Commit
·
c35407a
1
Parent(s):
a9b07d2
Fix
Browse filesThis view is limited to 50 files because it contains too many changes.
See raw diff
- 7m100m100m/3571584.err +257 -0
- 7m100m100m/3571584.out +0 -0
- 7m100m100m/global_step190/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt +2 -2
- 7m100m100m/global_step190/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt +2 -2
- 7m100m100m/global_step190/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt +2 -2
- 7m100m100m/global_step190/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt +2 -2
- 7m100m100m/global_step190/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt +2 -2
- 7m100m100m/global_step190/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt +2 -2
- 7m100m100m/global_step190/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt +2 -2
- 7m100m100m/global_step190/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt +2 -2
- 7m100m100m/global_step190/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt +2 -2
- 7m100m100m/global_step190/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt +2 -2
- 7m100m100m/global_step190/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt +2 -2
- 7m100m100m/global_step190/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt +2 -2
- 7m100m100m/global_step190/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt +2 -2
- 7m100m100m/global_step190/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt +2 -2
- 7m100m100m/global_step190/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt +2 -2
- 7m100m100m/global_step190/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt +2 -2
- 7m100m100m/global_step190/layer_01-model_00-model_states.pt +1 -1
- 7m100m100m/global_step190/layer_03-model_00-model_states.pt +2 -2
- 7m100m100m/global_step190/layer_04-model_00-model_states.pt +2 -2
- 7m100m100m/global_step190/layer_05-model_00-model_states.pt +2 -2
- 7m100m100m/global_step190/layer_07-model_00-model_states.pt +1 -1
- 7m100m100m/global_step190/mp_rank_00_model_states.pt +1 -1
- 7m100m100m/{eval.txt → old/eval.txt} +0 -0
- 7m100m100m/old/global_step190/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt +3 -0
- 7m100m100m/old/global_step190/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt +3 -0
- 7m100m100m/old/global_step190/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt +3 -0
- 7m100m100m/old/global_step190/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt +3 -0
- 7m100m100m/old/global_step190/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt +3 -0
- 7m100m100m/old/global_step190/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt +3 -0
- 7m100m100m/old/global_step190/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt +3 -0
- 7m100m100m/old/global_step190/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt +3 -0
- 7m100m100m/old/global_step190/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt +3 -0
- 7m100m100m/old/global_step190/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt +3 -0
- 7m100m100m/old/global_step190/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt +3 -0
- 7m100m100m/old/global_step190/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt +3 -0
- 7m100m100m/old/global_step190/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt +3 -0
- 7m100m100m/old/global_step190/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt +3 -0
- 7m100m100m/old/global_step190/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt +3 -0
- 7m100m100m/old/global_step190/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt +3 -0
- 7m100m100m/old/global_step190/layer_01-model_00-model_states.pt +3 -0
- 7m100m100m/old/global_step190/layer_03-model_00-model_states.pt +3 -0
- 7m100m100m/old/global_step190/layer_04-model_00-model_states.pt +3 -0
- 7m100m100m/old/global_step190/layer_05-model_00-model_states.pt +3 -0
- 7m100m100m/old/global_step190/layer_07-model_00-model_states.pt +3 -0
- 7m100m100m/old/global_step190/mp_rank_00_model_states.pt +3 -0
- 7m100m100m/{logs → old/logs}/3163410.err +0 -0
- 7m100m100m/{logs → old/logs}/3163410.out +0 -0
- 7m100m100m/{tensorboard_7m100m100m → old/tensorboard_7m100m100m}/events.out.tfevents.1677508396.nid006608.48416.0 +0 -0
7m100m100m/3571584.err
ADDED
|
@@ -0,0 +1,257 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
1: 2023-05-23 21:56:55.656035: I tensorflow/core/platform/cpu_feature_guard.cc:193] This TensorFlow binary is optimized with oneAPI Deep Neural Network Library (oneDNN) to use the following CPU instructions in performance-critical operations: AVX2 FMA
|
| 2 |
+
1: To enable them in other operations, rebuild TensorFlow with the appropriate compiler flags.
|
| 3 |
+
1: 2023-05-23 21:56:55.656030: I tensorflow/core/platform/cpu_feature_guard.cc:193] This TensorFlow binary is optimized with oneAPI Deep Neural Network Library (oneDNN) to use the following CPU instructions in performance-critical operations: AVX2 FMA
|
| 4 |
+
1: To enable them in other operations, rebuild TensorFlow with the appropriate compiler flags.
|
| 5 |
+
1: 2023-05-23 21:56:55.656064: I tensorflow/core/platform/cpu_feature_guard.cc:193] This TensorFlow binary is optimized with oneAPI Deep Neural Network Library (oneDNN) to use the following CPU instructions in performance-critical operations: AVX2 FMA
|
| 6 |
+
1: To enable them in other operations, rebuild TensorFlow with the appropriate compiler flags.
|
| 7 |
+
1: 2023-05-23 21:56:55.656075: I tensorflow/core/platform/cpu_feature_guard.cc:193] This TensorFlow binary is optimized with oneAPI Deep Neural Network Library (oneDNN) to use the following CPU instructions in performance-critical operations: AVX2 FMA
|
| 8 |
+
1: To enable them in other operations, rebuild TensorFlow with the appropriate compiler flags.
|
| 9 |
+
1: 2023-05-23 21:56:55.656074: I tensorflow/core/platform/cpu_feature_guard.cc:193] This TensorFlow binary is optimized with oneAPI Deep Neural Network Library (oneDNN) to use the following CPU instructions in performance-critical operations: AVX2 FMA
|
| 10 |
+
1: To enable them in other operations, rebuild TensorFlow with the appropriate compiler flags.
|
| 11 |
+
1: 2023-05-23 21:56:55.656059: I tensorflow/core/platform/cpu_feature_guard.cc:193] This TensorFlow binary is optimized with oneAPI Deep Neural Network Library (oneDNN) to use the following CPU instructions in performance-critical operations: AVX2 FMA
|
| 12 |
+
1: To enable them in other operations, rebuild TensorFlow with the appropriate compiler flags.
|
| 13 |
+
1: 2023-05-23 21:56:55.656082: I tensorflow/core/platform/cpu_feature_guard.cc:193] This TensorFlow binary is optimized with oneAPI Deep Neural Network Library (oneDNN) to use the following CPU instructions in performance-critical operations: AVX2 FMA
|
| 14 |
+
1: To enable them in other operations, rebuild TensorFlow with the appropriate compiler flags.
|
| 15 |
+
1: 2023-05-23 21:56:55.656101: I tensorflow/core/platform/cpu_feature_guard.cc:193] This TensorFlow binary is optimized with oneAPI Deep Neural Network Library (oneDNN) to use the following CPU instructions in performance-critical operations: AVX2 FMA
|
| 16 |
+
1: To enable them in other operations, rebuild TensorFlow with the appropriate compiler flags.
|
| 17 |
+
0: 2023-05-23 21:56:55.657068: I tensorflow/core/platform/cpu_feature_guard.cc:193] This TensorFlow binary is optimized with oneAPI Deep Neural Network Library (oneDNN) to use the following CPU instructions in performance-critical operations: AVX2 FMA
|
| 18 |
+
0: To enable them in other operations, rebuild TensorFlow with the appropriate compiler flags.
|
| 19 |
+
0: 2023-05-23 21:56:55.657085: I tensorflow/core/platform/cpu_feature_guard.cc:193] This TensorFlow binary is optimized with oneAPI Deep Neural Network Library (oneDNN) to use the following CPU instructions in performance-critical operations: AVX2 FMA
|
| 20 |
+
0: To enable them in other operations, rebuild TensorFlow with the appropriate compiler flags.
|
| 21 |
+
0: 2023-05-23 21:56:55.657096: I tensorflow/core/platform/cpu_feature_guard.cc:193] This TensorFlow binary is optimized with oneAPI Deep Neural Network Library (oneDNN) to use the following CPU instructions in performance-critical operations: AVX2 FMA
|
| 22 |
+
0: To enable them in other operations, rebuild TensorFlow with the appropriate compiler flags.
|
| 23 |
+
0: 2023-05-23 21:56:55.657097: I tensorflow/core/platform/cpu_feature_guard.cc:193] This TensorFlow binary is optimized with oneAPI Deep Neural Network Library (oneDNN) to use the following CPU instructions in performance-critical operations: AVX2 FMA
|
| 24 |
+
0: To enable them in other operations, rebuild TensorFlow with the appropriate compiler flags.
|
| 25 |
+
0: 2023-05-23 21:56:55.657098: I tensorflow/core/platform/cpu_feature_guard.cc:193] This TensorFlow binary is optimized with oneAPI Deep Neural Network Library (oneDNN) to use the following CPU instructions in performance-critical operations: AVX2 FMA
|
| 26 |
+
0: To enable them in other operations, rebuild TensorFlow with the appropriate compiler flags.
|
| 27 |
+
0: 2023-05-23 21:56:55.657080: I tensorflow/core/platform/cpu_feature_guard.cc:193] This TensorFlow binary is optimized with oneAPI Deep Neural Network Library (oneDNN) to use the following CPU instructions in performance-critical operations: AVX2 FMA
|
| 28 |
+
0: To enable them in other operations, rebuild TensorFlow with the appropriate compiler flags.
|
| 29 |
+
0: 2023-05-23 21:56:55.657105: I tensorflow/core/platform/cpu_feature_guard.cc:193] This TensorFlow binary is optimized with oneAPI Deep Neural Network Library (oneDNN) to use the following CPU instructions in performance-critical operations: AVX2 FMA
|
| 30 |
+
0: To enable them in other operations, rebuild TensorFlow with the appropriate compiler flags.
|
| 31 |
+
0: 2023-05-23 21:56:55.657095: I tensorflow/core/platform/cpu_feature_guard.cc:193] This TensorFlow binary is optimized with oneAPI Deep Neural Network Library (oneDNN) to use the following CPU instructions in performance-critical operations: AVX2 FMA
|
| 32 |
+
0: To enable them in other operations, rebuild TensorFlow with the appropriate compiler flags.
|
| 33 |
+
0: 2023-05-23 21:56:58.533548: W tensorflow/compiler/xla/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'libcudart.so.11.0'; dlerror: libcudart.so.11.0: cannot open shared object file: No such file or directory; LD_LIBRARY_PATH: /pfs/lustrep2/projappl/project_462000125/samantao-public/apps-rocm-5.2.3/aws-ofi-rccl:/opt/rocm/lib64:/opt/rocm/lib:/opt/rocm/rocprofiler/lib:/opt/rocm/rocprofiler/tool:/opt/rocm/roctracer/lib:/opt/rocm/roctracer/tool:/opt/rocm/hip/lib:/opt/cray/pe/python/3.9.13.1/lib:/opt/cray/pe/gcc-libs:/opt/cray/libfabric/1.15.2.0/lib64
|
| 34 |
+
0: 2023-05-23 21:56:58.533560: W tensorflow/compiler/xla/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'libcudart.so.11.0'; dlerror: libcudart.so.11.0: cannot open shared object file: No such file or directory; LD_LIBRARY_PATH: /pfs/lustrep2/projappl/project_462000125/samantao-public/apps-rocm-5.2.3/aws-ofi-rccl:/opt/rocm/lib64:/opt/rocm/lib:/opt/rocm/rocprofiler/lib:/opt/rocm/rocprofiler/tool:/opt/rocm/roctracer/lib:/opt/rocm/roctracer/tool:/opt/rocm/hip/lib:/opt/cray/pe/python/3.9.13.1/lib:/opt/cray/pe/gcc-libs:/opt/cray/libfabric/1.15.2.0/lib64
|
| 35 |
+
1: 2023-05-23 21:56:58.533595: W tensorflow/compiler/xla/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'libcudart.so.11.0'; dlerror: libcudart.so.11.0: cannot open shared object file: No such file or directory; LD_LIBRARY_PATH: /pfs/lustrep2/projappl/project_462000125/samantao-public/apps-rocm-5.2.3/aws-ofi-rccl:/opt/rocm/lib64:/opt/rocm/lib:/opt/rocm/rocprofiler/lib:/opt/rocm/rocprofiler/tool:/opt/rocm/roctracer/lib:/opt/rocm/roctracer/tool:/opt/rocm/hip/lib:/opt/cray/pe/python/3.9.13.1/lib:/opt/cray/pe/gcc-libs:/opt/cray/libfabric/1.15.2.0/lib64
|
| 36 |
+
0: 2023-05-23 21:56:58.533563: W tensorflow/compiler/xla/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'libcudart.so.11.0'; dlerror: libcudart.so.11.0: cannot open shared object file: No such file or directory; LD_LIBRARY_PATH: /pfs/lustrep2/projappl/project_462000125/samantao-public/apps-rocm-5.2.3/aws-ofi-rccl:/opt/rocm/lib64:/opt/rocm/lib:/opt/rocm/rocprofiler/lib:/opt/rocm/rocprofiler/tool:/opt/rocm/roctracer/lib:/opt/rocm/roctracer/tool:/opt/rocm/hip/lib:/opt/cray/pe/python/3.9.13.1/lib:/opt/cray/pe/gcc-libs:/opt/cray/libfabric/1.15.2.0/lib64
|
| 37 |
+
1: 2023-05-23 21:56:58.533593: W tensorflow/compiler/xla/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'libcudart.so.11.0'; dlerror: libcudart.so.11.0: cannot open shared object file: No such file or directory; LD_LIBRARY_PATH: /pfs/lustrep2/projappl/project_462000125/samantao-public/apps-rocm-5.2.3/aws-ofi-rccl:/opt/rocm/lib64:/opt/rocm/lib:/opt/rocm/rocprofiler/lib:/opt/rocm/rocprofiler/tool:/opt/rocm/roctracer/lib:/opt/rocm/roctracer/tool:/opt/rocm/hip/lib:/opt/cray/pe/python/3.9.13.1/lib:/opt/cray/pe/gcc-libs:/opt/cray/libfabric/1.15.2.0/lib64
|
| 38 |
+
0: 2023-05-23 21:56:58.533556: W tensorflow/compiler/xla/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'libcudart.so.11.0'; dlerror: libcudart.so.11.0: cannot open shared object file: No such file or directory; LD_LIBRARY_PATH: /pfs/lustrep2/projappl/project_462000125/samantao-public/apps-rocm-5.2.3/aws-ofi-rccl:/opt/rocm/lib64:/opt/rocm/lib:/opt/rocm/rocprofiler/lib:/opt/rocm/rocprofiler/tool:/opt/rocm/roctracer/lib:/opt/rocm/roctracer/tool:/opt/rocm/hip/lib:/opt/cray/pe/python/3.9.13.1/lib:/opt/cray/pe/gcc-libs:/opt/cray/libfabric/1.15.2.0/lib64
|
| 39 |
+
1: 2023-05-23 21:56:58.533602: W tensorflow/compiler/xla/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'libcudart.so.11.0'; dlerror: libcudart.so.11.0: cannot open shared object file: No such file or directory; LD_LIBRARY_PATH: /pfs/lustrep2/projappl/project_462000125/samantao-public/apps-rocm-5.2.3/aws-ofi-rccl:/opt/rocm/lib64:/opt/rocm/lib:/opt/rocm/rocprofiler/lib:/opt/rocm/rocprofiler/tool:/opt/rocm/roctracer/lib:/opt/rocm/roctracer/tool:/opt/rocm/hip/lib:/opt/cray/pe/python/3.9.13.1/lib:/opt/cray/pe/gcc-libs:/opt/cray/libfabric/1.15.2.0/lib64
|
| 40 |
+
0: 2023-05-23 21:56:58.533567: W tensorflow/compiler/xla/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'libcudart.so.11.0'; dlerror: libcudart.so.11.0: cannot open shared object file: No such file or directory; LD_LIBRARY_PATH: /pfs/lustrep2/projappl/project_462000125/samantao-public/apps-rocm-5.2.3/aws-ofi-rccl:/opt/rocm/lib64:/opt/rocm/lib:/opt/rocm/rocprofiler/lib:/opt/rocm/rocprofiler/tool:/opt/rocm/roctracer/lib:/opt/rocm/roctracer/tool:/opt/rocm/hip/lib:/opt/cray/pe/python/3.9.13.1/lib:/opt/cray/pe/gcc-libs:/opt/cray/libfabric/1.15.2.0/lib64
|
| 41 |
+
1: 2023-05-23 21:56:58.533610: W tensorflow/compiler/xla/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'libcudart.so.11.0'; dlerror: libcudart.so.11.0: cannot open shared object file: No such file or directory; LD_LIBRARY_PATH: /pfs/lustrep2/projappl/project_462000125/samantao-public/apps-rocm-5.2.3/aws-ofi-rccl:/opt/rocm/lib64:/opt/rocm/lib:/opt/rocm/rocprofiler/lib:/opt/rocm/rocprofiler/tool:/opt/rocm/roctracer/lib:/opt/rocm/roctracer/tool:/opt/rocm/hip/lib:/opt/cray/pe/python/3.9.13.1/lib:/opt/cray/pe/gcc-libs:/opt/cray/libfabric/1.15.2.0/lib64
|
| 42 |
+
0: 2023-05-23 21:56:58.533565: W tensorflow/compiler/xla/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'libcudart.so.11.0'; dlerror: libcudart.so.11.0: cannot open shared object file: No such file or directory; LD_LIBRARY_PATH: /pfs/lustrep2/projappl/project_462000125/samantao-public/apps-rocm-5.2.3/aws-ofi-rccl:/opt/rocm/lib64:/opt/rocm/lib:/opt/rocm/rocprofiler/lib:/opt/rocm/rocprofiler/tool:/opt/rocm/roctracer/lib:/opt/rocm/roctracer/tool:/opt/rocm/hip/lib:/opt/cray/pe/python/3.9.13.1/lib:/opt/cray/pe/gcc-libs:/opt/cray/libfabric/1.15.2.0/lib64
|
| 43 |
+
1: 2023-05-23 21:56:58.533607: W tensorflow/compiler/xla/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'libcudart.so.11.0'; dlerror: libcudart.so.11.0: cannot open shared object file: No such file or directory; LD_LIBRARY_PATH: /pfs/lustrep2/projappl/project_462000125/samantao-public/apps-rocm-5.2.3/aws-ofi-rccl:/opt/rocm/lib64:/opt/rocm/lib:/opt/rocm/rocprofiler/lib:/opt/rocm/rocprofiler/tool:/opt/rocm/roctracer/lib:/opt/rocm/roctracer/tool:/opt/rocm/hip/lib:/opt/cray/pe/python/3.9.13.1/lib:/opt/cray/pe/gcc-libs:/opt/cray/libfabric/1.15.2.0/lib64
|
| 44 |
+
0: 2023-05-23 21:56:58.533575: W tensorflow/compiler/xla/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'libcudart.so.11.0'; dlerror: libcudart.so.11.0: cannot open shared object file: No such file or directory; LD_LIBRARY_PATH: /pfs/lustrep2/projappl/project_462000125/samantao-public/apps-rocm-5.2.3/aws-ofi-rccl:/opt/rocm/lib64:/opt/rocm/lib:/opt/rocm/rocprofiler/lib:/opt/rocm/rocprofiler/tool:/opt/rocm/roctracer/lib:/opt/rocm/roctracer/tool:/opt/rocm/hip/lib:/opt/cray/pe/python/3.9.13.1/lib:/opt/cray/pe/gcc-libs:/opt/cray/libfabric/1.15.2.0/lib64
|
| 45 |
+
1: 2023-05-23 21:56:58.533609: W tensorflow/compiler/xla/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'libcudart.so.11.0'; dlerror: libcudart.so.11.0: cannot open shared object file: No such file or directory; LD_LIBRARY_PATH: /pfs/lustrep2/projappl/project_462000125/samantao-public/apps-rocm-5.2.3/aws-ofi-rccl:/opt/rocm/lib64:/opt/rocm/lib:/opt/rocm/rocprofiler/lib:/opt/rocm/rocprofiler/tool:/opt/rocm/roctracer/lib:/opt/rocm/roctracer/tool:/opt/rocm/hip/lib:/opt/cray/pe/python/3.9.13.1/lib:/opt/cray/pe/gcc-libs:/opt/cray/libfabric/1.15.2.0/lib64
|
| 46 |
+
0: 2023-05-23 21:56:58.533571: W tensorflow/compiler/xla/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'libcudart.so.11.0'; dlerror: libcudart.so.11.0: cannot open shared object file: No such file or directory; LD_LIBRARY_PATH: /pfs/lustrep2/projappl/project_462000125/samantao-public/apps-rocm-5.2.3/aws-ofi-rccl:/opt/rocm/lib64:/opt/rocm/lib:/opt/rocm/rocprofiler/lib:/opt/rocm/rocprofiler/tool:/opt/rocm/roctracer/lib:/opt/rocm/roctracer/tool:/opt/rocm/hip/lib:/opt/cray/pe/python/3.9.13.1/lib:/opt/cray/pe/gcc-libs:/opt/cray/libfabric/1.15.2.0/lib64
|
| 47 |
+
1: 2023-05-23 21:56:58.533607: W tensorflow/compiler/xla/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'libcudart.so.11.0'; dlerror: libcudart.so.11.0: cannot open shared object file: No such file or directory; LD_LIBRARY_PATH: /pfs/lustrep2/projappl/project_462000125/samantao-public/apps-rocm-5.2.3/aws-ofi-rccl:/opt/rocm/lib64:/opt/rocm/lib:/opt/rocm/rocprofiler/lib:/opt/rocm/rocprofiler/tool:/opt/rocm/roctracer/lib:/opt/rocm/roctracer/tool:/opt/rocm/hip/lib:/opt/cray/pe/python/3.9.13.1/lib:/opt/cray/pe/gcc-libs:/opt/cray/libfabric/1.15.2.0/lib64
|
| 48 |
+
1: 2023-05-23 21:56:58.533609: W tensorflow/compiler/xla/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'libcudart.so.11.0'; dlerror: libcudart.so.11.0: cannot open shared object file: No such file or directory; LD_LIBRARY_PATH: /pfs/lustrep2/projappl/project_462000125/samantao-public/apps-rocm-5.2.3/aws-ofi-rccl:/opt/rocm/lib64:/opt/rocm/lib:/opt/rocm/rocprofiler/lib:/opt/rocm/rocprofiler/tool:/opt/rocm/roctracer/lib:/opt/rocm/roctracer/tool:/opt/rocm/hip/lib:/opt/cray/pe/python/3.9.13.1/lib:/opt/cray/pe/gcc-libs:/opt/cray/libfabric/1.15.2.0/lib64
|
| 49 |
+
0: 2023-05-23 21:56:58.534433: I tensorflow/compiler/xla/stream_executor/cuda/cudart_stub.cc:29] Ignore above cudart dlerror if you do not have a GPU set up on your machine.
|
| 50 |
+
0: 2023-05-23 21:56:58.534441: I tensorflow/compiler/xla/stream_executor/cuda/cudart_stub.cc:29] Ignore above cudart dlerror if you do not have a GPU set up on your machine.
|
| 51 |
+
0: 2023-05-23 21:56:58.534446: I tensorflow/compiler/xla/stream_executor/cuda/cudart_stub.cc:29] Ignore above cudart dlerror if you do not have a GPU set up on your machine.
|
| 52 |
+
0: 2023-05-23 21:56:58.534449: I tensorflow/compiler/xla/stream_executor/cuda/cudart_stub.cc:29] Ignore above cudart dlerror if you do not have a GPU set up on your machine.
|
| 53 |
+
0: 2023-05-23 21:56:58.534449: I tensorflow/compiler/xla/stream_executor/cuda/cudart_stub.cc:29] Ignore above cudart dlerror if you do not have a GPU set up on your machine.
|
| 54 |
+
0: 2023-05-23 21:56:58.534449: I tensorflow/compiler/xla/stream_executor/cuda/cudart_stub.cc:29] Ignore above cudart dlerror if you do not have a GPU set up on your machine.
|
| 55 |
+
0: 2023-05-23 21:56:58.534450: I tensorflow/compiler/xla/stream_executor/cuda/cudart_stub.cc:29] Ignore above cudart dlerror if you do not have a GPU set up on your machine.
|
| 56 |
+
0: 2023-05-23 21:56:58.534455: I tensorflow/compiler/xla/stream_executor/cuda/cudart_stub.cc:29] Ignore above cudart dlerror if you do not have a GPU set up on your machine.
|
| 57 |
+
1: 2023-05-23 21:56:58.534454: I tensorflow/compiler/xla/stream_executor/cuda/cudart_stub.cc:29] Ignore above cudart dlerror if you do not have a GPU set up on your machine.
|
| 58 |
+
1: 2023-05-23 21:56:58.534458: I tensorflow/compiler/xla/stream_executor/cuda/cudart_stub.cc:29] Ignore above cudart dlerror if you do not have a GPU set up on your machine.
|
| 59 |
+
1: 2023-05-23 21:56:58.534464: I tensorflow/compiler/xla/stream_executor/cuda/cudart_stub.cc:29] Ignore above cudart dlerror if you do not have a GPU set up on your machine.
|
| 60 |
+
1: 2023-05-23 21:56:58.534466: I tensorflow/compiler/xla/stream_executor/cuda/cudart_stub.cc:29] Ignore above cudart dlerror if you do not have a GPU set up on your machine.
|
| 61 |
+
1: 2023-05-23 21:56:58.534470: I tensorflow/compiler/xla/stream_executor/cuda/cudart_stub.cc:29] Ignore above cudart dlerror if you do not have a GPU set up on your machine.
|
| 62 |
+
1: 2023-05-23 21:56:58.534473: I tensorflow/compiler/xla/stream_executor/cuda/cudart_stub.cc:29] Ignore above cudart dlerror if you do not have a GPU set up on your machine.
|
| 63 |
+
1: 2023-05-23 21:56:58.534475: I tensorflow/compiler/xla/stream_executor/cuda/cudart_stub.cc:29] Ignore above cudart dlerror if you do not have a GPU set up on your machine.
|
| 64 |
+
1: 2023-05-23 21:56:58.534477: I tensorflow/compiler/xla/stream_executor/cuda/cudart_stub.cc:29] Ignore above cudart dlerror if you do not have a GPU set up on your machine.
|
| 65 |
+
0: 2023-05-23 21:57:04.859797: W tensorflow/compiler/xla/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'libnvinfer.so.7'; dlerror: libnvinfer.so.7: cannot open shared object file: No such file or directory; LD_LIBRARY_PATH: /pfs/lustrep2/projappl/project_462000125/samantao-public/apps-rocm-5.2.3/aws-ofi-rccl:/opt/rocm/lib64:/opt/rocm/lib:/opt/rocm/rocprofiler/lib:/opt/rocm/rocprofiler/tool:/opt/rocm/roctracer/lib:/opt/rocm/roctracer/tool:/opt/rocm/hip/lib:/opt/cray/pe/python/3.9.13.1/lib:/opt/cray/pe/gcc-libs:/opt/cray/libfabric/1.15.2.0/lib64
|
| 66 |
+
0: 2023-05-23 21:57:04.859806: W tensorflow/compiler/xla/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'libnvinfer.so.7'; dlerror: libnvinfer.so.7: cannot open shared object file: No such file or directory; LD_LIBRARY_PATH: /pfs/lustrep2/projappl/project_462000125/samantao-public/apps-rocm-5.2.3/aws-ofi-rccl:/opt/rocm/lib64:/opt/rocm/lib:/opt/rocm/rocprofiler/lib:/opt/rocm/rocprofiler/tool:/opt/rocm/roctracer/lib:/opt/rocm/roctracer/tool:/opt/rocm/hip/lib:/opt/cray/pe/python/3.9.13.1/lib:/opt/cray/pe/gcc-libs:/opt/cray/libfabric/1.15.2.0/lib64
|
| 67 |
+
0: 2023-05-23 21:57:04.859808: W tensorflow/compiler/xla/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'libnvinfer.so.7'; dlerror: libnvinfer.so.7: cannot open shared object file: No such file or directory; LD_LIBRARY_PATH: /pfs/lustrep2/projappl/project_462000125/samantao-public/apps-rocm-5.2.3/aws-ofi-rccl:/opt/rocm/lib64:/opt/rocm/lib:/opt/rocm/rocprofiler/lib:/opt/rocm/rocprofiler/tool:/opt/rocm/roctracer/lib:/opt/rocm/roctracer/tool:/opt/rocm/hip/lib:/opt/cray/pe/python/3.9.13.1/lib:/opt/cray/pe/gcc-libs:/opt/cray/libfabric/1.15.2.0/lib64
|
| 68 |
+
0: 2023-05-23 21:57:04.859811: W tensorflow/compiler/xla/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'libnvinfer.so.7'; dlerror: libnvinfer.so.7: cannot open shared object file: No such file or directory; LD_LIBRARY_PATH: /pfs/lustrep2/projappl/project_462000125/samantao-public/apps-rocm-5.2.3/aws-ofi-rccl:/opt/rocm/lib64:/opt/rocm/lib:/opt/rocm/rocprofiler/lib:/opt/rocm/rocprofiler/tool:/opt/rocm/roctracer/lib:/opt/rocm/roctracer/tool:/opt/rocm/hip/lib:/opt/cray/pe/python/3.9.13.1/lib:/opt/cray/pe/gcc-libs:/opt/cray/libfabric/1.15.2.0/lib64
|
| 69 |
+
0: 2023-05-23 21:57:04.859806: W tensorflow/compiler/xla/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'libnvinfer.so.7'; dlerror: libnvinfer.so.7: cannot open shared object file: No such file or directory; LD_LIBRARY_PATH: /pfs/lustrep2/projappl/project_462000125/samantao-public/apps-rocm-5.2.3/aws-ofi-rccl:/opt/rocm/lib64:/opt/rocm/lib:/opt/rocm/rocprofiler/lib:/opt/rocm/rocprofiler/tool:/opt/rocm/roctracer/lib:/opt/rocm/roctracer/tool:/opt/rocm/hip/lib:/opt/cray/pe/python/3.9.13.1/lib:/opt/cray/pe/gcc-libs:/opt/cray/libfabric/1.15.2.0/lib64
|
| 70 |
+
0: 2023-05-23 21:57:04.859811: W tensorflow/compiler/xla/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'libnvinfer.so.7'; dlerror: libnvinfer.so.7: cannot open shared object file: No such file or directory; LD_LIBRARY_PATH: /pfs/lustrep2/projappl/project_462000125/samantao-public/apps-rocm-5.2.3/aws-ofi-rccl:/opt/rocm/lib64:/opt/rocm/lib:/opt/rocm/rocprofiler/lib:/opt/rocm/rocprofiler/tool:/opt/rocm/roctracer/lib:/opt/rocm/roctracer/tool:/opt/rocm/hip/lib:/opt/cray/pe/python/3.9.13.1/lib:/opt/cray/pe/gcc-libs:/opt/cray/libfabric/1.15.2.0/lib64
|
| 71 |
+
0: 2023-05-23 21:57:04.859816: W tensorflow/compiler/xla/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'libnvinfer.so.7'; dlerror: libnvinfer.so.7: cannot open shared object file: No such file or directory; LD_LIBRARY_PATH: /pfs/lustrep2/projappl/project_462000125/samantao-public/apps-rocm-5.2.3/aws-ofi-rccl:/opt/rocm/lib64:/opt/rocm/lib:/opt/rocm/rocprofiler/lib:/opt/rocm/rocprofiler/tool:/opt/rocm/roctracer/lib:/opt/rocm/roctracer/tool:/opt/rocm/hip/lib:/opt/cray/pe/python/3.9.13.1/lib:/opt/cray/pe/gcc-libs:/opt/cray/libfabric/1.15.2.0/lib64
|
| 72 |
+
0: 2023-05-23 21:57:04.859819: W tensorflow/compiler/xla/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'libnvinfer.so.7'; dlerror: libnvinfer.so.7: cannot open shared object file: No such file or directory; LD_LIBRARY_PATH: /pfs/lustrep2/projappl/project_462000125/samantao-public/apps-rocm-5.2.3/aws-ofi-rccl:/opt/rocm/lib64:/opt/rocm/lib:/opt/rocm/rocprofiler/lib:/opt/rocm/rocprofiler/tool:/opt/rocm/roctracer/lib:/opt/rocm/roctracer/tool:/opt/rocm/hip/lib:/opt/cray/pe/python/3.9.13.1/lib:/opt/cray/pe/gcc-libs:/opt/cray/libfabric/1.15.2.0/lib64
|
| 73 |
+
0: 2023-05-23 21:57:04.885281: W tensorflow/compiler/xla/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'libnvinfer_plugin.so.7'; dlerror: libnvinfer_plugin.so.7: cannot open shared object file: No such file or directory; LD_LIBRARY_PATH: /pfs/lustrep2/projappl/project_462000125/samantao-public/apps-rocm-5.2.3/aws-ofi-rccl:/opt/rocm/lib64:/opt/rocm/lib:/opt/rocm/rocprofiler/lib:/opt/rocm/rocprofiler/tool:/opt/rocm/roctracer/lib:/opt/rocm/roctracer/tool:/opt/rocm/hip/lib:/opt/cray/pe/python/3.9.13.1/lib:/opt/cray/pe/gcc-libs:/opt/cray/libfabric/1.15.2.0/lib64
|
| 74 |
+
0: 2023-05-23 21:57:04.885281: W tensorflow/compiler/xla/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'libnvinfer_plugin.so.7'; dlerror: libnvinfer_plugin.so.7: cannot open shared object file: No such file or directory; LD_LIBRARY_PATH: /pfs/lustrep2/projappl/project_462000125/samantao-public/apps-rocm-5.2.3/aws-ofi-rccl:/opt/rocm/lib64:/opt/rocm/lib:/opt/rocm/rocprofiler/lib:/opt/rocm/rocprofiler/tool:/opt/rocm/roctracer/lib:/opt/rocm/roctracer/tool:/opt/rocm/hip/lib:/opt/cray/pe/python/3.9.13.1/lib:/opt/cray/pe/gcc-libs:/opt/cray/libfabric/1.15.2.0/lib64
|
| 75 |
+
0: 2023-05-23 21:57:04.885284: W tensorflow/compiler/xla/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'libnvinfer_plugin.so.7'; dlerror: libnvinfer_plugin.so.7: cannot open shared object file: No such file or directory; LD_LIBRARY_PATH: /pfs/lustrep2/projappl/project_462000125/samantao-public/apps-rocm-5.2.3/aws-ofi-rccl:/opt/rocm/lib64:/opt/rocm/lib:/opt/rocm/rocprofiler/lib:/opt/rocm/rocprofiler/tool:/opt/rocm/roctracer/lib:/opt/rocm/roctracer/tool:/opt/rocm/hip/lib:/opt/cray/pe/python/3.9.13.1/lib:/opt/cray/pe/gcc-libs:/opt/cray/libfabric/1.15.2.0/lib64
|
| 76 |
+
0: 2023-05-23 21:57:04.885287: W tensorflow/compiler/xla/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'libnvinfer_plugin.so.7'; dlerror: libnvinfer_plugin.so.7: cannot open shared object file: No such file or directory; LD_LIBRARY_PATH: /pfs/lustrep2/projappl/project_462000125/samantao-public/apps-rocm-5.2.3/aws-ofi-rccl:/opt/rocm/lib64:/opt/rocm/lib:/opt/rocm/rocprofiler/lib:/opt/rocm/rocprofiler/tool:/opt/rocm/roctracer/lib:/opt/rocm/roctracer/tool:/opt/rocm/hip/lib:/opt/cray/pe/python/3.9.13.1/lib:/opt/cray/pe/gcc-libs:/opt/cray/libfabric/1.15.2.0/lib64
|
| 77 |
+
0: 2023-05-23 21:57:04.885290: W tensorflow/compiler/xla/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'libnvinfer_plugin.so.7'; dlerror: libnvinfer_plugin.so.7: cannot open shared object file: No such file or directory; LD_LIBRARY_PATH: /pfs/lustrep2/projappl/project_462000125/samantao-public/apps-rocm-5.2.3/aws-ofi-rccl:/opt/rocm/lib64:/opt/rocm/lib:/opt/rocm/rocprofiler/lib:/opt/rocm/rocprofiler/tool:/opt/rocm/roctracer/lib:/opt/rocm/roctracer/tool:/opt/rocm/hip/lib:/opt/cray/pe/python/3.9.13.1/lib:/opt/cray/pe/gcc-libs:/opt/cray/libfabric/1.15.2.0/lib64
|
| 78 |
+
0: 2023-05-23 21:57:04.885293: W tensorflow/compiler/xla/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'libnvinfer_plugin.so.7'; dlerror: libnvinfer_plugin.so.7: cannot open shared object file: No such file or directory; LD_LIBRARY_PATH: /pfs/lustrep2/projappl/project_462000125/samantao-public/apps-rocm-5.2.3/aws-ofi-rccl:/opt/rocm/lib64:/opt/rocm/lib:/opt/rocm/rocprofiler/lib:/opt/rocm/rocprofiler/tool:/opt/rocm/roctracer/lib:/opt/rocm/roctracer/tool:/opt/rocm/hip/lib:/opt/cray/pe/python/3.9.13.1/lib:/opt/cray/pe/gcc-libs:/opt/cray/libfabric/1.15.2.0/lib64
|
| 79 |
+
0: 2023-05-23 21:57:04.885294: W tensorflow/compiler/xla/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'libnvinfer_plugin.so.7'; dlerror: libnvinfer_plugin.so.7: cannot open shared object file: No such file or directory; LD_LIBRARY_PATH: /pfs/lustrep2/projappl/project_462000125/samantao-public/apps-rocm-5.2.3/aws-ofi-rccl:/opt/rocm/lib64:/opt/rocm/lib:/opt/rocm/rocprofiler/lib:/opt/rocm/rocprofiler/tool:/opt/rocm/roctracer/lib:/opt/rocm/roctracer/tool:/opt/rocm/hip/lib:/opt/cray/pe/python/3.9.13.1/lib:/opt/cray/pe/gcc-libs:/opt/cray/libfabric/1.15.2.0/lib64
|
| 80 |
+
0: 2023-05-23 21:57:04.885309: W tensorflow/compiler/tf2tensorrt/utils/py_utils.cc:38] TF-TRT Warning: Cannot dlopen some TensorRT libraries. If you would like to use Nvidia GPU with TensorRT, please make sure the missing libraries mentioned above are installed properly.
|
| 81 |
+
0: 2023-05-23 21:57:04.885309: W tensorflow/compiler/tf2tensorrt/utils/py_utils.cc:38] TF-TRT Warning: Cannot dlopen some TensorRT libraries. If you would like to use Nvidia GPU with TensorRT, please make sure the missing libraries mentioned above are installed properly.
|
| 82 |
+
0: 2023-05-23 21:57:04.885310: W tensorflow/compiler/tf2tensorrt/utils/py_utils.cc:38] TF-TRT Warning: Cannot dlopen some TensorRT libraries. If you would like to use Nvidia GPU with TensorRT, please make sure the missing libraries mentioned above are installed properly.
|
| 83 |
+
0: 2023-05-23 21:57:04.885310: W tensorflow/compiler/tf2tensorrt/utils/py_utils.cc:38] TF-TRT Warning: Cannot dlopen some TensorRT libraries. If you would like to use Nvidia GPU with TensorRT, please make sure the missing libraries mentioned above are installed properly.
|
| 84 |
+
0: 2023-05-23 21:57:04.885311: W tensorflow/compiler/tf2tensorrt/utils/py_utils.cc:38] TF-TRT Warning: Cannot dlopen some TensorRT libraries. If you would like to use Nvidia GPU with TensorRT, please make sure the missing libraries mentioned above are installed properly.
|
| 85 |
+
0: 2023-05-23 21:57:04.885311: W tensorflow/compiler/tf2tensorrt/utils/py_utils.cc:38] TF-TRT Warning: Cannot dlopen some TensorRT libraries. If you would like to use Nvidia GPU with TensorRT, please make sure the missing libraries mentioned above are installed properly.
|
| 86 |
+
0: 2023-05-23 21:57:04.885313: W tensorflow/compiler/tf2tensorrt/utils/py_utils.cc:38] TF-TRT Warning: Cannot dlopen some TensorRT libraries. If you would like to use Nvidia GPU with TensorRT, please make sure the missing libraries mentioned above are installed properly.
|
| 87 |
+
1: 2023-05-23 21:57:04.887343: W tensorflow/compiler/xla/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'libnvinfer.so.7'; dlerror: libnvinfer.so.7: cannot open shared object file: No such file or directory; LD_LIBRARY_PATH: /pfs/lustrep2/projappl/project_462000125/samantao-public/apps-rocm-5.2.3/aws-ofi-rccl:/opt/rocm/lib64:/opt/rocm/lib:/opt/rocm/rocprofiler/lib:/opt/rocm/rocprofiler/tool:/opt/rocm/roctracer/lib:/opt/rocm/roctracer/tool:/opt/rocm/hip/lib:/opt/cray/pe/python/3.9.13.1/lib:/opt/cray/pe/gcc-libs:/opt/cray/libfabric/1.15.2.0/lib64
|
| 88 |
+
1: 2023-05-23 21:57:04.887347: W tensorflow/compiler/xla/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'libnvinfer.so.7'; dlerror: libnvinfer.so.7: cannot open shared object file: No such file or directory; LD_LIBRARY_PATH: /pfs/lustrep2/projappl/project_462000125/samantao-public/apps-rocm-5.2.3/aws-ofi-rccl:/opt/rocm/lib64:/opt/rocm/lib:/opt/rocm/rocprofiler/lib:/opt/rocm/rocprofiler/tool:/opt/rocm/roctracer/lib:/opt/rocm/roctracer/tool:/opt/rocm/hip/lib:/opt/cray/pe/python/3.9.13.1/lib:/opt/cray/pe/gcc-libs:/opt/cray/libfabric/1.15.2.0/lib64
|
| 89 |
+
1: 2023-05-23 21:57:04.887353: W tensorflow/compiler/xla/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'libnvinfer.so.7'; dlerror: libnvinfer.so.7: cannot open shared object file: No such file or directory; LD_LIBRARY_PATH: /pfs/lustrep2/projappl/project_462000125/samantao-public/apps-rocm-5.2.3/aws-ofi-rccl:/opt/rocm/lib64:/opt/rocm/lib:/opt/rocm/rocprofiler/lib:/opt/rocm/rocprofiler/tool:/opt/rocm/roctracer/lib:/opt/rocm/roctracer/tool:/opt/rocm/hip/lib:/opt/cray/pe/python/3.9.13.1/lib:/opt/cray/pe/gcc-libs:/opt/cray/libfabric/1.15.2.0/lib64
|
| 90 |
+
1: 2023-05-23 21:57:04.887356: W tensorflow/compiler/xla/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'libnvinfer.so.7'; dlerror: libnvinfer.so.7: cannot open shared object file: No such file or directory; LD_LIBRARY_PATH: /pfs/lustrep2/projappl/project_462000125/samantao-public/apps-rocm-5.2.3/aws-ofi-rccl:/opt/rocm/lib64:/opt/rocm/lib:/opt/rocm/rocprofiler/lib:/opt/rocm/rocprofiler/tool:/opt/rocm/roctracer/lib:/opt/rocm/roctracer/tool:/opt/rocm/hip/lib:/opt/cray/pe/python/3.9.13.1/lib:/opt/cray/pe/gcc-libs:/opt/cray/libfabric/1.15.2.0/lib64
|
| 91 |
+
1: 2023-05-23 21:57:04.887356: W tensorflow/compiler/xla/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'libnvinfer.so.7'; dlerror: libnvinfer.so.7: cannot open shared object file: No such file or directory; LD_LIBRARY_PATH: /pfs/lustrep2/projappl/project_462000125/samantao-public/apps-rocm-5.2.3/aws-ofi-rccl:/opt/rocm/lib64:/opt/rocm/lib:/opt/rocm/rocprofiler/lib:/opt/rocm/rocprofiler/tool:/opt/rocm/roctracer/lib:/opt/rocm/roctracer/tool:/opt/rocm/hip/lib:/opt/cray/pe/python/3.9.13.1/lib:/opt/cray/pe/gcc-libs:/opt/cray/libfabric/1.15.2.0/lib64
|
| 92 |
+
1: 2023-05-23 21:57:04.887360: W tensorflow/compiler/xla/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'libnvinfer.so.7'; dlerror: libnvinfer.so.7: cannot open shared object file: No such file or directory; LD_LIBRARY_PATH: /pfs/lustrep2/projappl/project_462000125/samantao-public/apps-rocm-5.2.3/aws-ofi-rccl:/opt/rocm/lib64:/opt/rocm/lib:/opt/rocm/rocprofiler/lib:/opt/rocm/rocprofiler/tool:/opt/rocm/roctracer/lib:/opt/rocm/roctracer/tool:/opt/rocm/hip/lib:/opt/cray/pe/python/3.9.13.1/lib:/opt/cray/pe/gcc-libs:/opt/cray/libfabric/1.15.2.0/lib64
|
| 93 |
+
1: 2023-05-23 21:57:04.887363: W tensorflow/compiler/xla/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'libnvinfer.so.7'; dlerror: libnvinfer.so.7: cannot open shared object file: No such file or directory; LD_LIBRARY_PATH: /pfs/lustrep2/projappl/project_462000125/samantao-public/apps-rocm-5.2.3/aws-ofi-rccl:/opt/rocm/lib64:/opt/rocm/lib:/opt/rocm/rocprofiler/lib:/opt/rocm/rocprofiler/tool:/opt/rocm/roctracer/lib:/opt/rocm/roctracer/tool:/opt/rocm/hip/lib:/opt/cray/pe/python/3.9.13.1/lib:/opt/cray/pe/gcc-libs:/opt/cray/libfabric/1.15.2.0/lib64
|
| 94 |
+
1: 2023-05-23 21:57:04.887364: W tensorflow/compiler/xla/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'libnvinfer.so.7'; dlerror: libnvinfer.so.7: cannot open shared object file: No such file or directory; LD_LIBRARY_PATH: /pfs/lustrep2/projappl/project_462000125/samantao-public/apps-rocm-5.2.3/aws-ofi-rccl:/opt/rocm/lib64:/opt/rocm/lib:/opt/rocm/rocprofiler/lib:/opt/rocm/rocprofiler/tool:/opt/rocm/roctracer/lib:/opt/rocm/roctracer/tool:/opt/rocm/hip/lib:/opt/cray/pe/python/3.9.13.1/lib:/opt/cray/pe/gcc-libs:/opt/cray/libfabric/1.15.2.0/lib64
|
| 95 |
+
1: 2023-05-23 21:57:04.888666: W tensorflow/compiler/xla/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'libnvinfer_plugin.so.7'; dlerror: libnvinfer_plugin.so.7: cannot open shared object file: No such file or directory; LD_LIBRARY_PATH: /pfs/lustrep2/projappl/project_462000125/samantao-public/apps-rocm-5.2.3/aws-ofi-rccl:/opt/rocm/lib64:/opt/rocm/lib:/opt/rocm/rocprofiler/lib:/opt/rocm/rocprofiler/tool:/opt/rocm/roctracer/lib:/opt/rocm/roctracer/tool:/opt/rocm/hip/lib:/opt/cray/pe/python/3.9.13.1/lib:/opt/cray/pe/gcc-libs:/opt/cray/libfabric/1.15.2.0/lib64
|
| 96 |
+
1: 2023-05-23 21:57:04.888672: W tensorflow/compiler/xla/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'libnvinfer_plugin.so.7'; dlerror: libnvinfer_plugin.so.7: cannot open shared object file: No such file or directory; LD_LIBRARY_PATH: /pfs/lustrep2/projappl/project_462000125/samantao-public/apps-rocm-5.2.3/aws-ofi-rccl:/opt/rocm/lib64:/opt/rocm/lib:/opt/rocm/rocprofiler/lib:/opt/rocm/rocprofiler/tool:/opt/rocm/roctracer/lib:/opt/rocm/roctracer/tool:/opt/rocm/hip/lib:/opt/cray/pe/python/3.9.13.1/lib:/opt/cray/pe/gcc-libs:/opt/cray/libfabric/1.15.2.0/lib64
|
| 97 |
+
1: 2023-05-23 21:57:04.888671: W tensorflow/compiler/xla/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'libnvinfer_plugin.so.7'; dlerror: libnvinfer_plugin.so.7: cannot open shared object file: No such file or directory; LD_LIBRARY_PATH: /pfs/lustrep2/projappl/project_462000125/samantao-public/apps-rocm-5.2.3/aws-ofi-rccl:/opt/rocm/lib64:/opt/rocm/lib:/opt/rocm/rocprofiler/lib:/opt/rocm/rocprofiler/tool:/opt/rocm/roctracer/lib:/opt/rocm/roctracer/tool:/opt/rocm/hip/lib:/opt/cray/pe/python/3.9.13.1/lib:/opt/cray/pe/gcc-libs:/opt/cray/libfabric/1.15.2.0/lib64
|
| 98 |
+
1: 2023-05-23 21:57:04.888675: W tensorflow/compiler/xla/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'libnvinfer_plugin.so.7'; dlerror: libnvinfer_plugin.so.7: cannot open shared object file: No such file or directory; LD_LIBRARY_PATH: /pfs/lustrep2/projappl/project_462000125/samantao-public/apps-rocm-5.2.3/aws-ofi-rccl:/opt/rocm/lib64:/opt/rocm/lib:/opt/rocm/rocprofiler/lib:/opt/rocm/rocprofiler/tool:/opt/rocm/roctracer/lib:/opt/rocm/roctracer/tool:/opt/rocm/hip/lib:/opt/cray/pe/python/3.9.13.1/lib:/opt/cray/pe/gcc-libs:/opt/cray/libfabric/1.15.2.0/lib64
|
| 99 |
+
1: 2023-05-23 21:57:04.888674: W tensorflow/compiler/xla/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'libnvinfer_plugin.so.7'; dlerror: libnvinfer_plugin.so.7: cannot open shared object file: No such file or directory; LD_LIBRARY_PATH: /pfs/lustrep2/projappl/project_462000125/samantao-public/apps-rocm-5.2.3/aws-ofi-rccl:/opt/rocm/lib64:/opt/rocm/lib:/opt/rocm/rocprofiler/lib:/opt/rocm/rocprofiler/tool:/opt/rocm/roctracer/lib:/opt/rocm/roctracer/tool:/opt/rocm/hip/lib:/opt/cray/pe/python/3.9.13.1/lib:/opt/cray/pe/gcc-libs:/opt/cray/libfabric/1.15.2.0/lib64
|
| 100 |
+
1: 2023-05-23 21:57:04.888678: W tensorflow/compiler/tf2tensorrt/utils/py_utils.cc:38] TF-TRT Warning: Cannot dlopen some TensorRT libraries. If you would like to use Nvidia GPU with TensorRT, please make sure the missing libraries mentioned above are installed properly.
|
| 101 |
+
1: 2023-05-23 21:57:04.888676: W tensorflow/compiler/xla/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'libnvinfer_plugin.so.7'; dlerror: libnvinfer_plugin.so.7: cannot open shared object file: No such file or directory; LD_LIBRARY_PATH: /pfs/lustrep2/projappl/project_462000125/samantao-public/apps-rocm-5.2.3/aws-ofi-rccl:/opt/rocm/lib64:/opt/rocm/lib:/opt/rocm/rocprofiler/lib:/opt/rocm/rocprofiler/tool:/opt/rocm/roctracer/lib:/opt/rocm/roctracer/tool:/opt/rocm/hip/lib:/opt/cray/pe/python/3.9.13.1/lib:/opt/cray/pe/gcc-libs:/opt/cray/libfabric/1.15.2.0/lib64
|
| 102 |
+
1: 2023-05-23 21:57:04.888677: W tensorflow/compiler/xla/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'libnvinfer_plugin.so.7'; dlerror: libnvinfer_plugin.so.7: cannot open shared object file: No such file or directory; LD_LIBRARY_PATH: /pfs/lustrep2/projappl/project_462000125/samantao-public/apps-rocm-5.2.3/aws-ofi-rccl:/opt/rocm/lib64:/opt/rocm/lib:/opt/rocm/rocprofiler/lib:/opt/rocm/rocprofiler/tool:/opt/rocm/roctracer/lib:/opt/rocm/roctracer/tool:/opt/rocm/hip/lib:/opt/cray/pe/python/3.9.13.1/lib:/opt/cray/pe/gcc-libs:/opt/cray/libfabric/1.15.2.0/lib64
|
| 103 |
+
1: 2023-05-23 21:57:04.888677: W tensorflow/compiler/xla/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'libnvinfer_plugin.so.7'; dlerror: libnvinfer_plugin.so.7: cannot open shared object file: No such file or directory; LD_LIBRARY_PATH: /pfs/lustrep2/projappl/project_462000125/samantao-public/apps-rocm-5.2.3/aws-ofi-rccl:/opt/rocm/lib64:/opt/rocm/lib:/opt/rocm/rocprofiler/lib:/opt/rocm/rocprofiler/tool:/opt/rocm/roctracer/lib:/opt/rocm/roctracer/tool:/opt/rocm/hip/lib:/opt/cray/pe/python/3.9.13.1/lib:/opt/cray/pe/gcc-libs:/opt/cray/libfabric/1.15.2.0/lib64
|
| 104 |
+
1: 2023-05-23 21:57:04.888690: W tensorflow/compiler/tf2tensorrt/utils/py_utils.cc:38] TF-TRT Warning: Cannot dlopen some TensorRT libraries. If you would like to use Nvidia GPU with TensorRT, please make sure the missing libraries mentioned above are installed properly.
|
| 105 |
+
1: 2023-05-23 21:57:04.888691: W tensorflow/compiler/tf2tensorrt/utils/py_utils.cc:38] TF-TRT Warning: Cannot dlopen some TensorRT libraries. If you would like to use Nvidia GPU with TensorRT, please make sure the missing libraries mentioned above are installed properly.
|
| 106 |
+
1: 2023-05-23 21:57:04.888691: W tensorflow/compiler/tf2tensorrt/utils/py_utils.cc:38] TF-TRT Warning: Cannot dlopen some TensorRT libraries. If you would like to use Nvidia GPU with TensorRT, please make sure the missing libraries mentioned above are installed properly.
|
| 107 |
+
1: 2023-05-23 21:57:04.888691: W tensorflow/compiler/tf2tensorrt/utils/py_utils.cc:38] TF-TRT Warning: Cannot dlopen some TensorRT libraries. If you would like to use Nvidia GPU with TensorRT, please make sure the missing libraries mentioned above are installed properly.
|
| 108 |
+
1: 2023-05-23 21:57:04.888694: W tensorflow/compiler/tf2tensorrt/utils/py_utils.cc:38] TF-TRT Warning: Cannot dlopen some TensorRT libraries. If you would like to use Nvidia GPU with TensorRT, please make sure the missing libraries mentioned above are installed properly.
|
| 109 |
+
1: 2023-05-23 21:57:04.888695: W tensorflow/compiler/tf2tensorrt/utils/py_utils.cc:38] TF-TRT Warning: Cannot dlopen some TensorRT libraries. If you would like to use Nvidia GPU with TensorRT, please make sure the missing libraries mentioned above are installed properly.
|
| 110 |
+
1: 2023-05-23 21:57:04.888694: W tensorflow/compiler/tf2tensorrt/utils/py_utils.cc:38] TF-TRT Warning: Cannot dlopen some TensorRT libraries. If you would like to use Nvidia GPU with TensorRT, please make sure the missing libraries mentioned above are installed properly.
|
| 111 |
+
0: 2023-05-23 21:57:04.885340: W tensorflow/compiler/xla/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'libnvinfer_plugin.so.7'; dlerror: libnvinfer_plugin.so.7: cannot open shared object file: No such file or directory; LD_LIBRARY_PATH: /pfs/lustrep2/projappl/project_462000125/samantao-public/apps-rocm-5.2.3/aws-ofi-rccl:/opt/rocm/lib64:/opt/rocm/lib:/opt/rocm/rocprofiler/lib:/opt/rocm/rocprofiler/tool:/opt/rocm/roctracer/lib:/opt/rocm/roctracer/tool:/opt/rocm/hip/lib:/opt/cray/pe/python/3.9.13.1/lib:/opt/cray/pe/gcc-libs:/opt/cray/libfabric/1.15.2.0/lib64
|
| 112 |
+
0: 2023-05-23 21:57:04.885353: W tensorflow/compiler/tf2tensorrt/utils/py_utils.cc:38] TF-TRT Warning: Cannot dlopen some TensorRT libraries. If you would like to use Nvidia GPU with TensorRT, please make sure the missing libraries mentioned above are installed properly.
|
| 113 |
+
0: [92mSuccessfully preprocessed all matching files.[0m
|
| 114 |
+
0: Detected CUDA files, patching ldflags
|
| 115 |
+
0: Emitting ninja build file /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/build/build.ninja...
|
| 116 |
+
0: Building extension module scaled_upper_triang_masked_softmax_cuda...
|
| 117 |
+
0: Allowing ninja to set a default number of workers... (overridable by setting the environment variable MAX_JOBS=N)
|
| 118 |
+
0: Loading extension module scaled_upper_triang_masked_softmax_cuda...
|
| 119 |
+
0: [92mSuccessfully preprocessed all matching files.[0m
|
| 120 |
+
0: Detected CUDA files, patching ldflags
|
| 121 |
+
0: Emitting ninja build file /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/build/build.ninja...
|
| 122 |
+
0: Building extension module scaled_masked_softmax_cuda...
|
| 123 |
+
0: Allowing ninja to set a default number of workers... (overridable by setting the environment variable MAX_JOBS=N)
|
| 124 |
+
0: Loading extension module scaled_masked_softmax_cuda...
|
| 125 |
+
0: [92mSuccessfully preprocessed all matching files.[0m
|
| 126 |
+
0: Detected CUDA files, patching ldflags
|
| 127 |
+
0: Emitting ninja build file /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/build/build.ninja...
|
| 128 |
+
0: Building extension module fused_mix_prec_layer_norm_cuda...
|
| 129 |
+
0: Allowing ninja to set a default number of workers... (overridable by setting the environment variable MAX_JOBS=N)
|
| 130 |
+
0: Loading extension module fused_mix_prec_layer_norm_cuda...
|
| 131 |
+
0: [92mSuccessfully preprocessed all matching files.[0m
|
| 132 |
+
0: [92mSuccessfully preprocessed all matching files.[0m
|
| 133 |
+
0: [92mSuccessfully preprocessed all matching files.[0m
|
| 134 |
+
0: [92mSuccessfully preprocessed all matching files.[0m
|
| 135 |
+
1: [92mSuccessfully preprocessed all matching files.[0m
|
| 136 |
+
1: [92mSuccessfully preprocessed all matching files.[0m
|
| 137 |
+
1: [92mSuccessfully preprocessed all matching files.[0m
|
| 138 |
+
1: [92mSuccessfully preprocessed all matching files.[0m
|
| 139 |
+
0: [92mSuccessfully preprocessed all matching files.[0m
|
| 140 |
+
1: [92mSuccessfully preprocessed all matching files.[0m
|
| 141 |
+
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
|
| 142 |
+
1: warnings.warn(
|
| 143 |
+
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
|
| 144 |
+
1: warnings.warn(
|
| 145 |
+
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
|
| 146 |
+
1: warnings.warn(
|
| 147 |
+
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
|
| 148 |
+
1: warnings.warn(
|
| 149 |
+
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
|
| 150 |
+
1: warnings.warn(
|
| 151 |
+
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
|
| 152 |
+
1: warnings.warn(
|
| 153 |
+
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
|
| 154 |
+
1: warnings.warn(
|
| 155 |
+
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
|
| 156 |
+
1: warnings.warn(
|
| 157 |
+
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
|
| 158 |
+
0: warnings.warn(
|
| 159 |
+
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
|
| 160 |
+
0: warnings.warn(
|
| 161 |
+
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
|
| 162 |
+
0: warnings.warn(
|
| 163 |
+
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
|
| 164 |
+
0: warnings.warn(
|
| 165 |
+
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
|
| 166 |
+
0: warnings.warn(
|
| 167 |
+
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
|
| 168 |
+
0: warnings.warn(
|
| 169 |
+
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
|
| 170 |
+
0: warnings.warn(
|
| 171 |
+
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
|
| 172 |
+
0: warnings.warn(
|
| 173 |
+
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...
|
| 174 |
+
0: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...
|
| 175 |
+
0: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...
|
| 176 |
+
0:
|
| 177 |
+
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...
|
| 178 |
+
0:
|
| 179 |
+
0:
|
| 180 |
+
1: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...
|
| 181 |
+
1:
|
| 182 |
+
1:
|
| 183 |
+
1:
|
| 184 |
+
1:
|
| 185 |
+
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...
|
| 186 |
+
1:
|
| 187 |
+
1:
|
| 188 |
+
0: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...
|
| 189 |
+
0: Emitting ninja build file /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu/utils/build.ninja...
|
| 190 |
+
0: Building extension module utils...
|
| 191 |
+
0: Allowing ninja to set a default number of workers... (overridable by setting the environment variable MAX_JOBS=N)
|
| 192 |
+
0: Loading extension module utils...
|
| 193 |
+
0: Loading extension module utils...
|
| 194 |
+
0: Loading extension module utils...
|
| 195 |
+
0: Loading extension module utils...
|
| 196 |
+
1: Loading extension module utils...
|
| 197 |
+
0: Loading extension module utils...
|
| 198 |
+
1: Loading extension module utils...
|
| 199 |
+
0: Loading extension module utils...
|
| 200 |
+
1: Loading extension module utils...
|
| 201 |
+
0: Loading extension module utils...
|
| 202 |
+
1: Loading extension module utils...
|
| 203 |
+
0: Loading extension module utils...
|
| 204 |
+
1: Loading extension module utils...
|
| 205 |
+
1: Loading extension module utils...
|
| 206 |
+
1: Loading extension module utils...
|
| 207 |
+
1: Loading extension module utils...
|
| 208 |
+
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...
|
| 209 |
+
0:
|
| 210 |
+
0:
|
| 211 |
+
0:
|
| 212 |
+
0: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...
|
| 213 |
+
0: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...
|
| 214 |
+
0: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...
|
| 215 |
+
0: No modifications detected for re-loaded extension module utils, skipping build step...No modifications detected for re-loaded extension module utils, skipping build step...No modifications detected for re-loaded extension module utils, skipping build step...No modifications detected for re-loaded extension module utils, skipping build step...
|
| 216 |
+
0:
|
| 217 |
+
0:
|
| 218 |
+
0:
|
| 219 |
+
0: Loading extension module utils...Loading extension module utils...Loading extension module utils...Loading extension module utils...
|
| 220 |
+
0:
|
| 221 |
+
0:
|
| 222 |
+
0:
|
| 223 |
+
0: No modifications detected for re-loaded extension module utils, skipping build step...
|
| 224 |
+
0: Loading extension module utils...
|
| 225 |
+
0: No modifications detected for re-loaded extension module utils, skipping build step...
|
| 226 |
+
0: Loading extension module utils...No modifications detected for re-loaded extension module utils, skipping build step...
|
| 227 |
+
0:
|
| 228 |
+
0: Loading extension module utils...
|
| 229 |
+
1: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...
|
| 230 |
+
1: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...
|
| 231 |
+
1: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...
|
| 232 |
+
1: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...
|
| 233 |
+
1: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...
|
| 234 |
+
1: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...
|
| 235 |
+
1: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...
|
| 236 |
+
1: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...
|
| 237 |
+
1: No modifications detected for re-loaded extension module utils, skipping build step...
|
| 238 |
+
1: Loading extension module utils...
|
| 239 |
+
1: No modifications detected for re-loaded extension module utils, skipping build step...
|
| 240 |
+
1: Loading extension module utils...
|
| 241 |
+
1: No modifications detected for re-loaded extension module utils, skipping build step...
|
| 242 |
+
1: Loading extension module utils...
|
| 243 |
+
1: No modifications detected for re-loaded extension module utils, skipping build step...
|
| 244 |
+
1: No modifications detected for re-loaded extension module utils, skipping build step...Loading extension module utils...
|
| 245 |
+
1:
|
| 246 |
+
1: Loading extension module utils...
|
| 247 |
+
1: No modifications detected for re-loaded extension module utils, skipping build step...
|
| 248 |
+
1: Loading extension module utils...
|
| 249 |
+
1: No modifications detected for re-loaded extension module utils, skipping build step...
|
| 250 |
+
1: Loading extension module utils...
|
| 251 |
+
1: No modifications detected for re-loaded extension module utils, skipping build step...
|
| 252 |
+
1: Loading extension module utils...
|
| 253 |
+
0: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...
|
| 254 |
+
0: No modifications detected for re-loaded extension module utils, skipping build step...
|
| 255 |
+
0: Loading extension module utils...
|
| 256 |
+
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
|
| 257 |
+
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")
|
7m100m100m/3571584.out
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
7m100m100m/global_step190/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e3efcfe9e388751224449755f471b2255c265548303fec751cfe3267535b8b0e
|
| 3 |
+
size 5476759
|
7m100m100m/global_step190/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2b640de6a45f9ca3568dbf617a4f26ee467bdeed93ba852c888277642ae54053
|
| 3 |
+
size 5476770
|
7m100m100m/global_step190/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:24d9a18af9bd86570c5c77d8cd978a9403b55ac313f05d0fcd17a58d59892d52
|
| 3 |
+
size 5476642
|
7m100m100m/global_step190/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:78bde61ab72af0d55db4d321cc13f747bab52867ab66ad10e45cdf26568fe524
|
| 3 |
+
size 5476834
|
7m100m100m/global_step190/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7f51e57933a5c3f47f24721ffae8880f026c1b85725226ec4405abe635d7ae63
|
| 3 |
+
size 5476642
|
7m100m100m/global_step190/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:241ccc89c43aa103a210853bef054bddccde98bb20bd8b4f94e841d3a3d13244
|
| 3 |
+
size 5476706
|
7m100m100m/global_step190/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6d9099035d73a614210536e3bc327000f79eca41479b3f13d450c3dcf438de2b
|
| 3 |
+
size 5477026
|
7m100m100m/global_step190/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2a5a48d4f1f4ebe4953251c421c062b0594ed2620ad326e331b82a35dc3ea235
|
| 3 |
+
size 5476631
|
7m100m100m/global_step190/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c2a6c8636d4ba7736a88fe4bd34e1cf5741d1c140b2c0220daf70f3bf31f6add
|
| 3 |
+
size 5476695
|
7m100m100m/global_step190/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3551d5bde164f7e3f413c3ff81463a7ca38eeeb196b92323b16794c64a2208a6
|
| 3 |
+
size 5476695
|
7m100m100m/global_step190/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:90c8c017e092d1484ce9adedefb8900872e1a4e7eae08d1e6547a6fa3302ed35
|
| 3 |
+
size 5476631
|
7m100m100m/global_step190/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a1e46a5f7fa922500fa54dfc72773f8b8ff342745efc5fa241edfdd006ef5371
|
| 3 |
+
size 5476759
|
7m100m100m/global_step190/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8a632293061cb20dbe9ca0789b19d5e57bf569d22dd041a8a3e5bcd08b14c13a
|
| 3 |
+
size 5476695
|
7m100m100m/global_step190/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b5775ea9bb91e65d41513d09289c43be532d98450648fc20c33df7f12ff17bbf
|
| 3 |
+
size 5476823
|
7m100m100m/global_step190/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:dfbdace11910c98a4d2b979755bbd43f4619329c1abb14336cee19304b25dcd7
|
| 3 |
+
size 5476695
|
7m100m100m/global_step190/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:021f23c70b67ae22e34c690118617cbea49ab766414087efdb74ddd7efc9b023
|
| 3 |
+
size 5476759
|
7m100m100m/global_step190/layer_01-model_00-model_states.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 13403395
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f2e9cfefae28dd2b607e34beed236d351988561d1af382afed6acc329783a2eb
|
| 3 |
size 13403395
|
7m100m100m/global_step190/layer_03-model_00-model_states.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:47b29407562e042b54c0158df50ab99fcb1168293ea2ec46b59e5efe8fcc413e
|
| 3 |
+
size 400899
|
7m100m100m/global_step190/layer_04-model_00-model_states.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:77694928eaf5003ff45cfc72af5280e356b4f6f4d609b07bdd369eedc18a16e2
|
| 3 |
+
size 400899
|
7m100m100m/global_step190/layer_05-model_00-model_states.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:74a8e96211a7813404f8fd683d3b7092c35ec7d327504e4af20512173346de9b
|
| 3 |
+
size 400899
|
7m100m100m/global_step190/layer_07-model_00-model_states.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1731
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9f87d6166302c37c4cdd4ab69f3ef99cbfbe659661d27d4e76c7cac90adfc77e
|
| 3 |
size 1731
|
7m100m100m/global_step190/mp_rank_00_model_states.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 26291
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6233cb22aeb9c32f37f55ca14c0927b651e0fd332e55e3da7a073b6f2a528182
|
| 3 |
size 26291
|
7m100m100m/{eval.txt → old/eval.txt}
RENAMED
|
File without changes
|
7m100m100m/old/global_step190/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 sha256:91e39ac7720cd88efa0f2792784d0995bd76bf801e9f5118f60ca32812df6a16
|
| 3 |
+
size 5328663
|
7m100m100m/old/global_step190/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 sha256:50524214c32ac1591a7ca179ae352d2d24c1cbc25af9c438a1932355bac9dac8
|
| 3 |
+
size 5328738
|
7m100m100m/old/global_step190/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:bf4eff0fae01461ece233f6f5c827d7276de91a0e7c1742594ebef134752c5e0
|
| 3 |
+
size 5328674
|
7m100m100m/old/global_step190/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:cb9e2a0f09e02c0b2bdee18476c2f6fbf29143a906d2eae4d11f5632ca613492
|
| 3 |
+
size 5328674
|
7m100m100m/old/global_step190/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 sha256:4d2024359a28d77bbb230eab81bbdebaa49a6d636e2b5fcb7ad390187b3a0323
|
| 3 |
+
size 5328738
|
7m100m100m/old/global_step190/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:d6ab9e28b46a1192a9329246816b6c8364a2f14f293ece347090682deb5443da
|
| 3 |
+
size 5328674
|
7m100m100m/old/global_step190/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 sha256:750f2efa4fd61f98ba33966e7f8af78607c1dc1d3f8a822084ef365fe233e1cc
|
| 3 |
+
size 5328930
|
7m100m100m/old/global_step190/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:eb8be589a26588c6c0f4263986b837fc702f03677ef616f7b143e4aa7f618ed0
|
| 3 |
+
size 5328663
|
7m100m100m/old/global_step190/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 sha256:1063c6a152da13d10d1c80b807901eea5c8690a26a39c756300c587e9140ef2f
|
| 3 |
+
size 5328663
|
7m100m100m/old/global_step190/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 sha256:9c7f93a598f10961626a76180aaa0709b39e99c78ff1b760462c14bf16acbc9d
|
| 3 |
+
size 5328727
|
7m100m100m/old/global_step190/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 sha256:531a2f6237ab987fc4a2f1f80b17ed0007e471a90d07f94bedbad693df99b9ea
|
| 3 |
+
size 5328599
|
7m100m100m/old/global_step190/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a8aac831f3f14d90d2cb5a292460d3d604063d1e91f925dae4613988c06e9336
|
| 3 |
+
size 5328727
|
7m100m100m/old/global_step190/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:09be9059c96563f1820729b24a4d4a7d1efba89f95ecdf534895f1efb6ba941b
|
| 3 |
+
size 5328663
|
7m100m100m/old/global_step190/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ce505b1046906abd28d585d2a4eeaa49afff654c2598a88f4f03fc553cca9e4a
|
| 3 |
+
size 5328727
|
7m100m100m/old/global_step190/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:13a62508ac67ee77f5f540f0ed683de121dee608599c6ad120885a8a4ee5fa60
|
| 3 |
+
size 5328663
|
7m100m100m/old/global_step190/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a7a781edd720d3c8509dd73d88f9b337f1bcea9c4b376df11254cc9650225a57
|
| 3 |
+
size 5328663
|
7m100m100m/old/global_step190/layer_01-model_00-model_states.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3dd9fd24e83426db607da9de56ffbec877aa9beb4280371e02dc307ba51c2894
|
| 3 |
+
size 13403395
|
7m100m100m/old/global_step190/layer_03-model_00-model_states.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9f360d0adbad0e5638df2813825909d6984834cebe9df58fb8392b54cf94aba7
|
| 3 |
+
size 269251
|
7m100m100m/old/global_step190/layer_04-model_00-model_states.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9e1d89c75ba47e3b24518e467dfd201455e5209ee6e7642b6c91d212f443f3e8
|
| 3 |
+
size 269251
|
7m100m100m/old/global_step190/layer_05-model_00-model_states.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e42c451c9a9ca671b3032df95728c86de351808a4133292212189a5dba87089c
|
| 3 |
+
size 269251
|
7m100m100m/old/global_step190/layer_07-model_00-model_states.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:aa7ca97d524a068d70c503b217faea25271ed1bfa94e8e2fd94c7e27050c9016
|
| 3 |
+
size 1731
|
7m100m100m/old/global_step190/mp_rank_00_model_states.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:337ac14e9140d70e974d88f9f29417e17d68da0290367b6dabda485b89aa63cb
|
| 3 |
+
size 26291
|
7m100m100m/{logs → old/logs}/3163410.err
RENAMED
|
File without changes
|
7m100m100m/{logs → old/logs}/3163410.out
RENAMED
|
File without changes
|
7m100m100m/{tensorboard_7m100m100m → old/tensorboard_7m100m100m}/events.out.tfevents.1677508396.nid006608.48416.0
RENAMED
|
File without changes
|