Package evaluation of Tsunami on Julia 1.11.4 (a71dd056e0*) started at 2025-04-08T19:06:15.549 ################################################################################ # Set-up # Installing PkgEval dependencies (TestEnv)... Set-up completed after 8.32s ################################################################################ # Installation # Installing Tsunami... Resolving package versions... Updating `~/.julia/environments/v1.11/Project.toml` [36e41bbe] + Tsunami v0.3.0 Updating `~/.julia/environments/v1.11/Manifest.toml` [621f4979] + AbstractFFTs v1.5.0 [7d9f7c33] + Accessors v0.1.42 [79e6a3ab] + Adapt v4.3.0 [66dad0bd] + AliasTables v1.1.3 [dce04be8] + ArgCheck v2.5.0 [a9b6321e] + Atomix v1.1.1 [ab4f0b2a] + BFloat16s v0.5.1 [fbb218c0] + BSON v0.3.9 [198e06fe] + BangBang v0.4.4 [9718e550] + Baselet v0.1.1 [e1450e63] + BufferedStreams v1.2.2 [082447d4] + ChainRules v1.72.3 [d360d2e6] + ChainRulesCore v1.25.1 [3da002f7] + ColorTypes v0.12.1 [c3611d14] + ColorVectorSpace v0.11.0 [5ae59095] + Colors v0.13.0 [bbf7d656] + CommonSubexpressions v0.3.1 [34da2185] + Compat v4.16.0 [a33af91c] + CompositionsBase v0.1.2 [187b0558] + ConstructionBase v1.5.8 [6add18c4] + ContextVariablesX v0.1.3 [a8cc5b0e] + Crayons v4.1.1 [9a962f9c] + DataAPI v1.16.0 [864edb3b] + DataStructures v0.18.22 [e2d170a0] + DataValueInterfaces v1.0.0 [244e2a9f] + DefineSingletons v0.1.2 [8bb1440f] + DelimitedFiles v1.9.1 [163ba53b] + DiffResults v1.1.0 [b552c78f] + DiffRules v1.15.1 [ffbed154] + DocStringExtensions v0.9.4 [4e289a0a] + EnumX v1.0.5 [f151be2c] + EnzymeCore v0.8.8 [cc61a311] + FLoops v0.2.2 [b9860ae5] + FLoopsBase v0.1.1 [5789e2e9] + FileIO v1.17.0 [1a297f60] + FillArrays v1.13.0 [53c48c17] + FixedPointNumbers v0.8.5 [587475ba] + Flux v0.16.3 [f6369f11] + ForwardDiff v1.0.1 [d9f16b24] + Functors v0.5.2 [46192b85] + GPUArraysCore v0.2.0 [076d061b] + HashArrayMappedTries v0.2.0 [7869d1d1] + IRTools v0.4.14 [a09fc81d] + ImageCore v0.10.5 [22cec73e] + InitialValues v0.3.1 [3587e190] + InverseFunctions v0.1.17 [92d709cd] + IrrationalConstants v0.2.4 [82899510] + IteratorInterfaceExtensions v1.0.0 [033835bb] + JLD2 v0.5.12 [692b3bcd] + JLLWrappers v1.7.0 [b14d175d] + JuliaVariables v0.2.4 [63c18a36] + KernelAbstractions v0.9.34 [2ab3a3ac] + LogExpFunctions v0.3.29 [c2834f40] + MLCore v1.0.0 [7e8f7934] + MLDataDevices v1.9.1 [d8e11817] + MLStyle v0.4.17 [f1d291b0] + MLUtils v0.4.8 [1914dd2f] + MacroTools v0.5.15 [dbb5928d] + MappedArrays v0.4.2 [128add7d] + MicroCollections v0.2.0 [e1d29d7a] + Missings v1.2.0 [e94cdb99] + MosaicViews v0.3.4 [872c559c] + NNlib v0.9.30 [77ba4419] + NaNMath v1.1.3 [71a1bf82] + NameResolution v0.1.5 [6fe1bfb0] + OffsetArrays v1.16.0 [0b1bfda6] + OneHotArrays v0.2.7 [3bd65402] + Optimisers v0.4.6 [bac558e1] + OrderedCollections v1.8.0 [5432bcbf] + PaddedViews v0.5.12 ⌅ [aea7be01] + PrecompileTools v1.2.1 [21216c6a] + Preferences v1.4.3 [8162dcfd] + PrettyPrint v0.2.0 [33c8b6b6] + ProgressLogging v0.1.4 [3349acd9] + ProtoBuf v1.1.1 [43287f4e] + PtrArrays v1.3.0 [c1ae055f] + RealDot v0.1.0 [189a3867] + Reexport v1.2.2 [ae029012] + Requires v1.3.1 [7e506255] + ScopedValues v1.3.0 [efcf1570] + Setfield v1.1.2 [605ecd9f] + ShowCases v0.1.0 [699a6c99] + SimpleTraits v0.9.4 [a2af1166] + SortingAlgorithms v1.2.1 [dc90abb0] + SparseInverseSubset v0.1.2 [276daf66] + SpecialFunctions v2.5.0 [171d559e] + SplittablesBase v0.1.15 [cae243ae] + StackViews v0.1.1 [90137ffa] + StaticArrays v1.9.13 [1e83bf80] + StaticArraysCore v1.4.3 [10745b16] + Statistics v1.11.1 [82ae8749] + StatsAPI v1.7.0 [2913bbd2] + StatsBase v0.34.4 [09ab397b] + StructArrays v0.7.1 [3783bdb8] + TableTraits v1.0.1 [bd369af6] + Tables v1.12.0 [899adc3e] + TensorBoardLogger v0.1.25 [62fd8b95] + TensorCore v0.1.1 [3bb67fe8] + TranscodingStreams v0.11.3 [28d57a85] + Transducers v0.4.84 [36e41bbe] + Tsunami v0.3.0 [3a884ed6] + UnPack v1.0.2 [013be700] + UnsafeAtomics v0.3.0 [e88e6eb3] + Zygote v0.7.6 [700de1a5] + ZygoteRules v0.2.7 [efe28fd5] + OpenSpecFun_jll v0.5.6+0 [0dad84c5] + ArgTools v1.1.2 [56f22d72] + Artifacts v1.11.0 [2a0f44e3] + Base64 v1.11.0 [8bf52ea8] + CRC32c v1.11.0 [ade2ca70] + Dates v1.11.0 [8ba89e20] + Distributed v1.11.0 [f43a241f] + Downloads v1.6.0 [7b1f6079] + FileWatching v1.11.0 [9fa8497b] + Future v1.11.0 [b77e0a4c] + InteractiveUtils v1.11.0 [b27032c2] + LibCURL v0.6.4 [76f85450] + LibGit2 v1.11.0 [8f399da3] + Libdl v1.11.0 [37e2e46d] + LinearAlgebra v1.11.0 [56ddb016] + Logging v1.11.0 [d6f4376e] + Markdown v1.11.0 [a63ad114] + Mmap v1.11.0 [ca575930] + NetworkOptions v1.2.0 [44cfe95a] + Pkg v1.11.0 [de0858da] + Printf v1.11.0 [9a3f8284] + Random v1.11.0 [ea8e919c] + SHA v0.7.0 [9e88b42a] + Serialization v1.11.0 [6462fe0b] + Sockets v1.11.0 [2f01184e] + SparseArrays v1.11.0 [4607b0f0] + SuiteSparse [fa267f1f] + TOML v1.0.3 [a4e569a6] + Tar v1.10.0 [8dfed614] + Test v1.11.0 [cf7118a7] + UUIDs v1.11.0 [4ec0a83e] + Unicode v1.11.0 [e66e0078] + CompilerSupportLibraries_jll v1.1.1+0 [deac9b47] + LibCURL_jll v8.6.0+0 [e37daf67] + LibGit2_jll v1.7.2+0 [29816b5a] + LibSSH2_jll v1.11.0+1 [c8ffd9c3] + MbedTLS_jll v2.28.6+0 [14a3606d] + MozillaCACerts_jll v2023.12.12 [4536629a] + OpenBLAS_jll v0.3.27+1 [05823500] + OpenLibm_jll v0.8.5+0 [bea87d4a] + SuiteSparse_jll v7.7.0+0 [83775a58] + Zlib_jll v1.2.13+1 [8e850b90] + libblastrampoline_jll v5.11.0+0 [8e850ede] + nghttp2_jll v1.59.0+0 [3f19e933] + p7zip_jll v17.4.0+2 Info Packages marked with ⌅ have new versions available but compatibility constraints restrict them from upgrading. To see why use `status --outdated -m` Installation completed after 4.14s ################################################################################ # Precompilation # Precompiling PkgEval dependencies... Precompiling package dependencies... Precompilation completed after 219.45s ################################################################################ # Testing # Testing Tsunami Status `/tmp/jl_pIfATj/Project.toml` [a93c6f00] DataFrames v1.7.0 [7da242da] Enzyme v0.13.35 [587475ba] Flux v0.16.3 [d9f16b24] Functors v0.5.2 [7e8f7934] MLDataDevices v1.9.1 [eb30cadb] MLDatasets v0.7.18 [f1d291b0] MLUtils v0.4.8 [3bd65402] Optimisers v0.4.6 [d7d3b36b] ParameterSchedulers v0.4.3 [189a3867] Reexport v1.2.2 [10745b16] Statistics v1.11.1 [f8b46487] TestItemRunner v1.1.0 [1c621080] TestItems v1.0.0 [36e41bbe] Tsunami v0.3.0 [44cfe95a] Pkg v1.11.0 [9a3f8284] Random v1.11.0 [8dfed614] Test v1.11.0 Status `/tmp/jl_pIfATj/Manifest.toml` [621f4979] AbstractFFTs v1.5.0 [7d9f7c33] Accessors v0.1.42 [79e6a3ab] Adapt v4.3.0 [66dad0bd] AliasTables v1.1.3 [dce04be8] ArgCheck v2.5.0 [4c555306] ArrayLayouts v1.11.1 [a9b6321e] Atomix v1.1.1 [a963bdd2] AtomsBase v0.5.1 [ab4f0b2a] BFloat16s v0.5.1 [fbb218c0] BSON v0.3.9 [198e06fe] BangBang v0.4.4 [9718e550] Baselet v0.1.1 [d1d4a3ce] BitFlags v0.1.9 [e1450e63] BufferedStreams v1.2.2 [fa961155] CEnum v0.5.0 [336ed68f] CSV v0.10.15 [082447d4] ChainRules v1.72.3 [d360d2e6] ChainRulesCore v1.25.1 [46823bd8] Chemfiles v0.10.42 [944b1d66] CodecZlib v0.7.8 [35d6a980] ColorSchemes v3.29.0 [3da002f7] ColorTypes v0.12.1 [c3611d14] ColorVectorSpace v0.11.0 [5ae59095] Colors v0.13.0 [bbf7d656] CommonSubexpressions v0.3.1 [34da2185] Compat v4.16.0 [a33af91c] CompositionsBase v0.1.2 [f0e56b4a] ConcurrentUtilities v2.5.0 [187b0558] ConstructionBase v1.5.8 [6add18c4] ContextVariablesX v0.1.3 [a8cc5b0e] Crayons v4.1.1 [9a962f9c] DataAPI v1.16.0 [124859b0] DataDeps v0.7.13 [a93c6f00] DataFrames v1.7.0 [864edb3b] DataStructures v0.18.22 [e2d170a0] DataValueInterfaces v1.0.0 [244e2a9f] DefineSingletons v0.1.2 [8bb1440f] DelimitedFiles v1.9.1 [163ba53b] DiffResults v1.1.0 [b552c78f] DiffRules v1.15.1 [ffbed154] DocStringExtensions v0.9.4 [4e289a0a] EnumX v1.0.5 [7da242da] Enzyme v0.13.35 [f151be2c] EnzymeCore v0.8.8 [460bff9d] ExceptionUnwrapping v0.1.11 [e2ba6199] ExprTools v0.1.10 [cc61a311] FLoops v0.2.2 [b9860ae5] FLoopsBase v0.1.1 [5789e2e9] FileIO v1.17.0 [48062228] FilePathsBase v0.9.24 [1a297f60] FillArrays v1.13.0 [53c48c17] FixedPointNumbers v0.8.5 [587475ba] Flux v0.16.3 [f6369f11] ForwardDiff v1.0.1 [d9f16b24] Functors v0.5.2 [46192b85] GPUArraysCore v0.2.0 [61eb1bfa] GPUCompiler v1.3.2 [92fee26a] GZip v0.6.2 [c27321d9] Glob v1.3.1 [f67ccb44] HDF5 v0.17.2 [cd3eb016] HTTP v1.10.15 [076d061b] HashArrayMappedTries v0.2.0 [7869d1d1] IRTools v0.4.14 [c817782e] ImageBase v0.1.7 [a09fc81d] ImageCore v0.10.5 [4e3cecfd] ImageShow v0.3.8 ⌅ [4858937d] InfiniteArrays v0.14.4 [e1ba4f0e] Infinities v0.1.11 [22cec73e] InitialValues v0.3.1 [842dd82b] InlineStrings v1.4.3 [7d512f48] InternedStrings v0.7.0 [3587e190] InverseFunctions v0.1.17 [41ab1584] InvertedIndices v1.3.1 [92d709cd] IrrationalConstants v0.2.4 [82899510] IteratorInterfaceExtensions v1.0.0 [033835bb] JLD2 v0.5.12 [692b3bcd] JLLWrappers v1.7.0 [0f8b85d8] JSON3 v1.14.2 [b14d175d] JuliaVariables v0.2.4 [63c18a36] KernelAbstractions v0.9.34 [929cbde3] LLVM v9.2.0 [b964fa9f] LaTeXStrings v1.4.0 [5078a376] LazyArrays v2.6.1 [8cdb02fc] LazyModules v0.3.1 [2ab3a3ac] LogExpFunctions v0.3.29 [e6f89c97] LoggingExtras v1.1.0 [23992714] MAT v0.10.7 [c2834f40] MLCore v1.0.0 [7e8f7934] MLDataDevices v1.9.1 [eb30cadb] MLDatasets v0.7.18 [d8e11817] MLStyle v0.4.17 [f1d291b0] MLUtils v0.4.8 [3da0fdf6] MPIPreferences v0.1.11 [1914dd2f] MacroTools v0.5.15 [dbb5928d] MappedArrays v0.4.2 [739be429] MbedTLS v1.1.9 [128add7d] MicroCollections v0.2.0 [e1d29d7a] Missings v1.2.0 [e94cdb99] MosaicViews v0.3.4 [872c559c] NNlib v0.9.30 [15e1cf62] NPZ v0.4.3 [77ba4419] NaNMath v1.1.3 [71a1bf82] NameResolution v0.1.5 [d8793406] ObjectFile v0.4.4 [6fe1bfb0] OffsetArrays v1.16.0 [0b1bfda6] OneHotArrays v0.2.7 [4d8831e6] OpenSSL v1.4.3 [3bd65402] Optimisers v0.4.6 [bac558e1] OrderedCollections v1.8.0 [65ce6f38] PackageExtensionCompat v1.0.2 [5432bcbf] PaddedViews v0.5.12 [d7d3b36b] ParameterSchedulers v0.4.3 [69de0a69] Parsers v2.8.1 [7b2266bf] PeriodicTable v1.2.1 [fbb45041] Pickle v0.3.5 [2dfb63ee] PooledArrays v1.4.3 ⌅ [aea7be01] PrecompileTools v1.2.1 [21216c6a] Preferences v1.4.3 [8162dcfd] PrettyPrint v0.2.0 [08abe8d2] PrettyTables v2.4.0 [33c8b6b6] ProgressLogging v0.1.4 [3349acd9] ProtoBuf v1.1.1 [43287f4e] PtrArrays v1.3.0 [c1ae055f] RealDot v0.1.0 [189a3867] Reexport v1.2.2 [ae029012] Requires v1.3.1 [7e506255] ScopedValues v1.3.0 [6c6a2e73] Scratch v1.2.1 [91c51154] SentinelArrays v1.4.8 [efcf1570] Setfield v1.1.2 [605ecd9f] ShowCases v0.1.0 [777ac1f9] SimpleBufferStream v1.2.0 [699a6c99] SimpleTraits v0.9.4 [a2af1166] SortingAlgorithms v1.2.1 [dc90abb0] SparseInverseSubset v0.1.2 [276daf66] SpecialFunctions v2.5.0 [171d559e] SplittablesBase v0.1.15 [cae243ae] StackViews v0.1.1 [90137ffa] StaticArrays v1.9.13 [1e83bf80] StaticArraysCore v1.4.3 [10745b16] Statistics v1.11.1 [82ae8749] StatsAPI v1.7.0 [2913bbd2] StatsBase v0.34.4 ⌅ [4db3bf67] StridedViews v0.2.2 [69024149] StringEncodings v0.3.7 [892a3eda] StringManipulation v0.4.1 [09ab397b] StructArrays v0.7.1 [53d494c1] StructIO v0.3.1 [856f2bd8] StructTypes v1.11.0 [3783bdb8] TableTraits v1.0.1 [bd369af6] Tables v1.12.0 [899adc3e] TensorBoardLogger v0.1.25 [62fd8b95] TensorCore v0.1.1 [f8b46487] TestItemRunner v1.1.0 [1c621080] TestItems v1.0.0 [a759f4b9] TimerOutputs v0.5.28 [3bb67fe8] TranscodingStreams v0.11.3 [28d57a85] Transducers v0.4.84 [36e41bbe] Tsunami v0.3.0 [5c2747f8] URIs v1.5.2 [3a884ed6] UnPack v1.0.2 [1986cc42] Unitful v1.22.0 [a7773ee8] UnitfulAtomic v1.0.0 [013be700] UnsafeAtomics v0.3.0 [ea10d353] WeakRefStrings v1.4.2 [76eceee3] WorkerUtilities v1.6.1 [a5390f91] ZipFile v0.10.1 [e88e6eb3] Zygote v0.7.6 [700de1a5] ZygoteRules v0.2.7 [78a364fa] Chemfiles_jll v0.10.4+0 [7cc45869] Enzyme_jll v0.0.173+0 [0234f1f7] HDF5_jll v1.14.6+0 [e33a78d0] Hwloc_jll v2.12.0+0 [dad2f222] LLVMExtra_jll v0.0.35+0 [94ce4f54] Libiconv_jll v1.18.0+0 [7cb0a576] MPICH_jll v4.3.0+1 [f1f71cc9] MPItrampoline_jll v5.5.3+0 [9237b28f] MicrosoftMPI_jll v10.1.4+3 [fe0851c0] OpenMPI_jll v5.0.7+2 [458c3c95] OpenSSL_jll v3.0.16+0 [efe28fd5] OpenSpecFun_jll v0.5.6+0 [477f73a3] libaec_jll v1.1.3+0 [0dad84c5] ArgTools v1.1.2 [56f22d72] Artifacts v1.11.0 [2a0f44e3] Base64 v1.11.0 [8bf52ea8] CRC32c v1.11.0 [ade2ca70] Dates v1.11.0 [8ba89e20] Distributed v1.11.0 [f43a241f] Downloads v1.6.0 [7b1f6079] FileWatching v1.11.0 [9fa8497b] Future v1.11.0 [b77e0a4c] InteractiveUtils v1.11.0 [4af54fe1] LazyArtifacts v1.11.0 [b27032c2] LibCURL v0.6.4 [76f85450] LibGit2 v1.11.0 [8f399da3] Libdl v1.11.0 [37e2e46d] LinearAlgebra v1.11.0 [56ddb016] Logging v1.11.0 [d6f4376e] Markdown v1.11.0 [a63ad114] Mmap v1.11.0 [ca575930] NetworkOptions v1.2.0 [44cfe95a] Pkg v1.11.0 [de0858da] Printf v1.11.0 [9a3f8284] Random v1.11.0 [ea8e919c] SHA v0.7.0 [9e88b42a] Serialization v1.11.0 [6462fe0b] Sockets v1.11.0 [2f01184e] SparseArrays v1.11.0 [4607b0f0] SuiteSparse [fa267f1f] TOML v1.0.3 [a4e569a6] Tar v1.10.0 [8dfed614] Test v1.11.0 [cf7118a7] UUIDs v1.11.0 [4ec0a83e] Unicode v1.11.0 [e66e0078] CompilerSupportLibraries_jll v1.1.1+0 [deac9b47] LibCURL_jll v8.6.0+0 [e37daf67] LibGit2_jll v1.7.2+0 [29816b5a] LibSSH2_jll v1.11.0+1 [c8ffd9c3] MbedTLS_jll v2.28.6+0 [14a3606d] MozillaCACerts_jll v2023.12.12 [4536629a] OpenBLAS_jll v0.3.27+1 [05823500] OpenLibm_jll v0.8.5+0 [bea87d4a] SuiteSparse_jll v7.7.0+0 [83775a58] Zlib_jll v1.2.13+1 [8e850b90] libblastrampoline_jll v5.11.0+0 [8e850ede] nghttp2_jll v1.59.0+0 [3f19e933] p7zip_jll v17.4.0+2 Info Packages marked with ⌅ have new versions available but compatibility constraints restrict them from upgrading. Testing Running tests... Precompiling FluxEnzymeExt... 20786.3 ms ✓ Enzyme → EnzymeSpecialFunctionsExt 19897.1 ms ✓ Enzyme → EnzymeLogExpFunctionsExt 72400.7 ms ✓ Flux → FluxEnzymeExt 3 dependencies successfully precompiled in 117 seconds. 183 already precompiled. Precompiling EnzymeBFloat16sExt... 19896.9 ms ✓ Enzyme → EnzymeBFloat16sExt 1 dependency successfully precompiled in 20 seconds. 46 already precompiled. ┌ Warning: No functional GPU backend found! Defaulting to CPU. │ │ 1. If no GPU is available, nothing needs to be done. Set `MLDATADEVICES_SILENCE_WARN_NO_GPU=1` to silence this warning. │ 2. If GPU is available, load the corresponding trigger package. │ a. `CUDA.jl` and `cuDNN.jl` (or just `LuxCUDA.jl`) for NVIDIA CUDA Support. │ b. `AMDGPU.jl` for AMD GPU ROCM Support. │ c. `Metal.jl` for Apple Metal GPU Support. (Experimental) │ d. `oneAPI.jl` for Intel oneAPI GPU Support. (Experimental) └ @ MLDataDevices.Internal ~/.julia/packages/MLDataDevices/lMKtX/src/internal.jl:96 [ Info: GPUs available: false, used: false [ Info: Model Summary: LinearModel() # 1_000 parameters, plus 1_000 non-trainable [ Info: Run Directory: /home/pkgeval/.julia/packages/Tsunami/AMGDr/test/tsunami_logs/run_1 [ Info: GPUs available: false, used: false [ Info: Model Summary: TBLoggingModule( Chain( Dense(4 => 3, relu), # 15 parameters Dense(3 => 2), # 8 parameters ), true, true, true, true, ) # Total: 4 arrays, 23 parameters, 316 bytes. [ Info: Run Directory: /home/pkgeval/.julia/packages/Tsunami/AMGDr/test/tsunami_logs/run_1 Train Epoch 1: 50%|███████████ | ETA: 0:00:20 (20.89 s/it) train/batch_idx_step: 1 train/loss_step: 2.56     Train Epoch 1: 100%|██████████████████████| Time: 0:00:21 (10.99 s/it) train/batch_idx_step: 2 train/loss_step: 0.461   Train Epoch 2: 100%|██████████████████████| Time: 0:00:00 ( 0.62 ms/it) train/batch_idx_step: 2 train/loss_step: 0.455   Train Epoch 3: 100%|██████████████████████| Time: 0:00:00 ( 0.47 ms/it) train/batch_idx_step: 2 train/loss_step: 0.45   Train Epoch 4: 100%|██████████████████████| Time: 0:00:00 ( 0.42 ms/it) train/batch_idx_step: 2 train/loss_step: 0.444 [ Info: GPUs available: false, used: false [ Info: Model Summary: TestModule1( Chain( Dense(4 => 3, relu), # 15 parameters Dense(3 => 2), # 8 parameters ), 1, 2, ) # Total: 4 arrays, 23 parameters, 324 bytes. [ Info: Run Directory: /home/pkgeval/.julia/packages/Tsunami/AMGDr/test/tsunami_logs/run_2 [ Info: GPUs available: false, used: false [ Info: Model Summary: TestModule1( Chain( Dense(4 => 3, relu), # 15 parameters Dense(3 => 2), # 8 parameters ), 1, 2, ) # Total: 4 arrays, 23 parameters, 324 bytes. [ Info: Run Directory: /home/pkgeval/.julia/packages/Tsunami/AMGDr/test/tsunami_logs/run_2 [ Info: GPUs available: false, used: false [ Info: Model Summary: TestModule1( Chain( Dense(4 => 3, relu), # 15 parameters Dense(3 => 2), # 8 parameters ), 1, 2, ) # Total: 4 arrays, 23 parameters, 324 bytes. [ Info: Run Directory: /home/pkgeval/.julia/packages/Tsunami/AMGDr/test/tsunami_logs/run_2 [ Info: GPUs available: false, used: false [ Info: Model Summary: TestModule1( Chain( Dense(4 => 3, relu), # 15 parameters BatchNorm(3), # 6 parameters, plus 6 Dense(3 => 2), # 8 parameters ), 1, 2, ) # Total: 6 trainable arrays, 29 parameters, # plus 2 non-trainable, 6 parameters, summarysize 596 bytes. [ Info: Run Directory: /home/pkgeval/.julia/packages/Tsunami/AMGDr/test/tsunami_logs/run_2 [ Info: GPUs available: false, used: false [ Info: Model Summary: TestModule1( Chain( Dense(4 => 3, relu), # 15 parameters Dense(3 => 2), # 8 parameters ), 1, 2, ) # Total: 4 arrays, 23 parameters, 324 bytes. [ Info: Run Directory: /home/pkgeval/.julia/packages/Tsunami/AMGDr/test/tsunami_logs/run_2 Train Epoch 1: 100%|██████████████████████| Time: 0:00:00 ( 0.52 ms/it) Train Epoch 2: 100%|██████████████████████| Time: 0:00:00 ( 0.42 ms/it) [ Info: GPUs available: false, used: false [ Info: Model Summary: TestModule1( Chain( Dense(4 => 3, relu), # 15 parameters Dense(3 => 2), # 8 parameters ), 1, 2, ) # Total: 4 arrays, 23 parameters, 324 bytes. [ Info: Run Directory: /home/pkgeval/.julia/packages/Tsunami/AMGDr/test/tsunami_logs/run_3 Train Epoch 1: 100%|██████████████████████| Time: 0:00:00 ( 0.37 ms/it) Train Epoch 2: 100%|██████████████████████| Time: 0:00:00 ( 0.37 ms/it) [ Info: GPUs available: false, used: false [ Info: Model Summary: TestModule1( Chain( Dense(4 => 3, relu), # 15 parameters Dense(3 => 2), # 8 parameters ), 1, 2, ) # Total: 4 arrays, 23 parameters, 324 bytes. [ Info: Run Directory: /home/pkgeval/.julia/packages/Tsunami/AMGDr/test/tsunami_logs/run_2 [ Info: GPUs available: false, used: false [ Info: Model Summary: TestModule1( Chain( Dense(4 => 3, relu), # 15 parameters Dense(3 => 2), # 8 parameters ), 1, 2, ) # Total: 4 arrays, 23 parameters, 324 bytes. [ Info: Run Directory: /home/pkgeval/.julia/packages/Tsunami/AMGDr/test/tsunami_logs/run_2 [ Info: GPUs available: false, used: false [ Info: Model Summary: TestModule1( Chain( Dense(4 => 3, relu), # 15 parameters Dense(3 => 2), # 8 parameters ), 1, 2, ) # Total: 4 arrays, 23 parameters, 324 bytes. [ Info: Run Directory: /home/pkgeval/.julia/packages/Tsunami/AMGDr/test/tsunami_logs/run_2 Testing: 100%|████████████████████████████| Time: 0:00:00 ( 6.54 ms/it) a: 1.0 b: 2.0 Validation: 100%|█████████████████████████| Time: 0:00:00 ( 6.77 ms/it) a: 1.0 b: 2.0 [ Info: GPUs available: false, used: false [ Info: Model Summary: TestModule1( Chain( Dense(4 => 3, relu), # 15 parameters Dense(3 => 2), # 8 parameters ), 1, 2, ) # Total: 4 arrays, 23 parameters, 324 bytes. [ Info: Run Directory: /home/pkgeval/.julia/packages/Tsunami/AMGDr/test/tsunami_logs/run_2 Train Epoch 1: 50%|███████████ | ETA: 0:00:28 (28.96 s/it) Train Epoch 1: 100%|██████████████████████| Time: 0:00:28 (14.48 s/it) Train Epoch 2: 100%|██████████████████████| Time: 0:00:00 ( 0.52 ms/it) [ Info: GPUs available: false, used: false [ Info: Model Summary: LinearModel() # 1_000 parameters, plus 1_000 non-trainable [ Info: Run Directory: /home/pkgeval/.julia/packages/Tsunami/AMGDr/test/tsunami_logs/run_3 ┌ Warning: TODO forward zero-set of memorycopy used memset rather than runtime type │ Caused by: │ Stacktrace: │ [1] copy │ @ ./array.jl:350 │ [2] unaliascopy │ @ ./abstractarray.jl:1516 │ [3] unalias │ @ ./abstractarray.jl:1500 │ [4] broadcast_unalias │ @ ./broadcast.jl:946 │ [5] preprocess │ @ ./broadcast.jl:953 │ [6] preprocess_args │ @ ./broadcast.jl:956 │ [7] preprocess_args │ @ ./broadcast.jl:955 │ [8] preprocess │ @ ./broadcast.jl:952 │ [9] preprocess_args │ @ ./broadcast.jl:956 │ [10] preprocess │ @ ./broadcast.jl:952 │ [11] override_bc_copyto! │ @ ~/.julia/packages/Enzyme/g1jMR/src/compiler/interpreter.jl:798 │ [12] copyto! │ @ ./broadcast.jl:925 │ [13] copy │ @ ./broadcast.jl:897 │ [14] materialize │ @ ./broadcast.jl:872 │ [15] #mse#12 │ @ ~/.julia/packages/Flux/3711C/src/losses/functions.jl:47 └ @ Enzyme.Compiler ~/.julia/packages/GPUCompiler/2MI6e/src/utils.jl:61 [ Info: GPUs available: false, used: false [ Info: Model Summary: MLP( Chain( Dense(784 => 128, relu), # 100_480 parameters Dense(128 => 10), # 1_290 parameters ), :classification, ) # Total: 4 arrays, 101_770 parameters, 397.750 KiB. [ Info: Run Directory: /home/pkgeval/.julia/packages/Tsunami/AMGDr/test/tsunami_logs/run_3 Precompiling MLDatasets... 1067.0 ms ✓ Chemfiles_jll 5306.3 ms ✓ AtomsBase 5788.9 ms ✓ ImageShow 4536.4 ms ✓ Pickle 5987.5 ms ✓ MAT 5641.1 ms ✓ Chemfiles 27659.0 ms ✓ MLDatasets 7 dependencies successfully precompiled in 60 seconds. 195 already precompiled. [ Info: GPUs available: false, used: false [ Info: Model Summary: MLP( Chain( Dense(784 => 128, relu), # 100_480 parameters Dense(128 => 10), # 1_290 parameters ), :classification, ) # Total: 4 arrays, 101_770 parameters, 397.750 KiB. [ Info: Run Directory: /home/pkgeval/.julia/packages/Tsunami/AMGDr/test/tsunami_logs/run_3 WARNING: Wrapping `Vararg` directly in UnionAll is deprecated (wrap the tuple instead). You may need to write `f(x::Vararg{T})` rather than `f(x::Vararg{<:T})` or `f(x::Vararg{T}) where T` instead of `f(x::Vararg{T} where T)`. WARNING: Wrapping `Vararg` directly in UnionAll is deprecated (wrap the tuple instead). You may need to write `f(x::Vararg{T})` rather than `f(x::Vararg{<:T})` or `f(x::Vararg{T}) where T` instead of `f(x::Vararg{T} where T)`. WARNING: Wrapping `Vararg` directly in UnionAll is deprecated (wrap the tuple instead). You may need to write `f(x::Vararg{T})` rather than `f(x::Vararg{<:T})` or `f(x::Vararg{T}) where T` instead of `f(x::Vararg{T} where T)`. WARNING: Wrapping `Vararg` directly in UnionAll is deprecated (wrap the tuple instead). You may need to write `f(x::Vararg{T})` rather than `f(x::Vararg{<:T})` or `f(x::Vararg{T}) where T` instead of `f(x::Vararg{T} where T)`. WARNING: Wrapping `Vararg` directly in UnionAll is deprecated (wrap the tuple instead). You may need to write `f(x::Vararg{T})` rather than `f(x::Vararg{<:T})` or `f(x::Vararg{T}) where T` instead of `f(x::Vararg{T} where T)`. WARNING: Wrapping `Vararg` directly in UnionAll is deprecated (wrap the tuple instead). You may need to write `f(x::Vararg{T})` rather than `f(x::Vararg{<:T})` or `f(x::Vararg{T}) where T` instead of `f(x::Vararg{T} where T)`. WARNING: Wrapping `Vararg` directly in UnionAll is deprecated (wrap the tuple instead). You may need to write `f(x::Vararg{T})` rather than `f(x::Vararg{<:T})` or `f(x::Vararg{T}) where T` instead of `f(x::Vararg{T} where T)`. WARNING: Wrapping `Vararg` directly in UnionAll is deprecated (wrap the tuple instead). You may need to write `f(x::Vararg{T})` rather than `f(x::Vararg{<:T})` or `f(x::Vararg{T}) where T` instead of `f(x::Vararg{T} where T)`. WARNING: Wrapping `Vararg` directly in UnionAll is deprecated (wrap the tuple instead). You may need to write `f(x::Vararg{T})` rather than `f(x::Vararg{<:T})` or `f(x::Vararg{T}) where T` instead of `f(x::Vararg{T} where T)`. WARNING: Wrapping `Vararg` directly in UnionAll is deprecated (wrap the tuple instead). You may need to write `f(x::Vararg{T})` rather than `f(x::Vararg{<:T})` or `f(x::Vararg{T}) where T` instead of `f(x::Vararg{T} where T)`. WARNING: Wrapping `Vararg` directly in UnionAll is deprecated (wrap the tuple instead). You may need to write `f(x::Vararg{T})` rather than `f(x::Vararg{<:T})` or `f(x::Vararg{T}) where T` instead of `f(x::Vararg{T} where T)`. WARNING: Wrapping `Vararg` directly in UnionAll is deprecated (wrap the tuple instead). You may need to write `f(x::Vararg{T})` rather than `f(x::Vararg{<:T})` or `f(x::Vararg{T}) where T` instead of `f(x::Vararg{T} where T)`. WARNING: Wrapping `Vararg` directly in UnionAll is deprecated (wrap the tuple instead). You may need to write `f(x::Vararg{T})` rather than `f(x::Vararg{<:T})` or `f(x::Vararg{T}) where T` instead of `f(x::Vararg{T} where T)`. WARNING: Wrapping `Vararg` directly in UnionAll is deprecated (wrap the tuple instead). You may need to write `f(x::Vararg{T})` rather than `f(x::Vararg{<:T})` or `f(x::Vararg{T}) where T` instead of `f(x::Vararg{T} where T)`. WARNING: Wrapping `Vararg` directly in UnionAll is deprecated (wrap the tuple instead). You may need to write `f(x::Vararg{T})` rather than `f(x::Vararg{<:T})` or `f(x::Vararg{T}) where T` instead of `f(x::Vararg{T} where T)`. WARNING: Wrapping `Vararg` directly in UnionAll is deprecated (wrap the tuple instead). You may need to write `f(x::Vararg{T})` rather than `f(x::Vararg{<:T})` or `f(x::Vararg{T}) where T` instead of `f(x::Vararg{T} where T)`. WARNING: Wrapping `Vararg` directly in UnionAll is deprecated (wrap the tuple instead). You may need to write `f(x::Vararg{T})` rather than `f(x::Vararg{<:T})` or `f(x::Vararg{T}) where T` instead of `f(x::Vararg{T} where T)`. WARNING: Wrapping `Vararg` directly in UnionAll is deprecated (wrap the tuple instead). You may need to write `f(x::Vararg{T})` rather than `f(x::Vararg{<:T})` or `f(x::Vararg{T}) where T` instead of `f(x::Vararg{T} where T)`. WARNING: Wrapping `Vararg` directly in UnionAll is deprecated (wrap the tuple instead). You may need to write `f(x::Vararg{T})` rather than `f(x::Vararg{<:T})` or `f(x::Vararg{T}) where T` instead of `f(x::Vararg{T} where T)`. WARNING: Wrapping `Vararg` directly in UnionAll is deprecated (wrap the tuple instead). You may need to write `f(x::Vararg{T})` rather than `f(x::Vararg{<:T})` or `f(x::Vararg{T}) where T` instead of `f(x::Vararg{T} where T)`. WARNING: Wrapping `Vararg` directly in UnionAll is deprecated (wrap the tuple instead). You may need to write `f(x::Vararg{T})` rather than `f(x::Vararg{<:T})` or `f(x::Vararg{T}) where T` instead of `f(x::Vararg{T} where T)`. WARNING: Wrapping `Vararg` directly in UnionAll is deprecated (wrap the tuple instead). You may need to write `f(x::Vararg{T})` rather than `f(x::Vararg{<:T})` or `f(x::Vararg{T}) where T` instead of `f(x::Vararg{T} where T)`. WARNING: Wrapping `Vararg` directly in UnionAll is deprecated (wrap the tuple instead). You may need to write `f(x::Vararg{T})` rather than `f(x::Vararg{<:T})` or `f(x::Vararg{T}) where T` instead of `f(x::Vararg{T} where T)`. WARNING: Wrapping `Vararg` directly in UnionAll is deprecated (wrap the tuple instead). You may need to write `f(x::Vararg{T})` rather than `f(x::Vararg{<:T})` or `f(x::Vararg{T}) where T` instead of `f(x::Vararg{T} where T)`. WARNING: Wrapping `Vararg` directly in UnionAll is deprecated (wrap the tuple instead). You may need to write `f(x::Vararg{T})` rather than `f(x::Vararg{<:T})` or `f(x::Vararg{T}) where T` instead of `f(x::Vararg{T} where T)`. WARNING: Wrapping `Vararg` directly in UnionAll is deprecated (wrap the tuple instead). You may need to write `f(x::Vararg{T})` rather than `f(x::Vararg{<:T})` or `f(x::Vararg{T}) where T` instead of `f(x::Vararg{T} where T)`. WARNING: Wrapping `Vararg` directly in UnionAll is deprecated (wrap the tuple instead). You may need to write `f(x::Vararg{T})` rather than `f(x::Vararg{<:T})` or `f(x::Vararg{T}) where T` instead of `f(x::Vararg{T} where T)`. WARNING: Wrapping `Vararg` directly in UnionAll is deprecated (wrap the tuple instead). You may need to write `f(x::Vararg{T})` rather than `f(x::Vararg{<:T})` or `f(x::Vararg{T}) where T` instead of `f(x::Vararg{T} where T)`. WARNING: Wrapping `Vararg` directly in UnionAll is deprecated (wrap the tuple instead). You may need to write `f(x::Vararg{T})` rather than `f(x::Vararg{<:T})` or `f(x::Vararg{T}) where T` instead of `f(x::Vararg{T} where T)`. WARNING: Wrapping `Vararg` directly in UnionAll is deprecated (wrap the tuple instead). You may need to write `f(x::Vararg{T})` rather than `f(x::Vararg{<:T})` or `f(x::Vararg{T}) where T` instead of `f(x::Vararg{T} where T)`. [ Info: GPUs available: false, used: false [ Info: Model Summary: TestModule1( Chain( Dense(4 => 3, relu), # 15 parameters Dense(3 => 2), # 8 parameters ), 1, 2, ) # Total: 4 arrays, 23 parameters, 324 bytes. [ Info: Run Directory: /home/pkgeval/.julia/packages/Tsunami/AMGDr/test/tsunami_logs/run_3 [ Info: GPUs available: false, used: false [ Info: Model Summary: TestModule1( Chain( Dense(4 => 3, relu), # 15 parameters Dense(3 => 2), # 8 parameters ), 1, 2, ) # Total: 4 arrays, 23 parameters, 324 bytes. [ Info: Run Directory: /home/pkgeval/.julia/packages/Tsunami/AMGDr/test/tsunami_logs/run_3 [ Info: GPUs available: false, used: false [ Info: Model Summary: TestModule1( Chain( Dense(4 => 3, relu), # 15 parameters Dense(3 => 2), # 8 parameters ), 1, 2, ) # Total: 4 arrays, 23 parameters, 324 bytes. [ Info: Run Directory: /home/pkgeval/.julia/packages/Tsunami/AMGDr/test/tsunami_logs/run_3 [ Info: GPUs available: false, used: false [ Info: Model Summary: TestModule1( Chain( Dense(4 => 3, relu), # 15 parameters Dense(3 => 2), # 8 parameters ), 1, 2, ) # Total: 4 arrays, 23 parameters, 324 bytes. [ Info: Run Directory: /home/pkgeval/.julia/packages/Tsunami/AMGDr/test/tsunami_logs/run_3 Test Summary: | Pass Total Time Package | 71 71 23m45.4s Precompiling ParameterSchedulers... 2757.1 ms ✓ InfiniteArrays 1926.4 ms ✓ InfiniteArrays → InfiniteArraysStatisticsExt 2355.5 ms ✓ ParameterSchedulers 3 dependencies successfully precompiled in 7 seconds. 26 already precompiled. Precompiling TransducersLazyArraysExt... 2512.1 ms ✓ Transducers → TransducersLazyArraysExt 1 dependency successfully precompiled in 3 seconds. 48 already precompiled. [ Info: GPUs available: false, used: false [ Info: Model Summary: MLP( Chain( MLUtils.flatten, Dense(784 => 256, relu), # 200_960 parameters Dense(256 => 10), # 2_570 parameters ), ) # Total: 4 arrays, 203_530 parameters, 795.242 KiB. [ Info: Run Directory: /home/pkgeval/.julia/packages/Tsunami/AMGDr/test/tsunami_logs/run_3 [ Info: GPUs available: false, used: false [ Info: Model Summary: MLP( Chain( MLUtils.flatten, Dense(784 => 256, relu), # 200_960 parameters Dense(256 => 10), # 2_570 parameters ), ) # Total: 4 arrays, 203_530 parameters, 795.242 KiB. [ Info: Run Directory: /home/pkgeval/.julia/packages/Tsunami/AMGDr/examples/MLP_MNIST/tsunami_logs/run_1 Val Epoch 0: 4%|█ | ETA: 0:00:04 ( 0.11 s/it) accuracy/val: 0.16 loss/val: 2.33     Val Epoch 0: 100%|████████████████████████| Time: 0:00:00 (14.86 ms/it) accuracy/val: 0.119 loss/val: 2.34   Train Epoch 1: 0%| | ETA: 2:19:11 (19.84 s/it) accuracy/train: 0.125 loss/train: 2.31     Train Epoch 1: 2%|▌ | ETA: 0:13:41 ( 2.00 s/it) accuracy/train: 0.828 loss/train: 0.628     Train Epoch 1: 4%|█ | ETA: 0:07:30 ( 1.11 s/it) accuracy/train: 0.906 loss/train: 0.329     Train Epoch 1: 6%|█▍ | ETA: 0:05:07 ( 0.78 s/it) accuracy/train: 0.875 loss/train: 0.484     Train Epoch 1: 8%|█▊ | ETA: 0:04:01 ( 0.62 s/it) accuracy/train: 0.945 loss/train: 0.207     Train Epoch 1: 10%|██▎ | ETA: 0:03:06 ( 0.49 s/it) accuracy/train: 0.93 loss/train: 0.273     Train Epoch 1: 12%|██▋ | ETA: 0:02:34 ( 0.42 s/it) accuracy/train: 0.906 loss/train: 0.223     Train Epoch 1: 14%|███ | ETA: 0:02:10 ( 0.36 s/it) accuracy/train: 0.93 loss/train: 0.229     Train Epoch 1: 16%|███▌ | ETA: 0:01:53 ( 0.32 s/it) accuracy/train: 0.922 loss/train: 0.258     Train Epoch 1: 17%|███▊ | ETA: 0:01:45 ( 0.30 s/it) accuracy/train: 0.945 loss/train: 0.273     Train Epoch 1: 19%|████▎ | ETA: 0:01:31 ( 0.27 s/it) accuracy/train: 0.953 loss/train: 0.214     Train Epoch 1: 22%|████▊ | ETA: 0:01:20 ( 0.24 s/it) accuracy/train: 0.898 loss/train: 0.344     Train Epoch 1: 24%|█████▎ | ETA: 0:01:11 ( 0.22 s/it) accuracy/train: 0.938 loss/train: 0.201     Train Epoch 1: 26%|█████▋ | ETA: 0:01:04 ( 0.21 s/it) accuracy/train: 0.922 loss/train: 0.213     Train Epoch 1: 28%|██████▏ | ETA: 0:00:58 ( 0.19 s/it) accuracy/train: 0.906 loss/train: 0.237     Train Epoch 1: 30%|██████▌ | ETA: 0:00:53 ( 0.18 s/it) accuracy/train: 0.945 loss/train: 0.164     Train Epoch 1: 31%|██████▉ | ETA: 0:00:49 ( 0.17 s/it) accuracy/train: 0.93 loss/train: 0.25     Train Epoch 1: 33%|███████▎ | ETA: 0:00:46 ( 0.16 s/it) accuracy/train: 0.945 loss/train: 0.159     Train Epoch 1: 35%|███████▋ | ETA: 0:00:42 ( 0.16 s/it) accuracy/train: 0.938 loss/train: 0.193     Train Epoch 1: 37%|████████▏ | ETA: 0:00:39 ( 0.15 s/it) accuracy/train: 0.953 loss/train: 0.135     Train Epoch 1: 38%|████████▌ | ETA: 0:00:37 ( 0.14 s/it) accuracy/train: 0.938 loss/train: 0.208     Train Epoch 1: 40%|████████▉ | ETA: 0:00:34 ( 0.14 s/it) accuracy/train: 0.984 loss/train: 0.104     Train Epoch 1: 42%|█████████▎ | ETA: 0:00:32 ( 0.13 s/it) accuracy/train: 0.977 loss/train: 0.131     Train Epoch 1: 44%|█████████▊ | ETA: 0:00:29 ( 0.13 s/it) accuracy/train: 0.93 loss/train: 0.182     Train Epoch 1: 46%|██████████▏ | ETA: 0:00:27 ( 0.12 s/it) accuracy/train: 0.945 loss/train: 0.182     Train Epoch 1: 48%|██████████▌ | ETA: 0:00:25 ( 0.12 s/it) accuracy/train: 0.93 loss/train: 0.287     Train Epoch 1: 50%|███████████ | ETA: 0:00:24 ( 0.11 s/it) accuracy/train: 0.938 loss/train: 0.218     Train Epoch 1: 52%|███████████▍ | ETA: 0:00:22 ( 0.11 s/it) accuracy/train: 0.93 loss/train: 0.25     Train Epoch 1: 54%|███████████▊ | ETA: 0:00:20 ( 0.11 s/it) accuracy/train: 0.961 loss/train: 0.216     Train Epoch 1: 55%|████████████▎ | ETA: 0:00:19 ( 0.10 s/it) accuracy/train: 0.961 loss/train: 0.0953     Train Epoch 1: 58%|████████████▋ | ETA: 0:00:17 ( 0.10 s/it) accuracy/train: 0.938 loss/train: 0.23     Train Epoch 1: 60%|█████████████▏ | ETA: 0:00:16 (96.84 ms/it) accuracy/train: 0.93 loss/train: 0.212     Train Epoch 1: 62%|█████████████▋ | ETA: 0:00:15 (93.92 ms/it) accuracy/train: 0.945 loss/train: 0.103     Train Epoch 1: 64%|██████████████▏ | ETA: 0:00:13 (91.20 ms/it) accuracy/train: 0.969 loss/train: 0.119     Train Epoch 1: 66%|██████████████▌ | ETA: 0:00:12 (88.66 ms/it) accuracy/train: 0.93 loss/train: 0.239     Train Epoch 1: 68%|██████████████▉ | ETA: 0:00:11 (86.86 ms/it) accuracy/train: 0.969 loss/train: 0.171     Train Epoch 1: 69%|███████████████▎ | ETA: 0:00:10 (85.14 ms/it) accuracy/train: 0.953 loss/train: 0.168     Train Epoch 1: 72%|███████████████▊ | ETA: 0:00:09 (82.97 ms/it) accuracy/train: 0.961 loss/train: 0.0952     Train Epoch 1: 74%|████████████████▎ | ETA: 0:00:08 (80.92 ms/it) accuracy/train: 0.953 loss/train: 0.133     Train Epoch 1: 76%|████████████████▋ | ETA: 0:00:08 (79.21 ms/it) accuracy/train: 0.984 loss/train: 0.0472     Train Epoch 1: 78%|█████████████████▏ | ETA: 0:00:07 (77.37 ms/it) accuracy/train: 0.953 loss/train: 0.0851     Train Epoch 1: 80%|█████████████████▋ | ETA: 0:00:06 (75.63 ms/it) accuracy/train: 0.93 loss/train: 0.164     Train Epoch 1: 82%|█████████████████▉ | ETA: 0:00:05 (74.39 ms/it) accuracy/train: 0.945 loss/train: 0.18     Train Epoch 1: 84%|██████████████████▍ | ETA: 0:00:05 (72.81 ms/it) accuracy/train: 0.977 loss/train: 0.108     Train Epoch 1: 86%|██████████████████▉ | ETA: 0:00:04 (71.47 ms/it) accuracy/train: 0.984 loss/train: 0.0694     Train Epoch 1: 88%|███████████████████▎ | ETA: 0:00:03 (70.03 ms/it) accuracy/train: 0.938 loss/train: 0.215     Train Epoch 1: 90%|███████████████████▊ | ETA: 0:00:02 (68.66 ms/it) accuracy/train: 0.945 loss/train: 0.189     Train Epoch 1: 92%|████████████████████▎ | ETA: 0:00:02 (67.35 ms/it) accuracy/train: 0.961 loss/train: 0.134     Train Epoch 1: 94%|████████████████████▊ | ETA: 0:00:01 (66.11 ms/it) accuracy/train: 0.969 loss/train: 0.0892     Train Epoch 1: 96%|█████████████████████▏| ETA: 0:00:01 (64.92 ms/it) accuracy/train: 0.977 loss/train: 0.144     Train Epoch 1: 98%|█████████████████████▋| ETA: 0:00:00 (63.78 ms/it) accuracy/train: 0.961 loss/train: 0.1     Train Epoch 1: 100%|██████████████████████| Time: 0:00:26 (62.92 ms/it) accuracy/train: 0.955 loss/train: 0.143   Val Epoch 1: 94%|██████████████████████▌ | ETA: 0:00:00 ( 5.16 ms/it) accuracy/val: 0.97 loss/val: 0.105        Val Epoch 1: 100%|████████████████████████| Time: 0:00:00 ( 4.97 ms/it) accuracy/val: 0.97 loss/val: 0.104      Train Epoch 2: 2%|▍ | ETA: 0:00:05 (12.90 ms/it) accuracy/train: 0.961 loss/train: 0.155     Train Epoch 2: 4%|▉ | ETA: 0:00:05 (12.70 ms/it) accuracy/train: 0.961 loss/train: 0.115     Train Epoch 2: 6%|█▍ | ETA: 0:00:04 (12.43 ms/it) accuracy/train: 0.992 loss/train: 0.0592     Train Epoch 2: 8%|█▊ | ETA: 0:00:05 (13.06 ms/it) accuracy/train: 0.977 loss/train: 0.0693     Train Epoch 2: 10%|██▎ | ETA: 0:00:04 (12.84 ms/it) accuracy/train: 0.984 loss/train: 0.108     Train Epoch 2: 12%|██▊ | ETA: 0:00:04 (12.76 ms/it) accuracy/train: 0.969 loss/train: 0.113     Train Epoch 2: 14%|███▏ | ETA: 0:00:04 (12.73 ms/it) accuracy/train: 0.969 loss/train: 0.0722     Train Epoch 2: 17%|███▋ | ETA: 0:00:04 (12.69 ms/it) accuracy/train: 0.984 loss/train: 0.0603     Train Epoch 2: 18%|████▏ | ETA: 0:00:04 (12.71 ms/it) accuracy/train: 0.977 loss/train: 0.0622     Train Epoch 2: 21%|████▌ | ETA: 0:00:04 (12.67 ms/it) accuracy/train: 0.969 loss/train: 0.154     Train Epoch 2: 23%|█████ | ETA: 0:00:04 (12.65 ms/it) accuracy/train: 0.953 loss/train: 0.149     Train Epoch 2: 25%|█████▌ | ETA: 0:00:03 (12.61 ms/it) accuracy/train: 0.938 loss/train: 0.159     Train Epoch 2: 27%|██████ | ETA: 0:00:03 (12.63 ms/it) accuracy/train: 0.938 loss/train: 0.165     Train Epoch 2: 29%|██████▍ | ETA: 0:00:03 (12.56 ms/it) accuracy/train: 0.969 loss/train: 0.0886     Train Epoch 2: 31%|██████▉ | ETA: 0:00:03 (12.52 ms/it) accuracy/train: 0.969 loss/train: 0.0589     Train Epoch 2: 33%|███████▍ | ETA: 0:00:03 (12.51 ms/it) accuracy/train: 0.938 loss/train: 0.15     Train Epoch 2: 36%|███████▉ | ETA: 0:00:03 (12.48 ms/it) accuracy/train: 0.992 loss/train: 0.0231     Train Epoch 2: 37%|████████▎ | ETA: 0:00:03 (12.49 ms/it) accuracy/train: 0.961 loss/train: 0.13     Train Epoch 2: 40%|████████▊ | ETA: 0:00:03 (12.46 ms/it) accuracy/train: 0.961 loss/train: 0.0917     Train Epoch 2: 42%|█████████▏ | ETA: 0:00:03 (12.43 ms/it) accuracy/train: 0.93 loss/train: 0.168     Train Epoch 2: 44%|█████████▋ | ETA: 0:00:02 (12.41 ms/it) accuracy/train: 0.961 loss/train: 0.133     Train Epoch 2: 46%|██████████▏ | ETA: 0:00:02 (12.39 ms/it) accuracy/train: 0.977 loss/train: 0.109     Train Epoch 2: 48%|██████████▌ | ETA: 0:00:02 (12.41 ms/it) accuracy/train: 0.984 loss/train: 0.0399     Train Epoch 2: 50%|███████████ | ETA: 0:00:02 (12.40 ms/it) accuracy/train: 0.969 loss/train: 0.091     Train Epoch 2: 52%|███████████▌ | ETA: 0:00:02 (12.40 ms/it) accuracy/train: 0.984 loss/train: 0.0475     Train Epoch 2: 54%|████████████ | ETA: 0:00:02 (12.39 ms/it) accuracy/train: 0.977 loss/train: 0.122     Train Epoch 2: 56%|████████████▎ | ETA: 0:00:02 (12.46 ms/it) accuracy/train: 0.969 loss/train: 0.078     Train Epoch 2: 58%|████████████▊ | ETA: 0:00:02 (12.46 ms/it) accuracy/train: 0.961 loss/train: 0.0834     Train Epoch 2: 60%|█████████████▎ | ETA: 0:00:02 (12.45 ms/it) accuracy/train: 0.977 loss/train: 0.171     Train Epoch 2: 62%|█████████████▊ | ETA: 0:00:01 (12.44 ms/it) accuracy/train: 0.953 loss/train: 0.186     Train Epoch 2: 64%|██████████████▏ | ETA: 0:00:01 (12.42 ms/it) accuracy/train: 0.984 loss/train: 0.0506     Train Epoch 2: 66%|██████████████▋ | ETA: 0:00:01 (12.46 ms/it) accuracy/train: 1.0 loss/train: 0.0207     Train Epoch 2: 68%|███████████████▏ | ETA: 0:00:01 (12.45 ms/it) accuracy/train: 0.984 loss/train: 0.0515     Train Epoch 2: 71%|███████████████▌ | ETA: 0:00:01 (12.45 ms/it) accuracy/train: 0.977 loss/train: 0.0976     Train Epoch 2: 73%|████████████████ | ETA: 0:00:01 (12.45 ms/it) accuracy/train: 0.945 loss/train: 0.188     Train Epoch 2: 75%|████████████████▍ | ETA: 0:00:01 (12.46 ms/it) accuracy/train: 0.969 loss/train: 0.0902     Train Epoch 2: 77%|████████████████▉ | ETA: 0:00:01 (12.48 ms/it) accuracy/train: 0.977 loss/train: 0.0578     Train Epoch 2: 78%|█████████████████▎ | ETA: 0:00:01 (12.50 ms/it) accuracy/train: 0.969 loss/train: 0.0682     Train Epoch 2: 80%|█████████████████▋ | ETA: 0:00:01 (12.51 ms/it) accuracy/train: 0.977 loss/train: 0.106     Train Epoch 2: 82%|██████████████████▏ | ETA: 0:00:00 (12.53 ms/it) accuracy/train: 0.969 loss/train: 0.057     Train Epoch 2: 84%|██████████████████▌ | ETA: 0:00:00 (12.54 ms/it) accuracy/train: 0.961 loss/train: 0.104     Train Epoch 2: 86%|██████████████████▉ | ETA: 0:00:00 (12.56 ms/it) accuracy/train: 0.961 loss/train: 0.122     Train Epoch 2: 88%|███████████████████▍ | ETA: 0:00:00 (12.57 ms/it) accuracy/train: 0.953 loss/train: 0.101     Train Epoch 2: 90%|███████████████████▊ | ETA: 0:00:00 (12.60 ms/it) accuracy/train: 0.961 loss/train: 0.181     Train Epoch 2: 92%|████████████████████▏ | ETA: 0:00:00 (12.61 ms/it) accuracy/train: 0.961 loss/train: 0.0869     Train Epoch 2: 94%|████████████████████▋ | ETA: 0:00:00 (12.62 ms/it) accuracy/train: 0.953 loss/train: 0.121     Train Epoch 2: 95%|█████████████████████ | ETA: 0:00:00 (12.63 ms/it) accuracy/train: 0.969 loss/train: 0.121     Train Epoch 2: 97%|█████████████████████▍| ETA: 0:00:00 (12.64 ms/it) accuracy/train: 0.992 loss/train: 0.0286     Train Epoch 2: 99%|█████████████████████▉| ETA: 0:00:00 (12.64 ms/it) accuracy/train: 0.977 loss/train: 0.106     Train Epoch 2: 100%|██████████████████████| Time: 0:00:05 (12.64 ms/it) accuracy/train: 0.982 loss/train: 0.0329   Val Epoch 2: 100%|████████████████████████| Time: 0:00:00 ( 2.07 ms/it) accuracy/val: 0.972 loss/val: 0.105      Train Epoch 3: 2%|▍ | ETA: 0:00:05 (13.56 ms/it) accuracy/train: 0.969 loss/train: 0.11     Train Epoch 3: 4%|▉ | ETA: 0:00:05 (13.09 ms/it) accuracy/train: 0.977 loss/train: 0.0603     Train Epoch 3: 6%|█▎ | ETA: 0:00:05 (13.05 ms/it) accuracy/train: 0.984 loss/train: 0.028     Train Epoch 3: 8%|█▋ | ETA: 0:00:05 (13.06 ms/it) accuracy/train: 0.969 loss/train: 0.0782     Train Epoch 3: 10%|██▏ | ETA: 0:00:04 (12.98 ms/it) accuracy/train: 0.984 loss/train: 0.0663     Train Epoch 3: 12%|██▌ | ETA: 0:00:04 (13.03 ms/it) accuracy/train: 1.0 loss/train: 0.0191     Train Epoch 3: 14%|███ | ETA: 0:00:04 (13.00 ms/it) accuracy/train: 0.984 loss/train: 0.0403     Train Epoch 3: 15%|███▍ | ETA: 0:00:04 (12.97 ms/it) accuracy/train: 1.0 loss/train: 0.00991     Train Epoch 3: 17%|███▊ | ETA: 0:00:04 (12.96 ms/it) accuracy/train: 0.969 loss/train: 0.0707     Train Epoch 3: 19%|████▎ | ETA: 0:00:04 (12.95 ms/it) accuracy/train: 0.984 loss/train: 0.0611     Train Epoch 3: 21%|████▋ | ETA: 0:00:04 (12.99 ms/it) accuracy/train: 0.992 loss/train: 0.0291     Train Epoch 3: 23%|█████ | ETA: 0:00:04 (12.98 ms/it) accuracy/train: 0.992 loss/train: 0.0249     Train Epoch 3: 25%|█████▌ | ETA: 0:00:04 (12.98 ms/it) accuracy/train: 0.992 loss/train: 0.0274     Train Epoch 3: 27%|██████ | ETA: 0:00:03 (12.95 ms/it) accuracy/train: 0.984 loss/train: 0.0685     Train Epoch 3: 29%|██████▍ | ETA: 0:00:03 (12.93 ms/it) accuracy/train: 0.977 loss/train: 0.0865     Train Epoch 3: 31%|██████▉ | ETA: 0:00:03 (12.96 ms/it) accuracy/train: 0.992 loss/train: 0.0224     Train Epoch 3: 33%|███████▎ | ETA: 0:00:03 (12.96 ms/it) accuracy/train: 0.984 loss/train: 0.0317     Train Epoch 3: 35%|███████▋ | ETA: 0:00:03 (12.95 ms/it) accuracy/train: 0.977 loss/train: 0.1     Train Epoch 3: 37%|████████▏ | ETA: 0:00:03 (12.93 ms/it) accuracy/train: 1.0 loss/train: 0.00915     Train Epoch 3: 39%|████████▌ | ETA: 0:00:03 (12.92 ms/it) accuracy/train: 0.977 loss/train: 0.075     Train Epoch 3: 41%|████████▉ | ETA: 0:00:03 (12.96 ms/it) accuracy/train: 0.977 loss/train: 0.0327     Train Epoch 3: 42%|█████████▍ | ETA: 0:00:03 (12.96 ms/it) accuracy/train: 0.969 loss/train: 0.0856     Train Epoch 3: 44%|█████████▊ | ETA: 0:00:03 (12.98 ms/it) accuracy/train: 1.0 loss/train: 0.0129     Train Epoch 3: 46%|██████████▏ | ETA: 0:00:02 (13.00 ms/it) accuracy/train: 0.992 loss/train: 0.0245     Train Epoch 3: 48%|██████████▋ | ETA: 0:00:02 (13.06 ms/it) accuracy/train: 0.992 loss/train: 0.0353     Train Epoch 3: 50%|███████████ | ETA: 0:00:02 (13.18 ms/it) accuracy/train: 1.0 loss/train: 0.0105     Train Epoch 3: 51%|███████████▍ | ETA: 0:00:02 (13.29 ms/it) accuracy/train: 1.0 loss/train: 0.00798     Train Epoch 3: 53%|███████████▋ | ETA: 0:00:02 (13.39 ms/it) accuracy/train: 1.0 loss/train: 0.0145     Train Epoch 3: 55%|████████████▏ | ETA: 0:00:02 (13.41 ms/it) accuracy/train: 0.977 loss/train: 0.0548     Train Epoch 3: 57%|████████████▌ | ETA: 0:00:02 (13.40 ms/it) accuracy/train: 1.0 loss/train: 0.0174     Train Epoch 3: 59%|████████████▉ | ETA: 0:00:02 (13.40 ms/it) accuracy/train: 1.0 loss/train: 0.021     Train Epoch 3: 60%|█████████████▎ | ETA: 0:00:02 (13.46 ms/it) accuracy/train: 1.0 loss/train: 0.00411     Train Epoch 3: 62%|█████████████▊ | ETA: 0:00:02 (13.45 ms/it) accuracy/train: 0.992 loss/train: 0.015     Train Epoch 3: 64%|██████████████▏ | ETA: 0:00:02 (13.43 ms/it) accuracy/train: 0.992 loss/train: 0.0156     Train Epoch 3: 66%|██████████████▌ | ETA: 0:00:01 (13.42 ms/it) accuracy/train: 0.984 loss/train: 0.0678     Train Epoch 3: 68%|███████████████ | ETA: 0:00:01 (13.44 ms/it) accuracy/train: 0.984 loss/train: 0.0473     Train Epoch 3: 70%|███████████████▍ | ETA: 0:00:01 (13.43 ms/it) accuracy/train: 0.984 loss/train: 0.0597     Train Epoch 3: 72%|███████████████▊ | ETA: 0:00:01 (13.42 ms/it) accuracy/train: 0.984 loss/train: 0.0355     Train Epoch 3: 74%|████████████████▎ | ETA: 0:00:01 (13.40 ms/it) accuracy/train: 0.992 loss/train: 0.0133     Train Epoch 3: 76%|████████████████▋ | ETA: 0:00:01 (13.38 ms/it) accuracy/train: 1.0 loss/train: 0.0054     Train Epoch 3: 78%|█████████████████▏ | ETA: 0:00:01 (13.38 ms/it) accuracy/train: 0.977 loss/train: 0.115     Train Epoch 3: 80%|█████████████████▌ | ETA: 0:00:01 (13.37 ms/it) accuracy/train: 0.984 loss/train: 0.0281     Train Epoch 3: 82%|█████████████████▉ | ETA: 0:00:01 (13.36 ms/it) accuracy/train: 0.984 loss/train: 0.0417     Train Epoch 3: 83%|██████████████████▍ | ETA: 0:00:00 (13.35 ms/it) accuracy/train: 0.992 loss/train: 0.0206     Train Epoch 3: 85%|██████████████████▊ | ETA: 0:00:00 (13.44 ms/it) accuracy/train: 0.984 loss/train: 0.0289     Train Epoch 3: 87%|███████████████████▏ | ETA: 0:00:00 (13.44 ms/it) accuracy/train: 0.984 loss/train: 0.0278     Train Epoch 3: 89%|███████████████████▋ | ETA: 0:00:00 (13.43 ms/it) accuracy/train: 0.992 loss/train: 0.0444     Train Epoch 3: 91%|████████████████████ | ETA: 0:00:00 (13.43 ms/it) accuracy/train: 0.992 loss/train: 0.0167     Train Epoch 3: 93%|████████████████████▍ | ETA: 0:00:00 (13.43 ms/it) accuracy/train: 1.0 loss/train: 0.00853     Train Epoch 3: 95%|████████████████████▉ | ETA: 0:00:00 (13.43 ms/it) accuracy/train: 0.984 loss/train: 0.0469     Train Epoch 3: 97%|█████████████████████▎| ETA: 0:00:00 (13.43 ms/it) accuracy/train: 0.969 loss/train: 0.0527     Train Epoch 3: 99%|█████████████████████▊| ETA: 0:00:00 (13.41 ms/it) accuracy/train: 0.992 loss/train: 0.0555     Train Epoch 3: 100%|██████████████████████| Time: 0:00:05 (13.40 ms/it) accuracy/train: 0.991 loss/train: 0.0222 Val Epoch 3: 100%|████████████████████████| Time: 0:00:00 ( 2.12 ms/it) accuracy/val: 0.98 loss/val: 0.0672 [ Info: GPUs available: false, used: false [ Info: Model Summary: MLP( Chain( MLUtils.flatten, Dense(784 => 256, relu), # 200_960 parameters Dense(256 => 10), # 2_570 parameters ), ) # Total: 4 arrays, 203_530 parameters, 795.242 KiB. [ Info: Run Directory: /home/pkgeval/.julia/packages/Tsunami/AMGDr/examples/MLP_MNIST/tsunami_logs/run_2 Val Epoch 3: 94%|██████████████████████▌ | ETA: 0:00:00 ( 2.30 ms/it) accuracy/val: 0.981 loss/val: 0.0677     Val Epoch 3: 100%|████████████████████████| Time: 0:00:00 ( 2.29 ms/it) accuracy/val: 0.98 loss/val: 0.0672   Train Epoch 4: 1%|▎ | ETA: 0:00:09 (21.92 ms/it) accuracy/train: 0.992 loss/train: 0.0206     Train Epoch 4: 3%|▋ | ETA: 0:00:06 (16.68 ms/it) accuracy/train: 1.0 loss/train: 0.0119     Train Epoch 4: 5%|█▏ | ETA: 0:00:06 (15.44 ms/it) accuracy/train: 1.0 loss/train: 0.0127     Train Epoch 4: 7%|█▌ | ETA: 0:00:06 (15.32 ms/it) accuracy/train: 0.992 loss/train: 0.0277     Train Epoch 4: 8%|█▉ | ETA: 0:00:05 (15.29 ms/it) accuracy/train: 1.0 loss/train: 0.0093     Train Epoch 4: 10%|██▎ | ETA: 0:00:05 (15.25 ms/it) accuracy/train: 0.992 loss/train: 0.0778     Train Epoch 4: 12%|██▌ | ETA: 0:00:05 (15.43 ms/it) accuracy/train: 1.0 loss/train: 0.0092     Train Epoch 4: 14%|███ | ETA: 0:00:05 (15.14 ms/it) accuracy/train: 0.992 loss/train: 0.0529     Train Epoch 4: 15%|███▍ | ETA: 0:00:05 (14.94 ms/it) accuracy/train: 1.0 loss/train: 0.0135     Train Epoch 4: 17%|███▊ | ETA: 0:00:05 (14.76 ms/it) accuracy/train: 0.992 loss/train: 0.027     Train Epoch 4: 19%|████▎ | ETA: 0:00:04 (14.61 ms/it) accuracy/train: 0.984 loss/train: 0.0433     Train Epoch 4: 21%|████▋ | ETA: 0:00:04 (14.53 ms/it) accuracy/train: 0.984 loss/train: 0.0343     Train Epoch 4: 23%|█████ | ETA: 0:00:04 (14.46 ms/it) accuracy/train: 1.0 loss/train: 0.00422     Train Epoch 4: 25%|█████▌ | ETA: 0:00:04 (14.40 ms/it) accuracy/train: 0.984 loss/train: 0.0296     Train Epoch 4: 27%|█████▉ | ETA: 0:00:04 (14.41 ms/it) accuracy/train: 0.984 loss/train: 0.0412     Train Epoch 4: 28%|██████▎ | ETA: 0:00:04 (14.42 ms/it) accuracy/train: 1.0 loss/train: 0.00816     Train Epoch 4: 30%|██████▋ | ETA: 0:00:04 (14.44 ms/it) accuracy/train: 0.977 loss/train: 0.0487     Train Epoch 4: 32%|██████▉ | ETA: 0:00:04 (14.55 ms/it) accuracy/train: 1.0 loss/train: 0.00841     Train Epoch 4: 33%|███████▍ | ETA: 0:00:04 (14.53 ms/it) accuracy/train: 0.984 loss/train: 0.0461     Train Epoch 4: 35%|███████▊ | ETA: 0:00:03 (14.52 ms/it) accuracy/train: 0.992 loss/train: 0.0213     Train Epoch 4: 37%|████████▏ | ETA: 0:00:03 (14.47 ms/it) accuracy/train: 0.992 loss/train: 0.0246     Train Epoch 4: 39%|████████▋ | ETA: 0:00:03 (14.40 ms/it) accuracy/train: 0.977 loss/train: 0.0686     Train Epoch 4: 41%|█████████ | ETA: 0:00:03 (14.52 ms/it) accuracy/train: 1.0 loss/train: 0.013     Train Epoch 4: 43%|█████████▍ | ETA: 0:00:03 (14.45 ms/it) accuracy/train: 1.0 loss/train: 0.01     Train Epoch 4: 45%|█████████▉ | ETA: 0:00:03 (14.39 ms/it) accuracy/train: 1.0 loss/train: 0.0158     Train Epoch 4: 47%|██████████▎ | ETA: 0:00:03 (14.34 ms/it) accuracy/train: 0.992 loss/train: 0.0351     Train Epoch 4: 49%|██████████▋ | ETA: 0:00:03 (14.29 ms/it) accuracy/train: 1.0 loss/train: 0.0101     Train Epoch 4: 50%|███████████▏ | ETA: 0:00:02 (14.26 ms/it) accuracy/train: 0.992 loss/train: 0.0416     Train Epoch 4: 52%|███████████▌ | ETA: 0:00:02 (14.22 ms/it) accuracy/train: 0.984 loss/train: 0.0295     Train Epoch 4: 54%|████████████ | ETA: 0:00:02 (14.19 ms/it) accuracy/train: 0.992 loss/train: 0.0226     Train Epoch 4: 56%|████████████▎ | ETA: 0:00:02 (14.24 ms/it) accuracy/train: 0.992 loss/train: 0.0153     Train Epoch 4: 58%|████████████▊ | ETA: 0:00:02 (14.22 ms/it) accuracy/train: 0.992 loss/train: 0.022     Train Epoch 4: 59%|█████████████▏ | ETA: 0:00:02 (14.23 ms/it) accuracy/train: 0.984 loss/train: 0.0365     Train Epoch 4: 61%|█████████████▌ | ETA: 0:00:02 (14.22 ms/it) accuracy/train: 0.992 loss/train: 0.0208     Train Epoch 4: 63%|█████████████▉ | ETA: 0:00:02 (14.22 ms/it) accuracy/train: 0.992 loss/train: 0.0339     Train Epoch 4: 65%|██████████████▎ | ETA: 0:00:02 (14.24 ms/it) accuracy/train: 0.984 loss/train: 0.0514     Train Epoch 4: 67%|██████████████▊ | ETA: 0:00:01 (14.22 ms/it) accuracy/train: 0.984 loss/train: 0.0809     Train Epoch 4: 68%|███████████████▏ | ETA: 0:00:01 (14.23 ms/it) accuracy/train: 0.984 loss/train: 0.0348     Train Epoch 4: 70%|███████████████▌ | ETA: 0:00:01 (14.22 ms/it) accuracy/train: 1.0 loss/train: 0.00911     Train Epoch 4: 72%|███████████████▉ | ETA: 0:00:01 (14.21 ms/it) accuracy/train: 1.0 loss/train: 0.0044     Train Epoch 4: 74%|████████████████▍ | ETA: 0:00:01 (14.18 ms/it) accuracy/train: 0.992 loss/train: 0.0185     Train Epoch 4: 76%|████████████████▊ | ETA: 0:00:01 (14.15 ms/it) accuracy/train: 0.992 loss/train: 0.018     Train Epoch 4: 78%|█████████████████▏ | ETA: 0:00:01 (14.14 ms/it) accuracy/train: 0.992 loss/train: 0.0172     Train Epoch 4: 80%|█████████████████▋ | ETA: 0:00:01 (14.11 ms/it) accuracy/train: 0.992 loss/train: 0.026     Train Epoch 4: 82%|██████████████████ | ETA: 0:00:01 (14.10 ms/it) accuracy/train: 0.992 loss/train: 0.0186     Train Epoch 4: 84%|██████████████████▍ | ETA: 0:00:00 (14.07 ms/it) accuracy/train: 0.984 loss/train: 0.0252     Train Epoch 4: 86%|██████████████████▉ | ETA: 0:00:00 (14.05 ms/it) accuracy/train: 1.0 loss/train: 0.0212     Train Epoch 4: 87%|███████████████████▎ | ETA: 0:00:00 (14.04 ms/it) accuracy/train: 0.992 loss/train: 0.0317     Train Epoch 4: 89%|███████████████████▋ | ETA: 0:00:00 (14.02 ms/it) accuracy/train: 0.977 loss/train: 0.0725     Train Epoch 4: 91%|████████████████████▏ | ETA: 0:00:00 (14.05 ms/it) accuracy/train: 0.992 loss/train: 0.0518     Train Epoch 4: 93%|████████████████████▌ | ETA: 0:00:00 (14.03 ms/it) accuracy/train: 1.0 loss/train: 0.0106     Train Epoch 4: 95%|████████████████████▉ | ETA: 0:00:00 (14.03 ms/it) accuracy/train: 0.984 loss/train: 0.0322     Train Epoch 4: 97%|█████████████████████▍| ETA: 0:00:00 (14.01 ms/it) accuracy/train: 0.977 loss/train: 0.055     Train Epoch 4: 99%|█████████████████████▊| ETA: 0:00:00 (14.00 ms/it) accuracy/train: 0.984 loss/train: 0.0723     Train Epoch 4: 100%|██████████████████████| Time: 0:00:05 (13.98 ms/it) accuracy/train: 1.0 loss/train: 0.0104   Val Epoch 4: 100%|████████████████████████| Time: 0:00:00 ( 2.16 ms/it) accuracy/val: 0.981 loss/val: 0.0668      Train Epoch 5: 2%|▍ | ETA: 0:00:05 (13.20 ms/it) accuracy/train: 1.0 loss/train: 0.0189     Train Epoch 5: 4%|▉ | ETA: 0:00:05 (13.52 ms/it) accuracy/train: 1.0 loss/train: 0.01     Train Epoch 5: 6%|█▎ | ETA: 0:00:05 (13.23 ms/it) accuracy/train: 1.0 loss/train: 0.0142     Train Epoch 5: 8%|█▋ | ETA: 0:00:05 (13.54 ms/it) accuracy/train: 1.0 loss/train: 0.0123     Train Epoch 5: 9%|██▏ | ETA: 0:00:05 (13.50 ms/it) accuracy/train: 0.992 loss/train: 0.0526     Train Epoch 5: 11%|██▌ | ETA: 0:00:05 (13.39 ms/it) accuracy/train: 1.0 loss/train: 0.0124     Train Epoch 5: 13%|██▉ | ETA: 0:00:04 (13.40 ms/it) accuracy/train: 1.0 loss/train: 0.00858     Train Epoch 5: 15%|███▍ | ETA: 0:00:04 (13.38 ms/it) accuracy/train: 1.0 loss/train: 0.00425     Train Epoch 5: 17%|███▊ | ETA: 0:00:04 (13.35 ms/it) accuracy/train: 0.992 loss/train: 0.0199     Train Epoch 5: 19%|████▏ | ETA: 0:00:04 (13.31 ms/it) accuracy/train: 0.992 loss/train: 0.0252     Train Epoch 5: 21%|████▋ | ETA: 0:00:04 (13.27 ms/it) accuracy/train: 0.992 loss/train: 0.0169     Train Epoch 5: 23%|█████ | ETA: 0:00:04 (13.30 ms/it) accuracy/train: 1.0 loss/train: 0.00547     Train Epoch 5: 25%|█████▍ | ETA: 0:00:04 (13.31 ms/it) accuracy/train: 0.992 loss/train: 0.029     Train Epoch 5: 27%|█████▉ | ETA: 0:00:04 (13.35 ms/it) accuracy/train: 0.992 loss/train: 0.0124     Train Epoch 5: 28%|██████▎ | ETA: 0:00:04 (13.37 ms/it) accuracy/train: 1.0 loss/train: 0.00886     Train Epoch 5: 30%|██████▋ | ETA: 0:00:03 (13.35 ms/it) accuracy/train: 0.992 loss/train: 0.0499     Train Epoch 5: 32%|███████▏ | ETA: 0:00:03 (13.38 ms/it) accuracy/train: 0.992 loss/train: 0.0208     Train Epoch 5: 34%|███████▌ | ETA: 0:00:03 (13.55 ms/it) accuracy/train: 1.0 loss/train: 0.0144     Train Epoch 5: 36%|███████▉ | ETA: 0:00:03 (13.50 ms/it) accuracy/train: 0.992 loss/train: 0.00942     Train Epoch 5: 38%|████████▎ | ETA: 0:00:03 (13.49 ms/it) accuracy/train: 1.0 loss/train: 0.014     Train Epoch 5: 40%|████████▊ | ETA: 0:00:03 (13.45 ms/it) accuracy/train: 1.0 loss/train: 0.0104     Train Epoch 5: 41%|█████████▏ | ETA: 0:00:03 (13.43 ms/it) accuracy/train: 0.992 loss/train: 0.019     Train Epoch 5: 43%|█████████▌ | ETA: 0:00:03 (13.45 ms/it) accuracy/train: 1.0 loss/train: 0.0075     Train Epoch 5: 45%|██████████ | ETA: 0:00:03 (13.45 ms/it) accuracy/train: 1.0 loss/train: 0.0239     Train Epoch 5: 47%|██████████▍ | ETA: 0:00:02 (13.43 ms/it) accuracy/train: 0.984 loss/train: 0.0234     Train Epoch 5: 49%|██████████▉ | ETA: 0:00:02 (13.39 ms/it) accuracy/train: 0.992 loss/train: 0.02     Train Epoch 5: 51%|███████████▎ | ETA: 0:00:02 (13.37 ms/it) accuracy/train: 0.992 loss/train: 0.0257     Train Epoch 5: 53%|███████████▋ | ETA: 0:00:02 (13.37 ms/it) accuracy/train: 0.992 loss/train: 0.0255     Train Epoch 5: 55%|████████████▏ | ETA: 0:00:02 (13.35 ms/it) accuracy/train: 1.0 loss/train: 0.0141     Train Epoch 5: 57%|████████████▌ | ETA: 0:00:02 (13.34 ms/it) accuracy/train: 1.0 loss/train: 0.013     Train Epoch 5: 59%|████████████▉ | ETA: 0:00:02 (13.32 ms/it) accuracy/train: 1.0 loss/train: 0.0105     Train Epoch 5: 61%|█████████████▍ | ETA: 0:00:02 (13.30 ms/it) accuracy/train: 0.992 loss/train: 0.0116     Train Epoch 5: 63%|█████████████▊ | ETA: 0:00:02 (13.31 ms/it) accuracy/train: 1.0 loss/train: 0.00939     Train Epoch 5: 64%|██████████████▏ | ETA: 0:00:01 (13.29 ms/it) accuracy/train: 1.0 loss/train: 0.00722     Train Epoch 5: 66%|██████████████▋ | ETA: 0:00:01 (13.28 ms/it) accuracy/train: 0.992 loss/train: 0.0162     Train Epoch 5: 68%|███████████████ | ETA: 0:00:01 (13.27 ms/it) accuracy/train: 0.992 loss/train: 0.013     Train Epoch 5: 70%|███████████████▍ | ETA: 0:00:01 (13.27 ms/it) accuracy/train: 0.992 loss/train: 0.0191     Train Epoch 5: 72%|███████████████▉ | ETA: 0:00:01 (13.28 ms/it) accuracy/train: 0.992 loss/train: 0.0207     Train Epoch 5: 74%|████████████████▎ | ETA: 0:00:01 (13.27 ms/it) accuracy/train: 0.992 loss/train: 0.02     Train Epoch 5: 76%|████████████████▋ | ETA: 0:00:01 (13.27 ms/it) accuracy/train: 0.992 loss/train: 0.0141     Train Epoch 5: 78%|█████████████████▏ | ETA: 0:00:01 (13.26 ms/it) accuracy/train: 0.977 loss/train: 0.0567     Train Epoch 5: 80%|█████████████████▌ | ETA: 0:00:01 (13.25 ms/it) accuracy/train: 0.984 loss/train: 0.03     Train Epoch 5: 82%|█████████████████▉ | ETA: 0:00:01 (13.26 ms/it) accuracy/train: 0.992 loss/train: 0.0487     Train Epoch 5: 83%|██████████████████▍ | ETA: 0:00:00 (13.25 ms/it) accuracy/train: 0.992 loss/train: 0.0264     Train Epoch 5: 85%|██████████████████▊ | ETA: 0:00:00 (13.25 ms/it) accuracy/train: 1.0 loss/train: 0.0116     Train Epoch 5: 87%|███████████████████▏ | ETA: 0:00:00 (13.25 ms/it) accuracy/train: 1.0 loss/train: 0.0181     Train Epoch 5: 89%|███████████████████▋ | ETA: 0:00:00 (13.25 ms/it) accuracy/train: 0.992 loss/train: 0.0333     Train Epoch 5: 91%|████████████████████ | ETA: 0:00:00 (13.25 ms/it) accuracy/train: 1.0 loss/train: 0.00785     Train Epoch 5: 93%|████████████████████▍ | ETA: 0:00:00 (13.25 ms/it) accuracy/train: 0.992 loss/train: 0.0475     Train Epoch 5: 95%|████████████████████▉ | ETA: 0:00:00 (13.24 ms/it) accuracy/train: 0.992 loss/train: 0.0276     Train Epoch 5: 97%|█████████████████████▍| ETA: 0:00:00 (13.23 ms/it) accuracy/train: 0.984 loss/train: 0.0373     Train Epoch 5: 99%|█████████████████████▊| ETA: 0:00:00 (13.23 ms/it) accuracy/train: 0.992 loss/train: 0.00869     Train Epoch 5: 100%|██████████████████████| Time: 0:00:05 (13.24 ms/it) accuracy/train: 1.0 loss/train: 0.0103 Val Epoch 5: 100%|████████████████████████| Time: 0:00:00 ( 2.04 ms/it) accuracy/val: 0.981 loss/val: 0.0653 Testing: 3%|▊ | ETA: 0:00:05 (66.34 ms/it) accuracy/test: 0.988 loss/test: 0.0427     Testing: 61%|█████████████████ | ETA: 0:00:00 ( 4.92 ms/it) accuracy/test: 0.976 loss/test: 0.0881     Testing: 100%|████████████████████████████| Time: 0:00:00 ( 3.86 ms/it) accuracy/test: 0.981 loss/test: 0.0713 Test Summary: | Total Time Examples | 0 2m20.9s Testing Tsunami tests passed Testing completed after 1618.87s PkgEval succeeded after 1875.41s