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 ............................... 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 .................................. 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: 2.87301 s *****
[rank:7] [train], epoch: 0/1, iter: 100/312, loss: 0.86734, top1: 0.00113, throughput: 428.53 | 2022-04-27 10:38:55.501
[rank:4] [train], epoch: 0/1, iter: 100/312, loss: 0.86726, top1: 0.00086, throughput: 428.52 | 2022-04-27 10:38:55.501
[rank:3] [train], epoch: 0/1, iter: 100/312, loss: 0.86727, top1: 0.00094, throughput: 428.50 | 2022-04-27 10:38:55.502
[rank:1] [train], epoch: 0/1, iter: 100/312, loss: 0.86715, top1: 0.00100, throughput: 428.51 | 2022-04-27 10:38:55.502
[rank:6] [train], epoch: 0/1, iter: 100/312, loss: 0.86744, top1: 0.00107, throughput: 428.55 | 2022-04-27 10:38:55.502
[rank:0] [train], epoch: 0/1, iter: 100/312, loss: 0.86749, top1: 0.00127, throughput: 428.50 | 2022-04-27 10:38:55.506
[rank:2] [train], epoch: 0/1, iter: 100/312, loss: 0.86733, top1: 0.00127, throughput: 428.49 | 2022-04-27 10:38:55.506
[rank:5] [train], epoch: 0/1, iter: 100/312, loss: 0.86732, top1: 0.00107, throughput: 428.47 | 2022-04-27 10:38:55.518
timestamp, name, driver_version, utilization.gpu [%], utilization.memory [%], memory.total [MiB], memory.free [MiB], memory.used [MiB]
2022/04/27 10:38:55.716, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 62 %, 32510 MiB, 7797 MiB, 24713 MiB
timestamp, name, driver_version, utilization.gpu [%], utilization.memory [%], memory.total [MiB], memory.free [MiB], memory.used [MiB]
2022/04/27 10:38:55.722, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 74 %, 32510 MiB, 7772 MiB, 24738 MiB
2022/04/27 10:38:55.724, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 62 %, 32510 MiB, 7797 MiB, 24713 MiB
2022/04/27 10:38:55.730, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 88 %, 32510 MiB, 7968 MiB, 24542 MiB
2022/04/27 10:38:55.739, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 74 %, 32510 MiB, 7772 MiB, 24738 MiB
2022/04/27 10:38:55.744, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 69 %, 32510 MiB, 7900 MiB, 24610 MiB
2022/04/27 10:38:55.746, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 88 %, 32510 MiB, 7968 MiB, 24542 MiB
2022/04/27 10:38:55.750, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 57 %, 32510 MiB, 7908 MiB, 24602 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]
2022/04/27 10:38:55.753, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 69 %, 32510 MiB, 7900 MiB, 24610 MiB
2022/04/27 10:38:55.756, Tesla V100-SXM2-32GB, 470.57.02, 98 %, 88 %, 32510 MiB, 7800 MiB, 24710 MiB
timestamp, name, driver_version, utilization.gpu [%], utilization.memory [%], memory.total [MiB], memory.free [MiB], memory.used [MiB]
2022/04/27 10:38:55.757, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 62 %, 32510 MiB, 7797 MiB, 24713 MiB
timestamp, name, driver_version, utilization.gpu [%], utilization.memory [%], memory.total [MiB], memory.free [MiB], memory.used [MiB]
2022/04/27 10:38:55.757, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 62 %, 32510 MiB, 7797 MiB, 24713 MiB
2022/04/27 10:38:55.758, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 57 %, 32510 MiB, 7908 MiB, 24602 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]
2022/04/27 10:38:55.761, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 66 %, 32510 MiB, 7672 MiB, 24838 MiB
2022/04/27 10:38:55.762, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 74 %, 32510 MiB, 7772 MiB, 24738 MiB
2022/04/27 10:38:55.762, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 62 %, 32510 MiB, 7797 MiB, 24713 MiB
2022/04/27 10:38:55.763, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 74 %, 32510 MiB, 7772 MiB, 24738 MiB
2022/04/27 10:38:55.763, Tesla V100-SXM2-32GB, 470.57.02, 98 %, 88 %, 32510 MiB, 7800 MiB, 24710 MiB
2022/04/27 10:38:55.763, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 62 %, 32510 MiB, 7797 MiB, 24713 MiB
2022/04/27 10:38:55.764, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 62 %, 32510 MiB, 7797 MiB, 24713 MiB
2022/04/27 10:38:55.764, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 62 %, 32510 MiB, 7797 MiB, 24713 MiB
2022/04/27 10:38:55.768, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 72 %, 32510 MiB, 7840 MiB, 24670 MiB
2022/04/27 10:38:55.770, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 88 %, 32510 MiB, 7968 MiB, 24542 MiB
2022/04/27 10:38:55.770, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 74 %, 32510 MiB, 7772 MiB, 24738 MiB
2022/04/27 10:38:55.771, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 88 %, 32510 MiB, 7968 MiB, 24542 MiB
2022/04/27 10:38:55.771, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 66 %, 32510 MiB, 7672 MiB, 24838 MiB
2022/04/27 10:38:55.772, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 74 %, 32510 MiB, 7772 MiB, 24738 MiB
2022/04/27 10:38:55.772, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 74 %, 32510 MiB, 7772 MiB, 24738 MiB
2022/04/27 10:38:55.773, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 74 %, 32510 MiB, 7772 MiB, 24738 MiB
2022/04/27 10:38:55.778, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 69 %, 32510 MiB, 7900 MiB, 24610 MiB
2022/04/27 10:38:55.784, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 88 %, 32510 MiB, 7968 MiB, 24542 MiB
2022/04/27 10:38:55.785, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 69 %, 32510 MiB, 7900 MiB, 24610 MiB
2022/04/27 10:38:55.785, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 72 %, 32510 MiB, 7840 MiB, 24670 MiB
2022/04/27 10:38:55.785, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 88 %, 32510 MiB, 7968 MiB, 24542 MiB
2022/04/27 10:38:55.786, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 88 %, 32510 MiB, 7968 MiB, 24542 MiB
2022/04/27 10:38:55.787, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 88 %, 32510 MiB, 7968 MiB, 24542 MiB
2022/04/27 10:38:55.792, Tesla V100-SXM2-32GB, 470.57.02, 76 %, 69 %, 32510 MiB, 7908 MiB, 24602 MiB
2022/04/27 10:38:55.792, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 69 %, 32510 MiB, 7900 MiB, 24610 MiB
2022/04/27 10:38:55.793, Tesla V100-SXM2-32GB, 470.57.02, 76 %, 69 %, 32510 MiB, 7908 MiB, 24602 MiB
2022/04/27 10:38:55.794, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 69 %, 32510 MiB, 7900 MiB, 24610 MiB
2022/04/27 10:38:55.794, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 69 %, 32510 MiB, 7900 MiB, 24610 MiB
2022/04/27 10:38:55.795, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 69 %, 32510 MiB, 7900 MiB, 24610 MiB
2022/04/27 10:38:55.800, Tesla V100-SXM2-32GB, 470.57.02, 98 %, 88 %, 32510 MiB, 7800 MiB, 24710 MiB
2022/04/27 10:38:55.801, Tesla V100-SXM2-32GB, 470.57.02, 76 %, 69 %, 32510 MiB, 7908 MiB, 24602 MiB
2022/04/27 10:38:55.801, Tesla V100-SXM2-32GB, 470.57.02, 98 %, 88 %, 32510 MiB, 7800 MiB, 24710 MiB
2022/04/27 10:38:55.802, Tesla V100-SXM2-32GB, 470.57.02, 76 %, 69 %, 32510 MiB, 7908 MiB, 24602 MiB
2022/04/27 10:38:55.803, Tesla V100-SXM2-32GB, 470.57.02, 76 %, 69 %, 32510 MiB, 7908 MiB, 24602 MiB
2022/04/27 10:38:55.804, Tesla V100-SXM2-32GB, 470.57.02, 76 %, 69 %, 32510 MiB, 7908 MiB, 24602 MiB
2022/04/27 10:38:55.809, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 66 %, 32510 MiB, 7672 MiB, 24838 MiB
2022/04/27 10:38:55.809, Tesla V100-SXM2-32GB, 470.57.02, 98 %, 88 %, 32510 MiB, 7800 MiB, 24710 MiB
2022/04/27 10:38:55.810, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 66 %, 32510 MiB, 7672 MiB, 24838 MiB
2022/04/27 10:38:55.810, Tesla V100-SXM2-32GB, 470.57.02, 98 %, 88 %, 32510 MiB, 7800 MiB, 24710 MiB
2022/04/27 10:38:55.811, Tesla V100-SXM2-32GB, 470.57.02, 98 %, 88 %, 32510 MiB, 7800 MiB, 24710 MiB
2022/04/27 10:38:55.812, Tesla V100-SXM2-32GB, 470.57.02, 98 %, 88 %, 32510 MiB, 7800 MiB, 24710 MiB
2022/04/27 10:38:55.820, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 72 %, 32510 MiB, 7840 MiB, 24670 MiB
2022/04/27 10:38:55.821, Tesla V100-SXM2-32GB, 470.57.02, 50 %, 42 %, 32510 MiB, 7672 MiB, 24838 MiB
2022/04/27 10:38:55.821, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 72 %, 32510 MiB, 7840 MiB, 24670 MiB
2022/04/27 10:38:55.822, Tesla V100-SXM2-32GB, 470.57.02, 50 %, 42 %, 32510 MiB, 7672 MiB, 24838 MiB
2022/04/27 10:38:55.823, Tesla V100-SXM2-32GB, 470.57.02, 50 %, 42 %, 32510 MiB, 7672 MiB, 24838 MiB
2022/04/27 10:38:55.824, Tesla V100-SXM2-32GB, 470.57.02, 50 %, 42 %, 32510 MiB, 7672 MiB, 24838 MiB
2022/04/27 10:38:55.831, Tesla V100-SXM2-32GB, 470.57.02, 67 %, 58 %, 32510 MiB, 7840 MiB, 24670 MiB
2022/04/27 10:38:55.832, Tesla V100-SXM2-32GB, 470.57.02, 67 %, 58 %, 32510 MiB, 7840 MiB, 24670 MiB
2022/04/27 10:38:55.833, Tesla V100-SXM2-32GB, 470.57.02, 67 %, 58 %, 32510 MiB, 7840 MiB, 24670 MiB
2022/04/27 10:38:55.833, Tesla V100-SXM2-32GB, 470.57.02, 67 %, 58 %, 32510 MiB, 7840 MiB, 24670 MiB
[rank:2] [train], epoch: 0/1, iter: 200/312, loss: 0.86750, top1: 0.00098, throughput: 1364.15 | 2022-04-27 10:39:33.039
[rank:6] [train], epoch: 0/1, iter: 200/312, loss: 0.86735, top1: 0.00109, throughput: 1363.95 | 2022-04-27 10:39:33.040
[rank:1] [train], epoch: 0/1, iter: 200/312, loss: 0.86741, top1: 0.00105, throughput: 1363.98 | 2022-04-27 10:39:33.039
[rank:0] [train], epoch: 0/1, iter: 200/312, loss: 0.86747, top1: 0.00102, throughput: 1364.16 | 2022-04-27 10:39:33.039
[rank:7] [train], epoch: 0/1, iter: 200/312, loss: 0.86724, top1: 0.00064, throughput: 1363.90 | 2022-04-27 10:39:33.041
[rank:3] [train], epoch: 0/1, iter: 200/312, loss: 0.86742, top1: 0.00133, throughput: 1364.02 | 2022-04-27 10:39:33.039
[rank:4] [train], epoch: 0/1, iter: 200/312, loss: 0.86741, top1: 0.00123, throughput: 1363.93 | 2022-04-27 10:39:33.039
[rank:5] [train], epoch: 0/1, iter: 200/312, loss: 0.86744, top1: 0.00129, throughput: 1364.55 | 2022-04-27 10:39:33.039
[rank:3] [train], epoch: 0/1, iter: 300/312, loss: 0.86735, top1: 0.00115, throughput: 1362.15 | 2022-04-27 10:40:10.626
[rank:1] [train], epoch: 0/1, iter: 300/312, loss: 0.86743, top1: 0.00098, throughput: 1362.10 [rank:0] [train], epoch: 0/1, iter: 300/312, loss: 0.86756, top1: 0.00094, throughput: 1362.15| 2022-04-27 10:40:10.628
 | 2022-04-27 10:40:10.626
[rank:2] [train], epoch: 0/1, iter: 300/312, loss: 0.86733, top1: 0.00105, throughput: 1362.16 | 2022-04-27 10:40:10.626
[rank:7] [train], epoch: 0/1, iter: 300/312, loss: 0.86735, top1: 0.00121, throughput: 1362.26 | 2022-04-27 10:40:10.625
[rank:6] [train], epoch: 0/1, iter: 300/312, loss: 0.86752, top1: 0.00115, throughput: 1362.19 | 2022-04-27 10:40:10.626
[rank:4] [train], epoch: 0/1, iter: 300/312, loss: 0.86765, top1: 0.00080, throughput: 1362.13 | 2022-04-27 10:40:10.627
[rank:5] [train], epoch: 0/1, iter: 300/312, loss: 0.86769, top1: 0.00119, throughput: 1361.88 | 2022-04-27 10:40:10.635