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: /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: 2.99448 s *****
[rank:3] [train], epoch: 0/1, iter: 100/625, loss: 0.86780, top1: 0.00066, throughput: 260.59 | 2022-04-30 02:33:02.085
[rank:5] [train], epoch: 0/1, iter: 100/625, loss: 0.86791, top1: 0.00094, throughput: 260.57 | 2022-04-30 02:33:02.085
[rank:1] [train], epoch: 0/1, iter: 100/625, loss: 0.86752, top1: 0.00129, throughput: 260.57 | 2022-04-30 02:33:02.084
[rank:6] [train], epoch: 0/1, iter: 100/625, loss: 0.86800, top1: 0.00117, throughput: 260.58 | 2022-04-30 02:33:02.085
[rank:4] [train], epoch: 0/1, iter: 100/625, loss: 0.86795, top1: 0.00102, throughput: 260.56 | 2022-04-30 02:33:02.087
[rank:7] [train], epoch: 0/1, iter: 100/625, loss: 0.86809, top1: 0.00070, throughput: 260.58[rank:0] [train], epoch: 0/1, iter: 100/625, loss: 0.86794, top1: 0.00074, throughput: 260.57 | 2022-04-30 02:33:02.085
 | 2022-04-30 02:33:02.085
[rank:2] [train], epoch: 0/1, iter: 100/625, loss: 0.86796, top1: 0.00090, throughput: 260.57 | 2022-04-30 02:33:02.084
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]
2022/04/30 02:33:02.365, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 58 %, 32510 MiB, 7801 MiB, 24709 MiB
2022/04/30 02:33:02.366, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 58 %, 32510 MiB, 7801 MiB, 24709 MiB
timestamp, name, driver_version, utilization.gpu [%], utilization.memory [%], memory.total [MiB], memory.free [MiB], memory.used [MiB]
2022/04/30 02:33:02.373, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 58 %, 32510 MiB, 7801 MiB, 24709 MiB
timestamp, name, driver_version, utilization.gpu [%], utilization.memory [%], memory.total [MiB], memory.free [MiB], memory.used [MiB]
2022/04/30 02:33:02.377, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 61 %, 32510 MiB, 7780 MiB, 24730 MiB
2022/04/30 02:33:02.383, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 61 %, 32510 MiB, 7780 MiB, 24730 MiB
2022/04/30 02:33:02.384, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 58 %, 32510 MiB, 7801 MiB, 24709 MiB
2022/04/30 02:33:02.386, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 61 %, 32510 MiB, 7780 MiB, 24730 MiB
timestamp, name, driver_version, utilization.gpu [%], utilization.memory [%], memory.total [MiB], memory.free [MiB], memory.used [MiB]
2022/04/30 02:33:02.396, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 58 %, 32510 MiB, 7801 MiB, 24709 MiB
2022/04/30 02:33:02.397, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 58 %, 32510 MiB, 7948 MiB, 24562 MiB
timestamp, name, driver_version, utilization.gpu [%], utilization.memory [%], memory.total [MiB], memory.free [MiB], memory.used [MiB]
2022/04/30 02:33:02.399, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 58 %, 32510 MiB, 7948 MiB, 24562 MiB
2022/04/30 02:33:02.400, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 61 %, 32510 MiB, 7780 MiB, 24730 MiB
timestamp, name, driver_version, utilization.gpu [%], utilization.memory [%], memory.total [MiB], memory.free [MiB], memory.used [MiB]
2022/04/30 02:33:02.400, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 58 %, 32510 MiB, 7948 MiB, 24562 MiB
2022/04/30 02:33:02.403, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 61 %, 32510 MiB, 7780 MiB, 24730 MiB
2022/04/30 02:33:02.404, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 59 %, 32510 MiB, 7888 MiB, 24622 MiB
2022/04/30 02:33:02.403, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 58 %, 32510 MiB, 7801 MiB, 24709 MiB
2022/04/30 02:33:02.405, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 59 %, 32510 MiB, 7888 MiB, 24622 MiB
2022/04/30 02:33:02.405, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 58 %, 32510 MiB, 7801 MiB, 24709 MiB
2022/04/30 02:33:02.408, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 63 %, 32510 MiB, 7948 MiB, 24562 MiB
2022/04/30 02:33:02.408, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 58 %, 32510 MiB, 7801 MiB, 24709 MiB
2022/04/30 02:33:02.409, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 59 %, 32510 MiB, 7888 MiB, 24622 MiB
2022/04/30 02:33:02.413, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 63 %, 32510 MiB, 7948 MiB, 24562 MiB
2022/04/30 02:33:02.413, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 61 %, 32510 MiB, 7846 MiB, 24664 MiB
2022/04/30 02:33:02.414, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 61 %, 32510 MiB, 7780 MiB, 24730 MiB
2022/04/30 02:33:02.416, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 61 %, 32510 MiB, 7846 MiB, 24664 MiB
2022/04/30 02:33:02.416, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 61 %, 32510 MiB, 7780 MiB, 24730 MiB
2022/04/30 02:33:02.417, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 59 %, 32510 MiB, 7888 MiB, 24622 MiB
2022/04/30 02:33:02.418, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 61 %, 32510 MiB, 7780 MiB, 24730 MiB
2022/04/30 02:33:02.418, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 61 %, 32510 MiB, 7846 MiB, 24664 MiB
2022/04/30 02:33:02.422, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 59 %, 32510 MiB, 7888 MiB, 24622 MiB
2022/04/30 02:33:02.423, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 57 %, 32510 MiB, 7750 MiB, 24760 MiB
2022/04/30 02:33:02.423, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 63 %, 32510 MiB, 7948 MiB, 24562 MiB
2022/04/30 02:33:02.425, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 57 %, 32510 MiB, 7750 MiB, 24760 MiB
2022/04/30 02:33:02.425, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 63 %, 32510 MiB, 7948 MiB, 24562 MiB
2022/04/30 02:33:02.426, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 61 %, 32510 MiB, 7846 MiB, 24664 MiB
2022/04/30 02:33:02.428, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 63 %, 32510 MiB, 7948 MiB, 24562 MiB
2022/04/30 02:33:02.428, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 57 %, 32510 MiB, 7750 MiB, 24760 MiB
2022/04/30 02:33:02.432, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 61 %, 32510 MiB, 7846 MiB, 24664 MiB
2022/04/30 02:33:02.432, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 64 %, 32510 MiB, 7630 MiB, 24880 MiB
2022/04/30 02:33:02.433, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 59 %, 32510 MiB, 7888 MiB, 24622 MiB
2022/04/30 02:33:02.435, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 64 %, 32510 MiB, 7630 MiB, 24880 MiB
2022/04/30 02:33:02.435, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 59 %, 32510 MiB, 7888 MiB, 24622 MiB
2022/04/30 02:33:02.436, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 57 %, 32510 MiB, 7750 MiB, 24760 MiB
2022/04/30 02:33:02.437, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 59 %, 32510 MiB, 7888 MiB, 24622 MiB
2022/04/30 02:33:02.437, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 64 %, 32510 MiB, 7630 MiB, 24880 MiB
2022/04/30 02:33:02.441, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 57 %, 32510 MiB, 7750 MiB, 24760 MiB
2022/04/30 02:33:02.441, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 58 %, 32510 MiB, 7770 MiB, 24740 MiB
2022/04/30 02:33:02.441, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 61 %, 32510 MiB, 7846 MiB, 24664 MiB
2022/04/30 02:33:02.443, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 58 %, 32510 MiB, 7770 MiB, 24740 MiB
2022/04/30 02:33:02.444, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 61 %, 32510 MiB, 7846 MiB, 24664 MiB
2022/04/30 02:33:02.445, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 64 %, 32510 MiB, 7630 MiB, 24880 MiB
2022/04/30 02:33:02.446, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 61 %, 32510 MiB, 7846 MiB, 24664 MiB
2022/04/30 02:33:02.446, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 58 %, 32510 MiB, 7770 MiB, 24740 MiB
2022/04/30 02:33:02.451, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 64 %, 32510 MiB, 7630 MiB, 24880 MiB
2022/04/30 02:33:02.452, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 57 %, 32510 MiB, 7750 MiB, 24760 MiB
2022/04/30 02:33:02.454, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 57 %, 32510 MiB, 7750 MiB, 24760 MiB
2022/04/30 02:33:02.455, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 58 %, 32510 MiB, 7770 MiB, 24740 MiB
2022/04/30 02:33:02.456, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 64 %, 32510 MiB, 7750 MiB, 24760 MiB
2022/04/30 02:33:02.460, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 58 %, 32510 MiB, 7770 MiB, 24740 MiB
2022/04/30 02:33:02.461, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 64 %, 32510 MiB, 7630 MiB, 24880 MiB
2022/04/30 02:33:02.464, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 64 %, 32510 MiB, 7630 MiB, 24880 MiB
2022/04/30 02:33:02.465, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 64 %, 32510 MiB, 7630 MiB, 24880 MiB
2022/04/30 02:33:02.471, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 58 %, 32510 MiB, 7770 MiB, 24740 MiB
2022/04/30 02:33:02.473, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 58 %, 32510 MiB, 7770 MiB, 24740 MiB
2022/04/30 02:33:02.474, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 58 %, 32510 MiB, 7770 MiB, 24740 MiB
[rank:7] [train], epoch: 0/1, iter: 200/625, loss: 0.86810, top1: 0.00086, throughput: 372.52 | 2022-04-30 02:34:10.807
[rank:3] [train], epoch: 0/1, iter: 200/625, loss: 0.86827, top1: 0.00105, throughput: 372.52 | 2022-04-30 02:34:10.807
[rank:0] [train], epoch: 0/1, iter: 200/625, loss: 0.86796, top1: 0.00062, throughput: 372.52 | 2022-04-30 02:34:10.807
[rank:5] [train], epoch: 0/1, iter: 200/625, loss: 0.86810, top1: 0.00121, throughput: 372.51 | 2022-04-30 02:34:10.807
[rank:1] [train], epoch: 0/1, iter: 200/625, loss: 0.86768, top1: 0.00074, throughput: 372.51 | 2022-04-30 02:34:10.806
[rank:2] [train], epoch: 0/1, iter: 200/625, loss: 0.86815, top1: 0.00043, throughput: 372.52 | 2022-04-30 02:34:10.806
[rank:6] [train], epoch: 0/1, iter: 200/625, loss: 0.86811, top1: 0.00074, throughput: 372.51 | 2022-04-30 02:34:10.807
[rank:4] [train], epoch: 0/1, iter: 200/625, loss: 0.86778, top1: 0.00090, throughput: 372.51 | 2022-04-30 02:34:10.810
[rank:2] [train], epoch: 0/1, iter: 300/625, loss: 0.86779, top1: 0.00090, throughput: 374.57 | 2022-04-30 02:35:19.150
[rank:5] [train], epoch: 0/1, iter: 300/625, loss: 0.86814, top1: 0.00070, throughput: 374.53 | 2022-04-30 02:35:19.159
[rank:0] [train], epoch: 0/1, iter: 300/625, loss: 0.86797, top1: 0.00078, throughput: 374.52 | 2022-04-30 02:35:19.160
[rank:7] [train], epoch: 0/1, iter: 300/625, loss: 0.86781, top1: 0.00117, throughput: 374.52 | 2022-04-30 02:35:19.161
[rank:3] [train], epoch: 0/1, iter: 300/625, loss: 0.86799, top1: 0.00086, throughput: 374.52 | 2022-04-30 02:35:19.161
[rank:6] [train], epoch: 0/1, iter: 300/625, loss: 0.86793, top1: 0.00117, throughput: 374.53 | 2022-04-30 02:35:19.160
[rank:4] [train], epoch: 0/1, iter: 300/625, loss: 0.86775, top1: 0.00109, throughput: 374.54 | 2022-04-30 02:35:19.162
[rank:1] [train], epoch: 0/1, iter: 300/625, loss: 0.86812, top1: 0.00086, throughput: 374.52 | 2022-04-30 02:35:19.160