Commit
·
532d238
1
Parent(s):
b7ea97e
Add
Browse filesThis view is limited to 50 files because it contains too many changes.
See raw diff
- 196m1b51b5/logs/3163481.err +296 -0
- 196m1b51b5/logs/3163481.out +0 -0
- 220m7b5100m/220m7b5100m/global_step14324/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt +3 -0
- 220m7b5100m/220m7b5100m/global_step14324/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt +3 -0
- 220m7b5100m/220m7b5100m/global_step14324/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt +3 -0
- 220m7b5100m/220m7b5100m/global_step14324/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt +3 -0
- 220m7b5100m/220m7b5100m/global_step14324/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt +3 -0
- 220m7b5100m/220m7b5100m/global_step14324/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt +3 -0
- 220m7b5100m/220m7b5100m/global_step14324/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt +3 -0
- 220m7b5100m/220m7b5100m/global_step14324/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt +3 -0
- 220m7b5100m/220m7b5100m/global_step14324/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt +3 -0
- 220m7b5100m/220m7b5100m/global_step14324/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt +3 -0
- 220m7b5100m/220m7b5100m/global_step14324/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt +3 -0
- 220m7b5100m/220m7b5100m/global_step14324/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt +3 -0
- 220m7b5100m/220m7b5100m/global_step14324/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt +3 -0
- 220m7b5100m/220m7b5100m/global_step14324/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt +3 -0
- 220m7b5100m/220m7b5100m/global_step14324/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt +3 -0
- 220m7b5100m/220m7b5100m/global_step14324/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt +3 -0
- 220m7b5100m/220m7b5100m/global_step14324/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt +3 -0
- 220m7b5100m/220m7b5100m/global_step14324/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt +3 -0
- 220m7b5100m/220m7b5100m/global_step14324/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt +3 -0
- 220m7b5100m/220m7b5100m/global_step14324/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt +3 -0
- 220m7b5100m/220m7b5100m/global_step14324/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt +3 -0
- 220m7b5100m/220m7b5100m/global_step14324/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt +3 -0
- 220m7b5100m/220m7b5100m/global_step14324/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt +3 -0
- 220m7b5100m/220m7b5100m/global_step14324/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt +3 -0
- 220m7b5100m/220m7b5100m/global_step14324/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt +3 -0
- 220m7b5100m/220m7b5100m/global_step14324/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt +3 -0
- 220m7b5100m/220m7b5100m/global_step14324/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt +3 -0
- 220m7b5100m/220m7b5100m/global_step14324/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt +3 -0
- 220m7b5100m/220m7b5100m/global_step14324/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt +3 -0
- 220m7b5100m/220m7b5100m/global_step14324/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt +3 -0
- 220m7b5100m/220m7b5100m/global_step14324/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt +3 -0
- 220m7b5100m/220m7b5100m/global_step14324/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt +3 -0
- 220m7b5100m/220m7b5100m/global_step14324/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt +3 -0
- 220m7b5100m/220m7b5100m/global_step14324/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt +3 -0
- 220m7b5100m/220m7b5100m/global_step14324/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt +3 -0
- 220m7b5100m/220m7b5100m/global_step14324/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt +3 -0
- 220m7b5100m/220m7b5100m/global_step14324/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt +3 -0
- 220m7b5100m/220m7b5100m/global_step14324/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt +3 -0
- 220m7b5100m/220m7b5100m/global_step14324/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt +3 -0
- 220m7b5100m/220m7b5100m/global_step14324/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt +3 -0
- 220m7b5100m/220m7b5100m/global_step14324/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt +3 -0
- 220m7b5100m/220m7b5100m/global_step14324/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt +3 -0
- 220m7b5100m/220m7b5100m/global_step14324/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt +3 -0
- 220m7b5100m/220m7b5100m/global_step14324/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt +3 -0
- 220m7b5100m/220m7b5100m/global_step14324/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt +3 -0
- 220m7b5100m/220m7b5100m/global_step14324/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt +3 -0
- 220m7b5100m/220m7b5100m/global_step14324/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt +3 -0
- 220m7b5100m/220m7b5100m/global_step14324/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt +3 -0
196m1b51b5/logs/3163481.err
ADDED
|
@@ -0,0 +1,296 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
0: 2023-02-27 16:54:28.024677: 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
|
| 2 |
+
0: To enable them in other operations, rebuild TensorFlow with the appropriate compiler flags.
|
| 3 |
+
0: 2023-02-27 16:54:28.024684: 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
|
| 4 |
+
0: To enable them in other operations, rebuild TensorFlow with the appropriate compiler flags.
|
| 5 |
+
0: 2023-02-27 16:54:28.024694: 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
|
| 6 |
+
0: To enable them in other operations, rebuild TensorFlow with the appropriate compiler flags.
|
| 7 |
+
0: 2023-02-27 16:54:28.024694: 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
|
| 8 |
+
0: To enable them in other operations, rebuild TensorFlow with the appropriate compiler flags.
|
| 9 |
+
0: 2023-02-27 16:54:28.024697: 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
|
| 10 |
+
0: To enable them in other operations, rebuild TensorFlow with the appropriate compiler flags.
|
| 11 |
+
0: 2023-02-27 16:54:28.024702: 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
|
| 12 |
+
0: To enable them in other operations, rebuild TensorFlow with the appropriate compiler flags.
|
| 13 |
+
0: 2023-02-27 16:54:28.024682: 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
|
| 14 |
+
0: To enable them in other operations, rebuild TensorFlow with the appropriate compiler flags.
|
| 15 |
+
0: 2023-02-27 16:54:28.024717: 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
|
| 16 |
+
0: To enable them in other operations, rebuild TensorFlow with the appropriate compiler flags.
|
| 17 |
+
1: 2023-02-27 16:54:28.025002: 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
|
| 18 |
+
1: To enable them in other operations, rebuild TensorFlow with the appropriate compiler flags.
|
| 19 |
+
1: 2023-02-27 16:54:28.025010: 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
|
| 20 |
+
1: To enable them in other operations, rebuild TensorFlow with the appropriate compiler flags.
|
| 21 |
+
1: 2023-02-27 16:54:28.025005: 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
|
| 22 |
+
1: To enable them in other operations, rebuild TensorFlow with the appropriate compiler flags.
|
| 23 |
+
1: 2023-02-27 16:54:28.024998: 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
|
| 24 |
+
1: To enable them in other operations, rebuild TensorFlow with the appropriate compiler flags.
|
| 25 |
+
1: 2023-02-27 16:54:28.025013: 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
|
| 26 |
+
1: To enable them in other operations, rebuild TensorFlow with the appropriate compiler flags.
|
| 27 |
+
1: 2023-02-27 16:54:28.025017: 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
|
| 28 |
+
1: To enable them in other operations, rebuild TensorFlow with the appropriate compiler flags.
|
| 29 |
+
1: 2023-02-27 16:54:28.025016: 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
|
| 30 |
+
1: To enable them in other operations, rebuild TensorFlow with the appropriate compiler flags.
|
| 31 |
+
1: 2023-02-27 16:54:28.025018: 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
|
| 32 |
+
1: To enable them in other operations, rebuild TensorFlow with the appropriate compiler flags.
|
| 33 |
+
0: 2023-02-27 16:54:30.148119: 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/aws-ofi-rccl:/pfs/lustrep2/projappl/project_462000125/samantao-public/apps/rccl/rccl-develop-release/rccl/lib:/pfs/lustrep4/projappl/project_462000075/samantao-public/rocm/glibc/selected:/pfs/lustrep2/projappl/project_462000125/samantao-public/rocm/rocm-5.2.3/hip/lib:/pfs/lustrep2/projappl/project_462000125/samantao-public/rocm/rocm-5.2.3/hsa/lib:/pfs/lustrep2/projappl/project_462000125/samantao-public/rocm/rocm-5.2.3/llvm/lib:/pfs/lustrep2/projappl/project_462000125/samantao-public/rocm/rocm-5.2.3/lib:/pfs/lustrep2/projappl/project_462000125/samantao-public/rocm/rocm-5.2.3/lib64:/pfs/lustrep2/projappl/project_462000125/samantao-public/rocm/rocm-5.2.3/llvm:/pfs/lustrep2/projappl/project_46200
|
| 34 |
+
0: 0125/samantao-public/apps/suse-repo-deps/lib64:/pfs/lustrep2/projappl/project_462000125/samantao-public/apps/suse-repo-deps/usr/lib64:/opt/cray/pe/python/3.9.12.1/lib:/opt/cray/pe/gcc-libs:/opt/cray/libfabric/1.15.0.0/lib64
|
| 35 |
+
0: 2023-02-27 16:54:30.148119: 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/aws-ofi-rccl:/pfs/lustrep2/projappl/project_462000125/samantao-public/apps/rccl/rccl-develop-release/rccl/lib:/pfs/lustrep4/projappl/project_462000075/samantao-public/rocm/glibc/selected:/pfs/lustrep2/projappl/project_462000125/samantao-public/rocm/rocm-5.2.3/hip/lib:/pfs/lustrep2/projappl/project_462000125/samantao-public/rocm/rocm-5.2.3/hsa/lib:/pfs/lustrep2/projappl/project_462000125/samantao-public/rocm/rocm-5.2.3/llvm/lib:/pfs/lustrep2/projappl/project_462000125/samantao-public/rocm/rocm-5.2.3/lib:/pfs/lustrep2/projappl/project_462000125/samantao-public/rocm/rocm-5.2.3/lib64:/pfs/lustrep2/projappl/project_462000125/samantao-public/rocm/rocm-5.2.3/llvm:/pfs/lustrep2/projappl/project_46200
|
| 36 |
+
0: 0125/samantao-public/apps/suse-repo-deps/lib64:/pfs/lustrep2/projappl/project_462000125/samantao-public/apps/suse-repo-deps/usr/lib64:/opt/cray/pe/python/3.9.12.1/lib:/opt/cray/pe/gcc-libs:/opt/cray/libfabric/1.15.0.0/lib64
|
| 37 |
+
0: 2023-02-27 16:54:30.148126: 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/aws-ofi-rccl:/pfs/lustrep2/projappl/project_462000125/samantao-public/apps/rccl/rccl-develop-release/rccl/lib:/pfs/lustrep4/projappl/project_462000075/samantao-public/rocm/glibc/selected:/pfs/lustrep2/projappl/project_462000125/samantao-public/rocm/rocm-5.2.3/hip/lib:/pfs/lustrep2/projappl/project_462000125/samantao-public/rocm/rocm-5.2.3/hsa/lib:/pfs/lustrep2/projappl/project_462000125/samantao-public/rocm/rocm-5.2.3/llvm/lib:/pfs/lustrep2/projappl/project_462000125/samantao-public/rocm/rocm-5.2.3/lib:/pfs/lustrep2/projappl/project_462000125/samantao-public/rocm/rocm-5.2.3/lib64:/pfs/lustrep2/projappl/project_462000125/samantao-public/rocm/rocm-5.2.3/llvm:/pfs/lustrep2/projappl/project_46200
|
| 38 |
+
0: 0125/samantao-public/apps/suse-repo-deps/lib64:/pfs/lustrep2/projappl/project_462000125/samantao-public/apps/suse-repo-deps/usr/lib64:/opt/cray/pe/python/3.9.12.1/lib:/opt/cray/pe/gcc-libs:/opt/cray/libfabric/1.15.0.0/lib64
|
| 39 |
+
0: 2023-02-27 16:54:30.148125: 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/aws-ofi-rccl:/pfs/lustrep2/projappl/project_462000125/samantao-public/apps/rccl/rccl-develop-release/rccl/lib:/pfs/lustrep4/projappl/project_462000075/samantao-public/rocm/glibc/selected:/pfs/lustrep2/projappl/project_462000125/samantao-public/rocm/rocm-5.2.3/hip/lib:/pfs/lustrep2/projappl/project_462000125/samantao-public/rocm/rocm-5.2.3/hsa/lib:/pfs/lustrep2/projappl/project_462000125/samantao-public/rocm/rocm-5.2.3/llvm/lib:/pfs/lustrep2/projappl/project_462000125/samantao-public/rocm/rocm-5.2.3/lib:/pfs/lustrep2/projappl/project_462000125/samantao-public/rocm/rocm-5.2.3/lib64:/pfs/lustrep2/projappl/project_462000125/samantao-public/rocm/rocm-5.2.3/llvm:/pfs/lustrep2/projappl/project_46200
|
| 40 |
+
0: 0125/samantao-public/apps/suse-repo-deps/lib64:/pfs/lustrep2/projappl/project_462000125/samantao-public/apps/suse-repo-deps/usr/lib64:/opt/cray/pe/python/3.9.12.1/lib:/opt/cray/pe/gcc-libs:/opt/cray/libfabric/1.15.0.0/lib64
|
| 41 |
+
0: 2023-02-27 16:54:30.148129: 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/aws-ofi-rccl:/pfs/lustrep2/projappl/project_462000125/samantao-public/apps/rccl/rccl-develop-release/rccl/lib:/pfs/lustrep4/projappl/project_462000075/samantao-public/rocm/glibc/selected:/pfs/lustrep2/projappl/project_462000125/samantao-public/rocm/rocm-5.2.3/hip/lib:/pfs/lustrep2/projappl/project_462000125/samantao-public/rocm/rocm-5.2.3/hsa/lib:/pfs/lustrep2/projappl/project_462000125/samantao-public/rocm/rocm-5.2.3/llvm/lib:/pfs/lustrep2/projappl/project_462000125/samantao-public/rocm/rocm-5.2.3/lib:/pfs/lustrep2/projappl/project_462000125/samantao-public/rocm/rocm-5.2.3/lib64:/pfs/lustrep2/projappl/project_462000125/samantao-public/rocm/rocm-5.2.3/llvm:/pfs/lustrep2/projappl/project_46200
|
| 42 |
+
0: 0125/samantao-public/apps/suse-repo-deps/lib64:/pfs/lustrep2/projappl/project_462000125/samantao-public/apps/suse-repo-deps/usr/lib64:/opt/cray/pe/python/3.9.12.1/lib:/opt/cray/pe/gcc-libs:/opt/cray/libfabric/1.15.0.0/lib64
|
| 43 |
+
0: 2023-02-27 16:54:30.148127: 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/aws-ofi-rccl:/pfs/lustrep2/projappl/project_462000125/samantao-public/apps/rccl/rccl-develop-release/rccl/lib:/pfs/lustrep4/projappl/project_462000075/samantao-public/rocm/glibc/selected:/pfs/lustrep2/projappl/project_462000125/samantao-public/rocm/rocm-5.2.3/hip/lib:/pfs/lustrep2/projappl/project_462000125/samantao-public/rocm/rocm-5.2.3/hsa/lib:/pfs/lustrep2/projappl/project_462000125/samantao-public/rocm/rocm-5.2.3/llvm/lib:/pfs/lustrep2/projappl/project_462000125/samantao-public/rocm/rocm-5.2.3/lib:/pfs/lustrep2/projappl/project_462000125/samantao-public/rocm/rocm-5.2.3/lib64:/pfs/lustrep2/projappl/project_462000125/samantao-public/rocm/rocm-5.2.3/llvm:/pfs/lustrep2/projappl/project_46200
|
| 44 |
+
0: 0125/samantao-public/apps/suse-repo-deps/lib64:/pfs/lustrep2/projappl/project_462000125/samantao-public/apps/suse-repo-deps/usr/lib64:/opt/cray/pe/python/3.9.12.1/lib:/opt/cray/pe/gcc-libs:/opt/cray/libfabric/1.15.0.0/lib64
|
| 45 |
+
0: 2023-02-27 16:54:30.148133: 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/aws-ofi-rccl:/pfs/lustrep2/projappl/project_462000125/samantao-public/apps/rccl/rccl-develop-release/rccl/lib:/pfs/lustrep4/projappl/project_462000075/samantao-public/rocm/glibc/selected:/pfs/lustrep2/projappl/project_462000125/samantao-public/rocm/rocm-5.2.3/hip/lib:/pfs/lustrep2/projappl/project_462000125/samantao-public/rocm/rocm-5.2.3/hsa/lib:/pfs/lustrep2/projappl/project_462000125/samantao-public/rocm/rocm-5.2.3/llvm/lib:/pfs/lustrep2/projappl/project_462000125/samantao-public/rocm/rocm-5.2.3/lib:/pfs/lustrep2/projappl/project_462000125/samantao-public/rocm/rocm-5.2.3/lib64:/pfs/lustrep2/projappl/project_462000125/samantao-public/rocm/rocm-5.2.3/llvm:/pfs/lustrep2/projappl/project_46200
|
| 46 |
+
0: 0125/samantao-public/apps/suse-repo-deps/lib64:/pfs/lustrep2/projappl/project_462000125/samantao-public/apps/suse-repo-deps/usr/lib64:/opt/cray/pe/python/3.9.12.1/lib:/opt/cray/pe/gcc-libs:/opt/cray/libfabric/1.15.0.0/lib64
|
| 47 |
+
0: 2023-02-27 16:54:30.148132: 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/aws-ofi-rccl:/pfs/lustrep2/projappl/project_462000125/samantao-public/apps/rccl/rccl-develop-release/rccl/lib:/pfs/lustrep4/projappl/project_462000075/samantao-public/rocm/glibc/selected:/pfs/lustrep2/projappl/project_462000125/samantao-public/rocm/rocm-5.2.3/hip/lib:/pfs/lustrep2/projappl/project_462000125/samantao-public/rocm/rocm-5.2.3/hsa/lib:/pfs/lustrep2/projappl/project_462000125/samantao-public/rocm/rocm-5.2.3/llvm/lib:/pfs/lustrep2/projappl/project_462000125/samantao-public/rocm/rocm-5.2.3/lib:/pfs/lustrep2/projappl/project_462000125/samantao-public/rocm/rocm-5.2.3/lib64:/pfs/lustrep2/projappl/project_462000125/samantao-public/rocm/rocm-5.2.3/llvm:/pfs/lustrep2/projappl/project_46200
|
| 48 |
+
0: 0125/samantao-public/apps/suse-repo-deps/lib64:/pfs/lustrep2/projappl/project_462000125/samantao-public/apps/suse-repo-deps/usr/lib64:/opt/cray/pe/python/3.9.12.1/lib:/opt/cray/pe/gcc-libs:/opt/cray/libfabric/1.15.0.0/lib64
|
| 49 |
+
0: 2023-02-27 16:54:30.148550: 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.
|
| 50 |
+
0: 2023-02-27 16:54:30.148553: 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.
|
| 51 |
+
0: 2023-02-27 16:54:30.148558: 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.
|
| 52 |
+
0: 2023-02-27 16:54:30.148560: 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.
|
| 53 |
+
0: 2023-02-27 16:54:30.148563: 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.
|
| 54 |
+
0: 2023-02-27 16:54:30.148563: 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.
|
| 55 |
+
0: 2023-02-27 16:54:30.148567: 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.
|
| 56 |
+
0: 2023-02-27 16:54:30.148575: 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.
|
| 57 |
+
1: 2023-02-27 16:54:30.241250: 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/aws-ofi-rccl:/pfs/lustrep2/projappl/project_462000125/samantao-public/apps/rccl/rccl-develop-release/rccl/lib:/pfs/lustrep4/projappl/project_462000075/samantao-public/rocm/glibc/selected:/pfs/lustrep2/projappl/project_462000125/samantao-public/rocm/rocm-5.2.3/hip/lib:/pfs/lustrep2/projappl/project_462000125/samantao-public/rocm/rocm-5.2.3/hsa/lib:/pfs/lustrep2/projappl/project_462000125/samantao-public/rocm/rocm-5.2.3/llvm/lib:/pfs/lustrep2/projappl/project_462000125/samantao-public/rocm/rocm-5.2.3/lib:/pfs/lustrep2/projappl/project_462000125/samantao-public/rocm/rocm-5.2.3/lib64:/pfs/lustrep2/projappl/project_462000125/samantao-public/rocm/rocm-5.2.3/llvm:/pfs/lustrep2/projappl/project_46200
|
| 58 |
+
1: 0125/samantao-public/apps/suse-repo-deps/lib64:/pfs/lustrep2/projappl/project_462000125/samantao-public/apps/suse-repo-deps/usr/lib64:/opt/cray/pe/python/3.9.12.1/lib:/opt/cray/pe/gcc-libs:/opt/cray/libfabric/1.15.0.0/lib64
|
| 59 |
+
1: 2023-02-27 16:54:30.241248: 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/aws-ofi-rccl:/pfs/lustrep2/projappl/project_462000125/samantao-public/apps/rccl/rccl-develop-release/rccl/lib:/pfs/lustrep4/projappl/project_462000075/samantao-public/rocm/glibc/selected:/pfs/lustrep2/projappl/project_462000125/samantao-public/rocm/rocm-5.2.3/hip/lib:/pfs/lustrep2/projappl/project_462000125/samantao-public/rocm/rocm-5.2.3/hsa/lib:/pfs/lustrep2/projappl/project_462000125/samantao-public/rocm/rocm-5.2.3/llvm/lib:/pfs/lustrep2/projappl/project_462000125/samantao-public/rocm/rocm-5.2.3/lib:/pfs/lustrep2/projappl/project_462000125/samantao-public/rocm/rocm-5.2.3/lib64:/pfs/lustrep2/projappl/project_462000125/samantao-public/rocm/rocm-5.2.3/llvm:/pfs/lustrep2/projappl/project_46200
|
| 60 |
+
1: 0125/samantao-public/apps/suse-repo-deps/lib64:/pfs/lustrep2/projappl/project_462000125/samantao-public/apps/suse-repo-deps/usr/lib64:/opt/cray/pe/python/3.9.12.1/lib:/opt/cray/pe/gcc-libs:/opt/cray/libfabric/1.15.0.0/lib64
|
| 61 |
+
1: 2023-02-27 16:54:30.241251: 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/aws-ofi-rccl:/pfs/lustrep2/projappl/project_462000125/samantao-public/apps/rccl/rccl-develop-release/rccl/lib:/pfs/lustrep4/projappl/project_462000075/samantao-public/rocm/glibc/selected:/pfs/lustrep2/projappl/project_462000125/samantao-public/rocm/rocm-5.2.3/hip/lib:/pfs/lustrep2/projappl/project_462000125/samantao-public/rocm/rocm-5.2.3/hsa/lib:/pfs/lustrep2/projappl/project_462000125/samantao-public/rocm/rocm-5.2.3/llvm/lib:/pfs/lustrep2/projappl/project_462000125/samantao-public/rocm/rocm-5.2.3/lib:/pfs/lustrep2/projappl/project_462000125/samantao-public/rocm/rocm-5.2.3/lib64:/pfs/lustrep2/projappl/project_462000125/samantao-public/rocm/rocm-5.2.3/llvm:/pfs/lustrep2/projappl/project_46200
|
| 62 |
+
1: 0125/samantao-public/apps/suse-repo-deps/lib64:/pfs/lustrep2/projappl/project_462000125/samantao-public/apps/suse-repo-deps/usr/lib64:/opt/cray/pe/python/3.9.12.1/lib:/opt/cray/pe/gcc-libs:/opt/cray/libfabric/1.15.0.0/lib64
|
| 63 |
+
1: 2023-02-27 16:54:30.241245: 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/aws-ofi-rccl:/pfs/lustrep2/projappl/project_462000125/samantao-public/apps/rccl/rccl-develop-release/rccl/lib:/pfs/lustrep4/projappl/project_462000075/samantao-public/rocm/glibc/selected:/pfs/lustrep2/projappl/project_462000125/samantao-public/rocm/rocm-5.2.3/hip/lib:/pfs/lustrep2/projappl/project_462000125/samantao-public/rocm/rocm-5.2.3/hsa/lib:/pfs/lustrep2/projappl/project_462000125/samantao-public/rocm/rocm-5.2.3/llvm/lib:/pfs/lustrep2/projappl/project_462000125/samantao-public/rocm/rocm-5.2.3/lib:/pfs/lustrep2/projappl/project_462000125/samantao-public/rocm/rocm-5.2.3/lib64:/pfs/lustrep2/projappl/project_462000125/samantao-public/rocm/rocm-5.2.3/llvm:/pfs/lustrep2/projappl/project_46200
|
| 64 |
+
1: 0125/samantao-public/apps/suse-repo-deps/lib64:/pfs/lustrep2/projappl/project_462000125/samantao-public/apps/suse-repo-deps/usr/lib64:/opt/cray/pe/python/3.9.12.1/lib:/opt/cray/pe/gcc-libs:/opt/cray/libfabric/1.15.0.0/lib64
|
| 65 |
+
1: 2023-02-27 16:54:30.241255: 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/aws-ofi-rccl:/pfs/lustrep2/projappl/project_462000125/samantao-public/apps/rccl/rccl-develop-release/rccl/lib:/pfs/lustrep4/projappl/project_462000075/samantao-public/rocm/glibc/selected:/pfs/lustrep2/projappl/project_462000125/samantao-public/rocm/rocm-5.2.3/hip/lib:/pfs/lustrep2/projappl/project_462000125/samantao-public/rocm/rocm-5.2.3/hsa/lib:/pfs/lustrep2/projappl/project_462000125/samantao-public/rocm/rocm-5.2.3/llvm/lib:/pfs/lustrep2/projappl/project_462000125/samantao-public/rocm/rocm-5.2.3/lib:/pfs/lustrep2/projappl/project_462000125/samantao-public/rocm/rocm-5.2.3/lib64:/pfs/lustrep2/projappl/project_462000125/samantao-public/rocm/rocm-5.2.3/llvm:/pfs/lustrep2/projappl/project_46200
|
| 66 |
+
1: 0125/samantao-public/apps/suse-repo-deps/lib64:/pfs/lustrep2/projappl/project_462000125/samantao-public/apps/suse-repo-deps/usr/lib64:/opt/cray/pe/python/3.9.12.1/lib:/opt/cray/pe/gcc-libs:/opt/cray/libfabric/1.15.0.0/lib64
|
| 67 |
+
1: 2023-02-27 16:54:30.241252: 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/aws-ofi-rccl:/pfs/lustrep2/projappl/project_462000125/samantao-public/apps/rccl/rccl-develop-release/rccl/lib:/pfs/lustrep4/projappl/project_462000075/samantao-public/rocm/glibc/selected:/pfs/lustrep2/projappl/project_462000125/samantao-public/rocm/rocm-5.2.3/hip/lib:/pfs/lustrep2/projappl/project_462000125/samantao-public/rocm/rocm-5.2.3/hsa/lib:/pfs/lustrep2/projappl/project_462000125/samantao-public/rocm/rocm-5.2.3/llvm/lib:/pfs/lustrep2/projappl/project_462000125/samantao-public/rocm/rocm-5.2.3/lib:/pfs/lustrep2/projappl/project_462000125/samantao-public/rocm/rocm-5.2.3/lib64:/pfs/lustrep2/projappl/project_462000125/samantao-public/rocm/rocm-5.2.3/llvm:/pfs/lustrep2/projappl/project_46200
|
| 68 |
+
1: 0125/samantao-public/apps/suse-repo-deps/lib64:/pfs/lustrep2/projappl/project_462000125/samantao-public/apps/suse-repo-deps/usr/lib64:/opt/cray/pe/python/3.9.12.1/lib:/opt/cray/pe/gcc-libs:/opt/cray/libfabric/1.15.0.0/lib64
|
| 69 |
+
1: 2023-02-27 16:54:30.241254: 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/aws-ofi-rccl:/pfs/lustrep2/projappl/project_462000125/samantao-public/apps/rccl/rccl-develop-release/rccl/lib:/pfs/lustrep4/projappl/project_462000075/samantao-public/rocm/glibc/selected:/pfs/lustrep2/projappl/project_462000125/samantao-public/rocm/rocm-5.2.3/hip/lib:/pfs/lustrep2/projappl/project_462000125/samantao-public/rocm/rocm-5.2.3/hsa/lib:/pfs/lustrep2/projappl/project_462000125/samantao-public/rocm/rocm-5.2.3/llvm/lib:/pfs/lustrep2/projappl/project_462000125/samantao-public/rocm/rocm-5.2.3/lib:/pfs/lustrep2/projappl/project_462000125/samantao-public/rocm/rocm-5.2.3/lib64:/pfs/lustrep2/projappl/project_462000125/samantao-public/rocm/rocm-5.2.3/llvm:/pfs/lustrep2/projappl/project_46200
|
| 70 |
+
1: 0125/samantao-public/apps/suse-repo-deps/lib64:/pfs/lustrep2/projappl/project_462000125/samantao-public/apps/suse-repo-deps/usr/lib64:/opt/cray/pe/python/3.9.12.1/lib:/opt/cray/pe/gcc-libs:/opt/cray/libfabric/1.15.0.0/lib64
|
| 71 |
+
1: 2023-02-27 16:54:30.241253: 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/aws-ofi-rccl:/pfs/lustrep2/projappl/project_462000125/samantao-public/apps/rccl/rccl-develop-release/rccl/lib:/pfs/lustrep4/projappl/project_462000075/samantao-public/rocm/glibc/selected:/pfs/lustrep2/projappl/project_462000125/samantao-public/rocm/rocm-5.2.3/hip/lib:/pfs/lustrep2/projappl/project_462000125/samantao-public/rocm/rocm-5.2.3/hsa/lib:/pfs/lustrep2/projappl/project_462000125/samantao-public/rocm/rocm-5.2.3/llvm/lib:/pfs/lustrep2/projappl/project_462000125/samantao-public/rocm/rocm-5.2.3/lib:/pfs/lustrep2/projappl/project_462000125/samantao-public/rocm/rocm-5.2.3/lib64:/pfs/lustrep2/projappl/project_462000125/samantao-public/rocm/rocm-5.2.3/llvm:/pfs/lustrep2/projappl/project_46200
|
| 72 |
+
1: 0125/samantao-public/apps/suse-repo-deps/lib64:/pfs/lustrep2/projappl/project_462000125/samantao-public/apps/suse-repo-deps/usr/lib64:/opt/cray/pe/python/3.9.12.1/lib:/opt/cray/pe/gcc-libs:/opt/cray/libfabric/1.15.0.0/lib64
|
| 73 |
+
1: 2023-02-27 16:54:30.241650: 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.
|
| 74 |
+
1: 2023-02-27 16:54:30.241652: 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.
|
| 75 |
+
1: 2023-02-27 16:54:30.241653: 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.
|
| 76 |
+
1: 2023-02-27 16:54:30.241656: 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.
|
| 77 |
+
1: 2023-02-27 16:54:30.241659: 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.
|
| 78 |
+
1: 2023-02-27 16:54:30.241660: 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.
|
| 79 |
+
1: 2023-02-27 16:54:30.241662: 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.
|
| 80 |
+
1: 2023-02-27 16:54:30.241661: 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.
|
| 81 |
+
1: 2023-02-27 16:54:38.684587: 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/aws-ofi-rccl:/pfs/lustrep2/projappl/project_462000125/samantao-public/apps/rccl/rccl-develop-release/rccl/lib:/pfs/lustrep4/projappl/project_462000075/samantao-public/rocm/glibc/selected:/pfs/lustrep2/projappl/project_462000125/samantao-public/rocm/rocm-5.2.3/hip/lib:/pfs/lustrep2/projappl/project_462000125/samantao-public/rocm/rocm-5.2.3/hsa/lib:/pfs/lustrep2/projappl/project_462000125/samantao-public/rocm/rocm-5.2.3/llvm/lib:/pfs/lustrep2/projappl/project_462000125/samantao-public/rocm/rocm-5.2.3/lib:/pfs/lustrep2/projappl/project_462000125/samantao-public/rocm/rocm-5.2.3/lib64:/pfs/lustrep2/projappl/project_462000125/samantao-public/rocm/rocm-5.2.3/llvm:/pfs/lustrep2/projappl/project_462000125
|
| 82 |
+
1: /samantao-public/apps/suse-repo-deps/lib64:/pfs/lustrep2/projappl/project_462000125/samantao-public/apps/suse-repo-deps/usr/lib64:/opt/cray/pe/python/3.9.12.1/lib:/opt/cray/pe/gcc-libs:/opt/cray/libfabric/1.15.0.0/lib64
|
| 83 |
+
1: 2023-02-27 16:54:38.684592: 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/aws-ofi-rccl:/pfs/lustrep2/projappl/project_462000125/samantao-public/apps/rccl/rccl-develop-release/rccl/lib:/pfs/lustrep4/projappl/project_462000075/samantao-public/rocm/glibc/selected:/pfs/lustrep2/projappl/project_462000125/samantao-public/rocm/rocm-5.2.3/hip/lib:/pfs/lustrep2/projappl/project_462000125/samantao-public/rocm/rocm-5.2.3/hsa/lib:/pfs/lustrep2/projappl/project_462000125/samantao-public/rocm/rocm-5.2.3/llvm/lib:/pfs/lustrep2/projappl/project_462000125/samantao-public/rocm/rocm-5.2.3/lib:/pfs/lustrep2/projappl/project_462000125/samantao-public/rocm/rocm-5.2.3/lib64:/pfs/lustrep2/projappl/project_462000125/samantao-public/rocm/rocm-5.2.3/llvm:/pfs/lustrep2/projappl/project_462000125
|
| 84 |
+
1: /samantao-public/apps/suse-repo-deps/lib64:/pfs/lustrep2/projappl/project_462000125/samantao-public/apps/suse-repo-deps/usr/lib64:/opt/cray/pe/python/3.9.12.1/lib:/opt/cray/pe/gcc-libs:/opt/cray/libfabric/1.15.0.0/lib64
|
| 85 |
+
1: 2023-02-27 16:54:38.684601: 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/aws-ofi-rccl:/pfs/lustrep2/projappl/project_462000125/samantao-public/apps/rccl/rccl-develop-release/rccl/lib:/pfs/lustrep4/projappl/project_462000075/samantao-public/rocm/glibc/selected:/pfs/lustrep2/projappl/project_462000125/samantao-public/rocm/rocm-5.2.3/hip/lib:/pfs/lustrep2/projappl/project_462000125/samantao-public/rocm/rocm-5.2.3/hsa/lib:/pfs/lustrep2/projappl/project_462000125/samantao-public/rocm/rocm-5.2.3/llvm/lib:/pfs/lustrep2/projappl/project_462000125/samantao-public/rocm/rocm-5.2.3/lib:/pfs/lustrep2/projappl/project_462000125/samantao-public/rocm/rocm-5.2.3/lib64:/pfs/lustrep2/projappl/project_462000125/samantao-public/rocm/rocm-5.2.3/llvm:/pfs/lustrep2/projappl/project_462000125
|
| 86 |
+
1: /samantao-public/apps/suse-repo-deps/lib64:/pfs/lustrep2/projappl/project_462000125/samantao-public/apps/suse-repo-deps/usr/lib64:/opt/cray/pe/python/3.9.12.1/lib:/opt/cray/pe/gcc-libs:/opt/cray/libfabric/1.15.0.0/lib64
|
| 87 |
+
1: 2023-02-27 16:54:38.684603: 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/aws-ofi-rccl:/pfs/lustrep2/projappl/project_462000125/samantao-public/apps/rccl/rccl-develop-release/rccl/lib:/pfs/lustrep4/projappl/project_462000075/samantao-public/rocm/glibc/selected:/pfs/lustrep2/projappl/project_462000125/samantao-public/rocm/rocm-5.2.3/hip/lib:/pfs/lustrep2/projappl/project_462000125/samantao-public/rocm/rocm-5.2.3/hsa/lib:/pfs/lustrep2/projappl/project_462000125/samantao-public/rocm/rocm-5.2.3/llvm/lib:/pfs/lustrep2/projappl/project_462000125/samantao-public/rocm/rocm-5.2.3/lib:/pfs/lustrep2/projappl/project_462000125/samantao-public/rocm/rocm-5.2.3/lib64:/pfs/lustrep2/projappl/project_462000125/samantao-public/rocm/rocm-5.2.3/llvm:/pfs/lustrep2/projappl/project_462000125
|
| 88 |
+
1: /samantao-public/apps/suse-repo-deps/lib64:/pfs/lustrep2/projappl/project_462000125/samantao-public/apps/suse-repo-deps/usr/lib64:/opt/cray/pe/python/3.9.12.1/lib:/opt/cray/pe/gcc-libs:/opt/cray/libfabric/1.15.0.0/lib64
|
| 89 |
+
1: 2023-02-27 16:54:38.684600: 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/aws-ofi-rccl:/pfs/lustrep2/projappl/project_462000125/samantao-public/apps/rccl/rccl-develop-release/rccl/lib:/pfs/lustrep4/projappl/project_462000075/samantao-public/rocm/glibc/selected:/pfs/lustrep2/projappl/project_462000125/samantao-public/rocm/rocm-5.2.3/hip/lib:/pfs/lustrep2/projappl/project_462000125/samantao-public/rocm/rocm-5.2.3/hsa/lib:/pfs/lustrep2/projappl/project_462000125/samantao-public/rocm/rocm-5.2.3/llvm/lib:/pfs/lustrep2/projappl/project_462000125/samantao-public/rocm/rocm-5.2.3/lib:/pfs/lustrep2/projappl/project_462000125/samantao-public/rocm/rocm-5.2.3/lib64:/pfs/lustrep2/projappl/project_462000125/samantao-public/rocm/rocm-5.2.3/llvm:/pfs/lustrep2/projappl/project_462000125
|
| 90 |
+
1: /samantao-public/apps/suse-repo-deps/lib64:/pfs/lustrep2/projappl/project_462000125/samantao-public/apps/suse-repo-deps/usr/lib64:/opt/cray/pe/python/3.9.12.1/lib:/opt/cray/pe/gcc-libs:/opt/cray/libfabric/1.15.0.0/lib64
|
| 91 |
+
1: 2023-02-27 16:54:38.684599: 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/aws-ofi-rccl:/pfs/lustrep2/projappl/project_462000125/samantao-public/apps/rccl/rccl-develop-release/rccl/lib:/pfs/lustrep4/projappl/project_462000075/samantao-public/rocm/glibc/selected:/pfs/lustrep2/projappl/project_462000125/samantao-public/rocm/rocm-5.2.3/hip/lib:/pfs/lustrep2/projappl/project_462000125/samantao-public/rocm/rocm-5.2.3/hsa/lib:/pfs/lustrep2/projappl/project_462000125/samantao-public/rocm/rocm-5.2.3/llvm/lib:/pfs/lustrep2/projappl/project_462000125/samantao-public/rocm/rocm-5.2.3/lib:/pfs/lustrep2/projappl/project_462000125/samantao-public/rocm/rocm-5.2.3/lib64:/pfs/lustrep2/projappl/project_462000125/samantao-public/rocm/rocm-5.2.3/llvm:/pfs/lustrep2/projappl/project_462000125
|
| 92 |
+
1: /samantao-public/apps/suse-repo-deps/lib64:/pfs/lustrep2/projappl/project_462000125/samantao-public/apps/suse-repo-deps/usr/lib64:/opt/cray/pe/python/3.9.12.1/lib:/opt/cray/pe/gcc-libs:/opt/cray/libfabric/1.15.0.0/lib64
|
| 93 |
+
1: 2023-02-27 16:54:38.684606: 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/aws-ofi-rccl:/pfs/lustrep2/projappl/project_462000125/samantao-public/apps/rccl/rccl-develop-release/rccl/lib:/pfs/lustrep4/projappl/project_462000075/samantao-public/rocm/glibc/selected:/pfs/lustrep2/projappl/project_462000125/samantao-public/rocm/rocm-5.2.3/hip/lib:/pfs/lustrep2/projappl/project_462000125/samantao-public/rocm/rocm-5.2.3/hsa/lib:/pfs/lustrep2/projappl/project_462000125/samantao-public/rocm/rocm-5.2.3/llvm/lib:/pfs/lustrep2/projappl/project_462000125/samantao-public/rocm/rocm-5.2.3/lib:/pfs/lustrep2/projappl/project_462000125/samantao-public/rocm/rocm-5.2.3/lib64:/pfs/lustrep2/projappl/project_462000125/samantao-public/rocm/rocm-5.2.3/llvm:/pfs/lustrep2/projappl/project_462000125
|
| 94 |
+
1: /samantao-public/apps/suse-repo-deps/lib64:/pfs/lustrep2/projappl/project_462000125/samantao-public/apps/suse-repo-deps/usr/lib64:/opt/cray/pe/python/3.9.12.1/lib:/opt/cray/pe/gcc-libs:/opt/cray/libfabric/1.15.0.0/lib64
|
| 95 |
+
1: 2023-02-27 16:54:38.684608: 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/aws-ofi-rccl:/pfs/lustrep2/projappl/project_462000125/samantao-public/apps/rccl/rccl-develop-release/rccl/lib:/pfs/lustrep4/projappl/project_462000075/samantao-public/rocm/glibc/selected:/pfs/lustrep2/projappl/project_462000125/samantao-public/rocm/rocm-5.2.3/hip/lib:/pfs/lustrep2/projappl/project_462000125/samantao-public/rocm/rocm-5.2.3/hsa/lib:/pfs/lustrep2/projappl/project_462000125/samantao-public/rocm/rocm-5.2.3/llvm/lib:/pfs/lustrep2/projappl/project_462000125/samantao-public/rocm/rocm-5.2.3/lib:/pfs/lustrep2/projappl/project_462000125/samantao-public/rocm/rocm-5.2.3/lib64:/pfs/lustrep2/projappl/project_462000125/samantao-public/rocm/rocm-5.2.3/llvm:/pfs/lustrep2/projappl/project_462000125
|
| 96 |
+
1: /samantao-public/apps/suse-repo-deps/lib64:/pfs/lustrep2/projappl/project_462000125/samantao-public/apps/suse-repo-deps/usr/lib64:/opt/cray/pe/python/3.9.12.1/lib:/opt/cray/pe/gcc-libs:/opt/cray/libfabric/1.15.0.0/lib64
|
| 97 |
+
1: 2023-02-27 16:54:38.687092: 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/aws-ofi-rccl:/pfs/lustrep2/projappl/project_462000125/samantao-public/apps/rccl/rccl-develop-release/rccl/lib:/pfs/lustrep4/projappl/project_462000075/samantao-public/rocm/glibc/selected:/pfs/lustrep2/projappl/project_462000125/samantao-public/rocm/rocm-5.2.3/hip/lib:/pfs/lustrep2/projappl/project_462000125/samantao-public/rocm/rocm-5.2.3/hsa/lib:/pfs/lustrep2/projappl/project_462000125/samantao-public/rocm/rocm-5.2.3/llvm/lib:/pfs/lustrep2/projappl/project_462000125/samantao-public/rocm/rocm-5.2.3/lib:/pfs/lustrep2/projappl/project_462000125/samantao-public/rocm/rocm-5.2.3/lib64:/pfs/lustrep2/projappl/project_462000125/samantao-public/rocm/rocm-5.2.3/llvm:/pfs/lustrep2/projappl/pro
|
| 98 |
+
1: ject_462000125/samantao-public/apps/suse-repo-deps/lib64:/pfs/lustrep2/projappl/project_462000125/samantao-public/apps/suse-repo-deps/usr/lib64:/opt/cray/pe/python/3.9.12.1/lib:/opt/cray/pe/gcc-libs:/opt/cray/libfabric/1.15.0.0/lib64
|
| 99 |
+
1: 2023-02-27 16:54:38.687093: 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/aws-ofi-rccl:/pfs/lustrep2/projappl/project_462000125/samantao-public/apps/rccl/rccl-develop-release/rccl/lib:/pfs/lustrep4/projappl/project_462000075/samantao-public/rocm/glibc/selected:/pfs/lustrep2/projappl/project_462000125/samantao-public/rocm/rocm-5.2.3/hip/lib:/pfs/lustrep2/projappl/project_462000125/samantao-public/rocm/rocm-5.2.3/hsa/lib:/pfs/lustrep2/projappl/project_462000125/samantao-public/rocm/rocm-5.2.3/llvm/lib:/pfs/lustrep2/projappl/project_462000125/samantao-public/rocm/rocm-5.2.3/lib:/pfs/lustrep2/projappl/project_462000125/samantao-public/rocm/rocm-5.2.3/lib64:/pfs/lustrep2/projappl/project_462000125/samantao-public/rocm/rocm-5.2.3/llvm:/pfs/lustrep2/projappl/pro
|
| 100 |
+
1: ject_462000125/samantao-public/apps/suse-repo-deps/lib64:/pfs/lustrep2/projappl/project_462000125/samantao-public/apps/suse-repo-deps/usr/lib64:/opt/cray/pe/python/3.9.12.1/lib:/opt/cray/pe/gcc-libs:/opt/cray/libfabric/1.15.0.0/lib64
|
| 101 |
+
1: 2023-02-27 16:54:38.687096: 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/aws-ofi-rccl:/pfs/lustrep2/projappl/project_462000125/samantao-public/apps/rccl/rccl-develop-release/rccl/lib:/pfs/lustrep4/projappl/project_462000075/samantao-public/rocm/glibc/selected:/pfs/lustrep2/projappl/project_462000125/samantao-public/rocm/rocm-5.2.3/hip/lib:/pfs/lustrep2/projappl/project_462000125/samantao-public/rocm/rocm-5.2.3/hsa/lib:/pfs/lustrep2/projappl/project_462000125/samantao-public/rocm/rocm-5.2.3/llvm/lib:/pfs/lustrep2/projappl/project_462000125/samantao-public/rocm/rocm-5.2.3/lib:/pfs/lustrep2/projappl/project_462000125/samantao-public/rocm/rocm-5.2.3/lib64:/pfs/lustrep2/projappl/project_462000125/samantao-public/rocm/rocm-5.2.3/llvm:/pfs/lustrep2/projappl/pro
|
| 102 |
+
1: ject_462000125/samantao-public/apps/suse-repo-deps/lib64:/pfs/lustrep2/projappl/project_462000125/samantao-public/apps/suse-repo-deps/usr/lib64:/opt/cray/pe/python/3.9.12.1/lib:/opt/cray/pe/gcc-libs:/opt/cray/libfabric/1.15.0.0/lib64
|
| 103 |
+
1: 2023-02-27 16:54:38.687099: 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/aws-ofi-rccl:/pfs/lustrep2/projappl/project_462000125/samantao-public/apps/rccl/rccl-develop-release/rccl/lib:/pfs/lustrep4/projappl/project_462000075/samantao-public/rocm/glibc/selected:/pfs/lustrep2/projappl/project_462000125/samantao-public/rocm/rocm-5.2.3/hip/lib:/pfs/lustrep2/projappl/project_462000125/samantao-public/rocm/rocm-5.2.3/hsa/lib:/pfs/lustrep2/projappl/project_462000125/samantao-public/rocm/rocm-5.2.3/llvm/lib:/pfs/lustrep2/projappl/project_462000125/samantao-public/rocm/rocm-5.2.3/lib:/pfs/lustrep2/projappl/project_462000125/samantao-public/rocm/rocm-5.2.3/lib64:/pfs/lustrep2/projappl/project_462000125/samantao-public/rocm/rocm-5.2.3/llvm:/pfs/lustrep2/projappl/pro
|
| 104 |
+
1: ject_462000125/samantao-public/apps/suse-repo-deps/lib64:/pfs/lustrep2/projappl/project_462000125/samantao-public/apps/suse-repo-deps/usr/lib64:/opt/cray/pe/python/3.9.12.1/lib:/opt/cray/pe/gcc-libs:/opt/cray/libfabric/1.15.0.0/lib64
|
| 105 |
+
1: 2023-02-27 16:54:38.687100: 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/aws-ofi-rccl:/pfs/lustrep2/projappl/project_462000125/samantao-public/apps/rccl/rccl-develop-release/rccl/lib:/pfs/lustrep4/projappl/project_462000075/samantao-public/rocm/glibc/selected:/pfs/lustrep2/projappl/project_462000125/samantao-public/rocm/rocm-5.2.3/hip/lib:/pfs/lustrep2/projappl/project_462000125/samantao-public/rocm/rocm-5.2.3/hsa/lib:/pfs/lustrep2/projappl/project_462000125/samantao-public/rocm/rocm-5.2.3/llvm/lib:/pfs/lustrep2/projappl/project_462000125/samantao-public/rocm/rocm-5.2.3/lib:/pfs/lustrep2/projappl/project_462000125/samantao-public/rocm/rocm-5.2.3/lib64:/pfs/lustrep2/projappl/project_462000125/samantao-public/rocm/rocm-5.2.3/llvm:/pfs/lustrep2/projappl/pro
|
| 106 |
+
1: ject_462000125/samantao-public/apps/suse-repo-deps/lib64:/pfs/lustrep2/projappl/project_462000125/samantao-public/apps/suse-repo-deps/usr/lib64:/opt/cray/pe/python/3.9.12.1/lib:/opt/cray/pe/gcc-libs:/opt/cray/libfabric/1.15.0.0/lib64
|
| 107 |
+
1: 2023-02-27 16:54:38.687102: 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/aws-ofi-rccl:/pfs/lustrep2/projappl/project_462000125/samantao-public/apps/rccl/rccl-develop-release/rccl/lib:/pfs/lustrep4/projappl/project_462000075/samantao-public/rocm/glibc/selected:/pfs/lustrep2/projappl/project_462000125/samantao-public/rocm/rocm-5.2.3/hip/lib:/pfs/lustrep2/projappl/project_462000125/samantao-public/rocm/rocm-5.2.3/hsa/lib:/pfs/lustrep2/projappl/project_462000125/samantao-public/rocm/rocm-5.2.3/llvm/lib:/pfs/lustrep2/projappl/project_462000125/samantao-public/rocm/rocm-5.2.3/lib:/pfs/lustrep2/projappl/project_462000125/samantao-public/rocm/rocm-5.2.3/lib64:/pfs/lustrep2/projappl/project_462000125/samantao-public/rocm/rocm-5.2.3/llvm:/pfs/lustrep2/projappl/pro
|
| 108 |
+
1: ject_462000125/samantao-public/apps/suse-repo-deps/lib64:/pfs/lustrep2/projappl/project_462000125/samantao-public/apps/suse-repo-deps/usr/lib64:/opt/cray/pe/python/3.9.12.1/lib:/opt/cray/pe/gcc-libs:/opt/cray/libfabric/1.15.0.0/lib64
|
| 109 |
+
1: 2023-02-27 16:54:38.687106: 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.
|
| 110 |
+
1: 2023-02-27 16:54:38.687107: 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.
|
| 111 |
+
1: 2023-02-27 16:54:38.687109: 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.
|
| 112 |
+
1: 2023-02-27 16:54:38.687104: 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/aws-ofi-rccl:/pfs/lustrep2/projappl/project_462000125/samantao-public/apps/rccl/rccl-develop-release/rccl/lib:/pfs/lustrep4/projappl/project_462000075/samantao-public/rocm/glibc/selected:/pfs/lustrep2/projappl/project_462000125/samantao-public/rocm/rocm-5.2.3/hip/lib:/pfs/lustrep2/projappl/project_462000125/samantao-public/rocm/rocm-5.2.3/hsa/lib:/pfs/lustrep2/projappl/project_462000125/samantao-public/rocm/rocm-5.2.3/llvm/lib:/pfs/lustrep2/projappl/project_462000125/samantao-public/rocm/rocm-5.2.3/lib:/pfs/lustrep2/projappl/project_462000125/samantao-public/rocm/rocm-5.2.3/lib64:/pfs/lustrep2/projappl/project_462000125/samantao-public/rocm/rocm-5.2.3/llvm:/pfs/lustrep2/projappl/pro
|
| 113 |
+
1: ject_462000125/samantao-public/apps/suse-repo-deps/lib64:/pfs/lustrep2/projappl/project_462000125/samantao-public/apps/suse-repo-deps/usr/lib64:/opt/cray/pe/python/3.9.12.1/lib:/opt/cray/pe/gcc-libs:/opt/cray/libfabric/1.15.0.0/lib64
|
| 114 |
+
1: 2023-02-27 16:54:38.687105: 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/aws-ofi-rccl:/pfs/lustrep2/projappl/project_462000125/samantao-public/apps/rccl/rccl-develop-release/rccl/lib:/pfs/lustrep4/projappl/project_462000075/samantao-public/rocm/glibc/selected:/pfs/lustrep2/projappl/project_462000125/samantao-public/rocm/rocm-5.2.3/hip/lib:/pfs/lustrep2/projappl/project_462000125/samantao-public/rocm/rocm-5.2.3/hsa/lib:/pfs/lustrep2/projappl/project_462000125/samantao-public/rocm/rocm-5.2.3/llvm/lib:/pfs/lustrep2/projappl/project_462000125/samantao-public/rocm/rocm-5.2.3/lib:/pfs/lustrep2/projappl/project_462000125/samantao-public/rocm/rocm-5.2.3/lib64:/pfs/lustrep2/projappl/project_462000125/samantao-public/rocm/rocm-5.2.3/llvm:/pfs/lustrep2/projappl/pro
|
| 115 |
+
1: ject_462000125/samantao-public/apps/suse-repo-deps/lib64:/pfs/lustrep2/projappl/project_462000125/samantao-public/apps/suse-repo-deps/usr/lib64:/opt/cray/pe/python/3.9.12.1/lib:/opt/cray/pe/gcc-libs:/opt/cray/libfabric/1.15.0.0/lib64
|
| 116 |
+
1: 2023-02-27 16:54:38.687117: 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.
|
| 117 |
+
1: 2023-02-27 16:54:38.687116: 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.
|
| 118 |
+
1: 2023-02-27 16:54:38.687116: 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.
|
| 119 |
+
1: 2023-02-27 16:54:38.687121: 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.
|
| 120 |
+
1: 2023-02-27 16:54:38.687122: 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.
|
| 121 |
+
0: 2023-02-27 16:54:38.693996: 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/aws-ofi-rccl:/pfs/lustrep2/projappl/project_462000125/samantao-public/apps/rccl/rccl-develop-release/rccl/lib:/pfs/lustrep4/projappl/project_462000075/samantao-public/rocm/glibc/selected:/pfs/lustrep2/projappl/project_462000125/samantao-public/rocm/rocm-5.2.3/hip/lib:/pfs/lustrep2/projappl/project_462000125/samantao-public/rocm/rocm-5.2.3/hsa/lib:/pfs/lustrep2/projappl/project_462000125/samantao-public/rocm/rocm-5.2.3/llvm/lib:/pfs/lustrep2/projappl/project_462000125/samantao-public/rocm/rocm-5.2.3/lib:/pfs/lustrep2/projappl/project_462000125/samantao-public/rocm/rocm-5.2.3/lib64:/pfs/lustrep2/projappl/project_462000125/samantao-public/rocm/rocm-5.2.3/llvm:/pfs/lustrep2/projappl/project_462000125
|
| 122 |
+
0: /samantao-public/apps/suse-repo-deps/lib64:/pfs/lustrep2/projappl/project_462000125/samantao-public/apps/suse-repo-deps/usr/lib64:/opt/cray/pe/python/3.9.12.1/lib:/opt/cray/pe/gcc-libs:/opt/cray/libfabric/1.15.0.0/lib64
|
| 123 |
+
0: 2023-02-27 16:54:38.694004: 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/aws-ofi-rccl:/pfs/lustrep2/projappl/project_462000125/samantao-public/apps/rccl/rccl-develop-release/rccl/lib:/pfs/lustrep4/projappl/project_462000075/samantao-public/rocm/glibc/selected:/pfs/lustrep2/projappl/project_462000125/samantao-public/rocm/rocm-5.2.3/hip/lib:/pfs/lustrep2/projappl/project_462000125/samantao-public/rocm/rocm-5.2.3/hsa/lib:/pfs/lustrep2/projappl/project_462000125/samantao-public/rocm/rocm-5.2.3/llvm/lib:/pfs/lustrep2/projappl/project_462000125/samantao-public/rocm/rocm-5.2.3/lib:/pfs/lustrep2/projappl/project_462000125/samantao-public/rocm/rocm-5.2.3/lib64:/pfs/lustrep2/projappl/project_462000125/samantao-public/rocm/rocm-5.2.3/llvm:/pfs/lustrep2/projappl/project_462000125
|
| 124 |
+
0: /samantao-public/apps/suse-repo-deps/lib64:/pfs/lustrep2/projappl/project_462000125/samantao-public/apps/suse-repo-deps/usr/lib64:/opt/cray/pe/python/3.9.12.1/lib:/opt/cray/pe/gcc-libs:/opt/cray/libfabric/1.15.0.0/lib64
|
| 125 |
+
0: 2023-02-27 16:54:38.694011: 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/aws-ofi-rccl:/pfs/lustrep2/projappl/project_462000125/samantao-public/apps/rccl/rccl-develop-release/rccl/lib:/pfs/lustrep4/projappl/project_462000075/samantao-public/rocm/glibc/selected:/pfs/lustrep2/projappl/project_462000125/samantao-public/rocm/rocm-5.2.3/hip/lib:/pfs/lustrep2/projappl/project_462000125/samantao-public/rocm/rocm-5.2.3/hsa/lib:/pfs/lustrep2/projappl/project_462000125/samantao-public/rocm/rocm-5.2.3/llvm/lib:/pfs/lustrep2/projappl/project_462000125/samantao-public/rocm/rocm-5.2.3/lib:/pfs/lustrep2/projappl/project_462000125/samantao-public/rocm/rocm-5.2.3/lib64:/pfs/lustrep2/projappl/project_462000125/samantao-public/rocm/rocm-5.2.3/llvm:/pfs/lustrep2/projappl/project_462000125
|
| 126 |
+
0: /samantao-public/apps/suse-repo-deps/lib64:/pfs/lustrep2/projappl/project_462000125/samantao-public/apps/suse-repo-deps/usr/lib64:/opt/cray/pe/python/3.9.12.1/lib:/opt/cray/pe/gcc-libs:/opt/cray/libfabric/1.15.0.0/lib64
|
| 127 |
+
0: 2023-02-27 16:54:38.694014: 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/aws-ofi-rccl:/pfs/lustrep2/projappl/project_462000125/samantao-public/apps/rccl/rccl-develop-release/rccl/lib:/pfs/lustrep4/projappl/project_462000075/samantao-public/rocm/glibc/selected:/pfs/lustrep2/projappl/project_462000125/samantao-public/rocm/rocm-5.2.3/hip/lib:/pfs/lustrep2/projappl/project_462000125/samantao-public/rocm/rocm-5.2.3/hsa/lib:/pfs/lustrep2/projappl/project_462000125/samantao-public/rocm/rocm-5.2.3/llvm/lib:/pfs/lustrep2/projappl/project_462000125/samantao-public/rocm/rocm-5.2.3/lib:/pfs/lustrep2/projappl/project_462000125/samantao-public/rocm/rocm-5.2.3/lib64:/pfs/lustrep2/projappl/project_462000125/samantao-public/rocm/rocm-5.2.3/llvm:/pfs/lustrep2/projappl/project_462000125
|
| 128 |
+
0: /samantao-public/apps/suse-repo-deps/lib64:/pfs/lustrep2/projappl/project_462000125/samantao-public/apps/suse-repo-deps/usr/lib64:/opt/cray/pe/python/3.9.12.1/lib:/opt/cray/pe/gcc-libs:/opt/cray/libfabric/1.15.0.0/lib64
|
| 129 |
+
0: 2023-02-27 16:54:38.694016: 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/aws-ofi-rccl:/pfs/lustrep2/projappl/project_462000125/samantao-public/apps/rccl/rccl-develop-release/rccl/lib:/pfs/lustrep4/projappl/project_462000075/samantao-public/rocm/glibc/selected:/pfs/lustrep2/projappl/project_462000125/samantao-public/rocm/rocm-5.2.3/hip/lib:/pfs/lustrep2/projappl/project_462000125/samantao-public/rocm/rocm-5.2.3/hsa/lib:/pfs/lustrep2/projappl/project_462000125/samantao-public/rocm/rocm-5.2.3/llvm/lib:/pfs/lustrep2/projappl/project_462000125/samantao-public/rocm/rocm-5.2.3/lib:/pfs/lustrep2/projappl/project_462000125/samantao-public/rocm/rocm-5.2.3/lib64:/pfs/lustrep2/projappl/project_462000125/samantao-public/rocm/rocm-5.2.3/llvm:/pfs/lustrep2/projappl/project_462000125
|
| 130 |
+
0: /samantao-public/apps/suse-repo-deps/lib64:/pfs/lustrep2/projappl/project_462000125/samantao-public/apps/suse-repo-deps/usr/lib64:/opt/cray/pe/python/3.9.12.1/lib:/opt/cray/pe/gcc-libs:/opt/cray/libfabric/1.15.0.0/lib64
|
| 131 |
+
0: 2023-02-27 16:54:38.694016: 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/aws-ofi-rccl:/pfs/lustrep2/projappl/project_462000125/samantao-public/apps/rccl/rccl-develop-release/rccl/lib:/pfs/lustrep4/projappl/project_462000075/samantao-public/rocm/glibc/selected:/pfs/lustrep2/projappl/project_462000125/samantao-public/rocm/rocm-5.2.3/hip/lib:/pfs/lustrep2/projappl/project_462000125/samantao-public/rocm/rocm-5.2.3/hsa/lib:/pfs/lustrep2/projappl/project_462000125/samantao-public/rocm/rocm-5.2.3/llvm/lib:/pfs/lustrep2/projappl/project_462000125/samantao-public/rocm/rocm-5.2.3/lib:/pfs/lustrep2/projappl/project_462000125/samantao-public/rocm/rocm-5.2.3/lib64:/pfs/lustrep2/projappl/project_462000125/samantao-public/rocm/rocm-5.2.3/llvm:/pfs/lustrep2/projappl/project_462000125
|
| 132 |
+
0: /samantao-public/apps/suse-repo-deps/lib64:/pfs/lustrep2/projappl/project_462000125/samantao-public/apps/suse-repo-deps/usr/lib64:/opt/cray/pe/python/3.9.12.1/lib:/opt/cray/pe/gcc-libs:/opt/cray/libfabric/1.15.0.0/lib64
|
| 133 |
+
0: 2023-02-27 16:54:38.694020: 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/aws-ofi-rccl:/pfs/lustrep2/projappl/project_462000125/samantao-public/apps/rccl/rccl-develop-release/rccl/lib:/pfs/lustrep4/projappl/project_462000075/samantao-public/rocm/glibc/selected:/pfs/lustrep2/projappl/project_462000125/samantao-public/rocm/rocm-5.2.3/hip/lib:/pfs/lustrep2/projappl/project_462000125/samantao-public/rocm/rocm-5.2.3/hsa/lib:/pfs/lustrep2/projappl/project_462000125/samantao-public/rocm/rocm-5.2.3/llvm/lib:/pfs/lustrep2/projappl/project_462000125/samantao-public/rocm/rocm-5.2.3/lib:/pfs/lustrep2/projappl/project_462000125/samantao-public/rocm/rocm-5.2.3/lib64:/pfs/lustrep2/projappl/project_462000125/samantao-public/rocm/rocm-5.2.3/llvm:/pfs/lustrep2/projappl/project_462000125
|
| 134 |
+
0: /samantao-public/apps/suse-repo-deps/lib64:/pfs/lustrep2/projappl/project_462000125/samantao-public/apps/suse-repo-deps/usr/lib64:/opt/cray/pe/python/3.9.12.1/lib:/opt/cray/pe/gcc-libs:/opt/cray/libfabric/1.15.0.0/lib64
|
| 135 |
+
0: 2023-02-27 16:54:38.694023: 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/aws-ofi-rccl:/pfs/lustrep2/projappl/project_462000125/samantao-public/apps/rccl/rccl-develop-release/rccl/lib:/pfs/lustrep4/projappl/project_462000075/samantao-public/rocm/glibc/selected:/pfs/lustrep2/projappl/project_462000125/samantao-public/rocm/rocm-5.2.3/hip/lib:/pfs/lustrep2/projappl/project_462000125/samantao-public/rocm/rocm-5.2.3/hsa/lib:/pfs/lustrep2/projappl/project_462000125/samantao-public/rocm/rocm-5.2.3/llvm/lib:/pfs/lustrep2/projappl/project_462000125/samantao-public/rocm/rocm-5.2.3/lib:/pfs/lustrep2/projappl/project_462000125/samantao-public/rocm/rocm-5.2.3/lib64:/pfs/lustrep2/projappl/project_462000125/samantao-public/rocm/rocm-5.2.3/llvm:/pfs/lustrep2/projappl/project_462000125
|
| 136 |
+
0: /samantao-public/apps/suse-repo-deps/lib64:/pfs/lustrep2/projappl/project_462000125/samantao-public/apps/suse-repo-deps/usr/lib64:/opt/cray/pe/python/3.9.12.1/lib:/opt/cray/pe/gcc-libs:/opt/cray/libfabric/1.15.0.0/lib64
|
| 137 |
+
0: 2023-02-27 16:54:38.696054: 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/aws-ofi-rccl:/pfs/lustrep2/projappl/project_462000125/samantao-public/apps/rccl/rccl-develop-release/rccl/lib:/pfs/lustrep4/projappl/project_462000075/samantao-public/rocm/glibc/selected:/pfs/lustrep2/projappl/project_462000125/samantao-public/rocm/rocm-5.2.3/hip/lib:/pfs/lustrep2/projappl/project_462000125/samantao-public/rocm/rocm-5.2.3/hsa/lib:/pfs/lustrep2/projappl/project_462000125/samantao-public/rocm/rocm-5.2.3/llvm/lib:/pfs/lustrep2/projappl/project_462000125/samantao-public/rocm/rocm-5.2.3/lib:/pfs/lustrep2/projappl/project_462000125/samantao-public/rocm/rocm-5.2.3/lib64:/pfs/lustrep2/projappl/project_462000125/samantao-public/rocm/rocm-5.2.3/llvm:/pfs/lustrep2/projappl/pro
|
| 138 |
+
0: ject_462000125/samantao-public/apps/suse-repo-deps/lib64:/pfs/lustrep2/projappl/project_462000125/samantao-public/apps/suse-repo-deps/usr/lib64:/opt/cray/pe/python/3.9.12.1/lib:/opt/cray/pe/gcc-libs:/opt/cray/libfabric/1.15.0.0/lib64
|
| 139 |
+
0: 2023-02-27 16:54:38.696055: 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/aws-ofi-rccl:/pfs/lustrep2/projappl/project_462000125/samantao-public/apps/rccl/rccl-develop-release/rccl/lib:/pfs/lustrep4/projappl/project_462000075/samantao-public/rocm/glibc/selected:/pfs/lustrep2/projappl/project_462000125/samantao-public/rocm/rocm-5.2.3/hip/lib:/pfs/lustrep2/projappl/project_462000125/samantao-public/rocm/rocm-5.2.3/hsa/lib:/pfs/lustrep2/projappl/project_462000125/samantao-public/rocm/rocm-5.2.3/llvm/lib:/pfs/lustrep2/projappl/project_462000125/samantao-public/rocm/rocm-5.2.3/lib:/pfs/lustrep2/projappl/project_462000125/samantao-public/rocm/rocm-5.2.3/lib64:/pfs/lustrep2/projappl/project_462000125/samantao-public/rocm/rocm-5.2.3/llvm:/pfs/lustrep2/projappl/pro
|
| 140 |
+
0: ject_462000125/samantao-public/apps/suse-repo-deps/lib64:/pfs/lustrep2/projappl/project_462000125/samantao-public/apps/suse-repo-deps/usr/lib64:/opt/cray/pe/python/3.9.12.1/lib:/opt/cray/pe/gcc-libs:/opt/cray/libfabric/1.15.0.0/lib64
|
| 141 |
+
0: 2023-02-27 16:54:38.696059: 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/aws-ofi-rccl:/pfs/lustrep2/projappl/project_462000125/samantao-public/apps/rccl/rccl-develop-release/rccl/lib:/pfs/lustrep4/projappl/project_462000075/samantao-public/rocm/glibc/selected:/pfs/lustrep2/projappl/project_462000125/samantao-public/rocm/rocm-5.2.3/hip/lib:/pfs/lustrep2/projappl/project_462000125/samantao-public/rocm/rocm-5.2.3/hsa/lib:/pfs/lustrep2/projappl/project_462000125/samantao-public/rocm/rocm-5.2.3/llvm/lib:/pfs/lustrep2/projappl/project_462000125/samantao-public/rocm/rocm-5.2.3/lib:/pfs/lustrep2/projappl/project_462000125/samantao-public/rocm/rocm-5.2.3/lib64:/pfs/lustrep2/projappl/project_462000125/samantao-public/rocm/rocm-5.2.3/llvm:/pfs/lustrep2/projappl/pro
|
| 142 |
+
0: ject_462000125/samantao-public/apps/suse-repo-deps/lib64:/pfs/lustrep2/projappl/project_462000125/samantao-public/apps/suse-repo-deps/usr/lib64:/opt/cray/pe/python/3.9.12.1/lib:/opt/cray/pe/gcc-libs:/opt/cray/libfabric/1.15.0.0/lib64
|
| 143 |
+
0: 2023-02-27 16:54:38.696060: 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/aws-ofi-rccl:/pfs/lustrep2/projappl/project_462000125/samantao-public/apps/rccl/rccl-develop-release/rccl/lib:/pfs/lustrep4/projappl/project_462000075/samantao-public/rocm/glibc/selected:/pfs/lustrep2/projappl/project_462000125/samantao-public/rocm/rocm-5.2.3/hip/lib:/pfs/lustrep2/projappl/project_462000125/samantao-public/rocm/rocm-5.2.3/hsa/lib:/pfs/lustrep2/projappl/project_462000125/samantao-public/rocm/rocm-5.2.3/llvm/lib:/pfs/lustrep2/projappl/project_462000125/samantao-public/rocm/rocm-5.2.3/lib:/pfs/lustrep2/projappl/project_462000125/samantao-public/rocm/rocm-5.2.3/lib64:/pfs/lustrep2/projappl/project_462000125/samantao-public/rocm/rocm-5.2.3/llvm:/pfs/lustrep2/projappl/pro
|
| 144 |
+
0: ject_462000125/samantao-public/apps/suse-repo-deps/lib64:/pfs/lustrep2/projappl/project_462000125/samantao-public/apps/suse-repo-deps/usr/lib64:/opt/cray/pe/python/3.9.12.1/lib:/opt/cray/pe/gcc-libs:/opt/cray/libfabric/1.15.0.0/lib64
|
| 145 |
+
0: 2023-02-27 16:54:38.696063: 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/aws-ofi-rccl:/pfs/lustrep2/projappl/project_462000125/samantao-public/apps/rccl/rccl-develop-release/rccl/lib:/pfs/lustrep4/projappl/project_462000075/samantao-public/rocm/glibc/selected:/pfs/lustrep2/projappl/project_462000125/samantao-public/rocm/rocm-5.2.3/hip/lib:/pfs/lustrep2/projappl/project_462000125/samantao-public/rocm/rocm-5.2.3/hsa/lib:/pfs/lustrep2/projappl/project_462000125/samantao-public/rocm/rocm-5.2.3/llvm/lib:/pfs/lustrep2/projappl/project_462000125/samantao-public/rocm/rocm-5.2.3/lib:/pfs/lustrep2/projappl/project_462000125/samantao-public/rocm/rocm-5.2.3/lib64:/pfs/lustrep2/projappl/project_462000125/samantao-public/rocm/rocm-5.2.3/llvm:/pfs/lustrep2/projappl/pro
|
| 146 |
+
0: ject_462000125/samantao-public/apps/suse-repo-deps/lib64:/pfs/lustrep2/projappl/project_462000125/samantao-public/apps/suse-repo-deps/usr/lib64:/opt/cray/pe/python/3.9.12.1/lib:/opt/cray/pe/gcc-libs:/opt/cray/libfabric/1.15.0.0/lib64
|
| 147 |
+
0: 2023-02-27 16:54:38.696053: 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/aws-ofi-rccl:/pfs/lustrep2/projappl/project_462000125/samantao-public/apps/rccl/rccl-develop-release/rccl/lib:/pfs/lustrep4/projappl/project_462000075/samantao-public/rocm/glibc/selected:/pfs/lustrep2/projappl/project_462000125/samantao-public/rocm/rocm-5.2.3/hip/lib:/pfs/lustrep2/projappl/project_462000125/samantao-public/rocm/rocm-5.2.3/hsa/lib:/pfs/lustrep2/projappl/project_462000125/samantao-public/rocm/rocm-5.2.3/llvm/lib:/pfs/lustrep2/projappl/project_462000125/samantao-public/rocm/rocm-5.2.3/lib:/pfs/lustrep2/projappl/project_462000125/samantao-public/rocm/rocm-5.2.3/lib64:/pfs/lustrep2/projappl/project_462000125/samantao-public/rocm/rocm-5.2.3/llvm:/pfs/lustrep2/projappl/pro
|
| 148 |
+
0: ject_462000125/samantao-public/apps/suse-repo-deps/lib64:/pfs/lustrep2/projappl/project_462000125/samantao-public/apps/suse-repo-deps/usr/lib64:/opt/cray/pe/python/3.9.12.1/lib:/opt/cray/pe/gcc-libs:/opt/cray/libfabric/1.15.0.0/lib64
|
| 149 |
+
0: 2023-02-27 16:54:38.696074: 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.
|
| 150 |
+
0: 2023-02-27 16:54:38.696075: 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.
|
| 151 |
+
0: 2023-02-27 16:54:38.696076: 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.
|
| 152 |
+
0: 2023-02-27 16:54:38.696077: 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.
|
| 153 |
+
0: 2023-02-27 16:54:38.696078: 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.
|
| 154 |
+
0: 2023-02-27 16:54:38.696079: 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.
|
| 155 |
+
0: 2023-02-27 16:54:38.696259: 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/aws-ofi-rccl:/pfs/lustrep2/projappl/project_462000125/samantao-public/apps/rccl/rccl-develop-release/rccl/lib:/pfs/lustrep4/projappl/project_462000075/samantao-public/rocm/glibc/selected:/pfs/lustrep2/projappl/project_462000125/samantao-public/rocm/rocm-5.2.3/hip/lib:/pfs/lustrep2/projappl/project_462000125/samantao-public/rocm/rocm-5.2.3/hsa/lib:/pfs/lustrep2/projappl/project_462000125/samantao-public/rocm/rocm-5.2.3/llvm/lib:/pfs/lustrep2/projappl/project_462000125/samantao-public/rocm/rocm-5.2.3/lib:/pfs/lustrep2/projappl/project_462000125/samantao-public/rocm/rocm-5.2.3/lib64:/pfs/lustrep2/projappl/project_462000125/samantao-public/rocm/rocm-5.2.3/llvm:/pfs/lustrep2/projappl/pro
|
| 156 |
+
0: ject_462000125/samantao-public/apps/suse-repo-deps/lib64:/pfs/lustrep2/projappl/project_462000125/samantao-public/apps/suse-repo-deps/usr/lib64:/opt/cray/pe/python/3.9.12.1/lib:/opt/cray/pe/gcc-libs:/opt/cray/libfabric/1.15.0.0/lib64
|
| 157 |
+
0: 2023-02-27 16:54:38.696259: 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/aws-ofi-rccl:/pfs/lustrep2/projappl/project_462000125/samantao-public/apps/rccl/rccl-develop-release/rccl/lib:/pfs/lustrep4/projappl/project_462000075/samantao-public/rocm/glibc/selected:/pfs/lustrep2/projappl/project_462000125/samantao-public/rocm/rocm-5.2.3/hip/lib:/pfs/lustrep2/projappl/project_462000125/samantao-public/rocm/rocm-5.2.3/hsa/lib:/pfs/lustrep2/projappl/project_462000125/samantao-public/rocm/rocm-5.2.3/llvm/lib:/pfs/lustrep2/projappl/project_462000125/samantao-public/rocm/rocm-5.2.3/lib:/pfs/lustrep2/projappl/project_462000125/samantao-public/rocm/rocm-5.2.3/lib64:/pfs/lustrep2/projappl/project_462000125/samantao-public/rocm/rocm-5.2.3/llvm:/pfs/lustrep2/projappl/pro
|
| 158 |
+
0: ject_462000125/samantao-public/apps/suse-repo-deps/lib64:/pfs/lustrep2/projappl/project_462000125/samantao-public/apps/suse-repo-deps/usr/lib64:/opt/cray/pe/python/3.9.12.1/lib:/opt/cray/pe/gcc-libs:/opt/cray/libfabric/1.15.0.0/lib64
|
| 159 |
+
0: 2023-02-27 16:54:38.696278: 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.
|
| 160 |
+
0: 2023-02-27 16:54:38.696278: 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.
|
| 161 |
+
0: Loading extension module scaled_upper_triang_masked_softmax_cuda...
|
| 162 |
+
0: [92mSuccessfully preprocessed all matching files.[0m
|
| 163 |
+
0: Detected CUDA files, patching ldflags
|
| 164 |
+
0: Emitting ninja build file /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/build/build.ninja...
|
| 165 |
+
0: Building extension module scaled_masked_softmax_cuda...
|
| 166 |
+
0: Allowing ninja to set a default number of workers... (overridable by setting the environment variable MAX_JOBS=N)
|
| 167 |
+
0: Loading extension module scaled_masked_softmax_cuda...
|
| 168 |
+
0: [92mSuccessfully preprocessed all matching files.[0m
|
| 169 |
+
0: Detected CUDA files, patching ldflags
|
| 170 |
+
0: Emitting ninja build file /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/build/build.ninja...
|
| 171 |
+
0: Building extension module fused_mix_prec_layer_norm_cuda...
|
| 172 |
+
0: Allowing ninja to set a default number of workers... (overridable by setting the environment variable MAX_JOBS=N)
|
| 173 |
+
0: Loading extension module fused_mix_prec_layer_norm_cuda...
|
| 174 |
+
0: [92mSuccessfully preprocessed all matching files.[0m
|
| 175 |
+
0: [92mSuccessfully preprocessed all matching files.[0m
|
| 176 |
+
0: [92mSuccessfully preprocessed all matching files.[0m
|
| 177 |
+
0: [92mSuccessfully preprocessed all matching files.[0m
|
| 178 |
+
0: [92mSuccessfully preprocessed all matching files.[0m
|
| 179 |
+
1: [92mSuccessfully preprocessed all matching files.[0m
|
| 180 |
+
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
|
| 181 |
+
1: warnings.warn(
|
| 182 |
+
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
|
| 183 |
+
1: warnings.warn(
|
| 184 |
+
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
|
| 185 |
+
1: warnings.warn(
|
| 186 |
+
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
|
| 187 |
+
0: warnings.warn(
|
| 188 |
+
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
|
| 189 |
+
0: warnings.warn(
|
| 190 |
+
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
|
| 191 |
+
1: warnings.warn(
|
| 192 |
+
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
|
| 193 |
+
1: warnings.warn(
|
| 194 |
+
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
|
| 195 |
+
0: warnings.warn(
|
| 196 |
+
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
|
| 197 |
+
0: warnings.warn(
|
| 198 |
+
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
|
| 199 |
+
0: warnings.warn(
|
| 200 |
+
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
|
| 201 |
+
1: warnings.warn(
|
| 202 |
+
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
|
| 203 |
+
1: warnings.warn(
|
| 204 |
+
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
|
| 205 |
+
0: warnings.warn(
|
| 206 |
+
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
|
| 207 |
+
0: warnings.warn(
|
| 208 |
+
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
|
| 209 |
+
1: warnings.warn(
|
| 210 |
+
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
|
| 211 |
+
0: warnings.warn(
|
| 212 |
+
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...
|
| 213 |
+
0:
|
| 214 |
+
0:
|
| 215 |
+
0:
|
| 216 |
+
0: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...
|
| 217 |
+
0: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...
|
| 218 |
+
0: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...
|
| 219 |
+
1: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...
|
| 220 |
+
1: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...
|
| 221 |
+
1: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...
|
| 222 |
+
1: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...
|
| 223 |
+
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...
|
| 224 |
+
1:
|
| 225 |
+
1: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...
|
| 226 |
+
1: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...
|
| 227 |
+
0: Loading extension module utils...
|
| 228 |
+
0: Loading extension module utils...
|
| 229 |
+
0: Loading extension module utils...
|
| 230 |
+
0: Loading extension module utils...
|
| 231 |
+
0: Loading extension module utils...
|
| 232 |
+
1: Loading extension module utils...
|
| 233 |
+
0: Loading extension module utils...
|
| 234 |
+
1: Loading extension module utils...
|
| 235 |
+
0: Loading extension module utils...
|
| 236 |
+
1: Loading extension module utils...
|
| 237 |
+
1: Loading extension module utils...
|
| 238 |
+
1: Loading extension module utils...
|
| 239 |
+
1: Loading extension module utils...
|
| 240 |
+
1: Loading extension module utils...
|
| 241 |
+
1: Loading extension module utils...
|
| 242 |
+
0: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...
|
| 243 |
+
1: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...
|
| 244 |
+
1: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...
|
| 245 |
+
1: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...
|
| 246 |
+
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...
|
| 247 |
+
1:
|
| 248 |
+
1: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...
|
| 249 |
+
1: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...
|
| 250 |
+
1: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...
|
| 251 |
+
1: No modifications detected for re-loaded extension module utils, skipping build step...
|
| 252 |
+
1: Loading extension module utils...
|
| 253 |
+
1: No modifications detected for re-loaded extension module utils, skipping build step...
|
| 254 |
+
1: Loading extension module utils...
|
| 255 |
+
1: No modifications detected for re-loaded extension module utils, skipping build step...
|
| 256 |
+
1: Loading extension module utils...
|
| 257 |
+
1: No modifications detected for re-loaded extension module utils, skipping build step...
|
| 258 |
+
1: Loading extension module utils...
|
| 259 |
+
1: No modifications detected for re-loaded extension module utils, skipping build step...
|
| 260 |
+
1: Loading extension module utils...
|
| 261 |
+
1: No modifications detected for re-loaded extension module utils, skipping build step...
|
| 262 |
+
1: Loading extension module utils...
|
| 263 |
+
1: No modifications detected for re-loaded extension module utils, skipping build step...
|
| 264 |
+
1: Loading extension module utils...
|
| 265 |
+
1: No modifications detected for re-loaded extension module utils, skipping build step...
|
| 266 |
+
1: Loading extension module utils...
|
| 267 |
+
0: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...
|
| 268 |
+
0: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...
|
| 269 |
+
0: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...
|
| 270 |
+
0: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...
|
| 271 |
+
0: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...
|
| 272 |
+
0: No modifications detected for re-loaded extension module utils, skipping build step...
|
| 273 |
+
0: Loading extension module utils...
|
| 274 |
+
0: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...
|
| 275 |
+
0: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...No modifications detected for re-loaded extension module utils, skipping build step...
|
| 276 |
+
0:
|
| 277 |
+
0: No modifications detected for re-loaded extension module utils, skipping build step...Loading extension module utils...
|
| 278 |
+
0:
|
| 279 |
+
0: Loading extension module utils...
|
| 280 |
+
0: No modifications detected for re-loaded extension module utils, skipping build step...
|
| 281 |
+
0: Loading extension module utils...
|
| 282 |
+
0: No modifications detected for re-loaded extension module utils, skipping build step...
|
| 283 |
+
0: Loading extension module utils...
|
| 284 |
+
0: No modifications detected for re-loaded extension module utils, skipping build step...
|
| 285 |
+
0: Loading extension module utils...
|
| 286 |
+
0: No modifications detected for re-loaded extension module utils, skipping build step...
|
| 287 |
+
0: Loading extension module utils...
|
| 288 |
+
0: Emitting ninja build file /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu/utils/build.ninja...
|
| 289 |
+
0: Building extension module utils...
|
| 290 |
+
0: Allowing ninja to set a default number of workers... (overridable by setting the environment variable MAX_JOBS=N)
|
| 291 |
+
0: Loading extension module utils...
|
| 292 |
+
0: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...
|
| 293 |
+
0: No modifications detected for re-loaded extension module utils, skipping build step...
|
| 294 |
+
0: Loading extension module utils...
|
| 295 |
+
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
|
| 296 |
+
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")
|
196m1b51b5/logs/3163481.out
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
220m7b5100m/220m7b5100m/global_step14324/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b700d9e8c3fb763599a76f4dffc0e8dac67c1d0fedd238768d11b41cc3332462
|
| 3 |
+
size 41353495
|
220m7b5100m/220m7b5100m/global_step14324/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:dd08828deb441f02df16b49db102eb3a907572ad8c43b7a4e8a5f83a0e5e0f46
|
| 3 |
+
size 41353570
|
220m7b5100m/220m7b5100m/global_step14324/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8cf1b1fac07d2956c805dae27f5c8cdb1c811417f5d6206790f66f52224c5e71
|
| 3 |
+
size 41353570
|
220m7b5100m/220m7b5100m/global_step14324/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d98dd7f4095a0f448b024d00240118e16ccb93df7353cda273cda8e0db1be311
|
| 3 |
+
size 41353570
|
220m7b5100m/220m7b5100m/global_step14324/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fe2c15bbb4edec681c2d4a31c128eb79d3c1625654c3b34d4df3383df09dbc60
|
| 3 |
+
size 41353506
|
220m7b5100m/220m7b5100m/global_step14324/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fd4f49b312b68efdfc2658e41e8087441ffa8c9777af12fdf52c5433569f3ab3
|
| 3 |
+
size 41353506
|
220m7b5100m/220m7b5100m/global_step14324/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d0bb1a14c089d1aadb2427b15c23456988fed1d267cc43b68249b59e95ed40c1
|
| 3 |
+
size 41353506
|
220m7b5100m/220m7b5100m/global_step14324/bf16_zero_pp_rank_16_mp_rank_00_optim_states.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:98c09f2339c6ee54a899f2d3edf3da11155223f5909c15f414345967f2af43e8
|
| 3 |
+
size 41353442
|
220m7b5100m/220m7b5100m/global_step14324/bf16_zero_pp_rank_17_mp_rank_00_optim_states.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9df76eda6d55a14d3eaba25888d5b173846e1a05a0f1137442b0fa1c09f27fdf
|
| 3 |
+
size 41353570
|
220m7b5100m/220m7b5100m/global_step14324/bf16_zero_pp_rank_18_mp_rank_00_optim_states.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6317ddb686f1e2c95b20eebe3d1fe369925841ed64198deaba2789e5a39525fc
|
| 3 |
+
size 41353570
|
220m7b5100m/220m7b5100m/global_step14324/bf16_zero_pp_rank_19_mp_rank_00_optim_states.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9a1597b6172e7791ce68e1d35bba68a3f45bfd38ea224b8ddc7e5e8bfc9e426d
|
| 3 |
+
size 41353570
|
220m7b5100m/220m7b5100m/global_step14324/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d468b36545af136a44681c1f1a14f5df38a04da00e5da2a40a790c833c3651d6
|
| 3 |
+
size 41353559
|
220m7b5100m/220m7b5100m/global_step14324/bf16_zero_pp_rank_20_mp_rank_00_optim_states.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ecee3fffa5d6cb012fa258a044f3a76743b9644bcaa661e0c8e54258368c5eab
|
| 3 |
+
size 41353506
|
220m7b5100m/220m7b5100m/global_step14324/bf16_zero_pp_rank_21_mp_rank_00_optim_states.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:eaeeef2cac51e12401ef9a41185966287d14156d44eb33a6306fb78379453429
|
| 3 |
+
size 41353506
|
220m7b5100m/220m7b5100m/global_step14324/bf16_zero_pp_rank_22_mp_rank_00_optim_states.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7ff9bbab62fa73c74caa8286e893dd9a57c47441e4fd23a8f92ece921b4b8154
|
| 3 |
+
size 41353634
|
220m7b5100m/220m7b5100m/global_step14324/bf16_zero_pp_rank_23_mp_rank_00_optim_states.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e123cfe4cdbd96ae5b300de08e90d1e4af8d817e95d572d628342ffe5fab9bf3
|
| 3 |
+
size 41353570
|
220m7b5100m/220m7b5100m/global_step14324/bf16_zero_pp_rank_24_mp_rank_00_optim_states.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9c6c10ebc7a98c9aa919c2e89501370b6620d9a468d7d5cc6ebebbaf61fae3a2
|
| 3 |
+
size 41353698
|
220m7b5100m/220m7b5100m/global_step14324/bf16_zero_pp_rank_25_mp_rank_00_optim_states.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bbb319f6301c9a95a9a0e83b4ab7e336781504bc5c0d19e5b8f5c583b425c8ef
|
| 3 |
+
size 41353506
|
220m7b5100m/220m7b5100m/global_step14324/bf16_zero_pp_rank_26_mp_rank_00_optim_states.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:70524938159e804936b29685bcb55650d957f821abc8740bc647e91ac01ead4a
|
| 3 |
+
size 41353634
|
220m7b5100m/220m7b5100m/global_step14324/bf16_zero_pp_rank_27_mp_rank_00_optim_states.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:696edce95aa919212279ea871995253889200aa9761b53bbadd9431096ed2dfa
|
| 3 |
+
size 41353506
|
220m7b5100m/220m7b5100m/global_step14324/bf16_zero_pp_rank_28_mp_rank_00_optim_states.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:19245be9b3d61ac93c5f07dbf8807c838287ca0354b5876fddced3660267845f
|
| 3 |
+
size 41353570
|
220m7b5100m/220m7b5100m/global_step14324/bf16_zero_pp_rank_29_mp_rank_00_optim_states.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:60cc86850e984ba633f3ce0f11b568464ce9ab03faa416a11c35ac4daacfdb74
|
| 3 |
+
size 41353634
|
220m7b5100m/220m7b5100m/global_step14324/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1431ed974a333c6d17ff184e82f2d6b4691787882054fa1181f84aef7f345eed
|
| 3 |
+
size 41353495
|
220m7b5100m/220m7b5100m/global_step14324/bf16_zero_pp_rank_30_mp_rank_00_optim_states.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a196b427e21476eb3b31f0ec8b0b5ace4aa4d3a925c4d6ed3df10c54a64527f3
|
| 3 |
+
size 41353570
|
220m7b5100m/220m7b5100m/global_step14324/bf16_zero_pp_rank_31_mp_rank_00_optim_states.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f828bb9a5ed9eaafcfe686872b136dec57e8908e838db0b21bd93312a547d602
|
| 3 |
+
size 41353506
|
220m7b5100m/220m7b5100m/global_step14324/bf16_zero_pp_rank_32_mp_rank_00_optim_states.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:080c511a16b6412b9d2e509b64eae5e11f00800bbcf8d20419bf50be4dfd2fa5
|
| 3 |
+
size 41353506
|
220m7b5100m/220m7b5100m/global_step14324/bf16_zero_pp_rank_33_mp_rank_00_optim_states.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3e2f45d2a9d6968498a73375ed1555a06ce866ff5d75abeec62c7ecb83f29b8f
|
| 3 |
+
size 41353698
|
220m7b5100m/220m7b5100m/global_step14324/bf16_zero_pp_rank_34_mp_rank_00_optim_states.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f0ed1f72820d440fdcb8ff111ab01e0d40df10dddb427c73d720c44b99551e4c
|
| 3 |
+
size 41353506
|
220m7b5100m/220m7b5100m/global_step14324/bf16_zero_pp_rank_35_mp_rank_00_optim_states.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d42e69f06f274e7d4d2367d101d3677efa6122f2074733bc3fc71a1878a93dfa
|
| 3 |
+
size 41353570
|
220m7b5100m/220m7b5100m/global_step14324/bf16_zero_pp_rank_36_mp_rank_00_optim_states.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f8b662b467dda49c027913e4611e82c86efaabe90ee477ed4edb709587afedee
|
| 3 |
+
size 41353570
|
220m7b5100m/220m7b5100m/global_step14324/bf16_zero_pp_rank_37_mp_rank_00_optim_states.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c535a5dabe5c8da6163cc5c875bee03400a7d7b0f905af51c5844b26edf4d2f8
|
| 3 |
+
size 41353570
|
220m7b5100m/220m7b5100m/global_step14324/bf16_zero_pp_rank_38_mp_rank_00_optim_states.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8b0a57ff2ce5efbd4ea53ad807d2c34514eae98f57cd2da4aa38180a7a25d0b3
|
| 3 |
+
size 41353698
|
220m7b5100m/220m7b5100m/global_step14324/bf16_zero_pp_rank_39_mp_rank_00_optim_states.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bd87a2c7a041ca62db181127266956128681adb0f05a1cbe228d152164d20b7b
|
| 3 |
+
size 41353442
|
220m7b5100m/220m7b5100m/global_step14324/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c3926c2d27c24bd08f7b9e1b9549290acecca404f9d56addd7e94461d0d98b05
|
| 3 |
+
size 41353495
|
220m7b5100m/220m7b5100m/global_step14324/bf16_zero_pp_rank_40_mp_rank_00_optim_states.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cfcfac2a0a9f60eb82c64a0a7c86774050bb6db30143f1d66b2af4c7bf0c2210
|
| 3 |
+
size 41353634
|
220m7b5100m/220m7b5100m/global_step14324/bf16_zero_pp_rank_41_mp_rank_00_optim_states.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e326ec462dabcbf9ad28b2ec11d95e2313653123bfd487d61ac5a69bcb06697f
|
| 3 |
+
size 41353506
|
220m7b5100m/220m7b5100m/global_step14324/bf16_zero_pp_rank_42_mp_rank_00_optim_states.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b25fe97f3ca6427f9605a674ffec1d14e39d78d1f0fd02e2bfe3cff25092d6d6
|
| 3 |
+
size 41353570
|
220m7b5100m/220m7b5100m/global_step14324/bf16_zero_pp_rank_43_mp_rank_00_optim_states.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6b705b40f4eb70cc6cea2e456f8d7adc1ecd4b430cb6e0333eb0f459de65eb00
|
| 3 |
+
size 41353698
|
220m7b5100m/220m7b5100m/global_step14324/bf16_zero_pp_rank_44_mp_rank_00_optim_states.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:aca00643528be831418af6e7d56f696ad6845fa59cc8e3780f37be06a658c72e
|
| 3 |
+
size 41353506
|
220m7b5100m/220m7b5100m/global_step14324/bf16_zero_pp_rank_45_mp_rank_00_optim_states.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7812f8b3eb0f283ed463ccfb8e44d1c13530ed1aac79080c3dc9d90c6721b577
|
| 3 |
+
size 41353634
|
220m7b5100m/220m7b5100m/global_step14324/bf16_zero_pp_rank_46_mp_rank_00_optim_states.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8b4b41a293186232e9d8a31af9be79f1dfeca79a2653278a7962ce6e70d8346c
|
| 3 |
+
size 41353570
|
220m7b5100m/220m7b5100m/global_step14324/bf16_zero_pp_rank_47_mp_rank_00_optim_states.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2d6be44dfc8f89e8c5b7b6f9a4a1f8772b4a002f062d5b05d7cbdcd5658b76b1
|
| 3 |
+
size 41353634
|
220m7b5100m/220m7b5100m/global_step14324/bf16_zero_pp_rank_48_mp_rank_00_optim_states.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:89686cdb7959d3ea674cd33a167dcbc3ebaeadb33a6dff97e8adb3682e6a1474
|
| 3 |
+
size 41353378
|
220m7b5100m/220m7b5100m/global_step14324/bf16_zero_pp_rank_49_mp_rank_00_optim_states.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8d2c3069f6a539feca63db22943cf1cc8debf7d18ef1051b11d3ca1f863d7400
|
| 3 |
+
size 41353634
|
220m7b5100m/220m7b5100m/global_step14324/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6929d412564c8903ed6186fffd84879cda3f85310aefdaa502d172cc25c66d1b
|
| 3 |
+
size 41353559
|
220m7b5100m/220m7b5100m/global_step14324/bf16_zero_pp_rank_50_mp_rank_00_optim_states.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3f27e074d95e87cd2429043076bdc04a93b534f26f14baf643b41d5f6317ad43
|
| 3 |
+
size 41353570
|
220m7b5100m/220m7b5100m/global_step14324/bf16_zero_pp_rank_51_mp_rank_00_optim_states.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2e8677cfdb5f726bbab143e4c0adc7819ecb0a2ce09691c2ff999d6291b35389
|
| 3 |
+
size 41353570
|
220m7b5100m/220m7b5100m/global_step14324/bf16_zero_pp_rank_52_mp_rank_00_optim_states.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:77df396d524a91e8fc337b94cefb048e58a2b2b580916fd6ff475d43edf84592
|
| 3 |
+
size 41353634
|