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: loaded library: /usr/lib/x86_64-linux-gnu/libibverbs.so.1/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: /usr/lib/x86_64-linux-gnu/libibverbs.so.1
loaded library: /usr/lib/x86_64-linux-gnu/libibverbs.so.1
------------------------ arguments ------------------------
  batches_per_epoch ............................... 312
  channel_last .................................... True
  ddp ............................................. False
  exit_num ........................................ 300
  fuse_bn_add_relu ................................ True
  fuse_bn_relu .................................... True
  gpu_stat_file ................................... None
  grad_clipping ................................... 0.0
  graph ........................................... True
  label_smoothing ................................. 0.1
  learning_rate ................................... 4.096
  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 ...................................... True
  skip_eval ....................................... True
  synthetic_data .................................. False
  total_batches ................................... -1
  train_batch_size ................................ 512
  train_global_batch_size ......................... 4096
  use_fp16 ........................................ True
  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: 3.13038 s *****
[rank:1] [train], epoch: 0/1, iter: 100/312, loss: 0.86745, top1: 0.00092, throughput: 447.71 | 2022-05-22 18:52:33.418
[rank:5] [train], epoch: 0/1, iter: 100/312, loss: 0.86745, top1: 0.00102, throughput: 447.74 | 2022-05-22 18:52:33.418
[rank:6] [train], epoch: 0/1, iter: 100/312, loss: 0.86745, top1: 0.00102, throughput: 447.74 | 2022-05-22 18:52:33.420
[rank:3] [train], epoch: 0/1, iter: 100/312, loss: 0.86740, top1: 0.00104, throughput: 447.72 | 2022-05-22 18:52:33.422
[rank:0] [train], epoch: 0/1, iter: 100/312, loss: 0.86713, top1: 0.00107, throughput: 447.70 | 2022-05-22 18:52:33.422
[rank:7] [train], epoch: 0/1, iter: 100/312, loss: 0.86734, top1: 0.00078, throughput: 447.71 | 2022-05-22 18:52:33.420
[rank:4] [train], epoch: 0/1, iter: 100/312, loss: 0.86735, top1: 0.00090, throughput: 447.73 | 2022-05-22 18:52:33.422
[rank:2] [train], epoch: 0/1, iter: 100/312, loss: 0.86744, top1: 0.00092, throughput: 447.70 | 2022-05-22 18:52:33.421
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]
timestamp, name, driver_version, utilization.gpu [%], utilization.memory [%], memory.total [MiB], memory.free [MiB], memory.used [MiB]
2022/05/22 18:52:33.730, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 50 %, 32510 MiB, 8555 MiB, 23955 MiB
2022/05/22 18:52:33.731, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 50 %, 32510 MiB, 8555 MiB, 23955 MiB
timestamp, name, driver_version, utilization.gpu [%], utilization.memory [%], memory.total [MiB], memory.free [MiB], memory.used [MiB]
2022/05/22 18:52:33.731, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 50 %, 32510 MiB, 8555 MiB, 23955 MiB
2022/05/22 18:52:33.738, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 63 %, 32510 MiB, 8542 MiB, 23968 MiB
2022/05/22 18:52:33.739, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 63 %, 32510 MiB, 8542 MiB, 23968 MiB
2022/05/22 18:52:33.740, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 63 %, 32510 MiB, 8542 MiB, 23968 MiB
2022/05/22 18:52:33.740, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 50 %, 32510 MiB, 8555 MiB, 23955 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]
2022/05/22 18:52:33.746, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 58 %, 32510 MiB, 8716 MiB, 23794 MiB
timestamp, name, driver_version, utilization.gpu [%], utilization.memory [%], memory.total [MiB], memory.free [MiB], memory.used [MiB]
2022/05/22 18:52:33.746, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 58 %, 32510 MiB, 8716 MiB, 23794 MiB
2022/05/22 18:52:33.747, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 58 %, 32510 MiB, 8716 MiB, 23794 MiB
2022/05/22 18:52:33.747, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 63 %, 32510 MiB, 8542 MiB, 23968 MiB
timestamp, name, driver_version, utilization.gpu [%], utilization.memory [%], memory.total [MiB], memory.free [MiB], memory.used [MiB]
2022/05/22 18:52:33.747, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 50 %, 32510 MiB, 8555 MiB, 23955 MiB
2022/05/22 18:52:33.750, Tesla V100-SXM2-32GB, 470.57.02, 98 %, 91 %, 32510 MiB, 8555 MiB, 23955 MiB
2022/05/22 18:52:33.752, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 83 %, 32510 MiB, 8666 MiB, 23844 MiB
2022/05/22 18:52:33.753, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 83 %, 32510 MiB, 8666 MiB, 23844 MiB
2022/05/22 18:52:33.753, Tesla V100-SXM2-32GB, 470.57.02, 98 %, 91 %, 32510 MiB, 8555 MiB, 23955 MiB
2022/05/22 18:52:33.753, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 83 %, 32510 MiB, 8666 MiB, 23844 MiB
2022/05/22 18:52:33.754, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 58 %, 32510 MiB, 8716 MiB, 23794 MiB
2022/05/22 18:52:33.754, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 63 %, 32510 MiB, 8542 MiB, 23968 MiB
2022/05/22 18:52:33.754, Tesla V100-SXM2-32GB, 470.57.02, 98 %, 91 %, 32510 MiB, 8555 MiB, 23955 MiB
2022/05/22 18:52:33.758, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 63 %, 32510 MiB, 8542 MiB, 23968 MiB
2022/05/22 18:52:33.760, Tesla V100-SXM2-32GB, 470.57.02, 98 %, 90 %, 32510 MiB, 8686 MiB, 23824 MiB
2022/05/22 18:52:33.761, Tesla V100-SXM2-32GB, 470.57.02, 98 %, 90 %, 32510 MiB, 8686 MiB, 23824 MiB
2022/05/22 18:52:33.762, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 63 %, 32510 MiB, 8542 MiB, 23968 MiB
2022/05/22 18:52:33.762, Tesla V100-SXM2-32GB, 470.57.02, 98 %, 90 %, 32510 MiB, 8686 MiB, 23824 MiB
2022/05/22 18:52:33.762, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 83 %, 32510 MiB, 8666 MiB, 23844 MiB
2022/05/22 18:52:33.763, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 58 %, 32510 MiB, 8716 MiB, 23794 MiB
2022/05/22 18:52:33.764, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 63 %, 32510 MiB, 8542 MiB, 23968 MiB
2022/05/22 18:52:33.767, Tesla V100-SXM2-32GB, 470.57.02, 98 %, 88 %, 32510 MiB, 8716 MiB, 23794 MiB
2022/05/22 18:52:33.769, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 70 %, 32510 MiB, 8546 MiB, 23964 MiB
2022/05/22 18:52:33.770, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 70 %, 32510 MiB, 8546 MiB, 23964 MiB
2022/05/22 18:52:33.770, Tesla V100-SXM2-32GB, 470.57.02, 98 %, 88 %, 32510 MiB, 8716 MiB, 23794 MiB
2022/05/22 18:52:33.771, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 70 %, 32510 MiB, 8546 MiB, 23964 MiB
2022/05/22 18:52:33.771, Tesla V100-SXM2-32GB, 470.57.02, 98 %, 90 %, 32510 MiB, 8686 MiB, 23824 MiB
2022/05/22 18:52:33.772, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 83 %, 32510 MiB, 8666 MiB, 23844 MiB
2022/05/22 18:52:33.773, Tesla V100-SXM2-32GB, 470.57.02, 98 %, 88 %, 32510 MiB, 8716 MiB, 23794 MiB
2022/05/22 18:52:33.776, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 83 %, 32510 MiB, 8666 MiB, 23844 MiB
2022/05/22 18:52:33.777, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 93 %, 32510 MiB, 8436 MiB, 24074 MiB
2022/05/22 18:52:33.779, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 93 %, 32510 MiB, 8436 MiB, 24074 MiB
2022/05/22 18:52:33.779, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 83 %, 32510 MiB, 8666 MiB, 23844 MiB
2022/05/22 18:52:33.779, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 93 %, 32510 MiB, 8436 MiB, 24074 MiB
2022/05/22 18:52:33.783, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 79 %, 32510 MiB, 8546 MiB, 23964 MiB
2022/05/22 18:52:33.788, Tesla V100-SXM2-32GB, 470.57.02, 98 %, 88 %, 32510 MiB, 8686 MiB, 23824 MiB
2022/05/22 18:52:33.788, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 83 %, 32510 MiB, 8666 MiB, 23844 MiB
2022/05/22 18:52:33.792, Tesla V100-SXM2-32GB, 470.57.02, 98 %, 88 %, 32510 MiB, 8686 MiB, 23824 MiB
2022/05/22 18:52:33.811, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 72 %, 32510 MiB, 8614 MiB, 23896 MiB
2022/05/22 18:52:33.813, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 72 %, 32510 MiB, 8614 MiB, 23896 MiB
2022/05/22 18:52:33.818, Tesla V100-SXM2-32GB, 470.57.02, 98 %, 88 %, 32510 MiB, 8686 MiB, 23824 MiB
2022/05/22 18:52:33.818, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 72 %, 32510 MiB, 8614 MiB, 23896 MiB
2022/05/22 18:52:33.821, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 93 %, 32510 MiB, 8436 MiB, 24074 MiB
2022/05/22 18:52:33.824, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 79 %, 32510 MiB, 8546 MiB, 23964 MiB
2022/05/22 18:52:33.825, Tesla V100-SXM2-32GB, 470.57.02, 98 %, 88 %, 32510 MiB, 8686 MiB, 23824 MiB
2022/05/22 18:52:33.830, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 79 %, 32510 MiB, 8546 MiB, 23964 MiB
2022/05/22 18:52:33.838, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 79 %, 32510 MiB, 8546 MiB, 23964 MiB
2022/05/22 18:52:33.841, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 72 %, 32510 MiB, 8614 MiB, 23896 MiB
2022/05/22 18:52:33.843, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 93 %, 32510 MiB, 8436 MiB, 24074 MiB
2022/05/22 18:52:33.847, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 79 %, 32510 MiB, 8546 MiB, 23964 MiB
2022/05/22 18:52:33.850, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 93 %, 32510 MiB, 8436 MiB, 24074 MiB
2022/05/22 18:52:33.855, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 93 %, 32510 MiB, 8436 MiB, 24074 MiB
2022/05/22 18:52:33.856, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 72 %, 32510 MiB, 8614 MiB, 23896 MiB
2022/05/22 18:52:33.858, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 93 %, 32510 MiB, 8436 MiB, 24074 MiB
2022/05/22 18:52:33.867, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 72 %, 32510 MiB, 8614 MiB, 23896 MiB
2022/05/22 18:52:33.870, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 72 %, 32510 MiB, 8614 MiB, 23896 MiB
2022/05/22 18:52:33.871, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 72 %, 32510 MiB, 8614 MiB, 23896 MiB
[rank:4] [train], epoch: 0/1, iter: 200/312, loss: 0.86761, top1: 0.00084, throughput: 1352.20[rank:1] [train], epoch: 0/1, iter: 200/312, loss: 0.86729, top1: 0.00104, throughput: 1352.13  | 2022-05-22 18:53:11.286| 2022-05-22 18:53:11.285

[rank:3] [train], epoch: 0/1, iter: 200/312, loss: 0.86737, top1: 0.00121, throughput: 1352.09 | 2022-05-22 18:53:11.289
[rank:0] [train], epoch: 0/1, iter: 200/312, loss: 0.86734, top1: 0.00078, throughput: 1352.12 | 2022-05-22 18:53:11.289
[rank:5] [train], epoch: 0/1, iter: 200/312, loss: 0.86739, top1: 0.00092, throughput: 1352.10 | 2022-05-22 18:53:11.285
[rank:2] [train], epoch: 0/1, iter: 200/312, loss: 0.86722, top1: 0.00086, throughput: 1352.10 | 2022-05-22 18:53:11.288
[rank:6] [train], epoch: 0/1, iter: 200/312, loss: 0.86726, top1: 0.00102, throughput: 1352.15 | 2022-05-22 18:53:11.286
[rank:7] [train], epoch: 0/1, iter: 200/312, loss: 0.86737, top1: 0.00092, throughput: 1352.13 | 2022-05-22 18:53:11.286
[rank:0] [train], epoch: 0/1, iter: 300/312, loss: 0.86740, top1: 0.00115, throughput: 1343.78 | 2022-05-22 18:53:49.390
[rank:7] [train], epoch: 0/1, iter: 300/312, loss: 0.86753, top1: 0.00117, throughput: 1343.71 | 2022-05-22 18:53:49.390
[rank:3] [train], epoch: 0/1, iter: 300/312, loss: 0.86741, top1: 0.00096, throughput: 1343.78 | 2022-05-22 18:53:49.390
[rank:2] [train], epoch: 0/1, iter: 300/312, loss: 0.86733, top1: 0.00105, throughput: 1343.81 [rank:1] [train], epoch: 0/1, iter: 300/312, loss: 0.86712, top1: 0.00066, throughput: 1343.60| 2022-05-22 18:53:49.389 | 2022-05-22 18:53:49.391

[rank:6] [train], epoch: 0/1, iter: 300/312, loss: 0.86725, top1: 0.00111, throughput: 1343.71 | 2022-05-22 18:53:49.389
[rank:4] [train], epoch: 0/1, iter: 300/312, loss: 0.86740, top1: 0.00094, throughput: 1343.63 | 2022-05-22 18:53:49.392
[rank:5] [train], epoch: 0/1, iter: 300/312, loss: 0.86742, top1: 0.00094, throughput: 1343.71 | 2022-05-22 18:53:49.389