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: 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/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 ............................... 625
  channel_last .................................... False
  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 ................................... 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 ...................................... True
  skip_eval ....................................... True
  synthetic_data .................................. False
  total_batches ................................... -1
  train_batch_size ................................ 256
  train_global_batch_size ......................... 2048
  use_fp16 ........................................ False
  use_gpu_decode .................................. True
  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: 3.15560 s *****
[rank:4] [train], epoch: 0/1, iter: 100/625, loss: 0.86741, top1: 0.00090, throughput: 265.27[rank:3] [train], epoch: 0/1, iter: 100/625, loss: 0.86742, top1: 0.00137, throughput: 265.30 | 2022-05-03 02:03:53.347
 | 2022-05-03 02:03:53.347
[rank:7] [train], epoch: 0/1, iter: 100/625, loss: 0.86743, top1: 0.00156, throughput: 265.27 | 2022-05-03 02:03:53.347
[rank:2] [train], epoch: 0/1, iter: 100/625, loss: 0.86731, top1: 0.00141, throughput: 265.28 | 2022-05-03 02:03:53.346
[rank:5] [train], epoch: 0/1, iter: 100/625, loss: 0.86743, top1: 0.00082, throughput: 265.29 | 2022-05-03 02:03:53.345
[rank:0] [train], epoch: 0/1, iter: 100/625, loss: 0.86742, top1: 0.00121, throughput: 265.27 | 2022-05-03 02:03:53.347
[rank:1] [train], epoch: 0/1, iter: 100/625, loss: 0.86756, top1: 0.00105, throughput: 265.26 | 2022-05-03 02:03:53.347
[rank:6] [train], epoch: 0/1, iter: 100/625, loss: 0.86743, top1: 0.00117, throughput: 265.27 | 2022-05-03 02:03:53.349
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]
2022/05/03 02:03:53.629, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 60 %, 32510 MiB, 7805 MiB, 24705 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]
2022/05/03 02:03:53.629, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 60 %, 32510 MiB, 7805 MiB, 24705 MiB
2022/05/03 02:03:53.642, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 58 %, 32510 MiB, 7722 MiB, 24788 MiB
timestamp, name, driver_version, utilization.gpu [%], utilization.memory [%], memory.total [MiB], memory.free [MiB], memory.used [MiB]
2022/05/03 02:03:53.642, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 58 %, 32510 MiB, 7722 MiB, 24788 MiB
2022/05/03 02:03:53.642, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 60 %, 32510 MiB, 7805 MiB, 24705 MiB
2022/05/03 02:03:53.642, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 60 %, 32510 MiB, 7805 MiB, 24705 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]
timestamp, name, driver_version, utilization.gpu [%], utilization.memory [%], memory.total [MiB], memory.free [MiB], memory.used [MiB]
2022/05/03 02:03:53.649, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 56 %, 32510 MiB, 7872 MiB, 24638 MiB
2022/05/03 02:03:53.649, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 56 %, 32510 MiB, 7872 MiB, 24638 MiB
2022/05/03 02:03:53.650, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 63 %, 32510 MiB, 7722 MiB, 24788 MiB
2022/05/03 02:03:53.649, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 60 %, 32510 MiB, 7805 MiB, 24705 MiB
2022/05/03 02:03:53.650, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 63 %, 32510 MiB, 7722 MiB, 24788 MiB
2022/05/03 02:03:53.651, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 60 %, 32510 MiB, 7805 MiB, 24705 MiB
2022/05/03 02:03:53.657, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 60 %, 32510 MiB, 7805 MiB, 24705 MiB
2022/05/03 02:03:53.658, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 60 %, 32510 MiB, 7805 MiB, 24705 MiB
2022/05/03 02:03:53.662, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 56 %, 32510 MiB, 7850 MiB, 24660 MiB
2022/05/03 02:03:53.663, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 56 %, 32510 MiB, 7850 MiB, 24660 MiB
2022/05/03 02:03:53.663, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 56 %, 32510 MiB, 7872 MiB, 24638 MiB
2022/05/03 02:03:53.663, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 63 %, 32510 MiB, 7722 MiB, 24788 MiB
2022/05/03 02:03:53.664, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 56 %, 32510 MiB, 7872 MiB, 24638 MiB
2022/05/03 02:03:53.665, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 63 %, 32510 MiB, 7722 MiB, 24788 MiB
2022/05/03 02:03:53.668, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 63 %, 32510 MiB, 7722 MiB, 24788 MiB
2022/05/03 02:03:53.669, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 63 %, 32510 MiB, 7722 MiB, 24788 MiB
2022/05/03 02:03:53.671, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 61 %, 32510 MiB, 7836 MiB, 24674 MiB
2022/05/03 02:03:53.671, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 61 %, 32510 MiB, 7836 MiB, 24674 MiB
2022/05/03 02:03:53.672, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 56 %, 32510 MiB, 7850 MiB, 24660 MiB
2022/05/03 02:03:53.672, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 56 %, 32510 MiB, 7872 MiB, 24638 MiB
2022/05/03 02:03:53.672, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 56 %, 32510 MiB, 7850 MiB, 24660 MiB
2022/05/03 02:03:53.674, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 56 %, 32510 MiB, 7872 MiB, 24638 MiB
2022/05/03 02:03:53.676, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 56 %, 32510 MiB, 7872 MiB, 24638 MiB
2022/05/03 02:03:53.677, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 56 %, 32510 MiB, 7872 MiB, 24638 MiB
2022/05/03 02:03:53.680, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 57 %, 32510 MiB, 7736 MiB, 24774 MiB
2022/05/03 02:03:53.681, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 57 %, 32510 MiB, 7736 MiB, 24774 MiB
2022/05/03 02:03:53.682, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 61 %, 32510 MiB, 7836 MiB, 24674 MiB
2022/05/03 02:03:53.682, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 56 %, 32510 MiB, 7850 MiB, 24660 MiB
2022/05/03 02:03:53.682, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 61 %, 32510 MiB, 7836 MiB, 24674 MiB
2022/05/03 02:03:53.684, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 56 %, 32510 MiB, 7850 MiB, 24660 MiB
2022/05/03 02:03:53.686, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 56 %, 32510 MiB, 7850 MiB, 24660 MiB
2022/05/03 02:03:53.687, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 56 %, 32510 MiB, 7850 MiB, 24660 MiB
2022/05/03 02:03:53.689, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 60 %, 32510 MiB, 7632 MiB, 24878 MiB
2022/05/03 02:03:53.690, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 60 %, 32510 MiB, 7632 MiB, 24878 MiB
2022/05/03 02:03:53.690, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 57 %, 32510 MiB, 7736 MiB, 24774 MiB
2022/05/03 02:03:53.691, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 61 %, 32510 MiB, 7836 MiB, 24674 MiB
2022/05/03 02:03:53.691, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 57 %, 32510 MiB, 7736 MiB, 24774 MiB
2022/05/03 02:03:53.693, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 61 %, 32510 MiB, 7836 MiB, 24674 MiB
2022/05/03 02:03:53.695, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 61 %, 32510 MiB, 7836 MiB, 24674 MiB
2022/05/03 02:03:53.696, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 61 %, 32510 MiB, 7836 MiB, 24674 MiB
2022/05/03 02:03:53.698, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 61 %, 32510 MiB, 7780 MiB, 24730 MiB
2022/05/03 02:03:53.700, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 61 %, 32510 MiB, 7780 MiB, 24730 MiB
2022/05/03 02:03:53.700, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 60 %, 32510 MiB, 7632 MiB, 24878 MiB
2022/05/03 02:03:53.700, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 57 %, 32510 MiB, 7736 MiB, 24774 MiB
2022/05/03 02:03:53.701, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 60 %, 32510 MiB, 7632 MiB, 24878 MiB
2022/05/03 02:03:53.702, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 57 %, 32510 MiB, 7736 MiB, 24774 MiB
2022/05/03 02:03:53.705, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 57 %, 32510 MiB, 7736 MiB, 24774 MiB
2022/05/03 02:03:53.706, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 57 %, 32510 MiB, 7736 MiB, 24774 MiB
2022/05/03 02:03:53.708, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 61 %, 32510 MiB, 7780 MiB, 24730 MiB
2022/05/03 02:03:53.709, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 60 %, 32510 MiB, 7632 MiB, 24878 MiB
2022/05/03 02:03:53.709, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 61 %, 32510 MiB, 7780 MiB, 24730 MiB
2022/05/03 02:03:53.711, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 60 %, 32510 MiB, 7632 MiB, 24878 MiB
2022/05/03 02:03:53.713, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 60 %, 32510 MiB, 7632 MiB, 24878 MiB
2022/05/03 02:03:53.714, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 60 %, 32510 MiB, 7632 MiB, 24878 MiB
2022/05/03 02:03:53.716, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 61 %, 32510 MiB, 7780 MiB, 24730 MiB
2022/05/03 02:03:53.718, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 61 %, 32510 MiB, 7780 MiB, 24730 MiB
2022/05/03 02:03:53.721, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 61 %, 32510 MiB, 7780 MiB, 24730 MiB
2022/05/03 02:03:53.722, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 61 %, 32510 MiB, 7780 MiB, 24730 MiB
[rank:5] [train], epoch: 0/1, iter: 200/625, loss: 0.86728, top1: 0.00066, throughput: 375.53 | 2022-05-03 02:05:01.516
[rank:3] [train], epoch: 0/1, iter: 200/625, loss: 0.86759, top1: 0.00113, throughput: 375.52 | 2022-05-03 02:05:01.518
[rank:2] [train], epoch: 0/1, iter: 200/625, loss: 0.86737, top1: 0.00121, throughput: 375.52 | 2022-05-03 02:05:01.518
[rank:4] [train], epoch: 0/1, iter: 200/625, loss: 0.86744, top1: 0.00086, throughput: 375.52 | 2022-05-03 02:05:01.519
[rank:1] [train], epoch: 0/1, iter: 200/625, loss: 0.86711, top1: 0.00098, throughput: 375.52 | 2022-05-03 02:05:01.519
[rank:0] [train], epoch: 0/1, iter: 200/625, loss: 0.86714, top1: 0.00113, throughput: 375.52 | 2022-05-03 02:05:01.519
[rank:7] [train], epoch: 0/1, iter: 200/625, loss: 0.86720, top1: 0.00145, throughput: 375.52 | 2022-05-03 02:05:01.519
[rank:6] [train], epoch: 0/1, iter: 200/625, loss: 0.86714, top1: 0.00117, throughput: 375.53 | 2022-05-03 02:05:01.519
[rank:2] [train], epoch: 0/1, iter: 300/625, loss: 0.86722, top1: 0.00102, throughput: 375.01 | 2022-05-03 02:06:09.782
[rank:7] [train], epoch: 0/1, iter: 300/625, loss: 0.86741, top1: 0.00109, throughput: 375.01 | 2022-05-03 02:06:09.785
[rank:1] [train], epoch: 0/1, iter: 300/625, loss: 0.86687, top1: 0.00148, throughput: 375.00 | 2022-05-03 02:06:09.785
[rank:3] [train], epoch: 0/1, iter: 300/625, loss: 0.86738, top1: 0.00105, throughput: 374.99 | 2022-05-03 02:06:09.786
[rank:6] [train], epoch: 0/1, iter: 300/625, loss: 0.86722, top1: 0.00113, throughput: 375.01 | 2022-05-03 02:06:09.785
[rank:0] [train], epoch: 0/1, iter: 300/625, loss: 0.86699, top1: 0.00086, throughput: 375.01 | 2022-05-03 02:06:09.785
[rank:5] [train], epoch: 0/1, iter: 300/625, loss: 0.86729, top1: 0.00137, throughput: 375.00 | 2022-05-03 02:06:09.783
[rank:4] [train], epoch: 0/1, iter: 300/625, loss: 0.86756, top1: 0.00109, throughput: 375.00 | 2022-05-03 02:06:09.786