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: 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/usr/lib/x86_64-linux-gnu/libibverbs.so.1

/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

------------------------ 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: 2.66348 s *****
[rank:7] [train], epoch: 0/1, iter: 100/625, loss: 0.86770, top1: 0.00094, throughput: 259.64 | 2022-04-15 11:54:16.118
[rank:5] [train], epoch: 0/1, iter: 100/625, loss: 0.86767, top1: 0.00098, throughput: 259.74 | 2022-04-15 11:54:16.119
[rank:4] [train], epoch: 0/1, iter: 100/625, loss: 0.86772, top1: 0.00070, throughput: 259.71 | 2022-04-15 11:54:16.121[rank:6] [train], epoch: 0/1, iter: 100/625, loss: 0.86802, top1: 0.00117, throughput: 259.58
 | 2022-04-15 11:54:16.120
[rank:3] [train], epoch: 0/1, iter: 100/625, loss: 0.86775, top1: 0.00129, throughput: 259.67 | 2022-04-15 11:54:16.127
[rank:2] [train], epoch: 0/1, iter: 100/625, loss: 0.86748, top1: 0.00070, throughput: 259.55 | 2022-04-15 11:54:16.123
[rank:0] [train], epoch: 0/1, iter: 100/625, loss: 0.86728, top1: 0.00102, throughput: 259.62 | 2022-04-15 11:54:16.125
[rank:1] [train], epoch: 0/1, iter: 100/625, loss: 0.86757, top1: 0.00082, throughput: 259.54 | 2022-04-15 11:54:16.125
timestamp, name, driver_version, utilization.gpu [%], utilization.memory [%], memory.total [MiB], memory.free [MiB], memory.used [MiB]
2022/04/15 11:54:16.412, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 58 %, 32510 MiB, 7745 MiB, 24765 MiB
2022/04/15 11:54:16.419, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 58 %, 32510 MiB, 7734 MiB, 24776 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]
2022/04/15 11:54:16.430, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 60 %, 32510 MiB, 7852 MiB, 24658 MiB
2022/04/15 11:54:16.432, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 58 %, 32510 MiB, 7745 MiB, 24765 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]
2022/04/15 11:54:16.434, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 58 %, 32510 MiB, 7745 MiB, 24765 MiB
2022/04/15 11:54:16.435, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 58 %, 32510 MiB, 7846 MiB, 24664 MiB
2022/04/15 11:54:16.438, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 58 %, 32510 MiB, 7734 MiB, 24776 MiB
2022/04/15 11:54:16.440, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 58 %, 32510 MiB, 7745 MiB, 24765 MiB
2022/04/15 11:54:16.441, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 58 %, 32510 MiB, 7745 MiB, 24765 MiB
2022/04/15 11:54:16.444, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 58 %, 32510 MiB, 7734 MiB, 24776 MiB
2022/04/15 11:54:16.442, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 58 %, 32510 MiB, 7745 MiB, 24765 MiB
timestamp, name, driver_version, utilization.gpu [%], utilization.memory [%], memory.total [MiB], memory.free [MiB], memory.used [MiB]
2022/04/15 11:54:16.445, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 64 %, 32510 MiB, 7894 MiB, 24616 MiB
timestamp, name, driver_version, utilization.gpu [%], utilization.memory [%], memory.total [MiB], memory.free [MiB], memory.used [MiB]
2022/04/15 11:54:16.449, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 60 %, 32510 MiB, 7852 MiB, 24658 MiB
2022/04/15 11:54:16.450, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 58 %, 32510 MiB, 7734 MiB, 24776 MiB
2022/04/15 11:54:16.451, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 58 %, 32510 MiB, 7734 MiB, 24776 MiB
2022/04/15 11:54:16.452, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 60 %, 32510 MiB, 7852 MiB, 24658 MiB
2022/04/15 11:54:16.452, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 58 %, 32510 MiB, 7734 MiB, 24776 MiB
2022/04/15 11:54:16.453, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 59 %, 32510 MiB, 7752 MiB, 24758 MiB
2022/04/15 11:54:16.452, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 58 %, 32510 MiB, 7745 MiB, 24765 MiB
2022/04/15 11:54:16.454, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 58 %, 32510 MiB, 7745 MiB, 24765 MiB
2022/04/15 11:54:16.457, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 58 %, 32510 MiB, 7846 MiB, 24664 MiB
2022/04/15 11:54:16.459, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 60 %, 32510 MiB, 7852 MiB, 24658 MiB
2022/04/15 11:54:16.461, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 60 %, 32510 MiB, 7852 MiB, 24658 MiB
2022/04/15 11:54:16.462, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 58 %, 32510 MiB, 7846 MiB, 24664 MiB
2022/04/15 11:54:16.463, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 60 %, 32510 MiB, 7852 MiB, 24658 MiB
2022/04/15 11:54:16.465, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 62 %, 32510 MiB, 7636 MiB, 24874 MiB
2022/04/15 11:54:16.465, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 58 %, 32510 MiB, 7734 MiB, 24776 MiB
2022/04/15 11:54:16.467, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 58 %, 32510 MiB, 7734 MiB, 24776 MiB
2022/04/15 11:54:16.469, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 64 %, 32510 MiB, 7894 MiB, 24616 MiB
2022/04/15 11:54:16.471, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 58 %, 32510 MiB, 7846 MiB, 24664 MiB
2022/04/15 11:54:16.472, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 58 %, 32510 MiB, 7846 MiB, 24664 MiB
2022/04/15 11:54:16.473, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 64 %, 32510 MiB, 7894 MiB, 24616 MiB
2022/04/15 11:54:16.473, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 58 %, 32510 MiB, 7846 MiB, 24664 MiB
2022/04/15 11:54:16.474, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 60 %, 32510 MiB, 7780 MiB, 24730 MiB
2022/04/15 11:54:16.475, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 60 %, 32510 MiB, 7852 MiB, 24658 MiB
2022/04/15 11:54:16.476, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 60 %, 32510 MiB, 7852 MiB, 24658 MiB
2022/04/15 11:54:16.479, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 64 %, 32510 MiB, 7752 MiB, 24758 MiB
2022/04/15 11:54:16.484, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 64 %, 32510 MiB, 7894 MiB, 24616 MiB
2022/04/15 11:54:16.485, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 64 %, 32510 MiB, 7894 MiB, 24616 MiB
2022/04/15 11:54:16.486, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 64 %, 32510 MiB, 7752 MiB, 24758 MiB
2022/04/15 11:54:16.487, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 64 %, 32510 MiB, 7894 MiB, 24616 MiB
2022/04/15 11:54:16.488, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 58 %, 32510 MiB, 7846 MiB, 24664 MiB
2022/04/15 11:54:16.489, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 58 %, 32510 MiB, 7846 MiB, 24664 MiB
2022/04/15 11:54:16.492, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 62 %, 32510 MiB, 7636 MiB, 24874 MiB
2022/04/15 11:54:16.498, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 64 %, 32510 MiB, 7752 MiB, 24758 MiB
2022/04/15 11:54:16.499, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 64 %, 32510 MiB, 7752 MiB, 24758 MiB
2022/04/15 11:54:16.500, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 62 %, 32510 MiB, 7636 MiB, 24874 MiB
2022/04/15 11:54:16.500, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 64 %, 32510 MiB, 7752 MiB, 24758 MiB
2022/04/15 11:54:16.501, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 64 %, 32510 MiB, 7894 MiB, 24616 MiB
2022/04/15 11:54:16.503, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 64 %, 32510 MiB, 7894 MiB, 24616 MiB
2022/04/15 11:54:16.505, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 60 %, 32510 MiB, 7780 MiB, 24730 MiB
2022/04/15 11:54:16.507, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 62 %, 32510 MiB, 7636 MiB, 24874 MiB
2022/04/15 11:54:16.507, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 62 %, 32510 MiB, 7636 MiB, 24874 MiB
2022/04/15 11:54:16.508, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 60 %, 32510 MiB, 7780 MiB, 24730 MiB
2022/04/15 11:54:16.508, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 62 %, 32510 MiB, 7636 MiB, 24874 MiB
2022/04/15 11:54:16.509, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 64 %, 32510 MiB, 7752 MiB, 24758 MiB
2022/04/15 11:54:16.510, Tesla V100-SXM2-32GB, 470.57.02, 100 %, 64 %, 32510 MiB, 7752 MiB, 24758 MiB
2022/04/15 11:54:16.514, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 60 %, 32510 MiB, 7780 MiB, 24730 MiB
2022/04/15 11:54:16.515, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 60 %, 32510 MiB, 7780 MiB, 24730 MiB
2022/04/15 11:54:16.516, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 60 %, 32510 MiB, 7780 MiB, 24730 MiB
2022/04/15 11:54:16.517, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 62 %, 32510 MiB, 7636 MiB, 24874 MiB
2022/04/15 11:54:16.518, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 62 %, 32510 MiB, 7636 MiB, 24874 MiB
2022/04/15 11:54:16.532, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 60 %, 32510 MiB, 7780 MiB, 24730 MiB
2022/04/15 11:54:16.534, Tesla V100-SXM2-32GB, 470.57.02, 99 %, 60 %, 32510 MiB, 7780 MiB, 24730 MiB
[rank:5] [train], epoch: 0/1, iter: 200/625, loss: 0.86753, top1: 0.00043, throughput: 375.89 | 2022-04-15 11:55:24.224
[rank:4] [train], epoch: 0/1, iter: 200/625, loss: 0.86772, top1: 0.00078, throughput: 375.90 | 2022-04-15 11:55:24.224
[rank:3] [train], epoch: 0/1, iter: 200/625, loss: 0.86753, top1: 0.00090, throughput: 375.90 | 2022-04-15 11:55:24.230
[rank:0] [train], epoch: 0/1, iter: 200/625, loss: 0.86743, top1: 0.00094, throughput: 375.90 | 2022-04-15 11:55:24.227
[rank:6] [train], epoch: 0/1, iter: 200/625, loss: 0.86739, top1: 0.00074, throughput: 375.90 | 2022-04-15 11:55:24.224
[rank:1] [train], epoch: 0/1, iter: 200/625, loss: 0.86761, top1: 0.00082, throughput: 375.90 | 2022-04-15 11:55:24.228
[rank:2] [train], epoch: 0/1, iter: 200/625, loss: 0.86709, top1: 0.00098, throughput: 375.91 | 2022-04-15 11:55:24.225
[rank:7] [train], epoch: 0/1, iter: 200/625, loss: 0.86767, top1: 0.00070, throughput: 375.86 | 2022-04-15 11:55:24.228
[rank:6] [train], epoch: 0/1, iter: 300/625, loss: 0.86729, top1: 0.00066, throughput: 376.44 | 2022-04-15 11:56:32.229
[rank:2] [train], epoch: 0/1, iter: 300/625, loss: 0.86733, top1: 0.00055, throughput: 376.44 | 2022-04-15 11:56:32.231
[rank:4] [train], epoch: 0/1, iter: 300/625, loss: 0.86745, top1: 0.00082, throughput: 376.43 | 2022-04-15 11:56:32.230
[rank:0] [train], epoch: 0/1, iter: 300/625, loss: 0.86759, top1: 0.00105, throughput: 376.43 | 2022-04-15 11:56:32.234
[rank:5] [train], epoch: 0/1, iter: 300/625, loss: 0.86741, top1: 0.00109, throughput: 376.44 | 2022-04-15 11:56:32.230
[rank:7] [train], epoch: 0/1, iter: 300/625, loss: 0.86738, top1: 0.00043, throughput: 376.44 | 2022-04-15 11:56:32.234
[rank:1] [train], epoch: 0/1, iter: 300/625, loss: 0.86763, top1: 0.00090, throughput: 376.43 | 2022-04-15 11:56:32.236
[rank:3] [train], epoch: 0/1, iter: 300/625, loss: 0.86754, top1: 0.00059, throughput: 376.43 | 2022-04-15 11:56:32.236