make method comparison device agnostic, so it can expand to more accelerators like XPU (#2610)

make method comparision device agnostic, so it can expand to more
accelerators like XPU

---------

Signed-off-by: YAO Matrix <[email protected]>

Author: yao-matrix

method_comparison/MetaMathQA/README.md

@@ -159,9 +159,9 @@ Results are stored in one of the result directories. An example output could loo
     }
   },
   "train_info": {
-    "cuda_memory_reserved_avg": 14229219940,
-    "cuda_memory_max": 24847056896,
-    "cuda_memory_reserved_99th": 19115624366,
+    "accelerator_memory_reserved_avg": 14229219940,
+    "accelerator_memory_max": 24847056896,
+    "accelerator_memory_reserved_99th": 19115624366,
     "train_time": 2238.65277833899,
     "file_size": 1157064,
     "status": "success",
@@ -211,7 +211,7 @@ Results are stored in one of the result directories. An example output could loo
       "version": "#17~24.04.2-Ubuntu SMP PREEMPT_DYNAMIC Mon Jan 20 22:48:29 UTC 2",
       "machine": "x86_64",
       "processor": "x86_64",
-      "gpu": "NVIDIA GeForce RTX 4090"
+      "accelerator": "NVIDIA GeForce RTX 4090"
     },
     "pytorch_info": "PyTorch built with: [...]"
   }

method_comparison/MetaMathQA/results/adalora--llama-3.2-3B-rank32.json

@@ -3773,9 +3773,9 @@
     "error_msg": ""
   },
   "train_info": {
-    "cuda_memory_reserved_avg": 12361399900,
-    "cuda_memory_max": 22793945088,
-    "cuda_memory_reserved_99th": 18203426160,
+    "accelerator_memory_reserved_avg": 12361399900,
+    "accelerator_memory_max": 22793945088,
+    "accelerator_memory_reserved_99th": 18203426160,
     "train_time": 1986.3603882369862,
     "file_size": 35147440,
     "num_trainable_params": 18353664,
@@ -4064,8 +4064,8 @@
       "version": "#31-Ubuntu SMP Wed Apr 23 18:42:41 UTC 2025",
       "machine": "x86_64",
       "processor": "x86_64",
-      "gpu": "NVIDIA L40S"
+      "accelerator": "NVIDIA L40S"
     },
     "pytorch_info": "PyTorch built with:\n  - GCC 11.2\n  - C++ Version: 201703\n  - Intel(R) oneAPI Math Kernel Library Version 2024.2-Product Build 20240605 for Intel(R) 64 architecture applications\n  - Intel(R) MKL-DNN v3.7.1 (Git Hash 8d263e693366ef8db40acc569cc7d8edf644556d)\n  - OpenMP 201511 (a.k.a. OpenMP 4.5)\n  - LAPACK is enabled (usually provided by MKL)\n  - NNPACK is enabled\n  - CPU capability usage: AVX2\n  - CUDA Runtime 12.6\n  - NVCC architecture flags: -gencode;arch=compute_50,code=sm_50;-gencode;arch=compute_60,code=sm_60;-gencode;arch=compute_70,code=sm_70;-gencode;arch=compute_75,code=sm_75;-gencode;arch=compute_80,code=sm_80;-gencode;arch=compute_86,code=sm_86;-gencode;arch=compute_90,code=sm_90\n  - CuDNN 90.7.1  (built against CUDA 12.8)\n    - Built with CuDNN 90.5.1\n  - Magma 2.6.1\n  - Build settings: BLAS_INFO=mkl, BUILD_TYPE=Release, COMMIT_SHA=e2d141dbde55c2a4370fac5165b0561b6af4798b, CUDA_VERSION=12.6, CUDNN_VERSION=9.5.1, CXX_COMPILER=/opt/rh/gcc-toolset-11/root/usr/bin/c++, CXX_FLAGS= -D_GLIBCXX_USE_CXX11_ABI=1 -fvisibility-inlines-hidden -DUSE_PTHREADPOOL -DNDEBUG -DUSE_KINETO -DLIBKINETO_NOROCTRACER -DLIBKINETO_NOXPUPTI=ON -DUSE_FBGEMM -DUSE_PYTORCH_QNNPACK -DUSE_XNNPACK -DSYMBOLICATE_MOBILE_DEBUG_HANDLE -O2 -fPIC -Wall -Wextra -Werror=return-type -Werror=non-virtual-dtor -Werror=range-loop-construct -Werror=bool-operation -Wnarrowing -Wno-missing-field-initializers -Wno-unknown-pragmas -Wno-unused-parameter -Wno-strict-overflow -Wno-strict-aliasing -Wno-stringop-overflow -Wsuggest-override -Wno-psabi -Wno-error=old-style-cast -fdiagnostics-color=always -faligned-new -Wno-maybe-uninitialized -fno-math-errno -fno-trapping-math -Werror=format -Wno-stringop-overflow, LAPACK_INFO=mkl, PERF_WITH_AVX=1, PERF_WITH_AVX2=1, TORCH_VERSION=2.7.1, USE_CUDA=ON, USE_CUDNN=ON, USE_CUSPARSELT=1, USE_GFLAGS=OFF, USE_GLOG=OFF, USE_GLOO=ON, USE_MKL=ON, USE_MKLDNN=ON, USE_MPI=OFF, USE_NCCL=1, USE_NNPACK=ON, USE_OPENMP=ON, USE_ROCM=OFF, USE_ROCM_KERNEL_ASSERT=OFF, \n"
   }
-}
+}

method_comparison/MetaMathQA/results/adaptionprompt--llama-3.2-3B-lr_0.0005.json

@@ -43,9 +43,9 @@
     "error_msg": ""
   },
   "train_info": {
-    "cuda_memory_reserved_avg": 11893757234,
-    "cuda_memory_max": 22410166272,
-    "cuda_memory_reserved_99th": 17907664814,
+    "accelerator_memory_reserved_avg": 11893757234,
+    "accelerator_memory_max": 22410166272,
+    "accelerator_memory_reserved_99th": 17907664814,
     "train_time": 1989.2834085189897,
     "file_size": 17210384,
     "num_trainable_params": 8601628,
@@ -334,8 +334,8 @@
       "version": "#31-Ubuntu SMP Wed Apr 23 18:42:41 UTC 2025",
       "machine": "x86_64",
       "processor": "x86_64",
-      "gpu": "NVIDIA L40S"
+      "accelerator": "NVIDIA L40S"
     },
     "pytorch_info": "PyTorch built with:\n  - GCC 11.2\n  - C++ Version: 201703\n  - Intel(R) oneAPI Math Kernel Library Version 2024.2-Product Build 20240605 for Intel(R) 64 architecture applications\n  - Intel(R) MKL-DNN v3.7.1 (Git Hash 8d263e693366ef8db40acc569cc7d8edf644556d)\n  - OpenMP 201511 (a.k.a. OpenMP 4.5)\n  - LAPACK is enabled (usually provided by MKL)\n  - NNPACK is enabled\n  - CPU capability usage: AVX2\n  - CUDA Runtime 12.6\n  - NVCC architecture flags: -gencode;arch=compute_50,code=sm_50;-gencode;arch=compute_60,code=sm_60;-gencode;arch=compute_70,code=sm_70;-gencode;arch=compute_75,code=sm_75;-gencode;arch=compute_80,code=sm_80;-gencode;arch=compute_86,code=sm_86;-gencode;arch=compute_90,code=sm_90\n  - CuDNN 90.7.1  (built against CUDA 12.8)\n    - Built with CuDNN 90.5.1\n  - Magma 2.6.1\n  - Build settings: BLAS_INFO=mkl, BUILD_TYPE=Release, COMMIT_SHA=e2d141dbde55c2a4370fac5165b0561b6af4798b, CUDA_VERSION=12.6, CUDNN_VERSION=9.5.1, CXX_COMPILER=/opt/rh/gcc-toolset-11/root/usr/bin/c++, CXX_FLAGS= -D_GLIBCXX_USE_CXX11_ABI=1 -fvisibility-inlines-hidden -DUSE_PTHREADPOOL -DNDEBUG -DUSE_KINETO -DLIBKINETO_NOROCTRACER -DLIBKINETO_NOXPUPTI=ON -DUSE_FBGEMM -DUSE_PYTORCH_QNNPACK -DUSE_XNNPACK -DSYMBOLICATE_MOBILE_DEBUG_HANDLE -O2 -fPIC -Wall -Wextra -Werror=return-type -Werror=non-virtual-dtor -Werror=range-loop-construct -Werror=bool-operation -Wnarrowing -Wno-missing-field-initializers -Wno-unknown-pragmas -Wno-unused-parameter -Wno-strict-overflow -Wno-strict-aliasing -Wno-stringop-overflow -Wsuggest-override -Wno-psabi -Wno-error=old-style-cast -fdiagnostics-color=always -faligned-new -Wno-maybe-uninitialized -fno-math-errno -fno-trapping-math -Werror=format -Wno-stringop-overflow, LAPACK_INFO=mkl, PERF_WITH_AVX=1, PERF_WITH_AVX2=1, TORCH_VERSION=2.7.1, USE_CUDA=ON, USE_CUDNN=ON, USE_CUSPARSELT=1, USE_GFLAGS=OFF, USE_GLOG=OFF, USE_GLOO=ON, USE_MKL=ON, USE_MKLDNN=ON, USE_MPI=OFF, USE_NCCL=1, USE_NNPACK=ON, USE_OPENMP=ON, USE_ROCM=OFF, USE_ROCM_KERNEL_ASSERT=OFF, \n"
   }
-}
+}

method_comparison/MetaMathQA/results/boft--llama-3.2-3B-default.json

@@ -56,9 +56,9 @@
     "error_msg": ""
   },
   "train_info": {
-    "cuda_memory_reserved_avg": 14814855089,
-    "cuda_memory_max": 24427626496,
-    "cuda_memory_reserved_99th": 20103445872,
+    "accelerator_memory_reserved_avg": 14814855089,
+    "accelerator_memory_max": 24427626496,
+    "accelerator_memory_reserved_99th": 20103445872,
     "train_time": 8291.859631775995,
     "file_size": 3225360,
     "num_trainable_params": 802816,
@@ -347,8 +347,8 @@
       "version": "#31-Ubuntu SMP Wed Apr 23 18:42:41 UTC 2025",
       "machine": "x86_64",
       "processor": "x86_64",
-      "gpu": "NVIDIA L40S"
+      "accelerator": "NVIDIA L40S"
     },
     "pytorch_info": "PyTorch built with:\n  - GCC 11.2\n  - C++ Version: 201703\n  - Intel(R) oneAPI Math Kernel Library Version 2024.2-Product Build 20240605 for Intel(R) 64 architecture applications\n  - Intel(R) MKL-DNN v3.7.1 (Git Hash 8d263e693366ef8db40acc569cc7d8edf644556d)\n  - OpenMP 201511 (a.k.a. OpenMP 4.5)\n  - LAPACK is enabled (usually provided by MKL)\n  - NNPACK is enabled\n  - CPU capability usage: AVX2\n  - CUDA Runtime 12.6\n  - NVCC architecture flags: -gencode;arch=compute_50,code=sm_50;-gencode;arch=compute_60,code=sm_60;-gencode;arch=compute_70,code=sm_70;-gencode;arch=compute_75,code=sm_75;-gencode;arch=compute_80,code=sm_80;-gencode;arch=compute_86,code=sm_86;-gencode;arch=compute_90,code=sm_90\n  - CuDNN 90.7.1  (built against CUDA 12.8)\n    - Built with CuDNN 90.5.1\n  - Magma 2.6.1\n  - Build settings: BLAS_INFO=mkl, BUILD_TYPE=Release, COMMIT_SHA=e2d141dbde55c2a4370fac5165b0561b6af4798b, CUDA_VERSION=12.6, CUDNN_VERSION=9.5.1, CXX_COMPILER=/opt/rh/gcc-toolset-11/root/usr/bin/c++, CXX_FLAGS= -D_GLIBCXX_USE_CXX11_ABI=1 -fvisibility-inlines-hidden -DUSE_PTHREADPOOL -DNDEBUG -DUSE_KINETO -DLIBKINETO_NOROCTRACER -DLIBKINETO_NOXPUPTI=ON -DUSE_FBGEMM -DUSE_PYTORCH_QNNPACK -DUSE_XNNPACK -DSYMBOLICATE_MOBILE_DEBUG_HANDLE -O2 -fPIC -Wall -Wextra -Werror=return-type -Werror=non-virtual-dtor -Werror=range-loop-construct -Werror=bool-operation -Wnarrowing -Wno-missing-field-initializers -Wno-unknown-pragmas -Wno-unused-parameter -Wno-strict-overflow -Wno-strict-aliasing -Wno-stringop-overflow -Wsuggest-override -Wno-psabi -Wno-error=old-style-cast -fdiagnostics-color=always -faligned-new -Wno-maybe-uninitialized -fno-math-errno -fno-trapping-math -Werror=format -Wno-stringop-overflow, LAPACK_INFO=mkl, PERF_WITH_AVX=1, PERF_WITH_AVX2=1, TORCH_VERSION=2.7.1, USE_CUDA=ON, USE_CUDNN=ON, USE_CUSPARSELT=1, USE_GFLAGS=OFF, USE_GLOG=OFF, USE_GLOO=ON, USE_MKL=ON, USE_MKLDNN=ON, USE_MPI=OFF, USE_NCCL=1, USE_NNPACK=ON, USE_OPENMP=ON, USE_ROCM=OFF, USE_ROCM_KERNEL_ASSERT=OFF, \n"
   }
-}
+}

method_comparison/MetaMathQA/results/bone--llama-3.2-3B-bat.json

@@ -52,9 +52,9 @@
     "error_msg": ""
   },
   "train_info": {
-    "cuda_memory_reserved_avg": 14713983755,
-    "cuda_memory_max": 25251807232,
-    "cuda_memory_reserved_99th": 20472733368,
+    "accelerator_memory_reserved_avg": 14713983755,
+    "accelerator_memory_max": 25251807232,
+    "accelerator_memory_reserved_99th": 20472733368,
     "train_time": 2430.7548372539895,
     "file_size": 29367552,
     "num_trainable_params": 7340032,
@@ -343,8 +343,8 @@
       "version": "#31-Ubuntu SMP Wed Apr 23 18:42:41 UTC 2025",
       "machine": "x86_64",
       "processor": "x86_64",
-      "gpu": "NVIDIA L40S"
+      "accelerator": "NVIDIA L40S"
     },
     "pytorch_info": "PyTorch built with:\n  - GCC 11.2\n  - C++ Version: 201703\n  - Intel(R) oneAPI Math Kernel Library Version 2024.2-Product Build 20240605 for Intel(R) 64 architecture applications\n  - Intel(R) MKL-DNN v3.7.1 (Git Hash 8d263e693366ef8db40acc569cc7d8edf644556d)\n  - OpenMP 201511 (a.k.a. OpenMP 4.5)\n  - LAPACK is enabled (usually provided by MKL)\n  - NNPACK is enabled\n  - CPU capability usage: AVX2\n  - CUDA Runtime 12.6\n  - NVCC architecture flags: -gencode;arch=compute_50,code=sm_50;-gencode;arch=compute_60,code=sm_60;-gencode;arch=compute_70,code=sm_70;-gencode;arch=compute_75,code=sm_75;-gencode;arch=compute_80,code=sm_80;-gencode;arch=compute_86,code=sm_86;-gencode;arch=compute_90,code=sm_90\n  - CuDNN 90.7.1  (built against CUDA 12.8)\n    - Built with CuDNN 90.5.1\n  - Magma 2.6.1\n  - Build settings: BLAS_INFO=mkl, BUILD_TYPE=Release, COMMIT_SHA=e2d141dbde55c2a4370fac5165b0561b6af4798b, CUDA_VERSION=12.6, CUDNN_VERSION=9.5.1, CXX_COMPILER=/opt/rh/gcc-toolset-11/root/usr/bin/c++, CXX_FLAGS= -D_GLIBCXX_USE_CXX11_ABI=1 -fvisibility-inlines-hidden -DUSE_PTHREADPOOL -DNDEBUG -DUSE_KINETO -DLIBKINETO_NOROCTRACER -DLIBKINETO_NOXPUPTI=ON -DUSE_FBGEMM -DUSE_PYTORCH_QNNPACK -DUSE_XNNPACK -DSYMBOLICATE_MOBILE_DEBUG_HANDLE -O2 -fPIC -Wall -Wextra -Werror=return-type -Werror=non-virtual-dtor -Werror=range-loop-construct -Werror=bool-operation -Wnarrowing -Wno-missing-field-initializers -Wno-unknown-pragmas -Wno-unused-parameter -Wno-strict-overflow -Wno-strict-aliasing -Wno-stringop-overflow -Wsuggest-override -Wno-psabi -Wno-error=old-style-cast -fdiagnostics-color=always -faligned-new -Wno-maybe-uninitialized -fno-math-errno -fno-trapping-math -Werror=format -Wno-stringop-overflow, LAPACK_INFO=mkl, PERF_WITH_AVX=1, PERF_WITH_AVX2=1, TORCH_VERSION=2.7.1, USE_CUDA=ON, USE_CUDNN=ON, USE_CUSPARSELT=1, USE_GFLAGS=OFF, USE_GLOG=OFF, USE_GLOO=ON, USE_MKL=ON, USE_MKLDNN=ON, USE_MPI=OFF, USE_NCCL=1, USE_NNPACK=ON, USE_OPENMP=ON, USE_ROCM=OFF, USE_ROCM_KERNEL_ASSERT=OFF, \n"
   }
-}
+}

method_comparison/MetaMathQA/results/bone--llama-3.2-3B-default.json

@@ -52,9 +52,9 @@
     "error_msg": ""
   },
   "train_info": {
-    "cuda_memory_reserved_avg": 11170837063,
-    "cuda_memory_max": 20248002560,
-    "cuda_memory_reserved_99th": 16303469363,
+    "accelerator_memory_reserved_avg": 11170837063,
+    "accelerator_memory_max": 20248002560,
+    "accelerator_memory_reserved_99th": 16303469363,
     "train_time": 1664.0814183089897,
     "file_size": 29367496,
     "num_trainable_params": 7340032,
@@ -343,8 +343,8 @@
       "version": "#31-Ubuntu SMP Wed Apr 23 18:42:41 UTC 2025",
       "machine": "x86_64",
       "processor": "x86_64",
-      "gpu": "NVIDIA L40S"
+      "accelerator": "NVIDIA L40S"
     },
     "pytorch_info": "PyTorch built with:\n  - GCC 11.2\n  - C++ Version: 201703\n  - Intel(R) oneAPI Math Kernel Library Version 2024.2-Product Build 20240605 for Intel(R) 64 architecture applications\n  - Intel(R) MKL-DNN v3.7.1 (Git Hash 8d263e693366ef8db40acc569cc7d8edf644556d)\n  - OpenMP 201511 (a.k.a. OpenMP 4.5)\n  - LAPACK is enabled (usually provided by MKL)\n  - NNPACK is enabled\n  - CPU capability usage: AVX2\n  - CUDA Runtime 12.6\n  - NVCC architecture flags: -gencode;arch=compute_50,code=sm_50;-gencode;arch=compute_60,code=sm_60;-gencode;arch=compute_70,code=sm_70;-gencode;arch=compute_75,code=sm_75;-gencode;arch=compute_80,code=sm_80;-gencode;arch=compute_86,code=sm_86;-gencode;arch=compute_90,code=sm_90\n  - CuDNN 90.7.1  (built against CUDA 12.8)\n    - Built with CuDNN 90.5.1\n  - Magma 2.6.1\n  - Build settings: BLAS_INFO=mkl, BUILD_TYPE=Release, COMMIT_SHA=e2d141dbde55c2a4370fac5165b0561b6af4798b, CUDA_VERSION=12.6, CUDNN_VERSION=9.5.1, CXX_COMPILER=/opt/rh/gcc-toolset-11/root/usr/bin/c++, CXX_FLAGS= -D_GLIBCXX_USE_CXX11_ABI=1 -fvisibility-inlines-hidden -DUSE_PTHREADPOOL -DNDEBUG -DUSE_KINETO -DLIBKINETO_NOROCTRACER -DLIBKINETO_NOXPUPTI=ON -DUSE_FBGEMM -DUSE_PYTORCH_QNNPACK -DUSE_XNNPACK -DSYMBOLICATE_MOBILE_DEBUG_HANDLE -O2 -fPIC -Wall -Wextra -Werror=return-type -Werror=non-virtual-dtor -Werror=range-loop-construct -Werror=bool-operation -Wnarrowing -Wno-missing-field-initializers -Wno-unknown-pragmas -Wno-unused-parameter -Wno-strict-overflow -Wno-strict-aliasing -Wno-stringop-overflow -Wsuggest-override -Wno-psabi -Wno-error=old-style-cast -fdiagnostics-color=always -faligned-new -Wno-maybe-uninitialized -fno-math-errno -fno-trapping-math -Werror=format -Wno-stringop-overflow, LAPACK_INFO=mkl, PERF_WITH_AVX=1, PERF_WITH_AVX2=1, TORCH_VERSION=2.7.1, USE_CUDA=ON, USE_CUDNN=ON, USE_CUSPARSELT=1, USE_GFLAGS=OFF, USE_GLOG=OFF, USE_GLOO=ON, USE_MKL=ON, USE_MKLDNN=ON, USE_MPI=OFF, USE_NCCL=1, USE_NNPACK=ON, USE_OPENMP=ON, USE_ROCM=OFF, USE_ROCM_KERNEL_ASSERT=OFF, \n"
   }
-}
+}

method_comparison/MetaMathQA/results/fourierft--llama-3.2-3B-default.json

@@ -56,9 +56,9 @@
     "error_msg": ""
   },
   "train_info": {
-    "cuda_memory_reserved_avg": 13104129350,
-    "cuda_memory_max": 23653777408,
-    "cuda_memory_reserved_99th": 19017267937,
+    "accelerator_memory_reserved_avg": 13104129350,
+    "accelerator_memory_max": 23653777408,
+    "accelerator_memory_reserved_99th": 19017267937,
     "train_time": 2424.3862988609762,
     "file_size": 231416,
     "num_trainable_params": 56000,
@@ -347,8 +347,8 @@
       "version": "#31-Ubuntu SMP Wed Apr 23 18:42:41 UTC 2025",
       "machine": "x86_64",
       "processor": "x86_64",
-      "gpu": "NVIDIA L40S"
+      "accelerator": "NVIDIA L40S"
     },
     "pytorch_info": "PyTorch built with:\n  - GCC 11.2\n  - C++ Version: 201703\n  - Intel(R) oneAPI Math Kernel Library Version 2024.2-Product Build 20240605 for Intel(R) 64 architecture applications\n  - Intel(R) MKL-DNN v3.7.1 (Git Hash 8d263e693366ef8db40acc569cc7d8edf644556d)\n  - OpenMP 201511 (a.k.a. OpenMP 4.5)\n  - LAPACK is enabled (usually provided by MKL)\n  - NNPACK is enabled\n  - CPU capability usage: AVX2\n  - CUDA Runtime 12.6\n  - NVCC architecture flags: -gencode;arch=compute_50,code=sm_50;-gencode;arch=compute_60,code=sm_60;-gencode;arch=compute_70,code=sm_70;-gencode;arch=compute_75,code=sm_75;-gencode;arch=compute_80,code=sm_80;-gencode;arch=compute_86,code=sm_86;-gencode;arch=compute_90,code=sm_90\n  - CuDNN 90.7.1  (built against CUDA 12.8)\n    - Built with CuDNN 90.5.1\n  - Magma 2.6.1\n  - Build settings: BLAS_INFO=mkl, BUILD_TYPE=Release, COMMIT_SHA=e2d141dbde55c2a4370fac5165b0561b6af4798b, CUDA_VERSION=12.6, CUDNN_VERSION=9.5.1, CXX_COMPILER=/opt/rh/gcc-toolset-11/root/usr/bin/c++, CXX_FLAGS= -D_GLIBCXX_USE_CXX11_ABI=1 -fvisibility-inlines-hidden -DUSE_PTHREADPOOL -DNDEBUG -DUSE_KINETO -DLIBKINETO_NOROCTRACER -DLIBKINETO_NOXPUPTI=ON -DUSE_FBGEMM -DUSE_PYTORCH_QNNPACK -DUSE_XNNPACK -DSYMBOLICATE_MOBILE_DEBUG_HANDLE -O2 -fPIC -Wall -Wextra -Werror=return-type -Werror=non-virtual-dtor -Werror=range-loop-construct -Werror=bool-operation -Wnarrowing -Wno-missing-field-initializers -Wno-unknown-pragmas -Wno-unused-parameter -Wno-strict-overflow -Wno-strict-aliasing -Wno-stringop-overflow -Wsuggest-override -Wno-psabi -Wno-error=old-style-cast -fdiagnostics-color=always -faligned-new -Wno-maybe-uninitialized -fno-math-errno -fno-trapping-math -Werror=format -Wno-stringop-overflow, LAPACK_INFO=mkl, PERF_WITH_AVX=1, PERF_WITH_AVX2=1, TORCH_VERSION=2.7.1, USE_CUDA=ON, USE_CUDNN=ON, USE_CUSPARSELT=1, USE_GFLAGS=OFF, USE_GLOG=OFF, USE_GLOO=ON, USE_MKL=ON, USE_MKLDNN=ON, USE_MPI=OFF, USE_NCCL=1, USE_NNPACK=ON, USE_OPENMP=ON, USE_ROCM=OFF, USE_ROCM_KERNEL_ASSERT=OFF, \n"
   }
-}
+}

method_comparison/MetaMathQA/results/fourierft--llama-3.2-3B-n_frequency-5000.json

@@ -56,9 +56,9 @@
     "error_msg": ""
   },
   "train_info": {
-    "cuda_memory_reserved_avg": 13111221498,
-    "cuda_memory_max": 23681040384,
-    "cuda_memory_reserved_99th": 19054869872,
+    "accelerator_memory_reserved_avg": 13111221498,
+    "accelerator_memory_max": 23681040384,
+    "accelerator_memory_reserved_99th": 19054869872,
     "train_time": 2421.913372163006,
     "file_size": 1127472,
     "num_trainable_params": 280000,
@@ -347,8 +347,8 @@
       "version": "#31-Ubuntu SMP Wed Apr 23 18:42:41 UTC 2025",
       "machine": "x86_64",
       "processor": "x86_64",
-      "gpu": "NVIDIA L40S"
+      "accelerator": "NVIDIA L40S"
     },
     "pytorch_info": "PyTorch built with:\n  - GCC 11.2\n  - C++ Version: 201703\n  - Intel(R) oneAPI Math Kernel Library Version 2024.2-Product Build 20240605 for Intel(R) 64 architecture applications\n  - Intel(R) MKL-DNN v3.7.1 (Git Hash 8d263e693366ef8db40acc569cc7d8edf644556d)\n  - OpenMP 201511 (a.k.a. OpenMP 4.5)\n  - LAPACK is enabled (usually provided by MKL)\n  - NNPACK is enabled\n  - CPU capability usage: AVX2\n  - CUDA Runtime 12.6\n  - NVCC architecture flags: -gencode;arch=compute_50,code=sm_50;-gencode;arch=compute_60,code=sm_60;-gencode;arch=compute_70,code=sm_70;-gencode;arch=compute_75,code=sm_75;-gencode;arch=compute_80,code=sm_80;-gencode;arch=compute_86,code=sm_86;-gencode;arch=compute_90,code=sm_90\n  - CuDNN 90.7.1  (built against CUDA 12.8)\n    - Built with CuDNN 90.5.1\n  - Magma 2.6.1\n  - Build settings: BLAS_INFO=mkl, BUILD_TYPE=Release, COMMIT_SHA=e2d141dbde55c2a4370fac5165b0561b6af4798b, CUDA_VERSION=12.6, CUDNN_VERSION=9.5.1, CXX_COMPILER=/opt/rh/gcc-toolset-11/root/usr/bin/c++, CXX_FLAGS= -D_GLIBCXX_USE_CXX11_ABI=1 -fvisibility-inlines-hidden -DUSE_PTHREADPOOL -DNDEBUG -DUSE_KINETO -DLIBKINETO_NOROCTRACER -DLIBKINETO_NOXPUPTI=ON -DUSE_FBGEMM -DUSE_PYTORCH_QNNPACK -DUSE_XNNPACK -DSYMBOLICATE_MOBILE_DEBUG_HANDLE -O2 -fPIC -Wall -Wextra -Werror=return-type -Werror=non-virtual-dtor -Werror=range-loop-construct -Werror=bool-operation -Wnarrowing -Wno-missing-field-initializers -Wno-unknown-pragmas -Wno-unused-parameter -Wno-strict-overflow -Wno-strict-aliasing -Wno-stringop-overflow -Wsuggest-override -Wno-psabi -Wno-error=old-style-cast -fdiagnostics-color=always -faligned-new -Wno-maybe-uninitialized -fno-math-errno -fno-trapping-math -Werror=format -Wno-stringop-overflow, LAPACK_INFO=mkl, PERF_WITH_AVX=1, PERF_WITH_AVX2=1, TORCH_VERSION=2.7.1, USE_CUDA=ON, USE_CUDNN=ON, USE_CUSPARSELT=1, USE_GFLAGS=OFF, USE_GLOG=OFF, USE_GLOO=ON, USE_MKL=ON, USE_MKLDNN=ON, USE_MPI=OFF, USE_NCCL=1, USE_NNPACK=ON, USE_OPENMP=ON, USE_ROCM=OFF, USE_ROCM_KERNEL_ASSERT=OFF, \n"
   }
-}
+}