loaded library: /usr/lib/x86_64-linux-gnu/libibverbs.so.1
*****************************************
Setting OMP_NUM_THREADS environment variable for each process to be 1 in default, to avoid your system being overloaded, please further tune the variable for optimal performance in your application as needed. 
*****************************************
loaded library: loaded library: /usr/lib/x86_64-linux-gnu/libibverbs.so.1/usr/lib/x86_64-linux-gnu/libibverbs.so.1

loaded library: /usr/lib/x86_64-linux-gnu/libibverbs.so.1
loaded library: /usr/lib/x86_64-linux-gnu/libibverbs.so.1
loaded library: /usr/lib/x86_64-linux-gnu/libibverbs.so.1
loaded library: loaded library: /usr/lib/x86_64-linux-gnu/libibverbs.so.1/usr/lib/x86_64-linux-gnu/libibverbs.so.1

loaded library: /usr/lib/x86_64-linux-gnu/libibverbs.so.1
------------------------ arguments ------------------------
  batches_per_epoch ............................... 625
  channel_last .................................... False
  ddp ............................................. True
  exit_num ........................................ 300
  fuse_bn_add_relu ................................ False
  fuse_bn_relu .................................... False
  gpu_stat_file ................................... None
  grad_clipping ................................... 0.0
  graph ........................................... False
  label_smoothing ................................. 0.1
  learning_rate ................................... 2.048
  legacy_init ..................................... False
  load_path ....................................... None
  lr_decay_type ................................... cosine
  metric_local .................................... True
  metric_train_acc ................................ True
  momentum ........................................ 0.875
  nccl_fusion_max_ops ............................. 24
  nccl_fusion_threshold_mb ........................ 16
  num_classes ..................................... 1000
  num_devices_per_node ............................ 8
  num_epochs ...................................... 1
  num_nodes ....................................... 1
  ofrecord_part_num ............................... 256
  ofrecord_path ................................... /dataset/79846248
  print_interval .................................. 100
  print_timestamp ................................. False
  samples_per_epoch ............................... 1281167
  save_init ....................................... False
  save_path ....................................... None
  scale_grad ...................................... False
  skip_eval ....................................... True
  synthetic_data .................................. False
  total_batches ................................... -1
  train_batch_size ................................ 256
  train_global_batch_size ......................... 2048
  use_fp16 ........................................ False
  use_gpu_decode .................................. False
  val_batch_size .................................. 50
  val_batches_per_epoch ........................... 125
  val_global_batch_size ........................... 400
  val_samples_per_epoch ........................... 50000
  warmup_epochs ................................... 5
  weight_decay .................................... 3.0517578125e-05
  zero_init_residual .............................. True
-------------------- end of arguments ---------------------
***** Model Init *****
***** Model Init Finish, time escapled: 2.73365 s *****
[rank:3] [train], epoch: 0/1, iter: 100/625, loss: 0.86726, lr: 0.000000, top1: 0.00133, throughput: 275.76 | 2022-04-13 01:57:56.148
[rank:5] [train], epoch: 0/1, iter: 100/625, loss: 0.86725, lr: 0.000000, top1: 0.00121, throughput: 275.82 | 2022-04-13 01:57:56.151
[rank:7] [train], epoch: 0/1, iter: 100/625, loss: 0.86727, lr: 0.000000, top1: 0.00117, throughput: 275.58 | 2022-04-13 01:57:56.157
[rank:0] [train], epoch: 0/1, iter: 100/625, loss: 0.86719, lr: 0.000000, top1: 0.00125, throughput: 275.39 | 2022-04-13 01:57:56.192
[rank:2] [train], epoch: 0/1, iter: 100/625, loss: 0.86720, lr: 0.000000, top1: 0.00121, throughput: 275.42 | 2022-04-13 01:57:56.195
[rank:4] [train], epoch: 0/1, iter: 100/625, loss: 0.86712, lr: 0.000000, top1: 0.00117, throughput: 275.48 | 2022-04-13 01:57:56.195
[rank:1] [train], epoch: 0/1, iter: 100/625, loss: 0.86718, lr: 0.000000, top1: 0.00090, throughput: 275.40 | 2022-04-13 01:57:56.232
[rank:6] [train], epoch: 0/1, iter: 100/625, loss: 0.86748, lr: 0.000000, top1: 0.00129, throughput: 275.36 | 2022-04-13 01:57:56.246
timestamp, name, driver_version, utilization.gpu [%], utilization.memory [%], memory.total [MiB], memory.free [MiB], memory.used [MiB]
2022/04/13 01:57:56.322, Tesla V100-SXM2-32GB, 470.57.02, 34 %, 0 %, 32510 MiB, 5134 MiB, 27376 MiB
timestamp, name, driver_version, utilization.gpu [%], utilization.memory [%], memory.total [MiB], memory.free [MiB], memory.used [MiB]
2022/04/13 01:57:56.327, Tesla V100-SXM2-32GB, 470.57.02, 47 %, 33 %, 32510 MiB, 5154 MiB, 27356 MiB
2022/04/13 01:57:56.327, Tesla V100-SXM2-32GB, 470.57.02, 34 %, 0 %, 32510 MiB, 5134 MiB, 27376 MiB
2022/04/13 01:57:56.332, Tesla V100-SXM2-32GB, 470.57.02, 44 %, 4 %, 32510 MiB, 5230 MiB, 27280 MiB
2022/04/13 01:57:56.333, Tesla V100-SXM2-32GB, 470.57.02, 47 %, 33 %, 32510 MiB, 5154 MiB, 27356 MiB
timestamp, name, driver_version, utilization.gpu [%], utilization.memory [%], memory.total [MiB], memory.free [MiB], memory.used [MiB]
2022/04/13 01:57:56.339, Tesla V100-SXM2-32GB, 470.57.02, 78 %, 27 %, 32510 MiB, 5206 MiB, 27304 MiB
2022/04/13 01:57:56.340, Tesla V100-SXM2-32GB, 470.57.02, 44 %, 4 %, 32510 MiB, 5230 MiB, 27280 MiB
2022/04/13 01:57:56.345, Tesla V100-SXM2-32GB, 470.57.02, 34 %, 0 %, 32510 MiB, 5134 MiB, 27376 MiB
2022/04/13 01:57:56.345, Tesla V100-SXM2-32GB, 470.57.02, 45 %, 31 %, 32510 MiB, 5214 MiB, 27296 MiB
2022/04/13 01:57:56.346, Tesla V100-SXM2-32GB, 470.57.02, 78 %, 27 %, 32510 MiB, 5206 MiB, 27304 MiB
2022/04/13 01:57:56.350, Tesla V100-SXM2-32GB, 470.57.02, 47 %, 33 %, 32510 MiB, 5154 MiB, 27356 MiB
2022/04/13 01:57:56.351, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 47 %, 32510 MiB, 5146 MiB, 27364 MiB
2022/04/13 01:57:56.352, Tesla V100-SXM2-32GB, 470.57.02, 45 %, 31 %, 32510 MiB, 5214 MiB, 27296 MiB
2022/04/13 01:57:56.358, Tesla V100-SXM2-32GB, 470.57.02, 44 %, 4 %, 32510 MiB, 5230 MiB, 27280 MiB
2022/04/13 01:57:56.358, Tesla V100-SXM2-32GB, 470.57.02, 22 %, 15 %, 32510 MiB, 5090 MiB, 27420 MiB
2022/04/13 01:57:56.359, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 47 %, 32510 MiB, 5146 MiB, 27364 MiB
2022/04/13 01:57:56.365, Tesla V100-SXM2-32GB, 470.57.02, 78 %, 27 %, 32510 MiB, 5206 MiB, 27304 MiB
2022/04/13 01:57:56.365, Tesla V100-SXM2-32GB, 470.57.02, 68 %, 11 %, 32510 MiB, 5170 MiB, 27340 MiB
2022/04/13 01:57:56.366, Tesla V100-SXM2-32GB, 470.57.02, 22 %, 15 %, 32510 MiB, 5090 MiB, 27420 MiB
2022/04/13 01:57:56.372, Tesla V100-SXM2-32GB, 470.57.02, 97 %, 56 %, 32510 MiB, 5214 MiB, 27296 MiB
2022/04/13 01:57:56.373, Tesla V100-SXM2-32GB, 470.57.02, 68 %, 11 %, 32510 MiB, 5170 MiB, 27340 MiB
2022/04/13 01:57:56.379, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 47 %, 32510 MiB, 5146 MiB, 27364 MiB
2022/04/13 01:57:56.387, Tesla V100-SXM2-32GB, 470.57.02, 22 %, 15 %, 32510 MiB, 5090 MiB, 27420 MiB
timestamp, name, driver_version, utilization.gpu [%], utilization.memory [%], memory.total [MiB], memory.free [MiB], memory.used [MiB]
2022/04/13 01:57:56.398, Tesla V100-SXM2-32GB, 470.57.02, 68 %, 11 %, 32510 MiB, 5170 MiB, 27340 MiB
2022/04/13 01:57:56.415, Tesla V100-SXM2-32GB, 470.57.02, 34 %, 0 %, 32510 MiB, 5134 MiB, 27376 MiB
2022/04/13 01:57:56.424, Tesla V100-SXM2-32GB, 470.57.02, 26 %, 8 %, 32510 MiB, 5154 MiB, 27356 MiB
timestamp, name, driver_version, utilization.gpu [%], utilization.memory [%], memory.total [MiB], memory.free [MiB], memory.used [MiB]
timestamp, name, driver_version, utilization.gpu [%], utilization.memory [%], memory.total [MiB], memory.free [MiB], memory.used [MiB]
2022/04/13 01:57:56.440, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 87 %, 32510 MiB, 5230 MiB, 27280 MiB
2022/04/13 01:57:56.493, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 86 %, 32510 MiB, 5134 MiB, 27376 MiB
2022/04/13 01:57:56.493, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 86 %, 32510 MiB, 5134 MiB, 27376 MiB
2022/04/13 01:57:56.494, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 84 %, 32510 MiB, 5206 MiB, 27304 MiB
2022/04/13 01:57:56.518, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 89 %, 32510 MiB, 5154 MiB, 27356 MiB
2022/04/13 01:57:56.518, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 89 %, 32510 MiB, 5154 MiB, 27356 MiB
2022/04/13 01:57:56.519, Tesla V100-SXM2-32GB, 470.57.02, 97 %, 53 %, 32510 MiB, 5214 MiB, 27296 MiB
2022/04/13 01:57:56.535, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 87 %, 32510 MiB, 5230 MiB, 27280 MiB
2022/04/13 01:57:56.535, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 87 %, 32510 MiB, 5230 MiB, 27280 MiB
2022/04/13 01:57:56.535, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 78 %, 32510 MiB, 5146 MiB, 27364 MiB
2022/04/13 01:57:56.552, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 84 %, 32510 MiB, 5206 MiB, 27304 MiB
2022/04/13 01:57:56.552, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 84 %, 32510 MiB, 5206 MiB, 27304 MiB
2022/04/13 01:57:56.553, Tesla V100-SXM2-32GB, 470.57.02, 69 %, 54 %, 32510 MiB, 5090 MiB, 27420 MiB
2022/04/13 01:57:56.570, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 74 %, 32510 MiB, 5214 MiB, 27296 MiB
2022/04/13 01:57:56.570, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 74 %, 32510 MiB, 5214 MiB, 27296 MiB
2022/04/13 01:57:56.571, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 86 %, 32510 MiB, 5170 MiB, 27340 MiB
2022/04/13 01:57:56.591, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 78 %, 32510 MiB, 5146 MiB, 27364 MiB
2022/04/13 01:57:56.591, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 78 %, 32510 MiB, 5146 MiB, 27364 MiB
2022/04/13 01:57:56.612, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 75 %, 32510 MiB, 5090 MiB, 27420 MiB
2022/04/13 01:57:56.612, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 75 %, 32510 MiB, 5090 MiB, 27420 MiB
timestamp, name, driver_version, utilization.gpu [%], utilization.memory [%], memory.total [MiB], memory.free [MiB], memory.used [MiB]
2022/04/13 01:57:56.644, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 51 %, 32510 MiB, 5170 MiB, 27340 MiB
2022/04/13 01:57:56.644, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 51 %, 32510 MiB, 5170 MiB, 27340 MiB
2022/04/13 01:57:56.646, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 54 %, 32510 MiB, 5134 MiB, 27376 MiB
timestamp, name, driver_version, utilization.gpu [%], utilization.memory [%], memory.total [MiB], memory.free [MiB], memory.used [MiB]
2022/04/13 01:57:56.651, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 89 %, 32510 MiB, 5154 MiB, 27356 MiB
2022/04/13 01:57:56.656, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 54 %, 32510 MiB, 5134 MiB, 27376 MiB
2022/04/13 01:57:56.658, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 53 %, 32510 MiB, 5230 MiB, 27280 MiB
2022/04/13 01:57:56.661, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 89 %, 32510 MiB, 5154 MiB, 27356 MiB
2022/04/13 01:57:56.663, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 45 %, 32510 MiB, 5206 MiB, 27304 MiB
2022/04/13 01:57:56.665, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 53 %, 32510 MiB, 5230 MiB, 27280 MiB
2022/04/13 01:57:56.671, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 74 %, 32510 MiB, 5214 MiB, 27296 MiB
2022/04/13 01:57:56.680, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 45 %, 32510 MiB, 5206 MiB, 27304 MiB
2022/04/13 01:57:56.682, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 43 %, 32510 MiB, 5146 MiB, 27364 MiB
2022/04/13 01:57:56.684, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 74 %, 32510 MiB, 5214 MiB, 27296 MiB
2022/04/13 01:57:56.685, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 75 %, 32510 MiB, 5090 MiB, 27420 MiB
2022/04/13 01:57:56.687, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 43 %, 32510 MiB, 5146 MiB, 27364 MiB
2022/04/13 01:57:56.688, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 51 %, 32510 MiB, 5170 MiB, 27340 MiB
2022/04/13 01:57:56.690, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 75 %, 32510 MiB, 5090 MiB, 27420 MiB
2022/04/13 01:57:56.693, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 51 %, 32510 MiB, 5170 MiB, 27340 MiB
[rank:4] [train], epoch: 0/1, iter: 200/625, loss: 0.86717, lr: 0.000000, top1: 0.00090, throughput: 295.56 | 2022-04-13 01:59:22.810
[rank:2] [train], epoch: 0/1, iter: 200/625, loss: 0.86705, lr: 0.000000, top1: 0.00129, throughput: 295.56 | 2022-04-13 01:59:22.810
[rank:1] [train], epoch: 0/1, iter: 200/625, loss: 0.86741, lr: 0.000000, top1: 0.00105, throughput: 295.68 | 2022-04-13 01:59:22.813
[rank:7] [train], epoch: 0/1, iter: 200/625, loss: 0.86741, lr: 0.000000, top1: 0.00098, throughput: 295.42 | 2022-04-13 01:59:22.814
[rank:3] [train], epoch: 0/1, iter: 200/625, loss: 0.86734, lr: 0.000000, top1: 0.00109, throughput: 295.28 | 2022-04-13 01:59:22.846
[rank:5] [train], epoch: 0/1, iter: 200/625, loss: 0.86760, lr: 0.000000, top1: 0.00113, throughput: 295.21 | 2022-04-13 01:59:22.869
[rank:0] [train], epoch: 0/1, iter: 200/625, loss: 0.86727, lr: 0.000000, top1: 0.00113, throughput: 295.33 | 2022-04-13 01:59:22.876
[rank:6] [train], epoch: 0/1, iter: 200/625, loss: 0.86712, lr: 0.000000, top1: 0.00105, throughput: 295.38 | 2022-04-13 01:59:22.913
[rank:5] [train], epoch: 0/1, iter: 300/625, loss: 0.86736, lr: 0.000000, top1: 0.00090, throughput: 296.70 | 2022-04-13 02:00:49.152
[rank:7] [train], epoch: 0/1, iter: 300/625, loss: 0.86745, lr: 0.000000, top1: 0.00133, throughput: 296.50 | 2022-04-13 02:00:49.154
[rank:4] [train], epoch: 0/1, iter: 300/625, loss: 0.86759, lr: 0.000000, top1: 0.00086, throughput: 296.42 | 2022-04-13 02:00:49.172
[rank:0] [train], epoch: 0/1, iter: 300/625, loss: 0.86742, lr: 0.000000, top1: 0.00094, throughput: 296.62 | 2022-04-13 02:00:49.183
[rank:3] [train], epoch: 0/1, iter: 300/625, loss: 0.86731, lr: 0.000000, top1: 0.00195, throughput: 296.50 | 2022-04-13 02:00:49.186
[rank:2] [train], epoch: 0/1, iter: 300/625, loss: 0.86744, lr: 0.000000, top1: 0.00121, throughput: 296.35 | 2022-04-13 02:00:49.193
[rank:1] [train], epoch: 0/1, iter: 300/625, loss: 0.86763, lr: 0.000000, top1: 0.00102, throughput: 296.26 | 2022-04-13 02:00:49.223
[rank:6] [train], epoch: 0/1, iter: 300/625, loss: 0.86743, lr: 0.000000, top1: 0.00070, throughput: 296.58 | 2022-04-13 02:00:49.230