diff --git a/7m100m100m/3571584.err b/7m100m100m/3571584.err new file mode 100644 index 0000000000000000000000000000000000000000..f1634998a5cbf429efd3f05a275989c3a576813e --- /dev/null +++ b/7m100m100m/3571584.err @@ -0,0 +1,257 @@ +1: 2023-05-23 21:56:55.656035: I tensorflow/core/platform/cpu_feature_guard.cc:193] This TensorFlow binary is optimized with oneAPI Deep Neural Network Library (oneDNN) to use the following CPU instructions in performance-critical operations: AVX2 FMA +1: To enable them in other operations, rebuild TensorFlow with the appropriate compiler flags. +1: 2023-05-23 21:56:55.656030: I tensorflow/core/platform/cpu_feature_guard.cc:193] This TensorFlow binary is optimized with oneAPI Deep Neural Network Library (oneDNN) to use the following CPU instructions in performance-critical operations: AVX2 FMA +1: To enable them in other operations, rebuild TensorFlow with the appropriate compiler flags. +1: 2023-05-23 21:56:55.656064: I tensorflow/core/platform/cpu_feature_guard.cc:193] This TensorFlow binary is optimized with oneAPI Deep Neural Network Library (oneDNN) to use the following CPU instructions in performance-critical operations: AVX2 FMA +1: To enable them in other operations, rebuild TensorFlow with the appropriate compiler flags. +1: 2023-05-23 21:56:55.656075: I tensorflow/core/platform/cpu_feature_guard.cc:193] This TensorFlow binary is optimized with oneAPI Deep Neural Network Library (oneDNN) to use the following CPU instructions in performance-critical operations: AVX2 FMA +1: To enable them in other operations, rebuild TensorFlow with the appropriate compiler flags. +1: 2023-05-23 21:56:55.656074: I tensorflow/core/platform/cpu_feature_guard.cc:193] This TensorFlow binary is optimized with oneAPI Deep Neural Network Library (oneDNN) to use the following CPU instructions in performance-critical operations: AVX2 FMA +1: To enable them in other operations, rebuild TensorFlow with the appropriate compiler flags. +1: 2023-05-23 21:56:55.656059: I tensorflow/core/platform/cpu_feature_guard.cc:193] This TensorFlow binary is optimized with oneAPI Deep Neural Network Library (oneDNN) to use the following CPU instructions in performance-critical operations: AVX2 FMA +1: To enable them in other operations, rebuild TensorFlow with the appropriate compiler flags. +1: 2023-05-23 21:56:55.656082: I tensorflow/core/platform/cpu_feature_guard.cc:193] This TensorFlow binary is optimized with oneAPI Deep Neural Network Library (oneDNN) to use the following CPU instructions in performance-critical operations: AVX2 FMA +1: To enable them in other operations, rebuild TensorFlow with the appropriate compiler flags. +1: 2023-05-23 21:56:55.656101: I tensorflow/core/platform/cpu_feature_guard.cc:193] This TensorFlow binary is optimized with oneAPI Deep Neural Network Library (oneDNN) to use the following CPU instructions in performance-critical operations: AVX2 FMA +1: To enable them in other operations, rebuild TensorFlow with the appropriate compiler flags. +0: 2023-05-23 21:56:55.657068: I tensorflow/core/platform/cpu_feature_guard.cc:193] This TensorFlow binary is optimized with oneAPI Deep Neural Network Library (oneDNN) to use the following CPU instructions in performance-critical operations: AVX2 FMA +0: To enable them in other operations, rebuild TensorFlow with the appropriate compiler flags. +0: 2023-05-23 21:56:55.657085: I tensorflow/core/platform/cpu_feature_guard.cc:193] This TensorFlow binary is optimized with oneAPI Deep Neural Network Library (oneDNN) to use the following CPU instructions in performance-critical operations: AVX2 FMA +0: To enable them in other operations, rebuild TensorFlow with the appropriate compiler flags. +0: 2023-05-23 21:56:55.657096: I tensorflow/core/platform/cpu_feature_guard.cc:193] This TensorFlow binary is optimized with oneAPI Deep Neural Network Library (oneDNN) to use the following CPU instructions in performance-critical operations: AVX2 FMA +0: To enable them in other operations, rebuild TensorFlow with the appropriate compiler flags. +0: 2023-05-23 21:56:55.657097: I tensorflow/core/platform/cpu_feature_guard.cc:193] This TensorFlow binary is optimized with oneAPI Deep Neural Network Library (oneDNN) to use the following CPU instructions in performance-critical operations: AVX2 FMA +0: To enable them in other operations, rebuild TensorFlow with the appropriate compiler flags. +0: 2023-05-23 21:56:55.657098: I tensorflow/core/platform/cpu_feature_guard.cc:193] This TensorFlow binary is optimized with oneAPI Deep Neural Network Library (oneDNN) to use the following CPU instructions in performance-critical operations: AVX2 FMA +0: To enable them in other operations, rebuild TensorFlow with the appropriate compiler flags. +0: 2023-05-23 21:56:55.657080: I tensorflow/core/platform/cpu_feature_guard.cc:193] This TensorFlow binary is optimized with oneAPI Deep Neural Network Library (oneDNN) to use the following CPU instructions in performance-critical operations: AVX2 FMA +0: To enable them in other operations, rebuild TensorFlow with the appropriate compiler flags. +0: 2023-05-23 21:56:55.657105: I tensorflow/core/platform/cpu_feature_guard.cc:193] This TensorFlow binary is optimized with oneAPI Deep Neural Network Library (oneDNN) to use the following CPU instructions in performance-critical operations: AVX2 FMA +0: To enable them in other operations, rebuild TensorFlow with the appropriate compiler flags. +0: 2023-05-23 21:56:55.657095: I tensorflow/core/platform/cpu_feature_guard.cc:193] This TensorFlow binary is optimized with oneAPI Deep Neural Network Library (oneDNN) to use the following CPU instructions in performance-critical operations: AVX2 FMA +0: To enable them in other operations, rebuild TensorFlow with the appropriate compiler flags. +0: 2023-05-23 21:56:58.533548: W tensorflow/compiler/xla/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'libcudart.so.11.0'; dlerror: libcudart.so.11.0: cannot open shared object file: No such file or directory; LD_LIBRARY_PATH: /pfs/lustrep2/projappl/project_462000125/samantao-public/apps-rocm-5.2.3/aws-ofi-rccl:/opt/rocm/lib64:/opt/rocm/lib:/opt/rocm/rocprofiler/lib:/opt/rocm/rocprofiler/tool:/opt/rocm/roctracer/lib:/opt/rocm/roctracer/tool:/opt/rocm/hip/lib:/opt/cray/pe/python/3.9.13.1/lib:/opt/cray/pe/gcc-libs:/opt/cray/libfabric/1.15.2.0/lib64 +0: 2023-05-23 21:56:58.533560: W tensorflow/compiler/xla/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'libcudart.so.11.0'; dlerror: libcudart.so.11.0: cannot open shared object file: No such file or directory; LD_LIBRARY_PATH: /pfs/lustrep2/projappl/project_462000125/samantao-public/apps-rocm-5.2.3/aws-ofi-rccl:/opt/rocm/lib64:/opt/rocm/lib:/opt/rocm/rocprofiler/lib:/opt/rocm/rocprofiler/tool:/opt/rocm/roctracer/lib:/opt/rocm/roctracer/tool:/opt/rocm/hip/lib:/opt/cray/pe/python/3.9.13.1/lib:/opt/cray/pe/gcc-libs:/opt/cray/libfabric/1.15.2.0/lib64 +1: 2023-05-23 21:56:58.533595: W tensorflow/compiler/xla/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'libcudart.so.11.0'; dlerror: libcudart.so.11.0: cannot open shared object file: No such file or directory; LD_LIBRARY_PATH: /pfs/lustrep2/projappl/project_462000125/samantao-public/apps-rocm-5.2.3/aws-ofi-rccl:/opt/rocm/lib64:/opt/rocm/lib:/opt/rocm/rocprofiler/lib:/opt/rocm/rocprofiler/tool:/opt/rocm/roctracer/lib:/opt/rocm/roctracer/tool:/opt/rocm/hip/lib:/opt/cray/pe/python/3.9.13.1/lib:/opt/cray/pe/gcc-libs:/opt/cray/libfabric/1.15.2.0/lib64 +0: 2023-05-23 21:56:58.533563: W tensorflow/compiler/xla/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'libcudart.so.11.0'; dlerror: libcudart.so.11.0: cannot open shared object file: No such file or directory; LD_LIBRARY_PATH: /pfs/lustrep2/projappl/project_462000125/samantao-public/apps-rocm-5.2.3/aws-ofi-rccl:/opt/rocm/lib64:/opt/rocm/lib:/opt/rocm/rocprofiler/lib:/opt/rocm/rocprofiler/tool:/opt/rocm/roctracer/lib:/opt/rocm/roctracer/tool:/opt/rocm/hip/lib:/opt/cray/pe/python/3.9.13.1/lib:/opt/cray/pe/gcc-libs:/opt/cray/libfabric/1.15.2.0/lib64 +1: 2023-05-23 21:56:58.533593: W tensorflow/compiler/xla/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'libcudart.so.11.0'; dlerror: libcudart.so.11.0: cannot open shared object file: No such file or directory; LD_LIBRARY_PATH: /pfs/lustrep2/projappl/project_462000125/samantao-public/apps-rocm-5.2.3/aws-ofi-rccl:/opt/rocm/lib64:/opt/rocm/lib:/opt/rocm/rocprofiler/lib:/opt/rocm/rocprofiler/tool:/opt/rocm/roctracer/lib:/opt/rocm/roctracer/tool:/opt/rocm/hip/lib:/opt/cray/pe/python/3.9.13.1/lib:/opt/cray/pe/gcc-libs:/opt/cray/libfabric/1.15.2.0/lib64 +0: 2023-05-23 21:56:58.533556: W tensorflow/compiler/xla/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'libcudart.so.11.0'; dlerror: libcudart.so.11.0: cannot open shared object file: No such file or directory; LD_LIBRARY_PATH: /pfs/lustrep2/projappl/project_462000125/samantao-public/apps-rocm-5.2.3/aws-ofi-rccl:/opt/rocm/lib64:/opt/rocm/lib:/opt/rocm/rocprofiler/lib:/opt/rocm/rocprofiler/tool:/opt/rocm/roctracer/lib:/opt/rocm/roctracer/tool:/opt/rocm/hip/lib:/opt/cray/pe/python/3.9.13.1/lib:/opt/cray/pe/gcc-libs:/opt/cray/libfabric/1.15.2.0/lib64 +1: 2023-05-23 21:56:58.533602: W tensorflow/compiler/xla/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'libcudart.so.11.0'; dlerror: libcudart.so.11.0: cannot open shared object file: No such file or directory; LD_LIBRARY_PATH: /pfs/lustrep2/projappl/project_462000125/samantao-public/apps-rocm-5.2.3/aws-ofi-rccl:/opt/rocm/lib64:/opt/rocm/lib:/opt/rocm/rocprofiler/lib:/opt/rocm/rocprofiler/tool:/opt/rocm/roctracer/lib:/opt/rocm/roctracer/tool:/opt/rocm/hip/lib:/opt/cray/pe/python/3.9.13.1/lib:/opt/cray/pe/gcc-libs:/opt/cray/libfabric/1.15.2.0/lib64 +0: 2023-05-23 21:56:58.533567: W tensorflow/compiler/xla/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'libcudart.so.11.0'; dlerror: libcudart.so.11.0: cannot open shared object file: No such file or directory; LD_LIBRARY_PATH: /pfs/lustrep2/projappl/project_462000125/samantao-public/apps-rocm-5.2.3/aws-ofi-rccl:/opt/rocm/lib64:/opt/rocm/lib:/opt/rocm/rocprofiler/lib:/opt/rocm/rocprofiler/tool:/opt/rocm/roctracer/lib:/opt/rocm/roctracer/tool:/opt/rocm/hip/lib:/opt/cray/pe/python/3.9.13.1/lib:/opt/cray/pe/gcc-libs:/opt/cray/libfabric/1.15.2.0/lib64 +1: 2023-05-23 21:56:58.533610: W tensorflow/compiler/xla/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'libcudart.so.11.0'; dlerror: libcudart.so.11.0: cannot open shared object file: No such file or directory; LD_LIBRARY_PATH: /pfs/lustrep2/projappl/project_462000125/samantao-public/apps-rocm-5.2.3/aws-ofi-rccl:/opt/rocm/lib64:/opt/rocm/lib:/opt/rocm/rocprofiler/lib:/opt/rocm/rocprofiler/tool:/opt/rocm/roctracer/lib:/opt/rocm/roctracer/tool:/opt/rocm/hip/lib:/opt/cray/pe/python/3.9.13.1/lib:/opt/cray/pe/gcc-libs:/opt/cray/libfabric/1.15.2.0/lib64 +0: 2023-05-23 21:56:58.533565: W tensorflow/compiler/xla/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'libcudart.so.11.0'; dlerror: libcudart.so.11.0: cannot open shared object file: No such file or directory; LD_LIBRARY_PATH: /pfs/lustrep2/projappl/project_462000125/samantao-public/apps-rocm-5.2.3/aws-ofi-rccl:/opt/rocm/lib64:/opt/rocm/lib:/opt/rocm/rocprofiler/lib:/opt/rocm/rocprofiler/tool:/opt/rocm/roctracer/lib:/opt/rocm/roctracer/tool:/opt/rocm/hip/lib:/opt/cray/pe/python/3.9.13.1/lib:/opt/cray/pe/gcc-libs:/opt/cray/libfabric/1.15.2.0/lib64 +1: 2023-05-23 21:56:58.533607: W tensorflow/compiler/xla/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'libcudart.so.11.0'; dlerror: libcudart.so.11.0: cannot open shared object file: No such file or directory; LD_LIBRARY_PATH: /pfs/lustrep2/projappl/project_462000125/samantao-public/apps-rocm-5.2.3/aws-ofi-rccl:/opt/rocm/lib64:/opt/rocm/lib:/opt/rocm/rocprofiler/lib:/opt/rocm/rocprofiler/tool:/opt/rocm/roctracer/lib:/opt/rocm/roctracer/tool:/opt/rocm/hip/lib:/opt/cray/pe/python/3.9.13.1/lib:/opt/cray/pe/gcc-libs:/opt/cray/libfabric/1.15.2.0/lib64 +0: 2023-05-23 21:56:58.533575: W tensorflow/compiler/xla/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'libcudart.so.11.0'; dlerror: libcudart.so.11.0: cannot open shared object file: No such file or directory; LD_LIBRARY_PATH: /pfs/lustrep2/projappl/project_462000125/samantao-public/apps-rocm-5.2.3/aws-ofi-rccl:/opt/rocm/lib64:/opt/rocm/lib:/opt/rocm/rocprofiler/lib:/opt/rocm/rocprofiler/tool:/opt/rocm/roctracer/lib:/opt/rocm/roctracer/tool:/opt/rocm/hip/lib:/opt/cray/pe/python/3.9.13.1/lib:/opt/cray/pe/gcc-libs:/opt/cray/libfabric/1.15.2.0/lib64 +1: 2023-05-23 21:56:58.533609: W tensorflow/compiler/xla/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'libcudart.so.11.0'; dlerror: libcudart.so.11.0: cannot open shared object file: No such file or directory; LD_LIBRARY_PATH: /pfs/lustrep2/projappl/project_462000125/samantao-public/apps-rocm-5.2.3/aws-ofi-rccl:/opt/rocm/lib64:/opt/rocm/lib:/opt/rocm/rocprofiler/lib:/opt/rocm/rocprofiler/tool:/opt/rocm/roctracer/lib:/opt/rocm/roctracer/tool:/opt/rocm/hip/lib:/opt/cray/pe/python/3.9.13.1/lib:/opt/cray/pe/gcc-libs:/opt/cray/libfabric/1.15.2.0/lib64 +0: 2023-05-23 21:56:58.533571: W tensorflow/compiler/xla/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'libcudart.so.11.0'; dlerror: libcudart.so.11.0: cannot open shared object file: No such file or directory; LD_LIBRARY_PATH: /pfs/lustrep2/projappl/project_462000125/samantao-public/apps-rocm-5.2.3/aws-ofi-rccl:/opt/rocm/lib64:/opt/rocm/lib:/opt/rocm/rocprofiler/lib:/opt/rocm/rocprofiler/tool:/opt/rocm/roctracer/lib:/opt/rocm/roctracer/tool:/opt/rocm/hip/lib:/opt/cray/pe/python/3.9.13.1/lib:/opt/cray/pe/gcc-libs:/opt/cray/libfabric/1.15.2.0/lib64 +1: 2023-05-23 21:56:58.533607: W tensorflow/compiler/xla/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'libcudart.so.11.0'; dlerror: libcudart.so.11.0: cannot open shared object file: No such file or directory; LD_LIBRARY_PATH: /pfs/lustrep2/projappl/project_462000125/samantao-public/apps-rocm-5.2.3/aws-ofi-rccl:/opt/rocm/lib64:/opt/rocm/lib:/opt/rocm/rocprofiler/lib:/opt/rocm/rocprofiler/tool:/opt/rocm/roctracer/lib:/opt/rocm/roctracer/tool:/opt/rocm/hip/lib:/opt/cray/pe/python/3.9.13.1/lib:/opt/cray/pe/gcc-libs:/opt/cray/libfabric/1.15.2.0/lib64 +1: 2023-05-23 21:56:58.533609: W tensorflow/compiler/xla/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'libcudart.so.11.0'; dlerror: libcudart.so.11.0: cannot open shared object file: No such file or directory; LD_LIBRARY_PATH: /pfs/lustrep2/projappl/project_462000125/samantao-public/apps-rocm-5.2.3/aws-ofi-rccl:/opt/rocm/lib64:/opt/rocm/lib:/opt/rocm/rocprofiler/lib:/opt/rocm/rocprofiler/tool:/opt/rocm/roctracer/lib:/opt/rocm/roctracer/tool:/opt/rocm/hip/lib:/opt/cray/pe/python/3.9.13.1/lib:/opt/cray/pe/gcc-libs:/opt/cray/libfabric/1.15.2.0/lib64 +0: 2023-05-23 21:56:58.534433: I tensorflow/compiler/xla/stream_executor/cuda/cudart_stub.cc:29] Ignore above cudart dlerror if you do not have a GPU set up on your machine. +0: 2023-05-23 21:56:58.534441: I tensorflow/compiler/xla/stream_executor/cuda/cudart_stub.cc:29] Ignore above cudart dlerror if you do not have a GPU set up on your machine. +0: 2023-05-23 21:56:58.534446: I tensorflow/compiler/xla/stream_executor/cuda/cudart_stub.cc:29] Ignore above cudart dlerror if you do not have a GPU set up on your machine. +0: 2023-05-23 21:56:58.534449: I tensorflow/compiler/xla/stream_executor/cuda/cudart_stub.cc:29] Ignore above cudart dlerror if you do not have a GPU set up on your machine. +0: 2023-05-23 21:56:58.534449: I tensorflow/compiler/xla/stream_executor/cuda/cudart_stub.cc:29] Ignore above cudart dlerror if you do not have a GPU set up on your machine. +0: 2023-05-23 21:56:58.534449: I tensorflow/compiler/xla/stream_executor/cuda/cudart_stub.cc:29] Ignore above cudart dlerror if you do not have a GPU set up on your machine. +0: 2023-05-23 21:56:58.534450: I tensorflow/compiler/xla/stream_executor/cuda/cudart_stub.cc:29] Ignore above cudart dlerror if you do not have a GPU set up on your machine. +0: 2023-05-23 21:56:58.534455: I tensorflow/compiler/xla/stream_executor/cuda/cudart_stub.cc:29] Ignore above cudart dlerror if you do not have a GPU set up on your machine. +1: 2023-05-23 21:56:58.534454: I tensorflow/compiler/xla/stream_executor/cuda/cudart_stub.cc:29] Ignore above cudart dlerror if you do not have a GPU set up on your machine. +1: 2023-05-23 21:56:58.534458: I tensorflow/compiler/xla/stream_executor/cuda/cudart_stub.cc:29] Ignore above cudart dlerror if you do not have a GPU set up on your machine. +1: 2023-05-23 21:56:58.534464: I tensorflow/compiler/xla/stream_executor/cuda/cudart_stub.cc:29] Ignore above cudart dlerror if you do not have a GPU set up on your machine. +1: 2023-05-23 21:56:58.534466: I tensorflow/compiler/xla/stream_executor/cuda/cudart_stub.cc:29] Ignore above cudart dlerror if you do not have a GPU set up on your machine. +1: 2023-05-23 21:56:58.534470: I tensorflow/compiler/xla/stream_executor/cuda/cudart_stub.cc:29] Ignore above cudart dlerror if you do not have a GPU set up on your machine. +1: 2023-05-23 21:56:58.534473: I tensorflow/compiler/xla/stream_executor/cuda/cudart_stub.cc:29] Ignore above cudart dlerror if you do not have a GPU set up on your machine. +1: 2023-05-23 21:56:58.534475: I tensorflow/compiler/xla/stream_executor/cuda/cudart_stub.cc:29] Ignore above cudart dlerror if you do not have a GPU set up on your machine. +1: 2023-05-23 21:56:58.534477: I tensorflow/compiler/xla/stream_executor/cuda/cudart_stub.cc:29] Ignore above cudart dlerror if you do not have a GPU set up on your machine. +0: 2023-05-23 21:57:04.859797: W tensorflow/compiler/xla/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'libnvinfer.so.7'; dlerror: libnvinfer.so.7: cannot open shared object file: No such file or directory; LD_LIBRARY_PATH: /pfs/lustrep2/projappl/project_462000125/samantao-public/apps-rocm-5.2.3/aws-ofi-rccl:/opt/rocm/lib64:/opt/rocm/lib:/opt/rocm/rocprofiler/lib:/opt/rocm/rocprofiler/tool:/opt/rocm/roctracer/lib:/opt/rocm/roctracer/tool:/opt/rocm/hip/lib:/opt/cray/pe/python/3.9.13.1/lib:/opt/cray/pe/gcc-libs:/opt/cray/libfabric/1.15.2.0/lib64 +0: 2023-05-23 21:57:04.859806: W tensorflow/compiler/xla/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'libnvinfer.so.7'; dlerror: libnvinfer.so.7: cannot open shared object file: No such file or directory; LD_LIBRARY_PATH: /pfs/lustrep2/projappl/project_462000125/samantao-public/apps-rocm-5.2.3/aws-ofi-rccl:/opt/rocm/lib64:/opt/rocm/lib:/opt/rocm/rocprofiler/lib:/opt/rocm/rocprofiler/tool:/opt/rocm/roctracer/lib:/opt/rocm/roctracer/tool:/opt/rocm/hip/lib:/opt/cray/pe/python/3.9.13.1/lib:/opt/cray/pe/gcc-libs:/opt/cray/libfabric/1.15.2.0/lib64 +0: 2023-05-23 21:57:04.859808: W tensorflow/compiler/xla/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'libnvinfer.so.7'; dlerror: libnvinfer.so.7: cannot open shared object file: No such file or directory; LD_LIBRARY_PATH: /pfs/lustrep2/projappl/project_462000125/samantao-public/apps-rocm-5.2.3/aws-ofi-rccl:/opt/rocm/lib64:/opt/rocm/lib:/opt/rocm/rocprofiler/lib:/opt/rocm/rocprofiler/tool:/opt/rocm/roctracer/lib:/opt/rocm/roctracer/tool:/opt/rocm/hip/lib:/opt/cray/pe/python/3.9.13.1/lib:/opt/cray/pe/gcc-libs:/opt/cray/libfabric/1.15.2.0/lib64 +0: 2023-05-23 21:57:04.859811: W tensorflow/compiler/xla/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'libnvinfer.so.7'; dlerror: libnvinfer.so.7: cannot open shared object file: No such file or directory; LD_LIBRARY_PATH: /pfs/lustrep2/projappl/project_462000125/samantao-public/apps-rocm-5.2.3/aws-ofi-rccl:/opt/rocm/lib64:/opt/rocm/lib:/opt/rocm/rocprofiler/lib:/opt/rocm/rocprofiler/tool:/opt/rocm/roctracer/lib:/opt/rocm/roctracer/tool:/opt/rocm/hip/lib:/opt/cray/pe/python/3.9.13.1/lib:/opt/cray/pe/gcc-libs:/opt/cray/libfabric/1.15.2.0/lib64 +0: 2023-05-23 21:57:04.859806: W tensorflow/compiler/xla/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'libnvinfer.so.7'; dlerror: libnvinfer.so.7: cannot open shared object file: No such file or directory; LD_LIBRARY_PATH: /pfs/lustrep2/projappl/project_462000125/samantao-public/apps-rocm-5.2.3/aws-ofi-rccl:/opt/rocm/lib64:/opt/rocm/lib:/opt/rocm/rocprofiler/lib:/opt/rocm/rocprofiler/tool:/opt/rocm/roctracer/lib:/opt/rocm/roctracer/tool:/opt/rocm/hip/lib:/opt/cray/pe/python/3.9.13.1/lib:/opt/cray/pe/gcc-libs:/opt/cray/libfabric/1.15.2.0/lib64 +0: 2023-05-23 21:57:04.859811: W tensorflow/compiler/xla/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'libnvinfer.so.7'; dlerror: libnvinfer.so.7: cannot open shared object file: No such file or directory; LD_LIBRARY_PATH: /pfs/lustrep2/projappl/project_462000125/samantao-public/apps-rocm-5.2.3/aws-ofi-rccl:/opt/rocm/lib64:/opt/rocm/lib:/opt/rocm/rocprofiler/lib:/opt/rocm/rocprofiler/tool:/opt/rocm/roctracer/lib:/opt/rocm/roctracer/tool:/opt/rocm/hip/lib:/opt/cray/pe/python/3.9.13.1/lib:/opt/cray/pe/gcc-libs:/opt/cray/libfabric/1.15.2.0/lib64 +0: 2023-05-23 21:57:04.859816: W tensorflow/compiler/xla/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'libnvinfer.so.7'; dlerror: libnvinfer.so.7: cannot open shared object file: No such file or directory; LD_LIBRARY_PATH: /pfs/lustrep2/projappl/project_462000125/samantao-public/apps-rocm-5.2.3/aws-ofi-rccl:/opt/rocm/lib64:/opt/rocm/lib:/opt/rocm/rocprofiler/lib:/opt/rocm/rocprofiler/tool:/opt/rocm/roctracer/lib:/opt/rocm/roctracer/tool:/opt/rocm/hip/lib:/opt/cray/pe/python/3.9.13.1/lib:/opt/cray/pe/gcc-libs:/opt/cray/libfabric/1.15.2.0/lib64 +0: 2023-05-23 21:57:04.859819: W tensorflow/compiler/xla/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'libnvinfer.so.7'; dlerror: libnvinfer.so.7: cannot open shared object file: No such file or directory; LD_LIBRARY_PATH: /pfs/lustrep2/projappl/project_462000125/samantao-public/apps-rocm-5.2.3/aws-ofi-rccl:/opt/rocm/lib64:/opt/rocm/lib:/opt/rocm/rocprofiler/lib:/opt/rocm/rocprofiler/tool:/opt/rocm/roctracer/lib:/opt/rocm/roctracer/tool:/opt/rocm/hip/lib:/opt/cray/pe/python/3.9.13.1/lib:/opt/cray/pe/gcc-libs:/opt/cray/libfabric/1.15.2.0/lib64 +0: 2023-05-23 21:57:04.885281: W tensorflow/compiler/xla/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'libnvinfer_plugin.so.7'; dlerror: libnvinfer_plugin.so.7: cannot open shared object file: No such file or directory; LD_LIBRARY_PATH: /pfs/lustrep2/projappl/project_462000125/samantao-public/apps-rocm-5.2.3/aws-ofi-rccl:/opt/rocm/lib64:/opt/rocm/lib:/opt/rocm/rocprofiler/lib:/opt/rocm/rocprofiler/tool:/opt/rocm/roctracer/lib:/opt/rocm/roctracer/tool:/opt/rocm/hip/lib:/opt/cray/pe/python/3.9.13.1/lib:/opt/cray/pe/gcc-libs:/opt/cray/libfabric/1.15.2.0/lib64 +0: 2023-05-23 21:57:04.885281: W tensorflow/compiler/xla/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'libnvinfer_plugin.so.7'; dlerror: libnvinfer_plugin.so.7: cannot open shared object file: No such file or directory; LD_LIBRARY_PATH: /pfs/lustrep2/projappl/project_462000125/samantao-public/apps-rocm-5.2.3/aws-ofi-rccl:/opt/rocm/lib64:/opt/rocm/lib:/opt/rocm/rocprofiler/lib:/opt/rocm/rocprofiler/tool:/opt/rocm/roctracer/lib:/opt/rocm/roctracer/tool:/opt/rocm/hip/lib:/opt/cray/pe/python/3.9.13.1/lib:/opt/cray/pe/gcc-libs:/opt/cray/libfabric/1.15.2.0/lib64 +0: 2023-05-23 21:57:04.885284: W tensorflow/compiler/xla/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'libnvinfer_plugin.so.7'; dlerror: libnvinfer_plugin.so.7: cannot open shared object file: No such file or directory; LD_LIBRARY_PATH: /pfs/lustrep2/projappl/project_462000125/samantao-public/apps-rocm-5.2.3/aws-ofi-rccl:/opt/rocm/lib64:/opt/rocm/lib:/opt/rocm/rocprofiler/lib:/opt/rocm/rocprofiler/tool:/opt/rocm/roctracer/lib:/opt/rocm/roctracer/tool:/opt/rocm/hip/lib:/opt/cray/pe/python/3.9.13.1/lib:/opt/cray/pe/gcc-libs:/opt/cray/libfabric/1.15.2.0/lib64 +0: 2023-05-23 21:57:04.885287: W tensorflow/compiler/xla/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'libnvinfer_plugin.so.7'; dlerror: libnvinfer_plugin.so.7: cannot open shared object file: No such file or directory; LD_LIBRARY_PATH: /pfs/lustrep2/projappl/project_462000125/samantao-public/apps-rocm-5.2.3/aws-ofi-rccl:/opt/rocm/lib64:/opt/rocm/lib:/opt/rocm/rocprofiler/lib:/opt/rocm/rocprofiler/tool:/opt/rocm/roctracer/lib:/opt/rocm/roctracer/tool:/opt/rocm/hip/lib:/opt/cray/pe/python/3.9.13.1/lib:/opt/cray/pe/gcc-libs:/opt/cray/libfabric/1.15.2.0/lib64 +0: 2023-05-23 21:57:04.885290: W tensorflow/compiler/xla/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'libnvinfer_plugin.so.7'; dlerror: libnvinfer_plugin.so.7: cannot open shared object file: No such file or directory; LD_LIBRARY_PATH: /pfs/lustrep2/projappl/project_462000125/samantao-public/apps-rocm-5.2.3/aws-ofi-rccl:/opt/rocm/lib64:/opt/rocm/lib:/opt/rocm/rocprofiler/lib:/opt/rocm/rocprofiler/tool:/opt/rocm/roctracer/lib:/opt/rocm/roctracer/tool:/opt/rocm/hip/lib:/opt/cray/pe/python/3.9.13.1/lib:/opt/cray/pe/gcc-libs:/opt/cray/libfabric/1.15.2.0/lib64 +0: 2023-05-23 21:57:04.885293: W tensorflow/compiler/xla/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'libnvinfer_plugin.so.7'; dlerror: libnvinfer_plugin.so.7: cannot open shared object file: No such file or directory; LD_LIBRARY_PATH: /pfs/lustrep2/projappl/project_462000125/samantao-public/apps-rocm-5.2.3/aws-ofi-rccl:/opt/rocm/lib64:/opt/rocm/lib:/opt/rocm/rocprofiler/lib:/opt/rocm/rocprofiler/tool:/opt/rocm/roctracer/lib:/opt/rocm/roctracer/tool:/opt/rocm/hip/lib:/opt/cray/pe/python/3.9.13.1/lib:/opt/cray/pe/gcc-libs:/opt/cray/libfabric/1.15.2.0/lib64 +0: 2023-05-23 21:57:04.885294: W tensorflow/compiler/xla/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'libnvinfer_plugin.so.7'; dlerror: libnvinfer_plugin.so.7: cannot open shared object file: No such file or directory; LD_LIBRARY_PATH: /pfs/lustrep2/projappl/project_462000125/samantao-public/apps-rocm-5.2.3/aws-ofi-rccl:/opt/rocm/lib64:/opt/rocm/lib:/opt/rocm/rocprofiler/lib:/opt/rocm/rocprofiler/tool:/opt/rocm/roctracer/lib:/opt/rocm/roctracer/tool:/opt/rocm/hip/lib:/opt/cray/pe/python/3.9.13.1/lib:/opt/cray/pe/gcc-libs:/opt/cray/libfabric/1.15.2.0/lib64 +0: 2023-05-23 21:57:04.885309: W tensorflow/compiler/tf2tensorrt/utils/py_utils.cc:38] TF-TRT Warning: Cannot dlopen some TensorRT libraries. If you would like to use Nvidia GPU with TensorRT, please make sure the missing libraries mentioned above are installed properly. +0: 2023-05-23 21:57:04.885309: W tensorflow/compiler/tf2tensorrt/utils/py_utils.cc:38] TF-TRT Warning: Cannot dlopen some TensorRT libraries. If you would like to use Nvidia GPU with TensorRT, please make sure the missing libraries mentioned above are installed properly. +0: 2023-05-23 21:57:04.885310: W tensorflow/compiler/tf2tensorrt/utils/py_utils.cc:38] TF-TRT Warning: Cannot dlopen some TensorRT libraries. If you would like to use Nvidia GPU with TensorRT, please make sure the missing libraries mentioned above are installed properly. +0: 2023-05-23 21:57:04.885310: W tensorflow/compiler/tf2tensorrt/utils/py_utils.cc:38] TF-TRT Warning: Cannot dlopen some TensorRT libraries. If you would like to use Nvidia GPU with TensorRT, please make sure the missing libraries mentioned above are installed properly. +0: 2023-05-23 21:57:04.885311: W tensorflow/compiler/tf2tensorrt/utils/py_utils.cc:38] TF-TRT Warning: Cannot dlopen some TensorRT libraries. If you would like to use Nvidia GPU with TensorRT, please make sure the missing libraries mentioned above are installed properly. +0: 2023-05-23 21:57:04.885311: W tensorflow/compiler/tf2tensorrt/utils/py_utils.cc:38] TF-TRT Warning: Cannot dlopen some TensorRT libraries. If you would like to use Nvidia GPU with TensorRT, please make sure the missing libraries mentioned above are installed properly. +0: 2023-05-23 21:57:04.885313: W tensorflow/compiler/tf2tensorrt/utils/py_utils.cc:38] TF-TRT Warning: Cannot dlopen some TensorRT libraries. If you would like to use Nvidia GPU with TensorRT, please make sure the missing libraries mentioned above are installed properly. +1: 2023-05-23 21:57:04.887343: W tensorflow/compiler/xla/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'libnvinfer.so.7'; dlerror: libnvinfer.so.7: cannot open shared object file: No such file or directory; LD_LIBRARY_PATH: /pfs/lustrep2/projappl/project_462000125/samantao-public/apps-rocm-5.2.3/aws-ofi-rccl:/opt/rocm/lib64:/opt/rocm/lib:/opt/rocm/rocprofiler/lib:/opt/rocm/rocprofiler/tool:/opt/rocm/roctracer/lib:/opt/rocm/roctracer/tool:/opt/rocm/hip/lib:/opt/cray/pe/python/3.9.13.1/lib:/opt/cray/pe/gcc-libs:/opt/cray/libfabric/1.15.2.0/lib64 +1: 2023-05-23 21:57:04.887347: W tensorflow/compiler/xla/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'libnvinfer.so.7'; dlerror: libnvinfer.so.7: cannot open shared object file: No such file or directory; LD_LIBRARY_PATH: /pfs/lustrep2/projappl/project_462000125/samantao-public/apps-rocm-5.2.3/aws-ofi-rccl:/opt/rocm/lib64:/opt/rocm/lib:/opt/rocm/rocprofiler/lib:/opt/rocm/rocprofiler/tool:/opt/rocm/roctracer/lib:/opt/rocm/roctracer/tool:/opt/rocm/hip/lib:/opt/cray/pe/python/3.9.13.1/lib:/opt/cray/pe/gcc-libs:/opt/cray/libfabric/1.15.2.0/lib64 +1: 2023-05-23 21:57:04.887353: W tensorflow/compiler/xla/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'libnvinfer.so.7'; dlerror: libnvinfer.so.7: cannot open shared object file: No such file or directory; LD_LIBRARY_PATH: /pfs/lustrep2/projappl/project_462000125/samantao-public/apps-rocm-5.2.3/aws-ofi-rccl:/opt/rocm/lib64:/opt/rocm/lib:/opt/rocm/rocprofiler/lib:/opt/rocm/rocprofiler/tool:/opt/rocm/roctracer/lib:/opt/rocm/roctracer/tool:/opt/rocm/hip/lib:/opt/cray/pe/python/3.9.13.1/lib:/opt/cray/pe/gcc-libs:/opt/cray/libfabric/1.15.2.0/lib64 +1: 2023-05-23 21:57:04.887356: W tensorflow/compiler/xla/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'libnvinfer.so.7'; dlerror: libnvinfer.so.7: cannot open shared object file: No such file or directory; LD_LIBRARY_PATH: /pfs/lustrep2/projappl/project_462000125/samantao-public/apps-rocm-5.2.3/aws-ofi-rccl:/opt/rocm/lib64:/opt/rocm/lib:/opt/rocm/rocprofiler/lib:/opt/rocm/rocprofiler/tool:/opt/rocm/roctracer/lib:/opt/rocm/roctracer/tool:/opt/rocm/hip/lib:/opt/cray/pe/python/3.9.13.1/lib:/opt/cray/pe/gcc-libs:/opt/cray/libfabric/1.15.2.0/lib64 +1: 2023-05-23 21:57:04.887356: W tensorflow/compiler/xla/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'libnvinfer.so.7'; dlerror: libnvinfer.so.7: cannot open shared object file: No such file or directory; LD_LIBRARY_PATH: /pfs/lustrep2/projappl/project_462000125/samantao-public/apps-rocm-5.2.3/aws-ofi-rccl:/opt/rocm/lib64:/opt/rocm/lib:/opt/rocm/rocprofiler/lib:/opt/rocm/rocprofiler/tool:/opt/rocm/roctracer/lib:/opt/rocm/roctracer/tool:/opt/rocm/hip/lib:/opt/cray/pe/python/3.9.13.1/lib:/opt/cray/pe/gcc-libs:/opt/cray/libfabric/1.15.2.0/lib64 +1: 2023-05-23 21:57:04.887360: W tensorflow/compiler/xla/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'libnvinfer.so.7'; dlerror: libnvinfer.so.7: cannot open shared object file: No such file or directory; LD_LIBRARY_PATH: /pfs/lustrep2/projappl/project_462000125/samantao-public/apps-rocm-5.2.3/aws-ofi-rccl:/opt/rocm/lib64:/opt/rocm/lib:/opt/rocm/rocprofiler/lib:/opt/rocm/rocprofiler/tool:/opt/rocm/roctracer/lib:/opt/rocm/roctracer/tool:/opt/rocm/hip/lib:/opt/cray/pe/python/3.9.13.1/lib:/opt/cray/pe/gcc-libs:/opt/cray/libfabric/1.15.2.0/lib64 +1: 2023-05-23 21:57:04.887363: W tensorflow/compiler/xla/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'libnvinfer.so.7'; dlerror: libnvinfer.so.7: cannot open shared object file: No such file or directory; LD_LIBRARY_PATH: /pfs/lustrep2/projappl/project_462000125/samantao-public/apps-rocm-5.2.3/aws-ofi-rccl:/opt/rocm/lib64:/opt/rocm/lib:/opt/rocm/rocprofiler/lib:/opt/rocm/rocprofiler/tool:/opt/rocm/roctracer/lib:/opt/rocm/roctracer/tool:/opt/rocm/hip/lib:/opt/cray/pe/python/3.9.13.1/lib:/opt/cray/pe/gcc-libs:/opt/cray/libfabric/1.15.2.0/lib64 +1: 2023-05-23 21:57:04.887364: W tensorflow/compiler/xla/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'libnvinfer.so.7'; dlerror: libnvinfer.so.7: cannot open shared object file: No such file or directory; LD_LIBRARY_PATH: /pfs/lustrep2/projappl/project_462000125/samantao-public/apps-rocm-5.2.3/aws-ofi-rccl:/opt/rocm/lib64:/opt/rocm/lib:/opt/rocm/rocprofiler/lib:/opt/rocm/rocprofiler/tool:/opt/rocm/roctracer/lib:/opt/rocm/roctracer/tool:/opt/rocm/hip/lib:/opt/cray/pe/python/3.9.13.1/lib:/opt/cray/pe/gcc-libs:/opt/cray/libfabric/1.15.2.0/lib64 +1: 2023-05-23 21:57:04.888666: W tensorflow/compiler/xla/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'libnvinfer_plugin.so.7'; dlerror: libnvinfer_plugin.so.7: cannot open shared object file: No such file or directory; LD_LIBRARY_PATH: /pfs/lustrep2/projappl/project_462000125/samantao-public/apps-rocm-5.2.3/aws-ofi-rccl:/opt/rocm/lib64:/opt/rocm/lib:/opt/rocm/rocprofiler/lib:/opt/rocm/rocprofiler/tool:/opt/rocm/roctracer/lib:/opt/rocm/roctracer/tool:/opt/rocm/hip/lib:/opt/cray/pe/python/3.9.13.1/lib:/opt/cray/pe/gcc-libs:/opt/cray/libfabric/1.15.2.0/lib64 +1: 2023-05-23 21:57:04.888672: W tensorflow/compiler/xla/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'libnvinfer_plugin.so.7'; dlerror: libnvinfer_plugin.so.7: cannot open shared object file: No such file or directory; LD_LIBRARY_PATH: /pfs/lustrep2/projappl/project_462000125/samantao-public/apps-rocm-5.2.3/aws-ofi-rccl:/opt/rocm/lib64:/opt/rocm/lib:/opt/rocm/rocprofiler/lib:/opt/rocm/rocprofiler/tool:/opt/rocm/roctracer/lib:/opt/rocm/roctracer/tool:/opt/rocm/hip/lib:/opt/cray/pe/python/3.9.13.1/lib:/opt/cray/pe/gcc-libs:/opt/cray/libfabric/1.15.2.0/lib64 +1: 2023-05-23 21:57:04.888671: W tensorflow/compiler/xla/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'libnvinfer_plugin.so.7'; dlerror: libnvinfer_plugin.so.7: cannot open shared object file: No such file or directory; LD_LIBRARY_PATH: /pfs/lustrep2/projappl/project_462000125/samantao-public/apps-rocm-5.2.3/aws-ofi-rccl:/opt/rocm/lib64:/opt/rocm/lib:/opt/rocm/rocprofiler/lib:/opt/rocm/rocprofiler/tool:/opt/rocm/roctracer/lib:/opt/rocm/roctracer/tool:/opt/rocm/hip/lib:/opt/cray/pe/python/3.9.13.1/lib:/opt/cray/pe/gcc-libs:/opt/cray/libfabric/1.15.2.0/lib64 +1: 2023-05-23 21:57:04.888675: W tensorflow/compiler/xla/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'libnvinfer_plugin.so.7'; dlerror: libnvinfer_plugin.so.7: cannot open shared object file: No such file or directory; LD_LIBRARY_PATH: /pfs/lustrep2/projappl/project_462000125/samantao-public/apps-rocm-5.2.3/aws-ofi-rccl:/opt/rocm/lib64:/opt/rocm/lib:/opt/rocm/rocprofiler/lib:/opt/rocm/rocprofiler/tool:/opt/rocm/roctracer/lib:/opt/rocm/roctracer/tool:/opt/rocm/hip/lib:/opt/cray/pe/python/3.9.13.1/lib:/opt/cray/pe/gcc-libs:/opt/cray/libfabric/1.15.2.0/lib64 +1: 2023-05-23 21:57:04.888674: W tensorflow/compiler/xla/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'libnvinfer_plugin.so.7'; dlerror: libnvinfer_plugin.so.7: cannot open shared object file: No such file or directory; LD_LIBRARY_PATH: /pfs/lustrep2/projappl/project_462000125/samantao-public/apps-rocm-5.2.3/aws-ofi-rccl:/opt/rocm/lib64:/opt/rocm/lib:/opt/rocm/rocprofiler/lib:/opt/rocm/rocprofiler/tool:/opt/rocm/roctracer/lib:/opt/rocm/roctracer/tool:/opt/rocm/hip/lib:/opt/cray/pe/python/3.9.13.1/lib:/opt/cray/pe/gcc-libs:/opt/cray/libfabric/1.15.2.0/lib64 +1: 2023-05-23 21:57:04.888678: W tensorflow/compiler/tf2tensorrt/utils/py_utils.cc:38] TF-TRT Warning: Cannot dlopen some TensorRT libraries. If you would like to use Nvidia GPU with TensorRT, please make sure the missing libraries mentioned above are installed properly. +1: 2023-05-23 21:57:04.888676: W tensorflow/compiler/xla/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'libnvinfer_plugin.so.7'; dlerror: libnvinfer_plugin.so.7: cannot open shared object file: No such file or directory; LD_LIBRARY_PATH: /pfs/lustrep2/projappl/project_462000125/samantao-public/apps-rocm-5.2.3/aws-ofi-rccl:/opt/rocm/lib64:/opt/rocm/lib:/opt/rocm/rocprofiler/lib:/opt/rocm/rocprofiler/tool:/opt/rocm/roctracer/lib:/opt/rocm/roctracer/tool:/opt/rocm/hip/lib:/opt/cray/pe/python/3.9.13.1/lib:/opt/cray/pe/gcc-libs:/opt/cray/libfabric/1.15.2.0/lib64 +1: 2023-05-23 21:57:04.888677: W tensorflow/compiler/xla/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'libnvinfer_plugin.so.7'; dlerror: libnvinfer_plugin.so.7: cannot open shared object file: No such file or directory; LD_LIBRARY_PATH: /pfs/lustrep2/projappl/project_462000125/samantao-public/apps-rocm-5.2.3/aws-ofi-rccl:/opt/rocm/lib64:/opt/rocm/lib:/opt/rocm/rocprofiler/lib:/opt/rocm/rocprofiler/tool:/opt/rocm/roctracer/lib:/opt/rocm/roctracer/tool:/opt/rocm/hip/lib:/opt/cray/pe/python/3.9.13.1/lib:/opt/cray/pe/gcc-libs:/opt/cray/libfabric/1.15.2.0/lib64 +1: 2023-05-23 21:57:04.888677: W tensorflow/compiler/xla/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'libnvinfer_plugin.so.7'; dlerror: libnvinfer_plugin.so.7: cannot open shared object file: No such file or directory; LD_LIBRARY_PATH: /pfs/lustrep2/projappl/project_462000125/samantao-public/apps-rocm-5.2.3/aws-ofi-rccl:/opt/rocm/lib64:/opt/rocm/lib:/opt/rocm/rocprofiler/lib:/opt/rocm/rocprofiler/tool:/opt/rocm/roctracer/lib:/opt/rocm/roctracer/tool:/opt/rocm/hip/lib:/opt/cray/pe/python/3.9.13.1/lib:/opt/cray/pe/gcc-libs:/opt/cray/libfabric/1.15.2.0/lib64 +1: 2023-05-23 21:57:04.888690: W tensorflow/compiler/tf2tensorrt/utils/py_utils.cc:38] TF-TRT Warning: Cannot dlopen some TensorRT libraries. If you would like to use Nvidia GPU with TensorRT, please make sure the missing libraries mentioned above are installed properly. +1: 2023-05-23 21:57:04.888691: W tensorflow/compiler/tf2tensorrt/utils/py_utils.cc:38] TF-TRT Warning: Cannot dlopen some TensorRT libraries. If you would like to use Nvidia GPU with TensorRT, please make sure the missing libraries mentioned above are installed properly. +1: 2023-05-23 21:57:04.888691: W tensorflow/compiler/tf2tensorrt/utils/py_utils.cc:38] TF-TRT Warning: Cannot dlopen some TensorRT libraries. If you would like to use Nvidia GPU with TensorRT, please make sure the missing libraries mentioned above are installed properly. +1: 2023-05-23 21:57:04.888691: W tensorflow/compiler/tf2tensorrt/utils/py_utils.cc:38] TF-TRT Warning: Cannot dlopen some TensorRT libraries. If you would like to use Nvidia GPU with TensorRT, please make sure the missing libraries mentioned above are installed properly. +1: 2023-05-23 21:57:04.888694: W tensorflow/compiler/tf2tensorrt/utils/py_utils.cc:38] TF-TRT Warning: Cannot dlopen some TensorRT libraries. If you would like to use Nvidia GPU with TensorRT, please make sure the missing libraries mentioned above are installed properly. +1: 2023-05-23 21:57:04.888695: W tensorflow/compiler/tf2tensorrt/utils/py_utils.cc:38] TF-TRT Warning: Cannot dlopen some TensorRT libraries. If you would like to use Nvidia GPU with TensorRT, please make sure the missing libraries mentioned above are installed properly. +1: 2023-05-23 21:57:04.888694: W tensorflow/compiler/tf2tensorrt/utils/py_utils.cc:38] TF-TRT Warning: Cannot dlopen some TensorRT libraries. If you would like to use Nvidia GPU with TensorRT, please make sure the missing libraries mentioned above are installed properly. +0: 2023-05-23 21:57:04.885340: W tensorflow/compiler/xla/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'libnvinfer_plugin.so.7'; dlerror: libnvinfer_plugin.so.7: cannot open shared object file: No such file or directory; LD_LIBRARY_PATH: /pfs/lustrep2/projappl/project_462000125/samantao-public/apps-rocm-5.2.3/aws-ofi-rccl:/opt/rocm/lib64:/opt/rocm/lib:/opt/rocm/rocprofiler/lib:/opt/rocm/rocprofiler/tool:/opt/rocm/roctracer/lib:/opt/rocm/roctracer/tool:/opt/rocm/hip/lib:/opt/cray/pe/python/3.9.13.1/lib:/opt/cray/pe/gcc-libs:/opt/cray/libfabric/1.15.2.0/lib64 +0: 2023-05-23 21:57:04.885353: W tensorflow/compiler/tf2tensorrt/utils/py_utils.cc:38] TF-TRT Warning: Cannot dlopen some TensorRT libraries. If you would like to use Nvidia GPU with TensorRT, please make sure the missing libraries mentioned above are installed properly. +0: Successfully preprocessed all matching files. +0: Detected CUDA files, patching ldflags +0: Emitting ninja build file /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/build/build.ninja... +0: Building extension module scaled_upper_triang_masked_softmax_cuda... +0: Allowing ninja to set a default number of workers... (overridable by setting the environment variable MAX_JOBS=N) +0: Loading extension module scaled_upper_triang_masked_softmax_cuda... +0: Successfully preprocessed all matching files. +0: Detected CUDA files, patching ldflags +0: Emitting ninja build file /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/build/build.ninja... +0: Building extension module scaled_masked_softmax_cuda... +0: Allowing ninja to set a default number of workers... (overridable by setting the environment variable MAX_JOBS=N) +0: Loading extension module scaled_masked_softmax_cuda... +0: Successfully preprocessed all matching files. +0: Detected CUDA files, patching ldflags +0: Emitting ninja build file /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/build/build.ninja... +0: Building extension module fused_mix_prec_layer_norm_cuda... +0: Allowing ninja to set a default number of workers... (overridable by setting the environment variable MAX_JOBS=N) +0: Loading extension module fused_mix_prec_layer_norm_cuda... +0: Successfully preprocessed all matching files. +0: Successfully preprocessed all matching files. +0: Successfully preprocessed all matching files. +0: Successfully preprocessed all matching files. +1: Successfully preprocessed all matching files. +1: Successfully preprocessed all matching files. +1: Successfully preprocessed all matching files. +1: Successfully preprocessed all matching files. +0: Successfully preprocessed all matching files. +1: Successfully preprocessed all matching files. +1: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +1: warnings.warn( +1: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +1: warnings.warn( +1: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +1: warnings.warn( +1: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +1: warnings.warn( +1: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +1: warnings.warn( +1: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +1: warnings.warn( +1: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +1: warnings.warn( +1: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +1: warnings.warn( +0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +0: warnings.warn( +0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +0: warnings.warn( +0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +0: warnings.warn( +0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +0: warnings.warn( +0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +0: warnings.warn( +0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +0: warnings.warn( +0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +0: warnings.warn( +0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/distributed/distributed_c10d.py:429: UserWarning: torch.distributed.distributed_c10d._get_global_rank is deprecated please use torch.distributed.distributed_c10d.get_global_rank instead +0: warnings.warn( +0: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +0: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +0: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +0: +0: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +0: +0: +1: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +1: +1: +1: +1: +1: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +1: +1: +0: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +0: Emitting ninja build file /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu/utils/build.ninja... +0: Building extension module utils... +0: Allowing ninja to set a default number of workers... (overridable by setting the environment variable MAX_JOBS=N) +0: Loading extension module utils... +0: Loading extension module utils... +0: Loading extension module utils... +0: Loading extension module utils... +1: Loading extension module utils... +0: Loading extension module utils... +1: Loading extension module utils... +0: Loading extension module utils... +1: Loading extension module utils... +0: Loading extension module utils... +1: Loading extension module utils... +0: Loading extension module utils... +1: Loading extension module utils... +1: Loading extension module utils... +1: Loading extension module utils... +1: Loading extension module utils... +0: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +0: +0: +0: +0: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +0: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +0: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +0: No modifications detected for re-loaded extension module utils, skipping build step...No modifications detected for re-loaded extension module utils, skipping build step...No modifications detected for re-loaded extension module utils, skipping build step...No modifications detected for re-loaded extension module utils, skipping build step... +0: +0: +0: +0: Loading extension module utils...Loading extension module utils...Loading extension module utils...Loading extension module utils... +0: +0: +0: +0: No modifications detected for re-loaded extension module utils, skipping build step... +0: Loading extension module utils... +0: No modifications detected for re-loaded extension module utils, skipping build step... +0: Loading extension module utils...No modifications detected for re-loaded extension module utils, skipping build step... +0: +0: Loading extension module utils... +1: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +1: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +1: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +1: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +1: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +1: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +1: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +1: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +1: No modifications detected for re-loaded extension module utils, skipping build step... +1: Loading extension module utils... +1: No modifications detected for re-loaded extension module utils, skipping build step... +1: Loading extension module utils... +1: No modifications detected for re-loaded extension module utils, skipping build step... +1: Loading extension module utils... +1: No modifications detected for re-loaded extension module utils, skipping build step... +1: No modifications detected for re-loaded extension module utils, skipping build step...Loading extension module utils... +1: +1: Loading extension module utils... +1: No modifications detected for re-loaded extension module utils, skipping build step... +1: Loading extension module utils... +1: No modifications detected for re-loaded extension module utils, skipping build step... +1: Loading extension module utils... +1: No modifications detected for re-loaded extension module utils, skipping build step... +1: Loading extension module utils... +0: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root... +0: No modifications detected for re-loaded extension module utils, skipping build step... +0: Loading extension module utils... +0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/utils.py:349: UserWarning: Parameter count with the embeddings will be inaccurate with PP > 1, as the first and last stage hold several copies of the embeddings +0: warnings.warn("Parameter count with the embeddings will be inaccurate with PP > 1, as the first and last stage hold several copies of the embeddings") diff --git a/7m100m100m/3571584.out b/7m100m100m/3571584.out new file mode 100644 index 0000000000000000000000000000000000000000..cd00dee88e6ed9c8dbcbd828370c39c7684a0831 --- /dev/null +++ b/7m100m100m/3571584.out @@ -0,0 +1,1042 @@ +Model parameters: d_model 128 ffw_size 512 kv_size 32 n_heads 4 n_layers 3 +Megatron-DeepSpeed/pretrain_gpt.py --tensor-model-parallel-size 1 --pipeline-model-parallel-size 1 --num-layers 3 --hidden-size 128 --num-attention-heads 4 --kv-channels 32 --ffn-hidden-size 512 --seq-length 2048 --max-position-embeddings 2048 --micro-batch-size 4 --global-batch-size 64 --train-samples 1 --vocab-file gpt2/vocab.json --merge-file gpt2/merges.txt --clip-grad 1.0 --kill-switch-path kill-switch-7m100m100mval --bf16 --optimizer adam --adam-beta1 0.9 --adam-beta2 0.999 --adam-eps 1e-8 --lr 2e-4 --min-lr 2e-5 --lr-decay-style cosine --lr-decay-samples 1 --lr-warmup-samples 0 --clip-grad 1.0 --weight-decay 1e-1 --override-lr-scheduler --no-load-optim --reset-progress --log-interval 10 --save-interval 1000 --eval-interval 1 --eval-iters 100 --tensorboard-dir tensorboard_7m100m100mval --tensorboard-queue-size 5 --log-timers-to-tensorboard --log-batch-size-to-tensorboard --log-validation-ppl-to-tensorboard --save checkpoints_7m100m100m --load checkpoints_7m100m100m --train-weighted-split-paths-path train100m.txt --valid-weighted-split-paths-path val.txt --data-impl mmap --deepspeed --deepspeed_config ds_configs/3571584.json --zero-stage 0 +START 3571584: Tue 23 May 2023 09:56:22 PM EEST +0: +0: +0: ======================= ROCm System Management Interface ======================= +0: ================================= Concise Info ================================= +0: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% +0: 0 45.0c 88.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +0: 1 48.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +0: 2 41.0c 98.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +0: 3 44.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +0: 4 41.0c 92.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +0: 5 47.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +0: 6 41.0c 97.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +0: 7 44.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +0: ================================================================================ +0: ============================= End of ROCm SMI Log ============================== +1: +1: +1: ======================= ROCm System Management Interface ======================= +1: ================================= Concise Info ================================= +1: GPU Temp AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% +1: 0 45.0c 88.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +1: 1 50.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +1: 2 41.0c 92.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +1: 3 45.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +1: 4 35.0c 90.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +1: 5 45.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +1: 6 38.0c 92.0W 800Mhz 1600Mhz 0% auto 560.0W 0% 0% +1: 7 44.0c N/A 800Mhz 1600Mhz 0% auto 0.0W 0% 0% +1: ================================================================================ +1: ============================= End of ROCm SMI Log ============================== +0: Launching on nid007377 (0/2), master nid007377 port 9999, GPUs 8, CUDA: True +1: Launching on nid007378 (1/2), master nid007377 port 9999, GPUs 8, CUDA: True +0: using world size: 16, data-parallel-size: 16, tensor-model-parallel size: 1, pipeline-model-parallel size: 1 +0: accumulate and all-reduce gradients in fp32 for bfloat16 data type. +0: using torch.bfloat16 for parameters ... +0: ------------------------ arguments ------------------------ +0: abort_on_unmet_fused_kernel_constraints ......... False +0: accumulate_allreduce_grads_in_fp32 .............. True +0: adam_beta1 ...................................... 0.9 +0: adam_beta2 ...................................... 0.999 +0: adam_eps ........................................ 1e-08 +0: adlr_autoresume ................................. False +0: adlr_autoresume_interval ........................ 1000 +0: apply_query_key_layer_scaling ................... True +0: apply_residual_connection_post_layernorm ........ False +0: attention_dropout ............................... 0.1 +0: attention_softmax_in_fp32 ....................... False +0: bert_binary_head ................................ True +0: bert_load ....................................... None +0: bf16 ............................................ True +0: bias_dropout_fusion ............................. True +0: bias_gelu_fusion ................................ True +0: biencoder_projection_dim ........................ 0 +0: biencoder_shared_query_context_model ............ False +0: block_data_path ................................. None +0: checkpoint_activations .......................... False +0: checkpoint_in_cpu ............................... False +0: checkpoint_num_layers ........................... 1 +0: clip_grad ....................................... 1.0 +0: codecarbon_dir .................................. None +0: consumed_train_samples .......................... 0 +0: consumed_train_tokens ........................... 0 +0: consumed_valid_samples .......................... 0 +0: contigious_checkpointing ........................ False +0: cpu_optimizer ................................... False +0: cpu_torch_adam .................................. False +0: curriculum_learning ............................. False +0: data_impl ....................................... mmap +0: data_parallel_size .............................. 16 +0: data_path ....................................... None +0: dataloader_type ................................. single +0: DDP_impl ........................................ local +0: decoder_seq_length .............................. None +0: deepscale ....................................... False +0: deepscale_config ................................ None +0: deepspeed ....................................... True +0: deepspeed_activation_checkpointing .............. False +0: deepspeed_config ................................ ds_configs/3571584.json +0: deepspeed_mpi ................................... False +0: distribute_checkpointed_activations ............. False +0: distributed_backend ............................. nccl +0: embed_layernorm ................................. False +0: embedding_path .................................. None +0: encoder_seq_length .............................. 2048 +0: eod_mask_loss ................................... False +0: eval_interval ................................... 1 +0: eval_iters ...................................... 100 +0: eval_only ....................................... None +0: evidence_data_path .............................. None +0: exit_duration_in_mins ........................... None +0: exit_interval ................................... None +0: ffn_hidden_size ................................. 512 +0: finetune ........................................ False +0: fp16 ............................................ False +0: fp16_lm_cross_entropy ........................... False +0: fp32_residual_connection ........................ False +0: gigaflos_no_embeds .............................. 0 +0: global_batch_size ............................... 64 +0: glu_activation .................................. None +0: hidden_dropout .................................. 0.1 +0: hidden_size ..................................... 128 +0: hysteresis ...................................... 2 +0: ict_head_size ................................... None +0: ict_load ........................................ None +0: img_dim ......................................... 224 +0: indexer_batch_size .............................. 128 +0: indexer_log_interval ............................ 1000 +0: inference ....................................... False +0: init_method_std ................................. 0.02 +0: init_method_xavier_uniform ...................... False +0: initial_loss_scale .............................. 4294967296 +0: kill_switch_path ................................ kill-switch-7m100m100mval +0: kv_channels ..................................... 32 +0: layer_norm_fusion ............................... True +0: layernorm_epsilon ............................... 1e-05 +0: lazy_mpu_init ................................... None +0: load ............................................ checkpoints_7m100m100m +0: local_rank ...................................... None +0: log_batch_size_to_tensorboard ................... True +0: log_interval .................................... 10 +0: log_learning_rate_to_tensorboard ................ True +0: log_level ....................................... None +0: log_level_replica ............................... None +0: log_loss_scale_to_tensorboard ................... True +0: log_num_zeros_in_grad ........................... False +0: log_params_norm ................................. False +0: log_path ........................................ None +0: log_timers_to_tensorboard ....................... True +0: log_validation_ppl_to_tensorboard ............... True +0: loss_on_targets_only ............................ False +0: loss_scale ...................................... None +0: loss_scale_window ............................... 1000 +0: lr .............................................. 0.0002 +0: lr_decay_iters .................................. None +0: lr_decay_samples ................................ 1 +0: lr_decay_style .................................. cosine +0: lr_decay_tokens ................................. None +0: lr_warmup_fraction .............................. None +0: lr_warmup_iters ................................. 0 +0: lr_warmup_samples ............................... 0 +0: make_vocab_size_divisible_by .................... 128 +0: mask_prob ....................................... 0.15 +0: masked_softmax_fusion ........................... True +0: max_position_embeddings ......................... 2048 +0: mean_noise_span_length .......................... None +0: memory_centric_tiled_linear ..................... False +0: merge_file ...................................... gpt2/merges.txt +0: micro_batch_size ................................ 4 +0: min_loss_scale .................................. 1.0 +0: min_lr .......................................... 2e-05 +0: mmap_warmup ..................................... False +0: no_load_optim ................................... True +0: no_load_rng ..................................... None +0: no_save_optim ................................... None +0: no_save_rng ..................................... None +0: noise_density ................................... None +0: num_attention_heads ............................. 4 +0: num_channels .................................... 3 +0: num_classes ..................................... 1000 +0: num_layers ...................................... 3 +0: num_layers_per_virtual_pipeline_stage ........... None +0: num_workers ..................................... 2 +0: onnx_safe ....................................... None +0: openai_gelu ..................................... False +0: optimizer ....................................... adam +0: optimizer_fusion ................................ True +0: override_lr_scheduler ........................... True +0: pad_vocab_size_to ............................... None +0: params_dtype .................................... torch.bfloat16 +0: partition_activations ........................... False +0: patch_dim ....................................... 16 +0: pipeline_model_parallel_size .................... 1 +0: position_embedding_type ......................... PositionEmbeddingType.absolute +0: pp_partition_method ............................. None +0: profile_backward ................................ False +0: query_in_block_prob ............................. 0.1 +0: rampup_batch_size ............................... None +0: rank ............................................ 0 +0: remote_device ................................... none +0: reset_attention_mask ............................ False +0: reset_position_ids .............................. False +0: reset_progress .................................. True +0: retriever_report_topk_accuracies ................ [] +0: retriever_score_scaling ......................... False +0: retriever_seq_length ............................ 256 +0: reweight_loss_based_on_position_frequency ....... False +0: sample_rate ..................................... 1.0 +0: save ............................................ checkpoints_7m100m100m +0: save_interval ................................... 1000 +0: scatter_gather_tensors_in_pipeline .............. True +0: scattered_embeddings ............................ False +0: seed ............................................ 1234 +0: seq_length ...................................... 2048 +0: sgd_momentum .................................... 0.9 +0: short_seq_prob .................................. 0.1 +0: skip_train_iteration_range ...................... None +0: split ........................................... None +0: split_transformers .............................. False +0: sync_tp_duplicated_parameters ................... False +0: synchronize_each_layer .......................... False +0: tensor_model_parallel_size ...................... 1 +0: tensorboard_dir ................................. tensorboard_7m100m100mval +0: tensorboard_log_interval ........................ 1 +0: tensorboard_queue_size .......................... 5 +0: test_weighted_split_paths ....................... None +0: test_weighted_split_paths_path .................. None +0: tile_factor ..................................... 1 +0: titles_data_path ................................ None +0: tokenizer_name_or_path .......................... None +0: tokenizer_type .................................. GPT2BPETokenizer +0: train_iters ..................................... None +0: train_samples ................................... 1 +0: train_tokens .................................... None +0: train_weighted_split_names ...................... ['train'] +0: train_weighted_split_paths ...................... [['/scratch/project_462000119/data/c4_subsampled/gpt2tok_c4_en_100M_text_document']] +0: train_weighted_split_paths_path ................. None +0: train_weighted_split_splits ..................... [['0:1']] +0: train_weighted_split_weights .................... [['1.0']] +0: universal_checkpoint ............................ False +0: use_bnb_optimizer ............................... False +0: use_checkpoint_lr_scheduler ..................... False +0: use_contiguous_buffers_in_ddp ................... True +0: use_cpu_initialization .......................... None +0: use_one_sent_docs ............................... False +0: use_pin_memory .................................. False +0: valid_num_workers ............................... 2 +0: valid_weighted_split_names ...................... ['validation'] +0: valid_weighted_split_paths ...................... [['/scratch/project_462000119/data/c4_validation/gpt2tok_c4validation_rerun_text_document']] +0: valid_weighted_split_paths_path ................. None +0: valid_weighted_split_splits ..................... [['0:1']] +0: valid_weighted_split_weights .................... [['1.0']] +0: virtual_pipeline_model_parallel_size ............ None +0: vocab_extra_ids ................................. 0 +0: vocab_file ...................................... gpt2/vocab.json +0: weight_decay .................................... 0.1 +0: world_size ...................................... 16 +0: zero_allgather_bucket_size ...................... 0.0 +0: zero_contigious_gradients ....................... False +0: zero_reduce_bucket_size ......................... 0.0 +0: zero_reduce_scatter ............................. False +0: zero_stage ...................................... 0 +0: -------------------- end of arguments --------------------- +0: setting number of micro-batches to constant 1 +0: > building GPT2BPETokenizer tokenizer ... +0: > padded vocab (size: 50257) with 47 dummy tokens (new size: 50304) +0: DeepSpeed general environment info: +0: torch install path ............... ['/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch'] +0: torch version .................... 1.13.0+rocm5.2 +0: torch cuda version ............... None +0: torch hip version ................ 5.2.21151-afdc89f8 +0: nvcc version ..................... None +0: deepspeed install path ........... ['/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/deepspeed'] +0: deepspeed info ................... 0.7.5, unknown, unknown +0: deepspeed wheel compiled w. ...... torch 1.13, hip 5.1 +0: **** Git info for Megatron: git_hash=unknown git_branch=unknown **** +0: > initializing torch distributed ... +0: [2023-05-23 21:57:24,662] [INFO] [comm.py:633:init_distributed] Initializing TorchBackend in DeepSpeed with backend nccl +1: > setting tensorboard ... +0: > initializing tensor model parallel with size 1 +0: > initializing pipeline model parallel with size 1 +0: > setting random seeds to 1234 ... +0: > initializing model parallel cuda seeds on global rank 0, model parallel rank 0, and data parallel rank 0 with model parallel seed: 3952 and data parallel seed: 1234 +0: > compiling dataset index builder ... +0: make: Entering directory '/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/data' +0: make: Nothing to be done for 'default'. +0: make: Leaving directory '/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/data' +0: >>> done with dataset index builder. Compilation time: 0.090 seconds +0: > compiling and loading fused kernels ... +0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/scaled_upper_triang_masked_softmax.cpp -> /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/scaled_upper_triang_masked_softmax_hip.cpp [skipped, already hipified] +0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/scaled_upper_triang_masked_softmax.h -> /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/scaled_upper_triang_masked_softmax_hip.h [skipped, already hipified] +0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/compat.h -> /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/compat.h [skipped, no changes] +0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/type_shim.h -> /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/type_shim.h [skipped, no changes] +0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/scaled_upper_triang_masked_softmax_cuda.cu -> /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/scaled_upper_triang_masked_softmax_hip.hip [skipped, already hipified] +0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/type_shim.h -> /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/type_shim.h [skipped, no changes] +0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/compat.h -> /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/compat.h [skipped, no changes] +0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/scaled_upper_triang_masked_softmax.h -> /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/scaled_upper_triang_masked_softmax_hip.h [skipped, already hipified] +0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/scaled_masked_softmax.h -> /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/scaled_masked_softmax_hip.h [skipped, already hipified] +0: Total number of unsupported CUDA function calls: 0 +0: +0: +0: Total number of replaced kernel launches: 87 +0: [1/1] c++ scaled_upper_triang_masked_softmax_hip.o scaled_upper_triang_masked_softmax_hip.cuda.o -shared -L/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/lib -lc10 -lc10_hip -ltorch_cpu -ltorch_hip -ltorch -ltorch_python -L/opt/rocm/lib -lamdhip64 -o scaled_upper_triang_masked_softmax_cuda.so +0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/scaled_masked_softmax.cpp -> /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/scaled_masked_softmax_hip.cpp [skipped, already hipified] +0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/scaled_masked_softmax_cuda.cu -> /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/scaled_masked_softmax_hip.hip [skipped, already hipified] +0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/type_shim.h -> /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/type_shim.h [skipped, no changes] +0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/compat.h -> /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/compat.h [skipped, no changes] +0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/scaled_upper_triang_masked_softmax.h -> /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/scaled_upper_triang_masked_softmax_hip.h [skipped, already hipified] +0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/scaled_masked_softmax.h -> /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/scaled_masked_softmax_hip.h [skipped, already hipified] +0: Total number of unsupported CUDA function calls: 0 +0: +0: +0: Total number of replaced kernel launches: 63 +0: ninja: no work to do. +0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/layer_norm_cuda.cpp -> /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/layer_norm_cuda.cpp [skipped, no changes] +0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/layer_norm_cuda_kernel.cu -> /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/layer_norm_hip_kernel.hip [skipped, already hipified] +0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/type_shim.h -> /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/type_shim.h [skipped, no changes] +0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/compat.h -> /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/compat.h [skipped, no changes] +0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/scaled_upper_triang_masked_softmax.h -> /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/scaled_upper_triang_masked_softmax_hip.h [skipped, already hipified] +0: /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/scaled_masked_softmax.h -> /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/scaled_masked_softmax_hip.h [skipped, already hipified] +0: Total number of unsupported CUDA function calls: 0 +0: +0: +0: Total number of replaced kernel launches: 67 +0: [1/1] c++ layer_norm_cuda.o layer_norm_hip_kernel.cuda.o -shared -L/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/venv/lib/python3.9/site-packages/torch/lib -lc10 -lc10_hip -ltorch_cpu -ltorch_hip -ltorch -ltorch_python -L/opt/rocm/lib -lamdhip64 -o fused_mix_prec_layer_norm_cuda.so +0: >>> done with compiling and loading fused kernels. Compilation time: 17.139 seconds +0: time to initialize megatron (seconds): 39.206 +0: [after megatron is initialized] datetime: 2023-05-23 21:57:43 +0: building GPT model ... +0: [2023-05-23 21:57:43,345] [INFO] [utils.py:827:see_memory_usage] Before Building Model +0: [2023-05-23 21:57:43,346] [INFO] [utils.py:828:see_memory_usage] MA 0.0 GB Max_MA 0.0 GB CA 0.0 GB Max_CA 0 GB +0: [2023-05-23 21:57:43,346] [INFO] [utils.py:836:see_memory_usage] CPU Virtual Memory: used = 40.39 GB, percent = 8.0% +0: SEED_LAYERS=False BASE_SEED=1234 SEED_FN=None +0: Using topology: {ProcessCoord(pipe=0, data=0, model=0): 0, ProcessCoord(pipe=0, data=1, model=0): 1, ProcessCoord(pipe=0, data=2, model=0): 2, ProcessCoord(pipe=0, data=3, model=0): 3, ProcessCoord(pipe=0, data=4, model=0): 4, ProcessCoord(pipe=0, data=5, model=0): 5, ProcessCoord(pipe=0, data=6, model=0): 6, ProcessCoord(pipe=0, data=7, model=0): 7, ProcessCoord(pipe=0, data=8, model=0): 8, ProcessCoord(pipe=0, data=9, model=0): 9, ProcessCoord(pipe=0, data=10, model=0): 10, ProcessCoord(pipe=0, data=11, model=0): 11, ProcessCoord(pipe=0, data=12, model=0): 12, ProcessCoord(pipe=0, data=13, model=0): 13, ProcessCoord(pipe=0, data=14, model=0): 14, ProcessCoord(pipe=0, data=15, model=0): 15} +0: [2023-05-23 21:57:43,821] [INFO] [module.py:366:_partition_layers] Partitioning pipeline stages with method type:transformer +0: stage=0 layers=10 +0: 0: _to_float16 +0: 1: EmbeddingPipe +0: 2: +0: 3: ParallelTransformerLayerPipe +0: 4: ParallelTransformerLayerPipe +0: 5: ParallelTransformerLayerPipe +0: 6: undo +0: 7: MixedFusedLayerNorm +0: 8: EmbeddingPipe +0: 9: float16_to_fp32 +0: loss: CrossEntropy +0: [2023-05-23 21:57:44,072] [INFO] [utils.py:827:see_memory_usage] After Building Model +0: [2023-05-23 21:57:44,073] [INFO] [utils.py:828:see_memory_usage] MA 0.01 GB Max_MA 0.01 GB CA 0.02 GB Max_CA 0 GB +0: [2023-05-23 21:57:44,073] [INFO] [utils.py:836:see_memory_usage] CPU Virtual Memory: used = 40.4 GB, percent = 8.0% +0: setting training iterations to 0 +0: > learning rate decay style: cosine +0: DeepSpeed is enabled. +0: [2023-05-23 21:57:44,074] [INFO] [logging.py:68:log_dist] [Rank 0] DeepSpeed info: version=0.7.5, git-hash=unknown, git-branch=unknown +0: [2023-05-23 21:57:52,275] [INFO] [logging.py:68:log_dist] [Rank 0] DeepSpeed Flops Profiler Enabled: False +0: [2023-05-23 21:57:52,275] [INFO] [logging.py:68:log_dist] [Rank 0] Removing param_group that has no 'params' in the client Optimizer +0: [2023-05-23 21:57:52,275] [INFO] [logging.py:68:log_dist] [Rank 0] Using client Optimizer as basic optimizer +0: [2023-05-23 21:57:52,276] [INFO] [logging.py:68:log_dist] [Rank 0] DeepSpeed Basic Optimizer = FusedAdam +0: [2023-05-23 21:57:52,276] [INFO] [logging.py:68:log_dist] [Rank 0] Creating BF16 optimizer +0: [2023-05-23 21:57:52,410] [INFO] [utils.py:827:see_memory_usage] begin bf16_optimizer +0: [2023-05-23 21:57:52,410] [INFO] [utils.py:828:see_memory_usage] MA 0.01 GB Max_MA 0.01 GB CA 0.02 GB Max_CA 0 GB +0: [2023-05-23 21:57:52,410] [INFO] [utils.py:836:see_memory_usage] CPU Virtual Memory: used = 44.49 GB, percent = 8.8% +0: ninja: no work to do. +0: Time to load utils op: 0.5655617713928223 seconds +0: Time to load utils op: 0.5654017925262451 seconds +0: Time to load utils op: 0.5654177665710449 seconds +0: Time to load utils op: 0.5653722286224365 seconds +0: Time to load utils op: 0.43936586380004883 seconds +0: Time to load utils op: 0.5655136108398438 seconds +0: Time to load utils op: 0.5655460357666016 seconds +0: Time to load utils op: 0.5657577514648438 seconds +1: Time to load utils op: 0.6284787654876709 secondsTime to load utils op: 0.6284852027893066 seconds +1: +1: Time to load utils op: 0.6286215782165527 secondsTime to load utils op: 0.628633975982666 seconds +1: +1: Time to load utils op: 0.6285183429718018 seconds +1: Time to load utils op: 0.6286149024963379 seconds +1: Time to load utils op: 0.6286239624023438 secondsTime to load utils op: 0.6285309791564941 seconds +1: +0: [2023-05-23 21:57:52,976] [INFO] [utils.py:827:see_memory_usage] before initializing group 0 +0: [2023-05-23 21:57:52,977] [INFO] [utils.py:828:see_memory_usage] MA 0.01 GB Max_MA 0.01 GB CA 0.02 GB Max_CA 0 GB +0: [2023-05-23 21:57:52,977] [INFO] [utils.py:836:see_memory_usage] CPU Virtual Memory: used = 44.11 GB, percent = 8.8% +0: Time to load utils op: 0.0055811405181884766 secondsTime to load utils op: 0.0055904388427734375 secondsTime to load utils op: 0.0055501461029052734 secondsTime to load utils op: 0.005563020706176758 seconds +0: +0: +0: +0: Time to load utils op: 0.0056192874908447266 seconds +0: Time to load utils op: 0.005530357360839844 seconds +0: Time to load utils op: 0.005404233932495117 seconds +0: [2023-05-23 21:57:53,902] [INFO] [utils.py:827:see_memory_usage] after initializing group 0 +0: [2023-05-23 21:57:53,903] [INFO] [utils.py:828:see_memory_usage] MA 0.04 GB Max_MA 0.04 GB CA 0.06 GB Max_CA 0 GB +0: [2023-05-23 21:57:53,903] [INFO] [utils.py:836:see_memory_usage] CPU Virtual Memory: used = 43.24 GB, percent = 8.6% +1: Time to load utils op: 0.04885268211364746 seconds +1: Time to load utils op: 0.04864144325256348 seconds +1: Time to load utils op: 0.04862093925476074 seconds +1: Time to load utils op: 0.04868006706237793 seconds +1: Time to load utils op: 0.04865312576293945 seconds +1: Time to load utils op: 0.04876399040222168 seconds +1: Time to load utils op: 0.049111366271972656 seconds +1: Time to load utils op: 0.04910707473754883 seconds +0: [2023-05-23 21:57:54,033] [INFO] [utils.py:827:see_memory_usage] before initializing group 1 +0: [2023-05-23 21:57:54,034] [INFO] [utils.py:828:see_memory_usage] MA 0.04 GB Max_MA 0.04 GB CA 0.06 GB Max_CA 0 GB +0: [2023-05-23 21:57:54,034] [INFO] [utils.py:836:see_memory_usage] CPU Virtual Memory: used = 42.97 GB, percent = 8.5% +0: [2023-05-23 21:57:54,156] [INFO] [utils.py:827:see_memory_usage] after initializing group 1 +0: [2023-05-23 21:57:54,157] [INFO] [utils.py:828:see_memory_usage] MA 0.04 GB Max_MA 0.04 GB CA 0.06 GB Max_CA 0 GB +0: [2023-05-23 21:57:54,157] [INFO] [utils.py:836:see_memory_usage] CPU Virtual Memory: used = 42.75 GB, percent = 8.5% +0: [2023-05-23 21:57:54,278] [INFO] [utils.py:827:see_memory_usage] before initializing group 2 +0: [2023-05-23 21:57:54,278] [INFO] [utils.py:828:see_memory_usage] MA 0.04 GB Max_MA 0.04 GB CA 0.06 GB Max_CA 0 GB +0: [2023-05-23 21:57:54,278] [INFO] [utils.py:836:see_memory_usage] CPU Virtual Memory: used = 42.49 GB, percent = 8.4% +0: [2023-05-23 21:57:54,400] [INFO] [utils.py:827:see_memory_usage] after initializing group 2 +0: [2023-05-23 21:57:54,401] [INFO] [utils.py:828:see_memory_usage] MA 0.04 GB Max_MA 0.04 GB CA 0.06 GB Max_CA 0 GB +0: [2023-05-23 21:57:54,401] [INFO] [utils.py:836:see_memory_usage] CPU Virtual Memory: used = 42.19 GB, percent = 8.4% +0: [2023-05-23 21:57:54,522] [INFO] [utils.py:827:see_memory_usage] before initialize_optimizer +0: [2023-05-23 21:57:54,522] [INFO] [utils.py:828:see_memory_usage] MA 0.04 GB Max_MA 0.04 GB CA 0.06 GB Max_CA 0 GB +0: [2023-05-23 21:57:54,522] [INFO] [utils.py:836:see_memory_usage] CPU Virtual Memory: used = 41.88 GB, percent = 8.3% +0: [2023-05-23 21:57:55,083] [INFO] [utils.py:827:see_memory_usage] end initialize_optimizer +0: [2023-05-23 21:57:55,084] [INFO] [utils.py:828:see_memory_usage] MA 0.05 GB Max_MA 0.05 GB CA 0.06 GB Max_CA 0 GB +0: [2023-05-23 21:57:55,084] [INFO] [utils.py:836:see_memory_usage] CPU Virtual Memory: used = 41.24 GB, percent = 8.2% +0: [2023-05-23 21:57:55,194] [INFO] [utils.py:827:see_memory_usage] end bf16_optimizer +0: [2023-05-23 21:57:55,195] [INFO] [utils.py:828:see_memory_usage] MA 0.05 GB Max_MA 0.05 GB CA 0.06 GB Max_CA 0 GB +0: [2023-05-23 21:57:55,195] [INFO] [utils.py:836:see_memory_usage] CPU Virtual Memory: used = 41.24 GB, percent = 8.2% +0: [2023-05-23 21:57:55,195] [INFO] [logging.py:68:log_dist] [Rank 0] DeepSpeed Final Optimizer = FusedAdam +0: [2023-05-23 21:57:55,195] [INFO] [logging.py:68:log_dist] [Rank 0] DeepSpeed using client LR scheduler +0: [2023-05-23 21:57:55,195] [INFO] [logging.py:68:log_dist] [Rank 0] DeepSpeed LR Scheduler = +0: [2023-05-23 21:57:55,195] [INFO] [logging.py:68:log_dist] [Rank 0] step=0, skipped=0, lr=[0.0002, 0.0002, 0.0002], mom=[(0.9, 0.999), (0.9, 0.999), (0.9, 0.999)] +0: [2023-05-23 21:57:55,196] [INFO] [config.py:1007:print] DeepSpeedEngine configuration: +0: [2023-05-23 21:57:55,196] [INFO] [config.py:1011:print] activation_checkpointing_config { +0: "partition_activations": false, +0: "contiguous_memory_optimization": false, +0: "cpu_checkpointing": false, +0: "number_checkpoints": null, +0: "synchronize_checkpoint_boundary": false, +0: "profile": false +0: } +0: [2023-05-23 21:57:55,196] [INFO] [config.py:1011:print] aio_config ................... {'block_size': 1048576, 'queue_depth': 8, 'thread_count': 1, 'single_submit': False, 'overlap_events': True} +0: [2023-05-23 21:57:55,196] [INFO] [config.py:1011:print] amp_enabled .................. False +0: [2023-05-23 21:57:55,196] [INFO] [config.py:1011:print] amp_params ................... False +0: [2023-05-23 21:57:55,196] [INFO] [config.py:1011:print] autotuning_config ............ { +0: "enabled": false, +0: "start_step": null, +0: "end_step": null, +0: "metric_path": null, +0: "arg_mappings": null, +0: "metric": "throughput", +0: "model_info": null, +0: "results_dir": "/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/autotuning_results", +0: "exps_dir": "/pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/autotuning_exps", +0: "overwrite": true, +0: "fast": true, +0: "start_profile_step": 3, +0: "end_profile_step": 5, +0: "tuner_type": "gridsearch", +0: "tuner_early_stopping": 5, +0: "tuner_num_trials": 50, +0: "model_info_path": null, +0: "mp_size": 1, +0: "max_train_batch_size": null, +0: "min_train_batch_size": 1, +0: "max_train_micro_batch_size_per_gpu": 1.024000e+03, +0: "min_train_micro_batch_size_per_gpu": 1, +0: "num_tuning_micro_batch_sizes": 3 +0: } +0: [2023-05-23 21:57:55,196] [INFO] [config.py:1011:print] bfloat16_enabled ............. True +0: [2023-05-23 21:57:55,196] [INFO] [config.py:1011:print] checkpoint_parallel_write_pipeline False +0: [2023-05-23 21:57:55,196] [INFO] [config.py:1011:print] checkpoint_tag_validation_enabled True +0: [2023-05-23 21:57:55,196] [INFO] [config.py:1011:print] checkpoint_tag_validation_fail False +0: [2023-05-23 21:57:55,196] [INFO] [config.py:1011:print] comms_config ................. +0: [2023-05-23 21:57:55,197] [INFO] [config.py:1011:print] communication_data_type ...... None +0: [2023-05-23 21:57:55,197] [INFO] [config.py:1011:print] compression_config ........... {'weight_quantization': {'shared_parameters': {'enabled': False, 'quantizer_kernel': False, 'schedule_offset': 0, 'quantize_groups': 1, 'quantize_verbose': False, 'quantization_type': 'symmetric', 'quantize_weight_in_forward': False, 'rounding': 'nearest', 'fp16_mixed_quantize': False, 'quantize_change_ratio': 0.001}, 'different_groups': {}}, 'activation_quantization': {'shared_parameters': {'enabled': False, 'quantization_type': 'symmetric', 'range_calibration': 'dynamic', 'schedule_offset': 1000}, 'different_groups': {}}, 'sparse_pruning': {'shared_parameters': {'enabled': False, 'method': 'l1', 'schedule_offset': 1000}, 'different_groups': {}}, 'row_pruning': {'shared_parameters': {'enabled': False, 'method': 'l1', 'schedule_offset': 1000}, 'different_groups': {}}, 'head_pruning': {'shared_parameters': {'enabled': False, 'method': 'topk', 'schedule_offset': 1000}, 'different_groups': {}}, 'channel_pruning': {'shared_pa +0: rameters': {'enabled': False, 'method': 'l1', 'schedule_offset': 1000}, 'different_groups': {}}, 'layer_reduction': {'enabled': False}} +0: [2023-05-23 21:57:55,197] [INFO] [config.py:1011:print] curriculum_enabled ........... False +0: [2023-05-23 21:57:55,197] [INFO] [config.py:1011:print] curriculum_params ............ False +0: [2023-05-23 21:57:55,197] [INFO] [config.py:1011:print] dataloader_drop_last ......... False +0: [2023-05-23 21:57:55,197] [INFO] [config.py:1011:print] disable_allgather ............ False +0: [2023-05-23 21:57:55,197] [INFO] [config.py:1011:print] dump_state ................... False +0: [2023-05-23 21:57:55,197] [INFO] [config.py:1011:print] dynamic_loss_scale_args ...... None +0: [2023-05-23 21:57:55,197] [INFO] [config.py:1011:print] eigenvalue_enabled ........... False +0: [2023-05-23 21:57:55,197] [INFO] [config.py:1011:print] eigenvalue_gas_boundary_resolution 1 +0: [2023-05-23 21:57:55,197] [INFO] [config.py:1011:print] eigenvalue_layer_name ........ bert.encoder.layer +0: [2023-05-23 21:57:55,197] [INFO] [config.py:1011:print] eigenvalue_layer_num ......... 0 +0: [2023-05-23 21:57:55,197] [INFO] [config.py:1011:print] eigenvalue_max_iter .......... 100 +0: [2023-05-23 21:57:55,197] [INFO] [config.py:1011:print] eigenvalue_stability ......... 1e-06 +0: [2023-05-23 21:57:55,197] [INFO] [config.py:1011:print] eigenvalue_tol ............... 0.01 +0: [2023-05-23 21:57:55,197] [INFO] [config.py:1011:print] eigenvalue_verbose ........... False +0: [2023-05-23 21:57:55,197] [INFO] [config.py:1011:print] elasticity_enabled ........... False +0: [2023-05-23 21:57:55,197] [INFO] [config.py:1011:print] flops_profiler_config ........ { +0: "enabled": false, +0: "profile_step": 1, +0: "module_depth": -1, +0: "top_modules": 1, +0: "detailed": true, +0: "output_file": null +0: } +0: [2023-05-23 21:57:55,197] [INFO] [config.py:1011:print] fp16_auto_cast ............... None +0: [2023-05-23 21:57:55,197] [INFO] [config.py:1011:print] fp16_enabled ................. False +0: [2023-05-23 21:57:55,197] [INFO] [config.py:1011:print] fp16_master_weights_and_gradients False +0: [2023-05-23 21:57:55,197] [INFO] [config.py:1011:print] global_rank .................. 0 +0: [2023-05-23 21:57:55,197] [INFO] [config.py:1011:print] gradient_accumulation_steps .. 1 +0: [2023-05-23 21:57:55,197] [INFO] [config.py:1011:print] gradient_clipping ............ 1.0 +0: [2023-05-23 21:57:55,197] [INFO] [config.py:1011:print] gradient_predivide_factor .... 1.0 +0: [2023-05-23 21:57:55,197] [INFO] [config.py:1011:print] initial_dynamic_scale ........ 1 +0: [2023-05-23 21:57:55,197] [INFO] [config.py:1011:print] load_universal_checkpoint .... False +0: [2023-05-23 21:57:55,197] [INFO] [config.py:1011:print] loss_scale ................... 1.0 +0: [2023-05-23 21:57:55,197] [INFO] [config.py:1011:print] memory_breakdown ............. False +0: [2023-05-23 21:57:55,197] [INFO] [config.py:1011:print] monitor_config ............... +0: [2023-05-23 21:57:55,197] [INFO] [config.py:1011:print] nebula_config ................ { +0: "enabled": false, +0: "persistent_storage_path": null, +0: "persistent_time_interval": 100, +0: "num_of_version_in_retention": 2, +0: "enable_nebula_load": true, +0: "load_path": null +0: } +0: [2023-05-23 21:57:55,197] [INFO] [config.py:1011:print] optimizer_legacy_fusion ...... False +0: [2023-05-23 21:57:55,197] [INFO] [config.py:1011:print] optimizer_name ............... None +0: [2023-05-23 21:57:55,197] [INFO] [config.py:1011:print] optimizer_params ............. None +0: [2023-05-23 21:57:55,197] [INFO] [config.py:1011:print] pipeline ..................... {'stages': 'auto', 'partition': 'best', 'seed_layers': False, 'activation_checkpoint_interval': 0} +0: [2023-05-23 21:57:55,197] [INFO] [config.py:1011:print] pld_enabled .................. False +0: [2023-05-23 21:57:55,197] [INFO] [config.py:1011:print] pld_params ................... False +0: [2023-05-23 21:57:55,197] [INFO] [config.py:1011:print] prescale_gradients ........... False +0: [2023-05-23 21:57:55,197] [INFO] [config.py:1011:print] scheduler_name ............... None +0: [2023-05-23 21:57:55,198] [INFO] [config.py:1011:print] scheduler_params ............. None +0: [2023-05-23 21:57:55,198] [INFO] [config.py:1011:print] sparse_attention ............. None +0: [2023-05-23 21:57:55,198] [INFO] [config.py:1011:print] sparse_gradients_enabled ..... False +0: [2023-05-23 21:57:55,198] [INFO] [config.py:1011:print] steps_per_print .............. 2000 +0: [2023-05-23 21:57:55,198] [INFO] [config.py:1011:print] train_batch_size ............. 64 +0: [2023-05-23 21:57:55,198] [INFO] [config.py:1011:print] train_micro_batch_size_per_gpu 4 +0: [2023-05-23 21:57:55,198] [INFO] [config.py:1011:print] use_node_local_storage ....... False +0: [2023-05-23 21:57:55,198] [INFO] [config.py:1011:print] wall_clock_breakdown ......... False +0: [2023-05-23 21:57:55,198] [INFO] [config.py:1011:print] world_size ................... 16 +0: [2023-05-23 21:57:55,198] [INFO] [config.py:1011:print] zero_allow_untested_optimizer False +0: [2023-05-23 21:57:55,198] [INFO] [config.py:1011:print] zero_config .................. stage=0 contiguous_gradients=True reduce_scatter=True reduce_bucket_size=500000000 allgather_partitions=True allgather_bucket_size=500000000 overlap_comm=False load_from_fp32_weights=True elastic_checkpoint=False offload_param=None offload_optimizer=None sub_group_size=1000000000 cpu_offload_param=None cpu_offload_use_pin_memory=None cpu_offload=None prefetch_bucket_size=50000000 param_persistence_threshold=100000 model_persistence_threshold=9223372036854775807 max_live_parameters=1000000000 max_reuse_distance=1000000000 gather_16bit_weights_on_model_save=False stage3_gather_fp16_weights_on_model_save=False ignore_unused_parameters=True legacy_stage1=False round_robin_gradients=False +0: [2023-05-23 21:57:55,198] [INFO] [config.py:1011:print] zero_enabled ................. False +0: [2023-05-23 21:57:55,198] [INFO] [config.py:1011:print] zero_optimization_stage ...... 0 +0: [2023-05-23 21:57:55,198] [INFO] [config.py:996:print_user_config] json = { +0: "train_micro_batch_size_per_gpu": 4, +0: "train_batch_size": 64, +0: "gradient_clipping": 1.0, +0: "zero_optimization": { +0: "stage": 0 +0: }, +0: "bf16": { +0: "enabled": true +0: }, +0: "steps_per_print": 2.000000e+03, +0: "wall_clock_breakdown": false +0: } +0: Time to load utils op: 0.0004265308380126953 seconds +0: [2023-05-23 21:57:55,198] [INFO] [engine.py:87:__init__] CONFIG: micro_batches=1 micro_batch_size=4 +0: [2023-05-23 21:57:55,267] [INFO] [engine.py:145:__init__] RANK=0 STAGE=0 LAYERS=10 [0, 10) STAGE_PARAMS=7296128 (7.296M) TOTAL_PARAMS=7296128 (7.296M) UNIQUE_PARAMS=7296128 (7.296M) +1: [2023-05-23 21:57:55,273] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_7m100m100m/global_step190/mp_rank_00_model_states.pt... +1: [2023-05-23 21:57:55,273] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_7m100m100m/global_step190/mp_rank_00_model_states.pt... +1: [2023-05-23 21:57:55,273] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_7m100m100m/global_step190/mp_rank_00_model_states.pt... +1: [2023-05-23 21:57:55,273] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_7m100m100m/global_step190/mp_rank_00_model_states.pt... +1: [2023-05-23 21:57:55,273] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_7m100m100m/global_step190/mp_rank_00_model_states.pt... +1: [2023-05-23 21:57:55,273] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_7m100m100m/global_step190/mp_rank_00_model_states.pt... +1: [2023-05-23 21:57:55,273] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_7m100m100m/global_step190/mp_rank_00_model_states.pt... +1: [2023-05-23 21:57:55,273] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_7m100m100m/global_step190/mp_rank_00_model_states.pt... +1: [2023-05-23 21:57:55,281] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_7m100m100m/global_step190/mp_rank_00_model_states.pt. +1: [2023-05-23 21:57:55,281] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_7m100m100m/global_step190/mp_rank_00_model_states.pt. +1: [2023-05-23 21:57:55,281] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_7m100m100m/global_step190/mp_rank_00_model_states.pt. +1: [2023-05-23 21:57:55,281] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_7m100m100m/global_step190/mp_rank_00_model_states.pt. +1: [2023-05-23 21:57:55,281] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_7m100m100m/global_step190/mp_rank_00_model_states.pt. +1: [2023-05-23 21:57:55,282] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_7m100m100m/global_step190/mp_rank_00_model_states.pt. +1: [2023-05-23 21:57:55,282] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_7m100m100m/global_step190/mp_rank_00_model_states.pt. +1: [2023-05-23 21:57:55,282] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_7m100m100m/global_step190/mp_rank_00_model_states.pt... +1: [2023-05-23 21:57:55,282] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_7m100m100m/global_step190/mp_rank_00_model_states.pt... +1: [2023-05-23 21:57:55,282] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_7m100m100m/global_step190/mp_rank_00_model_states.pt... +1: [2023-05-23 21:57:55,282] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_7m100m100m/global_step190/mp_rank_00_model_states.pt... +1: [2023-05-23 21:57:55,282] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_7m100m100m/global_step190/mp_rank_00_model_states.pt... +1: [2023-05-23 21:57:55,282] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_7m100m100m/global_step190/mp_rank_00_model_states.pt... +1: [2023-05-23 21:57:55,282] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_7m100m100m/global_step190/mp_rank_00_model_states.pt... +1: [2023-05-23 21:57:55,282] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_7m100m100m/global_step190/mp_rank_00_model_states.pt. +1: [2023-05-23 21:57:55,282] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_7m100m100m/global_step190/mp_rank_00_model_states.pt... +1: [2023-05-23 21:57:55,282] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_7m100m100m/global_step190/mp_rank_00_model_states.pt. +1: [2023-05-23 21:57:55,283] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_7m100m100m/global_step190/mp_rank_00_model_states.pt. +1: [2023-05-23 21:57:55,283] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_7m100m100m/global_step190/mp_rank_00_model_states.pt. +1: [2023-05-23 21:57:55,283] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_7m100m100m/global_step190/mp_rank_00_model_states.pt. +1: [2023-05-23 21:57:55,283] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_7m100m100m/global_step190/layer_01-model_00-model_states.pt... +1: [2023-05-23 21:57:55,283] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_7m100m100m/global_step190/layer_01-model_00-model_states.pt... +1: [2023-05-23 21:57:55,283] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_7m100m100m/global_step190/mp_rank_00_model_states.pt. +1: [2023-05-23 21:57:55,283] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_7m100m100m/global_step190/layer_01-model_00-model_states.pt... +1: [2023-05-23 21:57:55,283] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_7m100m100m/global_step190/mp_rank_00_model_states.pt. +1: [2023-05-23 21:57:55,283] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_7m100m100m/global_step190/mp_rank_00_model_states.pt. +1: [2023-05-23 21:57:55,283] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_7m100m100m/global_step190/layer_01-model_00-model_states.pt... +1: [2023-05-23 21:57:55,283] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_7m100m100m/global_step190/mp_rank_00_model_states.pt. +1: [2023-05-23 21:57:55,283] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_7m100m100m/global_step190/layer_01-model_00-model_states.pt... +1: [2023-05-23 21:57:55,283] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_7m100m100m/global_step190/layer_01-model_00-model_states.pt... +1: [2023-05-23 21:57:55,283] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_7m100m100m/global_step190/layer_01-model_00-model_states.pt... +1: [2023-05-23 21:57:55,283] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_7m100m100m/global_step190/layer_01-model_00-model_states.pt... +0: [2023-05-23 21:57:55,474] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_7m100m100m/global_step190/mp_rank_00_model_states.pt... +0: [2023-05-23 21:57:55,474] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_7m100m100m/global_step190/mp_rank_00_model_states.pt... +0: [2023-05-23 21:57:55,474] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_7m100m100m/global_step190/mp_rank_00_model_states.pt... +0: [2023-05-23 21:57:55,474] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_7m100m100m/global_step190/mp_rank_00_model_states.pt... +0: [2023-05-23 21:57:55,474] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_7m100m100m/global_step190/mp_rank_00_model_states.pt... +0: [2023-05-23 21:57:55,474] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_7m100m100m/global_step190/mp_rank_00_model_states.pt... +0: [2023-05-23 21:57:55,474] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_7m100m100m/global_step190/mp_rank_00_model_states.pt... +0: [2023-05-23 21:57:55,474] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_7m100m100m/global_step190/mp_rank_00_model_states.pt... +0: [2023-05-23 21:57:55,487] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_7m100m100m/global_step190/mp_rank_00_model_states.pt. +0: [2023-05-23 21:57:55,487] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_7m100m100m/global_step190/mp_rank_00_model_states.pt. +0: [2023-05-23 21:57:55,487] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_7m100m100m/global_step190/mp_rank_00_model_states.pt. +0: [2023-05-23 21:57:55,487] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_7m100m100m/global_step190/mp_rank_00_model_states.pt. +0: [2023-05-23 21:57:55,487] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_7m100m100m/global_step190/mp_rank_00_model_states.pt. +0: [2023-05-23 21:57:55,487] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_7m100m100m/global_step190/mp_rank_00_model_states.pt. +0: [2023-05-23 21:57:55,487] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_7m100m100m/global_step190/mp_rank_00_model_states.pt. +0: [2023-05-23 21:57:55,487] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_7m100m100m/global_step190/mp_rank_00_model_states.pt... +0: [2023-05-23 21:57:55,487] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_7m100m100m/global_step190/mp_rank_00_model_states.pt... +0: [2023-05-23 21:57:55,487] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_7m100m100m/global_step190/mp_rank_00_model_states.pt... +0: [2023-05-23 21:57:55,487] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_7m100m100m/global_step190/mp_rank_00_model_states.pt... +0: [2023-05-23 21:57:55,487] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_7m100m100m/global_step190/mp_rank_00_model_states.pt... +0: [2023-05-23 21:57:55,487] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_7m100m100m/global_step190/mp_rank_00_model_states.pt... +0: [2023-05-23 21:57:55,487] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_7m100m100m/global_step190/mp_rank_00_model_states.pt... +0: [2023-05-23 21:57:55,487] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_7m100m100m/global_step190/mp_rank_00_model_states.pt. +0: [2023-05-23 21:57:55,487] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_7m100m100m/global_step190/mp_rank_00_model_states.pt... +0: [2023-05-23 21:57:55,488] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_7m100m100m/global_step190/mp_rank_00_model_states.pt. +0: [2023-05-23 21:57:55,488] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_7m100m100m/global_step190/mp_rank_00_model_states.pt. +0: [2023-05-23 21:57:55,488] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_7m100m100m/global_step190/mp_rank_00_model_states.pt. +0: [2023-05-23 21:57:55,488] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_7m100m100m/global_step190/mp_rank_00_model_states.pt. +0: [2023-05-23 21:57:55,488] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_7m100m100m/global_step190/mp_rank_00_model_states.pt. +0: [2023-05-23 21:57:55,488] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_7m100m100m/global_step190/mp_rank_00_model_states.pt. +0: [2023-05-23 21:57:55,488] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_7m100m100m/global_step190/mp_rank_00_model_states.pt. +0: [2023-05-23 21:57:55,488] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_7m100m100m/global_step190/mp_rank_00_model_states.pt. +0: [2023-05-23 21:57:55,489] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_7m100m100m/global_step190/layer_01-model_00-model_states.pt... +0: [2023-05-23 21:57:55,489] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_7m100m100m/global_step190/layer_01-model_00-model_states.pt... +0: [2023-05-23 21:57:55,489] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_7m100m100m/global_step190/layer_01-model_00-model_states.pt... +0: [2023-05-23 21:57:55,489] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_7m100m100m/global_step190/layer_01-model_00-model_states.pt... +0: [2023-05-23 21:57:55,489] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_7m100m100m/global_step190/layer_01-model_00-model_states.pt... +0: [2023-05-23 21:57:55,489] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_7m100m100m/global_step190/layer_01-model_00-model_states.pt... +0: [2023-05-23 21:57:55,489] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_7m100m100m/global_step190/layer_01-model_00-model_states.pt... +0: [2023-05-23 21:57:55,489] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_7m100m100m/global_step190/layer_01-model_00-model_states.pt... +1: [2023-05-23 21:57:55,554] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_7m100m100m/global_step190/layer_01-model_00-model_states.pt. +1: [2023-05-23 21:57:55,554] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_7m100m100m/global_step190/layer_01-model_00-model_states.pt. +1: [2023-05-23 21:57:55,554] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_7m100m100m/global_step190/layer_01-model_00-model_states.pt... +1: [2023-05-23 21:57:55,554] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_7m100m100m/global_step190/layer_01-model_00-model_states.pt... +1: [2023-05-23 21:57:55,554] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_7m100m100m/global_step190/layer_01-model_00-model_states.pt. +1: [2023-05-23 21:57:55,554] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_7m100m100m/global_step190/layer_01-model_00-model_states.pt... +1: [2023-05-23 21:57:55,554] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_7m100m100m/global_step190/layer_01-model_00-model_states.pt. +1: [2023-05-23 21:57:55,554] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_7m100m100m/global_step190/layer_01-model_00-model_states.pt. +1: [2023-05-23 21:57:55,554] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_7m100m100m/global_step190/layer_01-model_00-model_states.pt. +1: [2023-05-23 21:57:55,554] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_7m100m100m/global_step190/layer_01-model_00-model_states.pt. +1: [2023-05-23 21:57:55,555] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_7m100m100m/global_step190/layer_01-model_00-model_states.pt. +1: [2023-05-23 21:57:55,555] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_7m100m100m/global_step190/layer_01-model_00-model_states.pt... +1: [2023-05-23 21:57:55,555] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_7m100m100m/global_step190/layer_01-model_00-model_states.pt... +1: [2023-05-23 21:57:55,555] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_7m100m100m/global_step190/layer_01-model_00-model_states.pt... +1: [2023-05-23 21:57:55,555] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_7m100m100m/global_step190/layer_01-model_00-model_states.pt... +1: [2023-05-23 21:57:55,555] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_7m100m100m/global_step190/layer_01-model_00-model_states.pt... +0: [2023-05-23 21:57:55,555] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_7m100m100m/global_step190/layer_01-model_00-model_states.pt. +0: [2023-05-23 21:57:55,555] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_7m100m100m/global_step190/layer_01-model_00-model_states.pt... +0: [2023-05-23 21:57:55,555] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_7m100m100m/global_step190/layer_01-model_00-model_states.pt. +0: [2023-05-23 21:57:55,556] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_7m100m100m/global_step190/layer_01-model_00-model_states.pt... +0: [2023-05-23 21:57:55,556] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_7m100m100m/global_step190/layer_01-model_00-model_states.pt. +0: [2023-05-23 21:57:55,556] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_7m100m100m/global_step190/layer_01-model_00-model_states.pt... +0: [2023-05-23 21:57:55,556] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_7m100m100m/global_step190/layer_01-model_00-model_states.pt. +0: [2023-05-23 21:57:55,556] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_7m100m100m/global_step190/layer_01-model_00-model_states.pt. +0: [2023-05-23 21:57:55,556] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_7m100m100m/global_step190/layer_01-model_00-model_states.pt. +0: [2023-05-23 21:57:55,556] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_7m100m100m/global_step190/layer_01-model_00-model_states.pt. +0: [2023-05-23 21:57:55,556] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_7m100m100m/global_step190/layer_01-model_00-model_states.pt. +0: [2023-05-23 21:57:55,556] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_7m100m100m/global_step190/layer_01-model_00-model_states.pt... +0: [2023-05-23 21:57:55,556] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_7m100m100m/global_step190/layer_01-model_00-model_states.pt... +0: [2023-05-23 21:57:55,556] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_7m100m100m/global_step190/layer_01-model_00-model_states.pt... +0: [2023-05-23 21:57:55,556] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_7m100m100m/global_step190/layer_01-model_00-model_states.pt... +0: [2023-05-23 21:57:55,556] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_7m100m100m/global_step190/layer_01-model_00-model_states.pt... +1: [2023-05-23 21:57:55,557] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_7m100m100m/global_step190/layer_01-model_00-model_states.pt. +1: [2023-05-23 21:57:55,557] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_7m100m100m/global_step190/layer_01-model_00-model_states.pt. +1: [2023-05-23 21:57:55,558] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_7m100m100m/global_step190/layer_01-model_00-model_states.pt. +1: [2023-05-23 21:57:55,558] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_7m100m100m/global_step190/layer_01-model_00-model_states.pt. +1: [2023-05-23 21:57:55,560] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_7m100m100m/global_step190/layer_03-model_00-model_states.pt... +1: [2023-05-23 21:57:55,560] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_7m100m100m/global_step190/layer_01-model_00-model_states.pt. +1: [2023-05-23 21:57:55,560] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_7m100m100m/global_step190/layer_01-model_00-model_states.pt. +1: [2023-05-23 21:57:55,561] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_7m100m100m/global_step190/layer_03-model_00-model_states.pt... +0: [2023-05-23 21:57:55,561] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_7m100m100m/global_step190/layer_01-model_00-model_states.pt. +1: [2023-05-23 21:57:55,561] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_7m100m100m/global_step190/layer_03-model_00-model_states.pt... +0: [2023-05-23 21:57:55,561] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_7m100m100m/global_step190/layer_01-model_00-model_states.pt. +1: [2023-05-23 21:57:55,561] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_7m100m100m/global_step190/layer_03-model_00-model_states.pt... +1: [2023-05-23 21:57:55,561] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_7m100m100m/global_step190/layer_01-model_00-model_states.pt. +0: [2023-05-23 21:57:55,563] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_7m100m100m/global_step190/layer_01-model_00-model_states.pt. +0: [2023-05-23 21:57:55,563] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_7m100m100m/global_step190/layer_01-model_00-model_states.pt. +0: [2023-05-23 21:57:55,563] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_7m100m100m/global_step190/layer_01-model_00-model_states.pt. +0: [2023-05-23 21:57:55,563] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_7m100m100m/global_step190/layer_01-model_00-model_states.pt. +1: [2023-05-23 21:57:55,563] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_7m100m100m/global_step190/layer_03-model_00-model_states.pt... +1: [2023-05-23 21:57:55,563] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_7m100m100m/global_step190/layer_01-model_00-model_states.pt. +1: [2023-05-23 21:57:55,563] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_7m100m100m/global_step190/layer_03-model_00-model_states.pt... +1: [2023-05-23 21:57:55,563] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_7m100m100m/global_step190/layer_03-model_00-model_states.pt... +0: [2023-05-23 21:57:55,564] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_7m100m100m/global_step190/layer_01-model_00-model_states.pt. +0: [2023-05-23 21:57:55,564] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_7m100m100m/global_step190/layer_03-model_00-model_states.pt... +0: [2023-05-23 21:57:55,564] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_7m100m100m/global_step190/layer_03-model_00-model_states.pt... +1: [2023-05-23 21:57:55,565] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_7m100m100m/global_step190/layer_03-model_00-model_states.pt... +1: [2023-05-23 21:57:55,566] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_7m100m100m/global_step190/layer_03-model_00-model_states.pt. +1: [2023-05-23 21:57:55,566] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_7m100m100m/global_step190/layer_03-model_00-model_states.pt... +1: [2023-05-23 21:57:55,566] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_7m100m100m/global_step190/layer_03-model_00-model_states.pt. +1: [2023-05-23 21:57:55,566] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_7m100m100m/global_step190/layer_03-model_00-model_states.pt... +1: [2023-05-23 21:57:55,566] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_7m100m100m/global_step190/layer_03-model_00-model_states.pt. +1: [2023-05-23 21:57:55,566] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_7m100m100m/global_step190/layer_03-model_00-model_states.pt. +1: [2023-05-23 21:57:55,566] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_7m100m100m/global_step190/layer_03-model_00-model_states.pt... +1: [2023-05-23 21:57:55,566] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_7m100m100m/global_step190/layer_03-model_00-model_states.pt... +1: [2023-05-23 21:57:55,566] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_7m100m100m/global_step190/layer_03-model_00-model_states.pt. +1: [2023-05-23 21:57:55,566] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_7m100m100m/global_step190/layer_03-model_00-model_states.pt. +1: [2023-05-23 21:57:55,566] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_7m100m100m/global_step190/layer_03-model_00-model_states.pt. +1: [2023-05-23 21:57:55,566] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_7m100m100m/global_step190/layer_03-model_00-model_states.pt... +1: [2023-05-23 21:57:55,566] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_7m100m100m/global_step190/layer_03-model_00-model_states.pt... +1: [2023-05-23 21:57:55,566] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_7m100m100m/global_step190/layer_03-model_00-model_states.pt... +1: [2023-05-23 21:57:55,566] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_7m100m100m/global_step190/layer_03-model_00-model_states.pt. +1: [2023-05-23 21:57:55,566] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_7m100m100m/global_step190/layer_03-model_00-model_states.pt... +0: [2023-05-23 21:57:55,566] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_7m100m100m/global_step190/layer_03-model_00-model_states.pt... +0: [2023-05-23 21:57:55,566] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_7m100m100m/global_step190/layer_03-model_00-model_states.pt... +0: [2023-05-23 21:57:55,566] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_7m100m100m/global_step190/layer_03-model_00-model_states.pt... +1: [2023-05-23 21:57:55,566] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_7m100m100m/global_step190/layer_03-model_00-model_states.pt. +1: [2023-05-23 21:57:55,567] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_7m100m100m/global_step190/layer_03-model_00-model_states.pt. +0: [2023-05-23 21:57:55,567] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_7m100m100m/global_step190/layer_03-model_00-model_states.pt... +0: [2023-05-23 21:57:55,567] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_7m100m100m/global_step190/layer_03-model_00-model_states.pt... +1: [2023-05-23 21:57:55,567] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_7m100m100m/global_step190/layer_03-model_00-model_states.pt. +1: [2023-05-23 21:57:55,567] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_7m100m100m/global_step190/layer_03-model_00-model_states.pt. +1: [2023-05-23 21:57:55,567] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_7m100m100m/global_step190/layer_03-model_00-model_states.pt. +1: [2023-05-23 21:57:55,567] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_7m100m100m/global_step190/layer_03-model_00-model_states.pt. +1: [2023-05-23 21:57:55,567] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_7m100m100m/global_step190/layer_03-model_00-model_states.pt. +1: [2023-05-23 21:57:55,567] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_7m100m100m/global_step190/layer_03-model_00-model_states.pt. +1: [2023-05-23 21:57:55,567] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_7m100m100m/global_step190/layer_04-model_00-model_states.pt... +0: [2023-05-23 21:57:55,567] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_7m100m100m/global_step190/layer_01-model_00-model_states.pt. +1: [2023-05-23 21:57:55,568] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_7m100m100m/global_step190/layer_04-model_00-model_states.pt... +1: [2023-05-23 21:57:55,568] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_7m100m100m/global_step190/layer_04-model_00-model_states.pt... +1: [2023-05-23 21:57:55,568] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_7m100m100m/global_step190/layer_04-model_00-model_states.pt... +1: [2023-05-23 21:57:55,568] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_7m100m100m/global_step190/layer_04-model_00-model_states.pt... +1: [2023-05-23 21:57:55,568] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_7m100m100m/global_step190/layer_04-model_00-model_states.pt... +1: [2023-05-23 21:57:55,568] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_7m100m100m/global_step190/layer_04-model_00-model_states.pt... +1: [2023-05-23 21:57:55,568] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_7m100m100m/global_step190/layer_04-model_00-model_states.pt... +0: [2023-05-23 21:57:55,570] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_7m100m100m/global_step190/layer_03-model_00-model_states.pt... +1: [2023-05-23 21:57:55,571] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_7m100m100m/global_step190/layer_04-model_00-model_states.pt. +1: [2023-05-23 21:57:55,571] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_7m100m100m/global_step190/layer_04-model_00-model_states.pt... +1: [2023-05-23 21:57:55,571] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_7m100m100m/global_step190/layer_04-model_00-model_states.pt. +1: [2023-05-23 21:57:55,571] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_7m100m100m/global_step190/layer_04-model_00-model_states.pt. +1: [2023-05-23 21:57:55,571] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_7m100m100m/global_step190/layer_04-model_00-model_states.pt. +1: [2023-05-23 21:57:55,571] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_7m100m100m/global_step190/layer_04-model_00-model_states.pt... +1: [2023-05-23 21:57:55,571] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_7m100m100m/global_step190/layer_04-model_00-model_states.pt. +1: [2023-05-23 21:57:55,571] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_7m100m100m/global_step190/layer_04-model_00-model_states.pt... +1: [2023-05-23 21:57:55,571] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_7m100m100m/global_step190/layer_04-model_00-model_states.pt. +1: [2023-05-23 21:57:55,571] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_7m100m100m/global_step190/layer_04-model_00-model_states.pt... +1: [2023-05-23 21:57:55,571] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_7m100m100m/global_step190/layer_04-model_00-model_states.pt. +1: [2023-05-23 21:57:55,571] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_7m100m100m/global_step190/layer_04-model_00-model_states.pt. +1: [2023-05-23 21:57:55,571] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_7m100m100m/global_step190/layer_04-model_00-model_states.pt... +1: [2023-05-23 21:57:55,571] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_7m100m100m/global_step190/layer_04-model_00-model_states.pt... +1: [2023-05-23 21:57:55,571] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_7m100m100m/global_step190/layer_04-model_00-model_states.pt... +1: [2023-05-23 21:57:55,572] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_7m100m100m/global_step190/layer_04-model_00-model_states.pt... +1: [2023-05-23 21:57:55,572] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_7m100m100m/global_step190/layer_04-model_00-model_states.pt. +1: [2023-05-23 21:57:55,572] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_7m100m100m/global_step190/layer_04-model_00-model_states.pt. +1: [2023-05-23 21:57:55,572] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_7m100m100m/global_step190/layer_04-model_00-model_states.pt. +1: [2023-05-23 21:57:55,572] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_7m100m100m/global_step190/layer_04-model_00-model_states.pt. +1: [2023-05-23 21:57:55,572] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_7m100m100m/global_step190/layer_04-model_00-model_states.pt. +1: [2023-05-23 21:57:55,572] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_7m100m100m/global_step190/layer_04-model_00-model_states.pt. +1: [2023-05-23 21:57:55,572] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_7m100m100m/global_step190/layer_04-model_00-model_states.pt. +1: [2023-05-23 21:57:55,572] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_7m100m100m/global_step190/layer_04-model_00-model_states.pt. +1: [2023-05-23 21:57:55,573] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_7m100m100m/global_step190/layer_05-model_00-model_states.pt... +1: [2023-05-23 21:57:55,573] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_7m100m100m/global_step190/layer_05-model_00-model_states.pt... +1: [2023-05-23 21:57:55,573] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_7m100m100m/global_step190/layer_05-model_00-model_states.pt... +1: [2023-05-23 21:57:55,573] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_7m100m100m/global_step190/layer_05-model_00-model_states.pt... +1: [2023-05-23 21:57:55,573] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_7m100m100m/global_step190/layer_05-model_00-model_states.pt... +1: [2023-05-23 21:57:55,573] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_7m100m100m/global_step190/layer_05-model_00-model_states.pt... +1: [2023-05-23 21:57:55,573] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_7m100m100m/global_step190/layer_05-model_00-model_states.pt... +1: [2023-05-23 21:57:55,573] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_7m100m100m/global_step190/layer_05-model_00-model_states.pt... +0: [2023-05-23 21:57:55,779] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_7m100m100m/global_step190/layer_03-model_00-model_states.pt. +0: [2023-05-23 21:57:55,779] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_7m100m100m/global_step190/layer_03-model_00-model_states.pt... +0: [2023-05-23 21:57:55,780] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_7m100m100m/global_step190/layer_03-model_00-model_states.pt. +0: [2023-05-23 21:57:55,780] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_7m100m100m/global_step190/layer_03-model_00-model_states.pt. +0: [2023-05-23 21:57:55,780] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_7m100m100m/global_step190/layer_03-model_00-model_states.pt... +0: [2023-05-23 21:57:55,780] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_7m100m100m/global_step190/layer_03-model_00-model_states.pt. +0: [2023-05-23 21:57:55,780] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_7m100m100m/global_step190/layer_03-model_00-model_states.pt. +0: [2023-05-23 21:57:55,780] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_7m100m100m/global_step190/layer_03-model_00-model_states.pt. +0: [2023-05-23 21:57:55,780] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_7m100m100m/global_step190/layer_03-model_00-model_states.pt... +0: [2023-05-23 21:57:55,780] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_7m100m100m/global_step190/layer_03-model_00-model_states.pt. +0: [2023-05-23 21:57:55,780] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_7m100m100m/global_step190/layer_03-model_00-model_states.pt... +0: [2023-05-23 21:57:55,780] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_7m100m100m/global_step190/layer_03-model_00-model_states.pt... +0: [2023-05-23 21:57:55,780] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_7m100m100m/global_step190/layer_03-model_00-model_states.pt... +0: [2023-05-23 21:57:55,780] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_7m100m100m/global_step190/layer_03-model_00-model_states.pt. +0: [2023-05-23 21:57:55,780] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_7m100m100m/global_step190/layer_03-model_00-model_states.pt... +0: [2023-05-23 21:57:55,780] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_7m100m100m/global_step190/layer_03-model_00-model_states.pt... +0: [2023-05-23 21:57:55,780] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_7m100m100m/global_step190/layer_03-model_00-model_states.pt. +0: [2023-05-23 21:57:55,780] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_7m100m100m/global_step190/layer_03-model_00-model_states.pt. +0: [2023-05-23 21:57:55,781] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_7m100m100m/global_step190/layer_03-model_00-model_states.pt. +0: [2023-05-23 21:57:55,781] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_7m100m100m/global_step190/layer_03-model_00-model_states.pt. +0: [2023-05-23 21:57:55,781] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_7m100m100m/global_step190/layer_03-model_00-model_states.pt. +0: [2023-05-23 21:57:55,781] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_7m100m100m/global_step190/layer_03-model_00-model_states.pt. +0: [2023-05-23 21:57:55,781] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_7m100m100m/global_step190/layer_03-model_00-model_states.pt. +0: [2023-05-23 21:57:55,781] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_7m100m100m/global_step190/layer_03-model_00-model_states.pt. +0: [2023-05-23 21:57:55,781] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_7m100m100m/global_step190/layer_04-model_00-model_states.pt... +0: [2023-05-23 21:57:55,781] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_7m100m100m/global_step190/layer_04-model_00-model_states.pt... +0: [2023-05-23 21:57:55,782] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_7m100m100m/global_step190/layer_04-model_00-model_states.pt... +0: [2023-05-23 21:57:55,782] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_7m100m100m/global_step190/layer_04-model_00-model_states.pt... +0: [2023-05-23 21:57:55,782] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_7m100m100m/global_step190/layer_04-model_00-model_states.pt... +0: [2023-05-23 21:57:55,782] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_7m100m100m/global_step190/layer_04-model_00-model_states.pt... +0: [2023-05-23 21:57:55,782] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_7m100m100m/global_step190/layer_04-model_00-model_states.pt... +0: [2023-05-23 21:57:55,782] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_7m100m100m/global_step190/layer_04-model_00-model_states.pt... +1: [2023-05-23 21:57:55,783] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_7m100m100m/global_step190/layer_05-model_00-model_states.pt. +1: [2023-05-23 21:57:55,783] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_7m100m100m/global_step190/layer_05-model_00-model_states.pt. +1: [2023-05-23 21:57:55,783] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_7m100m100m/global_step190/layer_05-model_00-model_states.pt. +1: [2023-05-23 21:57:55,783] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_7m100m100m/global_step190/layer_05-model_00-model_states.pt. +1: [2023-05-23 21:57:55,783] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_7m100m100m/global_step190/layer_05-model_00-model_states.pt. +1: [2023-05-23 21:57:55,783] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_7m100m100m/global_step190/layer_05-model_00-model_states.pt... +1: [2023-05-23 21:57:55,783] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_7m100m100m/global_step190/layer_05-model_00-model_states.pt... +1: [2023-05-23 21:57:55,783] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_7m100m100m/global_step190/layer_05-model_00-model_states.pt... +1: [2023-05-23 21:57:55,783] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_7m100m100m/global_step190/layer_05-model_00-model_states.pt... +1: [2023-05-23 21:57:55,783] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_7m100m100m/global_step190/layer_05-model_00-model_states.pt. +1: [2023-05-23 21:57:55,783] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_7m100m100m/global_step190/layer_05-model_00-model_states.pt... +1: [2023-05-23 21:57:55,783] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_7m100m100m/global_step190/layer_05-model_00-model_states.pt. +1: [2023-05-23 21:57:55,783] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_7m100m100m/global_step190/layer_05-model_00-model_states.pt... +1: [2023-05-23 21:57:55,783] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_7m100m100m/global_step190/layer_05-model_00-model_states.pt... +1: [2023-05-23 21:57:55,783] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_7m100m100m/global_step190/layer_05-model_00-model_states.pt. +1: [2023-05-23 21:57:55,784] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_7m100m100m/global_step190/layer_05-model_00-model_states.pt... +1: [2023-05-23 21:57:55,784] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_7m100m100m/global_step190/layer_05-model_00-model_states.pt. +1: [2023-05-23 21:57:55,784] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_7m100m100m/global_step190/layer_05-model_00-model_states.pt. +1: [2023-05-23 21:57:55,784] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_7m100m100m/global_step190/layer_05-model_00-model_states.pt. +1: [2023-05-23 21:57:55,784] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_7m100m100m/global_step190/layer_05-model_00-model_states.pt. +1: [2023-05-23 21:57:55,784] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_7m100m100m/global_step190/layer_05-model_00-model_states.pt. +1: [2023-05-23 21:57:55,784] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_7m100m100m/global_step190/layer_05-model_00-model_states.pt. +1: [2023-05-23 21:57:55,784] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_7m100m100m/global_step190/layer_05-model_00-model_states.pt. +1: [2023-05-23 21:57:55,785] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_7m100m100m/global_step190/layer_05-model_00-model_states.pt. +0: [2023-05-23 21:57:55,785] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_7m100m100m/global_step190/layer_04-model_00-model_states.pt. +1: [2023-05-23 21:57:55,785] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_7m100m100m/global_step190/layer_07-model_00-model_states.pt... +0: [2023-05-23 21:57:55,785] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_7m100m100m/global_step190/layer_04-model_00-model_states.pt... +1: [2023-05-23 21:57:55,785] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_7m100m100m/global_step190/layer_07-model_00-model_states.pt... +1: [2023-05-23 21:57:55,785] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_7m100m100m/global_step190/layer_07-model_00-model_states.pt... +1: [2023-05-23 21:57:55,785] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_7m100m100m/global_step190/layer_07-model_00-model_states.pt... +1: [2023-05-23 21:57:55,785] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_7m100m100m/global_step190/layer_07-model_00-model_states.pt... +1: [2023-05-23 21:57:55,785] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_7m100m100m/global_step190/layer_07-model_00-model_states.pt... +0: [2023-05-23 21:57:55,785] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_7m100m100m/global_step190/layer_04-model_00-model_states.pt. +0: [2023-05-23 21:57:55,785] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_7m100m100m/global_step190/layer_04-model_00-model_states.pt. +0: [2023-05-23 21:57:55,785] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_7m100m100m/global_step190/layer_04-model_00-model_states.pt. +0: [2023-05-23 21:57:55,785] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_7m100m100m/global_step190/layer_04-model_00-model_states.pt. +0: [2023-05-23 21:57:55,785] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_7m100m100m/global_step190/layer_04-model_00-model_states.pt... +1: [2023-05-23 21:57:55,785] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_7m100m100m/global_step190/layer_07-model_00-model_states.pt... +0: [2023-05-23 21:57:55,785] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_7m100m100m/global_step190/layer_04-model_00-model_states.pt. +0: [2023-05-23 21:57:55,785] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_7m100m100m/global_step190/layer_04-model_00-model_states.pt... +0: [2023-05-23 21:57:55,785] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_7m100m100m/global_step190/layer_04-model_00-model_states.pt... +0: [2023-05-23 21:57:55,785] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_7m100m100m/global_step190/layer_04-model_00-model_states.pt... +0: [2023-05-23 21:57:55,785] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_7m100m100m/global_step190/layer_04-model_00-model_states.pt. +0: [2023-05-23 21:57:55,785] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_7m100m100m/global_step190/layer_04-model_00-model_states.pt... +1: [2023-05-23 21:57:55,785] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_7m100m100m/global_step190/layer_07-model_00-model_states.pt... +0: [2023-05-23 21:57:55,785] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_7m100m100m/global_step190/layer_04-model_00-model_states.pt... +0: [2023-05-23 21:57:55,785] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_7m100m100m/global_step190/layer_04-model_00-model_states.pt. +0: [2023-05-23 21:57:55,786] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_7m100m100m/global_step190/layer_04-model_00-model_states.pt. +0: [2023-05-23 21:57:55,786] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_7m100m100m/global_step190/layer_04-model_00-model_states.pt. +0: [2023-05-23 21:57:55,786] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_7m100m100m/global_step190/layer_05-model_00-model_states.pt... +0: [2023-05-23 21:57:55,786] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_7m100m100m/global_step190/layer_04-model_00-model_states.pt. +0: [2023-05-23 21:57:55,786] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_7m100m100m/global_step190/layer_04-model_00-model_states.pt. +0: [2023-05-23 21:57:55,786] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_7m100m100m/global_step190/layer_04-model_00-model_states.pt. +0: [2023-05-23 21:57:55,786] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_7m100m100m/global_step190/layer_04-model_00-model_states.pt. +1: [2023-05-23 21:57:55,787] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_7m100m100m/global_step190/layer_07-model_00-model_states.pt. +1: [2023-05-23 21:57:55,787] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_7m100m100m/global_step190/layer_07-model_00-model_states.pt. +1: [2023-05-23 21:57:55,787] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_7m100m100m/global_step190/layer_07-model_00-model_states.pt. +0: [2023-05-23 21:57:55,787] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_7m100m100m/global_step190/layer_05-model_00-model_states.pt... +1: [2023-05-23 21:57:55,787] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_7m100m100m/global_step190/layer_07-model_00-model_states.pt. +1: [2023-05-23 21:57:55,787] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_7m100m100m/global_step190/layer_07-model_00-model_states.pt. +1: [2023-05-23 21:57:55,787] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_7m100m100m/global_step190/layer_07-model_00-model_states.pt. +1: [2023-05-23 21:57:55,787] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_7m100m100m/global_step190/layer_07-model_00-model_states.pt... +1: [2023-05-23 21:57:55,787] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_7m100m100m/global_step190/layer_07-model_00-model_states.pt... +1: [2023-05-23 21:57:55,787] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_7m100m100m/global_step190/layer_07-model_00-model_states.pt... +1: [2023-05-23 21:57:55,787] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_7m100m100m/global_step190/layer_07-model_00-model_states.pt... +1: [2023-05-23 21:57:55,787] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_7m100m100m/global_step190/layer_07-model_00-model_states.pt... +1: [2023-05-23 21:57:55,787] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_7m100m100m/global_step190/layer_07-model_00-model_states.pt... +0: [2023-05-23 21:57:55,787] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_7m100m100m/global_step190/layer_05-model_00-model_states.pt... +0: [2023-05-23 21:57:55,787] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_7m100m100m/global_step190/layer_05-model_00-model_states.pt... +0: [2023-05-23 21:57:55,787] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_7m100m100m/global_step190/layer_05-model_00-model_states.pt... +0: [2023-05-23 21:57:55,787] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_7m100m100m/global_step190/layer_05-model_00-model_states.pt... +0: [2023-05-23 21:57:55,787] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_7m100m100m/global_step190/layer_05-model_00-model_states.pt... +1: [2023-05-23 21:57:55,787] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_7m100m100m/global_step190/layer_07-model_00-model_states.pt. +1: [2023-05-23 21:57:55,787] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_7m100m100m/global_step190/layer_07-model_00-model_states.pt. +1: [2023-05-23 21:57:55,787] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_7m100m100m/global_step190/layer_07-model_00-model_states.pt. +1: [2023-05-23 21:57:55,787] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_7m100m100m/global_step190/layer_07-model_00-model_states.pt. +1: [2023-05-23 21:57:55,787] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_7m100m100m/global_step190/layer_07-model_00-model_states.pt. +1: [2023-05-23 21:57:55,787] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_7m100m100m/global_step190/layer_07-model_00-model_states.pt. +0: [2023-05-23 21:57:55,787] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_7m100m100m/global_step190/layer_04-model_00-model_states.pt. +0: [2023-05-23 21:57:55,788] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_7m100m100m/global_step190/layer_04-model_00-model_states.pt... +0: [2023-05-23 21:57:55,789] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_7m100m100m/global_step190/layer_04-model_00-model_states.pt. +0: [2023-05-23 21:57:55,789] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_7m100m100m/global_step190/layer_05-model_00-model_states.pt... +0: [2023-05-23 21:57:55,790] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_7m100m100m/global_step190/layer_05-model_00-model_states.pt. +0: [2023-05-23 21:57:55,790] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_7m100m100m/global_step190/layer_05-model_00-model_states.pt. +0: [2023-05-23 21:57:55,790] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_7m100m100m/global_step190/layer_05-model_00-model_states.pt... +0: [2023-05-23 21:57:55,790] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_7m100m100m/global_step190/layer_05-model_00-model_states.pt... +0: [2023-05-23 21:57:55,790] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_7m100m100m/global_step190/layer_05-model_00-model_states.pt. +0: [2023-05-23 21:57:55,790] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_7m100m100m/global_step190/layer_05-model_00-model_states.pt. +0: [2023-05-23 21:57:55,790] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_7m100m100m/global_step190/layer_05-model_00-model_states.pt. +0: [2023-05-23 21:57:55,790] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_7m100m100m/global_step190/layer_05-model_00-model_states.pt. +0: [2023-05-23 21:57:55,790] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_7m100m100m/global_step190/layer_05-model_00-model_states.pt. +0: [2023-05-23 21:57:55,790] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_7m100m100m/global_step190/layer_05-model_00-model_states.pt... +0: [2023-05-23 21:57:55,790] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_7m100m100m/global_step190/layer_05-model_00-model_states.pt. +0: [2023-05-23 21:57:55,790] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_7m100m100m/global_step190/layer_05-model_00-model_states.pt... +0: [2023-05-23 21:57:55,790] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_7m100m100m/global_step190/layer_05-model_00-model_states.pt... +0: [2023-05-23 21:57:55,790] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_7m100m100m/global_step190/layer_05-model_00-model_states.pt... +0: [2023-05-23 21:57:55,790] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_7m100m100m/global_step190/layer_05-model_00-model_states.pt... +0: [2023-05-23 21:57:55,790] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_7m100m100m/global_step190/layer_05-model_00-model_states.pt... +0: [2023-05-23 21:57:55,791] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_7m100m100m/global_step190/layer_05-model_00-model_states.pt. +0: [2023-05-23 21:57:55,791] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_7m100m100m/global_step190/layer_05-model_00-model_states.pt. +0: [2023-05-23 21:57:55,791] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_7m100m100m/global_step190/layer_05-model_00-model_states.pt. +0: [2023-05-23 21:57:55,791] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_7m100m100m/global_step190/layer_05-model_00-model_states.pt. +0: [2023-05-23 21:57:55,791] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_7m100m100m/global_step190/layer_05-model_00-model_states.pt. +0: [2023-05-23 21:57:55,791] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_7m100m100m/global_step190/layer_05-model_00-model_states.pt. +0: [2023-05-23 21:57:55,791] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_7m100m100m/global_step190/layer_05-model_00-model_states.pt. +0: [2023-05-23 21:57:55,792] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_7m100m100m/global_step190/layer_07-model_00-model_states.pt... +0: [2023-05-23 21:57:55,792] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_7m100m100m/global_step190/layer_05-model_00-model_states.pt. +0: [2023-05-23 21:57:55,792] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_7m100m100m/global_step190/layer_07-model_00-model_states.pt... +0: [2023-05-23 21:57:55,792] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_7m100m100m/global_step190/layer_07-model_00-model_states.pt... +0: [2023-05-23 21:57:55,792] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_7m100m100m/global_step190/layer_07-model_00-model_states.pt... +0: [2023-05-23 21:57:55,792] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_7m100m100m/global_step190/layer_07-model_00-model_states.pt... +0: [2023-05-23 21:57:55,792] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_7m100m100m/global_step190/layer_07-model_00-model_states.pt... +0: [2023-05-23 21:57:55,792] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_7m100m100m/global_step190/layer_07-model_00-model_states.pt... +0: [2023-05-23 21:57:55,793] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_7m100m100m/global_step190/layer_07-model_00-model_states.pt... +0: [2023-05-23 21:57:55,793] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_7m100m100m/global_step190/layer_07-model_00-model_states.pt. +0: [2023-05-23 21:57:55,793] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_7m100m100m/global_step190/layer_07-model_00-model_states.pt. +0: [2023-05-23 21:57:55,793] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_7m100m100m/global_step190/layer_07-model_00-model_states.pt. +0: [2023-05-23 21:57:55,793] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_7m100m100m/global_step190/layer_07-model_00-model_states.pt. +0: [2023-05-23 21:57:55,793] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_7m100m100m/global_step190/layer_07-model_00-model_states.pt... +0: [2023-05-23 21:57:55,793] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_7m100m100m/global_step190/layer_07-model_00-model_states.pt. +0: [2023-05-23 21:57:55,793] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_7m100m100m/global_step190/layer_07-model_00-model_states.pt. +0: [2023-05-23 21:57:55,793] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_7m100m100m/global_step190/layer_07-model_00-model_states.pt. +0: [2023-05-23 21:57:55,793] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_7m100m100m/global_step190/layer_07-model_00-model_states.pt... +0: [2023-05-23 21:57:55,793] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_7m100m100m/global_step190/layer_07-model_00-model_states.pt... +0: [2023-05-23 21:57:55,793] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_7m100m100m/global_step190/layer_07-model_00-model_states.pt... +0: [2023-05-23 21:57:55,793] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_7m100m100m/global_step190/layer_07-model_00-model_states.pt... +0: [2023-05-23 21:57:55,793] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_7m100m100m/global_step190/layer_07-model_00-model_states.pt... +0: [2023-05-23 21:57:55,793] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_7m100m100m/global_step190/layer_07-model_00-model_states.pt... +0: [2023-05-23 21:57:55,793] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_7m100m100m/global_step190/layer_07-model_00-model_states.pt. +0: [2023-05-23 21:57:55,793] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_7m100m100m/global_step190/layer_07-model_00-model_states.pt... +0: [2023-05-23 21:57:55,794] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_7m100m100m/global_step190/layer_07-model_00-model_states.pt. +0: [2023-05-23 21:57:55,794] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_7m100m100m/global_step190/layer_07-model_00-model_states.pt. +0: [2023-05-23 21:57:55,794] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_7m100m100m/global_step190/layer_07-model_00-model_states.pt. +0: [2023-05-23 21:57:55,794] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_7m100m100m/global_step190/layer_07-model_00-model_states.pt. +0: [2023-05-23 21:57:55,794] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_7m100m100m/global_step190/layer_07-model_00-model_states.pt. +0: [2023-05-23 21:57:55,794] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_7m100m100m/global_step190/layer_07-model_00-model_states.pt. +0: [2023-05-23 21:57:55,794] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_7m100m100m/global_step190/layer_07-model_00-model_states.pt. +0: > overriding learning rate value to 0.0002 +0: [2023-05-23 21:57:55,795] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_7m100m100m/global_step190/layer_07-model_00-model_states.pt. +0: > overriding minimum learning rate value to 2e-05 +0: > overriding warmup iterations value to 0 +0: > overriding total number of iterations value to 1 +0: > overriding decay style value to cosine +0: [2023-05-23 21:57:55,805] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_7m100m100m/global_step190/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt... +0: [2023-05-23 21:57:55,805] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_7m100m100m/global_step190/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt... +1: [2023-05-23 21:57:55,805] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_7m100m100m/global_step190/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt... +0: [2023-05-23 21:57:55,806] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_7m100m100m/global_step190/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt... +0: [2023-05-23 21:57:55,806] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_7m100m100m/global_step190/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt... +1: [2023-05-23 21:57:55,806] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_7m100m100m/global_step190/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt... +1: [2023-05-23 21:57:55,806] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_7m100m100m/global_step190/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt... +1: [2023-05-23 21:57:55,806] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_7m100m100m/global_step190/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt... +1: [2023-05-23 21:57:55,806] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_7m100m100m/global_step190/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt... +1: [2023-05-23 21:57:55,806] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_7m100m100m/global_step190/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt... +0: [2023-05-23 21:57:55,807] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_7m100m100m/global_step190/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt... +0: [2023-05-23 21:57:55,818] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_7m100m100m/global_step190/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt. +0: [2023-05-23 21:57:55,819] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 16 ZeRO state_dicts for rank 0 +0: [2023-05-23 21:57:55,820] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 16 zero partition checkpoints for rank 0 +0: could not find arguments in the checkpoint ... +0: checkpoint version 3.0 +0: [2023-05-23 21:57:55,820] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_7m100m100m/global_step190/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt. +0: [2023-05-23 21:57:55,820] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_7m100m100m/global_step190/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt. +0: [2023-05-23 21:57:55,820] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 16 ZeRO state_dicts for rank 3 +0: [2023-05-23 21:57:55,820] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 16 ZeRO state_dicts for rank 4 +0: [2023-05-23 21:57:55,821] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_7m100m100m/global_step190/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt. +0: [2023-05-23 21:57:55,821] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 16 zero partition checkpoints for rank 3 +0: [2023-05-23 21:57:55,821] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 16 ZeRO state_dicts for rank 2 +0: [2023-05-23 21:57:55,821] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 16 zero partition checkpoints for rank 4 +0: [2023-05-23 21:57:55,821] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 16 zero partition checkpoints for rank 2 +1: [2023-05-23 21:57:55,821] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_7m100m100m/global_step190/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt. +1: [2023-05-23 21:57:55,822] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 16 ZeRO state_dicts for rank 12 +1: [2023-05-23 21:57:55,822] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_7m100m100m/global_step190/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt. +1: [2023-05-23 21:57:55,822] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 16 ZeRO state_dicts for rank 13 +1: [2023-05-23 21:57:55,822] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 16 zero partition checkpoints for rank 12 +1: [2023-05-23 21:57:55,823] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 16 zero partition checkpoints for rank 13 +1: [2023-05-23 21:57:55,824] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_7m100m100m/global_step190/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt. +1: [2023-05-23 21:57:55,824] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 16 ZeRO state_dicts for rank 14 +1: [2023-05-23 21:57:55,825] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_7m100m100m/global_step190/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt. +1: [2023-05-23 21:57:55,825] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 16 ZeRO state_dicts for rank 11 +1: [2023-05-23 21:57:55,825] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 16 zero partition checkpoints for rank 14 +1: [2023-05-23 21:57:55,825] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_7m100m100m/global_step190/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt. +1: [2023-05-23 21:57:55,825] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 16 ZeRO state_dicts for rank 10 +1: [2023-05-23 21:57:55,826] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 16 zero partition checkpoints for rank 11 +1: [2023-05-23 21:57:55,826] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 16 zero partition checkpoints for rank 10 +0: [2023-05-23 21:57:55,875] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_7m100m100m/global_step190/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt. +0: [2023-05-23 21:57:55,876] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 16 ZeRO state_dicts for rank 7 +0: [2023-05-23 21:57:55,876] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 16 zero partition checkpoints for rank 7 +1: [2023-05-23 21:57:55,995] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_7m100m100m/global_step190/layer_07-model_00-model_states.pt. +1: [2023-05-23 21:57:55,995] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_7m100m100m/global_step190/layer_07-model_00-model_states.pt... +1: [2023-05-23 21:57:55,995] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_7m100m100m/global_step190/layer_07-model_00-model_states.pt. +1: [2023-05-23 21:57:55,996] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_7m100m100m/global_step190/layer_07-model_00-model_states.pt... +1: [2023-05-23 21:57:55,996] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_7m100m100m/global_step190/layer_07-model_00-model_states.pt. +1: [2023-05-23 21:57:55,996] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_7m100m100m/global_step190/layer_07-model_00-model_states.pt. +1: [2023-05-23 21:57:55,998] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_7m100m100m/global_step190/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt... +0: [2023-05-23 21:57:56,004] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_7m100m100m/global_step190/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt... +0: [2023-05-23 21:57:56,005] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_7m100m100m/global_step190/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt... +0: [2023-05-23 21:57:56,012] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_7m100m100m/global_step190/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt... +0: [2023-05-23 21:57:56,017] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_7m100m100m/global_step190/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt. +0: [2023-05-23 21:57:56,018] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 16 ZeRO state_dicts for rank 6 +0: [2023-05-23 21:57:56,018] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 16 zero partition checkpoints for rank 6 +1: [2023-05-23 21:57:56,021] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_7m100m100m/global_step190/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt. +1: [2023-05-23 21:57:56,021] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 16 ZeRO state_dicts for rank 8 +1: [2023-05-23 21:57:56,022] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 16 zero partition checkpoints for rank 8 +0: [2023-05-23 21:57:56,026] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_7m100m100m/global_step190/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt. +0: [2023-05-23 21:57:56,026] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 16 ZeRO state_dicts for rank 1 +0: [2023-05-23 21:57:56,027] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 16 zero partition checkpoints for rank 1 +1: [2023-05-23 21:57:56,036] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_7m100m100m/global_step190/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt. +1: [2023-05-23 21:57:56,036] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 16 ZeRO state_dicts for rank 15 +1: [2023-05-23 21:57:56,037] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 16 zero partition checkpoints for rank 15 +1: [2023-05-23 21:57:56,209] [INFO] [torch_checkpoint_engine.py:21:load] [Torch] Loading checkpoint from checkpoints_7m100m100m/global_step190/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt... +0: [2023-05-23 21:57:56,224] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_7m100m100m/global_step190/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt. +0: [2023-05-23 21:57:56,225] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 16 ZeRO state_dicts for rank 5 +0: [2023-05-23 21:57:56,225] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 16 zero partition checkpoints for rank 5 +1: [2023-05-23 21:57:56,280] [INFO] [torch_checkpoint_engine.py:23:load] [Torch] Loaded checkpoint from checkpoints_7m100m100m/global_step190/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt. +1: [2023-05-23 21:57:56,280] [INFO] [engine.py:2844:_get_all_zero_checkpoint_state_dicts] successfully read 16 ZeRO state_dicts for rank 9 +1: [2023-05-23 21:57:56,281] [INFO] [engine.py:2784:_load_zero_checkpoint] loading 16 zero partition checkpoints for rank 9 +0: successfully loaded checkpoint from checkpoints_7m100m100m at iteration 0 +1: time (ms) | load-checkpoint: 1015.13 +0: estimated model parameters: 0.007296128 +0: estimated model parameters without embeddings: 0.000595072 +0: [after model, optimizer, and learning rate scheduler are built] datetime: 2023-05-23 21:57:58 +0: > building train, validation, and test datasets ... +0: > datasets target sizes (minimum size): +0: train: 1 +0: validation: 6400 +0: test: 6400 +0: > building train, validation, and test datasets for GPT ... +0: > building dataset index ... +0: reading sizes... +0: reading pointers... +0: reading document index... +0: creating numpy buffer of mmap... +0: creating memory view of numpy buffer... +0: > finished creating indexed dataset in 0.030603 seconds +0: number of documents: 208931 +0: > dataset split: +0: train: +0: document indices in [0, 208931) total of 208931 documents +0: > loading doc-idx mapping from /scratch/project_462000119/data/c4_subsampled/gpt2tok_c4_en_100M_text_document_train_indexmap_1ns_2048sl_1234s_doc_idx.npy +0: > loading sample-idx mapping from /scratch/project_462000119/data/c4_subsampled/gpt2tok_c4_en_100M_text_document_train_indexmap_1ns_2048sl_1234s_sample_idx.npy +0: > loading shuffle-idx mapping from /scratch/project_462000119/data/c4_subsampled/gpt2tok_c4_en_100M_text_document_train_indexmap_1ns_2048sl_1234s_shuffle_idx.npy +0: loaded indexed file in 0.309 seconds +0: total number of samples: 48805 +0: total number of epochs: 1 +0: > building dataset index ... +0: reading sizes... +0: reading pointers... +0: reading document index... +0: creating numpy buffer of mmap... +0: creating memory view of numpy buffer... +0: > finished creating indexed dataset in 0.104512 seconds +0: number of documents: 364608 +0: > dataset split: +0: validation: +0: document indices in [0, 364608) total of 364608 documents +0: > loading doc-idx mapping from /scratch/project_462000119/data/c4_validation/gpt2tok_c4validation_rerun_text_document_validation_indexmap_6400ns_2048sl_1234s_doc_idx.npy +0: > loading sample-idx mapping from /scratch/project_462000119/data/c4_validation/gpt2tok_c4validation_rerun_text_document_validation_indexmap_6400ns_2048sl_1234s_sample_idx.npy +0: > loading shuffle-idx mapping from /scratch/project_462000119/data/c4_validation/gpt2tok_c4validation_rerun_text_document_validation_indexmap_6400ns_2048sl_1234s_shuffle_idx.npy +0: loaded indexed file in 0.319 seconds +0: total number of samples: 84978 +0: total number of epochs: 1 +0: > finished creating GPT datasets ... +0: [after dataloaders are built] datetime: 2023-05-23 21:58:10 +0: done with setup ... +0: training ... +1: time (ms) | model-and-optimizer-setup: 14335.52 | train/valid/test-data-iterators-setup: 12024.81 +0: [after training is done] datetime: 2023-05-23 21:58:10 +1: ----------------------------------------------------------------------------------------------------------------- +1: validation loss at the end of training for val data | lm loss value: 8.102005E+00 | lm loss PPL: 3.301080E+03 | +1: ----------------------------------------------------------------------------------------------------------------- +END 3571584: Tue 23 May 2023 09:58:28 PM EEST diff --git a/7m100m100m/global_step190/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt b/7m100m100m/global_step190/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt index 2f5f0e351b4cccedf9d7114fcc08028730ac3337..3fd3fd0047d3f55f08ac42eeb89926ee13e70ef5 100644 --- a/7m100m100m/global_step190/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt +++ b/7m100m100m/global_step190/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:91e39ac7720cd88efa0f2792784d0995bd76bf801e9f5118f60ca32812df6a16 -size 5328663 +oid sha256:e3efcfe9e388751224449755f471b2255c265548303fec751cfe3267535b8b0e +size 5476759 diff --git a/7m100m100m/global_step190/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt b/7m100m100m/global_step190/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt index 17c00a1083f7a4860e053ef0e7303827fbfb1238..34a51fde6e73adab311e02d8623a2d8c56a9c256 100644 --- a/7m100m100m/global_step190/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt +++ b/7m100m100m/global_step190/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:50524214c32ac1591a7ca179ae352d2d24c1cbc25af9c438a1932355bac9dac8 -size 5328738 +oid sha256:2b640de6a45f9ca3568dbf617a4f26ee467bdeed93ba852c888277642ae54053 +size 5476770 diff --git a/7m100m100m/global_step190/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt b/7m100m100m/global_step190/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt index ecb0886d879390da4b964ed68300ca1be56f8a8e..dd16b63a3adf4453a21800cab584ed0568b996fe 100644 --- a/7m100m100m/global_step190/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt +++ b/7m100m100m/global_step190/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:bf4eff0fae01461ece233f6f5c827d7276de91a0e7c1742594ebef134752c5e0 -size 5328674 +oid sha256:24d9a18af9bd86570c5c77d8cd978a9403b55ac313f05d0fcd17a58d59892d52 +size 5476642 diff --git a/7m100m100m/global_step190/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt b/7m100m100m/global_step190/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt index 4a6b5adc1d5b0974dabe02d7a27086f4b671b77c..99d224986e8455eee930fdbe9d2c2ab16240f1e2 100644 --- a/7m100m100m/global_step190/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt +++ b/7m100m100m/global_step190/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:cb9e2a0f09e02c0b2bdee18476c2f6fbf29143a906d2eae4d11f5632ca613492 -size 5328674 +oid sha256:78bde61ab72af0d55db4d321cc13f747bab52867ab66ad10e45cdf26568fe524 +size 5476834 diff --git a/7m100m100m/global_step190/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt b/7m100m100m/global_step190/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt index ec860a3d6f5db0a37abb55c26691515ff98e03fb..ea9baf31bd20721b24dab1813d5faa2322a304ca 100644 --- a/7m100m100m/global_step190/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt +++ b/7m100m100m/global_step190/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:4d2024359a28d77bbb230eab81bbdebaa49a6d636e2b5fcb7ad390187b3a0323 -size 5328738 +oid sha256:7f51e57933a5c3f47f24721ffae8880f026c1b85725226ec4405abe635d7ae63 +size 5476642 diff --git a/7m100m100m/global_step190/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt b/7m100m100m/global_step190/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt index 9c54a259015d7e5586d3e88e4158422b20c9fe01..2e10efee4f4a75a508a64465e835757f4f83610b 100644 --- a/7m100m100m/global_step190/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt +++ b/7m100m100m/global_step190/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:d6ab9e28b46a1192a9329246816b6c8364a2f14f293ece347090682deb5443da -size 5328674 +oid sha256:241ccc89c43aa103a210853bef054bddccde98bb20bd8b4f94e841d3a3d13244 +size 5476706 diff --git a/7m100m100m/global_step190/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt b/7m100m100m/global_step190/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt index b4943fe7a0fc5b4f4c6870cc8a82b64e54026fbb..cb1b54831b28004614aafaf93fbc9b008fa9a220 100644 --- a/7m100m100m/global_step190/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt +++ b/7m100m100m/global_step190/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:750f2efa4fd61f98ba33966e7f8af78607c1dc1d3f8a822084ef365fe233e1cc -size 5328930 +oid sha256:6d9099035d73a614210536e3bc327000f79eca41479b3f13d450c3dcf438de2b +size 5477026 diff --git a/7m100m100m/global_step190/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt b/7m100m100m/global_step190/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt index 27122daab8d4825c5bcdfad630b194cfe823ff9e..2a49c4d7654eddccac5523462426b9445e4d2a8d 100644 --- a/7m100m100m/global_step190/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt +++ b/7m100m100m/global_step190/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:eb8be589a26588c6c0f4263986b837fc702f03677ef616f7b143e4aa7f618ed0 -size 5328663 +oid sha256:2a5a48d4f1f4ebe4953251c421c062b0594ed2620ad326e331b82a35dc3ea235 +size 5476631 diff --git a/7m100m100m/global_step190/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt b/7m100m100m/global_step190/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt index 73de7ac2670a200007e07ea72e3d69c783d6fe9a..0fa720263cc84dcddb5b6195e2d9aad344fd4d40 100644 --- a/7m100m100m/global_step190/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt +++ b/7m100m100m/global_step190/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:1063c6a152da13d10d1c80b807901eea5c8690a26a39c756300c587e9140ef2f -size 5328663 +oid sha256:c2a6c8636d4ba7736a88fe4bd34e1cf5741d1c140b2c0220daf70f3bf31f6add +size 5476695 diff --git a/7m100m100m/global_step190/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt b/7m100m100m/global_step190/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt index 76b02e45f5a94676dc3fadd343d32838debcb86d..94efad214a41e153d6dde8db7b1008131cdabd50 100644 --- a/7m100m100m/global_step190/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt +++ b/7m100m100m/global_step190/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:9c7f93a598f10961626a76180aaa0709b39e99c78ff1b760462c14bf16acbc9d -size 5328727 +oid sha256:3551d5bde164f7e3f413c3ff81463a7ca38eeeb196b92323b16794c64a2208a6 +size 5476695 diff --git a/7m100m100m/global_step190/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt b/7m100m100m/global_step190/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt index 909df08ffa19b97f90380410b3bc15bb48efb820..1c1c9dcf4ff4078fdd2f59c321bc9100bfbc3909 100644 --- a/7m100m100m/global_step190/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt +++ b/7m100m100m/global_step190/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:531a2f6237ab987fc4a2f1f80b17ed0007e471a90d07f94bedbad693df99b9ea -size 5328599 +oid sha256:90c8c017e092d1484ce9adedefb8900872e1a4e7eae08d1e6547a6fa3302ed35 +size 5476631 diff --git a/7m100m100m/global_step190/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt b/7m100m100m/global_step190/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt index a93cbf71483ac5becb9d1db4c11edbac17a1d55f..7f1265b438cb4c6c0b52f9c327e1e287be46e96d 100644 --- a/7m100m100m/global_step190/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt +++ b/7m100m100m/global_step190/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:a8aac831f3f14d90d2cb5a292460d3d604063d1e91f925dae4613988c06e9336 -size 5328727 +oid sha256:a1e46a5f7fa922500fa54dfc72773f8b8ff342745efc5fa241edfdd006ef5371 +size 5476759 diff --git a/7m100m100m/global_step190/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt b/7m100m100m/global_step190/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt index a98ce9cd5b2466687e783baa73de179f93c7b252..a0f95d1b8ebe0234f88c64b80f2aa164f54eec99 100644 --- a/7m100m100m/global_step190/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt +++ b/7m100m100m/global_step190/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:09be9059c96563f1820729b24a4d4a7d1efba89f95ecdf534895f1efb6ba941b -size 5328663 +oid sha256:8a632293061cb20dbe9ca0789b19d5e57bf569d22dd041a8a3e5bcd08b14c13a +size 5476695 diff --git a/7m100m100m/global_step190/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt b/7m100m100m/global_step190/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt index 667465472d2b6de734ab31f68d9eb3e0acfe913c..9183cdf383005a5da1cfa14317794cc0b62b8f53 100644 --- a/7m100m100m/global_step190/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt +++ b/7m100m100m/global_step190/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:ce505b1046906abd28d585d2a4eeaa49afff654c2598a88f4f03fc553cca9e4a -size 5328727 +oid sha256:b5775ea9bb91e65d41513d09289c43be532d98450648fc20c33df7f12ff17bbf +size 5476823 diff --git a/7m100m100m/global_step190/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt b/7m100m100m/global_step190/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt index fe88f0be68ba7014a56a536eba05392147ee385b..9bbd06f0640253ddb11b6995a4b4b49aa4e6dba2 100644 --- a/7m100m100m/global_step190/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt +++ b/7m100m100m/global_step190/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:13a62508ac67ee77f5f540f0ed683de121dee608599c6ad120885a8a4ee5fa60 -size 5328663 +oid sha256:dfbdace11910c98a4d2b979755bbd43f4619329c1abb14336cee19304b25dcd7 +size 5476695 diff --git a/7m100m100m/global_step190/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt b/7m100m100m/global_step190/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt index 9727c24420977141cb72eb92bf363f6cc8c13fd7..a20581297587542b5e192070c5608e4e1f7fd08b 100644 --- a/7m100m100m/global_step190/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt +++ b/7m100m100m/global_step190/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:a7a781edd720d3c8509dd73d88f9b337f1bcea9c4b376df11254cc9650225a57 -size 5328663 +oid sha256:021f23c70b67ae22e34c690118617cbea49ab766414087efdb74ddd7efc9b023 +size 5476759 diff --git a/7m100m100m/global_step190/layer_01-model_00-model_states.pt b/7m100m100m/global_step190/layer_01-model_00-model_states.pt index 41615f38d5c4266431bc191f39c97b12c2b8da4a..f3cb4b8569b4ff81b02d924c3cbe820b7dafded3 100644 --- a/7m100m100m/global_step190/layer_01-model_00-model_states.pt +++ b/7m100m100m/global_step190/layer_01-model_00-model_states.pt @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:3dd9fd24e83426db607da9de56ffbec877aa9beb4280371e02dc307ba51c2894 +oid sha256:f2e9cfefae28dd2b607e34beed236d351988561d1af382afed6acc329783a2eb size 13403395 diff --git a/7m100m100m/global_step190/layer_03-model_00-model_states.pt b/7m100m100m/global_step190/layer_03-model_00-model_states.pt index 28409c4c3a311dd5857e1153a21c7eb1fc7cfca0..6e52a49a48f253e46ab7b44dcb464f5b4afda517 100644 --- a/7m100m100m/global_step190/layer_03-model_00-model_states.pt +++ b/7m100m100m/global_step190/layer_03-model_00-model_states.pt @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:9f360d0adbad0e5638df2813825909d6984834cebe9df58fb8392b54cf94aba7 -size 269251 +oid sha256:47b29407562e042b54c0158df50ab99fcb1168293ea2ec46b59e5efe8fcc413e +size 400899 diff --git a/7m100m100m/global_step190/layer_04-model_00-model_states.pt b/7m100m100m/global_step190/layer_04-model_00-model_states.pt index 97cc183afaa34769535a1680ee3c7d99d873b4be..d914aae08aa2a9591db3c00be50ae108ac3a5df0 100644 --- a/7m100m100m/global_step190/layer_04-model_00-model_states.pt +++ b/7m100m100m/global_step190/layer_04-model_00-model_states.pt @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:9e1d89c75ba47e3b24518e467dfd201455e5209ee6e7642b6c91d212f443f3e8 -size 269251 +oid sha256:77694928eaf5003ff45cfc72af5280e356b4f6f4d609b07bdd369eedc18a16e2 +size 400899 diff --git a/7m100m100m/global_step190/layer_05-model_00-model_states.pt b/7m100m100m/global_step190/layer_05-model_00-model_states.pt index 5b00675f5399fbd885fa105f2d7059eb25a78a37..2e38d20b358241996570514cbfd261891da458e2 100644 --- a/7m100m100m/global_step190/layer_05-model_00-model_states.pt +++ b/7m100m100m/global_step190/layer_05-model_00-model_states.pt @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:e42c451c9a9ca671b3032df95728c86de351808a4133292212189a5dba87089c -size 269251 +oid sha256:74a8e96211a7813404f8fd683d3b7092c35ec7d327504e4af20512173346de9b +size 400899 diff --git a/7m100m100m/global_step190/layer_07-model_00-model_states.pt b/7m100m100m/global_step190/layer_07-model_00-model_states.pt index 4026d1fdf023ac33223bd4ce9959289e4cd58d51..5336d0c2fb2f34f104aec1c4e9342a8ad6178ac2 100644 --- a/7m100m100m/global_step190/layer_07-model_00-model_states.pt +++ b/7m100m100m/global_step190/layer_07-model_00-model_states.pt @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:aa7ca97d524a068d70c503b217faea25271ed1bfa94e8e2fd94c7e27050c9016 +oid sha256:9f87d6166302c37c4cdd4ab69f3ef99cbfbe659661d27d4e76c7cac90adfc77e size 1731 diff --git a/7m100m100m/global_step190/mp_rank_00_model_states.pt b/7m100m100m/global_step190/mp_rank_00_model_states.pt index f6ffe4015c3d00ed8fb14878ea8e0bc1ed1e5a55..29c5a8d788af9a2bc03b407eca4deef95700b3b3 100644 --- a/7m100m100m/global_step190/mp_rank_00_model_states.pt +++ b/7m100m100m/global_step190/mp_rank_00_model_states.pt @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:337ac14e9140d70e974d88f9f29417e17d68da0290367b6dabda485b89aa63cb +oid sha256:6233cb22aeb9c32f37f55ca14c0927b651e0fd332e55e3da7a073b6f2a528182 size 26291 diff --git a/7m100m100m/eval.txt b/7m100m100m/old/eval.txt similarity index 100% rename from 7m100m100m/eval.txt rename to 7m100m100m/old/eval.txt diff --git a/7m100m100m/old/global_step190/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt b/7m100m100m/old/global_step190/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..2f5f0e351b4cccedf9d7114fcc08028730ac3337 --- /dev/null +++ b/7m100m100m/old/global_step190/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:91e39ac7720cd88efa0f2792784d0995bd76bf801e9f5118f60ca32812df6a16 +size 5328663 diff --git a/7m100m100m/old/global_step190/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt b/7m100m100m/old/global_step190/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..17c00a1083f7a4860e053ef0e7303827fbfb1238 --- /dev/null +++ b/7m100m100m/old/global_step190/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:50524214c32ac1591a7ca179ae352d2d24c1cbc25af9c438a1932355bac9dac8 +size 5328738 diff --git a/7m100m100m/old/global_step190/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt b/7m100m100m/old/global_step190/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..ecb0886d879390da4b964ed68300ca1be56f8a8e --- /dev/null +++ b/7m100m100m/old/global_step190/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bf4eff0fae01461ece233f6f5c827d7276de91a0e7c1742594ebef134752c5e0 +size 5328674 diff --git a/7m100m100m/old/global_step190/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt b/7m100m100m/old/global_step190/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..4a6b5adc1d5b0974dabe02d7a27086f4b671b77c --- /dev/null +++ b/7m100m100m/old/global_step190/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cb9e2a0f09e02c0b2bdee18476c2f6fbf29143a906d2eae4d11f5632ca613492 +size 5328674 diff --git a/7m100m100m/old/global_step190/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt b/7m100m100m/old/global_step190/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..ec860a3d6f5db0a37abb55c26691515ff98e03fb --- /dev/null +++ b/7m100m100m/old/global_step190/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4d2024359a28d77bbb230eab81bbdebaa49a6d636e2b5fcb7ad390187b3a0323 +size 5328738 diff --git a/7m100m100m/old/global_step190/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt b/7m100m100m/old/global_step190/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..9c54a259015d7e5586d3e88e4158422b20c9fe01 --- /dev/null +++ b/7m100m100m/old/global_step190/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d6ab9e28b46a1192a9329246816b6c8364a2f14f293ece347090682deb5443da +size 5328674 diff --git a/7m100m100m/old/global_step190/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt b/7m100m100m/old/global_step190/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..b4943fe7a0fc5b4f4c6870cc8a82b64e54026fbb --- /dev/null +++ b/7m100m100m/old/global_step190/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:750f2efa4fd61f98ba33966e7f8af78607c1dc1d3f8a822084ef365fe233e1cc +size 5328930 diff --git a/7m100m100m/old/global_step190/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt b/7m100m100m/old/global_step190/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..27122daab8d4825c5bcdfad630b194cfe823ff9e --- /dev/null +++ b/7m100m100m/old/global_step190/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eb8be589a26588c6c0f4263986b837fc702f03677ef616f7b143e4aa7f618ed0 +size 5328663 diff --git a/7m100m100m/old/global_step190/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt b/7m100m100m/old/global_step190/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..73de7ac2670a200007e07ea72e3d69c783d6fe9a --- /dev/null +++ b/7m100m100m/old/global_step190/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1063c6a152da13d10d1c80b807901eea5c8690a26a39c756300c587e9140ef2f +size 5328663 diff --git a/7m100m100m/old/global_step190/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt b/7m100m100m/old/global_step190/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..76b02e45f5a94676dc3fadd343d32838debcb86d --- /dev/null +++ b/7m100m100m/old/global_step190/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9c7f93a598f10961626a76180aaa0709b39e99c78ff1b760462c14bf16acbc9d +size 5328727 diff --git a/7m100m100m/old/global_step190/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt b/7m100m100m/old/global_step190/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..909df08ffa19b97f90380410b3bc15bb48efb820 --- /dev/null +++ b/7m100m100m/old/global_step190/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:531a2f6237ab987fc4a2f1f80b17ed0007e471a90d07f94bedbad693df99b9ea +size 5328599 diff --git a/7m100m100m/old/global_step190/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt b/7m100m100m/old/global_step190/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..a93cbf71483ac5becb9d1db4c11edbac17a1d55f --- /dev/null +++ b/7m100m100m/old/global_step190/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a8aac831f3f14d90d2cb5a292460d3d604063d1e91f925dae4613988c06e9336 +size 5328727 diff --git a/7m100m100m/old/global_step190/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt b/7m100m100m/old/global_step190/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..a98ce9cd5b2466687e783baa73de179f93c7b252 --- /dev/null +++ b/7m100m100m/old/global_step190/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:09be9059c96563f1820729b24a4d4a7d1efba89f95ecdf534895f1efb6ba941b +size 5328663 diff --git a/7m100m100m/old/global_step190/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt b/7m100m100m/old/global_step190/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..667465472d2b6de734ab31f68d9eb3e0acfe913c --- /dev/null +++ b/7m100m100m/old/global_step190/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ce505b1046906abd28d585d2a4eeaa49afff654c2598a88f4f03fc553cca9e4a +size 5328727 diff --git a/7m100m100m/old/global_step190/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt b/7m100m100m/old/global_step190/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..fe88f0be68ba7014a56a536eba05392147ee385b --- /dev/null +++ b/7m100m100m/old/global_step190/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:13a62508ac67ee77f5f540f0ed683de121dee608599c6ad120885a8a4ee5fa60 +size 5328663 diff --git a/7m100m100m/old/global_step190/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt b/7m100m100m/old/global_step190/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..9727c24420977141cb72eb92bf363f6cc8c13fd7 --- /dev/null +++ b/7m100m100m/old/global_step190/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a7a781edd720d3c8509dd73d88f9b337f1bcea9c4b376df11254cc9650225a57 +size 5328663 diff --git a/7m100m100m/old/global_step190/layer_01-model_00-model_states.pt b/7m100m100m/old/global_step190/layer_01-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..41615f38d5c4266431bc191f39c97b12c2b8da4a --- /dev/null +++ b/7m100m100m/old/global_step190/layer_01-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3dd9fd24e83426db607da9de56ffbec877aa9beb4280371e02dc307ba51c2894 +size 13403395 diff --git a/7m100m100m/old/global_step190/layer_03-model_00-model_states.pt b/7m100m100m/old/global_step190/layer_03-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..28409c4c3a311dd5857e1153a21c7eb1fc7cfca0 --- /dev/null +++ b/7m100m100m/old/global_step190/layer_03-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9f360d0adbad0e5638df2813825909d6984834cebe9df58fb8392b54cf94aba7 +size 269251 diff --git a/7m100m100m/old/global_step190/layer_04-model_00-model_states.pt b/7m100m100m/old/global_step190/layer_04-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..97cc183afaa34769535a1680ee3c7d99d873b4be --- /dev/null +++ b/7m100m100m/old/global_step190/layer_04-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9e1d89c75ba47e3b24518e467dfd201455e5209ee6e7642b6c91d212f443f3e8 +size 269251 diff --git a/7m100m100m/old/global_step190/layer_05-model_00-model_states.pt b/7m100m100m/old/global_step190/layer_05-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..5b00675f5399fbd885fa105f2d7059eb25a78a37 --- /dev/null +++ b/7m100m100m/old/global_step190/layer_05-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e42c451c9a9ca671b3032df95728c86de351808a4133292212189a5dba87089c +size 269251 diff --git a/7m100m100m/old/global_step190/layer_07-model_00-model_states.pt b/7m100m100m/old/global_step190/layer_07-model_00-model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..4026d1fdf023ac33223bd4ce9959289e4cd58d51 --- /dev/null +++ b/7m100m100m/old/global_step190/layer_07-model_00-model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aa7ca97d524a068d70c503b217faea25271ed1bfa94e8e2fd94c7e27050c9016 +size 1731 diff --git a/7m100m100m/old/global_step190/mp_rank_00_model_states.pt b/7m100m100m/old/global_step190/mp_rank_00_model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..f6ffe4015c3d00ed8fb14878ea8e0bc1ed1e5a55 --- /dev/null +++ b/7m100m100m/old/global_step190/mp_rank_00_model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:337ac14e9140d70e974d88f9f29417e17d68da0290367b6dabda485b89aa63cb +size 26291 diff --git a/7m100m100m/logs/3163410.err b/7m100m100m/old/logs/3163410.err similarity index 100% rename from 7m100m100m/logs/3163410.err rename to 7m100m100m/old/logs/3163410.err diff --git a/7m100m100m/logs/3163410.out b/7m100m100m/old/logs/3163410.out similarity index 100% rename from 7m100m100m/logs/3163410.out rename to 7m100m100m/old/logs/3163410.out diff --git a/7m100m100m/tensorboard_7m100m100m/events.out.tfevents.1677508396.nid006608.48416.0 b/7m100m100m/old/tensorboard_7m100m100m/events.out.tfevents.1677508396.nid006608.48416.0 similarity index 100% rename from 7m100m100m/tensorboard_7m100m100m/events.out.tfevents.1677508396.nid006608.48416.0 rename to 7m100m100m/old/tensorboard_7m100m100m/events.out.tfevents.1677508396.nid006608.48416.0 diff --git a/7m100m100m/tensorboard_7m100m100mval/events.out.tfevents.1677509121.nid007242.99140.0 b/7m100m100m/old/tensorboard_7m100m100mval/events.out.tfevents.1677509121.nid007242.99140.0 similarity index 100% rename from 7m100m100m/tensorboard_7m100m100mval/events.out.tfevents.1677509121.nid007242.99140.0 rename to 7m100m100m/old/tensorboard_7m100m100mval/events.out.tfevents.1677509121.nid007242.99140.0