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: 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
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 .................................. 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: 3.36408 s *****
[rank:0] [train], epoch: 0/1, iter: 100/312, loss: 0.86794, top1: 0.00100, throughput: 452.83 | 2022-04-27 10:46:25.595
[rank:3] [train], epoch: 0/1, iter: 100/312, loss: 0.86786, top1: 0.00098, throughput: 452.84 | 2022-04-27 10:46:25.598
[rank:1] [train], epoch: 0/1, iter: 100/312, loss: 0.86817, top1: 0.00115, throughput: 452.85 | 2022-04-27 10:46:25.595
[rank:6] [train], epoch: 0/1, iter: 100/312, loss: 0.86779, top1: 0.00125, throughput: 452.83 | 2022-04-27 10:46:25.597
[rank:5] [train], epoch: 0/1, iter: 100/312, loss: 0.86816, top1: 0.00082, throughput: 452.86 | 2022-04-27 10:46:25.597
[rank:2] [train], epoch: 0/1, iter: 100/312, loss: 0.86800, top1: 0.00105, throughput: 452.82 | 2022-04-27 10:46:25.597
[rank:7] [train], epoch: 0/1, iter: 100/312, loss: 0.86772, top1: 0.00090, throughput: 452.84 | 2022-04-27 10:46:25.598
[rank:4] [train], epoch: 0/1, iter: 100/312, loss: 0.86804, top1: 0.00094, throughput: 452.85 | 2022-04-27 10:46:25.599
timestamp, name, driver_version, utilization.gpu [%], utilization.memory [%], memory.total [MiB], memory.free [MiB], memory.used [MiB]
2022/04/27 10:46:25.882, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 51 %, 32510 MiB, 8561 MiB, 23949 MiB
2022/04/27 10:46:25.886, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 62 %, 32510 MiB, 8570 MiB, 23940 MiB
2022/04/27 10:46:25.894, Tesla V100-SXM2-32GB, 470.57.02, 98 %, 80 %, 32510 MiB, 8744 MiB, 23766 MiB
2022/04/27 10:46:25.901, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 64 %, 32510 MiB, 8676 MiB, 23834 MiB
2022/04/27 10:46:25.907, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 78 %, 32510 MiB, 8692 MiB, 23818 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 10:46:25.911, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 75 %, 32510 MiB, 8556 MiB, 23954 MiB
2022/04/27 10:46:25.913, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 51 %, 32510 MiB, 8561 MiB, 23949 MiB
2022/04/27 10:46:25.914, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 51 %, 32510 MiB, 8561 MiB, 23949 MiB
timestamp, name, driver_version, utilization.gpu [%], utilization.memory [%], memory.total [MiB], memory.free [MiB], memory.used [MiB]
2022/04/27 10:46:25.918, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 81 %, 32510 MiB, 8444 MiB, 24066 MiB
2022/04/27 10:46:25.921, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 62 %, 32510 MiB, 8570 MiB, 23940 MiB
2022/04/27 10:46:25.923, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 62 %, 32510 MiB, 8570 MiB, 23940 MiB
2022/04/27 10:46:25.923, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 88 %, 32510 MiB, 8561 MiB, 23949 MiB
2022/04/27 10:46:25.926, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 82 %, 32510 MiB, 8604 MiB, 23906 MiB
timestamp, name, driver_version, utilization.gpu [%], utilization.memory [%], memory.total [MiB], memory.free [MiB], memory.used [MiB]
2022/04/27 10:46:25.930, Tesla V100-SXM2-32GB, 470.57.02, 98 %, 80 %, 32510 MiB, 8744 MiB, 23766 MiB
2022/04/27 10:46:25.931, Tesla V100-SXM2-32GB, 470.57.02, 98 %, 80 %, 32510 MiB, 8744 MiB, 23766 MiB
timestamp, name, driver_version, utilization.gpu [%], utilization.memory [%], memory.total [MiB], memory.free [MiB], memory.used [MiB]
2022/04/27 10:46:25.932, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 62 %, 32510 MiB, 8570 MiB, 23940 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 10:46:25.935, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 88 %, 32510 MiB, 8561 MiB, 23949 MiB
2022/04/27 10:46:25.937, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 64 %, 32510 MiB, 8676 MiB, 23834 MiB
2022/04/27 10:46:25.937, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 64 %, 32510 MiB, 8676 MiB, 23834 MiB
2022/04/27 10:46:25.939, Tesla V100-SXM2-32GB, 470.57.02, 98 %, 80 %, 32510 MiB, 8744 MiB, 23766 MiB
2022/04/27 10:46:25.938, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 88 %, 32510 MiB, 8561 MiB, 23949 MiB
2022/04/27 10:46:25.939, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 88 %, 32510 MiB, 8561 MiB, 23949 MiB
2022/04/27 10:46:25.940, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 88 %, 32510 MiB, 8561 MiB, 23949 MiB
2022/04/27 10:46:25.942, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 62 %, 32510 MiB, 8570 MiB, 23940 MiB
2022/04/27 10:46:25.944, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 78 %, 32510 MiB, 8692 MiB, 23818 MiB
2022/04/27 10:46:25.945, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 78 %, 32510 MiB, 8692 MiB, 23818 MiB
2022/04/27 10:46:25.947, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 64 %, 32510 MiB, 8676 MiB, 23834 MiB
2022/04/27 10:46:25.947, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 62 %, 32510 MiB, 8570 MiB, 23940 MiB
2022/04/27 10:46:25.949, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 83 %, 32510 MiB, 8570 MiB, 23940 MiB
2022/04/27 10:46:25.949, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 83 %, 32510 MiB, 8570 MiB, 23940 MiB
2022/04/27 10:46:25.951, Tesla V100-SXM2-32GB, 470.57.02, 98 %, 80 %, 32510 MiB, 8744 MiB, 23766 MiB
2022/04/27 10:46:25.957, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 74 %, 32510 MiB, 8556 MiB, 23954 MiB
2022/04/27 10:46:25.958, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 74 %, 32510 MiB, 8556 MiB, 23954 MiB
2022/04/27 10:46:25.959, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 77 %, 32510 MiB, 8692 MiB, 23818 MiB
2022/04/27 10:46:25.960, Tesla V100-SXM2-32GB, 470.57.02, 98 %, 79 %, 32510 MiB, 8744 MiB, 23766 MiB
2022/04/27 10:46:25.961, Tesla V100-SXM2-32GB, 470.57.02, 98 %, 79 %, 32510 MiB, 8744 MiB, 23766 MiB
2022/04/27 10:46:25.962, Tesla V100-SXM2-32GB, 470.57.02, 98 %, 79 %, 32510 MiB, 8744 MiB, 23766 MiB
2022/04/27 10:46:25.963, Tesla V100-SXM2-32GB, 470.57.02, 98 %, 79 %, 32510 MiB, 8676 MiB, 23834 MiB
2022/04/27 10:46:25.978, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 81 %, 32510 MiB, 8444 MiB, 24066 MiB
2022/04/27 10:46:25.979, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 81 %, 32510 MiB, 8444 MiB, 24066 MiB
2022/04/27 10:46:25.980, Tesla V100-SXM2-32GB, 470.57.02, 98 %, 66 %, 32510 MiB, 8556 MiB, 23954 MiB
2022/04/27 10:46:25.984, Tesla V100-SXM2-32GB, 470.57.02, 98 %, 79 %, 32510 MiB, 8676 MiB, 23834 MiB
2022/04/27 10:46:25.986, Tesla V100-SXM2-32GB, 470.57.02, 98 %, 79 %, 32510 MiB, 8676 MiB, 23834 MiB
2022/04/27 10:46:25.993, Tesla V100-SXM2-32GB, 470.57.02, 98 %, 79 %, 32510 MiB, 8676 MiB, 23834 MiB
2022/04/27 10:46:26.011, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 66 %, 32510 MiB, 8692 MiB, 23818 MiB
2022/04/27 10:46:26.016, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 80 %, 32510 MiB, 8604 MiB, 23906 MiB
2022/04/27 10:46:26.017, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 67 %, 32510 MiB, 8604 MiB, 23906 MiB
2022/04/27 10:46:26.018, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 81 %, 32510 MiB, 8444 MiB, 24066 MiB
2022/04/27 10:46:26.019, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 66 %, 32510 MiB, 8692 MiB, 23818 MiB
2022/04/27 10:46:26.020, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 66 %, 32510 MiB, 8692 MiB, 23818 MiB
2022/04/27 10:46:26.021, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 66 %, 32510 MiB, 8692 MiB, 23818 MiB
2022/04/27 10:46:26.022, Tesla V100-SXM2-32GB, 470.57.02, 98 %, 66 %, 32510 MiB, 8556 MiB, 23954 MiB
2022/04/27 10:46:26.037, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 67 %, 32510 MiB, 8604 MiB, 23906 MiB
2022/04/27 10:46:26.038, Tesla V100-SXM2-32GB, 470.57.02, 98 %, 66 %, 32510 MiB, 8556 MiB, 23954 MiB
2022/04/27 10:46:26.039, Tesla V100-SXM2-32GB, 470.57.02, 98 %, 66 %, 32510 MiB, 8556 MiB, 23954 MiB
2022/04/27 10:46:26.039, Tesla V100-SXM2-32GB, 470.57.02, 98 %, 66 %, 32510 MiB, 8556 MiB, 23954 MiB
2022/04/27 10:46:26.041, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 67 %, 32510 MiB, 8444 MiB, 24066 MiB
2022/04/27 10:46:26.044, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 67 %, 32510 MiB, 8444 MiB, 24066 MiB
2022/04/27 10:46:26.048, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 67 %, 32510 MiB, 8444 MiB, 24066 MiB
2022/04/27 10:46:26.048, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 67 %, 32510 MiB, 8444 MiB, 24066 MiB
2022/04/27 10:46:26.051, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 67 %, 32510 MiB, 8604 MiB, 23906 MiB
2022/04/27 10:46:26.056, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 67 %, 32510 MiB, 8604 MiB, 23906 MiB
2022/04/27 10:46:26.057, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 67 %, 32510 MiB, 8604 MiB, 23906 MiB
2022/04/27 10:46:26.060, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 67 %, 32510 MiB, 8604 MiB, 23906 MiB
[rank:1] [train], epoch: 0/1, iter: 200/312, loss: 0.86767, top1: 0.00107, throughput: 1340.40 | 2022-04-27 10:47:03.792
[rank:2] [train], epoch: 0/1, iter: 200/312, loss: 0.86776, top1: 0.00117, throughput: 1340.52 | 2022-04-27 10:47:03.791
[rank:5] [train], epoch: 0/1, iter: 200/312, loss: 0.86796, top1: 0.00088, throughput: 1340.44 | 2022-04-27 10:47:03.794
[rank:7] [train], epoch: 0/1, iter: 200/312, loss: 0.86805, top1: 0.00100, throughput: 1340.49 | 2022-04-27 10:47:03.793
[rank:0] [train], epoch: 0/1, iter: 200/312, loss: 0.86789, top1: 0.00115, throughput: 1340.34 | 2022-04-27 10:47:03.794
[rank:3] [train], epoch: 0/1, iter: 200/312, loss: 0.86790, top1: 0.00109, throughput: 1340.43[rank:6] [train], epoch: 0/1, iter: 200/312, loss: 0.86794, top1: 0.00104, throughput: 1340.40 | 2022-04-27 10:47:03.795
 | 2022-04-27 10:47:03.794
[rank:4] [train], epoch: 0/1, iter: 200/312, loss: 0.86785, top1: 0.00105, throughput: 1340.42 | 2022-04-27 10:47:03.796
[rank:0] [train], epoch: 0/1, iter: 300/312, loss: 0.86788, top1: 0.00104, throughput: 1346.24 | 2022-04-27 10:47:41.826
[rank:1] [train], epoch: 0/1, iter: 300/312, loss: 0.86811, top1: 0.00111, throughput: 1346.14 | 2022-04-27 10:47:41.827
[rank:7] [train], epoch: 0/1, iter: 300/312, loss: 0.86796, top1: 0.00113, throughput: 1346.16 | 2022-04-27 10:47:41.827
[rank:5] [train], epoch: 0/1, iter: 300/312, loss: 0.86787, top1: 0.00102, throughput: 1346.21 | 2022-04-27 10:47:41.827
[rank:3] [train], epoch: 0/1, iter: 300/312, loss: 0.86779, top1: 0.00115, throughput: 1346.16 | 2022-04-27 10:47:41.828
[rank:2] [train], epoch: 0/1, iter: 300/312, loss: 0.86798, top1: 0.00113, throughput: 1346.03 | 2022-04-27 10:47:41.829
[rank:6] [train], epoch: 0/1, iter: 300/312, loss: 0.86807, top1: 0.00098, throughput: 1346.15 | 2022-04-27 10:47:41.829
[rank:4] [train], epoch: 0/1, iter: 300/312, loss: 0.86788, top1: 0.00104, throughput: 1346.17 | 2022-04-27 10:47:41.829