss -0.4549 +2025-11-01 23:41:06.211600: Pseudo dice [np.float32(0.9327), np.float32(0.7623), np.float32(0.6895), np.float32(0.6514), np.float32(0.8674), np.float32(0.8068), np.float32(0.8992), np.float32(0.8722), np.float32(0.9804), np.float32(0.9757), np.float32(0.9612), np.float32(0.8502), np.float32(0.7908), np.float32(0.8615), np.float32(0.9587), np.float32(0.2115), np.float32(0.3076)] +2025-11-01 23:41:06.214515: Epoch time: 562.51 s +2025-11-01 23:41:08.203341: +2025-11-01 23:41:08.211091: Epoch 535 +2025-11-01 23:41:08.213740: Current learning rate: 0.00502 +2025-11-01 23:50:36.211879: train_loss -0.4021 +2025-11-01 23:50:36.226627: val_loss -0.4269 +2025-11-01 23:50:36.232935: Pseudo dice [np.float32(0.9208), np.float32(0.5671), np.float32(0.7307), np.float32(0.6457), np.float32(0.8654), np.float32(0.7609), np.float32(0.8084), np.float32(0.874), np.float32(0.9759), np.float32(0.97), np.float32(0.9518), np.float32(0.8029), np.float32(0.7822), np.float32(0.8498), np.float32(0.9511), np.float32(0.2487), np.float32(0.3233)] +2025-11-01 23:50:36.236990: Epoch time: 568.01 s +2025-11-01 23:50:38.404059: +2025-11-01 23:50:38.408271: Epoch 536 +2025-11-01 23:50:38.416021: Current learning rate: 0.00501 +2025-11-02 00:01:11.767671: train_loss -0.4073 +2025-11-02 00:01:11.794837: val_loss -0.4468 +2025-11-02 00:01:11.797276: Pseudo dice [np.float32(0.9284), np.float32(0.743), np.float32(0.6991), np.float32(0.5931), np.float32(0.8566), np.float32(0.7809), np.float32(0.8716), np.float32(0.8724), np.float32(0.9361), np.float32(0.9448), np.float32(0.9561), np.float32(0.84), np.float32(0.7608), np.float32(0.8642), np.float32(0.9441), np.float32(0.2206), np.float32(0.2486)] +2025-11-02 00:01:11.811048: Epoch time: 633.37 s +2025-11-02 00:01:14.550864: +2025-11-02 00:01:14.556320: Epoch 537 +2025-11-02 00:01:14.559138: Current learning rate: 0.005 +2025-11-02 00:10:33.196940: train_loss -0.4005 +2025-11-02 00:10:33.220793: val_loss -0.3989 +2025-11-02 00:10:33.229471: Pseudo dice [np.float32(0.9274), np.float32(0.7166), np.float32(0.6787), np.float32(0.6651), np.float32(0.8331), np.float32(0.7923), np.float32(0.7954), np.float32(0.855), np.float32(0.9297), np.float32(0.9162), np.float32(0.9481), np.float32(0.831), np.float32(0.7716), np.float32(0.8634), np.float32(0.9229), np.float32(0.2683), np.float32(0.2085)] +2025-11-02 00:10:33.235111: Epoch time: 558.65 s +2025-11-02 00:10:35.430989: +2025-11-02 00:10:35.435327: Epoch 538 +2025-11-02 00:10:35.438918: Current learning rate: 0.00499 +2025-11-02 00:19:55.375846: train_loss -0.3985 +2025-11-02 00:19:55.395489: val_loss -0.3599 +2025-11-02 00:19:55.399233: Pseudo dice [np.float32(0.8717), np.float32(0.763), np.float32(0.728), np.float32(0.601), np.float32(0.859), np.float32(0.7595), np.float32(0.7417), np.float32(0.8691), np.float32(0.9745), np.float32(0.968), np.float32(0.9608), np.float32(0.7965), np.float32(0.7429), np.float32(0.868), np.float32(0.9616), np.float32(0.2736), np.float32(0.2907)] +2025-11-02 00:19:55.403156: Epoch time: 559.95 s +2025-11-02 00:19:57.799197: +2025-11-02 00:19:57.804718: Epoch 539 +2025-11-02 00:19:57.806668: Current learning rate: 0.00498 +2025-11-02 00:29:07.983256: train_loss -0.4166 +2025-11-02 00:29:08.071805: val_loss -0.4067 +2025-11-02 00:29:08.074162: Pseudo dice [np.float32(0.9272), np.float32(0.6783), np.float32(0.6665), np.float32(0.6434), np.float32(0.8493), np.float32(0.7585), np.float32(0.7165), np.float32(0.8675), np.float32(0.9686), np.float32(0.9548), np.float32(0.9598), np.float32(0.8172), np.float32(0.7753), np.float32(0.834), np.float32(0.951), np.float32(0.2585), np.float32(0.3845)] +2025-11-02 00:29:08.078323: Epoch time: 550.19 s +2025-11-02 00:29:10.065298: +2025-11-02 00:29:10.074859: Epoch 540 +2025-11-02 00:29:10.079674: Current learning rate: 0.00497 +2025-11-02 00:38:09.942402: train_loss -0.4203 +2025-11-02 00:38:09.958334: val_loss -0.4772 +2025-11-02 00:38:09.960358: Pseudo dice [np.float32(0.9317), np.float32(0.7687), np.float32(0.7228), np.float32(0.6539), np.float32(0.8854), np.float32(0.7674), np.float32(0.8929), np.float32(0.8814), np.float32(0.9774), np.float32(0.9728), np.float32(0.9609), np.float32(0.8455), np.float32(0.7771), np.float32(0.8715), np.float32(0.9697), np.float32(0.371), np.float32(0.4167)] +2025-11-02 00:38:09.962162: Epoch time: 539.88 s +2025-11-02 00:38:12.326777: +2025-11-02 00:38:12.328498: Epoch 541 +2025-11-02 00:38:12.335527: Current learning rate: 0.00496 +2025-11-02 00:47:13.300838: train_loss -0.4382 +2025-11-02 00:47:14.022502: val_loss -0.4281 +2025-11-02 00:47:14.025615: Pseudo dice [np.float32(0.9024), np.float32(0.7368), np.float32(0.7028), np.float32(0.66), np.float32(0.8554), np.float32(0.765), np.float32(0.8915), np.float32(0.8778), np.float32(0.966), np.float32(0.9685), np.float32(0.9655), np.float32(0.849), np.float32(0.7809), np.float32(0.8613), np.float32(0.9633), np.float32(0.317), np.float32(0.3464)] +2025-11-02 00:47:14.028267: Epoch time: 540.98 s +2025-11-02 00:47:17.694686: +2025-11-02 00:47:17.697819: Epoch 542 +2025-11-02 00:47:17.699861: Current learning rate: 0.00495 +2025-11-02 00:56:28.263806: train_loss -0.4357 +2025-11-02 00:56:28.564713: val_loss -0.48 +2025-11-02 00:56:28.567057: Pseudo dice [np.float32(0.9248), np.float32(0.7574), np.float32(0.6854), np.float32(0.559), np.float32(0.8673), np.float32(0.7862), np.float32(0.8604), np.float32(0.869), np.float32(0.9438), np.float32(0.9656), np.float32(0.9682), np.float32(0.8269), np.float32(0.7821), np.float32(0.8625), np.float32(0.9577), np.float32(0.3439), np.float32(0.3597)] +2025-11-02 00:56:28.578152: Epoch time: 550.57 s +2025-11-02 00:56:32.901675: +2025-11-02 00:56:32.904807: Epoch 543 +2025-11-02 00:56:32.906817: Current learning rate: 0.00494 +2025-11-02 01:05:45.754364: train_loss -0.446 +2025-11-02 01:05:46.174419: val_loss -0.4308 +2025-11-02 01:05:46.176250: Pseudo dice [np.float32(0.9276), np.float32(0.7304), np.float32(0.7136), np.float32(0.7245), np.float32(0.8503), np.float32(0.82), np.float32(0.8853), np.float32(0.8865), np.float32(0.937), np.float32(0.9524), np.float32(0.966), np.float32(0.8382), np.float32(0.7757), np.float32(0.8717), np.float32(0.9456), np.float32(0.2534), np.float32(0.3023)] +2025-11-02 01:05:46.240016: Epoch time: 552.86 s +2025-11-02 01:05:48.545778: +2025-11-02 01:05:48.549039: Epoch 544 +2025-11-02 01:05:48.554573: Current learning rate: 0.00493 +2025-11-02 01:14:49.815794: train_loss -0.4385 +2025-11-02 01:14:49.820530: val_loss -0.4251 +2025-11-02 01:14:49.821975: Pseudo dice [np.float32(0.9148), np.float32(0.7544), np.float32(0.7106), np.float32(0.6524), np.float32(0.8527), np.float32(0.7136), np.float32(0.8146), np.float32(0.8783), np.float32(0.9757), np.float32(0.9748), np.float32(0.9591), np.float32(0.8543), np.float32(0.734), np.float32(0.8654), np.float32(0.9632), np.float32(0.3128), np.float32(0.1271)] +2025-11-02 01:14:49.823628: Epoch time: 541.27 s +2025-11-02 01:14:52.359137: +2025-11-02 01:14:52.360946: Epoch 545 +2025-11-02 01:14:52.362912: Current learning rate: 0.00492 +2025-11-02 01:23:18.136568: train_loss -0.4445 +2025-11-02 01:23:18.143818: val_loss -0.429 +2025-11-02 01:23:18.146425: Pseudo dice [np.float32(0.9191), np.float32(0.394), np.float32(0.7099), np.float32(0.6549), np.float32(0.8572), np.float32(0.7885), np.float32(0.888), np.float32(0.8729), np.float32(0.98), np.float32(0.9662), np.float32(0.952), np.float32(0.8604), np.float32(0.7854), np.float32(0.8822), np.float32(0.947), np.float32(0.416), np.float32(0.3107)] +2025-11-02 01:23:18.148359: Epoch time: 505.78 s +2025-11-02 01:23:21.560245: +2025-11-02 01:23:21.562039: Epoch 546 +2025-11-02 01:23:21.563492: Current learning rate: 0.00491 +2025-11-02 01:32:08.012352: train_loss -0.445 +2025-11-02 01:32:08.072746: val_loss -0.4247 +2025-11-02 01:32:08.074535: Pseudo dice [np.float32(0.9237), np.float32(0.7449), np.float32(0.6999), np.float32(0.5794), np.float32(0.8667), np.float32(0.7757), np.float32(0.8756), np.float32(0.8756), np.float32(0.9547), np.float32(0.9486), np.float32(0.9591), np.float32(0.8258), np.float32(0.7881), np.float32(0.8813), np.float32(0.9494), np.float32(0.2655), np.float32(0.116)] +2025-11-02 01:32:08.076136: Epoch time: 526.46 s +2025-11-02 01:32:26.206073: +2025-11-02 01:32:26.207517: Epoch 547 +2025-11-02 01:32:26.208836: Current learning rate: 0.0049 +2025-11-02 01:40:58.606154: train_loss -0.4491 +2025-11-02 01:40:58.617357: val_loss -0.4244 +2025-11-02 01:40:58.619083: Pseudo dice [np.float32(0.9096), np.float32(0.7936), np.float32(0.7263), np.float32(0.6345), np.float32(0.8667), np.float32(0.7786), np.float32(0.822), np.float32(0.8786), np.float32(0.965), np.float32(0.9701), np.float32(0.9625), np.float32(0.8138), np.float32(0.755), np.float32(0.8747), np.float32(0.9398), np.float32(0.3404), np.float32(0.2536)] +2025-11-02 01:40:58.621390: Epoch time: 512.4 s +2025-11-02 01:41:00.615561: +2025-11-02 01:41:00.617651: Epoch 548 +2025-11-02 01:41:00.619109: Current learning rate: 0.00489 +2025-11-02 01:49:54.543414: train_loss -0.4454 +2025-11-02 01:49:54.548401: val_loss -0.4657 +2025-11-02 01:49:54.549612: Pseudo dice [np.float32(0.9337), np.float32(0.7105), np.float32(0.6628), np.float32(0.6749), np.float32(0.85), np.float32(0.8006), np.float32(0.8651), np.float32(0.8716), np.float32(0.9794), np.float32(0.978), np.float32(0.9613), np.float32(0.8268), np.float32(0.7739), np.float32(0.8642), np.float32(0.9592), np.float32(0.272), np.float32(0.2399)] +2025-11-02 01:49:54.550795: Epoch time: 533.93 s +2025-11-02 01:49:56.468441: +2025-11-02 01:49:56.470373: Epoch 549 +2025-11-02 01:49:56.471768: Current learning rate: 0.00488 +2025-11-02 01:58:41.024766: train_loss -0.4219 +2025-11-02 01:58:41.030193: val_loss -0.4659 +2025-11-02 01:58:41.032747: Pseudo dice [np.float32(0.9153), np.float32(0.7627), np.float32(0.7365), np.float32(0.6534), np.float32(0.8675), np.float32(0.7804), np.float32(0.8553), np.float32(0.8904), np.float32(0.9767), np.float32(0.9768), np.float32(0.962), np.float32(0.8263), np.float32(0.795), np.float32(0.8522), np.float32(0.9669), np.float32(0.2998), np.float32(0.202)] +2025-11-02 01:58:41.033924: Epoch time: 524.56 s +2025-11-02 01:58:45.913217: +2025-11-02 01:58:45.914915: Epoch 550 +2025-11-02 01:58:45.916521: Current learning rate: 0.00487 +2025-11-02 01:07:20.952783: train_loss -0.4373 +2025-11-02 01:07:20.959719: val_loss -0.4488 +2025-11-02 01:07:20.961324: Pseudo dice [np.float32(0.9239), np.float32(0.7729), np.float32(0.7518), np.float32(0.6547), np.float32(0.8389), np.float32(0.7917), np.float32(0.8987), np.float32(0.8637), np.float32(0.9737), np.float32(0.9694), np.float32(0.9649), np.float32(0.8294), np.float32(0.7661), np.float32(0.8431), np.float32(0.961), np.float32(0.2112), np.float32(0.2317)] +2025-11-02 01:07:20.963103: Epoch time: 515.04 s +2025-11-02 01:07:23.030753: +2025-11-02 01:07:23.032352: Epoch 551 +2025-11-02 01:07:23.034158: Current learning rate: 0.00486 +2025-11-02 01:16:06.019926: train_loss -0.4572 +2025-11-02 01:16:06.025843: val_loss -0.4732 +2025-11-02 01:16:06.027220: Pseudo dice [np.float32(0.941), np.float32(0.7385), np.float32(0.7004), np.float32(0.6796), np.float32(0.8573), np.float32(0.8112), np.float32(0.8661), np.float32(0.8985), np.float32(0.9816), np.float32(0.9806), np.float32(0.967), np.float32(0.8625), np.float32(0.7736), np.float32(0.8584), np.float32(0.9625), np.float32(0.4137), np.float32(0.2799)] +2025-11-02 01:16:06.028888: Epoch time: 523.0 s +2025-11-02 01:16:07.977027: +2025-11-02 01:16:07.979190: Epoch 552 +2025-11-02 01:16:07.980944: Current learning rate: 0.00485 +2025-11-02 01:24:44.728050: train_loss -0.4047 +2025-11-02 01:24:44.732488: val_loss -0.3944 +2025-11-02 01:24:44.733979: Pseudo dice [np.float32(0.9077), np.float32(0.7646), np.float32(0.7046), np.float32(0.645), np.float32(0.8497), np.float32(0.8007), np.float32(0.8786), np.float32(0.8677), np.float32(0.9603), np.float32(0.9706), np.float32(0.9537), np.float32(0.8457), np.float32(0.7459), np.float32(0.8673), np.float32(0.9474), np.float32(0.3435), np.float32(0.3393)] +2025-11-02 01:24:44.735254: Epoch time: 516.76 s +2025-11-02 01:24:46.805419: +2025-11-02 01:24:46.808082: Epoch 553 +2025-11-02 01:24:46.810062: Current learning rate: 0.00484 +2025-11-02 01:33:16.181723: train_loss -0.4395 +2025-11-02 01:33:16.187468: val_loss -0.4028 +2025-11-02 01:33:16.189003: Pseudo dice [np.float32(0.9104), np.float32(0.7154), np.float32(0.6334), np.float32(0.5976), np.float32(0.8594), np.float32(0.7658), np.float32(0.898), np.float32(0.8746), np.float32(0.9529), np.float32(0.965), np.float32(0.9656), np.float32(0.8489), np.float32(0.7578), np.float32(0.8609), np.float32(0.8933), np.float32(0.292), np.float32(0.3304)] +2025-11-02 01:33:16.190458: Epoch time: 509.38 s +2025-11-02 01:33:18.421656: +2025-11-02 01:33:18.422997: Epoch 554 +2025-11-02 01:33:18.424402: Current learning rate: 0.00484 +2025-11-02 01:42:01.880487: train_loss -0.4207 +2025-11-02 01:42:01.895775: val_loss -0.4407 +2025-11-02 01:42:01.899543: Pseudo dice [np.float32(0.9165), np.float32(0.7598), np.float32(0.72), np.float32(0.6771), np.float32(0.8531), np.float32(0.7789), np.float32(0.8195), np.float32(0.88), np.float32(0.9636), np.float32(0.9626), np.float32(0.9443), np.float32(0.8643), np.float32(0.7888), np.float32(0.8541), np.float32(0.9382), np.float32(0.3422), np.float32(0.3115)] +2025-11-02 01:42:01.900887: Epoch time: 523.46 s +2025-11-02 01:42:04.067256: +2025-11-02 01:42:04.068959: Epoch 555 +2025-11-02 01:42:04.070934: Current learning rate: 0.00483 +2025-11-02 01:50:35.055678: train_loss -0.4227 +2025-11-02 01:50:35.075066: val_loss -0.4457 +2025-11-02 01:50:35.077226: Pseudo dice [np.float32(0.9284), np.float32(0.7729), np.float32(0.7067), np.float32(0.662), np.float32(0.834), np.float32(0.7863), np.float32(0.867), np.float32(0.8915), np.float32(0.9666), np.float32(0.9724), np.float32(0.9648), np.float32(0.8516), np.float32(0.761), np.float32(0.8637), np.float32(0.9659), np.float32(0.3209), np.float32(0.2714)] +2025-11-02 01:50:35.087914: Epoch time: 510.99 s +2025-11-02 01:50:37.151055: +2025-11-02 01:50:37.152462: Epoch 556 +2025-11-02 01:50:37.154923: Current learning rate: 0.00482 +2025-11-02 01:59:16.020725: train_loss -0.4533 +2025-11-02 01:59:16.070017: val_loss -0.4432 +2025-11-02 01:59:16.073020: Pseudo dice [np.float32(0.929), np.float32(0.779), np.float32(0.7086), np.float32(0.5976), np.float32(0.8632), np.float32(0.7878), np.float32(0.8667), np.float32(0.8861), np.float32(0.98), np.float32(0.9791), np.float32(0.9658), np.float32(0.8392), np.float32(0.7855), np.float32(0.856), np.float32(0.9677), np.float32(0.3165), np.float32(0.3184)] +2025-11-02 01:59:16.074455: Epoch time: 518.88 s +2025-11-02 01:59:18.322662: +2025-11-02 01:59:18.324157: Epoch 557 +2025-11-02 01:59:18.325221: Current learning rate: 0.00481 +2025-11-02 02:08:02.608484: train_loss -0.4422 +2025-11-02 02:08:02.621231: val_loss -0.4586 +2025-11-02 02:08:02.626100: Pseudo dice [np.float32(0.9083), np.float32(0.7847), np.float32(0.7128), np.float32(0.6093), np.float32(0.8769), np.float32(0.8031), np.float32(0.909), np.float32(0.879), np.float32(0.9146), np.float32(0.9417), np.float32(0.9703), np.float32(0.8364), np.float32(0.7977), np.float32(0.847), np.float32(0.9593), np.float32(0.4555), np.float32(0.485)] +2025-11-02 02:08:02.641684: Epoch time: 524.29 s +2025-11-02 02:08:04.663796: +2025-11-02 02:08:04.665112: Epoch 558 +2025-11-02 02:08:04.666434: Current learning rate: 0.0048 +2025-11-02 02:16:57.702827: train_loss -0.4218 +2025-11-02 02:16:57.711098: val_loss -0.4433 +2025-11-02 02:16:57.715850: Pseudo dice [np.float32(0.92), np.float32(0.7816), np.float32(0.7298), np.float32(0.586), np.float32(0.8405), np.float32(0.7909), np.float32(0.8926), np.float32(0.877), np.float32(0.9654), np.float32(0.9599), np.float32(0.9648), np.float32(0.8544), np.float32(0.7867), np.float32(0.8604), np.float32(0.962), np.float32(0.4258), np.float32(0.3415)] +2025-11-02 02:16:57.717269: Epoch time: 533.04 s +2025-11-02 02:16:59.577361: +2025-11-02 02:16:59.578732: Epoch 559 +2025-11-02 02:16:59.585687: Current learning rate: 0.00479 +2025-11-02 02:25:26.994436: train_loss -0.4541 +2025-11-02 02:25:27.000316: val_loss -0.4727 +2025-11-02 02:25:27.001621: Pseudo dice [np.float32(0.9376), np.float32(0.7945), np.float32(0.7057), np.float32(0.7164), np.float32(0.8572), np.float32(0.7695), np.float32(0.8758), np.float32(0.8758), np.float32(0.9703), np.float32(0.9717), np.float32(0.9623), np.float32(0.8179), np.float32(0.7877), np.float32(0.8934), np.float32(0.9427), np.float32(0.2954), np.float32(0.3028)] +2025-11-02 02:25:27.002900: Epoch time: 507.42 s +2025-11-02 02:25:29.013413: +2025-11-02 02:25:29.029706: Epoch 560 +2025-11-02 02:25:29.035226: Current learning rate: 0.00478 +2025-11-02 02:34:08.988257: train_loss -0.4334 +2025-11-02 02:34:08.999092: val_loss -0.453 +2025-11-02 02:34:09.000591: Pseudo dice [np.float32(0.944), np.float32(0.7519), np.float32(0.7255), np.float32(0.6576), np.float32(0.86), np.float32(0.7509), np.float32(0.8254), np.float32(0.87), np.float32(0.9633), np.float32(0.9625), np.float32(0.9666), np.float32(0.834), np.float32(0.7988), np.float32(0.8666), np.float32(0.9631), np.float32(0.416), np.float32(0.3639)] +2025-11-02 02:34:09.002609: Epoch time: 519.98 s +2025-11-02 02:34:10.923102: +2025-11-02 02:34:10.924704: Epoch 561 +2025-11-02 02:34:10.926135: Current learning rate: 0.00477 +2025-11-02 02:43:32.759191: train_loss -0.4659 +2025-11-02 02:43:32.777021: val_loss -0.4686 +2025-11-02 02:43:32.779162: Pseudo dice [np.float32(0.9098), np.float32(0.7923), np.float32(0.6758), np.float32(0.6326), np.float32(0.8553), np.float32(0.76), np.float32(0.9021), np.float32(0.8792), np.float32(0.9787), np.float32(0.977), np.float32(0.9594), np.float32(0.8337), np.float32(0.7935), np.float32(0.8585), np.float32(0.965), np.float32(0.2637), np.float32(0.3662)] +2025-11-02 02:43:32.783949: Epoch time: 561.84 s +2025-11-02 02:43:34.839825: +2025-11-02 02:43:34.842054: Epoch 562 +2025-11-02 02:43:34.843308: Current learning rate: 0.00476 +2025-11-02 02:55:32.527332: train_loss -0.4477 +2025-11-02 02:55:32.582533: val_loss -0.4466 +2025-11-02 02:55:32.585105: Pseudo dice [np.float32(0.9193), np.float32(0.7517), np.float32(0.6884), np.float32(0.7263), np.float32(0.8318), np.float32(0.7976), np.float32(0.8951), np.float32(0.8698), np.float32(0.9791), np.float32(0.953), np.float32(0.9681), np.float32(0.861), np.float32(0.7824), np.float32(0.8672), np.float32(0.9577), np.float32(0.4939), np.float32(0.2368)] +2025-11-02 02:55:32.587108: Epoch time: 717.69 s +2025-11-02 02:55:34.537767: +2025-11-02 02:55:34.550132: Epoch 563 +2025-11-02 02:55:34.551826: Current learning rate: 0.00475 +2025-11-02 03:07:43.045626: train_loss -0.4501 +2025-11-02 03:07:43.174829: val_loss -0.416 +2025-11-02 03:07:43.176356: Pseudo dice [np.float32(0.9207), np.float32(0.749), np.float32(0.7008), np.float32(0.6703), np.float32(0.8578), np.float32(0.7839), np.float32(0.8903), np.float32(0.8674), np.float32(0.9745), np.float32(0.9325), np.float32(0.9609), np.float32(0.8412), np.float32(0.7825), np.float32(0.8584), np.float32(0.9498), np.float32(0.2764), np.float32(0.1698)] +2025-11-02 03:07:43.183348: Epoch time: 728.51 s +2025-11-02 03:07:45.178099: +2025-11-02 03:07:45.184061: Epoch 564 +2025-11-02 03:07:45.186435: Current learning rate: 0.00474 +2025-11-02 03:19:47.087045: train_loss -0.456 +2025-11-02 03:19:47.216523: val_loss -0.4603 +2025-11-02 03:19:47.223364: Pseudo dice [np.float32(0.9388), np.float32(0.7436), np.float32(0.7244), np.float32(0.6804), np.float32(0.8742), np.float32(0.7832), np.float32(0.8616), np.float32(0.8793), np.float32(0.9644), np.float32(0.9561), np.float32(0.9663), np.float32(0.8384), np.float32(0.7821), np.float32(0.8797), np.float32(0.9678), np.float32(0.3172), np.float32(0.2327)] +2025-11-02 03:19:47.230644: Epoch time: 721.92 s +2025-11-02 03:19:49.731356: +2025-11-02 03:19:49.738912: Epoch 565 +2025-11-02 03:19:49.740657: Current learning rate: 0.00473 +2025-11-02 03:32:10.615391: train_loss -0.4413 +2025-11-02 03:32:10.648404: val_loss -0.441 +2025-11-02 03:32:10.660008: Pseudo dice [np.float32(0.9333), np.float32(0.7361), np.float32(0.7263), np.float32(0.6544), np.float32(0.8735), np.float32(0.7948), np.float32(0.8893), np.float32(0.8781), np.float32(0.939), np.float32(0.9189), np.float32(0.9629), np.float32(0.8525), np.float32(0.7759), np.float32(0.8729), np.float32(0.9319), np.float32(0.2823), np.float32(0.2432)] +2025-11-02 03:32:10.661874: Epoch time: 740.89 s +2025-11-02 03:32:12.875391: +2025-11-02 03:32:12.879898: Epoch 566 +2025-11-02 03:32:12.884590: Current learning rate: 0.00472 +2025-11-02 03:44:30.061948: train_loss -0.4331 +2025-11-02 03:44:30.074775: val_loss -0.4226 +2025-11-02 03:44:30.076370: Pseudo dice [np.float32(0.9238), np.float32(0.7718), np.float32(0.7139), np.float32(0.6356), np.float32(0.8445), np.float32(0.788), np.float32(0.873), np.float32(0.8694), np.float32(0.9622), np.float32(0.9719), np.float32(0.9637), np.float32(0.8279), np.float32(0.76), np.float32(0.8614), np.float32(0.9592), np.float32(0.341), np.float32(0.1458)] +2025-11-02 03:44:30.082086: Epoch time: 737.2 s +2025-11-02 03:44:32.322603: +2025-11-02 03:44:32.329711: Epoch 567 +2025-11-02 03:44:32.342107: Current learning rate: 0.00471 +2025-11-02 03:56:38.412412: train_loss -0.4563 +2025-11-02 03:56:38.426635: val_loss -0.4687 +2025-11-02 03:56:38.427835: Pseudo dice [np.float32(0.929), np.float32(0.7355), np.float32(0.7159), np.float32(0.6619), np.float32(0.8748), np.float32(0.7763), np.float32(0.8746), np.float32(0.8919), np.float32(0.9739), np.float32(0.9682), np.float32(0.962), np.float32(0.8408), np.float32(0.7668), np.float32(0.8651), np.float32(0.9665), np.float32(0.3952), np.float32(0.3467)] +2025-11-02 03:56:38.429833: Epoch time: 726.09 s +2025-11-02 03:56:41.719767: +2025-11-02 03:56:41.747274: Epoch 568 +2025-11-02 03:56:41.749248: Current learning rate: 0.0047 +2025-11-02 04:08:57.955122: train_loss -0.4304 +2025-11-02 04:08:57.973599: val_loss -0.4483 +2025-11-02 04:08:57.980843: Pseudo dice [np.float32(0.9282), np.float32(0.7521), np.float32(0.677), np.float32(0.6413), np.float32(0.8568), np.float32(0.7813), np.float32(0.8469), np.float32(0.864), np.float32(0.9642), np.float32(0.9407), np.float32(0.9637), np.float32(0.8349), np.float32(0.7748), np.float32(0.8715), np.float32(0.9519), np.float32(0.2866), np.float32(0.3356)] +2025-11-02 04:08:57.983644: Epoch time: 736.24 s +2025-11-02 04:09:00.256020: +2025-11-02 04:09:00.265388: Epoch 569 +2025-11-02 04:09:00.279226: Current learning rate: 0.00469 +2025-11-02 04:21:06.113124: train_loss -0.4659 +2025-11-02 04:21:06.145838: val_loss -0.424 +2025-11-02 04:21:06.149734: Pseudo dice [np.float32(0.937), np.float32(0.7196), np.float32(0.6839), np.float32(0.6303), np.float32(0.8477), np.float32(0.7872), np.float32(0.8724), np.float32(0.8673), np.float32(0.9689), np.float32(0.9701), np.float32(0.9621), np.float32(0.8373), np.float32(0.7402), np.float32(0.8451), np.float32(0.9248), np.float32(0.4377), np.float32(0.3548)] +2025-11-02 04:21:06.156167: Epoch time: 725.86 s +2025-11-02 04:21:08.339872: +2025-11-02 04:21:08.347984: Epoch 570 +2025-11-02 04:21:08.353674: Current learning rate: 0.00468 +2025-11-02 04:33:06.490072: train_loss -0.4433 +2025-11-02 04:33:06.528029: val_loss -0.4495 +2025-11-02 04:33:06.530978: Pseudo dice [np.float32(0.9285), np.float32(0.802), np.float32(0.6744), np.float32(0.6567), np.float32(0.8605), np.float32(0.773), np.float32(0.8331), np.float32(0.8912), np.float32(0.9647), np.float32(0.9741), np.float32(0.9617), np.float32(0.8204), np.float32(0.7702), np.float32(0.8683), np.float32(0.9585), np.float32(0.3341), np.float32(0.2537)] +2025-11-02 04:33:06.539130: Epoch time: 718.16 s +2025-11-02 04:33:09.140499: +2025-11-02 04:33:09.150867: Epoch 571 +2025-11-02 04:33:09.153094: Current learning rate: 0.00467 +2025-11-02 04:43:42.543624: train_loss -0.405 +2025-11-02 04:43:42.559770: val_loss -0.4055 +2025-11-02 04:43:42.561535: Pseudo dice [np.float32(0.8966), np.float32(0.7536), np.float32(0.6972), np.float32(0.5903), np.float32(0.8556), np.float32(0.7596), np.float32(0.9), np.float32(0.8611), np.float32(0.9367), np.float32(0.9015), np.float32(0.9561), np.float32(0.8057), np.float32(0.7819), np.float32(0.8553), np.float32(0.9375), np.float32(0.2532), np.float32(0.2988)] +2025-11-02 04:43:42.563642: Epoch time: 633.41 s +2025-11-02 04:44:06.997254: +2025-11-02 04:44:06.998750: Epoch 572 +2025-11-02 04:44:07.000329: Current learning rate: 0.00466 +2025-11-02 04:52:39.501721: train_loss -0.4196 +2025-11-02 04:52:39.512401: val_loss -0.4326 +2025-11-02 04:52:39.514568: Pseudo dice [np.float32(0.9363), np.float32(0.2999), np.float32(0.6693), np.float32(0.6629), np.float32(0.8404), np.float32(0.7895), np.float32(0.88), np.float32(0.8802), np.float32(0.9548), np.float32(0.9779), np.float32(0.9597), np.float32(0.8195), np.float32(0.7909), np.float32(0.8648), np.float32(0.9343), np.float32(0.3058), np.float32(0.3115)] +2025-11-02 04:52:39.517127: Epoch time: 512.51 s +2025-11-02 04:52:41.471053: +2025-11-02 04:52:41.484312: Epoch 573 +2025-11-02 04:52:41.485898: Current learning rate: 0.00465 +2025-11-02 05:01:28.332806: train_loss -0.4387 +2025-11-02 05:01:28.337005: val_loss -0.4279 +2025-11-02 05:01:28.338230: Pseudo dice [np.float32(0.902), np.float32(0.7259), np.float32(0.6834), np.float32(0.6349), np.float32(0.8701), np.float32(0.7807), np.float32(0.8958), np.float32(0.8812), np.float32(0.9676), np.float32(0.9709), np.float32(0.9676), np.float32(0.8388), np.float32(0.7687), np.float32(0.8509), np.float32(0.9594), np.float32(0.2863), np.float32(0.2189)] +2025-11-02 05:01:28.339366: Epoch time: 526.87 s +2025-11-02 05:01:30.297632: +2025-11-02 05:01:30.298931: Epoch 574 +2025-11-02 05:01:30.299994: Current learning rate: 0.00464 +2025-11-02 05:10:10.539192: train_loss -0.4398 +2025-11-02 05:10:10.547089: val_loss -0.4659 +2025-11-02 05:10:10.548831: Pseudo dice [np.float32(0.9346), np.float32(0.7839), np.float32(0.7257), np.float32(0.6697), np.float32(0.8486), np.float32(0.803), np.float32(0.8491), np.float32(0.872), np.float32(0.9674), np.float32(0.961), np.float32(0.9584), np.float32(0.8455), np.float32(0.8076), np.float32(0.8509), np.float32(0.9687), np.float32(0.3339), np.float32(0.3178)] +2025-11-02 05:10:10.552031: Epoch time: 520.25 s +2025-11-02 05:10:12.700715: +2025-11-02 05:10:12.703631: Epoch 575 +2025-11-02 05:10:12.704697: Current learning rate: 0.00463 +2025-11-02 05:18:45.936006: train_loss -0.4383 +2025-11-02 05:18:45.976542: val_loss -0.405 +2025-11-02 05:18:45.978712: Pseudo dice [np.float32(0.8829), np.float32(0.7698), np.float32(0.6717), np.float32(0.6209), np.float32(0.8432), np.float32(0.7577), np.float32(0.8494), np.float32(0.8831), np.float32(0.9811), np.float32(0.9793), np.float32(0.9535), np.float32(0.8286), np.float32(0.7336), np.float32(0.8586), np.float32(0.9439), np.float32(0.4093), np.float32(0.3843)] +2025-11-02 05:18:46.324205: Epoch time: 513.24 s +2025-11-02 05:18:48.579768: +2025-11-02 05:18:48.581057: Epoch 576 +2025-11-02 05:18:48.585800: Current learning rate: 0.00462 +2025-11-02 05:27:39.456239: train_loss -0.4575 +2025-11-02 05:27:39.465193: val_loss -0.4732 +2025-11-02 05:27:39.467059: Pseudo dice [np.float32(0.9009), np.float32(0.7447), np.float32(0.5915), np.float32(0.581), np.float32(0.8639), np.float32(0.771), np.float32(0.8667), np.float32(0.8839), np.float32(0.9811), np.float32(0.9737), np.float32(0.9667), np.float32(0.8396), np.float32(0.798), np.float32(0.8708), np.float32(0.9667), np.float32(0.4767), np.float32(0.3929)] +2025-11-02 05:27:39.470351: Epoch time: 530.89 s +2025-11-02 05:27:41.628362: +2025-11-02 05:27:41.630972: Epoch 577 +2025-11-02 05:27:41.632064: Current learning rate: 0.00461 +2025-11-02 05:36:12.867482: train_loss -0.4412 +2025-11-02 05:36:12.874988: val_loss -0.449 +2025-11-02 05:36:12.876546: Pseudo dice [np.float32(0.8882), np.float32(0.7544), np.float32(0.6989), np.float32(0.5998), np.float32(0.8554), np.float32(0.7757), np.float32(0.9034), np.float32(0.8816), np.float32(0.9542), np.float32(0.9595), np.float32(0.9581), np.float32(0.8584), np.float32(0.7771), np.float32(0.8728), np.float32(0.905), np.float32(0.4228), np.float32(0.2973)] +2025-11-02 05:36:12.877827: Epoch time: 511.24 s +2025-11-02 05:36:15.026282: +2025-11-02 05:36:15.028418: Epoch 578 +2025-11-02 05:36:15.040526: Current learning rate: 0.0046 +2025-11-02 05:56:50.270855: train_loss -0.4635 +2025-11-02 05:56:50.300170: val_loss -0.4389 +2025-11-02 05:56:50.302633: Pseudo dice [np.float32(0.9403), np.float32(0.7615), np.float32(0.7063), np.float32(0.6629), np.float32(0.8513), np.float32(0.7891), np.float32(0.8821), np.float32(0.8962), np.float32(0.9567), np.float32(0.8743), np.float32(0.9557), np.float32(0.8519), np.float32(0.7849), np.float32(0.8632), np.float32(0.9337), np.float32(0.3551), np.float32(0.2549)] +2025-11-02 05:56:50.305686: Epoch time: 1235.25 s +2025-11-02 05:56:52.534116: +2025-11-02 05:56:52.542395: Epoch 579 +2025-11-02 05:56:52.551382: Current learning rate: 0.00459 +2025-11-02 06:05:45.349884: train_loss -0.4487 +2025-11-02 06:05:45.390280: val_loss -0.4102 +2025-11-02 06:05:45.397095: Pseudo dice [np.float32(0.9399), np.float32(0.7341), np.float32(0.7008), np.float32(0.6458), np.float32(0.8363), np.float32(0.7944), np.float32(0.8584), np.float32(0.8519), np.float32(0.9374), np.float32(0.9461), np.float32(0.9602), np.float32(0.8544), np.float32(0.7746), np.float32(0.8601), np.float32(0.9552), np.float32(0.3987), np.float32(0.1479)] +2025-11-02 06:05:45.413327: Epoch time: 532.82 s +2025-11-02 06:05:47.958015: +2025-11-02 06:05:47.974321: Epoch 580 +2025-11-02 06:05:47.986986: Current learning rate: 0.00458 +2025-11-02 06:14:40.442538: train_loss -0.4323 +2025-11-02 06:14:40.470686: val_loss -0.4282 +2025-11-02 06:14:40.473567: Pseudo dice [np.float32(0.8952), np.float32(0.7304), np.float32(0.6843), np.float32(0.6506), np.float32(0.8763), np.float32(0.7898), np.float32(0.9001), np.float32(0.8737), np.float32(0.9699), np.float32(0.9684), np.float32(0.9628), np.float32(0.8319), np.float32(0.7711), np.float32(0.8421), np.float32(0.9451), np.float32(0.2347), np.float32(0.3736)] +2025-11-02 06:14:40.482310: Epoch time: 532.49 s +2025-11-02 06:14:42.707425: +2025-11-02 06:14:42.709725: Epoch 581 +2025-11-02 06:14:42.711239: Current learning rate: 0.00457 +2025-11-02 06:23:27.212749: train_loss -0.4298 +2025-11-02 06:23:27.275616: val_loss -0.4453 +2025-11-02 06:23:27.277428: Pseudo dice [np.float32(0.9172), np.float32(0.7133), np.float32(0.6656), np.float32(0.6497), np.float32(0.8807), np.float32(0.8054), np.float32(0.8929), np.float32(0.8761), np.float32(0.978), np.float32(0.9775), np.float32(0.9648), np.float32(0.8493), np.float32(0.7579), np.float32(0.8833), np.float32(0.9542), np.float32(0.2762), np.float32(0.1958)] +2025-11-02 06:23:27.279089: Epoch time: 524.51 s +2025-11-02 06:23:29.870999: +2025-11-02 06:23:29.873434: Epoch 582 +2025-11-02 06:23:29.875484: Current learning rate: 0.00456 +2025-11-02 06:32:25.491512: train_loss -0.4303 +2025-11-02 06:32:25.498969: val_loss -0.454 +2025-11-02 06:32:25.500952: Pseudo dice [np.float32(0.9331), np.float32(0.7934), np.float32(0.69), np.float32(0.6321), np.float32(0.87), np.float32(0.7861), np.float32(0.8813), np.float32(0.8786), np.float32(0.9601), np.float32(0.9621), np.float32(0.9583), np.float32(0.8644), np.float32(0.7934), np.float32(0.8529), np.float32(0.8806), np.float32(0.3101), np.float32(0.3005)] +2025-11-02 06:32:25.502527: Epoch time: 535.63 s +2025-11-02 06:32:27.823790: +2025-11-02 06:32:27.830248: Epoch 583 +2025-11-02 06:32:27.836009: Current learning rate: 0.00455 +2025-11-02 06:41:16.223643: train_loss -0.4155 +2025-11-02 06:41:16.234870: val_loss -0.4503 +2025-11-02 06:41:16.238819: Pseudo dice [np.float32(0.899), np.float32(0.7361), np.float32(0.6618), np.float32(0.6417), np.float32(0.8722), np.float32(0.7998), np.float32(0.9016), np.float32(0.8867), np.float32(0.9155), np.float32(0.9077), np.float32(0.9649), np.float32(0.8628), np.float32(0.7834), np.float32(0.8837), np.float32(0.955), np.float32(0.435), np.float32(0.3768)] +2025-11-02 06:41:16.245210: Epoch time: 528.4 s +2025-11-02 06:41:18.763356: +2025-11-02 06:41:18.765209: Epoch 584 +2025-11-02 06:41:18.767269: Current learning rate: 0.00454 +2025-11-02 06:50:02.244165: train_loss -0.4392 +2025-11-02 06:50:02.257883: val_loss -0.4177 +2025-11-02 06:50:02.262331: Pseudo dice [np.float32(0.9274), np.float32(0.4197), np.float32(0.6938), np.float32(0.6599), np.float32(0.8406), np.float32(0.8024), np.float32(0.8611), np.float32(0.8855), np.float32(0.9469), np.float32(0.9558), np.float32(0.9498), np.float32(0.842), np.float32(0.7852), np.float32(0.8788), np.float32(0.9496), np.float32(0.3104), np.float32(0.3616)] +2025-11-02 06:50:02.268370: Epoch time: 523.49 s +2025-11-02 06:50:04.981907: +2025-11-02 06:50:04.985723: Epoch 585 +2025-11-02 06:50:04.987892: Current learning rate: 0.00453 +2025-11-02 06:58:53.538696: train_loss -0.4667 +2025-11-02 06:58:53.553497: val_loss -0.4502 +2025-11-02 06:58:53.556076: Pseudo dice [np.float32(0.9311), np.float32(0.7822), np.float32(0.7264), np.float32(0.6683), np.float32(0.89), np.float32(0.7886), np.float32(0.888), np.float32(0.8744), np.float32(0.9653), np.float32(0.9684), np.float32(0.9644), np.float32(0.822), np.float32(0.7929), np.float32(0.8804), np.float32(0.9642), np.float32(0.3297), np.float32(0.2226)] +2025-11-02 06:58:53.558988: Epoch time: 528.56 s +2025-11-02 06:58:56.027561: +2025-11-02 06:58:56.029659: Epoch 586 +2025-11-02 06:58:56.031200: Current learning rate: 0.00452 +2025-11-02 07:07:29.369700: train_loss -0.4595 +2025-11-02 07:07:29.374612: val_loss -0.484 +2025-11-02 07:07:29.377520: Pseudo dice [np.float32(0.9433), np.float32(0.7582), np.float32(0.7151), np.float32(0.6661), np.float32(0.8808), np.float32(0.8225), np.float32(0.8713), np.float32(0.8857), np.float32(0.9722), np.float32(0.9721), np.float32(0.9625), np.float32(0.8482), np.float32(0.7675), np.float32(0.8874), np.float32(0.9633), np.float32(0.4204), np.float32(0.3215)] +2025-11-02 07:07:29.382802: Epoch time: 513.35 s +2025-11-02 07:07:31.571268: +2025-11-02 07:07:31.574569: Epoch 587 +2025-11-02 07:07:31.577353: Current learning rate: 0.00451 +2025-11-02 07:16:29.570820: train_loss -0.4437 +2025-11-02 07:16:29.589827: val_loss -0.446 +2025-11-02 07:16:29.591572: Pseudo dice [np.float32(0.9313), np.float32(0.7727), np.float32(0.7226), np.float32(0.5994), np.float32(0.8662), np.float32(0.8077), np.float32(0.9008), np.float32(0.8745), np.float32(0.9698), np.float32(0.9722), np.float32(0.9694), np.float32(0.8404), np.float32(0.762), np.float32(0.848), np.float32(0.9611), np.float32(0.3903), np.float32(0.3615)] +2025-11-02 07:16:29.594299: Epoch time: 538.01 s +2025-11-02 07:16:32.381301: +2025-11-02 07:16:32.384108: Epoch 588 +2025-11-02 07:16:32.385540: Current learning rate: 0.0045 +2025-11-02 07:25:07.735358: train_loss -0.4411 +2025-11-02 07:25:07.747579: val_loss -0.44 +2025-11-02 07:25:07.751455: Pseudo dice [np.float32(0.9382), np.float32(0.7889), np.float32(0.7086), np.float32(0.6807), np.float32(0.8771), np.float32(0.792), np.float32(0.8734), np.float32(0.8916), np.float32(0.9784), np.float32(0.9814), np.float32(0.9652), np.float32(0.8432), np.float32(0.7646), np.float32(0.89), np.float32(0.9664), np.float32(0.3267), np.float32(0.1744)] +2025-11-02 07:25:07.753960: Epoch time: 515.36 s +2025-11-02 07:25:10.158619: +2025-11-02 07:25:10.165937: Epoch 589 +2025-11-02 07:25:10.169802: Current learning rate: 0.00449 +2025-11-02 07:34:02.826713: train_loss -0.4331 +2025-11-02 07:34:02.852270: val_loss -0.4617 +2025-11-02 07:34:02.858645: Pseudo dice [np.float32(0.9399), np.float32(0.7722), np.float32(0.71), np.float32(0.6607), np.float32(0.8542), np.float32(0.7797), np.float32(0.9062), np.float32(0.8851), np.float32(0.9428), np.float32(0.9113), np.float32(0.9645), np.float32(0.8502), np.float32(0.7581), np.float32(0.8676), np.float32(0.9481), np.float32(0.2665), np.float32(0.3548)] +2025-11-02 07:34:02.860504: Epoch time: 532.67 s +2025-11-02 07:34:05.135387: +2025-11-02 07:34:05.157234: Epoch 590 +2025-11-02 07:34:05.158997: Current learning rate: 0.00448 +2025-11-02 07:42:42.429660: train_loss -0.4383 +2025-11-02 07:42:42.442230: val_loss -0.4524 +2025-11-02 07:42:42.444944: Pseudo dice [np.float32(0.9197), np.float32(0.7624), np.float32(0.7228), np.float32(0.731), np.float32(0.8626), np.float32(0.785), np.float32(0.8544), np.float32(0.8805), np.float32(0.9551), np.float32(0.9655), np.float32(0.9622), np.float32(0.8308), np.float32(0.7766), np.float32(0.8929), np.float32(0.933), np.float32(0.3793), np.float32(0.3342)] +2025-11-02 07:42:42.446866: Epoch time: 517.3 s +2025-11-02 07:42:44.734968: +2025-11-02 07:42:44.756305: Epoch 591 +2025-11-02 07:42:44.759897: Current learning rate: 0.00447 +2025-11-02 07:51:32.286641: train_loss -0.4554 +2025-11-02 07:51:32.309367: val_loss -0.437 +2025-11-02 07:51:32.310648: Pseudo dice [np.float32(0.9344), np.float32(0.7049), np.float32(0.7066), np.float32(0.6841), np.float32(0.8694), np.float32(0.7843), np.float32(0.878), np.float32(0.8785), np.float32(0.9423), np.float32(0.9599), np.float32(0.962), np.float32(0.8292), np.float32(0.8203), np.float32(0.879), np.float32(0.9186), np.float32(0.3523), np.float32(0.3483)] +2025-11-02 07:51:32.315537: Epoch time: 527.56 s +2025-11-02 07:51:34.740853: +2025-11-02 07:51:34.752316: Epoch 592 +2025-11-02 07:51:34.756765: Current learning rate: 0.00446 +2025-11-02 08:00:11.718477: train_loss -0.4471 +2025-11-02 08:00:11.726794: val_loss -0.4559 +2025-11-02 08:00:11.729137: Pseudo dice [np.float32(0.9339), np.float32(0.7306), np.float32(0.6872), np.float32(0.6475), np.float32(0.8602), np.float32(0.7858), np.float32(0.8773), np.float32(0.87), np.float32(0.9802), np.float32(0.9743), np.float32(0.967), np.float32(0.8398), np.float32(0.7703), np.float32(0.871), np.float32(0.9701), np.float32(0.4122), np.float32(0.3248)] +2025-11-02 08:00:11.731565: Epoch time: 516.98 s +2025-11-02 08:00:14.392422: +2025-11-02 08:00:14.399758: Epoch 593 +2025-11-02 08:00:14.406815: Current learning rate: 0.00445 +2025-11-02 08:08:46.659097: train_loss -0.4457 +2025-11-02 08:08:46.670992: val_loss -0.4883 +2025-11-02 08:08:46.673606: Pseudo dice [np.float32(0.9386), np.float32(0.7562), np.float32(0.7209), np.float32(0.6704), np.float32(0.8659), np.float32(0.7631), np.float32(0.8986), np.float32(0.8887), np.float32(0.9812), np.float32(0.9813), np.float32(0.9657), np.float32(0.8459), np.float32(0.7726), np.float32(0.877), np.float32(0.9608), np.float32(0.2717), np.float32(0.2529)] +2025-11-02 08:08:46.677632: Epoch time: 512.27 s +2025-11-02 08:08:48.795729: +2025-11-02 08:08:48.799247: Epoch 594 +2025-11-02 08:08:48.800304: Current learning rate: 0.00444 +2025-11-02 08:17:46.659267: train_loss -0.4373 +2025-11-02 08:17:46.664799: val_loss -0.4652 +2025-11-02 08:17:46.667513: Pseudo dice [np.float32(0.9371), np.float32(0.7574), np.float32(0.6613), np.float32(0.6717), np.float32(0.8836), np.float32(0.7816), np.float32(0.8965), np.float32(0.8877), np.float32(0.9772), np.float32(0.9288), np.float32(0.9614), np.float32(0.8561), np.float32(0.791), np.float32(0.8842), np.float32(0.9512), np.float32(0.2734), np.float32(0.2708)] +2025-11-02 08:17:46.674831: Epoch time: 537.87 s +2025-11-02 08:17:48.817752: +2025-11-02 08:17:48.819104: Epoch 595 +2025-11-02 08:17:48.820374: Current learning rate: 0.00443 +2025-11-02 08:26:48.270613: train_loss -0.4648 +2025-11-02 08:26:48.294997: val_loss -0.4359 +2025-11-02 08:26:48.296825: Pseudo dice [np.float32(0.9197), np.float32(0.7814), np.float32(0.7462), np.float32(0.6727), np.float32(0.8755), np.float32(0.7865), np.float32(0.9072), np.float32(0.8798), np.float32(0.9569), np.float32(0.9572), np.float32(0.9659), np.float32(0.846), np.float32(0.8094), np.float32(0.8802), np.float32(0.9559), np.float32(0.3294), np.float32(0.1344)] +2025-11-02 08:26:48.298681: Epoch time: 539.46 s +2025-11-02 08:26:50.350889: +2025-11-02 08:26:50.352905: Epoch 596 +2025-11-02 08:26:50.354614: Current learning rate: 0.00442 +2025-11-02 08:35:32.469970: train_loss -0.472 +2025-11-02 08:35:32.474313: val_loss -0.458 +2025-11-02 08:35:32.475725: Pseudo dice [np.float32(0.933), np.float32(0.7588), np.float32(0.7556), np.float32(0.6418), np.float32(0.8726), np.float32(0.8269), np.float32(0.8864), np.float32(0.8872), np.float32(0.9524), np.float32(0.9448), np.float32(0.9676), np.float32(0.8365), np.float32(0.748), np.float32(0.8779), np.float32(0.9657), np.float32(0.3677), np.float32(0.3142)] +2025-11-02 08:35:32.477245: Epoch time: 522.12 s +2025-11-02 08:35:35.291985: +2025-11-02 08:35:35.293162: Epoch 597 +2025-11-02 08:35:35.294483: Current learning rate: 0.00441 +2025-11-02 08:44:29.707914: train_loss -0.4275 +2025-11-02 08:44:29.726266: val_loss -0.3979 +2025-11-02 08:44:29.728389: Pseudo dice [np.float32(0.9004), np.float32(0.7653), np.float32(0.73), np.float32(0.6511), np.float32(0.8555), np.float32(0.7696), np.float32(0.8887), np.float32(0.8712), np.float32(0.9645), np.float32(0.9633), np.float32(0.9641), np.float32(0.8507), np.float32(0.7651), np.float32(0.8161), np.float32(0.9648), np.float32(0.1913), np.float32(0.1886)] +2025-11-02 08:44:29.730315: Epoch time: 534.42 s +2025-11-02 08:44:32.062162: +2025-11-02 08:44:32.063459: Epoch 598 +2025-11-02 08:44:32.064667: Current learning rate: 0.0044 +2025-11-02 08:53:16.502175: train_loss -0.4378 +2025-11-02 08:53:16.511166: val_loss -0.4428 +2025-11-02 08:53:16.519367: Pseudo dice [np.float32(0.8997), np.float32(0.7683), np.float32(0.6781), np.float32(0.7033), np.float32(0.8688), np.float32(0.7915), np.float32(0.8037), np.float32(0.8692), np.float32(0.9802), np.float32(0.9767), np.float32(0.9626), np.float32(0.8362), np.float32(0.7545), np.float32(0.8641), np.float32(0.9366), np.float32(0.2169), np.float32(0.2838)] +2025-11-02 08:53:16.520831: Epoch time: 524.44 s +2025-11-02 08:53:18.711550: +2025-11-02 08:53:18.713280: Epoch 599 +2025-11-02 08:53:18.715098: Current learning rate: 0.00439 +2025-11-02 09:02:00.610415: train_loss -0.4143 +2025-11-02 09:02:00.615611: val_loss -0.3619 +2025-11-02 09:02:00.618016: Pseudo dice [np.float32(0.9167), np.float32(0.6941), np.float32(0.6593), np.float32(0.6105), np.float32(0.8644), np.float32(0.7649), np.float32(0.784), np.float32(0.8668), np.float32(0.9661), np.float32(0.97), np.float32(0.9558), np.float32(0.8368), np.float32(0.7836), np.float32(0.8333), np.float32(0.9343), np.float32(0.2463), np.float32(0.2852)] +2025-11-02 09:02:00.620034: Epoch time: 521.9 s +2025-11-02 09:02:10.259919: +2025-11-02 09:02:10.261603: Epoch 600 +2025-11-02 09:02:10.263160: Current learning rate: 0.00438 +2025-11-02 09:10:37.626977: train_loss -0.4107 +2025-11-02 09:10:37.640904: val_loss -0.4603 +2025-11-02 09:10:37.642184: Pseudo dice [np.float32(0.9302), np.float32(0.4987), np.float32(0.7543), np.float32(0.6153), np.float32(0.8754), np.float32(0.7919), np.float32(0.8936), np.float32(0.8747), np.float32(0.9691), np.float32(0.9759), np.float32(0.9637), np.float32(0.8544), np.float32(0.7912), np.float32(0.8804), np.float32(0.938), np.float32(0.2079), np.float32(0.1508)] +2025-11-02 09:10:37.643919: Epoch time: 507.37 s +2025-11-02 09:10:40.584341: +2025-11-02 09:10:40.585759: Epoch 601 +2025-11-02 09:10:40.586873: Current learning rate: 0.00437 +2025-11-02 09:19:07.384894: train_loss -0.4387 +2025-11-02 09:19:07.392989: val_loss -0.4944 +2025-11-02 09:19:07.396422: Pseudo dice [np.float32(0.9305), np.float32(0.7896), np.float32(0.7276), np.float32(0.6367), np.float32(0.8684), np.float32(0.7848), np.float32(0.8585), np.float32(0.8809), np.float32(0.9663), np.float32(0.9733), np.float32(0.965), np.float32(0.8335), np.float32(0.7673), np.float32(0.8562), np.float32(0.9572), np.float32(0.5586), np.float32(0.4165)] +2025-11-02 09:19:07.404410: Epoch time: 506.8 s +2025-11-02 09:19:09.471584: +2025-11-02 09:19:09.474675: Epoch 602 +2025-11-02 09:19:09.484350: Current learning rate: 0.00436 +2025-11-02 09:27:43.946245: train_loss -0.443 +2025-11-02 09:27:43.954950: val_loss -0.4238 +2025-11-02 09:27:43.956975: Pseudo dice [np.float32(0.9264), np.float32(0.7507), np.float32(0.6729), np.float32(0.6864), np.float32(0.8617), np.float32(0.757), np.float32(0.8071), np.float32(0.8728), np.float32(0.9788), np.float32(0.9784), np.float32(0.9591), np.float32(0.8366), np.float32(0.8107), np.float32(0.8741), np.float32(0.9677), np.float32(0.2499), np.float32(0.1339)] +2025-11-02 09:27:43.958117: Epoch time: 514.48 s +2025-11-02 09:27:46.303639: +2025-11-02 09:27:46.309809: Epoch 603 +2025-11-02 09:27:46.311841: Current learning rate: 0.00435 +2025-11-02 09:36:21.805922: train_loss -0.4391 +2025-11-02 09:36:21.828300: val_loss -0.4804 +2025-11-02 09:36:21.830940: Pseudo dice [np.float32(0.9199), np.float32(0.7601), np.float32(0.7254), np.float32(0.6158), np.float32(0.8726), np.float32(0.8093), np.float32(0.8808), np.float32(0.8874), np.float32(0.9579), np.float32(0.9647), np.float32(0.9483), np.float32(0.8489), np.float32(0.7788), np.float32(0.8499), np.float32(0.9579), np.float32(0.4829), np.float32(0.4426)] +2025-11-02 09:36:21.832365: Epoch time: 515.51 s +2025-11-02 09:36:25.007533: +2025-11-02 09:36:25.008881: Epoch 604 +2025-11-02 09:36:25.015290: Current learning rate: 0.00434 +2025-11-02 09:45:11.139031: train_loss -0.4349 +2025-11-02 09:45:11.159952: val_loss -0.4345 +2025-11-02 09:45:11.162556: Pseudo dice [np.float32(0.9392), np.float32(0.7491), np.float32(0.6976), np.float32(0.6059), np.float32(0.8478), np.float32(0.7731), np.float32(0.8691), np.float32(0.8694), np.float32(0.9638), np.float32(0.9603), np.float32(0.9517), np.float32(0.8389), np.float32(0.777), np.float32(0.8394), np.float32(0.9301), np.float32(0.2695), np.float32(0.2268)] +2025-11-02 09:45:11.169975: Epoch time: 526.14 s +2025-11-02 09:45:13.515358: +2025-11-02 09:45:13.518055: Epoch 605 +2025-11-02 09:45:13.519411: Current learning rate: 0.00433 +2025-11-02 09:53:43.850090: train_loss -0.4218 +2025-11-02 09:53:43.866222: val_loss -0.4519 +2025-11-02 09:53:43.867910: Pseudo dice [np.float32(0.9378), np.float32(0.7492), np.float32(0.7221), np.float32(0.6508), np.float32(0.8491), np.float32(0.7955), np.float32(0.8425), np.float32(0.866), np.float32(0.9731), np.float32(0.9655), np.float32(0.9668), np.float32(0.8219), np.float32(0.7585), np.float32(0.8725), np.float32(0.9589), np.float32(0.3461), np.float32(0.3269)] +2025-11-02 09:53:43.874317: Epoch time: 510.34 s +2025-11-02 09:53:46.632659: +2025-11-02 09:53:46.634201: Epoch 606 +2025-11-02 09:53:46.635691: Current learning rate: 0.00432 +2025-11-02 10:02:33.194624: train_loss -0.4117 +2025-11-02 10:02:33.206213: val_loss -0.4116 +2025-11-02 10:02:33.207955: Pseudo dice [np.float32(0.9255), np.float32(0.8118), np.float32(0.7734), np.float32(0.6598), np.float32(0.8682), np.float32(0.7879), np.float32(0.8373), np.float32(0.8845), np.float32(0.9338), np.float32(0.9256), np.float32(0.9544), np.float32(0.8267), np.float32(0.7774), np.float32(0.8502), np.float32(0.9229), np.float32(0.2189), np.float32(0.4384)] +2025-11-02 10:02:33.211051: Epoch time: 526.57 s +2025-11-02 10:02:35.592659: +2025-11-02 10:02:35.597905: Epoch 607 +2025-11-02 10:02:35.599032: Current learning rate: 0.00431 +2025-11-02 10:12:56.687074: train_loss -0.4358 +2025-11-02 10:12:56.749825: val_loss -0.4917 +2025-11-02 10:12:56.753758: Pseudo dice [np.float32(0.9406), np.float32(0.7939), np.float32(0.7214), np.float32(0.65), np.float32(0.8821), np.float32(0.7854), np.float32(0.8996), np.float32(0.8844), np.float32(0.9735), np.float32(0.9711), np.float32(0.9654), np.float32(0.8716), np.float32(0.7563), np.float32(0.8775), np.float32(0.9538), np.float32(0.4354), np.float32(0.3624)] +2025-11-02 10:12:56.757634: Epoch time: 621.1 s +2025-11-02 10:12:59.421835: +2025-11-02 10:12:59.509595: Epoch 608 +2025-11-02 10:12:59.583691: Current learning rate: 0.0043 +2025-11-02 10:29:17.650771: train_loss -0.424 +2025-11-02 10:29:17.707406: val_loss -0.42 +2025-11-02 10:29:17.725514: Pseudo dice [np.float32(0.9205), np.float32(0.7515), np.float32(0.7036), np.float32(0.6223), np.float32(0.8761), np.float32(0.7765), np.float32(0.9246), np.float32(0.8665), np.float32(0.9762), np.float32(0.9344), np.float32(0.9586), np.float32(0.834), np.float32(0.7435), np.float32(0.859), np.float32(0.9384), np.float32(0.3683), np.float32(0.3041)] +2025-11-02 10:29:17.735058: Epoch time: 978.23 s +2025-11-02 10:29:19.861696: +2025-11-02 10:29:19.873427: Epoch 609 +2025-11-02 10:29:19.884212: Current learning rate: 0.00429 +2025-11-02 10:45:03.164907: train_loss -0.4583 +2025-11-02 10:45:03.219871: val_loss -0.4383 +2025-11-02 10:45:03.240456: Pseudo dice [np.float32(0.8945), np.float32(0.7649), np.float32(0.7175), np.float32(0.6577), np.float32(0.8568), np.float32(0.7985), np.float32(0.8808), np.float32(0.888), np.float32(0.9708), np.float32(0.9651), np.float32(0.9672), np.float32(0.8519), np.float32(0.7748), np.float32(0.8599), np.float32(0.9624), np.float32(0.3553), np.float32(0.3336)] +2025-11-02 10:45:03.252695: Epoch time: 943.31 s +2025-11-02 10:45:05.700053: +2025-11-02 10:45:05.709969: Epoch 610 +2025-11-02 10:45:05.717614: Current learning rate: 0.00429 +2025-11-02 11:00:56.969284: train_loss -0.4434 +2025-11-02 11:00:56.994056: val_loss -0.4882 +2025-11-02 11:00:57.000871: Pseudo dice [np.float32(0.9478), np.float32(0.7775), np.float32(0.7408), np.float32(0.6169), np.float32(0.8651), np.float32(0.7799), np.float32(0.8733), np.float32(0.8885), np.float32(0.9741), np.float32(0.971), np.float32(0.9686), np.float32(0.8364), np.float32(0.7533), np.float32(0.8836), np.float32(0.9661), np.float32(0.3514), np.float32(0.2813)] +2025-11-02 11:00:57.007514: Epoch time: 951.27 s +2025-11-02 11:00:59.155886: +2025-11-02 11:00:59.162169: Epoch 611 +2025-11-02 11:00:59.164046: Current learning rate: 0.00428 +2025-11-02 11:09:36.193953: train_loss -0.4437 +2025-11-02 11:09:36.199443: val_loss -0.4394 +2025-11-02 11:09:36.200855: Pseudo dice [np.float32(0.9348), np.float32(0.7742), np.float32(0.7307), np.float32(0.5539), np.float32(0.869), np.float32(0.7691), np.float32(0.8529), np.float32(0.8948), np.float32(0.9447), np.float32(0.9421), np.float32(0.9639), np.float32(0.8498), np.float32(0.7821), np.float32(0.8636), np.float32(0.9187), np.float32(0.1652), np.float32(0.1461)] +2025-11-02 11:09:36.202378: Epoch time: 517.04 s +2025-11-02 11:09:38.457762: +2025-11-02 11:09:38.459093: Epoch 612 +2025-11-02 11:09:38.460277: Current learning rate: 0.00427 +2025-11-02 11:18:24.041748: train_loss -0.432 +2025-11-02 11:18:24.048242: val_loss -0.4465 +2025-11-02 11:18:24.049484: Pseudo dice [np.float32(0.9315), np.float32(0.797), np.float32(0.7509), np.float32(0.6312), np.float32(0.8556), np.float32(0.7727), np.float32(0.8676), np.float32(0.8878), np.float32(0.9578), np.float32(0.9623), np.float32(0.9644), np.float32(0.8405), np.float32(0.789), np.float32(0.885), np.float32(0.9443), np.float32(0.2912), np.float32(0.2508)] +2025-11-02 11:18:24.051101: Epoch time: 525.59 s +2025-11-02 11:18:26.219129: +2025-11-02 11:18:26.220809: Epoch 613 +2025-11-02 11:18:26.222269: Current learning rate: 0.00426 +2025-11-02 11:26:58.034293: train_loss -0.4454 +2025-11-02 11:26:58.054004: val_loss -0.4524 +2025-11-02 11:26:58.055383: Pseudo dice [np.float32(0.9399), np.float32(0.7567), np.float32(0.7303), np.float32(0.6577), np.float32(0.8554), np.float32(0.7751), np.float32(0.8733), np.float32(0.872), np.float32(0.9653), np.float32(0.9664), np.float32(0.9636), np.float32(0.8352), np.float32(0.7904), np.float32(0.838), np.float32(0.9352), np.float32(0.3847), np.float32(0.1692)] +2025-11-02 11:26:58.056947: Epoch time: 511.82 s +2025-11-02 11:27:00.523839: +2025-11-02 11:27:00.525959: Epoch 614 +2025-11-02 11:27:00.527294: Current learning rate: 0.00425 +2025-11-02 11:35:35.286845: train_loss -0.4349 +2025-11-02 11:35:35.296477: val_loss -0.3942 +2025-11-02 11:35:35.298413: Pseudo dice [np.float32(0.8807), np.float32(0.7701), np.float32(0.6914), np.float32(0.5553), np.float32(0.8675), np.float32(0.7789), np.float32(0.8862), np.float32(0.8772), np.float32(0.9784), np.float32(0.9777), np.float32(0.9375), np.float32(0.8401), np.float32(0.7696), np.float32(0.8719), np.float32(0.8124), np.float32(0.5075), np.float32(0.411)] +2025-11-02 11:35:35.300081: Epoch time: 514.77 s +2025-11-02 11:35:37.584860: +2025-11-02 11:35:37.586046: Epoch 615 +2025-11-02 11:35:37.587067: Current learning rate: 0.00424 +2025-11-02 11:44:07.642637: train_loss -0.4358 +2025-11-02 11:44:07.660577: val_loss -0.5008 +2025-11-02 11:44:07.662242: Pseudo dice [np.float32(0.9177), np.float32(0.7539), np.float32(0.7483), np.float32(0.6735), np.float32(0.8577), np.float32(0.7889), np.float32(0.8785), np.float32(0.8821), np.float32(0.9633), np.float32(0.9709), np.float32(0.9667), np.float32(0.8555), np.float32(0.8012), np.float32(0.8728), np.float32(0.9651), np.float32(0.3763), np.float32(0.3494)] +2025-11-02 11:44:07.663720: Epoch time: 510.07 s +2025-11-02 11:44:09.823451: +2025-11-02 11:44:09.830790: Epoch 616 +2025-11-02 11:44:09.835921: Current learning rate: 0.00423 +2025-11-02 11:52:43.285534: train_loss -0.4254 +2025-11-02 11:52:43.292078: val_loss -0.4665 +2025-11-02 11:52:43.293251: Pseudo dice [np.float32(0.9346), np.float32(0.7599), np.float32(0.707), np.float32(0.6978), np.float32(0.8722), np.float32(0.793), np.float32(0.8733), np.float32(0.8718), np.float32(0.9457), np.float32(0.9541), np.float32(0.9642), np.float32(0.8231), np.float32(0.8115), np.float32(0.8648), np.float32(0.9633), np.float32(0.478), np.float32(0.3809)] +2025-11-02 11:52:43.294759: Epoch time: 513.47 s +2025-11-02 11:52:45.538804: +2025-11-02 11:52:45.540072: Epoch 617 +2025-11-02 11:52:45.541377: Current learning rate: 0.00422 +2025-11-02 12:01:22.529032: train_loss -0.422 +2025-11-02 12:01:22.533594: val_loss -0.4428 +2025-11-02 12:01:22.534896: Pseudo dice [np.float32(0.9219), np.float32(0.7442), np.float32(0.7276), np.float32(0.6659), np.float32(0.8279), np.float32(0.8038), np.float32(0.8566), np.float32(0.8774), np.float32(0.972), np.float32(0.9584), np.float32(0.9597), np.float32(0.8372), np.float32(0.772), np.float32(0.8527), np.float32(0.9648), np.float32(0.196), np.float32(0.3479)] +2025-11-02 12:01:22.536227: Epoch time: 517.0 s +2025-11-02 12:01:24.572842: +2025-11-02 12:01:24.574269: Epoch 618 +2025-11-02 12:01:24.575303: Current learning rate: 0.00421 +2025-11-02 12:09:50.492196: train_loss -0.4485 +2025-11-02 12:09:50.499539: val_loss -0.4568 +2025-11-02 12:09:50.500883: Pseudo dice [np.float32(0.9265), np.float32(0.7747), np.float32(0.7336), np.float32(0.6857), np.float32(0.8624), np.float32(0.7857), np.float32(0.8353), np.float32(0.8822), np.float32(0.9569), np.float32(0.966), np.float32(0.9678), np.float32(0.8111), np.float32(0.7983), np.float32(0.8651), np.float32(0.9354), np.float32(0.1815), np.float32(0.3059)] +2025-11-02 12:09:50.502110: Epoch time: 505.92 s +2025-11-02 12:09:52.816516: +2025-11-02 12:09:52.817725: Epoch 619 +2025-11-02 12:09:52.818773: Current learning rate: 0.0042 +2025-11-02 12:18:29.967010: train_loss -0.4632 +2025-11-02 12:18:29.971385: val_loss -0.4295 +2025-11-02 12:18:29.972592: Pseudo dice [np.float32(0.9041), np.float32(0.7574), np.float32(0.7281), np.float32(0.6261), np.float32(0.87), np.float32(0.7884), np.float32(0.8826), np.float32(0.8759), np.float32(0.966), np.float32(0.9654), np.float32(0.9632), np.float32(0.8411), np.float32(0.7751), np.float32(0.8899), np.float32(0.9447), np.float32(0.3503), np.float32(0.318)] +2025-11-02 12:18:29.973797: Epoch time: 517.16 s +2025-11-02 12:18:32.144951: +2025-11-02 12:18:32.146160: Epoch 620 +2025-11-02 12:18:32.147388: Current learning rate: 0.00419 +2025-11-02 12:27:13.511947: train_loss -0.4483 +2025-11-02 12:27:13.542040: val_loss -0.453 +2025-11-02 12:27:13.543350: Pseudo dice [np.float32(0.9229), np.float32(0.7634), np.float32(0.7289), np.float32(0.6458), np.float32(0.8624), np.float32(0.8079), np.float32(0.8974), np.float32(0.8782), np.float32(0.9708), np.float32(0.9602), np.float32(0.9648), np.float32(0.8286), np.float32(0.7997), np.float32(0.8679), np.float32(0.9565), np.float32(0.3079), np.float32(0.2425)] +2025-11-02 12:27:13.544588: Epoch time: 521.37 s +2025-11-02 12:27:15.554808: +2025-11-02 12:27:15.556097: Epoch 621 +2025-11-02 12:27:15.559553: Current learning rate: 0.00418 +2025-11-02 12:35:44.354691: train_loss -0.442 +2025-11-02 12:35:44.363804: val_loss -0.4189 +2025-11-02 12:35:44.365339: Pseudo dice [np.float32(0.9405), np.float32(0.7484), np.float32(0.6776), np.float32(0.6576), np.float32(0.8597), np.float32(0.7584), np.float32(0.8344), np.float32(0.8772), np.float32(0.9658), np.float32(0.9729), np.float32(0.9651), np.float32(0.8356), np.float32(0.7847), np.float32(0.836), np.float32(0.9609), np.float32(0.3705), np.float32(0.1771)] +2025-11-02 12:35:44.368850: Epoch time: 508.8 s +2025-11-02 12:35:46.492011: +2025-11-02 12:35:46.494244: Epoch 622 +2025-11-02 12:35:46.496301: Current learning rate: 0.00417 +2025-11-02 12:44:21.037818: train_loss -0.4409 +2025-11-02 12:44:21.042990: val_loss -0.4281 +2025-11-02 12:44:21.044322: Pseudo dice [np.float32(0.9313), np.float32(0.7706), np.float32(0.704), np.float32(0.6991), np.float32(0.8589), np.float32(0.7654), np.float32(0.8716), np.float32(0.8753), np.float32(0.9645), np.float32(0.9011), np.float32(0.9494), np.float32(0.8429), np.float32(0.8049), np.float32(0.8744), np.float32(0.9712), np.float32(0.3133), np.float32(0.2332)] +2025-11-02 12:44:21.045660: Epoch time: 514.56 s +2025-11-02 12:44:23.396953: +2025-11-02 12:44:23.398443: Epoch 623 +2025-11-02 12:44:23.400025: Current learning rate: 0.00416 +2025-11-02 12:52:55.751027: train_loss -0.4237 +2025-11-02 12:52:55.755950: val_loss -0.4748 +2025-11-02 12:52:55.758090: Pseudo dice [np.float32(0.9467), np.float32(0.7529), np.float32(0.6817), np.float32(0.6885), np.float32(0.8608), np.float32(0.8052), np.float32(0.9105), np.float32(0.8732), np.float32(0.9731), np.float32(0.9691), np.float32(0.965), np.float32(0.8666), np.float32(0.7842), np.float32(0.8764), np.float32(0.9642), np.float32(0.3471), np.float32(0.2897)] +2025-11-02 12:52:55.759838: Epoch time: 512.36 s +2025-11-02 12:52:57.945589: +2025-11-02 12:52:57.946867: Epoch 624 +2025-11-02 12:52:57.948129: Current learning rate: 0.00415 +2025-11-02 13:01:44.877412: train_loss -0.4473 +2025-11-02 13:01:44.885867: val_loss -0.4201 +2025-11-02 13:01:44.888361: Pseudo dice [np.float32(0.9362), np.float32(0.7297), np.float32(0.6959), np.float32(0.6469), np.float32(0.8432), np.float32(0.7998), np.float32(0.8239), np.float32(0.8739), np.float32(0.976), np.float32(0.9788), np.float32(0.9618), np.float32(0.8316), np.float32(0.7881), np.float32(0.8375), np.float32(0.9394), np.float32(0.3564), np.float32(0.3176)] +2025-11-02 13:01:44.890087: Epoch time: 526.94 s +2025-11-02 13:01:47.142289: +2025-11-02 13:01:47.143872: Epoch 625 +2025-11-02 13:01:47.145061: Current learning rate: 0.00414 +2025-11-02 13:10:11.389791: train_loss -0.4404 +2025-11-02 13:10:11.400976: val_loss -0.4435 +2025-11-02 13:10:11.403241: Pseudo dice [np.float32(0.8995), np.float32(0.7494), np.float32(0.7074), np.float32(0.681), np.float32(0.8736), np.float32(0.8216), np.float32(0.904), np.float32(0.8554), np.float32(0.9546), np.float32(0.9441), np.float32(0.9636), np.float32(0.8619), np.float32(0.7863), np.float32(0.8857), np.float32(0.9615), np.float32(0.2393), np.float32(0.2928)] +2025-11-02 13:10:11.405340: Epoch time: 504.25 s +2025-11-02 13:10:13.684619: +2025-11-02 13:10:13.693310: Epoch 626 +2025-11-02 13:10:13.697881: Current learning rate: 0.00413 +2025-11-02 13:18:53.367681: train_loss -0.4398 +2025-11-02 13:18:53.372651: val_loss -0.4688 +2025-11-02 13:18:53.377112: Pseudo dice [np.float32(0.9365), np.float32(0.7868), np.float32(0.7126), np.float32(0.6943), np.float32(0.8675), np.float32(0.7931), np.float32(0.7747), np.float32(0.8714), np.float32(0.9615), np.float32(0.9631), np.float32(0.9597), np.float32(0.8534), np.float32(0.8202), np.float32(0.8782), np.float32(0.9592), np.float32(0.3543), np.float32(0.4476)] +2025-11-02 13:18:53.401738: Epoch time: 519.69 s +2025-11-02 13:18:55.543322: +2025-11-02 13:18:55.544827: Epoch 627 +2025-11-02 13:18:55.546258: Current learning rate: 0.00412 +2025-11-02 13:27:28.153381: train_loss -0.4255 +2025-11-02 13:27:28.171064: val_loss -0.4857 +2025-11-02 13:27:28.178714: Pseudo dice [np.float32(0.935), np.float32(0.6836), np.float32(0.718), np.float32(0.6647), np.float32(0.8624), np.float32(0.8095), np.float32(0.8732), np.float32(0.8909), np.float32(0.9691), np.float32(0.9718), np.float32(0.9637), np.float32(0.8476), np.float32(0.7756), np.float32(0.8523), np.float32(0.956), np.float32(0.2673), np.float32(0.3146)] +2025-11-02 13:27:28.180425: Epoch time: 512.62 s +2025-11-02 13:27:30.284091: +2025-11-02 13:27:30.285440: Epoch 628 +2025-11-02 13:27:30.286677: Current learning rate: 0.00411 +2025-11-02 13:36:06.014990: train_loss -0.4395 +2025-11-02 13:36:06.022959: val_loss -0.4969 +2025-11-02 13:36:06.024901: Pseudo dice [np.float32(0.9471), np.float32(0.8062), np.float32(0.7258), np.float32(0.6815), np.float32(0.8498), np.float32(0.8211), np.float32(0.8977), np.float32(0.8881), np.float32(0.9768), np.float32(0.9771), np.float32(0.9685), np.float32(0.8642), np.float32(0.77), np.float32(0.8595), np.float32(0.9614), np.float32(0.3046), np.float32(0.3519)] +2025-11-02 13:36:06.030882: Epoch time: 515.74 s +2025-11-02 13:36:08.466160: +2025-11-02 13:36:08.467989: Epoch 629 +2025-11-02 13:36:08.469530: Current learning rate: 0.0041 +2025-11-02 13:44:48.863652: train_loss -0.4409 +2025-11-02 13:44:48.880466: val_loss -0.4428 +2025-11-02 13:44:48.881803: Pseudo dice [np.float32(0.926), np.float32(0.7751), np.float32(0.6941), np.float32(0.6341), np.float32(0.8409), np.float32(0.7958), np.float32(0.8836), np.float32(0.8788), np.float32(0.9822), np.float32(0.9782), np.float32(0.9625), np.float32(0.8566), np.float32(0.7954), np.float32(0.8403), np.float32(0.9575), np.float32(0.2554), np.float32(0.2233)] +2025-11-02 13:44:48.883425: Epoch time: 520.41 s +2025-11-02 13:44:51.285299: +2025-11-02 13:44:51.287076: Epoch 630 +2025-11-02 13:44:51.289719: Current learning rate: 0.00409 +2025-11-02 13:53:38.138448: train_loss -0.4551 +2025-11-02 13:53:38.149120: val_loss -0.4756 +2025-11-02 13:53:38.150689: Pseudo dice [np.float32(0.9282), np.float32(0.7654), np.float32(0.6967), np.float32(0.707), np.float32(0.8687), np.float32(0.7951), np.float32(0.8698), np.float32(0.8838), np.float32(0.9835), np.float32(0.9686), np.float32(0.9669), np.float32(0.8489), np.float32(0.8147), np.float32(0.8886), np.float32(0.9672), np.float32(0.2982), np.float32(0.2397)] +2025-11-02 13:53:38.152592: Epoch time: 526.87 s +2025-11-02 13:53:40.572739: +2025-11-02 13:53:40.575813: Epoch 631 +2025-11-02 13:53:40.577695: Current learning rate: 0.00408 +2025-11-02 14:02:20.789389: train_loss -0.4562 +2025-11-02 14:02:20.794716: val_loss -0.4635 +2025-11-02 14:02:20.797013: Pseudo dice [np.float32(0.9394), np.float32(0.7644), np.float32(0.7423), np.float32(0.5919), np.float32(0.8593), np.float32(0.7944), np.float32(0.9116), np.float32(0.8682), np.float32(0.9785), np.float32(0.9498), np.float32(0.959), np.float32(0.8299), np.float32(0.789), np.float32(0.8393), np.float32(0.9568), np.float32(0.3656), np.float32(0.2209)] +2025-11-02 14:02:20.814583: Epoch time: 520.22 s +2025-11-02 14:02:23.361400: +2025-11-02 14:02:23.363034: Epoch 632 +2025-11-02 14:02:23.365096: Current learning rate: 0.00407 +2025-11-02 14:11:02.820510: train_loss -0.4586 +2025-11-02 14:11:02.827702: val_loss -0.4788 +2025-11-02 14:11:02.830308: Pseudo dice [np.float32(0.9305), np.float32(0.7877), np.float32(0.7705), np.float32(0.6782), np.float32(0.8731), np.float32(0.7843), np.float32(0.8812), np.float32(0.8918), np.float32(0.9792), np.float32(0.9787), np.float32(0.9667), np.float32(0.8617), np.float32(0.7693), np.float32(0.8731), np.float32(0.961), np.float32(0.4029), np.float32(0.3331)] +2025-11-02 14:11:02.832300: Epoch time: 519.46 s +2025-11-02 14:11:05.080877: +2025-11-02 14:11:05.084121: Epoch 633 +2025-11-02 14:11:05.087132: Current learning rate: 0.00406 +2025-11-02 14:19:48.450182: train_loss -0.4199 +2025-11-02 14:19:48.454426: val_loss -0.4318 +2025-11-02 14:19:48.455945: Pseudo dice [np.float32(0.9393), np.float32(0.7493), np.float32(0.721), np.float32(0.6013), np.float32(0.8156), np.float32(0.7679), np.float32(0.8902), np.float32(0.8792), np.float32(0.9385), np.float32(0.934), np.float32(0.9508), np.float32(0.8375), np.float32(0.7998), np.float32(0.8382), np.float32(0.8977), np.float32(0.3353), np.float32(0.3186)] +2025-11-02 14:19:48.457675: Epoch time: 523.37 s +2025-11-02 14:19:50.645099: +2025-11-02 14:19:50.646311: Epoch 634 +2025-11-02 14:19:50.647824: Current learning rate: 0.00405 +2025-11-02 14:28:25.910416: train_loss -0.4364 +2025-11-02 14:28:25.917106: val_loss -0.4522 +2025-11-02 14:28:25.918609: Pseudo dice [np.float32(0.9203), np.float32(0.7522), np.float32(0.7245), np.float32(0.6821), np.float32(0.8649), np.float32(0.7911), np.float32(0.8029), np.float32(0.8798), np.float32(0.9637), np.float32(0.9538), np.float32(0.9596), np.float32(0.8275), np.float32(0.7737), np.float32(0.8639), np.float32(0.9347), np.float32(0.3697), np.float32(0.3797)] +2025-11-02 14:28:25.919921: Epoch time: 515.27 s +2025-11-02 14:28:28.116550: +2025-11-02 14:28:28.117908: Epoch 635 +2025-11-02 14:28:28.119276: Current learning rate: 0.00404 +2025-11-02 14:37:05.562455: train_loss -0.4432 +2025-11-02 14:37:05.576195: val_loss -0.4528 +2025-11-02 14:37:05.578136: Pseudo dice [np.float32(0.9221), np.float32(0.7576), np.float32(0.7321), np.float32(0.6912), np.float32(0.8717), np.float32(0.8071), np.float32(0.8201), np.float32(0.8786), np.float32(0.9541), np.float32(0.9755), np.float32(0.9659), np.float32(0.8163), np.float32(0.7579), np.float32(0.8854), np.float32(0.9596), np.float32(0.4906), np.float32(0.404)] +2025-11-02 14:37:05.580113: Epoch time: 517.46 s +2025-11-02 14:37:07.860447: +2025-11-02 14:37:07.874432: Epoch 636 +2025-11-02 14:37:07.885565: Current learning rate: 0.00403 +2025-11-02 14:45:54.883504: train_loss -0.405 +2025-11-02 14:45:54.897643: val_loss -0.4214 +2025-11-02 14:45:54.899665: Pseudo dice [np.float32(0.8698), np.float32(0.7673), np.float32(0.7206), np.float32(0.632), np.float32(0.8364), np.float32(0.7605), np.float32(0.7582), np.float32(0.857), np.float32(0.9589), np.float32(0.9457), np.float32(0.9425), np.float32(0.8294), np.float32(0.7504), np.float32(0.8522), np.float32(0.9508), np.float32(0.2781), np.float32(0.3426)] +2025-11-02 14:45:54.901677: Epoch time: 527.03 s +2025-11-02 14:45:57.048677: +2025-11-02 14:45:57.050879: Epoch 637 +2025-11-02 14:45:57.052753: Current learning rate: 0.00402 +2025-11-02 14:54:36.938207: train_loss -0.4337 +2025-11-02 14:54:36.954219: val_loss -0.4446 +2025-11-02 14:54:36.955999: Pseudo dice [np.float32(0.9299), np.float32(0.7605), np.float32(0.717), np.float32(0.643), np.float32(0.853), np.float32(0.7929), np.float32(0.8349), np.float32(0.8728), np.float32(0.9509), np.float32(0.9524), np.float32(0.9642), np.float32(0.8342), np.float32(0.7821), np.float32(0.849), np.float32(0.9625), np.float32(0.2934), np.float32(0.302)] +2025-11-02 14:54:36.958259: Epoch time: 519.89 s +2025-11-02 14:54:39.012266: +2025-11-02 14:54:39.013730: Epoch 638 +2025-11-02 14:54:39.015367: Current learning rate: 0.00401 +2025-11-02 15:03:27.314328: train_loss -0.4446 +2025-11-02 15:03:27.327615: val_loss -0.447 +2025-11-02 15:03:27.328969: Pseudo dice [np.float32(0.908), np.float32(0.7415), np.float32(0.7225), np.float32(0.6976), np.float32(0.8502), np.float32(0.7863), np.float32(0.8962), np.float32(0.8833), np.float32(0.9612), np.float32(0.9638), np.float32(0.9574), np.float32(0.8299), np.float32(0.8113), np.float32(0.8687), np.float32(0.9366), np.float32(0.3533), np.float32(0.4028)] +2025-11-02 15:03:27.330103: Epoch time: 528.31 s +2025-11-02 15:03:29.562880: +2025-11-02 15:03:29.564839: Epoch 639 +2025-11-02 15:03:29.566522: Current learning rate: 0.004 +2025-11-02 15:12:24.823169: train_loss -0.4383 +2025-11-02 15:12:24.832704: val_loss -0.4448 +2025-11-02 15:12:24.834343: Pseudo dice [np.float32(0.9323), np.float32(0.7942), np.float32(0.7554), np.float32(0.6415), np.float32(0.8506), np.float32(0.8026), np.float32(0.8413), np.float32(0.8866), np.float32(0.9721), np.float32(0.9677), np.float32(0.96), np.float32(0.8457), np.float32(0.7679), np.float32(0.8614), np.float32(0.9536), np.float32(0.2662), np.float32(0.2575)] +2025-11-02 15:12:24.835973: Epoch time: 535.27 s +2025-11-02 15:12:27.153310: +2025-11-02 15:12:27.155036: Epoch 640 +2025-11-02 15:12:27.156060: Current learning rate: 0.00399 +2025-11-02 15:21:11.612216: train_loss -0.4216 +2025-11-02 15:21:11.625741: val_loss -0.4792 +2025-11-02 15:21:11.628868: Pseudo dice [np.float32(0.9493), np.float32(0.7654), np.float32(0.7283), np.float32(0.7079), np.float32(0.8935), np.float32(0.7959), np.float32(0.865), np.float32(0.8901), np.float32(0.9625), np.float32(0.9318), np.float32(0.9572), np.float32(0.8633), np.float32(0.7846), np.float32(0.892), np.float32(0.9613), np.float32(0.2775), np.float32(0.2327)] +2025-11-02 15:21:11.630154: Epoch time: 524.46 s +2025-11-02 15:21:14.409831: +2025-11-02 15:21:14.411432: Epoch 641 +2025-11-02 15:21:14.417197: Current learning rate: 0.00398 +2025-11-02 15:29:54.843092: train_loss -0.4311 +2025-11-02 15:29:54.849484: val_loss -0.4515 +2025-11-02 15:29:54.851104: Pseudo dice [np.float32(0.9397), np.float32(0.761), np.float32(0.7118), np.float32(0.6439), np.float32(0.8657), np.float32(0.7656), np.float32(0.8392), np.float32(0.8867), np.float32(0.9738), np.float32(0.9684), np.float32(0.9697), np.float32(0.8478), np.float32(0.7705), np.float32(0.8777), np.float32(0.9415), np.float32(0.371), np.float32(0.341)] +2025-11-02 15:29:54.852987: Epoch time: 520.44 s +2025-11-02 15:29:57.323327: +2025-11-02 15:29:57.324916: Epoch 642 +2025-11-02 15:29:57.328465: Current learning rate: 0.00397 +2025-11-02 15:38:17.638432: train_loss -0.4211 +2025-11-02 15:38:17.653887: val_loss -0.4234 +2025-11-02 15:38:17.655804: Pseudo dice [np.float32(0.916), np.float32(0.7615), np.float32(0.6812), np.float32(0.6632), np.float32(0.8483), np.float32(0.7647), np.float32(0.8459), np.float32(0.8597), np.float32(0.967), np.float32(0.9705), np.float32(0.9322), np.float32(0.8249), np.float32(0.7916), np.float32(0.8702), np.float32(0.9464), np.float32(0.3669), np.float32(0.2319)] +2025-11-02 15:38:17.657325: Epoch time: 500.32 s +2025-11-02 15:38:19.738384: +2025-11-02 15:38:19.739720: Epoch 643 +2025-11-02 15:38:19.748891: Current learning rate: 0.00396 +2025-11-02 15:47:10.279108: train_loss -0.4328 +2025-11-02 15:47:10.285280: val_loss -0.4354 +2025-11-02 15:47:10.287220: Pseudo dice [np.float32(0.9359), np.float32(0.79), np.float32(0.73), np.float32(0.6825), np.float32(0.8436), np.float32(0.7961), np.float32(0.8845), np.float32(0.8838), np.float32(0.9531), np.float32(0.9679), np.float32(0.9587), np.float32(0.8591), np.float32(0.8026), np.float32(0.8416), np.float32(0.9015), np.float32(0.2639), np.float32(0.1639)] +2025-11-02 15:47:10.289244: Epoch time: 530.55 s +2025-11-02 15:47:12.335376: +2025-11-02 15:47:12.347083: Epoch 644 +2025-11-02 15:47:12.348578: Current learning rate: 0.00395 +2025-11-02 15:55:48.589298: train_loss -0.4238 +2025-11-02 15:55:48.596498: val_loss -0.46 +2025-11-02 15:55:48.600060: Pseudo dice [np.float32(0.923), np.float32(0.7771), np.float32(0.7241), np.float32(0.7066), np.float32(0.8589), np.float32(0.7941), np.float32(0.8872), np.float32(0.8884), np.float32(0.9733), np.float32(0.9754), np.float32(0.9561), np.float32(0.8436), np.float32(0.8023), np.float32(0.8675), np.float32(0.9468), np.float32(0.2723), np.float32(0.3114)] +2025-11-02 15:55:48.608608: Epoch time: 516.26 s +2025-11-02 15:56:12.196220: +2025-11-02 15:56:12.199607: Epoch 645 +2025-11-02 15:56:12.200729: Current learning rate: 0.00394 +2025-11-02 16:04:44.145612: train_loss -0.4244 +2025-11-02 16:04:44.152717: val_loss -0.4533 +2025-11-02 16:04:44.182418: Pseudo dice [np.float32(0.9377), np.float32(0.7601), np.float32(0.7047), np.float32(0.6747), np.float32(0.8639), np.float32(0.7822), np.float32(0.8482), np.float32(0.8908), np.float32(0.9669), np.float32(0.9669), np.float32(0.9654), np.float32(0.8348), np.float32(0.7726), np.float32(0.8793), np.float32(0.9514), np.float32(0.2898), np.float32(0.2908)] +2025-11-02 16:04:44.183934: Epoch time: 511.95 s +2025-11-02 16:04:46.203135: +2025-11-02 16:04:46.204840: Epoch 646 +2025-11-02 16:04:46.206560: Current learning rate: 0.00393 +2025-11-02 16:13:27.098971: train_loss -0.4367 +2025-11-02 16:13:27.105743: val_loss -0.4539 +2025-11-02 16:13:27.107891: Pseudo dice [np.float32(0.9326), np.float32(0.8262), np.float32(0.731), np.float32(0.6436), np.float32(0.8768), np.float32(0.8119), np.float32(0.8905), np.float32(0.8945), np.float32(0.9817), np.float32(0.9816), np.float32(0.9677), np.float32(0.8514), np.float32(0.8124), np.float32(0.864), np.float32(0.9646), np.float32(0.3849), np.float32(0.3567)] +2025-11-02 16:13:27.109862: Epoch time: 520.9 s +2025-11-02 16:13:29.404812: +2025-11-02 16:13:29.410390: Epoch 647 +2025-11-02 16:13:29.411818: Current learning rate: 0.00392 +2025-11-02 16:22:16.482745: train_loss -0.4558 +2025-11-02 16:22:16.489045: val_loss -0.4236 +2025-11-02 16:22:16.492901: Pseudo dice [np.float32(0.8849), np.float32(0.7651), np.float32(0.7412), np.float32(0.675), np.float32(0.8785), np.float32(0.7993), np.float32(0.8326), np.float32(0.8859), np.float32(0.9372), np.float32(0.947), np.float32(0.969), np.float32(0.8559), np.float32(0.8051), np.float32(0.8832), np.float32(0.9093), np.float32(0.2873), np.float32(0.3613)] +2025-11-02 16:22:16.495605: Epoch time: 527.09 s +2025-11-02 16:22:18.543981: +2025-11-02 16:22:18.546011: Epoch 648 +2025-11-02 16:22:18.547394: Current learning rate: 0.00391 +2025-11-02 16:30:58.302328: train_loss -0.455 +2025-11-02 16:30:58.326002: val_loss -0.4537 +2025-11-02 16:30:58.328108: Pseudo dice [np.float32(0.9436), np.float32(0.77), np.float32(0.7444), np.float32(0.6573), np.float32(0.8233), np.float32(0.7647), np.float32(0.868), np.float32(0.8771), np.float32(0.9728), np.float32(0.9549), np.float32(0.9576), np.float32(0.8484), np.float32(0.7969), np.float32(0.8548), np.float32(0.9289), np.float32(0.4096), np.float32(0.4042)] +2025-11-02 16:30:58.337947: Epoch time: 519.76 s +2025-11-02 16:31:00.689064: +2025-11-02 16:31:00.690544: Epoch 649 +2025-11-02 16:31:00.691653: Current learning rate: 0.0039 +2025-11-02 16:39:51.135672: train_loss -0.4363 +2025-11-02 16:39:51.140177: val_loss -0.4585 +2025-11-02 16:39:51.141630: Pseudo dice [np.float32(0.9397), np.float32(0.7575), np.float32(0.7133), np.float32(0.7061), np.float32(0.8785), np.float32(0.796), np.float32(0.9012), np.float32(0.8696), np.float32(0.9461), np.float32(0.9242), np.float32(0.9513), np.float32(0.8443), np.float32(0.7873), np.float32(0.8772), np.float32(0.9321), np.float32(0.4913), np.float32(0.3735)] +2025-11-02 16:39:51.142918: Epoch time: 530.46 s +2025-11-02 16:39:56.074808: Yayy! New best EMA pseudo Dice: 0.7925000190734863 +2025-11-02 16:40:00.627202: +2025-11-02 16:40:00.628601: Epoch 650 +2025-11-02 16:40:00.630054: Current learning rate: 0.00389 +2025-11-02 16:48:24.535114: train_loss -0.4449 +2025-11-02 16:48:24.563829: val_loss -0.4399 +2025-11-02 16:48:24.571189: Pseudo dice [np.float32(0.9363), np.float32(0.5952), np.float32(0.7042), np.float32(0.6474), np.float32(0.8402), np.float32(0.7625), np.float32(0.8692), np.float32(0.8782), np.float32(0.9778), np.float32(0.9764), np.float32(0.9599), np.float32(0.8503), np.float32(0.7568), np.float32(0.8616), np.float32(0.9641), np.float32(0.3509), np.float32(0.287)] +2025-11-02 16:48:24.572634: Epoch time: 503.91 s +2025-11-02 16:48:26.587669: +2025-11-02 16:48:26.589206: Epoch 651 +2025-11-02 16:48:26.593547: Current learning rate: 0.00388 +2025-11-02 16:56:52.792741: train_loss -0.4533 +2025-11-02 16:56:52.797468: val_loss -0.4763 +2025-11-02 16:56:52.799496: Pseudo dice [np.float32(0.935), np.float32(0.7713), np.float32(0.6882), np.float32(0.701), np.float32(0.8722), np.float32(0.8099), np.float32(0.8744), np.float32(0.8861), np.float32(0.983), np.float32(0.9833), np.float32(0.9683), np.float32(0.8602), np.float32(0.7616), np.float32(0.8831), np.float32(0.9683), np.float32(0.2352), np.float32(0.2354)] +2025-11-02 16:56:52.802211: Epoch time: 506.21 s +2025-11-02 16:56:55.075018: +2025-11-02 16:56:55.076215: Epoch 652 +2025-11-02 16:56:55.077316: Current learning rate: 0.00387 +2025-11-02 17:05:38.015832: train_loss -0.4445 +2025-11-02 17:05:38.023999: val_loss -0.4232 +2025-11-02 17:05:38.025431: Pseudo dice [np.float32(0.9344), np.float32(0.717), np.float32(0.6888), np.float32(0.6437), np.float32(0.8427), np.float32(0.8098), np.float32(0.8898), np.float32(0.8876), np.float32(0.9381), np.float32(0.9593), np.float32(0.9637), np.float32(0.8484), np.float32(0.8023), np.float32(0.838), np.float32(0.9603), np.float32(0.3393), np.float32(0.2819)] +2025-11-02 17:05:38.031067: Epoch time: 522.95 s +2025-11-02 17:05:40.366789: +2025-11-02 17:05:40.371265: Epoch 653 +2025-11-02 17:05:40.374107: Current learning rate: 0.00386 +2025-11-02 17:14:01.636040: train_loss -0.4589 +2025-11-02 17:14:01.643536: val_loss -0.4965 +2025-11-02 17:14:01.645714: Pseudo dice [np.float32(0.9249), np.float32(0.7721), np.float32(0.668), np.float32(0.668), np.float32(0.8777), np.float32(0.8085), np.float32(0.9263), np.float32(0.879), np.float32(0.9836), np.float32(0.9811), np.float32(0.9634), np.float32(0.8396), np.float32(0.7833), np.float32(0.8954), np.float32(0.9673), np.float32(0.2276), np.float32(0.197)] +2025-11-02 17:14:01.650241: Epoch time: 501.28 s +2025-11-02 17:14:03.980278: +2025-11-02 17:14:03.990126: Epoch 654 +2025-11-02 17:14:03.991703: Current learning rate: 0.00385 +2025-11-02 17:22:37.607023: train_loss -0.4483 +2025-11-02 17:22:37.614278: val_loss -0.4704 +2025-11-02 17:22:37.616404: Pseudo dice [np.float32(0.9302), np.float32(0.7988), np.float32(0.7371), np.float32(0.6856), np.float32(0.8732), np.float32(0.8051), np.float32(0.9052), np.float32(0.8781), np.float32(0.9722), np.float32(0.9708), np.float32(0.9642), np.float32(0.855), np.float32(0.8118), np.float32(0.8841), np.float32(0.9457), np.float32(0.3584), np.float32(0.3169)] +2025-11-02 17:22:37.617982: Epoch time: 513.63 s +2025-11-02 17:22:39.989629: +2025-11-02 17:22:39.991366: Epoch 655 +2025-11-02 17:22:39.992673: Current learning rate: 0.00384 +2025-11-02 17:31:33.307026: train_loss -0.448 +2025-11-02 17:31:33.314824: val_loss -0.4705 +2025-11-02 17:31:33.318152: Pseudo dice [np.float32(0.9427), np.float32(0.7954), np.float32(0.7683), np.float32(0.7155), np.float32(0.8518), np.float32(0.7532), np.float32(0.8967), np.float32(0.8577), np.float32(0.9441), np.float32(0.9616), np.float32(0.9609), np.float32(0.8542), np.float32(0.8089), np.float32(0.8682), np.float32(0.9291), np.float32(0.285), np.float32(0.2317)] +2025-11-02 17:31:33.320447: Epoch time: 533.32 s +2025-11-02 17:31:35.597530: +2025-11-02 17:31:35.598814: Epoch 656 +2025-11-02 17:31:35.600311: Current learning rate: 0.00383 +2025-11-02 17:40:07.564822: train_loss -0.4458 +2025-11-02 17:40:07.569604: val_loss -0.4369 +2025-11-02 17:40:07.571185: Pseudo dice [np.float32(0.923), np.float32(0.7384), np.float32(0.6734), np.float32(0.6925), np.float32(0.8345), np.float32(0.7857), np.float32(0.8831), np.float32(0.8818), np.float32(0.9691), np.float32(0.974), np.float32(0.9586), np.float32(0.8489), np.float32(0.774), np.float32(0.8697), np.float32(0.9478), np.float32(0.3233), np.float32(0.2899)] +2025-11-02 17:40:07.572442: Epoch time: 511.97 s +2025-11-02 17:40:09.862406: +2025-11-02 17:40:09.866525: Epoch 657 +2025-11-02 17:40:09.867733: Current learning rate: 0.00382 +2025-11-02 17:48:55.077328: train_loss -0.4503 +2025-11-02 17:48:55.083660: val_loss -0.4714 +2025-11-02 17:48:55.085001: Pseudo dice [np.float32(0.9116), np.float32(0.7886), np.float32(0.721), np.float32(0.6249), np.float32(0.886), np.float32(0.7863), np.float32(0.8372), np.float32(0.8883), np.float32(0.9663), np.float32(0.9695), np.float32(0.9652), np.float32(0.8483), np.float32(0.7753), np.float32(0.8817), np.float32(0.9554), np.float32(0.2031), np.float32(0.1138)] +2025-11-02 17:48:55.087040: Epoch time: 525.22 s +2025-11-02 17:48:57.233077: +2025-11-02 17:48:57.236234: Epoch 658 +2025-11-02 17:48:57.239035: Current learning rate: 0.00381 +2025-11-02 17:57:42.875525: train_loss -0.4296 +2025-11-02 17:57:42.880742: val_loss -0.4482 +2025-11-02 17:57:42.882557: Pseudo dice [np.float32(0.9324), np.float32(0.7832), np.float32(0.7332), np.float32(0.565), np.float32(0.8715), np.float32(0.8057), np.float32(0.9128), np.float32(0.8958), np.float32(0.9747), np.float32(0.9756), np.float32(0.9616), np.float32(0.8284), np.float32(0.7471), np.float32(0.8711), np.float32(0.9614), np.float32(0.426), np.float32(0.3956)] +2025-11-02 17:57:42.883731: Epoch time: 525.65 s +2025-11-02 17:57:45.166413: +2025-11-02 17:57:45.180293: Epoch 659 +2025-11-02 17:57:45.181851: Current learning rate: 0.0038 +2025-11-02 18:06:48.721344: train_loss -0.4711 +2025-11-02 18:06:48.728156: val_loss -0.4752 +2025-11-02 18:06:48.730291: Pseudo dice [np.float32(0.9494), np.float32(0.7742), np.float32(0.7299), np.float32(0.6819), np.float32(0.8517), np.float32(0.8081), np.float32(0.8606), np.float32(0.8798), np.float32(0.981), np.float32(0.9778), np.float32(0.9657), np.float32(0.8364), np.float32(0.7856), np.float32(0.8687), np.float32(0.9661), np.float32(0.206), np.float32(0.2293)] +2025-11-02 18:06:48.731805: Epoch time: 543.56 s +2025-11-02 18:06:50.929729: +2025-11-02 18:06:50.934079: Epoch 660 +2025-11-02 18:06:50.936627: Current learning rate: 0.00379 +2025-11-02 18:16:41.990029: train_loss -0.4378 +2025-11-02 18:16:41.998553: val_loss -0.4542 +2025-11-02 18:16:42.012530: Pseudo dice [np.float32(0.9261), np.float32(0.7796), np.float32(0.7425), np.float32(0.7119), np.float32(0.8696), np.float32(0.7882), np.float32(0.883), np.float32(0.8696), np.float32(0.9712), np.float32(0.9753), np.float32(0.9578), np.float32(0.8463), np.float32(0.775), np.float32(0.8488), np.float32(0.9472), np.float32(0.2708), np.float32(0.1964)] +2025-11-02 18:16:42.013730: Epoch time: 591.06 s +2025-11-02 18:16:44.122444: +2025-11-02 18:16:44.124028: Epoch 661 +2025-11-02 18:16:44.125303: Current learning rate: 0.00378 +2025-11-02 18:27:28.279916: train_loss -0.419 +2025-11-02 18:27:28.292677: val_loss -0.4231 +2025-11-02 18:27:28.294015: Pseudo dice [np.float32(0.9382), np.float32(0.3605), np.float32(0.7117), np.float32(0.6997), np.float32(0.8332), np.float32(0.751), np.float32(0.8356), np.float32(0.887), np.float32(0.967), np.float32(0.9787), np.float32(0.9591), np.float32(0.8306), np.float32(0.7643), np.float32(0.851), np.float32(0.966), np.float32(0.4018), np.float32(0.3097)] +2025-11-02 18:27:28.330009: Epoch time: 644.17 s +2025-11-02 18:27:30.492953: +2025-11-02 18:27:30.494380: Epoch 662 +2025-11-02 18:27:30.495687: Current learning rate: 0.00377 +2025-11-02 18:36:55.173653: train_loss -0.4206 +2025-11-02 18:36:55.180218: val_loss -0.4367 +2025-11-02 18:36:55.187392: Pseudo dice [np.float32(0.941), np.float32(0.76), np.float32(0.7059), np.float32(0.679), np.float32(0.8604), np.float32(0.7955), np.float32(0.8141), np.float32(0.888), np.float32(0.947), np.float32(0.9443), np.float32(0.9659), np.float32(0.8106), np.float32(0.7958), np.float32(0.8789), np.float32(0.9145), np.float32(0.3547), np.float32(0.3502)] +2025-11-02 18:36:55.192493: Epoch time: 564.69 s +2025-11-02 18:36:57.248705: +2025-11-02 18:36:57.251185: Epoch 663 +2025-11-02 18:36:57.252591: Current learning rate: 0.00376 +2025-11-02 18:46:49.006528: train_loss -0.4286 +2025-11-02 18:46:49.013979: val_loss -0.459 +2025-11-02 18:46:49.015765: Pseudo dice [np.float32(0.9268), np.float32(0.7409), np.float32(0.5671), np.float32(0.5839), np.float32(0.8583), np.float32(0.7762), np.float32(0.8563), np.float32(0.8674), np.float32(0.9706), np.float32(0.9656), np.float32(0.9634), np.float32(0.8575), np.float32(0.7564), np.float32(0.8647), np.float32(0.9643), np.float32(0.322), np.float32(0.225)] +2025-11-02 18:46:49.017337: Epoch time: 591.77 s +2025-11-02 18:46:51.131839: +2025-11-02 18:46:51.136064: Epoch 664 +2025-11-02 18:46:51.137444: Current learning rate: 0.00375 +2025-11-02 18:56:30.950198: train_loss -0.4365 +2025-11-02 18:56:30.960819: val_loss -0.4479 +2025-11-02 18:56:30.963965: Pseudo dice [np.float32(0.9122), np.float32(0.8124), np.float32(0.7112), np.float32(0.6746), np.float32(0.8302), np.float32(0.7871), np.float32(0.9014), np.float32(0.8762), np.float32(0.9792), np.float32(0.9803), np.float32(0.9656), np.float32(0.8329), np.float32(0.7362), np.float32(0.8677), np.float32(0.9668), np.float32(0.3701), np.float32(0.2498)] +2025-11-02 18:56:30.966532: Epoch time: 579.82 s +2025-11-02 18:56:33.475338: +2025-11-02 18:56:33.477145: Epoch 665 +2025-11-02 18:56:33.479047: Current learning rate: 0.00374 +2025-11-02 19:07:34.522973: train_loss -0.4286 +2025-11-02 19:07:34.530459: val_loss -0.4337 +2025-11-02 19:07:34.533728: Pseudo dice [np.float32(0.9373), np.float32(0.7926), np.float32(0.7255), np.float32(0.6561), np.float32(0.8729), np.float32(0.755), np.float32(0.8713), np.float32(0.8539), np.float32(0.9637), np.float32(0.9436), np.float32(0.9639), np.float32(0.8509), np.float32(0.7776), np.float32(0.8708), np.float32(0.9556), np.float32(0.3474), np.float32(0.2428)] +2025-11-02 19:07:34.535813: Epoch time: 661.06 s +2025-11-02 19:07:36.686232: +2025-11-02 19:07:36.690080: Epoch 666 +2025-11-02 19:07:36.695054: Current learning rate: 0.00373 +2025-11-02 19:17:56.706696: train_loss -0.4408 +2025-11-02 19:17:56.711130: val_loss -0.4089 +2025-11-02 19:17:56.712370: Pseudo dice [np.float32(0.931), np.float32(0.756), np.float32(0.7099), np.float32(0.629), np.float32(0.8509), np.float32(0.7846), np.float32(0.9154), np.float32(0.8767), np.float32(0.9472), np.float32(0.9569), np.float32(0.9627), np.float32(0.8413), np.float32(0.7701), np.float32(0.8849), np.float32(0.926), np.float32(0.3739), np.float32(0.3108)] +2025-11-02 19:17:56.713692: Epoch time: 620.02 s +2025-11-02 19:17:59.089837: +2025-11-02 19:17:59.091311: Epoch 667 +2025-11-02 19:17:59.092768: Current learning rate: 0.00372 +2025-11-02 19:27:12.759209: train_loss -0.4454 +2025-11-02 19:27:12.763861: val_loss -0.4731 +2025-11-02 19:27:12.765262: Pseudo dice [np.float32(0.9449), np.float32(0.7426), np.float32(0.6518), np.float32(0.6642), np.float32(0.8724), np.float32(0.8004), np.float32(0.9178), np.float32(0.8861), np.float32(0.9709), np.float32(0.9719), np.float32(0.9634), np.float32(0.8521), np.float32(0.8129), np.float32(0.8637), np.float32(0.9187), np.float32(0.3476), np.float32(0.3503)] +2025-11-02 19:27:12.766438: Epoch time: 553.68 s +2025-11-02 19:27:15.274841: +2025-11-02 19:27:15.276263: Epoch 668 +2025-11-02 19:27:15.277565: Current learning rate: 0.00371 +2025-11-02 19:36:32.302372: train_loss -0.4569 +2025-11-02 19:36:32.310993: val_loss -0.4943 +2025-11-02 19:36:32.314659: Pseudo dice [np.float32(0.9309), np.float32(0.7822), np.float32(0.7179), np.float32(0.7142), np.float32(0.8959), np.float32(0.7977), np.float32(0.8934), np.float32(0.882), np.float32(0.9685), np.float32(0.9687), np.float32(0.9659), np.float32(0.8398), np.float32(0.7961), np.float32(0.8783), np.float32(0.9486), np.float32(0.3245), np.float32(0.2938)] +2025-11-02 19:36:32.316295: Epoch time: 557.03 s +2025-11-02 19:36:53.569737: +2025-11-02 19:36:53.571060: Epoch 669 +2025-11-02 19:36:53.572506: Current learning rate: 0.0037 +2025-11-02 19:45:41.603376: train_loss -0.4599 +2025-11-02 19:45:41.609761: val_loss -0.4326 +2025-11-02 19:45:41.611772: Pseudo dice [np.float32(0.9316), np.float32(0.7826), np.float32(0.7018), np.float32(0.6751), np.float32(0.8592), np.float32(0.806), np.float32(0.8986), np.float32(0.8822), np.float32(0.9677), np.float32(0.9689), np.float32(0.9374), np.float32(0.847), np.float32(0.7965), np.float32(0.87), np.float32(0.7773), np.float32(0.4275), np.float32(0.3315)] +2025-11-02 19:45:41.613639: Epoch time: 528.04 s +2025-11-02 19:45:44.509042: +2025-11-02 19:45:44.510465: Epoch 670 +2025-11-02 19:45:44.511659: Current learning rate: 0.00369 +2025-11-02 19:55:13.544143: train_loss -0.4397 +2025-11-02 19:55:13.554566: val_loss -0.4938 +2025-11-02 19:55:13.566943: Pseudo dice [np.float32(0.941), np.float32(0.7962), np.float32(0.7504), np.float32(0.649), np.float32(0.8654), np.float32(0.8064), np.float32(0.8675), np.float32(0.8905), np.float32(0.9787), np.float32(0.9752), np.float32(0.9614), np.float32(0.8505), np.float32(0.7996), np.float32(0.8713), np.float32(0.9543), np.float32(0.3243), np.float32(0.2824)] +2025-11-02 19:55:13.568986: Epoch time: 569.04 s +2025-11-02 19:55:15.860613: +2025-11-02 19:55:15.863147: Epoch 671 +2025-11-02 19:55:15.865050: Current learning rate: 0.00368 +2025-11-02 20:04:05.262167: train_loss -0.4403 +2025-11-02 20:04:05.269923: val_loss -0.4569 +2025-11-02 20:04:05.272241: Pseudo dice [np.float32(0.9346), np.float32(0.7151), np.float32(0.7102), np.float32(0.666), np.float32(0.8719), np.float32(0.7772), np.float32(0.87), np.float32(0.8886), np.float32(0.9776), np.float32(0.9761), np.float32(0.9643), np.float32(0.8531), np.float32(0.7946), np.float32(0.8815), np.float32(0.9655), np.float32(0.2875), np.float32(0.3627)] +2025-11-02 20:04:05.273677: Epoch time: 529.41 s +2025-11-02 20:04:07.866102: +2025-11-02 20:04:07.882448: Epoch 672 +2025-11-02 20:04:07.888023: Current learning rate: 0.00367 +2025-11-02 20:13:28.224806: train_loss -0.4479 +2025-11-02 20:13:28.232761: val_loss -0.4387 +2025-11-02 20:13:28.233964: Pseudo dice [np.float32(0.9337), np.float32(0.7051), np.float32(0.6891), np.float32(0.6721), np.float32(0.8808), np.float32(0.8017), np.float32(0.8921), np.float32(0.8712), np.float32(0.971), np.float32(0.9704), np.float32(0.9671), np.float32(0.8572), np.float32(0.7701), np.float32(0.8749), np.float32(0.9478), np.float32(0.2003), np.float32(0.0809)] +2025-11-02 20:13:28.235026: Epoch time: 560.37 s +2025-11-02 20:13:31.049638: +2025-11-02 20:13:31.052948: Epoch 673 +2025-11-02 20:13:31.055823: Current learning rate: 0.00366 +2025-11-02 20:22:27.473107: train_loss -0.4479 +2025-11-02 20:22:27.477578: val_loss -0.4511 +2025-11-02 20:22:27.482261: Pseudo dice [np.float32(0.9378), np.float32(0.778), np.float32(0.7767), np.float32(0.6424), np.float32(0.8563), np.float32(0.8214), np.float32(0.8446), np.float32(0.867), np.float32(0.9646), np.float32(0.9508), np.float32(0.9633), np.float32(0.8447), np.float32(0.7979), np.float32(0.8674), np.float32(0.9571), np.float32(0.4367), np.float32(0.36)] +2025-11-02 20:22:27.483645: Epoch time: 536.5 s +2025-11-02 20:22:29.636369: +2025-11-02 20:22:29.638599: Epoch 674 +2025-11-02 20:22:29.641409: Current learning rate: 0.00365 +2025-11-02 20:31:49.730725: train_loss -0.4405 +2025-11-02 20:31:49.735744: val_loss -0.4856 +2025-11-02 20:31:49.736963: Pseudo dice [np.float32(0.9447), np.float32(0.7755), np.float32(0.7349), np.float32(0.6769), np.float32(0.8749), np.float32(0.7956), np.float32(0.9054), np.float32(0.8852), np.float32(0.9777), np.float32(0.9792), np.float32(0.9538), np.float32(0.8443), np.float32(0.7705), np.float32(0.8661), np.float32(0.8698), np.float32(0.4765), np.float32(0.3303)] +2025-11-02 20:31:49.738377: Epoch time: 560.1 s +2025-11-02 20:31:52.071718: +2025-11-02 20:31:52.073680: Epoch 675 +2025-11-02 20:31:52.080686: Current learning rate: 0.00364 +2025-11-02 20:41:09.095098: train_loss -0.4532 +2025-11-02 20:41:09.110019: val_loss -0.457 +2025-11-02 20:41:09.111549: Pseudo dice [np.float32(0.9285), np.float32(0.7461), np.float32(0.7394), np.float32(0.6147), np.float32(0.8752), np.float32(0.7467), np.float32(0.8947), np.float32(0.8811), np.float32(0.9745), np.float32(0.9678), np.float32(0.9661), np.float32(0.8653), np.float32(0.811), np.float32(0.8612), np.float32(0.9431), np.float32(0.1749), np.float32(0.1546)] +2025-11-02 20:41:09.119696: Epoch time: 557.03 s +2025-11-02 20:41:11.269661: +2025-11-02 20:41:11.271165: Epoch 676 +2025-11-02 20:41:11.272300: Current learning rate: 0.00363 +2025-11-02 20:51:10.793106: train_loss -0.4411 +2025-11-02 20:51:10.801738: val_loss -0.4643 +2025-11-02 20:51:10.805292: Pseudo dice [np.float32(0.9267), np.float32(0.7911), np.float32(0.7617), np.float32(0.7189), np.float32(0.8477), np.float32(0.7999), np.float32(0.8828), np.float32(0.8752), np.float32(0.9673), np.float32(0.9622), np.float32(0.9664), np.float32(0.8612), np.float32(0.799), np.float32(0.8641), np.float32(0.9668), np.float32(0.1928), np.float32(0.284)] +2025-11-02 20:51:10.806467: Epoch time: 599.53 s +2025-11-02 20:51:13.032767: +2025-11-02 20:51:13.034866: Epoch 677 +2025-11-02 20:51:13.036363: Current learning rate: 0.00362 +2025-11-02 21:01:15.560978: train_loss -0.4576 +2025-11-02 21:01:15.570490: val_loss -0.4648 +2025-11-02 21:01:15.571836: Pseudo dice [np.float32(0.9393), np.float32(0.7769), np.float32(0.6889), np.float32(0.6625), np.float32(0.8466), np.float32(0.7965), np.float32(0.8689), np.float32(0.8709), np.float32(0.9806), np.float32(0.9783), np.float32(0.9664), np.float32(0.8532), np.float32(0.791), np.float32(0.8639), np.float32(0.9733), np.float32(0.2721), np.float32(0.1837)] +2025-11-02 21:01:15.573901: Epoch time: 602.54 s +2025-11-02 21:01:17.867696: +2025-11-02 21:01:17.869214: Epoch 678 +2025-11-02 21:01:17.873539: Current learning rate: 0.00361 +2025-11-02 21:11:10.458253: train_loss -0.4508 +2025-11-02 21:11:10.467920: val_loss -0.4622 +2025-11-02 21:11:10.469657: Pseudo dice [np.float32(0.9379), np.float32(0.7706), np.float32(0.6927), np.float32(0.6602), np.float32(0.8444), np.float32(0.7946), np.float32(0.8802), np.float32(0.8609), np.float32(0.9724), np.float32(0.9707), np.float32(0.9656), np.float32(0.8651), np.float32(0.7793), np.float32(0.8534), np.float32(0.9635), np.float32(0.2984), np.float32(0.2788)] +2025-11-02 21:11:10.473944: Epoch time: 592.59 s +2025-11-02 21:11:13.101941: +2025-11-02 21:11:13.103755: Epoch 679 +2025-11-02 21:11:13.105345: Current learning rate: 0.0036 +2025-11-02 21:20:37.220168: train_loss -0.4656 +2025-11-02 21:20:37.225657: val_loss -0.4333 +2025-11-02 21:20:37.227018: Pseudo dice [np.float32(0.9043), np.float32(0.7717), np.float32(0.7126), np.float32(0.6138), np.float32(0.8589), np.float32(0.7831), np.float32(0.8795), np.float32(0.8921), np.float32(0.968), np.float32(0.9717), np.float32(0.9641), np.float32(0.8642), np.float32(0.7818), np.float32(0.8546), np.float32(0.9572), np.float32(0.2035), np.float32(0.2554)] +2025-11-02 21:20:37.228750: Epoch time: 564.13 s +2025-11-02 21:20:39.555537: +2025-11-02 21:20:39.558083: Epoch 680 +2025-11-02 21:20:39.562385: Current learning rate: 0.00359 +2025-11-02 21:30:11.601281: train_loss -0.4451 +2025-11-02 21:30:11.607415: val_loss -0.5052 +2025-11-02 21:30:11.609190: Pseudo dice [np.float32(0.9343), np.float32(0.8068), np.float32(0.7215), np.float32(0.68), np.float32(0.8937), np.float32(0.7949), np.float32(0.8852), np.float32(0.8845), np.float32(0.9822), np.float32(0.9837), np.float32(0.9715), np.float32(0.8453), np.float32(0.794), np.float32(0.874), np.float32(0.968), np.float32(0.2869), np.float32(0.28)] +2025-11-02 21:30:11.610594: Epoch time: 572.06 s +2025-11-02 21:30:14.013366: +2025-11-02 21:30:14.014951: Epoch 681 +2025-11-02 21:30:14.016249: Current learning rate: 0.00358 +2025-11-02 21:39:23.597735: train_loss -0.4677 +2025-11-02 21:39:23.606133: val_loss -0.4742 +2025-11-02 21:39:23.607803: Pseudo dice [np.float32(0.921), np.float32(0.7848), np.float32(0.7684), np.float32(0.6359), np.float32(0.8935), np.float32(0.8067), np.float32(0.7998), np.float32(0.8935), np.float32(0.9781), np.float32(0.9701), np.float32(0.9613), np.float32(0.8684), np.float32(0.8112), np.float32(0.8824), np.float32(0.9672), np.float32(0.2746), np.float32(0.201)] +2025-11-02 21:39:23.609728: Epoch time: 549.59 s +2025-11-02 21:39:25.989414: +2025-11-02 21:39:25.998324: Epoch 682 +2025-11-02 21:39:26.000241: Current learning rate: 0.00357 +2025-11-02 21:48:46.384167: train_loss -0.428 +2025-11-02 21:48:46.390851: val_loss -0.4832 +2025-11-02 21:48:46.393110: Pseudo dice [np.float32(0.9369), np.float32(0.7013), np.float32(0.7308), np.float32(0.7049), np.float32(0.845), np.float32(0.8091), np.float32(0.8491), np.float32(0.8929), np.float32(0.9477), np.float32(0.9484), np.float32(0.9694), np.float32(0.845), np.float32(0.8078), np.float32(0.8726), np.float32(0.9651), np.float32(0.4652), np.float32(0.2727)] +2025-11-02 21:48:46.394828: Epoch time: 560.4 s +2025-11-02 21:48:49.454736: +2025-11-02 21:48:49.458210: Epoch 683 +2025-11-02 21:48:49.461440: Current learning rate: 0.00356 +2025-11-02 21:58:14.011641: train_loss -0.4505 +2025-11-02 21:58:14.018042: val_loss -0.4403 +2025-11-02 21:58:14.022688: Pseudo dice [np.float32(0.9282), np.float32(0.7625), np.float32(0.6987), np.float32(0.6417), np.float32(0.8478), np.float32(0.8198), np.float32(0.8126), np.float32(0.8863), np.float32(0.9561), np.float32(0.9591), np.float32(0.9644), np.float32(0.8446), np.float32(0.812), np.float32(0.8502), np.float32(0.9476), np.float32(0.4343), np.float32(0.2905)] +2025-11-02 21:58:14.025251: Epoch time: 564.6 s +2025-11-02 21:58:16.155288: +2025-11-02 21:58:16.157452: Epoch 684 +2025-11-02 21:58:16.159292: Current learning rate: 0.00355 +2025-11-02 22:07:17.334706: train_loss -0.4589 +2025-11-02 22:07:17.347960: val_loss -0.4536 +2025-11-02 22:07:17.358759: Pseudo dice [np.float32(0.9341), np.float32(0.6488), np.float32(0.7363), np.float32(0.6644), np.float32(0.8711), np.float32(0.7925), np.float32(0.9162), np.float32(0.8849), np.float32(0.9751), np.float32(0.9802), np.float32(0.9656), np.float32(0.8497), np.float32(0.7573), np.float32(0.8654), np.float32(0.9608), np.float32(0.2472), np.float32(0.2367)] +2025-11-02 22:07:17.360522: Epoch time: 541.18 s +2025-11-02 22:07:19.705582: +2025-11-02 22:07:19.711658: Epoch 685 +2025-11-02 22:07:19.716464: Current learning rate: 0.00354 +2025-11-02 22:16:16.647928: train_loss -0.4367 +2025-11-02 22:16:16.652463: val_loss -0.4975 +2025-11-02 22:16:16.653904: Pseudo dice [np.float32(0.8942), np.float32(0.7619), np.float32(0.7413), np.float32(0.6561), np.float32(0.8848), np.float32(0.7794), np.float32(0.8985), np.float32(0.8894), np.float32(0.9763), np.float32(0.9768), np.float32(0.9676), np.float32(0.8541), np.float32(0.7948), np.float32(0.8904), np.float32(0.96), np.float32(0.3708), np.float32(0.3991)] +2025-11-02 22:16:16.659324: Epoch time: 536.95 s +2025-11-02 22:16:18.823550: +2025-11-02 22:16:18.826330: Epoch 686 +2025-11-02 22:16:18.827756: Current learning rate: 0.00353 +2025-11-02 22:25:41.334765: train_loss -0.4512 +2025-11-02 22:25:41.342229: val_loss -0.4028 +2025-11-02 22:25:41.347086: Pseudo dice [np.float32(0.9437), np.float32(0.731), np.float32(0.7249), np.float32(0.6076), np.float32(0.8561), np.float32(0.7658), np.float32(0.8616), np.float32(0.8738), np.float32(0.9745), np.float32(0.8645), np.float32(0.9474), np.float32(0.8424), np.float32(0.7607), np.float32(0.8734), np.float32(0.9642), np.float32(0.2733), np.float32(0.2227)] +2025-11-02 22:25:41.348473: Epoch time: 562.52 s +2025-11-02 22:25:43.729302: +2025-11-02 22:25:43.745823: Epoch 687 +2025-11-02 22:25:43.748078: Current learning rate: 0.00352 +2025-11-02 22:35:19.359734: train_loss -0.4445 +2025-11-02 22:35:19.372152: val_loss -0.4783 +2025-11-02 22:35:19.378878: Pseudo dice [np.float32(0.9296), np.float32(0.7992), np.float32(0.7607), np.float32(0.6333), np.float32(0.8556), np.float32(0.81), np.float32(0.8602), np.float32(0.8722), np.float32(0.9658), np.float32(0.9754), np.float32(0.96), np.float32(0.8418), np.float32(0.807), np.float32(0.8746), np.float32(0.9588), np.float32(0.3279), np.float32(0.3451)] +2025-11-02 22:35:19.386827: Epoch time: 575.64 s +2025-11-02 22:35:21.686106: +2025-11-02 22:35:21.689558: Epoch 688 +2025-11-02 22:35:21.693991: Current learning rate: 0.00351 +2025-11-02 22:45:17.625413: train_loss -0.4317 +2025-11-02 22:45:17.632846: val_loss -0.4325 +2025-11-02 22:45:17.634143: Pseudo dice [np.float32(0.9297), np.float32(0.7532), np.float32(0.6899), np.float32(0.6491), np.float32(0.8631), np.float32(0.7912), np.float32(0.8601), np.float32(0.8818), np.float32(0.9689), np.float32(0.9685), np.float32(0.9614), np.float32(0.844), np.float32(0.7957), np.float32(0.8658), np.float32(0.9329), np.float32(0.346), np.float32(0.2385)] +2025-11-02 22:45:17.635214: Epoch time: 595.94 s +2025-11-02 22:45:19.995664: +2025-11-02 22:45:19.997319: Epoch 689 +2025-11-02 22:45:19.998463: Current learning rate: 0.0035 +2025-11-02 22:54:55.225104: train_loss -0.4508 +2025-11-02 22:54:55.246646: val_loss -0.4647 +2025-11-02 22:54:55.248007: Pseudo dice [np.float32(0.9286), np.float32(0.7893), np.float32(0.7218), np.float32(0.6992), np.float32(0.8507), np.float32(0.8113), np.float32(0.9083), np.float32(0.9001), np.float32(0.96), np.float32(0.9718), np.float32(0.9667), np.float32(0.846), np.float32(0.7697), np.float32(0.857), np.float32(0.9476), np.float32(0.423), np.float32(0.3306)] +2025-11-02 22:54:55.249171: Epoch time: 575.23 s +2025-11-02 22:54:57.602420: +2025-11-02 22:54:57.603964: Epoch 690 +2025-11-02 22:54:57.606021: Current learning rate: 0.00349 +2025-11-02 23:04:18.058294: train_loss -0.4517 +2025-11-02 23:04:18.062496: val_loss -0.4478 +2025-11-02 23:04:18.064047: Pseudo dice [np.float32(0.92), np.float32(0.794), np.float32(0.7525), np.float32(0.5976), np.float32(0.883), np.float32(0.8196), np.float32(0.785), np.float32(0.8841), np.float32(0.9706), np.float32(0.9729), np.float32(0.9672), np.float32(0.8549), np.float32(0.7603), np.float32(0.8953), np.float32(0.9682), np.float32(0.4064), np.float32(0.3208)] +2025-11-02 23:04:18.065103: Epoch time: 560.46 s +2025-11-02 23:04:20.308494: +2025-11-02 23:04:20.311101: Epoch 691 +2025-11-02 23:04:20.313012: Current learning rate: 0.00348 +2025-11-02 23:13:17.891962: train_loss -0.4494 +2025-11-02 23:13:17.901279: val_loss -0.4404 +2025-11-02 23:13:17.902972: Pseudo dice [np.float32(0.9112), np.float32(0.7791), np.float32(0.6744), np.float32(0.6829), np.float32(0.8454), np.float32(0.7973), np.float32(0.9072), np.float32(0.8777), np.float32(0.9808), np.float32(0.9709), np.float32(0.9588), np.float32(0.8439), np.float32(0.8126), np.float32(0.8602), np.float32(0.9674), np.float32(0.3143), np.float32(0.4028)] +2025-11-02 23:13:17.907879: Epoch time: 537.59 s +2025-11-02 23:13:20.124060: +2025-11-02 23:13:20.126143: Epoch 692 +2025-11-02 23:13:20.128211: Current learning rate: 0.00346 +2025-11-02 23:22:14.774416: train_loss -0.4474 +2025-11-02 23:22:14.779530: val_loss -0.4276 +2025-11-02 23:22:14.780708: Pseudo dice [np.float32(0.945), np.float32(0.7985), np.float32(0.7422), np.float32(0.642), np.float32(0.8529), np.float32(0.7677), np.float32(0.8371), np.float32(0.8755), np.float32(0.9755), np.float32(0.9703), np.float32(0.9646), np.float32(0.8601), np.float32(0.7571), np.float32(0.8628), np.float32(0.9634), np.float32(0.157), np.float32(0.2959)] +2025-11-02 23:22:14.781916: Epoch time: 534.66 s +2025-11-02 23:22:16.805211: +2025-11-02 23:22:16.814639: Epoch 693 +2025-11-02 23:22:16.816430: Current learning rate: 0.00345 +2025-11-02 23:30:50.288726: train_loss -0.4597 +2025-11-02 23:30:50.293616: val_loss -0.4358 +2025-11-02 23:30:50.295192: Pseudo dice [np.float32(0.9072), np.float32(0.7214), np.float32(0.6771), np.float32(0.6931), np.float32(0.8777), np.float32(0.7757), np.float32(0.8346), np.float32(0.8769), np.float32(0.9716), np.float32(0.9733), np.float32(0.968), np.float32(0.8393), np.float32(0.7571), np.float32(0.8775), np.float32(0.9683), np.float32(0.0905), np.float32(0.2924)] +2025-11-02 23:30:50.300103: Epoch time: 513.49 s +2025-11-02 23:30:52.306042: +2025-11-02 23:30:52.307493: Epoch 694 +2025-11-02 23:30:52.308729: Current learning rate: 0.00344 +2025-11-02 23:39:30.264196: train_loss -0.4464 +2025-11-02 23:39:30.276046: val_loss -0.4164 +2025-11-02 23:39:30.280772: Pseudo dice [np.float32(0.9055), np.float32(0.7922), np.float32(0.7158), np.float32(0.5719), np.float32(0.8443), np.float32(0.7536), np.float32(0.8636), np.float32(0.8839), np.float32(0.9583), np.float32(0.9675), np.float32(0.9662), np.float32(0.8519), np.float32(0.7721), np.float32(0.8542), np.float32(0.9685), np.float32(0.3131), np.float32(0.2027)] +2025-11-02 23:39:30.283936: Epoch time: 517.96 s +2025-11-02 23:39:32.246286: +2025-11-02 23:39:32.248278: Epoch 695 +2025-11-02 23:39:32.249661: Current learning rate: 0.00343 +2025-11-02 23:48:02.836060: train_loss -0.4459 +2025-11-02 23:48:02.843659: val_loss -0.4644 +2025-11-02 23:48:02.844941: Pseudo dice [np.float32(0.9417), np.float32(0.7758), np.float32(0.7605), np.float32(0.7302), np.float32(0.8684), np.float32(0.7905), np.float32(0.8028), np.float32(0.89), np.float32(0.9365), np.float32(0.9349), np.float32(0.9565), np.float32(0.8428), np.float32(0.7945), np.float32(0.8737), np.float32(0.9053), np.float32(0.2982), np.float32(0.3454)] +2025-11-02 23:48:02.846152: Epoch time: 510.59 s +2025-11-02 23:48:04.874311: +2025-11-02 23:48:04.876071: Epoch 696 +2025-11-02 23:48:04.877621: Current learning rate: 0.00342 +2025-11-02 23:56:37.800103: train_loss -0.449 +2025-11-02 23:56:37.804282: val_loss -0.3954 +2025-11-02 23:56:37.805472: Pseudo dice [np.float32(0.9022), np.float32(0.7598), np.float32(0.6761), np.float32(0.6431), np.float32(0.8661), np.float32(0.792), np.float32(0.8844), np.float32(0.8603), np.float32(0.9608), np.float32(0.9693), np.float32(0.9622), np.float32(0.8397), np.float32(0.7685), np.float32(0.863), np.float32(0.9589), np.float32(0.2866), np.float32(0.2132)] +2025-11-02 23:56:37.806559: Epoch time: 512.93 s +2025-11-02 23:56:39.841645: +2025-11-02 23:56:39.844379: Epoch 697 +2025-11-02 23:56:39.846878: Current learning rate: 0.00341 +2025-11-03 00:05:10.332335: train_loss -0.4361 +2025-11-03 00:05:10.341019: val_loss -0.4582 +2025-11-03 00:05:10.342659: Pseudo dice [np.float32(0.936), np.float32(0.7742), np.float32(0.6869), np.float32(0.7108), np.float32(0.8746), np.float32(0.7642), np.float32(0.8309), np.float32(0.8758), np.float32(0.9624), np.float32(0.9501), np.float32(0.9598), np.float32(0.8441), np.float32(0.8053), np.float32(0.8799), np.float32(0.9428), np.float32(0.1834), np.float32(0.2938)] +2025-11-03 00:05:10.344017: Epoch time: 510.5 s +2025-11-03 00:05:12.346402: +2025-11-03 00:05:12.347901: Epoch 698 +2025-11-03 00:05:12.349051: Current learning rate: 0.0034 +2025-11-03 00:13:49.709772: train_loss -0.4458 +2025-11-03 00:13:49.717880: val_loss -0.4797 +2025-11-03 00:13:49.719092: Pseudo dice [np.float32(0.9344), np.float32(0.7541), np.float32(0.7442), np.float32(0.6372), np.float32(0.8644), np.float32(0.7855), np.float32(0.8132), np.float32(0.8764), np.float32(0.971), np.float32(0.9713), np.float32(0.9634), np.float32(0.8546), np.float32(0.7814), np.float32(0.8669), np.float32(0.8993), np.float32(0.3239), np.float32(0.3143)] +2025-11-03 00:13:49.720268: Epoch time: 517.37 s +2025-11-03 00:13:51.936827: +2025-11-03 00:13:51.941281: Epoch 699 +2025-11-03 00:13:51.942937: Current learning rate: 0.00339 +2025-11-03 00:22:14.581262: train_loss -0.4635 +2025-11-03 00:22:14.591579: val_loss -0.5122 +2025-11-03 00:22:14.593351: Pseudo dice [np.float32(0.9428), np.float32(0.7785), np.float32(0.74), np.float32(0.747), np.float32(0.8627), np.float32(0.8249), np.float32(0.8992), np.float32(0.8804), np.float32(0.9617), np.float32(0.9614), np.float32(0.9661), np.float32(0.8398), np.float32(0.8128), np.float32(0.881), np.float32(0.967), np.float32(0.4225), np.float32(0.3998)] +2025-11-03 00:22:14.595059: Epoch time: 502.65 s +2025-11-03 00:22:20.872058: +2025-11-03 00:22:20.885455: Epoch 700 +2025-11-03 00:22:20.892069: Current learning rate: 0.00338 +2025-11-03 00:31:00.273175: train_loss -0.4522 +2025-11-03 00:31:00.283491: val_loss -0.4449 +2025-11-03 00:31:00.285730: Pseudo dice [np.float32(0.9221), np.float32(0.7777), np.float32(0.7389), np.float32(0.581), np.float32(0.8661), np.float32(0.8211), np.float32(0.8969), np.float32(0.8987), np.float32(0.9098), np.float32(0.9241), np.float32(0.9677), np.float32(0.8422), np.float32(0.7982), np.float32(0.8747), np.float32(0.957), np.float32(0.4657), np.float32(0.384)] +2025-11-03 00:31:00.286762: Epoch time: 519.41 s +2025-11-03 00:31:02.463801: +2025-11-03 00:31:02.467439: Epoch 701 +2025-11-03 00:31:02.471918: Current learning rate: 0.00337 +2025-11-03 00:39:35.466606: train_loss -0.462 +2025-11-03 00:39:35.476153: val_loss -0.4909 +2025-11-03 00:39:35.478452: Pseudo dice [np.float32(0.929), np.float32(0.8054), np.float32(0.7637), np.float32(0.6972), np.float32(0.8656), np.float32(0.7772), np.float32(0.8924), np.float32(0.8904), np.float32(0.9807), np.float32(0.9823), np.float32(0.9682), np.float32(0.8643), np.float32(0.7896), np.float32(0.8539), np.float32(0.9608), np.float32(0.3359), np.float32(0.3245)] +2025-11-03 00:39:35.484122: Epoch time: 513.01 s +2025-11-03 00:39:37.550257: +2025-11-03 00:39:37.551435: Epoch 702 +2025-11-03 00:39:37.552735: Current learning rate: 0.00336 +2025-11-03 00:48:17.595065: train_loss -0.476 +2025-11-03 00:48:17.601104: val_loss -0.4547 +2025-11-03 00:48:17.602567: Pseudo dice [np.float32(0.9065), np.float32(0.7785), np.float32(0.7377), np.float32(0.6879), np.float32(0.8606), np.float32(0.8093), np.float32(0.8942), np.float32(0.898), np.float32(0.9787), np.float32(0.9806), np.float32(0.9725), np.float32(0.8488), np.float32(0.7801), np.float32(0.8751), np.float32(0.9641), np.float32(0.5573), np.float32(0.4321)] +2025-11-03 00:48:17.604172: Epoch time: 520.05 s +2025-11-03 00:48:17.605289: Yayy! New best EMA pseudo Dice: 0.7949000000953674 +2025-11-03 00:48:23.665418: +2025-11-03 00:48:23.666747: Epoch 703 +2025-11-03 00:48:23.668645: Current learning rate: 0.00335 +2025-11-03 00:56:45.220083: train_loss -0.4657 +2025-11-03 00:56:45.256584: val_loss -0.4248 +2025-11-03 00:56:45.258756: Pseudo dice [np.float32(0.9298), np.float32(0.7836), np.float32(0.7341), np.float32(0.677), np.float32(0.8777), np.float32(0.8347), np.float32(0.8798), np.float32(0.8681), np.float32(0.9218), np.float32(0.9714), np.float32(0.9628), np.float32(0.8439), np.float32(0.7804), np.float32(0.8738), np.float32(0.9621), np.float32(0.3518), np.float32(0.2727)] +2025-11-03 00:56:45.261111: Epoch time: 501.56 s +2025-11-03 00:56:45.267842: Yayy! New best EMA pseudo Dice: 0.7949000000953674 +2025-11-03 00:56:49.917878: +2025-11-03 00:56:49.920089: Epoch 704 +2025-11-03 00:56:49.921477: Current learning rate: 0.00334 +2025-11-03 01:05:23.427950: train_loss -0.4386 +2025-11-03 01:05:23.433459: val_loss -0.4359 +2025-11-03 01:05:23.435256: Pseudo dice [np.float32(0.9295), np.float32(0.7639), np.float32(0.7192), np.float32(0.6539), np.float32(0.869), np.float32(0.8025), np.float32(0.8801), np.float32(0.9029), np.float32(0.9695), np.float32(0.9688), np.float32(0.963), np.float32(0.828), np.float32(0.8138), np.float32(0.8706), np.float32(0.9598), np.float32(0.3536), np.float32(0.3471)] +2025-11-03 01:05:23.436882: Epoch time: 513.51 s +2025-11-03 01:05:23.438761: Yayy! New best EMA pseudo Dice: 0.7954000234603882 +2025-11-03 01:05:28.005960: +2025-11-03 01:05:28.009904: Epoch 705 +2025-11-03 01:05:28.011465: Current learning rate: 0.00333 +2025-11-03 01:14:10.907410: train_loss -0.4458 +2025-11-03 01:14:10.912858: val_loss -0.4432 +2025-11-03 01:14:10.914519: Pseudo dice [np.float32(0.9259), np.float32(0.3998), np.float32(0.7062), np.float32(0.6855), np.float32(0.8573), np.float32(0.7908), np.float32(0.8623), np.float32(0.8754), np.float32(0.9526), np.float32(0.9742), np.float32(0.9666), np.float32(0.8146), np.float32(0.8207), np.float32(0.8804), np.float32(0.9259), np.float32(0.2623), np.float32(0.2539)] +2025-11-03 01:14:10.916223: Epoch time: 522.91 s +2025-11-03 01:14:13.056987: +2025-11-03 01:14:13.061486: Epoch 706 +2025-11-03 01:14:13.064056: Current learning rate: 0.00332 +2025-11-03 01:22:39.485419: train_loss -0.4519 +2025-11-03 01:22:39.491323: val_loss -0.4697 +2025-11-03 01:22:39.493589: Pseudo dice [np.float32(0.9344), np.float32(0.7744), np.float32(0.7113), np.float32(0.6222), np.float32(0.8817), np.float32(0.7738), np.float32(0.8934), np.float32(0.8799), np.float32(0.9622), np.float32(0.962), np.float32(0.9638), np.float32(0.8417), np.float32(0.7828), np.float32(0.863), np.float32(0.9627), np.float32(0.4706), np.float32(0.4634)] +2025-11-03 01:22:39.495191: Epoch time: 506.43 s +2025-11-03 01:22:41.580620: +2025-11-03 01:22:41.590967: Epoch 707 +2025-11-03 01:22:41.592177: Current learning rate: 0.00331 +2025-11-03 01:31:07.098180: train_loss -0.4588 +2025-11-03 01:31:07.102721: val_loss -0.4575 +2025-11-03 01:31:07.110046: Pseudo dice [np.float32(0.9193), np.float32(0.7801), np.float32(0.734), np.float32(0.654), np.float32(0.8456), np.float32(0.7885), np.float32(0.8989), np.float32(0.8799), np.float32(0.9591), np.float32(0.9619), np.float32(0.9692), np.float32(0.8521), np.float32(0.7924), np.float32(0.8552), np.float32(0.9674), np.float32(0.4473), np.float32(0.374)] +2025-11-03 01:31:07.111416: Epoch time: 505.52 s +2025-11-03 01:31:09.122974: +2025-11-03 01:31:09.136496: Epoch 708 +2025-11-03 01:31:09.137779: Current learning rate: 0.0033 +2025-11-03 01:39:45.137215: train_loss -0.459 +2025-11-03 01:39:45.144206: val_loss -0.4812 +2025-11-03 01:39:45.146232: Pseudo dice [np.float32(0.9226), np.float32(0.7683), np.float32(0.6926), np.float32(0.6312), np.float32(0.8601), np.float32(0.7758), np.float32(0.9185), np.float32(0.8901), np.float32(0.9779), np.float32(0.9762), np.float32(0.9647), np.float32(0.861), np.float32(0.7912), np.float32(0.8764), np.float32(0.9688), np.float32(0.2833), np.float32(0.2971)] +2025-11-03 01:39:45.148125: Epoch time: 516.02 s +2025-11-03 01:39:47.231948: +2025-11-03 01:39:47.233294: Epoch 709 +2025-11-03 01:39:47.234570: Current learning rate: 0.00329 +2025-11-03 01:48:12.632248: train_loss -0.4658 +2025-11-03 01:48:12.638334: val_loss -0.4644 +2025-11-03 01:48:12.640157: Pseudo dice [np.float32(0.9354), np.float32(0.7459), np.float32(0.7283), np.float32(0.6281), np.float32(0.8616), np.float32(0.7798), np.float32(0.8919), np.float32(0.894), np.float32(0.9788), np.float32(0.9826), np.float32(0.9666), np.float32(0.8485), np.float32(0.7664), np.float32(0.8566), np.float32(0.9647), np.float32(0.3584), np.float32(0.3401)] +2025-11-03 01:48:12.642012: Epoch time: 505.4 s +2025-11-03 01:48:14.712962: +2025-11-03 01:48:14.719582: Epoch 710 +2025-11-03 01:48:14.721581: Current learning rate: 0.00328 +2025-11-03 01:56:47.695299: train_loss -0.4384 +2025-11-03 01:56:47.700486: val_loss -0.4582 +2025-11-03 01:56:47.701780: Pseudo dice [np.float32(0.9374), np.float32(0.7575), np.float32(0.7026), np.float32(0.6684), np.float32(0.8574), np.float32(0.8223), np.float32(0.8904), np.float32(0.8727), np.float32(0.9712), np.float32(0.9747), np.float32(0.9697), np.float32(0.8319), np.float32(0.7903), np.float32(0.8634), np.float32(0.9614), np.float32(0.3608), np.float32(0.2407)] +2025-11-03 01:56:47.703527: Epoch time: 512.99 s +2025-11-03 01:56:49.792133: +2025-11-03 01:56:49.796986: Epoch 711 +2025-11-03 01:56:49.798536: Current learning rate: 0.00327 +2025-11-03 02:05:25.638147: train_loss -0.4413 +2025-11-03 02:05:25.650122: val_loss -0.4431 +2025-11-03 02:05:25.651972: Pseudo dice [np.float32(0.9192), np.float32(0.7826), np.float32(0.7212), np.float32(0.6541), np.float32(0.8605), np.float32(0.7272), np.float32(0.8592), np.float32(0.8726), np.float32(0.9835), np.float32(0.9835), np.float32(0.9662), np.float32(0.8369), np.float32(0.7567), np.float32(0.8688), np.float32(0.9621), np.float32(0.128), np.float32(0.1253)] +2025-11-03 02:05:25.653234: Epoch time: 515.85 s +2025-11-03 02:05:27.980601: +2025-11-03 02:05:27.983234: Epoch 712 +2025-11-03 02:05:27.984406: Current learning rate: 0.00326 +2025-11-03 02:13:58.162289: train_loss -0.4585 +2025-11-03 02:13:58.171025: val_loss -0.488 +2025-11-03 02:13:58.173058: Pseudo dice [np.float32(0.9365), np.float32(0.7808), np.float32(0.7037), np.float32(0.7088), np.float32(0.8363), np.float32(0.7843), np.float32(0.8694), np.float32(0.8866), np.float32(0.9546), np.float32(0.9566), np.float32(0.9665), np.float32(0.862), np.float32(0.8038), np.float32(0.8589), np.float32(0.9648), np.float32(0.2691), np.float32(0.3307)] +2025-11-03 02:13:58.175064: Epoch time: 510.19 s +2025-11-03 02:14:00.275277: +2025-11-03 02:14:00.276751: Epoch 713 +2025-11-03 02:14:00.277953: Current learning rate: 0.00325 +2025-11-03 02:22:35.398740: train_loss -0.4483 +2025-11-03 02:22:35.406171: val_loss -0.448 +2025-11-03 02:22:35.408102: Pseudo dice [np.float32(0.9162), np.float32(0.7858), np.float32(0.7432), np.float32(0.6958), np.float32(0.863), np.float32(0.7855), np.float32(0.893), np.float32(0.8863), np.float32(0.9435), np.float32(0.9446), np.float32(0.9676), np.float32(0.8284), np.float32(0.7906), np.float32(0.877), np.float32(0.9446), np.float32(0.3021), np.float32(0.2968)] +2025-11-03 02:22:35.416063: Epoch time: 515.13 s +2025-11-03 02:22:37.458783: +2025-11-03 02:22:37.459972: Epoch 714 +2025-11-03 02:22:37.461160: Current learning rate: 0.00324 +2025-11-03 02:31:26.165355: train_loss -0.4343 +2025-11-03 02:31:26.190094: val_loss -0.4672 +2025-11-03 02:31:26.192076: Pseudo dice [np.float32(0.9344), np.float32(0.7958), np.float32(0.7111), np.float32(0.6122), np.float32(0.8581), np.float32(0.8083), np.float32(0.9003), np.float32(0.8822), np.float32(0.9765), np.float32(0.9767), np.float32(0.9591), np.float32(0.8635), np.float32(0.7637), np.float32(0.8549), np.float32(0.9628), np.float32(0.4003), np.float32(0.3852)] +2025-11-03 02:31:26.199261: Epoch time: 528.71 s +2025-11-03 02:31:28.332650: +2025-11-03 02:31:28.338755: Epoch 715 +2025-11-03 02:31:28.342909: Current learning rate: 0.00323 +2025-11-03 02:40:01.903976: train_loss -0.4403 +2025-11-03 02:40:01.909542: val_loss -0.4452 +2025-11-03 02:40:01.911022: Pseudo dice [np.float32(0.9354), np.float32(0.7135), np.float32(0.6971), np.float32(0.6273), np.float32(0.8579), np.float32(0.7683), np.float32(0.9143), np.float32(0.8704), np.float32(0.9715), np.float32(0.9594), np.float32(0.9662), np.float32(0.8525), np.float32(0.7521), np.float32(0.8624), np.float32(0.9639), np.float32(0.2438), np.float32(0.176)] +2025-11-03 02:40:01.912587: Epoch time: 513.58 s +2025-11-03 02:40:21.861348: +2025-11-03 02:40:21.862681: Epoch 716 +2025-11-03 02:40:21.863965: Current learning rate: 0.00322 +2025-11-03 02:48:51.560957: train_loss -0.4487 +2025-11-03 02:48:51.566453: val_loss -0.4329 +2025-11-03 02:48:51.567739: Pseudo dice [np.float32(0.9369), np.float32(0.6783), np.float32(0.6466), np.float32(0.6727), np.float32(0.827), np.float32(0.7668), np.float32(0.906), np.float32(0.8846), np.float32(0.9783), np.float32(0.9786), np.float32(0.9628), np.float32(0.8488), np.float32(0.7759), np.float32(0.8564), np.float32(0.9569), np.float32(0.3778), np.float32(0.336)] +2025-11-03 02:48:51.568819: Epoch time: 509.7 s +2025-11-03 02:48:53.569764: +2025-11-03 02:48:53.571531: Epoch 717 +2025-11-03 02:48:53.573002: Current learning rate: 0.00321 +2025-11-03 02:57:40.209699: train_loss -0.4676 +2025-11-03 02:57:40.218091: val_loss -0.4605 +2025-11-03 02:57:40.219939: Pseudo dice [np.float32(0.9444), np.float32(0.7763), np.float32(0.6925), np.float32(0.6153), np.float32(0.8833), np.float32(0.7875), np.float32(0.8556), np.float32(0.8881), np.float32(0.9508), np.float32(0.9504), np.float32(0.9586), np.float32(0.8514), np.float32(0.7544), np.float32(0.8612), np.float32(0.9585), np.float32(0.443), np.float32(0.4122)] +2025-11-03 02:57:40.222652: Epoch time: 526.64 s +2025-11-03 02:57:42.259093: +2025-11-03 02:57:42.261209: Epoch 718 +2025-11-03 02:57:42.262491: Current learning rate: 0.0032 +2025-11-03 03:06:19.236829: train_loss -0.4554 +2025-11-03 03:06:19.242864: val_loss -0.4434 +2025-11-03 03:06:19.244010: Pseudo dice [np.float32(0.9333), np.float32(0.7262), np.float32(0.6748), np.float32(0.6621), np.float32(0.853), np.float32(0.8005), np.float32(0.8716), np.float32(0.8732), np.float32(0.9389), np.float32(0.9355), np.float32(0.9695), np.float32(0.8439), np.float32(0.8139), np.float32(0.8535), np.float32(0.9442), np.float32(0.4386), np.float32(0.307)] +2025-11-03 03:06:19.245391: Epoch time: 516.99 s +2025-11-03 03:06:21.438186: +2025-11-03 03:06:21.441927: Epoch 719 +2025-11-03 03:06:21.446881: Current learning rate: 0.00319 +2025-11-03 03:14:57.883231: train_loss -0.4664 +2025-11-03 03:14:57.887941: val_loss -0.4585 +2025-11-03 03:14:57.889224: Pseudo dice [np.float32(0.9371), np.float32(0.7449), np.float32(0.7332), np.float32(0.6158), np.float32(0.8619), np.float32(0.7871), np.float32(0.8875), np.float32(0.8833), np.float32(0.9699), np.float32(0.9683), np.float32(0.9692), np.float32(0.8493), np.float32(0.8032), np.float32(0.8769), np.float32(0.9509), np.float32(0.3911), np.float32(0.2241)] +2025-11-03 03:14:57.890849: Epoch time: 516.45 s +2025-11-03 03:14:59.911558: +2025-11-03 03:14:59.915755: Epoch 720 +2025-11-03 03:14:59.917277: Current learning rate: 0.00318 +2025-11-03 03:23:38.840790: train_loss -0.4472 +2025-11-03 03:23:38.854595: val_loss -0.4421 +2025-11-03 03:23:38.859040: Pseudo dice [np.float32(0.9033), np.float32(0.7661), np.float32(0.7471), np.float32(0.6507), np.float32(0.8992), np.float32(0.8239), np.float32(0.8646), np.float32(0.8888), np.float32(0.9571), np.float32(0.9673), np.float32(0.9686), np.float32(0.8403), np.float32(0.7947), np.float32(0.8752), np.float32(0.9519), np.float32(0.3276), np.float32(0.2251)] +2025-11-03 03:23:38.861126: Epoch time: 518.93 s +2025-11-03 03:23:41.143769: +2025-11-03 03:23:41.145349: Epoch 721 +2025-11-03 03:23:41.146614: Current learning rate: 0.00317 +2025-11-03 03:32:10.874351: train_loss -0.4726 +2025-11-03 03:32:10.878833: val_loss -0.476 +2025-11-03 03:32:10.880169: Pseudo dice [np.float32(0.8887), np.float32(0.7922), np.float32(0.7671), np.float32(0.6452), np.float32(0.8968), np.float32(0.8144), np.float32(0.8781), np.float32(0.8829), np.float32(0.9823), np.float32(0.9828), np.float32(0.9669), np.float32(0.8511), np.float32(0.7699), np.float32(0.8803), np.float32(0.9708), np.float32(0.3314), np.float32(0.439)] +2025-11-03 03:32:10.881867: Epoch time: 509.74 s +2025-11-03 03:32:12.965250: +2025-11-03 03:32:12.966722: Epoch 722 +2025-11-03 03:32:12.968022: Current learning rate: 0.00316 +2025-11-03 03:40:54.298920: train_loss -0.4646 +2025-11-03 03:40:54.307406: val_loss -0.4263 +2025-11-03 03:40:54.313670: Pseudo dice [np.float32(0.9182), np.float32(0.7743), np.float32(0.7), np.float32(0.6463), np.float32(0.8331), np.float32(0.7981), np.float32(0.8769), np.float32(0.88), np.float32(0.9626), np.float32(0.9668), np.float32(0.9641), np.float32(0.855), np.float32(0.7607), np.float32(0.8746), np.float32(0.9609), np.float32(0.3888), np.float32(0.2559)] +2025-11-03 03:40:54.315653: Epoch time: 521.34 s +2025-11-03 03:40:56.406289: +2025-11-03 03:40:56.408412: Epoch 723 +2025-11-03 03:40:56.409839: Current learning rate: 0.00315 +2025-11-03 03:49:38.553012: train_loss -0.4657 +2025-11-03 03:49:38.557804: val_loss -0.4217 +2025-11-03 03:49:38.562241: Pseudo dice [np.float32(0.9303), np.float32(0.7714), np.float32(0.7229), np.float32(0.6887), np.float32(0.8425), np.float32(0.7852), np.float32(0.8901), np.float32(0.8832), np.float32(0.9646), np.float32(0.9705), np.float32(0.9688), np.float32(0.8523), np.float32(0.821), np.float32(0.8753), np.float32(0.961), np.float32(0.1852), np.float32(0.2834)] +2025-11-03 03:49:38.563896: Epoch time: 522.15 s +2025-11-03 03:49:40.730823: +2025-11-03 03:49:40.734591: Epoch 724 +2025-11-03 03:49:40.736308: Current learning rate: 0.00314 +2025-11-03 03:58:16.547706: train_loss -0.462 +2025-11-03 03:58:16.552876: val_loss -0.5258 +2025-11-03 03:58:16.559836: Pseudo dice [np.float32(0.9437), np.float32(0.8044), np.float32(0.7519), np.float32(0.623), np.float32(0.8793), np.float32(0.7932), np.float32(0.8799), np.float32(0.8892), np.float32(0.9826), np.float32(0.9826), np.float32(0.9647), np.float32(0.8597), np.float32(0.7879), np.float32(0.8782), np.float32(0.9618), np.float32(0.4568), np.float32(0.3366)] +2025-11-03 03:58:16.561573: Epoch time: 515.83 s +2025-11-03 03:58:18.891608: +2025-11-03 03:58:18.893116: Epoch 725 +2025-11-03 03:58:18.894348: Current learning rate: 0.00313 +2025-11-03 04:06:43.126547: train_loss -0.4536 +2025-11-03 04:06:43.130568: val_loss -0.4862 +2025-11-03 04:06:43.132273: Pseudo dice [np.float32(0.9248), np.float32(0.797), np.float32(0.7529), np.float32(0.6315), np.float32(0.8737), np.float32(0.7969), np.float32(0.8882), np.float32(0.8879), np.float32(0.9705), np.float32(0.9667), np.float32(0.9681), np.float32(0.8677), np.float32(0.801), np.float32(0.8814), np.float32(0.969), np.float32(0.3193), np.float32(0.3578)] +2025-11-03 04:06:43.133656: Epoch time: 504.24 s +2025-11-03 04:06:45.410981: +2025-11-03 04:06:45.417227: Epoch 726 +2025-11-03 04:06:45.425140: Current learning rate: 0.00312 +2025-11-03 04:15:20.856164: train_loss -0.4638 +2025-11-03 04:15:20.861366: val_loss -0.4574 +2025-11-03 04:15:20.862625: Pseudo dice [np.float32(0.9298), np.float32(0.776), np.float32(0.7074), np.float32(0.6872), np.float32(0.8474), np.float32(0.7812), np.float32(0.9039), np.float32(0.8817), np.float32(0.9675), np.float32(0.9702), np.float32(0.9686), np.float32(0.8582), np.float32(0.759), np.float32(0.858), np.float32(0.9572), np.float32(0.303), np.float32(0.3033)] +2025-11-03 04:15:20.864623: Epoch time: 515.45 s +2025-11-03 04:15:23.069399: +2025-11-03 04:15:23.070608: Epoch 727 +2025-11-03 04:15:23.072039: Current learning rate: 0.00311 +2025-11-03 04:24:10.007442: train_loss -0.4629 +2025-11-03 04:24:10.011952: val_loss -0.4607 +2025-11-03 04:24:10.013311: Pseudo dice [np.float32(0.928), np.float32(0.7558), np.float32(0.7224), np.float32(0.716), np.float32(0.8561), np.float32(0.7923), np.float32(0.8854), np.float32(0.8806), np.float32(0.9658), np.float32(0.9421), np.float32(0.9651), np.float32(0.8592), np.float32(0.8001), np.float32(0.8666), np.float32(0.9379), np.float32(0.2343), np.float32(0.3215)] +2025-11-03 04:24:10.014531: Epoch time: 526.94 s +2025-11-03 04:24:12.119043: +2025-11-03 04:24:12.120406: Epoch 728 +2025-11-03 04:24:12.121789: Current learning rate: 0.0031 +2025-11-03 04:33:00.439800: train_loss -0.4663 +2025-11-03 04:33:00.454605: val_loss -0.4605 +2025-11-03 04:33:00.456400: Pseudo dice [np.float32(0.9478), np.float32(0.7334), np.float32(0.6945), np.float32(0.7233), np.float32(0.8654), np.float32(0.8102), np.float32(0.8726), np.float32(0.8761), np.float32(0.9841), np.float32(0.9824), np.float32(0.9674), np.float32(0.8679), np.float32(0.7714), np.float32(0.8637), np.float32(0.9681), np.float32(0.2841), np.float32(0.3242)] +2025-11-03 04:33:00.457992: Epoch time: 528.33 s +2025-11-03 04:33:02.714650: +2025-11-03 04:33:02.716241: Epoch 729 +2025-11-03 04:33:02.717539: Current learning rate: 0.00309 +2025-11-03 04:41:31.351527: train_loss -0.4701 +2025-11-03 04:41:31.418444: val_loss -0.4458 +2025-11-03 04:41:31.419630: Pseudo dice [np.float32(0.9375), np.float32(0.7594), np.float32(0.7096), np.float32(0.6913), np.float32(0.8599), np.float32(0.8038), np.float32(0.8979), np.float32(0.8769), np.float32(0.9724), np.float32(0.9715), np.float32(0.9609), np.float32(0.8592), np.float32(0.761), np.float32(0.8784), np.float32(0.9389), np.float32(0.2282), np.float32(0.3057)] +2025-11-03 04:41:31.420774: Epoch time: 508.64 s +2025-11-03 04:41:33.754247: +2025-11-03 04:41:33.756197: Epoch 730 +2025-11-03 04:41:33.758037: Current learning rate: 0.00308 +2025-11-03 04:50:30.967923: train_loss -0.4477 +2025-11-03 04:50:31.098697: val_loss -0.4075 +2025-11-03 04:50:31.106521: Pseudo dice [np.float32(0.8908), np.float32(0.7692), np.float32(0.6724), np.float32(0.6427), np.float32(0.8653), np.float32(0.7866), np.float32(0.8869), np.float32(0.8674), np.float32(0.985), np.float32(0.9819), np.float32(0.9612), np.float32(0.837), np.float32(0.7829), np.float32(0.861), np.float32(0.9673), np.float32(0.2824), np.float32(0.3033)] +2025-11-03 04:50:31.185284: Epoch time: 537.22 s +2025-11-03 04:50:33.511089: +2025-11-03 04:50:33.596887: Epoch 731 +2025-11-03 04:50:33.604810: Current learning rate: 0.00307 +2025-11-03 05:01:48.871762: train_loss -0.4704 +2025-11-03 05:01:48.891929: val_loss -0.4941 +2025-11-03 05:01:48.899590: Pseudo dice [np.float32(0.9415), np.float32(0.7958), np.float32(0.7887), np.float32(0.7064), np.float32(0.8723), np.float32(0.8308), np.float32(0.8938), np.float32(0.8871), np.float32(0.9771), np.float32(0.9692), np.float32(0.9694), np.float32(0.877), np.float32(0.8004), np.float32(0.8909), np.float32(0.9582), np.float32(0.3259), np.float32(0.2875)] +2025-11-03 05:01:48.901922: Epoch time: 675.37 s +2025-11-03 05:01:50.992995: +2025-11-03 05:01:51.000648: Epoch 732 +2025-11-03 05:01:51.003664: Current learning rate: 0.00306 +2025-11-03 05:10:29.519335: train_loss -0.4701 +2025-11-03 05:10:29.543770: val_loss -0.4855 +2025-11-03 05:10:29.554632: Pseudo dice [np.float32(0.9464), np.float32(0.3992), np.float32(0.7142), np.float32(0.6855), np.float32(0.87), np.float32(0.8041), np.float32(0.8697), np.float32(0.8812), np.float32(0.9753), np.float32(0.982), np.float32(0.965), np.float32(0.8395), np.float32(0.7983), np.float32(0.8671), np.float32(0.9675), np.float32(0.374), np.float32(0.3933)] +2025-11-03 05:10:29.558079: Epoch time: 518.53 s +2025-11-03 05:10:32.031790: +2025-11-03 05:10:32.035928: Epoch 733 +2025-11-03 05:10:32.037089: Current learning rate: 0.00305 +2025-11-03 05:19:06.645441: train_loss -0.4496 +2025-11-03 05:19:06.719080: val_loss -0.478 +2025-11-03 05:19:06.721583: Pseudo dice [np.float32(0.932), np.float32(0.8078), np.float32(0.7128), np.float32(0.6303), np.float32(0.8768), np.float32(0.8034), np.float32(0.899), np.float32(0.875), np.float32(0.9825), np.float32(0.9808), np.float32(0.9636), np.float32(0.8664), np.float32(0.7693), np.float32(0.8818), np.float32(0.9731), np.float32(0.3464), np.float32(0.1925)] +2025-11-03 05:19:06.788050: Epoch time: 514.62 s +2025-11-03 05:19:09.275849: +2025-11-03 05:19:09.283030: Epoch 734 +2025-11-03 05:19:09.284481: Current learning rate: 0.00304 +2025-11-03 05:27:52.631863: train_loss -0.4531 +2025-11-03 05:27:52.668889: val_loss -0.4614 +2025-11-03 05:27:52.671946: Pseudo dice [np.float32(0.9336), np.float32(0.8128), np.float32(0.7314), np.float32(0.6823), np.float32(0.8785), np.float32(0.8201), np.float32(0.7742), np.float32(0.8837), np.float32(0.9802), np.float32(0.9813), np.float32(0.9677), np.float32(0.8681), np.float32(0.7965), np.float32(0.8646), np.float32(0.9636), np.float32(0.1992), np.float32(0.1953)] +2025-11-03 05:27:52.673232: Epoch time: 523.36 s +2025-11-03 05:27:54.795295: +2025-11-03 05:27:54.796660: Epoch 735 +2025-11-03 05:27:54.797939: Current learning rate: 0.00303 +2025-11-03 05:36:31.508909: train_loss -0.4515 +2025-11-03 05:36:31.518975: val_loss -0.4957 +2025-11-03 05:36:31.522792: Pseudo dice [np.float32(0.945), np.float32(0.7633), np.float32(0.697), np.float32(0.6663), np.float32(0.8707), np.float32(0.7787), np.float32(0.8944), np.float32(0.8857), np.float32(0.9759), np.float32(0.9736), np.float32(0.9663), np.float32(0.8557), np.float32(0.7809), np.float32(0.8612), np.float32(0.9627), np.float32(0.3609), np.float32(0.3618)] +2025-11-03 05:36:31.524192: Epoch time: 516.72 s +2025-11-03 05:36:33.649232: +2025-11-03 05:36:33.654256: Epoch 736 +2025-11-03 05:36:33.662279: Current learning rate: 0.00302 +2025-11-03 05:45:08.460179: train_loss -0.4518 +2025-11-03 05:45:08.472981: val_loss -0.4715 +2025-11-03 05:45:08.475162: Pseudo dice [np.float32(0.9392), np.float32(0.7802), np.float32(0.7263), np.float32(0.6408), np.float32(0.8949), np.float32(0.7891), np.float32(0.914), np.float32(0.878), np.float32(0.9772), np.float32(0.9794), np.float32(0.9655), np.float32(0.8629), np.float32(0.7957), np.float32(0.9032), np.float32(0.9645), np.float32(0.3571), np.float32(0.3362)] +2025-11-03 05:45:08.478843: Epoch time: 514.82 s +2025-11-03 05:45:10.535093: +2025-11-03 05:45:10.539254: Epoch 737 +2025-11-03 05:45:10.544348: Current learning rate: 0.00301 +2025-11-03 05:53:53.780474: train_loss -0.4357 +2025-11-03 05:53:53.791531: val_loss -0.4604 +2025-11-03 05:53:53.799643: Pseudo dice [np.float32(0.9329), np.float32(0.7721), np.float32(0.7189), np.float32(0.6759), np.float32(0.8652), np.float32(0.8079), np.float32(0.9025), np.float32(0.8872), np.float32(0.9413), np.float32(0.9417), np.float32(0.9635), np.float32(0.8484), np.float32(0.7585), np.float32(0.8784), np.float32(0.9727), np.float32(0.4462), np.float32(0.3211)] +2025-11-03 05:53:53.801305: Epoch time: 523.25 s +2025-11-03 05:53:55.967840: +2025-11-03 05:53:56.000526: Epoch 738 +2025-11-03 05:53:56.002115: Current learning rate: 0.003 +2025-11-03 06:02:26.834908: train_loss -0.4629 +2025-11-03 06:02:26.846577: val_loss -0.4615 +2025-11-03 06:02:26.865178: Pseudo dice [np.float32(0.9319), np.float32(0.7974), np.float32(0.7625), np.float32(0.6861), np.float32(0.8707), np.float32(0.8031), np.float32(0.8525), np.float32(0.8919), np.float32(0.9768), np.float32(0.9774), np.float32(0.9626), np.float32(0.8677), np.float32(0.8074), np.float32(0.8824), np.float32(0.9688), np.float32(0.3343), np.float32(0.3445)] +2025-11-03 06:02:26.874050: Epoch time: 510.87 s +2025-11-03 06:02:26.875854: Yayy! New best EMA pseudo Dice: 0.7965999841690063 +2025-11-03 06:02:32.084221: +2025-11-03 06:02:32.087484: Epoch 739 +2025-11-03 06:02:32.089441: Current learning rate: 0.00299 +2025-11-03 06:11:02.448851: train_loss -0.4519 +2025-11-03 06:11:02.469945: val_loss -0.4265 +2025-11-03 06:11:02.472222: Pseudo dice [np.float32(0.9325), np.float32(0.7107), np.float32(0.6728), np.float32(0.7269), np.float32(0.8637), np.float32(0.7931), np.float32(0.8705), np.float32(0.8775), np.float32(0.9785), np.float32(0.976), np.float32(0.9645), np.float32(0.8484), np.float32(0.7946), np.float32(0.849), np.float32(0.9691), np.float32(0.1297), np.float32(0.2356)] +2025-11-03 06:11:02.474307: Epoch time: 510.37 s +2025-11-03 06:11:04.563672: +2025-11-03 06:11:04.565532: Epoch 740 +2025-11-03 06:11:04.567232: Current learning rate: 0.00297 +2025-11-03 06:19:41.405965: train_loss -0.4682 +2025-11-03 06:19:41.423833: val_loss -0.472 +2025-11-03 06:19:41.425565: Pseudo dice [np.float32(0.9255), np.float32(0.7851), np.float32(0.7019), np.float32(0.6625), np.float32(0.8654), np.float32(0.7672), np.float32(0.8758), np.float32(0.8812), np.float32(0.9824), np.float32(0.9794), np.float32(0.9613), np.float32(0.8584), np.float32(0.7703), np.float32(0.8619), np.float32(0.9451), np.float32(0.4378), np.float32(0.3338)] +2025-11-03 06:19:41.426677: Epoch time: 516.85 s +2025-11-03 06:19:43.432375: +2025-11-03 06:19:43.434526: Epoch 741 +2025-11-03 06:19:43.436134: Current learning rate: 0.00296 +2025-11-03 06:28:18.560916: train_loss -0.4616 +2025-11-03 06:28:18.577190: val_loss -0.4539 +2025-11-03 06:28:18.579667: Pseudo dice [np.float32(0.9319), np.float32(0.7549), np.float32(0.6899), np.float32(0.6952), np.float32(0.8425), np.float32(0.7717), np.float32(0.9133), np.float32(0.8881), np.float32(0.9568), np.float32(0.9551), np.float32(0.9632), np.float32(0.8458), np.float32(0.8016), np.float32(0.8549), np.float32(0.9188), np.float32(0.1962), np.float32(0.1956)] +2025-11-03 06:28:18.584110: Epoch time: 515.13 s +2025-11-03 06:28:20.613937: +2025-11-03 06:28:20.621542: Epoch 742 +2025-11-03 06:28:20.623653: Current learning rate: 0.00295 +2025-11-03 06:37:04.235320: train_loss -0.444 +2025-11-03 06:37:04.274333: val_loss -0.4375 +2025-11-03 06:37:04.276318: Pseudo dice [np.float32(0.9258), np.float32(0.7312), np.float32(0.7572), np.float32(0.712), np.float32(0.8688), np.float32(0.7825), np.float32(0.8983), np.float32(0.8816), np.float32(0.9605), np.float32(0.9644), np.float32(0.9614), np.float32(0.8471), np.float32(0.8027), np.float32(0.8654), np.float32(0.8892), np.float32(0.3259), np.float32(0.3275)] +2025-11-03 06:37:04.278193: Epoch time: 523.63 s +2025-11-03 06:37:06.327595: +2025-11-03 06:37:06.330845: Epoch 743 +2025-11-03 06:37:06.332048: Current learning rate: 0.00294 +2025-11-03 06:45:49.953598: train_loss -0.4392 +2025-11-03 06:45:49.962673: val_loss -0.4589 +2025-11-03 06:45:49.968642: Pseudo dice [np.float32(0.9364), np.float32(0.7287), np.float32(0.6556), np.float32(0.6629), np.float32(0.8606), np.float32(0.7679), np.float32(0.8909), np.float32(0.8771), np.float32(0.9661), np.float32(0.9472), np.float32(0.9518), np.float32(0.8479), np.float32(0.7795), np.float32(0.8787), np.float32(0.894), np.float32(0.3824), np.float32(0.2507)] +2025-11-03 06:45:49.971722: Epoch time: 523.63 s +2025-11-03 06:45:52.057133: +2025-11-03 06:45:52.070446: Epoch 744 +2025-11-03 06:45:52.072280: Current learning rate: 0.00293 +2025-11-03 06:54:22.974834: train_loss -0.4537 +2025-11-03 06:54:23.007943: val_loss -0.4621 +2025-11-03 06:54:23.009770: Pseudo dice [np.float32(0.9417), np.float32(0.8037), np.float32(0.7556), np.float32(0.5834), np.float32(0.8541), np.float32(0.812), np.float32(0.893), np.float32(0.891), np.float32(0.9723), np.float32(0.9728), np.float32(0.9589), np.float32(0.858), np.float32(0.7851), np.float32(0.8679), np.float32(0.9554), np.float32(0.3366), np.float32(0.3817)] +2025-11-03 06:54:23.017303: Epoch time: 510.92 s +2025-11-03 06:54:25.182492: +2025-11-03 06:54:25.185088: Epoch 745 +2025-11-03 06:54:25.188333: Current learning rate: 0.00292 +2025-11-03 07:02:51.089518: train_loss -0.4439 +2025-11-03 07:02:51.128040: val_loss -0.4226 +2025-11-03 07:02:51.129337: Pseudo dice [np.float32(0.9203), np.float32(0.7848), np.float32(0.6959), np.float32(0.6995), np.float32(0.8674), np.float32(0.805), np.float32(0.8703), np.float32(0.8594), np.float32(0.9553), np.float32(0.9547), np.float32(0.9633), np.float32(0.8421), np.float32(0.816), np.float32(0.8706), np.float32(0.9425), np.float32(0.3444), np.float32(0.278)] +2025-11-03 07:02:51.132903: Epoch time: 505.91 s +2025-11-03 07:02:53.410126: +2025-11-03 07:02:53.417027: Epoch 746 +2025-11-03 07:02:53.418651: Current learning rate: 0.00291 +2025-11-03 07:11:39.025866: train_loss -0.4329 +2025-11-03 07:11:39.033328: val_loss -0.4449 +2025-11-03 07:11:39.034795: Pseudo dice [np.float32(0.9015), np.float32(0.8113), np.float32(0.7541), np.float32(0.6487), np.float32(0.8734), np.float32(0.8169), np.float32(0.8922), np.float32(0.8891), np.float32(0.9802), np.float32(0.98), np.float32(0.968), np.float32(0.8338), np.float32(0.7871), np.float32(0.88), np.float32(0.974), np.float32(0.5107), np.float32(0.3491)] +2025-11-03 07:11:39.036312: Epoch time: 525.62 s +2025-11-03 07:11:41.327660: +2025-11-03 07:11:41.331006: Epoch 747 +2025-11-03 07:11:41.332656: Current learning rate: 0.0029 +2025-11-03 07:20:26.818943: train_loss -0.4407 +2025-11-03 07:20:26.828881: val_loss -0.4477 +2025-11-03 07:20:26.830621: Pseudo dice [np.float32(0.9323), np.float32(0.7487), np.float32(0.6586), np.float32(0.6458), np.float32(0.8354), np.float32(0.7986), np.float32(0.9115), np.float32(0.8791), np.float32(0.9582), np.float32(0.9555), np.float32(0.9559), np.float32(0.8554), np.float32(0.7388), np.float32(0.8605), np.float32(0.9505), np.float32(0.504), np.float32(0.3817)] +2025-11-03 07:20:26.832973: Epoch time: 525.5 s +2025-11-03 07:20:29.155140: +2025-11-03 07:20:29.156804: Epoch 748 +2025-11-03 07:20:29.159008: Current learning rate: 0.00289 +2025-11-03 07:28:54.573382: train_loss -0.4509 +2025-11-03 07:28:54.585976: val_loss -0.4737 +2025-11-03 07:28:54.591888: Pseudo dice [np.float32(0.9446), np.float32(0.7561), np.float32(0.7018), np.float32(0.668), np.float32(0.875), np.float32(0.7877), np.float32(0.8807), np.float32(0.8947), np.float32(0.9837), np.float32(0.9785), np.float32(0.9662), np.float32(0.8444), np.float32(0.7963), np.float32(0.8689), np.float32(0.9633), np.float32(0.4002), np.float32(0.4446)] +2025-11-03 07:28:54.596294: Epoch time: 505.42 s +2025-11-03 07:28:54.597944: Yayy! New best EMA pseudo Dice: 0.7967000007629395 +2025-11-03 07:29:00.682306: +2025-11-03 07:29:00.684370: Epoch 749 +2025-11-03 07:29:00.687565: Current learning rate: 0.00288 +2025-11-03 07:37:37.646157: train_loss -0.4652 +2025-11-03 07:37:37.712880: val_loss -0.488 +2025-11-03 07:37:37.719486: Pseudo dice [np.float32(0.9342), np.float32(0.7708), np.float32(0.7151), np.float32(0.6598), np.float32(0.887), np.float32(0.7783), np.float32(0.9032), np.float32(0.8937), np.float32(0.9812), np.float32(0.9799), np.float32(0.9662), np.float32(0.8363), np.float32(0.7976), np.float32(0.8892), np.float32(0.9645), np.float32(0.4029), np.float32(0.3784)] +2025-11-03 07:37:37.721622: Epoch time: 516.97 s +2025-11-03 07:37:40.353183: Yayy! New best EMA pseudo Dice: 0.7979000210762024 +2025-11-03 07:37:44.645430: +2025-11-03 07:37:44.646777: Epoch 750 +2025-11-03 07:37:44.648200: Current learning rate: 0.00287 +2025-11-03 07:46:13.168870: train_loss -0.4553 +2025-11-03 07:46:13.184874: val_loss -0.4394 +2025-11-03 07:46:13.187659: Pseudo dice [np.float32(0.9031), np.float32(0.79), np.float32(0.7115), np.float32(0.6458), np.float32(0.8831), np.float32(0.7953), np.float32(0.8997), np.float32(0.8668), np.float32(0.9664), np.float32(0.9533), np.float32(0.9565), np.float32(0.8401), np.float32(0.793), np.float32(0.8796), np.float32(0.969), np.float32(0.1916), np.float32(0.3757)] +2025-11-03 07:46:13.192481: Epoch time: 508.53 s +2025-11-03 07:46:15.228184: +2025-11-03 07:46:15.239989: Epoch 751 +2025-11-03 07:46:15.243981: Current learning rate: 0.00286 +2025-11-03 07:54:41.612622: train_loss -0.4752 +2025-11-03 07:54:41.641771: val_loss -0.5034 +2025-11-03 07:54:41.644458: Pseudo dice [np.float32(0.937), np.float32(0.7746), np.float32(0.6615), np.float32(0.671), np.float32(0.88), np.float32(0.7896), np.float32(0.9086), np.float32(0.8885), np.float32(0.9616), np.float32(0.9547), np.float32(0.9582), np.float32(0.856), np.float32(0.8283), np.float32(0.8715), np.float32(0.9599), np.float32(0.5186), np.float32(0.3701)] +2025-11-03 07:54:41.678129: Epoch time: 506.39 s +2025-11-03 07:54:41.687638: Yayy! New best EMA pseudo Dice: 0.7983999848365784 +2025-11-03 07:54:47.089810: +2025-11-03 07:54:47.109630: Epoch 752 +2025-11-03 07:54:47.112027: Current learning rate: 0.00285 +2025-11-03 08:03:23.065154: train_loss -0.4533 +2025-11-03 08:03:23.103192: val_loss -0.4543 +2025-11-03 08:03:23.104831: Pseudo dice [np.float32(0.8958), np.float32(0.7663), np.float32(0.7229), np.float32(0.6618), np.float32(0.8555), np.float32(0.7692), np.float32(0.8644), np.float32(0.8845), np.float32(0.977), np.float32(0.9749), np.float32(0.9673), np.float32(0.8352), np.float32(0.8187), np.float32(0.8562), np.float32(0.9568), np.float32(0.4118), np.float32(0.4097)] +2025-11-03 08:03:23.106795: Epoch time: 515.98 s +2025-11-03 08:03:23.108642: Yayy! New best EMA pseudo Dice: 0.7986999750137329 +2025-11-03 08:03:28.055849: +2025-11-03 08:03:28.076871: Epoch 753 +2025-11-03 08:03:28.081305: Current learning rate: 0.00284 +2025-11-03 08:11:55.593358: train_loss -0.4586 +2025-11-03 08:11:55.604457: val_loss -0.4143 +2025-11-03 08:11:55.608272: Pseudo dice [np.float32(0.9389), np.float32(0.7638), np.float32(0.6944), np.float32(0.655), np.float32(0.8588), np.float32(0.8097), np.float32(0.9189), np.float32(0.8824), np.float32(0.9515), np.float32(0.9545), np.float32(0.9649), np.float32(0.8239), np.float32(0.7967), np.float32(0.8664), np.float32(0.9497), np.float32(0.4236), np.float32(0.336)] +2025-11-03 08:11:55.611048: Epoch time: 507.55 s +2025-11-03 08:11:55.612808: Yayy! New best EMA pseudo Dice: 0.798799991607666 +2025-11-03 08:12:00.405367: +2025-11-03 08:12:00.413533: Epoch 754 +2025-11-03 08:12:00.415637: Current learning rate: 0.00283 +2025-11-03 08:20:30.606715: train_loss -0.4314 +2025-11-03 08:20:30.617248: val_loss -0.4779 +2025-11-03 08:20:30.619253: Pseudo dice [np.float32(0.926), np.float32(0.7505), np.float32(0.6931), np.float32(0.6376), np.float32(0.8935), np.float32(0.7811), np.float32(0.8986), np.float32(0.8919), np.float32(0.9777), np.float32(0.9778), np.float32(0.9657), np.float32(0.8541), np.float32(0.7717), np.float32(0.8649), np.float32(0.9445), np.float32(0.2947), np.float32(0.2858)] +2025-11-03 08:20:30.620846: Epoch time: 510.21 s +2025-11-03 08:20:32.922135: +2025-11-03 08:20:32.923404: Epoch 755 +2025-11-03 08:20:32.945907: Current learning rate: 0.00282 +2025-11-03 08:34:16.116541: train_loss -0.4459 +2025-11-03 08:34:16.128684: val_loss -0.4838 +2025-11-03 08:34:16.130955: Pseudo dice [np.float32(0.9209), np.float32(0.7704), np.float32(0.7445), np.float32(0.667), np.float32(0.8792), np.float32(0.8052), np.float32(0.9076), np.float32(0.8944), np.float32(0.9764), np.float32(0.9771), np.float32(0.9701), np.float32(0.8536), np.float32(0.7964), np.float32(0.8663), np.float32(0.9682), np.float32(0.4222), np.float32(0.397)] +2025-11-03 08:34:16.133686: Epoch time: 823.2 s +2025-11-03 08:34:16.142664: Yayy! New best EMA pseudo Dice: 0.7993000149726868 +2025-11-03 08:34:20.571638: +2025-11-03 08:34:20.574149: Epoch 756 +2025-11-03 08:34:20.585822: Current learning rate: 0.00281 +2025-11-03 08:43:13.444595: train_loss -0.4609 +2025-11-03 08:43:13.466727: val_loss -0.4335 +2025-11-03 08:43:13.469386: Pseudo dice [np.float32(0.9404), np.float32(0.7954), np.float32(0.7702), np.float32(0.6582), np.float32(0.8486), np.float32(0.8086), np.float32(0.8981), np.float32(0.8901), np.float32(0.9757), np.float32(0.9718), np.float32(0.9711), np.float32(0.8318), np.float32(0.782), np.float32(0.8618), np.float32(0.9674), np.float32(0.2941), np.float32(0.3381)] +2025-11-03 08:43:13.477765: Epoch time: 532.88 s +2025-11-03 08:43:13.486552: Yayy! New best EMA pseudo Dice: 0.7993999719619751 +2025-11-03 08:43:17.971959: +2025-11-03 08:43:17.982306: Epoch 757 +2025-11-03 08:43:17.984364: Current learning rate: 0.0028 +2025-11-03 08:52:05.567328: train_loss -0.4383 +2025-11-03 08:52:05.582305: val_loss -0.482 +2025-11-03 08:52:05.584879: Pseudo dice [np.float32(0.9293), np.float32(0.8071), np.float32(0.7731), np.float32(0.6277), np.float32(0.8791), np.float32(0.8147), np.float32(0.8766), np.float32(0.8739), np.float32(0.9721), np.float32(0.9608), np.float32(0.9683), np.float32(0.8644), np.float32(0.7865), np.float32(0.896), np.float32(0.9658), np.float32(0.3484), np.float32(0.2758)] +2025-11-03 08:52:05.592041: Epoch time: 527.6 s +2025-11-03 08:52:05.596461: Yayy! New best EMA pseudo Dice: 0.7996000051498413 +2025-11-03 08:52:10.020509: +2025-11-03 08:52:10.029571: Epoch 758 +2025-11-03 08:52:10.032903: Current learning rate: 0.00279 +2025-11-03 09:01:02.226458: train_loss -0.4438 +2025-11-03 09:01:02.261237: val_loss -0.4492 +2025-11-03 09:01:02.264570: Pseudo dice [np.float32(0.9385), np.float32(0.8152), np.float32(0.7637), np.float32(0.6857), np.float32(0.8412), np.float32(0.8288), np.float32(0.9003), np.float32(0.8849), np.float32(0.9739), np.float32(0.9776), np.float32(0.9679), np.float32(0.8452), np.float32(0.8075), np.float32(0.8696), np.float32(0.9624), np.float32(0.2442), np.float32(0.2191)] +2025-11-03 09:01:02.270320: Epoch time: 532.21 s +2025-11-03 09:01:04.478096: +2025-11-03 09:01:04.495185: Epoch 759 +2025-11-03 09:01:04.497480: Current learning rate: 0.00278 +2025-11-03 09:09:57.882719: train_loss -0.4663 +2025-11-03 09:09:57.953919: val_loss -0.4522 +2025-11-03 09:09:57.957263: Pseudo dice [np.float32(0.9252), np.float32(0.796), np.float32(0.7187), np.float32(0.6939), np.float32(0.8672), np.float32(0.8135), np.float32(0.8719), np.float32(0.8848), np.float32(0.9814), np.float32(0.9803), np.float32(0.9693), np.float32(0.8332), np.float32(0.8028), np.float32(0.8717), np.float32(0.9677), np.float32(0.3184), np.float32(0.2755)] +2025-11-03 09:09:57.959998: Epoch time: 533.41 s +2025-11-03 09:10:00.017217: +2025-11-03 09:10:00.025030: Epoch 760 +2025-11-03 09:10:00.029552: Current learning rate: 0.00277 +2025-11-03 09:18:57.940301: train_loss -0.4577 +2025-11-03 09:18:57.960250: val_loss -0.4967 +2025-11-03 09:18:57.962553: Pseudo dice [np.float32(0.932), np.float32(0.7807), np.float32(0.723), np.float32(0.6689), np.float32(0.8864), np.float32(0.7943), np.float32(0.9112), np.float32(0.8929), np.float32(0.9796), np.float32(0.9795), np.float32(0.9661), np.float32(0.8426), np.float32(0.8044), np.float32(0.8826), np.float32(0.957), np.float32(0.4143), np.float32(0.2426)] +2025-11-03 09:18:57.965971: Epoch time: 537.93 s +2025-11-03 09:19:00.081819: +2025-11-03 09:19:00.090711: Epoch 761 +2025-11-03 09:19:00.097653: Current learning rate: 0.00276 +2025-11-03 09:27:52.195688: train_loss -0.4716 +2025-11-03 09:27:52.209294: val_loss -0.4543 +2025-11-03 09:27:52.211130: Pseudo dice [np.float32(0.928), np.float32(0.7622), np.float32(0.6801), np.float32(0.6665), np.float32(0.8864), np.float32(0.7818), np.float32(0.7546), np.float32(0.896), np.float32(0.9819), np.float32(0.9805), np.float32(0.9588), np.float32(0.8403), np.float32(0.7751), np.float32(0.89), np.float32(0.9563), np.float32(0.4127), np.float32(0.0808)] +2025-11-03 09:27:52.213000: Epoch time: 532.12 s +2025-11-03 09:27:54.188367: +2025-11-03 09:27:54.189993: Epoch 762 +2025-11-03 09:27:54.191524: Current learning rate: 0.00275 +2025-11-03 09:36:37.895532: train_loss -0.4765 +2025-11-03 09:36:37.935974: val_loss -0.4823 +2025-11-03 09:36:37.940125: Pseudo dice [np.float32(0.9415), np.float32(0.7806), np.float32(0.7336), np.float32(0.6777), np.float32(0.8755), np.float32(0.8101), np.float32(0.8875), np.float32(0.8836), np.float32(0.9682), np.float32(0.925), np.float32(0.9698), np.float32(0.8661), np.float32(0.7794), np.float32(0.8653), np.float32(0.9574), np.float32(0.3077), np.float32(0.274)] +2025-11-03 09:36:37.949558: Epoch time: 523.71 s +2025-11-03 09:36:40.259422: +2025-11-03 09:36:40.262018: Epoch 763 +2025-11-03 09:36:40.263479: Current learning rate: 0.00274 +2025-11-03 09:45:32.626726: train_loss -0.4617 +2025-11-03 09:45:32.645819: val_loss -0.4679 +2025-11-03 09:45:32.650312: Pseudo dice [np.float32(0.9235), np.float32(0.79), np.float32(0.7301), np.float32(0.615), np.float32(0.8632), np.float32(0.8005), np.float32(0.9088), np.float32(0.8886), np.float32(0.983), np.float32(0.9814), np.float32(0.9655), np.float32(0.8499), np.float32(0.7864), np.float32(0.8563), np.float32(0.9536), np.float32(0.3476), np.float32(0.2979)] +2025-11-03 09:45:32.656901: Epoch time: 532.37 s +2025-11-03 09:45:34.993624: +2025-11-03 09:45:34.995428: Epoch 764 +2025-11-03 09:45:34.997600: Current learning rate: 0.00273 +2025-11-03 09:53:59.306927: train_loss -0.4713 +2025-11-03 09:53:59.312009: val_loss -0.471 +2025-11-03 09:53:59.313441: Pseudo dice [np.float32(0.9212), np.float32(0.7645), np.float32(0.7269), np.float32(0.6939), np.float32(0.8712), np.float32(0.7606), np.float32(0.8886), np.float32(0.8792), np.float32(0.9815), np.float32(0.9809), np.float32(0.9669), np.float32(0.8527), np.float32(0.7906), np.float32(0.8739), np.float32(0.9594), np.float32(0.3041), np.float32(0.3237)] +2025-11-03 09:53:59.314650: Epoch time: 504.32 s +2025-11-03 09:54:01.584773: +2025-11-03 09:54:01.585976: Epoch 765 +2025-11-03 09:54:01.587315: Current learning rate: 0.00272 +2025-11-03 10:02:50.753895: train_loss -0.4688 +2025-11-03 10:02:50.762597: val_loss -0.4921 +2025-11-03 10:02:50.764059: Pseudo dice [np.float32(0.94), np.float32(0.8075), np.float32(0.7159), np.float32(0.6836), np.float32(0.8851), np.float32(0.7965), np.float32(0.8832), np.float32(0.8701), np.float32(0.9739), np.float32(0.9737), np.float32(0.9697), np.float32(0.8484), np.float32(0.7968), np.float32(0.8789), np.float32(0.9599), np.float32(0.4524), np.float32(0.3626)] +2025-11-03 10:02:50.765883: Epoch time: 529.17 s +2025-11-03 10:02:52.944352: +2025-11-03 10:02:52.945568: Epoch 766 +2025-11-03 10:02:52.947034: Current learning rate: 0.00271 +2025-11-03 10:13:27.154740: train_loss -0.4644 +2025-11-03 10:13:27.169775: val_loss -0.4713 +2025-11-03 10:13:27.177011: Pseudo dice [np.float32(0.9387), np.float32(0.7628), np.float32(0.7355), np.float32(0.6647), np.float32(0.8848), np.float32(0.7752), np.float32(0.8956), np.float32(0.901), np.float32(0.9727), np.float32(0.9713), np.float32(0.9663), np.float32(0.8459), np.float32(0.7905), np.float32(0.8533), np.float32(0.9301), np.float32(0.2901), np.float32(0.2792)] +2025-11-03 10:13:27.185015: Epoch time: 634.22 s +2025-11-03 10:13:29.829159: +2025-11-03 10:13:29.830964: Epoch 767 +2025-11-03 10:13:29.833038: Current learning rate: 0.0027 +2025-11-03 10:22:06.728806: train_loss -0.4741 +2025-11-03 10:22:06.744246: val_loss -0.5094 +2025-11-03 10:22:06.746184: Pseudo dice [np.float32(0.9468), np.float32(0.7561), np.float32(0.744), np.float32(0.6939), np.float32(0.8665), np.float32(0.7945), np.float32(0.9051), np.float32(0.8859), np.float32(0.9741), np.float32(0.9738), np.float32(0.9669), np.float32(0.8756), np.float32(0.8059), np.float32(0.8551), np.float32(0.9448), np.float32(0.2682), np.float32(0.2295)] +2025-11-03 10:22:06.747519: Epoch time: 516.9 s +2025-11-03 10:22:09.098408: +2025-11-03 10:22:09.100483: Epoch 768 +2025-11-03 10:22:09.102577: Current learning rate: 0.00268 +2025-11-03 10:30:44.594107: train_loss -0.47 +2025-11-03 10:30:44.618988: val_loss -0.4686 +2025-11-03 10:30:44.620490: Pseudo dice [np.float32(0.9172), np.float32(0.8252), np.float32(0.7331), np.float32(0.6431), np.float32(0.8643), np.float32(0.8144), np.float32(0.8945), np.float32(0.8994), np.float32(0.9816), np.float32(0.9807), np.float32(0.9687), np.float32(0.8327), np.float32(0.7916), np.float32(0.8858), np.float32(0.9706), np.float32(0.4215), np.float32(0.2406)] +2025-11-03 10:30:44.624291: Epoch time: 515.5 s +2025-11-03 10:30:47.199051: +2025-11-03 10:30:47.200962: Epoch 769 +2025-11-03 10:30:47.202153: Current learning rate: 0.00267 +2025-11-03 10:39:20.083100: train_loss -0.4813 +2025-11-03 10:39:20.089582: val_loss -0.4809 +2025-11-03 10:39:20.091072: Pseudo dice [np.float32(0.9405), np.float32(0.7641), np.float32(0.7243), np.float32(0.7115), np.float32(0.88), np.float32(0.7944), np.float32(0.9217), np.float32(0.9028), np.float32(0.9814), np.float32(0.9783), np.float32(0.9675), np.float32(0.8776), np.float32(0.818), np.float32(0.88), np.float32(0.9665), np.float32(0.376), np.float32(0.3521)] +2025-11-03 10:39:20.092753: Epoch time: 512.89 s +2025-11-03 10:39:20.095206: Yayy! New best EMA pseudo Dice: 0.7996000051498413 +2025-11-03 10:39:27.081063: +2025-11-03 10:39:27.083005: Epoch 770 +2025-11-03 10:39:27.084754: Current learning rate: 0.00266 +2025-11-03 10:48:47.722357: train_loss -0.4612 +2025-11-03 10:48:48.100087: val_loss -0.5004 +2025-11-03 10:48:48.173151: Pseudo dice [np.float32(0.9353), np.float32(0.7932), np.float32(0.7412), np.float32(0.6928), np.float32(0.856), np.float32(0.7883), np.float32(0.9036), np.float32(0.8933), np.float32(0.9804), np.float32(0.9773), np.float32(0.9651), np.float32(0.8529), np.float32(0.8264), np.float32(0.8679), np.float32(0.923), np.float32(0.2671), np.float32(0.2569)] +2025-11-03 10:48:48.182791: Epoch time: 560.65 s +2025-11-03 10:48:50.434091: +2025-11-03 10:48:50.449548: Epoch 771 +2025-11-03 10:48:50.452528: Current learning rate: 0.00265 +2025-11-03 11:00:29.109886: train_loss -0.4676 +2025-11-03 11:00:29.226126: val_loss -0.4032 +2025-11-03 11:00:29.227751: Pseudo dice [np.float32(0.9422), np.float32(0.7635), np.float32(0.7586), np.float32(0.5508), np.float32(0.8525), np.float32(0.811), np.float32(0.8883), np.float32(0.8855), np.float32(0.9793), np.float32(0.9759), np.float32(0.9686), np.float32(0.8669), np.float32(0.8185), np.float32(0.8542), np.float32(0.9635), np.float32(0.2903), np.float32(0.2814)] +2025-11-03 11:00:29.229359: Epoch time: 698.68 s +2025-11-03 11:00:31.518629: +2025-11-03 11:00:31.522111: Epoch 772 +2025-11-03 11:00:31.523695: Current learning rate: 0.00264 +2025-11-03 11:09:51.593079: train_loss -0.4477 +2025-11-03 11:09:51.613353: val_loss -0.4685 +2025-11-03 11:09:51.617225: Pseudo dice [np.float32(0.9325), np.float32(0.7768), np.float32(0.7397), np.float32(0.6422), np.float32(0.86), np.float32(0.7721), np.float32(0.8829), np.float32(0.8738), np.float32(0.9821), np.float32(0.9825), np.float32(0.9694), np.float32(0.8595), np.float32(0.8369), np.float32(0.8829), np.float32(0.9689), np.float32(0.4653), np.float32(0.374)] +2025-11-03 11:09:51.618988: Epoch time: 560.08 s +2025-11-03 11:09:51.620212: Yayy! New best EMA pseudo Dice: 0.7997000217437744 +2025-11-03 11:09:57.472275: +2025-11-03 11:09:57.481955: Epoch 773 +2025-11-03 11:09:57.504565: Current learning rate: 0.00263 +2025-11-03 11:18:45.561595: train_loss -0.4653 +2025-11-03 11:18:45.588573: val_loss -0.4524 +2025-11-03 11:18:45.590781: Pseudo dice [np.float32(0.9311), np.float32(0.8059), np.float32(0.7243), np.float32(0.6701), np.float32(0.8715), np.float32(0.8234), np.float32(0.8456), np.float32(0.896), np.float32(0.9812), np.float32(0.9554), np.float32(0.9683), np.float32(0.8557), np.float32(0.8281), np.float32(0.855), np.float32(0.9597), np.float32(0.348), np.float32(0.3841)] +2025-11-03 11:18:45.613433: Epoch time: 528.1 s +2025-11-03 11:18:45.615142: Yayy! New best EMA pseudo Dice: 0.8003000020980835 +2025-11-03 11:18:50.060080: +2025-11-03 11:18:50.066980: Epoch 774 +2025-11-03 11:18:50.071134: Current learning rate: 0.00262 +2025-11-03 11:27:57.369890: train_loss -0.4568 +2025-11-03 11:27:57.403096: val_loss -0.4748 +2025-11-03 11:27:57.405599: Pseudo dice [np.float32(0.9467), np.float32(0.7763), np.float32(0.6511), np.float32(0.6313), np.float32(0.8799), np.float32(0.8295), np.float32(0.8852), np.float32(0.8896), np.float32(0.9826), np.float32(0.9828), np.float32(0.9658), np.float32(0.8438), np.float32(0.8022), np.float32(0.877), np.float32(0.9654), np.float32(0.4033), np.float32(0.3353)] +2025-11-03 11:27:57.413141: Epoch time: 547.31 s +2025-11-03 11:27:57.416342: Yayy! New best EMA pseudo Dice: 0.800599992275238 +2025-11-03 11:28:01.647335: +2025-11-03 11:28:01.650663: Epoch 775 +2025-11-03 11:28:01.659094: Current learning rate: 0.00261 +2025-11-03 11:36:59.619180: train_loss -0.4437 +2025-11-03 11:36:59.632701: val_loss -0.4791 +2025-11-03 11:36:59.638218: Pseudo dice [np.float32(0.9457), np.float32(0.7475), np.float32(0.7147), np.float32(0.6218), np.float32(0.8559), np.float32(0.7941), np.float32(0.9149), np.float32(0.8907), np.float32(0.9824), np.float32(0.9804), np.float32(0.9683), np.float32(0.8525), np.float32(0.7772), np.float32(0.8826), np.float32(0.963), np.float32(0.2424), np.float32(0.2775)] +2025-11-03 11:36:59.641711: Epoch time: 537.98 s +2025-11-03 11:37:01.584054: +2025-11-03 11:37:01.591833: Epoch 776 +2025-11-03 11:37:01.593737: Current learning rate: 0.0026 +2025-11-03 11:46:15.707003: train_loss -0.4653 +2025-11-03 11:46:15.812432: val_loss -0.4459 +2025-11-03 11:46:15.814553: Pseudo dice [np.float32(0.9488), np.float32(0.7461), np.float32(0.5908), np.float32(0.6491), np.float32(0.8729), np.float32(0.7717), np.float32(0.8899), np.float32(0.8842), np.float32(0.9593), np.float32(0.9526), np.float32(0.9693), np.float32(0.8549), np.float32(0.7962), np.float32(0.8759), np.float32(0.9697), np.float32(0.292), np.float32(0.1216)] +2025-11-03 11:46:15.819708: Epoch time: 554.13 s +2025-11-03 11:46:17.812845: +2025-11-03 11:46:17.834430: Epoch 777 +2025-11-03 11:46:17.836146: Current learning rate: 0.00259 +2025-11-03 11:55:06.345739: train_loss -0.4761 +2025-11-03 11:55:06.368787: val_loss -0.4571 +2025-11-03 11:55:06.370779: Pseudo dice [np.float32(0.9257), np.float32(0.756), np.float32(0.7393), np.float32(0.7075), np.float32(0.8542), np.float32(0.8246), np.float32(0.8678), np.float32(0.8967), np.float32(0.9825), np.float32(0.9768), np.float32(0.9695), np.float32(0.8527), np.float32(0.7765), np.float32(0.8448), np.float32(0.9568), np.float32(0.3412), np.float32(0.2833)] +2025-11-03 11:55:06.372303: Epoch time: 528.54 s +2025-11-03 11:55:08.575480: +2025-11-03 11:55:08.578512: Epoch 778 +2025-11-03 11:55:08.581877: Current learning rate: 0.00258 +2025-11-03 12:04:13.783688: train_loss -0.4815 +2025-11-03 12:04:13.789814: val_loss -0.4349 +2025-11-03 12:04:13.791672: Pseudo dice [np.float32(0.9433), np.float32(0.7432), np.float32(0.7398), np.float32(0.6114), np.float32(0.8664), np.float32(0.7843), np.float32(0.8966), np.float32(0.8827), np.float32(0.9777), np.float32(0.976), np.float32(0.9674), np.float32(0.868), np.float32(0.7848), np.float32(0.8708), np.float32(0.954), np.float32(0.486), np.float32(0.4623)] +2025-11-03 12:04:13.793776: Epoch time: 545.21 s +2025-11-03 12:04:15.977035: +2025-11-03 12:04:15.978497: Epoch 779 +2025-11-03 12:04:15.980216: Current learning rate: 0.00257 +2025-11-03 12:13:14.016526: train_loss -0.4609 +2025-11-03 12:13:14.022618: val_loss -0.4675 +2025-11-03 12:13:14.026092: Pseudo dice [np.float32(0.9215), np.float32(0.7959), np.float32(0.7426), np.float32(0.6711), np.float32(0.8666), np.float32(0.8003), np.float32(0.8865), np.float32(0.8773), np.float32(0.9672), np.float32(0.9676), np.float32(0.9669), np.float32(0.8588), np.float32(0.7809), np.float32(0.8785), np.float32(0.965), np.float32(0.4067), np.float32(0.2998)] +2025-11-03 12:13:14.027591: Epoch time: 538.04 s +2025-11-03 12:13:16.190204: +2025-11-03 12:13:16.191827: Epoch 780 +2025-11-03 12:13:16.195485: Current learning rate: 0.00256 +2025-11-03 12:22:07.632666: train_loss -0.4695 +2025-11-03 12:22:07.751203: val_loss -0.4381 +2025-11-03 12:22:07.752758: Pseudo dice [np.float32(0.9441), np.float32(0.7724), np.float32(0.6926), np.float32(0.6543), np.float32(0.8407), np.float32(0.8365), np.float32(0.9086), np.float32(0.8671), np.float32(0.9817), np.float32(0.9842), np.float32(0.9673), np.float32(0.8586), np.float32(0.7995), np.float32(0.8473), np.float32(0.9479), np.float32(0.1782), np.float32(0.1599)] +2025-11-03 12:22:07.817818: Epoch time: 531.45 s +2025-11-03 12:22:10.522721: +2025-11-03 12:22:10.528651: Epoch 781 +2025-11-03 12:22:10.531005: Current learning rate: 0.00255 +2025-11-03 12:31:10.556143: train_loss -0.4472 +2025-11-03 12:31:10.579522: val_loss -0.4445 +2025-11-03 12:31:10.581389: Pseudo dice [np.float32(0.929), np.float32(0.7789), np.float32(0.7344), np.float32(0.6724), np.float32(0.8403), np.float32(0.7999), np.float32(0.913), np.float32(0.8832), np.float32(0.9705), np.float32(0.9686), np.float32(0.9689), np.float32(0.8596), np.float32(0.7706), np.float32(0.877), np.float32(0.969), np.float32(0.5683), np.float32(0.4521)] +2025-11-03 12:31:10.582890: Epoch time: 540.04 s +2025-11-03 12:31:12.566612: +2025-11-03 12:31:12.568750: Epoch 782 +2025-11-03 12:31:12.570316: Current learning rate: 0.00254 +2025-11-03 12:40:12.361767: train_loss -0.4579 +2025-11-03 12:40:12.368449: val_loss -0.4565 +2025-11-03 12:40:12.373533: Pseudo dice [np.float32(0.9428), np.float32(0.8253), np.float32(0.8132), np.float32(0.681), np.float32(0.8758), np.float32(0.8202), np.float32(0.8625), np.float32(0.8935), np.float32(0.977), np.float32(0.9726), np.float32(0.9627), np.float32(0.8699), np.float32(0.7821), np.float32(0.8959), np.float32(0.9346), np.float32(0.4544), np.float32(0.2917)] +2025-11-03 12:40:12.380222: Epoch time: 539.8 s +2025-11-03 12:40:12.381440: Yayy! New best EMA pseudo Dice: 0.8008999824523926 +2025-11-03 12:40:18.103673: +2025-11-03 12:40:18.106272: Epoch 783 +2025-11-03 12:40:18.107685: Current learning rate: 0.00253 +2025-11-03 12:49:26.296875: train_loss -0.4396 +2025-11-03 12:49:26.301814: val_loss -0.4673 +2025-11-03 12:49:26.303362: Pseudo dice [np.float32(0.9446), np.float32(0.7543), np.float32(0.7491), np.float32(0.6906), np.float32(0.8801), np.float32(0.812), np.float32(0.8975), np.float32(0.8829), np.float32(0.9684), np.float32(0.9546), np.float32(0.9582), np.float32(0.8655), np.float32(0.7847), np.float32(0.8771), np.float32(0.9496), np.float32(0.3659), np.float32(0.0359)] +2025-11-03 12:49:26.304880: Epoch time: 548.2 s +2025-11-03 12:49:44.122754: +2025-11-03 12:49:44.124316: Epoch 784 +2025-11-03 12:49:44.125429: Current learning rate: 0.00252 +2025-11-03 12:58:48.548632: train_loss -0.4541 +2025-11-03 12:58:48.611119: val_loss -0.4844 +2025-11-03 12:58:48.612771: Pseudo dice [np.float32(0.9158), np.float32(0.7952), np.float32(0.7651), np.float32(0.6652), np.float32(0.8833), np.float32(0.82), np.float32(0.8977), np.float32(0.8897), np.float32(0.9774), np.float32(0.974), np.float32(0.9657), np.float32(0.8548), np.float32(0.804), np.float32(0.8868), np.float32(0.9512), np.float32(0.4839), np.float32(0.3163)] +2025-11-03 12:58:48.633156: Epoch time: 544.43 s +2025-11-03 12:58:48.634821: Yayy! New best EMA pseudo Dice: 0.8008999824523926 +2025-11-03 12:58:53.478830: +2025-11-03 12:58:53.484185: Epoch 785 +2025-11-03 12:58:53.485862: Current learning rate: 0.00251 +2025-11-03 13:07:56.349314: train_loss -0.4678 +2025-11-03 13:07:56.355819: val_loss -0.4822 +2025-11-03 13:07:56.357400: Pseudo dice [np.float32(0.9437), np.float32(0.8121), np.float32(0.7516), np.float32(0.6237), np.float32(0.8717), np.float32(0.7944), np.float32(0.9078), np.float32(0.8967), np.float32(0.9813), np.float32(0.9831), np.float32(0.9675), np.float32(0.8515), np.float32(0.7992), np.float32(0.8869), np.float32(0.966), np.float32(0.3236), np.float32(0.316)] +2025-11-03 13:07:56.360404: Epoch time: 542.87 s +2025-11-03 13:07:56.364925: Yayy! New best EMA pseudo Dice: 0.8012999892234802 +2025-11-03 13:08:01.165488: +2025-11-03 13:08:01.166961: Epoch 786 +2025-11-03 13:08:01.168316: Current learning rate: 0.0025 +2025-11-03 13:16:49.371337: train_loss -0.464 +2025-11-03 13:16:49.379655: val_loss -0.4413 +2025-11-03 13:16:49.381172: Pseudo dice [np.float32(0.917), np.float32(0.7405), np.float32(0.6969), np.float32(0.6885), np.float32(0.8666), np.float32(0.8209), np.float32(0.884), np.float32(0.8933), np.float32(0.9653), np.float32(0.9649), np.float32(0.9691), np.float32(0.8338), np.float32(0.7858), np.float32(0.8552), np.float32(0.9597), np.float32(0.4527), np.float32(0.2967)] +2025-11-03 13:16:49.382643: Epoch time: 528.21 s +2025-11-03 13:16:51.388857: +2025-11-03 13:16:51.390308: Epoch 787 +2025-11-03 13:16:51.391668: Current learning rate: 0.00249 +2025-11-03 13:25:51.076574: train_loss -0.4637 +2025-11-03 13:25:51.084611: val_loss -0.4017 +2025-11-03 13:25:51.087018: Pseudo dice [np.float32(0.9226), np.float32(0.7677), np.float32(0.729), np.float32(0.6677), np.float32(0.8497), np.float32(0.7179), np.float32(0.8913), np.float32(0.8644), np.float32(0.9852), np.float32(0.9841), np.float32(0.9667), np.float32(0.8552), np.float32(0.7318), np.float32(0.8661), np.float32(0.9537), np.float32(0.2981), np.float32(0.364)] +2025-11-03 13:25:51.089000: Epoch time: 539.7 s +2025-11-03 13:25:53.378919: +2025-11-03 13:25:53.380936: Epoch 788 +2025-11-03 13:25:53.382348: Current learning rate: 0.00248 +2025-11-03 13:35:08.386640: train_loss -0.4702 +2025-11-03 13:35:08.397998: val_loss -0.4506 +2025-11-03 13:35:08.399216: Pseudo dice [np.float32(0.9436), np.float32(0.725), np.float32(0.7385), np.float32(0.6794), np.float32(0.8603), np.float32(0.774), np.float32(0.9013), np.float32(0.8799), np.float32(0.9796), np.float32(0.9796), np.float32(0.9642), np.float32(0.8529), np.float32(0.8154), np.float32(0.8748), np.float32(0.9616), np.float32(0.3368), np.float32(0.2414)] +2025-11-03 13:35:08.400748: Epoch time: 555.01 s +2025-11-03 13:35:10.776062: +2025-11-03 13:35:10.778636: Epoch 789 +2025-11-03 13:35:10.779823: Current learning rate: 0.00247 +2025-11-03 13:44:15.105399: train_loss -0.4938 +2025-11-03 13:44:15.115023: val_loss -0.4682 +2025-11-03 13:44:15.117177: Pseudo dice [np.float32(0.9413), np.float32(0.7934), np.float32(0.6976), np.float32(0.6589), np.float32(0.8622), np.float32(0.8079), np.float32(0.8815), np.float32(0.8819), np.float32(0.9773), np.float32(0.9807), np.float32(0.9664), np.float32(0.8678), np.float32(0.7743), np.float32(0.8535), np.float32(0.97), np.float32(0.3945), np.float32(0.3489)] +2025-11-03 13:44:15.119193: Epoch time: 544.34 s +2025-11-03 13:44:17.916928: +2025-11-03 13:44:17.918324: Epoch 790 +2025-11-03 13:44:17.919975: Current learning rate: 0.00245 +2025-11-03 13:53:30.291116: train_loss -0.4759 +2025-11-03 13:53:30.296854: val_loss -0.4912 +2025-11-03 13:53:30.298216: Pseudo dice [np.float32(0.9294), np.float32(0.7748), np.float32(0.6936), np.float32(0.6683), np.float32(0.8685), np.float32(0.7873), np.float32(0.8814), np.float32(0.8937), np.float32(0.9765), np.float32(0.9788), np.float32(0.9604), np.float32(0.8483), np.float32(0.7997), np.float32(0.8723), np.float32(0.9633), np.float32(0.4867), np.float32(0.3104)] +2025-11-03 13:53:30.299565: Epoch time: 552.38 s +2025-11-03 13:53:32.482379: +2025-11-03 13:53:32.483711: Epoch 791 +2025-11-03 13:53:32.484929: Current learning rate: 0.00244 +2025-11-03 14:02:35.117812: train_loss -0.4714 +2025-11-03 14:02:35.129965: val_loss -0.468 +2025-11-03 14:02:35.133090: Pseudo dice [np.float32(0.926), np.float32(0.7553), np.float32(0.7027), np.float32(0.6187), np.float32(0.8633), np.float32(0.7997), np.float32(0.891), np.float32(0.8624), np.float32(0.985), np.float32(0.9651), np.float32(0.9631), np.float32(0.8617), np.float32(0.7633), np.float32(0.8685), np.float32(0.9698), np.float32(0.2849), np.float32(0.2797)] +2025-11-03 14:02:35.134995: Epoch time: 542.64 s +2025-11-03 14:02:37.424844: +2025-11-03 14:02:37.426168: Epoch 792 +2025-11-03 14:02:37.427205: Current learning rate: 0.00243 +2025-11-03 14:12:09.103193: train_loss -0.4643 +2025-11-03 14:12:09.108263: val_loss -0.4389 +2025-11-03 14:12:09.109751: Pseudo dice [np.float32(0.9297), np.float32(0.8088), np.float32(0.7499), np.float32(0.6834), np.float32(0.8669), np.float32(0.8074), np.float32(0.8669), np.float32(0.8822), np.float32(0.9633), np.float32(0.9715), np.float32(0.9649), np.float32(0.8278), np.float32(0.8118), np.float32(0.8661), np.float32(0.9503), np.float32(0.3412), np.float32(0.3075)] +2025-11-03 14:12:09.113292: Epoch time: 571.68 s +2025-11-03 14:12:11.386221: +2025-11-03 14:12:11.423793: Epoch 793 +2025-11-03 14:12:11.429412: Current learning rate: 0.00242 +2025-11-03 14:21:25.875922: train_loss -0.4815 +2025-11-03 14:21:25.881594: val_loss -0.4738 +2025-11-03 14:21:25.882863: Pseudo dice [np.float32(0.9381), np.float32(0.8037), np.float32(0.6962), np.float32(0.6945), np.float32(0.8669), np.float32(0.8044), np.float32(0.8937), np.float32(0.8798), np.float32(0.9769), np.float32(0.9771), np.float32(0.9687), np.float32(0.8485), np.float32(0.7852), np.float32(0.8195), np.float32(0.9369), np.float32(0.3792), np.float32(0.309)] +2025-11-03 14:21:25.893478: Epoch time: 554.5 s +2025-11-03 14:21:28.322829: +2025-11-03 14:21:28.325819: Epoch 794 +2025-11-03 14:21:28.327488: Current learning rate: 0.00241 +2025-11-03 14:30:36.721941: train_loss -0.4719 +2025-11-03 14:30:36.733353: val_loss -0.4773 +2025-11-03 14:30:36.734456: Pseudo dice [np.float32(0.9421), np.float32(0.7903), np.float32(0.7416), np.float32(0.6143), np.float32(0.8584), np.float32(0.8084), np.float32(0.8459), np.float32(0.8833), np.float32(0.9839), np.float32(0.9832), np.float32(0.9682), np.float32(0.8598), np.float32(0.7966), np.float32(0.8766), np.float32(0.9495), np.float32(0.262), np.float32(0.1748)] +2025-11-03 14:30:36.737473: Epoch time: 548.4 s +2025-11-03 14:30:38.978777: +2025-11-03 14:30:38.980245: Epoch 795 +2025-11-03 14:30:38.981446: Current learning rate: 0.0024 +2025-11-03 14:39:45.788599: train_loss -0.4867 +2025-11-03 14:39:45.797669: val_loss -0.4586 +2025-11-03 14:39:45.804942: Pseudo dice [np.float32(0.8849), np.float32(0.805), np.float32(0.7485), np.float32(0.6837), np.float32(0.8676), np.float32(0.8042), np.float32(0.9021), np.float32(0.8771), np.float32(0.9679), np.float32(0.9654), np.float32(0.9641), np.float32(0.8629), np.float32(0.7982), np.float32(0.8591), np.float32(0.9478), np.float32(0.2372), np.float32(0.3207)] +2025-11-03 14:39:45.811395: Epoch time: 546.81 s +2025-11-03 14:39:48.146698: +2025-11-03 14:39:48.148289: Epoch 796 +2025-11-03 14:39:48.150024: Current learning rate: 0.00239 +2025-11-03 14:48:29.662863: train_loss -0.4779 +2025-11-03 14:48:29.669114: val_loss -0.479 +2025-11-03 14:48:29.670366: Pseudo dice [np.float32(0.9463), np.float32(0.8124), np.float32(0.7772), np.float32(0.6841), np.float32(0.8709), np.float32(0.8081), np.float32(0.8852), np.float32(0.8829), np.float32(0.9654), np.float32(0.9662), np.float32(0.97), np.float32(0.8664), np.float32(0.8282), np.float32(0.851), np.float32(0.9699), np.float32(0.3836), np.float32(0.4155)] +2025-11-03 14:48:29.672176: Epoch time: 521.53 s +2025-11-03 14:48:31.806640: +2025-11-03 14:48:31.808141: Epoch 797 +2025-11-03 14:48:31.809209: Current learning rate: 0.00238 +2025-11-03 14:57:10.585601: train_loss -0.4772 +2025-11-03 14:57:10.595239: val_loss -0.4688 +2025-11-03 14:57:10.598691: Pseudo dice [np.float32(0.9341), np.float32(0.7732), np.float32(0.724), np.float32(0.6377), np.float32(0.85), np.float32(0.8073), np.float32(0.911), np.float32(0.8873), np.float32(0.9799), np.float32(0.9822), np.float32(0.9686), np.float32(0.8465), np.float32(0.8074), np.float32(0.8562), np.float32(0.9694), np.float32(0.3431), np.float32(0.3445)] +2025-11-03 14:57:10.602833: Epoch time: 518.78 s +2025-11-03 14:57:12.926805: +2025-11-03 14:57:12.935089: Epoch 798 +2025-11-03 14:57:12.936450: Current learning rate: 0.00237 +2025-11-03 15:06:03.256532: train_loss -0.4728 +2025-11-03 15:06:03.266489: val_loss -0.4951 +2025-11-03 15:06:03.270691: Pseudo dice [np.float32(0.938), np.float32(0.7494), np.float32(0.7141), np.float32(0.6597), np.float32(0.8649), np.float32(0.8254), np.float32(0.8956), np.float32(0.8862), np.float32(0.9679), np.float32(0.9558), np.float32(0.9641), np.float32(0.8674), np.float32(0.7897), np.float32(0.8774), np.float32(0.9661), np.float32(0.354), np.float32(0.3054)] +2025-11-03 15:06:03.273870: Epoch time: 530.33 s +2025-11-03 15:06:05.391625: +2025-11-03 15:06:05.394968: Epoch 799 +2025-11-03 15:06:05.401073: Current learning rate: 0.00236 +2025-11-03 15:14:55.176239: train_loss -0.4758 +2025-11-03 15:14:55.190225: val_loss -0.4593 +2025-11-03 15:14:55.191608: Pseudo dice [np.float32(0.9086), np.float32(0.7912), np.float32(0.7129), np.float32(0.6654), np.float32(0.8499), np.float32(0.8157), np.float32(0.889), np.float32(0.8759), np.float32(0.9818), np.float32(0.9684), np.float32(0.9679), np.float32(0.8721), np.float32(0.7567), np.float32(0.8521), np.float32(0.9638), np.float32(0.2502), np.float32(0.1341)] +2025-11-03 15:14:55.201954: Epoch time: 529.79 s +2025-11-03 15:15:00.889968: +2025-11-03 15:15:00.891929: Epoch 800 +2025-11-03 15:15:00.895548: Current learning rate: 0.00235 +2025-11-03 15:24:00.545144: train_loss -0.4659 +2025-11-03 15:24:00.549348: val_loss -0.4438 +2025-11-03 15:24:00.550494: Pseudo dice [np.float32(0.9212), np.float32(0.7635), np.float32(0.7723), np.float32(0.6652), np.float32(0.8648), np.float32(0.8112), np.float32(0.8639), np.float32(0.8691), np.float32(0.9643), np.float32(0.9468), np.float32(0.9625), np.float32(0.8575), np.float32(0.8201), np.float32(0.878), np.float32(0.9244), np.float32(0.2869), np.float32(0.2983)] +2025-11-03 15:24:00.551764: Epoch time: 539.66 s +2025-11-03 15:24:02.716782: +2025-11-03 15:24:02.719618: Epoch 801 +2025-11-03 15:24:02.721983: Current learning rate: 0.00234 +2025-11-03 15:32:31.115307: train_loss -0.4799 +2025-11-03 15:32:31.121527: val_loss -0.4791 +2025-11-03 15:32:31.128129: Pseudo dice [np.float32(0.9312), np.float32(0.8067), np.float32(0.7342), np.float32(0.7116), np.float32(0.8545), np.float32(0.8131), np.float32(0.9305), np.float32(0.897), np.float32(0.9784), np.float32(0.9778), np.float32(0.9701), np.float32(0.8515), np.float32(0.7946), np.float32(0.8744), np.float32(0.9635), np.float32(0.2067), np.float32(0.2754)] +2025-11-03 15:32:31.130385: Epoch time: 508.4 s +2025-11-03 15:32:33.657566: +2025-11-03 15:32:33.658838: Epoch 802 +2025-11-03 15:32:33.660151: Current learning rate: 0.00233 +2025-11-03 15:41:24.510190: train_loss -0.4607 +2025-11-03 15:41:24.516812: val_loss -0.483 +2025-11-03 15:41:24.518727: Pseudo dice [np.float32(0.9425), np.float32(0.7818), np.float32(0.7467), np.float32(0.7243), np.float32(0.8332), np.float32(0.792), np.float32(0.8688), np.float32(0.8896), np.float32(0.9743), np.float32(0.9681), np.float32(0.9669), np.float32(0.8592), np.float32(0.7717), np.float32(0.8551), np.float32(0.9675), np.float32(0.364), np.float32(0.4296)] +2025-11-03 15:41:24.568179: Epoch time: 530.86 s +2025-11-03 15:41:27.029488: +2025-11-03 15:41:27.030764: Epoch 803 +2025-11-03 15:41:27.031934: Current learning rate: 0.00232 +2025-11-03 15:49:59.192333: train_loss -0.4663 +2025-11-03 15:49:59.202933: val_loss -0.4652 +2025-11-03 15:49:59.204306: Pseudo dice [np.float32(0.942), np.float32(0.7538), np.float32(0.7056), np.float32(0.668), np.float32(0.8821), np.float32(0.759), np.float32(0.8911), np.float32(0.8844), np.float32(0.9684), np.float32(0.9576), np.float32(0.9625), np.float32(0.8523), np.float32(0.784), np.float32(0.881), np.float32(0.9553), np.float32(0.3882), np.float32(0.3748)] +2025-11-03 15:49:59.205604: Epoch time: 512.17 s +2025-11-03 15:50:01.350924: +2025-11-03 15:50:01.352250: Epoch 804 +2025-11-03 15:50:01.353651: Current learning rate: 0.00231 +2025-11-03 15:58:47.890094: train_loss -0.4819 +2025-11-03 15:58:47.928802: val_loss -0.4889 +2025-11-03 15:58:47.930140: Pseudo dice [np.float32(0.9223), np.float32(0.7721), np.float32(0.6868), np.float32(0.6968), np.float32(0.8783), np.float32(0.7917), np.float32(0.8844), np.float32(0.8883), np.float32(0.9781), np.float32(0.9795), np.float32(0.9674), np.float32(0.8682), np.float32(0.7956), np.float32(0.8641), np.float32(0.9597), np.float32(0.4271), np.float32(0.3441)] +2025-11-03 15:58:47.931406: Epoch time: 526.54 s +2025-11-03 15:58:50.150344: +2025-11-03 15:58:50.152039: Epoch 805 +2025-11-03 15:58:50.153456: Current learning rate: 0.0023 +2025-11-03 16:07:28.599602: train_loss -0.477 +2025-11-03 16:07:28.618369: val_loss -0.4352 +2025-11-03 16:07:28.624514: Pseudo dice [np.float32(0.9288), np.float32(0.5787), np.float32(0.7212), np.float32(0.659), np.float32(0.8674), np.float32(0.7919), np.float32(0.883), np.float32(0.8906), np.float32(0.9654), np.float32(0.9291), np.float32(0.9416), np.float32(0.847), np.float32(0.7875), np.float32(0.8816), np.float32(0.9217), np.float32(0.3735), np.float32(0.2042)] +2025-11-03 16:07:28.625980: Epoch time: 518.45 s +2025-11-03 16:07:30.698770: +2025-11-03 16:07:30.704753: Epoch 806 +2025-11-03 16:07:30.714082: Current learning rate: 0.00229 +2025-11-03 16:15:48.324868: train_loss -0.4544 +2025-11-03 16:15:48.332148: val_loss -0.4327 +2025-11-03 16:15:48.338493: Pseudo dice [np.float32(0.9391), np.float32(0.783), np.float32(0.7214), np.float32(0.6194), np.float32(0.8828), np.float32(0.7697), np.float32(0.8972), np.float32(0.8882), np.float32(0.9591), np.float32(0.9618), np.float32(0.9651), np.float32(0.8443), np.float32(0.8229), np.float32(0.8924), np.float32(0.9562), np.float32(0.3974), np.float32(0.1748)] +2025-11-03 16:15:48.340442: Epoch time: 497.63 s +2025-11-03 16:16:02.327672: +2025-11-03 16:16:02.329275: Epoch 807 +2025-11-03 16:16:02.330792: Current learning rate: 0.00228 +2025-11-03 16:24:42.484424: train_loss -0.4609 +2025-11-03 16:24:42.527806: val_loss -0.5036 +2025-11-03 16:24:42.529407: Pseudo dice [np.float32(0.9446), np.float32(0.8162), np.float32(0.7592), np.float32(0.6458), np.float32(0.8839), np.float32(0.7993), np.float32(0.891), np.float32(0.8888), np.float32(0.9754), np.float32(0.9637), np.float32(0.9642), np.float32(0.8613), np.float32(0.7642), np.float32(0.8695), np.float32(0.9663), np.float32(0.4019), np.float32(0.1943)] +2025-11-03 16:24:42.530970: Epoch time: 520.16 s +2025-11-03 16:24:44.521517: +2025-11-03 16:24:44.525659: Epoch 808 +2025-11-03 16:24:44.528645: Current learning rate: 0.00226 +2025-11-03 16:33:17.394432: train_loss -0.4567 +2025-11-03 16:33:17.408915: val_loss -0.4921 +2025-11-03 16:33:17.412122: Pseudo dice [np.float32(0.9389), np.float32(0.7704), np.float32(0.7301), np.float32(0.7098), np.float32(0.8692), np.float32(0.8122), np.float32(0.8936), np.float32(0.8759), np.float32(0.9843), np.float32(0.9816), np.float32(0.9693), np.float32(0.8589), np.float32(0.8037), np.float32(0.8739), np.float32(0.9628), np.float32(0.3719), np.float32(0.2778)] +2025-11-03 16:33:17.414055: Epoch time: 512.88 s +2025-11-03 16:33:19.451907: +2025-11-03 16:33:19.453618: Epoch 809 +2025-11-03 16:33:19.454881: Current learning rate: 0.00225 +2025-11-03 16:41:55.429876: train_loss -0.4696 +2025-11-03 16:41:55.435183: val_loss -0.5121 +2025-11-03 16:41:55.436675: Pseudo dice [np.float32(0.9372), np.float32(0.7958), np.float32(0.7121), np.float32(0.7089), np.float32(0.8789), np.float32(0.8063), np.float32(0.8642), np.float32(0.8848), np.float32(0.9779), np.float32(0.9747), np.float32(0.9669), np.float32(0.8538), np.float32(0.7972), np.float32(0.8799), np.float32(0.9442), np.float32(0.3359), np.float32(0.3339)] +2025-11-03 16:41:55.439033: Epoch time: 515.98 s +2025-11-03 16:41:57.604881: +2025-11-03 16:41:57.608687: Epoch 810 +2025-11-03 16:41:57.610190: Current learning rate: 0.00224 +2025-11-03 16:50:32.392033: train_loss -0.4585 +2025-11-03 16:50:32.396882: val_loss -0.4795 +2025-11-03 16:50:32.398161: Pseudo dice [np.float32(0.9333), np.float32(0.7743), np.float32(0.7162), np.float32(0.6676), np.float32(0.8687), np.float32(0.7965), np.float32(0.862), np.float32(0.8899), np.float32(0.9488), np.float32(0.942), np.float32(0.9668), np.float32(0.8409), np.float32(0.7613), np.float32(0.8869), np.float32(0.9673), np.float32(0.1939), np.float32(0.212)] +2025-11-03 16:50:32.399226: Epoch time: 514.8 s +2025-11-03 16:50:34.647774: +2025-11-03 16:50:34.661341: Epoch 811 +2025-11-03 16:50:34.663420: Current learning rate: 0.00223 +2025-11-03 16:59:05.850575: train_loss -0.4739 +2025-11-03 16:59:05.859066: val_loss -0.4452 +2025-11-03 16:59:05.860403: Pseudo dice [np.float32(0.9441), np.float32(0.7695), np.float32(0.7453), np.float32(0.6798), np.float32(0.8706), np.float32(0.8314), np.float32(0.912), np.float32(0.89), np.float32(0.958), np.float32(0.9674), np.float32(0.9716), np.float32(0.8706), np.float32(0.7528), np.float32(0.8599), np.float32(0.9575), np.float32(0.241), np.float32(0.3056)] +2025-11-03 16:59:05.862553: Epoch time: 511.21 s +2025-11-03 16:59:08.041259: +2025-11-03 16:59:08.045096: Epoch 812 +2025-11-03 16:59:08.046385: Current learning rate: 0.00222 +2025-11-03 17:07:53.749169: train_loss -0.4583 +2025-11-03 17:07:53.756987: val_loss -0.4695 +2025-11-03 17:07:53.758409: Pseudo dice [np.float32(0.9307), np.float32(0.791), np.float32(0.7604), np.float32(0.6906), np.float32(0.8564), np.float32(0.8082), np.float32(0.8913), np.float32(0.8886), np.float32(0.9728), np.float32(0.963), np.float32(0.9615), np.float32(0.8759), np.float32(0.8056), np.float32(0.843), np.float32(0.933), np.float32(0.4227), np.float32(0.4482)] +2025-11-03 17:07:53.760401: Epoch time: 525.72 s +2025-11-03 17:07:56.038817: +2025-11-03 17:07:56.041212: Epoch 813 +2025-11-03 17:07:56.043212: Current learning rate: 0.00221 +2025-11-03 17:16:20.445263: train_loss -0.4741 +2025-11-03 17:16:20.457903: val_loss -0.5021 +2025-11-03 17:16:20.459687: Pseudo dice [np.float32(0.9481), np.float32(0.7898), np.float32(0.7204), np.float32(0.6885), np.float32(0.8505), np.float32(0.8032), np.float32(0.8648), np.float32(0.8958), np.float32(0.9566), np.float32(0.9613), np.float32(0.9661), np.float32(0.8547), np.float32(0.7977), np.float32(0.8735), np.float32(0.9641), np.float32(0.4169), np.float32(0.3238)] +2025-11-03 17:16:20.461112: Epoch time: 504.42 s +2025-11-03 17:16:22.604938: +2025-11-03 17:16:22.606538: Epoch 814 +2025-11-03 17:16:22.608330: Current learning rate: 0.0022 +2025-11-03 17:24:53.524485: train_loss -0.4615 +2025-11-03 17:24:53.538840: val_loss -0.4836 +2025-11-03 17:24:53.540390: Pseudo dice [np.float32(0.9372), np.float32(0.788), np.float32(0.7801), np.float32(0.6818), np.float32(0.892), np.float32(0.8033), np.float32(0.8968), np.float32(0.8863), np.float32(0.9744), np.float32(0.9685), np.float32(0.9694), np.float32(0.8604), np.float32(0.7923), np.float32(0.8898), np.float32(0.9703), np.float32(0.4037), np.float32(0.302)] +2025-11-03 17:24:53.541549: Epoch time: 510.92 s +2025-11-03 17:24:55.687401: +2025-11-03 17:24:55.692612: Epoch 815 +2025-11-03 17:24:55.696196: Current learning rate: 0.00219 +2025-11-03 17:33:36.387661: train_loss -0.4666 +2025-11-03 17:33:36.393116: val_loss -0.4463 +2025-11-03 17:33:36.394779: Pseudo dice [np.float32(0.94), np.float32(0.7834), np.float32(0.7211), np.float32(0.6462), np.float32(0.875), np.float32(0.8023), np.float32(0.9099), np.float32(0.8913), np.float32(0.9552), np.float32(0.9551), np.float32(0.9599), np.float32(0.8395), np.float32(0.7447), np.float32(0.8777), np.float32(0.9291), np.float32(0.3027), np.float32(0.3428)] +2025-11-03 17:33:36.430817: Epoch time: 520.71 s +2025-11-03 17:33:38.875342: +2025-11-03 17:33:38.877263: Epoch 816 +2025-11-03 17:33:38.878713: Current learning rate: 0.00218 +2025-11-03 17:41:58.812155: train_loss -0.4704 +2025-11-03 17:41:58.842656: val_loss -0.4942 +2025-11-03 17:41:58.844204: Pseudo dice [np.float32(0.9446), np.float32(0.7889), np.float32(0.739), np.float32(0.6498), np.float32(0.8653), np.float32(0.807), np.float32(0.894), np.float32(0.879), np.float32(0.9732), np.float32(0.9711), np.float32(0.9687), np.float32(0.8586), np.float32(0.8093), np.float32(0.879), np.float32(0.9696), np.float32(0.329), np.float32(0.3197)] +2025-11-03 17:41:58.845495: Epoch time: 499.94 s +2025-11-03 17:42:00.986478: +2025-11-03 17:42:00.989636: Epoch 817 +2025-11-03 17:42:00.993908: Current learning rate: 0.00217 +2025-11-03 17:50:18.290676: train_loss -0.4763 +2025-11-03 17:50:18.307729: val_loss -0.461 +2025-11-03 17:50:18.309174: Pseudo dice [np.float32(0.925), np.float32(0.7917), np.float32(0.7158), np.float32(0.6875), np.float32(0.8527), np.float32(0.7793), np.float32(0.8713), np.float32(0.8922), np.float32(0.9724), np.float32(0.9594), np.float32(0.9687), np.float32(0.8767), np.float32(0.7693), np.float32(0.8774), np.float32(0.9687), np.float32(0.3201), np.float32(0.2618)] +2025-11-03 17:50:18.312645: Epoch time: 497.31 s +2025-11-03 17:50:20.514290: +2025-11-03 17:50:20.516851: Epoch 818 +2025-11-03 17:50:20.518487: Current learning rate: 0.00216 +2025-11-03 17:59:05.346456: train_loss -0.4837 +2025-11-03 17:59:05.363099: val_loss -0.4617 +2025-11-03 17:59:05.366282: Pseudo dice [np.float32(0.9425), np.float32(0.7756), np.float32(0.716), np.float32(0.7156), np.float32(0.8386), np.float32(0.8031), np.float32(0.892), np.float32(0.8869), np.float32(0.9589), np.float32(0.9489), np.float32(0.9613), np.float32(0.856), np.float32(0.8154), np.float32(0.8639), np.float32(0.9344), np.float32(0.3356), np.float32(0.2149)] +2025-11-03 17:59:05.368049: Epoch time: 524.84 s +2025-11-03 17:59:07.561134: +2025-11-03 17:59:07.562555: Epoch 819 +2025-11-03 17:59:07.563886: Current learning rate: 0.00215 +2025-11-03 18:07:50.539958: train_loss -0.477 +2025-11-03 18:07:50.547061: val_loss -0.4798 +2025-11-03 18:07:50.548317: Pseudo dice [np.float32(0.9366), np.float32(0.7688), np.float32(0.7553), np.float32(0.7281), np.float32(0.88), np.float32(0.7952), np.float32(0.92), np.float32(0.8891), np.float32(0.9839), np.float32(0.9827), np.float32(0.9707), np.float32(0.8485), np.float32(0.8026), np.float32(0.8798), np.float32(0.9674), np.float32(0.3337), np.float32(0.401)] +2025-11-03 18:07:50.550115: Epoch time: 522.98 s +2025-11-03 18:07:52.663348: +2025-11-03 18:07:52.664746: Epoch 820 +2025-11-03 18:07:52.666483: Current learning rate: 0.00214 +2025-11-03 18:16:51.950644: train_loss -0.4649 +2025-11-03 18:16:51.957924: val_loss -0.4707 +2025-11-03 18:16:51.959565: Pseudo dice [np.float32(0.9345), np.float32(0.7572), np.float32(0.7413), np.float32(0.6808), np.float32(0.853), np.float32(0.8195), np.float32(0.9071), np.float32(0.8876), np.float32(0.9772), np.float32(0.9784), np.float32(0.968), np.float32(0.8532), np.float32(0.7842), np.float32(0.8593), np.float32(0.9621), np.float32(0.3353), np.float32(0.2661)] +2025-11-03 18:16:51.961287: Epoch time: 539.3 s +2025-11-03 18:16:54.784016: +2025-11-03 18:16:54.785949: Epoch 821 +2025-11-03 18:16:54.787565: Current learning rate: 0.00213 +2025-11-03 18:25:14.230601: train_loss -0.4676 +2025-11-03 18:25:14.235797: val_loss -0.4719 +2025-11-03 18:25:14.237451: Pseudo dice [np.float32(0.9412), np.float32(0.7675), np.float32(0.7007), np.float32(0.6901), np.float32(0.8737), np.float32(0.7951), np.float32(0.906), np.float32(0.8875), np.float32(0.9694), np.float32(0.9553), np.float32(0.9659), np.float32(0.8353), np.float32(0.7915), np.float32(0.8775), np.float32(0.9642), np.float32(0.3364), np.float32(0.2326)] +2025-11-03 18:25:14.238878: Epoch time: 499.46 s +2025-11-03 18:25:16.506253: +2025-11-03 18:25:16.517406: Epoch 822 +2025-11-03 18:25:16.518665: Current learning rate: 0.00212 +2025-11-03 18:33:51.396100: train_loss -0.4539 +2025-11-03 18:33:51.402081: val_loss -0.4523 +2025-11-03 18:33:51.403696: Pseudo dice [np.float32(0.9404), np.float32(0.7942), np.float32(0.7321), np.float32(0.6129), np.float32(0.8737), np.float32(0.7856), np.float32(0.8642), np.float32(0.8871), np.float32(0.981), np.float32(0.9824), np.float32(0.9678), np.float32(0.8805), np.float32(0.7962), np.float32(0.8783), np.float32(0.9546), np.float32(0.2451), np.float32(0.2033)] +2025-11-03 18:33:51.405744: Epoch time: 514.89 s +2025-11-03 18:33:53.418778: +2025-11-03 18:33:53.424661: Epoch 823 +2025-11-03 18:33:53.430281: Current learning rate: 0.0021 +2025-11-03 18:42:42.284436: train_loss -0.4806 +2025-11-03 18:42:42.289368: val_loss -0.4852 +2025-11-03 18:42:42.290761: Pseudo dice [np.float32(0.9049), np.float32(0.7776), np.float32(0.7208), np.float32(0.6353), np.float32(0.8771), np.float32(0.798), np.float32(0.9139), np.float32(0.8876), np.float32(0.9802), np.float32(0.9782), np.float32(0.9664), np.float32(0.8548), np.float32(0.8003), np.float32(0.8814), np.float32(0.9682), np.float32(0.3092), np.float32(0.3418)] +2025-11-03 18:42:42.292344: Epoch time: 528.87 s +2025-11-03 18:42:44.528008: +2025-11-03 18:42:44.545813: Epoch 824 +2025-11-03 18:42:44.551713: Current learning rate: 0.00209 +2025-11-03 18:51:14.053787: train_loss -0.4587 +2025-11-03 18:51:14.063651: val_loss -0.4901 +2025-11-03 18:51:14.065709: Pseudo dice [np.float32(0.9472), np.float32(0.7536), np.float32(0.7476), np.float32(0.6875), np.float32(0.8584), np.float32(0.8121), np.float32(0.9211), np.float32(0.8774), np.float32(0.981), np.float32(0.9827), np.float32(0.9691), np.float32(0.8551), np.float32(0.8036), np.float32(0.8745), np.float32(0.9626), np.float32(0.3843), np.float32(0.3223)] +2025-11-03 18:51:14.068550: Epoch time: 509.53 s +2025-11-03 18:51:16.078230: +2025-11-03 18:51:16.082114: Epoch 825 +2025-11-03 18:51:16.083441: Current learning rate: 0.00208 +2025-11-03 18:59:54.577062: train_loss -0.4311 +2025-11-03 18:59:54.581602: val_loss -0.4572 +2025-11-03 18:59:54.583480: Pseudo dice [np.float32(0.9366), np.float32(0.7557), np.float32(0.7146), np.float32(0.691), np.float32(0.8673), np.float32(0.7801), np.float32(0.9012), np.float32(0.8851), np.float32(0.9706), np.float32(0.9669), np.float32(0.9625), np.float32(0.8415), np.float32(0.8121), np.float32(0.8387), np.float32(0.9709), np.float32(0.2625), np.float32(0.2642)] +2025-11-03 18:59:54.584756: Epoch time: 518.5 s +2025-11-03 18:59:56.646203: +2025-11-03 18:59:56.647929: Epoch 826 +2025-11-03 18:59:56.649476: Current learning rate: 0.00207 +2025-11-03 19:08:38.528636: train_loss -0.4647 +2025-11-03 19:08:38.587748: val_loss -0.5018 +2025-11-03 19:08:38.589345: Pseudo dice [np.float32(0.9397), np.float32(0.5654), np.float32(0.7118), np.float32(0.716), np.float32(0.8747), np.float32(0.8211), np.float32(0.8989), np.float32(0.8693), np.float32(0.9717), np.float32(0.9755), np.float32(0.9711), np.float32(0.8626), np.float32(0.7715), np.float32(0.8669), np.float32(0.9701), np.float32(0.2791), np.float32(0.2747)] +2025-11-03 19:08:38.590728: Epoch time: 521.89 s +2025-11-03 19:08:40.502002: +2025-11-03 19:08:40.508237: Epoch 827 +2025-11-03 19:08:40.511053: Current learning rate: 0.00206 +2025-11-03 19:17:11.835946: train_loss -0.4727 +2025-11-03 19:17:11.868253: val_loss -0.4571 +2025-11-03 19:17:11.870061: Pseudo dice [np.float32(0.9271), np.float32(0.8037), np.float32(0.7315), np.float32(0.6746), np.float32(0.8538), np.float32(0.7923), np.float32(0.9006), np.float32(0.8972), np.float32(0.9633), np.float32(0.9589), np.float32(0.9631), np.float32(0.8404), np.float32(0.7574), np.float32(0.8709), np.float32(0.9074), np.float32(0.2928), np.float32(0.4181)] +2025-11-03 19:17:11.871706: Epoch time: 511.34 s +2025-11-03 19:17:13.920871: +2025-11-03 19:17:13.922354: Epoch 828 +2025-11-03 19:17:13.923893: Current learning rate: 0.00205 +2025-11-03 19:25:34.787013: train_loss -0.4557 +2025-11-03 19:25:34.828941: val_loss -0.4672 +2025-11-03 19:25:34.831860: Pseudo dice [np.float32(0.9158), np.float32(0.7976), np.float32(0.7729), np.float32(0.6007), np.float32(0.8579), np.float32(0.8187), np.float32(0.8965), np.float32(0.8885), np.float32(0.9747), np.float32(0.9781), np.float32(0.9694), np.float32(0.844), np.float32(0.7833), np.float32(0.8822), np.float32(0.9579), np.float32(0.3134), np.float32(0.2606)] +2025-11-03 19:25:34.833436: Epoch time: 500.87 s +2025-11-03 19:25:36.990413: +2025-11-03 19:25:36.992098: Epoch 829 +2025-11-03 19:25:36.993968: Current learning rate: 0.00204 +2025-11-03 19:34:24.239809: train_loss -0.4752 +2025-11-03 19:34:24.249661: val_loss -0.498 +2025-11-03 19:34:24.251436: Pseudo dice [np.float32(0.9467), np.float32(0.7773), np.float32(0.7497), np.float32(0.6644), np.float32(0.8794), np.float32(0.8073), np.float32(0.876), np.float32(0.8788), np.float32(0.9601), np.float32(0.9637), np.float32(0.9621), np.float32(0.8533), np.float32(0.7872), np.float32(0.8909), np.float32(0.927), np.float32(0.3673), np.float32(0.3837)] +2025-11-03 19:34:24.253929: Epoch time: 527.25 s +2025-11-03 19:34:26.225322: +2025-11-03 19:34:26.232440: Epoch 830 +2025-11-03 19:34:26.239265: Current learning rate: 0.00203 +2025-11-03 19:42:45.621795: train_loss -0.4687 +2025-11-03 19:42:45.636419: val_loss -0.5243 +2025-11-03 19:42:45.639122: Pseudo dice [np.float32(0.9407), np.float32(0.7977), np.float32(0.7628), np.float32(0.6766), np.float32(0.878), np.float32(0.7975), np.float32(0.8722), np.float32(0.8916), np.float32(0.9831), np.float32(0.9831), np.float32(0.9692), np.float32(0.8703), np.float32(0.8167), np.float32(0.8642), np.float32(0.9597), np.float32(0.4579), np.float32(0.3945)] +2025-11-03 19:42:45.655484: Epoch time: 499.4 s +2025-11-03 19:42:47.461259: +2025-11-03 19:42:47.470951: Epoch 831 +2025-11-03 19:42:47.473762: Current learning rate: 0.00202 +2025-11-03 19:51:26.299810: train_loss -0.4818 +2025-11-03 19:51:26.389066: val_loss -0.4753 +2025-11-03 19:51:26.391011: Pseudo dice [np.float32(0.9213), np.float32(0.7621), np.float32(0.752), np.float32(0.6719), np.float32(0.8603), np.float32(0.7993), np.float32(0.8805), np.float32(0.8937), np.float32(0.9638), np.float32(0.9583), np.float32(0.9652), np.float32(0.8792), np.float32(0.8096), np.float32(0.9017), np.float32(0.9524), np.float32(0.3765), np.float32(0.3784)] +2025-11-03 19:51:26.393315: Epoch time: 518.85 s +2025-11-03 19:51:43.457844: +2025-11-03 19:51:43.459508: Epoch 832 +2025-11-03 19:51:43.461477: Current learning rate: 0.00201 +2025-11-03 20:00:27.800715: train_loss -0.4716 +2025-11-03 20:00:27.816101: val_loss -0.4281 +2025-11-03 20:00:27.817477: Pseudo dice [np.float32(0.9171), np.float32(0.797), np.float32(0.804), np.float32(0.6638), np.float32(0.8123), np.float32(0.8102), np.float32(0.8934), np.float32(0.8688), np.float32(0.9646), np.float32(0.9617), np.float32(0.9622), np.float32(0.8252), np.float32(0.7825), np.float32(0.8618), np.float32(0.9622), np.float32(0.433), np.float32(0.4126)] +2025-11-03 20:00:27.818803: Epoch time: 524.35 s +2025-11-03 20:00:29.725721: +2025-11-03 20:00:29.727425: Epoch 833 +2025-11-03 20:00:29.729228: Current learning rate: 0.002 +2025-11-03 20:08:50.541069: train_loss -0.4768 +2025-11-03 20:08:50.547260: val_loss -0.4659 +2025-11-03 20:08:50.549282: Pseudo dice [np.float32(0.9387), np.float32(0.8068), np.float32(0.7351), np.float32(0.7072), np.float32(0.8784), np.float32(0.8023), np.float32(0.9202), np.float32(0.8872), np.float32(0.9722), np.float32(0.9764), np.float32(0.9673), np.float32(0.8715), np.float32(0.8048), np.float32(0.8574), np.float32(0.9138), np.float32(0.5019), np.float32(0.4188)] +2025-11-03 20:08:50.608151: Epoch time: 500.82 s +2025-11-03 20:08:50.609520: Yayy! New best EMA pseudo Dice: 0.8029999732971191 +2025-11-03 20:08:56.054713: +2025-11-03 20:08:56.056114: Epoch 834 +2025-11-03 20:08:56.057516: Current learning rate: 0.00199 +2025-11-03 20:17:27.334286: train_loss -0.4618 +2025-11-03 20:17:27.342407: val_loss -0.4296 +2025-11-03 20:17:27.347340: Pseudo dice [np.float32(0.9343), np.float32(0.7818), np.float32(0.6791), np.float32(0.634), np.float32(0.8392), np.float32(0.7835), np.float32(0.8805), np.float32(0.8814), np.float32(0.96), np.float32(0.9705), np.float32(0.9665), np.float32(0.866), np.float32(0.7994), np.float32(0.8562), np.float32(0.9665), np.float32(0.1661), np.float32(0.1624)] +2025-11-03 20:17:27.350045: Epoch time: 511.28 s +2025-11-03 20:17:29.140375: +2025-11-03 20:17:29.142041: Epoch 835 +2025-11-03 20:17:29.143204: Current learning rate: 0.00198 +2025-11-03 20:26:06.014678: train_loss -0.4662 +2025-11-03 20:26:06.019183: val_loss -0.4626 +2025-11-03 20:26:06.021205: Pseudo dice [np.float32(0.9498), np.float32(0.3292), np.float32(0.7655), np.float32(0.6362), np.float32(0.8382), np.float32(0.8195), np.float32(0.8715), np.float32(0.8852), np.float32(0.9751), np.float32(0.9795), np.float32(0.9694), np.float32(0.867), np.float32(0.8214), np.float32(0.8716), np.float32(0.9632), np.float32(0.2361), np.float32(0.3138)] +2025-11-03 20:26:06.022485: Epoch time: 516.88 s +2025-11-03 20:26:08.009049: +2025-11-03 20:26:08.011456: Epoch 836 +2025-11-03 20:26:08.013215: Current learning rate: 0.00196 +2025-11-03 20:34:49.595723: train_loss -0.4549 +2025-11-03 20:34:49.600911: val_loss -0.4849 +2025-11-03 20:34:49.602880: Pseudo dice [np.float32(0.9386), np.float32(0.7957), np.float32(0.7399), np.float32(0.713), np.float32(0.871), np.float32(0.784), np.float32(0.9048), np.float32(0.8917), np.float32(0.9753), np.float32(0.9754), np.float32(0.9674), np.float32(0.8569), np.float32(0.7924), np.float32(0.8739), np.float32(0.9654), np.float32(0.1706), np.float32(0.2452)] +2025-11-03 20:34:49.605011: Epoch time: 521.59 s +2025-11-03 20:34:51.709731: +2025-11-03 20:34:51.711520: Epoch 837 +2025-11-03 20:34:51.713207: Current learning rate: 0.00195 +2025-11-03 20:43:26.838083: train_loss -0.466 +2025-11-03 20:43:26.848410: val_loss -0.4909 +2025-11-03 20:43:26.851031: Pseudo dice [np.float32(0.9374), np.float32(0.8243), np.float32(0.7686), np.float32(0.6361), np.float32(0.8599), np.float32(0.7969), np.float32(0.9196), np.float32(0.8822), np.float32(0.9659), np.float32(0.9697), np.float32(0.9664), np.float32(0.8607), np.float32(0.8274), np.float32(0.8643), np.float32(0.9646), np.float32(0.2572), np.float32(0.2155)] +2025-11-03 20:43:26.852632: Epoch time: 515.13 s +2025-11-03 20:43:28.756229: +2025-11-03 20:43:28.758606: Epoch 838 +2025-11-03 20:43:28.759949: Current learning rate: 0.00194 +2025-11-03 20:52:07.124030: train_loss -0.4695 +2025-11-03 20:52:07.133609: val_loss -0.4744 +2025-11-03 20:52:07.134949: Pseudo dice [np.float32(0.9463), np.float32(0.8007), np.float32(0.6929), np.float32(0.628), np.float32(0.8563), np.float32(0.8086), np.float32(0.8131), np.float32(0.8949), np.float32(0.9817), np.float32(0.9822), np.float32(0.9663), np.float32(0.8464), np.float32(0.7937), np.float32(0.8834), np.float32(0.9695), np.float32(0.378), np.float32(0.3905)] +2025-11-03 20:52:07.136445: Epoch time: 518.37 s +2025-11-03 20:52:09.418159: +2025-11-03 20:52:09.419658: Epoch 839 +2025-11-03 20:52:09.421785: Current learning rate: 0.00193 +2025-11-03 21:00:39.335573: train_loss -0.4804 +2025-11-03 21:00:39.340652: val_loss -0.5058 +2025-11-03 21:00:39.342019: Pseudo dice [np.float32(0.9306), np.float32(0.795), np.float32(0.7694), np.float32(0.6548), np.float32(0.8802), np.float32(0.7995), np.float32(0.913), np.float32(0.8827), np.float32(0.9782), np.float32(0.979), np.float32(0.9665), np.float32(0.8696), np.float32(0.8097), np.float32(0.8824), np.float32(0.963), np.float32(0.4057), np.float32(0.4159)] +2025-11-03 21:00:39.343395: Epoch time: 509.92 s +2025-11-03 21:00:41.399383: +2025-11-03 21:00:41.400688: Epoch 840 +2025-11-03 21:00:41.401769: Current learning rate: 0.00192 +2025-11-03 21:09:11.184290: train_loss -0.4706 +2025-11-03 21:09:11.188761: val_loss -0.4731 +2025-11-03 21:09:11.190124: Pseudo dice [np.float32(0.9401), np.float32(0.8131), np.float32(0.7455), np.float32(0.6671), np.float32(0.8777), np.float32(0.7867), np.float32(0.8831), np.float32(0.8828), np.float32(0.9773), np.float32(0.9478), np.float32(0.9623), np.float32(0.8452), np.float32(0.7923), np.float32(0.8896), np.float32(0.9669), np.float32(0.3855), np.float32(0.2388)] +2025-11-03 21:09:11.191406: Epoch time: 509.79 s +2025-11-03 21:09:13.278371: +2025-11-03 21:09:13.280047: Epoch 841 +2025-11-03 21:09:13.281934: Current learning rate: 0.00191 +2025-11-03 21:17:58.721375: train_loss -0.4634 +2025-11-03 21:17:58.843152: val_loss -0.5072 +2025-11-03 21:17:58.844867: Pseudo dice [np.float32(0.9491), np.float32(0.8349), np.float32(0.7618), np.float32(0.6573), np.float32(0.8759), np.float32(0.7866), np.float32(0.8916), np.float32(0.8844), np.float32(0.9785), np.float32(0.9611), np.float32(0.9595), np.float32(0.8531), np.float32(0.8013), np.float32(0.8837), np.float32(0.9478), np.float32(0.3856), np.float32(0.2839)] +2025-11-03 21:17:58.846547: Epoch time: 525.45 s +2025-11-03 21:18:00.866244: +2025-11-03 21:18:00.867692: Epoch 842 +2025-11-03 21:18:00.869582: Current learning rate: 0.0019 +2025-11-03 21:26:42.721590: train_loss -0.471 +2025-11-03 21:26:42.730196: val_loss -0.4269 +2025-11-03 21:26:42.731647: Pseudo dice [np.float32(0.9202), np.float32(0.7986), np.float32(0.7309), np.float32(0.6591), np.float32(0.863), np.float32(0.8139), np.float32(0.7621), np.float32(0.8753), np.float32(0.9442), np.float32(0.927), np.float32(0.9652), np.float32(0.8785), np.float32(0.7682), np.float32(0.8544), np.float32(0.9631), np.float32(0.256), np.float32(0.2408)] +2025-11-03 21:26:42.733118: Epoch time: 521.86 s +2025-11-03 21:26:44.831493: +2025-11-03 21:26:44.832884: Epoch 843 +2025-11-03 21:26:44.834104: Current learning rate: 0.00189 +2025-11-03 21:35:16.405520: train_loss -0.4658 +2025-11-03 21:35:16.410574: val_loss -0.4222 +2025-11-03 21:35:16.412230: Pseudo dice [np.float32(0.9313), np.float32(0.7606), np.float32(0.7312), np.float32(0.6687), np.float32(0.8807), np.float32(0.8007), np.float32(0.8681), np.float32(0.8908), np.float32(0.9705), np.float32(0.9719), np.float32(0.968), np.float32(0.8575), np.float32(0.7398), np.float32(0.8622), np.float32(0.9118), np.float32(0.4354), np.float32(0.3028)] +2025-11-03 21:35:16.413377: Epoch time: 511.58 s +2025-11-03 21:35:18.551406: +2025-11-03 21:35:18.552924: Epoch 844 +2025-11-03 21:35:18.554245: Current learning rate: 0.00188 +2025-11-03 21:43:52.099796: train_loss -0.4713 +2025-11-03 21:43:52.104597: val_loss -0.476 +2025-11-03 21:43:52.106029: Pseudo dice [np.float32(0.9333), np.float32(0.802), np.float32(0.753), np.float32(0.6778), np.float32(0.887), np.float32(0.8075), np.float32(0.909), np.float32(0.867), np.float32(0.9765), np.float32(0.9733), np.float32(0.9683), np.float32(0.8458), np.float32(0.7912), np.float32(0.8964), np.float32(0.9607), np.float32(0.3479), np.float32(0.1949)] +2025-11-03 21:43:52.107579: Epoch time: 513.55 s +2025-11-03 21:43:54.092644: +2025-11-03 21:43:54.102150: Epoch 845 +2025-11-03 21:43:54.104116: Current learning rate: 0.00187 +2025-11-03 21:52:38.532227: train_loss -0.4683 +2025-11-03 21:52:38.537457: val_loss -0.5351 +2025-11-03 21:52:38.538867: Pseudo dice [np.float32(0.9479), np.float32(0.6588), np.float32(0.7477), np.float32(0.742), np.float32(0.8646), np.float32(0.794), np.float32(0.9072), np.float32(0.9045), np.float32(0.9784), np.float32(0.9623), np.float32(0.9677), np.float32(0.8518), np.float32(0.7945), np.float32(0.8721), np.float32(0.9592), np.float32(0.3976), np.float32(0.1961)] +2025-11-03 21:52:38.540446: Epoch time: 524.44 s +2025-11-03 21:52:40.855293: +2025-11-03 21:52:40.857446: Epoch 846 +2025-11-03 21:52:40.859096: Current learning rate: 0.00186 +2025-11-03 22:01:10.682391: train_loss -0.4454 +2025-11-03 22:01:10.689483: val_loss -0.4802 +2025-11-03 22:01:10.690738: Pseudo dice [np.float32(0.9368), np.float32(0.7868), np.float32(0.7176), np.float32(0.6951), np.float32(0.8934), np.float32(0.8212), np.float32(0.9042), np.float32(0.8793), np.float32(0.9772), np.float32(0.9778), np.float32(0.9671), np.float32(0.8678), np.float32(0.7894), np.float32(0.8844), np.float32(0.9554), np.float32(0.4249), np.float32(0.328)] +2025-11-03 22:01:10.692463: Epoch time: 509.83 s +2025-11-03 22:01:12.760445: +2025-11-03 22:01:12.764645: Epoch 847 +2025-11-03 22:01:12.766309: Current learning rate: 0.00185 +2025-11-03 22:09:46.518824: train_loss -0.4743 +2025-11-03 22:09:46.532919: val_loss -0.4454 +2025-11-03 22:09:46.535051: Pseudo dice [np.float32(0.9385), np.float32(0.7565), np.float32(0.7319), np.float32(0.6021), np.float32(0.8645), np.float32(0.7791), np.float32(0.9137), np.float32(0.8867), np.float32(0.9462), np.float32(0.9337), np.float32(0.9682), np.float32(0.8553), np.float32(0.784), np.float32(0.8723), np.float32(0.9641), np.float32(0.391), np.float32(0.2209)] +2025-11-03 22:09:46.537285: Epoch time: 513.76 s +2025-11-03 22:09:48.603438: +2025-11-03 22:09:48.605261: Epoch 848 +2025-11-03 22:09:48.607014: Current learning rate: 0.00184 +2025-11-03 22:18:28.709095: train_loss -0.4828 +2025-11-03 22:18:28.715083: val_loss -0.5321 +2025-11-03 22:18:28.716480: Pseudo dice [np.float32(0.933), np.float32(0.7878), np.float32(0.7407), np.float32(0.7023), np.float32(0.8763), np.float32(0.8178), np.float32(0.9205), np.float32(0.8839), np.float32(0.9712), np.float32(0.9676), np.float32(0.9688), np.float32(0.8608), np.float32(0.8131), np.float32(0.8483), np.float32(0.9673), np.float32(0.3766), np.float32(0.273)] +2025-11-03 22:18:28.719170: Epoch time: 520.11 s +2025-11-03 22:18:30.607394: +2025-11-03 22:18:30.609121: Epoch 849 +2025-11-03 22:18:30.610744: Current learning rate: 0.00182 +2025-11-03 22:27:14.815422: train_loss -0.4835 +2025-11-03 22:27:14.823314: val_loss -0.4347 +2025-11-03 22:27:14.825169: Pseudo dice [np.float32(0.9199), np.float32(0.7524), np.float32(0.6944), np.float32(0.652), np.float32(0.8758), np.float32(0.8249), np.float32(0.8948), np.float32(0.8595), np.float32(0.9818), np.float32(0.9808), np.float32(0.9678), np.float32(0.853), np.float32(0.736), np.float32(0.8839), np.float32(0.9637), np.float32(0.1555), np.float32(0.1737)] +2025-11-03 22:27:14.833636: Epoch time: 524.21 s +2025-11-03 22:27:20.777904: +2025-11-03 22:27:20.784240: Epoch 850 +2025-11-03 22:27:20.789171: Current learning rate: 0.00181 +2025-11-03 22:36:10.966336: train_loss -0.4701 +2025-11-03 22:36:10.973998: val_loss -0.5028 +2025-11-03 22:36:10.975612: Pseudo dice [np.float32(0.9342), np.float32(0.8064), np.float32(0.74), np.float32(0.6882), np.float32(0.8719), np.float32(0.8066), np.float32(0.8932), np.float32(0.8969), np.float32(0.9807), np.float32(0.9802), np.float32(0.9657), np.float32(0.8444), np.float32(0.7785), np.float32(0.8649), np.float32(0.9641), np.float32(0.319), np.float32(0.3381)] +2025-11-03 22:36:10.976898: Epoch time: 530.25 s +2025-11-03 22:36:12.787973: +2025-11-03 22:36:12.789711: Epoch 851 +2025-11-03 22:36:12.791275: Current learning rate: 0.0018 +2025-11-03 22:44:52.619562: train_loss -0.4761 +2025-11-03 22:44:52.624318: val_loss -0.4942 +2025-11-03 22:44:52.625907: Pseudo dice [np.float32(0.9323), np.float32(0.8083), np.float32(0.7396), np.float32(0.6786), np.float32(0.8596), np.float32(0.7794), np.float32(0.895), np.float32(0.885), np.float32(0.9783), np.float32(0.975), np.float32(0.963), np.float32(0.8553), np.float32(0.7824), np.float32(0.8673), np.float32(0.9668), np.float32(0.3638), np.float32(0.3597)] +2025-11-03 22:44:52.627652: Epoch time: 519.84 s +2025-11-03 22:44:54.475394: +2025-11-03 22:44:54.476966: Epoch 852 +2025-11-03 22:44:54.478472: Current learning rate: 0.00179 +2025-11-03 22:53:21.628780: train_loss -0.4865 +2025-11-03 22:53:21.638158: val_loss -0.5127 +2025-11-03 22:53:21.639466: Pseudo dice [np.float32(0.9377), np.float32(0.7813), np.float32(0.7482), np.float32(0.6398), np.float32(0.903), np.float32(0.8288), np.float32(0.9187), np.float32(0.8897), np.float32(0.981), np.float32(0.9815), np.float32(0.9687), np.float32(0.8499), np.float32(0.7939), np.float32(0.8867), np.float32(0.9677), np.float32(0.3853), np.float32(0.3603)] +2025-11-03 22:53:21.641019: Epoch time: 507.16 s +2025-11-03 22:53:23.490098: +2025-11-03 22:53:23.492096: Epoch 853 +2025-11-03 22:53:23.500407: Current learning rate: 0.00178 +2025-11-03 23:01:48.957491: train_loss -0.4725 +2025-11-03 23:01:48.962142: val_loss -0.4682 +2025-11-03 23:01:48.963919: Pseudo dice [np.float32(0.9045), np.float32(0.7632), np.float32(0.6721), np.float32(0.6931), np.float32(0.8824), np.float32(0.8051), np.float32(0.9073), np.float32(0.891), np.float32(0.9745), np.float32(0.9714), np.float32(0.9687), np.float32(0.8573), np.float32(0.7759), np.float32(0.8746), np.float32(0.9628), np.float32(0.3471), np.float32(0.378)] +2025-11-03 23:01:48.965552: Epoch time: 505.47 s +2025-11-03 23:01:50.922007: +2025-11-03 23:01:50.923578: Epoch 854 +2025-11-03 23:01:50.925161: Current learning rate: 0.00177 +2025-11-03 23:10:31.587282: train_loss -0.463 +2025-11-03 23:10:31.599293: val_loss -0.4844 +2025-11-03 23:10:31.600812: Pseudo dice [np.float32(0.9436), np.float32(0.8171), np.float32(0.7344), np.float32(0.6558), np.float32(0.8866), np.float32(0.81), np.float32(0.8937), np.float32(0.8922), np.float32(0.9698), np.float32(0.9753), np.float32(0.9695), np.float32(0.8824), np.float32(0.8276), np.float32(0.8911), np.float32(0.9621), np.float32(0.3996), np.float32(0.3246)] +2025-11-03 23:10:31.601991: Epoch time: 520.67 s +2025-11-03 23:10:33.551324: +2025-11-03 23:10:33.553137: Epoch 855 +2025-11-03 23:10:33.554386: Current learning rate: 0.00176 +2025-11-03 23:19:20.730778: train_loss -0.4773 +2025-11-03 23:19:20.735858: val_loss -0.5038 +2025-11-03 23:19:20.737284: Pseudo dice [np.float32(0.941), np.float32(0.7577), np.float32(0.7413), np.float32(0.6639), np.float32(0.8878), np.float32(0.7904), np.float32(0.903), np.float32(0.8899), np.float32(0.9817), np.float32(0.9809), np.float32(0.9676), np.float32(0.8566), np.float32(0.8188), np.float32(0.8786), np.float32(0.9726), np.float32(0.2703), np.float32(0.2834)] +2025-11-03 23:19:20.740411: Epoch time: 527.18 s +2025-11-03 23:19:22.706356: +2025-11-03 23:19:22.707977: Epoch 856 +2025-11-03 23:19:22.709857: Current learning rate: 0.00175 +2025-11-03 23:28:02.511957: train_loss -0.4725 +2025-11-03 23:28:02.528397: val_loss -0.4857 +2025-11-03 23:28:02.529815: Pseudo dice [np.float32(0.9493), np.float32(0.7807), np.float32(0.7361), np.float32(0.7155), np.float32(0.8834), np.float32(0.7926), np.float32(0.9074), np.float32(0.8931), np.float32(0.9666), np.float32(0.969), np.float32(0.9704), np.float32(0.8331), np.float32(0.7773), np.float32(0.8913), np.float32(0.9672), np.float32(0.2341), np.float32(0.1659)] +2025-11-03 23:28:02.531037: Epoch time: 519.81 s +2025-11-03 23:28:05.046972: +2025-11-03 23:28:05.052923: Epoch 857 +2025-11-03 23:28:05.054378: Current learning rate: 0.00174 +2025-11-03 23:36:36.300074: train_loss -0.4847 +2025-11-03 23:36:36.307293: val_loss -0.4739 +2025-11-03 23:36:36.308879: Pseudo dice [np.float32(0.9385), np.float32(0.8175), np.float32(0.7408), np.float32(0.664), np.float32(0.8623), np.float32(0.8228), np.float32(0.9243), np.float32(0.8845), np.float32(0.9789), np.float32(0.9738), np.float32(0.9629), np.float32(0.8721), np.float32(0.8028), np.float32(0.8805), np.float32(0.9664), np.float32(0.2656), np.float32(0.2516)] +2025-11-03 23:36:36.310717: Epoch time: 511.26 s +2025-11-03 23:36:53.716071: +2025-11-03 23:36:53.717436: Epoch 858 +2025-11-03 23:36:53.718893: Current learning rate: 0.00173 +2025-11-03 23:45:21.580101: train_loss -0.4692 +2025-11-03 23:45:21.587957: val_loss -0.484 +2025-11-03 23:45:21.593633: Pseudo dice [np.float32(0.9398), np.float32(0.7957), np.float32(0.7323), np.float32(0.6791), np.float32(0.9001), np.float32(0.8171), np.float32(0.8213), np.float32(0.8892), np.float32(0.9823), np.float32(0.9835), np.float32(0.9681), np.float32(0.8554), np.float32(0.8274), np.float32(0.8992), np.float32(0.9282), np.float32(0.3665), np.float32(0.3726)] +2025-11-03 23:45:21.595456: Epoch time: 507.87 s +2025-11-03 23:45:23.522274: +2025-11-03 23:45:23.523710: Epoch 859 +2025-11-03 23:45:23.526349: Current learning rate: 0.00172 +2025-11-03 23:54:14.325986: train_loss -0.4792 +2025-11-03 23:54:14.398935: val_loss -0.4628 +2025-11-03 23:54:14.400681: Pseudo dice [np.float32(0.9361), np.float32(0.7987), np.float32(0.7463), np.float32(0.6506), np.float32(0.8723), np.float32(0.827), np.float32(0.8805), np.float32(0.8933), np.float32(0.9825), np.float32(0.985), np.float32(0.9689), np.float32(0.8677), np.float32(0.8062), np.float32(0.886), np.float32(0.9697), np.float32(0.4456), np.float32(0.2075)] +2025-11-03 23:54:14.401993: Epoch time: 530.81 s +2025-11-03 23:54:16.265645: +2025-11-03 23:54:16.267291: Epoch 860 +2025-11-03 23:54:16.268747: Current learning rate: 0.0017 +2025-11-04 00:02:37.190420: train_loss -0.4636 +2025-11-04 00:02:37.199153: val_loss -0.4818 +2025-11-04 00:02:37.201634: Pseudo dice [np.float32(0.9338), np.float32(0.8018), np.float32(0.7342), np.float32(0.7154), np.float32(0.8723), np.float32(0.7805), np.float32(0.9031), np.float32(0.8904), np.float32(0.9837), np.float32(0.9845), np.float32(0.9703), np.float32(0.8537), np.float32(0.7995), np.float32(0.8636), np.float32(0.932), np.float32(0.3079), np.float32(0.2895)] +2025-11-04 00:02:37.203149: Epoch time: 500.93 s +2025-11-04 00:02:39.419754: +2025-11-04 00:02:39.421189: Epoch 861 +2025-11-04 00:02:39.423420: Current learning rate: 0.00169 +2025-11-04 00:11:12.487176: train_loss -0.4842 +2025-11-04 00:11:12.495945: val_loss -0.4827 +2025-11-04 00:11:12.497473: Pseudo dice [np.float32(0.9349), np.float32(0.7708), np.float32(0.7473), np.float32(0.6631), np.float32(0.8722), np.float32(0.7937), np.float32(0.8975), np.float32(0.8889), np.float32(0.9587), np.float32(0.9568), np.float32(0.9656), np.float32(0.8694), np.float32(0.7884), np.float32(0.8773), np.float32(0.9251), np.float32(0.1247), np.float32(0.1084)] +2025-11-04 00:11:12.505914: Epoch time: 513.07 s +2025-11-04 00:11:14.366062: +2025-11-04 00:11:14.367501: Epoch 862 +2025-11-04 00:11:14.368870: Current learning rate: 0.00168 +2025-11-04 00:19:51.634605: train_loss -0.4625 +2025-11-04 00:19:51.643726: val_loss -0.4233 +2025-11-04 00:19:51.645239: Pseudo dice [np.float32(0.9223), np.float32(0.7587), np.float32(0.7477), np.float32(0.6077), np.float32(0.8728), np.float32(0.8103), np.float32(0.9281), np.float32(0.8913), np.float32(0.9809), np.float32(0.9833), np.float32(0.9683), np.float32(0.8582), np.float32(0.777), np.float32(0.8834), np.float32(0.9686), np.float32(0.3775), np.float32(0.1587)] +2025-11-04 00:19:51.721376: Epoch time: 517.27 s +2025-11-04 00:19:53.654009: +2025-11-04 00:19:53.658639: Epoch 863 +2025-11-04 00:19:53.661325: Current learning rate: 0.00167 +2025-11-04 00:28:39.797926: train_loss -0.473 +2025-11-04 00:28:39.809083: val_loss -0.5353 +2025-11-04 00:28:39.810338: Pseudo dice [np.float32(0.9458), np.float32(0.7757), np.float32(0.6998), np.float32(0.6905), np.float32(0.8933), np.float32(0.8339), np.float32(0.9264), np.float32(0.8973), np.float32(0.9835), np.float32(0.9841), np.float32(0.9705), np.float32(0.8634), np.float32(0.8047), np.float32(0.8778), np.float32(0.9621), np.float32(0.3801), np.float32(0.3238)] +2025-11-04 00:28:39.812360: Epoch time: 526.15 s +2025-11-04 00:28:41.745520: +2025-11-04 00:28:41.746759: Epoch 864 +2025-11-04 00:28:41.748295: Current learning rate: 0.00166 +2025-11-04 00:37:18.101563: train_loss -0.4869 +2025-11-04 00:37:18.132780: val_loss -0.4717 +2025-11-04 00:37:18.134342: Pseudo dice [np.float32(0.9476), np.float32(0.818), np.float32(0.7796), np.float32(0.7029), np.float32(0.8315), np.float32(0.8059), np.float32(0.8738), np.float32(0.8841), np.float32(0.9845), np.float32(0.9818), np.float32(0.9684), np.float32(0.865), np.float32(0.799), np.float32(0.8449), np.float32(0.9686), np.float32(0.2942), np.float32(0.3453)] +2025-11-04 00:37:18.150277: Epoch time: 516.36 s +2025-11-04 00:37:20.155658: +2025-11-04 00:37:20.158956: Epoch 865 +2025-11-04 00:37:20.164553: Current learning rate: 0.00165 +2025-11-04 00:45:54.684888: train_loss -0.4753 +2025-11-04 00:45:54.691875: val_loss -0.4608 +2025-11-04 00:45:54.693909: Pseudo dice [np.float32(0.9422), np.float32(0.7501), np.float32(0.6921), np.float32(0.676), np.float32(0.8351), np.float32(0.8009), np.float32(0.8991), np.float32(0.8794), np.float32(0.985), np.float32(0.9806), np.float32(0.9692), np.float32(0.8622), np.float32(0.7773), np.float32(0.8736), np.float32(0.9676), np.float32(0.3232), np.float32(0.4215)] +2025-11-04 00:45:54.695704: Epoch time: 514.53 s +2025-11-04 00:45:56.631135: +2025-11-04 00:45:56.633724: Epoch 866 +2025-11-04 00:45:56.639282: Current learning rate: 0.00164 +2025-11-04 00:54:37.568926: train_loss -0.4736 +2025-11-04 00:54:37.573977: val_loss -0.4585 +2025-11-04 00:54:37.575629: Pseudo dice [np.float32(0.9202), np.float32(0.7718), np.float32(0.7327), np.float32(0.6683), np.float32(0.8854), np.float32(0.8067), np.float32(0.8927), np.float32(0.8807), np.float32(0.9828), np.float32(0.983), np.float32(0.9677), np.float32(0.853), np.float32(0.7978), np.float32(0.8712), np.float32(0.9484), np.float32(0.3961), np.float32(0.4043)] +2025-11-04 00:54:37.576957: Epoch time: 520.94 s +2025-11-04 00:54:39.510863: +2025-11-04 00:54:39.513586: Epoch 867 +2025-11-04 00:54:39.515598: Current learning rate: 0.00163 +2025-11-04 01:03:07.877485: train_loss -0.4837 +2025-11-04 01:03:07.894327: val_loss -0.4696 +2025-11-04 01:03:07.897391: Pseudo dice [np.float32(0.9303), np.float32(0.8224), np.float32(0.7501), np.float32(0.6994), np.float32(0.8677), np.float32(0.8087), np.float32(0.864), np.float32(0.8965), np.float32(0.9797), np.float32(0.9635), np.float32(0.966), np.float32(0.8454), np.float32(0.7829), np.float32(0.8758), np.float32(0.965), np.float32(0.338), np.float32(0.1752)] +2025-11-04 01:03:07.899088: Epoch time: 508.38 s +2025-11-04 01:03:09.915311: +2025-11-04 01:03:09.917271: Epoch 868 +2025-11-04 01:03:09.918555: Current learning rate: 0.00162 +2025-11-04 01:12:05.904295: train_loss -0.4864 +2025-11-04 01:12:05.909556: val_loss -0.495 +2025-11-04 01:12:05.911060: Pseudo dice [np.float32(0.9473), np.float32(0.8111), np.float32(0.7591), np.float32(0.6229), np.float32(0.8694), np.float32(0.8062), np.float32(0.9083), np.float32(0.8856), np.float32(0.9848), np.float32(0.9816), np.float32(0.9692), np.float32(0.8558), np.float32(0.815), np.float32(0.8771), np.float32(0.9659), np.float32(0.4074), np.float32(0.4478)] +2025-11-04 01:12:05.912969: Epoch time: 535.99 s +2025-11-04 01:12:07.813248: +2025-11-04 01:12:07.814692: Epoch 869 +2025-11-04 01:12:07.816072: Current learning rate: 0.00161 +2025-11-04 01:20:58.523148: train_loss -0.4774 +2025-11-04 01:20:58.534420: val_loss -0.4878 +2025-11-04 01:20:58.535759: Pseudo dice [np.float32(0.928), np.float32(0.8077), np.float32(0.7514), np.float32(0.7095), np.float32(0.873), np.float32(0.8143), np.float32(0.935), np.float32(0.8861), np.float32(0.9414), np.float32(0.9269), np.float32(0.9675), np.float32(0.859), np.float32(0.8124), np.float32(0.8614), np.float32(0.9026), np.float32(0.2246), np.float32(0.182)] +2025-11-04 01:20:58.537442: Epoch time: 530.71 s +2025-11-04 01:21:00.708746: +2025-11-04 01:21:00.713196: Epoch 870 +2025-11-04 01:21:00.715090: Current learning rate: 0.00159 +2025-11-04 01:29:39.231128: train_loss -0.4716 +2025-11-04 01:29:39.238150: val_loss -0.5005 +2025-11-04 01:29:39.240850: Pseudo dice [np.float32(0.9406), np.float32(0.7712), np.float32(0.7351), np.float32(0.7336), np.float32(0.8723), np.float32(0.8313), np.float32(0.9213), np.float32(0.8765), np.float32(0.9748), np.float32(0.978), np.float32(0.9643), np.float32(0.8362), np.float32(0.8061), np.float32(0.8817), np.float32(0.9732), np.float32(0.4059), np.float32(0.3218)] +2025-11-04 01:29:39.244391: Epoch time: 518.53 s +2025-11-04 01:29:41.244832: +2025-11-04 01:29:41.246360: Epoch 871 +2025-11-04 01:29:41.247772: Current learning rate: 0.00158 +2025-11-04 01:38:21.751298: train_loss -0.4711 +2025-11-04 01:38:21.758730: val_loss -0.4822 +2025-11-04 01:38:21.760183: Pseudo dice [np.float32(0.9365), np.float32(0.7883), np.float32(0.7303), np.float32(0.7085), np.float32(0.8626), np.float32(0.8077), np.float32(0.9248), np.float32(0.8967), np.float32(0.9764), np.float32(0.9775), np.float32(0.9714), np.float32(0.8495), np.float32(0.7789), np.float32(0.8758), np.float32(0.9452), np.float32(0.3763), np.float32(0.1986)] +2025-11-04 01:38:21.762250: Epoch time: 520.51 s +2025-11-04 01:38:23.909284: +2025-11-04 01:38:23.911385: Epoch 872 +2025-11-04 01:38:23.913653: Current learning rate: 0.00157 +2025-11-04 01:46:54.722720: train_loss -0.4632 +2025-11-04 01:46:54.752175: val_loss -0.4567 +2025-11-04 01:46:54.754473: Pseudo dice [np.float32(0.9358), np.float32(0.7921), np.float32(0.7765), np.float32(0.6749), np.float32(0.8872), np.float32(0.7973), np.float32(0.911), np.float32(0.883), np.float32(0.9798), np.float32(0.9785), np.float32(0.9652), np.float32(0.8541), np.float32(0.8072), np.float32(0.8854), np.float32(0.9647), np.float32(0.4662), np.float32(0.3775)] +2025-11-04 01:46:54.755734: Epoch time: 510.83 s +2025-11-04 01:46:54.757056: Yayy! New best EMA pseudo Dice: 0.8037999868392944 +2025-11-04 01:47:00.182790: +2025-11-04 01:47:00.184790: Epoch 873 +2025-11-04 01:47:00.186124: Current learning rate: 0.00156 +2025-11-04 01:55:21.826530: train_loss -0.4768 +2025-11-04 01:55:21.841224: val_loss -0.516 +2025-11-04 01:55:21.843934: Pseudo dice [np.float32(0.948), np.float32(0.8084), np.float32(0.7545), np.float32(0.6486), np.float32(0.8651), np.float32(0.7885), np.float32(0.8928), np.float32(0.8908), np.float32(0.9814), np.float32(0.9734), np.float32(0.9676), np.float32(0.8588), np.float32(0.7956), np.float32(0.8885), np.float32(0.9696), np.float32(0.4541), np.float32(0.3805)] +2025-11-04 01:55:21.849252: Epoch time: 501.65 s +2025-11-04 01:55:21.851500: Yayy! New best EMA pseudo Dice: 0.8050000071525574 +2025-11-04 01:55:26.281229: +2025-11-04 01:55:26.286569: Epoch 874 +2025-11-04 01:55:26.289390: Current learning rate: 0.00155 +2025-11-04 02:04:09.780545: train_loss -0.4873 +2025-11-04 02:04:09.786762: val_loss -0.5052 +2025-11-04 02:04:09.789686: Pseudo dice [np.float32(0.9434), np.float32(0.7882), np.float32(0.737), np.float32(0.7124), np.float32(0.858), np.float32(0.7898), np.float32(0.8894), np.float32(0.8834), np.float32(0.9839), np.float32(0.9846), np.float32(0.9687), np.float32(0.8566), np.float32(0.8263), np.float32(0.8635), np.float32(0.9651), np.float32(0.3082), np.float32(0.2044)] +2025-11-04 02:04:09.819191: Epoch time: 523.5 s +2025-11-04 02:04:11.715503: +2025-11-04 02:04:11.717027: Epoch 875 +2025-11-04 02:04:11.718813: Current learning rate: 0.00154 +2025-11-04 02:12:53.097372: train_loss -0.473 +2025-11-04 02:12:53.105998: val_loss -0.4924 +2025-11-04 02:12:53.107304: Pseudo dice [np.float32(0.9361), np.float32(0.7904), np.float32(0.7561), np.float32(0.6319), np.float32(0.8743), np.float32(0.7981), np.float32(0.9046), np.float32(0.8908), np.float32(0.9839), np.float32(0.9811), np.float32(0.9698), np.float32(0.8635), np.float32(0.7949), np.float32(0.861), np.float32(0.9609), np.float32(0.2222), np.float32(0.289)] +2025-11-04 02:12:53.108595: Epoch time: 521.39 s +2025-11-04 02:12:55.059705: +2025-11-04 02:12:55.061069: Epoch 876 +2025-11-04 02:12:55.062485: Current learning rate: 0.00153 +2025-11-04 02:21:27.919551: train_loss -0.4641 +2025-11-04 02:21:27.932540: val_loss -0.492 +2025-11-04 02:21:27.934162: Pseudo dice [np.float32(0.9222), np.float32(0.8189), np.float32(0.7785), np.float32(0.6941), np.float32(0.8665), np.float32(0.8329), np.float32(0.8944), np.float32(0.897), np.float32(0.9835), np.float32(0.9823), np.float32(0.9695), np.float32(0.8766), np.float32(0.8253), np.float32(0.9045), np.float32(0.969), np.float32(0.3796), np.float32(0.3622)] +2025-11-04 02:21:27.935603: Epoch time: 512.86 s +2025-11-04 02:21:27.937679: Yayy! New best EMA pseudo Dice: 0.8051000237464905 +2025-11-04 02:21:32.879504: +2025-11-04 02:21:32.880934: Epoch 877 +2025-11-04 02:21:32.884171: Current learning rate: 0.00152 +2025-11-04 02:29:59.289548: train_loss -0.493 +2025-11-04 02:29:59.295252: val_loss -0.477 +2025-11-04 02:29:59.296808: Pseudo dice [np.float32(0.9411), np.float32(0.7942), np.float32(0.7456), np.float32(0.657), np.float32(0.8961), np.float32(0.8017), np.float32(0.9058), np.float32(0.8921), np.float32(0.9812), np.float32(0.9779), np.float32(0.9685), np.float32(0.8459), np.float32(0.8047), np.float32(0.8903), np.float32(0.9674), np.float32(0.4909), np.float32(0.3482)] +2025-11-04 02:29:59.298577: Epoch time: 506.41 s +2025-11-04 02:29:59.300451: Yayy! New best EMA pseudo Dice: 0.8064000010490417 +2025-11-04 02:30:03.636079: +2025-11-04 02:30:03.637442: Epoch 878 +2025-11-04 02:30:03.638771: Current learning rate: 0.00151 +2025-11-04 02:38:36.479916: train_loss -0.4714 +2025-11-04 02:38:36.515678: val_loss -0.5019 +2025-11-04 02:38:36.517315: Pseudo dice [np.float32(0.9467), np.float32(0.4925), np.float32(0.72), np.float32(0.7132), np.float32(0.8801), np.float32(0.8067), np.float32(0.9064), np.float32(0.8965), np.float32(0.9787), np.float32(0.9832), np.float32(0.9681), np.float32(0.8341), np.float32(0.7789), np.float32(0.8776), np.float32(0.9686), np.float32(0.4107), np.float32(0.3738)] +2025-11-04 02:38:36.520119: Epoch time: 512.85 s +2025-11-04 02:38:38.534669: +2025-11-04 02:38:38.536304: Epoch 879 +2025-11-04 02:38:38.537958: Current learning rate: 0.00149 +2025-11-04 02:47:09.470845: train_loss -0.472 +2025-11-04 02:47:09.482032: val_loss -0.4651 +2025-11-04 02:47:09.483562: Pseudo dice [np.float32(0.9491), np.float32(0.8056), np.float32(0.7678), np.float32(0.654), np.float32(0.8445), np.float32(0.8184), np.float32(0.8949), np.float32(0.8924), np.float32(0.9787), np.float32(0.9773), np.float32(0.9662), np.float32(0.8618), np.float32(0.7774), np.float32(0.8424), np.float32(0.9666), np.float32(0.3807), np.float32(0.3191)] +2025-11-04 02:47:09.484868: Epoch time: 510.94 s +2025-11-04 02:47:11.297035: +2025-11-04 02:47:11.298513: Epoch 880 +2025-11-04 02:47:11.300007: Current learning rate: 0.00148 +2025-11-04 02:56:04.427352: train_loss -0.4837 +2025-11-04 02:56:04.448868: val_loss -0.4904 +2025-11-04 02:56:04.450788: Pseudo dice [np.float32(0.9404), np.float32(0.7922), np.float32(0.7139), np.float32(0.674), np.float32(0.8871), np.float32(0.8088), np.float32(0.8643), np.float32(0.9043), np.float32(0.9674), np.float32(0.9658), np.float32(0.9675), np.float32(0.8478), np.float32(0.8059), np.float32(0.8826), np.float32(0.9598), np.float32(0.3609), np.float32(0.2159)] +2025-11-04 02:56:04.464607: Epoch time: 533.13 s +2025-11-04 02:56:06.579728: +2025-11-04 02:56:06.581728: Epoch 881 +2025-11-04 02:56:06.583140: Current learning rate: 0.00147 +2025-11-04 03:04:41.603945: train_loss -0.473 +2025-11-04 03:04:41.664304: val_loss -0.4623 +2025-11-04 03:04:41.665717: Pseudo dice [np.float32(0.9407), np.float32(0.7675), np.float32(0.7284), np.float32(0.6805), np.float32(0.8816), np.float32(0.8134), np.float32(0.9033), np.float32(0.8809), np.float32(0.9815), np.float32(0.9826), np.float32(0.967), np.float32(0.8667), np.float32(0.8157), np.float32(0.8842), np.float32(0.9665), np.float32(0.2114), np.float32(0.2007)] +2025-11-04 03:04:41.667051: Epoch time: 515.03 s +2025-11-04 03:04:43.626525: +2025-11-04 03:04:43.627944: Epoch 882 +2025-11-04 03:04:43.631812: Current learning rate: 0.00146 +2025-11-04 03:13:25.450833: train_loss -0.4798 +2025-11-04 03:13:25.459486: val_loss -0.4475 +2025-11-04 03:13:25.461076: Pseudo dice [np.float32(0.944), np.float32(0.8235), np.float32(0.742), np.float32(0.6772), np.float32(0.8319), np.float32(0.8052), np.float32(0.8496), np.float32(0.8863), np.float32(0.9754), np.float32(0.9768), np.float32(0.9579), np.float32(0.853), np.float32(0.8144), np.float32(0.8529), np.float32(0.953), np.float32(0.3426), np.float32(0.3842)] +2025-11-04 03:13:25.462860: Epoch time: 521.83 s +2025-11-04 03:13:27.344399: +2025-11-04 03:13:27.345712: Epoch 883 +2025-11-04 03:13:27.347061: Current learning rate: 0.00145 +2025-11-04 03:21:52.950572: train_loss -0.4772 +2025-11-04 03:21:52.958043: val_loss -0.518 +2025-11-04 03:21:52.959287: Pseudo dice [np.float32(0.9358), np.float32(0.7996), np.float32(0.7518), np.float32(0.6443), np.float32(0.885), np.float32(0.8377), np.float32(0.8948), np.float32(0.9134), np.float32(0.9801), np.float32(0.9815), np.float32(0.9704), np.float32(0.8637), np.float32(0.7635), np.float32(0.8861), np.float32(0.9637), np.float32(0.3914), np.float32(0.3906)] +2025-11-04 03:21:52.960724: Epoch time: 505.61 s +2025-11-04 03:21:55.033894: +2025-11-04 03:21:55.035551: Epoch 884 +2025-11-04 03:21:55.037071: Current learning rate: 0.00144 +2025-11-04 03:30:28.984358: train_loss -0.4626 +2025-11-04 03:30:28.991466: val_loss -0.5121 +2025-11-04 03:30:28.996687: Pseudo dice [np.float32(0.9527), np.float32(0.7915), np.float32(0.748), np.float32(0.7206), np.float32(0.8723), np.float32(0.8045), np.float32(0.8745), np.float32(0.8998), np.float32(0.9843), np.float32(0.9816), np.float32(0.9709), np.float32(0.8516), np.float32(0.8035), np.float32(0.885), np.float32(0.9685), np.float32(0.3731), np.float32(0.4009)] +2025-11-04 03:30:28.998414: Epoch time: 513.96 s +2025-11-04 03:30:30.909499: +2025-11-04 03:30:30.911498: Epoch 885 +2025-11-04 03:30:30.913371: Current learning rate: 0.00143 +2025-11-04 03:38:58.862864: train_loss -0.4968 +2025-11-04 03:38:58.867970: val_loss -0.4826 +2025-11-04 03:38:58.870448: Pseudo dice [np.float32(0.9277), np.float32(0.8196), np.float32(0.7093), np.float32(0.6334), np.float32(0.8837), np.float32(0.8302), np.float32(0.9044), np.float32(0.8862), np.float32(0.9596), np.float32(0.9572), np.float32(0.968), np.float32(0.8446), np.float32(0.8066), np.float32(0.8901), np.float32(0.9662), np.float32(0.3686), np.float32(0.3335)] +2025-11-04 03:38:58.873062: Epoch time: 507.96 s +2025-11-04 03:39:00.921302: +2025-11-04 03:39:00.923010: Epoch 886 +2025-11-04 03:39:00.926738: Current learning rate: 0.00142 +2025-11-04 03:47:40.879114: train_loss -0.4768 +2025-11-04 03:47:40.977420: val_loss -0.4917 +2025-11-04 03:47:41.007070: Pseudo dice [np.float32(0.9435), np.float32(0.7599), np.float32(0.7636), np.float32(0.704), np.float32(0.8942), np.float32(0.8216), np.float32(0.92), np.float32(0.8879), np.float32(0.9839), np.float32(0.9839), np.float32(0.9709), np.float32(0.8588), np.float32(0.7925), np.float32(0.8928), np.float32(0.9732), np.float32(0.4099), np.float32(0.3734)] +2025-11-04 03:47:41.035756: Epoch time: 519.96 s +2025-11-04 03:47:41.066195: Yayy! New best EMA pseudo Dice: 0.807200014591217 +2025-11-04 03:47:47.237200: +2025-11-04 03:47:47.241268: Epoch 887 +2025-11-04 03:47:47.242723: Current learning rate: 0.00141 +2025-11-04 03:56:09.611256: train_loss -0.4697 +2025-11-04 03:56:09.660591: val_loss -0.4464 +2025-11-04 03:56:09.663085: Pseudo dice [np.float32(0.9266), np.float32(0.8081), np.float32(0.7929), np.float32(0.6854), np.float32(0.8797), np.float32(0.8123), np.float32(0.8934), np.float32(0.8958), np.float32(0.974), np.float32(0.9819), np.float32(0.9672), np.float32(0.8508), np.float32(0.766), np.float32(0.8625), np.float32(0.9691), np.float32(0.1685), np.float32(0.2459)] +2025-11-04 03:56:09.665220: Epoch time: 502.38 s +2025-11-04 03:56:11.439889: +2025-11-04 03:56:11.441511: Epoch 888 +2025-11-04 03:56:11.442862: Current learning rate: 0.00139 +2025-11-04 04:04:34.007932: train_loss -0.4545 +2025-11-04 04:04:34.015783: val_loss -0.4589 +2025-11-04 04:04:34.017804: Pseudo dice [np.float32(0.9191), np.float32(0.5079), np.float32(0.7542), np.float32(0.6818), np.float32(0.8606), np.float32(0.7512), np.float32(0.8838), np.float32(0.8728), np.float32(0.981), np.float32(0.9822), np.float32(0.9631), np.float32(0.8448), np.float32(0.8118), np.float32(0.8763), np.float32(0.9588), np.float32(0.2367), np.float32(0.287)] +2025-11-04 04:04:34.020036: Epoch time: 502.57 s +2025-11-04 04:04:35.881990: +2025-11-04 04:04:35.884183: Epoch 889 +2025-11-04 04:04:35.885398: Current learning rate: 0.00138 +2025-11-04 04:13:06.410682: train_loss -0.4901 +2025-11-04 04:13:06.451926: val_loss -0.4833 +2025-11-04 04:13:06.453652: Pseudo dice [np.float32(0.9298), np.float32(0.8186), np.float32(0.741), np.float32(0.7717), np.float32(0.8881), np.float32(0.8494), np.float32(0.8972), np.float32(0.8946), np.float32(0.9811), np.float32(0.9805), np.float32(0.9714), np.float32(0.8617), np.float32(0.7892), np.float32(0.8898), np.float32(0.9736), np.float32(0.2997), np.float32(0.3526)] +2025-11-04 04:13:06.502198: Epoch time: 510.53 s +2025-11-04 04:13:08.583641: +2025-11-04 04:13:08.585518: Epoch 890 +2025-11-04 04:13:08.587126: Current learning rate: 0.00137 +2025-11-04 04:21:33.580061: train_loss -0.4831 +2025-11-04 04:21:33.584844: val_loss -0.4702 +2025-11-04 04:21:33.586054: Pseudo dice [np.float32(0.9257), np.float32(0.7642), np.float32(0.6881), np.float32(0.6643), np.float32(0.877), np.float32(0.786), np.float32(0.8958), np.float32(0.8879), np.float32(0.981), np.float32(0.9804), np.float32(0.9643), np.float32(0.8599), np.float32(0.7842), np.float32(0.8688), np.float32(0.968), np.float32(0.2539), np.float32(0.2033)] +2025-11-04 04:21:33.587491: Epoch time: 505.01 s +2025-11-04 04:21:36.605111: +2025-11-04 04:21:36.606830: Epoch 891 +2025-11-04 04:21:36.608529: Current learning rate: 0.00136 +2025-11-04 04:30:07.717953: train_loss -0.4813 +2025-11-04 04:30:07.727533: val_loss -0.5273 +2025-11-04 04:30:07.728715: Pseudo dice [np.float32(0.9285), np.float32(0.8075), np.float32(0.761), np.float32(0.7283), np.float32(0.8889), np.float32(0.8172), np.float32(0.9065), np.float32(0.8896), np.float32(0.9763), np.float32(0.9666), np.float32(0.968), np.float32(0.8555), np.float32(0.8223), np.float32(0.893), np.float32(0.9644), np.float32(0.4999), np.float32(0.535)] +2025-11-04 04:30:07.730115: Epoch time: 511.12 s +2025-11-04 04:30:09.768942: +2025-11-04 04:30:09.770344: Epoch 892 +2025-11-04 04:30:09.771578: Current learning rate: 0.00135 +2025-11-04 04:38:42.466277: train_loss -0.4702 +2025-11-04 04:38:42.478715: val_loss -0.4845 +2025-11-04 04:38:42.480520: Pseudo dice [np.float32(0.9503), np.float32(0.7891), np.float32(0.6892), np.float32(0.6887), np.float32(0.8871), np.float32(0.7914), np.float32(0.9163), np.float32(0.8974), np.float32(0.9736), np.float32(0.9719), np.float32(0.9683), np.float32(0.8639), np.float32(0.7909), np.float32(0.9072), np.float32(0.9669), np.float32(0.3752), np.float32(0.321)] +2025-11-04 04:38:42.482363: Epoch time: 512.7 s +2025-11-04 04:38:44.440462: +2025-11-04 04:38:44.443980: Epoch 893 +2025-11-04 04:38:44.452002: Current learning rate: 0.00134 +2025-11-04 04:47:16.405222: train_loss -0.485 +2025-11-04 04:47:16.438981: val_loss -0.487 +2025-11-04 04:47:16.440354: Pseudo dice [np.float32(0.9319), np.float32(0.7724), np.float32(0.7375), np.float32(0.6152), np.float32(0.8979), np.float32(0.787), np.float32(0.8492), np.float32(0.9036), np.float32(0.979), np.float32(0.9765), np.float32(0.966), np.float32(0.8741), np.float32(0.7876), np.float32(0.8891), np.float32(0.9711), np.float32(0.2781), np.float32(0.3262)] +2025-11-04 04:47:16.441779: Epoch time: 511.97 s +2025-11-04 04:47:18.343799: +2025-11-04 04:47:18.345151: Epoch 894 +2025-11-04 04:47:18.353407: Current learning rate: 0.00133 +2025-11-04 04:55:43.979642: train_loss -0.4494 +2025-11-04 04:55:43.984477: val_loss -0.4921 +2025-11-04 04:55:43.986012: Pseudo dice [np.float32(0.9322), np.float32(0.7925), np.float32(0.7243), np.float32(0.7066), np.float32(0.8882), np.float32(0.8102), np.float32(0.9095), np.float32(0.8906), np.float32(0.9669), np.float32(0.9683), np.float32(0.9663), np.float32(0.8562), np.float32(0.779), np.float32(0.8923), np.float32(0.9409), np.float32(0.2658), np.float32(0.2978)] +2025-11-04 04:55:43.987832: Epoch time: 505.64 s +2025-11-04 04:55:46.010446: +2025-11-04 04:55:46.012294: Epoch 895 +2025-11-04 04:55:46.013772: Current learning rate: 0.00132 +2025-11-04 05:04:29.674086: train_loss -0.4923 +2025-11-04 05:04:29.680465: val_loss -0.4781 +2025-11-04 05:04:29.682234: Pseudo dice [np.float32(0.9328), np.float32(0.7718), np.float32(0.7536), np.float32(0.6947), np.float32(0.87), np.float32(0.7938), np.float32(0.911), np.float32(0.8665), np.float32(0.9833), np.float32(0.9828), np.float32(0.9717), np.float32(0.869), np.float32(0.7762), np.float32(0.8689), np.float32(0.9689), np.float32(0.2016), np.float32(0.2833)] +2025-11-04 05:04:29.687888: Epoch time: 523.67 s +2025-11-04 05:04:31.574251: +2025-11-04 05:04:31.577317: Epoch 896 +2025-11-04 05:04:31.578607: Current learning rate: 0.0013 +2025-11-04 05:13:08.347465: train_loss -0.4843 +2025-11-04 05:13:08.352549: val_loss -0.4421 +2025-11-04 05:13:08.354080: Pseudo dice [np.float32(0.9333), np.float32(0.7704), np.float32(0.7309), np.float32(0.675), np.float32(0.8783), np.float32(0.7498), np.float32(0.9382), np.float32(0.8723), np.float32(0.9846), np.float32(0.9749), np.float32(0.9588), np.float32(0.8445), np.float32(0.7632), np.float32(0.8847), np.float32(0.9408), np.float32(0.3016), np.float32(0.4092)] +2025-11-04 05:13:08.355835: Epoch time: 516.78 s +2025-11-04 05:13:10.261912: +2025-11-04 05:13:10.263984: Epoch 897 +2025-11-04 05:13:10.265840: Current learning rate: 0.00129 +2025-11-04 05:21:56.291764: train_loss -0.486 +2025-11-04 05:21:56.303404: val_loss -0.4671 +2025-11-04 05:21:56.305547: Pseudo dice [np.float32(0.9322), np.float32(0.7957), np.float32(0.7638), np.float32(0.6718), np.float32(0.8729), np.float32(0.7962), np.float32(0.9138), np.float32(0.8807), np.float32(0.9815), np.float32(0.9617), np.float32(0.9717), np.float32(0.8669), np.float32(0.7984), np.float32(0.8735), np.float32(0.9658), np.float32(0.3847), np.float32(0.3303)] +2025-11-04 05:21:56.308833: Epoch time: 526.04 s +2025-11-04 05:21:58.331111: +2025-11-04 05:21:58.334168: Epoch 898 +2025-11-04 05:21:58.337470: Current learning rate: 0.00128 +2025-11-04 05:30:30.378168: train_loss -0.4706 +2025-11-04 05:30:30.386487: val_loss -0.4722 +2025-11-04 05:30:30.388325: Pseudo dice [np.float32(0.9454), np.float32(0.6689), np.float32(0.7232), np.float32(0.7195), np.float32(0.8829), np.float32(0.8243), np.float32(0.9243), np.float32(0.8986), np.float32(0.9728), np.float32(0.9743), np.float32(0.9644), np.float32(0.8527), np.float32(0.803), np.float32(0.8947), np.float32(0.961), np.float32(0.3372), np.float32(0.2804)] +2025-11-04 05:30:30.389731: Epoch time: 512.05 s +2025-11-04 05:30:32.360210: +2025-11-04 05:30:32.361730: Epoch 899 +2025-11-04 05:30:32.363790: Current learning rate: 0.00127 +2025-11-04 05:39:17.462202: train_loss -0.4774 +2025-11-04 05:39:17.474141: val_loss -0.4763 +2025-11-04 05:39:17.477123: Pseudo dice [np.float32(0.9389), np.float32(0.7843), np.float32(0.778), np.float32(0.6885), np.float32(0.8461), np.float32(0.8157), np.float32(0.9132), np.float32(0.8982), np.float32(0.9839), np.float32(0.9833), np.float32(0.9711), np.float32(0.865), np.float32(0.8023), np.float32(0.8629), np.float32(0.9661), np.float32(0.4225), np.float32(0.3756)] +2025-11-04 05:39:17.478851: Epoch time: 525.11 s +2025-11-04 05:39:22.627503: +2025-11-04 05:39:22.629071: Epoch 900 +2025-11-04 05:39:22.630516: Current learning rate: 0.00126 +2025-11-04 05:47:47.536180: train_loss -0.4888 +2025-11-04 05:47:47.541229: val_loss -0.4947 +2025-11-04 05:47:47.545696: Pseudo dice [np.float32(0.9224), np.float32(0.7703), np.float32(0.7348), np.float32(0.6586), np.float32(0.8445), np.float32(0.816), np.float32(0.8628), np.float32(0.9019), np.float32(0.979), np.float32(0.9793), np.float32(0.9691), np.float32(0.8654), np.float32(0.8028), np.float32(0.88), np.float32(0.9684), np.float32(0.3893), np.float32(0.3459)] +2025-11-04 05:47:47.548399: Epoch time: 504.91 s +2025-11-04 05:47:49.575763: +2025-11-04 05:47:49.577471: Epoch 901 +2025-11-04 05:47:49.578763: Current learning rate: 0.00125 +2025-11-04 05:56:23.448585: train_loss -0.4859 +2025-11-04 05:56:23.454084: val_loss -0.4889 +2025-11-04 05:56:23.455568: Pseudo dice [np.float32(0.9416), np.float32(0.8013), np.float32(0.7351), np.float32(0.6763), np.float32(0.85), np.float32(0.7997), np.float32(0.9247), np.float32(0.8986), np.float32(0.9685), np.float32(0.9639), np.float32(0.969), np.float32(0.8755), np.float32(0.8258), np.float32(0.8679), np.float32(0.9613), np.float32(0.3386), np.float32(0.3463)] +2025-11-04 05:56:23.456845: Epoch time: 513.88 s +2025-11-04 05:56:25.259380: +2025-11-04 05:56:25.260716: Epoch 902 +2025-11-04 05:56:25.262017: Current learning rate: 0.00124 +2025-11-04 06:05:06.374652: train_loss -0.469 +2025-11-04 06:05:06.387357: val_loss -0.4717 +2025-11-04 06:05:06.389207: Pseudo dice [np.float32(0.9474), np.float32(0.7863), np.float32(0.7107), np.float32(0.6043), np.float32(0.8992), np.float32(0.803), np.float32(0.9191), np.float32(0.8889), np.float32(0.9655), np.float32(0.9658), np.float32(0.9685), np.float32(0.8685), np.float32(0.8113), np.float32(0.8679), np.float32(0.9686), np.float32(0.4931), np.float32(0.5201)] +2025-11-04 06:05:06.390605: Epoch time: 521.12 s +2025-11-04 06:05:08.252009: +2025-11-04 06:05:08.255382: Epoch 903 +2025-11-04 06:05:08.256883: Current learning rate: 0.00122 +2025-11-04 06:13:33.155177: train_loss -0.4837 +2025-11-04 06:13:33.164680: val_loss -0.4619 +2025-11-04 06:13:33.166271: Pseudo dice [np.float32(0.9246), np.float32(0.7998), np.float32(0.7498), np.float32(0.6973), np.float32(0.8501), np.float32(0.8201), np.float32(0.9075), np.float32(0.8802), np.float32(0.9686), np.float32(0.9712), np.float32(0.9666), np.float32(0.8489), np.float32(0.7916), np.float32(0.8837), np.float32(0.9562), np.float32(0.4541), np.float32(0.4369)] +2025-11-04 06:13:33.168121: Epoch time: 504.91 s +2025-11-04 06:13:33.169362: Yayy! New best EMA pseudo Dice: 0.8082000017166138 +2025-11-04 06:13:38.127366: +2025-11-04 06:13:38.129753: Epoch 904 +2025-11-04 06:13:38.131353: Current learning rate: 0.00121 +2025-11-04 06:22:19.551078: train_loss -0.4829 +2025-11-04 06:22:19.558096: val_loss -0.4785 +2025-11-04 06:22:19.560042: Pseudo dice [np.float32(0.932), np.float32(0.8027), np.float32(0.7224), np.float32(0.6806), np.float32(0.8814), np.float32(0.8227), np.float32(0.9061), np.float32(0.8764), np.float32(0.9746), np.float32(0.9763), np.float32(0.9708), np.float32(0.8679), np.float32(0.7804), np.float32(0.8474), np.float32(0.9723), np.float32(0.3818), np.float32(0.3001)] +2025-11-04 06:22:19.561586: Epoch time: 521.43 s +2025-11-04 06:22:21.504882: +2025-11-04 06:22:21.506517: Epoch 905 +2025-11-04 06:22:21.508131: Current learning rate: 0.0012 +2025-11-04 06:30:58.487090: train_loss -0.4629 +2025-11-04 06:30:58.493718: val_loss -0.4997 +2025-11-04 06:30:58.495278: Pseudo dice [np.float32(0.9463), np.float32(0.7566), np.float32(0.7008), np.float32(0.7002), np.float32(0.8795), np.float32(0.8163), np.float32(0.9073), np.float32(0.8893), np.float32(0.9808), np.float32(0.9827), np.float32(0.9691), np.float32(0.8561), np.float32(0.7713), np.float32(0.8826), np.float32(0.9531), np.float32(0.2032), np.float32(0.1816)] +2025-11-04 06:30:58.496521: Epoch time: 516.99 s +2025-11-04 06:31:00.504803: +2025-11-04 06:31:00.507173: Epoch 906 +2025-11-04 06:31:00.509006: Current learning rate: 0.00119 +2025-11-04 06:39:33.884285: train_loss -0.4779 +2025-11-04 06:39:33.889310: val_loss -0.467 +2025-11-04 06:39:33.890423: Pseudo dice [np.float32(0.9214), np.float32(0.7875), np.float32(0.7888), np.float32(0.7096), np.float32(0.8676), np.float32(0.8132), np.float32(0.9032), np.float32(0.8806), np.float32(0.9629), np.float32(0.972), np.float32(0.9678), np.float32(0.8571), np.float32(0.7891), np.float32(0.8718), np.float32(0.9654), np.float32(0.49), np.float32(0.3781)] +2025-11-04 06:39:33.891510: Epoch time: 513.38 s +2025-11-04 06:39:35.865601: +2025-11-04 06:39:35.867435: Epoch 907 +2025-11-04 06:39:35.870697: Current learning rate: 0.00118 +2025-11-04 06:48:10.294138: train_loss -0.4871 +2025-11-04 06:48:10.300624: val_loss -0.4832 +2025-11-04 06:48:10.306379: Pseudo dice [np.float32(0.9541), np.float32(0.7824), np.float32(0.7553), np.float32(0.6467), np.float32(0.8809), np.float32(0.8189), np.float32(0.9336), np.float32(0.9067), np.float32(0.9674), np.float32(0.9691), np.float32(0.9713), np.float32(0.852), np.float32(0.7906), np.float32(0.8831), np.float32(0.9652), np.float32(0.4123), np.float32(0.3687)] +2025-11-04 06:48:10.337204: Epoch time: 514.43 s +2025-11-04 06:48:26.137074: +2025-11-04 06:48:26.138719: Epoch 908 +2025-11-04 06:48:26.140049: Current learning rate: 0.00117 +2025-11-04 06:57:06.927284: train_loss -0.493 +2025-11-04 06:57:06.933003: val_loss -0.5215 +2025-11-04 06:57:06.943967: Pseudo dice [np.float32(0.941), np.float32(0.7888), np.float32(0.7282), np.float32(0.6689), np.float32(0.8814), np.float32(0.8168), np.float32(0.9391), np.float32(0.886), np.float32(0.978), np.float32(0.9767), np.float32(0.9691), np.float32(0.8719), np.float32(0.7896), np.float32(0.8659), np.float32(0.9701), np.float32(0.2932), np.float32(0.2685)] +2025-11-04 06:57:06.945588: Epoch time: 520.79 s +2025-11-04 06:57:09.176644: +2025-11-04 06:57:09.177987: Epoch 909 +2025-11-04 06:57:09.179281: Current learning rate: 0.00116 +2025-11-04 07:05:49.904650: train_loss -0.4969 +2025-11-04 07:05:49.909461: val_loss -0.479 +2025-11-04 07:05:49.910862: Pseudo dice [np.float32(0.9449), np.float32(0.8049), np.float32(0.7238), np.float32(0.6216), np.float32(0.8518), np.float32(0.819), np.float32(0.9228), np.float32(0.8962), np.float32(0.9815), np.float32(0.9819), np.float32(0.9693), np.float32(0.8675), np.float32(0.8282), np.float32(0.883), np.float32(0.966), np.float32(0.4321), np.float32(0.3391)] +2025-11-04 07:05:49.912283: Epoch time: 520.73 s +2025-11-04 07:05:52.386508: +2025-11-04 07:05:52.388984: Epoch 910 +2025-11-04 07:05:52.391431: Current learning rate: 0.00115 +2025-11-04 07:14:19.901647: train_loss -0.4813 +2025-11-04 07:14:19.913788: val_loss -0.5129 +2025-11-04 07:14:19.918595: Pseudo dice [np.float32(0.9437), np.float32(0.7877), np.float32(0.7112), np.float32(0.6361), np.float32(0.874), np.float32(0.7956), np.float32(0.9156), np.float32(0.8934), np.float32(0.9696), np.float32(0.9677), np.float32(0.9677), np.float32(0.8492), np.float32(0.8125), np.float32(0.8804), np.float32(0.9546), np.float32(0.3374), np.float32(0.3203)] +2025-11-04 07:14:19.926964: Epoch time: 507.53 s +2025-11-04 07:14:21.992703: +2025-11-04 07:14:22.001835: Epoch 911 +2025-11-04 07:14:22.004088: Current learning rate: 0.00113 +2025-11-04 07:22:47.504169: train_loss -0.4792 +2025-11-04 07:22:47.513529: val_loss -0.4933 +2025-11-04 07:22:47.514876: Pseudo dice [np.float32(0.9427), np.float32(0.8356), np.float32(0.7562), np.float32(0.7282), np.float32(0.8864), np.float32(0.84), np.float32(0.9072), np.float32(0.8904), np.float32(0.9678), np.float32(0.9758), np.float32(0.9716), np.float32(0.8689), np.float32(0.7786), np.float32(0.8845), np.float32(0.9625), np.float32(0.3993), np.float32(0.3663)] +2025-11-04 07:22:47.563577: Epoch time: 505.52 s +2025-11-04 07:22:47.565452: Yayy! New best EMA pseudo Dice: 0.8087000250816345 +2025-11-04 07:22:53.529520: +2025-11-04 07:22:53.531005: Epoch 912 +2025-11-04 07:22:53.532300: Current learning rate: 0.00112 +2025-11-04 07:31:38.496856: train_loss -0.4799 +2025-11-04 07:31:38.567259: val_loss -0.4957 +2025-11-04 07:31:38.569119: Pseudo dice [np.float32(0.944), np.float32(0.7918), np.float32(0.7268), np.float32(0.6461), np.float32(0.8926), np.float32(0.8251), np.float32(0.9135), np.float32(0.8865), np.float32(0.9741), np.float32(0.9742), np.float32(0.9685), np.float32(0.8561), np.float32(0.7842), np.float32(0.896), np.float32(0.9458), np.float32(0.3524), np.float32(0.2504)] +2025-11-04 07:31:38.589610: Epoch time: 524.97 s +2025-11-04 07:31:40.985723: +2025-11-04 07:31:40.987450: Epoch 913 +2025-11-04 07:31:40.988687: Current learning rate: 0.00111 +2025-11-04 07:40:07.521777: train_loss -0.4885 +2025-11-04 07:40:07.527994: val_loss -0.4813 +2025-11-04 07:40:07.529454: Pseudo dice [np.float32(0.9304), np.float32(0.7676), np.float32(0.725), np.float32(0.7235), np.float32(0.8914), np.float32(0.8335), np.float32(0.926), np.float32(0.886), np.float32(0.975), np.float32(0.9731), np.float32(0.9693), np.float32(0.8557), np.float32(0.8024), np.float32(0.8836), np.float32(0.9558), np.float32(0.2504), np.float32(0.2455)] +2025-11-04 07:40:07.531229: Epoch time: 506.55 s +2025-11-04 07:40:09.569950: +2025-11-04 07:40:09.571362: Epoch 914 +2025-11-04 07:40:09.572827: Current learning rate: 0.0011 +2025-11-04 07:48:40.510773: train_loss -0.4745 +2025-11-04 07:48:40.518220: val_loss -0.4768 +2025-11-04 07:48:40.519984: Pseudo dice [np.float32(0.92), np.float32(0.7365), np.float32(0.7041), np.float32(0.7339), np.float32(0.87), np.float32(0.7617), np.float32(0.8792), np.float32(0.8918), np.float32(0.9771), np.float32(0.9763), np.float32(0.9681), np.float32(0.8263), np.float32(0.8004), np.float32(0.8502), np.float32(0.9579), np.float32(0.2637), np.float32(0.1524)] +2025-11-04 07:48:40.521477: Epoch time: 510.95 s +2025-11-04 07:48:43.156155: +2025-11-04 07:48:43.158036: Epoch 915 +2025-11-04 07:48:43.160427: Current learning rate: 0.00109 +2025-11-04 07:57:15.928143: train_loss -0.4584 +2025-11-04 07:57:15.933201: val_loss -0.4497 +2025-11-04 07:57:15.934637: Pseudo dice [np.float32(0.9355), np.float32(0.7838), np.float32(0.7504), np.float32(0.6547), np.float32(0.8695), np.float32(0.8352), np.float32(0.8803), np.float32(0.9068), np.float32(0.9821), np.float32(0.9798), np.float32(0.9708), np.float32(0.8853), np.float32(0.7529), np.float32(0.8862), np.float32(0.9679), np.float32(0.473), np.float32(0.4069)] +2025-11-04 07:57:15.936000: Epoch time: 512.78 s +2025-11-04 07:57:18.031098: +2025-11-04 07:57:18.032656: Epoch 916 +2025-11-04 07:57:18.037816: Current learning rate: 0.00108 +2025-11-04 08:05:57.713284: train_loss -0.4828 +2025-11-04 08:05:57.718460: val_loss -0.4797 +2025-11-04 08:05:57.720038: Pseudo dice [np.float32(0.9505), np.float32(0.7712), np.float32(0.7174), np.float32(0.7081), np.float32(0.8805), np.float32(0.7912), np.float32(0.9051), np.float32(0.8845), np.float32(0.9838), np.float32(0.9835), np.float32(0.9651), np.float32(0.8497), np.float32(0.8094), np.float32(0.8766), np.float32(0.9661), np.float32(0.3313), np.float32(0.2296)] +2025-11-04 08:05:57.750696: Epoch time: 519.69 s +2025-11-04 08:05:59.796764: +2025-11-04 08:05:59.800419: Epoch 917 +2025-11-04 08:05:59.802049: Current learning rate: 0.00106 +2025-11-04 08:14:31.599968: train_loss -0.4803 +2025-11-04 08:14:31.605275: val_loss -0.4896 +2025-11-04 08:14:31.606441: Pseudo dice [np.float32(0.9452), np.float32(0.7688), np.float32(0.7074), np.float32(0.7009), np.float32(0.8838), np.float32(0.8188), np.float32(0.835), np.float32(0.8861), np.float32(0.9639), np.float32(0.9619), np.float32(0.9673), np.float32(0.8635), np.float32(0.8004), np.float32(0.8826), np.float32(0.9588), np.float32(0.3578), np.float32(0.4389)] +2025-11-04 08:14:31.607751: Epoch time: 511.81 s +2025-11-04 08:14:33.557437: +2025-11-04 08:14:33.559751: Epoch 918 +2025-11-04 08:14:33.561223: Current learning rate: 0.00105 +2025-11-04 08:23:10.276345: train_loss -0.4724 +2025-11-04 08:23:10.282635: val_loss -0.459 +2025-11-04 08:23:10.290162: Pseudo dice [np.float32(0.9242), np.float32(0.8149), np.float32(0.7352), np.float32(0.7049), np.float32(0.8557), np.float32(0.8131), np.float32(0.9061), np.float32(0.8876), np.float32(0.9464), np.float32(0.9617), np.float32(0.9689), np.float32(0.8787), np.float32(0.7901), np.float32(0.8837), np.float32(0.9665), np.float32(0.4402), np.float32(0.2698)] +2025-11-04 08:23:10.292436: Epoch time: 516.72 s +2025-11-04 08:23:12.382715: +2025-11-04 08:23:12.384304: Epoch 919 +2025-11-04 08:23:12.385601: Current learning rate: 0.00104 +2025-11-04 08:31:59.630210: train_loss -0.4696 +2025-11-04 08:31:59.657976: val_loss -0.4917 +2025-11-04 08:31:59.659200: Pseudo dice [np.float32(0.9383), np.float32(0.8115), np.float32(0.6494), np.float32(0.6428), np.float32(0.8743), np.float32(0.7896), np.float32(0.8875), np.float32(0.8888), np.float32(0.973), np.float32(0.9765), np.float32(0.9627), np.float32(0.8706), np.float32(0.7971), np.float32(0.8674), np.float32(0.944), np.float32(0.3981), np.float32(0.473)] +2025-11-04 08:31:59.660793: Epoch time: 527.25 s +2025-11-04 08:32:01.724636: +2025-11-04 08:32:01.727786: Epoch 920 +2025-11-04 08:32:01.729154: Current learning rate: 0.00103 +2025-11-04 08:40:29.142063: train_loss -0.4747 +2025-11-04 08:40:29.201175: val_loss -0.4701 +2025-11-04 08:40:29.202697: Pseudo dice [np.float32(0.9377), np.float32(0.8199), np.float32(0.7623), np.float32(0.6884), np.float32(0.861), np.float32(0.819), np.float32(0.9179), np.float32(0.8995), np.float32(0.9685), np.float32(0.9726), np.float32(0.9678), np.float32(0.8708), np.float32(0.7921), np.float32(0.8761), np.float32(0.9634), np.float32(0.2486), np.float32(0.2131)] +2025-11-04 08:40:29.204313: Epoch time: 507.42 s +2025-11-04 08:40:31.273902: +2025-11-04 08:40:31.276734: Epoch 921 +2025-11-04 08:40:31.279787: Current learning rate: 0.00102 +2025-11-04 08:49:00.548667: train_loss -0.4876 +2025-11-04 08:49:00.575361: val_loss -0.4815 +2025-11-04 08:49:00.577049: Pseudo dice [np.float32(0.9389), np.float32(0.7565), np.float32(0.7255), np.float32(0.6468), np.float32(0.857), np.float32(0.8033), np.float32(0.8923), np.float32(0.8951), np.float32(0.9739), np.float32(0.9773), np.float32(0.9684), np.float32(0.8766), np.float32(0.8174), np.float32(0.8584), np.float32(0.9707), np.float32(0.3834), np.float32(0.2434)] +2025-11-04 08:49:00.578752: Epoch time: 509.28 s +2025-11-04 08:49:02.510200: +2025-11-04 08:49:02.511818: Epoch 922 +2025-11-04 08:49:02.513973: Current learning rate: 0.00101 +2025-11-04 08:57:28.576471: train_loss -0.4927 +2025-11-04 08:57:28.583860: val_loss -0.4916 +2025-11-04 08:57:28.585501: Pseudo dice [np.float32(0.915), np.float32(0.7621), np.float32(0.7439), np.float32(0.7095), np.float32(0.8577), np.float32(0.8435), np.float32(0.9238), np.float32(0.8877), np.float32(0.9747), np.float32(0.9719), np.float32(0.9696), np.float32(0.8474), np.float32(0.8092), np.float32(0.8806), np.float32(0.9654), np.float32(0.4174), np.float32(0.3065)] +2025-11-04 08:57:28.586919: Epoch time: 506.07 s +2025-11-04 08:57:30.409011: +2025-11-04 08:57:30.410260: Epoch 923 +2025-11-04 08:57:30.411854: Current learning rate: 0.001 +2025-11-04 09:09:42.713585: train_loss -0.494 +2025-11-04 09:09:42.747177: val_loss -0.5066 +2025-11-04 09:09:42.753391: Pseudo dice [np.float32(0.9444), np.float32(0.8029), np.float32(0.7352), np.float32(0.7024), np.float32(0.8587), np.float32(0.8335), np.float32(0.8922), np.float32(0.8923), np.float32(0.9849), np.float32(0.9772), np.float32(0.9704), np.float32(0.8777), np.float32(0.7914), np.float32(0.8916), np.float32(0.9646), np.float32(0.3018), np.float32(0.2813)] +2025-11-04 09:09:42.761523: Epoch time: 732.31 s +2025-11-04 09:09:44.675767: +2025-11-04 09:09:44.693793: Epoch 924 +2025-11-04 09:09:44.697871: Current learning rate: 0.00098 +2025-11-04 09:27:34.842355: train_loss -0.4749 +2025-11-04 09:27:34.880546: val_loss -0.5061 +2025-11-04 09:27:34.885644: Pseudo dice [np.float32(0.9444), np.float32(0.8026), np.float32(0.7193), np.float32(0.6637), np.float32(0.8762), np.float32(0.8159), np.float32(0.9146), np.float32(0.9123), np.float32(0.9784), np.float32(0.9779), np.float32(0.9712), np.float32(0.8773), np.float32(0.7811), np.float32(0.8909), np.float32(0.9659), np.float32(0.4038), np.float32(0.3724)] +2025-11-04 09:27:34.908274: Epoch time: 1070.17 s +2025-11-04 09:27:36.896346: +2025-11-04 09:27:36.908294: Epoch 925 +2025-11-04 09:27:36.922571: Current learning rate: 0.00097 +2025-11-04 09:37:57.148320: train_loss -0.488 +2025-11-04 09:37:57.181590: val_loss -0.4494 +2025-11-04 09:37:57.208533: Pseudo dice [np.float32(0.9481), np.float32(0.8393), np.float32(0.7647), np.float32(0.6807), np.float32(0.8757), np.float32(0.8236), np.float32(0.8934), np.float32(0.9039), np.float32(0.9826), np.float32(0.9842), np.float32(0.9737), np.float32(0.8588), np.float32(0.7938), np.float32(0.8872), np.float32(0.9701), np.float32(0.2324), np.float32(0.2457)] +2025-11-04 09:37:57.219938: Epoch time: 620.26 s +2025-11-04 09:37:59.369903: +2025-11-04 09:37:59.393690: Epoch 926 +2025-11-04 09:37:59.400576: Current learning rate: 0.00096 +2025-11-04 09:55:55.793480: train_loss -0.4874 +2025-11-04 09:55:55.813706: val_loss -0.4463 +2025-11-04 09:55:55.816318: Pseudo dice [np.float32(0.9142), np.float32(0.7753), np.float32(0.7181), np.float32(0.6939), np.float32(0.873), np.float32(0.8014), np.float32(0.9156), np.float32(0.8797), np.float32(0.9806), np.float32(0.9802), np.float32(0.9675), np.float32(0.8449), np.float32(0.7485), np.float32(0.8684), np.float32(0.9675), np.float32(0.3975), np.float32(0.1988)] +2025-11-04 09:55:55.820532: Epoch time: 1076.43 s +2025-11-04 09:55:57.830391: +2025-11-04 09:55:57.833848: Epoch 927 +2025-11-04 09:55:57.842824: Current learning rate: 0.00095 +2025-11-04 10:05:18.825032: train_loss -0.4937 +2025-11-04 10:05:18.837589: val_loss -0.4765 +2025-11-04 10:05:18.842427: Pseudo dice [np.float32(0.9358), np.float32(0.7767), np.float32(0.7018), np.float32(0.7374), np.float32(0.8544), np.float32(0.8136), np.float32(0.8978), np.float32(0.9045), np.float32(0.9839), np.float32(0.9835), np.float32(0.9737), np.float32(0.8504), np.float32(0.8097), np.float32(0.8725), np.float32(0.9721), np.float32(0.3559), np.float32(0.3034)] +2025-11-04 10:05:18.845758: Epoch time: 561.0 s +2025-11-04 10:05:20.923184: +2025-11-04 10:05:20.931111: Epoch 928 +2025-11-04 10:05:20.934786: Current learning rate: 0.00094 +2025-11-04 10:14:42.825030: train_loss -0.4758 +2025-11-04 10:14:42.835695: val_loss -0.4782 +2025-11-04 10:14:42.837988: Pseudo dice [np.float32(0.9436), np.float32(0.7872), np.float32(0.7599), np.float32(0.7259), np.float32(0.8737), np.float32(0.7997), np.float32(0.8943), np.float32(0.8818), np.float32(0.9854), np.float32(0.9845), np.float32(0.9729), np.float32(0.8578), np.float32(0.799), np.float32(0.8569), np.float32(0.9694), np.float32(0.4127), np.float32(0.1951)] +2025-11-04 10:14:42.840017: Epoch time: 561.91 s +2025-11-04 10:14:44.855358: +2025-11-04 10:14:44.856665: Epoch 929 +2025-11-04 10:14:44.858942: Current learning rate: 0.00092 +2025-11-04 10:23:50.492193: train_loss -0.4847 +2025-11-04 10:23:50.497509: val_loss -0.4897 +2025-11-04 10:23:50.498752: Pseudo dice [np.float32(0.9471), np.float32(0.7968), np.float32(0.7111), np.float32(0.7158), np.float32(0.9002), np.float32(0.8251), np.float32(0.9035), np.float32(0.8949), np.float32(0.9794), np.float32(0.9812), np.float32(0.9712), np.float32(0.862), np.float32(0.7782), np.float32(0.8988), np.float32(0.9713), np.float32(0.4224), np.float32(0.2761)] +2025-11-04 10:23:50.500260: Epoch time: 545.64 s +2025-11-04 10:23:52.531278: +2025-11-04 10:23:52.536766: Epoch 930 +2025-11-04 10:23:52.545450: Current learning rate: 0.00091 +2025-11-04 10:32:11.868513: train_loss -0.4684 +2025-11-04 10:32:11.878644: val_loss -0.5351 +2025-11-04 10:32:11.881091: Pseudo dice [np.float32(0.946), np.float32(0.8059), np.float32(0.7509), np.float32(0.68), np.float32(0.9001), np.float32(0.8064), np.float32(0.8999), np.float32(0.8992), np.float32(0.9844), np.float32(0.9846), np.float32(0.9697), np.float32(0.8631), np.float32(0.8145), np.float32(0.8865), np.float32(0.9721), np.float32(0.3809), np.float32(0.3465)] +2025-11-04 10:32:11.882671: Epoch time: 499.34 s +2025-11-04 10:32:13.795391: +2025-11-04 10:32:13.808446: Epoch 931 +2025-11-04 10:32:13.811530: Current learning rate: 0.0009 +2025-11-04 10:41:05.273439: train_loss -0.4705 +2025-11-04 10:41:05.309792: val_loss -0.5001 +2025-11-04 10:41:05.311767: Pseudo dice [np.float32(0.9497), np.float32(0.7816), np.float32(0.7734), np.float32(0.7346), np.float32(0.8532), np.float32(0.8232), np.float32(0.9291), np.float32(0.8875), np.float32(0.9682), np.float32(0.9652), np.float32(0.9679), np.float32(0.8633), np.float32(0.8142), np.float32(0.8805), np.float32(0.9653), np.float32(0.272), np.float32(0.15)] +2025-11-04 10:41:05.313748: Epoch time: 531.48 s +2025-11-04 10:41:07.399485: +2025-11-04 10:41:07.407681: Epoch 932 +2025-11-04 10:41:07.416495: Current learning rate: 0.00089 +2025-11-04 10:50:00.452983: train_loss -0.4803 +2025-11-04 10:50:00.457472: val_loss -0.4825 +2025-11-04 10:50:00.459209: Pseudo dice [np.float32(0.9419), np.float32(0.8046), np.float32(0.7578), np.float32(0.6507), np.float32(0.8894), np.float32(0.8192), np.float32(0.8681), np.float32(0.8798), np.float32(0.9644), np.float32(0.9699), np.float32(0.9697), np.float32(0.868), np.float32(0.7923), np.float32(0.8743), np.float32(0.9652), np.float32(0.3381), np.float32(0.1913)] +2025-11-04 10:50:00.460713: Epoch time: 533.06 s +2025-11-04 10:50:02.465122: +2025-11-04 10:50:02.473038: Epoch 933 +2025-11-04 10:50:02.479105: Current learning rate: 0.00088 +2025-11-04 10:58:53.030249: train_loss -0.4782 +2025-11-04 10:58:53.049984: val_loss -0.4926 +2025-11-04 10:58:53.056408: Pseudo dice [np.float32(0.9287), np.float32(0.7467), np.float32(0.7553), np.float32(0.6995), np.float32(0.8678), np.float32(0.8528), np.float32(0.8705), np.float32(0.9012), np.float32(0.9832), np.float32(0.9774), np.float32(0.966), np.float32(0.8917), np.float32(0.8086), np.float32(0.8864), np.float32(0.9562), np.float32(0.4813), np.float32(0.4701)] +2025-11-04 10:58:53.058422: Epoch time: 530.57 s +2025-11-04 10:59:09.728536: +2025-11-04 10:59:09.730252: Epoch 934 +2025-11-04 10:59:09.731742: Current learning rate: 0.00087 +2025-11-04 11:09:26.730497: train_loss -0.4999 +2025-11-04 11:09:26.747580: val_loss -0.4973 +2025-11-04 11:09:26.752366: Pseudo dice [np.float32(0.9307), np.float32(0.7956), np.float32(0.7619), np.float32(0.7371), np.float32(0.8972), np.float32(0.8167), np.float32(0.9149), np.float32(0.9005), np.float32(0.9758), np.float32(0.9806), np.float32(0.969), np.float32(0.8669), np.float32(0.806), np.float32(0.896), np.float32(0.9718), np.float32(0.3162), np.float32(0.2922)] +2025-11-04 11:09:26.761750: Epoch time: 617.01 s +2025-11-04 11:09:28.615772: +2025-11-04 11:09:28.617109: Epoch 935 +2025-11-04 11:09:28.618992: Current learning rate: 0.00085 diff --git a/Dataset809_AbdomenAtlasF17/nnUNetTrainer__nnUNetResEncUNetLPlans__3d_fullres/fold_all/training_log_2025_11_7_21_08_06.txt b/Dataset809_AbdomenAtlasF17/nnUNetTrainer__nnUNetResEncUNetLPlans__3d_fullres/fold_all/training_log_2025_11_7_21_08_06.txt new file mode 100644 index 0000000000000000000000000000000000000000..be379f73fd81cb48bf81ed37177127875bfb9c2b --- /dev/null +++ b/Dataset809_AbdomenAtlasF17/nnUNetTrainer__nnUNetResEncUNetLPlans__3d_fullres/fold_all/training_log_2025_11_7_21_08_06.txt @@ -0,0 +1,1491 @@ + +####################################################################### +Please cite the following paper when using nnU-Net: +Isensee, F., Jaeger, P. F., Kohl, S. A., Petersen, J., & Maier-Hein, K. H. (2021). nnU-Net: a self-configuring method for deep learning-based biomedical image segmentation. Nature methods, 18(2), 203-211. +####################################################################### + +2025-11-07 21:08:29.353927: Using torch.compile... +2025-11-07 21:11:19.574881: do_dummy_2d_data_aug: False + +This is the configuration used by this training: +Configuration name: 3d_fullres + {'data_identifier': 'nnUNetPlans_3d_fullres', 'preprocessor_name': 'DefaultPreprocessor', 'batch_size': 2, 'patch_size': [160, 224, 192], 'median_image_size_in_voxels': [512.0, 613.0, 513.0], 'spacing': [0.7109375, 0.5, 0.7109375], 'normalization_schemes': ['CTNormalization'], 'use_mask_for_norm': [False], 'resampling_fn_data': 'resample_data_or_seg_to_shape', 'resampling_fn_seg': 'resample_data_or_seg_to_shape', 'resampling_fn_data_kwargs': {'is_seg': False, 'order': 3, 'order_z': 0, 'force_separate_z': None}, 'resampling_fn_seg_kwargs': {'is_seg': True, 'order': 1, 'order_z': 0, 'force_separate_z': None}, 'resampling_fn_probabilities': 'resample_data_or_seg_to_shape', 'resampling_fn_probabilities_kwargs': {'is_seg': False, 'order': 1, 'order_z': 0, 'force_separate_z': None}, 'architecture': {'network_class_name': 'dynamic_network_architectures.architectures.unet.ResidualEncoderUNet', 'arch_kwargs': {'n_stages': 6, 'features_per_stage': [32, 64, 128, 256, 320, 320], 'conv_op': 'torch.nn.modules.conv.Conv3d', 'kernel_sizes': [[3, 3, 3], [3, 3, 3], [3, 3, 3], [3, 3, 3], [3, 3, 3], [3, 3, 3]], 'strides': [[1, 1, 1], [2, 2, 2], [2, 2, 2], [2, 2, 2], [2, 2, 2], [2, 2, 2]], 'n_blocks_per_stage': [1, 3, 4, 6, 6, 6], 'n_conv_per_stage_decoder': [1, 1, 1, 1, 1], 'conv_bias': True, 'norm_op': 'torch.nn.modules.instancenorm.InstanceNorm3d', 'norm_op_kwargs': {'eps': 1e-05, 'affine': True}, 'dropout_op': None, 'dropout_op_kwargs': None, 'nonlin': 'torch.nn.LeakyReLU', 'nonlin_kwargs': {'inplace': True}}, '_kw_requires_import': ['conv_op', 'norm_op', 'dropout_op', 'nonlin']}, 'batch_dice': True} + +These are the global plan.json settings: + {'dataset_name': 'Dataset809_AbdomenAtlasF17', 'plans_name': 'nnUNetResEncUNetLPlans', 'original_median_spacing_after_transp': [0.7109375, 0.5, 0.7109375], 'original_median_shape_after_transp': [512, 608, 512], 'image_reader_writer': 'SimpleITKIO', 'transpose_forward': [1, 0, 2], 'transpose_backward': [1, 0, 2], 'experiment_planner_used': 'nnUNetPlannerResEncL', 'label_manager': 'LabelManager', 'foreground_intensity_properties_per_channel': {'0': {'max': 1000.0, 'mean': 39.68027877807617, 'median': 71.0, 'min': -1000.0, 'percentile_00_5': -1000.0, 'percentile_99_5': 379.0, 'std': 192.4669952392578}}} + +2025-11-07 21:12:20.713260: unpacking dataset... +2025-11-07 21:13:34.092129: unpacking done... +2025-11-07 21:13:34.112461: Unable to plot network architecture: nnUNet_compile is enabled! +2025-11-07 21:13:34.787188: +2025-11-07 21:13:34.788712: Epoch 900 +2025-11-07 21:13:34.791106: Current learning rate: 0.00126 +2025-11-07 21:24:10.567204: train_loss -0.4956 +2025-11-07 21:24:10.571768: val_loss -0.5039 +2025-11-07 21:24:10.573044: Pseudo dice [np.float32(0.9459), np.float32(0.8001), np.float32(0.7355), np.float32(0.6913), np.float32(0.8729), np.float32(0.8292), np.float32(0.8801), np.float32(0.8903), np.float32(0.9782), np.float32(0.978), np.float32(0.968), np.float32(0.8843), np.float32(0.8), np.float32(0.8747), np.float32(0.965), np.float32(0.3785), np.float32(0.3888)] +2025-11-07 21:24:10.574151: Epoch time: 635.79 s +2025-11-07 21:24:13.385852: +2025-11-07 21:24:13.387140: Epoch 901 +2025-11-07 21:24:13.388546: Current learning rate: 0.00125 +2025-11-07 21:34:06.397393: train_loss -0.487 +2025-11-07 21:34:06.446288: val_loss -0.479 +2025-11-07 21:34:06.447629: Pseudo dice [np.float32(0.9306), np.float32(0.7953), np.float32(0.6977), np.float32(0.6029), np.float32(0.8563), np.float32(0.8103), np.float32(0.9088), np.float32(0.8759), np.float32(0.9798), np.float32(0.9772), np.float32(0.9692), np.float32(0.85), np.float32(0.8135), np.float32(0.8744), np.float32(0.9656), np.float32(0.459), np.float32(0.4162)] +2025-11-07 21:34:06.461429: Epoch time: 593.02 s +2025-11-07 21:34:08.360429: +2025-11-07 21:34:08.368369: Epoch 902 +2025-11-07 21:34:08.369941: Current learning rate: 0.00124 +2025-11-07 21:43:26.497300: train_loss -0.4885 +2025-11-07 21:43:26.514052: val_loss -0.4781 +2025-11-07 21:43:26.515732: Pseudo dice [np.float32(0.9378), np.float32(0.7561), np.float32(0.7162), np.float32(0.6589), np.float32(0.8887), np.float32(0.7897), np.float32(0.831), np.float32(0.8823), np.float32(0.9824), np.float32(0.9816), np.float32(0.9702), np.float32(0.8626), np.float32(0.7906), np.float32(0.8896), np.float32(0.9693), np.float32(0.3905), np.float32(0.3208)] +2025-11-07 21:43:26.517603: Epoch time: 558.14 s +2025-11-07 21:43:28.330215: +2025-11-07 21:43:28.331563: Epoch 903 +2025-11-07 21:43:28.333973: Current learning rate: 0.00122 +2025-11-07 21:52:19.165632: train_loss -0.4786 +2025-11-07 21:52:19.172042: val_loss -0.492 +2025-11-07 21:52:19.173295: Pseudo dice [np.float32(0.9281), np.float32(0.7855), np.float32(0.693), np.float32(0.6842), np.float32(0.8838), np.float32(0.8064), np.float32(0.9127), np.float32(0.8809), np.float32(0.9778), np.float32(0.9784), np.float32(0.9698), np.float32(0.8644), np.float32(0.7889), np.float32(0.8953), np.float32(0.9716), np.float32(0.2248), np.float32(0.1783)] +2025-11-07 21:52:19.174452: Epoch time: 530.84 s +2025-11-07 21:52:20.994549: +2025-11-07 21:52:20.997553: Epoch 904 +2025-11-07 21:52:20.998845: Current learning rate: 0.00121 +2025-11-07 22:01:36.931363: train_loss -0.462 +2025-11-07 22:01:37.003681: val_loss -0.4696 +2025-11-07 22:01:37.005683: Pseudo dice [np.float32(0.9368), np.float32(0.7922), np.float32(0.756), np.float32(0.6761), np.float32(0.8687), np.float32(0.7851), np.float32(0.9137), np.float32(0.8968), np.float32(0.9841), np.float32(0.9822), np.float32(0.9693), np.float32(0.8564), np.float32(0.7685), np.float32(0.8958), np.float32(0.9741), np.float32(0.2583), np.float32(0.2409)] +2025-11-07 22:01:37.026760: Epoch time: 555.94 s +2025-11-07 22:01:39.124051: +2025-11-07 22:01:39.127702: Epoch 905 +2025-11-07 22:01:39.138071: Current learning rate: 0.0012 +2025-11-07 22:10:41.821495: train_loss -0.4916 +2025-11-07 22:10:41.829146: val_loss -0.4938 +2025-11-07 22:10:41.830677: Pseudo dice [np.float32(0.939), np.float32(0.7951), np.float32(0.7156), np.float32(0.6637), np.float32(0.8814), np.float32(0.8082), np.float32(0.9113), np.float32(0.8502), np.float32(0.9765), np.float32(0.9748), np.float32(0.9674), np.float32(0.8576), np.float32(0.8243), np.float32(0.8859), np.float32(0.9607), np.float32(0.3058), np.float32(0.1776)] +2025-11-07 22:10:41.832467: Epoch time: 542.7 s +2025-11-07 22:10:43.654635: +2025-11-07 22:10:43.655984: Epoch 906 +2025-11-07 22:10:43.657485: Current learning rate: 0.00119 +2025-11-07 22:20:10.613606: train_loss -0.4837 +2025-11-07 22:20:10.620665: val_loss -0.47 +2025-11-07 22:20:10.623052: Pseudo dice [np.float32(0.9278), np.float32(0.7569), np.float32(0.6919), np.float32(0.6982), np.float32(0.877), np.float32(0.8118), np.float32(0.929), np.float32(0.8763), np.float32(0.9833), np.float32(0.9778), np.float32(0.9696), np.float32(0.8615), np.float32(0.8244), np.float32(0.8647), np.float32(0.9661), np.float32(0.3313), np.float32(0.306)] +2025-11-07 22:20:10.653125: Epoch time: 566.96 s +2025-11-07 22:20:12.620425: +2025-11-07 22:20:12.629016: Epoch 907 +2025-11-07 22:20:12.635160: Current learning rate: 0.00118 +2025-11-07 22:29:44.089165: train_loss -0.4959 +2025-11-07 22:29:44.102579: val_loss -0.46 +2025-11-07 22:29:44.104870: Pseudo dice [np.float32(0.942), np.float32(0.7581), np.float32(0.7217), np.float32(0.6831), np.float32(0.8679), np.float32(0.8244), np.float32(0.8908), np.float32(0.8913), np.float32(0.9823), np.float32(0.9799), np.float32(0.9666), np.float32(0.8533), np.float32(0.8048), np.float32(0.8705), np.float32(0.9578), np.float32(0.2361), np.float32(0.3313)] +2025-11-07 22:29:44.107508: Epoch time: 571.47 s +2025-11-07 22:29:46.094253: +2025-11-07 22:29:46.096428: Epoch 908 +2025-11-07 22:29:46.098262: Current learning rate: 0.00117 +2025-11-07 22:39:11.480562: train_loss -0.4875 +2025-11-07 22:39:11.539690: val_loss -0.4781 +2025-11-07 22:39:11.555072: Pseudo dice [np.float32(0.9434), np.float32(0.8124), np.float32(0.7532), np.float32(0.6607), np.float32(0.8943), np.float32(0.8015), np.float32(0.9115), np.float32(0.8944), np.float32(0.9635), np.float32(0.9664), np.float32(0.9696), np.float32(0.8713), np.float32(0.8201), np.float32(0.8761), np.float32(0.9505), np.float32(0.3987), np.float32(0.306)] +2025-11-07 22:39:11.556779: Epoch time: 565.39 s +2025-11-07 22:39:13.550415: +2025-11-07 22:39:13.552649: Epoch 909 +2025-11-07 22:39:13.554341: Current learning rate: 0.00116 +2025-11-07 22:48:48.848326: train_loss -0.4946 +2025-11-07 22:48:48.857336: val_loss -0.4706 +2025-11-07 22:48:48.858959: Pseudo dice [np.float32(0.9327), np.float32(0.8024), np.float32(0.743), np.float32(0.7262), np.float32(0.8806), np.float32(0.805), np.float32(0.9176), np.float32(0.897), np.float32(0.9844), np.float32(0.9826), np.float32(0.9722), np.float32(0.8686), np.float32(0.7772), np.float32(0.883), np.float32(0.9669), np.float32(0.3273), np.float32(0.3412)] +2025-11-07 22:48:48.861007: Epoch time: 575.3 s +2025-11-07 22:48:50.783411: +2025-11-07 22:48:50.784956: Epoch 910 +2025-11-07 22:48:50.789807: Current learning rate: 0.00115 +2025-11-07 22:58:35.219168: train_loss -0.4903 +2025-11-07 22:58:35.231912: val_loss -0.4886 +2025-11-07 22:58:35.236552: Pseudo dice [np.float32(0.8923), np.float32(0.793), np.float32(0.6783), np.float32(0.7015), np.float32(0.8437), np.float32(0.7761), np.float32(0.91), np.float32(0.8801), np.float32(0.9832), np.float32(0.9842), np.float32(0.9653), np.float32(0.8401), np.float32(0.7734), np.float32(0.8656), np.float32(0.9609), np.float32(0.3526), np.float32(0.2869)] +2025-11-07 22:58:35.239610: Epoch time: 584.44 s +2025-11-07 22:58:37.031801: +2025-11-07 22:58:37.033257: Epoch 911 +2025-11-07 22:58:37.035181: Current learning rate: 0.00113 +2025-11-07 23:08:06.494445: train_loss -0.486 +2025-11-07 23:08:06.498716: val_loss -0.5041 +2025-11-07 23:08:06.499991: Pseudo dice [np.float32(0.9339), np.float32(0.8215), np.float32(0.7686), np.float32(0.7051), np.float32(0.8355), np.float32(0.8444), np.float32(0.9238), np.float32(0.8722), np.float32(0.9841), np.float32(0.9857), np.float32(0.9706), np.float32(0.8683), np.float32(0.784), np.float32(0.8478), np.float32(0.9704), np.float32(0.3215), np.float32(0.324)] +2025-11-07 23:08:06.502066: Epoch time: 569.47 s +2025-11-07 23:08:08.319002: +2025-11-07 23:08:08.322649: Epoch 912 +2025-11-07 23:08:08.326539: Current learning rate: 0.00112 +2025-11-07 23:17:23.234450: train_loss -0.4922 +2025-11-07 23:17:23.270157: val_loss -0.4637 +2025-11-07 23:17:23.273877: Pseudo dice [np.float32(0.9298), np.float32(0.8088), np.float32(0.7113), np.float32(0.65), np.float32(0.8548), np.float32(0.8176), np.float32(0.9051), np.float32(0.881), np.float32(0.9804), np.float32(0.9799), np.float32(0.9642), np.float32(0.8447), np.float32(0.7921), np.float32(0.8722), np.float32(0.9514), np.float32(0.3189), np.float32(0.3)] +2025-11-07 23:17:23.279168: Epoch time: 554.92 s +2025-11-07 23:17:25.121203: +2025-11-07 23:17:25.127309: Epoch 913 +2025-11-07 23:17:25.132202: Current learning rate: 0.00111 +2025-11-07 23:26:37.696066: train_loss -0.4765 +2025-11-07 23:26:37.702558: val_loss -0.498 +2025-11-07 23:26:37.704965: Pseudo dice [np.float32(0.9527), np.float32(0.7707), np.float32(0.7372), np.float32(0.6512), np.float32(0.8763), np.float32(0.7841), np.float32(0.9195), np.float32(0.89), np.float32(0.9852), np.float32(0.9851), np.float32(0.9671), np.float32(0.8667), np.float32(0.7952), np.float32(0.8687), np.float32(0.9684), np.float32(0.3357), np.float32(0.3027)] +2025-11-07 23:26:37.706188: Epoch time: 552.58 s +2025-11-07 23:26:39.637225: +2025-11-07 23:26:39.645678: Epoch 914 +2025-11-07 23:26:39.646988: Current learning rate: 0.0011 +2025-11-07 23:35:44.421101: train_loss -0.4949 +2025-11-07 23:35:44.451595: val_loss -0.5056 +2025-11-07 23:35:44.452850: Pseudo dice [np.float32(0.9321), np.float32(0.793), np.float32(0.7132), np.float32(0.6792), np.float32(0.8847), np.float32(0.8174), np.float32(0.8919), np.float32(0.8959), np.float32(0.9591), np.float32(0.9575), np.float32(0.9663), np.float32(0.8678), np.float32(0.7935), np.float32(0.8802), np.float32(0.9332), np.float32(0.2493), np.float32(0.2803)] +2025-11-07 23:35:44.454581: Epoch time: 544.79 s +2025-11-07 23:35:46.210776: +2025-11-07 23:35:46.211871: Epoch 915 +2025-11-07 23:35:46.213831: Current learning rate: 0.00109 +2025-11-07 23:44:54.697398: train_loss -0.489 +2025-11-07 23:44:54.704025: val_loss -0.4883 +2025-11-07 23:44:54.705101: Pseudo dice [np.float32(0.929), np.float32(0.819), np.float32(0.7576), np.float32(0.7547), np.float32(0.8611), np.float32(0.8067), np.float32(0.8754), np.float32(0.8948), np.float32(0.9821), np.float32(0.9826), np.float32(0.9659), np.float32(0.8755), np.float32(0.7992), np.float32(0.886), np.float32(0.9669), np.float32(0.4111), np.float32(0.326)] +2025-11-07 23:44:54.706943: Epoch time: 548.49 s +2025-11-07 23:44:56.533318: +2025-11-07 23:44:56.536488: Epoch 916 +2025-11-07 23:44:56.538814: Current learning rate: 0.00108 +2025-11-07 23:53:48.329738: train_loss -0.4775 +2025-11-07 23:53:48.340141: val_loss -0.4968 +2025-11-07 23:53:48.341445: Pseudo dice [np.float32(0.9191), np.float32(0.7674), np.float32(0.7684), np.float32(0.6699), np.float32(0.8748), np.float32(0.8133), np.float32(0.9148), np.float32(0.9036), np.float32(0.9824), np.float32(0.9838), np.float32(0.9699), np.float32(0.8633), np.float32(0.7826), np.float32(0.8723), np.float32(0.9633), np.float32(0.3798), np.float32(0.4429)] +2025-11-07 23:53:48.344057: Epoch time: 531.8 s +2025-11-07 23:53:50.109342: +2025-11-07 23:53:50.110778: Epoch 917 +2025-11-07 23:53:50.115560: Current learning rate: 0.00106 +2025-11-08 00:03:10.663993: train_loss -0.4767 +2025-11-08 00:03:10.722062: val_loss -0.4838 +2025-11-08 00:03:10.723540: Pseudo dice [np.float32(0.9247), np.float32(0.8084), np.float32(0.7456), np.float32(0.6956), np.float32(0.8655), np.float32(0.7813), np.float32(0.9138), np.float32(0.8988), np.float32(0.9582), np.float32(0.9838), np.float32(0.9691), np.float32(0.8735), np.float32(0.8112), np.float32(0.8826), np.float32(0.9173), np.float32(0.3721), np.float32(0.3029)] +2025-11-08 00:03:10.733769: Epoch time: 560.56 s +2025-11-08 00:03:12.873936: +2025-11-08 00:03:12.875351: Epoch 918 +2025-11-08 00:03:12.876523: Current learning rate: 0.00105 +2025-11-08 00:12:23.024155: train_loss -0.4978 +2025-11-08 00:12:23.094177: val_loss -0.4883 +2025-11-08 00:12:23.095597: Pseudo dice [np.float32(0.9283), np.float32(0.7703), np.float32(0.7441), np.float32(0.7051), np.float32(0.8843), np.float32(0.8134), np.float32(0.9107), np.float32(0.9015), np.float32(0.9752), np.float32(0.9781), np.float32(0.9699), np.float32(0.8678), np.float32(0.7846), np.float32(0.876), np.float32(0.9579), np.float32(0.4335), np.float32(0.3415)] +2025-11-08 00:12:23.224238: Epoch time: 550.16 s +2025-11-08 00:12:25.327546: +2025-11-08 00:12:25.329055: Epoch 919 +2025-11-08 00:12:25.330550: Current learning rate: 0.00104 +2025-11-08 00:21:43.879496: train_loss -0.4837 +2025-11-08 00:21:43.886609: val_loss -0.4333 +2025-11-08 00:21:43.887717: Pseudo dice [np.float32(0.9479), np.float32(0.7547), np.float32(0.7585), np.float32(0.6546), np.float32(0.8715), np.float32(0.8367), np.float32(0.8992), np.float32(0.892), np.float32(0.9412), np.float32(0.9463), np.float32(0.9688), np.float32(0.8431), np.float32(0.8043), np.float32(0.8751), np.float32(0.9531), np.float32(0.3382), np.float32(0.3307)] +2025-11-08 00:21:43.888854: Epoch time: 558.56 s +2025-11-08 00:21:45.743807: +2025-11-08 00:21:45.749647: Epoch 920 +2025-11-08 00:21:45.751813: Current learning rate: 0.00103 +2025-11-08 00:31:49.650692: train_loss -0.4897 +2025-11-08 00:31:49.688902: val_loss -0.4961 +2025-11-08 00:31:49.691164: Pseudo dice [np.float32(0.9536), np.float32(0.8205), np.float32(0.7511), np.float32(0.6227), np.float32(0.865), np.float32(0.8249), np.float32(0.9047), np.float32(0.9046), np.float32(0.9777), np.float32(0.9792), np.float32(0.9677), np.float32(0.8782), np.float32(0.7866), np.float32(0.8716), np.float32(0.9634), np.float32(0.4244), np.float32(0.3405)] +2025-11-08 00:31:49.692716: Epoch time: 603.91 s +2025-11-08 00:31:51.554334: +2025-11-08 00:31:51.555800: Epoch 921 +2025-11-08 00:31:51.557158: Current learning rate: 0.00102 +2025-11-08 00:41:24.111988: train_loss -0.483 +2025-11-08 00:41:24.156658: val_loss -0.474 +2025-11-08 00:41:24.158936: Pseudo dice [np.float32(0.924), np.float32(0.8033), np.float32(0.7472), np.float32(0.6765), np.float32(0.8602), np.float32(0.8087), np.float32(0.8679), np.float32(0.9016), np.float32(0.9839), np.float32(0.959), np.float32(0.9638), np.float32(0.8579), np.float32(0.8049), np.float32(0.8364), np.float32(0.9709), np.float32(0.2994), np.float32(0.3207)] +2025-11-08 00:41:24.183981: Epoch time: 572.56 s +2025-11-08 00:41:26.069299: +2025-11-08 00:41:26.073916: Epoch 922 +2025-11-08 00:41:26.079013: Current learning rate: 0.00101 +2025-11-08 00:50:46.955997: train_loss -0.4976 +2025-11-08 00:50:46.971827: val_loss -0.4966 +2025-11-08 00:50:46.973745: Pseudo dice [np.float32(0.9481), np.float32(0.7564), np.float32(0.7114), np.float32(0.6926), np.float32(0.8497), np.float32(0.795), np.float32(0.9138), np.float32(0.8993), np.float32(0.9851), np.float32(0.9834), np.float32(0.967), np.float32(0.8449), np.float32(0.8088), np.float32(0.8781), np.float32(0.9678), np.float32(0.4282), np.float32(0.3631)] +2025-11-08 00:50:46.975379: Epoch time: 560.89 s +2025-11-08 00:50:48.845539: +2025-11-08 00:50:48.848021: Epoch 923 +2025-11-08 00:50:48.851344: Current learning rate: 0.001 +2025-11-08 01:00:06.353187: train_loss -0.4852 +2025-11-08 01:00:06.414819: val_loss -0.499 +2025-11-08 01:00:06.416328: Pseudo dice [np.float32(0.9173), np.float32(0.8009), np.float32(0.7411), np.float32(0.6798), np.float32(0.8718), np.float32(0.8287), np.float32(0.9032), np.float32(0.9139), np.float32(0.9848), np.float32(0.9836), np.float32(0.9672), np.float32(0.8538), np.float32(0.819), np.float32(0.8659), np.float32(0.9728), np.float32(0.3384), np.float32(0.1878)] +2025-11-08 01:00:06.417884: Epoch time: 557.51 s +2025-11-08 01:00:08.628834: +2025-11-08 01:00:08.630152: Epoch 924 +2025-11-08 01:00:08.631230: Current learning rate: 0.00098 +2025-11-08 01:09:35.768420: train_loss -0.4837 +2025-11-08 01:09:35.795069: val_loss -0.4892 +2025-11-08 01:09:35.796493: Pseudo dice [np.float32(0.9285), np.float32(0.8123), np.float32(0.7526), np.float32(0.7261), np.float32(0.8908), np.float32(0.7815), np.float32(0.9188), np.float32(0.8725), np.float32(0.9852), np.float32(0.982), np.float32(0.968), np.float32(0.8628), np.float32(0.7979), np.float32(0.8793), np.float32(0.969), np.float32(0.1806), np.float32(0.2)] +2025-11-08 01:09:35.797776: Epoch time: 567.14 s +2025-11-08 01:09:37.844288: +2025-11-08 01:09:37.848347: Epoch 925 +2025-11-08 01:09:37.849985: Current learning rate: 0.00097 +2025-11-08 01:18:36.575247: train_loss -0.4919 +2025-11-08 01:18:37.920719: val_loss -0.4859 +2025-11-08 01:18:37.922525: Pseudo dice [np.float32(0.9198), np.float32(0.8021), np.float32(0.7439), np.float32(0.7294), np.float32(0.8772), np.float32(0.8145), np.float32(0.8958), np.float32(0.9063), np.float32(0.9759), np.float32(0.976), np.float32(0.9706), np.float32(0.8556), np.float32(0.81), np.float32(0.8936), np.float32(0.9658), np.float32(0.2947), np.float32(0.2593)] +2025-11-08 01:18:37.924234: Epoch time: 538.74 s +2025-11-08 01:18:41.271373: +2025-11-08 01:18:41.273209: Epoch 926 +2025-11-08 01:18:41.279060: Current learning rate: 0.00096 +2025-11-08 01:27:53.806141: train_loss -0.4816 +2025-11-08 01:27:53.919760: val_loss -0.4769 +2025-11-08 01:27:53.923917: Pseudo dice [np.float32(0.9482), np.float32(0.7856), np.float32(0.7736), np.float32(0.7107), np.float32(0.879), np.float32(0.7846), np.float32(0.9098), np.float32(0.8787), np.float32(0.9798), np.float32(0.9692), np.float32(0.9676), np.float32(0.8631), np.float32(0.8229), np.float32(0.8626), np.float32(0.9714), np.float32(0.2619), np.float32(0.221)] +2025-11-08 01:27:53.928591: Epoch time: 552.54 s +2025-11-08 01:27:57.730306: +2025-11-08 01:27:57.735982: Epoch 927 +2025-11-08 01:27:57.738184: Current learning rate: 0.00095 +2025-11-08 01:37:31.253799: train_loss -0.4917 +2025-11-08 01:37:32.706269: val_loss -0.5034 +2025-11-08 01:37:32.712060: Pseudo dice [np.float32(0.9406), np.float32(0.7995), np.float32(0.7746), np.float32(0.6982), np.float32(0.8511), np.float32(0.8195), np.float32(0.9097), np.float32(0.8968), np.float32(0.9819), np.float32(0.9794), np.float32(0.9704), np.float32(0.8731), np.float32(0.7963), np.float32(0.8417), np.float32(0.966), np.float32(0.2634), np.float32(0.3003)] +2025-11-08 01:37:33.165633: Epoch time: 573.53 s +2025-11-08 01:37:36.539761: +2025-11-08 01:37:36.541335: Epoch 928 +2025-11-08 01:37:36.543081: Current learning rate: 0.00094 +2025-11-08 01:46:24.211596: train_loss -0.4796 +2025-11-08 01:46:24.303415: val_loss -0.4637 +2025-11-08 01:46:24.310212: Pseudo dice [np.float32(0.9148), np.float32(0.7956), np.float32(0.7225), np.float32(0.6939), np.float32(0.8754), np.float32(0.7818), np.float32(0.9068), np.float32(0.8757), np.float32(0.9662), np.float32(0.9668), np.float32(0.9695), np.float32(0.8732), np.float32(0.8051), np.float32(0.8767), np.float32(0.9739), np.float32(0.2272), np.float32(0.3104)] +2025-11-08 01:46:24.312401: Epoch time: 527.68 s +2025-11-08 01:46:27.585009: +2025-11-08 01:46:27.586390: Epoch 929 +2025-11-08 01:46:27.587734: Current learning rate: 0.00092 +2025-11-08 01:55:43.058814: train_loss -0.4916 +2025-11-08 01:55:43.068435: val_loss -0.4807 +2025-11-08 01:55:43.069731: Pseudo dice [np.float32(0.948), np.float32(0.7639), np.float32(0.7501), np.float32(0.7237), np.float32(0.872), np.float32(0.8147), np.float32(0.9148), np.float32(0.868), np.float32(0.9862), np.float32(0.9846), np.float32(0.9668), np.float32(0.8731), np.float32(0.8274), np.float32(0.8743), np.float32(0.96), np.float32(0.1908), np.float32(0.3923)] +2025-11-08 01:55:43.070828: Epoch time: 555.48 s +2025-11-08 01:55:44.959594: +2025-11-08 01:55:44.960869: Epoch 930 +2025-11-08 01:55:44.962432: Current learning rate: 0.00091 +2025-11-08 02:05:08.030483: train_loss -0.5028 +2025-11-08 02:05:08.036041: val_loss -0.4891 +2025-11-08 02:05:08.037921: Pseudo dice [np.float32(0.9474), np.float32(0.8042), np.float32(0.7842), np.float32(0.595), np.float32(0.8679), np.float32(0.8121), np.float32(0.9158), np.float32(0.8855), np.float32(0.9483), np.float32(0.9642), np.float32(0.9698), np.float32(0.8699), np.float32(0.8333), np.float32(0.881), np.float32(0.965), np.float32(0.3704), np.float32(0.3908)] +2025-11-08 02:05:08.164649: Epoch time: 563.08 s +2025-11-08 02:05:10.472256: +2025-11-08 02:05:10.473884: Epoch 931 +2025-11-08 02:05:10.478019: Current learning rate: 0.0009 +2025-11-08 02:14:22.327969: train_loss -0.4871 +2025-11-08 02:14:22.891624: val_loss -0.5014 +2025-11-08 02:14:22.893205: Pseudo dice [np.float32(0.9455), np.float32(0.819), np.float32(0.7597), np.float32(0.7127), np.float32(0.8799), np.float32(0.8173), np.float32(0.9135), np.float32(0.8907), np.float32(0.977), np.float32(0.974), np.float32(0.9709), np.float32(0.8642), np.float32(0.7956), np.float32(0.8803), np.float32(0.9739), np.float32(0.3284), np.float32(0.3671)] +2025-11-08 02:14:22.927155: Epoch time: 551.86 s +2025-11-08 02:14:26.719309: +2025-11-08 02:14:26.720759: Epoch 932 +2025-11-08 02:14:26.727588: Current learning rate: 0.00089 +2025-11-08 02:24:01.205781: train_loss -0.483 +2025-11-08 02:24:01.907396: val_loss -0.4703 +2025-11-08 02:24:01.909240: Pseudo dice [np.float32(0.9377), np.float32(0.8087), np.float32(0.7171), np.float32(0.6281), np.float32(0.8608), np.float32(0.8123), np.float32(0.9213), np.float32(0.8918), np.float32(0.9791), np.float32(0.9624), np.float32(0.9692), np.float32(0.8601), np.float32(0.827), np.float32(0.8706), np.float32(0.9614), np.float32(0.2828), np.float32(0.1643)] +2025-11-08 02:24:02.108168: Epoch time: 574.49 s +2025-11-08 02:24:05.027262: +2025-11-08 02:24:05.029485: Epoch 933 +2025-11-08 02:24:05.031341: Current learning rate: 0.00088 +2025-11-08 02:33:23.620300: train_loss -0.472 +2025-11-08 02:33:23.627079: val_loss -0.4899 +2025-11-08 02:33:23.628681: Pseudo dice [np.float32(0.933), np.float32(0.8197), np.float32(0.739), np.float32(0.7274), np.float32(0.8925), np.float32(0.8175), np.float32(0.9171), np.float32(0.8923), np.float32(0.9852), np.float32(0.9796), np.float32(0.968), np.float32(0.8613), np.float32(0.8174), np.float32(0.8869), np.float32(0.9697), np.float32(0.3695), np.float32(0.2293)] +2025-11-08 02:33:23.629845: Epoch time: 558.6 s +2025-11-08 02:33:25.735708: +2025-11-08 02:33:25.737392: Epoch 934 +2025-11-08 02:33:25.738496: Current learning rate: 0.00087 +2025-11-08 02:43:01.254085: train_loss -0.4858 +2025-11-08 02:43:01.263787: val_loss -0.4745 +2025-11-08 02:43:01.266435: Pseudo dice [np.float32(0.9184), np.float32(0.7597), np.float32(0.7287), np.float32(0.664), np.float32(0.8503), np.float32(0.7975), np.float32(0.85), np.float32(0.8929), np.float32(0.953), np.float32(0.9803), np.float32(0.9637), np.float32(0.8647), np.float32(0.7835), np.float32(0.852), np.float32(0.9495), np.float32(0.3336), np.float32(0.2996)] +2025-11-08 02:43:01.275279: Epoch time: 575.52 s +2025-11-08 02:43:03.380949: +2025-11-08 02:43:03.382240: Epoch 935 +2025-11-08 02:43:03.383736: Current learning rate: 0.00085 +2025-11-08 02:51:58.958658: train_loss -0.4859 +2025-11-08 02:52:00.041116: val_loss -0.4982 +2025-11-08 02:52:00.042907: Pseudo dice [np.float32(0.9277), np.float32(0.7591), np.float32(0.6941), np.float32(0.7208), np.float32(0.8901), np.float32(0.8002), np.float32(0.8789), np.float32(0.8993), np.float32(0.9867), np.float32(0.9839), np.float32(0.9712), np.float32(0.8764), np.float32(0.7968), np.float32(0.8954), np.float32(0.9704), np.float32(0.133), np.float32(0.1193)] +2025-11-08 02:52:00.111496: Epoch time: 535.58 s +2025-11-08 02:52:03.788303: +2025-11-08 02:52:03.789814: Epoch 936 +2025-11-08 02:52:03.791441: Current learning rate: 0.00084 +2025-11-08 03:01:30.171289: train_loss -0.493 +2025-11-08 03:01:30.664814: val_loss -0.4971 +2025-11-08 03:01:30.667234: Pseudo dice [np.float32(0.9418), np.float32(0.7659), np.float32(0.7117), np.float32(0.7325), np.float32(0.8516), np.float32(0.8082), np.float32(0.9058), np.float32(0.8942), np.float32(0.9756), np.float32(0.9784), np.float32(0.9705), np.float32(0.8716), np.float32(0.811), np.float32(0.8649), np.float32(0.9559), np.float32(0.465), np.float32(0.3581)] +2025-11-08 03:01:30.739376: Epoch time: 566.39 s +2025-11-08 03:01:33.673865: +2025-11-08 03:01:33.685812: Epoch 937 +2025-11-08 03:01:33.687479: Current learning rate: 0.00083 +2025-11-08 03:11:02.077257: train_loss -0.4951 +2025-11-08 03:11:02.085199: val_loss -0.5032 +2025-11-08 03:11:02.086381: Pseudo dice [np.float32(0.9364), np.float32(0.5868), np.float32(0.7316), np.float32(0.7023), np.float32(0.856), np.float32(0.7875), np.float32(0.8883), np.float32(0.8797), np.float32(0.9635), np.float32(0.9664), np.float32(0.9696), np.float32(0.8599), np.float32(0.7786), np.float32(0.8724), np.float32(0.9686), np.float32(0.4049), np.float32(0.2946)] +2025-11-08 03:11:02.087997: Epoch time: 568.41 s +2025-11-08 03:11:04.465788: +2025-11-08 03:11:04.467085: Epoch 938 +2025-11-08 03:11:04.468474: Current learning rate: 0.00082 +2025-11-08 03:20:15.296808: train_loss -0.4891 +2025-11-08 03:20:15.301682: val_loss -0.4618 +2025-11-08 03:20:15.303493: Pseudo dice [np.float32(0.9414), np.float32(0.807), np.float32(0.757), np.float32(0.6813), np.float32(0.8885), np.float32(0.7629), np.float32(0.9092), np.float32(0.8957), np.float32(0.9544), np.float32(0.9344), np.float32(0.9627), np.float32(0.8712), np.float32(0.8193), np.float32(0.8822), np.float32(0.9721), np.float32(0.2626), np.float32(0.134)] +2025-11-08 03:20:15.315143: Epoch time: 550.84 s +2025-11-08 03:20:18.667048: +2025-11-08 03:20:18.668454: Epoch 939 +2025-11-08 03:20:18.669570: Current learning rate: 0.00081 +2025-11-08 03:29:37.869606: train_loss -0.4922 +2025-11-08 03:29:38.506249: val_loss -0.5144 +2025-11-08 03:29:38.508119: Pseudo dice [np.float32(0.9407), np.float32(0.7715), np.float32(0.7198), np.float32(0.7319), np.float32(0.8723), np.float32(0.7837), np.float32(0.9), np.float32(0.8675), np.float32(0.9823), np.float32(0.9846), np.float32(0.9643), np.float32(0.8531), np.float32(0.8153), np.float32(0.884), np.float32(0.9656), np.float32(0.4317), np.float32(0.4817)] +2025-11-08 03:29:38.669138: Epoch time: 559.21 s +2025-11-08 03:29:41.706136: +2025-11-08 03:29:41.707557: Epoch 940 +2025-11-08 03:29:41.711226: Current learning rate: 0.00079 +2025-11-08 03:38:25.869562: train_loss -0.4761 +2025-11-08 03:38:25.885834: val_loss -0.4975 +2025-11-08 03:38:25.887545: Pseudo dice [np.float32(0.9205), np.float32(0.8456), np.float32(0.7436), np.float32(0.647), np.float32(0.8688), np.float32(0.8394), np.float32(0.8867), np.float32(0.8995), np.float32(0.9782), np.float32(0.9792), np.float32(0.9715), np.float32(0.8601), np.float32(0.8201), np.float32(0.8608), np.float32(0.9661), np.float32(0.3606), np.float32(0.34)] +2025-11-08 03:38:25.888920: Epoch time: 524.17 s +2025-11-08 03:38:28.139862: +2025-11-08 03:38:28.147699: Epoch 941 +2025-11-08 03:38:28.159050: Current learning rate: 0.00078 +2025-11-08 03:47:38.770082: train_loss -0.4733 +2025-11-08 03:47:38.779984: val_loss -0.4911 +2025-11-08 03:47:38.781731: Pseudo dice [np.float32(0.9398), np.float32(0.8091), np.float32(0.7129), np.float32(0.6532), np.float32(0.8688), np.float32(0.7869), np.float32(0.9019), np.float32(0.8784), np.float32(0.9837), np.float32(0.9823), np.float32(0.9696), np.float32(0.8685), np.float32(0.8263), np.float32(0.8972), np.float32(0.9709), np.float32(0.4712), np.float32(0.2732)] +2025-11-08 03:47:38.783496: Epoch time: 550.63 s +2025-11-08 03:47:41.099673: +2025-11-08 03:47:41.112735: Epoch 942 +2025-11-08 03:47:41.114246: Current learning rate: 0.00077 +2025-11-08 03:56:56.814057: train_loss -0.4848 +2025-11-08 03:56:56.993607: val_loss -0.4815 +2025-11-08 03:56:56.995605: Pseudo dice [np.float32(0.944), np.float32(0.7959), np.float32(0.7126), np.float32(0.7266), np.float32(0.8624), np.float32(0.7984), np.float32(0.8954), np.float32(0.9002), np.float32(0.9759), np.float32(0.976), np.float32(0.9692), np.float32(0.8663), np.float32(0.8093), np.float32(0.8929), np.float32(0.95), np.float32(0.2869), np.float32(0.2065)] +2025-11-08 03:56:56.998027: Epoch time: 555.72 s +2025-11-08 03:56:59.582266: +2025-11-08 03:56:59.583573: Epoch 943 +2025-11-08 03:56:59.584857: Current learning rate: 0.00076 +2025-11-08 04:06:10.964382: train_loss -0.4877 +2025-11-08 04:06:11.145499: val_loss -0.4652 +2025-11-08 04:06:11.147578: Pseudo dice [np.float32(0.9342), np.float32(0.7833), np.float32(0.758), np.float32(0.6754), np.float32(0.8826), np.float32(0.7964), np.float32(0.9056), np.float32(0.8966), np.float32(0.9804), np.float32(0.983), np.float32(0.9697), np.float32(0.8604), np.float32(0.79), np.float32(0.8893), np.float32(0.9704), np.float32(0.2631), np.float32(0.3385)] +2025-11-08 04:06:11.201801: Epoch time: 551.39 s +2025-11-08 04:06:14.140133: +2025-11-08 04:06:14.141601: Epoch 944 +2025-11-08 04:06:14.142855: Current learning rate: 0.00075 +2025-11-08 04:15:13.694283: train_loss -0.4752 +2025-11-08 04:15:13.700404: val_loss -0.5082 +2025-11-08 04:15:13.701694: Pseudo dice [np.float32(0.9379), np.float32(0.7826), np.float32(0.7289), np.float32(0.7125), np.float32(0.8495), np.float32(0.8204), np.float32(0.9127), np.float32(0.886), np.float32(0.9836), np.float32(0.9818), np.float32(0.9703), np.float32(0.866), np.float32(0.8049), np.float32(0.8596), np.float32(0.9627), np.float32(0.3254), np.float32(0.3606)] +2025-11-08 04:15:13.702874: Epoch time: 539.56 s +2025-11-08 04:15:15.748260: +2025-11-08 04:15:15.749751: Epoch 945 +2025-11-08 04:15:15.751089: Current learning rate: 0.00074 +2025-11-08 04:24:26.462912: train_loss -0.5005 +2025-11-08 04:24:29.253458: val_loss -0.4797 +2025-11-08 04:24:29.255445: Pseudo dice [np.float32(0.9429), np.float32(0.814), np.float32(0.7567), np.float32(0.6929), np.float32(0.8797), np.float32(0.842), np.float32(0.9301), np.float32(0.8992), np.float32(0.979), np.float32(0.9789), np.float32(0.9717), np.float32(0.8618), np.float32(0.7946), np.float32(0.8899), np.float32(0.9553), np.float32(0.2776), np.float32(0.3155)] +2025-11-08 04:24:29.257286: Epoch time: 550.72 s +2025-11-08 04:24:32.147221: +2025-11-08 04:24:32.161733: Epoch 946 +2025-11-08 04:24:32.163546: Current learning rate: 0.00072 +2025-11-08 04:33:37.387736: train_loss -0.4828 +2025-11-08 04:33:37.392908: val_loss -0.4908 +2025-11-08 04:33:37.403359: Pseudo dice [np.float32(0.9338), np.float32(0.7641), np.float32(0.7701), np.float32(0.6031), np.float32(0.8756), np.float32(0.787), np.float32(0.8995), np.float32(0.8954), np.float32(0.9829), np.float32(0.9832), np.float32(0.9646), np.float32(0.8622), np.float32(0.7732), np.float32(0.895), np.float32(0.9664), np.float32(0.222), np.float32(0.1873)] +2025-11-08 04:33:37.407046: Epoch time: 545.25 s +2025-11-08 04:33:39.496066: +2025-11-08 04:33:39.500212: Epoch 947 +2025-11-08 04:33:39.501818: Current learning rate: 0.00071 +2025-11-08 04:43:00.020801: train_loss -0.4928 +2025-11-08 04:43:21.919140: val_loss -0.5127 +2025-11-08 04:43:21.920857: Pseudo dice [np.float32(0.9377), np.float32(0.8002), np.float32(0.7234), np.float32(0.627), np.float32(0.8826), np.float32(0.8221), np.float32(0.9345), np.float32(0.888), np.float32(0.9839), np.float32(0.9823), np.float32(0.969), np.float32(0.8568), np.float32(0.788), np.float32(0.8784), np.float32(0.97), np.float32(0.3902), np.float32(0.3421)] +2025-11-08 04:43:21.998128: Epoch time: 560.53 s +2025-11-08 04:43:25.150983: +2025-11-08 04:43:25.152309: Epoch 948 +2025-11-08 04:43:25.153539: Current learning rate: 0.0007 +2025-11-08 04:52:37.181034: train_loss -0.5035 +2025-11-08 04:52:38.047790: val_loss -0.4623 +2025-11-08 04:52:38.049461: Pseudo dice [np.float32(0.9151), np.float32(0.7765), np.float32(0.7408), np.float32(0.6967), np.float32(0.8752), np.float32(0.8402), np.float32(0.9243), np.float32(0.8945), np.float32(0.9431), np.float32(0.9574), np.float32(0.9677), np.float32(0.8763), np.float32(0.8207), np.float32(0.8968), np.float32(0.9609), np.float32(0.4551), np.float32(0.3493)] +2025-11-08 04:52:38.051129: Epoch time: 552.03 s +2025-11-08 04:52:42.236986: +2025-11-08 04:52:42.238312: Epoch 949 +2025-11-08 04:52:42.239847: Current learning rate: 0.00069 +2025-11-08 05:02:00.585401: train_loss -0.497 +2025-11-08 05:02:00.685532: val_loss -0.4985 +2025-11-08 05:02:00.687823: Pseudo dice [np.float32(0.9439), np.float32(0.7849), np.float32(0.7111), np.float32(0.6963), np.float32(0.8813), np.float32(0.8254), np.float32(0.9251), np.float32(0.8875), np.float32(0.9744), np.float32(0.9659), np.float32(0.9661), np.float32(0.8689), np.float32(0.8251), np.float32(0.8923), np.float32(0.9604), np.float32(0.2709), np.float32(0.3655)] +2025-11-08 05:02:00.689100: Epoch time: 558.35 s +2025-11-08 05:02:13.065394: +2025-11-08 05:02:13.066843: Epoch 950 +2025-11-08 05:02:13.068067: Current learning rate: 0.00067 +2025-11-08 05:11:30.151193: train_loss -0.5045 +2025-11-08 05:11:30.157132: val_loss -0.4845 +2025-11-08 05:11:30.159322: Pseudo dice [np.float32(0.9305), np.float32(0.8007), np.float32(0.7735), np.float32(0.6979), np.float32(0.8912), np.float32(0.8306), np.float32(0.921), np.float32(0.8982), np.float32(0.9845), np.float32(0.983), np.float32(0.9732), np.float32(0.8696), np.float32(0.7765), np.float32(0.8989), np.float32(0.9675), np.float32(0.3884), np.float32(0.273)] +2025-11-08 05:11:30.161334: Epoch time: 557.09 s +2025-11-08 05:11:36.456056: +2025-11-08 05:11:36.460916: Epoch 951 +2025-11-08 05:11:36.462995: Current learning rate: 0.00066 +2025-11-08 05:21:39.293419: train_loss -0.5041 +2025-11-08 05:21:39.301593: val_loss -0.4868 +2025-11-08 05:21:39.309861: Pseudo dice [np.float32(0.9428), np.float32(0.7683), np.float32(0.7427), np.float32(0.6966), np.float32(0.8895), np.float32(0.8207), np.float32(0.8968), np.float32(0.8788), np.float32(0.9725), np.float32(0.9716), np.float32(0.9667), np.float32(0.8673), np.float32(0.8028), np.float32(0.863), np.float32(0.9656), np.float32(0.3478), np.float32(0.2565)] +2025-11-08 05:21:39.620510: Epoch time: 602.85 s +2025-11-08 05:21:44.586305: +2025-11-08 05:21:44.592698: Epoch 952 +2025-11-08 05:21:44.594437: Current learning rate: 0.00065 +2025-11-08 05:31:00.958922: train_loss -0.4736 +2025-11-08 05:31:04.145105: val_loss -0.5009 +2025-11-08 05:31:04.146984: Pseudo dice [np.float32(0.9511), np.float32(0.7763), np.float32(0.7196), np.float32(0.6563), np.float32(0.8799), np.float32(0.7882), np.float32(0.9146), np.float32(0.8773), np.float32(0.9754), np.float32(0.9752), np.float32(0.9648), np.float32(0.8604), np.float32(0.8206), np.float32(0.8844), np.float32(0.9498), np.float32(0.3721), np.float32(0.3303)] +2025-11-08 05:31:04.148678: Epoch time: 556.38 s +2025-11-08 05:31:16.463351: +2025-11-08 05:31:16.464672: Epoch 953 +2025-11-08 05:31:16.465984: Current learning rate: 0.00064 +2025-11-08 05:40:27.334379: train_loss -0.4861 +2025-11-08 05:40:27.343404: val_loss -0.4697 +2025-11-08 05:40:27.344747: Pseudo dice [np.float32(0.9445), np.float32(0.7672), np.float32(0.7494), np.float32(0.6668), np.float32(0.856), np.float32(0.8109), np.float32(0.8693), np.float32(0.8829), np.float32(0.9815), np.float32(0.9801), np.float32(0.9695), np.float32(0.8508), np.float32(0.7957), np.float32(0.8556), np.float32(0.9668), np.float32(0.3459), np.float32(0.1388)] +2025-11-08 05:40:27.346026: Epoch time: 550.88 s +2025-11-08 05:40:29.807289: +2025-11-08 05:40:29.815750: Epoch 954 +2025-11-08 05:40:29.816878: Current learning rate: 0.00063 +2025-11-08 05:49:43.301459: train_loss -0.466 +2025-11-08 05:49:50.140240: val_loss -0.4897 +2025-11-08 05:49:50.141776: Pseudo dice [np.float32(0.9292), np.float32(0.782), np.float32(0.7323), np.float32(0.734), np.float32(0.8833), np.float32(0.8125), np.float32(0.9263), np.float32(0.9073), np.float32(0.9821), np.float32(0.982), np.float32(0.9695), np.float32(0.8494), np.float32(0.7742), np.float32(0.8888), np.float32(0.9718), np.float32(0.1982), np.float32(0.2759)] +2025-11-08 05:49:50.143510: Epoch time: 553.5 s +2025-11-08 05:49:55.857275: +2025-11-08 05:49:55.858685: Epoch 955 +2025-11-08 05:49:55.860013: Current learning rate: 0.00061 +2025-11-08 05:59:06.688529: train_loss -0.4799 +2025-11-08 05:59:28.430680: val_loss -0.4836 +2025-11-08 05:59:28.432807: Pseudo dice [np.float32(0.9176), np.float32(0.79), np.float32(0.7787), np.float32(0.6619), np.float32(0.8869), np.float32(0.8469), np.float32(0.9233), np.float32(0.8891), np.float32(0.9614), np.float32(0.9517), np.float32(0.9736), np.float32(0.8727), np.float32(0.8112), np.float32(0.8728), np.float32(0.9718), np.float32(0.4054), np.float32(0.2528)] +2025-11-08 05:59:31.827149: Epoch time: 550.84 s +2025-11-08 06:00:11.329811: +2025-11-08 06:00:11.331442: Epoch 956 +2025-11-08 06:00:11.332781: Current learning rate: 0.0006 +2025-11-08 06:09:37.287859: train_loss -0.4885 +2025-11-08 06:09:37.567379: val_loss -0.4688 +2025-11-08 06:09:37.568643: Pseudo dice [np.float32(0.9423), np.float32(0.7568), np.float32(0.7304), np.float32(0.6434), np.float32(0.8692), np.float32(0.8131), np.float32(0.9236), np.float32(0.8775), np.float32(0.9836), np.float32(0.9789), np.float32(0.9689), np.float32(0.8558), np.float32(0.7684), np.float32(0.8895), np.float32(0.9694), np.float32(0.1856), np.float32(0.1714)] +2025-11-08 06:09:37.570024: Epoch time: 565.96 s +2025-11-08 06:09:40.205574: +2025-11-08 06:09:40.206873: Epoch 957 +2025-11-08 06:09:40.208252: Current learning rate: 0.00059 +2025-11-08 06:19:13.754725: train_loss -0.5015 +2025-11-08 06:19:13.760747: val_loss -0.4553 +2025-11-08 06:19:13.762347: Pseudo dice [np.float32(0.9311), np.float32(0.779), np.float32(0.7295), np.float32(0.7123), np.float32(0.8776), np.float32(0.805), np.float32(0.9155), np.float32(0.8909), np.float32(0.9795), np.float32(0.9765), np.float32(0.9714), np.float32(0.872), np.float32(0.7992), np.float32(0.886), np.float32(0.9606), np.float32(0.2115), np.float32(0.3799)] +2025-11-08 06:19:13.763833: Epoch time: 573.55 s +2025-11-08 06:19:16.201764: +2025-11-08 06:19:16.203144: Epoch 958 +2025-11-08 06:19:16.204458: Current learning rate: 0.00058 +2025-11-08 06:29:44.949900: train_loss -0.4756 +2025-11-08 06:29:44.956504: val_loss -0.5558 +2025-11-08 06:29:44.958060: Pseudo dice [np.float32(0.9483), np.float32(0.8005), np.float32(0.746), np.float32(0.6139), np.float32(0.8664), np.float32(0.8182), np.float32(0.9265), np.float32(0.8936), np.float32(0.9836), np.float32(0.9835), np.float32(0.9722), np.float32(0.864), np.float32(0.8098), np.float32(0.8747), np.float32(0.9705), np.float32(0.4833), np.float32(0.3912)] +2025-11-08 06:29:44.959508: Epoch time: 628.75 s +2025-11-08 06:29:50.282228: +2025-11-08 06:29:50.283613: Epoch 959 +2025-11-08 06:29:50.284761: Current learning rate: 0.00056 +2025-11-08 06:39:09.217307: train_loss -0.4772 +2025-11-08 06:39:16.807712: val_loss -0.466 +2025-11-08 06:39:16.809375: Pseudo dice [np.float32(0.9275), np.float32(0.7935), np.float32(0.7773), np.float32(0.7037), np.float32(0.8723), np.float32(0.8148), np.float32(0.8929), np.float32(0.894), np.float32(0.9838), np.float32(0.9837), np.float32(0.9736), np.float32(0.8475), np.float32(0.7547), np.float32(0.8861), np.float32(0.9688), np.float32(0.2874), np.float32(0.2739)] +2025-11-08 06:39:16.811022: Epoch time: 558.94 s +2025-11-08 06:39:18.719179: +2025-11-08 06:39:18.720683: Epoch 960 +2025-11-08 06:39:18.721761: Current learning rate: 0.00055 +2025-11-08 06:51:04.043034: train_loss -0.4751 +2025-11-08 06:51:36.214063: val_loss -0.4919 +2025-11-08 06:51:36.215436: Pseudo dice [np.float32(0.9458), np.float32(0.7851), np.float32(0.7552), np.float32(0.7197), np.float32(0.8823), np.float32(0.8402), np.float32(0.9217), np.float32(0.8812), np.float32(0.9833), np.float32(0.9742), np.float32(0.97), np.float32(0.8533), np.float32(0.7915), np.float32(0.8959), np.float32(0.9625), np.float32(0.2803), np.float32(0.2336)] +2025-11-08 06:51:36.216767: Epoch time: 705.33 s +2025-11-08 06:51:38.172513: +2025-11-08 06:51:38.173782: Epoch 961 +2025-11-08 06:51:38.174860: Current learning rate: 0.00054 +2025-11-08 07:00:56.082016: train_loss -0.4898 +2025-11-08 07:00:56.095566: val_loss -0.5346 +2025-11-08 07:00:56.098151: Pseudo dice [np.float32(0.9525), np.float32(0.8204), np.float32(0.7665), np.float32(0.7008), np.float32(0.8951), np.float32(0.8025), np.float32(0.9024), np.float32(0.908), np.float32(0.9841), np.float32(0.984), np.float32(0.9689), np.float32(0.8671), np.float32(0.7783), np.float32(0.8869), np.float32(0.9708), np.float32(0.3952), np.float32(0.371)] +2025-11-08 07:00:56.099491: Epoch time: 557.91 s +2025-11-08 07:00:57.948834: +2025-11-08 07:00:57.951569: Epoch 962 +2025-11-08 07:00:57.952753: Current learning rate: 0.00053 +2025-11-08 07:10:17.882813: train_loss -0.5003 +2025-11-08 07:10:26.466083: val_loss -0.5204 +2025-11-08 07:10:26.467756: Pseudo dice [np.float32(0.9317), np.float32(0.7968), np.float32(0.7692), np.float32(0.6365), np.float32(0.8789), np.float32(0.8046), np.float32(0.9098), np.float32(0.9105), np.float32(0.9699), np.float32(0.9651), np.float32(0.9705), np.float32(0.8622), np.float32(0.8206), np.float32(0.891), np.float32(0.9682), np.float32(0.3293), np.float32(0.3067)] +2025-11-08 07:10:26.470422: Epoch time: 559.94 s +2025-11-08 07:10:40.207930: +2025-11-08 07:10:40.209438: Epoch 963 +2025-11-08 07:10:40.210732: Current learning rate: 0.00051 +2025-11-08 07:20:05.110250: train_loss -0.4883 +2025-11-08 07:20:05.161883: val_loss -0.487 +2025-11-08 07:20:05.163581: Pseudo dice [np.float32(0.9363), np.float32(0.7926), np.float32(0.7104), np.float32(0.6591), np.float32(0.8567), np.float32(0.8126), np.float32(0.8553), np.float32(0.8703), np.float32(0.963), np.float32(0.9631), np.float32(0.9664), np.float32(0.8788), np.float32(0.7879), np.float32(0.8777), np.float32(0.9663), np.float32(0.3236), np.float32(0.1658)] +2025-11-08 07:20:05.165903: Epoch time: 564.91 s +2025-11-08 07:20:07.078470: +2025-11-08 07:20:07.080924: Epoch 964 +2025-11-08 07:20:07.082016: Current learning rate: 0.0005 +2025-11-08 07:29:23.256335: train_loss -0.4942 +2025-11-08 07:29:23.261733: val_loss -0.4772 +2025-11-08 07:29:23.263316: Pseudo dice [np.float32(0.94), np.float32(0.7923), np.float32(0.7185), np.float32(0.6726), np.float32(0.8622), np.float32(0.8246), np.float32(0.9174), np.float32(0.886), np.float32(0.9786), np.float32(0.9773), np.float32(0.9684), np.float32(0.8598), np.float32(0.8183), np.float32(0.8679), np.float32(0.9633), np.float32(0.4493), np.float32(0.3788)] +2025-11-08 07:29:23.267596: Epoch time: 556.18 s +2025-11-08 07:29:25.161401: +2025-11-08 07:29:25.167886: Epoch 965 +2025-11-08 07:29:25.169150: Current learning rate: 0.00049 +2025-11-08 07:38:56.765459: train_loss -0.4941 +2025-11-08 07:38:56.770916: val_loss -0.435 +2025-11-08 07:38:56.772093: Pseudo dice [np.float32(0.945), np.float32(0.8193), np.float32(0.7591), np.float32(0.7433), np.float32(0.8771), np.float32(0.818), np.float32(0.9217), np.float32(0.8734), np.float32(0.9734), np.float32(0.9737), np.float32(0.9726), np.float32(0.8561), np.float32(0.8076), np.float32(0.8874), np.float32(0.9711), np.float32(0.384), np.float32(0.2054)] +2025-11-08 07:38:56.773674: Epoch time: 571.61 s +2025-11-08 07:38:58.563111: +2025-11-08 07:38:58.564768: Epoch 966 +2025-11-08 07:38:58.566104: Current learning rate: 0.00048 +2025-11-08 07:48:31.317165: train_loss -0.4957 +2025-11-08 07:48:31.328125: val_loss -0.4904 +2025-11-08 07:48:31.329617: Pseudo dice [np.float32(0.935), np.float32(0.7699), np.float32(0.6922), np.float32(0.7361), np.float32(0.8606), np.float32(0.8101), np.float32(0.9265), np.float32(0.8956), np.float32(0.9775), np.float32(0.9762), np.float32(0.967), np.float32(0.8752), np.float32(0.8182), np.float32(0.876), np.float32(0.9635), np.float32(0.0836), np.float32(0.0857)] +2025-11-08 07:48:31.335534: Epoch time: 572.76 s +2025-11-08 07:48:33.150014: +2025-11-08 07:48:33.152524: Epoch 967 +2025-11-08 07:48:33.154614: Current learning rate: 0.00046 +2025-11-08 07:57:53.310927: train_loss -0.4869 +2025-11-08 07:57:53.318745: val_loss -0.4906 +2025-11-08 07:57:53.322285: Pseudo dice [np.float32(0.9429), np.float32(0.7771), np.float32(0.7251), np.float32(0.7391), np.float32(0.8686), np.float32(0.827), np.float32(0.9136), np.float32(0.8962), np.float32(0.9769), np.float32(0.9801), np.float32(0.969), np.float32(0.8692), np.float32(0.8142), np.float32(0.8947), np.float32(0.9443), np.float32(0.209), np.float32(0.2711)] +2025-11-08 07:57:53.324290: Epoch time: 560.17 s +2025-11-08 07:57:55.166010: +2025-11-08 07:57:55.167739: Epoch 968 +2025-11-08 07:57:55.169082: Current learning rate: 0.00045 +2025-11-08 08:07:05.997627: train_loss -0.4763 +2025-11-08 08:07:06.006692: val_loss -0.5099 +2025-11-08 08:07:06.012081: Pseudo dice [np.float32(0.9528), np.float32(0.8012), np.float32(0.7484), np.float32(0.7277), np.float32(0.8624), np.float32(0.8093), np.float32(0.9062), np.float32(0.8889), np.float32(0.9791), np.float32(0.9786), np.float32(0.9674), np.float32(0.8562), np.float32(0.83), np.float32(0.8673), np.float32(0.9565), np.float32(0.3167), np.float32(0.3458)] +2025-11-08 08:07:06.014706: Epoch time: 550.84 s +2025-11-08 08:07:07.895055: +2025-11-08 08:07:07.896503: Epoch 969 +2025-11-08 08:07:07.897827: Current learning rate: 0.00044 +2025-11-08 08:16:24.451009: train_loss -0.4806 +2025-11-08 08:16:24.457602: val_loss -0.4839 +2025-11-08 08:16:24.459560: Pseudo dice [np.float32(0.9374), np.float32(0.8022), np.float32(0.741), np.float32(0.6131), np.float32(0.8808), np.float32(0.8141), np.float32(0.9084), np.float32(0.899), np.float32(0.9745), np.float32(0.9733), np.float32(0.9696), np.float32(0.8571), np.float32(0.791), np.float32(0.8842), np.float32(0.9605), np.float32(0.3922), np.float32(0.3926)] +2025-11-08 08:16:24.461221: Epoch time: 556.56 s +2025-11-08 08:16:26.437997: +2025-11-08 08:16:26.440223: Epoch 970 +2025-11-08 08:16:26.442907: Current learning rate: 0.00043 +2025-11-08 08:25:34.986256: train_loss -0.4853 +2025-11-08 08:25:35.012773: val_loss -0.5356 +2025-11-08 08:25:35.014754: Pseudo dice [np.float32(0.9435), np.float32(0.8089), np.float32(0.7999), np.float32(0.7211), np.float32(0.8585), np.float32(0.8552), np.float32(0.9069), np.float32(0.8946), np.float32(0.9765), np.float32(0.9749), np.float32(0.9714), np.float32(0.8751), np.float32(0.796), np.float32(0.8631), np.float32(0.9609), np.float32(0.4582), np.float32(0.3797)] +2025-11-08 08:25:35.028751: Epoch time: 548.55 s +2025-11-08 08:25:36.833708: +2025-11-08 08:25:36.836966: Epoch 971 +2025-11-08 08:25:36.838202: Current learning rate: 0.00041 +2025-11-08 08:34:45.103458: train_loss -0.4927 +2025-11-08 08:34:45.113324: val_loss -0.4376 +2025-11-08 08:34:45.115930: Pseudo dice [np.float32(0.8768), np.float32(0.8063), np.float32(0.7467), np.float32(0.6949), np.float32(0.8492), np.float32(0.8069), np.float32(0.9189), np.float32(0.8858), np.float32(0.9749), np.float32(0.9721), np.float32(0.9721), np.float32(0.8512), np.float32(0.7889), np.float32(0.8831), np.float32(0.9691), np.float32(0.1518), np.float32(0.1484)] +2025-11-08 08:34:45.118318: Epoch time: 548.27 s +2025-11-08 08:34:47.038239: +2025-11-08 08:34:47.040503: Epoch 972 +2025-11-08 08:34:47.041694: Current learning rate: 0.0004 +2025-11-08 08:43:58.547504: train_loss -0.5237 +2025-11-08 08:43:58.554256: val_loss -0.487 +2025-11-08 08:43:58.555633: Pseudo dice [np.float32(0.9398), np.float32(0.8216), np.float32(0.7525), np.float32(0.7002), np.float32(0.8366), np.float32(0.8076), np.float32(0.8937), np.float32(0.8903), np.float32(0.9813), np.float32(0.9767), np.float32(0.9706), np.float32(0.8581), np.float32(0.8191), np.float32(0.8953), np.float32(0.9645), np.float32(0.3406), np.float32(0.2783)] +2025-11-08 08:43:58.557655: Epoch time: 551.51 s +2025-11-08 08:44:00.431694: +2025-11-08 08:44:00.433506: Epoch 973 +2025-11-08 08:44:00.435020: Current learning rate: 0.00039 +2025-11-08 08:53:17.589041: train_loss -0.4958 +2025-11-08 08:53:17.598620: val_loss -0.4716 +2025-11-08 08:53:17.600181: Pseudo dice [np.float32(0.9437), np.float32(0.8037), np.float32(0.7218), np.float32(0.6723), np.float32(0.8608), np.float32(0.8049), np.float32(0.892), np.float32(0.8873), np.float32(0.9806), np.float32(0.9794), np.float32(0.9734), np.float32(0.8705), np.float32(0.8083), np.float32(0.8823), np.float32(0.9662), np.float32(0.2831), np.float32(0.2354)] +2025-11-08 08:53:17.601837: Epoch time: 557.16 s +2025-11-08 08:53:19.530150: +2025-11-08 08:53:19.531643: Epoch 974 +2025-11-08 08:53:19.532918: Current learning rate: 0.00037 +2025-11-08 09:02:37.181288: train_loss -0.4859 +2025-11-08 09:02:37.188729: val_loss -0.4622 +2025-11-08 09:02:37.191319: Pseudo dice [np.float32(0.9217), np.float32(0.7725), np.float32(0.7162), np.float32(0.6966), np.float32(0.8746), np.float32(0.797), np.float32(0.9082), np.float32(0.8913), np.float32(0.9773), np.float32(0.9733), np.float32(0.969), np.float32(0.8782), np.float32(0.7694), np.float32(0.8821), np.float32(0.9656), np.float32(0.3358), np.float32(0.1984)] +2025-11-08 09:02:37.193376: Epoch time: 557.66 s +2025-11-08 09:02:39.309774: +2025-11-08 09:02:39.311665: Epoch 975 +2025-11-08 09:02:39.313660: Current learning rate: 0.00036 +2025-11-08 09:11:48.085834: train_loss -0.4996 +2025-11-08 09:11:48.097555: val_loss -0.4819 +2025-11-08 09:11:48.100173: Pseudo dice [np.float32(0.9383), np.float32(0.8047), np.float32(0.7432), np.float32(0.6355), np.float32(0.8585), np.float32(0.8212), np.float32(0.8965), np.float32(0.8983), np.float32(0.9785), np.float32(0.9776), np.float32(0.9695), np.float32(0.8618), np.float32(0.7997), np.float32(0.8767), np.float32(0.9671), np.float32(0.4337), np.float32(0.4537)] +2025-11-08 09:11:48.101734: Epoch time: 548.78 s +2025-11-08 09:11:49.938646: +2025-11-08 09:11:49.941027: Epoch 976 +2025-11-08 09:11:49.943393: Current learning rate: 0.00035 +2025-11-08 09:20:50.324929: train_loss -0.4983 +2025-11-08 09:20:50.341599: val_loss -0.5077 +2025-11-08 09:20:50.342935: Pseudo dice [np.float32(0.9176), np.float32(0.8213), np.float32(0.772), np.float32(0.6766), np.float32(0.8868), np.float32(0.8499), np.float32(0.9144), np.float32(0.8966), np.float32(0.982), np.float32(0.9827), np.float32(0.9706), np.float32(0.8671), np.float32(0.809), np.float32(0.9016), np.float32(0.9665), np.float32(0.346), np.float32(0.2171)] +2025-11-08 09:20:50.344445: Epoch time: 540.39 s +2025-11-08 09:20:52.202450: +2025-11-08 09:20:52.204258: Epoch 977 +2025-11-08 09:20:52.210208: Current learning rate: 0.00034 +2025-11-08 09:29:42.988774: train_loss -0.501 +2025-11-08 09:29:43.000267: val_loss -0.4927 +2025-11-08 09:29:43.001683: Pseudo dice [np.float32(0.9411), np.float32(0.7762), np.float32(0.7568), np.float32(0.657), np.float32(0.8727), np.float32(0.8317), np.float32(0.9234), np.float32(0.9039), np.float32(0.9534), np.float32(0.9569), np.float32(0.9728), np.float32(0.8718), np.float32(0.796), np.float32(0.896), np.float32(0.9723), np.float32(0.3542), np.float32(0.3041)] +2025-11-08 09:29:43.004004: Epoch time: 530.79 s +2025-11-08 09:29:44.846145: +2025-11-08 09:29:44.848158: Epoch 978 +2025-11-08 09:29:44.849975: Current learning rate: 0.00032 +2025-11-08 09:38:46.407085: train_loss -0.4877 +2025-11-08 09:38:46.439299: val_loss -0.4756 +2025-11-08 09:38:46.441638: Pseudo dice [np.float32(0.943), np.float32(0.8085), np.float32(0.736), np.float32(0.6552), np.float32(0.8845), np.float32(0.8183), np.float32(0.9057), np.float32(0.8909), np.float32(0.9697), np.float32(0.9696), np.float32(0.9702), np.float32(0.8816), np.float32(0.8089), np.float32(0.8539), np.float32(0.9567), np.float32(0.3605), np.float32(0.2975)] +2025-11-08 09:38:46.444864: Epoch time: 541.57 s +2025-11-08 09:38:48.364572: +2025-11-08 09:38:48.368209: Epoch 979 +2025-11-08 09:38:48.369761: Current learning rate: 0.00031 +2025-11-08 09:47:51.673832: train_loss -0.5134 +2025-11-08 09:47:51.680332: val_loss -0.508 +2025-11-08 09:47:51.681731: Pseudo dice [np.float32(0.9339), np.float32(0.7711), np.float32(0.6879), np.float32(0.7197), np.float32(0.8928), np.float32(0.8186), np.float32(0.9104), np.float32(0.8864), np.float32(0.9827), np.float32(0.9813), np.float32(0.9684), np.float32(0.88), np.float32(0.8107), np.float32(0.9069), np.float32(0.9706), np.float32(0.3958), np.float32(0.3133)] +2025-11-08 09:47:51.683046: Epoch time: 543.31 s +2025-11-08 09:47:53.592174: +2025-11-08 09:47:53.594166: Epoch 980 +2025-11-08 09:47:53.595951: Current learning rate: 0.0003 +2025-11-08 09:56:49.706097: train_loss -0.4877 +2025-11-08 09:56:49.717705: val_loss -0.4737 +2025-11-08 09:56:49.719366: Pseudo dice [np.float32(0.9373), np.float32(0.7748), np.float32(0.7368), np.float32(0.6702), np.float32(0.8694), np.float32(0.8051), np.float32(0.9051), np.float32(0.8841), np.float32(0.9826), np.float32(0.9808), np.float32(0.9711), np.float32(0.854), np.float32(0.7786), np.float32(0.8757), np.float32(0.9704), np.float32(0.3161), np.float32(0.2812)] +2025-11-08 09:56:49.720843: Epoch time: 536.12 s +2025-11-08 09:56:51.716123: +2025-11-08 09:56:51.717440: Epoch 981 +2025-11-08 09:56:51.718788: Current learning rate: 0.00028 +2025-11-08 10:05:46.649615: train_loss -0.4999 +2025-11-08 10:05:46.708738: val_loss -0.4793 +2025-11-08 10:05:46.711821: Pseudo dice [np.float32(0.9312), np.float32(0.8153), np.float32(0.7074), np.float32(0.7228), np.float32(0.8821), np.float32(0.8043), np.float32(0.8836), np.float32(0.8782), np.float32(0.9855), np.float32(0.9857), np.float32(0.97), np.float32(0.8764), np.float32(0.8058), np.float32(0.8741), np.float32(0.9735), np.float32(0.4451), np.float32(0.3855)] +2025-11-08 10:05:46.714721: Epoch time: 534.94 s +2025-11-08 10:05:48.794958: +2025-11-08 10:05:48.797171: Epoch 982 +2025-11-08 10:05:48.800019: Current learning rate: 0.00027 +2025-11-08 10:14:55.009187: train_loss -0.4879 +2025-11-08 10:14:55.016978: val_loss -0.4947 +2025-11-08 10:14:55.018288: Pseudo dice [np.float32(0.9391), np.float32(0.7596), np.float32(0.7366), np.float32(0.7005), np.float32(0.888), np.float32(0.7895), np.float32(0.9238), np.float32(0.8927), np.float32(0.9846), np.float32(0.9824), np.float32(0.9689), np.float32(0.8713), np.float32(0.7885), np.float32(0.8854), np.float32(0.9659), np.float32(0.3638), np.float32(0.2726)] +2025-11-08 10:14:55.019584: Epoch time: 546.22 s +2025-11-08 10:14:57.024070: +2025-11-08 10:14:57.029159: Epoch 983 +2025-11-08 10:14:57.031497: Current learning rate: 0.00026 +2025-11-08 10:24:02.842737: train_loss -0.5006 +2025-11-08 10:24:02.887359: val_loss -0.5033 +2025-11-08 10:24:02.894535: Pseudo dice [np.float32(0.9487), np.float32(0.8048), np.float32(0.7385), np.float32(0.6862), np.float32(0.8739), np.float32(0.8082), np.float32(0.9143), np.float32(0.8777), np.float32(0.9858), np.float32(0.9861), np.float32(0.9576), np.float32(0.8591), np.float32(0.7942), np.float32(0.8822), np.float32(0.9677), np.float32(0.2979), np.float32(0.429)] +2025-11-08 10:24:02.986344: Epoch time: 545.83 s +2025-11-08 10:24:02.993567: Yayy! New best EMA pseudo Dice: 0.8076000213623047 +2025-11-08 10:24:09.878304: +2025-11-08 10:24:09.880076: Epoch 984 +2025-11-08 10:24:09.881997: Current learning rate: 0.00024 +2025-11-08 10:33:42.249466: train_loss -0.4877 +2025-11-08 10:33:42.272796: val_loss -0.5171 +2025-11-08 10:33:42.276734: Pseudo dice [np.float32(0.9456), np.float32(0.7678), np.float32(0.7112), np.float32(0.6863), np.float32(0.8809), np.float32(0.8228), np.float32(0.9131), np.float32(0.8778), np.float32(0.9831), np.float32(0.9833), np.float32(0.9691), np.float32(0.8714), np.float32(0.7749), np.float32(0.8866), np.float32(0.9648), np.float32(0.3392), np.float32(0.2426)] +2025-11-08 10:33:42.280455: Epoch time: 572.37 s +2025-11-08 10:33:44.377441: +2025-11-08 10:33:44.379674: Epoch 985 +2025-11-08 10:33:44.386448: Current learning rate: 0.00023 +2025-11-08 10:43:06.846088: train_loss -0.4846 +2025-11-08 10:43:07.024688: val_loss -0.4637 +2025-11-08 10:43:07.026401: Pseudo dice [np.float32(0.9425), np.float32(0.7628), np.float32(0.7561), np.float32(0.6673), np.float32(0.8643), np.float32(0.8), np.float32(0.902), np.float32(0.8862), np.float32(0.9541), np.float32(0.9756), np.float32(0.9685), np.float32(0.8775), np.float32(0.8064), np.float32(0.889), np.float32(0.968), np.float32(0.522), np.float32(0.5344)] +2025-11-08 10:43:07.239735: Epoch time: 562.47 s +2025-11-08 10:43:07.241615: Yayy! New best EMA pseudo Dice: 0.8090999722480774 +2025-11-08 10:43:14.324203: +2025-11-08 10:43:14.325742: Epoch 986 +2025-11-08 10:43:14.328415: Current learning rate: 0.00021 +2025-11-08 10:52:20.683380: train_loss -0.5001 +2025-11-08 10:52:20.690839: val_loss -0.4714 +2025-11-08 10:52:20.693347: Pseudo dice [np.float32(0.9434), np.float32(0.7503), np.float32(0.7096), np.float32(0.6278), np.float32(0.863), np.float32(0.7958), np.float32(0.9063), np.float32(0.8924), np.float32(0.9796), np.float32(0.9751), np.float32(0.9565), np.float32(0.8667), np.float32(0.821), np.float32(0.8818), np.float32(0.9266), np.float32(0.3845), np.float32(0.2649)] +2025-11-08 10:52:20.695653: Epoch time: 546.37 s +2025-11-08 10:52:22.885677: +2025-11-08 10:52:22.887382: Epoch 987 +2025-11-08 10:52:22.888637: Current learning rate: 0.0002 +2025-11-08 11:01:22.517233: train_loss -0.4979 +2025-11-08 11:01:22.525520: val_loss -0.5103 +2025-11-08 11:01:22.530647: Pseudo dice [np.float32(0.9222), np.float32(0.79), np.float32(0.7515), np.float32(0.6783), np.float32(0.8667), np.float32(0.8214), np.float32(0.9111), np.float32(0.9073), np.float32(0.9866), np.float32(0.9834), np.float32(0.9703), np.float32(0.8556), np.float32(0.8244), np.float32(0.8671), np.float32(0.9649), np.float32(0.3042), np.float32(0.3282)] +2025-11-08 11:01:22.539779: Epoch time: 539.64 s +2025-11-08 11:01:25.308498: +2025-11-08 11:01:25.311102: Epoch 988 +2025-11-08 11:01:25.314114: Current learning rate: 0.00019 +2025-11-08 11:10:25.271910: train_loss -0.4798 +2025-11-08 11:10:25.524501: val_loss -0.4974 +2025-11-08 11:10:25.526256: Pseudo dice [np.float32(0.9443), np.float32(0.8236), np.float32(0.7438), np.float32(0.7392), np.float32(0.8835), np.float32(0.8374), np.float32(0.9263), np.float32(0.8939), np.float32(0.9787), np.float32(0.9786), np.float32(0.9718), np.float32(0.868), np.float32(0.8296), np.float32(0.8814), np.float32(0.972), np.float32(0.4548), np.float32(0.4209)] +2025-11-08 11:10:25.948859: Epoch time: 539.97 s +2025-11-08 11:10:25.950936: Yayy! New best EMA pseudo Dice: 0.8102999925613403 +2025-11-08 11:10:36.806365: +2025-11-08 11:10:36.808046: Epoch 989 +2025-11-08 11:10:36.809453: Current learning rate: 0.00017 +2025-11-08 11:19:38.723006: train_loss -0.4798 +2025-11-08 11:19:39.203670: val_loss -0.5094 +2025-11-08 11:19:39.205615: Pseudo dice [np.float32(0.942), np.float32(0.7916), np.float32(0.7253), np.float32(0.7388), np.float32(0.8904), np.float32(0.8126), np.float32(0.8957), np.float32(0.8907), np.float32(0.9867), np.float32(0.9846), np.float32(0.9669), np.float32(0.8725), np.float32(0.8099), np.float32(0.8861), np.float32(0.9675), np.float32(0.3139), np.float32(0.2071)] +2025-11-08 11:19:39.312048: Epoch time: 541.93 s +2025-11-08 11:19:41.684728: +2025-11-08 11:19:41.686054: Epoch 990 +2025-11-08 11:19:41.687572: Current learning rate: 0.00016 +2025-11-08 11:29:12.416399: train_loss -0.4999 +2025-11-08 11:29:12.422078: val_loss -0.4875 +2025-11-08 11:29:12.423852: Pseudo dice [np.float32(0.9372), np.float32(0.8227), np.float32(0.7974), np.float32(0.7004), np.float32(0.8463), np.float32(0.8117), np.float32(0.9162), np.float32(0.9034), np.float32(0.9853), np.float32(0.9837), np.float32(0.9749), np.float32(0.8837), np.float32(0.8055), np.float32(0.8865), np.float32(0.9757), np.float32(0.3738), np.float32(0.2895)] +2025-11-08 11:29:12.425142: Epoch time: 570.74 s +2025-11-08 11:29:12.426628: Yayy! New best EMA pseudo Dice: 0.8105000257492065 +2025-11-08 11:29:18.039571: +2025-11-08 11:29:18.074957: Epoch 991 +2025-11-08 11:29:18.076409: Current learning rate: 0.00014 +2025-11-08 11:38:31.707067: train_loss -0.4892 +2025-11-08 11:38:31.722102: val_loss -0.527 +2025-11-08 11:38:31.726941: Pseudo dice [np.float32(0.9411), np.float32(0.8156), np.float32(0.7929), np.float32(0.727), np.float32(0.869), np.float32(0.8255), np.float32(0.9019), np.float32(0.9045), np.float32(0.9834), np.float32(0.9838), np.float32(0.9693), np.float32(0.8789), np.float32(0.8266), np.float32(0.8859), np.float32(0.9666), np.float32(0.4121), np.float32(0.2613)] +2025-11-08 11:38:31.730287: Epoch time: 553.67 s +2025-11-08 11:38:31.731937: Yayy! New best EMA pseudo Dice: 0.8115000128746033 +2025-11-08 11:38:36.263994: +2025-11-08 11:38:36.269907: Epoch 992 +2025-11-08 11:38:36.273289: Current learning rate: 0.00013 +2025-11-08 11:47:43.436279: train_loss -0.5015 +2025-11-08 11:47:43.441535: val_loss -0.5222 +2025-11-08 11:47:43.443261: Pseudo dice [np.float32(0.9425), np.float32(0.8043), np.float32(0.7787), np.float32(0.6934), np.float32(0.851), np.float32(0.8227), np.float32(0.9204), np.float32(0.8987), np.float32(0.9812), np.float32(0.9783), np.float32(0.9721), np.float32(0.8847), np.float32(0.8379), np.float32(0.8744), np.float32(0.9725), np.float32(0.3947), np.float32(0.3572)] +2025-11-08 11:47:43.470741: Epoch time: 547.18 s +2025-11-08 11:47:43.480536: Yayy! New best EMA pseudo Dice: 0.8125 +2025-11-08 11:47:48.003060: +2025-11-08 11:47:48.004602: Epoch 993 +2025-11-08 11:47:48.006333: Current learning rate: 0.00011 +2025-11-08 11:56:54.094148: train_loss -0.4583 +2025-11-08 11:56:54.104601: val_loss -0.4922 +2025-11-08 11:56:54.106125: Pseudo dice [np.float32(0.9364), np.float32(0.7745), np.float32(0.7533), np.float32(0.6802), np.float32(0.8825), np.float32(0.797), np.float32(0.9266), np.float32(0.8912), np.float32(0.984), np.float32(0.9834), np.float32(0.972), np.float32(0.8736), np.float32(0.814), np.float32(0.8874), np.float32(0.9723), np.float32(0.4096), np.float32(0.3326)] +2025-11-08 11:56:54.111913: Epoch time: 546.09 s +2025-11-08 11:56:54.115221: Yayy! New best EMA pseudo Dice: 0.8127999901771545 +2025-11-08 11:56:58.639472: +2025-11-08 11:56:58.641409: Epoch 994 +2025-11-08 11:56:58.642606: Current learning rate: 0.0001 +2025-11-08 12:06:06.943951: train_loss -0.496 +2025-11-08 12:06:07.074946: val_loss -0.5033 +2025-11-08 12:06:07.076852: Pseudo dice [np.float32(0.9396), np.float32(0.8138), np.float32(0.7058), np.float32(0.6463), np.float32(0.8883), np.float32(0.7956), np.float32(0.925), np.float32(0.8967), np.float32(0.9858), np.float32(0.9832), np.float32(0.969), np.float32(0.8674), np.float32(0.7989), np.float32(0.8768), np.float32(0.9716), np.float32(0.3999), np.float32(0.217)] +2025-11-08 12:06:07.078677: Epoch time: 548.31 s +2025-11-08 12:06:09.148072: +2025-11-08 12:06:09.149296: Epoch 995 +2025-11-08 12:06:09.150594: Current learning rate: 8e-05 +2025-11-08 12:15:31.755147: train_loss -0.4616 +2025-11-08 12:15:31.763960: val_loss -0.5136 +2025-11-08 12:15:31.766279: Pseudo dice [np.float32(0.9456), np.float32(0.7982), np.float32(0.7674), np.float32(0.7288), np.float32(0.8768), np.float32(0.8174), np.float32(0.9229), np.float32(0.9025), np.float32(0.9605), np.float32(0.9632), np.float32(0.9685), np.float32(0.8686), np.float32(0.8009), np.float32(0.8709), np.float32(0.9567), np.float32(0.2549), np.float32(0.3199)] +2025-11-08 12:15:31.769452: Epoch time: 562.61 s +2025-11-08 12:15:34.168048: +2025-11-08 12:15:34.169655: Epoch 996 +2025-11-08 12:15:34.171118: Current learning rate: 7e-05 +2025-11-08 12:24:38.773903: train_loss -0.4955 +2025-11-08 12:24:38.920541: val_loss -0.523 +2025-11-08 12:24:38.922201: Pseudo dice [np.float32(0.947), np.float32(0.6705), np.float32(0.6921), np.float32(0.6568), np.float32(0.9058), np.float32(0.7885), np.float32(0.907), np.float32(0.8905), np.float32(0.9825), np.float32(0.982), np.float32(0.9688), np.float32(0.8614), np.float32(0.7898), np.float32(0.8979), np.float32(0.9673), np.float32(0.5329), np.float32(0.4951)] +2025-11-08 12:24:39.111191: Epoch time: 544.61 s +2025-11-08 12:24:42.575925: +2025-11-08 12:24:42.577706: Epoch 997 +2025-11-08 12:24:42.579410: Current learning rate: 5e-05 +2025-11-08 12:34:11.619794: train_loss -0.4953 +2025-11-08 12:34:11.626208: val_loss -0.4856 +2025-11-08 12:34:11.627837: Pseudo dice [np.float32(0.94), np.float32(0.7575), np.float32(0.6878), np.float32(0.7247), np.float32(0.8728), np.float32(0.8012), np.float32(0.8804), np.float32(0.8883), np.float32(0.9806), np.float32(0.9766), np.float32(0.965), np.float32(0.8593), np.float32(0.8008), np.float32(0.8841), np.float32(0.9549), np.float32(0.3955), np.float32(0.2845)] +2025-11-08 12:34:11.629229: Epoch time: 569.05 s +2025-11-08 12:34:13.738534: +2025-11-08 12:34:13.739847: Epoch 998 +2025-11-08 12:34:13.741169: Current learning rate: 4e-05 +2025-11-08 12:43:28.521910: train_loss -0.4895 +2025-11-08 12:43:28.530662: val_loss -0.4929 +2025-11-08 12:43:28.532674: Pseudo dice [np.float32(0.9399), np.float32(0.7677), np.float32(0.7202), np.float32(0.6746), np.float32(0.8726), np.float32(0.7824), np.float32(0.8971), np.float32(0.8804), np.float32(0.9807), np.float32(0.9807), np.float32(0.9711), np.float32(0.8471), np.float32(0.7984), np.float32(0.8903), np.float32(0.9666), np.float32(0.3852), np.float32(0.3054)] +2025-11-08 12:43:28.534761: Epoch time: 554.79 s +2025-11-08 12:43:31.184829: +2025-11-08 12:43:31.186226: Epoch 999 +2025-11-08 12:43:31.188689: Current learning rate: 2e-05 +2025-11-08 12:52:31.824957: train_loss -0.5056 +2025-11-08 12:52:31.830210: val_loss -0.4908 +2025-11-08 12:52:31.831506: Pseudo dice [np.float32(0.9204), np.float32(0.8167), np.float32(0.7369), np.float32(0.6614), np.float32(0.883), np.float32(0.8062), np.float32(0.9084), np.float32(0.8665), np.float32(0.9806), np.float32(0.984), np.float32(0.9678), np.float32(0.8557), np.float32(0.8286), np.float32(0.9046), np.float32(0.9659), np.float32(0.4026), np.float32(0.336)] +2025-11-08 12:52:31.832619: Epoch time: 540.65 s +2025-11-08 12:53:10.988823: Training done. +2025-11-08 12:53:13.312010: predicting BDMAP_A0000001 +2025-11-08 12:53:13.801241: BDMAP_A0000001, shape torch.Size([1, 554, 541, 554]), rank 0 +2025-11-08 13:01:59.716942: predicting BDMAP_A0000002 +2025-11-08 13:01:59.816253: BDMAP_A0000002, shape torch.Size([1, 523, 523, 523]), rank 0 +2025-11-08 13:04:19.818384: predicting BDMAP_A0000004 +2025-11-08 13:04:19.891764: BDMAP_A0000004, shape torch.Size([1, 567, 547, 567]), rank 0 +2025-11-08 13:11:59.686151: predicting BDMAP_A0000005 +2025-11-08 13:11:59.786864: BDMAP_A0000005, shape torch.Size([1, 453, 437, 453]), rank 0 +2025-11-08 13:13:10.799767: predicting BDMAP_A0000006 +2025-11-08 13:13:10.852943: BDMAP_A0000006, shape torch.Size([1, 686, 582, 686]), rank 0 +2025-11-08 13:26:08.746612: predicting BDMAP_A0000007 +2025-11-08 13:26:08.861789: BDMAP_A0000007, shape torch.Size([1, 630, 595, 630]), rank 0 +2025-11-08 13:35:52.583112: predicting BDMAP_A0000008 +2025-11-08 13:35:52.694437: BDMAP_A0000008, shape torch.Size([1, 499, 472, 499]), rank 0 +2025-11-08 13:38:11.949536: predicting BDMAP_A0000010 +2025-11-08 13:38:12.020418: BDMAP_A0000010, shape torch.Size([1, 494, 879, 494]), rank 0 +2025-11-08 13:47:55.276464: predicting BDMAP_A0000011 +2025-11-08 13:47:55.375202: BDMAP_A0000011, shape torch.Size([1, 501, 522, 501]), rank 0 +2025-11-08 13:50:15.177805: predicting BDMAP_A0000012 +2025-11-08 13:50:15.256416: BDMAP_A0000012, shape torch.Size([1, 540, 606, 540]), rank 0 +2025-11-08 13:57:14.393426: predicting BDMAP_A0000013 +2025-11-08 13:57:14.465927: BDMAP_A0000013, shape torch.Size([1, 537, 620, 537]), rank 0 +2025-11-08 14:04:13.572699: predicting BDMAP_A0000019 +2025-11-08 14:04:13.649830: BDMAP_A0000019, shape torch.Size([1, 433, 549, 433]), rank 0 +2025-11-08 14:05:47.301605: predicting BDMAP_A0000021 +2025-11-08 14:05:47.368326: BDMAP_A0000021, shape torch.Size([1, 495, 817, 495]), rank 0 +2025-11-08 14:15:25.930189: predicting BDMAP_A0000022 +2025-11-08 14:15:26.013736: BDMAP_A0000022, shape torch.Size([1, 523, 504, 523]), rank 0 +2025-11-08 14:17:45.945407: predicting BDMAP_A0000023 +2025-11-08 14:17:46.013399: BDMAP_A0000023, shape torch.Size([1, 428, 470, 428]), rank 0 +2025-11-08 14:19:19.912203: predicting BDMAP_A0000024 +2025-11-08 14:19:19.975403: BDMAP_A0000024, shape torch.Size([1, 523, 565, 523]), rank 0 +2025-11-08 14:22:14.823867: predicting BDMAP_A0000026 +2025-11-08 14:22:14.889691: BDMAP_A0000026, shape torch.Size([1, 475, 490, 475]), rank 0 +2025-11-08 14:23:48.952972: predicting BDMAP_A0000027 +2025-11-08 14:23:49.013623: BDMAP_A0000027, shape torch.Size([1, 571, 772, 571]), rank 0 +2025-11-08 14:33:35.680039: predicting BDMAP_A0000030 +2025-11-08 14:33:35.775750: BDMAP_A0000030, shape torch.Size([1, 468, 579, 468]), rank 0 +2025-11-08 14:35:32.738310: predicting BDMAP_A0000031 +2025-11-08 14:35:32.811620: BDMAP_A0000031, shape torch.Size([1, 535, 561, 535]), rank 0 +2025-11-08 14:38:27.684617: predicting BDMAP_A0000033 +2025-11-08 14:38:27.744866: BDMAP_A0000033, shape torch.Size([1, 570, 485, 570]), rank 0 +2025-11-08 14:41:11.362429: predicting BDMAP_A0000034 +2025-11-08 14:41:11.440443: BDMAP_A0000034, shape torch.Size([1, 594, 371, 594]), rank 0 +2025-11-08 14:43:38.470870: predicting BDMAP_A0000035 +2025-11-08 14:43:38.539157: BDMAP_A0000035, shape torch.Size([1, 630, 697, 630]), rank 0 +2025-11-08 14:55:19.564397: predicting BDMAP_A0000036 +2025-11-08 14:55:19.666622: BDMAP_A0000036, shape torch.Size([1, 456, 409, 456]), rank 0 +2025-11-08 14:56:30.747160: predicting BDMAP_A0000037 +2025-11-08 14:56:30.812649: BDMAP_A0000037, shape torch.Size([1, 547, 553, 547]), rank 0 +2025-11-08 15:02:09.320491: predicting BDMAP_A0000038 +2025-11-08 15:02:09.385003: BDMAP_A0000038, shape torch.Size([1, 703, 557, 703]), rank 0 +2025-11-08 15:12:36.772745: predicting BDMAP_A0000040 +2025-11-08 15:12:36.867097: BDMAP_A0000040, shape torch.Size([1, 499, 589, 499]), rank 0 +2025-11-08 15:15:30.498212: predicting BDMAP_A0000042 +2025-11-08 15:15:30.576312: BDMAP_A0000042, shape torch.Size([1, 542, 416, 542]), rank 0 +2025-11-08 15:17:16.425999: predicting BDMAP_A0000043 +2025-11-08 15:17:16.493633: BDMAP_A0000043, shape torch.Size([1, 450, 481, 450]), rank 0 +2025-11-08 15:18:49.996846: predicting BDMAP_A0000044 +2025-11-08 15:18:50.049271: BDMAP_A0000044, shape torch.Size([1, 591, 498, 591]), rank 0 +2025-11-08 15:26:36.552691: predicting BDMAP_A0000045 +2025-11-08 15:26:36.638632: BDMAP_A0000045, shape torch.Size([1, 504, 453, 504]), rank 0 +2025-11-08 15:28:55.433022: predicting BDMAP_A0000046 +2025-11-08 15:28:55.510195: BDMAP_A0000046, shape torch.Size([1, 509, 436, 509]), rank 0 +2025-11-08 15:30:40.792563: predicting BDMAP_A0000047 +2025-11-08 15:30:40.851291: BDMAP_A0000047, shape torch.Size([1, 571, 581, 571]), rank 0 +2025-11-08 15:38:45.903800: predicting BDMAP_A0000048 +2025-11-08 15:38:45.993468: BDMAP_A0000048, shape torch.Size([1, 440, 485, 440]), rank 0 +2025-11-08 15:40:19.210366: predicting BDMAP_A0000049 +2025-11-08 15:40:19.278948: BDMAP_A0000049, shape torch.Size([1, 585, 545, 585]), rank 0 +2025-11-08 15:48:05.172179: predicting BDMAP_A0000050 +2025-11-08 15:48:05.245069: BDMAP_A0000050, shape torch.Size([1, 563, 553, 563]), rank 0 +2025-11-08 15:54:35.420882: predicting BDMAP_A0000051 +2025-11-08 15:54:35.510445: BDMAP_A0000051, shape torch.Size([1, 667, 621, 667]), rank 0 +2025-11-08 16:05:30.818672: predicting BDMAP_A0000053 +2025-11-08 16:05:30.942354: BDMAP_A0000053, shape torch.Size([1, 487, 470, 487]), rank 0 +2025-11-08 16:07:49.559549: predicting BDMAP_A0000054 +2025-11-08 16:07:49.630708: BDMAP_A0000054, shape torch.Size([1, 477, 855, 477]), rank 0 +2025-11-08 16:14:16.012795: predicting BDMAP_A0000058 +2025-11-08 16:14:16.078790: BDMAP_A0000058, shape torch.Size([1, 408, 423, 408]), rank 0 +2025-11-08 16:15:26.202051: predicting BDMAP_A0000060 +2025-11-08 16:15:26.256818: BDMAP_A0000060, shape torch.Size([1, 467, 443, 467]), rank 0 +2025-11-08 16:16:37.070134: predicting BDMAP_A0000061 +2025-11-08 16:16:37.138852: BDMAP_A0000061, shape torch.Size([1, 620, 542, 620]), rank 0 +2025-11-08 16:24:18.970017: predicting BDMAP_A0000064 +2025-11-08 16:24:19.057738: BDMAP_A0000064, shape torch.Size([1, 459, 602, 459]), rank 0 +2025-11-08 16:26:15.855805: predicting BDMAP_A0000065 +2025-11-08 16:26:15.933087: BDMAP_A0000065, shape torch.Size([1, 485, 453, 485]), rank 0 +2025-11-08 16:28:34.372556: predicting BDMAP_A0000067 +2025-11-08 16:28:34.433855: BDMAP_A0000067, shape torch.Size([1, 473, 453, 473]), rank 0 +2025-11-08 16:30:08.031586: predicting BDMAP_A0000068 +2025-11-08 16:30:08.103107: BDMAP_A0000068, shape torch.Size([1, 513, 491, 513]), rank 0 +2025-11-08 16:32:27.469155: predicting BDMAP_A0000069 +2025-11-08 16:32:27.530500: BDMAP_A0000069, shape torch.Size([1, 518, 581, 518]), rank 0 +2025-11-08 16:35:21.920749: predicting BDMAP_A0000070 +2025-11-08 16:35:22.004514: BDMAP_A0000070, shape torch.Size([1, 556, 553, 556]), rank 0 +2025-11-08 16:40:55.869448: predicting BDMAP_A0000071 +2025-11-08 16:40:55.935380: BDMAP_A0000071, shape torch.Size([1, 422, 535, 422]), rank 0 +2025-11-08 16:42:29.195049: predicting BDMAP_A0000072 +2025-11-08 16:42:29.267543: BDMAP_A0000072, shape torch.Size([1, 606, 885, 606]), rank 0 +2025-11-08 16:55:47.631318: predicting BDMAP_A0000077 +2025-11-08 16:55:47.753659: BDMAP_A0000077, shape torch.Size([1, 556, 581, 556]), rank 0 +2025-11-08 17:02:42.691442: predicting BDMAP_A0000079 +2025-11-08 17:02:42.764487: BDMAP_A0000079, shape torch.Size([1, 526, 581, 526]), rank 0 +2025-11-08 17:05:36.877849: predicting BDMAP_A0000080 +2025-11-08 17:05:36.948879: BDMAP_A0000080, shape torch.Size([1, 440, 521, 440]), rank 0 +2025-11-08 17:07:10.520596: predicting BDMAP_A0000082 +2025-11-08 17:07:10.582197: BDMAP_A0000082, shape torch.Size([1, 612, 853, 612]), rank 0 +2025-11-08 17:20:25.974792: predicting BDMAP_A0000083 +2025-11-08 17:20:26.086602: BDMAP_A0000083, shape torch.Size([1, 512, 536, 512]), rank 0 +2025-11-08 17:22:45.589205: predicting BDMAP_A0000084 +2025-11-08 17:22:45.661956: BDMAP_A0000084, shape torch.Size([1, 556, 557, 556]), rank 0 +2025-11-08 17:28:22.746620: predicting BDMAP_A0000085 +2025-11-08 17:28:22.818611: BDMAP_A0000085, shape torch.Size([1, 588, 882, 588]), rank 0 +2025-11-08 17:41:34.821273: predicting BDMAP_A0000090 +2025-11-08 17:41:34.912361: BDMAP_A0000090, shape torch.Size([1, 477, 462, 477]), rank 0 +2025-11-08 17:43:08.483380: predicting BDMAP_A0000091 +2025-11-08 17:43:08.542279: BDMAP_A0000091, shape torch.Size([1, 484, 601, 484]), rank 0 +2025-11-08 17:46:02.087162: predicting BDMAP_A0000094 +2025-11-08 17:46:02.163478: BDMAP_A0000094, shape torch.Size([1, 450, 431, 450]), rank 0 +2025-11-08 17:47:13.049948: predicting BDMAP_A0000095 +2025-11-08 17:47:13.130525: BDMAP_A0000095, shape torch.Size([1, 696, 585, 696]), rank 0 +2025-11-08 17:59:54.766795: predicting BDMAP_A0000096 +2025-11-08 17:59:54.878532: BDMAP_A0000096, shape torch.Size([1, 456, 525, 456]), rank 0 +2025-11-08 18:01:28.986809: predicting BDMAP_A0000097 +2025-11-08 18:01:29.065399: BDMAP_A0000097, shape torch.Size([1, 623, 542, 623]), rank 0 +2025-11-08 18:09:11.365461: predicting BDMAP_A0000098 +2025-11-08 18:09:11.455658: BDMAP_A0000098, shape torch.Size([1, 523, 549, 523]), rank 0 +2025-11-08 18:11:31.293771: predicting BDMAP_A0000101 +2025-11-08 18:11:31.367186: BDMAP_A0000101, shape torch.Size([1, 453, 493, 453]), rank 0 +2025-11-08 18:13:04.785122: predicting BDMAP_A0000102 +2025-11-08 18:13:04.848858: BDMAP_A0000102, shape torch.Size([1, 582, 598, 582]), rank 0 +2025-11-08 18:22:30.421807: predicting BDMAP_A0000107 +2025-11-08 18:22:30.504554: BDMAP_A0000107, shape torch.Size([1, 422, 505, 422]), rank 0 +2025-11-08 18:24:03.586657: predicting BDMAP_A0000108 +2025-11-08 18:24:03.654556: BDMAP_A0000108, shape torch.Size([1, 498, 437, 498]), rank 0 +2025-11-08 18:25:48.725924: predicting BDMAP_A0000109 +2025-11-08 18:25:48.791851: BDMAP_A0000109, shape torch.Size([1, 580, 630, 580]), rank 0 +2025-11-08 18:35:16.294641: predicting BDMAP_A0000110 +2025-11-08 18:35:16.341319: BDMAP_A0000110, shape torch.Size([1, 421, 450, 421]), rank 0 +2025-11-08 18:36:49.029672: predicting BDMAP_A0000112 +2025-11-08 18:36:49.096211: BDMAP_A0000112, shape torch.Size([1, 563, 524, 563]), rank 0 +2025-11-08 18:43:11.616140: predicting BDMAP_A0000113 +2025-11-08 18:43:11.709027: BDMAP_A0000113, shape torch.Size([1, 574, 497, 574]), rank 0 +2025-11-08 18:49:34.220460: predicting BDMAP_A0000114 +2025-11-08 18:49:34.317849: BDMAP_A0000114, shape torch.Size([1, 460, 464, 460]), rank 0 +2025-11-08 18:51:07.603176: predicting BDMAP_A0000116 +2025-11-08 18:51:07.678361: BDMAP_A0000116, shape torch.Size([1, 504, 577, 504]), rank 0 +2025-11-08 18:54:01.943435: predicting BDMAP_A0000117 +2025-11-08 18:54:02.029085: BDMAP_A0000117, shape torch.Size([1, 492, 505, 492]), rank 0 +2025-11-08 18:56:21.101349: predicting BDMAP_A0000118 +2025-11-08 18:56:21.163738: BDMAP_A0000118, shape torch.Size([1, 588, 462, 588]), rank 0 +2025-11-08 18:59:36.087685: predicting BDMAP_A0000119 +2025-11-08 18:59:36.153563: BDMAP_A0000119, shape torch.Size([1, 644, 570, 644]), rank 0 +2025-11-08 19:10:22.842225: predicting BDMAP_A0000120 +2025-11-08 19:10:22.923800: BDMAP_A0000120, shape torch.Size([1, 491, 586, 491]), rank 0 +2025-11-08 19:13:16.707731: predicting BDMAP_A0000122 +2025-11-08 19:13:16.796364: BDMAP_A0000122, shape torch.Size([1, 526, 557, 526]), rank 0 +2025-11-08 19:15:37.497863: predicting BDMAP_A0000123 +2025-11-08 19:15:37.569605: BDMAP_A0000123, shape torch.Size([1, 617, 525, 617]), rank 0 +2025-11-08 19:23:17.319377: predicting BDMAP_A0000125 +2025-11-08 19:23:17.408379: BDMAP_A0000125, shape torch.Size([1, 474, 485, 474]), rank 0 +2025-11-08 19:24:51.180335: predicting BDMAP_A0000126 +2025-11-08 19:24:51.252806: BDMAP_A0000126, shape torch.Size([1, 529, 565, 529]), rank 0 +2025-11-08 19:27:45.702076: predicting BDMAP_A0000127 +2025-11-08 19:27:45.779978: BDMAP_A0000127, shape torch.Size([1, 450, 429, 450]), rank 0 +2025-11-08 19:28:56.560806: predicting BDMAP_A0000128 +2025-11-08 19:28:56.614717: BDMAP_A0000128, shape torch.Size([1, 495, 553, 495]), rank 0 +2025-11-08 19:31:16.726716: predicting BDMAP_A0000129 +2025-11-08 19:31:16.809010: BDMAP_A0000129, shape torch.Size([1, 492, 450, 492]), rank 0 +2025-11-08 19:33:35.504177: predicting BDMAP_A0000130 +2025-11-08 19:33:35.570335: BDMAP_A0000130, shape torch.Size([1, 661, 561, 661]), rank 0 +2025-11-08 19:44:23.004360: predicting BDMAP_A0000132 +2025-11-08 19:44:23.094349: BDMAP_A0000132, shape torch.Size([1, 543, 472, 543]), rank 0 +2025-11-08 19:46:42.682082: predicting BDMAP_A0000133 +2025-11-08 19:46:42.758504: BDMAP_A0000133, shape torch.Size([1, 551, 805, 551]), rank 0 +2025-11-08 19:56:16.400757: predicting BDMAP_A0000134 +2025-11-08 19:56:16.458245: BDMAP_A0000134, shape torch.Size([1, 440, 525, 440]), rank 0 +2025-11-08 19:57:50.003485: predicting BDMAP_A0000135 +2025-11-08 19:57:50.071120: BDMAP_A0000135, shape torch.Size([1, 575, 572, 575]), rank 0 +2025-11-08 20:05:45.724508: predicting BDMAP_A0000136 +2025-11-08 20:05:45.809810: BDMAP_A0000136, shape torch.Size([1, 588, 959, 588]), rank 0 +2025-11-08 20:20:56.186704: predicting BDMAP_A0000137 +2025-11-08 20:20:56.337424: BDMAP_A0000137, shape torch.Size([1, 540, 559, 540]), rank 0 +2025-11-08 20:26:30.774278: predicting BDMAP_A0000138 +2025-11-08 20:26:30.861883: BDMAP_A0000138, shape torch.Size([1, 543, 481, 543]), rank 0 +2025-11-08 20:28:50.727623: predicting BDMAP_A0000139 +2025-11-08 20:28:50.796276: BDMAP_A0000139, shape torch.Size([1, 658, 552, 658]), rank 0 +2025-11-08 20:37:37.827871: predicting BDMAP_A0000143 +2025-11-08 20:37:37.927117: BDMAP_A0000143, shape torch.Size([1, 494, 510, 494]), rank 0 +2025-11-08 20:39:57.103570: predicting BDMAP_A0000147 +2025-11-08 20:39:57.177119: BDMAP_A0000147, shape torch.Size([1, 518, 449, 518]), rank 0 +2025-11-08 20:42:16.198098: predicting BDMAP_A0000148 +2025-11-08 20:42:16.271544: BDMAP_A0000148, shape torch.Size([1, 520, 663, 520]), rank 0 +2025-11-08 20:49:05.836640: predicting BDMAP_A0000149 +2025-11-08 20:49:05.925202: BDMAP_A0000149, shape torch.Size([1, 598, 609, 598]), rank 0 +2025-11-08 20:58:36.577146: predicting BDMAP_A0000152 +2025-11-08 20:58:36.676874: BDMAP_A0000152, shape torch.Size([1, 542, 432, 542]), rank 0 +2025-11-08 21:00:22.449874: predicting BDMAP_A0000153 +2025-11-08 21:00:22.523949: BDMAP_A0000153, shape torch.Size([1, 572, 534, 572]), rank 0 +2025-11-08 21:06:47.270608: predicting BDMAP_A0000154 +2025-11-08 21:06:47.343239: BDMAP_A0000154, shape torch.Size([1, 482, 523, 482]), rank 0 +2025-11-08 21:09:06.407143: predicting BDMAP_A0000155 +2025-11-08 21:09:06.477161: BDMAP_A0000155, shape torch.Size([1, 473, 521, 473]), rank 0 +2025-11-08 21:10:40.838760: predicting BDMAP_A0000157 +2025-11-08 21:10:40.949789: BDMAP_A0000157, shape torch.Size([1, 429, 461, 429]), rank 0 +2025-11-08 21:12:13.997066: predicting BDMAP_A0000158 +2025-11-08 21:12:14.063509: BDMAP_A0000158, shape torch.Size([1, 467, 453, 467]), rank 0 +2025-11-08 21:13:47.619908: predicting BDMAP_A0000160 +2025-11-08 21:13:47.685159: BDMAP_A0000160, shape torch.Size([1, 442, 431, 442]), rank 0 +2025-11-08 21:14:58.271580: predicting BDMAP_A0000162 +2025-11-08 21:14:58.335235: BDMAP_A0000162, shape torch.Size([1, 444, 521, 444]), rank 0 +2025-11-08 21:16:32.220066: predicting BDMAP_A0000163 +2025-11-08 21:16:32.293313: BDMAP_A0000163, shape torch.Size([1, 482, 521, 482]), rank 0 +2025-11-08 21:18:51.377123: predicting BDMAP_A0000164 +2025-11-08 21:18:51.449609: BDMAP_A0000164, shape torch.Size([1, 592, 498, 592]), rank 0 +2025-11-08 21:26:29.105550: predicting BDMAP_A0000167 +2025-11-08 21:26:29.199486: BDMAP_A0000167, shape torch.Size([1, 478, 490, 478]), rank 0 +2025-11-08 21:28:03.447053: predicting BDMAP_A0000168 +2025-11-08 21:28:03.521680: BDMAP_A0000168, shape torch.Size([1, 371, 461, 371]), rank 0 +2025-11-08 21:28:59.869087: predicting BDMAP_A0000169 +2025-11-08 21:29:00.015502: BDMAP_A0000169, shape torch.Size([1, 567, 639, 567]), rank 0 +2025-11-08 21:37:02.187904: predicting BDMAP_A0000170 +2025-11-08 21:37:02.320114: BDMAP_A0000170, shape torch.Size([1, 580, 514, 580]), rank 0 +2025-11-08 21:44:39.574855: predicting BDMAP_A0000171 +2025-11-08 21:44:39.663191: BDMAP_A0000171, shape torch.Size([1, 481, 547, 481]), rank 0 +2025-11-08 21:46:59.333043: predicting BDMAP_A0000173 +2025-11-08 21:46:59.477629: BDMAP_A0000173, shape torch.Size([1, 498, 883, 498]), rank 0 +2025-11-08 21:56:35.374718: predicting BDMAP_A0000174 +2025-11-08 21:56:35.482048: BDMAP_A0000174, shape torch.Size([1, 529, 471, 529]), rank 0 +2025-11-08 21:58:55.993953: predicting BDMAP_A0000175 +2025-11-08 21:58:56.083685: BDMAP_A0000175, shape torch.Size([1, 540, 491, 540]), rank 0 +2025-11-08 22:01:18.052227: predicting BDMAP_A0000176 +2025-11-08 22:01:18.143548: BDMAP_A0000176, shape torch.Size([1, 450, 429, 450]), rank 0 +2025-11-08 22:02:29.203868: predicting BDMAP_A0000178 +2025-11-08 22:02:29.266030: BDMAP_A0000178, shape torch.Size([1, 703, 1026, 703]), rank 0 +2025-11-08 22:16:21.564092: predicting BDMAP_A0000180 +2025-11-08 22:16:21.715344: BDMAP_A0000180, shape torch.Size([1, 489, 449, 489]), rank 0 +2025-11-08 22:18:42.916126: predicting BDMAP_A0000184 +2025-11-08 22:18:43.003035: BDMAP_A0000184, shape torch.Size([1, 487, 553, 487]), rank 0 +2025-11-08 22:21:06.281270: predicting BDMAP_A0000185 +2025-11-08 22:21:06.355864: BDMAP_A0000185, shape torch.Size([1, 447, 542, 447]), rank 0 +2025-11-08 22:22:46.819198: predicting BDMAP_A0000186 +2025-11-08 22:22:47.048217: BDMAP_A0000186, shape torch.Size([1, 394, 481, 394]), rank 0 +2025-11-08 22:24:04.901797: predicting BDMAP_A0000188 +2025-11-08 22:24:04.978824: BDMAP_A0000188, shape torch.Size([1, 487, 705, 487]), rank 0 +2025-11-08 22:32:25.488096: predicting BDMAP_A0000189 +2025-11-08 22:32:25.659167: BDMAP_A0000189, shape torch.Size([1, 560, 585, 560]), rank 0 +2025-11-08 22:39:22.154517: predicting BDMAP_A0000191 +2025-11-08 22:39:22.243295: BDMAP_A0000191, shape torch.Size([1, 696, 605, 696]), rank 0 +2025-11-08 22:52:04.199517: predicting BDMAP_A0000192 +2025-11-08 22:52:04.315712: BDMAP_A0000192, shape torch.Size([1, 492, 523, 492]), rank 0 +2025-11-08 22:54:23.801475: predicting BDMAP_A0000193 +2025-11-08 22:54:23.876617: BDMAP_A0000193, shape torch.Size([1, 505, 425, 505]), rank 0 +2025-11-08 22:56:09.378862: predicting BDMAP_A0000195 +2025-11-08 22:56:09.457982: BDMAP_A0000195, shape torch.Size([1, 495, 410, 495]), rank 0 +2025-11-08 22:57:54.701771: predicting BDMAP_A0000196 +2025-11-08 22:57:54.776139: BDMAP_A0000196, shape torch.Size([1, 509, 901, 509]), rank 0 +2025-11-08 23:08:39.722598: predicting BDMAP_A0000197 +2025-11-08 23:08:39.820977: BDMAP_A0000197, shape torch.Size([1, 499, 472, 499]), rank 0 +2025-11-08 23:10:58.860152: predicting BDMAP_A0000198 +2025-11-08 23:10:58.931479: BDMAP_A0000198, shape torch.Size([1, 453, 441, 453]), rank 0 +2025-11-08 23:12:09.775543: predicting BDMAP_A0000199 +2025-11-08 23:12:09.838073: BDMAP_A0000199, shape torch.Size([1, 422, 561, 422]), rank 0 +2025-11-08 23:14:06.365745: predicting BDMAP_A0000201 +2025-11-08 23:14:06.439452: BDMAP_A0000201, shape torch.Size([1, 571, 592, 571]), rank 0 +2025-11-08 23:22:03.937374: predicting BDMAP_A0000202 +2025-11-08 23:22:04.025444: BDMAP_A0000202, shape torch.Size([1, 513, 584, 513]), rank 0 +2025-11-08 23:24:57.981841: predicting BDMAP_A0000203 +2025-11-08 23:24:58.068788: BDMAP_A0000203, shape torch.Size([1, 468, 589, 468]), rank 0 +2025-11-08 23:26:55.319711: predicting BDMAP_A0000206 +2025-11-08 23:26:55.395335: BDMAP_A0000206, shape torch.Size([1, 519, 565, 519]), rank 0 +2025-11-08 23:29:49.822316: predicting BDMAP_A0000208 +2025-11-08 23:29:49.896708: BDMAP_A0000208, shape torch.Size([1, 526, 502, 526]), rank 0 +2025-11-08 23:32:10.121412: predicting BDMAP_A0000209 +2025-11-08 23:32:10.197836: BDMAP_A0000209, shape torch.Size([1, 480, 554, 480]), rank 0 +2025-11-08 23:33:45.085005: predicting BDMAP_A0000210 +2025-11-08 23:33:45.152419: BDMAP_A0000210, shape torch.Size([1, 385, 765, 385]), rank 0 +2025-11-08 23:35:37.604418: predicting BDMAP_A0000211 +2025-11-08 23:35:37.681158: BDMAP_A0000211, shape torch.Size([1, 563, 481, 563]), rank 0 +2025-11-08 23:38:20.827991: predicting BDMAP_A0000212 +2025-11-08 23:38:20.899234: BDMAP_A0000212, shape torch.Size([1, 549, 649, 549]), rank 0 +2025-11-08 23:45:16.006096: predicting BDMAP_A0000213 +2025-11-08 23:45:16.097527: BDMAP_A0000213, shape torch.Size([1, 501, 476, 501]), rank 0 +2025-11-08 23:47:35.294259: predicting BDMAP_A0000215 +2025-11-08 23:47:35.365288: BDMAP_A0000215, shape torch.Size([1, 488, 518, 488]), rank 0 +2025-11-08 23:49:54.875616: predicting BDMAP_A0000216 +2025-11-08 23:49:54.947193: BDMAP_A0000216, shape torch.Size([1, 639, 942, 639]), rank 0 +2025-11-09 00:05:12.406223: predicting BDMAP_A0000218 +2025-11-09 00:05:12.548611: BDMAP_A0000218, shape torch.Size([1, 470, 500, 470]), rank 0 +2025-11-09 00:06:46.941158: predicting BDMAP_A0000219 +2025-11-09 00:06:47.024467: BDMAP_A0000219, shape torch.Size([1, 454, 411, 454]), rank 0 +2025-11-09 00:07:57.688158: predicting BDMAP_A0000316 +2025-11-09 00:07:57.756708: BDMAP_A0000316, shape torch.Size([1, 543, 569, 543]), rank 0 +2025-11-09 00:14:48.636280: predicting BDMAP_A0000317 +2025-11-09 00:14:48.721818: BDMAP_A0000317, shape torch.Size([1, 563, 608, 563]), rank 0 +2025-11-09 00:22:43.712456: predicting BDMAP_A0000319 +2025-11-09 00:22:43.800936: BDMAP_A0000319, shape torch.Size([1, 520, 490, 520]), rank 0 +2025-11-09 00:25:03.609705: predicting BDMAP_A0000320 +2025-11-09 00:25:03.693996: BDMAP_A0000320, shape torch.Size([1, 471, 406, 471]), rank 0 +2025-11-09 00:26:14.963536: predicting BDMAP_A0000321 +2025-11-09 00:26:15.034858: BDMAP_A0000321, shape torch.Size([1, 610, 465, 610]), rank 0 +2025-11-09 00:34:04.140120: predicting BDMAP_A0000323 +2025-11-09 00:34:04.239838: BDMAP_A0000323, shape torch.Size([1, 661, 546, 661]), rank 0 +2025-11-09 00:43:04.079180: predicting BDMAP_A0000324 +2025-11-09 00:43:04.176436: BDMAP_A0000324, shape torch.Size([1, 489, 492, 489]), rank 0 +2025-11-09 00:45:23.335672: predicting BDMAP_A0000325 +2025-11-09 00:45:23.410311: BDMAP_A0000325, shape torch.Size([1, 480, 485, 480]), rank 0 +2025-11-09 00:46:57.846777: predicting BDMAP_A0000326 +2025-11-09 00:46:57.927586: BDMAP_A0000326, shape torch.Size([1, 397, 559, 397]), rank 0 +2025-11-09 00:48:13.628542: predicting BDMAP_A0000329 +2025-11-09 00:48:13.706986: BDMAP_A0000329, shape torch.Size([1, 459, 577, 459]), rank 0 +2025-11-09 00:50:11.025641: predicting BDMAP_A0000330 +2025-11-09 00:50:11.105325: BDMAP_A0000330, shape torch.Size([1, 585, 533, 585]), rank 0 +2025-11-09 00:58:03.146767: predicting BDMAP_A0000331 +2025-11-09 00:58:09.747562: BDMAP_A0000331, shape torch.Size([1, 574, 528, 574]), rank 0 +2025-11-09 01:05:26.371431: predicting BDMAP_A0000332 +2025-11-09 01:05:26.472475: BDMAP_A0000332, shape torch.Size([1, 509, 874, 509]), rank 0 +2025-11-09 01:15:12.843129: predicting BDMAP_A0000336 +2025-11-09 01:15:12.950229: BDMAP_A0000336, shape torch.Size([1, 563, 946, 563]), rank 0 +2025-11-09 01:28:19.490925: predicting BDMAP_A0000337 +2025-11-09 01:28:19.604037: BDMAP_A0000337, shape torch.Size([1, 523, 461, 523]), rank 0 +2025-11-09 01:30:39.011624: predicting BDMAP_A0000340 +2025-11-09 01:30:39.090057: BDMAP_A0000340, shape torch.Size([1, 589, 903, 589]), rank 0 +2025-11-09 01:46:07.749290: predicting BDMAP_A0000341 +2025-11-09 01:46:07.862964: BDMAP_A0000341, shape torch.Size([1, 570, 879, 570]), rank 0 +2025-11-09 01:57:37.517436: predicting BDMAP_A0000343 +2025-11-09 01:57:37.627277: BDMAP_A0000343, shape torch.Size([1, 616, 493, 616]), rank 0 +2025-11-09 02:05:26.591105: predicting BDMAP_A0000344 +2025-11-09 02:05:26.678394: BDMAP_A0000344, shape torch.Size([1, 506, 437, 506]), rank 0 +2025-11-09 02:07:12.314508: predicting BDMAP_A0000345 +2025-11-09 02:07:12.403647: BDMAP_A0000345, shape torch.Size([1, 565, 601, 565]), rank 0 +2025-11-09 02:15:21.402467: predicting BDMAP_A0000346 +2025-11-09 02:15:21.478272: BDMAP_A0000346, shape torch.Size([1, 622, 554, 622]), rank 0 +2025-11-09 02:23:16.530071: predicting BDMAP_A0000349 +2025-11-09 02:23:16.620713: BDMAP_A0000349, shape torch.Size([1, 489, 486, 489]), rank 0 +2025-11-09 02:25:35.588651: predicting BDMAP_A0000350 +2025-11-09 02:25:35.663583: BDMAP_A0000350, shape torch.Size([1, 543, 569, 543]), rank 0 +2025-11-09 02:32:37.347293: predicting BDMAP_A0000351 +2025-11-09 02:32:37.425139: BDMAP_A0000351, shape torch.Size([1, 484, 873, 484]), rank 0 +2025-11-09 02:42:23.720856: predicting BDMAP_A0000353 +2025-11-09 02:42:23.802441: BDMAP_A0000353, shape torch.Size([1, 387, 499, 387]), rank 0 +2025-11-09 02:43:38.583815: predicting BDMAP_A0000354 +2025-11-09 02:43:38.644860: BDMAP_A0000354, shape torch.Size([1, 515, 565, 515]), rank 0 +2025-11-09 02:46:32.816336: predicting BDMAP_A0000356 +2025-11-09 02:46:32.890579: BDMAP_A0000356, shape torch.Size([1, 487, 533, 487]), rank 0 +2025-11-09 02:48:52.876513: predicting BDMAP_A0000357 +2025-11-09 02:48:52.969069: BDMAP_A0000357, shape torch.Size([1, 484, 473, 484]), rank 0 +2025-11-09 02:51:11.964519: predicting BDMAP_A0000360 +2025-11-09 02:51:12.034935: BDMAP_A0000360, shape torch.Size([1, 606, 562, 606]), rank 0 +2025-11-09 03:00:55.400309: predicting BDMAP_A0000361 +2025-11-09 03:00:55.520262: BDMAP_A0000361, shape torch.Size([1, 506, 493, 506]), rank 0 +2025-11-09 03:03:14.836850: predicting BDMAP_A0000362 +2025-11-09 03:03:14.904501: BDMAP_A0000362, shape torch.Size([1, 543, 474, 543]), rank 0 +2025-11-09 03:05:34.864108: predicting BDMAP_A0000366 +2025-11-09 03:05:34.947989: BDMAP_A0000366, shape torch.Size([1, 560, 644, 560]), rank 0 +2025-11-09 03:12:40.000206: predicting BDMAP_A0000368 +2025-11-09 03:12:40.093244: BDMAP_A0000368, shape torch.Size([1, 565, 470, 565]), rank 0 +2025-11-09 03:15:22.555888: predicting BDMAP_A0000370 +2025-11-09 03:15:22.628385: BDMAP_A0000370, shape torch.Size([1, 532, 540, 532]), rank 0 +2025-11-09 03:17:43.154892: predicting BDMAP_A0000371 +2025-11-09 03:17:43.231463: BDMAP_A0000371, shape torch.Size([1, 515, 501, 515]), rank 0 +2025-11-09 03:20:03.030219: predicting BDMAP_A0000374 +2025-11-09 03:20:03.099266: BDMAP_A0000374, shape torch.Size([1, 467, 389, 467]), rank 0 +2025-11-09 03:21:13.854246: predicting BDMAP_A0000375 +2025-11-09 03:21:13.917338: BDMAP_A0000375, shape torch.Size([1, 550, 423, 550]), rank 0 +2025-11-09 03:22:59.824447: predicting BDMAP_A0000377 +2025-11-09 03:22:59.894493: BDMAP_A0000377, shape torch.Size([1, 571, 493, 571]), rank 0 +2025-11-09 03:25:43.234558: predicting BDMAP_A0000378 +2025-11-09 03:25:43.314812: BDMAP_A0000378, shape torch.Size([1, 588, 529, 588]), rank 0 +2025-11-09 03:33:42.724422: predicting BDMAP_A0000379 +2025-11-09 03:33:42.820540: BDMAP_A0000379, shape torch.Size([1, 582, 529, 582]), rank 0 +2025-11-09 03:41:41.349626: predicting BDMAP_A0000380 +2025-11-09 03:41:41.433014: BDMAP_A0000380, shape torch.Size([1, 481, 361, 481]), rank 0 +2025-11-09 03:43:25.836748: predicting BDMAP_A0000382 +2025-11-09 03:43:25.905846: BDMAP_A0000382, shape torch.Size([1, 684, 596, 684]), rank 0 +2025-11-09 03:56:13.069090: predicting BDMAP_A0000384 +2025-11-09 03:56:13.160297: BDMAP_A0000384, shape torch.Size([1, 696, 582, 696]), rank 0 +2025-11-09 04:09:05.761859: predicting BDMAP_A0000386 +2025-11-09 04:09:05.866123: BDMAP_A0000386, shape torch.Size([1, 473, 471, 473]), rank 0 +2025-11-09 04:10:39.864683: predicting BDMAP_A0000387 +2025-11-09 04:10:39.927580: BDMAP_A0000387, shape torch.Size([1, 487, 533, 487]), rank 0 +2025-11-09 04:12:59.285567: predicting BDMAP_A0000389 +2025-11-09 04:12:59.348214: BDMAP_A0000389, shape torch.Size([1, 501, 506, 501]), rank 0 +2025-11-09 04:15:18.884288: predicting BDMAP_A0000390 +2025-11-09 04:15:18.949714: BDMAP_A0000390, shape torch.Size([1, 481, 509, 481]), rank 0 +2025-11-09 04:17:38.279047: predicting BDMAP_A0000391 +2025-11-09 04:17:38.338784: BDMAP_A0000391, shape torch.Size([1, 568, 586, 568]), rank 0 +2025-11-09 04:25:48.705912: predicting BDMAP_A0000392 +2025-11-09 04:25:48.780202: BDMAP_A0000392, shape torch.Size([1, 549, 438, 549]), rank 0 +2025-11-09 04:27:35.041493: predicting BDMAP_A0000393 +2025-11-09 04:27:35.126214: BDMAP_A0000393, shape torch.Size([1, 508, 504, 508]), rank 0 +2025-11-09 04:29:54.826868: predicting BDMAP_A0000394 +2025-11-09 04:29:54.895584: BDMAP_A0000394, shape torch.Size([1, 557, 497, 557]), rank 0 +2025-11-09 04:32:15.733639: predicting BDMAP_A0000396 +2025-11-09 04:32:15.803888: BDMAP_A0000396, shape torch.Size([1, 422, 793, 422]), rank 0 +2025-11-09 04:34:58.590638: predicting BDMAP_A0000398 +2025-11-09 04:34:58.658867: BDMAP_A0000398, shape torch.Size([1, 421, 520, 421]), rank 0 +2025-11-09 04:36:32.162456: predicting BDMAP_A0000399 +2025-11-09 04:36:32.222860: BDMAP_A0000399, shape torch.Size([1, 509, 417, 509]), rank 0 +2025-11-09 04:38:17.670255: predicting BDMAP_A0000401 +2025-11-09 04:38:17.728137: BDMAP_A0000401, shape torch.Size([1, 504, 393, 504]), rank 0 +2025-11-09 04:40:02.579241: predicting BDMAP_A0000402 +2025-11-09 04:40:02.641642: BDMAP_A0000402, shape torch.Size([1, 484, 512, 484]), rank 0 +2025-11-09 04:42:21.911183: predicting BDMAP_A0000576 +2025-11-09 04:42:21.977566: BDMAP_A0000576, shape torch.Size([1, 409, 596, 409]), rank 0 +2025-11-09 04:44:18.130306: predicting BDMAP_A0000577 +2025-11-09 04:44:18.196591: BDMAP_A0000577, shape torch.Size([1, 402, 569, 402]), rank 0 +2025-11-09 04:46:13.968958: predicting BDMAP_A0000578 +2025-11-09 04:46:14.033914: BDMAP_A0000578, shape torch.Size([1, 422, 587, 422]), rank 0 +2025-11-09 04:48:10.219966: predicting BDMAP_A0000579 +2025-11-09 04:48:10.278924: BDMAP_A0000579, shape torch.Size([1, 394, 569, 394]), rank 0 +2025-11-09 04:49:43.626293: predicting BDMAP_A0000580 +2025-11-09 04:49:43.694322: BDMAP_A0000580, shape torch.Size([1, 444, 617, 444]), rank 0 +2025-11-09 04:51:40.679074: predicting BDMAP_A0000581 +2025-11-09 04:51:40.750048: BDMAP_A0000581, shape torch.Size([1, 459, 587, 459]), rank 0 +2025-11-09 04:53:37.760993: predicting BDMAP_A0000582 +2025-11-09 04:53:37.827770: BDMAP_A0000582, shape torch.Size([1, 422, 591, 422]), rank 0 +2025-11-09 04:55:34.189320: predicting BDMAP_A0000583 +2025-11-09 04:55:34.258782: BDMAP_A0000583, shape torch.Size([1, 422, 547, 422]), rank 0 +2025-11-09 04:57:07.947496: predicting BDMAP_A0000584 +2025-11-09 04:57:08.014703: BDMAP_A0000584, shape torch.Size([1, 502, 636, 502]), rank 0 +2025-11-09 05:00:02.702649: predicting BDMAP_A0000585 +2025-11-09 05:00:02.772052: BDMAP_A0000585, shape torch.Size([1, 459, 481, 459]), rank 0 +2025-11-09 05:01:36.484188: predicting BDMAP_A0000586 +2025-11-09 05:01:36.557338: BDMAP_A0000586, shape torch.Size([1, 450, 676, 450]), rank 0 +2025-11-09 05:03:56.446278: predicting BDMAP_A0000587 +2025-11-09 05:03:56.508975: BDMAP_A0000587, shape torch.Size([1, 422, 587, 422]), rank 0 +2025-11-09 05:05:52.755306: predicting BDMAP_A0000588 +2025-11-09 05:05:52.818672: BDMAP_A0000588, shape torch.Size([1, 422, 655, 422]), rank 0 +2025-11-09 05:07:49.593013: predicting BDMAP_A0000589 +2025-11-09 05:07:49.668433: BDMAP_A0000589, shape torch.Size([1, 422, 502, 422]), rank 0 +2025-11-09 05:09:22.924476: predicting BDMAP_A0000590 +2025-11-09 05:09:22.995012: BDMAP_A0000590, shape torch.Size([1, 428, 632, 428]), rank 0 +2025-11-09 05:11:19.986424: predicting BDMAP_A0000591 +2025-11-09 05:11:20.050995: BDMAP_A0000591, shape torch.Size([1, 506, 445, 506]), rank 0 +2025-11-09 05:13:05.440738: predicting BDMAP_A0000592 +2025-11-09 05:13:05.516377: BDMAP_A0000592, shape torch.Size([1, 456, 605, 456]), rank 0 +2025-11-09 05:15:02.608143: predicting BDMAP_A0000593 +2025-11-09 05:15:02.678932: BDMAP_A0000593, shape torch.Size([1, 422, 563, 422]), rank 0 +2025-11-09 05:16:58.720655: predicting BDMAP_A0000594 +2025-11-09 05:16:58.795763: BDMAP_A0000594, shape torch.Size([1, 456, 579, 456]), rank 0 +2025-11-09 05:18:55.705739: predicting BDMAP_A0000595 +2025-11-09 05:18:55.773088: BDMAP_A0000595, shape torch.Size([1, 475, 667, 475]), rank 0 +2025-11-09 05:20:54.143993: predicting BDMAP_A0000596 +2025-11-09 05:20:54.214142: BDMAP_A0000596, shape torch.Size([1, 571, 601, 571]), rank 0 +2025-11-09 05:29:00.804152: predicting BDMAP_A0000597 +2025-11-09 05:29:00.892678: BDMAP_A0000597, shape torch.Size([1, 463, 632, 463]), rank 0 +2025-11-09 05:30:58.433969: predicting BDMAP_A0000598 +2025-11-09 05:30:58.528404: BDMAP_A0000598, shape torch.Size([1, 495, 653, 495]), rank 0 +2025-11-09 05:33:53.137925: predicting BDMAP_A0000600 +2025-11-09 05:33:53.220588: BDMAP_A0000600, shape torch.Size([1, 422, 585, 422]), rank 0 +2025-11-09 05:35:49.478607: predicting BDMAP_A0000601 +2025-11-09 05:35:49.542232: BDMAP_A0000601, shape torch.Size([1, 460, 521, 460]), rank 0 +2025-11-09 05:37:23.595642: predicting BDMAP_A0000602 +2025-11-09 05:37:23.661031: BDMAP_A0000602, shape torch.Size([1, 457, 667, 457]), rank 0 +2025-11-09 05:39:21.492740: predicting BDMAP_A0000604 +2025-11-09 05:39:21.567258: BDMAP_A0000604, shape torch.Size([1, 474, 609, 474]), rank 0 +2025-11-09 05:41:19.213297: predicting BDMAP_A0000605 +2025-11-09 05:41:19.282818: BDMAP_A0000605, shape torch.Size([1, 418, 606, 418]), rank 0 +2025-11-09 05:43:15.681992: predicting BDMAP_A0000606 +2025-11-09 05:43:15.749928: BDMAP_A0000606, shape torch.Size([1, 495, 483, 495]), rank 0 +2025-11-09 05:45:35.022824: predicting BDMAP_A0000607 +2025-11-09 05:45:35.106354: BDMAP_A0000607, shape torch.Size([1, 513, 641, 513]), rank 0 +2025-11-09 05:52:30.481896: predicting BDMAP_A0000608 +2025-11-09 05:52:30.572637: BDMAP_A0000608, shape torch.Size([1, 519, 590, 519]), rank 0 +2025-11-09 05:55:24.883766: predicting BDMAP_A0000609 +2025-11-09 05:55:24.972594: BDMAP_A0000609, shape torch.Size([1, 412, 708, 412]), rank 0 +2025-11-09 05:57:44.284526: predicting BDMAP_A0000610 +2025-11-09 05:57:44.352185: BDMAP_A0000610, shape torch.Size([1, 456, 617, 456]), rank 0 +2025-11-09 05:59:41.524983: predicting BDMAP_A0000611 +2025-11-09 05:59:41.591814: BDMAP_A0000611, shape torch.Size([1, 473, 672, 473]), rank 0 +2025-11-09 06:01:40.040134: predicting BDMAP_A0000612 +2025-11-09 06:01:40.125754: BDMAP_A0000612, shape torch.Size([1, 422, 461, 422]), rank 0 +2025-11-09 06:03:13.243422: predicting BDMAP_A0000614 +2025-11-09 06:03:13.308905: BDMAP_A0000614, shape torch.Size([1, 422, 655, 422]), rank 0 +2025-11-09 06:05:10.127620: predicting BDMAP_A0000615 +2025-11-09 06:05:10.197729: BDMAP_A0000615, shape torch.Size([1, 511, 633, 511]), rank 0 +2025-11-09 06:12:04.877551: predicting BDMAP_A0000616 +2025-11-09 06:12:04.959896: BDMAP_A0000616, shape torch.Size([1, 492, 493, 492]), rank 0 +2025-11-09 06:14:23.944622: predicting BDMAP_A0000617 +2025-11-09 06:14:24.017081: BDMAP_A0000617, shape torch.Size([1, 405, 477, 405]), rank 0 +2025-11-09 06:15:56.886743: predicting BDMAP_A0000618 +2025-11-09 06:15:56.947858: BDMAP_A0000618, shape torch.Size([1, 535, 606, 535]), rank 0 +2025-11-09 06:22:55.538782: predicting BDMAP_A0000620 +2025-11-09 06:22:55.630640: BDMAP_A0000620, shape torch.Size([1, 535, 590, 535]), rank 0 +2025-11-09 06:29:53.967151: predicting BDMAP_A0000621 +2025-11-09 06:29:54.062893: BDMAP_A0000621, shape torch.Size([1, 515, 629, 515]), rank 0 +2025-11-09 06:36:48.778596: predicting BDMAP_A0000623 +2025-11-09 06:36:48.869760: BDMAP_A0000623, shape torch.Size([1, 456, 489, 456]), rank 0 +2025-11-09 06:38:22.259230: predicting BDMAP_A0000624 +2025-11-09 06:38:22.332348: BDMAP_A0000624, shape torch.Size([1, 492, 469, 492]), rank 0 +2025-11-09 06:40:41.464352: predicting BDMAP_A0000625 +2025-11-09 06:40:41.530364: BDMAP_A0000625, shape torch.Size([1, 428, 543, 428]), rank 0 +2025-11-09 06:42:15.283734: predicting BDMAP_A0000626 +2025-11-09 06:42:15.349735: BDMAP_A0000626, shape torch.Size([1, 385, 713, 385]), rank 0 +2025-11-09 06:44:07.350952: predicting BDMAP_A0000627 +2025-11-09 06:44:07.422854: BDMAP_A0000627, shape torch.Size([1, 495, 643, 495]), rank 0 +2025-11-09 06:47:02.049645: predicting BDMAP_A0000631 +2025-11-09 06:47:02.135272: BDMAP_A0000631, shape torch.Size([1, 563, 553, 563]), rank 0 +2025-11-09 06:53:33.048241: predicting BDMAP_A0000632 +2025-11-09 06:53:33.138419: BDMAP_A0000632, shape torch.Size([1, 537, 557, 537]), rank 0 +2025-11-09 06:55:53.983397: predicting BDMAP_A0000633 +2025-11-09 06:55:54.062701: BDMAP_A0000633, shape torch.Size([1, 440, 655, 440]), rank 0 +2025-11-09 06:57:51.311915: predicting BDMAP_A0000634 +2025-11-09 06:57:51.387486: BDMAP_A0000634, shape torch.Size([1, 492, 512, 492]), rank 0 +2025-11-09 07:00:11.324817: predicting BDMAP_A0000635 +2025-11-09 07:00:11.392591: BDMAP_A0000635, shape torch.Size([1, 608, 490, 608]), rank 0 +2025-11-09 07:07:55.835667: predicting BDMAP_A0000636 +2025-11-09 07:07:55.912712: BDMAP_A0000636, shape torch.Size([1, 492, 521, 492]), rank 0 +2025-11-09 07:10:15.216839: predicting BDMAP_A0000638 +2025-11-09 07:10:15.294499: BDMAP_A0000638, shape torch.Size([1, 428, 627, 428]), rank 0 +2025-11-09 07:12:12.044870: predicting BDMAP_A0000639 +2025-11-09 07:12:12.121667: BDMAP_A0000639, shape torch.Size([1, 523, 675, 523]), rank 0 +2025-11-09 07:20:27.148268: predicting BDMAP_A0000640 +2025-11-09 07:20:27.229483: BDMAP_A0000640, shape torch.Size([1, 446, 553, 446]), rank 0 +2025-11-09 07:22:01.292333: predicting BDMAP_A0000641 +2025-11-09 07:22:01.369753: BDMAP_A0000641, shape torch.Size([1, 461, 642, 461]), rank 0 +2025-11-09 07:23:59.048137: predicting BDMAP_A0000642 +2025-11-09 07:23:59.121953: BDMAP_A0000642, shape torch.Size([1, 473, 726, 473]), rank 0 +2025-11-09 07:29:35.939393: predicting BDMAP_A0000643 +2025-11-09 07:29:36.021600: BDMAP_A0000643, shape torch.Size([1, 426, 539, 426]), rank 0 +2025-11-09 07:31:09.375021: predicting BDMAP_A0000644 +2025-11-09 07:31:09.448661: BDMAP_A0000644, shape torch.Size([1, 551, 421, 551]), rank 0 +2025-11-09 07:32:55.522857: predicting BDMAP_A0000645 +2025-11-09 07:32:55.603591: BDMAP_A0000645, shape torch.Size([1, 596, 697, 596]), rank 0 +2025-11-09 07:44:29.111857: predicting BDMAP_A0000646 +2025-11-09 07:44:29.209403: BDMAP_A0000646, shape torch.Size([1, 388, 631, 388]), rank 0 +2025-11-09 07:46:02.642005: predicting BDMAP_A0000647 +2025-11-09 07:46:02.715753: BDMAP_A0000647, shape torch.Size([1, 456, 611, 456]), rank 0 +2025-11-09 07:47:59.706310: predicting BDMAP_A0000648 +2025-11-09 07:47:59.779714: BDMAP_A0000648, shape torch.Size([1, 484, 557, 484]), rank 0 +2025-11-09 07:50:19.653380: predicting BDMAP_A0000649 +2025-11-09 07:50:19.729353: BDMAP_A0000649, shape torch.Size([1, 433, 479, 433]), rank 0 +2025-11-09 07:51:53.145489: predicting BDMAP_A0000650 +2025-11-09 07:51:53.226265: BDMAP_A0000650, shape torch.Size([1, 473, 605, 473]), rank 0 +2025-11-09 07:53:50.956328: predicting BDMAP_A0000651 +2025-11-09 07:53:51.034123: BDMAP_A0000651, shape torch.Size([1, 543, 585, 543]), rank 0 +2025-11-09 08:00:45.699069: predicting BDMAP_A0000652 +2025-11-09 08:00:45.789618: BDMAP_A0000652, shape torch.Size([1, 422, 637, 422]), rank 0 +2025-11-09 08:02:42.259542: predicting BDMAP_A0000653 +2025-11-09 08:02:42.334320: BDMAP_A0000653, shape torch.Size([1, 428, 627, 428]), rank 0 +2025-11-09 08:04:39.177473: predicting BDMAP_A0000654 +2025-11-09 08:04:39.242517: BDMAP_A0000654, shape torch.Size([1, 388, 531, 388]), rank 0 +2025-11-09 08:05:54.290033: predicting BDMAP_A0000655 +2025-11-09 08:05:54.358271: BDMAP_A0000655, shape torch.Size([1, 464, 631, 464]), rank 0 +2025-11-09 08:07:51.966787: predicting BDMAP_A0000656 +2025-11-09 08:07:52.035826: BDMAP_A0000656, shape torch.Size([1, 459, 431, 459]), rank 0 +2025-11-09 08:09:03.074016: predicting BDMAP_A0000657 +2025-11-09 08:09:03.138850: BDMAP_A0000657, shape torch.Size([1, 475, 641, 475]), rank 0 +2025-11-09 08:11:01.071187: predicting BDMAP_A0000658 +2025-11-09 08:11:01.155728: BDMAP_A0000658, shape torch.Size([1, 522, 561, 522]), rank 0 +2025-11-09 08:13:55.382471: predicting BDMAP_A0000659 +2025-11-09 08:13:55.460868: BDMAP_A0000659, shape torch.Size([1, 518, 711, 518]), rank 0 +2025-11-09 08:22:10.756530: predicting BDMAP_A0000661 +2025-11-09 08:22:10.837907: BDMAP_A0000661, shape torch.Size([1, 422, 659, 422]), rank 0 +2025-11-09 08:24:07.482207: predicting BDMAP_A0000662 +2025-11-09 08:24:07.555723: BDMAP_A0000662, shape torch.Size([1, 425, 525, 425]), rank 0 +2025-11-09 08:25:41.017685: predicting BDMAP_A0000663 +2025-11-09 08:25:41.078521: BDMAP_A0000663, shape torch.Size([1, 443, 593, 443]), rank 0 +2025-11-09 08:27:37.913645: predicting BDMAP_A0000664 +2025-11-09 08:27:37.992726: BDMAP_A0000664, shape torch.Size([1, 430, 613, 430]), rank 0 +2025-11-09 08:29:34.838120: predicting BDMAP_A0000665 +2025-11-09 08:29:34.914613: BDMAP_A0000665, shape torch.Size([1, 525, 709, 525]), rank 0 +2025-11-09 08:37:52.320776: predicting BDMAP_A0000666 +2025-11-09 08:37:52.424788: BDMAP_A0000666, shape torch.Size([1, 422, 631, 422]), rank 0 +2025-11-09 08:39:48.857637: predicting BDMAP_A0000667 +2025-11-09 08:39:48.935532: BDMAP_A0000667, shape torch.Size([1, 433, 499, 433]), rank 0 +2025-11-09 08:41:22.511132: predicting BDMAP_A0000668 +2025-11-09 08:41:22.580769: BDMAP_A0000668, shape torch.Size([1, 422, 643, 422]), rank 0 +2025-11-09 08:43:19.419870: predicting BDMAP_A0000669 +2025-11-09 08:43:19.490831: BDMAP_A0000669, shape torch.Size([1, 509, 657, 509]), rank 0 +2025-11-09 08:50:13.017904: predicting BDMAP_A0000670 +2025-11-09 08:50:13.110967: BDMAP_A0000670, shape torch.Size([1, 452, 625, 452]), rank 0 +2025-11-09 08:52:10.178589: predicting BDMAP_A0000671 +2025-11-09 08:52:10.265211: BDMAP_A0000671, shape torch.Size([1, 419, 513, 419]), rank 0 +2025-11-09 08:53:43.674190: predicting BDMAP_A0000672 +2025-11-09 08:53:43.738764: BDMAP_A0000672, shape torch.Size([1, 506, 545, 506]), rank 0 +2025-11-09 08:56:04.142363: predicting BDMAP_A0000673 +2025-11-09 08:56:04.216939: BDMAP_A0000673, shape torch.Size([1, 512, 603, 512]), rank 0 +2025-11-09 08:58:58.901916: predicting BDMAP_A0000674 +2025-11-09 08:58:58.982450: BDMAP_A0000674, shape torch.Size([1, 450, 575, 450]), rank 0 +2025-11-09 09:00:55.907827: predicting BDMAP_A0000675 +2025-11-09 09:00:55.989483: BDMAP_A0000675, shape torch.Size([1, 535, 611, 535]), rank 0 +2025-11-09 09:07:53.964156: predicting BDMAP_A0000676 +2025-11-09 09:07:54.055732: BDMAP_A0000676, shape torch.Size([1, 475, 618, 475]), rank 0 +2025-11-09 09:09:51.557042: predicting BDMAP_A0000677 +2025-11-09 09:09:51.642448: BDMAP_A0000677, shape torch.Size([1, 422, 643, 422]), rank 0 +2025-11-09 09:11:48.579575: predicting BDMAP_A0000678 +2025-11-09 09:11:48.648885: BDMAP_A0000678, shape torch.Size([1, 460, 675, 460]), rank 0 +2025-11-09 09:14:08.967294: predicting BDMAP_A0000679 +2025-11-09 09:14:09.047696: BDMAP_A0000679, shape torch.Size([1, 467, 553, 467]), rank 0 +2025-11-09 09:15:43.681709: predicting BDMAP_A0000680 +2025-11-09 09:15:43.751806: BDMAP_A0000680, shape torch.Size([1, 535, 635, 535]), rank 0 +2025-11-09 09:22:42.862405: predicting BDMAP_A0000681 +2025-11-09 09:22:42.959872: BDMAP_A0000681, shape torch.Size([1, 523, 585, 523]), rank 0 +2025-11-09 09:25:37.281915: predicting BDMAP_A0000682 +2025-11-09 09:25:37.373344: BDMAP_A0000682, shape torch.Size([1, 487, 677, 487]), rank 0 +2025-11-09 09:29:06.108078: predicting BDMAP_A0000683 +2025-11-09 09:29:06.186970: BDMAP_A0000683, shape torch.Size([1, 422, 655, 422]), rank 0 +2025-11-09 09:31:03.069868: predicting BDMAP_A0000684 +2025-11-09 09:31:03.149326: BDMAP_A0000684, shape torch.Size([1, 461, 667, 461]), rank 0 +2025-11-09 09:33:01.058472: predicting BDMAP_A0000685 +2025-11-09 09:33:01.126393: BDMAP_A0000685, shape torch.Size([1, 422, 655, 422]), rank 0 +2025-11-09 09:34:58.136942: predicting BDMAP_A0000686 +2025-11-09 09:34:58.216495: BDMAP_A0000686, shape torch.Size([1, 468, 568, 468]), rank 0 +2025-11-09 09:36:55.465926: predicting BDMAP_A0000687 +2025-11-09 09:36:55.543395: BDMAP_A0000687, shape torch.Size([1, 444, 445, 444]), rank 0 +2025-11-09 09:38:06.368546: predicting BDMAP_A0000688 +2025-11-09 09:38:06.436248: BDMAP_A0000688, shape torch.Size([1, 422, 659, 422]), rank 0 +2025-11-09 09:40:03.264467: predicting BDMAP_A0000689 +2025-11-09 09:40:03.327446: BDMAP_A0000689, shape torch.Size([1, 443, 497, 443]), rank 0 +2025-11-09 09:41:37.037812: predicting BDMAP_A0000690 +2025-11-09 09:41:37.104747: BDMAP_A0000690, shape torch.Size([1, 535, 581, 535]), rank 0 +2025-11-09 09:48:34.409548: predicting BDMAP_A0000691 +2025-11-09 09:48:34.486929: BDMAP_A0000691, shape torch.Size([1, 568, 721, 568]), rank 0 +2025-11-09 09:58:16.132035: predicting BDMAP_A0000692 +2025-11-09 09:58:16.234793: BDMAP_A0000692, shape torch.Size([1, 478, 651, 478]), rank 0 +2025-11-09 10:00:14.190625: predicting BDMAP_A0000693 +2025-11-09 10:00:14.280779: BDMAP_A0000693, shape torch.Size([1, 422, 639, 422]), rank 0 +2025-11-09 10:02:11.005446: predicting BDMAP_A0000694 +2025-11-09 10:02:11.078000: BDMAP_A0000694, shape torch.Size([1, 570, 748, 570]), rank 0 +2025-11-09 10:11:56.189101: predicting BDMAP_A0000695 +2025-11-09 10:11:56.281019: BDMAP_A0000695, shape torch.Size([1, 467, 554, 467]), rank 0 +2025-11-09 10:13:30.559569: predicting BDMAP_A0000696 +2025-11-09 10:13:30.641340: BDMAP_A0000696, shape torch.Size([1, 422, 502, 422]), rank 0 +2025-11-09 10:15:03.866201: predicting BDMAP_A0000697 +2025-11-09 10:15:03.931631: BDMAP_A0000697, shape torch.Size([1, 454, 587, 454]), rank 0 +2025-11-09 10:17:01.060254: predicting BDMAP_A0000699 +2025-11-09 10:17:01.126934: BDMAP_A0000699, shape torch.Size([1, 537, 761, 537]), rank 0 +2025-11-09 10:25:22.692636: predicting BDMAP_A0000700 +2025-11-09 10:25:22.799015: BDMAP_A0000700, shape torch.Size([1, 470, 537, 470]), rank 0 +2025-11-09 10:26:57.253936: predicting BDMAP_A0000701 +2025-11-09 10:26:57.330216: BDMAP_A0000701, shape torch.Size([1, 422, 621, 422]), rank 0 +2025-11-09 10:28:53.773302: predicting BDMAP_A0000702 +2025-11-09 10:28:53.837681: BDMAP_A0000702, shape torch.Size([1, 422, 563, 422]), rank 0 +2025-11-09 10:30:50.175193: predicting BDMAP_A0000703 +2025-11-09 10:30:50.247700: BDMAP_A0000703, shape torch.Size([1, 422, 671, 422]), rank 0 +2025-11-09 10:32:47.269842: predicting BDMAP_A0000704 +2025-11-09 10:32:47.340520: BDMAP_A0000704, shape torch.Size([1, 473, 663, 473]), rank 0 +2025-11-09 10:34:45.436014: predicting BDMAP_A0000705 +2025-11-09 10:34:45.512735: BDMAP_A0000705, shape torch.Size([1, 515, 581, 515]), rank 0 +2025-11-09 10:37:39.870715: predicting BDMAP_A0000706 +2025-11-09 10:37:39.941271: BDMAP_A0000706, shape torch.Size([1, 428, 632, 428]), rank 0 +2025-11-09 10:39:36.795154: predicting BDMAP_A0000707 +2025-11-09 10:39:36.865109: BDMAP_A0000707, shape torch.Size([1, 398, 600, 398]), rank 0 +2025-11-09 10:41:10.675901: predicting BDMAP_A0000708 +2025-11-09 10:41:10.753253: BDMAP_A0000708, shape torch.Size([1, 484, 657, 484]), rank 0 +2025-11-09 10:44:05.230387: predicting BDMAP_A0000709 +2025-11-09 10:44:05.307040: BDMAP_A0000709, shape torch.Size([1, 461, 775, 461]), rank 0 +2025-11-09 10:49:44.278444: predicting BDMAP_A0000710 +2025-11-09 10:49:44.368928: BDMAP_A0000710, shape torch.Size([1, 492, 684, 492]), rank 0 +2025-11-09 10:57:58.643068: predicting BDMAP_A0000711 +2025-11-09 10:57:58.736573: BDMAP_A0000711, shape torch.Size([1, 454, 707, 454]), rank 0 +2025-11-09 11:00:18.920192: predicting BDMAP_A0000712 +2025-11-09 11:00:19.012179: BDMAP_A0000712, shape torch.Size([1, 430, 624, 430]), rank 0 +2025-11-09 11:02:15.859687: predicting BDMAP_A0000713 +2025-11-09 11:02:15.937308: BDMAP_A0000713, shape torch.Size([1, 422, 625, 422]), rank 0 +2025-11-09 11:04:12.469515: predicting BDMAP_A0000714 +2025-11-09 11:04:12.537615: BDMAP_A0000714, shape torch.Size([1, 422, 469, 422]), rank 0 +2025-11-09 11:05:45.551667: predicting BDMAP_A0000715 +2025-11-09 11:05:45.621045: BDMAP_A0000715, shape torch.Size([1, 414, 697, 414]), rank 0 +2025-11-09 11:08:05.130478: predicting BDMAP_A0000716 +2025-11-09 11:08:05.196154: BDMAP_A0000716, shape torch.Size([1, 480, 585, 480]), rank 0 +2025-11-09 11:10:02.660367: predicting BDMAP_A0000717 +2025-11-09 11:10:02.730373: BDMAP_A0000717, shape torch.Size([1, 506, 445, 506]), rank 0 +2025-11-09 11:11:48.108276: predicting BDMAP_A0000718 +2025-11-09 11:11:48.172129: BDMAP_A0000718, shape torch.Size([1, 399, 634, 399]), rank 0 +2025-11-09 11:13:21.869480: predicting BDMAP_A0000719 +2025-11-09 11:13:21.946779: BDMAP_A0000719, shape torch.Size([1, 535, 557, 535]), rank 0 +2025-11-09 11:15:42.909250: predicting BDMAP_A0000720 +2025-11-09 11:15:42.982418: BDMAP_A0000720, shape torch.Size([1, 422, 623, 422]), rank 0 +2025-11-09 11:17:39.668884: predicting BDMAP_A0000721 +2025-11-09 11:17:39.743461: BDMAP_A0000721, shape torch.Size([1, 422, 613, 422]), rank 0 +2025-11-09 11:19:36.294041: predicting BDMAP_A0000722 +2025-11-09 11:19:36.369039: BDMAP_A0000722, shape torch.Size([1, 504, 735, 504]), rank 0 +2025-11-09 11:27:53.769364: predicting BDMAP_A0000723 +2025-11-09 11:27:53.863501: BDMAP_A0000723, shape torch.Size([1, 533, 639, 533]), rank 0 +2025-11-09 11:34:52.797522: predicting BDMAP_A0000724 +2025-11-09 11:34:52.901825: BDMAP_A0000724, shape torch.Size([1, 630, 808, 630]), rank 0 +2025-11-09 11:48:29.022214: predicting BDMAP_A0000725 +2025-11-09 11:48:29.172484: BDMAP_A0000725, shape torch.Size([1, 456, 605, 456]), rank 0 +2025-11-09 11:50:26.370876: predicting BDMAP_A0000726 +2025-11-09 11:50:26.447681: BDMAP_A0000726, shape torch.Size([1, 470, 679, 470]), rank 0 +2025-11-09 11:52:47.151975: predicting BDMAP_A0000727 +2025-11-09 11:52:47.221386: BDMAP_A0000727, shape torch.Size([1, 443, 659, 443]), rank 0 +2025-11-09 11:54:44.727830: predicting BDMAP_A0000728 +2025-11-09 11:54:44.803780: BDMAP_A0000728, shape torch.Size([1, 452, 660, 452]), rank 0 +2025-11-09 11:56:42.462914: predicting BDMAP_A0000729 +2025-11-09 11:56:42.536292: BDMAP_A0000729, shape torch.Size([1, 422, 496, 422]), rank 0 +2025-11-09 11:58:15.986562: predicting BDMAP_A0000730 +2025-11-09 11:58:16.046731: BDMAP_A0000730, shape torch.Size([1, 480, 624, 480]), rank 0 +2025-11-09 12:00:13.956785: predicting BDMAP_A0000731 +2025-11-09 12:00:14.035038: BDMAP_A0000731, shape torch.Size([1, 499, 619, 499]), rank 0 +2025-11-09 12:03:08.493349: predicting BDMAP_A0000732 +2025-11-09 12:03:08.566184: BDMAP_A0000732, shape torch.Size([1, 481, 635, 481]), rank 0 +2025-11-09 12:06:02.960087: predicting BDMAP_A0000733 +2025-11-09 12:06:03.033966: BDMAP_A0000733, shape torch.Size([1, 456, 697, 456]), rank 0 +2025-11-09 12:08:23.506410: predicting BDMAP_A0000734 +2025-11-09 12:08:23.576613: BDMAP_A0000734, shape torch.Size([1, 509, 859, 509]), rank 0 +2025-11-09 12:18:05.285956: predicting BDMAP_A0000735 +2025-11-09 12:18:05.362838: BDMAP_A0000735, shape torch.Size([1, 422, 563, 422]), rank 0 +2025-11-09 12:20:01.289802: predicting BDMAP_A0000736 +2025-11-09 12:20:01.361180: BDMAP_A0000736, shape torch.Size([1, 487, 653, 487]), rank 0 +2025-11-09 12:22:55.776805: predicting BDMAP_A0000737 +2025-11-09 12:22:55.852785: BDMAP_A0000737, shape torch.Size([1, 473, 614, 473]), rank 0 +2025-11-09 12:24:53.626035: predicting BDMAP_A0000738 +2025-11-09 12:24:53.687515: BDMAP_A0000738, shape torch.Size([1, 422, 611, 422]), rank 0 +2025-11-09 12:26:50.289696: predicting BDMAP_A0000739 +2025-11-09 12:26:50.360620: BDMAP_A0000739, shape torch.Size([1, 480, 685, 480]), rank 0 +2025-11-09 12:29:11.559146: predicting BDMAP_A0000740 +2025-11-09 12:29:11.631282: BDMAP_A0000740, shape torch.Size([1, 474, 591, 474]), rank 0 +2025-11-09 12:31:09.255579: predicting BDMAP_A0000742 +2025-11-09 12:31:09.321643: BDMAP_A0000742, shape torch.Size([1, 440, 616, 440]), rank 0 +2025-11-09 12:33:06.307368: predicting BDMAP_A0000743 +2025-11-09 12:33:06.379901: BDMAP_A0000743, shape torch.Size([1, 498, 723, 498]), rank 0 +2025-11-09 12:41:23.342363: predicting BDMAP_A0000744 +2025-11-09 12:41:23.425292: BDMAP_A0000744, shape torch.Size([1, 422, 683, 422]), rank 0 +2025-11-09 12:43:42.311401: predicting BDMAP_A0000745 +2025-11-09 12:43:42.381426: BDMAP_A0000745, shape torch.Size([1, 456, 579, 456]), rank 0 +2025-11-09 12:45:39.143792: predicting BDMAP_A0000746 +2025-11-09 12:45:39.210157: BDMAP_A0000746, shape torch.Size([1, 449, 647, 449]), rank 0 +2025-11-09 12:47:36.430460: predicting BDMAP_A0000747 +2025-11-09 12:47:36.496896: BDMAP_A0000747, shape torch.Size([1, 430, 709, 430]), rank 0 +2025-11-09 12:49:56.247342: predicting BDMAP_A0000748 +2025-11-09 12:49:56.310398: BDMAP_A0000748, shape torch.Size([1, 475, 667, 475]), rank 0 +2025-11-09 12:51:54.698376: predicting BDMAP_A0000749 +2025-11-09 12:51:54.781332: BDMAP_A0000749, shape torch.Size([1, 456, 649, 456]), rank 0 +2025-11-09 12:53:52.600425: predicting BDMAP_A0000750 +2025-11-09 12:53:52.672906: BDMAP_A0000750, shape torch.Size([1, 421, 568, 421]), rank 0 +2025-11-09 12:55:48.808901: predicting BDMAP_A0000751 +2025-11-09 12:55:48.882147: BDMAP_A0000751, shape torch.Size([1, 435, 580, 435]), rank 0 +2025-11-09 12:57:45.417352: predicting BDMAP_A0000752 +2025-11-09 12:57:45.483512: BDMAP_A0000752, shape torch.Size([1, 477, 441, 477]), rank 0 +2025-11-09 12:58:56.910219: predicting BDMAP_A0000753 +2025-11-09 12:58:56.969262: BDMAP_A0000753, shape torch.Size([1, 457, 363, 457]), rank 0 +2025-11-09 13:00:07.395398: predicting BDMAP_A0000754 +2025-11-09 13:00:07.454346: BDMAP_A0000754, shape torch.Size([1, 511, 479, 511]), rank 0 +2025-11-09 13:02:27.071773: predicting BDMAP_A0000755 +2025-11-09 13:02:27.148292: BDMAP_A0000755, shape torch.Size([1, 473, 557, 473]), rank 0 +2025-11-09 13:04:01.849889: predicting BDMAP_A0000756 +2025-11-09 13:04:01.918148: BDMAP_A0000756, shape torch.Size([1, 335, 603, 335]), rank 0 +2025-11-09 13:05:12.028099: predicting BDMAP_A0000757 +2025-11-09 13:05:12.101079: BDMAP_A0000757, shape torch.Size([1, 430, 767, 430]), rank 0 +2025-11-09 13:07:32.484753: predicting BDMAP_A0000758 +2025-11-09 13:07:32.570243: BDMAP_A0000758, shape torch.Size([1, 522, 657, 522]), rank 0 +2025-11-09 13:14:28.560579: predicting BDMAP_A0000759 +2025-11-09 13:14:28.637524: BDMAP_A0000759, shape torch.Size([1, 571, 601, 571]), rank 0 +2025-11-09 13:22:33.317481: predicting BDMAP_A0000760 +2025-11-09 13:22:33.415123: BDMAP_A0000760, shape torch.Size([1, 422, 575, 422]), rank 0 +2025-11-09 13:24:29.270132: predicting BDMAP_A0000761 +2025-11-09 13:24:29.351355: BDMAP_A0000761, shape torch.Size([1, 535, 668, 535]), rank 0 +2025-11-09 13:31:27.652665: predicting BDMAP_A0000762 +2025-11-09 13:31:27.745548: BDMAP_A0000762, shape torch.Size([1, 498, 528, 498]), rank 0 +2025-11-09 13:33:47.172671: predicting BDMAP_A0000763 +2025-11-09 13:33:47.260550: BDMAP_A0000763, shape torch.Size([1, 453, 585, 453]), rank 0 +2025-11-09 13:35:44.540941: predicting BDMAP_A0000764 +2025-11-09 13:35:44.613614: BDMAP_A0000764, shape torch.Size([1, 422, 586, 422]), rank 0 +2025-11-09 13:37:40.966161: predicting BDMAP_A0000765 +2025-11-09 13:37:41.042082: BDMAP_A0000765, shape torch.Size([1, 473, 625, 473]), rank 0 +2025-11-09 13:39:38.827660: predicting BDMAP_A0000766 +2025-11-09 13:39:38.898568: BDMAP_A0000766, shape torch.Size([1, 512, 695, 512]), rank 0 +2025-11-09 13:47:51.612350: predicting BDMAP_A0000767 +2025-11-09 13:47:51.697351: BDMAP_A0000767, shape torch.Size([1, 608, 757, 608]), rank 0 diff --git a/Dataset809_AbdomenAtlasF17/nnUNetTrainer__nnUNetResEncUNetLPlans__3d_fullres/plans.json b/Dataset809_AbdomenAtlasF17/nnUNetTrainer__nnUNetResEncUNetLPlans__3d_fullres/plans.json new file mode 100644 index 0000000000000000000000000000000000000000..6a454377902d2dc1d2629a9bf5d73e8c3d812623 --- /dev/null +++ b/Dataset809_AbdomenAtlasF17/nnUNetTrainer__nnUNetResEncUNetLPlans__3d_fullres/plans.json @@ -0,0 +1,532 @@ +{ + "dataset_name": "Dataset809_AbdomenAtlasF17", + "plans_name": "nnUNetResEncUNetLPlans", + "original_median_spacing_after_transp": [ + 0.7109375, + 0.5, + 0.7109375 + ], + "original_median_shape_after_transp": [ + 512, + 608, + 512 + ], + "image_reader_writer": "SimpleITKIO", + "transpose_forward": [ + 1, + 0, + 2 + ], + "transpose_backward": [ + 1, + 0, + 2 + ], + "configurations": { + "2d": { + "data_identifier": "nnUNetPlans_2d", + "preprocessor_name": "DefaultPreprocessor", + "batch_size": 22, + "patch_size": [ + 640, + 640 + ], + "median_image_size_in_voxels": [ + 613.0, + 513.0 + ], + "spacing": [ + 0.5, + 0.7109375 + ], + "normalization_schemes": [ + "CTNormalization" + ], + "use_mask_for_norm": [ + false + ], + "resampling_fn_data": "resample_data_or_seg_to_shape", + "resampling_fn_seg": "resample_data_or_seg_to_shape", + "resampling_fn_data_kwargs": { + "is_seg": false, + "order": 3, + "order_z": 0, + "force_separate_z": null + }, + "resampling_fn_seg_kwargs": { + "is_seg": true, + "order": 1, + "order_z": 0, + "force_separate_z": null + }, + "resampling_fn_probabilities": "resample_data_or_seg_to_shape", + "resampling_fn_probabilities_kwargs": { + "is_seg": false, + "order": 1, + "order_z": 0, + "force_separate_z": null + }, + "architecture": { + "network_class_name": "dynamic_network_architectures.architectures.unet.ResidualEncoderUNet", + "arch_kwargs": { + "n_stages": 8, + "features_per_stage": [ + 32, + 64, + 128, + 256, + 512, + 512, + 512, + 512 + ], + "conv_op": "torch.nn.modules.conv.Conv2d", + "kernel_sizes": [ + [ + 3, + 3 + ], + [ + 3, + 3 + ], + [ + 3, + 3 + ], + [ + 3, + 3 + ], + [ + 3, + 3 + ], + [ + 3, + 3 + ], + [ + 3, + 3 + ], + [ + 3, + 3 + ] + ], + "strides": [ + [ + 1, + 1 + ], + [ + 2, + 2 + ], + [ + 2, + 2 + ], + [ + 2, + 2 + ], + [ + 2, + 2 + ], + [ + 2, + 2 + ], + [ + 2, + 2 + ], + [ + 2, + 2 + ] + ], + "n_blocks_per_stage": [ + 1, + 3, + 4, + 6, + 6, + 6, + 6, + 6 + ], + "n_conv_per_stage_decoder": [ + 1, + 1, + 1, + 1, + 1, + 1, + 1 + ], + "conv_bias": true, + "norm_op": "torch.nn.modules.instancenorm.InstanceNorm2d", + "norm_op_kwargs": { + "eps": 1e-05, + "affine": true + }, + "dropout_op": null, + "dropout_op_kwargs": null, + "nonlin": "torch.nn.LeakyReLU", + "nonlin_kwargs": { + "inplace": true + } + }, + "_kw_requires_import": [ + "conv_op", + "norm_op", + "dropout_op", + "nonlin" + ] + }, + "batch_dice": true + }, + "3d_lowres": { + "data_identifier": "nnUNetResEncUNetLPlans_3d_lowres", + "preprocessor_name": "DefaultPreprocessor", + "batch_size": 2, + "patch_size": [ + 160, + 224, + 192 + ], + "median_image_size_in_voxels": [ + 283, + 339, + 284 + ], + "spacing": [ + 1.284032205897787, + 0.9030556173347075, + 1.284032205897787 + ], + "normalization_schemes": [ + "CTNormalization" + ], + "use_mask_for_norm": [ + false + ], + "resampling_fn_data": "resample_data_or_seg_to_shape", + "resampling_fn_seg": "resample_data_or_seg_to_shape", + "resampling_fn_data_kwargs": { + "is_seg": false, + "order": 3, + "order_z": 0, + "force_separate_z": null + }, + "resampling_fn_seg_kwargs": { + "is_seg": true, + "order": 1, + "order_z": 0, + "force_separate_z": null + }, + "resampling_fn_probabilities": "resample_data_or_seg_to_shape", + "resampling_fn_probabilities_kwargs": { + "is_seg": false, + "order": 1, + "order_z": 0, + "force_separate_z": null + }, + "architecture": { + "network_class_name": "dynamic_network_architectures.architectures.unet.ResidualEncoderUNet", + "arch_kwargs": { + "n_stages": 6, + "features_per_stage": [ + 32, + 64, + 128, + 256, + 320, + 320 + ], + "conv_op": "torch.nn.modules.conv.Conv3d", + "kernel_sizes": [ + [ + 3, + 3, + 3 + ], + [ + 3, + 3, + 3 + ], + [ + 3, + 3, + 3 + ], + [ + 3, + 3, + 3 + ], + [ + 3, + 3, + 3 + ], + [ + 3, + 3, + 3 + ] + ], + "strides": [ + [ + 1, + 1, + 1 + ], + [ + 2, + 2, + 2 + ], + [ + 2, + 2, + 2 + ], + [ + 2, + 2, + 2 + ], + [ + 2, + 2, + 2 + ], + [ + 2, + 2, + 2 + ] + ], + "n_blocks_per_stage": [ + 1, + 3, + 4, + 6, + 6, + 6 + ], + "n_conv_per_stage_decoder": [ + 1, + 1, + 1, + 1, + 1 + ], + "conv_bias": true, + "norm_op": "torch.nn.modules.instancenorm.InstanceNorm3d", + "norm_op_kwargs": { + "eps": 1e-05, + "affine": true + }, + "dropout_op": null, + "dropout_op_kwargs": null, + "nonlin": "torch.nn.LeakyReLU", + "nonlin_kwargs": { + "inplace": true + } + }, + "_kw_requires_import": [ + "conv_op", + "norm_op", + "dropout_op", + "nonlin" + ] + }, + "batch_dice": false, + "next_stage": "3d_cascade_fullres" + }, + "3d_fullres": { + "data_identifier": "nnUNetPlans_3d_fullres", + "preprocessor_name": "DefaultPreprocessor", + "batch_size": 2, + "patch_size": [ + 160, + 224, + 192 + ], + "median_image_size_in_voxels": [ + 512.0, + 613.0, + 513.0 + ], + "spacing": [ + 0.7109375, + 0.5, + 0.7109375 + ], + "normalization_schemes": [ + "CTNormalization" + ], + "use_mask_for_norm": [ + false + ], + "resampling_fn_data": "resample_data_or_seg_to_shape", + "resampling_fn_seg": "resample_data_or_seg_to_shape", + "resampling_fn_data_kwargs": { + "is_seg": false, + "order": 3, + "order_z": 0, + "force_separate_z": null + }, + "resampling_fn_seg_kwargs": { + "is_seg": true, + "order": 1, + "order_z": 0, + "force_separate_z": null + }, + "resampling_fn_probabilities": "resample_data_or_seg_to_shape", + "resampling_fn_probabilities_kwargs": { + "is_seg": false, + "order": 1, + "order_z": 0, + "force_separate_z": null + }, + "architecture": { + "network_class_name": "dynamic_network_architectures.architectures.unet.ResidualEncoderUNet", + "arch_kwargs": { + "n_stages": 6, + "features_per_stage": [ + 32, + 64, + 128, + 256, + 320, + 320 + ], + "conv_op": "torch.nn.modules.conv.Conv3d", + "kernel_sizes": [ + [ + 3, + 3, + 3 + ], + [ + 3, + 3, + 3 + ], + [ + 3, + 3, + 3 + ], + [ + 3, + 3, + 3 + ], + [ + 3, + 3, + 3 + ], + [ + 3, + 3, + 3 + ] + ], + "strides": [ + [ + 1, + 1, + 1 + ], + [ + 2, + 2, + 2 + ], + [ + 2, + 2, + 2 + ], + [ + 2, + 2, + 2 + ], + [ + 2, + 2, + 2 + ], + [ + 2, + 2, + 2 + ] + ], + "n_blocks_per_stage": [ + 1, + 3, + 4, + 6, + 6, + 6 + ], + "n_conv_per_stage_decoder": [ + 1, + 1, + 1, + 1, + 1 + ], + "conv_bias": true, + "norm_op": "torch.nn.modules.instancenorm.InstanceNorm3d", + "norm_op_kwargs": { + "eps": 1e-05, + "affine": true + }, + "dropout_op": null, + "dropout_op_kwargs": null, + "nonlin": "torch.nn.LeakyReLU", + "nonlin_kwargs": { + "inplace": true + } + }, + "_kw_requires_import": [ + "conv_op", + "norm_op", + "dropout_op", + "nonlin" + ] + }, + "batch_dice": true + }, + "3d_cascade_fullres": { + "inherits_from": "3d_fullres", + "previous_stage": "3d_lowres" + } + }, + "experiment_planner_used": "nnUNetPlannerResEncL", + "label_manager": "LabelManager", + "foreground_intensity_properties_per_channel": { + "0": { + "max": 1000.0, + "mean": 39.68027877807617, + "median": 71.0, + "min": -1000.0, + "percentile_00_5": -1000.0, + "percentile_99_5": 379.0, + "std": 192.4669952392578 + } + } +} \ No newline at end of file