Commit
·
de1dac2
1
Parent(s):
7f89c55
Move models
Browse filesThis view is limited to 50 files because it contains too many changes. Â
See raw diff
- 14m100m100m/global_step190/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt +3 -0
- 14m100m100m/global_step190/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt +3 -0
- 14m100m100m/global_step190/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt +3 -0
- 14m100m100m/global_step190/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt +3 -0
- 14m100m100m/global_step190/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt +3 -0
- 14m100m100m/global_step190/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt +3 -0
- 14m100m100m/global_step190/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt +3 -0
- 14m100m100m/global_step190/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt +3 -0
- 14m100m100m/global_step190/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt +3 -0
- 14m100m100m/global_step190/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt +3 -0
- 14m100m100m/global_step190/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt +3 -0
- 14m100m100m/global_step190/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt +3 -0
- 14m100m100m/global_step190/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt +3 -0
- 14m100m100m/global_step190/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt +3 -0
- 14m100m100m/global_step190/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt +3 -0
- 14m100m100m/global_step190/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt +3 -0
- 14m100m100m/global_step190/layer_01-model_00-model_states.pt +3 -0
- 14m100m100m/global_step190/layer_03-model_00-model_states.pt +3 -0
- 14m100m100m/global_step190/layer_04-model_00-model_states.pt +3 -0
- 14m100m100m/global_step190/layer_05-model_00-model_states.pt +3 -0
- 14m100m100m/global_step190/layer_06-model_00-model_states.pt +3 -0
- 14m100m100m/global_step190/layer_08-model_00-model_states.pt +3 -0
- 14m100m100m/global_step190/mp_rank_00_model_states.pt +3 -0
- 14m100m100m/logs/3163413.err +301 -0
- 14m100m100m/logs/3163413.out +0 -0
- 14m100m100m/sbatch_14m100m100m.sh +168 -0
- 14m100m100m/sbatch_14m100m100mval.sh +167 -0
- 14m100m100m/tensorboard_14m100m100m/events.out.tfevents.1677508517.nid006613.13417.0 +3 -0
- 14m100m100m/tensorboard_14m100m100mval/events.out.tfevents.1677509121.nid007495.92522.0 +3 -0
- 14m100m100m/tensorboard_14m100m100mval/events.out.tfevents.1678800406.nid007281.60225.0 +3 -0
- {14m1b5100mv → 14m1b5100m}/3307602.err +0 -0
- {14m1b5100mv → 14m1b5100m}/3307602.out +0 -0
- {14m7b5100mv → 14m7b5100m}/3307761.err +0 -0
- {14m7b5100mv → 14m7b5100m}/3307761.out +0 -0
- 1b112b100m/1b112b100m/global_step23189/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt +3 -0
- 1b112b100m/1b112b100m/global_step23189/bf16_zero_pp_rank_100_mp_rank_00_optim_states.pt +3 -0
- 1b112b100m/1b112b100m/global_step23189/bf16_zero_pp_rank_101_mp_rank_00_optim_states.pt +3 -0
- 1b112b100m/1b112b100m/global_step23189/bf16_zero_pp_rank_102_mp_rank_00_optim_states.pt +3 -0
- 1b112b100m/1b112b100m/global_step23189/bf16_zero_pp_rank_103_mp_rank_00_optim_states.pt +3 -0
- 1b112b100m/1b112b100m/global_step23189/bf16_zero_pp_rank_104_mp_rank_00_optim_states.pt +3 -0
- 1b112b100m/1b112b100m/global_step23189/bf16_zero_pp_rank_105_mp_rank_00_optim_states.pt +3 -0
- 1b112b100m/1b112b100m/global_step23189/bf16_zero_pp_rank_106_mp_rank_00_optim_states.pt +3 -0
- 1b112b100m/1b112b100m/global_step23189/bf16_zero_pp_rank_107_mp_rank_00_optim_states.pt +3 -0
- 1b112b100m/1b112b100m/global_step23189/bf16_zero_pp_rank_108_mp_rank_00_optim_states.pt +3 -0
- 1b112b100m/1b112b100m/global_step23189/bf16_zero_pp_rank_109_mp_rank_00_optim_states.pt +3 -0
- 1b112b100m/1b112b100m/global_step23189/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt +3 -0
- 1b112b100m/1b112b100m/global_step23189/bf16_zero_pp_rank_110_mp_rank_00_optim_states.pt +3 -0
- 1b112b100m/1b112b100m/global_step23189/bf16_zero_pp_rank_111_mp_rank_00_optim_states.pt +3 -0
- 1b112b100m/1b112b100m/global_step23189/bf16_zero_pp_rank_112_mp_rank_00_optim_states.pt +3 -0
- 1b112b100m/1b112b100m/global_step23189/bf16_zero_pp_rank_113_mp_rank_00_optim_states.pt +3 -0
14m100m100m/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 sha256:6c628e1090f463618347286f69aa3e507204d302358e32a025d0b65c8f9545ca
|
| 3 |
+
size 10614999
|
14m100m100m/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:c012dab7e55337e0b0aff2b427e9969cb29681d61877181a522bc0199314f0e8
|
| 3 |
+
size 10615074
|
14m100m100m/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 sha256:2060669813e272a71abd4140a4fd2557c426a8863389b67d1e8912dd90bfe11f
|
| 3 |
+
size 10615138
|
14m100m100m/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 sha256:1948d595de13f97ca9a54ddc2eeb8b1504fcff641d41bbb5ddceb9996bc09124
|
| 3 |
+
size 10615010
|
14m100m100m/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 sha256:0e26dbb67778c4d56ce590294d707e37ec02ab5f3832886b610fce694e969e64
|
| 3 |
+
size 10615202
|
14m100m100m/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 sha256:44767c6dcded60bb44da8040750076543902878e809f045f5ce161dc32337dac
|
| 3 |
+
size 10615202
|
14m100m100m/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:f9aafd26fc2d64f0ca2e93f103a31013eb707973522242df74cdb75e241f4a4f
|
| 3 |
+
size 10615266
|
14m100m100m/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:faa9c102a2087d607eba917b620d569c1b02b7d4a809de60f98fea51bfbe1913
|
| 3 |
+
size 10615063
|
14m100m100m/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:ceb01cf4f17188679e552effa47ab7dd99039439ba13ee0fef722adfeccdca06
|
| 3 |
+
size 10615127
|
14m100m100m/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:a19929e016dd32bd618e4f51667b913ccc4f04f99e63317350a3c97c09ca2804
|
| 3 |
+
size 10614999
|
14m100m100m/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 sha256:4865027f32f57ed28bbb022570e78683576a9b20aa707f304eb3125fed7a0677
|
| 3 |
+
size 10615063
|
14m100m100m/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 sha256:5f4996f10f0fe2086dd9f09b633fe7f40f6d90dac0fa051dad19f64985a7d014
|
| 3 |
+
size 10615127
|
14m100m100m/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:a05b7bb4f6af4f24baef0f1cd40ba9253055212057dd5b8b761e121a0edfe8ed
|
| 3 |
+
size 10614999
|
14m100m100m/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 sha256:4c7cc3611f3142efc1799549e0112b8bd317def2d887062f1548f4a8b6e6de74
|
| 3 |
+
size 10614999
|
14m100m100m/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 sha256:477bedcec57e414afffb3afd6ec93d50ebf7af37008dd494923b2569aeb3acbc
|
| 3 |
+
size 10614999
|
14m100m100m/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 sha256:766117132e9d4b120aa3e6fadb6186850eac3d7b98bfbd5038413d7cd60fd6c2
|
| 3 |
+
size 10615191
|
14m100m100m/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 sha256:36e37eeead5e761eb8043b259d2a8467e17a2441704d411126e391fdd80cda17
|
| 3 |
+
size 23454979
|
14m100m100m/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 sha256:41bde257eb5783d1423d3d2f1a12e64fbbefe682f0fef37bf323dfb8e48cf717
|
| 3 |
+
size 1214403
|
14m100m100m/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 sha256:8da1358dcd3720b9d840026efe1c62aef85c0d17e450b105b217c515bb67765b
|
| 3 |
+
size 1214403
|
14m100m100m/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 sha256:86b64c8a8b36c4b168a33724d2761bb787e12d0182870e6632a653dfa1fb00d7
|
| 3 |
+
size 1214403
|
14m100m100m/global_step190/layer_06-model_00-model_states.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7338d4f71a29dbbecbf090abf6f0be3ac6c1118839e96b4b15fc23b7a1aa00b3
|
| 3 |
+
size 1214403
|
14m100m100m/global_step190/layer_08-model_00-model_states.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:dec12d04b1ce30ef368fc14028401fab453e8086e92983dfc8347e293631aef7
|
| 3 |
+
size 2115
|
14m100m100m/global_step190/mp_rank_00_model_states.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:93fdb4efd17f0cff9b3a9a672e07fede6681c70783e1ccd383daa62abeb6608c
|
| 3 |
+
size 26995
|
14m100m100m/logs/3163413.err
ADDED
|
@@ -0,0 +1,301 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
0: 2023-02-27 16:44:48.450670: 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 16:44:48.450675: 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 16:44:48.450684: 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 16:44:48.450679: 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 16:44:48.450684: 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 16:44:48.450682: 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 16:44:48.450688: 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 16:44:48.450691: 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 16:44:48.526135: 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 16:44:48.526142: 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 16:44:48.526148: 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 16:44:48.526151: 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 16:44:48.526146: 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 16:44:48.526154: 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 16:44:48.526160: 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 16:44:48.526159: 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 16:44:50.091673: 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 16:44:50.091674: 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 16:44:50.091682: 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 16:44:50.091694: 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 16:44:50.091689: 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 16:44:50.091690: 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 16:44:50.091699: 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 16:44:50.091691: 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 16:44:50.092026: 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 16:44:50.092029: 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 16:44:50.092033: 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 16:44:50.092037: 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 16:44:50.092039: 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 16:44:50.092040: 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 16:44:50.092041: 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 16:44:50.092044: 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 16:44:50.240535: 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 16:44:50.240536: 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 16:44:50.240540: 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 16:44:50.240542: 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 16:44:50.240545: 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 16:44:50.240543: 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 16:44:50.240733: 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.
|
| 70 |
+
1: 2023-02-27 16:44:50.240735: 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.
|
| 71 |
+
1: 2023-02-27 16:44:50.240546: 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 16:44:50.240540: 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
|
| 74 |
+
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
|
| 75 |
+
1: 2023-02-27 16:44:50.240742: 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 16:44:50.240743: 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 16:44:50.240749: 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 16:44:50.240750: 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 16:44:50.240752: 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 16:44:50.240751: 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 |
+
0: 2023-02-27 16:44:55.272694: 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 |
+
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
|
| 83 |
+
1: 2023-02-27 16:44:55.272688: 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 |
+
0: 2023-02-27 16:44:55.272700: 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
|
| 85 |
+
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
|
| 86 |
+
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
|
| 87 |
+
1: 2023-02-27 16:44:55.272697: 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 |
+
0: 2023-02-27 16:44:55.272706: 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
|
| 89 |
+
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
|
| 90 |
+
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
|
| 91 |
+
1: 2023-02-27 16:44:55.272694: 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 |
+
0: 2023-02-27 16:44:55.272706: 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
|
| 93 |
+
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
|
| 94 |
+
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
|
| 95 |
+
1: 2023-02-27 16:44:55.272695: 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 |
+
0: 2023-02-27 16:44:55.272709: 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
|
| 97 |
+
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
|
| 98 |
+
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
|
| 99 |
+
1: 2023-02-27 16:44:55.272701: 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
|
| 100 |
+
0: 2023-02-27 16:44:55.272711: 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
|
| 101 |
+
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
|
| 102 |
+
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
|
| 103 |
+
1: 2023-02-27 16:44:55.272699: 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
|
| 104 |
+
0: 2023-02-27 16:44:55.272713: 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
|
| 105 |
+
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
|
| 106 |
+
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
|
| 107 |
+
1: 2023-02-27 16:44:55.272703: 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
|
| 108 |
+
0: 2023-02-27 16:44:55.272717: 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
|
| 109 |
+
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
|
| 110 |
+
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
|
| 111 |
+
1: 2023-02-27 16:44:55.272702: 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
|
| 112 |
+
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
|
| 113 |
+
1: 2023-02-27 16:44:55.274738: 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
|
| 114 |
+
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
|
| 115 |
+
1: 2023-02-27 16:44:55.274737: 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
|
| 116 |
+
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
|
| 117 |
+
1: 2023-02-27 16:44:55.274738: 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
|
| 118 |
+
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
|
| 119 |
+
1: 2023-02-27 16:44:55.274740: 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
|
| 120 |
+
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
|
| 121 |
+
1: 2023-02-27 16:44:55.274742: 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
|
| 122 |
+
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
|
| 123 |
+
1: 2023-02-27 16:44:55.274743: 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
|
| 124 |
+
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
|
| 125 |
+
1: 2023-02-27 16:44:55.274756: 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.
|
| 126 |
+
1: 2023-02-27 16:44:55.274752: 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
|
| 127 |
+
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
|
| 128 |
+
1: 2023-02-27 16:44:55.274757: 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.
|
| 129 |
+
1: 2023-02-27 16:44:55.274756: 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.
|
| 130 |
+
1: 2023-02-27 16:44:55.274759: 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.
|
| 131 |
+
1: 2023-02-27 16:44:55.274758: 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.
|
| 132 |
+
1: 2023-02-27 16:44:55.274758: 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.
|
| 133 |
+
1: 2023-02-27 16:44:55.274768: 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.
|
| 134 |
+
1: 2023-02-27 16:44:55.274797: 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
|
| 135 |
+
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
|
| 136 |
+
1: 2023-02-27 16:44:55.274809: 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.
|
| 137 |
+
0: 2023-02-27 16:44:55.274653: 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 16:44:55.274654: 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 16:44:55.274655: 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 16:44:55.274658: 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 16:44:55.274662: 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 16:44:55.274662: 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 16:44:55.274663: 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
|
| 150 |
+
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
|
| 151 |
+
0: 2023-02-27 16:44:55.274669: 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 16:44:55.274664: 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
|
| 153 |
+
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
|
| 154 |
+
0: 2023-02-27 16:44:55.274671: 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 16:44:55.274671: 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.
|
| 156 |
+
0: 2023-02-27 16:44:55.274673: 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.
|
| 157 |
+
0: 2023-02-27 16:44:55.274680: 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.
|
| 158 |
+
0: 2023-02-27 16:44:55.274683: 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.
|
| 159 |
+
0: 2023-02-27 16:44:55.274684: 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 16:44:55.274686: 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: [92mSuccessfully preprocessed all matching files.[0m
|
| 162 |
+
0: Detected CUDA files, patching ldflags
|
| 163 |
+
0: Emitting ninja build file /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/build/build.ninja...
|
| 164 |
+
0: Building extension module scaled_upper_triang_masked_softmax_cuda...
|
| 165 |
+
0: Allowing ninja to set a default number of workers... (overridable by setting the environment variable MAX_JOBS=N)
|
| 166 |
+
0: Loading extension module scaled_upper_triang_masked_softmax_cuda...
|
| 167 |
+
0: [92mSuccessfully preprocessed all matching files.[0m
|
| 168 |
+
0: Detected CUDA files, patching ldflags
|
| 169 |
+
0: Emitting ninja build file /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/build/build.ninja...
|
| 170 |
+
0: Building extension module scaled_masked_softmax_cuda...
|
| 171 |
+
0: Allowing ninja to set a default number of workers... (overridable by setting the environment variable MAX_JOBS=N)
|
| 172 |
+
0: Loading extension module scaled_masked_softmax_cuda...
|
| 173 |
+
0: [92mSuccessfully preprocessed all matching files.[0m
|
| 174 |
+
0: Detected CUDA files, patching ldflags
|
| 175 |
+
0: Emitting ninja build file /pfs/lustrep4/scratch/project_462000119/muennighoff/nov-2022-bettercom/Megatron-DeepSpeed/megatron/fused_kernels/build/build.ninja...
|
| 176 |
+
0: Building extension module fused_mix_prec_layer_norm_cuda...
|
| 177 |
+
0: Allowing ninja to set a default number of workers... (overridable by setting the environment variable MAX_JOBS=N)
|
| 178 |
+
0: Loading extension module fused_mix_prec_layer_norm_cuda...
|
| 179 |
+
0: [92mSuccessfully preprocessed all matching files.[0m
|
| 180 |
+
0: [92mSuccessfully preprocessed all matching files.[0m
|
| 181 |
+
0: [92mSuccessfully preprocessed all matching files.[0m
|
| 182 |
+
0: [92mSuccessfully preprocessed all matching files.[0m
|
| 183 |
+
0: [92mSuccessfully preprocessed all matching files.[0m
|
| 184 |
+
0: [92mSuccessfully preprocessed all matching files.[0m
|
| 185 |
+
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
|
| 186 |
+
0: warnings.warn(
|
| 187 |
+
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
|
| 188 |
+
0: warnings.warn(
|
| 189 |
+
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
|
| 190 |
+
0: warnings.warn(
|
| 191 |
+
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
|
| 192 |
+
0: warnings.warn(
|
| 193 |
+
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
|
| 194 |
+
0: warnings.warn(
|
| 195 |
+
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
|
| 196 |
+
0: warnings.warn(
|
| 197 |
+
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
|
| 198 |
+
0: warnings.warn(
|
| 199 |
+
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
|
| 200 |
+
1: warnings.warn(
|
| 201 |
+
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
|
| 202 |
+
1: warnings.warn(
|
| 203 |
+
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
|
| 204 |
+
1: warnings.warn(
|
| 205 |
+
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
|
| 206 |
+
1: warnings.warn(
|
| 207 |
+
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
|
| 208 |
+
1: warnings.warn(
|
| 209 |
+
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
|
| 210 |
+
1: warnings.warn(
|
| 211 |
+
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
|
| 212 |
+
1: warnings.warn(
|
| 213 |
+
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
|
| 214 |
+
1: warnings.warn(
|
| 215 |
+
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
|
| 216 |
+
0: warnings.warn(
|
| 217 |
+
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...
|
| 218 |
+
0:
|
| 219 |
+
0: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...
|
| 220 |
+
0: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...
|
| 221 |
+
0: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...
|
| 222 |
+
0: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...
|
| 223 |
+
0: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...
|
| 224 |
+
1: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...
|
| 225 |
+
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...
|
| 226 |
+
1:
|
| 227 |
+
1:
|
| 228 |
+
1: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...
|
| 229 |
+
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...
|
| 230 |
+
1:
|
| 231 |
+
1:
|
| 232 |
+
0: Emitting ninja build file /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu/utils/build.ninja...
|
| 233 |
+
0: Building extension module utils...
|
| 234 |
+
0: Allowing ninja to set a default number of workers... (overridable by setting the environment variable MAX_JOBS=N)
|
| 235 |
+
0: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...
|
| 236 |
+
0: Loading extension module utils...
|
| 237 |
+
0: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...
|
| 238 |
+
0: No modifications detected for re-loaded extension module utils, skipping build step...
|
| 239 |
+
0: Loading extension module utils...
|
| 240 |
+
0: Loading extension module utils...
|
| 241 |
+
0: Loading extension module utils...
|
| 242 |
+
0: Loading extension module utils...Loading extension module utils...
|
| 243 |
+
0:
|
| 244 |
+
0: Loading extension module utils...
|
| 245 |
+
0: Loading extension module utils...
|
| 246 |
+
0: Loading extension module utils...
|
| 247 |
+
1: Loading extension module utils...
|
| 248 |
+
1: Loading extension module utils...
|
| 249 |
+
1: Loading extension module utils...
|
| 250 |
+
1: Loading extension module utils...
|
| 251 |
+
1: Loading extension module utils...
|
| 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: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...
|
| 257 |
+
0: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...
|
| 258 |
+
0: No modifications detected for re-loaded extension module utils, skipping build step...
|
| 259 |
+
0: Loading extension module utils...
|
| 260 |
+
0: No modifications detected for re-loaded extension module utils, skipping build step...
|
| 261 |
+
0: Loading extension module utils...
|
| 262 |
+
0: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...
|
| 263 |
+
0: No modifications detected for re-loaded extension module utils, skipping build step...
|
| 264 |
+
0: Loading extension module utils...
|
| 265 |
+
0: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...
|
| 266 |
+
0: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...
|
| 267 |
+
0: No modifications detected for re-loaded extension module utils, skipping build step...
|
| 268 |
+
0: Loading extension module utils...
|
| 269 |
+
0: No modifications detected for re-loaded extension module utils, skipping build step...
|
| 270 |
+
0: Loading extension module utils...
|
| 271 |
+
1: Loading extension module utils...
|
| 272 |
+
1: Loading extension module utils...
|
| 273 |
+
1: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...
|
| 274 |
+
1: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...
|
| 275 |
+
1: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...
|
| 276 |
+
1: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...
|
| 277 |
+
1: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...
|
| 278 |
+
1: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...
|
| 279 |
+
1: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...
|
| 280 |
+
1: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...
|
| 281 |
+
1: No modifications detected for re-loaded extension module utils, skipping build step...
|
| 282 |
+
1: Loading extension module utils...
|
| 283 |
+
1: No modifications detected for re-loaded extension module utils, skipping build step...
|
| 284 |
+
1: Loading extension module utils...
|
| 285 |
+
1: No modifications detected for re-loaded extension module utils, skipping build step...
|
| 286 |
+
1: Loading extension module utils...
|
| 287 |
+
1: No modifications detected for re-loaded extension module utils, skipping build step...
|
| 288 |
+
1: Loading extension module utils...
|
| 289 |
+
1: No modifications detected for re-loaded extension module utils, skipping build step...
|
| 290 |
+
1: Loading extension module utils...
|
| 291 |
+
1: No modifications detected for re-loaded extension module utils, skipping build step...
|
| 292 |
+
1: Loading extension module utils...
|
| 293 |
+
1: No modifications detected for re-loaded extension module utils, skipping build step...
|
| 294 |
+
1: Loading extension module utils...
|
| 295 |
+
1: No modifications detected for re-loaded extension module utils, skipping build step...
|
| 296 |
+
1: Loading extension module utils...
|
| 297 |
+
0: Using /pfs/lustrep4/users/muennighoff/.cache/torch_extensions/py39_cpu as PyTorch extensions root...
|
| 298 |
+
0: No modifications detected for re-loaded extension module utils, skipping build step...
|
| 299 |
+
0: Loading extension module utils...
|
| 300 |
+
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
|
| 301 |
+
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")
|
14m100m100m/logs/3163413.out
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
14m100m100m/sbatch_14m100m100m.sh
ADDED
|
@@ -0,0 +1,168 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
#!/bin/bash
|
| 2 |
+
#SBATCH --exclude=nid007571,nid007112,nid006774,nid007502,nid007506,nid007507,nid005145,nid006692,nid007218,nid007123,nid006124,nid006123,nid007496,nid007237,nid006852,nid007206,nid006947,nid007212,nid006977,nid007222,nid005444,nid007219,nid007493,nid007221,nid005300,nid005619,nid006118,nid005203,nid006113,nid006481,nid007077,nid005208,nid005207,nid005879,nid005901
|
| 3 |
+
#SBATCH --nodes=2
|
| 4 |
+
#SBATCH --ntasks-per-node=1
|
| 5 |
+
#SBATCH --cpus-per-task=32
|
| 6 |
+
#SBATCH --mem=256G
|
| 7 |
+
#SBATCH -p standard-g
|
| 8 |
+
#SBATCH -t 2-0:00:00
|
| 9 |
+
#SBATCH --gpus-per-node=mi250:8
|
| 10 |
+
#SBATCH --exclusive=user
|
| 11 |
+
#SBATCH --hint=nomultithread
|
| 12 |
+
#SBATCH --account=project_462000119
|
| 13 |
+
#SBATCH -o logs/%j.out
|
| 14 |
+
#SBATCH -e logs/%j.err
|
| 15 |
+
|
| 16 |
+
VARIANT=14m100m100m
|
| 17 |
+
|
| 18 |
+
# if run without sbatch, invoke here
|
| 19 |
+
if [ -z $SLURM_JOB_ID ]; then
|
| 20 |
+
mkdir -p logs
|
| 21 |
+
sbatch "$0"
|
| 22 |
+
exit
|
| 23 |
+
fi
|
| 24 |
+
|
| 25 |
+
set -euo pipefail
|
| 26 |
+
|
| 27 |
+
# symlink logs/latest.out and logs/latest.err
|
| 28 |
+
ln -f -s $SLURM_JOB_ID.out logs/latest.out
|
| 29 |
+
ln -f -s $SLURM_JOB_ID.err logs/latest.err
|
| 30 |
+
|
| 31 |
+
KILL_SWITCH_PATH=kill-switch-$VARIANT
|
| 32 |
+
CHECKPOINT_PATH=checkpoints_$VARIANT
|
| 33 |
+
TENSORBOARD_PATH=tensorboard_$VARIANT
|
| 34 |
+
mkdir -p $CHECKPOINT_PATH
|
| 35 |
+
mkdir -p $TENSORBOARD_PATH
|
| 36 |
+
|
| 37 |
+
# Data
|
| 38 |
+
VOCAB_FILE="gpt2/vocab.json"
|
| 39 |
+
MERGE_FILE="gpt2/merges.txt"
|
| 40 |
+
#DATA_PATH="/scratch/project_462000119/data/pile/megatron_data/meg-gpt2_pile_text_document"
|
| 41 |
+
TRAIN_DATA_PATH=train100m.txt
|
| 42 |
+
# "train: 1.0 0:1 /scratch/project_462000119/data/c4_subsampled/gpt2tok_c4_en_1B5_text_document"
|
| 43 |
+
VALID_DATA_PATH=val.txt
|
| 44 |
+
# "validation: 1.0 0:1 /scratch/project_462000119/data/c4_validation/gpt2tok_c4validation_rerun_text_document"
|
| 45 |
+
|
| 46 |
+
|
| 47 |
+
PP_SIZE=1
|
| 48 |
+
TP_SIZE=1
|
| 49 |
+
|
| 50 |
+
MICRO_BATCH_SIZE=16
|
| 51 |
+
GRADIENT_ACCUMULATION_STEPS=1
|
| 52 |
+
WORLD_SIZE=$((SLURM_GPUS_ON_NODE*SLURM_JOB_NUM_NODES))
|
| 53 |
+
GLOBAL_BATCH_SIZE=$((MICRO_BATCH_SIZE*WORLD_SIZE*GRADIENT_ACCUMULATION_STEPS))
|
| 54 |
+
|
| 55 |
+
# Model parameters
|
| 56 |
+
source model_params.sh
|
| 57 |
+
MODEL_PARAM=("${PARAM_14M[@]}")
|
| 58 |
+
NHIDDEN=${MODEL_PARAM[0]}
|
| 59 |
+
FFN_HIDDEN_SIZE=${MODEL_PARAM[1]}
|
| 60 |
+
KV_SIZE=${MODEL_PARAM[2]}
|
| 61 |
+
NHEADS=${MODEL_PARAM[3]}
|
| 62 |
+
NLAYERS=${MODEL_PARAM[4]}
|
| 63 |
+
SEQ_LEN=2048
|
| 64 |
+
|
| 65 |
+
echo "Model parameters: d_model $NHIDDEN ffw_size $FFN_HIDDEN_SIZE kv_size $KV_SIZE n_heads $NHEADS n_layers $NLAYERS"
|
| 66 |
+
|
| 67 |
+
SAVE_INTERVAL=10000
|
| 68 |
+
|
| 69 |
+
# Tokens: 100 000 000
|
| 70 |
+
# -> Samples: 48828.125
|
| 71 |
+
TRAIN_SAMPLES=48_828
|
| 72 |
+
|
| 73 |
+
OPTIMIZER_ARGS=" \
|
| 74 |
+
--optimizer adam \
|
| 75 |
+
--adam-beta1 0.9 \
|
| 76 |
+
--adam-beta2 0.999 \
|
| 77 |
+
--adam-eps 1e-8 \
|
| 78 |
+
--lr 2e-4 \
|
| 79 |
+
--min-lr 2e-5 \
|
| 80 |
+
--lr-decay-style cosine \
|
| 81 |
+
--lr-decay-samples $TRAIN_SAMPLES \
|
| 82 |
+
--lr-warmup-samples 488 \
|
| 83 |
+
--clip-grad 1.0 \
|
| 84 |
+
--weight-decay 1e-1 \
|
| 85 |
+
"
|
| 86 |
+
|
| 87 |
+
GPT_ARGS=" \
|
| 88 |
+
--num-layers $NLAYERS \
|
| 89 |
+
--hidden-size $NHIDDEN \
|
| 90 |
+
--num-attention-heads $NHEADS \
|
| 91 |
+
--kv-channels $KV_SIZE \
|
| 92 |
+
--ffn-hidden-size $FFN_HIDDEN_SIZE \
|
| 93 |
+
--seq-length $SEQ_LEN \
|
| 94 |
+
--max-position-embeddings $SEQ_LEN \
|
| 95 |
+
--micro-batch-size $MICRO_BATCH_SIZE \
|
| 96 |
+
--global-batch-size $GLOBAL_BATCH_SIZE \
|
| 97 |
+
--train-samples $TRAIN_SAMPLES \
|
| 98 |
+
--vocab-file $VOCAB_FILE \
|
| 99 |
+
--merge-file $MERGE_FILE \
|
| 100 |
+
--loss-scale 12 \
|
| 101 |
+
--clip-grad 1.0 \
|
| 102 |
+
--kill-switch-path $KILL_SWITCH_PATH \
|
| 103 |
+
--bf16 \
|
| 104 |
+
--checkpoint-activations \
|
| 105 |
+
$OPTIMIZER_ARGS \
|
| 106 |
+
"
|
| 107 |
+
|
| 108 |
+
OUTPUT_ARGS=" \
|
| 109 |
+
--log-interval 10 \
|
| 110 |
+
--save-interval $SAVE_INTERVAL \
|
| 111 |
+
--eval-interval 1000 \
|
| 112 |
+
--eval-iters 1 \
|
| 113 |
+
--tensorboard-dir $TENSORBOARD_PATH \
|
| 114 |
+
--tensorboard-queue-size 5 \
|
| 115 |
+
--log-timers-to-tensorboard \
|
| 116 |
+
--log-batch-size-to-tensorboard \
|
| 117 |
+
--log-validation-ppl-to-tensorboard \
|
| 118 |
+
"
|
| 119 |
+
|
| 120 |
+
ZERO_STAGE=0
|
| 121 |
+
|
| 122 |
+
mkdir -p ds_configs
|
| 123 |
+
DS_CONFIG_PATH="ds_configs/$SLURM_JOB_ID.json"
|
| 124 |
+
|
| 125 |
+
cat <<EOF > $DS_CONFIG_PATH
|
| 126 |
+
{
|
| 127 |
+
"train_micro_batch_size_per_gpu": $MICRO_BATCH_SIZE,
|
| 128 |
+
"train_batch_size": $GLOBAL_BATCH_SIZE,
|
| 129 |
+
"gradient_clipping": 1.0,
|
| 130 |
+
"zero_optimization": {
|
| 131 |
+
"stage": $ZERO_STAGE
|
| 132 |
+
},
|
| 133 |
+
"bf16": {
|
| 134 |
+
"enabled": true
|
| 135 |
+
},
|
| 136 |
+
"steps_per_print": 2000,
|
| 137 |
+
"wall_clock_breakdown": false
|
| 138 |
+
}
|
| 139 |
+
EOF
|
| 140 |
+
|
| 141 |
+
DEEPSPEED_ARGS=" \
|
| 142 |
+
--deepspeed \
|
| 143 |
+
--deepspeed_config $DS_CONFIG_PATH \
|
| 144 |
+
--zero-stage $ZERO_STAGE \
|
| 145 |
+
"
|
| 146 |
+
|
| 147 |
+
CMD=" \
|
| 148 |
+
Megatron-DeepSpeed/pretrain_gpt.py \
|
| 149 |
+
--tensor-model-parallel-size $TP_SIZE \
|
| 150 |
+
--pipeline-model-parallel-size $PP_SIZE \
|
| 151 |
+
$GPT_ARGS \
|
| 152 |
+
$OUTPUT_ARGS \
|
| 153 |
+
--save $CHECKPOINT_PATH \
|
| 154 |
+
--load $CHECKPOINT_PATH \
|
| 155 |
+
--train-weighted-split-paths-path $TRAIN_DATA_PATH \
|
| 156 |
+
--valid-weighted-split-paths-path $VALID_DATA_PATH \
|
| 157 |
+
--data-impl mmap \
|
| 158 |
+
$DEEPSPEED_ARGS \
|
| 159 |
+
"
|
| 160 |
+
|
| 161 |
+
echo $CMD
|
| 162 |
+
|
| 163 |
+
echo "START $SLURM_JOBID: $(date)"
|
| 164 |
+
|
| 165 |
+
# bash launch_srun.sh $CMD
|
| 166 |
+
srun --label launch.sh $CMD
|
| 167 |
+
|
| 168 |
+
echo "END $SLURM_JOBID: $(date)"
|
14m100m100m/sbatch_14m100m100mval.sh
ADDED
|
@@ -0,0 +1,167 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
#!/bin/bash
|
| 2 |
+
#SBATCH --exclude=nid007571,nid007112,nid006774,nid007502,nid007506,nid007507,nid005145,nid006692,nid007218,nid007123,nid006124,nid006123,nid007496,nid007237,nid006852,nid007206,nid006947,nid007212,nid006977,nid007222,nid005444,nid007219,nid007493,nid007221,nid005300,nid005619,nid006118,nid005203,nid006113,nid006481,nid007077,nid005208,nid005207,nid005879,nid005901
|
| 3 |
+
#SBATCH --nodes=2
|
| 4 |
+
#SBATCH --ntasks-per-node=1
|
| 5 |
+
#SBATCH --cpus-per-task=32
|
| 6 |
+
#SBATCH --mem=256G
|
| 7 |
+
#SBATCH -p small-g
|
| 8 |
+
#SBATCH -t 12:00:00
|
| 9 |
+
#SBATCH --gpus-per-node=mi250:8
|
| 10 |
+
#SBATCH --exclusive=user
|
| 11 |
+
#SBATCH --hint=nomultithread
|
| 12 |
+
#SBATCH --account=project_462000119
|
| 13 |
+
#SBATCH -o logs/%j.out
|
| 14 |
+
#SBATCH -e logs/%j.err
|
| 15 |
+
|
| 16 |
+
VARIANT=14m100m100mval
|
| 17 |
+
VARIANT_CKPT=14m100m100m
|
| 18 |
+
|
| 19 |
+
# if run without sbatch, invoke here
|
| 20 |
+
if [ -z $SLURM_JOB_ID ]; then
|
| 21 |
+
mkdir -p logs
|
| 22 |
+
sbatch "$0"
|
| 23 |
+
exit
|
| 24 |
+
fi
|
| 25 |
+
|
| 26 |
+
set -euo pipefail
|
| 27 |
+
|
| 28 |
+
# symlink logs/latest.out and logs/latest.err
|
| 29 |
+
ln -f -s $SLURM_JOB_ID.out logs/latest.out
|
| 30 |
+
ln -f -s $SLURM_JOB_ID.err logs/latest.err
|
| 31 |
+
|
| 32 |
+
KILL_SWITCH_PATH=kill-switch-$VARIANT
|
| 33 |
+
CHECKPOINT_PATH=checkpoints_$VARIANT_CKPT
|
| 34 |
+
TENSORBOARD_PATH=tensorboard_$VARIANT
|
| 35 |
+
|
| 36 |
+
# Data
|
| 37 |
+
VOCAB_FILE="gpt2/vocab.json"
|
| 38 |
+
MERGE_FILE="gpt2/merges.txt"
|
| 39 |
+
#DATA_PATH="/scratch/project_462000119/data/pile/megatron_data/meg-gpt2_pile_text_document"
|
| 40 |
+
TRAIN_DATA_PATH=train100m.txt
|
| 41 |
+
# "train: 1.0 0:1 /scratch/project_462000119/data/c4_subsampled/gpt2tok_c4_en_4B8_text_document"
|
| 42 |
+
VALID_DATA_PATH=val.txt
|
| 43 |
+
# "validation: 1.0 0:1 /scratch/project_462000119/data/c4_validation/gpt2tok_c4validation_rerun_text_document"
|
| 44 |
+
|
| 45 |
+
PP_SIZE=1
|
| 46 |
+
TP_SIZE=1
|
| 47 |
+
|
| 48 |
+
MICRO_BATCH_SIZE=4
|
| 49 |
+
GRADIENT_ACCUMULATION_STEPS=1
|
| 50 |
+
WORLD_SIZE=$((SLURM_GPUS_ON_NODE*SLURM_JOB_NUM_NODES))
|
| 51 |
+
GLOBAL_BATCH_SIZE=$((MICRO_BATCH_SIZE*WORLD_SIZE*GRADIENT_ACCUMULATION_STEPS))
|
| 52 |
+
|
| 53 |
+
# Model parameters
|
| 54 |
+
source model_params.sh
|
| 55 |
+
MODEL_PARAM=("${PARAM_14M[@]}")
|
| 56 |
+
NHIDDEN=${MODEL_PARAM[0]}
|
| 57 |
+
FFN_HIDDEN_SIZE=${MODEL_PARAM[1]}
|
| 58 |
+
KV_SIZE=${MODEL_PARAM[2]}
|
| 59 |
+
NHEADS=${MODEL_PARAM[3]}
|
| 60 |
+
NLAYERS=${MODEL_PARAM[4]}
|
| 61 |
+
SEQ_LEN=2048
|
| 62 |
+
|
| 63 |
+
echo "Model parameters: d_model $NHIDDEN ffw_size $FFN_HIDDEN_SIZE kv_size $KV_SIZE n_heads $NHEADS n_layers $NLAYERS"
|
| 64 |
+
|
| 65 |
+
SAVE_INTERVAL=1000
|
| 66 |
+
|
| 67 |
+
# Tokens: 31633480000
|
| 68 |
+
# -> Samples: 15446035
|
| 69 |
+
TRAIN_SAMPLES=1
|
| 70 |
+
|
| 71 |
+
OPTIMIZER_ARGS=" \
|
| 72 |
+
--optimizer adam \
|
| 73 |
+
--adam-beta1 0.9 \
|
| 74 |
+
--adam-beta2 0.999 \
|
| 75 |
+
--adam-eps 1e-8 \
|
| 76 |
+
--lr 2e-4 \
|
| 77 |
+
--min-lr 2e-5 \
|
| 78 |
+
--lr-decay-style cosine \
|
| 79 |
+
--lr-decay-samples $TRAIN_SAMPLES \
|
| 80 |
+
--lr-warmup-samples 0 \
|
| 81 |
+
--clip-grad 1.0 \
|
| 82 |
+
--weight-decay 1e-1 \
|
| 83 |
+
--override-lr-scheduler \
|
| 84 |
+
--no-load-optim \
|
| 85 |
+
--reset-progress \
|
| 86 |
+
"
|
| 87 |
+
|
| 88 |
+
GPT_ARGS=" \
|
| 89 |
+
--num-layers $NLAYERS \
|
| 90 |
+
--hidden-size $NHIDDEN \
|
| 91 |
+
--num-attention-heads $NHEADS \
|
| 92 |
+
--kv-channels $KV_SIZE \
|
| 93 |
+
--ffn-hidden-size $FFN_HIDDEN_SIZE \
|
| 94 |
+
--seq-length $SEQ_LEN \
|
| 95 |
+
--max-position-embeddings $SEQ_LEN \
|
| 96 |
+
--micro-batch-size $MICRO_BATCH_SIZE \
|
| 97 |
+
--global-batch-size $GLOBAL_BATCH_SIZE \
|
| 98 |
+
--train-samples $TRAIN_SAMPLES \
|
| 99 |
+
--vocab-file $VOCAB_FILE \
|
| 100 |
+
--merge-file $MERGE_FILE \
|
| 101 |
+
--clip-grad 1.0 \
|
| 102 |
+
--kill-switch-path $KILL_SWITCH_PATH \
|
| 103 |
+
--bf16 \
|
| 104 |
+
$OPTIMIZER_ARGS \
|
| 105 |
+
"
|
| 106 |
+
|
| 107 |
+
OUTPUT_ARGS=" \
|
| 108 |
+
--log-interval 10 \
|
| 109 |
+
--save-interval $SAVE_INTERVAL \
|
| 110 |
+
--eval-interval 1 \
|
| 111 |
+
--eval-iters 100 \
|
| 112 |
+
--tensorboard-dir $TENSORBOARD_PATH \
|
| 113 |
+
--tensorboard-queue-size 5 \
|
| 114 |
+
--log-timers-to-tensorboard \
|
| 115 |
+
--log-batch-size-to-tensorboard \
|
| 116 |
+
--log-validation-ppl-to-tensorboard \
|
| 117 |
+
"
|
| 118 |
+
|
| 119 |
+
ZERO_STAGE=0
|
| 120 |
+
|
| 121 |
+
mkdir -p ds_configs
|
| 122 |
+
DS_CONFIG_PATH="ds_configs/$SLURM_JOB_ID.json"
|
| 123 |
+
|
| 124 |
+
cat <<EOF > $DS_CONFIG_PATH
|
| 125 |
+
{
|
| 126 |
+
"train_micro_batch_size_per_gpu": $MICRO_BATCH_SIZE,
|
| 127 |
+
"train_batch_size": $GLOBAL_BATCH_SIZE,
|
| 128 |
+
"gradient_clipping": 1.0,
|
| 129 |
+
"zero_optimization": {
|
| 130 |
+
"stage": $ZERO_STAGE
|
| 131 |
+
},
|
| 132 |
+
"bf16": {
|
| 133 |
+
"enabled": true
|
| 134 |
+
},
|
| 135 |
+
"steps_per_print": 2000,
|
| 136 |
+
"wall_clock_breakdown": false
|
| 137 |
+
}
|
| 138 |
+
EOF
|
| 139 |
+
|
| 140 |
+
DEEPSPEED_ARGS=" \
|
| 141 |
+
--deepspeed \
|
| 142 |
+
--deepspeed_config $DS_CONFIG_PATH \
|
| 143 |
+
--zero-stage $ZERO_STAGE \
|
| 144 |
+
"
|
| 145 |
+
|
| 146 |
+
CMD=" \
|
| 147 |
+
Megatron-DeepSpeed/pretrain_gpt.py \
|
| 148 |
+
--tensor-model-parallel-size $TP_SIZE \
|
| 149 |
+
--pipeline-model-parallel-size $PP_SIZE \
|
| 150 |
+
$GPT_ARGS \
|
| 151 |
+
$OUTPUT_ARGS \
|
| 152 |
+
--save $CHECKPOINT_PATH \
|
| 153 |
+
--load $CHECKPOINT_PATH \
|
| 154 |
+
--train-weighted-split-paths-path $TRAIN_DATA_PATH \
|
| 155 |
+
--valid-weighted-split-paths-path $VALID_DATA_PATH \
|
| 156 |
+
--data-impl mmap \
|
| 157 |
+
$DEEPSPEED_ARGS \
|
| 158 |
+
"
|
| 159 |
+
|
| 160 |
+
echo $CMD
|
| 161 |
+
|
| 162 |
+
echo "START $SLURM_JOBID: $(date)"
|
| 163 |
+
|
| 164 |
+
# bash launch_srun.sh $CMD
|
| 165 |
+
srun --label launch.sh $CMD
|
| 166 |
+
|
| 167 |
+
echo "END $SLURM_JOBID: $(date)"
|
14m100m100m/tensorboard_14m100m100m/events.out.tfevents.1677508517.nid006613.13417.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:41e5422c9e2fcd0c5db2be12c2a71e1f9a96c5897ded7a3ffd50c01d25d5534a
|
| 3 |
+
size 355324
|
14m100m100m/tensorboard_14m100m100mval/events.out.tfevents.1677509121.nid007495.92522.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:34a2c6f2333cf39f269d79aab690d59e95e286140cd83c0fc335adab3226351d
|
| 3 |
+
size 980
|
14m100m100m/tensorboard_14m100m100mval/events.out.tfevents.1678800406.nid007281.60225.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8f4ba864573adf53dc8d0673c544f12cb5e07a2711b018e2a3d2266a17e4b03b
|
| 3 |
+
size 980
|
{14m1b5100mv → 14m1b5100m}/3307602.err
RENAMED
|
File without changes
|
{14m1b5100mv → 14m1b5100m}/3307602.out
RENAMED
|
File without changes
|
{14m7b5100mv → 14m7b5100m}/3307761.err
RENAMED
|
File without changes
|
{14m7b5100mv → 14m7b5100m}/3307761.out
RENAMED
|
File without changes
|
1b112b100m/1b112b100m/global_step23189/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 sha256:5c4b69f38a245da6e4d0513eccbb04c26c76b474abeac577ecbb3773aec6e629
|
| 3 |
+
size 51395415
|
1b112b100m/1b112b100m/global_step23189/bf16_zero_pp_rank_100_mp_rank_00_optim_states.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e1b34567610692468ac21331c9e23ed6ed3863f8c63081e212bfb8879611667a
|
| 3 |
+
size 51395373
|
1b112b100m/1b112b100m/global_step23189/bf16_zero_pp_rank_101_mp_rank_00_optim_states.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7447a3a8cdabd9ec3e4b72f779d6492f1cfb529f2775357c0a489190d5f94795
|
| 3 |
+
size 51395437
|
1b112b100m/1b112b100m/global_step23189/bf16_zero_pp_rank_102_mp_rank_00_optim_states.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:03291cf5118afad0a131fc7705594bd07bfbee912ee4defdac94fd682c678117
|
| 3 |
+
size 51395501
|
1b112b100m/1b112b100m/global_step23189/bf16_zero_pp_rank_103_mp_rank_00_optim_states.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bf5081ba8de8e3d229a8e54fb43c192fb5c51ae6ffc8f4769a5ec2871c1253e9
|
| 3 |
+
size 51395565
|
1b112b100m/1b112b100m/global_step23189/bf16_zero_pp_rank_104_mp_rank_00_optim_states.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1979150e5ddc2df4bce1339ab00276fce8721cfbb4cfa29816d61a7dd65b0441
|
| 3 |
+
size 51395373
|
1b112b100m/1b112b100m/global_step23189/bf16_zero_pp_rank_105_mp_rank_00_optim_states.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:df3a858ac35888b1acb0ed9db854b4eb7ffa7eb7de08532c91e87cdff58810eb
|
| 3 |
+
size 51395373
|
1b112b100m/1b112b100m/global_step23189/bf16_zero_pp_rank_106_mp_rank_00_optim_states.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bd5dd0a03580e3d1cfd18d949c833097e194c9dffc9a661d108d5867a1fe71da
|
| 3 |
+
size 51395437
|
1b112b100m/1b112b100m/global_step23189/bf16_zero_pp_rank_107_mp_rank_00_optim_states.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4d0237a57736cfdf4dfc5b4987d2c7ca3794164c42b93ce2d37cc6c00b001616
|
| 3 |
+
size 51395501
|
1b112b100m/1b112b100m/global_step23189/bf16_zero_pp_rank_108_mp_rank_00_optim_states.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0d4a57711df649bc7569868378a6aa543d4dbd02eb83fc6fc7720b5c8685e133
|
| 3 |
+
size 51395437
|
1b112b100m/1b112b100m/global_step23189/bf16_zero_pp_rank_109_mp_rank_00_optim_states.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:130656d77b8a7ac04a92747124612fe3abea6473a0ea55be3bc76bb3ab04386c
|
| 3 |
+
size 51395501
|
1b112b100m/1b112b100m/global_step23189/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 sha256:291bd2d97eab3485e7aab1a656533129d7f4233ea771a2fc172bbab641312b9f
|
| 3 |
+
size 51395426
|
1b112b100m/1b112b100m/global_step23189/bf16_zero_pp_rank_110_mp_rank_00_optim_states.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8e121359c0a68dff23c7c5342db576d9af4aa6e6c831b7d916feb5baef63ef3a
|
| 3 |
+
size 51395373
|
1b112b100m/1b112b100m/global_step23189/bf16_zero_pp_rank_111_mp_rank_00_optim_states.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a6755c268beff0fdfe0350c8c5f1d03ac320b9e167a426fbe9f935c04aa47389
|
| 3 |
+
size 51395437
|
1b112b100m/1b112b100m/global_step23189/bf16_zero_pp_rank_112_mp_rank_00_optim_states.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4fbd4300577ba63e9fc50bd62e1720ae9f8a9251388c7b8e3119829f9dcf62d8
|
| 3 |
+
size 51395501
|
1b112b100m/1b112b100m/global_step23189/bf16_zero_pp_rank_113_mp_rank_00_optim_states.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:23c999e23b8f2cdf65437f5147d246a3f2c39af746e52e25e898241331694510
|
| 3 |
+
size 51395501
|