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 .................................. 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: 3.14457 s *****
[rank:4] [train], epoch: 0/1, iter: 100/625, loss: 0.86759, top1: 0.00125, throughput: 275.63 | 2022-04-28 10:41:23.670
[rank:2] [train], epoch: 0/1, iter: 100/625, loss: 0.86774, top1: 0.00133, throughput: 275.62 | 2022-04-28 10:41:23.669
[rank:0] [train], epoch: 0/1, iter: 100/625, loss: 0.86743, top1: 0.00105, throughput: 275.62 | 2022-04-28 10:41:23.670
[rank:7] [train], epoch: 0/1, iter: 100/625, loss: 0.86742, top1: 0.00109, throughput: 275.62 | 2022-04-28 10:41:23.669
[rank:6] [train], epoch: 0/1, iter: 100/625, loss: 0.86749, top1: 0.00121, throughput: 275.63 | 2022-04-28 10:41:23.670
[rank:5] [train], epoch: 0/1, iter: 100/625, loss: 0.86775, top1: 0.00086, throughput: 275.63 | 2022-04-28 10:41:23.670
[rank:1] [train], epoch: 0/1, iter: 100/625, loss: 0.86741, top1: 0.00098, throughput: 275.63 | 2022-04-28 10:41:23.671
[rank:3] [train], epoch: 0/1, iter: 100/625, loss: 0.86789, top1: 0.00082, throughput: 275.64 | 2022-04-28 10:41:23.670
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]
2022/04/28 10:41:24.007, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 60 %, 32510 MiB, 8466 MiB, 24044 MiB
timestamp, name, driver_version, utilization.gpu [%], utilization.memory [%], memory.total [MiB], memory.free [MiB], memory.used [MiB]
2022/04/28 10:41:24.008, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 60 %, 32510 MiB, 8466 MiB, 24044 MiB
timestamp, name, driver_version, utilization.gpu [%], utilization.memory [%], memory.total [MiB], memory.free [MiB], memory.used [MiB]
2022/04/28 10:41:24.015, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 60 %, 32510 MiB, 8510 MiB, 24000 MiB
2022/04/28 10:41:24.019, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 60 %, 32510 MiB, 8510 MiB, 24000 MiB
2022/04/28 10:41:24.018, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 60 %, 32510 MiB, 8466 MiB, 24044 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]
2022/04/28 10:41:24.030, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 60 %, 32510 MiB, 8666 MiB, 23844 MiB
2022/04/28 10:41:24.030, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 60 %, 32510 MiB, 8466 MiB, 24044 MiB
2022/04/28 10:41:24.031, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 60 %, 32510 MiB, 8666 MiB, 23844 MiB
timestamp, name, driver_version, utilization.gpu [%], utilization.memory [%], memory.total [MiB], memory.free [MiB], memory.used [MiB]
2022/04/28 10:41:24.031, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 60 %, 32510 MiB, 8510 MiB, 24000 MiB
2022/04/28 10:41:24.032, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 60 %, 32510 MiB, 8466 MiB, 24044 MiB
2022/04/28 10:41:24.033, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 60 %, 32510 MiB, 8466 MiB, 24044 MiB
2022/04/28 10:41:24.035, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 60 %, 32510 MiB, 8466 MiB, 24044 MiB
2022/04/28 10:41:24.038, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 62 %, 32510 MiB, 8536 MiB, 23974 MiB
2022/04/28 10:41:24.038, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 60 %, 32510 MiB, 8510 MiB, 24000 MiB
2022/04/28 10:41:24.039, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 62 %, 32510 MiB, 8536 MiB, 23974 MiB
2022/04/28 10:41:24.040, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 60 %, 32510 MiB, 8666 MiB, 23844 MiB
2022/04/28 10:41:24.039, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 60 %, 32510 MiB, 8466 MiB, 24044 MiB
2022/04/28 10:41:24.041, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 60 %, 32510 MiB, 8510 MiB, 24000 MiB
2022/04/28 10:41:24.042, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 60 %, 32510 MiB, 8510 MiB, 24000 MiB
2022/04/28 10:41:24.046, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 60 %, 32510 MiB, 8510 MiB, 24000 MiB
2022/04/28 10:41:24.047, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 64 %, 32510 MiB, 8610 MiB, 23900 MiB
2022/04/28 10:41:24.047, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 60 %, 32510 MiB, 8666 MiB, 23844 MiB
2022/04/28 10:41:24.048, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 64 %, 32510 MiB, 8610 MiB, 23900 MiB
2022/04/28 10:41:24.049, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 62 %, 32510 MiB, 8536 MiB, 23974 MiB
2022/04/28 10:41:24.049, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 60 %, 32510 MiB, 8510 MiB, 24000 MiB
2022/04/28 10:41:24.051, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 60 %, 32510 MiB, 8666 MiB, 23844 MiB
2022/04/28 10:41:24.052, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 65 %, 32510 MiB, 8666 MiB, 23844 MiB
2022/04/28 10:41:24.055, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 65 %, 32510 MiB, 8666 MiB, 23844 MiB
2022/04/28 10:41:24.056, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 64 %, 32510 MiB, 8478 MiB, 24032 MiB
2022/04/28 10:41:24.058, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 62 %, 32510 MiB, 8536 MiB, 23974 MiB
2022/04/28 10:41:24.059, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 64 %, 32510 MiB, 8478 MiB, 24032 MiB
2022/04/28 10:41:24.060, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 64 %, 32510 MiB, 8610 MiB, 23900 MiB
2022/04/28 10:41:24.060, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 65 %, 32510 MiB, 8666 MiB, 23844 MiB
2022/04/28 10:41:24.061, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 62 %, 32510 MiB, 8536 MiB, 23974 MiB
2022/04/28 10:41:24.063, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 62 %, 32510 MiB, 8536 MiB, 23974 MiB
2022/04/28 10:41:24.066, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 62 %, 32510 MiB, 8536 MiB, 23974 MiB
2022/04/28 10:41:24.067, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 59 %, 32510 MiB, 8350 MiB, 24160 MiB
2022/04/28 10:41:24.067, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 64 %, 32510 MiB, 8610 MiB, 23900 MiB
2022/04/28 10:41:24.068, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 66 %, 32510 MiB, 8350 MiB, 24160 MiB
2022/04/28 10:41:24.069, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 64 %, 32510 MiB, 8478 MiB, 24032 MiB
2022/04/28 10:41:24.069, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 62 %, 32510 MiB, 8536 MiB, 23974 MiB
2022/04/28 10:41:24.071, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 64 %, 32510 MiB, 8610 MiB, 23900 MiB
2022/04/28 10:41:24.072, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 64 %, 32510 MiB, 8610 MiB, 23900 MiB
2022/04/28 10:41:24.075, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 64 %, 32510 MiB, 8610 MiB, 23900 MiB
2022/04/28 10:41:24.076, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 62 %, 32510 MiB, 8566 MiB, 23944 MiB
2022/04/28 10:41:24.076, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 64 %, 32510 MiB, 8478 MiB, 24032 MiB
2022/04/28 10:41:24.077, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 62 %, 32510 MiB, 8566 MiB, 23944 MiB
2022/04/28 10:41:24.078, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 66 %, 32510 MiB, 8350 MiB, 24160 MiB
2022/04/28 10:41:24.078, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 64 %, 32510 MiB, 8610 MiB, 23900 MiB
2022/04/28 10:41:24.079, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 64 %, 32510 MiB, 8478 MiB, 24032 MiB
2022/04/28 10:41:24.081, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 64 %, 32510 MiB, 8478 MiB, 24032 MiB
2022/04/28 10:41:24.084, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 64 %, 32510 MiB, 8478 MiB, 24032 MiB
2022/04/28 10:41:24.085, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 66 %, 32510 MiB, 8350 MiB, 24160 MiB
2022/04/28 10:41:24.087, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 62 %, 32510 MiB, 8566 MiB, 23944 MiB
2022/04/28 10:41:24.087, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 64 %, 32510 MiB, 8478 MiB, 24032 MiB
2022/04/28 10:41:24.090, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 66 %, 32510 MiB, 8350 MiB, 24160 MiB
2022/04/28 10:41:24.091, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 66 %, 32510 MiB, 8350 MiB, 24160 MiB
2022/04/28 10:41:24.094, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 66 %, 32510 MiB, 8350 MiB, 24160 MiB
2022/04/28 10:41:24.095, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 62 %, 32510 MiB, 8566 MiB, 23944 MiB
2022/04/28 10:41:24.097, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 66 %, 32510 MiB, 8350 MiB, 24160 MiB
2022/04/28 10:41:24.098, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 62 %, 32510 MiB, 8566 MiB, 23944 MiB
2022/04/28 10:41:24.099, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 62 %, 32510 MiB, 8566 MiB, 23944 MiB
2022/04/28 10:41:24.102, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 62 %, 32510 MiB, 8566 MiB, 23944 MiB
2022/04/28 10:41:24.105, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 62 %, 32510 MiB, 8566 MiB, 23944 MiB
[rank:0] [train], epoch: 0/1, iter: 200/625, loss: 0.86773, top1: 0.00102, throughput: 378.89 | 2022-04-28 10:42:31.236
[rank:2] [train], epoch: 0/1, iter: 200/625, loss: 0.86759, top1: 0.00113, throughput: 378.88 | 2022-04-28 10:42:31.236
[rank:1] [train], epoch: 0/1, iter: 200/625, loss: 0.86776, top1: 0.00156, throughput: 378.89 | 2022-04-28 10:42:31.236
[rank:7] [train], epoch: 0/1, iter: 200/625, loss: 0.86765, top1: 0.00105, throughput: 378.88 | 2022-04-28 10:42:31.236
[rank:3] [train], epoch: 0/1, iter: 200/625, loss: 0.86791, top1: 0.00086, throughput: 378.88 | 2022-04-28 10:42:31.238
[rank:6] [train], epoch: 0/1, iter: 200/625, loss: 0.86752, top1: 0.00094, throughput: 378.88 | 2022-04-28 10:42:31.237
[rank:4] [train], epoch: 0/1, iter: 200/625, loss: 0.86741, top1: 0.00078, throughput: 378.87 | 2022-04-28 10:42:31.239
[rank:5] [train], epoch: 0/1, iter: 200/625, loss: 0.86779, top1: 0.00098, throughput: 378.88 | 2022-04-28 10:42:31.237
[rank:6] [train], epoch: 0/1, iter: 300/625, loss: 0.86765, top1: 0.00086, throughput: 377.64 | 2022-04-28 10:43:39.027
[rank:0] [train], epoch: 0/1, iter: 300/625, loss: 0.86762, top1: 0.00086, throughput: 377.60 | 2022-04-28 10:43:39.032
[rank:5] [train], epoch: 0/1, iter: 300/625, loss: 0.86780, top1: 0.00117, throughput: 377.60 | 2022-04-28 10:43:39.033
[rank:1] [train], epoch: 0/1, iter: 300/625, loss: 0.86769, top1: 0.00086, throughput: 377.60 | 2022-04-28 10:43:39.033
[rank:3] [train], epoch: 0/1, iter: 300/625, loss: 0.86801, top1: 0.00125, throughput: 377.60 | 2022-04-28 10:43:39.034
[rank:2] [train], epoch: 0/1, iter: 300/625, loss: 0.86736, top1: 0.00098, throughput: 377.59 | 2022-04-28 10:43:39.034
[rank:7] [train], epoch: 0/1, iter: 300/625, loss: 0.86755, top1: 0.00082, throughput: 377.59 | 2022-04-28 10:43:39.034
[rank:4] [train], epoch: 0/1, iter: 300/625, loss: 0.86760, top1: 0.00109, throughput: 377.60 | 2022-04-28 10:43:39.036