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: /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
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 .................................. 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: 2.56380 s *****
[rank:4] [train], epoch: 0/1, iter: 100/625, loss: 0.86804, top1: 0.00102, throughput: 275.69 | 2022-04-22 10:20:53.415
[rank:5] [train], epoch: 0/1, iter: 100/625, loss: 0.86798, top1: 0.00078, throughput: 275.85 | 2022-04-22 10:20:53.417
[rank:0] [train], epoch: 0/1, iter: 100/625, loss: 0.86768, top1: 0.00090, throughput: 275.80 | 2022-04-22 10:20:53.421
[rank:1] [train], epoch: 0/1, iter: 100/625, loss: 0.86810, top1: 0.00129, throughput: 274.44 | 2022-04-22 10:20:53.420
[rank:3] [train], epoch: 0/1, iter: 100/625, loss: 0.86795, top1: 0.00129, throughput: 275.67 | 2022-04-22 10:20:53.422
[rank:6] [train], epoch: 0/1, iter: 100/625, loss: 0.86820, top1: 0.00098, throughput: 275.72 | 2022-04-22 10:20:53.417
[rank:2] [train], epoch: 0/1, iter: 100/625, loss: 0.86824, top1: 0.00121, throughput: 275.87 | 2022-04-22 10:20:53.419
[rank:7] [train], epoch: 0/1, iter: 100/625, loss: 0.86781, top1: 0.00090, throughput: 275.92 | 2022-04-22 10:20:53.422
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]
2022/04/22 10:20:53.797, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 63 %, 32510 MiB, 8476 MiB, 24034 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]
2022/04/22 10:20:53.803, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 63 %, 32510 MiB, 8476 MiB, 24034 MiB
2022/04/22 10:20:53.804, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 61 %, 32510 MiB, 8514 MiB, 23996 MiB
2022/04/22 10:20:53.810, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 63 %, 32510 MiB, 8476 MiB, 24034 MiB
2022/04/22 10:20:53.810, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 63 %, 32510 MiB, 8476 MiB, 24034 MiB
2022/04/22 10:20:53.811, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 63 %, 32510 MiB, 8476 MiB, 24034 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]
2022/04/22 10:20:53.814, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 61 %, 32510 MiB, 8514 MiB, 23996 MiB
2022/04/22 10:20:53.815, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 65 %, 32510 MiB, 8634 MiB, 23876 MiB
timestamp, name, driver_version, utilization.gpu [%], utilization.memory [%], memory.total [MiB], memory.free [MiB], memory.used [MiB]
2022/04/22 10:20:53.817, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 61 %, 32510 MiB, 8514 MiB, 23996 MiB
2022/04/22 10:20:53.818, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 61 %, 32510 MiB, 8514 MiB, 23996 MiB
2022/04/22 10:20:53.818, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 61 %, 32510 MiB, 8514 MiB, 23996 MiB
2022/04/22 10:20:53.819, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 63 %, 32510 MiB, 8476 MiB, 24034 MiB
2022/04/22 10:20:53.821, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 65 %, 32510 MiB, 8634 MiB, 23876 MiB
2022/04/22 10:20:53.821, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 61 %, 32510 MiB, 8610 MiB, 23900 MiB
2022/04/22 10:20:53.820, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 63 %, 32510 MiB, 8476 MiB, 24034 MiB
2022/04/22 10:20:53.822, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 63 %, 32510 MiB, 8476 MiB, 24034 MiB
2022/04/22 10:20:53.825, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 65 %, 32510 MiB, 8634 MiB, 23876 MiB
2022/04/22 10:20:53.826, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 65 %, 32510 MiB, 8634 MiB, 23876 MiB
2022/04/22 10:20:53.826, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 65 %, 32510 MiB, 8634 MiB, 23876 MiB
2022/04/22 10:20:53.828, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 61 %, 32510 MiB, 8514 MiB, 23996 MiB
2022/04/22 10:20:53.829, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 61 %, 32510 MiB, 8610 MiB, 23900 MiB
2022/04/22 10:20:53.829, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 65 %, 32510 MiB, 8628 MiB, 23882 MiB
2022/04/22 10:20:53.830, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 61 %, 32510 MiB, 8514 MiB, 23996 MiB
2022/04/22 10:20:53.832, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 61 %, 32510 MiB, 8514 MiB, 23996 MiB
2022/04/22 10:20:53.833, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 61 %, 32510 MiB, 8610 MiB, 23900 MiB
2022/04/22 10:20:53.834, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 61 %, 32510 MiB, 8610 MiB, 23900 MiB
2022/04/22 10:20:53.834, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 61 %, 32510 MiB, 8610 MiB, 23900 MiB
2022/04/22 10:20:53.837, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 65 %, 32510 MiB, 8634 MiB, 23876 MiB
2022/04/22 10:20:53.838, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 65 %, 32510 MiB, 8628 MiB, 23882 MiB
2022/04/22 10:20:53.838, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 64 %, 32510 MiB, 8492 MiB, 24018 MiB
2022/04/22 10:20:53.838, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 65 %, 32510 MiB, 8634 MiB, 23876 MiB
2022/04/22 10:20:53.840, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 65 %, 32510 MiB, 8634 MiB, 23876 MiB
2022/04/22 10:20:53.842, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 65 %, 32510 MiB, 8628 MiB, 23882 MiB
2022/04/22 10:20:53.843, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 65 %, 32510 MiB, 8628 MiB, 23882 MiB
2022/04/22 10:20:53.843, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 65 %, 32510 MiB, 8628 MiB, 23882 MiB
2022/04/22 10:20:53.846, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 65 %, 32510 MiB, 8610 MiB, 23900 MiB
2022/04/22 10:20:53.846, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 64 %, 32510 MiB, 8492 MiB, 24018 MiB
2022/04/22 10:20:53.856, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 63 %, 32510 MiB, 8342 MiB, 24168 MiB
2022/04/22 10:20:53.857, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 65 %, 32510 MiB, 8610 MiB, 23900 MiB
2022/04/22 10:20:53.859, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 65 %, 32510 MiB, 8610 MiB, 23900 MiB
2022/04/22 10:20:53.861, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 64 %, 32510 MiB, 8492 MiB, 24018 MiB
2022/04/22 10:20:53.862, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 64 %, 32510 MiB, 8492 MiB, 24018 MiB
2022/04/22 10:20:53.862, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 64 %, 32510 MiB, 8492 MiB, 24018 MiB
2022/04/22 10:20:53.865, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 65 %, 32510 MiB, 8628 MiB, 23882 MiB
2022/04/22 10:20:53.866, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 63 %, 32510 MiB, 8342 MiB, 24168 MiB
2022/04/22 10:20:53.866, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 66 %, 32510 MiB, 8494 MiB, 24016 MiB
2022/04/22 10:20:53.866, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 65 %, 32510 MiB, 8628 MiB, 23882 MiB
2022/04/22 10:20:53.868, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 65 %, 32510 MiB, 8628 MiB, 23882 MiB
2022/04/22 10:20:53.870, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 63 %, 32510 MiB, 8342 MiB, 24168 MiB
2022/04/22 10:20:53.871, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 63 %, 32510 MiB, 8342 MiB, 24168 MiB
2022/04/22 10:20:53.871, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 63 %, 32510 MiB, 8342 MiB, 24168 MiB
2022/04/22 10:20:53.874, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 64 %, 32510 MiB, 8492 MiB, 24018 MiB
2022/04/22 10:20:53.874, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 66 %, 32510 MiB, 8494 MiB, 24016 MiB
2022/04/22 10:20:53.875, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 64 %, 32510 MiB, 8492 MiB, 24018 MiB
2022/04/22 10:20:53.877, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 64 %, 32510 MiB, 8492 MiB, 24018 MiB
2022/04/22 10:20:53.879, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 66 %, 32510 MiB, 8494 MiB, 24016 MiB
2022/04/22 10:20:53.880, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 66 %, 32510 MiB, 8494 MiB, 24016 MiB
2022/04/22 10:20:53.880, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 66 %, 32510 MiB, 8494 MiB, 24016 MiB
2022/04/22 10:20:53.882, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 63 %, 32510 MiB, 8342 MiB, 24168 MiB
2022/04/22 10:20:53.884, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 63 %, 32510 MiB, 8342 MiB, 24168 MiB
2022/04/22 10:20:53.885, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 63 %, 32510 MiB, 8342 MiB, 24168 MiB
2022/04/22 10:20:53.890, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 66 %, 32510 MiB, 8494 MiB, 24016 MiB
2022/04/22 10:20:53.891, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 66 %, 32510 MiB, 8494 MiB, 24016 MiB
2022/04/22 10:20:53.893, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 66 %, 32510 MiB, 8494 MiB, 24016 MiB
[rank:5] [train], epoch: 0/1, iter: 200/625, loss: 0.86770, top1: 0.00113, throughput: 379.05 | 2022-04-22 10:22:00.954
[rank:4] [train], epoch: 0/1, iter: 200/625, loss: 0.86795, top1: 0.00109, throughput: 379.03 | 2022-04-22 10:22:00.955
[rank:6] [train], epoch: 0/1, iter: 200/625, loss: 0.86833, top1: 0.00109, throughput: 379.04 | 2022-04-22 10:22:00.955
[rank:1] [train], epoch: 0/1, iter: 200/625, loss: 0.86799, top1: 0.00109, throughput: 379.04 | 2022-04-22 10:22:00.959
[rank:0] [train], epoch: 0/1, iter: 200/625, loss: 0.86795, top1: 0.00094, throughput: 379.04 | 2022-04-22 10:22:00.960
[rank:2] [train], epoch: 0/1, iter: 200/625, loss: 0.86777, top1: 0.00098, throughput: 379.04 | 2022-04-22 10:22:00.958
[rank:7] [train], epoch: 0/1, iter: 200/625, loss: 0.86803, top1: 0.00121, throughput: 379.04 | 2022-04-22 10:22:00.961
[rank:3] [train], epoch: 0/1, iter: 200/625, loss: 0.86778, top1: 0.00105, throughput: 379.02 | 2022-04-22 10:22:00.964
[rank:5] [train], epoch: 0/1, iter: 300/625, loss: 0.86767, top1: 0.00137, throughput: 378.95 | 2022-04-22 10:23:08.510
[rank:4] [train], epoch: 0/1, iter: 300/625, loss: 0.86781, top1: 0.00082, throughput: 378.95 | 2022-04-22 10:23:08.511
[rank:2] [train], epoch: 0/1, iter: 300/625, loss: 0.86785, top1: 0.00105, throughput: 378.95 | 2022-04-22 10:23:08.513
[rank:6] [train], epoch: 0/1, iter: 300/625, loss: 0.86770, top1: 0.00113, throughput: 378.95 | 2022-04-22 10:23:08.511
[rank:3] [train], epoch: 0/1, iter: 300/625, loss: 0.86812, top1: 0.00105, throughput: 378.96 | 2022-04-22 10:23:08.517
[rank:1] [train], epoch: 0/1, iter: 300/625, loss: 0.86792, top1: 0.00062, throughput: 378.94 | 2022-04-22 10:23:08.516
[rank:0] [train], epoch: 0/1, iter: 300/625, loss: 0.86813, top1: 0.00070, throughput: 378.94 | 2022-04-22 10:23:08.517
[rank:7] [train], epoch: 0/1, iter: 300/625, loss: 0.86792, top1: 0.00105, throughput: 378.95 | 2022-04-22 10:23:08.516