{
 "returncode": 1,
 "stdout": "submission.py:classify at 1.90% error: 15 timed calls, each in a fresh process\n  review flag: embedded data? 1 high-entropy literal(s), 19,775 characters\n  review flag: decodes data: imports base64, lzma\n  review flag: 20,428 bytes, close to the 20,480-byte limit\n  NVIDIA A100-SXM4-80GB, torch 2.12.0+cu130, sandbox on\n  call  1/15: 7,039.615 ms, scorer's clock 7,043.164 ms\n  call  2/15: 7,037.441 ms, scorer's clock 7,040.767 ms\n  call  3/15: 7,041.421 ms, scorer's clock 7,047.020 ms\n  call  4/15: 7,036.862 ms, scorer's clock 7,040.449 ms\n  call  5/15: 7,036.214 ms, scorer's clock 7,040.319 ms\n  call  6/15: 7,036.548 ms, scorer's clock 7,039.865 ms\n  call  7/15: 7,035.864 ms, scorer's clock 7,039.124 ms\n  call  8/15: 7,036.944 ms, scorer's clock 7,039.827 ms\n  call  9/15: 7,038.543 ms, scorer's clock 7,042.427 ms\n  call 10/15: 7,039.640 ms, scorer's clock 7,044.932 ms\n  call 11/15: 7,037.579 ms, scorer's clock 7,040.012 ms\n  call 12/15: 7,036.899 ms, scorer's clock 7,039.305 ms\n  call 13/15: 7,036.399 ms, scorer's clock 7,039.622 ms\n  call 14/15: 7,036.125 ms, scorer's clock 7,039.199 ms\n  call 15/15: 7,039.893 ms, scorer's clock 7,043.720 ms\nMNIST 98.07% (107,873/110,000), 7037.559 ms/call; hold-out (fashion) 88.22%, 7038.209 ms/call\ndisqualified: MNIST accuracy 98.066% (107,873/110,000); the band needs 107,910 correct\n",
 "stderr": "es=8 winner=0 id=6 tile=20 split=1 us=56.0640\nLT tuned m=4096 n=16 k=512 at=0 bt=1 E=4 candidates=6 winner=2 id=31 tile=15 split=1 us=17.4933\nLT tuned m=512 n=16 k=4096 at=1 bt=1 E=4 candidates=4 winner=2 id=31 tile=15 split=1 us=22.6987\nLT tuned m=4096 n=512 k=16 at=0 bt=0 E=4 candidates=4 winner=0 id=5 tile=24 split=1 us=22.8693\nLT tuned m=512 n=512 k=4096 at=1 bt=1 E=4 candidates=5 winner=3 id=31 tile=18 split=1 us=86.1013\nLT tuned m=4096 n=512 k=512 at=0 bt=1 E=4 candidates=8 winner=0 id=6 tile=20 split=1 us=55.2960\nLT tuned m=512 n=128 k=4096 at=1 bt=1 E=4 candidates=5 winner=0 id=31 tile=15 split=1 us=24.6613\nLT tuned m=20000 n=512 k=128 at=0 bt=0 E=4 candidates=8 winner=0 id=6 tile=20 split=1 us=111.1040\nLT tuned m=20000 n=512 k=512 at=0 bt=0 E=4 candidates=8 winner=0 id=6 tile=20 split=1 us=233.3013\nLT tuned m=20000 n=16 k=512 at=0 bt=1 E=4 candidates=8 winner=0 id=6 tile=17 split=1 us=62.8907\n[1/3] /usr/local/cuda/bin/nvcc -MD -MF centered_halfnorm_small_members.cuda.o.d -DTORCH_EXTENSION_NAME=sutro_centered_halfnorm_small_members_bn_stagepack -DTORCH_API_INCLUDE_EXTENSION_H -isystem /usr/local/lib/python3.13/site-packages/torch/include -isystem /usr/local/lib/python3.13/site-packages/torch/include/torch/csrc/api/include -isystem /usr/local/cuda/include -isystem /usr/local/include/python3.13 -D__CUDA_NO_HALF_OPERATORS__ -D__CUDA_NO_HALF_CONVERSIONS__ -D__CUDA_NO_BFLOAT16_CONVERSIONS__ -D__CUDA_NO_HALF2_OPERATORS__ --expt-relaxed-constexpr -gencode=arch=compute_80,code=sm_80 --compiler-options '-fPIC' -O3 -lineinfo --ptxas-options=-v -std=c++20 -c /tmp/sutro-bn-stage-582fe8613daf6be1-65534/kernels/centered_halfnorm_small_members.cu -o centered_halfnorm_small_members.cuda.o \nptxas info    : 0 bytes gmem\nptxas info    : Compiling entry function '_Z9transformILi8EEvPK13__nv_bfloat16S2_PKfPS0_i' for 'sm_80'\nptxas info    : Function properties for _Z9transformILi8EEvPK13__nv_bfloat16S2_PKfPS0_i\n    0 bytes stack frame, 0 bytes spill stores, 0 bytes spill loads\nptxas info    : Used 50 registers, used 1 barriers, 68 bytes smem, 388 bytes cmem[0]\nptxas info    : Compile time = 33.846 ms\nptxas info    : Compiling entry function '_Z9transformILi4EEvPK13__nv_bfloat16S2_PKfPS0_i' for 'sm_80'\nptxas info    : Function properties for _Z9transformILi4EEvPK13__nv_bfloat16S2_PKfPS0_i\n    0 bytes stack frame, 0 bytes spill stores, 0 bytes spill loads\nptxas info    : Used 32 registers, used 1 barriers, 36 bytes smem, 388 bytes cmem[0]\nptxas info    : Compile time = 18.877 ms\nptxas info    : Compiling entry function '_Z9transformILi2EEvPK13__nv_bfloat16S2_PKfPS0_i' for 'sm_80'\nptxas info    : Function properties for _Z9transformILi2EEvPK13__nv_bfloat16S2_PKfPS0_i\n    0 bytes stack frame, 0 bytes spill stores, 0 bytes spill loads\nptxas info    : Used 32 registers, used 1 barriers, 20 bytes smem, 388 bytes cmem[0]\nptxas info    : Compile time = 18.127 ms\nptxas info    : Compiling entry function '_Z9transformILi1EEvPK13__nv_bfloat16S2_PKfPS0_i' for 'sm_80'\nptxas info    : Function properties for _Z9transformILi1EEvPK13__nv_bfloat16S2_PKfPS0_i\n    0 bytes stack frame, 0 bytes spill stores, 0 bytes spill loads\nptxas info    : Used 32 registers, used 1 barriers, 12 bytes smem, 388 bytes cmem[0]\nptxas info    : Compile time = 16.433 ms\nptxas info    : Compiling entry function '_Z11finish_meanPKfPfiii' for 'sm_80'\nptxas info    : Function properties for _Z11finish_meanPKfPfiii\n    0 bytes stack frame, 0 bytes spill stores, 0 bytes spill loads\nptxas info    : Used 32 registers, used 0 barriers, 380 bytes cmem[0]\nptxas info    : Compile time = 11.389 ms\nptxas info    : Compiling entry function '_Z12partial_meanPK13__nv_bfloat16S1_Pfiiii' for 'sm_80'\nptxas info    : Function properties for _Z12partial_meanPK13__nv_bfloat16S1_Pfiiii\n    0 bytes stack frame, 0 bytes spill stores, 0 bytes spill loads\nptxas info    : Used 32 registers, used 1 barriers, 1024 bytes smem, 392 bytes cmem[0]\nptxas info    : Compile time = 9.018 ms\n[2/3] c++ -MMD -MF centered_halfnorm_small_members_bindings.o.d -DTORCH_EXTENSION_NAME=sutro_centered_halfnorm_small_members_bn_stagepack -DTORCH_API_INCLUDE_EXTENSION_H -isystem /usr/local/lib/python3.13/site-packages/torch/include -isystem /usr/local/lib/python3.13/site-packages/torch/include/torch/csrc/api/include -isystem /usr/local/cuda/include -isystem /usr/local/include/python3.13 -fPIC -std=c++20 -O0 -g0 -c /tmp/sutro-bn-stage-582fe8613daf6be1-65534/kernels/centered_halfnorm_small_members_bindings.cpp -o centered_halfnorm_small_members_bindings.o \n[3/3] c++ centered_halfnorm_small_members_bindings.o centered_halfnorm_small_members.cuda.o -shared -L/usr/local/lib/python3.13/site-packages/torch/lib -lc10 -lc10_cuda -ltorch_cpu -ltorch_cuda -ltorch -ltorch_python -L/usr/local/cuda/lib64 -lcudart -o sutro_centered_halfnorm_small_members_bn_stagepack.so\nLT tuned m=10 n=128 k=20000 at=1 bt=1 E=1 candidates=7 winner=0 id=23 tile=11 split=48 us=19.2000\nLT tuned m=4096 n=512 k=128 at=0 bt=0 E=4 candidates=8 winner=4 id=6 tile=18 split=1 us=33.1947\nLT tuned m=4096 n=512 k=512 at=0 bt=0 E=4 candidates=8 winner=0 id=6 tile=20 split=1 us=56.2347\nLT tuned m=4096 n=16 k=512 at=0 bt=1 E=4 candidates=6 winner=2 id=31 tile=15 split=1 us=16.8960\nLT tuned m=512 n=16 k=4096 at=1 bt=1 E=4 candidates=4 winner=2 id=31 tile=15 split=1 us=22.6987\nLT tuned m=4096 n=512 k=16 at=0 bt=0 E=4 candidates=4 winner=0 id=5 tile=24 split=1 us=22.8693\nLT tuned m=512 n=512 k=4096 at=1 bt=1 E=4 candidates=5 winner=3 id=31 tile=18 split=1 us=86.4427\nLT tuned m=4096 n=512 k=512 at=0 bt=1 E=4 candidates=8 winner=0 id=6 tile=20 split=1 us=55.8080\nLT tuned m=512 n=128 k=4096 at=1 bt=1 E=4 candidates=5 winner=2 id=31 tile=15 split=1 us=24.5760\nLT tuned m=20000 n=512 k=128 at=0 bt=0 E=4 candidates=8 winner=0 id=6 tile=20 split=1 us=111.2747\nLT tuned m=20000 n=512 k=512 at=0 bt=0 E=4 candidates=8 winner=0 id=6 tile=20 split=1 us=236.7147\nLT tuned m=20000 n=16 k=512 at=0 bt=1 E=4 candidates=8 winner=0 id=6 tile=17 split=1 us=62.4640\n",
 "record": {
  "version": "mnist-a100/1.2.0 (protections of sutro-mnist-medium/3.0.0, tightened; energy column)",
  "file": "submission.py",
  "function": "classify",
  "source_sha256": "86a1a749f5b12c34be86c2e5025487827bda6b8b20f55fac72bb2911dcaa9066",
  "band_bp": 190,
  "sandboxed": true,
  "holdout": "fashion",
  "device": "NVIDIA A100-SXM4-80GB",
  "torch": "2.12.0+cu130",
  "calls": [
   {
    "dataset": "mnist",
    "ms": 7039.61474609375,
    "parent_ms": 7045.682272000007,
    "correct": 9822,
    "total": 10000,
    "overhead_ms": 2.5185200007702875
   },
   {
    "dataset": "fashion",
    "ms": 7037.44091796875,
    "parent_ms": 7043.586369000024,
    "correct": 8817,
    "total": 10000,
    "overhead_ms": 2.819627498078944
   },
   {
    "dataset": "mnist",
    "ms": 7041.42138671875,
    "parent_ms": 7049.663853999988,
    "correct": 9812,
    "total": 10000,
    "overhead_ms": 2.643639497750769
   },
   {
    "dataset": "mnist",
    "ms": 7036.8623046875,
    "parent_ms": 7043.035307999958,
    "correct": 9794,
    "total": 10000,
    "overhead_ms": 2.5864829993728335
   },
   {
    "dataset": "mnist",
    "ms": 7036.21435546875,
    "parent_ms": 7043.302983000047,
    "correct": 9802,
    "total": 10000,
    "overhead_ms": 2.9842544998186895
   },
   {
    "dataset": "mnist",
    "ms": 7036.54833984375,
    "parent_ms": 7042.501603999995,
    "correct": 9803,
    "total": 10000,
    "overhead_ms": 2.6367094980716956
   },
   {
    "dataset": "fashion",
    "ms": 7035.8642578125,
    "parent_ms": 7041.5885849999995,
    "correct": 8857,
    "total": 10000,
    "overhead_ms": 2.465044000022999
   },
   {
    "dataset": "mnist",
    "ms": 7036.9443359375,
    "parent_ms": 7042.645928999946,
    "correct": 9818,
    "total": 10000,
    "overhead_ms": 2.819404997754191
   },
   {
    "dataset": "mnist",
    "ms": 7038.54296875,
    "parent_ms": 7045.252411999968,
    "correct": 9789,
    "total": 10000,
    "overhead_ms": 2.8249289987184056
   },
   {
    "dataset": "fashion",
    "ms": 7039.6396484375,
    "parent_ms": 7048.707512999954,
    "correct": 8856,
    "total": 10000,
    "overhead_ms": 3.7759439985943573
   },
   {
    "dataset": "mnist",
    "ms": 7037.5791015625,
    "parent_ms": 7044.459147999987,
    "correct": 9817,
    "total": 10000,
    "overhead_ms": 4.446971999663674
   },
   {
    "dataset": "mnist",
    "ms": 7036.8994140625,
    "parent_ms": 7043.455254000037,
    "correct": 9805,
    "total": 10000,
    "overhead_ms": 4.150170502962737
   },
   {
    "dataset": "mnist",
    "ms": 7036.3994140625,
    "parent_ms": 7042.424553000046,
    "correct": 9804,
    "total": 10000,
    "overhead_ms": 2.8026700013174377
   },
   {
    "dataset": "mnist",
    "ms": 7036.125,
    "parent_ms": 7042.356558999927,
    "correct": 9807,
    "total": 10000,
    "overhead_ms": 3.1572414994279825
   },
   {
    "dataset": "fashion",
    "ms": 7039.892578125,
    "parent_ms": 7046.387574999926,
    "correct": 8756,
    "total": 10000,
    "overhead_ms": 2.667214498966132
   }
  ],
  "problems": [
   "MNIST accuracy 98.066% (107,873/110,000); the band needs 107,910 correct"
  ],
  "summary": "MNIST 98.07% (107,873/110,000), 7037.559 ms/call; hold-out (fashion) 88.22%, 7038.209 ms/call",
  "ranked_ms": null
 }
}
